2710 files changed, 76651 insertions, 37850 deletions

diff --git a/.mailmap b/.mailmap
index 42e42cabb36d..ae0adc499f4a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -142,13 +142,17 @@ Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com>
 Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com>
 Brendan Higgins <brendan.higgins@linux.dev> <brendanhiggins@google.com>
 Brian Avery <b.avery@hp.com>
+Brian Cain <bcain@kernel.org> <brian.cain@oss.qualcomm.com>
+Brian Cain <bcain@kernel.org> <bcain@quicinc.com>
 Brian King <brking@us.ibm.com>
 Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com>
 Bryan Tan <bryan-bt.tan@broadcom.com> <bryantan@vmware.com>
 Cai Huoqing <cai.huoqing@linux.dev> <caihuoqing@baidu.com>
 Can Guo <quic_cang@quicinc.com> <cang@codeaurora.org>
 Carl Huang <quic_cjhuang@quicinc.com> <cjhuang@codeaurora.org>
-Carlos Bilbao <carlos.bilbao.osdev@gmail.com> <carlos.bilbao@amd.com>
+Carlos Bilbao <carlos.bilbao@kernel.org> <carlos.bilbao@amd.com>
+Carlos Bilbao <carlos.bilbao@kernel.org> <carlos.bilbao.osdev@gmail.com>
+Carlos Bilbao <carlos.bilbao@kernel.org> <bilbao@vt.edu>
 Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
 Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
 Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
@@ -165,6 +169,7 @@ Christian Brauner <brauner@kernel.org> <christian.brauner@canonical.com>
 Christian Brauner <brauner@kernel.org> <christian.brauner@ubuntu.com>
 Christian Marangi <ansuelsmth@gmail.com>
 Christophe Ricard <christophe.ricard@gmail.com>
+Christopher Obbard <christopher.obbard@linaro.org> <chris.obbard@collabora.com>
 Christoph Hellwig <hch@lst.de>
 Chuck Lever <chuck.lever@oracle.com> <cel@kernel.org>
 Chuck Lever <chuck.lever@oracle.com> <cel@netapp.com>
@@ -261,6 +266,7 @@ Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com>
 Guru Das Srinagesh <quic_gurus@quicinc.com> <gurus@codeaurora.org>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
 Gustavo Padovan <padovan@profusion.mobi>
+Hamza Mahfooz <hamzamahfooz@linux.microsoft.com> <hamza.mahfooz@amd.com>
 Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
 Hans Verkuil <hverkuil@xs4all.nl> <hansverk@cisco.com>
 Hans Verkuil <hverkuil@xs4all.nl> <hverkuil-cisco@xs4all.nl>
@@ -415,6 +421,7 @@ Liam Mark <quic_lmark@quicinc.com> <lmark@codeaurora.org>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
+Linus Lüssing <linus.luessing@c0d3.blue> <ll@simonwunderlich.de>
 <linux-hardening@vger.kernel.org> <kernel-hardening@lists.openwall.com>
 Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
 Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
@@ -760,6 +767,7 @@ Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de>
 Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn>
 Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com>
+Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
 Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com>
diff --git a/CREDITS b/CREDITS
index cda68f04d5f1..53d11a46fd69 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2515,11 +2515,9 @@ D: SLS distribution
 D: Initial implementation of VC's, pty's and select()
 
 N: Pavel Machek
-E: pavel@ucw.cz
+E: pavel@kernel.org
 P: 4096R/92DFCE96 4FA7 9EEF FCD4 C44F C585  B8C7 C060 2241 92DF CE96
-D: Softcursor for vga, hypertech cdrom support, vcsa bugfix, nbd,
-D: sun4/330 port, capabilities for elf, speedup for rm on ext2, USB,
-D: work on suspend-to-ram/disk, killing duplicates from ioctl32,
+D: NBD, Sun4/330 port, USB, work on suspend-to-ram/disk,
 D: Altera SoCFPGA and Nokia N900 support.
 S: Czech Republic
 
@@ -4339,7 +4337,7 @@ D: Freescale Highspeed USB device driver
 D: Freescale QE SoC support and Ethernet driver
 S: B-1206 Jingmao Guojigongyu
 S: 16 Baliqiao Nanjie, Beijing 101100
-S: People's Repulic of China
+S: People's Republic of China
 
 N: Vlad Yasevich
 E: vyasevich@gmail.com
diff --git a/Documentation/ABI/stable/sysfs-class-bluetooth b/Documentation/ABI/stable/sysfs-class-bluetooth
new file mode 100644
index 000000000000..36be02471174
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-class-bluetooth
@@ -0,0 +1,9 @@
+What: 		/sys/class/bluetooth/hci<index>/reset
+Date:		14-Jan-2025
+KernelVersion:	6.13
+Contact:	linux-bluetooth@vger.kernel.org
+Description: 	This write-only attribute allows users to trigger the vendor reset
+		method on the Bluetooth device when arbitrary data is written.
+		The reset may or may not be done through the device transport
+		(e.g., UART/USB), and can also be done through an out-of-band
+		approach such as GPIO.
diff --git a/Documentation/ABI/testing/sysfs-bus-coresight-devices-dummy-source b/Documentation/ABI/testing/sysfs-bus-coresight-devices-dummy-source
new file mode 100644
index 000000000000..0830661ef656
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-coresight-devices-dummy-source
@@ -0,0 +1,15 @@
+What:		/sys/bus/coresight/devices/dummy_source<N>/enable_source
+Date:		Dec 2024
+KernelVersion:	6.14
+Contact:	Mao Jinlong <quic_jinlmao@quicinc.com>
+Description:	(RW) Enable/disable tracing of dummy source. A sink should be activated
+		before enabling the source. The path of coresight components linking
+		the source to the sink is configured and managed automatically by the
+		coresight framework.
+
+What:		/sys/bus/coresight/devices/dummy_source<N>/traceid
+Date:		Dec 2024
+KernelVersion:	6.14
+Contact:	Mao Jinlong <quic_jinlmao@quicinc.com>
+Description:	(R) Show the trace ID that will appear in the trace stream
+		coming from this trace entity.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index f83bd6829285..25d366d452a5 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -168,18 +168,6 @@ Description:
 		is required is a consistent labeling.  Units after application
 		of scale and offset are millivolts.
 
-What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_supply_raw
-KernelVersion:	3.17
-Contact:	linux-iio@vger.kernel.org
-Description:
-		Raw (unscaled no bias removal etc.) current measurement from
-		channel Y. In special cases where the channel does not
-		correspond to externally available input one of the named
-		versions may be used. The number must always be specified and
-		unique to allow association with event codes. Units after
-		application of scale and offset are milliamps.
-
 What:		/sys/bus/iio/devices/iio:deviceX/in_powerY_raw
 KernelVersion:	4.5
 Contact:	linux-iio@vger.kernel.org
@@ -227,7 +215,7 @@ Description:
 		same scaling as _raw.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_tempX_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_tempY_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_x_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_y_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_ambient_raw
@@ -416,11 +404,11 @@ Contact:	linux-iio@vger.kernel.org
 Description:
 		Scaled humidity measurement in milli percent.
 
-What:		/sys/bus/iio/devices/iio:deviceX/in_X_mean_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_Y_mean_raw
 KernelVersion:	3.5
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Averaged raw measurement from channel X. The number of values
+		Averaged raw measurement from channel Y. The number of values
 		used for averaging is device specific. The converting rules for
 		normal raw values also applies to the averaged raw values.
 
@@ -448,7 +436,7 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_humidityrelative_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_magn_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_rot_offset
 What:		/sys/bus/iio/devices/iio:deviceX/in_angl_offset
-What:		/sys/bus/iio/devices/iio:deviceX/in_capacitanceX_offset
+What:		/sys/bus/iio/devices/iio:deviceX/in_capacitanceY_offset
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -508,6 +496,9 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_angl_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_x_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_y_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_z_scale
+What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_red_scale
+What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_green_scale
+What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_blue_scale
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_co2_scale
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
@@ -660,10 +651,10 @@ What:		/sys/.../iio:deviceX/in_magn_scale_available
 What:		/sys/.../iio:deviceX/in_illuminance_scale_available
 What:		/sys/.../iio:deviceX/in_intensity_scale_available
 What:		/sys/.../iio:deviceX/in_proximity_scale_available
-What:		/sys/.../iio:deviceX/in_voltageX_scale_available
+What:		/sys/.../iio:deviceX/in_voltageY_scale_available
 What:		/sys/.../iio:deviceX/in_voltage-voltage_scale_available
-What:		/sys/.../iio:deviceX/out_voltageX_scale_available
-What:		/sys/.../iio:deviceX/out_altvoltageX_scale_available
+What:		/sys/.../iio:deviceX/out_voltageY_scale_available
+What:		/sys/.../iio:deviceX/out_altvoltageY_scale_available
 What:		/sys/.../iio:deviceX/in_capacitance_scale_available
 What:		/sys/.../iio:deviceX/in_pressure_scale_available
 What:		/sys/.../iio:deviceX/in_pressureY_scale_available
@@ -681,6 +672,7 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_red_hardwaregain
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_green_hardwaregain
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_blue_hardwaregain
 What:		/sys/bus/iio/devices/iio:deviceX/in_intensity_clear_hardwaregain
+What:		/sys/bus/iio/devices/iio:deviceX/in_illuminance_hardwaregain
 KernelVersion:	2.6.35
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -1562,7 +1554,7 @@ Description:
 		This attribute is used to read the amount of quadrature error
 		present in the device at a given time.
 
-What:		/sys/.../iio:deviceX/in_accelX_power_mode
+What:		/sys/.../iio:deviceX/in_accelY_power_mode
 KernelVersion:	3.11
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -1633,6 +1625,10 @@ What:		/sys/.../iio:deviceX/in_intensityY_uv_raw
 What:		/sys/.../iio:deviceX/in_intensityY_uva_raw
 What:		/sys/.../iio:deviceX/in_intensityY_uvb_raw
 What:		/sys/.../iio:deviceX/in_intensityY_duv_raw
+What:		/sys/.../iio:deviceX/in_intensity_red_raw
+What:		/sys/.../iio:deviceX/in_intensity_green_raw
+What:		/sys/.../iio:deviceX/in_intensity_blue_raw
+What:		/sys/.../iio:deviceX/in_intensity_clear_raw
 KernelVersion:	3.4
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -1691,16 +1687,19 @@ Description:
 		Raw value of rotation from true/magnetic north measured with
 		or without compensation from tilt sensors.
 
-What:		/sys/bus/iio/devices/iio:deviceX/in_currentX_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_currentX_i_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_currentX_q_raw
-KernelVersion:	3.18
+What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_supply_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_i_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_q_raw
+KernelVersion:	3.17
 Contact:	linux-iio@vger.kernel.org
 Description:
-		Raw current measurement from channel X. Units are in milliamps
+		Raw current measurement from channel Y. Units are in milliamps
 		after application of scale and offset. If no offset or scale is
 		present, output should be considered as processed with the
-		unit in milliamps.
+		unit in milliamps. In special cases where the channel does not
+		correspond to externally available input one of the named
+		versions may be used.
 
 		Channels with 'i' and 'q' modifiers always exist in pairs and both
 		channels refer to the same signal. The 'i' channel contains the in-phase
@@ -1864,9 +1863,9 @@ Description:
 		hardware fifo watermark level.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_calibemissivity
-What:		/sys/bus/iio/devices/iio:deviceX/in_tempX_calibemissivity
+What:		/sys/bus/iio/devices/iio:deviceX/in_tempY_calibemissivity
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_object_calibemissivity
-What:		/sys/bus/iio/devices/iio:deviceX/in_tempX_object_calibemissivity
+What:		/sys/bus/iio/devices/iio:deviceX/in_tempY_object_calibemissivity
 KernelVersion:	4.1
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -1887,17 +1886,17 @@ Description:
 		is considered as one sample for <type>[_name]_sampling_frequency.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationY_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_co2_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_co2_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationY_co2_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_ethanol_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_ethanol_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationY_ethanol_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_h2_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_h2_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationY_h2_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_o2_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_o2_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationY_o2_raw
 What:		/sys/bus/iio/devices/iio:deviceX/in_concentration_voc_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_concentrationY_voc_raw
 KernelVersion:	4.3
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -1905,9 +1904,9 @@ Description:
 		after application of scale and offset are percents.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_resistance_raw
-What:		/sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw
+What:		/sys/bus/iio/devices/iio:deviceX/in_resistanceY_raw
 What:		/sys/bus/iio/devices/iio:deviceX/out_resistance_raw
-What:		/sys/bus/iio/devices/iio:deviceX/out_resistanceX_raw
+What:		/sys/bus/iio/devices/iio:deviceX/out_resistanceY_raw
 KernelVersion:	4.3
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -2096,7 +2095,7 @@ Description:
 		One of the following thermocouple types: B, E, J, K, N, R, S, T.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_temp_object_calibambient
-What:		/sys/bus/iio/devices/iio:deviceX/in_tempX_object_calibambient
+What:		/sys/bus/iio/devices/iio:deviceX/in_tempY_object_calibambient
 KernelVersion:	5.10
 Contact:	linux-iio@vger.kernel.org
 Description:
@@ -2172,9 +2171,9 @@ Description:
 
 		- a range specified as "[min step max]"
 
-What:		/sys/bus/iio/devices/iio:deviceX/in_voltageX_sampling_frequency
+What:		/sys/bus/iio/devices/iio:deviceX/in_voltageY_sampling_frequency
 What:		/sys/bus/iio/devices/iio:deviceX/in_powerY_sampling_frequency
-What:		/sys/bus/iio/devices/iio:deviceX/in_currentZ_sampling_frequency
+What:		/sys/bus/iio/devices/iio:deviceX/in_currentY_sampling_frequency
 KernelVersion:	5.20
 Contact:	linux-iio@vger.kernel.org
 Description:
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-ad-sigma-delta b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad-sigma-delta
new file mode 100644
index 000000000000..a5a8a579f4f3
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad-sigma-delta
@@ -0,0 +1,23 @@
+What:		/sys/bus/iio/devices/iio:deviceX/in_voltageY_sys_calibration
+KernelVersion: 5.5
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This attribute, if available, initiates the system calibration procedure. This is done on a
+		single channel at a time. Write '1' to start the calibration.
+
+What:		/sys/bus/iio/devices/iio:deviceX/in_voltageY_sys_calibration_mode_available
+KernelVersion: 5.5
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This attribute, if available, returns a list with the possible calibration modes.
+		There are two available options:
+		"zero_scale" - calibrate to zero scale
+		"full_scale" - calibrate to full scale
+
+What:		/sys/bus/iio/devices/iio:deviceX/in_voltageY_sys_calibration_mode
+KernelVersion: 5.5
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This attribute, if available, sets up the calibration mode used in the system calibration
+		procedure. Reading returns the current calibration mode.
+		Writing sets the system calibration mode.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192 b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192
index f8315202c8f0..28be1cabf112 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192
+++ b/Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192
@@ -19,33 +19,9 @@ Description:
 		the bridge can be disconnected (when it is not being used
 		using the bridge_switch_en attribute.
 
-What:		/sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration
-KernelVersion:
-Contact:	linux-iio@vger.kernel.org
-Description:
-		Initiates the system calibration procedure. This is done on a
-		single channel at a time. Write '1' to start the calibration.
-
 What:		/sys/bus/iio/devices/iio:deviceX/in_voltage2-voltage2_shorted_raw
 KernelVersion:
 Contact:	linux-iio@vger.kernel.org
 Description:
 		Measure voltage from AIN2 pin connected to AIN(+)
 		and AIN(-) shorted.
-
-What:		/sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration_mode_available
-KernelVersion:
-Contact:	linux-iio@vger.kernel.org
-Description:
-		Reading returns a list with the possible calibration modes.
-		There are two available options:
-		"zero_scale" - calibrate to zero scale
-		"full_scale" - calibrate to full scale
-
-What:		/sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration_mode
-KernelVersion:
-Contact:	linux-iio@vger.kernel.org
-Description:
-		Sets up the calibration mode used in the system calibration
-		procedure. Reading returns the current calibration mode.
-		Writing sets the system calibration mode.
diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index 45180b62d426..2a5c1a09a28f 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -407,10 +407,30 @@ Description:
 
 		Access: Read, Write
 
+		Reading this returns the current active value, e.g. 'Standard'.
+		Check charge_types to get the values supported by the battery.
+
 		Valid values:
 			      "Unknown", "N/A", "Trickle", "Fast", "Standard",
 			      "Adaptive", "Custom", "Long Life", "Bypass"
 
+What:		/sys/class/power_supply/<supply_name>/charge_types
+Date:		December 2024
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Identical to charge_type but reading returns a list of supported
+		charge-types with the currently active type surrounded by square
+		brackets, e.g.: "Fast [Standard] Long_Life".
+
+		power_supply class devices may support both charge_type and
+		charge_types for backward compatibility. In this case both will
+		always have the same active value and the active value can be
+		changed by writing either property.
+
+		Note charge-types which contain a space such as "Long Life" will
+		have the space replaced by a '_' resulting in e.g. "Long_Life".
+		When writing charge-types both variants are accepted.
+
 What:		/sys/class/power_supply/<supply_name>/charge_term_current
 Date:		July 2014
 Contact:	linux-pm@vger.kernel.org
@@ -433,7 +453,7 @@ Description:
 
 		Valid values:
 			      "Unknown", "Good", "Overheat", "Dead",
-			      "Over voltage", "Unspecified failure", "Cold",
+			      "Over voltage", "Under voltage", "Unspecified failure", "Cold",
 			      "Watchdog timer expire", "Safety timer expire",
 			      "Over current", "Calibration required", "Warm",
 			      "Cool", "Hot", "No battery"
@@ -793,3 +813,12 @@ Description:
 
 		Access: Read
 		Valid values: 1-31
+
+What:		/sys/class/power_supply/<supply_name>/extensions/<extension_name>
+Date:		March 2025
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Reports the extensions registered to the power supply.
+		Each entry is a link to the device which registered the extension.
+
+		Access: Read
diff --git a/Documentation/ABI/testing/sysfs-class-power-max1720x b/Documentation/ABI/testing/sysfs-class-power-max1720x
new file mode 100644
index 000000000000..7d895bfda9ce
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-power-max1720x
@@ -0,0 +1,32 @@
+What:		/sys/class/power_supply/max1720x/temp_ain1
+Date:		January 2025
+KernelVersion:	6.14
+Contact:	Dimitri Fedrau <dimitri.fedrau@liebherr.com>
+Description:
+		Reports the current temperature reading from AIN1 thermistor.
+
+		Access: Read
+
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/max1720x/temp_ain2
+Date:		January 2025
+KernelVersion:	6.14
+Contact:	Dimitri Fedrau <dimitri.fedrau@liebherr.com>
+Description:
+		Reports the current temperature reading from AIN2 thermistor.
+
+		Access: Read
+
+		Valid values: Represented in 1/10 Degrees Celsius
+
+What:		/sys/class/power_supply/max1720x/temp_int
+Date:		January 2025
+KernelVersion:	6.14
+Contact:	Dimitri Fedrau <dimitri.fedrau@liebherr.com>
+Description:
+		Reports the current temperature reading from internal die.
+
+		Access: Read
+
+		Valid values: Represented in 1/10 Degrees Celsius
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon
index f1b90cf1249b..b057eddefbfc 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-damon
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon
@@ -355,10 +355,15 @@ Description:	If 'target' is written to the 'type' file, writing to or
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/filters/<F>/matching
 Date:		Dec 2022
 Contact:	SeongJae Park <sj@kernel.org>
-Description:	Writing 'Y' or 'N' to this file sets whether to filter out
-		pages that do or do not match to the 'type' and 'memcg_path',
-		respectively.  Filter out means the action of the scheme will
-		not be applied to.
+Description:	Writing 'Y' or 'N' to this file sets whether the filter is for
+		the memory of the 'type', or all except the 'type'.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/filters/<F>/allow
+Date:		Jan 2025
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Writing 'Y' or 'N' to this file sets whether to allow or reject
+		applying the scheme's action to the memory that satisfies the
+		'type' and the 'matching' of the directory.
 
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/nr_tried
 Date:		Mar 2022
@@ -384,6 +389,12 @@ Contact:	SeongJae Park <sj@kernel.org>
 Description:	Reading this file returns the total size of regions that the
 		action of the scheme has successfully applied in bytes.
 
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/sz_ops_filter_passed
+Date:		Dec 2024
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Reading this file returns the total size of memory that passed
+		DAMON operations layer-handled filters of the scheme in bytes.
+
 What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/stats/qt_exceeds
 Date:		Mar 2022
 Contact:	SeongJae Park <sj@kernel.org>
@@ -424,3 +435,10 @@ Contact:	SeongJae Park <sj@kernel.org>
 Description:	Reading this file returns the 'age' of a memory region that
 		corresponding DAMON-based Operation Scheme's action has tried
 		to be applied.
+
+What:		/sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/tried_regions/<R>/sz_filter_passed
+Date:		Dec 2024
+Contact:	SeongJae Park <sj@kernel.org>
+Description:	Reading this file returns the size of the memory in the region
+		that passed DAMON operations layer-handled filters of the
+		scheme in bytes.
diff --git a/Documentation/ABI/testing/sysfs-pps-gen b/Documentation/ABI/testing/sysfs-pps-gen
new file mode 100644
index 000000000000..2519207b88fd
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-pps-gen
@@ -0,0 +1,43 @@
+What:		/sys/class/pps-gen/
+Date:		February 2025
+KernelVersion:  6.13
+Contact:	Rodolfo Giometti <giometti@enneenne.com>
+Description:
+		The /sys/class/pps-gen/ directory contains files and
+		directories that provide a unified interface to the PPS
+		generators.
+
+What:		/sys/class/pps-gen/pps-genX/
+Date:		February 2025
+KernelVersion:  6.13
+Contact:	Rodolfo Giometti <giometti@enneenne.com>
+Description:
+		The /sys/class/pps-gen/pps-genX/ directory is related to X-th
+		PPS generator in the system. Each directory contain files to
+		manage and control its PPS generator.
+
+What:		/sys/class/pps-gen/pps-genX/enable
+Date:		February 2025
+KernelVersion:  6.13
+Contact:	Rodolfo Giometti <giometti@enneenne.com>
+Description:
+		This write-only file enables or disables generation of the
+		PPS signal.
+
+What:		/sys/class/pps-gen/pps-genX/system
+Date:		February 2025
+KernelVersion:  6.13
+Contact:	Rodolfo Giometti <giometti@enneenne.com>
+Description:
+		This read-only file returns "1" if the generator takes the
+		timing from the system clock, while it returns "0" if not
+		(i.e. from a peripheral device clock).
+
+What:		/sys/class/pps-gen/pps-genX/time
+Date:		February 2025
+KernelVersion:  6.13
+Contact:	Rodolfo Giometti <giometti@enneenne.com>
+Description:
+		This read-only file contains the current time stored into the
+		generator clock as two integers representing the current time
+		seconds and nanoseconds.
diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst
index f61c01fc376e..210c194d4a7b 100644
--- a/Documentation/accounting/delay-accounting.rst
+++ b/Documentation/accounting/delay-accounting.rst
@@ -100,29 +100,29 @@ Get delays, since system boot, for pid 10::
 	# ./getdelays -d -p 10
 	(output similar to next case)
 
-Get sum of delays, since system boot, for all pids with tgid 5::
+Get sum and peak of delays, since system boot, for all pids with tgid 242::
 
-	# ./getdelays -d -t 5
+	bash-4.4# ./getdelays -d -t 242
 	print delayacct stats ON
-	TGID	5
-
-
-	CPU             count     real total  virtual total    delay total  delay average
-	                    8        7000000        6872122        3382277          0.423ms
-	IO              count    delay total  delay average
-                   0              0          0.000ms
-	SWAP            count    delay total  delay average
-                       0              0          0.000ms
-	RECLAIM         count    delay total  delay average
-                   0              0          0.000ms
-	THRASHING       count    delay total  delay average
-                       0              0          0.000ms
-	COMPACT         count    delay total  delay average
-                       0              0          0.000ms
-	WPCOPY          count    delay total  delay average
-                       0              0          0.000ms
-	IRQ             count    delay total  delay average
-                       0              0          0.000ms
+	TGID    242
+
+
+	CPU         count     real total  virtual total    delay total  delay average      delay max      delay min
+	               39      156000000      156576579        2111069          0.054ms     0.212296ms     0.031307ms
+	IO          count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	SWAP        count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	RECLAIM     count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	THRASHING   count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	COMPACT     count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
+	WPCOPY      count    delay total  delay average      delay max      delay min
+	              156       11215873          0.072ms     0.207403ms     0.033913ms
+	IRQ         count    delay total  delay average      delay max      delay min
+	                0              0          0.000ms     0.000000ms     0.000000ms
 
 Get IO accounting for pid 1, it works only with -p::
 
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f4183bb8d66e..fb8752b42ec8 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2824,17 +2824,21 @@
 			nvhe: Standard nVHE-based mode, without support for
 			      protected guests.
 
-			protected: nVHE-based mode with support for guests whose
-				   state is kept private from the host.
+			protected: Mode with support for guests whose state is
+				   kept private from the host, using VHE or
+				   nVHE depending on HW support.
 
 			nested: VHE-based mode with support for nested
-				virtualization. Requires at least ARMv8.3
-				hardware.
+				virtualization. Requires at least ARMv8.4
+				hardware (with FEAT_NV2).
 
 			Defaults to VHE/nVHE based on hardware support. Setting
 			mode to "protected" will disable kexec and hibernation
-			for the host. "nested" is experimental and should be
-			used with extreme caution.
+			for the host. To force nVHE on VHE hardware, add
+			"arm64_sw.hvhe=0 id_aa64mmfr1.vh=0" to the
+			command-line.
+			"nested" is experimental and should be used with
+			extreme caution.
 
 	kvm-arm.vgic_v3_group0_trap=
 			[KVM,ARM,EARLY] Trap guest accesses to GICv3 group-0
@@ -3495,8 +3499,8 @@
 			[KNL] Set the initial state for the memory hotplug
 			onlining policy. If not specified, the default value is
 			set according to the
-			CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
-			option.
+			CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config
+			options.
 			See Documentation/admin-guide/mm/memory-hotplug.rst.
 
 	memmap=exactmap	[KNL,X86,EARLY] Enable setting of an exact
@@ -7303,6 +7307,13 @@
 			See Documentation/admin-guide/mm/transhuge.rst
 			for more details.
 
+	transparent_hugepage_tmpfs= [KNL]
+			Format: [always|within_size|advise|never]
+			Can be used to control the default hugepage allocation policy
+			for the tmpfs mount.
+			See Documentation/admin-guide/mm/transhuge.rst
+			for more details.
+
 	trusted.source=	[KEYS]
 			Format: <string>
 			This parameter identifies the trust source as a backend
diff --git a/Documentation/admin-guide/mm/damon/start.rst b/Documentation/admin-guide/mm/damon/start.rst
index c4dddf6733cd..ede14b679d02 100644
--- a/Documentation/admin-guide/mm/damon/start.rst
+++ b/Documentation/admin-guide/mm/damon/start.rst
@@ -42,32 +42,45 @@ the execution. ::
 
     $ git clone https://github.com/sjp38/masim; cd masim; make
     $ sudo damo start "./masim ./configs/stairs.cfg --quiet"
-    $ sudo ./damo show
-    0   addr [85.541 TiB  , 85.541 TiB ) (57.707 MiB ) access 0 %   age 10.400 s
-    1   addr [85.541 TiB  , 85.542 TiB ) (413.285 MiB) access 0 %   age 11.400 s
-    2   addr [127.649 TiB , 127.649 TiB) (57.500 MiB ) access 0 %   age 1.600 s
-    3   addr [127.649 TiB , 127.649 TiB) (32.500 MiB ) access 0 %   age 500 ms
-    4   addr [127.649 TiB , 127.649 TiB) (9.535 MiB  ) access 100 % age 300 ms
-    5   addr [127.649 TiB , 127.649 TiB) (8.000 KiB  ) access 60 %  age 0 ns
-    6   addr [127.649 TiB , 127.649 TiB) (6.926 MiB  ) access 0 %   age 1 s
-    7   addr [127.998 TiB , 127.998 TiB) (120.000 KiB) access 0 %   age 11.100 s
-    8   addr [127.998 TiB , 127.998 TiB) (8.000 KiB  ) access 40 %  age 100 ms
-    9   addr [127.998 TiB , 127.998 TiB) (4.000 KiB  ) access 0 %   age 11 s
-    total size: 577.590 MiB
-    $ sudo ./damo stop
+    $ sudo damo report access
+    heatmap: 641111111000000000000000000000000000000000000000000000[...]33333333333333335557984444[...]7
+    # min/max temperatures: -1,840,000,000, 370,010,000, column size: 3.925 MiB
+    0   addr 86.182 TiB   size 8.000 KiB   access 0 %   age 14.900 s
+    1   addr 86.182 TiB   size 8.000 KiB   access 60 %  age 0 ns
+    2   addr 86.182 TiB   size 3.422 MiB   access 0 %   age 4.100 s
+    3   addr 86.182 TiB   size 2.004 MiB   access 95 %  age 2.200 s
+    4   addr 86.182 TiB   size 29.688 MiB  access 0 %   age 14.100 s
+    5   addr 86.182 TiB   size 29.516 MiB  access 0 %   age 16.700 s
+    6   addr 86.182 TiB   size 29.633 MiB  access 0 %   age 17.900 s
+    7   addr 86.182 TiB   size 117.652 MiB access 0 %   age 18.400 s
+    8   addr 126.990 TiB  size 62.332 MiB  access 0 %   age 9.500 s
+    9   addr 126.990 TiB  size 13.980 MiB  access 0 %   age 5.200 s
+    10  addr 126.990 TiB  size 9.539 MiB   access 100 % age 3.700 s
+    11  addr 126.990 TiB  size 16.098 MiB  access 0 %   age 6.400 s
+    12  addr 127.987 TiB  size 132.000 KiB access 0 %   age 2.900 s
+    total size: 314.008 MiB
+    $ sudo damo stop
 
 The first command of the above example downloads and builds an artificial
 memory access generator program called ``masim``.  The second command asks DAMO
-to execute the artificial generator process start via the given command and
-make DAMON monitors the generator process.  The third command retrieves the
-current snapshot of the monitored access pattern of the process from DAMON and
-shows the pattern in a human readable format.
-
-Each line of the output shows which virtual address range (``addr [XX, XX)``)
-of the process is how frequently (``access XX %``) accessed for how long time
-(``age XX``).  For example, the fifth region of ~9 MiB size is being most
-frequently accessed for last 300 milliseconds.  Finally, the fourth command
-stops DAMON.
+to start the program via the given command and make DAMON monitors the newly
+started process.  The third command retrieves the current snapshot of the
+monitored access pattern of the process from DAMON and shows the pattern in a
+human readable format.
+
+The first line of the output shows the relative access temperature (hotness) of
+the regions in a single row hetmap format.  Each column on the heatmap
+represents regions of same size on the monitored virtual address space.  The
+position of the colun on the row and the number on the column represents the
+relative location and access temperature of the region.  ``[...]`` means
+unmapped huge regions on the virtual address spaces.  The second line shows
+additional information for better understanding the heatmap.
+
+Each line of the output from the third line shows which virtual address range
+(``addr XX size XX``) of the process is how frequently (``access XX %``)
+accessed for how long time (``age XX``).  For example, the evelenth region of
+~9.5 MiB size is being most frequently accessed for last 3.7 seconds.  Finally,
+the fourth command stops DAMON.
 
 Note that DAMON can monitor not only virtual address spaces but multiple types
 of address spaces including the physical address space.
@@ -95,7 +108,7 @@ Visualizing Recorded Patterns
 You can visualize the pattern in a heatmap, showing which memory region
 (x-axis) got accessed when (y-axis) and how frequently (number).::
 
-    $ sudo damo report heats --heatmap stdout
+    $ sudo damo report heatmap
     22222222222222222222222222222222222222211111111111111111111111111111111111111100
     44444444444444444444444444444444444444434444444444444444444444444444444444443200
     44444444444444444444444444444444444444433444444444444444444444444444444444444200
@@ -160,6 +173,6 @@ Data Access Pattern Aware Memory Management
 Below command makes every memory region of size >=4K that has not accessed for
 >=60 seconds in your workload to be swapped out. ::
 
-    $ sudo damo schemes --damos_access_rate 0 0 --damos_sz_region 4K max \
-                        --damos_age 60s max --damos_action pageout \
-                        <pid of your workload>
+    $ sudo damo start --damos_access_rate 0 0 --damos_sz_region 4K max \
+                      --damos_age 60s max --damos_action pageout \
+                      <pid of your workload>
diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst
index d9be9f7caa7d..47a44bd348ab 100644
--- a/Documentation/admin-guide/mm/damon/usage.rst
+++ b/Documentation/admin-guide/mm/damon/usage.rst
@@ -26,12 +26,6 @@ DAMON provides below interfaces for different users.
   writing kernel space DAMON application programs for you.  You can even extend
   DAMON for various address spaces.  For detail, please refer to the interface
   :doc:`document </mm/damon/api>`.
-- *debugfs interface. (DEPRECATED!)*
-  :ref:`This <debugfs_interface>` is almost identical to :ref:`sysfs interface
-  <sysfs_interface>`.  This is deprecated, so users should move to the
-  :ref:`sysfs interface <sysfs_interface>`.  If you depend on this and cannot
-  move, please report your usecase to damon@lists.linux.dev and
-  linux-mm@kvack.org.
 
 .. _sysfs_interface:
 
@@ -89,10 +83,10 @@ comma (",").
     │ │ │ │ │ │ │ │ │ 0/target_metric,target_value,current_value
     │ │ │ │ │ │ │ :ref:`watermarks <sysfs_watermarks>`/metric,interval_us,high,mid,low
     │ │ │ │ │ │ │ :ref:`filters <sysfs_filters>`/nr_filters
-    │ │ │ │ │ │ │ │ 0/type,matching,memcg_id
-    │ │ │ │ │ │ │ :ref:`stats <sysfs_schemes_stats>`/nr_tried,sz_tried,nr_applied,sz_applied,qt_exceeds
+    │ │ │ │ │ │ │ │ 0/type,matching,allow,memcg_path,addr_start,addr_end,target_idx
+    │ │ │ │ │ │ │ :ref:`stats <sysfs_schemes_stats>`/nr_tried,sz_tried,nr_applied,sz_applied,sz_ops_filter_passed,qt_exceeds
     │ │ │ │ │ │ │ :ref:`tried_regions <sysfs_schemes_tried_regions>`/total_bytes
-    │ │ │ │ │ │ │ │ 0/start,end,nr_accesses,age
+    │ │ │ │ │ │ │ │ 0/start,end,nr_accesses,age,sz_filter_passed
     │ │ │ │ │ │ │ │ ...
     │ │ │ │ │ │ ...
     │ │ │ │ ...
@@ -412,59 +406,62 @@ number (``N``) to the file creates the number of child directories named ``0``
 to ``N-1``.  Each directory represents each filter.  The filters are evaluated
 in the numeric order.
 
-Each filter directory contains six files, namely ``type``, ``matcing``,
-``memcg_path``, ``addr_start``, ``addr_end``, and ``target_idx``.  To ``type``
-file, you can write one of five special keywords: ``anon`` for anonymous pages,
-``memcg`` for specific memory cgroup, ``young`` for young pages, ``addr`` for
-specific address range (an open-ended interval), or ``target`` for specific
-DAMON monitoring target filtering.  In case of the memory cgroup filtering, you
-can specify the memory cgroup of the interest by writing the path of the memory
-cgroup from the cgroups mount point to ``memcg_path`` file.  In case of the
-address range filtering, you can specify the start and end address of the range
-to ``addr_start`` and ``addr_end`` files, respectively.  For the DAMON
-monitoring target filtering, you can specify the index of the target between
-the list of the DAMON context's monitoring targets list to ``target_idx`` file.
-You can write ``Y`` or ``N`` to ``matching`` file to filter out pages that does
-or does not match to the type, respectively.  Then, the scheme's action will
-not be applied to the pages that specified to be filtered out.
+Each filter directory contains seven files, namely ``type``, ``matching``,
+``allow``, ``memcg_path``, ``addr_start``, ``addr_end``, and ``target_idx``.
+To ``type`` file, you can write one of five special keywords: ``anon`` for
+anonymous pages, ``memcg`` for specific memory cgroup, ``young`` for young
+pages, ``addr`` for specific address range (an open-ended interval), or
+``target`` for specific DAMON monitoring target filtering.  Meaning of the
+types are same to the description on the :ref:`design doc
+<damon_design_damos_filters>`.
+
+In case of the memory cgroup filtering, you can specify the memory cgroup of
+the interest by writing the path of the memory cgroup from the cgroups mount
+point to ``memcg_path`` file.  In case of the address range filtering, you can
+specify the start and end address of the range to ``addr_start`` and
+``addr_end`` files, respectively.  For the DAMON monitoring target filtering,
+you can specify the index of the target between the list of the DAMON context's
+monitoring targets list to ``target_idx`` file.
+
+You can write ``Y`` or ``N`` to ``matching`` file to specify whether the filter
+is for memory that matches the ``type``.  You can write ``Y`` or ``N`` to
+``allow`` file to specify if applying the action to the memory that satisfies
+the ``type`` and ``matching`` should be allowed or not.
 
 For example, below restricts a DAMOS action to be applied to only non-anonymous
 pages of all memory cgroups except ``/having_care_already``.::
 
     # echo 2 > nr_filters
-    # # filter out anonymous pages
+    # # disallow anonymous pages
     echo anon > 0/type
     echo Y > 0/matching
+    echo N > 0/allow
     # # further filter out all cgroups except one at '/having_care_already'
     echo memcg > 1/type
     echo /having_care_already > 1/memcg_path
     echo Y > 1/matching
+    echo N > 1/allow
 
-Note that ``anon`` and ``memcg`` filters are currently supported only when
-``paddr`` :ref:`implementation <sysfs_context>` is being used.
-
-Also, memory regions that are filtered out by ``addr`` or ``target`` filters
-are not counted as the scheme has tried to those, while regions that filtered
-out by other type filters are counted as the scheme has tried to.  The
-difference is applied to :ref:`stats <damos_stats>` and
-:ref:`tried regions <sysfs_schemes_tried_regions>`.
+Refer to the :ref:`DAMOS filters design documentation
+<damon_design_damos_filters>` for more details including how multiple filters
+of different ``allow`` works, when each of the filters are supported, and
+differences on stats.
 
 .. _sysfs_schemes_stats:
 
 schemes/<N>/stats/
 ------------------
 
-DAMON counts the total number and bytes of regions that each scheme is tried to
-be applied, the two numbers for the regions that each scheme is successfully
-applied, and the total number of the quota limit exceeds.  This statistics can
-be used for online analysis or tuning of the schemes.
+DAMON counts statistics for each scheme.  This statistics can be used for
+online analysis or tuning of the schemes.  Refer to :ref:`design doc
+<damon_design_damos_stat>` for more details about the stats.
 
 The statistics can be retrieved by reading the files under ``stats`` directory
-(``nr_tried``, ``sz_tried``, ``nr_applied``, ``sz_applied``, and
-``qt_exceeds``), respectively.  The files are not updated in real time, so you
-should ask DAMON sysfs interface to update the content of the files for the
-stats by writing a special keyword, ``update_schemes_stats`` to the relevant
-``kdamonds/<N>/state`` file.
+(``nr_tried``, ``sz_tried``, ``nr_applied``, ``sz_applied``,
+``sz_ops_filter_passed``, and ``qt_exceeds``), respectively.  The files are not
+updated in real time, so you should ask DAMON sysfs interface to update the
+content of the files for the stats by writing a special keyword,
+``update_schemes_stats`` to the relevant ``kdamonds/<N>/state`` file.
 
 .. _sysfs_schemes_tried_regions:
 
@@ -501,10 +498,10 @@ set the ``access pattern`` as their interested pattern that they want to query.
 tried_regions/<N>/
 ------------------
 
-In each region directory, you will find four files (``start``, ``end``,
-``nr_accesses``, and ``age``).  Reading the files will show the start and end
-addresses, ``nr_accesses``, and ``age`` of the region that corresponding
-DAMON-based operation scheme ``action`` has tried to be applied.
+In each region directory, you will find five files (``start``, ``end``,
+``nr_accesses``, ``age``, and ``sz_filter_passed``).  Reading the files will
+show the properties of the region that corresponding DAMON-based operation
+scheme ``action`` has tried to be applied.
 
 Example
 ~~~~~~~
@@ -600,306 +597,3 @@ fields are as usual.  It shows the index of the DAMON context (``ctx_idx=X``)
 of the scheme in the list of the contexts of the context's kdamond, the index
 of the scheme (``scheme_idx=X``) in the list of the schemes of the context, in
 addition to the output of ``damon_aggregated`` tracepoint.
-
-
-.. _debugfs_interface:
-
-debugfs Interface (DEPRECATED!)
-===============================
-
-.. note::
-
-  THIS IS DEPRECATED!
-
-  DAMON debugfs interface is deprecated, so users should move to the
-  :ref:`sysfs interface <sysfs_interface>`.  If you depend on this and cannot
-  move, please report your usecase to damon@lists.linux.dev and
-  linux-mm@kvack.org.
-
-DAMON exports nine files, ``DEPRECATED``, ``attrs``, ``target_ids``,
-``init_regions``, ``schemes``, ``monitor_on_DEPRECATED``, ``kdamond_pid``,
-``mk_contexts`` and ``rm_contexts`` under its debugfs directory,
-``<debugfs>/damon/``.
-
-
-``DEPRECATED`` is a read-only file for the DAMON debugfs interface deprecation
-notice.  Reading it returns the deprecation notice, as below::
-
-    # cat DEPRECATED
-    DAMON debugfs interface is deprecated, so users should move to DAMON_SYSFS. If you cannot, please report your usecase to damon@lists.linux.dev and linux-mm@kvack.org.
-
-
-Attributes
-----------
-
-Users can get and set the ``sampling interval``, ``aggregation interval``,
-``update interval``, and min/max number of monitoring target regions by
-reading from and writing to the ``attrs`` file.  To know about the monitoring
-attributes in detail, please refer to the :doc:`/mm/damon/design`.  For
-example, below commands set those values to 5 ms, 100 ms, 1,000 ms, 10 and
-1000, and then check it again::
-
-    # cd <debugfs>/damon
-    # echo 5000 100000 1000000 10 1000 > attrs
-    # cat attrs
-    5000 100000 1000000 10 1000
-
-
-Target IDs
-----------
-
-Some types of address spaces supports multiple monitoring target.  For example,
-the virtual memory address spaces monitoring can have multiple processes as the
-monitoring targets.  Users can set the targets by writing relevant id values of
-the targets to, and get the ids of the current targets by reading from the
-``target_ids`` file.  In case of the virtual address spaces monitoring, the
-values should be pids of the monitoring target processes.  For example, below
-commands set processes having pids 42 and 4242 as the monitoring targets and
-check it again::
-
-    # cd <debugfs>/damon
-    # echo 42 4242 > target_ids
-    # cat target_ids
-    42 4242
-
-Users can also monitor the physical memory address space of the system by
-writing a special keyword, "``paddr\n``" to the file.  Because physical address
-space monitoring doesn't support multiple targets, reading the file will show a
-fake value, ``42``, as below::
-
-    # cd <debugfs>/damon
-    # echo paddr > target_ids
-    # cat target_ids
-    42
-
-Note that setting the target ids doesn't start the monitoring.
-
-
-Initial Monitoring Target Regions
----------------------------------
-
-In case of the virtual address space monitoring, DAMON automatically sets and
-updates the monitoring target regions so that entire memory mappings of target
-processes can be covered.  However, users can want to limit the monitoring
-region to specific address ranges, such as the heap, the stack, or specific
-file-mapped area.  Or, some users can know the initial access pattern of their
-workloads and therefore want to set optimal initial regions for the 'adaptive
-regions adjustment'.
-
-In contrast, DAMON do not automatically sets and updates the monitoring target
-regions in case of physical memory monitoring.  Therefore, users should set the
-monitoring target regions by themselves.
-
-In such cases, users can explicitly set the initial monitoring target regions
-as they want, by writing proper values to the ``init_regions`` file.  The input
-should be a sequence of three integers separated by white spaces that represent
-one region in below form.::
-
-    <target idx> <start address> <end address>
-
-The ``target idx`` should be the index of the target in ``target_ids`` file,
-starting from ``0``, and the regions should be passed in address order.  For
-example, below commands will set a couple of address ranges, ``1-100`` and
-``100-200`` as the initial monitoring target region of pid 42, which is the
-first one (index ``0``) in ``target_ids``, and another couple of address
-ranges, ``20-40`` and ``50-100`` as that of pid 4242, which is the second one
-(index ``1``) in ``target_ids``.::
-
-    # cd <debugfs>/damon
-    # cat target_ids
-    42 4242
-    # echo "0   1       100 \
-            0   100     200 \
-            1   20      40  \
-            1   50      100" > init_regions
-
-Note that this sets the initial monitoring target regions only.  In case of
-virtual memory monitoring, DAMON will automatically updates the boundary of the
-regions after one ``update interval``.  Therefore, users should set the
-``update interval`` large enough in this case, if they don't want the
-update.
-
-
-Schemes
--------
-
-Users can get and set the DAMON-based operation :ref:`schemes
-<damon_design_damos>` by reading from and writing to ``schemes`` debugfs file.
-Reading the file also shows the statistics of each scheme.  To the file, each
-of the schemes should be represented in each line in below form::
-
-    <target access pattern> <action> <quota> <watermarks>
-
-You can disable schemes by simply writing an empty string to the file.
-
-Target Access Pattern
-~~~~~~~~~~~~~~~~~~~~~
-
-The target access :ref:`pattern <damon_design_damos_access_pattern>` of the
-scheme.  The ``<target access pattern>`` is constructed with three ranges in
-below form::
-
-    min-size max-size min-acc max-acc min-age max-age
-
-Specifically, bytes for the size of regions (``min-size`` and ``max-size``),
-number of monitored accesses per aggregate interval for access frequency
-(``min-acc`` and ``max-acc``), number of aggregate intervals for the age of
-regions (``min-age`` and ``max-age``) are specified.  Note that the ranges are
-closed interval.
-
-Action
-~~~~~~
-
-The ``<action>`` is a predefined integer for memory management :ref:`actions
-<damon_design_damos_action>`.  The mapping between the ``<action>`` values and
-the memory management actions is as below.  For the detailed meaning of the
-action and DAMON operations set supporting each action, please refer to the
-list on :ref:`design doc <damon_design_damos_action>`.
-
- - 0: ``willneed``
- - 1: ``cold``
- - 2: ``pageout``
- - 3: ``hugepage``
- - 4: ``nohugepage``
- - 5: ``stat``
-
-Quota
-~~~~~
-
-Users can set the :ref:`quotas <damon_design_damos_quotas>` of the given scheme
-via the ``<quota>`` in below form::
-
-    <ms> <sz> <reset interval> <priority weights>
-
-This makes DAMON to try to use only up to ``<ms>`` milliseconds for applying
-the action to memory regions of the ``target access pattern`` within the
-``<reset interval>`` milliseconds, and to apply the action to only up to
-``<sz>`` bytes of memory regions within the ``<reset interval>``.  Setting both
-``<ms>`` and ``<sz>`` zero disables the quota limits.
-
-For the :ref:`prioritization <damon_design_damos_quotas_prioritization>`, users
-can set the weights for the three properties in ``<priority weights>`` in below
-form::
-
-    <size weight> <access frequency weight> <age weight>
-
-Watermarks
-~~~~~~~~~~
-
-Users can specify :ref:`watermarks <damon_design_damos_watermarks>` of the
-given scheme via ``<watermarks>`` in below form::
-
-    <metric> <check interval> <high mark> <middle mark> <low mark>
-
-``<metric>`` is a predefined integer for the metric to be checked.  The
-supported numbers and their meanings are as below.
-
- - 0: Ignore the watermarks
- - 1: System's free memory rate (per thousand)
-
-The value of the metric is checked every ``<check interval>`` microseconds.
-
-If the value is higher than ``<high mark>`` or lower than ``<low mark>``, the
-scheme is deactivated.  If the value is lower than ``<mid mark>``, the scheme
-is activated.
-
-.. _damos_stats:
-
-Statistics
-~~~~~~~~~~
-
-It also counts the total number and bytes of regions that each scheme is tried
-to be applied, the two numbers for the regions that each scheme is successfully
-applied, and the total number of the quota limit exceeds.  This statistics can
-be used for online analysis or tuning of the schemes.
-
-The statistics can be shown by reading the ``schemes`` file.  Reading the file
-will show each scheme you entered in each line, and the five numbers for the
-statistics will be added at the end of each line.
-
-Example
-~~~~~~~
-
-Below commands applies a scheme saying "If a memory region of size in [4KiB,
-8KiB] is showing accesses per aggregate interval in [0, 5] for aggregate
-interval in [10, 20], page out the region.  For the paging out, use only up to
-10ms per second, and also don't page out more than 1GiB per second.  Under the
-limitation, page out memory regions having longer age first.  Also, check the
-free memory rate of the system every 5 seconds, start the monitoring and paging
-out when the free memory rate becomes lower than 50%, but stop it if the free
-memory rate becomes larger than 60%, or lower than 30%".::
-
-    # cd <debugfs>/damon
-    # scheme="4096 8192  0 5    10 20    2"  # target access pattern and action
-    # scheme+=" 10 $((1024*1024*1024)) 1000" # quotas
-    # scheme+=" 0 0 100"                     # prioritization weights
-    # scheme+=" 1 5000000 600 500 300"       # watermarks
-    # echo "$scheme" > schemes
-
-
-Turning On/Off
---------------
-
-Setting the files as described above doesn't incur effect unless you explicitly
-start the monitoring.  You can start, stop, and check the current status of the
-monitoring by writing to and reading from the ``monitor_on_DEPRECATED`` file.
-Writing ``on`` to the file starts the monitoring of the targets with the
-attributes.  Writing ``off`` to the file stops those.  DAMON also stops if
-every target process is terminated.  Below example commands turn on, off, and
-check the status of DAMON::
-
-    # cd <debugfs>/damon
-    # echo on > monitor_on_DEPRECATED
-    # echo off > monitor_on_DEPRECATED
-    # cat monitor_on_DEPRECATED
-    off
-
-Please note that you cannot write to the above-mentioned debugfs files while
-the monitoring is turned on.  If you write to the files while DAMON is running,
-an error code such as ``-EBUSY`` will be returned.
-
-
-Monitoring Thread PID
----------------------
-
-DAMON does requested monitoring with a kernel thread called ``kdamond``.  You
-can get the pid of the thread by reading the ``kdamond_pid`` file.  When the
-monitoring is turned off, reading the file returns ``none``. ::
-
-    # cd <debugfs>/damon
-    # cat monitor_on_DEPRECATED
-    off
-    # cat kdamond_pid
-    none
-    # echo on > monitor_on_DEPRECATED
-    # cat kdamond_pid
-    18594
-
-
-Using Multiple Monitoring Threads
----------------------------------
-
-One ``kdamond`` thread is created for each monitoring context.  You can create
-and remove monitoring contexts for multiple ``kdamond`` required use case using
-the ``mk_contexts`` and ``rm_contexts`` files.
-
-Writing the name of the new context to the ``mk_contexts`` file creates a
-directory of the name on the DAMON debugfs directory.  The directory will have
-DAMON debugfs files for the context. ::
-
-    # cd <debugfs>/damon
-    # ls foo
-    # ls: cannot access 'foo': No such file or directory
-    # echo foo > mk_contexts
-    # ls foo
-    # attrs  init_regions  kdamond_pid  schemes  target_ids
-
-If the context is not needed anymore, you can remove it and the corresponding
-directory by putting the name of the context to the ``rm_contexts`` file. ::
-
-    # echo foo > rm_contexts
-    # ls foo
-    # ls: cannot access 'foo': No such file or directory
-
-Note that ``mk_contexts``, ``rm_contexts``, and ``monitor_on_DEPRECATED`` files
-are in the root directory only.
diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst
index cb2c080f400c..33c886f3d198 100644
--- a/Documentation/admin-guide/mm/memory-hotplug.rst
+++ b/Documentation/admin-guide/mm/memory-hotplug.rst
@@ -280,8 +280,8 @@ The following files are currently defined:
 		       blocks; configure auto-onlining.
 
 		       The default value depends on the
-		       CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel configuration
-		       option.
+		       CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel configuration
+		       options.
 
 		       See the ``state`` property of memory blocks for details.
 ``block_size_bytes``   read-only: the size in bytes of a memory block.
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index 8872203df088..dff8d5985f0f 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -332,6 +332,12 @@ allocation policy for the internal shmem mount by using the kernel parameter
 seven valid policies for shmem (``always``, ``within_size``, ``advise``,
 ``never``, ``deny``, and ``force``).
 
+Similarly to ``transparent_hugepage_shmem``, you can control the default
+hugepage allocation policy for the tmpfs mount by using the kernel parameter
+``transparent_hugepage_tmpfs=<policy>``, where ``<policy>`` is one of the
+four valid policies for tmpfs (``always``, ``within_size``, ``advise``,
+``never``). The tmpfs mount default policy is ``never``.
+
 In the same manner as ``thp_anon`` controls each supported anonymous THP
 size, ``thp_shmem`` controls each supported shmem THP size. ``thp_shmem``
 has the same format as ``thp_anon``, but also supports the policy
@@ -352,8 +358,21 @@ default to ``never``.
 Hugepages in tmpfs/shmem
 ========================
 
-You can control hugepage allocation policy in tmpfs with mount option
-``huge=``. It can have following values:
+Traditionally, tmpfs only supported a single huge page size ("PMD"). Today,
+it also supports smaller sizes just like anonymous memory, often referred
+to as "multi-size THP" (mTHP). Huge pages of any size are commonly
+represented in the kernel as "large folios".
+
+While there is fine control over the huge page sizes to use for the internal
+shmem mount (see below), ordinary tmpfs mounts will make use of all available
+huge page sizes without any control over the exact sizes, behaving more like
+other file systems.
+
+tmpfs mounts
+------------
+
+The THP allocation policy for tmpfs mounts can be adjusted using the mount
+option: ``huge=``. It can have following values:
 
 always
     Attempt to allocate huge pages every time we need a new page;
@@ -363,24 +382,24 @@ never
 
 within_size
     Only allocate huge page if it will be fully within i_size.
-    Also respect fadvise()/madvise() hints;
+    Also respect madvise() hints;
 
 advise
-    Only allocate huge pages if requested with fadvise()/madvise();
+    Only allocate huge pages if requested with madvise();
+
+Remember, that the kernel may use huge pages of all available sizes, and
+that no fine control as for the internal tmpfs mount is available.
 
-The default policy is ``never``.
+The default policy in the past was ``never``, but it can now be adjusted
+using the kernel parameter ``transparent_hugepage_tmpfs=<policy>``.
 
 ``mount -o remount,huge= /mountpoint`` works fine after mount: remounting
 ``huge=never`` will not attempt to break up huge pages at all, just stop more
 from being allocated.
 
-There's also sysfs knob to control hugepage allocation policy for internal
-shmem mount: /sys/kernel/mm/transparent_hugepage/shmem_enabled. The mount
-is used for SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or
-MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem.
-
-In addition to policies listed above, shmem_enabled allows two further
-values:
+In addition to policies listed above, the sysfs knob
+/sys/kernel/mm/transparent_hugepage/shmem_enabled will affect the
+allocation policy of tmpfs mounts, when set to the following values:
 
 deny
     For use in emergencies, to force the huge option off from
@@ -388,13 +407,24 @@ deny
 force
     Force the huge option on for all - very useful for testing;
 
-Shmem can also use "multi-size THP" (mTHP) by adding a new sysfs knob to
-control mTHP allocation:
-'/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/shmem_enabled',
-and its value for each mTHP is essentially consistent with the global
-setting.  An 'inherit' option is added to ensure compatibility with these
-global settings.  Conversely, the options 'force' and 'deny' are dropped,
-which are rather testing artifacts from the old ages.
+shmem / internal tmpfs
+----------------------
+The mount internal tmpfs mount is used for SysV SHM, memfds, shared anonymous
+mmaps (of /dev/zero or MAP_ANONYMOUS), GPU drivers' DRM  objects, Ashmem.
+
+To control the THP allocation policy for this internal tmpfs mount, the
+sysfs knob /sys/kernel/mm/transparent_hugepage/shmem_enabled and the knobs
+per THP size in
+'/sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/shmem_enabled'
+can be used.
+
+The global knob has the same semantics as the ``huge=`` mount options
+for tmpfs mounts, except that the different huge page sizes can be controlled
+individually, and will only use the setting of the global knob when the
+per-size knob is set to 'inherit'.
+
+The options 'force' and 'deny' are dropped for the individual sizes, which
+are rather testing artifacts from the old ages.
 
 always
     Attempt to allocate <size> huge pages every time we need a new page;
@@ -408,10 +438,10 @@ never
 
 within_size
     Only allocate <size> huge page if it will be fully within i_size.
-    Also respect fadvise()/madvise() hints;
+    Also respect madvise() hints;
 
 advise
-    Only allocate <size> huge pages if requested with fadvise()/madvise();
+    Only allocate <size> huge pages if requested with madvise();
 
 Need of application restart
 ===========================
@@ -561,6 +591,16 @@ swpin
 	is incremented every time a huge page is swapped in from a non-zswap
 	swap device in one piece.
 
+swpin_fallback
+	is incremented if swapin fails to allocate or charge a huge page
+	and instead falls back to using huge pages with lower orders or
+	small pages.
+
+swpin_fallback_charge
+	is incremented if swapin fails to charge a huge page and instead
+	falls back to using  huge pages with lower orders or small pages
+	even though the allocation was successful.
+
 swpout
 	is incremented every time a huge page is swapped out to a non-zswap
 	swap device in one piece without splitting.
diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst
index 955fbcd19ce9..f273ea15a8e8 100644
--- a/Documentation/arch/riscv/hwprobe.rst
+++ b/Documentation/arch/riscv/hwprobe.rst
@@ -293,3 +293,13 @@ The following keys are defined:
 
   * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are
     not supported at all and will generate a misaligned address fault.
+
+* :c:macro:`RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0`: A bitmask containing the
+  thead vendor extensions that are compatible with the
+  :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: base system behavior.
+
+  * T-HEAD
+
+    * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR`: The xtheadvector vendor
+        extension is supported in the T-Head ISA extensions spec starting from
+	commit a18c801634 ("Add T-Head VECTOR vendor extension. ").
diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst
index 51665a3e6a50..1e0e7358e14a 100644
--- a/Documentation/block/ublk.rst
+++ b/Documentation/block/ublk.rst
@@ -333,6 +333,4 @@ References
 
 .. [#userspace_readme] https://github.com/ming1/ubdsrv/blob/master/README
 
-.. [#stefan] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/
-
 .. [#xiaoguang] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/
diff --git a/Documentation/core-api/min_heap.rst b/Documentation/core-api/min_heap.rst
index 0c636c8b7aa5..683bc6d09f00 100644
--- a/Documentation/core-api/min_heap.rst
+++ b/Documentation/core-api/min_heap.rst
@@ -4,6 +4,8 @@
 Min Heap API
 ============
 
+:Author: Kuan-Wei Chiu <visitorckw@gmail.com>
+
 Introduction
 ============
 
diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst
index 77e0ece2b1d6..f6a3eef4fe7f 100644
--- a/Documentation/core-api/xarray.rst
+++ b/Documentation/core-api/xarray.rst
@@ -42,8 +42,8 @@ call xa_tag_pointer() to create an entry with a tag, xa_untag_pointer()
 to turn a tagged entry back into an untagged pointer and xa_pointer_tag()
 to retrieve the tag of an entry.  Tagged pointers use the same bits that
 are used to distinguish value entries from normal pointers, so you must
-decide whether they want to store value entries or tagged pointers in
-any particular XArray.
+decide whether you want to store value entries or tagged pointers in any
+particular XArray.
 
 The XArray does not support storing IS_ERR() pointers as some
 conflict with value entries or internal entries.
@@ -52,8 +52,9 @@ An unusual feature of the XArray is the ability to create entries which
 occupy a range of indices.  Once stored to, looking up any index in
 the range will return the same entry as looking up any other index in
 the range.  Storing to any index will store to all of them.  Multi-index
-entries can be explicitly split into smaller entries, or storing ``NULL``
-into any entry will cause the XArray to forget about the range.
+entries can be explicitly split into smaller entries. Unsetting (using
+xa_erase() or xa_store() with ``NULL``) any entry will cause the XArray
+to forget about the range.
 
 Normal API
 ==========
@@ -63,13 +64,14 @@ for statically allocated XArrays or xa_init() for dynamically
 allocated ones.  A freshly-initialised XArray contains a ``NULL``
 pointer at every index.
 
-You can then set entries using xa_store() and get entries
-using xa_load().  xa_store will overwrite any entry with the
-new entry and return the previous entry stored at that index.  You can
-use xa_erase() instead of calling xa_store() with a
-``NULL`` entry.  There is no difference between an entry that has never
-been stored to, one that has been erased and one that has most recently
-had ``NULL`` stored to it.
+You can then set entries using xa_store() and get entries using
+xa_load().  xa_store() will overwrite any entry with the new entry and
+return the previous entry stored at that index.  You can unset entries
+using xa_erase() or by setting the entry to ``NULL`` using xa_store().
+There is no difference between an entry that has never been stored to
+and one that has been erased with xa_erase(); an entry that has most
+recently had ``NULL`` stored to it is also equivalent except if the
+XArray was initialized with ``XA_FLAGS_ALLOC``.
 
 You can conditionally replace an entry at an index by using
 xa_cmpxchg().  Like cmpxchg(), it will only succeed if
diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
index 04a8c37b4aff..742dc4e25d3b 100644
--- a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
@@ -38,6 +38,12 @@ properties:
     enum:
       - arm,coresight-dummy-source
 
+  arm,static-trace-id:
+    description: If dummy source needs static id support, use this to set trace id.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 1
+    maximum: 111
+
   out-ports:
     $ref: /schemas/graph.yaml#/properties/ports
 
diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml
index 1892a091ac35..a6f793ea03b6 100644
--- a/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,coresight-static-replicator.yaml
@@ -45,7 +45,22 @@ properties:
     patternProperties:
       '^port@[01]$':
         description: Output connections to CoreSight Trace bus
-        $ref: /schemas/graph.yaml#/properties/port
+        $ref: /schemas/graph.yaml#/$defs/port-base
+        unevaluatedProperties: false
+
+        properties:
+          endpoint:
+            $ref: /schemas/graph.yaml#/$defs/endpoint-base
+            unevaluatedProperties: false
+
+            properties:
+              filter-source:
+                $ref: /schemas/types.yaml#/definitions/phandle
+                description:
+                  phandle to the coresight trace source device matching the
+                  hard coded filtering for this port
+
+              remote-endpoint: true
 
 required:
   - compatible
@@ -72,6 +87,7 @@ examples:
                 reg = <0>;
                 replicator_out_port0: endpoint {
                     remote-endpoint = <&etb_in_port>;
+                    filter-source = <&tpdm_video>;
                 };
             };
 
@@ -79,6 +95,7 @@ examples:
                 reg = <1>;
                 replicator_out_port1: endpoint {
                     remote-endpoint = <&tpiu_in_port>;
+                    filter-source = <&tpdm_mdss>;
                 };
             };
         };
diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml
index 371317554863..0db2cbd7891f 100644
--- a/Documentation/devicetree/bindings/arm/fsl.yaml
+++ b/Documentation/devicetree/bindings/arm/fsl.yaml
@@ -1091,6 +1091,7 @@ properties:
               - dmo,imx8mp-data-modul-edm-sbc # i.MX8MP eDM SBC
               - emcraft,imx8mp-navqp      # i.MX8MP Emcraft Systems NavQ+ Kit
               - fsl,imx8mp-evk            # i.MX8MP EVK Board
+              - fsl,imx8mp-evk-revb4      # i.MX8MP EVK Rev B4 Board
               - gateworks,imx8mp-gw71xx-2x # i.MX8MP Gateworks Board
               - gateworks,imx8mp-gw72xx-2x # i.MX8MP Gateworks Board
               - gateworks,imx8mp-gw73xx-2x # i.MX8MP Gateworks Board
@@ -1271,6 +1272,7 @@ properties:
         items:
           - enum:
               - fsl,imx8qm-mek           # i.MX8QM MEK Board
+              - fsl,imx8qm-mek-revd      # i.MX8QM MEK Rev D Board
               - toradex,apalis-imx8      # Apalis iMX8 Modules
               - toradex,apalis-imx8-v1.1 # Apalis iMX8 V1.1 Modules
           - const: fsl,imx8qm
@@ -1299,6 +1301,7 @@ properties:
           - enum:
               - einfochips,imx8qxp-ai_ml  # i.MX8QXP AI_ML Board
               - fsl,imx8qxp-mek           # i.MX8QXP MEK Board
+              - fsl,imx8qxp-mek-wcpu      # i.MX8QXP MEK WCPU Board
           - const: fsl,imx8qxp
 
       - description: i.MX8DXL based Boards
diff --git a/Documentation/devicetree/bindings/connector/usb-connector.yaml b/Documentation/devicetree/bindings/connector/usb-connector.yaml
index 67700440e23b..11e40d225b9f 100644
--- a/Documentation/devicetree/bindings/connector/usb-connector.yaml
+++ b/Documentation/devicetree/bindings/connector/usb-connector.yaml
@@ -293,6 +293,13 @@ properties:
       PD negotiation till BC1.2 detection completes.
     default: 0
 
+  pd-revision:
+    description: Specifies the maximum USB PD revision and version supported by
+      the connector. This property is specified in the following order;
+      <revision_major, revision_minor, version_major, version_minor>.
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    maxItems: 4
+
 dependencies:
   sink-vdos-v1: [ sink-vdos ]
   sink-vdos: [ sink-vdos-v1 ]
diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
deleted file mode 100644
index cd17684aaab5..000000000000
--- a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt
+++ /dev/null
@@ -1,61 +0,0 @@
-Analog Devices AXI-DMAC DMA controller
-
-Required properties:
- - compatible: Must be "adi,axi-dmac-1.00.a".
- - reg: Specification for the controllers memory mapped register map.
- - interrupts: Specification for the controllers interrupt.
- - clocks: Phandle and specifier to the controllers AXI interface clock
- - #dma-cells: Must be 1.
-
-Required sub-nodes:
- - adi,channels: This sub-node must contain a sub-node for each DMA channel. For
-   the channel sub-nodes the following bindings apply. They must match the
-   configuration options of the peripheral as it was instantiated.
-
-Required properties for adi,channels sub-node:
- - #size-cells: Must be 0
- - #address-cells: Must be 1
-
-Required channel sub-node properties:
- - reg: Which channel this node refers to.
- - adi,source-bus-width,
-   adi,destination-bus-width: Width of the source or destination bus in bits.
- - adi,source-bus-type,
-   adi,destination-bus-type: Type of the source or destination bus. Must be one
-   of the following:
-	0 (AXI_DMAC_TYPE_AXI_MM): Memory mapped AXI interface
-	1 (AXI_DMAC_TYPE_AXI_STREAM): Streaming AXI interface
-	2 (AXI_DMAC_TYPE_AXI_FIFO): FIFO interface
-
-Deprecated optional channel properties:
- - adi,length-width: Width of the DMA transfer length register.
- - adi,cyclic: Must be set if the channel supports hardware cyclic DMA
-   transfers.
- - adi,2d: Must be set if the channel supports hardware 2D DMA transfers.
-
-DMA clients connected to the AXI-DMAC DMA controller must use the format
-described in the dma.txt file using a one-cell specifier. The value of the
-specifier refers to the DMA channel index.
-
-Example:
-
-dma: dma@7c420000 {
-	compatible = "adi,axi-dmac-1.00.a";
-	reg = <0x7c420000 0x10000>;
-	interrupts = <0 57 0>;
-	clocks = <&clkc 16>;
-	#dma-cells = <1>;
-
-	adi,channels {
-		#size-cells = <0>;
-		#address-cells = <1>;
-
-		dma-channel@0 {
-			reg = <0>;
-			adi,source-bus-width = <32>;
-			adi,source-bus-type = <ADI_AXI_DMAC_TYPE_MM_AXI>;
-			adi,destination-bus-width = <64>;
-			adi,destination-bus-type = <ADI_AXI_DMAC_TYPE_FIFO>;
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml b/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml
new file mode 100644
index 000000000000..63b6fb0423c2
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml
@@ -0,0 +1,129 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/adi,axi-dmac.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Analog Devices AXI-DMAC DMA controller
+
+description: |
+  FPGA-based DMA controller designed for use with high-speed converter hardware.
+
+  http://analogdevicesinc.github.io/hdl/library/axi_dmac/index.html
+
+maintainers:
+  - Nuno Sa <nuno.sa@analog.com>
+
+additionalProperties: false
+
+properties:
+  compatible:
+    const: adi,axi-dmac-1.00.a
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  "#dma-cells":
+    const: 1
+
+  adi,channels:
+    deprecated: true
+    type: object
+    description:
+      This sub-node must contain a sub-node for each DMA channel. This node is
+      only required for IP versions older than 4.3.a and should otherwise be
+      omitted.
+    additionalProperties: false
+
+    properties:
+      "#size-cells":
+        const: 0
+      "#address-cells":
+        const: 1
+
+    patternProperties:
+      "^dma-channel@[0-9a-f]+$":
+        type: object
+        description:
+          DMA channel properties based on HDL compile-time configuration.
+        additionalProperties: false
+
+        properties:
+          reg:
+            maxItems: 1
+
+          adi,source-bus-width:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: Width of the source bus in bits.
+            enum: [8, 16, 32, 64, 128]
+
+          adi,destination-bus-width:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: Width of the destination bus in bits.
+            enum: [8, 16, 32, 64, 128]
+
+          adi,source-bus-type:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: |
+              Type of the source bus.
+
+              0: Memory mapped AXI interface
+              1: Streaming AXI interface
+              2: FIFO interface
+            enum: [0, 1, 2]
+
+          adi,destination-bus-type:
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: Type of the destination bus (see adi,source-bus-type).
+            enum: [0, 1, 2]
+
+          adi,length-width:
+            deprecated: true
+            $ref: /schemas/types.yaml#/definitions/uint32
+            description: Width of the DMA transfer length register.
+
+          adi,cyclic:
+            deprecated: true
+            type: boolean
+            description:
+              Must be set if the channel supports hardware cyclic DMA transfers.
+
+          adi,2d:
+            deprecated: true
+            type: boolean
+            description:
+              Must be set if the channel supports hardware 2D DMA transfers.
+
+        required:
+          - reg
+          - adi,source-bus-width
+          - adi,destination-bus-width
+          - adi,source-bus-type
+          - adi,destination-bus-type
+
+    required:
+      - "#size-cells"
+      - "#address-cells"
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - "#dma-cells"
+
+examples:
+  - |
+    dma-controller@7c420000 {
+        compatible = "adi,axi-dmac-1.00.a";
+        reg = <0x7c420000 0x10000>;
+        interrupts = <0 57 0>;
+        clocks = <&clkc 16>;
+        #dma-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml b/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml
index 02d5bd035409..9b5180c0a7c4 100644
--- a/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml
@@ -22,7 +22,9 @@ properties:
       number.
 
   compatible:
-    const: allwinner,sun4i-a10-dma
+    enum:
+      - allwinner,sun4i-a10-dma
+      - allwinner,suniv-f1c100s-dma
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml b/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml
new file mode 100644
index 000000000000..9ca1c5d1f00f
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml
@@ -0,0 +1,79 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/atmel,sama5d4-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip AT91 Extensible Direct Memory Access Controller
+
+maintainers:
+  - Nicolas Ferre <nicolas.ferre@microchip.com>
+  - Charan Pedumuru <charan.pedumuru@microchip.com>
+
+description:
+  The DMA Controller (XDMAC) is a AHB-protocol central direct memory access
+  controller. It performs peripheral data transfer and memory move operations
+  over one or two bus ports through the unidirectional communication
+  channel. Each channel is fully programmable and provides both peripheral
+  or memory-to-memory transfers. The channel features are configurable at
+  implementation.
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - enum:
+          - atmel,sama5d4-dma
+          - microchip,sama7g5-dma
+      - items:
+          - enum:
+              - microchip,sam9x60-dma
+              - microchip,sam9x7-dma
+          - const: atmel,sama5d4-dma
+
+  "#dma-cells":
+    description: |
+      Represents the number of integer cells in the `dmas` property of client
+      devices. The single cell specifies the channel configuration register:
+        - bit 13: SIF (Source Interface Identifier) for memory interface.
+        - bit 14: DIF (Destination Interface Identifier) for peripheral interface.
+        - bit 30-24: PERID (Peripheral Identifier).
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: dma_clk
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - "#dma-cells"
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/at91.h>
+    #include <dt-bindings/dma/at91.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    dma-controller@f0008000 {
+        compatible = "atmel,sama5d4-dma";
+        reg = <0xf0008000 0x1000>;
+        interrupts = <20 IRQ_TYPE_LEVEL_HIGH 0>;
+        #dma-cells = <1>;
+        clocks = <&pmc PMC_TYPE_PERIPHERAL 20>;
+        clock-names = "dma_clk";
+    };
diff --git a/Documentation/devicetree/bindings/dma/atmel-xdma.txt b/Documentation/devicetree/bindings/dma/atmel-xdma.txt
deleted file mode 100644
index 76d649b3a25d..000000000000
--- a/Documentation/devicetree/bindings/dma/atmel-xdma.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-* Atmel Extensible Direct Memory Access Controller (XDMAC)
-
-* XDMA Controller
-Required properties:
-- compatible: Should be "atmel,sama5d4-dma", "microchip,sam9x60-dma" or
-  "microchip,sama7g5-dma" or
-  "microchip,sam9x7-dma", "atmel,sama5d4-dma".
-- reg: Should contain DMA registers location and length.
-- interrupts: Should contain DMA interrupt.
-- #dma-cells: Must be <1>, used to represent the number of integer cells in
-the dmas property of client devices.
-  - The 1st cell specifies the channel configuration register:
-    - bit 13: SIF, source interface identifier, used to get the memory
-    interface identifier,
-    - bit 14: DIF, destination interface identifier, used to get the peripheral
-    interface identifier,
-    - bit 30-24: PERID, peripheral identifier.
-
-Example:
-
-dma1: dma-controller@f0004000 {
-	compatible = "atmel,sama5d4-dma";
-	reg = <0xf0004000 0x200>;
-	interrupts = <50 4 0>;
-	#dma-cells = <1>;
-};
-
-
-* DMA clients
-DMA clients connected to the Atmel XDMA controller must use the format
-described in the dma.txt file, using a one-cell specifier for each channel.
-The two cells in order are:
-1. A phandle pointing to the DMA controller.
-2. Channel configuration register. Configurable fields are:
-    - bit 13: SIF, source interface identifier, used to get the memory
-    interface identifier,
-    - bit 14: DIF, destination interface identifier, used to get the peripheral
-    interface identifier,
-  - bit 30-24: PERID, peripheral identifier.
-
-Example:
-
-i2c2: i2c@f8024000 {
-	compatible = "atmel,at91sam9x5-i2c";
-	reg = <0xf8024000 0x4000>;
-	interrupts = <34 4 6>;
-	dmas = <&dma1
-		(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)
-		 | AT91_XDMAC_DT_PERID(6))>,
-	       <&dma1
-		(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1)
-		| AT91_XDMAC_DT_PERID(7))>;
-	dma-names = "tx", "rx";
-};
diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml
index d54140f18d34..4f925469533e 100644
--- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml
+++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml
@@ -26,9 +26,13 @@ properties:
           - fsl,imx93-edma3
           - fsl,imx93-edma4
           - fsl,imx95-edma5
+          - nxp,s32g2-edma
       - items:
           - const: fsl,ls1028a-edma
           - const: fsl,vf610-edma
+      - items:
+          - const: nxp,s32g3-edma
+          - const: nxp,s32g2-edma
 
   reg:
     minItems: 1
@@ -221,6 +225,36 @@ allOf:
       properties:
         power-domains: false
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: nxp,s32g2-edma
+    then:
+      properties:
+        clocks:
+          minItems: 2
+          maxItems: 2
+        clock-names:
+          items:
+            - const: dmamux0
+            - const: dmamux1
+        interrupts:
+          minItems: 3
+          maxItems: 3
+        interrupt-names:
+          items:
+            - const: tx-0-15
+            - const: tx-16-31
+            - const: err
+        reg:
+          minItems: 3
+          maxItems: 3
+        "#dma-cells":
+          const: 2
+        dma-channels:
+          const: 32
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
index 877147e95ecc..d3f8c269916c 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml
@@ -13,9 +13,6 @@ description: |
 maintainers:
   - Jon Hunter <jonathanh@nvidia.com>
 
-allOf:
-  - $ref: dma-controller.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -29,7 +26,19 @@ properties:
           - const: nvidia,tegra186-adma
 
   reg:
-    maxItems: 1
+    description:
+      The 'page' region describes the address space of the page
+      used for accessing the DMA channel registers. The 'global'
+      region describes the address space of the global DMA registers.
+      In the absence of the 'reg-names' property, there must be a
+      single entry that covers the address space of the global DMA
+      registers and the DMA channel registers.
+    minItems: 1
+    maxItems: 2
+
+  reg-names:
+    minItems: 1
+    maxItems: 2
 
   interrupts:
     description: |
@@ -63,6 +72,49 @@ required:
   - clocks
   - clock-names
 
+allOf:
+  - $ref: dma-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra210-adma
+    then:
+      properties:
+        reg:
+          items:
+            - description: Full address space range of DMA registers.
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - nvidia,tegra186-adma
+    then:
+      anyOf:
+        - properties:
+            reg:
+              items:
+                - description: Full address space range of DMA registers.
+        - properties:
+            reg:
+              items:
+                - description: Channel Page address space range of DMA registers.
+            reg-names:
+              items:
+                - const: page
+        - properties:
+            reg:
+              items:
+                - description: Channel Page address space range of DMA registers.
+                - description: Global Page address space range of DMA registers.
+            reg-names:
+              items:
+                - const: page
+                - const: global
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
index 4ad56a409b9c..7052468b15c8 100644
--- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml
@@ -25,7 +25,9 @@ properties:
       - items:
           - enum:
               - qcom,qcm2290-gpi-dma
+              - qcom,qcs8300-gpi-dma
               - qcom,qdu1000-gpi-dma
+              - qcom,sa8775p-gpi-dma
               - qcom,sar2130p-gpi-dma
               - qcom,sc7280-gpi-dma
               - qcom,sdx75-gpi-dma
@@ -35,10 +37,12 @@ properties:
               - qcom,sm8450-gpi-dma
               - qcom,sm8550-gpi-dma
               - qcom,sm8650-gpi-dma
+              - qcom,sm8750-gpi-dma
               - qcom,x1e80100-gpi-dma
           - const: qcom,sm6350-gpi-dma
       - items:
           - enum:
+              - qcom,qcs615-gpi-dma
               - qcom,sdm670-gpi-dma
               - qcom,sm6125-gpi-dma
               - qcom,sm8150-gpi-dma
diff --git a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml
index f26c914a3a9a..b7bca1a83769 100644
--- a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml
+++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml
@@ -15,6 +15,16 @@ allOf:
 properties:
   "#dma-cells":
     const: 3
+    description: |
+      Each cell represents the following:
+      1. The mux input number/line for the request
+      2. Bitfield representing DMA channel configuration that is passed
+         to the real DMA controller
+      3. Bitfield representing device dependent DMA features passed to
+         the real DMA controller
+
+      For bitfield definitions of cells 2 and 3, see the associated
+      bindings doc for the actual DMA controller in st,stm32-dma.yaml.
 
   compatible:
     const: st,stm32h7-dmamux
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index 27b8e1636560..b5bc842c5a0e 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -34,6 +34,7 @@ properties:
       - ti,am62a-dmss-bcdma-csirx
       - ti,am64-dmss-bcdma
       - ti,j721s2-dmss-bcdma-csi
+      - ti,j722s-dmss-bcdma-csi
 
   reg:
     minItems: 3
@@ -196,7 +197,9 @@ allOf:
       properties:
         compatible:
           contains:
-            const: ti,j721s2-dmss-bcdma-csi
+            enum:
+              - ti,j721s2-dmss-bcdma-csi
+              - ti,j722s-dmss-bcdma-csi
     then:
       properties:
         ti,sci-rm-range-bchan: false
diff --git a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml
index 280ed479ef5a..84d949392012 100644
--- a/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml
+++ b/Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml
@@ -37,10 +37,17 @@ properties:
   interrupts:
     maxItems: 1
 
+  interrupt-names:
+    items:
+      - enum: [INT1, INT2]
+
+dependencies:
+  interrupts: [ interrupt-names ]
+  interrupt-names: [ interrupts ]
+
 required:
   - compatible
   - reg
-  - interrupts
 
 allOf:
   - $ref: /schemas/spi/spi-peripheral-props.yaml#
@@ -61,6 +68,7 @@ examples:
             reg = <0x2a>;
             interrupt-parent = <&gpio0>;
             interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "INT1";
         };
     };
   - |
@@ -79,5 +87,6 @@ examples:
             spi-cpha;
             interrupt-parent = <&gpio0>;
             interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "INT2";
         };
     };
diff --git a/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml b/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml
index 66ea894dbe55..f07c70e51c45 100644
--- a/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml
+++ b/Documentation/devicetree/bindings/iio/accel/kionix,kx022a.yaml
@@ -4,23 +4,26 @@
 $id: http://devicetree.org/schemas/iio/accel/kionix,kx022a.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: ROHM/Kionix KX022A, KX132-1211 and KX132ACR-LBZ Accelerometers
+title: ROHM/Kionix KX022A, KX132/134-1211 and KX132/134ACR-LBZ Accelerometers
 
 maintainers:
   - Matti Vaittinen <mazziesaccount@gmail.com>
 
 description: |
   KX022A, KX132ACR-LBZ and KX132-1211 are 3-axis accelerometers supporting
-  +/- 2G, 4G, 8G and 16G ranges, variable output data-rates and a
-  hardware-fifo buffering. These accelerometers can be accessed either
-  via I2C or SPI.
+  +/- 2G, 4G, 8G and 16G ranges. The KX134ACR-LBZ and KX134-1211 support
+  +/- 8G, 16G, 32G and 64G. All the sensors also have variable output
+  data-rates and a hardware-fifo buffering. These accelerometers can be
+  accessed either via I2C or SPI.
 
 properties:
   compatible:
     enum:
       - kionix,kx022a
       - kionix,kx132-1211
+      - kionix,kx134-1211
       - rohm,kx132acr-lbz
+      - rohm,kx134acr-lbz
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml b/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml
index 783c7ddfcd90..c175f4c4cbdb 100644
--- a/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml
+++ b/Documentation/devicetree/bindings/iio/accel/nxp,fxls8962af.yaml
@@ -14,12 +14,20 @@ description: |
   SPI and I2C interface.
     https://www.nxp.com/docs/en/data-sheet/FXLS8962AF.pdf
     https://www.nxp.com/docs/en/data-sheet/FXLS8964AF.pdf
+    https://www.nxp.com/docs/en/data-sheet/FXLS8967AF.pdf
+    https://www.nxp.com/docs/en/data-sheet/FXLS8974CF.pdf
 
 properties:
   compatible:
-    enum:
-      - nxp,fxls8962af
-      - nxp,fxls8964af
+    oneOf:
+      - enum:
+          - nxp,fxls8962af
+          - nxp,fxls8964af
+      - items:
+          - enum:
+              - nxp,fxls8967af
+              - nxp,fxls8974cf
+          - const: nxp,fxls8962af
 
   reg:
     maxItems: 1
@@ -38,6 +46,11 @@ properties:
   drive-open-drain:
     type: boolean
 
+  wakeup-source:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      Enable wake on accelerometer event
+
 required:
   - compatible
   - reg
@@ -61,6 +74,7 @@ examples:
             interrupt-parent = <&gpio0>;
             interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
             interrupt-names = "INT1";
+            wakeup-source;
         };
     };
   - |
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml
index e413a9d8d2a2..96e01a97dd95 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad4000.yaml
@@ -19,49 +19,82 @@ description: |
     https://www.analog.com/media/en/technical-documentation/data-sheets/ad4020-4021-4022.pdf
     https://www.analog.com/media/en/technical-documentation/data-sheets/adaq4001.pdf
     https://www.analog.com/media/en/technical-documentation/data-sheets/adaq4003.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7685.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7686.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7687.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7688.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7690.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7691.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7693.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7942.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7946.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7980.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7982.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7983.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7984.pdf
+    https://www.analog.com/media/en/technical-documentation/data-sheets/ad7988-1_7988-5.pdf
 
 $ref: /schemas/spi/spi-peripheral-props.yaml#
 
 properties:
   compatible:
     oneOf:
-      - const: adi,ad4000
+      - enum:
+          - adi,ad4000
+          - adi,ad4001
+          - adi,ad4002
+          - adi,ad4003
+          - adi,ad4020
+          - adi,adaq4001
+          - adi,adaq4003
+          - adi,ad7687
+          - adi,ad7691
+          - adi,ad7942
+          - adi,ad7946
+          - adi,ad7983
       - items:
           - enum:
               - adi,ad4004
               - adi,ad4008
           - const: adi,ad4000
-
-      - const: adi,ad4001
       - items:
           - enum:
               - adi,ad4005
           - const: adi,ad4001
-
-      - const: adi,ad4002
       - items:
           - enum:
               - adi,ad4006
               - adi,ad4010
           - const: adi,ad4002
-
-      - const: adi,ad4003
       - items:
           - enum:
               - adi,ad4007
               - adi,ad4011
           - const: adi,ad4003
-
-      - const: adi,ad4020
       - items:
           - enum:
               - adi,ad4021
               - adi,ad4022
           - const: adi,ad4020
-
-      - const: adi,adaq4001
-
-      - const: adi,adaq4003
+      - items:
+          - enum:
+              - adi,ad7685
+              - adi,ad7686
+              - adi,ad7980
+              - adi,ad7988-1
+              - adi,ad7988-5
+          - const: adi,ad7983
+      - items:
+          - enum:
+              - adi,ad7688
+              - adi,ad7693
+          - const: adi,ad7687
+      - items:
+          - enum:
+              - adi,ad7690
+              - adi,ad7982
+              - adi,ad7984
+          - const: adi,ad7691
 
   reg:
     maxItems: 1
@@ -133,6 +166,22 @@ required:
   - ref-supply
 
 allOf:
+  # Single-channel PulSAR devices have SDI either tied to VIO, GND, or host CS.
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - adi,ad7687
+              - adi,ad7691
+              - adi,ad7942
+              - adi,ad7946
+              - adi,ad7983
+    then:
+      properties:
+        adi,sdi-pin:
+          enum: [ high, low, cs ]
+          default: cs
   # The configuration register can only be accessed if SDI is connected to MOSI
   - if:
       required:
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml
index 310f046e139f..7d2229dee444 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml
@@ -134,8 +134,9 @@ patternProperties:
         description:
           Describes the common mode channel for single channels. 0xFF is REFGND
           and OxFE is COM. Macros are available for these values in
-          dt-bindings/iio/adi,ad4695.h. Values 1 to 15 correspond to INx inputs.
-          Only odd numbered INx inputs can be used as common mode channels.
+          dt-bindings/iio/adc/adi,ad4695.h. Values 1 to 15 correspond to INx
+          inputs. Only odd numbered INx inputs can be used as common mode
+          channels.
         enum: [1, 3, 5, 7, 9, 11, 13, 15, 0xFE, 0xFF]
         default: 0xFF
 
@@ -209,7 +210,7 @@ unevaluatedProperties: false
 examples:
   - |
     #include <dt-bindings/gpio/gpio.h>
-    #include <dt-bindings/iio/adi,ad4695.h>
+    #include <dt-bindings/iio/adc/adi,ad4695.h>
 
     spi {
         #address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
index 35ed04350e28..7146a654ae38 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
@@ -37,6 +37,17 @@ properties:
     description: IRQ line for the ADC
     maxItems: 1
 
+  rdy-gpios:
+    description:
+      GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but
+      highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its
+      DOUT aka MISO role) and so usually triggers a spurious interrupt. The
+      distinction between such a spurious event and a real one can only be done
+      by reading such a GPIO. (There is a register telling the same
+      information, but accessing that one needs a SPI transfer which then
+      triggers another interrupt event.)
+    maxItems: 1
+
   '#address-cells':
     const: 1
 
@@ -111,6 +122,7 @@ unevaluatedProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     spi {
       #address-cells = <1>;
       #size-cells = <0>;
@@ -121,6 +133,7 @@ examples:
         spi-max-frequency = <5000000>;
         interrupts = <25 2>;
         interrupt-parent = <&gpio>;
+        rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>;
         refin1-supply = <&adc_vref>;
         clocks = <&ad7124_mclk>;
         clock-names = "mclk";
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml
index ad15cf9bc2ff..21ee319d4675 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7173.yaml
@@ -135,6 +135,17 @@ properties:
   '#clock-cells':
     const: 0
 
+  rdy-gpios:
+    description:
+      GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but
+      highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its
+      DOUT aka MISO role) and so usually triggers a spurious interrupt. The
+      distinction between such a spurious event and a real one can only be done
+      by reading such a GPIO. (There is a register telling the same
+      information, but accessing that one needs a SPI transfer which then
+      triggers another interrupt event.)
+    maxItems: 1
+
 patternProperties:
   "^channel@[0-9a-f]$":
     type: object
@@ -443,6 +454,7 @@ examples:
         interrupts = <25 IRQ_TYPE_EDGE_FALLING>;
         interrupt-names = "rdy";
         interrupt-parent = <&gpio>;
+        rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>;
         spi-max-frequency = <5000000>;
         gpio-controller;
         #gpio-cells = <2>;
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
index 66dd1c549bd3..0bd2c6906c83 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
@@ -106,6 +106,17 @@ properties:
     description: see Documentation/devicetree/bindings/iio/adc/adc.yaml
     type: boolean
 
+  rdy-gpios:
+    description:
+      GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but
+      highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its
+      DOUT aka MISO role) and so usually triggers a spurious interrupt. The
+      distinction between such a spurious event and a real one can only be done
+      by reading such a GPIO. (There is a register telling the same
+      information, but accessing that one needs a SPI transfer which then
+      triggers another interrupt event.)
+    maxItems: 1
+
 patternProperties:
   "^channel@[0-9a-f]+$":
     type: object
@@ -181,6 +192,7 @@ unevaluatedProperties: false
 
 examples:
   - |
+    #include <dt-bindings/gpio/gpio.h>
     spi {
         #address-cells = <1>;
         #size-cells = <0>;
@@ -195,6 +207,7 @@ examples:
             clock-names = "mclk";
             interrupts = <25 0x2>;
             interrupt-parent = <&gpio>;
+            rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>;
             aincom-supply = <&aincom>;
             dvdd-supply = <&dvdd>;
             avdd-supply = <&avdd>;
@@ -207,6 +220,7 @@ examples:
         };
     };
   - |
+    #include <dt-bindings/gpio/gpio.h>
     spi {
         #address-cells = <1>;
         #size-cells = <0>;
@@ -224,6 +238,7 @@ examples:
             #clock-cells = <0>;
             interrupts = <25 0x2>;
             interrupt-parent = <&gpio>;
+            rdy-gpios = <&gpio 25 GPIO_ACTIVE_LOW>;
             aincom-supply = <&aincom>;
             dvdd-supply = <&dvdd>;
             avdd-supply = <&avdd>;
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml
index be2616ff9af6..5c8df45bfab0 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml
@@ -63,6 +63,17 @@ properties:
       marked GPIO_ACTIVE_LOW.
     maxItems: 1
 
+  rdy-gpios:
+    description:
+      GPIO reading the R̅D̅Y̅ line. Having such a GPIO is technically optional but
+      highly recommended because DOUT/R̅D̅Y̅ toggles during SPI transfers (in its
+      DOUT aka MISO role) and so usually triggers a spurious interrupt. The
+      distinction between such a spurious event and a real one can only be done
+      by reading such a GPIO. (There is a register telling the same
+      information, but accessing that one needs a SPI transfer which then
+      triggers another interrupt event.)
+    maxItems: 1
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml b/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml
index ba86c7b7d622..40341d541726 100644
--- a/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml
@@ -17,12 +17,15 @@ description: |
 
 properties:
   compatible:
-    items:
-      - enum:
-          - renesas,r9a07g043-adc   # RZ/G2UL and RZ/Five
-          - renesas,r9a07g044-adc   # RZ/G2L
-          - renesas,r9a07g054-adc   # RZ/V2L
-      - const: renesas,rzg2l-adc
+    oneOf:
+      - items:
+          - enum:
+              - renesas,r9a07g043-adc   # RZ/G2UL and RZ/Five
+              - renesas,r9a07g044-adc   # RZ/G2L
+              - renesas,r9a07g054-adc   # RZ/V2L
+          - const: renesas,rzg2l-adc
+      - items:
+          - const: renesas,r9a08g045-adc  # RZ/G3S
 
   reg:
     maxItems: 1
@@ -57,6 +60,9 @@ properties:
   '#size-cells':
     const: 0
 
+  "#io-channel-cells":
+    const: 1
+
 required:
   - compatible
   - reg
@@ -68,7 +74,7 @@ required:
   - reset-names
 
 patternProperties:
-  "^channel@[0-7]$":
+  "^channel@[0-8]$":
     $ref: adc.yaml
     type: object
     description: |
@@ -78,6 +84,8 @@ patternProperties:
       reg:
         description: |
           The channel number.
+        minimum: 0
+        maximum: 8
 
     required:
       - reg
@@ -92,18 +100,25 @@ allOf:
             const: renesas,r9a07g043-adc
     then:
       patternProperties:
-        "^channel@[2-7]$": false
+        "^channel@[2-8]$": false
         "^channel@[0-1]$":
           properties:
             reg:
-              minimum: 0
               maximum: 1
-    else:
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,r9a07g044-adc
+              - renesas,r9a07g054-adc
+    then:
       patternProperties:
+        "^channel@[8]$": false
         "^channel@[0-7]$":
           properties:
             reg:
-              minimum: 0
               maximum: 7
 
 additionalProperties: false
diff --git a/Documentation/devicetree/bindings/iio/chemical/bosch,bme680.yaml b/Documentation/devicetree/bindings/iio/chemical/bosch,bme680.yaml
new file mode 100644
index 000000000000..fe98ec44f081
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/chemical/bosch,bme680.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/chemical/bosch,bme680.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Bosch BME680 Gas sensor
+
+maintainers:
+  - Vasileios Amoiridis <vassilisamir@gmail.com>
+
+description: >
+  BME680 is a gas sensor which combines relative humidity, barometric pressure,
+  ambient temperature and gas (VOC - Volatile Organic Compounds) measurements.
+
+  https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bme680-ds001.pdf
+
+properties:
+  compatible:
+    const: bosch,bme680
+
+  reg:
+    maxItems: 1
+
+  vdd-supply: true
+  vddio-supply: true
+
+required:
+  - compatible
+  - reg
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        co2-sensor@77 {
+            compatible = "bosch,bme680";
+            reg = <0x77>;
+            vddio-supply = <&vddio>;
+            vdd-supply = <&vdd>;
+        };
+    };
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        co2-sensor@0 {
+            compatible = "bosch,bme680";
+            reg = <0>;
+            spi-max-frequency = <500000>;
+            vddio-supply = <&vddio>;
+            vdd-supply = <&vdd>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
index 79cb4b78a88a..2bd89e0aa46b 100644
--- a/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/adi,ad5791.yaml
@@ -91,7 +91,7 @@ examples:
             vrefn-supply = <&dac_vrefn>;
             reset-gpios = <&gpio_bd 16 GPIO_ACTIVE_LOW>;
             clear-gpios = <&gpio_bd 17 GPIO_ACTIVE_LOW>;
-            ldac-gpios = <&gpio_bd 18 GPIO_ACTIVE_HIGH>;
+            ldac-gpios = <&gpio_bd 18 GPIO_ACTIVE_LOW>;
         };
     };
 ...
diff --git a/Documentation/devicetree/bindings/iio/dac/rohm,bd79703.yaml b/Documentation/devicetree/bindings/iio/dac/rohm,bd79703.yaml
new file mode 100644
index 000000000000..941a49c93943
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/dac/rohm,bd79703.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright 2024 ROHM Semiconductor.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/dac/rohm,bd79703.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ROHM BD79703 DAC device driver
+
+maintainers:
+  - Matti Vaittinen <mazziesaccount@gmail.com>
+
+description: |
+  The ROHM BD79703 is a 6 channel, 8-bit DAC.
+  Datasheet can be found here:
+  https://fscdn.rohm.com/en/products/databook/datasheet/ic/data_converter/dac/bd79702fv-lb_bd79703fv-lb-e.pdf
+
+properties:
+  compatible:
+    const: rohm,bd79703
+
+  reg:
+    maxItems: 1
+
+  spi-max-frequency:
+    maximum: 30000000
+
+  vfs-supply:
+    description:
+      The regulator to use as a full scale voltage. The voltage should be between 2.7V .. VCC
+
+  vcc-supply:
+    description:
+      The regulator supplying the operating voltage. Should be between 2.7V ... 5.5V
+
+required:
+  - compatible
+  - reg
+  - spi-max-frequency
+  - vfs-supply
+  - vcc-supply
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+additionalProperties: false
+
+examples:
+  - |
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        dac@0 {
+            compatible = "rohm,bd79703";
+            reg = <0>;
+            spi-max-frequency = <30000000>;
+            vcc-supply = <&vcc>;
+            vfs-supply = <&vref>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml b/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml
index e3eec38897bf..7a1a74fec281 100644
--- a/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/adi,adis16480.yaml
@@ -11,24 +11,30 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - adi,adis16375
-      - adi,adis16480
-      - adi,adis16485
-      - adi,adis16488
-      - adi,adis16490
-      - adi,adis16495-1
-      - adi,adis16495-2
-      - adi,adis16495-3
-      - adi,adis16497-1
-      - adi,adis16497-2
-      - adi,adis16497-3
-      - adi,adis16545-1
-      - adi,adis16545-2
-      - adi,adis16545-3
-      - adi,adis16547-1
-      - adi,adis16547-2
-      - adi,adis16547-3
+    oneOf:
+      - enum:
+          - adi,adis16375
+          - adi,adis16480
+          - adi,adis16485
+          - adi,adis16486
+          - adi,adis16488
+          - adi,adis16489
+          - adi,adis16490
+          - adi,adis16495-1
+          - adi,adis16495-2
+          - adi,adis16495-3
+          - adi,adis16497-1
+          - adi,adis16497-2
+          - adi,adis16497-3
+          - adi,adis16545-1
+          - adi,adis16545-2
+          - adi,adis16545-3
+          - adi,adis16547-1
+          - adi,adis16547-2
+          - adi,adis16547-3
+      - items:
+          - const: adi,adis16487
+          - const: adi,adis16485
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml
index 3b0a2d8b2e91..2cf8a0c7eb4c 100644
--- a/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi160.yaml
@@ -37,6 +37,7 @@ properties:
       to "INT2" if INT2 pin should be used instead
 
   drive-open-drain:
+    type: boolean
     description: |
       set if the specified interrupt pin should be configured as
       open drain. If not set, defaults to push-pull.
diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml
index 7b0cde1c9b0a..860a6c1fea3c 100644
--- a/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi270.yaml
@@ -41,6 +41,7 @@ properties:
         - INT2
 
   drive-open-drain:
+    type: boolean
     description:
       set if the specified interrupt pins should be configured as
       open drain. If not set, defaults to push-pull.
diff --git a/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
index 64ef26e19669..7bf8294a8f2e 100644
--- a/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/bosch,bmi323.yaml
@@ -38,6 +38,7 @@ properties:
         - INT2
 
   drive-open-drain:
+    type: boolean
     description:
       set if the specified interrupt pin should be configured as
       open drain. If not set, defaults to push-pull.
diff --git a/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml b/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml
index f91954870a44..0bce71529e34 100644
--- a/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml
+++ b/Documentation/devicetree/bindings/iio/imu/invensense,mpu6050.yaml
@@ -16,6 +16,7 @@ properties:
   compatible:
     oneOf:
       - enum:
+          - invensense,iam20380
           - invensense,iam20680
           - invensense,icm20608
           - invensense,icm20609
diff --git a/Documentation/devicetree/bindings/iio/light/rohm,bu27008.yaml b/Documentation/devicetree/bindings/iio/light/rohm,bu27008.yaml
deleted file mode 100644
index 4f66fd47b016..000000000000
--- a/Documentation/devicetree/bindings/iio/light/rohm,bu27008.yaml
+++ /dev/null
@@ -1,49 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/iio/light/rohm,bu27008.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: ROHM BU27008 color sensor
-
-maintainers:
-  - Matti Vaittinen <mazziesaccount@gmail.com>
-
-description:
-  The ROHM BU27008 is a sensor with 5 photodiodes (red, green, blue, clear
-  and IR) with four configurable channels. Red and green being always
-  available and two out of the rest three (blue, clear, IR) can be
-  selected to be simultaneously measured. Typical application is adjusting
-  LCD backlight of TVs, mobile phones and tablet PCs.
-
-properties:
-  compatible:
-    const: rohm,bu27008
-
-  reg:
-    maxItems: 1
-
-  interrupts:
-    maxItems: 1
-
-  vdd-supply: true
-
-required:
-  - compatible
-  - reg
-
-additionalProperties: false
-
-examples:
-  - |
-    i2c {
-      #address-cells = <1>;
-      #size-cells = <0>;
-
-      light-sensor@38 {
-        compatible = "rohm,bu27008";
-        reg = <0x38>;
-      };
-    };
-
-...
diff --git a/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml b/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml
deleted file mode 100644
index bed42d5d0d94..000000000000
--- a/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml
+++ /dev/null
@@ -1,50 +0,0 @@
-# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/iio/light/rohm,bu27010.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: ROHM BU27010 color sensor
-
-maintainers:
-  - Matti Vaittinen <mazziesaccount@gmail.com>
-
-description: |
-  The ROHM BU27010 is a sensor with 6 photodiodes (red, green, blue, clear,
-  IR and flickering detection) with five configurable channels. Red, green
-  and flickering detection being always available and two out of the rest
-  three (blue, clear, IR) can be selected to be simultaneously measured.
-  Typical application is adjusting LCD/OLED backlight of TVs, mobile phones
-  and tablet PCs.
-
-properties:
-  compatible:
-    const: rohm,bu27010
-
-  reg:
-    maxItems: 1
-
-  interrupts:
-    maxItems: 1
-
-  vdd-supply: true
-
-required:
-  - compatible
-  - reg
-  - vdd-supply
-
-additionalProperties: false
-
-examples:
-  - |
-    i2c {
-      #address-cells = <1>;
-      #size-cells = <0>;
-
-      light-sensor@38 {
-        compatible = "rohm,bu27010";
-        reg = <0x38>;
-        vdd-supply = <&vdd>;
-      };
-    };
diff --git a/Documentation/devicetree/bindings/iio/light/ti,opt4060.yaml b/Documentation/devicetree/bindings/iio/light/ti,opt4060.yaml
new file mode 100644
index 000000000000..568fb2a9b7a3
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/ti,opt4060.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/light/ti,opt4060.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments OPT4060 RGBW Color Sensor
+
+maintainers:
+  - Per-Daniel Olsson <perdaniel.olsson@axis.com>
+
+description:
+  Texas Instrument RGBW high resolution color sensor over I2C.
+  https://www.ti.com/lit/gpn/opt4060
+
+properties:
+  compatible:
+    enum:
+      - ti,opt4060
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  vdd-supply: true
+
+required:
+  - compatible
+  - reg
+  - vdd-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        light-sensor@44 {
+            compatible = "ti,opt4060";
+            reg = <0x44>;
+            vdd-supply = <&vdd_reg>;
+            interrupt-parent = <&gpio5>;
+            interrupts = <13 IRQ_TYPE_EDGE_FALLING>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml b/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml
index cb201cecfa1a..706b7e24f182 100644
--- a/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml
+++ b/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml
@@ -55,12 +55,16 @@ properties:
       If not set, defaults to push-pull configuration.
     type: boolean
 
+  spi-max-frequency:
+    maximum: 10000000
+
 required:
   - compatible
   - vddd-supply
   - vdda-supply
 
 allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
   - if:
       properties:
         compatible:
@@ -73,6 +77,16 @@ allOf:
     then:
       properties:
         interrupts: false
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - bosch,bmp085
+              - bosch,bmp180
+    then:
+      properties:
+        spi-max-frequency: false
 
 additionalProperties: false
 
@@ -93,3 +107,18 @@ examples:
             vdda-supply = <&bar>;
         };
     };
+  - |
+    # include <dt-bindings/gpio/gpio.h>
+    # include <dt-bindings/interrupt-controller/irq.h>
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        pressure@0 {
+            compatible = "bosch,bmp280";
+            reg = <0>;
+            spi-max-frequency = <10000000>;
+            reset-gpios = <&gpio0 26 GPIO_ACTIVE_LOW>;
+            vddd-supply = <&foo>;
+            vdda-supply = <&bar>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
index ff24b5ee2c66..83bcf0575cd3 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml
@@ -38,6 +38,7 @@ properties:
               - qcom,sm8250-cpu-bwmon
               - qcom,sm8550-cpu-bwmon
               - qcom,sm8650-cpu-bwmon
+              - qcom,sm8750-cpu-bwmon
               - qcom,x1e80100-cpu-bwmon
           - const: qcom,sdm845-bwmon    # BWMON v4, unified register space
       - items:
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml
index 21dae0b92819..4ac0863205b3 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml
@@ -33,6 +33,7 @@ properties:
               - qcom,sm6375-cpucp-l3
               - qcom,sm8250-epss-l3
               - qcom,sm8350-epss-l3
+              - qcom,sm8650-epss-l3
           - const: qcom,epss-l3
 
   reg:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml b/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml
index b2adc7174177..dca16e202da9 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml
@@ -14,9 +14,8 @@ allOf:
 
 description: |
   The Microchip LAN966x outband interrupt controller (OIC) maps the internal
-  interrupt sources of the LAN966x device to an external interrupt.
-  When the LAN966x device is used as a PCI device, the external interrupt is
-  routed to the PCI interrupt.
+  interrupt sources of the LAN966x device to a PCI interrupt when the LAN966x
+  device is used as a PCI device.
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml
index f117471fb06f..e7ee0d9efed8 100644
--- a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml
+++ b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml
@@ -22,12 +22,12 @@ properties:
     oneOf:
       - items:
           - enum:
-              - qcom,qcs8300-ethqos
-          - const: qcom,sa8775p-ethqos
+              - qcom,qcs615-ethqos
+          - const: qcom,qcs404-ethqos
       - items:
           - enum:
-              - qcom,qcs615-ethqos
-          - const: qcom,sm8150-ethqos
+              - qcom,qcs8300-ethqos
+          - const: qcom,sa8775p-ethqos
       - enum:
           - qcom,qcs404-ethqos
           - qcom,sa8775p-ethqos
diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
index 38e0d50f0e1c..d37f544ab8aa 100644
--- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
+++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
@@ -20,12 +20,14 @@ properties:
           - qcom,apq8064-qfprom
           - qcom,apq8084-qfprom
           - qcom,ipq5332-qfprom
+          - qcom,ipq5424-qfprom
           - qcom,ipq6018-qfprom
           - qcom,ipq8064-qfprom
           - qcom,ipq8074-qfprom
           - qcom,ipq9574-qfprom
           - qcom,msm8226-qfprom
           - qcom,msm8916-qfprom
+          - qcom,msm8917-qfprom
           - qcom,msm8974-qfprom
           - qcom,msm8976-qfprom
           - qcom,msm8996-qfprom
@@ -33,6 +35,7 @@ properties:
           - qcom,qcm2290-qfprom
           - qcom,qcs404-qfprom
           - qcom,qcs615-qfprom
+          - qcom,qcs8300-qfprom
           - qcom,sc7180-qfprom
           - qcom,sc7280-qfprom
           - qcom,sc8280xp-qfprom
diff --git a/Documentation/devicetree/bindings/nvmem/rmem.yaml b/Documentation/devicetree/bindings/nvmem/rmem.yaml
index 1ec0d09bcafa..85f9f5de3906 100644
--- a/Documentation/devicetree/bindings/nvmem/rmem.yaml
+++ b/Documentation/devicetree/bindings/nvmem/rmem.yaml
@@ -16,6 +16,7 @@ properties:
   compatible:
     items:
       - enum:
+          - mobileye,eyeq5-bootloader-config
           - raspberrypi,bootloader-config
           - raspberrypi,bootloader-public-key
       - const: nvmem-rmem
diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml
index d3cd7997879f..1b3de6678c08 100644
--- a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml
@@ -13,6 +13,7 @@ properties:
   compatible:
     enum:
       - rockchip,rk3568-naneng-combphy
+      - rockchip,rk3576-naneng-combphy
       - rockchip,rk3588-naneng-combphy
 
   reg:
diff --git a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml
index 58ce2d91d28c..f60804687412 100644
--- a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml
@@ -15,12 +15,21 @@ description:
 
 properties:
   compatible:
-    enum:
-      - qcom,ipq6018-qmp-pcie-phy
-      - qcom,ipq8074-qmp-gen3-pcie-phy
-      - qcom,ipq8074-qmp-pcie-phy
-      - qcom,ipq9574-qmp-gen3x1-pcie-phy
-      - qcom,ipq9574-qmp-gen3x2-pcie-phy
+    oneOf:
+      - enum:
+          - qcom,ipq6018-qmp-pcie-phy
+          - qcom,ipq8074-qmp-gen3-pcie-phy
+          - qcom,ipq8074-qmp-pcie-phy
+          - qcom,ipq9574-qmp-gen3x1-pcie-phy
+          - qcom,ipq9574-qmp-gen3x2-pcie-phy
+      - items:
+          - enum:
+              - qcom,ipq5424-qmp-gen3x1-pcie-phy
+          - const: qcom,ipq9574-qmp-gen3x1-pcie-phy
+      - items:
+          - enum:
+              - qcom,ipq5424-qmp-gen3x2-pcie-phy
+          - const: qcom,ipq9574-qmp-gen3x2-pcie-phy
 
   reg:
     items:
diff --git a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml
index 4aed4b5d65ec..39851ba9de43 100644
--- a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml
@@ -18,6 +18,7 @@ properties:
     oneOf:
       - items:
           - enum:
+              - qcom,ipq5424-qusb2-phy
               - qcom,ipq6018-qusb2-phy
               - qcom,ipq8074-qusb2-phy
               - qcom,ipq9574-qusb2-phy
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index 13fdf5f1beba..89391649e0b5 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -16,8 +16,10 @@ description:
 properties:
   compatible:
     enum:
+      - qcom,qcs615-qmp-gen3x1-pcie-phy
       - qcom,sa8775p-qmp-gen4x2-pcie-phy
       - qcom,sa8775p-qmp-gen4x4-pcie-phy
+      - qcom,sar2130p-qmp-gen3x2-pcie-phy
       - qcom,sc8180x-qmp-pcie-phy
       - qcom,sc8280xp-qmp-gen3x1-pcie-phy
       - qcom,sc8280xp-qmp-gen3x2-pcie-phy
@@ -32,6 +34,7 @@ properties:
       - qcom,sm8250-qmp-gen3x2-pcie-phy
       - qcom,sm8250-qmp-modem-pcie-phy
       - qcom,sm8350-qmp-gen3x1-pcie-phy
+      - qcom,sm8350-qmp-gen3x2-pcie-phy
       - qcom,sm8450-qmp-gen3x1-pcie-phy
       - qcom,sm8450-qmp-gen4x2-pcie-phy
       - qcom,sm8550-qmp-gen3x2-pcie-phy
@@ -139,6 +142,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,sar2130p-qmp-gen3x2-pcie-phy
               - qcom,sc8180x-qmp-pcie-phy
               - qcom,sdm845-qhp-pcie-phy
               - qcom,sdm845-qmp-pcie-phy
@@ -149,6 +153,7 @@ allOf:
               - qcom,sm8250-qmp-gen3x2-pcie-phy
               - qcom,sm8250-qmp-modem-pcie-phy
               - qcom,sm8350-qmp-gen3x1-pcie-phy
+              - qcom,sm8350-qmp-gen3x2-pcie-phy
               - qcom,sm8450-qmp-gen3x1-pcie-phy
               - qcom,sm8450-qmp-gen3x2-pcie-phy
               - qcom,sm8550-qmp-gen3x2-pcie-phy
@@ -167,6 +172,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,qcs615-qmp-gen3x1-pcie-phy
               - qcom,sc8280xp-qmp-gen3x1-pcie-phy
               - qcom,sc8280xp-qmp-gen3x2-pcie-phy
               - qcom,sc8280xp-qmp-gen3x4-pcie-phy
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
index baf5134ea3d8..a1b55168e050 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
@@ -16,6 +16,7 @@ description:
 properties:
   compatible:
     enum:
+      - qcom,ipq5424-qmp-usb3-phy
       - qcom,ipq6018-qmp-usb3-phy
       - qcom,ipq8074-qmp-usb3-phy
       - qcom,ipq9574-qmp-usb3-phy
@@ -89,6 +90,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,ipq5424-qmp-usb3-phy
               - qcom,ipq6018-qmp-usb3-phy
               - qcom,ipq8074-qmp-usb3-phy
               - qcom,ipq9574-qmp-usb3-phy
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
index 2d0d7e9e6431..358a6736a951 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml
@@ -16,6 +16,7 @@ description:
 properties:
   compatible:
     enum:
+      - qcom,sar2130p-qmp-usb3-dp-phy
       - qcom,sc7180-qmp-usb3-dp-phy
       - qcom,sc7280-qmp-usb3-dp-phy
       - qcom,sc8180x-qmp-usb3-dp-phy
@@ -127,6 +128,7 @@ allOf:
       properties:
         compatible:
           enum:
+            - qcom,sar2130p-qmp-usb3-dp-phy
             - qcom,sc8280xp-qmp-usb43dp-phy
             - qcom,sm6350-qmp-usb3-dp-phy
             - qcom,sm8550-qmp-usb3-dp-phy
diff --git a/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml b/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml
index 8c58e12cdb60..0735ceb7c103 100644
--- a/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml
+++ b/Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml
@@ -22,6 +22,9 @@ properties:
       - enum:
           - atmel,sama5d2-shdwc
           - microchip,sam9x60-shdwc
+      - items:
+          - const: microchip,sam9x7-shdwc
+          - const: microchip,sam9x60-shdwc
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/power/supply/bq24190.yaml b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
index 131b7e57d22f..07adf88997b4 100644
--- a/Documentation/devicetree/bindings/power/supply/bq24190.yaml
+++ b/Documentation/devicetree/bindings/power/supply/bq24190.yaml
@@ -21,6 +21,7 @@ properties:
       - ti,bq24192i
       - ti,bq24196
       - ti,bq24296
+      - ti,bq24297
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml b/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml
index 89f8e2bcb2d7..25826bfc289c 100644
--- a/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml
+++ b/Documentation/devicetree/bindings/power/supply/gpio-charger.yaml
@@ -58,6 +58,10 @@ properties:
             charge-current-limit-gpios property. Bit 1 second to last
             GPIO and so on.
 
+  charge-current-limit-default-microamp:
+    description: Default charge current limit. Must be listed in
+      charge-current-limit-mapping.
+
 required:
   - compatible
 
@@ -72,6 +76,7 @@ anyOf:
 dependencies:
   charge-current-limit-gpios: [ charge-current-limit-mapping ]
   charge-current-limit-mapping: [ charge-current-limit-gpios ]
+  charge-current-limit-default-microamp: [charge-current-limit-mapping]
 
 additionalProperties: false
 
@@ -91,4 +96,5 @@ examples:
       charge-current-limit-mapping = <2500000 0x00>, // 2.5 A => both GPIOs low
                                      <700000 0x01>, // 700 mA => GPIO A.12 high
                                      <0 0x02>; // 0 mA => GPIO A.11 high
+      charge-current-limit-default-microamp = <700000>;
     };
diff --git a/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml b/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml
index 29d536541152..06595a953659 100644
--- a/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml
+++ b/Documentation/devicetree/bindings/power/supply/ltc4162-l.yaml
@@ -17,12 +17,18 @@ description: |
   panels, etc., and a rechargeable Lithium-Ion/Polymer battery.
 
   Specifications about the charger can be found at:
+    https://www.analog.com/en/products/ltc4162-l.html
+    https://www.analog.com/en/products/ltc4162-f.html
     https://www.analog.com/en/products/ltc4162-s.html
+    https://www.analog.com/en/products/ltc4015.html
 
 properties:
   compatible:
     enum:
+      - lltc,ltc4015
+      - lltc,ltc4162-f
       - lltc,ltc4162-l
+      - lltc,ltc4162-s
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml b/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml
index 085e2504d0dc..14242de7fc08 100644
--- a/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml
+++ b/Documentation/devicetree/bindings/power/supply/maxim,max17042.yaml
@@ -19,6 +19,7 @@ properties:
       - maxim,max17047
       - maxim,max17050
       - maxim,max17055
+      - maxim,max77705-battery
       - maxim,max77849-battery
 
   reg:
diff --git a/Documentation/devicetree/bindings/power/supply/st,stc3117.yaml b/Documentation/devicetree/bindings/power/supply/st,stc3117.yaml
new file mode 100644
index 000000000000..e486131a27a9
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/st,stc3117.yaml
@@ -0,0 +1,74 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/power/supply/st,stc3117.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STC3117 Fuel Gauge Unit Power Supply
+
+maintainers:
+  - Hardevsinh Palaniya <hardevsinh.palaniya@siliconsignals.io>
+  - Bhavin Sharma <bhavin.sharma@siliconsignals.io>
+
+description: |
+  The STC3117 includes the STMicroelectronics OptimGauge algorithm.
+  It provides accurate battery state-of-charge (SOC) monitoring, tracks
+  battery parameter changes with operation conditions, temperature,
+  and aging, and allows the application to get a battery state-of-health
+  (SOH) indication.
+
+  An alarm output signals low SOC or low voltage conditions and also
+  indicates fault conditions like a missing or swapped battery.
+
+  Datasheet is available at
+  https://www.st.com/resource/en/datasheet/stc3117.pdf
+
+allOf:
+  - $ref: power-supply.yaml#
+
+properties:
+  compatible:
+    enum:
+      - st,stc3117
+
+  reg:
+    maxItems: 1
+
+  monitored-battery:
+    description: |
+      The fuel gauge uses the following battery properties:
+      - charge-full-design-microamp-hours
+      - voltage-min-design-microvolt
+      - voltage-max-design-microvolt
+
+  shunt-resistor-micro-ohms:
+    description: Current sense resistor
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - monitored-battery
+  - shunt-resistor-micro-ohms
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    i2c {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      battery@70 {
+        compatible = "st,stc3117";
+        reg = <0x70>;
+        interrupt-parent = <&gpio0>;
+        interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
+        monitored-battery = <&bat>;
+        shunt-resistor-micro-ohms = <10000>;
+      };
+    };
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index acb5b9ba6f04..2c72f148a74b 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -26,6 +26,18 @@ description: |
 allOf:
   - $ref: /schemas/cpu.yaml#
   - $ref: extensions.yaml
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - thead,c906
+                - thead,c910
+                - thead,c920
+    then:
+      properties:
+        thead,vlenb: false
 
 properties:
   compatible:
@@ -96,6 +108,13 @@ properties:
     description:
       The blocksize in bytes for the Zicboz cache operations.
 
+  thead,vlenb:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      VLEN/8, the vector register length in bytes. This property is required on
+      thead systems where the vector register length is not identical on all harts, or
+      the vlenb CSR is not available.
+
   # RISC-V has multiple properties for cache op block sizes as the sizes
   # differ between individual CBO extensions
   cache-op-block-size: false
diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml
index 9c7dd7e75e0c..a63b994e0763 100644
--- a/Documentation/devicetree/bindings/riscv/extensions.yaml
+++ b/Documentation/devicetree/bindings/riscv/extensions.yaml
@@ -621,6 +621,10 @@ properties:
             latency, as ratified in commit 56ed795 ("Update
             riscv-crypto-spec-vector.adoc") of riscv-crypto.
 
+        # vendor extensions, each extension sorted alphanumerically under the
+        # vendor they belong to. Vendors are sorted alphanumerically as well.
+
+        # Andes
         - const: xandespmu
           description:
             The Andes Technology performance monitor extension for counter overflow
@@ -628,6 +632,12 @@ properties:
             Registers in the AX45MP datasheet.
             https://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf
 
+        # T-HEAD
+        - const: xtheadvector
+          description:
+            The T-HEAD specific 0.7.1 vector implementation as written in
+            https://github.com/T-head-Semi/thead-extension-spec/blob/95358cb2cca9489361c61d335e03d3134b14133f/xtheadvector.adoc.
+
     allOf:
       # Zcb depends on Zca
       - if:
diff --git a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml
index a14b52178c4b..2599b847f406 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml
+++ b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml
@@ -14,9 +14,13 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - fsl,imx1-rtc
-      - fsl,imx21-rtc
+    oneOf:
+      - const: fsl,imx1-rtc
+      - const: fsl,imx21-rtc
+      - items:
+          - enum:
+              - fsl,imx31-rtc
+          - const: fsl,imx21-rtc
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml
index 88871480018e..ab39b95dae40 100644
--- a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml
+++ b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.yaml
@@ -23,6 +23,8 @@ properties:
     maxItems: 1
 
   interrupts:
+    description:
+      When missing, device driver uses polling instead.
     maxItems: 1
 
   clocks:
@@ -76,7 +78,6 @@ properties:
 required:
   - compatible
   - reg
-  - interrupts
 
 allOf:
   - $ref: /schemas/spi/spi-peripheral-props.yaml#
diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml
index 51d9fb0f4763..8e82999e6acb 100644
--- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml
+++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml
@@ -83,6 +83,11 @@ properties:
 
       - const: renesas,scif-r9a09g057       # RZ/V2H(P)
 
+      - items:
+          - enum:
+              - renesas,scif-r9a09g047      # RZ/G3E
+          - const: renesas,scif-r9a09g057   # RZ/V2H fallback
+
   reg:
     maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml b/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml
index 5aa00617291c..1f0e6787a746 100644
--- a/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml
+++ b/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml
@@ -4,7 +4,7 @@
 $id: http://devicetree.org/schemas/sound/ti,pcm1681.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Texas Instruments PCM1681 8-channel PWM Processor
+title: Texas Instruments PCM1681 8-channel Digital-to-Analog Converter
 
 maintainers:
   - Shenghao Ding <shenghao-ding@ti.com>
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 6bdcd055e763..fadbd3c041c8 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -55,8 +55,6 @@ properties:
           - atmel,atsha204a
             # BPA-RS600: Power Supply
           - blutek,bpa-rs600
-            # Bosch Sensortec pressure, temperature, humididty and VOC sensor
-          - bosch,bme680
             # CM32181: Ambient Light Sensor
           - capella,cm32181
             # CM3232: Ambient Light Sensor
@@ -147,6 +145,8 @@ properties:
           - injoinic,ip5207
             # Injoinic IP5209 2.4A Power Bank IC with I2C
           - injoinic,ip5209
+            # Injoinic IP5306 2.1A Power Bank IC with I2C option
+          - injoinic,ip5306
             # Inspur Power System power supply unit version 1
           - inspur,ipsps1
             # Intel common redudant power supply crps185
diff --git a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml
index a86bcd95100e..7f22f9c031b2 100644
--- a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml
+++ b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml
@@ -113,27 +113,27 @@ examples:
   - |
     #include <dt-bindings/clock/aspeed-clock.h>
     vhub: usb-vhub@1e6a0000 {
-            compatible = "aspeed,ast2500-usb-vhub";
-            reg = <0x1e6a0000 0x300>;
-            interrupts = <5>;
-            clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>;
-            aspeed,vhub-downstream-ports = <5>;
-            aspeed,vhub-generic-endpoints = <15>;
-            pinctrl-names = "default";
-            pinctrl-0 = <&pinctrl_usb2ad_default>;
-
-            vhub-vendor-id = <0x1d6b>;
-            vhub-product-id = <0x0107>;
-            vhub-device-revision = <0x0100>;
-            vhub-strings {
-                #address-cells = <1>;
-                #size-cells = <0>;
-
-                string@409 {
-                        reg = <0x409>;
-                        manufacturer = "ASPEED";
-                        product = "USB Virtual Hub";
-                        serial-number = "0000";
-                };
+        compatible = "aspeed,ast2500-usb-vhub";
+        reg = <0x1e6a0000 0x300>;
+        interrupts = <5>;
+        clocks = <&syscon ASPEED_CLK_GATE_USBPORT1CLK>;
+        aspeed,vhub-downstream-ports = <5>;
+        aspeed,vhub-generic-endpoints = <15>;
+        pinctrl-names = "default";
+        pinctrl-0 = <&pinctrl_usb2ad_default>;
+
+        vhub-vendor-id = <0x1d6b>;
+        vhub-product-id = <0x0107>;
+        vhub-device-revision = <0x0100>;
+        vhub-strings {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            string@409 {
+                reg = <0x409>;
+                manufacturer = "ASPEED";
+                product = "USB Virtual Hub";
+                serial-number = "0000";
             };
+        };
     };
diff --git a/Documentation/devicetree/bindings/usb/brcm,bdc.yaml b/Documentation/devicetree/bindings/usb/brcm,bdc.yaml
index 9e561fee98f1..f9375c69e86b 100644
--- a/Documentation/devicetree/bindings/usb/brcm,bdc.yaml
+++ b/Documentation/devicetree/bindings/usb/brcm,bdc.yaml
@@ -41,10 +41,10 @@ additionalProperties: false
 
 examples:
   - |
-        usb@f0b02000 {
-                compatible = "brcm,bdc-udc-v2";
-                reg = <0xf0b02000 0xfc4>;
-                interrupts = <0x0 0x60 0x0>;
-                phys = <&usbphy_0 0x0>;
-                clocks = <&sw_usbd>;
-        };
+    usb@f0b02000 {
+        compatible = "brcm,bdc-udc-v2";
+        reg = <0xf0b02000 0xfc4>;
+        interrupts = <0x0 0x60 0x0>;
+        phys = <&usbphy_0 0x0>;
+        clocks = <&sw_usbd>;
+    };
diff --git a/Documentation/devicetree/bindings/usb/cypress,hx3.yaml b/Documentation/devicetree/bindings/usb/cypress,hx3.yaml
index e44e88d993d0..1033b7a4b8f9 100644
--- a/Documentation/devicetree/bindings/usb/cypress,hx3.yaml
+++ b/Documentation/devicetree/bindings/usb/cypress,hx3.yaml
@@ -56,21 +56,21 @@ examples:
 
         /* 2.0 hub on port 1 */
         hub_2_0: hub@1 {
-          compatible = "usb4b4,6504";
-          reg = <1>;
-          peer-hub = <&hub_3_0>;
-          reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
-          vdd-supply = <&reg_1v2_usb>;
-          vdd2-supply = <&reg_3v3_usb>;
+            compatible = "usb4b4,6504";
+            reg = <1>;
+            peer-hub = <&hub_3_0>;
+            reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
+            vdd-supply = <&reg_1v2_usb>;
+            vdd2-supply = <&reg_3v3_usb>;
         };
 
         /* 3.0 hub on port 2 */
         hub_3_0: hub@2 {
-          compatible = "usb4b4,6506";
-          reg = <2>;
-          peer-hub = <&hub_2_0>;
-          reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
-          vdd-supply = <&reg_1v2_usb>;
-          vdd2-supply = <&reg_3v3_usb>;
+            compatible = "usb4b4,6506";
+            reg = <2>;
+            peer-hub = <&hub_2_0>;
+            reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
+            vdd-supply = <&reg_1v2_usb>;
+            vdd2-supply = <&reg_3v3_usb>;
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/dwc2.yaml b/Documentation/devicetree/bindings/usb/dwc2.yaml
index a5f2e3442a0e..e83d30a91b88 100644
--- a/Documentation/devicetree/bindings/usb/dwc2.yaml
+++ b/Documentation/devicetree/bindings/usb/dwc2.yaml
@@ -192,7 +192,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-      usb@101c0000 {
+    usb@101c0000 {
         compatible = "rockchip,rk3066-usb", "snps,dwc2";
         reg = <0x10180000 0x40000>;
         interrupts = <18>;
@@ -200,6 +200,6 @@ examples:
         clock-names = "otg";
         phys = <&usbphy>;
         phy-names = "usb2-phy";
-      };
+    };
 
 ...
diff --git a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml
index 8b25b9a01ced..e3a7df91f7f1 100644
--- a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml
+++ b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml
@@ -87,21 +87,21 @@ examples:
         #size-cells = <0>;
 
         typec-mux@42 {
-          compatible = "fcs,fsa4480";
-          reg = <0x42>;
+            compatible = "fcs,fsa4480";
+            reg = <0x42>;
 
-          interrupts-extended = <&tlmm 2 IRQ_TYPE_LEVEL_LOW>;
+            interrupts-extended = <&tlmm 2 IRQ_TYPE_LEVEL_LOW>;
 
-          vcc-supply = <&vreg_bob>;
+            vcc-supply = <&vreg_bob>;
 
-          mode-switch;
-          orientation-switch;
+            mode-switch;
+            orientation-switch;
 
-          port {
-            fsa4480_ept: endpoint {
-              remote-endpoint = <&typec_controller>;
+            port {
+                fsa4480_ept: endpoint {
+                    remote-endpoint = <&typec_controller>;
+                };
             };
-          };
         };
     };
 ...
diff --git a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml
index 8a5f837eff94..e588514fab2d 100644
--- a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml
+++ b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml
@@ -20,6 +20,7 @@ properties:
     items:
       - enum:
           - nxp,cbdtu02043
+          - onnn,fsusb42
           - onnn,fsusb43l10x
           - pericom,pi3usb102
           - ti,tmuxhs4212
diff --git a/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml b/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml
index d3511f48cd55..1a75544a8c31 100644
--- a/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/intel,keembay-dwc3.yaml
@@ -58,20 +58,20 @@ examples:
     #define KEEM_BAY_A53_AUX_USB_SUSPEND
 
     usb {
-          compatible = "intel,keembay-dwc3";
-          clocks = <&scmi_clk KEEM_BAY_A53_AUX_USB>,
-                   <&scmi_clk KEEM_BAY_A53_AUX_USB_REF>,
-                   <&scmi_clk KEEM_BAY_A53_AUX_USB_ALT_REF>,
-                   <&scmi_clk KEEM_BAY_A53_AUX_USB_SUSPEND>;
-          clock-names = "async_master", "ref", "alt_ref", "suspend";
-          ranges;
-          #address-cells = <1>;
-          #size-cells = <1>;
-
-          usb@34000000 {
-                compatible = "snps,dwc3";
-                reg = <0x34000000 0x10000>;
-                interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
-                dr_mode = "peripheral";
-          };
+        compatible = "intel,keembay-dwc3";
+        clocks = <&scmi_clk KEEM_BAY_A53_AUX_USB>,
+                 <&scmi_clk KEEM_BAY_A53_AUX_USB_REF>,
+                 <&scmi_clk KEEM_BAY_A53_AUX_USB_ALT_REF>,
+                 <&scmi_clk KEEM_BAY_A53_AUX_USB_SUSPEND>;
+        clock-names = "async_master", "ref", "alt_ref", "suspend";
+        ranges;
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        usb@34000000 {
+            compatible = "snps,dwc3";
+            reg = <0x34000000 0x10000>;
+            interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
+            dr_mode = "peripheral";
+        };
     };
diff --git a/Documentation/devicetree/bindings/usb/ite,it5205.yaml b/Documentation/devicetree/bindings/usb/ite,it5205.yaml
index 36ec4251b5f2..889710733de5 100644
--- a/Documentation/devicetree/bindings/usb/ite,it5205.yaml
+++ b/Documentation/devicetree/bindings/usb/ite,it5205.yaml
@@ -54,19 +54,19 @@ examples:
         #size-cells = <0>;
 
         typec-mux@48 {
-          compatible = "ite,it5205";
-          reg = <0x48>;
+            compatible = "ite,it5205";
+            reg = <0x48>;
 
-          mode-switch;
-          orientation-switch;
+            mode-switch;
+            orientation-switch;
 
-          vcc-supply = <&mt6359_vibr_ldo_reg>;
+            vcc-supply = <&mt6359_vibr_ldo_reg>;
 
-          port {
-            it5205_usbss_sbu: endpoint {
-              remote-endpoint = <&typec_controller>;
+            port {
+                it5205_usbss_sbu: endpoint {
+                    remote-endpoint = <&typec_controller>;
+                };
             };
-          };
         };
     };
 ...
diff --git a/Documentation/devicetree/bindings/usb/maxim,max33359.yaml b/Documentation/devicetree/bindings/usb/maxim,max33359.yaml
index 20b62228371b..3de4dc40b791 100644
--- a/Documentation/devicetree/bindings/usb/maxim,max33359.yaml
+++ b/Documentation/devicetree/bindings/usb/maxim,max33359.yaml
@@ -13,8 +13,12 @@ description: Maxim TCPCI Type-C PD controller
 
 properties:
   compatible:
-    enum:
-      - maxim,max33359
+    oneOf:
+      - enum:
+          - maxim,max33359
+      - items:
+          - const: maxim,max77759-tcpci
+          - const: maxim,max33359
 
   reg:
     maxItems: 1
@@ -70,6 +74,7 @@ examples:
                                        PDO_FIXED_DUAL_ROLE)
                                        PDO_FIXED(9000, 2000, 0)>;
                 sink-bc12-completion-time-ms = <500>;
+                pd-revision = /bits/ 8 <0x03 0x01 0x01 0x08>;
             };
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml b/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml
index 8e0f4ecc010d..6edb1fc5044e 100644
--- a/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml
+++ b/Documentation/devicetree/bindings/usb/maxim,max3420-udc.yaml
@@ -50,18 +50,18 @@ additionalProperties: false
 
 examples:
   - |
-      #include <dt-bindings/gpio/gpio.h>
-      #include <dt-bindings/interrupt-controller/irq.h>
-      spi {
-            #address-cells = <1>;
-            #size-cells = <0>;
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
 
-            udc@0 {
-                  compatible = "maxim,max3420-udc";
-                  reg = <0>;
-                  interrupt-parent = <&gpio>;
-                  interrupts = <0 IRQ_TYPE_EDGE_FALLING>, <10 IRQ_TYPE_EDGE_BOTH>;
-                  interrupt-names = "udc", "vbus";
-                  spi-max-frequency = <12500000>;
-            };
-      };
+        udc@0 {
+            compatible = "maxim,max3420-udc";
+            reg = <0>;
+            interrupt-parent = <&gpio>;
+            interrupts = <0 IRQ_TYPE_EDGE_FALLING>, <10 IRQ_TYPE_EDGE_BOTH>;
+            interrupt-names = "udc", "vbus";
+            spi-max-frequency = <12500000>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml b/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml
index 90296613b3a5..c0e313c70bba 100644
--- a/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml
+++ b/Documentation/devicetree/bindings/usb/nvidia,tegra210-xusb.yaml
@@ -189,7 +189,7 @@ examples:
         #size-cells = <0>;
 
         ethernet@1 {
-                compatible = "usb955,9ff";
-                reg = <1>;
+            compatible = "usb955,9ff";
+            reg = <1>;
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
index 2622a1f3bcab..a2b3cf625e5b 100644
--- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml
@@ -27,6 +27,7 @@ properties:
           - qcom,msm8998-dwc3
           - qcom,qcm2290-dwc3
           - qcom,qcs404-dwc3
+          - qcom,qcs615-dwc3
           - qcom,qcs8300-dwc3
           - qcom,qdu1000-dwc3
           - qcom,sa8775p-dwc3
@@ -342,6 +343,7 @@ allOf:
           contains:
             enum:
               - qcom,qcm2290-dwc3
+              - qcom,qcs615-dwc3
               - qcom,sar2130p-dwc3
               - qcom,sc8180x-dwc3
               - qcom,sc8180x-dwc3-mp
@@ -454,8 +456,10 @@ allOf:
     then:
       properties:
         interrupts:
+          minItems: 3
           maxItems: 4
         interrupt-names:
+          minItems: 3
           items:
             - const: pwr_event
             - const: dp_hs_phy_irq
@@ -470,6 +474,7 @@ allOf:
               - qcom,ipq4019-dwc3
               - qcom,ipq8064-dwc3
               - qcom,msm8994-dwc3
+              - qcom,qcs615-dwc3
               - qcom,qcs8300-dwc3
               - qcom,qdu1000-dwc3
               - qcom,sa8775p-dwc3
diff --git a/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml b/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml
index ff625600d9af..b87e139c29e5 100644
--- a/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,rzv2m-usb3drd.yaml
@@ -104,26 +104,26 @@ examples:
         #size-cells = <1>;
 
         usb3host: usb@85060000 {
-           compatible = "renesas,r9a09g011-xhci",
-                        "renesas,rzv2m-xhci";
-           reg = <0x85060000 0x2000>;
-           interrupts = <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>;
-           clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_H>,
-                    <&cpg CPG_MOD R9A09G011_USB_PCLK>;
-           clock-names = "axi", "reg";
-           power-domains = <&cpg>;
-           resets = <&cpg R9A09G011_USB_ARESETN_H>;
+            compatible = "renesas,r9a09g011-xhci",
+                         "renesas,rzv2m-xhci";
+            reg = <0x85060000 0x2000>;
+            interrupts = <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_H>,
+                     <&cpg CPG_MOD R9A09G011_USB_PCLK>;
+            clock-names = "axi", "reg";
+            power-domains = <&cpg>;
+            resets = <&cpg R9A09G011_USB_ARESETN_H>;
         };
 
         usb3peri: usb3peri@85070000 {
-           compatible = "renesas,r9a09g011-usb3-peri",
-                        "renesas,rzv2m-usb3-peri";
-           reg = <0x85070000 0x400>;
-           interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
-           clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_P>,
-                    <&cpg CPG_MOD R9A09G011_USB_PCLK>;
-           clock-names = "axi", "reg";
-           power-domains = <&cpg>;
-           resets = <&cpg R9A09G011_USB_ARESETN_P>;
+            compatible = "renesas,r9a09g011-usb3-peri",
+                         "renesas,rzv2m-usb3-peri";
+            reg = <0x85070000 0x400>;
+            interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD R9A09G011_USB_ACLK_P>,
+                     <&cpg CPG_MOD R9A09G011_USB_PCLK>;
+            clock-names = "axi", "reg";
+            power-domains = <&cpg>;
+            resets = <&cpg R9A09G011_USB_ARESETN_P>;
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml b/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml
index b2b811a0ade8..4e56e4ffeaf2 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usb3-peri.yaml
@@ -132,19 +132,19 @@ examples:
         usb-role-switch;
 
         ports {
-                #address-cells = <1>;
-                #size-cells = <0>;
-                port@0 {
-                        reg = <0>;
-                        usb3_hs_ep: endpoint {
-                                remote-endpoint = <&hs_ep>;
-                        };
+            #address-cells = <1>;
+            #size-cells = <0>;
+            port@0 {
+                reg = <0>;
+                usb3_hs_ep: endpoint {
+                    remote-endpoint = <&hs_ep>;
                 };
-                port@1 {
-                        reg = <1>;
-                        usb3_role_switch: endpoint {
-                                remote-endpoint = <&hd3ss3220_out_ep>;
-                        };
+            };
+            port@1 {
+                reg = <1>;
+                usb3_role_switch: endpoint {
+                    remote-endpoint = <&hd3ss3220_out_ep>;
                 };
+            };
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
index b23ef29bf794..980f325341d4 100644
--- a/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
+++ b/Documentation/devicetree/bindings/usb/renesas,usbhs.yaml
@@ -26,6 +26,7 @@ properties:
               - renesas,usbhs-r9a07g043 # RZ/G2UL and RZ/Five
               - renesas,usbhs-r9a07g044 # RZ/G2{L,LC}
               - renesas,usbhs-r9a07g054 # RZ/V2L
+              - renesas,usbhs-r9a08g045 # RZ/G3S
           - const: renesas,rzg2l-usbhs
 
       - items:
@@ -130,6 +131,7 @@ allOf:
               - renesas,usbhs-r9a07g043
               - renesas,usbhs-r9a07g044
               - renesas,usbhs-r9a07g054
+              - renesas,usbhs-r9a08g045
     then:
       properties:
         interrupts:
diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3-common.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3-common.yaml
new file mode 100644
index 000000000000..c956053fd036
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/snps,dwc3-common.yaml
@@ -0,0 +1,415 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/usb/snps,dwc3-common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Synopsys DesignWare USB3 Controller common properties
+
+maintainers:
+  - Felipe Balbi <balbi@kernel.org>
+
+description:
+  Defines the properties of the DWC3 core as being embedded in either an
+  vendor-specific implementation or as a standalone component.
+
+allOf:
+  - $ref: usb-drd.yaml#
+  - if:
+      properties:
+        dr_mode:
+          const: peripheral
+
+      required:
+        - dr_mode
+    then:
+      $ref: usb.yaml#
+    else:
+      $ref: usb-xhci.yaml#
+
+properties:
+  extcon:
+    maxItems: 1
+    deprecated: true
+
+  usb-phy:
+    minItems: 1
+    items:
+      - description: USB2/HS PHY
+      - description: USB3/SS PHY
+
+  phys:
+    minItems: 1
+    maxItems: 19
+
+  phy-names:
+    minItems: 1
+    maxItems: 19
+    oneOf:
+      - items:
+          enum: [ usb2-phy, usb3-phy ]
+      - items:
+          pattern: "^usb(2-([0-9]|1[0-4])|3-[0-3])$"
+
+  snps,usb2-lpm-disable:
+    description: Indicate if we don't want to enable USB2 HW LPM for host
+      mode.
+    type: boolean
+
+  snps,usb3_lpm_capable:
+    description: Determines if platform is USB3 LPM capable
+    type: boolean
+
+  snps,usb2-gadget-lpm-disable:
+    description: Indicate if we don't want to enable USB2 HW LPM for gadget
+      mode.
+    type: boolean
+
+  snps,dis-start-transfer-quirk:
+    description:
+      When set, disable isoc START TRANSFER command failure SW work-around
+      for DWC_usb31 version 1.70a-ea06 and prior.
+    type: boolean
+
+  snps,disable_scramble_quirk:
+    description:
+      True when SW should disable data scrambling. Only really useful for FPGA
+      builds.
+    type: boolean
+
+  snps,has-lpm-erratum:
+    description: True when DWC3 was configured with LPM Erratum enabled
+    type: boolean
+
+  snps,lpm-nyet-threshold:
+    description: LPM NYET threshold
+    $ref: /schemas/types.yaml#/definitions/uint8
+
+  snps,u2exit_lfps_quirk:
+    description: Set if we want to enable u2exit lfps quirk
+    type: boolean
+
+  snps,u2ss_inp3_quirk:
+    description: Set if we enable P3 OK for U2/SS Inactive quirk
+    type: boolean
+
+  snps,req_p1p2p3_quirk:
+    description:
+      When set, the core will always request for P1/P2/P3 transition sequence.
+    type: boolean
+
+  snps,del_p1p2p3_quirk:
+    description:
+      When set core will delay P1/P2/P3 until a certain amount of 8B10B errors
+      occur.
+    type: boolean
+
+  snps,del_phy_power_chg_quirk:
+    description: When set core will delay PHY power change from P0 to P1/P2/P3.
+    type: boolean
+
+  snps,lfps_filter_quirk:
+    description: When set core will filter LFPS reception.
+    type: boolean
+
+  snps,rx_detect_poll_quirk:
+    description:
+      when set core will disable a 400us delay to start Polling LFPS after
+      RX.Detect.
+    type: boolean
+
+  snps,tx_de_emphasis_quirk:
+    description: When set core will set Tx de-emphasis value
+    type: boolean
+
+  snps,tx_de_emphasis:
+    description:
+      The value driven to the PHY is controlled by the LTSSM during USB3
+      Compliance mode.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    enum:
+      - 0 # -6dB de-emphasis
+      - 1 # -3.5dB de-emphasis
+      - 2 # No de-emphasis
+
+  snps,dis_u3_susphy_quirk:
+    description: When set core will disable USB3 suspend phy
+    type: boolean
+
+  snps,dis_u2_susphy_quirk:
+    description: When set core will disable USB2 suspend phy
+    type: boolean
+
+  snps,dis_enblslpm_quirk:
+    description:
+      When set clears the enblslpm in GUSB2PHYCFG, disabling the suspend signal
+      to the PHY.
+    type: boolean
+
+  snps,dis-u1-entry-quirk:
+    description: Set if link entering into U1 needs to be disabled
+    type: boolean
+
+  snps,dis-u2-entry-quirk:
+    description: Set if link entering into U2 needs to be disabled
+    type: boolean
+
+  snps,dis_rxdet_inp3_quirk:
+    description:
+      When set core will disable receiver detection in PHY P3 power state.
+    type: boolean
+
+  snps,dis-u2-freeclk-exists-quirk:
+    description:
+      When set, clear the u2_freeclk_exists in GUSB2PHYCFG, specify that USB2
+      PHY doesn't provide a free-running PHY clock.
+    type: boolean
+
+  snps,dis-del-phy-power-chg-quirk:
+    description:
+      When set core will change PHY power from P0 to P1/P2/P3 without delay.
+    type: boolean
+
+  snps,dis-tx-ipgap-linecheck-quirk:
+    description: When set, disable u2mac linestate check during HS transmit
+    type: boolean
+
+  snps,parkmode-disable-ss-quirk:
+    description:
+      When set, all SuperSpeed bus instances in park mode are disabled.
+    type: boolean
+
+  snps,parkmode-disable-hs-quirk:
+    description:
+      When set, all HighSpeed bus instances in park mode are disabled.
+    type: boolean
+
+  snps,dis_metastability_quirk:
+    description:
+      When set, disable metastability workaround. CAUTION! Use only if you are
+      absolutely sure of it.
+    type: boolean
+
+  snps,dis-split-quirk:
+    description:
+      When set, change the way URBs are handled by the driver. Needed to
+      avoid -EPROTO errors with usbhid on some devices (Hikey 970).
+    type: boolean
+
+  snps,gfladj-refclk-lpm-sel-quirk:
+    description:
+      When set, run the SOF/ITP counter based on ref_clk.
+    type: boolean
+
+  snps,resume-hs-terminations:
+    description:
+      Fix the issue of HS terminations CRC error on resume by enabling this
+      quirk. When set, all the termsel, xcvrsel, opmode becomes 0 during end
+      of resume. This option is to support certain legacy ULPI PHYs.
+    type: boolean
+
+  snps,ulpi-ext-vbus-drv:
+    description:
+      Some ULPI USB PHY does not support internal VBUS supply, and driving
+      the CPEN pin, requires the configuration of the ulpi DRVVBUSEXTERNAL
+      bit. When set, the xhci host will configure the USB2 PHY drives VBUS
+      with an external supply.
+    type: boolean
+
+  snps,is-utmi-l1-suspend:
+    description:
+      True when DWC3 asserts output signal utmi_l1_suspend_n, false when
+      asserts utmi_sleep_n.
+    type: boolean
+
+  snps,hird-threshold:
+    description: HIRD threshold
+    $ref: /schemas/types.yaml#/definitions/uint8
+
+  snps,hsphy_interface:
+    description:
+      High-Speed PHY interface selection between UTMI+ and ULPI when the
+      DWC_USB3_HSPHY_INTERFACE has value 3.
+    $ref: /schemas/types.yaml#/definitions/string
+    enum: [utmi, ulpi]
+
+  snps,quirk-frame-length-adjustment:
+    description:
+      Value for GFLADJ_30MHZ field of GFLADJ register for post-silicon frame
+      length adjustment when the fladj_30mhz_sdbnd signal is invalid or
+      incorrect.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    minimum: 0
+    maximum: 0x3f
+
+  snps,ref-clock-period-ns:
+    description:
+      Value for REFCLKPER field of GUCTL register for reference clock period in
+      nanoseconds, when the hardware set default does not match the actual
+      clock.
+
+      This binding is deprecated. Instead, provide an appropriate reference clock.
+    minimum: 8
+    maximum: 62
+    deprecated: true
+
+  snps,rx-thr-num-pkt:
+    description:
+      USB RX packet threshold count. In host mode, this field specifies
+      the space that must be available in the RX FIFO before the core can
+      start the corresponding USB RX transaction (burst).
+      In device mode, this field specifies the space that must be
+      available in the RX FIFO before the core can send ERDY for a
+      flow-controlled endpoint. It is only used for SuperSpeed.
+      The valid values for this field are from 1 to 15. (DWC3 SuperSpeed
+      USB 3.0 Controller Databook)
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 15
+
+  snps,rx-max-burst:
+    description:
+      Max USB RX burst size. In host mode, this field specifies the
+      Maximum Bulk IN burst the DWC_usb3 core can perform. When the system
+      bus is slower than the USB, RX FIFO can overrun during a long burst.
+      You can program a smaller value to this field to limit the RX burst
+      size that the core can perform. It only applies to SS Bulk,
+      Isochronous, and Interrupt IN endpoints in the host mode.
+      In device mode, this field specifies the NUMP value that is sent in
+      ERDY for an OUT endpoint.
+      The valid values for this field are from 1 to 16. (DWC3 SuperSpeed
+      USB 3.0 Controller Databook)
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 16
+
+  snps,tx-thr-num-pkt:
+    description:
+      USB TX packet threshold count. This field specifies the number of
+      packets that must be in the TXFIFO before the core can start
+      transmission for the corresponding USB transaction (burst).
+      This count is valid in both host and device modes. It is only used
+      for SuperSpeed operation.
+      Valid values are from 1 to 15. (DWC3 SuperSpeed USB 3.0 Controller
+      Databook)
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 15
+
+  snps,tx-max-burst:
+    description:
+      Max USB TX burst size. When the system bus is slower than the USB,
+      TX FIFO can underrun during a long burst. Program a smaller value
+      to this field to limit the TX burst size that the core can execute.
+      In Host mode, it only applies to SS Bulk, Isochronous, and Interrupt
+      OUT endpoints. This value is not used in device mode.
+      Valid values are from 1 to 16. (DWC3 SuperSpeed USB 3.0 Controller
+      Databook)
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 16
+
+  snps,rx-thr-num-pkt-prd:
+    description:
+      Periodic ESS RX packet threshold count (host mode only). Set this and
+      snps,rx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31
+      programming guide section 1.2.4) to enable periodic ESS RX threshold.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 16
+
+  snps,rx-max-burst-prd:
+    description:
+      Max periodic ESS RX burst size (host mode only). Set this and
+      snps,rx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31
+      programming guide section 1.2.4) to enable periodic ESS RX threshold.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 16
+
+  snps,tx-thr-num-pkt-prd:
+    description:
+      Periodic ESS TX packet threshold count (host mode only). Set this and
+      snps,tx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31
+      programming guide section 1.2.3) to enable periodic ESS TX threshold.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 16
+
+  snps,tx-max-burst-prd:
+    description:
+      Max periodic ESS TX burst size (host mode only). Set this and
+      snps,tx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31
+      programming guide section 1.2.3) to enable periodic ESS TX threshold.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 1
+    maximum: 16
+
+  tx-fifo-resize:
+    description: Determines if the TX fifos can be dynamically resized depending
+      on the number of IN endpoints used and if bursting is supported.  This
+      may help improve bandwidth on platforms with higher system latencies, as
+      increased fifo space allows for the controller to prefetch data into its
+      internal memory.
+    type: boolean
+
+  tx-fifo-max-num:
+    description: Specifies the max number of packets the txfifo resizing logic
+      can account for when higher endpoint bursting is used. (bMaxBurst > 6) The
+      higher the number, the more fifo space the txfifo resizing logic will
+      allocate for that endpoint.
+    $ref: /schemas/types.yaml#/definitions/uint8
+    minimum: 3
+
+  snps,incr-burst-type-adjustment:
+    description:
+      Value for INCR burst type of GSBUSCFG0 register, undefined length INCR
+      burst type enable and INCRx type. A single value means INCRX burst mode
+      enabled. If more than one value specified, undefined length INCR burst
+      type will be enabled with burst lengths utilized up to the maximum
+      of the values passed in this property.
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    minItems: 1
+    maxItems: 8
+    uniqueItems: true
+    items:
+      enum: [1, 4, 8, 16, 32, 64, 128, 256]
+
+  num-hc-interrupters:
+    maximum: 8
+    default: 1
+
+  port:
+    $ref: /schemas/graph.yaml#/properties/port
+    description:
+      This port is used with the 'usb-role-switch' property  to connect the
+      dwc3 to type C connector.
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+    description:
+      Those ports should be used with any connector to the data bus of this
+      controller using the OF graph bindings specified if the "usb-role-switch"
+      property is used.
+
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: High Speed (HS) data bus.
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: Super Speed (SS) data bus.
+
+  wakeup-source:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      Enable USB remote wakeup.
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: true
+...
+
diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
index 1cd0ca90127d..4380bb6fa2f0 100644
--- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
+++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml
@@ -15,18 +15,7 @@ description:
   compatible string.
 
 allOf:
-  - $ref: usb-drd.yaml#
-  - if:
-      properties:
-        dr_mode:
-          const: peripheral
-
-      required:
-        - dr_mode
-    then:
-      $ref: usb.yaml#
-    else:
-      $ref: usb-xhci.yaml#
+  - $ref: snps,dwc3-common.yaml#
 
 properties:
   compatible:
@@ -70,32 +59,9 @@ properties:
 
   dma-coherent: true
 
-  extcon:
-    maxItems: 1
-    deprecated: true
-
   iommus:
     maxItems: 1
 
-  usb-phy:
-    minItems: 1
-    items:
-      - description: USB2/HS PHY
-      - description: USB3/SS PHY
-
-  phys:
-    minItems: 1
-    maxItems: 19
-
-  phy-names:
-    minItems: 1
-    maxItems: 19
-    oneOf:
-      - items:
-          enum: [ usb2-phy, usb3-phy ]
-      - items:
-          pattern: "^usb(2-([0-9]|1[0-4])|3-[0-3])$"
-
   power-domains:
     description:
       The DWC3 has 2 power-domains. The power management unit (PMU) and
@@ -109,361 +75,6 @@ properties:
   resets:
     minItems: 1
 
-  snps,usb2-lpm-disable:
-    description: Indicate if we don't want to enable USB2 HW LPM for host
-      mode.
-    type: boolean
-
-  snps,usb3_lpm_capable:
-    description: Determines if platform is USB3 LPM capable
-    type: boolean
-
-  snps,usb2-gadget-lpm-disable:
-    description: Indicate if we don't want to enable USB2 HW LPM for gadget
-      mode.
-    type: boolean
-
-  snps,dis-start-transfer-quirk:
-    description:
-      When set, disable isoc START TRANSFER command failure SW work-around
-      for DWC_usb31 version 1.70a-ea06 and prior.
-    type: boolean
-
-  snps,disable_scramble_quirk:
-    description:
-      True when SW should disable data scrambling. Only really useful for FPGA
-      builds.
-    type: boolean
-
-  snps,has-lpm-erratum:
-    description: True when DWC3 was configured with LPM Erratum enabled
-    type: boolean
-
-  snps,lpm-nyet-threshold:
-    description: LPM NYET threshold
-    $ref: /schemas/types.yaml#/definitions/uint8
-
-  snps,u2exit_lfps_quirk:
-    description: Set if we want to enable u2exit lfps quirk
-    type: boolean
-
-  snps,u2ss_inp3_quirk:
-    description: Set if we enable P3 OK for U2/SS Inactive quirk
-    type: boolean
-
-  snps,req_p1p2p3_quirk:
-    description:
-      When set, the core will always request for P1/P2/P3 transition sequence.
-    type: boolean
-
-  snps,del_p1p2p3_quirk:
-    description:
-      When set core will delay P1/P2/P3 until a certain amount of 8B10B errors
-      occur.
-    type: boolean
-
-  snps,del_phy_power_chg_quirk:
-    description: When set core will delay PHY power change from P0 to P1/P2/P3.
-    type: boolean
-
-  snps,lfps_filter_quirk:
-    description: When set core will filter LFPS reception.
-    type: boolean
-
-  snps,rx_detect_poll_quirk:
-    description:
-      when set core will disable a 400us delay to start Polling LFPS after
-      RX.Detect.
-    type: boolean
-
-  snps,tx_de_emphasis_quirk:
-    description: When set core will set Tx de-emphasis value
-    type: boolean
-
-  snps,tx_de_emphasis:
-    description:
-      The value driven to the PHY is controlled by the LTSSM during USB3
-      Compliance mode.
-    $ref: /schemas/types.yaml#/definitions/uint8
-    enum:
-      - 0 # -6dB de-emphasis
-      - 1 # -3.5dB de-emphasis
-      - 2 # No de-emphasis
-
-  snps,dis_u3_susphy_quirk:
-    description: When set core will disable USB3 suspend phy
-    type: boolean
-
-  snps,dis_u2_susphy_quirk:
-    description: When set core will disable USB2 suspend phy
-    type: boolean
-
-  snps,dis_enblslpm_quirk:
-    description:
-      When set clears the enblslpm in GUSB2PHYCFG, disabling the suspend signal
-      to the PHY.
-    type: boolean
-
-  snps,dis-u1-entry-quirk:
-    description: Set if link entering into U1 needs to be disabled
-    type: boolean
-
-  snps,dis-u2-entry-quirk:
-    description: Set if link entering into U2 needs to be disabled
-    type: boolean
-
-  snps,dis_rxdet_inp3_quirk:
-    description:
-      When set core will disable receiver detection in PHY P3 power state.
-    type: boolean
-
-  snps,dis-u2-freeclk-exists-quirk:
-    description:
-      When set, clear the u2_freeclk_exists in GUSB2PHYCFG, specify that USB2
-      PHY doesn't provide a free-running PHY clock.
-    type: boolean
-
-  snps,dis-del-phy-power-chg-quirk:
-    description:
-      When set core will change PHY power from P0 to P1/P2/P3 without delay.
-    type: boolean
-
-  snps,dis-tx-ipgap-linecheck-quirk:
-    description: When set, disable u2mac linestate check during HS transmit
-    type: boolean
-
-  snps,parkmode-disable-ss-quirk:
-    description:
-      When set, all SuperSpeed bus instances in park mode are disabled.
-    type: boolean
-
-  snps,parkmode-disable-hs-quirk:
-    description:
-      When set, all HighSpeed bus instances in park mode are disabled.
-    type: boolean
-
-  snps,dis_metastability_quirk:
-    description:
-      When set, disable metastability workaround. CAUTION! Use only if you are
-      absolutely sure of it.
-    type: boolean
-
-  snps,dis-split-quirk:
-    description:
-      When set, change the way URBs are handled by the driver. Needed to
-      avoid -EPROTO errors with usbhid on some devices (Hikey 970).
-    type: boolean
-
-  snps,gfladj-refclk-lpm-sel-quirk:
-    description:
-      When set, run the SOF/ITP counter based on ref_clk.
-    type: boolean
-
-  snps,resume-hs-terminations:
-    description:
-      Fix the issue of HS terminations CRC error on resume by enabling this
-      quirk. When set, all the termsel, xcvrsel, opmode becomes 0 during end
-      of resume. This option is to support certain legacy ULPI PHYs.
-    type: boolean
-
-  snps,ulpi-ext-vbus-drv:
-    description:
-      Some ULPI USB PHY does not support internal VBUS supply, and driving
-      the CPEN pin, requires the configuration of the ulpi DRVVBUSEXTERNAL
-      bit. When set, the xhci host will configure the USB2 PHY drives VBUS
-      with an external supply.
-    type: boolean
-
-  snps,is-utmi-l1-suspend:
-    description:
-      True when DWC3 asserts output signal utmi_l1_suspend_n, false when
-      asserts utmi_sleep_n.
-    type: boolean
-
-  snps,hird-threshold:
-    description: HIRD threshold
-    $ref: /schemas/types.yaml#/definitions/uint8
-
-  snps,hsphy_interface:
-    description:
-      High-Speed PHY interface selection between UTMI+ and ULPI when the
-      DWC_USB3_HSPHY_INTERFACE has value 3.
-    $ref: /schemas/types.yaml#/definitions/string
-    enum: [utmi, ulpi]
-
-  snps,quirk-frame-length-adjustment:
-    description:
-      Value for GFLADJ_30MHZ field of GFLADJ register for post-silicon frame
-      length adjustment when the fladj_30mhz_sdbnd signal is invalid or
-      incorrect.
-    $ref: /schemas/types.yaml#/definitions/uint32
-    minimum: 0
-    maximum: 0x3f
-
-  snps,ref-clock-period-ns:
-    description:
-      Value for REFCLKPER field of GUCTL register for reference clock period in
-      nanoseconds, when the hardware set default does not match the actual
-      clock.
-
-      This binding is deprecated. Instead, provide an appropriate reference clock.
-    minimum: 8
-    maximum: 62
-    deprecated: true
-
-  snps,rx-thr-num-pkt:
-    description:
-      USB RX packet threshold count. In host mode, this field specifies
-      the space that must be available in the RX FIFO before the core can
-      start the corresponding USB RX transaction (burst).
-      In device mode, this field specifies the space that must be
-      available in the RX FIFO before the core can send ERDY for a
-      flow-controlled endpoint. It is only used for SuperSpeed.
-      The valid values for this field are from 1 to 15. (DWC3 SuperSpeed
-      USB 3.0 Controller Databook)
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 15
-
-  snps,rx-max-burst:
-    description:
-      Max USB RX burst size. In host mode, this field specifies the
-      Maximum Bulk IN burst the DWC_usb3 core can perform. When the system
-      bus is slower than the USB, RX FIFO can overrun during a long burst.
-      You can program a smaller value to this field to limit the RX burst
-      size that the core can perform. It only applies to SS Bulk,
-      Isochronous, and Interrupt IN endpoints in the host mode.
-      In device mode, this field specifies the NUMP value that is sent in
-      ERDY for an OUT endpoint.
-      The valid values for this field are from 1 to 16. (DWC3 SuperSpeed
-      USB 3.0 Controller Databook)
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 16
-
-  snps,tx-thr-num-pkt:
-    description:
-      USB TX packet threshold count. This field specifies the number of
-      packets that must be in the TXFIFO before the core can start
-      transmission for the corresponding USB transaction (burst).
-      This count is valid in both host and device modes. It is only used
-      for SuperSpeed operation.
-      Valid values are from 1 to 15. (DWC3 SuperSpeed USB 3.0 Controller
-      Databook)
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 15
-
-  snps,tx-max-burst:
-    description:
-      Max USB TX burst size. When the system bus is slower than the USB,
-      TX FIFO can underrun during a long burst. Program a smaller value
-      to this field to limit the TX burst size that the core can execute.
-      In Host mode, it only applies to SS Bulk, Isochronous, and Interrupt
-      OUT endpoints. This value is not used in device mode.
-      Valid values are from 1 to 16. (DWC3 SuperSpeed USB 3.0 Controller
-      Databook)
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 16
-
-  snps,rx-thr-num-pkt-prd:
-    description:
-      Periodic ESS RX packet threshold count (host mode only). Set this and
-      snps,rx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31
-      programming guide section 1.2.4) to enable periodic ESS RX threshold.
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 16
-
-  snps,rx-max-burst-prd:
-    description:
-      Max periodic ESS RX burst size (host mode only). Set this and
-      snps,rx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31
-      programming guide section 1.2.4) to enable periodic ESS RX threshold.
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 16
-
-  snps,tx-thr-num-pkt-prd:
-    description:
-      Periodic ESS TX packet threshold count (host mode only). Set this and
-      snps,tx-max-burst-prd to a valid, non-zero value 1-16 (DWC_usb31
-      programming guide section 1.2.3) to enable periodic ESS TX threshold.
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 16
-
-  snps,tx-max-burst-prd:
-    description:
-      Max periodic ESS TX burst size (host mode only). Set this and
-      snps,tx-thr-num-pkt-prd to a valid, non-zero value 1-16 (DWC_usb31
-      programming guide section 1.2.3) to enable periodic ESS TX threshold.
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 1
-    maximum: 16
-
-  tx-fifo-resize:
-    description: Determines if the TX fifos can be dynamically resized depending
-      on the number of IN endpoints used and if bursting is supported.  This
-      may help improve bandwidth on platforms with higher system latencies, as
-      increased fifo space allows for the controller to prefetch data into its
-      internal memory.
-    type: boolean
-
-  tx-fifo-max-num:
-    description: Specifies the max number of packets the txfifo resizing logic
-      can account for when higher endpoint bursting is used. (bMaxBurst > 6) The
-      higher the number, the more fifo space the txfifo resizing logic will
-      allocate for that endpoint.
-    $ref: /schemas/types.yaml#/definitions/uint8
-    minimum: 3
-
-  snps,incr-burst-type-adjustment:
-    description:
-      Value for INCR burst type of GSBUSCFG0 register, undefined length INCR
-      burst type enable and INCRx type. A single value means INCRX burst mode
-      enabled. If more than one value specified, undefined length INCR burst
-      type will be enabled with burst lengths utilized up to the maximum
-      of the values passed in this property.
-    $ref: /schemas/types.yaml#/definitions/uint32-array
-    minItems: 1
-    maxItems: 8
-    uniqueItems: true
-    items:
-      enum: [1, 4, 8, 16, 32, 64, 128, 256]
-
-  num-hc-interrupters:
-    maximum: 8
-    default: 1
-
-  port:
-    $ref: /schemas/graph.yaml#/properties/port
-    description:
-      This port is used with the 'usb-role-switch' property  to connect the
-      dwc3 to type C connector.
-
-  ports:
-    $ref: /schemas/graph.yaml#/properties/ports
-    description:
-      Those ports should be used with any connector to the data bus of this
-      controller using the OF graph bindings specified if the "usb-role-switch"
-      property is used.
-
-    properties:
-      port@0:
-        $ref: /schemas/graph.yaml#/properties/port
-        description: High Speed (HS) data bus.
-
-      port@1:
-        $ref: /schemas/graph.yaml#/properties/port
-        description: Super Speed (SS) data bus.
-
-  wakeup-source:
-    $ref: /schemas/types.yaml#/definitions/flag
-    description:
-      Enable USB remote wakeup.
-
 unevaluatedProperties: false
 
 required:
diff --git a/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml b/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml
index 54c6586cb56d..bec1c8047bc0 100644
--- a/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,hd3ss3220.yaml
@@ -56,26 +56,26 @@ examples:
         #size-cells = <0>;
 
         hd3ss3220@47 {
-                compatible = "ti,hd3ss3220";
-                reg = <0x47>;
-                interrupt-parent = <&gpio6>;
-                interrupts = <3>;
+            compatible = "ti,hd3ss3220";
+            reg = <0x47>;
+            interrupt-parent = <&gpio6>;
+            interrupts = <3>;
 
-                ports {
-                        #address-cells = <1>;
-                        #size-cells = <0>;
-                        port@0 {
-                                reg = <0>;
-                                hd3ss3220_in_ep: endpoint {
-                                        remote-endpoint = <&ss_ep>;
-                                };
-                        };
-                        port@1 {
-                                reg = <1>;
-                                hd3ss3220_out_ep: endpoint {
-                                        remote-endpoint = <&usb3_role_switch>;
-                                };
-                        };
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                port@0 {
+                    reg = <0>;
+                    hd3ss3220_in_ep: endpoint {
+                        remote-endpoint = <&ss_ep>;
+                    };
                 };
+                port@1 {
+                    reg = <1>;
+                    hd3ss3220_out_ep: endpoint {
+                        remote-endpoint = <&usb3_role_switch>;
+                    };
+                };
+            };
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml b/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml
index ddda734f36fb..c4a91b3d6612 100644
--- a/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,tusb73x0-pci.yaml
@@ -48,8 +48,8 @@ examples:
         device_type = "pci";
 
         usb@0 {
-              compatible = "pci104c,8241";
-              reg = <0x0 0x0 0x0 0x0 0x0>;
-              ti,pwron-active-high;
+            compatible = "pci104c,8241";
+            reg = <0x0 0x0 0x0 0x0 0x0>;
+            ti,pwron-active-high;
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml b/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml
index 8ef117793e11..61217da8b2f3 100644
--- a/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,usb8020b.yaml
@@ -51,19 +51,19 @@ examples:
 
         /* 2.0 hub on port 1 */
         hub_2_0: hub@1 {
-          compatible = "usb451,8027";
-          reg = <1>;
-          peer-hub = <&hub_3_0>;
-          reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
-          vdd-supply = <&usb_hub_fixed_3v3>;
+            compatible = "usb451,8027";
+            reg = <1>;
+            peer-hub = <&hub_3_0>;
+            reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
+            vdd-supply = <&usb_hub_fixed_3v3>;
         };
 
         /* 3.0 hub on port 2 */
         hub_3_0: hub@2 {
-          compatible = "usb451,8025";
-          reg = <2>;
-          peer-hub = <&hub_2_0>;
-          reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
-          vdd-supply = <&usb_hub_fixed_3v3>;
+            compatible = "usb451,8025";
+            reg = <2>;
+            peer-hub = <&hub_2_0>;
+            reset-gpios = <&pio 7 GPIO_ACTIVE_HIGH>;
+            vdd-supply = <&usb_hub_fixed_3v3>;
         };
     };
diff --git a/Documentation/devicetree/bindings/usb/ti,usb8041.yaml b/Documentation/devicetree/bindings/usb/ti,usb8041.yaml
index c2e29bd61e11..bce730a5e237 100644
--- a/Documentation/devicetree/bindings/usb/ti,usb8041.yaml
+++ b/Documentation/devicetree/bindings/usb/ti,usb8041.yaml
@@ -51,17 +51,17 @@ examples:
 
         /* 2.0 hub on port 1 */
         hub_2_0: hub@1 {
-          compatible = "usb451,8142";
-          reg = <1>;
-          peer-hub = <&hub_3_0>;
-          reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
+            compatible = "usb451,8142";
+            reg = <1>;
+            peer-hub = <&hub_3_0>;
+            reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
         };
 
         /* 3.0 hub on port 2 */
         hub_3_0: hub@2 {
-          compatible = "usb451,8140";
-          reg = <2>;
-          peer-hub = <&hub_2_0>;
-          reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
+            compatible = "usb451,8140";
+            reg = <2>;
+            peer-hub = <&hub_2_0>;
+            reset-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>;
         };
     };
diff --git a/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml b/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml
index 422becc6e1fa..fe6b3f9a3f8b 100644
--- a/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml
+++ b/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml
@@ -25,6 +25,8 @@ properties:
   reg:
     maxItems: 1
 
+  vcc-supply: true
+
 required:
   - compatible
   - reg
diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index d594d0ea0e9d..d75728eb05f8 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -404,7 +404,6 @@ PHY
   devm_usb_get_phy()
   devm_usb_get_phy_by_node()
   devm_usb_get_phy_by_phandle()
-  devm_usb_put_phy()
 
 PINCTRL
   devm_pinctrl_get()
diff --git a/Documentation/driver-api/extcon.rst b/Documentation/driver-api/extcon.rst
new file mode 100644
index 000000000000..d3217b9cdcd5
--- /dev/null
+++ b/Documentation/driver-api/extcon.rst
@@ -0,0 +1,255 @@
+=======================
+Extcon Device Subsystem
+=======================
+
+Overview
+========
+
+The Extcon (External Connector) subsystem provides a unified framework for
+managing external connectors in Linux systems. It allows drivers to report
+the state of external connectors and provides a standardized interface for
+userspace to query and monitor these states.
+
+Extcon is particularly useful in modern devices with multiple connectivity
+options, such as smartphones, tablets, and laptops. It helps manage various
+types of connectors, including:
+
+1. USB connectors (e.g., USB-C, micro-USB)
+2. Charging ports (e.g., fast charging, wireless charging)
+3. Audio jacks (e.g., 3.5mm headphone jack)
+4. Video outputs (e.g., HDMI, DisplayPort)
+5. Docking stations
+
+Real-world examples:
+
+1. Smartphone USB-C port:
+   A single USB-C port on a smartphone can serve multiple functions. Extcon
+   can manage the different states of this port, such as:
+   - USB data connection
+   - Charging (various types like fast charging, USB Power Delivery)
+   - Audio output (USB-C headphones)
+   - Video output (USB-C to HDMI adapter)
+
+2. Laptop docking station:
+   When a laptop is connected to a docking station, multiple connections are
+   made simultaneously. Extcon can handle the state changes for:
+   - Power delivery
+   - External displays
+   - USB hub connections
+   - Ethernet connectivity
+
+3. Wireless charging pad:
+   Extcon can manage the state of a wireless charging connection, allowing
+   the system to respond appropriately when a device is placed on or removed
+   from the charging pad.
+
+4. Smart TV HDMI ports:
+   In a smart TV, Extcon can manage multiple HDMI ports, detecting when
+   devices are connected or disconnected, and potentially identifying the
+   type of device (e.g., gaming console, set-top box, Blu-ray player).
+
+The Extcon framework simplifies the development of drivers for these complex
+scenarios by providing a standardized way to report and query connector
+states, handle mutually exclusive connections, and manage connector
+properties. This allows for more robust and flexible handling of external
+connections in modern devices.
+
+Key Components
+==============
+
+extcon_dev
+----------
+
+The core structure representing an Extcon device::
+
+    struct extcon_dev {
+        const char *name;
+        const unsigned int *supported_cable;
+        const u32 *mutually_exclusive;
+
+        /* Internal data */
+        struct device dev;
+        unsigned int id;
+        struct raw_notifier_head nh_all;
+        struct raw_notifier_head *nh;
+        struct list_head entry;
+        int max_supported;
+        spinlock_t lock;
+        u32 state;
+
+        /* Sysfs related */
+        struct device_type extcon_dev_type;
+        struct extcon_cable *cables;
+        struct attribute_group attr_g_muex;
+        struct attribute **attrs_muex;
+        struct device_attribute *d_attrs_muex;
+    };
+
+Key fields:
+
+- ``name``: Name of the Extcon device
+- ``supported_cable``: Array of supported cable types
+- ``mutually_exclusive``: Array defining mutually exclusive cable types
+  This field is crucial for enforcing hardware constraints. It's an array of
+  32-bit unsigned integers, where each element represents a set of mutually
+  exclusive cable types. The array should be terminated with a 0.
+
+  For example:
+
+  ::
+
+      static const u32 mutually_exclusive[] = {
+          BIT(0) | BIT(1),  /* Cable 0 and 1 are mutually exclusive */
+          BIT(2) | BIT(3) | BIT(4),  /* Cables 2, 3, and 4 are mutually exclusive */
+          0  /* Terminator */
+      };
+
+  In this example, cables 0 and 1 cannot be connected simultaneously, and
+  cables 2, 3, and 4 are also mutually exclusive. This is useful for
+  scenarios like a single port that can either be USB or HDMI, but not both
+  at the same time.
+
+  The Extcon core uses this information to prevent invalid combinations of
+  cable states, ensuring that the reported states are always consistent
+  with the hardware capabilities.
+
+- ``state``: Current state of the device (bitmap of connected cables)
+
+
+extcon_cable
+------------
+
+Represents an individual cable managed by an Extcon device::
+
+    struct extcon_cable {
+        struct extcon_dev *edev;
+        int cable_index;
+        struct attribute_group attr_g;
+        struct device_attribute attr_name;
+        struct device_attribute attr_state;
+        struct attribute *attrs[3];
+        union extcon_property_value usb_propval[EXTCON_PROP_USB_CNT];
+        union extcon_property_value chg_propval[EXTCON_PROP_CHG_CNT];
+        union extcon_property_value jack_propval[EXTCON_PROP_JACK_CNT];
+        union extcon_property_value disp_propval[EXTCON_PROP_DISP_CNT];
+        DECLARE_BITMAP(usb_bits, EXTCON_PROP_USB_CNT);
+        DECLARE_BITMAP(chg_bits, EXTCON_PROP_CHG_CNT);
+        DECLARE_BITMAP(jack_bits, EXTCON_PROP_JACK_CNT);
+        DECLARE_BITMAP(disp_bits, EXTCON_PROP_DISP_CNT);
+    };
+
+Core Functions
+==============
+
+.. kernel-doc:: drivers/extcon/extcon.c
+   :identifiers: extcon_get_state
+
+.. kernel-doc:: drivers/extcon/extcon.c
+   :identifiers: extcon_set_state
+
+.. kernel-doc:: drivers/extcon/extcon.c
+   :identifiers: extcon_set_state_sync
+
+.. kernel-doc:: drivers/extcon/extcon.c
+   :identifiers: extcon_get_property
+
+
+Sysfs Interface
+===============
+
+Extcon devices expose the following sysfs attributes:
+
+- ``name``: Name of the Extcon device
+- ``state``: Current state of all supported cables
+- ``cable.N/name``: Name of the Nth supported cable
+- ``cable.N/state``: State of the Nth supported cable
+
+Usage Example
+-------------
+
+.. code-block:: c
+
+    #include <linux/module.h>
+    #include <linux/platform_device.h>
+    #include <linux/extcon.h>
+
+    struct my_extcon_data {
+        struct extcon_dev *edev;
+        struct device *dev;
+    };
+
+    static const unsigned int my_extcon_cable[] = {
+        EXTCON_USB,
+        EXTCON_USB_HOST,
+        EXTCON_NONE,
+    };
+
+    static int my_extcon_probe(struct platform_device *pdev)
+    {
+        struct my_extcon_data *data;
+        int ret;
+
+        data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+        if (!data)
+            return -ENOMEM;
+
+        data->dev = &pdev->dev;
+
+        /* Initialize extcon device */
+        data->edev = devm_extcon_dev_allocate(data->dev, my_extcon_cable);
+        if (IS_ERR(data->edev)) {
+            dev_err(data->dev, "Failed to allocate extcon device\n");
+            return PTR_ERR(data->edev);
+        }
+
+        /* Register extcon device */
+        ret = devm_extcon_dev_register(data->dev, data->edev);
+        if (ret < 0) {
+            dev_err(data->dev, "Failed to register extcon device\n");
+            return ret;
+        }
+
+        platform_set_drvdata(pdev, data);
+
+        /* Example: Set initial state */
+        extcon_set_state_sync(data->edev, EXTCON_USB, true);
+
+        dev_info(data->dev, "My extcon driver probed successfully\n");
+        return 0;
+    }
+
+    static int my_extcon_remove(struct platform_device *pdev)
+    {
+        struct my_extcon_data *data = platform_get_drvdata(pdev);
+
+        /* Example: Clear state before removal */
+        extcon_set_state_sync(data->edev, EXTCON_USB, false);
+
+        dev_info(data->dev, "My extcon driver removed\n");
+        return 0;
+    }
+
+    static const struct of_device_id my_extcon_of_match[] = {
+        { .compatible = "my,extcon-device", },
+        { },
+    };
+    MODULE_DEVICE_TABLE(of, my_extcon_of_match);
+
+    static struct platform_driver my_extcon_driver = {
+        .driver = {
+            .name = "my-extcon-driver",
+            .of_match_table = my_extcon_of_match,
+        },
+        .probe = my_extcon_probe,
+        .remove = my_extcon_remove,
+    };
+
+    module_platform_driver(my_extcon_driver);
+
+This example demonstrates:
+---------------------------
+
+- Defining supported cable types (USB and USB Host in this case).
+- Allocating and registering an extcon device.
+- Setting an initial state for a cable (USB connected in this example).
+- Clearing the state when the driver is removed.
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index 7f83e05769b4..16e2c4ec3c01 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -86,6 +86,7 @@ Subsystem-specific APIs
    dmaengine/index
    dpll
    edac
+   extcon
    firmware/index
    fpga/index
    frame-buffer
diff --git a/Documentation/driver-api/pps.rst b/Documentation/driver-api/pps.rst
index 78dded03e5d8..71ad04c82d6c 100644
--- a/Documentation/driver-api/pps.rst
+++ b/Documentation/driver-api/pps.rst
@@ -202,6 +202,46 @@ Sometimes one needs to be able not only to catch PPS signals but to produce
 them also. For example, running a distributed simulation, which requires
 computers' clock to be synchronized very tightly.
 
+To do so the class pps-gen has been added. PPS generators can be
+registered in the kernel by defining a struct pps_gen_source_info as
+follows::
+
+    static struct pps_gen_source_info pps_gen_dummy_info = {
+            .name                   = "dummy",
+            .use_system_clock       = true,
+            .get_time               = pps_gen_dummy_get_time,
+            .enable                 = pps_gen_dummy_enable,
+    };
+
+Where the use_system_clock states if the generator uses the system
+clock to generate its pulses, or they are from a peripheral device
+clock. Method get_time() is used to query the time stored into the
+generator clock, while the method enable() is used to enable or
+disable the PPS pulse generation.
+
+Then calling the function pps_gen_register_source() in your
+initialization routine as follows creates a new generator in the
+system::
+
+    pps_gen = pps_gen_register_source(&pps_gen_dummy_info);
+
+Generators SYSFS support
+------------------------
+
+If the SYSFS filesystem is enabled in the kernel it provides a new class::
+
+    $ ls /sys/class/pps-gen/
+    pps-gen0/  pps-gen1/  pps-gen2/
+
+Every directory is the ID of a PPS generator defined in the system and
+inside of it you find several files::
+
+    $ ls -F /sys/class/pps-gen/pps-gen0/
+    dev  enable  name  power/  subsystem@  system  time  uevent
+
+To enable the PPS signal generation you can use the command below::
+
+    $ echo 1 > /sys/class/pps-gen/pps-gen0/enable
 
 Parallel port generator
 ------------------------
diff --git a/Documentation/driver-api/scsi.rst b/Documentation/driver-api/scsi.rst
index 273281474c09..bf2be96cc2d6 100644
--- a/Documentation/driver-api/scsi.rst
+++ b/Documentation/driver-api/scsi.rst
@@ -126,7 +126,7 @@ Manage scsi_dev_info_list, which tracks blacklisted and whitelisted
 devices.
 
 .. kernel-doc:: drivers/scsi/scsi_devinfo.c
-   :internal:
+   :export:
 
 drivers/scsi/scsi_ioctl.c
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -162,7 +162,6 @@ statistics and to pass information directly to the lowlevel driver. I.E.
 plumbing to manage /proc/scsi/\*
 
 .. kernel-doc:: drivers/scsi/scsi_proc.c
-   :internal:
 
 drivers/scsi/scsi_netlink.c
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -193,7 +192,7 @@ else, sequentially scan LUNs up until some maximum is reached, or a LUN
 is seen that cannot have a device attached to it.
 
 .. kernel-doc:: drivers/scsi/scsi_scan.c
-   :internal:
+   :export:
 
 drivers/scsi/scsi_sysctl.c
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/filesystems/bcachefs/SubmittingPatches.rst b/Documentation/filesystems/bcachefs/SubmittingPatches.rst
new file mode 100644
index 000000000000..026b12ae0d6a
--- /dev/null
+++ b/Documentation/filesystems/bcachefs/SubmittingPatches.rst
@@ -0,0 +1,98 @@
+Submitting patches to bcachefs:
+===============================
+
+Patches must be tested before being submitted, either with the xfstests suite
+[0], or the full bcachefs test suite in ktest [1], depending on what's being
+touched. Note that ktest wraps xfstests and will be an easier method to running
+it for most users; it includes single-command wrappers for all the mainstream
+in-kernel local filesystems.
+
+Patches will undergo more testing after being merged (including
+lockdep/kasan/preempt/etc. variants), these are not generally required to be
+run by the submitter - but do put some thought into what you're changing and
+which tests might be relevant, e.g. are you dealing with tricky memory layout
+work? kasan, are you doing locking work? then lockdep; and ktest includes
+single-command variants for the debug build types you'll most likely need.
+
+The exception to this rule is incomplete WIP/RFC patches: if you're working on
+something nontrivial, it's encouraged to send out a WIP patch to let people
+know what you're doing and make sure you're on the right track. Just make sure
+it includes a brief note as to what's done and what's incomplete, to avoid
+confusion.
+
+Rigorous checkpatch.pl adherence is not required (many of its warnings are
+considered out of date), but try not to deviate too much without reason.
+
+Focus on writing code that reads well and is organized well; code should be
+aesthetically pleasing.
+
+CI:
+===
+
+Instead of running your tests locally, when running the full test suite it's
+prefereable to let a server farm do it in parallel, and then have the results
+in a nice test dashboard (which can tell you which failures are new, and
+presents results in a git log view, avoiding the need for most bisecting).
+
+That exists [2], and community members may request an account. If you work for
+a big tech company, you'll need to help out with server costs to get access -
+but the CI is not restricted to running bcachefs tests: it runs any ktest test
+(which generally makes it easy to wrap other tests that can run in qemu).
+
+Other things to think about:
+============================
+
+- How will we debug this code? Is there sufficient introspection to diagnose
+  when something starts acting wonky on a user machine?
+
+  We don't necessarily need every single field of every data structure visible
+  with introspection, but having the important fields of all the core data
+  types wired up makes debugging drastically easier - a bit of thoughtful
+  foresight greatly reduces the need to have people build custom kernels with
+  debug patches.
+
+  More broadly, think about all the debug tooling that might be needed.
+
+- Does it make the codebase more or less of a mess? Can we also try to do some
+  organizing, too?
+
+- Do new tests need to be written? New assertions? How do we know and verify
+  that the code is correct, and what happens if something goes wrong?
+
+  We don't yet have automated code coverage analysis or easy fault injection -
+  but for now, pretend we did and ask what they might tell us.
+
+  Assertions are hugely important, given that we don't yet have a systems
+  language that can do ergonomic embedded correctness proofs. Hitting an assert
+  in testing is much better than wandering off into undefined behaviour la-la
+  land - use them. Use them judiciously, and not as a replacement for proper
+  error handling, but use them.
+
+- Does it need to be performance tested? Should we add new peformance counters?
+
+  bcachefs has a set of persistent runtime counters which can be viewed with
+  the 'bcachefs fs top' command; this should give users a basic idea of what
+  their filesystem is currently doing. If you're doing a new feature or looking
+  at old code, think if anything should be added.
+
+- If it's a new on disk format feature - have upgrades and downgrades been
+  tested? (Automated tests exists but aren't in the CI, due to the hassle of
+  disk image management; coordinate to have them run.)
+
+Mailing list, IRC:
+==================
+
+Patches should hit the list [3], but much discussion and code review happens on
+IRC as well [4]; many people appreciate the more conversational approach and
+quicker feedback.
+
+Additionally, we have a lively user community doing excellent QA work, which
+exists primarily on IRC. Please make use of that resource; user feedback is
+important for any nontrivial feature, and documenting it in commit messages
+would be a good idea.
+
+[0]: git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git
+[1]: https://evilpiepirate.org/git/ktest.git/
+[2]: https://evilpiepirate.org/~testdashboard/ci/
+[3]: linux-bcachefs@vger.kernel.org
+[4]: irc.oftc.net#bcache, #bcachefs-dev
diff --git a/Documentation/filesystems/bcachefs/index.rst b/Documentation/filesystems/bcachefs/index.rst
index 95fc4b90739e..7db4d7ceab58 100644
--- a/Documentation/filesystems/bcachefs/index.rst
+++ b/Documentation/filesystems/bcachefs/index.rst
@@ -9,4 +9,5 @@ bcachefs Documentation
    :numbered:
 
    CodingStyle
+   SubmittingPatches
    errorcodes
diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst
index dc35da8b8792..f7f977ffbf8d 100644
--- a/Documentation/filesystems/debugfs.rst
+++ b/Documentation/filesystems/debugfs.rst
@@ -211,18 +211,16 @@ seq_file content.
 
 There are a couple of other directory-oriented helper functions::
 
-    struct dentry *debugfs_rename(struct dentry *old_dir,
-    				  struct dentry *old_dentry,
-		                  struct dentry *new_dir,
-				  const char *new_name);
+    struct dentry *debugfs_change_name(struct dentry *dentry,
+					  const char *fmt, ...);
 
     struct dentry *debugfs_create_symlink(const char *name,
                                           struct dentry *parent,
 				      	  const char *target);
 
-A call to debugfs_rename() will give a new name to an existing debugfs
-file, possibly in a different directory.  The new_name must not exist prior
-to the call; the return value is old_dentry with updated information.
+A call to debugfs_change_name() will give a new name to an existing debugfs
+file, always in the same directory.  The new_name must not exist prior
+to the call; the return value is 0 on success and -E... on failuer.
 Symbolic links can be created with debugfs_create_symlink().
 
 There is one important thing that all debugfs users must take into account:
diff --git a/Documentation/filesystems/fuse-io-uring.rst b/Documentation/filesystems/fuse-io-uring.rst
new file mode 100644
index 000000000000..d73dd0dbd238
--- /dev/null
+++ b/Documentation/filesystems/fuse-io-uring.rst
@@ -0,0 +1,99 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+FUSE-over-io-uring design documentation
+=======================================
+
+This documentation covers basic details how the fuse
+kernel/userspace communication through io-uring is configured
+and works. For generic details about FUSE see fuse.rst.
+
+This document also covers the current interface, which is
+still in development and might change.
+
+Limitations
+===========
+As of now not all requests types are supported through io-uring, userspace
+is required to also handle requests through /dev/fuse after io-uring setup
+is complete. Specifically notifications (initiated from the daemon side)
+and interrupts.
+
+Fuse io-uring configuration
+===========================
+
+Fuse kernel requests are queued through the classical /dev/fuse
+read/write interface - until io-uring setup is complete.
+
+In order to set up fuse-over-io-uring fuse-server (user-space)
+needs to submit SQEs (opcode = IORING_OP_URING_CMD) to the /dev/fuse
+connection file descriptor. Initial submit is with the sub command
+FUSE_URING_REQ_REGISTER, which will just register entries to be
+available in the kernel.
+
+Once at least one entry per queue is submitted, kernel starts
+to enqueue to ring queues.
+Note, every CPU core has its own fuse-io-uring queue.
+Userspace handles the CQE/fuse-request and submits the result as
+subcommand FUSE_URING_REQ_COMMIT_AND_FETCH - kernel completes
+the requests and also marks the entry available again. If there are
+pending requests waiting the request will be immediately submitted
+to the daemon again.
+
+Initial SQE
+-----------::
+
+ |                                    |  FUSE filesystem daemon
+ |                                    |
+ |                                    |  >io_uring_submit()
+ |                                    |   IORING_OP_URING_CMD /
+ |                                    |   FUSE_URING_CMD_REGISTER
+ |                                    |  [wait cqe]
+ |                                    |   >io_uring_wait_cqe() or
+ |                                    |   >io_uring_submit_and_wait()
+ |                                    |
+ |  >fuse_uring_cmd()                 |
+ |   >fuse_uring_register()           |
+
+
+Sending requests with CQEs
+--------------------------::
+
+ |                                           |  FUSE filesystem daemon
+ |                                           |  [waiting for CQEs]
+ |  "rm /mnt/fuse/file"                      |
+ |                                           |
+ |  >sys_unlink()                            |
+ |    >fuse_unlink()                         |
+ |      [allocate request]                   |
+ |      >fuse_send_one()                     |
+ |        ...                                |
+ |       >fuse_uring_queue_fuse_req          |
+ |        [queue request on fg queue]        |
+ |         >fuse_uring_add_req_to_ring_ent() |
+ |         ...                               |
+ |          >fuse_uring_copy_to_ring()       |
+ |          >io_uring_cmd_done()             |
+ |       >request_wait_answer()              |
+ |         [sleep on req->waitq]             |
+ |                                           |  [receives and handles CQE]
+ |                                           |  [submit result and fetch next]
+ |                                           |  >io_uring_submit()
+ |                                           |   IORING_OP_URING_CMD/
+ |                                           |   FUSE_URING_CMD_COMMIT_AND_FETCH
+ |  >fuse_uring_cmd()                        |
+ |   >fuse_uring_commit_fetch()              |
+ |    >fuse_uring_commit()                   |
+ |     >fuse_uring_copy_from_ring()          |
+ |      [ copy the result to the fuse req]   |
+ |     >fuse_uring_req_end()                 |
+ |      >fuse_request_end()                  |
+ |       [wake up req->waitq]                |
+ |    >fuse_uring_next_fuse_req              |
+ |       [wait or handle next req]           |
+ |                                           |
+ |       [req->waitq woken up]               |
+ |    <fuse_unlink()                         |
+ |  <sys_unlink()                            |
+
+
+
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 44e9e77ffe0d..2636f2a41bd3 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -98,6 +98,7 @@ Documentation for filesystem implementations.
    hpfs
    fuse
    fuse-io
+   fuse-io-uring
    inotify
    isofs
    nilfs2
diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index f5e3676db954..d20a32b77b60 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -17,7 +17,8 @@ dentry_operations
 
 prototypes::
 
-	int (*d_revalidate)(struct dentry *, unsigned int);
+	int (*d_revalidate)(struct inode *, const struct qstr *,
+			    struct dentry *, unsigned int);
 	int (*d_weak_revalidate)(struct dentry *, unsigned int);
 	int (*d_hash)(const struct dentry *, struct qstr *);
 	int (*d_compare)(const struct dentry *,
@@ -30,6 +31,8 @@ prototypes::
 	struct vfsmount *(*d_automount)(struct path *path);
 	int (*d_manage)(const struct path *, bool);
 	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
+	bool (*d_unalias_trylock)(const struct dentry *);
+	void (*d_unalias_unlock)(const struct dentry *);
 
 locking rules:
 
@@ -49,6 +52,8 @@ d_dname:	   no		no		no		no
 d_automount:	   no		no		yes		no
 d_manage:	   no		no		yes (ref-walk)	maybe
 d_real		   no		no		yes 		no
+d_unalias_trylock  yes		no		no 		no
+d_unalias_unlock   yes		no		no 		no
 ================== ===========	========	==============	========
 
 inode_operations
diff --git a/Documentation/filesystems/nfs/localio.rst b/Documentation/filesystems/nfs/localio.rst
index bd1967e2eab3..79808b37d745 100644
--- a/Documentation/filesystems/nfs/localio.rst
+++ b/Documentation/filesystems/nfs/localio.rst
@@ -218,64 +218,30 @@ NFS Client and Server Interlock
 ===============================
 
 LOCALIO provides the nfs_uuid_t object and associated interfaces to
-allow proper network namespace (net-ns) and NFSD object refcounting:
-
-    We don't want to keep a long-term counted reference on each NFSD's
-    net-ns in the client because that prevents a server container from
-    completely shutting down.
-
-    So we avoid taking a reference at all and rely on the per-cpu
-    reference to the server (detailed below) being sufficient to keep
-    the net-ns active. This involves allowing the NFSD's net-ns exit
-    code to iterate all active clients and clear their ->net pointers
-    (which are needed to find the per-cpu-refcount for the nfsd_serv).
-
-    Details:
-
-     - Embed nfs_uuid_t in nfs_client. nfs_uuid_t provides a list_head
-       that can be used to find the client. It does add the 16-byte
-       uuid_t to nfs_client so it is bigger than needed (given that
-       uuid_t is only used during the initial NFS client and server
-       LOCALIO handshake to determine if they are local to each other).
-       If that is really a problem we can find a fix.
-
-     - When the nfs server confirms that the uuid_t is local, it moves
-       the nfs_uuid_t onto a per-net-ns list in NFSD's nfsd_net.
-
-     - When each server's net-ns is shutting down - in a "pre_exit"
-       handler, all these nfs_uuid_t have their ->net cleared. There is
-       an rcu_synchronize() call between pre_exit() handlers and exit()
-       handlers so any caller that sees nfs_uuid_t ->net as not NULL can
-       safely manage the per-cpu-refcount for nfsd_serv.
-
-     - The client's nfs_uuid_t is passed to nfsd_open_local_fh() so it
-       can safely dereference ->net in a private rcu_read_lock() section
-       to allow safe access to the associated nfsd_net and nfsd_serv.
-
-So LOCALIO required the introduction and use of NFSD's percpu_ref to
-interlock nfsd_destroy_serv() and nfsd_open_local_fh(), to ensure each
-nn->nfsd_serv is not destroyed while in use by nfsd_open_local_fh(), and
+allow proper network namespace (net-ns) and NFSD object refcounting.
+
+LOCALIO required the introduction and use of NFSD's percpu nfsd_net_ref
+to interlock nfsd_shutdown_net() and nfsd_open_local_fh(), to ensure
+each net-ns is not destroyed while in use by nfsd_open_local_fh(), and
 warrants a more detailed explanation:
 
-    nfsd_open_local_fh() uses nfsd_serv_try_get() before opening its
+    nfsd_open_local_fh() uses nfsd_net_try_get() before opening its
     nfsd_file handle and then the caller (NFS client) must drop the
-    reference for the nfsd_file and associated nn->nfsd_serv using
-    nfs_file_put_local() once it has completed its IO.
+    reference for the nfsd_file and associated net-ns using
+    nfsd_file_put_local() once it has completed its IO.
 
     This interlock working relies heavily on nfsd_open_local_fh() being
     afforded the ability to safely deal with the possibility that the
     NFSD's net-ns (and nfsd_net by association) may have been destroyed
-    by nfsd_destroy_serv() via nfsd_shutdown_net() -- which is only
-    possible given the nfs_uuid_t ->net pointer managemenet detailed
-    above.
-
-All told, this elaborate interlock of the NFS client and server has been
-verified to fix an easy to hit crash that would occur if an NFSD
-instance running in a container, with a LOCALIO client mounted, is
-shutdown. Upon restart of the container and associated NFSD the client
-would go on to crash due to NULL pointer dereference that occurred due
-to the LOCALIO client's attempting to nfsd_open_local_fh(), using
-nn->nfsd_serv, without having a proper reference on nn->nfsd_serv.
+    by nfsd_destroy_serv() via nfsd_shutdown_net().
+
+This interlock of the NFS client and server has been verified to fix an
+easy to hit crash that would occur if an NFSD instance running in a
+container, with a LOCALIO client mounted, is shutdown. Upon restart of
+the container and associated NFSD, the client would go on to crash due
+to NULL pointer dereference that occurred due to the LOCALIO client's
+attempting to nfsd_open_local_fh() without having a proper reference on
+NFSD's net-ns.
 
 NFS Client issues IO instead of Server
 ======================================
@@ -306,10 +272,26 @@ is issuing IO to the underlying local filesystem that it is sharing with
 the NFS server. See: fs/nfs/localio.c:nfs_local_doio() and
 fs/nfs/localio.c:nfs_local_commit().
 
+With normal NFS that makes use of RPC to issue IO to the server, if an
+application uses O_DIRECT the NFS client will bypass the pagecache but
+the NFS server will not. The NFS server's use of buffered IO affords
+applications to be less precise with their alignment when issuing IO to
+the NFS client. But if all applications properly align their IO, LOCALIO
+can be configured to use end-to-end O_DIRECT semantics from the NFS
+client to the underlying local filesystem, that it is sharing with
+the NFS server, by setting the 'localio_O_DIRECT_semantics' nfs module
+parameter to Y, e.g.:
+
+    echo Y > /sys/module/nfs/parameters/localio_O_DIRECT_semantics
+
+Once enabled, it will cause LOCALIO to use end-to-end O_DIRECT semantics
+(but again, this may cause IO to fail if applications do not properly
+align their IO).
+
 Security
 ========
 
-Localio is only supported when UNIX-style authentication (AUTH_UNIX, aka
+LOCALIO is only supported when UNIX-style authentication (AUTH_UNIX, aka
 AUTH_SYS) is used.
 
 Care is taken to ensure the same NFS security mechanisms are used
@@ -324,6 +306,24 @@ client is afforded this same level of access (albeit in terms of the NFS
 protocol via SUNRPC). No other namespaces (user, mount, etc) have been
 altered or purposely extended from the server to the client.
 
+Module Parameters
+=================
+
+/sys/module/nfs/parameters/localio_enabled (bool)
+controls if LOCALIO is enabled, defaults to Y. If client and server are
+local but 'localio_enabled' is set to N then LOCALIO will not be used.
+
+/sys/module/nfs/parameters/localio_O_DIRECT_semantics (bool)
+controls if O_DIRECT extends down to the underlying filesystem, defaults
+to N. Application IO must be logical blocksize aligned, otherwise
+O_DIRECT will fail.
+
+/sys/module/nfsv3/parameters/nfs3_localio_probe_throttle (uint)
+controls if NFSv3 read and write IOs will trigger (re)enabling of
+LOCALIO every N (nfs3_localio_probe_throttle) IOs, defaults to 0
+(disabled). Must be power-of-2, admin keeps all the pieces if they
+misconfigure (too low a value or non-power-of-2).
+
 Testing
 =======
 
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index c1c121055204..1639e78e3146 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1141,3 +1141,19 @@ pointer are gone.
 
 set_blocksize() takes opened struct file instead of struct block_device now
 and it *must* be opened exclusive.
+
+---
+
+** mandatory**
+
+->d_revalidate() gets two extra arguments - inode of parent directory and
+name our dentry is expected to have.  Both are stable (dir is pinned in
+non-RCU case and will stay around during the call in RCU case, and name
+is guaranteed to stay unchanging).  Your instance doesn't have to use
+either, but it often helps to avoid a lot of painful boilerplate.
+Note that while name->name is stable and NUL-terminated, it may (and
+often will) have name->name[name->len] equal to '/' rather than '\0' -
+in normal case it points into the pathname being looked up.
+NOTE: if you need something like full path from the root of filesystem,
+you are still on your own - this assists with simple cases, but it's not
+magic.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 6a882c57a7e7..09f0aed5a08b 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -48,6 +48,7 @@ fixes/update part 1.1  Stefani Seibold <stefani@seibold.net>    June 9 2009
   3.11	/proc/<pid>/patch_state - Livepatch patch operation state
   3.12	/proc/<pid>/arch_status - Task architecture specific information
   3.13  /proc/<pid>/fd - List of symlinks to open files
+  3.14  /proc/<pid/ksm_stat - Information about the process's ksm status.
 
   4	Configuring procfs
   4.1	Mount options
@@ -484,14 +485,15 @@ Memory Area, or VMA) there is a series of lines such as the following::
     THPeligible:           0
     VmFlags: rd ex mr mw me dw
 
-The first of these lines shows the same information as is displayed for the
-mapping in /proc/PID/maps.  Following lines show the size of the mapping
-(size); the size of each page allocated when backing a VMA (KernelPageSize),
-which is usually the same as the size in the page table entries; the page size
-used by the MMU when backing a VMA (in most cases, the same as KernelPageSize);
-the amount of the mapping that is currently resident in RAM (RSS); the
-process' proportional share of this mapping (PSS); and the number of clean and
-dirty shared and private pages in the mapping.
+The first of these lines shows the same information as is displayed for
+the mapping in /proc/PID/maps.  Following lines show the size of the
+mapping (size); the size of each page allocated when backing a VMA
+(KernelPageSize), which is usually the same as the size in the page table
+entries; the page size used by the MMU when backing a VMA (in most cases,
+the same as KernelPageSize); the amount of the mapping that is currently
+resident in RAM (RSS); the process's proportional share of this mapping
+(PSS); and the number of clean and dirty shared and private pages in the
+mapping.
 
 The "proportional set size" (PSS) of a process is the count of pages it has
 in memory, where each page is divided by the number of processes sharing it.
@@ -2232,6 +2234,74 @@ The number of open files for the process is stored in 'size' member
 of stat() output for /proc/<pid>/fd for fast access.
 -------------------------------------------------------
 
+3.14 /proc/<pid/ksm_stat - Information about the process's ksm status
+---------------------------------------------------------------------
+When CONFIG_KSM is enabled, each process has this file which displays
+the information of ksm merging status.
+
+Example
+~~~~~~~
+
+::
+
+    / # cat /proc/self/ksm_stat
+    ksm_rmap_items 0
+    ksm_zero_pages 0
+    ksm_merging_pages 0
+    ksm_process_profit 0
+    ksm_merge_any: no
+    ksm_mergeable: no
+
+Description
+~~~~~~~~~~~
+
+ksm_rmap_items
+^^^^^^^^^^^^^^
+
+The number of ksm_rmap_item structures in use.  The structure
+ksm_rmap_item stores the reverse mapping information for virtual
+addresses.  KSM will generate a ksm_rmap_item for each ksm-scanned page of
+the process.
+
+ksm_zero_pages
+^^^^^^^^^^^^^^
+
+When /sys/kernel/mm/ksm/use_zero_pages is enabled, it represent how many
+empty pages are merged with kernel zero pages by KSM.
+
+ksm_merging_pages
+^^^^^^^^^^^^^^^^^
+
+It represents how many pages of this process are involved in KSM merging
+(not including ksm_zero_pages). It is the same with what
+/proc/<pid>/ksm_merging_pages shows.
+
+ksm_process_profit
+^^^^^^^^^^^^^^^^^^
+
+The profit that KSM brings (Saved bytes). KSM can save memory by merging
+identical pages, but also can consume additional memory, because it needs
+to generate a number of rmap_items to save each scanned page's brief rmap
+information. Some of these pages may be merged, but some may not be abled
+to be merged after being checked several times, which are unprofitable
+memory consumed.
+
+ksm_merge_any
+^^^^^^^^^^^^^
+
+It specifies whether the process's 'mm is added by prctl() into the
+candidate list of KSM or not, and if KSM scanning is fully enabled at
+process level.
+
+ksm_mergeable
+^^^^^^^^^^^^^
+
+It specifies whether any VMAs of the process''s mms are currently
+applicable to KSM.
+
+More information about KSM can be found in
+Documentation/admin-guide/mm/ksm.rst.
+
 
 Chapter 4: Configuring procfs
 =============================
@@ -2261,7 +2331,7 @@ arguments are now protected against local eavesdroppers.
 hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be
 fully invisible to other users.  It doesn't mean that it hides a fact whether a
 process with a specific pid value exists (it can be learned by other means, e.g.
-by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by
+by "kill -0 $PID"), but it hides process's uid and gid, which may be learned by
 stat()'ing /proc/<pid>/ otherwise.  It greatly complicates an intruder's task of
 gathering information about running processes, whether some daemon runs with
 elevated privileges, whether other user runs some sensitive program, whether
diff --git a/Documentation/filesystems/squashfs.rst b/Documentation/filesystems/squashfs.rst
index 4af8d6207509..45653b3228f9 100644
--- a/Documentation/filesystems/squashfs.rst
+++ b/Documentation/filesystems/squashfs.rst
@@ -6,7 +6,7 @@ Squashfs 4.0 Filesystem
 
 Squashfs is a compressed read-only filesystem for Linux.
 
-It uses zlib, lz4, lzo, or xz compression to compress files, inodes and
+It uses zlib, lz4, lzo, xz or zstd compression to compress files, inodes and
 directories.  Inodes in the system are very small and all blocks are packed to
 minimise data overhead. Block sizes greater than 4K are supported up to a
 maximum of 1Mbytes (default block size 128K).
@@ -16,8 +16,8 @@ use (i.e. in cases where a .tar.gz file may be used), and in constrained
 block device/memory systems (e.g. embedded systems) where low overhead is
 needed.
 
-Mailing list: squashfs-devel@lists.sourceforge.net
-Web site: www.squashfs.org
+Mailing list (kernel code): linux-fsdevel@vger.kernel.org
+Web site: github.com/plougher/squashfs-tools
 
 1. Filesystem Features
 ----------------------
@@ -58,11 +58,9 @@ inodes have different sizes).
 
 As squashfs is a read-only filesystem, the mksquashfs program must be used to
 create populated squashfs filesystems.  This and other squashfs utilities
-can be obtained from http://www.squashfs.org.  Usage instructions can be
-obtained from this site also.
-
-The squashfs-tools development tree is now located on kernel.org
-	git://git.kernel.org/pub/scm/fs/squashfs/squashfs-tools.git
+are very likely packaged by your linux distribution (called squashfs-tools).
+The source code can be obtained from github.com/plougher/squashfs-tools.
+Usage instructions can also be obtained from this site.
 
 2.1 Mount options
 -----------------
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 0b18af3f954e..31eea688609a 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -1251,7 +1251,8 @@ defined:
 .. code-block:: c
 
 	struct dentry_operations {
-		int (*d_revalidate)(struct dentry *, unsigned int);
+		int (*d_revalidate)(struct inode *, const struct qstr *,
+				    struct dentry *, unsigned int);
 		int (*d_weak_revalidate)(struct dentry *, unsigned int);
 		int (*d_hash)(const struct dentry *, struct qstr *);
 		int (*d_compare)(const struct dentry *,
@@ -1264,6 +1265,8 @@ defined:
 		struct vfsmount *(*d_automount)(struct path *);
 		int (*d_manage)(const struct path *, bool);
 		struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
+		bool (*d_unalias_trylock)(const struct dentry *);
+		void (*d_unalias_unlock)(const struct dentry *);
 	};
 
 ``d_revalidate``
@@ -1427,6 +1430,25 @@ defined:
 
 	For non-regular files, the 'dentry' argument is returned.
 
+``d_unalias_trylock``
+	if present, will be called by d_splice_alias() before moving a
+	preexisting attached alias.  Returning false prevents __d_move(),
+	making d_splice_alias() fail with -ESTALE.
+
+	Rationale: setting FS_RENAME_DOES_D_MOVE will prevent d_move()
+	and d_exchange() calls from the outside of filesystem methods;
+	however, it does not guarantee that attached dentries won't
+	be renamed or moved by d_splice_alias() finding a preexisting
+	alias for a directory inode.  Normally we would not care;
+	however, something that wants to stabilize the entire path to
+	root over a blocking operation might need that.  See 9p for one
+	(and hopefully only) example.
+
+``d_unalias_unlock``
+	should be paired with ``d_unalias_trylock``; that one is called after
+	__d_move() call in __d_unalias().
+
+
 Each dentry has a pointer to its parent dentry, as well as a hash list
 of child dentries.  Child dentries are basically like files in a
 directory.
diff --git a/Documentation/gpu/zynqmp.rst b/Documentation/gpu/zynqmp.rst
index f57bfa0ad6ec..1a6f9193de22 100644
--- a/Documentation/gpu/zynqmp.rst
+++ b/Documentation/gpu/zynqmp.rst
@@ -144,6 +144,4 @@ Internals
 
 .. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dp.c
 
-.. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_dpsub.c
-
 .. kernel-doc:: drivers/gpu/drm/xlnx/zynqmp_kms.c
diff --git a/Documentation/iio/ad4695.rst b/Documentation/iio/ad4695.rst
index 33ed29b7c98a..9ec8bf466c15 100644
--- a/Documentation/iio/ad4695.rst
+++ b/Documentation/iio/ad4695.rst
@@ -101,7 +101,7 @@ The macro comes from:
 
 .. code-block::
 
-    #include <dt-bindings/iio/adi,ad4695.h>
+    #include <dt-bindings/iio/adc/adi,ad4695.h>
 
 Pairing two INx pins
 ^^^^^^^^^^^^^^^^^^^^
diff --git a/Documentation/iio/adis16480.rst b/Documentation/iio/adis16480.rst
index bc78fa04d958..4a2d40e0daa7 100644
--- a/Documentation/iio/adis16480.rst
+++ b/Documentation/iio/adis16480.rst
@@ -12,7 +12,10 @@ This driver supports Analog Device's IMUs on SPI bus.
 * `ADIS16375 <https://www.analog.com/ADIS16375>`_
 * `ADIS16480 <https://www.analog.com/ADIS16480>`_
 * `ADIS16485 <https://www.analog.com/ADIS16485>`_
+* `ADIS16486 <https://www.analog.com/ADIS16486>`_
+* `ADIS16487 <https://www.analog.com/ADIS16487>`_
 * `ADIS16488 <https://www.analog.com/ADIS16488>`_
+* `ADIS16489 <https://www.analog.com/ADIS16489>`_
 * `ADIS16490 <https://www.analog.com/ADIS16490>`_
 * `ADIS16495 <https://www.analog.com/ADIS16495>`_
 * `ADIS16497 <https://www.analog.com/ADIS16497>`_
diff --git a/Documentation/iio/index.rst b/Documentation/iio/index.rst
index 074dbbf7ba0a..5710f5b9e958 100644
--- a/Documentation/iio/index.rst
+++ b/Documentation/iio/index.rst
@@ -29,3 +29,4 @@ Industrial I/O Kernel Drivers
    adxl380
    bno055
    ep93xx_adc
+   opt4060
diff --git a/Documentation/iio/opt4060.rst b/Documentation/iio/opt4060.rst
new file mode 100644
index 000000000000..eb155089b6d2
--- /dev/null
+++ b/Documentation/iio/opt4060.rst
@@ -0,0 +1,61 @@
+==============================
+OPT4060 driver
+==============================
+
+1. Overview
+=============================
+
+This driver supports the Texas Instrument RGBW high resolution color sensor over
+I2C.
+https://www.ti.com/lit/gpn/opt4060
+
+The driver supports:
+- Raw values for red, green, blue and clear.
+- Illuminance values.
+- Scaled color values for red, green and blue.
+- IIO events for thresholds.
+- IIO triggered buffer using both its own data ready trigger and triggers from
+other drivers.
+
+2. Illuminance calculation
+=============================
+
+Illuminance is calculated using the wide spectrum green channel.
+
+lux = GREEN_RAW x 2.15e-3
+
+The value is accessed from:
+/sys/bus/iio/devices/iio:deviceX/in_illuminance_input
+
+See section 8.4.5.2 in the data sheet for additional details.
+
+3. Color scale values
+=============================
+
+The sensor has different sensitivity for the different color components and
+compensating factors are exposed from the driver.
+
+The values are accessed from:
+/sys/bus/iio/devices/iio:deviceX/in_intensity_red_scale
+/sys/bus/iio/devices/iio:deviceX/in_intensity_green_scale
+/sys/bus/iio/devices/iio:deviceX/in_intensity_blue_scale
+
+A userspace application can multiply the raw values with the scale values so
+that for a particular test light source, typically white, the measurement
+intensity is the same across the different color channels. This is calculated
+in the following way:
+
+R = RED_RAW x SCALE_RED(2.4)
+G = GREEN_RAW x SCALE_GREEN(1.0)
+B = BLUE_RAW x SCALE_BLUE(1.3)
+
+The data sheet suggests using the scaled values to normalize the scaled R, G
+and B values. This is useful to get a value for the ratio between colors
+independent of light intensity. A userspace application can do this in the
+following way:
+
+R_NORMALIZED = R / (R + G + B)
+G_NORMALIZED = G / (R + G + B)
+B_NORMALIZED = B / (R + G + B)
+
+See section 8.4.5.2 in the data sheet for additional details.
diff --git a/Documentation/kbuild/gendwarfksyms.rst b/Documentation/kbuild/gendwarfksyms.rst
new file mode 100644
index 000000000000..e4beaae7e456
--- /dev/null
+++ b/Documentation/kbuild/gendwarfksyms.rst
@@ -0,0 +1,308 @@
+=======================
+DWARF module versioning
+=======================
+
+1. Introduction
+===============
+
+When CONFIG_MODVERSIONS is enabled, symbol versions for modules
+are typically calculated from preprocessed source code using the
+**genksyms** tool.  However, this is incompatible with languages such
+as Rust, where the source code has insufficient information about
+the resulting ABI. With CONFIG_GENDWARFKSYMS (and CONFIG_DEBUG_INFO)
+selected, **gendwarfksyms** is used instead to calculate symbol versions
+from the DWARF debugging information, which contains the necessary
+details about the final module ABI.
+
+1.1. Usage
+==========
+
+gendwarfksyms accepts a list of object files on the command line, and a
+list of symbol names (one per line) in standard input::
+
+        Usage: gendwarfksyms [options] elf-object-file ... < symbol-list
+
+        Options:
+          -d, --debug          Print debugging information
+              --dump-dies      Dump DWARF DIE contents
+              --dump-die-map   Print debugging information about die_map changes
+              --dump-types     Dump type strings
+              --dump-versions  Dump expanded type strings used for symbol versions
+          -s, --stable         Support kABI stability features
+          -T, --symtypes file  Write a symtypes file
+          -h, --help           Print this message
+
+
+2. Type information availability
+================================
+
+While symbols are typically exported in the same translation unit (TU)
+where they're defined, it's also perfectly fine for a TU to export
+external symbols. For example, this is done when calculating symbol
+versions for exports in stand-alone assembly code.
+
+To ensure the compiler emits the necessary DWARF type information in the
+TU where symbols are actually exported, gendwarfksyms adds a pointer
+to exported symbols in the `EXPORT_SYMBOL()` macro using the following
+macro::
+
+        #define __GENDWARFKSYMS_EXPORT(sym)                             \
+                static typeof(sym) *__gendwarfksyms_ptr_##sym __used    \
+                        __section(".discard.gendwarfksyms") = &sym;
+
+
+When a symbol pointer is found in DWARF, gendwarfksyms can use its
+type for calculating symbol versions even if the symbol is defined
+elsewhere. The name of the symbol pointer is expected to start with
+`__gendwarfksyms_ptr_`, followed by the name of the exported symbol.
+
+3. Symtypes output format
+=========================
+
+Similarly to genksyms, gendwarfksyms supports writing a symtypes
+file for each processed object that contain types for exported
+symbols and each referenced type that was used in calculating symbol
+versions. These files can be useful when trying to determine what
+exactly caused symbol versions to change between builds. To generate
+symtypes files during a kernel build, set `KBUILD_SYMTYPES=1`.
+
+Matching the existing format, the first column of each line contains
+either a type reference or a symbol name. Type references have a
+one-letter prefix followed by "#" and the name of the type. Four
+reference types are supported::
+
+        e#<type> = enum
+        s#<type> = struct
+        t#<type> = typedef
+        u#<type> = union
+
+Type names with spaces in them are wrapped in single quotes, e.g.::
+
+        s#'core::result::Result<u8, core::num::error::ParseIntError>'
+
+The rest of the line contains a type string. Unlike with genksyms that
+produces C-style type strings, gendwarfksyms uses the same simple parsed
+DWARF format produced by **--dump-dies**, but with type references
+instead of fully expanded strings.
+
+4. Maintaining a stable kABI
+============================
+
+Distribution maintainers often need the ability to make ABI compatible
+changes to kernel data structures due to LTS updates or backports. Using
+the traditional `#ifndef __GENKSYMS__` to hide these changes from symbol
+versioning won't work when processing object files. To support this
+use case, gendwarfksyms provides kABI stability features designed to
+hide changes that won't affect the ABI when calculating versions. These
+features are all gated behind the **--stable** command line flag and are
+not used in the mainline kernel. To use stable features during a kernel
+build, set `KBUILD_GENDWARFKSYMS_STABLE=1`.
+
+Examples for using these features are provided in the
+**scripts/gendwarfksyms/examples** directory, including helper macros
+for source code annotation. Note that as these features are only used to
+transform the inputs for symbol versioning, the user is responsible for
+ensuring that their changes actually won't break the ABI.
+
+4.1. kABI rules
+===============
+
+kABI rules allow distributions to fine-tune certain parts
+of gendwarfksyms output and thus control how symbol
+versions are calculated. These rules are defined in the
+`.discard.gendwarfksyms.kabi_rules` section of the object file and
+consist of simple null-terminated strings with the following structure::
+
+	version\0type\0target\0value\0
+
+This string sequence is repeated as many times as needed to express all
+the rules. The fields are as follows:
+
+- `version`: Ensures backward compatibility for future changes to the
+  structure. Currently expected to be "1".
+- `type`: Indicates the type of rule being applied.
+- `target`: Specifies the target of the rule, typically the fully
+  qualified name of the DWARF Debugging Information Entry (DIE).
+- `value`: Provides rule-specific data.
+
+The following helper macro, for example, can be used to specify rules
+in the source code::
+
+	#define __KABI_RULE(hint, target, value)                             \
+		static const char __PASTE(__gendwarfksyms_rule_,             \
+					  __COUNTER__)[] __used __aligned(1) \
+			__section(".discard.gendwarfksyms.kabi_rules") =     \
+				"1\0" #hint "\0" #target "\0" #value
+
+
+Currently, only the rules discussed in this section are supported, but
+the format is extensible enough to allow further rules to be added as
+need arises.
+
+4.1.1. Managing definition visibility
+=====================================
+
+A declaration can change into a full definition when additional includes
+are pulled into the translation unit. This changes the versions of any
+symbol that references the type even if the ABI remains unchanged. As
+it may not be possible to drop includes without breaking the build, the
+`declonly` rule can be used to specify a type as declaration-only, even
+if the debugging information contains the full definition.
+
+The rule fields are expected to be as follows:
+
+- `type`: "declonly"
+- `target`: The fully qualified name of the target data structure
+  (as shown in **--dump-dies** output).
+- `value`: This field is ignored.
+
+Using the `__KABI_RULE` macro, this rule can be defined as::
+
+	#define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, )
+
+Example usage::
+
+	struct s {
+		/* definition */
+	};
+
+	KABI_DECLONLY(s);
+
+4.1.2. Adding enumerators
+=========================
+
+For enums, all enumerators and their values are included in calculating
+symbol versions, which becomes a problem if we later need to add more
+enumerators without changing symbol versions. The `enumerator_ignore`
+rule allows us to hide named enumerators from the input.
+
+The rule fields are expected to be as follows:
+
+- `type`: "enumerator_ignore"
+- `target`: The fully qualified name of the target enum
+  (as shown in **--dump-dies** output) and the name of the
+  enumerator field separated by a space.
+- `value`: This field is ignored.
+
+Using the `__KABI_RULE` macro, this rule can be defined as::
+
+	#define KABI_ENUMERATOR_IGNORE(fqn, field) \
+		__KABI_RULE(enumerator_ignore, fqn field, )
+
+Example usage::
+
+	enum e {
+		A, B, C, D,
+	};
+
+	KABI_ENUMERATOR_IGNORE(e, B);
+	KABI_ENUMERATOR_IGNORE(e, C);
+
+If the enum additionally includes an end marker and new values must
+be added in the middle, we may need to use the old value for the last
+enumerator when calculating versions. The `enumerator_value` rule allows
+us to override the value of an enumerator for version calculation:
+
+- `type`: "enumerator_value"
+- `target`: The fully qualified name of the target enum
+  (as shown in **--dump-dies** output) and the name of the
+  enumerator field separated by a space.
+- `value`: Integer value used for the field.
+
+Using the `__KABI_RULE` macro, this rule can be defined as::
+
+	#define KABI_ENUMERATOR_VALUE(fqn, field, value) \
+		__KABI_RULE(enumerator_value, fqn field, value)
+
+Example usage::
+
+	enum e {
+		A, B, C, LAST,
+	};
+
+	KABI_ENUMERATOR_IGNORE(e, C);
+	KABI_ENUMERATOR_VALUE(e, LAST, 2);
+
+4.3. Adding structure members
+=============================
+
+Perhaps the most common ABI compatible change is adding a member to a
+kernel data structure. When changes to a structure are anticipated,
+distribution maintainers can pre-emptively reserve space in the
+structure and take it into use later without breaking the ABI. If
+changes are needed to data structures without reserved space, existing
+alignment holes can potentially be used instead. While kABI rules could
+be added for these type of changes, using unions is typically a more
+natural method. This section describes gendwarfksyms support for using
+reserved space in data structures and hiding members that don't change
+the ABI when calculating symbol versions.
+
+4.3.1. Reserving space and replacing members
+============================================
+
+Space is typically reserved for later use by appending integer types, or
+arrays, to the end of the data structure, but any type can be used. Each
+reserved member needs a unique name, but as the actual purpose is usually
+not known at the time the space is reserved, for convenience, names that
+start with `__kabi_` are left out when calculating symbol versions::
+
+        struct s {
+                long a;
+                long __kabi_reserved_0; /* reserved for future use */
+        };
+
+The reserved space can be taken into use by wrapping the member in a
+union, which includes the original type and the replacement member::
+
+        struct s {
+                long a;
+                union {
+                        long __kabi_reserved_0; /* original type */
+                        struct b b; /* replaced field */
+                };
+        };
+
+If the `__kabi_` naming scheme was used when reserving space, the name
+of the first member of the union must start with `__kabi_reserved`. This
+ensures the original type is used when calculating versions, but the name
+is again left out. The rest of the union is ignored.
+
+If we're replacing a member that doesn't follow this naming convention,
+we also need to preserve the original name to avoid changing versions,
+which we can do by changing the first union member's name to start with
+`__kabi_renamed` followed by the original name.
+
+The examples include `KABI_(RESERVE|USE|REPLACE)*` macros that help
+simplify the process and also ensure the replacement member is correctly
+aligned and its size won't exceed the reserved space.
+
+4.3.2. Hiding members
+=====================
+
+Predicting which structures will require changes during the support
+timeframe isn't always possible, in which case one might have to resort
+to placing new members into existing alignment holes::
+
+        struct s {
+                int a;
+                /* a 4-byte alignment hole */
+                unsigned long b;
+        };
+
+
+While this won't change the size of the data structure, one needs to
+be able to hide the added members from symbol versioning. Similarly
+to reserved fields, this can be accomplished by wrapping the added
+member to a union where one of the fields has a name starting with
+`__kabi_ignored`::
+
+        struct s {
+                int a;
+                union {
+                        char __kabi_ignored_0;
+                        int n;
+                };
+                unsigned long b;
+        };
+
+With **--stable**, both versions produce the same symbol version.
diff --git a/Documentation/kbuild/index.rst b/Documentation/kbuild/index.rst
index cee2f99f734b..e82af05cd652 100644
--- a/Documentation/kbuild/index.rst
+++ b/Documentation/kbuild/index.rst
@@ -21,6 +21,7 @@ Kernel Build System
     reproducible-builds
     gcc-plugins
     llvm
+    gendwarfksyms
 
 .. only::  subproject and html
 
diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst
index 101de236cd0c..a42f00d8cb90 100644
--- a/Documentation/kbuild/modules.rst
+++ b/Documentation/kbuild/modules.rst
@@ -423,6 +423,26 @@ Symbols From the Kernel (vmlinux + modules)
 	1) It lists all exported symbols from vmlinux and all modules.
 	2) It lists the CRC if CONFIG_MODVERSIONS is enabled.
 
+Version Information Formats
+---------------------------
+
+	Exported symbols have information stored in __ksymtab or __ksymtab_gpl
+	sections. Symbol names and namespaces are stored in __ksymtab_strings,
+	using a format similar to the string table used for ELF. If
+	CONFIG_MODVERSIONS is enabled, the CRCs corresponding to exported
+	symbols will be added to the __kcrctab or __kcrctab_gpl.
+
+	If CONFIG_BASIC_MODVERSIONS is enabled (default with
+	CONFIG_MODVERSIONS), imported symbols will have their symbol name and
+	CRC stored in the __versions section of the importing module. This
+	mode only supports symbols of length up to 64 bytes.
+
+	If CONFIG_EXTENDED_MODVERSIONS is enabled (required to enable both
+	CONFIG_MODVERSIONS and CONFIG_RUST at the same time), imported symbols
+	will have their symbol name recorded in the __version_ext_names
+	section as a series of concatenated, null-terminated strings. CRCs for
+	these symbols will be recorded in the __version_ext_crcs section.
+
 Symbols and External Modules
 ----------------------------
 
diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst
index f9c50525bdbf..e28c6a1b40ae 100644
--- a/Documentation/mm/damon/design.rst
+++ b/Documentation/mm/damon/design.rst
@@ -203,6 +203,8 @@ This scheme, however, cannot preserve the quality of the output if the
 assumption is not guaranteed.
 
 
+.. _damon_design_adaptive_regions_adjustment:
+
 Adaptive Regions Adjustment
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -264,6 +266,61 @@ tracepoints.  For more details, please refer to the documentations for
 respectively.
 
 
+.. _damon_design_monitoring_params_tuning_guide:
+
+Monitoring Parameters Tuning Guide
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In short, set ``aggregation interval`` to capture meaningful amount of accesses
+for the purpose.  The amount of accesses can be measured using ``nr_accesses``
+and ``age`` of regions in the aggregated monitoring results snapshot.  The
+default value of the interval, ``100ms``, turns out to be too short in many
+cases.  Set ``sampling interval`` proportional to ``aggregation interval``.  By
+default, ``1/20`` is recommended as the ratio.
+
+``Aggregation interval`` should be set as the time interval that the workload
+can make an amount of accesses for the monitoring purpose, within the interval.
+If the interval is too short, only small number of accesses are captured.  As a
+result, the monitoring results look everything is samely accessed only rarely.
+For many purposes, that would be useless.  If it is too long, however, the time
+to converge regions with the :ref:`regions adjustment mechanism
+<damon_design_adaptive_regions_adjustment>` can be too long, depending on the
+time scale of the given purpose.  This could happen if the workload is actually
+making only rare accesses but the user thinks the amount of accesses for the
+monitoring purpose too high.  For such cases, the target amount of access to
+capture per ``aggregation interval`` should carefully reconsidered.  Also, note
+that the captured amount of accesses is represented with not only
+``nr_accesses``, but also ``age``.  For example, even if every region on the
+monitoring results show zero ``nr_accesses``, regions could still be
+distinguished using ``age`` values as the recency information.
+
+Hence the optimum value of ``aggregation interval`` depends on the access
+intensiveness of the workload.  The user should tune the interval based on the
+amount of access that captured on each aggregated snapshot of the monitoring
+results.
+
+Note that the default value of the interval is 100 milliseconds, which is too
+short in many cases, especially on large systems.
+
+``Sampling interval`` defines the resolution of each aggregation.  If it is set
+too large, monitoring results will look like every region was samely rarely
+accessed, or samely frequently accessed.  That is, regions become
+undistinguishable based on access pattern, and therefore the results will be
+useless in many use cases.  If ``sampling interval`` is too small, it will not
+degrade the resolution, but will increase the monitoring overhead.  If it is
+appropriate enough to provide a resolution of the monitoring results that
+sufficient for the given purpose, it shouldn't be unnecessarily further
+lowered.  It is recommended to be set proportional to ``aggregation interval``.
+By default, the ratio is set as ``1/20``, and it is still recommended.
+
+Refer to below documents for an example tuning based on the above guide.
+
+.. toctree::
+   :maxdepth: 1
+
+   monitoring_intervals_tuning_example
+
+
 .. _damon_design_damos:
 
 Operation Schemes
@@ -504,9 +561,34 @@ have a list of latency-critical processes.
 
 To let users optimize DAMOS schemes with such special knowledge, DAMOS provides
 a feature called DAMOS filters.  The feature allows users to set an arbitrary
-number of filters for each scheme.  Each filter specifies the type of target
-memory, and whether it should exclude the memory of the type (filter-out), or
-all except the memory of the type (filter-in).
+number of filters for each scheme.  Each filter specifies
+
+- a type of memory (``type``),
+- whether it is for the memory of the type or all except the type
+  (``matching``), and
+- whether it is to allow (include) or reject (exclude) applying
+  the scheme's action to the memory (``allow``).
+
+When multiple filters are installed, each filter is evaluated in the installed
+order.  If a part of memory is matched to one of the filter, next filters are
+ignored.  If the memory passes through the filters evaluation stage because it
+is not matched to any of the filters, applying the scheme's action to it is
+allowed, same to the behavior when no filter exists.
+
+For example, let's assume 1) a filter for allowing anonymous pages and 2)
+another filter for rejecting young pages are installed in the order.  If a page
+of a region that eligible to apply the scheme's action is an anonymous page,
+the scheme's action will be applied to the page regardless of whether it is
+young or not, since it matches with the first allow-filter.  If the page is
+not anonymous but young, the scheme's action will not be applied, since the
+second reject-filter blocks it.  If the page is neither anonymous nor young,
+the page will pass through the filters evaluation stage since there is no
+matching filter, and the action will be applied to the page.
+
+Note that the action can equally be applied to memory that either explicitly
+filter-allowed or filters evaluation stage passed.  It means that installing
+allow-filters at the end of the list makes no practical change but only
+filters-checking overhead.
 
 For efficient handling of filters, some types of filters are handled by the
 core layer, while others are handled by operations set.  In the latter case,
@@ -516,7 +598,7 @@ filter are not counted as the scheme has tried to the region.  In contrast, if
 a memory regions is filtered by an operations set layer-handled filter, it is
 counted as the scheme has tried.  This difference affects the statistics.
 
-Below types of filters are currently supported.
+Below ``type`` of filters are currently supported.
 
 - anonymous page
     - Applied to pages that containing data that not stored in files.
@@ -539,6 +621,60 @@ To know how user-space can set the watermarks via :ref:`DAMON sysfs interface
 <sysfs_interface>`, refer to :ref:`filters <sysfs_filters>` part of the
 documentation.
 
+.. _damon_design_damos_stat:
+
+Statistics
+~~~~~~~~~~
+
+The statistics of DAMOS behaviors that designed to help monitoring, tuning and
+debugging of DAMOS.
+
+DAMOS accounts below statistics for each scheme, from the beginning of the
+scheme's execution.
+
+- ``nr_tried``: Total number of regions that the scheme is tried to be applied.
+- ``sz_trtied``: Total size of regions that the scheme is tried to be applied.
+- ``sz_ops_filter_passed``: Total bytes that passed operations set
+  layer-handled DAMOS filters.
+- ``nr_applied``: Total number of regions that the scheme is applied.
+- ``sz_applied``: Total size of regions that the scheme is applied.
+- ``qt_exceeds``: Total number of times the quota of the scheme has exceeded.
+
+"A scheme is tried to be applied to a region" means DAMOS core logic determined
+the region is eligible to apply the scheme's :ref:`action
+<damon_design_damos_action>`.  The :ref:`access pattern
+<damon_design_damos_access_pattern>`, :ref:`quotas
+<damon_design_damos_quotas>`, :ref:`watermarks
+<damon_design_damos_watermarks>`, and :ref:`filters
+<damon_design_damos_filters>` that handled on core logic could affect this.
+The core logic will only ask the underlying :ref:`operation set
+<damon_operations_set>` to do apply the action to the region, so whether the
+action is really applied or not is unclear.  That's why it is called "tried".
+
+"A scheme is applied to a region" means the :ref:`operation set
+<damon_operations_set>` has applied the action to at least a part of the
+region.  The :ref:`filters <damon_design_damos_filters>` that handled by the
+operation set, and the types of the :ref:`action <damon_design_damos_action>`
+and the pages of the region can affect this.  For example, if a filter is set
+to exclude anonymous pages and the region has only anonymous pages, or if the
+action is ``pageout`` while all pages of the region are unreclaimable, applying
+the action to the region will fail.
+
+To know how user-space can read the stats via :ref:`DAMON sysfs interface
+<sysfs_interface>`, refer to :ref:s`stats <sysfs_stats>` part of the
+documentation.
+
+Regions Walking
+~~~~~~~~~~~~~~~
+
+DAMOS feature allowing users access each region that a DAMOS action has just
+applied.  Using this feature, DAMON :ref:`API <damon_design_api>` allows users
+access full properties of the regions including the access monitoring results
+and amount of the region's internal memory that passed the DAMOS filters.
+:ref:`DAMON sysfs interface <sysfs_interface>` also allows users read the data
+via special :ref:`files <sysfs_schemes_tried_regions>`.
+
+.. _damon_design_api:
 
 Application Programming Interface
 ---------------------------------
@@ -573,15 +709,11 @@ General Purpose User Interface Modules
 DAMON modules that provide user space ABIs for general purpose DAMON usage in
 runtime.
 
-DAMON user interface modules, namely 'DAMON sysfs interface' and 'DAMON debugfs
-interface' are DAMON API user kernel modules that provide ABIs to the
-user-space.  Please note that DAMON debugfs interface is currently deprecated.
-
-Like many other ABIs, the modules create files on sysfs and debugfs, allow
-users to specify their requests to and get the answers from DAMON by writing to
-and reading from the files.  As a response to such I/O, DAMON user interface
-modules control DAMON and retrieve the results as user requested via the DAMON
-API, and return the results to the user-space.
+Like many other ABIs, the modules create files on pseudo file systems like
+'sysfs', allow users to specify their requests to and get the answers from
+DAMON by writing to and reading from the files.  As a response to such I/O,
+DAMON user interface modules control DAMON and retrieve the results as user
+requested via the DAMON API, and return the results to the user-space.
 
 The ABIs are designed to be used for user space applications development,
 rather than human beings' fingers.  Human users are recommended to use such
@@ -590,8 +722,9 @@ Github (https://github.com/damonitor/damo), Pypi
 (https://pypistats.org/packages/damo), and Fedora
 (https://packages.fedoraproject.org/pkgs/python-damo/damo/).
 
-Please refer to the ABI :doc:`document </admin-guide/mm/damon/usage>` for
-details of the interfaces.
+Currently, one module for this type, namely 'DAMON sysfs interface' is
+available.  Please refer to the ABI :ref:`doc <sysfs_interface>` for details of
+the interfaces.
 
 
 Special-Purpose Access-aware Kernel Modules
@@ -599,8 +732,8 @@ Special-Purpose Access-aware Kernel Modules
 
 DAMON modules that provide user space ABI for specific purpose DAMON usage.
 
-DAMON sysfs/debugfs user interfaces are for full control of all DAMON features
-in runtime.  For each special-purpose system-wide data access-aware system
+DAMON user interface modules are for full control of all DAMON features in
+runtime.  For each special-purpose system-wide data access-aware system
 operations such as proactive reclamation or LRU lists balancing, the interfaces
 could be simplified by removing unnecessary knobs for the specific purpose, and
 extended for boot-time and even compile time control.  Default values of DAMON
diff --git a/Documentation/mm/damon/monitoring_intervals_tuning_example.rst b/Documentation/mm/damon/monitoring_intervals_tuning_example.rst
new file mode 100644
index 000000000000..334a854efb40
--- /dev/null
+++ b/Documentation/mm/damon/monitoring_intervals_tuning_example.rst
@@ -0,0 +1,247 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================================================
+DAMON Moniting Interval Parameters Tuning Example
+=================================================
+
+DAMON's monitoring parameters need tuning based on given workload and the
+monitoring purpose.  There is a :ref:`tuning guide
+<damon_design_monitoring_params_tuning_guide>` for that.  This document
+provides an example tuning based on the guide.
+
+Setup
+=====
+
+For below example, DAMON of Linux kernel v6.11 and `damo
+<https://github.com/damonitor/damo>`_ (DAMON user-space tool) v2.5.9 was used to
+monitor and visualize access patterns on the physical address space of a system
+running a real-world server workload.
+
+5ms/100ms intervals: Too Short Interval
+=======================================
+
+Let's start by capturing the access pattern snapshot on the physical address
+space of the system using DAMON, with the default interval parameters (5
+milliseconds and 100 milliseconds for the sampling and the aggregation
+intervals, respectively).  Wait ten minutes between the start of DAMON and
+the capturing of the snapshot, to show a meaningful time-wise access patterns.
+::
+
+    # damo start
+    # sleep 600
+    # damo record --snapshot 0 1
+    # damo stop
+
+Then, list the DAMON-found regions of different access patterns, sorted by the
+"access temperature".  "Access temperature" is a metric representing the
+access-hotness of a region.  It is calculated as a weighted sum of the access
+frequency and the age of the region.  If the access frequency is 0 %, the
+temperature is multipled by minus one.  That is, if a region is not accessed,
+it gets minus temperature and it gets lower as not accessed for longer time.
+The sorting is in temperature-ascendint order, so the region at the top of the
+list is the coldest, and the one at the bottom is the hottest one. ::
+
+    # damo report access --sort_regions_by temperature
+    0   addr 16.052 GiB   size 5.985 GiB   access 0 %   age 5.900 s    # coldest
+    1   addr 22.037 GiB   size 6.029 GiB   access 0 %   age 5.300 s
+    2   addr 28.065 GiB   size 6.045 GiB   access 0 %   age 5.200 s
+    3   addr 10.069 GiB   size 5.983 GiB   access 0 %   age 4.500 s
+    4   addr 4.000 GiB    size 6.069 GiB   access 0 %   age 4.400 s
+    5   addr 62.008 GiB   size 3.992 GiB   access 0 %   age 3.700 s
+    6   addr 56.795 GiB   size 5.213 GiB   access 0 %   age 3.300 s
+    7   addr 39.393 GiB   size 6.096 GiB   access 0 %   age 2.800 s
+    8   addr 50.782 GiB   size 6.012 GiB   access 0 %   age 2.800 s
+    9   addr 34.111 GiB   size 5.282 GiB   access 0 %   age 2.300 s
+    10  addr 45.489 GiB   size 5.293 GiB   access 0 %   age 1.800 s    # hottest
+    total size: 62.000 GiB
+
+The list shows not seemingly hot regions, and only minimum access pattern
+diversity.  Every region has zero access frequency.  The number of region is
+10, which is the default ``min_nr_regions value``.  Size of each region is also
+nearly idential.  We can suspect this is because “adaptive regions adjustment”
+mechanism was not well working.  As the guide suggested, we can get relative
+hotness of regions using ``age`` as the recency information.  That would be
+better than nothing, but given the fact that the longest age is only about 6
+seconds while we waited about ten minuts, it is unclear how useful this will
+be.
+
+The temperature ranges to total size of regions of each range histogram
+visualization of the results also shows no interesting distribution pattern. ::
+
+    # damo report access --style temperature-sz-hist
+    <temperature> <total size>
+    [-,590,000,000, -,549,000,000) 5.985 GiB  |**********          |
+    [-,549,000,000, -,508,000,000) 12.074 GiB |********************|
+    [-,508,000,000, -,467,000,000) 0 B        |                    |
+    [-,467,000,000, -,426,000,000) 12.052 GiB |********************|
+    [-,426,000,000, -,385,000,000) 0 B        |                    |
+    [-,385,000,000, -,344,000,000) 3.992 GiB  |*******             |
+    [-,344,000,000, -,303,000,000) 5.213 GiB  |*********           |
+    [-,303,000,000, -,262,000,000) 12.109 GiB |********************|
+    [-,262,000,000, -,221,000,000) 5.282 GiB  |*********           |
+    [-,221,000,000, -,180,000,000) 0 B        |                    |
+    [-,180,000,000, -,139,000,000) 5.293 GiB  |*********           |
+    total size: 62.000 GiB
+
+In short, the parameters provide poor quality monitoring results for hot
+regions detection. According to the :ref:`guide
+<damon_design_monitoring_params_tuning_guide>`, this is due to the too short
+aggregation interval.
+
+100ms/2s intervals: Starts Showing Small Hot Regions
+====================================================
+
+Following the guide, increase the interval 20 times (100 milliseocnds and 2
+seconds for sampling and aggregation intervals, respectively). ::
+
+    # damo start -s 100ms -a 2s
+    # sleep 600
+    # damo record --snapshot 0 1
+    # damo stop
+    # damo report access --sort_regions_by temperature
+    0   addr 10.180 GiB   size 6.117 GiB   access 0 %   age 7 m 8 s    # coldest
+    1   addr 49.275 GiB   size 6.195 GiB   access 0 %   age 6 m 14 s
+    2   addr 62.421 GiB   size 3.579 GiB   access 0 %   age 6 m 4 s
+    3   addr 40.154 GiB   size 6.127 GiB   access 0 %   age 5 m 40 s
+    4   addr 16.296 GiB   size 6.182 GiB   access 0 %   age 5 m 32 s
+    5   addr 34.254 GiB   size 5.899 GiB   access 0 %   age 5 m 24 s
+    6   addr 46.281 GiB   size 2.995 GiB   access 0 %   age 5 m 20 s
+    7   addr 28.420 GiB   size 5.835 GiB   access 0 %   age 5 m 6 s
+    8   addr 4.000 GiB    size 6.180 GiB   access 0 %   age 4 m 16 s
+    9   addr 22.478 GiB   size 5.942 GiB   access 0 %   age 3 m 58 s
+    10  addr 55.470 GiB   size 915.645 MiB access 0 %   age 3 m 6 s
+    11  addr 56.364 GiB   size 6.056 GiB   access 0 %   age 2 m 8 s
+    12  addr 56.364 GiB   size 4.000 KiB   access 95 %  age 16 s
+    13  addr 49.275 GiB   size 4.000 KiB   access 100 % age 8 m 24 s   # hottest
+    total size: 62.000 GiB
+    # damo report access --style temperature-sz-hist
+    <temperature> <total size>
+    [-42,800,000,000, -33,479,999,000) 22.018 GiB |*****************   |
+    [-33,479,999,000, -24,159,998,000) 27.090 GiB |********************|
+    [-24,159,998,000, -14,839,997,000) 6.836 GiB  |******              |
+    [-14,839,997,000, -5,519,996,000)  6.056 GiB  |*****               |
+    [-5,519,996,000, 3,800,005,000)    4.000 KiB  |*                   |
+    [3,800,005,000, 13,120,006,000)    0 B        |                    |
+    [13,120,006,000, 22,440,007,000)   0 B        |                    |
+    [22,440,007,000, 31,760,008,000)   0 B        |                    |
+    [31,760,008,000, 41,080,009,000)   0 B        |                    |
+    [41,080,009,000, 50,400,010,000)   0 B        |                    |
+    [50,400,010,000, 59,720,011,000)   4.000 KiB  |*                   |
+    total size: 62.000 GiB
+
+DAMON found two distinct 4 KiB regions that pretty hot.  The regions are also
+well aged.  The hottest 4 KiB region was keeping the access frequency for about
+8 minutes, and the coldest region was keeping no access for about 7 minutes.
+The distribution on the histogram also looks like having a pattern.
+
+Especially, the finding of the 4 KiB regions among the 62 GiB total memory
+shows DAMON’s adaptive regions adjustment is working as designed.
+
+Still the number of regions is close to the ``min_nr_regions``, and sizes of
+cold regions are similar, though.  Apparently it is improved, but it still has
+rooms to improve.
+
+400ms/8s intervals: Pretty Improved Results
+===========================================
+
+Increase the intervals four times (400 milliseconds and 8 seconds
+for sampling and aggregation intervals, respectively). ::
+
+    # damo start -s 400ms -a 8s
+    # sleep 600
+    # damo record --snapshot 0 1
+    # damo stop
+    # damo report access --sort_regions_by temperature
+    0   addr 64.492 GiB   size 1.508 GiB   access 0 %   age 6 m 48 s    # coldest
+    1   addr 21.749 GiB   size 5.674 GiB   access 0 %   age 6 m 8 s
+    2   addr 27.422 GiB   size 5.801 GiB   access 0 %   age 6 m
+    3   addr 49.431 GiB   size 8.675 GiB   access 0 %   age 5 m 28 s
+    4   addr 33.223 GiB   size 5.645 GiB   access 0 %   age 5 m 12 s
+    5   addr 58.321 GiB   size 6.170 GiB   access 0 %   age 5 m 4 s
+    [...]
+    25  addr 6.615 GiB    size 297.531 MiB access 15 %  age 0 ns
+    26  addr 9.513 GiB    size 12.000 KiB  access 20 %  age 0 ns
+    27  addr 9.511 GiB    size 108.000 KiB access 25 %  age 0 ns
+    28  addr 9.513 GiB    size 20.000 KiB  access 25 %  age 0 ns
+    29  addr 9.511 GiB    size 12.000 KiB  access 30 %  age 0 ns
+    30  addr 9.520 GiB    size 4.000 KiB   access 40 %  age 0 ns
+    [...]
+    41  addr 9.520 GiB    size 4.000 KiB   access 80 %  age 56 s
+    42  addr 9.511 GiB    size 12.000 KiB  access 100 % age 6 m 16 s
+    43  addr 58.321 GiB   size 4.000 KiB   access 100 % age 6 m 24 s
+    44  addr 9.512 GiB    size 4.000 KiB   access 100 % age 6 m 48 s
+    45  addr 58.106 GiB   size 4.000 KiB   access 100 % age 6 m 48 s    # hottest
+    total size: 62.000 GiB
+    # damo report access --style temperature-sz-hist
+    <temperature> <total size>
+    [-40,800,000,000, -32,639,999,000) 21.657 GiB  |********************|
+    [-32,639,999,000, -24,479,998,000) 17.938 GiB  |*****************   |
+    [-24,479,998,000, -16,319,997,000) 16.885 GiB  |****************    |
+    [-16,319,997,000, -8,159,996,000)  586.879 MiB |*                   |
+    [-8,159,996,000, 5,000)            4.946 GiB   |*****               |
+    [5,000, 8,160,006,000)             260.000 KiB |*                   |
+    [8,160,006,000, 16,320,007,000)    0 B         |                    |
+    [16,320,007,000, 24,480,008,000)   0 B         |                    |
+    [24,480,008,000, 32,640,009,000)   0 B         |                    |
+    [32,640,009,000, 40,800,010,000)   16.000 KiB  |*                   |
+    [40,800,010,000, 48,960,011,000)   8.000 KiB   |*                   |
+    total size: 62.000 GiB
+
+The number of regions having different access patterns has significantly
+increased.  Size of each region is also more varied. Total size of non-zero
+access frequency regions is also significantly increased. Maybe this is already
+good enough to make some meaningful memory management efficieny changes.
+
+800ms/16s intervals: Another bias
+=================================
+
+Further double the intervals (800 milliseconds and 16 seconds for sampling
+and aggregation intervals, respectively).  The results is more improved for the
+hot regions detection, but starts looking degrading cold regions detection. ::
+
+    # damo start -s 800ms -a 16s
+    # sleep 600
+    # damo record --snapshot 0 1
+    # damo stop
+    # damo report access --sort_regions_by temperature
+    0   addr 64.781 GiB   size 1.219 GiB   access 0 %   age 4 m 48 s
+    1   addr 24.505 GiB   size 2.475 GiB   access 0 %   age 4 m 16 s
+    2   addr 26.980 GiB   size 504.273 MiB access 0 %   age 4 m
+    3   addr 29.443 GiB   size 2.462 GiB   access 0 %   age 4 m
+    4   addr 37.264 GiB   size 5.645 GiB   access 0 %   age 4 m
+    5   addr 31.905 GiB   size 5.359 GiB   access 0 %   age 3 m 44 s
+    [...]
+    20  addr 8.711 GiB    size 40.000 KiB  access 5 %   age 2 m 40 s
+    21  addr 27.473 GiB   size 1.970 GiB   access 5 %   age 4 m
+    22  addr 48.185 GiB   size 4.625 GiB   access 5 %   age 4 m
+    23  addr 47.304 GiB   size 902.117 MiB access 10 %  age 4 m
+    24  addr 8.711 GiB    size 4.000 KiB   access 100 % age 4 m
+    25  addr 20.793 GiB   size 3.713 GiB   access 5 %   age 4 m 16 s
+    26  addr 8.773 GiB    size 4.000 KiB   access 100 % age 4 m 16 s
+    total size: 62.000 GiB
+    # damo report access --style temperature-sz-hist
+    <temperature> <total size>
+    [-28,800,000,000, -23,359,999,000) 12.294 GiB  |*****************   |
+    [-23,359,999,000, -17,919,998,000) 9.753 GiB   |*************       |
+    [-17,919,998,000, -12,479,997,000) 15.131 GiB  |********************|
+    [-12,479,997,000, -7,039,996,000)  0 B         |                    |
+    [-7,039,996,000, -1,599,995,000)   7.506 GiB   |**********          |
+    [-1,599,995,000, 3,840,006,000)    6.127 GiB   |*********           |
+    [3,840,006,000, 9,280,007,000)     0 B         |                    |
+    [9,280,007,000, 14,720,008,000)    136.000 KiB |*                   |
+    [14,720,008,000, 20,160,009,000)   40.000 KiB  |*                   |
+    [20,160,009,000, 25,600,010,000)   11.188 GiB  |***************     |
+    [25,600,010,000, 31,040,011,000)   4.000 KiB   |*                   |
+    total size: 62.000 GiB
+
+It found more non-zero access frequency regions. The number of regions is still
+much higher than the ``min_nr_regions``, but it is reduced from that of the
+previous setup. And apparently the distribution seems bit biased to hot
+regions.
+
+Conclusion
+==========
+
+With the above experimental tuning results, we can conclude the theory and the
+guide makes sense to at least this workload, and could be applied to similar
+cases.
diff --git a/Documentation/mm/process_addrs.rst b/Documentation/mm/process_addrs.rst
index 1d416658d7f5..81417fa2ed20 100644
--- a/Documentation/mm/process_addrs.rst
+++ b/Documentation/mm/process_addrs.rst
@@ -531,6 +531,10 @@ are extra requirements for accessing them:
   new page table has been installed in the same location and filled with
   entries. Writers normally need to take the PTE lock and revalidate that the
   PMD entry still refers to the same PTE-level page table.
+  If the writer does not care whether it is the same PTE-level page table, it
+  can take the PMD lock and revalidate that the contents of pmd entry still meet
+  the requirements. In particular, this also happens in :c:func:`!retract_page_tables`
+  when handling :c:macro:`!MADV_COLLAPSE`.
 
 To access PTE-level page tables, a helper like :c:func:`!pte_offset_map_lock` or
 :c:func:`!pte_offset_map` can be used depending on stability requirements.
diff --git a/Documentation/mm/split_page_table_lock.rst b/Documentation/mm/split_page_table_lock.rst
index 581446d4a4eb..8e1ceb0a6619 100644
--- a/Documentation/mm/split_page_table_lock.rst
+++ b/Documentation/mm/split_page_table_lock.rst
@@ -62,7 +62,7 @@ Support of split page table lock by an architecture
 ===================================================
 
 There's no need in special enabling of PTE split page table lock: everything
-required is done by pagetable_pte_ctor() and pagetable_pte_dtor(), which
+required is done by pagetable_pte_ctor() and pagetable_dtor(), which
 must be called on PTE table allocation / freeing.
 
 Make sure the architecture doesn't use slab allocator for page table
@@ -73,7 +73,7 @@ PMD split lock only makes sense if you have more than two page table
 levels.
 
 PMD split lock enabling requires pagetable_pmd_ctor() call on PMD table
-allocation and pagetable_pmd_dtor() on freeing.
+allocation and pagetable_dtor() on freeing.
 
 Allocation usually happens in pmd_alloc_one(), freeing in pmd_free() and
 pmd_free_tlb(), but make sure you cover all PMD table allocation / freeing
diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
index 62519d38c58b..b018ce346392 100644
--- a/Documentation/networking/can.rst
+++ b/Documentation/networking/can.rst
@@ -699,10 +699,10 @@ RAW socket option CAN_RAW_JOIN_FILTERS
 
 The CAN_RAW socket can set multiple CAN identifier specific filters that
 lead to multiple filters in the af_can.c filter processing. These filters
-are indenpendent from each other which leads to logical OR'ed filters when
+are independent from each other which leads to logical OR'ed filters when
 applied (see :ref:`socketcan-rawfilter`).
 
-This socket option joines the given CAN filters in the way that only CAN
+This socket option joins the given CAN filters in the way that only CAN
 frames are passed to user space that matched *all* given CAN filters. The
 semantic for the applied filters is therefore changed to a logical AND.
 
diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index dc45c0211353..03e1d3610333 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -41,7 +41,7 @@ blackhole_timeout - INTEGER (seconds)
 	MPTCP is re-enabled and will reset to the initial value when the
 	blackhole issue goes away.
 
-	0 to disable the blackhole detection.
+	0 to disable the blackhole detection. This is a per-namespace sysctl.
 
 	Default: 3600
 
diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index 6083210ab2a4..f970a2be271a 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -362,7 +362,7 @@ It is expected that ``irq-suspend-timeout`` will be set to a value much larger
 than ``gro_flush_timeout`` as ``irq-suspend-timeout`` should suspend IRQs for
 the duration of one userland processing cycle.
 
-While it is not stricly necessary to use ``napi_defer_hard_irqs`` and
+While it is not strictly necessary to use ``napi_defer_hard_irqs`` and
 ``gro_flush_timeout`` to use IRQ suspension, their use is strongly
 recommended.
 
diff --git a/Documentation/power/video.rst b/Documentation/power/video.rst
index 337a2ba9f32f..8ab2458d1304 100644
--- a/Documentation/power/video.rst
+++ b/Documentation/power/video.rst
@@ -190,7 +190,7 @@ Toshiba Portege 3020CT		s3_mode (3)
 Toshiba Satellite 4030CDT	s3_mode (3) (S1 also works OK)
 Toshiba Satellite 4080XCDT      s3_mode (3) (S1 also works OK)
 Toshiba Satellite 4090XCDT      ??? [#f1]_
-Toshiba Satellite P10-554       s3_bios,s3_mode (4)[#f3]_
+Toshiba Satellite P10-554       s3_bios,s3_mode (4) [#f3]_
 Toshiba M30                     (2) xor X with nvidia driver using internal AGP
 Uniwill 244IIO			??? [#f1]_
 =============================== ===============================================
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 82b5e378eebf..a0beca805362 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -59,7 +59,6 @@ iptables               1.4.2            iptables -V
 openssl & libcrypto    1.0.0            openssl version
 bc                     1.06.95          bc --version
 Sphinx\ [#f1]_         2.4.4            sphinx-build --version
-cpio                   any              cpio --version
 GNU tar                1.28             tar --version
 gtags (optional)       6.6.5            gtags --version
 mkimage (optional)     2017.01          mkimage --version
@@ -536,11 +535,6 @@ mcelog
 
 - <https://www.mcelog.org/>
 
-cpio
-----
-
-- <https://www.gnu.org/software/cpio/>
-
 Networking
 **********
 
diff --git a/Documentation/scsi/scsi_eh.rst b/Documentation/scsi/scsi_eh.rst
index 104d09e9af09..36cff176c5e6 100644
--- a/Documentation/scsi/scsi_eh.rst
+++ b/Documentation/scsi/scsi_eh.rst
@@ -54,13 +54,13 @@ invoking hostt->queuecommand() or the block layer will time it out.
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 For all non-EH commands, scsi_done() is the completion callback.  It
-just calls blk_complete_request() to delete the block layer timer and
-raise SCSI_SOFTIRQ
+just calls blk_mq_complete_request() to delete the block layer timer and
+raise BLOCK_SOFTIRQ.
 
-SCSI_SOFTIRQ handler scsi_softirq calls scsi_decide_disposition() to
-determine what to do with the command.  scsi_decide_disposition()
-looks at the scmd->result value and sense data to determine what to do
-with the command.
+The BLOCK_SOFTIRQ indirectly calls scsi_complete(), which calls
+scsi_decide_disposition() to determine what to do with the command.
+scsi_decide_disposition() looks at the scmd->result value and sense
+data to determine what to do with the command.
 
  - SUCCESS
 
@@ -110,7 +110,7 @@ The timeout handler is scsi_timeout().  When a timeout occurs, this function
     retry which failed), when retries are exceeded, or when the EH deadline is
     expired. In these cases Step #3 is taken.
 
- 3. scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD) is invoked for the
+ 3. scsi_eh_scmd_add(scmd) is invoked for the
     command.  See [1-4] for more information.
 
 1.3 Asynchronous command aborts
@@ -277,7 +277,6 @@ scmd->allowed.
 
     :ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd
 
-	- scsi_setup_cmd_retry()
 	- move from local eh_work_q to local eh_done_q
 
     :LOCKING: none
@@ -317,7 +316,7 @@ scmd->allowed.
     ``scsi_eh_get_sense``
 
 	This action is taken for each error-completed
-	(!SCSI_EH_CANCEL_CMD) commands without valid sense data.  Most
+	command without valid sense data.  Most
 	SCSI transports/LLDDs automatically acquire sense data on
 	command failures (autosense).  Autosense is recommended for
 	performance reasons and as sense information could get out of
@@ -347,30 +346,6 @@ scmd->allowed.
 	   - otherwise
 		No action.
 
-    3. If !list_empty(&eh_work_q), invoke scsi_eh_abort_cmds().
-
-    ``scsi_eh_abort_cmds``
-
-	This action is taken for each timed out command when
-	no_async_abort is enabled in the host template.
-	hostt->eh_abort_handler() is invoked for each scmd.  The
-	handler returns SUCCESS if it has succeeded to make LLDD and
-	all related hardware forget about the scmd.
-
-	If a timedout scmd is successfully aborted and the sdev is
-	either offline or ready, scsi_eh_finish_cmd() is invoked for
-	the scmd.  Otherwise, the scmd is left in eh_work_q for
-	higher-severity actions.
-
-	Note that both offline and ready status mean that the sdev is
-	ready to process new scmds, where processing also implies
-	immediate failing; thus, if a sdev is in one of the two
-	states, no further recovery action is needed.
-
-	Device readiness is tested using scsi_eh_tur() which issues
-	TEST_UNIT_READY command.  Note that the scmd must have been
-	aborted successfully before reusing it for TEST_UNIT_READY.
-
     4. If !list_empty(&eh_work_q), invoke scsi_eh_ready_devs()
 
     ``scsi_eh_ready_devs``
@@ -384,7 +359,7 @@ scmd->allowed.
 
 	    For each sdev which has failed scmds with valid sense data
 	    of which scsi_check_sense()'s verdict is FAILED,
-	    START_STOP_UNIT command is issued w/ start=1.  Note that
+	    START STOP UNIT command is issued w/ start=1.  Note that
 	    as we explicitly choose error-completed scmds, it is known
 	    that lower layers have forgotten about the scmd and we can
 	    reuse it for STU.
@@ -478,9 +453,6 @@ except for #1 must be implemented by eh_strategy_handler().
 
  - shost->host_failed is zero.
 
- - Each scmd is in such a state that scsi_setup_cmd_retry() on the
-   scmd doesn't make any difference.
-
  - shost->eh_cmd_q is cleared.
 
  - Each scmd->eh_entry is cleared.
diff --git a/Documentation/scsi/scsi_mid_low_api.rst b/Documentation/scsi/scsi_mid_low_api.rst
index 2df29b92e196..3cd6dce98e74 100644
--- a/Documentation/scsi/scsi_mid_low_api.rst
+++ b/Documentation/scsi/scsi_mid_low_api.rst
@@ -101,7 +101,7 @@ supplied functions" below.
 Those functions in group b) are listed in a section entitled "Interface
 functions" below. Their function pointers are placed in the members of
 "struct scsi_host_template", an instance of which is passed to
-scsi_host_alloc() [#]_.  Those interface functions that the LLD does not
+scsi_host_alloc().  Those interface functions that the LLD does not
 wish to supply should have NULL placed in the corresponding member of
 struct scsi_host_template.  Defining an instance of struct
 scsi_host_template at file scope will cause NULL to be  placed in function
@@ -112,12 +112,9 @@ Those usages in group c) should be handled with care, especially in a
 that are shared with the mid level and other layers.
 
 All functions defined within an LLD and all data defined at file scope
-should be static. For example the slave_alloc() function in an LLD
+should be static. For example the sdev_init() function in an LLD
 called "xxx" could be defined as
-``static int xxx_slave_alloc(struct scsi_device * sdev) { /* code */ }``
-
-.. [#] the scsi_host_alloc() function is a replacement for the rather vaguely
-       named scsi_register() function in most situations.
+``static int xxx_sdev_init(struct scsi_device * sdev) { /* code */ }``
 
 
 Hotplug initialization model
@@ -149,21 +146,21 @@ scsi devices of which only the first 2 respond::
     scsi_add_host()  ---->
     scsi_scan_host()  -------+
 			    |
-			slave_alloc()
-			slave_configure() -->  scsi_change_queue_depth()
+			sdev_init()
+			sdev_configure() -->  scsi_change_queue_depth()
 			    |
-			slave_alloc()
-			slave_configure()
+			sdev_init()
+			sdev_configure()
 			    |
-			slave_alloc()   ***
-			slave_destroy() ***
+			sdev_init()   ***
+			sdev_destroy() ***
 
 
     *** For scsi devices that the mid level tries to scan but do not
-	respond, a slave_alloc(), slave_destroy() pair is called.
+	respond, a sdev_init(), sdev_destroy() pair is called.
 
 If the LLD wants to adjust the default queue settings, it can invoke
-scsi_change_queue_depth() in its slave_configure() routine.
+scsi_change_queue_depth() in its sdev_configure() routine.
 
 When an HBA is being removed it could be as part of an orderly shutdown
 associated with the LLD module being unloaded (e.g. with the "rmmod"
@@ -176,8 +173,8 @@ same::
     ===----------------------=========-----------------===------
     scsi_remove_host() ---------+
 				|
-			slave_destroy()
-			slave_destroy()
+			sdev_destroy()
+			sdev_destroy()
     scsi_host_put()
 
 It may be useful for a LLD to keep track of struct Scsi_Host instances
@@ -202,8 +199,8 @@ An LLD can use this sequence to make the mid level aware of a SCSI device::
     ===-------------------=========--------------------===------
     scsi_add_device()  ------+
 			    |
-			slave_alloc()
-			slave_configure()   [--> scsi_change_queue_depth()]
+			sdev_init()
+			sdev_configure()   [--> scsi_change_queue_depth()]
 
 In a similar fashion, an LLD may become aware that a SCSI device has been
 removed (unplugged) or the connection to it has been interrupted. Some
@@ -218,12 +215,12 @@ upper layers with this sequence::
     ===----------------------=========-----------------===------
     scsi_remove_device() -------+
 				|
-			slave_destroy()
+			sdev_destroy()
 
 It may be useful for an LLD to keep track of struct scsi_device instances
-(a pointer is passed as the parameter to slave_alloc() and
-slave_configure() callbacks). Such instances are "owned" by the mid-level.
-struct scsi_device instances are freed after slave_destroy().
+(a pointer is passed as the parameter to sdev_init() and
+sdev_configure() callbacks). Such instances are "owned" by the mid-level.
+struct scsi_device instances are freed after sdev_destroy().
 
 
 Reference Counting
@@ -302,14 +299,12 @@ Summary:
   - scsi_host_alloc - return a new scsi_host instance whose refcount==1
   - scsi_host_get - increments Scsi_Host instance's refcount
   - scsi_host_put - decrements Scsi_Host instance's refcount (free if 0)
-  - scsi_register - create and register a scsi host adapter instance.
   - scsi_remove_device - detach and remove a SCSI device
   - scsi_remove_host - detach and remove all SCSI devices owned by host
   - scsi_report_bus_reset - report scsi _bus_ reset observed
   - scsi_scan_host - scan SCSI bus
   - scsi_track_queue_full - track successive QUEUE_FULL events
   - scsi_unblock_requests - allow further commands to be queued to given host
-  - scsi_unregister - [calls scsi_host_put()]
 
 
 Details::
@@ -331,7 +326,7 @@ Details::
     *      bus scan when an HBA is added (i.e. scsi_scan_host()). So it
     *      should only be called if the HBA becomes aware of a new scsi
     *      device (lu) after scsi_scan_host() has completed. If successful
-    *      this call can lead to slave_alloc() and slave_configure() callbacks
+    *      this call can lead to sdev_init() and sdev_configure() callbacks
     *      into the LLD.
     *
     *      Defined in: drivers/scsi/scsi_scan.c
@@ -374,8 +369,8 @@ Details::
     *      Might block: no
     *
     *      Notes: Can be invoked any time on a SCSI device controlled by this
-    *      LLD. [Specifically during and after slave_configure() and prior to
-    *      slave_destroy().] Can safely be invoked from interrupt code.
+    *      LLD. [Specifically during and after sdev_configure() and prior to
+    *      sdev_destroy().] Can safely be invoked from interrupt code.
     *
     *      Defined in: drivers/scsi/scsi.c [see source code for more notes]
     *
@@ -475,27 +470,6 @@ Details::
 
 
     /**
-    * scsi_register - create and register a scsi host adapter instance.
-    * @sht:        pointer to scsi host template
-    * @privsize:   extra bytes to allocate in hostdata array (which is the
-    *              last member of the returned Scsi_Host instance)
-    *
-    *      Returns pointer to new Scsi_Host instance or NULL on failure
-    *
-    *      Might block: yes
-    *
-    *      Notes: When this call returns to the LLD, the SCSI bus scan on
-    *      this host has _not_ yet been done.
-    *      The hostdata array (by default zero length) is a per host scratch
-    *      area for the LLD.
-    *
-    *      Defined in: drivers/scsi/hosts.c .
-    **/
-    struct Scsi_Host * scsi_register(struct scsi_host_template * sht,
-				    int privsize)
-
-
-    /**
     * scsi_remove_device - detach and remove a SCSI device
     * @sdev:      a pointer to a scsi device instance
     *
@@ -506,7 +480,7 @@ Details::
     *      Notes: If an LLD becomes aware that a scsi device (lu) has
     *      been removed but its host is still present then it can request
     *      the removal of that scsi device. If successful this call will
-    *      lead to the slave_destroy() callback being invoked. sdev is an
+    *      lead to the sdev_destroy() callback being invoked. sdev is an
     *      invalid pointer after this call.
     *
     *      Defined in: drivers/scsi/scsi_sysfs.c .
@@ -524,7 +498,7 @@ Details::
     *
     *      Notes: Should only be invoked if the "hotplug initialization
     *      model" is being used. It should be called _prior_ to
-    *      scsi_unregister().
+    *      calling scsi_host_put().
     *
     *      Defined in: drivers/scsi/hosts.c .
     **/
@@ -601,43 +575,24 @@ Details::
     void scsi_unblock_requests(struct Scsi_Host * shost)
 
 
-    /**
-    * scsi_unregister - unregister and free memory used by host instance
-    * @shp:        pointer to scsi host instance to unregister.
-    *
-    *      Returns nothing
-    *
-    *      Might block: no
-    *
-    *      Notes: Should not be invoked if the "hotplug initialization
-    *      model" is being used. Called internally by exit_this_scsi_driver()
-    *      in the "passive initialization model". Hence a LLD has no need to
-    *      call this function directly.
-    *
-    *      Defined in: drivers/scsi/hosts.c .
-    **/
-    void scsi_unregister(struct Scsi_Host * shp)
-
-
-
 
 Interface Functions
 ===================
 Interface functions are supplied (defined) by LLDs and their function
 pointers are placed in an instance of struct scsi_host_template which
-is passed to scsi_host_alloc() [or scsi_register() / init_this_scsi_driver()].
+is passed to scsi_host_alloc().
 Some are mandatory. Interface functions should be declared static. The
-accepted convention is that driver "xyz" will declare its slave_configure()
+accepted convention is that driver "xyz" will declare its sdev_configure()
 function as::
 
-    static int xyz_slave_configure(struct scsi_device * sdev);
+    static int xyz_sdev_configure(struct scsi_device * sdev);
 
 and so forth for all interface functions listed below.
 
-A pointer to this function should be placed in the 'slave_configure' member
+A pointer to this function should be placed in the 'sdev_configure' member
 of a "struct scsi_host_template" instance. A pointer to such an instance
-should be passed to the mid level's scsi_host_alloc() [or scsi_register() /
-init_this_scsi_driver()].
+should be passed to the mid level's scsi_host_alloc().
+.
 
 The interface functions are also described in the include/scsi/scsi_host.h
 file immediately above their definition point in "struct scsi_host_template".
@@ -657,9 +612,9 @@ Summary:
   - ioctl - driver can respond to ioctls
   - proc_info - supports /proc/scsi/{driver_name}/{host_no}
   - queuecommand - queue scsi command, invoke 'done' on completion
-  - slave_alloc - prior to any commands being sent to a new device
-  - slave_configure - driver fine tuning for given device after attach
-  - slave_destroy - given device is about to be shut down
+  - sdev_init - prior to any commands being sent to a new device
+  - sdev_configure - driver fine tuning for given device after attach
+  - sdev_destroy - given device is about to be shut down
 
 
 Details::
@@ -728,11 +683,7 @@ Details::
     *
     *      Calling context: kernel thread
     *
-    *      Notes: If 'no_async_abort' is defined this callback
-    *  	will be invoked from scsi_eh thread. No other commands
-    *	will then be queued on current host during eh.
-    *	Otherwise it will be called whenever scsi_timeout()
-    *      is called due to a command timeout.
+    *      Notes: This is called only for a command that has timed out.
     *
     *      Optionally defined in: LLD
     **/
@@ -817,10 +768,6 @@ Details::
     *      The SCSI_IOCTL_PROBE_HOST ioctl yields the string returned by this
     *      function (or struct Scsi_Host::name if this function is not
     *      available).
-    *      In a similar manner, init_this_scsi_driver() outputs to the console
-    *      each host's "info" (or name) for the driver it is registering.
-    *      Also if proc_info() is not supplied, the output of this function
-    *      is used instead.
     *
     *      Optionally defined in: LLD
     **/
@@ -960,7 +907,7 @@ Details::
 
 
     /**
-    *      slave_alloc -   prior to any commands being sent to a new device
+    *      sdev_init -   prior to any commands being sent to a new device
     *                      (i.e. just prior to scan) this call is made
     *      @sdp: pointer to new device (about to be scanned)
     *
@@ -975,24 +922,24 @@ Details::
     *      prior to its initial scan. The corresponding scsi device may not
     *      exist but the mid level is just about to scan for it (i.e. send
     *      and INQUIRY command plus ...). If a device is found then
-    *      slave_configure() will be called while if a device is not found
-    *      slave_destroy() is called.
+    *      sdev_configure() will be called while if a device is not found
+    *      sdev_destroy() is called.
     *      For more details see the include/scsi/scsi_host.h file.
     *
     *      Optionally defined in: LLD
     **/
-	int slave_alloc(struct scsi_device *sdp)
+	int sdev_init(struct scsi_device *sdp)
 
 
     /**
-    *      slave_configure - driver fine tuning for given device just after it
+    *      sdev_configure - driver fine tuning for given device just after it
     *                     has been first scanned (i.e. it responded to an
     *                     INQUIRY)
     *      @sdp: device that has just been attached
     *
     *      Returns 0 if ok. Any other return is assumed to be an error and
     *      the device is taken offline. [offline devices will _not_ have
-    *      slave_destroy() called on them so clean up resources.]
+    *      sdev_destroy() called on them so clean up resources.]
     *
     *      Locks: none
     *
@@ -1004,11 +951,11 @@ Details::
     *
     *      Optionally defined in: LLD
     **/
-	int slave_configure(struct scsi_device *sdp)
+	int sdev_configure(struct scsi_device *sdp)
 
 
     /**
-    *      slave_destroy - given device is about to be shut down. All
+    *      sdev_destroy - given device is about to be shut down. All
     *                      activity has ceased on this device.
     *      @sdp: device that is about to be shut down
     *
@@ -1023,12 +970,12 @@ Details::
     *      by this driver for given device should be freed now. No further
     *      commands will be sent for this sdp instance. [However the device
     *      could be re-attached in the future in which case a new instance
-    *      of struct scsi_device would be supplied by future slave_alloc()
-    *      and slave_configure() calls.]
+    *      of struct scsi_device would be supplied by future sdev_init()
+    *      and sdev_configure() calls.]
     *
     *      Optionally defined in: LLD
     **/
-	void slave_destroy(struct scsi_device *sdp)
+	void sdev_destroy(struct scsi_device *sdp)
 
 
 
@@ -1039,7 +986,7 @@ struct scsi_host_template
 There is one "struct scsi_host_template" instance per LLD [#]_. It is
 typically initialized as a file scope static in a driver's header file. That
 way members that are not explicitly initialized will be set to 0 or NULL.
-Member of interest:
+Members of interest:
 
     name
 		 - name of driver (may contain spaces, please limit to
@@ -1055,6 +1002,13 @@ Member of interest:
 		 - primary callback that the mid level uses to inject
                    SCSI commands into an LLD.
 
+    vendor_id
+		 - a unique value that identifies the vendor supplying
+                   the LLD for the Scsi_Host.  Used most often in validating
+                   vendor-specific message requests.  Value consists of an
+                   identifier type and a vendor-specific value.
+                   See scsi_netlink.h for a description of valid formats.
+
 The structure is defined and commented in include/scsi/scsi_host.h
 
 .. [#] In extreme situations a single driver may have several instances
@@ -1095,9 +1049,6 @@ of interest:
 		 - maximum number of commands that can be queued on devices
                    controlled by the host. Overridden by LLD calls to
                    scsi_change_queue_depth().
-    no_async_abort
-		 - 1=>Asynchronous aborts are not supported
-		 - 0=>Timed-out commands will be aborted asynchronously
     hostt
 		 - pointer to driver's struct scsi_host_template from which
                    this struct Scsi_Host instance was spawned
@@ -1106,22 +1057,10 @@ of interest:
     transportt
 		 - pointer to driver's struct scsi_transport_template instance
                    (if any). FC and SPI transports currently supported.
-    sh_list
-		 - a double linked list of pointers to all struct Scsi_Host
-                   instances (currently ordered by ascending host_no)
-    my_devices
-		 - a double linked list of pointers to struct scsi_device
-                   instances that belong to this host.
     hostdata[0]
 		 - area reserved for LLD at end of struct Scsi_Host. Size
-                   is set by the second argument (named 'xtr_bytes') to
-                   scsi_host_alloc() or scsi_register().
-    vendor_id
-		 - a unique value that identifies the vendor supplying
-                   the LLD for the Scsi_Host.  Used most often in validating
-                   vendor-specific message requests.  Value consists of an
-                   identifier type and a vendor-specific value.
-                   See scsi_netlink.h for a description of valid formats.
+                   is set by the second argument (named 'privsize') to
+                   scsi_host_alloc().
 
 The scsi_host structure is defined in include/scsi/scsi_host.h
 
@@ -1143,30 +1082,11 @@ Members of interest:
 
     cmnd
 		 - array containing SCSI command
-    cmnd_len
+    cmd_len
 		 - length (in bytes) of SCSI command
     sc_data_direction
 		 - direction of data transfer in data phase. See
                    "enum dma_data_direction" in include/linux/dma-mapping.h
-    request_bufflen
-		 - number of data bytes to transfer (0 if no data phase)
-    use_sg
-		 - ==0 -> no scatter gather list, hence transfer data
-                          to/from request_buffer
-                 - >0 ->  scatter gather list (actually an array) in
-                          request_buffer with use_sg elements
-    request_buffer
-		   - either contains data buffer or scatter gather list
-                     depending on the setting of use_sg. Scatter gather
-                     elements are defined by 'struct scatterlist' found
-                     in include/linux/scatterlist.h .
-    done
-		 - function pointer that should be invoked by LLD when the
-                   SCSI command is completed (successfully or otherwise).
-                   Should only be called by an LLD if the LLD has accepted
-                   the command (i.e. queuecommand() returned or will return
-                   0). The LLD may invoke 'done'  prior to queuecommand()
-                   finishing.
     result
 		 - should be set by LLD prior to calling 'done'. A value
                    of 0 implies a successfully completed command (and all
@@ -1189,13 +1109,13 @@ Members of interest:
     device
 		 - pointer to scsi_device object that this command is
                    associated with.
-    resid
+    resid_len   (access by calling scsi_set_resid() / scsi_get_resid())
 		 - an LLD should set this unsigned integer to the requested
                    transfer length (i.e. 'request_bufflen') less the number
-                   of bytes that are actually transferred. 'resid' is
+                   of bytes that are actually transferred. 'resid_len' is
                    preset to 0 so an LLD can ignore it if it cannot detect
                    underruns (overruns should not be reported). An LLD
-                   should set 'resid' prior to invoking 'done'. The most
+                   should set 'resid_len' prior to invoking 'done'. The most
                    interesting case is data transfers from a SCSI target
                    device (e.g. READs) that underrun.
     underflow
@@ -1204,10 +1124,10 @@ Members of interest:
                    figure. Not many LLDs implement this check and some that
                    do just output an error message to the log rather than
                    report a DID_ERROR. Better for an LLD to implement
-                   'resid'.
+                   'resid_len'.
 
-It is recommended that a LLD set 'resid' on data transfers from a SCSI
-target device (e.g. READs). It is especially important that 'resid' is set
+It is recommended that a LLD set 'resid_len' on data transfers from a SCSI
+target device (e.g. READs). It is especially important that 'resid_len' is set
 when such data transfers have sense keys of MEDIUM ERROR and HARDWARE ERROR
 (and possibly RECOVERED ERROR). In these cases if a LLD is in doubt how much
 data has been received then the safest approach is to indicate no bytes have
@@ -1217,7 +1137,7 @@ a LLD might use these helpers::
     scsi_set_resid(SCpnt, scsi_bufflen(SCpnt));
 
 where 'SCpnt' is a pointer to a scsi_cmnd object. To indicate only three 512
-bytes blocks has been received 'resid' could be set like this::
+bytes blocks have been received 'resid_len' could be set like this::
 
     scsi_set_resid(SCpnt, scsi_bufflen(SCpnt) - (3 * 512));
 
diff --git a/Documentation/sunrpc/xdr/nfs4_1.x b/Documentation/sunrpc/xdr/nfs4_1.x
new file mode 100644
index 000000000000..ca95150a3a29
--- /dev/null
+++ b/Documentation/sunrpc/xdr/nfs4_1.x
@@ -0,0 +1,186 @@
+/*
+ * Copyright (c) 2010 IETF Trust and the persons identified
+ * as the document authors.  All rights reserved.
+ *
+ * The document authors are identified in RFC 3530 and
+ * RFC 5661.
+ *
+ * Redistribution and use in source and binary forms, with
+ * or without modification, are permitted provided that the
+ * following conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ *   copyright notice, this list of conditions and the
+ *   following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ *   copyright notice, this list of conditions and the
+ *   following disclaimer in the documentation and/or other
+ *   materials provided with the distribution.
+ *
+ * - Neither the name of Internet Society, IETF or IETF
+ *   Trust, nor the names of specific contributors, may be
+ *   used to endorse or promote products derived from this
+ *   software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS
+ *   AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED
+ *   WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ *   IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ *   FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
+ *   EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ *   LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+ *   EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+ *   NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+ *   SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *   INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *   LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ *   OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ *   IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ *   ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+pragma header nfs4;
+
+/*
+ * Basic typedefs for RFC 1832 data type definitions
+ */
+typedef hyper		int64_t;
+typedef unsigned int	uint32_t;
+
+/*
+ * Basic data types
+ */
+typedef uint32_t	bitmap4<>;
+
+/*
+ * Timeval
+ */
+struct nfstime4 {
+	int64_t		seconds;
+	uint32_t	nseconds;
+};
+
+
+/*
+ * The following content was extracted from draft-ietf-nfsv4-delstid
+ */
+
+typedef bool            fattr4_offline;
+
+
+const FATTR4_OFFLINE            = 83;
+
+
+struct open_arguments4 {
+  bitmap4  oa_share_access;
+  bitmap4  oa_share_deny;
+  bitmap4  oa_share_access_want;
+  bitmap4  oa_open_claim;
+  bitmap4  oa_create_mode;
+};
+
+
+enum open_args_share_access4 {
+   OPEN_ARGS_SHARE_ACCESS_READ  = 1,
+   OPEN_ARGS_SHARE_ACCESS_WRITE = 2,
+   OPEN_ARGS_SHARE_ACCESS_BOTH  = 3
+};
+
+
+enum open_args_share_deny4 {
+   OPEN_ARGS_SHARE_DENY_NONE  = 0,
+   OPEN_ARGS_SHARE_DENY_READ  = 1,
+   OPEN_ARGS_SHARE_DENY_WRITE = 2,
+   OPEN_ARGS_SHARE_DENY_BOTH  = 3
+};
+
+
+enum open_args_share_access_want4 {
+   OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG           = 3,
+   OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG            = 4,
+   OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL              = 5,
+   OPEN_ARGS_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL
+                                                   = 17,
+   OPEN_ARGS_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED
+                                                   = 18,
+   OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS    = 20,
+   OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 21
+};
+
+
+enum open_args_open_claim4 {
+   OPEN_ARGS_OPEN_CLAIM_NULL          = 0,
+   OPEN_ARGS_OPEN_CLAIM_PREVIOUS      = 1,
+   OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR  = 2,
+   OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV = 3,
+   OPEN_ARGS_OPEN_CLAIM_FH            = 4,
+   OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH  = 5,
+   OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH = 6
+};
+
+
+enum open_args_createmode4 {
+   OPEN_ARGS_CREATEMODE_UNCHECKED4     = 0,
+   OPEN_ARGS_CREATE_MODE_GUARDED       = 1,
+   OPEN_ARGS_CREATEMODE_EXCLUSIVE4     = 2,
+   OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1  = 3
+};
+
+
+typedef open_arguments4 fattr4_open_arguments;
+pragma public fattr4_open_arguments;
+
+
+%/*
+% * Determine what OPEN supports.
+% */
+const FATTR4_OPEN_ARGUMENTS     = 86;
+
+
+
+
+const OPEN4_RESULT_NO_OPEN_STATEID = 0x00000010;
+
+
+/*
+ * attributes for the delegation times being
+ * cached and served by the "client"
+ */
+typedef nfstime4        fattr4_time_deleg_access;
+typedef nfstime4        fattr4_time_deleg_modify;
+pragma public 		fattr4_time_deleg_access;
+pragma public		fattr4_time_deleg_modify;
+
+
+%/*
+% * New RECOMMENDED Attribute for
+% * delegation caching of times
+% */
+const FATTR4_TIME_DELEG_ACCESS  = 84;
+const FATTR4_TIME_DELEG_MODIFY  = 85;
+
+
+
+/* new flags for share_access field of OPEN4args */
+const OPEN4_SHARE_ACCESS_WANT_DELEG_MASK        = 0xFF00;
+const OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE     = 0x0000;
+const OPEN4_SHARE_ACCESS_WANT_READ_DELEG        = 0x0100;
+const OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG       = 0x0200;
+const OPEN4_SHARE_ACCESS_WANT_ANY_DELEG         = 0x0300;
+const OPEN4_SHARE_ACCESS_WANT_NO_DELEG          = 0x0400;
+const OPEN4_SHARE_ACCESS_WANT_CANCEL            = 0x0500;
+
+const OPEN4_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 0x10000;
+const OPEN4_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 0x20000;
+const OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 0x100000;
+const OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 0x200000;
+
+enum open_delegation_type4 {
+       OPEN_DELEGATE_NONE                  = 0,
+       OPEN_DELEGATE_READ                  = 1,
+       OPEN_DELEGATE_WRITE                 = 2,
+       OPEN_DELEGATE_NONE_EXT              = 3, /* new to v4.1 */
+       OPEN_DELEGATE_READ_ATTRS_DELEG      = 4,
+       OPEN_DELEGATE_WRITE_ATTRS_DELEG     = 5
+};
diff --git a/Documentation/translations/sp_SP/index.rst b/Documentation/translations/sp_SP/index.rst
index aae7018b0d1a..2b50283e1608 100644
--- a/Documentation/translations/sp_SP/index.rst
+++ b/Documentation/translations/sp_SP/index.rst
@@ -7,7 +7,7 @@ Traducción al español
 
 	\kerneldocCJKoff
 
-:maintainer: Carlos Bilbao <carlos.bilbao.osdev@gmail.com>
+:maintainer: Carlos Bilbao <carlos.bilbao@kernel.org>
 
 .. _sp_disclaimer:
 
diff --git a/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst b/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst
index 50f6f0b6bf11..9d7cb51be493 100644
--- a/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst
+++ b/Documentation/translations/zh_CN/admin-guide/mm/damon/usage.rst
@@ -26,12 +26,7 @@ DAMON 为不同的用户提供了下面这些接口。
   使用它，用户可以通过读取和写入特殊的sysfs文件来使用DAMON的主要功能。因此，你可以编写和使
   用你个性化的DAMON sysfs包装程序，代替你读/写sysfs文件。  `DAMON用户空间工具
   <https://github.com/damonitor/damo>`_ 就是这种程序的一个例子  它同时支持虚拟和物理地址
-  空间的监测。注意，这个界面只提供简单的监测结果 :ref:`统计 <damos_stats>`。对于详细的监测
-  结果，DAMON提供了一个:ref:`跟踪点 <tracepoint>`。
-- *debugfs interface.*
-  :ref:`这 <debugfs_interface>` 几乎与:ref:`sysfs interface <sysfs_interface>` 接
-  口相同。这将在下一个LTS内核发布后被移除，所以用户应该转移到
-  :ref:`sysfs interface <sysfs_interface>`。
+  空间的监测。
 - *内核空间编程接口。*
   :doc:`这 </mm/damon/api>` 这是为内核空间程序员准备的。使用它，用户可以通过为你编写内
   核空间的DAMON应用程序，最灵活有效地利用DAMON的每一个功能。你甚至可以为各种地址空间扩展DAMON。
@@ -335,247 +330,6 @@ tried_regions/<N>/
 请注意，我们强烈建议使用用户空间的工具，如 `damo <https://github.com/damonitor/damo>`_ ，
 而不是像上面那样手动读写文件。以上只是一个例子。
 
-debugfs接口
-===========
-
-.. note::
-
-  DAMON debugfs接口将在下一个LTS内核发布后被移除，所以用户应该转移到
-  :ref:`sysfs接口<sysfs_interface>`。
-
-DAMON导出了八个文件, ``attrs``, ``target_ids``, ``init_regions``,
-``schemes``, ``monitor_on_DEPRECATED``, ``kdamond_pid``, ``mk_contexts`` 和
-``rm_contexts`` under its debugfs directory, ``<debugfs>/damon/``.
-
-
-属性
-----
-
-用户可以通过读取和写入 ``attrs`` 文件获得和设置 ``采样间隔`` 、 ``聚集间隔`` 、 ``更新间隔``
-以及监测目标区域的最小/最大数量。要详细了解监测属性，请参考 `:doc:/mm/damon/design` 。例如，
-下面的命令将这些值设置为5ms、100ms、1000ms、10和1000，然后再次检查::
-
-    # cd <debugfs>/damon
-    # echo 5000 100000 1000000 10 1000 > attrs
-    # cat attrs
-    5000 100000 1000000 10 1000
-
-
-目标ID
-------
-
-一些类型的地址空间支持多个监测目标。例如，虚拟内存地址空间的监测可以有多个进程作为监测目标。用户
-可以通过写入目标的相关id值来设置目标，并通过读取 ``target_ids`` 文件来获得当前目标的id。在监
-测虚拟地址空间的情况下，这些值应该是监测目标进程的pid。例如，下面的命令将pid为42和4242的进程设
-为监测目标，并再次检查::
-
-    # cd <debugfs>/damon
-    # echo 42 4242 > target_ids
-    # cat target_ids
-    42 4242
-
-用户还可以通过在文件中写入一个特殊的关键字 "paddr\n" 来监测系统的物理内存地址空间。因为物理地
-址空间监测不支持多个目标，读取文件会显示一个假值，即 ``42`` ，如下图所示::
-
-    # cd <debugfs>/damon
-    # echo paddr > target_ids
-    # cat target_ids
-    42
-
-请注意，设置目标ID并不启动监测。
-
-
-初始监测目标区域
-----------------
-
-在虚拟地址空间监测的情况下，DAMON自动设置和更新监测的目标区域，这样就可以覆盖目标进程的整个
-内存映射。然而，用户可能希望将监测区域限制在特定的地址范围内，如堆、栈或特定的文件映射区域。
-或者，一些用户可以知道他们工作负载的初始访问模式，因此希望为“自适应区域调整”设置最佳初始区域。
-
-相比之下，DAMON在物理内存监测的情况下不会自动设置和更新监测目标区域。因此，用户应该自己设置
-监测目标区域。
-
-在这种情况下，用户可以通过在 ``init_regions`` 文件中写入适当的值，明确地设置他们想要的初
-始监测目标区域。输入应该是一个由三个整数组成的队列，用空格隔开，代表一个区域的形式如下::
-
-    <target idx> <start address> <end address>
-
-目标idx应该是 ``target_ids`` 文件中目标的索引，从 ``0`` 开始，区域应该按照地址顺序传递。
-例如，下面的命令将设置几个地址范围， ``1-100`` 和 ``100-200`` 作为pid 42的初始监测目标
-区域，这是 ``target_ids`` 中的第一个（索引 ``0`` ），另外几个地址范围， ``20-40`` 和
-``50-100`` 作为pid 4242的地址，这是 ``target_ids`` 中的第二个（索引 ``1`` ）::
-
-    # cd <debugfs>/damon
-    # cat target_ids
-    42 4242
-    # echo "0   1       100 \
-            0   100     200 \
-            1   20      40  \
-            1   50      100" > init_regions
-
-请注意，这只是设置了初始的监测目标区域。在虚拟内存监测的情况下，DAMON会在一个 ``更新间隔``
-后自动更新区域的边界。因此，在这种情况下，如果用户不希望更新的话，应该把 ``更新间隔`` 设
-置得足够大。
-
-
-方案
-----
-
-对于通常的基于DAMON的数据访问感知的内存管理优化，用户只是希望系统对特定访问模式的内存区域应用内
-存管理操作。DAMON从用户那里接收这种形式化的操作方案，并将这些方案应用到目标进程中。
-
-用户可以通过读取和写入 ``scheme`` debugfs文件来获得和设置这些方案。读取该文件还可以显示每个
-方案的统计数据。在文件中，每一个方案都应该在每一行中以下列形式表示出来::
-
-    <target access pattern> <action> <quota> <watermarks>
-
-你可以通过简单地在文件中写入一个空字符串来禁用方案。
-
-目标访问模式
-~~~~~~~~~~~~
-
-``<目标访问模式>`` 是由三个范围构成的，形式如下::
-
-    min-size max-size min-acc max-acc min-age max-age
-
-具体来说，区域大小的字节数（ `min-size` 和 `max-size` ），访问频率的每聚合区间的监测访问次
-数（ `min-acc` 和 `max-acc` ），区域年龄的聚合区间数（ `min-age` 和 `max-age` ）都被指定。
-请注意，这些范围是封闭区间。
-
-动作
-~~~~
-
-``<action>`` 是一个预定义的内存管理动作的整数，DAMON将应用于具有目标访问模式的区域。支持
-的数字和它们的含义如下::
-
- - 0: Call ``madvise()`` for the region with ``MADV_WILLNEED``
- - 1: Call ``madvise()`` for the region with ``MADV_COLD``
- - 2: Call ``madvise()`` for the region with ``MADV_PAGEOUT``
- - 3: Call ``madvise()`` for the region with ``MADV_HUGEPAGE``
- - 4: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE``
- - 5: Do nothing but count the statistics
-
-配额
-~~~~
-
-每个 ``动作`` 的最佳 ``目标访问模式`` 取决于工作负载，所以不容易找到。更糟糕的是，将某个
-动作的方案设置得过于激进会导致严重的开销。为了避免这种开销，用户可以通过下面表格中的 ``<quota>``
-来限制方案的时间和大小配额::
-
-    <ms> <sz> <reset interval> <priority weights>
-
-这使得DAMON在 ``<reset interval>`` 毫秒内，尽量只用 ``<ms>`` 毫秒的时间对 ``目标访
-问模式`` 的内存区域应用动作，并在 ``<reset interval>`` 内只对最多<sz>字节的内存区域应
-用动作。将 ``<ms>`` 和 ``<sz>`` 都设置为零，可以禁用配额限制。
-
-当预计超过配额限制时，DAMON会根据 ``目标访问模式`` 的大小、访问频率和年龄，对发现的内存
-区域进行优先排序。为了实现个性化的优先级，用户可以在 ``<优先级权重>`` 中设置这三个属性的
-权重，具体形式如下::
-
-    <size weight> <access frequency weight> <age weight>
-
-水位
-~~~~
-
-有些方案需要根据系统特定指标的当前值来运行，如自由内存比率。对于这种情况，用户可以为该条
-件指定水位。::
-
-    <metric> <check interval> <high mark> <middle mark> <low mark>
-
-``<metric>`` 是一个预定义的整数，用于要检查的度量。支持的数字和它们的含义如下。
-
- - 0: 忽视水位
- - 1: 系统空闲内存率 (千分比)
-
-每隔 ``<检查间隔>`` 微秒检查一次公制的值。
-
-如果该值高于 ``<高标>`` 或低于 ``<低标>`` ，该方案被停用。如果该值低于 ``<中标>`` ，
-该方案将被激活。
-
-统计数据
-~~~~~~~~
-
-它还统计每个方案被尝试应用的区域的总数量和字节数，每个方案被成功应用的区域的两个数量，以
-及超过配额限制的总数量。这些统计数据可用于在线分析或调整方案。
-
-统计数据可以通过读取方案文件来显示。读取该文件将显示你在每一行中输入的每个 ``方案`` ，
-统计的五个数字将被加在每一行的末尾。
-
-例子
-~~~~
-
-下面的命令应用了一个方案：”如果一个大小为[4KiB, 8KiB]的内存区域在[10, 20]的聚合时间
-间隔内显示出每一个聚合时间间隔[0, 5]的访问量，请分页出该区域。对于分页，每秒最多只能使
-用10ms，而且每秒分页不能超过1GiB。在这一限制下，首先分页出具有较长年龄的内存区域。另外，
-每5秒钟检查一次系统的可用内存率，当可用内存率低于50%时开始监测和分页，但如果可用内存率
-大于60%，或低于30%，则停止监测“::
-
-    # cd <debugfs>/damon
-    # scheme="4096 8192  0 5    10 20    2"  # target access pattern and action
-    # scheme+=" 10 $((1024*1024*1024)) 1000" # quotas
-    # scheme+=" 0 0 100"                     # prioritization weights
-    # scheme+=" 1 5000000 600 500 300"       # watermarks
-    # echo "$scheme" > schemes
-
-
-开关
-----
-
-除非你明确地启动监测，否则如上所述的文件设置不会产生效果。你可以通过写入和读取 ``monitor_on_DEPRECATED``
-文件来启动、停止和检查监测的当前状态。写入 ``on`` 该文件可以启动对有属性的目标的监测。写入
-``off`` 该文件则停止这些目标。如果每个目标进程被终止，DAMON也会停止。下面的示例命令开启、关
-闭和检查DAMON的状态::
-
-    # cd <debugfs>/damon
-    # echo on > monitor_on_DEPRECATED
-    # echo off > monitor_on_DEPRECATED
-    # cat monitor_on_DEPRECATED
-    off
-
-请注意，当监测开启时，你不能写到上述的debugfs文件。如果你在DAMON运行时写到这些文件，将会返
-回一个错误代码，如 ``-EBUSY`` 。
-
-
-监测线程PID
------------
-
-DAMON通过一个叫做kdamond的内核线程来进行请求监测。你可以通过读取 ``kdamond_pid`` 文件获
-得该线程的 ``pid`` 。当监测被 ``关闭`` 时，读取该文件不会返回任何信息::
-
-    # cd <debugfs>/damon
-    # cat monitor_on_DEPRECATED
-    off
-    # cat kdamond_pid
-    none
-    # echo on > monitor_on_DEPRECATED
-    # cat kdamond_pid
-    18594
-
-
-使用多个监测线程
-----------------
-
-每个监测上下文都会创建一个 ``kdamond`` 线程。你可以使用 ``mk_contexts`` 和 ``rm_contexts``
-文件为多个 ``kdamond`` 需要的用例创建和删除监测上下文。
-
-将新上下文的名称写入 ``mk_contexts`` 文件，在 ``DAMON debugfs`` 目录上创建一个该名称的目录。
-该目录将有该上下文的 ``DAMON debugfs`` 文件::
-
-    # cd <debugfs>/damon
-    # ls foo
-    # ls: cannot access 'foo': No such file or directory
-    # echo foo > mk_contexts
-    # ls foo
-    # attrs  init_regions  kdamond_pid  schemes  target_ids
-
-如果不再需要上下文，你可以通过把上下文的名字放到 ``rm_contexts`` 文件中来删除它和相应的目录::
-
-    # echo foo > rm_contexts
-    # ls foo
-    # ls: cannot access 'foo': No such file or directory
-
-注意， ``mk_contexts`` 、 ``rm_contexts`` 和 ``monitor_on_DEPRECATED`` 文件只在根目录下。
-
 
 监测结果的监测点
 ================
diff --git a/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst b/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst
index fbbbbad59ee4..d3fd4f850793 100644
--- a/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst
+++ b/Documentation/translations/zh_TW/admin-guide/mm/damon/usage.rst
@@ -26,12 +26,7 @@ DAMON 爲不同的用戶提供了下面這些接口。
   使用它，用戶可以通過讀取和寫入特殊的sysfs文件來使用DAMON的主要功能。因此，你可以編寫和使
   用你個性化的DAMON sysfs包裝程序，代替你讀/寫sysfs文件。  `DAMON用戶空間工具
   <https://github.com/damonitor/damo>`_ 就是這種程序的一個例子  它同時支持虛擬和物理地址
-  空間的監測。注意，這個界面只提供簡單的監測結果 :ref:`統計 <damos_stats>`。對於詳細的監測
-  結果，DAMON提供了一個:ref:`跟蹤點 <tracepoint>`。
-- *debugfs interface.*
-  :ref:`這 <debugfs_interface>` 幾乎與:ref:`sysfs interface <sysfs_interface>` 接
-  口相同。這將在下一個LTS內核發佈後被移除，所以用戶應該轉移到
-  :ref:`sysfs interface <sysfs_interface>`。
+  空間的監測。
 - *內核空間編程接口。*
   :doc:`這 </mm/damon/api>` 這是爲內核空間程序員準備的。使用它，用戶可以通過爲你編寫內
   核空間的DAMON應用程序，最靈活有效地利用DAMON的每一個功能。你甚至可以爲各種地址空間擴展DAMON。
@@ -335,247 +330,6 @@ tried_regions/<N>/
 請注意，我們強烈建議使用用戶空間的工具，如 `damo <https://github.com/damonitor/damo>`_ ，
 而不是像上面那樣手動讀寫文件。以上只是一個例子。
 
-debugfs接口
-===========
-
-.. note::
-
-  DAMON debugfs接口將在下一個LTS內核發佈後被移除，所以用戶應該轉移到
-  :ref:`sysfs接口<sysfs_interface>`。
-
-DAMON導出了八個文件, ``attrs``, ``target_ids``, ``init_regions``,
-``schemes``, ``monitor_on_DEPRECATED``, ``kdamond_pid``, ``mk_contexts`` 和
-``rm_contexts`` under its debugfs directory, ``<debugfs>/damon/``.
-
-
-屬性
-----
-
-用戶可以通過讀取和寫入 ``attrs`` 文件獲得和設置 ``採樣間隔`` 、 ``聚集間隔`` 、 ``更新間隔``
-以及監測目標區域的最小/最大數量。要詳細瞭解監測屬性，請參考 `:doc:/mm/damon/design` 。例如，
-下面的命令將這些值設置爲5ms、100ms、1000ms、10和1000，然後再次檢查::
-
-    # cd <debugfs>/damon
-    # echo 5000 100000 1000000 10 1000 > attrs
-    # cat attrs
-    5000 100000 1000000 10 1000
-
-
-目標ID
-------
-
-一些類型的地址空間支持多個監測目標。例如，虛擬內存地址空間的監測可以有多個進程作爲監測目標。用戶
-可以通過寫入目標的相關id值來設置目標，並通過讀取 ``target_ids`` 文件來獲得當前目標的id。在監
-測虛擬地址空間的情況下，這些值應該是監測目標進程的pid。例如，下面的命令將pid爲42和4242的進程設
-爲監測目標，並再次檢查::
-
-    # cd <debugfs>/damon
-    # echo 42 4242 > target_ids
-    # cat target_ids
-    42 4242
-
-用戶還可以通過在文件中寫入一個特殊的關鍵字 "paddr\n" 來監測系統的物理內存地址空間。因爲物理地
-址空間監測不支持多個目標，讀取文件會顯示一個假值，即 ``42`` ，如下圖所示::
-
-    # cd <debugfs>/damon
-    # echo paddr > target_ids
-    # cat target_ids
-    42
-
-請注意，設置目標ID並不啓動監測。
-
-
-初始監測目標區域
-----------------
-
-在虛擬地址空間監測的情況下，DAMON自動設置和更新監測的目標區域，這樣就可以覆蓋目標進程的整個
-內存映射。然而，用戶可能希望將監測區域限制在特定的地址範圍內，如堆、棧或特定的文件映射區域。
-或者，一些用戶可以知道他們工作負載的初始訪問模式，因此希望爲“自適應區域調整”設置最佳初始區域。
-
-相比之下，DAMON在物理內存監測的情況下不會自動設置和更新監測目標區域。因此，用戶應該自己設置
-監測目標區域。
-
-在這種情況下，用戶可以通過在 ``init_regions`` 文件中寫入適當的值，明確地設置他們想要的初
-始監測目標區域。輸入應該是一個由三個整數組成的隊列，用空格隔開，代表一個區域的形式如下::
-
-    <target idx> <start address> <end address>
-
-目標idx應該是 ``target_ids`` 文件中目標的索引，從 ``0`` 開始，區域應該按照地址順序傳遞。
-例如，下面的命令將設置幾個地址範圍， ``1-100`` 和 ``100-200`` 作爲pid 42的初始監測目標
-區域，這是 ``target_ids`` 中的第一個（索引 ``0`` ），另外幾個地址範圍， ``20-40`` 和
-``50-100`` 作爲pid 4242的地址，這是 ``target_ids`` 中的第二個（索引 ``1`` ）::
-
-    # cd <debugfs>/damon
-    # cat target_ids
-    42 4242
-    # echo "0   1       100 \
-            0   100     200 \
-            1   20      40  \
-            1   50      100" > init_regions
-
-請注意，這只是設置了初始的監測目標區域。在虛擬內存監測的情況下，DAMON會在一個 ``更新間隔``
-後自動更新區域的邊界。因此，在這種情況下，如果用戶不希望更新的話，應該把 ``更新間隔`` 設
-置得足夠大。
-
-
-方案
-----
-
-對於通常的基於DAMON的數據訪問感知的內存管理優化，用戶只是希望系統對特定訪問模式的內存區域應用內
-存管理操作。DAMON從用戶那裏接收這種形式化的操作方案，並將這些方案應用到目標進程中。
-
-用戶可以通過讀取和寫入 ``scheme`` debugfs文件來獲得和設置這些方案。讀取該文件還可以顯示每個
-方案的統計數據。在文件中，每一個方案都應該在每一行中以下列形式表示出來::
-
-    <target access pattern> <action> <quota> <watermarks>
-
-你可以通過簡單地在文件中寫入一個空字符串來禁用方案。
-
-目標訪問模式
-~~~~~~~~~~~~
-
-``<目標訪問模式>`` 是由三個範圍構成的，形式如下::
-
-    min-size max-size min-acc max-acc min-age max-age
-
-具體來說，區域大小的字節數（ `min-size` 和 `max-size` ），訪問頻率的每聚合區間的監測訪問次
-數（ `min-acc` 和 `max-acc` ），區域年齡的聚合區間數（ `min-age` 和 `max-age` ）都被指定。
-請注意，這些範圍是封閉區間。
-
-動作
-~~~~
-
-``<action>`` 是一個預定義的內存管理動作的整數，DAMON將應用於具有目標訪問模式的區域。支持
-的數字和它們的含義如下::
-
- - 0: Call ``madvise()`` for the region with ``MADV_WILLNEED``
- - 1: Call ``madvise()`` for the region with ``MADV_COLD``
- - 2: Call ``madvise()`` for the region with ``MADV_PAGEOUT``
- - 3: Call ``madvise()`` for the region with ``MADV_HUGEPAGE``
- - 4: Call ``madvise()`` for the region with ``MADV_NOHUGEPAGE``
- - 5: Do nothing but count the statistics
-
-配額
-~~~~
-
-每個 ``動作`` 的最佳 ``目標訪問模式`` 取決於工作負載，所以不容易找到。更糟糕的是，將某個
-動作的方案設置得過於激進會導致嚴重的開銷。爲了避免這種開銷，用戶可以通過下面表格中的 ``<quota>``
-來限制方案的時間和大小配額::
-
-    <ms> <sz> <reset interval> <priority weights>
-
-這使得DAMON在 ``<reset interval>`` 毫秒內，儘量只用 ``<ms>`` 毫秒的時間對 ``目標訪
-問模式`` 的內存區域應用動作，並在 ``<reset interval>`` 內只對最多<sz>字節的內存區域應
-用動作。將 ``<ms>`` 和 ``<sz>`` 都設置爲零，可以禁用配額限制。
-
-當預計超過配額限制時，DAMON會根據 ``目標訪問模式`` 的大小、訪問頻率和年齡，對發現的內存
-區域進行優先排序。爲了實現個性化的優先級，用戶可以在 ``<優先級權重>`` 中設置這三個屬性的
-權重，具體形式如下::
-
-    <size weight> <access frequency weight> <age weight>
-
-水位
-~~~~
-
-有些方案需要根據系統特定指標的當前值來運行，如自由內存比率。對於這種情況，用戶可以爲該條
-件指定水位。::
-
-    <metric> <check interval> <high mark> <middle mark> <low mark>
-
-``<metric>`` 是一個預定義的整數，用於要檢查的度量。支持的數字和它們的含義如下。
-
- - 0: 忽視水位
- - 1: 系統空閒內存率 (千分比)
-
-每隔 ``<檢查間隔>`` 微秒檢查一次公制的值。
-
-如果該值高於 ``<高標>`` 或低於 ``<低標>`` ，該方案被停用。如果該值低於 ``<中標>`` ，
-該方案將被激活。
-
-統計數據
-~~~~~~~~
-
-它還統計每個方案被嘗試應用的區域的總數量和字節數，每個方案被成功應用的區域的兩個數量，以
-及超過配額限制的總數量。這些統計數據可用於在線分析或調整方案。
-
-統計數據可以通過讀取方案文件來顯示。讀取該文件將顯示你在每一行中輸入的每個 ``方案`` ，
-統計的五個數字將被加在每一行的末尾。
-
-例子
-~~~~
-
-下面的命令應用了一個方案：”如果一個大小爲[4KiB, 8KiB]的內存區域在[10, 20]的聚合時間
-間隔內顯示出每一個聚合時間間隔[0, 5]的訪問量，請分頁出該區域。對於分頁，每秒最多隻能使
-用10ms，而且每秒分頁不能超過1GiB。在這一限制下，首先分頁出具有較長年齡的內存區域。另外，
-每5秒鐘檢查一次系統的可用內存率，當可用內存率低於50%時開始監測和分頁，但如果可用內存率
-大於60%，或低於30%，則停止監測“::
-
-    # cd <debugfs>/damon
-    # scheme="4096 8192  0 5    10 20    2"  # target access pattern and action
-    # scheme+=" 10 $((1024*1024*1024)) 1000" # quotas
-    # scheme+=" 0 0 100"                     # prioritization weights
-    # scheme+=" 1 5000000 600 500 300"       # watermarks
-    # echo "$scheme" > schemes
-
-
-開關
-----
-
-除非你明確地啓動監測，否則如上所述的文件設置不會產生效果。你可以通過寫入和讀取 ``monitor_on_DEPRECATED``
-文件來啓動、停止和檢查監測的當前狀態。寫入 ``on`` 該文件可以啓動對有屬性的目標的監測。寫入
-``off`` 該文件則停止這些目標。如果每個目標進程被終止，DAMON也會停止。下面的示例命令開啓、關
-閉和檢查DAMON的狀態::
-
-    # cd <debugfs>/damon
-    # echo on > monitor_on_DEPRECATED
-    # echo off > monitor_on_DEPRECATED
-    # cat monitor_on_DEPRECATED
-    off
-
-請注意，當監測開啓時，你不能寫到上述的debugfs文件。如果你在DAMON運行時寫到這些文件，將會返
-回一個錯誤代碼，如 ``-EBUSY`` 。
-
-
-監測線程PID
------------
-
-DAMON通過一個叫做kdamond的內核線程來進行請求監測。你可以通過讀取 ``kdamond_pid`` 文件獲
-得該線程的 ``pid`` 。當監測被 ``關閉`` 時，讀取該文件不會返回任何信息::
-
-    # cd <debugfs>/damon
-    # cat monitor_on_DEPRECATED
-    off
-    # cat kdamond_pid
-    none
-    # echo on > monitor_on_DEPRECATED
-    # cat kdamond_pid
-    18594
-
-
-使用多個監測線程
-----------------
-
-每個監測上下文都會創建一個 ``kdamond`` 線程。你可以使用 ``mk_contexts`` 和 ``rm_contexts``
-文件爲多個 ``kdamond`` 需要的用例創建和刪除監測上下文。
-
-將新上下文的名稱寫入 ``mk_contexts`` 文件，在 ``DAMON debugfs`` 目錄上創建一個該名稱的目錄。
-該目錄將有該上下文的 ``DAMON debugfs`` 文件::
-
-    # cd <debugfs>/damon
-    # ls foo
-    # ls: cannot access 'foo': No such file or directory
-    # echo foo > mk_contexts
-    # ls foo
-    # attrs  init_regions  kdamond_pid  schemes  target_ids
-
-如果不再需要上下文，你可以通過把上下文的名字放到 ``rm_contexts`` 文件中來刪除它和相應的目錄::
-
-    # echo foo > rm_contexts
-    # ls foo
-    # ls: cannot access 'foo': No such file or directory
-
-注意， ``mk_contexts`` 、 ``rm_contexts`` 和 ``monitor_on_DEPRECATED`` 文件只在根目錄下。
-
 
 監測結果的監測點
 ================
diff --git a/Documentation/usb/usbip_protocol.rst b/Documentation/usb/usbip_protocol.rst
index adc158967cc6..3da1df3d94f5 100644
--- a/Documentation/usb/usbip_protocol.rst
+++ b/Documentation/usb/usbip_protocol.rst
@@ -285,17 +285,17 @@ OP_REP_IMPORT:
 +-----------+--------+------------+---------------------------------------------------+
 | 0x138     | 2      |            | bcdDevice                                         |
 +-----------+--------+------------+---------------------------------------------------+
-| 0x139     | 1      |            | bDeviceClass                                      |
+| 0x13A     | 1      |            | bDeviceClass                                      |
 +-----------+--------+------------+---------------------------------------------------+
-| 0x13A     | 1      |            | bDeviceSubClass                                   |
+| 0x13B     | 1      |            | bDeviceSubClass                                   |
 +-----------+--------+------------+---------------------------------------------------+
-| 0x13B     | 1      |            | bDeviceProtocol                                   |
+| 0x13C     | 1      |            | bDeviceProtocol                                   |
 +-----------+--------+------------+---------------------------------------------------+
-| 0x13C     | 1      |            | bConfigurationValue                               |
+| 0x13D     | 1      |            | bConfigurationValue                               |
 +-----------+--------+------------+---------------------------------------------------+
-| 0x13D     | 1      |            | bNumConfigurations                                |
+| 0x13E     | 1      |            | bNumConfigurations                                |
 +-----------+--------+------------+---------------------------------------------------+
-| 0x13E     | 1      |            | bNumInterfaces                                    |
+| 0x13F     | 1      |            | bNumInterfaces                                    |
 +-----------+--------+------------+---------------------------------------------------+
 
 The following four commands have a common basic header called
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 6272bcf11296..b1395d94b3fd 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -64,6 +64,7 @@ Everything else
    vduse
    futex2
    perf_ring_buffer
+   ntsync
 
 .. only::  subproject and html
 
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 243f1f1b554a..6d1465315df3 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -283,6 +283,7 @@ Code  Seq#    Include File                                           Comments
 'p'   80-9F  linux/ppdev.h                                           user-space parport
                                                                      <mailto:tim@cyberelk.net>
 'p'   A1-A5  linux/pps.h                                             LinuxPPS
+'p'   B1-B3  linux/pps_gen.h                                         LinuxPPS
                                                                      <mailto:giometti@linux.it>
 'q'   00-1F  linux/serio.h
 'q'   80-FF  linux/telephony.h                                       Internet PhoneJACK, Internet LineJACK
@@ -311,6 +312,7 @@ Code  Seq#    Include File                                           Comments
                                                                      <mailto:oe@port.de>
 'z'   10-4F  drivers/s390/crypto/zcrypt_api.h                        conflict!
 '|'   00-7F  linux/media.h
+'|'   80-9F  samples/                                                Any sample and example drivers
 0x80  00-1F  linux/fb.h
 0x81  00-1F  linux/vduse.h
 0x89  00-06  arch/x86/include/asm/sockios.h
diff --git a/Documentation/userspace-api/ntsync.rst b/Documentation/userspace-api/ntsync.rst
new file mode 100644
index 000000000000..25e7c4aef968
--- /dev/null
+++ b/Documentation/userspace-api/ntsync.rst
@@ -0,0 +1,385 @@
+===================================
+NT synchronization primitive driver
+===================================
+
+This page documents the user-space API for the ntsync driver.
+
+ntsync is a support driver for emulation of NT synchronization
+primitives by user-space NT emulators. It exists because implementation
+in user-space, using existing tools, cannot match Windows performance
+while offering accurate semantics. It is implemented entirely in
+software, and does not drive any hardware device.
+
+This interface is meant as a compatibility tool only, and should not
+be used for general synchronization. Instead use generic, versatile
+interfaces such as futex(2) and poll(2).
+
+Synchronization primitives
+==========================
+
+The ntsync driver exposes three types of synchronization primitives:
+semaphores, mutexes, and events.
+
+A semaphore holds a single volatile 32-bit counter, and a static 32-bit
+integer denoting the maximum value. It is considered signaled (that is,
+can be acquired without contention, or will wake up a waiting thread)
+when the counter is nonzero. The counter is decremented by one when a
+wait is satisfied. Both the initial and maximum count are established
+when the semaphore is created.
+
+A mutex holds a volatile 32-bit recursion count, and a volatile 32-bit
+identifier denoting its owner. A mutex is considered signaled when its
+owner is zero (indicating that it is not owned). The recursion count is
+incremented when a wait is satisfied, and ownership is set to the given
+identifier.
+
+A mutex also holds an internal flag denoting whether its previous owner
+has died; such a mutex is said to be abandoned. Owner death is not
+tracked automatically based on thread death, but rather must be
+communicated using ``NTSYNC_IOC_MUTEX_KILL``. An abandoned mutex is
+inherently considered unowned.
+
+Except for the "unowned" semantics of zero, the actual value of the
+owner identifier is not interpreted by the ntsync driver at all. The
+intended use is to store a thread identifier; however, the ntsync
+driver does not actually validate that a calling thread provides
+consistent or unique identifiers.
+
+An event is similar to a semaphore with a maximum count of one. It holds
+a volatile boolean state denoting whether it is signaled or not. There
+are two types of events, auto-reset and manual-reset. An auto-reset
+event is designaled when a wait is satisfied; a manual-reset event is
+not. The event type is specified when the event is created.
+
+Unless specified otherwise, all operations on an object are atomic and
+totally ordered with respect to other operations on the same object.
+
+Objects are represented by files. When all file descriptors to an
+object are closed, that object is deleted.
+
+Char device
+===========
+
+The ntsync driver creates a single char device /dev/ntsync. Each file
+description opened on the device represents a unique instance intended
+to back an individual NT virtual machine. Objects created by one ntsync
+instance may only be used with other objects created by the same
+instance.
+
+ioctl reference
+===============
+
+All operations on the device are done through ioctls. There are four
+structures used in ioctl calls::
+
+   struct ntsync_sem_args {
+   	__u32 count;
+   	__u32 max;
+   };
+
+   struct ntsync_mutex_args {
+   	__u32 owner;
+   	__u32 count;
+   };
+
+   struct ntsync_event_args {
+   	__u32 signaled;
+   	__u32 manual;
+   };
+
+   struct ntsync_wait_args {
+   	__u64 timeout;
+   	__u64 objs;
+   	__u32 count;
+   	__u32 owner;
+   	__u32 index;
+   	__u32 alert;
+   	__u32 flags;
+   	__u32 pad;
+   };
+
+Depending on the ioctl, members of the structure may be used as input,
+output, or not at all.
+
+The ioctls on the device file are as follows:
+
+.. c:macro:: NTSYNC_IOC_CREATE_SEM
+
+  Create a semaphore object. Takes a pointer to struct
+  :c:type:`ntsync_sem_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``count``
+       - Initial count of the semaphore.
+     * - ``max``
+       - Maximum count of the semaphore.
+
+  Fails with ``EINVAL`` if ``count`` is greater than ``max``.
+  On success, returns a file descriptor the created semaphore.
+
+.. c:macro:: NTSYNC_IOC_CREATE_MUTEX
+
+  Create a mutex object. Takes a pointer to struct
+  :c:type:`ntsync_mutex_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``count``
+       - Initial recursion count of the mutex.
+     * - ``owner``
+       - Initial owner of the mutex.
+
+  If ``owner`` is nonzero and ``count`` is zero, or if ``owner`` is
+  zero and ``count`` is nonzero, the function fails with ``EINVAL``.
+  On success, returns a file descriptor the created mutex.
+
+.. c:macro:: NTSYNC_IOC_CREATE_EVENT
+
+  Create an event object. Takes a pointer to struct
+  :c:type:`ntsync_event_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``signaled``
+       - If nonzero, the event is initially signaled, otherwise
+         nonsignaled.
+     * - ``manual``
+       - If nonzero, the event is a manual-reset event, otherwise
+         auto-reset.
+
+  On success, returns a file descriptor the created event.
+
+The ioctls on the individual objects are as follows:
+
+.. c:macro:: NTSYNC_IOC_SEM_POST
+
+  Post to a semaphore object. Takes a pointer to a 32-bit integer,
+  which on input holds the count to be added to the semaphore, and on
+  output contains its previous count.
+
+  If adding to the semaphore's current count would raise the latter
+  past the semaphore's maximum count, the ioctl fails with
+  ``EOVERFLOW`` and the semaphore is not affected. If raising the
+  semaphore's count causes it to become signaled, eligible threads
+  waiting on this semaphore will be woken and the semaphore's count
+  decremented appropriately.
+
+.. c:macro:: NTSYNC_IOC_MUTEX_UNLOCK
+
+  Release a mutex object. Takes a pointer to struct
+  :c:type:`ntsync_mutex_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``owner``
+       - Specifies the owner trying to release this mutex.
+     * - ``count``
+       - On output, contains the previous recursion count.
+
+  If ``owner`` is zero, the ioctl fails with ``EINVAL``. If ``owner``
+  is not the current owner of the mutex, the ioctl fails with
+  ``EPERM``.
+
+  The mutex's count will be decremented by one. If decrementing the
+  mutex's count causes it to become zero, the mutex is marked as
+  unowned and signaled, and eligible threads waiting on it will be
+  woken as appropriate.
+
+.. c:macro:: NTSYNC_IOC_SET_EVENT
+
+  Signal an event object. Takes a pointer to a 32-bit integer, which on
+  output contains the previous state of the event.
+
+  Eligible threads will be woken, and auto-reset events will be
+  designaled appropriately.
+
+.. c:macro:: NTSYNC_IOC_RESET_EVENT
+
+  Designal an event object. Takes a pointer to a 32-bit integer, which
+  on output contains the previous state of the event.
+
+.. c:macro:: NTSYNC_IOC_PULSE_EVENT
+
+  Wake threads waiting on an event object while leaving it in an
+  unsignaled state. Takes a pointer to a 32-bit integer, which on
+  output contains the previous state of the event.
+
+  A pulse operation can be thought of as a set followed by a reset,
+  performed as a single atomic operation. If two threads are waiting on
+  an auto-reset event which is pulsed, only one will be woken. If two
+  threads are waiting a manual-reset event which is pulsed, both will
+  be woken. However, in both cases, the event will be unsignaled
+  afterwards, and a simultaneous read operation will always report the
+  event as unsignaled.
+
+.. c:macro:: NTSYNC_IOC_READ_SEM
+
+  Read the current state of a semaphore object. Takes a pointer to
+  struct :c:type:`ntsync_sem_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``count``
+       - On output, contains the current count of the semaphore.
+     * - ``max``
+       - On output, contains the maximum count of the semaphore.
+
+.. c:macro:: NTSYNC_IOC_READ_MUTEX
+
+  Read the current state of a mutex object. Takes a pointer to struct
+  :c:type:`ntsync_mutex_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``owner``
+       - On output, contains the current owner of the mutex, or zero
+         if the mutex is not currently owned.
+     * - ``count``
+       - On output, contains the current recursion count of the mutex.
+
+  If the mutex is marked as abandoned, the function fails with
+  ``EOWNERDEAD``. In this case, ``count`` and ``owner`` are set to
+  zero.
+
+.. c:macro:: NTSYNC_IOC_READ_EVENT
+
+  Read the current state of an event object. Takes a pointer to struct
+  :c:type:`ntsync_event_args`, which is used as follows:
+
+  .. list-table::
+
+     * - ``signaled``
+       - On output, contains the current state of the event.
+     * - ``manual``
+       - On output, contains 1 if the event is a manual-reset event,
+         and 0 otherwise.
+
+.. c:macro:: NTSYNC_IOC_KILL_OWNER
+
+  Mark a mutex as unowned and abandoned if it is owned by the given
+  owner. Takes an input-only pointer to a 32-bit integer denoting the
+  owner. If the owner is zero, the ioctl fails with ``EINVAL``. If the
+  owner does not own the mutex, the function fails with ``EPERM``.
+
+  Eligible threads waiting on the mutex will be woken as appropriate
+  (and such waits will fail with ``EOWNERDEAD``, as described below).
+
+.. c:macro:: NTSYNC_IOC_WAIT_ANY
+
+  Poll on any of a list of objects, atomically acquiring at most one.
+  Takes a pointer to struct :c:type:`ntsync_wait_args`, which is
+  used as follows:
+
+  .. list-table::
+
+     * - ``timeout``
+       - Absolute timeout in nanoseconds. If ``NTSYNC_WAIT_REALTIME``
+         is set, the timeout is measured against the REALTIME clock;
+         otherwise it is measured against the MONOTONIC clock. If the
+         timeout is equal to or earlier than the current time, the
+         function returns immediately without sleeping. If ``timeout``
+         is U64_MAX, the function will sleep until an object is
+         signaled, and will not fail with ``ETIMEDOUT``.
+     * - ``objs``
+       - Pointer to an array of ``count`` file descriptors
+         (specified as an integer so that the structure has the same
+         size regardless of architecture). If any object is
+         invalid, the function fails with ``EINVAL``.
+     * - ``count``
+       - Number of objects specified in the ``objs`` array.
+         If greater than ``NTSYNC_MAX_WAIT_COUNT``, the function fails
+         with ``EINVAL``.
+     * - ``owner``
+       - Mutex owner identifier. If any object in ``objs`` is a mutex,
+         the ioctl will attempt to acquire that mutex on behalf of
+         ``owner``. If ``owner`` is zero, the ioctl fails with
+         ``EINVAL``.
+     * - ``index``
+       - On success, contains the index (into ``objs``) of the object
+         which was signaled. If ``alert`` was signaled instead,
+         this contains ``count``.
+     * - ``alert``
+       - Optional event object file descriptor. If nonzero, this
+         specifies an "alert" event object which, if signaled, will
+         terminate the wait. If nonzero, the identifier must point to a
+         valid event.
+     * - ``flags``
+       - Zero or more flags. Currently the only flag is
+         ``NTSYNC_WAIT_REALTIME``, which causes the timeout to be
+         measured against the REALTIME clock instead of MONOTONIC.
+     * - ``pad``
+       - Unused, must be set to zero.
+
+  This function attempts to acquire one of the given objects. If unable
+  to do so, it sleeps until an object becomes signaled, subsequently
+  acquiring it, or the timeout expires. In the latter case the ioctl
+  fails with ``ETIMEDOUT``. The function only acquires one object, even
+  if multiple objects are signaled.
+
+  A semaphore is considered to be signaled if its count is nonzero, and
+  is acquired by decrementing its count by one. A mutex is considered
+  to be signaled if it is unowned or if its owner matches the ``owner``
+  argument, and is acquired by incrementing its recursion count by one
+  and setting its owner to the ``owner`` argument. An auto-reset event
+  is acquired by designaling it; a manual-reset event is not affected
+  by acquisition.
+
+  Acquisition is atomic and totally ordered with respect to other
+  operations on the same object. If two wait operations (with different
+  ``owner`` identifiers) are queued on the same mutex, only one is
+  signaled. If two wait operations are queued on the same semaphore,
+  and a value of one is posted to it, only one is signaled.
+
+  If an abandoned mutex is acquired, the ioctl fails with
+  ``EOWNERDEAD``. Although this is a failure return, the function may
+  otherwise be considered successful. The mutex is marked as owned by
+  the given owner (with a recursion count of 1) and as no longer
+  abandoned, and ``index`` is still set to the index of the mutex.
+
+  The ``alert`` argument is an "extra" event which can terminate the
+  wait, independently of all other objects.
+
+  It is valid to pass the same object more than once, including by
+  passing the same event in the ``objs`` array and in ``alert``. If a
+  wakeup occurs due to that object being signaled, ``index`` is set to
+  the lowest index corresponding to that object.
+
+  The function may fail with ``EINTR`` if a signal is received.
+
+.. c:macro:: NTSYNC_IOC_WAIT_ALL
+
+  Poll on a list of objects, atomically acquiring all of them. Takes a
+  pointer to struct :c:type:`ntsync_wait_args`, which is used
+  identically to ``NTSYNC_IOC_WAIT_ANY``, except that ``index`` is
+  always filled with zero on success if not woken via alert.
+
+  This function attempts to simultaneously acquire all of the given
+  objects. If unable to do so, it sleeps until all objects become
+  simultaneously signaled, subsequently acquiring them, or the timeout
+  expires. In the latter case the ioctl fails with ``ETIMEDOUT`` and no
+  objects are modified.
+
+  Objects may become signaled and subsequently designaled (through
+  acquisition by other threads) while this thread is sleeping. Only
+  once all objects are simultaneously signaled does the ioctl acquire
+  them and return. The entire acquisition is atomic and totally ordered
+  with respect to other operations on any of the given objects.
+
+  If an abandoned mutex is acquired, the ioctl fails with
+  ``EOWNERDEAD``. Similarly to ``NTSYNC_IOC_WAIT_ANY``, all objects are
+  nevertheless marked as acquired. Note that if multiple mutex objects
+  are specified, there is no way to know which were marked as
+  abandoned.
+
+  As with "any" waits, the ``alert`` argument is an "extra" event which
+  can terminate the wait. Critically, however, an "all" wait will
+  succeed if all members in ``objs`` are signaled, *or* if ``alert`` is
+  signaled. In the latter case ``index`` will be set to ``count``. As
+  with "any" waits, if both conditions are filled, the former takes
+  priority, and objects in ``objs`` will be acquired.
+
+  Unlike ``NTSYNC_IOC_WAIT_ANY``, it is not valid to pass the same
+  object more than once, nor is it valid to pass the same object in
+  ``objs`` and in ``alert``. If this is attempted, the function fails
+  with ``EINVAL``.
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 0d1c3a820ce6..2b52eb77e29c 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1419,7 +1419,7 @@ fetch) is injected in the guest.
 S390:
 ^^^^^
 
-Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set.
+Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set.
 Returns -EINVAL if called on a protected VM.
 
 4.36 KVM_SET_TSS_ADDR
diff --git a/Documentation/virt/kvm/devices/vcpu.rst b/Documentation/virt/kvm/devices/vcpu.rst
index 31f14ec4a65b..31a9576c07af 100644
--- a/Documentation/virt/kvm/devices/vcpu.rst
+++ b/Documentation/virt/kvm/devices/vcpu.rst
@@ -142,8 +142,8 @@ the cpu field to the processor id.
 
 :Architectures: ARM64
 
-2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_VTIMER, KVM_ARM_VCPU_TIMER_IRQ_PTIMER
------------------------------------------------------------------------------
+2.1. ATTRIBUTES: KVM_ARM_VCPU_TIMER_IRQ_{VTIMER,PTIMER,HVTIMER,HPTIMER}
+-----------------------------------------------------------------------
 
 :Parameters: in kvm_device_attr.addr the address for the timer interrupt is a
 	     pointer to an int
@@ -159,10 +159,12 @@ A value describing the architected timer interrupt number when connected to an
 in-kernel virtual GIC.  These must be a PPI (16 <= intid < 32).  Setting the
 attribute overrides the default values (see below).
 
-=============================  ==========================================
-KVM_ARM_VCPU_TIMER_IRQ_VTIMER  The EL1 virtual timer intid (default: 27)
-KVM_ARM_VCPU_TIMER_IRQ_PTIMER  The EL1 physical timer intid (default: 30)
-=============================  ==========================================
+==============================  ==========================================
+KVM_ARM_VCPU_TIMER_IRQ_VTIMER   The EL1 virtual timer intid (default: 27)
+KVM_ARM_VCPU_TIMER_IRQ_PTIMER   The EL1 physical timer intid (default: 30)
+KVM_ARM_VCPU_TIMER_IRQ_HVTIMER  The EL2 virtual timer intid (default: 28)
+KVM_ARM_VCPU_TIMER_IRQ_HPTIMER  The EL2 physical timer intid (default: 26)
+==============================  ==========================================
 
 Setting the same PPI for different timers will prevent the VCPUs from running.
 Setting the interrupt number on a VCPU configures all VCPUs created at that
diff --git a/MAINTAINERS b/MAINTAINERS
index 8baa5a900b45..25c86f47353d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -987,6 +987,12 @@ L:	linux-edac@vger.kernel.org
 S:	Supported
 F:	drivers/ras/amd/atl/*
 
+AMD AE4DMA DRIVER
+M:	Basavaraj Natikar <Basavaraj.Natikar@amd.com>
+L:	dmaengine@vger.kernel.org
+S:	Supported
+F:	drivers/dma/amd/ae4dma/
+
 AMD AXI W1 DRIVER
 M:	Kris Chaplin <kris.chaplin@amd.com>
 R:	Thomas Delev <thomas.delev@amd.com>
@@ -1084,7 +1090,7 @@ F:	drivers/video/fbdev/geode/
 
 AMD HSMP DRIVER
 M:	Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com>
-R:	Carlos Bilbao <carlos.bilbao.osdev@gmail.com>
+R:	Carlos Bilbao <carlos.bilbao@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	Documentation/arch/x86/amd_hsmp.rst
@@ -1179,8 +1185,8 @@ F:	tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py
 AMD PTDMA DRIVER
 M:	Basavaraj Natikar <Basavaraj.Natikar@amd.com>
 L:	dmaengine@vger.kernel.org
-S:	Maintained
-F:	drivers/dma/ptdma/
+S:	Supported
+F:	drivers/dma/amd/ptdma/
 
 AMD QDMA DRIVER
 M:	Nishad Saraf <nishads@amd.com>
@@ -1318,7 +1324,7 @@ W:	https://ez.analog.com/linux-software-drivers
 F:	Documentation/devicetree/bindings/iio/adc/adi,ad4695.yaml
 F:	Documentation/iio/ad4695.rst
 F:	drivers/iio/adc/ad4695.c
-F:	include/dt-bindings/iio/adi,ad4695.h
+F:	include/dt-bindings/iio/adc/adi,ad4695.h
 
 ANALOG DEVICES INC AD7091R DRIVER
 M:	Marcelo Schmitt <marcelo.schmitt@analog.com>
@@ -2203,7 +2209,6 @@ F:	sound/soc/codecs/cs42l84.*
 F:	sound/soc/codecs/ssm3515.c
 
 ARM/APPLE MACHINE SUPPORT
-M:	Hector Martin <marcan@marcan.st>
 M:	Sven Peter <sven@svenpeter.dev>
 R:	Alyssa Rosenzweig <alyssa@rosenzweig.io>
 L:	asahi@lists.linux.dev
@@ -2864,7 +2869,7 @@ ARM/NXP S32G ARCHITECTURE
 R:	Chester Lin <chester62515@gmail.com>
 R:	Matthias Brugger <mbrugger@suse.com>
 R:	Ghennadi Procopciuc <ghennadi.procopciuc@oss.nxp.com>
-L:	NXP S32 Linux Team <s32@nxp.com>
+R:	NXP S32 Linux Team <s32@nxp.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm64/boot/dts/freescale/s32g*.dts*
@@ -3949,6 +3954,7 @@ M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcachefs@vger.kernel.org
 S:	Supported
 C:	irc://irc.oftc.net/bcache
+P:      Documentation/filesystems/bcachefs/SubmittingPatches.rst
 T:	git https://evilpiepirate.org/git/bcachefs.git
 F:	fs/bcachefs/
 F:	Documentation/filesystems/bcachefs/
@@ -4096,6 +4102,7 @@ S:	Supported
 W:	http://www.bluez.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git
+F:	Documentation/ABI/stable/sysfs-class-bluetooth
 F:	include/net/bluetooth/
 F:	net/bluetooth/
 
@@ -5366,6 +5373,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
 F:	drivers/char/
 F:	drivers/misc/
 F:	include/linux/miscdevice.h
+F:	samples/rust/rust_misc_device.rs
 X:	drivers/char/agp/
 X:	drivers/char/hw_random/
 X:	drivers/char/ipmi/
@@ -5481,9 +5489,12 @@ F:	include/linux/platform_data/cros_usbpd_notify.h
 
 CHROMEOS EC USB TYPE-C DRIVER
 M:	Prashant Malani <pmalani@chromium.org>
+M:	Benson Leung <bleung@chromium.org>
+M:	Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
 L:	chrome-platform@lists.linux.dev
 S:	Maintained
 F:	drivers/platform/chrome/cros_ec_typec.*
+F:	drivers/platform/chrome/cros_typec_altmode.*
 F:	drivers/platform/chrome/cros_typec_switch.c
 F:	drivers/platform/chrome/cros_typec_vdm.*
 
@@ -5499,6 +5510,13 @@ L:	chrome-platform@lists.linux.dev
 S:	Maintained
 F:	drivers/watchdog/cros_ec_wdt.c
 
+CHROMEOS UCSI DRIVER
+M:	Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
+M:	Łukasz Bartosik <ukaszb@chromium.org>
+L:	chrome-platform@lists.linux.dev
+S:	Maintained
+F:	drivers/usb/typec/ucsi/cros_ec_ucsi.c
+
 CHRONTEL CH7322 CEC DRIVER
 M:	Joe Tessler <jrt@google.com>
 L:	linux-media@vger.kernel.org
@@ -5839,7 +5857,7 @@ F:	drivers/usb/atm/cxacru.c
 
 CONFIDENTIAL COMPUTING THREAT MODEL FOR X86 VIRTUALIZATION (SNP/TDX)
 M:	Elena Reshetova <elena.reshetova@intel.com>
-M:	Carlos Bilbao <carlos.bilbao.osdev@gmail.com>
+M:	Carlos Bilbao <carlos.bilbao@kernel.org>
 S:	Maintained
 F:	Documentation/security/snp-tdx-threat-model.rst
 
@@ -6394,6 +6412,7 @@ F:	Documentation/mm/damon/
 F:	include/linux/damon.h
 F:	include/trace/events/damon.h
 F:	mm/damon/
+F:	samples/damon/
 F:	tools/testing/selftests/damon/
 
 DAVICOM FAST ETHERNET (DMFE) NETWORK DRIVER
@@ -7080,6 +7099,7 @@ F:	include/linux/component.h
 DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 R:	"Rafael J. Wysocki" <rafael@kernel.org>
+R:	Danilo Krummrich <dakr@kernel.org>
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
 F:	Documentation/core-api/kobject.rst
@@ -7090,8 +7110,14 @@ F:	include/linux/debugfs.h
 F:	include/linux/fwnode.h
 F:	include/linux/kobj*
 F:	include/linux/property.h
+F:	include/linux/sysfs.h
 F:	lib/kobj*
 F:	rust/kernel/device.rs
+F:	rust/kernel/device_id.rs
+F:	rust/kernel/devres.rs
+F:	rust/kernel/driver.rs
+F:	rust/kernel/platform.rs
+F:	samples/rust/rust_driver_platform.rs
 
 DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS)
 M:	Nishanth Menon <nm@ti.com>
@@ -8699,6 +8725,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon.git
 F:	Documentation/devicetree/bindings/extcon/
+F:	Documentation/driver-api/extcon.rst
 F:	Documentation/firmware-guide/acpi/extcon-intel-int3496.rst
 F:	drivers/extcon/
 F:	include/linux/extcon.h
@@ -9391,7 +9418,7 @@ F:	fs/freevxfs/
 
 FREEZER
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
-M:	Pavel Machek <pavel@ucw.cz>
+M:	Pavel Machek <pavel@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	Documentation/power/freezing-of-tasks.rst
@@ -9614,6 +9641,13 @@ W:	https://linuxtv.org
 T:	git git://linuxtv.org/media.git
 F:	drivers/media/radio/radio-gemtek*
 
+GENDWARFKSYMS
+M:	Sami Tolvanen <samitolvanen@google.com>
+L:	linux-modules@vger.kernel.org
+L:	linux-kbuild@vger.kernel.org
+S:	Maintained
+F:	scripts/gendwarfksyms/
+
 GENERIC ARCHITECTURE TOPOLOGY
 M:	Sudeep Holla <sudeep.holla@arm.com>
 L:	linux-kernel@vger.kernel.org
@@ -9844,7 +9878,7 @@ S:	Maintained
 F:	drivers/staging/gpib/
 
 GPIO ACPI SUPPORT
-M:	Mika Westerberg <mika.westerberg@linux.intel.com>
+M:	Mika Westerberg <westeri@kernel.org>
 M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 L:	linux-gpio@vger.kernel.org
 L:	linux-acpi@vger.kernel.org
@@ -10219,7 +10253,7 @@ F:	drivers/video/fbdev/hgafb.c
 
 HIBERNATION (aka Software Suspend, aka swsusp)
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
-M:	Pavel Machek <pavel@ucw.cz>
+M:	Pavel Machek <pavel@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 B:	https://bugzilla.kernel.org
@@ -11297,7 +11331,7 @@ S:	Orphan
 F:	drivers/video/fbdev/imsttfb.c
 
 INDEX OF FURTHER KERNEL DOCUMENTATION
-M:	Carlos Bilbao <carlos.bilbao.osdev@gmail.com>
+M:	Carlos Bilbao <carlos.bilbao@kernel.org>
 S:	Maintained
 F:	Documentation/process/kernel-docs.rst
 
@@ -11511,9 +11545,8 @@ F:	drivers/mfd/intel_pmc_bxt.c
 F:	include/linux/mfd/intel_pmc_bxt.h
 
 INTEL C600 SERIES SAS CONTROLLER DRIVER
-M:	Artur Paszkiewicz <artur.paszkiewicz@intel.com>
 L:	linux-scsi@vger.kernel.org
-S:	Supported
+S:	Orphan
 T:	git git://git.code.sf.net/p/intel-sas/isci
 F:	drivers/scsi/isci/
 
@@ -13091,8 +13124,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har
 F:	scripts/leaking_addresses.pl
 
 LED SUBSYSTEM
-M:	Pavel Machek <pavel@ucw.cz>
 M:	Lee Jones <lee@kernel.org>
+M:	Pavel Machek <pavel@kernel.org>
 L:	linux-leds@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lee/leds.git
@@ -15173,7 +15206,15 @@ L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	mm/mlock.c
 F:	mm/mmap.c
+F:	mm/mprotect.c
+F:	mm/mremap.c
+F:	mm/mseal.c
+F:	mm/vma.c
+F:	mm/vma.h
+F:	mm/vma_internal.h
+F:	tools/testing/vma/
 
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
@@ -16244,6 +16285,7 @@ F:	drivers/scsi/sun3_scsi_vme.c
 
 NCSI LIBRARY
 M:	Samuel Mendoza-Jonas <sam@mendozajonas.com>
+R:	Paul Fertser <fercerpav@gmail.com>
 S:	Maintained
 F:	net/ncsi/
 
@@ -16420,6 +16462,22 @@ F:	include/net/dsa.h
 F:	net/dsa/
 F:	tools/testing/selftests/drivers/net/dsa/
 
+NETWORKING [ETHTOOL]
+M:	Andrew Lunn <andrew@lunn.ch>
+M:	Jakub Kicinski <kuba@kernel.org>
+F:	Documentation/netlink/specs/ethtool.yaml
+F:	Documentation/networking/ethtool-netlink.rst
+F:	include/linux/ethtool*
+F:	include/uapi/linux/ethtool*
+F:	net/ethtool/
+F:	tools/testing/selftests/drivers/net/*/ethtool*
+
+NETWORKING [ETHTOOL CABLE TEST]
+M:	Andrew Lunn <andrew@lunn.ch>
+F:	net/ethtool/cabletest.c
+F:	tools/testing/selftests/drivers/net/*/ethtool*
+K:	cable_test
+
 NETWORKING [GENERAL]
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Eric Dumazet <edumazet@google.com>
@@ -16578,6 +16636,8 @@ F:	tools/testing/selftests/net/mptcp/
 
 NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
+M:	Neal Cardwell <ncardwell@google.com>
+R:	Kuniyuki Iwashima <kuniyu@amazon.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/net_cachelines/tcp_sock.rst
@@ -16605,6 +16665,31 @@ F:	include/net/tls.h
 F:	include/uapi/linux/tls.h
 F:	net/tls/*
 
+NETWORKING [SOCKETS]
+M:	Eric Dumazet <edumazet@google.com>
+M:	Kuniyuki Iwashima <kuniyu@amazon.com>
+M:	Paolo Abeni <pabeni@redhat.com>
+M:	Willem de Bruijn <willemb@google.com>
+S:	Maintained
+F:	include/linux/sock_diag.h
+F:	include/linux/socket.h
+F:	include/linux/sockptr.h
+F:	include/net/sock.h
+F:	include/net/sock_reuseport.h
+F:	include/uapi/linux/socket.h
+F:	net/core/*sock*
+F:	net/core/scm.c
+F:	net/socket.c
+
+NETWORKING [UNIX SOCKETS]
+M:	Kuniyuki Iwashima <kuniyu@amazon.com>
+S:	Maintained
+F:	include/net/af_unix.h
+F:	include/net/netns/unix.h
+F:	include/uapi/linux/unix_diag.h
+F:	net/unix/
+F:	tools/testing/selftests/net/af_unix/
+
 NETXEN (1/10) GbE SUPPORT
 M:	Manish Chopra <manishc@marvell.com>
 M:	Rahul Verma <rahulv@marvell.com>
@@ -16706,8 +16791,8 @@ F:	arch/nios2/
 
 NITRO ENCLAVES (NE)
 M:	Alexandru Ciobotaru <alcioa@amazon.com>
+R:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
 L:	linux-kernel@vger.kernel.org
-L:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
 S:	Supported
 W:	https://aws.amazon.com/ec2/nitro/nitro-enclaves/
 F:	Documentation/virt/ne_overview.rst
@@ -16718,8 +16803,8 @@ F:	samples/nitro_enclaves/
 
 NITRO SECURE MODULE (NSM)
 M:	Alexander Graf <graf@amazon.com>
+R:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
 L:	linux-kernel@vger.kernel.org
-L:	The AWS Nitro Enclaves Team <aws-nitro-enclaves-devel@amazon.com>
 S:	Supported
 W:	https://aws.amazon.com/ec2/nitro/nitro-enclaves/
 F:	drivers/misc/nsm.c
@@ -16738,7 +16823,7 @@ F:	include/linux/tick.h
 F:	kernel/time/tick*.*
 
 NOKIA N900 CAMERA SUPPORT (ET8EK8 SENSOR, AD5820 FOCUS)
-M:	Pavel Machek <pavel@ucw.cz>
+M:	Pavel Machek <pavel@kernel.org>
 M:	Sakari Ailus <sakari.ailus@iki.fi>
 L:	linux-media@vger.kernel.org
 S:	Maintained
@@ -16815,6 +16900,15 @@ T:	git https://github.com/Paragon-Software-Group/linux-ntfs3.git
 F:	Documentation/filesystems/ntfs3.rst
 F:	fs/ntfs3/
 
+NTSYNC SYNCHRONIZATION PRIMITIVE DRIVER
+M:	Elizabeth Figura <zfigura@codeweavers.com>
+L:	wine-devel@winehq.org
+S:	Supported
+F:	Documentation/userspace-api/ntsync.rst
+F:	drivers/misc/ntsync.c
+F:	include/uapi/linux/ntsync.h
+F:	tools/testing/selftests/drivers/ntsync/
+
 NUBUS SUBSYSTEM
 M:	Finn Thain <fthain@linux-m68k.org>
 L:	linux-m68k@lists.linux-m68k.org
@@ -16896,6 +16990,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/srini/nvmem.git
 F:	Documentation/ABI/stable/sysfs-bus-nvmem
 F:	Documentation/devicetree/bindings/nvmem/
 F:	drivers/nvmem/
+F:	include/dt-bindings/nvmem/
 F:	include/linux/nvmem-consumer.h
 F:	include/linux/nvmem-provider.h
 
@@ -17603,6 +17698,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git
 F:	Documentation/ABI/testing/sysfs-firmware-ofw
 F:	drivers/of/
 F:	include/linux/of*.h
+F:	rust/kernel/of.rs
 F:	scripts/dtc/
 F:	tools/testing/selftests/dt/
 K:	of_overlay_notifier_
@@ -17659,6 +17755,7 @@ L:	netdev@vger.kernel.org
 L:	dev@openvswitch.org
 S:	Maintained
 W:	http://openvswitch.org
+F:	Documentation/networking/openvswitch.rst
 F:	include/uapi/linux/openvswitch.h
 F:	net/openvswitch/
 F:	tools/testing/selftests/net/openvswitch/
@@ -18203,6 +18300,8 @@ F:	include/asm-generic/pci*
 F:	include/linux/of_pci.h
 F:	include/linux/pci*
 F:	include/uapi/linux/pci*
+F:	rust/kernel/pci.rs
+F:	samples/rust/rust_driver_pci.rs
 
 PCIE BANDWIDTH CONTROLLER
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
@@ -18531,8 +18630,8 @@ M:	Fabio Estevam <festevam@gmail.com>
 M:	Shawn Guo <shawnguo@kernel.org>
 M:	Jacky Bai <ping.bai@nxp.com>
 R:	Pengutronix Kernel Team <kernel@pengutronix.de>
+R:	NXP S32 Linux Team <s32@nxp.com>
 L:	linux-gpio@vger.kernel.org
-L:	NXP S32 Linux Team <s32@nxp.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/pinctrl/fsl,*
 F:	Documentation/devicetree/bindings/pinctrl/nxp,s32*
@@ -18816,11 +18915,13 @@ L:	linuxpps@ml.enneenne.com (subscribers-only)
 S:	Maintained
 W:	http://wiki.enneenne.com/index.php/LinuxPPS_support
 F:	Documentation/ABI/testing/sysfs-pps
+F:	Documentation/ABI/testing/sysfs-pps-gen
 F:	Documentation/devicetree/bindings/pps/pps-gpio.yaml
 F:	Documentation/driver-api/pps.rst
 F:	drivers/pps/
 F:	include/linux/pps*.h
 F:	include/uapi/linux/pps.h
+F:	include/uapi/linux/pps_gen.h
 
 PRESSURE STALL INFORMATION (PSI)
 M:	Johannes Weiner <hannes@cmpxchg.org>
@@ -19395,7 +19496,7 @@ F:	drivers/misc/fastrpc.c
 F:	include/uapi/misc/fastrpc.h
 
 QUALCOMM HEXAGON ARCHITECTURE
-M:	Brian Cain <bcain@quicinc.com>
+M:	Brian Cain <brian.cain@oss.qualcomm.com>
 L:	linux-hexagon@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bcain/linux.git
@@ -19676,7 +19777,7 @@ F:	drivers/ras/amd/fmpm.c
 
 RASPBERRY PI PISP BACK END
 M:	Jacopo Mondi <jacopo.mondi@ideasonboard.com>
-L:	Raspberry Pi Kernel Maintenance <kernel-list@raspberrypi.com>
+R:	Raspberry Pi Kernel Maintenance <kernel-list@raspberrypi.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/media/raspberrypi,pispbe.yaml
@@ -19799,6 +19900,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux.git rcu/dev
 F:	Documentation/RCU/
 F:	include/linux/rcu*
 F:	kernel/rcu/
+F:	rust/kernel/sync/rcu.rs
 X:	Documentation/RCU/torture.rst
 X:	include/linux/srcu*.h
 X:	kernel/rcu/srcu*.c
@@ -20411,6 +20513,11 @@ L:	linux-serial@vger.kernel.org
 S:	Odd Fixes
 F:	drivers/tty/serial/rp2.*
 
+ROHM BD79703 DAC
+M:	Matti Vaittinen <mazziesaccount@gmail.com>
+S:	Supported
+F:	drivers/iio/dac/rohm-bd79703.c
+
 ROHM BD99954 CHARGER IC
 M:	Matti Vaittinen <mazziesaccount@gmail.com>
 S:	Supported
@@ -20439,7 +20546,6 @@ ROHM BU270xx LIGHT SENSOR DRIVERs
 M:	Matti Vaittinen <mazziesaccount@gmail.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
-F:	drivers/iio/light/rohm-bu27008.c
 F:	drivers/iio/light/rohm-bu27034.c
 
 ROHM MULTIFUNCTION BD9571MWV-M PMIC DEVICE DRIVERS
@@ -20781,8 +20887,7 @@ F:	arch/s390/include/uapi/asm/zcrypt.h
 F:	drivers/s390/crypto/
 
 S390 ZFCP DRIVER
-M:	Steffen Maier <maier@linux.ibm.com>
-M:	Benjamin Block <bblock@linux.ibm.com>
+M:	Nihar Panda <niharp@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 F:	drivers/s390/scsi/zfcp_*
@@ -21372,6 +21477,7 @@ M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
 L:	linux-sound@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/slimbus/
+F:	Documentation/driver-api/slimbus.rst
 F:	drivers/slimbus/
 F:	include/linux/slimbus.h
 
@@ -22152,7 +22258,7 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/dvb-frontends/sp2*
 
 SPANISH DOCUMENTATION
-M:	Carlos Bilbao <carlos.bilbao.osdev@gmail.com>
+M:	Carlos Bilbao <carlos.bilbao@kernel.org>
 R:	Avadhut Naik <avadhut.naik@amd.com>
 S:	Maintained
 F:	Documentation/translations/sp_SP/
@@ -22302,6 +22408,14 @@ T:	git git://linuxtv.org/media.git
 F:	Documentation/devicetree/bindings/media/i2c/st,st-mipid02.yaml
 F:	drivers/media/i2c/st-mipid02.c
 
+ST STC3117 FUEL GAUGE DRIVER
+M:	Hardevsinh Palaniya <hardevsinh.palaniya@siliconsignals.io>
+M:	Bhavin Sharma <bhavin.sharma@siliconsignals.io>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/power/supply/st,stc3117.yaml
+F:	drivers/power/supply/stc3117_fuel_gauge.c
+
 ST STM32 FIREWALL
 M:	Gatien Chevallier <gatien.chevallier@foss.st.com>
 S:	Maintained
@@ -22446,7 +22560,6 @@ F:	drivers/phy/starfive/phy-jh7110-dphy-rx.c
 
 STARFIVE JH7110 DPHY TX DRIVER
 M:	Keith Zhao <keith.zhao@starfivetech.com>
-M:	Shengyang Chen <shengyang.chen@starfivetech.com>
 S:	Supported
 F:	Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml
 F:	drivers/phy/starfive/phy-jh7110-dphy-tx.c
@@ -22736,7 +22849,7 @@ F:	drivers/sh/
 SUSPEND TO RAM
 M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Len Brown <len.brown@intel.com>
-M:	Pavel Machek <pavel@ucw.cz>
+M:	Pavel Machek <pavel@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 B:	https://bugzilla.kernel.org
@@ -25165,21 +25278,6 @@ F:	include/uapi/linux/vsockmon.h
 F:	net/vmw_vsock/
 F:	tools/testing/vsock/
 
-VMA
-M:	Andrew Morton <akpm@linux-foundation.org>
-M:	Liam R. Howlett <Liam.Howlett@oracle.com>
-M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
-R:	Vlastimil Babka <vbabka@suse.cz>
-R:	Jann Horn <jannh@google.com>
-L:	linux-mm@kvack.org
-S:	Maintained
-W:	https://www.linux-mm.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
-F:	mm/vma.c
-F:	mm/vma.h
-F:	mm/vma_internal.h
-F:	tools/testing/vma/
-
 VMALLOC
 M:	Andrew Morton <akpm@linux-foundation.org>
 R:	Uladzislau Rezki <urezki@gmail.com>
@@ -25684,11 +25782,13 @@ F:	arch/x86/entry/vdso/
 XARRAY
 M:	Matthew Wilcox <willy@infradead.org>
 L:	linux-fsdevel@vger.kernel.org
+L:	linux-mm@kvack.org
 S:	Supported
 F:	Documentation/core-api/xarray.rst
 F:	include/linux/idr.h
 F:	include/linux/xarray.h
 F:	lib/idr.c
+F:	lib/test_xarray.c
 F:	lib/xarray.c
 F:	tools/testing/radix-tree
 
@@ -26168,7 +26268,7 @@ K:	zstd
 
 ZSWAP COMPRESSED SWAP CACHING
 M:	Johannes Weiner <hannes@cmpxchg.org>
-M:	Yosry Ahmed <yosryahmed@google.com>
+M:	Yosry Ahmed <yosry.ahmed@linux.dev>
 M:	Nhat Pham <nphamcs@gmail.com>
 R:	Chengming Zhou <chengming.zhou@linux.dev>
 L:	linux-mm@kvack.org
diff --git a/Makefile b/Makefile
index 4117cc79748b..89628e354ca7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 6
-PATCHLEVEL = 13
+PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION =
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/include/asm/elf.h b/arch/alpha/include/asm/elf.h
index 4d7c46f50382..50c82187e60e 100644
--- a/arch/alpha/include/asm/elf.h
+++ b/arch/alpha/include/asm/elf.h
@@ -74,7 +74,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 /*
  * This is used to ensure we don't load something for the wrong architecture.
  */
-#define elf_check_arch(x) ((x)->e_machine == EM_ALPHA)
+#define elf_check_arch(x) (((x)->e_machine == EM_ALPHA) && !((x)->e_flags & EF_ALPHA_32BIT))
 
 /*
  * These are used to set parameters in the core dumps.
@@ -137,10 +137,6 @@ extern int dump_elf_task(elf_greg_t *dest, struct task_struct *task);
 	: amask (AMASK_CIX) ? "ev6" : "ev67");	\
 })
 
-#define SET_PERSONALITY(EX)					\
-	set_personality(((EX).e_flags & EF_ALPHA_32BIT)		\
-	   ? PER_LINUX_32BIT : PER_LINUX)
-
 extern int alpha_l1i_cacheshape;
 extern int alpha_l1d_cacheshape;
 extern int alpha_l2_cacheshape;
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 635f0a5f5bbd..02e8817a8921 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -360,7 +360,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 
 extern void paging_init(void);
 
-/* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT.  */
+/* We have our own get_unmapped_area */
 #define HAVE_ARCH_UNMAPPED_AREA
 
 #endif /* _ALPHA_PGTABLE_H */
diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 55bb1c09fd39..5dce5518a211 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/arch/alpha/include/asm/processor.h
@@ -8,23 +8,19 @@
 #ifndef __ASM_ALPHA_PROCESSOR_H
 #define __ASM_ALPHA_PROCESSOR_H
 
-#include <linux/personality.h>	/* for ADDR_LIMIT_32BIT */
-
 /*
  * We have a 42-bit user address space: 4TB user VM...
  */
 #define TASK_SIZE (0x40000000000UL)
 
-#define STACK_TOP \
-  (current->personality & ADDR_LIMIT_32BIT ? 0x80000000 : 0x00120000000UL)
+#define STACK_TOP (0x00120000000UL)
 
 #define STACK_TOP_MAX	0x00120000000UL
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE \
-  ((current->personality & ADDR_LIMIT_32BIT) ? 0x40000000 : TASK_SIZE / 2)
+#define TASK_UNMAPPED_BASE (TASK_SIZE / 2)
 
 /* This is dead.  Everything has been moved to thread_info.  */
 struct thread_struct { };
diff --git a/arch/alpha/kernel/core_cia.c b/arch/alpha/kernel/core_cia.c
index ca3d9c732b61..6e577228e175 100644
--- a/arch/alpha/kernel/core_cia.c
+++ b/arch/alpha/kernel/core_cia.c
@@ -331,10 +331,7 @@ cia_prepare_tbia_workaround(int window)
 	long i;
 
 	/* Use minimal 1K map. */
-	ppte = memblock_alloc(CIA_BROKEN_TBIA_SIZE, 32768);
-	if (!ppte)
-		panic("%s: Failed to allocate %u bytes align=0x%x\n",
-		      __func__, CIA_BROKEN_TBIA_SIZE, 32768);
+	ppte = memblock_alloc_or_panic(CIA_BROKEN_TBIA_SIZE, 32768);
 	pte = (virt_to_phys(ppte) >> (PAGE_SHIFT - 1)) | 1;
 
 	for (i = 0; i < CIA_BROKEN_TBIA_SIZE / sizeof(unsigned long); ++i)
diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c
index b22248044bf0..b1bfbd11980d 100644
--- a/arch/alpha/kernel/core_marvel.c
+++ b/arch/alpha/kernel/core_marvel.c
@@ -81,10 +81,7 @@ mk_resource_name(int pe, int port, char *str)
 	char *name;
 	
 	sprintf(tmp, "PCI %s PE %d PORT %d", str, pe, port);
-	name = memblock_alloc(strlen(tmp) + 1, SMP_CACHE_BYTES);
-	if (!name)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      strlen(tmp) + 1);
+	name = memblock_alloc_or_panic(strlen(tmp) + 1, SMP_CACHE_BYTES);
 	strcpy(name, tmp);
 
 	return name;
@@ -119,10 +116,7 @@ alloc_io7(unsigned int pe)
 		return NULL;
 	}
 
-	io7 = memblock_alloc(sizeof(*io7), SMP_CACHE_BYTES);
-	if (!io7)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*io7));
+	io7 = memblock_alloc_or_panic(sizeof(*io7), SMP_CACHE_BYTES);
 	io7->pe = pe;
 	raw_spin_lock_init(&io7->irq_lock);
 
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 86185021f75a..a08e8edef1a4 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1210,8 +1210,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p)
 	return ret;
 }
 
-/* Get an address range which is currently unmapped.  Similar to the
-   generic version except that we know how to honor ADDR_LIMIT_32BIT.  */
+/* Get an address range which is currently unmapped. */
 
 static unsigned long
 arch_get_unmapped_area_1(unsigned long addr, unsigned long len,
@@ -1230,13 +1229,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		       unsigned long len, unsigned long pgoff,
 		       unsigned long flags, vm_flags_t vm_flags)
 {
-	unsigned long limit;
-
-	/* "32 bit" actually means 31 bit, since pointers sign extend.  */
-	if (current->personality & ADDR_LIMIT_32BIT)
-		limit = 0x80000000;
-	else
-		limit = TASK_SIZE;
+	unsigned long limit = TASK_SIZE;
 
 	if (len > limit)
 		return -ENOMEM;
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index 4458eb7f44f0..8e9b4ac86b7e 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -391,10 +391,7 @@ alloc_pci_controller(void)
 {
 	struct pci_controller *hose;
 
-	hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES);
-	if (!hose)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*hose));
+	hose = memblock_alloc_or_panic(sizeof(*hose), SMP_CACHE_BYTES);
 
 	*hose_tail = hose;
 	hose_tail = &hose->next;
@@ -405,13 +402,7 @@ alloc_pci_controller(void)
 struct resource * __init
 alloc_resource(void)
 {
-	void *ptr = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
-
-	if (!ptr)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(struct resource));
-
-	return ptr;
+	return memblock_alloc_or_panic(sizeof(struct resource), SMP_CACHE_BYTES);
 }
 
 
diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 7fcf3e9b7103..681f56089d9c 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -71,14 +71,8 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base,
 	if (align < mem_size)
 		align = mem_size;
 
-	arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES);
-	if (!arena)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*arena));
-	arena->ptes = memblock_alloc(mem_size, align);
-	if (!arena->ptes)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, mem_size, align);
+	arena = memblock_alloc_or_panic(sizeof(*arena), SMP_CACHE_BYTES);
+	arena->ptes = memblock_alloc_or_panic(mem_size, align);
 
 	spin_lock_init(&arena->lock);
 	arena->hose = hose;
diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c
index 9a238e7536ae..3d32165043f8 100644
--- a/arch/alpha/lib/fpreg.c
+++ b/arch/alpha/lib/fpreg.c
@@ -10,7 +10,6 @@
 #include <linux/preempt.h>
 #include <asm/fpu.h>
 #include <asm/thread_info.h>
-#include <asm/fpu.h>
 
 #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67)
 #define STT(reg,val)  asm volatile ("ftoit $f"#reg",%0" : "=r"(val));
diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 4fe618446e4c..61c2198b1359 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -42,7 +42,7 @@ pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *ret, *init;
 
-	ret = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	ret = __pgd_alloc(mm, 0);
 	init = pgd_offset(&init_mm, 0UL);
 	if (ret) {
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 62da5827f471..f27e6b90428e 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -18,6 +18,7 @@ config ARC
 	select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC
 	select ARCH_32BIT_OFF_T
 	select BUILDTIME_TABLE_SORT
+	select GENERIC_BUILTIN_DTB
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select DMA_DIRECT_REMAP
@@ -550,11 +551,11 @@ config ARC_DBG_JUMP_LABEL
 	  part of static keys (jump labels) related code.
 endif
 
-config ARC_BUILTIN_DTB_NAME
+config BUILTIN_DTB_NAME
 	string "Built in DTB"
+	default "nsim_700"
 	help
-	  Set the name of the DTB to embed in the vmlinux binary
-	  Leaving it blank selects the "nsim_700" dtb.
+	  Set the name of the DTB to embed in the vmlinux binary.
 
 endmenu	 # "ARC Architecture Configuration"
 
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index fb98478ed1ab..0c5e6e6314f2 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -82,9 +82,6 @@ KBUILD_CFLAGS	+= $(cflags-y)
 KBUILD_AFLAGS	+= $(KBUILD_CFLAGS)
 KBUILD_LDFLAGS	+= $(ldflags-y)
 
-# w/o this dtb won't embed into kernel binary
-core-y		+= arch/arc/boot/dts/
-
 core-y				+= arch/arc/plat-sim/
 core-$(CONFIG_ARC_PLAT_TB10X)	+= arch/arc/plat-tb10x/
 core-$(CONFIG_ARC_PLAT_AXS10X)	+= arch/arc/plat-axs10x/
diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile
index 48704dfdf75c..ee5664f0640d 100644
--- a/arch/arc/boot/dts/Makefile
+++ b/arch/arc/boot/dts/Makefile
@@ -1,13 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
-# Built-in dtb
-builtindtb-y		:= nsim_700
 
-ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),)
-	builtindtb-y	:= $(CONFIG_ARC_BUILTIN_DTB_NAME)
-endif
-
-obj-y   += $(builtindtb-y).dtb.o
-dtb-y := $(builtindtb-y).dtb
+dtb-y	:= $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME))
 
 # for CONFIG_OF_ALL_DTBS test
 dtb-	:= $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts))
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 319bbe270322..a7cd526dd7ca 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -23,7 +23,7 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS101=y
 CONFIG_ARC_CACHE_LINE_SHIFT=5
-CONFIG_ARC_BUILTIN_DTB_NAME="axs101"
+CONFIG_BUILTIN_DTB_NAME="axs101"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 8c1f1a111a17..afa6a348f444 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -22,7 +22,7 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
-CONFIG_ARC_BUILTIN_DTB_NAME="axs103"
+CONFIG_BUILTIN_DTB_NAME="axs103"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 75cab9f25b5b..2bfa6371953c 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -22,7 +22,7 @@ CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
-CONFIG_ARC_BUILTIN_DTB_NAME="axs103_idu"
+CONFIG_BUILTIN_DTB_NAME="axs103_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
index 8c3ed5d6e6c3..3a1577112078 100644
--- a/arch/arc/configs/haps_hs_defconfig
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -14,7 +14,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
-CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs"
+CONFIG_BUILTIN_DTB_NAME="haps_hs"
 CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_COMPACTION is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index 6fc98c1b9b36..a3cf940b1f5b 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -16,7 +16,7 @@ CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SMP=y
-CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu"
+CONFIG_BUILTIN_DTB_NAME="haps_hs_idu"
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 9e79154b5535..1558e8e87767 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -20,7 +20,7 @@ CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 CONFIG_LINUX_LINK_BASE=0x90000000
 CONFIG_LINUX_RAM_BASE=0x80000000
-CONFIG_ARC_BUILTIN_DTB_NAME="hsdk"
+CONFIG_BUILTIN_DTB_NAME="hsdk"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 51092c39e360..f8b3235d9a65 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -17,7 +17,7 @@ CONFIG_PERF_EVENTS=y
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_ISA_ARCOMPACT=y
-CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700"
+CONFIG_BUILTIN_DTB_NAME="nsim_700"
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 70c17bca4939..ee45dc0877fb 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -19,7 +19,7 @@ CONFIG_ISA_ARCOMPACT=y
 CONFIG_KPROBES=y
 CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
-CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci"
+CONFIG_BUILTIN_DTB_NAME="nsimosci"
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 59a3b6642fe7..e0a309970c20 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -19,7 +19,7 @@ CONFIG_KPROBES=y
 CONFIG_MODULES=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_ISA_ARCV2=y
-CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs"
+CONFIG_BUILTIN_DTB_NAME="nsimosci_hs"
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 1419fc946a08..88325b8b49cf 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -16,7 +16,7 @@ CONFIG_MODULES=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 # CONFIG_ARC_TIMERS_64BIT is not set
-CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu"
+CONFIG_BUILTIN_DTB_NAME="nsimosci_hs_idu"
 CONFIG_PREEMPT=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 5aba3d850fa2..865fbc19ef03 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -26,7 +26,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARC_PLAT_TB10X=y
 CONFIG_ARC_CACHE_LINE_SHIFT=5
 CONFIG_HZ=250
-CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk"
+CONFIG_BUILTIN_DTB_NAME="abilis_tb100_dvk"
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_COMPACTION is not set
 CONFIG_NET=y
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index 50c343913825..03d9ac20baa9 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -13,7 +13,7 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_ARC_PLAT_AXS10X=y
 CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
-CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38"
+CONFIG_BUILTIN_DTB_NAME="vdk_hs38"
 CONFIG_PREEMPT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 6d9e1d9f71d2..c09488992f13 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -15,7 +15,7 @@ CONFIG_AXS103=y
 CONFIG_ISA_ARCV2=y
 CONFIG_SMP=y
 # CONFIG_ARC_TIMERS_64BIT is not set
-CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp"
+CONFIG_BUILTIN_DTB_NAME="vdk_hs38_smp"
 CONFIG_PREEMPT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h
index 096b8ef58edb..dfae070fe8d5 100644
--- a/arch/arc/include/asm/pgalloc.h
+++ b/arch/arc/include/asm/pgalloc.h
@@ -53,19 +53,14 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte_
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *ret = (pgd_t *) __get_free_page(GFP_KERNEL);
+	pgd_t *ret = __pgd_alloc(mm, 0);
 
 	if (ret) {
 		int num, num2;
-		num = USER_PTRS_PER_PGD + USER_KERNEL_GUTTER / PGDIR_SIZE;
-		memzero(ret, num * sizeof(pgd_t));
 
+		num = USER_PTRS_PER_PGD + USER_KERNEL_GUTTER / PGDIR_SIZE;
 		num2 = VMALLOC_SIZE / PGDIR_SIZE;
 		memcpy(ret + num, swapper_pg_dir + num, num2 * sizeof(pgd_t));
-
-		memzero(ret + num + num2,
-			       (PTRS_PER_PGD - num - num2) * sizeof(pgd_t));
-
 	}
 	return ret;
 }
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index d2f5ceaaed1b..3b2d8b1bd271 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -200,7 +200,6 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 		     struct callee_regs *cregs)
 {
 	struct disasm_state state;
-	char buf[TASK_COMM_LEN];
 
 	/* handle user mode only and only if enabled by sysadmin */
 	if (!user_mode(regs) || !unaligned_enabled)
@@ -212,11 +211,11 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 			     " performance significantly\n. To enable further"
 			     " logging of such instances, please \n"
 			     " echo 0 > /proc/sys/kernel/ignore-unaligned-usertrap\n",
-			     get_task_comm(buf, current), task_pid_nr(current));
+			     current->comm, task_pid_nr(current));
 	} else {
 		/* Add rate limiting if it gets down to it */
 		pr_warn("%s(%d): unaligned access to/from 0x%lx by PC: 0x%lx\n",
-			get_task_comm(buf, current), task_pid_nr(current),
+			current->comm, task_pid_nr(current),
 			address, regs->ret);
 
 	}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3ad4c3c97918..835b5f100e92 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -5,6 +5,7 @@ config ARM
 	select ARCH_32BIT_OFF_T
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND
 	select ARCH_HAS_BINFMT_FLAT
+	select ARCH_HAS_CACHE_LINE_SIZE if OF
 	select ARCH_HAS_CPU_CACHE_ALIASING
 	select ARCH_HAS_CPU_FINALIZE_INIT if MMU
 	select ARCH_HAS_CRC32 if KERNEL_MODE_NEON
@@ -1753,5 +1754,3 @@ config ARCH_HIBERNATION_POSSIBLE
 	default y if ARCH_SUSPEND_POSSIBLE
 
 endmenu
-
-source "arch/arm/Kconfig.assembler"
diff --git a/arch/arm/Kconfig.assembler b/arch/arm/Kconfig.assembler
deleted file mode 100644
index 5cb31aae1188..000000000000
--- a/arch/arm/Kconfig.assembler
+++ /dev/null
@@ -1,6 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-config AS_VFP_VMRS_FPINST
-	def_bool $(as-instr,.fpu vfpv2\nvmrs r0$(comma)FPINST)
-	help
-	  Supported by binutils >= 2.24 and LLVM integrated assembler.
diff --git a/arch/arm/include/asm/cache.h b/arch/arm/include/asm/cache.h
index e3ea34558ada..ecbc100d22a5 100644
--- a/arch/arm/include/asm/cache.h
+++ b/arch/arm/include/asm/cache.h
@@ -26,4 +26,10 @@
 
 #define __read_mostly __section(".data..read_mostly")
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_ARCH_HAS_CACHE_LINE_SIZE
+int cache_line_size(void);
+#endif
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h
index b9dbe1d4c8fe..b01c59076b84 100644
--- a/arch/arm/include/asm/cachetype.h
+++ b/arch/arm/include/asm/cachetype.h
@@ -83,6 +83,14 @@ static inline unsigned int read_ccsidr(void)
 	asm volatile("mrc p15, 1, %0, c0, c0, 0" : "=r" (val));
 	return val;
 }
+
+static inline unsigned int read_clidr(void)
+{
+	unsigned int val;
+
+	asm volatile("mrc p15, 1, %0, c0, c0, 1" : "=r" (val));
+	return val;
+}
 #else /* CONFIG_CPU_V7M */
 #include <linux/io.h>
 #include "asm/v7m.h"
@@ -96,6 +104,11 @@ static inline unsigned int read_ccsidr(void)
 {
 	return readl(BASEADDR_V7M_SCB + V7M_SCB_CCSIDR);
 }
+
+static inline unsigned int read_clidr(void)
+{
+	return readl(BASEADDR_V7M_SCB + V7M_SCB_CLIDR);
+}
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/ecard.h b/arch/arm/include/asm/ecard.h
index 4befe8d2ae19..7cbe001bf9cc 100644
--- a/arch/arm/include/asm/ecard.h
+++ b/arch/arm/include/asm/ecard.h
@@ -195,7 +195,7 @@ void __iomem *ecardm_iomap(struct expansion_card *ec, unsigned int res,
 			   unsigned long offset, unsigned long maxsize);
 #define ecardm_iounmap(__ec, __addr)	devm_iounmap(&(__ec)->dev, __addr)
 
-extern struct bus_type ecard_bus_type;
+extern const struct bus_type ecard_bus_type;
 
 #define ECARD_DEV(_d)	container_of((_d), struct expansion_card, dev)
 
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f40d06ad5d2a..ea4fbe7b17f6 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -26,14 +26,7 @@
 
 #else /* !CONFIG_MMU */
 
-#include <linux/swap.h>
 #include <asm/tlbflush.h>
-
-static inline void __tlb_remove_table(void *_table)
-{
-	free_page_and_swap_cache((struct page *)_table);
-}
-
 #include <asm-generic/tlb.h>
 
 static inline void
@@ -41,8 +34,6 @@ __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
 {
 	struct ptdesc *ptdesc = page_ptdesc(pte);
 
-	pagetable_pte_dtor(ptdesc);
-
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
@@ -61,7 +52,6 @@ __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 #ifdef CONFIG_ARM_LPAE
 	struct ptdesc *ptdesc = virt_to_ptdesc(pmdp);
 
-	pagetable_pmd_dtor(ptdesc);
 	tlb_remove_ptdesc(tlb, ptdesc);
 #endif
 }
diff --git a/arch/arm/include/asm/vfp.h b/arch/arm/include/asm/vfp.h
index 157ea3426158..85ccc422d4d0 100644
--- a/arch/arm/include/asm/vfp.h
+++ b/arch/arm/include/asm/vfp.h
@@ -9,16 +9,6 @@
 #ifndef __ASM_VFP_H
 #define __ASM_VFP_H
 
-#ifndef CONFIG_AS_VFP_VMRS_FPINST
-#define FPSID			cr0
-#define FPSCR			cr1
-#define MVFR1			cr6
-#define MVFR0			cr7
-#define FPEXC			cr8
-#define FPINST			cr9
-#define FPINST2			cr10
-#endif
-
 /* FPSID bits */
 #define FPSID_IMPLEMENTER_BIT	(24)
 #define FPSID_IMPLEMENTER_MASK	(0xff << FPSID_IMPLEMENTER_BIT)
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index ba0d4cb5377e..e2e1d5a3727a 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -8,7 +8,6 @@
 
 #include <asm/vfp.h>
 
-#ifdef CONFIG_AS_VFP_VMRS_FPINST
 	.macro	VFPFMRX, rd, sysreg, cond
 	vmrs\cond	\rd, \sysreg
 	.endm
@@ -16,16 +15,6 @@
 	.macro	VFPFMXR, sysreg, rd, cond
 	vmsr\cond	\sysreg, \rd
 	.endm
-#else
-	@ Macros to allow building with old toolkits (with no VFP support)
-	.macro	VFPFMRX, rd, sysreg, cond
-	MRC\cond	p10, 7, \rd, \sysreg, cr0, 0	@ FMRX	\rd, \sysreg
-	.endm
-
-	.macro	VFPFMXR, sysreg, rd, cond
-	MCR\cond	p10, 7, \rd, \sysreg, cr0, 0	@ FMXR	\sysreg, \rd
-	.endm
-#endif
 
 	@ read all the working registers back into the VFP
 	.macro	VFPFLDMIA, base, tmp
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index aaae31b8c4a5..b3333d070390 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -40,6 +40,7 @@ obj-y		+= entry-armv.o
 endif
 
 obj-$(CONFIG_MMU)		+= bugs.o
+obj-$(CONFIG_OF)		+= cacheinfo.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
 obj-$(CONFIG_FIQ)		+= fiq.o fiqasm.o
diff --git a/arch/arm/kernel/cacheinfo.c b/arch/arm/kernel/cacheinfo.c
new file mode 100644
index 000000000000..e1469b641780
--- /dev/null
+++ b/arch/arm/kernel/cacheinfo.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  ARM cacheinfo support
+ *
+ *  Copyright (C) 2023 Linaro Ltd.
+ *  Copyright (C) 2015 ARM Ltd.
+ *  All Rights Reserved
+ */
+
+#include <linux/bitfield.h>
+#include <linux/cacheinfo.h>
+#include <linux/of.h>
+
+#include <asm/cachetype.h>
+#include <asm/cputype.h>
+#include <asm/system_info.h>
+
+/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */
+#define CLIDR_CTYPE_SHIFT(level)	(3 * (level - 1))
+#define CLIDR_CTYPE_MASK(level)		(7 << CLIDR_CTYPE_SHIFT(level))
+#define CLIDR_CTYPE(clidr, level)	\
+	(((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level))
+
+#define MAX_CACHE_LEVEL			7	/* Max 7 level supported */
+
+#define CTR_FORMAT_MASK	GENMASK(31, 29)
+#define CTR_FORMAT_ARMV6 0
+#define CTR_FORMAT_ARMV7 4
+#define CTR_CWG_MASK	GENMASK(27, 24)
+#define CTR_DSIZE_LEN_MASK GENMASK(13, 12)
+#define CTR_ISIZE_LEN_MASK GENMASK(1, 0)
+
+/* Also valid for v7m */
+static inline int cache_line_size_cp15(void)
+{
+	u32 ctr = read_cpuid_cachetype();
+	u32 format = FIELD_GET(CTR_FORMAT_MASK, ctr);
+
+	if (format == CTR_FORMAT_ARMV7) {
+		u32 cwg = FIELD_GET(CTR_CWG_MASK, ctr);
+
+		return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
+	} else if (WARN_ON_ONCE(format != CTR_FORMAT_ARMV6)) {
+		return ARCH_DMA_MINALIGN;
+	}
+
+	return 8 << max(FIELD_GET(CTR_ISIZE_LEN_MASK, ctr),
+			FIELD_GET(CTR_DSIZE_LEN_MASK, ctr));
+}
+
+int cache_line_size(void)
+{
+	if (coherency_max_size != 0)
+		return coherency_max_size;
+
+	/* CP15 is optional / implementation defined before ARMv6 */
+	if (cpu_architecture() < CPU_ARCH_ARMv6)
+		return ARCH_DMA_MINALIGN;
+
+	return cache_line_size_cp15();
+}
+EXPORT_SYMBOL_GPL(cache_line_size);
+
+static inline enum cache_type get_cache_type(int level)
+{
+	u32 clidr;
+
+	if (level > MAX_CACHE_LEVEL)
+		return CACHE_TYPE_NOCACHE;
+
+	clidr = read_clidr();
+
+	return CLIDR_CTYPE(clidr, level);
+}
+
+static void ci_leaf_init(struct cacheinfo *this_leaf,
+			 enum cache_type type, unsigned int level)
+{
+	this_leaf->level = level;
+	this_leaf->type = type;
+}
+
+static int detect_cache_level(unsigned int *level_p, unsigned int *leaves_p)
+{
+	unsigned int ctype, level, leaves;
+	u32 ctr, format;
+
+	/* CLIDR is not present before ARMv7/v7m */
+	if (cpu_architecture() < CPU_ARCH_ARMv7)
+		return -EOPNOTSUPP;
+
+	/* Don't try reading CLIDR if CTR declares old format */
+	ctr = read_cpuid_cachetype();
+	format = FIELD_GET(CTR_FORMAT_MASK, ctr);
+	if (format != CTR_FORMAT_ARMV7)
+		return -EOPNOTSUPP;
+
+	for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) {
+		ctype = get_cache_type(level);
+		if (ctype == CACHE_TYPE_NOCACHE) {
+			level--;
+			break;
+		}
+		/* Separate instruction and data caches */
+		leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1;
+	}
+
+	*level_p = level;
+	*leaves_p = leaves;
+
+	return 0;
+}
+
+int early_cache_level(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+
+	return detect_cache_level(&this_cpu_ci->num_levels, &this_cpu_ci->num_leaves);
+}
+
+int init_cache_level(unsigned int cpu)
+{
+	unsigned int level, leaves;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	int fw_level;
+	int ret;
+
+	ret = detect_cache_level(&level, &leaves);
+	if (ret)
+		return ret;
+
+	fw_level = of_find_last_cache_level(cpu);
+
+	if (level < fw_level) {
+		/*
+		 * some external caches not specified in CLIDR_EL1
+		 * the information may be available in the device tree
+		 * only unified external caches are considered here
+		 */
+		leaves += (fw_level - level);
+		level = fw_level;
+	}
+
+	this_cpu_ci->num_levels = level;
+	this_cpu_ci->num_leaves = leaves;
+	return 0;
+}
+
+int populate_cache_leaves(unsigned int cpu)
+{
+	unsigned int level, idx;
+	enum cache_type type;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+	unsigned int arch = cpu_architecture();
+
+	/* CLIDR is not present before ARMv7/v7m */
+	if (arch < CPU_ARCH_ARMv7)
+		return -EOPNOTSUPP;
+
+	for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
+	     idx < this_cpu_ci->num_leaves; idx++, level++) {
+		type = get_cache_type(level);
+		if (type == CACHE_TYPE_SEPARATE) {
+			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
+			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
+		} else {
+			ci_leaf_init(this_leaf++, type, level);
+		}
+	}
+
+	return 0;
+}
diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c
index 905b1b191546..db8be609fab2 100644
--- a/arch/arm/kernel/isa.c
+++ b/arch/arm/kernel/isa.c
@@ -16,7 +16,7 @@
 
 static unsigned int isa_membase, isa_portbase, isa_portshift;
 
-static struct ctl_table ctl_isa_vars[] = {
+static const struct ctl_table ctl_isa_vars[] = {
 	{
 		.procname	= "membase",
 		.data		= &isa_membase, 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index e6a857bf0ce6..a41c93988d2c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -880,10 +880,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 		 */
 		boot_alias_start = phys_to_idmap(start);
 		if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) {
-			res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES);
-			if (!res)
-				panic("%s: Failed to allocate %zu bytes\n",
-				      __func__, sizeof(*res));
+			res = memblock_alloc_or_panic(sizeof(*res), SMP_CACHE_BYTES);
 			res->name = "System RAM (boot alias)";
 			res->start = boot_alias_start;
 			res->end = phys_to_idmap(res_end);
@@ -891,10 +888,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 			request_resource(&iomem_resource, res);
 		}
 
-		res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      sizeof(*res));
+		res = memblock_alloc_or_panic(sizeof(*res), SMP_CACHE_BYTES);
 		res->name  = "System RAM";
 		res->start = start;
 		res->end = res_end;
diff --git a/arch/arm/mach-pxa/sharpsl_pm.c b/arch/arm/mach-pxa/sharpsl_pm.c
index 0c8d9000df5a..dd930e3a61a4 100644
--- a/arch/arm/mach-pxa/sharpsl_pm.c
+++ b/arch/arm/mach-pxa/sharpsl_pm.c
@@ -31,10 +31,10 @@
 /*
  * Constants
  */
-#define SHARPSL_CHARGE_ON_TIME_INTERVAL        (msecs_to_jiffies(1*60*1000))  /* 1 min */
-#define SHARPSL_CHARGE_FINISH_TIME             (msecs_to_jiffies(10*60*1000)) /* 10 min */
-#define SHARPSL_BATCHK_TIME                    (msecs_to_jiffies(15*1000))    /* 15 sec */
-#define SHARPSL_BATCHK_TIME_SUSPEND            (60*10)                        /* 10 min */
+#define SHARPSL_CHARGE_ON_TIME_INTERVAL        (secs_to_jiffies(60))
+#define SHARPSL_CHARGE_FINISH_TIME             (secs_to_jiffies(10*60))
+#define SHARPSL_BATCHK_TIME                    (secs_to_jiffies(15))
+#define SHARPSL_BATCHK_TIME_SUSPEND            (60*10) /* 10 min */
 
 #define SHARPSL_WAIT_CO_TIME                   15  /* 15 sec */
 #define SHARPSL_WAIT_DISCHARGE_ON              100 /* 100 msec */
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 9f7454b8efa7..2cde4c83b7f9 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -1124,7 +1124,7 @@ static int ecard_match(struct device *_dev, const struct device_driver *_drv)
 	return ret;
 }
 
-struct bus_type ecard_bus_type = {
+const struct bus_type ecard_bus_type = {
 	.name		= "ecard",
 	.dev_groups	= ecard_dev_groups,
 	.match		= ecard_match,
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index f5b7a16c5803..f02f872ea8a9 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -726,13 +726,8 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 
 static void __init *early_alloc(unsigned long sz)
 {
-	void *ptr = memblock_alloc(sz, sz);
+	return memblock_alloc_or_panic(sz, sz);
 
-	if (!ptr)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, sz, sz);
-
-	return ptr;
 }
 
 static void *__init late_alloc(unsigned long sz)
@@ -1027,10 +1022,7 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 	if (!nr)
 		return;
 
-	svm = memblock_alloc(sizeof(*svm) * nr, __alignof__(*svm));
-	if (!svm)
-		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
-		      __func__, sizeof(*svm) * nr, __alignof__(*svm));
+	svm = memblock_alloc_or_panic(sizeof(*svm) * nr, __alignof__(*svm));
 
 	for (md = io_desc; nr; md++, nr--) {
 		create_mapping(md);
@@ -1052,10 +1044,7 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size,
 	struct vm_struct *vm;
 	struct static_vm *svm;
 
-	svm = memblock_alloc(sizeof(*svm), __alignof__(*svm));
-	if (!svm)
-		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
-		      __func__, sizeof(*svm), __alignof__(*svm));
+	svm = memblock_alloc_or_panic(sizeof(*svm), __alignof__(*svm));
 
 	vm = &svm->vm;
 	vm->addr = (void *)addr;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index c415f3859b20..1a8f6914ee59 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -162,10 +162,7 @@ void __init paging_init(const struct machine_desc *mdesc)
 	mpu_setup();
 
 	/* allocate the zero page. */
-	zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	zero_page = (void *)memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 	bootmem_init();
 
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index f8e9bc58a84f..4eb81b7ed03a 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -17,11 +17,11 @@
 #include "mm.h"
 
 #ifdef CONFIG_ARM_LPAE
-#define __pgd_alloc()	kmalloc_array(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL)
-#define __pgd_free(pgd)	kfree(pgd)
+#define _pgd_alloc(mm)		kmalloc_array(PTRS_PER_PGD, sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO)
+#define _pgd_free(mm, pgd)	kfree(pgd)
 #else
-#define __pgd_alloc()	(pgd_t *)__get_free_pages(GFP_KERNEL, 2)
-#define __pgd_free(pgd)	free_pages((unsigned long)pgd, 2)
+#define _pgd_alloc(mm)		__pgd_alloc(mm, 2)
+#define _pgd_free(mm, pgd)	__pgd_free(mm, pgd)
 #endif
 
 /*
@@ -35,12 +35,10 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;
 
-	new_pgd = __pgd_alloc();
+	new_pgd = _pgd_alloc(mm);
 	if (!new_pgd)
 		goto no_pgd;
 
-	memset(new_pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
-
 	/*
 	 * Copy over the kernel and IO PGD entries
 	 */
@@ -134,7 +132,7 @@ no_pmd:
 no_pud:
 	p4d_free(mm, new_p4d);
 no_p4d:
-	__pgd_free(new_pgd);
+	_pgd_free(mm, new_pgd);
 no_pgd:
 	return NULL;
 }
@@ -207,5 +205,5 @@ no_pgd:
 		p4d_free(mm, p4d);
 	}
 #endif
-	__pgd_free(pgd_base);
+	_pgd_free(mm, pgd_base);
 }
diff --git a/arch/arm/vfp/vfpinstr.h b/arch/arm/vfp/vfpinstr.h
index 32090b0fb250..a2f0c47e0ce7 100644
--- a/arch/arm/vfp/vfpinstr.h
+++ b/arch/arm/vfp/vfpinstr.h
@@ -62,8 +62,6 @@
 #define FPSCR_C (1 << 29)
 #define FPSCR_V	(1 << 28)
 
-#ifdef CONFIG_AS_VFP_VMRS_FPINST
-
 #define fmrx(_vfp_) ({				\
 	u32 __v;				\
 	asm volatile (".fpu	vfpv2\n"	\
@@ -78,26 +76,6 @@
 		     : : "r" (_var_) : "cc");	\
 })
 
-#else
-
-#define vfpreg(_vfp_) #_vfp_
-
-#define fmrx(_vfp_) ({						\
-	u32 __v;						\
-	asm volatile ("mrc p10, 7, %0, " vfpreg(_vfp_) ","	\
-		      "cr0, 0 @ fmrx	%0, " #_vfp_		\
-		     : "=r" (__v) : : "cc");			\
-	__v;							\
-})
-
-#define fmxr(_vfp_, _var_) ({					\
-	asm volatile ("mcr p10, 7, %0, " vfpreg(_vfp_) ","	\
-		      "cr0, 0 @ fmxr	" #_vfp_ ", %0"		\
-		     : : "r" (_var_) : "cc");			\
-})
-
-#endif
-
 u32 vfp_single_cpdo(u32 inst, u32 fpscr);
 u32 vfp_single_cprt(u32 inst, u32 fpscr, struct pt_regs *regs);
 
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index d44867fc0c5e..7803d50b90f8 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -168,7 +168,7 @@ static void vfp_thread_copy(struct thread_info *thread)
 /*
  * When this function is called with the following 'cmd's, the following
  * is true while this function is being run:
- *  THREAD_NOFTIFY_SWTICH:
+ *  THREAD_NOTIFY_SWITCH:
  *   - the previously running thread will not be scheduled onto another CPU.
  *   - the next thread to be run (v) will not be running on another CPU.
  *   - thread->cpu is the local CPU number
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 488f8e751349..6f3f4142e214 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -122,6 +122,7 @@
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
 #define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
+#define QCOM_CPU_PART_ORYON_X1		0x001
 
 #define NVIDIA_CPU_PART_DENVER		0x003
 #define NVIDIA_CPU_PART_CARMEL		0x004
@@ -198,6 +199,7 @@
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
 #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
+#define MIDR_QCOM_ORYON_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_ORYON_X1)
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 43e365fbff0b..8d94a6c0ed5c 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -300,7 +300,7 @@
 #define CPTR_EL2_TSM	(1 << 12)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
-#define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */
+#define CPTR_NVHE_EL2_RES1	(BIT(13) | BIT(9) | GENMASK(7, 0))
 #define CPTR_NVHE_EL2_RES0	(GENMASK(63, 32) |	\
 				 GENMASK(29, 21) |	\
 				 GENMASK(19, 14) |	\
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index ca2590344313..bec227f9500a 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -53,8 +53,7 @@
 enum __kvm_host_smccc_func {
 	/* Hypercalls available only prior to pKVM finalisation */
 	/* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
-	__KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
-	__KVM_HOST_SMCCC_FUNC___pkvm_init,
+	__KVM_HOST_SMCCC_FUNC___pkvm_init = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
 	__KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,
 	__KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector,
 	__KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
@@ -65,6 +64,12 @@ enum __kvm_host_smccc_func {
 	/* Hypercalls available after pKVM finalisation */
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
 	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_hyp,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_share_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_unshare_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_relax_perms_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_wrprotect_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_test_clear_young_guest,
+	__KVM_HOST_SMCCC_FUNC___pkvm_host_mkyoung_guest,
 	__KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
@@ -79,6 +84,9 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vm,
 	__KVM_HOST_SMCCC_FUNC___pkvm_init_vcpu,
 	__KVM_HOST_SMCCC_FUNC___pkvm_teardown_vm,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_load,
+	__KVM_HOST_SMCCC_FUNC___pkvm_vcpu_put,
+	__KVM_HOST_SMCCC_FUNC___pkvm_tlb_flush_vmid,
 };
 
 #define DECLARE_KVM_VHE_SYM(sym)	extern char sym[]
@@ -247,8 +255,6 @@ extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu);
 extern u64 __vgic_v3_get_gic_config(void);
 extern void __vgic_v3_init_lrs(void);
 
-extern u64 __kvm_get_mdcr_el2(void);
-
 #define __KVM_EXTABLE(from, to)						\
 	"	.pushsection	__kvm_ex_table, \"a\"\n"		\
 	"	.align		3\n"					\
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 4f1d99725f6b..47f2cf408eed 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -184,29 +184,30 @@ static inline bool vcpu_is_el2(const struct kvm_vcpu *vcpu)
 	return vcpu_is_el2_ctxt(&vcpu->arch.ctxt);
 }
 
-static inline bool __vcpu_el2_e2h_is_set(const struct kvm_cpu_context *ctxt)
+static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu)
 {
 	return (!cpus_have_final_cap(ARM64_HAS_HCR_NV1) ||
-		(ctxt_sys_reg(ctxt, HCR_EL2) & HCR_E2H));
+		(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_E2H));
 }
 
-static inline bool vcpu_el2_e2h_is_set(const struct kvm_vcpu *vcpu)
+static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu)
 {
-	return __vcpu_el2_e2h_is_set(&vcpu->arch.ctxt);
+	return ctxt_sys_reg(&vcpu->arch.ctxt, HCR_EL2) & HCR_TGE;
 }
 
-static inline bool __vcpu_el2_tge_is_set(const struct kvm_cpu_context *ctxt)
+static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
 {
-	return ctxt_sys_reg(ctxt, HCR_EL2) & HCR_TGE;
-}
+	bool e2h, tge;
+	u64 hcr;
 
-static inline bool vcpu_el2_tge_is_set(const struct kvm_vcpu *vcpu)
-{
-	return __vcpu_el2_tge_is_set(&vcpu->arch.ctxt);
-}
+	if (!vcpu_has_nv(vcpu))
+		return false;
+
+	hcr = __vcpu_sys_reg(vcpu, HCR_EL2);
+
+	e2h = (hcr & HCR_E2H);
+	tge = (hcr & HCR_TGE);
 
-static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
-{
 	/*
 	 * We are in a hypervisor context if the vcpu mode is EL2 or
 	 * E2H and TGE bits are set. The latter means we are in the user space
@@ -215,14 +216,7 @@ static inline bool __is_hyp_ctxt(const struct kvm_cpu_context *ctxt)
 	 * Note that the HCR_EL2.{E2H,TGE}={0,1} isn't really handled in the
 	 * rest of the KVM code, and will result in a misbehaving guest.
 	 */
-	return vcpu_is_el2_ctxt(ctxt) ||
-		(__vcpu_el2_e2h_is_set(ctxt) && __vcpu_el2_tge_is_set(ctxt)) ||
-		__vcpu_el2_tge_is_set(ctxt);
-}
-
-static inline bool is_hyp_ctxt(const struct kvm_vcpu *vcpu)
-{
-	return vcpu_has_nv(vcpu) && __is_hyp_ctxt(&vcpu->arch.ctxt);
+	return vcpu_is_el2(vcpu) || (e2h && tge) || tge;
 }
 
 static inline bool vcpu_is_host_el0(const struct kvm_vcpu *vcpu)
@@ -619,7 +613,8 @@ static __always_inline void kvm_write_cptr_el2(u64 val)
 		write_sysreg(val, cptr_el2);
 }
 
-static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
+/* Resets the value of cptr_el2 when returning to the host. */
+static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm)
 {
 	u64 val;
 
@@ -630,29 +625,28 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
 	} else if (has_hvhe()) {
 		val = CPACR_EL1_FPEN;
 
-		if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
+		if (!kvm_has_sve(kvm) || !guest_owns_fp_regs())
 			val |= CPACR_EL1_ZEN;
 		if (cpus_have_final_cap(ARM64_SME))
 			val |= CPACR_EL1_SMEN;
 	} else {
 		val = CPTR_NVHE_EL2_RES1;
 
-		if (vcpu_has_sve(vcpu) && guest_owns_fp_regs())
+		if (kvm_has_sve(kvm) && guest_owns_fp_regs())
 			val |= CPTR_EL2_TZ;
-		if (cpus_have_final_cap(ARM64_SME))
-			val &= ~CPTR_EL2_TSM;
+		if (!cpus_have_final_cap(ARM64_SME))
+			val |= CPTR_EL2_TSM;
 	}
 
-	return val;
-}
-
-static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu)
-{
-	u64 val = kvm_get_reset_cptr_el2(vcpu);
-
 	kvm_write_cptr_el2(val);
 }
 
+#ifdef __KVM_NVHE_HYPERVISOR__
+#define kvm_reset_cptr_el2(v)	__kvm_reset_cptr_el2(kern_hyp_va((v)->kvm))
+#else
+#define kvm_reset_cptr_el2(v)	__kvm_reset_cptr_el2((v)->kvm)
+#endif
+
 /*
  * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
  * format if E2H isn't set.
@@ -697,9 +691,4 @@ static inline bool guest_hyp_sve_traps_enabled(const struct kvm_vcpu *vcpu)
 {
 	return __guest_hyp_cptr_xen_trap_enabled(vcpu, ZEN);
 }
-
-static inline void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu)
-{
-	vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH);
-}
 #endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e18e9244d17a..7cfa024de4e3 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -85,6 +85,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 struct kvm_hyp_memcache {
 	phys_addr_t head;
 	unsigned long nr_pages;
+	struct pkvm_mapping *mapping; /* only used from EL1 */
 };
 
 static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
@@ -331,6 +332,8 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		7
 	/* Fine-Grained UNDEF initialised */
 #define KVM_ARCH_FLAG_FGU_INITIALIZED			8
+	/* SVE exposed to guest */
+#define KVM_ARCH_FLAG_GUEST_HAS_SVE			9
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */
@@ -490,7 +493,6 @@ enum vcpu_sysreg {
 	VBAR_EL2,	/* Vector Base Address Register (EL2) */
 	RVBAR_EL2,	/* Reset Vector Base Address Register */
 	CONTEXTIDR_EL2,	/* Context ID Register (EL2) */
-	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 	SP_EL2,		/* EL2 Stack Pointer */
 	CNTHP_CTL_EL2,
 	CNTHP_CVAL_EL2,
@@ -501,6 +503,7 @@ enum vcpu_sysreg {
 	MARKER(__SANITISED_REG_START__),
 	TCR2_EL2,	/* Extended Translation Control Register (EL2) */
 	MDCR_EL2,	/* Monitor Debug Configuration Register (EL2) */
+	CNTHCTL_EL2,	/* Counter-timer Hypervisor Control register */
 
 	/* Any VNCR-capable reg goes after this point */
 	MARKER(__VNCR_START__),
@@ -610,6 +613,14 @@ struct cpu_sve_state {
  * field.
  */
 struct kvm_host_data {
+#define KVM_HOST_DATA_FLAG_HAS_SPE			0
+#define KVM_HOST_DATA_FLAG_HAS_TRBE			1
+#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED		2
+#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED		3
+#define KVM_HOST_DATA_FLAG_TRBE_ENABLED			4
+#define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED	5
+	unsigned long flags;
+
 	struct kvm_cpu_context host_ctxt;
 
 	/*
@@ -642,7 +653,7 @@ struct kvm_host_data {
 	 * host_debug_state contains the host registers which are
 	 * saved and restored during world switches.
 	 */
-	 struct {
+	struct {
 		/* {Break,watch}point registers */
 		struct kvm_guest_debug_arch regs;
 		/* Statistical profiling extension */
@@ -652,6 +663,16 @@ struct kvm_host_data {
 		/* Values of trap registers for the host before guest entry. */
 		u64 mdcr_el2;
 	} host_debug_state;
+
+	/* Guest trace filter value */
+	u64 trfcr_while_in_guest;
+
+	/* Number of programmable event counters (PMCR_EL0.N) for this CPU */
+	unsigned int nr_event_counters;
+
+	/* Number of debug breakpoints/watchpoints for this CPU (minus 1) */
+	unsigned int debug_brps;
+	unsigned int debug_wrps;
 };
 
 struct kvm_host_psci_config {
@@ -708,7 +729,6 @@ struct kvm_vcpu_arch {
 	u64 hcr_el2;
 	u64 hcrx_el2;
 	u64 mdcr_el2;
-	u64 cptr_el2;
 
 	/* Exception Information */
 	struct kvm_vcpu_fault_info fault;
@@ -739,31 +759,22 @@ struct kvm_vcpu_arch {
 	 *
 	 * external_debug_state contains the debug values we want to debug the
 	 * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl.
-	 *
-	 * debug_ptr points to the set of debug registers that should be loaded
-	 * onto the hardware when running the guest.
 	 */
-	struct kvm_guest_debug_arch *debug_ptr;
 	struct kvm_guest_debug_arch vcpu_debug_state;
 	struct kvm_guest_debug_arch external_debug_state;
+	u64 external_mdscr_el1;
+
+	enum {
+		VCPU_DEBUG_FREE,
+		VCPU_DEBUG_HOST_OWNED,
+		VCPU_DEBUG_GUEST_OWNED,
+	} debug_owner;
 
 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
 	struct arch_timer_cpu timer_cpu;
 	struct kvm_pmu pmu;
 
-	/*
-	 * Guest registers we preserve during guest debugging.
-	 *
-	 * These shadow registers are updated by the kvm_handle_sys_reg
-	 * trap handler if the guest accesses or updates them while we
-	 * are using guest debug.
-	 */
-	struct {
-		u32	mdscr_el1;
-		bool	pstate_ss;
-	} guest_debug_preserved;
-
 	/* vcpu power state */
 	struct kvm_mp_state mp_state;
 	spinlock_t mp_state_lock;
@@ -771,6 +782,9 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
+	/* Pages to top-up the pKVM/EL2 guest pool */
+	struct kvm_hyp_memcache pkvm_memcache;
+
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
 
@@ -863,14 +877,10 @@ struct kvm_vcpu_arch {
 #define vcpu_set_flag(v, ...)	__vcpu_set_flag((v), __VA_ARGS__)
 #define vcpu_clear_flag(v, ...)	__vcpu_clear_flag((v), __VA_ARGS__)
 
-/* SVE exposed to guest */
-#define GUEST_HAS_SVE		__vcpu_single_flag(cflags, BIT(0))
+/* KVM_ARM_VCPU_INIT completed */
+#define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(0))
 /* SVE config completed */
 #define VCPU_SVE_FINALIZED	__vcpu_single_flag(cflags, BIT(1))
-/* PTRAUTH exposed to guest */
-#define GUEST_HAS_PTRAUTH	__vcpu_single_flag(cflags, BIT(2))
-/* KVM_ARM_VCPU_INIT completed */
-#define VCPU_INITIALIZED	__vcpu_single_flag(cflags, BIT(3))
 
 /* Exception pending */
 #define PENDING_EXCEPTION	__vcpu_single_flag(iflags, BIT(0))
@@ -906,29 +916,21 @@ struct kvm_vcpu_arch {
 #define EXCEPT_AA64_EL2_IRQ	__vcpu_except_flags(5)
 #define EXCEPT_AA64_EL2_FIQ	__vcpu_except_flags(6)
 #define EXCEPT_AA64_EL2_SERR	__vcpu_except_flags(7)
-/* Guest debug is live */
-#define DEBUG_DIRTY		__vcpu_single_flag(iflags, BIT(4))
-/* Save SPE context if active  */
-#define DEBUG_STATE_SAVE_SPE	__vcpu_single_flag(iflags, BIT(5))
-/* Save TRBE context if active  */
-#define DEBUG_STATE_SAVE_TRBE	__vcpu_single_flag(iflags, BIT(6))
-
-/* SVE enabled for host EL0 */
-#define HOST_SVE_ENABLED	__vcpu_single_flag(sflags, BIT(0))
-/* SME enabled for EL0 */
-#define HOST_SME_ENABLED	__vcpu_single_flag(sflags, BIT(1))
+
 /* Physical CPU not in supported_cpus */
-#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(2))
+#define ON_UNSUPPORTED_CPU	__vcpu_single_flag(sflags, BIT(0))
 /* WFIT instruction trapped */
-#define IN_WFIT			__vcpu_single_flag(sflags, BIT(3))
+#define IN_WFIT			__vcpu_single_flag(sflags, BIT(1))
 /* vcpu system registers loaded on physical CPU */
-#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(4))
-/* Software step state is Active-pending */
-#define DBG_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(5))
+#define SYSREGS_ON_CPU		__vcpu_single_flag(sflags, BIT(2))
+/* Software step state is Active-pending for external debug */
+#define HOST_SS_ACTIVE_PENDING	__vcpu_single_flag(sflags, BIT(3))
+/* Software step state is Active pending for guest debug */
+#define GUEST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(4))
 /* PMUSERENR for the guest EL0 is on physical CPU */
-#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(6))
+#define PMUSERENR_ON_CPU	__vcpu_single_flag(sflags, BIT(5))
 /* WFI instruction trapped */
-#define IN_WFI			__vcpu_single_flag(sflags, BIT(7))
+#define IN_WFI			__vcpu_single_flag(sflags, BIT(6))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -959,14 +961,21 @@ struct kvm_vcpu_arch {
 				 KVM_GUESTDBG_USE_HW | \
 				 KVM_GUESTDBG_SINGLESTEP)
 
-#define vcpu_has_sve(vcpu) (system_supports_sve() &&			\
-			    vcpu_get_flag(vcpu, GUEST_HAS_SVE))
+#define kvm_has_sve(kvm)	(system_supports_sve() &&		\
+				 test_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &(kvm)->arch.flags))
+
+#ifdef __KVM_NVHE_HYPERVISOR__
+#define vcpu_has_sve(vcpu)	kvm_has_sve(kern_hyp_va((vcpu)->kvm))
+#else
+#define vcpu_has_sve(vcpu)	kvm_has_sve((vcpu)->kvm)
+#endif
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 #define vcpu_has_ptrauth(vcpu)						\
 	((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) ||		\
 	  cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) &&		\
-	  vcpu_get_flag(vcpu, GUEST_HAS_PTRAUTH))
+	 (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) ||       \
+	  vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
 #else
 #define vcpu_has_ptrauth(vcpu)		false
 #endif
@@ -1307,6 +1316,13 @@ DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data);
 	 &this_cpu_ptr_hyp_sym(kvm_host_data)->f)
 #endif
 
+#define host_data_test_flag(flag)					\
+	(test_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)))
+#define host_data_set_flag(flag)					\
+	set_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))
+#define host_data_clear_flag(flag)					\
+	clear_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))
+
 /* Check whether the FP regs are owned by the guest */
 static inline bool guest_owns_fp_regs(void)
 {
@@ -1332,15 +1348,22 @@ static inline bool kvm_system_needs_idmapped_vectors(void)
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 
-void kvm_arm_init_debug(void);
-void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu);
-void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
-void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
-void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+void kvm_init_host_debug_data(void);
+void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu);
+void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu);
+void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val);
 
 #define kvm_vcpu_os_lock_enabled(vcpu)		\
 	(!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK))
 
+#define kvm_debug_regs_in_use(vcpu)		\
+	((vcpu)->arch.debug_owner != VCPU_DEBUG_FREE)
+#define kvm_host_owns_debug_regs(vcpu)		\
+	((vcpu)->arch.debug_owner == VCPU_DEBUG_HOST_OWNED)
+#define kvm_guest_owns_debug_regs(vcpu)		\
+	((vcpu)->arch.debug_owner == VCPU_DEBUG_GUEST_OWNED)
+
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
@@ -1367,14 +1390,13 @@ static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr)
 	return (!has_vhe() && attr->exclude_host);
 }
 
-/* Flags for host debug state */
-void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu);
-void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu);
-
 #ifdef CONFIG_KVM
 void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr);
 void kvm_clr_pmu_events(u64 clr);
 bool kvm_set_pmuserenr(u64 val);
+void kvm_enable_trbe(void);
+void kvm_disable_trbe(void);
+void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest);
 #else
 static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {}
 static inline void kvm_clr_pmu_events(u64 clr) {}
@@ -1382,6 +1404,9 @@ static inline bool kvm_set_pmuserenr(u64 val)
 {
 	return false;
 }
+static inline void kvm_enable_trbe(void) {}
+static inline void kvm_disable_trbe(void) {}
+static inline void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) {}
 #endif
 
 void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
@@ -1422,6 +1447,7 @@ static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature)
 	return test_bit(feature, ka->vcpu_features);
 }
 
+#define kvm_vcpu_has_feature(k, f)	__vcpu_has_feature(&(k)->arch, (f))
 #define vcpu_has_feature(v, f)	__vcpu_has_feature(&(v)->kvm->arch, (f))
 
 #define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 66d93e320ec8..b98ac6aa631f 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -139,6 +139,8 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
 
 #define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))
 
+extern u32 __hyp_va_bits;
+
 /*
  * We currently support using a VM-specified IPA size. For backward
  * compatibility, the default IPA size is fixed to 40bits.
@@ -353,6 +355,22 @@ static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
 	return &kvm->arch.mmu != mmu;
 }
 
+static inline void kvm_fault_lock(struct kvm *kvm)
+{
+	if (is_protected_kvm_enabled())
+		write_lock(&kvm->mmu_lock);
+	else
+		read_lock(&kvm->mmu_lock);
+}
+
+static inline void kvm_fault_unlock(struct kvm *kvm)
+{
+	if (is_protected_kvm_enabled())
+		write_unlock(&kvm->mmu_lock);
+	else
+		read_unlock(&kvm->mmu_lock);
+}
+
 #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS
 void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
 #else
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 6cd08198bf19..56c4bcd35e2e 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -64,6 +64,7 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0)
 }
 
 extern bool forward_smc_trap(struct kvm_vcpu *vcpu);
+extern bool forward_debug_exception(struct kvm_vcpu *vcpu);
 extern void kvm_init_nested(struct kvm *kvm);
 extern int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu);
 extern void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu);
@@ -186,7 +187,7 @@ static inline bool kvm_supported_tlbi_s1e2_op(struct kvm_vcpu *vpcu, u32 instr)
 	return true;
 }
 
-int kvm_init_nv_sysregs(struct kvm *kvm);
+int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu);
 
 #ifdef CONFIG_ARM64_PTR_AUTH
 bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr);
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index aab04097b505..6b9d274052c7 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -412,15 +412,20 @@ static inline bool kvm_pgtable_walk_lock_held(void)
  *			be used instead of block mappings.
  */
 struct kvm_pgtable {
-	u32					ia_bits;
-	s8					start_level;
-	kvm_pteref_t				pgd;
-	struct kvm_pgtable_mm_ops		*mm_ops;
-
-	/* Stage-2 only */
-	struct kvm_s2_mmu			*mmu;
-	enum kvm_pgtable_stage2_flags		flags;
-	kvm_pgtable_force_pte_cb_t		force_pte_cb;
+	union {
+		struct rb_root					pkvm_mappings;
+		struct {
+			u32					ia_bits;
+			s8					start_level;
+			kvm_pteref_t				pgd;
+			struct kvm_pgtable_mm_ops		*mm_ops;
+
+			/* Stage-2 only */
+			enum kvm_pgtable_stage2_flags		flags;
+			kvm_pgtable_force_pte_cb_t		force_pte_cb;
+		};
+	};
+	struct kvm_s2_mmu					*mmu;
 };
 
 /**
@@ -526,8 +531,11 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			      enum kvm_pgtable_stage2_flags flags,
 			      kvm_pgtable_force_pte_cb_t force_pte_cb);
 
-#define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \
-	__kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL)
+static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
+					  struct kvm_pgtable_mm_ops *mm_ops)
+{
+	return __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL);
+}
 
 /**
  * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
@@ -669,13 +677,15 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
  * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry.
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Intermediate physical address to identify the page-table entry.
+ * @flags:	Flags to control the page-table walk (ex. a shared walk)
  *
  * The offset of @addr within a page is ignored.
  *
  * If there is a valid, leaf page-table entry used to translate @addr, then
  * set the access flag in that entry.
  */
-void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr);
+void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
+				enum kvm_pgtable_walk_flags flags);
 
 /**
  * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access
@@ -705,6 +715,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
  * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
  * @addr:	Intermediate physical address to identify the page-table entry.
  * @prot:	Additional permissions to grant for the mapping.
+ * @flags:	Flags to control the page-table walk (ex. a shared walk)
  *
  * The offset of @addr within a page is ignored.
  *
@@ -717,7 +728,8 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
  * Return: 0 on success, negative error code on failure.
  */
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
-				   enum kvm_pgtable_prot prot);
+				   enum kvm_pgtable_prot prot,
+				   enum kvm_pgtable_walk_flags flags);
 
 /**
  * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index cd56acd9a842..eb65f12e81d9 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -20,6 +20,31 @@ int pkvm_init_host_vm(struct kvm *kvm);
 int pkvm_create_hyp_vm(struct kvm *kvm);
 void pkvm_destroy_hyp_vm(struct kvm *kvm);
 
+/*
+ * This functions as an allow-list of protected VM capabilities.
+ * Features not explicitly allowed by this function are denied.
+ */
+static inline bool kvm_pvm_ext_allowed(long ext)
+{
+	switch (ext) {
+	case KVM_CAP_IRQCHIP:
+	case KVM_CAP_ARM_PSCI:
+	case KVM_CAP_ARM_PSCI_0_2:
+	case KVM_CAP_NR_VCPUS:
+	case KVM_CAP_MAX_VCPUS:
+	case KVM_CAP_MAX_VCPU_ID:
+	case KVM_CAP_MSI_DEVID:
+	case KVM_CAP_ARM_VM_IPA_SIZE:
+	case KVM_CAP_ARM_PMU_V3:
+	case KVM_CAP_ARM_SVE:
+	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
+	case KVM_CAP_ARM_PTRAUTH_GENERIC:
+		return true;
+	default:
+		return false;
+	}
+}
+
 extern struct memblock_region kvm_nvhe_sym(hyp_memory)[];
 extern unsigned int kvm_nvhe_sym(hyp_memblock_nr);
 
@@ -137,4 +162,30 @@ static inline size_t pkvm_host_sve_state_size(void)
 			SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl)));
 }
 
+struct pkvm_mapping {
+	struct rb_node node;
+	u64 gfn;
+	u64 pfn;
+};
+
+int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
+			     struct kvm_pgtable_mm_ops *mm_ops);
+void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
+			    enum kvm_pgtable_prot prot, void *mc,
+			    enum kvm_pgtable_walk_flags flags);
+int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size);
+int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size);
+int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
+bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold);
+int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
+				    enum kvm_pgtable_walk_flags flags);
+void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
+				 enum kvm_pgtable_walk_flags flags);
+int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			      struct kvm_mmu_memory_cache *mc);
+void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level);
+kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
+					       enum kvm_pgtable_prot prot, void *mc,
+					       bool force_pte);
 #endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 8b9f33cf561b..717829df294e 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -145,13 +145,16 @@
 
 #define OVERFLOW_STACK_SIZE	SZ_4K
 
+#define NVHE_STACK_SHIFT       PAGE_SHIFT
+#define NVHE_STACK_SIZE        (UL(1) << NVHE_STACK_SHIFT)
+
 /*
  * With the minimum frame size of [x29, x30], exactly half the combined
  * sizes of the hyp and overflow stacks is the maximum size needed to
  * save the unwinded stacktrace; plus an additional entry to delimit the
  * end.
  */
-#define NVHE_STACKTRACE_SIZE	((OVERFLOW_STACK_SIZE + PAGE_SIZE) / 2 + sizeof(long))
+#define NVHE_STACKTRACE_SIZE	((OVERFLOW_STACK_SIZE + NVHE_STACK_SIZE) / 2 + sizeof(long))
 
 /*
  * Alignment of kernel segments (e.g. .text, .data).
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index e75422864d1b..1b4509d3382c 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -85,24 +85,6 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp)
 	__pgd_populate(pgdp, __pa(p4dp), pgdval);
 }
 
-static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	gfp_t gfp = GFP_PGTABLE_USER;
-
-	if (mm == &init_mm)
-		gfp = GFP_PGTABLE_KERNEL;
-	return (p4d_t *)get_zeroed_page(gfp);
-}
-
-static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
-{
-	if (!pgtable_l5_enabled())
-		return;
-	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
-	free_page((unsigned long)p4d);
-}
-
-#define __p4d_free_tlb(tlb, p4d, addr)  p4d_free((tlb)->mm, p4d)
 #else
 static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot)
 {
diff --git a/arch/arm64/include/asm/stacktrace/nvhe.h b/arch/arm64/include/asm/stacktrace/nvhe.h
index 44759281d0d4..171f9edef49f 100644
--- a/arch/arm64/include/asm/stacktrace/nvhe.h
+++ b/arch/arm64/include/asm/stacktrace/nvhe.h
@@ -47,7 +47,7 @@ static inline void kvm_nvhe_unwind_init(struct unwind_state *state,
 
 DECLARE_KVM_NVHE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
 DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_stacktrace_info, kvm_stacktrace_info);
-DECLARE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
+DECLARE_PER_CPU(unsigned long, kvm_arm_hyp_stack_base);
 
 void kvm_nvhe_dump_backtrace(unsigned long hyp_offset);
 
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b8303a83c0bf..05ea5223d2d5 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -283,8 +283,6 @@
 #define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
 #define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
 
-#define SYS_TRFCR_EL1			sys_reg(3, 0, 1, 2, 1)
-
 #define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
 
 #define SYS_APIAKEYLO_EL1		sys_reg(3, 0, 2, 1, 0)
@@ -477,6 +475,7 @@
 #define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
 
 #define SYS_CNTPCT_EL0			sys_reg(3, 3, 14, 0, 1)
+#define SYS_CNTVCT_EL0			sys_reg(3, 3, 14, 0, 2)
 #define SYS_CNTPCTSS_EL0		sys_reg(3, 3, 14, 0, 5)
 #define SYS_CNTVCTSS_EL0		sys_reg(3, 3, 14, 0, 6)
 
@@ -484,14 +483,17 @@
 #define SYS_CNTP_CTL_EL0		sys_reg(3, 3, 14, 2, 1)
 #define SYS_CNTP_CVAL_EL0		sys_reg(3, 3, 14, 2, 2)
 
+#define SYS_CNTV_TVAL_EL0		sys_reg(3, 3, 14, 3, 0)
 #define SYS_CNTV_CTL_EL0		sys_reg(3, 3, 14, 3, 1)
 #define SYS_CNTV_CVAL_EL0		sys_reg(3, 3, 14, 3, 2)
 
 #define SYS_AARCH32_CNTP_TVAL		sys_reg(0, 0, 14, 2, 0)
 #define SYS_AARCH32_CNTP_CTL		sys_reg(0, 0, 14, 2, 1)
 #define SYS_AARCH32_CNTPCT		sys_reg(0, 0, 0, 14, 0)
+#define SYS_AARCH32_CNTVCT		sys_reg(0, 1, 0, 14, 0)
 #define SYS_AARCH32_CNTP_CVAL		sys_reg(0, 2, 0, 14, 0)
 #define SYS_AARCH32_CNTPCTSS		sys_reg(0, 8, 0, 14, 0)
+#define SYS_AARCH32_CNTVCTSS		sys_reg(0, 9, 0, 14, 0)
 
 #define __PMEV_op2(n)			((n) & 0x7)
 #define __CNTR_CRm(n)			(0x8 | (((n) >> 3) & 0x3))
@@ -519,7 +521,6 @@
 #define SYS_VTTBR_EL2			sys_reg(3, 4, 2, 1, 0)
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
-#define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
 #define SYS_VNCR_EL2			sys_reg(3, 4, 2, 2, 0)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
@@ -983,15 +984,6 @@
 /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
 #define SYS_MPIDR_SAFE_VAL	(BIT(31))
 
-#define TRFCR_ELx_TS_SHIFT		5
-#define TRFCR_ELx_TS_MASK		((0x3UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_ELx_TS_VIRTUAL		((0x1UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_ELx_TS_GUEST_PHYSICAL	((0x2UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_ELx_TS_PHYSICAL		((0x3UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_EL2_CX			BIT(3)
-#define TRFCR_ELx_ExTRE			BIT(1)
-#define TRFCR_ELx_E0TRE			BIT(0)
-
 /* GIC Hypervisor interface registers */
 /* ICH_MISR_EL2 bit definitions */
 #define ICH_MISR_EOI		(1 << 0)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index a947c6e784ed..8d762607285c 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -9,12 +9,7 @@
 #define __ASM_TLB_H
 
 #include <linux/pagemap.h>
-#include <linux/swap.h>
 
-static inline void __tlb_remove_table(void *_table)
-{
-	free_page_and_swap_cache((struct page *)_table);
-}
 
 #define tlb_flush tlb_flush
 static void tlb_flush(struct mmu_gather *tlb);
@@ -82,7 +77,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 {
 	struct ptdesc *ptdesc = page_ptdesc(pte);
 
-	pagetable_pte_dtor(ptdesc);
 	tlb_remove_ptdesc(tlb, ptdesc);
 }
 
@@ -92,7 +86,6 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 {
 	struct ptdesc *ptdesc = virt_to_ptdesc(pmdp);
 
-	pagetable_pmd_dtor(ptdesc);
 	tlb_remove_ptdesc(tlb, ptdesc);
 }
 #endif
@@ -106,7 +99,19 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 	if (!pgtable_l4_enabled())
 		return;
 
-	pagetable_pud_dtor(ptdesc);
+	tlb_remove_ptdesc(tlb, ptdesc);
+}
+#endif
+
+#if CONFIG_PGTABLE_LEVELS > 4
+static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4dp,
+				  unsigned long addr)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(p4dp);
+
+	if (!pgtable_l5_enabled())
+		return;
+
 	tlb_remove_ptdesc(tlb, ptdesc);
 }
 #endif
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index a78f247029ae..7ce555862895 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -787,5 +787,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	},
 #endif
 	{
+		.desc = "Broken CNTVOFF_EL2",
+		.capability = ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF,
+		ERRATA_MIDR_RANGE_LIST(((const struct midr_range[]) {
+					MIDR_ALL_VERSIONS(MIDR_QCOM_ORYON_X1),
+					{}
+				})),
+	},
+	{
 	}
 };
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 8c4c1a2186cc..2b601d88762d 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -562,7 +562,7 @@ static int vec_proc_do_default_vl(const struct ctl_table *table, int write,
 	return 0;
 }
 
-static struct ctl_table sve_default_vl_table[] = {
+static const struct ctl_table sve_default_vl_table[] = {
 	{
 		.procname	= "sve_default_vector_length",
 		.mode		= 0644,
@@ -585,7 +585,7 @@ static int __init sve_sysctl_init(void) { return 0; }
 #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */
 
 #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL)
-static struct ctl_table sme_default_vl_table[] = {
+static const struct ctl_table sme_default_vl_table[] = {
 	{
 		.procname	= "sme_default_vector_length",
 		.mode		= 0644,
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 8f5422ed1b75..ef3a69cc398e 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -105,6 +105,9 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors);
 KVM_NVHE_ALIAS(vgic_v2_cpuif_trap);
 KVM_NVHE_ALIAS(vgic_v3_cpuif_trap);
 
+/* Static key which is set if CNTVOFF_EL2 is unusable */
+KVM_NVHE_ALIAS(broken_cntvoff_key);
+
 /* EL2 exception handling */
 KVM_NVHE_ALIAS(__start___kvm_ex_table);
 KVM_NVHE_ALIAS(__stop___kvm_ex_table);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 2968a33bb3bc..42faebb7b712 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -859,7 +859,7 @@ long get_tagged_addr_ctrl(struct task_struct *task)
  * disable it for tasks that already opted in to the relaxed ABI.
  */
 
-static struct ctl_table tagged_addr_sysctl_table[] = {
+static const struct ctl_table tagged_addr_sysctl_table[] = {
 	{
 		.procname	= "tagged_addr_disabled",
 		.mode		= 0644,
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 4f613e8e0745..85104587f849 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -223,9 +223,7 @@ static void __init request_standard_resources(void)
 
 	num_standard_resources = memblock.memory.cnt;
 	res_size = num_standard_resources * sizeof(*standard_resources);
-	standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
-	if (!standard_resources)
-		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
+	standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES);
 
 	for_each_mem_region(region) {
 		res = &standard_resources[i++];
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 1215df590418..231c0cd9c7b4 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -30,6 +30,7 @@ static u32 host_vtimer_irq_flags;
 static u32 host_ptimer_irq_flags;
 
 static DEFINE_STATIC_KEY_FALSE(has_gic_active_state);
+DEFINE_STATIC_KEY_FALSE(broken_cntvoff_key);
 
 static const u8 default_ppi[] = {
 	[TIMER_PTIMER]  = 30,
@@ -101,21 +102,6 @@ u64 timer_get_cval(struct arch_timer_context *ctxt)
 	}
 }
 
-static u64 timer_get_offset(struct arch_timer_context *ctxt)
-{
-	u64 offset = 0;
-
-	if (!ctxt)
-		return 0;
-
-	if (ctxt->offset.vm_offset)
-		offset += *ctxt->offset.vm_offset;
-	if (ctxt->offset.vcpu_offset)
-		offset += *ctxt->offset.vcpu_offset;
-
-	return offset;
-}
-
 static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
 {
 	struct kvm_vcpu *vcpu = ctxt->vcpu;
@@ -441,11 +427,30 @@ void kvm_timer_update_run(struct kvm_vcpu *vcpu)
 		regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
 }
 
+static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level)
+{
+	/*
+	 * Paper over NV2 brokenness by publishing the interrupt status
+	 * bit. This still results in a poor quality of emulation (guest
+	 * writes will have no effect until the next exit).
+	 *
+	 * But hey, it's fast, right?
+	 */
+	if (is_hyp_ctxt(ctx->vcpu) &&
+	    (ctx == vcpu_vtimer(ctx->vcpu) || ctx == vcpu_ptimer(ctx->vcpu))) {
+		unsigned long val = timer_get_ctl(ctx);
+		__assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &val, level);
+		timer_set_ctl(ctx, val);
+	}
+}
+
 static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
 				 struct arch_timer_context *timer_ctx)
 {
 	int ret;
 
+	kvm_timer_update_status(timer_ctx, new_level);
+
 	timer_ctx->irq.level = new_level;
 	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx),
 				   timer_ctx->irq.level);
@@ -466,10 +471,10 @@ static void timer_emulate(struct arch_timer_context *ctx)
 
 	trace_kvm_timer_emulate(ctx, should_fire);
 
-	if (should_fire != ctx->irq.level) {
+	if (should_fire != ctx->irq.level)
 		kvm_timer_update_irq(ctx->vcpu, should_fire, ctx);
-		return;
-	}
+
+	kvm_timer_update_status(ctx, should_fire);
 
 	/*
 	 * If the timer can fire now, we don't need to have a soft timer
@@ -513,7 +518,12 @@ static void timer_save_state(struct arch_timer_context *ctx)
 	case TIMER_VTIMER:
 	case TIMER_HVTIMER:
 		timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL));
-		timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL));
+		cval = read_sysreg_el0(SYS_CNTV_CVAL);
+
+		if (has_broken_cntvoff())
+			cval -= timer_get_offset(ctx);
+
+		timer_set_cval(ctx, cval);
 
 		/* Disable the timer */
 		write_sysreg_el0(0, SYS_CNTV_CTL);
@@ -618,8 +628,15 @@ static void timer_restore_state(struct arch_timer_context *ctx)
 
 	case TIMER_VTIMER:
 	case TIMER_HVTIMER:
-		set_cntvoff(timer_get_offset(ctx));
-		write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL);
+		cval = timer_get_cval(ctx);
+		offset = timer_get_offset(ctx);
+		if (has_broken_cntvoff()) {
+			set_cntvoff(0);
+			cval += offset;
+		} else {
+			set_cntvoff(offset);
+		}
+		write_sysreg_el0(cval, SYS_CNTV_CVAL);
 		isb();
 		write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL);
 		break;
@@ -742,27 +759,12 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
 					    timer_irq(map->direct_ptimer),
 					    &arch_timer_irq_ops);
 		WARN_ON_ONCE(ret);
-
-		/*
-		 * The virtual offset behaviour is "interesting", as it
-		 * always applies when HCR_EL2.E2H==0, but only when
-		 * accessed from EL1 when HCR_EL2.E2H==1. So make sure we
-		 * track E2H when putting the HV timer in "direct" mode.
-		 */
-		if (map->direct_vtimer == vcpu_hvtimer(vcpu)) {
-			struct arch_timer_offset *offs = &map->direct_vtimer->offset;
-
-			if (vcpu_el2_e2h_is_set(vcpu))
-				offs->vcpu_offset = NULL;
-			else
-				offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
-		}
 	}
 }
 
 static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 {
-	bool tpt, tpc;
+	bool tvt, tpt, tvc, tpc, tvt02, tpt02;
 	u64 clr, set;
 
 	/*
@@ -777,7 +779,29 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 	 * within this function, reality kicks in and we start adding
 	 * traps based on emulation requirements.
 	 */
-	tpt = tpc = false;
+	tvt = tpt = tvc = tpc = false;
+	tvt02 = tpt02 = false;
+
+	/*
+	 * NV2 badly breaks the timer semantics by redirecting accesses to
+	 * the EL1 timer state to memory, so let's call ECV to the rescue if
+	 * available: we trap all CNT{P,V}_{CTL,CVAL,TVAL}_EL0 accesses.
+	 *
+	 * The treatment slightly varies depending whether we run a nVHE or
+	 * VHE guest: nVHE will use the _EL0 registers directly, while VHE
+	 * will use the _EL02 accessors. This translates in different trap
+	 * bits.
+	 *
+	 * None of the trapping is required when running in non-HYP context,
+	 * unless required by the L1 hypervisor settings once we advertise
+	 * ECV+NV in the guest, or that we need trapping for other reasons.
+	 */
+	if (cpus_have_final_cap(ARM64_HAS_ECV) && is_hyp_ctxt(vcpu)) {
+		if (vcpu_el2_e2h_is_set(vcpu))
+			tvt02 = tpt02 = true;
+		else
+			tvt = tpt = true;
+	}
 
 	/*
 	 * We have two possibility to deal with a physical offset:
@@ -793,9 +817,20 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 		tpt = tpc = true;
 
 	/*
+	 * For the poor sods that could not correctly substract one value
+	 * from another, trap the full virtual timer and counter.
+	 */
+	if (has_broken_cntvoff() && timer_get_offset(map->direct_vtimer))
+		tvt = tvc = true;
+
+	/*
 	 * Apply the enable bits that the guest hypervisor has requested for
 	 * its own guest. We can only add traps that wouldn't have been set
 	 * above.
+	 * Implementation choices: we do not support NV when E2H=0 in the
+	 * guest, and we don't support configuration where E2H is writable
+	 * by the guest (either FEAT_VHE or FEAT_E2H0 is implemented, but
+	 * not both). This simplifies the handling of the EL1NV* bits.
 	 */
 	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
 		u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2);
@@ -806,6 +841,9 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 
 		tpt |= !(val & (CNTHCTL_EL1PCEN << 10));
 		tpc |= !(val & (CNTHCTL_EL1PCTEN << 10));
+
+		tpt02 |= (val & CNTHCTL_EL1NVPCT);
+		tvt02 |= (val & CNTHCTL_EL1NVVCT);
 	}
 
 	/*
@@ -817,6 +855,10 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map)
 
 	assign_clear_set_bit(tpt, CNTHCTL_EL1PCEN << 10, set, clr);
 	assign_clear_set_bit(tpc, CNTHCTL_EL1PCTEN << 10, set, clr);
+	assign_clear_set_bit(tvt, CNTHCTL_EL1TVT, clr, set);
+	assign_clear_set_bit(tvc, CNTHCTL_EL1TVCT, clr, set);
+	assign_clear_set_bit(tvt02, CNTHCTL_EL1NVVCT, clr, set);
+	assign_clear_set_bit(tpt02, CNTHCTL_EL1NVPCT, clr, set);
 
 	/* This only happens on VHE, so use the CNTHCTL_EL2 accessor. */
 	sysreg_clear_set(cnthctl_el2, clr, set);
@@ -905,6 +947,44 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 		kvm_timer_blocking(vcpu);
 }
 
+void kvm_timer_sync_nested(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When NV2 is on, guest hypervisors have their EL1 timer register
+	 * accesses redirected to the VNCR page. Any guest action taken on
+	 * the timer is postponed until the next exit, leading to a very
+	 * poor quality of emulation.
+	 *
+	 * This is an unmitigated disaster, only papered over by FEAT_ECV,
+	 * which allows trapping of the timer registers even with NV2.
+	 * Still, this is still worse than FEAT_NV on its own. Meh.
+	 */
+	if (!cpus_have_final_cap(ARM64_HAS_ECV)) {
+		/*
+		 * For a VHE guest hypervisor, the EL2 state is directly
+		 * stored in the host EL1 timers, while the emulated EL1
+		 * state is stored in the VNCR page. The latter could have
+		 * been updated behind our back, and we must reset the
+		 * emulation of the timers.
+		 *
+		 * A non-VHE guest hypervisor doesn't have any direct access
+		 * to its timers: the EL2 registers trap despite being
+		 * notionally direct (we use the EL1 HW, as for VHE), while
+		 * the EL1 registers access memory.
+		 *
+		 * In both cases, process the emulated timers on each guest
+		 * exit. Boo.
+		 */
+		struct timer_map map;
+		get_timer_map(vcpu, &map);
+
+		soft_timer_cancel(&map.emul_vtimer->hrtimer);
+		soft_timer_cancel(&map.emul_ptimer->hrtimer);
+		timer_emulate(map.emul_vtimer);
+		timer_emulate(map.emul_ptimer);
+	}
+}
+
 /*
  * With a userspace irqchip we have to check if the guest de-asserted the
  * timer and if so, unmask the timer irq signal on the host interrupt
@@ -1363,6 +1443,37 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info)
 	return 0;
 }
 
+static void kvm_timer_handle_errata(void)
+{
+	u64 mmfr0, mmfr1, mmfr4;
+
+	/*
+	 * CNTVOFF_EL2 is broken on some implementations. For those, we trap
+	 * all virtual timer/counter accesses, requiring FEAT_ECV.
+	 *
+	 * However, a hypervisor supporting nesting is likely to mitigate the
+	 * erratum at L0, and not require other levels to mitigate it (which
+	 * would otherwise be a terrible performance sink due to trap
+	 * amplification).
+	 *
+	 * Given that the affected HW implements both FEAT_VHE and FEAT_E2H0,
+	 * and that NV is likely not to (because of limitations of the
+	 * architecture), only enable the workaround when FEAT_VHE and
+	 * FEAT_E2H0 are both detected. Time will tell if this actually holds.
+	 */
+	mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+	mmfr4 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR4_EL1);
+	if (SYS_FIELD_GET(ID_AA64MMFR1_EL1, VH, mmfr1)		&&
+	    !SYS_FIELD_GET(ID_AA64MMFR4_EL1, E2H0, mmfr4)	&&
+	    SYS_FIELD_GET(ID_AA64MMFR0_EL1, ECV, mmfr0)		&&
+	    (has_vhe() || has_hvhe())				&&
+	    cpus_have_final_cap(ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF)) {
+		static_branch_enable(&broken_cntvoff_key);
+		kvm_info("Broken CNTVOFF_EL2, trapping virtual timer\n");
+	}
+}
+
 int __init kvm_timer_hyp_init(bool has_gic)
 {
 	struct arch_timer_kvm_info *info;
@@ -1431,6 +1542,7 @@ int __init kvm_timer_hyp_init(bool has_gic)
 		goto out_free_vtimer_irq;
 	}
 
+	kvm_timer_handle_errata();
 	return 0;
 
 out_free_ptimer_irq:
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 7b2735ad32e9..071a7d75be68 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -61,7 +61,7 @@ static enum kvm_wfx_trap_policy kvm_wfe_trap_policy __read_mostly = KVM_WFX_NOTR
 
 DECLARE_KVM_HYP_PER_CPU(unsigned long, kvm_hyp_vector);
 
-DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
+DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_base);
 DECLARE_KVM_NVHE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
 DECLARE_KVM_NVHE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
@@ -80,31 +80,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
 }
 
-/*
- * This functions as an allow-list of protected VM capabilities.
- * Features not explicitly allowed by this function are denied.
- */
-static bool pkvm_ext_allowed(struct kvm *kvm, long ext)
-{
-	switch (ext) {
-	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_ARM_PSCI:
-	case KVM_CAP_ARM_PSCI_0_2:
-	case KVM_CAP_NR_VCPUS:
-	case KVM_CAP_MAX_VCPUS:
-	case KVM_CAP_MAX_VCPU_ID:
-	case KVM_CAP_MSI_DEVID:
-	case KVM_CAP_ARM_VM_IPA_SIZE:
-	case KVM_CAP_ARM_PMU_V3:
-	case KVM_CAP_ARM_SVE:
-	case KVM_CAP_ARM_PTRAUTH_ADDRESS:
-	case KVM_CAP_ARM_PTRAUTH_GENERIC:
-		return true;
-	default:
-		return false;
-	}
-}
-
 int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			    struct kvm_enable_cap *cap)
 {
@@ -113,7 +88,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	if (cap->flags)
 		return -EINVAL;
 
-	if (kvm_vm_is_protected(kvm) && !pkvm_ext_allowed(kvm, cap->cap))
+	if (kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(cap->cap))
 		return -EINVAL;
 
 	switch (cap->cap) {
@@ -311,7 +286,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
 
-	if (kvm && kvm_vm_is_protected(kvm) && !pkvm_ext_allowed(kvm, ext))
+	if (kvm && kvm_vm_is_protected(kvm) && !kvm_pvm_ext_allowed(ext))
 		return 0;
 
 	switch (ext) {
@@ -476,8 +451,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	kvm_pmu_vcpu_init(vcpu);
 
-	kvm_arm_reset_debug_ptr(vcpu);
-
 	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
 
 	vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
@@ -502,7 +475,10 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+	if (!is_protected_kvm_enabled())
+		kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
+	else
+		free_hyp_memcache(&vcpu->arch.pkvm_memcache);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
 	kvm_vgic_vcpu_destroy(vcpu);
@@ -574,6 +550,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	struct kvm_s2_mmu *mmu;
 	int *last_ran;
 
+	if (is_protected_kvm_enabled())
+		goto nommu;
+
 	if (vcpu_has_nv(vcpu))
 		kvm_vcpu_load_hw_mmu(vcpu);
 
@@ -594,10 +573,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		*last_ran = vcpu->vcpu_idx;
 	}
 
+nommu:
 	vcpu->cpu = cpu;
 
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
+	kvm_vcpu_load_debug(vcpu);
 	if (has_vhe())
 		kvm_vcpu_load_vhe(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
@@ -617,7 +598,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	vcpu_set_pauth_traps(vcpu);
 
-	kvm_arch_vcpu_load_debug_state_flags(vcpu);
+	if (is_protected_kvm_enabled()) {
+		kvm_call_hyp_nvhe(__pkvm_vcpu_load,
+				  vcpu->kvm->arch.pkvm.handle,
+				  vcpu->vcpu_idx, vcpu->arch.hcr_el2);
+		kvm_call_hyp(__vgic_v3_restore_vmcr_aprs,
+			     &vcpu->arch.vgic_cpu.vgic_v3);
+	}
 
 	if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus))
 		vcpu_set_on_unsupported_cpu(vcpu);
@@ -625,7 +612,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvm_arch_vcpu_put_debug_state_flags(vcpu);
+	if (is_protected_kvm_enabled()) {
+		kvm_call_hyp(__vgic_v3_save_vmcr_aprs,
+			     &vcpu->arch.vgic_cpu.vgic_v3);
+		kvm_call_hyp_nvhe(__pkvm_vcpu_put);
+	}
+
+	kvm_vcpu_put_debug(vcpu);
 	kvm_arch_vcpu_put_fp(vcpu);
 	if (has_vhe())
 		kvm_vcpu_put_vhe(vcpu);
@@ -808,8 +801,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 
 	kvm_init_mpidr_data(kvm);
 
-	kvm_arm_vcpu_init_debug(vcpu);
-
 	if (likely(irqchip_in_kernel(kvm))) {
 		/*
 		 * Map the VGIC hardware resources before running a vcpu the
@@ -1187,7 +1178,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		kvm_arm_setup_debug(vcpu);
 		kvm_arch_vcpu_ctxflush_fp(vcpu);
 
 		/**************************************************************
@@ -1204,8 +1194,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * Back from guest
 		 *************************************************************/
 
-		kvm_arm_clear_debug(vcpu);
-
 		/*
 		 * We must sync the PMU state before the vgic state so
 		 * that the vgic can properly sample the updated state of the
@@ -1228,6 +1216,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
 			kvm_timer_sync_user(vcpu);
 
+		if (is_hyp_ctxt(vcpu))
+			kvm_timer_sync_nested(vcpu);
+
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
 		/*
@@ -1571,7 +1562,6 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	}
 
 	vcpu_reset_hcr(vcpu);
-	vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu);
 
 	/*
 	 * Handle the "start in power-off" case.
@@ -2109,6 +2099,7 @@ static void cpu_set_hyp_vector(void)
 static void cpu_hyp_init_context(void)
 {
 	kvm_init_host_cpu_context(host_data_ptr(host_ctxt));
+	kvm_init_host_debug_data();
 
 	if (!is_kernel_in_hyp_mode())
 		cpu_init_hyp_mode();
@@ -2117,7 +2108,6 @@ static void cpu_hyp_init_context(void)
 static void cpu_hyp_init_features(void)
 {
 	cpu_set_hyp_vector();
-	kvm_arm_init_debug();
 
 	if (is_kernel_in_hyp_mode())
 		kvm_timer_init_vhe();
@@ -2300,6 +2290,19 @@ static int __init init_subsystems(void)
 		break;
 	case -ENODEV:
 	case -ENXIO:
+		/*
+		 * No VGIC? No pKVM for you.
+		 *
+		 * Protected mode assumes that VGICv3 is present, so no point
+		 * in trying to hobble along if vgic initialization fails.
+		 */
+		if (is_protected_kvm_enabled())
+			goto out;
+
+		/*
+		 * Otherwise, userspace could choose to implement a GIC for its
+		 * guest on non-cooperative hardware.
+		 */
 		vgic_present = false;
 		err = 0;
 		break;
@@ -2339,7 +2342,7 @@ static void __init teardown_hyp_mode(void)
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
-		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
+		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
 		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
 
 		if (free_sve) {
@@ -2410,6 +2413,13 @@ static void kvm_hyp_init_symbols(void)
 	kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1);
 	kvm_nvhe_sym(__icache_flags) = __icache_flags;
 	kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
+
+	/*
+	 * Flush entire BSS since part of its data containing init symbols is read
+	 * while the MMU is off.
+	 */
+	kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start),
+				kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start));
 }
 
 static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
@@ -2527,15 +2537,15 @@ static int __init init_hyp_mode(void)
 	 * Allocate stack pages for Hypervisor-mode
 	 */
 	for_each_possible_cpu(cpu) {
-		unsigned long stack_page;
+		unsigned long stack_base;
 
-		stack_page = __get_free_page(GFP_KERNEL);
-		if (!stack_page) {
+		stack_base = __get_free_pages(GFP_KERNEL, NVHE_STACK_SHIFT - PAGE_SHIFT);
+		if (!stack_base) {
 			err = -ENOMEM;
 			goto out_err;
 		}
 
-		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
+		per_cpu(kvm_arm_hyp_stack_base, cpu) = stack_base;
 	}
 
 	/*
@@ -2604,9 +2614,9 @@ static int __init init_hyp_mode(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
+		char *stack_base = (char *)per_cpu(kvm_arm_hyp_stack_base, cpu);
 
-		err = create_hyp_stack(__pa(stack_page), &params->stack_hyp_va);
+		err = create_hyp_stack(__pa(stack_base), &params->stack_hyp_va);
 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
 			goto out_err;
@@ -2618,7 +2628,7 @@ static int __init init_hyp_mode(void)
 		 * __hyp_pa() won't do the right thing there, since the stack
 		 * has been mapped in the flexible private VA space.
 		 */
-		params->stack_pa = __pa(stack_page);
+		params->stack_pa = __pa(stack_base);
 	}
 
 	for_each_possible_cpu(cpu) {
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index ce8886122ed3..0e4c805e7e89 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -3,7 +3,8 @@
  * Debug and Guest Debug support
  *
  * Copyright (C) 2015 - Linaro Ltd
- * Author: Alex Bennée <alex.bennee@linaro.org>
+ * Authors: Alex Bennée <alex.bennee@linaro.org>
+ * 	    Oliver Upton <oliver.upton@linux.dev>
  */
 
 #include <linux/kvm_host.h>
@@ -14,72 +15,6 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_emulate.h>
 
-#include "trace.h"
-
-/* These are the bits of MDSCR_EL1 we may manipulate */
-#define MDSCR_EL1_DEBUG_MASK	(DBG_MDSCR_SS | \
-				DBG_MDSCR_KDE | \
-				DBG_MDSCR_MDE)
-
-static DEFINE_PER_CPU(u64, mdcr_el2);
-
-/*
- * save/restore_guest_debug_regs
- *
- * For some debug operations we need to tweak some guest registers. As
- * a result we need to save the state of those registers before we
- * make those modifications.
- *
- * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled
- * after we have restored the preserved value to the main context.
- *
- * When single-step is enabled by userspace, we tweak PSTATE.SS on every
- * guest entry. Preserve PSTATE.SS so we can restore the original value
- * for the vcpu after the single-step is disabled.
- */
-static void save_guest_debug_regs(struct kvm_vcpu *vcpu)
-{
-	u64 val = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-
-	vcpu->arch.guest_debug_preserved.mdscr_el1 = val;
-
-	trace_kvm_arm_set_dreg32("Saved MDSCR_EL1",
-				vcpu->arch.guest_debug_preserved.mdscr_el1);
-
-	vcpu->arch.guest_debug_preserved.pstate_ss =
-					(*vcpu_cpsr(vcpu) & DBG_SPSR_SS);
-}
-
-static void restore_guest_debug_regs(struct kvm_vcpu *vcpu)
-{
-	u64 val = vcpu->arch.guest_debug_preserved.mdscr_el1;
-
-	vcpu_write_sys_reg(vcpu, val, MDSCR_EL1);
-
-	trace_kvm_arm_set_dreg32("Restored MDSCR_EL1",
-				vcpu_read_sys_reg(vcpu, MDSCR_EL1));
-
-	if (vcpu->arch.guest_debug_preserved.pstate_ss)
-		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
-	else
-		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
-}
-
-/**
- * kvm_arm_init_debug - grab what we need for debug
- *
- * Currently the sole task of this function is to retrieve the initial
- * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has
- * presumably been set-up by some knowledgeable bootcode.
- *
- * It is called once per-cpu during CPU hyp initialisation.
- */
-
-void kvm_arm_init_debug(void)
-{
-	__this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2));
-}
-
 /**
  * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value
  *
@@ -95,11 +30,14 @@ void kvm_arm_init_debug(void)
  */
 static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
 {
+	preempt_disable();
+
 	/*
 	 * This also clears MDCR_EL2_E2PB_MASK and MDCR_EL2_E2TB_MASK
 	 * to disable guest access to the profiling and trace buffers
 	 */
-	vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
+	vcpu->arch.mdcr_el2 = FIELD_PREP(MDCR_EL2_HPMN,
+					 *host_data_ptr(nr_event_counters));
 	vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
 				MDCR_EL2_TPMS |
 				MDCR_EL2_TTRF |
@@ -113,233 +51,215 @@ static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu)
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE;
 
 	/*
-	 * Trap debug register access when one of the following is true:
-	 *  - Userspace is using the hardware to debug the guest
-	 *  (KVM_GUESTDBG_USE_HW is set).
-	 *  - The guest is not using debug (DEBUG_DIRTY clear).
-	 *  - The guest has enabled the OS Lock (debug exceptions are blocked).
+	 * Trap debug registers if the guest doesn't have ownership of them.
 	 */
-	if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) ||
-	    !vcpu_get_flag(vcpu, DEBUG_DIRTY) ||
-	    kvm_vcpu_os_lock_enabled(vcpu))
+	if (!kvm_guest_owns_debug_regs(vcpu))
 		vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA;
 
-	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
-}
+	/* Write MDCR_EL2 directly if we're already at EL2 */
+	if (has_vhe())
+		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
 
-/**
- * kvm_arm_vcpu_init_debug - setup vcpu debug traps
- *
- * @vcpu:	the vcpu pointer
- *
- * Set vcpu initial mdcr_el2 value.
- */
-void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu)
-{
-	preempt_disable();
-	kvm_arm_setup_mdcr_el2(vcpu);
 	preempt_enable();
 }
 
-/**
- * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state
- * @vcpu:	the vcpu pointer
- */
-
-void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
+void kvm_init_host_debug_data(void)
 {
-	vcpu->arch.debug_ptr = &vcpu->arch.vcpu_debug_state;
+	u64 dfr0 = read_sysreg(id_aa64dfr0_el1);
+
+	if (cpuid_feature_extract_signed_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT) > 0)
+		*host_data_ptr(nr_event_counters) = FIELD_GET(ARMV8_PMU_PMCR_N,
+							      read_sysreg(pmcr_el0));
+
+	*host_data_ptr(debug_brps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, BRPs, dfr0);
+	*host_data_ptr(debug_wrps) = SYS_FIELD_GET(ID_AA64DFR0_EL1, WRPs, dfr0);
+
+	if (has_vhe())
+		return;
+
+	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) &&
+	    !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P))
+		host_data_set_flag(HAS_SPE);
+
+	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) {
+		/* Force disable trace in protected mode in case of no TRBE */
+		if (is_protected_kvm_enabled())
+			host_data_set_flag(EL1_TRACING_CONFIGURED);
+
+		if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) &&
+		    !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P))
+			host_data_set_flag(HAS_TRBE);
+	}
 }
 
-/**
- * kvm_arm_setup_debug - set up debug related stuff
+/*
+ * Configures the 'external' MDSCR_EL1 value for the guest, i.e. when the host
+ * has taken over MDSCR_EL1.
  *
- * @vcpu:	the vcpu pointer
+ *  - Userspace is single-stepping the guest, and MDSCR_EL1.SS is forced to 1.
  *
- * This is called before each entry into the hypervisor to setup any
- * debug related registers.
+ *  - Userspace is using the breakpoint/watchpoint registers to debug the
+ *    guest, and MDSCR_EL1.MDE is forced to 1.
  *
- * Additionally, KVM only traps guest accesses to the debug registers if
- * the guest is not actively using them (see the DEBUG_DIRTY
- * flag on vcpu->arch.iflags).  Since the guest must not interfere
- * with the hardware state when debugging the guest, we must ensure that
- * trapping is enabled whenever we are debugging the guest using the
- * debug registers.
+ *  - The guest has enabled the OS Lock, and KVM is forcing MDSCR_EL1.MDE to 0,
+ *    masking all debug exceptions affected by the OS Lock.
  */
-
-void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
+static void setup_external_mdscr(struct kvm_vcpu *vcpu)
 {
-	unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2;
+	/*
+	 * Use the guest's MDSCR_EL1 as a starting point, since there are
+	 * several other features controlled by MDSCR_EL1 that are not relevant
+	 * to the host.
+	 *
+	 * Clear the bits that KVM may use which also satisfies emulation of
+	 * the OS Lock as MDSCR_EL1.MDE is cleared.
+	 */
+	u64 mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1) & ~(MDSCR_EL1_SS |
+							   MDSCR_EL1_MDE |
+							   MDSCR_EL1_KDE);
 
-	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		mdscr |= MDSCR_EL1_SS;
 
-	kvm_arm_setup_mdcr_el2(vcpu);
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW)
+		mdscr |= MDSCR_EL1_MDE | MDSCR_EL1_KDE;
 
-	/* Check if we need to use the debug registers. */
+	vcpu->arch.external_mdscr_el1 = mdscr;
+}
+
+void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu)
+{
+	u64 mdscr;
+
+	/* Must be called before kvm_vcpu_load_vhe() */
+	KVM_BUG_ON(vcpu_get_flag(vcpu, SYSREGS_ON_CPU), vcpu->kvm);
+
+	/*
+	 * Determine which of the possible debug states we're in:
+	 *
+	 *  - VCPU_DEBUG_HOST_OWNED: KVM has taken ownership of the guest's
+	 *    breakpoint/watchpoint registers, or needs to use MDSCR_EL1 to do
+	 *    software step or emulate the effects of the OS Lock being enabled.
+	 *
+	 *  - VCPU_DEBUG_GUEST_OWNED: The guest has debug exceptions enabled, and
+	 *    the breakpoint/watchpoint registers need to be loaded eagerly.
+	 *
+	 *  - VCPU_DEBUG_FREE: Neither of the above apply, no breakpoint/watchpoint
+	 *    context needs to be loaded on the CPU.
+	 */
 	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
-		/* Save guest debug state */
-		save_guest_debug_regs(vcpu);
+		vcpu->arch.debug_owner = VCPU_DEBUG_HOST_OWNED;
+		setup_external_mdscr(vcpu);
 
 		/*
-		 * Single Step (ARM ARM D2.12.3 The software step state
-		 * machine)
-		 *
-		 * If we are doing Single Step we need to manipulate
-		 * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the
-		 * step has occurred the hypervisor will trap the
-		 * debug exception and we return to userspace.
-		 *
-		 * If the guest attempts to single step its userspace
-		 * we would have to deal with a trapped exception
-		 * while in the guest kernel. Because this would be
-		 * hard to unwind we suppress the guest's ability to
-		 * do so by masking MDSCR_EL.SS.
-		 *
-		 * This confuses guest debuggers which use
-		 * single-step behind the scenes but everything
-		 * returns to normal once the host is no longer
-		 * debugging the system.
+		 * Steal the guest's single-step state machine if userspace wants
+		 * single-step the guest.
 		 */
 		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			/*
-			 * If the software step state at the last guest exit
-			 * was Active-pending, we don't set DBG_SPSR_SS so
-			 * that the state is maintained (to not run another
-			 * single-step until the pending Software Step
-			 * exception is taken).
-			 */
-			if (!vcpu_get_flag(vcpu, DBG_SS_ACTIVE_PENDING))
+			if (*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
+				vcpu_clear_flag(vcpu, GUEST_SS_ACTIVE_PENDING);
+			else
+				vcpu_set_flag(vcpu, GUEST_SS_ACTIVE_PENDING);
+
+			if (!vcpu_get_flag(vcpu, HOST_SS_ACTIVE_PENDING))
 				*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
 			else
 				*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
-
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr |= DBG_MDSCR_SS;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
-		} else {
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr &= ~DBG_MDSCR_SS;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 		}
+	} else {
+		mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
 
-		trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu));
-
-		/*
-		 * HW Breakpoints and watchpoints
-		 *
-		 * We simply switch the debug_ptr to point to our new
-		 * external_debug_state which has been populated by the
-		 * debug ioctl. The existing DEBUG_DIRTY mechanism ensures
-		 * the registers are updated on the world switch.
-		 */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
-			/* Enable breakpoints/watchpoints */
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr |= DBG_MDSCR_MDE;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
-
-			vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state;
-			vcpu_set_flag(vcpu, DEBUG_DIRTY);
-
-			trace_kvm_arm_set_regset("BKPTS", get_num_brps(),
-						&vcpu->arch.debug_ptr->dbg_bcr[0],
-						&vcpu->arch.debug_ptr->dbg_bvr[0]);
-
-			trace_kvm_arm_set_regset("WAPTS", get_num_wrps(),
-						&vcpu->arch.debug_ptr->dbg_wcr[0],
-						&vcpu->arch.debug_ptr->dbg_wvr[0]);
-
-		/*
-		 * The OS Lock blocks debug exceptions in all ELs when it is
-		 * enabled. If the guest has enabled the OS Lock, constrain its
-		 * effects to the guest. Emulate the behavior by clearing
-		 * MDSCR_EL1.MDE. In so doing, we ensure that host debug
-		 * exceptions are unaffected by guest configuration of the OS
-		 * Lock.
-		 */
-		} else if (kvm_vcpu_os_lock_enabled(vcpu)) {
-			mdscr = vcpu_read_sys_reg(vcpu, MDSCR_EL1);
-			mdscr &= ~DBG_MDSCR_MDE;
-			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
-		}
+		if (mdscr & (MDSCR_EL1_KDE | MDSCR_EL1_MDE))
+			vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED;
+		else
+			vcpu->arch.debug_owner = VCPU_DEBUG_FREE;
 	}
 
-	BUG_ON(!vcpu->guest_debug &&
-		vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state);
-
-	/* If KDE or MDE are set, perform a full save/restore cycle. */
-	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
-		vcpu_set_flag(vcpu, DEBUG_DIRTY);
-
-	/* Write mdcr_el2 changes since vcpu_load on VHE systems */
-	if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2)
-		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
-
-	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
+	kvm_arm_setup_mdcr_el2(vcpu);
 }
 
-void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
+void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu)
 {
-	trace_kvm_arm_clear_debug(vcpu->guest_debug);
+	if (likely(!(vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		return;
 
 	/*
-	 * Restore the guest's debug registers if we were using them.
+	 * Save the host's software step state and restore the guest's before
+	 * potentially returning to userspace.
 	 */
-	if (vcpu->guest_debug || kvm_vcpu_os_lock_enabled(vcpu)) {
-		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS))
-				/*
-				 * Mark the vcpu as ACTIVE_PENDING
-				 * until Software Step exception is taken.
-				 */
-				vcpu_set_flag(vcpu, DBG_SS_ACTIVE_PENDING);
-		}
-
-		restore_guest_debug_regs(vcpu);
+	if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS))
+		vcpu_set_flag(vcpu, HOST_SS_ACTIVE_PENDING);
+	else
+		vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING);
 
-		/*
-		 * If we were using HW debug we need to restore the
-		 * debug_ptr to the guest debug state.
-		 */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
-			kvm_arm_reset_debug_ptr(vcpu);
+	if (vcpu_get_flag(vcpu, GUEST_SS_ACTIVE_PENDING))
+		*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
+	else
+		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
+}
 
-			trace_kvm_arm_set_regset("BKPTS", get_num_brps(),
-						&vcpu->arch.debug_ptr->dbg_bcr[0],
-						&vcpu->arch.debug_ptr->dbg_bvr[0]);
+/*
+ * Updates ownership of the debug registers after a trapped guest access to a
+ * breakpoint/watchpoint register. Host ownership of the debug registers is of
+ * strictly higher priority, and it is the responsibility of the VMM to emulate
+ * guest debug exceptions in this configuration.
+ */
+void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu)
+{
+	if (kvm_host_owns_debug_regs(vcpu))
+		return;
 
-			trace_kvm_arm_set_regset("WAPTS", get_num_wrps(),
-						&vcpu->arch.debug_ptr->dbg_wcr[0],
-						&vcpu->arch.debug_ptr->dbg_wvr[0]);
-		}
-	}
+	vcpu->arch.debug_owner = VCPU_DEBUG_GUEST_OWNED;
+	kvm_arm_setup_mdcr_el2(vcpu);
 }
 
-void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu)
+void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val)
 {
-	u64 dfr0;
+	if (val & OSLAR_EL1_OSLK)
+		__vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK;
+	else
+		__vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK;
 
-	/* For VHE, there is nothing to do */
-	if (has_vhe())
+	preempt_disable();
+	kvm_arch_vcpu_put(vcpu);
+	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	preempt_enable();
+}
+
+void kvm_enable_trbe(void)
+{
+	if (has_vhe() || is_protected_kvm_enabled() ||
+	    WARN_ON_ONCE(preemptible()))
 		return;
 
-	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	/*
-	 * If SPE is present on this CPU and is available at current EL,
-	 * we may need to check if the host state needs to be saved.
-	 */
-	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) &&
-	    !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT)))
-		vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE);
+	host_data_set_flag(TRBE_ENABLED);
+}
+EXPORT_SYMBOL_GPL(kvm_enable_trbe);
+
+void kvm_disable_trbe(void)
+{
+	if (has_vhe() || is_protected_kvm_enabled() ||
+	    WARN_ON_ONCE(preemptible()))
+		return;
 
-	/* Check if we have TRBE implemented and available at the host */
-	if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceBuffer_SHIFT) &&
-	    !(read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_P))
-		vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_TRBE);
+	host_data_clear_flag(TRBE_ENABLED);
 }
+EXPORT_SYMBOL_GPL(kvm_disable_trbe);
 
-void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu)
+void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest)
 {
-	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_SPE);
-	vcpu_clear_flag(vcpu, DEBUG_STATE_SAVE_TRBE);
+	if (is_protected_kvm_enabled() || WARN_ON_ONCE(preemptible()))
+		return;
+
+	if (has_vhe()) {
+		write_sysreg_s(trfcr_while_in_guest, SYS_TRFCR_EL12);
+		return;
+	}
+
+	*host_data_ptr(trfcr_while_in_guest) = trfcr_while_in_guest;
+	if (read_sysreg_s(SYS_TRFCR_EL1) != trfcr_while_in_guest)
+		host_data_set_flag(EL1_TRACING_CONFIGURED);
+	else
+		host_data_clear_flag(EL1_TRACING_CONFIGURED);
 }
+EXPORT_SYMBOL_GPL(kvm_tracing_set_el1_configuration);
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index f1b7287e1f3c..607d37bab70b 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -89,6 +89,9 @@ enum cgt_group_id {
 	CGT_HCRX_EnFPM,
 	CGT_HCRX_TCR2En,
 
+	CGT_CNTHCTL_EL1TVT,
+	CGT_CNTHCTL_EL1TVCT,
+
 	CGT_ICH_HCR_TC,
 	CGT_ICH_HCR_TALL0,
 	CGT_ICH_HCR_TALL1,
@@ -124,6 +127,8 @@ enum cgt_group_id {
 	__COMPLEX_CONDITIONS__,
 	CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__,
 	CGT_CNTHCTL_EL1PTEN,
+	CGT_CNTHCTL_EL1NVPCT,
+	CGT_CNTHCTL_EL1NVVCT,
 
 	CGT_CPTR_TTA,
 	CGT_MDCR_HPMN,
@@ -393,6 +398,18 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= HCRX_EL2_TCR2En,
 		.behaviour	= BEHAVE_FORWARD_RW,
 	},
+	[CGT_CNTHCTL_EL1TVT] = {
+		.index		= CNTHCTL_EL2,
+		.value		= CNTHCTL_EL1TVT,
+		.mask		= CNTHCTL_EL1TVT,
+		.behaviour	= BEHAVE_FORWARD_RW,
+	},
+	[CGT_CNTHCTL_EL1TVCT] = {
+		.index		= CNTHCTL_EL2,
+		.value		= CNTHCTL_EL1TVCT,
+		.mask		= CNTHCTL_EL1TVCT,
+		.behaviour	= BEHAVE_FORWARD_READ,
+	},
 	[CGT_ICH_HCR_TC] = {
 		.index		= ICH_HCR_EL2,
 		.value		= ICH_HCR_TC,
@@ -487,6 +504,32 @@ static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu)
 	return BEHAVE_FORWARD_RW;
 }
 
+static bool is_nested_nv2_guest(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	val = __vcpu_sys_reg(vcpu, HCR_EL2);
+	return ((val & (HCR_E2H | HCR_TGE | HCR_NV2 | HCR_NV1 | HCR_NV)) == (HCR_E2H | HCR_NV2 | HCR_NV));
+}
+
+static enum trap_behaviour check_cnthctl_el1nvpct(struct kvm_vcpu *vcpu)
+{
+	if (!is_nested_nv2_guest(vcpu) ||
+	    !(__vcpu_sys_reg(vcpu, CNTHCTL_EL2) & CNTHCTL_EL1NVPCT))
+		return BEHAVE_HANDLE_LOCALLY;
+
+	return BEHAVE_FORWARD_RW;
+}
+
+static enum trap_behaviour check_cnthctl_el1nvvct(struct kvm_vcpu *vcpu)
+{
+	if (!is_nested_nv2_guest(vcpu) ||
+	    !(__vcpu_sys_reg(vcpu, CNTHCTL_EL2) & CNTHCTL_EL1NVVCT))
+		return BEHAVE_HANDLE_LOCALLY;
+
+	return BEHAVE_FORWARD_RW;
+}
+
 static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu)
 {
 	u64 val = __vcpu_sys_reg(vcpu, CPTR_EL2);
@@ -534,6 +577,8 @@ static enum trap_behaviour check_mdcr_hpmn(struct kvm_vcpu *vcpu)
 static const complex_condition_check ccc[] = {
 	CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten),
 	CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten),
+	CCC(CGT_CNTHCTL_EL1NVPCT, check_cnthctl_el1nvpct),
+	CCC(CGT_CNTHCTL_EL1NVVCT, check_cnthctl_el1nvvct),
 	CCC(CGT_CPTR_TTA, check_cptr_tta),
 	CCC(CGT_MDCR_HPMN, check_mdcr_hpmn),
 };
@@ -850,11 +895,15 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 		      SYS_CNTHP_CVAL_EL2, CGT_HCR_NV),
 	SR_RANGE_TRAP(SYS_CNTHV_TVAL_EL2,
 		      SYS_CNTHV_CVAL_EL2, CGT_HCR_NV),
-	/* All _EL02, _EL12 registers */
+	/* All _EL02, _EL12 registers up to CNTKCTL_EL12*/
 	SR_RANGE_TRAP(sys_reg(3, 5, 0, 0, 0),
 		      sys_reg(3, 5, 10, 15, 7), CGT_HCR_NV),
 	SR_RANGE_TRAP(sys_reg(3, 5, 12, 0, 0),
-		      sys_reg(3, 5, 14, 15, 7), CGT_HCR_NV),
+		      sys_reg(3, 5, 14, 1, 0), CGT_HCR_NV),
+	SR_TRAP(SYS_CNTP_CTL_EL02,	CGT_CNTHCTL_EL1NVPCT),
+	SR_TRAP(SYS_CNTP_CVAL_EL02,	CGT_CNTHCTL_EL1NVPCT),
+	SR_TRAP(SYS_CNTV_CTL_EL02,	CGT_CNTHCTL_EL1NVVCT),
+	SR_TRAP(SYS_CNTV_CVAL_EL02,	CGT_CNTHCTL_EL1NVVCT),
 	SR_TRAP(OP_AT_S1E2R,		CGT_HCR_NV),
 	SR_TRAP(OP_AT_S1E2W,		CGT_HCR_NV),
 	SR_TRAP(OP_AT_S12E1R,		CGT_HCR_NV),
@@ -1184,6 +1233,11 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_CNTP_CTL_EL0,	CGT_CNTHCTL_EL1PTEN),
 	SR_TRAP(SYS_CNTPCT_EL0,		CGT_CNTHCTL_EL1PCTEN),
 	SR_TRAP(SYS_CNTPCTSS_EL0,	CGT_CNTHCTL_EL1PCTEN),
+	SR_TRAP(SYS_CNTV_TVAL_EL0,	CGT_CNTHCTL_EL1TVT),
+	SR_TRAP(SYS_CNTV_CVAL_EL0,	CGT_CNTHCTL_EL1TVT),
+	SR_TRAP(SYS_CNTV_CTL_EL0,	CGT_CNTHCTL_EL1TVT),
+	SR_TRAP(SYS_CNTVCT_EL0,		CGT_CNTHCTL_EL1TVCT),
+	SR_TRAP(SYS_CNTVCTSS_EL0,	CGT_CNTHCTL_EL1TVCT),
 	SR_TRAP(SYS_FPMR,		CGT_HCRX_EnFPM),
 	/*
 	 * IMPDEF choice:
@@ -2345,14 +2399,14 @@ inject:
 	return true;
 }
 
-static bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+static bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg, u64 control_bit)
 {
 	bool control_bit_set;
 
 	if (!vcpu_has_nv(vcpu))
 		return false;
 
-	control_bit_set = __vcpu_sys_reg(vcpu, HCR_EL2) & control_bit;
+	control_bit_set = __vcpu_sys_reg(vcpu, reg) & control_bit;
 	if (!is_hyp_ctxt(vcpu) && control_bit_set) {
 		kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu));
 		return true;
@@ -2360,9 +2414,24 @@ static bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit)
 	return false;
 }
 
+static bool forward_hcr_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+{
+	return __forward_traps(vcpu, HCR_EL2, control_bit);
+}
+
 bool forward_smc_trap(struct kvm_vcpu *vcpu)
 {
-	return forward_traps(vcpu, HCR_TSC);
+	return forward_hcr_traps(vcpu, HCR_TSC);
+}
+
+static bool forward_mdcr_traps(struct kvm_vcpu *vcpu, u64 control_bit)
+{
+	return __forward_traps(vcpu, MDCR_EL2, control_bit);
+}
+
+bool forward_debug_exception(struct kvm_vcpu *vcpu)
+{
+	return forward_mdcr_traps(vcpu, MDCR_EL2_TDE);
 }
 
 static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr)
@@ -2406,7 +2475,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	 * Forward this trap to the virtual EL2 if the virtual
 	 * HCR_EL2.NV bit is set and this is coming from !EL2.
 	 */
-	if (forward_traps(vcpu, HCR_NV))
+	if (forward_hcr_traps(vcpu, HCR_NV))
 		return;
 
 	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 98718bd65bf1..4d3d1a2eb157 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -65,14 +65,14 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	*host_data_ptr(fpsimd_state) = kern_hyp_va(&current->thread.uw.fpsimd_state);
 	*host_data_ptr(fpmr_ptr) = kern_hyp_va(&current->thread.uw.fpmr);
 
-	vcpu_clear_flag(vcpu, HOST_SVE_ENABLED);
+	host_data_clear_flag(HOST_SVE_ENABLED);
 	if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
-		vcpu_set_flag(vcpu, HOST_SVE_ENABLED);
+		host_data_set_flag(HOST_SVE_ENABLED);
 
 	if (system_supports_sme()) {
-		vcpu_clear_flag(vcpu, HOST_SME_ENABLED);
+		host_data_clear_flag(HOST_SME_ENABLED);
 		if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
-			vcpu_set_flag(vcpu, HOST_SME_ENABLED);
+			host_data_set_flag(HOST_SME_ENABLED);
 
 		/*
 		 * If PSTATE.SM is enabled then save any pending FP
@@ -168,7 +168,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 	 */
 	if (has_vhe() && system_supports_sme()) {
 		/* Also restore EL0 state seen on entry */
-		if (vcpu_get_flag(vcpu, HOST_SME_ENABLED))
+		if (host_data_test_flag(HOST_SME_ENABLED))
 			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN);
 		else
 			sysreg_clear_set(CPACR_EL1,
@@ -227,7 +227,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 		 * for EL0.  To avoid spurious traps, restore the trap state
 		 * seen by kvm_arch_vcpu_load_fp():
 		 */
-		if (vcpu_get_flag(vcpu, HOST_SVE_ENABLED))
+		if (host_data_test_flag(HOST_SVE_ENABLED))
 			sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
 		else
 			sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 12dad841f2a5..2196979a24a3 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -917,31 +917,24 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
-	int ret = 0;
-
 	trace_kvm_set_guest_debug(vcpu, dbg->control);
 
-	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (dbg->control & KVM_GUESTDBG_ENABLE) {
-		vcpu->guest_debug = dbg->control;
-
-		/* Hardware assisted Break and Watch points */
-		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) {
-			vcpu->arch.external_debug_state = dbg->arch;
-		}
+	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK)
+		return -EINVAL;
 
-	} else {
-		/* If not enabled clear all flags */
+	if (!(dbg->control & KVM_GUESTDBG_ENABLE)) {
 		vcpu->guest_debug = 0;
-		vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING);
+		vcpu_clear_flag(vcpu, HOST_SS_ACTIVE_PENDING);
+		return 0;
 	}
 
-out:
-	return ret;
+	vcpu->guest_debug = dbg->control;
+
+	/* Hardware assisted Break and Watch points */
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW)
+		vcpu->arch.external_debug_state = dbg->arch;
+
+	return 0;
 }
 
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index d7c2990e7c9e..512d152233ff 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -183,6 +183,9 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 	struct kvm_run *run = vcpu->run;
 	u64 esr = kvm_vcpu_get_esr(vcpu);
 
+	if (!vcpu->guest_debug && forward_debug_exception(vcpu))
+		return 1;
+
 	run->exit_reason = KVM_EXIT_DEBUG;
 	run->debug.arch.hsr = lower_32_bits(esr);
 	run->debug.arch.hsr_high = upper_32_bits(esr);
@@ -193,7 +196,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
 		run->debug.arch.far = vcpu->arch.fault.far_el2;
 		break;
 	case ESR_ELx_EC_SOFTSTP_LOW:
-		vcpu_clear_flag(vcpu, DBG_SS_ACTIVE_PENDING);
+		*vcpu_cpsr(vcpu) |= DBG_SPSR_SS;
 		break;
 	}
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index d00093699aaf..502a5b73ee70 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -88,15 +88,26 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
+static struct kvm_guest_debug_arch *__vcpu_debug_regs(struct kvm_vcpu *vcpu)
+{
+	switch (vcpu->arch.debug_owner) {
+	case VCPU_DEBUG_FREE:
+		WARN_ON_ONCE(1);
+		fallthrough;
+	case VCPU_DEBUG_GUEST_OWNED:
+		return &vcpu->arch.vcpu_debug_state;
+	case VCPU_DEBUG_HOST_OWNED:
+		return &vcpu->arch.external_debug_state;
+	}
+
+	return NULL;
+}
+
 static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
 			       struct kvm_cpu_context *ctxt)
 {
-	u64 aa64dfr0;
-	int brps, wrps;
-
-	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
-	brps = (aa64dfr0 >> 12) & 0xf;
-	wrps = (aa64dfr0 >> 20) & 0xf;
+	int brps = *host_data_ptr(debug_brps);
+	int wrps = *host_data_ptr(debug_wrps);
 
 	save_debug(dbg->dbg_bcr, dbgbcr, brps);
 	save_debug(dbg->dbg_bvr, dbgbvr, brps);
@@ -109,13 +120,8 @@ static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
 static void __debug_restore_state(struct kvm_guest_debug_arch *dbg,
 				  struct kvm_cpu_context *ctxt)
 {
-	u64 aa64dfr0;
-	int brps, wrps;
-
-	aa64dfr0 = read_sysreg(id_aa64dfr0_el1);
-
-	brps = (aa64dfr0 >> 12) & 0xf;
-	wrps = (aa64dfr0 >> 20) & 0xf;
+	int brps = *host_data_ptr(debug_brps);
+	int wrps = *host_data_ptr(debug_wrps);
 
 	restore_debug(dbg->dbg_bcr, dbgbcr, brps);
 	restore_debug(dbg->dbg_bvr, dbgbvr, brps);
@@ -132,13 +138,13 @@ static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	if (!vcpu_get_flag(vcpu, DEBUG_DIRTY))
+	if (!kvm_debug_regs_in_use(vcpu))
 		return;
 
 	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
 	host_dbg = host_data_ptr(host_debug_state.regs);
-	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
+	guest_dbg = __vcpu_debug_regs(vcpu);
 
 	__debug_save_state(host_dbg, host_ctxt);
 	__debug_restore_state(guest_dbg, guest_ctxt);
@@ -151,18 +157,16 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	if (!vcpu_get_flag(vcpu, DEBUG_DIRTY))
+	if (!kvm_debug_regs_in_use(vcpu))
 		return;
 
 	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
 	host_dbg = host_data_ptr(host_debug_state.regs);
-	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
+	guest_dbg = __vcpu_debug_regs(vcpu);
 
 	__debug_save_state(guest_dbg, guest_ctxt);
 	__debug_restore_state(host_dbg, host_ctxt);
-
-	vcpu_clear_flag(vcpu, DEBUG_DIRTY);
 }
 
 #endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index abfa6ad92e91..f838a45665f2 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -501,7 +501,12 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu)
+static inline u64 compute_counter_value(struct arch_timer_context *ctxt)
+{
+	return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt);
+}
+
+static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_context *ctxt;
 	u32 sysreg;
@@ -511,18 +516,19 @@ static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu)
 	 * We only get here for 64bit guests, 32bit guests will hit
 	 * the long and winding road all the way to the standard
 	 * handling. Yes, it sucks to be irrelevant.
+	 *
+	 * Also, we only deal with non-hypervisor context here (either
+	 * an EL1 guest, or a non-HYP context of an EL2 guest).
 	 */
+	if (is_hyp_ctxt(vcpu))
+		return false;
+
 	sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
 
 	switch (sysreg) {
 	case SYS_CNTPCT_EL0:
 	case SYS_CNTPCTSS_EL0:
 		if (vcpu_has_nv(vcpu)) {
-			if (is_hyp_ctxt(vcpu)) {
-				ctxt = vcpu_hptimer(vcpu);
-				break;
-			}
-
 			/* Check for guest hypervisor trapping */
 			val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2);
 			if (!vcpu_el2_e2h_is_set(vcpu))
@@ -534,16 +540,23 @@ static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu)
 
 		ctxt = vcpu_ptimer(vcpu);
 		break;
+	case SYS_CNTVCT_EL0:
+	case SYS_CNTVCTSS_EL0:
+		if (vcpu_has_nv(vcpu)) {
+			/* Check for guest hypervisor trapping */
+			val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2);
+
+			if (val & CNTHCTL_EL1TVCT)
+				return false;
+		}
+
+		ctxt = vcpu_vtimer(vcpu);
+		break;
 	default:
 		return false;
 	}
 
-	val = arch_timer_read_cntpct_el0();
-
-	if (ctxt->offset.vm_offset)
-		val -= *kern_hyp_va(ctxt->offset.vm_offset);
-	if (ctxt->offset.vcpu_offset)
-		val -= *kern_hyp_va(ctxt->offset.vcpu_offset);
+	val = compute_counter_value(ctxt);
 
 	vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val);
 	__kvm_skip_instr(vcpu);
@@ -588,7 +601,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
 	    __vgic_v3_perform_cpuif_access(vcpu) == 1)
 		return true;
 
-	if (kvm_hyp_handle_cntpct(vcpu))
+	if (kvm_handle_cntxct(vcpu))
 		return true;
 
 	return false;
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index a651c43ad679..76ff095c6b6e 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -18,9 +18,34 @@
 
 static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt);
 
+static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu;
+
+	if (!vcpu)
+		vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
+
+	return vcpu;
+}
+
+static inline bool ctxt_is_guest(struct kvm_cpu_context *ctxt)
+{
+	return host_data_ptr(host_ctxt) != ctxt;
+}
+
+static inline u64 *ctxt_mdscr_el1(struct kvm_cpu_context *ctxt)
+{
+	struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt);
+
+	if (ctxt_is_guest(ctxt) && kvm_host_owns_debug_regs(vcpu))
+		return &vcpu->arch.external_mdscr_el1;
+
+	return &ctxt_sys_reg(ctxt, MDSCR_EL1);
+}
+
 static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
 {
-	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
+	*ctxt_mdscr_el1(ctxt)	= read_sysreg(mdscr_el1);
 
 	// POR_EL0 can affect uaccess, so must be saved/restored early.
 	if (ctxt_has_s1poe(ctxt))
@@ -33,16 +58,6 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, TPIDRRO_EL0)	= read_sysreg(tpidrro_el0);
 }
 
-static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt)
-{
-	struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu;
-
-	if (!vcpu)
-		vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
-
-	return vcpu;
-}
-
 static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt)
 {
 	struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt);
@@ -139,7 +154,7 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 
 static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
 {
-	write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1),  mdscr_el1);
+	write_sysreg(*ctxt_mdscr_el1(ctxt),  mdscr_el1);
 
 	// POR_EL0 can affect uaccess, so must be saved/restored early.
 	if (ctxt_has_s1poe(ctxt))
@@ -283,7 +298,7 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
 	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
 
-	if (has_vhe() || vcpu_get_flag(vcpu, DEBUG_DIRTY))
+	if (has_vhe() || kvm_debug_regs_in_use(vcpu))
 		__vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
 }
 
@@ -300,7 +315,7 @@ static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 	write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2);
 	write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2);
 
-	if (has_vhe() || vcpu_get_flag(vcpu, DEBUG_DIRTY))
+	if (has_vhe() || kvm_debug_regs_in_use(vcpu))
 		write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2);
 }
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
deleted file mode 100644
index f957890c7e38..000000000000
--- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
+++ /dev/null
@@ -1,223 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2021 Google LLC
- * Author: Fuad Tabba <tabba@google.com>
- */
-
-#ifndef __ARM64_KVM_FIXED_CONFIG_H__
-#define __ARM64_KVM_FIXED_CONFIG_H__
-
-#include <asm/sysreg.h>
-
-/*
- * This file contains definitions for features to be allowed or restricted for
- * guest virtual machines, depending on the mode KVM is running in and on the
- * type of guest that is running.
- *
- * The ALLOW masks represent a bitmask of feature fields that are allowed
- * without any restrictions as long as they are supported by the system.
- *
- * The RESTRICT_UNSIGNED masks, if present, represent unsigned fields for
- * features that are restricted to support at most the specified feature.
- *
- * If a feature field is not present in either, than it is not supported.
- *
- * The approach taken for protected VMs is to allow features that are:
- * - Needed by common Linux distributions (e.g., floating point)
- * - Trivial to support, e.g., supporting the feature does not introduce or
- * require tracking of additional state in KVM
- * - Cannot be trapped or prevent the guest from using anyway
- */
-
-/*
- * Allow for protected VMs:
- * - Floating-point and Advanced SIMD
- * - Data Independent Timing
- * - Spectre/Meltdown Mitigation
- */
-#define PVM_ID_AA64PFR0_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP) | \
-	ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD) | \
-	ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_DIT) | \
-	ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) | \
-	ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3) \
-	)
-
-/*
- * Restrict to the following *unsigned* features for protected VMs:
- * - AArch64 guests only (no support for AArch32 guests):
- *	AArch32 adds complexity in trap handling, emulation, condition codes,
- *	etc...
- * - RAS (v1)
- *	Supported by KVM
- */
-#define PVM_ID_AA64PFR0_RESTRICT_UNSIGNED (\
-	SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP) | \
-	SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP) | \
-	SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP) | \
-	SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP) | \
-	SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, RAS, IMP) \
-	)
-
-/*
- * Allow for protected VMs:
- * - Branch Target Identification
- * - Speculative Store Bypassing
- */
-#define PVM_ID_AA64PFR1_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_BT) | \
-	ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SSBS) \
-	)
-
-#define PVM_ID_AA64PFR2_ALLOW 0ULL
-
-/*
- * Allow for protected VMs:
- * - Mixed-endian
- * - Distinction between Secure and Non-secure Memory
- * - Mixed-endian at EL0 only
- * - Non-context synchronizing exception entry and exit
- */
-#define PVM_ID_AA64MMFR0_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_BIGEND) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_SNSMEM) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_BIGENDEL0) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_EXS) \
-	)
-
-/*
- * Restrict to the following *unsigned* features for protected VMs:
- * - 40-bit IPA
- * - 16-bit ASID
- */
-#define PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED (\
-	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_PARANGE), ID_AA64MMFR0_EL1_PARANGE_40) | \
-	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_ASIDBITS), ID_AA64MMFR0_EL1_ASIDBITS_16) \
-	)
-
-/*
- * Allow for protected VMs:
- * - Hardware translation table updates to Access flag and Dirty state
- * - Number of VMID bits from CPU
- * - Hierarchical Permission Disables
- * - Privileged Access Never
- * - SError interrupt exceptions from speculative reads
- * - Enhanced Translation Synchronization
- * - Control for cache maintenance permission
- */
-#define PVM_ID_AA64MMFR1_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_VMIDBits) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HPDS) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_PAN) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_SpecSEI) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_ETS) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_CMOW) \
-	)
-
-/*
- * Allow for protected VMs:
- * - Common not Private translations
- * - User Access Override
- * - IESB bit in the SCTLR_ELx registers
- * - Unaligned single-copy atomicity and atomic functions
- * - ESR_ELx.EC value on an exception by read access to feature ID space
- * - TTL field in address operations.
- * - Break-before-make sequences when changing translation block size
- * - E0PDx mechanism
- */
-#define PVM_ID_AA64MMFR2_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_CnP) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_UAO) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_IESB) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_AT) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_IDS) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_TTL) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_BBM) | \
-	ARM64_FEATURE_MASK(ID_AA64MMFR2_EL1_E0PD) \
-	)
-
-#define PVM_ID_AA64MMFR3_ALLOW (0ULL)
-
-/*
- * No support for Scalable Vectors for protected VMs:
- *	Requires additional support from KVM, e.g., context-switching and
- *	trapping at EL2
- */
-#define PVM_ID_AA64ZFR0_ALLOW (0ULL)
-
-/*
- * No support for debug, including breakpoints, and watchpoints for protected
- * VMs:
- *	The Arm architecture mandates support for at least the Armv8 debug
- *	architecture, which would include at least 2 hardware breakpoints and
- *	watchpoints. Providing that support to protected guests adds
- *	considerable state and complexity. Therefore, the reserved value of 0 is
- *	used for debug-related fields.
- */
-#define PVM_ID_AA64DFR0_ALLOW (0ULL)
-#define PVM_ID_AA64DFR1_ALLOW (0ULL)
-
-/*
- * No support for implementation defined features.
- */
-#define PVM_ID_AA64AFR0_ALLOW (0ULL)
-#define PVM_ID_AA64AFR1_ALLOW (0ULL)
-
-/*
- * No restrictions on instructions implemented in AArch64.
- */
-#define PVM_ID_AA64ISAR0_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_AES) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA1) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA2) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_CRC32) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RDM) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SHA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_SM4) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_DP) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_FHM) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TS) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_TLB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_RNDR) \
-	)
-
-/* Restrict pointer authentication to the basic version. */
-#define PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED (\
-	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), ID_AA64ISAR1_EL1_APA_PAuth) | \
-	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), ID_AA64ISAR1_EL1_API_PAuth) \
-	)
-
-#define PVM_ID_AA64ISAR2_RESTRICT_UNSIGNED (\
-	FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3), ID_AA64ISAR2_EL1_APA3_PAuth) \
-	)
-
-#define PVM_ID_AA64ISAR1_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DPB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_JSCVT) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FCMA) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_LRCPC) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_FRINTTS) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_SB) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_SPECRES) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_BF16) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_DGH) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_I8MM) \
-	)
-
-#define PVM_ID_AA64ISAR2_ALLOW (\
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_ATS1A)| \
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3) | \
-	ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_MOPS) \
-	)
-
-u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id);
-bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code);
-bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code);
-int kvm_check_pvm_sysreg_table(void);
-
-#endif /* __ARM64_KVM_FIXED_CONFIG_H__ */
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index 97c527ef53c2..3766333bace9 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -7,7 +7,7 @@
 #include <nvhe/memory.h>
 #include <nvhe/spinlock.h>
 
-#define HYP_NO_ORDER	USHRT_MAX
+#define HYP_NO_ORDER	((u8)(~0))
 
 struct hyp_pool {
 	/*
@@ -19,11 +19,11 @@ struct hyp_pool {
 	struct list_head free_area[NR_PAGE_ORDERS];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
-	unsigned short max_order;
+	u8 max_order;
 };
 
 /* Allocation */
-void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void *hyp_alloc_pages(struct hyp_pool *pool, u8 order);
 void hyp_split_page(struct hyp_page *page);
 void hyp_get_page(struct hyp_pool *pool, void *addr);
 void hyp_put_page(struct hyp_pool *pool, void *addr);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 0972faccc2af..978f38c386ee 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -11,40 +11,10 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
 #include <asm/virt.h>
+#include <nvhe/memory.h>
 #include <nvhe/pkvm.h>
 #include <nvhe/spinlock.h>
 
-/*
- * SW bits 0-1 are reserved to track the memory ownership state of each page:
- *   00: The page is owned exclusively by the page-table owner.
- *   01: The page is owned by the page-table owner, but is shared
- *       with another entity.
- *   10: The page is shared with, but not owned by the page-table owner.
- *   11: Reserved for future use (lending).
- */
-enum pkvm_page_state {
-	PKVM_PAGE_OWNED			= 0ULL,
-	PKVM_PAGE_SHARED_OWNED		= KVM_PGTABLE_PROT_SW0,
-	PKVM_PAGE_SHARED_BORROWED	= KVM_PGTABLE_PROT_SW1,
-	__PKVM_PAGE_RESERVED		= KVM_PGTABLE_PROT_SW0 |
-					  KVM_PGTABLE_PROT_SW1,
-
-	/* Meta-states which aren't encoded directly in the PTE's SW bits */
-	PKVM_NOPAGE,
-};
-
-#define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
-static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
-						 enum pkvm_page_state state)
-{
-	return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state;
-}
-
-static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
-{
-	return prot & PKVM_PAGE_STATE_PROT_MASK;
-}
-
 struct host_mmu {
 	struct kvm_arch arch;
 	struct kvm_pgtable pgt;
@@ -69,6 +39,13 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
 int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
 int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
+int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
+			    enum kvm_pgtable_prot prot);
+int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
+int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);
+int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index ab205c4d6774..34233d586060 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -7,9 +7,47 @@
 
 #include <linux/types.h>
 
+/*
+ * Bits 0-1 are reserved to track the memory ownership state of each page:
+ *   00: The page is owned exclusively by the page-table owner.
+ *   01: The page is owned by the page-table owner, but is shared
+ *       with another entity.
+ *   10: The page is shared with, but not owned by the page-table owner.
+ *   11: Reserved for future use (lending).
+ */
+enum pkvm_page_state {
+	PKVM_PAGE_OWNED			= 0ULL,
+	PKVM_PAGE_SHARED_OWNED		= BIT(0),
+	PKVM_PAGE_SHARED_BORROWED	= BIT(1),
+	__PKVM_PAGE_RESERVED		= BIT(0) | BIT(1),
+
+	/* Meta-states which aren't encoded directly in the PTE's SW bits */
+	PKVM_NOPAGE			= BIT(2),
+};
+#define PKVM_PAGE_META_STATES_MASK	(~__PKVM_PAGE_RESERVED)
+
+#define PKVM_PAGE_STATE_PROT_MASK	(KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
+static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
+						 enum pkvm_page_state state)
+{
+	prot &= ~PKVM_PAGE_STATE_PROT_MASK;
+	prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state);
+	return prot;
+}
+
+static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
+{
+	return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot);
+}
+
 struct hyp_page {
-	unsigned short refcount;
-	unsigned short order;
+	u16 refcount;
+	u8 order;
+
+	/* Host (non-meta) state. Guarded by the host stage-2 lock. */
+	enum pkvm_page_state host_state : 8;
+
+	u32 host_share_guest_count;
 };
 
 extern u64 __hyp_vmemmap;
@@ -29,7 +67,13 @@ static inline phys_addr_t hyp_virt_to_phys(void *addr)
 
 #define hyp_phys_to_pfn(phys)	((phys) >> PAGE_SHIFT)
 #define hyp_pfn_to_phys(pfn)	((phys_addr_t)((pfn) << PAGE_SHIFT))
-#define hyp_phys_to_page(phys)	(&hyp_vmemmap[hyp_phys_to_pfn(phys)])
+
+static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys)
+{
+	BUILD_BUG_ON(sizeof(struct hyp_page) != sizeof(u64));
+	return &hyp_vmemmap[hyp_phys_to_pfn(phys)];
+}
+
 #define hyp_virt_to_page(virt)	hyp_phys_to_page(__hyp_pa(virt))
 #define hyp_virt_to_pfn(virt)	hyp_phys_to_pfn(__hyp_pa(virt))
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
index 24a9a8330d19..e42bf68c8848 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h
@@ -20,6 +20,12 @@ struct pkvm_hyp_vcpu {
 
 	/* Backpointer to the host's (untrusted) vCPU instance. */
 	struct kvm_vcpu *host_vcpu;
+
+	/*
+	 * If this hyp vCPU is loaded, then this is a backpointer to the
+	 * per-cpu pointer tracking us. Otherwise, NULL if not loaded.
+	 */
+	struct pkvm_hyp_vcpu **loaded_hyp_vcpu;
 };
 
 /*
@@ -47,6 +53,8 @@ struct pkvm_hyp_vm {
 	struct pkvm_hyp_vcpu *vcpus[];
 };
 
+extern hyp_spinlock_t vm_table_lock;
+
 static inline struct pkvm_hyp_vm *
 pkvm_hyp_vcpu_to_hyp_vm(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
@@ -58,6 +66,11 @@ static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu)
 	return vcpu_is_protected(&hyp_vcpu->vcpu);
 }
 
+static inline bool pkvm_hyp_vm_is_protected(struct pkvm_hyp_vm *hyp_vm)
+{
+	return kvm_vm_is_protected(&hyp_vm->kvm);
+}
+
 void pkvm_hyp_vm_table_init(void *tbl);
 
 int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva,
@@ -69,5 +82,15 @@ int __pkvm_teardown_vm(pkvm_handle_t handle);
 struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 					 unsigned int vcpu_idx);
 void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu);
+struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void);
+
+struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle);
+struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle);
+void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm);
+
+bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code);
+bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code);
+void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu);
+int kvm_check_pvm_sysreg_table(void);
 
 #endif /* __ARM64_KVM_NVHE_PKVM_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 53efda0235cf..2f4a4f5036bb 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -51,42 +51,55 @@ static void __debug_restore_spe(u64 pmscr_el1)
 	write_sysreg_el1(pmscr_el1, SYS_PMSCR);
 }
 
-static void __debug_save_trace(u64 *trfcr_el1)
+static void __trace_do_switch(u64 *saved_trfcr, u64 new_trfcr)
 {
-	*trfcr_el1 = 0;
+	*saved_trfcr = read_sysreg_el1(SYS_TRFCR);
+	write_sysreg_el1(new_trfcr, SYS_TRFCR);
+}
 
-	/* Check if the TRBE is enabled */
-	if (!(read_sysreg_s(SYS_TRBLIMITR_EL1) & TRBLIMITR_EL1_E))
-		return;
-	/*
-	 * Prohibit trace generation while we are in guest.
-	 * Since access to TRFCR_EL1 is trapped, the guest can't
-	 * modify the filtering set by the host.
-	 */
-	*trfcr_el1 = read_sysreg_el1(SYS_TRFCR);
-	write_sysreg_el1(0, SYS_TRFCR);
-	isb();
-	/* Drain the trace buffer to memory */
-	tsb_csync();
+static bool __trace_needs_drain(void)
+{
+	if (is_protected_kvm_enabled() && host_data_test_flag(HAS_TRBE))
+		return read_sysreg_s(SYS_TRBLIMITR_EL1) & TRBLIMITR_EL1_E;
+
+	return host_data_test_flag(TRBE_ENABLED);
 }
 
-static void __debug_restore_trace(u64 trfcr_el1)
+static bool __trace_needs_switch(void)
 {
-	if (!trfcr_el1)
-		return;
+	return host_data_test_flag(TRBE_ENABLED) ||
+	       host_data_test_flag(EL1_TRACING_CONFIGURED);
+}
 
-	/* Restore trace filter controls */
-	write_sysreg_el1(trfcr_el1, SYS_TRFCR);
+static void __trace_switch_to_guest(void)
+{
+	/* Unsupported with TRBE so disable */
+	if (host_data_test_flag(TRBE_ENABLED))
+		*host_data_ptr(trfcr_while_in_guest) = 0;
+
+	__trace_do_switch(host_data_ptr(host_debug_state.trfcr_el1),
+			  *host_data_ptr(trfcr_while_in_guest));
+
+	if (__trace_needs_drain()) {
+		isb();
+		tsb_csync();
+	}
+}
+
+static void __trace_switch_to_host(void)
+{
+	__trace_do_switch(host_data_ptr(trfcr_while_in_guest),
+			  *host_data_ptr(host_debug_state.trfcr_el1));
 }
 
 void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
 	/* Disable and flush SPE data generation */
-	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE))
+	if (host_data_test_flag(HAS_SPE))
 		__debug_save_spe(host_data_ptr(host_debug_state.pmscr_el1));
-	/* Disable and flush Self-Hosted Trace generation */
-	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE))
-		__debug_save_trace(host_data_ptr(host_debug_state.trfcr_el1));
+
+	if (__trace_needs_switch())
+		__trace_switch_to_guest();
 }
 
 void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
@@ -96,18 +109,13 @@ void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 
 void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
 {
-	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE))
+	if (host_data_test_flag(HAS_SPE))
 		__debug_restore_spe(*host_data_ptr(host_debug_state.pmscr_el1));
-	if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE))
-		__debug_restore_trace(*host_data_ptr(host_debug_state.trfcr_el1));
+	if (__trace_needs_switch())
+		__trace_switch_to_host();
 }
 
 void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_switch_to_host_common(vcpu);
 }
-
-u64 __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 3d610fc51f4d..58f0cb2298cc 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -188,12 +188,12 @@ SYM_FUNC_END(__host_hvc)
 
 	/*
 	 * Test whether the SP has overflowed, without corrupting a GPR.
-	 * nVHE hypervisor stacks are aligned so that the PAGE_SHIFT bit
+	 * nVHE hypervisor stacks are aligned so that the NVHE_STACK_SHIFT bit
 	 * of SP should always be 1.
 	 */
 	add	sp, sp, x0			// sp' = sp + x0
 	sub	x0, sp, x0			// x0' = sp' - x0 = (sp + x0) - x0 = sp
-	tbz	x0, #PAGE_SHIFT, .L__hyp_sp_overflow\@
+	tbz	x0, #NVHE_STACK_SHIFT, .L__hyp_sp_overflow\@
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
 
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 6c90ef6736d6..6e12c070832f 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -91,11 +91,34 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 	*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
 }
 
+static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+	hyp_vcpu->vcpu.arch.debug_owner = host_vcpu->arch.debug_owner;
+
+	if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu))
+		hyp_vcpu->vcpu.arch.vcpu_debug_state = host_vcpu->arch.vcpu_debug_state;
+	else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu))
+		hyp_vcpu->vcpu.arch.external_debug_state = host_vcpu->arch.external_debug_state;
+}
+
+static void sync_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+	if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu))
+		host_vcpu->arch.vcpu_debug_state = hyp_vcpu->vcpu.arch.vcpu_debug_state;
+	else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu))
+		host_vcpu->arch.external_debug_state = hyp_vcpu->vcpu.arch.external_debug_state;
+}
+
 static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
 	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
 
 	fpsimd_sve_flush();
+	flush_debug_state(hyp_vcpu);
 
 	hyp_vcpu->vcpu.arch.ctxt	= host_vcpu->arch.ctxt;
 
@@ -103,8 +126,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	/* Limit guest vector length to the maximum supported by the host.  */
 	hyp_vcpu->vcpu.arch.sve_max_vl	= min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
 
-	hyp_vcpu->vcpu.arch.hw_mmu	= host_vcpu->arch.hw_mmu;
-
 	hyp_vcpu->vcpu.arch.mdcr_el2	= host_vcpu->arch.mdcr_el2;
 	hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
 	hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
@@ -112,8 +133,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 
 	hyp_vcpu->vcpu.arch.iflags	= host_vcpu->arch.iflags;
 
-	hyp_vcpu->vcpu.arch.debug_ptr	= kern_hyp_va(host_vcpu->arch.debug_ptr);
-
 	hyp_vcpu->vcpu.arch.vsesr_el2	= host_vcpu->arch.vsesr_el2;
 
 	hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3 = host_vcpu->arch.vgic_cpu.vgic_v3;
@@ -127,6 +146,7 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	unsigned int i;
 
 	fpsimd_sve_sync(&hyp_vcpu->vcpu);
+	sync_debug_state(hyp_vcpu);
 
 	host_vcpu->arch.ctxt		= hyp_vcpu->vcpu.arch.ctxt;
 
@@ -141,16 +161,46 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 		host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i];
 }
 
+static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(unsigned int, vcpu_idx, host_ctxt, 2);
+	DECLARE_REG(u64, hcr_el2, host_ctxt, 3);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vcpu = pkvm_load_hyp_vcpu(handle, vcpu_idx);
+	if (!hyp_vcpu)
+		return;
+
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) {
+		/* Propagate WFx trapping flags */
+		hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI);
+		hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI);
+	}
+}
+
+static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt)
+{
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (hyp_vcpu)
+		pkvm_put_hyp_vcpu(hyp_vcpu);
+}
+
 static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 1);
 	int ret;
 
-	host_vcpu = kern_hyp_va(host_vcpu);
-
 	if (unlikely(is_protected_kvm_enabled())) {
-		struct pkvm_hyp_vcpu *hyp_vcpu;
-		struct kvm *host_kvm;
+		struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
 
 		/*
 		 * KVM (and pKVM) doesn't support SME guests for now, and
@@ -163,9 +213,6 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 			goto out;
 		}
 
-		host_kvm = kern_hyp_va(host_vcpu->kvm);
-		hyp_vcpu = pkvm_load_hyp_vcpu(host_kvm->arch.pkvm.handle,
-					      host_vcpu->vcpu_idx);
 		if (!hyp_vcpu) {
 			ret = -EINVAL;
 			goto out;
@@ -176,12 +223,141 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
 		ret = __kvm_vcpu_run(&hyp_vcpu->vcpu);
 
 		sync_hyp_vcpu(hyp_vcpu);
-		pkvm_put_hyp_vcpu(hyp_vcpu);
 	} else {
 		/* The host is fully trusted, run its vCPU directly. */
-		ret = __kvm_vcpu_run(host_vcpu);
+		ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu));
 	}
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
+static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+	struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
+
+	return refill_memcache(&hyp_vcpu->vcpu.arch.pkvm_memcache,
+			       host_vcpu->arch.pkvm_memcache.nr_pages,
+			       &host_vcpu->arch.pkvm_memcache);
+}
+
+static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, pfn, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
+
+	ret = pkvm_refill_memcache(hyp_vcpu);
+	if (ret)
+		goto out;
+
+	ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot);
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
+static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		goto out;
+
+	ret = __pkvm_host_unshare_guest(gfn, hyp_vm);
+	put_pkvm_hyp_vm(hyp_vm);
+out:
+	cpu_reg(host_ctxt, 1) =  ret;
+}
+
+static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, gfn, host_ctxt, 1);
+	DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 2);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
+
+	ret = __pkvm_host_relax_perms_guest(gfn, hyp_vcpu, prot);
+out:
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
+static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		goto out;
+
+	ret = __pkvm_host_wrprotect_guest(gfn, hyp_vm);
+	put_pkvm_hyp_vm(hyp_vm);
+out:
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
+static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	DECLARE_REG(u64, gfn, host_ctxt, 2);
+	DECLARE_REG(bool, mkold, host_ctxt, 3);
+	struct pkvm_hyp_vm *hyp_vm;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		goto out;
+
+	ret = __pkvm_host_test_clear_young_guest(gfn, mkold, hyp_vm);
+	put_pkvm_hyp_vm(hyp_vm);
+out:
+	cpu_reg(host_ctxt, 1) = ret;
+}
+
+static void handle___pkvm_host_mkyoung_guest(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(u64, gfn, host_ctxt, 1);
+	struct pkvm_hyp_vcpu *hyp_vcpu;
+	int ret = -EINVAL;
+
+	if (!is_protected_kvm_enabled())
+		goto out;
+
+	hyp_vcpu = pkvm_get_loaded_hyp_vcpu();
+	if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		goto out;
 
+	ret = __pkvm_host_mkyoung_guest(gfn, hyp_vcpu);
 out:
 	cpu_reg(host_ctxt, 1) =  ret;
 }
@@ -233,6 +409,22 @@ static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
 	__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
 }
 
+static void handle___pkvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt)
+{
+	DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
+	struct pkvm_hyp_vm *hyp_vm;
+
+	if (!is_protected_kvm_enabled())
+		return;
+
+	hyp_vm = get_np_pkvm_hyp_vm(handle);
+	if (!hyp_vm)
+		return;
+
+	__kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu);
+	put_pkvm_hyp_vm(hyp_vm);
+}
+
 static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
@@ -264,11 +456,6 @@ static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt)
 	__vgic_v3_init_lrs();
 }
 
-static void handle___kvm_get_mdcr_el2(struct kvm_cpu_context *host_ctxt)
-{
-	cpu_reg(host_ctxt, 1) = __kvm_get_mdcr_el2();
-}
-
 static void handle___vgic_v3_save_vmcr_aprs(struct kvm_cpu_context *host_ctxt)
 {
 	DECLARE_REG(struct vgic_v3_cpu_if *, cpu_if, host_ctxt, 1);
@@ -384,7 +571,6 @@ typedef void (*hcall_t)(struct kvm_cpu_context *);
 
 static const hcall_t host_hcall[] = {
 	/* ___kvm_hyp_init */
-	HANDLE_FUNC(__kvm_get_mdcr_el2),
 	HANDLE_FUNC(__pkvm_init),
 	HANDLE_FUNC(__pkvm_create_private_mapping),
 	HANDLE_FUNC(__pkvm_cpu_set_vector),
@@ -395,6 +581,12 @@ static const hcall_t host_hcall[] = {
 
 	HANDLE_FUNC(__pkvm_host_share_hyp),
 	HANDLE_FUNC(__pkvm_host_unshare_hyp),
+	HANDLE_FUNC(__pkvm_host_share_guest),
+	HANDLE_FUNC(__pkvm_host_unshare_guest),
+	HANDLE_FUNC(__pkvm_host_relax_perms_guest),
+	HANDLE_FUNC(__pkvm_host_wrprotect_guest),
+	HANDLE_FUNC(__pkvm_host_test_clear_young_guest),
+	HANDLE_FUNC(__pkvm_host_mkyoung_guest),
 	HANDLE_FUNC(__kvm_adjust_pc),
 	HANDLE_FUNC(__kvm_vcpu_run),
 	HANDLE_FUNC(__kvm_flush_vm_context),
@@ -409,6 +601,9 @@ static const hcall_t host_hcall[] = {
 	HANDLE_FUNC(__pkvm_init_vm),
 	HANDLE_FUNC(__pkvm_init_vcpu),
 	HANDLE_FUNC(__pkvm_teardown_vm),
+	HANDLE_FUNC(__pkvm_vcpu_load),
+	HANDLE_FUNC(__pkvm_vcpu_put),
+	HANDLE_FUNC(__pkvm_tlb_flush_vmid),
 };
 
 static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index e75374d682f4..7ad7b133b81a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -201,8 +201,8 @@ static void *guest_s2_zalloc_page(void *mc)
 
 	memset(addr, 0, PAGE_SIZE);
 	p = hyp_virt_to_page(addr);
-	memset(p, 0, sizeof(*p));
 	p->refcount = 1;
+	p->order = 0;
 
 	return addr;
 }
@@ -268,6 +268,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
 
 void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
 {
+	struct hyp_page *page;
 	void *addr;
 
 	/* Dump all pgtable pages in the hyp_pool */
@@ -279,7 +280,9 @@ void reclaim_guest_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc)
 	/* Drain the hyp_pool into the memcache */
 	addr = hyp_alloc_pages(&vm->pool, 0);
 	while (addr) {
-		memset(hyp_virt_to_page(addr), 0, sizeof(struct hyp_page));
+		page = hyp_virt_to_page(addr);
+		page->refcount = 0;
+		page->order = 0;
 		push_hyp_memcache(mc, addr, hyp_virt_to_phys);
 		WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1));
 		addr = hyp_alloc_pages(&vm->pool, 0);
@@ -382,19 +385,28 @@ bool addr_is_memory(phys_addr_t phys)
 	return !!find_mem_range(phys, &range);
 }
 
-static bool addr_is_allowed_memory(phys_addr_t phys)
+static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
+{
+	return range->start <= addr && addr < range->end;
+}
+
+static int check_range_allowed_memory(u64 start, u64 end)
 {
 	struct memblock_region *reg;
 	struct kvm_mem_range range;
 
-	reg = find_mem_range(phys, &range);
+	/*
+	 * Callers can't check the state of a range that overlaps memory and
+	 * MMIO regions, so ensure [start, end[ is in the same kvm_mem_range.
+	 */
+	reg = find_mem_range(start, &range);
+	if (!is_in_mem_range(end - 1, &range))
+		return -EINVAL;
 
-	return reg && !(reg->flags & MEMBLOCK_NOMAP);
-}
+	if (!reg || reg->flags & MEMBLOCK_NOMAP)
+		return -EPERM;
 
-static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
-{
-	return range->start <= addr && addr < range->end;
+	return 0;
 }
 
 static bool range_is_memory(u64 start, u64 end)
@@ -454,8 +466,10 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 	if (kvm_pte_valid(pte))
 		return -EAGAIN;
 
-	if (pte)
+	if (pte) {
+		WARN_ON(addr_is_memory(addr) && hyp_phys_to_page(addr)->host_state != PKVM_NOPAGE);
 		return -EPERM;
+	}
 
 	do {
 		u64 granule = kvm_granule_size(level);
@@ -477,10 +491,33 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
 	return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
 }
 
+static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state)
+{
+	phys_addr_t end = addr + size;
+
+	for (; addr < end; addr += PAGE_SIZE)
+		hyp_phys_to_page(addr)->host_state = state;
+}
+
 int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
 {
-	return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
-			       addr, size, &host_s2_pool, owner_id);
+	int ret;
+
+	if (!addr_is_memory(addr))
+		return -EPERM;
+
+	ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt,
+			      addr, size, &host_s2_pool, owner_id);
+	if (ret)
+		return ret;
+
+	/* Don't forget to update the vmemmap tracking for the host */
+	if (owner_id == PKVM_ID_HOST)
+		__host_update_page_state(addr, size, PKVM_PAGE_OWNED);
+	else
+		__host_update_page_state(addr, size, PKVM_NOPAGE);
+
+	return 0;
 }
 
 static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
@@ -546,39 +583,6 @@ void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
 	BUG_ON(ret && ret != -EAGAIN);
 }
 
-struct pkvm_mem_transition {
-	u64				nr_pages;
-
-	struct {
-		enum pkvm_component_id	id;
-		/* Address in the initiator's address space */
-		u64			addr;
-
-		union {
-			struct {
-				/* Address in the completer's address space */
-				u64	completer_addr;
-			} host;
-			struct {
-				u64	completer_addr;
-			} hyp;
-		};
-	} initiator;
-
-	struct {
-		enum pkvm_component_id	id;
-	} completer;
-};
-
-struct pkvm_mem_share {
-	const struct pkvm_mem_transition	tx;
-	const enum kvm_pgtable_prot		completer_prot;
-};
-
-struct pkvm_mem_donation {
-	const struct pkvm_mem_transition	tx;
-};
-
 struct check_walk_data {
 	enum pkvm_page_state	desired;
 	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte, u64 addr);
@@ -604,115 +608,38 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
 	return kvm_pgtable_walk(pgt, addr, size, &walker);
 }
 
-static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr)
-{
-	if (!addr_is_allowed_memory(addr))
-		return PKVM_NOPAGE;
-
-	if (!kvm_pte_valid(pte) && pte)
-		return PKVM_NOPAGE;
-
-	return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
-}
-
 static int __host_check_page_state_range(u64 addr, u64 size,
 					 enum pkvm_page_state state)
 {
-	struct check_walk_data d = {
-		.desired	= state,
-		.get_page_state	= host_get_page_state,
-	};
+	u64 end = addr + size;
+	int ret;
+
+	ret = check_range_allowed_memory(addr, end);
+	if (ret)
+		return ret;
 
 	hyp_assert_lock_held(&host_mmu.lock);
-	return check_page_state_range(&host_mmu.pgt, addr, size, &d);
+	for (; addr < end; addr += PAGE_SIZE) {
+		if (hyp_phys_to_page(addr)->host_state != state)
+			return -EPERM;
+	}
+
+	return 0;
 }
 
 static int __host_set_page_state_range(u64 addr, u64 size,
 				       enum pkvm_page_state state)
 {
-	enum kvm_pgtable_prot prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, state);
-
-	return host_stage2_idmap_locked(addr, size, prot);
-}
-
-static int host_request_owned_transition(u64 *completer_addr,
-					 const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	u64 addr = tx->initiator.addr;
-
-	*completer_addr = tx->initiator.host.completer_addr;
-	return __host_check_page_state_range(addr, size, PKVM_PAGE_OWNED);
-}
-
-static int host_request_unshare(u64 *completer_addr,
-				const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	u64 addr = tx->initiator.addr;
-
-	*completer_addr = tx->initiator.host.completer_addr;
-	return __host_check_page_state_range(addr, size, PKVM_PAGE_SHARED_OWNED);
-}
-
-static int host_initiate_share(u64 *completer_addr,
-			       const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	u64 addr = tx->initiator.addr;
-
-	*completer_addr = tx->initiator.host.completer_addr;
-	return __host_set_page_state_range(addr, size, PKVM_PAGE_SHARED_OWNED);
-}
-
-static int host_initiate_unshare(u64 *completer_addr,
-				 const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	u64 addr = tx->initiator.addr;
-
-	*completer_addr = tx->initiator.host.completer_addr;
-	return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED);
-}
-
-static int host_initiate_donation(u64 *completer_addr,
-				  const struct pkvm_mem_transition *tx)
-{
-	u8 owner_id = tx->completer.id;
-	u64 size = tx->nr_pages * PAGE_SIZE;
-
-	*completer_addr = tx->initiator.host.completer_addr;
-	return host_stage2_set_owner_locked(tx->initiator.addr, size, owner_id);
-}
-
-static bool __host_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
-{
-	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
-		 tx->initiator.id != PKVM_ID_HYP);
-}
-
-static int __host_ack_transition(u64 addr, const struct pkvm_mem_transition *tx,
-				 enum pkvm_page_state state)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-
-	if (__host_ack_skip_pgtable_check(tx))
-		return 0;
-
-	return __host_check_page_state_range(addr, size, state);
-}
+	if (hyp_phys_to_page(addr)->host_state == PKVM_NOPAGE) {
+		int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
 
-static int host_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
-{
-	return __host_ack_transition(addr, tx, PKVM_NOPAGE);
-}
+		if (ret)
+			return ret;
+	}
 
-static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	u8 host_id = tx->completer.id;
+	__host_update_page_state(addr, size, state);
 
-	return host_stage2_set_owner_locked(addr, size, host_id);
+	return 0;
 }
 
 static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr)
@@ -735,573 +662,418 @@ static int __hyp_check_page_state_range(u64 addr, u64 size,
 	return check_page_state_range(&pkvm_pgtable, addr, size, &d);
 }
 
-static int hyp_request_donation(u64 *completer_addr,
-				const struct pkvm_mem_transition *tx)
+static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr)
 {
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	u64 addr = tx->initiator.addr;
+	if (!kvm_pte_valid(pte))
+		return PKVM_NOPAGE;
 
-	*completer_addr = tx->initiator.hyp.completer_addr;
-	return __hyp_check_page_state_range(addr, size, PKVM_PAGE_OWNED);
+	return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
 }
 
-static int hyp_initiate_donation(u64 *completer_addr,
-				 const struct pkvm_mem_transition *tx)
+static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr,
+					  u64 size, enum pkvm_page_state state)
 {
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	int ret;
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	struct check_walk_data d = {
+		.desired	= state,
+		.get_page_state	= guest_get_page_state,
+	};
 
-	*completer_addr = tx->initiator.hyp.completer_addr;
-	ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, tx->initiator.addr, size);
-	return (ret != size) ? -EFAULT : 0;
+	hyp_assert_lock_held(&vm->lock);
+	return check_page_state_range(&vm->pgt, addr, size, &d);
 }
 
-static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
+int __pkvm_host_share_hyp(u64 pfn)
 {
-	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
-		 tx->initiator.id != PKVM_ID_HOST);
-}
+	u64 phys = hyp_pfn_to_phys(pfn);
+	void *virt = __hyp_va(phys);
+	enum kvm_pgtable_prot prot;
+	u64 size = PAGE_SIZE;
+	int ret;
 
-static int hyp_ack_share(u64 addr, const struct pkvm_mem_transition *tx,
-			 enum kvm_pgtable_prot perms)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
+	host_lock_component();
+	hyp_lock_component();
 
-	if (perms != PAGE_HYP)
-		return -EPERM;
+	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
+	if (ret)
+		goto unlock;
+	if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
+		ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE);
+		if (ret)
+			goto unlock;
+	}
 
-	if (__hyp_ack_skip_pgtable_check(tx))
-		return 0;
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+	WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot));
+	WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED));
 
-	return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE);
+unlock:
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
 }
 
-static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx)
+int __pkvm_host_unshare_hyp(u64 pfn)
 {
-	u64 size = tx->nr_pages * PAGE_SIZE;
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 virt = (u64)__hyp_va(phys);
+	u64 size = PAGE_SIZE;
+	int ret;
 
-	if (tx->initiator.id == PKVM_ID_HOST && hyp_page_count((void *)addr))
-		return -EBUSY;
+	host_lock_component();
+	hyp_lock_component();
 
-	return __hyp_check_page_state_range(addr, size,
-					    PKVM_PAGE_SHARED_BORROWED);
-}
+	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
+	if (ret)
+		goto unlock;
+	ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_SHARED_BORROWED);
+	if (ret)
+		goto unlock;
+	if (hyp_page_count((void *)virt)) {
+		ret = -EBUSY;
+		goto unlock;
+	}
 
-static int hyp_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
+	WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size);
+	WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_OWNED));
 
-	if (__hyp_ack_skip_pgtable_check(tx))
-		return 0;
+unlock:
+	hyp_unlock_component();
+	host_unlock_component();
 
-	return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE);
+	return ret;
 }
 
-static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx,
-			      enum kvm_pgtable_prot perms)
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
 {
-	void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE);
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 size = PAGE_SIZE * nr_pages;
+	void *virt = __hyp_va(phys);
 	enum kvm_pgtable_prot prot;
+	int ret;
 
-	prot = pkvm_mkstate(perms, PKVM_PAGE_SHARED_BORROWED);
-	return pkvm_create_mappings_locked(start, end, prot);
-}
+	host_lock_component();
+	hyp_lock_component();
 
-static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx)
-{
-	u64 size = tx->nr_pages * PAGE_SIZE;
-	int ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, addr, size);
+	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
+	if (ret)
+		goto unlock;
+	if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
+		ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE);
+		if (ret)
+			goto unlock;
+	}
 
-	return (ret != size) ? -EFAULT : 0;
-}
+	prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED);
+	WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot));
+	WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP));
 
-static int hyp_complete_donation(u64 addr,
-				 const struct pkvm_mem_transition *tx)
-{
-	void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE);
-	enum kvm_pgtable_prot prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED);
+unlock:
+	hyp_unlock_component();
+	host_unlock_component();
 
-	return pkvm_create_mappings_locked(start, end, prot);
+	return ret;
 }
 
-static int check_share(struct pkvm_mem_share *share)
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
 {
-	const struct pkvm_mem_transition *tx = &share->tx;
-	u64 completer_addr;
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 size = PAGE_SIZE * nr_pages;
+	u64 virt = (u64)__hyp_va(phys);
 	int ret;
 
-	switch (tx->initiator.id) {
-	case PKVM_ID_HOST:
-		ret = host_request_owned_transition(&completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	host_lock_component();
+	hyp_lock_component();
 
+	ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_OWNED);
 	if (ret)
-		return ret;
-
-	switch (tx->completer.id) {
-	case PKVM_ID_HYP:
-		ret = hyp_ack_share(completer_addr, tx, share->completer_prot);
-		break;
-	case PKVM_ID_FFA:
-		/*
-		 * We only check the host; the secure side will check the other
-		 * end when we forward the FFA call.
-		 */
-		ret = 0;
-		break;
-	default:
-		ret = -EINVAL;
+		goto unlock;
+	if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
+		ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE);
+		if (ret)
+			goto unlock;
 	}
 
+	WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size);
+	WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST));
+
+unlock:
+	hyp_unlock_component();
+	host_unlock_component();
+
 	return ret;
 }
 
-static int __do_share(struct pkvm_mem_share *share)
+int hyp_pin_shared_mem(void *from, void *to)
 {
-	const struct pkvm_mem_transition *tx = &share->tx;
-	u64 completer_addr;
+	u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
+	u64 end = PAGE_ALIGN((u64)to);
+	u64 size = end - start;
 	int ret;
 
-	switch (tx->initiator.id) {
-	case PKVM_ID_HOST:
-		ret = host_initiate_share(&completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	host_lock_component();
+	hyp_lock_component();
 
+	ret = __host_check_page_state_range(__hyp_pa(start), size,
+					    PKVM_PAGE_SHARED_OWNED);
 	if (ret)
-		return ret;
-
-	switch (tx->completer.id) {
-	case PKVM_ID_HYP:
-		ret = hyp_complete_share(completer_addr, tx, share->completer_prot);
-		break;
-	case PKVM_ID_FFA:
-		/*
-		 * We're not responsible for any secure page-tables, so there's
-		 * nothing to do here.
-		 */
-		ret = 0;
-		break;
-	default:
-		ret = -EINVAL;
-	}
+		goto unlock;
 
-	return ret;
-}
+	ret = __hyp_check_page_state_range(start, size,
+					   PKVM_PAGE_SHARED_BORROWED);
+	if (ret)
+		goto unlock;
 
-/*
- * do_share():
- *
- * The page owner grants access to another component with a given set
- * of permissions.
- *
- * Initiator: OWNED	=> SHARED_OWNED
- * Completer: NOPAGE	=> SHARED_BORROWED
- */
-static int do_share(struct pkvm_mem_share *share)
-{
-	int ret;
+	for (cur = start; cur < end; cur += PAGE_SIZE)
+		hyp_page_ref_inc(hyp_virt_to_page(cur));
 
-	ret = check_share(share);
-	if (ret)
-		return ret;
+unlock:
+	hyp_unlock_component();
+	host_unlock_component();
 
-	return WARN_ON(__do_share(share));
+	return ret;
 }
 
-static int check_unshare(struct pkvm_mem_share *share)
+void hyp_unpin_shared_mem(void *from, void *to)
 {
-	const struct pkvm_mem_transition *tx = &share->tx;
-	u64 completer_addr;
-	int ret;
-
-	switch (tx->initiator.id) {
-	case PKVM_ID_HOST:
-		ret = host_request_unshare(&completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
+	u64 end = PAGE_ALIGN((u64)to);
 
-	if (ret)
-		return ret;
+	host_lock_component();
+	hyp_lock_component();
 
-	switch (tx->completer.id) {
-	case PKVM_ID_HYP:
-		ret = hyp_ack_unshare(completer_addr, tx);
-		break;
-	case PKVM_ID_FFA:
-		/* See check_share() */
-		ret = 0;
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	for (cur = start; cur < end; cur += PAGE_SIZE)
+		hyp_page_ref_dec(hyp_virt_to_page(cur));
 
-	return ret;
+	hyp_unlock_component();
+	host_unlock_component();
 }
 
-static int __do_unshare(struct pkvm_mem_share *share)
+int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages)
 {
-	const struct pkvm_mem_transition *tx = &share->tx;
-	u64 completer_addr;
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 size = PAGE_SIZE * nr_pages;
 	int ret;
 
-	switch (tx->initiator.id) {
-	case PKVM_ID_HOST:
-		ret = host_initiate_unshare(&completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	if (ret)
-		return ret;
-
-	switch (tx->completer.id) {
-	case PKVM_ID_HYP:
-		ret = hyp_complete_unshare(completer_addr, tx);
-		break;
-	case PKVM_ID_FFA:
-		/* See __do_share() */
-		ret = 0;
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	host_lock_component();
+	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
+	if (!ret)
+		ret = __host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
+	host_unlock_component();
 
 	return ret;
 }
 
-/*
- * do_unshare():
- *
- * The page owner revokes access from another component for a range of
- * pages which were previously shared using do_share().
- *
- * Initiator: SHARED_OWNED	=> OWNED
- * Completer: SHARED_BORROWED	=> NOPAGE
- */
-static int do_unshare(struct pkvm_mem_share *share)
+int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
 {
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 size = PAGE_SIZE * nr_pages;
 	int ret;
 
-	ret = check_unshare(share);
-	if (ret)
-		return ret;
+	host_lock_component();
+	ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
+	if (!ret)
+		ret = __host_set_page_state_range(phys, size, PKVM_PAGE_OWNED);
+	host_unlock_component();
 
-	return WARN_ON(__do_unshare(share));
+	return ret;
 }
 
-static int check_donation(struct pkvm_mem_donation *donation)
+int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
+			    enum kvm_pgtable_prot prot)
 {
-	const struct pkvm_mem_transition *tx = &donation->tx;
-	u64 completer_addr;
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 phys = hyp_pfn_to_phys(pfn);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	struct hyp_page *page;
 	int ret;
 
-	switch (tx->initiator.id) {
-	case PKVM_ID_HOST:
-		ret = host_request_owned_transition(&completer_addr, tx);
-		break;
-	case PKVM_ID_HYP:
-		ret = hyp_request_donation(&completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
+	if (prot & ~KVM_PGTABLE_PROT_RWX)
+		return -EINVAL;
 
+	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
 	if (ret)
 		return ret;
 
-	switch (tx->completer.id) {
-	case PKVM_ID_HOST:
-		ret = host_ack_donation(completer_addr, tx);
-		break;
-	case PKVM_ID_HYP:
-		ret = hyp_ack_donation(completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
+	host_lock_component();
+	guest_lock_component(vm);
 
-static int __do_donate(struct pkvm_mem_donation *donation)
-{
-	const struct pkvm_mem_transition *tx = &donation->tx;
-	u64 completer_addr;
-	int ret;
+	ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE);
+	if (ret)
+		goto unlock;
 
-	switch (tx->initiator.id) {
-	case PKVM_ID_HOST:
-		ret = host_initiate_donation(&completer_addr, tx);
-		break;
-	case PKVM_ID_HYP:
-		ret = hyp_initiate_donation(&completer_addr, tx);
+	page = hyp_phys_to_page(phys);
+	switch (page->host_state) {
+	case PKVM_PAGE_OWNED:
+		WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED));
 		break;
+	case PKVM_PAGE_SHARED_OWNED:
+		if (page->host_share_guest_count)
+			break;
+		/* Only host to np-guest multi-sharing is tolerated */
+		WARN_ON(1);
+		fallthrough;
 	default:
-		ret = -EINVAL;
+		ret = -EPERM;
+		goto unlock;
 	}
 
-	if (ret)
-		return ret;
+	WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
+				       pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED),
+				       &vcpu->vcpu.arch.pkvm_memcache, 0));
+	page->host_share_guest_count++;
 
-	switch (tx->completer.id) {
-	case PKVM_ID_HOST:
-		ret = host_complete_donation(completer_addr, tx);
-		break;
-	case PKVM_ID_HYP:
-		ret = hyp_complete_donation(completer_addr, tx);
-		break;
-	default:
-		ret = -EINVAL;
-	}
+unlock:
+	guest_unlock_component(vm);
+	host_unlock_component();
 
 	return ret;
 }
 
-/*
- * do_donate():
- *
- * The page owner transfers ownership to another component, losing access
- * as a consequence.
- *
- * Initiator: OWNED	=> NOPAGE
- * Completer: NOPAGE	=> OWNED
- */
-static int do_donate(struct pkvm_mem_donation *donation)
+static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
 {
+	enum pkvm_page_state state;
+	struct hyp_page *page;
+	kvm_pte_t pte;
+	u64 phys;
+	s8 level;
 	int ret;
 
-	ret = check_donation(donation);
+	ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
 	if (ret)
 		return ret;
+	if (level != KVM_PGTABLE_LAST_LEVEL)
+		return -E2BIG;
+	if (!kvm_pte_valid(pte))
+		return -ENOENT;
 
-	return WARN_ON(__do_donate(donation));
-}
-
-int __pkvm_host_share_hyp(u64 pfn)
-{
-	int ret;
-	u64 host_addr = hyp_pfn_to_phys(pfn);
-	u64 hyp_addr = (u64)__hyp_va(host_addr);
-	struct pkvm_mem_share share = {
-		.tx	= {
-			.nr_pages	= 1,
-			.initiator	= {
-				.id	= PKVM_ID_HOST,
-				.addr	= host_addr,
-				.host	= {
-					.completer_addr = hyp_addr,
-				},
-			},
-			.completer	= {
-				.id	= PKVM_ID_HYP,
-			},
-		},
-		.completer_prot	= PAGE_HYP,
-	};
+	state = guest_get_page_state(pte, ipa);
+	if (state != PKVM_PAGE_SHARED_BORROWED)
+		return -EPERM;
 
-	host_lock_component();
-	hyp_lock_component();
+	phys = kvm_pte_to_phys(pte);
+	ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
+	if (WARN_ON(ret))
+		return ret;
 
-	ret = do_share(&share);
+	page = hyp_phys_to_page(phys);
+	if (page->host_state != PKVM_PAGE_SHARED_OWNED)
+		return -EPERM;
+	if (WARN_ON(!page->host_share_guest_count))
+		return -EINVAL;
 
-	hyp_unlock_component();
-	host_unlock_component();
+	*__phys = phys;
 
-	return ret;
+	return 0;
 }
 
-int __pkvm_host_unshare_hyp(u64 pfn)
+int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
 {
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	struct hyp_page *page;
+	u64 phys;
 	int ret;
-	u64 host_addr = hyp_pfn_to_phys(pfn);
-	u64 hyp_addr = (u64)__hyp_va(host_addr);
-	struct pkvm_mem_share share = {
-		.tx	= {
-			.nr_pages	= 1,
-			.initiator	= {
-				.id	= PKVM_ID_HOST,
-				.addr	= host_addr,
-				.host	= {
-					.completer_addr = hyp_addr,
-				},
-			},
-			.completer	= {
-				.id	= PKVM_ID_HYP,
-			},
-		},
-		.completer_prot	= PAGE_HYP,
-	};
 
 	host_lock_component();
-	hyp_lock_component();
+	guest_lock_component(vm);
+
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (ret)
+		goto unlock;
+
+	ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE);
+	if (ret)
+		goto unlock;
 
-	ret = do_unshare(&share);
+	page = hyp_phys_to_page(phys);
+	page->host_share_guest_count--;
+	if (!page->host_share_guest_count)
+		WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED));
 
-	hyp_unlock_component();
+unlock:
+	guest_unlock_component(vm);
 	host_unlock_component();
 
 	return ret;
 }
 
-int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
+int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
 {
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
 	int ret;
-	u64 host_addr = hyp_pfn_to_phys(pfn);
-	u64 hyp_addr = (u64)__hyp_va(host_addr);
-	struct pkvm_mem_donation donation = {
-		.tx	= {
-			.nr_pages	= nr_pages,
-			.initiator	= {
-				.id	= PKVM_ID_HOST,
-				.addr	= host_addr,
-				.host	= {
-					.completer_addr = hyp_addr,
-				},
-			},
-			.completer	= {
-				.id	= PKVM_ID_HYP,
-			},
-		},
-	};
+
+	if (prot & ~KVM_PGTABLE_PROT_RWX)
+		return -EINVAL;
 
 	host_lock_component();
-	hyp_lock_component();
+	guest_lock_component(vm);
 
-	ret = do_donate(&donation);
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
 
-	hyp_unlock_component();
+	guest_unlock_component(vm);
 	host_unlock_component();
 
 	return ret;
 }
 
-int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
+int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
 {
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
 	int ret;
-	u64 host_addr = hyp_pfn_to_phys(pfn);
-	u64 hyp_addr = (u64)__hyp_va(host_addr);
-	struct pkvm_mem_donation donation = {
-		.tx	= {
-			.nr_pages	= nr_pages,
-			.initiator	= {
-				.id	= PKVM_ID_HYP,
-				.addr	= hyp_addr,
-				.hyp	= {
-					.completer_addr = host_addr,
-				},
-			},
-			.completer	= {
-				.id	= PKVM_ID_HOST,
-			},
-		},
-	};
 
 	host_lock_component();
-	hyp_lock_component();
+	guest_lock_component(vm);
 
-	ret = do_donate(&donation);
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
 
-	hyp_unlock_component();
+	guest_unlock_component(vm);
 	host_unlock_component();
 
 	return ret;
 }
 
-int hyp_pin_shared_mem(void *from, void *to)
+int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
 {
-	u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
-	u64 end = PAGE_ALIGN((u64)to);
-	u64 size = end - start;
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
 	int ret;
 
 	host_lock_component();
-	hyp_lock_component();
-
-	ret = __host_check_page_state_range(__hyp_pa(start), size,
-					    PKVM_PAGE_SHARED_OWNED);
-	if (ret)
-		goto unlock;
-
-	ret = __hyp_check_page_state_range(start, size,
-					   PKVM_PAGE_SHARED_BORROWED);
-	if (ret)
-		goto unlock;
+	guest_lock_component(vm);
 
-	for (cur = start; cur < end; cur += PAGE_SIZE)
-		hyp_page_ref_inc(hyp_virt_to_page(cur));
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
 
-unlock:
-	hyp_unlock_component();
+	guest_unlock_component(vm);
 	host_unlock_component();
 
 	return ret;
 }
 
-void hyp_unpin_shared_mem(void *from, void *to)
-{
-	u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
-	u64 end = PAGE_ALIGN((u64)to);
-
-	host_lock_component();
-	hyp_lock_component();
-
-	for (cur = start; cur < end; cur += PAGE_SIZE)
-		hyp_page_ref_dec(hyp_virt_to_page(cur));
-
-	hyp_unlock_component();
-	host_unlock_component();
-}
-
-int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages)
+int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
 {
+	struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+	u64 ipa = hyp_pfn_to_phys(gfn);
+	u64 phys;
 	int ret;
-	struct pkvm_mem_share share = {
-		.tx	= {
-			.nr_pages	= nr_pages,
-			.initiator	= {
-				.id	= PKVM_ID_HOST,
-				.addr	= hyp_pfn_to_phys(pfn),
-			},
-			.completer	= {
-				.id	= PKVM_ID_FFA,
-			},
-		},
-	};
 
 	host_lock_component();
-	ret = do_share(&share);
-	host_unlock_component();
+	guest_lock_component(vm);
 
-	return ret;
-}
+	ret = __check_host_shared_guest(vm, &phys, ipa);
+	if (!ret)
+		kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
 
-int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
-{
-	int ret;
-	struct pkvm_mem_share share = {
-		.tx	= {
-			.nr_pages	= nr_pages,
-			.initiator	= {
-				.id	= PKVM_ID_HOST,
-				.addr	= hyp_pfn_to_phys(pfn),
-			},
-			.completer	= {
-				.id	= PKVM_ID_FFA,
-			},
-		},
-	};
-
-	host_lock_component();
-	ret = do_unshare(&share);
+	guest_unlock_component(vm);
 	host_unlock_component();
 
 	return ret;
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 8850b591d775..f41c7440b34b 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -360,10 +360,10 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
 
 	prev_base = __io_map_base;
 	/*
-	 * Efficient stack verification using the PAGE_SHIFT bit implies
+	 * Efficient stack verification using the NVHE_STACK_SHIFT bit implies
 	 * an alignment of our allocation on the order of the size.
 	 */
-	size = PAGE_SIZE * 2;
+	size = NVHE_STACK_SIZE * 2;
 	addr = ALIGN(__io_map_base, size);
 
 	ret = __pkvm_alloc_private_va_range(addr, size);
@@ -373,12 +373,12 @@ int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr)
 		 * at the higher address and leave the lower guard page
 		 * unbacked.
 		 *
-		 * Any valid stack address now has the PAGE_SHIFT bit as 1
+		 * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1
 		 * and addresses corresponding to the guard page have the
-		 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
+		 * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection.
 		 */
-		ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + PAGE_SIZE,
-					  PAGE_SIZE, phys, PAGE_HYP);
+		ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + NVHE_STACK_SIZE,
+					  NVHE_STACK_SIZE, phys, PAGE_HYP);
 		if (ret)
 			__io_map_base = prev_base;
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index e691290d3765..a1eb27a1a747 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -32,7 +32,7 @@ u64 __hyp_vmemmap;
  */
 static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
 					     struct hyp_page *p,
-					     unsigned short order)
+					     u8 order)
 {
 	phys_addr_t addr = hyp_page_to_phys(p);
 
@@ -51,7 +51,7 @@ static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
 /* Find a buddy page currently available for allocation */
 static struct hyp_page *__find_buddy_avail(struct hyp_pool *pool,
 					   struct hyp_page *p,
-					   unsigned short order)
+					   u8 order)
 {
 	struct hyp_page *buddy = __find_buddy_nocheck(pool, p, order);
 
@@ -94,7 +94,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 			      struct hyp_page *p)
 {
 	phys_addr_t phys = hyp_page_to_phys(p);
-	unsigned short order = p->order;
+	u8 order = p->order;
 	struct hyp_page *buddy;
 
 	memset(hyp_page_to_virt(p), 0, PAGE_SIZE << p->order);
@@ -129,7 +129,7 @@ insert:
 
 static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool,
 					   struct hyp_page *p,
-					   unsigned short order)
+					   u8 order)
 {
 	struct hyp_page *buddy;
 
@@ -183,7 +183,7 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
 
 void hyp_split_page(struct hyp_page *p)
 {
-	unsigned short order = p->order;
+	u8 order = p->order;
 	unsigned int i;
 
 	p->order = 0;
@@ -195,10 +195,10 @@ void hyp_split_page(struct hyp_page *p)
 	}
 }
 
-void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
+void *hyp_alloc_pages(struct hyp_pool *pool, u8 order)
 {
-	unsigned short i = order;
 	struct hyp_page *p;
+	u8 i = order;
 
 	hyp_spin_lock(&pool->lock);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 73e319891327..3927fe52a3dd 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -9,7 +9,6 @@
 
 #include <asm/kvm_emulate.h>
 
-#include <nvhe/fixed_config.h>
 #include <nvhe/mem_protect.h>
 #include <nvhe/memory.h>
 #include <nvhe/pkvm.h>
@@ -24,232 +23,160 @@ unsigned int kvm_arm_vmid_bits;
 unsigned int kvm_host_sve_max_vl;
 
 /*
- * Set trap register values based on features in ID_AA64PFR0.
+ * The currently loaded hyp vCPU for each physical CPU. Used only when
+ * protected KVM is enabled, but for both protected and non-protected VMs.
  */
-static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
-{
-	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR0_EL1);
-	u64 hcr_set = HCR_RW;
-	u64 hcr_clear = 0;
-	u64 cptr_set = 0;
-	u64 cptr_clear = 0;
-
-	/* Protected KVM does not support AArch32 guests. */
-	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0),
-		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_EL1_EL0_IMP);
-	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL1),
-		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_EL1_EL1_IMP);
+static DEFINE_PER_CPU(struct pkvm_hyp_vcpu *, loaded_hyp_vcpu);
 
-	/*
-	 * Linux guests assume support for floating-point and Advanced SIMD. Do
-	 * not change the trapping behavior for these from the KVM default.
-	 */
-	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_FP),
-				PVM_ID_AA64PFR0_ALLOW));
-	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD),
-				PVM_ID_AA64PFR0_ALLOW));
+static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 
 	if (has_hvhe())
-		hcr_set |= HCR_E2H;
+		vcpu->arch.hcr_el2 |= HCR_E2H;
 
-	/* Trap RAS unless all current versions are supported */
-	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_RAS), feature_ids) <
-	    ID_AA64PFR0_EL1_RAS_V1P1) {
-		hcr_set |= HCR_TERR | HCR_TEA;
-		hcr_clear |= HCR_FIEN;
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) {
+		/* route synchronous external abort exceptions to EL2 */
+		vcpu->arch.hcr_el2 |= HCR_TEA;
+		/* trap error record accesses */
+		vcpu->arch.hcr_el2 |= HCR_TERR;
 	}
 
-	/* Trap AMU */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AMU), feature_ids)) {
-		hcr_clear |= HCR_AMVOFFEN;
-		cptr_set |= CPTR_EL2_TAM;
-	}
+	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
+		vcpu->arch.hcr_el2 |= HCR_FWB;
 
-	/* Trap SVE */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
-		if (has_hvhe())
-			cptr_clear |= CPACR_EL1_ZEN;
-		else
-			cptr_set |= CPTR_EL2_TZ;
-	}
+	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
+	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
+		vcpu->arch.hcr_el2 |= HCR_TID4;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TID2;
 
-	vcpu->arch.hcr_el2 |= hcr_set;
-	vcpu->arch.hcr_el2 &= ~hcr_clear;
-	vcpu->arch.cptr_el2 |= cptr_set;
-	vcpu->arch.cptr_el2 &= ~cptr_clear;
+	if (vcpu_has_ptrauth(vcpu))
+		vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
+
+	if (kvm_has_mte(vcpu->kvm))
+		vcpu->arch.hcr_el2 |= HCR_ATA;
 }
 
-/*
- * Set trap register values based on features in ID_AA64PFR1.
- */
-static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu)
+static void pvm_init_traps_hcr(struct kvm_vcpu *vcpu)
 {
-	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR1_EL1);
-	u64 hcr_set = 0;
-	u64 hcr_clear = 0;
+	struct kvm *kvm = vcpu->kvm;
+	u64 val = vcpu->arch.hcr_el2;
 
-	/* Memory Tagging: Trap and Treat as Untagged if not supported. */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), feature_ids)) {
-		hcr_set |= HCR_TID5;
-		hcr_clear |= HCR_DCT | HCR_ATA;
+	/* No support for AArch32. */
+	val |= HCR_RW;
+
+	/*
+	 * Always trap:
+	 * - Feature id registers: to control features exposed to guests
+	 * - Implementation-defined features
+	 */
+	val |= HCR_TACR | HCR_TIDCP | HCR_TID3 | HCR_TID1;
+
+	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) {
+		val |= HCR_TERR | HCR_TEA;
+		val &= ~(HCR_FIEN);
 	}
 
-	vcpu->arch.hcr_el2 |= hcr_set;
-	vcpu->arch.hcr_el2 &= ~hcr_clear;
-}
+	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP))
+		val &= ~(HCR_AMVOFFEN);
 
-/*
- * Set trap register values based on features in ID_AA64DFR0.
- */
-static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
-{
-	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64DFR0_EL1);
-	u64 mdcr_set = 0;
-	u64 mdcr_clear = 0;
-	u64 cptr_set = 0;
-
-	/* Trap/constrain PMU */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), feature_ids)) {
-		mdcr_set |= MDCR_EL2_TPM | MDCR_EL2_TPMCR;
-		mdcr_clear |= MDCR_EL2_HPME | MDCR_EL2_MTPME |
-			      MDCR_EL2_HPMN_MASK;
+	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, IMP)) {
+		val |= HCR_TID5;
+		val &= ~(HCR_DCT | HCR_ATA);
 	}
 
-	/* Trap Debug */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), feature_ids))
-		mdcr_set |= MDCR_EL2_TDRA | MDCR_EL2_TDA | MDCR_EL2_TDE;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
+		val |= HCR_TLOR;
 
-	/* Trap OS Double Lock */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DoubleLock), feature_ids))
-		mdcr_set |= MDCR_EL2_TDOSA;
+	vcpu->arch.hcr_el2 = val;
+}
+
+static void pvm_init_traps_mdcr(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 val = vcpu->arch.mdcr_el2;
 
-	/* Trap SPE */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer), feature_ids)) {
-		mdcr_set |= MDCR_EL2_TPMS;
-		mdcr_clear |= MDCR_EL2_E2PB_MASK;
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) {
+		val |= MDCR_EL2_TPM | MDCR_EL2_TPMCR;
+		val &= ~(MDCR_EL2_HPME | MDCR_EL2_MTPME | MDCR_EL2_HPMN_MASK);
 	}
 
-	/* Trap Trace Filter */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceFilt), feature_ids))
-		mdcr_set |= MDCR_EL2_TTRF;
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, IMP))
+		val |= MDCR_EL2_TDRA | MDCR_EL2_TDA;
 
-	/* Trap Trace */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceVer), feature_ids)) {
-		if (has_hvhe())
-			cptr_set |= CPACR_EL1_TTA;
-		else
-			cptr_set |= CPTR_EL2_TTA;
-	}
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP))
+		val |= MDCR_EL2_TDOSA;
 
-	/* Trap External Trace */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids))
-		mdcr_clear |= MDCR_EL2_E2TB_MASK;
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) {
+		val |= MDCR_EL2_TPMS;
+		val &= ~MDCR_EL2_E2PB_MASK;
+	}
 
-	vcpu->arch.mdcr_el2 |= mdcr_set;
-	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
-	vcpu->arch.cptr_el2 |= cptr_set;
-}
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP))
+		val |= MDCR_EL2_TTRF;
 
-/*
- * Set trap register values based on features in ID_AA64MMFR0.
- */
-static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu)
-{
-	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR0_EL1);
-	u64 mdcr_set = 0;
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, ExtTrcBuff, IMP))
+		val |= MDCR_EL2_E2TB_MASK;
 
 	/* Trap Debug Communications Channel registers */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_FGT), feature_ids))
-		mdcr_set |= MDCR_EL2_TDCC;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, FGT, IMP))
+		val |= MDCR_EL2_TDCC;
 
-	vcpu->arch.mdcr_el2 |= mdcr_set;
+	vcpu->arch.mdcr_el2 = val;
 }
 
 /*
- * Set trap register values based on features in ID_AA64MMFR1.
+ * Check that cpu features that are neither trapped nor supported are not
+ * enabled for protected VMs.
  */
-static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu)
+static int pkvm_check_pvm_cpu_features(struct kvm_vcpu *vcpu)
 {
-	const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR1_EL1);
-	u64 hcr_set = 0;
-
-	/* Trap LOR */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_LO), feature_ids))
-		hcr_set |= HCR_TLOR;
+	struct kvm *kvm = vcpu->kvm;
 
-	vcpu->arch.hcr_el2 |= hcr_set;
-}
-
-/*
- * Set baseline trap register values.
- */
-static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
-{
-	const u64 hcr_trap_feat_regs = HCR_TID3;
-	const u64 hcr_trap_impdef = HCR_TACR | HCR_TIDCP | HCR_TID1;
+	/* Protected KVM does not support AArch32 guests. */
+	if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL0, AARCH32) ||
+	    kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL1, AARCH32))
+		return -EINVAL;
 
 	/*
-	 * Always trap:
-	 * - Feature id registers: to control features exposed to guests
-	 * - Implementation-defined features
+	 * Linux guests assume support for floating-point and Advanced SIMD. Do
+	 * not change the trapping behavior for these from the KVM default.
 	 */
-	vcpu->arch.hcr_el2 |= hcr_trap_feat_regs | hcr_trap_impdef;
-
-	/* Clear res0 and set res1 bits to trap potential new features. */
-	vcpu->arch.hcr_el2 &= ~(HCR_RES0);
-	vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0);
-	if (!has_hvhe()) {
-		vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1;
-		vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0);
-	}
-}
-
-static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
-
-	if (has_hvhe())
-		vcpu->arch.hcr_el2 |= HCR_E2H;
-
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) {
-		/* route synchronous external abort exceptions to EL2 */
-		vcpu->arch.hcr_el2 |= HCR_TEA;
-		/* trap error record accesses */
-		vcpu->arch.hcr_el2 |= HCR_TERR;
-	}
-
-	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
-		vcpu->arch.hcr_el2 |= HCR_FWB;
+	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, FP, IMP) ||
+	    !kvm_has_feat(kvm, ID_AA64PFR0_EL1, AdvSIMD, IMP))
+		return -EINVAL;
 
-	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
-	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
-		vcpu->arch.hcr_el2 |= HCR_TID4;
-	else
-		vcpu->arch.hcr_el2 |= HCR_TID2;
+	/* No SME support in KVM right now. Check to catch if it changes. */
+	if (kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP))
+		return -EINVAL;
 
-	if (vcpu_has_ptrauth(vcpu))
-		vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK);
+	return 0;
 }
 
 /*
  * Initialize trap register values in protected mode.
  */
-static void pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
+static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu)
 {
-	vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu);
+	struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
+	int ret;
+
 	vcpu->arch.mdcr_el2 = 0;
 
 	pkvm_vcpu_reset_hcr(vcpu);
 
-	if ((!vcpu_is_protected(vcpu)))
-		return;
+	if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu)))
+		return 0;
+
+	ret = pkvm_check_pvm_cpu_features(vcpu);
+	if (ret)
+		return ret;
+
+	pvm_init_traps_hcr(vcpu);
+	pvm_init_traps_mdcr(vcpu);
 
-	pvm_init_trap_regs(vcpu);
-	pvm_init_traps_aa64pfr0(vcpu);
-	pvm_init_traps_aa64pfr1(vcpu);
-	pvm_init_traps_aa64dfr0(vcpu);
-	pvm_init_traps_aa64mmfr0(vcpu);
-	pvm_init_traps_aa64mmfr1(vcpu);
+	return 0;
 }
 
 /*
@@ -270,10 +197,10 @@ static pkvm_handle_t idx_to_vm_handle(unsigned int idx)
 
 /*
  * Spinlock for protecting state related to the VM table. Protects writes
- * to 'vm_table' and 'nr_table_entries' as well as reads and writes to
- * 'last_hyp_vcpu_lookup'.
+ * to 'vm_table', 'nr_table_entries', and other per-vm state on initialization.
+ * Also protects reads and writes to 'last_hyp_vcpu_lookup'.
  */
-static DEFINE_HYP_SPINLOCK(vm_table_lock);
+DEFINE_HYP_SPINLOCK(vm_table_lock);
 
 /*
  * The table of VM entries for protected VMs in hyp.
@@ -306,15 +233,30 @@ struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle,
 	struct pkvm_hyp_vcpu *hyp_vcpu = NULL;
 	struct pkvm_hyp_vm *hyp_vm;
 
+	/* Cannot load a new vcpu without putting the old one first. */
+	if (__this_cpu_read(loaded_hyp_vcpu))
+		return NULL;
+
 	hyp_spin_lock(&vm_table_lock);
 	hyp_vm = get_vm_by_handle(handle);
 	if (!hyp_vm || hyp_vm->nr_vcpus <= vcpu_idx)
 		goto unlock;
 
 	hyp_vcpu = hyp_vm->vcpus[vcpu_idx];
+
+	/* Ensure vcpu isn't loaded on more than one cpu simultaneously. */
+	if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) {
+		hyp_vcpu = NULL;
+		goto unlock;
+	}
+
+	hyp_vcpu->loaded_hyp_vcpu = this_cpu_ptr(&loaded_hyp_vcpu);
 	hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
 unlock:
 	hyp_spin_unlock(&vm_table_lock);
+
+	if (hyp_vcpu)
+		__this_cpu_write(loaded_hyp_vcpu, hyp_vcpu);
 	return hyp_vcpu;
 }
 
@@ -323,17 +265,63 @@ void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
 	struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu);
 
 	hyp_spin_lock(&vm_table_lock);
+	hyp_vcpu->loaded_hyp_vcpu = NULL;
+	__this_cpu_write(loaded_hyp_vcpu, NULL);
+	hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
+	hyp_spin_unlock(&vm_table_lock);
+}
+
+struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void)
+{
+	return __this_cpu_read(loaded_hyp_vcpu);
+
+}
+
+struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle)
+{
+	struct pkvm_hyp_vm *hyp_vm;
+
+	hyp_spin_lock(&vm_table_lock);
+	hyp_vm = get_vm_by_handle(handle);
+	if (hyp_vm)
+		hyp_page_ref_inc(hyp_virt_to_page(hyp_vm));
+	hyp_spin_unlock(&vm_table_lock);
+
+	return hyp_vm;
+}
+
+void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm)
+{
+	hyp_spin_lock(&vm_table_lock);
 	hyp_page_ref_dec(hyp_virt_to_page(hyp_vm));
 	hyp_spin_unlock(&vm_table_lock);
 }
 
+struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle)
+{
+	struct pkvm_hyp_vm *hyp_vm = get_pkvm_hyp_vm(handle);
+
+	if (hyp_vm && pkvm_hyp_vm_is_protected(hyp_vm)) {
+		put_pkvm_hyp_vm(hyp_vm);
+		hyp_vm = NULL;
+	}
+
+	return hyp_vm;
+}
+
 static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm)
 {
 	struct kvm *kvm = &hyp_vm->kvm;
+	unsigned long host_arch_flags = READ_ONCE(host_kvm->arch.flags);
 	DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES);
 
+	if (test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &host_kvm->arch.flags))
+		set_bit(KVM_ARCH_FLAG_MTE_ENABLED, &kvm->arch.flags);
+
 	/* No restrictions for non-protected VMs. */
 	if (!kvm_vm_is_protected(kvm)) {
+		hyp_vm->kvm.arch.flags = host_arch_flags;
+
 		bitmap_copy(kvm->arch.vcpu_features,
 			    host_kvm->arch.vcpu_features,
 			    KVM_VCPU_MAX_FEATURES);
@@ -342,50 +330,26 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc
 
 	bitmap_zero(allowed_features, KVM_VCPU_MAX_FEATURES);
 
-	/*
-	 * For protected VMs, always allow:
-	 * - CPU starting in poweroff state
-	 * - PSCI v0.2
-	 */
-	set_bit(KVM_ARM_VCPU_POWER_OFF, allowed_features);
 	set_bit(KVM_ARM_VCPU_PSCI_0_2, allowed_features);
 
-	/*
-	 * Check if remaining features are allowed:
-	 * - Performance Monitoring
-	 * - Scalable Vectors
-	 * - Pointer Authentication
-	 */
-	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), PVM_ID_AA64DFR0_ALLOW))
+	if (kvm_pvm_ext_allowed(KVM_CAP_ARM_PMU_V3))
 		set_bit(KVM_ARM_VCPU_PMU_V3, allowed_features);
 
-	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), PVM_ID_AA64PFR0_ALLOW))
-		set_bit(KVM_ARM_VCPU_SVE, allowed_features);
-
-	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API), PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED) &&
-	    FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA), PVM_ID_AA64ISAR1_RESTRICT_UNSIGNED))
+	if (kvm_pvm_ext_allowed(KVM_CAP_ARM_PTRAUTH_ADDRESS))
 		set_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, allowed_features);
 
-	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI), PVM_ID_AA64ISAR1_ALLOW) &&
-	    FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA), PVM_ID_AA64ISAR1_ALLOW))
+	if (kvm_pvm_ext_allowed(KVM_CAP_ARM_PTRAUTH_GENERIC))
 		set_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, allowed_features);
 
+	if (kvm_pvm_ext_allowed(KVM_CAP_ARM_SVE)) {
+		set_bit(KVM_ARM_VCPU_SVE, allowed_features);
+		kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_GUEST_HAS_SVE);
+	}
+
 	bitmap_and(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features,
 		   allowed_features, KVM_VCPU_MAX_FEATURES);
 }
 
-static void pkvm_vcpu_init_ptrauth(struct pkvm_hyp_vcpu *hyp_vcpu)
-{
-	struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
-
-	if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) ||
-	    vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)) {
-		kvm_vcpu_enable_ptrauth(vcpu);
-	} else {
-		vcpu_clear_flag(&hyp_vcpu->vcpu, GUEST_HAS_PTRAUTH);
-	}
-}
-
 static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu)
 {
 	if (host_vcpu)
@@ -408,6 +372,7 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
 	hyp_vm->kvm.created_vcpus = nr_vcpus;
 	hyp_vm->kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr;
 	hyp_vm->kvm.arch.pkvm.enabled = READ_ONCE(host_kvm->arch.pkvm.enabled);
+	hyp_vm->kvm.arch.flags = 0;
 	pkvm_init_features_from_host(hyp_vm, host_kvm);
 }
 
@@ -415,10 +380,8 @@ static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *
 {
 	struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
 
-	if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) {
-		vcpu_clear_flag(vcpu, GUEST_HAS_SVE);
+	if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE))
 		vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED);
-	}
 }
 
 static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
@@ -446,9 +409,14 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
 	hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags);
 	hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED;
 
+	if (pkvm_hyp_vcpu_is_protected(hyp_vcpu))
+		kvm_init_pvm_id_regs(&hyp_vcpu->vcpu);
+
+	ret = pkvm_vcpu_init_traps(hyp_vcpu);
+	if (ret)
+		goto done;
+
 	pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
-	pkvm_vcpu_init_ptrauth(hyp_vcpu);
-	pkvm_vcpu_init_traps(&hyp_vcpu->vcpu);
 done:
 	if (ret)
 		unpin_host_vcpu(host_vcpu);
@@ -693,8 +661,6 @@ unlock:
 		return ret;
 	}
 
-	hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
-
 	return 0;
 }
 
@@ -746,6 +712,14 @@ int __pkvm_teardown_vm(pkvm_handle_t handle)
 	/* Push the metadata pages to the teardown memcache */
 	for (idx = 0; idx < hyp_vm->nr_vcpus; ++idx) {
 		struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx];
+		struct kvm_hyp_memcache *vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache;
+
+		while (vcpu_mc->nr_pages) {
+			void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt);
+
+			push_hyp_memcache(mc, addr, hyp_virt_to_phys);
+			unmap_donated_memory_noclear(addr, PAGE_SIZE);
+		}
 
 		teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu));
 	}
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index cbdd18cd3f98..d62bcb5634a2 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -12,7 +12,6 @@
 
 #include <nvhe/early_alloc.h>
 #include <nvhe/ffa.h>
-#include <nvhe/fixed_config.h>
 #include <nvhe/gfp.h>
 #include <nvhe/memory.h>
 #include <nvhe/mem_protect.h>
@@ -180,7 +179,6 @@ static void hpool_put_page(void *addr)
 static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 				     enum kvm_pgtable_walk_flags visit)
 {
-	enum kvm_pgtable_prot prot;
 	enum pkvm_page_state state;
 	phys_addr_t phys;
 
@@ -203,16 +201,16 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	case PKVM_PAGE_OWNED:
 		return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP);
 	case PKVM_PAGE_SHARED_OWNED:
-		prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED);
+		hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_BORROWED;
 		break;
 	case PKVM_PAGE_SHARED_BORROWED:
-		prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED);
+		hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_OWNED;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	return host_stage2_idmap_locked(phys, PAGE_SIZE, prot);
+	return 0;
 }
 
 static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx,
diff --git a/arch/arm64/kvm/hyp/nvhe/stacktrace.c b/arch/arm64/kvm/hyp/nvhe/stacktrace.c
index ed6b58b19cfa..5b6eeab1a774 100644
--- a/arch/arm64/kvm/hyp/nvhe/stacktrace.c
+++ b/arch/arm64/kvm/hyp/nvhe/stacktrace.c
@@ -28,7 +28,7 @@ static void hyp_prepare_backtrace(unsigned long fp, unsigned long pc)
 	struct kvm_nvhe_stacktrace_info *stacktrace_info = this_cpu_ptr(&kvm_stacktrace_info);
 	struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params);
 
-	stacktrace_info->stack_base = (unsigned long)(params->stack_hyp_va - PAGE_SIZE);
+	stacktrace_info->stack_base = (unsigned long)(params->stack_hyp_va - NVHE_STACK_SIZE);
 	stacktrace_info->overflow_stack_base = (unsigned long)this_cpu_ptr(overflow_stack);
 	stacktrace_info->fp = fp;
 	stacktrace_info->pc = pc;
@@ -54,7 +54,7 @@ static struct stack_info stackinfo_get_hyp(void)
 {
 	struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params);
 	unsigned long high = params->stack_hyp_va;
-	unsigned long low = high - PAGE_SIZE;
+	unsigned long low = high - NVHE_STACK_SIZE;
 
 	return (struct stack_info) {
 		.low = low,
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 0f6b01b3da5c..6c846d033d24 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -26,7 +26,6 @@
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>
 
-#include <nvhe/fixed_config.h>
 #include <nvhe/mem_protect.h>
 
 /* Non-VHE specific context */
@@ -36,33 +35,46 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
 
 extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc);
 
-static void __activate_traps(struct kvm_vcpu *vcpu)
+static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
 {
-	u64 val;
+	u64 val = CPTR_EL2_TAM;	/* Same bit irrespective of E2H */
 
-	___activate_traps(vcpu, vcpu->arch.hcr_el2);
-	__activate_traps_common(vcpu);
+	if (has_hvhe()) {
+		val |= CPACR_EL1_TTA;
 
-	val = vcpu->arch.cptr_el2;
-	val |= CPTR_EL2_TAM;	/* Same bit irrespective of E2H */
-	val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
-	if (cpus_have_final_cap(ARM64_SME)) {
-		if (has_hvhe())
-			val &= ~CPACR_EL1_SMEN;
-		else
-			val |= CPTR_EL2_TSM;
-	}
+		if (guest_owns_fp_regs()) {
+			val |= CPACR_EL1_FPEN;
+			if (vcpu_has_sve(vcpu))
+				val |= CPACR_EL1_ZEN;
+		}
+	} else {
+		val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;
 
-	if (!guest_owns_fp_regs()) {
-		if (has_hvhe())
-			val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
-		else
-			val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
+		/*
+		 * Always trap SME since it's not supported in KVM.
+		 * TSM is RES1 if SME isn't implemented.
+		 */
+		val |= CPTR_EL2_TSM;
 
-		__activate_traps_fpsimd32(vcpu);
+		if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
+			val |= CPTR_EL2_TZ;
+
+		if (!guest_owns_fp_regs())
+			val |= CPTR_EL2_TFP;
 	}
 
+	if (!guest_owns_fp_regs())
+		__activate_traps_fpsimd32(vcpu);
+
 	kvm_write_cptr_el2(val);
+}
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+	___activate_traps(vcpu, vcpu->arch.hcr_el2);
+	__activate_traps_common(vcpu);
+	__activate_cptr_traps(vcpu);
+
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
 
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index 2860548d4250..1ddd9ed3cbb3 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -11,7 +11,7 @@
 
 #include <hyp/adjust_pc.h>
 
-#include <nvhe/fixed_config.h>
+#include <nvhe/pkvm.h>
 
 #include "../../sys_regs.h"
 
@@ -28,222 +28,255 @@ u64 id_aa64mmfr1_el1_sys_val;
 u64 id_aa64mmfr2_el1_sys_val;
 u64 id_aa64smfr0_el1_sys_val;
 
-/*
- * Inject an unknown/undefined exception to an AArch64 guest while most of its
- * sysregs are live.
- */
-static void inject_undef64(struct kvm_vcpu *vcpu)
-{
-	u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
-
-	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
-	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
-
-	kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
-
-	__kvm_adjust_pc(vcpu);
-
-	write_sysreg_el1(esr, SYS_ESR);
-	write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
-	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
-	write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
-}
-
-/*
- * Returns the restricted features values of the feature register based on the
- * limitations in restrict_fields.
- * A feature id field value of 0b0000 does not impose any restrictions.
- * Note: Use only for unsigned feature field values.
- */
-static u64 get_restricted_features_unsigned(u64 sys_reg_val,
-					    u64 restrict_fields)
-{
-	u64 value = 0UL;
-	u64 mask = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+struct pvm_ftr_bits {
+	bool		sign;
+	u8		shift;
+	u8		width;
+	u8		max_val;
+	bool (*vm_supported)(const struct kvm *kvm);
+};
 
-	/*
-	 * According to the Arm Architecture Reference Manual, feature fields
-	 * use increasing values to indicate increases in functionality.
-	 * Iterate over the restricted feature fields and calculate the minimum
-	 * unsigned value between the one supported by the system, and what the
-	 * value is being restricted to.
-	 */
-	while (sys_reg_val && restrict_fields) {
-		value |= min(sys_reg_val & mask, restrict_fields & mask);
-		sys_reg_val &= ~mask;
-		restrict_fields &= ~mask;
-		mask <<= ARM64_FEATURE_FIELD_BITS;
+#define __MAX_FEAT_FUNC(id, fld, max, func, sgn)				\
+	{									\
+		.sign = sgn,							\
+		.shift = id##_##fld##_SHIFT,					\
+		.width = id##_##fld##_WIDTH,					\
+		.max_val = id##_##fld##_##max,					\
+		.vm_supported = func,						\
 	}
 
-	return value;
-}
-
-/*
- * Functions that return the value of feature id registers for protected VMs
- * based on allowed features, system features, and KVM support.
- */
+#define MAX_FEAT_FUNC(id, fld, max, func)					\
+	__MAX_FEAT_FUNC(id, fld, max, func, id##_##fld##_SIGNED)
 
-static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu)
-{
-	u64 set_mask = 0;
-	u64 allow_mask = PVM_ID_AA64PFR0_ALLOW;
+#define MAX_FEAT(id, fld, max)							\
+	MAX_FEAT_FUNC(id, fld, max, NULL)
 
-	set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val,
-		PVM_ID_AA64PFR0_RESTRICT_UNSIGNED);
+#define MAX_FEAT_ENUM(id, fld, max)						\
+	__MAX_FEAT_FUNC(id, fld, max, NULL, false)
 
-	return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask;
-}
+#define FEAT_END {	.width = 0,	}
 
-static u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu)
+static bool vm_has_ptrauth(const struct kvm *kvm)
 {
-	const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
-	u64 allow_mask = PVM_ID_AA64PFR1_ALLOW;
-
-	if (!kvm_has_mte(kvm))
-		allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
-
-	return id_aa64pfr1_el1_sys_val & allow_mask;
-}
-
-static u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu)
-{
-	/*
-	 * No support for Scalable Vectors, therefore, hyp has no sanitized
-	 * copy of the feature id register.
-	 */
-	BUILD_BUG_ON(PVM_ID_AA64ZFR0_ALLOW != 0ULL);
-	return 0;
-}
-
-static u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu)
-{
-	/*
-	 * No support for debug, including breakpoints, and watchpoints,
-	 * therefore, pKVM has no sanitized copy of the feature id register.
-	 */
-	BUILD_BUG_ON(PVM_ID_AA64DFR0_ALLOW != 0ULL);
-	return 0;
-}
-
-static u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu)
-{
-	/*
-	 * No support for debug, therefore, hyp has no sanitized copy of the
-	 * feature id register.
-	 */
-	BUILD_BUG_ON(PVM_ID_AA64DFR1_ALLOW != 0ULL);
-	return 0;
-}
+	if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH))
+		return false;
 
-static u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu)
-{
-	/*
-	 * No support for implementation defined features, therefore, hyp has no
-	 * sanitized copy of the feature id register.
-	 */
-	BUILD_BUG_ON(PVM_ID_AA64AFR0_ALLOW != 0ULL);
-	return 0;
+	return (cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) ||
+		cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) &&
+		kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC);
 }
 
-static u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu)
+static bool vm_has_sve(const struct kvm *kvm)
 {
-	/*
-	 * No support for implementation defined features, therefore, hyp has no
-	 * sanitized copy of the feature id register.
-	 */
-	BUILD_BUG_ON(PVM_ID_AA64AFR1_ALLOW != 0ULL);
-	return 0;
+	return system_supports_sve() && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_SVE);
 }
 
-static u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu)
-{
-	return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW;
-}
+/*
+ * Definitions for features to be allowed or restricted for protected guests.
+ *
+ * Each field in the masks represents the highest supported value for the
+ * feature. If a feature field is not present, it is not supported. Moreover,
+ * these are used to generate the guest's view of the feature registers.
+ *
+ * The approach for protected VMs is to at least support features that are:
+ * - Needed by common Linux distributions (e.g., floating point)
+ * - Trivial to support, e.g., supporting the feature does not introduce or
+ * require tracking of additional state in KVM
+ * - Cannot be trapped or prevent the guest from using anyway
+ */
 
-static u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu)
-{
-	u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW;
+static const struct pvm_ftr_bits pvmid_aa64pfr0[] = {
+	MAX_FEAT(ID_AA64PFR0_EL1, EL0, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, EL1, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, EL2, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, EL3, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, FP, FP16),
+	MAX_FEAT(ID_AA64PFR0_EL1, AdvSIMD, FP16),
+	MAX_FEAT(ID_AA64PFR0_EL1, GIC, IMP),
+	MAX_FEAT_FUNC(ID_AA64PFR0_EL1, SVE, IMP, vm_has_sve),
+	MAX_FEAT(ID_AA64PFR0_EL1, RAS, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, DIT, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, CSV2, IMP),
+	MAX_FEAT(ID_AA64PFR0_EL1, CSV3, IMP),
+	FEAT_END
+};
 
-	if (!vcpu_has_ptrauth(vcpu))
-		allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) |
-				ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) |
-				ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) |
-				ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI));
+static const struct pvm_ftr_bits pvmid_aa64pfr1[] = {
+	MAX_FEAT(ID_AA64PFR1_EL1, BT, IMP),
+	MAX_FEAT(ID_AA64PFR1_EL1, SSBS, SSBS2),
+	MAX_FEAT_ENUM(ID_AA64PFR1_EL1, MTE_frac, NI),
+	FEAT_END
+};
 
-	return id_aa64isar1_el1_sys_val & allow_mask;
-}
+static const struct pvm_ftr_bits pvmid_aa64mmfr0[] = {
+	MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, PARANGE, 40),
+	MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, ASIDBITS, 16),
+	MAX_FEAT(ID_AA64MMFR0_EL1, BIGEND, IMP),
+	MAX_FEAT(ID_AA64MMFR0_EL1, SNSMEM, IMP),
+	MAX_FEAT(ID_AA64MMFR0_EL1, BIGENDEL0, IMP),
+	MAX_FEAT(ID_AA64MMFR0_EL1, EXS, IMP),
+	FEAT_END
+};
 
-static u64 get_pvm_id_aa64isar2(const struct kvm_vcpu *vcpu)
-{
-	u64 allow_mask = PVM_ID_AA64ISAR2_ALLOW;
+static const struct pvm_ftr_bits pvmid_aa64mmfr1[] = {
+	MAX_FEAT(ID_AA64MMFR1_EL1, HAFDBS, DBM),
+	MAX_FEAT_ENUM(ID_AA64MMFR1_EL1, VMIDBits, 16),
+	MAX_FEAT(ID_AA64MMFR1_EL1, HPDS, HPDS2),
+	MAX_FEAT(ID_AA64MMFR1_EL1, PAN, PAN3),
+	MAX_FEAT(ID_AA64MMFR1_EL1, SpecSEI, IMP),
+	MAX_FEAT(ID_AA64MMFR1_EL1, ETS, IMP),
+	MAX_FEAT(ID_AA64MMFR1_EL1, CMOW, IMP),
+	FEAT_END
+};
 
-	if (!vcpu_has_ptrauth(vcpu))
-		allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) |
-				ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3));
+static const struct pvm_ftr_bits pvmid_aa64mmfr2[] = {
+	MAX_FEAT(ID_AA64MMFR2_EL1, CnP, IMP),
+	MAX_FEAT(ID_AA64MMFR2_EL1, UAO, IMP),
+	MAX_FEAT(ID_AA64MMFR2_EL1, IESB, IMP),
+	MAX_FEAT(ID_AA64MMFR2_EL1, AT, IMP),
+	MAX_FEAT_ENUM(ID_AA64MMFR2_EL1, IDS, 0x18),
+	MAX_FEAT(ID_AA64MMFR2_EL1, TTL, IMP),
+	MAX_FEAT(ID_AA64MMFR2_EL1, BBM, 2),
+	MAX_FEAT(ID_AA64MMFR2_EL1, E0PD, IMP),
+	FEAT_END
+};
 
-	return id_aa64isar2_el1_sys_val & allow_mask;
-}
+static const struct pvm_ftr_bits pvmid_aa64isar1[] = {
+	MAX_FEAT(ID_AA64ISAR1_EL1, DPB, DPB2),
+	MAX_FEAT_FUNC(ID_AA64ISAR1_EL1, APA, PAuth, vm_has_ptrauth),
+	MAX_FEAT_FUNC(ID_AA64ISAR1_EL1, API, PAuth, vm_has_ptrauth),
+	MAX_FEAT(ID_AA64ISAR1_EL1, JSCVT, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, FCMA, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, LRCPC, LRCPC3),
+	MAX_FEAT(ID_AA64ISAR1_EL1, GPA, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, GPI, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, FRINTTS, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, SB, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX),
+	MAX_FEAT(ID_AA64ISAR1_EL1, BF16, EBF16),
+	MAX_FEAT(ID_AA64ISAR1_EL1, DGH, IMP),
+	MAX_FEAT(ID_AA64ISAR1_EL1, I8MM, IMP),
+	FEAT_END
+};
 
-static u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu)
-{
-	u64 set_mask;
+static const struct pvm_ftr_bits pvmid_aa64isar2[] = {
+	MAX_FEAT_FUNC(ID_AA64ISAR2_EL1, GPA3, IMP, vm_has_ptrauth),
+	MAX_FEAT_FUNC(ID_AA64ISAR2_EL1, APA3, PAuth, vm_has_ptrauth),
+	MAX_FEAT(ID_AA64ISAR2_EL1, ATS1A, IMP),
+	FEAT_END
+};
 
-	set_mask = get_restricted_features_unsigned(id_aa64mmfr0_el1_sys_val,
-		PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED);
+/*
+ * None of the features in ID_AA64DFR0_EL1 nor ID_AA64MMFR4_EL1 are supported.
+ * However, both have Not-Implemented values that are non-zero. Define them
+ * so they can be used when getting the value of these registers.
+ */
+#define ID_AA64DFR0_EL1_NONZERO_NI					\
+(									\
+	SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, DoubleLock, NI)	|	\
+	SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, MTPMU, NI)			\
+)
 
-	return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask;
-}
+#define ID_AA64MMFR4_EL1_NONZERO_NI					\
+	SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI)
 
-static u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu)
+/*
+ * Returns the value of the feature registers based on the system register
+ * value, the vcpu support for the revelant features, and the additional
+ * restrictions for protected VMs.
+ */
+static u64 get_restricted_features(const struct kvm_vcpu *vcpu,
+				   u64 sys_reg_val,
+				   const struct pvm_ftr_bits restrictions[])
 {
-	return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW;
-}
+	u64 val = 0UL;
+	int i;
+
+	for (i = 0; restrictions[i].width != 0; i++) {
+		bool (*vm_supported)(const struct kvm *) = restrictions[i].vm_supported;
+		bool sign = restrictions[i].sign;
+		int shift = restrictions[i].shift;
+		int width = restrictions[i].width;
+		u64 min_signed = (1UL << width) - 1UL;
+		u64 sign_bit = 1UL << (width - 1);
+		u64 mask = GENMASK_ULL(width + shift - 1, shift);
+		u64 sys_val = (sys_reg_val & mask) >> shift;
+		u64 pvm_max = restrictions[i].max_val;
+
+		if (vm_supported && !vm_supported(vcpu->kvm))
+			val |= (sign ? min_signed : 0) << shift;
+		else if (sign && (sys_val >= sign_bit || pvm_max >= sign_bit))
+			val |= max(sys_val, pvm_max) << shift;
+		else
+			val |= min(sys_val, pvm_max) << shift;
+	}
 
-static u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu)
-{
-	return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW;
+	return val;
 }
 
-/* Read a sanitized cpufeature ID register by its encoding */
-u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
+static u64 pvm_calc_id_reg(const struct kvm_vcpu *vcpu, u32 id)
 {
 	switch (id) {
 	case SYS_ID_AA64PFR0_EL1:
-		return get_pvm_id_aa64pfr0(vcpu);
+		return get_restricted_features(vcpu, id_aa64pfr0_el1_sys_val, pvmid_aa64pfr0);
 	case SYS_ID_AA64PFR1_EL1:
-		return get_pvm_id_aa64pfr1(vcpu);
-	case SYS_ID_AA64ZFR0_EL1:
-		return get_pvm_id_aa64zfr0(vcpu);
-	case SYS_ID_AA64DFR0_EL1:
-		return get_pvm_id_aa64dfr0(vcpu);
-	case SYS_ID_AA64DFR1_EL1:
-		return get_pvm_id_aa64dfr1(vcpu);
-	case SYS_ID_AA64AFR0_EL1:
-		return get_pvm_id_aa64afr0(vcpu);
-	case SYS_ID_AA64AFR1_EL1:
-		return get_pvm_id_aa64afr1(vcpu);
+		return get_restricted_features(vcpu, id_aa64pfr1_el1_sys_val, pvmid_aa64pfr1);
 	case SYS_ID_AA64ISAR0_EL1:
-		return get_pvm_id_aa64isar0(vcpu);
+		return id_aa64isar0_el1_sys_val;
 	case SYS_ID_AA64ISAR1_EL1:
-		return get_pvm_id_aa64isar1(vcpu);
+		return get_restricted_features(vcpu, id_aa64isar1_el1_sys_val, pvmid_aa64isar1);
 	case SYS_ID_AA64ISAR2_EL1:
-		return get_pvm_id_aa64isar2(vcpu);
+		return get_restricted_features(vcpu, id_aa64isar2_el1_sys_val, pvmid_aa64isar2);
 	case SYS_ID_AA64MMFR0_EL1:
-		return get_pvm_id_aa64mmfr0(vcpu);
+		return get_restricted_features(vcpu, id_aa64mmfr0_el1_sys_val, pvmid_aa64mmfr0);
 	case SYS_ID_AA64MMFR1_EL1:
-		return get_pvm_id_aa64mmfr1(vcpu);
+		return get_restricted_features(vcpu, id_aa64mmfr1_el1_sys_val, pvmid_aa64mmfr1);
 	case SYS_ID_AA64MMFR2_EL1:
-		return get_pvm_id_aa64mmfr2(vcpu);
+		return get_restricted_features(vcpu, id_aa64mmfr2_el1_sys_val, pvmid_aa64mmfr2);
+	case SYS_ID_AA64DFR0_EL1:
+		return ID_AA64DFR0_EL1_NONZERO_NI;
+	case SYS_ID_AA64MMFR4_EL1:
+		return ID_AA64MMFR4_EL1_NONZERO_NI;
 	default:
 		/* Unhandled ID register, RAZ */
 		return 0;
 	}
 }
 
+/*
+ * Inject an unknown/undefined exception to an AArch64 guest while most of its
+ * sysregs are live.
+ */
+static void inject_undef64(struct kvm_vcpu *vcpu)
+{
+	u64 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
+
+	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+
+	kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
+
+	__kvm_adjust_pc(vcpu);
+
+	write_sysreg_el1(esr, SYS_ESR);
+	write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
+	write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+	write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+}
+
 static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		       struct sys_reg_desc const *r)
 {
-	return pvm_read_id_reg(vcpu, reg_to_encoding(r));
+	struct kvm *kvm = vcpu->kvm;
+	u32 reg = reg_to_encoding(r);
+
+	if (WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)))
+		return 0;
+
+	if (reg >= sys_reg(3, 0, 0, 1, 0) && reg <= sys_reg(3, 0, 0, 7, 7))
+		return kvm->arch.id_regs[IDREG_IDX(reg)];
+
+	return 0;
 }
 
 /* Handler to RAZ/WI sysregs */
@@ -271,13 +304,6 @@ static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu,
 		return false;
 	}
 
-	/*
-	 * No support for AArch32 guests, therefore, pKVM has no sanitized copy
-	 * of AArch32 feature id registers.
-	 */
-	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL1),
-		     PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_EL1_EL1_IMP);
-
 	return pvm_access_raz_wi(vcpu, p, r);
 }
 
@@ -449,6 +475,30 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 };
 
 /*
+ * Initializes feature registers for protected vms.
+ */
+void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_arch *ka = &kvm->arch;
+	u32 r;
+
+	hyp_assert_lock_held(&vm_table_lock);
+
+	if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))
+		return;
+
+	/*
+	 * Initialize only AArch64 id registers since AArch32 isn't supported
+	 * for protected VMs.
+	 */
+	for (r = sys_reg(3, 0, 0, 4, 0); r <= sys_reg(3, 0, 0, 7, 7); r += sys_reg(0, 0, 0, 0, 1))
+		ka->id_regs[IDREG_IDX(r)] = pvm_calc_id_reg(vcpu, r);
+
+	set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);
+}
+
+/*
  * Checks that the sysreg table is unique and in-order.
  *
  * Returns 0 if the table is consistent, or 1 otherwise.
diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
index 3aaab20ae5b4..ff176f4ce7de 100644
--- a/arch/arm64/kvm/hyp/nvhe/timer-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c
@@ -22,15 +22,16 @@ void __kvm_timer_set_cntvoff(u64 cntvoff)
  */
 void __timer_disable_traps(struct kvm_vcpu *vcpu)
 {
-	u64 val, shift = 0;
+	u64 set, clr, shift = 0;
 
 	if (has_hvhe())
 		shift = 10;
 
 	/* Allow physical timer/counter access for the host */
-	val = read_sysreg(cnthctl_el2);
-	val |= (CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN) << shift;
-	write_sysreg(val, cnthctl_el2);
+	set = (CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN) << shift;
+	clr = CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT;
+
+	sysreg_clear_set(cnthctl_el2, clr, set);
 }
 
 /*
@@ -58,5 +59,12 @@ void __timer_enable_traps(struct kvm_vcpu *vcpu)
 		set <<= 10;
 	}
 
+	/*
+	 * Trap the virtual counter/timer if we have a broken cntvoff
+	 * implementation.
+	 */
+	if (has_broken_cntvoff())
+		set |= CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT;
+
 	sysreg_clear_set(cnthctl_el2, clr, set);
 }
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index d2b6fa051d6b..df5cc74a7dd0 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1232,14 +1232,13 @@ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
 					NULL, NULL, 0);
 }
 
-void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr)
+void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
+				enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 
 	ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0,
-				       NULL, NULL,
-				       KVM_PGTABLE_WALK_HANDLE_FAULT |
-				       KVM_PGTABLE_WALK_SHARED);
+				       NULL, NULL, flags);
 	if (!ret)
 		dsb(ishst);
 }
@@ -1295,7 +1294,7 @@ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr,
 }
 
 int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
-				   enum kvm_pgtable_prot prot)
+				   enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags)
 {
 	int ret;
 	s8 level;
@@ -1313,9 +1312,7 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
 	if (prot & KVM_PGTABLE_PROT_X)
 		clr |= KVM_PTE_LEAF_ATTR_HI_S2_XN;
 
-	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level,
-				       KVM_PGTABLE_WALK_HANDLE_FAULT |
-				       KVM_PGTABLE_WALK_SHARED);
+	ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags);
 	if (!ret || ret == -EAGAIN)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, level);
 	return ret;
diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c
index 289689b2682d..0100339b09e0 100644
--- a/arch/arm64/kvm/hyp/vhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c
@@ -19,8 +19,3 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_switch_to_host_common(vcpu);
 }
-
-u64 __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 59d992455793..b5b9dbaf1fdd 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -256,6 +256,110 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
 	host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL;
 }
 
+static u64 compute_emulated_cntx_ctl_el0(struct kvm_vcpu *vcpu,
+					 enum vcpu_sysreg reg)
+{
+	unsigned long ctl;
+	u64 cval, cnt;
+	bool stat;
+
+	switch (reg) {
+	case CNTP_CTL_EL0:
+		cval = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		ctl  = __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
+		cnt  = compute_counter_value(vcpu_ptimer(vcpu));
+		break;
+	case CNTV_CTL_EL0:
+		cval = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+		ctl  = __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
+		cnt  = compute_counter_value(vcpu_vtimer(vcpu));
+		break;
+	default:
+		BUG();
+	}
+
+	stat = cval <= cnt;
+	__assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &ctl, stat);
+
+	return ctl;
+}
+
+static bool kvm_hyp_handle_timer(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr, val;
+
+	/*
+	 * Having FEAT_ECV allows for a better quality of timer emulation.
+	 * However, this comes at a huge cost in terms of traps. Try and
+	 * satisfy the reads from guest's hypervisor context without
+	 * returning to the kernel if we can.
+	 */
+	if (!is_hyp_ctxt(vcpu))
+		return false;
+
+	esr = kvm_vcpu_get_esr(vcpu);
+	if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) != ESR_ELx_SYS64_ISS_DIR_READ)
+		return false;
+
+	switch (esr_sys64_to_sysreg(esr)) {
+	case SYS_CNTP_CTL_EL02:
+		val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0);
+		break;
+	case SYS_CNTP_CTL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu))
+			val = read_sysreg_el0(SYS_CNTP_CTL);
+		else
+			val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0);
+		break;
+	case SYS_CNTP_CVAL_EL02:
+		val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		break;
+	case SYS_CNTP_CVAL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu)) {
+			val = read_sysreg_el0(SYS_CNTP_CVAL);
+
+			if (!has_cntpoff())
+				val -= timer_get_offset(vcpu_hptimer(vcpu));
+		} else {
+			val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		}
+		break;
+	case SYS_CNTPCT_EL0:
+	case SYS_CNTPCTSS_EL0:
+		val = compute_counter_value(vcpu_hptimer(vcpu));
+		break;
+	case SYS_CNTV_CTL_EL02:
+		val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0);
+		break;
+	case SYS_CNTV_CTL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu))
+			val = read_sysreg_el0(SYS_CNTV_CTL);
+		else
+			val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0);
+		break;
+	case SYS_CNTV_CVAL_EL02:
+		val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+		break;
+	case SYS_CNTV_CVAL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu))
+			val = read_sysreg_el0(SYS_CNTV_CVAL);
+		else
+			val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+		break;
+	case SYS_CNTVCT_EL0:
+	case SYS_CNTVCTSS_EL0:
+		val = compute_counter_value(vcpu_hvtimer(vcpu));
+		break;
+	default:
+		return false;
+	}
+
+	vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val);
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
 static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	u64 esr = kvm_vcpu_get_esr(vcpu);
@@ -409,6 +513,9 @@ static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code))
 		return true;
 
+	if (kvm_hyp_handle_timer(vcpu, exit_code))
+		return true;
+
 	if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code))
 		return true;
 
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 5f78a39053a7..90b018e06f2c 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -216,7 +216,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_user_state(guest_ctxt);
 
-	if (unlikely(__is_hyp_ctxt(guest_ctxt))) {
+	if (unlikely(is_hyp_ctxt(vcpu))) {
 		__sysreg_restore_vel2_state(vcpu);
 	} else {
 		if (vcpu_has_nv(vcpu)) {
@@ -260,7 +260,7 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
 
 	host_ctxt = host_data_ptr(host_ctxt);
 
-	if (unlikely(__is_hyp_ctxt(guest_ctxt)))
+	if (unlikely(is_hyp_ctxt(vcpu)))
 		__sysreg_save_vel2_state(vcpu);
 	else
 		__sysreg_save_el1_state(guest_ctxt);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c9d46ad57e52..1f55b0c7b11d 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -15,6 +15,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
+#include <asm/kvm_pkvm.h>
 #include <asm/kvm_ras.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -29,8 +30,12 @@ static unsigned long __ro_after_init hyp_idmap_start;
 static unsigned long __ro_after_init hyp_idmap_end;
 static phys_addr_t __ro_after_init hyp_idmap_vector;
 
+u32 __ro_after_init __hyp_va_bits;
+
 static unsigned long __ro_after_init io_map_base;
 
+#define KVM_PGT_FN(fn)		(!is_protected_kvm_enabled() ? fn : p ## fn)
+
 static phys_addr_t __stage2_range_addr_end(phys_addr_t addr, phys_addr_t end,
 					   phys_addr_t size)
 {
@@ -147,7 +152,7 @@ static int kvm_mmu_split_huge_pages(struct kvm *kvm, phys_addr_t addr,
 			return -EINVAL;
 
 		next = __stage2_range_addr_end(addr, end, chunk_size);
-		ret = kvm_pgtable_stage2_split(pgt, addr, next - addr, cache);
+		ret = KVM_PGT_FN(kvm_pgtable_stage2_split)(pgt, addr, next - addr, cache);
 		if (ret)
 			break;
 	} while (addr = next, addr != end);
@@ -168,15 +173,23 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
  */
 int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
-	kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
+	if (is_protected_kvm_enabled())
+		kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
+	else
+		kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
 	return 0;
 }
 
 int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
 				      gfn_t gfn, u64 nr_pages)
 {
-	kvm_tlb_flush_vmid_range(&kvm->arch.mmu,
-				gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
+	u64 size = nr_pages << PAGE_SHIFT;
+	u64 addr = gfn << PAGE_SHIFT;
+
+	if (is_protected_kvm_enabled())
+		kvm_call_hyp_nvhe(__pkvm_tlb_flush_vmid, kvm->arch.pkvm.handle);
+	else
+		kvm_tlb_flush_vmid_range(&kvm->arch.mmu, addr, size);
 	return 0;
 }
 
@@ -225,7 +238,7 @@ static void stage2_free_unlinked_table_rcu_cb(struct rcu_head *head)
 	void *pgtable = page_to_virt(page);
 	s8 level = page_private(page);
 
-	kvm_pgtable_stage2_free_unlinked(&kvm_s2_mm_ops, pgtable, level);
+	KVM_PGT_FN(kvm_pgtable_stage2_free_unlinked)(&kvm_s2_mm_ops, pgtable, level);
 }
 
 static void stage2_free_unlinked_table(void *addr, s8 level)
@@ -324,7 +337,7 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
 
 	lockdep_assert_held_write(&kvm->mmu_lock);
 	WARN_ON(size & ~PAGE_MASK);
-	WARN_ON(stage2_apply_range(mmu, start, end, kvm_pgtable_stage2_unmap,
+	WARN_ON(stage2_apply_range(mmu, start, end, KVM_PGT_FN(kvm_pgtable_stage2_unmap),
 				   may_block));
 }
 
@@ -336,7 +349,7 @@ void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
 
 void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
-	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_flush);
+	stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_flush));
 }
 
 static void stage2_flush_memslot(struct kvm *kvm,
@@ -704,10 +717,10 @@ int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
 
 	mutex_lock(&kvm_hyp_pgd_mutex);
 	/*
-	 * Efficient stack verification using the PAGE_SHIFT bit implies
+	 * Efficient stack verification using the NVHE_STACK_SHIFT bit implies
 	 * an alignment of our allocation on the order of the size.
 	 */
-	size = PAGE_SIZE * 2;
+	size = NVHE_STACK_SIZE * 2;
 	base = ALIGN_DOWN(io_map_base - size, size);
 
 	ret = __hyp_alloc_private_va_range(base);
@@ -724,12 +737,12 @@ int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr)
 	 * at the higher address and leave the lower guard page
 	 * unbacked.
 	 *
-	 * Any valid stack address now has the PAGE_SHIFT bit as 1
+	 * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1
 	 * and addresses corresponding to the guard page have the
-	 * PAGE_SHIFT bit as 0 - this is used for overflow detection.
+	 * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection.
 	 */
-	ret = __create_hyp_mappings(base + PAGE_SIZE, PAGE_SIZE, phys_addr,
-				    PAGE_HYP);
+	ret = __create_hyp_mappings(base + NVHE_STACK_SIZE, NVHE_STACK_SIZE,
+				    phys_addr, PAGE_HYP);
 	if (ret)
 		kvm_err("Cannot map hyp stack\n");
 
@@ -942,10 +955,14 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 		return -ENOMEM;
 
 	mmu->arch = &kvm->arch;
-	err = kvm_pgtable_stage2_init(pgt, mmu, &kvm_s2_mm_ops);
+	err = KVM_PGT_FN(kvm_pgtable_stage2_init)(pgt, mmu, &kvm_s2_mm_ops);
 	if (err)
 		goto out_free_pgtable;
 
+	mmu->pgt = pgt;
+	if (is_protected_kvm_enabled())
+		return 0;
+
 	mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran));
 	if (!mmu->last_vcpu_ran) {
 		err = -ENOMEM;
@@ -959,7 +976,6 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	mmu->split_page_chunk_size = KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT;
 	mmu->split_page_cache.gfp_zero = __GFP_ZERO;
 
-	mmu->pgt = pgt;
 	mmu->pgd_phys = __pa(pgt->pgd);
 
 	if (kvm_is_nested_s2_mmu(kvm, mmu))
@@ -968,7 +984,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return 0;
 
 out_destroy_pgtable:
-	kvm_pgtable_stage2_destroy(pgt);
+	KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
 out_free_pgtable:
 	kfree(pgt);
 	return err;
@@ -1065,7 +1081,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
-		kvm_pgtable_stage2_destroy(pgt);
+		KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
 		kfree(pgt);
 	}
 }
@@ -1082,9 +1098,11 @@ static void *hyp_mc_alloc_fn(void *unused)
 
 void free_hyp_memcache(struct kvm_hyp_memcache *mc)
 {
-	if (is_protected_kvm_enabled())
-		__free_hyp_memcache(mc, hyp_mc_free_fn,
-				    kvm_host_va, NULL);
+	if (!is_protected_kvm_enabled())
+		return;
+
+	kfree(mc->mapping);
+	__free_hyp_memcache(mc, hyp_mc_free_fn, kvm_host_va, NULL);
 }
 
 int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
@@ -1092,6 +1110,12 @@ int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages)
 	if (!is_protected_kvm_enabled())
 		return 0;
 
+	if (!mc->mapping) {
+		mc->mapping = kzalloc(sizeof(struct pkvm_mapping), GFP_KERNEL_ACCOUNT);
+		if (!mc->mapping)
+			return -ENOMEM;
+	}
+
 	return __topup_hyp_memcache(mc, min_pages, hyp_mc_alloc_fn,
 				    kvm_host_pa, NULL);
 }
@@ -1130,8 +1154,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			break;
 
 		write_lock(&kvm->mmu_lock);
-		ret = kvm_pgtable_stage2_map(pgt, addr, PAGE_SIZE, pa, prot,
-					     &cache, 0);
+		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, addr, PAGE_SIZE,
+				 pa, prot, &cache, 0);
 		write_unlock(&kvm->mmu_lock);
 		if (ret)
 			break;
@@ -1151,7 +1175,7 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
  */
 void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
 {
-	stage2_apply_range_resched(mmu, addr, end, kvm_pgtable_stage2_wrprotect);
+	stage2_apply_range_resched(mmu, addr, end, KVM_PGT_FN(kvm_pgtable_stage2_wrprotect));
 }
 
 /**
@@ -1442,9 +1466,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
 	short vma_shift;
+	void *memcache;
 	gfn_t gfn;
 	kvm_pfn_t pfn;
 	bool logging_active = memslot_is_logging(memslot);
@@ -1452,6 +1476,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
 	struct kvm_pgtable *pgt;
 	struct page *page;
+	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
 
 	if (fault_is_perm)
 		fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
@@ -1471,8 +1496,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * and a write fault needs to collapse a block entry into a table.
 	 */
 	if (!fault_is_perm || (logging_active && write_fault)) {
-		ret = kvm_mmu_topup_memory_cache(memcache,
-						 kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu));
+		int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu);
+
+		if (!is_protected_kvm_enabled()) {
+			memcache = &vcpu->arch.mmu_page_cache;
+			ret = kvm_mmu_topup_memory_cache(memcache, min_pages);
+		} else {
+			memcache = &vcpu->arch.pkvm_memcache;
+			ret = topup_hyp_memcache(memcache, min_pages);
+		}
 		if (ret)
 			return ret;
 	}
@@ -1493,7 +1525,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * logging_active is guaranteed to never be true for VM_PFNMAP
 	 * memslots.
 	 */
-	if (logging_active) {
+	if (logging_active || is_protected_kvm_enabled()) {
 		force_pte = true;
 		vma_shift = PAGE_SHIFT;
 	} else {
@@ -1633,7 +1665,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		prot |= kvm_encode_nested_level(nested);
 	}
 
-	read_lock(&kvm->mmu_lock);
+	kvm_fault_lock(kvm);
 	pgt = vcpu->arch.hw_mmu->pgt;
 	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		ret = -EAGAIN;
@@ -1695,18 +1727,16 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		 * PTE, which will be preserved.
 		 */
 		prot &= ~KVM_NV_GUEST_MAP_SZ;
-		ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
+		ret = KVM_PGT_FN(kvm_pgtable_stage2_relax_perms)(pgt, fault_ipa, prot, flags);
 	} else {
-		ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
+		ret = KVM_PGT_FN(kvm_pgtable_stage2_map)(pgt, fault_ipa, vma_pagesize,
 					     __pfn_to_phys(pfn), prot,
-					     memcache,
-					     KVM_PGTABLE_WALK_HANDLE_FAULT |
-					     KVM_PGTABLE_WALK_SHARED);
+					     memcache, flags);
 	}
 
 out_unlock:
 	kvm_release_faultin_page(kvm, page, !!ret, writable);
-	read_unlock(&kvm->mmu_lock);
+	kvm_fault_unlock(kvm);
 
 	/* Mark the page dirty only if the fault is handled successfully */
 	if (writable && !ret)
@@ -1718,13 +1748,14 @@ out_unlock:
 /* Resolve the access fault by making the page young again. */
 static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
+	enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
 	struct kvm_s2_mmu *mmu;
 
 	trace_kvm_access_fault(fault_ipa);
 
 	read_lock(&vcpu->kvm->mmu_lock);
 	mmu = vcpu->arch.hw_mmu;
-	kvm_pgtable_stage2_mkyoung(mmu->pgt, fault_ipa);
+	KVM_PGT_FN(kvm_pgtable_stage2_mkyoung)(mmu->pgt, fault_ipa, flags);
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
@@ -1764,7 +1795,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 		}
 
 		/* Falls between the IPA range and the PARange? */
-		if (fault_ipa >= BIT_ULL(vcpu->arch.hw_mmu->pgt->ia_bits)) {
+		if (fault_ipa >= BIT_ULL(VTCR_EL2_IPA(vcpu->arch.hw_mmu->vtcr))) {
 			fault_ipa |= kvm_vcpu_get_hfar(vcpu) & GENMASK(11, 0);
 
 			if (is_iabt)
@@ -1930,7 +1961,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+	return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, true);
 	/*
@@ -1946,7 +1977,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
 	if (!kvm->arch.mmu.pgt)
 		return false;
 
-	return kvm_pgtable_stage2_test_clear_young(kvm->arch.mmu.pgt,
+	return KVM_PGT_FN(kvm_pgtable_stage2_test_clear_young)(kvm->arch.mmu.pgt,
 						   range->start << PAGE_SHIFT,
 						   size, false);
 }
@@ -2056,6 +2087,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits)
 		goto out_destroy_pgtable;
 
 	io_map_base = hyp_idmap_start;
+	__hyp_va_bits = *hyp_va_bits;
 	return 0;
 
 out_destroy_pgtable:
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9b36218b48de..0c9387d2f507 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -67,26 +67,27 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
 	if (!tmp)
 		return -ENOMEM;
 
+	swap(kvm->arch.nested_mmus, tmp);
+
 	/*
 	 * If we went through a realocation, adjust the MMU back-pointers in
 	 * the previously initialised kvm_pgtable structures.
 	 */
 	if (kvm->arch.nested_mmus != tmp)
 		for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
-			tmp[i].pgt->mmu = &tmp[i];
+			kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i];
 
 	for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
-		ret = init_nested_s2_mmu(kvm, &tmp[i]);
+		ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]);
 
 	if (ret) {
 		for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
-			kvm_free_stage2_pgd(&tmp[i]);
+			kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]);
 
 		return ret;
 	}
 
 	kvm->arch.nested_mmus_size = num_mmus;
-	kvm->arch.nested_mmus = tmp;
 
 	return 0;
 }
@@ -830,8 +831,10 @@ static void limit_nv_id_regs(struct kvm *kvm)
 		 NV_FTR(PFR0, RAS)	|
 		 NV_FTR(PFR0, EL3)	|
 		 NV_FTR(PFR0, EL2)	|
-		 NV_FTR(PFR0, EL1));
-	/* 64bit EL1/EL2/EL3 only */
+		 NV_FTR(PFR0, EL1)	|
+		 NV_FTR(PFR0, EL0));
+	/* 64bit only at any EL */
+	val |= FIELD_PREP(NV_FTR(PFR0, EL0), 0b0001);
 	val |= FIELD_PREP(NV_FTR(PFR0, EL1), 0b0001);
 	val |= FIELD_PREP(NV_FTR(PFR0, EL2), 0b0001);
 	val |= FIELD_PREP(NV_FTR(PFR0, EL3), 0b0001);
@@ -963,14 +966,15 @@ static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0,
 	kvm->arch.sysreg_masks->mask[i].res1 = res1;
 }
 
-int kvm_init_nv_sysregs(struct kvm *kvm)
+int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 {
+	struct kvm *kvm = vcpu->kvm;
 	u64 res0, res1;
 
 	lockdep_assert_held(&kvm->arch.config_lock);
 
 	if (kvm->arch.sysreg_masks)
-		return 0;
+		goto out;
 
 	kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)),
 					 GFP_KERNEL_ACCOUNT);
@@ -1021,8 +1025,8 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		res0 |= HCR_NV2;
 	if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, IMP))
 		res0 |= (HCR_AT | HCR_NV1 | HCR_NV);
-	if (!(__vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
-	      __vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
+	if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
+	      kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
 		res0 |= (HCR_API | HCR_APK);
 	if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP))
 		res0 |= BIT(39);
@@ -1078,8 +1082,8 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 
 	/* HFG[RW]TR_EL2 */
 	res0 = res1 = 0;
-	if (!(__vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
-	      __vcpu_has_feature(&kvm->arch, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
+	if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
+	      kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
 		res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey |
 			 HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey |
 			 HFGxTR_EL2_APIBKey);
@@ -1271,6 +1275,25 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		res0 |= MDCR_EL2_EnSTEPOP;
 	set_sysreg_masks(kvm, MDCR_EL2, res0, res1);
 
+	/* CNTHCTL_EL2 */
+	res0 = GENMASK(63, 20);
+	res1 = 0;
+	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RME, IMP))
+		res0 |= CNTHCTL_CNTPMASK | CNTHCTL_CNTVMASK;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, CNTPOFF)) {
+		res0 |= CNTHCTL_ECV;
+		if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, IMP))
+			res0 |= (CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT |
+				 CNTHCTL_EL1NVPCT | CNTHCTL_EL1NVVCT);
+	}
+	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
+		res0 |= GENMASK(11, 8);
+	set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1);
+
+out:
+	for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
+		(void)__vcpu_sys_reg(vcpu, sr);
+
 	return 0;
 }
 
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 85117ea8f351..930b677eb9b0 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/kmemleak.h>
 #include <linux/kvm_host.h>
+#include <asm/kvm_mmu.h>
 #include <linux/memblock.h>
 #include <linux/mutex.h>
 #include <linux/sort.h>
@@ -268,3 +269,203 @@ static int __init finalize_pkvm(void)
 	return ret;
 }
 device_initcall_sync(finalize_pkvm);
+
+static int cmp_mappings(struct rb_node *node, const struct rb_node *parent)
+{
+	struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node);
+	struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node);
+
+	if (a->gfn < b->gfn)
+		return -1;
+	if (a->gfn > b->gfn)
+		return 1;
+	return 0;
+}
+
+static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn)
+{
+	struct rb_node *node = root->rb_node, *prev = NULL;
+	struct pkvm_mapping *mapping;
+
+	while (node) {
+		mapping = rb_entry(node, struct pkvm_mapping, node);
+		if (mapping->gfn == gfn)
+			return node;
+		prev = node;
+		node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right;
+	}
+
+	return prev;
+}
+
+/*
+ * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing
+ * of __map inline.
+ */
+#define for_each_mapping_in_range_safe(__pgt, __start, __end, __map)				\
+	for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings,		\
+							     ((__start) >> PAGE_SHIFT));	\
+	     __tmp && ({									\
+				__map = rb_entry(__tmp, struct pkvm_mapping, node);		\
+				__tmp = rb_next(__tmp);						\
+				true;								\
+		       });									\
+	    )											\
+		if (__map->gfn < ((__start) >> PAGE_SHIFT))					\
+			continue;								\
+		else if (__map->gfn >= ((__end) >> PAGE_SHIFT))					\
+			break;									\
+		else
+
+int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
+			     struct kvm_pgtable_mm_ops *mm_ops)
+{
+	pgt->pkvm_mappings	= RB_ROOT;
+	pgt->mmu		= mmu;
+
+	return 0;
+}
+
+void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	struct rb_node *node;
+
+	if (!handle)
+		return;
+
+	node = rb_first(&pgt->pkvm_mappings);
+	while (node) {
+		mapping = rb_entry(node, struct pkvm_mapping, node);
+		kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
+		node = rb_next(node);
+		rb_erase(&mapping->node, &pgt->pkvm_mappings);
+		kfree(mapping);
+	}
+}
+
+int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			   u64 phys, enum kvm_pgtable_prot prot,
+			   void *mc, enum kvm_pgtable_walk_flags flags)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	struct pkvm_mapping *mapping = NULL;
+	struct kvm_hyp_memcache *cache = mc;
+	u64 gfn = addr >> PAGE_SHIFT;
+	u64 pfn = phys >> PAGE_SHIFT;
+	int ret;
+
+	if (size != PAGE_SIZE)
+		return -EINVAL;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot);
+	if (ret) {
+		/* Is the gfn already mapped due to a racing vCPU? */
+		if (ret == -EPERM)
+			return -EAGAIN;
+	}
+
+	swap(mapping, cache->mapping);
+	mapping->gfn = gfn;
+	mapping->pfn = pfn;
+	WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings));
+
+	return ret;
+}
+
+int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	int ret = 0;
+
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
+		if (WARN_ON(ret))
+			break;
+		rb_erase(&mapping->node, &pgt->pkvm_mappings);
+		kfree(mapping);
+	}
+
+	return ret;
+}
+
+int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	int ret = 0;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
+		ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn);
+		if (WARN_ON(ret))
+			break;
+	}
+
+	return ret;
+}
+
+int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	struct pkvm_mapping *mapping;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
+		__clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE);
+
+	return 0;
+}
+
+bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold)
+{
+	struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
+	pkvm_handle_t handle = kvm->arch.pkvm.handle;
+	struct pkvm_mapping *mapping;
+	bool young = false;
+
+	lockdep_assert_held(&kvm->mmu_lock);
+	for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
+		young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
+					   mkold);
+
+	return young;
+}
+
+int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot,
+				    enum kvm_pgtable_walk_flags flags)
+{
+	return kvm_call_hyp_nvhe(__pkvm_host_relax_perms_guest, addr >> PAGE_SHIFT, prot);
+}
+
+void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr,
+				 enum kvm_pgtable_walk_flags flags)
+{
+	WARN_ON(kvm_call_hyp_nvhe(__pkvm_host_mkyoung_guest, addr >> PAGE_SHIFT));
+}
+
+void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
+{
+	WARN_ON_ONCE(1);
+}
+
+kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level,
+					enum kvm_pgtable_prot prot, void *mc, bool force_pte)
+{
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			      struct kvm_mmu_memory_cache *mc)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 470524b31951..803e11b0dc8f 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -85,7 +85,7 @@ static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu)
 	 * KVM_REG_ARM64_SVE_VLS.  Allocation is deferred until
 	 * kvm_arm_vcpu_finalize(), which freezes the configuration.
 	 */
-	vcpu_set_flag(vcpu, GUEST_HAS_SVE);
+	set_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &vcpu->kvm->arch.flags);
 }
 
 /*
@@ -211,10 +211,6 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		kvm_vcpu_reset_sve(vcpu);
 	}
 
-	if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) ||
-	    vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC))
-		kvm_vcpu_enable_ptrauth(vcpu);
-
 	if (vcpu_el1_is_32bit(vcpu))
 		pstate = VCPU_RESET_PSTATE_SVC;
 	else if (vcpu_has_nv(vcpu))
diff --git a/arch/arm64/kvm/stacktrace.c b/arch/arm64/kvm/stacktrace.c
index 3ace5b75813b..af5eec681127 100644
--- a/arch/arm64/kvm/stacktrace.c
+++ b/arch/arm64/kvm/stacktrace.c
@@ -19,6 +19,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+#include <asm/kvm_mmu.h>
 #include <asm/stacktrace/nvhe.h>
 
 static struct stack_info stackinfo_get_overflow(void)
@@ -50,7 +51,7 @@ static struct stack_info stackinfo_get_hyp(void)
 	struct kvm_nvhe_stacktrace_info *stacktrace_info
 				= this_cpu_ptr_nvhe_sym(kvm_stacktrace_info);
 	unsigned long low = (unsigned long)stacktrace_info->stack_base;
-	unsigned long high = low + PAGE_SIZE;
+	unsigned long high = low + NVHE_STACK_SIZE;
 
 	return (struct stack_info) {
 		.low = low,
@@ -60,8 +61,8 @@ static struct stack_info stackinfo_get_hyp(void)
 
 static struct stack_info stackinfo_get_hyp_kern_va(void)
 {
-	unsigned long low = (unsigned long)*this_cpu_ptr(&kvm_arm_hyp_stack_page);
-	unsigned long high = low + PAGE_SIZE;
+	unsigned long low = (unsigned long)*this_cpu_ptr(&kvm_arm_hyp_stack_base);
+	unsigned long high = low + NVHE_STACK_SIZE;
 
 	return (struct stack_info) {
 		.low = low,
@@ -145,7 +146,7 @@ static void unwind(struct unwind_state *state,
  */
 static bool kvm_nvhe_dump_backtrace_entry(void *arg, unsigned long where)
 {
-	unsigned long va_mask = GENMASK_ULL(vabits_actual - 1, 0);
+	unsigned long va_mask = GENMASK_ULL(__hyp_va_bits - 1, 0);
 	unsigned long hyp_offset = (unsigned long)arg;
 
 	/* Mask tags and convert to kern addr */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e4749ecbcd79..82430c1e1dd0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -570,17 +570,10 @@ static bool trap_oslar_el1(struct kvm_vcpu *vcpu,
 			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	u64 oslsr;
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p, r);
 
-	/* Forward the OSLK bit to OSLSR */
-	oslsr = __vcpu_sys_reg(vcpu, OSLSR_EL1) & ~OSLSR_EL1_OSLK;
-	if (p->regval & OSLAR_EL1_OSLK)
-		oslsr |= OSLSR_EL1_OSLK;
-
-	__vcpu_sys_reg(vcpu, OSLSR_EL1) = oslsr;
+	kvm_debug_handle_oslar(vcpu, p->regval);
 	return true;
 }
 
@@ -621,43 +614,13 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
 	}
 }
 
-/*
- * We want to avoid world-switching all the DBG registers all the
- * time:
- *
- * - If we've touched any debug register, it is likely that we're
- *   going to touch more of them. It then makes sense to disable the
- *   traps and start doing the save/restore dance
- * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
- *   then mandatory to save/restore the registers, as the guest
- *   depends on them.
- *
- * For this, we use a DIRTY bit, indicating the guest has modified the
- * debug registers, used as follow:
- *
- * On guest entry:
- * - If the dirty bit is set (because we're coming back from trapping),
- *   disable the traps, save host registers, restore guest registers.
- * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
- *   set the dirty bit, disable the traps, save host registers,
- *   restore guest registers.
- * - Otherwise, enable the traps
- *
- * On guest exit:
- * - If the dirty bit is set, save guest registers, restore host
- *   registers and clear the dirty bit. This ensure that the host can
- *   now use the debug registers.
- */
 static bool trap_debug_regs(struct kvm_vcpu *vcpu,
 			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
 	access_rw(vcpu, p, r);
-	if (p->is_write)
-		vcpu_set_flag(vcpu, DEBUG_DIRTY);
-
-	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
 
+	kvm_debug_set_guest_ownership(vcpu);
 	return true;
 }
 
@@ -666,9 +629,6 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
  *
  * A 32 bit write to a debug register leave top bits alone
  * A 32 bit read from a debug register only returns the bottom bits
- *
- * All writes will set the DEBUG_DIRTY flag to ensure the hyp code
- * switches between host and guest values in future.
  */
 static void reg_to_dbg(struct kvm_vcpu *vcpu,
 		       struct sys_reg_params *p,
@@ -683,8 +643,6 @@ static void reg_to_dbg(struct kvm_vcpu *vcpu,
 	val &= ~mask;
 	val |= (p->regval & (mask >> shift)) << shift;
 	*dbg_reg = val;
-
-	vcpu_set_flag(vcpu, DEBUG_DIRTY);
 }
 
 static void dbg_to_reg(struct kvm_vcpu *vcpu,
@@ -698,152 +656,79 @@ static void dbg_to_reg(struct kvm_vcpu *vcpu,
 	p->regval = (*dbg_reg & mask) >> shift;
 }
 
-static bool trap_bvr(struct kvm_vcpu *vcpu,
-		     struct sys_reg_params *p,
-		     const struct sys_reg_desc *rd)
-{
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
-
-	if (p->is_write)
-		reg_to_dbg(vcpu, p, rd, dbg_reg);
-	else
-		dbg_to_reg(vcpu, p, rd, dbg_reg);
-
-	trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
-
-	return true;
-}
-
-static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 val)
+static u64 *demux_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd)
 {
-	vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = val;
-	return 0;
-}
+	struct kvm_guest_debug_arch *dbg = &vcpu->arch.vcpu_debug_state;
 
-static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 *val)
-{
-	*val = vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm];
-	return 0;
+	switch (rd->Op2) {
+	case 0b100:
+		return &dbg->dbg_bvr[rd->CRm];
+	case 0b101:
+		return &dbg->dbg_bcr[rd->CRm];
+	case 0b110:
+		return &dbg->dbg_wvr[rd->CRm];
+	case 0b111:
+		return &dbg->dbg_wcr[rd->CRm];
+	default:
+		KVM_BUG_ON(1, vcpu->kvm);
+		return NULL;
+	}
 }
 
-static u64 reset_bvr(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_desc *rd)
+static bool trap_dbg_wb_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+			    const struct sys_reg_desc *rd)
 {
-	vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val;
-	return rd->val;
-}
+	u64 *reg = demux_wb_reg(vcpu, rd);
 
-static bool trap_bcr(struct kvm_vcpu *vcpu,
-		     struct sys_reg_params *p,
-		     const struct sys_reg_desc *rd)
-{
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
+	if (!reg)
+		return false;
 
 	if (p->is_write)
-		reg_to_dbg(vcpu, p, rd, dbg_reg);
+		reg_to_dbg(vcpu, p, rd, reg);
 	else
-		dbg_to_reg(vcpu, p, rd, dbg_reg);
-
-	trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
+		dbg_to_reg(vcpu, p, rd, reg);
 
+	kvm_debug_set_guest_ownership(vcpu);
 	return true;
 }
 
-static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 val)
-{
-	vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = val;
-	return 0;
-}
-
-static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 *val)
+static int set_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+			  u64 val)
 {
-	*val = vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm];
-	return 0;
-}
+	u64 *reg = demux_wb_reg(vcpu, rd);
 
-static u64 reset_bcr(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_desc *rd)
-{
-	vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val;
-	return rd->val;
-}
-
-static bool trap_wvr(struct kvm_vcpu *vcpu,
-		     struct sys_reg_params *p,
-		     const struct sys_reg_desc *rd)
-{
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
-
-	if (p->is_write)
-		reg_to_dbg(vcpu, p, rd, dbg_reg);
-	else
-		dbg_to_reg(vcpu, p, rd, dbg_reg);
-
-	trace_trap_reg(__func__, rd->CRm, p->is_write,
-		vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]);
-
-	return true;
-}
-
-static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 val)
-{
-	vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = val;
-	return 0;
-}
+	if (!reg)
+		return -EINVAL;
 
-static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 *val)
-{
-	*val = vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm];
+	*reg = val;
 	return 0;
 }
 
-static u64 reset_wvr(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_desc *rd)
-{
-	vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val;
-	return rd->val;
-}
-
-static bool trap_wcr(struct kvm_vcpu *vcpu,
-		     struct sys_reg_params *p,
-		     const struct sys_reg_desc *rd)
+static int get_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+			  u64 *val)
 {
-	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
-
-	if (p->is_write)
-		reg_to_dbg(vcpu, p, rd, dbg_reg);
-	else
-		dbg_to_reg(vcpu, p, rd, dbg_reg);
+	u64 *reg = demux_wb_reg(vcpu, rd);
 
-	trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg);
-
-	return true;
-}
+	if (!reg)
+		return -EINVAL;
 
-static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 val)
-{
-	vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = val;
+	*val = *reg;
 	return 0;
 }
 
-static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
-		   u64 *val)
+static u64 reset_dbg_wb_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd)
 {
-	*val = vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm];
-	return 0;
-}
+	u64 *reg = demux_wb_reg(vcpu, rd);
 
-static u64 reset_wcr(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_desc *rd)
-{
-	vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val;
+	/*
+	 * Bail early if we couldn't find storage for the register, the
+	 * KVM_BUG_ON() in demux_wb_reg() will prevent this VM from ever
+	 * being run.
+	 */
+	if (!reg)
+		return 0;
+
+	*reg = rd->val;
 	return rd->val;
 }
 
@@ -1350,13 +1235,17 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
-	  trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr },		\
+	  trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0,			\
+	  get_dbg_wb_reg, set_dbg_wb_reg },				\
 	{ SYS_DESC(SYS_DBGBCRn_EL1(n)),					\
-	  trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr },		\
+	  trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0,			\
+	  get_dbg_wb_reg, set_dbg_wb_reg },				\
 	{ SYS_DESC(SYS_DBGWVRn_EL1(n)),					\
-	  trap_wvr, reset_wvr, 0, 0,  get_wvr, set_wvr },		\
+	  trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0,			\
+	  get_dbg_wb_reg, set_dbg_wb_reg },				\
 	{ SYS_DESC(SYS_DBGWCRn_EL1(n)),					\
-	  trap_wcr, reset_wcr, 0, 0,  get_wcr, set_wcr }
+	  trap_dbg_wb_reg, reset_dbg_wb_reg, 0, 0,			\
+	  get_dbg_wb_reg, set_dbg_wb_reg }
 
 #define PMU_SYS_REG(name)						\
 	SYS_DESC(SYS_##name), .reset = reset_pmu_reg,			\
@@ -1410,26 +1299,146 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 
 	switch (reg) {
 	case SYS_CNTP_TVAL_EL0:
+		if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
+	case SYS_CNTV_TVAL_EL0:
+		if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HVTIMER;
+		else
+			tmr = TIMER_VTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
 	case SYS_AARCH32_CNTP_TVAL:
+	case SYS_CNTP_TVAL_EL02:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_TVAL;
 		break;
+
+	case SYS_CNTV_TVAL_EL02:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
+	case SYS_CNTHP_TVAL_EL2:
+		tmr = TIMER_HPTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
+	case SYS_CNTHV_TVAL_EL2:
+		tmr = TIMER_HVTIMER;
+		treg = TIMER_REG_TVAL;
+		break;
+
 	case SYS_CNTP_CTL_EL0:
+		if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
+	case SYS_CNTV_CTL_EL0:
+		if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HVTIMER;
+		else
+			tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
 	case SYS_AARCH32_CNTP_CTL:
+	case SYS_CNTP_CTL_EL02:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_CTL;
 		break;
+
+	case SYS_CNTV_CTL_EL02:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
+	case SYS_CNTHP_CTL_EL2:
+		tmr = TIMER_HPTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
+	case SYS_CNTHV_CTL_EL2:
+		tmr = TIMER_HVTIMER;
+		treg = TIMER_REG_CTL;
+		break;
+
 	case SYS_CNTP_CVAL_EL0:
+		if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
+	case SYS_CNTV_CVAL_EL0:
+		if (is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu))
+			tmr = TIMER_HVTIMER;
+		else
+			tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
 	case SYS_AARCH32_CNTP_CVAL:
+	case SYS_CNTP_CVAL_EL02:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_CVAL;
 		break;
+
+	case SYS_CNTV_CVAL_EL02:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
+	case SYS_CNTHP_CVAL_EL2:
+		tmr = TIMER_HPTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
+	case SYS_CNTHV_CVAL_EL2:
+		tmr = TIMER_HVTIMER;
+		treg = TIMER_REG_CVAL;
+		break;
+
 	case SYS_CNTPCT_EL0:
 	case SYS_CNTPCTSS_EL0:
+		if (is_hyp_ctxt(vcpu))
+			tmr = TIMER_HPTIMER;
+		else
+			tmr = TIMER_PTIMER;
+		treg = TIMER_REG_CNT;
+		break;
+
 	case SYS_AARCH32_CNTPCT:
+	case SYS_AARCH32_CNTPCTSS:
 		tmr = TIMER_PTIMER;
 		treg = TIMER_REG_CNT;
 		break;
+
+	case SYS_CNTVCT_EL0:
+	case SYS_CNTVCTSS_EL0:
+		if (is_hyp_ctxt(vcpu))
+			tmr = TIMER_HVTIMER;
+		else
+			tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CNT;
+		break;
+
+	case SYS_AARCH32_CNTVCT:
+	case SYS_AARCH32_CNTVCTSS:
+		tmr = TIMER_VTIMER;
+		treg = TIMER_REG_CNT;
+		break;
+
 	default:
 		print_sys_reg_msg(p, "%s", "Unhandled trapped timer register");
 		return undef_access(vcpu, p, r);
@@ -1443,6 +1452,16 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static bool access_hv_timer(struct kvm_vcpu *vcpu,
+			    struct sys_reg_params *p,
+			    const struct sys_reg_desc *r)
+{
+	if (!vcpu_el2_e2h_is_set(vcpu))
+		return undef_access(vcpu, p, r);
+
+	return access_arch_timer(vcpu, p, r);
+}
+
 static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp,
 				    s64 new, s64 cur)
 {
@@ -1599,7 +1618,8 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		if (!vcpu_has_ptrauth(vcpu))
 			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) |
 				 ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3));
-		if (!cpus_have_final_cap(ARM64_HAS_WFXT))
+		if (!cpus_have_final_cap(ARM64_HAS_WFXT) ||
+		    has_broken_cntvoff())
 			val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT);
 		break;
 	case SYS_ID_AA64ISAR3_EL1:
@@ -1807,6 +1827,9 @@ static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 	/* Hide SPE from guests */
 	val &= ~ID_AA64DFR0_EL1_PMSVer_MASK;
 
+	/* Hide BRBE from guests */
+	val &= ~ID_AA64DFR0_EL1_BRBE_MASK;
+
 	return val;
 }
 
@@ -2924,11 +2947,17 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	AMU_AMEVTYPER1_EL0(15),
 
 	{ SYS_DESC(SYS_CNTPCT_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTVCT_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTPCTSS_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTVCTSS_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
 	{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
 
+	{ SYS_DESC(SYS_CNTV_TVAL_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTV_CTL_EL0), access_arch_timer },
+	{ SYS_DESC(SYS_CNTV_CVAL_EL0), access_arch_timer },
+
 	/* PMEVCNTRn_EL0 */
 	PMU_PMEVCNTR_EL0(0),
 	PMU_PMEVCNTR_EL0(1),
@@ -3080,9 +3109,24 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	EL2_REG_VNCR(CNTVOFF_EL2, reset_val, 0),
 	EL2_REG(CNTHCTL_EL2, access_rw, reset_val, 0),
+	{ SYS_DESC(SYS_CNTHP_TVAL_EL2), access_arch_timer },
+	EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0),
+	EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0),
+
+	{ SYS_DESC(SYS_CNTHV_TVAL_EL2), access_hv_timer },
+	EL2_REG(CNTHV_CTL_EL2, access_hv_timer, reset_val, 0),
+	EL2_REG(CNTHV_CVAL_EL2, access_hv_timer, reset_val, 0),
 
 	{ SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 },
 
+	{ SYS_DESC(SYS_CNTP_TVAL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CTL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTP_CVAL_EL02), access_arch_timer },
+
+	{ SYS_DESC(SYS_CNTV_TVAL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTV_CTL_EL02), access_arch_timer },
+	{ SYS_DESC(SYS_CNTV_CVAL_EL02), access_arch_timer },
+
 	EL2_REG(SP_EL2, NULL, reset_unknown, 0),
 };
 
@@ -3594,18 +3638,20 @@ static bool trap_dbgdidr(struct kvm_vcpu *vcpu,
  * None of the other registers share their location, so treat them as
  * if they were 64bit.
  */
-#define DBG_BCR_BVR_WCR_WVR(n)						      \
-	/* DBGBVRn */							      \
-	{ AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, \
-	/* DBGBCRn */							      \
-	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n },	      \
-	/* DBGWVRn */							      \
-	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n },	      \
-	/* DBGWCRn */							      \
-	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_wcr, NULL, n }
-
-#define DBGBXVR(n)							      \
-	{ AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_bvr, NULL, n }
+#define DBG_BCR_BVR_WCR_WVR(n)							\
+	/* DBGBVRn */								\
+	{ AA32(LO), Op1( 0), CRn( 0), CRm((n)), Op2( 4),			\
+	  trap_dbg_wb_reg, NULL, n },						\
+	/* DBGBCRn */								\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_dbg_wb_reg, NULL, n },	\
+	/* DBGWVRn */								\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_dbg_wb_reg, NULL, n },	\
+	/* DBGWCRn */								\
+	{ Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_dbg_wb_reg, NULL, n }
+
+#define DBGBXVR(n)								\
+	{ AA32(HI), Op1( 0), CRn( 1), CRm((n)), Op2( 1),			\
+	  trap_dbg_wb_reg, NULL, n }
 
 /*
  * Trapped cp14 registers. We generally ignore most of the external
@@ -3902,9 +3948,11 @@ static const struct sys_reg_desc cp15_64_regs[] = {
 	{ SYS_DESC(SYS_AARCH32_CNTPCT),	      access_arch_timer },
 	{ Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 },
 	{ Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */
+	{ SYS_DESC(SYS_AARCH32_CNTVCT),	      access_arch_timer },
 	{ Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */
 	{ SYS_DESC(SYS_AARCH32_CNTP_CVAL),    access_arch_timer },
 	{ SYS_DESC(SYS_AARCH32_CNTPCTSS),     access_arch_timer },
+	{ SYS_DESC(SYS_AARCH32_CNTVCTSS),     access_arch_timer },
 };
 
 static bool check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
@@ -4419,6 +4467,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 			reset_vcpu_ftr_id_reg(vcpu, r);
 		else
 			r->reset(vcpu, r);
+
+		if (r->reg >= __SANITISED_REG_START__ && r->reg < NR_SYS_REGS)
+			(void)__vcpu_sys_reg(vcpu, r->reg);
 	}
 
 	set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);
@@ -4995,6 +5046,14 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
 		kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 |
 						  HAFGRTR_EL2_RES1);
 
+	if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) {
+		kvm->arch.fgu[HDFGRTR_GROUP] |= (HDFGRTR_EL2_nBRBDATA  |
+						 HDFGRTR_EL2_nBRBCTL   |
+						 HDFGRTR_EL2_nBRBIDR);
+		kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_nBRBINJ |
+						HFGITR_EL2_nBRBIALL);
+	}
+
 	set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags);
 out:
 	mutex_unlock(&kvm->arch.config_lock);
@@ -5022,7 +5081,7 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu)
 	}
 
 	if (vcpu_has_nv(vcpu)) {
-		int ret = kvm_init_nv_sysregs(kvm);
+		int ret = kvm_init_nv_sysregs(vcpu);
 		if (ret)
 			return ret;
 	}
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 064a58c19f48..f85415db7713 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -46,38 +46,6 @@ TRACE_EVENT(kvm_hvc_arm64,
 		  __entry->vcpu_pc, __entry->r0, __entry->imm)
 );
 
-TRACE_EVENT(kvm_arm_setup_debug,
-	TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug),
-	TP_ARGS(vcpu, guest_debug),
-
-	TP_STRUCT__entry(
-		__field(struct kvm_vcpu *, vcpu)
-		__field(__u32, guest_debug)
-	),
-
-	TP_fast_assign(
-		__entry->vcpu = vcpu;
-		__entry->guest_debug = guest_debug;
-	),
-
-	TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug)
-);
-
-TRACE_EVENT(kvm_arm_clear_debug,
-	TP_PROTO(__u32 guest_debug),
-	TP_ARGS(guest_debug),
-
-	TP_STRUCT__entry(
-		__field(__u32, guest_debug)
-	),
-
-	TP_fast_assign(
-		__entry->guest_debug = guest_debug;
-	),
-
-	TP_printk("flags: 0x%08x", __entry->guest_debug)
-);
-
 /*
  * The dreg32 name is a leftover from a distant past. This will really
  * output a 64bit value...
@@ -99,49 +67,6 @@ TRACE_EVENT(kvm_arm_set_dreg32,
 	TP_printk("%s: 0x%llx", __entry->name, __entry->value)
 );
 
-TRACE_DEFINE_SIZEOF(__u64);
-
-TRACE_EVENT(kvm_arm_set_regset,
-	TP_PROTO(const char *type, int len, __u64 *control, __u64 *value),
-	TP_ARGS(type, len, control, value),
-	TP_STRUCT__entry(
-		__field(const char *, name)
-		__field(int, len)
-		__array(u64, ctrls, 16)
-		__array(u64, values, 16)
-	),
-	TP_fast_assign(
-		__entry->name = type;
-		__entry->len = len;
-		memcpy(__entry->ctrls, control, len << 3);
-		memcpy(__entry->values, value, len << 3);
-	),
-	TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name,
-		__print_array(__entry->ctrls, __entry->len, sizeof(__u64)),
-		__print_array(__entry->values, __entry->len, sizeof(__u64)))
-);
-
-TRACE_EVENT(trap_reg,
-	TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value),
-	TP_ARGS(fn, reg, is_write, write_value),
-
-	TP_STRUCT__entry(
-		__field(const char *, fn)
-		__field(int, reg)
-		__field(bool, is_write)
-		__field(u64, write_value)
-	),
-
-	TP_fast_assign(
-		__entry->fn = fn;
-		__entry->reg = reg;
-		__entry->is_write = is_write;
-		__entry->write_value = write_value;
-	),
-
-	TP_printk("%s %s reg %d (0x%016llx)", __entry->fn,  __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value)
-);
-
 TRACE_EVENT(kvm_handle_sys_reg,
 	TP_PROTO(unsigned long hsr),
 	TP_ARGS(hsr),
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index f267bc2486a1..d7233ab982d0 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -6,6 +6,7 @@
 #include <linux/kstrtox.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <linux/string_choices.h>
 #include <kvm/arm_vgic.h>
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_mmu.h>
@@ -663,9 +664,9 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
 	if (info->has_v4) {
 		kvm_vgic_global_state.has_gicv4 = gicv4_enable;
 		kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable;
-		kvm_info("GICv4%s support %sabled\n",
+		kvm_info("GICv4%s support %s\n",
 			 kvm_vgic_global_state.has_gicv4_1 ? ".1" : "",
-			 gicv4_enable ? "en" : "dis");
+			 str_enabled_disabled(gicv4_enable));
 	}
 
 	kvm_vgic_global_state.vcpu_base = 0;
@@ -734,7 +735,8 @@ void vgic_v3_load(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
+	if (likely(!is_protected_kvm_enabled()))
+		kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if);
 
 	if (has_vhe())
 		__vgic_v3_activate_traps(cpu_if);
@@ -746,7 +748,8 @@ void vgic_v3_put(struct kvm_vcpu *vcpu)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
 
-	kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
+	if (likely(!is_protected_kvm_enabled()))
+		kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if);
 	WARN_ON(vgic_v4_put(vcpu));
 
 	if (has_vhe())
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 0c501cabc238..8160cff35089 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -33,7 +33,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	gfp_t gfp = GFP_PGTABLE_USER;
 
 	if (pgdir_is_page_size())
-		return (pgd_t *)__get_free_page(gfp);
+		return __pgd_alloc(mm, 0);
 	else
 		return kmem_cache_alloc(pgd_cache, gfp);
 }
@@ -41,7 +41,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	if (pgdir_is_page_size())
-		free_page((unsigned long)pgd);
+		__pgd_free(mm, pgd);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index eb17f59e543c..1e65f2fb45bd 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -105,6 +105,7 @@ WORKAROUND_CLEAN_CACHE
 WORKAROUND_DEVICE_LOAD_ACQUIRE
 WORKAROUND_NVIDIA_CARMEL_CNP
 WORKAROUND_QCOM_FALKOR_E1003
+WORKAROUND_QCOM_ORYON_CNTVOFF
 WORKAROUND_REPEAT_TLBI
 WORKAROUND_SPECULATIVE_AT
 WORKAROUND_SPECULATIVE_SSBS
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 94ca9cdb0b16..762ee084b37c 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -2064,6 +2064,18 @@ Field	17:16	ZEN
 Res0	15:0
 EndSysreg
 
+Sysreg	TRFCR_EL1	3	0	1	2	1
+Res0	63:7
+UnsignedEnum	6:5	TS
+	0b0001	VIRTUAL
+	0b0010	GUEST_PHYSICAL
+	0b0011	PHYSICAL
+EndEnum
+Res0	4:2
+Field	1	ExTRE
+Field	0	E0TRE
+EndSysregFields
+
 Sysreg	SMPRI_EL1	3	0	1	2	4
 Res0	63:4
 Field	3:0	PRIORITY
@@ -2613,6 +2625,22 @@ Field	1	ICIALLU
 Field	0	ICIALLUIS
 EndSysreg
 
+Sysreg TRFCR_EL2	3	4	1	2	1
+Res0	63:7
+UnsignedEnum	6:5	TS
+	0b0000	USE_TRFCR_EL1_TS
+	0b0001	VIRTUAL
+	0b0010	GUEST_PHYSICAL
+	0b0011	PHYSICAL
+EndEnum
+Res0	4
+Field	3	CX
+Res0	2
+Field	1	E2TRE
+Field	0	E0HTRE
+EndSysreg
+
+
 Sysreg HDFGRTR_EL2	3	4	3	1	4
 Field	63	PMBIDR_EL1
 Field	62	nPMSNEVFR_EL1
@@ -3023,6 +3051,10 @@ Sysreg	ZCR_EL12	3	5	1	2	0
 Mapping	ZCR_EL1
 EndSysreg
 
+Sysreg	TRFCR_EL12	3	5	1	2	1
+Mapping	TRFCR_EL1
+EndSysreg
+
 Sysreg	SMCR_EL12	3	5	1	2	6
 Mapping	SMCR_EL1
 EndSysreg
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index 9c84c9012e53..bf8400c28b5a 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -44,7 +44,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 	pgd_t *ret;
 	pgd_t *init;
 
-	ret = (pgd_t *) __get_free_page(GFP_KERNEL);
+	ret = __pgd_alloc(mm, 0);
 	if (ret) {
 		init = pgd_offset(&init_mm, 0UL);
 		pgd_init((unsigned long *)ret);
@@ -63,7 +63,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 #define __pte_free_tlb(tlb, pte, address)		\
 do {							\
-	pagetable_pte_dtor(page_ptdesc(pte));		\
+	pagetable_dtor(page_ptdesc(pte));		\
 	tlb_remove_page_ptdesc(tlb, page_ptdesc(pte));	\
 } while (0)
 
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index bf6cf5579cf4..9c58fb81f7fd 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -56,7 +56,7 @@ __arch_xchg(unsigned long x, volatile void *ptr, int size)
 	__typeof__(ptr) __ptr = (ptr);				\
 	__typeof__(*(ptr)) __old = (old);			\
 	__typeof__(*(ptr)) __new = (new);			\
-	__typeof__(*(ptr)) __oldval = 0;			\
+	__typeof__(*(ptr)) __oldval = (__typeof__(*(ptr))) 0;	\
 								\
 	asm volatile(						\
 		"1:	%0 = memw_locked(%1);\n"		\
diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h
index 55988625e6fb..1ee5f5f157ca 100644
--- a/arch/hexagon/include/asm/pgalloc.h
+++ b/arch/hexagon/include/asm/pgalloc.h
@@ -22,7 +22,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 
-	pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	pgd = __pgd_alloc(mm, 0);
 
 	/*
 	 * There may be better ways to do this, but to ensure
@@ -89,7 +89,7 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 do {								\
-	pagetable_pte_dtor((page_ptdesc(pte)));			\
+	pagetable_dtor((page_ptdesc(pte)));			\
 	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
 } while (0)
 
diff --git a/arch/hexagon/include/asm/setup.h b/arch/hexagon/include/asm/setup.h
new file mode 100644
index 000000000000..9f2749cd4052
--- /dev/null
+++ b/arch/hexagon/include/asm/setup.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_HEXAGON_SETUP_H
+#define _ASM_HEXAGON_SETUP_H
+
+#include <linux/init.h>
+#include <uapi/asm/setup.h>
+
+extern char external_cmdline_buffer;
+
+void __init setup_arch_memory(void);
+
+#endif
diff --git a/arch/hexagon/include/uapi/asm/setup.h b/arch/hexagon/include/uapi/asm/setup.h
index 8ce9428b1583..598f74f671f6 100644
--- a/arch/hexagon/include/uapi/asm/setup.h
+++ b/arch/hexagon/include/uapi/asm/setup.h
@@ -17,19 +17,9 @@
  * 02110-1301, USA.
  */
 
-#ifndef _ASM_SETUP_H
-#define _ASM_SETUP_H
-
-#ifdef __KERNEL__
-#include <linux/init.h>
-#else
-#define __init
-#endif
+#ifndef _UAPI_ASM_HEXAGON_SETUP_H
+#define _UAPI_ASM_HEXAGON_SETUP_H
 
 #include <asm-generic/setup.h>
 
-extern char external_cmdline_buffer;
-
-void __init setup_arch_memory(void);
-
 #endif
diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c
index f0f207e2a694..6f851e1cd4ee 100644
--- a/arch/hexagon/kernel/time.c
+++ b/arch/hexagon/kernel/time.c
@@ -170,8 +170,7 @@ static void __init time_init_deferred(void)
 
 	ce_dev->cpumask = cpu_all_mask;
 
-	if (!resource)
-		resource = rtos_timer_device.resource;
+	resource = rtos_timer_device.resource;
 
 	/*  ioremap here means this has to run later, after paging init  */
 	rtos_timer = ioremap(resource->start, resource_size(resource));
diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c
index 75e062722d28..e732aa01c2ff 100644
--- a/arch/hexagon/kernel/traps.c
+++ b/arch/hexagon/kernel/traps.c
@@ -135,7 +135,7 @@ static void do_show_stack(struct task_struct *task, unsigned long *fp,
 		}
 
 		/* Attempt to continue past exception. */
-		if (0 == newfp) {
+		if (!newfp) {
 			struct pt_regs *regs = (struct pt_regs *) (((void *)fp)
 						+ 8);
 
@@ -195,8 +195,10 @@ int die(const char *str, struct pt_regs *regs, long err)
 	printk(KERN_EMERG "Oops: %s[#%d]:\n", str, ++die.counter);
 
 	if (notify_die(DIE_OOPS, str, regs, err, pt_cause(regs), SIGSEGV) ==
-	    NOTIFY_STOP)
+	    NOTIFY_STOP) {
+		spin_unlock_irq(&die.lock);
 		return 1;
+	}
 
 	print_modules();
 	show_regs(regs);
diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index bfa21465d83a..beb8499dd8ed 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -4,7 +4,6 @@ obj-y += net/
 obj-y += vdso/
 
 obj-$(CONFIG_KVM) += kvm/
-obj-$(CONFIG_BUILTIN_DTB) += boot/dts/
 
 # for cleaning
 subdir- += boot
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 22b531f45ffa..2b8bd27a852f 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -249,7 +249,7 @@ config MACH_LOONGSON64
 	def_bool 64BIT
 
 config FIX_EARLYCON_MEM
-	def_bool y
+	def_bool !ARCH_IOREMAP
 
 config PGTABLE_2LEVEL
 	bool
@@ -400,6 +400,7 @@ endchoice
 config BUILTIN_DTB
 	bool "Enable built-in dtb in kernel"
 	depends on OF
+	select GENERIC_BUILTIN_DTB
 	help
 	  Some existing systems do not provide a canonical device tree to
 	  the kernel at boot time. Let's provide a device tree table in the
diff --git a/arch/loongarch/boot/dts/Makefile b/arch/loongarch/boot/dts/Makefile
index 747d0c3f6389..15d5e14fe418 100644
--- a/arch/loongarch/boot/dts/Makefile
+++ b/arch/loongarch/boot/dts/Makefile
@@ -1,5 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 dtb-y = loongson-2k0500-ref.dtb loongson-2k1000-ref.dtb loongson-2k2000-ref.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index a3d513919484..73c77500ac46 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -113,7 +113,10 @@ CONFIG_ZBUD=y
 CONFIG_ZSMALLOC=m
 # CONFIG_COMPAT_BRK is not set
 CONFIG_MEMORY_HOTPLUG=y
-CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y
+# CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE is not set
+CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO=y
+# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL is not set
+# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE is not set
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
diff --git a/arch/loongarch/include/asm/cpu-info.h b/arch/loongarch/include/asm/cpu-info.h
index 900589cb159d..35e0a230a484 100644
--- a/arch/loongarch/include/asm/cpu-info.h
+++ b/arch/loongarch/include/asm/cpu-info.h
@@ -57,6 +57,7 @@ struct cpuinfo_loongarch {
 	int			global_id; /* physical global thread number */
 	int			vabits; /* Virtual Address size in bits */
 	int			pabits; /* Physical Address size in bits */
+	int			timerbits; /* Width of arch timer in bits */
 	unsigned int		ksave_mask; /* Usable KSave mask. */
 	unsigned int		watch_dreg_count;   /* Number data breakpoints */
 	unsigned int		watch_ireg_count;   /* Number instruction breakpoints */
diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h
index d78330916bd1..13b2462f3d8c 100644
--- a/arch/loongarch/include/asm/hw_breakpoint.h
+++ b/arch/loongarch/include/asm/hw_breakpoint.h
@@ -38,8 +38,8 @@ struct arch_hw_breakpoint {
  * Limits.
  * Changing these will require modifications to the register accessors.
  */
-#define LOONGARCH_MAX_BRP		8
-#define LOONGARCH_MAX_WRP		8
+#define LOONGARCH_MAX_BRP		14
+#define LOONGARCH_MAX_WRP		14
 
 /* Virtual debug register bases. */
 #define CSR_CFG_ADDR	0
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 64ad277e096e..52651aa0e583 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -108,6 +108,12 @@
 #define  CPUCFG3_SPW_HG_HF		BIT(11)
 #define  CPUCFG3_RVA			BIT(12)
 #define  CPUCFG3_RVAMAX			GENMASK(16, 13)
+#define  CPUCFG3_ALDORDER_CAP		BIT(18) /* All address load ordered, capability */
+#define  CPUCFG3_ASTORDER_CAP		BIT(19) /* All address store ordered, capability */
+#define  CPUCFG3_ALDORDER_STA		BIT(20) /* All address load ordered, status */
+#define  CPUCFG3_ASTORDER_STA		BIT(21) /* All address store ordered, status */
+#define  CPUCFG3_SLDORDER_CAP		BIT(22) /* Same address load ordered, capability */
+#define  CPUCFG3_SLDORDER_STA		BIT(23) /* Same address load ordered, status */
 
 #define LOONGARCH_CPUCFG4		0x4
 #define  CPUCFG4_CCFREQ			GENMASK(31, 0)
@@ -466,7 +472,6 @@
 
 #define LOONGARCH_CSR_TCFG		0x41	/* Timer config */
 #define  CSR_TCFG_VAL_SHIFT		2
-#define	 CSR_TCFG_VAL_WIDTH		48
 #define  CSR_TCFG_VAL			(_ULCAST_(0x3fffffffffff) << CSR_TCFG_VAL_SHIFT)
 #define  CSR_TCFG_PERIOD_SHIFT		1
 #define  CSR_TCFG_PERIOD		(_ULCAST_(0x1) << CSR_TCFG_PERIOD_SHIFT)
@@ -566,6 +571,15 @@
 
 /* Implement dependent */
 #define LOONGARCH_CSR_IMPCTL1		0x80	/* Loongson config1 */
+#define  CSR_LDSTORDER_SHIFT		28
+#define  CSR_LDSTORDER_WIDTH		3
+#define  CSR_LDSTORDER_MASK		(_ULCAST_(0x7) << CSR_LDSTORDER_SHIFT)
+#define  CSR_LDSTORDER_NLD_NST		(_ULCAST_(0x0) << CSR_LDSTORDER_SHIFT) /* 000 = No Load No Store */
+#define  CSR_LDSTORDER_ALD_NST		(_ULCAST_(0x1) << CSR_LDSTORDER_SHIFT) /* 001 = All Load No Store */
+#define  CSR_LDSTORDER_SLD_NST		(_ULCAST_(0x3) << CSR_LDSTORDER_SHIFT) /* 011 = Same Load No Store */
+#define  CSR_LDSTORDER_NLD_AST		(_ULCAST_(0x4) << CSR_LDSTORDER_SHIFT) /* 100 = No Load All Store */
+#define  CSR_LDSTORDER_ALD_AST		(_ULCAST_(0x5) << CSR_LDSTORDER_SHIFT) /* 101 = All Load All Store */
+#define  CSR_LDSTORDER_SLD_AST		(_ULCAST_(0x7) << CSR_LDSTORDER_SHIFT) /* 111 = Same Load All Store */
 #define  CSR_MISPEC_SHIFT		20
 #define  CSR_MISPEC_WIDTH		8
 #define  CSR_MISPEC			(_ULCAST_(0xff) << CSR_MISPEC_SHIFT)
@@ -959,6 +973,36 @@
 #define LOONGARCH_CSR_DB7CTRL		0x34a	/* data breakpoint 7 control */
 #define LOONGARCH_CSR_DB7ASID		0x34b	/* data breakpoint 7 asid */
 
+#define LOONGARCH_CSR_DB8ADDR		0x350	/* data breakpoint 8 address */
+#define LOONGARCH_CSR_DB8MASK		0x351	/* data breakpoint 8 mask */
+#define LOONGARCH_CSR_DB8CTRL		0x352	/* data breakpoint 8 control */
+#define LOONGARCH_CSR_DB8ASID		0x353	/* data breakpoint 8 asid */
+
+#define LOONGARCH_CSR_DB9ADDR		0x358	/* data breakpoint 9 address */
+#define LOONGARCH_CSR_DB9MASK		0x359	/* data breakpoint 9 mask */
+#define LOONGARCH_CSR_DB9CTRL		0x35a	/* data breakpoint 9 control */
+#define LOONGARCH_CSR_DB9ASID		0x35b	/* data breakpoint 9 asid */
+
+#define LOONGARCH_CSR_DB10ADDR		0x360	/* data breakpoint 10 address */
+#define LOONGARCH_CSR_DB10MASK		0x361	/* data breakpoint 10 mask */
+#define LOONGARCH_CSR_DB10CTRL		0x362	/* data breakpoint 10 control */
+#define LOONGARCH_CSR_DB10ASID		0x363	/* data breakpoint 10 asid */
+
+#define LOONGARCH_CSR_DB11ADDR		0x368	/* data breakpoint 11 address */
+#define LOONGARCH_CSR_DB11MASK		0x369	/* data breakpoint 11 mask */
+#define LOONGARCH_CSR_DB11CTRL		0x36a	/* data breakpoint 11 control */
+#define LOONGARCH_CSR_DB11ASID		0x36b	/* data breakpoint 11 asid */
+
+#define LOONGARCH_CSR_DB12ADDR		0x370	/* data breakpoint 12 address */
+#define LOONGARCH_CSR_DB12MASK		0x371	/* data breakpoint 12 mask */
+#define LOONGARCH_CSR_DB12CTRL		0x372	/* data breakpoint 12 control */
+#define LOONGARCH_CSR_DB12ASID		0x373	/* data breakpoint 12 asid */
+
+#define LOONGARCH_CSR_DB13ADDR		0x378	/* data breakpoint 13 address */
+#define LOONGARCH_CSR_DB13MASK		0x379	/* data breakpoint 13 mask */
+#define LOONGARCH_CSR_DB13CTRL		0x37a	/* data breakpoint 13 control */
+#define LOONGARCH_CSR_DB13ASID		0x37b	/* data breakpoint 13 asid */
+
 #define LOONGARCH_CSR_FWPC		0x380	/* instruction breakpoint config */
 #define LOONGARCH_CSR_FWPS		0x381	/* instruction breakpoint status */
 
@@ -1002,6 +1046,36 @@
 #define LOONGARCH_CSR_IB7CTRL		0x3ca	/* inst breakpoint 7 control */
 #define LOONGARCH_CSR_IB7ASID		0x3cb	/* inst breakpoint 7 asid */
 
+#define LOONGARCH_CSR_IB8ADDR		0x3d0	/* inst breakpoint 8 address */
+#define LOONGARCH_CSR_IB8MASK		0x3d1	/* inst breakpoint 8 mask */
+#define LOONGARCH_CSR_IB8CTRL		0x3d2	/* inst breakpoint 8 control */
+#define LOONGARCH_CSR_IB8ASID		0x3d3	/* inst breakpoint 8 asid */
+
+#define LOONGARCH_CSR_IB9ADDR		0x3d8	/* inst breakpoint 9 address */
+#define LOONGARCH_CSR_IB9MASK		0x3d9	/* inst breakpoint 9 mask */
+#define LOONGARCH_CSR_IB9CTRL		0x3da	/* inst breakpoint 9 control */
+#define LOONGARCH_CSR_IB9ASID		0x3db	/* inst breakpoint 9 asid */
+
+#define LOONGARCH_CSR_IB10ADDR		0x3e0	/* inst breakpoint 10 address */
+#define LOONGARCH_CSR_IB10MASK		0x3e1	/* inst breakpoint 10 mask */
+#define LOONGARCH_CSR_IB10CTRL		0x3e2	/* inst breakpoint 10 control */
+#define LOONGARCH_CSR_IB10ASID		0x3e3	/* inst breakpoint 10 asid */
+
+#define LOONGARCH_CSR_IB11ADDR		0x3e8	/* inst breakpoint 11 address */
+#define LOONGARCH_CSR_IB11MASK		0x3e9	/* inst breakpoint 11 mask */
+#define LOONGARCH_CSR_IB11CTRL		0x3ea	/* inst breakpoint 11 control */
+#define LOONGARCH_CSR_IB11ASID		0x3eb	/* inst breakpoint 11 asid */
+
+#define LOONGARCH_CSR_IB12ADDR		0x3f0	/* inst breakpoint 12 address */
+#define LOONGARCH_CSR_IB12MASK		0x3f1	/* inst breakpoint 12 mask */
+#define LOONGARCH_CSR_IB12CTRL		0x3f2	/* inst breakpoint 12 control */
+#define LOONGARCH_CSR_IB12ASID		0x3f3	/* inst breakpoint 12 asid */
+
+#define LOONGARCH_CSR_IB13ADDR		0x3f8	/* inst breakpoint 13 address */
+#define LOONGARCH_CSR_IB13MASK		0x3f9	/* inst breakpoint 13 mask */
+#define LOONGARCH_CSR_IB13CTRL		0x3fa	/* inst breakpoint 13 control */
+#define LOONGARCH_CSR_IB13ASID		0x3fb	/* inst breakpoint 13 asid */
+
 #define LOONGARCH_CSR_DEBUG		0x500	/* debug config */
 #define LOONGARCH_CSR_DERA		0x501	/* debug era */
 #define LOONGARCH_CSR_DESAVE		0x502	/* debug save */
diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index a7b9c9e73593..7211dff8c969 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -57,7 +57,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 
 #define __pte_free_tlb(tlb, pte, address)			\
 do {								\
-	pagetable_pte_dtor(page_ptdesc(pte));			\
+	pagetable_dtor(page_ptdesc(pte));			\
 	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
 } while (0)
 
diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h
index 82cd3a9f094b..45bfc65a0c9f 100644
--- a/arch/loongarch/include/asm/pgtable-bits.h
+++ b/arch/loongarch/include/asm/pgtable-bits.h
@@ -96,6 +96,13 @@
 
 #define _PAGE_IOREMAP		pgprot_val(PAGE_KERNEL_SUC)
 
+#define pgprot_nx pgprot_nx
+
+static inline pgprot_t pgprot_nx(pgprot_t _prot)
+{
+	return __pgprot(pgprot_val(_prot) | _PAGE_NO_EXEC);
+}
+
 #define pgprot_noncached pgprot_noncached
 
 static inline pgprot_t pgprot_noncached(pgprot_t _prot)
diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h
index ac915f841650..aafb3cd9e943 100644
--- a/arch/loongarch/include/uapi/asm/ptrace.h
+++ b/arch/loongarch/include/uapi/asm/ptrace.h
@@ -72,6 +72,16 @@ struct user_watch_state {
 	} dbg_regs[8];
 };
 
+struct user_watch_state_v2 {
+	uint64_t dbg_info;
+	struct {
+		uint64_t    addr;
+		uint64_t    mask;
+		uint32_t    ctrl;
+		uint32_t    pad;
+	} dbg_regs[14];
+};
+
 #define PTRACE_SYSEMU			0x1f
 #define PTRACE_SYSEMU_SINGLESTEP	0x20
 
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 9497968ee158..4853e8b04c6f 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -10,7 +10,7 @@ extra-y		:= vmlinux.lds
 obj-y		+= head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
 		   traps.o irq.o idle.o process.o dma.o mem.o reset.o switch.o \
 		   elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \
-		   alternative.o unwind.o
+		   alternative.o kdebugfs.o unwind.o
 
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-$(CONFIG_EFI) 		+= efi.o
diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c
index c7988f757281..8e231b0d2cd6 100644
--- a/arch/loongarch/kernel/cacheinfo.c
+++ b/arch/loongarch/kernel/cacheinfo.c
@@ -51,6 +51,12 @@ static void cache_cpumap_setup(unsigned int cpu)
 				continue;
 
 			sib_leaf = sib_cpu_ci->info_list + index;
+			/* SMT cores share all caches */
+			if (cpus_are_siblings(i, cpu)) {
+				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
+				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+			}
+			/* Node's cores share shared caches */
 			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
 				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
 				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c
index cbce099037b2..fedaa67cde41 100644
--- a/arch/loongarch/kernel/cpu-probe.c
+++ b/arch/loongarch/kernel/cpu-probe.c
@@ -190,6 +190,7 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 	set_cpu_asid_mask(c, asid_mask);
 
 	config = read_csr_prcfg1();
+	c->timerbits = (config & CSR_CONF1_TMRBITS) >> CSR_CONF1_TMRBITS_SHIFT;
 	c->ksave_mask = GENMASK((config & CSR_CONF1_KSNUM) - 1, 0);
 	c->ksave_mask &= ~(EXC_KSAVE_MASK | PERCPU_KSAVE_MASK | KVM_KSAVE_MASK);
 
diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c
index a6e4b605bfa8..c35f9bf38033 100644
--- a/arch/loongarch/kernel/hw_breakpoint.c
+++ b/arch/loongarch/kernel/hw_breakpoint.c
@@ -51,7 +51,13 @@ int hw_breakpoint_slots(int type)
 	READ_WB_REG_CASE(OFF, 4, REG, T, VAL);		\
 	READ_WB_REG_CASE(OFF, 5, REG, T, VAL);		\
 	READ_WB_REG_CASE(OFF, 6, REG, T, VAL);		\
-	READ_WB_REG_CASE(OFF, 7, REG, T, VAL);
+	READ_WB_REG_CASE(OFF, 7, REG, T, VAL);		\
+	READ_WB_REG_CASE(OFF, 8, REG, T, VAL);		\
+	READ_WB_REG_CASE(OFF, 9, REG, T, VAL);		\
+	READ_WB_REG_CASE(OFF, 10, REG, T, VAL);		\
+	READ_WB_REG_CASE(OFF, 11, REG, T, VAL);		\
+	READ_WB_REG_CASE(OFF, 12, REG, T, VAL);		\
+	READ_WB_REG_CASE(OFF, 13, REG, T, VAL);
 
 #define GEN_WRITE_WB_REG_CASES(OFF, REG, T, VAL)	\
 	WRITE_WB_REG_CASE(OFF, 0, REG, T, VAL);		\
@@ -61,7 +67,13 @@ int hw_breakpoint_slots(int type)
 	WRITE_WB_REG_CASE(OFF, 4, REG, T, VAL);		\
 	WRITE_WB_REG_CASE(OFF, 5, REG, T, VAL);		\
 	WRITE_WB_REG_CASE(OFF, 6, REG, T, VAL);		\
-	WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL);
+	WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL);		\
+	WRITE_WB_REG_CASE(OFF, 8, REG, T, VAL);		\
+	WRITE_WB_REG_CASE(OFF, 9, REG, T, VAL);		\
+	WRITE_WB_REG_CASE(OFF, 10, REG, T, VAL);	\
+	WRITE_WB_REG_CASE(OFF, 11, REG, T, VAL);	\
+	WRITE_WB_REG_CASE(OFF, 12, REG, T, VAL);	\
+	WRITE_WB_REG_CASE(OFF, 13, REG, T, VAL);
 
 static u64 read_wb_reg(int reg, int n, int t)
 {
diff --git a/arch/loongarch/kernel/kdebugfs.c b/arch/loongarch/kernel/kdebugfs.c
new file mode 100644
index 000000000000..80cf64772399
--- /dev/null
+++ b/arch/loongarch/kernel/kdebugfs.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/debugfs.h>
+#include <linux/kstrtox.h>
+#include <asm/loongarch.h>
+
+struct dentry *arch_debugfs_dir;
+EXPORT_SYMBOL(arch_debugfs_dir);
+
+static int sfb_state, tso_state;
+
+static void set_sfb_state(void *info)
+{
+	int val = *(int *)info << CSR_STFILL_SHIFT;
+
+	csr_xchg32(val, CSR_STFILL, LOONGARCH_CSR_IMPCTL1);
+}
+
+static ssize_t sfb_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	int s, state;
+	char str[32];
+
+	state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT;
+
+	s = snprintf(str, sizeof(str), "Boot State: %x\nCurrent State: %x\n", sfb_state, state);
+
+	if (*ppos >= s)
+		return 0;
+
+	s -= *ppos;
+	s = min_t(u32, s, count);
+
+	if (copy_to_user(buf, &str[*ppos], s))
+		return -EFAULT;
+
+	*ppos += s;
+
+	return s;
+}
+
+static ssize_t sfb_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	int state;
+
+	if (kstrtoint_from_user(buf, count, 10, &state))
+		return -EFAULT;
+
+	switch (state) {
+	case 0: case 1:
+		on_each_cpu(set_sfb_state, &state, 1);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static const struct file_operations sfb_fops = {
+	.read = sfb_read,
+	.write = sfb_write,
+	.open = simple_open,
+	.llseek = default_llseek
+};
+
+#define LDSTORDER_NLD_NST        0x0 /* 000 = No Load No Store */
+#define LDSTORDER_ALD_NST        0x1 /* 001 = All Load No Store */
+#define LDSTORDER_SLD_NST        0x3 /* 011 = Same Load No Store */
+#define LDSTORDER_NLD_AST        0x4 /* 100 = No Load All Store */
+#define LDSTORDER_ALD_AST        0x5 /* 101 = All Load All Store */
+#define LDSTORDER_SLD_AST        0x7 /* 111 = Same Load All Store */
+
+static char *tso_hints[] = {
+	"No Load No Store",
+	"All Load No Store",
+	"Invalid Config",
+	"Same Load No Store",
+	"No Load All Store",
+	"All Load All Store",
+	"Invalid Config",
+	"Same Load All Store"
+};
+
+static void set_tso_state(void *info)
+{
+	int val = *(int *)info << CSR_LDSTORDER_SHIFT;
+
+	csr_xchg32(val, CSR_LDSTORDER_MASK, LOONGARCH_CSR_IMPCTL1);
+}
+
+static ssize_t tso_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	int s, state;
+	char str[240];
+
+	state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT;
+
+	s = snprintf(str, sizeof(str), "Boot State: %d (%s)\n"
+			               "Current State: %d (%s)\n\n"
+				       "Available States:\n"
+				       "0 (%s)\t" "1 (%s)\t" "3 (%s)\n"
+				       "4 (%s)\t" "5 (%s)\t" "7 (%s)\n",
+				       tso_state, tso_hints[tso_state], state, tso_hints[state],
+				       tso_hints[0], tso_hints[1], tso_hints[3], tso_hints[4], tso_hints[5], tso_hints[7]);
+
+	if (*ppos >= s)
+		return 0;
+
+	s -= *ppos;
+	s = min_t(u32, s, count);
+
+	if (copy_to_user(buf, &str[*ppos], s))
+		return -EFAULT;
+
+	*ppos += s;
+
+	return s;
+}
+
+static ssize_t tso_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	int state;
+
+	if (kstrtoint_from_user(buf, count, 10, &state))
+		return -EFAULT;
+
+	switch (state) {
+	case 0: case 1: case 3:
+	case 4: case 5: case 7:
+		on_each_cpu(set_tso_state, &state, 1);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return count;
+}
+
+static const struct file_operations tso_fops = {
+	.read = tso_read,
+	.write = tso_write,
+	.open = simple_open,
+	.llseek = default_llseek
+};
+
+static int __init arch_kdebugfs_init(void)
+{
+	unsigned int config = read_cpucfg(LOONGARCH_CPUCFG3);
+
+	arch_debugfs_dir = debugfs_create_dir("loongarch", NULL);
+
+	if (config & CPUCFG3_SFB) {
+		debugfs_create_file("sfb_state", S_IRUGO | S_IWUSR,
+			    arch_debugfs_dir, &sfb_state, &sfb_fops);
+		sfb_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_STFILL) >> CSR_STFILL_SHIFT;
+	}
+
+	if (config & (CPUCFG3_ALDORDER_CAP | CPUCFG3_ASTORDER_CAP)) {
+		debugfs_create_file("tso_state", S_IRUGO | S_IWUSR,
+			    arch_debugfs_dir, &tso_state, &tso_fops);
+		tso_state = (csr_read32(LOONGARCH_CSR_IMPCTL1) & CSR_LDSTORDER_MASK) >> CSR_LDSTORDER_SHIFT;
+	}
+
+	return 0;
+}
+postcore_initcall(arch_kdebugfs_init);
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index 19dc6eff45cc..5e2402cfcab0 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -720,7 +720,7 @@ static int hw_break_set(struct task_struct *target,
 	unsigned int note_type = regset->core_note_type;
 
 	/* Resource info */
-	offset = offsetof(struct user_watch_state, dbg_regs);
+	offset = offsetof(struct user_watch_state_v2, dbg_regs);
 	user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset);
 
 	/* (address, mask, ctrl) registers */
@@ -920,7 +920,7 @@ static const struct user_regset loongarch64_regsets[] = {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	[REGSET_HW_BREAK] = {
 		.core_note_type = NT_LOONGARCH_HW_BREAK,
-		.n = sizeof(struct user_watch_state) / sizeof(u32),
+		.n = sizeof(struct user_watch_state_v2) / sizeof(u32),
 		.size = sizeof(u32),
 		.align = sizeof(u32),
 		.regset_get = hw_break_get,
@@ -928,7 +928,7 @@ static const struct user_regset loongarch64_regsets[] = {
 	},
 	[REGSET_HW_WATCH] = {
 		.core_note_type = NT_LOONGARCH_HW_WATCH,
-		.n = sizeof(struct user_watch_state) / sizeof(u32),
+		.n = sizeof(struct user_watch_state_v2) / sizeof(u32),
 		.size = sizeof(u32),
 		.align = sizeof(u32),
 		.regset_get = hw_break_get,
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 56934fe58170..edcfdfcad7d2 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -431,7 +431,7 @@ static void __init resource_init(void)
 
 	num_standard_resources = memblock.memory.cnt;
 	res_size = num_standard_resources * sizeof(*standard_resources);
-	standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
+	standard_resources = memblock_alloc_or_panic(res_size, SMP_CACHE_BYTES);
 
 	for_each_mem_region(region) {
 		res = &standard_resources[i++];
diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S
index 31dd8199b245..9c23cb7e432f 100644
--- a/arch/loongarch/kernel/switch.S
+++ b/arch/loongarch/kernel/switch.S
@@ -12,7 +12,7 @@
 
 /*
  * task_struct *__switch_to(task_struct *prev, task_struct *next,
- *			    struct thread_info *next_ti)
+ *			    struct thread_info *next_ti, void *sched_ra, void *sched_cfa)
  */
 	.align	5
 SYM_FUNC_START(__switch_to)
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index a07d7eff4dc5..e2d3bfeb6366 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -132,7 +132,7 @@ int constant_clockevent_init(void)
 #else
 	unsigned long min_delta = 1000;
 #endif
-	unsigned long max_delta = (1UL << 48) - 1;
+	unsigned long max_delta = GENMASK_ULL(boot_cpu_data.timerbits, 0);
 	struct clock_event_device *cd;
 	static int irq = 0, timer_irq_installed = 0;
 
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index c57b4134f3e8..2ec3106c0da3 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -597,17 +597,24 @@ int is_valid_bugaddr(unsigned long addr)
 
 static void bug_handler(struct pt_regs *regs)
 {
+	if (user_mode(regs)) {
+		force_sig(SIGTRAP);
+		return;
+	}
+
 	switch (report_bug(regs->csr_era, regs)) {
 	case BUG_TRAP_TYPE_BUG:
-	case BUG_TRAP_TYPE_NONE:
-		die_if_kernel("Oops - BUG", regs);
-		force_sig(SIGTRAP);
+		die("Oops - BUG", regs);
 		break;
 
 	case BUG_TRAP_TYPE_WARN:
 		/* Skip the BUG instruction and continue */
 		regs->csr_era += LOONGARCH_INSN_SIZE;
 		break;
+
+	default:
+		if (!fixup_exception(regs))
+			die("Oops - BUG", regs);
 	}
 }
 
diff --git a/arch/loongarch/kernel/unaligned.c b/arch/loongarch/kernel/unaligned.c
index 3abf163dda05..487be604b96a 100644
--- a/arch/loongarch/kernel/unaligned.c
+++ b/arch/loongarch/kernel/unaligned.c
@@ -482,14 +482,10 @@ sigbus:
 #ifdef CONFIG_DEBUG_FS
 static int __init debugfs_unaligned(void)
 {
-	struct dentry *d;
-
-	d = debugfs_create_dir("loongarch", NULL);
-
 	debugfs_create_u32("unaligned_instructions_user",
-				S_IRUGO, d, &unaligned_instructions_user);
+				S_IRUGO, arch_debugfs_dir, &unaligned_instructions_user);
 	debugfs_create_u32("unaligned_instructions_kernel",
-				S_IRUGO, d, &unaligned_instructions_kernel);
+				S_IRUGO, arch_debugfs_dir, &unaligned_instructions_kernel);
 
 	return 0;
 }
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 188b52bbb254..ca5aa5f46a9f 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -174,9 +174,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	pmd_t *pmd;
 
 	if (p4d_none(p4dp_get(p4d))) {
-		pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pud)
-			panic("%s: Failed to allocate memory\n", __func__);
+		pud = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 		p4d_populate(&init_mm, p4d, pud);
 #ifndef __PAGETABLE_PUD_FOLDED
 		pud_init(pud);
@@ -185,9 +183,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 
 	pud = pud_offset(p4d, addr);
 	if (pud_none(pudp_get(pud))) {
-		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pmd)
-			panic("%s: Failed to allocate memory\n", __func__);
+		pmd = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 		pud_populate(&init_mm, pud, pmd);
 #ifndef __PAGETABLE_PMD_FOLDED
 		pmd_init(pmd);
@@ -198,10 +194,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 	if (!pmd_present(pmdp_get(pmd))) {
 		pte_t *pte;
 
-		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pte)
-			panic("%s: Failed to allocate memory\n", __func__);
-
+		pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 		pmd_populate_kernel(&init_mm, pmd, pte);
 		kernel_pte_init(pte);
 	}
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 3fa69b23ff84..22a94bb3e6e8 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -23,11 +23,10 @@ EXPORT_SYMBOL(tlb_virt_to_page);
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *init, *ret = NULL;
-	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0);
+	pgd_t *init, *ret;
 
-	if (ptdesc) {
-		ret = (pgd_t *)ptdesc_address(ptdesc);
+	ret = __pgd_alloc(mm, 0);
+	if (ret) {
 		init = pgd_offset(&init_mm, 0UL);
 		pgd_init(ret);
 		memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD,
diff --git a/arch/loongarch/power/platform.c b/arch/loongarch/power/platform.c
index 0909729dc2e1..5bbdb9fd76e5 100644
--- a/arch/loongarch/power/platform.c
+++ b/arch/loongarch/power/platform.c
@@ -17,7 +17,7 @@ void enable_gpe_wakeup(void)
 	if (acpi_gbl_reduced_hardware)
 	       return;
 
-	acpi_enable_all_wakeup_gpes();
+	acpi_hw_enable_all_wakeup_gpes();
 }
 
 void enable_pci_wakeup(void)
diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S
index 9fe28d5a0270..df0865df26fa 100644
--- a/arch/loongarch/power/suspend_asm.S
+++ b/arch/loongarch/power/suspend_asm.S
@@ -30,9 +30,6 @@
 	st.d		$r29, sp, PT_R29
 	st.d		$r30, sp, PT_R30
 	st.d		$r31, sp, PT_R31
-
-	la.pcrel	t0, acpi_saved_sp
-	st.d		sp, t0, 0
 .endm
 
 .macro SETUP_WAKEUP
@@ -51,6 +48,7 @@
 	ld.d		$r29, sp, PT_R29
 	ld.d		$r30, sp, PT_R30
 	ld.d		$r31, sp, PT_R31
+	addi.d		sp, sp, PT_SIZE
 .endm
 
 	.text
@@ -59,6 +57,10 @@
 /* Sleep/wakeup code for Loongson-3 */
 SYM_FUNC_START(loongarch_suspend_enter)
 	SETUP_SLEEP
+
+	la.pcrel	t0, acpi_saved_sp
+	st.d		sp, t0, 0
+
 	bl		__flush_cache_all
 
 	/* Pass RA and SP to BIOS */
@@ -82,7 +84,7 @@ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL)
 
 	la.pcrel	t0, acpi_saved_sp
 	ld.d		sp, t0, 0
+
 	SETUP_WAKEUP
-	addi.d		sp, sp, PT_SIZE
 	jr		ra
 SYM_FUNC_END(loongarch_suspend_enter)
diff --git a/arch/m68k/coldfire/m5441x.c b/arch/m68k/coldfire/m5441x.c
index 405e9d5c832c..7a25cfc7ac07 100644
--- a/arch/m68k/coldfire/m5441x.c
+++ b/arch/m68k/coldfire/m5441x.c
@@ -33,14 +33,14 @@ DEFINE_CLK(0, "mcfuart.0", 24, MCF_BUSCLK);
 DEFINE_CLK(0, "mcfuart.1", 25, MCF_BUSCLK);
 DEFINE_CLK(0, "mcfuart.2", 26, MCF_BUSCLK);
 DEFINE_CLK(0, "mcfuart.3", 27, MCF_BUSCLK);
-DEFINE_CLK(0, "mcftmr.0", 28, MCF_CLK);
-DEFINE_CLK(0, "mcftmr.1", 29, MCF_CLK);
-DEFINE_CLK(0, "mcftmr.2", 30, MCF_CLK);
-DEFINE_CLK(0, "mcftmr.3", 31, MCF_CLK);
-DEFINE_CLK(0, "mcfpit.0", 32, MCF_CLK);
-DEFINE_CLK(0, "mcfpit.1", 33, MCF_CLK);
-DEFINE_CLK(0, "mcfpit.2", 34, MCF_CLK);
-DEFINE_CLK(0, "mcfpit.3", 35, MCF_CLK);
+DEFINE_CLK(0, "mcftmr.0", 28, MCF_BUSCLK);
+DEFINE_CLK(0, "mcftmr.1", 29, MCF_BUSCLK);
+DEFINE_CLK(0, "mcftmr.2", 30, MCF_BUSCLK);
+DEFINE_CLK(0, "mcftmr.3", 31, MCF_BUSCLK);
+DEFINE_CLK(0, "mcfpit.0", 32, MCF_BUSCLK);
+DEFINE_CLK(0, "mcfpit.1", 33, MCF_BUSCLK);
+DEFINE_CLK(0, "mcfpit.2", 34, MCF_BUSCLK);
+DEFINE_CLK(0, "mcfpit.3", 35, MCF_BUSCLK);
 DEFINE_CLK(0, "mcfeport.0", 37, MCF_CLK);
 DEFINE_CLK(0, "mcfadc.0", 38, MCF_CLK);
 DEFINE_CLK(0, "mcfdac.0", 39, MCF_CLK);
@@ -167,8 +167,8 @@ static struct clk * const disable_clks[] __initconst = {
 	&__clk_0_14, /* i2c.1 */
 	&__clk_0_22, /* i2c.0 */
 	&__clk_0_23, /* dspi.0 */
-	&__clk_0_28, /* tmr.1 */
-	&__clk_0_29, /* tmr.2 */
+	&__clk_0_28, /* tmr.0 */
+	&__clk_0_29, /* tmr.1 */
 	&__clk_0_30, /* tmr.2 */
 	&__clk_0_31, /* tmr.3 */
 	&__clk_0_32, /* pit.0 */
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index 302c5bf67179..4c648b51e7fd 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -37,7 +37,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable,
 {
 	struct ptdesc *ptdesc = virt_to_ptdesc(pgtable);
 
-	pagetable_pte_dtor(ptdesc);
+	pagetable_dtor(ptdesc);
 	pagetable_free(ptdesc);
 }
 
@@ -61,7 +61,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable)
 {
 	struct ptdesc *ptdesc = virt_to_ptdesc(pgtable);
 
-	pagetable_pte_dtor(ptdesc);
+	pagetable_dtor(ptdesc);
 	pagetable_free(ptdesc);
 }
 
@@ -73,7 +73,7 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t pgtable)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	pagetable_free(virt_to_ptdesc(pgd));
+	pagetable_dtor_free(virt_to_ptdesc(pgd));
 }
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
@@ -84,6 +84,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	if (!ptdesc)
 		return NULL;
+	pagetable_pgd_ctor(ptdesc);
 	new_pgd = ptdesc_address(ptdesc);
 
 	memcpy(new_pgd, swapper_pg_dir, PTRS_PER_PGD * sizeof(pgd_t));
diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h
index 74a817d9387f..5abe7da8ac5a 100644
--- a/arch/m68k/include/asm/motorola_pgalloc.h
+++ b/arch/m68k/include/asm/motorola_pgalloc.h
@@ -9,9 +9,9 @@ extern void mmu_page_ctor(void *page);
 extern void mmu_page_dtor(void *page);
 
 enum m68k_table_types {
-	TABLE_PGD = 0,
-	TABLE_PMD = 0, /* same size as PGD */
-	TABLE_PTE = 1,
+	TABLE_PGD,
+	TABLE_PMD,
+	TABLE_PTE,
 };
 
 extern void init_pointer_table(void *table, int type);
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index 4a137eecb6fe..f1ae4ed890db 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -19,7 +19,7 @@ extern const char bad_pmd_string[];
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 do {								\
-	pagetable_pte_dtor(page_ptdesc(pte));			\
+	pagetable_dtor(page_ptdesc(pte));			\
 	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
 } while (0)
 
@@ -43,7 +43,7 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *new_pgd;
 
-	new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+	new_pgd = __pgd_alloc(mm, 0);
 	memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
 	memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
 	return new_pgd;
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 1b47bec15832..8b11d0d545aa 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -68,10 +68,7 @@ void __init paging_init(void)
 
 	high_memory = (void *) end_mem;
 
-	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!empty_zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	max_zone_pfn[ZONE_DMA] = end_mem >> PAGE_SHIFT;
 	free_area_init(max_zone_pfn);
 }
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 9a6fa342e872..19a75029036c 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -42,20 +42,14 @@ void __init paging_init(void)
 	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
 	int i;
 
-	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!empty_zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 	pg_dir = swapper_pg_dir;
 	memset(swapper_pg_dir, 0, sizeof(swapper_pg_dir));
 
 	size = num_pages * sizeof(pte_t);
 	size = (size + PAGE_SIZE) & ~(PAGE_SIZE-1);
-	next_pgtable = (unsigned long) memblock_alloc(size, PAGE_SIZE);
-	if (!next_pgtable)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, size, PAGE_SIZE);
+	next_pgtable = (unsigned long) memblock_alloc_or_panic(size, PAGE_SIZE);
 
 	pg_dir += PAGE_OFFSET >> PGDIR_SHIFT;
 
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index c1761d309fc6..73651e093c4d 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -97,17 +97,19 @@ void mmu_page_dtor(void *page)
 
 typedef struct list_head ptable_desc;
 
-static struct list_head ptable_list[2] = {
+static struct list_head ptable_list[3] = {
 	LIST_HEAD_INIT(ptable_list[0]),
 	LIST_HEAD_INIT(ptable_list[1]),
+	LIST_HEAD_INIT(ptable_list[2]),
 };
 
 #define PD_PTABLE(page) ((ptable_desc *)&(virt_to_page((void *)(page))->lru))
 #define PD_PAGE(ptable) (list_entry(ptable, struct page, lru))
 #define PD_MARKBITS(dp) (*(unsigned int *)&PD_PAGE(dp)->index)
 
-static const int ptable_shift[2] = {
-	7+2, /* PGD, PMD */
+static const int ptable_shift[3] = {
+	7+2, /* PGD */
+	7+2, /* PMD */
 	6+2, /* PTE */
 };
 
@@ -156,12 +158,20 @@ void *get_pointer_table(int type)
 		if (!(page = (void *)get_zeroed_page(GFP_KERNEL)))
 			return NULL;
 
-		if (type == TABLE_PTE) {
+		switch (type) {
+		case TABLE_PTE:
 			/*
 			 * m68k doesn't have SPLIT_PTE_PTLOCKS for not having
 			 * SMP.
 			 */
 			pagetable_pte_ctor(virt_to_ptdesc(page));
+			break;
+		case TABLE_PMD:
+			pagetable_pmd_ctor(virt_to_ptdesc(page));
+			break;
+		case TABLE_PGD:
+			pagetable_pgd_ctor(virt_to_ptdesc(page));
+			break;
 		}
 
 		mmu_page_ctor(page);
@@ -200,8 +210,7 @@ int free_pointer_table(void *table, int type)
 		/* all tables in page are free, free page */
 		list_del(dp);
 		mmu_page_dtor((void *)page);
-		if (type == TABLE_PTE)
-			pagetable_pte_dtor(virt_to_ptdesc((void *)page));
+		pagetable_dtor(virt_to_ptdesc((void *)page));
 		free_page (page);
 		return 1;
 	} else if (ptable_list[type].next != dp) {
@@ -491,10 +500,7 @@ void __init paging_init(void)
 	 * initialize the bad page table and bad page to point
 	 * to a couple of allocated pages
 	 */
-	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!empty_zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 	/*
 	 * Set up SFC/DFC registers
diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c
index 494739c1783e..1ecf6bdd08bf 100644
--- a/arch/m68k/mm/sun3mmu.c
+++ b/arch/m68k/mm/sun3mmu.c
@@ -44,10 +44,7 @@ void __init paging_init(void)
 	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0, };
 	unsigned long size;
 
-	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!empty_zero_page)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 	address = PAGE_OFFSET;
 	pg_dir = swapper_pg_dir;
@@ -57,10 +54,7 @@ void __init paging_init(void)
 	size = num_pages * sizeof(pte_t);
 	size = (size + PAGE_SIZE) & ~(PAGE_SIZE-1);
 
-	next_pgtable = (unsigned long)memblock_alloc(size, PAGE_SIZE);
-	if (!next_pgtable)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, size, PAGE_SIZE);
+	next_pgtable = (unsigned long)memblock_alloc_or_panic(size, PAGE_SIZE);
 	bootmem_end = (next_pgtable + size + PAGE_SIZE) & PAGE_MASK;
 
 	/* Map whole memory from PAGE_OFFSET (0x0E000000) */
diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c
index 6ebf52740ad7..225fc735e466 100644
--- a/arch/m68k/sun3/sun3dvma.c
+++ b/arch/m68k/sun3/sun3dvma.c
@@ -252,12 +252,8 @@ void __init dvma_init(void)
 
 	list_add(&(hole->list), &hole_list);
 
-	iommu_use = memblock_alloc(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long),
+	iommu_use = memblock_alloc_or_panic(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long),
 				   SMP_CACHE_BYTES);
-	if (!iommu_use)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      IOMMU_TOTAL_ENTRIES * sizeof(unsigned long));
-
 	dvma_unmap_iommu(DVMA_START, DVMA_SIZE);
 
 	sun3_dvma_init();
diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h
index 6c33b05f730f..084a8a0dc239 100644
--- a/arch/microblaze/include/asm/pgalloc.h
+++ b/arch/microblaze/include/asm/pgalloc.h
@@ -21,12 +21,7 @@
 
 extern void __bad_pte(pmd_t *pmd);
 
-static inline pgd_t *get_pgd(void)
-{
-	return (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, 0);
-}
-
-#define pgd_alloc(mm)		get_pgd()
+#define pgd_alloc(mm)		__pgd_alloc(mm, 0)
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a33f05e1ad6d..1924f2d83932 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -29,10 +29,12 @@ config MIPS
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select BUILDTIME_TABLE_SORT
+	select BUILTIN_DTB_ALL if BUILTIN_DTB
 	select CLONE_BACKWARDS
 	select CPU_NO_EFFICIENT_FFS if (TARGET_ISA_REV < 1)
 	select CPU_PM if CPU_IDLE || SUSPEND
 	select GENERIC_ATOMIC64 if !64BIT
+	select GENERIC_BUILTIN_DTB if BUILTIN_DTB
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_GETTIMEOFDAY
@@ -1084,7 +1086,6 @@ config CSRC_IOASIC
 
 config CSRC_R4K
 	select CLOCKSOURCE_WATCHDOG if CPU_FREQ
-	select HAVE_UNSTABLE_SCHED_CLOCK if SMP && 64BIT
 	bool
 
 config CSRC_SB1250
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 5785a3d5ccfb..be8cb44a89fd 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -423,9 +423,6 @@ endif
 
 CLEAN_FILES += vmlinux.32 vmlinux.64
 
-# device-trees
-core-y += arch/mips/boot/dts/
-
 archprepare:
 ifdef CONFIG_MIPS32_N32
 	@$(kecho) '  Checking missing-syscalls for N32'
diff --git a/arch/mips/boot/dts/Makefile b/arch/mips/boot/dts/Makefile
index e2476b12bb0c..ff468439a8c4 100644
--- a/arch/mips/boot/dts/Makefile
+++ b/arch/mips/boot/dts/Makefile
@@ -16,5 +16,3 @@ subdir-$(CONFIG_ATH79)			+= qca
 subdir-$(CONFIG_RALINK)			+= ralink
 subdir-$(CONFIG_MACH_REALTEK_RTL)	+= realtek
 subdir-$(CONFIG_FIT_IMAGE_FDT_XILFPGA)	+= xilfpga
-
-obj-$(CONFIG_BUILTIN_DTB)	:= $(addsuffix /, $(subdir-y))
diff --git a/arch/mips/boot/dts/brcm/Makefile b/arch/mips/boot/dts/brcm/Makefile
index d85f446cc0ce..1798209697c6 100644
--- a/arch/mips/boot/dts/brcm/Makefile
+++ b/arch/mips/boot/dts/brcm/Makefile
@@ -33,5 +33,3 @@ dtb-$(CONFIG_DT_NONE) += \
 	bcm97420c.dtb \
 	bcm97425svmb.dtb \
 	bcm97435svmb.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/cavium-octeon/Makefile b/arch/mips/boot/dts/cavium-octeon/Makefile
index 17aef35f311b..48085bca666c 100644
--- a/arch/mips/boot/dts/cavium-octeon/Makefile
+++ b/arch/mips/boot/dts/cavium-octeon/Makefile
@@ -1,4 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_CAVIUM_OCTEON_SOC)	+= octeon_3xxx.dtb octeon_68xx.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/ingenic/Makefile b/arch/mips/boot/dts/ingenic/Makefile
index 54aa0c4e6091..6e674f1a3aa3 100644
--- a/arch/mips/boot/dts/ingenic/Makefile
+++ b/arch/mips/boot/dts/ingenic/Makefile
@@ -5,5 +5,3 @@ dtb-$(CONFIG_JZ4770_GCW0)	+= gcw0.dtb
 dtb-$(CONFIG_JZ4780_CI20)	+= ci20.dtb
 dtb-$(CONFIG_X1000_CU1000_NEO)	+= cu1000-neo.dtb
 dtb-$(CONFIG_X1830_CU1830_NEO)	+= cu1830-neo.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/lantiq/Makefile b/arch/mips/boot/dts/lantiq/Makefile
index ae6e3e21ebeb..d8531b4653c0 100644
--- a/arch/mips/boot/dts/lantiq/Makefile
+++ b/arch/mips/boot/dts/lantiq/Makefile
@@ -1,4 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_DT_EASY50712)	+= danube_easy50712.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/loongson/Makefile b/arch/mips/boot/dts/loongson/Makefile
index 5c6433e441ee..5e3ab984d70f 100644
--- a/arch/mips/boot/dts/loongson/Makefile
+++ b/arch/mips/boot/dts/loongson/Makefile
@@ -5,5 +5,3 @@ dtb-$(CONFIG_MACH_LOONGSON64)	+= loongson64c_4core_rs780e.dtb
 dtb-$(CONFIG_MACH_LOONGSON64)	+= loongson64c_8core_rs780e.dtb
 dtb-$(CONFIG_MACH_LOONGSON64)	+= loongson64g_4core_ls7a.dtb
 dtb-$(CONFIG_MACH_LOONGSON64)	+= loongson64v_4core_virtio.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/mobileye/eyeq5.dtsi b/arch/mips/boot/dts/mobileye/eyeq5.dtsi
index 5d73e8320b8e..a84e6e720619 100644
--- a/arch/mips/boot/dts/mobileye/eyeq5.dtsi
+++ b/arch/mips/boot/dts/mobileye/eyeq5.dtsi
@@ -49,6 +49,28 @@
 		mhm_reserved_0: the-mhm-reserved-0@0 {
 			reg = <0x8 0x00000000 0x0 0x0000800>;
 		};
+
+		nvram@461fe00 {
+			compatible = "mobileye,eyeq5-bootloader-config", "nvmem-rmem";
+			reg = <0x0 0x0461fe00 0x0 0x200>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			no-map;
+
+			nvmem-layout {
+				compatible = "fixed-layout";
+				#address-cells = <1>;
+				#size-cells = <1>;
+
+				eth0_mac: mac@7c {
+					reg = <0x7c 0x6>;
+				};
+
+				eth1_mac: mac@82 {
+					reg = <0x82 0x6>;
+				};
+			};
+		};
 	};
 
 	aliases {
diff --git a/arch/mips/boot/dts/mscc/Makefile b/arch/mips/boot/dts/mscc/Makefile
index eeb6b7aae83b..566dbec3c7fb 100644
--- a/arch/mips/boot/dts/mscc/Makefile
+++ b/arch/mips/boot/dts/mscc/Makefile
@@ -8,6 +8,3 @@ dtb-$(CONFIG_SOC_VCOREIII)	+= \
 	ocelot_pcb123.dtb \
 	serval_pcb105.dtb \
 	serval_pcb106.dtb
-
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/mti/Makefile b/arch/mips/boot/dts/mti/Makefile
index b5f7426998b1..c1c7b27296dd 100644
--- a/arch/mips/boot/dts/mti/Makefile
+++ b/arch/mips/boot/dts/mti/Makefile
@@ -1,5 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 dtb-$(CONFIG_MIPS_MALTA)	+= malta.dtb
 dtb-$(CONFIG_LEGACY_BOARD_SEAD3)	+= sead3.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/pic32/Makefile b/arch/mips/boot/dts/pic32/Makefile
index fb57f36324db..4069cda2370c 100644
--- a/arch/mips/boot/dts/pic32/Makefile
+++ b/arch/mips/boot/dts/pic32/Makefile
@@ -3,5 +3,3 @@ dtb-$(CONFIG_DTB_PIC32_MZDA_SK)		+= pic32mzda_sk.dtb
 
 dtb-$(CONFIG_DTB_PIC32_NONE)		+= \
 					pic32mzda_sk.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/ralink/Makefile b/arch/mips/boot/dts/ralink/Makefile
index d27d7e8c700f..dc002152d843 100644
--- a/arch/mips/boot/dts/ralink/Makefile
+++ b/arch/mips/boot/dts/ralink/Makefile
@@ -10,5 +10,3 @@ dtb-$(CONFIG_SOC_MT7621) += \
 	mt7621-gnubee-gb-pc1.dtb \
 	mt7621-gnubee-gb-pc2.dtb \
 	mt7621-tplink-hc220-g5-v1.dtb
-
-obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
index 9218b3ae3383..3a11ce85762b 100644
--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
@@ -128,10 +128,10 @@ struct irq_source_routing_table {
 } __packed;
 
 struct interface_info {
-	u16 vers; /* version of the specificition */
-	u16 size;
-	u8  flag;
-	char description[64];
+	u16 vers; /* version of the specification */
+	u16 size; /* size of this interface */
+	u8  flag; /* used or unused */
+	char description[64]; /* description for each change */
 } __packed;
 
 #define MAX_RESOURCE_NUMBER 128
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 3c6ddc0c2c7a..c025558754d5 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -2039,8 +2039,8 @@ do {									\
 #define read_c0_perfcntr3_64()	__read_64bit_c0_register($25, 7)
 #define write_c0_perfcntr3_64(val) __write_64bit_c0_register($25, 7, val)
 
-#define read_c0_ecc()		__read_32bit_c0_register($26, 0)
-#define write_c0_ecc(val)	__write_32bit_c0_register($26, 0, val)
+#define read_c0_errctl()	__read_32bit_c0_register($26, 0)
+#define write_c0_errctl(val)	__write_32bit_c0_register($26, 0, val)
 
 #define read_c0_derraddr0()	__read_ulong_c0_register($26, 1)
 #define write_c0_derraddr0(val) __write_ulong_c0_register($26, 1, val)
diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h
index f4440edcd8fe..26c7a6ede983 100644
--- a/arch/mips/include/asm/pgalloc.h
+++ b/arch/mips/include/asm/pgalloc.h
@@ -15,7 +15,6 @@
 
 #define __HAVE_ARCH_PMD_ALLOC_ONE
 #define __HAVE_ARCH_PUD_ALLOC_ONE
-#define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -49,14 +48,9 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 extern void pgd_init(void *addr);
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	pagetable_free(virt_to_ptdesc(pgd));
-}
-
 #define __pte_free_tlb(tlb, pte, address)			\
 do {								\
-	pagetable_pte_dtor(page_ptdesc(pte));			\
+	pagetable_dtor(page_ptdesc(pte));			\
 	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));	\
 } while (0)
 
diff --git a/arch/mips/kernel/cevt-bcm1480.c b/arch/mips/kernel/cevt-bcm1480.c
index d39a2963b451..2a14dc4ee57e 100644
--- a/arch/mips/kernel/cevt-bcm1480.c
+++ b/arch/mips/kernel/cevt-bcm1480.c
@@ -103,7 +103,7 @@ void sb1480_clockevent_init(void)
 
 	BUG_ON(cpu > 3);	/* Only have 4 general purpose timers */
 
-	sprintf(name, "bcm1480-counter-%d", cpu);
+	sprintf(name, "bcm1480-counter-%u", cpu);
 	cd->name		= name;
 	cd->features		= CLOCK_EVT_FEAT_PERIODIC |
 				  CLOCK_EVT_FEAT_ONESHOT;
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 8c401e42301c..f39e85fd58fa 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -248,7 +248,7 @@ int ftrace_disable_ftrace_graph_caller(void)
 #define S_R_SP	(0xafb0 << 16)	/* s{d,w} R, offset(sp) */
 #define OFFSET_MASK	0xffff	/* stack offset range: 0 ~ PT_SIZE */
 
-unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long
+static unsigned long ftrace_get_parent_ra_addr(unsigned long self_ra, unsigned long
 		old_parent_ra, unsigned long parent_ra_addr, unsigned long fp)
 {
 	unsigned long sp, ip, tmp;
diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S
index e3ff6179c99f..d99ed58b7043 100644
--- a/arch/mips/kernel/head.S
+++ b/arch/mips/kernel/head.S
@@ -60,6 +60,7 @@
 	.endm
 
 	__HEAD
+
 #ifndef CONFIG_NO_EXCEPT_FILL
 	/*
 	 * Reserved space for exception handlers.
diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c
index 37676a44fefb..2ef610650a9e 100644
--- a/arch/mips/kernel/mips-mt.c
+++ b/arch/mips/kernel/mips-mt.c
@@ -122,9 +122,8 @@ void mips_mt_set_cpuoptions(void)
 		unsigned long ectlval;
 		unsigned long itcblkgrn;
 
-		/* ErrCtl register is known as "ecc" to Linux */
-		ectlval = read_c0_ecc();
-		write_c0_ecc(ectlval | (0x1 << 26));
+		ectlval = read_c0_errctl();
+		write_c0_errctl(ectlval | (0x1 << 26));
 		ehb();
 #define INDEX_0 (0x80000000)
 #define INDEX_8 (0x80000008)
@@ -145,7 +144,7 @@ void mips_mt_set_cpuoptions(void)
 		ehb();
 		/* Write out to ITU with CACHE op */
 		cache_op(Index_Store_Tag_D, INDEX_0);
-		write_c0_ecc(ectlval);
+		write_c0_errctl(ectlval);
 		ehb();
 		printk("Mapped %ld ITC cells starting at 0x%08x\n",
 			((itcblkgrn & 0x7fe00000) >> 20), itc_base);
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 12a1a4ffb602..fbfe0771317e 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -704,10 +704,7 @@ static void __init resource_init(void)
 	for_each_mem_range(i, &start, &end) {
 		struct resource *res;
 
-		res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      sizeof(struct resource));
+		res = memblock_alloc_or_panic(sizeof(struct resource), SMP_CACHE_BYTES);
 
 		res->start = start;
 		/*
diff --git a/arch/mips/kernel/spram.c b/arch/mips/kernel/spram.c
index 71c7e5e27567..dd31e3fffd24 100644
--- a/arch/mips/kernel/spram.c
+++ b/arch/mips/kernel/spram.c
@@ -26,10 +26,6 @@
 
 #define ERRCTL_SPRAM		(1 << 28)
 
-/* errctl access */
-#define read_c0_errctl(x) read_c0_ecc(x)
-#define write_c0_errctl(x) write_c0_ecc(x)
-
 /*
  * Different semantics to the set_c0_* function built by __BUILD_SET_C0
  */
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index dc29bd9656b0..39e248d0ed59 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -38,6 +38,7 @@
 #include <linux/kdb.h>
 #include <linux/irq.h>
 #include <linux/perf_event.h>
+#include <linux/string_choices.h>
 
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
@@ -1705,10 +1706,10 @@ static inline __init void parity_protection_init(void)
 		l2parity &= l1parity;
 
 		/* Probe L1 ECC support */
-		cp0_ectl = read_c0_ecc();
-		write_c0_ecc(cp0_ectl | ERRCTL_PE);
+		cp0_ectl = read_c0_errctl();
+		write_c0_errctl(cp0_ectl | ERRCTL_PE);
 		back_to_back_c0_hazard();
-		cp0_ectl = read_c0_ecc();
+		cp0_ectl = read_c0_errctl();
 
 		/* Probe L2 ECC support */
 		gcr_ectl = read_gcr_err_control();
@@ -1727,9 +1728,9 @@ static inline __init void parity_protection_init(void)
 			cp0_ectl |= ERRCTL_PE;
 		else
 			cp0_ectl &= ~ERRCTL_PE;
-		write_c0_ecc(cp0_ectl);
+		write_c0_errctl(cp0_ectl);
 		back_to_back_c0_hazard();
-		WARN_ON(!!(read_c0_ecc() & ERRCTL_PE) != l1parity);
+		WARN_ON(!!(read_c0_errctl() & ERRCTL_PE) != l1parity);
 
 		/* Configure L2 ECC checking */
 		if (l2parity)
@@ -1741,8 +1742,8 @@ static inline __init void parity_protection_init(void)
 		gcr_ectl &= CM_GCR_ERR_CONTROL_L2_ECC_EN;
 		WARN_ON(!!gcr_ectl != l2parity);
 
-		pr_info("Cache parity protection %sabled\n",
-			l1parity ? "en" : "dis");
+		pr_info("Cache parity protection %s\n",
+			str_enabled_disabled(l1parity));
 		return;
 	}
 
@@ -1761,18 +1762,18 @@ static inline __init void parity_protection_init(void)
 			unsigned long errctl;
 			unsigned int l1parity_present, l2parity_present;
 
-			errctl = read_c0_ecc();
+			errctl = read_c0_errctl();
 			errctl &= ~(ERRCTL_PE|ERRCTL_L2P);
 
 			/* probe L1 parity support */
-			write_c0_ecc(errctl | ERRCTL_PE);
+			write_c0_errctl(errctl | ERRCTL_PE);
 			back_to_back_c0_hazard();
-			l1parity_present = (read_c0_ecc() & ERRCTL_PE);
+			l1parity_present = (read_c0_errctl() & ERRCTL_PE);
 
 			/* probe L2 parity support */
-			write_c0_ecc(errctl|ERRCTL_L2P);
+			write_c0_errctl(errctl|ERRCTL_L2P);
 			back_to_back_c0_hazard();
-			l2parity_present = (read_c0_ecc() & ERRCTL_L2P);
+			l2parity_present = (read_c0_errctl() & ERRCTL_L2P);
 
 			if (l1parity_present && l2parity_present) {
 				if (l1parity)
@@ -1791,20 +1792,20 @@ static inline __init void parity_protection_init(void)
 
 			printk(KERN_INFO "Writing ErrCtl register=%08lx\n", errctl);
 
-			write_c0_ecc(errctl);
+			write_c0_errctl(errctl);
 			back_to_back_c0_hazard();
-			errctl = read_c0_ecc();
+			errctl = read_c0_errctl();
 			printk(KERN_INFO "Readback ErrCtl register=%08lx\n", errctl);
 
 			if (l1parity_present)
-				printk(KERN_INFO "Cache parity protection %sabled\n",
-				       (errctl & ERRCTL_PE) ? "en" : "dis");
+				pr_info("Cache parity protection %s\n",
+					str_enabled_disabled(errctl & ERRCTL_PE));
 
 			if (l2parity_present) {
 				if (l1parity_present && l1parity)
 					errctl ^= ERRCTL_L2P;
-				printk(KERN_INFO "L2 cache parity protection %sabled\n",
-				       (errctl & ERRCTL_L2P) ? "en" : "dis");
+				pr_info("L2 cache parity protection %s\n",
+					str_enabled_disabled(errctl & ERRCTL_L2P));
 			}
 		}
 		break;
@@ -1812,11 +1813,11 @@ static inline __init void parity_protection_init(void)
 	case CPU_5KC:
 	case CPU_5KE:
 	case CPU_LOONGSON32:
-		write_c0_ecc(0x80000000);
+		write_c0_errctl(0x80000000);
 		back_to_back_c0_hazard();
 		/* Set the PE bit (bit 31) in the c0_errctl register. */
-		printk(KERN_INFO "Cache parity protection %sabled\n",
-		       (read_c0_ecc() & 0x80000000) ? "en" : "dis");
+		pr_info("Cache parity protection %s\n",
+			str_enabled_disabled(read_c0_errctl() & 0x80000000));
 		break;
 	case CPU_20KC:
 	case CPU_25KF:
@@ -1887,8 +1888,8 @@ asmlinkage void do_ftlb(void)
 	if ((cpu_has_mips_r2_r6) &&
 	    (((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_MIPS) ||
 	    ((current_cpu_data.processor_id & 0xff0000) == PRID_COMP_LOONGSON))) {
-		pr_err("FTLB error exception, cp0_ecc=0x%08x:\n",
-		       read_c0_ecc());
+		pr_err("FTLB error exception, cp0_errctl=0x%08x:\n",
+		       read_c0_errctl());
 		pr_err("cp0_errorepc == %0*lx\n", field, read_c0_errorepc());
 		reg_val = read_c0_cacheerr();
 		pr_err("c0_cacheerr == %08x\n", reg_val);
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 4c8e3c0aa210..75c9d3618f58 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -11,6 +11,7 @@
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/mman.h>
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -97,11 +98,12 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return -EINTR;
 
 	if (IS_ENABLED(CONFIG_MIPS_FP_SUPPORT)) {
+		unsigned long unused;
+
 		/* Map delay slot emulation page */
-		base = mmap_region(NULL, STACK_TOP, PAGE_SIZE,
-				VM_READ | VM_EXEC |
-				VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
-				0, NULL);
+		base = do_mmap(NULL, STACK_TOP, PAGE_SIZE, PROT_READ | PROT_EXEC,
+			       MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, 0, 0, &unused,
+			       NULL);
 		if (IS_ERR_VALUE(base)) {
 			ret = base;
 			goto out;
diff --git a/arch/mips/loongson64/boardinfo.c b/arch/mips/loongson64/boardinfo.c
index 280989c5a137..8bb275c93ac0 100644
--- a/arch/mips/loongson64/boardinfo.c
+++ b/arch/mips/loongson64/boardinfo.c
@@ -21,13 +21,11 @@ static ssize_t boardinfo_show(struct kobject *kobj,
 		       "BIOS Info\n"
 		       "Vendor\t\t\t: %s\n"
 		       "Version\t\t\t: %s\n"
-		       "ROM Size\t\t: %d KB\n"
 		       "Release Date\t\t: %s\n",
 		       strsep(&tmp_board_manufacturer, "-"),
 		       eboard->name,
 		       strsep(&tmp_bios_vendor, "-"),
 		       einter->description,
-		       einter->size,
 		       especial->special_name);
 }
 static struct kobj_attribute boardinfo_attr = __ATTR(boardinfo, 0444,
diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
index 09ff05269861..be8d2ad10750 100644
--- a/arch/mips/loongson64/env.c
+++ b/arch/mips/loongson64/env.c
@@ -17,6 +17,7 @@
 #include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/pci_ids.h>
+#include <linux/string_choices.h>
 #include <asm/bootinfo.h>
 #include <loongson.h>
 #include <boot_param.h>
@@ -162,7 +163,7 @@ void __init prom_lefi_init_env(void)
 		dma_default_coherent = !eirq_source->dma_noncoherent;
 	}
 
-	pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off");
+	pr_info("Firmware: Coherent DMA: %s\n", str_on_off(dma_default_coherent));
 
 	loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm;
 	loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown;
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 265bc57819df..c89e70df43d8 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1660,7 +1660,7 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		break;
 	}
 
-	case 0x3:
+	case 0x7:
 		if (MIPSInst_FUNC(ir) != pfetch_op)
 			return SIGILL;
 
diff --git a/arch/mips/mm/pgtable.c b/arch/mips/mm/pgtable.c
index 1506e458040d..10835414819f 100644
--- a/arch/mips/mm/pgtable.c
+++ b/arch/mips/mm/pgtable.c
@@ -10,12 +10,10 @@
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *init, *ret = NULL;
-	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM,
-			PGD_TABLE_ORDER);
+	pgd_t *init, *ret;
 
-	if (ptdesc) {
-		ret = ptdesc_address(ptdesc);
+	ret = __pgd_alloc(mm, PGD_TABLE_ORDER);
+	if (ret) {
 		init = pgd_offset(&init_mm, 0UL);
 		pgd_init(ret);
 		memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD,
diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c
index ec2567f8efd8..66898fd182dc 100644
--- a/arch/mips/pci/pci-legacy.c
+++ b/arch/mips/pci/pci-legacy.c
@@ -29,6 +29,14 @@ static LIST_HEAD(controllers);
 
 static int pci_initialized;
 
+unsigned long pci_address_to_pio(phys_addr_t address)
+{
+	if (address > IO_SPACE_LIMIT)
+		return (unsigned long)-1;
+
+	return (unsigned long) address;
+}
+
 /*
  * We need to avoid collisions with `mirrored' VGA ports
  * and other strange ISA hardware, so we always want the
diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h
index ce6bb8e74271..12a536b7bfbd 100644
--- a/arch/nios2/include/asm/pgalloc.h
+++ b/arch/nios2/include/asm/pgalloc.h
@@ -30,7 +30,7 @@ extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
 #define __pte_free_tlb(tlb, pte, addr)					\
 	do {								\
-		pagetable_pte_dtor(page_ptdesc(pte));			\
+		pagetable_dtor(page_ptdesc(pte));			\
 		tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
 	} while (0)
 
diff --git a/arch/nios2/mm/pgtable.c b/arch/nios2/mm/pgtable.c
index 7c76e8a7447a..6470ed378782 100644
--- a/arch/nios2/mm/pgtable.c
+++ b/arch/nios2/mm/pgtable.c
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 
 #include <asm/cpuinfo.h>
+#include <asm/pgalloc.h>
 
 /* pteaddr:
  *   ptbase | vpn* | zero
@@ -54,7 +55,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *ret, *init;
 
-	ret = (pgd_t *) __get_free_page(GFP_KERNEL);
+	ret = __pgd_alloc(mm, 0);
 	if (ret) {
 		init = pgd_offset(&init_mm, 0UL);
 		pgd_init(ret);
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index c6a73772a546..3372f4e6ab4b 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -41,15 +41,13 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
  */
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *ret = (pgd_t *)__get_free_page(GFP_KERNEL);
+	pgd_t *ret = __pgd_alloc(mm, 0);
 
-	if (ret) {
-		memset(ret, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+	if (ret)
 		memcpy(ret + USER_PTRS_PER_PGD,
 		       swapper_pg_dir + USER_PTRS_PER_PGD,
 		       (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
 
-	}
 	return ret;
 }
 
@@ -68,7 +66,7 @@ extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 do {								\
-	pagetable_pte_dtor(page_ptdesc(pte));			\
+	pagetable_dtor(page_ptdesc(pte));			\
 	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
 } while (0)
 
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index f59ea4c10b0f..8e63e86251ca 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -38,10 +38,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm)
 	if (likely(mem_init_done)) {
 		pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
 	} else {
-		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pte)
-			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-			      __func__, PAGE_SIZE, PAGE_SIZE);
+		pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	}
 
 	return pte;
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index e3e142b1c5c5..2ca74a56415c 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -11,27 +11,12 @@
 #include <asm/cache.h>
 
 #define __HAVE_ARCH_PMD_ALLOC_ONE
-#define __HAVE_ARCH_PMD_FREE
-#define __HAVE_ARCH_PGD_FREE
 #include <asm-generic/pgalloc.h>
 
 /* Allocate the top level pgd (page directory) */
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *pgd;
-
-	pgd = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER);
-	if (unlikely(pgd == NULL))
-		return NULL;
-
-	memset(pgd, 0, PAGE_SIZE << PGD_TABLE_ORDER);
-
-	return pgd;
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	free_pages((unsigned long)pgd, PGD_TABLE_ORDER);
+	return __pgd_alloc(mm, PGD_TABLE_ORDER);
 }
 
 #if CONFIG_PGTABLE_LEVELS == 3
@@ -46,17 +31,19 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-	pmd_t *pmd;
-
-	pmd = (pmd_t *)__get_free_pages(GFP_PGTABLE_KERNEL, PMD_TABLE_ORDER);
-	if (likely(pmd))
-		memset ((void *)pmd, 0, PAGE_SIZE << PMD_TABLE_ORDER);
-	return pmd;
-}
+	struct ptdesc *ptdesc;
+	gfp_t gfp = GFP_PGTABLE_USER;
 
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-	free_pages((unsigned long)pmd, PMD_TABLE_ORDER);
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	ptdesc = pagetable_alloc(gfp, PMD_TABLE_ORDER);
+	if (!ptdesc)
+		return NULL;
+	if (!pagetable_pmd_ctor(ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
+	}
+	return ptdesc_address(ptdesc);
 }
 #endif
 
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 96970fa75e4a..61c0a2477072 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -377,10 +377,8 @@ static void __ref map_pages(unsigned long start_vaddr,
 
 #if CONFIG_PGTABLE_LEVELS == 3
 		if (pud_none(*pud)) {
-			pmd = memblock_alloc(PAGE_SIZE << PMD_TABLE_ORDER,
+			pmd = memblock_alloc_or_panic(PAGE_SIZE << PMD_TABLE_ORDER,
 					     PAGE_SIZE << PMD_TABLE_ORDER);
-			if (!pmd)
-				panic("pmd allocation failed.\n");
 			pud_populate(NULL, pud, pmd);
 		}
 #endif
@@ -388,9 +386,7 @@ static void __ref map_pages(unsigned long start_vaddr,
 		pmd = pmd_offset(pud, vaddr);
 		for (tmp1 = start_pmd; tmp1 < PTRS_PER_PMD; tmp1++, pmd++) {
 			if (pmd_none(*pmd)) {
-				pg_table = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-				if (!pg_table)
-					panic("page table allocation failed\n");
+				pg_table = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 				pmd_populate_kernel(NULL, pmd, pg_table);
 			}
 
@@ -648,9 +644,7 @@ static void __init pagetable_init(void)
 	}
 #endif
 
-	empty_zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!empty_zero_page)
-		panic("zero page allocation failed.\n");
+	empty_zero_page = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 }
 
@@ -687,19 +681,15 @@ static void __init fixmap_init(void)
 
 #if CONFIG_PGTABLE_LEVELS == 3
 	if (pud_none(*pud)) {
-		pmd = memblock_alloc(PAGE_SIZE << PMD_TABLE_ORDER,
+		pmd = memblock_alloc_or_panic(PAGE_SIZE << PMD_TABLE_ORDER,
 				     PAGE_SIZE << PMD_TABLE_ORDER);
-		if (!pmd)
-			panic("fixmap: pmd allocation failed.\n");
 		pud_populate(NULL, pud, pmd);
 	}
 #endif
 
 	pmd = pmd_offset(pud, addr);
 	do {
-		pte_t *pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pte)
-			panic("fixmap: pte allocation failed.\n");
+		pte_t *pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 
 		pmd_populate_kernel(&init_mm, pmd, pte);
 
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 1ca7d4c4b90d..2058e8d3e013 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -37,6 +37,7 @@ extern void tlb_flush(struct mmu_gather *tlb);
  */
 #define tlb_needs_table_invalidate()	radix_enabled()
 
+#define __HAVE_ARCH_TLB_REMOVE_TABLE
 /* Get the generic bits... */
 #include <asm-generic/tlb.h>
 
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 1bee15c013e7..3af6c06af02f 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -1087,12 +1087,10 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
 	/* Count and allocate space for cpu features */
 	of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
 						&nr_dt_cpu_features);
-	dt_cpu_features = memblock_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE);
-	if (!dt_cpu_features)
-		panic("%s: Failed to allocate %zu bytes align=0x%lx\n",
-		      __func__,
-		      sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
-		      PAGE_SIZE);
+	dt_cpu_features =
+		memblock_alloc_or_panic(
+			sizeof(struct dt_cpu_feature) * nr_dt_cpu_features,
+			PAGE_SIZE);
 
 	cpufeatures_setup_start(isa);
 
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 30b56c67fa61..e527cd3ef128 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -97,7 +97,7 @@ void power4_idle(void)
 /*
  * Register the sysctl to set/clear powersave_nap.
  */
-static struct ctl_table powersave_nap_ctl_table[] = {
+static const struct ctl_table powersave_nap_ctl_table[] = {
 	{
 		.procname	= "powersave-nap",
 		.data		= &powersave_nap,
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 45dac7b46aa3..34a5aec4908f 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -369,6 +369,24 @@ static void dedotify_versions(struct modversion_info *vers,
 		}
 }
 
+/* Same as normal versions, remove a leading dot if present. */
+static void dedotify_ext_version_names(char *str_seq, unsigned long size)
+{
+	unsigned long out = 0;
+	unsigned long in;
+	char last = '\0';
+
+	for (in = 0; in < size; in++) {
+		/* Skip one leading dot */
+		if (last == '\0' && str_seq[in] == '.')
+			in++;
+		last = str_seq[in];
+		str_seq[out++] = last;
+	}
+	/* Zero the trailing portion of the names table for robustness */
+	memset(&str_seq[out], 0, size - out);
+}
+
 /*
  * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC.
  * seem to be defined (value set later).
@@ -438,10 +456,12 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 			me->arch.toc_section = i;
 			if (sechdrs[i].sh_addralign < 8)
 				sechdrs[i].sh_addralign = 8;
-		}
-		else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0)
+		} else if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0)
 			dedotify_versions((void *)hdr + sechdrs[i].sh_offset,
 					  sechdrs[i].sh_size);
+		else if (strcmp(secstrings + sechdrs[i].sh_name, "__version_ext_names") == 0)
+			dedotify_ext_version_names((void *)hdr + sechdrs[i].sh_offset,
+						   sechdrs[i].sh_size);
 
 		if (sechdrs[i].sh_type == SHT_SYMTAB)
 			dedotify((void *)hdr + sechdrs[i].sh_offset,
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index ce0c8623e563..f8a3bd8cfae4 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -213,11 +213,8 @@ pci_create_OF_bus_map(void)
 	struct property* of_prop;
 	struct device_node *dn;
 
-	of_prop = memblock_alloc(sizeof(struct property) + 256,
+	of_prop = memblock_alloc_or_panic(sizeof(struct property) + 256,
 				 SMP_CACHE_BYTES);
-	if (!of_prop)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(struct property) + 256);
 	dn = of_find_node_by_path("/");
 	if (dn) {
 		memset(of_prop, -1, sizeof(struct property) + 256);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index f7d7a93f07fc..a08b0ede4e64 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -458,11 +458,8 @@ void __init smp_setup_cpu_maps(void)
 
 	DBG("smp_setup_cpu_maps()\n");
 
-	cpu_to_phys_id = memblock_alloc(nr_cpu_ids * sizeof(u32),
+	cpu_to_phys_id = memblock_alloc_or_panic(nr_cpu_ids * sizeof(u32),
 					__alignof__(u32));
-	if (!cpu_to_phys_id)
-		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
-		      __func__, nr_cpu_ids * sizeof(u32), __alignof__(u32));
 
 	for_each_node_by_type(dn, "cpu") {
 		const __be32 *intserv;
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 75dbf3e0d9c4..5a1bf501fbe1 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -140,13 +140,7 @@ arch_initcall(ppc_init);
 
 static void *__init alloc_stack(void)
 {
-	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
-
-	if (!ptr)
-		panic("cannot allocate %d bytes for stack at %pS\n",
-		      THREAD_SIZE, (void *)_RET_IP_);
-
-	return ptr;
+	return memblock_alloc_or_panic(THREAD_SIZE, THREAD_ALIGN);
 }
 
 void __init irqstack_early_init(void)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 25429905ae90..86bff159c51e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4957,7 +4957,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 			 * states are synchronized from L0 to L1. L1 needs to inform L0 about
 			 * MER=1 only when there are pending external interrupts.
 			 * In the above if check, MER bit is set if there are pending
-			 * external interrupts. Hence, explicity mask off MER bit
+			 * external interrupts. Hence, explicitly mask off MER bit
 			 * here as otherwise it may generate spurious interrupts in L2 KVM
 			 * causing an endless loop, which results in L2 guest getting hung.
 			 */
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 6978344edcb4..be9c4106e22f 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -377,10 +377,7 @@ void __init MMU_init_hw(void)
 	 * Find some memory for the hash table.
 	 */
 	if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322);
-	Hash = memblock_alloc(Hash_size, Hash_size);
-	if (!Hash)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, Hash_size, Hash_size);
+	Hash = memblock_alloc_or_panic(Hash_size, Hash_size);
 	_SDR1 = __pa(Hash) | SDR1_LOW_BITS;
 
 	pr_info("Total memory = %lldMB; using %ldkB for hash table\n",
diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c
index 1715b07c630c..4e1e45420bd4 100644
--- a/arch/powerpc/mm/book3s64/mmu_context.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -253,7 +253,7 @@ static void pmd_frag_destroy(void *pmd_frag)
 	count = ((unsigned long)pmd_frag & ~PAGE_MASK) >> PMD_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
 	if (atomic_sub_and_test(PMD_FRAG_NR - count, &ptdesc->pt_frag_refcount)) {
-		pagetable_pmd_dtor(ptdesc);
+		pagetable_dtor(ptdesc);
 		pagetable_free(ptdesc);
 	}
 }
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 374542528080..ce64abea9e3e 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -330,11 +330,7 @@ void __init mmu_partition_table_init(void)
 	unsigned long ptcr;
 
 	/* Initialize the Partition Table with no entries */
-	partition_tb = memblock_alloc(patb_size, patb_size);
-	if (!partition_tb)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, patb_size, patb_size);
-
+	partition_tb = memblock_alloc_or_panic(patb_size, patb_size);
 	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
 	set_ptcr_when_no_uv(ptcr);
 	powernv_set_nmmu_ptcr(ptcr);
@@ -477,7 +473,7 @@ void pmd_fragment_free(unsigned long *pmd)
 
 	BUG_ON(atomic_read(&ptdesc->pt_frag_refcount) <= 0);
 	if (atomic_dec_and_test(&ptdesc->pt_frag_refcount)) {
-		pagetable_pmd_dtor(ptdesc);
+		pagetable_dtor(ptdesc);
 		pagetable_free(ptdesc);
 	}
 }
diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c
index 43c03b84ff32..60c78aac0f63 100644
--- a/arch/powerpc/mm/kasan/init_book3e_64.c
+++ b/arch/powerpc/mm/kasan/init_book3e_64.c
@@ -40,19 +40,19 @@ static int __init kasan_map_kernel_page(unsigned long ea, unsigned long pa, pgpr
 	pgdp = pgd_offset_k(ea);
 	p4dp = p4d_offset(pgdp, ea);
 	if (kasan_pud_table(*p4dp)) {
-		pudp = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
+		pudp = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
 		memcpy(pudp, kasan_early_shadow_pud, PUD_TABLE_SIZE);
 		p4d_populate(&init_mm, p4dp, pudp);
 	}
 	pudp = pud_offset(p4dp, ea);
 	if (kasan_pmd_table(*pudp)) {
-		pmdp = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
+		pmdp = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
 		memcpy(pmdp, kasan_early_shadow_pmd, PMD_TABLE_SIZE);
 		pud_populate(&init_mm, pudp, pmdp);
 	}
 	pmdp = pmd_offset(pudp, ea);
 	if (kasan_pte_table(*pmdp)) {
-		ptep = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
+		ptep = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
 		memcpy(ptep, kasan_early_shadow_pte, PTE_TABLE_SIZE);
 		pmd_populate_kernel(&init_mm, pmdp, ptep);
 	}
@@ -74,7 +74,7 @@ static void __init kasan_init_phys_region(void *start, void *end)
 	k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
 	k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
 
-	va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+	va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE);
 	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
 		kasan_map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
 }
diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c
index 3fb5ce4f48f4..7d959544c077 100644
--- a/arch/powerpc/mm/kasan/init_book3s_64.c
+++ b/arch/powerpc/mm/kasan/init_book3s_64.c
@@ -32,7 +32,7 @@ static void __init kasan_init_phys_region(void *start, void *end)
 	k_start = ALIGN_DOWN((unsigned long)kasan_mem_to_shadow(start), PAGE_SIZE);
 	k_end = ALIGN((unsigned long)kasan_mem_to_shadow(end), PAGE_SIZE);
 
-	va = memblock_alloc(k_end - k_start, PAGE_SIZE);
+	va = memblock_alloc_or_panic(k_end - k_start, PAGE_SIZE);
 	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE, va += PAGE_SIZE)
 		map_kernel_page(k_cur, __pa(va), PAGE_KERNEL);
 }
diff --git a/arch/powerpc/mm/nohash/mmu_context.c b/arch/powerpc/mm/nohash/mmu_context.c
index 0b181da40ddb..a1a4e697251a 100644
--- a/arch/powerpc/mm/nohash/mmu_context.c
+++ b/arch/powerpc/mm/nohash/mmu_context.c
@@ -385,21 +385,11 @@ void __init mmu_context_init(void)
 	/*
 	 * Allocate the maps used by context management
 	 */
-	context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
-	if (!context_map)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      CTX_MAP_SIZE);
-	context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1),
+	context_map = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES);
+	context_mm = memblock_alloc_or_panic(sizeof(void *) * (LAST_CONTEXT + 1),
 				    SMP_CACHE_BYTES);
-	if (!context_mm)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(void *) * (LAST_CONTEXT + 1));
 	if (IS_ENABLED(CONFIG_SMP)) {
-		stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES);
-		if (!stale_map[boot_cpuid])
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      CTX_MAP_SIZE);
-
+		stale_map[boot_cpuid] = memblock_alloc_or_panic(CTX_MAP_SIZE, SMP_CACHE_BYTES);
 		cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
 					  "powerpc/mmu/ctx:prepare",
 					  mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead);
diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c
index e89f64a0f24a..713268ccb1a0 100644
--- a/arch/powerpc/mm/pgtable-frag.c
+++ b/arch/powerpc/mm/pgtable-frag.c
@@ -25,7 +25,7 @@ void pte_frag_destroy(void *pte_frag)
 	count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
 	if (atomic_sub_and_test(PTE_FRAG_NR - count, &ptdesc->pt_frag_refcount)) {
-		pagetable_pte_dtor(ptdesc);
+		pagetable_dtor(ptdesc);
 		pagetable_free(ptdesc);
 	}
 }
@@ -111,7 +111,7 @@ static void pte_free_now(struct rcu_head *head)
 	struct ptdesc *ptdesc;
 
 	ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
-	pagetable_pte_dtor(ptdesc);
+	pagetable_dtor(ptdesc);
 	pagetable_free(ptdesc);
 }
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 787b22206386..15276068f657 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -50,13 +50,8 @@ notrace void __init early_ioremap_init(void)
 
 void __init *early_alloc_pgtable(unsigned long size)
 {
-	void *ptr = memblock_alloc(size, size);
+	return memblock_alloc_or_panic(size, size);
 
-	if (!ptr)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, size, size);
-
-	return ptr;
 }
 
 pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index fe2e0249cbc2..a112d26185a0 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -514,10 +514,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr)
 		printk(KERN_ERR "nvram: no address\n");
 		return -EINVAL;
 	}
-	nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES);
-	if (!nvram_image)
-		panic("%s: Failed to allocate %u bytes\n", __func__,
-		      NVRAM_SIZE);
+	nvram_image = memblock_alloc_or_panic(NVRAM_SIZE, SMP_CACHE_BYTES);
 	nvram_data = ioremap(addr, NVRAM_SIZE*2);
 	nvram_naddrs = 1; /* Make sure we get the correct case */
 
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 877720c64515..4ac9808e55a4 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -88,26 +88,6 @@ static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
 	}
 }
 
-static void memtrace_clear_range(unsigned long start_pfn,
-				 unsigned long nr_pages)
-{
-	unsigned long pfn;
-
-	/* As HIGHMEM does not apply, use clear_page() directly. */
-	for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
-		if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
-			cond_resched();
-		clear_page(__va(PFN_PHYS(pfn)));
-	}
-	/*
-	 * Before we go ahead and use this range as cache inhibited range
-	 * flush the cache.
-	 */
-	flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
-				   (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
-				   FLUSH_CHUNK_SIZE);
-}
-
 static u64 memtrace_alloc_node(u32 nid, u64 size)
 {
 	const unsigned long nr_pages = PHYS_PFN(size);
@@ -119,17 +99,18 @@ static u64 memtrace_alloc_node(u32 nid, u64 size)
 	 * by alloc_contig_pages().
 	 */
 	page = alloc_contig_pages(nr_pages, GFP_KERNEL | __GFP_THISNODE |
-				  __GFP_NOWARN, nid, NULL);
+				  __GFP_NOWARN | __GFP_ZERO, nid, NULL);
 	if (!page)
 		return 0;
 	start_pfn = page_to_pfn(page);
 
 	/*
-	 * Clear the range while we still have a linear mapping.
-	 *
-	 * TODO: use __GFP_ZERO with alloc_contig_pages() once supported.
+	 * Before we go ahead and use this range as cache inhibited range
+	 * flush the cache.
 	 */
-	memtrace_clear_range(start_pfn, nr_pages);
+	flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
+				   (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
+				   FLUSH_CHUNK_SIZE);
 
 	/*
 	 * Set pages PageOffline(), to indicate that nobody (e.g., hibernation,
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 5d0f35bb917e..9ec265fcaff4 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -180,10 +180,7 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
 	/*
 	 * Allocate a buffer to hold the MC recoverable ranges.
 	 */
-	mc_recoverable_range = memblock_alloc(size, __alignof__(u64));
-	if (!mc_recoverable_range)
-		panic("%s: Failed to allocate %u bytes align=0x%lx\n",
-		      __func__, size, __alignof__(u64));
+	mc_recoverable_range = memblock_alloc_or_panic(size, __alignof__(u64));
 
 	for (i = 0; i < mc_recoverable_range_len; i++) {
 		mc_recoverable_range[i].start_addr =
@@ -818,7 +815,7 @@ static int opal_add_one_export(struct kobject *parent, const char *export_name,
 	sysfs_bin_attr_init(attr);
 	attr->attr.name = name;
 	attr->attr.mode = 0400;
-	attr->read = sysfs_bin_attr_simple_read;
+	attr->read_new = sysfs_bin_attr_simple_read;
 	attr->private = __va(vals[0]);
 	attr->size = vals[1];
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 5144f11359f7..150c09b58ae8 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -115,10 +115,7 @@ static void __init prealloc(struct ps3_prealloc *p)
 	if (!p->size)
 		return;
 
-	p->address = memblock_alloc(p->size, p->align);
-	if (!p->address)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, p->size, p->align);
+	p->address = memblock_alloc_or_panic(p->size, p->align);
 
 	printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size,
 	       p->address);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 1893f66371fa..b12ef382fec7 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -580,8 +580,10 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay)
 
 	switch(rets[0]) {
 	case 0:
-		result = EEH_STATE_MMIO_ACTIVE |
-			 EEH_STATE_DMA_ACTIVE;
+		result = EEH_STATE_MMIO_ACTIVE	|
+			 EEH_STATE_DMA_ACTIVE	|
+			 EEH_STATE_MMIO_ENABLED	|
+			 EEH_STATE_DMA_ENABLED;
 		break;
 	case 1:
 		result = EEH_STATE_RESET_ACTIVE |
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 29f1a0cc59cd..ae6f7a235d8b 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -2208,6 +2208,9 @@ static long spapr_tce_unset_window(struct iommu_table_group *table_group, int nu
 	const char *win_name;
 	int ret = -ENODEV;
 
+	if (!tbl) /* The table was never created OR window was never opened */
+		return 0;
+
 	mutex_lock(&dma_win_init_mutex);
 
 	if ((num == 0) && is_default_window_table(table_group, tbl))
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 1798f0f14d58..62bd8e2d5d4c 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -53,7 +53,7 @@ struct update_props_workarea {
 static unsigned int nmi_wd_lpm_factor = 200;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
+static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
 	{
 		.procname	= "nmi_wd_lpm_factor",
 		.data		= &nmi_wd_lpm_factor,
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index f84ac9fbe203..f7c9271bda58 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -544,7 +544,7 @@ static int drc_pmem_query_health(struct papr_scm_priv *p)
 
 	/* Jiffies offset for which the health data is assumed to be same */
 	cache_timeout = p->lasthealth_jiffies +
-		msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000);
+		secs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL);
 
 	/* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */
 	if (time_after(jiffies, cache_timeout))
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 1aa0cb097c9c..7b9a5ea9cad9 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -75,7 +75,7 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p)
 	srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK;
 	cascade_virq = msi_data->cascade_array[srs]->virq;
 
-	seq_printf(p, " fsl-msi-%d", cascade_virq);
+	seq_printf(p, "fsl-msi-%d", cascade_virq);
 }
 
 
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 0b6e37f3ffb8..456a4f64ae0a 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -124,10 +124,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count,
 	if (bmp->bitmap_from_slab)
 		bmp->bitmap = kzalloc(size, GFP_KERNEL);
 	else {
-		bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES);
-		if (!bmp->bitmap)
-			panic("%s: Failed to allocate %u bytes\n", __func__,
-			      size);
+		bmp->bitmap = memblock_alloc_or_panic(size, SMP_CACHE_BYTES);
 		/* the bitmap won't be freed from memblock allocator */
 		kmemleak_not_leak(bmp->bitmap);
 	}
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 2acc7d876e1f..e318119d570d 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -119,4 +119,15 @@ config ERRATA_THEAD_PMU
 
 	  If you don't know what to do here, say "Y".
 
+config ERRATA_THEAD_GHOSTWRITE
+	bool "Apply T-Head Ghostwrite errata"
+	depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR
+	default y
+	help
+	  The T-Head C9xx cores have a vulnerability in the xtheadvector
+	  instruction set. When this errata is enabled, the CPUs will be probed
+	  to determine if they are vulnerable and disable xtheadvector.
+
+	  If you don't know what to do here, say "Y".
+
 endmenu # "CPU errata selection"
diff --git a/arch/riscv/Kconfig.vendor b/arch/riscv/Kconfig.vendor
index 6f1cdd32ed29..b096548fe0ff 100644
--- a/arch/riscv/Kconfig.vendor
+++ b/arch/riscv/Kconfig.vendor
@@ -16,4 +16,30 @@ config RISCV_ISA_VENDOR_EXT_ANDES
 	  If you don't know what to do here, say Y.
 endmenu
 
+menu "T-Head"
+config RISCV_ISA_VENDOR_EXT_THEAD
+	bool "T-Head vendor extension support"
+	select RISCV_ISA_VENDOR_EXT
+	default y
+	help
+	  Say N here to disable detection of and support for all T-Head vendor
+	  extensions. Without this option enabled, T-Head vendor extensions will
+	  not be detected at boot and their presence not reported to userspace.
+
+	  If you don't know what to do here, say Y.
+
+config RISCV_ISA_XTHEADVECTOR
+	bool "xtheadvector extension support"
+	depends on RISCV_ISA_VENDOR_EXT_THEAD
+	depends on RISCV_ISA_V
+	depends on FPU
+	default y
+	help
+	  Say N here if you want to disable all xtheadvector related procedures
+	  in the kernel. This will disable vector for any T-Head board that
+	  contains xtheadvector rather than the standard vector.
+
+	  If you don't know what to do here, say Y.
+endmenu
+
 endmenu
diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink
index 829b9abc91f6..6b0580949b6a 100644
--- a/arch/riscv/Makefile.postlink
+++ b/arch/riscv/Makefile.postlink
@@ -10,6 +10,7 @@ __archpost:
 
 -include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
+include $(srctree)/scripts/Makefile.lib
 
 quiet_cmd_relocs_check = CHKREL  $@
 cmd_relocs_check = 							\
@@ -19,11 +20,6 @@ ifdef CONFIG_RELOCATABLE
 quiet_cmd_cp_vmlinux_relocs = CPREL   vmlinux.relocs
 cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs
 
-quiet_cmd_relocs_strip = STRIPREL $@
-cmd_relocs_strip = $(OBJCOPY)   --remove-section='.rel.*'       \
-                                --remove-section='.rel__*'      \
-                                --remove-section='.rela.*'      \
-                                --remove-section='.rela__*' $@
 endif
 
 # `@true` prevents complaint when there is nothing to be done
@@ -33,7 +29,7 @@ vmlinux: FORCE
 ifdef CONFIG_RELOCATABLE
 	$(call if_changed,relocs_check)
 	$(call if_changed,cp_vmlinux_relocs)
-	$(call if_changed,relocs_strip)
+	$(call if_changed,strip_relocs)
 endif
 
 clean:
diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi
index 64c3c2e6cbe0..6367112e614a 100644
--- a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi
+++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi
@@ -27,7 +27,8 @@
 			riscv,isa = "rv64imafdc";
 			riscv,isa-base = "rv64i";
 			riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr",
-					       "zifencei", "zihpm";
+					       "zifencei", "zihpm", "xtheadvector";
+			thead,vlenb = <128>;
 			#cooling-cells = <2>;
 
 			cpu0_intc: interrupt-controller {
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index a924ef116d5e..0f7dcbe3c45b 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -10,7 +10,6 @@ CONFIG_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_CFS_BANDWIDTH=y
-CONFIG_RT_GROUP_SCHED=y
 CONFIG_CGROUP_PIDS=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_HUGETLB=y
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index e24770a77932..0b942183f708 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -10,6 +10,7 @@
 #include <linux/string.h>
 #include <linux/uaccess.h>
 #include <asm/alternative.h>
+#include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/dma-noncoherent.h>
@@ -142,6 +143,31 @@ static bool errata_probe_pmu(unsigned int stage,
 	return true;
 }
 
+static bool errata_probe_ghostwrite(unsigned int stage,
+				    unsigned long arch_id, unsigned long impid)
+{
+	if (!IS_ENABLED(CONFIG_ERRATA_THEAD_GHOSTWRITE))
+		return false;
+
+	/*
+	 * target-c9xx cores report arch_id and impid as 0
+	 *
+	 * While ghostwrite may not affect all c9xx cores that implement
+	 * xtheadvector, there is no futher granularity than c9xx. Assume
+	 * vulnerable for this entire class of processors when xtheadvector is
+	 * enabled.
+	 */
+	if (arch_id != 0 || impid != 0)
+		return false;
+
+	if (stage != RISCV_ALTERNATIVES_EARLY_BOOT)
+		return false;
+
+	ghostwrite_set_vulnerable();
+
+	return true;
+}
+
 static u32 thead_errata_probe(unsigned int stage,
 			      unsigned long archid, unsigned long impid)
 {
@@ -155,6 +181,8 @@ static u32 thead_errata_probe(unsigned int stage,
 	if (errata_probe_pmu(stage, archid, impid))
 		cpu_req_errata |= BIT(ERRATA_THEAD_PMU);
 
+	errata_probe_ghostwrite(stage, archid, impid);
+
 	return cpu_req_errata;
 }
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index fae152ea0508..c6bd3d8354a9 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -228,7 +228,7 @@ legacy:
  *
  * This operation may be reordered on other architectures than x86.
  */
-static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr)
 {
 	return __test_and_op_bit(or, __NOP, nr, addr);
 }
@@ -240,7 +240,7 @@ static inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr)
  *
  * This operation can be reordered on other architectures other than x86.
  */
-static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
 	return __test_and_op_bit(and, __NOT, nr, addr);
 }
@@ -253,7 +253,7 @@ static inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr)
+static __always_inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr)
 {
 	return __test_and_op_bit(xor, __NOP, nr, addr);
 }
@@ -270,7 +270,7 @@ static inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void arch_set_bit(int nr, volatile unsigned long *addr)
+static __always_inline void arch_set_bit(int nr, volatile unsigned long *addr)
 {
 	__op_bit(or, __NOP, nr, addr);
 }
@@ -284,7 +284,7 @@ static inline void arch_set_bit(int nr, volatile unsigned long *addr)
  * on non x86 architectures, so if you are writing portable code,
  * make sure not to rely on its reordering guarantees.
  */
-static inline void arch_clear_bit(int nr, volatile unsigned long *addr)
+static __always_inline void arch_clear_bit(int nr, volatile unsigned long *addr)
 {
 	__op_bit(and, __NOT, nr, addr);
 }
@@ -298,7 +298,7 @@ static inline void arch_clear_bit(int nr, volatile unsigned long *addr)
  * Note that @nr may be almost arbitrarily large; this function is not
  * restricted to acting on a single-word quantity.
  */
-static inline void arch_change_bit(int nr, volatile unsigned long *addr)
+static __always_inline void arch_change_bit(int nr, volatile unsigned long *addr)
 {
 	__op_bit(xor, __NOP, nr, addr);
 }
@@ -311,7 +311,7 @@ static inline void arch_change_bit(int nr, volatile unsigned long *addr)
  * This operation is atomic and provides acquire barrier semantics.
  * It can be used to implement bit locks.
  */
-static inline int arch_test_and_set_bit_lock(
+static __always_inline int arch_test_and_set_bit_lock(
 	unsigned long nr, volatile unsigned long *addr)
 {
 	return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq);
@@ -324,7 +324,7 @@ static inline int arch_test_and_set_bit_lock(
  *
  * This operation is atomic and provides release barrier semantics.
  */
-static inline void arch_clear_bit_unlock(
+static __always_inline void arch_clear_bit_unlock(
 	unsigned long nr, volatile unsigned long *addr)
 {
 	__op_bit_ord(and, __NOT, nr, addr, .rl);
@@ -345,13 +345,13 @@ static inline void arch_clear_bit_unlock(
  * non-atomic property here: it's a lot more instructions and we still have to
  * provide release semantics anyway.
  */
-static inline void arch___clear_bit_unlock(
+static __always_inline void arch___clear_bit_unlock(
 	unsigned long nr, volatile unsigned long *addr)
 {
 	arch_clear_bit_unlock(nr, addr);
 }
 
-static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
 		volatile unsigned long *addr)
 {
 	unsigned long res;
diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h
new file mode 100644
index 000000000000..17ca0a947730
--- /dev/null
+++ b/arch/riscv/include/asm/bugs.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Interface for managing mitigations for riscv vulnerabilities.
+ *
+ * Copyright (C) 2024 Rivos Inc.
+ */
+
+#ifndef __ASM_BUGS_H
+#define __ASM_BUGS_H
+
+/* Watch out, ordering is important here. */
+enum mitigation_state {
+	UNAFFECTED,
+	MITIGATED,
+	VULNERABLE,
+};
+
+void ghostwrite_set_vulnerable(void);
+bool ghostwrite_enable_mitigation(void);
+enum mitigation_state ghostwrite_get_state(void);
+
+#endif /* __ASM_BUGS_H */
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index 4bd054c54c21..569140d6e639 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -34,6 +34,8 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
+extern u32 thead_vlenb_of;
+
 void __init riscv_user_isa_enable(void);
 
 #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) {	\
diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h
index 37bdea65bbd8..6fed42e37705 100644
--- a/arch/riscv/include/asm/csr.h
+++ b/arch/riscv/include/asm/csr.h
@@ -30,6 +30,12 @@
 #define SR_VS_CLEAN	_AC(0x00000400, UL)
 #define SR_VS_DIRTY	_AC(0x00000600, UL)
 
+#define SR_VS_THEAD		_AC(0x01800000, UL) /* xtheadvector Status */
+#define SR_VS_OFF_THEAD		_AC(0x00000000, UL)
+#define SR_VS_INITIAL_THEAD	_AC(0x00800000, UL)
+#define SR_VS_CLEAN_THEAD	_AC(0x01000000, UL)
+#define SR_VS_DIRTY_THEAD	_AC(0x01800000, UL)
+
 #define SR_XS		_AC(0x00018000, UL) /* Extension Status */
 #define SR_XS_OFF	_AC(0x00000000, UL)
 #define SR_XS_INITIAL	_AC(0x00008000, UL)
@@ -315,6 +321,15 @@
 #define CSR_STIMECMP		0x14D
 #define CSR_STIMECMPH		0x15D
 
+/* xtheadvector symbolic CSR names */
+#define CSR_VXSAT		0x9
+#define CSR_VXRM		0xa
+
+/* xtheadvector CSR masks */
+#define CSR_VXRM_MASK		3
+#define CSR_VXRM_SHIFT		1
+#define CSR_VXSAT_MASK		1
+
 /* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */
 #define CSR_SISELECT		0x150
 #define CSR_SIREG		0x151
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 7c8a71a526a3..6e426ed7919a 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -25,7 +25,8 @@
 #ifdef CONFIG_ERRATA_THEAD
 #define	ERRATA_THEAD_MAE 0
 #define	ERRATA_THEAD_PMU 1
-#define	ERRATA_THEAD_NUMBER 2
+#define	ERRATA_THEAD_GHOSTWRITE 2
+#define	ERRATA_THEAD_NUMBER 3
 #endif
 
 #ifdef __ASSEMBLY__
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index fc8130f995c1..72be100afa23 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 	__enable_user_access();
 	__asm__ __volatile__ (
-	"1:	lr.w.aqrl %[v],%[u]			\n"
+	"1:	lr.w %[v],%[u]			        \n"
 	"	bne %[v],%z[ov],3f			\n"
 	"2:	sc.w.aqrl %[t],%z[nv],%[u]		\n"
 	"	bnez %[t],1b				\n"
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 1ce1df6d0ff3..dd624523981c 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * Copyright 2023 Rivos, Inc
+ * Copyright 2023-2024 Rivos, Inc
  */
 
 #ifndef _ASM_HWPROBE_H
@@ -8,7 +8,7 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 10
+#define RISCV_HWPROBE_MAX_KEY 11
 
 static inline bool riscv_hwprobe_key_is_valid(__s64 key)
 {
@@ -21,6 +21,7 @@ static inline bool hwprobe_key_is_bitmask(__s64 key)
 	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
 	case RISCV_HWPROBE_KEY_IMA_EXT_0:
 	case RISCV_HWPROBE_KEY_CPUPERF_0:
+	case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0:
 		return true;
 	}
 
diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h
index f52264304f77..3e2aebea6312 100644
--- a/arch/riscv/include/asm/pgalloc.h
+++ b/arch/riscv/include/asm/pgalloc.h
@@ -12,16 +12,25 @@
 #include <asm/tlb.h>
 
 #ifdef CONFIG_MMU
-#define __HAVE_ARCH_PUD_ALLOC_ONE
 #define __HAVE_ARCH_PUD_FREE
 #include <asm-generic/pgalloc.h>
 
+/*
+ * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
+ * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
+ * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
+ * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
+ * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
+ * for more details.
+ */
 static inline void riscv_tlb_remove_ptdesc(struct mmu_gather *tlb, void *pt)
 {
-	if (riscv_use_sbi_for_rfence())
+	if (riscv_use_sbi_for_rfence()) {
 		tlb_remove_ptdesc(tlb, pt);
-	else
+	} else {
+		pagetable_dtor(pt);
 		tlb_remove_page_ptdesc(tlb, pt);
+	}
 }
 
 static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -88,15 +97,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd,
 	}
 }
 
-#define pud_alloc_one pud_alloc_one
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	if (pgtable_l4_enabled)
-		return __pud_alloc_one(mm, addr);
-
-	return NULL;
-}
-
 #define pud_free pud_free
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
@@ -107,39 +107,8 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 				  unsigned long addr)
 {
-	if (pgtable_l4_enabled) {
-		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
-
-		pagetable_pud_dtor(ptdesc);
-		riscv_tlb_remove_ptdesc(tlb, ptdesc);
-	}
-}
-
-#define p4d_alloc_one p4d_alloc_one
-static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	if (pgtable_l5_enabled) {
-		gfp_t gfp = GFP_PGTABLE_USER;
-
-		if (mm == &init_mm)
-			gfp = GFP_PGTABLE_KERNEL;
-		return (p4d_t *)get_zeroed_page(gfp);
-	}
-
-	return NULL;
-}
-
-static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
-{
-	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
-	free_page((unsigned long)p4d);
-}
-
-#define p4d_free p4d_free
-static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
-{
-	if (pgtable_l5_enabled)
-		__p4d_free(mm, p4d);
+	if (pgtable_l4_enabled)
+		riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
 }
 
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
@@ -161,9 +130,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 
-	pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+	pgd = __pgd_alloc(mm, 0);
 	if (likely(pgd != NULL)) {
-		memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
 		/* Copy kernel mappings */
 		sync_kernel_mappings(pgd);
 	}
@@ -175,10 +143,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				  unsigned long addr)
 {
-	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
-
-	pagetable_pmd_dtor(ptdesc);
-	riscv_tlb_remove_ptdesc(tlb, ptdesc);
+	riscv_tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
 }
 
 #endif /* __PAGETABLE_PMD_FOLDED */
@@ -186,10 +151,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				  unsigned long addr)
 {
-	struct ptdesc *ptdesc = page_ptdesc(pte);
-
-	pagetable_pte_dtor(ptdesc);
-	riscv_tlb_remove_ptdesc(tlb, ptdesc);
+	riscv_tlb_remove_ptdesc(tlb, page_ptdesc(pte));
 }
 #endif /* CONFIG_MMU */
 
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index 94e33216b2d9..0e71eb82f920 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -117,7 +117,7 @@ do {							\
 	__set_prev_cpu(__prev->thread);			\
 	if (has_fpu())					\
 		__switch_to_fpu(__prev, __next);	\
-	if (has_vector())					\
+	if (has_vector() || has_xtheadvector())		\
 		__switch_to_vector(__prev, __next);	\
 	if (switch_to_should_flush_icache(__next))	\
 		local_flush_icache_all();		\
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 1f6c38420d8e..50b63b5c15bd 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -10,24 +10,6 @@ struct mmu_gather;
 
 static void tlb_flush(struct mmu_gather *tlb);
 
-#ifdef CONFIG_MMU
-#include <linux/swap.h>
-
-/*
- * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
- * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
- * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
- * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
- * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
- * for more details.
- */
-static inline void __tlb_remove_table(void *table)
-{
-	free_page_and_swap_cache(table);
-}
-
-#endif /* CONFIG_MMU */
-
 #define tlb_flush tlb_flush
 #include <asm-generic/tlb.h>
 
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index c7c023afbacd..e8a83f55be2b 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -18,6 +18,27 @@
 #include <asm/cpufeature.h>
 #include <asm/csr.h>
 #include <asm/asm.h>
+#include <asm/vendorid_list.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/thead.h>
+
+#define __riscv_v_vstate_or(_val, TYPE) ({				\
+	typeof(_val) _res = _val;					\
+	if (has_xtheadvector()) \
+		_res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD;	\
+	else								\
+		_res = (_res & ~SR_VS) | SR_VS_##TYPE;			\
+	_res;								\
+})
+
+#define __riscv_v_vstate_check(_val, TYPE) ({				\
+	bool _res;							\
+	if (has_xtheadvector()) \
+		_res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD;	\
+	else								\
+		_res = ((_val) & SR_VS) == SR_VS_##TYPE;		\
+	_res;								\
+})
 
 extern unsigned long riscv_v_vsize;
 int riscv_v_setup_vsize(void);
@@ -41,39 +62,62 @@ static __always_inline bool has_vector(void)
 	return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X);
 }
 
+static __always_inline bool has_xtheadvector_no_alternatives(void)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+		return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR);
+	else
+		return false;
+}
+
+static __always_inline bool has_xtheadvector(void)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+		return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID,
+							   RISCV_ISA_VENDOR_EXT_XTHEADVECTOR);
+	else
+		return false;
+}
+
 static inline void __riscv_v_vstate_clean(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN;
+	regs->status = __riscv_v_vstate_or(regs->status, CLEAN);
 }
 
 static inline void __riscv_v_vstate_dirty(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY;
+	regs->status = __riscv_v_vstate_or(regs->status, DIRTY);
 }
 
 static inline void riscv_v_vstate_off(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_OFF;
+	regs->status = __riscv_v_vstate_or(regs->status, OFF);
 }
 
 static inline void riscv_v_vstate_on(struct pt_regs *regs)
 {
-	regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL;
+	regs->status = __riscv_v_vstate_or(regs->status, INITIAL);
 }
 
 static inline bool riscv_v_vstate_query(struct pt_regs *regs)
 {
-	return (regs->status & SR_VS) != 0;
+	return !__riscv_v_vstate_check(regs->status, OFF);
 }
 
 static __always_inline void riscv_v_enable(void)
 {
-	csr_set(CSR_SSTATUS, SR_VS);
+	if (has_xtheadvector())
+		csr_set(CSR_SSTATUS, SR_VS_THEAD);
+	else
+		csr_set(CSR_SSTATUS, SR_VS);
 }
 
 static __always_inline void riscv_v_disable(void)
 {
-	csr_clear(CSR_SSTATUS, SR_VS);
+	if (has_xtheadvector())
+		csr_clear(CSR_SSTATUS, SR_VS_THEAD);
+	else
+		csr_clear(CSR_SSTATUS, SR_VS);
 }
 
 static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
@@ -82,10 +126,36 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest)
 		"csrr	%0, " __stringify(CSR_VSTART) "\n\t"
 		"csrr	%1, " __stringify(CSR_VTYPE) "\n\t"
 		"csrr	%2, " __stringify(CSR_VL) "\n\t"
-		"csrr	%3, " __stringify(CSR_VCSR) "\n\t"
-		"csrr	%4, " __stringify(CSR_VLENB) "\n\t"
 		: "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl),
-		  "=r" (dest->vcsr), "=r" (dest->vlenb) : :);
+		"=r" (dest->vcsr) : :);
+
+	if (has_xtheadvector()) {
+		unsigned long status;
+
+		/*
+		 * CSR_VCSR is defined as
+		 * [2:1] - vxrm[1:0]
+		 * [0] - vxsat
+		 * The earlier vector spec implemented by T-Head uses separate
+		 * registers for the same bit-elements, so just combine those
+		 * into the existing output field.
+		 *
+		 * Additionally T-Head cores need FS to be enabled when accessing
+		 * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions.
+		 * Though the cores do not implement the VXRM and VXSAT fields in the
+		 * FCSR CSR that vector-0.7.1 specifies.
+		 */
+		status = csr_read_set(CSR_STATUS, SR_FS_DIRTY);
+		dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT;
+
+		dest->vlenb = riscv_v_vsize / 32;
+
+		if ((status & SR_FS) != SR_FS_DIRTY)
+			csr_write(CSR_STATUS, status);
+	} else {
+		dest->vcsr = csr_read(CSR_VCSR);
+		dest->vlenb = csr_read(CSR_VLENB);
+	}
 }
 
 static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src)
@@ -96,9 +166,25 @@ static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src
 		"vsetvl	 x0, %2, %1\n\t"
 		".option pop\n\t"
 		"csrw	" __stringify(CSR_VSTART) ", %0\n\t"
-		"csrw	" __stringify(CSR_VCSR) ", %3\n\t"
-		: : "r" (src->vstart), "r" (src->vtype), "r" (src->vl),
-		    "r" (src->vcsr) :);
+		: : "r" (src->vstart), "r" (src->vtype), "r" (src->vl));
+
+	if (has_xtheadvector()) {
+		unsigned long status = csr_read(CSR_SSTATUS);
+
+		/*
+		 * Similar to __vstate_csr_save above, restore values for the
+		 * separate VXRM and VXSAT CSRs from the vcsr variable.
+		 */
+		status = csr_read_set(CSR_STATUS, SR_FS_DIRTY);
+
+		csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK);
+		csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK);
+
+		if ((status & SR_FS) != SR_FS_DIRTY)
+			csr_write(CSR_STATUS, status);
+	} else {
+		csr_write(CSR_VCSR, src->vcsr);
+	}
 }
 
 static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
@@ -108,19 +194,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
 
 	riscv_v_enable();
 	__vstate_csr_save(save_to);
-	asm volatile (
-		".option push\n\t"
-		".option arch, +zve32x\n\t"
-		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
-		"vse8.v		v0, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vse8.v		v8, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vse8.v		v16, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vse8.v		v24, (%1)\n\t"
-		".option pop\n\t"
-		: "=&r" (vl) : "r" (datap) : "memory");
+	if (has_xtheadvector()) {
+		asm volatile (
+			"mv t0, %0\n\t"
+			THEAD_VSETVLI_T4X0E8M8D1
+			THEAD_VSB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VSB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VSB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VSB_V_V0T0
+			: : "r" (datap) : "memory", "t0", "t4");
+	} else {
+		asm volatile (
+			".option push\n\t"
+			".option arch, +zve32x\n\t"
+			"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
+			"vse8.v		v0, (%1)\n\t"
+			"add		%1, %1, %0\n\t"
+			"vse8.v		v8, (%1)\n\t"
+			"add		%1, %1, %0\n\t"
+			"vse8.v		v16, (%1)\n\t"
+			"add		%1, %1, %0\n\t"
+			"vse8.v		v24, (%1)\n\t"
+			".option pop\n\t"
+			: "=&r" (vl) : "r" (datap) : "memory");
+	}
 	riscv_v_disable();
 }
 
@@ -130,19 +230,33 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 	unsigned long vl;
 
 	riscv_v_enable();
-	asm volatile (
-		".option push\n\t"
-		".option arch, +zve32x\n\t"
-		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
-		"vle8.v		v0, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vle8.v		v8, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vle8.v		v16, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vle8.v		v24, (%1)\n\t"
-		".option pop\n\t"
-		: "=&r" (vl) : "r" (datap) : "memory");
+	if (has_xtheadvector()) {
+		asm volatile (
+			"mv t0, %0\n\t"
+			THEAD_VSETVLI_T4X0E8M8D1
+			THEAD_VLB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VLB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VLB_V_V0T0
+			"add		t0, t0, t4\n\t"
+			THEAD_VLB_V_V0T0
+			: : "r" (datap) : "memory", "t0", "t4");
+	} else {
+		asm volatile (
+			".option push\n\t"
+			".option arch, +zve32x\n\t"
+			"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
+			"vle8.v		v0, (%1)\n\t"
+			"add		%1, %1, %0\n\t"
+			"vle8.v		v8, (%1)\n\t"
+			"add		%1, %1, %0\n\t"
+			"vle8.v		v16, (%1)\n\t"
+			"add		%1, %1, %0\n\t"
+			"vle8.v		v24, (%1)\n\t"
+			".option pop\n\t"
+			: "=&r" (vl) : "r" (datap) : "memory");
+	}
 	__vstate_csr_restore(restore_from);
 	riscv_v_disable();
 }
@@ -152,33 +266,41 @@ static inline void __riscv_v_vstate_discard(void)
 	unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1);
 
 	riscv_v_enable();
+	if (has_xtheadvector())
+		asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4");
+	else
+		asm volatile (
+			".option push\n\t"
+			".option arch, +zve32x\n\t"
+			"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
+			".option pop\n\t": "=&r" (vl));
+
 	asm volatile (
 		".option push\n\t"
 		".option arch, +zve32x\n\t"
-		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
 		"vmv.v.i	v0, -1\n\t"
 		"vmv.v.i	v8, -1\n\t"
 		"vmv.v.i	v16, -1\n\t"
 		"vmv.v.i	v24, -1\n\t"
 		"vsetvl		%0, x0, %1\n\t"
 		".option pop\n\t"
-		: "=&r" (vl) : "r" (vtype_inval) : "memory");
+		: "=&r" (vl) : "r" (vtype_inval));
+
 	riscv_v_disable();
 }
 
 static inline void riscv_v_vstate_discard(struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) == SR_VS_OFF)
-		return;
-
-	__riscv_v_vstate_discard();
-	__riscv_v_vstate_dirty(regs);
+	if (riscv_v_vstate_query(regs)) {
+		__riscv_v_vstate_discard();
+		__riscv_v_vstate_dirty(regs);
+	}
 }
 
 static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 				       struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) == SR_VS_DIRTY) {
+	if (__riscv_v_vstate_check(regs->status, DIRTY)) {
 		__riscv_v_vstate_save(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
@@ -187,7 +309,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate,
 static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 					  struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) != SR_VS_OFF) {
+	if (riscv_v_vstate_query(regs)) {
 		__riscv_v_vstate_restore(vstate, vstate->datap);
 		__riscv_v_vstate_clean(regs);
 	}
@@ -196,7 +318,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate,
 static inline void riscv_v_vstate_set_restore(struct task_struct *task,
 					      struct pt_regs *regs)
 {
-	if ((regs->status & SR_VS) != SR_VS_OFF) {
+	if (riscv_v_vstate_query(regs)) {
 		set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE);
 		riscv_v_vstate_on(regs);
 	}
@@ -270,6 +392,8 @@ struct pt_regs;
 static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; }
 static __always_inline bool has_vector(void) { return false; }
 static __always_inline bool insn_is_vector(u32 insn_buf) { return false; }
+static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; }
+static __always_inline bool has_xtheadvector(void) { return false; }
 static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; }
 static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; }
diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h
new file mode 100644
index 000000000000..e85c75b3b340
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/thead.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H
+
+#include <asm/vendor_extensions.h>
+
+#include <linux/types.h>
+
+/*
+ * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX.
+ */
+#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR		0
+
+extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead;
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+void disable_xtheadvector(void);
+#else
+static inline void disable_xtheadvector(void) { }
+#endif
+
+/* Extension specific helpers */
+
+/*
+ * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older
+ * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for
+ * vsetvli	t4, x0, e8, m8, d1
+ */
+#define THEAD_VSETVLI_T4X0E8M8D1	".long	0x00307ed7\n\t"
+
+/*
+ * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same
+ * encoding as the standard vse8.v and vle8.v, compilers seem to optimize
+ * the call resulting in a different encoding and then using a value for
+ * the "mop" field that is not part of vector-0.7.1
+ * So encode specific variants for vstate_save and _restore.
+ */
+#define THEAD_VSB_V_V0T0		".long	0x02028027\n\t"
+#define THEAD_VSB_V_V8T0		".long	0x02028427\n\t"
+#define THEAD_VSB_V_V16T0		".long	0x02028827\n\t"
+#define THEAD_VSB_V_V24T0		".long	0x02028c27\n\t"
+#define THEAD_VLB_V_V0T0		".long	0x012028007\n\t"
+#define THEAD_VLB_V_V8T0		".long	0x012028407\n\t"
+#define THEAD_VLB_V_V16T0		".long	0x012028807\n\t"
+#define THEAD_VLB_V_V24T0		".long	0x012028c07\n\t"
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h
new file mode 100644
index 000000000000..65a9c5612466
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H
+#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H
+
+#include <linux/cpumask.h>
+
+#include <uapi/asm/hwprobe.h>
+
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus);
+#else
+static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair,
+						  const struct cpumask *cpus)
+{
+	pair->value = 0;
+}
+#endif
+
+#endif
diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h
new file mode 100644
index 000000000000..6b9293e984a9
--- /dev/null
+++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2024 Rivos, Inc
+ */
+
+#ifndef _ASM_RISCV_SYS_HWPROBE_H
+#define _ASM_RISCV_SYS_HWPROBE_H
+
+#include <asm/cpufeature.h>
+
+#define VENDOR_EXT_KEY(ext)								\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \
+			pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext;			\
+		else									\
+			missing |= RISCV_HWPROBE_VENDOR_EXT_##ext;			\
+	} while (false)
+
+/*
+ * Loop through and record extensions that 1) anyone has, and 2) anyone
+ * doesn't have.
+ *
+ * _extension_checks is an arbitrary C block to set the values of pair->value
+ * and missing. It should be filled with VENDOR_EXT_KEY expressions.
+ */
+#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks)	\
+	do {											\
+		int cpu;									\
+		u64 missing = 0;								\
+		for_each_cpu(cpu, (cpus)) {							\
+			struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu];	\
+			_extension_checks							\
+		}										\
+		(pair)->value &= ~missing;							\
+	} while (false)										\
+
+#endif /* _ASM_RISCV_SYS_HWPROBE_H */
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 3af142b99f77..c3c1cc951cb9 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * Copyright 2023 Rivos, Inc
+ * Copyright 2023-2024 Rivos, Inc
  */
 
 #ifndef _UAPI_ASM_HWPROBE_H
@@ -94,6 +94,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW		2
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_FAST		3
 #define		RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED	4
+#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0	11
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 /* Flags */
diff --git a/arch/riscv/include/uapi/asm/vendor/thead.h b/arch/riscv/include/uapi/asm/vendor/thead.h
new file mode 100644
index 000000000000..43790ebe5faf
--- /dev/null
+++ b/arch/riscv/include/uapi/asm/vendor/thead.h
@@ -0,0 +1,3 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#define		RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR	(1 << 0)
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 063d1faf5a53..8d186bfced45 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -123,3 +123,5 @@ obj-$(CONFIG_COMPAT)		+= compat_vdso/
 obj-$(CONFIG_64BIT)		+= pi/
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-$(CONFIG_ACPI_NUMA)	+= acpi_numa.o
+
+obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o
diff --git a/arch/riscv/kernel/bugs.c b/arch/riscv/kernel/bugs.c
new file mode 100644
index 000000000000..3655fe7d678c
--- /dev/null
+++ b/arch/riscv/kernel/bugs.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Rivos Inc.
+ */
+
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/sprintf.h>
+
+#include <asm/bugs.h>
+#include <asm/vendor_extensions/thead.h>
+
+static enum mitigation_state ghostwrite_state;
+
+void ghostwrite_set_vulnerable(void)
+{
+	ghostwrite_state = VULNERABLE;
+}
+
+/*
+ * Vendor extension alternatives will use the value set at the time of boot
+ * alternative patching, thus this must be called before boot alternatives are
+ * patched (and after extension probing) to be effective.
+ *
+ * Returns true if mitgated, false otherwise.
+ */
+bool ghostwrite_enable_mitigation(void)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR) &&
+	    ghostwrite_state == VULNERABLE && !cpu_mitigations_off()) {
+		disable_xtheadvector();
+		ghostwrite_state = MITIGATED;
+		return true;
+	}
+
+	return false;
+}
+
+enum mitigation_state ghostwrite_get_state(void)
+{
+	return ghostwrite_state;
+}
+
+ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) {
+		switch (ghostwrite_state) {
+		case UNAFFECTED:
+			return sprintf(buf, "Not affected\n");
+		case MITIGATED:
+			return sprintf(buf, "Mitigation: xtheadvector disabled\n");
+		case VULNERABLE:
+			fallthrough;
+		default:
+			return sprintf(buf, "Vulnerable\n");
+		}
+	} else {
+		return sprintf(buf, "Not affected\n");
+	}
+}
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c0916ed318c2..c6ba750536c3 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -17,6 +17,7 @@
 #include <linux/of.h>
 #include <asm/acpi.h>
 #include <asm/alternative.h>
+#include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/hwcap.h>
@@ -26,6 +27,7 @@
 #include <asm/sbi.h>
 #include <asm/vector.h>
 #include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/thead.h>
 
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
@@ -39,6 +41,8 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 /* Per-cpu ISA extensions. */
 struct riscv_isainfo hart_isa[NR_CPUS];
 
+u32 thead_vlenb_of;
+
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -791,9 +795,50 @@ static void __init riscv_fill_vendor_ext_list(int cpu)
 	}
 }
 
+static int has_thead_homogeneous_vlenb(void)
+{
+	int cpu;
+	u32 prev_vlenb = 0;
+	u32 vlenb;
+
+	/* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */
+	if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR))
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		struct device_node *cpu_node;
+
+		cpu_node = of_cpu_device_node_get(cpu);
+		if (!cpu_node) {
+			pr_warn("Unable to find cpu node\n");
+			return -ENOENT;
+		}
+
+		if (of_property_read_u32(cpu_node, "thead,vlenb", &vlenb)) {
+			of_node_put(cpu_node);
+
+			if (prev_vlenb)
+				return -ENOENT;
+			continue;
+		}
+
+		if (prev_vlenb && vlenb != prev_vlenb) {
+			of_node_put(cpu_node);
+			return -ENOENT;
+		}
+
+		prev_vlenb = vlenb;
+		of_node_put(cpu_node);
+	}
+
+	thead_vlenb_of = vlenb;
+	return 0;
+}
+
 static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 {
 	unsigned int cpu;
+	bool mitigated;
 
 	for_each_possible_cpu(cpu) {
 		unsigned long this_hwcap = 0;
@@ -844,6 +889,17 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 		riscv_fill_vendor_ext_list(cpu);
 	}
 
+	/*
+	 * Execute ghostwrite mitigation immediately after detecting extensions
+	 * to disable xtheadvector if necessary.
+	 */
+	mitigated = ghostwrite_enable_mitigation();
+
+	if (!mitigated && has_xtheadvector_no_alternatives() && has_thead_homogeneous_vlenb() < 0) {
+		pr_warn("Unsupported heterogeneous vlenb detected, vector extension disabled.\n");
+		disable_xtheadvector();
+	}
+
 	if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX))
 		return -ENOENT;
 
@@ -896,7 +952,8 @@ void __init riscv_fill_hwcap(void)
 		elf_hwcap &= ~COMPAT_HWCAP_ISA_F;
 	}
 
-	if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X)) {
+	if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X) ||
+	    has_xtheadvector_no_alternatives()) {
 		/*
 		 * This cannot fail when called on the boot hart
 		 */
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
index 6afe80c7f03a..99972a48e86b 100644
--- a/arch/riscv/kernel/kernel_mode_vector.c
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -143,7 +143,7 @@ static int riscv_v_start_kernel_context(bool *is_nested)
 
 	/* Transfer the ownership of V from user to kernel, then save */
 	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
-	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+	if (__riscv_v_vstate_check(task_pt_regs(current)->status, DIRTY)) {
 		uvstate = &current->thread.vstate;
 		__riscv_v_vstate_save(uvstate, uvstate->datap);
 	}
@@ -160,7 +160,7 @@ asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
 		return;
 
 	depth = riscv_v_ctx_get_depth();
-	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+	if (depth == 0 && __riscv_v_vstate_check(regs->status, DIRTY))
 		riscv_preempt_v_set_dirty();
 
 	riscv_v_ctx_depth_inc();
@@ -208,7 +208,7 @@ void kernel_vector_begin(void)
 {
 	bool nested = false;
 
-	if (WARN_ON(!has_vector()))
+	if (WARN_ON(!(has_vector() || has_xtheadvector())))
 		return;
 
 	BUG_ON(!may_use_simd());
@@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(kernel_vector_begin);
  */
 void kernel_vector_end(void)
 {
-	if (WARN_ON(!has_vector()))
+	if (WARN_ON(!(has_vector() || has_xtheadvector())))
 		return;
 
 	riscv_v_disable();
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 58b6482c2bf6..7c244de77180 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -190,7 +190,7 @@ void flush_thread(void)
 void arch_release_task_struct(struct task_struct *tsk)
 {
 	/* Free the vector context of datap. */
-	if (has_vector())
+	if (has_vector() || has_xtheadvector())
 		riscv_v_thread_free(tsk);
 }
 
@@ -240,7 +240,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.s[0] = 0;
 	}
 	p->thread.riscv_v_flags = 0;
-	if (has_vector())
+	if (has_vector() || has_xtheadvector())
 		riscv_v_thread_alloc(p);
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
@@ -364,7 +364,7 @@ static bool try_to_set_pmm(unsigned long value)
  * disable it for tasks that already opted in to the relaxed ABI.
  */
 
-static struct ctl_table tagged_addr_sysctl_table[] = {
+static const struct ctl_table tagged_addr_sysctl_table[] = {
 	{
 		.procname	= "tagged_addr_disabled",
 		.mode		= 0644,
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 45010e71df86..f1793630fc51 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -147,9 +147,7 @@ static void __init init_resources(void)
 	res_idx = num_resources - 1;
 
 	mem_res_sz = num_resources * sizeof(*mem_res);
-	mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
-	if (!mem_res)
-		panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
+	mem_res = memblock_alloc_or_panic(mem_res_sz, SMP_CACHE_BYTES);
 
 	/*
 	 * Start by adding the reserved regions, if they overlap
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index dcd282419456..94e905eea1de 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -189,7 +189,7 @@ static long restore_sigcontext(struct pt_regs *regs,
 
 			return 0;
 		case RISCV_V_MAGIC:
-			if (!has_vector() || !riscv_v_vstate_query(regs) ||
+			if (!(has_vector() || has_xtheadvector()) || !riscv_v_vstate_query(regs) ||
 			    size != riscv_v_sc_size)
 				return -EINVAL;
 
@@ -211,7 +211,7 @@ static size_t get_rt_frame_size(bool cal_all)
 
 	frame_size = sizeof(*frame);
 
-	if (has_vector()) {
+	if (has_vector() || has_xtheadvector()) {
 		if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
 			total_context_size += riscv_v_sc_size;
 	}
@@ -284,7 +284,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame,
 	if (has_fpu())
 		err |= save_fp_state(regs, &sc->sc_fpregs);
 	/* Save the vector state. */
-	if (has_vector() && riscv_v_vstate_query(regs))
+	if ((has_vector() || has_xtheadvector()) && riscv_v_vstate_query(regs))
 		err |= save_v_state(regs, (void __user **)&sc_ext_ptr);
 	/* Write zero to fp-reserved space and check it on restore_sigcontext */
 	err |= __put_user(0, &sc->sc_extdesc.reserved);
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
index cb93adfffc48..bcd3b816306c 100644
--- a/arch/riscv/kernel/sys_hwprobe.c
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -15,6 +15,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/vector.h>
+#include <asm/vendor_extensions/thead_hwprobe.h>
 #include <vdso/vsyscall.h>
 
 
@@ -286,6 +287,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair,
 		pair->value = riscv_timebase;
 		break;
 
+	case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0:
+		hwprobe_isa_vendor_ext_thead_0(pair, cpus);
+		break;
+
 	/*
 	 * For forward compatibility, unknown keys don't fail the whole
 	 * call, but get their element key set to -1 and value set to 0
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 821818886fab..184f780c932d 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -33,7 +33,17 @@ int riscv_v_setup_vsize(void)
 {
 	unsigned long this_vsize;
 
-	/* There are 32 vector registers with vlenb length. */
+	/*
+	 * There are 32 vector registers with vlenb length.
+	 *
+	 * If the thead,vlenb property was provided by the firmware, use that
+	 * instead of probing the CSRs.
+	 */
+	if (thead_vlenb_of) {
+		riscv_v_vsize = thead_vlenb_of * 32;
+		return 0;
+	}
+
 	riscv_v_enable();
 	this_vsize = csr_read(CSR_VLENB) * 32;
 	riscv_v_disable();
@@ -53,7 +63,7 @@ int riscv_v_setup_vsize(void)
 
 void __init riscv_v_setup_ctx_cache(void)
 {
-	if (!has_vector())
+	if (!(has_vector() || has_xtheadvector()))
 		return;
 
 	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
@@ -173,7 +183,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	u32 __user *epc = (u32 __user *)regs->epc;
 	u32 insn = (u32)regs->badaddr;
 
-	if (!has_vector())
+	if (!(has_vector() || has_xtheadvector()))
 		return false;
 
 	/* Do not handle if V is not supported, or disabled */
@@ -216,7 +226,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk)
 	bool inherit;
 	int cur, next;
 
-	if (!has_vector())
+	if (!(has_vector() || has_xtheadvector()))
 		return;
 
 	next = riscv_v_ctrl_get_next(tsk);
@@ -238,7 +248,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk)
 
 long riscv_v_vstate_ctrl_get_current(void)
 {
-	if (!has_vector())
+	if (!(has_vector() || has_xtheadvector()))
 		return -EINVAL;
 
 	return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK;
@@ -249,7 +259,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg)
 	bool inherit;
 	int cur, next;
 
-	if (!has_vector())
+	if (!(has_vector() || has_xtheadvector()))
 		return -EINVAL;
 
 	if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK)
@@ -287,7 +297,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg)
 
 #ifdef CONFIG_SYSCTL
 
-static struct ctl_table riscv_v_default_vstate_table[] = {
+static const struct ctl_table riscv_v_default_vstate_table[] = {
 	{
 		.procname	= "riscv_v_default_allow",
 		.data		= &riscv_v_implicit_uacc,
@@ -299,7 +309,7 @@ static struct ctl_table riscv_v_default_vstate_table[] = {
 
 static int __init riscv_v_sysctl_init(void)
 {
-	if (has_vector())
+	if (has_vector() || has_xtheadvector())
 		if (!register_sysctl("abi", riscv_v_default_vstate_table))
 			return -EINVAL;
 	return 0;
@@ -309,7 +319,7 @@ static int __init riscv_v_sysctl_init(void)
 static int __init riscv_v_sysctl_init(void) { return 0; }
 #endif /* ! CONFIG_SYSCTL */
 
-static int riscv_v_init(void)
+static int __init riscv_v_init(void)
 {
 	return riscv_v_sysctl_init();
 }
diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c
index a8126d118341..a31ff84740eb 100644
--- a/arch/riscv/kernel/vendor_extensions.c
+++ b/arch/riscv/kernel/vendor_extensions.c
@@ -6,6 +6,7 @@
 #include <asm/vendorid_list.h>
 #include <asm/vendor_extensions.h>
 #include <asm/vendor_extensions/andes.h>
+#include <asm/vendor_extensions/thead.h>
 
 #include <linux/array_size.h>
 #include <linux/types.h>
@@ -14,6 +15,9 @@ struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[] = {
 #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES
 	&riscv_isa_vendor_ext_list_andes,
 #endif
+#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+	&riscv_isa_vendor_ext_list_thead,
+#endif
 };
 
 const size_t riscv_isa_vendor_ext_list_size = ARRAY_SIZE(riscv_isa_vendor_ext_list);
@@ -41,6 +45,12 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig
 		cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap;
 		break;
 	#endif
+	#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD
+	case THEAD_VENDOR_ID:
+		bmap = &riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap;
+		cpu_bmap = riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap;
+		break;
+	#endif
 	default:
 		return false;
 	}
diff --git a/arch/riscv/kernel/vendor_extensions/Makefile b/arch/riscv/kernel/vendor_extensions/Makefile
index 6a61aed944f1..866414c81a9f 100644
--- a/arch/riscv/kernel/vendor_extensions/Makefile
+++ b/arch/riscv/kernel/vendor_extensions/Makefile
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_ANDES)	+= andes.o
+obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD)	+= thead.o
+obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD)	+= thead_hwprobe.o
diff --git a/arch/riscv/kernel/vendor_extensions/thead.c b/arch/riscv/kernel/vendor_extensions/thead.c
new file mode 100644
index 000000000000..519dbf70710a
--- /dev/null
+++ b/arch/riscv/kernel/vendor_extensions/thead.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <asm/cpufeature.h>
+#include <asm/vendor_extensions.h>
+#include <asm/vendor_extensions/thead.h>
+
+#include <linux/array_size.h>
+#include <linux/cpumask.h>
+#include <linux/types.h>
+
+/* All T-Head vendor extensions supported in Linux */
+static const struct riscv_isa_ext_data riscv_isa_vendor_ext_thead[] = {
+	__RISCV_ISA_EXT_DATA(xtheadvector, RISCV_ISA_VENDOR_EXT_XTHEADVECTOR),
+};
+
+struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead = {
+	.ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_thead),
+	.ext_data = riscv_isa_vendor_ext_thead,
+};
+
+void disable_xtheadvector(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap[cpu].isa);
+
+	clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap.isa);
+}
diff --git a/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c
new file mode 100644
index 000000000000..2eba34011786
--- /dev/null
+++ b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <asm/vendor_extensions/thead.h>
+#include <asm/vendor_extensions/thead_hwprobe.h>
+#include <asm/vendor_extensions/vendor_hwprobe.h>
+
+#include <linux/cpumask.h>
+#include <linux/types.h>
+
+#include <uapi/asm/hwprobe.h>
+#include <uapi/asm/vendor/thead.h>
+
+void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus)
+{
+	VENDOR_EXTENSION_SUPPORTED(pair, cpus,
+				   riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap, {
+		VENDOR_EXT_KEY(XTHEADVECTOR);
+	});
+}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index a9f2b4af8f3f..0194324a0c50 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -22,6 +22,57 @@
 
 #include "../kernel/head.h"
 
+static void show_pte(unsigned long addr)
+{
+	pgd_t *pgdp, pgd;
+	p4d_t *p4dp, p4d;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
+	struct mm_struct *mm = current->mm;
+
+	if (!mm)
+		mm = &init_mm;
+
+	pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n",
+		 current->comm, PAGE_SIZE / SZ_1K, VA_BITS,
+		 mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd));
+
+	pgdp = pgd_offset(mm, addr);
+	pgd = pgdp_get(pgdp);
+	pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd));
+	if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd))
+		goto out;
+
+	p4dp = p4d_offset(pgdp, addr);
+	p4d = p4dp_get(p4dp);
+	pr_cont(", p4d=%016lx", p4d_val(p4d));
+	if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d))
+		goto out;
+
+	pudp = pud_offset(p4dp, addr);
+	pud = pudp_get(pudp);
+	pr_cont(", pud=%016lx", pud_val(pud));
+	if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud))
+		goto out;
+
+	pmdp = pmd_offset(pudp, addr);
+	pmd = pmdp_get(pmdp);
+	pr_cont(", pmd=%016lx", pmd_val(pmd));
+	if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd))
+		goto out;
+
+	ptep = pte_offset_map(pmdp, addr);
+	if (!ptep)
+		goto out;
+
+	pte = ptep_get(ptep);
+	pr_cont(", pte=%016lx", pte_val(pte));
+	pte_unmap(ptep);
+out:
+	pr_cont("\n");
+}
+
 static void die_kernel_fault(const char *msg, unsigned long addr,
 		struct pt_regs *regs)
 {
@@ -31,6 +82,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
 		addr);
 
 	bust_spinlocks(0);
+	show_pte(addr);
 	die(regs, "Oops");
 	make_task_dead(SIGKILL);
 }
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 8d167e09f1fe..15b2eda4c364 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -268,8 +268,12 @@ static void __init setup_bootmem(void)
 	 */
 	if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) {
 		max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE;
-		memblock_cap_memory_range(phys_ram_base,
-					  max_mapped_addr - phys_ram_base);
+		if (memblock_end_of_DRAM() > max_mapped_addr) {
+			memblock_cap_memory_range(phys_ram_base,
+						  max_mapped_addr - phys_ram_base);
+			pr_warn("Physical memory overflows the linear mapping size: region above %pa removed",
+				&max_mapped_addr);
+		}
 	}
 
 	/*
@@ -1573,7 +1577,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
 			return;
 	}
 
-	pagetable_pte_dtor(ptdesc);
+	pagetable_dtor(ptdesc);
 	if (PageReserved(page))
 		free_reserved_page(page);
 	else
@@ -1595,7 +1599,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemm
 	}
 
 	if (!is_vmemmap)
-		pagetable_pmd_dtor(ptdesc);
+		pagetable_dtor(ptdesc);
 	if (PageReserved(page))
 		free_reserved_page(page);
 	else
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index c301c8d291d2..41c635d6aca4 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -32,7 +32,7 @@ static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned
 	pte_t *ptep, *p;
 
 	if (pmd_none(pmdp_get(pmd))) {
-		p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
+		p = memblock_alloc_or_panic(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
 		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
 
@@ -54,7 +54,7 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned
 	unsigned long next;
 
 	if (pud_none(pudp_get(pud))) {
-		p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+		p = memblock_alloc_or_panic(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
 		set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
 
@@ -85,7 +85,7 @@ static void __init kasan_populate_pud(p4d_t *p4d,
 	unsigned long next;
 
 	if (p4d_none(p4dp_get(p4d))) {
-		p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+		p = memblock_alloc_or_panic(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
 		set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
 
@@ -116,7 +116,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 	unsigned long next;
 
 	if (pgd_none(pgdp_get(pgd))) {
-		p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
+		p = memblock_alloc_or_panic(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
 		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 	}
 
@@ -385,7 +385,7 @@ static void __init kasan_shallow_populate_pud(p4d_t *p4d,
 		next = pud_addr_end(vaddr, end);
 
 		if (pud_none(pudp_get(pud_k))) {
-			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+			p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 			set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
 		}
@@ -405,7 +405,7 @@ static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
 		next = p4d_addr_end(vaddr, end);
 
 		if (p4d_none(p4dp_get(p4d_k))) {
-			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+			p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 			set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
 		}
@@ -424,7 +424,7 @@ static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long
 		next = pgd_addr_end(vaddr, end);
 
 		if (pgd_none(pgdp_get(pgd_k))) {
-			p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+			p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
 			continue;
 		}
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 570558a99359..9c9ec08d78c7 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -52,13 +52,19 @@ config KASAN_SHADOW_OFFSET
 	depends on KASAN
 	default 0x1C000000000000
 
-config GCC_ASM_FLAG_OUTPUT_BROKEN
+config CC_ASM_FLAG_OUTPUT_BROKEN
 	def_bool CC_IS_GCC && GCC_VERSION < 140200
 	help
 	  GCC versions before 14.2.0 may die with an internal
 	  compiler error in some configurations if flag output
 	  operands are used within inline assemblies.
 
+config CC_HAS_ASM_AOR_FORMAT_FLAGS
+	def_bool !(CC_IS_CLANG && CLANG_VERSION < 190100)
+	help
+	  Clang versions before 19.1.0 do not support A,
+	  O, and R inline assembly format flags.
+
 config S390
 	def_bool y
 	#
@@ -72,6 +78,7 @@ config S390
 	select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
+	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_CRC32
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
@@ -244,6 +251,7 @@ config S390
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE	if PCI
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	select NEED_PROC_VMCORE_DEVICE_RAM if PROC_VMCORE
 	select NEED_SG_DMA_LENGTH	if PCI
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 3f25498dac65..5fae311203c2 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -22,7 +22,7 @@ KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
 ifndef CONFIG_AS_IS_LLVM
 KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
 endif
-KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack
+KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack -std=gnu11
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS_DECOMPRESSOR += -D__DECOMPRESSOR
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float -mbackchain
diff --git a/arch/s390/Makefile.postlink b/arch/s390/Makefile.postlink
index df82f5410769..1ae5478cd6ac 100644
--- a/arch/s390/Makefile.postlink
+++ b/arch/s390/Makefile.postlink
@@ -11,6 +11,7 @@ __archpost:
 
 -include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
+include $(srctree)/scripts/Makefile.lib
 
 CMD_RELOCS=arch/s390/tools/relocs
 OUT_RELOCS = arch/s390/boot
@@ -19,11 +20,6 @@ quiet_cmd_relocs = RELOCS  $(OUT_RELOCS)/relocs.S
 	mkdir -p $(OUT_RELOCS); \
 	$(CMD_RELOCS) $@ > $(OUT_RELOCS)/relocs.S
 
-quiet_cmd_strip_relocs = RSTRIP  $@
-      cmd_strip_relocs = \
-	$(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \
-		   --remove-section='.rela.*' --remove-section='.rela__*' $@
-
 vmlinux: FORCE
 	$(call cmd,relocs)
 	$(call cmd,strip_relocs)
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 91a30e017d65..dd7ba7587dd5 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -52,7 +52,7 @@ static int appldata_interval_handler(const struct ctl_table *ctl, int write,
 				     void *buffer, size_t *lenp, loff_t *ppos);
 
 static struct ctl_table_header *appldata_sysctl_header;
-static struct ctl_table appldata_table[] = {
+static const struct ctl_table appldata_table[] = {
 	{
 		.procname	= "timer",
 		.mode		= S_IRUGO | S_IWUSR,
diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c
index 11e0c3d5dbc8..79afb5fa7f1f 100644
--- a/arch/s390/boot/als.c
+++ b/arch/s390/boot/als.c
@@ -46,7 +46,7 @@ void print_missing_facilities(void)
 			 * z/VM adds a four character prefix.
 			 */
 			if (strlen(als_str) > 70) {
-				boot_printk("%s\n", als_str);
+				boot_emerg("%s\n", als_str);
 				*als_str = '\0';
 			}
 			u16_to_decimal(val_str, i * BITS_PER_LONG + j);
@@ -54,7 +54,7 @@ void print_missing_facilities(void)
 			first = 0;
 		}
 	}
-	boot_printk("%s\n", als_str);
+	boot_emerg("%s\n", als_str);
 }
 
 static void facility_mismatch(void)
@@ -62,10 +62,10 @@ static void facility_mismatch(void)
 	struct cpuid id;
 
 	get_cpu_id(&id);
-	boot_printk("The Linux kernel requires more recent processor hardware\n");
-	boot_printk("Detected machine-type number: %4x\n", id.machine);
+	boot_emerg("The Linux kernel requires more recent processor hardware\n");
+	boot_emerg("Detected machine-type number: %4x\n", id.machine);
 	print_missing_facilities();
-	boot_printk("See Principles of Operations for facility bits\n");
+	boot_emerg("See Principles of Operations for facility bits\n");
 	disabled_wait();
 }
 
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 56244fe78182..69f261566a64 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -8,6 +8,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/printk.h>
 #include <asm/physmem_info.h>
 
 struct machine_info {
@@ -47,13 +48,16 @@ void physmem_set_usable_limit(unsigned long limit);
 void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size);
 void physmem_free(enum reserved_range_type type);
 /* for continuous/multiple allocations per type */
-unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size,
-				     unsigned long align);
+unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size,
+				   unsigned long align);
+unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size,
+			    unsigned long align, bool die_on_oom);
 /* for single allocations, 1 per type */
 unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size,
 				  unsigned long align, unsigned long min, unsigned long max,
 				  bool die_on_oom);
 unsigned long get_physmem_alloc_pos(void);
+void dump_physmem_reserved(void);
 bool ipl_report_certs_intersects(unsigned long addr, unsigned long size,
 				 unsigned long *intersection_start);
 bool is_ipl_block_dump(void);
@@ -69,12 +73,28 @@ void print_pgm_check_info(void);
 unsigned long randomize_within_range(unsigned long size, unsigned long align,
 				     unsigned long min, unsigned long max);
 void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit);
-void __printf(1, 2) boot_printk(const char *fmt, ...);
+int __printf(1, 2) boot_printk(const char *fmt, ...);
 void print_stacktrace(unsigned long sp);
 void error(char *m);
 int get_random(unsigned long limit, unsigned long *value);
+void boot_rb_dump(void);
+
+#ifndef boot_fmt
+#define boot_fmt(fmt)	fmt
+#endif
+
+#define boot_emerg(fmt, ...)	boot_printk(KERN_EMERG boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_alert(fmt, ...)	boot_printk(KERN_ALERT boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_crit(fmt, ...)	boot_printk(KERN_CRIT boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_err(fmt, ...)	boot_printk(KERN_ERR boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_warn(fmt, ...)	boot_printk(KERN_WARNING boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_notice(fmt, ...)	boot_printk(KERN_NOTICE boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_info(fmt, ...)	boot_printk(KERN_INFO boot_fmt(fmt), ##__VA_ARGS__)
+#define boot_debug(fmt, ...)	boot_printk(KERN_DEBUG boot_fmt(fmt), ##__VA_ARGS__)
 
 extern struct machine_info machine;
+extern int boot_console_loglevel;
+extern bool boot_ignore_loglevel;
 
 /* Symbols defined by linker scripts */
 extern const char kernel_version[];
diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c
index f478e8e9cbda..03500b9d9fb9 100644
--- a/arch/s390/boot/decompressor.c
+++ b/arch/s390/boot/decompressor.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <asm/boot_data.h>
 #include <asm/page.h>
 #include "decompressor.h"
 #include "boot.h"
@@ -63,6 +64,15 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE;
 #include "../../../../lib/decompress_unzstd.c"
 #endif
 
+static void decompress_error(char *m)
+{
+	if (bootdebug)
+		boot_rb_dump();
+	boot_emerg("Decompression error: %s\n", m);
+	boot_emerg(" -- System halted\n");
+	disabled_wait();
+}
+
 unsigned long mem_safe_offset(void)
 {
 	return ALIGN(free_mem_end_ptr, PAGE_SIZE);
@@ -71,5 +81,5 @@ unsigned long mem_safe_offset(void)
 void deploy_kernel(void *output)
 {
 	__decompress(_compressed_start, _compressed_end - _compressed_start,
-		     NULL, NULL, output, vmlinux.image_size, NULL, error);
+		     NULL, NULL, output, vmlinux.image_size, NULL, decompress_error);
 }
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 557462e62cd7..d3731f2983b7 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -215,7 +215,7 @@ static void check_cleared_facilities(void)
 
 	for (i = 0; i < ARRAY_SIZE(als); i++) {
 		if ((stfle_fac_list[i] & als[i]) != als[i]) {
-			boot_printk("Warning: The Linux kernel requires facilities cleared via command line option\n");
+			boot_emerg("The Linux kernel requires facilities cleared via command line option\n");
 			print_missing_facilities();
 			break;
 		}
@@ -313,5 +313,23 @@ void parse_boot_command_line(void)
 #endif
 		if (!strcmp(param, "relocate_lowcore") && test_facility(193))
 			relocate_lowcore = 1;
+		if (!strcmp(param, "earlyprintk"))
+			boot_earlyprintk = true;
+		if (!strcmp(param, "debug"))
+			boot_console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
+		if (!strcmp(param, "bootdebug")) {
+			bootdebug = true;
+			if (val)
+				strncpy(bootdebug_filter, val, sizeof(bootdebug_filter) - 1);
+		}
+		if (!strcmp(param, "quiet"))
+			boot_console_loglevel = CONSOLE_LOGLEVEL_QUIET;
+		if (!strcmp(param, "ignore_loglevel"))
+			boot_ignore_loglevel = true;
+		if (!strcmp(param, "loglevel")) {
+			boot_console_loglevel = simple_strtoull(val, NULL, 10);
+			if (boot_console_loglevel < CONSOLE_LOGLEVEL_MIN)
+				boot_console_loglevel = CONSOLE_LOGLEVEL_MIN;
+		}
 	}
 }
diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c
index d00898852a88..f73cd757a5f7 100644
--- a/arch/s390/boot/ipl_report.c
+++ b/arch/s390/boot/ipl_report.c
@@ -30,7 +30,6 @@ static unsigned long get_cert_comp_list_size(void)
 {
 	struct ipl_rb_certificate_entry *cert;
 	struct ipl_rb_component_entry *comp;
-	size_t size;
 
 	/*
 	 * Find the length for the IPL report boot data
@@ -155,7 +154,7 @@ void save_ipl_cert_comp_list(void)
 		return;
 
 	size = get_cert_comp_list_size();
-	early_ipl_comp_list_addr = physmem_alloc_top_down(RR_CERT_COMP_LIST, size, sizeof(int));
+	early_ipl_comp_list_addr = physmem_alloc_or_die(RR_CERT_COMP_LIST, size, sizeof(int));
 	ipl_cert_list_addr = early_ipl_comp_list_addr + early_ipl_comp_list_size;
 
 	copy_components_bootdata();
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
index f864d2bff775..941f4c9e27cc 100644
--- a/arch/s390/boot/kaslr.c
+++ b/arch/s390/boot/kaslr.c
@@ -32,7 +32,7 @@ struct prng_parm {
 static int check_prng(void)
 {
 	if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) {
-		boot_printk("KASLR disabled: CPU has no PRNG\n");
+		boot_warn("KASLR disabled: CPU has no PRNG\n");
 		return 0;
 	}
 	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
@@ -168,7 +168,7 @@ static unsigned long iterate_valid_positions(unsigned long size, unsigned long a
  * cannot have chains.
  *
  * On the other hand, "dynamic" or "repetitive" allocations are done via
- * physmem_alloc_top_down(). These allocations are tightly packed together
+ * physmem_alloc_or_die(). These allocations are tightly packed together
  * top down from the end of online memory. physmem_alloc_pos represents
  * current position where those allocations start.
  *
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
index 5abe59fb3bc0..633f11600aab 100644
--- a/arch/s390/boot/pgm_check_info.c
+++ b/arch/s390/boot/pgm_check_info.c
@@ -17,13 +17,14 @@ void print_stacktrace(unsigned long sp)
 					 (unsigned long)_stack_end };
 	bool first = true;
 
-	boot_printk("Call Trace:\n");
+	boot_emerg("Call Trace:\n");
 	while (!(sp & 0x7) && on_stack(&boot_stack, sp, sizeof(struct stack_frame))) {
 		struct stack_frame *sf = (struct stack_frame *)sp;
 
-		boot_printk(first ? "(sp:%016lx [<%016lx>] %pS)\n" :
-				    " sp:%016lx [<%016lx>] %pS\n",
-			    sp, sf->gprs[8], (void *)sf->gprs[8]);
+		if (first)
+			boot_emerg("(sp:%016lx [<%016lx>] %pS)\n", sp, sf->gprs[8], (void *)sf->gprs[8]);
+		else
+			boot_emerg(" sp:%016lx [<%016lx>] %pS\n", sp, sf->gprs[8], (void *)sf->gprs[8]);
 		if (sf->back_chain <= sp)
 			break;
 		sp = sf->back_chain;
@@ -36,30 +37,30 @@ void print_pgm_check_info(void)
 	unsigned long *gpregs = (unsigned long *)get_lowcore()->gpregs_save_area;
 	struct psw_bits *psw = &psw_bits(get_lowcore()->psw_save_area);
 
-	boot_printk("Linux version %s\n", kernel_version);
+	if (bootdebug)
+		boot_rb_dump();
+	boot_emerg("Linux version %s\n", kernel_version);
 	if (!is_prot_virt_guest() && early_command_line[0])
-		boot_printk("Kernel command line: %s\n", early_command_line);
-	boot_printk("Kernel fault: interruption code %04x ilc:%x\n",
-		    get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1);
+		boot_emerg("Kernel command line: %s\n", early_command_line);
+	boot_emerg("Kernel fault: interruption code %04x ilc:%d\n",
+		   get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1);
 	if (kaslr_enabled()) {
-		boot_printk("Kernel random base: %lx\n", __kaslr_offset);
-		boot_printk("Kernel random base phys: %lx\n", __kaslr_offset_phys);
+		boot_emerg("Kernel random base: %lx\n", __kaslr_offset);
+		boot_emerg("Kernel random base phys: %lx\n", __kaslr_offset_phys);
 	}
-	boot_printk("PSW : %016lx %016lx (%pS)\n",
-		    get_lowcore()->psw_save_area.mask,
-		    get_lowcore()->psw_save_area.addr,
-		    (void *)get_lowcore()->psw_save_area.addr);
-	boot_printk(
-		"      R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n",
-		psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck,
-		psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri,
-		psw->eaba);
-	boot_printk("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]);
-	boot_printk("      %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]);
-	boot_printk("      %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]);
-	boot_printk("      %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]);
+	boot_emerg("PSW : %016lx %016lx (%pS)\n",
+		   get_lowcore()->psw_save_area.mask,
+		   get_lowcore()->psw_save_area.addr,
+		   (void *)get_lowcore()->psw_save_area.addr);
+	boot_emerg("      R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n",
+		   psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck,
+		   psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, psw->eaba);
+	boot_emerg("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]);
+	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]);
+	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]);
+	boot_emerg("      %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]);
 	print_stacktrace(get_lowcore()->gpregs_save_area[15]);
-	boot_printk("Last Breaking-Event-Address:\n");
-	boot_printk(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break,
-		    (void *)get_lowcore()->pgm_last_break);
+	boot_emerg("Last Breaking-Event-Address:\n");
+	boot_emerg(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break,
+		   (void *)get_lowcore()->pgm_last_break);
 }
diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c
index 7617aa2d2f7e..aa096ef68e8c 100644
--- a/arch/s390/boot/physmem_info.c
+++ b/arch/s390/boot/physmem_info.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define boot_fmt(fmt) "physmem: " fmt
 #include <linux/processor.h>
 #include <linux/errno.h>
 #include <linux/init.h>
@@ -28,7 +29,7 @@ static struct physmem_range *__get_physmem_range_ptr(u32 n)
 		return &physmem_info.online[n];
 	if (unlikely(!physmem_info.online_extended)) {
 		physmem_info.online_extended = (struct physmem_range *)physmem_alloc_range(
-			RR_MEM_DETECT_EXTENDED, ENTRIES_EXTENDED_MAX, sizeof(long), 0,
+			RR_MEM_DETECT_EXT, ENTRIES_EXTENDED_MAX, sizeof(long), 0,
 			physmem_alloc_pos, true);
 	}
 	return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES];
@@ -207,11 +208,16 @@ unsigned long detect_max_physmem_end(void)
 		max_physmem_end = search_mem_end();
 		physmem_info.info_source = MEM_DETECT_BIN_SEARCH;
 	}
+	boot_debug("Max physical memory: 0x%016lx (info source: %s)\n", max_physmem_end,
+		   get_physmem_info_source());
 	return max_physmem_end;
 }
 
 void detect_physmem_online_ranges(unsigned long max_physmem_end)
 {
+	unsigned long start, end;
+	int i;
+
 	if (!sclp_early_read_storage_info()) {
 		physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO;
 	} else if (physmem_info.info_source == MEM_DETECT_DIAG500_STOR_LIMIT) {
@@ -226,12 +232,16 @@ void detect_physmem_online_ranges(unsigned long max_physmem_end)
 	} else if (max_physmem_end) {
 		add_physmem_online_range(0, max_physmem_end);
 	}
+	boot_debug("Online memory ranges (info source: %s):\n", get_physmem_info_source());
+	for_each_physmem_online_range(i, &start, &end)
+		boot_debug(" online [%d]:   0x%016lx-0x%016lx\n", i, start, end);
 }
 
 void physmem_set_usable_limit(unsigned long limit)
 {
 	physmem_info.usable = limit;
 	physmem_alloc_pos = limit;
+	boot_debug("Usable memory limit: 0x%016lx\n", limit);
 }
 
 static void die_oom(unsigned long size, unsigned long align, unsigned long min, unsigned long max)
@@ -241,38 +251,47 @@ static void die_oom(unsigned long size, unsigned long align, unsigned long min,
 	enum reserved_range_type t;
 	int i;
 
-	boot_printk("Linux version %s\n", kernel_version);
+	boot_emerg("Linux version %s\n", kernel_version);
 	if (!is_prot_virt_guest() && early_command_line[0])
-		boot_printk("Kernel command line: %s\n", early_command_line);
-	boot_printk("Out of memory allocating %lx bytes %lx aligned in range %lx:%lx\n",
-		    size, align, min, max);
-	boot_printk("Reserved memory ranges:\n");
+		boot_emerg("Kernel command line: %s\n", early_command_line);
+	boot_emerg("Out of memory allocating %lu bytes 0x%lx aligned in range %lx:%lx\n",
+		   size, align, min, max);
+	boot_emerg("Reserved memory ranges:\n");
 	for_each_physmem_reserved_range(t, range, &start, &end) {
-		boot_printk("%016lx %016lx %s\n", start, end, get_rr_type_name(t));
+		boot_emerg("%016lx %016lx %s\n", start, end, get_rr_type_name(t));
 		total_reserved_mem += end - start;
 	}
-	boot_printk("Usable online memory ranges (info source: %s [%x]):\n",
-		    get_physmem_info_source(), physmem_info.info_source);
+	boot_emerg("Usable online memory ranges (info source: %s [%d]):\n",
+		   get_physmem_info_source(), physmem_info.info_source);
 	for_each_physmem_usable_range(i, &start, &end) {
-		boot_printk("%016lx %016lx\n", start, end);
+		boot_emerg("%016lx %016lx\n", start, end);
 		total_mem += end - start;
 	}
-	boot_printk("Usable online memory total: %lx Reserved: %lx Free: %lx\n",
-		    total_mem, total_reserved_mem,
-		    total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0);
+	boot_emerg("Usable online memory total: %lu Reserved: %lu Free: %lu\n",
+		   total_mem, total_reserved_mem,
+		   total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0);
 	print_stacktrace(current_frame_address());
-	boot_printk("\n\n -- System halted\n");
+	boot_emerg(" -- System halted\n");
 	disabled_wait();
 }
 
-void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size)
+static void _physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size)
 {
 	physmem_info.reserved[type].start = addr;
 	physmem_info.reserved[type].end = addr + size;
 }
 
+void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size)
+{
+	_physmem_reserve(type, addr, size);
+	boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Reserve:", addr, addr + size,
+		   get_rr_type_name(type));
+}
+
 void physmem_free(enum reserved_range_type type)
 {
+	boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Free:", physmem_info.reserved[type].start,
+		   physmem_info.reserved[type].end, get_rr_type_name(type));
 	physmem_info.reserved[type].start = 0;
 	physmem_info.reserved[type].end = 0;
 }
@@ -339,41 +358,73 @@ unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long s
 	max = min(max, physmem_alloc_pos);
 	addr = __physmem_alloc_range(size, align, min, max, 0, NULL, die_on_oom);
 	if (addr)
-		physmem_reserve(type, addr, size);
+		_physmem_reserve(type, addr, size);
+	boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Alloc range:", addr, addr + size,
+		   get_rr_type_name(type));
 	return addr;
 }
 
-unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size,
-				     unsigned long align)
+unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size,
+			    unsigned long align, bool die_on_oom)
 {
 	struct reserved_range *range = &physmem_info.reserved[type];
-	struct reserved_range *new_range;
+	struct reserved_range *new_range = NULL;
 	unsigned int ranges_left;
 	unsigned long addr;
 
 	addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, physmem_alloc_ranges,
-				     &ranges_left, true);
+				     &ranges_left, die_on_oom);
+	if (!addr)
+		return 0;
 	/* if not a consecutive allocation of the same type or first allocation */
 	if (range->start != addr + size) {
 		if (range->end) {
-			physmem_alloc_pos = __physmem_alloc_range(
-				sizeof(struct reserved_range), 0, 0, physmem_alloc_pos,
-				physmem_alloc_ranges, &ranges_left, true);
-			new_range = (struct reserved_range *)physmem_alloc_pos;
+			addr = __physmem_alloc_range(sizeof(struct reserved_range), 0, 0,
+						     physmem_alloc_pos, physmem_alloc_ranges,
+						     &ranges_left, true);
+			new_range = (struct reserved_range *)addr;
+			addr = __physmem_alloc_range(size, align, 0, addr, ranges_left,
+						     &ranges_left, die_on_oom);
+			if (!addr)
+				return 0;
 			*new_range = *range;
 			range->chain = new_range;
-			addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos,
-						     ranges_left, &ranges_left, true);
 		}
 		range->end = addr + size;
 	}
+	if (type != RR_VMEM) {
+		boot_debug("%-14s 0x%016lx-0x%016lx %-20s align 0x%lx split %d\n", "Alloc topdown:",
+			   addr, addr + size, get_rr_type_name(type), align, !!new_range);
+	}
 	range->start = addr;
 	physmem_alloc_pos = addr;
 	physmem_alloc_ranges = ranges_left;
 	return addr;
 }
 
+unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size,
+				   unsigned long align)
+{
+	return physmem_alloc(type, size, align, true);
+}
+
 unsigned long get_physmem_alloc_pos(void)
 {
 	return physmem_alloc_pos;
 }
+
+void dump_physmem_reserved(void)
+{
+	struct reserved_range *range;
+	enum reserved_range_type t;
+	unsigned long start, end;
+
+	boot_debug("Reserved memory ranges:\n");
+	for_each_physmem_reserved_range(t, range, &start, &end) {
+		if (end) {
+			boot_debug("%-14s 0x%016lx-0x%016lx @%012lx chain %012lx\n",
+				   get_rr_type_name(t), start, end, (unsigned long)range,
+				   (unsigned long)range->chain);
+		}
+	}
+}
diff --git a/arch/s390/boot/printk.c b/arch/s390/boot/printk.c
index 35f18f2b936e..b4c66fa667d5 100644
--- a/arch/s390/boot/printk.c
+++ b/arch/s390/boot/printk.c
@@ -5,21 +5,111 @@
 #include <linux/ctype.h>
 #include <asm/stacktrace.h>
 #include <asm/boot_data.h>
+#include <asm/sections.h>
 #include <asm/lowcore.h>
 #include <asm/setup.h>
 #include <asm/sclp.h>
 #include <asm/uv.h>
 #include "boot.h"
 
+int boot_console_loglevel = CONFIG_CONSOLE_LOGLEVEL_DEFAULT;
+bool boot_ignore_loglevel;
+char __bootdata(boot_rb)[PAGE_SIZE * 2];
+bool __bootdata(boot_earlyprintk);
+size_t __bootdata(boot_rb_off);
+char __bootdata(bootdebug_filter)[128];
+bool __bootdata(bootdebug);
+
+static void boot_rb_add(const char *str, size_t len)
+{
+	/* leave double '\0' in the end */
+	size_t avail = sizeof(boot_rb) - boot_rb_off - 1;
+
+	/* store strings separated by '\0' */
+	if (len + 1 > avail)
+		boot_rb_off = 0;
+	strcpy(boot_rb + boot_rb_off, str);
+	boot_rb_off += len + 1;
+}
+
+static void print_rb_entry(const char *str)
+{
+	sclp_early_printk(printk_skip_level(str));
+}
+
+static bool debug_messages_printed(void)
+{
+	return boot_earlyprintk && (boot_ignore_loglevel || boot_console_loglevel > LOGLEVEL_DEBUG);
+}
+
+void boot_rb_dump(void)
+{
+	if (debug_messages_printed())
+		return;
+	sclp_early_printk("Boot messages ring buffer:\n");
+	boot_rb_foreach(print_rb_entry);
+}
+
 const char hex_asc[] = "0123456789abcdef";
 
 static char *as_hex(char *dst, unsigned long val, int pad)
 {
-	char *p, *end = p = dst + max(pad, (int)__fls(val | 1) / 4 + 1);
+	char *p = dst + max(pad, (int)__fls(val | 1) / 4 + 1);
 
-	for (*p-- = 0; p >= dst; val >>= 4)
+	for (*p-- = '\0'; p >= dst; val >>= 4)
 		*p-- = hex_asc[val & 0x0f];
-	return end;
+	return dst;
+}
+
+#define MAX_NUMLEN 21
+static char *as_dec(char *buf, unsigned long val, bool is_signed)
+{
+	bool negative = false;
+	char *p = buf + MAX_NUMLEN;
+
+	if (is_signed && (long)val < 0) {
+		val = (val == LONG_MIN ? LONG_MIN : -(long)val);
+		negative = true;
+	}
+
+	*--p = '\0';
+	do {
+		*--p = '0' + (val % 10);
+		val /= 10;
+	} while (val);
+
+	if (negative)
+		*--p = '-';
+	return p;
+}
+
+static ssize_t strpad(char *dst, size_t dst_size, const char *src,
+		      int _pad, bool zero_pad, bool decimal)
+{
+	ssize_t len = strlen(src), pad = _pad;
+	char *p = dst;
+
+	if (max(len, abs(pad)) >= dst_size)
+		return -E2BIG;
+
+	if (pad > len) {
+		if (decimal && zero_pad && *src == '-') {
+			*p++ = '-';
+			src++;
+			len--;
+			pad--;
+		}
+		memset(p, zero_pad ? '0' : ' ', pad - len);
+		p += pad - len;
+	}
+	memcpy(p, src, len);
+	p += len;
+	if (pad < 0 && -pad > len) {
+		memset(p, ' ', -pad - len);
+		p += -pad - len;
+	}
+	*p = '\0';
+	return p - dst;
 }
 
 static char *symstart(char *p)
@@ -58,35 +148,94 @@ static noinline char *findsym(unsigned long ip, unsigned short *off, unsigned sh
 	return NULL;
 }
 
-static noinline char *strsym(void *ip)
+#define MAX_SYMLEN 64
+static noinline char *strsym(char *buf, void *ip)
 {
-	static char buf[64];
 	unsigned short off;
 	unsigned short len;
 	char *p;
 
 	p = findsym((unsigned long)ip, &off, &len);
 	if (p) {
-		strncpy(buf, p, sizeof(buf));
+		strncpy(buf, p, MAX_SYMLEN);
 		/* reserve 15 bytes for offset/len in symbol+0x1234/0x1234 */
-		p = buf + strnlen(buf, sizeof(buf) - 15);
+		p = buf + strnlen(buf, MAX_SYMLEN - 15);
 		strcpy(p, "+0x");
-		p = as_hex(p + 3, off, 0);
-		strcpy(p, "/0x");
-		as_hex(p + 3, len, 0);
+		as_hex(p + 3, off, 0);
+		strcat(p, "/0x");
+		as_hex(p + strlen(p), len, 0);
 	} else {
 		as_hex(buf, (unsigned long)ip, 16);
 	}
 	return buf;
 }
 
-void boot_printk(const char *fmt, ...)
+static inline int printk_loglevel(const char *buf)
+{
+	if (buf[0] == KERN_SOH_ASCII && buf[1]) {
+		switch (buf[1]) {
+		case '0' ... '7':
+			return buf[1] - '0';
+		}
+	}
+	return MESSAGE_LOGLEVEL_DEFAULT;
+}
+
+static void boot_console_earlyprintk(const char *buf)
+{
+	int level = printk_loglevel(buf);
+
+	/* always print emergency messages */
+	if (level > LOGLEVEL_EMERG && !boot_earlyprintk)
+		return;
+	buf = printk_skip_level(buf);
+	/* print debug messages only when bootdebug is enabled */
+	if (level == LOGLEVEL_DEBUG && (!bootdebug || !bootdebug_filter_match(skip_timestamp(buf))))
+		return;
+	if (boot_ignore_loglevel || level < boot_console_loglevel)
+		sclp_early_printk(buf);
+}
+
+static char *add_timestamp(char *buf)
+{
+#ifdef CONFIG_PRINTK_TIME
+	union tod_clock *boot_clock = (union tod_clock *)&get_lowcore()->boot_clock;
+	unsigned long ns = tod_to_ns(get_tod_clock() - boot_clock->tod);
+	char ts[MAX_NUMLEN];
+
+	*buf++ = '[';
+	buf += strpad(buf, MAX_NUMLEN, as_dec(ts, ns / NSEC_PER_SEC, 0), 5, 0, 0);
+	*buf++ = '.';
+	buf += strpad(buf, MAX_NUMLEN, as_dec(ts, (ns % NSEC_PER_SEC) / NSEC_PER_USEC, 0), 6, 1, 0);
+	*buf++ = ']';
+	*buf++ = ' ';
+#endif
+	return buf;
+}
+
+#define va_arg_len_type(args, lenmod, typemod)				\
+	((lenmod == 'l') ? va_arg(args, typemod long) :			\
+	 (lenmod == 'h') ? (typemod short)va_arg(args, typemod int) :	\
+	 (lenmod == 'H') ? (typemod char)va_arg(args, typemod int) :	\
+	 (lenmod == 'z') ? va_arg(args, typemod long) :			\
+			   va_arg(args, typemod int))
+
+int boot_printk(const char *fmt, ...)
 {
 	char buf[1024] = { 0 };
 	char *end = buf + sizeof(buf) - 1; /* make sure buf is 0 terminated */
-	unsigned long pad;
-	char *p = buf;
+	bool zero_pad, decimal;
+	char *strval, *p = buf;
+	char valbuf[MAX(MAX_SYMLEN, MAX_NUMLEN)];
 	va_list args;
+	char lenmod;
+	ssize_t len;
+	int pad;
+
+	*p++ = KERN_SOH_ASCII;
+	*p++ = printk_get_level(fmt) ?: '0' + MESSAGE_LOGLEVEL_DEFAULT;
+	p = add_timestamp(p);
+	fmt = printk_skip_level(fmt);
 
 	va_start(args, fmt);
 	for (; p < end && *fmt; fmt++) {
@@ -94,31 +243,56 @@ void boot_printk(const char *fmt, ...)
 			*p++ = *fmt;
 			continue;
 		}
-		pad = isdigit(*++fmt) ? simple_strtol(fmt, (char **)&fmt, 10) : 0;
+		if (*++fmt == '%') {
+			*p++ = '%';
+			continue;
+		}
+		zero_pad = (*fmt == '0');
+		pad = simple_strtol(fmt, (char **)&fmt, 10);
+		lenmod = (*fmt == 'h' || *fmt == 'l' || *fmt == 'z') ? *fmt++ : 0;
+		if (lenmod == 'h' && *fmt == 'h') {
+			lenmod = 'H';
+			fmt++;
+		}
+		decimal = false;
 		switch (*fmt) {
 		case 's':
-			p = buf + strlcat(buf, va_arg(args, char *), sizeof(buf));
+			if (lenmod)
+				goto out;
+			strval = va_arg(args, char *);
+			zero_pad = false;
 			break;
 		case 'p':
-			if (*++fmt != 'S')
+			if (*++fmt != 'S' || lenmod)
 				goto out;
-			p = buf + strlcat(buf, strsym(va_arg(args, void *)), sizeof(buf));
+			strval = strsym(valbuf, va_arg(args, void *));
+			zero_pad = false;
 			break;
-		case 'l':
-			if (*++fmt != 'x' || end - p <= max(sizeof(long) * 2, pad))
-				goto out;
-			p = as_hex(p, va_arg(args, unsigned long), pad);
+		case 'd':
+		case 'i':
+			strval = as_dec(valbuf, va_arg_len_type(args, lenmod, signed), 1);
+			decimal = true;
+			break;
+		case 'u':
+			strval = as_dec(valbuf, va_arg_len_type(args, lenmod, unsigned), 0);
 			break;
 		case 'x':
-			if (end - p <= max(sizeof(int) * 2, pad))
-				goto out;
-			p = as_hex(p, va_arg(args, unsigned int), pad);
+			strval = as_hex(valbuf, va_arg_len_type(args, lenmod, unsigned), 0);
 			break;
 		default:
 			goto out;
 		}
+		len = strpad(p, end - p, strval, pad, zero_pad, decimal);
+		if (len == -E2BIG)
+			break;
+		p += len;
 	}
 out:
 	va_end(args);
-	sclp_early_printk(buf);
+	len = strlen(buf);
+	if (len) {
+		boot_rb_add(buf, len);
+		boot_console_earlyprintk(buf);
+	}
+	return len;
 }
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index e6b06692ddc8..885bd1dd2c82 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define boot_fmt(fmt) "startup: " fmt
 #include <linux/string.h>
 #include <linux/elf.h>
 #include <asm/page-states.h>
@@ -42,7 +43,8 @@ struct machine_info machine;
 
 void error(char *x)
 {
-	boot_printk("\n\n%s\n\n -- System halted", x);
+	boot_emerg("%s\n", x);
+	boot_emerg(" -- System halted\n");
 	disabled_wait();
 }
 
@@ -143,7 +145,7 @@ static void rescue_initrd(unsigned long min, unsigned long max)
 		return;
 	old_addr = addr;
 	physmem_free(RR_INITRD);
-	addr = physmem_alloc_top_down(RR_INITRD, size, 0);
+	addr = physmem_alloc_or_die(RR_INITRD, size, 0);
 	memmove((void *)addr, (void *)old_addr, size);
 }
 
@@ -222,12 +224,16 @@ static void setup_ident_map_size(unsigned long max_physmem_end)
 	if (oldmem_data.start) {
 		__kaslr_enabled = 0;
 		ident_map_size = min(ident_map_size, oldmem_data.size);
+		boot_debug("kdump memory limit:  0x%016lx\n", oldmem_data.size);
 	} else if (ipl_block_valid && is_ipl_block_dump()) {
 		__kaslr_enabled = 0;
-		if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size)
+		if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size) {
 			ident_map_size = min(ident_map_size, hsa_size);
+			boot_debug("Stand-alone dump limit: 0x%016lx\n", hsa_size);
+		}
 	}
 #endif
+	boot_debug("Identity map size:   0x%016lx\n", ident_map_size);
 }
 
 #define FIXMAP_SIZE	round_up(MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore))
@@ -267,6 +273,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 	BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE));
 	BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE);
 	vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE);
+	boot_debug("vmem size estimated: 0x%016lx\n", vsize);
 	if (IS_ENABLED(CONFIG_KASAN) || __NO_KASLR_END_KERNEL > _REGION2_SIZE ||
 	    (vsize > _REGION2_SIZE && kaslr_enabled())) {
 		asce_limit = _REGION1_SIZE;
@@ -290,8 +297,10 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 	 * otherwise asce_limit and rte_size would have been adjusted.
 	 */
 	vmax = adjust_to_uv_max(asce_limit);
+	boot_debug("%d level paging       0x%016lx vmax\n", vmax == _REGION1_SIZE ? 4 : 3, vmax);
 #ifdef CONFIG_KASAN
 	BUILD_BUG_ON(__NO_KASLR_END_KERNEL > KASAN_SHADOW_START);
+	boot_debug("KASAN shadow area:   0x%016lx-0x%016lx\n", KASAN_SHADOW_START, KASAN_SHADOW_END);
 	/* force vmalloc and modules below kasan shadow */
 	vmax = min(vmax, KASAN_SHADOW_START);
 #endif
@@ -305,19 +314,27 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 			pos = 0;
 		kernel_end = vmax - pos * THREAD_SIZE;
 		kernel_start = round_down(kernel_end - kernel_size, THREAD_SIZE);
+		boot_debug("Randomization range: 0x%016lx-0x%016lx\n", vmax - kaslr_len, vmax);
+		boot_debug("kernel image:        0x%016lx-0x%016lx (kaslr)\n", kernel_start,
+			   kernel_size + kernel_size);
 	} else if (vmax < __NO_KASLR_END_KERNEL || vsize > __NO_KASLR_END_KERNEL) {
 		kernel_start = round_down(vmax - kernel_size, THREAD_SIZE);
-		boot_printk("The kernel base address is forced to %lx\n", kernel_start);
+		boot_debug("kernel image:        0x%016lx-0x%016lx (constrained)\n", kernel_start,
+			   kernel_start + kernel_size);
 	} else {
 		kernel_start = __NO_KASLR_START_KERNEL;
+		boot_debug("kernel image:        0x%016lx-0x%016lx (nokaslr)\n", kernel_start,
+			   kernel_start + kernel_size);
 	}
 	__kaslr_offset = kernel_start;
+	boot_debug("__kaslr_offset:      0x%016lx\n", __kaslr_offset);
 
 	MODULES_END = round_down(kernel_start, _SEGMENT_SIZE);
 	MODULES_VADDR = MODULES_END - MODULES_LEN;
 	VMALLOC_END = MODULES_VADDR;
 	if (IS_ENABLED(CONFIG_KMSAN))
 		VMALLOC_END -= MODULES_LEN * 2;
+	boot_debug("modules area:        0x%016lx-0x%016lx\n", MODULES_VADDR, MODULES_END);
 
 	/* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */
 	vsize = (VMALLOC_END - FIXMAP_SIZE) / 2;
@@ -329,10 +346,15 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 		VMALLOC_END -= vmalloc_size * 2;
 	}
 	VMALLOC_START = VMALLOC_END - vmalloc_size;
+	boot_debug("vmalloc area:        0x%016lx-0x%016lx\n", VMALLOC_START, VMALLOC_END);
 
 	__memcpy_real_area = round_down(VMALLOC_START - MEMCPY_REAL_SIZE, PAGE_SIZE);
+	boot_debug("memcpy real area:    0x%016lx-0x%016lx\n", __memcpy_real_area,
+		   __memcpy_real_area + MEMCPY_REAL_SIZE);
 	__abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE,
 				   sizeof(struct lowcore));
+	boot_debug("abs lowcore:         0x%016lx-0x%016lx\n", __abs_lowcore,
+		   __abs_lowcore + ABS_LOWCORE_MAP_SIZE);
 
 	/* split remaining virtual space between 1:1 mapping & vmemmap array */
 	pages = __abs_lowcore / (PAGE_SIZE + sizeof(struct page));
@@ -352,8 +374,11 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 	BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS));
 	max_mappable = max(ident_map_size, MAX_DCSS_ADDR);
 	max_mappable = min(max_mappable, vmemmap_start);
-	if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE))
-		__identity_base = round_down(vmemmap_start - max_mappable, rte_size);
+#ifdef CONFIG_RANDOMIZE_IDENTITY_BASE
+	__identity_base = round_down(vmemmap_start - max_mappable, rte_size);
+#endif
+	boot_debug("identity map:        0x%016lx-0x%016lx\n", __identity_base,
+		   __identity_base + ident_map_size);
 
 	return asce_limit;
 }
@@ -412,6 +437,10 @@ void startup_kernel(void)
 	psw_t psw;
 
 	setup_lpp();
+	store_ipl_parmblock();
+	uv_query_info();
+	setup_boot_command_line();
+	parse_boot_command_line();
 
 	/*
 	 * Non-randomized kernel physical start address must be _SEGMENT_SIZE
@@ -431,12 +460,8 @@ void startup_kernel(void)
 	oldmem_data.start = parmarea.oldmem_base;
 	oldmem_data.size = parmarea.oldmem_size;
 
-	store_ipl_parmblock();
 	read_ipl_report();
-	uv_query_info();
 	sclp_early_read_info();
-	setup_boot_command_line();
-	parse_boot_command_line();
 	detect_facilities();
 	cmma_init();
 	sanitize_prot_virt_host();
@@ -526,6 +551,7 @@ void startup_kernel(void)
 			    __kaslr_offset, __kaslr_offset_phys);
 	kaslr_adjust_got(__kaslr_offset);
 	setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit);
+	dump_physmem_reserved();
 	copy_bootdata();
 	__apply_alternatives((struct alt_instr *)_vmlinux_info.alt_instructions,
 			     (struct alt_instr *)_vmlinux_info.alt_instructions_end,
@@ -542,5 +568,6 @@ void startup_kernel(void)
 	 */
 	psw.addr = __kaslr_offset + vmlinux.entry;
 	psw.mask = PSW_KERNEL_BITS;
+	boot_debug("Starting kernel at:  0x%016lx\n", psw.addr);
 	__load_psw(psw);
 }
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 881a1ece422f..cfca94a8eac4 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define boot_fmt(fmt) "vmem: " fmt
 #include <linux/sched/task.h>
 #include <linux/pgtable.h>
 #include <linux/kasan.h>
@@ -13,6 +14,7 @@
 #include "decompressor.h"
 #include "boot.h"
 
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 struct ctlreg __bootdata_preserved(s390_invalid_asce);
 
 #ifdef CONFIG_PROC_FS
@@ -31,12 +33,42 @@ enum populate_mode {
 	POPULATE_IDENTITY,
 	POPULATE_KERNEL,
 #ifdef CONFIG_KASAN
+	/* KASAN modes should be last and grouped together, see is_kasan_populate_mode() */
 	POPULATE_KASAN_MAP_SHADOW,
 	POPULATE_KASAN_ZERO_SHADOW,
 	POPULATE_KASAN_SHALLOW
 #endif
 };
 
+#define POPULATE_MODE_NAME(t) case POPULATE_ ## t: return #t
+static inline const char *get_populate_mode_name(enum populate_mode t)
+{
+	switch (t) {
+	POPULATE_MODE_NAME(NONE);
+	POPULATE_MODE_NAME(DIRECT);
+	POPULATE_MODE_NAME(LOWCORE);
+	POPULATE_MODE_NAME(ABS_LOWCORE);
+	POPULATE_MODE_NAME(IDENTITY);
+	POPULATE_MODE_NAME(KERNEL);
+#ifdef CONFIG_KASAN
+	POPULATE_MODE_NAME(KASAN_MAP_SHADOW);
+	POPULATE_MODE_NAME(KASAN_ZERO_SHADOW);
+	POPULATE_MODE_NAME(KASAN_SHALLOW);
+#endif
+	default:
+		return "UNKNOWN";
+	}
+}
+
+static bool is_kasan_populate_mode(enum populate_mode mode)
+{
+#ifdef CONFIG_KASAN
+	return mode >= POPULATE_KASAN_MAP_SHADOW;
+#else
+	return false;
+#endif
+}
+
 static void pgtable_populate(unsigned long addr, unsigned long end, enum populate_mode mode);
 
 #ifdef CONFIG_KASAN
@@ -52,9 +84,12 @@ static pte_t pte_z;
 
 static inline void kasan_populate(unsigned long start, unsigned long end, enum populate_mode mode)
 {
-	start = PAGE_ALIGN_DOWN(__sha(start));
-	end = PAGE_ALIGN(__sha(end));
-	pgtable_populate(start, end, mode);
+	unsigned long sha_start = PAGE_ALIGN_DOWN(__sha(start));
+	unsigned long sha_end = PAGE_ALIGN(__sha(end));
+
+	boot_debug("%-17s 0x%016lx-0x%016lx >> 0x%016lx-0x%016lx\n", get_populate_mode_name(mode),
+		   start, end, sha_start, sha_end);
+	pgtable_populate(sha_start, sha_end, mode);
 }
 
 static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kernel_end)
@@ -200,7 +235,7 @@ static void *boot_crst_alloc(unsigned long val)
 	unsigned long size = PAGE_SIZE << CRST_ALLOC_ORDER;
 	unsigned long *table;
 
-	table = (unsigned long *)physmem_alloc_top_down(RR_VMEM, size, size);
+	table = (unsigned long *)physmem_alloc_or_die(RR_VMEM, size, size);
 	crst_table_init(table, val);
 	__arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER);
 	return table;
@@ -216,7 +251,7 @@ static pte_t *boot_pte_alloc(void)
 	 * during POPULATE_KASAN_MAP_SHADOW when EDAT is off
 	 */
 	if (!pte_leftover) {
-		pte_leftover = (void *)physmem_alloc_top_down(RR_VMEM, PAGE_SIZE, PAGE_SIZE);
+		pte_leftover = (void *)physmem_alloc_or_die(RR_VMEM, PAGE_SIZE, PAGE_SIZE);
 		pte = pte_leftover + _PAGE_TABLE_SIZE;
 		__arch_set_page_dat(pte, 1);
 	} else {
@@ -228,11 +263,12 @@ static pte_t *boot_pte_alloc(void)
 	return pte;
 }
 
-static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_mode mode)
+static unsigned long resolve_pa_may_alloc(unsigned long addr, unsigned long size,
+					  enum populate_mode mode)
 {
 	switch (mode) {
 	case POPULATE_NONE:
-		return -1;
+		return INVALID_PHYS_ADDR;
 	case POPULATE_DIRECT:
 		return addr;
 	case POPULATE_LOWCORE:
@@ -245,38 +281,64 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m
 		return __identity_pa(addr);
 #ifdef CONFIG_KASAN
 	case POPULATE_KASAN_MAP_SHADOW:
-		addr = physmem_alloc_top_down(RR_VMEM, size, size);
-		memset((void *)addr, 0, size);
-		return addr;
+		/* Allow to fail large page allocations, this will fall back to 1mb/4k pages */
+		addr = physmem_alloc(RR_VMEM, size, size, size == PAGE_SIZE);
+		if (addr) {
+			memset((void *)addr, 0, size);
+			return addr;
+		}
+		return INVALID_PHYS_ADDR;
 #endif
 	default:
-		return -1;
+		return INVALID_PHYS_ADDR;
 	}
 }
 
-static bool large_allowed(enum populate_mode mode)
+static bool large_page_mapping_allowed(enum populate_mode mode)
 {
-	return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL);
+	switch (mode) {
+	case POPULATE_DIRECT:
+	case POPULATE_IDENTITY:
+	case POPULATE_KERNEL:
+#ifdef CONFIG_KASAN
+	case POPULATE_KASAN_MAP_SHADOW:
+#endif
+		return true;
+	default:
+		return false;
+	}
 }
 
-static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end,
-			  enum populate_mode mode)
+static unsigned long try_get_large_pud_pa(pud_t *pu_dir, unsigned long addr, unsigned long end,
+					  enum populate_mode mode)
 {
-	unsigned long size = end - addr;
+	unsigned long pa, size = end - addr;
+
+	if (!machine.has_edat2 || !large_page_mapping_allowed(mode) ||
+	    !IS_ALIGNED(addr, PUD_SIZE) || (size < PUD_SIZE))
+		return INVALID_PHYS_ADDR;
+
+	pa = resolve_pa_may_alloc(addr, size, mode);
+	if (!IS_ALIGNED(pa, PUD_SIZE))
+		return INVALID_PHYS_ADDR;
 
-	return machine.has_edat2 && large_allowed(mode) &&
-	       IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) &&
-	       IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE);
+	return pa;
 }
 
-static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end,
-			  enum populate_mode mode)
+static unsigned long try_get_large_pmd_pa(pmd_t *pm_dir, unsigned long addr, unsigned long end,
+					  enum populate_mode mode)
 {
-	unsigned long size = end - addr;
+	unsigned long pa, size = end - addr;
 
-	return machine.has_edat1 && large_allowed(mode) &&
-	       IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) &&
-	       IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE);
+	if (!machine.has_edat1 || !large_page_mapping_allowed(mode) ||
+	    !IS_ALIGNED(addr, PMD_SIZE) || (size < PMD_SIZE))
+		return INVALID_PHYS_ADDR;
+
+	pa = resolve_pa_may_alloc(addr, size, mode);
+	if (!IS_ALIGNED(pa, PMD_SIZE))
+		return INVALID_PHYS_ADDR;
+
+	return pa;
 }
 
 static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end,
@@ -290,7 +352,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
 		if (pte_none(*pte)) {
 			if (kasan_pte_populate_zero_shadow(pte, mode))
 				continue;
-			entry = __pte(_pa(addr, PAGE_SIZE, mode));
+			entry = __pte(resolve_pa_may_alloc(addr, PAGE_SIZE, mode));
 			entry = set_pte_bit(entry, PAGE_KERNEL);
 			set_pte(pte, entry);
 			pages++;
@@ -303,7 +365,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e
 static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long end,
 				 enum populate_mode mode)
 {
-	unsigned long next, pages = 0;
+	unsigned long pa, next, pages = 0;
 	pmd_t *pmd, entry;
 	pte_t *pte;
 
@@ -313,8 +375,9 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
 		if (pmd_none(*pmd)) {
 			if (kasan_pmd_populate_zero_shadow(pmd, addr, next, mode))
 				continue;
-			if (can_large_pmd(pmd, addr, next, mode)) {
-				entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode));
+			pa = try_get_large_pmd_pa(pmd, addr, next, mode);
+			if (pa != INVALID_PHYS_ADDR) {
+				entry = __pmd(pa);
 				entry = set_pmd_bit(entry, SEGMENT_KERNEL);
 				set_pmd(pmd, entry);
 				pages++;
@@ -334,7 +397,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e
 static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end,
 				 enum populate_mode mode)
 {
-	unsigned long next, pages = 0;
+	unsigned long pa, next, pages = 0;
 	pud_t *pud, entry;
 	pmd_t *pmd;
 
@@ -344,8 +407,9 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e
 		if (pud_none(*pud)) {
 			if (kasan_pud_populate_zero_shadow(pud, addr, next, mode))
 				continue;
-			if (can_large_pud(pud, addr, next, mode)) {
-				entry = __pud(_pa(addr, _REGION3_SIZE, mode));
+			pa = try_get_large_pud_pa(pud, addr, next, mode);
+			if (pa != INVALID_PHYS_ADDR) {
+				entry = __pud(pa);
 				entry = set_pud_bit(entry, REGION3_KERNEL);
 				set_pud(pud, entry);
 				pages++;
@@ -388,6 +452,13 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat
 	pgd_t *pgd;
 	p4d_t *p4d;
 
+	if (!is_kasan_populate_mode(mode)) {
+		boot_debug("%-17s 0x%016lx-0x%016lx -> 0x%016lx-0x%016lx\n",
+			   get_populate_mode_name(mode), addr, end,
+			   resolve_pa_may_alloc(addr, 0, mode),
+			   resolve_pa_may_alloc(end - 1, 0, mode) + 1);
+	}
+
 	pgd = pgd_offset(&init_mm, addr);
 	for (; addr < end; addr = next, pgd++) {
 		next = pgd_addr_end(addr, end);
diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h
index 4a6b0a8b6412..2e829c16fd8a 100644
--- a/arch/s390/include/asm/asm-extable.h
+++ b/arch/s390/include/asm/asm-extable.h
@@ -9,11 +9,11 @@
 #define EX_TYPE_NONE		0
 #define EX_TYPE_FIXUP		1
 #define EX_TYPE_BPF		2
-#define EX_TYPE_UA_STORE	3
-#define EX_TYPE_UA_LOAD_MEM	4
+#define EX_TYPE_UA_FAULT	3
 #define EX_TYPE_UA_LOAD_REG	5
 #define EX_TYPE_UA_LOAD_REGPAIR	6
 #define EX_TYPE_ZEROPAD		7
+#define EX_TYPE_FPC		8
 
 #define EX_DATA_REG_ERR_SHIFT	0
 #define EX_DATA_REG_ERR		GENMASK(3, 0)
@@ -69,11 +69,8 @@
 #define EX_TABLE_AMODE31(_fault, _target)				\
 	__EX_TABLE(.amode31.ex_table, _fault, _target, EX_TYPE_FIXUP, __stringify(%%r0), __stringify(%%r0), 0)
 
-#define EX_TABLE_UA_STORE(_fault, _target, _regerr)			\
-	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_STORE, _regerr, _regerr, 0)
-
-#define EX_TABLE_UA_LOAD_MEM(_fault, _target, _regerr, _regmem, _len)	\
-	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_MEM, _regerr, _regmem, _len)
+#define EX_TABLE_UA_FAULT(_fault, _target, _regerr)			\
+	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_FAULT, _regerr, _regerr, 0)
 
 #define EX_TABLE_UA_LOAD_REG(_fault, _target, _regerr, _regzero)	\
 	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REG, _regerr, _regzero, 0)
@@ -84,4 +81,7 @@
 #define EX_TABLE_ZEROPAD(_fault, _target, _regdata, _regaddr)		\
 	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_ZEROPAD, _regdata, _regaddr, 0)
 
+#define EX_TABLE_FPC(_fault, _target)					\
+	__EX_TABLE(__ex_table, _fault, _target, EX_TYPE_FPC, __stringify(%%r0), __stringify(%%r0), 0)
+
 #endif /* __ASM_EXTABLE_H */
diff --git a/arch/s390/include/asm/asm.h b/arch/s390/include/asm/asm.h
index ec011b94af2a..e9062b01e2a2 100644
--- a/arch/s390/include/asm/asm.h
+++ b/arch/s390/include/asm/asm.h
@@ -28,7 +28,7 @@
  * [var] also contains the program mask. CC_TRANSFORM() moves the condition
  * code to the two least significant bits and sets all other bits to zero.
  */
-#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_GCC_ASM_FLAG_OUTPUT_BROKEN))
+#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_CC_ASM_FLAG_OUTPUT_BROKEN))
 
 #define __HAVE_ASM_FLAG_OUTPUTS__
 
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 15aa64e3020e..d5125296ade2 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -60,7 +60,7 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig
 		asm volatile(
 			"	tm	%[addr],%[mask]\n"
 			: "=@cc" (cc)
-			: [addr] "R" (*addr), [mask] "I" (mask)
+			: [addr] "Q" (*addr), [mask] "I" (mask)
 			);
 		return cc == 3;
 	}
diff --git a/arch/s390/include/asm/boot_data.h b/arch/s390/include/asm/boot_data.h
index f7eed27b3220..f55f8227058e 100644
--- a/arch/s390/include/asm/boot_data.h
+++ b/arch/s390/include/asm/boot_data.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_S390_BOOT_DATA_H
 
+#include <linux/string.h>
 #include <asm/setup.h>
 #include <asm/ipl.h>
 
@@ -15,4 +16,54 @@ extern unsigned long ipl_cert_list_size;
 extern unsigned long early_ipl_comp_list_addr;
 extern unsigned long early_ipl_comp_list_size;
 
+extern char boot_rb[PAGE_SIZE * 2];
+extern bool boot_earlyprintk;
+extern size_t boot_rb_off;
+extern char bootdebug_filter[128];
+extern bool bootdebug;
+
+#define boot_rb_foreach(cb)							\
+	do {									\
+		size_t off = boot_rb_off + strlen(boot_rb + boot_rb_off) + 1;	\
+		size_t len;							\
+		for (; off < sizeof(boot_rb) && (len = strlen(boot_rb + off)); off += len + 1) \
+			cb(boot_rb + off);					\
+		for (off = 0; off < boot_rb_off && (len = strlen(boot_rb + off)); off += len + 1) \
+			cb(boot_rb + off);					\
+	} while (0)
+
+/*
+ * bootdebug_filter is a comma separated list of strings,
+ * where each string can be a prefix of the message.
+ */
+static inline bool bootdebug_filter_match(const char *buf)
+{
+	char *p = bootdebug_filter, *s;
+	char *end;
+
+	if (!*p)
+		return true;
+
+	end = p + strlen(p);
+	while (p < end) {
+		p = skip_spaces(p);
+		s = memscan(p, ',', end - p);
+		if (!strncmp(p, buf, s - p))
+			return true;
+		p = s + 1;
+	}
+	return false;
+}
+
+static inline const char *skip_timestamp(const char *buf)
+{
+#ifdef CONFIG_PRINTK_TIME
+	const char *p = memchr(buf, ']', strlen(buf));
+
+	if (p && p[1] == ' ')
+		return p + 2;
+#endif
+	return buf;
+}
+
 #endif /* _ASM_S390_BOOT_DATA_H */
diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h
index de510c9f6efa..f668bffd6dd3 100644
--- a/arch/s390/include/asm/fpu-insn.h
+++ b/arch/s390/include/asm/fpu-insn.h
@@ -100,19 +100,12 @@ static __always_inline void fpu_lfpc(unsigned int *fpc)
  */
 static inline void fpu_lfpc_safe(unsigned int *fpc)
 {
-	u32 tmp;
-
 	instrument_read(fpc, sizeof(*fpc));
 	asm_inline volatile(
-		"0:	lfpc	%[fpc]\n"
-		"1:	nopr	%%r7\n"
-		".pushsection .fixup, \"ax\"\n"
-		"2:	lghi	%[tmp],0\n"
-		"	sfpc	%[tmp]\n"
-		"	jg	1b\n"
-		".popsection\n"
-		EX_TABLE(1b, 2b)
-		: [tmp] "=d" (tmp)
+		"	lfpc	%[fpc]\n"
+		"0:	nopr	%%r7\n"
+		EX_TABLE_FPC(0b, 0b)
+		:
 		: [fpc] "Q" (*fpc)
 		: "memory");
 }
@@ -183,7 +176,19 @@ static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3)
 		     : "memory");
 }
 
-#ifdef CONFIG_CC_IS_CLANG
+#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS
+
+static __always_inline void fpu_vl(u8 v1, const void *vxr)
+{
+	instrument_read(vxr, sizeof(__vector128));
+	asm volatile("VL	%[v1],%O[vxr],,%R[vxr]\n"
+		     :
+		     : [vxr] "Q" (*(__vector128 *)vxr),
+		       [v1] "I" (v1)
+		     : "memory");
+}
+
+#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vl(u8 v1, const void *vxr)
 {
@@ -197,19 +202,7 @@ static __always_inline void fpu_vl(u8 v1, const void *vxr)
 		: "memory", "1");
 }
 
-#else /* CONFIG_CC_IS_CLANG */
-
-static __always_inline void fpu_vl(u8 v1, const void *vxr)
-{
-	instrument_read(vxr, sizeof(__vector128));
-	asm volatile("VL	%[v1],%O[vxr],,%R[vxr]\n"
-		     :
-		     : [vxr] "Q" (*(__vector128 *)vxr),
-		       [v1] "I" (v1)
-		     : "memory");
-}
-
-#endif /* CONFIG_CC_IS_CLANG */
+#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vleib(u8 v, s16 val, u8 index)
 {
@@ -238,7 +231,7 @@ static __always_inline u64 fpu_vlgvf(u8 v, u16 index)
 	return val;
 }
 
-#ifdef CONFIG_CC_IS_CLANG
+#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS
 
 static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 {
@@ -246,17 +239,15 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 
 	size = min(index + 1, sizeof(__vector128));
 	instrument_read(vxr, size);
-	asm volatile(
-		"	la	1,%[vxr]\n"
-		"	VLL	%[v1],%[index],0,1\n"
-		:
-		: [vxr] "R" (*(u8 *)vxr),
-		  [index] "d" (index),
-		  [v1] "I" (v1)
-		: "memory", "1");
+	asm volatile("VLL	%[v1],%[index],%O[vxr],%R[vxr]\n"
+		     :
+		     : [vxr] "Q" (*(u8 *)vxr),
+		       [index] "d" (index),
+		       [v1] "I" (v1)
+		     : "memory");
 }
 
-#else /* CONFIG_CC_IS_CLANG */
+#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 {
@@ -264,17 +255,19 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 
 	size = min(index + 1, sizeof(__vector128));
 	instrument_read(vxr, size);
-	asm volatile("VLL	%[v1],%[index],%O[vxr],%R[vxr]\n"
-		     :
-		     : [vxr] "Q" (*(u8 *)vxr),
-		       [index] "d" (index),
-		       [v1] "I" (v1)
-		     : "memory");
+	asm volatile(
+		"	la	1,%[vxr]\n"
+		"	VLL	%[v1],%[index],0,1\n"
+		:
+		: [vxr] "R" (*(u8 *)vxr),
+		  [index] "d" (index),
+		  [v1] "I" (v1)
+		: "memory", "1");
 }
 
-#endif /* CONFIG_CC_IS_CLANG */
+#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
-#ifdef CONFIG_CC_IS_CLANG
+#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS
 
 #define fpu_vlm(_v1, _v3, _vxrs)					\
 ({									\
@@ -284,17 +277,15 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 	} *_v = (void *)(_vxrs);					\
 									\
 	instrument_read(_v, size);					\
-	asm volatile(							\
-		"	la	1,%[vxrs]\n"				\
-		"	VLM	%[v1],%[v3],0,1\n"			\
-		:							\
-		: [vxrs] "R" (*_v),					\
-		  [v1] "I" (_v1), [v3] "I" (_v3)			\
-		: "memory", "1");					\
+	asm volatile("VLM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
+		     :							\
+		     : [vxrs] "Q" (*_v),				\
+		       [v1] "I" (_v1), [v3] "I" (_v3)			\
+		     : "memory");					\
 	(_v3) - (_v1) + 1;						\
 })
 
-#else /* CONFIG_CC_IS_CLANG */
+#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 #define fpu_vlm(_v1, _v3, _vxrs)					\
 ({									\
@@ -304,15 +295,17 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr)
 	} *_v = (void *)(_vxrs);					\
 									\
 	instrument_read(_v, size);					\
-	asm volatile("VLM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
-		     :							\
-		     : [vxrs] "Q" (*_v),				\
-		       [v1] "I" (_v1), [v3] "I" (_v3)			\
-		     : "memory");					\
+	asm volatile(							\
+		"	la	1,%[vxrs]\n"				\
+		"	VLM	%[v1],%[v3],0,1\n"			\
+		:							\
+		: [vxrs] "R" (*_v),					\
+		  [v1] "I" (_v1), [v3] "I" (_v3)			\
+		: "memory", "1");					\
 	(_v3) - (_v1) + 1;						\
 })
 
-#endif /* CONFIG_CC_IS_CLANG */
+#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vlr(u8 v1, u8 v2)
 {
@@ -362,7 +355,18 @@ static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3)
 		     : "memory");
 }
 
-#ifdef CONFIG_CC_IS_CLANG
+#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS
+
+static __always_inline void fpu_vst(u8 v1, const void *vxr)
+{
+	instrument_write(vxr, sizeof(__vector128));
+	asm volatile("VST	%[v1],%O[vxr],,%R[vxr]\n"
+		     : [vxr] "=Q" (*(__vector128 *)vxr)
+		     : [v1] "I" (v1)
+		     : "memory");
+}
+
+#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vst(u8 v1, const void *vxr)
 {
@@ -375,20 +379,23 @@ static __always_inline void fpu_vst(u8 v1, const void *vxr)
 		: "memory", "1");
 }
 
-#else /* CONFIG_CC_IS_CLANG */
+#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
-static __always_inline void fpu_vst(u8 v1, const void *vxr)
+#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS
+
+static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 {
-	instrument_write(vxr, sizeof(__vector128));
-	asm volatile("VST	%[v1],%O[vxr],,%R[vxr]\n"
-		     : [vxr] "=Q" (*(__vector128 *)vxr)
-		     : [v1] "I" (v1)
+	unsigned int size;
+
+	size = min(index + 1, sizeof(__vector128));
+	instrument_write(vxr, size);
+	asm volatile("VSTL	%[v1],%[index],%O[vxr],%R[vxr]\n"
+		     : [vxr] "=Q" (*(u8 *)vxr)
+		     : [index] "d" (index), [v1] "I" (v1)
 		     : "memory");
 }
 
-#endif /* CONFIG_CC_IS_CLANG */
-
-#ifdef CONFIG_CC_IS_CLANG
+#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 {
@@ -404,23 +411,9 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 		: "memory", "1");
 }
 
-#else /* CONFIG_CC_IS_CLANG */
+#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
-static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
-{
-	unsigned int size;
-
-	size = min(index + 1, sizeof(__vector128));
-	instrument_write(vxr, size);
-	asm volatile("VSTL	%[v1],%[index],%O[vxr],%R[vxr]\n"
-		     : [vxr] "=Q" (*(u8 *)vxr)
-		     : [index] "d" (index), [v1] "I" (v1)
-		     : "memory");
-}
-
-#endif /* CONFIG_CC_IS_CLANG */
-
-#ifdef CONFIG_CC_IS_CLANG
+#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS
 
 #define fpu_vstm(_v1, _v3, _vxrs)					\
 ({									\
@@ -430,16 +423,14 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 	} *_v = (void *)(_vxrs);					\
 									\
 	instrument_write(_v, size);					\
-	asm volatile(							\
-		"	la	1,%[vxrs]\n"				\
-		"	VSTM	%[v1],%[v3],0,1\n"			\
-		: [vxrs] "=R" (*_v)					\
-		: [v1] "I" (_v1), [v3] "I" (_v3)			\
-		: "memory", "1");					\
+	asm volatile("VSTM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
+		     : [vxrs] "=Q" (*_v)				\
+		     : [v1] "I" (_v1), [v3] "I" (_v3)			\
+		     : "memory");					\
 	(_v3) - (_v1) + 1;						\
 })
 
-#else /* CONFIG_CC_IS_CLANG */
+#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 #define fpu_vstm(_v1, _v3, _vxrs)					\
 ({									\
@@ -449,14 +440,16 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr)
 	} *_v = (void *)(_vxrs);					\
 									\
 	instrument_write(_v, size);					\
-	asm volatile("VSTM	%[v1],%[v3],%O[vxrs],%R[vxrs]\n"	\
-		     : [vxrs] "=Q" (*_v)				\
-		     : [v1] "I" (_v1), [v3] "I" (_v3)			\
-		     : "memory");					\
+	asm volatile(							\
+		"	la	1,%[vxrs]\n"				\
+		"	VSTM	%[v1],%[v3],0,1\n"			\
+		: [vxrs] "=R" (*_v)					\
+		: [v1] "I" (_v1), [v3] "I" (_v3)			\
+		: "memory", "1");					\
 	(_v3) - (_v1) + 1;						\
 })
 
-#endif /* CONFIG_CC_IS_CLANG */
+#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
 static __always_inline void fpu_vupllf(u8 v1, u8 v2)
 {
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index a3b73a4f626e..185331e91f83 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -51,6 +51,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	return addr;
 }
+#define ftrace_get_symaddr(fentry_ip) ((unsigned long)(fentry_ip))
 
 #include <linux/ftrace_regs.h>
 
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 752a2310f0d6..f5781794356b 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -2,80 +2,95 @@
 #ifndef _ASM_S390_FUTEX_H
 #define _ASM_S390_FUTEX_H
 
+#include <linux/instrumented.h>
 #include <linux/uaccess.h>
 #include <linux/futex.h>
 #include <asm/asm-extable.h>
 #include <asm/mmu_context.h>
 #include <asm/errno.h>
 
-#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg)	\
-	asm volatile(							\
-		"   sacf  256\n"					\
-		"0: l     %1,0(%6)\n"					\
-		"1:"insn						\
-		"2: cs    %1,%2,0(%6)\n"				\
-		"3: jl    1b\n"						\
-		"   lhi   %0,0\n"					\
-		"4: sacf  768\n"					\
-		EX_TABLE(0b,4b) EX_TABLE(1b,4b)				\
-		EX_TABLE(2b,4b) EX_TABLE(3b,4b)				\
-		: "=d" (ret), "=&d" (oldval), "=&d" (newval),		\
-		  "=m" (*uaddr)						\
-		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
-		  "m" (*uaddr) : "cc");
+#define FUTEX_OP_FUNC(name, insn)						\
+static uaccess_kmsan_or_inline int						\
+__futex_atomic_##name(int oparg, int *old, u32 __user *uaddr)			\
+{										\
+	int rc, new;								\
+										\
+	instrument_copy_from_user_before(old, uaddr, sizeof(*old));		\
+	asm_inline volatile(							\
+		"	sacf	256\n"						\
+		"0:	l	%[old],%[uaddr]\n"				\
+		"1:"insn							\
+		"2:	cs	%[old],%[new],%[uaddr]\n"			\
+		"3:	jl	1b\n"						\
+		"	lhi	%[rc],0\n"					\
+		"4:	sacf	768\n"						\
+		EX_TABLE_UA_FAULT(0b, 4b, %[rc])				\
+		EX_TABLE_UA_FAULT(1b, 4b, %[rc])				\
+		EX_TABLE_UA_FAULT(2b, 4b, %[rc])				\
+		EX_TABLE_UA_FAULT(3b, 4b, %[rc])				\
+		: [rc] "=d" (rc), [old] "=&d" (*old),				\
+		  [new] "=&d" (new), [uaddr] "+Q" (*uaddr)			\
+		: [oparg] "d" (oparg)						\
+		: "cc");							\
+	if (!rc)								\
+		instrument_copy_from_user_after(old, uaddr, sizeof(*old), 0);	\
+	return rc;								\
+}
+
+FUTEX_OP_FUNC(set, "lr %[new],%[oparg]\n")
+FUTEX_OP_FUNC(add, "lr %[new],%[old]\n ar %[new],%[oparg]\n")
+FUTEX_OP_FUNC(or,  "lr %[new],%[old]\n or %[new],%[oparg]\n")
+FUTEX_OP_FUNC(and, "lr %[new],%[old]\n nr %[new],%[oparg]\n")
+FUTEX_OP_FUNC(xor, "lr %[new],%[old]\n xr %[new],%[oparg]\n")
 
-static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
-		u32 __user *uaddr)
+static inline
+int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int oldval = 0, newval, ret;
+	int old, rc;
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("lr %2,%5\n",
-				  ret, oldval, newval, uaddr, oparg);
+		rc = __futex_atomic_set(oparg, &old, uaddr);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("lr %2,%1\nar %2,%5\n",
-				  ret, oldval, newval, uaddr, oparg);
+		rc = __futex_atomic_add(oparg, &old, uaddr);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("lr %2,%1\nor %2,%5\n",
-				  ret, oldval, newval, uaddr, oparg);
+		rc = __futex_atomic_or(oparg, &old, uaddr);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("lr %2,%1\nnr %2,%5\n",
-				  ret, oldval, newval, uaddr, ~oparg);
+		rc = __futex_atomic_and(~oparg, &old, uaddr);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("lr %2,%1\nxr %2,%5\n",
-				  ret, oldval, newval, uaddr, oparg);
+		rc = __futex_atomic_xor(oparg, &old, uaddr);
 		break;
 	default:
-		ret = -ENOSYS;
+		rc = -ENOSYS;
 	}
-
-	if (!ret)
-		*oval = oldval;
-
-	return ret;
+	if (!rc)
+		*oval = old;
+	return rc;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-						u32 oldval, u32 newval)
+static uaccess_kmsan_or_inline
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval)
 {
-	int ret;
+	int rc;
 
-	asm volatile(
-		"   sacf 256\n"
-		"0: cs   %1,%4,0(%5)\n"
-		"1: la   %0,0\n"
-		"2: sacf 768\n"
-		EX_TABLE(0b,2b) EX_TABLE(1b,2b)
-		: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
-		: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
+	instrument_copy_from_user_before(uval, uaddr, sizeof(*uval));
+	asm_inline volatile(
+		"	sacf	256\n"
+		"0:	cs	%[old],%[new],%[uaddr]\n"
+		"1:	lhi	%[rc],0\n"
+		"2:	sacf	768\n"
+		EX_TABLE_UA_FAULT(0b, 2b, %[rc])
+		EX_TABLE_UA_FAULT(1b, 2b, %[rc])
+		: [rc] "=d" (rc), [old] "+d" (oldval), [uaddr] "+Q" (*uaddr)
+		: [new] "d" (newval)
 		: "cc", "memory");
 	*uval = oldval;
-	return ret;
+	instrument_copy_from_user_after(uval, uaddr, sizeof(*uval), 0);
+	return rc;
 }
 
 #endif /* _ASM_S390_FUTEX_H */
diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 13f51a6a5bb1..4e73ef46d4b2 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -23,7 +23,6 @@
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
- * @crst_list: list of all crst tables used in the guest address space
  * @mm: pointer to the parent mm_struct
  * @guest_to_host: radix tree with guest to host address translation
  * @host_to_guest: radix tree with pointer to segment table entries
@@ -35,7 +34,6 @@
  * @guest_handle: protected virtual machine handle for the ultravisor
  * @host_to_rmap: radix tree with gmap_rmap lists
  * @children: list of shadow gmap structures
- * @pt_list: list of all page tables used in the shadow guest address space
  * @shadow_lock: spinlock to protect the shadow gmap list
  * @parent: pointer to the parent gmap for shadow guest address spaces
  * @orig_asce: ASCE for which the shadow page table has been created
@@ -45,7 +43,6 @@
  */
 struct gmap {
 	struct list_head list;
-	struct list_head crst_list;
 	struct mm_struct *mm;
 	struct radix_tree_root guest_to_host;
 	struct radix_tree_root host_to_guest;
@@ -61,7 +58,6 @@ struct gmap {
 	/* Additional data for shadow guest address spaces */
 	struct radix_tree_root host_to_rmap;
 	struct list_head children;
-	struct list_head pt_list;
 	spinlock_t shadow_lock;
 	struct gmap *parent;
 	unsigned long orig_asce;
@@ -106,23 +102,21 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit);
 void gmap_remove(struct gmap *gmap);
 struct gmap *gmap_get(struct gmap *gmap);
 void gmap_put(struct gmap *gmap);
+void gmap_free(struct gmap *gmap);
+struct gmap *gmap_alloc(unsigned long limit);
 
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
 		     unsigned long to, unsigned long len);
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
 unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
-unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
 int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
-int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
 void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
 void __gmap_zap(struct gmap *, unsigned long gaddr);
 void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
 
 int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val);
 
-struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
-			 int edat_level);
-int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level);
+void gmap_unshadow(struct gmap *sg);
 int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
 		    int fake);
 int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
@@ -131,24 +125,22 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
 		    int fake);
 int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
 		    int fake);
-int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
-			   unsigned long *pgt, int *dat_protection, int *fake);
 int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
 
 void gmap_register_pte_notifier(struct gmap_notifier *);
 void gmap_unregister_pte_notifier(struct gmap_notifier *);
 
-int gmap_mprotect_notify(struct gmap *, unsigned long start,
-			 unsigned long len, int prot);
+int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits);
 
 void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
 			     unsigned long gaddr, unsigned long vmaddr);
 int s390_disable_cow_sharing(void);
-void s390_unlist_old_asce(struct gmap *gmap);
 int s390_replace_asce(struct gmap *gmap);
 void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
 int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
 			    unsigned long end, bool interruptible);
+int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split);
+unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
 
 /**
  * s390_uv_destroy_range - Destroy a range of pages in the given mm.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 97c7c8127543..9a367866cab0 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -30,6 +30,8 @@
 #define KVM_S390_ESCA_CPU_SLOTS 248
 #define KVM_MAX_VCPUS 255
 
+#define KVM_INTERNAL_MEM_SLOTS 1
+
 /*
  * These seem to be used for allocating ->chip in the routing table, which we
  * don't use. 1 is as small as we can get to reduce the needed memory. If we
@@ -931,12 +933,14 @@ struct sie_page2 {
 	u8 reserved928[0x1000 - 0x928];			/* 0x0928 */
 };
 
+struct vsie_page;
+
 struct kvm_s390_vsie {
 	struct mutex mutex;
 	struct radix_tree_root addr_to_page;
 	int page_count;
 	int next;
-	struct page *pages[KVM_MAX_VCPUS];
+	struct vsie_page *pages[KVM_MAX_VCPUS];
 };
 
 struct kvm_s390_gisa_iam {
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 4f43cdd9835b..1ff145f7b52b 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -184,7 +184,11 @@ extern struct vm_layout vm_layout;
 
 #define __kaslr_offset		vm_layout.kaslr_offset
 #define __kaslr_offset_phys	vm_layout.kaslr_offset_phys
+#ifdef CONFIG_RANDOMIZE_IDENTITY_BASE
 #define __identity_base		vm_layout.identity_base
+#else
+#define __identity_base		0UL
+#endif
 #define ident_map_size		vm_layout.identity_size
 
 static inline unsigned long kaslr_offset(void)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 7b84ef6dc4b6..b19b6ed2ab53 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -53,29 +53,42 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	unsigned long *table = crst_table_alloc(mm);
 
-	if (table)
-		crst_table_init(table, _REGION2_ENTRY_EMPTY);
+	if (!table)
+		return NULL;
+	crst_table_init(table, _REGION2_ENTRY_EMPTY);
+	pagetable_p4d_ctor(virt_to_ptdesc(table));
+
 	return (p4d_t *) table;
 }
 
 static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 {
-	if (!mm_p4d_folded(mm))
-		crst_table_free(mm, (unsigned long *) p4d);
+	if (mm_p4d_folded(mm))
+		return;
+
+	pagetable_dtor(virt_to_ptdesc(p4d));
+	crst_table_free(mm, (unsigned long *) p4d);
 }
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	unsigned long *table = crst_table_alloc(mm);
-	if (table)
-		crst_table_init(table, _REGION3_ENTRY_EMPTY);
+
+	if (!table)
+		return NULL;
+	crst_table_init(table, _REGION3_ENTRY_EMPTY);
+	pagetable_pud_ctor(virt_to_ptdesc(table));
+
 	return (pud_t *) table;
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	if (!mm_pud_folded(mm))
-		crst_table_free(mm, (unsigned long *) pud);
+	if (mm_pud_folded(mm))
+		return;
+
+	pagetable_dtor(virt_to_ptdesc(pud));
+	crst_table_free(mm, (unsigned long *) pud);
 }
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
@@ -96,7 +109,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 	if (mm_pmd_folded(mm))
 		return;
-	pagetable_pmd_dtor(virt_to_ptdesc(pmd));
+	pagetable_dtor(virt_to_ptdesc(pmd));
 	crst_table_free(mm, (unsigned long *) pmd);
 }
 
@@ -117,11 +130,18 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return (pgd_t *) crst_table_alloc(mm);
+	unsigned long *table = crst_table_alloc(mm);
+
+	if (!table)
+		return NULL;
+	pagetable_pgd_ctor(virt_to_ptdesc(table));
+
+	return (pgd_t *) table;
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
+	pagetable_dtor(virt_to_ptdesc(pgd));
 	crst_table_free(mm, (unsigned long *) pgd);
 }
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index a3b51056a177..3ca5af4cfe43 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -420,9 +420,10 @@ void setup_protection_map(void);
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
-#define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
-#define PGSTE_VSIE_BIT	0x0000200000000000UL	/* ref'd in a shadow table */
+#define PGSTE_ST2_MASK	0x0000ffff00000000UL
+#define PGSTE_UC_BIT	0x0000000000008000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x0000000000004000UL	/* IPTE notify bit */
+#define PGSTE_VSIE_BIT	0x0000000000002000UL	/* ref'd in a shadow table */
 
 /* Guest Page State used for virtualization */
 #define _PGSTE_GPS_ZERO			0x0000000080000000UL
@@ -2007,4 +2008,18 @@ extern void s390_reset_cmma(struct mm_struct *mm);
 #define pmd_pgtable(pmd) \
 	((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE))
 
+static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt)
+{
+	unsigned long *pgstes, res;
+
+	pgstes = pgt + _PAGE_ENTRIES;
+
+	res = (pgstes[0] & PGSTE_ST2_MASK) << 16;
+	res |= pgstes[1] & PGSTE_ST2_MASK;
+	res |= (pgstes[2] & PGSTE_ST2_MASK) >> 16;
+	res |= (pgstes[3] & PGSTE_ST2_MASK) >> 32;
+
+	return res;
+}
+
 #endif /* _S390_PAGE_H */
diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h
index 51b68a43e195..7ef3bbec98b0 100644
--- a/arch/s390/include/asm/physmem_info.h
+++ b/arch/s390/include/asm/physmem_info.h
@@ -26,7 +26,7 @@ enum reserved_range_type {
 	RR_AMODE31,
 	RR_IPLREPORT,
 	RR_CERT_COMP_LIST,
-	RR_MEM_DETECT_EXTENDED,
+	RR_MEM_DETECT_EXT,
 	RR_VMEM,
 	RR_MAX
 };
@@ -128,7 +128,7 @@ static inline const char *get_rr_type_name(enum reserved_range_type t)
 	RR_TYPE_NAME(AMODE31);
 	RR_TYPE_NAME(IPLREPORT);
 	RR_TYPE_NAME(CERT_COMP_LIST);
-	RR_TYPE_NAME(MEM_DETECT_EXTENDED);
+	RR_TYPE_NAME(MEM_DETECT_EXT);
 	RR_TYPE_NAME(VMEM);
 	default:
 		return "UNKNOWN";
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 4da3b2956285..18f37dff03c9 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -172,6 +172,7 @@ void sclp_early_printk(const char *s);
 void __sclp_early_printk(const char *s, unsigned int len);
 void sclp_emergency_printk(const char *s);
 
+int sclp_init(void);
 int sclp_early_get_memsize(unsigned long *mem);
 int sclp_early_get_hsa_size(unsigned long *hsa_size);
 int _sclp_get_core_info(struct sclp_core_info *info);
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index ea150ea83e57..72655fd2d867 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -22,7 +22,6 @@
  * Pages used for the page tables is a different story. FIXME: more
  */
 
-void __tlb_remove_table(void *_table);
 static inline void tlb_flush(struct mmu_gather *tlb);
 static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
 		struct page *page, bool delay_rmap, int page_size);
@@ -87,7 +86,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb->cleared_pmds = 1;
 	if (mm_alloc_pgste(tlb->mm))
 		gmap_unlink(tlb->mm, (unsigned long *)pte, address);
-	tlb_remove_ptdesc(tlb, pte);
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pte));
 }
 
 /*
@@ -102,12 +101,11 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 {
 	if (mm_pmd_folded(tlb->mm))
 		return;
-	pagetable_pmd_dtor(virt_to_ptdesc(pmd));
 	__tlb_adjust_range(tlb, address, PAGE_SIZE);
 	tlb->mm->context.flush_mm = 1;
 	tlb->freed_tables = 1;
 	tlb->cleared_puds = 1;
-	tlb_remove_ptdesc(tlb, pmd);
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
 }
 
 /*
@@ -125,7 +123,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 	__tlb_adjust_range(tlb, address, PAGE_SIZE);
 	tlb->mm->context.flush_mm = 1;
 	tlb->freed_tables = 1;
-	tlb_remove_ptdesc(tlb, p4d);
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
 }
 
 /*
@@ -144,7 +142,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 	tlb->mm->context.flush_mm = 1;
 	tlb->freed_tables = 1;
 	tlb->cleared_p4ds = 1;
-	tlb_remove_ptdesc(tlb, pud);
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
 }
 
 #endif /* _S390_TLB_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index a81f897a81ce..f5920163ee97 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -22,16 +22,117 @@
 
 void debug_user_asce(int exit);
 
-unsigned long __must_check
-raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+union oac {
+	unsigned int val;
+	struct {
+		struct {
+			unsigned short key : 4;
+			unsigned short	   : 4;
+			unsigned short as  : 2;
+			unsigned short	   : 4;
+			unsigned short k   : 1;
+			unsigned short a   : 1;
+		} oac1;
+		struct {
+			unsigned short key : 4;
+			unsigned short	   : 4;
+			unsigned short as  : 2;
+			unsigned short	   : 4;
+			unsigned short k   : 1;
+			unsigned short a   : 1;
+		} oac2;
+	};
+};
 
-unsigned long __must_check
-raw_copy_to_user(void __user *to, const void *from, unsigned long n);
+static __always_inline __must_check unsigned long
+raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key)
+{
+	unsigned long rem;
+	union oac spec = {
+		.oac2.key = key,
+		.oac2.as = PSW_BITS_AS_SECONDARY,
+		.oac2.k = 1,
+		.oac2.a = 1,
+	};
 
-#ifndef CONFIG_KASAN
-#define INLINE_COPY_FROM_USER
-#define INLINE_COPY_TO_USER
-#endif
+	asm_inline volatile(
+		"	lr	%%r0,%[spec]\n"
+		"0:	mvcos	0(%[to]),0(%[from]),%[size]\n"
+		"1:	jz	5f\n"
+		"	algr	%[size],%[val]\n"
+		"	slgr	%[from],%[val]\n"
+		"	slgr	%[to],%[val]\n"
+		"	j	0b\n"
+		"2:	la	%[rem],4095(%[from])\n" /* rem = from + 4095 */
+		"	nr	%[rem],%[val]\n"	/* rem = (from + 4095) & -4096 */
+		"	slgr	%[rem],%[from]\n"
+		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
+		"	jnh	6f\n"
+		"3:	mvcos	0(%[to]),0(%[from]),%[rem]\n"
+		"4:	slgr	%[size],%[rem]\n"
+		"	j	6f\n"
+		"5:	lghi	%[size],0\n"
+		"6:\n"
+		EX_TABLE(0b, 2b)
+		EX_TABLE(1b, 2b)
+		EX_TABLE(3b, 6b)
+		EX_TABLE(4b, 6b)
+		: [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem)
+		: [val] "a" (-4096UL), [spec] "d" (spec.val)
+		: "cc", "memory", "0");
+	return size;
+}
+
+static __always_inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return raw_copy_from_user_key(to, from, n, 0);
+}
+
+static __always_inline __must_check unsigned long
+raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key)
+{
+	unsigned long rem;
+	union oac spec = {
+		.oac1.key = key,
+		.oac1.as = PSW_BITS_AS_SECONDARY,
+		.oac1.k = 1,
+		.oac1.a = 1,
+	};
+
+	asm_inline volatile(
+		"	lr	%%r0,%[spec]\n"
+		"0:	mvcos	0(%[to]),0(%[from]),%[size]\n"
+		"1:	jz	5f\n"
+		"	algr	%[size],%[val]\n"
+		"	slgr	%[to],%[val]\n"
+		"	slgr	%[from],%[val]\n"
+		"	j	0b\n"
+		"2:	la	%[rem],4095(%[to])\n"	/* rem = to + 4095 */
+		"	nr	%[rem],%[val]\n"	/* rem = (to + 4095) & -4096 */
+		"	slgr	%[rem],%[to]\n"
+		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
+		"	jnh	6f\n"
+		"3:	mvcos	0(%[to]),0(%[from]),%[rem]\n"
+		"4:	slgr	%[size],%[rem]\n"
+		"	j	6f\n"
+		"5:	lghi	%[size],0\n"
+		"6:\n"
+		EX_TABLE(0b, 2b)
+		EX_TABLE(1b, 2b)
+		EX_TABLE(3b, 6b)
+		EX_TABLE(4b, 6b)
+		: [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem)
+		: [val] "a" (-4096UL), [spec] "d" (spec.val)
+		: "cc", "memory", "0");
+	return size;
+}
+
+static __always_inline __must_check unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	return raw_copy_to_user_key(to, from, n, 0);
+}
 
 unsigned long __must_check
 _copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned long key);
@@ -55,63 +156,71 @@ copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned lo
 	return n;
 }
 
-union oac {
-	unsigned int val;
-	struct {
-		struct {
-			unsigned short key : 4;
-			unsigned short	   : 4;
-			unsigned short as  : 2;
-			unsigned short	   : 4;
-			unsigned short k   : 1;
-			unsigned short a   : 1;
-		} oac1;
-		struct {
-			unsigned short key : 4;
-			unsigned short	   : 4;
-			unsigned short as  : 2;
-			unsigned short	   : 4;
-			unsigned short k   : 1;
-			unsigned short a   : 1;
-		} oac2;
-	};
-};
-
 int __noreturn __put_user_bad(void);
 
 #ifdef CONFIG_KMSAN
-#define get_put_user_noinstr_attributes \
-	noinline __maybe_unused __no_sanitize_memory
+#define uaccess_kmsan_or_inline noinline __maybe_unused __no_sanitize_memory
 #else
-#define get_put_user_noinstr_attributes __always_inline
+#define uaccess_kmsan_or_inline __always_inline
 #endif
 
-#define DEFINE_PUT_USER(type)						\
-static get_put_user_noinstr_attributes int				\
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+
+#define DEFINE_PUT_USER_NOINSTR(type)					\
+static uaccess_kmsan_or_inline int					\
+__put_user_##type##_noinstr(unsigned type __user *to,			\
+			    unsigned type *from,			\
+			    unsigned long size)				\
+{									\
+	asm goto(							\
+		"	llilh	%%r0,%[spec]\n"				\
+		"0:	mvcos	%[to],%[from],%[size]\n"		\
+		"1:	nopr	%%r7\n"					\
+		EX_TABLE(0b, %l[Efault])				\
+		EX_TABLE(1b, %l[Efault])				\
+		: [to] "+Q" (*to)					\
+		: [size] "d" (size), [from] "Q" (*from),		\
+		  [spec] "I" (0x81)					\
+		: "cc", "0"						\
+		: Efault						\
+		);							\
+	return 0;							\
+Efault:									\
+	return -EFAULT;							\
+}
+
+#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+#define DEFINE_PUT_USER_NOINSTR(type)					\
+static uaccess_kmsan_or_inline int					\
 __put_user_##type##_noinstr(unsigned type __user *to,			\
 			    unsigned type *from,			\
 			    unsigned long size)				\
 {									\
-	union oac __oac_spec = {					\
-		.oac1.as = PSW_BITS_AS_SECONDARY,			\
-		.oac1.a = 1,						\
-	};								\
 	int rc;								\
 									\
 	asm volatile(							\
-		"	lr	0,%[spec]\n"				\
-		"0:	mvcos	%[_to],%[_from],%[_size]\n"		\
-		"1:	xr	%[rc],%[rc]\n"				\
+		"	llilh	%%r0,%[spec]\n"				\
+		"0:	mvcos	%[to],%[from],%[size]\n"		\
+		"1:	lhi	%[rc],0\n"				\
 		"2:\n"							\
-		EX_TABLE_UA_STORE(0b, 2b, %[rc])			\
-		EX_TABLE_UA_STORE(1b, 2b, %[rc])			\
-		: [rc] "=&d" (rc), [_to] "+Q" (*(to))			\
-		: [_size] "d" (size), [_from] "Q" (*(from)),		\
-		  [spec] "d" (__oac_spec.val)				\
+		EX_TABLE_UA_FAULT(0b, 2b, %[rc])			\
+		EX_TABLE_UA_FAULT(1b, 2b, %[rc])			\
+		: [rc] "=d" (rc), [to] "+Q" (*to)			\
+		: [size] "d" (size), [from] "Q" (*from),		\
+		  [spec] "I" (0x81)					\
 		: "cc", "0");						\
 	return rc;							\
-}									\
-									\
+}
+
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+DEFINE_PUT_USER_NOINSTR(char);
+DEFINE_PUT_USER_NOINSTR(short);
+DEFINE_PUT_USER_NOINSTR(int);
+DEFINE_PUT_USER_NOINSTR(long);
+
+#define DEFINE_PUT_USER(type)						\
 static __always_inline int						\
 __put_user_##type(unsigned type __user *to, unsigned type *from,	\
 		  unsigned long size)					\
@@ -128,69 +237,111 @@ DEFINE_PUT_USER(short);
 DEFINE_PUT_USER(int);
 DEFINE_PUT_USER(long);
 
-static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
-{
-	int rc;
+#define __put_user(x, ptr)						\
+({									\
+	__typeof__(*(ptr)) __x = (x);					\
+	int __prc;							\
+									\
+	__chk_user_ptr(ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		__prc = __put_user_char((unsigned char __user *)(ptr),	\
+					(unsigned char *)&__x,		\
+					sizeof(*(ptr)));		\
+		break;							\
+	case 2:								\
+		__prc = __put_user_short((unsigned short __user *)(ptr),\
+					 (unsigned short *)&__x,	\
+					 sizeof(*(ptr)));		\
+		break;							\
+	case 4:								\
+		__prc = __put_user_int((unsigned int __user *)(ptr),	\
+				       (unsigned int *)&__x,		\
+				       sizeof(*(ptr)));			\
+		break;							\
+	case 8:								\
+		__prc = __put_user_long((unsigned long __user *)(ptr),	\
+					(unsigned long *)&__x,		\
+					sizeof(*(ptr)));		\
+		break;							\
+	default:							\
+		__prc = __put_user_bad();				\
+		break;							\
+	}								\
+	__builtin_expect(__prc, 0);					\
+})
 
-	switch (size) {
-	case 1:
-		rc = __put_user_char((unsigned char __user *)ptr,
-				     (unsigned char *)x,
-				     size);
-		break;
-	case 2:
-		rc = __put_user_short((unsigned short __user *)ptr,
-				      (unsigned short *)x,
-				      size);
-		break;
-	case 4:
-		rc = __put_user_int((unsigned int __user *)ptr,
-				    (unsigned int *)x,
-				    size);
-		break;
-	case 8:
-		rc = __put_user_long((unsigned long __user *)ptr,
-				     (unsigned long *)x,
-				     size);
-		break;
-	default:
-		__put_user_bad();
-		break;
-	}
-	return rc;
-}
+#define put_user(x, ptr)						\
+({									\
+	might_fault();							\
+	__put_user(x, ptr);						\
+})
 
 int __noreturn __get_user_bad(void);
 
-#define DEFINE_GET_USER(type)						\
-static get_put_user_noinstr_attributes int				\
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+
+#define DEFINE_GET_USER_NOINSTR(type)					\
+static uaccess_kmsan_or_inline int					\
 __get_user_##type##_noinstr(unsigned type *to,				\
-			    unsigned type __user *from,			\
+			    const unsigned type __user *from,		\
+			    unsigned long size)				\
+{									\
+	asm goto(							\
+		"	lhi	%%r0,%[spec]\n"				\
+		"0:	mvcos	%[to],%[from],%[size]\n"		\
+		"1:	nopr	%%r7\n"					\
+		EX_TABLE(0b, %l[Efault])				\
+		EX_TABLE(1b, %l[Efault])				\
+		: [to] "=Q" (*to)					\
+		: [size] "d" (size), [from] "Q" (*from),		\
+		  [spec] "I" (0x81)					\
+		: "cc", "0"						\
+		: Efault						\
+		);							\
+	return 0;							\
+Efault:									\
+	*to = 0;							\
+	return -EFAULT;							\
+}
+
+#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+#define DEFINE_GET_USER_NOINSTR(type)					\
+static uaccess_kmsan_or_inline int					\
+__get_user_##type##_noinstr(unsigned type *to,				\
+			    const unsigned type __user *from,		\
 			    unsigned long size)				\
 {									\
-	union oac __oac_spec = {					\
-		.oac2.as = PSW_BITS_AS_SECONDARY,			\
-		.oac2.a = 1,						\
-	};								\
 	int rc;								\
 									\
 	asm volatile(							\
-		"	lr	0,%[spec]\n"				\
-		"0:	mvcos	0(%[_to]),%[_from],%[_size]\n"		\
-		"1:	xr	%[rc],%[rc]\n"				\
+		"	lhi	%%r0,%[spec]\n"				\
+		"0:	mvcos	%[to],%[from],%[size]\n"		\
+		"1:	lhi	%[rc],0\n"				\
 		"2:\n"							\
-		EX_TABLE_UA_LOAD_MEM(0b, 2b, %[rc], %[_to], %[_ksize])	\
-		EX_TABLE_UA_LOAD_MEM(1b, 2b, %[rc], %[_to], %[_ksize])	\
-		: [rc] "=&d" (rc), "=Q" (*(to))				\
-		: [_size] "d" (size), [_from] "Q" (*(from)),		\
-		  [spec] "d" (__oac_spec.val), [_to] "a" (to),		\
-		  [_ksize] "K" (size)					\
+		EX_TABLE_UA_FAULT(0b, 2b, %[rc])			\
+		EX_TABLE_UA_FAULT(1b, 2b, %[rc])			\
+		: [rc] "=d" (rc), [to] "=Q" (*to)			\
+		: [size] "d" (size), [from] "Q" (*from),		\
+		  [spec] "I" (0x81)					\
 		: "cc", "0");						\
+	if (likely(!rc))						\
+		return 0;						\
+	*to = 0;							\
 	return rc;							\
-}									\
-									\
+}
+
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+DEFINE_GET_USER_NOINSTR(char);
+DEFINE_GET_USER_NOINSTR(short);
+DEFINE_GET_USER_NOINSTR(int);
+DEFINE_GET_USER_NOINSTR(long);
+
+#define DEFINE_GET_USER(type)						\
 static __always_inline int						\
-__get_user_##type(unsigned type *to, unsigned type __user *from,	\
+__get_user_##type(unsigned type *to, const unsigned type __user *from,	\
 		  unsigned long size)					\
 {									\
 	int rc;								\
@@ -205,107 +356,50 @@ DEFINE_GET_USER(short);
 DEFINE_GET_USER(int);
 DEFINE_GET_USER(long);
 
-static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
-{
-	int rc;
-
-	switch (size) {
-	case 1:
-		rc = __get_user_char((unsigned char *)x,
-				     (unsigned char __user *)ptr,
-				     size);
-		break;
-	case 2:
-		rc = __get_user_short((unsigned short *)x,
-				      (unsigned short __user *)ptr,
-				      size);
-		break;
-	case 4:
-		rc = __get_user_int((unsigned int *)x,
-				    (unsigned int __user *)ptr,
-				    size);
-		break;
-	case 8:
-		rc = __get_user_long((unsigned long *)x,
-				     (unsigned long __user *)ptr,
-				     size);
-		break;
-	default:
-		__get_user_bad();
-		break;
-	}
-	return rc;
-}
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- */
-#define __put_user(x, ptr)						\
-({									\
-	__typeof__(*(ptr)) __x = (x);					\
-	int __pu_err = -EFAULT;						\
-									\
-	__chk_user_ptr(ptr);						\
-	switch (sizeof(*(ptr))) {					\
-	case 1:								\
-	case 2:								\
-	case 4:								\
-	case 8:								\
-		__pu_err = __put_user_fn(&__x, ptr, sizeof(*(ptr)));	\
-		break;							\
-	default:							\
-		__put_user_bad();					\
-		break;							\
-	}								\
-	__builtin_expect(__pu_err, 0);					\
-})
-
-#define put_user(x, ptr)						\
-({									\
-	might_fault();							\
-	__put_user(x, ptr);						\
-})
-
 #define __get_user(x, ptr)						\
 ({									\
-	int __gu_err = -EFAULT;						\
+	const __user void *____guptr = (ptr);				\
+	int __grc;							\
 									\
 	__chk_user_ptr(ptr);						\
 	switch (sizeof(*(ptr))) {					\
 	case 1: {							\
+		const unsigned char __user *__guptr = ____guptr;	\
 		unsigned char __x;					\
 									\
-		__gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr)));	\
+		__grc = __get_user_char(&__x, __guptr, sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *)&__x;		\
 		break;							\
 	};								\
 	case 2: {							\
+		const unsigned short __user *__guptr = ____guptr;	\
 		unsigned short __x;					\
 									\
-		__gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr)));	\
+		__grc = __get_user_short(&__x, __guptr, sizeof(*(ptr)));\
 		(x) = *(__force __typeof__(*(ptr)) *)&__x;		\
 		break;							\
 	};								\
 	case 4: {							\
+		const unsigned int __user *__guptr = ____guptr;		\
 		unsigned int __x;					\
 									\
-		__gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr)));	\
+		__grc = __get_user_int(&__x, __guptr, sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *)&__x;		\
 		break;							\
 	};								\
 	case 8: {							\
+		const unsigned long __user *__guptr = ____guptr;	\
 		unsigned long __x;					\
 									\
-		__gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr)));	\
+		__grc = __get_user_long(&__x, __guptr, sizeof(*(ptr)));	\
 		(x) = *(__force __typeof__(*(ptr)) *)&__x;		\
 		break;							\
 	};								\
 	default:							\
-		__get_user_bad();					\
+		__grc = __get_user_bad();				\
 		break;							\
 	}								\
-	__builtin_expect(__gu_err, 0);					\
+	__builtin_expect(__grc, 0);					\
 })
 
 #define get_user(x, ptr)						\
@@ -341,109 +435,71 @@ static inline void *s390_kernel_write(void *dst, const void *src, size_t size)
 	return __s390_kernel_write(dst, src, size);
 }
 
-int __noreturn __put_kernel_bad(void);
+void __noreturn __mvc_kernel_nofault_bad(void);
 
-#define __put_kernel_asm(val, to, insn)					\
-({									\
-	int __rc;							\
-									\
-	asm volatile(							\
-		"0:   " insn "  %[_val],%[_to]\n"			\
-		"1:	xr	%[rc],%[rc]\n"				\
-		"2:\n"							\
-		EX_TABLE_UA_STORE(0b, 2b, %[rc])			\
-		EX_TABLE_UA_STORE(1b, 2b, %[rc])			\
-		: [rc] "=d" (__rc), [_to] "+Q" (*(to))			\
-		: [_val] "d" (val)					\
-		: "cc");						\
-	__rc;								\
-})
+#if defined(CONFIG_CC_HAS_ASM_GOTO_OUTPUT) && defined(CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS)
 
-#define __put_kernel_nofault(dst, src, type, err_label)			\
+#define __mvc_kernel_nofault(dst, src, type, err_label)			\
 do {									\
-	unsigned long __x = (unsigned long)(*((type *)(src)));		\
-	int __pk_err;							\
-									\
 	switch (sizeof(type)) {						\
 	case 1:								\
-		__pk_err = __put_kernel_asm(__x, (type *)(dst), "stc"); \
-		break;							\
 	case 2:								\
-		__pk_err = __put_kernel_asm(__x, (type *)(dst), "sth"); \
-		break;							\
 	case 4:								\
-		__pk_err = __put_kernel_asm(__x, (type *)(dst), "st");	\
-		break;							\
 	case 8:								\
-		__pk_err = __put_kernel_asm(__x, (type *)(dst), "stg"); \
+		asm goto(						\
+			"0:	mvc	%O[_dst](%[_len],%R[_dst]),%[_src]\n" \
+			"1:	nopr	%%r7\n"				\
+			EX_TABLE(0b, %l[err_label])			\
+			EX_TABLE(1b, %l[err_label])			\
+			: [_dst] "=Q" (*(type *)dst)			\
+			: [_src] "Q" (*(type *)(src)),			\
+			  [_len] "I" (sizeof(type))			\
+			:						\
+			: err_label);					\
 		break;							\
 	default:							\
-		__pk_err = __put_kernel_bad();				\
+		__mvc_kernel_nofault_bad();				\
 		break;							\
 	}								\
-	if (unlikely(__pk_err))						\
-		goto err_label;						\
 } while (0)
 
-int __noreturn __get_kernel_bad(void);
-
-#define __get_kernel_asm(val, from, insn)				\
-({									\
-	int __rc;							\
-									\
-	asm volatile(							\
-		"0:   " insn "  %[_val],%[_from]\n"			\
-		"1:	xr	%[rc],%[rc]\n"				\
-		"2:\n"							\
-		EX_TABLE_UA_LOAD_REG(0b, 2b, %[rc], %[_val])		\
-		EX_TABLE_UA_LOAD_REG(1b, 2b, %[rc], %[_val])		\
-		: [rc] "=d" (__rc), [_val] "=d" (val)			\
-		: [_from] "Q" (*(from))					\
-		: "cc");						\
-	__rc;								\
-})
+#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT) && CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
 
-#define __get_kernel_nofault(dst, src, type, err_label)			\
+#define __mvc_kernel_nofault(dst, src, type, err_label)			\
 do {									\
-	int __gk_err;							\
+	type *(__dst) = (type *)(dst);					\
+	int __rc;							\
 									\
 	switch (sizeof(type)) {						\
-	case 1: {							\
-		unsigned char __x;					\
-									\
-		__gk_err = __get_kernel_asm(__x, (type *)(src), "ic");	\
-		*((type *)(dst)) = (type)__x;				\
-		break;							\
-	};								\
-	case 2: {							\
-		unsigned short __x;					\
-									\
-		__gk_err = __get_kernel_asm(__x, (type *)(src), "lh");	\
-		*((type *)(dst)) = (type)__x;				\
-		break;							\
-	};								\
-	case 4: {							\
-		unsigned int __x;					\
-									\
-		__gk_err = __get_kernel_asm(__x, (type *)(src), "l");	\
-		*((type *)(dst)) = (type)__x;				\
-		break;							\
-	};								\
-	case 8: {							\
-		unsigned long __x;					\
-									\
-		__gk_err = __get_kernel_asm(__x, (type *)(src), "lg");	\
-		*((type *)(dst)) = (type)__x;				\
+	case 1:								\
+	case 2:								\
+	case 4:								\
+	case 8:								\
+		asm_inline volatile(					\
+			"0:	mvc	0(%[_len],%[_dst]),%[_src]\n"	\
+			"1:	lhi	%[_rc],0\n"			\
+			"2:\n"						\
+			EX_TABLE_UA_FAULT(0b, 2b, %[_rc])		\
+			EX_TABLE_UA_FAULT(1b, 2b, %[_rc])		\
+			: [_rc] "=d" (__rc),				\
+			  "=m" (*__dst)					\
+			: [_src] "Q" (*(type *)(src)),			\
+			[_dst] "a" (__dst),				\
+			[_len] "I" (sizeof(type)));			\
+		if (__rc)						\
+			goto err_label;					\
 		break;							\
-	};								\
 	default:							\
-		__gk_err = __get_kernel_bad();				\
+		__mvc_kernel_nofault_bad();				\
 		break;							\
 	}								\
-	if (unlikely(__gk_err))						\
-		goto err_label;						\
 } while (0)
 
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT && CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */
+
+#define __get_kernel_nofault __mvc_kernel_nofault
+#define __put_kernel_nofault __mvc_kernel_nofault
+
 void __cmpxchg_user_key_called_with_bad_pointer(void);
 
 #define CMPXCHG_USER_KEY_MAX_LOOPS 128
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
index dc332609f2c3..b11f5b6d0bd1 100644
--- a/arch/s390/include/asm/uv.h
+++ b/arch/s390/include/asm/uv.h
@@ -628,12 +628,12 @@ static inline int is_prot_virt_host(void)
 }
 
 int uv_pin_shared(unsigned long paddr);
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
 int uv_destroy_folio(struct folio *folio);
 int uv_destroy_pte(pte_t pte);
 int uv_convert_from_secure_pte(pte_t pte);
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
+int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb);
+int uv_convert_from_secure(unsigned long paddr);
+int uv_convert_from_secure_folio(struct folio *folio);
 
 void setup_uv(void);
 
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index cd0c93a8fb8b..276cb4c1e11b 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -63,9 +63,7 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu)
 {
 	struct save_area *sa;
 
-	sa = memblock_alloc(sizeof(*sa), 8);
-	if (!sa)
-		return NULL;
+	sa = memblock_alloc_or_panic(sizeof(*sa), 8);
 
 	if (is_boot_cpu)
 		list_add(&sa->list, &dump_save_areas);
@@ -508,6 +506,19 @@ static int get_mem_chunk_cnt(void)
 	return cnt;
 }
 
+static void fill_ptload(Elf64_Phdr *phdr, unsigned long paddr,
+		unsigned long vaddr, unsigned long size)
+{
+	phdr->p_type = PT_LOAD;
+	phdr->p_vaddr = vaddr;
+	phdr->p_offset = paddr;
+	phdr->p_paddr = paddr;
+	phdr->p_filesz = size;
+	phdr->p_memsz = size;
+	phdr->p_flags = PF_R | PF_W | PF_X;
+	phdr->p_align = PAGE_SIZE;
+}
+
 /*
  * Initialize ELF loads (new kernel)
  */
@@ -520,14 +531,8 @@ static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm)
 	if (os_info_has_vm)
 		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
 	for_each_physmem_range(idx, &oldmem_type, &start, &end) {
-		phdr->p_type = PT_LOAD;
-		phdr->p_vaddr = old_identity_base + start;
-		phdr->p_offset = start;
-		phdr->p_paddr = start;
-		phdr->p_filesz = end - start;
-		phdr->p_memsz = end - start;
-		phdr->p_flags = PF_R | PF_W | PF_X;
-		phdr->p_align = PAGE_SIZE;
+		fill_ptload(phdr, start, old_identity_base + start,
+			    end - start);
 		phdr++;
 	}
 }
@@ -537,6 +542,22 @@ static bool os_info_has_vm(void)
 	return os_info_old_value(OS_INFO_KASLR_OFFSET);
 }
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+/*
+ * Fill PT_LOAD for a physical memory range owned by a device and detected by
+ * its device driver.
+ */
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+		unsigned long long paddr, unsigned long long size)
+{
+	unsigned long old_identity_base = 0;
+
+	if (os_info_has_vm())
+		old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
+	fill_ptload(phdr, paddr, old_identity_base + paddr, size);
+}
+#endif
+
 /*
  * Prepare PT_LOAD type program header for kernel image region
  */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index ba6b7329a10e..ce038e9205f7 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -1122,7 +1122,7 @@ static int s390dbf_procactive(const struct ctl_table *table, int write,
 		return 0;
 }
 
-static struct ctl_table s390dbf_table[] = {
+static const struct ctl_table s390dbf_table[] = {
 	{
 		.procname	= "debug_stoppable",
 		.data		= &debug_stoppable,
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 62f8f5a750a3..2fa25164df7d 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -50,6 +50,7 @@ decompressor_handled_param(facilities);
 decompressor_handled_param(nokaslr);
 decompressor_handled_param(cmma);
 decompressor_handled_param(relocate_lowcore);
+decompressor_handled_param(bootdebug);
 #if IS_ENABLED(CONFIG_KVM)
 decompressor_handled_param(prot_virt);
 #endif
@@ -58,7 +59,7 @@ static void __init kasan_early_init(void)
 {
 #ifdef CONFIG_KASAN
 	init_task.kasan_depth = 0;
-	sclp_early_printk("KernelAddressSanitizer initialized\n");
+	pr_info("KernelAddressSanitizer initialized\n");
 #endif
 }
 
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index c0b2c97efefb..63ba6306632e 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -266,18 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
-	int bit;
 
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
-	bit = ftrace_test_recursion_trylock(ip, *parent);
-	if (bit < 0)
-		return;
 	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
 		*parent = (unsigned long)&return_to_handler;
-	ftrace_test_recursion_unlock(bit);
 }
 
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c
index 2a99a216ab62..7857a7e8e56c 100644
--- a/arch/s390/kernel/hiperdispatch.c
+++ b/arch/s390/kernel/hiperdispatch.c
@@ -292,7 +292,7 @@ static int hiperdispatch_ctl_handler(const struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static struct ctl_table hiperdispatch_ctl_table[] = {
+static const struct ctl_table hiperdispatch_ctl_table[] = {
 	{
 		.procname	= "hiperdispatch",
 		.mode		= 0644,
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index 6652e54cf3db..6d1ffca5f798 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -166,7 +166,7 @@ static struct timer_list lgr_timer;
  */
 static void lgr_timer_set(void)
 {
-	mod_timer(&lgr_timer, jiffies + msecs_to_jiffies(LGR_TIMER_INTERVAL_SECS * MSEC_PER_SEC));
+	mod_timer(&lgr_timer, jiffies + secs_to_jiffies(LGR_TIMER_INTERVAL_SECS));
 }
 
 /*
diff --git a/arch/s390/kernel/numa.c b/arch/s390/kernel/numa.c
index ddc1448ea2e1..2fc40f97c0ad 100644
--- a/arch/s390/kernel/numa.c
+++ b/arch/s390/kernel/numa.c
@@ -21,12 +21,8 @@ void __init numa_setup(void)
 	nodes_clear(node_possible_map);
 	node_set(0, node_possible_map);
 	node_set_online(0);
-	for (nid = 0; nid < MAX_NUMNODES; nid++) {
-		NODE_DATA(nid) = memblock_alloc(sizeof(pg_data_t), 8);
-		if (!NODE_DATA(nid))
-			panic("%s: Failed to allocate %zu bytes align=0x%x\n",
-			      __func__, sizeof(pg_data_t), 8);
-	}
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		NODE_DATA(nid) = memblock_alloc_or_panic(sizeof(pg_data_t), 8);
 	NODE_DATA(0)->node_spanned_pages = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	NODE_DATA(0)->node_id = 0;
 }
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 0ce550faf073..d78bcfe707b5 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -157,6 +157,12 @@ u64 __bootdata_preserved(stfle_fac_list[16]);
 EXPORT_SYMBOL(stfle_fac_list);
 struct oldmem_data __bootdata_preserved(oldmem_data);
 
+char __bootdata(boot_rb)[PAGE_SIZE * 2];
+bool __bootdata(boot_earlyprintk);
+size_t __bootdata(boot_rb_off);
+char __bootdata(bootdebug_filter)[128];
+bool __bootdata(bootdebug);
+
 unsigned long __bootdata_preserved(VMALLOC_START);
 EXPORT_SYMBOL(VMALLOC_START);
 
@@ -376,11 +382,7 @@ static unsigned long __init stack_alloc_early(void)
 {
 	unsigned long stack;
 
-	stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE);
-	if (!stack) {
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, THREAD_SIZE, THREAD_SIZE);
-	}
+	stack = (unsigned long)memblock_alloc_or_panic(THREAD_SIZE, THREAD_SIZE);
 	return stack;
 }
 
@@ -504,10 +506,7 @@ static void __init setup_resources(void)
 	bss_resource.end = __pa_symbol(__bss_stop) - 1;
 
 	for_each_mem_range(i, &start, &end) {
-		res = memblock_alloc(sizeof(*res), 8);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes align=0x%x\n",
-			      __func__, sizeof(*res), 8);
+		res = memblock_alloc_or_panic(sizeof(*res), 8);
 		res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
 
 		res->name = "System RAM";
@@ -526,10 +525,7 @@ static void __init setup_resources(void)
 			    std_res->start > res->end)
 				continue;
 			if (std_res->end > res->end) {
-				sub_res = memblock_alloc(sizeof(*sub_res), 8);
-				if (!sub_res)
-					panic("%s: Failed to allocate %zu bytes align=0x%x\n",
-					      __func__, sizeof(*sub_res), 8);
+				sub_res = memblock_alloc_or_panic(sizeof(*sub_res), 8);
 				*sub_res = *std_res;
 				sub_res->end = res->end;
 				std_res->start = res->end + 1;
@@ -696,7 +692,7 @@ static void __init reserve_physmem_info(void)
 {
 	unsigned long addr, size;
 
-	if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size))
+	if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size))
 		memblock_reserve(addr, size);
 }
 
@@ -704,7 +700,7 @@ static void __init free_physmem_info(void)
 {
 	unsigned long addr, size;
 
-	if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size))
+	if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size))
 		memblock_phys_free(addr, size);
 }
 
@@ -734,7 +730,7 @@ static void __init reserve_lowcore(void)
 	void *lowcore_end = lowcore_start + sizeof(struct lowcore);
 	void *start, *end;
 
-	if ((void *)__identity_base < lowcore_end) {
+	if (absolute_pointer(__identity_base) < lowcore_end) {
 		start = max(lowcore_start, (void *)__identity_base);
 		end = min(lowcore_end, (void *)(__identity_base + ident_map_size));
 		memblock_reserve(__pa(start), __pa(end));
@@ -816,9 +812,7 @@ static void __init setup_randomness(void)
 {
 	struct sysinfo_3_2_2 *vmms;
 
-	vmms = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!vmms)
-		panic("Failed to allocate memory for sysinfo structure\n");
+	vmms = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
 		add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
 	memblock_free(vmms, PAGE_SIZE);
@@ -878,6 +872,23 @@ static void __init log_component_list(void)
 }
 
 /*
+ * Print avoiding interpretation of % in buf and taking bootdebug option
+ * into consideration.
+ */
+static void __init print_rb_entry(const char *buf)
+{
+	char fmt[] = KERN_SOH "0boot: %s";
+	int level = printk_get_level(buf);
+
+	buf = skip_timestamp(printk_skip_level(buf));
+	if (level == KERN_DEBUG[1] && (!bootdebug || !bootdebug_filter_match(buf)))
+		return;
+
+	fmt[1] = level;
+	printk(fmt, buf);
+}
+
+/*
  * Setup function called from init/main.c just after the banner
  * was printed.
  */
@@ -896,6 +907,9 @@ void __init setup_arch(char **cmdline_p)
 		pr_info("Linux is running natively in 64-bit mode\n");
 	else
 		pr_info("Linux is running as a guest in 64-bit mode\n");
+	/* Print decompressor messages if not already printed */
+	if (!boot_earlyprintk)
+		boot_rb_foreach(print_rb_entry);
 
 	if (have_relocated_lowcore())
 		pr_info("Lowcore relocated to 0x%px\n", get_lowcore());
@@ -999,3 +1013,8 @@ void __init setup_arch(char **cmdline_p)
 	/* Add system specific data to the random pool */
 	setup_randomness();
 }
+
+void __init arch_cpu_finalize_init(void)
+{
+	sclp_init();
+}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 822d8e6f8717..7b08399b0846 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -611,9 +611,7 @@ void __init smp_save_dump_ipl_cpu(void)
 	if (!dump_available())
 		return;
 	sa = save_area_alloc(true);
-	regs = memblock_alloc(512, 8);
-	if (!sa || !regs)
-		panic("could not allocate memory for boot CPU save area\n");
+	regs = memblock_alloc_or_panic(512, 8);
 	copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512);
 	save_area_add_regs(sa, regs);
 	memblock_free(regs, 512);
@@ -646,8 +644,6 @@ void __init smp_save_dump_secondary_cpus(void)
 		    SIGP_CC_NOT_OPERATIONAL)
 			continue;
 		sa = save_area_alloc(false);
-		if (!sa)
-			panic("could not allocate memory for save area\n");
 		__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(page));
 		save_area_add_regs(sa, page);
 		if (cpu_has_vx()) {
@@ -792,10 +788,7 @@ void __init smp_detect_cpus(void)
 	u16 address;
 
 	/* Get CPU information */
-	info = memblock_alloc(sizeof(*info), 8);
-	if (!info)
-		panic("%s: Failed to allocate %zu bytes align=0x%x\n",
-		      __func__, sizeof(*info), 8);
+	info = memblock_alloc_or_panic(sizeof(*info), 8);
 	smp_get_core_info(info, 1);
 	/* Find boot CPU type */
 	if (sclp.has_core_type) {
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 34a65c141ea0..e9f47c3a6197 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -662,12 +662,12 @@ static void stp_check_leap(void)
 		if (ret < 0)
 			pr_err("failed to set leap second flags\n");
 		/* arm Timer to clear leap second flags */
-		mod_timer(&stp_timer, jiffies + msecs_to_jiffies(14400 * MSEC_PER_SEC));
+		mod_timer(&stp_timer, jiffies + secs_to_jiffies(14400));
 	} else {
 		/* The day the leap second is scheduled for hasn't been reached. Retry
 		 * in one hour.
 		 */
-		mod_timer(&stp_timer, jiffies + msecs_to_jiffies(3600 * MSEC_PER_SEC));
+		mod_timer(&stp_timer, jiffies + secs_to_jiffies(3600));
 	}
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 39f5ed21f31a..211cc8382e4a 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -371,7 +371,7 @@ static void set_topology_timer(void)
 	if (atomic_add_unless(&topology_poll, -1, 0))
 		mod_timer(&topology_timer, jiffies + msecs_to_jiffies(100));
 	else
-		mod_timer(&topology_timer, jiffies + msecs_to_jiffies(60 * MSEC_PER_SEC));
+		mod_timer(&topology_timer, jiffies + secs_to_jiffies(60));
 }
 
 void topology_expect_change(void)
@@ -548,10 +548,7 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info,
 		nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
 	nr_masks = max(nr_masks, 1);
 	for (i = 0; i < nr_masks; i++) {
-		mask->next = memblock_alloc(sizeof(*mask->next), 8);
-		if (!mask->next)
-			panic("%s: Failed to allocate %zu bytes align=0x%x\n",
-			      __func__, sizeof(*mask->next), 8);
+		mask->next = memblock_alloc_or_panic(sizeof(*mask->next), 8);
 		mask = mask->next;
 	}
 }
@@ -579,10 +576,7 @@ void __init topology_init_early(void)
 	}
 	if (!MACHINE_HAS_TOPOLOGY)
 		goto out;
-	tl_info = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	if (!tl_info)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, PAGE_SIZE, PAGE_SIZE);
+	tl_info = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	info = tl_info;
 	store_topology(info);
 	cpu_management = detect_polarization(info->tle);
@@ -673,7 +667,7 @@ static int polarization_ctl_handler(const struct ctl_table *ctl, int write,
 	return set_polarization(polarization);
 }
 
-static struct ctl_table topology_ctl_table[] = {
+static const struct ctl_table topology_ctl_table[] = {
 	{
 		.procname	= "topology",
 		.mode		= 0644,
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 6f9654a191ad..9f05df2da2f7 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -19,19 +19,6 @@
 #include <asm/sections.h>
 #include <asm/uv.h>
 
-#if !IS_ENABLED(CONFIG_KVM)
-unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
-{
-	return 0;
-}
-
-int gmap_fault(struct gmap *gmap, unsigned long gaddr,
-	       unsigned int fault_flags)
-{
-	return 0;
-}
-#endif
-
 /* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
 int __bootdata_preserved(prot_virt_guest);
 EXPORT_SYMBOL(prot_virt_guest);
@@ -159,6 +146,7 @@ int uv_destroy_folio(struct folio *folio)
 	folio_put(folio);
 	return rc;
 }
+EXPORT_SYMBOL(uv_destroy_folio);
 
 /*
  * The present PTE still indirectly holds a folio reference through the mapping.
@@ -175,7 +163,7 @@ int uv_destroy_pte(pte_t pte)
  *
  * @paddr: Absolute host address of page to be exported
  */
-static int uv_convert_from_secure(unsigned long paddr)
+int uv_convert_from_secure(unsigned long paddr)
 {
 	struct uv_cb_cfs uvcb = {
 		.header.cmd = UVC_CMD_CONV_FROM_SEC_STOR,
@@ -187,11 +175,12 @@ static int uv_convert_from_secure(unsigned long paddr)
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(uv_convert_from_secure);
 
 /*
  * The caller must already hold a reference to the folio.
  */
-static int uv_convert_from_secure_folio(struct folio *folio)
+int uv_convert_from_secure_folio(struct folio *folio)
 {
 	int rc;
 
@@ -206,6 +195,7 @@ static int uv_convert_from_secure_folio(struct folio *folio)
 	folio_put(folio);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(uv_convert_from_secure_folio);
 
 /*
  * The present PTE still indirectly holds a folio reference through the mapping.
@@ -237,13 +227,33 @@ static int expected_folio_refs(struct folio *folio)
 	return res;
 }
 
-static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
+/**
+ * make_folio_secure() - make a folio secure
+ * @folio: the folio to make secure
+ * @uvcb: the uvcb that describes the UVC to be used
+ *
+ * The folio @folio will be made secure if possible, @uvcb will be passed
+ * as-is to the UVC.
+ *
+ * Return: 0 on success;
+ *         -EBUSY if the folio is in writeback or has too many references;
+ *         -E2BIG if the folio is large;
+ *         -EAGAIN if the UVC needs to be attempted again;
+ *         -ENXIO if the address is not mapped;
+ *         -EINVAL if the UVC failed for other reasons.
+ *
+ * Context: The caller must hold exactly one extra reference on the folio
+ *          (it's the same logic as split_folio())
+ */
+int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
 {
 	int expected, cc = 0;
 
+	if (folio_test_large(folio))
+		return -E2BIG;
 	if (folio_test_writeback(folio))
-		return -EAGAIN;
-	expected = expected_folio_refs(folio);
+		return -EBUSY;
+	expected = expected_folio_refs(folio) + 1;
 	if (!folio_ref_freeze(folio, expected))
 		return -EBUSY;
 	set_bit(PG_arch_1, &folio->flags);
@@ -267,251 +277,7 @@ static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
 		return -EAGAIN;
 	return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
 }
-
-/**
- * should_export_before_import - Determine whether an export is needed
- * before an import-like operation
- * @uvcb: the Ultravisor control block of the UVC to be performed
- * @mm: the mm of the process
- *
- * Returns whether an export is needed before every import-like operation.
- * This is needed for shared pages, which don't trigger a secure storage
- * exception when accessed from a different guest.
- *
- * Although considered as one, the Unpin Page UVC is not an actual import,
- * so it is not affected.
- *
- * No export is needed also when there is only one protected VM, because the
- * page cannot belong to the wrong VM in that case (there is no "other VM"
- * it can belong to).
- *
- * Return: true if an export is needed before every import, otherwise false.
- */
-static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
-{
-	/*
-	 * The misc feature indicates, among other things, that importing a
-	 * shared page from a different protected VM will automatically also
-	 * transfer its ownership.
-	 */
-	if (uv_has_feature(BIT_UV_FEAT_MISC))
-		return false;
-	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
-		return false;
-	return atomic_read(&mm->context.protected_count) > 1;
-}
-
-/*
- * Drain LRU caches: the local one on first invocation and the ones of all
- * CPUs on successive invocations. Returns "true" on the first invocation.
- */
-static bool drain_lru(bool *drain_lru_called)
-{
-	/*
-	 * If we have tried a local drain and the folio refcount
-	 * still does not match our expected safe value, try with a
-	 * system wide drain. This is needed if the pagevecs holding
-	 * the page are on a different CPU.
-	 */
-	if (*drain_lru_called) {
-		lru_add_drain_all();
-		/* We give up here, don't retry immediately. */
-		return false;
-	}
-	/*
-	 * We are here if the folio refcount does not match the
-	 * expected safe value. The main culprits are usually
-	 * pagevecs. With lru_add_drain() we drain the pagevecs
-	 * on the local CPU so that hopefully the refcount will
-	 * reach the expected safe value.
-	 */
-	lru_add_drain();
-	*drain_lru_called = true;
-	/* The caller should try again immediately */
-	return true;
-}
-
-/*
- * Requests the Ultravisor to make a page accessible to a guest.
- * If it's brought in the first time, it will be cleared. If
- * it has been exported before, it will be decrypted and integrity
- * checked.
- */
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
-{
-	struct vm_area_struct *vma;
-	bool drain_lru_called = false;
-	spinlock_t *ptelock;
-	unsigned long uaddr;
-	struct folio *folio;
-	pte_t *ptep;
-	int rc;
-
-again:
-	rc = -EFAULT;
-	mmap_read_lock(gmap->mm);
-
-	uaddr = __gmap_translate(gmap, gaddr);
-	if (IS_ERR_VALUE(uaddr))
-		goto out;
-	vma = vma_lookup(gmap->mm, uaddr);
-	if (!vma)
-		goto out;
-	/*
-	 * Secure pages cannot be huge and userspace should not combine both.
-	 * In case userspace does it anyway this will result in an -EFAULT for
-	 * the unpack. The guest is thus never reaching secure mode. If
-	 * userspace is playing dirty tricky with mapping huge pages later
-	 * on this will result in a segmentation fault.
-	 */
-	if (is_vm_hugetlb_page(vma))
-		goto out;
-
-	rc = -ENXIO;
-	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
-	if (!ptep)
-		goto out;
-	if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
-		folio = page_folio(pte_page(*ptep));
-		rc = -EAGAIN;
-		if (folio_test_large(folio)) {
-			rc = -E2BIG;
-		} else if (folio_trylock(folio)) {
-			if (should_export_before_import(uvcb, gmap->mm))
-				uv_convert_from_secure(PFN_PHYS(folio_pfn(folio)));
-			rc = make_folio_secure(folio, uvcb);
-			folio_unlock(folio);
-		}
-
-		/*
-		 * Once we drop the PTL, the folio may get unmapped and
-		 * freed immediately. We need a temporary reference.
-		 */
-		if (rc == -EAGAIN || rc == -E2BIG)
-			folio_get(folio);
-	}
-	pte_unmap_unlock(ptep, ptelock);
-out:
-	mmap_read_unlock(gmap->mm);
-
-	switch (rc) {
-	case -E2BIG:
-		folio_lock(folio);
-		rc = split_folio(folio);
-		folio_unlock(folio);
-		folio_put(folio);
-
-		switch (rc) {
-		case 0:
-			/* Splitting succeeded, try again immediately. */
-			goto again;
-		case -EAGAIN:
-			/* Additional folio references. */
-			if (drain_lru(&drain_lru_called))
-				goto again;
-			return -EAGAIN;
-		case -EBUSY:
-			/* Unexpected race. */
-			return -EAGAIN;
-		}
-		WARN_ON_ONCE(1);
-		return -ENXIO;
-	case -EAGAIN:
-		/*
-		 * If we are here because the UVC returned busy or partial
-		 * completion, this is just a useless check, but it is safe.
-		 */
-		folio_wait_writeback(folio);
-		folio_put(folio);
-		return -EAGAIN;
-	case -EBUSY:
-		/* Additional folio references. */
-		if (drain_lru(&drain_lru_called))
-			goto again;
-		return -EAGAIN;
-	case -ENXIO:
-		if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE))
-			return -EFAULT;
-		return -EAGAIN;
-	}
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_make_secure);
-
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
-{
-	struct uv_cb_cts uvcb = {
-		.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
-		.header.len = sizeof(uvcb),
-		.guest_handle = gmap->guest_handle,
-		.gaddr = gaddr,
-	};
-
-	return gmap_make_secure(gmap, gaddr, &uvcb);
-}
-EXPORT_SYMBOL_GPL(gmap_convert_to_secure);
-
-/**
- * gmap_destroy_page - Destroy a guest page.
- * @gmap: the gmap of the guest
- * @gaddr: the guest address to destroy
- *
- * An attempt will be made to destroy the given guest page. If the attempt
- * fails, an attempt is made to export the page. If both attempts fail, an
- * appropriate error is returned.
- */
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
-{
-	struct vm_area_struct *vma;
-	struct folio_walk fw;
-	unsigned long uaddr;
-	struct folio *folio;
-	int rc;
-
-	rc = -EFAULT;
-	mmap_read_lock(gmap->mm);
-
-	uaddr = __gmap_translate(gmap, gaddr);
-	if (IS_ERR_VALUE(uaddr))
-		goto out;
-	vma = vma_lookup(gmap->mm, uaddr);
-	if (!vma)
-		goto out;
-	/*
-	 * Huge pages should not be able to become secure
-	 */
-	if (is_vm_hugetlb_page(vma))
-		goto out;
-
-	rc = 0;
-	folio = folio_walk_start(&fw, vma, uaddr, 0);
-	if (!folio)
-		goto out;
-	/*
-	 * See gmap_make_secure(): large folios cannot be secure. Small
-	 * folio implies FW_LEVEL_PTE.
-	 */
-	if (folio_test_large(folio) || !pte_write(fw.pte))
-		goto out_walk_end;
-	rc = uv_destroy_folio(folio);
-	/*
-	 * Fault handlers can race; it is possible that two CPUs will fault
-	 * on the same secure page. One CPU can destroy the page, reboot,
-	 * re-enter secure mode and import it, while the second CPU was
-	 * stuck at the beginning of the handler. At some point the second
-	 * CPU will be able to progress, and it will not be able to destroy
-	 * the page. In that case we do not want to terminate the process,
-	 * we instead try to export the page.
-	 */
-	if (rc)
-		rc = uv_convert_from_secure_folio(folio);
-out_walk_end:
-	folio_walk_end(&fw, vma);
-out:
-	mmap_read_unlock(gmap->mm);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_destroy_page);
+EXPORT_SYMBOL_GPL(make_folio_secure);
 
 /*
  * To be called with the folio locked or with an extra reference! This will
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 377b9aaf8c92..ff1ddba96352 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -52,7 +52,6 @@ SECTIONS
 		SOFTIRQENTRY_TEXT
 		FTRACE_HOTPATCH_TRAMPOLINES_TEXT
 		*(.text.*_indirect_*)
-		*(.fixup)
 		*(.gnu.warning)
 		. = ALIGN(PAGE_SIZE);
 		_etext = .;		/* End of text section */
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 02217fb4ae10..f0ffe874adc2 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
 kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o
-kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o
+kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o
 
 kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o
 obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 9816b0060fbe..f6fded15633a 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -16,6 +16,7 @@
 #include <asm/gmap.h>
 #include <asm/dat-bits.h>
 #include "kvm-s390.h"
+#include "gmap.h"
 #include "gaccess.h"
 
 /*
@@ -1393,6 +1394,44 @@ shadow_pgt:
 }
 
 /**
+ * shadow_pgt_lookup() - find a shadow page table
+ * @sg: pointer to the shadow guest address space structure
+ * @saddr: the address in the shadow aguest address space
+ * @pgt: parent gmap address of the page table to get shadowed
+ * @dat_protection: if the pgtable is marked as protected by dat
+ * @fake: pgt references contiguous guest memory block, not a pgtable
+ *
+ * Returns 0 if the shadow page table was found and -EAGAIN if the page
+ * table was not found.
+ *
+ * Called with sg->mm->mmap_lock in read.
+ */
+static int shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt,
+			     int *dat_protection, int *fake)
+{
+	unsigned long pt_index;
+	unsigned long *table;
+	struct page *page;
+	int rc;
+
+	spin_lock(&sg->guest_table_lock);
+	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
+	if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
+		/* Shadow page tables are full pages (pte+pgste) */
+		page = pfn_to_page(*table >> PAGE_SHIFT);
+		pt_index = gmap_pgste_get_pgt_addr(page_to_virt(page));
+		*pgt = pt_index & ~GMAP_SHADOW_FAKE_TABLE;
+		*dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
+		*fake = !!(pt_index & GMAP_SHADOW_FAKE_TABLE);
+		rc = 0;
+	} else  {
+		rc = -EAGAIN;
+	}
+	spin_unlock(&sg->guest_table_lock);
+	return rc;
+}
+
+/**
  * kvm_s390_shadow_fault - handle fault on a shadow page table
  * @vcpu: virtual cpu
  * @sg: pointer to the shadow guest address space structure
@@ -1415,6 +1454,9 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	int dat_protection, fake;
 	int rc;
 
+	if (KVM_BUG_ON(!gmap_is_shadow(sg), vcpu->kvm))
+		return -EFAULT;
+
 	mmap_read_lock(sg->mm);
 	/*
 	 * We don't want any guest-2 tables to change - so the parent
@@ -1423,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
 	 */
 	ipte_lock(vcpu->kvm);
 
-	rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
+	rc = shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
 	if (rc)
 		rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection,
 					    &fake);
diff --git a/arch/s390/kvm/gmap-vsie.c b/arch/s390/kvm/gmap-vsie.c
new file mode 100644
index 000000000000..a6d1dbb04c97
--- /dev/null
+++ b/arch/s390/kvm/gmap-vsie.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Guest memory management for KVM/s390 nested VMs.
+ *
+ * Copyright IBM Corp. 2008, 2020, 2024
+ *
+ *    Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
+ *               Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               David Hildenbrand <david@redhat.com>
+ *               Janosch Frank <frankja@linux.vnet.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/pgtable.h>
+#include <linux/pagemap.h>
+#include <linux/mman.h>
+
+#include <asm/lowcore.h>
+#include <asm/gmap.h>
+#include <asm/uv.h>
+
+#include "kvm-s390.h"
+#include "gmap.h"
+
+/**
+ * gmap_find_shadow - find a specific asce in the list of shadow tables
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns the pointer to a gmap if a shadow table with the given asce is
+ * already available, ERR_PTR(-EAGAIN) if another one is just being created,
+ * otherwise NULL
+ *
+ * Context: Called with parent->shadow_lock held
+ */
+static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level)
+{
+	struct gmap *sg;
+
+	lockdep_assert_held(&parent->shadow_lock);
+	list_for_each_entry(sg, &parent->children, list) {
+		if (!gmap_shadow_valid(sg, asce, edat_level))
+			continue;
+		if (!sg->initialized)
+			return ERR_PTR(-EAGAIN);
+		refcount_inc(&sg->ref_count);
+		return sg;
+	}
+	return NULL;
+}
+
+/**
+ * gmap_shadow - create/find a shadow guest address space
+ * @parent: pointer to the parent gmap
+ * @asce: ASCE for which the shadow table is created
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * The pages of the top level page table referred by the asce parameter
+ * will be set to read-only and marked in the PGSTEs of the kvm process.
+ * The shadow table will be removed automatically on any change to the
+ * PTE mapping for the source table.
+ *
+ * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
+ * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
+ * parent gmap table could not be protected.
+ */
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level)
+{
+	struct gmap *sg, *new;
+	unsigned long limit;
+	int rc;
+
+	if (KVM_BUG_ON(parent->mm->context.allow_gmap_hpage_1m, (struct kvm *)parent->private) ||
+	    KVM_BUG_ON(gmap_is_shadow(parent), (struct kvm *)parent->private))
+		return ERR_PTR(-EFAULT);
+	spin_lock(&parent->shadow_lock);
+	sg = gmap_find_shadow(parent, asce, edat_level);
+	spin_unlock(&parent->shadow_lock);
+	if (sg)
+		return sg;
+	/* Create a new shadow gmap */
+	limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
+	if (asce & _ASCE_REAL_SPACE)
+		limit = -1UL;
+	new = gmap_alloc(limit);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+	new->mm = parent->mm;
+	new->parent = gmap_get(parent);
+	new->private = parent->private;
+	new->orig_asce = asce;
+	new->edat_level = edat_level;
+	new->initialized = false;
+	spin_lock(&parent->shadow_lock);
+	/* Recheck if another CPU created the same shadow */
+	sg = gmap_find_shadow(parent, asce, edat_level);
+	if (sg) {
+		spin_unlock(&parent->shadow_lock);
+		gmap_free(new);
+		return sg;
+	}
+	if (asce & _ASCE_REAL_SPACE) {
+		/* only allow one real-space gmap shadow */
+		list_for_each_entry(sg, &parent->children, list) {
+			if (sg->orig_asce & _ASCE_REAL_SPACE) {
+				spin_lock(&sg->guest_table_lock);
+				gmap_unshadow(sg);
+				spin_unlock(&sg->guest_table_lock);
+				list_del(&sg->list);
+				gmap_put(sg);
+				break;
+			}
+		}
+	}
+	refcount_set(&new->ref_count, 2);
+	list_add(&new->list, &parent->children);
+	if (asce & _ASCE_REAL_SPACE) {
+		/* nothing to protect, return right away */
+		new->initialized = true;
+		spin_unlock(&parent->shadow_lock);
+		return new;
+	}
+	spin_unlock(&parent->shadow_lock);
+	/* protect after insertion, so it will get properly invalidated */
+	mmap_read_lock(parent->mm);
+	rc = __kvm_s390_mprotect_many(parent, asce & _ASCE_ORIGIN,
+				      ((asce & _ASCE_TABLE_LENGTH) + 1),
+				      PROT_READ, GMAP_NOTIFY_SHADOW);
+	mmap_read_unlock(parent->mm);
+	spin_lock(&parent->shadow_lock);
+	new->initialized = true;
+	if (rc) {
+		list_del(&new->list);
+		gmap_free(new);
+		new = ERR_PTR(rc);
+	}
+	spin_unlock(&parent->shadow_lock);
+	return new;
+}
diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c
new file mode 100644
index 000000000000..02adf151d4de
--- /dev/null
+++ b/arch/s390/kvm/gmap.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Guest memory management for KVM/s390
+ *
+ * Copyright IBM Corp. 2008, 2020, 2024
+ *
+ *    Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
+ *               Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               David Hildenbrand <david@redhat.com>
+ *               Janosch Frank <frankja@linux.vnet.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/pgtable.h>
+#include <linux/pagemap.h>
+
+#include <asm/lowcore.h>
+#include <asm/gmap.h>
+#include <asm/uv.h>
+
+#include "gmap.h"
+
+/**
+ * should_export_before_import - Determine whether an export is needed
+ * before an import-like operation
+ * @uvcb: the Ultravisor control block of the UVC to be performed
+ * @mm: the mm of the process
+ *
+ * Returns whether an export is needed before every import-like operation.
+ * This is needed for shared pages, which don't trigger a secure storage
+ * exception when accessed from a different guest.
+ *
+ * Although considered as one, the Unpin Page UVC is not an actual import,
+ * so it is not affected.
+ *
+ * No export is needed also when there is only one protected VM, because the
+ * page cannot belong to the wrong VM in that case (there is no "other VM"
+ * it can belong to).
+ *
+ * Return: true if an export is needed before every import, otherwise false.
+ */
+static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+{
+	/*
+	 * The misc feature indicates, among other things, that importing a
+	 * shared page from a different protected VM will automatically also
+	 * transfer its ownership.
+	 */
+	if (uv_has_feature(BIT_UV_FEAT_MISC))
+		return false;
+	if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
+		return false;
+	return atomic_read(&mm->context.protected_count) > 1;
+}
+
+static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
+{
+	struct folio *folio = page_folio(page);
+	int rc;
+
+	/*
+	 * Secure pages cannot be huge and userspace should not combine both.
+	 * In case userspace does it anyway this will result in an -EFAULT for
+	 * the unpack. The guest is thus never reaching secure mode.
+	 * If userspace plays dirty tricks and decides to map huge pages at a
+	 * later point in time, it will receive a segmentation fault or
+	 * KVM_RUN will return -EFAULT.
+	 */
+	if (folio_test_hugetlb(folio))
+		return -EFAULT;
+	if (folio_test_large(folio)) {
+		mmap_read_unlock(gmap->mm);
+		rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true);
+		mmap_read_lock(gmap->mm);
+		if (rc)
+			return rc;
+		folio = page_folio(page);
+	}
+
+	if (!folio_trylock(folio))
+		return -EAGAIN;
+	if (should_export_before_import(uvcb, gmap->mm))
+		uv_convert_from_secure(folio_to_phys(folio));
+	rc = make_folio_secure(folio, uvcb);
+	folio_unlock(folio);
+
+	/*
+	 * In theory a race is possible and the folio might have become
+	 * large again before the folio_trylock() above. In that case, no
+	 * action is performed and -EAGAIN is returned; the callers will
+	 * have to try again later.
+	 * In most cases this implies running the VM again, getting the same
+	 * exception again, and make another attempt in this function.
+	 * This is expected to happen extremely rarely.
+	 */
+	if (rc == -E2BIG)
+		return -EAGAIN;
+	/* The folio has too many references, try to shake some off */
+	if (rc == -EBUSY) {
+		mmap_read_unlock(gmap->mm);
+		kvm_s390_wiggle_split_folio(gmap->mm, folio, false);
+		mmap_read_lock(gmap->mm);
+		return -EAGAIN;
+	}
+
+	return rc;
+}
+
+/**
+ * gmap_make_secure() - make one guest page secure
+ * @gmap: the guest gmap
+ * @gaddr: the guest address that needs to be made secure
+ * @uvcb: the UVCB specifying which operation needs to be performed
+ *
+ * Context: needs to be called with kvm->srcu held.
+ * Return: 0 on success, < 0 in case of error (see __gmap_make_secure()).
+ */
+int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
+{
+	struct kvm *kvm = gmap->private;
+	struct page *page;
+	int rc = 0;
+
+	lockdep_assert_held(&kvm->srcu);
+
+	page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
+	mmap_read_lock(gmap->mm);
+	if (page)
+		rc = __gmap_make_secure(gmap, page, uvcb);
+	kvm_release_page_clean(page);
+	mmap_read_unlock(gmap->mm);
+
+	return rc;
+}
+
+int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
+{
+	struct uv_cb_cts uvcb = {
+		.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
+		.header.len = sizeof(uvcb),
+		.guest_handle = gmap->guest_handle,
+		.gaddr = gaddr,
+	};
+
+	return gmap_make_secure(gmap, gaddr, &uvcb);
+}
+
+/**
+ * __gmap_destroy_page() - Destroy a guest page.
+ * @gmap: the gmap of the guest
+ * @page: the page to destroy
+ *
+ * An attempt will be made to destroy the given guest page. If the attempt
+ * fails, an attempt is made to export the page. If both attempts fail, an
+ * appropriate error is returned.
+ *
+ * Context: must be called holding the mm lock for gmap->mm
+ */
+static int __gmap_destroy_page(struct gmap *gmap, struct page *page)
+{
+	struct folio *folio = page_folio(page);
+	int rc;
+
+	/*
+	 * See gmap_make_secure(): large folios cannot be secure. Small
+	 * folio implies FW_LEVEL_PTE.
+	 */
+	if (folio_test_large(folio))
+		return -EFAULT;
+
+	rc = uv_destroy_folio(folio);
+	/*
+	 * Fault handlers can race; it is possible that two CPUs will fault
+	 * on the same secure page. One CPU can destroy the page, reboot,
+	 * re-enter secure mode and import it, while the second CPU was
+	 * stuck at the beginning of the handler. At some point the second
+	 * CPU will be able to progress, and it will not be able to destroy
+	 * the page. In that case we do not want to terminate the process,
+	 * we instead try to export the page.
+	 */
+	if (rc)
+		rc = uv_convert_from_secure_folio(folio);
+
+	return rc;
+}
+
+/**
+ * gmap_destroy_page() - Destroy a guest page.
+ * @gmap: the gmap of the guest
+ * @gaddr: the guest address to destroy
+ *
+ * An attempt will be made to destroy the given guest page. If the attempt
+ * fails, an attempt is made to export the page. If both attempts fail, an
+ * appropriate error is returned.
+ *
+ * Context: may sleep.
+ */
+int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
+{
+	struct page *page;
+	int rc = 0;
+
+	mmap_read_lock(gmap->mm);
+	page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr));
+	if (page)
+		rc = __gmap_destroy_page(gmap, page);
+	kvm_release_page_clean(page);
+	mmap_read_unlock(gmap->mm);
+	return rc;
+}
diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h
new file mode 100644
index 000000000000..c8f031c9ea5f
--- /dev/null
+++ b/arch/s390/kvm/gmap.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  KVM guest address space mapping code
+ *
+ *    Copyright IBM Corp. 2007, 2016, 2025
+ *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *               Claudio Imbrenda <imbrenda@linux.ibm.com>
+ */
+
+#ifndef ARCH_KVM_S390_GMAP_H
+#define ARCH_KVM_S390_GMAP_H
+
+#define GMAP_SHADOW_FAKE_TABLE 1ULL
+
+int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
+int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
+int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
+struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level);
+
+/**
+ * gmap_shadow_valid - check if a shadow guest address space matches the
+ *                     given properties and is still valid
+ * @sg: pointer to the shadow guest address space structure
+ * @asce: ASCE for which the shadow table is requested
+ * @edat_level: edat level to be used for the shadow translation
+ *
+ * Returns 1 if the gmap shadow is still valid and matches the given
+ * properties, the caller can continue using it. Returns 0 otherwise, the
+ * caller has to request a new shadow gmap in this case.
+ *
+ */
+static inline int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
+{
+	if (sg->removed)
+		return 0;
+	return sg->orig_asce == asce && sg->edat_level == edat_level;
+}
+
+#endif
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 5bbaadf75dc6..610dd44a948b 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -21,6 +21,7 @@
 #include "gaccess.h"
 #include "trace.h"
 #include "trace-s390.h"
+#include "gmap.h"
 
 u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
 {
@@ -367,7 +368,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 					      reg2, &srcaddr, GACC_FETCH, 0);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
-	rc = gmap_fault(vcpu->arch.gmap, srcaddr, 0);
+	rc = kvm_s390_handle_dat_fault(vcpu, srcaddr, 0);
 	if (rc != 0)
 		return rc;
 
@@ -376,7 +377,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
 					      reg1, &dstaddr, GACC_STORE, 0);
 	if (rc)
 		return kvm_s390_inject_prog_cond(vcpu, rc);
-	rc = gmap_fault(vcpu->arch.gmap, dstaddr, FAULT_FLAG_WRITE);
+	rc = kvm_s390_handle_dat_fault(vcpu, dstaddr, FOLL_WRITE);
 	if (rc != 0)
 		return rc;
 
@@ -549,7 +550,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
 	 * If the unpin did not succeed, the guest will exit again for the UVC
 	 * and we will retry the unpin.
 	 */
-	if (rc == -EINVAL)
+	if (rc == -EINVAL || rc == -ENXIO)
 		return 0;
 	/*
 	 * If we got -EAGAIN here, we simply return it. It will eventually
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index d4f031e086fc..07ff0e10cb7f 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2893,7 +2893,8 @@ int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
-	u64 uaddr;
+	u64 uaddr_s, uaddr_i;
+	int idx;
 
 	switch (ue->type) {
 	/* we store the userspace addresses instead of the guest addresses */
@@ -2901,14 +2902,16 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		if (kvm_is_ucontrol(kvm))
 			return -EINVAL;
 		e->set = set_adapter_int;
-		uaddr =  gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr);
-		if (uaddr == -EFAULT)
-			return -EFAULT;
-		e->adapter.summary_addr = uaddr;
-		uaddr =  gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr);
-		if (uaddr == -EFAULT)
+
+		idx = srcu_read_lock(&kvm->srcu);
+		uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr);
+		uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr);
+		srcu_read_unlock(&kvm->srcu, idx);
+
+		if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i))
 			return -EFAULT;
-		e->adapter.ind_addr = uaddr;
+		e->adapter.summary_addr = uaddr_s;
+		e->adapter.ind_addr = uaddr_i;
 		e->adapter.summary_offset = ue->u.adapter.summary_offset;
 		e->adapter.ind_offset = ue->u.adapter.ind_offset;
 		e->adapter.adapter_id = ue->u.adapter.adapter_id;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d8080c27d45b..ebecb96bacce 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -50,6 +50,7 @@
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "pci.h"
+#include "gmap.h"
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -3428,8 +3429,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	VM_EVENT(kvm, 3, "vm created with type %lu", type);
 
 	if (type & KVM_VM_S390_UCONTROL) {
+		struct kvm_userspace_memory_region2 fake_memslot = {
+			.slot = KVM_S390_UCONTROL_MEMSLOT,
+			.guest_phys_addr = 0,
+			.userspace_addr = 0,
+			.memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE),
+			.flags = 0,
+		};
+
 		kvm->arch.gmap = NULL;
 		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
+		/* one flat fake memslot covering the whole address-space */
+		mutex_lock(&kvm->slots_lock);
+		KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm);
+		mutex_unlock(&kvm->slots_lock);
 	} else {
 		if (sclp.hamax == U64_MAX)
 			kvm->arch.mem_limit = TASK_SIZE_MAX;
@@ -4498,6 +4511,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 	return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
 }
 
+static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags)
+{
+	struct kvm *kvm = gmap->private;
+	gfn_t gfn = gpa_to_gfn(gaddr);
+	bool unlocked;
+	hva_t vmaddr;
+	gpa_t tmp;
+	int rc;
+
+	if (kvm_is_ucontrol(kvm)) {
+		tmp = __gmap_translate(gmap, gaddr);
+		gfn = gpa_to_gfn(tmp);
+	}
+
+	vmaddr = gfn_to_hva(kvm, gfn);
+	rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
+	if (!rc)
+		rc = __gmap_link(gmap, gaddr, vmaddr);
+	return rc;
+}
+
+/**
+ * __kvm_s390_mprotect_many() - Apply specified protection to guest pages
+ * @gmap: the gmap of the guest
+ * @gpa: the starting guest address
+ * @npages: how many pages to protect
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: pgste notification bits to set
+ *
+ * Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one()
+ *
+ * Context: kvm->srcu and gmap->mm need to be held in read mode
+ */
+int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
+			     unsigned long bits)
+{
+	unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
+	gpa_t end = gpa + npages * PAGE_SIZE;
+	int rc;
+
+	for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) {
+		rc = gmap_protect_one(gmap, gpa, prot, bits);
+		if (rc == -EAGAIN) {
+			__kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag);
+			rc = gmap_protect_one(gmap, gpa, prot, bits);
+		}
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu)
+{
+	gpa_t gaddr = kvm_s390_get_prefix(vcpu);
+	int idx, rc;
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	mmap_read_lock(vcpu->arch.gmap->mm);
+
+	rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT);
+
+	mmap_read_unlock(vcpu->arch.gmap->mm);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	return rc;
+}
+
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
 retry:
@@ -4513,9 +4595,8 @@ retry:
 	 */
 	if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) {
 		int rc;
-		rc = gmap_mprotect_notify(vcpu->arch.gmap,
-					  kvm_s390_get_prefix(vcpu),
-					  PAGE_SIZE * 2, PROT_WRITE);
+
+		rc = kvm_s390_mprotect_notify_prefix(vcpu);
 		if (rc) {
 			kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu);
 			return rc;
@@ -4766,11 +4847,111 @@ static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu)
 	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
+static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu)
+{
+	KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
+		"Unexpected program interrupt 0x%x, TEID 0x%016lx",
+		current->thread.gmap_int_code, current->thread.gmap_teid.val);
+}
+
+/*
+ * __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu
+ * @vcpu: the vCPU whose gmap is to be fixed up
+ * @gfn: the guest frame number used for memslots (including fake memslots)
+ * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps
+ * @flags: FOLL_* flags
+ *
+ * Return: 0 on success, < 0 in case of error.
+ * Context: The mm lock must not be held before calling. May sleep.
+ */
+int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags)
+{
+	struct kvm_memory_slot *slot;
+	unsigned int fault_flags;
+	bool writable, unlocked;
+	unsigned long vmaddr;
+	struct page *page;
+	kvm_pfn_t pfn;
+	int rc;
+
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+		return vcpu_post_run_addressing_exception(vcpu);
+
+	fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0;
+	if (vcpu->arch.gmap->pfault_enabled)
+		flags |= FOLL_NOWAIT;
+	vmaddr = __gfn_to_hva_memslot(slot, gfn);
+
+try_again:
+	pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page);
+
+	/* Access outside memory, inject addressing exception */
+	if (is_noslot_pfn(pfn))
+		return vcpu_post_run_addressing_exception(vcpu);
+	/* Signal pending: try again */
+	if (pfn == KVM_PFN_ERR_SIGPENDING)
+		return -EAGAIN;
+
+	/* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */
+	if (pfn == KVM_PFN_ERR_NEEDS_IO) {
+		trace_kvm_s390_major_guest_pfault(vcpu);
+		if (kvm_arch_setup_async_pf(vcpu))
+			return 0;
+		vcpu->stat.pfault_sync++;
+		/* Could not setup async pfault, try again synchronously */
+		flags &= ~FOLL_NOWAIT;
+		goto try_again;
+	}
+	/* Any other error */
+	if (is_error_pfn(pfn))
+		return -EFAULT;
+
+	/* Success */
+	mmap_read_lock(vcpu->arch.gmap->mm);
+	/* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */
+	rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked);
+	if (!rc)
+		rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr);
+	scoped_guard(spinlock, &vcpu->kvm->mmu_lock) {
+		kvm_release_faultin_page(vcpu->kvm, page, false, writable);
+	}
+	mmap_read_unlock(vcpu->arch.gmap->mm);
+	return rc;
+}
+
+static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags)
+{
+	unsigned long gaddr_tmp;
+	gfn_t gfn;
+
+	gfn = gpa_to_gfn(gaddr);
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		/*
+		 * This translates the per-vCPU guest address into a
+		 * fake guest address, which can then be used with the
+		 * fake memslots that are identity mapping userspace.
+		 * This allows ucontrol VMs to use the normal fault
+		 * resolution path, like normal VMs.
+		 */
+		mmap_read_lock(vcpu->arch.gmap->mm);
+		gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr);
+		mmap_read_unlock(vcpu->arch.gmap->mm);
+		if (gaddr_tmp == -EFAULT) {
+			vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
+			vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
+			vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION;
+			return -EREMOTE;
+		}
+		gfn = gpa_to_gfn(gaddr_tmp);
+	}
+	return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags);
+}
+
 static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 {
 	unsigned int flags = 0;
 	unsigned long gaddr;
-	int rc = 0;
 
 	gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
 	if (kvm_s390_cur_gmap_fault_is_write())
@@ -4781,9 +4962,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 		vcpu->stat.exit_null++;
 		break;
 	case PGM_NON_SECURE_STORAGE_ACCESS:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
+		kvm_s390_assert_primary_as(vcpu);
 		/*
 		 * This is normal operation; a page belonging to a protected
 		 * guest has not been imported yet. Try to import the page into
@@ -4794,9 +4973,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 		break;
 	case PGM_SECURE_STORAGE_ACCESS:
 	case PGM_SECURE_STORAGE_VIOLATION:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
+		kvm_s390_assert_primary_as(vcpu);
 		/*
 		 * This can happen after a reboot with asynchronous teardown;
 		 * the new guest (normal or protected) will run on top of the
@@ -4825,40 +5002,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 	case PGM_REGION_FIRST_TRANS:
 	case PGM_REGION_SECOND_TRANS:
 	case PGM_REGION_THIRD_TRANS:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
-		if (vcpu->arch.gmap->pfault_enabled) {
-			rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT);
-			if (rc == -EFAULT)
-				return vcpu_post_run_addressing_exception(vcpu);
-			if (rc == -EAGAIN) {
-				trace_kvm_s390_major_guest_pfault(vcpu);
-				if (kvm_arch_setup_async_pf(vcpu))
-					return 0;
-				vcpu->stat.pfault_sync++;
-			} else {
-				return rc;
-			}
-		}
-		rc = gmap_fault(vcpu->arch.gmap, gaddr, flags);
-		if (rc == -EFAULT) {
-			if (kvm_is_ucontrol(vcpu->kvm)) {
-				vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
-				vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
-				vcpu->run->s390_ucontrol.pgm_code = 0x10;
-				return -EREMOTE;
-			}
-			return vcpu_post_run_addressing_exception(vcpu);
-		}
-		break;
+		kvm_s390_assert_primary_as(vcpu);
+		return vcpu_dat_fault_handler(vcpu, gaddr, flags);
 	default:
 		KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx",
 			current->thread.gmap_int_code, current->thread.gmap_teid.val);
 		send_sig(SIGSEGV, current, 0);
 		break;
 	}
-	return rc;
+	return 0;
 }
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@@ -5737,7 +5889,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 #endif
 	case KVM_S390_VCPU_FAULT: {
-		r = gmap_fault(vcpu->arch.gmap, arg, 0);
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = vcpu_dat_fault_handler(vcpu, arg, 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_ENABLE_CAP:
@@ -5853,7 +6007,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 {
 	gpa_t size;
 
-	if (kvm_is_ucontrol(kvm))
+	if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	/* When we are protected, we should not change the memory slots */
@@ -5905,6 +6059,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 {
 	int rc = 0;
 
+	if (kvm_is_ucontrol(kvm))
+		return;
+
 	switch (change) {
 	case KVM_MR_DELETE:
 		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 597d7a71deeb..8d3bbb2dd8d2 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -20,6 +20,8 @@
 #include <asm/processor.h>
 #include <asm/sclp.h>
 
+#define KVM_S390_UCONTROL_MEMSLOT (KVM_USER_MEM_SLOTS + 0)
+
 static inline void kvm_s390_fpu_store(struct kvm_run *run)
 {
 	fpu_stfpc(&run->s.regs.fpc);
@@ -279,6 +281,15 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm)
 	return gd;
 }
 
+static inline hva_t gpa_to_hva(struct kvm *kvm, gpa_t gpa)
+{
+	hva_t hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+	if (!kvm_is_error_hva(hva))
+		hva |= offset_in_page(gpa);
+	return hva;
+}
+
 /* implemented in pv.c */
 int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
 int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
@@ -408,6 +419,14 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
 void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
 __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
 int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc);
+int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags);
+int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
+			     unsigned long bits);
+
+static inline int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gpa_t gaddr, unsigned int flags)
+{
+	return __kvm_s390_handle_dat_fault(vcpu, gpa_to_gfn(gaddr), gaddr, flags);
+}
 
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 75e81ba26d04..22c012aa5206 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -17,6 +17,7 @@
 #include <linux/sched/mm.h>
 #include <linux/mmu_notifier.h>
 #include "kvm-s390.h"
+#include "gmap.h"
 
 bool kvm_s390_pv_is_protected(struct kvm *kvm)
 {
@@ -638,10 +639,28 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak,
 		.tweak[1] = offset,
 	};
 	int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb);
+	unsigned long vmaddr;
+	bool unlocked;
 
 	*rc = uvcb.header.rc;
 	*rrc = uvcb.header.rrc;
 
+	if (ret == -ENXIO) {
+		mmap_read_lock(kvm->mm);
+		vmaddr = gfn_to_hva(kvm, gpa_to_gfn(addr));
+		if (kvm_is_error_hva(vmaddr)) {
+			ret = -EFAULT;
+		} else {
+			ret = fixup_user_fault(kvm->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
+			if (!ret)
+				ret = __gmap_link(kvm->arch.gmap, addr, vmaddr);
+		}
+		mmap_read_unlock(kvm->mm);
+		if (!ret)
+			return -EAGAIN;
+		return ret;
+	}
+
 	if (ret && ret != -EAGAIN)
 		KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x",
 			     uvcb.gaddr, *rc, *rrc);
@@ -660,6 +679,8 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
 	KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx",
 		     addr, size);
 
+	guard(srcu)(&kvm->srcu);
+
 	while (offset < size) {
 		ret = unpack_one(kvm, addr, tweak, offset, rc, rrc);
 		if (ret == -EAGAIN) {
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a687695d8f68..a78df3a4f353 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -13,6 +13,7 @@
 #include <linux/bitmap.h>
 #include <linux/sched/signal.h>
 #include <linux/io.h>
+#include <linux/mman.h>
 
 #include <asm/gmap.h>
 #include <asm/mmu_context.h>
@@ -22,6 +23,11 @@
 #include <asm/facility.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
+#include "gmap.h"
+
+enum vsie_page_flags {
+	VSIE_PAGE_IN_USE = 0,
+};
 
 struct vsie_page {
 	struct kvm_s390_sie_block scb_s;	/* 0x0000 */
@@ -46,7 +52,18 @@ struct vsie_page {
 	gpa_t gvrd_gpa;				/* 0x0240 */
 	gpa_t riccbd_gpa;			/* 0x0248 */
 	gpa_t sdnx_gpa;				/* 0x0250 */
-	__u8 reserved[0x0700 - 0x0258];		/* 0x0258 */
+	/*
+	 * guest address of the original SCB. Remains set for free vsie
+	 * pages, so we can properly look them up in our addr_to_page
+	 * radix tree.
+	 */
+	gpa_t scb_gpa;				/* 0x0258 */
+	/*
+	 * Flags: must be set/cleared atomically after the vsie page can be
+	 * looked up by other CPUs.
+	 */
+	unsigned long flags;			/* 0x0260 */
+	__u8 reserved[0x0700 - 0x0268];		/* 0x0268 */
 	struct kvm_s390_crypto_cb crycb;	/* 0x0700 */
 	__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE];	/* 0x0800 */
 };
@@ -584,7 +601,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 	struct kvm *kvm = gmap->private;
 	struct vsie_page *cur;
 	unsigned long prefix;
-	struct page *page;
 	int i;
 
 	if (!gmap_is_shadow(gmap))
@@ -594,10 +610,9 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
 	 * therefore we can safely reference them all the time.
 	 */
 	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
-		page = READ_ONCE(kvm->arch.vsie.pages[i]);
-		if (!page)
+		cur = READ_ONCE(kvm->arch.vsie.pages[i]);
+		if (!cur)
 			continue;
-		cur = page_to_virt(page);
 		if (READ_ONCE(cur->gmap) != gmap)
 			continue;
 		prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT;
@@ -1345,6 +1360,20 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	return rc;
 }
 
+/* Try getting a given vsie page, returning "true" on success. */
+static inline bool try_get_vsie_page(struct vsie_page *vsie_page)
+{
+	if (test_bit(VSIE_PAGE_IN_USE, &vsie_page->flags))
+		return false;
+	return !test_and_set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
+}
+
+/* Put a vsie page acquired through get_vsie_page / try_get_vsie_page. */
+static void put_vsie_page(struct vsie_page *vsie_page)
+{
+	clear_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
+}
+
 /*
  * Get or create a vsie page for a scb address.
  *
@@ -1355,16 +1384,21 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 {
 	struct vsie_page *vsie_page;
-	struct page *page;
 	int nr_vcpus;
 
 	rcu_read_lock();
-	page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
+	vsie_page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
 	rcu_read_unlock();
-	if (page) {
-		if (page_ref_inc_return(page) == 2)
-			return page_to_virt(page);
-		page_ref_dec(page);
+	if (vsie_page) {
+		if (try_get_vsie_page(vsie_page)) {
+			if (vsie_page->scb_gpa == addr)
+				return vsie_page;
+			/*
+			 * We raced with someone reusing + putting this vsie
+			 * page before we grabbed it.
+			 */
+			put_vsie_page(vsie_page);
+		}
 	}
 
 	/*
@@ -1375,36 +1409,40 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 
 	mutex_lock(&kvm->arch.vsie.mutex);
 	if (kvm->arch.vsie.page_count < nr_vcpus) {
-		page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
-		if (!page) {
+		vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
+		if (!vsie_page) {
 			mutex_unlock(&kvm->arch.vsie.mutex);
 			return ERR_PTR(-ENOMEM);
 		}
-		page_ref_inc(page);
-		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page;
+		__set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
+		kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = vsie_page;
 		kvm->arch.vsie.page_count++;
 	} else {
 		/* reuse an existing entry that belongs to nobody */
 		while (true) {
-			page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
-			if (page_ref_inc_return(page) == 2)
+			vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
+			if (try_get_vsie_page(vsie_page))
 				break;
-			page_ref_dec(page);
 			kvm->arch.vsie.next++;
 			kvm->arch.vsie.next %= nr_vcpus;
 		}
-		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
+		if (vsie_page->scb_gpa != ULONG_MAX)
+			radix_tree_delete(&kvm->arch.vsie.addr_to_page,
+					  vsie_page->scb_gpa >> 9);
 	}
-	page->index = addr;
-	/* double use of the same address */
-	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) {
-		page_ref_dec(page);
+	/* Mark it as invalid until it resides in the tree. */
+	vsie_page->scb_gpa = ULONG_MAX;
+
+	/* Double use of the same address or allocation failure. */
+	if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9,
+			      vsie_page)) {
+		put_vsie_page(vsie_page);
 		mutex_unlock(&kvm->arch.vsie.mutex);
 		return NULL;
 	}
+	vsie_page->scb_gpa = addr;
 	mutex_unlock(&kvm->arch.vsie.mutex);
 
-	vsie_page = page_to_virt(page);
 	memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block));
 	release_gmap_shadow(vsie_page);
 	vsie_page->fault_addr = 0;
@@ -1412,14 +1450,6 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
 	return vsie_page;
 }
 
-/* put a vsie page acquired via get_vsie_page */
-static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page)
-{
-	struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT);
-
-	page_ref_dec(page);
-}
-
 int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
 {
 	struct vsie_page *vsie_page;
@@ -1470,7 +1500,7 @@ out_unshadow:
 out_unpin_scb:
 	unpin_scb(vcpu, vsie_page, scb_addr);
 out_put:
-	put_vsie_page(vcpu->kvm, vsie_page);
+	put_vsie_page(vsie_page);
 
 	return rc < 0 ? rc : 0;
 }
@@ -1486,18 +1516,18 @@ void kvm_s390_vsie_init(struct kvm *kvm)
 void kvm_s390_vsie_destroy(struct kvm *kvm)
 {
 	struct vsie_page *vsie_page;
-	struct page *page;
 	int i;
 
 	mutex_lock(&kvm->arch.vsie.mutex);
 	for (i = 0; i < kvm->arch.vsie.page_count; i++) {
-		page = kvm->arch.vsie.pages[i];
+		vsie_page = kvm->arch.vsie.pages[i];
 		kvm->arch.vsie.pages[i] = NULL;
-		vsie_page = page_to_virt(page);
 		release_gmap_shadow(vsie_page);
 		/* free the radix tree entry */
-		radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
-		__free_page(page);
+		if (vsie_page->scb_gpa != ULONG_MAX)
+			radix_tree_delete(&kvm->arch.vsie.addr_to_page,
+					  vsie_page->scb_gpa >> 9);
+		free_page((unsigned long)vsie_page);
 	}
 	kvm->arch.vsie.page_count = 0;
 	mutex_unlock(&kvm->arch.vsie.mutex);
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index c7c269d5c491..f977b7c37efc 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -31,51 +31,6 @@ void debug_user_asce(int exit)
 }
 #endif /*CONFIG_DEBUG_ENTRY */
 
-static unsigned long raw_copy_from_user_key(void *to, const void __user *from,
-					    unsigned long size, unsigned long key)
-{
-	unsigned long rem;
-	union oac spec = {
-		.oac2.key = key,
-		.oac2.as = PSW_BITS_AS_SECONDARY,
-		.oac2.k = 1,
-		.oac2.a = 1,
-	};
-
-	asm volatile(
-		"	lr	0,%[spec]\n"
-		"0:	mvcos	0(%[to]),0(%[from]),%[size]\n"
-		"1:	jz	5f\n"
-		"	algr	%[size],%[val]\n"
-		"	slgr	%[from],%[val]\n"
-		"	slgr	%[to],%[val]\n"
-		"	j	0b\n"
-		"2:	la	%[rem],4095(%[from])\n"	/* rem = from + 4095 */
-		"	nr	%[rem],%[val]\n"	/* rem = (from + 4095) & -4096 */
-		"	slgr	%[rem],%[from]\n"
-		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
-		"	jnh	6f\n"
-		"3:	mvcos	0(%[to]),0(%[from]),%[rem]\n"
-		"4:	slgr	%[size],%[rem]\n"
-		"	j	6f\n"
-		"5:	slgr	%[size],%[size]\n"
-		"6:\n"
-		EX_TABLE(0b, 2b)
-		EX_TABLE(1b, 2b)
-		EX_TABLE(3b, 6b)
-		EX_TABLE(4b, 6b)
-		: [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem)
-		: [val] "a" (-4096UL), [spec] "d" (spec.val)
-		: "cc", "memory", "0");
-	return size;
-}
-
-unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	return raw_copy_from_user_key(to, from, n, 0);
-}
-EXPORT_SYMBOL(raw_copy_from_user);
-
 unsigned long _copy_from_user_key(void *to, const void __user *from,
 				  unsigned long n, unsigned long key)
 {
@@ -93,51 +48,6 @@ unsigned long _copy_from_user_key(void *to, const void __user *from,
 }
 EXPORT_SYMBOL(_copy_from_user_key);
 
-static unsigned long raw_copy_to_user_key(void __user *to, const void *from,
-					  unsigned long size, unsigned long key)
-{
-	unsigned long rem;
-	union oac spec = {
-		.oac1.key = key,
-		.oac1.as = PSW_BITS_AS_SECONDARY,
-		.oac1.k = 1,
-		.oac1.a = 1,
-	};
-
-	asm volatile(
-		"	lr	0,%[spec]\n"
-		"0:	mvcos	0(%[to]),0(%[from]),%[size]\n"
-		"1:	jz	5f\n"
-		"	algr	%[size],%[val]\n"
-		"	slgr	%[to],%[val]\n"
-		"	slgr	%[from],%[val]\n"
-		"	j	0b\n"
-		"2:	la	%[rem],4095(%[to])\n"	/* rem = to + 4095 */
-		"	nr	%[rem],%[val]\n"	/* rem = (to + 4095) & -4096 */
-		"	slgr	%[rem],%[to]\n"
-		"	clgr	%[size],%[rem]\n"	/* copy crosses next page boundary? */
-		"	jnh	6f\n"
-		"3:	mvcos	0(%[to]),0(%[from]),%[rem]\n"
-		"4:	slgr	%[size],%[rem]\n"
-		"	j	6f\n"
-		"5:	slgr	%[size],%[size]\n"
-		"6:\n"
-		EX_TABLE(0b, 2b)
-		EX_TABLE(1b, 2b)
-		EX_TABLE(3b, 6b)
-		EX_TABLE(4b, 6b)
-		: [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem)
-		: [val] "a" (-4096UL), [spec] "d" (spec.val)
-		: "cc", "memory", "0");
-	return size;
-}
-
-unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	return raw_copy_to_user_key(to, from, n, 0);
-}
-EXPORT_SYMBOL(raw_copy_to_user);
-
 unsigned long _copy_to_user_key(void __user *to, const void *from,
 				unsigned long n, unsigned long key)
 {
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index d01724a715d0..39f44b6256e0 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -204,7 +204,7 @@ static void cmm_set_timer(void)
 			del_timer(&cmm_timer);
 		return;
 	}
-	mod_timer(&cmm_timer, jiffies + msecs_to_jiffies(cmm_timeout_seconds * MSEC_PER_SEC));
+	mod_timer(&cmm_timer, jiffies + secs_to_jiffies(cmm_timeout_seconds));
 }
 
 static void cmm_timer_fn(struct timer_list *unused)
@@ -332,7 +332,7 @@ static int cmm_timeout_handler(const struct ctl_table *ctl, int write,
 	return 0;
 }
 
-static struct ctl_table cmm_table[] = {
+static const struct ctl_table cmm_table[] = {
 	{
 		.procname	= "cmm_pages",
 		.mode		= 0644,
diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c
index 0a0738a473af..a046be1715cf 100644
--- a/arch/s390/mm/extable.c
+++ b/arch/s390/mm/extable.c
@@ -7,6 +7,7 @@
 #include <linux/panic.h>
 #include <asm/asm-extable.h>
 #include <asm/extable.h>
+#include <asm/fpu.h>
 
 const struct exception_table_entry *s390_search_extables(unsigned long addr)
 {
@@ -26,7 +27,7 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex, struct pt_r
 	return true;
 }
 
-static bool ex_handler_ua_store(const struct exception_table_entry *ex, struct pt_regs *regs)
+static bool ex_handler_ua_fault(const struct exception_table_entry *ex, struct pt_regs *regs)
 {
 	unsigned int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data);
 
@@ -35,18 +36,6 @@ static bool ex_handler_ua_store(const struct exception_table_entry *ex, struct p
 	return true;
 }
 
-static bool ex_handler_ua_load_mem(const struct exception_table_entry *ex, struct pt_regs *regs)
-{
-	unsigned int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
-	unsigned int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data);
-	size_t len = FIELD_GET(EX_DATA_LEN, ex->data);
-
-	regs->gprs[reg_err] = -EFAULT;
-	memset((void *)regs->gprs[reg_addr], 0, len);
-	regs->psw.addr = extable_fixup(ex);
-	return true;
-}
-
 static bool ex_handler_ua_load_reg(const struct exception_table_entry *ex,
 				   bool pair, struct pt_regs *regs)
 {
@@ -77,6 +66,13 @@ static bool ex_handler_zeropad(const struct exception_table_entry *ex, struct pt
 	return true;
 }
 
+static bool ex_handler_fpc(const struct exception_table_entry *ex, struct pt_regs *regs)
+{
+	fpu_sfpc(0);
+	regs->psw.addr = extable_fixup(ex);
+	return true;
+}
+
 bool fixup_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *ex;
@@ -89,16 +85,16 @@ bool fixup_exception(struct pt_regs *regs)
 		return ex_handler_fixup(ex, regs);
 	case EX_TYPE_BPF:
 		return ex_handler_bpf(ex, regs);
-	case EX_TYPE_UA_STORE:
-		return ex_handler_ua_store(ex, regs);
-	case EX_TYPE_UA_LOAD_MEM:
-		return ex_handler_ua_load_mem(ex, regs);
+	case EX_TYPE_UA_FAULT:
+		return ex_handler_ua_fault(ex, regs);
 	case EX_TYPE_UA_LOAD_REG:
 		return ex_handler_ua_load_reg(ex, false, regs);
 	case EX_TYPE_UA_LOAD_REGPAIR:
 		return ex_handler_ua_load_reg(ex, true, regs);
 	case EX_TYPE_ZEROPAD:
 		return ex_handler_zeropad(ex, regs);
+	case EX_TYPE_FPC:
+		return ex_handler_fpc(ex, regs);
 	}
 	panic("invalid exception table entry");
 }
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 16b8a36c56de..94d927785800 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -24,6 +24,16 @@
 #include <asm/page.h>
 #include <asm/tlb.h>
 
+/*
+ * The address is saved in a radix tree directly; NULL would be ambiguous,
+ * since 0 is a valid address, and NULL is returned when nothing was found.
+ * The lower bits are ignored by all users of the macro, so it can be used
+ * to distinguish a valid address 0 from a NULL.
+ */
+#define VALID_GADDR_FLAG 1
+#define IS_GADDR_VALID(gaddr) ((gaddr) & VALID_GADDR_FLAG)
+#define MAKE_VALID_GADDR(gaddr) (((gaddr) & HPAGE_MASK) | VALID_GADDR_FLAG)
+
 #define GMAP_SHADOW_FAKE_TABLE 1ULL
 
 static struct page *gmap_alloc_crst(void)
@@ -43,7 +53,7 @@ static struct page *gmap_alloc_crst(void)
  *
  * Returns a guest address space structure.
  */
-static struct gmap *gmap_alloc(unsigned long limit)
+struct gmap *gmap_alloc(unsigned long limit)
 {
 	struct gmap *gmap;
 	struct page *page;
@@ -70,9 +80,7 @@ static struct gmap *gmap_alloc(unsigned long limit)
 	gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT);
 	if (!gmap)
 		goto out;
-	INIT_LIST_HEAD(&gmap->crst_list);
 	INIT_LIST_HEAD(&gmap->children);
-	INIT_LIST_HEAD(&gmap->pt_list);
 	INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT);
 	INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT);
 	INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT);
@@ -82,8 +90,6 @@ static struct gmap *gmap_alloc(unsigned long limit)
 	page = gmap_alloc_crst();
 	if (!page)
 		goto out_free;
-	page->index = 0;
-	list_add(&page->lru, &gmap->crst_list);
 	table = page_to_virt(page);
 	crst_table_init(table, etype);
 	gmap->table = table;
@@ -97,6 +103,7 @@ out_free:
 out:
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(gmap_alloc);
 
 /**
  * gmap_create - create a guest address space
@@ -185,32 +192,46 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root)
 	} while (nr > 0);
 }
 
+static void gmap_free_crst(unsigned long *table, bool free_ptes)
+{
+	bool is_segment = (table[0] & _SEGMENT_ENTRY_TYPE_MASK) == 0;
+	int i;
+
+	if (is_segment) {
+		if (!free_ptes)
+			goto out;
+		for (i = 0; i < _CRST_ENTRIES; i++)
+			if (!(table[i] & _SEGMENT_ENTRY_INVALID))
+				page_table_free_pgste(page_ptdesc(phys_to_page(table[i])));
+	} else {
+		for (i = 0; i < _CRST_ENTRIES; i++)
+			if (!(table[i] & _REGION_ENTRY_INVALID))
+				gmap_free_crst(__va(table[i] & PAGE_MASK), free_ptes);
+	}
+
+out:
+	free_pages((unsigned long)table, CRST_ALLOC_ORDER);
+}
+
 /**
  * gmap_free - free a guest address space
  * @gmap: pointer to the guest address space structure
  *
  * No locks required. There are no references to this gmap anymore.
  */
-static void gmap_free(struct gmap *gmap)
+void gmap_free(struct gmap *gmap)
 {
-	struct page *page, *next;
-
 	/* Flush tlb of all gmaps (if not already done for shadows) */
 	if (!(gmap_is_shadow(gmap) && gmap->removed))
 		gmap_flush_tlb(gmap);
 	/* Free all segment & region tables. */
-	list_for_each_entry_safe(page, next, &gmap->crst_list, lru)
-		__free_pages(page, CRST_ALLOC_ORDER);
+	gmap_free_crst(gmap->table, gmap_is_shadow(gmap));
+
 	gmap_radix_tree_free(&gmap->guest_to_host);
 	gmap_radix_tree_free(&gmap->host_to_guest);
 
 	/* Free additional data for a shadow gmap */
 	if (gmap_is_shadow(gmap)) {
-		struct ptdesc *ptdesc, *n;
-
-		/* Free all page tables. */
-		list_for_each_entry_safe(ptdesc, n, &gmap->pt_list, pt_list)
-			page_table_free_pgste(ptdesc);
 		gmap_rmap_radix_tree_free(&gmap->host_to_rmap);
 		/* Release reference to the parent */
 		gmap_put(gmap->parent);
@@ -218,6 +239,7 @@ static void gmap_free(struct gmap *gmap)
 
 	kfree(gmap);
 }
+EXPORT_SYMBOL_GPL(gmap_free);
 
 /**
  * gmap_get - increase reference counter for guest address space
@@ -298,10 +320,8 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 	crst_table_init(new, init);
 	spin_lock(&gmap->guest_table_lock);
 	if (*table & _REGION_ENTRY_INVALID) {
-		list_add(&page->lru, &gmap->crst_list);
 		*table = __pa(new) | _REGION_ENTRY_LENGTH |
 			(*table & _REGION_ENTRY_TYPE_MASK);
-		page->index = gaddr;
 		page = NULL;
 	}
 	spin_unlock(&gmap->guest_table_lock);
@@ -310,21 +330,23 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 	return 0;
 }
 
-/**
- * __gmap_segment_gaddr - find virtual address from segment pointer
- * @entry: pointer to a segment table entry in the guest address space
- *
- * Returns the virtual address in the guest address space for the segment
- */
-static unsigned long __gmap_segment_gaddr(unsigned long *entry)
+static unsigned long host_to_guest_lookup(struct gmap *gmap, unsigned long vmaddr)
 {
-	struct page *page;
-	unsigned long offset;
+	return (unsigned long)radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+}
 
-	offset = (unsigned long) entry / sizeof(unsigned long);
-	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
-	page = pmd_pgtable_page((pmd_t *) entry);
-	return page->index + offset;
+static unsigned long host_to_guest_delete(struct gmap *gmap, unsigned long vmaddr)
+{
+	return (unsigned long)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+}
+
+static pmd_t *host_to_guest_pmd_delete(struct gmap *gmap, unsigned long vmaddr,
+				       unsigned long *gaddr)
+{
+	*gaddr = host_to_guest_delete(gmap, vmaddr);
+	if (IS_GADDR_VALID(*gaddr))
+		return (pmd_t *)gmap_table_walk(gmap, *gaddr, 1);
+	return NULL;
 }
 
 /**
@@ -336,16 +358,19 @@ static unsigned long __gmap_segment_gaddr(unsigned long *entry)
  */
 static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
 {
-	unsigned long *entry;
+	unsigned long gaddr;
 	int flush = 0;
+	pmd_t *pmdp;
 
 	BUG_ON(gmap_is_shadow(gmap));
 	spin_lock(&gmap->guest_table_lock);
-	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
-	if (entry) {
-		flush = (*entry != _SEGMENT_ENTRY_EMPTY);
-		*entry = _SEGMENT_ENTRY_EMPTY;
+
+	pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+	if (pmdp) {
+		flush = (pmd_val(*pmdp) != _SEGMENT_ENTRY_EMPTY);
+		*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 	}
+
 	spin_unlock(&gmap->guest_table_lock);
 	return flush;
 }
@@ -464,26 +489,6 @@ unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
 EXPORT_SYMBOL_GPL(__gmap_translate);
 
 /**
- * gmap_translate - translate a guest address to a user space address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- *
- * Returns user space address which corresponds to the guest address or
- * -EFAULT if no such mapping exists.
- * This function does not establish potentially missing page table entries.
- */
-unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr)
-{
-	unsigned long rc;
-
-	mmap_read_lock(gmap->mm);
-	rc = __gmap_translate(gmap, gaddr);
-	mmap_read_unlock(gmap->mm);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_translate);
-
-/**
  * gmap_unlink - disconnect a page table from the gmap shadow tables
  * @mm: pointer to the parent mm_struct
  * @table: pointer to the host page table
@@ -582,7 +587,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	spin_lock(&gmap->guest_table_lock);
 	if (*table == _SEGMENT_ENTRY_EMPTY) {
 		rc = radix_tree_insert(&gmap->host_to_guest,
-				       vmaddr >> PMD_SHIFT, table);
+				       vmaddr >> PMD_SHIFT,
+				       (void *)MAKE_VALID_GADDR(gaddr));
 		if (!rc) {
 			if (pmd_leaf(*pmd)) {
 				*table = (pmd_val(*pmd) &
@@ -605,130 +611,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	radix_tree_preload_end();
 	return rc;
 }
-
-/**
- * fixup_user_fault_nowait - manually resolve a user page fault without waiting
- * @mm:		mm_struct of target mm
- * @address:	user address
- * @fault_flags:flags to pass down to handle_mm_fault()
- * @unlocked:	did we unlock the mmap_lock while retrying
- *
- * This function behaves similarly to fixup_user_fault(), but it guarantees
- * that the fault will be resolved without waiting. The function might drop
- * and re-acquire the mm lock, in which case @unlocked will be set to true.
- *
- * The guarantee is that the fault is handled without waiting, but the
- * function itself might sleep, due to the lock.
- *
- * Context: Needs to be called with mm->mmap_lock held in read mode, and will
- * return with the lock held in read mode; @unlocked will indicate whether
- * the lock has been dropped and re-acquired. This is the same behaviour as
- * fixup_user_fault().
- *
- * Return: 0 on success, -EAGAIN if the fault cannot be resolved without
- * waiting, -EFAULT if the fault cannot be resolved, -ENOMEM if out of
- * memory.
- */
-static int fixup_user_fault_nowait(struct mm_struct *mm, unsigned long address,
-				   unsigned int fault_flags, bool *unlocked)
-{
-	struct vm_area_struct *vma;
-	unsigned int test_flags;
-	vm_fault_t fault;
-	int rc;
-
-	fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
-	test_flags = fault_flags & FAULT_FLAG_WRITE ? VM_WRITE : VM_READ;
-
-	vma = find_vma(mm, address);
-	if (unlikely(!vma || address < vma->vm_start))
-		return -EFAULT;
-	if (unlikely(!(vma->vm_flags & test_flags)))
-		return -EFAULT;
-
-	fault = handle_mm_fault(vma, address, fault_flags, NULL);
-	/* the mm lock has been dropped, take it again */
-	if (fault & VM_FAULT_COMPLETED) {
-		*unlocked = true;
-		mmap_read_lock(mm);
-		return 0;
-	}
-	/* the mm lock has not been dropped */
-	if (fault & VM_FAULT_ERROR) {
-		rc = vm_fault_to_errno(fault, 0);
-		BUG_ON(!rc);
-		return rc;
-	}
-	/* the mm lock has not been dropped because of FAULT_FLAG_RETRY_NOWAIT */
-	if (fault & VM_FAULT_RETRY)
-		return -EAGAIN;
-	/* nothing needed to be done and the mm lock has not been dropped */
-	return 0;
-}
-
-/**
- * __gmap_fault - resolve a fault on a guest address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- * @fault_flags: flags to pass down to handle_mm_fault()
- *
- * Context: Needs to be called with mm->mmap_lock held in read mode. Might
- * drop and re-acquire the lock. Will always return with the lock held.
- */
-static int __gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags)
-{
-	unsigned long vmaddr;
-	bool unlocked;
-	int rc = 0;
-
-retry:
-	unlocked = false;
-
-	vmaddr = __gmap_translate(gmap, gaddr);
-	if (IS_ERR_VALUE(vmaddr))
-		return vmaddr;
-
-	if (fault_flags & FAULT_FLAG_RETRY_NOWAIT)
-		rc = fixup_user_fault_nowait(gmap->mm, vmaddr, fault_flags, &unlocked);
-	else
-		rc = fixup_user_fault(gmap->mm, vmaddr, fault_flags, &unlocked);
-	if (rc)
-		return rc;
-	/*
-	 * In the case that fixup_user_fault unlocked the mmap_lock during
-	 * fault-in, redo __gmap_translate() to avoid racing with a
-	 * map/unmap_segment.
-	 * In particular, __gmap_translate(), fixup_user_fault{,_nowait}(),
-	 * and __gmap_link() must all be called atomically in one go; if the
-	 * lock had been dropped in between, a retry is needed.
-	 */
-	if (unlocked)
-		goto retry;
-
-	return __gmap_link(gmap, gaddr, vmaddr);
-}
-
-/**
- * gmap_fault - resolve a fault on a guest address
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: guest address
- * @fault_flags: flags to pass down to handle_mm_fault()
- *
- * Returns 0 on success, -ENOMEM for out of memory conditions, -EFAULT if the
- * vm address is already mapped to a different guest segment, and -EAGAIN if
- * FAULT_FLAG_RETRY_NOWAIT was specified and the fault could not be processed
- * immediately.
- */
-int gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags)
-{
-	int rc;
-
-	mmap_read_lock(gmap->mm);
-	rc = __gmap_fault(gmap, gaddr, fault_flags);
-	mmap_read_unlock(gmap->mm);
-	return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_fault);
+EXPORT_SYMBOL(__gmap_link);
 
 /*
  * this function is assumed to be called with mmap_lock held
@@ -853,8 +736,7 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start,
  *
  * Note: Can also be called for shadow gmaps.
  */
-static inline unsigned long *gmap_table_walk(struct gmap *gmap,
-					     unsigned long gaddr, int level)
+unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level)
 {
 	const int asce_type = gmap->asce & _ASCE_TYPE_MASK;
 	unsigned long *table = gmap->table;
@@ -905,6 +787,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 	}
 	return table;
 }
+EXPORT_SYMBOL(gmap_table_walk);
 
 /**
  * gmap_pte_op_walk - walk the gmap page table, get the page table lock
@@ -1101,86 +984,40 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
  * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
  * @bits: pgste notification bits to set
  *
- * Returns 0 if successfully protected, -ENOMEM if out of memory and
- * -EFAULT if gaddr is invalid (or mapping for shadows is missing).
+ * Returns:
+ *   PAGE_SIZE if a small page was successfully protected;
+ *   HPAGE_SIZE if a large page was successfully protected;
+ *   -ENOMEM if out of memory;
+ *   -EFAULT if gaddr is invalid (or mapping for shadows is missing);
+ *   -EAGAIN if the guest mapping is missing and should be fixed by the caller.
  *
- * Called with sg->mm->mmap_lock in read.
+ * Context: Called with sg->mm->mmap_lock in read.
  */
-static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
-			      unsigned long len, int prot, unsigned long bits)
+int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits)
 {
-	unsigned long vmaddr, dist;
 	pmd_t *pmdp;
-	int rc;
+	int rc = 0;
 
 	BUG_ON(gmap_is_shadow(gmap));
-	while (len) {
-		rc = -EAGAIN;
-		pmdp = gmap_pmd_op_walk(gmap, gaddr);
-		if (pmdp) {
-			if (!pmd_leaf(*pmdp)) {
-				rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
-						      bits);
-				if (!rc) {
-					len -= PAGE_SIZE;
-					gaddr += PAGE_SIZE;
-				}
-			} else {
-				rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot,
-						      bits);
-				if (!rc) {
-					dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK);
-					len = len < dist ? 0 : len - dist;
-					gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE;
-				}
-			}
-			gmap_pmd_op_end(gmap, pmdp);
-		}
-		if (rc) {
-			if (rc == -EINVAL)
-				return rc;
 
-			/* -EAGAIN, fixup of userspace mm and gmap */
-			vmaddr = __gmap_translate(gmap, gaddr);
-			if (IS_ERR_VALUE(vmaddr))
-				return vmaddr;
-			rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
-			if (rc)
-				return rc;
-		}
-	}
-	return 0;
-}
+	pmdp = gmap_pmd_op_walk(gmap, gaddr);
+	if (!pmdp)
+		return -EAGAIN;
 
-/**
- * gmap_mprotect_notify - change access rights for a range of ptes and
- *                        call the notifier if any pte changes again
- * @gmap: pointer to guest mapping meta data structure
- * @gaddr: virtual address in the guest address space
- * @len: size of area
- * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
- *
- * Returns 0 if for each page in the given range a gmap mapping exists,
- * the new access rights could be set and the notifier could be armed.
- * If the gmap mapping is missing for one or more pages -EFAULT is
- * returned. If no memory could be allocated -ENOMEM is returned.
- * This function establishes missing page table entries.
- */
-int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
-			 unsigned long len, int prot)
-{
-	int rc;
+	if (!pmd_leaf(*pmdp)) {
+		rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, bits);
+		if (!rc)
+			rc = PAGE_SIZE;
+	} else {
+		rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, bits);
+		if (!rc)
+			rc = HPAGE_SIZE;
+	}
+	gmap_pmd_op_end(gmap, pmdp);
 
-	if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap))
-		return -EINVAL;
-	if (!MACHINE_HAS_ESOP && prot == PROT_READ)
-		return -EINVAL;
-	mmap_read_lock(gmap->mm);
-	rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT);
-	mmap_read_unlock(gmap->mm);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(gmap_mprotect_notify);
+EXPORT_SYMBOL_GPL(gmap_protect_one);
 
 /**
  * gmap_read_table - get an unsigned long value from a guest page table using
@@ -1414,7 +1251,6 @@ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr)
 	__gmap_unshadow_pgt(sg, raddr, __va(pgt));
 	/* Free page table */
 	ptdesc = page_ptdesc(phys_to_page(pgt));
-	list_del(&ptdesc->pt_list);
 	page_table_free_pgste(ptdesc);
 }
 
@@ -1442,7 +1278,6 @@ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr,
 		__gmap_unshadow_pgt(sg, raddr, __va(pgt));
 		/* Free page table */
 		ptdesc = page_ptdesc(phys_to_page(pgt));
-		list_del(&ptdesc->pt_list);
 		page_table_free_pgste(ptdesc);
 	}
 }
@@ -1472,7 +1307,6 @@ static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr)
 	__gmap_unshadow_sgt(sg, raddr, __va(sgt));
 	/* Free segment table */
 	page = phys_to_page(sgt);
-	list_del(&page->lru);
 	__free_pages(page, CRST_ALLOC_ORDER);
 }
 
@@ -1500,7 +1334,6 @@ static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr,
 		__gmap_unshadow_sgt(sg, raddr, __va(sgt));
 		/* Free segment table */
 		page = phys_to_page(sgt);
-		list_del(&page->lru);
 		__free_pages(page, CRST_ALLOC_ORDER);
 	}
 }
@@ -1530,7 +1363,6 @@ static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr)
 	__gmap_unshadow_r3t(sg, raddr, __va(r3t));
 	/* Free region 3 table */
 	page = phys_to_page(r3t);
-	list_del(&page->lru);
 	__free_pages(page, CRST_ALLOC_ORDER);
 }
 
@@ -1558,7 +1390,6 @@ static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr,
 		__gmap_unshadow_r3t(sg, raddr, __va(r3t));
 		/* Free region 3 table */
 		page = phys_to_page(r3t);
-		list_del(&page->lru);
 		__free_pages(page, CRST_ALLOC_ORDER);
 	}
 }
@@ -1588,7 +1419,6 @@ static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr)
 	__gmap_unshadow_r2t(sg, raddr, __va(r2t));
 	/* Free region 2 table */
 	page = phys_to_page(r2t);
-	list_del(&page->lru);
 	__free_pages(page, CRST_ALLOC_ORDER);
 }
 
@@ -1620,7 +1450,6 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr,
 		r1t[i] = _REGION1_ENTRY_EMPTY;
 		/* Free region 2 table */
 		page = phys_to_page(r2t);
-		list_del(&page->lru);
 		__free_pages(page, CRST_ALLOC_ORDER);
 	}
 }
@@ -1631,7 +1460,7 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr,
  *
  * Called with sg->guest_table_lock
  */
-static void gmap_unshadow(struct gmap *sg)
+void gmap_unshadow(struct gmap *sg)
 {
 	unsigned long *table;
 
@@ -1657,143 +1486,7 @@ static void gmap_unshadow(struct gmap *sg)
 		break;
 	}
 }
-
-/**
- * gmap_find_shadow - find a specific asce in the list of shadow tables
- * @parent: pointer to the parent gmap
- * @asce: ASCE for which the shadow table is created
- * @edat_level: edat level to be used for the shadow translation
- *
- * Returns the pointer to a gmap if a shadow table with the given asce is
- * already available, ERR_PTR(-EAGAIN) if another one is just being created,
- * otherwise NULL
- */
-static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce,
-				     int edat_level)
-{
-	struct gmap *sg;
-
-	list_for_each_entry(sg, &parent->children, list) {
-		if (sg->orig_asce != asce || sg->edat_level != edat_level ||
-		    sg->removed)
-			continue;
-		if (!sg->initialized)
-			return ERR_PTR(-EAGAIN);
-		refcount_inc(&sg->ref_count);
-		return sg;
-	}
-	return NULL;
-}
-
-/**
- * gmap_shadow_valid - check if a shadow guest address space matches the
- *                     given properties and is still valid
- * @sg: pointer to the shadow guest address space structure
- * @asce: ASCE for which the shadow table is requested
- * @edat_level: edat level to be used for the shadow translation
- *
- * Returns 1 if the gmap shadow is still valid and matches the given
- * properties, the caller can continue using it. Returns 0 otherwise, the
- * caller has to request a new shadow gmap in this case.
- *
- */
-int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
-{
-	if (sg->removed)
-		return 0;
-	return sg->orig_asce == asce && sg->edat_level == edat_level;
-}
-EXPORT_SYMBOL_GPL(gmap_shadow_valid);
-
-/**
- * gmap_shadow - create/find a shadow guest address space
- * @parent: pointer to the parent gmap
- * @asce: ASCE for which the shadow table is created
- * @edat_level: edat level to be used for the shadow translation
- *
- * The pages of the top level page table referred by the asce parameter
- * will be set to read-only and marked in the PGSTEs of the kvm process.
- * The shadow table will be removed automatically on any change to the
- * PTE mapping for the source table.
- *
- * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
- * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
- * parent gmap table could not be protected.
- */
-struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
-			 int edat_level)
-{
-	struct gmap *sg, *new;
-	unsigned long limit;
-	int rc;
-
-	BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
-	BUG_ON(gmap_is_shadow(parent));
-	spin_lock(&parent->shadow_lock);
-	sg = gmap_find_shadow(parent, asce, edat_level);
-	spin_unlock(&parent->shadow_lock);
-	if (sg)
-		return sg;
-	/* Create a new shadow gmap */
-	limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
-	if (asce & _ASCE_REAL_SPACE)
-		limit = -1UL;
-	new = gmap_alloc(limit);
-	if (!new)
-		return ERR_PTR(-ENOMEM);
-	new->mm = parent->mm;
-	new->parent = gmap_get(parent);
-	new->private = parent->private;
-	new->orig_asce = asce;
-	new->edat_level = edat_level;
-	new->initialized = false;
-	spin_lock(&parent->shadow_lock);
-	/* Recheck if another CPU created the same shadow */
-	sg = gmap_find_shadow(parent, asce, edat_level);
-	if (sg) {
-		spin_unlock(&parent->shadow_lock);
-		gmap_free(new);
-		return sg;
-	}
-	if (asce & _ASCE_REAL_SPACE) {
-		/* only allow one real-space gmap shadow */
-		list_for_each_entry(sg, &parent->children, list) {
-			if (sg->orig_asce & _ASCE_REAL_SPACE) {
-				spin_lock(&sg->guest_table_lock);
-				gmap_unshadow(sg);
-				spin_unlock(&sg->guest_table_lock);
-				list_del(&sg->list);
-				gmap_put(sg);
-				break;
-			}
-		}
-	}
-	refcount_set(&new->ref_count, 2);
-	list_add(&new->list, &parent->children);
-	if (asce & _ASCE_REAL_SPACE) {
-		/* nothing to protect, return right away */
-		new->initialized = true;
-		spin_unlock(&parent->shadow_lock);
-		return new;
-	}
-	spin_unlock(&parent->shadow_lock);
-	/* protect after insertion, so it will get properly invalidated */
-	mmap_read_lock(parent->mm);
-	rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
-				((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE,
-				PROT_READ, GMAP_NOTIFY_SHADOW);
-	mmap_read_unlock(parent->mm);
-	spin_lock(&parent->shadow_lock);
-	new->initialized = true;
-	if (rc) {
-		list_del(&new->list);
-		gmap_free(new);
-		new = ERR_PTR(rc);
-	}
-	spin_unlock(&parent->shadow_lock);
-	return new;
-}
-EXPORT_SYMBOL_GPL(gmap_shadow);
+EXPORT_SYMBOL(gmap_unshadow);
 
 /**
  * gmap_shadow_r2t - create an empty shadow region 2 table
@@ -1827,9 +1520,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
 	page = gmap_alloc_crst();
 	if (!page)
 		return -ENOMEM;
-	page->index = r2t & _REGION_ENTRY_ORIGIN;
-	if (fake)
-		page->index |= GMAP_SHADOW_FAKE_TABLE;
 	s_r2t = page_to_phys(page);
 	/* Install shadow region second table */
 	spin_lock(&sg->guest_table_lock);
@@ -1851,7 +1541,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
 		 _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID;
 	if (sg->edat_level >= 1)
 		*table |= (r2t & _REGION_ENTRY_PROTECT);
-	list_add(&page->lru, &sg->crst_list);
 	if (fake) {
 		/* nothing to protect for fake tables */
 		*table &= ~_REGION_ENTRY_INVALID;
@@ -1911,9 +1600,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
 	page = gmap_alloc_crst();
 	if (!page)
 		return -ENOMEM;
-	page->index = r3t & _REGION_ENTRY_ORIGIN;
-	if (fake)
-		page->index |= GMAP_SHADOW_FAKE_TABLE;
 	s_r3t = page_to_phys(page);
 	/* Install shadow region second table */
 	spin_lock(&sg->guest_table_lock);
@@ -1935,7 +1621,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
 		 _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID;
 	if (sg->edat_level >= 1)
 		*table |= (r3t & _REGION_ENTRY_PROTECT);
-	list_add(&page->lru, &sg->crst_list);
 	if (fake) {
 		/* nothing to protect for fake tables */
 		*table &= ~_REGION_ENTRY_INVALID;
@@ -1995,9 +1680,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
 	page = gmap_alloc_crst();
 	if (!page)
 		return -ENOMEM;
-	page->index = sgt & _REGION_ENTRY_ORIGIN;
-	if (fake)
-		page->index |= GMAP_SHADOW_FAKE_TABLE;
 	s_sgt = page_to_phys(page);
 	/* Install shadow region second table */
 	spin_lock(&sg->guest_table_lock);
@@ -2019,7 +1701,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
 		 _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID;
 	if (sg->edat_level >= 1)
 		*table |= sgt & _REGION_ENTRY_PROTECT;
-	list_add(&page->lru, &sg->crst_list);
 	if (fake) {
 		/* nothing to protect for fake tables */
 		*table &= ~_REGION_ENTRY_INVALID;
@@ -2052,45 +1733,22 @@ out_free:
 }
 EXPORT_SYMBOL_GPL(gmap_shadow_sgt);
 
-/**
- * gmap_shadow_pgt_lookup - find a shadow page table
- * @sg: pointer to the shadow guest address space structure
- * @saddr: the address in the shadow aguest address space
- * @pgt: parent gmap address of the page table to get shadowed
- * @dat_protection: if the pgtable is marked as protected by dat
- * @fake: pgt references contiguous guest memory block, not a pgtable
- *
- * Returns 0 if the shadow page table was found and -EAGAIN if the page
- * table was not found.
- *
- * Called with sg->mm->mmap_lock in read.
- */
-int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
-			   unsigned long *pgt, int *dat_protection,
-			   int *fake)
+static void gmap_pgste_set_pgt_addr(struct ptdesc *ptdesc, unsigned long pgt_addr)
 {
-	unsigned long *table;
-	struct page *page;
-	int rc;
+	unsigned long *pgstes = page_to_virt(ptdesc_page(ptdesc));
 
-	BUG_ON(!gmap_is_shadow(sg));
-	spin_lock(&sg->guest_table_lock);
-	table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
-	if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
-		/* Shadow page tables are full pages (pte+pgste) */
-		page = pfn_to_page(*table >> PAGE_SHIFT);
-		*pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE;
-		*dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
-		*fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE);
-		rc = 0;
-	} else  {
-		rc = -EAGAIN;
-	}
-	spin_unlock(&sg->guest_table_lock);
-	return rc;
+	pgstes += _PAGE_ENTRIES;
+
+	pgstes[0] &= ~PGSTE_ST2_MASK;
+	pgstes[1] &= ~PGSTE_ST2_MASK;
+	pgstes[2] &= ~PGSTE_ST2_MASK;
+	pgstes[3] &= ~PGSTE_ST2_MASK;
 
+	pgstes[0] |= (pgt_addr >> 16) & PGSTE_ST2_MASK;
+	pgstes[1] |= pgt_addr & PGSTE_ST2_MASK;
+	pgstes[2] |= (pgt_addr << 16) & PGSTE_ST2_MASK;
+	pgstes[3] |= (pgt_addr << 32) & PGSTE_ST2_MASK;
 }
-EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup);
 
 /**
  * gmap_shadow_pgt - instantiate a shadow page table
@@ -2119,9 +1777,10 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
 	ptdesc = page_table_alloc_pgste(sg->mm);
 	if (!ptdesc)
 		return -ENOMEM;
-	ptdesc->pt_index = pgt & _SEGMENT_ENTRY_ORIGIN;
+	origin = pgt & _SEGMENT_ENTRY_ORIGIN;
 	if (fake)
-		ptdesc->pt_index |= GMAP_SHADOW_FAKE_TABLE;
+		origin |= GMAP_SHADOW_FAKE_TABLE;
+	gmap_pgste_set_pgt_addr(ptdesc, origin);
 	s_pgt = page_to_phys(ptdesc_page(ptdesc));
 	/* Install shadow page table */
 	spin_lock(&sg->guest_table_lock);
@@ -2140,7 +1799,6 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
 	/* mark as invalid as long as the parent table is not protected */
 	*table = (unsigned long) s_pgt | _SEGMENT_ENTRY |
 		 (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID;
-	list_add(&ptdesc->pt_list, &sg->pt_list);
 	if (fake) {
 		/* nothing to protect for fake tables */
 		*table &= ~_SEGMENT_ENTRY_INVALID;
@@ -2318,7 +1976,6 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 		 pte_t *pte, unsigned long bits)
 {
 	unsigned long offset, gaddr = 0;
-	unsigned long *table;
 	struct gmap *gmap, *sg, *next;
 
 	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
@@ -2326,12 +1983,9 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		table = radix_tree_lookup(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (table)
-			gaddr = __gmap_segment_gaddr(table) + offset;
+		gaddr = host_to_guest_lookup(gmap, vmaddr) + offset;
 		spin_unlock(&gmap->guest_table_lock);
-		if (!table)
+		if (!IS_GADDR_VALID(gaddr))
 			continue;
 
 		if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
@@ -2391,10 +2045,8 @@ static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
-						  vmaddr >> PMD_SHIFT);
+		pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
 		if (pmdp) {
-			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
 			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
 						   _SEGMENT_ENTRY_GMAP_UC |
@@ -2438,28 +2090,25 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
  */
 void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *entry, gaddr;
+	unsigned long gaddr;
 	struct gmap *gmap;
 	pmd_t *pmdp;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		entry = radix_tree_delete(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (entry) {
-			pmdp = (pmd_t *)entry;
-			gaddr = __gmap_segment_gaddr(entry);
+		pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+		if (pmdp) {
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
-					   _SEGMENT_ENTRY_GMAP_UC |
-					   _SEGMENT_ENTRY));
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC |
+						   _SEGMENT_ENTRY));
 			if (MACHINE_HAS_TLB_GUEST)
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_LOCAL);
 			else if (MACHINE_HAS_IDTE)
 				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
-			*entry = _SEGMENT_ENTRY_EMPTY;
+			*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 		}
 		spin_unlock(&gmap->guest_table_lock);
 	}
@@ -2474,22 +2123,19 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
  */
 void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *entry, gaddr;
+	unsigned long gaddr;
 	struct gmap *gmap;
 	pmd_t *pmdp;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		entry = radix_tree_delete(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (entry) {
-			pmdp = (pmd_t *)entry;
-			gaddr = __gmap_segment_gaddr(entry);
+		pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+		if (pmdp) {
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
-					   _SEGMENT_ENTRY_GMAP_UC |
-					   _SEGMENT_ENTRY));
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC |
+						   _SEGMENT_ENTRY));
 			if (MACHINE_HAS_TLB_GUEST)
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_GLOBAL);
@@ -2497,7 +2143,7 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
 			else
 				__pmdp_csp(pmdp);
-			*entry = _SEGMENT_ENTRY_EMPTY;
+			*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 		}
 		spin_unlock(&gmap->guest_table_lock);
 	}
@@ -2943,49 +2589,6 @@ int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
 EXPORT_SYMBOL_GPL(__s390_uv_destroy_range);
 
 /**
- * s390_unlist_old_asce - Remove the topmost level of page tables from the
- * list of page tables of the gmap.
- * @gmap: the gmap whose table is to be removed
- *
- * On s390x, KVM keeps a list of all pages containing the page tables of the
- * gmap (the CRST list). This list is used at tear down time to free all
- * pages that are now not needed anymore.
- *
- * This function removes the topmost page of the tree (the one pointed to by
- * the ASCE) from the CRST list.
- *
- * This means that it will not be freed when the VM is torn down, and needs
- * to be handled separately by the caller, unless a leak is actually
- * intended. Notice that this function will only remove the page from the
- * list, the page will still be used as a top level page table (and ASCE).
- */
-void s390_unlist_old_asce(struct gmap *gmap)
-{
-	struct page *old;
-
-	old = virt_to_page(gmap->table);
-	spin_lock(&gmap->guest_table_lock);
-	list_del(&old->lru);
-	/*
-	 * Sometimes the topmost page might need to be "removed" multiple
-	 * times, for example if the VM is rebooted into secure mode several
-	 * times concurrently, or if s390_replace_asce fails after calling
-	 * s390_remove_old_asce and is attempted again later. In that case
-	 * the old asce has been removed from the list, and therefore it
-	 * will not be freed when the VM terminates, but the ASCE is still
-	 * in use and still pointed to.
-	 * A subsequent call to replace_asce will follow the pointer and try
-	 * to remove the same page from the list again.
-	 * Therefore it's necessary that the page of the ASCE has valid
-	 * pointers, so list_del can work (and do nothing) without
-	 * dereferencing stale or invalid pointers.
-	 */
-	INIT_LIST_HEAD(&old->lru);
-	spin_unlock(&gmap->guest_table_lock);
-}
-EXPORT_SYMBOL_GPL(s390_unlist_old_asce);
-
-/**
  * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy
  * @gmap: the gmap whose ASCE needs to be replaced
  *
@@ -3004,8 +2607,6 @@ int s390_replace_asce(struct gmap *gmap)
 	struct page *page;
 	void *table;
 
-	s390_unlist_old_asce(gmap);
-
 	/* Replacing segment type ASCEs would cause serious issues */
 	if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT)
 		return -EINVAL;
@@ -3013,19 +2614,9 @@ int s390_replace_asce(struct gmap *gmap)
 	page = gmap_alloc_crst();
 	if (!page)
 		return -ENOMEM;
-	page->index = 0;
 	table = page_to_virt(page);
 	memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));
 
-	/*
-	 * The caller has to deal with the old ASCE, but here we make sure
-	 * the new one is properly added to the CRST list, so that
-	 * it will be freed when the VM is torn down.
-	 */
-	spin_lock(&gmap->guest_table_lock);
-	list_add(&page->lru, &gmap->crst_list);
-	spin_unlock(&gmap->guest_table_lock);
-
 	/* Set new table origin while preserving existing ASCE control bits */
 	asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table);
 	WRITE_ONCE(gmap->asce, asce);
@@ -3035,3 +2626,31 @@ int s390_replace_asce(struct gmap *gmap)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(s390_replace_asce);
+
+/**
+ * kvm_s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split
+ * @mm:    the mm containing the folio to work on
+ * @folio: the folio
+ * @split: whether to split a large folio
+ *
+ * Context: Must be called while holding an extra reference to the folio;
+ *          the mm lock should not be held.
+ */
+int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split)
+{
+	int rc;
+
+	lockdep_assert_not_held(&mm->mmap_lock);
+	folio_wait_writeback(folio);
+	lru_add_drain_all();
+	if (split) {
+		folio_lock(folio);
+		rc = split_folio(folio);
+		folio_unlock(folio);
+
+		if (rc != -EBUSY)
+			return rc;
+	}
+	return -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(kvm_s390_wiggle_split_folio);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 58696a0c4e4a..30387a6e98ff 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -21,7 +21,7 @@
 int page_table_allocate_pgste = 0;
 EXPORT_SYMBOL(page_table_allocate_pgste);
 
-static struct ctl_table page_table_sysctl[] = {
+static const struct ctl_table page_table_sysctl[] = {
 	{
 		.procname	= "allocate_pgste",
 		.data		= &page_table_allocate_pgste,
@@ -88,12 +88,14 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 		if (unlikely(!p4d))
 			goto err_p4d;
 		crst_table_init(p4d, _REGION2_ENTRY_EMPTY);
+		pagetable_p4d_ctor(virt_to_ptdesc(p4d));
 	}
 	if (end > _REGION1_SIZE) {
 		pgd = crst_table_alloc(mm);
 		if (unlikely(!pgd))
 			goto err_pgd;
 		crst_table_init(pgd, _REGION1_ENTRY_EMPTY);
+		pagetable_pgd_ctor(virt_to_ptdesc(pgd));
 	}
 
 	spin_lock_bh(&mm->page_table_lock);
@@ -130,6 +132,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 	return 0;
 
 err_pgd:
+	pagetable_dtor(virt_to_ptdesc(p4d));
 	crst_table_free(mm, p4d);
 err_p4d:
 	return -ENOMEM;
@@ -173,37 +176,16 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	}
 	table = ptdesc_to_virt(ptdesc);
 	__arch_set_page_dat(table, 1);
-	/* pt_list is used by gmap only */
-	INIT_LIST_HEAD(&ptdesc->pt_list);
 	memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE);
 	memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
 	return table;
 }
 
-static void pagetable_pte_dtor_free(struct ptdesc *ptdesc)
-{
-	pagetable_pte_dtor(ptdesc);
-	pagetable_free(ptdesc);
-}
-
 void page_table_free(struct mm_struct *mm, unsigned long *table)
 {
 	struct ptdesc *ptdesc = virt_to_ptdesc(table);
 
-	pagetable_pte_dtor_free(ptdesc);
-}
-
-void __tlb_remove_table(void *table)
-{
-	struct ptdesc *ptdesc = virt_to_ptdesc(table);
-	struct page *page = ptdesc_page(ptdesc);
-
-	if (compound_order(page) == CRST_ALLOC_ORDER) {
-		/* pmd, pud, or p4d */
-		pagetable_free(ptdesc);
-		return;
-	}
-	pagetable_pte_dtor_free(ptdesc);
+	pagetable_dtor_free(ptdesc);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -211,7 +193,7 @@ static void pte_free_now(struct rcu_head *head)
 {
 	struct ptdesc *ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
 
-	pagetable_pte_dtor_free(ptdesc);
+	pagetable_dtor_free(ptdesc);
 }
 
 void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 7c684c54e721..8ead999e340b 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -662,7 +662,7 @@ void __init vmem_map_init(void)
 	if (!static_key_enabled(&cpu_has_bear))
 		set_memory_x(0, 1);
 	if (debug_pagealloc_enabled())
-		__set_memory_4k(__va(0), __va(0) + ident_map_size);
+		__set_memory_4k(__va(0), absolute_pointer(__va(0)) + ident_map_size);
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);
 }
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index d5ace00d10f0..857afbc4828f 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -171,7 +171,6 @@ void zpci_bus_scan_busses(void)
 static bool zpci_bus_is_multifunction_root(struct zpci_dev *zdev)
 {
 	return !s390_pci_no_rid && zdev->rid_available &&
-		zpci_is_device_configured(zdev) &&
 		!zdev->vfn;
 }
 
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 24eccaa29337..bdcf2a3b6c41 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -13,7 +13,7 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
+KBUILD_CFLAGS := -std=gnu11 -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c
index a1bc02b29c81..7d76c417f83f 100644
--- a/arch/s390/tools/gen_opcode_table.c
+++ b/arch/s390/tools/gen_opcode_table.c
@@ -201,6 +201,17 @@ static int cmp_long_insn(const void *a, const void *b)
 	return strcmp(((struct insn *)a)->name, ((struct insn *)b)->name);
 }
 
+static void print_insn_name(const char *name)
+{
+	size_t i, len;
+
+	len = strlen(name);
+	printf("{");
+	for (i = 0; i < len; i++)
+		printf(" \'%c\',", name[i]);
+	printf(" }");
+}
+
 static void print_long_insn(struct gen_opcode *desc)
 {
 	struct insn *insn;
@@ -223,7 +234,9 @@ static void print_long_insn(struct gen_opcode *desc)
 		insn = &desc->insn[i];
 		if (insn->name_len < 6)
 			continue;
-		printf("\t[LONG_INSN_%s] = \"%s\", \\\n", insn->upper, insn->name);
+		printf("\t[LONG_INSN_%s] = ", insn->upper);
+		print_insn_name(insn->name);
+		printf(", \\\n");
 	}
 	printf("}\n\n");
 }
@@ -236,11 +249,13 @@ static void print_opcode(struct insn *insn, int nr)
 	if (insn->type->byte != 0)
 		opcode += 2;
 	printf("\t[%4d] = { .opfrag = 0x%s, .format = INSTR_%s, ", nr, opcode, insn->format);
-	if (insn->name_len < 6)
-		printf(".name = \"%s\" ", insn->name);
-	else
-		printf(".offset = LONG_INSN_%s ", insn->upper);
-	printf("}, \\\n");
+	if (insn->name_len < 6) {
+		printf(".name =  ");
+		print_insn_name(insn->name);
+	} else {
+		printf(".offset = LONG_INSN_%s", insn->upper);
+	}
+	printf(" }, \\\n");
 }
 
 static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset)
diff --git a/arch/sh/Kbuild b/arch/sh/Kbuild
index 056efec72c2a..0da6c6d6821a 100644
--- a/arch/sh/Kbuild
+++ b/arch/sh/Kbuild
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y				+= kernel/ mm/ boards/
 obj-$(CONFIG_SH_FPU_EMU)	+= math-emu/
-obj-$(CONFIG_USE_BUILTIN_DTB)	+= boot/dts/
 
 obj-$(CONFIG_HD6446X_SERIES)	+= cchips/hd6446x/
 
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 04ff5fb9242e..89185af7bcc9 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -648,10 +648,11 @@ endmenu
 
 menu "Boot options"
 
-config USE_BUILTIN_DTB
+config BUILTIN_DTB
 	bool "Use builtin DTB"
 	default n
 	depends on SH_DEVICE_TREE
+	select GENERIC_BUILTIN_DTB
 	help
 	  Link a device tree blob for particular hardware into the kernel,
 	  suppressing use of the DTB pointer provided by the bootloader.
@@ -659,10 +660,10 @@ config USE_BUILTIN_DTB
 	  not capable of providing a DTB to the kernel, or for experimental
 	  hardware without stable device tree bindings.
 
-config BUILTIN_DTB_SOURCE
+config BUILTIN_DTB_NAME
 	string "Source file for builtin DTB"
 	default ""
-	depends on USE_BUILTIN_DTB
+	depends on BUILTIN_DTB
 	help
 	  Base name (without suffix, relative to arch/sh/boot/dts) for the
 	  a DTS file that will be used to produce the DTB linked into the
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index 109bec4dad94..1af93be61b1f 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -80,8 +80,8 @@ config SH_7724_SOLUTION_ENGINE
 	select SOLUTION_ENGINE
 	depends on CPU_SUBTYPE_SH7724
 	select GPIOLIB
-	select SND_SOC_AK4642 if SND_SIMPLE_CARD
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	imply SND_SOC_AK4642 if SND_SIMPLE_CARD
 	help
 	  Select 7724 SolutionEngine if configuring for a Hitachi SH7724
 	  evaluation board.
@@ -259,8 +259,8 @@ config SH_ECOVEC
 	bool "EcoVec"
 	depends on CPU_SUBTYPE_SH7724
 	select GPIOLIB
-	select SND_SOC_DA7210 if SND_SIMPLE_CARD
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	imply SND_SOC_DA7210 if SND_SIMPLE_CARD
 	help
 	  Renesas "R0P7724LC0011/21RL (EcoVec)" support.
 
diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile
index 4a6dec9714a9..d109978a5eb9 100644
--- a/arch/sh/boot/dts/Makefile
+++ b/arch/sh/boot/dts/Makefile
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_USE_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE))
+obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME))
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 5d8577ab1591..96d938fdf224 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 do {								\
-	pagetable_pte_dtor(page_ptdesc(pte));			\
+	pagetable_dtor(page_ptdesc(pte));			\
 	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
 } while (0)
 
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 4e6835de54cf..9022d8af9d68 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -43,9 +43,9 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	int j;
 
-	seq_printf(p, "%*s: ", prec, "NMI");
+	seq_printf(p, "%*s:", prec, "NMI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", per_cpu(irq_stat.__nmi_count, j));
+		seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat.__nmi_count, j), 10);
 	seq_printf(p, "  Non-maskable interrupts\n");
 
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index f2b6f16a46b8..039a51291002 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -249,7 +249,7 @@ void __ref sh_fdt_init(phys_addr_t dt_phys)
 	/* Avoid calling an __init function on secondary cpus. */
 	if (done) return;
 
-#ifdef CONFIG_USE_BUILTIN_DTB
+#ifdef CONFIG_BUILTIN_DTB
 	dt_virt = __dtb_start;
 #else
 	dt_virt = phys_to_virt(dt_phys);
@@ -323,7 +323,7 @@ void __init setup_arch(char **cmdline_p)
 	sh_early_platform_driver_probe("earlyprintk", 1, 1);
 
 #ifdef CONFIG_OF_EARLY_FLATTREE
-#ifdef CONFIG_USE_BUILTIN_DTB
+#ifdef CONFIG_BUILTIN_DTB
 	unflatten_and_copy_device_tree();
 #else
 	unflatten_device_tree();
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 2a88b0c9e70f..289a2fecebef 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -137,10 +137,7 @@ static pmd_t * __init one_md_table_init(pud_t *pud)
 	if (pud_none(*pud)) {
 		pmd_t *pmd;
 
-		pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pmd)
-			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-			      __func__, PAGE_SIZE, PAGE_SIZE);
+		pmd = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 		pud_populate(&init_mm, pud, pmd);
 		BUG_ON(pmd != pmd_offset(pud, 0));
 	}
@@ -153,10 +150,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	if (pmd_none(*pmd)) {
 		pte_t *pte;
 
-		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-		if (!pte)
-			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-			      __func__, PAGE_SIZE, PAGE_SIZE);
+		pte = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 		pmd_populate_kernel(&init_mm, pmd, pte);
 		BUG_ON(pte != pte_offset_kernel(pmd, 0));
 	}
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 3037187482db..1a6e694418e3 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -33,6 +33,7 @@ void flush_tlb_pending(void);
 #define tlb_needs_table_invalidate()	(false)
 #endif
 
+#define __HAVE_ARCH_TLB_REMOVE_TABLE
 #include <asm-generic/tlb.h>
 
 #endif /* _SPARC64_TLB_H */
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index 8605dd710f3c..5210991429d5 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -199,18 +199,18 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	int j;
 
 #ifdef CONFIG_SMP
-	seq_printf(p, "RES: ");
+	seq_printf(p, "RES:");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", cpu_data(j).irq_resched_count);
+		seq_put_decimal_ull_width(p, " ", cpu_data(j).irq_resched_count, 10);
 	seq_printf(p, "     IPI rescheduling interrupts\n");
-	seq_printf(p, "CAL: ");
+	seq_printf(p, "CAL:");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", cpu_data(j).irq_call_count);
+		seq_put_decimal_ull_width(p, " ", cpu_data(j).irq_call_count, 10);
 	seq_printf(p, "     IPI function call interrupts\n");
 #endif
-	seq_printf(p, "NMI: ");
+	seq_printf(p, "NMI:");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", cpu_data(j).counter);
+		seq_put_decimal_ull_width(p, " ", cpu_data(j).counter, 10);
 	seq_printf(p, "     Non-maskable interrupts\n");
 	return 0;
 }
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 01ee800efde3..ded463c82abd 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -22,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/ftrace.h>
 #include <linux/irq.h>
+#include <linux/string_choices.h>
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
@@ -145,9 +146,7 @@ static int hv_irq_version;
  */
 static bool sun4v_cookie_only_virqs(void)
 {
-	if (hv_irq_version >= 3)
-		return true;
-	return false;
+	return hv_irq_version >= 3;
 }
 
 static void __init irq_init_hv(void)
@@ -170,7 +169,7 @@ static void __init irq_init_hv(void)
 
 	pr_info("SUN4V: Using IRQ API major %d, cookie only virqs %s\n",
 		hv_irq_version,
-		sun4v_cookie_only_virqs() ? "enabled" : "disabled");
+		str_enabled_disabled(sun4v_cookie_only_virqs()));
 }
 
 /* This function is for the timer interrupt.*/
@@ -304,9 +303,9 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	int j;
 
-	seq_printf(p, "NMI: ");
+	seq_printf(p, "NMI:");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", cpu_data(j).__nmi_count);
+		seq_put_decimal_ull_width(p, " ", cpu_data(j).__nmi_count, 10);
 	seq_printf(p, "     Non-maskable interrupts\n");
 	return 0;
 }
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 50a0927a84a6..ddac216a2aff 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -932,7 +932,7 @@ static void pci_bus_slot_names(struct device_node *node, struct pci_bus *bus)
 {
 	const struct pci_slot_names {
 		u32	slot_mask;
-		char	names[0];
+		char	names[];
 	} *prop;
 	const char *sp;
 	int len, i;
diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c
index 3df960c137f7..a67dd67f10c8 100644
--- a/arch/sparc/kernel/prom_32.c
+++ b/arch/sparc/kernel/prom_32.c
@@ -28,9 +28,7 @@ void * __init prom_early_alloc(unsigned long size)
 {
 	void *ret;
 
-	ret = memblock_alloc(size, SMP_CACHE_BYTES);
-	if (!ret)
-		panic("%s: Failed to allocate %lu bytes\n", __func__, size);
+	ret = memblock_alloc_or_panic(size, SMP_CACHE_BYTES);
 
 	prom_early_allocated += size;
 
diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c
index 07933d75ac81..1a1a9d6b8f2e 100644
--- a/arch/sparc/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
@@ -419,13 +419,13 @@ struct vio_remove_node_data {
 	u64 node;
 };
 
-static int vio_md_node_match(struct device *dev, void *arg)
+static int vio_md_node_match(struct device *dev, const void *arg)
 {
 	struct vio_dev *vdev = to_vio_dev(dev);
-	struct vio_remove_node_data *node_data;
+	const struct vio_remove_node_data *node_data;
 	u64 node;
 
-	node_data = (struct vio_remove_node_data *)arg;
+	node_data = (const struct vio_remove_node_data *)arg;
 
 	node = vio_vdev_node(node_data->hp, vdev);
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 21f8cbbd0581..05882bca5b73 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2915,7 +2915,7 @@ static void __pte_free(pgtable_t pte)
 {
 	struct ptdesc *ptdesc = virt_to_ptdesc(pte);
 
-	pagetable_pte_dtor(ptdesc);
+	pagetable_dtor(ptdesc);
 	pagetable_free(ptdesc);
 }
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 9df51a62333d..dd32711022f5 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -277,19 +277,13 @@ static void __init srmmu_nocache_init(void)
 
 	bitmap_bits = srmmu_nocache_size >> SRMMU_NOCACHE_BITMAP_SHIFT;
 
-	srmmu_nocache_pool = memblock_alloc(srmmu_nocache_size,
+	srmmu_nocache_pool = memblock_alloc_or_panic(srmmu_nocache_size,
 					    SRMMU_NOCACHE_ALIGN_MAX);
-	if (!srmmu_nocache_pool)
-		panic("%s: Failed to allocate %lu bytes align=0x%x\n",
-		      __func__, srmmu_nocache_size, SRMMU_NOCACHE_ALIGN_MAX);
 	memset(srmmu_nocache_pool, 0, srmmu_nocache_size);
 
 	srmmu_nocache_bitmap =
-		memblock_alloc(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
+		memblock_alloc_or_panic(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
 			       SMP_CACHE_BYTES);
-	if (!srmmu_nocache_bitmap)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      BITS_TO_LONGS(bitmap_bits) * sizeof(long));
 	bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits);
 
 	srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
@@ -372,7 +366,7 @@ void pte_free(struct mm_struct *mm, pgtable_t ptep)
 	page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
 	spin_lock(&mm->page_table_lock);
 	if (page_ref_dec_return(page) == 1)
-		pagetable_pte_dtor(page_ptdesc(page));
+		pagetable_dtor(page_ptdesc(page));
 	spin_unlock(&mm->page_table_lock);
 
 	srmmu_free_nocache(ptep, SRMMU_PTE_TABLE_SIZE);
@@ -452,9 +446,7 @@ static void __init sparc_context_init(int numctx)
 	unsigned long size;
 
 	size = numctx * sizeof(struct ctx_list);
-	ctx_list_pool = memblock_alloc(size, SMP_CACHE_BYTES);
-	if (!ctx_list_pool)
-		panic("%s: Failed to allocate %lu bytes\n", __func__, size);
+	ctx_list_pool = memblock_alloc_or_panic(size, SMP_CACHE_BYTES);
 
 	for (ctx = 0; ctx < numctx; ctx++) {
 		struct ctx_list *clist;
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 75d04fb4994a..d5a9c5aabaec 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -636,10 +636,7 @@ static int __init eth_setup(char *str)
 		return 1;
 	}
 
-	new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES);
-	if (!new)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*new));
+	new = memblock_alloc_or_panic(sizeof(*new), SMP_CACHE_BYTES);
 
 	INIT_LIST_HEAD(&new->list);
 	new->index = n;
diff --git a/arch/um/drivers/rtc_kern.c b/arch/um/drivers/rtc_kern.c
index 134a58f93c85..9158c936c128 100644
--- a/arch/um/drivers/rtc_kern.c
+++ b/arch/um/drivers/rtc_kern.c
@@ -51,6 +51,7 @@ static int uml_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 {
+	struct timespec64 ts;
 	unsigned long long secs;
 
 	if (!enable && !uml_rtc_alarm_enabled)
@@ -58,7 +59,8 @@ static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 
 	uml_rtc_alarm_enabled = enable;
 
-	secs = uml_rtc_alarm_time - ktime_get_real_seconds();
+	read_persistent_clock64(&ts);
+	secs = uml_rtc_alarm_time - ts.tv_sec;
 
 	if (time_travel_mode == TT_MODE_OFF) {
 		if (!enable) {
@@ -73,7 +75,8 @@ static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
 
 		if (enable)
 			time_travel_add_event_rel(&uml_rtc_alarm_event,
-						  secs * NSEC_PER_SEC);
+						  secs * NSEC_PER_SEC -
+						  ts.tv_nsec);
 	}
 
 	return 0;
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index 64c09db392c1..85b129e2b70b 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1694,10 +1694,7 @@ static int __init vector_setup(char *str)
 				 str, error);
 		return 1;
 	}
-	new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES);
-	if (!new)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*new));
+	new = memblock_alloc_or_panic(sizeof(*new), SMP_CACHE_BYTES);
 	INIT_LIST_HEAD(&new->list);
 	new->unit = n;
 	new->arguments = str;
diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h
deleted file mode 100644
index 2efac5827188..000000000000
--- a/arch/um/include/asm/fixmap.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_FIXMAP_H
-#define __UM_FIXMAP_H
-
-#include <asm/processor.h>
-#include <asm/archparam.h>
-#include <asm/page.h>
-#include <linux/threads.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process. We allocate these special  addresses
- * from the end of virtual memory (0xfffff000) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-
-/*
- * on UP currently we will have no trace of the fixmap mechanizm,
- * no page table allocations, etc. This might change in the
- * future, say framebuffers for the console driver(s) could be
- * fix-mapped?
- */
-enum fixed_addresses {
-	__end_of_fixed_addresses
-};
-
-extern void __set_fixmap (enum fixed_addresses idx,
-			  unsigned long phys, pgprot_t flags);
-
-/*
- * used by vmalloc.c.
- *
- * Leave one empty page between vmalloc'ed areas and
- * the start of the fixmap, and leave one page empty
- * at the top of mem..
- */
-
-#define FIXADDR_TOP	(TASK_SIZE - 2 * PAGE_SIZE)
-#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
-
-#include <asm-generic/fixmap.h>
-
-#endif
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
index 04fb4e6969a4..f0af23c3aeb2 100644
--- a/arch/um/include/asm/pgalloc.h
+++ b/arch/um/include/asm/pgalloc.h
@@ -27,7 +27,7 @@ extern pgd_t *pgd_alloc(struct mm_struct *);
 
 #define __pte_free_tlb(tlb, pte, address)			\
 do {								\
-	pagetable_pte_dtor(page_ptdesc(pte));			\
+	pagetable_dtor(page_ptdesc(pte));			\
 	tlb_remove_page_ptdesc((tlb), (page_ptdesc(pte)));	\
 } while (0)
 
@@ -35,7 +35,7 @@ do {								\
 
 #define __pmd_free_tlb(tlb, pmd, address)			\
 do {								\
-	pagetable_pmd_dtor(virt_to_ptdesc(pmd));			\
+	pagetable_dtor(virt_to_ptdesc(pmd));			\
 	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd));	\
 } while (0)
 
@@ -43,7 +43,7 @@ do {								\
 
 #define __pud_free_tlb(tlb, pud, address)			\
 do {								\
-	pagetable_pud_dtor(virt_to_ptdesc(pud));		\
+	pagetable_dtor(virt_to_ptdesc(pud));		\
 	tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud));	\
 } while (0)
 
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index 0bd60afcc37d..5601ca98e8a6 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -8,7 +8,8 @@
 #ifndef __UM_PGTABLE_H
 #define __UM_PGTABLE_H
 
-#include <asm/fixmap.h>
+#include <asm/page.h>
+#include <linux/mm_types.h>
 
 #define _PAGE_PRESENT	0x001
 #define _PAGE_NEEDSYNC	0x002
@@ -48,11 +49,9 @@ extern unsigned long end_iomem;
 
 #define VMALLOC_OFFSET	(__va_space)
 #define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
-#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK)
-#define VMALLOC_END	(FIXADDR_START-2*PAGE_SIZE)
+#define VMALLOC_END	(TASK_SIZE-2*PAGE_SIZE)
 #define MODULES_VADDR	VMALLOC_START
 #define MODULES_END	VMALLOC_END
-#define MODULES_LEN	(MODULES_VADDR - MODULES_END)
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
diff --git a/arch/um/kernel/load_file.c b/arch/um/kernel/load_file.c
index 5cecd0e291fb..cb9d178ab7d8 100644
--- a/arch/um/kernel/load_file.c
+++ b/arch/um/kernel/load_file.c
@@ -48,9 +48,7 @@ void *uml_load_file(const char *filename, unsigned long long *size)
 		return NULL;
 	}
 
-	area = memblock_alloc(*size, SMP_CACHE_BYTES);
-	if (!area)
-		panic("%s: Failed to allocate %llu bytes\n", __func__, *size);
+	area = memblock_alloc_or_panic(*size, SMP_CACHE_BYTES);
 
 	if (__uml_load_file(filename, area, *size)) {
 		memblock_free(area, *size);
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 53248ed04771..befed230aac2 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
-#include <asm/fixmap.h>
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 #include <as-layout.h>
@@ -74,6 +73,7 @@ void __init mem_init(void)
 	kmalloc_ok = 1;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA)
 /*
  * Create a page table and place a pointer to it in a middle page
  * directory entry.
@@ -152,7 +152,6 @@ static void __init fixrange_init(unsigned long start, unsigned long end,
 
 static void __init fixaddr_user_init( void)
 {
-#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
 	long size = FIXADDR_USER_END - FIXADDR_USER_START;
 	pte_t *pte;
 	phys_t p;
@@ -174,13 +173,12 @@ static void __init fixaddr_user_init( void)
 		pte = virt_to_kpte(vaddr);
 		pte_set_val(*pte, p, PAGE_READONLY);
 	}
-#endif
 }
+#endif
 
 void __init paging_init(void)
 {
 	unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
-	unsigned long vaddr;
 
 	empty_zero_page = (unsigned long *) memblock_alloc_low(PAGE_SIZE,
 							       PAGE_SIZE);
@@ -191,14 +189,9 @@ void __init paging_init(void)
 	max_zone_pfn[ZONE_NORMAL] = end_iomem >> PAGE_SHIFT;
 	free_area_init(max_zone_pfn);
 
-	/*
-	 * Fixed mappings, only the page table structure has to be
-	 * created - mappings will be set by set_fixmap():
-	 */
-	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
-	fixrange_init(vaddr, FIXADDR_TOP, swapper_pg_dir);
-
+#if IS_ENABLED(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA)
 	fixaddr_user_init();
+#endif
 }
 
 /*
@@ -214,14 +207,13 @@ void free_initmem(void)
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
+	pgd_t *pgd = __pgd_alloc(mm, 0);
 
-	if (pgd) {
-		memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
+	if (pgd)
 		memcpy(pgd + USER_PTRS_PER_PGD,
 		       swapper_pg_dir + USER_PTRS_PER_PGD,
 		       (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
-	}
+
 	return pgd;
 }
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 30bdc0a87dc8..e5a2d4d897e0 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -213,14 +213,6 @@ int __uml_cant_sleep(void) {
 	/* Is in_interrupt() really needed? */
 }
 
-int user_context(unsigned long sp)
-{
-	unsigned long stack;
-
-	stack = sp & (PAGE_MASK << CONFIG_KERNEL_STACK_ORDER);
-	return stack != (unsigned long) current_thread_info();
-}
-
 extern exitcall_t __uml_exitcall_begin, __uml_exitcall_end;
 
 void do_uml_exitcalls(void)
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 8037a967225d..79ea97d4797e 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -264,7 +264,7 @@ EXPORT_SYMBOL(end_iomem);
 
 #define MIN_VMALLOC (32 * 1024 * 1024)
 
-static void parse_host_cpu_flags(char *line)
+static void __init parse_host_cpu_flags(char *line)
 {
 	int i;
 	for (i = 0; i < 32*NCAPINTS; i++) {
@@ -272,7 +272,8 @@ static void parse_host_cpu_flags(char *line)
 			set_cpu_cap(&boot_cpu_data, i);
 	}
 }
-static void parse_cache_line(char *line)
+
+static void __init parse_cache_line(char *line)
 {
 	long res;
 	char *to_parse = strstr(line, ":");
@@ -288,7 +289,7 @@ static void parse_cache_line(char *line)
 	}
 }
 
-static unsigned long get_top_address(char **envp)
+static unsigned long __init get_top_address(char **envp)
 {
 	unsigned long top_addr = (unsigned long) &top_addr;
 	int i;
@@ -376,9 +377,8 @@ int __init linux_main(int argc, char **argv, char **envp)
 	iomem_size = (iomem_size + PAGE_SIZE - 1) & PAGE_MASK;
 
 	max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC;
-
-	if (physmem_size + iomem_size > max_physmem) {
-		physmem_size = max_physmem - iomem_size;
+	if (physmem_size > max_physmem) {
+		physmem_size = max_physmem;
 		os_info("Physical memory size shrunk to %llu bytes\n",
 			physmem_size);
 	}
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index 0afcdeb8995b..3c63ce19e3bf 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -19,13 +19,11 @@
 #include <um_malloc.h>
 #include "internal.h"
 
-#define PGD_BOUND (4 * 1024 * 1024)
 #define STACKSIZE (8 * 1024 * 1024)
-#define THREAD_NAME_LEN (256)
 
 long elf_aux_hwcap;
 
-static void set_stklim(void)
+static void __init set_stklim(void)
 {
 	struct rlimit lim;
 
@@ -48,7 +46,7 @@ static void last_ditch_exit(int sig)
 	exit(1);
 }
 
-static void install_fatal_handler(int sig)
+static void __init install_fatal_handler(int sig)
 {
 	struct sigaction action;
 
@@ -73,7 +71,7 @@ static void install_fatal_handler(int sig)
 
 #define UML_LIB_PATH	":" OS_LIB_PATH "/uml"
 
-static void setup_env_path(void)
+static void __init setup_env_path(void)
 {
 	char *new_path = NULL;
 	char *old_path = NULL;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9bf9620d8f22..be2c311f5118 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -325,6 +325,7 @@ config X86
 	select FUNCTION_ALIGNMENT_4B
 	imply IMA_SECURE_AND_OR_TRUSTED_BOOT    if EFI
 	select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
+	select ARCH_SUPPORTS_PT_RECLAIM		if X86_64
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -2598,7 +2599,8 @@ config MITIGATION_IBPB_ENTRY
 	depends on CPU_SUP_AMD && X86_64
 	default y
 	help
-	  Compile the kernel with support for the retbleed=ibpb mitigation.
+	  Compile the kernel with support for the retbleed=ibpb and
+	  spec_rstack_overflow={ibpb,ibpb-vmexit} mitigations.
 
 config MITIGATION_IBRS_ENTRY
 	bool "Enable IBRS on kernel entry"
diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink
index fef2e977cc7d..8b8a68162c94 100644
--- a/arch/x86/Makefile.postlink
+++ b/arch/x86/Makefile.postlink
@@ -11,6 +11,7 @@ __archpost:
 
 -include include/config/auto.conf
 include $(srctree)/scripts/Kbuild.include
+include $(srctree)/scripts/Makefile.lib
 
 CMD_RELOCS = arch/x86/tools/relocs
 OUT_RELOCS = arch/x86/boot/compressed
@@ -20,11 +21,6 @@ quiet_cmd_relocs = RELOCS  $(OUT_RELOCS)/$@.relocs
 	$(CMD_RELOCS) $@ > $(OUT_RELOCS)/$@.relocs; \
 	$(CMD_RELOCS) --abs-relocs $@
 
-quiet_cmd_strip_relocs = RSTRIP  $@
-      cmd_strip_relocs = \
-	$(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \
-		   --remove-section='.rela.*' --remove-section='.rela__*' $@
-
 # `@true` prevents complaint when there is nothing to be done
 
 vmlinux: FORCE
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index f2051644de94..606c74f27459 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -25,6 +25,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 # avoid errors with '-march=i386', and future flags may depend on the target to
 # be valid.
 KBUILD_CFLAGS := -m$(BITS) -O2 $(CLANG_FLAGS)
+KBUILD_CFLAGS += -std=gnu11
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE
 KBUILD_CFLAGS += -Wundef
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
index 08de37559307..dcb06dc8b5ae 100644
--- a/arch/x86/coco/sev/Makefile
+++ b/arch/x86/coco/sev/Makefile
@@ -2,6 +2,10 @@
 
 obj-y += core.o
 
+# jump tables are emitted using absolute references in non-PIC code
+# so they cannot be used in the early SEV startup code
+CFLAGS_core.o += -fno-jump-tables
+
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_core.o = -pg
 endif
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 4dbdb9561019..82492efc5d94 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -1630,9 +1630,7 @@ static void __init alloc_runtime_data(int cpu)
 		struct svsm_ca *caa;
 
 		/* Allocate the SVSM CA page if an SVSM is present */
-		caa = memblock_alloc(sizeof(*caa), PAGE_SIZE);
-		if (!caa)
-			panic("Can't allocate SVSM CA page\n");
+		caa = memblock_alloc_or_panic(sizeof(*caa), PAGE_SIZE);
 
 		per_cpu(svsm_caa, cpu) = caa;
 		per_cpu(svsm_caa_pa, cpu) = __pa(caa);
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 76e4e74f35b5..f6d2d8aba643 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -57,7 +57,7 @@ __setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 /* Register vsyscall32 into the ABI table */
 #include <linux/sysctl.h>
 
-static struct ctl_table abi_table2[] = {
+static const struct ctl_table abi_table2[] = {
 	{
 		.procname	= "vsyscall32",
 		.data		= &vdso32_enabled,
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index ab9f3dd87c80..ab0c78855ecb 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -84,7 +84,6 @@ extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
 extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
 			       unsigned char sec);
 extern int hpet_set_periodic_freq(unsigned long freq);
-extern int hpet_rtc_dropped_irq(void);
 extern int hpet_rtc_timer_init(void);
 extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
 extern int hpet_register_irq_handler(rtc_irq_handler handler);
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index ce4677b8b735..3b496cdcb74b 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -37,6 +37,8 @@ typedef struct {
 	 */
 	atomic64_t tlb_gen;
 
+	unsigned long next_trim_cpumask;
+
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct rw_semaphore	ldt_usr_sem;
 	struct ldt_struct	*ldt;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 2886cb668d7f..795fdd53bd0a 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -151,6 +151,7 @@ static inline int init_new_context(struct task_struct *tsk,
 
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
+	mm->context.next_trim_cpumask = jiffies + HZ;
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dcd836b59beb..dd4841231bb9 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -147,24 +147,6 @@ static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4
 	set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d)));
 }
 
-static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	gfp_t gfp = GFP_KERNEL_ACCOUNT;
-
-	if (mm == &init_mm)
-		gfp &= ~__GFP_ACCOUNT;
-	return (p4d_t *)get_zeroed_page(gfp);
-}
-
-static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
-{
-	if (!pgtable_l5_enabled())
-		return;
-
-	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
-	free_page((unsigned long)p4d);
-}
-
 extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d);
 
 static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 4d3c9d00d6b6..77f52bc1578a 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -20,22 +20,9 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 	flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables);
 }
 
-/*
- * While x86 architecture in general requires an IPI to perform TLB
- * shootdown, enablement code for several hypervisors overrides
- * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing
- * a hypercall. To keep software pagetable walkers safe in this case we
- * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment
- * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
- * for more details.
- */
-static inline void __tlb_remove_table(void *table)
-{
-	free_page_and_swap_cache(table);
-}
-
 static inline void invlpg(unsigned long addr)
 {
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 }
+
 #endif /* _ASM_X86_TLB_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 69e79fff41b8..02fc2aa06e9e 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -222,6 +222,7 @@ struct flush_tlb_info {
 	unsigned int		initiating_cpu;
 	u8			stride_shift;
 	u8			freed_tables;
+	u8			trim_cpumask;
 };
 
 void flush_tlb_local(void);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3a44a9dc3fb7..dae6a73be40e 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -227,6 +227,28 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end)
 }
 
 static int __init
+acpi_check_lapic(union acpi_subtable_headers *header, const unsigned long end)
+{
+	struct acpi_madt_local_apic *processor = NULL;
+
+	processor = (struct acpi_madt_local_apic *)header;
+
+	if (BAD_MADT_ENTRY(processor, end))
+		return -EINVAL;
+
+	/* Ignore invalid ID */
+	if (processor->id == 0xff)
+		return 0;
+
+	/* Ignore processors that can not be onlined */
+	if (!acpi_is_processor_usable(processor->lapic_flags))
+		return 0;
+
+	has_lapic_cpus = true;
+	return 0;
+}
+
+static int __init
 acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 {
 	struct acpi_madt_local_apic *processor = NULL;
@@ -257,7 +279,6 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end)
 			       processor->processor_id, /* ACPI ID */
 			       processor->lapic_flags & ACPI_MADT_ENABLED);
 
-	has_lapic_cpus = true;
 	return 0;
 }
 
@@ -911,11 +932,8 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
 	 * the resource tree during the lateinit timeframe.
 	 */
 #define HPET_RESOURCE_NAME_SIZE 9
-	hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE,
+	hpet_res = memblock_alloc_or_panic(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE,
 				  SMP_CACHE_BYTES);
-	if (!hpet_res)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE);
 
 	hpet_res->name = (void *)&hpet_res[1];
 	hpet_res->flags = IORESOURCE_MEM;
@@ -1029,6 +1047,8 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void)
 static int __init acpi_parse_madt_lapic_entries(void)
 {
 	int count, x2count = 0;
+	struct acpi_subtable_proc madt_proc[2];
+	int ret;
 
 	if (!boot_cpu_has(X86_FEATURE_APIC))
 		return -ENODEV;
@@ -1037,10 +1057,27 @@ static int __init acpi_parse_madt_lapic_entries(void)
 				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
 	if (!count) {
-		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
-					acpi_parse_lapic, MAX_LOCAL_APIC);
-		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
-					acpi_parse_x2apic, MAX_LOCAL_APIC);
+		/* Check if there are valid LAPIC entries */
+		acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_check_lapic, MAX_LOCAL_APIC);
+
+		/*
+		 * Enumerate the APIC IDs in the order that they appear in the
+		 * MADT, no matter LAPIC entry or x2APIC entry is used.
+		 */
+		memset(madt_proc, 0, sizeof(madt_proc));
+		madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC;
+		madt_proc[0].handler = acpi_parse_lapic;
+		madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC;
+		madt_proc[1].handler = acpi_parse_x2apic;
+		ret = acpi_table_parse_entries_array(ACPI_SIG_MADT,
+				sizeof(struct acpi_table_madt),
+				madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC);
+		if (ret < 0) {
+			pr_err("Error parsing LAPIC/X2APIC entries\n");
+			return ret;
+		}
+		count = madt_proc[0].count;
+		x2count = madt_proc[1].count;
 	}
 	if (!count && !x2count) {
 		pr_err("No LAPIC entries present\n");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 243843e44e89..c71b575bf229 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1854,11 +1854,18 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
 	return temp_state;
 }
 
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
 static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
 {
 	lockdep_assert_irqs_disabled();
+
 	switch_mm_irqs_off(NULL, prev_state.mm, current);
 
+	/* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
+	cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm));
+
 	/*
 	 * Restore the breakpoints if they were disabled before the temporary mm
 	 * was loaded.
@@ -1867,9 +1874,6 @@ static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
 		hw_breakpoint_restore();
 }
 
-__ro_after_init struct mm_struct *poking_mm;
-__ro_after_init unsigned long poking_addr;
-
 static void text_poke_memcpy(void *dst, const void *src, size_t len)
 {
 	memcpy(dst, src, len);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 17af7ced2c73..eebc360ed1bb 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2503,9 +2503,7 @@ static struct resource * __init ioapic_setup_resources(void)
 	n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
 	n *= nr_ioapics;
 
-	mem = memblock_alloc(n, SMP_CACHE_BYTES);
-	if (!mem)
-		panic("%s: Failed to allocate %lu bytes\n", __func__, n);
+	mem = memblock_alloc_or_panic(n, SMP_CACHE_BYTES);
 	res = (void *)mem;
 
 	mem += sizeof(struct resource) * nr_ioapics;
@@ -2564,11 +2562,8 @@ void __init io_apic_init_mappings(void)
 #ifdef CONFIG_X86_32
 fake_ioapic_page:
 #endif
-			ioapic_phys = (unsigned long)memblock_alloc(PAGE_SIZE,
+			ioapic_phys = (unsigned long)memblock_alloc_or_panic(PAGE_SIZE,
 								    PAGE_SIZE);
-			if (!ioapic_phys)
-				panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-				      __func__, PAGE_SIZE, PAGE_SIZE);
 			ioapic_phys = __pa(ioapic_phys);
 		}
 		io_apic_set_fixmap(idx, ioapic_phys);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5a505aa65489..a5d0998d7604 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1115,6 +1115,8 @@ do_cmd_auto:
 
 	case RETBLEED_MITIGATION_IBPB:
 		setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+		setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
+		mitigate_smt = true;
 
 		/*
 		 * IBPB on entry already obviates the need for
@@ -1124,9 +1126,6 @@ do_cmd_auto:
 		setup_clear_cpu_cap(X86_FEATURE_UNRET);
 		setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
 
-		setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
-		mitigate_smt = true;
-
 		/*
 		 * There is no need for RSB filling: entry_ibpb() ensures
 		 * all predictions, including the RSB, are invalidated,
@@ -2646,6 +2645,7 @@ static void __init srso_select_mitigation(void)
 		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
 			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
 				srso_mitigation = SRSO_MITIGATION_IBPB;
 
 				/*
@@ -2655,6 +2655,13 @@ static void __init srso_select_mitigation(void)
 				 */
 				setup_clear_cpu_cap(X86_FEATURE_UNRET);
 				setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
+
+				/*
+				 * There is no need for RSB filling: entry_ibpb() ensures
+				 * all predictions, including the RSB, are invalidated,
+				 * regardless of IBPB implementation.
+				 */
+				setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
 			}
 		} else {
 			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
@@ -2663,8 +2670,8 @@ static void __init srso_select_mitigation(void)
 
 ibpb_on_vmexit:
 	case SRSO_CMD_IBPB_ON_VMEXIT:
-		if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
-			if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
+		if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
+			if (has_microcode) {
 				setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
 				srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
 
@@ -2676,8 +2683,8 @@ ibpb_on_vmexit:
 				setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
 			}
 		} else {
-			pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
-                }
+			pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+		}
 		break;
 	default:
 		break;
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 704e9241b964..6cba85c79d42 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -49,7 +49,7 @@ static unsigned int sysctl_sld_mitigate = 1;
 static DEFINE_SEMAPHORE(buslock_sem, 1);
 
 #ifdef CONFIG_PROC_SYSCTL
-static struct ctl_table sld_sysctls[] = {
+static const struct ctl_table sld_sysctls[] = {
 	{
 		.procname       = "split_lock_mitigate",
 		.data           = &sysctl_sld_mitigate,
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 4893d30ce438..82b96ed9890a 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1146,11 +1146,8 @@ void __init e820__reserve_resources(void)
 	struct resource *res;
 	u64 end;
 
-	res = memblock_alloc(sizeof(*res) * e820_table->nr_entries,
+	res = memblock_alloc_or_panic(sizeof(*res) * e820_table->nr_entries,
 			     SMP_CACHE_BYTES);
-	if (!res)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*res) * e820_table->nr_entries);
 	e820_res = res;
 
 	for (i = 0; i < e820_table->nr_entries; i++) {
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 9182303a50b0..7f4b2966e15c 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1382,12 +1382,6 @@ int hpet_set_periodic_freq(unsigned long freq)
 }
 EXPORT_SYMBOL_GPL(hpet_set_periodic_freq);
 
-int hpet_rtc_dropped_irq(void)
-{
-	return is_hpet_enabled();
-}
-EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq);
-
 static void hpet_rtc_timer_reinit(void)
 {
 	unsigned int delta;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 927e33e6843a..1ccaa3397a67 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -59,10 +59,20 @@ void __init native_pv_lock_init(void)
 		static_branch_enable(&virt_spin_lock_key);
 }
 
+#ifndef CONFIG_PT_RECLAIM
 static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
-	tlb_remove_page(tlb, table);
+	struct ptdesc *ptdesc = (struct ptdesc *)table;
+
+	pagetable_dtor(ptdesc);
+	tlb_remove_page(tlb, ptdesc_page(ptdesc));
 }
+#else
+static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	tlb_remove_table(tlb, table);
+}
+#endif
 
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f1fea506e20f..cebee310e200 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -259,6 +259,7 @@ static void __init relocate_initrd(void)
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
+	int ret = 0;
 
 	/* We need to move the initrd down into directly mapped mem */
 	u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0,
@@ -272,7 +273,9 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
 	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
-	copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
+	ret = copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
+	if (ret)
+		panic("Copy RAMDISK failed\n");
 
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index e9e803a4d44c..e6cc84143f3e 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -246,9 +246,8 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 
 	/* VM86_SCREEN_BITMAP had numerous bugs and appears to have no users. */
 	if (v.flags & VM86_SCREEN_BITMAP) {
-		char comm[TASK_COMM_LEN];
-
-		pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", get_task_comm(comm, current));
+		pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n",
+			     current->comm);
 		return -EINVAL;
 	}
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 2cbb3874ad39..8eb3a88707f2 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1180,7 +1180,7 @@ void kvm_set_cpu_caps(void)
 		SYNTHESIZED_F(SBPB),
 		SYNTHESIZED_F(IBPB_BRTYPE),
 		SYNTHESIZED_F(SRSO_NO),
-		SYNTHESIZED_F(SRSO_USER_KERNEL_NO),
+		F(SRSO_USER_KERNEL_NO),
 	);
 
 	kvm_cpu_cap_init(CPUID_8000_0022_EAX,
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a45ae60e84ab..74c20dbb92da 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7120,6 +7120,19 @@ static void mmu_destroy_caches(void)
 	kmem_cache_destroy(mmu_page_header_cache);
 }
 
+static void kvm_wake_nx_recovery_thread(struct kvm *kvm)
+{
+	/*
+	 * The NX recovery thread is spawned on-demand at the first KVM_RUN and
+	 * may not be valid even though the VM is globally visible.  Do nothing,
+	 * as such a VM can't have any possible NX huge pages.
+	 */
+	struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread);
+
+	if (nx_thread)
+		vhost_task_wake(nx_thread);
+}
+
 static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp)
 {
 	if (nx_hugepage_mitigation_hard_disabled)
@@ -7180,7 +7193,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 			kvm_mmu_zap_all_fast(kvm);
 			mutex_unlock(&kvm->slots_lock);
 
-			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+			kvm_wake_nx_recovery_thread(kvm);
 		}
 		mutex_unlock(&kvm_lock);
 	}
@@ -7315,7 +7328,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
 		mutex_lock(&kvm_lock);
 
 		list_for_each_entry(kvm, &vm_list, vm_list)
-			vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread);
+			kvm_wake_nx_recovery_thread(kvm);
 
 		mutex_unlock(&kvm_lock);
 	}
@@ -7451,14 +7464,20 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
+	struct vhost_task *nx_thread;
 
 	kvm->arch.nx_huge_page_last = get_jiffies_64();
-	kvm->arch.nx_huge_page_recovery_thread = vhost_task_create(
-		kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill,
-		kvm, "kvm-nx-lpage-recovery");
+	nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker,
+				      kvm_nx_huge_page_recovery_worker_kill,
+				      kvm, "kvm-nx-lpage-recovery");
 
-	if (kvm->arch.nx_huge_page_recovery_thread)
-		vhost_task_start(kvm->arch.nx_huge_page_recovery_thread);
+	if (!nx_thread)
+		return;
+
+	vhost_task_start(nx_thread);
+
+	/* Make the task visible only once it is fully started. */
+	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d4a6734b2d6..8e77e61d4fbd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12741,6 +12741,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 			     "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n");
 	}
 
+	once_init(&kvm->arch.nx_once);
 	return 0;
 
 out_uninit_mmu:
@@ -12750,12 +12751,6 @@ out:
 	return ret;
 }
 
-int kvm_arch_post_init_vm(struct kvm *kvm)
-{
-	once_init(&kvm->arch.nx_once);
-	return 0;
-}
-
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index ac52255fab01..296d294142c8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -7,7 +7,6 @@
 #include <linux/sched.h>		/* test_thread_flag(), ...	*/
 #include <linux/sched/task_stack.h>	/* task_stack_*(), ...		*/
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
-#include <linux/extable.h>		/* search_exception_tables	*/
 #include <linux/memblock.h>		/* max_low_pfn			*/
 #include <linux/kfence.h>		/* kfence_handle_page_fault	*/
 #include <linux/kprobes.h>		/* NOKPROBE_SYMBOL, ...		*/
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5745a354a241..1fef5ad32d5a 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -19,12 +19,23 @@ EXPORT_SYMBOL(physical_mask);
 #endif
 
 #ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PT_RECLAIM
 static inline
 void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
-	tlb_remove_page(tlb, table);
+	struct ptdesc *ptdesc = (struct ptdesc *)table;
+
+	pagetable_dtor(ptdesc);
+	tlb_remove_page(tlb, ptdesc_page(ptdesc));
 }
-#endif
+#else
+static inline
+void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	tlb_remove_table(tlb, table);
+}
+#endif /* !CONFIG_PT_RECLAIM */
+#endif /* !CONFIG_PARAVIRT */
 
 gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
 
@@ -52,15 +63,13 @@ early_param("userpte", setup_userpte);
 
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
-	pagetable_pte_dtor(page_ptdesc(pte));
 	paravirt_release_pte(page_to_pfn(pte));
-	paravirt_tlb_remove_table(tlb, pte);
+	paravirt_tlb_remove_table(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
-	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
 	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
 	/*
 	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
@@ -69,25 +78,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	pagetable_pmd_dtor(ptdesc);
-	paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc));
+	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
-	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
-
-	pagetable_pud_dtor(ptdesc);
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_page(pud));
+	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_page(p4d));
+	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
@@ -222,7 +227,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 		if (pmds[i]) {
 			ptdesc = virt_to_ptdesc(pmds[i]);
 
-			pagetable_pmd_dtor(ptdesc);
+			pagetable_dtor(ptdesc);
 			pagetable_free(ptdesc);
 			mm_dec_nr_pmds(mm);
 		}
@@ -392,15 +397,14 @@ void __init pgtable_cache_init(void)
 				      SLAB_PANIC, NULL);
 }
 
-static inline pgd_t *_pgd_alloc(void)
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
 	/*
 	 * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
-						 PGD_ALLOCATION_ORDER);
+		return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -409,24 +413,23 @@ static inline pgd_t *_pgd_alloc(void)
 	return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
 }
 
-static inline void _pgd_free(pgd_t *pgd)
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	if (!SHARED_KERNEL_PMD)
-		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
+		__pgd_free(mm, pgd);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
 #else
 
-static inline pgd_t *_pgd_alloc(void)
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
-	return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
-					 PGD_ALLOCATION_ORDER);
+	return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
 }
 
-static inline void _pgd_free(pgd_t *pgd)
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
+	__pgd_free(mm, pgd);
 }
 #endif /* CONFIG_X86_PAE */
 
@@ -436,7 +439,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
 	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
 
-	pgd = _pgd_alloc();
+	pgd = _pgd_alloc(mm);
 
 	if (pgd == NULL)
 		goto out;
@@ -479,7 +482,7 @@ out_free_pmds:
 	if (sizeof(pmds) != 0)
 		free_pmds(mm, pmds, PREALLOCATED_PMDS);
 out_free_pgd:
-	_pgd_free(pgd);
+	_pgd_free(mm, pgd);
 out:
 	return NULL;
 }
@@ -489,7 +492,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	pgd_mop_up_pmds(mm, pgd);
 	pgd_dtor(pgd);
 	paravirt_pgd_free(mm, pgd);
-	_pgd_free(pgd);
+	_pgd_free(mm, pgd);
 }
 
 /*
@@ -856,7 +859,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 
 	free_page((unsigned long)pmd_sv);
 
-	pagetable_pmd_dtor(virt_to_ptdesc(pmd));
+	pagetable_dtor(virt_to_ptdesc(pmd));
 	free_page((unsigned long)pmd);
 
 	return 1;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a2becb85bea7..6cf881a942bb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -607,18 +607,15 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		cond_mitigation(tsk);
 
 		/*
-		 * Stop remote flushes for the previous mm.
-		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
-		 * but the bitmap manipulation can cause cache line contention.
+		 * Leave this CPU in prev's mm_cpumask. Atomic writes to
+		 * mm_cpumask can be expensive under contention. The CPU
+		 * will be removed lazily at TLB flush time.
 		 */
-		if (prev != &init_mm) {
-			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
-						mm_cpumask(prev)));
-			cpumask_clear_cpu(cpu, mm_cpumask(prev));
-		}
+		VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu,
+				mm_cpumask(prev)));
 
 		/* Start receiving IPIs and then read tlb_gen (and LAM below) */
-		if (next != &init_mm)
+		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
@@ -760,10 +757,13 @@ static void flush_tlb_func(void *info)
 	if (!local) {
 		inc_irq_stat(irq_tlb_count);
 		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	}
 
-		/* Can only happen on remote CPUs */
-		if (f->mm && f->mm != loaded_mm)
-			return;
+	/* The CPU was left in the mm_cpumask of the target mm. Clear it. */
+	if (f->mm && f->mm != loaded_mm) {
+		cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm));
+		trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0);
+		return;
 	}
 
 	if (unlikely(loaded_mm == &init_mm))
@@ -893,9 +893,36 @@ done:
 			nr_invalidate);
 }
 
-static bool tlb_is_not_lazy(int cpu, void *data)
+static bool should_flush_tlb(int cpu, void *data)
+{
+	struct flush_tlb_info *info = data;
+
+	/* Lazy TLB will get flushed at the next context switch. */
+	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+		return false;
+
+	/* No mm means kernel memory flush. */
+	if (!info->mm)
+		return true;
+
+	/* The target mm is loaded, and the CPU is not lazy. */
+	if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+		return true;
+
+	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
+	if (info->trim_cpumask)
+		return true;
+
+	return false;
+}
+
+static bool should_trim_cpumask(struct mm_struct *mm)
 {
-	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
+	if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) {
+		WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ);
+		return true;
+	}
+	return false;
 }
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
@@ -929,7 +956,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	if (info->freed_tables)
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
-		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
+		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
 				(void *)info, 1, cpumask);
 }
 
@@ -980,6 +1007,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	info->freed_tables	= freed_tables;
 	info->new_tlb_gen	= new_tlb_gen;
 	info->initiating_cpu	= smp_processor_id();
+	info->trim_cpumask	= 0;
 
 	return info;
 }
@@ -1022,6 +1050,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * flush_tlb_func_local() directly in this case.
 	 */
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c
index 74ebd6882690..cf5dca2dbb91 100644
--- a/arch/x86/platform/olpc/olpc_dt.c
+++ b/arch/x86/platform/olpc/olpc_dt.c
@@ -136,11 +136,7 @@ void * __init prom_early_alloc(unsigned long size)
 		 * fast enough on the platforms we care about while minimizing
 		 * wasted bootmem) and hand off chunks of it to callers.
 		 */
-		res = memblock_alloc(chunk_size, SMP_CACHE_BYTES);
-		if (!res)
-			panic("%s: Failed to allocate %zu bytes\n", __func__,
-			      chunk_size);
-		BUG_ON(!res);
+		res = memblock_alloc_or_panic(chunk_size, SMP_CACHE_BYTES);
 		prom_early_allocated += chunk_size;
 		memset(res, 0, chunk_size);
 		free_mem = chunk_size;
diff --git a/arch/x86/um/asm/archparam.h b/arch/x86/um/asm/archparam.h
deleted file mode 100644
index c17cf68dda0f..000000000000
--- a/arch/x86/um/asm/archparam.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
- * Copyright 2003 PathScale, Inc.
- * Licensed under the GPL
- */
-
-#ifndef __UM_ARCHPARAM_H
-#define __UM_ARCHPARAM_H
-
-#ifdef CONFIG_X86_32
-
-#ifdef CONFIG_X86_PAE
-#define LAST_PKMAP 512
-#else
-#define LAST_PKMAP 1024
-#endif
-
-#endif
-
-#endif
diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h
index 2dd4ca6713f8..8f7476ff6e95 100644
--- a/arch/x86/um/shared/sysdep/ptrace.h
+++ b/arch/x86/um/shared/sysdep/ptrace.h
@@ -74,8 +74,6 @@ struct uml_pt_regs {
 #define UPT_FAULTINFO(r) (&(r)->faultinfo)
 #define UPT_IS_USER(r) ((r)->is_user)
 
-extern int user_context(unsigned long sp);
-
 extern int arch_init_registers(int pid);
 
 #endif /* __SYSDEP_X86_PTRACE_H */
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 55a4996d0c04..2c70cd35e72c 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -781,6 +781,7 @@ void xen_mm_pin_all(void)
 {
 	struct page *page;
 
+	spin_lock(&init_mm.page_table_lock);
 	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
@@ -791,6 +792,7 @@ void xen_mm_pin_all(void)
 	}
 
 	spin_unlock(&pgd_lock);
+	spin_unlock(&init_mm.page_table_lock);
 }
 
 static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
@@ -887,6 +889,7 @@ void xen_mm_unpin_all(void)
 {
 	struct page *page;
 
+	spin_lock(&init_mm.page_table_lock);
 	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
@@ -898,6 +901,7 @@ void xen_mm_unpin_all(void)
 	}
 
 	spin_unlock(&pgd_lock);
+	spin_unlock(&init_mm.page_table_lock);
 }
 
 static void xen_enter_mmap(struct mm_struct *mm)
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index b52d3e17e2c1..56914e21e303 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -178,13 +178,7 @@ static void p2m_init_identity(unsigned long *p2m, unsigned long pfn)
 static void * __ref alloc_p2m_page(void)
 {
 	if (unlikely(!slab_is_available())) {
-		void *ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-
-		if (!ptr)
-			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-			      __func__, PAGE_SIZE, PAGE_SIZE);
-
-		return ptr;
+		return memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
 	}
 
 	return (void *)__get_free_page(GFP_KERNEL);
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 9252652afe59..894edf8d6d62 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -100,9 +100,6 @@ SYM_FUNC_START(xen_hypercall_hvm)
 	push %r10
 	push %r9
 	push %r8
-#ifdef CONFIG_FRAME_POINTER
-	pushq $0	/* Dummy push for stack alignment. */
-#endif
 #endif
 	/* Set the vendor specific function. */
 	call __xen_hypercall_setfunc
@@ -117,11 +114,8 @@ SYM_FUNC_START(xen_hypercall_hvm)
 	pop %ebx
 	pop %eax
 #else
-	lea xen_hypercall_amd(%rip), %rbx
-	cmp %rax, %rbx
-#ifdef CONFIG_FRAME_POINTER
-	pop %rax	/* Dummy pop. */
-#endif
+	lea xen_hypercall_amd(%rip), %rcx
+	cmp %rax, %rcx
 	pop %r8
 	pop %r9
 	pop %r10
@@ -132,6 +126,7 @@ SYM_FUNC_START(xen_hypercall_hvm)
 	pop %rcx
 	pop %rax
 #endif
+	FRAME_END
 	/* Use correct hypercall function. */
 	jz xen_hypercall_amd
 	jmp xen_hypercall_intel
diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index 7fc0f9126dd3..1919ee9c3dd6 100644
--- a/arch/xtensa/include/asm/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
@@ -29,7 +29,7 @@
 static inline pgd_t*
 pgd_alloc(struct mm_struct *mm)
 {
-	return (pgd_t*) __get_free_page(GFP_KERNEL | __GFP_ZERO);
+	return __pgd_alloc(mm, 0);
 }
 
 static inline void ptes_clear(pte_t *ptep)
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 7ed1a2085bd7..47b5df86ab5c 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -160,9 +160,7 @@ struct thread_struct {
 	struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK];
 	struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK];
 #endif
-	/* Make structure 16 bytes aligned. */
-	int align[0] __attribute__ ((aligned(16)));
-};
+} __aligned(16);
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index e51f2060e830..f72e280363be 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -55,7 +55,7 @@ extern int initrd_below_start_ok;
 #endif
 
 #ifdef CONFIG_USE_OF
-void *dtb_start = __dtb_start;
+static void *dtb_start __initdata = __dtb_start;
 #endif
 
 extern unsigned long loops_per_jiffy;
diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c
index f00d122aa806..f39c4d83173a 100644
--- a/arch/xtensa/mm/kasan_init.c
+++ b/arch/xtensa/mm/kasan_init.c
@@ -39,11 +39,7 @@ static void __init populate(void *start, void *end)
 	unsigned long i, j;
 	unsigned long vaddr = (unsigned long)start;
 	pmd_t *pmd = pmd_off_k(vaddr);
-	pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE);
-
-	if (!pte)
-		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-		      __func__, n_pages * sizeof(pte_t), PAGE_SIZE);
+	pte_t *pte = memblock_alloc_or_panic(n_pages * sizeof(pte_t), PAGE_SIZE);
 
 	pr_debug("%s: %p - %p\n", __func__, start, end);
 
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index d6d2b533a574..6ed009318d24 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/proc_fs.h>
@@ -75,7 +76,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector,
 
 	if (offset > dev->size || dev->size - offset < nbytes) {
 		pr_notice("Beyond-end %s (%ld %ld)\n",
-				write ? "write" : "read", offset, nbytes);
+				str_write_read(write), offset, nbytes);
 		return;
 	}
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 45a395862fbc..9ed93d91d754 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1138,6 +1138,7 @@ static void blkcg_fill_root_iostats(void)
 		blkg_iostat_set(&blkg->iostat.cur, &tmp);
 		u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags);
 	}
+	class_dev_iter_exit(&iter);
 }
 
 static void blkcg_print_one_stat(struct blkcg_gq *blkg, struct seq_file *s)
@@ -1545,6 +1546,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 	struct request_queue *q = disk->queue;
 	struct blkg_policy_data *pd_prealloc = NULL;
 	struct blkcg_gq *blkg, *pinned_blkg = NULL;
+	unsigned int memflags;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1559,7 +1561,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol)
 		return -EINVAL;
 
 	if (queue_is_mq(q))
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 retry:
 	spin_lock_irq(&q->queue_lock);
 
@@ -1623,7 +1625,7 @@ retry:
 	spin_unlock_irq(&q->queue_lock);
 out:
 	if (queue_is_mq(q))
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 	if (pinned_blkg)
 		blkg_put(pinned_blkg);
 	if (pd_prealloc)
@@ -1667,12 +1669,13 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 {
 	struct request_queue *q = disk->queue;
 	struct blkcg_gq *blkg;
+	unsigned int memflags;
 
 	if (!blkcg_policy_enabled(q, pol))
 		return;
 
 	if (queue_is_mq(q))
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 
 	mutex_lock(&q->blkcg_mutex);
 	spin_lock_irq(&q->queue_lock);
@@ -1696,7 +1699,7 @@ void blkcg_deactivate_policy(struct gendisk *disk,
 	mutex_unlock(&q->blkcg_mutex);
 
 	if (queue_is_mq(q))
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 32fb28a6372c..d6c4fa3943b5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -430,7 +430,6 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 	refcount_set(&q->refs, 1);
 	mutex_init(&q->debugfs_mutex);
 	mutex_init(&q->sysfs_lock);
-	mutex_init(&q->sysfs_dir_lock);
 	mutex_init(&q->limits_lock);
 	mutex_init(&q->rq_qos_mutex);
 	spin_lock_init(&q->queue_lock);
diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c
index c9eb4241e048..d479f5481b66 100644
--- a/block/blk-ia-ranges.c
+++ b/block/blk-ia-ranges.c
@@ -111,7 +111,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk)
 	struct request_queue *q = disk->queue;
 	int i, ret;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (!iars)
@@ -155,7 +154,6 @@ void disk_unregister_independent_access_ranges(struct gendisk *disk)
 	struct blk_independent_access_ranges *iars = disk->ia_ranges;
 	int i;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
 	lockdep_assert_held(&q->sysfs_lock);
 
 	if (!iars)
@@ -289,7 +287,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk,
 {
 	struct request_queue *q = disk->queue;
 
-	mutex_lock(&q->sysfs_dir_lock);
 	mutex_lock(&q->sysfs_lock);
 	if (iars && !disk_check_ia_ranges(disk, iars)) {
 		kfree(iars);
@@ -313,6 +310,5 @@ void disk_set_independent_access_ranges(struct gendisk *disk,
 		disk_register_independent_access_ranges(disk);
 unlock:
 	mutex_unlock(&q->sysfs_lock);
-	mutex_unlock(&q->sysfs_dir_lock);
 }
 EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges);
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index a5894ec9696e..65a1d4427ccf 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -3224,6 +3224,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 	u32 qos[NR_QOS_PARAMS];
 	bool enable, user;
 	char *body, *p;
+	unsigned int memflags;
 	int ret;
 
 	blkg_conf_init(&ctx, input);
@@ -3247,7 +3248,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 		ioc = q_to_ioc(disk->queue);
 	}
 
-	blk_mq_freeze_queue(disk->queue);
+	memflags = blk_mq_freeze_queue(disk->queue);
 	blk_mq_quiesce_queue(disk->queue);
 
 	spin_lock_irq(&ioc->lock);
@@ -3347,7 +3348,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
 		wbt_enable_default(disk);
 
 	blk_mq_unquiesce_queue(disk->queue);
-	blk_mq_unfreeze_queue(disk->queue);
+	blk_mq_unfreeze_queue(disk->queue, memflags);
 
 	blkg_conf_exit(&ctx);
 	return nbytes;
@@ -3355,7 +3356,7 @@ einval:
 	spin_unlock_irq(&ioc->lock);
 
 	blk_mq_unquiesce_queue(disk->queue);
-	blk_mq_unfreeze_queue(disk->queue);
+	blk_mq_unfreeze_queue(disk->queue, memflags);
 
 	ret = -EINVAL;
 err:
@@ -3414,6 +3415,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 {
 	struct blkg_conf_ctx ctx;
 	struct request_queue *q;
+	unsigned int memflags;
 	struct ioc *ioc;
 	u64 u[NR_I_LCOEFS];
 	bool user;
@@ -3441,7 +3443,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 		ioc = q_to_ioc(q);
 	}
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	spin_lock_irq(&ioc->lock);
@@ -3493,7 +3495,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
 	spin_unlock_irq(&ioc->lock);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	blkg_conf_exit(&ctx);
 	return nbytes;
@@ -3502,7 +3504,7 @@ einval:
 	spin_unlock_irq(&ioc->lock);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	ret = -EINVAL;
 err:
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index ebb522788d97..42c1e0b9a68f 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -749,9 +749,11 @@ static void blkiolatency_enable_work_fn(struct work_struct *work)
 	 */
 	enabled = atomic_read(&blkiolat->enable_cnt);
 	if (enabled != blkiolat->enabled) {
-		blk_mq_freeze_queue(blkiolat->rqos.disk->queue);
+		unsigned int memflags;
+
+		memflags = blk_mq_freeze_queue(blkiolat->rqos.disk->queue);
 		blkiolat->enabled = enabled;
-		blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue);
+		blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue, memflags);
 	}
 }
 
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index ad8d6a363f24..444798c5374f 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -87,7 +87,6 @@ void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
 	return;
 
 fallback:
-	WARN_ON_ONCE(qmap->nr_queues > 1);
-	blk_mq_clear_mq_map(qmap);
+	blk_mq_map_queues(qmap);
 }
 EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues);
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 156e9bb07abf..3feeeccf8a99 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -223,30 +223,27 @@ int blk_mq_sysfs_register(struct gendisk *disk)
 	unsigned long i, j;
 	int ret;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
-
 	ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq");
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	kobject_uevent(q->mq_kobj, KOBJ_ADD);
 
+	mutex_lock(&q->tag_set->tag_list_lock);
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
-			goto unreg;
+			goto out_unreg;
 	}
+	mutex_unlock(&q->tag_set->tag_list_lock);
+	return 0;
 
-	q->mq_sysfs_init_done = true;
-
-out:
-	return ret;
-
-unreg:
+out_unreg:
 	queue_for_each_hw_ctx(q, hctx, j) {
 		if (j < i)
 			blk_mq_unregister_hctx(hctx);
 	}
+	mutex_unlock(&q->tag_set->tag_list_lock);
 
 	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(q->mq_kobj);
@@ -259,15 +256,13 @@ void blk_mq_sysfs_unregister(struct gendisk *disk)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
-	lockdep_assert_held(&q->sysfs_dir_lock);
-
+	mutex_lock(&q->tag_set->tag_list_lock);
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
+	mutex_unlock(&q->tag_set->tag_list_lock);
 
 	kobject_uevent(q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(q->mq_kobj);
-
-	q->mq_sysfs_init_done = false;
 }
 
 void blk_mq_sysfs_unregister_hctxs(struct request_queue *q)
@@ -275,15 +270,11 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
-	mutex_lock(&q->sysfs_dir_lock);
-	if (!q->mq_sysfs_init_done)
-		goto unlock;
+	if (!blk_queue_registered(q))
+		return;
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
-
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
 }
 
 int blk_mq_sysfs_register_hctxs(struct request_queue *q)
@@ -292,9 +283,8 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 	unsigned long i;
 	int ret = 0;
 
-	mutex_lock(&q->sysfs_dir_lock);
-	if (!q->mq_sysfs_init_done)
-		goto unlock;
+	if (!blk_queue_registered(q))
+		goto out;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
@@ -302,8 +292,6 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q)
 			break;
 	}
 
-unlock:
-	mutex_unlock(&q->sysfs_dir_lock);
-
+out:
 	return ret;
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index da39a1cac702..40490ac88045 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -210,12 +210,12 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
 
-void blk_mq_freeze_queue(struct request_queue *q)
+void blk_mq_freeze_queue_nomemsave(struct request_queue *q)
 {
 	blk_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
-EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
+EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_nomemsave);
 
 bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 {
@@ -236,12 +236,12 @@ bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic)
 	return unfreeze;
 }
 
-void blk_mq_unfreeze_queue(struct request_queue *q)
+void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q)
 {
 	if (__blk_mq_unfreeze_queue(q, false))
 		blk_unfreeze_release_lock(q);
 }
-EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
+EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_nomemrestore);
 
 /*
  * non_owner variant of blk_freeze_queue_start
@@ -4223,13 +4223,14 @@ static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set,
 					 bool shared)
 {
 	struct request_queue *q;
+	unsigned int memflags;
 
 	lockdep_assert_held(&set->tag_list_lock);
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
-		blk_mq_freeze_queue(q);
+		memflags = blk_mq_freeze_queue(q);
 		queue_set_hctx_shared(q, shared);
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 	}
 }
 
@@ -4992,6 +4993,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	LIST_HEAD(head);
 	int prev_nr_hw_queues = set->nr_hw_queues;
+	unsigned int memflags;
 	int i;
 
 	lockdep_assert_held(&set->tag_list_lock);
@@ -5003,8 +5005,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues)
 		return;
 
+	memflags = memalloc_noio_save();
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_freeze_queue(q);
+		blk_mq_freeze_queue_nomemsave(q);
+
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -5052,7 +5056,8 @@ switch_back:
 		blk_mq_elv_switch_back(&head, q);
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue_nomemrestore(q);
+	memalloc_noio_restore(memflags);
 
 	/* Free the excess tags when nr_hw_queues shrink. */
 	for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++)
diff --git a/block/blk-pm.c b/block/blk-pm.c
index 42e842074715..8d3e052f91da 100644
--- a/block/blk-pm.c
+++ b/block/blk-pm.c
@@ -89,7 +89,7 @@ int blk_pre_runtime_suspend(struct request_queue *q)
 	if (percpu_ref_is_zero(&q->q_usage_counter))
 		ret = 0;
 	/* Switch q_usage_counter back to per-cpu mode. */
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue_nomemrestore(q);
 
 	if (ret < 0) {
 		spin_lock_irq(&q->queue_lock);
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index eb9618cd68ad..d4d4f4dc0e23 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -299,6 +299,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 		const struct rq_qos_ops *ops)
 {
 	struct request_queue *q = disk->queue;
+	unsigned int memflags;
 
 	lockdep_assert_held(&q->rq_qos_mutex);
 
@@ -310,14 +311,14 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 	 * No IO can be in-flight when adding rqos, so freeze queue, which
 	 * is fine since we only support rq_qos for blk-mq queue.
 	 */
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 
 	if (rq_qos_id(q, rqos->id))
 		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
 
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	if (rqos->ops->debugfs_attrs) {
 		mutex_lock(&q->debugfs_mutex);
@@ -327,7 +328,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 
 	return 0;
 ebusy:
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 	return -EBUSY;
 }
 
@@ -335,17 +336,18 @@ void rq_qos_del(struct rq_qos *rqos)
 {
 	struct request_queue *q = rqos->disk->queue;
 	struct rq_qos **cur;
+	unsigned int memflags;
 
 	lockdep_assert_held(&q->rq_qos_mutex);
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
 		if (*cur == rqos) {
 			*cur = rqos->next;
 			break;
 		}
 	}
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	mutex_lock(&q->debugfs_mutex);
 	blk_mq_debugfs_unregister_rqos(rqos);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index db12396ff5c7..c44dadc35e1e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -461,11 +461,12 @@ EXPORT_SYMBOL_GPL(queue_limits_commit_update);
 int queue_limits_commit_update_frozen(struct request_queue *q,
 		struct queue_limits *lim)
 {
+	unsigned int memflags;
 	int ret;
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	ret = queue_limits_commit_update(q, lim);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	return ret;
 }
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e09b455874bf..6f548a4376aa 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -681,7 +681,7 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct queue_sysfs_entry *entry = to_queue(attr);
 	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
 	struct request_queue *q = disk->queue;
-	unsigned int noio_flag;
+	unsigned int memflags;
 	ssize_t res;
 
 	if (!entry->store_limit && !entry->store)
@@ -711,11 +711,9 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	}
 
 	mutex_lock(&q->sysfs_lock);
-	blk_mq_freeze_queue(q);
-	noio_flag = memalloc_noio_save();
+	memflags = blk_mq_freeze_queue(q);
 	res = entry->store(disk, page, length);
-	memalloc_noio_restore(noio_flag);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -764,7 +762,6 @@ int blk_register_queue(struct gendisk *disk)
 	struct request_queue *q = disk->queue;
 	int ret;
 
-	mutex_lock(&q->sysfs_dir_lock);
 	kobject_init(&disk->queue_kobj, &blk_queue_ktype);
 	ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue");
 	if (ret < 0)
@@ -805,7 +802,6 @@ int blk_register_queue(struct gendisk *disk)
 	if (q->elevator)
 		kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
 	mutex_unlock(&q->sysfs_lock);
-	mutex_unlock(&q->sysfs_dir_lock);
 
 	/*
 	 * SCSI probing may synchronously create and destroy a lot of
@@ -830,7 +826,6 @@ out_debugfs_remove:
 	mutex_unlock(&q->sysfs_lock);
 out_put_queue_kobj:
 	kobject_put(&disk->queue_kobj);
-	mutex_unlock(&q->sysfs_dir_lock);
 	return ret;
 }
 
@@ -861,7 +856,6 @@ void blk_unregister_queue(struct gendisk *disk)
 	blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
 	mutex_unlock(&q->sysfs_lock);
 
-	mutex_lock(&q->sysfs_dir_lock);
 	/*
 	 * Remove the sysfs attributes before unregistering the queue data
 	 * structures that can be modified through sysfs.
@@ -878,7 +872,6 @@ void blk_unregister_queue(struct gendisk *disk)
 	/* Now that we've deleted all child objects, we can delete the queue. */
 	kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE);
 	kobject_del(&disk->queue_kobj);
-	mutex_unlock(&q->sysfs_dir_lock);
 
 	blk_debugfs_remove(disk);
 }
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 82dbaefcfa3b..8d149aff9fd0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1202,6 +1202,7 @@ static int blk_throtl_init(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	struct throtl_data *td;
+	unsigned int memflags;
 	int ret;
 
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
@@ -1215,7 +1216,7 @@ static int blk_throtl_init(struct gendisk *disk)
 	 * Freeze queue before activating policy, to synchronize with IO path,
 	 * which is protected by 'q_usage_counter'.
 	 */
-	blk_mq_freeze_queue(disk->queue);
+	memflags = blk_mq_freeze_queue(disk->queue);
 	blk_mq_quiesce_queue(disk->queue);
 
 	q->td = td;
@@ -1239,7 +1240,7 @@ static int blk_throtl_init(struct gendisk *disk)
 
 out:
 	blk_mq_unquiesce_queue(disk->queue);
-	blk_mq_unfreeze_queue(disk->queue);
+	blk_mq_unfreeze_queue(disk->queue, memflags);
 
 	return ret;
 }
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 9d08a54c201e..761ea662ddc3 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1717,9 +1717,10 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 	else
 		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
 	if (ret) {
-		blk_mq_freeze_queue(q);
+		unsigned int memflags = blk_mq_freeze_queue(q);
+
 		disk_free_zone_resources(disk);
-		blk_mq_unfreeze_queue(q);
+		blk_mq_unfreeze_queue(q, memflags);
 	}
 
 	return ret;
diff --git a/block/elevator.c b/block/elevator.c
index b81216c48b6b..cd2ce4921601 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -570,6 +570,7 @@ static struct elevator_type *elevator_get_default(struct request_queue *q)
 void elevator_init_mq(struct request_queue *q)
 {
 	struct elevator_type *e;
+	unsigned int memflags;
 	int err;
 
 	WARN_ON_ONCE(blk_queue_registered(q));
@@ -590,13 +591,13 @@ void elevator_init_mq(struct request_queue *q)
 	 *
 	 * Disk isn't added yet, so verifying queue lock only manually.
 	 */
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 
 	blk_mq_cancel_work_sync(q);
 
 	err = blk_mq_init_sched(q, e);
 
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	if (err) {
 		pr_warn("\"%s\" elevator initialization failed, "
@@ -614,11 +615,12 @@ void elevator_init_mq(struct request_queue *q)
  */
 int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
+	unsigned int memflags;
 	int ret;
 
 	lockdep_assert_held(&q->sysfs_lock);
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	if (q->elevator) {
@@ -639,7 +641,7 @@ int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
 out_unfreeze:
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	if (ret) {
 		pr_warn("elv: switch to \"%s\" failed, falling back to \"none\"\n",
@@ -651,9 +653,11 @@ out_unfreeze:
 
 void elevator_disable(struct request_queue *q)
 {
+	unsigned int memflags;
+
 	lockdep_assert_held(&q->sysfs_lock);
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	elv_unregister_queue(q);
@@ -664,7 +668,7 @@ void elevator_disable(struct request_queue *q)
 	blk_add_trace_msg(q, "elv switch: none");
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 }
 
 /*
diff --git a/block/fops.c b/block/fops.c
index 6d5c4fc5a216..be9f1dbea9ce 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -783,11 +783,12 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		file_accessed(iocb->ki_filp);
 
 		ret = blkdev_direct_IO(iocb, to);
-		if (ret >= 0) {
+		if (ret > 0) {
 			iocb->ki_pos += ret;
 			count -= ret;
 		}
-		iov_iter_revert(to, count - iov_iter_count(to));
+		if (ret != -EIOCBQUEUED)
+			iov_iter_revert(to, count - iov_iter_count(to));
 		if (ret < 0 || !count)
 			goto reexpand;
 	}
diff --git a/crypto/fips.c b/crypto/fips.c
index a58e7750f532..2fa3a9ee61a1 100644
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -41,7 +41,7 @@ __setup("fips=", fips_enable);
 static char fips_name[] = FIPS_MODULE_NAME;
 static char fips_version[] = FIPS_MODULE_VERSION;
 
-static struct ctl_table crypto_sysctl_table[] = {
+static const struct ctl_table crypto_sysctl_table[] = {
 	{
 		.procname	= "fips_enabled",
 		.data		= &fips_enabled,
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c
index 97d4a032171f..f5b8497cf5ad 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.c
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c
@@ -21,6 +21,11 @@
 
 #define AMDXDNA_AUTOSUSPEND_DELAY	5000 /* milliseconds */
 
+MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin");
+MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin");
+
 /*
  * Bind the driver base on (vendor_id, device_id) pair and later use the
  * (device_id, rev_id) pair as a key to select the devices. The devices with
diff --git a/drivers/accel/habanalabs/common/context.c b/drivers/accel/habanalabs/common/context.c
index b83141f58319..9f212b17611a 100644
--- a/drivers/accel/habanalabs/common/context.c
+++ b/drivers/accel/habanalabs/common/context.c
@@ -199,7 +199,6 @@ out_err:
 
 int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
 {
-	char task_comm[TASK_COMM_LEN];
 	int rc = 0, i;
 
 	ctx->hdev = hdev;
@@ -272,7 +271,7 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
 		mutex_init(&ctx->ts_reg_lock);
 
 		dev_dbg(hdev->dev, "create user context, comm=\"%s\", asid=%u\n",
-			get_task_comm(task_comm, current), ctx->asid);
+			current->comm, ctx->asid);
 	}
 
 	return 0;
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index e0cf3b4343bb..30277ae410d4 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -817,7 +817,7 @@ static void device_hard_reset_pending(struct work_struct *work)
 		}
 
 		queue_delayed_work(hdev->reset_wq, &device_reset_work->reset_work,
-					msecs_to_jiffies(HL_PENDING_RESET_PER_SEC * 1000));
+					secs_to_jiffies(HL_PENDING_RESET_PER_SEC));
 	}
 }
 
diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index 5409b2c656c8..596c52e8aa26 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -361,8 +361,7 @@ static void fixup_device_params_per_asic(struct hl_device *hdev, int timeout)
 		 * a different default timeout for Gaudi
 		 */
 		if (timeout == HL_DEFAULT_TIMEOUT_LOCKED)
-			hdev->timeout_jiffies = msecs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED *
-										MSEC_PER_SEC);
+			hdev->timeout_jiffies = secs_to_jiffies(GAUDI_DEFAULT_TIMEOUT_LOCKED);
 
 		hdev->reset_upon_device_release = 0;
 		break;
diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index 1dd6e23172ca..8729a0c57d78 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -1279,13 +1279,10 @@ static long _hl_ioctl(struct hl_fpriv *hpriv, unsigned int cmd, unsigned long ar
 		retcode = -EFAULT;
 
 out_err:
-	if (retcode) {
-		char task_comm[TASK_COMM_LEN];
-
+	if (retcode)
 		dev_dbg_ratelimited(dev,
 				"error in ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n",
-				task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr);
-	}
+				task_pid_nr(current), current->comm, cmd, nr);
 
 	if (kdata != stack_kdata)
 		kfree(kdata);
@@ -1308,11 +1305,9 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
 	if (nr == _IOC_NR(DRM_IOCTL_HL_INFO)) {
 		ioctl = &hl_ioctls_control[nr - HL_COMMAND_START];
 	} else {
-		char task_comm[TASK_COMM_LEN];
-
 		dev_dbg_ratelimited(hdev->dev_ctrl,
 				"invalid ioctl: pid=%d, comm=\"%s\", cmd=%#010x, nr=%#04x\n",
-				task_pid_nr(current), get_task_comm(task_comm, current), cmd, nr);
+				task_pid_nr(current), current->comm, cmd, nr);
 		return -ENOTTY;
 	}
 
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 1e8ffbe25eee..38cf1c342c72 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -397,15 +397,19 @@ int ivpu_boot(struct ivpu_device *vdev)
 	if (ivpu_fw_is_cold_boot(vdev)) {
 		ret = ivpu_pm_dct_init(vdev);
 		if (ret)
-			goto err_diagnose_failure;
+			goto err_disable_ipc;
 
 		ret = ivpu_hw_sched_init(vdev);
 		if (ret)
-			goto err_diagnose_failure;
+			goto err_disable_ipc;
 	}
 
 	return 0;
 
+err_disable_ipc:
+	ivpu_ipc_disable(vdev);
+	ivpu_hw_irq_disable(vdev);
+	disable_irq(vdev->irq);
 err_diagnose_failure:
 	ivpu_hw_diagnose_failure(vdev);
 	ivpu_mmu_evtq_dump(vdev);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 87d7411ae059..5060c5dd40d1 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -115,41 +115,57 @@ err_power_down:
 	return ret;
 }
 
-static void ivpu_pm_recovery_work(struct work_struct *work)
+static void ivpu_pm_reset_begin(struct ivpu_device *vdev)
 {
-	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
-	struct ivpu_device *vdev = pm->vdev;
-	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
-	int ret;
-
-	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
-
-	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	if (ret)
-		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
-
-	ivpu_jsm_state_dump(vdev);
-	ivpu_dev_coredump(vdev);
+	pm_runtime_disable(vdev->drm.dev);
 
 	atomic_inc(&vdev->pm->reset_counter);
 	atomic_set(&vdev->pm->reset_pending, 1);
 	down_write(&vdev->pm->reset_lock);
+}
+
+static void ivpu_pm_reset_complete(struct ivpu_device *vdev)
+{
+	int ret;
 
-	ivpu_suspend(vdev);
 	ivpu_pm_prepare_cold_boot(vdev);
 	ivpu_jobs_abort_all(vdev);
 	ivpu_ms_cleanup_all(vdev);
 
 	ret = ivpu_resume(vdev);
-	if (ret)
+	if (ret) {
 		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	} else {
+		pm_runtime_set_active(vdev->drm.dev);
+	}
 
 	up_write(&vdev->pm->reset_lock);
 	atomic_set(&vdev->pm->reset_pending, 0);
 
-	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	pm_runtime_enable(vdev->drm.dev);
+}
+
+static void ivpu_pm_recovery_work(struct work_struct *work)
+{
+	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work);
+	struct ivpu_device *vdev = pm->vdev;
+	char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL};
+
+	ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter));
+
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_jsm_state_dump(vdev);
+		ivpu_dev_coredump(vdev);
+		ivpu_suspend(vdev);
+	}
+
+	ivpu_pm_reset_complete(vdev);
+
+	kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt);
 }
 
 void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason)
@@ -309,7 +325,10 @@ int ivpu_rpm_get(struct ivpu_device *vdev)
 	int ret;
 
 	ret = pm_runtime_resume_and_get(vdev->drm.dev);
-	drm_WARN_ON(&vdev->drm, ret < 0);
+	if (ret < 0) {
+		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
+		pm_runtime_set_suspended(vdev->drm.dev);
+	}
 
 	return ret;
 }
@@ -325,16 +344,13 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
 
 	ivpu_dbg(vdev, PM, "Pre-reset..\n");
-	atomic_inc(&vdev->pm->reset_counter);
-	atomic_set(&vdev->pm->reset_pending, 1);
 
-	pm_runtime_get_sync(vdev->drm.dev);
-	down_write(&vdev->pm->reset_lock);
-	ivpu_prepare_for_reset(vdev);
-	ivpu_hw_reset(vdev);
-	ivpu_pm_prepare_cold_boot(vdev);
-	ivpu_jobs_abort_all(vdev);
-	ivpu_ms_cleanup_all(vdev);
+	ivpu_pm_reset_begin(vdev);
+
+	if (!pm_runtime_status_suspended(vdev->drm.dev)) {
+		ivpu_prepare_for_reset(vdev);
+		ivpu_hw_reset(vdev);
+	}
 
 	ivpu_dbg(vdev, PM, "Pre-reset done.\n");
 }
@@ -342,18 +358,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev)
 void ivpu_pm_reset_done_cb(struct pci_dev *pdev)
 {
 	struct ivpu_device *vdev = pci_get_drvdata(pdev);
-	int ret;
 
 	ivpu_dbg(vdev, PM, "Post-reset..\n");
-	ret = ivpu_resume(vdev);
-	if (ret)
-		ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret);
-	up_write(&vdev->pm->reset_lock);
-	atomic_set(&vdev->pm->reset_pending, 0);
-	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 
-	pm_runtime_mark_last_busy(vdev->drm.dev);
-	pm_runtime_put_autosuspend(vdev->drm.dev);
+	ivpu_pm_reset_complete(vdev);
+
+	ivpu_dbg(vdev, PM, "Post-reset done.\n");
 }
 
 void ivpu_pm_init(struct ivpu_device *vdev)
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index ca87a0939135..f7fb7205028d 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -251,6 +251,10 @@ static int __init extlog_init(void)
 	}
 
 	extlog_l1_hdr = acpi_os_map_iomem(l1_dirbase, l1_hdr_size);
+	if (!extlog_l1_hdr) {
+		rc = -ENOMEM;
+		goto err_release_l1_hdr;
+	}
 	l1_head = (struct extlog_l1_head *)extlog_l1_hdr;
 	l1_size = l1_head->total_len;
 	l1_percpu_entry = l1_head->entries;
@@ -268,6 +272,10 @@ static int __init extlog_init(void)
 		goto err;
 	}
 	extlog_l1_addr = acpi_os_map_iomem(l1_dirbase, l1_size);
+	if (!extlog_l1_addr) {
+		rc = -ENOMEM;
+		goto err_release_l1_dir;
+	}
 	l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size);
 
 	/* remap elog table */
@@ -279,6 +287,10 @@ static int __init extlog_init(void)
 		goto err_release_l1_dir;
 	}
 	elog_addr = acpi_os_map_iomem(elog_base, elog_size);
+	if (!elog_addr) {
+		rc = -ENOMEM;
+		goto err_release_elog;
+	}
 
 	rc = -ENOMEM;
 	/* allocate buffer to save elog record */
@@ -300,6 +312,8 @@ err_release_l1_dir:
 	if (extlog_l1_addr)
 		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
 	release_mem_region(l1_dirbase, l1_size);
+err_release_l1_hdr:
+	release_mem_region(l1_dirbase, l1_hdr_size);
 err:
 	pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n");
 	return rc;
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index 79bbfe00d241..b8543a34caea 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -103,8 +103,6 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info *gpe_event_info,
 
 acpi_status acpi_hw_enable_all_runtime_gpes(void);
 
-acpi_status acpi_hw_enable_all_wakeup_gpes(void);
-
 u8 acpi_hw_check_all_gpes(acpi_handle gpe_skip_device, u32 gpe_skip_number);
 
 acpi_status
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 80a3481c0470..bfbb08b1e6af 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -442,9 +442,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 		return -EINVAL;
 	}
 
-	pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
-		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
-		hmat_loc->entry_base_unit);
+	pr_debug("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
+		 hmat_loc->flags, hmat_data_type(type), ipds, tpds,
+		 hmat_loc->entry_base_unit);
 
 	inits = (u32 *)(hmat_loc + 1);
 	targs = inits + ipds;
@@ -455,9 +455,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header,
 			value = hmat_normalize(entries[init * tpds + targ],
 					       hmat_loc->entry_base_unit,
 					       type);
-			pr_info("  Initiator-Target[%u-%u]:%u%s\n",
-				inits[init], targs[targ], value,
-				hmat_data_type_suffix(type));
+			pr_debug("  Initiator-Target[%u-%u]:%u%s\n",
+				 inits[init], targs[targ], value,
+				 hmat_data_type_suffix(type));
 
 			hmat_update_target(targs[targ], inits[init],
 					   mem_hier, type, value);
@@ -485,9 +485,9 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header,
 	}
 
 	attrs = cache->cache_attributes;
-	pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
-		cache->memory_PD, cache->cache_size, attrs,
-		cache->number_of_SMBIOShandles);
+	pr_debug("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
+		 cache->memory_PD, cache->cache_size, attrs,
+		 cache->number_of_SMBIOShandles);
 
 	target = find_mem_target(cache->memory_PD);
 	if (!target)
@@ -546,9 +546,9 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 	}
 
 	if (hmat_revision == 1)
-		pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
-			p->reserved3, p->reserved4, p->flags, p->processor_PD,
-			p->memory_PD);
+		pr_debug("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
+			 p->reserved3, p->reserved4, p->flags, p->processor_PD,
+			 p->memory_PD);
 	else
 		pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
 			p->flags, p->processor_PD, p->memory_PD);
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index bec0dcd1f9c3..00ac0d7bb8c9 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -81,6 +81,101 @@ int acpi_map_pxm_to_node(int pxm)
 }
 EXPORT_SYMBOL(acpi_map_pxm_to_node);
 
+#ifdef CONFIG_NUMA_EMU
+/*
+ * Take max_nid - 1 fake-numa nodes into account in both
+ * pxm_to_node_map()/node_to_pxm_map[] tables.
+ */
+int __init fix_pxm_node_maps(int max_nid)
+{
+	static int pxm_to_node_map_copy[MAX_PXM_DOMAINS] __initdata
+			= { [0 ... MAX_PXM_DOMAINS - 1] = NUMA_NO_NODE };
+	static int node_to_pxm_map_copy[MAX_NUMNODES] __initdata
+			= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
+	int i, j, index = -1, count = 0;
+	nodemask_t nodes_to_enable;
+
+	if (numa_off)
+		return -1;
+
+	/* no or incomplete node/PXM mapping set, nothing to do */
+	if (srat_disabled())
+		return 0;
+
+	/* find fake nodes PXM mapping */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_to_pxm_map[i] != PXM_INVAL) {
+			for (j = 0; j <= max_nid; j++) {
+				if ((emu_nid_to_phys[j] == i) &&
+				    WARN(node_to_pxm_map_copy[j] != PXM_INVAL,
+					 "Node %d is already binded to PXM %d\n",
+					 j, node_to_pxm_map_copy[j]))
+					return -1;
+				if (emu_nid_to_phys[j] == i) {
+					node_to_pxm_map_copy[j] =
+						node_to_pxm_map[i];
+					if (j > index)
+						index = j;
+					count++;
+				}
+			}
+		}
+	}
+	if (index == -1) {
+		pr_debug("No node/PXM mapping has been set\n");
+		/* nothing more to be done */
+		return 0;
+	}
+	if (WARN(index != max_nid, "%d max nid  when expected %d\n",
+		      index, max_nid))
+		return -1;
+
+	nodes_clear(nodes_to_enable);
+
+	/* map phys nodes not used for fake nodes */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_to_pxm_map[i] != PXM_INVAL) {
+			for (j = 0; j <= max_nid; j++)
+				if (emu_nid_to_phys[j] == i)
+					break;
+			/* fake nodes PXM mapping has been done */
+			if (j <= max_nid)
+				continue;
+			/* find first hole */
+			for (j = 0;
+			     j < MAX_NUMNODES &&
+				 node_to_pxm_map_copy[j] != PXM_INVAL;
+			     j++)
+			;
+			if (WARN(j == MAX_NUMNODES,
+			    "Number of nodes exceeds MAX_NUMNODES\n"))
+				return -1;
+			node_to_pxm_map_copy[j] = node_to_pxm_map[i];
+			node_set(j, nodes_to_enable);
+			count++;
+		}
+	}
+
+	/* creating reverse mapping in pxm_to_node_map[] */
+	for (i = 0; i < MAX_NUMNODES; i++)
+		if (node_to_pxm_map_copy[i] != PXM_INVAL &&
+		    pxm_to_node_map_copy[node_to_pxm_map_copy[i]] == NUMA_NO_NODE)
+			pxm_to_node_map_copy[node_to_pxm_map_copy[i]] = i;
+
+	/* overwrite with new mapping */
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		node_to_pxm_map[i] = node_to_pxm_map_copy[i];
+		pxm_to_node_map[i] = pxm_to_node_map_copy[i];
+	}
+
+	/* enable other nodes found in PXM for hotplug */
+	nodes_or(numa_nodes_parsed, nodes_to_enable, numa_nodes_parsed);
+
+	pr_debug("found %d total number of nodes\n", count);
+	return 0;
+}
+#endif
+
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {
diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c
index 747f83f7114d..e549914a636c 100644
--- a/drivers/acpi/prmt.c
+++ b/drivers/acpi/prmt.c
@@ -287,9 +287,7 @@ static acpi_status acpi_platformrt_space_handler(u32 function,
 		if (!handler || !module)
 			goto invalid_guid;
 
-		if (!handler->handler_addr ||
-		    !handler->static_data_buffer_addr ||
-		    !handler->acpi_param_buffer_addr) {
+		if (!handler->handler_addr) {
 			buffer->prm_status = PRM_HANDLER_ERROR;
 			return AE_OK;
 		}
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 98d93ed58315..436019d96027 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1187,8 +1187,6 @@ static int acpi_data_prop_read(const struct acpi_device_data *data,
 		}
 		break;
 	}
-	if (nval == 0)
-		return -EINVAL;
 
 	if (obj->type == ACPI_TYPE_BUFFER) {
 		if (proptype != DEV_PROP_U8)
@@ -1212,9 +1210,11 @@ static int acpi_data_prop_read(const struct acpi_device_data *data,
 		ret = acpi_copy_property_array_uint(items, (u64 *)val, nval);
 		break;
 	case DEV_PROP_STRING:
-		ret = acpi_copy_property_array_string(
-			items, (char **)val,
-			min_t(u32, nval, obj->package.count));
+		nval = min_t(u32, nval, obj->package.count);
+		if (nval == 0)
+			return -ENODATA;
+
+		ret = acpi_copy_property_array_string(items, (char **)val, nval);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 90aaec923889..b4cd14e7fa76 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -564,6 +564,12 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 		},
 	},
 	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."),
+			DMI_MATCH(DMI_BOARD_NAME, "MECH-17"),
+		},
+	},
+	{
 		/* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"),
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index cb45ef5240da..068c1612660b 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -408,6 +408,19 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = {
 					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
 	},
 	{
+		/* Vexia Edu Atla 10 tablet 5V version */
+		.matches = {
+			/* Having all 3 of these not set is somewhat unique */
+			DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."),
+			/* Above strings are too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"),
+		},
+		.driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS |
+					ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY),
+	},
+	{
 		/* Vexia Edu Atla 10 tablet 9V version */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index a4b98e95ab85..76052006bd87 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1971,7 +1971,7 @@ static bool binder_validate_fixup(struct binder_proc *proc,
  * struct binder_task_work_cb - for deferred close
  *
  * @twork:                callback_head for task work
- * @fd:                   fd to close
+ * @file:                 file to close
  *
  * Structure to pass task work to be handled after
  * returning from binder_ioctl() via task_work_add().
@@ -3800,13 +3800,13 @@ err_invalid_target_handle:
 	}
 
 	binder_debug(BINDER_DEBUG_FAILED_TRANSACTION,
-		     "%d:%d transaction %s to %d:%d failed %d/%d/%d, size %lld-%lld line %d\n",
+		     "%d:%d transaction %s to %d:%d failed %d/%d/%d, code %u size %lld-%lld line %d\n",
 		     proc->pid, thread->pid, reply ? "reply" :
 		     (tr->flags & TF_ONE_WAY ? "async" : "call"),
 		     target_proc ? target_proc->pid : 0,
 		     target_thread ? target_thread->pid : 0,
 		     t_debug_id, return_error, return_error_param,
-		     (u64)tr->data_size, (u64)tr->offsets_size,
+		     tr->code, (u64)tr->data_size, (u64)tr->offsets_size,
 		     return_error_line);
 
 	if (target_thread)
@@ -6373,7 +6373,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m,
 		seq_printf(m, " node %d", buffer->target_node->debug_id);
 	seq_printf(m, " size %zd:%zd offset %lx\n",
 		   buffer->data_size, buffer->offsets_size,
-		   proc->alloc.buffer - buffer->user_data);
+		   proc->alloc.vm_start - buffer->user_data);
 }
 
 static void print_binder_work_ilocked(struct seq_file *m,
@@ -6927,6 +6927,11 @@ const struct binder_debugfs_entry binder_debugfs_entries[] = {
 	{} /* terminator */
 };
 
+void binder_add_device(struct binder_device *device)
+{
+	hlist_add_head(&device->hlist, &binder_devices);
+}
+
 static int __init init_binder_device(const char *name)
 {
 	int ret;
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index a738e7745865..fcfaf1b899c8 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -61,7 +61,7 @@ static size_t binder_alloc_buffer_size(struct binder_alloc *alloc,
 				       struct binder_buffer *buffer)
 {
 	if (list_is_last(&buffer->entry, &alloc->buffers))
-		return alloc->buffer + alloc->buffer_size - buffer->user_data;
+		return alloc->vm_start + alloc->buffer_size - buffer->user_data;
 	return binder_buffer_next(buffer)->user_data - buffer->user_data;
 }
 
@@ -169,32 +169,33 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc,
 {
 	struct binder_buffer *buffer;
 
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	buffer = binder_alloc_prepare_to_free_locked(alloc, user_ptr);
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 	return buffer;
 }
 
 static inline void
-binder_set_installed_page(struct binder_lru_page *lru_page,
+binder_set_installed_page(struct binder_alloc *alloc,
+			  unsigned long index,
 			  struct page *page)
 {
 	/* Pairs with acquire in binder_get_installed_page() */
-	smp_store_release(&lru_page->page_ptr, page);
+	smp_store_release(&alloc->pages[index], page);
 }
 
 static inline struct page *
-binder_get_installed_page(struct binder_lru_page *lru_page)
+binder_get_installed_page(struct binder_alloc *alloc, unsigned long index)
 {
 	/* Pairs with release in binder_set_installed_page() */
-	return smp_load_acquire(&lru_page->page_ptr);
+	return smp_load_acquire(&alloc->pages[index]);
 }
 
 static void binder_lru_freelist_add(struct binder_alloc *alloc,
 				    unsigned long start, unsigned long end)
 {
-	struct binder_lru_page *page;
 	unsigned long page_addr;
+	struct page *page;
 
 	trace_binder_update_page_range(alloc, false, start, end);
 
@@ -202,65 +203,159 @@ static void binder_lru_freelist_add(struct binder_alloc *alloc,
 		size_t index;
 		int ret;
 
-		index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		page = &alloc->pages[index];
-
-		if (!binder_get_installed_page(page))
+		index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		page = binder_get_installed_page(alloc, index);
+		if (!page)
 			continue;
 
 		trace_binder_free_lru_start(alloc, index);
 
-		ret = list_lru_add_obj(&binder_freelist, &page->lru);
+		ret = list_lru_add(&binder_freelist,
+				   page_to_lru(page),
+				   page_to_nid(page),
+				   NULL);
 		WARN_ON(!ret);
 
 		trace_binder_free_lru_end(alloc, index);
 	}
 }
 
-static int binder_install_single_page(struct binder_alloc *alloc,
-				      struct binder_lru_page *lru_page,
-				      unsigned long addr)
+static inline
+void binder_alloc_set_mapped(struct binder_alloc *alloc, bool state)
 {
-	struct page *page;
-	int ret = 0;
+	/* pairs with smp_load_acquire in binder_alloc_is_mapped() */
+	smp_store_release(&alloc->mapped, state);
+}
 
-	if (!mmget_not_zero(alloc->mm))
-		return -ESRCH;
+static inline bool binder_alloc_is_mapped(struct binder_alloc *alloc)
+{
+	/* pairs with smp_store_release in binder_alloc_set_mapped() */
+	return smp_load_acquire(&alloc->mapped);
+}
+
+static struct page *binder_page_lookup(struct binder_alloc *alloc,
+				       unsigned long addr)
+{
+	struct mm_struct *mm = alloc->mm;
+	struct page *page;
+	long npages = 0;
 
 	/*
-	 * Protected with mmap_sem in write mode as multiple tasks
-	 * might race to install the same page.
+	 * Find an existing page in the remote mm. If missing,
+	 * don't attempt to fault-in just propagate an error.
 	 */
-	mmap_write_lock(alloc->mm);
-	if (binder_get_installed_page(lru_page))
-		goto out;
+	mmap_read_lock(mm);
+	if (binder_alloc_is_mapped(alloc))
+		npages = get_user_pages_remote(mm, addr, 1, FOLL_NOFAULT,
+					       &page, NULL);
+	mmap_read_unlock(mm);
 
-	if (!alloc->vma) {
-		pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
-		ret = -ESRCH;
-		goto out;
+	return npages > 0 ? page : NULL;
+}
+
+static int binder_page_insert(struct binder_alloc *alloc,
+			      unsigned long addr,
+			      struct page *page)
+{
+	struct mm_struct *mm = alloc->mm;
+	struct vm_area_struct *vma;
+	int ret = -ESRCH;
+
+	/* attempt per-vma lock first */
+	vma = lock_vma_under_rcu(mm, addr);
+	if (vma) {
+		if (binder_alloc_is_mapped(alloc))
+			ret = vm_insert_page(vma, addr, page);
+		vma_end_read(vma);
+		return ret;
 	}
 
+	/* fall back to mmap_lock */
+	mmap_read_lock(mm);
+	vma = vma_lookup(mm, addr);
+	if (vma && binder_alloc_is_mapped(alloc))
+		ret = vm_insert_page(vma, addr, page);
+	mmap_read_unlock(mm);
+
+	return ret;
+}
+
+static struct page *binder_page_alloc(struct binder_alloc *alloc,
+				      unsigned long index)
+{
+	struct binder_shrinker_mdata *mdata;
+	struct page *page;
+
 	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+	if (!page)
+		return NULL;
+
+	/* allocate and install shrinker metadata under page->private */
+	mdata = kzalloc(sizeof(*mdata), GFP_KERNEL);
+	if (!mdata) {
+		__free_page(page);
+		return NULL;
+	}
+
+	mdata->alloc = alloc;
+	mdata->page_index = index;
+	INIT_LIST_HEAD(&mdata->lru);
+	set_page_private(page, (unsigned long)mdata);
+
+	return page;
+}
+
+static void binder_free_page(struct page *page)
+{
+	kfree((struct binder_shrinker_mdata *)page_private(page));
+	__free_page(page);
+}
+
+static int binder_install_single_page(struct binder_alloc *alloc,
+				      unsigned long index,
+				      unsigned long addr)
+{
+	struct page *page;
+	int ret;
+
+	if (!mmget_not_zero(alloc->mm))
+		return -ESRCH;
+
+	page = binder_page_alloc(alloc, index);
 	if (!page) {
-		pr_err("%d: failed to allocate page\n", alloc->pid);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	ret = vm_insert_page(alloc->vma, addr, page);
-	if (ret) {
+	ret = binder_page_insert(alloc, addr, page);
+	switch (ret) {
+	case -EBUSY:
+		/*
+		 * EBUSY is ok. Someone installed the pte first but the
+		 * alloc->pages[index] has not been updated yet. Discard
+		 * our page and look up the one already installed.
+		 */
+		ret = 0;
+		binder_free_page(page);
+		page = binder_page_lookup(alloc, addr);
+		if (!page) {
+			pr_err("%d: failed to find page at offset %lx\n",
+			       alloc->pid, addr - alloc->vm_start);
+			ret = -ESRCH;
+			break;
+		}
+		fallthrough;
+	case 0:
+		/* Mark page installation complete and safe to use */
+		binder_set_installed_page(alloc, index, page);
+		break;
+	default:
+		binder_free_page(page);
 		pr_err("%d: %s failed to insert page at offset %lx with %d\n",
-		       alloc->pid, __func__, addr - alloc->buffer, ret);
-		__free_page(page);
-		ret = -ENOMEM;
-		goto out;
+		       alloc->pid, __func__, addr - alloc->vm_start, ret);
+		break;
 	}
-
-	/* Mark page installation complete and safe to use */
-	binder_set_installed_page(lru_page, page);
 out:
-	mmap_write_unlock(alloc->mm);
 	mmput_async(alloc->mm);
 	return ret;
 }
@@ -269,7 +364,6 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc,
 				       struct binder_buffer *buffer,
 				       size_t size)
 {
-	struct binder_lru_page *page;
 	unsigned long start, final;
 	unsigned long page_addr;
 
@@ -280,15 +374,13 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc,
 		unsigned long index;
 		int ret;
 
-		index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		page = &alloc->pages[index];
-
-		if (binder_get_installed_page(page))
+		index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		if (binder_get_installed_page(alloc, index))
 			continue;
 
 		trace_binder_alloc_page_start(alloc, index);
 
-		ret = binder_install_single_page(alloc, page, page_addr);
+		ret = binder_install_single_page(alloc, index, page_addr);
 		if (ret)
 			return ret;
 
@@ -302,8 +394,8 @@ static int binder_install_buffer_pages(struct binder_alloc *alloc,
 static void binder_lru_freelist_del(struct binder_alloc *alloc,
 				    unsigned long start, unsigned long end)
 {
-	struct binder_lru_page *page;
 	unsigned long page_addr;
+	struct page *page;
 
 	trace_binder_update_page_range(alloc, true, start, end);
 
@@ -311,13 +403,16 @@ static void binder_lru_freelist_del(struct binder_alloc *alloc,
 		unsigned long index;
 		bool on_lru;
 
-		index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		page = &alloc->pages[index];
+		index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		page = binder_get_installed_page(alloc, index);
 
-		if (page->page_ptr) {
+		if (page) {
 			trace_binder_alloc_lru_start(alloc, index);
 
-			on_lru = list_lru_del_obj(&binder_freelist, &page->lru);
+			on_lru = list_lru_del(&binder_freelist,
+					      page_to_lru(page),
+					      page_to_nid(page),
+					      NULL);
 			WARN_ON(!on_lru);
 
 			trace_binder_alloc_lru_end(alloc, index);
@@ -329,20 +424,6 @@ static void binder_lru_freelist_del(struct binder_alloc *alloc,
 	}
 }
 
-static inline void binder_alloc_set_vma(struct binder_alloc *alloc,
-		struct vm_area_struct *vma)
-{
-	/* pairs with smp_load_acquire in binder_alloc_get_vma() */
-	smp_store_release(&alloc->vma, vma);
-}
-
-static inline struct vm_area_struct *binder_alloc_get_vma(
-		struct binder_alloc *alloc)
-{
-	/* pairs with smp_store_release in binder_alloc_set_vma() */
-	return smp_load_acquire(&alloc->vma);
-}
-
 static void debug_no_space_locked(struct binder_alloc *alloc)
 {
 	size_t largest_alloc_size = 0;
@@ -576,7 +657,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	int ret;
 
 	/* Check binder_alloc is fully initialized */
-	if (!binder_alloc_get_vma(alloc)) {
+	if (!binder_alloc_is_mapped(alloc)) {
 		binder_alloc_debug(BINDER_DEBUG_USER_ERROR,
 				   "%d: binder_alloc_buf, no vma\n",
 				   alloc->pid);
@@ -597,10 +678,10 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	if (!next)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	buffer = binder_alloc_new_buf_locked(alloc, next, size, is_async);
 	if (IS_ERR(buffer)) {
-		spin_unlock(&alloc->lock);
+		mutex_unlock(&alloc->mutex);
 		goto out;
 	}
 
@@ -608,7 +689,7 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc,
 	buffer->offsets_size = offsets_size;
 	buffer->extra_buffers_size = extra_buffers_size;
 	buffer->pid = current->tgid;
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 
 	ret = binder_install_buffer_pages(alloc, buffer, size);
 	if (ret) {
@@ -674,8 +755,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	BUG_ON(buffer->free);
 	BUG_ON(size > buffer_size);
 	BUG_ON(buffer->transaction != NULL);
-	BUG_ON(buffer->user_data < alloc->buffer);
-	BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
+	BUG_ON(buffer->user_data < alloc->vm_start);
+	BUG_ON(buffer->user_data > alloc->vm_start + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
 		alloc->free_async_space += buffer_size;
@@ -734,14 +815,13 @@ static struct page *binder_alloc_get_page(struct binder_alloc *alloc,
 					  pgoff_t *pgoffp)
 {
 	binder_size_t buffer_space_offset = buffer_offset +
-		(buffer->user_data - alloc->buffer);
+		(buffer->user_data - alloc->vm_start);
 	pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK;
 	size_t index = buffer_space_offset >> PAGE_SHIFT;
-	struct binder_lru_page *lru_page;
 
-	lru_page = &alloc->pages[index];
 	*pgoffp = pgoff;
-	return lru_page->page_ptr;
+
+	return alloc->pages[index];
 }
 
 /**
@@ -785,17 +865,17 @@ void binder_alloc_free_buf(struct binder_alloc *alloc,
 	 * We could eliminate the call to binder_alloc_clear_buf()
 	 * from binder_alloc_deferred_release() by moving this to
 	 * binder_free_buf_locked(). However, that could
-	 * increase contention for the alloc->lock if clear_on_free
-	 * is used frequently for large buffers. This lock is not
+	 * increase contention for the alloc mutex if clear_on_free
+	 * is used frequently for large buffers. The mutex is not
 	 * needed for correctness here.
 	 */
 	if (buffer->clear_on_free) {
 		binder_alloc_clear_buf(alloc, buffer);
 		buffer->clear_on_free = false;
 	}
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	binder_free_buf_locked(alloc, buffer);
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 }
 
 /**
@@ -816,7 +896,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 {
 	struct binder_buffer *buffer;
 	const char *failure_string;
-	int ret, i;
+	int ret;
 
 	if (unlikely(vma->vm_mm != alloc->mm)) {
 		ret = -EINVAL;
@@ -834,22 +914,17 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 				   SZ_4M);
 	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->buffer = vma->vm_start;
+	alloc->vm_start = vma->vm_start;
 
 	alloc->pages = kvcalloc(alloc->buffer_size / PAGE_SIZE,
 				sizeof(alloc->pages[0]),
 				GFP_KERNEL);
-	if (alloc->pages == NULL) {
+	if (!alloc->pages) {
 		ret = -ENOMEM;
 		failure_string = "alloc page array";
 		goto err_alloc_pages_failed;
 	}
 
-	for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-		alloc->pages[i].alloc = alloc;
-		INIT_LIST_HEAD(&alloc->pages[i].lru);
-	}
-
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer) {
 		ret = -ENOMEM;
@@ -857,14 +932,14 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		goto err_alloc_buf_struct_failed;
 	}
 
-	buffer->user_data = alloc->buffer;
+	buffer->user_data = alloc->vm_start;
 	list_add(&buffer->entry, &alloc->buffers);
 	buffer->free = 1;
 	binder_insert_free_buffer(alloc, buffer);
 	alloc->free_async_space = alloc->buffer_size / 2;
 
 	/* Signal binder_alloc is fully initialized */
-	binder_alloc_set_vma(alloc, vma);
+	binder_alloc_set_mapped(alloc, true);
 
 	return 0;
 
@@ -872,7 +947,7 @@ err_alloc_buf_struct_failed:
 	kvfree(alloc->pages);
 	alloc->pages = NULL;
 err_alloc_pages_failed:
-	alloc->buffer = 0;
+	alloc->vm_start = 0;
 	mutex_lock(&binder_alloc_mmap_lock);
 	alloc->buffer_size = 0;
 err_already_mapped:
@@ -893,8 +968,8 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 	struct binder_buffer *buffer;
 
 	buffers = 0;
-	spin_lock(&alloc->lock);
-	BUG_ON(alloc->vma);
+	mutex_lock(&alloc->mutex);
+	BUG_ON(alloc->mapped);
 
 	while ((n = rb_first(&alloc->allocated_buffers))) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
@@ -925,22 +1000,26 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)
 		int i;
 
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
+			struct page *page;
 			bool on_lru;
 
-			if (!alloc->pages[i].page_ptr)
+			page = binder_get_installed_page(alloc, i);
+			if (!page)
 				continue;
 
-			on_lru = list_lru_del_obj(&binder_freelist,
-						  &alloc->pages[i].lru);
+			on_lru = list_lru_del(&binder_freelist,
+					      page_to_lru(page),
+					      page_to_nid(page),
+					      NULL);
 			binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC,
 				     "%s: %d: page %d %s\n",
 				     __func__, alloc->pid, i,
 				     on_lru ? "on lru" : "active");
-			__free_page(alloc->pages[i].page_ptr);
+			binder_free_page(page);
 			page_count++;
 		}
 	}
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 	kvfree(alloc->pages);
 	if (alloc->mm)
 		mmdrop(alloc->mm);
@@ -964,17 +1043,17 @@ void binder_alloc_print_allocated(struct seq_file *m,
 	struct binder_buffer *buffer;
 	struct rb_node *n;
 
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	for (n = rb_first(&alloc->allocated_buffers); n; n = rb_next(n)) {
 		buffer = rb_entry(n, struct binder_buffer, rb_node);
 		seq_printf(m, "  buffer %d: %lx size %zd:%zd:%zd %s\n",
 			   buffer->debug_id,
-			   buffer->user_data - alloc->buffer,
+			   buffer->user_data - alloc->vm_start,
 			   buffer->data_size, buffer->offsets_size,
 			   buffer->extra_buffers_size,
 			   buffer->transaction ? "active" : "delivered");
 	}
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 }
 
 /**
@@ -985,29 +1064,29 @@ void binder_alloc_print_allocated(struct seq_file *m,
 void binder_alloc_print_pages(struct seq_file *m,
 			      struct binder_alloc *alloc)
 {
-	struct binder_lru_page *page;
+	struct page *page;
 	int i;
 	int active = 0;
 	int lru = 0;
 	int free = 0;
 
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	/*
 	 * Make sure the binder_alloc is fully initialized, otherwise we might
 	 * read inconsistent state.
 	 */
-	if (binder_alloc_get_vma(alloc) != NULL) {
+	if (binder_alloc_is_mapped(alloc)) {
 		for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) {
-			page = &alloc->pages[i];
-			if (!page->page_ptr)
+			page = binder_get_installed_page(alloc, i);
+			if (!page)
 				free++;
-			else if (list_empty(&page->lru))
+			else if (list_empty(page_to_lru(page)))
 				active++;
 			else
 				lru++;
 		}
 	}
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 	seq_printf(m, "  pages: %d:%d:%d\n", active, lru, free);
 	seq_printf(m, "  pages high watermark: %zu\n", alloc->pages_high);
 }
@@ -1023,10 +1102,10 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
 	struct rb_node *n;
 	int count = 0;
 
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	for (n = rb_first(&alloc->allocated_buffers); n != NULL; n = rb_next(n))
 		count++;
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 	return count;
 }
 
@@ -1036,12 +1115,12 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc)
  * @alloc: binder_alloc for this proc
  *
  * Called from binder_vma_close() when releasing address space.
- * Clears alloc->vma to prevent new incoming transactions from
+ * Clears alloc->mapped to prevent new incoming transactions from
  * allocating more buffers.
  */
 void binder_alloc_vma_close(struct binder_alloc *alloc)
 {
-	binder_alloc_set_vma(alloc, NULL);
+	binder_alloc_set_mapped(alloc, false);
 }
 
 /**
@@ -1058,39 +1137,50 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 				       void *cb_arg)
 	__must_hold(&lru->lock)
 {
-	struct binder_lru_page *page = container_of(item, typeof(*page), lru);
-	struct binder_alloc *alloc = page->alloc;
+	struct binder_shrinker_mdata *mdata = container_of(item, typeof(*mdata), lru);
+	struct binder_alloc *alloc = mdata->alloc;
 	struct mm_struct *mm = alloc->mm;
 	struct vm_area_struct *vma;
 	struct page *page_to_free;
 	unsigned long page_addr;
+	int mm_locked = 0;
 	size_t index;
 
 	if (!mmget_not_zero(mm))
 		goto err_mmget;
-	if (!mmap_read_trylock(mm))
-		goto err_mmap_read_lock_failed;
-	if (!spin_trylock(&alloc->lock))
-		goto err_get_alloc_lock_failed;
-	if (!page->page_ptr)
-		goto err_page_already_freed;
-
-	index = page - alloc->pages;
-	page_addr = alloc->buffer + index * PAGE_SIZE;
-
-	vma = vma_lookup(mm, page_addr);
-	if (vma && vma != binder_alloc_get_vma(alloc))
+
+	index = mdata->page_index;
+	page_addr = alloc->vm_start + index * PAGE_SIZE;
+
+	/* attempt per-vma lock first */
+	vma = lock_vma_under_rcu(mm, page_addr);
+	if (!vma) {
+		/* fall back to mmap_lock */
+		if (!mmap_read_trylock(mm))
+			goto err_mmap_read_lock_failed;
+		mm_locked = 1;
+		vma = vma_lookup(mm, page_addr);
+	}
+
+	if (!mutex_trylock(&alloc->mutex))
+		goto err_get_alloc_mutex_failed;
+
+	/*
+	 * Since a binder_alloc can only be mapped once, we ensure
+	 * the vma corresponds to this mapping by checking whether
+	 * the binder_alloc is still mapped.
+	 */
+	if (vma && !binder_alloc_is_mapped(alloc))
 		goto err_invalid_vma;
 
 	trace_binder_unmap_kernel_start(alloc, index);
 
-	page_to_free = page->page_ptr;
-	page->page_ptr = NULL;
+	page_to_free = alloc->pages[index];
+	binder_set_installed_page(alloc, index, NULL);
 
 	trace_binder_unmap_kernel_end(alloc, index);
 
 	list_lru_isolate(lru, item);
-	spin_unlock(&alloc->lock);
 	spin_unlock(&lru->lock);
 
 	if (vma) {
@@ -1101,17 +1191,23 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		trace_binder_unmap_user_end(alloc, index);
 	}
 
-	mmap_read_unlock(mm);
+	mutex_unlock(&alloc->mutex);
+	if (mm_locked)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 	mmput_async(mm);
-	__free_page(page_to_free);
+	binder_free_page(page_to_free);
 
 	return LRU_REMOVED_RETRY;
 
 err_invalid_vma:
-err_page_already_freed:
-	spin_unlock(&alloc->lock);
-err_get_alloc_lock_failed:
-	mmap_read_unlock(mm);
+	mutex_unlock(&alloc->mutex);
+err_get_alloc_mutex_failed:
+	if (mm_locked)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 err_mmap_read_lock_failed:
 	mmput_async(mm);
 err_mmget:
@@ -1145,7 +1241,7 @@ void binder_alloc_init(struct binder_alloc *alloc)
 	alloc->pid = current->group_leader->pid;
 	alloc->mm = current->mm;
 	mmgrab(alloc->mm);
-	spin_lock_init(&alloc->lock);
+	mutex_init(&alloc->mutex);
 	INIT_LIST_HEAD(&alloc->buffers);
 }
 
diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h
index c02c8ebcb466..feecd7414241 100644
--- a/drivers/android/binder_alloc.h
+++ b/drivers/android/binder_alloc.h
@@ -9,7 +9,7 @@
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <linux/mm.h>
-#include <linux/spinlock.h>
+#include <linux/rtmutex.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/list_lru.h>
@@ -59,34 +59,43 @@ struct binder_buffer {
 };
 
 /**
- * struct binder_lru_page - page object used for binder shrinker
- * @page_ptr: pointer to physical page in mmap'd space
- * @lru:      entry in binder_freelist
- * @alloc:    binder_alloc for a proc
+ * struct binder_shrinker_mdata - binder metadata used to reclaim pages
+ * @lru:         LRU entry in binder_freelist
+ * @alloc:       binder_alloc owning the page to reclaim
+ * @page_index:  offset in @alloc->pages[] into the page to reclaim
  */
-struct binder_lru_page {
+struct binder_shrinker_mdata {
 	struct list_head lru;
-	struct page *page_ptr;
 	struct binder_alloc *alloc;
+	unsigned long page_index;
 };
 
+static inline struct list_head *page_to_lru(struct page *p)
+{
+	struct binder_shrinker_mdata *mdata;
+
+	mdata = (struct binder_shrinker_mdata *)page_private(p);
+
+	return &mdata->lru;
+}
+
 /**
  * struct binder_alloc - per-binder proc state for binder allocator
- * @lock:               protects binder_alloc fields
- * @vma:                vm_area_struct passed to mmap_handler
- *                      (invariant after mmap)
+ * @mutex:              protects binder_alloc fields
  * @mm:                 copy of task->mm (invariant after open)
- * @buffer:             base of per-proc address space mapped via mmap
+ * @vm_start:           base of per-proc address space mapped via mmap
  * @buffers:            list of all buffers for this proc
  * @free_buffers:       rb tree of buffers available for allocation
  *                      sorted by size
  * @allocated_buffers:  rb tree of allocated buffers sorted by address
  * @free_async_space:   VA space available for async buffers. This is
  *                      initialized at mmap time to 1/2 the full VA space
- * @pages:              array of binder_lru_page
+ * @pages:              array of struct page *
  * @buffer_size:        size of address space specified via mmap
  * @pid:                pid for associated binder_proc (invariant after init)
  * @pages_high:         high watermark of offset in @pages
+ * @mapped:             whether the vm area is mapped, each binder instance is
+ *                      allowed a single mapping throughout its lifetime
  * @oneway_spam_detected: %true if oneway spam detection fired, clear that
  * flag once the async buffer has returned to a healthy state
  *
@@ -96,18 +105,18 @@ struct binder_lru_page {
  * struct binder_buffer objects used to track the user buffers
  */
 struct binder_alloc {
-	spinlock_t lock;
-	struct vm_area_struct *vma;
+	struct mutex mutex;
 	struct mm_struct *mm;
-	unsigned long buffer;
+	unsigned long vm_start;
 	struct list_head buffers;
 	struct rb_root free_buffers;
 	struct rb_root allocated_buffers;
 	size_t free_async_space;
-	struct binder_lru_page *pages;
+	struct page **pages;
 	size_t buffer_size;
 	int pid;
 	size_t pages_high;
+	bool mapped;
 	bool oneway_spam_detected;
 };
 
@@ -153,9 +162,9 @@ binder_alloc_get_free_async_space(struct binder_alloc *alloc)
 {
 	size_t free_async_space;
 
-	spin_lock(&alloc->lock);
+	mutex_lock(&alloc->mutex);
 	free_async_space = alloc->free_async_space;
-	spin_unlock(&alloc->lock);
+	mutex_unlock(&alloc->mutex);
 	return free_async_space;
 }
 
diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c
index 81442fe20a69..c88735c54848 100644
--- a/drivers/android/binder_alloc_selftest.c
+++ b/drivers/android/binder_alloc_selftest.c
@@ -104,11 +104,11 @@ static bool check_buffer_pages_allocated(struct binder_alloc *alloc,
 	end = PAGE_ALIGN(buffer->user_data + size);
 	page_addr = buffer->user_data;
 	for (; page_addr < end; page_addr += PAGE_SIZE) {
-		page_index = (page_addr - alloc->buffer) / PAGE_SIZE;
-		if (!alloc->pages[page_index].page_ptr ||
-		    !list_empty(&alloc->pages[page_index].lru)) {
+		page_index = (page_addr - alloc->vm_start) / PAGE_SIZE;
+		if (!alloc->pages[page_index] ||
+		    !list_empty(page_to_lru(alloc->pages[page_index]))) {
 			pr_err("expect alloc but is %s at page index %d\n",
-			       alloc->pages[page_index].page_ptr ?
+			       alloc->pages[page_index] ?
 			       "lru" : "free", page_index);
 			return false;
 		}
@@ -148,10 +148,10 @@ static void binder_selftest_free_buf(struct binder_alloc *alloc,
 		 * if binder shrinker ran during binder_alloc_free_buf
 		 * calls above.
 		 */
-		if (list_empty(&alloc->pages[i].lru)) {
+		if (list_empty(page_to_lru(alloc->pages[i]))) {
 			pr_err_size_seq(sizes, seq);
 			pr_err("expect lru but is %s at page index %d\n",
-			       alloc->pages[i].page_ptr ? "alloc" : "free", i);
+			       alloc->pages[i] ? "alloc" : "free", i);
 			binder_selftest_failures++;
 		}
 	}
@@ -168,9 +168,9 @@ static void binder_selftest_free_page(struct binder_alloc *alloc)
 	}
 
 	for (i = 0; i < (alloc->buffer_size / PAGE_SIZE); i++) {
-		if (alloc->pages[i].page_ptr) {
+		if (alloc->pages[i]) {
 			pr_err("expect free but is %s at page index %d\n",
-			       list_empty(&alloc->pages[i].lru) ?
+			       list_empty(page_to_lru(alloc->pages[i])) ?
 			       "alloc" : "lru", i);
 			binder_selftest_failures++;
 		}
@@ -291,7 +291,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc)
 	if (!binder_selftest_run)
 		return;
 	mutex_lock(&binder_selftest_lock);
-	if (!binder_selftest_run || !alloc->vma)
+	if (!binder_selftest_run || !alloc->mapped)
 		goto done;
 	pr_info("STARTED\n");
 	binder_selftest_alloc_offset(alloc, end_offset, 0);
diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h
index f8d6be682f23..e4eb8357989c 100644
--- a/drivers/android/binder_internal.h
+++ b/drivers/android/binder_internal.h
@@ -25,8 +25,7 @@ struct binder_context {
 
 /**
  * struct binder_device - information about a binder device node
- * @hlist:          list of binder devices (only used for devices requested via
- *                  CONFIG_ANDROID_BINDER_DEVICES)
+ * @hlist:          list of binder devices
  * @miscdev:        information about a binder character device node
  * @context:        binder context information
  * @binderfs_inode: This is the inode of the root dentry of the super block
@@ -582,4 +581,12 @@ struct binder_object {
 	};
 };
 
+/**
+ * Add a binder device to binder_devices
+ * @device: the new binder device to add to the global list
+ *
+ * Not reentrant as the list is not protected by any locks
+ */
+void binder_add_device(struct binder_device *device);
+
 #endif /* _LINUX_BINDER_INTERNAL_H */
diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h
index fe38c6fc65d0..16de1b9e72f7 100644
--- a/drivers/android/binder_trace.h
+++ b/drivers/android/binder_trace.h
@@ -328,7 +328,7 @@ TRACE_EVENT(binder_update_page_range,
 	TP_fast_assign(
 		__entry->proc = alloc->pid;
 		__entry->allocate = allocate;
-		__entry->offset = start - alloc->buffer;
+		__entry->offset = start - alloc->vm_start;
 		__entry->size = end - start;
 	),
 	TP_printk("proc=%d allocate=%d offset=%zu size=%zu",
diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index ad1fa7abc323..bc6bae76ccaf 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -207,6 +207,8 @@ static int binderfs_binder_device_create(struct inode *ref_inode,
 	fsnotify_create(root->d_inode, dentry);
 	inode_unlock(d_inode(root));
 
+	binder_add_device(device);
+
 	return 0;
 
 err:
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 06781bdde0d2..8e895ae45c86 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -328,7 +328,7 @@ struct ahci_port_priv {
 struct ahci_host_priv {
 	/* Input fields */
 	unsigned int		flags;		/* AHCI_HFLAG_* */
-	u32			mask_port_map;	/* mask out particular bits */
+	u32			mask_port_map;	/* Mask of valid ports */
 
 	void __iomem *		mmio;		/* bus-independent mem map */
 	u32			cap;		/* cap to use */
@@ -379,6 +379,17 @@ struct ahci_host_priv {
 						  int port);
 };
 
+/*
+ * Return true if a port should be ignored because it is excluded from
+ * the host port map.
+ */
+static inline bool ahci_ignore_port(struct ahci_host_priv *hpriv,
+				    unsigned int portid)
+{
+	return portid >= hpriv->nports ||
+		!(hpriv->mask_port_map & (1 << portid));
+}
+
 extern int ahci_ignore_sss;
 
 extern const struct attribute_group *ahci_shost_groups[];
@@ -397,7 +408,7 @@ extern const struct attribute_group *ahci_sdev_groups[];
 	.sdev_groups		= ahci_sdev_groups,			\
 	.change_queue_depth     = ata_scsi_change_queue_depth,		\
 	.tag_alloc_policy_rr	= true,					\
-	.device_configure	= ata_scsi_device_configure
+	.sdev_configure		= ata_scsi_sdev_configure
 
 extern struct ata_port_operations ahci_ops;
 extern struct ata_port_operations ahci_platform_ops;
diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c
index ef569eae4ce4..29be74fedcf0 100644
--- a/drivers/ata/ahci_brcm.c
+++ b/drivers/ata/ahci_brcm.c
@@ -288,6 +288,9 @@ static unsigned int brcm_ahci_read_id(struct ata_device *dev,
 
 	/* Re-initialize and calibrate the PHY */
 	for (i = 0; i < hpriv->nports; i++) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		rc = phy_init(hpriv->phys[i]);
 		if (rc)
 			goto disable_phys;
diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c
index 1ec35778903d..2d6a08c23d6a 100644
--- a/drivers/ata/ahci_ceva.c
+++ b/drivers/ata/ahci_ceva.c
@@ -206,6 +206,9 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 		goto disable_clks;
 
 	for (i = 0; i < hpriv->nports; i++) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		rc = phy_init(hpriv->phys[i]);
 		if (rc)
 			goto disable_rsts;
@@ -215,6 +218,9 @@ static int ceva_ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 	ahci_platform_deassert_rsts(hpriv);
 
 	for (i = 0; i < hpriv->nports; i++) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		rc = phy_power_on(hpriv->phys[i]);
 		if (rc) {
 			phy_exit(hpriv->phys[i]);
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
index 6b9b4a1dfa15..4336c8a6e208 100644
--- a/drivers/ata/ahci_st.c
+++ b/drivers/ata/ahci_st.c
@@ -176,7 +176,6 @@ static int st_ahci_probe(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int st_ahci_suspend(struct device *dev)
 {
 	struct ata_host *host = dev_get_drvdata(dev);
@@ -221,9 +220,8 @@ static int st_ahci_resume(struct device *dev)
 
 	return ahci_platform_resume_host(dev);
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(st_ahci_pm_ops, st_ahci_suspend, st_ahci_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(st_ahci_pm_ops, st_ahci_suspend, st_ahci_resume);
 
 static const struct of_device_id st_ahci_match[] = {
 	{ .compatible = "st,ahci", },
@@ -234,7 +232,7 @@ MODULE_DEVICE_TABLE(of, st_ahci_match);
 static struct platform_driver st_ahci_driver = {
 	.driver = {
 		.name = DRV_NAME,
-		.pm = &st_ahci_pm_ops,
+		.pm = pm_sleep_ptr(&st_ahci_pm_ops),
 		.of_match_table = st_ahci_match,
 	},
 	.probe = st_ahci_probe,
diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c
index 2f57ec00ab82..e70b6c089cf1 100644
--- a/drivers/ata/ata_generic.c
+++ b/drivers/ata/ata_generic.c
@@ -209,7 +209,7 @@ static int ata_generic_init_one(struct pci_dev *dev, const struct pci_device_id
 	return ata_pci_bmdma_init_one(dev, ppi, &generic_sht, (void *)id, 0);
 }
 
-static struct pci_device_id ata_generic[] = {
+static const struct pci_device_id ata_generic[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_PCTECH, PCI_DEVICE_ID_PCTECH_SAMURAI_IDE), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_HOLTEK, PCI_DEVICE_ID_HOLTEK_6565), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_UMC,    PCI_DEVICE_ID_UMC_UM8673F), },
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 7a8064520a35..53b2c7719dc5 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -49,6 +49,9 @@ int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
 	int rc, i;
 
 	for (i = 0; i < hpriv->nports; i++) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		rc = phy_init(hpriv->phys[i]);
 		if (rc)
 			goto disable_phys;
@@ -70,6 +73,9 @@ int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
 
 disable_phys:
 	while (--i >= 0) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		phy_power_off(hpriv->phys[i]);
 		phy_exit(hpriv->phys[i]);
 	}
@@ -88,6 +94,9 @@ void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
 	int i;
 
 	for (i = 0; i < hpriv->nports; i++) {
+		if (ahci_ignore_port(hpriv, i))
+			continue;
+
 		phy_power_off(hpriv->phys[i]);
 		phy_exit(hpriv->phys[i]);
 	}
@@ -432,6 +441,20 @@ static int ahci_platform_get_firmware(struct ahci_host_priv *hpriv,
 	return 0;
 }
 
+static u32 ahci_platform_find_max_port_id(struct device *dev)
+{
+	u32 max_port = 0;
+
+	for_each_child_of_node_scoped(dev->of_node, child) {
+		u32 port;
+
+		if (!of_property_read_u32(child, "reg", &port))
+			max_port = max(max_port, port);
+	}
+
+	return max_port;
+}
+
 /**
  * ahci_platform_get_resources - Get platform resources
  * @pdev: platform device to get resources for
@@ -458,6 +481,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	struct ahci_host_priv *hpriv;
 	u32 mask_port_map = 0;
+	u32 max_port;
 
 	if (!devres_open_group(dev, NULL, GFP_KERNEL))
 		return ERR_PTR(-ENOMEM);
@@ -549,15 +573,17 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		goto err_out;
 	}
 
+	/* find maximum port id for allocating structures */
+	max_port = ahci_platform_find_max_port_id(dev);
 	/*
-	 * If no sub-node was found, we still need to set nports to
-	 * one in order to be able to use the
+	 * Set nports according to maximum port id. Clamp at
+	 * AHCI_MAX_PORTS, warning message for invalid port id
+	 * is generated later.
+	 * When DT has no sub-nodes max_port is 0, nports is 1,
+	 * in order to be able to use the
 	 * ahci_platform_[en|dis]able_[phys|regulators] functions.
 	 */
-	if (child_nodes)
-		hpriv->nports = child_nodes;
-	else
-		hpriv->nports = 1;
+	hpriv->nports = min(AHCI_MAX_PORTS, max_port + 1);
 
 	hpriv->phys = devm_kcalloc(dev, hpriv->nports, sizeof(*hpriv->phys), GFP_KERNEL);
 	if (!hpriv->phys) {
@@ -625,6 +651,8 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		 * If no sub-node was found, keep this for device tree
 		 * compatibility
 		 */
+		hpriv->mask_port_map |= BIT(0);
+
 		rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node);
 		if (rc)
 			goto err_out;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c085dd81ebe7..63ec2f218431 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4143,6 +4143,10 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	{ "Samsung SSD 860*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
 						ATA_QUIRK_NO_NCQ_ON_ATI },
+	{ "Samsung SSD 870 QVO*",	NULL,	ATA_QUIRK_NO_NCQ_TRIM |
+						ATA_QUIRK_ZERO_AFTER_TRIM |
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NOLPM },
 	{ "Samsung SSD 870*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
 						ATA_QUIRK_NO_NCQ_ON_ATI },
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 9c76fb1ad2ec..ba300cc0a3a3 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1313,7 +1313,7 @@ int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth)
 EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth);
 
 /**
- *	ata_sas_device_configure - Default device_configure routine for libata
+ *	ata_sas_sdev_configure - Default sdev_configure routine for libata
  *				   devices
  *	@sdev: SCSI device to configure
  *	@lim: queue limits
@@ -1323,14 +1323,14 @@ EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth);
  *	Zero.
  */
 
-int ata_sas_device_configure(struct scsi_device *sdev, struct queue_limits *lim,
-		struct ata_port *ap)
+int ata_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim,
+			   struct ata_port *ap)
 {
 	ata_scsi_sdev_config(sdev);
 
 	return ata_scsi_dev_config(sdev, lim, ap->link.device);
 }
-EXPORT_SYMBOL_GPL(ata_sas_device_configure);
+EXPORT_SYMBOL_GPL(ata_sas_sdev_configure);
 
 /**
  *	ata_sas_queuecmd - Issue SCSI cdb to libata-managed device
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2ce5befd2242..2796c0da8257 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1133,7 +1133,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim,
 }
 
 /**
- *	ata_scsi_slave_alloc - Early setup of SCSI device
+ *	ata_scsi_sdev_init - Early setup of SCSI device
  *	@sdev: SCSI device to examine
  *
  *	This is called from scsi_alloc_sdev() when the scsi device
@@ -1143,7 +1143,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct queue_limits *lim,
  *	Defined by SCSI layer.  We don't really care.
  */
 
-int ata_scsi_slave_alloc(struct scsi_device *sdev)
+int ata_scsi_sdev_init(struct scsi_device *sdev)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct device_link *link;
@@ -1166,10 +1166,10 @@ int ata_scsi_slave_alloc(struct scsi_device *sdev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc);
+EXPORT_SYMBOL_GPL(ata_scsi_sdev_init);
 
 /**
- *	ata_scsi_device_configure - Set SCSI device attributes
+ *	ata_scsi_sdev_configure - Set SCSI device attributes
  *	@sdev: SCSI device to examine
  *	@lim: queue limits
  *
@@ -1181,8 +1181,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_slave_alloc);
  *	Defined by SCSI layer.  We don't really care.
  */
 
-int ata_scsi_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+int ata_scsi_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct ata_device *dev = __ata_scsi_find_dev(ap, sdev);
@@ -1192,10 +1191,10 @@ int ata_scsi_device_configure(struct scsi_device *sdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ata_scsi_device_configure);
+EXPORT_SYMBOL_GPL(ata_scsi_sdev_configure);
 
 /**
- *	ata_scsi_slave_destroy - SCSI device is about to be destroyed
+ *	ata_scsi_sdev_destroy - SCSI device is about to be destroyed
  *	@sdev: SCSI device to be destroyed
  *
  *	@sdev is about to be destroyed for hot/warm unplugging.  If
@@ -1208,7 +1207,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_device_configure);
  *	LOCKING:
  *	Defined by SCSI layer.  We don't really care.
  */
-void ata_scsi_slave_destroy(struct scsi_device *sdev)
+void ata_scsi_sdev_destroy(struct scsi_device *sdev)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	unsigned long flags;
@@ -1228,7 +1227,7 @@ void ata_scsi_slave_destroy(struct scsi_device *sdev)
 
 	kfree(sdev->dma_drain_buf);
 }
-EXPORT_SYMBOL_GPL(ata_scsi_slave_destroy);
+EXPORT_SYMBOL_GPL(ata_scsi_sdev_destroy);
 
 /**
  *	ata_scsi_start_stop_xlat - Translate SCSI START STOP UNIT command
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 67f277e1c3bf..5a46c066abc3 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -601,7 +601,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	struct page *page;
-	unsigned int offset;
+	unsigned int offset, count;
 
 	if (!qc->cursg) {
 		qc->curbytes = qc->nbytes;
@@ -617,25 +617,27 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
 	page = nth_page(page, (offset >> PAGE_SHIFT));
 	offset %= PAGE_SIZE;
 
-	trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size);
+	/* don't overrun current sg */
+	count = min(qc->cursg->length - qc->cursg_ofs, qc->sect_size);
+
+	trace_ata_sff_pio_transfer_data(qc, offset, count);
 
 	/*
 	 * Split the transfer when it splits a page boundary.  Note that the
 	 * split still has to be dword aligned like all ATA data transfers.
 	 */
 	WARN_ON_ONCE(offset % 4);
-	if (offset + qc->sect_size > PAGE_SIZE) {
+	if (offset + count > PAGE_SIZE) {
 		unsigned int split_len = PAGE_SIZE - offset;
 
 		ata_pio_xfer(qc, page, offset, split_len);
-		ata_pio_xfer(qc, nth_page(page, 1), 0,
-			     qc->sect_size - split_len);
+		ata_pio_xfer(qc, nth_page(page, 1), 0, count - split_len);
 	} else {
-		ata_pio_xfer(qc, page, offset, qc->sect_size);
+		ata_pio_xfer(qc, page, offset, count);
 	}
 
-	qc->curbytes += qc->sect_size;
-	qc->cursg_ofs += qc->sect_size;
+	qc->curbytes += count;
+	qc->cursg_ofs += count;
 
 	if (qc->cursg_ofs == qc->cursg->length) {
 		qc->cursg = sg_next(qc->cursg);
diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c
index aaef5924f636..308f86f9e2f0 100644
--- a/drivers/ata/pata_atp867x.c
+++ b/drivers/ata/pata_atp867x.c
@@ -525,7 +525,7 @@ static int atp867x_reinit_one(struct pci_dev *pdev)
 }
 #endif
 
-static struct pci_device_id atp867x_pci_tbl[] = {
+static const struct pci_device_id atp867x_pci_tbl[] = {
 	{ PCI_VDEVICE(ARTOP, PCI_DEVICE_ID_ARTOP_ATP867A),	0 },
 	{ PCI_VDEVICE(ARTOP, PCI_DEVICE_ID_ARTOP_ATP867B),	0 },
 	{ },
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 4b01bb6880b0..fbf5f07ea357 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -812,8 +812,8 @@ static void pata_macio_reset_hw(struct pata_macio_priv *priv, int resume)
 /* Hook the standard slave config to fixup some HW related alignment
  * restrictions
  */
-static int pata_macio_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int pata_macio_sdev_configure(struct scsi_device *sdev,
+				     struct queue_limits *lim)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct pata_macio_priv *priv = ap->private_data;
@@ -822,7 +822,7 @@ static int pata_macio_device_configure(struct scsi_device *sdev,
 	int rc;
 
 	/* First call original */
-	rc = ata_scsi_device_configure(sdev, lim);
+	rc = ata_scsi_sdev_configure(sdev, lim);
 	if (rc)
 		return rc;
 
@@ -932,7 +932,7 @@ static const struct scsi_host_template pata_macio_sht = {
 	/* We may not need that strict one */
 	.dma_boundary		= ATA_DMA_BOUNDARY,
 	.max_segment_size	= PATA_MACIO_MAX_SEGMENT_SIZE,
-	.device_configure	= pata_macio_device_configure,
+	.sdev_configure		= pata_macio_sdev_configure,
 	.sdev_groups		= ata_common_sdev_groups,
 	.can_queue		= ATA_DEF_QUEUE,
 	.tag_alloc_policy_rr	= true,
diff --git a/drivers/ata/pata_piccolo.c b/drivers/ata/pata_piccolo.c
index ced906bf56be..beb53bd990be 100644
--- a/drivers/ata/pata_piccolo.c
+++ b/drivers/ata/pata_piccolo.c
@@ -97,7 +97,7 @@ static int ata_tosh_init_one(struct pci_dev *dev, const struct pci_device_id *id
 	return ata_pci_bmdma_init_one(dev, ppi, &tosh_sht, NULL, 0);
 }
 
-static struct pci_device_id ata_tosh[] = {
+static const struct pci_device_id ata_tosh[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_1), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_2),  },
 	{ PCI_DEVICE(PCI_VENDOR_ID_TOSHIBA,PCI_DEVICE_ID_TOSHIBA_PICCOLO_3),  },
diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c
index d040799bf9cb..530ee26b3012 100644
--- a/drivers/ata/sata_gemini.c
+++ b/drivers/ata/sata_gemini.c
@@ -11,7 +11,6 @@
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
 #include <linux/delay.h>
-#include <linux/reset.h>
 #include <linux/of.h>
 #include <linux/clk.h>
 #include <linux/io.h>
@@ -27,8 +26,6 @@
  * @muxmode: the current muxing mode
  * @ide_pins: if the device is using the plain IDE interface pins
  * @sata_bridge: if the device enables the SATA bridge
- * @sata0_reset: SATA0 reset handler
- * @sata1_reset: SATA1 reset handler
  * @sata0_pclk: SATA0 PCLK handler
  * @sata1_pclk: SATA1 PCLK handler
  */
@@ -38,8 +35,6 @@ struct sata_gemini {
 	enum gemini_muxmode muxmode;
 	bool ide_pins;
 	bool sata_bridge;
-	struct reset_control *sata0_reset;
-	struct reset_control *sata1_reset;
 	struct clk *sata0_pclk;
 	struct clk *sata1_pclk;
 };
@@ -224,18 +219,6 @@ void gemini_sata_stop_bridge(struct sata_gemini *sg, unsigned int bridge)
 }
 EXPORT_SYMBOL(gemini_sata_stop_bridge);
 
-int gemini_sata_reset_bridge(struct sata_gemini *sg,
-			     unsigned int bridge)
-{
-	if (bridge == 0)
-		reset_control_reset(sg->sata0_reset);
-	else
-		reset_control_reset(sg->sata1_reset);
-	msleep(10);
-	return gemini_sata_setup_bridge(sg, bridge);
-}
-EXPORT_SYMBOL(gemini_sata_reset_bridge);
-
 static int gemini_sata_bridge_init(struct sata_gemini *sg)
 {
 	struct device *dev = sg->dev;
@@ -265,21 +248,6 @@ static int gemini_sata_bridge_init(struct sata_gemini *sg)
 		return ret;
 	}
 
-	sg->sata0_reset = devm_reset_control_get_exclusive(dev, "sata0");
-	if (IS_ERR(sg->sata0_reset)) {
-		dev_err(dev, "no SATA0 reset controller\n");
-		clk_disable_unprepare(sg->sata1_pclk);
-		clk_disable_unprepare(sg->sata0_pclk);
-		return PTR_ERR(sg->sata0_reset);
-	}
-	sg->sata1_reset = devm_reset_control_get_exclusive(dev, "sata1");
-	if (IS_ERR(sg->sata1_reset)) {
-		dev_err(dev, "no SATA1 reset controller\n");
-		clk_disable_unprepare(sg->sata1_pclk);
-		clk_disable_unprepare(sg->sata0_pclk);
-		return PTR_ERR(sg->sata1_reset);
-	}
-
 	sata_id = readl(sg->base + GEMINI_SATA_ID);
 	sata_phy_id = readl(sg->base + GEMINI_SATA_PHY_ID);
 	sg->sata_bridge = true;
diff --git a/drivers/ata/sata_gemini.h b/drivers/ata/sata_gemini.h
index 6f6e691d6007..b6e4a5c86e01 100644
--- a/drivers/ata/sata_gemini.h
+++ b/drivers/ata/sata_gemini.h
@@ -17,6 +17,5 @@ bool gemini_sata_bridge_enabled(struct sata_gemini *sg, bool is_ata1);
 enum gemini_muxmode gemini_sata_get_muxmode(struct sata_gemini *sg);
 int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge);
 void gemini_sata_stop_bridge(struct sata_gemini *sg, unsigned int bridge);
-int gemini_sata_reset_bridge(struct sata_gemini *sg, unsigned int bridge);
 
 #endif
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 21c72650f9cc..bcbf96867f89 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -673,7 +673,7 @@ static const struct scsi_host_template mv6_sht = {
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth	= ata_scsi_change_queue_depth,
 	.tag_alloc_policy_rr	= true,
-	.device_configure	= ata_scsi_device_configure
+	.sdev_configure		= ata_scsi_sdev_configure
 };
 
 static struct ata_port_operations mv5_ops = {
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 823cce5ea1e9..f36e2915ccf1 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -296,8 +296,8 @@ static void nv_nf2_freeze(struct ata_port *ap);
 static void nv_nf2_thaw(struct ata_port *ap);
 static void nv_ck804_freeze(struct ata_port *ap);
 static void nv_ck804_thaw(struct ata_port *ap);
-static int nv_adma_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim);
+static int nv_adma_sdev_configure(struct scsi_device *sdev,
+				  struct queue_limits *lim);
 static int nv_adma_check_atapi_dma(struct ata_queued_cmd *qc);
 static enum ata_completion_errors nv_adma_qc_prep(struct ata_queued_cmd *qc);
 static unsigned int nv_adma_qc_issue(struct ata_queued_cmd *qc);
@@ -319,8 +319,8 @@ static void nv_adma_tf_read(struct ata_port *ap, struct ata_taskfile *tf);
 static void nv_mcp55_thaw(struct ata_port *ap);
 static void nv_mcp55_freeze(struct ata_port *ap);
 static void nv_swncq_error_handler(struct ata_port *ap);
-static int nv_swncq_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim);
+static int nv_swncq_sdev_configure(struct scsi_device *sdev,
+				   struct queue_limits *lim);
 static int nv_swncq_port_start(struct ata_port *ap);
 static enum ata_completion_errors nv_swncq_qc_prep(struct ata_queued_cmd *qc);
 static void nv_swncq_fill_sg(struct ata_queued_cmd *qc);
@@ -382,7 +382,7 @@ static const struct scsi_host_template nv_adma_sht = {
 	.can_queue		= NV_ADMA_MAX_CPBS,
 	.sg_tablesize		= NV_ADMA_SGTBL_TOTAL_LEN,
 	.dma_boundary		= NV_ADMA_DMA_BOUNDARY,
-	.device_configure	= nv_adma_device_configure,
+	.sdev_configure		= nv_adma_sdev_configure,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth     = ata_scsi_change_queue_depth,
 	.tag_alloc_policy_rr	= true,
@@ -393,7 +393,7 @@ static const struct scsi_host_template nv_swncq_sht = {
 	.can_queue		= ATA_MAX_QUEUE - 1,
 	.sg_tablesize		= LIBATA_MAX_PRD,
 	.dma_boundary		= ATA_DMA_BOUNDARY,
-	.device_configure	= nv_swncq_device_configure,
+	.sdev_configure		= nv_swncq_sdev_configure,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth     = ata_scsi_change_queue_depth,
 	.tag_alloc_policy_rr	= true,
@@ -663,8 +663,8 @@ static void nv_adma_mode(struct ata_port *ap)
 	pp->flags &= ~NV_ADMA_PORT_REGISTER_MODE;
 }
 
-static int nv_adma_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int nv_adma_sdev_configure(struct scsi_device *sdev,
+				  struct queue_limits *lim)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct nv_adma_port_priv *pp = ap->private_data;
@@ -676,7 +676,7 @@ static int nv_adma_device_configure(struct scsi_device *sdev,
 	int adma_enable;
 	u32 current_reg, new_reg, config_mask;
 
-	rc = ata_scsi_device_configure(sdev, lim);
+	rc = ata_scsi_sdev_configure(sdev, lim);
 
 	if (sdev->id >= ATA_MAX_DEVICES || sdev->channel || sdev->lun)
 		/* Not a proper libata device, ignore */
@@ -1871,8 +1871,8 @@ static void nv_swncq_host_init(struct ata_host *host)
 	writel(~0x0, mmio + NV_INT_STATUS_MCP55);
 }
 
-static int nv_swncq_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int nv_swncq_sdev_configure(struct scsi_device *sdev,
+				   struct queue_limits *lim)
 {
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
@@ -1882,7 +1882,7 @@ static int nv_swncq_device_configure(struct scsi_device *sdev,
 	u8 check_maxtor = 0;
 	unsigned char model_num[ATA_ID_PROD_LEN + 1];
 
-	rc = ata_scsi_device_configure(sdev, lim);
+	rc = ata_scsi_sdev_configure(sdev, lim);
 	if (sdev->id >= ATA_MAX_DEVICES || sdev->channel || sdev->lun)
 		/* Not a proper libata device, ignore */
 		return rc;
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index b0e22ab76f0e..87f4cde6a686 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -380,7 +380,7 @@ static const struct scsi_host_template sil24_sht = {
 	.dma_boundary		= ATA_DMA_BOUNDARY,
 	.sdev_groups		= ata_ncq_sdev_groups,
 	.change_queue_depth	= ata_scsi_change_queue_depth,
-	.device_configure	= ata_scsi_device_configure
+	.sdev_configure		= ata_scsi_sdev_configure
 };
 
 static struct ata_port_operations sil24_ops = {
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 657c93c38b0d..6b9e65a42cd2 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -354,7 +354,7 @@ static struct device *next_device(struct klist_iter *i)
  * count in the supplied callback.
  */
 int bus_for_each_dev(const struct bus_type *bus, struct device *start,
-		     void *data, int (*fn)(struct device *, void *))
+		     void *data, device_iter_t fn)
 {
 	struct subsys_private *sp = bus_to_subsys(bus);
 	struct klist_iter i;
@@ -402,9 +402,12 @@ struct device *bus_find_device(const struct bus_type *bus,
 
 	klist_iter_init_node(&sp->klist_devices, &i,
 			     (start ? &start->p->knode_bus : NULL));
-	while ((dev = next_device(&i)))
-		if (match(dev, data) && get_device(dev))
+	while ((dev = next_device(&i))) {
+		if (match(dev, data)) {
+			get_device(dev);
 			break;
+		}
+	}
 	klist_iter_exit(&i);
 	subsys_put(sp);
 	return dev;
diff --git a/drivers/base/class.c b/drivers/base/class.c
index 582b5a02a5c4..2526c57d924e 100644
--- a/drivers/base/class.c
+++ b/drivers/base/class.c
@@ -323,8 +323,12 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class,
 	struct subsys_private *sp = class_to_subsys(class);
 	struct klist_node *start_knode = NULL;
 
-	if (!sp)
+	memset(iter, 0, sizeof(*iter));
+	if (!sp) {
+		pr_crit("%s: class %p was not registered yet\n",
+			__func__, class);
 		return;
+	}
 
 	if (start)
 		start_knode = &start->p->knode_class;
@@ -351,6 +355,9 @@ struct device *class_dev_iter_next(struct class_dev_iter *iter)
 	struct klist_node *knode;
 	struct device *dev;
 
+	if (!iter->sp)
+		return NULL;
+
 	while (1) {
 		knode = klist_next(&iter->ki);
 		if (!knode)
@@ -395,7 +402,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_exit);
  * code.  There's no locking restriction.
  */
 int class_for_each_device(const struct class *class, const struct device *start,
-			  void *data, int (*fn)(struct device *, void *))
+			  void *data, device_iter_t fn)
 {
 	struct subsys_private *sp = class_to_subsys(class);
 	struct class_dev_iter iter;
@@ -594,30 +601,10 @@ EXPORT_SYMBOL_GPL(class_compat_unregister);
  *			      a bus device
  * @cls: the compatibility class
  * @dev: the target bus device
- * @device_link: an optional device to which a "device" link should be created
  */
-int class_compat_create_link(struct class_compat *cls, struct device *dev,
-			     struct device *device_link)
+int class_compat_create_link(struct class_compat *cls, struct device *dev)
 {
-	int error;
-
-	error = sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev));
-	if (error)
-		return error;
-
-	/*
-	 * Optionally add a "device" link (typically to the parent), as a
-	 * class device would have one and we want to provide as much
-	 * backwards compatibility as possible.
-	 */
-	if (device_link) {
-		error = sysfs_create_link(&dev->kobj, &device_link->kobj,
-					  "device");
-		if (error)
-			sysfs_remove_link(cls->kobj, dev_name(dev));
-	}
-
-	return error;
+	return sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev));
 }
 EXPORT_SYMBOL_GPL(class_compat_create_link);
 
@@ -626,14 +613,9 @@ EXPORT_SYMBOL_GPL(class_compat_create_link);
  *			      a bus device
  * @cls: the compatibility class
  * @dev: the target bus device
- * @device_link: an optional device to which a "device" link was previously
- * 		 created
  */
-void class_compat_remove_link(struct class_compat *cls, struct device *dev,
-			      struct device *device_link)
+void class_compat_remove_link(struct class_compat *cls, struct device *dev)
 {
-	if (device_link)
-		sysfs_remove_link(&dev->kobj, "device");
 	sysfs_remove_link(cls->kobj, dev_name(dev));
 }
 EXPORT_SYMBOL_GPL(class_compat_remove_link);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 94865c9d8adc..5a1f05198114 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -3980,7 +3980,7 @@ const char *device_get_devnode(const struct device *dev,
  * other than 0, we break out and return that value.
  */
 int device_for_each_child(struct device *parent, void *data,
-			  int (*fn)(struct device *dev, void *data))
+			  device_iter_t fn)
 {
 	struct klist_iter i;
 	struct device *child;
@@ -4010,7 +4010,7 @@ EXPORT_SYMBOL_GPL(device_for_each_child);
  * other than 0, we break out and return that value.
  */
 int device_for_each_child_reverse(struct device *parent, void *data,
-				  int (*fn)(struct device *dev, void *data))
+				  device_iter_t fn)
 {
 	struct klist_iter i;
 	struct device *child;
@@ -4043,14 +4043,14 @@ EXPORT_SYMBOL_GPL(device_for_each_child_reverse);
  * device_for_each_child_reverse_from();
  */
 int device_for_each_child_reverse_from(struct device *parent,
-				       struct device *from, const void *data,
-				       int (*fn)(struct device *, const void *))
+				       struct device *from, void *data,
+				       device_iter_t fn)
 {
 	struct klist_iter i;
 	struct device *child;
 	int error = 0;
 
-	if (!parent->p)
+	if (!parent || !parent->p)
 		return 0;
 
 	klist_iter_init_node(&parent->p->klist_children, &i,
@@ -4079,8 +4079,8 @@ EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from);
  *
  * NOTE: you will need to drop the reference with put_device() after use.
  */
-struct device *device_find_child(struct device *parent, void *data,
-				 int (*match)(struct device *dev, void *data))
+struct device *device_find_child(struct device *parent, const void *data,
+				 device_match_t match)
 {
 	struct klist_iter i;
 	struct device *child;
@@ -4089,62 +4089,17 @@ struct device *device_find_child(struct device *parent, void *data,
 		return NULL;
 
 	klist_iter_init(&parent->p->klist_children, &i);
-	while ((child = next_device(&i)))
-		if (match(child, data) && get_device(child))
+	while ((child = next_device(&i))) {
+		if (match(child, data)) {
+			get_device(child);
 			break;
+		}
+	}
 	klist_iter_exit(&i);
 	return child;
 }
 EXPORT_SYMBOL_GPL(device_find_child);
 
-/**
- * device_find_child_by_name - device iterator for locating a child device.
- * @parent: parent struct device
- * @name: name of the child device
- *
- * This is similar to the device_find_child() function above, but it
- * returns a reference to a device that has the name @name.
- *
- * NOTE: you will need to drop the reference with put_device() after use.
- */
-struct device *device_find_child_by_name(struct device *parent,
-					 const char *name)
-{
-	struct klist_iter i;
-	struct device *child;
-
-	if (!parent)
-		return NULL;
-
-	klist_iter_init(&parent->p->klist_children, &i);
-	while ((child = next_device(&i)))
-		if (sysfs_streq(dev_name(child), name) && get_device(child))
-			break;
-	klist_iter_exit(&i);
-	return child;
-}
-EXPORT_SYMBOL_GPL(device_find_child_by_name);
-
-static int match_any(struct device *dev, void *unused)
-{
-	return 1;
-}
-
-/**
- * device_find_any_child - device iterator for locating a child device, if any.
- * @parent: parent struct device
- *
- * This is similar to the device_find_child() function above, but it
- * returns a reference to a child device, if any.
- *
- * NOTE: you will need to drop the reference with put_device() after use.
- */
-struct device *device_find_any_child(struct device *parent)
-{
-	return device_find_child(parent, NULL, match_any);
-}
-EXPORT_SYMBOL_GPL(device_find_any_child);
-
 int __init devices_init(void)
 {
 	devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL);
@@ -5244,15 +5199,21 @@ int device_match_name(struct device *dev, const void *name)
 }
 EXPORT_SYMBOL_GPL(device_match_name);
 
+int device_match_type(struct device *dev, const void *type)
+{
+	return dev->type == type;
+}
+EXPORT_SYMBOL_GPL(device_match_type);
+
 int device_match_of_node(struct device *dev, const void *np)
 {
-	return dev->of_node == np;
+	return np && dev->of_node == np;
 }
 EXPORT_SYMBOL_GPL(device_match_of_node);
 
 int device_match_fwnode(struct device *dev, const void *fwnode)
 {
-	return dev_fwnode(dev) == fwnode;
+	return fwnode && dev_fwnode(dev) == fwnode;
 }
 EXPORT_SYMBOL_GPL(device_match_fwnode);
 
@@ -5264,13 +5225,13 @@ EXPORT_SYMBOL_GPL(device_match_devt);
 
 int device_match_acpi_dev(struct device *dev, const void *adev)
 {
-	return ACPI_COMPANION(dev) == adev;
+	return adev && ACPI_COMPANION(dev) == adev;
 }
 EXPORT_SYMBOL(device_match_acpi_dev);
 
 int device_match_acpi_handle(struct device *dev, const void *handle)
 {
-	return ACPI_HANDLE(dev) == handle;
+	return handle && ACPI_HANDLE(dev) == handle;
 }
 EXPORT_SYMBOL(device_match_acpi_handle);
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index fdaa24bb641a..a7e511849875 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -599,6 +599,7 @@ CPU_SHOW_VULN_FALLBACK(retbleed);
 CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow);
 CPU_SHOW_VULN_FALLBACK(gds);
 CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
+CPU_SHOW_VULN_FALLBACK(ghostwrite);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -614,6 +615,7 @@ static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
 static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL);
 static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
 static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL);
+static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -630,6 +632,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_spec_rstack_overflow.attr,
 	&dev_attr_gather_data_sampling.attr,
 	&dev_attr_reg_file_data_sampling.attr,
+	&dev_attr_ghostwrite.attr,
 	NULL
 };
 
diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c
index c795edad1b96..64840e5d5fcc 100644
--- a/drivers/base/devcoredump.c
+++ b/drivers/base/devcoredump.c
@@ -106,7 +106,7 @@ static void devcd_del(struct work_struct *wk)
 }
 
 static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr,
+			       const struct bin_attribute *bin_attr,
 			       char *buffer, loff_t offset, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -116,7 +116,7 @@ static ssize_t devcd_data_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buffer, loff_t offset, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -132,19 +132,15 @@ static ssize_t devcd_data_write(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute devcd_attr_data = {
-	.attr = { .name = "data", .mode = S_IRUSR | S_IWUSR, },
-	.size = 0,
-	.read = devcd_data_read,
-	.write = devcd_data_write,
-};
+static const struct bin_attribute devcd_attr_data =
+	__BIN_ATTR(data, 0600, devcd_data_read, devcd_data_write, 0);
 
-static struct bin_attribute *devcd_dev_bin_attrs[] = {
+static const struct bin_attribute *const devcd_dev_bin_attrs[] = {
 	&devcd_attr_data, NULL,
 };
 
 static const struct attribute_group devcd_dev_group = {
-	.bin_attrs = devcd_dev_bin_attrs,
+	.bin_attrs_new = devcd_dev_bin_attrs,
 };
 
 static const struct attribute_group *devcd_dev_groups[] = {
@@ -186,9 +182,9 @@ static ssize_t disabled_show(const struct class *class, const struct class_attri
  *             mutex_lock(&devcd->mutex);
  *
  *
- * In the above diagram, It looks like disabled_store() would be racing with parallely
+ * In the above diagram, it looks like disabled_store() would be racing with parallelly
  * running devcd_del() and result in memory abort while acquiring devcd->mutex which
- * is called after kfree of devcd memory  after dropping its last reference with
+ * is called after kfree of devcd memory after dropping its last reference with
  * put_device(). However, this will not happens as fn(dev, data) runs
  * with its own reference to device via klist_node so it is not its last reference.
  * so, above situation would not occur.
@@ -285,6 +281,8 @@ static void devcd_free_sgtable(void *data)
  * @offset: start copy from @offset@ bytes from the head of the data
  *	in the given scatterlist
  * @data_len: the length of the data in the sg_table
+ *
+ * Returns: the number of bytes copied
  */
 static ssize_t devcd_read_from_sgtable(char *buffer, loff_t offset,
 				       size_t buf_len, void *data,
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 2152eec0c135..93e7779ef21e 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -750,25 +750,38 @@ int __devm_add_action(struct device *dev, void (*action)(void *), void *data, co
 EXPORT_SYMBOL_GPL(__devm_add_action);
 
 /**
- * devm_remove_action() - removes previously added custom action
+ * devm_remove_action_nowarn() - removes previously added custom action
  * @dev: Device that owns the action
  * @action: Function implementing the action
  * @data: Pointer to data passed to @action implementation
  *
  * Removes instance of @action previously added by devm_add_action().
  * Both action and data should match one of the existing entries.
+ *
+ * In contrast to devm_remove_action(), this function does not WARN() if no
+ * entry could have been found.
+ *
+ * This should only be used if the action is contained in an object with
+ * independent lifetime management, e.g. the Devres rust abstraction.
+ *
+ * Causing the warning from regular driver code most likely indicates an abuse
+ * of the devres API.
+ *
+ * Returns: 0 on success, -ENOENT if no entry could have been found.
  */
-void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
+int devm_remove_action_nowarn(struct device *dev,
+			      void (*action)(void *),
+			      void *data)
 {
 	struct action_devres devres = {
 		.data = data,
 		.action = action,
 	};
 
-	WARN_ON(devres_destroy(dev, devm_action_release, devm_action_match,
-			       &devres));
+	return devres_destroy(dev, devm_action_release, devm_action_match,
+			      &devres);
 }
-EXPORT_SYMBOL_GPL(devm_remove_action);
+EXPORT_SYMBOL_GPL(devm_remove_action_nowarn);
 
 /**
  * devm_release_action() - release previously added custom action
diff --git a/drivers/base/driver.c b/drivers/base/driver.c
index b4eb5b89c4ee..8ab010ddf709 100644
--- a/drivers/base/driver.c
+++ b/drivers/base/driver.c
@@ -115,7 +115,7 @@ EXPORT_SYMBOL_GPL(driver_set_override);
  * Iterate over the @drv's list of devices calling @fn for each one.
  */
 int driver_for_each_device(struct device_driver *drv, struct device *start,
-			   void *data, int (*fn)(struct device *, void *))
+			   void *data, device_iter_t fn)
 {
 	struct klist_iter i;
 	struct device *dev;
@@ -160,9 +160,12 @@ struct device *driver_find_device(const struct device_driver *drv,
 
 	klist_iter_init_node(&drv->p->klist_devices, &i,
 			     (start ? &start->p->knode_driver : NULL));
-	while ((dev = next_device(&i)))
-		if (match(dev, data) && get_device(dev))
+	while ((dev = next_device(&i))) {
+		if (match(dev, data)) {
+			get_device(dev);
 			break;
+		}
+	}
 	klist_iter_exit(&i);
 	return dev;
 }
diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c
index ddb70e29eb42..c8afc501a8a4 100644
--- a/drivers/base/firmware_loader/fallback_table.c
+++ b/drivers/base/firmware_loader/fallback_table.c
@@ -25,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = {
 EXPORT_SYMBOL_NS_GPL(fw_fallback_config, "FIRMWARE_LOADER_PRIVATE");
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table firmware_config_table[] = {
+static const struct ctl_table firmware_config_table[] = {
 	{
 		.procname	= "force_sysfs_fallback",
 		.data		= &fw_fallback_config.force_sysfs_fallback,
diff --git a/drivers/base/firmware_loader/sysfs.c b/drivers/base/firmware_loader/sysfs.c
index c9c93b47d9a5..d254ceb56d84 100644
--- a/drivers/base/firmware_loader/sysfs.c
+++ b/drivers/base/firmware_loader/sysfs.c
@@ -259,7 +259,7 @@ static void firmware_rw(struct fw_priv *fw_priv, char *buffer,
 }
 
 static ssize_t firmware_data_read(struct file *filp, struct kobject *kobj,
-				  struct bin_attribute *bin_attr,
+				  const struct bin_attribute *bin_attr,
 				  char *buffer, loff_t offset, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -316,7 +316,7 @@ static int fw_realloc_pages(struct fw_sysfs *fw_sysfs, int min_size)
  *	the driver as a firmware image.
  **/
 static ssize_t firmware_data_write(struct file *filp, struct kobject *kobj,
-				   struct bin_attribute *bin_attr,
+				   const struct bin_attribute *bin_attr,
 				   char *buffer, loff_t offset, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -356,11 +356,11 @@ out:
 	return retval;
 }
 
-static struct bin_attribute firmware_attr_data = {
+static const struct bin_attribute firmware_attr_data = {
 	.attr = { .name = "data", .mode = 0644 },
 	.size = 0,
-	.read = firmware_data_read,
-	.write = firmware_data_write,
+	.read_new = firmware_data_read,
+	.write_new = firmware_data_write,
 };
 
 static struct attribute *fw_dev_attrs[] = {
@@ -374,14 +374,14 @@ static struct attribute *fw_dev_attrs[] = {
 	NULL
 };
 
-static struct bin_attribute *fw_dev_bin_attrs[] = {
+static const struct bin_attribute *const fw_dev_bin_attrs[] = {
 	&firmware_attr_data,
 	NULL
 };
 
 static const struct attribute_group fw_dev_attr_group = {
 	.attrs = fw_dev_attrs,
-	.bin_attrs = fw_dev_bin_attrs,
+	.bin_attrs_new = fw_dev_bin_attrs,
 #ifdef CONFIG_FW_UPLOAD
 	.is_visible = fw_upload_is_visible,
 #endif
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 67858eeb92ed..348c5dbbfa68 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -512,7 +512,7 @@ static ssize_t auto_online_blocks_show(struct device *dev,
 				       struct device_attribute *attr, char *buf)
 {
 	return sysfs_emit(buf, "%s\n",
-			  online_type_to_str[mhp_default_online_type]);
+			  online_type_to_str[mhp_get_default_online_type()]);
 }
 
 static ssize_t auto_online_blocks_store(struct device *dev,
@@ -524,7 +524,7 @@ static ssize_t auto_online_blocks_store(struct device *dev,
 	if (online_type < 0)
 		return -EINVAL;
 
-	mhp_default_online_type = online_type;
+	mhp_set_default_online_type(online_type);
 	return count;
 }
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index cbc9a7a75def..40e1d8d8a589 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -656,13 +656,15 @@ static void device_resume_noirq(struct device *dev, pm_message_t state, bool asy
 	 * so change its status accordingly.
 	 *
 	 * Otherwise, the device is going to be resumed, so set its PM-runtime
-	 * status to "active", but do that only if DPM_FLAG_SMART_SUSPEND is set
-	 * to avoid confusing drivers that don't use it.
+	 * status to "active" unless its power.set_active flag is clear, in
+	 * which case it is not necessary to update its PM-runtime status.
 	 */
-	if (skip_resume)
+	if (skip_resume) {
 		pm_runtime_set_suspended(dev);
-	else if (dev_pm_skip_suspend(dev))
+	} else if (dev->power.set_active) {
 		pm_runtime_set_active(dev);
+		dev->power.set_active = false;
+	}
 
 	if (dev->pm_domain) {
 		info = "noirq power domain ";
@@ -1278,8 +1280,14 @@ Skip:
 	      dev->power.may_skip_resume))
 		dev->power.must_resume = true;
 
-	if (dev->power.must_resume)
+	if (dev->power.must_resume) {
+		if (dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) {
+			dev->power.set_active = true;
+			if (dev->parent && !dev->parent->power.ignore_children)
+				dev->parent->power.set_active = true;
+		}
 		dpm_superior_set_must_resume(dev);
+	}
 
 Complete:
 	complete_all(&dev->power.completion);
diff --git a/drivers/base/test/Kconfig b/drivers/base/test/Kconfig
index 5c7fac80611c..2756870615cc 100644
--- a/drivers/base/test/Kconfig
+++ b/drivers/base/test/Kconfig
@@ -12,6 +12,7 @@ config TEST_ASYNC_DRIVER_PROBE
 config DM_KUNIT_TEST
 	tristate "KUnit Tests for the device model" if !KUNIT_ALL_TESTS
 	depends on KUNIT
+	default KUNIT_ALL_TESTS
 
 config DRIVER_PE_KUNIT_TEST
 	tristate "KUnit Tests for property entry API" if !KUNIT_ALL_TESTS
diff --git a/drivers/base/test/platform-device-test.c b/drivers/base/test/platform-device-test.c
index ea05b8785743..6355a2231b74 100644
--- a/drivers/base/test/platform-device-test.c
+++ b/drivers/base/test/platform-device-test.c
@@ -1,8 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <kunit/platform_device.h>
 #include <kunit/resource.h>
 
 #include <linux/device.h>
+#include <linux/device/bus.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 
 #define DEVICE_NAME "test"
@@ -217,7 +220,43 @@ static struct kunit_suite platform_device_devm_test_suite = {
 	.test_cases = platform_device_devm_tests,
 };
 
-kunit_test_suite(platform_device_devm_test_suite);
+static void platform_device_find_by_null_test(struct kunit *test)
+{
+	struct platform_device *pdev;
+	int ret;
+
+	pdev = kunit_platform_device_alloc(test, DEVICE_NAME, PLATFORM_DEVID_NONE);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pdev);
+
+	ret = kunit_platform_device_add(test, pdev);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	KUNIT_EXPECT_PTR_EQ(test, of_find_device_by_node(NULL), NULL);
+
+	KUNIT_EXPECT_PTR_EQ(test, bus_find_device_by_of_node(&platform_bus_type, NULL), NULL);
+	KUNIT_EXPECT_PTR_EQ(test, bus_find_device_by_fwnode(&platform_bus_type, NULL), NULL);
+	KUNIT_EXPECT_PTR_EQ(test, bus_find_device_by_acpi_dev(&platform_bus_type, NULL), NULL);
+
+	KUNIT_EXPECT_FALSE(test, device_match_of_node(&pdev->dev, NULL));
+	KUNIT_EXPECT_FALSE(test, device_match_fwnode(&pdev->dev, NULL));
+	KUNIT_EXPECT_FALSE(test, device_match_acpi_dev(&pdev->dev, NULL));
+	KUNIT_EXPECT_FALSE(test, device_match_acpi_handle(&pdev->dev, NULL));
+}
+
+static struct kunit_case platform_device_match_tests[] = {
+	KUNIT_CASE(platform_device_find_by_null_test),
+	{}
+};
+
+static struct kunit_suite platform_device_match_test_suite = {
+	.name = "platform-device-match",
+	.test_cases = platform_device_match_tests,
+};
+
+kunit_test_suites(
+	&platform_device_devm_test_suite,
+	&platform_device_match_test_suite,
+);
 
 MODULE_DESCRIPTION("Test module for platform devices");
 MODULE_AUTHOR("Maxime Ripard <mripard@kernel.org>");
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 3523dd82d7a0..4db7f6ce8ade 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -226,10 +226,11 @@ aoedev_downdev(struct aoedev *d)
 	/* fast fail all pending I/O */
 	if (d->blkq) {
 		/* UP is cleared, freeze+quiesce to insure all are errored */
-		blk_mq_freeze_queue(d->blkq);
+		unsigned int memflags = blk_mq_freeze_queue(d->blkq);
+
 		blk_mq_quiesce_queue(d->blkq);
 		blk_mq_unquiesce_queue(d->blkq);
-		blk_mq_unfreeze_queue(d->blkq);
+		blk_mq_unfreeze_queue(d->blkq, memflags);
 	}
 
 	if (d->gd)
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 110f9aca2667..a81ade622a01 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -746,6 +746,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
 	unsigned char	*p;
 	int sect, nsect;
 	unsigned long	flags;
+	unsigned int memflags;
 	int ret;
 
 	if (type) {
@@ -758,7 +759,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
 	}
 
 	q = unit[drive].disk[type]->queue;
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	local_irq_save(flags);
@@ -817,7 +818,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
 	ret = FormatError ? -EIO : 0;
 out:
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 	return ret;
 }
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1ec7417c7f00..c05fe27a96b6 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -586,6 +586,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 {
 	struct file *file = fget(arg);
 	struct file *old_file;
+	unsigned int memflags;
 	int error;
 	bool partscan;
 	bool is_loop;
@@ -623,14 +624,14 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 
 	/* and ... switch */
 	disk_force_media_change(lo->lo_disk);
-	blk_mq_freeze_queue(lo->lo_queue);
+	memflags = blk_mq_freeze_queue(lo->lo_queue);
 	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
 	lo->lo_backing_file = file;
 	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
 	mapping_set_gfp_mask(file->f_mapping,
 			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
 	loop_update_dio(lo);
-	blk_mq_unfreeze_queue(lo->lo_queue);
+	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 	partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
 	loop_global_unlock(lo, is_loop);
 
@@ -1255,6 +1256,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	int err;
 	bool partscan = false;
 	bool size_changed = false;
+	unsigned int memflags;
 
 	err = mutex_lock_killable(&lo->lo_mutex);
 	if (err)
@@ -1272,7 +1274,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	}
 
 	/* I/O needs to be drained before changing lo_offset or lo_sizelimit */
-	blk_mq_freeze_queue(lo->lo_queue);
+	memflags = blk_mq_freeze_queue(lo->lo_queue);
 
 	err = loop_set_status_from_info(lo, info);
 	if (err)
@@ -1281,8 +1283,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	partscan = !(lo->lo_flags & LO_FLAGS_PARTSCAN) &&
 		(info->lo_flags & LO_FLAGS_PARTSCAN);
 
-	lo->lo_flags &= ~(LOOP_SET_STATUS_SETTABLE_FLAGS |
-			  LOOP_SET_STATUS_CLEARABLE_FLAGS);
+	lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
 	lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS);
 
 	if (size_changed) {
@@ -1295,7 +1296,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	loop_update_dio(lo);
 
 out_unfreeze:
-	blk_mq_unfreeze_queue(lo->lo_queue);
+	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 out_unlock:
@@ -1447,6 +1448,7 @@ static int loop_set_capacity(struct loop_device *lo)
 static int loop_set_dio(struct loop_device *lo, unsigned long arg)
 {
 	bool use_dio = !!arg;
+	unsigned int memflags;
 
 	if (lo->lo_state != Lo_bound)
 		return -ENXIO;
@@ -1460,18 +1462,19 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg)
 		vfs_fsync(lo->lo_backing_file, 0);
 	}
 
-	blk_mq_freeze_queue(lo->lo_queue);
+	memflags = blk_mq_freeze_queue(lo->lo_queue);
 	if (use_dio)
 		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
 	else
 		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
-	blk_mq_unfreeze_queue(lo->lo_queue);
+	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 	return 0;
 }
 
 static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 {
 	struct queue_limits lim;
+	unsigned int memflags;
 	int err = 0;
 
 	if (lo->lo_state != Lo_bound)
@@ -1486,10 +1489,10 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
 	lim = queue_limits_start_update(lo->lo_queue);
 	loop_update_limits(lo, &lim, arg);
 
-	blk_mq_freeze_queue(lo->lo_queue);
+	memflags = blk_mq_freeze_queue(lo->lo_queue);
 	err = queue_limits_commit_update(lo->lo_queue, &lim);
 	loop_update_dio(lo);
-	blk_mq_unfreeze_queue(lo->lo_queue);
+	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 
 	return err;
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index b63a0f29a54a..7bdc7eb808ea 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1234,6 +1234,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	struct socket *sock;
 	struct nbd_sock **socks;
 	struct nbd_sock *nsock;
+	unsigned int memflags;
 	int err;
 
 	/* Arg will be cast to int, check it to avoid overflow */
@@ -1247,7 +1248,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	 * We need to make sure we don't get any errant requests while we're
 	 * reallocating the ->socks array.
 	 */
-	blk_mq_freeze_queue(nbd->disk->queue);
+	memflags = blk_mq_freeze_queue(nbd->disk->queue);
 
 	if (!netlink && !nbd->task_setup &&
 	    !test_bit(NBD_RT_BOUND, &config->runtime_flags))
@@ -1288,12 +1289,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	INIT_WORK(&nsock->work, nbd_pending_cmd_work);
 	socks[config->num_connections++] = nsock;
 	atomic_inc(&config->live_connections);
-	blk_mq_unfreeze_queue(nbd->disk->queue);
+	blk_mq_unfreeze_queue(nbd->disk->queue, memflags);
 
 	return 0;
 
 put_socket:
-	blk_mq_unfreeze_queue(nbd->disk->queue);
+	blk_mq_unfreeze_queue(nbd->disk->queue, memflags);
 	sockfd_put(sock);
 	return err;
 }
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 5b393e4a1ddf..faafd7ff43d6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -7281,9 +7281,10 @@ static ssize_t do_rbd_remove(const char *buf, size_t count)
 		 * Prevent new IO from being queued and wait for existing
 		 * IO to complete/fail.
 		 */
-		blk_mq_freeze_queue(rbd_dev->disk->queue);
+		unsigned int memflags = blk_mq_freeze_queue(rbd_dev->disk->queue);
+
 		blk_mark_disk_dead(rbd_dev->disk);
-		blk_mq_unfreeze_queue(rbd_dev->disk->queue);
+		blk_mq_unfreeze_queue(rbd_dev->disk->queue, memflags);
 	}
 
 	del_gendisk(rbd_dev->disk);
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 88dcae6ec575..282f81616a78 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -918,12 +918,12 @@ struct vdc_check_port_data {
 	char	*type;
 };
 
-static int vdc_device_probed(struct device *dev, void *arg)
+static int vdc_device_probed(struct device *dev, const void *arg)
 {
 	struct vio_dev *vdev = to_vio_dev(dev);
-	struct vdc_check_port_data *port_data;
+	const struct vdc_check_port_data *port_data;
 
-	port_data = (struct vdc_check_port_data *)arg;
+	port_data = (const struct vdc_check_port_data *)arg;
 
 	if ((vdev->dev_no == port_data->dev_no) &&
 	    (!(strcmp((char *)&vdev->type, port_data->type))) &&
@@ -1113,6 +1113,7 @@ static void vdc_requeue_inflight(struct vdc_port *port)
 static void vdc_queue_drain(struct vdc_port *port)
 {
 	struct request_queue *q = port->disk->queue;
+	unsigned int memflags;
 
 	/*
 	 * Mark the queue as draining, then freeze/quiesce to ensure
@@ -1121,13 +1122,13 @@ static void vdc_queue_drain(struct vdc_port *port)
 	port->drain = 1;
 	spin_unlock_irq(&port->vio.lock);
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	spin_lock_irq(&port->vio.lock);
 	port->drain = 0;
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 }
 
 static void vdc_ldc_reset_timer_work(struct work_struct *work)
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 9914153b365b..3aedcb5add61 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -840,6 +840,7 @@ static int grab_drive(struct floppy_state *fs, enum swim_state state,
 static void release_drive(struct floppy_state *fs)
 {
 	struct request_queue *q = disks[fs->index]->queue;
+	unsigned int memflags;
 	unsigned long flags;
 
 	swim3_dbg("%s", "-> release drive\n");
@@ -848,10 +849,10 @@ static void release_drive(struct floppy_state *fs)
 	fs->state = idle;
 	spin_unlock_irqrestore(&swim3_lock, flags);
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 }
 
 static int fd_eject(struct floppy_state *fs)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index bbaa26b523b8..6a61ec35f426 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1579,16 +1579,16 @@ static void virtblk_remove(struct virtio_device *vdev)
 	put_disk(vblk->disk);
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int virtblk_freeze(struct virtio_device *vdev)
+static int virtblk_freeze_priv(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 	struct request_queue *q = vblk->disk->queue;
+	unsigned int memflags;
 
 	/* Ensure no requests in virtqueues before deleting vqs. */
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue_nowait(q);
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	/* Ensure we don't receive any more interrupts */
 	virtio_reset_device(vdev);
@@ -1602,7 +1602,7 @@ static int virtblk_freeze(struct virtio_device *vdev)
 	return 0;
 }
 
-static int virtblk_restore(struct virtio_device *vdev)
+static int virtblk_restore_priv(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 	int ret;
@@ -1616,8 +1616,29 @@ static int virtblk_restore(struct virtio_device *vdev)
 
 	return 0;
 }
+
+#ifdef CONFIG_PM_SLEEP
+static int virtblk_freeze(struct virtio_device *vdev)
+{
+	return virtblk_freeze_priv(vdev);
+}
+
+static int virtblk_restore(struct virtio_device *vdev)
+{
+	return virtblk_restore_priv(vdev);
+}
 #endif
 
+static int virtblk_reset_prepare(struct virtio_device *vdev)
+{
+	return virtblk_freeze_priv(vdev);
+}
+
+static int virtblk_reset_done(struct virtio_device *vdev)
+{
+	return virtblk_restore_priv(vdev);
+}
+
 static const struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -1653,6 +1674,8 @@ static struct virtio_driver virtio_blk = {
 	.freeze				= virtblk_freeze,
 	.restore			= virtblk_restore,
 #endif
+	.reset_prepare			= virtblk_reset_prepare,
+	.reset_done			= virtblk_reset_done,
 };
 
 static int __init virtio_blk_init(void)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 838064593f62..a7c2b04ab943 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -544,7 +544,7 @@ static void print_stats(struct xen_blkif_ring *ring)
 		 ring->st_rd_req, ring->st_wr_req,
 		 ring->st_f_req, ring->st_ds_req,
 		 ring->persistent_gnt_c, max_pgrants);
-	ring->st_print = jiffies + msecs_to_jiffies(10 * 1000);
+	ring->st_print = jiffies + secs_to_jiffies(10);
 	ring->st_rd_req = 0;
 	ring->st_wr_req = 0;
 	ring->st_oo_req = 0;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7903a4da40ac..9f5020b077c5 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -55,8 +55,8 @@ static size_t huge_class_size;
 static const struct block_device_operations zram_devops;
 
 static void zram_free_page(struct zram *zram, size_t index);
-static int zram_read_page(struct zram *zram, struct page *page, u32 index,
-			  struct bio *parent);
+static int zram_read_from_zspool(struct zram *zram, struct page *page,
+				 u32 index);
 
 static int zram_slot_trylock(struct zram *zram, u32 index)
 {
@@ -112,17 +112,6 @@ static void zram_clear_flag(struct zram *zram, u32 index,
 	zram->table[index].flags &= ~BIT(flag);
 }
 
-static inline void zram_set_element(struct zram *zram, u32 index,
-			unsigned long element)
-{
-	zram->table[index].element = element;
-}
-
-static unsigned long zram_get_element(struct zram *zram, u32 index)
-{
-	return zram->table[index].element;
-}
-
 static size_t zram_get_obj_size(struct zram *zram, u32 index)
 {
 	return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1);
@@ -143,6 +132,27 @@ static inline bool zram_allocated(struct zram *zram, u32 index)
 			zram_test_flag(zram, index, ZRAM_WB);
 }
 
+static inline void update_used_max(struct zram *zram, const unsigned long pages)
+{
+	unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages);
+
+	do {
+		if (cur_max >= pages)
+			return;
+	} while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages,
+					  &cur_max, pages));
+}
+
+static bool zram_can_store_page(struct zram *zram)
+{
+	unsigned long alloced_pages;
+
+	alloced_pages = zs_get_total_pages(zram->mem_pool);
+	update_used_max(zram, alloced_pages);
+
+	return !zram->limit_pages || alloced_pages <= zram->limit_pages;
+}
+
 #if PAGE_SIZE != 4096
 static inline bool is_partial_io(struct bio_vec *bvec)
 {
@@ -277,18 +287,6 @@ static struct zram_pp_slot *select_pp_slot(struct zram_pp_ctl *ctl)
 }
 #endif
 
-static inline void update_used_max(struct zram *zram,
-					const unsigned long pages)
-{
-	unsigned long cur_max = atomic_long_read(&zram->stats.max_used_pages);
-
-	do {
-		if (cur_max >= pages)
-			return;
-	} while (!atomic_long_try_cmpxchg(&zram->stats.max_used_pages,
-					  &cur_max, pages));
-}
-
 static inline void zram_fill_page(void *ptr, unsigned long len,
 					unsigned long value)
 {
@@ -833,13 +831,10 @@ static ssize_t writeback_store(struct device *dev,
 		 */
 		if (!zram_test_flag(zram, index, ZRAM_PP_SLOT))
 			goto next;
+		if (zram_read_from_zspool(zram, page, index))
+			goto next;
 		zram_slot_unlock(zram, index);
 
-		if (zram_read_page(zram, page, index, NULL)) {
-			release_pp_slot(zram, pps);
-			continue;
-		}
-
 		bio_init(&bio, zram->bdev, &bio_vec, 1,
 			 REQ_OP_WRITE | REQ_SYNC);
 		bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9);
@@ -879,7 +874,7 @@ static ssize_t writeback_store(struct device *dev,
 
 		zram_free_page(zram, index);
 		zram_set_flag(zram, index, ZRAM_WB);
-		zram_set_element(zram, index, blk_idx);
+		zram_set_handle(zram, index, blk_idx);
 		blk_idx = 0;
 		atomic64_inc(&zram->stats.pages_stored);
 		spin_lock(&zram->wb_limit_lock);
@@ -889,6 +884,8 @@ static ssize_t writeback_store(struct device *dev,
 next:
 		zram_slot_unlock(zram, index);
 		release_pp_slot(zram, pps);
+
+		cond_resched();
 	}
 
 	if (blk_idx)
@@ -1505,7 +1502,7 @@ static void zram_free_page(struct zram *zram, size_t index)
 
 	if (zram_test_flag(zram, index, ZRAM_WB)) {
 		zram_clear_flag(zram, index, ZRAM_WB);
-		free_block_bdev(zram, zram_get_element(zram, index));
+		free_block_bdev(zram, zram_get_handle(zram, index));
 		goto out;
 	}
 
@@ -1533,56 +1530,73 @@ out:
 	zram_set_obj_size(zram, index, 0);
 }
 
-/*
- * Reads (decompresses if needed) a page from zspool (zsmalloc).
- * Corresponding ZRAM slot should be locked.
- */
-static int zram_read_from_zspool(struct zram *zram, struct page *page,
+static int read_same_filled_page(struct zram *zram, struct page *page,
 				 u32 index)
 {
+	void *mem;
+
+	mem = kmap_local_page(page);
+	zram_fill_page(mem, PAGE_SIZE, zram_get_handle(zram, index));
+	kunmap_local(mem);
+	return 0;
+}
+
+static int read_incompressible_page(struct zram *zram, struct page *page,
+				    u32 index)
+{
+	unsigned long handle;
+	void *src, *dst;
+
+	handle = zram_get_handle(zram, index);
+	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
+	dst = kmap_local_page(page);
+	copy_page(dst, src);
+	kunmap_local(dst);
+	zs_unmap_object(zram->mem_pool, handle);
+
+	return 0;
+}
+
+static int read_compressed_page(struct zram *zram, struct page *page, u32 index)
+{
 	struct zcomp_strm *zstrm;
 	unsigned long handle;
 	unsigned int size;
 	void *src, *dst;
-	u32 prio;
-	int ret;
+	int ret, prio;
 
 	handle = zram_get_handle(zram, index);
-	if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
-		unsigned long value;
-		void *mem;
-
-		value = handle ? zram_get_element(zram, index) : 0;
-		mem = kmap_local_page(page);
-		zram_fill_page(mem, PAGE_SIZE, value);
-		kunmap_local(mem);
-		return 0;
-	}
-
 	size = zram_get_obj_size(zram, index);
+	prio = zram_get_priority(zram, index);
 
-	if (size != PAGE_SIZE) {
-		prio = zram_get_priority(zram, index);
-		zstrm = zcomp_stream_get(zram->comps[prio]);
-	}
-
+	zstrm = zcomp_stream_get(zram->comps[prio]);
 	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
-	if (size == PAGE_SIZE) {
-		dst = kmap_local_page(page);
-		copy_page(dst, src);
-		kunmap_local(dst);
-		ret = 0;
-	} else {
-		dst = kmap_local_page(page);
-		ret = zcomp_decompress(zram->comps[prio], zstrm,
-				       src, size, dst);
-		kunmap_local(dst);
-		zcomp_stream_put(zram->comps[prio]);
-	}
+	dst = kmap_local_page(page);
+	ret = zcomp_decompress(zram->comps[prio], zstrm, src, size, dst);
+	kunmap_local(dst);
 	zs_unmap_object(zram->mem_pool, handle);
+	zcomp_stream_put(zram->comps[prio]);
+
 	return ret;
 }
 
+/*
+ * Reads (decompresses if needed) a page from zspool (zsmalloc).
+ * Corresponding ZRAM slot should be locked.
+ */
+static int zram_read_from_zspool(struct zram *zram, struct page *page,
+				 u32 index)
+{
+	if (zram_test_flag(zram, index, ZRAM_SAME) ||
+	    !zram_get_handle(zram, index))
+		return read_same_filled_page(zram, page, index);
+
+	if (!zram_test_flag(zram, index, ZRAM_HUGE))
+		return read_compressed_page(zram, page, index);
+	else
+		return read_incompressible_page(zram, page, index);
+}
+
 static int zram_read_page(struct zram *zram, struct page *page, u32 index,
 			  struct bio *parent)
 {
@@ -1600,7 +1614,7 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index,
 		 */
 		zram_slot_unlock(zram, index);
 
-		ret = read_from_bdev(zram, page, zram_get_element(zram, index),
+		ret = read_from_bdev(zram, page, zram_get_handle(zram, index),
 				     parent);
 	}
 
@@ -1638,33 +1652,88 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 	return zram_read_page(zram, bvec->bv_page, index, bio);
 }
 
+static int write_same_filled_page(struct zram *zram, unsigned long fill,
+				  u32 index)
+{
+	zram_slot_lock(zram, index);
+	zram_set_flag(zram, index, ZRAM_SAME);
+	zram_set_handle(zram, index, fill);
+	zram_slot_unlock(zram, index);
+
+	atomic64_inc(&zram->stats.same_pages);
+	atomic64_inc(&zram->stats.pages_stored);
+
+	return 0;
+}
+
+static int write_incompressible_page(struct zram *zram, struct page *page,
+				     u32 index)
+{
+	unsigned long handle;
+	void *src, *dst;
+
+	/*
+	 * This function is called from preemptible context so we don't need
+	 * to do optimistic and fallback to pessimistic handle allocation,
+	 * like we do for compressible pages.
+	 */
+	handle = zs_malloc(zram->mem_pool, PAGE_SIZE,
+			   GFP_NOIO | __GFP_HIGHMEM | __GFP_MOVABLE);
+	if (IS_ERR_VALUE(handle))
+		return PTR_ERR((void *)handle);
+
+	if (!zram_can_store_page(zram)) {
+		zs_free(zram->mem_pool, handle);
+		return -ENOMEM;
+	}
+
+	dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);
+	src = kmap_local_page(page);
+	memcpy(dst, src, PAGE_SIZE);
+	kunmap_local(src);
+	zs_unmap_object(zram->mem_pool, handle);
+
+	zram_slot_lock(zram, index);
+	zram_set_flag(zram, index, ZRAM_HUGE);
+	zram_set_handle(zram, index, handle);
+	zram_set_obj_size(zram, index, PAGE_SIZE);
+	zram_slot_unlock(zram, index);
+
+	atomic64_add(PAGE_SIZE, &zram->stats.compr_data_size);
+	atomic64_inc(&zram->stats.huge_pages);
+	atomic64_inc(&zram->stats.huge_pages_since);
+	atomic64_inc(&zram->stats.pages_stored);
+
+	return 0;
+}
+
 static int zram_write_page(struct zram *zram, struct page *page, u32 index)
 {
 	int ret = 0;
-	unsigned long alloced_pages;
 	unsigned long handle = -ENOMEM;
 	unsigned int comp_len = 0;
-	void *src, *dst, *mem;
+	void *dst, *mem;
 	struct zcomp_strm *zstrm;
 	unsigned long element = 0;
-	enum zram_pageflags flags = 0;
+	bool same_filled;
+
+	/* First, free memory allocated to this slot (if any) */
+	zram_slot_lock(zram, index);
+	zram_free_page(zram, index);
+	zram_slot_unlock(zram, index);
 
 	mem = kmap_local_page(page);
-	if (page_same_filled(mem, &element)) {
-		kunmap_local(mem);
-		/* Free memory associated with this sector now. */
-		flags = ZRAM_SAME;
-		atomic64_inc(&zram->stats.same_pages);
-		goto out;
-	}
+	same_filled = page_same_filled(mem, &element);
 	kunmap_local(mem);
+	if (same_filled)
+		return write_same_filled_page(zram, element, index);
 
 compress_again:
 	zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
-	src = kmap_local_page(page);
+	mem = kmap_local_page(page);
 	ret = zcomp_compress(zram->comps[ZRAM_PRIMARY_COMP], zstrm,
-			     src, &comp_len);
-	kunmap_local(src);
+			     mem, &comp_len);
+	kunmap_local(mem);
 
 	if (unlikely(ret)) {
 		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
@@ -1673,8 +1742,11 @@ compress_again:
 		return ret;
 	}
 
-	if (comp_len >= huge_class_size)
-		comp_len = PAGE_SIZE;
+	if (comp_len >= huge_class_size) {
+		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
+		return write_incompressible_page(zram, page, index);
+	}
+
 	/*
 	 * handle allocation has 2 paths:
 	 * a) fast path is executed with preemption disabled (for
@@ -1690,35 +1762,23 @@ compress_again:
 	 */
 	if (IS_ERR_VALUE(handle))
 		handle = zs_malloc(zram->mem_pool, comp_len,
-				__GFP_KSWAPD_RECLAIM |
-				__GFP_NOWARN |
-				__GFP_HIGHMEM |
-				__GFP_MOVABLE);
+				   __GFP_KSWAPD_RECLAIM |
+				   __GFP_NOWARN |
+				   __GFP_HIGHMEM |
+				   __GFP_MOVABLE);
 	if (IS_ERR_VALUE(handle)) {
 		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 		atomic64_inc(&zram->stats.writestall);
 		handle = zs_malloc(zram->mem_pool, comp_len,
-				GFP_NOIO | __GFP_HIGHMEM |
-				__GFP_MOVABLE);
+				   GFP_NOIO | __GFP_HIGHMEM |
+				   __GFP_MOVABLE);
 		if (IS_ERR_VALUE(handle))
 			return PTR_ERR((void *)handle);
 
-		if (comp_len != PAGE_SIZE)
-			goto compress_again;
-		/*
-		 * If the page is not compressible, you need to acquire the
-		 * lock and execute the code below. The zcomp_stream_get()
-		 * call is needed to disable the cpu hotplug and grab the
-		 * zstrm buffer back. It is necessary that the dereferencing
-		 * of the zstrm variable below occurs correctly.
-		 */
-		zstrm = zcomp_stream_get(zram->comps[ZRAM_PRIMARY_COMP]);
+		goto compress_again;
 	}
 
-	alloced_pages = zs_get_total_pages(zram->mem_pool);
-	update_used_max(zram, alloced_pages);
-
-	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+	if (!zram_can_store_page(zram)) {
 		zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 		zs_free(zram->mem_pool, handle);
 		return -ENOMEM;
@@ -1726,41 +1786,19 @@ compress_again:
 
 	dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);
 
-	src = zstrm->buffer;
-	if (comp_len == PAGE_SIZE)
-		src = kmap_local_page(page);
-	memcpy(dst, src, comp_len);
-	if (comp_len == PAGE_SIZE)
-		kunmap_local(src);
-
+	memcpy(dst, zstrm->buffer, comp_len);
 	zcomp_stream_put(zram->comps[ZRAM_PRIMARY_COMP]);
 	zs_unmap_object(zram->mem_pool, handle);
-	atomic64_add(comp_len, &zram->stats.compr_data_size);
-out:
-	/*
-	 * Free memory associated with this sector
-	 * before overwriting unused sectors.
-	 */
-	zram_slot_lock(zram, index);
-	zram_free_page(zram, index);
-
-	if (comp_len == PAGE_SIZE) {
-		zram_set_flag(zram, index, ZRAM_HUGE);
-		atomic64_inc(&zram->stats.huge_pages);
-		atomic64_inc(&zram->stats.huge_pages_since);
-	}
 
-	if (flags) {
-		zram_set_flag(zram, index, flags);
-		zram_set_element(zram, index, element);
-	}  else {
-		zram_set_handle(zram, index, handle);
-		zram_set_obj_size(zram, index, comp_len);
-	}
+	zram_slot_lock(zram, index);
+	zram_set_handle(zram, index, handle);
+	zram_set_obj_size(zram, index, comp_len);
 	zram_slot_unlock(zram, index);
 
 	/* Update stats */
 	atomic64_inc(&zram->stats.pages_stored);
+	atomic64_add(comp_len, &zram->stats.compr_data_size);
+
 	return ret;
 }
 
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 134be414e210..db78d7c01b9a 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -62,10 +62,7 @@ enum zram_pageflags {
 
 /* Allocated for each disk page */
 struct zram_table_entry {
-	union {
-		unsigned long handle;
-		unsigned long element;
-	};
+	unsigned long handle;
 	unsigned int flags;
 	spinlock_t lock;
 #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 1230045d78a5..aa5ec1d444a9 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1381,13 +1381,12 @@ static void btnxpuart_tx_work(struct work_struct *work)
 
 	while ((skb = nxp_dequeue(nxpdev))) {
 		len = serdev_device_write_buf(serdev, skb->data, skb->len);
-		serdev_device_wait_until_sent(serdev, 0);
 		hdev->stat.byte_tx += len;
 
 		skb_pull(skb, len);
 		if (skb->len > 0) {
 			skb_queue_head(&nxpdev->txq, skb);
-			break;
+			continue;
 		}
 
 		switch (hci_skb_pkt_type(skb)) {
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 9aa018d4f6f5..90966dfbd278 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -899,11 +899,6 @@ static void btusb_reset(struct hci_dev *hdev)
 	struct btusb_data *data;
 	int err;
 
-	if (hdev->reset) {
-		hdev->reset(hdev);
-		return;
-	}
-
 	data = hci_get_drvdata(hdev);
 	/* This is not an unbalanced PM reference since the device will reset */
 	err = usb_autopm_get_interface(data->intf);
@@ -2639,8 +2634,15 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data)
 	struct btmtk_data *btmtk_data = hci_get_priv(data->hdev);
 	int err;
 
+	/*
+	 * The function usb_driver_claim_interface() is documented to need
+	 * locks held if it's not called from a probe routine. The code here
+	 * is called from the hci_power_on workqueue, so grab the lock.
+	 */
+	device_lock(&btmtk_data->isopkt_intf->dev);
 	err = usb_driver_claim_interface(&btusb_driver,
 					 btmtk_data->isopkt_intf, data);
+	device_unlock(&btmtk_data->isopkt_intf->dev);
 	if (err < 0) {
 		btmtk_data->isopkt_intf = NULL;
 		bt_dev_err(data->hdev, "Failed to claim iso interface");
diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c
index 4b68c84ef485..52053f7c6d9a 100644
--- a/drivers/bus/fsl-mc/dprc-driver.c
+++ b/drivers/bus/fsl-mc/dprc-driver.c
@@ -22,8 +22,8 @@ struct fsl_mc_child_objs {
 	struct fsl_mc_obj_desc *child_array;
 };
 
-static bool fsl_mc_device_match(struct fsl_mc_device *mc_dev,
-				struct fsl_mc_obj_desc *obj_desc)
+static bool fsl_mc_device_match(const struct fsl_mc_device *mc_dev,
+				const struct fsl_mc_obj_desc *obj_desc)
 {
 	return mc_dev->obj_desc.id == obj_desc->id &&
 	       strcmp(mc_dev->obj_desc.type, obj_desc->type) == 0;
@@ -112,9 +112,9 @@ void dprc_remove_devices(struct fsl_mc_device *mc_bus_dev,
 }
 EXPORT_SYMBOL_GPL(dprc_remove_devices);
 
-static int __fsl_mc_device_match(struct device *dev, void *data)
+static int __fsl_mc_device_match(struct device *dev, const void *data)
 {
-	struct fsl_mc_obj_desc *obj_desc = data;
+	const struct fsl_mc_obj_desc *obj_desc = data;
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
 
 	return fsl_mc_device_match(mc_dev, obj_desc);
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 2916d1333649..d1f3d327ddd1 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -320,90 +320,90 @@ const struct bus_type fsl_mc_bus_type = {
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_type);
 
-struct device_type fsl_mc_bus_dprc_type = {
+const struct device_type fsl_mc_bus_dprc_type = {
 	.name = "fsl_mc_bus_dprc"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dprc_type);
 
-struct device_type fsl_mc_bus_dpni_type = {
+const struct device_type fsl_mc_bus_dpni_type = {
 	.name = "fsl_mc_bus_dpni"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpni_type);
 
-struct device_type fsl_mc_bus_dpio_type = {
+const struct device_type fsl_mc_bus_dpio_type = {
 	.name = "fsl_mc_bus_dpio"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpio_type);
 
-struct device_type fsl_mc_bus_dpsw_type = {
+const struct device_type fsl_mc_bus_dpsw_type = {
 	.name = "fsl_mc_bus_dpsw"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpsw_type);
 
-struct device_type fsl_mc_bus_dpbp_type = {
+const struct device_type fsl_mc_bus_dpbp_type = {
 	.name = "fsl_mc_bus_dpbp"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpbp_type);
 
-struct device_type fsl_mc_bus_dpcon_type = {
+const struct device_type fsl_mc_bus_dpcon_type = {
 	.name = "fsl_mc_bus_dpcon"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpcon_type);
 
-struct device_type fsl_mc_bus_dpmcp_type = {
+const struct device_type fsl_mc_bus_dpmcp_type = {
 	.name = "fsl_mc_bus_dpmcp"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpmcp_type);
 
-struct device_type fsl_mc_bus_dpmac_type = {
+const struct device_type fsl_mc_bus_dpmac_type = {
 	.name = "fsl_mc_bus_dpmac"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpmac_type);
 
-struct device_type fsl_mc_bus_dprtc_type = {
+const struct device_type fsl_mc_bus_dprtc_type = {
 	.name = "fsl_mc_bus_dprtc"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dprtc_type);
 
-struct device_type fsl_mc_bus_dpseci_type = {
+const struct device_type fsl_mc_bus_dpseci_type = {
 	.name = "fsl_mc_bus_dpseci"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpseci_type);
 
-struct device_type fsl_mc_bus_dpdmux_type = {
+const struct device_type fsl_mc_bus_dpdmux_type = {
 	.name = "fsl_mc_bus_dpdmux"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdmux_type);
 
-struct device_type fsl_mc_bus_dpdcei_type = {
+const struct device_type fsl_mc_bus_dpdcei_type = {
 	.name = "fsl_mc_bus_dpdcei"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdcei_type);
 
-struct device_type fsl_mc_bus_dpaiop_type = {
+const struct device_type fsl_mc_bus_dpaiop_type = {
 	.name = "fsl_mc_bus_dpaiop"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpaiop_type);
 
-struct device_type fsl_mc_bus_dpci_type = {
+const struct device_type fsl_mc_bus_dpci_type = {
 	.name = "fsl_mc_bus_dpci"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpci_type);
 
-struct device_type fsl_mc_bus_dpdmai_type = {
+const struct device_type fsl_mc_bus_dpdmai_type = {
 	.name = "fsl_mc_bus_dpdmai"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdmai_type);
 
-struct device_type fsl_mc_bus_dpdbg_type = {
+const struct device_type fsl_mc_bus_dpdbg_type = {
 	.name = "fsl_mc_bus_dpdbg"
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_dpdbg_type);
 
-static struct device_type *fsl_mc_get_device_type(const char *type)
+static const struct device_type *fsl_mc_get_device_type(const char *type)
 {
 	static const struct {
-		struct device_type *dev_type;
+		const struct device_type *dev_type;
 		const char *type;
 	} dev_types[] = {
 		{ &fsl_mc_bus_dprc_type, "dprc" },
diff --git a/drivers/bus/mhi/host/boot.c b/drivers/bus/mhi/host/boot.c
index e8c92972f9df..9dcc7184817d 100644
--- a/drivers/bus/mhi/host/boot.c
+++ b/drivers/bus/mhi/host/boot.c
@@ -357,6 +357,7 @@ error_alloc_segment:
 	for (--i, --mhi_buf; i >= 0; i--, mhi_buf--)
 		dma_free_coherent(mhi_cntrl->cntrl_dev, mhi_buf->len,
 				  mhi_buf->buf, mhi_buf->dma_addr);
+	kfree(img_info->mhi_buf);
 
 error_alloc_mhi_buf:
 	kfree(img_info);
diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
index 56ba4192c89c..c41119b9079f 100644
--- a/drivers/bus/mhi/host/pci_generic.c
+++ b/drivers/bus/mhi/host/pci_generic.c
@@ -245,6 +245,58 @@ struct mhi_pci_dev_info {
 		.channel = ch_num,		\
 	}
 
+static const struct mhi_channel_config mhi_qcom_qdu100_channels[] = {
+	MHI_CHANNEL_CONFIG_UL(0, "LOOPBACK", 32, 2),
+	MHI_CHANNEL_CONFIG_DL(1, "LOOPBACK", 32, 2),
+	MHI_CHANNEL_CONFIG_UL_SBL(2, "SAHARA", 128, 1),
+	MHI_CHANNEL_CONFIG_DL_SBL(3, "SAHARA", 128, 1),
+	MHI_CHANNEL_CONFIG_UL(4, "DIAG", 64, 3),
+	MHI_CHANNEL_CONFIG_DL(5, "DIAG", 64, 3),
+	MHI_CHANNEL_CONFIG_UL(9, "QDSS", 64, 3),
+	MHI_CHANNEL_CONFIG_UL(14, "NMEA", 32, 4),
+	MHI_CHANNEL_CONFIG_DL(15, "NMEA", 32, 4),
+	MHI_CHANNEL_CONFIG_UL(16, "CSM_CTRL", 32, 4),
+	MHI_CHANNEL_CONFIG_DL(17, "CSM_CTRL", 32, 4),
+	MHI_CHANNEL_CONFIG_UL(40, "MHI_PHC", 32, 4),
+	MHI_CHANNEL_CONFIG_DL(41, "MHI_PHC", 32, 4),
+	MHI_CHANNEL_CONFIG_UL(46, "IP_SW0", 256, 5),
+	MHI_CHANNEL_CONFIG_DL(47, "IP_SW0", 256, 5),
+};
+
+static struct mhi_event_config mhi_qcom_qdu100_events[] = {
+	/* first ring is control+data ring */
+	MHI_EVENT_CONFIG_CTRL(0, 64),
+	/* SAHARA dedicated event ring */
+	MHI_EVENT_CONFIG_SW_DATA(1, 256),
+	/* Software channels dedicated event ring */
+	MHI_EVENT_CONFIG_SW_DATA(2, 64),
+	MHI_EVENT_CONFIG_SW_DATA(3, 256),
+	MHI_EVENT_CONFIG_SW_DATA(4, 256),
+	/* Software IP channels dedicated event ring */
+	MHI_EVENT_CONFIG_SW_DATA(5, 512),
+	MHI_EVENT_CONFIG_SW_DATA(6, 512),
+	MHI_EVENT_CONFIG_SW_DATA(7, 512),
+};
+
+static const struct mhi_controller_config mhi_qcom_qdu100_config = {
+	.max_channels = 128,
+	.timeout_ms = 120000,
+	.num_channels = ARRAY_SIZE(mhi_qcom_qdu100_channels),
+	.ch_cfg = mhi_qcom_qdu100_channels,
+	.num_events = ARRAY_SIZE(mhi_qcom_qdu100_events),
+	.event_cfg = mhi_qcom_qdu100_events,
+};
+
+static const struct mhi_pci_dev_info mhi_qcom_qdu100_info = {
+	.name = "qcom-qdu100",
+	.fw = "qcom/qdu100/xbl_s.melf",
+	.edl_trigger = true,
+	.config = &mhi_qcom_qdu100_config,
+	.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
+	.dma_data_width = 32,
+	.sideband_wake = false,
+};
+
 static const struct mhi_channel_config modem_qcom_v1_mhi_channels[] = {
 	MHI_CHANNEL_CONFIG_UL(4, "DIAG", 16, 1),
 	MHI_CHANNEL_CONFIG_DL(5, "DIAG", 16, 1),
@@ -742,6 +794,9 @@ static const struct pci_device_id mhi_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0309),
 		.driver_data = (kernel_ulong_t) &mhi_qcom_sdx75_info },
+	/* QDU100, x100-DU */
+	{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0601),
+		.driver_data = (kernel_ulong_t) &mhi_qcom_qdu100_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1001), /* EM120R-GL (sdx24) */
 		.driver_data = (kernel_ulong_t) &mhi_quectel_em1xx_info },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QUECTEL, 0x1002), /* EM160R-GL (sdx24) */
@@ -949,7 +1004,7 @@ static int mhi_pci_get_irqs(struct mhi_controller *mhi_cntrl,
 	 */
 	mhi_cntrl->nr_irqs = 1 + mhi_cntrl_config->num_events;
 
-	nr_vectors = pci_alloc_irq_vectors(pdev, 1, mhi_cntrl->nr_irqs, PCI_IRQ_MSI);
+	nr_vectors = pci_alloc_irq_vectors(pdev, 1, mhi_cntrl->nr_irqs, PCI_IRQ_MSIX | PCI_IRQ_MSI);
 	if (nr_vectors < 0) {
 		dev_err(&pdev->dev, "Error allocating MSI vectors %d\n",
 			nr_vectors);
diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c
index 6276551d7968..1e57ebfb7622 100644
--- a/drivers/bus/moxtet.c
+++ b/drivers/bus/moxtet.c
@@ -657,7 +657,7 @@ static void moxtet_irq_print_chip(struct irq_data *d, struct seq_file *p)
 
 	id = moxtet->modules[pos->idx];
 
-	seq_printf(p, " moxtet-%s.%i#%i", mox_module_name(id), pos->idx,
+	seq_printf(p, "moxtet-%s.%i#%i", mox_module_name(id), pos->idx,
 		   pos->bit);
 }
 
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 51745ed1bbab..b163e043c687 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -3612,7 +3612,7 @@ static int cdrom_sysctl_handler(const struct ctl_table *ctl, int write,
 }
 
 /* Place files in /proc/sys/dev/cdrom */
-static struct ctl_table cdrom_table[] = {
+static const struct ctl_table cdrom_table[] = {
 	{
 		.procname	= "info",
 		.data		= &cdrom_sysctl_settings.info, 
diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index 76eac3653b1c..c573ed2ee71a 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -338,7 +338,10 @@ static void cdx_shutdown(struct device *dev)
 {
 	struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver);
 	struct cdx_device *cdx_dev = to_cdx_device(dev);
+	struct cdx_controller *cdx = cdx_dev->cdx;
 
+	if (cdx_dev->is_bus && cdx_dev->enabled && cdx->ops->bus_disable)
+		cdx->ops->bus_disable(cdx, cdx_dev->bus_num);
 	if (cdx_drv && cdx_drv->shutdown)
 		cdx_drv->shutdown(cdx_dev);
 }
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 48fe96ab4649..e110857824fc 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -724,7 +724,7 @@ static int hpet_is_known(struct hpet_data *hdp)
 	return 0;
 }
 
-static struct ctl_table hpet_table[] = {
+static const struct ctl_table hpet_table[] = {
 	{
 	 .procname = "max-user-freq",
 	 .data = &hpet_max_freq,
diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c
index 05f17e3e6207..e63c316d8aaa 100644
--- a/drivers/char/ipmi/ipmi_poweroff.c
+++ b/drivers/char/ipmi/ipmi_poweroff.c
@@ -650,7 +650,7 @@ static struct ipmi_smi_watcher smi_watcher = {
 #ifdef CONFIG_PROC_FS
 #include <linux/sysctl.h>
 
-static struct ctl_table ipmi_table[] = {
+static const struct ctl_table ipmi_table[] = {
 	{ .procname	= "poweroff_powercycle",
 	  .data		= &poweroff_powercycle,
 	  .maxlen	= sizeof(poweroff_powercycle),
diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 541edc26ec89..2cf595d2e10b 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -63,16 +63,30 @@ static DEFINE_MUTEX(misc_mtx);
 #define DYNAMIC_MINORS 128 /* like dynamic majors */
 static DEFINE_IDA(misc_minors_ida);
 
-static int misc_minor_alloc(void)
+static int misc_minor_alloc(int minor)
 {
-	int ret;
-
-	ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL);
-	if (ret >= 0) {
-		ret = DYNAMIC_MINORS - ret - 1;
+	int ret = 0;
+
+	if (minor == MISC_DYNAMIC_MINOR) {
+		/* allocate free id */
+		ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL);
+		if (ret >= 0) {
+			ret = DYNAMIC_MINORS - ret - 1;
+		} else {
+			ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1,
+					      MINORMASK, GFP_KERNEL);
+		}
 	} else {
-		ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1,
-				      MINORMASK, GFP_KERNEL);
+		/* specific minor, check if it is in dynamic or misc dynamic range  */
+		if (minor < DYNAMIC_MINORS) {
+			minor = DYNAMIC_MINORS - minor - 1;
+			ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL);
+		} else if (minor > MISC_DYNAMIC_MINOR) {
+			ret = ida_alloc_range(&misc_minors_ida, minor, minor, GFP_KERNEL);
+		} else {
+			/* case of non-dynamic minors, no need to allocate id */
+			ret = 0;
+		}
 	}
 	return ret;
 }
@@ -219,7 +233,7 @@ int misc_register(struct miscdevice *misc)
 	mutex_lock(&misc_mtx);
 
 	if (is_dynamic) {
-		int i = misc_minor_alloc();
+		int i = misc_minor_alloc(misc->minor);
 
 		if (i < 0) {
 			err = -EBUSY;
@@ -228,6 +242,7 @@ int misc_register(struct miscdevice *misc)
 		misc->minor = i;
 	} else {
 		struct miscdevice *c;
+		int i;
 
 		list_for_each_entry(c, &misc_list, list) {
 			if (c->minor == misc->minor) {
@@ -235,6 +250,12 @@ int misc_register(struct miscdevice *misc)
 				goto out;
 			}
 		}
+
+		i = misc_minor_alloc(misc->minor);
+		if (i < 0) {
+			err = -EBUSY;
+			goto out;
+		}
 	}
 
 	dev = MKDEV(MISC_MAJOR, misc->minor);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 23ee76bbb4aa..2581186fa61b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1665,7 +1665,7 @@ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf,
 	return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos);
 }
 
-static struct ctl_table random_table[] = {
+static const struct ctl_table random_table[] = {
 	{
 		.procname	= "poolsize",
 		.data		= &sysctl_poolsize,
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index c62b208b42f1..24442485e73e 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -883,9 +883,9 @@ static int pipe_to_sg(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		if (len + offset > PAGE_SIZE)
 			len = PAGE_SIZE - offset;
 
-		src = kmap_atomic(buf->page);
+		src = kmap_local_page(buf->page);
 		memcpy(page_address(page) + offset, src + buf->offset, len);
-		kunmap_atomic(src);
+		kunmap_local(src);
 
 		sg_set_page(&(sgl->sg[sgl->n]), page, len, offset);
 	}
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index f2117fef7c7d..9c75dcc9a534 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -449,10 +449,7 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem)
 {
 	struct clk_iomap *io;
 
-	io = memblock_alloc(sizeof(*io), SMP_CACHE_BYTES);
-	if (!io)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(*io));
+	io = memblock_alloc_or_panic(sizeof(*io), SMP_CACHE_BYTES);
 
 	io->mem = mem;
 
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 704e84d00639..9e46960f6a86 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -18,6 +18,7 @@ config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
 config ARM_AIROHA_SOC_CPUFREQ
 	tristate "Airoha EN7581 SoC CPUFreq support"
 	depends on ARCH_AIROHA || COMPILE_TEST
+	depends on OF
 	select PM_OPP
 	default ARCH_AIROHA
 	help
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 302df42d6887..463b69a2dff5 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -909,11 +909,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency)
 		pr_warn(FW_WARN "P-state 0 is not max freq\n");
 
-	if (acpi_cpufreq_driver.set_boost) {
-		set_boost(policy, acpi_cpufreq_driver.boost_enabled);
-		policy->boost_enabled = acpi_cpufreq_driver.boost_enabled;
-	}
-
 	return result;
 
 err_unreg:
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index dd9b8d6993d6..313550fa62d4 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -699,7 +699,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (min_perf < lowest_nonlinear_perf)
 		min_perf = lowest_nonlinear_perf;
 
-	max_perf = cap_perf;
+	max_perf = cpudata->max_limit_perf;
 	if (max_perf < min_perf)
 		max_perf = min_perf;
 
@@ -747,7 +747,6 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 	guard(mutex)(&amd_pstate_driver_lock);
 
 	ret = amd_pstate_cpu_boost_update(policy, state);
-	policy->boost_enabled = !ret ? state : false;
 	refresh_frequency_limits(policy);
 
 	return ret;
@@ -822,25 +821,28 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 
 static void amd_pstate_update_limits(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy *policy = NULL;
 	struct amd_cpudata *cpudata;
 	u32 prev_high = 0, cur_high = 0;
 	int ret;
 	bool highest_perf_changed = false;
 
+	if (!amd_pstate_prefcore)
+		return;
+
+	policy = cpufreq_cpu_get(cpu);
 	if (!policy)
 		return;
 
 	cpudata = policy->driver_data;
 
-	if (!amd_pstate_prefcore)
-		return;
-
 	guard(mutex)(&amd_pstate_driver_lock);
 
 	ret = amd_get_highest_perf(cpu, &cur_high);
-	if (ret)
-		goto free_cpufreq_put;
+	if (ret) {
+		cpufreq_cpu_put(policy);
+		return;
+	}
 
 	prev_high = READ_ONCE(cpudata->prefcore_ranking);
 	highest_perf_changed = (prev_high != cur_high);
@@ -850,8 +852,6 @@ static void amd_pstate_update_limits(unsigned int cpu)
 		if (cur_high < CPPC_MAX_PERF)
 			sched_set_itmt_core_prio((int)cur_high, cpu);
 	}
-
-free_cpufreq_put:
 	cpufreq_cpu_put(policy);
 
 	if (!highest_perf_changed)
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 2486a6c5256a..8f512448382f 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -611,7 +611,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
 	policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
-	policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
+	policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ?
+						caps->highest_perf : caps->nominal_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
@@ -619,7 +620,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * nonlinear perf
 	 */
 	policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf);
-	policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf);
+	policy->cpuinfo.max_freq = policy->max;
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 1076e37a18ad..30ffbddc7ece 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1410,10 +1410,6 @@ static int cpufreq_online(unsigned int cpu)
 			goto out_free_policy;
 		}
 
-		/* Let the per-policy boost flag mirror the cpufreq_driver boost during init */
-		if (cpufreq_boost_enabled() && policy_has_boost_freq(policy))
-			policy->boost_enabled = true;
-
 		/*
 		 * The initialization has succeeded and the policy is online.
 		 * If there is a problem with its frequency table, take it
@@ -1476,6 +1472,10 @@ static int cpufreq_online(unsigned int cpu)
 
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
+	} else {
+		ret = freq_qos_update_request(policy->max_freq_req, policy->max);
+		if (ret < 0)
+			goto out_destroy_policy;
 	}
 
 	if (cpufreq_driver->get && has_target()) {
@@ -1570,6 +1570,19 @@ static int cpufreq_online(unsigned int cpu)
 	if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver))
 		policy->cdev = of_cpufreq_cooling_register(policy);
 
+	/* Let the per-policy boost flag mirror the cpufreq_driver boost during init */
+	if (cpufreq_driver->set_boost &&
+	    policy->boost_enabled != cpufreq_boost_enabled()) {
+		policy->boost_enabled = cpufreq_boost_enabled();
+		ret = cpufreq_driver->set_boost(policy, policy->boost_enabled);
+		if (ret) {
+			/* If the set_boost fails, the online operation is not affected */
+			pr_info("%s: CPU%d: Cannot %s BOOST\n", __func__, policy->cpu,
+				policy->boost_enabled ? "enable" : "disable");
+			policy->boost_enabled = !policy->boost_enabled;
+		}
+	}
+
 	pr_debug("initialization complete\n");
 
 	return 0;
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index c6bdfc308e99..9cef71528076 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -24,6 +24,7 @@ struct s3c64xx_dvfs {
 	unsigned int vddarm_max;
 };
 
+#ifdef CONFIG_REGULATOR
 static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = {
 	[0] = { 1000000, 1150000 },
 	[1] = { 1050000, 1150000 },
@@ -31,6 +32,7 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = {
 	[3] = { 1200000, 1350000 },
 	[4] = { 1300000, 1350000 },
 };
+#endif
 
 static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
 	{ 0, 0,  66000 },
@@ -51,15 +53,16 @@ static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
 static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy,
 				      unsigned int index)
 {
-	struct s3c64xx_dvfs *dvfs;
-	unsigned int old_freq, new_freq;
+	unsigned int new_freq = s3c64xx_freq_table[index].frequency;
 	int ret;
 
+#ifdef CONFIG_REGULATOR
+	struct s3c64xx_dvfs *dvfs;
+	unsigned int old_freq;
+
 	old_freq = clk_get_rate(policy->clk) / 1000;
-	new_freq = s3c64xx_freq_table[index].frequency;
 	dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[index].driver_data];
 
-#ifdef CONFIG_REGULATOR
 	if (vddarm && new_freq > old_freq) {
 		ret = regulator_set_voltage(vddarm,
 					    dvfs->vddarm_min,
diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c
index 173ddcac540a..8fe5e1b47ef9 100644
--- a/drivers/cpuidle/governors/teo.c
+++ b/drivers/cpuidle/governors/teo.c
@@ -41,11 +41,7 @@
  * idle state 2, the third bin spans from the target residency of idle state 2
  * up to, but not including, the target residency of idle state 3 and so on.
  * The last bin spans from the target residency of the deepest idle state
- * supplied by the driver to the scheduler tick period length or to infinity if
- * the tick period length is less than the target residency of that state.  In
- * the latter case, the governor also counts events with the measured idle
- * duration between the tick period length and the target residency of the
- * deepest idle state.
+ * supplied by the driver to infinity.
  *
  * Two metrics called "hits" and "intercepts" are associated with each bin.
  * They are updated every time before selecting an idle state for the given CPU
@@ -60,6 +56,10 @@
  * into by the sleep length (these events are also referred to as "intercepts"
  * below).
  *
+ * The governor also counts "intercepts" with the measured idle duration below
+ * the tick period length and uses this information when deciding whether or not
+ * to stop the scheduler tick.
+ *
  * In order to select an idle state for a CPU, the governor takes the following
  * steps (modulo the possible latency constraint that must be taken into account
  * too):
@@ -106,6 +106,12 @@
 #include "gov.h"
 
 /*
+ * Idle state exit latency threshold used for deciding whether or not to check
+ * the time till the closest expected timer event.
+ */
+#define LATENCY_THRESHOLD_NS	(RESIDENCY_THRESHOLD_NS / 2)
+
+/*
  * The PULSE value is added to metrics when they grow and the DECAY_SHIFT value
  * is used for decreasing metrics on a regular basis.
  */
@@ -124,18 +130,20 @@ struct teo_bin {
 
 /**
  * struct teo_cpu - CPU data used by the TEO cpuidle governor.
- * @time_span_ns: Time between idle state selection and post-wakeup update.
  * @sleep_length_ns: Time till the closest timer event (at the selection time).
  * @state_bins: Idle state data bins for this CPU.
  * @total: Grand total of the "intercepts" and "hits" metrics for all bins.
- * @tick_hits: Number of "hits" after TICK_NSEC.
+ * @tick_intercepts: "Intercepts" before TICK_NSEC.
+ * @short_idles: Wakeups after short idle periods.
+ * @artificial_wakeup: Set if the wakeup has been triggered by a safety net.
  */
 struct teo_cpu {
-	s64 time_span_ns;
 	s64 sleep_length_ns;
 	struct teo_bin state_bins[CPUIDLE_STATE_MAX];
 	unsigned int total;
-	unsigned int tick_hits;
+	unsigned int tick_intercepts;
+	unsigned int short_idles;
+	bool artificial_wakeup;
 };
 
 static DEFINE_PER_CPU(struct teo_cpu, teo_cpus);
@@ -152,23 +160,17 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	s64 target_residency_ns;
 	u64 measured_ns;
 
-	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
+	cpu_data->short_idles -= cpu_data->short_idles >> DECAY_SHIFT;
+
+	if (cpu_data->artificial_wakeup) {
 		/*
-		 * One of the safety nets has triggered or the wakeup was close
-		 * enough to the closest timer event expected at the idle state
-		 * selection time to be discarded.
+		 * If one of the safety nets has triggered, assume that this
+		 * might have been a long sleep.
 		 */
 		measured_ns = U64_MAX;
 	} else {
 		u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns;
 
-		/*
-		 * The computations below are to determine whether or not the
-		 * (saved) time till the next timer event and the measured idle
-		 * duration fall into the same "bin", so use last_residency_ns
-		 * for that instead of time_span_ns which includes the cpuidle
-		 * overhead.
-		 */
 		measured_ns = dev->last_residency_ns;
 		/*
 		 * The delay between the wakeup and the first instruction
@@ -176,14 +178,16 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		 * time, so take 1/2 of the exit latency as a very rough
 		 * approximation of the average of it.
 		 */
-		if (measured_ns >= lat_ns)
+		if (measured_ns >= lat_ns) {
 			measured_ns -= lat_ns / 2;
-		else
+			if (measured_ns < RESIDENCY_THRESHOLD_NS)
+				cpu_data->short_idles += PULSE;
+		} else {
 			measured_ns /= 2;
+			cpu_data->short_idles += PULSE;
+		}
 	}
 
-	cpu_data->total = 0;
-
 	/*
 	 * Decay the "hits" and "intercepts" metrics for all of the bins and
 	 * find the bins that the sleep length and the measured idle duration
@@ -195,8 +199,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		bin->hits -= bin->hits >> DECAY_SHIFT;
 		bin->intercepts -= bin->intercepts >> DECAY_SHIFT;
 
-		cpu_data->total += bin->hits + bin->intercepts;
-
 		target_residency_ns = drv->states[i].target_residency_ns;
 
 		if (target_residency_ns <= cpu_data->sleep_length_ns) {
@@ -206,38 +208,22 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		}
 	}
 
-	/*
-	 * If the deepest state's target residency is below the tick length,
-	 * make a record of it to help teo_select() decide whether or not
-	 * to stop the tick.  This effectively adds an extra hits-only bin
-	 * beyond the last state-related one.
-	 */
-	if (target_residency_ns < TICK_NSEC) {
-		cpu_data->tick_hits -= cpu_data->tick_hits >> DECAY_SHIFT;
-
-		cpu_data->total += cpu_data->tick_hits;
-
-		if (TICK_NSEC <= cpu_data->sleep_length_ns) {
-			idx_timer = drv->state_count;
-			if (TICK_NSEC <= measured_ns) {
-				cpu_data->tick_hits += PULSE;
-				goto end;
-			}
-		}
-	}
-
+	cpu_data->tick_intercepts -= cpu_data->tick_intercepts >> DECAY_SHIFT;
 	/*
 	 * If the measured idle duration falls into the same bin as the sleep
 	 * length, this is a "hit", so update the "hits" metric for that bin.
 	 * Otherwise, update the "intercepts" metric for the bin fallen into by
 	 * the measured idle duration.
 	 */
-	if (idx_timer == idx_duration)
+	if (idx_timer == idx_duration) {
 		cpu_data->state_bins[idx_timer].hits += PULSE;
-	else
+	} else {
 		cpu_data->state_bins[idx_duration].intercepts += PULSE;
+		if (TICK_NSEC <= measured_ns)
+			cpu_data->tick_intercepts += PULSE;
+	}
 
-end:
+	cpu_data->total -= cpu_data->total >> DECAY_SHIFT;
 	cpu_data->total += PULSE;
 }
 
@@ -285,14 +271,12 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 	ktime_t delta_tick = TICK_NSEC / 2;
-	unsigned int tick_intercept_sum = 0;
 	unsigned int idx_intercept_sum = 0;
 	unsigned int intercept_sum = 0;
 	unsigned int idx_hit_sum = 0;
 	unsigned int hit_sum = 0;
 	int constraint_idx = 0;
 	int idx0 = 0, idx = -1;
-	int prev_intercept_idx;
 	s64 duration_ns;
 	int i;
 
@@ -301,10 +285,14 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		dev->last_state_idx = -1;
 	}
 
-	cpu_data->time_span_ns = local_clock();
 	/*
-	 * Set the expected sleep length to infinity in case of an early
-	 * return.
+	 * Set the sleep length to infinity in case the invocation of
+	 * tick_nohz_get_sleep_length() below is skipped, in which case it won't
+	 * be known whether or not the subsequent wakeup is caused by a timer.
+	 * It is generally fine to count the wakeup as an intercept then, except
+	 * for the cases when the CPU is mostly woken up by timers and there may
+	 * be opportunities to ask for a deeper idle state when no imminent
+	 * timers are scheduled which may be missed.
 	 */
 	cpu_data->sleep_length_ns = KTIME_MAX;
 
@@ -360,17 +348,13 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		goto end;
 	}
 
-	tick_intercept_sum = intercept_sum +
-			cpu_data->state_bins[drv->state_count-1].intercepts;
-
 	/*
 	 * If the sum of the intercepts metric for all of the idle states
 	 * shallower than the current candidate one (idx) is greater than the
 	 * sum of the intercepts and hits metrics for the candidate state and
-	 * all of the deeper states a shallower idle state is likely to be a
+	 * all of the deeper states, a shallower idle state is likely to be a
 	 * better choice.
 	 */
-	prev_intercept_idx = idx;
 	if (2 * idx_intercept_sum > cpu_data->total - idx_hit_sum) {
 		int first_suitable_idx = idx;
 
@@ -396,41 +380,38 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 				 * first enabled state that is deep enough.
 				 */
 				if (teo_state_ok(i, drv) &&
-				    !dev->states_usage[i].disable)
+				    !dev->states_usage[i].disable) {
 					idx = i;
-				else
-					idx = first_suitable_idx;
-
+					break;
+				}
+				idx = first_suitable_idx;
 				break;
 			}
 
 			if (dev->states_usage[i].disable)
 				continue;
 
-			if (!teo_state_ok(i, drv)) {
+			if (teo_state_ok(i, drv)) {
 				/*
-				 * The current state is too shallow, but if an
-				 * alternative candidate state has been found,
-				 * it may still turn out to be a better choice.
+				 * The current state is deep enough, but still
+				 * there may be a better one.
 				 */
-				if (first_suitable_idx != idx)
-					continue;
-
-				break;
+				first_suitable_idx = i;
+				continue;
 			}
 
-			first_suitable_idx = i;
+			/*
+			 * The current state is too shallow, so if no suitable
+			 * states other than the initial candidate have been
+			 * found, give up (the remaining states to check are
+			 * shallower still), but otherwise the first suitable
+			 * state other than the initial candidate may turn out
+			 * to be preferable.
+			 */
+			if (first_suitable_idx == idx)
+				break;
 		}
 	}
-	if (!idx && prev_intercept_idx) {
-		/*
-		 * We have to query the sleep length here otherwise we don't
-		 * know after wakeup if our guess was correct.
-		 */
-		duration_ns = tick_nohz_get_sleep_length(&delta_tick);
-		cpu_data->sleep_length_ns = duration_ns;
-		goto out_tick;
-	}
 
 	/*
 	 * If there is a latency constraint, it may be necessary to select an
@@ -440,24 +421,39 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		idx = constraint_idx;
 
 	/*
-	 * Skip the timers check if state 0 is the current candidate one,
-	 * because an immediate non-timer wakeup is expected in that case.
+	 * If either the candidate state is state 0 or its target residency is
+	 * low enough, there is basically nothing more to do, but if the sleep
+	 * length is not updated, the subsequent wakeup will be counted as an
+	 * "intercept" which may be problematic in the cases when timer wakeups
+	 * are dominant.  Namely, it may effectively prevent deeper idle states
+	 * from being selected at one point even if no imminent timers are
+	 * scheduled.
+	 *
+	 * However, frequent timers in the RESIDENCY_THRESHOLD_NS range on one
+	 * CPU are unlikely (user space has a default 50 us slack value for
+	 * hrtimers and there are relatively few timers with a lower deadline
+	 * value in the kernel), and even if they did happen, the potential
+	 * benefit from using a deep idle state in that case would be
+	 * questionable anyway for latency reasons.  Thus if the measured idle
+	 * duration falls into that range in the majority of cases, assume
+	 * non-timer wakeups to be dominant and skip updating the sleep length
+	 * to reduce latency.
+	 *
+	 * Also, if the latency constraint is sufficiently low, it will force
+	 * shallow idle states regardless of the wakeup type, so the sleep
+	 * length need not be known in that case.
 	 */
-	if (!idx)
-		goto out_tick;
-
-	/*
-	 * If state 0 is a polling one, check if the target residency of
-	 * the current candidate state is low enough and skip the timers
-	 * check in that case too.
-	 */
-	if ((drv->states[0].flags & CPUIDLE_FLAG_POLLING) &&
-	    drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS)
+	if ((!idx || drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS) &&
+	    (2 * cpu_data->short_idles >= cpu_data->total ||
+	     latency_req < LATENCY_THRESHOLD_NS))
 		goto out_tick;
 
 	duration_ns = tick_nohz_get_sleep_length(&delta_tick);
 	cpu_data->sleep_length_ns = duration_ns;
 
+	if (!idx)
+		goto out_tick;
+
 	/*
 	 * If the closest expected timer is before the target residency of the
 	 * candidate state, a shallower one needs to be found.
@@ -474,7 +470,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	 * total wakeup events, do not stop the tick.
 	 */
 	if (drv->states[idx].target_residency_ns < TICK_NSEC &&
-	    tick_intercept_sum > cpu_data->total / 2 + cpu_data->total / 8)
+	    cpu_data->tick_intercepts > cpu_data->total / 2 + cpu_data->total / 8)
 		duration_ns = TICK_NSEC / 2;
 
 end:
@@ -511,17 +507,16 @@ static void teo_reflect(struct cpuidle_device *dev, int state)
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 
 	dev->last_state_idx = state;
-	/*
-	 * If the wakeup was not "natural", but triggered by one of the safety
-	 * nets, assume that the CPU might have been idle for the entire sleep
-	 * length time.
-	 */
 	if (dev->poll_time_limit ||
 	    (tick_nohz_idle_got_tick() && cpu_data->sleep_length_ns > TICK_NSEC)) {
+		/*
+		 * The wakeup was not "genuine", but triggered by one of the
+		 * safety nets.
+		 */
 		dev->poll_time_limit = false;
-		cpu_data->time_span_ns = cpu_data->sleep_length_ns;
+		cpu_data->artificial_wakeup = true;
 	} else {
-		cpu_data->time_span_ns = local_clock() - cpu_data->time_span_ns;
+		cpu_data->artificial_wakeup = false;
 	}
 }
 
diff --git a/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c
index c8241f5a0a26..f20ae7e35a0d 100644
--- a/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c
+++ b/drivers/crypto/intel/qat/qat_common/adf_tl_debugfs.c
@@ -473,22 +473,6 @@ unlock_and_exit:
 }
 DEFINE_SHOW_STORE_ATTRIBUTE(tl_control);
 
-static int get_rp_index_from_file(const struct file *f, u8 *rp_id, u8 rp_num)
-{
-	char alpha;
-	u8 index;
-	int ret;
-
-	ret = sscanf(f->f_path.dentry->d_name.name, ADF_TL_RP_REGS_FNAME, &alpha);
-	if (ret != 1)
-		return -EINVAL;
-
-	index = ADF_TL_DBG_RP_INDEX_ALPHA(alpha);
-	*rp_id = index;
-
-	return 0;
-}
-
 static int adf_tl_dbg_change_rp_index(struct adf_accel_dev *accel_dev,
 				      unsigned int new_rp_num,
 				      unsigned int rp_regs_index)
@@ -611,18 +595,11 @@ static int tl_rp_data_show(struct seq_file *s, void *unused)
 {
 	struct adf_accel_dev *accel_dev = s->private;
 	u8 rp_regs_index;
-	u8 max_rp;
-	int ret;
 
 	if (!accel_dev)
 		return -EINVAL;
 
-	max_rp = GET_TL_DATA(accel_dev).max_rp;
-	ret = get_rp_index_from_file(s->file, &rp_regs_index, max_rp);
-	if (ret) {
-		dev_dbg(&GET_DEV(accel_dev), "invalid RP data file name\n");
-		return ret;
-	}
+	rp_regs_index = debugfs_get_aux_num(s->file);
 
 	return tl_print_rp_data(accel_dev, s, rp_regs_index);
 }
@@ -635,7 +612,6 @@ static ssize_t tl_rp_data_write(struct file *file, const char __user *userbuf,
 	struct adf_telemetry *telemetry;
 	unsigned int new_rp_num;
 	u8 rp_regs_index;
-	u8 max_rp;
 	int ret;
 
 	accel_dev = seq_f->private;
@@ -643,15 +619,10 @@ static ssize_t tl_rp_data_write(struct file *file, const char __user *userbuf,
 		return -EINVAL;
 
 	telemetry = accel_dev->telemetry;
-	max_rp = GET_TL_DATA(accel_dev).max_rp;
 
 	mutex_lock(&telemetry->wr_lock);
 
-	ret = get_rp_index_from_file(file, &rp_regs_index, max_rp);
-	if (ret) {
-		dev_dbg(&GET_DEV(accel_dev), "invalid RP data file name\n");
-		goto unlock_and_exit;
-	}
+	rp_regs_index = debugfs_get_aux_num(file);
 
 	ret = kstrtou32_from_user(userbuf, count, 10, &new_rp_num);
 	if (ret)
@@ -689,7 +660,8 @@ void adf_tl_dbgfs_add(struct adf_accel_dev *accel_dev)
 	for (i = 0; i < max_rp; i++) {
 		snprintf(name, sizeof(name), ADF_TL_RP_REGS_FNAME,
 			 ADF_TL_DBG_RP_ALPHA_INDEX(i));
-		debugfs_create_file(name, 0644, dir, accel_dev, &tl_rp_data_fops);
+		debugfs_create_file_aux_num(name, 0644, dir, accel_dev, i,
+					    &tl_rp_data_fops);
 	}
 }
 
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 28edd5822486..50e6a45b30ba 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -703,7 +703,7 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld)
 	return 0;
 }
 
-static int commit_reap(struct device *dev, const void *data)
+static int commit_reap(struct device *dev, void *data)
 {
 	struct cxl_port *port = to_cxl_port(dev->parent);
 	struct cxl_decoder *cxld;
diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 9d58ab9d33c5..013b869b66cb 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -252,9 +252,9 @@ static int devm_cxl_enable_mem(struct device *host, struct cxl_dev_state *cxlds)
 }
 
 /* require dvsec ranges to be covered by a locked platform window */
-static int dvsec_range_allowed(struct device *dev, void *arg)
+static int dvsec_range_allowed(struct device *dev, const void *arg)
 {
-	struct range *dev_range = arg;
+	const struct range *dev_range = arg;
 	struct cxl_decoder *cxld;
 
 	if (!is_root_decoder(dev))
@@ -291,11 +291,11 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm)
 	return devm_add_action_or_reset(host, disable_hdm, cxlhdm);
 }
 
-int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
+int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds,
 			struct cxl_endpoint_dvsec_info *info)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
+	struct device *dev = cxlds->dev;
 	int hdm_count, rc, i, ranges = 0;
 	int d = cxlds->cxl_dvsec;
 	u16 cap, ctrl;
diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index b3378d3f6acb..8853415c106a 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -51,17 +51,6 @@ struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev)
 }
 EXPORT_SYMBOL_NS_GPL(to_cxl_nvdimm_bridge, "CXL");
 
-bool is_cxl_nvdimm_bridge(struct device *dev)
-{
-	return dev->type == &cxl_nvdimm_bridge_type;
-}
-EXPORT_SYMBOL_NS_GPL(is_cxl_nvdimm_bridge, "CXL");
-
-static int match_nvdimm_bridge(struct device *dev, void *data)
-{
-	return is_cxl_nvdimm_bridge(dev);
-}
-
 /**
  * cxl_find_nvdimm_bridge() - find a bridge device relative to a port
  * @port: any descendant port of an nvdimm-bridge associated
@@ -75,7 +64,9 @@ struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port)
 	if (!cxl_root)
 		return NULL;
 
-	dev = device_find_child(&cxl_root->port.dev, NULL, match_nvdimm_bridge);
+	dev = device_find_child(&cxl_root->port.dev,
+				&cxl_nvdimm_bridge_type,
+				device_match_type);
 
 	if (!dev)
 		return NULL;
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index b98b1ccffd1c..e8d11a988fd9 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -778,7 +778,7 @@ out:
 	return rc;
 }
 
-static int check_commit_order(struct device *dev, const void *data)
+static int check_commit_order(struct device *dev, void *data)
 {
 	struct cxl_decoder *cxld = to_cxl_decoder(dev);
 
@@ -792,7 +792,7 @@ static int check_commit_order(struct device *dev, const void *data)
 	return 0;
 }
 
-static int match_free_decoder(struct device *dev, void *data)
+static int match_free_decoder(struct device *dev, const void *data)
 {
 	struct cxl_port *port = to_cxl_port(dev->parent);
 	struct cxl_decoder *cxld;
@@ -824,9 +824,9 @@ static int match_free_decoder(struct device *dev, void *data)
 	return 1;
 }
 
-static int match_auto_decoder(struct device *dev, void *data)
+static int match_auto_decoder(struct device *dev, const void *data)
 {
-	struct cxl_region_params *p = data;
+	const struct cxl_region_params *p = data;
 	struct cxl_decoder *cxld;
 	struct range *r;
 
@@ -1733,10 +1733,12 @@ static struct cxl_port *next_port(struct cxl_port *port)
 	return port->parent_dport->port;
 }
 
-static int match_switch_decoder_by_range(struct device *dev, void *data)
+static int match_switch_decoder_by_range(struct device *dev,
+					 const void *data)
 {
 	struct cxl_switch_decoder *cxlsd;
-	struct range *r1, *r2 = data;
+	const struct range *r1, *r2 = data;
+
 
 	if (!is_switch_decoder(dev))
 		return 0;
@@ -3187,9 +3189,10 @@ err:
 	return rc;
 }
 
-static int match_root_decoder_by_range(struct device *dev, void *data)
+static int match_root_decoder_by_range(struct device *dev,
+				       const void *data)
 {
-	struct range *r1, *r2 = data;
+	const struct range *r1, *r2 = data;
 	struct cxl_root_decoder *cxlrd;
 
 	if (!is_root_decoder(dev))
@@ -3200,11 +3203,11 @@ static int match_root_decoder_by_range(struct device *dev, void *data)
 	return range_contains(r1, r2);
 }
 
-static int match_region_by_range(struct device *dev, void *data)
+static int match_region_by_range(struct device *dev, const void *data)
 {
 	struct cxl_region_params *p;
 	struct cxl_region *cxlr;
-	struct range *r = data;
+	const struct range *r = data;
 	int rc = 0;
 
 	if (!is_cxl_region(dev))
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index 59cb35b40c7e..117c2e94c761 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -289,21 +289,17 @@ static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi,
 	return true;
 }
 
-/**
- * cxl_find_regblock_instance() - Locate a register block by type / index
- * @pdev: The CXL PCI device to enumerate.
- * @type: Register Block Indicator id
- * @map: Enumeration output, clobbered on error
- * @index: Index into which particular instance of a regblock wanted in the
- *	   order found in register locator DVSEC.
- *
- * Return: 0 if register block enumerated, negative error code otherwise
+/*
+ * __cxl_find_regblock_instance() - Locate a register block or count instances by type / index
+ * Use CXL_INSTANCES_COUNT for @index if counting instances.
  *
- * A CXL DVSEC may point to one or more register blocks, search for them
- * by @type and @index.
+ * __cxl_find_regblock_instance() may return:
+ * 0 - if register block enumerated.
+ * >= 0 - if counting instances.
+ * < 0 - error code otherwise.
  */
-int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
-			       struct cxl_register_map *map, int index)
+static int __cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
+					struct cxl_register_map *map, int index)
 {
 	u32 regloc_size, regblocks;
 	int instance = 0;
@@ -342,8 +338,30 @@ int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
 	}
 
 	map->resource = CXL_RESOURCE_NONE;
+	if (index == CXL_INSTANCES_COUNT)
+		return instance;
+
 	return -ENODEV;
 }
+
+/**
+ * cxl_find_regblock_instance() - Locate a register block by type / index
+ * @pdev: The CXL PCI device to enumerate.
+ * @type: Register Block Indicator id
+ * @map: Enumeration output, clobbered on error
+ * @index: Index into which particular instance of a regblock wanted in the
+ *	   order found in register locator DVSEC.
+ *
+ * Return: 0 if register block enumerated, negative error code otherwise
+ *
+ * A CXL DVSEC may point to one or more register blocks, search for them
+ * by @type and @index.
+ */
+int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
+			       struct cxl_register_map *map, unsigned int index)
+{
+	return __cxl_find_regblock_instance(pdev, type, map, index);
+}
 EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL");
 
 /**
@@ -360,7 +378,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL");
 int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type,
 		      struct cxl_register_map *map)
 {
-	return cxl_find_regblock_instance(pdev, type, map, 0);
+	return __cxl_find_regblock_instance(pdev, type, map, 0);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL");
 
@@ -371,19 +389,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL");
  *
  * Some regblocks may be repeated. Count how many instances.
  *
- * Return: count of matching regblocks.
+ * Return: non-negative count of matching regblocks, negative error code otherwise.
  */
 int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type)
 {
 	struct cxl_register_map map;
-	int rc, count = 0;
 
-	while (1) {
-		rc = cxl_find_regblock_instance(pdev, type, &map, count);
-		if (rc)
-			return count;
-		count++;
-	}
+	return __cxl_find_regblock_instance(pdev, type, &map, CXL_INSTANCES_COUNT);
 }
 EXPORT_SYMBOL_NS_GPL(cxl_count_regblock, "CXL");
 
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index 8389a94adb1a..cea706b683b5 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -166,11 +166,13 @@ TRACE_EVENT(cxl_overflow,
 #define CXL_EVENT_RECORD_FLAG_MAINT_NEEDED	BIT(3)
 #define CXL_EVENT_RECORD_FLAG_PERF_DEGRADED	BIT(4)
 #define CXL_EVENT_RECORD_FLAG_HW_REPLACE	BIT(5)
+#define CXL_EVENT_RECORD_FLAG_MAINT_OP_SUB_CLASS_VALID	BIT(6)
 #define show_hdr_flags(flags)	__print_flags(flags, " | ",			   \
 	{ CXL_EVENT_RECORD_FLAG_PERMANENT,	"PERMANENT_CONDITION"		}, \
 	{ CXL_EVENT_RECORD_FLAG_MAINT_NEEDED,	"MAINTENANCE_NEEDED"		}, \
 	{ CXL_EVENT_RECORD_FLAG_PERF_DEGRADED,	"PERFORMANCE_DEGRADED"		}, \
-	{ CXL_EVENT_RECORD_FLAG_HW_REPLACE,	"HARDWARE_REPLACEMENT_NEEDED"	}  \
+	{ CXL_EVENT_RECORD_FLAG_HW_REPLACE,	"HARDWARE_REPLACEMENT_NEEDED"	},  \
+	{ CXL_EVENT_RECORD_FLAG_MAINT_OP_SUB_CLASS_VALID,	"MAINT_OP_SUB_CLASS_VALID" }	\
 )
 
 /*
@@ -197,7 +199,8 @@ TRACE_EVENT(cxl_overflow,
 	__field(u16, hdr_related_handle)			\
 	__field(u64, hdr_timestamp)				\
 	__field(u8, hdr_length)					\
-	__field(u8, hdr_maint_op_class)
+	__field(u8, hdr_maint_op_class)				\
+	__field(u8, hdr_maint_op_sub_class)
 
 #define CXL_EVT_TP_fast_assign(cxlmd, l, hdr)					\
 	__assign_str(memdev);				\
@@ -209,17 +212,19 @@ TRACE_EVENT(cxl_overflow,
 	__entry->hdr_handle = le16_to_cpu((hdr).handle);			\
 	__entry->hdr_related_handle = le16_to_cpu((hdr).related_handle);	\
 	__entry->hdr_timestamp = le64_to_cpu((hdr).timestamp);			\
-	__entry->hdr_maint_op_class = (hdr).maint_op_class
+	__entry->hdr_maint_op_class = (hdr).maint_op_class;			\
+	__entry->hdr_maint_op_sub_class = (hdr).maint_op_sub_class
 
 #define CXL_EVT_TP_printk(fmt, ...) \
 	TP_printk("memdev=%s host=%s serial=%lld log=%s : time=%llu uuid=%pUb "	\
 		"len=%d flags='%s' handle=%x related_handle=%x "		\
-		"maint_op_class=%u : " fmt,					\
+		"maint_op_class=%u maint_op_sub_class=%u : " fmt,		\
 		__get_str(memdev), __get_str(host), __entry->serial,		\
 		cxl_event_log_type_str(__entry->log),				\
 		__entry->hdr_timestamp, &__entry->hdr_uuid, __entry->hdr_length,\
 		show_hdr_flags(__entry->hdr_flags), __entry->hdr_handle,	\
 		__entry->hdr_related_handle, __entry->hdr_maint_op_class,	\
+		__entry->hdr_maint_op_sub_class,	\
 		##__VA_ARGS__)
 
 TRACE_EVENT(cxl_generic_event,
@@ -264,8 +269,30 @@ TRACE_EVENT(cxl_generic_event,
 )
 
 /*
+ * Component ID Format
+ * CXL 3.1 section 8.2.9.2.1; Table 8-44
+ */
+#define CXL_PLDM_COMPONENT_ID_ENTITY_VALID	BIT(0)
+#define CXL_PLDM_COMPONENT_ID_RES_VALID		BIT(1)
+
+#define show_comp_id_pldm_flags(flags)  __print_flags(flags, " | ",	\
+	{ CXL_PLDM_COMPONENT_ID_ENTITY_VALID,   "PLDM Entity ID" },	\
+	{ CXL_PLDM_COMPONENT_ID_RES_VALID,      "Resource ID" }		\
+)
+
+#define show_pldm_entity_id(flags, valid_comp_id, valid_id_format, comp_id)	\
+	(flags & valid_comp_id && flags & valid_id_format) ?			\
+	(comp_id[0] & CXL_PLDM_COMPONENT_ID_ENTITY_VALID) ?			\
+	__print_hex(&comp_id[1], 6) : "0x00" : "0x00"
+
+#define show_pldm_resource_id(flags, valid_comp_id, valid_id_format, comp_id)	\
+	(flags & valid_comp_id && flags & valid_id_format) ?			\
+	(comp_id[0] & CXL_PLDM_COMPONENT_ID_RES_VALID) ?			\
+	__print_hex(&comp_id[7], 4) : "0x00" : "0x00"
+
+/*
  * General Media Event Record - GMER
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45
  */
 #define CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT		BIT(0)
 #define CXL_GMER_EVT_DESC_THRESHOLD_EVENT		BIT(1)
@@ -279,10 +306,18 @@ TRACE_EVENT(cxl_generic_event,
 #define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR			0x00
 #define CXL_GMER_MEM_EVT_TYPE_INV_ADDR			0x01
 #define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR		0x02
-#define show_gmer_mem_event_type(type)	__print_symbolic(type,			\
-	{ CXL_GMER_MEM_EVT_TYPE_ECC_ERROR,		"ECC Error" },		\
-	{ CXL_GMER_MEM_EVT_TYPE_INV_ADDR,		"Invalid Address" },	\
-	{ CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,	"Data Path Error" }	\
+#define CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION	0x03
+#define CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR	0x04
+#define CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE	0x05
+#define CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION		0x06
+#define show_gmer_mem_event_type(type)	__print_symbolic(type,				\
+	{ CXL_GMER_MEM_EVT_TYPE_ECC_ERROR,		"ECC Error" },			\
+	{ CXL_GMER_MEM_EVT_TYPE_INV_ADDR,		"Invalid Address" },		\
+	{ CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR,	"Data Path Error" },		\
+	{ CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION,	"TE State Violation" },		\
+	{ CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR,	"Scrub Media ECC Error" },	\
+	{ CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE,	"Adv Prog CME Counter Expiration" },	\
+	{ CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION,		"CKID Violation" }		\
 )
 
 #define CXL_GMER_TRANS_UNKNOWN				0x00
@@ -292,6 +327,8 @@ TRACE_EVENT(cxl_generic_event,
 #define CXL_GMER_TRANS_HOST_INJECT_POISON		0x04
 #define CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB		0x05
 #define CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT	0x06
+#define CXL_GMER_TRANS_INTERNAL_MEDIA_ECS		0x07
+#define CXL_GMER_TRANS_MEDIA_INITIALIZATION		0x08
 #define show_trans_type(type)	__print_symbolic(type,					\
 	{ CXL_GMER_TRANS_UNKNOWN,			"Unknown" },			\
 	{ CXL_GMER_TRANS_HOST_READ,			"Host Read" },			\
@@ -299,18 +336,57 @@ TRACE_EVENT(cxl_generic_event,
 	{ CXL_GMER_TRANS_HOST_SCAN_MEDIA,		"Host Scan Media" },		\
 	{ CXL_GMER_TRANS_HOST_INJECT_POISON,		"Host Inject Poison" },		\
 	{ CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB,		"Internal Media Scrub" },	\
-	{ CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT,	"Internal Media Management" }	\
+	{ CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT,	"Internal Media Management" },	\
+	{ CXL_GMER_TRANS_INTERNAL_MEDIA_ECS,		"Internal Media Error Check Scrub" },	\
+	{ CXL_GMER_TRANS_MEDIA_INITIALIZATION,		"Media Initialization" }	\
 )
 
 #define CXL_GMER_VALID_CHANNEL				BIT(0)
 #define CXL_GMER_VALID_RANK				BIT(1)
 #define CXL_GMER_VALID_DEVICE				BIT(2)
 #define CXL_GMER_VALID_COMPONENT			BIT(3)
+#define CXL_GMER_VALID_COMPONENT_ID_FORMAT		BIT(4)
 #define show_valid_flags(flags)	__print_flags(flags, "|",		   \
 	{ CXL_GMER_VALID_CHANNEL,			"CHANNEL"	}, \
 	{ CXL_GMER_VALID_RANK,				"RANK"		}, \
 	{ CXL_GMER_VALID_DEVICE,			"DEVICE"	}, \
-	{ CXL_GMER_VALID_COMPONENT,			"COMPONENT"	}  \
+	{ CXL_GMER_VALID_COMPONENT,			"COMPONENT"	}, \
+	{ CXL_GMER_VALID_COMPONENT_ID_FORMAT,		"COMPONENT PLDM FORMAT"	} \
+)
+
+#define CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA		BIT(0)
+#define CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED		BIT(1)
+#define show_cme_threshold_ev_flags(flags)	__print_flags(flags, "|",	\
+	{									\
+		CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA,			\
+		"Corrected Memory Errors in Multiple Media Components"		\
+	}, {									\
+		CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED,			\
+		"Exceeded Programmable Threshold"				\
+	}									\
+)
+
+#define CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED				0x00
+#define CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR		0x01
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR	0x02
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR	0x03
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR	0x04
+#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR			0x05
+#define show_mem_event_sub_type(sub_type)	__print_symbolic(sub_type,			\
+	{ CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" },				\
+	{ CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR, "Internal Datapath Error" },	\
+	{											\
+		CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR,			\
+		"Media Link Command Training Error"						\
+	}, {											\
+		CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR,			\
+		"Media Link Control Training Error"						\
+	}, {											\
+		CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR,			\
+		"Media Link Data Training Error"						\
+	}, {											\
+		CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR, "Media Link CRC Error"		\
+	}											\
 )
 
 TRACE_EVENT(cxl_general_media,
@@ -336,6 +412,9 @@ TRACE_EVENT(cxl_general_media,
 		__field(u16, validity_flags)
 		__field(u8, rank)
 		__field(u8, dpa_flags)
+		__field(u32, cme_count)
+		__field(u8, sub_type)
+		__field(u8, cme_threshold_ev_flags)
 		__string(region_name, cxlr ? dev_name(&cxlr->dev) : "")
 	),
 
@@ -350,6 +429,7 @@ TRACE_EVENT(cxl_general_media,
 		__entry->dpa &= CXL_DPA_MASK;
 		__entry->descriptor = rec->media_hdr.descriptor;
 		__entry->type = rec->media_hdr.type;
+		__entry->sub_type = rec->sub_type;
 		__entry->transaction_type = rec->media_hdr.transaction_type;
 		__entry->channel = rec->media_hdr.channel;
 		__entry->rank = rec->media_hdr.rank;
@@ -365,27 +445,40 @@ TRACE_EVENT(cxl_general_media,
 			__assign_str(region_name);
 			uuid_copy(&__entry->region_uuid, &uuid_null);
 		}
+		__entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags;
+		__entry->cme_count = get_unaligned_le24(rec->cme_count);
 	),
 
 	CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \
-		"descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \
-		"device=%x comp_id=%s validity_flags='%s' " \
-		"hpa=%llx region=%s region_uuid=%pUb",
+		"descriptor='%s' type='%s' sub_type='%s' " \
+		"transaction_type='%s' channel=%u rank=%u " \
+		"device=%x validity_flags='%s' " \
+		"comp_id=%s comp_id_pldm_valid_flags='%s' " \
+		"pldm_entity_id=%s pldm_resource_id=%s " \
+		"hpa=%llx region=%s region_uuid=%pUb " \
+		"cme_threshold_ev_flags='%s' cme_count=%u",
 		__entry->dpa, show_dpa_flags(__entry->dpa_flags),
 		show_event_desc_flags(__entry->descriptor),
 		show_gmer_mem_event_type(__entry->type),
+		show_mem_event_sub_type(__entry->sub_type),
 		show_trans_type(__entry->transaction_type),
 		__entry->channel, __entry->rank, __entry->device,
-		__print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
 		show_valid_flags(__entry->validity_flags),
-		__entry->hpa, __get_str(region_name), &__entry->region_uuid
+		__print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
+		show_comp_id_pldm_flags(__entry->comp_id[0]),
+		show_pldm_entity_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT,
+				    CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+		show_pldm_resource_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT,
+				      CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+		__entry->hpa, __get_str(region_name), &__entry->region_uuid,
+		show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags), __entry->cme_count
 	)
 );
 
 /*
  * DRAM Event Record - DER
  *
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46
  */
 /*
  * DRAM Event Record defines many fields the same as the General Media Event
@@ -395,11 +488,17 @@ TRACE_EVENT(cxl_general_media,
 #define CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR	0x01
 #define CXL_DER_MEM_EVT_TYPE_INV_ADDR			0x02
 #define CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR		0x03
-#define show_dram_mem_event_type(type)  __print_symbolic(type,				\
-	{ CXL_DER_MEM_EVT_TYPE_ECC_ERROR,		"ECC Error" },			\
-	{ CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR,	"Scrub Media ECC Error" },	\
-	{ CXL_DER_MEM_EVT_TYPE_INV_ADDR,		"Invalid Address" },		\
-	{ CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR,		"Data Path Error" }		\
+#define CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION	0x04
+#define CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE	0x05
+#define CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION		0x06
+#define show_dram_mem_event_type(type)	__print_symbolic(type,					\
+	{ CXL_DER_MEM_EVT_TYPE_ECC_ERROR,		"ECC Error" },				\
+	{ CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR,	"Scrub Media ECC Error" },		\
+	{ CXL_DER_MEM_EVT_TYPE_INV_ADDR,		"Invalid Address" },			\
+	{ CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR,		"Data Path Error" },			\
+	{ CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION,	"TE State Violation" },			\
+	{ CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE,	"Adv Prog CME Counter Expiration" },	\
+	{ CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION,		"CKID Violation" }			\
 )
 
 #define CXL_DER_VALID_CHANNEL				BIT(0)
@@ -410,15 +509,21 @@ TRACE_EVENT(cxl_general_media,
 #define CXL_DER_VALID_ROW				BIT(5)
 #define CXL_DER_VALID_COLUMN				BIT(6)
 #define CXL_DER_VALID_CORRECTION_MASK			BIT(7)
-#define show_dram_valid_flags(flags)	__print_flags(flags, "|",			   \
-	{ CXL_DER_VALID_CHANNEL,			"CHANNEL"		}, \
-	{ CXL_DER_VALID_RANK,				"RANK"			}, \
-	{ CXL_DER_VALID_NIBBLE,				"NIBBLE"		}, \
-	{ CXL_DER_VALID_BANK_GROUP,			"BANK GROUP"		}, \
-	{ CXL_DER_VALID_BANK,				"BANK"			}, \
-	{ CXL_DER_VALID_ROW,				"ROW"			}, \
-	{ CXL_DER_VALID_COLUMN,				"COLUMN"		}, \
-	{ CXL_DER_VALID_CORRECTION_MASK,		"CORRECTION MASK"	}  \
+#define CXL_DER_VALID_COMPONENT				BIT(8)
+#define CXL_DER_VALID_COMPONENT_ID_FORMAT		BIT(9)
+#define CXL_DER_VALID_SUB_CHANNEL			BIT(10)
+#define show_dram_valid_flags(flags)	__print_flags(flags, "|",			\
+	{ CXL_DER_VALID_CHANNEL,			"CHANNEL"		},	\
+	{ CXL_DER_VALID_RANK,				"RANK"			},	\
+	{ CXL_DER_VALID_NIBBLE,				"NIBBLE"		},	\
+	{ CXL_DER_VALID_BANK_GROUP,			"BANK GROUP"		},	\
+	{ CXL_DER_VALID_BANK,				"BANK"			},	\
+	{ CXL_DER_VALID_ROW,				"ROW"			},	\
+	{ CXL_DER_VALID_COLUMN,				"COLUMN"		},	\
+	{ CXL_DER_VALID_CORRECTION_MASK,		"CORRECTION MASK"	},	\
+	{ CXL_DER_VALID_COMPONENT,			"COMPONENT"		},	\
+	{ CXL_DER_VALID_COMPONENT_ID_FORMAT,		"COMPONENT PLDM FORMAT"	},	\
+	{ CXL_DER_VALID_SUB_CHANNEL,			"SUB CHANNEL"		}	\
 )
 
 TRACE_EVENT(cxl_dram,
@@ -447,6 +552,12 @@ TRACE_EVENT(cxl_dram,
 		__field(u8, bank_group)	/* Out of order to pack trace record */
 		__field(u8, bank)	/* Out of order to pack trace record */
 		__field(u8, dpa_flags)	/* Out of order to pack trace record */
+		/* Following are out of order to pack trace record */
+		__array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE)
+		__field(u32, cvme_count)
+		__field(u8, sub_type)
+		__field(u8, sub_channel)
+		__field(u8, cme_threshold_ev_flags)
 		__string(region_name, cxlr ? dev_name(&cxlr->dev) : "")
 	),
 
@@ -460,6 +571,7 @@ TRACE_EVENT(cxl_dram,
 		__entry->dpa &= CXL_DPA_MASK;
 		__entry->descriptor = rec->media_hdr.descriptor;
 		__entry->type = rec->media_hdr.type;
+		__entry->sub_type = rec->sub_type;
 		__entry->transaction_type = rec->media_hdr.transaction_type;
 		__entry->validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags);
 		__entry->channel = rec->media_hdr.channel;
@@ -479,30 +591,47 @@ TRACE_EVENT(cxl_dram,
 			__assign_str(region_name);
 			uuid_copy(&__entry->region_uuid, &uuid_null);
 		}
+		memcpy(__entry->comp_id, &rec->component_id,
+		       CXL_EVENT_GEN_MED_COMP_ID_SIZE);
+		__entry->sub_channel = rec->sub_channel;
+		__entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags;
+		__entry->cvme_count = get_unaligned_le24(rec->cvme_count);
 	),
 
-	CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \
+	CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' sub_type='%s' " \
 		"transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \
 		"bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \
 		"validity_flags='%s' " \
-		"hpa=%llx region=%s region_uuid=%pUb",
+		"comp_id=%s comp_id_pldm_valid_flags='%s' " \
+		"pldm_entity_id=%s pldm_resource_id=%s " \
+		"hpa=%llx region=%s region_uuid=%pUb " \
+		"sub_channel=%u cme_threshold_ev_flags='%s' cvme_count=%u",
 		__entry->dpa, show_dpa_flags(__entry->dpa_flags),
 		show_event_desc_flags(__entry->descriptor),
 		show_dram_mem_event_type(__entry->type),
+		show_mem_event_sub_type(__entry->sub_type),
 		show_trans_type(__entry->transaction_type),
 		__entry->channel, __entry->rank, __entry->nibble_mask,
 		__entry->bank_group, __entry->bank,
 		__entry->row, __entry->column,
 		__print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE),
 		show_dram_valid_flags(__entry->validity_flags),
-		__entry->hpa, __get_str(region_name), &__entry->region_uuid
+		__print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
+		show_comp_id_pldm_flags(__entry->comp_id[0]),
+		show_pldm_entity_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT,
+				    CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+		show_pldm_resource_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT,
+				      CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+		__entry->hpa, __get_str(region_name), &__entry->region_uuid,
+		__entry->sub_channel, show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags),
+		__entry->cvme_count
 	)
 );
 
 /*
  * Memory Module Event Record - MMER
  *
- * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45
+ * CXL res 3.1 section 8.2.9.2.1.3; Table 8-47
  */
 #define CXL_MMER_HEALTH_STATUS_CHANGE		0x00
 #define CXL_MMER_MEDIA_STATUS_CHANGE		0x01
@@ -510,27 +639,35 @@ TRACE_EVENT(cxl_dram,
 #define CXL_MMER_TEMP_CHANGE			0x03
 #define CXL_MMER_DATA_PATH_ERROR		0x04
 #define CXL_MMER_LSA_ERROR			0x05
+#define CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR	0x06
+#define CXL_MMER_MEMORY_MEDIA_FRU_ERROR		0x07
+#define CXL_MMER_POWER_MANAGEMENT_FAULT		0x08
 #define show_dev_evt_type(type)	__print_symbolic(type,			   \
 	{ CXL_MMER_HEALTH_STATUS_CHANGE,	"Health Status Change"	}, \
 	{ CXL_MMER_MEDIA_STATUS_CHANGE,		"Media Status Change"	}, \
 	{ CXL_MMER_LIFE_USED_CHANGE,		"Life Used Change"	}, \
 	{ CXL_MMER_TEMP_CHANGE,			"Temperature Change"	}, \
 	{ CXL_MMER_DATA_PATH_ERROR,		"Data Path Error"	}, \
-	{ CXL_MMER_LSA_ERROR,			"LSA Error"		}  \
+	{ CXL_MMER_LSA_ERROR,			"LSA Error"		}, \
+	{ CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR,	"Unrecoverable Internal Sideband Bus Error"	}, \
+	{ CXL_MMER_MEMORY_MEDIA_FRU_ERROR,	"Memory Media FRU Error"	}, \
+	{ CXL_MMER_POWER_MANAGEMENT_FAULT,	"Power Management Fault"	}  \
 )
 
 /*
  * Device Health Information - DHI
  *
- * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100
+ * CXL res 3.1 section 8.2.9.9.3.1; Table 8-133
  */
 #define CXL_DHI_HS_MAINTENANCE_NEEDED				BIT(0)
 #define CXL_DHI_HS_PERFORMANCE_DEGRADED				BIT(1)
 #define CXL_DHI_HS_HW_REPLACEMENT_NEEDED			BIT(2)
+#define CXL_DHI_HS_MEM_CAPACITY_DEGRADED			BIT(3)
 #define show_health_status_flags(flags)	__print_flags(flags, "|",	   \
 	{ CXL_DHI_HS_MAINTENANCE_NEEDED,	"MAINTENANCE_NEEDED"	}, \
 	{ CXL_DHI_HS_PERFORMANCE_DEGRADED,	"PERFORMANCE_DEGRADED"	}, \
-	{ CXL_DHI_HS_HW_REPLACEMENT_NEEDED,	"REPLACEMENT_NEEDED"	}  \
+	{ CXL_DHI_HS_HW_REPLACEMENT_NEEDED,	"REPLACEMENT_NEEDED"	}, \
+	{ CXL_DHI_HS_MEM_CAPACITY_DEGRADED,	"MEM_CAPACITY_DEGRADED"	}  \
 )
 
 #define CXL_DHI_MS_NORMAL							0x00
@@ -584,6 +721,26 @@ TRACE_EVENT(cxl_dram,
 #define CXL_DHI_AS_COR_VOL_ERR_CNT(as)			((as & 0x10) >> 4)
 #define CXL_DHI_AS_COR_PER_ERR_CNT(as)			((as & 0x20) >> 5)
 
+#define CXL_MMER_VALID_COMPONENT			BIT(0)
+#define CXL_MMER_VALID_COMPONENT_ID_FORMAT		BIT(1)
+#define show_mem_module_valid_flags(flags)	__print_flags(flags, "|",	\
+	{ CXL_MMER_VALID_COMPONENT,		"COMPONENT" },			\
+	{ CXL_MMER_VALID_COMPONENT_ID_FORMAT,	"COMPONENT PLDM FORMAT"	}	\
+)
+#define CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED			0x00
+#define CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA		0x01
+#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA		0x02
+#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU		0x03
+#define show_dev_event_sub_type(sub_type)	__print_symbolic(sub_type,			\
+	{ CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED,		"Not Reported" },		\
+	{ CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA,	"Invalid Config Data" },	\
+	{ CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA,		"Unsupported Config Data" },	\
+	{											\
+		CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU,					\
+		"Unsupported Memory Media FRU"							\
+	}											\
+)
+
 TRACE_EVENT(cxl_memory_module,
 
 	TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log,
@@ -606,6 +763,9 @@ TRACE_EVENT(cxl_memory_module,
 		__field(u32, cor_per_err_cnt)
 		__field(s16, device_temp)
 		__field(u8, add_status)
+		__field(u8, event_sub_type)
+		__array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE)
+		__field(u16, validity_flags)
 	),
 
 	TP_fast_assign(
@@ -614,6 +774,7 @@ TRACE_EVENT(cxl_memory_module,
 
 		/* Memory Module Event */
 		__entry->event_type = rec->event_type;
+		__entry->event_sub_type = rec->event_sub_type;
 
 		/* Device Health Info */
 		__entry->health_status = rec->info.health_status;
@@ -624,13 +785,20 @@ TRACE_EVENT(cxl_memory_module,
 		__entry->cor_per_err_cnt = get_unaligned_le32(rec->info.cor_per_err_cnt);
 		__entry->device_temp = get_unaligned_le16(rec->info.device_temp);
 		__entry->add_status = rec->info.add_status;
+		__entry->validity_flags = get_unaligned_le16(rec->validity_flags);
+		memcpy(__entry->comp_id, &rec->component_id,
+		       CXL_EVENT_GEN_MED_COMP_ID_SIZE);
 	),
 
-	CXL_EVT_TP_printk("event_type='%s' health_status='%s' media_status='%s' " \
-		"as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \
+	CXL_EVT_TP_printk("event_type='%s' event_sub_type='%s' health_status='%s' " \
+		"media_status='%s' as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \
 		"as_cor_per_err_cnt=%s life_used=%u device_temp=%d " \
-		"dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u",
+		"dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u " \
+		"validity_flags='%s' " \
+		"comp_id=%s comp_id_pldm_valid_flags='%s' " \
+		"pldm_entity_id=%s pldm_resource_id=%s",
 		show_dev_evt_type(__entry->event_type),
+		show_dev_event_sub_type(__entry->event_sub_type),
 		show_health_status_flags(__entry->health_status),
 		show_media_status(__entry->media_status),
 		show_two_bit_status(CXL_DHI_AS_LIFE_USED(__entry->add_status)),
@@ -639,7 +807,14 @@ TRACE_EVENT(cxl_memory_module,
 		show_one_bit_status(CXL_DHI_AS_COR_PER_ERR_CNT(__entry->add_status)),
 		__entry->life_used, __entry->device_temp,
 		__entry->dirty_shutdown_cnt, __entry->cor_vol_err_cnt,
-		__entry->cor_per_err_cnt
+		__entry->cor_per_err_cnt,
+		show_mem_module_valid_flags(__entry->validity_flags),
+		__print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE),
+		show_comp_id_pldm_flags(__entry->comp_id[0]),
+		show_pldm_entity_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT,
+				    CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id),
+		show_pldm_resource_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT,
+				      CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id)
 	)
 );
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index f6015f24ad38..bbbaa0d0a670 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -302,10 +302,11 @@ int cxl_map_device_regs(const struct cxl_register_map *map,
 			struct cxl_device_regs *regs);
 int cxl_map_pmu_regs(struct cxl_register_map *map, struct cxl_pmu_regs *regs);
 
+#define CXL_INSTANCES_COUNT -1
 enum cxl_regloc_type;
 int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type);
 int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type,
-			       struct cxl_register_map *map, int index);
+			       struct cxl_register_map *map, unsigned int index);
 int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type,
 		      struct cxl_register_map *map);
 int cxl_setup_regs(struct cxl_register_map *map);
@@ -821,7 +822,8 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
 int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 				struct cxl_endpoint_dvsec_info *info);
 int devm_cxl_add_passthrough_decoder(struct cxl_port *port);
-int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
+struct cxl_dev_state;
+int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds,
 			struct cxl_endpoint_dvsec_info *info);
 
 bool is_cxl_region(struct device *dev);
@@ -864,7 +866,6 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host,
 						     struct cxl_port *port);
 struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev);
 bool is_cxl_nvdimm(struct device *dev);
-bool is_cxl_nvdimm_bridge(struct device *dev);
 int devm_cxl_add_nvdimm(struct cxl_port *parent_port, struct cxl_memdev *cxlmd);
 struct cxl_nvdimm_bridge *cxl_find_nvdimm_bridge(struct cxl_port *port);
 
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 6d94ff4a4f1a..a96e54c6259e 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -907,7 +907,8 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct cxl_dev_state *cxlds;
 	struct cxl_register_map map;
 	struct cxl_memdev *cxlmd;
-	int i, rc, pmu_count;
+	int rc, pmu_count;
+	unsigned int i;
 	bool irq_avail;
 
 	/*
@@ -1009,6 +1010,9 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return rc;
 
 	pmu_count = cxl_count_regblock(pdev, CXL_REGLOC_RBI_PMU);
+	if (pmu_count < 0)
+		return pmu_count;
+
 	for (i = 0; i < pmu_count; i++) {
 		struct cxl_pmu_regs pmu_regs;
 
diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 4c83f6a22e58..d2bfd1ff5492 100644
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -98,7 +98,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
 	struct cxl_port *root;
 	int rc;
 
-	rc = cxl_dvsec_rr_decode(cxlds->dev, port, &info);
+	rc = cxl_dvsec_rr_decode(cxlds, &info);
 	if (rc < 0)
 		return rc;
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e994d6e0779e..8afea2e23360 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -162,8 +162,8 @@ config DMA_SA11X0
 
 config DMA_SUN4I
 	tristate "Allwinner A10 DMA SoCs support"
-	depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I
-	default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I)
+	depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I || MACH_SUNIV
+	default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I || MACH_SUNIV)
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
@@ -740,8 +740,6 @@ source "drivers/dma/bestcomm/Kconfig"
 
 source "drivers/dma/mediatek/Kconfig"
 
-source "drivers/dma/ptdma/Kconfig"
-
 source "drivers/dma/qcom/Kconfig"
 
 source "drivers/dma/dw/Kconfig"
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 5b2a52f4f2ee..19ba465011a6 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -16,7 +16,6 @@ obj-$(CONFIG_DMATEST) += dmatest.o
 obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o
 obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o
 obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
-obj-$(CONFIG_AMD_PTDMA) += ptdma/
 obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_AT_XDMAC) += at_xdmac.o
diff --git a/drivers/dma/amd/Kconfig b/drivers/dma/amd/Kconfig
index 7d1f51d69675..00d874872a8f 100644
--- a/drivers/dma/amd/Kconfig
+++ b/drivers/dma/amd/Kconfig
@@ -1,4 +1,32 @@
 # SPDX-License-Identifier: GPL-2.0-only
+#
+
+config AMD_AE4DMA
+	tristate  "AMD AE4DMA Engine"
+	depends on (X86_64 || COMPILE_TEST) && PCI
+	depends on AMD_PTDMA
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the AMD AE4DMA controller. This controller
+	  provides DMA capabilities to perform high bandwidth memory to
+	  memory and IO copy operations. It performs DMA transfer through
+	  queue-based descriptor management. This DMA controller is intended
+	  to be used with AMD Non-Transparent Bridge devices and not for
+	  general purpose peripheral DMA.
+
+config AMD_PTDMA
+	tristate  "AMD PassThru DMA Engine"
+	depends on X86_64 && PCI
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the AMD PTDMA controller. This controller
+	  provides DMA capabilities to perform high bandwidth memory to
+	  memory and IO copy operations. It performs DMA transfer through
+	  queue-based descriptor management. This DMA controller is intended
+	  to be used with AMD Non-Transparent Bridge devices and not for
+	  general purpose peripheral DMA.
 
 config AMD_QDMA
 	tristate "AMD Queue-based DMA"
diff --git a/drivers/dma/amd/Makefile b/drivers/dma/amd/Makefile
index 37212be9364f..11278c06374d 100644
--- a/drivers/dma/amd/Makefile
+++ b/drivers/dma/amd/Makefile
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
+obj-$(CONFIG_AMD_AE4DMA) += ae4dma/
+obj-$(CONFIG_AMD_PTDMA) += ptdma/
 obj-$(CONFIG_AMD_QDMA) += qdma/
diff --git a/drivers/dma/amd/ae4dma/Makefile b/drivers/dma/amd/ae4dma/Makefile
new file mode 100644
index 000000000000..e918f85a80ec
--- /dev/null
+++ b/drivers/dma/amd/ae4dma/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# AMD AE4DMA driver
+#
+
+obj-$(CONFIG_AMD_AE4DMA) += ae4dma.o
+
+ae4dma-objs := ae4dma-dev.o
+
+ae4dma-$(CONFIG_PCI) += ae4dma-pci.o
diff --git a/drivers/dma/amd/ae4dma/ae4dma-dev.c b/drivers/dma/amd/ae4dma/ae4dma-dev.c
new file mode 100644
index 000000000000..8de3bef41b58
--- /dev/null
+++ b/drivers/dma/amd/ae4dma/ae4dma-dev.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD AE4DMA driver
+ *
+ * Copyright (c) 2024, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
+ */
+
+#include "ae4dma.h"
+
+static unsigned int max_hw_q = 1;
+module_param(max_hw_q, uint, 0444);
+MODULE_PARM_DESC(max_hw_q, "max hw queues supported by engine (any non-zero value, default: 1)");
+
+static void ae4_pending_work(struct work_struct *work)
+{
+	struct ae4_cmd_queue *ae4cmd_q = container_of(work, struct ae4_cmd_queue, p_work.work);
+	struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q;
+	struct pt_cmd *cmd;
+	u32 cridx;
+
+	for (;;) {
+		wait_event_interruptible(ae4cmd_q->q_w,
+					 ((atomic64_read(&ae4cmd_q->done_cnt)) <
+					   atomic64_read(&ae4cmd_q->intr_cnt)));
+
+		atomic64_inc(&ae4cmd_q->done_cnt);
+
+		mutex_lock(&ae4cmd_q->cmd_lock);
+		cridx = readl(cmd_q->reg_control + AE4_RD_IDX_OFF);
+		while ((ae4cmd_q->dridx != cridx) && !list_empty(&ae4cmd_q->cmd)) {
+			cmd = list_first_entry(&ae4cmd_q->cmd, struct pt_cmd, entry);
+			list_del(&cmd->entry);
+
+			ae4_check_status_error(ae4cmd_q, ae4cmd_q->dridx);
+			cmd->pt_cmd_callback(cmd->data, cmd->ret);
+
+			ae4cmd_q->q_cmd_count--;
+			ae4cmd_q->dridx = (ae4cmd_q->dridx + 1) % CMD_Q_LEN;
+
+			complete_all(&ae4cmd_q->cmp);
+		}
+		mutex_unlock(&ae4cmd_q->cmd_lock);
+	}
+}
+
+static irqreturn_t ae4_core_irq_handler(int irq, void *data)
+{
+	struct ae4_cmd_queue *ae4cmd_q = data;
+	struct pt_cmd_queue *cmd_q;
+	struct pt_device *pt;
+	u32 status;
+
+	cmd_q = &ae4cmd_q->cmd_q;
+	pt = cmd_q->pt;
+
+	pt->total_interrupts++;
+	atomic64_inc(&ae4cmd_q->intr_cnt);
+
+	status = readl(cmd_q->reg_control + AE4_INTR_STS_OFF);
+	if (status & BIT(0)) {
+		status &= GENMASK(31, 1);
+		writel(status, cmd_q->reg_control + AE4_INTR_STS_OFF);
+	}
+
+	wake_up(&ae4cmd_q->q_w);
+
+	return IRQ_HANDLED;
+}
+
+void ae4_destroy_work(struct ae4_device *ae4)
+{
+	struct ae4_cmd_queue *ae4cmd_q;
+	int i;
+
+	for (i = 0; i < ae4->cmd_q_count; i++) {
+		ae4cmd_q = &ae4->ae4cmd_q[i];
+
+		if (!ae4cmd_q->pws)
+			break;
+
+		cancel_delayed_work_sync(&ae4cmd_q->p_work);
+		destroy_workqueue(ae4cmd_q->pws);
+	}
+}
+
+int ae4_core_init(struct ae4_device *ae4)
+{
+	struct pt_device *pt = &ae4->pt;
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct device *dev = pt->dev;
+	struct pt_cmd_queue *cmd_q;
+	int i, ret = 0;
+
+	writel(max_hw_q, pt->io_regs);
+
+	for (i = 0; i < max_hw_q; i++) {
+		ae4cmd_q = &ae4->ae4cmd_q[i];
+		ae4cmd_q->id = ae4->cmd_q_count;
+		ae4->cmd_q_count++;
+
+		cmd_q = &ae4cmd_q->cmd_q;
+		cmd_q->pt = pt;
+
+		cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ);
+
+		ret = devm_request_irq(dev, ae4->ae4_irq[i], ae4_core_irq_handler, 0,
+				       dev_name(pt->dev), ae4cmd_q);
+		if (ret)
+			return ret;
+
+		cmd_q->qsize = Q_SIZE(sizeof(struct ae4dma_desc));
+
+		cmd_q->qbase = dmam_alloc_coherent(dev, cmd_q->qsize, &cmd_q->qbase_dma,
+						   GFP_KERNEL);
+		if (!cmd_q->qbase)
+			return -ENOMEM;
+	}
+
+	for (i = 0; i < ae4->cmd_q_count; i++) {
+		ae4cmd_q = &ae4->ae4cmd_q[i];
+
+		cmd_q = &ae4cmd_q->cmd_q;
+
+		cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ);
+
+		/* Update the device registers with queue information. */
+		writel(CMD_Q_LEN, cmd_q->reg_control + AE4_MAX_IDX_OFF);
+
+		cmd_q->qdma_tail = cmd_q->qbase_dma;
+		writel(lower_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_L_OFF);
+		writel(upper_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_H_OFF);
+
+		INIT_LIST_HEAD(&ae4cmd_q->cmd);
+		init_waitqueue_head(&ae4cmd_q->q_w);
+
+		ae4cmd_q->pws = alloc_ordered_workqueue("ae4dma_%d", WQ_MEM_RECLAIM, ae4cmd_q->id);
+		if (!ae4cmd_q->pws) {
+			ae4_destroy_work(ae4);
+			return -ENOMEM;
+		}
+		INIT_DELAYED_WORK(&ae4cmd_q->p_work, ae4_pending_work);
+		queue_delayed_work(ae4cmd_q->pws, &ae4cmd_q->p_work,  usecs_to_jiffies(100));
+
+		init_completion(&ae4cmd_q->cmp);
+	}
+
+	ret = pt_dmaengine_register(pt);
+	if (ret)
+		ae4_destroy_work(ae4);
+	else
+		ptdma_debugfs_setup(pt);
+
+	return ret;
+}
diff --git a/drivers/dma/amd/ae4dma/ae4dma-pci.c b/drivers/dma/amd/ae4dma/ae4dma-pci.c
new file mode 100644
index 000000000000..aad0dc4294a3
--- /dev/null
+++ b/drivers/dma/amd/ae4dma/ae4dma-pci.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD AE4DMA driver
+ *
+ * Copyright (c) 2024, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
+ */
+
+#include "ae4dma.h"
+
+static int ae4_get_irqs(struct ae4_device *ae4)
+{
+	struct ae4_msix *ae4_msix = ae4->ae4_msix;
+	struct pt_device *pt = &ae4->pt;
+	struct device *dev = pt->dev;
+	struct pci_dev *pdev;
+	int i, v, ret;
+
+	pdev = to_pci_dev(dev);
+
+	for (v = 0; v < ARRAY_SIZE(ae4_msix->msix_entry); v++)
+		ae4_msix->msix_entry[v].entry = v;
+
+	ret = pci_alloc_irq_vectors(pdev, v, v, PCI_IRQ_MSIX);
+	if (ret != v) {
+		if (ret > 0)
+			pci_free_irq_vectors(pdev);
+
+		dev_err(dev, "could not enable MSI-X (%d), trying MSI\n", ret);
+		ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+		if (ret < 0) {
+			dev_err(dev, "could not enable MSI (%d)\n", ret);
+			return ret;
+		}
+
+		ret = pci_irq_vector(pdev, 0);
+		if (ret < 0) {
+			pci_free_irq_vectors(pdev);
+			return ret;
+		}
+
+		for (i = 0; i < MAX_AE4_HW_QUEUES; i++)
+			ae4->ae4_irq[i] = ret;
+
+	} else {
+		ae4_msix->msix_count = ret;
+		for (i = 0; i < MAX_AE4_HW_QUEUES; i++)
+			ae4->ae4_irq[i] = ae4_msix->msix_entry[i].vector;
+	}
+
+	return ret;
+}
+
+static void ae4_free_irqs(struct ae4_device *ae4)
+{
+	struct ae4_msix *ae4_msix = ae4->ae4_msix;
+	struct pt_device *pt = &ae4->pt;
+	struct device *dev = pt->dev;
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(dev);
+
+	if (ae4_msix && (ae4_msix->msix_count || ae4->ae4_irq[MAX_AE4_HW_QUEUES - 1]))
+		pci_free_irq_vectors(pdev);
+}
+
+static void ae4_deinit(struct ae4_device *ae4)
+{
+	ae4_free_irqs(ae4);
+}
+
+static int ae4_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *dev = &pdev->dev;
+	struct ae4_device *ae4;
+	struct pt_device *pt;
+	int bar_mask;
+	int ret = 0;
+
+	ae4 = devm_kzalloc(dev, sizeof(*ae4), GFP_KERNEL);
+	if (!ae4)
+		return -ENOMEM;
+
+	ae4->ae4_msix = devm_kzalloc(dev, sizeof(struct ae4_msix), GFP_KERNEL);
+	if (!ae4->ae4_msix)
+		return -ENOMEM;
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		goto ae4_error;
+
+	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
+	ret = pcim_iomap_regions(pdev, bar_mask, "ae4dma");
+	if (ret)
+		goto ae4_error;
+
+	pt = &ae4->pt;
+	pt->dev = dev;
+	pt->ver = AE4_DMA_VERSION;
+
+	pt->io_regs = pcim_iomap_table(pdev)[0];
+	if (!pt->io_regs) {
+		ret = -ENOMEM;
+		goto ae4_error;
+	}
+
+	ret = ae4_get_irqs(ae4);
+	if (ret < 0)
+		goto ae4_error;
+
+	pci_set_master(pdev);
+
+	dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+
+	dev_set_drvdata(dev, ae4);
+
+	ret = ae4_core_init(ae4);
+	if (ret)
+		goto ae4_error;
+
+	return 0;
+
+ae4_error:
+	ae4_deinit(ae4);
+
+	return ret;
+}
+
+static void ae4_pci_remove(struct pci_dev *pdev)
+{
+	struct ae4_device *ae4 = dev_get_drvdata(&pdev->dev);
+
+	ae4_destroy_work(ae4);
+	ae4_deinit(ae4);
+}
+
+static const struct pci_device_id ae4_pci_table[] = {
+	{ PCI_VDEVICE(AMD, 0x14C8), },
+	{ PCI_VDEVICE(AMD, 0x14DC), },
+	{ PCI_VDEVICE(AMD, 0x149B), },
+	/* Last entry must be zero */
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ae4_pci_table);
+
+static struct pci_driver ae4_pci_driver = {
+	.name = "ae4dma",
+	.id_table = ae4_pci_table,
+	.probe = ae4_pci_probe,
+	.remove = ae4_pci_remove,
+};
+
+module_pci_driver(ae4_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("AMD AE4DMA driver");
diff --git a/drivers/dma/amd/ae4dma/ae4dma.h b/drivers/dma/amd/ae4dma/ae4dma.h
new file mode 100644
index 000000000000..265c5d436008
--- /dev/null
+++ b/drivers/dma/amd/ae4dma/ae4dma.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD AE4DMA driver
+ *
+ * Copyright (c) 2024, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
+ */
+#ifndef __AE4DMA_H__
+#define __AE4DMA_H__
+
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/dmapool.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+
+#include "../ptdma/ptdma.h"
+#include "../../virt-dma.h"
+
+#define MAX_AE4_HW_QUEUES		16
+
+#define AE4_DESC_COMPLETED		0x03
+
+#define AE4_MAX_IDX_OFF			0x08
+#define AE4_RD_IDX_OFF			0x0c
+#define AE4_WR_IDX_OFF			0x10
+#define AE4_INTR_STS_OFF		0x14
+#define AE4_Q_BASE_L_OFF		0x18
+#define AE4_Q_BASE_H_OFF		0x1c
+#define AE4_Q_SZ			0x20
+
+#define AE4_DMA_VERSION			4
+#define CMD_AE4_DESC_DW0_VAL		2
+
+struct ae4_msix {
+	int msix_count;
+	struct msix_entry msix_entry[MAX_AE4_HW_QUEUES];
+};
+
+struct ae4_cmd_queue {
+	struct ae4_device *ae4;
+	struct pt_cmd_queue cmd_q;
+	struct list_head cmd;
+	/* protect command operations */
+	struct mutex cmd_lock;
+	struct delayed_work p_work;
+	struct workqueue_struct *pws;
+	struct completion cmp;
+	wait_queue_head_t q_w;
+	atomic64_t intr_cnt;
+	atomic64_t done_cnt;
+	u64 q_cmd_count;
+	u32 dridx;
+	u32 tail_wi;
+	u32 id;
+};
+
+union dwou {
+	u32 dw0;
+	struct dword0 {
+	u8	byte0;
+	u8	byte1;
+	u16	timestamp;
+	} dws;
+};
+
+struct dword1 {
+	u8	status;
+	u8	err_code;
+	u16	desc_id;
+};
+
+struct ae4dma_desc {
+	union dwou dwouv;
+	struct dword1 dw1;
+	u32 length;
+	u32 rsvd;
+	u32 src_hi;
+	u32 src_lo;
+	u32 dst_hi;
+	u32 dst_lo;
+};
+
+struct ae4_device {
+	struct pt_device pt;
+	struct ae4_msix *ae4_msix;
+	struct ae4_cmd_queue ae4cmd_q[MAX_AE4_HW_QUEUES];
+	unsigned int ae4_irq[MAX_AE4_HW_QUEUES];
+	unsigned int cmd_q_count;
+};
+
+int ae4_core_init(struct ae4_device *ae4);
+void ae4_destroy_work(struct ae4_device *ae4);
+void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx);
+#endif
diff --git a/drivers/dma/ptdma/Makefile b/drivers/dma/amd/ptdma/Makefile
index ce5410268a9a..ce5410268a9a 100644
--- a/drivers/dma/ptdma/Makefile
+++ b/drivers/dma/amd/ptdma/Makefile
diff --git a/drivers/dma/ptdma/ptdma-debugfs.c b/drivers/dma/amd/ptdma/ptdma-debugfs.c
index c8307d3044a3..c7c90bbf6fd8 100644
--- a/drivers/dma/ptdma/ptdma-debugfs.c
+++ b/drivers/dma/amd/ptdma/ptdma-debugfs.c
@@ -13,6 +13,7 @@
 #include <linux/seq_file.h>
 
 #include "ptdma.h"
+#include "../ae4dma/ae4dma.h"
 
 /* DebugFS helpers */
 #define	RI_VERSION_NUM	0x0000003F
@@ -23,11 +24,19 @@
 static int pt_debugfs_info_show(struct seq_file *s, void *p)
 {
 	struct pt_device *pt = s->private;
+	struct ae4_device *ae4;
 	unsigned int regval;
 
 	seq_printf(s, "Device name: %s\n", dev_name(pt->dev));
-	seq_printf(s, "   # Queues: %d\n", 1);
-	seq_printf(s, "     # Cmds: %d\n", pt->cmd_count);
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		seq_printf(s, "   # Queues: %d\n", ae4->cmd_q_count);
+		seq_printf(s, "     # Cmds per queue: %d\n", CMD_Q_LEN);
+	} else {
+		seq_printf(s, "   # Queues: %d\n", 1);
+		seq_printf(s, "     # Cmds: %d\n", pt->cmd_count);
+	}
 
 	regval = ioread32(pt->io_regs + CMD_PT_VERSION);
 
@@ -55,6 +64,7 @@ static int pt_debugfs_stats_show(struct seq_file *s, void *p)
 static int pt_debugfs_queue_show(struct seq_file *s, void *p)
 {
 	struct pt_cmd_queue *cmd_q = s->private;
+	struct pt_device *pt;
 	unsigned int regval;
 
 	if (!cmd_q)
@@ -62,18 +72,24 @@ static int pt_debugfs_queue_show(struct seq_file *s, void *p)
 
 	seq_printf(s, "               Pass-Thru: %ld\n", cmd_q->total_pt_ops);
 
-	regval = ioread32(cmd_q->reg_control + 0x000C);
-
-	seq_puts(s, "      Enabled Interrupts:");
-	if (regval & INT_EMPTY_QUEUE)
-		seq_puts(s, " EMPTY");
-	if (regval & INT_QUEUE_STOPPED)
-		seq_puts(s, " STOPPED");
-	if (regval & INT_ERROR)
-		seq_puts(s, " ERROR");
-	if (regval & INT_COMPLETION)
-		seq_puts(s, " COMPLETION");
-	seq_puts(s, "\n");
+	pt = cmd_q->pt;
+	if (pt->ver == AE4_DMA_VERSION) {
+		regval = readl(cmd_q->reg_control + 0x4);
+		seq_printf(s, "     Enabled Interrupts:: status 0x%x\n", regval);
+	} else {
+		regval = ioread32(cmd_q->reg_control + 0x000C);
+
+		seq_puts(s, "      Enabled Interrupts:");
+		if (regval & INT_EMPTY_QUEUE)
+			seq_puts(s, " EMPTY");
+		if (regval & INT_QUEUE_STOPPED)
+			seq_puts(s, " STOPPED");
+		if (regval & INT_ERROR)
+			seq_puts(s, " ERROR");
+		if (regval & INT_COMPLETION)
+			seq_puts(s, " COMPLETION");
+		seq_puts(s, "\n");
+	}
 
 	return 0;
 }
@@ -84,8 +100,12 @@ DEFINE_SHOW_ATTRIBUTE(pt_debugfs_stats);
 
 void ptdma_debugfs_setup(struct pt_device *pt)
 {
-	struct pt_cmd_queue *cmd_q;
 	struct dentry *debugfs_q_instance;
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct pt_cmd_queue *cmd_q;
+	struct ae4_device *ae4;
+	char name[30];
+	int i;
 
 	if (!debugfs_initialized())
 		return;
@@ -96,11 +116,28 @@ void ptdma_debugfs_setup(struct pt_device *pt)
 	debugfs_create_file("stats", 0400, pt->dma_dev.dbg_dev_root, pt,
 			    &pt_debugfs_stats_fops);
 
-	cmd_q = &pt->cmd_q;
-
-	debugfs_q_instance =
-		debugfs_create_dir("q", pt->dma_dev.dbg_dev_root);
 
-	debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q,
-			    &pt_debugfs_queue_fops);
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		for (i = 0; i < ae4->cmd_q_count; i++) {
+			ae4cmd_q = &ae4->ae4cmd_q[i];
+			cmd_q = &ae4cmd_q->cmd_q;
+
+			memset(name, 0, sizeof(name));
+			snprintf(name, 29, "q%d", ae4cmd_q->id);
+
+			debugfs_q_instance =
+				debugfs_create_dir(name, pt->dma_dev.dbg_dev_root);
+
+			debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q,
+					    &pt_debugfs_queue_fops);
+		}
+	} else {
+		debugfs_q_instance =
+			debugfs_create_dir("q", pt->dma_dev.dbg_dev_root);
+		cmd_q = &pt->cmd_q;
+		debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q,
+				    &pt_debugfs_queue_fops);
+	}
 }
+EXPORT_SYMBOL_GPL(ptdma_debugfs_setup);
diff --git a/drivers/dma/ptdma/ptdma-dev.c b/drivers/dma/amd/ptdma/ptdma-dev.c
index a2bf13ff18b6..a2bf13ff18b6 100644
--- a/drivers/dma/ptdma/ptdma-dev.c
+++ b/drivers/dma/amd/ptdma/ptdma-dev.c
diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
index f79240734807..35c84ec9608b 100644
--- a/drivers/dma/ptdma/ptdma-dmaengine.c
+++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c
@@ -9,9 +9,58 @@
  * Author: Gary R Hook <gary.hook@amd.com>
  */
 
+#include <linux/bitfield.h>
 #include "ptdma.h"
-#include "../dmaengine.h"
-#include "../virt-dma.h"
+#include "../ae4dma/ae4dma.h"
+#include "../../dmaengine.h"
+
+static char *ae4_error_codes[] = {
+	"",
+	"ERR 01: INVALID HEADER DW0",
+	"ERR 02: INVALID STATUS",
+	"ERR 03: INVALID LENGTH - 4 BYTE ALIGNMENT",
+	"ERR 04: INVALID SRC ADDR - 4 BYTE ALIGNMENT",
+	"ERR 05: INVALID DST ADDR - 4 BYTE ALIGNMENT",
+	"ERR 06: INVALID ALIGNMENT",
+	"ERR 07: INVALID DESCRIPTOR",
+};
+
+static void ae4_log_error(struct pt_device *d, int e)
+{
+	/* ERR 01 - 07 represents Invalid AE4 errors */
+	if (e <= 7)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", ae4_error_codes[e], e);
+	/* ERR 08 - 15 represents Invalid Descriptor errors */
+	else if (e > 7 && e <= 15)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "INVALID DESCRIPTOR", e);
+	/* ERR 16 - 31 represents Firmware errors */
+	else if (e > 15 && e <= 31)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FIRMWARE ERROR", e);
+	/* ERR 32 - 63 represents Fatal errors */
+	else if (e > 31 && e <= 63)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FATAL ERROR", e);
+	/* ERR 64 - 255 represents PTE errors */
+	else if (e > 63 && e <= 255)
+		dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "PTE ERROR", e);
+	else
+		dev_info(d->dev, "Unknown AE4DMA error");
+}
+
+void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx)
+{
+	struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q;
+	struct ae4dma_desc desc;
+	u8 status;
+
+	memcpy(&desc, &cmd_q->qbase[idx], sizeof(struct ae4dma_desc));
+	status = desc.dw1.status;
+	if (status && status != AE4_DESC_COMPLETED) {
+		cmd_q->cmd_error = desc.dw1.err_code;
+		if (cmd_q->cmd_error)
+			ae4_log_error(cmd_q->pt, cmd_q->cmd_error);
+	}
+}
+EXPORT_SYMBOL_GPL(ae4_check_status_error);
 
 static inline struct pt_dma_chan *to_pt_chan(struct dma_chan *dma_chan)
 {
@@ -45,7 +94,71 @@ static void pt_do_cleanup(struct virt_dma_desc *vd)
 	kmem_cache_free(pt->dma_desc_cache, desc);
 }
 
-static int pt_dma_start_desc(struct pt_dma_desc *desc)
+static struct pt_cmd_queue *pt_get_cmd_queue(struct pt_device *pt, struct pt_dma_chan *chan)
+{
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct pt_cmd_queue *cmd_q;
+	struct ae4_device *ae4;
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+		cmd_q = &ae4cmd_q->cmd_q;
+	} else {
+		cmd_q = &pt->cmd_q;
+	}
+
+	return cmd_q;
+}
+
+static int ae4_core_execute_cmd(struct ae4dma_desc *desc, struct ae4_cmd_queue *ae4cmd_q)
+{
+	bool soc = FIELD_GET(DWORD0_SOC, desc->dwouv.dw0);
+	struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q;
+
+	if (soc) {
+		desc->dwouv.dw0 |= FIELD_PREP(DWORD0_IOC, desc->dwouv.dw0);
+		desc->dwouv.dw0 &= ~DWORD0_SOC;
+	}
+
+	mutex_lock(&ae4cmd_q->cmd_lock);
+	memcpy(&cmd_q->qbase[ae4cmd_q->tail_wi], desc, sizeof(struct ae4dma_desc));
+	ae4cmd_q->q_cmd_count++;
+	ae4cmd_q->tail_wi = (ae4cmd_q->tail_wi + 1) % CMD_Q_LEN;
+	writel(ae4cmd_q->tail_wi, cmd_q->reg_control + AE4_WR_IDX_OFF);
+	mutex_unlock(&ae4cmd_q->cmd_lock);
+
+	wake_up(&ae4cmd_q->q_w);
+
+	return 0;
+}
+
+static int pt_core_perform_passthru_ae4(struct pt_cmd_queue *cmd_q,
+					struct pt_passthru_engine *pt_engine)
+{
+	struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q);
+	struct ae4dma_desc desc;
+
+	cmd_q->cmd_error = 0;
+	cmd_q->total_pt_ops++;
+	memset(&desc, 0, sizeof(desc));
+	desc.dwouv.dws.byte0 = CMD_AE4_DESC_DW0_VAL;
+
+	desc.dw1.status = 0;
+	desc.dw1.err_code = 0;
+	desc.dw1.desc_id = 0;
+
+	desc.length = pt_engine->src_len;
+
+	desc.src_lo = upper_32_bits(pt_engine->src_dma);
+	desc.src_hi = lower_32_bits(pt_engine->src_dma);
+	desc.dst_lo = upper_32_bits(pt_engine->dst_dma);
+	desc.dst_hi = lower_32_bits(pt_engine->dst_dma);
+
+	return ae4_core_execute_cmd(&desc, ae4cmd_q);
+}
+
+static int pt_dma_start_desc(struct pt_dma_desc *desc, struct pt_dma_chan *chan)
 {
 	struct pt_passthru_engine *pt_engine;
 	struct pt_device *pt;
@@ -56,13 +169,18 @@ static int pt_dma_start_desc(struct pt_dma_desc *desc)
 
 	pt_cmd = &desc->pt_cmd;
 	pt = pt_cmd->pt;
-	cmd_q = &pt->cmd_q;
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
+
 	pt_engine = &pt_cmd->passthru;
 
 	pt->tdata.cmd = pt_cmd;
 
 	/* Execute the command */
-	pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine);
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_cmd->ret = pt_core_perform_passthru_ae4(cmd_q, pt_engine);
+	else
+		pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine);
 
 	return 0;
 }
@@ -151,7 +269,7 @@ static void pt_cmd_callback(void *data, int err)
 		if (!desc)
 			break;
 
-		ret = pt_dma_start_desc(desc);
+		ret = pt_dma_start_desc(desc, chan);
 		if (!ret)
 			break;
 
@@ -186,7 +304,10 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
 	struct pt_passthru_engine *pt_engine;
+	struct pt_device *pt = chan->pt;
+	struct ae4_cmd_queue *ae4cmd_q;
 	struct pt_dma_desc *desc;
+	struct ae4_device *ae4;
 	struct pt_cmd *pt_cmd;
 
 	desc = pt_alloc_dma_desc(chan, flags);
@@ -194,7 +315,7 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
 		return NULL;
 
 	pt_cmd = &desc->pt_cmd;
-	pt_cmd->pt = chan->pt;
+	pt_cmd->pt = pt;
 	pt_engine = &pt_cmd->passthru;
 	pt_cmd->engine = PT_ENGINE_PASSTHRU;
 	pt_engine->src_dma = src;
@@ -205,6 +326,14 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
 
 	desc->len = len;
 
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+		mutex_lock(&ae4cmd_q->cmd_lock);
+		list_add_tail(&pt_cmd->entry, &ae4cmd_q->cmd);
+		mutex_unlock(&ae4cmd_q->cmd_lock);
+	}
+
 	return desc;
 }
 
@@ -258,24 +387,43 @@ static void pt_issue_pending(struct dma_chan *dma_chan)
 		pt_cmd_callback(desc, 0);
 }
 
+static void pt_check_status_trans_ae4(struct pt_device *pt, struct pt_cmd_queue *cmd_q)
+{
+	struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q);
+	int i;
+
+	for (i = 0; i < CMD_Q_LEN; i++)
+		ae4_check_status_error(ae4cmd_q, i);
+}
+
 static enum dma_status
 pt_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 		struct dma_tx_state *txstate)
 {
-	struct pt_device *pt = to_pt_chan(c)->pt;
-	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+	struct pt_dma_chan *chan = to_pt_chan(c);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
+
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_check_status_trans_ae4(pt, cmd_q);
+	else
+		pt_check_status_trans(pt, cmd_q);
 
-	pt_check_status_trans(pt, cmd_q);
 	return dma_cookie_status(c, cookie, txstate);
 }
 
 static int pt_pause(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
-	pt_stop_queue(&chan->pt->cmd_q);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	pt_stop_queue(cmd_q);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
 	return 0;
@@ -285,10 +433,13 @@ static int pt_resume(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
 	struct pt_dma_desc *desc = NULL;
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
-	pt_start_queue(&chan->pt->cmd_q);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	pt_start_queue(cmd_q);
 	desc = pt_next_dma_desc(chan);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
@@ -302,11 +453,17 @@ static int pt_resume(struct dma_chan *dma_chan)
 static int pt_terminate_all(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
 	unsigned long flags;
-	struct pt_cmd_queue *cmd_q = &chan->pt->cmd_q;
 	LIST_HEAD(head);
 
-	iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_stop_queue(cmd_q);
+	else
+		iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vchan_get_all_descriptors(&chan->vc, &head);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
@@ -319,14 +476,24 @@ static int pt_terminate_all(struct dma_chan *dma_chan)
 
 int pt_dmaengine_register(struct pt_device *pt)
 {
-	struct pt_dma_chan *chan;
 	struct dma_device *dma_dev = &pt->dma_dev;
-	char *cmd_cache_name;
+	struct ae4_cmd_queue *ae4cmd_q = NULL;
+	struct ae4_device *ae4 = NULL;
+	struct pt_dma_chan *chan;
 	char *desc_cache_name;
-	int ret;
+	char *cmd_cache_name;
+	int ret, i;
+
+	if (pt->ver == AE4_DMA_VERSION)
+		ae4 = container_of(pt, struct ae4_device, pt);
+
+	if (ae4)
+		pt->pt_dma_chan = devm_kcalloc(pt->dev, ae4->cmd_q_count,
+					       sizeof(*pt->pt_dma_chan), GFP_KERNEL);
+	else
+		pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan),
+					       GFP_KERNEL);
 
-	pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan),
-				       GFP_KERNEL);
 	if (!pt->pt_dma_chan)
 		return -ENOMEM;
 
@@ -368,9 +535,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 
 	INIT_LIST_HEAD(&dma_dev->channels);
 
-	chan = pt->pt_dma_chan;
-	chan->pt = pt;
-
 	/* Set base and prep routines */
 	dma_dev->device_free_chan_resources = pt_free_chan_resources;
 	dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy;
@@ -382,8 +546,21 @@ int pt_dmaengine_register(struct pt_device *pt)
 	dma_dev->device_terminate_all = pt_terminate_all;
 	dma_dev->device_synchronize = pt_synchronize;
 
-	chan->vc.desc_free = pt_do_cleanup;
-	vchan_init(&chan->vc, dma_dev);
+	if (ae4) {
+		for (i = 0; i < ae4->cmd_q_count; i++) {
+			chan = pt->pt_dma_chan + i;
+			ae4cmd_q = &ae4->ae4cmd_q[i];
+			chan->id = ae4cmd_q->id;
+			chan->pt = pt;
+			chan->vc.desc_free = pt_do_cleanup;
+			vchan_init(&chan->vc, dma_dev);
+		}
+	} else {
+		chan = pt->pt_dma_chan;
+		chan->pt = pt;
+		chan->vc.desc_free = pt_do_cleanup;
+		vchan_init(&chan->vc, dma_dev);
+	}
 
 	ret = dma_async_device_register(dma_dev);
 	if (ret)
@@ -399,6 +576,7 @@ err_cache:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pt_dmaengine_register);
 
 void pt_dmaengine_unregister(struct pt_device *pt)
 {
diff --git a/drivers/dma/ptdma/ptdma-pci.c b/drivers/dma/amd/ptdma/ptdma-pci.c
index 22739ff0c3c5..22739ff0c3c5 100644
--- a/drivers/dma/ptdma/ptdma-pci.c
+++ b/drivers/dma/amd/ptdma/ptdma-pci.c
diff --git a/drivers/dma/ptdma/ptdma.h b/drivers/dma/amd/ptdma/ptdma.h
index 39bc37268235..0a7939105e51 100644
--- a/drivers/dma/ptdma/ptdma.h
+++ b/drivers/dma/amd/ptdma/ptdma.h
@@ -22,7 +22,7 @@
 #include <linux/wait.h>
 #include <linux/dmapool.h>
 
-#include "../virt-dma.h"
+#include "../../virt-dma.h"
 
 #define MAX_PT_NAME_LEN			16
 #define MAX_DMAPOOL_NAME_LEN		32
@@ -184,6 +184,7 @@ struct pt_dma_desc {
 struct pt_dma_chan {
 	struct virt_dma_chan vc;
 	struct pt_device *pt;
+	u32 id;
 };
 
 struct pt_cmd_queue {
@@ -262,6 +263,7 @@ struct pt_device {
 	unsigned long total_interrupts;
 
 	struct pt_tasklet_data tdata;
+	int ver;
 };
 
 /*
diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c
index 66f00ad67351..8fb2d5e1df20 100644
--- a/drivers/dma/amd/qdma/qdma.c
+++ b/drivers/dma/amd/qdma/qdma.c
@@ -283,16 +283,20 @@ static int qdma_check_queue_status(struct qdma_device *qdev,
 
 static int qdma_clear_queue_context(const struct qdma_queue *queue)
 {
-	enum qdma_ctxt_type h2c_types[] = { QDMA_CTXT_DESC_SW_H2C,
-					    QDMA_CTXT_DESC_HW_H2C,
-					    QDMA_CTXT_DESC_CR_H2C,
-					    QDMA_CTXT_PFTCH, };
-	enum qdma_ctxt_type c2h_types[] = { QDMA_CTXT_DESC_SW_C2H,
-					    QDMA_CTXT_DESC_HW_C2H,
-					    QDMA_CTXT_DESC_CR_C2H,
-					    QDMA_CTXT_PFTCH, };
+	static const enum qdma_ctxt_type h2c_types[] = {
+		QDMA_CTXT_DESC_SW_H2C,
+		QDMA_CTXT_DESC_HW_H2C,
+		QDMA_CTXT_DESC_CR_H2C,
+		QDMA_CTXT_PFTCH,
+	};
+	static const enum qdma_ctxt_type c2h_types[] = {
+		QDMA_CTXT_DESC_SW_C2H,
+		QDMA_CTXT_DESC_HW_C2H,
+		QDMA_CTXT_DESC_CR_C2H,
+		QDMA_CTXT_PFTCH,
+	};
 	struct qdma_device *qdev = queue->qdev;
-	enum qdma_ctxt_type *type;
+	const enum qdma_ctxt_type *type;
 	int ret, num, i;
 
 	if (queue->dir == DMA_MEM_TO_DEV) {
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 7ba52dee40a9..20b10c15c696 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -875,6 +875,27 @@ static struct dma_chan *bcm2835_dma_xlate(struct of_phandle_args *spec,
 	return chan;
 }
 
+static int bcm2835_dma_suspend_late(struct device *dev)
+{
+	struct bcm2835_dmadev *od = dev_get_drvdata(dev);
+	struct bcm2835_chan *c, *next;
+
+	list_for_each_entry_safe(c, next, &od->ddev.channels,
+				 vc.chan.device_node) {
+		void __iomem *chan_base = c->chan_base;
+
+		/* Check if DMA channel is busy */
+		if (readl(chan_base + BCM2835_DMA_ADDR))
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops bcm2835_dma_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(bcm2835_dma_suspend_late, NULL)
+};
+
 static int bcm2835_dma_probe(struct platform_device *pdev)
 {
 	struct bcm2835_dmadev *od;
@@ -1033,6 +1054,7 @@ static struct platform_driver bcm2835_dma_driver = {
 	.driver = {
 		.name = "bcm2835-dma",
 		.of_match_table = of_match_ptr(bcm2835_dma_of_match),
+		.pm = pm_ptr(&bcm2835_dma_pm_ops),
 	},
 };
 
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index b7f15ab96855..443b2430466c 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -480,8 +480,8 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 		       bool disable_req, bool enable_sg)
 {
 	struct dma_slave_config *cfg = &fsl_chan->cfg;
+	u32 burst = 0;
 	u16 csr = 0;
-	u32 burst;
 
 	/*
 	 * eDMA hardware SGs require the TCDs to be stored in little
@@ -496,16 +496,30 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 
 	fsl_edma_set_tcd_to_le(fsl_chan, tcd, soff, soff);
 
-	if (fsl_chan->is_multi_fifo) {
-		/* set mloff to support multiple fifo */
-		burst = cfg->direction == DMA_DEV_TO_MEM ?
-				cfg->src_maxburst : cfg->dst_maxburst;
-		nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4));
-		/* enable DMLOE/SMLOE */
-		if (cfg->direction == DMA_MEM_TO_DEV) {
+	/* If we expect to have either multi_fifo or a port window size,
+	 * we will use minor loop offset, meaning bits 29-10 will be used for
+	 * address offset, while bits 9-0 will be used to tell DMA how much
+	 * data to read from addr.
+	 * If we don't have either of those, will use a major loop reading from addr
+	 * nbytes (29bits).
+	 */
+	if (cfg->direction == DMA_MEM_TO_DEV) {
+		if (fsl_chan->is_multi_fifo)
+			burst = cfg->dst_maxburst * 4;
+		if (cfg->dst_port_window_size)
+			burst = cfg->dst_port_window_size * cfg->dst_addr_width;
+		if (burst) {
+			nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-burst);
 			nbytes |= EDMA_V3_TCD_NBYTES_DMLOE;
 			nbytes &= ~EDMA_V3_TCD_NBYTES_SMLOE;
-		} else {
+		}
+	} else {
+		if (fsl_chan->is_multi_fifo)
+			burst = cfg->src_maxburst * 4;
+		if (cfg->src_port_window_size)
+			burst = cfg->src_port_window_size * cfg->src_addr_width;
+		if (burst) {
+			nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-burst);
 			nbytes |= EDMA_V3_TCD_NBYTES_SMLOE;
 			nbytes &= ~EDMA_V3_TCD_NBYTES_DMLOE;
 		}
@@ -623,11 +637,15 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
 			doff = fsl_chan->is_multi_fifo ? 4 : 0;
+			if (fsl_chan->cfg.dst_port_window_size)
+				doff = fsl_chan->cfg.dst_addr_width;
 		} else if (direction == DMA_DEV_TO_MEM) {
 			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = dma_buf_next;
 			soff = fsl_chan->is_multi_fifo ? 4 : 0;
 			doff = fsl_chan->cfg.src_addr_width;
+			if (fsl_chan->cfg.src_port_window_size)
+				soff = fsl_chan->cfg.src_addr_width;
 		} else {
 			/* DMA_DEV_TO_DEV */
 			src_addr = fsl_chan->cfg.src_addr;
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index fe8f103d4a63..10a5565ddfd7 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -68,6 +68,8 @@
 #define EDMA_V3_CH_CSR_EEI         BIT(2)
 #define EDMA_V3_CH_CSR_DONE        BIT(30)
 #define EDMA_V3_CH_CSR_ACTIVE      BIT(31)
+#define EDMA_V3_CH_ES_ERR          BIT(31)
+#define EDMA_V3_MP_ES_VLD          BIT(31)
 
 enum fsl_edma_pm_state {
 	RUNNING = 0,
@@ -241,6 +243,7 @@ struct fsl_edma_engine {
 	const struct fsl_edma_drvdata *drvdata;
 	u32			n_chans;
 	int			txirq;
+	int			txirq_16_31;
 	int			errirq;
 	bool			big_endian;
 	struct edma_regs	regs;
diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
index 1a613236b3e4..f989b6c9c0a9 100644
--- a/drivers/dma/fsl-edma-main.c
+++ b/drivers/dma/fsl-edma-main.c
@@ -3,10 +3,11 @@
  * drivers/dma/fsl-edma.c
  *
  * Copyright 2013-2014 Freescale Semiconductor, Inc.
+ * Copyright 2024 NXP
  *
  * Driver for the Freescale eDMA engine with flexible channel multiplexing
  * capability for DMA request sources. The eDMA block can be found on some
- * Vybrid and Layerscape SoCs.
+ * Vybrid, Layerscape and S32G SoCs.
  */
 
 #include <dt-bindings/dma/fsl-edma.h>
@@ -72,6 +73,60 @@ static irqreturn_t fsl_edma2_tx_handler(int irq, void *devi_id)
 	return fsl_edma_tx_handler(irq, fsl_chan->edma);
 }
 
+static irqreturn_t fsl_edma3_or_tx_handler(int irq, void *dev_id,
+					   u8 start, u8 end)
+{
+	struct fsl_edma_engine *fsl_edma = dev_id;
+	struct fsl_edma_chan *chan;
+	int i;
+
+	end = min(end, fsl_edma->n_chans);
+
+	for (i = start; i < end; i++) {
+		chan = &fsl_edma->chans[i];
+
+		fsl_edma3_tx_handler(irq, chan);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_edma3_tx_0_15_handler(int irq, void *dev_id)
+{
+	return fsl_edma3_or_tx_handler(irq, dev_id, 0, 16);
+}
+
+static irqreturn_t fsl_edma3_tx_16_31_handler(int irq, void *dev_id)
+{
+	return fsl_edma3_or_tx_handler(irq, dev_id, 16, 32);
+}
+
+static irqreturn_t fsl_edma3_or_err_handler(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *fsl_edma = dev_id;
+	struct edma_regs *regs = &fsl_edma->regs;
+	unsigned int err, ch, ch_es;
+	struct fsl_edma_chan *chan;
+
+	err = edma_readl(fsl_edma, regs->es);
+	if (!(err & EDMA_V3_MP_ES_VLD))
+		return IRQ_NONE;
+
+	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
+		chan = &fsl_edma->chans[ch];
+
+		ch_es = edma_readl_chreg(chan, ch_es);
+		if (!(ch_es & EDMA_V3_CH_ES_ERR))
+			continue;
+
+		edma_writel_chreg(chan, EDMA_V3_CH_ES_ERR, ch_es);
+		fsl_edma_disable_request(chan);
+		fsl_edma->chans[ch].status = DMA_ERROR;
+	}
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
 {
 	struct fsl_edma_engine *fsl_edma = dev_id;
@@ -274,6 +329,49 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi
 	return 0;
 }
 
+static int fsl_edma3_or_irq_init(struct platform_device *pdev,
+				 struct fsl_edma_engine *fsl_edma)
+{
+	int ret;
+
+	fsl_edma->txirq = platform_get_irq_byname(pdev, "tx-0-15");
+	if (fsl_edma->txirq < 0)
+		return fsl_edma->txirq;
+
+	fsl_edma->txirq_16_31 = platform_get_irq_byname(pdev, "tx-16-31");
+	if (fsl_edma->txirq_16_31 < 0)
+		return fsl_edma->txirq_16_31;
+
+	fsl_edma->errirq = platform_get_irq_byname(pdev, "err");
+	if (fsl_edma->errirq < 0)
+		return fsl_edma->errirq;
+
+	ret = devm_request_irq(&pdev->dev, fsl_edma->txirq,
+			       fsl_edma3_tx_0_15_handler, 0, "eDMA tx0_15",
+			       fsl_edma);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+			       "Can't register eDMA tx0_15 IRQ.\n");
+
+	if (fsl_edma->n_chans > 16) {
+		ret = devm_request_irq(&pdev->dev, fsl_edma->txirq_16_31,
+				       fsl_edma3_tx_16_31_handler, 0,
+				       "eDMA tx16_31", fsl_edma);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret,
+					"Can't register eDMA tx16_31 IRQ.\n");
+	}
+
+	ret = devm_request_irq(&pdev->dev, fsl_edma->errirq,
+			       fsl_edma3_or_err_handler, 0, "eDMA err",
+			       fsl_edma);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "Can't register eDMA err IRQ.\n");
+
+	return 0;
+}
+
 static int
 fsl_edma2_irq_init(struct platform_device *pdev,
 		   struct fsl_edma_engine *fsl_edma)
@@ -404,6 +502,14 @@ static struct fsl_edma_drvdata imx95_data5 = {
 	.setup_irq = fsl_edma3_irq_init,
 };
 
+static const struct fsl_edma_drvdata s32g2_data = {
+	.dmamuxs = DMAMUX_NR,
+	.chreg_space_sz = EDMA_TCD,
+	.chreg_off = 0x4000,
+	.flags = FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MUX_SWAP,
+	.setup_irq = fsl_edma3_or_irq_init,
+};
+
 static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,vf610-edma", .data = &vf610_data},
 	{ .compatible = "fsl,ls1028a-edma", .data = &ls1028a_data},
@@ -413,6 +519,7 @@ static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,imx93-edma3", .data = &imx93_data3},
 	{ .compatible = "fsl,imx93-edma4", .data = &imx93_data4},
 	{ .compatible = "fsl,imx95-edma5", .data = &imx95_data5},
+	{ .compatible = "nxp,s32g2-edma", .data = &s32g2_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids);
@@ -545,10 +652,6 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	for (i = 0; i < fsl_edma->drvdata->dmamuxs; i++) {
 		char clkname[32];
 
-		/* eDMAv3 mux register move to TCD area if ch_mux exist */
-		if (drvdata->flags & FSL_EDMA_DRV_SPLIT_REG)
-			break;
-
 		fsl_edma->muxbase[i] = devm_platform_ioremap_resource(pdev,
 								      1 + i);
 		if (IS_ERR(fsl_edma->muxbase[i])) {
@@ -677,7 +780,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	}
 
 	ret = of_dma_controller_register(np,
-			drvdata->flags & FSL_EDMA_DRV_SPLIT_REG ? fsl_edma3_xlate : fsl_edma_xlate,
+			drvdata->dmamuxs ? fsl_edma_xlate : fsl_edma3_xlate,
 			fsl_edma);
 	if (ret) {
 		dev_err(&pdev->dev,
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 57f1bf2ab20b..ff94ee892339 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -28,7 +28,6 @@ struct idxd_cdev_context {
  * global to avoid conflict file names.
  */
 static DEFINE_IDA(file_ida);
-static DEFINE_MUTEX(ida_lock);
 
 /*
  * ictx is an array based off of accelerator types. enum idxd_type
@@ -123,9 +122,7 @@ static void idxd_file_dev_release(struct device *dev)
 	struct idxd_device *idxd = wq->idxd;
 	int rc;
 
-	mutex_lock(&ida_lock);
 	ida_free(&file_ida, ctx->id);
-	mutex_unlock(&ida_lock);
 
 	/* Wait for in-flight operations to complete. */
 	if (wq_shared(wq)) {
@@ -284,9 +281,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp)
 	}
 
 	idxd_cdev = wq->idxd_cdev;
-	mutex_lock(&ida_lock);
 	ctx->id = ida_alloc(&file_ida, GFP_KERNEL);
-	mutex_unlock(&ida_lock);
 	if (ctx->id < 0) {
 		dev_warn(dev, "ida alloc failure\n");
 		goto failed_ida;
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index d84e21daa991..214b8039439f 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -374,6 +374,17 @@ struct idxd_device {
 	struct dentry *dbgfs_evl_file;
 
 	bool user_submission_safe;
+
+	struct idxd_saved_states *idxd_saved;
+};
+
+struct idxd_saved_states {
+	struct idxd_device saved_idxd;
+	struct idxd_evl saved_evl;
+	struct idxd_engine **saved_engines;
+	struct idxd_wq **saved_wqs;
+	struct idxd_group **saved_groups;
+	unsigned long *saved_wq_enable_map;
 };
 
 static inline unsigned int evl_ent_size(struct idxd_device *idxd)
@@ -725,8 +736,6 @@ static inline void idxd_desc_complete(struct idxd_desc *desc,
 				   &desc->txd, &status);
 }
 
-int idxd_register_bus_type(void);
-void idxd_unregister_bus_type(void);
 int idxd_register_devices(struct idxd_device *idxd);
 void idxd_unregister_devices(struct idxd_device *idxd);
 void idxd_wqs_quiesce(struct idxd_device *idxd);
@@ -742,6 +751,8 @@ void idxd_unmask_error_interrupts(struct idxd_device *idxd);
 
 /* device control */
 int idxd_device_drv_probe(struct idxd_dev *idxd_dev);
+int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev,
+			 const struct pci_device_id *id);
 void idxd_device_drv_remove(struct idxd_dev *idxd_dev);
 int idxd_drv_enable_wq(struct idxd_wq *wq);
 void idxd_drv_disable_wq(struct idxd_wq *wq);
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 140f8d772bee..b946f78f85e1 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -78,6 +78,8 @@ static struct pci_device_id idxd_pci_tbl[] = {
 	{ PCI_DEVICE_DATA(INTEL, IAX_SPR0, &idxd_driver_data[IDXD_TYPE_IAX]) },
 	/* IAA on DMR platforms */
 	{ PCI_DEVICE_DATA(INTEL, IAA_DMR, &idxd_driver_data[IDXD_TYPE_IAX]) },
+	/* IAA PTL platforms */
+	{ PCI_DEVICE_DATA(INTEL, IAA_PTL, &idxd_driver_data[IDXD_TYPE_IAX]) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, idxd_pci_tbl);
@@ -723,67 +725,464 @@ static void idxd_cleanup(struct idxd_device *idxd)
 		idxd_disable_sva(idxd->pdev);
 }
 
-static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+/*
+ * Attach IDXD device to IDXD driver.
+ */
+static int idxd_bind(struct device_driver *drv, const char *buf)
 {
-	struct device *dev = &pdev->dev;
-	struct idxd_device *idxd;
-	struct idxd_driver_data *data = (struct idxd_driver_data *)id->driver_data;
+	const struct bus_type *bus = drv->bus;
+	struct device *dev;
+	int err = -ENODEV;
+
+	dev = bus_find_device_by_name(bus, NULL, buf);
+	if (dev)
+		err = device_driver_attach(drv, dev);
+
+	put_device(dev);
+
+	return err;
+}
+
+/*
+ * Detach IDXD device from driver.
+ */
+static void idxd_unbind(struct device_driver *drv, const char *buf)
+{
+	const struct bus_type *bus = drv->bus;
+	struct device *dev;
+
+	dev = bus_find_device_by_name(bus, NULL, buf);
+	if (dev && dev->driver == drv)
+		device_release_driver(dev);
+
+	put_device(dev);
+}
+
+#define idxd_free_saved_configs(saved_configs, count)	\
+	do {						\
+		int i;					\
+							\
+		for (i = 0; i < (count); i++)		\
+			kfree(saved_configs[i]);	\
+	} while (0)
+
+static void idxd_free_saved(struct idxd_group **saved_groups,
+			    struct idxd_engine **saved_engines,
+			    struct idxd_wq **saved_wqs,
+			    struct idxd_device *idxd)
+{
+	if (saved_groups)
+		idxd_free_saved_configs(saved_groups, idxd->max_groups);
+	if (saved_engines)
+		idxd_free_saved_configs(saved_engines, idxd->max_engines);
+	if (saved_wqs)
+		idxd_free_saved_configs(saved_wqs, idxd->max_wqs);
+}
+
+/*
+ * Save IDXD device configurations including engines, groups, wqs etc.
+ * The saved configurations can be restored when needed.
+ */
+static int idxd_device_config_save(struct idxd_device *idxd,
+				   struct idxd_saved_states *idxd_saved)
+{
+	struct device *dev = &idxd->pdev->dev;
+	int i;
+
+	memcpy(&idxd_saved->saved_idxd, idxd, sizeof(*idxd));
+
+	if (idxd->evl) {
+		memcpy(&idxd_saved->saved_evl, idxd->evl,
+		       sizeof(struct idxd_evl));
+	}
+
+	struct idxd_group **saved_groups __free(kfree) =
+			kcalloc_node(idxd->max_groups,
+				     sizeof(struct idxd_group *),
+				     GFP_KERNEL, dev_to_node(dev));
+	if (!saved_groups)
+		return -ENOMEM;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *saved_group __free(kfree) =
+			kzalloc_node(sizeof(*saved_group), GFP_KERNEL,
+				     dev_to_node(dev));
+
+		if (!saved_group) {
+			/* Free saved groups */
+			idxd_free_saved(saved_groups, NULL, NULL, idxd);
+
+			return -ENOMEM;
+		}
+
+		memcpy(saved_group, idxd->groups[i], sizeof(*saved_group));
+		saved_groups[i] = no_free_ptr(saved_group);
+	}
+
+	struct idxd_engine **saved_engines =
+			kcalloc_node(idxd->max_engines,
+				     sizeof(struct idxd_engine *),
+				     GFP_KERNEL, dev_to_node(dev));
+	if (!saved_engines) {
+		/* Free saved groups */
+		idxd_free_saved(saved_groups, NULL, NULL, idxd);
+
+		return -ENOMEM;
+	}
+	for (i = 0; i < idxd->max_engines; i++) {
+		struct idxd_engine *saved_engine __free(kfree) =
+				kzalloc_node(sizeof(*saved_engine), GFP_KERNEL,
+					     dev_to_node(dev));
+		if (!saved_engine) {
+			/* Free saved groups and engines */
+			idxd_free_saved(saved_groups, saved_engines, NULL,
+					idxd);
+
+			return -ENOMEM;
+		}
+
+		memcpy(saved_engine, idxd->engines[i], sizeof(*saved_engine));
+		saved_engines[i] = no_free_ptr(saved_engine);
+	}
+
+	unsigned long *saved_wq_enable_map __free(bitmap) =
+			bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL,
+					   dev_to_node(dev));
+	if (!saved_wq_enable_map) {
+		/* Free saved groups and engines */
+		idxd_free_saved(saved_groups, saved_engines, NULL, idxd);
+
+		return -ENOMEM;
+	}
+
+	bitmap_copy(saved_wq_enable_map, idxd->wq_enable_map, idxd->max_wqs);
+
+	struct idxd_wq **saved_wqs __free(kfree) =
+			kcalloc_node(idxd->max_wqs, sizeof(struct idxd_wq *),
+				     GFP_KERNEL, dev_to_node(dev));
+	if (!saved_wqs) {
+		/* Free saved groups and engines */
+		idxd_free_saved(saved_groups, saved_engines, NULL, idxd);
+
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *saved_wq __free(kfree) =
+			kzalloc_node(sizeof(*saved_wq), GFP_KERNEL,
+				     dev_to_node(dev));
+		struct idxd_wq *wq;
+
+		if (!saved_wq) {
+			/* Free saved groups, engines, and wqs */
+			idxd_free_saved(saved_groups, saved_engines, saved_wqs,
+					idxd);
+
+			return -ENOMEM;
+		}
+
+		if (!test_bit(i, saved_wq_enable_map))
+			continue;
+
+		wq = idxd->wqs[i];
+		mutex_lock(&wq->wq_lock);
+		memcpy(saved_wq, wq, sizeof(*saved_wq));
+		saved_wqs[i] = no_free_ptr(saved_wq);
+		mutex_unlock(&wq->wq_lock);
+	}
+
+	/* Save configurations */
+	idxd_saved->saved_groups = no_free_ptr(saved_groups);
+	idxd_saved->saved_engines = no_free_ptr(saved_engines);
+	idxd_saved->saved_wq_enable_map = no_free_ptr(saved_wq_enable_map);
+	idxd_saved->saved_wqs = no_free_ptr(saved_wqs);
+
+	return 0;
+}
+
+/*
+ * Restore IDXD device configurations including engines, groups, wqs etc
+ * that were saved before.
+ */
+static void idxd_device_config_restore(struct idxd_device *idxd,
+				       struct idxd_saved_states *idxd_saved)
+{
+	struct idxd_evl *saved_evl = &idxd_saved->saved_evl;
+	int i;
+
+	idxd->rdbuf_limit = idxd_saved->saved_idxd.rdbuf_limit;
+
+	if (saved_evl)
+		idxd->evl->size = saved_evl->size;
+
+	for (i = 0; i < idxd->max_groups; i++) {
+		struct idxd_group *saved_group, *group;
+
+		saved_group = idxd_saved->saved_groups[i];
+		group = idxd->groups[i];
+
+		group->rdbufs_allowed = saved_group->rdbufs_allowed;
+		group->rdbufs_reserved = saved_group->rdbufs_reserved;
+		group->tc_a = saved_group->tc_a;
+		group->tc_b = saved_group->tc_b;
+		group->use_rdbuf_limit = saved_group->use_rdbuf_limit;
+
+		kfree(saved_group);
+	}
+	kfree(idxd_saved->saved_groups);
+
+	for (i = 0; i < idxd->max_engines; i++) {
+		struct idxd_engine *saved_engine, *engine;
+
+		saved_engine = idxd_saved->saved_engines[i];
+		engine = idxd->engines[i];
+
+		engine->group = saved_engine->group;
+
+		kfree(saved_engine);
+	}
+	kfree(idxd_saved->saved_engines);
+
+	bitmap_copy(idxd->wq_enable_map, idxd_saved->saved_wq_enable_map,
+		    idxd->max_wqs);
+	bitmap_free(idxd_saved->saved_wq_enable_map);
+
+	for (i = 0; i < idxd->max_wqs; i++) {
+		struct idxd_wq *saved_wq, *wq;
+		size_t len;
+
+		if (!test_bit(i, idxd->wq_enable_map))
+			continue;
+
+		saved_wq = idxd_saved->saved_wqs[i];
+		wq = idxd->wqs[i];
+
+		mutex_lock(&wq->wq_lock);
+
+		wq->group = saved_wq->group;
+		wq->flags = saved_wq->flags;
+		wq->threshold = saved_wq->threshold;
+		wq->size = saved_wq->size;
+		wq->priority = saved_wq->priority;
+		wq->type = saved_wq->type;
+		len = strlen(saved_wq->name) + 1;
+		strscpy(wq->name, saved_wq->name, len);
+		wq->max_xfer_bytes = saved_wq->max_xfer_bytes;
+		wq->max_batch_size = saved_wq->max_batch_size;
+		wq->enqcmds_retries = saved_wq->enqcmds_retries;
+		wq->descs = saved_wq->descs;
+		wq->idxd_chan = saved_wq->idxd_chan;
+		len = strlen(saved_wq->driver_name) + 1;
+		strscpy(wq->driver_name, saved_wq->driver_name, len);
+
+		mutex_unlock(&wq->wq_lock);
+
+		kfree(saved_wq);
+	}
+
+	kfree(idxd_saved->saved_wqs);
+}
+
+static void idxd_reset_prepare(struct pci_dev *pdev)
+{
+	struct idxd_device *idxd = pci_get_drvdata(pdev);
+	struct device *dev = &idxd->pdev->dev;
+	const char *idxd_name;
 	int rc;
 
-	rc = pci_enable_device(pdev);
-	if (rc)
-		return rc;
+	dev = &idxd->pdev->dev;
+	idxd_name = dev_name(idxd_confdev(idxd));
 
-	dev_dbg(dev, "Alloc IDXD context\n");
-	idxd = idxd_alloc(pdev, data);
-	if (!idxd) {
-		rc = -ENOMEM;
-		goto err_idxd_alloc;
+	struct idxd_saved_states *idxd_saved __free(kfree) =
+			kzalloc_node(sizeof(*idxd_saved), GFP_KERNEL,
+				     dev_to_node(&pdev->dev));
+	if (!idxd_saved) {
+		dev_err(dev, "HALT: no memory\n");
+
+		return;
 	}
 
-	dev_dbg(dev, "Mapping BARs\n");
-	idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0);
-	if (!idxd->reg_base) {
-		rc = -ENOMEM;
-		goto err_iomap;
+	/* Save IDXD configurations. */
+	rc = idxd_device_config_save(idxd, idxd_saved);
+	if (rc < 0) {
+		dev_err(dev, "HALT: cannot save %s configs\n", idxd_name);
+
+		return;
+	}
+
+	idxd->idxd_saved = no_free_ptr(idxd_saved);
+
+	/* Save PCI device state. */
+	pci_save_state(idxd->pdev);
+}
+
+static void idxd_reset_done(struct pci_dev *pdev)
+{
+	struct idxd_device *idxd = pci_get_drvdata(pdev);
+	const char *idxd_name;
+	struct device *dev;
+	int rc, i;
+
+	if (!idxd->idxd_saved)
+		return;
+
+	dev = &idxd->pdev->dev;
+	idxd_name = dev_name(idxd_confdev(idxd));
+
+	/* Restore PCI device state. */
+	pci_restore_state(idxd->pdev);
+
+	/* Unbind idxd device from driver. */
+	idxd_unbind(&idxd_drv.drv, idxd_name);
+
+	/*
+	 * Probe PCI device without allocating or changing
+	 * idxd software data which keeps the same as before FLR.
+	 */
+	idxd_pci_probe_alloc(idxd, NULL, NULL);
+
+	/* Restore IDXD configurations. */
+	idxd_device_config_restore(idxd, idxd->idxd_saved);
+
+	/* Re-configure IDXD device if allowed. */
+	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
+		rc = idxd_device_config(idxd);
+		if (rc < 0) {
+			dev_err(dev, "HALT: %s config fails\n", idxd_name);
+			goto out;
+		}
+	}
+
+	/* Bind IDXD device to driver. */
+	rc = idxd_bind(&idxd_drv.drv, idxd_name);
+	if (rc < 0) {
+		dev_err(dev, "HALT: binding %s to driver fails\n", idxd_name);
+		goto out;
 	}
 
-	dev_dbg(dev, "Set DMA masks\n");
-	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	/* Bind enabled wq in the IDXD device to driver. */
+	for (i = 0; i < idxd->max_wqs; i++) {
+		if (test_bit(i, idxd->wq_enable_map)) {
+			struct idxd_wq *wq = idxd->wqs[i];
+			char wq_name[32];
+
+			wq->state = IDXD_WQ_DISABLED;
+			sprintf(wq_name, "wq%d.%d", idxd->id, wq->id);
+			/*
+			 * Bind to user driver depending on wq type.
+			 *
+			 * Currently only support user type WQ. Will support
+			 * kernel type WQ in the future.
+			 */
+			if (wq->type == IDXD_WQT_USER)
+				rc = idxd_bind(&idxd_user_drv.drv, wq_name);
+			else
+				rc = -EINVAL;
+			if (rc < 0) {
+				clear_bit(i, idxd->wq_enable_map);
+				dev_err(dev,
+					"HALT: unable to re-enable wq %s\n",
+					dev_name(wq_confdev(wq)));
+			}
+		}
+	}
+out:
+	kfree(idxd->idxd_saved);
+}
+
+static const struct pci_error_handlers idxd_error_handler = {
+	.reset_prepare	= idxd_reset_prepare,
+	.reset_done	= idxd_reset_done,
+};
+
+/*
+ * Probe idxd PCI device.
+ * If idxd is not given, need to allocate idxd and set up its data.
+ *
+ * If idxd is given, idxd was allocated and setup already. Just need to
+ * configure device without re-allocating and re-configuring idxd data.
+ * This is useful for recovering from FLR.
+ */
+int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev,
+			 const struct pci_device_id *id)
+{
+	bool alloc_idxd = idxd ? false : true;
+	struct idxd_driver_data *data;
+	struct device *dev;
+	int rc;
+
+	pdev = idxd ? idxd->pdev : pdev;
+	dev = &pdev->dev;
+	data = id ? (struct idxd_driver_data *)id->driver_data : NULL;
+	rc = pci_enable_device(pdev);
 	if (rc)
-		goto err;
+		return rc;
+
+	if (alloc_idxd) {
+		dev_dbg(dev, "Alloc IDXD context\n");
+		idxd = idxd_alloc(pdev, data);
+		if (!idxd) {
+			rc = -ENOMEM;
+			goto err_idxd_alloc;
+		}
+
+		dev_dbg(dev, "Mapping BARs\n");
+		idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0);
+		if (!idxd->reg_base) {
+			rc = -ENOMEM;
+			goto err_iomap;
+		}
+
+		dev_dbg(dev, "Set DMA masks\n");
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+		if (rc)
+			goto err;
+	}
 
 	dev_dbg(dev, "Set PCI master\n");
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, idxd);
 
-	idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET);
-	rc = idxd_probe(idxd);
-	if (rc) {
-		dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n");
-		goto err;
-	}
+	if (alloc_idxd) {
+		idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET);
+		rc = idxd_probe(idxd);
+		if (rc) {
+			dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n");
+			goto err;
+		}
+
+		if (data->load_device_defaults) {
+			rc = data->load_device_defaults(idxd);
+			if (rc)
+				dev_warn(dev, "IDXD loading device defaults failed\n");
+		}
+
+		rc = idxd_register_devices(idxd);
+		if (rc) {
+			dev_err(dev, "IDXD sysfs setup failed\n");
+			goto err_dev_register;
+		}
 
-	if (data->load_device_defaults) {
-		rc = data->load_device_defaults(idxd);
+		rc = idxd_device_init_debugfs(idxd);
 		if (rc)
-			dev_warn(dev, "IDXD loading device defaults failed\n");
+			dev_warn(dev, "IDXD debugfs failed to setup\n");
 	}
 
-	rc = idxd_register_devices(idxd);
-	if (rc) {
-		dev_err(dev, "IDXD sysfs setup failed\n");
-		goto err_dev_register;
-	}
+	if (!alloc_idxd) {
+		/* Release interrupts in the IDXD device. */
+		idxd_cleanup_interrupts(idxd);
 
-	rc = idxd_device_init_debugfs(idxd);
-	if (rc)
-		dev_warn(dev, "IDXD debugfs failed to setup\n");
+		/* Re-enable interrupts in the IDXD device. */
+		rc = idxd_setup_interrupts(idxd);
+		if (rc)
+			dev_warn(dev, "IDXD interrupts failed to setup\n");
+	}
 
 	dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n",
 		 idxd->hw.version);
 
-	idxd->user_submission_safe = data->user_submission_safe;
+	if (data)
+		idxd->user_submission_safe = data->user_submission_safe;
 
 	return 0;
 
@@ -798,6 +1197,11 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return rc;
 }
 
+static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	return idxd_pci_probe_alloc(NULL, pdev, id);
+}
+
 void idxd_wqs_quiesce(struct idxd_device *idxd)
 {
 	struct idxd_wq *wq;
@@ -864,6 +1268,7 @@ static struct pci_driver idxd_pci_driver = {
 	.probe		= idxd_pci_probe,
 	.remove		= idxd_remove,
 	.shutdown	= idxd_shutdown,
+	.err_handler	= &idxd_error_handler,
 };
 
 static int __init idxd_init_module(void)
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index fc049c9c9892..1107db3ce0a3 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -383,15 +383,65 @@ static void process_evl_entries(struct idxd_device *idxd)
 	mutex_unlock(&evl->lock);
 }
 
+static void idxd_device_flr(struct work_struct *work)
+{
+	struct idxd_device *idxd = container_of(work, struct idxd_device, work);
+	int rc;
+
+	/*
+	 * IDXD device requires a Function Level Reset (FLR).
+	 * pci_reset_function() will reset the device with FLR.
+	 */
+	rc = pci_reset_function(idxd->pdev);
+	if (rc)
+		dev_err(&idxd->pdev->dev, "FLR failed\n");
+}
+
+static irqreturn_t idxd_halt(struct idxd_device *idxd)
+{
+	union gensts_reg gensts;
+
+	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
+	if (gensts.state == IDXD_DEVICE_STATE_HALT) {
+		idxd->state = IDXD_DEV_HALTED;
+		if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) {
+			/*
+			 * If we need a software reset, we will throw the work
+			 * on a system workqueue in order to allow interrupts
+			 * for the device command completions.
+			 */
+			INIT_WORK(&idxd->work, idxd_device_reinit);
+			queue_work(idxd->wq, &idxd->work);
+		} else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) {
+			idxd->state = IDXD_DEV_HALTED;
+			idxd_mask_error_interrupts(idxd);
+			dev_dbg(&idxd->pdev->dev,
+				"idxd halted, doing FLR. After FLR, configs are restored\n");
+			INIT_WORK(&idxd->work, idxd_device_flr);
+			queue_work(idxd->wq, &idxd->work);
+
+		} else {
+			idxd->state = IDXD_DEV_HALTED;
+			idxd_wqs_quiesce(idxd);
+			idxd_wqs_unmap_portal(idxd);
+			idxd_device_clear_state(idxd);
+			dev_err(&idxd->pdev->dev,
+				"idxd halted, need system reset");
+
+			return -ENXIO;
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
 irqreturn_t idxd_misc_thread(int vec, void *data)
 {
 	struct idxd_irq_entry *irq_entry = data;
 	struct idxd_device *idxd = ie_to_idxd(irq_entry);
 	struct device *dev = &idxd->pdev->dev;
-	union gensts_reg gensts;
 	u32 val = 0;
 	int i;
-	bool err = false;
 	u32 cause;
 
 	cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET);
@@ -401,7 +451,7 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 	iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET);
 
 	if (cause & IDXD_INTC_HALT_STATE)
-		goto halt;
+		return idxd_halt(idxd);
 
 	if (cause & IDXD_INTC_ERR) {
 		spin_lock(&idxd->dev_lock);
@@ -435,7 +485,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 		for (i = 0; i < 4; i++)
 			dev_warn_ratelimited(dev, "err[%d]: %#16.16llx\n",
 					     i, idxd->sw_err.bits[i]);
-		err = true;
 	}
 
 	if (cause & IDXD_INTC_INT_HANDLE_REVOKED) {
@@ -480,34 +529,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data)
 		dev_warn_once(dev, "Unexpected interrupt cause bits set: %#x\n",
 			      val);
 
-	if (!err)
-		goto out;
-
-halt:
-	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
-	if (gensts.state == IDXD_DEVICE_STATE_HALT) {
-		idxd->state = IDXD_DEV_HALTED;
-		if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) {
-			/*
-			 * If we need a software reset, we will throw the work
-			 * on a system workqueue in order to allow interrupts
-			 * for the device command completions.
-			 */
-			INIT_WORK(&idxd->work, idxd_device_reinit);
-			queue_work(idxd->wq, &idxd->work);
-		} else {
-			idxd->state = IDXD_DEV_HALTED;
-			idxd_wqs_quiesce(idxd);
-			idxd_wqs_unmap_portal(idxd);
-			idxd_device_clear_state(idxd);
-			dev_err(&idxd->pdev->dev,
-				"idxd halted, need %s.\n",
-				gensts.reset_type == IDXD_DEVICE_RESET_FLR ?
-				"FLR" : "system reset");
-		}
-	}
-
-out:
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index c426511f2104..006ba206ab1b 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -9,6 +9,7 @@
 #define PCI_DEVICE_ID_INTEL_DSA_GNRD	0x11fb
 #define PCI_DEVICE_ID_INTEL_DSA_DMR	0x1212
 #define PCI_DEVICE_ID_INTEL_IAA_DMR	0x1216
+#define PCI_DEVICE_ID_INTEL_IAA_PTL	0xb02d
 
 #define DEVICE_VERSION_1		0x100
 #define DEVICE_VERSION_2		0x200
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index f706eae0e76b..6af493f6ba77 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -1979,13 +1979,3 @@ void idxd_unregister_devices(struct idxd_device *idxd)
 		device_unregister(group_confdev(group));
 	}
 }
-
-int idxd_register_bus_type(void)
-{
-	return bus_register(&dsa_bus_type);
-}
-
-void idxd_unregister_bus_type(void)
-{
-	bus_unregister(&dsa_bus_type);
-}
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 40b76b40bc30..fa6e4646fdc2 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1369,10 +1369,9 @@ static int mv_xor_probe(struct platform_device *pdev)
 		return 0;
 
 	if (pdev->dev.of_node) {
-		struct device_node *np;
 		int i = 0;
 
-		for_each_child_of_node(pdev->dev.of_node, np) {
+		for_each_child_of_node_scoped(pdev->dev.of_node, np) {
 			struct mv_xor_chan *chan;
 			dma_cap_mask_t cap_mask;
 			int irq;
@@ -1388,7 +1387,6 @@ static int mv_xor_probe(struct platform_device *pdev)
 			irq = irq_of_parse_and_map(np, 0);
 			if (!irq) {
 				ret = -ENODEV;
-				of_node_put(np);
 				goto err_channel_add;
 			}
 
@@ -1397,7 +1395,6 @@ static int mv_xor_probe(struct platform_device *pdev)
 			if (IS_ERR(chan)) {
 				ret = PTR_ERR(chan);
 				irq_dispose_mapping(irq);
-				of_node_put(np);
 				goto err_channel_add;
 			}
 
diff --git a/drivers/dma/ptdma/Kconfig b/drivers/dma/ptdma/Kconfig
deleted file mode 100644
index b430edd709f9..000000000000
--- a/drivers/dma/ptdma/Kconfig
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config AMD_PTDMA
-	tristate  "AMD PassThru DMA Engine"
-	depends on X86_64 && PCI
-	select DMA_ENGINE
-	select DMA_VIRTUAL_CHANNELS
-	help
-	  Enable support for the AMD PTDMA controller. This controller
-	  provides DMA capabilities to perform high bandwidth memory to
-	  memory and IO copy operations. It performs DMA transfer through
-	  queue-based descriptor management. This DMA controller is intended
-	  to be used with AMD Non-Transparent Bridge devices and not for
-	  general purpose peripheral DMA.
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index bbc3276992bb..c14557efd577 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -59,6 +59,9 @@ struct bam_desc_hw {
 #define DESC_FLAG_NWD BIT(12)
 #define DESC_FLAG_CMD BIT(11)
 
+#define BAM_NDP_REVISION_START	0x20
+#define BAM_NDP_REVISION_END	0x27
+
 struct bam_async_desc {
 	struct virt_dma_desc vd;
 
@@ -398,6 +401,7 @@ struct bam_device {
 
 	/* dma start transaction tasklet */
 	struct tasklet_struct task;
+	u32 bam_revision;
 };
 
 /**
@@ -441,8 +445,10 @@ static void bam_reset(struct bam_device *bdev)
 	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
 
 	/* set descriptor threshold, start with 4 bytes */
-	writel_relaxed(DEFAULT_CNT_THRSHLD,
-			bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+	if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START,
+		     BAM_NDP_REVISION_END))
+		writel_relaxed(DEFAULT_CNT_THRSHLD,
+			       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
 
 	/* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */
 	writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS));
@@ -1000,9 +1006,10 @@ static void bam_apply_new_config(struct bam_chan *bchan,
 			maxburst = bchan->slave.src_maxburst;
 		else
 			maxburst = bchan->slave.dst_maxburst;
-
-		writel_relaxed(maxburst,
-			       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+		if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START,
+			     BAM_NDP_REVISION_END))
+			writel_relaxed(maxburst,
+				       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
 	}
 
 	bchan->reconfigure = 0;
@@ -1192,10 +1199,11 @@ static int bam_init(struct bam_device *bdev)
 	u32 val;
 
 	/* read revision and configuration information */
-	if (!bdev->num_ees) {
-		val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION));
+	val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION));
+	if (!bdev->num_ees)
 		bdev->num_ees = (val >> NUM_EES_SHIFT) & NUM_EES_MASK;
-	}
+
+	bdev->bam_revision = val & REVISION_MASK;
 
 	/* check that configured EE is within range */
 	if (bdev->ee >= bdev->num_ees)
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 52a7c8f2498f..b1f0001cc99c 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -18,6 +18,7 @@
 #include "../virt-dma.h"
 
 #define TRE_TYPE_DMA		0x10
+#define TRE_TYPE_IMMEDIATE_DMA	0x11
 #define TRE_TYPE_GO		0x20
 #define TRE_TYPE_CONFIG0	0x22
 
@@ -64,6 +65,7 @@
 
 /* DMA TRE */
 #define TRE_DMA_LEN		GENMASK(23, 0)
+#define TRE_DMA_IMMEDIATE_LEN	GENMASK(3, 0)
 
 /* Register offsets from gpi-top */
 #define GPII_n_CH_k_CNTXT_0_OFFS(n, k)	(0x20000 + (0x4000 * (n)) + (0x80 * (k)))
@@ -1711,6 +1713,7 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
 	dma_addr_t address;
 	struct gpi_tre *tre;
 	unsigned int i;
+	int len;
 
 	/* first create config tre if applicable */
 	if (direction == DMA_MEM_TO_DEV && spi->set_config) {
@@ -1763,14 +1766,30 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
 	tre_idx++;
 
 	address = sg_dma_address(sgl);
-	tre->dword[0] = lower_32_bits(address);
-	tre->dword[1] = upper_32_bits(address);
+	len = sg_dma_len(sgl);
 
-	tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN);
+	/* Support Immediate dma for write transfers for data length up to 8 bytes */
+	if (direction == DMA_MEM_TO_DEV && len <= 2 * sizeof(tre->dword[0])) {
+		/*
+		 * For Immediate dma, data length may not always be length of 8 bytes,
+		 * it can be length less than 8, hence initialize both dword's with 0
+		 */
+		tre->dword[0] = 0;
+		tre->dword[1] = 0;
+		memcpy(&tre->dword[0], sg_virt(sgl), len);
 
-	tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
-	if (direction == DMA_MEM_TO_DEV)
-		tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT);
+		tre->dword[2] = u32_encode_bits(len, TRE_DMA_IMMEDIATE_LEN);
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_IMMEDIATE_DMA, TRE_FLAGS_TYPE);
+	} else {
+		tre->dword[0] = lower_32_bits(address);
+		tre->dword[1] = upper_32_bits(address);
+
+		tre->dword[2] = u32_encode_bits(len, TRE_DMA_LEN);
+		tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE);
+	}
+
+	tre->dword[3] |= u32_encode_bits(direction == DMA_MEM_TO_DEV,
+					 TRE_FLAGS_IEOT);
 
 	for (i = 0; i < tre_idx; i++)
 		dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0],
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2679c1f09faf..0c45ce8c74aa 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -2023,6 +2023,10 @@ static const struct of_device_id rcar_dmac_of_ids[] = {
 		.compatible = "renesas,rcar-gen4-dmac",
 		.data = &rcar_gen4_dmac_data,
 	}, {
+		/*
+		 * Backward compatibility for between v5.12 - v5.19
+		 * which didn't combined with "renesas,rcar-gen4-dmac"
+		 */
 		.compatible = "renesas,dmac-r8a779a0",
 		.data = &rcar_gen4_dmac_data,
 	},
diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c
index f37cdf6f2179..24796aaaddfa 100644
--- a/drivers/dma/sun4i-dma.c
+++ b/drivers/dma/sun4i-dma.c
@@ -13,7 +13,9 @@
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/of_dma.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
@@ -31,12 +33,21 @@
 #define SUN4I_DMA_CFG_SRC_ADDR_MODE(mode)	((mode) << 5)
 #define SUN4I_DMA_CFG_SRC_DRQ_TYPE(type)	(type)
 
+#define SUNIV_DMA_CFG_DST_DATA_WIDTH(width)	((width) << 24)
+#define SUNIV_DMA_CFG_SRC_DATA_WIDTH(width)	((width) << 8)
+
+#define SUN4I_MAX_BURST	8
+#define SUNIV_MAX_BURST	4
+
 /** Normal DMA register values **/
 
 /* Normal DMA source/destination data request type values */
 #define SUN4I_NDMA_DRQ_TYPE_SDRAM		0x16
 #define SUN4I_NDMA_DRQ_TYPE_LIMIT		(0x1F + 1)
 
+#define SUNIV_NDMA_DRQ_TYPE_SDRAM		0x11
+#define SUNIV_NDMA_DRQ_TYPE_LIMIT		(0x17 + 1)
+
 /** Normal DMA register layout **/
 
 /* Dedicated DMA source/destination address mode values */
@@ -50,6 +61,9 @@
 #define SUN4I_NDMA_CFG_BYTE_COUNT_MODE_REMAIN	BIT(15)
 #define SUN4I_NDMA_CFG_SRC_NON_SECURE		BIT(6)
 
+#define SUNIV_NDMA_CFG_CONT_MODE		BIT(29)
+#define SUNIV_NDMA_CFG_WAIT_STATE(n)		((n) << 26)
+
 /** Dedicated DMA register values **/
 
 /* Dedicated DMA source/destination address mode values */
@@ -62,6 +76,9 @@
 #define SUN4I_DDMA_DRQ_TYPE_SDRAM		0x1
 #define SUN4I_DDMA_DRQ_TYPE_LIMIT		(0x1F + 1)
 
+#define SUNIV_DDMA_DRQ_TYPE_SDRAM		0x1
+#define SUNIV_DDMA_DRQ_TYPE_LIMIT		(0x9 + 1)
+
 /** Dedicated DMA register layout **/
 
 /* Dedicated DMA configuration register layout */
@@ -115,6 +132,11 @@
 #define SUN4I_DMA_NR_MAX_VCHANS						\
 	(SUN4I_NDMA_NR_MAX_VCHANS + SUN4I_DDMA_NR_MAX_VCHANS)
 
+#define SUNIV_NDMA_NR_MAX_CHANNELS	4
+#define SUNIV_DDMA_NR_MAX_CHANNELS	4
+#define SUNIV_NDMA_NR_MAX_VCHANS	(24 * 2 - 1)
+#define SUNIV_DDMA_NR_MAX_VCHANS	10
+
 /* This set of SUN4I_DDMA timing parameters were found experimentally while
  * working with the SPI driver and seem to make it behave correctly */
 #define SUN4I_DDMA_MAGIC_SPI_PARAMETERS \
@@ -132,6 +154,33 @@
 #define SUN4I_DDMA_MAX_SEG_SIZE		SZ_16M
 #define SUN4I_DMA_MAX_SEG_SIZE		SUN4I_NDMA_MAX_SEG_SIZE
 
+/*
+ * Hardware channels / ports representation
+ *
+ * The hardware is used in several SoCs, with differing numbers
+ * of channels and endpoints. This structure ties those numbers
+ * to a certain compatible string.
+ */
+struct sun4i_dma_config {
+	u32 ndma_nr_max_channels;
+	u32 ndma_nr_max_vchans;
+
+	u32 ddma_nr_max_channels;
+	u32 ddma_nr_max_vchans;
+
+	u32 dma_nr_max_channels;
+
+	void (*set_dst_data_width)(u32 *p_cfg, s8 data_width);
+	void (*set_src_data_width)(u32 *p_cfg, s8 data_width);
+	int (*convert_burst)(u32 maxburst);
+
+	u8 ndma_drq_sdram;
+	u8 ddma_drq_sdram;
+
+	u8 max_burst;
+	bool has_reset;
+};
+
 struct sun4i_dma_pchan {
 	/* Register base of channel */
 	void __iomem			*base;
@@ -170,7 +219,7 @@ struct sun4i_dma_contract {
 };
 
 struct sun4i_dma_dev {
-	DECLARE_BITMAP(pchans_used, SUN4I_DMA_NR_MAX_CHANNELS);
+	unsigned long *pchans_used;
 	struct dma_device		slave;
 	struct sun4i_dma_pchan		*pchans;
 	struct sun4i_dma_vchan		*vchans;
@@ -178,6 +227,8 @@ struct sun4i_dma_dev {
 	struct clk			*clk;
 	int				irq;
 	spinlock_t			lock;
+	const struct sun4i_dma_config *cfg;
+	struct reset_control *rst;
 };
 
 static struct sun4i_dma_dev *to_sun4i_dma_dev(struct dma_device *dev)
@@ -200,7 +251,27 @@ static struct device *chan2dev(struct dma_chan *chan)
 	return &chan->dev->device;
 }
 
-static int convert_burst(u32 maxburst)
+static void set_dst_data_width_a10(u32 *p_cfg, s8 data_width)
+{
+	*p_cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(data_width);
+}
+
+static void set_src_data_width_a10(u32 *p_cfg, s8 data_width)
+{
+	*p_cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(data_width);
+}
+
+static void set_dst_data_width_f1c100s(u32 *p_cfg, s8 data_width)
+{
+	*p_cfg |= SUNIV_DMA_CFG_DST_DATA_WIDTH(data_width);
+}
+
+static void set_src_data_width_f1c100s(u32 *p_cfg, s8 data_width)
+{
+	*p_cfg |= SUNIV_DMA_CFG_SRC_DATA_WIDTH(data_width);
+}
+
+static int convert_burst_a10(u32 maxburst)
 {
 	if (maxburst > 8)
 		return -EINVAL;
@@ -209,6 +280,15 @@ static int convert_burst(u32 maxburst)
 	return (maxburst >> 2);
 }
 
+static int convert_burst_f1c100s(u32 maxburst)
+{
+	if (maxburst > 4)
+		return -EINVAL;
+
+	/* 1 -> 0, 4 -> 1 */
+	return (maxburst >> 2);
+}
+
 static int convert_buswidth(enum dma_slave_buswidth addr_width)
 {
 	if (addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES)
@@ -233,15 +313,15 @@ static struct sun4i_dma_pchan *find_and_use_pchan(struct sun4i_dma_dev *priv,
 	int i, max;
 
 	/*
-	 * pchans 0-SUN4I_NDMA_NR_MAX_CHANNELS are normal, and
-	 * SUN4I_NDMA_NR_MAX_CHANNELS+ are dedicated ones
+	 * pchans 0-priv->cfg->ndma_nr_max_channels are normal, and
+	 * priv->cfg->ndma_nr_max_channels+ are dedicated ones
 	 */
 	if (vchan->is_dedicated) {
-		i = SUN4I_NDMA_NR_MAX_CHANNELS;
-		max = SUN4I_DMA_NR_MAX_CHANNELS;
+		i = priv->cfg->ndma_nr_max_channels;
+		max = priv->cfg->dma_nr_max_channels;
 	} else {
 		i = 0;
-		max = SUN4I_NDMA_NR_MAX_CHANNELS;
+		max = priv->cfg->ndma_nr_max_channels;
 	}
 
 	spin_lock_irqsave(&priv->lock, flags);
@@ -444,6 +524,7 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
 		      size_t len, struct dma_slave_config *sconfig,
 		      enum dma_transfer_direction direction)
 {
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
 	struct sun4i_dma_promise *promise;
 	int ret;
 
@@ -467,13 +548,13 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
 		sconfig->src_addr_width, sconfig->dst_addr_width);
 
 	/* Source burst */
-	ret = convert_burst(sconfig->src_maxburst);
+	ret = priv->cfg->convert_burst(sconfig->src_maxburst);
 	if (ret < 0)
 		goto fail;
 	promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret);
 
 	/* Destination burst */
-	ret = convert_burst(sconfig->dst_maxburst);
+	ret = priv->cfg->convert_burst(sconfig->dst_maxburst);
 	if (ret < 0)
 		goto fail;
 	promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret);
@@ -482,13 +563,13 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
 	ret = convert_buswidth(sconfig->src_addr_width);
 	if (ret < 0)
 		goto fail;
-	promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret);
+	priv->cfg->set_src_data_width(&promise->cfg, ret);
 
 	/* Destination bus width */
 	ret = convert_buswidth(sconfig->dst_addr_width);
 	if (ret < 0)
 		goto fail;
-	promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret);
+	priv->cfg->set_dst_data_width(&promise->cfg, ret);
 
 	return promise;
 
@@ -510,6 +591,7 @@ static struct sun4i_dma_promise *
 generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
 		      size_t len, struct dma_slave_config *sconfig)
 {
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
 	struct sun4i_dma_promise *promise;
 	int ret;
 
@@ -524,13 +606,13 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
 		SUN4I_DDMA_CFG_BYTE_COUNT_MODE_REMAIN;
 
 	/* Source burst */
-	ret = convert_burst(sconfig->src_maxburst);
+	ret = priv->cfg->convert_burst(sconfig->src_maxburst);
 	if (ret < 0)
 		goto fail;
 	promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret);
 
 	/* Destination burst */
-	ret = convert_burst(sconfig->dst_maxburst);
+	ret = priv->cfg->convert_burst(sconfig->dst_maxburst);
 	if (ret < 0)
 		goto fail;
 	promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret);
@@ -539,13 +621,13 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest,
 	ret = convert_buswidth(sconfig->src_addr_width);
 	if (ret < 0)
 		goto fail;
-	promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret);
+	priv->cfg->set_src_data_width(&promise->cfg, ret);
 
 	/* Destination bus width */
 	ret = convert_buswidth(sconfig->dst_addr_width);
 	if (ret < 0)
 		goto fail;
-	promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret);
+	priv->cfg->set_dst_data_width(&promise->cfg, ret);
 
 	return promise;
 
@@ -622,6 +704,7 @@ static struct dma_async_tx_descriptor *
 sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 			  dma_addr_t src, size_t len, unsigned long flags)
 {
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
 	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
 	struct dma_slave_config *sconfig = &vchan->cfg;
 	struct sun4i_dma_promise *promise;
@@ -638,8 +721,8 @@ sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 	 */
 	sconfig->src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 	sconfig->dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-	sconfig->src_maxburst = 8;
-	sconfig->dst_maxburst = 8;
+	sconfig->src_maxburst = priv->cfg->max_burst;
+	sconfig->dst_maxburst = priv->cfg->max_burst;
 
 	if (vchan->is_dedicated)
 		promise = generate_ddma_promise(chan, src, dest, len, sconfig);
@@ -654,11 +737,13 @@ sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 
 	/* Configure memcpy mode */
 	if (vchan->is_dedicated) {
-		promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM) |
-				SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM);
+		promise->cfg |=
+			SUN4I_DMA_CFG_SRC_DRQ_TYPE(priv->cfg->ddma_drq_sdram) |
+			SUN4I_DMA_CFG_DST_DRQ_TYPE(priv->cfg->ddma_drq_sdram);
 	} else {
-		promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM) |
-				SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM);
+		promise->cfg |=
+			SUN4I_DMA_CFG_SRC_DRQ_TYPE(priv->cfg->ndma_drq_sdram) |
+			SUN4I_DMA_CFG_DST_DRQ_TYPE(priv->cfg->ndma_drq_sdram);
 	}
 
 	/* Fill the contract with our only promise */
@@ -673,6 +758,7 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len,
 			  size_t period_len, enum dma_transfer_direction dir,
 			  unsigned long flags)
 {
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
 	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
 	struct dma_slave_config *sconfig = &vchan->cfg;
 	struct sun4i_dma_promise *promise;
@@ -696,11 +782,11 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len,
 	if (vchan->is_dedicated) {
 		io_mode = SUN4I_DDMA_ADDR_MODE_IO;
 		linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR;
-		ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM;
+		ram_type = priv->cfg->ddma_drq_sdram;
 	} else {
 		io_mode = SUN4I_NDMA_ADDR_MODE_IO;
 		linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR;
-		ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM;
+		ram_type = priv->cfg->ndma_drq_sdram;
 	}
 
 	if (dir == DMA_MEM_TO_DEV) {
@@ -793,6 +879,7 @@ sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction dir,
 			unsigned long flags, void *context)
 {
+	struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device);
 	struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan);
 	struct dma_slave_config *sconfig = &vchan->cfg;
 	struct sun4i_dma_promise *promise;
@@ -818,11 +905,11 @@ sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (vchan->is_dedicated) {
 		io_mode = SUN4I_DDMA_ADDR_MODE_IO;
 		linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR;
-		ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM;
+		ram_type = priv->cfg->ddma_drq_sdram;
 	} else {
 		io_mode = SUN4I_NDMA_ADDR_MODE_IO;
 		linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR;
-		ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM;
+		ram_type = priv->cfg->ndma_drq_sdram;
 	}
 
 	if (dir == DMA_MEM_TO_DEV)
@@ -1150,6 +1237,10 @@ static int sun4i_dma_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	priv->cfg = of_device_get_match_data(&pdev->dev);
+	if (!priv->cfg)
+		return -ENODEV;
+
 	priv->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
@@ -1164,6 +1255,13 @@ static int sun4i_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->clk);
 	}
 
+	if (priv->cfg->has_reset) {
+		priv->rst = devm_reset_control_get_exclusive_deasserted(&pdev->dev, NULL);
+		if (IS_ERR(priv->rst))
+			return dev_err_probe(&pdev->dev, PTR_ERR(priv->rst),
+					     "Failed to get reset control\n");
+	}
+
 	platform_set_drvdata(pdev, priv);
 	spin_lock_init(&priv->lock);
 
@@ -1197,23 +1295,26 @@ static int sun4i_dma_probe(struct platform_device *pdev)
 
 	priv->slave.dev = &pdev->dev;
 
-	priv->pchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_CHANNELS,
+	priv->pchans = devm_kcalloc(&pdev->dev, priv->cfg->dma_nr_max_channels,
 				    sizeof(struct sun4i_dma_pchan), GFP_KERNEL);
 	priv->vchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_VCHANS,
 				    sizeof(struct sun4i_dma_vchan), GFP_KERNEL);
-	if (!priv->vchans || !priv->pchans)
+	priv->pchans_used = devm_kcalloc(&pdev->dev,
+					 BITS_TO_LONGS(priv->cfg->dma_nr_max_channels),
+					 sizeof(unsigned long), GFP_KERNEL);
+	if (!priv->vchans || !priv->pchans || !priv->pchans_used)
 		return -ENOMEM;
 
 	/*
-	 * [0..SUN4I_NDMA_NR_MAX_CHANNELS) are normal pchans, and
-	 * [SUN4I_NDMA_NR_MAX_CHANNELS..SUN4I_DMA_NR_MAX_CHANNELS) are
+	 * [0..priv->cfg->ndma_nr_max_channels) are normal pchans, and
+	 * [priv->cfg->ndma_nr_max_channels..priv->cfg->dma_nr_max_channels) are
 	 * dedicated ones
 	 */
-	for (i = 0; i < SUN4I_NDMA_NR_MAX_CHANNELS; i++)
+	for (i = 0; i < priv->cfg->ndma_nr_max_channels; i++)
 		priv->pchans[i].base = priv->base +
 			SUN4I_NDMA_CHANNEL_REG_BASE(i);
 
-	for (j = 0; i < SUN4I_DMA_NR_MAX_CHANNELS; i++, j++) {
+	for (j = 0; i < priv->cfg->dma_nr_max_channels; i++, j++) {
 		priv->pchans[i].base = priv->base +
 			SUN4I_DDMA_CHANNEL_REG_BASE(j);
 		priv->pchans[i].is_dedicated = 1;
@@ -1284,8 +1385,51 @@ static void sun4i_dma_remove(struct platform_device *pdev)
 	clk_disable_unprepare(priv->clk);
 }
 
+static struct sun4i_dma_config sun4i_a10_dma_cfg = {
+	.ndma_nr_max_channels	= SUN4I_NDMA_NR_MAX_CHANNELS,
+	.ndma_nr_max_vchans	= SUN4I_NDMA_NR_MAX_VCHANS,
+
+	.ddma_nr_max_channels	= SUN4I_DDMA_NR_MAX_CHANNELS,
+	.ddma_nr_max_vchans	= SUN4I_DDMA_NR_MAX_VCHANS,
+
+	.dma_nr_max_channels	= SUN4I_DMA_NR_MAX_CHANNELS,
+
+	.set_dst_data_width	= set_dst_data_width_a10,
+	.set_src_data_width	= set_src_data_width_a10,
+	.convert_burst		= convert_burst_a10,
+
+	.ndma_drq_sdram		= SUN4I_NDMA_DRQ_TYPE_SDRAM,
+	.ddma_drq_sdram		= SUN4I_DDMA_DRQ_TYPE_SDRAM,
+
+	.max_burst		= SUN4I_MAX_BURST,
+	.has_reset		= false,
+};
+
+static struct sun4i_dma_config suniv_f1c100s_dma_cfg = {
+	.ndma_nr_max_channels	= SUNIV_NDMA_NR_MAX_CHANNELS,
+	.ndma_nr_max_vchans	= SUNIV_NDMA_NR_MAX_VCHANS,
+
+	.ddma_nr_max_channels	= SUNIV_DDMA_NR_MAX_CHANNELS,
+	.ddma_nr_max_vchans	= SUNIV_DDMA_NR_MAX_VCHANS,
+
+	.dma_nr_max_channels	= SUNIV_NDMA_NR_MAX_CHANNELS +
+		SUNIV_DDMA_NR_MAX_CHANNELS,
+
+	.set_dst_data_width	= set_dst_data_width_f1c100s,
+	.set_src_data_width	= set_src_data_width_f1c100s,
+	.convert_burst		= convert_burst_f1c100s,
+
+	.ndma_drq_sdram		= SUNIV_NDMA_DRQ_TYPE_SDRAM,
+	.ddma_drq_sdram		= SUNIV_DDMA_DRQ_TYPE_SDRAM,
+
+	.max_burst		= SUNIV_MAX_BURST,
+	.has_reset		= true,
+};
+
 static const struct of_device_id sun4i_dma_match[] = {
-	{ .compatible = "allwinner,sun4i-a10-dma" },
+	{ .compatible = "allwinner,sun4i-a10-dma", .data = &sun4i_a10_dma_cfg },
+	{ .compatible = "allwinner,suniv-f1c100s-dma",
+		.data = &suniv_f1c100s_dma_cfg },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, sun4i_dma_match);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 2953008d42ef..6896da8ac7ef 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -43,6 +43,10 @@
 #define ADMA_CH_CONFIG_MAX_BUFS				8
 #define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	(reqs << 4)
 
+#define TEGRA186_ADMA_GLOBAL_PAGE_CHGRP			0x30
+#define TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ		0x70
+#define TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ		0x84
+
 #define ADMA_CH_FIFO_CTRL				0x2c
 #define ADMA_CH_TX_FIFO_SIZE_SHIFT			8
 #define ADMA_CH_RX_FIFO_SIZE_SHIFT			0
@@ -96,6 +100,7 @@ struct tegra_adma_chip_data {
 	unsigned int ch_fifo_size_mask;
 	unsigned int sreq_index_offset;
 	bool has_outstanding_reqs;
+	void (*set_global_pg_config)(struct tegra_adma *tdma);
 };
 
 /*
@@ -151,6 +156,7 @@ struct tegra_adma {
 	struct dma_device		dma_dev;
 	struct device			*dev;
 	void __iomem			*base_addr;
+	void __iomem			*ch_base_addr;
 	struct clk			*ahub_clk;
 	unsigned int			nr_channels;
 	unsigned long			*dma_chan_mask;
@@ -159,6 +165,7 @@ struct tegra_adma {
 
 	/* Used to store global command register state when suspending */
 	unsigned int			global_cmd;
+	unsigned int			ch_page_no;
 
 	const struct tegra_adma_chip_data *cdata;
 
@@ -176,6 +183,11 @@ static inline u32 tdma_read(struct tegra_adma *tdma, u32 reg)
 	return readl(tdma->base_addr + tdma->cdata->global_reg_offset + reg);
 }
 
+static inline void tdma_ch_global_write(struct tegra_adma *tdma, u32 reg, u32 val)
+{
+	writel(val, tdma->ch_base_addr + tdma->cdata->global_reg_offset + reg);
+}
+
 static inline void tdma_ch_write(struct tegra_adma_chan *tdc, u32 reg, u32 val)
 {
 	writel(val, tdc->chan_addr + reg);
@@ -217,13 +229,30 @@ static int tegra_adma_slave_config(struct dma_chan *dc,
 	return 0;
 }
 
+static void tegra186_adma_global_page_config(struct tegra_adma *tdma)
+{
+	/*
+	 * Clear the default page1 channel group configs and program
+	 * the global registers based on the actual page usage
+	 */
+	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_CHGRP, 0);
+	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ, 0);
+	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ, 0);
+	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_CHGRP + (tdma->ch_page_no * 0x4), 0xff);
+	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ + (tdma->ch_page_no * 0x4), 0x1ffffff);
+	tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ + (tdma->ch_page_no * 0x4), 0xffffff);
+}
+
 static int tegra_adma_init(struct tegra_adma *tdma)
 {
 	u32 status;
 	int ret;
 
-	/* Clear any interrupts */
-	tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1);
+	/* Clear any channels group global interrupts */
+	tdma_ch_global_write(tdma, tdma->cdata->global_int_clear, 0x1);
+
+	if (!tdma->base_addr)
+		return 0;
 
 	/* Assert soft reset */
 	tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1);
@@ -237,6 +266,9 @@ static int tegra_adma_init(struct tegra_adma *tdma)
 	if (ret)
 		return ret;
 
+	if (tdma->cdata->set_global_pg_config)
+		tdma->cdata->set_global_pg_config(tdma);
+
 	/* Enable global ADMA registers */
 	tdma_write(tdma, ADMA_GLOBAL_CMD, 1);
 
@@ -736,7 +768,9 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 	struct tegra_adma_chan *tdc;
 	int i;
 
-	tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD);
+	if (tdma->base_addr)
+		tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD);
+
 	if (!tdma->global_cmd)
 		goto clk_disable;
 
@@ -777,7 +811,11 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 		dev_err(dev, "ahub clk_enable failed: %d\n", ret);
 		return ret;
 	}
-	tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd);
+	if (tdma->base_addr) {
+		tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd);
+		if (tdma->cdata->set_global_pg_config)
+			tdma->cdata->set_global_pg_config(tdma);
+	}
 
 	if (!tdma->global_cmd)
 		return 0;
@@ -817,6 +855,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.ch_fifo_size_mask	= 0xf,
 	.sreq_index_offset	= 2,
 	.has_outstanding_reqs	= false,
+	.set_global_pg_config	= NULL,
 };
 
 static const struct tegra_adma_chip_data tegra186_chip_data = {
@@ -833,6 +872,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.ch_fifo_size_mask	= 0x1f,
 	.sreq_index_offset	= 4,
 	.has_outstanding_reqs	= true,
+	.set_global_pg_config	= tegra186_adma_global_page_config,
 };
 
 static const struct of_device_id tegra_adma_of_match[] = {
@@ -846,7 +886,8 @@ static int tegra_adma_probe(struct platform_device *pdev)
 {
 	const struct tegra_adma_chip_data *cdata;
 	struct tegra_adma *tdma;
-	int ret, i;
+	struct resource *res_page, *res_base;
+	int ret, i, page_no;
 
 	cdata = of_device_get_match_data(&pdev->dev);
 	if (!cdata) {
@@ -865,9 +906,35 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	tdma->nr_channels = cdata->nr_channels;
 	platform_set_drvdata(pdev, tdma);
 
-	tdma->base_addr = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(tdma->base_addr))
-		return PTR_ERR(tdma->base_addr);
+	res_page = platform_get_resource_byname(pdev, IORESOURCE_MEM, "page");
+	if (res_page) {
+		tdma->ch_base_addr = devm_ioremap_resource(&pdev->dev, res_page);
+		if (IS_ERR(tdma->ch_base_addr))
+			return PTR_ERR(tdma->ch_base_addr);
+
+		res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global");
+		if (res_base) {
+			page_no = (res_page->start - res_base->start) / cdata->ch_base_offset;
+			if (page_no <= 0)
+				return -EINVAL;
+			tdma->ch_page_no = page_no - 1;
+			tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base);
+			if (IS_ERR(tdma->base_addr))
+				return PTR_ERR(tdma->base_addr);
+		}
+	} else {
+		/* If no 'page' property found, then reg DT binding would be legacy */
+		res_base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (res_base) {
+			tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base);
+			if (IS_ERR(tdma->base_addr))
+				return PTR_ERR(tdma->base_addr);
+		} else {
+			return -ENODEV;
+		}
+
+		tdma->ch_base_addr = tdma->base_addr + cdata->ch_base_offset;
+	}
 
 	tdma->ahub_clk = devm_clk_get(&pdev->dev, "d_audio");
 	if (IS_ERR(tdma->ahub_clk)) {
@@ -900,8 +967,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		if (!test_bit(i, tdma->dma_chan_mask))
 			continue;
 
-		tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
-				 + (cdata->ch_reg_size * i);
+		tdc->chan_addr = tdma->ch_base_addr + (cdata->ch_reg_size * i);
 
 		tdc->irq = of_irq_get(pdev->dev.of_node, i);
 		if (tdc->irq <= 0) {
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 343e986e66e7..4ece125b2ae7 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -208,7 +208,6 @@ struct edma_desc {
 struct edma_cc;
 
 struct edma_tc {
-	struct device_node		*node;
 	u16				id;
 };
 
@@ -2460,19 +2459,19 @@ static int edma_probe(struct platform_device *pdev)
 			goto err_reg1;
 		}
 
-		for (i = 0;; i++) {
+		for (i = 0; i < ecc->num_tc; i++) {
 			ret = of_parse_phandle_with_fixed_args(node, "ti,tptcs",
 							       1, i, &tc_args);
-			if (ret || i == ecc->num_tc)
+			if (ret)
 				break;
 
-			ecc->tc_list[i].node = tc_args.np;
 			ecc->tc_list[i].id = i;
 			queue_priority_mapping[i][1] = tc_args.args[0];
 			if (queue_priority_mapping[i][1] > lowest_priority) {
 				lowest_priority = queue_priority_mapping[i][1];
 				info->default_queue = i;
 			}
+			of_node_put(tc_args.np);
 		}
 
 		/* See if we have optional dma-channel-mask array */
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b3f27b3f9209..7ed1956b4642 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4404,6 +4404,18 @@ static struct udma_match_data j721s2_bcdma_csi_data = {
 	.soc_data = &j721s2_bcdma_csi_soc_data,
 };
 
+static struct udma_match_data j722s_bcdma_csi_data = {
+	.type = DMA_TYPE_BCDMA,
+	.psil_base = 0x3100,
+	.enable_memcpy_support = false,
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		0, /* No H Channels */
+		0, /* No UH Channels */
+	},
+	.soc_data = &j721s2_bcdma_csi_soc_data,
+};
+
 static const struct of_device_id udma_of_match[] = {
 	{
 		.compatible = "ti,am654-navss-main-udmap",
@@ -4435,6 +4447,10 @@ static const struct of_device_id udma_of_match[] = {
 		.compatible = "ti,j721s2-dmss-bcdma-csi",
 		.data = &j721s2_bcdma_csi_data,
 	},
+	{
+		.compatible = "ti,j722s-dmss-bcdma-csi",
+		.data = &j722s_bcdma_csi_data,
+	},
 	{ /* Sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, udma_of_match);
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 93772abc3b49..0d88b1a670e1 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -390,15 +390,11 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
  */
 static int xdma_xfer_stop(struct xdma_chan *xchan)
 {
-	int ret;
 	struct xdma_device *xdev = xchan->xdev_hdl;
 
 	/* clear run stop bit to prevent any further auto-triggering */
-	ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
-			   CHAN_CTRL_RUN_STOP);
-	if (ret)
-		return ret;
-	return ret;
+	return regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C,
+			    CHAN_CTRL_RUN_STOP);
 }
 
 /**
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 1bdd57de87a6..108a7287f4cd 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -1404,16 +1404,18 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan)
 
 	dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg);
 
-	j = chan->desc_submitcount;
-	reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR);
-	if (chan->direction == DMA_MEM_TO_DEV) {
-		reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK;
-		reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT;
-	} else {
-		reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK;
-		reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT;
+	if (config->park) {
+		j = chan->desc_submitcount;
+		reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR);
+		if (chan->direction == DMA_MEM_TO_DEV) {
+			reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK;
+			reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT;
+		} else {
+			reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK;
+			reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT;
+		}
+		dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg);
 	}
-	dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg);
 
 	/* Start the hardware */
 	xilinx_dma_start(chan);
diff --git a/drivers/extcon/extcon-fsa9480.c b/drivers/extcon/extcon-fsa9480.c
index e458ce0c45ab..b11b43171063 100644
--- a/drivers/extcon/extcon-fsa9480.c
+++ b/drivers/extcon/extcon-fsa9480.c
@@ -350,7 +350,7 @@ static const struct dev_pm_ops fsa9480_pm_ops = {
 };
 
 static const struct i2c_device_id fsa9480_id[] = {
-	{ "fsa9480", 0 },
+	{ "fsa9480" },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, fsa9480_id);
diff --git a/drivers/extcon/extcon-ptn5150.c b/drivers/extcon/extcon-ptn5150.c
index 4616da7e5430..78ad86c4a3be 100644
--- a/drivers/extcon/extcon-ptn5150.c
+++ b/drivers/extcon/extcon-ptn5150.c
@@ -338,7 +338,7 @@ static const struct of_device_id ptn5150_dt_match[] = {
 MODULE_DEVICE_TABLE(of, ptn5150_dt_match);
 
 static const struct i2c_device_id ptn5150_i2c_id[] = {
-	{ "ptn5150", 0 },
+	{ "ptn5150" },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ptn5150_i2c_id);
diff --git a/drivers/extcon/extcon-rtk-type-c.c b/drivers/extcon/extcon-rtk-type-c.c
index bdc2b7b3a246..82b60b927e41 100644
--- a/drivers/extcon/extcon-rtk-type-c.c
+++ b/drivers/extcon/extcon-rtk-type-c.c
@@ -1369,6 +1369,8 @@ static int extcon_rtk_type_c_probe(struct platform_device *pdev)
 	}
 
 	type_c->type_c_cfg = devm_kzalloc(dev, sizeof(*type_c_cfg), GFP_KERNEL);
+	if (!type_c->type_c_cfg)
+		return -ENOMEM;
 
 	memcpy(type_c->type_c_cfg, type_c_cfg, sizeof(*type_c_cfg));
 
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index a99fe35f1f0d..ec3e21ad2025 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -988,7 +988,7 @@ int fw_device_set_broadcast_channel(struct device *dev, void *gen)
 	return 0;
 }
 
-static int compare_configuration_rom(struct device *dev, void *data)
+static int compare_configuration_rom(struct device *dev, const void *data)
 {
 	const struct fw_device *old = fw_device(dev);
 	const u32 *config_rom = data;
@@ -1039,7 +1039,7 @@ static void fw_device_init(struct work_struct *work)
 	//
 	// serialize config_rom access.
 	scoped_guard(rwsem_read, &fw_device_rwsem) {
-		found = device_find_child(card->device, (void *)device->config_rom,
+		found = device_find_child(card->device, device->config_rom,
 					  compare_configuration_rom);
 	}
 	if (found) {
diff --git a/drivers/firewire/device-attribute-test.c b/drivers/firewire/device-attribute-test.c
index 2f123c6b0a16..97478a96d1c9 100644
--- a/drivers/firewire/device-attribute-test.c
+++ b/drivers/firewire/device-attribute-test.c
@@ -99,6 +99,7 @@ static void device_attr_simple_avc(struct kunit *test)
 	struct device *unit0_dev = (struct device *)&unit0.device;
 	static const int unit0_expected_ids[] = {0x00ffffff, 0x00ffffff, 0x0000a02d, 0x00010001};
 	char *buf = kunit_kzalloc(test, PAGE_SIZE, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf);
 	int ids[4] = {0, 0, 0, 0};
 
 	// Ensure associations for node and unit devices.
@@ -180,6 +181,7 @@ static void device_attr_legacy_avc(struct kunit *test)
 	struct device *unit0_dev = (struct device *)&unit0.device;
 	static const int unit0_expected_ids[] = {0x00012345, 0x00fedcba, 0x00abcdef, 0x00543210};
 	char *buf = kunit_kzalloc(test, PAGE_SIZE, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buf);
 	int ids[4] = {0, 0, 0, 0};
 
 	// Ensure associations for node and unit devices.
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index c02aed11b590..edaedd156a6d 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3301,8 +3301,7 @@ static int ohci_set_iso_channels(struct fw_iso_context *base, u64 *channels)
 	}
 }
 
-#ifdef CONFIG_PM
-static void ohci_resume_iso_dma(struct fw_ohci *ohci)
+static void __maybe_unused ohci_resume_iso_dma(struct fw_ohci *ohci)
 {
 	int i;
 	struct iso_context *ctx;
@@ -3319,7 +3318,6 @@ static void ohci_resume_iso_dma(struct fw_ohci *ohci)
 			ohci_start_iso(&ctx->base, 0, ctx->sync, ctx->tags);
 	}
 }
-#endif
 
 static int queue_iso_transmit(struct iso_context *ctx,
 			      struct fw_iso_packet *packet,
@@ -3888,39 +3886,25 @@ static void pci_remove(struct pci_dev *dev)
 	dev_notice(&dev->dev, "removing fw-ohci device\n");
 }
 
-#ifdef CONFIG_PM
-static int pci_suspend(struct pci_dev *dev, pm_message_t state)
+static int __maybe_unused pci_suspend(struct device *dev)
 {
-	struct fw_ohci *ohci = pci_get_drvdata(dev);
-	int err;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct fw_ohci *ohci = pci_get_drvdata(pdev);
 
 	software_reset(ohci);
-	err = pci_save_state(dev);
-	if (err) {
-		ohci_err(ohci, "pci_save_state failed\n");
-		return err;
-	}
-	err = pci_set_power_state(dev, pci_choose_state(dev, state));
-	if (err)
-		ohci_err(ohci, "pci_set_power_state failed with %d\n", err);
-	pmac_ohci_off(dev);
+	pmac_ohci_off(pdev);
 
 	return 0;
 }
 
-static int pci_resume(struct pci_dev *dev)
+
+static int __maybe_unused pci_resume(struct device *dev)
 {
-	struct fw_ohci *ohci = pci_get_drvdata(dev);
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct fw_ohci *ohci = pci_get_drvdata(pdev);
 	int err;
 
-	pmac_ohci_on(dev);
-	pci_set_power_state(dev, PCI_D0);
-	pci_restore_state(dev);
-	err = pci_enable_device(dev);
-	if (err) {
-		ohci_err(ohci, "pci_enable_device failed\n");
-		return err;
-	}
+	pmac_ohci_on(pdev);
 
 	/* Some systems don't setup GUID register on resume from ram  */
 	if (!reg_read(ohci, OHCI1394_GUIDLo) &&
@@ -3937,7 +3921,6 @@ static int pci_resume(struct pci_dev *dev)
 
 	return 0;
 }
-#endif
 
 static const struct pci_device_id pci_table[] = {
 	{ PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_FIREWIRE_OHCI, ~0) },
@@ -3946,15 +3929,14 @@ static const struct pci_device_id pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, pci_table);
 
+static SIMPLE_DEV_PM_OPS(pci_pm_ops, pci_suspend, pci_resume);
+
 static struct pci_driver fw_ohci_pci_driver = {
 	.name		= ohci_driver_name,
 	.id_table	= pci_table,
 	.probe		= pci_probe,
 	.remove		= pci_remove,
-#ifdef CONFIG_PM
-	.resume		= pci_resume,
-	.suspend	= pci_suspend,
-#endif
+	.driver.pm	= &pci_pm_ops,
 };
 
 static int __init fw_ohci_init(void)
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 827dee0f57dd..1a19828114cf 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1490,7 +1490,7 @@ static int sbp2_scsi_queuecommand(struct Scsi_Host *shost,
 	return retval;
 }
 
-static int sbp2_scsi_slave_alloc(struct scsi_device *sdev)
+static int sbp2_scsi_sdev_init(struct scsi_device *sdev)
 {
 	struct sbp2_logical_unit *lu = sdev->hostdata;
 
@@ -1506,8 +1506,8 @@ static int sbp2_scsi_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int sbp2_scsi_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int sbp2_scsi_sdev_configure(struct scsi_device *sdev,
+				    struct queue_limits *lim)
 {
 	struct sbp2_logical_unit *lu = sdev->hostdata;
 
@@ -1590,8 +1590,8 @@ static const struct scsi_host_template scsi_driver_template = {
 	.name			= "SBP-2 IEEE-1394",
 	.proc_name		= "sbp2",
 	.queuecommand		= sbp2_scsi_queuecommand,
-	.slave_alloc		= sbp2_scsi_slave_alloc,
-	.device_configure	= sbp2_scsi_device_configure,
+	.sdev_init		= sbp2_scsi_sdev_init,
+	.sdev_configure		= sbp2_scsi_sdev_configure,
 	.eh_abort_handler	= sbp2_scsi_abort,
 	.this_id		= -1,
 	.sg_tablesize		= SG_ALL,
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 71d8b26c4103..9f35f69e0f9e 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -106,7 +106,7 @@ config ISCSI_IBFT
 	select ISCSI_BOOT_SYSFS
 	select ISCSI_IBFT_FIND if X86
 	depends on ACPI && SCSI && SCSI_LOWLEVEL
-	default	n
+	default n
 	help
 	  This option enables support for detection and exposing of iSCSI
 	  Boot Firmware Table (iBFT) via sysfs to userspace. If you wish to
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index 157172a5f2b5..a3386bf36de5 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -238,10 +238,10 @@ static int scmi_dev_match(struct device *dev, const struct device_driver *drv)
 	return 0;
 }
 
-static int scmi_match_by_id_table(struct device *dev, void *data)
+static int scmi_match_by_id_table(struct device *dev, const void *data)
 {
 	struct scmi_device *sdev = to_scmi_dev(dev);
-	struct scmi_device_id *id_table = data;
+	const struct scmi_device_id *id_table = data;
 
 	return sdev->protocol_id == id_table->protocol_id &&
 		(id_table->name && !strcmp(sdev->name, id_table->name));
diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c
index 9e89a6a763da..7cc0d616b8de 100644
--- a/drivers/firmware/arm_scmi/raw_mode.c
+++ b/drivers/firmware/arm_scmi/raw_mode.c
@@ -886,10 +886,8 @@ static __poll_t scmi_dbg_raw_mode_message_poll(struct file *filp,
 
 static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp)
 {
-	u8 id;
 	struct scmi_raw_mode_info *raw;
 	struct scmi_dbg_raw_data *rd;
-	const char *id_str = filp->f_path.dentry->d_parent->d_name.name;
 
 	if (!inode->i_private)
 		return -ENODEV;
@@ -915,8 +913,8 @@ static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp)
 	}
 
 	/* Grab channel ID from debugfs entry naming if any */
-	if (!kstrtou8(id_str, 16, &id))
-		rd->chan_id = id;
+	/* not set - reassing 0 we already had after kzalloc() */
+	rd->chan_id = debugfs_get_aux_num(filp);
 
 	rd->raw = raw;
 	filp->private_data = rd;
@@ -1225,10 +1223,12 @@ void *scmi_raw_mode_init(const struct scmi_handle *handle,
 			snprintf(cdir, 8, "0x%02X", channels[i]);
 			chd = debugfs_create_dir(cdir, top_chans);
 
-			debugfs_create_file("message", 0600, chd, raw,
+			debugfs_create_file_aux_num("message", 0600, chd,
+					    raw, channels[i],
 					    &scmi_dbg_raw_mode_message_fops);
 
-			debugfs_create_file("message_async", 0600, chd, raw,
+			debugfs_create_file_aux_num("message_async", 0600, chd,
+					    raw, channels[i],
 					    &scmi_dbg_raw_mode_message_async_fops);
 		}
 	}
diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig
index ee09269c63b5..0a883091259a 100644
--- a/drivers/firmware/cirrus/Kconfig
+++ b/drivers/firmware/cirrus/Kconfig
@@ -6,15 +6,13 @@ config FW_CS_DSP
 
 config FW_CS_DSP_KUNIT_TEST_UTILS
 	tristate
-	depends on KUNIT
-	select REGMAP
+	depends on KUNIT && REGMAP
 	select FW_CS_DSP
 
 config FW_CS_DSP_KUNIT_TEST
 	tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS
-	depends on KUNIT
+	depends on KUNIT && REGMAP
 	default KUNIT_ALL_TESTS
-	select REGMAP
 	select FW_CS_DSP
 	select FW_CS_DSP_KUNIT_TEST_UTILS
 	help
diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c
index 937be269fee8..13ea141c0def 100644
--- a/drivers/firmware/efi/dev-path-parser.c
+++ b/drivers/firmware/efi/dev-path-parser.c
@@ -47,9 +47,9 @@ static long __init parse_acpi_path(const struct efi_dev_path *node,
 	return 0;
 }
 
-static int __init match_pci_dev(struct device *dev, void *data)
+static int __init match_pci_dev(struct device *dev, const void *data)
 {
-	unsigned int devfn = *(unsigned int *)data;
+	unsigned int devfn = *(const unsigned int *)data;
 
 	return dev_is_pci(dev) && to_pci_dev(dev)->devfn == devfn;
 }
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 6e9788324fea..371f24569b3b 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -310,7 +310,10 @@ static ssize_t ibft_attr_show_nic(void *data, int type, char *buf)
 		str += sprintf_ipaddr(str, nic->ip_addr);
 		break;
 	case ISCSI_BOOT_ETH_SUBNET_MASK:
-		val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1));
+		if (nic->subnet_mask_prefix > 32)
+			val = cpu_to_be32(~0);
+		else
+			val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1));
 		str += sprintf(str, "%pI4", &val);
 		break;
 	case ISCSI_BOOT_ETH_PREFIX_LEN:
diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c
index c5c78b869561..3c52cb73237a 100644
--- a/drivers/firmware/stratix10-svc.c
+++ b/drivers/firmware/stratix10-svc.c
@@ -967,18 +967,15 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg)
 	/* first client will create kernel thread */
 	if (!chan->ctrl->task) {
 		chan->ctrl->task =
-			kthread_create_on_node(svc_normal_to_secure_thread,
-					      (void *)chan->ctrl,
-					      cpu_to_node(cpu),
-					      "svc_smc_hvc_thread");
+			kthread_run_on_cpu(svc_normal_to_secure_thread,
+					   (void *)chan->ctrl,
+					   cpu, "svc_smc_hvc_thread");
 			if (IS_ERR(chan->ctrl->task)) {
 				dev_err(chan->ctrl->dev,
 					"failed to create svc_smc_hvc_thread\n");
 				kfree(p_data);
 				return -EINVAL;
 			}
-		kthread_bind(chan->ctrl->task, cpu);
-		wake_up_process(chan->ctrl->task);
 	}
 
 	pr_debug("%s: sent P-va=%p, P-com=%x, P-size=%u\n", __func__,
diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c
index 02b60fde0430..5aa7b8884374 100644
--- a/drivers/fpga/dfl-afu-dma-region.c
+++ b/drivers/fpga/dfl-afu-dma-region.c
@@ -16,26 +16,26 @@
 
 #include "dfl-afu.h"
 
-void afu_dma_region_init(struct dfl_feature_platform_data *pdata)
+void afu_dma_region_init(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata);
 
 	afu->dma_regions = RB_ROOT;
 }
 
 /**
  * afu_dma_pin_pages - pin pages of given dma memory region
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @region: dma memory region to be pinned
  *
  * Pin all the pages of given dfl_afu_dma_region.
  * Return 0 for success or negative error code.
  */
-static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
+static int afu_dma_pin_pages(struct dfl_feature_dev_data *fdata,
 			     struct dfl_afu_dma_region *region)
 {
 	int npages = region->length >> PAGE_SHIFT;
-	struct device *dev = &pdata->dev->dev;
+	struct device *dev = &fdata->dev->dev;
 	int ret, pinned;
 
 	ret = account_locked_vm(current->mm, npages, true);
@@ -73,17 +73,17 @@ unlock_vm:
 
 /**
  * afu_dma_unpin_pages - unpin pages of given dma memory region
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @region: dma memory region to be unpinned
  *
  * Unpin all the pages of given dfl_afu_dma_region.
  * Return 0 for success or negative error code.
  */
-static void afu_dma_unpin_pages(struct dfl_feature_platform_data *pdata,
+static void afu_dma_unpin_pages(struct dfl_feature_dev_data *fdata,
 				struct dfl_afu_dma_region *region)
 {
 	long npages = region->length >> PAGE_SHIFT;
-	struct device *dev = &pdata->dev->dev;
+	struct device *dev = &fdata->dev->dev;
 
 	unpin_user_pages(region->pages, npages);
 	kfree(region->pages);
@@ -133,20 +133,20 @@ static bool dma_region_check_iova(struct dfl_afu_dma_region *region,
 
 /**
  * afu_dma_region_add - add given dma region to rbtree
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @region: dma region to be added
  *
  * Return 0 for success, -EEXIST if dma region has already been added.
  *
- * Needs to be called with pdata->lock heold.
+ * Needs to be called with fdata->lock held.
  */
-static int afu_dma_region_add(struct dfl_feature_platform_data *pdata,
+static int afu_dma_region_add(struct dfl_feature_dev_data *fdata,
 			      struct dfl_afu_dma_region *region)
 {
-	struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata);
 	struct rb_node **new, *parent = NULL;
 
-	dev_dbg(&pdata->dev->dev, "add region (iova = %llx)\n",
+	dev_dbg(&fdata->dev->dev, "add region (iova = %llx)\n",
 		(unsigned long long)region->iova);
 
 	new = &afu->dma_regions.rb_node;
@@ -177,50 +177,50 @@ static int afu_dma_region_add(struct dfl_feature_platform_data *pdata,
 
 /**
  * afu_dma_region_remove - remove given dma region from rbtree
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @region: dma region to be removed
  *
- * Needs to be called with pdata->lock heold.
+ * Needs to be called with fdata->lock held.
  */
-static void afu_dma_region_remove(struct dfl_feature_platform_data *pdata,
+static void afu_dma_region_remove(struct dfl_feature_dev_data *fdata,
 				  struct dfl_afu_dma_region *region)
 {
 	struct dfl_afu *afu;
 
-	dev_dbg(&pdata->dev->dev, "del region (iova = %llx)\n",
+	dev_dbg(&fdata->dev->dev, "del region (iova = %llx)\n",
 		(unsigned long long)region->iova);
 
-	afu = dfl_fpga_pdata_get_private(pdata);
+	afu = dfl_fpga_fdata_get_private(fdata);
 	rb_erase(&region->node, &afu->dma_regions);
 }
 
 /**
  * afu_dma_region_destroy - destroy all regions in rbtree
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  *
- * Needs to be called with pdata->lock heold.
+ * Needs to be called with fdata->lock held.
  */
-void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata)
+void afu_dma_region_destroy(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata);
 	struct rb_node *node = rb_first(&afu->dma_regions);
 	struct dfl_afu_dma_region *region;
 
 	while (node) {
 		region = container_of(node, struct dfl_afu_dma_region, node);
 
-		dev_dbg(&pdata->dev->dev, "del region (iova = %llx)\n",
+		dev_dbg(&fdata->dev->dev, "del region (iova = %llx)\n",
 			(unsigned long long)region->iova);
 
 		rb_erase(node, &afu->dma_regions);
 
 		if (region->iova)
-			dma_unmap_page(dfl_fpga_pdata_to_parent(pdata),
+			dma_unmap_page(dfl_fpga_fdata_to_parent(fdata),
 				       region->iova, region->length,
 				       DMA_BIDIRECTIONAL);
 
 		if (region->pages)
-			afu_dma_unpin_pages(pdata, region);
+			afu_dma_unpin_pages(fdata, region);
 
 		node = rb_next(node);
 		kfree(region);
@@ -229,7 +229,7 @@ void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata)
 
 /**
  * afu_dma_region_find - find the dma region from rbtree based on iova and size
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @iova: address of the dma memory area
  * @size: size of the dma memory area
  *
@@ -239,14 +239,14 @@ void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata)
  *   [@iova, @iova+size)
  * If nothing is matched returns NULL.
  *
- * Needs to be called with pdata->lock held.
+ * Needs to be called with fdata->lock held.
  */
 struct dfl_afu_dma_region *
-afu_dma_region_find(struct dfl_feature_platform_data *pdata, u64 iova, u64 size)
+afu_dma_region_find(struct dfl_feature_dev_data *fdata, u64 iova, u64 size)
 {
-	struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata);
 	struct rb_node *node = afu->dma_regions.rb_node;
-	struct device *dev = &pdata->dev->dev;
+	struct device *dev = &fdata->dev->dev;
 
 	while (node) {
 		struct dfl_afu_dma_region *region;
@@ -276,20 +276,20 @@ afu_dma_region_find(struct dfl_feature_platform_data *pdata, u64 iova, u64 size)
 
 /**
  * afu_dma_region_find_iova - find the dma region from rbtree by iova
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @iova: address of the dma region
  *
- * Needs to be called with pdata->lock held.
+ * Needs to be called with fdata->lock held.
  */
 static struct dfl_afu_dma_region *
-afu_dma_region_find_iova(struct dfl_feature_platform_data *pdata, u64 iova)
+afu_dma_region_find_iova(struct dfl_feature_dev_data *fdata, u64 iova)
 {
-	return afu_dma_region_find(pdata, iova, 0);
+	return afu_dma_region_find(fdata, iova, 0);
 }
 
 /**
  * afu_dma_map_region - map memory region for dma
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @user_addr: address of the memory region
  * @length: size of the memory region
  * @iova: pointer of iova address
@@ -298,9 +298,10 @@ afu_dma_region_find_iova(struct dfl_feature_platform_data *pdata, u64 iova)
  * of the memory region via @iova.
  * Return 0 for success, otherwise error code.
  */
-int afu_dma_map_region(struct dfl_feature_platform_data *pdata,
+int afu_dma_map_region(struct dfl_feature_dev_data *fdata,
 		       u64 user_addr, u64 length, u64 *iova)
 {
+	struct device *dev = &fdata->dev->dev;
 	struct dfl_afu_dma_region *region;
 	int ret;
 
@@ -323,47 +324,47 @@ int afu_dma_map_region(struct dfl_feature_platform_data *pdata,
 	region->length = length;
 
 	/* Pin the user memory region */
-	ret = afu_dma_pin_pages(pdata, region);
+	ret = afu_dma_pin_pages(fdata, region);
 	if (ret) {
-		dev_err(&pdata->dev->dev, "failed to pin memory region\n");
+		dev_err(dev, "failed to pin memory region\n");
 		goto free_region;
 	}
 
 	/* Only accept continuous pages, return error else */
 	if (!afu_dma_check_continuous_pages(region)) {
-		dev_err(&pdata->dev->dev, "pages are not continuous\n");
+		dev_err(dev, "pages are not continuous\n");
 		ret = -EINVAL;
 		goto unpin_pages;
 	}
 
 	/* As pages are continuous then start to do DMA mapping */
-	region->iova = dma_map_page(dfl_fpga_pdata_to_parent(pdata),
+	region->iova = dma_map_page(dfl_fpga_fdata_to_parent(fdata),
 				    region->pages[0], 0,
 				    region->length,
 				    DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dfl_fpga_pdata_to_parent(pdata), region->iova)) {
-		dev_err(&pdata->dev->dev, "failed to map for dma\n");
+	if (dma_mapping_error(dfl_fpga_fdata_to_parent(fdata), region->iova)) {
+		dev_err(dev, "failed to map for dma\n");
 		ret = -EFAULT;
 		goto unpin_pages;
 	}
 
 	*iova = region->iova;
 
-	mutex_lock(&pdata->lock);
-	ret = afu_dma_region_add(pdata, region);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	ret = afu_dma_region_add(fdata, region);
+	mutex_unlock(&fdata->lock);
 	if (ret) {
-		dev_err(&pdata->dev->dev, "failed to add dma region\n");
+		dev_err(dev, "failed to add dma region\n");
 		goto unmap_dma;
 	}
 
 	return 0;
 
 unmap_dma:
-	dma_unmap_page(dfl_fpga_pdata_to_parent(pdata),
+	dma_unmap_page(dfl_fpga_fdata_to_parent(fdata),
 		       region->iova, region->length, DMA_BIDIRECTIONAL);
 unpin_pages:
-	afu_dma_unpin_pages(pdata, region);
+	afu_dma_unpin_pages(fdata, region);
 free_region:
 	kfree(region);
 	return ret;
@@ -371,34 +372,34 @@ free_region:
 
 /**
  * afu_dma_unmap_region - unmap dma memory region
- * @pdata: feature device platform data
+ * @fdata: feature dev data
  * @iova: dma address of the region
  *
  * Unmap dma memory region based on @iova.
  * Return 0 for success, otherwise error code.
  */
-int afu_dma_unmap_region(struct dfl_feature_platform_data *pdata, u64 iova)
+int afu_dma_unmap_region(struct dfl_feature_dev_data *fdata, u64 iova)
 {
 	struct dfl_afu_dma_region *region;
 
-	mutex_lock(&pdata->lock);
-	region = afu_dma_region_find_iova(pdata, iova);
+	mutex_lock(&fdata->lock);
+	region = afu_dma_region_find_iova(fdata, iova);
 	if (!region) {
-		mutex_unlock(&pdata->lock);
+		mutex_unlock(&fdata->lock);
 		return -EINVAL;
 	}
 
 	if (region->in_use) {
-		mutex_unlock(&pdata->lock);
+		mutex_unlock(&fdata->lock);
 		return -EBUSY;
 	}
 
-	afu_dma_region_remove(pdata, region);
-	mutex_unlock(&pdata->lock);
+	afu_dma_region_remove(fdata, region);
+	mutex_unlock(&fdata->lock);
 
-	dma_unmap_page(dfl_fpga_pdata_to_parent(pdata),
+	dma_unmap_page(dfl_fpga_fdata_to_parent(fdata),
 		       region->iova, region->length, DMA_BIDIRECTIONAL);
-	afu_dma_unpin_pages(pdata, region);
+	afu_dma_unpin_pages(fdata, region);
 	kfree(region);
 
 	return 0;
diff --git a/drivers/fpga/dfl-afu-error.c b/drivers/fpga/dfl-afu-error.c
index ab7be6217368..0f392d1f6d45 100644
--- a/drivers/fpga/dfl-afu-error.c
+++ b/drivers/fpga/dfl-afu-error.c
@@ -28,37 +28,36 @@
 #define ERROR_MASK		GENMASK_ULL(63, 0)
 
 /* mask or unmask port errors by the error mask register. */
-static void __afu_port_err_mask(struct device *dev, bool mask)
+static void __afu_port_err_mask(struct dfl_feature_dev_data *fdata, bool mask)
 {
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
 
 	writeq(mask ? ERROR_MASK : 0, base + PORT_ERROR_MASK);
 }
 
 static void afu_port_err_mask(struct device *dev, bool mask)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 
-	mutex_lock(&pdata->lock);
-	__afu_port_err_mask(dev, mask);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	__afu_port_err_mask(fdata, mask);
+	mutex_unlock(&fdata->lock);
 }
 
 /* clear port errors. */
 static int afu_port_err_clear(struct device *dev, u64 err)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
-	struct platform_device *pdev = to_platform_device(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base_err, *base_hdr;
 	int enable_ret = 0, ret = -EBUSY;
 	u64 v;
 
-	base_err = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR);
-	base_hdr = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base_err = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
+	base_hdr = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 
 	/*
 	 * clear Port Errors
@@ -80,12 +79,12 @@ static int afu_port_err_clear(struct device *dev, u64 err)
 	}
 
 	/* Halt Port by keeping Port in reset */
-	ret = __afu_port_disable(pdev);
+	ret = __afu_port_disable(fdata);
 	if (ret)
 		goto done;
 
 	/* Mask all errors */
-	__afu_port_err_mask(dev, true);
+	__afu_port_err_mask(fdata, true);
 
 	/* Clear errors if err input matches with current port errors.*/
 	v = readq(base_err + PORT_ERROR);
@@ -102,28 +101,28 @@ static int afu_port_err_clear(struct device *dev, u64 err)
 	}
 
 	/* Clear mask */
-	__afu_port_err_mask(dev, false);
+	__afu_port_err_mask(fdata, false);
 
 	/* Enable the Port by clearing the reset */
-	enable_ret = __afu_port_enable(pdev);
+	enable_ret = __afu_port_enable(fdata);
 
 done:
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return enable_ret ? enable_ret : ret;
 }
 
 static ssize_t errors_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 error;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	error = readq(base + PORT_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)error);
 }
@@ -146,15 +145,15 @@ static DEVICE_ATTR_RW(errors);
 static ssize_t first_error_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 error;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	error = readq(base + PORT_FIRST_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)error);
 }
@@ -164,16 +163,16 @@ static ssize_t first_malformed_req_show(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 req0, req1;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_ERROR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	req0 = readq(base + PORT_MALFORMED_REQ0);
 	req1 = readq(base + PORT_MALFORMED_REQ1);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%016llx%016llx\n",
 		       (unsigned long long)req1, (unsigned long long)req0);
@@ -191,12 +190,14 @@ static umode_t port_err_attrs_visible(struct kobject *kobj,
 				      struct attribute *attr, int n)
 {
 	struct device *dev = kobj_to_dev(kobj);
+	struct dfl_feature_dev_data *fdata;
 
+	fdata = to_dfl_feature_dev_data(dev);
 	/*
 	 * sysfs entries are visible only if related private feature is
 	 * enumerated.
 	 */
-	if (!dfl_get_feature_by_id(dev, PORT_FEATURE_ID_ERROR))
+	if (!dfl_get_feature_by_id(fdata, PORT_FEATURE_ID_ERROR))
 		return 0;
 
 	return attr->mode;
diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c
index 2fd4f07ed081..3bf8e7338dbe 100644
--- a/drivers/fpga/dfl-afu-main.c
+++ b/drivers/fpga/dfl-afu-main.c
@@ -26,7 +26,7 @@
 
 /**
  * __afu_port_enable - enable a port by clear reset
- * @pdev: port platform device.
+ * @fdata: port feature dev data.
  *
  * Enable Port by clear the port soft reset bit, which is set by default.
  * The AFU is unable to respond to any MMIO access while in reset.
@@ -35,18 +35,17 @@
  *
  * The caller needs to hold lock for protection.
  */
-int __afu_port_enable(struct platform_device *pdev)
+int __afu_port_enable(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	void __iomem *base;
 	u64 v;
 
-	WARN_ON(!pdata->disable_count);
+	WARN_ON(!fdata->disable_count);
 
-	if (--pdata->disable_count != 0)
+	if (--fdata->disable_count != 0)
 		return 0;
 
-	base = dfl_get_feature_ioaddr_by_id(&pdev->dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
 	/* Clear port soft reset */
 	v = readq(base + PORT_HDR_CTRL);
@@ -60,7 +59,8 @@ int __afu_port_enable(struct platform_device *pdev)
 	if (readq_poll_timeout(base + PORT_HDR_CTRL, v,
 			       !(v & PORT_CTRL_SFTRST_ACK),
 			       RST_POLL_INVL, RST_POLL_TIMEOUT)) {
-		dev_err(&pdev->dev, "timeout, failure to enable device\n");
+		dev_err(fdata->dfl_cdev->parent,
+			"timeout, failure to enable device\n");
 		return -ETIMEDOUT;
 	}
 
@@ -69,22 +69,21 @@ int __afu_port_enable(struct platform_device *pdev)
 
 /**
  * __afu_port_disable - disable a port by hold reset
- * @pdev: port platform device.
+ * @fdata: port feature dev data.
  *
  * Disable Port by setting the port soft reset bit, it puts the port into reset.
  *
  * The caller needs to hold lock for protection.
  */
-int __afu_port_disable(struct platform_device *pdev)
+int __afu_port_disable(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	void __iomem *base;
 	u64 v;
 
-	if (pdata->disable_count++ != 0)
+	if (fdata->disable_count++ != 0)
 		return 0;
 
-	base = dfl_get_feature_ioaddr_by_id(&pdev->dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
 	/* Set port soft reset */
 	v = readq(base + PORT_HDR_CTRL);
@@ -99,7 +98,8 @@ int __afu_port_disable(struct platform_device *pdev)
 	if (readq_poll_timeout(base + PORT_HDR_CTRL, v,
 			       v & PORT_CTRL_SFTRST_ACK,
 			       RST_POLL_INVL, RST_POLL_TIMEOUT)) {
-		dev_err(&pdev->dev, "timeout, failure to disable device\n");
+		dev_err(fdata->dfl_cdev->parent,
+			"timeout, failure to disable device\n");
 		return -ETIMEDOUT;
 	}
 
@@ -118,34 +118,34 @@ int __afu_port_disable(struct platform_device *pdev)
  * (disabled). Any attempts on MMIO access to AFU while in reset, will
  * result errors reported via port error reporting sub feature (if present).
  */
-static int __port_reset(struct platform_device *pdev)
+static int __port_reset(struct dfl_feature_dev_data *fdata)
 {
 	int ret;
 
-	ret = __afu_port_disable(pdev);
+	ret = __afu_port_disable(fdata);
 	if (ret)
 		return ret;
 
-	return __afu_port_enable(pdev);
+	return __afu_port_enable(fdata);
 }
 
 static int port_reset(struct platform_device *pdev)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	int ret;
 
-	mutex_lock(&pdata->lock);
-	ret = __port_reset(pdev);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	ret = __port_reset(fdata);
+	mutex_unlock(&fdata->lock);
 
 	return ret;
 }
 
-static int port_get_id(struct platform_device *pdev)
+static int port_get_id(struct dfl_feature_dev_data *fdata)
 {
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(&pdev->dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
 	return FIELD_GET(PORT_CAP_PORT_NUM, readq(base + PORT_HDR_CAP));
 }
@@ -153,7 +153,8 @@ static int port_get_id(struct platform_device *pdev)
 static ssize_t
 id_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	int id = port_get_id(to_platform_device(dev));
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
+	int id = port_get_id(fdata);
 
 	return scnprintf(buf, PAGE_SIZE, "%d\n", id);
 }
@@ -162,15 +163,15 @@ static DEVICE_ATTR_RO(id);
 static ssize_t
 ltr_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + PORT_HDR_CTRL);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "%x\n", (u8)FIELD_GET(PORT_CTRL_LATENCY, v));
 }
@@ -179,7 +180,7 @@ static ssize_t
 ltr_store(struct device *dev, struct device_attribute *attr,
 	  const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	bool ltr;
 	u64 v;
@@ -187,14 +188,14 @@ ltr_store(struct device *dev, struct device_attribute *attr,
 	if (kstrtobool(buf, &ltr))
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + PORT_HDR_CTRL);
 	v &= ~PORT_CTRL_LATENCY;
 	v |= FIELD_PREP(PORT_CTRL_LATENCY, ltr ? 1 : 0);
 	writeq(v, base + PORT_HDR_CTRL);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return count;
 }
@@ -203,15 +204,15 @@ static DEVICE_ATTR_RW(ltr);
 static ssize_t
 ap1_event_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + PORT_HDR_STS);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "%x\n", (u8)FIELD_GET(PORT_STS_AP1_EVT, v));
 }
@@ -220,18 +221,18 @@ static ssize_t
 ap1_event_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	bool clear;
 
 	if (kstrtobool(buf, &clear) || !clear)
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(PORT_STS_AP1_EVT, base + PORT_HDR_STS);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return count;
 }
@@ -241,15 +242,15 @@ static ssize_t
 ap2_event_show(struct device *dev, struct device_attribute *attr,
 	       char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + PORT_HDR_STS);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "%x\n", (u8)FIELD_GET(PORT_STS_AP2_EVT, v));
 }
@@ -258,18 +259,18 @@ static ssize_t
 ap2_event_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	bool clear;
 
 	if (kstrtobool(buf, &clear) || !clear)
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(PORT_STS_AP2_EVT, base + PORT_HDR_STS);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return count;
 }
@@ -278,15 +279,15 @@ static DEVICE_ATTR_RW(ap2_event);
 static ssize_t
 power_state_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + PORT_HDR_STS);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%x\n", (u8)FIELD_GET(PORT_STS_PWR_STATE, v));
 }
@@ -296,18 +297,18 @@ static ssize_t
 userclk_freqcmd_store(struct device *dev, struct device_attribute *attr,
 		      const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	u64 userclk_freq_cmd;
 	void __iomem *base;
 
 	if (kstrtou64(buf, 0, &userclk_freq_cmd))
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(userclk_freq_cmd, base + PORT_HDR_USRCLK_CMD0);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return count;
 }
@@ -317,18 +318,18 @@ static ssize_t
 userclk_freqcntrcmd_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	u64 userclk_freqcntr_cmd;
 	void __iomem *base;
 
 	if (kstrtou64(buf, 0, &userclk_freqcntr_cmd))
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(userclk_freqcntr_cmd, base + PORT_HDR_USRCLK_CMD1);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return count;
 }
@@ -338,15 +339,15 @@ static ssize_t
 userclk_freqsts_show(struct device *dev, struct device_attribute *attr,
 		     char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	u64 userclk_freqsts;
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	userclk_freqsts = readq(base + PORT_HDR_USRCLK_STS0);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)userclk_freqsts);
 }
@@ -356,15 +357,15 @@ static ssize_t
 userclk_freqcntrsts_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	u64 userclk_freqcntrsts;
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	userclk_freqcntrsts = readq(base + PORT_HDR_USRCLK_STS1);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n",
 		       (unsigned long long)userclk_freqcntrsts);
@@ -388,10 +389,12 @@ static umode_t port_hdr_attrs_visible(struct kobject *kobj,
 				      struct attribute *attr, int n)
 {
 	struct device *dev = kobj_to_dev(kobj);
+	struct dfl_feature_dev_data *fdata;
 	umode_t mode = attr->mode;
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_HEADER);
+	fdata = to_dfl_feature_dev_data(dev);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
 
 	if (dfl_feature_revision(base) > 0) {
 		/*
@@ -456,21 +459,21 @@ static const struct dfl_feature_ops port_hdr_ops = {
 static ssize_t
 afu_id_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 guidl, guidh;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, PORT_FEATURE_ID_AFU);
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_AFU);
 
-	mutex_lock(&pdata->lock);
-	if (pdata->disable_count) {
-		mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	if (fdata->disable_count) {
+		mutex_unlock(&fdata->lock);
 		return -EBUSY;
 	}
 
 	guidl = readq(base + GUID_L);
 	guidh = readq(base + GUID_H);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return scnprintf(buf, PAGE_SIZE, "%016llx%016llx\n", guidh, guidl);
 }
@@ -485,12 +488,14 @@ static umode_t port_afu_attrs_visible(struct kobject *kobj,
 				      struct attribute *attr, int n)
 {
 	struct device *dev = kobj_to_dev(kobj);
+	struct dfl_feature_dev_data *fdata;
 
+	fdata = to_dfl_feature_dev_data(dev);
 	/*
 	 * sysfs entries are visible only if related private feature is
 	 * enumerated.
 	 */
-	if (!dfl_get_feature_by_id(dev, PORT_FEATURE_ID_AFU))
+	if (!dfl_get_feature_by_id(fdata, PORT_FEATURE_ID_AFU))
 		return 0;
 
 	return attr->mode;
@@ -504,9 +509,10 @@ static const struct attribute_group port_afu_group = {
 static int port_afu_init(struct platform_device *pdev,
 			 struct dfl_feature *feature)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct resource *res = &pdev->resource[feature->resource_index];
 
-	return afu_mmio_region_add(dev_get_platdata(&pdev->dev),
+	return afu_mmio_region_add(fdata,
 				   DFL_PORT_REGION_INDEX_AFU,
 				   resource_size(res), res->start,
 				   DFL_PORT_REGION_MMAP | DFL_PORT_REGION_READ |
@@ -525,9 +531,10 @@ static const struct dfl_feature_ops port_afu_ops = {
 static int port_stp_init(struct platform_device *pdev,
 			 struct dfl_feature *feature)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct resource *res = &pdev->resource[feature->resource_index];
 
-	return afu_mmio_region_add(dev_get_platdata(&pdev->dev),
+	return afu_mmio_region_add(fdata,
 				   DFL_PORT_REGION_INDEX_STP,
 				   resource_size(res), res->start,
 				   DFL_PORT_REGION_MMAP | DFL_PORT_REGION_READ |
@@ -595,22 +602,18 @@ static struct dfl_feature_driver port_feature_drvs[] = {
 
 static int afu_open(struct inode *inode, struct file *filp)
 {
-	struct platform_device *fdev = dfl_fpga_inode_to_feature_dev(inode);
-	struct dfl_feature_platform_data *pdata;
+	struct dfl_feature_dev_data *fdata = dfl_fpga_inode_to_feature_dev_data(inode);
+	struct platform_device *fdev = fdata->dev;
 	int ret;
 
-	pdata = dev_get_platdata(&fdev->dev);
-	if (WARN_ON(!pdata))
-		return -ENODEV;
-
-	mutex_lock(&pdata->lock);
-	ret = dfl_feature_dev_use_begin(pdata, filp->f_flags & O_EXCL);
+	mutex_lock(&fdata->lock);
+	ret = dfl_feature_dev_use_begin(fdata, filp->f_flags & O_EXCL);
 	if (!ret) {
 		dev_dbg(&fdev->dev, "Device File Opened %d Times\n",
-			dfl_feature_dev_use_count(pdata));
+			dfl_feature_dev_use_count(fdata));
 		filp->private_data = fdev;
 	}
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return ret;
 }
@@ -618,29 +621,29 @@ static int afu_open(struct inode *inode, struct file *filp)
 static int afu_release(struct inode *inode, struct file *filp)
 {
 	struct platform_device *pdev = filp->private_data;
-	struct dfl_feature_platform_data *pdata;
+	struct dfl_feature_dev_data *fdata;
 	struct dfl_feature *feature;
 
 	dev_dbg(&pdev->dev, "Device File Release\n");
 
-	pdata = dev_get_platdata(&pdev->dev);
+	fdata = to_dfl_feature_dev_data(&pdev->dev);
 
-	mutex_lock(&pdata->lock);
-	dfl_feature_dev_use_end(pdata);
+	mutex_lock(&fdata->lock);
+	dfl_feature_dev_use_end(fdata);
 
-	if (!dfl_feature_dev_use_count(pdata)) {
-		dfl_fpga_dev_for_each_feature(pdata, feature)
+	if (!dfl_feature_dev_use_count(fdata)) {
+		dfl_fpga_dev_for_each_feature(fdata, feature)
 			dfl_fpga_set_irq_triggers(feature, 0,
 						  feature->nr_irqs, NULL);
-		__port_reset(pdev);
-		afu_dma_region_destroy(pdata);
+		__port_reset(fdata);
+		afu_dma_region_destroy(fdata);
 	}
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 }
 
-static long afu_ioctl_check_extension(struct dfl_feature_platform_data *pdata,
+static long afu_ioctl_check_extension(struct dfl_feature_dev_data *fdata,
 				      unsigned long arg)
 {
 	/* No extension support for now */
@@ -648,7 +651,7 @@ static long afu_ioctl_check_extension(struct dfl_feature_platform_data *pdata,
 }
 
 static long
-afu_ioctl_get_info(struct dfl_feature_platform_data *pdata, void __user *arg)
+afu_ioctl_get_info(struct dfl_feature_dev_data *fdata, void __user *arg)
 {
 	struct dfl_fpga_port_info info;
 	struct dfl_afu *afu;
@@ -662,12 +665,12 @@ afu_ioctl_get_info(struct dfl_feature_platform_data *pdata, void __user *arg)
 	if (info.argsz < minsz)
 		return -EINVAL;
 
-	mutex_lock(&pdata->lock);
-	afu = dfl_fpga_pdata_get_private(pdata);
+	mutex_lock(&fdata->lock);
+	afu = dfl_fpga_fdata_get_private(fdata);
 	info.flags = 0;
 	info.num_regions = afu->num_regions;
 	info.num_umsgs = afu->num_umsgs;
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	if (copy_to_user(arg, &info, sizeof(info)))
 		return -EFAULT;
@@ -675,7 +678,7 @@ afu_ioctl_get_info(struct dfl_feature_platform_data *pdata, void __user *arg)
 	return 0;
 }
 
-static long afu_ioctl_get_region_info(struct dfl_feature_platform_data *pdata,
+static long afu_ioctl_get_region_info(struct dfl_feature_dev_data *fdata,
 				      void __user *arg)
 {
 	struct dfl_fpga_port_region_info rinfo;
@@ -691,7 +694,7 @@ static long afu_ioctl_get_region_info(struct dfl_feature_platform_data *pdata,
 	if (rinfo.argsz < minsz || rinfo.padding)
 		return -EINVAL;
 
-	ret = afu_mmio_region_get_by_index(pdata, rinfo.index, &region);
+	ret = afu_mmio_region_get_by_index(fdata, rinfo.index, &region);
 	if (ret)
 		return ret;
 
@@ -706,7 +709,7 @@ static long afu_ioctl_get_region_info(struct dfl_feature_platform_data *pdata,
 }
 
 static long
-afu_ioctl_dma_map(struct dfl_feature_platform_data *pdata, void __user *arg)
+afu_ioctl_dma_map(struct dfl_feature_dev_data *fdata, void __user *arg)
 {
 	struct dfl_fpga_port_dma_map map;
 	unsigned long minsz;
@@ -720,16 +723,16 @@ afu_ioctl_dma_map(struct dfl_feature_platform_data *pdata, void __user *arg)
 	if (map.argsz < minsz || map.flags)
 		return -EINVAL;
 
-	ret = afu_dma_map_region(pdata, map.user_addr, map.length, &map.iova);
+	ret = afu_dma_map_region(fdata, map.user_addr, map.length, &map.iova);
 	if (ret)
 		return ret;
 
 	if (copy_to_user(arg, &map, sizeof(map))) {
-		afu_dma_unmap_region(pdata, map.iova);
+		afu_dma_unmap_region(fdata, map.iova);
 		return -EFAULT;
 	}
 
-	dev_dbg(&pdata->dev->dev, "dma map: ua=%llx, len=%llx, iova=%llx\n",
+	dev_dbg(&fdata->dev->dev, "dma map: ua=%llx, len=%llx, iova=%llx\n",
 		(unsigned long long)map.user_addr,
 		(unsigned long long)map.length,
 		(unsigned long long)map.iova);
@@ -738,7 +741,7 @@ afu_ioctl_dma_map(struct dfl_feature_platform_data *pdata, void __user *arg)
 }
 
 static long
-afu_ioctl_dma_unmap(struct dfl_feature_platform_data *pdata, void __user *arg)
+afu_ioctl_dma_unmap(struct dfl_feature_dev_data *fdata, void __user *arg)
 {
 	struct dfl_fpga_port_dma_unmap unmap;
 	unsigned long minsz;
@@ -751,33 +754,33 @@ afu_ioctl_dma_unmap(struct dfl_feature_platform_data *pdata, void __user *arg)
 	if (unmap.argsz < minsz || unmap.flags)
 		return -EINVAL;
 
-	return afu_dma_unmap_region(pdata, unmap.iova);
+	return afu_dma_unmap_region(fdata, unmap.iova);
 }
 
 static long afu_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct platform_device *pdev = filp->private_data;
-	struct dfl_feature_platform_data *pdata;
+	struct dfl_feature_dev_data *fdata;
 	struct dfl_feature *f;
 	long ret;
 
 	dev_dbg(&pdev->dev, "%s cmd 0x%x\n", __func__, cmd);
 
-	pdata = dev_get_platdata(&pdev->dev);
+	fdata = to_dfl_feature_dev_data(&pdev->dev);
 
 	switch (cmd) {
 	case DFL_FPGA_GET_API_VERSION:
 		return DFL_FPGA_API_VERSION;
 	case DFL_FPGA_CHECK_EXTENSION:
-		return afu_ioctl_check_extension(pdata, arg);
+		return afu_ioctl_check_extension(fdata, arg);
 	case DFL_FPGA_PORT_GET_INFO:
-		return afu_ioctl_get_info(pdata, (void __user *)arg);
+		return afu_ioctl_get_info(fdata, (void __user *)arg);
 	case DFL_FPGA_PORT_GET_REGION_INFO:
-		return afu_ioctl_get_region_info(pdata, (void __user *)arg);
+		return afu_ioctl_get_region_info(fdata, (void __user *)arg);
 	case DFL_FPGA_PORT_DMA_MAP:
-		return afu_ioctl_dma_map(pdata, (void __user *)arg);
+		return afu_ioctl_dma_map(fdata, (void __user *)arg);
 	case DFL_FPGA_PORT_DMA_UNMAP:
-		return afu_ioctl_dma_unmap(pdata, (void __user *)arg);
+		return afu_ioctl_dma_unmap(fdata, (void __user *)arg);
 	default:
 		/*
 		 * Let sub-feature's ioctl function to handle the cmd
@@ -785,7 +788,7 @@ static long afu_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		 * handled in this sub feature, and returns 0 and other
 		 * error code if cmd is handled.
 		 */
-		dfl_fpga_dev_for_each_feature(pdata, f)
+		dfl_fpga_dev_for_each_feature(fdata, f)
 			if (f->ops && f->ops->ioctl) {
 				ret = f->ops->ioctl(pdev, f, cmd, arg);
 				if (ret != -ENODEV)
@@ -805,8 +808,8 @@ static const struct vm_operations_struct afu_vma_ops = {
 static int afu_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct platform_device *pdev = filp->private_data;
-	struct dfl_feature_platform_data *pdata;
 	u64 size = vma->vm_end - vma->vm_start;
+	struct dfl_feature_dev_data *fdata;
 	struct dfl_afu_mmio_region region;
 	u64 offset;
 	int ret;
@@ -814,10 +817,10 @@ static int afu_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	pdata = dev_get_platdata(&pdev->dev);
+	fdata = to_dfl_feature_dev_data(&pdev->dev);
 
 	offset = vma->vm_pgoff << PAGE_SHIFT;
-	ret = afu_mmio_region_get_by_offset(pdata, offset, size, &region);
+	ret = afu_mmio_region_get_by_offset(fdata, offset, size, &region);
 	if (ret)
 		return ret;
 
@@ -851,46 +854,45 @@ static const struct file_operations afu_fops = {
 
 static int afu_dev_init(struct platform_device *pdev)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct dfl_afu *afu;
 
 	afu = devm_kzalloc(&pdev->dev, sizeof(*afu), GFP_KERNEL);
 	if (!afu)
 		return -ENOMEM;
 
-	mutex_lock(&pdata->lock);
-	dfl_fpga_pdata_set_private(pdata, afu);
-	afu_mmio_region_init(pdata);
-	afu_dma_region_init(pdata);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	dfl_fpga_fdata_set_private(fdata, afu);
+	afu_mmio_region_init(fdata);
+	afu_dma_region_init(fdata);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 }
 
 static int afu_dev_destroy(struct platform_device *pdev)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 
-	mutex_lock(&pdata->lock);
-	afu_mmio_region_destroy(pdata);
-	afu_dma_region_destroy(pdata);
-	dfl_fpga_pdata_set_private(pdata, NULL);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	afu_mmio_region_destroy(fdata);
+	afu_dma_region_destroy(fdata);
+	dfl_fpga_fdata_set_private(fdata, NULL);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 }
 
-static int port_enable_set(struct platform_device *pdev, bool enable)
+static int port_enable_set(struct dfl_feature_dev_data *fdata, bool enable)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int ret;
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	if (enable)
-		ret = __afu_port_enable(pdev);
+		ret = __afu_port_enable(fdata);
 	else
-		ret = __afu_port_disable(pdev);
-	mutex_unlock(&pdata->lock);
+		ret = __afu_port_disable(fdata);
+	mutex_unlock(&fdata->lock);
 
 	return ret;
 }
diff --git a/drivers/fpga/dfl-afu-region.c b/drivers/fpga/dfl-afu-region.c
index 2e7b41629406..b11a5b21e666 100644
--- a/drivers/fpga/dfl-afu-region.c
+++ b/drivers/fpga/dfl-afu-region.c
@@ -12,11 +12,11 @@
 
 /**
  * afu_mmio_region_init - init function for afu mmio region support
- * @pdata: afu platform device's pdata.
+ * @fdata: afu feature dev data
  */
-void afu_mmio_region_init(struct dfl_feature_platform_data *pdata)
+void afu_mmio_region_init(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata);
 
 	INIT_LIST_HEAD(&afu->regions);
 }
@@ -39,7 +39,7 @@ static struct dfl_afu_mmio_region *get_region_by_index(struct dfl_afu *afu,
 /**
  * afu_mmio_region_add - add a mmio region to given feature dev.
  *
- * @pdata: afu platform device's pdata.
+ * @fdata: afu feature dev data
  * @region_index: region index.
  * @region_size: region size.
  * @phys: region's physical address of this region.
@@ -47,14 +47,15 @@ static struct dfl_afu_mmio_region *get_region_by_index(struct dfl_afu *afu,
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int afu_mmio_region_add(struct dfl_feature_platform_data *pdata,
+int afu_mmio_region_add(struct dfl_feature_dev_data *fdata,
 			u32 region_index, u64 region_size, u64 phys, u32 flags)
 {
+	struct device *dev = &fdata->dev->dev;
 	struct dfl_afu_mmio_region *region;
 	struct dfl_afu *afu;
 	int ret = 0;
 
-	region = devm_kzalloc(&pdata->dev->dev, sizeof(*region), GFP_KERNEL);
+	region = devm_kzalloc(dev, sizeof(*region), GFP_KERNEL);
 	if (!region)
 		return -ENOMEM;
 
@@ -63,13 +64,13 @@ int afu_mmio_region_add(struct dfl_feature_platform_data *pdata,
 	region->phys = phys;
 	region->flags = flags;
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 
-	afu = dfl_fpga_pdata_get_private(pdata);
+	afu = dfl_fpga_fdata_get_private(fdata);
 
 	/* check if @index already exists */
 	if (get_region_by_index(afu, region_index)) {
-		mutex_unlock(&pdata->lock);
+		mutex_unlock(&fdata->lock);
 		ret = -EEXIST;
 		goto exit;
 	}
@@ -80,37 +81,37 @@ int afu_mmio_region_add(struct dfl_feature_platform_data *pdata,
 
 	afu->region_cur_offset += region_size;
 	afu->num_regions++;
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 
 exit:
-	devm_kfree(&pdata->dev->dev, region);
+	devm_kfree(dev, region);
 	return ret;
 }
 
 /**
  * afu_mmio_region_destroy - destroy all mmio regions under given feature dev.
- * @pdata: afu platform device's pdata.
+ * @fdata: afu feature dev data
  */
-void afu_mmio_region_destroy(struct dfl_feature_platform_data *pdata)
+void afu_mmio_region_destroy(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_afu *afu = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_afu *afu = dfl_fpga_fdata_get_private(fdata);
 	struct dfl_afu_mmio_region *tmp, *region;
 
 	list_for_each_entry_safe(region, tmp, &afu->regions, node)
-		devm_kfree(&pdata->dev->dev, region);
+		devm_kfree(&fdata->dev->dev, region);
 }
 
 /**
  * afu_mmio_region_get_by_index - find an afu region by index.
- * @pdata: afu platform device's pdata.
+ * @fdata: afu feature dev data
  * @region_index: region index.
  * @pregion: ptr to region for result.
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata,
+int afu_mmio_region_get_by_index(struct dfl_feature_dev_data *fdata,
 				 u32 region_index,
 				 struct dfl_afu_mmio_region *pregion)
 {
@@ -118,8 +119,8 @@ int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata,
 	struct dfl_afu *afu;
 	int ret = 0;
 
-	mutex_lock(&pdata->lock);
-	afu = dfl_fpga_pdata_get_private(pdata);
+	mutex_lock(&fdata->lock);
+	afu = dfl_fpga_fdata_get_private(fdata);
 	region = get_region_by_index(afu, region_index);
 	if (!region) {
 		ret = -EINVAL;
@@ -127,14 +128,14 @@ int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata,
 	}
 	*pregion = *region;
 exit:
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return ret;
 }
 
 /**
  * afu_mmio_region_get_by_offset - find an afu mmio region by offset and size
  *
- * @pdata: afu platform device's pdata.
+ * @fdata: afu feature dev data
  * @offset: region offset from start of the device fd.
  * @size: region size.
  * @pregion: ptr to region for result.
@@ -144,7 +145,7 @@ exit:
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata,
+int afu_mmio_region_get_by_offset(struct dfl_feature_dev_data *fdata,
 				  u64 offset, u64 size,
 				  struct dfl_afu_mmio_region *pregion)
 {
@@ -152,8 +153,8 @@ int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata,
 	struct dfl_afu *afu;
 	int ret = 0;
 
-	mutex_lock(&pdata->lock);
-	afu = dfl_fpga_pdata_get_private(pdata);
+	mutex_lock(&fdata->lock);
+	afu = dfl_fpga_fdata_get_private(fdata);
 	for_each_region(region, afu)
 		if (region->offset <= offset &&
 		    region->offset + region->size >= offset + size) {
@@ -162,6 +163,6 @@ int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata,
 		}
 	ret = -EINVAL;
 exit:
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return ret;
 }
diff --git a/drivers/fpga/dfl-afu.h b/drivers/fpga/dfl-afu.h
index 7bef3e300aa2..03be4f0969c7 100644
--- a/drivers/fpga/dfl-afu.h
+++ b/drivers/fpga/dfl-afu.h
@@ -76,27 +76,27 @@ struct dfl_afu {
 	struct rb_root dma_regions;
 };
 
-/* hold pdata->lock when call __afu_port_enable/disable */
-int __afu_port_enable(struct platform_device *pdev);
-int __afu_port_disable(struct platform_device *pdev);
+/* hold fdata->lock when call __afu_port_enable/disable */
+int __afu_port_enable(struct dfl_feature_dev_data *fdata);
+int __afu_port_disable(struct dfl_feature_dev_data *fdata);
 
-void afu_mmio_region_init(struct dfl_feature_platform_data *pdata);
-int afu_mmio_region_add(struct dfl_feature_platform_data *pdata,
+void afu_mmio_region_init(struct dfl_feature_dev_data *fdata);
+int afu_mmio_region_add(struct dfl_feature_dev_data *fdata,
 			u32 region_index, u64 region_size, u64 phys, u32 flags);
-void afu_mmio_region_destroy(struct dfl_feature_platform_data *pdata);
-int afu_mmio_region_get_by_index(struct dfl_feature_platform_data *pdata,
+void afu_mmio_region_destroy(struct dfl_feature_dev_data *fdata);
+int afu_mmio_region_get_by_index(struct dfl_feature_dev_data *fdata,
 				 u32 region_index,
 				 struct dfl_afu_mmio_region *pregion);
-int afu_mmio_region_get_by_offset(struct dfl_feature_platform_data *pdata,
+int afu_mmio_region_get_by_offset(struct dfl_feature_dev_data *fdata,
 				  u64 offset, u64 size,
 				  struct dfl_afu_mmio_region *pregion);
-void afu_dma_region_init(struct dfl_feature_platform_data *pdata);
-void afu_dma_region_destroy(struct dfl_feature_platform_data *pdata);
-int afu_dma_map_region(struct dfl_feature_platform_data *pdata,
+void afu_dma_region_init(struct dfl_feature_dev_data *fdata);
+void afu_dma_region_destroy(struct dfl_feature_dev_data *fdata);
+int afu_dma_map_region(struct dfl_feature_dev_data *fdata,
 		       u64 user_addr, u64 length, u64 *iova);
-int afu_dma_unmap_region(struct dfl_feature_platform_data *pdata, u64 iova);
+int afu_dma_unmap_region(struct dfl_feature_dev_data *fdata, u64 iova);
 struct dfl_afu_dma_region *
-afu_dma_region_find(struct dfl_feature_platform_data *pdata,
+afu_dma_region_find(struct dfl_feature_dev_data *fdata,
 		    u64 iova, u64 size);
 
 extern const struct dfl_feature_ops port_err_ops;
diff --git a/drivers/fpga/dfl-fme-br.c b/drivers/fpga/dfl-fme-br.c
index 950c606c59d4..28b0f9d062ac 100644
--- a/drivers/fpga/dfl-fme-br.c
+++ b/drivers/fpga/dfl-fme-br.c
@@ -22,34 +22,34 @@
 struct fme_br_priv {
 	struct dfl_fme_br_pdata *pdata;
 	struct dfl_fpga_port_ops *port_ops;
-	struct platform_device *port_pdev;
+	struct dfl_feature_dev_data *port_fdata;
 };
 
 static int fme_bridge_enable_set(struct fpga_bridge *bridge, bool enable)
 {
 	struct fme_br_priv *priv = bridge->priv;
-	struct platform_device *port_pdev;
+	struct dfl_feature_dev_data *port_fdata;
 	struct dfl_fpga_port_ops *ops;
 
-	if (!priv->port_pdev) {
-		port_pdev = dfl_fpga_cdev_find_port(priv->pdata->cdev,
-						    &priv->pdata->port_id,
-						    dfl_fpga_check_port_id);
-		if (!port_pdev)
+	if (!priv->port_fdata) {
+		port_fdata = dfl_fpga_cdev_find_port_data(priv->pdata->cdev,
+							  &priv->pdata->port_id,
+							  dfl_fpga_check_port_id);
+		if (!port_fdata)
 			return -ENODEV;
 
-		priv->port_pdev = port_pdev;
+		priv->port_fdata = port_fdata;
 	}
 
-	if (priv->port_pdev && !priv->port_ops) {
-		ops = dfl_fpga_port_ops_get(priv->port_pdev);
+	if (priv->port_fdata && !priv->port_ops) {
+		ops = dfl_fpga_port_ops_get(priv->port_fdata);
 		if (!ops || !ops->enable_set)
 			return -ENOENT;
 
 		priv->port_ops = ops;
 	}
 
-	return priv->port_ops->enable_set(priv->port_pdev, enable);
+	return priv->port_ops->enable_set(priv->port_fdata, enable);
 }
 
 static const struct fpga_bridge_ops fme_bridge_ops = {
@@ -85,8 +85,6 @@ static void fme_br_remove(struct platform_device *pdev)
 
 	fpga_bridge_unregister(br);
 
-	if (priv->port_pdev)
-		put_device(&priv->port_pdev->dev);
 	if (priv->port_ops)
 		dfl_fpga_port_ops_put(priv->port_ops);
 }
diff --git a/drivers/fpga/dfl-fme-error.c b/drivers/fpga/dfl-fme-error.c
index 51c2892ec06d..f00d949efe69 100644
--- a/drivers/fpga/dfl-fme-error.c
+++ b/drivers/fpga/dfl-fme-error.c
@@ -42,15 +42,15 @@
 static ssize_t pcie0_errors_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 value;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	value = readq(base + PCIE0_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)value);
 }
@@ -59,7 +59,7 @@ static ssize_t pcie0_errors_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	int ret = 0;
 	u64 v, val;
@@ -67,9 +67,9 @@ static ssize_t pcie0_errors_store(struct device *dev,
 	if (kstrtou64(buf, 0, &val))
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(GENMASK_ULL(63, 0), base + PCIE0_ERROR_MASK);
 
 	v = readq(base + PCIE0_ERROR);
@@ -79,7 +79,7 @@ static ssize_t pcie0_errors_store(struct device *dev,
 		ret = -EINVAL;
 
 	writeq(0ULL, base + PCIE0_ERROR_MASK);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return ret ? ret : count;
 }
 static DEVICE_ATTR_RW(pcie0_errors);
@@ -87,15 +87,15 @@ static DEVICE_ATTR_RW(pcie0_errors);
 static ssize_t pcie1_errors_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 value;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	value = readq(base + PCIE1_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)value);
 }
@@ -104,7 +104,7 @@ static ssize_t pcie1_errors_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	int ret = 0;
 	u64 v, val;
@@ -112,9 +112,9 @@ static ssize_t pcie1_errors_store(struct device *dev,
 	if (kstrtou64(buf, 0, &val))
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(GENMASK_ULL(63, 0), base + PCIE1_ERROR_MASK);
 
 	v = readq(base + PCIE1_ERROR);
@@ -124,7 +124,7 @@ static ssize_t pcie1_errors_store(struct device *dev,
 		ret = -EINVAL;
 
 	writeq(0ULL, base + PCIE1_ERROR_MASK);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return ret ? ret : count;
 }
 static DEVICE_ATTR_RW(pcie1_errors);
@@ -132,9 +132,10 @@ static DEVICE_ATTR_RW(pcie1_errors);
 static ssize_t nonfatal_errors_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
 	return sprintf(buf, "0x%llx\n",
 		       (unsigned long long)readq(base + RAS_NONFAT_ERROR));
@@ -144,9 +145,10 @@ static DEVICE_ATTR_RO(nonfatal_errors);
 static ssize_t catfatal_errors_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
 	return sprintf(buf, "0x%llx\n",
 		       (unsigned long long)readq(base + RAS_CATFAT_ERROR));
@@ -156,15 +158,15 @@ static DEVICE_ATTR_RO(catfatal_errors);
 static ssize_t inject_errors_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + RAS_ERROR_INJECT);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n",
 		       (unsigned long long)FIELD_GET(INJECT_ERROR_MASK, v));
@@ -174,7 +176,7 @@ static ssize_t inject_errors_store(struct device *dev,
 				   struct device_attribute *attr,
 				   const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u8 inject_error;
 	u64 v;
@@ -185,14 +187,14 @@ static ssize_t inject_errors_store(struct device *dev,
 	if (inject_error & ~INJECT_ERROR_MASK)
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	v = readq(base + RAS_ERROR_INJECT);
 	v &= ~INJECT_ERROR_MASK;
 	v |= FIELD_PREP(INJECT_ERROR_MASK, inject_error);
 	writeq(v, base + RAS_ERROR_INJECT);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return count;
 }
@@ -201,15 +203,15 @@ static DEVICE_ATTR_RW(inject_errors);
 static ssize_t fme_errors_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 value;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	value = readq(base + FME_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)value);
 }
@@ -218,7 +220,7 @@ static ssize_t fme_errors_store(struct device *dev,
 				struct device_attribute *attr,
 				const char *buf, size_t count)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v, val;
 	int ret = 0;
@@ -226,9 +228,9 @@ static ssize_t fme_errors_store(struct device *dev,
 	if (kstrtou64(buf, 0, &val))
 		return -EINVAL;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	writeq(GENMASK_ULL(63, 0), base + FME_ERROR_MASK);
 
 	v = readq(base + FME_ERROR);
@@ -240,7 +242,7 @@ static ssize_t fme_errors_store(struct device *dev,
 	/* Workaround: disable MBP_ERROR if feature revision is 0 */
 	writeq(dfl_feature_revision(base) ? 0ULL : MBP_ERROR,
 	       base + FME_ERROR_MASK);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return ret ? ret : count;
 }
 static DEVICE_ATTR_RW(fme_errors);
@@ -248,15 +250,15 @@ static DEVICE_ATTR_RW(fme_errors);
 static ssize_t first_error_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 value;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	value = readq(base + FME_FIRST_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)value);
 }
@@ -265,15 +267,15 @@ static DEVICE_ATTR_RO(first_error);
 static ssize_t next_error_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 value;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	value = readq(base + FME_NEXT_ERROR);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return sprintf(buf, "0x%llx\n", (unsigned long long)value);
 }
@@ -295,12 +297,14 @@ static umode_t fme_global_err_attrs_visible(struct kobject *kobj,
 					    struct attribute *attr, int n)
 {
 	struct device *dev = kobj_to_dev(kobj);
+	struct dfl_feature_dev_data *fdata;
 
+	fdata = to_dfl_feature_dev_data(dev);
 	/*
 	 * sysfs entries are visible only if related private feature is
 	 * enumerated.
 	 */
-	if (!dfl_get_feature_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR))
+	if (!dfl_get_feature_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR))
 		return 0;
 
 	return attr->mode;
@@ -314,12 +318,12 @@ const struct attribute_group fme_global_err_group = {
 
 static void fme_err_mask(struct device *dev, bool mask)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_GLOBAL_ERR);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_GLOBAL_ERR);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 
 	/* Workaround: keep MBP_ERROR always masked if revision is 0 */
 	if (dfl_feature_revision(base))
@@ -332,7 +336,7 @@ static void fme_err_mask(struct device *dev, bool mask)
 	writeq(mask ? ERROR_MASK : 0, base + RAS_NONFAT_ERROR_MASK);
 	writeq(mask ? ERROR_MASK : 0, base + RAS_CATFAT_ERROR_MASK);
 
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 }
 
 static int fme_global_err_init(struct platform_device *pdev,
diff --git a/drivers/fpga/dfl-fme-main.c b/drivers/fpga/dfl-fme-main.c
index f8d89a4a6ccb..8aca2fb20e87 100644
--- a/drivers/fpga/dfl-fme-main.c
+++ b/drivers/fpga/dfl-fme-main.c
@@ -28,10 +28,11 @@
 static ssize_t ports_num_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_CAP);
 
@@ -47,10 +48,11 @@ static DEVICE_ATTR_RO(ports_num);
 static ssize_t bitstream_id_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_BITSTREAM_ID);
 
@@ -65,10 +67,11 @@ static DEVICE_ATTR_RO(bitstream_id);
 static ssize_t bitstream_metadata_show(struct device *dev,
 				       struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_BITSTREAM_MD);
 
@@ -79,10 +82,11 @@ static DEVICE_ATTR_RO(bitstream_metadata);
 static ssize_t cache_size_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_CAP);
 
@@ -94,10 +98,11 @@ static DEVICE_ATTR_RO(cache_size);
 static ssize_t fabric_version_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_CAP);
 
@@ -109,10 +114,11 @@ static DEVICE_ATTR_RO(fabric_version);
 static ssize_t socket_id_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_CAP);
 
@@ -135,10 +141,10 @@ static const struct attribute_group fme_hdr_group = {
 	.attrs = fme_hdr_attrs,
 };
 
-static long fme_hdr_ioctl_release_port(struct dfl_feature_platform_data *pdata,
+static long fme_hdr_ioctl_release_port(struct dfl_feature_dev_data *fdata,
 				       unsigned long arg)
 {
-	struct dfl_fpga_cdev *cdev = pdata->dfl_cdev;
+	struct dfl_fpga_cdev *cdev = fdata->dfl_cdev;
 	int port_id;
 
 	if (get_user(port_id, (int __user *)arg))
@@ -147,10 +153,10 @@ static long fme_hdr_ioctl_release_port(struct dfl_feature_platform_data *pdata,
 	return dfl_fpga_cdev_release_port(cdev, port_id);
 }
 
-static long fme_hdr_ioctl_assign_port(struct dfl_feature_platform_data *pdata,
+static long fme_hdr_ioctl_assign_port(struct dfl_feature_dev_data *fdata,
 				      unsigned long arg)
 {
-	struct dfl_fpga_cdev *cdev = pdata->dfl_cdev;
+	struct dfl_fpga_cdev *cdev = fdata->dfl_cdev;
 	int port_id;
 
 	if (get_user(port_id, (int __user *)arg))
@@ -163,13 +169,13 @@ static long fme_hdr_ioctl(struct platform_device *pdev,
 			  struct dfl_feature *feature,
 			  unsigned int cmd, unsigned long arg)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 
 	switch (cmd) {
 	case DFL_FPGA_FME_PORT_RELEASE:
-		return fme_hdr_ioctl_release_port(pdata, arg);
+		return fme_hdr_ioctl_release_port(fdata, arg);
 	case DFL_FPGA_FME_PORT_ASSIGN:
-		return fme_hdr_ioctl_assign_port(pdata, arg);
+		return fme_hdr_ioctl_assign_port(fdata, arg);
 	}
 
 	return -ENODEV;
@@ -411,14 +417,14 @@ static int power_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 static int power_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
 			     u32 attr, int channel, long val)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev->parent);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev->parent);
 	struct dfl_feature *feature = dev_get_drvdata(dev);
 	int ret = 0;
 	u64 v;
 
 	val = clamp_val(val / MICRO, 0, PWR_THRESHOLD_MAX);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 
 	switch (attr) {
 	case hwmon_power_max:
@@ -438,7 +444,7 @@ static int power_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
 		break;
 	}
 
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return ret;
 }
@@ -589,7 +595,7 @@ static struct dfl_feature_driver fme_feature_drvs[] = {
 	},
 };
 
-static long fme_ioctl_check_extension(struct dfl_feature_platform_data *pdata,
+static long fme_ioctl_check_extension(struct dfl_feature_dev_data *fdata,
 				      unsigned long arg)
 {
 	/* No extension support for now */
@@ -598,49 +604,46 @@ static long fme_ioctl_check_extension(struct dfl_feature_platform_data *pdata,
 
 static int fme_open(struct inode *inode, struct file *filp)
 {
-	struct platform_device *fdev = dfl_fpga_inode_to_feature_dev(inode);
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&fdev->dev);
+	struct dfl_feature_dev_data *fdata = dfl_fpga_inode_to_feature_dev_data(inode);
+	struct platform_device *fdev = fdata->dev;
 	int ret;
 
-	if (WARN_ON(!pdata))
-		return -ENODEV;
-
-	mutex_lock(&pdata->lock);
-	ret = dfl_feature_dev_use_begin(pdata, filp->f_flags & O_EXCL);
+	mutex_lock(&fdata->lock);
+	ret = dfl_feature_dev_use_begin(fdata, filp->f_flags & O_EXCL);
 	if (!ret) {
 		dev_dbg(&fdev->dev, "Device File Opened %d Times\n",
-			dfl_feature_dev_use_count(pdata));
-		filp->private_data = pdata;
+			dfl_feature_dev_use_count(fdata));
+		filp->private_data = fdata;
 	}
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return ret;
 }
 
 static int fme_release(struct inode *inode, struct file *filp)
 {
-	struct dfl_feature_platform_data *pdata = filp->private_data;
-	struct platform_device *pdev = pdata->dev;
+	struct dfl_feature_dev_data *fdata = filp->private_data;
+	struct platform_device *pdev = fdata->dev;
 	struct dfl_feature *feature;
 
 	dev_dbg(&pdev->dev, "Device File Release\n");
 
-	mutex_lock(&pdata->lock);
-	dfl_feature_dev_use_end(pdata);
+	mutex_lock(&fdata->lock);
+	dfl_feature_dev_use_end(fdata);
 
-	if (!dfl_feature_dev_use_count(pdata))
-		dfl_fpga_dev_for_each_feature(pdata, feature)
+	if (!dfl_feature_dev_use_count(fdata))
+		dfl_fpga_dev_for_each_feature(fdata, feature)
 			dfl_fpga_set_irq_triggers(feature, 0,
 						  feature->nr_irqs, NULL);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 }
 
 static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
-	struct dfl_feature_platform_data *pdata = filp->private_data;
-	struct platform_device *pdev = pdata->dev;
+	struct dfl_feature_dev_data *fdata = filp->private_data;
+	struct platform_device *pdev = fdata->dev;
 	struct dfl_feature *f;
 	long ret;
 
@@ -650,7 +653,7 @@ static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case DFL_FPGA_GET_API_VERSION:
 		return DFL_FPGA_API_VERSION;
 	case DFL_FPGA_CHECK_EXTENSION:
-		return fme_ioctl_check_extension(pdata, arg);
+		return fme_ioctl_check_extension(fdata, arg);
 	default:
 		/*
 		 * Let sub-feature's ioctl function to handle the cmd.
@@ -658,7 +661,7 @@ static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		 * handled in this sub feature, and returns 0 or other
 		 * error code if cmd is handled.
 		 */
-		dfl_fpga_dev_for_each_feature(pdata, f) {
+		dfl_fpga_dev_for_each_feature(fdata, f) {
 			if (f->ops && f->ops->ioctl) {
 				ret = f->ops->ioctl(pdev, f, cmd, arg);
 				if (ret != -ENODEV)
@@ -672,27 +675,27 @@ static long fme_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 static int fme_dev_init(struct platform_device *pdev)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct dfl_fme *fme;
 
 	fme = devm_kzalloc(&pdev->dev, sizeof(*fme), GFP_KERNEL);
 	if (!fme)
 		return -ENOMEM;
 
-	mutex_lock(&pdata->lock);
-	dfl_fpga_pdata_set_private(pdata, fme);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	dfl_fpga_fdata_set_private(fdata, fme);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 }
 
 static void fme_dev_destroy(struct platform_device *pdev)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 
-	mutex_lock(&pdata->lock);
-	dfl_fpga_pdata_set_private(pdata, NULL);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	dfl_fpga_fdata_set_private(fdata, NULL);
+	mutex_unlock(&fdata->lock);
 }
 
 static const struct file_operations fme_fops = {
diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c
index cdcf6dea4cc9..b878b260af38 100644
--- a/drivers/fpga/dfl-fme-pr.c
+++ b/drivers/fpga/dfl-fme-pr.c
@@ -65,7 +65,7 @@ static struct fpga_region *dfl_fme_region_find(struct dfl_fme *fme, int port_id)
 
 static int fme_pr(struct platform_device *pdev, unsigned long arg)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	void __user *argp = (void __user *)arg;
 	struct dfl_fpga_fme_port_pr port_pr;
 	struct fpga_image_info *info;
@@ -87,8 +87,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 		return -EINVAL;
 
 	/* get fme header region */
-	fme_hdr = dfl_get_feature_ioaddr_by_id(&pdev->dev,
-					       FME_FEATURE_ID_HEADER);
+	fme_hdr = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	/* check port id */
 	v = readq(fme_hdr + FME_HDR_CAP);
@@ -123,8 +122,8 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 
 	info->flags |= FPGA_MGR_PARTIAL_RECONFIG;
 
-	mutex_lock(&pdata->lock);
-	fme = dfl_fpga_pdata_get_private(pdata);
+	mutex_lock(&fdata->lock);
+	fme = dfl_fpga_fdata_get_private(fdata);
 	/* fme device has been unregistered. */
 	if (!fme) {
 		ret = -EINVAL;
@@ -156,7 +155,7 @@ static int fme_pr(struct platform_device *pdev, unsigned long arg)
 
 	put_device(&region->dev);
 unlock_exit:
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 free_exit:
 	vfree(buf);
 	return ret;
@@ -164,16 +163,16 @@ free_exit:
 
 /**
  * dfl_fme_create_mgr - create fpga mgr platform device as child device
+ * @fdata: fme feature dev data
  * @feature: sub feature info
- * @pdata: fme platform_device's pdata
  *
  * Return: mgr platform device if successful, and error code otherwise.
  */
 static struct platform_device *
-dfl_fme_create_mgr(struct dfl_feature_platform_data *pdata,
+dfl_fme_create_mgr(struct dfl_feature_dev_data *fdata,
 		   struct dfl_feature *feature)
 {
-	struct platform_device *mgr, *fme = pdata->dev;
+	struct platform_device *mgr, *fme = fdata->dev;
 	struct dfl_fme_mgr_pdata mgr_pdata;
 	int ret = -ENOMEM;
 
@@ -209,11 +208,11 @@ create_mgr_err:
 
 /**
  * dfl_fme_destroy_mgr - destroy fpga mgr platform device
- * @pdata: fme platform device's pdata
+ * @fdata: fme feature dev data
  */
-static void dfl_fme_destroy_mgr(struct dfl_feature_platform_data *pdata)
+static void dfl_fme_destroy_mgr(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_fme *priv = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_fme *priv = dfl_fpga_fdata_get_private(fdata);
 
 	platform_device_unregister(priv->mgr);
 }
@@ -221,15 +220,15 @@ static void dfl_fme_destroy_mgr(struct dfl_feature_platform_data *pdata)
 /**
  * dfl_fme_create_bridge - create fme fpga bridge platform device as child
  *
- * @pdata: fme platform device's pdata
+ * @fdata: fme feature dev data
  * @port_id: port id for the bridge to be created.
  *
  * Return: bridge platform device if successful, and error code otherwise.
  */
 static struct dfl_fme_bridge *
-dfl_fme_create_bridge(struct dfl_feature_platform_data *pdata, int port_id)
+dfl_fme_create_bridge(struct dfl_feature_dev_data *fdata, int port_id)
 {
-	struct device *dev = &pdata->dev->dev;
+	struct device *dev = &fdata->dev->dev;
 	struct dfl_fme_br_pdata br_pdata;
 	struct dfl_fme_bridge *fme_br;
 	int ret = -ENOMEM;
@@ -238,7 +237,7 @@ dfl_fme_create_bridge(struct dfl_feature_platform_data *pdata, int port_id)
 	if (!fme_br)
 		return ERR_PTR(ret);
 
-	br_pdata.cdev = pdata->dfl_cdev;
+	br_pdata.cdev = fdata->dfl_cdev;
 	br_pdata.port_id = port_id;
 
 	fme_br->br = platform_device_alloc(DFL_FPGA_FME_BRIDGE,
@@ -274,11 +273,11 @@ static void dfl_fme_destroy_bridge(struct dfl_fme_bridge *fme_br)
 
 /**
  * dfl_fme_destroy_bridges - destroy all fpga bridge platform device
- * @pdata: fme platform device's pdata
+ * @fdata: fme feature dev data
  */
-static void dfl_fme_destroy_bridges(struct dfl_feature_platform_data *pdata)
+static void dfl_fme_destroy_bridges(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_fme *priv = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_fme *priv = dfl_fpga_fdata_get_private(fdata);
 	struct dfl_fme_bridge *fbridge, *tmp;
 
 	list_for_each_entry_safe(fbridge, tmp, &priv->bridge_list, node) {
@@ -290,7 +289,7 @@ static void dfl_fme_destroy_bridges(struct dfl_feature_platform_data *pdata)
 /**
  * dfl_fme_create_region - create fpga region platform device as child
  *
- * @pdata: fme platform device's pdata
+ * @fdata: fme feature dev data
  * @mgr: mgr platform device needed for region
  * @br: br platform device needed for region
  * @port_id: port id
@@ -298,12 +297,12 @@ static void dfl_fme_destroy_bridges(struct dfl_feature_platform_data *pdata)
  * Return: fme region if successful, and error code otherwise.
  */
 static struct dfl_fme_region *
-dfl_fme_create_region(struct dfl_feature_platform_data *pdata,
+dfl_fme_create_region(struct dfl_feature_dev_data *fdata,
 		      struct platform_device *mgr,
 		      struct platform_device *br, int port_id)
 {
 	struct dfl_fme_region_pdata region_pdata;
-	struct device *dev = &pdata->dev->dev;
+	struct device *dev = &fdata->dev->dev;
 	struct dfl_fme_region *fme_region;
 	int ret = -ENOMEM;
 
@@ -353,11 +352,11 @@ static void dfl_fme_destroy_region(struct dfl_fme_region *fme_region)
 
 /**
  * dfl_fme_destroy_regions - destroy all fme regions
- * @pdata: fme platform device's pdata
+ * @fdata: fme feature dev data
  */
-static void dfl_fme_destroy_regions(struct dfl_feature_platform_data *pdata)
+static void dfl_fme_destroy_regions(struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_fme *priv = dfl_fpga_pdata_get_private(pdata);
+	struct dfl_fme *priv = dfl_fpga_fdata_get_private(fdata);
 	struct dfl_fme_region *fme_region, *tmp;
 
 	list_for_each_entry_safe(fme_region, tmp, &priv->region_list, node) {
@@ -369,7 +368,7 @@ static void dfl_fme_destroy_regions(struct dfl_feature_platform_data *pdata)
 static int pr_mgmt_init(struct platform_device *pdev,
 			struct dfl_feature *feature)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct dfl_fme_region *fme_region;
 	struct dfl_fme_bridge *fme_br;
 	struct platform_device *mgr;
@@ -378,18 +377,17 @@ static int pr_mgmt_init(struct platform_device *pdev,
 	int ret = -ENODEV, i = 0;
 	u64 fme_cap, port_offset;
 
-	fme_hdr = dfl_get_feature_ioaddr_by_id(&pdev->dev,
-					       FME_FEATURE_ID_HEADER);
+	fme_hdr = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
-	mutex_lock(&pdata->lock);
-	priv = dfl_fpga_pdata_get_private(pdata);
+	mutex_lock(&fdata->lock);
+	priv = dfl_fpga_fdata_get_private(fdata);
 
 	/* Initialize the region and bridge sub device list */
 	INIT_LIST_HEAD(&priv->region_list);
 	INIT_LIST_HEAD(&priv->bridge_list);
 
 	/* Create fpga mgr platform device */
-	mgr = dfl_fme_create_mgr(pdata, feature);
+	mgr = dfl_fme_create_mgr(fdata, feature);
 	if (IS_ERR(mgr)) {
 		dev_err(&pdev->dev, "fail to create fpga mgr pdev\n");
 		goto unlock;
@@ -405,7 +403,7 @@ static int pr_mgmt_init(struct platform_device *pdev,
 			continue;
 
 		/* Create bridge for each port */
-		fme_br = dfl_fme_create_bridge(pdata, i);
+		fme_br = dfl_fme_create_bridge(fdata, i);
 		if (IS_ERR(fme_br)) {
 			ret = PTR_ERR(fme_br);
 			goto destroy_region;
@@ -414,7 +412,7 @@ static int pr_mgmt_init(struct platform_device *pdev,
 		list_add(&fme_br->node, &priv->bridge_list);
 
 		/* Create region for each port */
-		fme_region = dfl_fme_create_region(pdata, mgr,
+		fme_region = dfl_fme_create_region(fdata, mgr,
 						   fme_br->br, i);
 		if (IS_ERR(fme_region)) {
 			ret = PTR_ERR(fme_region);
@@ -423,30 +421,30 @@ static int pr_mgmt_init(struct platform_device *pdev,
 
 		list_add(&fme_region->node, &priv->region_list);
 	}
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	return 0;
 
 destroy_region:
-	dfl_fme_destroy_regions(pdata);
-	dfl_fme_destroy_bridges(pdata);
-	dfl_fme_destroy_mgr(pdata);
+	dfl_fme_destroy_regions(fdata);
+	dfl_fme_destroy_bridges(fdata);
+	dfl_fme_destroy_mgr(fdata);
 unlock:
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 	return ret;
 }
 
 static void pr_mgmt_uinit(struct platform_device *pdev,
 			  struct dfl_feature *feature)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 
-	dfl_fme_destroy_regions(pdata);
-	dfl_fme_destroy_bridges(pdata);
-	dfl_fme_destroy_mgr(pdata);
-	mutex_unlock(&pdata->lock);
+	dfl_fme_destroy_regions(fdata);
+	dfl_fme_destroy_bridges(fdata);
+	dfl_fme_destroy_mgr(fdata);
+	mutex_unlock(&fdata->lock);
 }
 
 static long fme_pr_ioctl(struct platform_device *pdev,
diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c
index c406b949026f..7022657243c0 100644
--- a/drivers/fpga/dfl.c
+++ b/drivers/fpga/dfl.c
@@ -119,17 +119,6 @@ static void dfl_id_free(enum dfl_id_type type, int id)
 	mutex_unlock(&dfl_id_mutex);
 }
 
-static enum dfl_id_type feature_dev_id_type(struct platform_device *pdev)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(dfl_devs); i++)
-		if (!strcmp(dfl_devs[i].name, pdev->name))
-			return i;
-
-	return DFL_ID_MAX;
-}
-
 static enum dfl_id_type dfh_id_to_type(u16 id)
 {
 	int i;
@@ -156,12 +145,12 @@ static LIST_HEAD(dfl_port_ops_list);
 
 /**
  * dfl_fpga_port_ops_get - get matched port ops from the global list
- * @pdev: platform device to match with associated port ops.
+ * @fdata: feature dev data to match with associated port ops.
  * Return: matched port ops on success, NULL otherwise.
  *
  * Please note that must dfl_fpga_port_ops_put after use the port_ops.
  */
-struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct platform_device *pdev)
+struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct dfl_feature_dev_data *fdata)
 {
 	struct dfl_fpga_port_ops *ops = NULL;
 
@@ -171,7 +160,7 @@ struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct platform_device *pdev)
 
 	list_for_each_entry(ops, &dfl_port_ops_list, node) {
 		/* match port_ops using the name of platform device */
-		if (!strcmp(pdev->name, ops->name)) {
+		if (!strcmp(fdata->pdev_name, ops->name)) {
 			if (!try_module_get(ops->owner))
 				ops = NULL;
 			goto done;
@@ -222,27 +211,26 @@ EXPORT_SYMBOL_GPL(dfl_fpga_port_ops_del);
 
 /**
  * dfl_fpga_check_port_id - check the port id
- * @pdev: port platform device.
+ * @fdata: port feature dev data.
  * @pport_id: port id to compare.
  *
  * Return: 1 if port device matches with given port id, otherwise 0.
  */
-int dfl_fpga_check_port_id(struct platform_device *pdev, void *pport_id)
+int dfl_fpga_check_port_id(struct dfl_feature_dev_data *fdata, void *pport_id)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct dfl_fpga_port_ops *port_ops;
 
-	if (pdata->id != FEATURE_DEV_ID_UNUSED)
-		return pdata->id == *(int *)pport_id;
+	if (fdata->id != FEATURE_DEV_ID_UNUSED)
+		return fdata->id == *(int *)pport_id;
 
-	port_ops = dfl_fpga_port_ops_get(pdev);
+	port_ops = dfl_fpga_port_ops_get(fdata);
 	if (!port_ops || !port_ops->get_id)
 		return 0;
 
-	pdata->id = port_ops->get_id(pdev);
+	fdata->id = port_ops->get_id(fdata);
 	dfl_fpga_port_ops_put(port_ops);
 
-	return pdata->id == *(int *)pport_id;
+	return fdata->id == *(int *)pport_id;
 }
 EXPORT_SYMBOL_GPL(dfl_fpga_check_port_id);
 
@@ -351,10 +339,10 @@ static void release_dfl_dev(struct device *dev)
 }
 
 static struct dfl_device *
-dfl_dev_add(struct dfl_feature_platform_data *pdata,
+dfl_dev_add(struct dfl_feature_dev_data *fdata,
 	    struct dfl_feature *feature)
 {
-	struct platform_device *pdev = pdata->dev;
+	struct platform_device *pdev = fdata->dev;
 	struct resource *parent_res;
 	struct dfl_device *ddev;
 	int id, i, ret;
@@ -380,11 +368,11 @@ dfl_dev_add(struct dfl_feature_platform_data *pdata,
 	if (ret)
 		goto put_dev;
 
-	ddev->type = feature_dev_id_type(pdev);
+	ddev->type = fdata->type;
 	ddev->feature_id = feature->id;
 	ddev->revision = feature->revision;
 	ddev->dfh_version = feature->dfh_version;
-	ddev->cdev = pdata->dfl_cdev;
+	ddev->cdev = fdata->dfl_cdev;
 	if (feature->param_size) {
 		ddev->params = kmemdup(feature->params, feature->param_size, GFP_KERNEL);
 		if (!ddev->params) {
@@ -435,11 +423,11 @@ put_dev:
 	return ERR_PTR(ret);
 }
 
-static void dfl_devs_remove(struct dfl_feature_platform_data *pdata)
+static void dfl_devs_remove(struct dfl_feature_dev_data *fdata)
 {
 	struct dfl_feature *feature;
 
-	dfl_fpga_dev_for_each_feature(pdata, feature) {
+	dfl_fpga_dev_for_each_feature(fdata, feature) {
 		if (feature->ddev) {
 			device_unregister(&feature->ddev->dev);
 			feature->ddev = NULL;
@@ -447,13 +435,13 @@ static void dfl_devs_remove(struct dfl_feature_platform_data *pdata)
 	}
 }
 
-static int dfl_devs_add(struct dfl_feature_platform_data *pdata)
+static int dfl_devs_add(struct dfl_feature_dev_data *fdata)
 {
 	struct dfl_feature *feature;
 	struct dfl_device *ddev;
 	int ret;
 
-	dfl_fpga_dev_for_each_feature(pdata, feature) {
+	dfl_fpga_dev_for_each_feature(fdata, feature) {
 		if (feature->ioaddr)
 			continue;
 
@@ -462,7 +450,7 @@ static int dfl_devs_add(struct dfl_feature_platform_data *pdata)
 			goto err;
 		}
 
-		ddev = dfl_dev_add(pdata, feature);
+		ddev = dfl_dev_add(fdata, feature);
 		if (IS_ERR(ddev)) {
 			ret = PTR_ERR(ddev);
 			goto err;
@@ -474,7 +462,7 @@ static int dfl_devs_add(struct dfl_feature_platform_data *pdata)
 	return 0;
 
 err:
-	dfl_devs_remove(pdata);
+	dfl_devs_remove(fdata);
 	return ret;
 }
 
@@ -504,12 +492,12 @@ EXPORT_SYMBOL(dfl_driver_unregister);
  */
 void dfl_fpga_dev_feature_uinit(struct platform_device *pdev)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct dfl_feature *feature;
 
-	dfl_devs_remove(pdata);
+	dfl_devs_remove(fdata);
 
-	dfl_fpga_dev_for_each_feature(pdata, feature) {
+	dfl_fpga_dev_for_each_feature(fdata, feature) {
 		if (feature->ops) {
 			if (feature->ops->uinit)
 				feature->ops->uinit(pdev, feature);
@@ -520,7 +508,6 @@ void dfl_fpga_dev_feature_uinit(struct platform_device *pdev)
 EXPORT_SYMBOL_GPL(dfl_fpga_dev_feature_uinit);
 
 static int dfl_feature_instance_init(struct platform_device *pdev,
-				     struct dfl_feature_platform_data *pdata,
 				     struct dfl_feature *feature,
 				     struct dfl_feature_driver *drv)
 {
@@ -579,16 +566,15 @@ static bool dfl_feature_drv_match(struct dfl_feature *feature,
 int dfl_fpga_dev_feature_init(struct platform_device *pdev,
 			      struct dfl_feature_driver *feature_drvs)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct dfl_feature_driver *drv = feature_drvs;
 	struct dfl_feature *feature;
 	int ret;
 
 	while (drv->ops) {
-		dfl_fpga_dev_for_each_feature(pdata, feature) {
+		dfl_fpga_dev_for_each_feature(fdata, feature) {
 			if (dfl_feature_drv_match(feature, drv)) {
-				ret = dfl_feature_instance_init(pdev, pdata,
-								feature, drv);
+				ret = dfl_feature_instance_init(pdev, feature, drv);
 				if (ret)
 					goto exit;
 			}
@@ -596,7 +582,7 @@ int dfl_fpga_dev_feature_init(struct platform_device *pdev,
 		drv++;
 	}
 
-	ret = dfl_devs_add(pdata);
+	ret = dfl_devs_add(fdata);
 	if (ret)
 		goto exit;
 
@@ -695,7 +681,7 @@ EXPORT_SYMBOL_GPL(dfl_fpga_dev_ops_unregister);
  * @nr_irqs: number of irqs for all feature devices.
  * @irq_table: Linux IRQ numbers for all irqs, indexed by local irq index of
  *	       this device.
- * @feature_dev: current feature device.
+ * @type: the current FIU type.
  * @ioaddr: header register region address of current FIU in enumeration.
  * @start: register resource start of current FIU.
  * @len: max register resource length of current FIU.
@@ -708,7 +694,7 @@ struct build_feature_devs_info {
 	unsigned int nr_irqs;
 	int *irq_table;
 
-	struct platform_device *feature_dev;
+	enum dfl_id_type type;
 	void __iomem *ioaddr;
 	resource_size_t start;
 	resource_size_t len;
@@ -743,50 +729,62 @@ struct dfl_feature_info {
 	u64 params[];
 };
 
-static void dfl_fpga_cdev_add_port_dev(struct dfl_fpga_cdev *cdev,
-				       struct platform_device *port)
+static void dfl_fpga_cdev_add_port_data(struct dfl_fpga_cdev *cdev,
+					struct dfl_feature_dev_data *fdata)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&port->dev);
-
 	mutex_lock(&cdev->lock);
-	list_add(&pdata->node, &cdev->port_dev_list);
-	get_device(&pdata->dev->dev);
+	list_add(&fdata->node, &cdev->port_dev_list);
 	mutex_unlock(&cdev->lock);
 }
 
-/*
- * register current feature device, it is called when we need to switch to
- * another feature parsing or we have parsed all features on given device
- * feature list.
- */
-static int build_info_commit_dev(struct build_feature_devs_info *binfo)
+static void dfl_id_free_action(void *arg)
+{
+	struct dfl_feature_dev_data *fdata = arg;
+
+	dfl_id_free(fdata->type, fdata->pdev_id);
+}
+
+static struct dfl_feature_dev_data *
+binfo_create_feature_dev_data(struct build_feature_devs_info *binfo)
 {
-	struct platform_device *fdev = binfo->feature_dev;
-	struct dfl_feature_platform_data *pdata;
+	enum dfl_id_type type = binfo->type;
 	struct dfl_feature_info *finfo, *p;
-	enum dfl_id_type type;
+	struct dfl_feature_dev_data *fdata;
 	int ret, index = 0, res_idx = 0;
 
-	type = feature_dev_id_type(fdev);
 	if (WARN_ON_ONCE(type >= DFL_ID_MAX))
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
-	/*
-	 * we do not need to care for the memory which is associated with
-	 * the platform device. After calling platform_device_unregister(),
-	 * it will be automatically freed by device's release() callback,
-	 * platform_device_release().
-	 */
-	pdata = kzalloc(struct_size(pdata, features, binfo->feature_num), GFP_KERNEL);
-	if (!pdata)
-		return -ENOMEM;
+	fdata = devm_kzalloc(binfo->dev, sizeof(*fdata), GFP_KERNEL);
+	if (!fdata)
+		return ERR_PTR(-ENOMEM);
+
+	fdata->features = devm_kcalloc(binfo->dev, binfo->feature_num,
+				       sizeof(*fdata->features), GFP_KERNEL);
+	if (!fdata->features)
+		return ERR_PTR(-ENOMEM);
+
+	fdata->resources = devm_kcalloc(binfo->dev, binfo->feature_num,
+					sizeof(*fdata->resources), GFP_KERNEL);
+	if (!fdata->resources)
+		return ERR_PTR(-ENOMEM);
+
+	fdata->type = type;
 
-	pdata->dev = fdev;
-	pdata->num = binfo->feature_num;
-	pdata->dfl_cdev = binfo->cdev;
-	pdata->id = FEATURE_DEV_ID_UNUSED;
-	mutex_init(&pdata->lock);
-	lockdep_set_class_and_name(&pdata->lock, &dfl_pdata_keys[type],
+	fdata->pdev_id = dfl_id_alloc(type, binfo->dev);
+	if (fdata->pdev_id < 0)
+		return ERR_PTR(fdata->pdev_id);
+
+	ret = devm_add_action_or_reset(binfo->dev, dfl_id_free_action, fdata);
+	if (ret)
+		return ERR_PTR(ret);
+
+	fdata->pdev_name = dfl_devs[type].name;
+	fdata->num = binfo->feature_num;
+	fdata->dfl_cdev = binfo->cdev;
+	fdata->id = FEATURE_DEV_ID_UNUSED;
+	mutex_init(&fdata->lock);
+	lockdep_set_class_and_name(&fdata->lock, &dfl_pdata_keys[type],
 				   dfl_pdata_key_strings[type]);
 
 	/*
@@ -795,25 +793,15 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo)
 	 * works properly for port device.
 	 * and it should always be 0 for fme device.
 	 */
-	WARN_ON(pdata->disable_count);
-
-	fdev->dev.platform_data = pdata;
-
-	/* each sub feature has one MMIO resource */
-	fdev->num_resources = binfo->feature_num;
-	fdev->resource = kcalloc(binfo->feature_num, sizeof(*fdev->resource),
-				 GFP_KERNEL);
-	if (!fdev->resource)
-		return -ENOMEM;
+	WARN_ON(fdata->disable_count);
 
 	/* fill features and resource information for feature dev */
 	list_for_each_entry_safe(finfo, p, &binfo->sub_features, node) {
-		struct dfl_feature *feature = &pdata->features[index++];
+		struct dfl_feature *feature = &fdata->features[index++];
 		struct dfl_feature_irq_ctx *ctx;
 		unsigned int i;
 
 		/* save resource information for each feature */
-		feature->dev = fdev;
 		feature->id = finfo->fid;
 		feature->revision = finfo->revision;
 		feature->dfh_version = finfo->dfh_version;
@@ -823,7 +811,7 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo)
 						       finfo->params, finfo->param_size,
 						       GFP_KERNEL);
 			if (!feature->params)
-				return -ENOMEM;
+				return ERR_PTR(-ENOMEM);
 
 			feature->param_size = finfo->param_size;
 		}
@@ -840,17 +828,17 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo)
 				devm_ioremap_resource(binfo->dev,
 						      &finfo->mmio_res);
 			if (IS_ERR(feature->ioaddr))
-				return PTR_ERR(feature->ioaddr);
+				return ERR_CAST(feature->ioaddr);
 		} else {
 			feature->resource_index = res_idx;
-			fdev->resource[res_idx++] = finfo->mmio_res;
+			fdata->resources[res_idx++] = finfo->mmio_res;
 		}
 
 		if (finfo->nr_irqs) {
 			ctx = devm_kcalloc(binfo->dev, finfo->nr_irqs,
 					   sizeof(*ctx), GFP_KERNEL);
 			if (!ctx)
-				return -ENOMEM;
+				return ERR_PTR(-ENOMEM);
 
 			for (i = 0; i < finfo->nr_irqs; i++)
 				ctx[i].irq =
@@ -864,55 +852,94 @@ static int build_info_commit_dev(struct build_feature_devs_info *binfo)
 		kfree(finfo);
 	}
 
-	ret = platform_device_add(binfo->feature_dev);
-	if (!ret) {
-		if (type == PORT_ID)
-			dfl_fpga_cdev_add_port_dev(binfo->cdev,
-						   binfo->feature_dev);
-		else
-			binfo->cdev->fme_dev =
-					get_device(&binfo->feature_dev->dev);
-		/*
-		 * reset it to avoid build_info_free() freeing their resource.
-		 *
-		 * The resource of successfully registered feature devices
-		 * will be freed by platform_device_unregister(). See the
-		 * comments in build_info_create_dev().
-		 */
-		binfo->feature_dev = NULL;
-	}
+	fdata->resource_num = res_idx;
 
-	return ret;
+	return fdata;
 }
 
-static int
-build_info_create_dev(struct build_feature_devs_info *binfo,
-		      enum dfl_id_type type)
+/*
+ * register current feature device, it is called when we need to switch to
+ * another feature parsing or we have parsed all features on given device
+ * feature list.
+ */
+static int feature_dev_register(struct dfl_feature_dev_data *fdata)
 {
+	struct dfl_feature_platform_data pdata = {};
 	struct platform_device *fdev;
+	struct dfl_feature *feature;
+	int ret;
 
-	if (type >= DFL_ID_MAX)
-		return -EINVAL;
-
-	/*
-	 * we use -ENODEV as the initialization indicator which indicates
-	 * whether the id need to be reclaimed
-	 */
-	fdev = platform_device_alloc(dfl_devs[type].name, -ENODEV);
+	fdev = platform_device_alloc(fdata->pdev_name, fdata->pdev_id);
 	if (!fdev)
 		return -ENOMEM;
 
-	binfo->feature_dev = fdev;
-	binfo->feature_num = 0;
+	fdata->dev = fdev;
 
-	INIT_LIST_HEAD(&binfo->sub_features);
+	fdev->dev.parent = &fdata->dfl_cdev->region->dev;
+	fdev->dev.devt = dfl_get_devt(dfl_devs[fdata->type].devt_type, fdev->id);
 
-	fdev->id = dfl_id_alloc(type, &fdev->dev);
-	if (fdev->id < 0)
-		return fdev->id;
+	dfl_fpga_dev_for_each_feature(fdata, feature)
+		feature->dev = fdev;
+
+	ret = platform_device_add_resources(fdev, fdata->resources,
+					    fdata->resource_num);
+	if (ret)
+		goto err_put_dev;
+
+	pdata.fdata = fdata;
+	ret = platform_device_add_data(fdev, &pdata, sizeof(pdata));
+	if (ret)
+		goto err_put_dev;
+
+	ret = platform_device_add(fdev);
+	if (ret)
+		goto err_put_dev;
+
+	return 0;
+
+err_put_dev:
+	platform_device_put(fdev);
+
+	fdata->dev = NULL;
+
+	dfl_fpga_dev_for_each_feature(fdata, feature)
+		feature->dev = NULL;
+
+	return ret;
+}
+
+static void feature_dev_unregister(struct dfl_feature_dev_data *fdata)
+{
+	struct dfl_feature *feature;
+
+	platform_device_unregister(fdata->dev);
+
+	fdata->dev = NULL;
+
+	dfl_fpga_dev_for_each_feature(fdata, feature)
+		feature->dev = NULL;
+}
+
+static int build_info_commit_dev(struct build_feature_devs_info *binfo)
+{
+	struct dfl_feature_dev_data *fdata;
+	int ret;
+
+	fdata = binfo_create_feature_dev_data(binfo);
+	if (IS_ERR(fdata))
+		return PTR_ERR(fdata);
+
+	ret = feature_dev_register(fdata);
+	if (ret)
+		return ret;
+
+	if (binfo->type == PORT_ID)
+		dfl_fpga_cdev_add_port_data(binfo->cdev, fdata);
+	else
+		binfo->cdev->fme_dev = get_device(&fdata->dev->dev);
 
-	fdev->dev.parent = &binfo->cdev->region->dev;
-	fdev->dev.devt = dfl_get_devt(dfl_devs[type].devt_type, fdev->id);
+	/* reset the binfo for next FIU */
+	binfo->type = DFL_ID_MAX;
 
 	return 0;
 }
@@ -921,22 +948,11 @@ static void build_info_free(struct build_feature_devs_info *binfo)
 {
 	struct dfl_feature_info *finfo, *p;
 
-	/*
-	 * it is a valid id, free it. See comments in
-	 * build_info_create_dev()
-	 */
-	if (binfo->feature_dev && binfo->feature_dev->id >= 0) {
-		dfl_id_free(feature_dev_id_type(binfo->feature_dev),
-			    binfo->feature_dev->id);
-
-		list_for_each_entry_safe(finfo, p, &binfo->sub_features, node) {
-			list_del(&finfo->node);
-			kfree(finfo);
-		}
+	list_for_each_entry_safe(finfo, p, &binfo->sub_features, node) {
+		list_del(&finfo->node);
+		kfree(finfo);
 	}
 
-	platform_device_put(binfo->feature_dev);
-
 	devm_kfree(binfo->dev, binfo);
 }
 
@@ -1025,7 +1041,7 @@ static int parse_feature_irqs(struct build_feature_devs_info *binfo,
 		 * Instead, features with interrupt functionality provide
 		 * the information in feature specific registers.
 		 */
-		type = feature_dev_id_type(binfo->feature_dev);
+		type = binfo->type;
 		if (type == PORT_ID) {
 			switch (fid) {
 			case PORT_FEATURE_ID_UINT:
@@ -1217,7 +1233,7 @@ static int parse_feature_port_afu(struct build_feature_devs_info *binfo,
 	return create_feature_instance(binfo, ofst, size, FEATURE_ID_AFU);
 }
 
-#define is_feature_dev_detected(binfo) (!!(binfo)->feature_dev)
+#define is_feature_dev_detected(binfo) ((binfo)->type != DFL_ID_MAX)
 
 static int parse_feature_afu(struct build_feature_devs_info *binfo,
 			     resource_size_t ofst)
@@ -1227,12 +1243,11 @@ static int parse_feature_afu(struct build_feature_devs_info *binfo,
 		return -EINVAL;
 	}
 
-	switch (feature_dev_id_type(binfo->feature_dev)) {
+	switch (binfo->type) {
 	case PORT_ID:
 		return parse_feature_port_afu(binfo, ofst);
 	default:
-		dev_info(binfo->dev, "AFU belonging to FIU %s is not supported yet.\n",
-			 binfo->feature_dev->name);
+		dev_info(binfo->dev, "AFU belonging to FIU is not supported yet.\n");
 	}
 
 	return 0;
@@ -1273,6 +1288,7 @@ static void build_info_complete(struct build_feature_devs_info *binfo)
 static int parse_feature_fiu(struct build_feature_devs_info *binfo,
 			     resource_size_t ofst)
 {
+	enum dfl_id_type type;
 	int ret = 0;
 	u32 offset;
 	u16 id;
@@ -1294,10 +1310,13 @@ static int parse_feature_fiu(struct build_feature_devs_info *binfo,
 	v = readq(binfo->ioaddr + DFH);
 	id = FIELD_GET(DFH_ID, v);
 
-	/* create platform device for dfl feature dev */
-	ret = build_info_create_dev(binfo, dfh_id_to_type(id));
-	if (ret)
-		return ret;
+	type = dfh_id_to_type(id);
+	if (type >= DFL_ID_MAX)
+		return -EINVAL;
+
+	binfo->type = type;
+	binfo->feature_num = 0;
+	INIT_LIST_HEAD(&binfo->sub_features);
 
 	ret = create_feature_instance(binfo, 0, 0, 0);
 	if (ret)
@@ -1515,13 +1534,9 @@ EXPORT_SYMBOL_GPL(dfl_fpga_enum_info_add_irq);
 
 static int remove_feature_dev(struct device *dev, void *data)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	enum dfl_id_type type = feature_dev_id_type(pdev);
-	int id = pdev->id;
-
-	platform_device_unregister(pdev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
 
-	dfl_id_free(type, id);
+	feature_dev_unregister(fdata);
 
 	return 0;
 }
@@ -1573,6 +1588,7 @@ dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info)
 		goto unregister_region_exit;
 	}
 
+	binfo->type = DFL_ID_MAX;
 	binfo->dev = info->dev;
 	binfo->cdev = cdev;
 
@@ -1614,25 +1630,10 @@ EXPORT_SYMBOL_GPL(dfl_fpga_feature_devs_enumerate);
  */
 void dfl_fpga_feature_devs_remove(struct dfl_fpga_cdev *cdev)
 {
-	struct dfl_feature_platform_data *pdata, *ptmp;
-
 	mutex_lock(&cdev->lock);
 	if (cdev->fme_dev)
 		put_device(cdev->fme_dev);
 
-	list_for_each_entry_safe(pdata, ptmp, &cdev->port_dev_list, node) {
-		struct platform_device *port_dev = pdata->dev;
-
-		/* remove released ports */
-		if (!device_is_registered(&port_dev->dev)) {
-			dfl_id_free(feature_dev_id_type(port_dev),
-				    port_dev->id);
-			platform_device_put(port_dev);
-		}
-
-		list_del(&pdata->node);
-		put_device(&port_dev->dev);
-	}
 	mutex_unlock(&cdev->lock);
 
 	remove_feature_devs(cdev);
@@ -1643,7 +1644,7 @@ void dfl_fpga_feature_devs_remove(struct dfl_fpga_cdev *cdev)
 EXPORT_SYMBOL_GPL(dfl_fpga_feature_devs_remove);
 
 /**
- * __dfl_fpga_cdev_find_port - find a port under given container device
+ * __dfl_fpga_cdev_find_port_data - find a port under given container device
  *
  * @cdev: container device
  * @data: data passed to match function
@@ -1656,23 +1657,20 @@ EXPORT_SYMBOL_GPL(dfl_fpga_feature_devs_remove);
  *
  * NOTE: you will need to drop the device reference with put_device() after use.
  */
-struct platform_device *
-__dfl_fpga_cdev_find_port(struct dfl_fpga_cdev *cdev, void *data,
-			  int (*match)(struct platform_device *, void *))
+struct dfl_feature_dev_data *
+__dfl_fpga_cdev_find_port_data(struct dfl_fpga_cdev *cdev, void *data,
+			       int (*match)(struct dfl_feature_dev_data *, void *))
 {
-	struct dfl_feature_platform_data *pdata;
-	struct platform_device *port_dev;
-
-	list_for_each_entry(pdata, &cdev->port_dev_list, node) {
-		port_dev = pdata->dev;
+	struct dfl_feature_dev_data *fdata;
 
-		if (match(port_dev, data) && get_device(&port_dev->dev))
-			return port_dev;
+	list_for_each_entry(fdata, &cdev->port_dev_list, node) {
+		if (match(fdata, data))
+			return fdata;
 	}
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(__dfl_fpga_cdev_find_port);
+EXPORT_SYMBOL_GPL(__dfl_fpga_cdev_find_port_data);
 
 static int __init dfl_fpga_init(void)
 {
@@ -1706,33 +1704,28 @@ static int __init dfl_fpga_init(void)
  */
 int dfl_fpga_cdev_release_port(struct dfl_fpga_cdev *cdev, int port_id)
 {
-	struct dfl_feature_platform_data *pdata;
-	struct platform_device *port_pdev;
+	struct dfl_feature_dev_data *fdata;
 	int ret = -ENODEV;
 
 	mutex_lock(&cdev->lock);
-	port_pdev = __dfl_fpga_cdev_find_port(cdev, &port_id,
-					      dfl_fpga_check_port_id);
-	if (!port_pdev)
+	fdata = __dfl_fpga_cdev_find_port_data(cdev, &port_id,
+					       dfl_fpga_check_port_id);
+	if (!fdata)
 		goto unlock_exit;
 
-	if (!device_is_registered(&port_pdev->dev)) {
+	if (!fdata->dev) {
 		ret = -EBUSY;
-		goto put_dev_exit;
+		goto unlock_exit;
 	}
 
-	pdata = dev_get_platdata(&port_pdev->dev);
-
-	mutex_lock(&pdata->lock);
-	ret = dfl_feature_dev_use_begin(pdata, true);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	ret = dfl_feature_dev_use_begin(fdata, true);
+	mutex_unlock(&fdata->lock);
 	if (ret)
-		goto put_dev_exit;
+		goto unlock_exit;
 
-	platform_device_del(port_pdev);
+	feature_dev_unregister(fdata);
 	cdev->released_port_num++;
-put_dev_exit:
-	put_device(&port_pdev->dev);
 unlock_exit:
 	mutex_unlock(&cdev->lock);
 	return ret;
@@ -1752,34 +1745,29 @@ EXPORT_SYMBOL_GPL(dfl_fpga_cdev_release_port);
  */
 int dfl_fpga_cdev_assign_port(struct dfl_fpga_cdev *cdev, int port_id)
 {
-	struct dfl_feature_platform_data *pdata;
-	struct platform_device *port_pdev;
+	struct dfl_feature_dev_data *fdata;
 	int ret = -ENODEV;
 
 	mutex_lock(&cdev->lock);
-	port_pdev = __dfl_fpga_cdev_find_port(cdev, &port_id,
-					      dfl_fpga_check_port_id);
-	if (!port_pdev)
+	fdata = __dfl_fpga_cdev_find_port_data(cdev, &port_id,
+					       dfl_fpga_check_port_id);
+	if (!fdata)
 		goto unlock_exit;
 
-	if (device_is_registered(&port_pdev->dev)) {
+	if (fdata->dev) {
 		ret = -EBUSY;
-		goto put_dev_exit;
+		goto unlock_exit;
 	}
 
-	ret = platform_device_add(port_pdev);
+	ret = feature_dev_register(fdata);
 	if (ret)
-		goto put_dev_exit;
-
-	pdata = dev_get_platdata(&port_pdev->dev);
+		goto unlock_exit;
 
-	mutex_lock(&pdata->lock);
-	dfl_feature_dev_use_end(pdata);
-	mutex_unlock(&pdata->lock);
+	mutex_lock(&fdata->lock);
+	dfl_feature_dev_use_end(fdata);
+	mutex_unlock(&fdata->lock);
 
 	cdev->released_port_num--;
-put_dev_exit:
-	put_device(&port_pdev->dev);
 unlock_exit:
 	mutex_unlock(&cdev->lock);
 	return ret;
@@ -1789,10 +1777,11 @@ EXPORT_SYMBOL_GPL(dfl_fpga_cdev_assign_port);
 static void config_port_access_mode(struct device *fme_dev, int port_id,
 				    bool is_vf)
 {
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(fme_dev);
 	void __iomem *base;
 	u64 v;
 
-	base = dfl_get_feature_ioaddr_by_id(fme_dev, FME_FEATURE_ID_HEADER);
+	base = dfl_get_feature_ioaddr_by_id(fdata, FME_FEATURE_ID_HEADER);
 
 	v = readq(base + FME_HDR_PORT_OFST(port_id));
 
@@ -1816,14 +1805,14 @@ static void config_port_access_mode(struct device *fme_dev, int port_id,
  */
 void dfl_fpga_cdev_config_ports_pf(struct dfl_fpga_cdev *cdev)
 {
-	struct dfl_feature_platform_data *pdata;
+	struct dfl_feature_dev_data *fdata;
 
 	mutex_lock(&cdev->lock);
-	list_for_each_entry(pdata, &cdev->port_dev_list, node) {
-		if (device_is_registered(&pdata->dev->dev))
+	list_for_each_entry(fdata, &cdev->port_dev_list, node) {
+		if (fdata->dev)
 			continue;
 
-		config_port_pf_mode(cdev->fme_dev, pdata->id);
+		config_port_pf_mode(cdev->fme_dev, fdata->id);
 	}
 	mutex_unlock(&cdev->lock);
 }
@@ -1842,7 +1831,7 @@ EXPORT_SYMBOL_GPL(dfl_fpga_cdev_config_ports_pf);
  */
 int dfl_fpga_cdev_config_ports_vf(struct dfl_fpga_cdev *cdev, int num_vfs)
 {
-	struct dfl_feature_platform_data *pdata;
+	struct dfl_feature_dev_data *fdata;
 	int ret = 0;
 
 	mutex_lock(&cdev->lock);
@@ -1856,11 +1845,11 @@ int dfl_fpga_cdev_config_ports_vf(struct dfl_fpga_cdev *cdev, int num_vfs)
 		goto done;
 	}
 
-	list_for_each_entry(pdata, &cdev->port_dev_list, node) {
-		if (device_is_registered(&pdata->dev->dev))
+	list_for_each_entry(fdata, &cdev->port_dev_list, node) {
+		if (fdata->dev)
 			continue;
 
-		config_port_vf_mode(cdev->fme_dev, pdata->id);
+		config_port_vf_mode(cdev->fme_dev, fdata->id);
 	}
 done:
 	mutex_unlock(&cdev->lock);
@@ -1993,7 +1982,7 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev,
 			       struct dfl_feature *feature,
 			       unsigned long arg)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(&pdev->dev);
 	struct dfl_fpga_irq_set hdr;
 	s32 *fds;
 	long ret;
@@ -2013,9 +2002,9 @@ long dfl_feature_ioctl_set_irq(struct platform_device *pdev,
 	if (IS_ERR(fds))
 		return PTR_ERR(fds);
 
-	mutex_lock(&pdata->lock);
+	mutex_lock(&fdata->lock);
 	ret = dfl_fpga_set_irq_triggers(feature, hdr.start, hdr.count, fds);
-	mutex_unlock(&pdata->lock);
+	mutex_unlock(&fdata->lock);
 
 	kfree(fds);
 	return ret;
diff --git a/drivers/fpga/dfl.h b/drivers/fpga/dfl.h
index 5063d73b0d82..95539f1213cb 100644
--- a/drivers/fpga/dfl.h
+++ b/drivers/fpga/dfl.h
@@ -17,6 +17,7 @@
 #include <linux/bitfield.h>
 #include <linux/cdev.h>
 #include <linux/delay.h>
+#include <linux/dfl.h>
 #include <linux/eventfd.h>
 #include <linux/fs.h>
 #include <linux/interrupt.h>
@@ -206,6 +207,8 @@
 #define PORT_UINT_CAP_INT_NUM	GENMASK_ULL(11, 0)	/* Interrupts num */
 #define PORT_UINT_CAP_FST_VECT	GENMASK_ULL(23, 12)	/* First Vector */
 
+struct dfl_feature_dev_data;
+
 /**
  * struct dfl_fpga_port_ops - port ops
  *
@@ -219,15 +222,15 @@ struct dfl_fpga_port_ops {
 	const char *name;
 	struct module *owner;
 	struct list_head node;
-	int (*get_id)(struct platform_device *pdev);
-	int (*enable_set)(struct platform_device *pdev, bool enable);
+	int (*get_id)(struct dfl_feature_dev_data *fdata);
+	int (*enable_set)(struct dfl_feature_dev_data *fdata, bool enable);
 };
 
 void dfl_fpga_port_ops_add(struct dfl_fpga_port_ops *ops);
 void dfl_fpga_port_ops_del(struct dfl_fpga_port_ops *ops);
-struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct platform_device *pdev);
+struct dfl_fpga_port_ops *dfl_fpga_port_ops_get(struct dfl_feature_dev_data *fdata);
 void dfl_fpga_port_ops_put(struct dfl_fpga_port_ops *ops);
-int dfl_fpga_check_port_id(struct platform_device *pdev, void *pport_id);
+int dfl_fpga_check_port_id(struct dfl_feature_dev_data *fdata, void *pport_id);
 
 /**
  * struct dfl_feature_id - dfl private feature id
@@ -300,26 +303,32 @@ struct dfl_feature {
 #define FEATURE_DEV_ID_UNUSED	(-1)
 
 /**
- * struct dfl_feature_platform_data - platform data for feature devices
+ * struct dfl_feature_dev_data - dfl enumeration data for dfl feature dev.
  *
- * @node: node to link feature devs to container device's port_dev_list.
- * @lock: mutex to protect platform data.
- * @cdev: cdev of feature dev.
- * @dev: ptr to platform device linked with this platform data.
+ * @node: node to link the data structure to container device's port_dev_list.
+ * @lock: mutex to protect feature dev data.
+ * @dev: ptr to the feature's platform device linked with this structure.
+ * @type: type of DFL FIU for the feature dev. See enum dfl_id_type.
+ * @pdev_id: platform device id for the feature dev.
+ * @pdev_name: platform device name for the feature dev.
  * @dfl_cdev: ptr to container device.
- * @id: id used for this feature device.
+ * @id: id used for the feature device.
  * @disable_count: count for port disable.
  * @excl_open: set on feature device exclusive open.
  * @open_count: count for feature device open.
  * @num: number for sub features.
  * @private: ptr to feature dev private data.
- * @features: sub features of this feature dev.
+ * @features: sub features for the feature dev.
+ * @resource_num: number of resources for the feature dev.
+ * @resources: resources for the feature dev.
  */
-struct dfl_feature_platform_data {
+struct dfl_feature_dev_data {
 	struct list_head node;
 	struct mutex lock;
-	struct cdev cdev;
 	struct platform_device *dev;
+	enum dfl_id_type type;
+	int pdev_id;
+	const char *pdev_name;
 	struct dfl_fpga_cdev *dfl_cdev;
 	int id;
 	unsigned int disable_count;
@@ -327,55 +336,68 @@ struct dfl_feature_platform_data {
 	int open_count;
 	void *private;
 	int num;
-	struct dfl_feature features[];
+	struct dfl_feature *features;
+	int resource_num;
+	struct resource *resources;
+};
+
+/**
+ * struct dfl_feature_platform_data - platform data for feature devices
+ *
+ * @cdev: cdev of feature dev.
+ * @fdata: dfl enumeration data for the dfl feature device.
+ */
+struct dfl_feature_platform_data {
+	struct cdev cdev;
+	struct dfl_feature_dev_data *fdata;
 };
 
 static inline
-int dfl_feature_dev_use_begin(struct dfl_feature_platform_data *pdata,
+int dfl_feature_dev_use_begin(struct dfl_feature_dev_data *fdata,
 			      bool excl)
 {
-	if (pdata->excl_open)
+	if (fdata->excl_open)
 		return -EBUSY;
 
 	if (excl) {
-		if (pdata->open_count)
+		if (fdata->open_count)
 			return -EBUSY;
 
-		pdata->excl_open = true;
+		fdata->excl_open = true;
 	}
-	pdata->open_count++;
+	fdata->open_count++;
 
 	return 0;
 }
 
 static inline
-void dfl_feature_dev_use_end(struct dfl_feature_platform_data *pdata)
+void dfl_feature_dev_use_end(struct dfl_feature_dev_data *fdata)
 {
-	pdata->excl_open = false;
+	fdata->excl_open = false;
 
-	if (WARN_ON(pdata->open_count <= 0))
+	if (WARN_ON(fdata->open_count <= 0))
 		return;
 
-	pdata->open_count--;
+	fdata->open_count--;
 }
 
 static inline
-int dfl_feature_dev_use_count(struct dfl_feature_platform_data *pdata)
+int dfl_feature_dev_use_count(struct dfl_feature_dev_data *fdata)
 {
-	return pdata->open_count;
+	return fdata->open_count;
 }
 
 static inline
-void dfl_fpga_pdata_set_private(struct dfl_feature_platform_data *pdata,
+void dfl_fpga_fdata_set_private(struct dfl_feature_dev_data *fdata,
 				void *private)
 {
-	pdata->private = private;
+	fdata->private = private;
 }
 
 static inline
-void *dfl_fpga_pdata_get_private(struct dfl_feature_platform_data *pdata)
+void *dfl_fpga_fdata_get_private(struct dfl_feature_dev_data *fdata)
 {
-	return pdata->private;
+	return fdata->private;
 }
 
 struct dfl_feature_ops {
@@ -398,37 +420,36 @@ int dfl_fpga_dev_ops_register(struct platform_device *pdev,
 			      struct module *owner);
 void dfl_fpga_dev_ops_unregister(struct platform_device *pdev);
 
-static inline
-struct platform_device *dfl_fpga_inode_to_feature_dev(struct inode *inode)
+static inline struct dfl_feature_dev_data *
+dfl_fpga_inode_to_feature_dev_data(struct inode *inode)
 {
 	struct dfl_feature_platform_data *pdata;
 
 	pdata = container_of(inode->i_cdev, struct dfl_feature_platform_data,
 			     cdev);
-	return pdata->dev;
+	return pdata->fdata;
 }
 
-#define dfl_fpga_dev_for_each_feature(pdata, feature)			    \
-	for ((feature) = (pdata)->features;				    \
-	   (feature) < (pdata)->features + (pdata)->num; (feature)++)
+#define dfl_fpga_dev_for_each_feature(fdata, feature)			    \
+	for ((feature) = (fdata)->features;				    \
+	   (feature) < (fdata)->features + (fdata)->num; (feature)++)
 
-static inline
-struct dfl_feature *dfl_get_feature_by_id(struct device *dev, u16 id)
+static inline struct dfl_feature *
+dfl_get_feature_by_id(struct dfl_feature_dev_data *fdata, u16 id)
 {
-	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
 	struct dfl_feature *feature;
 
-	dfl_fpga_dev_for_each_feature(pdata, feature)
+	dfl_fpga_dev_for_each_feature(fdata, feature)
 		if (feature->id == id)
 			return feature;
 
 	return NULL;
 }
 
-static inline
-void __iomem *dfl_get_feature_ioaddr_by_id(struct device *dev, u16 id)
+static inline void __iomem *
+dfl_get_feature_ioaddr_by_id(struct dfl_feature_dev_data *fdata, u16 id)
 {
-	struct dfl_feature *feature = dfl_get_feature_by_id(dev, id);
+	struct dfl_feature *feature = dfl_get_feature_by_id(fdata, id);
 
 	if (feature && feature->ioaddr)
 		return feature->ioaddr;
@@ -437,10 +458,18 @@ void __iomem *dfl_get_feature_ioaddr_by_id(struct device *dev, u16 id)
 	return NULL;
 }
 
+static inline struct dfl_feature_dev_data *
+to_dfl_feature_dev_data(struct device *dev)
+{
+	struct dfl_feature_platform_data *pdata = dev_get_platdata(dev);
+
+	return pdata->fdata;
+}
+
 static inline
-struct device *dfl_fpga_pdata_to_parent(struct dfl_feature_platform_data *pdata)
+struct device *dfl_fpga_fdata_to_parent(struct dfl_feature_dev_data *fdata)
 {
-	return pdata->dev->dev.parent->parent;
+	return fdata->dev->dev.parent->parent;
 }
 
 static inline bool dfl_feature_is_fme(void __iomem *base)
@@ -522,26 +551,21 @@ struct dfl_fpga_cdev *
 dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info);
 void dfl_fpga_feature_devs_remove(struct dfl_fpga_cdev *cdev);
 
-/*
- * need to drop the device reference with put_device() after use port platform
- * device returned by __dfl_fpga_cdev_find_port and dfl_fpga_cdev_find_port
- * functions.
- */
-struct platform_device *
-__dfl_fpga_cdev_find_port(struct dfl_fpga_cdev *cdev, void *data,
-			  int (*match)(struct platform_device *, void *));
+struct dfl_feature_dev_data *
+__dfl_fpga_cdev_find_port_data(struct dfl_fpga_cdev *cdev, void *data,
+			       int (*match)(struct dfl_feature_dev_data *, void *));
 
-static inline struct platform_device *
-dfl_fpga_cdev_find_port(struct dfl_fpga_cdev *cdev, void *data,
-			int (*match)(struct platform_device *, void *))
+static inline struct dfl_feature_dev_data *
+dfl_fpga_cdev_find_port_data(struct dfl_fpga_cdev *cdev, void *data,
+			     int (*match)(struct dfl_feature_dev_data *, void *))
 {
-	struct platform_device *pdev;
+	struct dfl_feature_dev_data *fdata;
 
 	mutex_lock(&cdev->lock);
-	pdev = __dfl_fpga_cdev_find_port(cdev, data, match);
+	fdata = __dfl_fpga_cdev_find_port_data(cdev, data, match);
 	mutex_unlock(&cdev->lock);
 
-	return pdev;
+	return fdata;
 }
 
 int dfl_fpga_cdev_release_port(struct dfl_fpga_cdev *cdev, int port_id);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index add5ad29a673..98b4d1633b25 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -338,6 +338,7 @@ config GPIO_GRANITERAPIDS
 
 config GPIO_GRGPIO
 	tristate "Aeroflex Gaisler GRGPIO support"
+	depends on OF || COMPILE_TEST
 	select GPIO_GENERIC
 	select IRQ_DOMAIN
 	help
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 4cb455b2bdee..619b6fb9d833 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -490,8 +490,7 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 	port->gc.request = mxc_gpio_request;
 	port->gc.free = mxc_gpio_free;
 	port->gc.to_irq = mxc_gpio_to_irq;
-	port->gc.base = (pdev->id < 0) ? of_alias_get_id(np, "gpio") * 32 :
-					     pdev->id * 32;
+	port->gc.base = of_alias_get_id(np, "gpio") * 32;
 
 	err = devm_gpiochip_add_data(&pdev->dev, &port->gc, port);
 	if (err)
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index be4c9981ebc4..d63c1030e6ac 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -841,25 +841,6 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin
 	DECLARE_BITMAP(trigger, MAX_LINE);
 	int ret;
 
-	if (chip->driver_data & PCA_PCAL) {
-		/* Read the current interrupt status from the device */
-		ret = pca953x_read_regs(chip, PCAL953X_INT_STAT, trigger);
-		if (ret)
-			return false;
-
-		/* Check latched inputs and clear interrupt status */
-		ret = pca953x_read_regs(chip, chip->regs->input, cur_stat);
-		if (ret)
-			return false;
-
-		/* Apply filter for rising/falling edge selection */
-		bitmap_replace(new_stat, chip->irq_trig_fall, chip->irq_trig_raise, cur_stat, gc->ngpio);
-
-		bitmap_and(pending, new_stat, trigger, gc->ngpio);
-
-		return !bitmap_empty(pending, gc->ngpio);
-	}
-
 	ret = pca953x_read_regs(chip, chip->regs->input, cur_stat);
 	if (ret)
 		return false;
diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c
index 686ae3d11ba3..b6c230fab840 100644
--- a/drivers/gpio/gpio-sim.c
+++ b/drivers/gpio/gpio-sim.c
@@ -413,11 +413,6 @@ static int gpio_sim_setup_sysfs(struct gpio_sim_chip *chip)
 	return devm_add_action_or_reset(dev, gpio_sim_sysfs_remove, chip);
 }
 
-static int gpio_sim_dev_match_fwnode(struct device *dev, void *data)
-{
-	return device_match_fwnode(dev, data);
-}
-
 static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev)
 {
 	struct gpio_sim_chip *chip;
@@ -503,7 +498,7 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev)
 	if (ret)
 		return ret;
 
-	chip->dev = device_find_child(dev, swnode, gpio_sim_dev_match_fwnode);
+	chip->dev = device_find_child(dev, swnode, device_match_fwnode);
 	if (!chip->dev)
 		return -ENODEV;
 
@@ -1033,20 +1028,23 @@ gpio_sim_device_lockup_configfs(struct gpio_sim_device *dev, bool lock)
 	struct configfs_subsystem *subsys = dev->group.cg_subsys;
 	struct gpio_sim_bank *bank;
 	struct gpio_sim_line *line;
+	struct config_item *item;
 
 	/*
-	 * The device only needs to depend on leaf line entries. This is
+	 * The device only needs to depend on leaf entries. This is
 	 * sufficient to lock up all the configfs entries that the
 	 * instantiated, alive device depends on.
 	 */
 	list_for_each_entry(bank, &dev->bank_list, siblings) {
 		list_for_each_entry(line, &bank->line_list, siblings) {
+			item = line->hog ? &line->hog->item
+					 : &line->group.cg_item;
+
 			if (lock)
-				WARN_ON(configfs_depend_item_unlocked(
-						subsys, &line->group.cg_item));
+				WARN_ON(configfs_depend_item_unlocked(subsys,
+								      item));
 			else
-				configfs_undepend_item_unlocked(
-						&line->group.cg_item);
+				configfs_undepend_item_unlocked(item);
 		}
 	}
 }
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2f51546b0b88..fbef3f471bd0 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -294,6 +294,7 @@ config DRM_TTM_HELPER
 	tristate
 	depends on DRM
 	select DRM_TTM
+	select DRM_KMS_HELPER if DRM_FBDEV_EMULATION
 	select FB_CORE if DRM_FBDEV_EMULATION
 	select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION
 	help
@@ -302,6 +303,7 @@ config DRM_TTM_HELPER
 config DRM_GEM_DMA_HELPER
 	tristate
 	depends on DRM
+	select DRM_KMS_HELPER if DRM_FBDEV_EMULATION
 	select FB_CORE if DRM_FBDEV_EMULATION
 	select FB_DMAMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION
 	help
@@ -310,6 +312,7 @@ config DRM_GEM_DMA_HELPER
 config DRM_GEM_SHMEM_HELPER
 	tristate
 	depends on DRM && MMU
+	select DRM_KMS_HELPER if DRM_FBDEV_EMULATION
 	select FB_CORE if DRM_FBDEV_EMULATION
 	select FB_SYSMEM_HELPERS_DEFERRED if DRM_FBDEV_EMULATION
 	help
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 36053b3d48b3..d100bb7a137c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2365,8 +2365,8 @@ int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
 		break;
 	}
 
-	DRM_INFO("add ip block number %d <%s>\n", adev->num_ip_blocks,
-		  ip_block_version->funcs->name);
+	dev_info(adev->dev, "detected ip block number %d <%s>\n",
+		 adev->num_ip_blocks, ip_block_version->funcs->name);
 
 	adev->ip_blocks[adev->num_ip_blocks].adev = adev;
 
@@ -6158,6 +6158,44 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev,
 }
 
 /**
+ * amdgpu_device_gpu_bandwidth - find the bandwidth of the GPU
+ *
+ * @adev: amdgpu_device pointer
+ * @speed: pointer to the speed of the link
+ * @width: pointer to the width of the link
+ *
+ * Evaluate the hierarchy to find the speed and bandwidth capabilities of the
+ * AMD dGPU which may be a virtual upstream bridge.
+ */
+static void amdgpu_device_gpu_bandwidth(struct amdgpu_device *adev,
+					enum pci_bus_speed *speed,
+					enum pcie_link_width *width)
+{
+	struct pci_dev *parent = adev->pdev;
+
+	if (!speed || !width)
+		return;
+
+	parent = pci_upstream_bridge(parent);
+	if (parent && parent->vendor == PCI_VENDOR_ID_ATI) {
+		/* use the upstream/downstream switches internal to dGPU */
+		*speed = pcie_get_speed_cap(parent);
+		*width = pcie_get_width_cap(parent);
+		while ((parent = pci_upstream_bridge(parent))) {
+			if (parent->vendor == PCI_VENDOR_ID_ATI) {
+				/* use the upstream/downstream switches internal to dGPU */
+				*speed = pcie_get_speed_cap(parent);
+				*width = pcie_get_width_cap(parent);
+			}
+		}
+	} else {
+		/* use the device itself */
+		*speed = pcie_get_speed_cap(adev->pdev);
+		*width = pcie_get_width_cap(adev->pdev);
+	}
+}
+
+/**
  * amdgpu_device_get_pcie_info - fence pcie info about the PCIE slot
  *
  * @adev: amdgpu_device pointer
@@ -6168,9 +6206,8 @@ static void amdgpu_device_partner_bandwidth(struct amdgpu_device *adev,
  */
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 {
-	struct pci_dev *pdev;
 	enum pci_bus_speed speed_cap, platform_speed_cap;
-	enum pcie_link_width platform_link_width;
+	enum pcie_link_width platform_link_width, link_width;
 
 	if (amdgpu_pcie_gen_cap)
 		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
@@ -6192,11 +6229,10 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 
 	amdgpu_device_partner_bandwidth(adev, &platform_speed_cap,
 					&platform_link_width);
+	amdgpu_device_gpu_bandwidth(adev, &speed_cap, &link_width);
 
 	if (adev->pm.pcie_gen_mask == 0) {
 		/* asic caps */
-		pdev = adev->pdev;
-		speed_cap = pcie_get_speed_cap(pdev);
 		if (speed_cap == PCI_SPEED_UNKNOWN) {
 			adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
@@ -6252,51 +6288,103 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 		}
 	}
 	if (adev->pm.pcie_mlw_mask == 0) {
+		/* asic caps */
+		if (link_width == PCIE_LNK_WIDTH_UNKNOWN) {
+			adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_ASIC_PCIE_MLW_MASK;
+		} else {
+			switch (link_width) {
+			case PCIE_LNK_X32:
+				adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X32 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case PCIE_LNK_X16:
+				adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case PCIE_LNK_X12:
+				adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case PCIE_LNK_X8:
+				adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case PCIE_LNK_X4:
+				adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case PCIE_LNK_X2:
+				adev->pm.pcie_mlw_mask |= (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1);
+				break;
+			case PCIE_LNK_X1:
+				adev->pm.pcie_mlw_mask |= CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1;
+				break;
+			default:
+				break;
+			}
+		}
+		/* platform caps */
 		if (platform_link_width == PCIE_LNK_WIDTH_UNKNOWN) {
 			adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		} else {
 			switch (platform_link_width) {
 			case PCIE_LNK_X32:
-				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
 			case PCIE_LNK_X16:
-				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
 			case PCIE_LNK_X12:
-				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
 			case PCIE_LNK_X8:
-				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
 			case PCIE_LNK_X4:
-				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
 			case PCIE_LNK_X2:
-				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
-							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
+				adev->pm.pcie_mlw_mask |= (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
+							   CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
 			case PCIE_LNK_X1:
-				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
+				adev->pm.pcie_mlw_mask |= CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
 				break;
 			default:
 				break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 492b09d84571..dce9323fb410 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -119,9 +119,10 @@
  * - 3.57.0 - Compute tunneling on GFX10+
  * - 3.58.0 - Add GFX12 DCC support
  * - 3.59.0 - Cleared VRAM
+ * - 3.60.0 - Add AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE (Vulkan requirement)
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	59
+#define KMS_DRIVER_MINOR	60
 #define KMS_DRIVER_PATCHLEVEL	0
 
 /*
@@ -280,7 +281,7 @@ module_param_named(gartsize, amdgpu_gart_size, uint, 0600);
 /**
  * DOC: gttsize (int)
  * Restrict the size of GTT domain (for userspace use) in MiB for testing.
- * The default is -1 (Use 1/2 RAM, minimum value is 3GB).
+ * The default is -1 (Use value specified by TTM).
  */
 MODULE_PARM_DESC(gttsize, "Size of the GTT userspace domain in megabytes (-1 = auto)");
 module_param_named(gttsize, amdgpu_gtt_size, int, 0600);
@@ -399,7 +400,7 @@ module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
  * the kernel log for the list of IPs on the asic. The default is 0xffffffff (enable all blocks on a device).
  */
 MODULE_PARM_DESC(ip_block_mask, "IP Block Mask (all blocks enabled (default))");
-module_param_named(ip_block_mask, amdgpu_ip_block_mask, uint, 0444);
+module_param_named_unsafe(ip_block_mask, amdgpu_ip_block_mask, uint, 0444);
 
 /**
  * DOC: bapm (int)
@@ -457,7 +458,7 @@ module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444);
  * Enable experimental hw support (1 = enable). The default is 0 (disabled).
  */
 MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))");
-module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
+module_param_named_unsafe(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
 
 /**
  * DOC: dc (int)
@@ -568,14 +569,14 @@ module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
  * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV).
  */
 MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)");
-module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
+module_param_named_unsafe(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
 
 /**
  * DOC: emu_mode (int)
  * Set value 1 to enable emulation mode. This is only needed when running on an emulator. The default is 0 (disabled).
  */
 MODULE_PARM_DESC(emu_mode, "Emulation mode, (1 = enable, 0 = disable)");
-module_param_named(emu_mode, amdgpu_emu_mode, int, 0444);
+module_param_named_unsafe(emu_mode, amdgpu_emu_mode, int, 0444);
 
 /**
  * DOC: ras_enable (int)
@@ -730,7 +731,7 @@ module_param_named(noretry, amdgpu_noretry, int, 0644);
  */
 MODULE_PARM_DESC(force_asic_type,
 	"A non negative value used to specify the asic type for all supported GPUs");
-module_param_named(force_asic_type, amdgpu_force_asic_type, int, 0444);
+module_param_named_unsafe(force_asic_type, amdgpu_force_asic_type, int, 0444);
 
 /**
  * DOC: use_xgmi_p2p (int)
@@ -749,7 +750,7 @@ module_param_named(use_xgmi_p2p, amdgpu_use_xgmi_p2p, int, 0444);
  * assigns queues to HQDs.
  */
 int sched_policy = KFD_SCHED_POLICY_HWS;
-module_param(sched_policy, int, 0444);
+module_param_unsafe(sched_policy, int, 0444);
 MODULE_PARM_DESC(sched_policy,
 	"Scheduling policy (0 = HWS (Default), 1 = HWS without over-subscription, 2 = Non-HWS (Used for debugging only)");
 
@@ -799,7 +800,7 @@ MODULE_PARM_DESC(send_sigterm,
  * Setting 1 enables halt on hang.
  */
 int halt_if_hws_hang;
-module_param(halt_if_hws_hang, int, 0644);
+module_param_unsafe(halt_if_hws_hang, int, 0644);
 MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
 
 /**
@@ -808,7 +809,7 @@ MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (defau
  * check says. Default value: false (rely on MEC2 firmware version check).
  */
 bool hws_gws_support;
-module_param(hws_gws_support, bool, 0444);
+module_param_unsafe(hws_gws_support, bool, 0444);
 MODULE_PARM_DESC(hws_gws_support, "Assume MEC2 FW supports GWS barriers (false = rely on FW version check (Default), true = force supported)");
 
 /**
@@ -841,7 +842,7 @@ MODULE_PARM_DESC(no_system_mem_limit, "disable system memory limit (false = defa
  */
 int amdgpu_no_queue_eviction_on_vm_fault;
 MODULE_PARM_DESC(no_queue_eviction_on_vm_fault, "No queue eviction on VM fault (0 = queue eviction, 1 = no queue eviction)");
-module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm_fault, int, 0444);
+module_param_named_unsafe(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm_fault, int, 0444);
 #endif
 
 /**
@@ -849,7 +850,7 @@ module_param_named(no_queue_eviction_on_vm_fault, amdgpu_no_queue_eviction_on_vm
  */
 int amdgpu_mtype_local;
 MODULE_PARM_DESC(mtype_local, "MTYPE for local memory (0 = MTYPE_RW (default), 1 = MTYPE_NC, 2 = MTYPE_CC)");
-module_param_named(mtype_local, amdgpu_mtype_local, int, 0444);
+module_param_named_unsafe(mtype_local, amdgpu_mtype_local, int, 0444);
 
 /**
  * DOC: pcie_p2p (bool)
@@ -953,7 +954,7 @@ module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
  * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
  */
 MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco/bamaco)");
-module_param_named(reset_method, amdgpu_reset_method, int, 0644);
+module_param_named_unsafe(reset_method, amdgpu_reset_method, int, 0644);
 
 /**
  * DOC: bad_page_threshold (int) Bad page threshold is specifies the
@@ -1049,7 +1050,7 @@ module_param_named(seamless, amdgpu_seamless, int, 0444);
  * - 0x4: Disable GPU soft recovery, always do a full reset
  */
 MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default");
-module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444);
+module_param_named_unsafe(debug_mask, amdgpu_debug_mask, uint, 0444);
 
 /**
  * DOC: agp (int)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index e0bc37557d2c..2ea98ec60220 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -297,7 +297,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
 	amdgpu_ring_patch_cond_exec(ring, cond_exec);
 
 	ring->current_ctx = fence_ctx;
-	if (vm && ring->funcs->emit_switch_buffer)
+	if (job && ring->funcs->emit_switch_buffer)
 		amdgpu_ring_emit_switch_buffer(ring);
 
 	if (ring->funcs->emit_wave_limit &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 016a6f6c4267..98528ee94c15 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -846,7 +846,7 @@ out:
 	case AMDGPU_INFO_DEV_INFO: {
 		struct drm_amdgpu_info_device *dev_info;
 		uint64_t vm_size;
-		uint32_t pcie_gen_mask;
+		uint32_t pcie_gen_mask, pcie_width_mask;
 
 		dev_info = kzalloc(sizeof(*dev_info), GFP_KERNEL);
 		if (!dev_info)
@@ -934,15 +934,18 @@ out:
 		dev_info->tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask;
 
 		/* Combine the chip gen mask with the platform (CPU/mobo) mask. */
-		pcie_gen_mask = adev->pm.pcie_gen_mask & (adev->pm.pcie_gen_mask >> 16);
+		pcie_gen_mask = adev->pm.pcie_gen_mask &
+			(adev->pm.pcie_gen_mask >> CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT);
+		pcie_width_mask = adev->pm.pcie_mlw_mask &
+			(adev->pm.pcie_mlw_mask >> CAIL_PCIE_LINK_WIDTH_SUPPORT_SHIFT);
 		dev_info->pcie_gen = fls(pcie_gen_mask);
 		dev_info->pcie_num_lanes =
-			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 ? 32 :
-			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 ? 16 :
-			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 ? 12 :
-			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 ? 8 :
-			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 :
-			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1;
+			pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X32 ? 32 :
+			pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16 ? 16 :
+			pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12 ? 12 :
+			pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 ? 8 :
+			pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 :
+			pcie_width_mask & CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1;
 
 		dev_info->tcp_cache_size = adev->gfx.config.gc_tcp_l1_size;
 		dev_info->num_sqc_per_wgp = adev->gfx.config.gc_num_sqc_per_wgp;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index c6f93cbd6739..2df2444ee892 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -40,7 +40,7 @@
 #define AMDGPU_MES_VERSION_MASK		0x00000fff
 #define AMDGPU_MES_API_VERSION_MASK	0x00fff000
 #define AMDGPU_MES_FEAT_VERSION_MASK	0xff000000
-#define AMDGPU_MES_MSCRATCH_SIZE	0x8000
+#define AMDGPU_MES_MSCRATCH_SIZE	0x40000
 
 enum amdgpu_mes_priority_level {
 	AMDGPU_MES_PRIORITY_LEVEL_LOW       = 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index 2db58b5812a8..5f60736051d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -107,6 +107,7 @@ struct amdgpu_sdma {
 	struct amdgpu_irq_src	doorbell_invalid_irq;
 	struct amdgpu_irq_src	pool_timeout_irq;
 	struct amdgpu_irq_src	srbm_write_irq;
+	struct amdgpu_irq_src	ctxt_empty_irq;
 
 	int			num_instances;
 	uint32_t 		sdma_mask;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index ff286940ab43..01ae2f88dec8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -309,7 +309,7 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
 	mutex_lock(&adev->mman.gtt_window_lock);
 	while (src_mm.remaining) {
 		uint64_t from, to, cur_size, tiling_flags;
-		uint32_t num_type, data_format, max_com;
+		uint32_t num_type, data_format, max_com, write_compress_disable;
 		struct dma_fence *next;
 
 		/* Never copy more than 256MiB at once to avoid a timeout */
@@ -340,9 +340,13 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev,
 			max_com = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_MAX_COMPRESSED_BLOCK);
 			num_type = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_NUMBER_TYPE);
 			data_format = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_DATA_FORMAT);
+			write_compress_disable =
+				AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_WRITE_COMPRESS_DISABLE);
 			copy_flags |= (AMDGPU_COPY_FLAGS_SET(MAX_COMPRESSED, max_com) |
 				       AMDGPU_COPY_FLAGS_SET(NUMBER_TYPE, num_type) |
-				       AMDGPU_COPY_FLAGS_SET(DATA_FORMAT, data_format));
+				       AMDGPU_COPY_FLAGS_SET(DATA_FORMAT, data_format) |
+				       AMDGPU_COPY_FLAGS_SET(WRITE_COMPRESS_DISABLE,
+							     write_compress_disable));
 		}
 
 		r = amdgpu_copy_buffer(ring, from, to, cur_size, resv,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 461fb8090ae0..208b7d1d8a27 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -119,6 +119,8 @@ struct amdgpu_copy_mem {
 #define AMDGPU_COPY_FLAGS_NUMBER_TYPE_MASK		0x07
 #define AMDGPU_COPY_FLAGS_DATA_FORMAT_SHIFT		8
 #define AMDGPU_COPY_FLAGS_DATA_FORMAT_MASK		0x3f
+#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_SHIFT	14
+#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_MASK	0x1
 
 #define AMDGPU_COPY_FLAGS_SET(field, value) \
 	(((__u32)(value) & AMDGPU_COPY_FLAGS_##field##_MASK) << AMDGPU_COPY_FLAGS_##field##_SHIFT)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index e209b5e101df..23b6f7a4aa4a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -427,7 +427,7 @@ void amdgpu_xcp_release_sched(struct amdgpu_device *adev,
 		return;
 
 	sched = entity->entity.rq->sched;
-	if (sched->ready) {
+	if (drm_sched_wqueue_ready(sched)) {
 		ring = to_amdgpu_ring(entity->entity.rq->sched);
 		atomic_dec(&adev->xcp_mgr->xcp[ring->xcp_id].ref_cnt);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 4b6e05750654..2523221a2519 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -1352,6 +1352,14 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block)
 	}
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(12, 0, 0):
+	case IP_VERSION(12, 0, 1):
+		if (adev->gfx.me_fw_version  >= 2480 &&
+		    adev->gfx.pfp_fw_version >= 2530 &&
+		    adev->gfx.mec_fw_version >= 2680 &&
+		    adev->mes.fw_version[0] >= 100)
+			adev->gfx.enable_cleaner_shader = true;
+		break;
 	default:
 		adev->gfx.enable_cleaner_shader = false;
 		break;
@@ -4013,17 +4021,6 @@ static void gfx_v12_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 
 		if (def != data)
 			WREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL_3D, data);
-
-		data = RREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL);
-		data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
-		WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
-
-		/* Some ASICs only have one SDMA instance, not need to configure SDMA1 */
-		if (adev->sdma.num_instances > 1) {
-			data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL);
-			data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK;
-			WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data);
-		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 5b537806b4da..901e924e69ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -756,7 +756,8 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
-		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr + pipe * AMDGPU_MES_LOG_BUFFER_SIZE;
+		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr +
+				pipe * (AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE);
 	}
 
 	if (enforce_isolation)
@@ -983,29 +984,50 @@ static void mes_v12_0_enable(struct amdgpu_device *adev, bool enable)
 	uint32_t pipe, data = 0;
 
 	if (enable) {
-		data = RREG32_SOC15(GC, 0, regCP_MES_CNTL);
-		data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1);
-		data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1);
-		WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
-
 		mutex_lock(&adev->srbm_mutex);
 		for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
 			soc21_grbm_select(adev, 3, pipe, 0, 0);
+			if (amdgpu_mes_log_enable) {
+				u32 log_size = AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE;
+				/* In case uni mes is not enabled, only program for pipe 0 */
+				if (adev->mes.event_log_size >= (pipe + 1) * log_size) {
+					WREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_LO,
+						     lower_32_bits(adev->mes.event_log_gpu_addr +
+						     pipe * log_size + AMDGPU_MES_LOG_BUFFER_SIZE));
+					WREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_HI,
+						     upper_32_bits(adev->mes.event_log_gpu_addr +
+						     pipe * log_size + AMDGPU_MES_LOG_BUFFER_SIZE));
+					dev_info(adev->dev, "Setup CP MES MSCRATCH address : 0x%x. 0x%x\n",
+						 RREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_HI),
+						 RREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_LO));
+				}
+			}
+
+			data = RREG32_SOC15(GC, 0, regCP_MES_CNTL);
+			if (pipe == 0)
+				data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1);
+			else
+				data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_RESET, 1);
+			WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
 
 			ucode_addr = adev->mes.uc_start_addr[pipe] >> 2;
 			WREG32_SOC15(GC, 0, regCP_MES_PRGRM_CNTR_START,
 				     lower_32_bits(ucode_addr));
 			WREG32_SOC15(GC, 0, regCP_MES_PRGRM_CNTR_START_HI,
 				     upper_32_bits(ucode_addr));
+
+			/* unhalt MES and activate one pipe each loop */
+			data = REG_SET_FIELD(0, CP_MES_CNTL, MES_PIPE0_ACTIVE, 1);
+			if (pipe)
+				data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, 1);
+			dev_info(adev->dev, "program CP_MES_CNTL : 0x%x\n", data);
+
+			WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
+
 		}
 		soc21_grbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 
-		/* unhalt MES and activate pipe0 */
-		data = REG_SET_FIELD(0, CP_MES_CNTL, MES_PIPE0_ACTIVE, 1);
-		data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE1_ACTIVE, 1);
-		WREG32_SOC15(GC, 0, regCP_MES_CNTL, data);
-
 		if (amdgpu_emu_mode)
 			msleep(100);
 		else if (adev->enable_uni_mes)
@@ -1479,8 +1501,9 @@ static int mes_v12_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->mes.kiq_hw_fini = &mes_v12_0_kiq_hw_fini;
 	adev->mes.enable_legacy_queue_map = true;
 
-	adev->mes.event_log_size = adev->enable_uni_mes ? (AMDGPU_MAX_MES_PIPES * AMDGPU_MES_LOG_BUFFER_SIZE) : AMDGPU_MES_LOG_BUFFER_SIZE;
-
+	adev->mes.event_log_size = adev->enable_uni_mes ?
+		(AMDGPU_MAX_MES_PIPES * (AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE)) :
+		(AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE);
 	r = amdgpu_mes_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 48537eba225d..5e0066cd6c51 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1406,6 +1406,12 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 				      &adev->sdma.srbm_write_irq);
 		if (r)
 			return r;
+
+		r = amdgpu_irq_add_id(adev, sdma_v4_4_2_seq_to_irq_id(i),
+				      SDMA0_4_0__SRCID__SDMA_CTXEMPTY,
+				      &adev->sdma.ctxt_empty_irq);
+		if (r)
+			return r;
 	}
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -1814,6 +1820,16 @@ static int sdma_v4_4_2_process_srbm_write_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int sdma_v4_4_2_process_ctxt_empty_irq(struct amdgpu_device *adev,
+					      struct amdgpu_irq_src *source,
+					      struct amdgpu_iv_entry *entry)
+{
+	/* There is nothing useful to be done here, only kept for debug */
+	dev_dbg_ratelimited(adev->dev, "SDMA context empty interrupt");
+	sdma_v4_4_2_print_iv_entry(adev, entry);
+	return 0;
+}
+
 static void sdma_v4_4_2_inst_update_medium_grain_light_sleep(
 	struct amdgpu_device *adev, bool enable, uint32_t inst_mask)
 {
@@ -2096,6 +2112,10 @@ static const struct amdgpu_irq_src_funcs sdma_v4_4_2_srbm_write_irq_funcs = {
 	.process = sdma_v4_4_2_process_srbm_write_irq,
 };
 
+static const struct amdgpu_irq_src_funcs sdma_v4_4_2_ctxt_empty_irq_funcs = {
+	.process = sdma_v4_4_2_process_ctxt_empty_irq,
+};
+
 static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->sdma.trap_irq.num_types = adev->sdma.num_instances;
@@ -2104,6 +2124,7 @@ static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev)
 	adev->sdma.doorbell_invalid_irq.num_types = adev->sdma.num_instances;
 	adev->sdma.pool_timeout_irq.num_types = adev->sdma.num_instances;
 	adev->sdma.srbm_write_irq.num_types = adev->sdma.num_instances;
+	adev->sdma.ctxt_empty_irq.num_types = adev->sdma.num_instances;
 
 	adev->sdma.trap_irq.funcs = &sdma_v4_4_2_trap_irq_funcs;
 	adev->sdma.illegal_inst_irq.funcs = &sdma_v4_4_2_illegal_inst_irq_funcs;
@@ -2112,6 +2133,7 @@ static void sdma_v4_4_2_set_irq_funcs(struct amdgpu_device *adev)
 	adev->sdma.doorbell_invalid_irq.funcs = &sdma_v4_4_2_doorbell_invalid_irq_funcs;
 	adev->sdma.pool_timeout_irq.funcs = &sdma_v4_4_2_pool_timeout_irq_funcs;
 	adev->sdma.srbm_write_irq.funcs = &sdma_v4_4_2_srbm_write_irq_funcs;
+	adev->sdma.ctxt_empty_irq.funcs = &sdma_v4_4_2_ctxt_empty_irq_funcs;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index 9c17df2cf37b..7e10e94624e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -1741,11 +1741,12 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib,
 				       uint32_t byte_count,
 				       uint32_t copy_flags)
 {
-	uint32_t num_type, data_format, max_com;
+	uint32_t num_type, data_format, max_com, write_cm;
 
 	max_com = AMDGPU_COPY_FLAGS_GET(copy_flags, MAX_COMPRESSED);
 	data_format = AMDGPU_COPY_FLAGS_GET(copy_flags, DATA_FORMAT);
 	num_type = AMDGPU_COPY_FLAGS_GET(copy_flags, NUMBER_TYPE);
+	write_cm = AMDGPU_COPY_FLAGS_GET(copy_flags, WRITE_COMPRESS_DISABLE) ? 2 : 1;
 
 	ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) |
 		SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) |
@@ -1762,7 +1763,7 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib,
 	if ((copy_flags & (AMDGPU_COPY_FLAGS_READ_DECOMPRESSED | AMDGPU_COPY_FLAGS_WRITE_COMPRESSED)))
 		ib->ptr[ib->length_dw++] = SDMA_DCC_DATA_FORMAT(data_format) | SDMA_DCC_NUM_TYPE(num_type) |
 			((copy_flags & AMDGPU_COPY_FLAGS_READ_DECOMPRESSED) ? SDMA_DCC_READ_CM(2) : 0) |
-			((copy_flags & AMDGPU_COPY_FLAGS_WRITE_COMPRESSED) ? SDMA_DCC_WRITE_CM(1) : 0) |
+			((copy_flags & AMDGPU_COPY_FLAGS_WRITE_COMPRESSED) ? SDMA_DCC_WRITE_CM(write_cm) : 0) |
 			SDMA_DCC_MAX_COM(max_com) | SDMA_DCC_MAX_UCOM(1);
 	else
 		ib->ptr[ib->length_dw++] = 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index 388b44ed5928..984f0e705078 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -274,7 +274,7 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 
 
 static const uint32_t cwsr_trap_gfx9_hex[] = {
-	0xbf820001, 0xbf820258,
+	0xbf820001, 0xbf820259,
 	0xb8f8f802, 0x8978ff78,
 	0x00020006, 0xb8fbf803,
 	0x866eff78, 0x00002000,
@@ -390,141 +390,98 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0xbefe007c, 0xbefc0070,
 	0xc0611c7a, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
-	0xbefc007e, 0x867aff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f7a, 0xb8f02a05,
-	0x80708170, 0x8e708a70,
-	0xb8fb1605, 0x807b817b,
-	0x8e7b847b, 0x8e76827b,
-	0xbef600ff, 0x01000000,
-	0xbef20174, 0x80747074,
-	0x82758075, 0xbefc0080,
-	0xbf800000, 0xbe802b00,
-	0xbe822b02, 0xbe842b04,
-	0xbe862b06, 0xbe882b08,
-	0xbe8a2b0a, 0xbe8c2b0c,
-	0xbe8e2b0e, 0xc06b003a,
-	0x00000000, 0xbf8cc07f,
-	0xc06b013a, 0x00000010,
-	0xbf8cc07f, 0xc06b023a,
-	0x00000020, 0xbf8cc07f,
-	0xc06b033a, 0x00000030,
-	0xbf8cc07f, 0x8074c074,
-	0x82758075, 0x807c907c,
-	0xbf0a7b7c, 0xbf85ffe7,
-	0xbef40172, 0xbef00080,
-	0xbefe00c1, 0xbeff00c1,
-	0xbee80080, 0xbee90080,
-	0xbef600ff, 0x01000000,
-	0x867aff78, 0x00400000,
-	0xbf850003, 0xb8faf803,
-	0x897a7aff, 0x10000000,
-	0xbf85004d, 0xbe840080,
-	0xd2890000, 0x00000900,
-	0x80048104, 0xd2890001,
-	0x00000900, 0x80048104,
-	0xd2890002, 0x00000900,
-	0x80048104, 0xd2890003,
-	0x00000900, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
+	0xbefc007e, 0xbf108080,
+	0x867aff7f, 0x04000000,
+	0xbeef0080, 0x876f6f7a,
+	0xb8f02a05, 0x80708170,
+	0x8e708a70, 0xb8fb1605,
+	0x807b817b, 0x8e7b847b,
+	0x8e76827b, 0xbef600ff,
+	0x01000000, 0xbef20174,
+	0x80747074, 0x82758075,
+	0xbefc0080, 0xbf800000,
+	0xbe802b00, 0xbe822b02,
+	0xbe842b04, 0xbe862b06,
+	0xbe882b08, 0xbe8a2b0a,
+	0xbe8c2b0c, 0xbe8e2b0e,
+	0xc06b003a, 0x00000000,
+	0xbf8cc07f, 0xc06b013a,
+	0x00000010, 0xbf8cc07f,
+	0xc06b023a, 0x00000020,
+	0xbf8cc07f, 0xc06b033a,
+	0x00000030, 0xbf8cc07f,
+	0x8074c074, 0x82758075,
+	0x807c907c, 0xbf0a7b7c,
+	0xbf85ffe7, 0xbef40172,
+	0xbef00080, 0xbefe00c1,
+	0xbeff00c1, 0xbee80080,
+	0xbee90080, 0xbef600ff,
+	0x01000000, 0x867aff78,
+	0x00400000, 0xbf850003,
+	0xb8faf803, 0x897a7aff,
+	0x10000000, 0xbf85004d,
 	0xbe840080, 0xd2890000,
-	0x00000901, 0x80048104,
-	0xd2890001, 0x00000901,
+	0x00000900, 0x80048104,
+	0xd2890001, 0x00000900,
 	0x80048104, 0xd2890002,
-	0x00000901, 0x80048104,
-	0xd2890003, 0x00000901,
+	0x00000900, 0x80048104,
+	0xd2890003, 0x00000900,
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
 	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000902,
+	0xd2890000, 0x00000901,
 	0x80048104, 0xd2890001,
-	0x00000902, 0x80048104,
-	0xd2890002, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890002, 0x00000901,
 	0x80048104, 0xd2890003,
-	0x00000902, 0x80048104,
+	0x00000901, 0x80048104,
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
 	0xbe840080, 0xd2890000,
-	0x00000903, 0x80048104,
-	0xd2890001, 0x00000903,
+	0x00000902, 0x80048104,
+	0xd2890001, 0x00000902,
 	0x80048104, 0xd2890002,
-	0x00000903, 0x80048104,
-	0xd2890003, 0x00000903,
+	0x00000902, 0x80048104,
+	0xd2890003, 0x00000902,
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbf820008,
-	0xe0724000, 0x701d0000,
-	0xe0724100, 0x701d0100,
-	0xe0724200, 0x701d0200,
-	0xe0724300, 0x701d0300,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8fb4306, 0x867bc17b,
-	0xbf840063, 0xbf8a0000,
-	0x867aff6f, 0x04000000,
-	0xbf84005f, 0x8e7b867b,
-	0x8e7b827b, 0xbef6007b,
-	0xb8f02a05, 0x80708170,
-	0x8e708a70, 0xb8fa1605,
-	0x807a817a, 0x8e7a867a,
-	0x80707a70, 0x8070ff70,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
-	0x867aff78, 0x00400000,
-	0xbf850003, 0xb8faf803,
-	0x897a7aff, 0x10000000,
-	0xbf850030, 0x24040682,
-	0xd86e4000, 0x00000002,
-	0xbf8cc07f, 0xbe840080,
-	0xd2890000, 0x00000900,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000903,
 	0x80048104, 0xd2890001,
-	0x00000900, 0x80048104,
-	0xd2890002, 0x00000900,
+	0x00000903, 0x80048104,
+	0xd2890002, 0x00000903,
 	0x80048104, 0xd2890003,
-	0x00000900, 0x80048104,
+	0x00000903, 0x80048104,
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
-	0xbe840080, 0xd2890000,
-	0x00000901, 0x80048104,
-	0xd2890001, 0x00000901,
-	0x80048104, 0xd2890002,
-	0x00000901, 0x80048104,
-	0xd2890003, 0x00000901,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0x680404ff,
-	0x00000200, 0xd0c9006a,
-	0x0000f702, 0xbf87ffd2,
-	0xbf820015, 0xd1060002,
-	0x00011103, 0x7e0602ff,
-	0x00000200, 0xbefc00ff,
-	0x00010000, 0xbe800077,
-	0x8677ff77, 0xff7fffff,
-	0x8777ff77, 0x00058000,
-	0xd8ec0000, 0x00000002,
-	0xbf8cc07f, 0xe0765000,
-	0x701d0002, 0x68040702,
-	0xd0c9006a, 0x0000f702,
-	0xbf87fff7, 0xbef70000,
-	0xbef000ff, 0x00000400,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8fb2a05, 0x807b817b,
-	0x8e7b827b, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a7b7c, 0xbf84006d,
-	0xbf11017c, 0x807bff7b,
-	0x00001000, 0x867aff78,
+	0xbf820008, 0xe0724000,
+	0x701d0000, 0xe0724100,
+	0x701d0100, 0xe0724200,
+	0x701d0200, 0xe0724300,
+	0x701d0300, 0xbefe00c1,
+	0xbeff00c1, 0xb8fb4306,
+	0x867bc17b, 0xbf840063,
+	0xbf8a0000, 0x867aff6f,
+	0x04000000, 0xbf84005f,
+	0x8e7b867b, 0x8e7b827b,
+	0xbef6007b, 0xb8f02a05,
+	0x80708170, 0x8e708a70,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x80707a70,
+	0x8070ff70, 0x00000080,
+	0xbef600ff, 0x01000000,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0x867aff78,
 	0x00400000, 0xbf850003,
 	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf850051,
+	0x10000000, 0xbf850030,
+	0x24040682, 0xd86e4000,
+	0x00000002, 0xbf8cc07f,
 	0xbe840080, 0xd2890000,
 	0x00000900, 0x80048104,
 	0xd2890001, 0x00000900,
@@ -544,137 +501,181 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
+	0x680404ff, 0x00000200,
+	0xd0c9006a, 0x0000f702,
+	0xbf87ffd2, 0xbf820015,
+	0xd1060002, 0x00011103,
+	0x7e0602ff, 0x00000200,
+	0xbefc00ff, 0x00010000,
+	0xbe800077, 0x8677ff77,
+	0xff7fffff, 0x8777ff77,
+	0x00058000, 0xd8ec0000,
+	0x00000002, 0xbf8cc07f,
+	0xe0765000, 0x701d0002,
+	0x68040702, 0xd0c9006a,
+	0x0000f702, 0xbf87fff7,
+	0xbef70000, 0xbef000ff,
+	0x00000400, 0xbefe00c1,
+	0xbeff00c1, 0xb8fb2a05,
+	0x807b817b, 0x8e7b827b,
+	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a7b7c,
+	0xbf84006d, 0xbf11017c,
+	0x807bff7b, 0x00001000,
+	0x867aff78, 0x00400000,
+	0xbf850003, 0xb8faf803,
+	0x897a7aff, 0x10000000,
+	0xbf850051, 0xbe840080,
+	0xd2890000, 0x00000900,
+	0x80048104, 0xd2890001,
+	0x00000900, 0x80048104,
+	0xd2890002, 0x00000900,
+	0x80048104, 0xd2890003,
+	0x00000900, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
 	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890001, 0x00000901,
 	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890003, 0x00000901,
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
 	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
+	0xd2890000, 0x00000902,
 	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
+	0x00000902, 0x80048104,
+	0xd2890002, 0x00000902,
 	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
+	0x00000902, 0x80048104,
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
-	0x807c847c, 0xbf0a7b7c,
-	0xbf85ffb1, 0xbf9c0000,
-	0xbf820012, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0x807c847c,
-	0x8070ff70, 0x00000400,
-	0xbf0a7b7c, 0xbf85ffef,
-	0xbf9c0000, 0xbf8200c7,
-	0xbef4007e, 0x8675ff7f,
-	0x0000ffff, 0x8775ff75,
-	0x00040000, 0xbef60080,
-	0xbef700ff, 0x00807fac,
-	0x866eff7f, 0x04000000,
-	0xbf84001e, 0xbefe00c1,
-	0xbeff00c1, 0xb8ef4306,
-	0x866fc16f, 0xbf840019,
-	0x8e6f866f, 0x8e6f826f,
-	0xbef6006f, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0xb8ee1605, 0x806e816e,
-	0x8e6e866e, 0x80786e78,
-	0x8078ff78, 0x00000080,
-	0xbef600ff, 0x01000000,
-	0xbefc0080, 0xe0510000,
-	0x781d0000, 0xe0510100,
-	0x781d0000, 0x807cff7c,
-	0x00000200, 0x8078ff78,
-	0x00000200, 0xbf0a6f7c,
-	0xbf85fff6, 0xbefe00c1,
-	0xbeff00c1, 0xbef600ff,
-	0x01000000, 0xb8ef2a05,
-	0x806f816f, 0x8e6f826f,
-	0x806fff6f, 0x00008000,
-	0xbef80080, 0xbeee0078,
-	0x8078ff78, 0x00000400,
-	0xbefc0084, 0xbf11087c,
-	0xe0524000, 0x781d0000,
-	0xe0524100, 0x781d0100,
-	0xe0524200, 0x781d0200,
-	0xe0524300, 0x781d0300,
-	0xbf8c0f70, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0x807c847c,
-	0x8078ff78, 0x00000400,
-	0xbf0a6f7c, 0xbf85ffee,
-	0xbf9c0000, 0xe0524000,
-	0x6e1d0000, 0xe0524100,
-	0x6e1d0100, 0xe0524200,
-	0x6e1d0200, 0xe0524300,
-	0x6e1d0300, 0xbf8c0f70,
+	0xbe840080, 0xd2890000,
+	0x00000903, 0x80048104,
+	0xd2890001, 0x00000903,
+	0x80048104, 0xd2890002,
+	0x00000903, 0x80048104,
+	0xd2890003, 0x00000903,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0x807c847c,
+	0xbf0a7b7c, 0xbf85ffb1,
+	0xbf9c0000, 0xbf820012,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
+	0xe0724000, 0x701d0000,
+	0xe0724100, 0x701d0100,
+	0xe0724200, 0x701d0200,
+	0xe0724300, 0x701d0300,
+	0x807c847c, 0x8070ff70,
+	0x00000400, 0xbf0a7b7c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbf8200c7, 0xbef4007e,
+	0x8675ff7f, 0x0000ffff,
+	0x8775ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x00807fac, 0x866eff7f,
+	0x04000000, 0xbf84001e,
+	0xbefe00c1, 0xbeff00c1,
+	0xb8ef4306, 0x866fc16f,
+	0xbf840019, 0x8e6f866f,
+	0x8e6f826f, 0xbef6006f,
 	0xb8f82a05, 0x80788178,
 	0x8e788a78, 0xb8ee1605,
 	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
+	0x80786e78, 0x8078ff78,
+	0x00000080, 0xbef600ff,
+	0x01000000, 0xbefc0080,
+	0xe0510000, 0x781d0000,
+	0xe0510100, 0x781d0000,
+	0x807cff7c, 0x00000200,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7c, 0xbf85fff6,
+	0xbefe00c1, 0xbeff00c1,
 	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82a05,
+	0xb8ef2a05, 0x806f816f,
+	0x8e6f826f, 0x806fff6f,
+	0x00008000, 0xbef80080,
+	0xbeee0078, 0x8078ff78,
+	0x00000400, 0xbefc0084,
+	0xbf11087c, 0xe0524000,
+	0x781d0000, 0xe0524100,
+	0x781d0100, 0xe0524200,
+	0x781d0200, 0xe0524300,
+	0x781d0300, 0xbf8c0f70,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
+	0x807c847c, 0x8078ff78,
+	0x00000400, 0xbf0a6f7c,
+	0xbf85ffee, 0xbf9c0000,
+	0xe0524000, 0x6e1d0000,
+	0xe0524100, 0x6e1d0100,
+	0xe0524200, 0x6e1d0200,
+	0xe0524300, 0x6e1d0300,
+	0xbf8c0f70, 0xb8f82a05,
 	0x80788178, 0x8e788a78,
 	0xb8ee1605, 0x806e816e,
 	0x8e6e866e, 0x80786e78,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xc0211bfa,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0xbef60084,
+	0xbef600ff, 0x01000000,
+	0xc0211bfa, 0x00000078,
+	0x80788478, 0xc0211b3a,
 	0x00000078, 0x80788478,
-	0xc0211b3a, 0x00000078,
-	0x80788478, 0xc0211b7a,
+	0xc0211b7a, 0x00000078,
+	0x80788478, 0xc0211c3a,
 	0x00000078, 0x80788478,
-	0xc0211c3a, 0x00000078,
-	0x80788478, 0xc0211c7a,
+	0xc0211c7a, 0x00000078,
+	0x80788478, 0xc0211eba,
 	0x00000078, 0x80788478,
-	0xc0211eba, 0x00000078,
-	0x80788478, 0xc0211efa,
+	0xc0211efa, 0x00000078,
+	0x80788478, 0xc0211a3a,
 	0x00000078, 0x80788478,
-	0xc0211a3a, 0x00000078,
-	0x80788478, 0xc0211a7a,
+	0xc0211a7a, 0x00000078,
+	0x80788478, 0xc0211cfa,
 	0x00000078, 0x80788478,
-	0xc0211cfa, 0x00000078,
-	0x80788478, 0xbf8cc07f,
-	0xbefc006f, 0xbefe0070,
-	0xbeff0071, 0x866f7bff,
-	0x000003ff, 0xb96f4803,
-	0x866f7bff, 0xfffff800,
-	0x8f6f8b6f, 0xb96fa2c3,
-	0xb973f801, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc00b1c37, 0x00000050,
-	0xc00b1d37, 0x00000060,
-	0xc0031e77, 0x00000074,
-	0xbf8cc07f, 0x8f6e8b77,
-	0x866eff6e, 0x001f8000,
-	0xb96ef807, 0x866dff6d,
-	0x0000ffff, 0x86fe7e7e,
-	0x86ea6a6a, 0x8f6e837a,
-	0xb96ee0c2, 0xbf800002,
-	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf9b0000,
+	0xbf8cc07f, 0xbefc006f,
+	0xbefe0070, 0xbeff0071,
+	0x866f7bff, 0x000003ff,
+	0xb96f4803, 0x866f7bff,
+	0xfffff800, 0x8f6f8b6f,
+	0xb96fa2c3, 0xb973f801,
+	0xb8ee2a05, 0x806e816e,
+	0x8e6e8a6e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc00b1c37,
+	0x00000050, 0xc00b1d37,
+	0x00000060, 0xc0031e77,
+	0x00000074, 0xbf8cc07f,
+	0x8f6e8b77, 0x866eff6e,
+	0x001f8000, 0xb96ef807,
+	0x866dff6d, 0x0000ffff,
+	0x86fe7e7e, 0x86ea6a6a,
+	0x8f6e837a, 0xb96ee0c2,
+	0xbf800002, 0xb97a0002,
+	0xbf8a0000, 0xbe801f6c,
+	0xbf9b0000, 0x00000000,
 };
 
 static const uint32_t cwsr_trap_nv1x_hex[] = {
@@ -1302,7 +1303,7 @@ static const uint32_t cwsr_trap_nv1x_hex[] = {
 };
 
 static const uint32_t cwsr_trap_arcturus_hex[] = {
-	0xbf820001, 0xbf8202d4,
+	0xbf820001, 0xbf8202d5,
 	0xb8f8f802, 0x8978ff78,
 	0x00020006, 0xb8fbf803,
 	0x866eff78, 0x00002000,
@@ -1419,99 +1420,37 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0xbefe007c, 0xbefc0070,
 	0xc0611c7a, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
-	0xbefc007e, 0x867aff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f7a, 0xb8f02a05,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fb1605,
-	0x807b817b, 0x8e7b847b,
-	0x8e76827b, 0xbef600ff,
-	0x01000000, 0xbef20174,
-	0x80747074, 0x82758075,
-	0xbefc0080, 0xbf800000,
-	0xbe802b00, 0xbe822b02,
-	0xbe842b04, 0xbe862b06,
-	0xbe882b08, 0xbe8a2b0a,
-	0xbe8c2b0c, 0xbe8e2b0e,
-	0xc06b003a, 0x00000000,
-	0xbf8cc07f, 0xc06b013a,
-	0x00000010, 0xbf8cc07f,
-	0xc06b023a, 0x00000020,
-	0xbf8cc07f, 0xc06b033a,
-	0x00000030, 0xbf8cc07f,
-	0x8074c074, 0x82758075,
-	0x807c907c, 0xbf0a7b7c,
-	0xbf85ffe7, 0xbef40172,
-	0xbef00080, 0xbefe00c1,
-	0xbeff00c1, 0xbee80080,
-	0xbee90080, 0xbef600ff,
-	0x01000000, 0x867aff78,
-	0x00400000, 0xbf850003,
-	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf85004d,
-	0xbe840080, 0xd2890000,
-	0x00000900, 0x80048104,
-	0xd2890001, 0x00000900,
-	0x80048104, 0xd2890002,
-	0x00000900, 0x80048104,
-	0xd2890003, 0x00000900,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000901,
-	0x80048104, 0xd2890001,
-	0x00000901, 0x80048104,
-	0xd2890002, 0x00000901,
-	0x80048104, 0xd2890003,
-	0x00000901, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
-	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
-	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
-	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0xbf820008, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0xbefe00c1,
-	0xbeff00c1, 0xb8fb4306,
-	0x867bc17b, 0xbf840064,
-	0xbf8a0000, 0x867aff6f,
-	0x04000000, 0xbf840060,
-	0x8e7b867b, 0x8e7b827b,
-	0xbef6007b, 0xb8f02a05,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fa1605,
-	0x807a817a, 0x8e7a867a,
-	0x80707a70, 0x8070ff70,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
+	0xbefc007e, 0xbf108080,
+	0x867aff7f, 0x04000000,
+	0xbeef0080, 0x876f6f7a,
+	0xb8f02a05, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fb1605, 0x807b817b,
+	0x8e7b847b, 0x8e76827b,
+	0xbef600ff, 0x01000000,
+	0xbef20174, 0x80747074,
+	0x82758075, 0xbefc0080,
+	0xbf800000, 0xbe802b00,
+	0xbe822b02, 0xbe842b04,
+	0xbe862b06, 0xbe882b08,
+	0xbe8a2b0a, 0xbe8c2b0c,
+	0xbe8e2b0e, 0xc06b003a,
+	0x00000000, 0xbf8cc07f,
+	0xc06b013a, 0x00000010,
+	0xbf8cc07f, 0xc06b023a,
+	0x00000020, 0xbf8cc07f,
+	0xc06b033a, 0x00000030,
+	0xbf8cc07f, 0x8074c074,
+	0x82758075, 0x807c907c,
+	0xbf0a7b7c, 0xbf85ffe7,
+	0xbef40172, 0xbef00080,
+	0xbefe00c1, 0xbeff00c1,
+	0xbee80080, 0xbee90080,
+	0xbef600ff, 0x01000000,
 	0x867aff78, 0x00400000,
 	0xbf850003, 0xb8faf803,
 	0x897a7aff, 0x10000000,
-	0xbf850030, 0x24040682,
-	0xd86e4000, 0x00000002,
-	0xbf8cc07f, 0xbe840080,
+	0xbf85004d, 0xbe840080,
 	0xd2890000, 0x00000900,
 	0x80048104, 0xd2890001,
 	0x00000900, 0x80048104,
@@ -1530,31 +1469,50 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0x680404ff,
-	0x00000200, 0xd0c9006a,
-	0x0000f702, 0xbf87ffd2,
-	0xbf820015, 0xd1060002,
-	0x00011103, 0x7e0602ff,
-	0x00000200, 0xbefc00ff,
-	0x00010000, 0xbe800077,
-	0x8677ff77, 0xff7fffff,
-	0x8777ff77, 0x00058000,
-	0xd8ec0000, 0x00000002,
-	0xbf8cc07f, 0xe0765000,
-	0x701d0002, 0x68040702,
-	0xd0c9006a, 0x0000f702,
-	0xbf87fff7, 0xbef70000,
-	0xbef000ff, 0x00000400,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000902,
+	0x80048104, 0xd2890001,
+	0x00000902, 0x80048104,
+	0xd2890002, 0x00000902,
+	0x80048104, 0xd2890003,
+	0x00000902, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0xbe840080, 0xd2890000,
+	0x00000903, 0x80048104,
+	0xd2890001, 0x00000903,
+	0x80048104, 0xd2890002,
+	0x00000903, 0x80048104,
+	0xd2890003, 0x00000903,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbf820008,
+	0xe0724000, 0x701d0000,
+	0xe0724100, 0x701d0100,
+	0xe0724200, 0x701d0200,
+	0xe0724300, 0x701d0300,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8fb2a05, 0x807b817b,
-	0x8e7b827b, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a7b7c, 0xbf84006d,
-	0xbf11017c, 0x807bff7b,
-	0x00001000, 0x867aff78,
+	0xb8fb4306, 0x867bc17b,
+	0xbf840064, 0xbf8a0000,
+	0x867aff6f, 0x04000000,
+	0xbf840060, 0x8e7b867b,
+	0x8e7b827b, 0xbef6007b,
+	0xb8f02a05, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x80707a70,
+	0x8070ff70, 0x00000080,
+	0xbef600ff, 0x01000000,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0x867aff78,
 	0x00400000, 0xbf850003,
 	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf850051,
+	0x10000000, 0xbf850030,
+	0x24040682, 0xd86e4000,
+	0x00000002, 0xbf8cc07f,
 	0xbe840080, 0xd2890000,
 	0x00000900, 0x80048104,
 	0xd2890001, 0x00000900,
@@ -1574,215 +1532,259 @@ static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
+	0x680404ff, 0x00000200,
+	0xd0c9006a, 0x0000f702,
+	0xbf87ffd2, 0xbf820015,
+	0xd1060002, 0x00011103,
+	0x7e0602ff, 0x00000200,
+	0xbefc00ff, 0x00010000,
+	0xbe800077, 0x8677ff77,
+	0xff7fffff, 0x8777ff77,
+	0x00058000, 0xd8ec0000,
+	0x00000002, 0xbf8cc07f,
+	0xe0765000, 0x701d0002,
+	0x68040702, 0xd0c9006a,
+	0x0000f702, 0xbf87fff7,
+	0xbef70000, 0xbef000ff,
+	0x00000400, 0xbefe00c1,
+	0xbeff00c1, 0xb8fb2a05,
+	0x807b817b, 0x8e7b827b,
+	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a7b7c,
+	0xbf84006d, 0xbf11017c,
+	0x807bff7b, 0x00001000,
+	0x867aff78, 0x00400000,
+	0xbf850003, 0xb8faf803,
+	0x897a7aff, 0x10000000,
+	0xbf850051, 0xbe840080,
+	0xd2890000, 0x00000900,
+	0x80048104, 0xd2890001,
+	0x00000900, 0x80048104,
+	0xd2890002, 0x00000900,
+	0x80048104, 0xd2890003,
+	0x00000900, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
 	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890001, 0x00000901,
 	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890003, 0x00000901,
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
 	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
+	0xd2890000, 0x00000902,
 	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
+	0x00000902, 0x80048104,
+	0xd2890002, 0x00000902,
 	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
+	0x00000902, 0x80048104,
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
-	0x807c847c, 0xbf0a7b7c,
-	0xbf85ffb1, 0xbf9c0000,
-	0xbf820012, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0x807c847c,
-	0x8070ff70, 0x00000400,
-	0xbf0a7b7c, 0xbf85ffef,
-	0xbf9c0000, 0xbefc0080,
-	0xbf11017c, 0x867aff78,
-	0x00400000, 0xbf850003,
-	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf850059,
-	0xd3d84000, 0x18000100,
-	0xd3d84001, 0x18000101,
-	0xd3d84002, 0x18000102,
-	0xd3d84003, 0x18000103,
 	0xbe840080, 0xd2890000,
-	0x00000900, 0x80048104,
-	0xd2890001, 0x00000900,
+	0x00000903, 0x80048104,
+	0xd2890001, 0x00000903,
 	0x80048104, 0xd2890002,
-	0x00000900, 0x80048104,
-	0xd2890003, 0x00000900,
+	0x00000903, 0x80048104,
+	0xd2890003, 0x00000903,
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000901,
+	0xbf84ffee, 0x807c847c,
+	0xbf0a7b7c, 0xbf85ffb1,
+	0xbf9c0000, 0xbf820012,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
+	0xe0724000, 0x701d0000,
+	0xe0724100, 0x701d0100,
+	0xe0724200, 0x701d0200,
+	0xe0724300, 0x701d0300,
+	0x807c847c, 0x8070ff70,
+	0x00000400, 0xbf0a7b7c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbefc0080, 0xbf11017c,
+	0x867aff78, 0x00400000,
+	0xbf850003, 0xb8faf803,
+	0x897a7aff, 0x10000000,
+	0xbf850059, 0xd3d84000,
+	0x18000100, 0xd3d84001,
+	0x18000101, 0xd3d84002,
+	0x18000102, 0xd3d84003,
+	0x18000103, 0xbe840080,
+	0xd2890000, 0x00000900,
 	0x80048104, 0xd2890001,
-	0x00000901, 0x80048104,
-	0xd2890002, 0x00000901,
+	0x00000900, 0x80048104,
+	0xd2890002, 0x00000900,
 	0x80048104, 0xd2890003,
-	0x00000901, 0x80048104,
+	0x00000900, 0x80048104,
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
 	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890001, 0x00000901,
 	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
+	0x00000901, 0x80048104,
+	0xd2890003, 0x00000901,
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
 	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
+	0xd2890000, 0x00000902,
 	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
+	0x00000902, 0x80048104,
+	0xd2890002, 0x00000902,
 	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
+	0x00000902, 0x80048104,
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
-	0x807c847c, 0xbf0a7b7c,
-	0xbf85ffa9, 0xbf9c0000,
-	0xbf820016, 0xd3d84000,
-	0x18000100, 0xd3d84001,
-	0x18000101, 0xd3d84002,
-	0x18000102, 0xd3d84003,
-	0x18000103, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0x807c847c,
-	0x8070ff70, 0x00000400,
-	0xbf0a7b7c, 0xbf85ffeb,
-	0xbf9c0000, 0xbf8200e3,
-	0xbef4007e, 0x8675ff7f,
-	0x0000ffff, 0x8775ff75,
-	0x00040000, 0xbef60080,
-	0xbef700ff, 0x00807fac,
-	0x866eff7f, 0x04000000,
-	0xbf84001f, 0xbefe00c1,
-	0xbeff00c1, 0xb8ef4306,
-	0x866fc16f, 0xbf84001a,
-	0x8e6f866f, 0x8e6f826f,
-	0xbef6006f, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x8078ff78,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0xbefc0080,
-	0xe0510000, 0x781d0000,
-	0xe0510100, 0x781d0000,
-	0x807cff7c, 0x00000200,
-	0x8078ff78, 0x00000200,
-	0xbf0a6f7c, 0xbf85fff6,
+	0xbe840080, 0xd2890000,
+	0x00000903, 0x80048104,
+	0xd2890001, 0x00000903,
+	0x80048104, 0xd2890002,
+	0x00000903, 0x80048104,
+	0xd2890003, 0x00000903,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0x807c847c,
+	0xbf0a7b7c, 0xbf85ffa9,
+	0xbf9c0000, 0xbf820016,
+	0xd3d84000, 0x18000100,
+	0xd3d84001, 0x18000101,
+	0xd3d84002, 0x18000102,
+	0xd3d84003, 0x18000103,
+	0xe0724000, 0x701d0000,
+	0xe0724100, 0x701d0100,
+	0xe0724200, 0x701d0200,
+	0xe0724300, 0x701d0300,
+	0x807c847c, 0x8070ff70,
+	0x00000400, 0xbf0a7b7c,
+	0xbf85ffeb, 0xbf9c0000,
+	0xbf8200e3, 0xbef4007e,
+	0x8675ff7f, 0x0000ffff,
+	0x8775ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x00807fac, 0x866eff7f,
+	0x04000000, 0xbf84001f,
 	0xbefe00c1, 0xbeff00c1,
+	0xb8ef4306, 0x866fc16f,
+	0xbf84001a, 0x8e6f866f,
+	0x8e6f826f, 0xbef6006f,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0x8078ff78, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xb8ef2a05, 0x806f816f,
-	0x8e6f826f, 0x806fff6f,
-	0x00008000, 0xbef80080,
-	0xbeee0078, 0x8078ff78,
-	0x00000400, 0xbefc0084,
-	0xbf11087c, 0xe0524000,
-	0x781d0000, 0xe0524100,
-	0x781d0100, 0xe0524200,
-	0x781d0200, 0xe0524300,
-	0x781d0300, 0xbf8c0f70,
-	0x7e000300, 0x7e020301,
-	0x7e040302, 0x7e060303,
-	0x807c847c, 0x8078ff78,
-	0x00000400, 0xbf0a6f7c,
-	0xbf85ffee, 0xbefc0080,
-	0xbf11087c, 0xe0524000,
-	0x781d0000, 0xe0524100,
-	0x781d0100, 0xe0524200,
-	0x781d0200, 0xe0524300,
-	0x781d0300, 0xbf8c0f70,
-	0xd3d94000, 0x18000100,
-	0xd3d94001, 0x18000101,
-	0xd3d94002, 0x18000102,
-	0xd3d94003, 0x18000103,
-	0x807c847c, 0x8078ff78,
-	0x00000400, 0xbf0a6f7c,
-	0xbf85ffea, 0xbf9c0000,
-	0xe0524000, 0x6e1d0000,
-	0xe0524100, 0x6e1d0100,
-	0xe0524200, 0x6e1d0200,
-	0xe0524300, 0x6e1d0300,
-	0xbf8c0f70, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
-	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0xbef60084,
-	0xbef600ff, 0x01000000,
-	0xc0211bfa, 0x00000078,
-	0x80788478, 0xc0211b3a,
+	0xbefc0080, 0xe0510000,
+	0x781d0000, 0xe0510100,
+	0x781d0000, 0x807cff7c,
+	0x00000200, 0x8078ff78,
+	0x00000200, 0xbf0a6f7c,
+	0xbf85fff6, 0xbefe00c1,
+	0xbeff00c1, 0xbef600ff,
+	0x01000000, 0xb8ef2a05,
+	0x806f816f, 0x8e6f826f,
+	0x806fff6f, 0x00008000,
+	0xbef80080, 0xbeee0078,
+	0x8078ff78, 0x00000400,
+	0xbefc0084, 0xbf11087c,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0x7e000300,
+	0x7e020301, 0x7e040302,
+	0x7e060303, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffee,
+	0xbefc0080, 0xbf11087c,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0xd3d94000,
+	0x18000100, 0xd3d94001,
+	0x18000101, 0xd3d94002,
+	0x18000102, 0xd3d94003,
+	0x18000103, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffea,
+	0xbf9c0000, 0xe0524000,
+	0x6e1d0000, 0xe0524100,
+	0x6e1d0100, 0xe0524200,
+	0x6e1d0200, 0xe0524300,
+	0x6e1d0300, 0xbf8c0f70,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0xbef60084, 0xbef600ff,
+	0x01000000, 0xc0211bfa,
 	0x00000078, 0x80788478,
-	0xc0211b7a, 0x00000078,
-	0x80788478, 0xc0211c3a,
+	0xc0211b3a, 0x00000078,
+	0x80788478, 0xc0211b7a,
 	0x00000078, 0x80788478,
-	0xc0211c7a, 0x00000078,
-	0x80788478, 0xc0211eba,
+	0xc0211c3a, 0x00000078,
+	0x80788478, 0xc0211c7a,
 	0x00000078, 0x80788478,
-	0xc0211efa, 0x00000078,
-	0x80788478, 0xc0211a3a,
+	0xc0211eba, 0x00000078,
+	0x80788478, 0xc0211efa,
 	0x00000078, 0x80788478,
-	0xc0211a7a, 0x00000078,
-	0x80788478, 0xc0211cfa,
+	0xc0211a3a, 0x00000078,
+	0x80788478, 0xc0211a7a,
 	0x00000078, 0x80788478,
-	0xbf8cc07f, 0xbefc006f,
-	0xbefe0070, 0xbeff0071,
-	0x866f7bff, 0x000003ff,
-	0xb96f4803, 0x866f7bff,
-	0xfffff800, 0x8f6f8b6f,
-	0xb96fa2c3, 0xb973f801,
-	0xb8ee2a05, 0x806e816e,
-	0x8e6e8a6e, 0x8e6e816e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc00b1c37, 0x00000050,
-	0xc00b1d37, 0x00000060,
-	0xc0031e77, 0x00000074,
-	0xbf8cc07f, 0x8f6e8b77,
-	0x866eff6e, 0x001f8000,
-	0xb96ef807, 0x866dff6d,
-	0x0000ffff, 0x86fe7e7e,
-	0x86ea6a6a, 0x8f6e837a,
-	0xb96ee0c2, 0xbf800002,
-	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf9b0000,
+	0xc0211cfa, 0x00000078,
+	0x80788478, 0xbf8cc07f,
+	0xbefc006f, 0xbefe0070,
+	0xbeff0071, 0x866f7bff,
+	0x000003ff, 0xb96f4803,
+	0x866f7bff, 0xfffff800,
+	0x8f6f8b6f, 0xb96fa2c3,
+	0xb973f801, 0xb8ee2a05,
+	0x806e816e, 0x8e6e8a6e,
+	0x8e6e816e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc00b1c37,
+	0x00000050, 0xc00b1d37,
+	0x00000060, 0xc0031e77,
+	0x00000074, 0xbf8cc07f,
+	0x8f6e8b77, 0x866eff6e,
+	0x001f8000, 0xb96ef807,
+	0x866dff6d, 0x0000ffff,
+	0x86fe7e7e, 0x86ea6a6a,
+	0x8f6e837a, 0xb96ee0c2,
+	0xbf800002, 0xb97a0002,
+	0xbf8a0000, 0xbe801f6c,
+	0xbf9b0000, 0x00000000,
 };
 
 static const uint32_t cwsr_trap_aldebaran_hex[] = {
-	0xbf820001, 0xbf8202df,
+	0xbf820001, 0xbf8202e0,
 	0xb8f8f802, 0x8978ff78,
 	0x00020006, 0xb8fbf803,
 	0x866eff78, 0x00002000,
@@ -1899,99 +1901,37 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0xbefe007c, 0xbefc0070,
 	0xc0611c7a, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
-	0xbefc007e, 0x867aff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f7a, 0xb8f02985,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fb1605,
-	0x807b817b, 0x8e7b847b,
-	0x8e76827b, 0xbef600ff,
-	0x01000000, 0xbef20174,
-	0x80747074, 0x82758075,
-	0xbefc0080, 0xbf800000,
-	0xbe802b00, 0xbe822b02,
-	0xbe842b04, 0xbe862b06,
-	0xbe882b08, 0xbe8a2b0a,
-	0xbe8c2b0c, 0xbe8e2b0e,
-	0xc06b003a, 0x00000000,
-	0xbf8cc07f, 0xc06b013a,
-	0x00000010, 0xbf8cc07f,
-	0xc06b023a, 0x00000020,
-	0xbf8cc07f, 0xc06b033a,
-	0x00000030, 0xbf8cc07f,
-	0x8074c074, 0x82758075,
-	0x807c907c, 0xbf0a7b7c,
-	0xbf85ffe7, 0xbef40172,
-	0xbef00080, 0xbefe00c1,
-	0xbeff00c1, 0xbee80080,
-	0xbee90080, 0xbef600ff,
-	0x01000000, 0x867aff78,
-	0x00400000, 0xbf850003,
-	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf85004d,
-	0xbe840080, 0xd2890000,
-	0x00000900, 0x80048104,
-	0xd2890001, 0x00000900,
-	0x80048104, 0xd2890002,
-	0x00000900, 0x80048104,
-	0xd2890003, 0x00000900,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000901,
-	0x80048104, 0xd2890001,
-	0x00000901, 0x80048104,
-	0xd2890002, 0x00000901,
-	0x80048104, 0xd2890003,
-	0x00000901, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
-	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
-	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
-	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0xbf820008, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0xbefe00c1,
-	0xbeff00c1, 0xb8fb4306,
-	0x867bc17b, 0xbf840064,
-	0xbf8a0000, 0x867aff6f,
-	0x04000000, 0xbf840060,
-	0x8e7b867b, 0x8e7b827b,
-	0xbef6007b, 0xb8f02985,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fa1605,
-	0x807a817a, 0x8e7a867a,
-	0x80707a70, 0x8070ff70,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
+	0xbefc007e, 0xbf108080,
+	0x867aff7f, 0x04000000,
+	0xbeef0080, 0x876f6f7a,
+	0xb8f02985, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fb1605, 0x807b817b,
+	0x8e7b847b, 0x8e76827b,
+	0xbef600ff, 0x01000000,
+	0xbef20174, 0x80747074,
+	0x82758075, 0xbefc0080,
+	0xbf800000, 0xbe802b00,
+	0xbe822b02, 0xbe842b04,
+	0xbe862b06, 0xbe882b08,
+	0xbe8a2b0a, 0xbe8c2b0c,
+	0xbe8e2b0e, 0xc06b003a,
+	0x00000000, 0xbf8cc07f,
+	0xc06b013a, 0x00000010,
+	0xbf8cc07f, 0xc06b023a,
+	0x00000020, 0xbf8cc07f,
+	0xc06b033a, 0x00000030,
+	0xbf8cc07f, 0x8074c074,
+	0x82758075, 0x807c907c,
+	0xbf0a7b7c, 0xbf85ffe7,
+	0xbef40172, 0xbef00080,
+	0xbefe00c1, 0xbeff00c1,
+	0xbee80080, 0xbee90080,
+	0xbef600ff, 0x01000000,
 	0x867aff78, 0x00400000,
 	0xbf850003, 0xb8faf803,
 	0x897a7aff, 0x10000000,
-	0xbf850030, 0x24040682,
-	0xd86e4000, 0x00000002,
-	0xbf8cc07f, 0xbe840080,
+	0xbf85004d, 0xbe840080,
 	0xd2890000, 0x00000900,
 	0x80048104, 0xd2890001,
 	0x00000900, 0x80048104,
@@ -2010,31 +1950,50 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0x680404ff,
-	0x00000200, 0xd0c9006a,
-	0x0000f702, 0xbf87ffd2,
-	0xbf820015, 0xd1060002,
-	0x00011103, 0x7e0602ff,
-	0x00000200, 0xbefc00ff,
-	0x00010000, 0xbe800077,
-	0x8677ff77, 0xff7fffff,
-	0x8777ff77, 0x00058000,
-	0xd8ec0000, 0x00000002,
-	0xbf8cc07f, 0xe0765000,
-	0x701d0002, 0x68040702,
-	0xd0c9006a, 0x0000f702,
-	0xbf87fff7, 0xbef70000,
-	0xbef000ff, 0x00000400,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000902,
+	0x80048104, 0xd2890001,
+	0x00000902, 0x80048104,
+	0xd2890002, 0x00000902,
+	0x80048104, 0xd2890003,
+	0x00000902, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0xbe840080, 0xd2890000,
+	0x00000903, 0x80048104,
+	0xd2890001, 0x00000903,
+	0x80048104, 0xd2890002,
+	0x00000903, 0x80048104,
+	0xd2890003, 0x00000903,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbf820008,
+	0xe0724000, 0x701d0000,
+	0xe0724100, 0x701d0100,
+	0xe0724200, 0x701d0200,
+	0xe0724300, 0x701d0300,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8fb2b05, 0x807b817b,
-	0x8e7b827b, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a7b7c, 0xbf84006d,
-	0xbf11017c, 0x807bff7b,
-	0x00001000, 0x867aff78,
+	0xb8fb4306, 0x867bc17b,
+	0xbf840064, 0xbf8a0000,
+	0x867aff6f, 0x04000000,
+	0xbf840060, 0x8e7b867b,
+	0x8e7b827b, 0xbef6007b,
+	0xb8f02985, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x80707a70,
+	0x8070ff70, 0x00000080,
+	0xbef600ff, 0x01000000,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0x867aff78,
 	0x00400000, 0xbf850003,
 	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf850051,
+	0x10000000, 0xbf850030,
+	0x24040682, 0xd86e4000,
+	0x00000002, 0xbf8cc07f,
 	0xbe840080, 0xd2890000,
 	0x00000900, 0x80048104,
 	0xd2890001, 0x00000900,
@@ -2054,51 +2013,31 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
-	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
-	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
-	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
-	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0x807c847c, 0xbf0a7b7c,
-	0xbf85ffb1, 0xbf9c0000,
-	0xbf820012, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0x807c847c,
-	0x8070ff70, 0x00000400,
-	0xbf0a7b7c, 0xbf85ffef,
-	0xbf9c0000, 0xb8fb2985,
-	0x807b817b, 0x8e7b837b,
-	0xb8fa2b05, 0x807a817a,
-	0x8e7a827a, 0x80fb7a7b,
-	0x867b7b7b, 0xbf84007a,
+	0x680404ff, 0x00000200,
+	0xd0c9006a, 0x0000f702,
+	0xbf87ffd2, 0xbf820015,
+	0xd1060002, 0x00011103,
+	0x7e0602ff, 0x00000200,
+	0xbefc00ff, 0x00010000,
+	0xbe800077, 0x8677ff77,
+	0xff7fffff, 0x8777ff77,
+	0x00058000, 0xd8ec0000,
+	0x00000002, 0xbf8cc07f,
+	0xe0765000, 0x701d0002,
+	0x68040702, 0xd0c9006a,
+	0x0000f702, 0xbf87fff7,
+	0xbef70000, 0xbef000ff,
+	0x00000400, 0xbefe00c1,
+	0xbeff00c1, 0xb8fb2b05,
+	0x807b817b, 0x8e7b827b,
+	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a7b7c,
+	0xbf84006d, 0xbf11017c,
 	0x807bff7b, 0x00001000,
-	0xbefc0080, 0xbf11017c,
 	0x867aff78, 0x00400000,
 	0xbf850003, 0xb8faf803,
 	0x897a7aff, 0x10000000,
-	0xbf850059, 0xd3d84000,
-	0x18000100, 0xd3d84001,
-	0x18000101, 0xd3d84002,
-	0x18000102, 0xd3d84003,
-	0x18000103, 0xbe840080,
+	0xbf850051, 0xbe840080,
 	0xd2890000, 0x00000900,
 	0x80048104, 0xd2890001,
 	0x00000900, 0x80048104,
@@ -2137,139 +2076,203 @@ static const uint32_t cwsr_trap_aldebaran_hex[] = {
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
 	0xbf84ffee, 0x807c847c,
-	0xbf0a7b7c, 0xbf85ffa9,
-	0xbf9c0000, 0xbf820016,
-	0xd3d84000, 0x18000100,
-	0xd3d84001, 0x18000101,
-	0xd3d84002, 0x18000102,
-	0xd3d84003, 0x18000103,
+	0xbf0a7b7c, 0xbf85ffb1,
+	0xbf9c0000, 0xbf820012,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0xe0724000, 0x701d0000,
 	0xe0724100, 0x701d0100,
 	0xe0724200, 0x701d0200,
 	0xe0724300, 0x701d0300,
 	0x807c847c, 0x8070ff70,
 	0x00000400, 0xbf0a7b7c,
-	0xbf85ffeb, 0xbf9c0000,
-	0xbf8200ee, 0xbef4007e,
-	0x8675ff7f, 0x0000ffff,
-	0x8775ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x00807fac, 0x866eff7f,
-	0x04000000, 0xbf84001f,
+	0xbf85ffef, 0xbf9c0000,
+	0xb8fb2985, 0x807b817b,
+	0x8e7b837b, 0xb8fa2b05,
+	0x807a817a, 0x8e7a827a,
+	0x80fb7a7b, 0x867b7b7b,
+	0xbf84007a, 0x807bff7b,
+	0x00001000, 0xbefc0080,
+	0xbf11017c, 0x867aff78,
+	0x00400000, 0xbf850003,
+	0xb8faf803, 0x897a7aff,
+	0x10000000, 0xbf850059,
+	0xd3d84000, 0x18000100,
+	0xd3d84001, 0x18000101,
+	0xd3d84002, 0x18000102,
+	0xd3d84003, 0x18000103,
+	0xbe840080, 0xd2890000,
+	0x00000900, 0x80048104,
+	0xd2890001, 0x00000900,
+	0x80048104, 0xd2890002,
+	0x00000900, 0x80048104,
+	0xd2890003, 0x00000900,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000901,
+	0x80048104, 0xd2890001,
+	0x00000901, 0x80048104,
+	0xd2890002, 0x00000901,
+	0x80048104, 0xd2890003,
+	0x00000901, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0xbe840080, 0xd2890000,
+	0x00000902, 0x80048104,
+	0xd2890001, 0x00000902,
+	0x80048104, 0xd2890002,
+	0x00000902, 0x80048104,
+	0xd2890003, 0x00000902,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000903,
+	0x80048104, 0xd2890001,
+	0x00000903, 0x80048104,
+	0xd2890002, 0x00000903,
+	0x80048104, 0xd2890003,
+	0x00000903, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0x807c847c, 0xbf0a7b7c,
+	0xbf85ffa9, 0xbf9c0000,
+	0xbf820016, 0xd3d84000,
+	0x18000100, 0xd3d84001,
+	0x18000101, 0xd3d84002,
+	0x18000102, 0xd3d84003,
+	0x18000103, 0xe0724000,
+	0x701d0000, 0xe0724100,
+	0x701d0100, 0xe0724200,
+	0x701d0200, 0xe0724300,
+	0x701d0300, 0x807c847c,
+	0x8070ff70, 0x00000400,
+	0xbf0a7b7c, 0xbf85ffeb,
+	0xbf9c0000, 0xbf8200ee,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0x866eff7f, 0x04000000,
+	0xbf84001f, 0xbefe00c1,
+	0xbeff00c1, 0xb8ef4306,
+	0x866fc16f, 0xbf84001a,
+	0x8e6f866f, 0x8e6f826f,
+	0xbef6006f, 0xb8f82985,
+	0x80788178, 0x8e788a78,
+	0x8e788178, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0x8078ff78,
+	0x00000080, 0xbef600ff,
+	0x01000000, 0xbefc0080,
+	0xe0510000, 0x781d0000,
+	0xe0510100, 0x781d0000,
+	0x807cff7c, 0x00000200,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7c, 0xbf85fff6,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8ef4306, 0x866fc16f,
-	0xbf84001a, 0x8e6f866f,
-	0x8e6f826f, 0xbef6006f,
-	0xb8f82985, 0x80788178,
-	0x8e788a78, 0x8e788178,
-	0xb8ee1605, 0x806e816e,
-	0x8e6e866e, 0x80786e78,
-	0x8078ff78, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xbefc0080, 0xe0510000,
-	0x781d0000, 0xe0510100,
-	0x781d0000, 0x807cff7c,
-	0x00000200, 0x8078ff78,
-	0x00000200, 0xbf0a6f7c,
-	0xbf85fff6, 0xbefe00c1,
-	0xbeff00c1, 0xbef600ff,
-	0x01000000, 0xb8ef2b05,
-	0x806f816f, 0x8e6f826f,
-	0x806fff6f, 0x00008000,
-	0xbef80080, 0xbeee0078,
-	0x8078ff78, 0x00000400,
-	0xbefc0084, 0xbf11087c,
-	0xe0524000, 0x781d0000,
-	0xe0524100, 0x781d0100,
-	0xe0524200, 0x781d0200,
-	0xe0524300, 0x781d0300,
-	0xbf8c0f70, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0x807c847c,
-	0x8078ff78, 0x00000400,
-	0xbf0a6f7c, 0xbf85ffee,
-	0xb8ef2985, 0x806f816f,
-	0x8e6f836f, 0xb8f92b05,
-	0x80798179, 0x8e798279,
-	0x80ef796f, 0x866f6f6f,
-	0xbf84001a, 0x806fff6f,
-	0x00008000, 0xbefc0080,
+	0xb8ef2b05, 0x806f816f,
+	0x8e6f826f, 0x806fff6f,
+	0x00008000, 0xbef80080,
+	0xbeee0078, 0x8078ff78,
+	0x00000400, 0xbefc0084,
 	0xbf11087c, 0xe0524000,
 	0x781d0000, 0xe0524100,
 	0x781d0100, 0xe0524200,
 	0x781d0200, 0xe0524300,
 	0x781d0300, 0xbf8c0f70,
-	0xd3d94000, 0x18000100,
-	0xd3d94001, 0x18000101,
-	0xd3d94002, 0x18000102,
-	0xd3d94003, 0x18000103,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0x807c847c, 0x8078ff78,
 	0x00000400, 0xbf0a6f7c,
-	0xbf85ffea, 0xbf9c0000,
-	0xe0524000, 0x6e1d0000,
-	0xe0524100, 0x6e1d0100,
-	0xe0524200, 0x6e1d0200,
-	0xe0524300, 0x6e1d0300,
-	0xbf8c0f70, 0xb8f82985,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
-	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82985,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0xbef60084,
-	0xbef600ff, 0x01000000,
-	0xc0211bfa, 0x00000078,
-	0x80788478, 0xc0211b3a,
+	0xbf85ffee, 0xb8ef2985,
+	0x806f816f, 0x8e6f836f,
+	0xb8f92b05, 0x80798179,
+	0x8e798279, 0x80ef796f,
+	0x866f6f6f, 0xbf84001a,
+	0x806fff6f, 0x00008000,
+	0xbefc0080, 0xbf11087c,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0xd3d94000,
+	0x18000100, 0xd3d94001,
+	0x18000101, 0xd3d94002,
+	0x18000102, 0xd3d94003,
+	0x18000103, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffea,
+	0xbf9c0000, 0xe0524000,
+	0x6e1d0000, 0xe0524100,
+	0x6e1d0100, 0xe0524200,
+	0x6e1d0200, 0xe0524300,
+	0x6e1d0300, 0xbf8c0f70,
+	0xb8f82985, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
+	0xb8f82985, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0xbef60084, 0xbef600ff,
+	0x01000000, 0xc0211bfa,
 	0x00000078, 0x80788478,
-	0xc0211b7a, 0x00000078,
-	0x80788478, 0xc0211c3a,
+	0xc0211b3a, 0x00000078,
+	0x80788478, 0xc0211b7a,
 	0x00000078, 0x80788478,
-	0xc0211c7a, 0x00000078,
-	0x80788478, 0xc0211eba,
+	0xc0211c3a, 0x00000078,
+	0x80788478, 0xc0211c7a,
 	0x00000078, 0x80788478,
-	0xc0211efa, 0x00000078,
-	0x80788478, 0xc0211a3a,
+	0xc0211eba, 0x00000078,
+	0x80788478, 0xc0211efa,
 	0x00000078, 0x80788478,
-	0xc0211a7a, 0x00000078,
-	0x80788478, 0xc0211cfa,
+	0xc0211a3a, 0x00000078,
+	0x80788478, 0xc0211a7a,
 	0x00000078, 0x80788478,
-	0xbf8cc07f, 0xbefc006f,
-	0xbefe0070, 0xbeff0071,
-	0x866f7bff, 0x000003ff,
-	0xb96f4803, 0x866f7bff,
-	0xfffff800, 0x8f6f8b6f,
-	0xb96fa2c3, 0xb973f801,
-	0xb8ee2985, 0x806e816e,
-	0x8e6e8a6e, 0x8e6e816e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc00b1c37, 0x00000050,
-	0xc00b1d37, 0x00000060,
-	0xc0031e77, 0x00000074,
-	0xbf8cc07f, 0x8f6e8b77,
-	0x866eff6e, 0x001f8000,
-	0xb96ef807, 0x866dff6d,
-	0x0000ffff, 0x86fe7e7e,
-	0x86ea6a6a, 0x8f6e837a,
-	0xb96ee0c2, 0xbf800002,
-	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf9b0000,
+	0xc0211cfa, 0x00000078,
+	0x80788478, 0xbf8cc07f,
+	0xbefc006f, 0xbefe0070,
+	0xbeff0071, 0x866f7bff,
+	0x000003ff, 0xb96f4803,
+	0x866f7bff, 0xfffff800,
+	0x8f6f8b6f, 0xb96fa2c3,
+	0xb973f801, 0xb8ee2985,
+	0x806e816e, 0x8e6e8a6e,
+	0x8e6e816e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc00b1c37,
+	0x00000050, 0xc00b1d37,
+	0x00000060, 0xc0031e77,
+	0x00000074, 0xbf8cc07f,
+	0x8f6e8b77, 0x866eff6e,
+	0x001f8000, 0xb96ef807,
+	0x866dff6d, 0x0000ffff,
+	0x86fe7e7e, 0x86ea6a6a,
+	0x8f6e837a, 0xb96ee0c2,
+	0xbf800002, 0xb97a0002,
+	0xbf8a0000, 0xbe801f6c,
+	0xbf9b0000, 0x00000000,
 };
 
 static const uint32_t cwsr_trap_gfx10_hex[] = {
@@ -3151,7 +3154,7 @@ static const uint32_t cwsr_trap_gfx11_hex[] = {
 };
 
 static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
-	0xbf820001, 0xbf8202db,
+	0xbf820001, 0xbf8202dc,
 	0xb8f8f802, 0x8978ff78,
 	0x00020006, 0xb8fbf803,
 	0x866eff78, 0x00002000,
@@ -3266,99 +3269,37 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0xbefe007c, 0xbefc0070,
 	0xc0611c7a, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
-	0xbefc007e, 0x867aff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f7a, 0xb8f02985,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fb1605,
-	0x807b817b, 0x8e7b847b,
-	0x8e76827b, 0xbef600ff,
-	0x01000000, 0xbef20174,
-	0x80747074, 0x82758075,
-	0xbefc0080, 0xbf800000,
-	0xbe802b00, 0xbe822b02,
-	0xbe842b04, 0xbe862b06,
-	0xbe882b08, 0xbe8a2b0a,
-	0xbe8c2b0c, 0xbe8e2b0e,
-	0xc06b003a, 0x00000000,
-	0xbf8cc07f, 0xc06b013a,
-	0x00000010, 0xbf8cc07f,
-	0xc06b023a, 0x00000020,
-	0xbf8cc07f, 0xc06b033a,
-	0x00000030, 0xbf8cc07f,
-	0x8074c074, 0x82758075,
-	0x807c907c, 0xbf0a7b7c,
-	0xbf85ffe7, 0xbef40172,
-	0xbef00080, 0xbefe00c1,
-	0xbeff00c1, 0xbee80080,
-	0xbee90080, 0xbef600ff,
-	0x01000000, 0x867aff78,
-	0x00400000, 0xbf850003,
-	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf85004d,
-	0xbe840080, 0xd2890000,
-	0x00000900, 0x80048104,
-	0xd2890001, 0x00000900,
-	0x80048104, 0xd2890002,
-	0x00000900, 0x80048104,
-	0xd2890003, 0x00000900,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000901,
-	0x80048104, 0xd2890001,
-	0x00000901, 0x80048104,
-	0xd2890002, 0x00000901,
-	0x80048104, 0xd2890003,
-	0x00000901, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
-	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
-	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
-	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0xbf820008, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0xbefe00c1,
-	0xbeff00c1, 0xb8fb4306,
-	0x867bc17b, 0xbf840064,
-	0xbf8a0000, 0x867aff6f,
-	0x04000000, 0xbf840060,
-	0x8e7b867b, 0x8e7b827b,
-	0xbef6007b, 0xb8f02985,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fa1605,
-	0x807a817a, 0x8e7a867a,
-	0x80707a70, 0x8070ff70,
-	0x00000080, 0xbef600ff,
-	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
+	0xbefc007e, 0xbf108080,
+	0x867aff7f, 0x04000000,
+	0xbeef0080, 0x876f6f7a,
+	0xb8f02985, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fb1605, 0x807b817b,
+	0x8e7b847b, 0x8e76827b,
+	0xbef600ff, 0x01000000,
+	0xbef20174, 0x80747074,
+	0x82758075, 0xbefc0080,
+	0xbf800000, 0xbe802b00,
+	0xbe822b02, 0xbe842b04,
+	0xbe862b06, 0xbe882b08,
+	0xbe8a2b0a, 0xbe8c2b0c,
+	0xbe8e2b0e, 0xc06b003a,
+	0x00000000, 0xbf8cc07f,
+	0xc06b013a, 0x00000010,
+	0xbf8cc07f, 0xc06b023a,
+	0x00000020, 0xbf8cc07f,
+	0xc06b033a, 0x00000030,
+	0xbf8cc07f, 0x8074c074,
+	0x82758075, 0x807c907c,
+	0xbf0a7b7c, 0xbf85ffe7,
+	0xbef40172, 0xbef00080,
+	0xbefe00c1, 0xbeff00c1,
+	0xbee80080, 0xbee90080,
+	0xbef600ff, 0x01000000,
 	0x867aff78, 0x00400000,
 	0xbf850003, 0xb8faf803,
 	0x897a7aff, 0x10000000,
-	0xbf850030, 0x24040682,
-	0xd86e4000, 0x00000002,
-	0xbf8cc07f, 0xbe840080,
+	0xbf85004d, 0xbe840080,
 	0xd2890000, 0x00000900,
 	0x80048104, 0xd2890001,
 	0x00000900, 0x80048104,
@@ -3377,31 +3318,50 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0x80048104, 0xc069003a,
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0x680404ff,
-	0x00000200, 0xd0c9006a,
-	0x0000f702, 0xbf87ffd2,
-	0xbf820015, 0xd1060002,
-	0x00011103, 0x7e0602ff,
-	0x00000200, 0xbefc00ff,
-	0x00010000, 0xbe800077,
-	0x8677ff77, 0xff7fffff,
-	0x8777ff77, 0x00058000,
-	0xd8ec0000, 0x00000002,
-	0xbf8cc07f, 0xe0765000,
-	0x701d0002, 0x68040702,
-	0xd0c9006a, 0x0000f702,
-	0xbf87fff7, 0xbef70000,
-	0xbef000ff, 0x00000400,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000902,
+	0x80048104, 0xd2890001,
+	0x00000902, 0x80048104,
+	0xd2890002, 0x00000902,
+	0x80048104, 0xd2890003,
+	0x00000902, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0xbe840080, 0xd2890000,
+	0x00000903, 0x80048104,
+	0xd2890001, 0x00000903,
+	0x80048104, 0xd2890002,
+	0x00000903, 0x80048104,
+	0xd2890003, 0x00000903,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbf820008,
+	0xe0724000, 0x701d0000,
+	0xe0724100, 0x701d0100,
+	0xe0724200, 0x701d0200,
+	0xe0724300, 0x701d0300,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8fb2b05, 0x807b817b,
-	0x8e7b827b, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a7b7c, 0xbf84006d,
-	0xbf11017c, 0x807bff7b,
-	0x00001000, 0x867aff78,
+	0xb8fb4306, 0x867bc17b,
+	0xbf840064, 0xbf8a0000,
+	0x867aff6f, 0x04000000,
+	0xbf840060, 0x8e7b867b,
+	0x8e7b827b, 0xbef6007b,
+	0xb8f02985, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x80707a70,
+	0x8070ff70, 0x00000080,
+	0xbef600ff, 0x01000000,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0x867aff78,
 	0x00400000, 0xbf850003,
 	0xb8faf803, 0x897a7aff,
-	0x10000000, 0xbf850051,
+	0x10000000, 0xbf850030,
+	0x24040682, 0xd86e4000,
+	0x00000002, 0xbf8cc07f,
 	0xbe840080, 0xd2890000,
 	0x00000900, 0x80048104,
 	0xd2890001, 0x00000900,
@@ -3421,51 +3381,31 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0xc069003a, 0x00000070,
 	0xbf8cc07f, 0x80709070,
 	0xbf06c004, 0xbf84ffee,
-	0xbe840080, 0xd2890000,
-	0x00000902, 0x80048104,
-	0xd2890001, 0x00000902,
-	0x80048104, 0xd2890002,
-	0x00000902, 0x80048104,
-	0xd2890003, 0x00000902,
-	0x80048104, 0xc069003a,
-	0x00000070, 0xbf8cc07f,
-	0x80709070, 0xbf06c004,
-	0xbf84ffee, 0xbe840080,
-	0xd2890000, 0x00000903,
-	0x80048104, 0xd2890001,
-	0x00000903, 0x80048104,
-	0xd2890002, 0x00000903,
-	0x80048104, 0xd2890003,
-	0x00000903, 0x80048104,
-	0xc069003a, 0x00000070,
-	0xbf8cc07f, 0x80709070,
-	0xbf06c004, 0xbf84ffee,
-	0x807c847c, 0xbf0a7b7c,
-	0xbf85ffb1, 0xbf9c0000,
-	0xbf820012, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x701d0000, 0xe0724100,
-	0x701d0100, 0xe0724200,
-	0x701d0200, 0xe0724300,
-	0x701d0300, 0x807c847c,
-	0x8070ff70, 0x00000400,
-	0xbf0a7b7c, 0xbf85ffef,
-	0xbf9c0000, 0xb8fb2985,
-	0x807b817b, 0x8e7b837b,
-	0xb8fa2b05, 0x807a817a,
-	0x8e7a827a, 0x80fb7a7b,
-	0x867b7b7b, 0xbf84007a,
+	0x680404ff, 0x00000200,
+	0xd0c9006a, 0x0000f702,
+	0xbf87ffd2, 0xbf820015,
+	0xd1060002, 0x00011103,
+	0x7e0602ff, 0x00000200,
+	0xbefc00ff, 0x00010000,
+	0xbe800077, 0x8677ff77,
+	0xff7fffff, 0x8777ff77,
+	0x00058000, 0xd8ec0000,
+	0x00000002, 0xbf8cc07f,
+	0xe0765000, 0x701d0002,
+	0x68040702, 0xd0c9006a,
+	0x0000f702, 0xbf87fff7,
+	0xbef70000, 0xbef000ff,
+	0x00000400, 0xbefe00c1,
+	0xbeff00c1, 0xb8fb2b05,
+	0x807b817b, 0x8e7b827b,
+	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a7b7c,
+	0xbf84006d, 0xbf11017c,
 	0x807bff7b, 0x00001000,
-	0xbefc0080, 0xbf11017c,
 	0x867aff78, 0x00400000,
 	0xbf850003, 0xb8faf803,
 	0x897a7aff, 0x10000000,
-	0xbf850059, 0xd3d84000,
-	0x18000100, 0xd3d84001,
-	0x18000101, 0xd3d84002,
-	0x18000102, 0xd3d84003,
-	0x18000103, 0xbe840080,
+	0xbf850051, 0xbe840080,
 	0xd2890000, 0x00000900,
 	0x80048104, 0xd2890001,
 	0x00000900, 0x80048104,
@@ -3504,139 +3444,203 @@ static const uint32_t cwsr_trap_gfx9_4_3_hex[] = {
 	0x00000070, 0xbf8cc07f,
 	0x80709070, 0xbf06c004,
 	0xbf84ffee, 0x807c847c,
-	0xbf0a7b7c, 0xbf85ffa9,
-	0xbf9c0000, 0xbf820016,
-	0xd3d84000, 0x18000100,
-	0xd3d84001, 0x18000101,
-	0xd3d84002, 0x18000102,
-	0xd3d84003, 0x18000103,
+	0xbf0a7b7c, 0xbf85ffb1,
+	0xbf9c0000, 0xbf820012,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0xe0724000, 0x701d0000,
 	0xe0724100, 0x701d0100,
 	0xe0724200, 0x701d0200,
 	0xe0724300, 0x701d0300,
 	0x807c847c, 0x8070ff70,
 	0x00000400, 0xbf0a7b7c,
-	0xbf85ffeb, 0xbf9c0000,
-	0xbf8200ee, 0xbef4007e,
-	0x8675ff7f, 0x0000ffff,
-	0x8775ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x00807fac, 0x866eff7f,
-	0x04000000, 0xbf84001f,
+	0xbf85ffef, 0xbf9c0000,
+	0xb8fb2985, 0x807b817b,
+	0x8e7b837b, 0xb8fa2b05,
+	0x807a817a, 0x8e7a827a,
+	0x80fb7a7b, 0x867b7b7b,
+	0xbf84007a, 0x807bff7b,
+	0x00001000, 0xbefc0080,
+	0xbf11017c, 0x867aff78,
+	0x00400000, 0xbf850003,
+	0xb8faf803, 0x897a7aff,
+	0x10000000, 0xbf850059,
+	0xd3d84000, 0x18000100,
+	0xd3d84001, 0x18000101,
+	0xd3d84002, 0x18000102,
+	0xd3d84003, 0x18000103,
+	0xbe840080, 0xd2890000,
+	0x00000900, 0x80048104,
+	0xd2890001, 0x00000900,
+	0x80048104, 0xd2890002,
+	0x00000900, 0x80048104,
+	0xd2890003, 0x00000900,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000901,
+	0x80048104, 0xd2890001,
+	0x00000901, 0x80048104,
+	0xd2890002, 0x00000901,
+	0x80048104, 0xd2890003,
+	0x00000901, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0xbe840080, 0xd2890000,
+	0x00000902, 0x80048104,
+	0xd2890001, 0x00000902,
+	0x80048104, 0xd2890002,
+	0x00000902, 0x80048104,
+	0xd2890003, 0x00000902,
+	0x80048104, 0xc069003a,
+	0x00000070, 0xbf8cc07f,
+	0x80709070, 0xbf06c004,
+	0xbf84ffee, 0xbe840080,
+	0xd2890000, 0x00000903,
+	0x80048104, 0xd2890001,
+	0x00000903, 0x80048104,
+	0xd2890002, 0x00000903,
+	0x80048104, 0xd2890003,
+	0x00000903, 0x80048104,
+	0xc069003a, 0x00000070,
+	0xbf8cc07f, 0x80709070,
+	0xbf06c004, 0xbf84ffee,
+	0x807c847c, 0xbf0a7b7c,
+	0xbf85ffa9, 0xbf9c0000,
+	0xbf820016, 0xd3d84000,
+	0x18000100, 0xd3d84001,
+	0x18000101, 0xd3d84002,
+	0x18000102, 0xd3d84003,
+	0x18000103, 0xe0724000,
+	0x701d0000, 0xe0724100,
+	0x701d0100, 0xe0724200,
+	0x701d0200, 0xe0724300,
+	0x701d0300, 0x807c847c,
+	0x8070ff70, 0x00000400,
+	0xbf0a7b7c, 0xbf85ffeb,
+	0xbf9c0000, 0xbf8200ee,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0x866eff7f, 0x04000000,
+	0xbf84001f, 0xbefe00c1,
+	0xbeff00c1, 0xb8ef4306,
+	0x866fc16f, 0xbf84001a,
+	0x8e6f866f, 0x8e6f826f,
+	0xbef6006f, 0xb8f82985,
+	0x80788178, 0x8e788a78,
+	0x8e788178, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0x8078ff78,
+	0x00000080, 0xbef600ff,
+	0x01000000, 0xbefc0080,
+	0xe0510000, 0x781d0000,
+	0xe0510100, 0x781d0000,
+	0x807cff7c, 0x00000200,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7c, 0xbf85fff6,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8ef4306, 0x866fc16f,
-	0xbf84001a, 0x8e6f866f,
-	0x8e6f826f, 0xbef6006f,
-	0xb8f82985, 0x80788178,
-	0x8e788a78, 0x8e788178,
-	0xb8ee1605, 0x806e816e,
-	0x8e6e866e, 0x80786e78,
-	0x8078ff78, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xbefc0080, 0xe0510000,
-	0x781d0000, 0xe0510100,
-	0x781d0000, 0x807cff7c,
-	0x00000200, 0x8078ff78,
-	0x00000200, 0xbf0a6f7c,
-	0xbf85fff6, 0xbefe00c1,
-	0xbeff00c1, 0xbef600ff,
-	0x01000000, 0xb8ef2b05,
-	0x806f816f, 0x8e6f826f,
-	0x806fff6f, 0x00008000,
-	0xbef80080, 0xbeee0078,
-	0x8078ff78, 0x00000400,
-	0xbefc0084, 0xbf11087c,
-	0xe0524000, 0x781d0000,
-	0xe0524100, 0x781d0100,
-	0xe0524200, 0x781d0200,
-	0xe0524300, 0x781d0300,
-	0xbf8c0f70, 0x7e000300,
-	0x7e020301, 0x7e040302,
-	0x7e060303, 0x807c847c,
-	0x8078ff78, 0x00000400,
-	0xbf0a6f7c, 0xbf85ffee,
-	0xb8ef2985, 0x806f816f,
-	0x8e6f836f, 0xb8f92b05,
-	0x80798179, 0x8e798279,
-	0x80ef796f, 0x866f6f6f,
-	0xbf84001a, 0x806fff6f,
-	0x00008000, 0xbefc0080,
+	0xb8ef2b05, 0x806f816f,
+	0x8e6f826f, 0x806fff6f,
+	0x00008000, 0xbef80080,
+	0xbeee0078, 0x8078ff78,
+	0x00000400, 0xbefc0084,
 	0xbf11087c, 0xe0524000,
 	0x781d0000, 0xe0524100,
 	0x781d0100, 0xe0524200,
 	0x781d0200, 0xe0524300,
 	0x781d0300, 0xbf8c0f70,
-	0xd3d94000, 0x18000100,
-	0xd3d94001, 0x18000101,
-	0xd3d94002, 0x18000102,
-	0xd3d94003, 0x18000103,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0x807c847c, 0x8078ff78,
 	0x00000400, 0xbf0a6f7c,
-	0xbf85ffea, 0xbf9c0000,
-	0xe0524000, 0x6e1d0000,
-	0xe0524100, 0x6e1d0100,
-	0xe0524200, 0x6e1d0200,
-	0xe0524300, 0x6e1d0300,
-	0xbf8c0f70, 0xb8f82985,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
-	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82985,
-	0x80788178, 0x8e788a78,
-	0x8e788178, 0xb8ee1605,
-	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0xbef60084,
-	0xbef600ff, 0x01000000,
-	0xc0211bfa, 0x00000078,
-	0x80788478, 0xc0211b3a,
+	0xbf85ffee, 0xb8ef2985,
+	0x806f816f, 0x8e6f836f,
+	0xb8f92b05, 0x80798179,
+	0x8e798279, 0x80ef796f,
+	0x866f6f6f, 0xbf84001a,
+	0x806fff6f, 0x00008000,
+	0xbefc0080, 0xbf11087c,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0xd3d94000,
+	0x18000100, 0xd3d94001,
+	0x18000101, 0xd3d94002,
+	0x18000102, 0xd3d94003,
+	0x18000103, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffea,
+	0xbf9c0000, 0xe0524000,
+	0x6e1d0000, 0xe0524100,
+	0x6e1d0100, 0xe0524200,
+	0x6e1d0200, 0xe0524300,
+	0x6e1d0300, 0xbf8c0f70,
+	0xb8f82985, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
+	0xb8f82985, 0x80788178,
+	0x8e788a78, 0x8e788178,
+	0xb8ee1605, 0x806e816e,
+	0x8e6e866e, 0x80786e78,
+	0xbef60084, 0xbef600ff,
+	0x01000000, 0xc0211bfa,
 	0x00000078, 0x80788478,
-	0xc0211b7a, 0x00000078,
-	0x80788478, 0xc0211c3a,
+	0xc0211b3a, 0x00000078,
+	0x80788478, 0xc0211b7a,
 	0x00000078, 0x80788478,
-	0xc0211c7a, 0x00000078,
-	0x80788478, 0xc0211eba,
+	0xc0211c3a, 0x00000078,
+	0x80788478, 0xc0211c7a,
 	0x00000078, 0x80788478,
-	0xc0211efa, 0x00000078,
-	0x80788478, 0xc0211a3a,
+	0xc0211eba, 0x00000078,
+	0x80788478, 0xc0211efa,
 	0x00000078, 0x80788478,
-	0xc0211a7a, 0x00000078,
-	0x80788478, 0xc0211cfa,
+	0xc0211a3a, 0x00000078,
+	0x80788478, 0xc0211a7a,
 	0x00000078, 0x80788478,
-	0xbf8cc07f, 0xbefc006f,
-	0xbefe0070, 0xbeff0071,
-	0x866f7bff, 0x000003ff,
-	0xb96f4803, 0x866f7bff,
-	0xfffff800, 0x8f6f8b6f,
-	0xb96fa2c3, 0xb973f801,
-	0xb8ee2985, 0x806e816e,
-	0x8e6e8a6e, 0x8e6e816e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc00b1c37, 0x00000050,
-	0xc00b1d37, 0x00000060,
-	0xc0031e77, 0x00000074,
-	0xbf8cc07f, 0x8f6e8b79,
-	0x866eff6e, 0x001f8000,
-	0xb96ef807, 0x866dff6d,
-	0x0000ffff, 0x86fe7e7e,
-	0x86ea6a6a, 0x8f6e837a,
-	0xb96ee0c2, 0xbf800002,
-	0xb97a0002, 0xbf8a0000,
-	0xbe801f6c, 0xbf9b0000,
+	0xc0211cfa, 0x00000078,
+	0x80788478, 0xbf8cc07f,
+	0xbefc006f, 0xbefe0070,
+	0xbeff0071, 0x866f7bff,
+	0x000003ff, 0xb96f4803,
+	0x866f7bff, 0xfffff800,
+	0x8f6f8b6f, 0xb96fa2c3,
+	0xb973f801, 0xb8ee2985,
+	0x806e816e, 0x8e6e8a6e,
+	0x8e6e816e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc00b1c37,
+	0x00000050, 0xc00b1d37,
+	0x00000060, 0xc0031e77,
+	0x00000074, 0xbf8cc07f,
+	0x8f6e8b79, 0x866eff6e,
+	0x001f8000, 0xb96ef807,
+	0x866dff6d, 0x0000ffff,
+	0x86fe7e7e, 0x86ea6a6a,
+	0x8f6e837a, 0xb96ee0c2,
+	0xbf800002, 0xb97a0002,
+	0xbf8a0000, 0xbe801f6c,
+	0xbf9b0000, 0x00000000,
 };
 
 static const uint32_t cwsr_trap_gfx12_hex[] = {
@@ -4124,27 +4128,25 @@ static const uint32_t cwsr_trap_gfx12_hex[] = {
 };
 
 static const uint32_t cwsr_trap_gfx9_5_0_hex[] = {
-	0xbf820001, 0xbf8202d8,
+	0xbf820001, 0xbf8202ca,
 	0xb8f8f802, 0x8978ff78,
 	0x00020006, 0xb8fbf803,
 	0x866eff78, 0x00002000,
-	0xbf840008, 0xbf0d986d,
-	0xbf85001f, 0x866eff7b,
-	0x00000400, 0xbf850061,
-	0xbf8e0010, 0xb8fbf803,
-	0xbf82fffa, 0x866eff7b,
-	0x03800900, 0xbf850015,
-	0x866eff7b, 0x000071ff,
-	0xbf840008, 0x866fff7b,
-	0x00007080, 0xbf840001,
-	0xbeee1a87, 0xb8eff801,
-	0x8e6e8c6e, 0x866e6f6e,
-	0xbf85000a, 0xbf0d986d,
-	0xbf850003, 0x866eff6d,
-	0x00ff0000, 0xbf850005,
-	0xbf0d986d, 0xbf850004,
+	0xbf840009, 0x866eff6d,
+	0x00ff0000, 0xbf85001a,
 	0x866eff7b, 0x00000400,
-	0xbf850046, 0xbeed1a9d,
+	0xbf850051, 0xbf8e0010,
+	0xb8fbf803, 0xbf82fffa,
+	0x866eff7b, 0x03c00900,
+	0xbf850011, 0x866eff7b,
+	0x000071ff, 0xbf840008,
+	0x866fff7b, 0x00007080,
+	0xbf840001, 0xbeee1a87,
+	0xb8eff801, 0x8e6e8c6e,
+	0x866e6f6e, 0xbf850006,
+	0x866eff6d, 0x00ff0000,
+	0xbf850003, 0x866eff7b,
+	0x00000400, 0xbf85003a,
 	0xb8faf807, 0x867aff7a,
 	0x001f8000, 0x8e7a8b7a,
 	0x8979ff79, 0xfc000000,
@@ -4153,100 +4155,95 @@ static const uint32_t cwsr_trap_gfx9_5_0_hex[] = {
 	0xb8fbf813, 0x8efa887a,
 	0xbf0d8f7b, 0xbf840002,
 	0x877bff7b, 0xffff0000,
-	0xc0031cfd, 0x00000010,
-	0xc0071bbd, 0x00000000,
+	0xc0031bbd, 0x00000010,
+	0xbf8cc07f, 0x8e6e976e,
+	0x8979ff79, 0x00800000,
+	0x87796e79, 0xc0071bbd,
+	0x00000000, 0xbf8cc07f,
 	0xc0071ebd, 0x00000008,
-	0xbf8cc07f, 0x8e739773,
-	0x8979ff79, 0x01800000,
-	0x87797379, 0xbf0d986d,
-	0xbf840009, 0xbf0d9879,
-	0xbf850007, 0x896dff6d,
-	0x01ff0000, 0xba7f0583,
-	0x00000000, 0xbf0d9d6d,
-	0xbeed189d, 0xbf840012,
-	0xbef91898, 0xbeed189d,
-	0x86ee6e6e, 0xbf840001,
-	0xbe801d6e, 0x866eff6d,
-	0x01ff0000, 0xbf850005,
-	0x8778ff78, 0x00002000,
-	0x80ec886c, 0x82ed806d,
-	0xbf820005, 0x866eff6d,
-	0x01000000, 0xbf850002,
-	0x806c846c, 0x826d806d,
-	0x866dff6d, 0x0000ffff,
-	0x8f7a8b79, 0x867aff7a,
-	0x001f8000, 0xb97af807,
-	0x86fe7e7e, 0x86ea6a6a,
-	0x8f6e8378, 0xb96ee0c2,
-	0xbf800002, 0xb9780002,
-	0xbe801f6c, 0x866dff6d,
-	0x0000ffff, 0xbefa0080,
-	0xb97a0283, 0xb8faf807,
+	0xbf8cc07f, 0x86ee6e6e,
+	0xbf840001, 0xbe801d6e,
+	0x866eff6d, 0x01ff0000,
+	0xbf850005, 0x8778ff78,
+	0x00002000, 0x80ec886c,
+	0x82ed806d, 0xbf820005,
+	0x866eff6d, 0x01000000,
+	0xbf850002, 0x806c846c,
+	0x826d806d, 0x866dff6d,
+	0x0000ffff, 0x8f7a8b79,
 	0x867aff7a, 0x001f8000,
-	0x8e7a8b7a, 0x8979ff79,
-	0xfc000000, 0x87797a79,
-	0xba7ff807, 0x00000000,
-	0xbeee007e, 0xbeef007f,
-	0xbefe0180, 0xbf900004,
-	0x877a8478, 0xb97af802,
-	0xbf8e0002, 0xbf88fffe,
-	0xb8fa2985, 0x807a817a,
-	0x8e7a8a7a, 0x8e7a817a,
-	0xb8fb1605, 0x807b817b,
-	0x8e7b867b, 0x807a7b7a,
-	0x807a7e7a, 0x827b807f,
-	0x867bff7b, 0x0000ffff,
-	0xc04b1c3d, 0x00000050,
-	0xbf8cc07f, 0xc04b1d3d,
-	0x00000060, 0xbf8cc07f,
-	0xc0431e7d, 0x00000074,
-	0xbf8cc07f, 0xbef4007e,
-	0x8675ff7f, 0x0000ffff,
-	0x8775ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x00807fac, 0xbef1007c,
-	0xbef00080, 0xb8f02985,
-	0x80708170, 0x8e708a70,
-	0x8e708170, 0xb8fa1605,
-	0x807a817a, 0x8e7a867a,
-	0x80707a70, 0xbef60084,
-	0xbef600ff, 0x01000000,
-	0xbefe007c, 0xbefc0070,
-	0xc0611c7a, 0x0000007c,
-	0xbf8cc07f, 0x80708470,
-	0xbefc007e, 0xbefe007c,
-	0xbefc0070, 0xc0611b3a,
+	0xb97af807, 0x86fe7e7e,
+	0x86ea6a6a, 0x8f6e8378,
+	0xb96ee0c2, 0xbf800002,
+	0xb9780002, 0xbe801f6c,
+	0x866dff6d, 0x0000ffff,
+	0xbefa0080, 0xb97a0283,
+	0xb8faf807, 0x867aff7a,
+	0x001f8000, 0x8e7a8b7a,
+	0x8979ff79, 0xfc000000,
+	0x87797a79, 0xba7ff807,
+	0x00000000, 0xbeee007e,
+	0xbeef007f, 0xbefe0180,
+	0xbf900004, 0x877a8478,
+	0xb97af802, 0xbf8e0002,
+	0xbf88fffe, 0xb8fa2985,
+	0x807a817a, 0x8e7a8a7a,
+	0x8e7a817a, 0xb8fb1605,
+	0x807b817b, 0x8e7b867b,
+	0x807a7b7a, 0x807a7e7a,
+	0x827b807f, 0x867bff7b,
+	0x0000ffff, 0xc04b1c3d,
+	0x00000050, 0xbf8cc07f,
+	0xc04b1d3d, 0x00000060,
+	0xbf8cc07f, 0xc0431e7d,
+	0x00000074, 0xbf8cc07f,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0xbef1007c, 0xbef00080,
+	0xb8f02985, 0x80708170,
+	0x8e708a70, 0x8e708170,
+	0xb8fa1605, 0x807a817a,
+	0x8e7a867a, 0x80707a70,
+	0xbef60084, 0xbef600ff,
+	0x01000000, 0xbefe007c,
+	0xbefc0070, 0xc0611c7a,
 	0x0000007c, 0xbf8cc07f,
 	0x80708470, 0xbefc007e,
 	0xbefe007c, 0xbefc0070,
-	0xc0611b7a, 0x0000007c,
+	0xc0611b3a, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
 	0xbefc007e, 0xbefe007c,
-	0xbefc0070, 0xc0611bba,
+	0xbefc0070, 0xc0611b7a,
 	0x0000007c, 0xbf8cc07f,
 	0x80708470, 0xbefc007e,
 	0xbefe007c, 0xbefc0070,
-	0xc0611bfa, 0x0000007c,
+	0xc0611bba, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
 	0xbefc007e, 0xbefe007c,
-	0xbefc0070, 0xc0611e3a,
-	0x0000007c, 0xbf8cc07f,
-	0x80708470, 0xbefc007e,
-	0xb8fbf803, 0xbefe007c,
-	0xbefc0070, 0xc0611efa,
+	0xbefc0070, 0xc0611bfa,
 	0x0000007c, 0xbf8cc07f,
 	0x80708470, 0xbefc007e,
 	0xbefe007c, 0xbefc0070,
-	0xc0611a3a, 0x0000007c,
+	0xc0611e3a, 0x0000007c,
+	0xbf8cc07f, 0x80708470,
+	0xbefc007e, 0xb8fbf803,
+	0xbefe007c, 0xbefc0070,
+	0xc0611efa, 0x0000007c,
 	0xbf8cc07f, 0x80708470,
 	0xbefc007e, 0xbefe007c,
-	0xbefc0070, 0xc0611a7a,
-	0x0000007c, 0xbf8cc07f,
-	0x80708470, 0xbefc007e,
-	0xb8f1f801, 0xbefe007c,
-	0xbefc0070, 0xc0611c7a,
+	0xbefc0070, 0xc0611a3a,
 	0x0000007c, 0xbf8cc07f,
 	0x80708470, 0xbefc007e,
+	0xbefe007c, 0xbefc0070,
+	0xc0611a7a, 0x0000007c,
+	0xbf8cc07f, 0x80708470,
+	0xbefc007e, 0xb8f1f801,
+	0xbefe007c, 0xbefc0070,
+	0xc0611c7a, 0x0000007c,
+	0xbf8cc07f, 0x80708470,
+	0xbefc007e, 0xbf108080,
 	0x867aff7f, 0x04000000,
 	0xbeef0080, 0x876f6f7a,
 	0xb8f02985, 0x80708170,
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index 0eabb7a8cab9..6869e07a2fff 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -447,7 +447,9 @@ L_SAVE:
     s_getreg_b32    s_save_m0, hwreg(HW_REG_MODE)						    //MODE
     write_hwreg_to_mem(s_save_m0, s_save_buf_rsrc0, s_save_mem_offset)
 
-
+    // Clear VSKIP state now that MODE.VSKIP has been saved.
+    // If user shader set it then vector instructions would be skipped.
+    s_setvskip	0,0
 
     /*	    the first wave in the threadgroup	 */
     s_and_b32	    s_save_tmp, s_save_spi_init_hi, S_SAVE_SPI_INIT_FIRST_WAVE_MASK	// extract fisrt wave bit
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 1405e8affd48..d4593374e7a1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2325,9 +2325,9 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	 */
 	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ];
 	if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) {
+		while (halt_if_hws_hang)
+			schedule();
 		if (reset_queues_on_hws_hang(dqm)) {
-			while (halt_if_hws_hang)
-				schedule();
 			dqm->is_hws_hang = true;
 			kfd_hws_hang(dqm);
 			retval = -ETIME;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 4b275937d05e..d05d199b5e44 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -278,10 +278,11 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
 			 dma_addr_t *scratch, uint64_t ttm_res_offset)
 {
-	uint64_t npages = migrate->cpages;
+	uint64_t npages = migrate->npages;
 	struct amdgpu_device *adev = node->adev;
 	struct device *dev = adev->dev;
 	struct amdgpu_res_cursor cursor;
+	uint64_t mpages = 0;
 	dma_addr_t *src;
 	uint64_t *dst;
 	uint64_t i, j;
@@ -295,14 +296,16 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 
 	amdgpu_res_first(prange->ttm_res, ttm_res_offset,
 			 npages << PAGE_SHIFT, &cursor);
-	for (i = j = 0; i < npages; i++) {
+	for (i = j = 0; (i < npages) && (mpages < migrate->cpages); i++) {
 		struct page *spage;
 
-		dst[i] = cursor.start + (j << PAGE_SHIFT);
-		migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
-		svm_migrate_get_vram_page(prange, migrate->dst[i]);
-		migrate->dst[i] = migrate_pfn(migrate->dst[i]);
-
+		if (migrate->src[i] & MIGRATE_PFN_MIGRATE) {
+			dst[i] = cursor.start + (j << PAGE_SHIFT);
+			migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
+			svm_migrate_get_vram_page(prange, migrate->dst[i]);
+			migrate->dst[i] = migrate_pfn(migrate->dst[i]);
+			mpages++;
+		}
 		spage = migrate_pfn_to_page(migrate->src[i]);
 		if (spage && !is_zone_device_page(spage)) {
 			src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE,
@@ -353,9 +356,12 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 out_free_vram_pages:
 	if (r) {
 		pr_debug("failed %d to copy memory to vram\n", r);
-		while (i--) {
+		for (i = 0; i < npages && mpages; i++) {
+			if (!dst[i])
+				continue;
 			svm_migrate_put_vram_page(adev, dst[i]);
 			migrate->dst[i] = 0;
+			mpages--;
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 9df56f8e09f9..bcddd989c7f3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -86,9 +86,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
 
 	if (pdd->already_dequeued)
 		return;
-
+	/* The MES context flush needs to filter out the case which the
+	 * KFD process is created without setting up the MES context and
+	 * queue for creating a compute queue.
+	 */
 	dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
-	if (dev->kfd->shared_resources.enable_mes &&
+	if (dev->kfd->shared_resources.enable_mes && !!pdd->proc_ctx_gpu_addr &&
 	    down_read_trylock(&dev->adev->reset_domain->sem)) {
 		amdgpu_mes_flush_shader_debugger(dev->adev,
 						 pdd->proc_ctx_gpu_addr);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0ec178ca7434..ac3fd81fecef 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2034,6 +2034,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_dc_debug_mask & DC_FORCE_SUBVP_MCLK_SWITCH)
 		adev->dm.dc->debug.force_subvp_mclk_switch = true;
 
+	if (amdgpu_dc_debug_mask & DC_DISABLE_SUBVP)
+		adev->dm.dc->debug.force_disable_subvp = true;
+
 	if (amdgpu_dc_debug_mask & DC_ENABLE_DML2) {
 		adev->dm.dc->debug.using_dml2 = true;
 		adev->dm.dc->debug.using_dml21 = true;
@@ -11483,6 +11486,11 @@ static bool amdgpu_dm_crtc_mem_type_changed(struct drm_device *dev,
 		new_plane_state = drm_atomic_get_plane_state(state, plane);
 		old_plane_state = drm_atomic_get_plane_state(state, plane);
 
+		if (IS_ERR(new_plane_state) || IS_ERR(old_plane_state)) {
+			DRM_ERROR("Failed to get plane state for plane %s\n", plane->name);
+			return false;
+		}
+
 		if (old_plane_state->fb && new_plane_state->fb &&
 		    get_mem_type(old_plane_state->fb) != get_mem_type(new_plane_state->fb))
 			return true;
@@ -12318,10 +12326,14 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 
 	if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT ||
 		     sink->sink_signal == SIGNAL_TYPE_EDP)) {
-		amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq;
-		amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq;
-		if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10)
-			freesync_capable = true;
+		if (amdgpu_dm_connector->dc_link &&
+		    amdgpu_dm_connector->dc_link->dpcd_caps.allow_invalid_MSA_timing_param) {
+			amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq;
+			amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq;
+			if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10)
+				freesync_capable = true;
+		}
+
 		parse_amd_vsdb(amdgpu_dm_connector, edid, &vsdb_info);
 
 		if (vsdb_info.replay_mode) {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 1f974ea3b0c6..1648226586e2 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -89,7 +89,7 @@
 #define mmCLK1_CLK4_ALLOW_DS 0x16EA8
 #define mmCLK1_CLK5_ALLOW_DS 0x16EB1
 
-#define mmCLK5_spll_field_8 0x1B04B
+#define mmCLK5_spll_field_8 0x1B24B
 #define mmDENTIST_DISPCLK_CNTL 0x0124
 #define regDENTIST_DISPCLK_CNTL 0x0064
 #define regDENTIST_DISPCLK_CNTL_BASE_IDX 1
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index cecaadf741ad..f84e795e35f5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2133,7 +2133,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
-	if (context->stream_count > get_seamless_boot_stream_count(context) ||
+	if (get_seamless_boot_stream_count(context) == 0 ||
 		context->stream_count == 0) {
 		/* Must wait for no flips to be pending before doing optimize bw */
 		hwss_wait_for_no_pipes_pending(dc, context);
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c
index 5bb8b78bf250..bf636b28e3e1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c
@@ -63,8 +63,7 @@ void dmub_hw_lock_mgr_inbox0_cmd(struct dc_dmub_srv *dmub_srv,
 
 bool should_use_dmub_lock(struct dc_link *link)
 {
-	if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 ||
-	    link->psr_settings.psr_version == DC_PSR_VERSION_1)
+	if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1)
 		return true;
 
 	if (link->replay_settings.replay_feature_enabled)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 46f9c05de16e..e1d500633dfa 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -29,11 +29,15 @@ dml_ccflags := $(CC_FLAGS_FPU)
 dml_rcflags := $(CC_FLAGS_NO_FPU)
 
 ifneq ($(CONFIG_FRAME_WARN),0)
-ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
-frame_warn_flag := -Wframe-larger-than=3072
-else
-frame_warn_flag := -Wframe-larger-than=2048
-endif
+    ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
+        frame_warn_limit := 3072
+    else
+        frame_warn_limit := 2048
+    endif
+
+    ifeq ($(call test-lt, $(CONFIG_FRAME_WARN), $(frame_warn_limit)),y)
+        frame_warn_flag := -Wframe-larger-than=$(frame_warn_limit)
+    endif
 endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/Makefile b/drivers/gpu/drm/amd/display/dc/dml2/Makefile
index 91c4f3b4bd5f..21fd466dba26 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml2/Makefile
@@ -28,15 +28,19 @@ dml2_ccflags := $(CC_FLAGS_FPU)
 dml2_rcflags := $(CC_FLAGS_NO_FPU)
 
 ifneq ($(CONFIG_FRAME_WARN),0)
-ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
-ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy)
-frame_warn_flag := -Wframe-larger-than=4096
-else
-frame_warn_flag := -Wframe-larger-than=3072
-endif
-else
-frame_warn_flag := -Wframe-larger-than=2048
-endif
+    ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y)
+        ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy)
+            frame_warn_limit := 4096
+        else
+            frame_warn_limit := 3072
+        endif
+    else
+        frame_warn_limit := 2048
+    endif
+
+    ifeq ($(call test-lt, $(CONFIG_FRAME_WARN), $(frame_warn_limit)),y)
+        frame_warn_flag := -Wframe-larger-than=$(frame_warn_limit)
+    endif
 endif
 
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/dml2
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index 35bc917631ae..84a2de9a76d4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -1736,7 +1736,7 @@ static void CalculateBytePerPixelAndBlockSizes(
 #endif
 } // CalculateBytePerPixelAndBlockSizes
 
-static dml_float_t CalculateTWait(
+static noinline_for_stack dml_float_t CalculateTWait(
 		dml_uint_t PrefetchMode,
 		enum dml_use_mall_for_pstate_change_mode UseMALLForPStateChange,
 		dml_bool_t SynchronizeDRRDisplaysForUCLKPStateChangeFinal,
@@ -4458,7 +4458,7 @@ static void CalculateSwathWidth(
 	}
 } // CalculateSwathWidth
 
-static  dml_float_t CalculateExtraLatency(
+static noinline_for_stack dml_float_t CalculateExtraLatency(
 		dml_uint_t RoundTripPingLatencyCycles,
 		dml_uint_t ReorderingBytes,
 		dml_float_t DCFCLK,
@@ -5915,7 +5915,7 @@ static dml_uint_t DSCDelayRequirement(
 	return DSCDelayRequirement_val;
 }
 
-static dml_bool_t CalculateVActiveBandwithSupport(dml_uint_t NumberOfActiveSurfaces,
+static noinline_for_stack dml_bool_t CalculateVActiveBandwithSupport(dml_uint_t NumberOfActiveSurfaces,
 										dml_float_t ReturnBW,
 										dml_bool_t NotUrgentLatencyHiding[],
 										dml_float_t ReadBandwidthLuma[],
@@ -6019,7 +6019,7 @@ static void CalculatePrefetchBandwithSupport(
 #endif
 }
 
-static dml_float_t CalculateBandwidthAvailableForImmediateFlip(
+static noinline_for_stack dml_float_t CalculateBandwidthAvailableForImmediateFlip(
 													dml_uint_t NumberOfActiveSurfaces,
 													dml_float_t ReturnBW,
 													dml_float_t ReadBandwidthLuma[],
@@ -6213,7 +6213,7 @@ static dml_uint_t CalculateMaxVStartup(
 	return max_vstartup_lines;
 }
 
-static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *mode_lib,
+static noinline_for_stack void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *mode_lib,
 						   struct CalculatePrefetchSchedule_params_st *CalculatePrefetchSchedule_params,
 						   dml_uint_t j,
 						   dml_uint_t k)
@@ -6265,7 +6265,7 @@ static void set_calculate_prefetch_schedule_params(struct display_mode_lib_st *m
 				CalculatePrefetchSchedule_params->Tno_bw = &mode_lib->ms.Tno_bw[k];
 }
 
-static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
+static noinline_for_stack void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 {
 	struct dml_core_mode_support_locals_st *s = &mode_lib->scratch.dml_core_mode_support_locals;
 	struct CalculatePrefetchSchedule_params_st *CalculatePrefetchSchedule_params = &mode_lib->scratch.CalculatePrefetchSchedule_params;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index b9c6b45f6872..0c8ec30ea672 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -1017,7 +1017,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 		if (disp_cfg_stream_location < 0)
 			disp_cfg_stream_location = dml_dispcfg->num_streams++;
 
-		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 		populate_dml21_timing_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, context->streams[stream_index], dml_ctx);
 		adjust_dml21_hblank_timing_config_from_pipe_ctx(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, &context->res_ctx.pipe_ctx[stream_index]);
 		populate_dml21_output_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].output, context->streams[stream_index], &context->res_ctx.pipe_ctx[stream_index]);
@@ -1042,7 +1042,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_planes++;
 
-				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 
 				populate_dml21_surface_config_from_plane_state(in_dc, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location].surface, context->stream_status[stream_index].plane_states[plane_index]);
 				populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index);
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
index c4dbf27abaf8..8ed49a9df378 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
@@ -2778,7 +2778,7 @@ static double dml_get_return_bandwidth_available(
 	return return_bw_mbps;
 }
 
-static void calculate_bandwidth_available(
+static noinline_for_stack void calculate_bandwidth_available(
 	double avg_bandwidth_available_min[dml2_core_internal_soc_state_max],
 	double avg_bandwidth_available[dml2_core_internal_soc_state_max][dml2_core_internal_bw_max],
 	double urg_bandwidth_available_min[dml2_core_internal_soc_state_max], // min between SDP and DRAM
@@ -3625,7 +3625,7 @@ static void CalculateDCFCLKDeepSleepTdlut(
 	dml2_printf("DML::%s: DCFClkDeepSleep = %f (final)\n", __func__, *DCFClkDeepSleep);
 }
 
-static void CalculateDCFCLKDeepSleep(
+static noinline_for_stack void CalculateDCFCLKDeepSleep(
 	const struct dml2_display_cfg *display_cfg,
 	unsigned int NumberOfActiveSurfaces,
 	unsigned int BytePerPixelY[],
@@ -4142,7 +4142,7 @@ static bool ValidateODMMode(enum dml2_odm_mode ODMMode,
 	return true;
 }
 
-static void CalculateODMMode(
+static noinline_for_stack void CalculateODMMode(
 	unsigned int MaximumPixelsPerLinePerDSCUnit,
 	unsigned int HActive,
 	enum dml2_output_format_class OutFormat,
@@ -4239,7 +4239,7 @@ static void CalculateODMMode(
 #endif
 }
 
-static void CalculateOutputLink(
+static noinline_for_stack void CalculateOutputLink(
 	struct dml2_core_internal_scratch *s,
 	double PHYCLK,
 	double PHYCLKD18,
@@ -5999,7 +5999,7 @@ static double calculate_impacted_Tsw(unsigned int exclude_plane_idx, unsigned in
 }
 
 // a global check against the aggregate effect of the per plane prefetch schedule
-static bool CheckGlobalPrefetchAdmissibility(struct dml2_core_internal_scratch *scratch,
+static noinline_for_stack bool CheckGlobalPrefetchAdmissibility(struct dml2_core_internal_scratch *scratch,
 											 struct dml2_core_calcs_CheckGlobalPrefetchAdmissibility_params *p)
 {
 	struct dml2_core_calcs_CheckGlobalPrefetchAdmissibility_locals *s = &scratch->CheckGlobalPrefetchAdmissibility_locals;
@@ -7012,7 +7012,7 @@ static void calculate_bytes_to_fetch_required_to_hide_latency(
 	}
 }
 
-static void calculate_vactive_det_fill_latency(
+static noinline_for_stack void calculate_vactive_det_fill_latency(
 		const struct dml2_display_cfg *display_cfg,
 		unsigned int num_active_planes,
 		unsigned int bytes_required_l[],
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index b416320873e1..b8a34abaf519 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -786,7 +786,7 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st *
 	case SIGNAL_TYPE_DISPLAY_PORT_MST:
 	case SIGNAL_TYPE_DISPLAY_PORT:
 		out->OutputEncoder[location] = dml_dp;
-		if (dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location] != -1)
+		if (location < MAX_HPO_DP2_ENCODERS && dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location] != -1)
 			out->OutputEncoder[dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location]] = dml_dp2p0;
 		break;
 	case SIGNAL_TYPE_EDP:
@@ -1343,7 +1343,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat
 		if (disp_cfg_stream_location < 0)
 			disp_cfg_stream_location = dml_dispcfg->num_timings++;
 
-		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+		ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 
 		populate_dml_timing_cfg_from_stream_state(&dml_dispcfg->timing, disp_cfg_stream_location, context->streams[i]);
 		populate_dml_output_cfg_from_stream_state(&dml_dispcfg->output, disp_cfg_stream_location, context->streams[i], current_pipe_context, dml2);
@@ -1383,7 +1383,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat
 				if (disp_cfg_plane_location < 0)
 					disp_cfg_plane_location = dml_dispcfg->num_surfaces++;
 
-				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__);
+				ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__);
 
 				populate_dml_surface_cfg_from_plane_state(dml2->v20.dml_core_ctx.project, &dml_dispcfg->surface, disp_cfg_plane_location, context->stream_status[i].plane_states[j]);
 				populate_dml_plane_cfg_from_plane_state(
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
index e1da48b05d00..75fb77bca83b 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
@@ -194,6 +194,9 @@ void dpp_reset(struct dpp *dpp_base)
 	dpp->filter_h = NULL;
 	dpp->filter_v = NULL;
 
+	memset(&dpp_base->pos, 0, sizeof(dpp_base->pos));
+	memset(&dpp_base->att, 0, sizeof(dpp_base->att));
+
 	memset(&dpp->scl_data, 0, sizeof(dpp->scl_data));
 	memset(&dpp->pwl_data, 0, sizeof(dpp->pwl_data));
 }
@@ -480,10 +483,11 @@ void dpp1_set_cursor_position(
 	if (src_y_offset + cursor_height <= 0)
 		cur_en = 0;  /* not visible beyond top edge*/
 
-	REG_UPDATE(CURSOR0_CONTROL,
-			CUR0_ENABLE, cur_en);
+	if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) {
+		REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
 
-	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+		dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+	}
 }
 
 void dpp1_cnv_set_optional_cursor_attributes(
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
index 3b6ca7974e18..1236e0f9a256 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c
@@ -154,9 +154,11 @@ void dpp401_set_cursor_position(
 	struct dcn401_dpp *dpp = TO_DCN401_DPP(dpp_base);
 	uint32_t cur_en = pos->enable ? 1 : 0;
 
-	REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
+	if (dpp_base->pos.cur0_ctl.bits.cur0_enable != cur_en) {
+		REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en);
 
-	dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+		dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en;
+	}
 }
 
 void dpp401_set_optional_cursor_attributes(
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
index fe741100c0f8..d347bb06577a 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
@@ -129,7 +129,8 @@ bool hubbub3_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 
 	return wm_pending;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
index 7fb5523f9722..b98505b240a7 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
@@ -750,7 +750,8 @@ static bool hubbub31_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 	return wm_pending;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
index 5264dc26cce1..32a6be543105 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
@@ -786,7 +786,8 @@ static bool hubbub32_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 
 	hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
index 5eb3da8d5206..dce7269959ce 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
@@ -326,7 +326,8 @@ static bool hubbub35_program_watermarks(
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND_COMMIT_THRESHOLD, 0xA);/*hw delta*/
 	REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DCHUBBUB_ARB_MAX_QOS_COMMIT_THRESHOLD, 0xF);
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
+		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 
 	hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c
index 8364c9f9231a..9b026600b90e 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.c
@@ -546,6 +546,12 @@ void hubp1_dcc_control(struct hubp *hubp, bool enable,
 			SECONDARY_SURFACE_DCC_IND_64B_BLK, dcc_ind_64b_blk);
 }
 
+void hubp_reset(struct hubp *hubp)
+{
+	memset(&hubp->pos, 0, sizeof(hubp->pos));
+	memset(&hubp->att, 0, sizeof(hubp->att));
+}
+
 void hubp1_program_surface_config(
 	struct hubp *hubp,
 	enum surface_pixel_format format,
@@ -1351,8 +1357,9 @@ static void hubp1_wait_pipe_read_start(struct hubp *hubp)
 
 void hubp1_init(struct hubp *hubp)
 {
-	//do nothing
+	hubp_reset(hubp);
 }
+
 static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_program_surface_flip_and_addr =
 			hubp1_program_surface_flip_and_addr,
@@ -1365,6 +1372,7 @@ static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_set_vm_context0_settings = hubp1_set_vm_context0_settings,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_hubp_blank_en = hubp1_set_hubp_blank_en,
 	.set_cursor_attributes	= hubp1_cursor_set_attributes,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
index a85dc3be786f..c7765e6f09e6 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
@@ -746,6 +746,8 @@ void hubp1_dcc_control(struct hubp *hubp,
 		bool enable,
 		enum hubp_ind_block_size independent_64b_blks);
 
+void hubp_reset(struct hubp *hubp);
+
 bool hubp1_program_surface_flip_and_addr(
 	struct hubp *hubp,
 	const struct dc_plane_address *address,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c
index c74f6a3313a2..91259b896e03 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.c
@@ -1058,11 +1058,13 @@ void hubp2_cursor_set_position(
 	if (src_y_offset + cursor_height <= 0)
 		cur_en = 0;  /* not visible beyond top edge*/
 
-	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+	if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) {
+		if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
+			hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
 
-	REG_UPDATE(CURSOR_CONTROL,
+		REG_UPDATE(CURSOR_CONTROL,
 			CURSOR_ENABLE, cur_en);
+	}
 
 	REG_SET_2(CURSOR_POSITION, 0,
 			CURSOR_X_POSITION, pos->x,
@@ -1674,6 +1676,7 @@ static struct hubp_funcs dcn20_hubp_funcs = {
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp2_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c
index 65c628078ca2..ec88ee424a7f 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn201/dcn201_hubp.c
@@ -121,6 +121,7 @@ static struct hubp_funcs dcn201_hubp_funcs = {
 	.set_cursor_position	= hubp1_cursor_set_position,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.hubp_clk_cntl = hubp1_clk_cntl,
 	.hubp_vtg_sel = hubp1_vtg_sel,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c
index edbdb8c88d5c..e2740482e1cf 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn21/dcn21_hubp.c
@@ -811,6 +811,8 @@ static void hubp21_init(struct hubp *hubp)
 	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
 	//hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1;
 	REG_WRITE(HUBPREQ_DEBUG, 1 << 26);
+
+	hubp_reset(hubp);
 }
 static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
@@ -823,6 +825,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp21_set_vm_system_aperture_settings,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = hubp21_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp1_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
index 12b282ed7067..0da70b50e86d 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
@@ -499,6 +499,10 @@ void hubp3_init(struct hubp *hubp)
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
 	//hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1;
 	REG_WRITE(HUBPREQ_DEBUG, 1 << 26);
+
+	REG_UPDATE(DCHUBP_CNTL, HUBP_TTU_DISABLE, 0);
+
+	hubp_reset(hubp);
 }
 
 static struct hubp_funcs dcn30_hubp_funcs = {
@@ -513,6 +517,7 @@ static struct hubp_funcs dcn30_hubp_funcs = {
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
index 46b804ed05fb..c2900c79a2d3 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
@@ -79,6 +79,7 @@ static struct hubp_funcs dcn31_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
index 8b5bd73b8094..f3a21c623f44 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
@@ -168,6 +168,8 @@ void hubp32_init(struct hubp *hubp)
 {
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
 	REG_WRITE(HUBPREQ_DEBUG_DB, 1 << 8);
+
+	REG_UPDATE(DCHUBP_CNTL, HUBP_TTU_DISABLE, 0);
 }
 static struct hubp_funcs dcn32_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
@@ -181,6 +183,7 @@ static struct hubp_funcs dcn32_hubp_funcs = {
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp32_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
index faf37febc6fb..5661d7a80d54 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
@@ -199,6 +199,7 @@ static struct hubp_funcs dcn35_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
 	.dcc_control = hubp3_dcc_control,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp2_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
index 28ceceaf9e31..5ed195377a6c 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
@@ -141,7 +141,7 @@ void hubp401_update_mall_sel(struct hubp *hubp, uint32_t mall_sel, bool c_cursor
 
 void hubp401_init(struct hubp *hubp)
 {
-	//For now nothing to do, HUBPREQ_DEBUG_DB register is removed on DCN4x.
+	hubp_reset(hubp);
 }
 
 void hubp401_vready_at_or_After_vsync(struct hubp *hubp,
@@ -742,11 +742,13 @@ void hubp401_cursor_set_position(
 			dc_fixpt_from_int(dst_x_offset),
 			param->h_scale_ratio));
 
-	if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
-		hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
+	if (hubp->pos.cur_ctl.bits.cur_enable != cur_en) {
+		if (cur_en && REG_READ(CURSOR_SURFACE_ADDRESS) == 0)
+			hubp->funcs->set_cursor_attributes(hubp, &hubp->curs_attr);
 
-	REG_UPDATE(CURSOR_CONTROL,
-		CURSOR_ENABLE, cur_en);
+		REG_UPDATE(CURSOR_CONTROL,
+			CURSOR_ENABLE, cur_en);
+	}
 
 	REG_SET_2(CURSOR_POSITION, 0,
 		CURSOR_X_POSITION, x_pos,
@@ -998,6 +1000,7 @@ static struct hubp_funcs dcn401_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
 	.set_blank_regs = hubp2_set_blank_regs,
+	.hubp_reset = hubp_reset,
 	.mem_program_viewport = hubp401_set_viewport,
 	.set_cursor_attributes	= hubp32_cursor_set_attributes,
 	.set_cursor_position	= hubp401_cursor_set_position,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 681bb92c6069..44e405e9bc97 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -1286,6 +1286,7 @@ void dcn10_plane_atomic_power_down(struct dc *dc,
 		if (hws->funcs.hubp_pg_control)
 			hws->funcs.hubp_pg_control(hws, hubp->inst, false);
 
+		hubp->funcs->hubp_reset(hubp);
 		dpp->funcs->dpp_reset(dpp);
 
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
@@ -1447,6 +1448,7 @@ void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		/* Disable on the current state so the new one isn't cleared. */
 		pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
 
+		hubp->funcs->hubp_reset(hubp);
 		dpp->funcs->dpp_reset(dpp);
 
 		pipe_ctx->stream_res.tg = tg;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 59fc1c114fbe..b907ad1acedd 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -236,7 +236,8 @@ void dcn35_init_hw(struct dc *dc)
 		}
 
 		hws->funcs.init_pipes(dc, dc->current_state);
-		if (dc->res_pool->hubbub->funcs->allow_self_refresh_control)
+		if (dc->res_pool->hubbub->funcs->allow_self_refresh_control &&
+			!dc->res_pool->hubbub->ctx->dc->debug.disable_stutter)
 			dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub,
 					!dc->res_pool->hubbub->ctx->dc->debug.disable_stutter);
 	}
@@ -800,6 +801,7 @@ void dcn35_init_pipes(struct dc *dc, struct dc_state *context)
 		/* Disable on the current state so the new one isn't cleared. */
 		pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
 
+		hubp->funcs->hubp_reset(hubp);
 		dpp->funcs->dpp_reset(dpp);
 
 		pipe_ctx->stream_res.tg = tg;
@@ -956,6 +958,7 @@ void dcn35_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 /*to do, need to support both case*/
 	hubp->power_gated = true;
 
+	hubp->funcs->hubp_reset(hubp);
 	dpp->funcs->dpp_reset(dpp);
 
 	pipe_ctx->stream = NULL;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 2a530a4a39f7..b610beb075d5 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -163,6 +163,8 @@ struct hubp_funcs {
 	void (*dcc_control)(struct hubp *hubp, bool enable,
 			enum hubp_ind_block_size blk_size);
 
+	void (*hubp_reset)(struct hubp *hubp);
+
 	void (*mem_program_viewport)(
 			struct hubp *hubp,
 			const struct rect *viewport,
diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h
index a1ece3eecdf5..a08611cb8041 100644
--- a/drivers/gpu/drm/amd/include/amd_pcie.h
+++ b/drivers/gpu/drm/amd/include/amd_pcie.h
@@ -49,6 +49,17 @@
 				      | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3)
 
 /* Following flags shows PCIe lane width switch supported in driver which are decided by chipset and ASIC */
+
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1          0x00000001
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2          0x00000002
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4          0x00000004
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8          0x00000008
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X12         0x00000010
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16         0x00000020
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X32         0x00000040
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_MASK        0x0000FFFF
+#define CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_SHIFT       0
+
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X1          0x00010000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X2          0x00020000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X4          0x00040000
@@ -56,6 +67,7 @@
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X12         0x00100000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X16         0x00200000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X32         0x00400000
+#define CAIL_PCIE_LINK_WIDTH_SUPPORT_MASK        0xFFFF0000
 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_SHIFT       16
 
 /* 1/2/4/8/16 lanes */
@@ -65,4 +77,10 @@
 				      | CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 \
 				      | CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
 
+#define AMDGPU_DEFAULT_ASIC_PCIE_MLW_MASK (CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X1 \
+					   | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X2 \
+					   | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X4 \
+					   | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X8 \
+					   | CAIL_ASIC_PCIE_LINK_WIDTH_SUPPORT_X16)
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 05bdb4e020ae..6dccee403a3d 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -345,10 +345,15 @@ enum DC_DEBUG_MASK {
 	 */
 	DC_DISABLE_ACPI_EDID = 0x8000,
 
-	/*
+	/**
 	 * @DC_DISABLE_HDMI_CEC: If set, disable HDMI-CEC feature in amdgpu driver.
 	 */
 	DC_DISABLE_HDMI_CEC = 0x10000,
+
+	/**
+	 * @DC_DISABLE_SUBVP: If set, disable DCN Sub-Viewport feature in amdgpu driver.
+	 */
+	DC_DISABLE_SUBVP = 0x20000,
 };
 
 enum amd_dpm_forced_level;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
index 7b65a27fb302..147bfb12fd75 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
@@ -93,7 +93,6 @@
 #define PPSMC_MSG_SelectPLPDMode                    0x40
 #define PPSMC_MSG_RmaDueToBadPageThreshold          0x43
 #define PPSMC_MSG_SelectPstatePolicy                0x44
-#define PPSMC_MSG_ResetSDMA2                        0x45
 #define PPSMC_MSG_ResetSDMA                         0x4D
 #define PPSMC_Message_Count                         0x4E
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index b0dab9797c70..e4cd6a0d13da 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -276,8 +276,7 @@
 	__SMU_DUMMY_MAP(SelectPstatePolicy), \
 	__SMU_DUMMY_MAP(MALLPowerController), \
 	__SMU_DUMMY_MAP(MALLPowerState), \
-	__SMU_DUMMY_MAP(ResetSDMA), \
-	__SMU_DUMMY_MAP(ResetSDMA2),
+	__SMU_DUMMY_MAP(ResetSDMA),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 356d9422b411..8d4a96e23326 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -107,6 +107,7 @@ struct smu_13_0_dpm_context {
 	struct smu_13_0_dpm_tables  dpm_tables;
 	uint32_t                    workload_policy_mask;
 	uint32_t                    dcef_min_ds_clk;
+	uint64_t                    caps;
 };
 
 enum smu_13_0_power_state {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index f6b029354327..83163d7c7f00 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1732,7 +1732,6 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 
 	gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity;
 	gpu_metrics->average_umc_activity = metrics.AverageUclkActivity;
-	gpu_metrics->average_mm_activity = 0;
 
 	/* Valid power data is available only from primary die */
 	if (aldebaran_is_primary(smu)) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 8ab30b2f7119..da7bd9227afe 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -101,38 +101,24 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_14.bin");
 #define MCA_BANK_IPID(_ip, _hwid, _type) \
 	[AMDGPU_MCA_IP_##_ip] = { .hwid = _hwid, .mcatype = _type, }
 
-static inline bool smu_v13_0_6_is_unified_metrics(struct smu_context *smu)
-{
-	return (smu->adev->flags & AMD_IS_APU) &&
-		smu->smc_fw_version <= 0x4556900;
-}
-
-static inline bool smu_v13_0_6_is_other_end_count_available(struct smu_context *smu)
-{
-	switch (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)) {
-	case IP_VERSION(13, 0, 6):
-		return smu->smc_fw_version >= 0x557600;
-	case IP_VERSION(13, 0, 14):
-		return smu->smc_fw_version >= 0x05550E00;
-	default:
-		return false;
-	}
-}
-
-static inline bool smu_v13_0_6_is_blw_host_limit_available(struct smu_context *smu)
-{
-	if (smu->adev->flags & AMD_IS_APU)
-		return smu->smc_fw_version >= 0x04556F00;
-
-	switch (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)) {
-	case IP_VERSION(13, 0, 6):
-		return smu->smc_fw_version >= 0x557900;
-	case IP_VERSION(13, 0, 14):
-		return smu->smc_fw_version >= 0x05551000;
-	default:
-		return false;
-	}
-}
+#define SMU_CAP(x) SMU_13_0_6_CAPS_##x
+
+enum smu_v13_0_6_caps {
+	SMU_CAP(DPM),
+	SMU_CAP(UNI_METRICS),
+	SMU_CAP(DPM_POLICY),
+	SMU_CAP(OTHER_END_METRICS),
+	SMU_CAP(SET_UCLK_MAX),
+	SMU_CAP(PCIE_METRICS),
+	SMU_CAP(HST_LIMIT_METRICS),
+	SMU_CAP(MCA_DEBUG_MODE),
+	SMU_CAP(PER_INST_METRICS),
+	SMU_CAP(CTF_LIMIT),
+	SMU_CAP(RMA_MSG),
+	SMU_CAP(ACA_SYND),
+	SMU_CAP(SDMA_RESET),
+	SMU_CAP(ALL),
+};
 
 struct mca_bank_ipid {
 	enum amdgpu_mca_ip ip;
@@ -209,7 +195,6 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(RmaDueToBadPageThreshold,            PPSMC_MSG_RmaDueToBadPageThreshold,        0),
 	MSG_MAP(SelectPstatePolicy,                  PPSMC_MSG_SelectPstatePolicy,              0),
 	MSG_MAP(ResetSDMA,                           PPSMC_MSG_ResetSDMA,                       0),
-	MSG_MAP(ResetSDMA2,                          PPSMC_MSG_ResetSDMA2,                      0),
 };
 
 // clang-format on
@@ -297,6 +282,162 @@ struct smu_v13_0_6_dpm_map {
 	uint32_t *freq_table;
 };
 
+static inline void smu_v13_0_6_cap_set(struct smu_context *smu,
+				       enum smu_v13_0_6_caps cap)
+{
+	struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context;
+
+	dpm_context->caps |= BIT_ULL(cap);
+}
+
+static inline void smu_v13_0_6_cap_clear(struct smu_context *smu,
+					 enum smu_v13_0_6_caps cap)
+{
+	struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context;
+
+	dpm_context->caps &= ~BIT_ULL(cap);
+}
+
+static inline bool smu_v13_0_6_cap_supported(struct smu_context *smu,
+					     enum smu_v13_0_6_caps cap)
+{
+	struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context;
+
+	return !!(dpm_context->caps & BIT_ULL(cap));
+}
+
+static void smu_v13_0_14_init_caps(struct smu_context *smu)
+{
+	enum smu_v13_0_6_caps default_cap_list[] = { SMU_CAP(DPM),
+						     SMU_CAP(UNI_METRICS),
+						     SMU_CAP(SET_UCLK_MAX),
+						     SMU_CAP(DPM_POLICY),
+						     SMU_CAP(PCIE_METRICS),
+						     SMU_CAP(CTF_LIMIT),
+						     SMU_CAP(MCA_DEBUG_MODE),
+						     SMU_CAP(RMA_MSG),
+						     SMU_CAP(ACA_SYND) };
+	uint32_t fw_ver = smu->smc_fw_version;
+
+	for (int i = 0; i < ARRAY_SIZE(default_cap_list); i++)
+		smu_v13_0_6_cap_set(smu, default_cap_list[i]);
+
+	if (fw_ver >= 0x05550E00)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(OTHER_END_METRICS));
+	if (fw_ver >= 0x05551000)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS));
+	if (fw_ver >= 0x05550B00)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS));
+	if (fw_ver >= 0x5551200)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
+}
+
+static void smu_v13_0_12_init_caps(struct smu_context *smu)
+{
+	enum smu_v13_0_6_caps default_cap_list[] = { SMU_CAP(DPM),
+						     SMU_CAP(UNI_METRICS),
+						     SMU_CAP(PCIE_METRICS),
+						     SMU_CAP(CTF_LIMIT),
+						     SMU_CAP(MCA_DEBUG_MODE),
+						     SMU_CAP(RMA_MSG),
+						     SMU_CAP(ACA_SYND) };
+	uint32_t fw_ver = smu->smc_fw_version;
+
+	for (int i = 0; i < ARRAY_SIZE(default_cap_list); i++)
+		smu_v13_0_6_cap_set(smu, default_cap_list[i]);
+
+	if (fw_ver < 0x00561900)
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM));
+
+	if (fw_ver >= 0x00561700)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
+}
+
+static void smu_v13_0_6_init_caps(struct smu_context *smu)
+{
+	enum smu_v13_0_6_caps default_cap_list[] = { SMU_CAP(DPM),
+						     SMU_CAP(UNI_METRICS),
+						     SMU_CAP(SET_UCLK_MAX),
+						     SMU_CAP(DPM_POLICY),
+						     SMU_CAP(PCIE_METRICS),
+						     SMU_CAP(CTF_LIMIT),
+						     SMU_CAP(MCA_DEBUG_MODE),
+						     SMU_CAP(RMA_MSG),
+						     SMU_CAP(ACA_SYND) };
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t fw_ver = smu->smc_fw_version;
+	uint32_t pgm = (fw_ver >> 24) & 0xFF;
+
+	for (int i = 0; i < ARRAY_SIZE(default_cap_list); i++)
+		smu_v13_0_6_cap_set(smu, default_cap_list[i]);
+
+	if (fw_ver < 0x552F00)
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM));
+	if (fw_ver < 0x554500)
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(CTF_LIMIT));
+
+	if (adev->flags & AMD_IS_APU) {
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(PCIE_METRICS));
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM_POLICY));
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(RMA_MSG));
+		smu_v13_0_6_cap_clear(smu, SMU_CAP(ACA_SYND));
+
+		if (fw_ver <= 0x4556900)
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(UNI_METRICS));
+		if (fw_ver >= 0x04556F00)
+			smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS));
+		if (fw_ver >= 0x04556A00)
+			smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS));
+	} else {
+		if (fw_ver >= 0x557600)
+			smu_v13_0_6_cap_set(smu, SMU_CAP(OTHER_END_METRICS));
+		if (fw_ver < 0x00556000)
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(DPM_POLICY));
+		if (amdgpu_sriov_vf(adev) && (fw_ver < 0x556600))
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(SET_UCLK_MAX));
+		if (fw_ver < 0x556300)
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(PCIE_METRICS));
+		if (fw_ver < 0x554800)
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(MCA_DEBUG_MODE));
+		if (fw_ver >= 0x556F00)
+			smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS));
+		if (fw_ver < 0x00555a00)
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(RMA_MSG));
+		if (fw_ver < 0x00555600)
+			smu_v13_0_6_cap_clear(smu, SMU_CAP(ACA_SYND));
+		if (pgm == 0 && fw_ver >= 0x557900)
+			smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS));
+	}
+	if (((pgm == 7) && (fw_ver >= 0x7550700)) ||
+	    ((pgm == 0) && (fw_ver >= 0x00557900)) ||
+	    ((pgm == 4) && (fw_ver >= 0x4557000)))
+		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
+}
+
+static void smu_v13_0_x_init_caps(struct smu_context *smu)
+{
+	switch (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)) {
+	case IP_VERSION(13, 0, 12):
+		return smu_v13_0_12_init_caps(smu);
+	case IP_VERSION(13, 0, 14):
+		return smu_v13_0_14_init_caps(smu);
+	default:
+		return smu_v13_0_6_init_caps(smu);
+	}
+}
+
+static int smu_v13_0_6_check_fw_version(struct smu_context *smu)
+{
+	int r;
+
+	r = smu_v13_0_check_fw_version(smu);
+	/* Initialize caps flags once fw version is fetched */
+	if (!r)
+		smu_v13_0_x_init_caps(smu);
+
+	return r;
+}
+
 static int smu_v13_0_6_init_microcode(struct smu_context *smu)
 {
 	const struct smc_firmware_header_v2_1 *v2_1;
@@ -618,7 +759,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 	MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table;
 	struct PPTable_t *pptable =
 		(struct PPTable_t *)smu_table->driver_pptable;
-	bool flag = smu_v13_0_6_is_unified_metrics(smu);
+	bool flag = !smu_v13_0_6_cap_supported(smu, SMU_CAP(UNI_METRICS));
 	int ret, i, retry = 100;
 	uint32_t table_version;
 
@@ -814,8 +955,7 @@ static int smu_v13_0_6_set_default_dpm_table(struct smu_context *smu)
 	smu_v13_0_6_setup_driver_pptable(smu);
 
 	/* DPM policy not supported in older firmwares */
-	if (!(smu->adev->flags & AMD_IS_APU) &&
-	    (smu->smc_fw_version < 0x00556000)) {
+	if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(DPM_POLICY))) {
 		struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
 
 		smu_dpm->dpm_policies->policy_mask &=
@@ -992,7 +1132,7 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 	struct smu_table_context *smu_table = &smu->smu_table;
 	MetricsTableX_t *metrics_x = (MetricsTableX_t *)smu_table->metrics_table;
 	MetricsTableA_t *metrics_a = (MetricsTableA_t *)smu_table->metrics_table;
-	bool flag = smu_v13_0_6_is_unified_metrics(smu);
+	bool flag = !smu_v13_0_6_cap_supported(smu, SMU_CAP(UNI_METRICS));
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	int xcc_id;
@@ -1005,7 +1145,7 @@ static int smu_v13_0_6_get_smu_metrics_data(struct smu_context *smu,
 	switch (member) {
 	case METRICS_CURR_GFXCLK:
 	case METRICS_AVERAGE_GFXCLK:
-		if (smu->smc_fw_version >= 0x552F00) {
+		if (smu_v13_0_6_cap_supported(smu, SMU_CAP(DPM))) {
 			xcc_id = GET_INST(GC, 0);
 			*value = SMUQ10_ROUND(GET_METRIC_FIELD(GfxclkFrequency, flag)[xcc_id]);
 		} else {
@@ -1692,7 +1832,7 @@ static int smu_v13_0_6_notify_unload(struct smu_context *smu)
 static int smu_v13_0_6_mca_set_debug_mode(struct smu_context *smu, bool enable)
 {
 	/* NOTE: this ClearMcaOnRead message is only supported for smu version 85.72.0 or higher */
-	if (smu->smc_fw_version < 0x554800)
+	if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(MCA_DEBUG_MODE)))
 		return 0;
 
 	return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ClearMcaOnRead,
@@ -1837,9 +1977,8 @@ static int smu_v13_0_6_set_soft_freq_limited_range(struct smu_context *smu,
 			if (max == pstate_table->uclk_pstate.curr.max)
 				return 0;
 			/* For VF, only allowed in FW versions 85.102 or greater */
-			if (amdgpu_sriov_vf(adev) &&
-			    ((smu->smc_fw_version < 0x556600) ||
-			     (adev->flags & AMD_IS_APU)))
+			if (!smu_v13_0_6_cap_supported(smu,
+						       SMU_CAP(SET_UCLK_MAX)))
 				return -EOPNOTSUPP;
 			/* Only max clock limiting is allowed for UCLK */
 			ret = smu_v13_0_set_soft_freq_limited_range(
@@ -2043,7 +2182,7 @@ static int smu_v13_0_6_get_enabled_mask(struct smu_context *smu,
 
 	ret = smu_cmn_get_enabled_mask(smu, feature_mask);
 
-	if (ret == -EIO && smu->smc_fw_version < 0x552F00) {
+	if (ret == -EIO && !smu_v13_0_6_cap_supported(smu, SMU_CAP(DPM))) {
 		*feature_mask = 0;
 		ret = 0;
 	}
@@ -2336,11 +2475,10 @@ static int smu_v13_0_6_get_current_pcie_link_speed(struct smu_context *smu)
 
 static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table)
 {
-	bool per_inst, smu_13_0_6_per_inst, smu_13_0_14_per_inst, apu_per_inst;
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct gpu_metrics_v1_7 *gpu_metrics =
 		(struct gpu_metrics_v1_7 *)smu_table->gpu_metrics_table;
-	bool flag = smu_v13_0_6_is_unified_metrics(smu);
+	bool flag = !smu_v13_0_6_cap_supported(smu, SMU_CAP(UNI_METRICS));
 	int ret = 0, xcc_id, inst, i, j, k, idx;
 	struct amdgpu_device *adev = smu->adev;
 	MetricsTableX_t *metrics_x;
@@ -2348,6 +2486,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	struct amdgpu_xcp *xcp;
 	u16 link_width_level;
 	u32 inst_mask;
+	bool per_inst;
 
 	metrics_x = kzalloc(max(sizeof(MetricsTableX_t), sizeof(MetricsTableA_t)), GFP_KERNEL);
 	ret = smu_v13_0_6_get_metrics_table(smu, metrics_x, true);
@@ -2421,7 +2560,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 		 * table for both pf & one vf for smu version 85.99.0 or higher else report only
 		 * for pf from registers
 		 */
-		if (smu->smc_fw_version >= 0x556300) {
+		if (smu_v13_0_6_cap_supported(smu, SMU_CAP(PCIE_METRICS))) {
 			gpu_metrics->pcie_link_width = metrics_x->PCIeLinkWidth;
 			gpu_metrics->pcie_link_speed =
 				pcie_gen_to_speed(metrics_x->PCIeLinkSpeed);
@@ -2450,7 +2589,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 				metrics_x->PCIeNAKSentCountAcc;
 		gpu_metrics->pcie_nak_rcvd_count_acc =
 				metrics_x->PCIeNAKReceivedCountAcc;
-		if (smu_v13_0_6_is_other_end_count_available(smu))
+		if (smu_v13_0_6_cap_supported(smu, SMU_CAP(OTHER_END_METRICS)))
 			gpu_metrics->pcie_lc_perf_other_end_recovery =
 				metrics_x->PCIeOtherEndRecoveryAcc;
 
@@ -2475,17 +2614,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 
 	gpu_metrics->num_partition = adev->xcp_mgr->num_xcps;
 
-	apu_per_inst = (adev->flags & AMD_IS_APU) && (smu->smc_fw_version >= 0x04556A00);
-	smu_13_0_6_per_inst = !(adev->flags & AMD_IS_APU) &&
-				(amdgpu_ip_version(smu->adev, MP1_HWIP, 0)
-				 == IP_VERSION(13, 0, 6)) &&
-				(smu->smc_fw_version >= 0x556F00);
-	smu_13_0_14_per_inst = !(adev->flags & AMD_IS_APU) &&
-				(amdgpu_ip_version(smu->adev, MP1_HWIP, 0)
-				 == IP_VERSION(13, 0, 14)) &&
-				(smu->smc_fw_version >= 0x05550B00);
-
-	per_inst = apu_per_inst || smu_13_0_6_per_inst || smu_13_0_14_per_inst;
+	per_inst = smu_v13_0_6_cap_supported(smu, SMU_CAP(PER_INST_METRICS));
 
 	for_each_xcp(adev->xcp_mgr, xcp, i) {
 		amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_VCN, &inst_mask);
@@ -2516,7 +2645,8 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 				gpu_metrics->xcp_stats[i].gfx_busy_acc[idx] =
 					SMUQ10_ROUND(metrics_x->GfxBusyAcc[inst]);
 
-				if (smu_v13_0_6_is_blw_host_limit_available(smu))
+				if (smu_v13_0_6_cap_supported(
+					    smu, SMU_CAP(HST_LIMIT_METRICS)))
 					gpu_metrics->xcp_stats[i].gfx_below_host_limit_acc[idx] =
 						SMUQ10_ROUND(metrics_x->GfxclkBelowHostLimitAcc
 								[inst]);
@@ -2624,7 +2754,7 @@ static int smu_v13_0_6_get_thermal_temperature_range(struct smu_context *smu,
 		return -EINVAL;
 
 	/*Check smu version, GetCtfLimit message only supported for smu version 85.69 or higher */
-	if (smu->smc_fw_version < 0x554500)
+	if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(CTF_LIMIT)))
 		return 0;
 
 	/* Get SOC Max operating temperature */
@@ -2726,11 +2856,10 @@ static int smu_v13_0_6_smu_send_hbm_bad_page_num(struct smu_context *smu,
 
 static int smu_v13_0_6_send_rma_reason(struct smu_context *smu)
 {
-	struct amdgpu_device *adev = smu->adev;
 	int ret;
 
 	/* NOTE: the message is only valid on dGPU with pmfw 85.90.0 and above */
-	if ((adev->flags & AMD_IS_APU) || smu->smc_fw_version < 0x00555a00)
+	if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(RMA_MSG)))
 		return 0;
 
 	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RmaDueToBadPageThreshold, NULL);
@@ -2744,31 +2873,13 @@ static int smu_v13_0_6_send_rma_reason(struct smu_context *smu)
 
 static int smu_v13_0_6_reset_sdma(struct smu_context *smu, uint32_t inst_mask)
 {
-	uint32_t smu_program;
 	int ret = 0;
 
-	smu_program = (smu->smc_fw_version >> 24) & 0xff;
-	switch (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)) {
-	case IP_VERSION(13, 0, 6):
-		if (((smu_program == 7) && (smu->smc_fw_version > 0x07550700)) ||
-			((smu_program == 0) && (smu->smc_fw_version > 0x00557700)))
-			ret = smu_cmn_send_smc_msg_with_param(smu,
-				SMU_MSG_ResetSDMA, inst_mask, NULL);
-		else if ((smu_program == 4) &&
-			(smu->smc_fw_version > 0x4556e6c))
-			ret = smu_cmn_send_smc_msg_with_param(smu,
-				      SMU_MSG_ResetSDMA2, inst_mask, NULL);
-		break;
-	case IP_VERSION(13, 0, 14):
-		if ((smu_program == 5) &&
-			(smu->smc_fw_version > 0x05550f00))
-			ret = smu_cmn_send_smc_msg_with_param(smu,
-				      SMU_MSG_ResetSDMA2, inst_mask, NULL);
-		break;
-	default:
-		break;
-	}
+	if (!smu_v13_0_6_cap_supported(smu, SMU_CAP(SDMA_RESET)))
+		return -EOPNOTSUPP;
 
+	ret = smu_cmn_send_smc_msg_with_param(smu,
+						SMU_MSG_ResetSDMA, inst_mask, NULL);
 	if (ret)
 		dev_err(smu->adev->dev,
 			"failed to send ResetSDMA event with mask 0x%x\n",
@@ -3087,7 +3198,7 @@ static bool mca_smu_bank_is_valid(const struct mca_ras_info *mca_ras, struct amd
 	if (instlo != 0x03b30400)
 		return false;
 
-	if (!(adev->flags & AMD_IS_APU) && smu->smc_fw_version >= 0x00555600) {
+	if (smu_v13_0_6_cap_supported(smu, SMU_CAP(ACA_SYND))) {
 		errcode = MCA_REG__SYND__ERRORINFORMATION(entry->regs[MCA_REG_IDX_SYND]);
 		errcode &= 0xff;
 	} else {
@@ -3373,9 +3484,10 @@ static int aca_smu_get_valid_aca_bank(struct amdgpu_device *adev,
 
 static int aca_smu_parse_error_code(struct amdgpu_device *adev, struct aca_bank *bank)
 {
+	struct smu_context *smu = adev->powerplay.pp_handle;
 	int error_code;
 
-	if (!(adev->flags & AMD_IS_APU) && adev->pm.fw_version >= 0x00555600)
+	if (smu_v13_0_6_cap_supported(smu, SMU_CAP(ACA_SYND)))
 		error_code = ACA_REG__SYND__ERRORINFORMATION(bank->regs[ACA_REG_IDX_SYND]);
 	else
 		error_code = ACA_REG__STATUS__ERRORCODE(bank->regs[ACA_REG_IDX_STATUS]);
@@ -3413,7 +3525,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.fini_power = smu_v13_0_fini_power,
 	.check_fw_status = smu_v13_0_6_check_fw_status,
 	/* pptable related */
-	.check_fw_version = smu_v13_0_check_fw_version,
+	.check_fw_version = smu_v13_0_6_check_fw_version,
 	.set_driver_table_location = smu_v13_0_set_driver_table_location,
 	.set_tool_table_location = smu_v13_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v13_0_notify_memory_pool_location,
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index ebccb74306a7..f30b3d5eeca5 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -160,6 +160,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms,
 	formats = komeda_get_layer_fourcc_list(&mdev->fmt_tbl,
 					       kwb_conn->wb_layer->layer_type,
 					       &n_formats);
+	if (!formats) {
+		kfree(kwb_conn);
+		return -ENOMEM;
+	}
 
 	err = drm_writeback_connector_init(&kms->base, wb_conn,
 					   &komeda_wb_connector_funcs,
diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
index 0e282b7b167c..b9eb67e3fa90 100644
--- a/drivers/gpu/drm/ast/ast_dp.c
+++ b/drivers/gpu/drm/ast/ast_dp.c
@@ -195,7 +195,7 @@ static bool __ast_dp_wait_enable(struct ast_device *ast, bool enabled)
 	if (enabled)
 		vgacrdf_test |= AST_IO_VGACRDF_DP_VIDEO_ENABLE;
 
-	for (i = 0; i < 200; ++i) {
+	for (i = 0; i < 1000; ++i) {
 		if (i)
 			mdelay(1);
 		vgacrdf = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xdf,
diff --git a/drivers/gpu/drm/display/drm_dp_cec.c b/drivers/gpu/drm/display/drm_dp_cec.c
index 007ceb281d00..56a4965e518c 100644
--- a/drivers/gpu/drm/display/drm_dp_cec.c
+++ b/drivers/gpu/drm/display/drm_dp_cec.c
@@ -311,16 +311,6 @@ void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address)
 	if (!aux->transfer)
 		return;
 
-#ifndef CONFIG_MEDIA_CEC_RC
-	/*
-	 * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by
-	 * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined.
-	 *
-	 * Do this here as well to ensure the tests against cec_caps are
-	 * correct.
-	 */
-	cec_caps &= ~CEC_CAP_RC;
-#endif
 	cancel_delayed_work_sync(&aux->cec.unregister_work);
 
 	mutex_lock(&aux->cec.lock);
@@ -337,7 +327,9 @@ void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address)
 		num_las = CEC_MAX_LOG_ADDRS;
 
 	if (aux->cec.adap) {
-		if (aux->cec.adap->capabilities == cec_caps &&
+		/* Check if the adapter properties have changed */
+		if ((aux->cec.adap->capabilities & CEC_CAP_MONITOR_ALL) ==
+		    (cec_caps & CEC_CAP_MONITOR_ALL) &&
 		    aux->cec.adap->available_log_addrs == num_las) {
 			/* Unchanged, so just set the phys addr */
 			cec_s_phys_addr(aux->cec.adap, source_physical_address, false);
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 251f94313717..aca442c25209 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -743,6 +743,15 @@ retry:
 	if ((conn_configured & mask) != mask && conn_configured != conn_seq)
 		goto retry;
 
+	for (i = 0; i < count; i++) {
+		struct drm_connector *connector = connectors[i];
+
+		if (connector->has_tile)
+			drm_client_get_tile_offsets(dev, connectors, connector_count,
+						    modes, offsets, i,
+						    connector->tile_h_loc, connector->tile_v_loc);
+	}
+
 	/*
 	 * If the BIOS didn't enable everything it could, fall back to have the
 	 * same user experiencing of lighting up as much as possible like the
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index c9008113111b..fb3614a7ba44 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1354,14 +1354,14 @@ int drm_fb_helper_set_par(struct fb_info *info)
 }
 EXPORT_SYMBOL(drm_fb_helper_set_par);
 
-static void pan_set(struct drm_fb_helper *fb_helper, int x, int y)
+static void pan_set(struct drm_fb_helper *fb_helper, int dx, int dy)
 {
 	struct drm_mode_set *mode_set;
 
 	mutex_lock(&fb_helper->client.modeset_mutex);
 	drm_client_for_each_modeset(mode_set, &fb_helper->client) {
-		mode_set->x = x;
-		mode_set->y = y;
+		mode_set->x += dx;
+		mode_set->y += dy;
 	}
 	mutex_unlock(&fb_helper->client.modeset_mutex);
 }
@@ -1370,16 +1370,18 @@ static int pan_display_atomic(struct fb_var_screeninfo *var,
 			      struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
-	int ret;
+	int ret, dx, dy;
 
-	pan_set(fb_helper, var->xoffset, var->yoffset);
+	dx = var->xoffset - info->var.xoffset;
+	dy = var->yoffset - info->var.yoffset;
+	pan_set(fb_helper, dx, dy);
 
 	ret = drm_client_modeset_commit_locked(&fb_helper->client);
 	if (!ret) {
 		info->var.xoffset = var->xoffset;
 		info->var.yoffset = var->yoffset;
 	} else
-		pan_set(fb_helper, info->var.xoffset, info->var.yoffset);
+		pan_set(fb_helper, -dx, -dy);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
index fc1e517e074a..7e6ce905bdaf 100644
--- a/drivers/gpu/drm/i915/display/intel_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_backlight.c
@@ -41,8 +41,9 @@ static u32 scale(u32 source_val,
 {
 	u64 target_val;
 
-	WARN_ON(source_min > source_max);
-	WARN_ON(target_min > target_max);
+	if (WARN_ON(source_min >= source_max) ||
+	    WARN_ON(target_min > target_max))
+		return target_min;
 
 	/* defensive */
 	source_val = clamp(source_val, source_min, source_max);
diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c
index 1aa0b298c278..50ec0c3c7588 100644
--- a/drivers/gpu/drm/i915/display/intel_display_driver.c
+++ b/drivers/gpu/drm/i915/display/intel_display_driver.c
@@ -397,7 +397,6 @@ void intel_display_driver_resume_access(struct intel_display *display)
  */
 bool intel_display_driver_check_access(struct intel_display *display)
 {
-	char comm[TASK_COMM_LEN];
 	char current_task[TASK_COMM_LEN + 16];
 	char allowed_task[TASK_COMM_LEN + 16] = "none";
 
@@ -406,12 +405,11 @@ bool intel_display_driver_check_access(struct intel_display *display)
 		return true;
 
 	snprintf(current_task, sizeof(current_task), "%s[%d]",
-		 get_task_comm(comm, current),
-		 task_pid_vnr(current));
+		 current->comm, task_pid_vnr(current));
 
 	if (display->access.allowed_task)
 		snprintf(allowed_task, sizeof(allowed_task), "%s[%d]",
-			 get_task_comm(comm, display->access.allowed_task),
+			 display->access.allowed_task->comm,
 			 task_pid_vnr(display->access.allowed_task));
 
 	drm_dbg_kms(display->drm,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f1f3b1bb1e89..aa77ddcee42c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1791,7 +1791,7 @@ int intel_dp_dsc_max_src_input_bpc(struct intel_display *display)
 	if (DISPLAY_VER(display) == 11)
 		return 10;
 
-	return 0;
+	return intel_dp_dsc_min_src_input_bpc();
 }
 
 int intel_dp_dsc_compute_max_bpp(const struct intel_connector *connector,
@@ -2072,11 +2072,10 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp,
 	/* Compressed BPP should be less than the Input DSC bpp */
 	dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1);
 
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) {
-		if (valid_dsc_bpp[i] < dsc_min_bpp)
+	for (i = ARRAY_SIZE(valid_dsc_bpp) - 1; i >= 0; i--) {
+		if (valid_dsc_bpp[i] < dsc_min_bpp ||
+		    valid_dsc_bpp[i] > dsc_max_bpp)
 			continue;
-		if (valid_dsc_bpp[i] > dsc_max_bpp)
-			break;
 
 		ret = dsc_compute_link_config(intel_dp,
 					      pipe_config,
@@ -2829,7 +2828,6 @@ static void intel_dp_compute_as_sdp(struct intel_dp *intel_dp,
 
 	crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_ADAPTIVE_SYNC);
 
-	/* Currently only DP_AS_SDP_AVT_FIXED_VTOTAL mode supported */
 	as_sdp->sdp_type = DP_SDP_ADAPTIVE_SYNC;
 	as_sdp->length = 0x9;
 	as_sdp->duration_incr_ms = 0;
@@ -2840,7 +2838,7 @@ static void intel_dp_compute_as_sdp(struct intel_dp *intel_dp,
 		as_sdp->target_rr = drm_mode_vrefresh(adjusted_mode);
 		as_sdp->target_rr_divider = true;
 	} else {
-		as_sdp->mode = DP_AS_SDP_AVT_FIXED_VTOTAL;
+		as_sdp->mode = DP_AS_SDP_AVT_DYNAMIC_VTOTAL;
 		as_sdp->vtotal = adjusted_mode->vtotal;
 		as_sdp->target_rr = 0;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 0c44fc7dd86c..a65cf97ad12d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -341,6 +341,10 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp,
 
 			break;
 		}
+
+		/* Allow using zero step to indicate one try */
+		if (!step)
+			break;
 	}
 
 	if (slots < 0) {
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 7464b44c8bb3..1bab7c34a794 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -41,7 +41,7 @@ intel_hdcp_adjust_hdcp_line_rekeying(struct intel_encoder *encoder,
 	u32 rekey_bit = 0;
 
 	/* Here we assume HDMI is in TMDS mode of operation */
-	if (encoder->type != INTEL_OUTPUT_HDMI)
+	if (!intel_encoder_is_hdmi(encoder))
 		return;
 
 	if (DISPLAY_VER(display) >= 30) {
@@ -2188,6 +2188,19 @@ static int intel_hdcp2_check_link(struct intel_connector *connector)
 
 		drm_dbg_kms(display->drm,
 			    "HDCP2.2 Downstream topology change\n");
+
+		ret = hdcp2_authenticate_repeater_topology(connector);
+		if (!ret) {
+			intel_hdcp_update_value(connector,
+						DRM_MODE_CONTENT_PROTECTION_ENABLED,
+						true);
+			goto out;
+		}
+
+		drm_dbg_kms(display->drm,
+			    "[CONNECTOR:%d:%s] Repeater topology auth failed.(%d)\n",
+			    connector->base.base.id, connector->base.name,
+			    ret);
 	} else {
 		drm_dbg_kms(display->drm,
 			    "[CONNECTOR:%d:%s] HDCP2.2 link failed, retrying auth\n",
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index ff9764cac1e7..80e558042d97 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -106,8 +106,6 @@ static const u32 icl_sdr_y_plane_formats[] = {
 	DRM_FORMAT_Y216,
 	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
-	DRM_FORMAT_XVYU12_16161616,
-	DRM_FORMAT_XVYU16161616,
 };
 
 static const u32 icl_sdr_uv_plane_formats[] = {
@@ -134,8 +132,6 @@ static const u32 icl_sdr_uv_plane_formats[] = {
 	DRM_FORMAT_Y216,
 	DRM_FORMAT_XYUV8888,
 	DRM_FORMAT_XVYU2101010,
-	DRM_FORMAT_XVYU12_16161616,
-	DRM_FORMAT_XVYU16161616,
 };
 
 static const u32 icl_hdr_plane_formats[] = {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index fe69f2c8527d..ae3343c81a64 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -209,8 +209,6 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
 	struct address_space *mapping = obj->base.filp->f_mapping;
 	unsigned int max_segment = i915_sg_segment_size(i915->drm.dev);
 	struct sg_table *st;
-	struct sgt_iter sgt_iter;
-	struct page *page;
 	int ret;
 
 	/*
@@ -239,9 +237,7 @@ rebuild_st:
 		 * for PAGE_SIZE chunks instead may be helpful.
 		 */
 		if (max_segment > PAGE_SIZE) {
-			for_each_sgt_page(page, sgt_iter, st)
-				put_page(page);
-			sg_free_table(st);
+			shmem_sg_free_table(st, mapping, false, false);
 			kfree(st);
 
 			max_segment = PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 12f1ba7ca9c1..cc05bd9e43b4 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1469,6 +1469,19 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
 	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
 }
 
+static void __update_guc_busyness_running_state(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&guc->timestamp.lock, flags);
+	for_each_engine(engine, gt, id)
+		engine->stats.guc.running = false;
+	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
+}
+
 static void __update_guc_busyness_stats(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -1619,6 +1632,9 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 	if (!guc_submission_initialized(guc))
 		return;
 
+	/* Assume no engines are running and set running state to false */
+	__update_guc_busyness_running_state(guc);
+
 	/*
 	 * There is a race with suspend flow where the worker runs after suspend
 	 * and causes an unclaimed register access warning. Cancel the worker
@@ -5519,12 +5535,20 @@ static inline void guc_log_context(struct drm_printer *p,
 {
 	drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id);
 	drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca);
-	drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n",
-		   ce->ring->head,
-		   ce->lrc_reg_state[CTX_RING_HEAD]);
-	drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n",
-		   ce->ring->tail,
-		   ce->lrc_reg_state[CTX_RING_TAIL]);
+	if (intel_context_pin_if_active(ce)) {
+		drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n",
+			   ce->ring->head,
+			   ce->lrc_reg_state[CTX_RING_HEAD]);
+		drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n",
+			   ce->ring->tail,
+			   ce->lrc_reg_state[CTX_RING_TAIL]);
+		intel_context_unpin(ce);
+	} else {
+		drm_printf(p, "\t\tLRC Head: Internal %u, Memory not pinned\n",
+			   ce->ring->head);
+		drm_printf(p, "\t\tLRC Tail: Internal %u, Memory not pinned\n",
+			   ce->ring->tail);
+	}
 	drm_printf(p, "\t\tContext Pin Count: %u\n",
 		   atomic_read(&ce->pin_count));
 	drm_printf(p, "\t\tGuC ID Ref Count: %u\n",
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2406cda75b7b..5384d1bb4923 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4802,7 +4802,7 @@ err_unlock:
 	return ret;
 }
 
-static struct ctl_table oa_table[] = {
+static const struct ctl_table oa_table[] = {
 	{
 	 .procname = "perf_stream_paranoid",
 	 .data = &i915_perf_stream_paranoid,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index cd25e5afe55a..f22ad2882697 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -358,7 +358,7 @@ static const struct of_device_id mtk_drm_of_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mtk_drm_of_ids);
 
-static int mtk_drm_match(struct device *dev, void *data)
+static int mtk_drm_match(struct device *dev, const void *data)
 {
 	if (!strncmp(dev_name(dev), "mediatek-drm", sizeof("mediatek-drm") - 1))
 		return true;
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 2cb2e5675807..cd659b9fd1d9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -279,7 +279,6 @@ nouveau_channel_ctor(struct nouveau_cli *cli, bool priv, u64 runm,
 	const u64 plength = 0x10000;
 	const u64 ioffset = plength;
 	const u64 ilength = 0x02000;
-	char name[TASK_COMM_LEN];
 	int cid, ret;
 	u64 size;
 
@@ -338,8 +337,7 @@ nouveau_channel_ctor(struct nouveau_cli *cli, bool priv, u64 runm,
 		chan->userd = &chan->user;
 	}
 
-	get_task_comm(name, current);
-	snprintf(args.name, sizeof(args.name), "%s[%d]", name, task_pid_nr(current));
+	snprintf(args.name, sizeof(args.name), "%s[%d]", current->comm, task_pid_nr(current));
 
 	ret = nvif_object_ctor(&device->object, "abi16ChanUser", 0, hosts[cid].oclass,
 			       &args, sizeof(args), &chan->user);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 21d2d9ca5e85..5664c4c71faf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -1175,7 +1175,7 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_cli *cli;
-	char name[32], tmpname[TASK_COMM_LEN];
+	char name[32];
 	int ret;
 
 	/* need to bring up power immediately if opening device */
@@ -1185,10 +1185,9 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 		return ret;
 	}
 
-	get_task_comm(tmpname, current);
 	rcu_read_lock();
 	snprintf(name, sizeof(name), "%s[%d]",
-		 tmpname, pid_nr(rcu_dereference(fpriv->pid)));
+		 current->comm, pid_nr(rcu_dereference(fpriv->pid)));
 	rcu_read_unlock();
 
 	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) {
diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c
index 89a699370a59..c67e1f906785 100644
--- a/drivers/gpu/drm/tiny/bochs.c
+++ b/drivers/gpu/drm/tiny/bochs.c
@@ -757,7 +757,6 @@ static void bochs_pci_remove(struct pci_dev *pdev)
 
 	drm_dev_unplug(dev);
 	drm_atomic_helper_shutdown(dev);
-	drm_dev_put(dev);
 }
 
 static void bochs_pci_shutdown(struct pci_dev *pdev)
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index da203045df9b..72b6a119412f 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -107,8 +107,10 @@ v3d_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->bin_job->base, V3D_BIN);
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->bin_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -118,8 +120,10 @@ v3d_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->render_job->base, V3D_RENDER);
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->render_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -129,8 +133,10 @@ v3d_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->csd_job->base, V3D_CSD);
 		trace_v3d_csd_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->csd_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
@@ -167,8 +173,10 @@ v3d_hub_irq(int irq, void *arg)
 
 		v3d_job_update_stats(&v3d->tfu_job->base, V3D_TFU);
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
-		dma_fence_signal(&fence->base);
+
 		v3d->tfu_job = NULL;
+		dma_fence_signal(&fence->base);
+
 		status = IRQ_HANDLED;
 	}
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c
index b3664c12843d..f92133a01195 100644
--- a/drivers/gpu/drm/virtio/virtgpu_prime.c
+++ b/drivers/gpu/drm/virtio/virtgpu_prime.c
@@ -189,10 +189,11 @@ static void virtgpu_dma_buf_free_obj(struct drm_gem_object *obj)
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj);
 	struct virtio_gpu_device *vgdev = obj->dev->dev_private;
 	struct dma_buf_attachment *attach = obj->import_attach;
-	struct dma_resv *resv = attach->dmabuf->resv;
 
 	if (attach) {
-		dma_resv_lock(resv, NULL);
+		struct dma_buf *dmabuf = attach->dmabuf;
+
+		dma_resv_lock(dmabuf->resv, NULL);
 
 		virtio_gpu_detach_object_fenced(bo);
 
@@ -200,10 +201,10 @@ static void virtgpu_dma_buf_free_obj(struct drm_gem_object *obj)
 			dma_buf_unmap_attachment(attach, bo->sgt,
 						 DMA_BIDIRECTIONAL);
 
-		dma_resv_unlock(resv);
+		dma_resv_unlock(dmabuf->resv);
 
-		dma_buf_detach(attach->dmabuf, attach);
-		dma_buf_put(attach->dmabuf);
+		dma_buf_detach(dmabuf, attach);
+		dma_buf_put(dmabuf);
 	}
 
 	if (bo->created) {
diff --git a/drivers/gpu/drm/xe/regs/xe_oa_regs.h b/drivers/gpu/drm/xe/regs/xe_oa_regs.h
index a49561e9f3c3..a79ad2da070c 100644
--- a/drivers/gpu/drm/xe/regs/xe_oa_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_oa_regs.h
@@ -51,6 +51,10 @@
 /* Common to all OA units */
 #define  OA_OACONTROL_REPORT_BC_MASK		REG_GENMASK(9, 9)
 #define  OA_OACONTROL_COUNTER_SIZE_MASK		REG_GENMASK(8, 8)
+#define  OAG_OACONTROL_USED_BITS \
+	(OAG_OACONTROL_OA_PES_DISAG_EN | OAG_OACONTROL_OA_CCS_SELECT_MASK | \
+	 OAG_OACONTROL_OA_COUNTER_SEL_MASK | OAG_OACONTROL_OA_COUNTER_ENABLE | \
+	 OA_OACONTROL_REPORT_BC_MASK | OA_OACONTROL_COUNTER_SIZE_MASK)
 
 #define OAG_OA_DEBUG XE_REG(0xdaf8, XE_REG_OPTION_MASKED)
 #define  OAG_OA_DEBUG_DISABLE_MMIO_TRG			REG_BIT(14)
@@ -78,6 +82,8 @@
 #define OAM_CONTEXT_CONTROL_OFFSET		(0x1bc)
 #define OAM_CONTROL_OFFSET			(0x194)
 #define  OAM_CONTROL_COUNTER_SEL_MASK		REG_GENMASK(3, 1)
+#define  OAM_OACONTROL_USED_BITS \
+	(OAM_CONTROL_COUNTER_SEL_MASK | OAG_OACONTROL_OA_COUNTER_ENABLE)
 #define OAM_DEBUG_OFFSET			(0x198)
 #define OAM_STATUS_OFFSET			(0x19c)
 #define OAM_MMIO_TRG_OFFSET			(0x1d0)
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 81dc7795c065..39fe485d2085 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -119,11 +119,7 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count,
 	drm_puts(&p, "\n**** GuC CT ****\n");
 	xe_guc_ct_snapshot_print(ss->guc.ct, &p);
 
-	/*
-	 * Don't add a new section header here because the mesa debug decoder
-	 * tool expects the context information to be in the 'GuC CT' section.
-	 */
-	/* drm_puts(&p, "\n**** Contexts ****\n"); */
+	drm_puts(&p, "\n**** Contexts ****\n");
 	xe_guc_exec_queue_snapshot_print(ss->ge, &p);
 
 	drm_puts(&p, "\n**** Job ****\n");
@@ -395,42 +391,34 @@ int xe_devcoredump_init(struct xe_device *xe)
 /**
  * xe_print_blob_ascii85 - print a BLOB to some useful location in ASCII85
  *
- * The output is split to multiple lines because some print targets, e.g. dmesg
- * cannot handle arbitrarily long lines. Note also that printing to dmesg in
- * piece-meal fashion is not possible, each separate call to drm_puts() has a
- * line-feed automatically added! Therefore, the entire output line must be
- * constructed in a local buffer first, then printed in one atomic output call.
+ * The output is split into multiple calls to drm_puts() because some print
+ * targets, e.g. dmesg, cannot handle arbitrarily long lines. These targets may
+ * add newlines, as is the case with dmesg: each drm_puts() call creates a
+ * separate line.
  *
  * There is also a scheduler yield call to prevent the 'task has been stuck for
  * 120s' kernel hang check feature from firing when printing to a slow target
  * such as dmesg over a serial port.
  *
- * TODO: Add compression prior to the ASCII85 encoding to shrink huge buffers down.
- *
  * @p: the printer object to output to
  * @prefix: optional prefix to add to output string
+ * @suffix: optional suffix to add at the end. 0 disables it and is
+ *          not added to the output, which is useful when using multiple calls
+ *          to dump data to @p
  * @blob: the Binary Large OBject to dump out
  * @offset: offset in bytes to skip from the front of the BLOB, must be a multiple of sizeof(u32)
  * @size: the size in bytes of the BLOB, must be a multiple of sizeof(u32)
  */
-void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
+void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
 			   const void *blob, size_t offset, size_t size)
 {
 	const u32 *blob32 = (const u32 *)blob;
 	char buff[ASCII85_BUFSZ], *line_buff;
 	size_t line_pos = 0;
 
-	/*
-	 * Splitting blobs across multiple lines is not compatible with the mesa
-	 * debug decoder tool. Note that even dropping the explicit '\n' below
-	 * doesn't help because the GuC log is so big some underlying implementation
-	 * still splits the lines at 512K characters. So just bail completely for
-	 * the moment.
-	 */
-	return;
-
 #define DMESG_MAX_LINE_LEN	800
-#define MIN_SPACE		(ASCII85_BUFSZ + 2)		/* 85 + "\n\0" */
+	/* Always leave space for the suffix char and the \0 */
+#define MIN_SPACE		(ASCII85_BUFSZ + 2)	/* 85 + "<suffix>\0" */
 
 	if (size & 3)
 		drm_printf(p, "Size not word aligned: %zu", size);
@@ -462,7 +450,6 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 		line_pos += strlen(line_buff + line_pos);
 
 		if ((line_pos + MIN_SPACE) >= DMESG_MAX_LINE_LEN) {
-			line_buff[line_pos++] = '\n';
 			line_buff[line_pos++] = 0;
 
 			drm_puts(p, line_buff);
@@ -474,10 +461,11 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
 		}
 	}
 
+	if (suffix)
+		line_buff[line_pos++] = suffix;
+
 	if (line_pos) {
-		line_buff[line_pos++] = '\n';
 		line_buff[line_pos++] = 0;
-
 		drm_puts(p, line_buff);
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
index 6a17e6d60102..5391a80a4d1b 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump.h
@@ -29,7 +29,7 @@ static inline int xe_devcoredump_init(struct xe_device *xe)
 }
 #endif
 
-void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix,
+void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix,
 			   const void *blob, size_t offset, size_t size);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 4de26470a4ae..4e1839b483a0 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -521,7 +521,7 @@ static int wait_for_lmem_ready(struct xe_device *xe)
 	drm_dbg(&xe->drm, "Waiting for lmem initialization\n");
 
 	start = jiffies;
-	timeout = start + msecs_to_jiffies(60 * 1000); /* 60 sec! */
+	timeout = start + secs_to_jiffies(60); /* 60 sec! */
 
 	do {
 		if (signal_pending(current))
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 26e64530ada2..5d6fb79957b6 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -532,8 +532,10 @@ static int all_fw_domain_init(struct xe_gt *gt)
 	if (IS_SRIOV_PF(gt_to_xe(gt)) && !xe_gt_is_media_type(gt))
 		xe_lmtt_init_hw(&gt_to_tile(gt)->sriov.pf.lmtt);
 
-	if (IS_SRIOV_PF(gt_to_xe(gt)))
+	if (IS_SRIOV_PF(gt_to_xe(gt))) {
+		xe_gt_sriov_pf_init(gt);
 		xe_gt_sriov_pf_init_hw(gt);
+	}
 
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index e71fc3d2bda2..6f906c8e8108 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -68,6 +68,19 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
 	return 0;
 }
 
+/**
+ * xe_gt_sriov_pf_init - Prepare SR-IOV PF data structures on PF.
+ * @gt: the &xe_gt to initialize
+ *
+ * Late one-time initialization of the PF data.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_pf_init(struct xe_gt *gt)
+{
+	return xe_gt_sriov_pf_migration_init(gt);
+}
+
 static bool pf_needs_enable_ggtt_guest_update(struct xe_device *xe)
 {
 	return GRAPHICS_VERx100(xe) == 1200;
@@ -90,7 +103,6 @@ void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 		pf_enable_ggtt_guest_update(gt);
 
 	xe_gt_sriov_pf_service_update(gt);
-	xe_gt_sriov_pf_migration_init(gt);
 }
 
 static u32 pf_get_vf_regs_stride(struct xe_device *xe)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
index 96fab779a906..f474509411c0 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
@@ -10,6 +10,7 @@ struct xe_gt;
 
 #ifdef CONFIG_PCI_IOV
 int xe_gt_sriov_pf_init_early(struct xe_gt *gt);
+int xe_gt_sriov_pf_init(struct xe_gt *gt);
 void xe_gt_sriov_pf_init_hw(struct xe_gt *gt);
 void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid);
 void xe_gt_sriov_pf_restart(struct xe_gt *gt);
@@ -19,6 +20,11 @@ static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
 	return 0;
 }
 
+static inline int xe_gt_sriov_pf_init(struct xe_gt *gt)
+{
+	return 0;
+}
+
 static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt)
 {
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 8b65c5e959cc..50c8076b5158 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1724,7 +1724,8 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 			   snapshot->g2h_outstanding);
 
 		if (snapshot->ctb)
-			xe_print_blob_ascii85(p, "CTB data", snapshot->ctb, 0, snapshot->ctb_size);
+			xe_print_blob_ascii85(p, "CTB data", '\n',
+					      snapshot->ctb, 0, snapshot->ctb_size);
 	} else {
 		drm_puts(p, "CT disabled\n");
 	}
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index df4cfb698cdb..2baa4d95571f 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -211,8 +211,10 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_
 	remain = snapshot->size;
 	for (i = 0; i < snapshot->num_chunks; i++) {
 		size_t size = min(GUC_LOG_CHUNK_SIZE, remain);
+		const char *prefix = i ? NULL : "Log data";
+		char suffix = i == snapshot->num_chunks - 1 ? '\n' : 0;
 
-		xe_print_blob_ascii85(p, i ? NULL : "Log data", snapshot->copy[i], 0, size);
+		xe_print_blob_ascii85(p, prefix, suffix, snapshot->copy[i], 0, size);
 		remain -= size;
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index eeb96b5f49e2..fa873f3d0a9d 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -237,7 +237,6 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream)
 	u32 tail, hw_tail, partial_report_size, available;
 	int report_size = stream->oa_buffer.format->size;
 	unsigned long flags;
-	bool pollin;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
@@ -282,11 +281,11 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream)
 	stream->oa_buffer.tail = tail;
 
 	available = xe_oa_circ_diff(stream, stream->oa_buffer.tail, stream->oa_buffer.head);
-	pollin = available >= stream->wait_num_reports * report_size;
+	stream->pollin = available >= stream->wait_num_reports * report_size;
 
 	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
 
-	return pollin;
+	return stream->pollin;
 }
 
 static enum hrtimer_restart xe_oa_poll_check_timer_cb(struct hrtimer *hrtimer)
@@ -294,10 +293,8 @@ static enum hrtimer_restart xe_oa_poll_check_timer_cb(struct hrtimer *hrtimer)
 	struct xe_oa_stream *stream =
 		container_of(hrtimer, typeof(*stream), poll_check_timer);
 
-	if (xe_oa_buffer_check_unlocked(stream)) {
-		stream->pollin = true;
+	if (xe_oa_buffer_check_unlocked(stream))
 		wake_up(&stream->poll_wq);
-	}
 
 	hrtimer_forward_now(hrtimer, ns_to_ktime(stream->poll_period_ns));
 
@@ -452,6 +449,12 @@ static u32 __oa_ccs_select(struct xe_oa_stream *stream)
 	return val;
 }
 
+static u32 __oactrl_used_bits(struct xe_oa_stream *stream)
+{
+	return stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG ?
+		OAG_OACONTROL_USED_BITS : OAM_OACONTROL_USED_BITS;
+}
+
 static void xe_oa_enable(struct xe_oa_stream *stream)
 {
 	const struct xe_oa_format *format = stream->oa_buffer.format;
@@ -472,14 +475,14 @@ static void xe_oa_enable(struct xe_oa_stream *stream)
 	    stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG)
 		val |= OAG_OACONTROL_OA_PES_DISAG_EN;
 
-	xe_mmio_write32(&stream->gt->mmio, regs->oa_ctrl, val);
+	xe_mmio_rmw32(&stream->gt->mmio, regs->oa_ctrl, __oactrl_used_bits(stream), val);
 }
 
 static void xe_oa_disable(struct xe_oa_stream *stream)
 {
 	struct xe_mmio *mmio = &stream->gt->mmio;
 
-	xe_mmio_write32(mmio, __oa_regs(stream)->oa_ctrl, 0);
+	xe_mmio_rmw32(mmio, __oa_regs(stream)->oa_ctrl, __oactrl_used_bits(stream), 0);
 	if (xe_mmio_wait32(mmio, __oa_regs(stream)->oa_ctrl,
 			   OAG_OACONTROL_OA_COUNTER_ENABLE, 0, 50000, NULL, false))
 		drm_err(&stream->oa->xe->drm,
@@ -2534,6 +2537,8 @@ static void __xe_oa_init_oa_units(struct xe_gt *gt)
 			u->type = DRM_XE_OA_UNIT_TYPE_OAM;
 		}
 
+		xe_mmio_write32(&gt->mmio, u->regs.oa_ctrl, 0);
+
 		/* Ensure MMIO trigger remains disabled till there is a stream */
 		xe_mmio_write32(&gt->mmio, u->regs.oa_debug,
 				oag_configure_mmio_trigger(NULL, false));
diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c
index 8ec1b84cbb9e..57cf01efc07f 100644
--- a/drivers/gpu/drm/xe/xe_observation.c
+++ b/drivers/gpu/drm/xe/xe_observation.c
@@ -56,7 +56,7 @@ int xe_observation_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 	}
 }
 
-static struct ctl_table observation_ctl_table[] = {
+static const struct ctl_table observation_ctl_table[] = {
 	{
 	 .procname = "observation_paranoid",
 	 .data = &xe_observation_paranoid,
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index 0b63fd48ea92..979f6d3239ba 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -1564,7 +1564,7 @@ static void zynqmp_dp_bridge_atomic_enable(struct drm_bridge *bridge,
 
 	pm_runtime_get_sync(dp->dev);
 
-	mutex_lock(&dp->lock);
+	guard(mutex)(&dp->lock);
 	zynqmp_dp_disp_enable(dp, old_bridge_state);
 
 	/*
@@ -1624,7 +1624,6 @@ static void zynqmp_dp_bridge_atomic_enable(struct drm_bridge *bridge,
 	zynqmp_dp_write(dp, ZYNQMP_DP_SOFTWARE_RESET,
 			ZYNQMP_DP_SOFTWARE_RESET_ALL);
 	zynqmp_dp_write(dp, ZYNQMP_DP_MAIN_STREAM_ENABLE, 1);
-	mutex_unlock(&dp->lock);
 }
 
 static void zynqmp_dp_bridge_atomic_disable(struct drm_bridge *bridge,
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.h b/drivers/gpu/drm/xlnx/zynqmp_dpsub.h
index 49875529c2a4..d771b8b199e0 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.h
+++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.h
@@ -60,6 +60,7 @@ struct zynqmp_dpsub_audio;
  * @layers: Video and graphics layers
  * @dp: The DisplayPort controller
  * @dma_align: DMA alignment constraint (must be a power of 2)
+ * @audio: DP audio data
  */
 struct zynqmp_dpsub {
 	struct device *dev;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index b53eb569bd49..dfc245867a46 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -570,6 +570,8 @@ config HID_LED
 
 config HID_LENOVO
 	tristate "Lenovo / Thinkpad devices"
+	depends on ACPI
+	select ACPI_PLATFORM_PROFILE
 	select NEW_LEDS
 	select LEDS_CLASS
 	help
@@ -1167,7 +1169,8 @@ config HID_TOPRE
 	tristate "Topre REALFORCE keyboards"
 	depends on HID
 	help
-	  Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key keyboards.
+	  Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key and
+          Topre REALFORCE R3S 87 key keyboards.
 
 config HID_THINGM
 	tristate "ThingM blink(1) USB RGB LED"
@@ -1374,10 +1377,6 @@ endmenu
 
 source "drivers/hid/bpf/Kconfig"
 
-endif # HID
-
-source "drivers/hid/usbhid/Kconfig"
-
 source "drivers/hid/i2c-hid/Kconfig"
 
 source "drivers/hid/intel-ish-hid/Kconfig"
@@ -1388,4 +1387,10 @@ source "drivers/hid/surface-hid/Kconfig"
 
 source "drivers/hid/intel-thc-hid/Kconfig"
 
+endif # HID
+
+# USB support may be used with HID disabled
+
+source "drivers/hid/usbhid/Kconfig"
+
 endif # HID_SUPPORT
diff --git a/drivers/hid/amd-sfh-hid/Kconfig b/drivers/hid/amd-sfh-hid/Kconfig
index 329de5e12c1a..3291786a5ee6 100644
--- a/drivers/hid/amd-sfh-hid/Kconfig
+++ b/drivers/hid/amd-sfh-hid/Kconfig
@@ -5,7 +5,6 @@ menu "AMD SFH HID Support"
 
 config AMD_SFH_HID
 	tristate "AMD Sensor Fusion Hub"
-	depends on HID
 	depends on X86
 	help
 	  If you say yes to this option, support will be included for the
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 7e1ae2a2bcc2..49812a76b7ed 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -474,6 +474,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2015)
 			table = magic_keyboard_2015_fn_keys;
 		else if (hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021 ||
+			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024 ||
 			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021 ||
 			 hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021)
 			table = apple2021_fn_keys;
@@ -545,6 +546,9 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 		}
 	}
 
+	if (usage->hid == 0xc0301) /* Omoton KB066 quirk */
+		code = KEY_F6;
+
 	if (usage->code != code) {
 		input_event_with_scancode(input, usage->type, code, usage->hid, value);
 
@@ -1150,6 +1154,10 @@ static const struct hid_device_id apple_devices[] = {
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
 	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021),
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
+	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021),
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY },
 	{ HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021),
diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c
index 6ece56b850fc..56e858066c3c 100644
--- a/drivers/hid/hid-corsair-void.c
+++ b/drivers/hid/hid-corsair-void.c
@@ -553,7 +553,7 @@ static void corsair_void_battery_remove_work_handler(struct work_struct *work)
 static void corsair_void_battery_add_work_handler(struct work_struct *work)
 {
 	struct corsair_void_drvdata *drvdata;
-	struct power_supply_config psy_cfg;
+	struct power_supply_config psy_cfg = {};
 	struct power_supply *new_supply;
 
 	drvdata = container_of(work, struct corsair_void_drvdata,
@@ -726,6 +726,7 @@ static void corsair_void_remove(struct hid_device *hid_dev)
 	if (drvdata->battery)
 		power_supply_unregister(drvdata->battery);
 
+	cancel_delayed_work_sync(&drvdata->delayed_status_work);
 	cancel_delayed_work_sync(&drvdata->delayed_firmware_work);
 	sysfs_remove_group(&hid_dev->dev.kobj, &corsair_void_attr_group);
 }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index c448de53bf91..7e400624908e 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -184,6 +184,7 @@
 #define USB_DEVICE_ID_APPLE_IRCONTROL4	0x8242
 #define USB_DEVICE_ID_APPLE_IRCONTROL5	0x8243
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021   0x029c
+#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024   0x0320
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021   0x029a
 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021   0x029f
 #define USB_DEVICE_ID_APPLE_TOUCHBAR_BACKLIGHT 0x8102
@@ -1095,6 +1096,7 @@
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001		0x3001
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003		0x3003
 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008		0x3008
+#define USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473		0x5473
 
 #define I2C_VENDOR_ID_RAYDIUM		0x2386
 #define I2C_PRODUCT_ID_RAYDIUM_4B33	0x4b33
@@ -1301,6 +1303,7 @@
 #define USB_VENDOR_ID_TOPRE			0x0853
 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_108			0x0148
 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_87			0x0146
+#define USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87			0x0313
 
 #define USB_VENDOR_ID_TOPSEED		0x0766
 #define USB_DEVICE_ID_TOPSEED_CYBERLINK	0x0204
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index 4d00bc4d656e..a7d9ca02779e 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -32,9 +32,7 @@
 #include <linux/leds.h>
 #include <linux/workqueue.h>
 
-#if IS_ENABLED(CONFIG_ACPI_PLATFORM_PROFILE)
 #include <linux/platform_profile.h>
-#endif /* CONFIG_ACPI_PLATFORM_PROFILE */
 
 #include "hid-ids.h"
 
@@ -730,13 +728,10 @@ static int lenovo_raw_event_TP_X12_tab(struct hid_device *hdev, u32 raw_data)
 			if (hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB) {
 				report_key_event(input, KEY_RFKILL);
 				return 1;
-			}
-#if IS_ENABLED(CONFIG_ACPI_PLATFORM_PROFILE)
-			else {
+			} else {
 				platform_profile_cycle();
 				return 1;
 			}
-#endif /* CONFIG_ACPI_PLATFORM_PROFILE */
 			return 0;
 		case TP_X12_RAW_HOTKEY_FN_F10:
 			/* TAB1 has PICKUP Phone and TAB2 use Snipping tool*/
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 82900857bfd8..e50887a6d22c 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1679,9 +1679,12 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 		break;
 	}
 
-	if (suffix)
+	if (suffix) {
 		hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL,
 						 "%s %s", hdev->name, suffix);
+		if (!hi->input->name)
+			return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index e0bbf0c6345d..5d7a418ccdbe 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -891,6 +891,7 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DPAD) },
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) },
 	{ }
 };
 
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index af38fc8eb34f..c9e65e9088b3 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -313,6 +313,7 @@ struct steam_device {
 	u16 rumble_left;
 	u16 rumble_right;
 	unsigned int sensor_timestamp_us;
+	struct work_struct unregister_work;
 };
 
 static int steam_recv_report(struct steam_device *steam,
@@ -1050,10 +1051,10 @@ static void steam_mode_switch_cb(struct work_struct *work)
 							struct steam_device, mode_switch);
 	unsigned long flags;
 	bool client_opened;
-	steam->gamepad_mode = !steam->gamepad_mode;
 	if (!lizard_mode)
 		return;
 
+	steam->gamepad_mode = !steam->gamepad_mode;
 	if (steam->gamepad_mode)
 		steam_set_lizard_mode(steam, false);
 	else {
@@ -1072,6 +1073,31 @@ static void steam_mode_switch_cb(struct work_struct *work)
 	}
 }
 
+static void steam_work_unregister_cb(struct work_struct *work)
+{
+	struct steam_device *steam = container_of(work, struct steam_device,
+							unregister_work);
+	unsigned long flags;
+	bool connected;
+	bool opened;
+
+	spin_lock_irqsave(&steam->lock, flags);
+	opened = steam->client_opened;
+	connected = steam->connected;
+	spin_unlock_irqrestore(&steam->lock, flags);
+
+	if (connected) {
+		if (opened) {
+			steam_sensors_unregister(steam);
+			steam_input_unregister(steam);
+		} else {
+			steam_set_lizard_mode(steam, lizard_mode);
+			steam_input_register(steam);
+			steam_sensors_register(steam);
+		}
+	}
+}
+
 static bool steam_is_valve_interface(struct hid_device *hdev)
 {
 	struct hid_report_enum *rep_enum;
@@ -1117,8 +1143,7 @@ static int steam_client_ll_open(struct hid_device *hdev)
 	steam->client_opened++;
 	spin_unlock_irqrestore(&steam->lock, flags);
 
-	steam_sensors_unregister(steam);
-	steam_input_unregister(steam);
+	schedule_work(&steam->unregister_work);
 
 	return 0;
 }
@@ -1135,11 +1160,7 @@ static void steam_client_ll_close(struct hid_device *hdev)
 	connected = steam->connected && !steam->client_opened;
 	spin_unlock_irqrestore(&steam->lock, flags);
 
-	if (connected) {
-		steam_set_lizard_mode(steam, lizard_mode);
-		steam_input_register(steam);
-		steam_sensors_register(steam);
-	}
+	schedule_work(&steam->unregister_work);
 }
 
 static int steam_client_ll_raw_request(struct hid_device *hdev,
@@ -1231,6 +1252,7 @@ static int steam_probe(struct hid_device *hdev,
 	INIT_LIST_HEAD(&steam->list);
 	INIT_WORK(&steam->rumble_work, steam_haptic_rumble_cb);
 	steam->sensor_timestamp_us = 0;
+	INIT_WORK(&steam->unregister_work, steam_work_unregister_cb);
 
 	/*
 	 * With the real steam controller interface, do not connect hidraw.
@@ -1291,6 +1313,7 @@ err_cancel_work:
 	cancel_work_sync(&steam->work_connect);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->rumble_work);
+	cancel_work_sync(&steam->unregister_work);
 
 	return ret;
 }
@@ -1307,6 +1330,7 @@ static void steam_remove(struct hid_device *hdev)
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->work_connect);
 	cancel_work_sync(&steam->rumble_work);
+	cancel_work_sync(&steam->unregister_work);
 	hid_destroy_device(steam->client_hdev);
 	steam->client_hdev = NULL;
 	steam->client_opened = 0;
@@ -1593,13 +1617,13 @@ static void steam_do_deck_input_event(struct steam_device *steam,
 
 	if (!(b9 & BIT(6)) && steam->did_mode_switch) {
 		steam->did_mode_switch = false;
-		cancel_delayed_work_sync(&steam->mode_switch);
+		cancel_delayed_work(&steam->mode_switch);
 	} else if (!steam->client_opened && (b9 & BIT(6)) && !steam->did_mode_switch) {
 		steam->did_mode_switch = true;
 		schedule_delayed_work(&steam->mode_switch, 45 * HZ / 100);
 	}
 
-	if (!steam->gamepad_mode)
+	if (!steam->gamepad_mode && lizard_mode)
 		return;
 
 	lpad_touched = b10 & BIT(3);
@@ -1669,7 +1693,7 @@ static void steam_do_deck_sensors_event(struct steam_device *steam,
 	 */
 	steam->sensor_timestamp_us += 4000;
 
-	if (!steam->gamepad_mode)
+	if (!steam->gamepad_mode && lizard_mode)
 		return;
 
 	input_event(sensors, EV_MSC, MSC_TIMESTAMP, steam->sensor_timestamp_us);
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index 6c3e758bbb09..3b81468a1df2 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -171,7 +171,7 @@ static void thrustmaster_interrupts(struct hid_device *hdev)
 	b_ep = ep->desc.bEndpointAddress;
 
 	/* Are the expected endpoints present? */
-	u8 ep_addr[1] = {b_ep};
+	u8 ep_addr[2] = {b_ep, 0};
 
 	if (!usb_check_int_endpoints(usbif, ep_addr)) {
 		hid_err(hdev, "Unexpected non-int endpoint\n");
diff --git a/drivers/hid/hid-topre.c b/drivers/hid/hid-topre.c
index 848361f6225d..ccedf8721722 100644
--- a/drivers/hid/hid-topre.c
+++ b/drivers/hid/hid-topre.c
@@ -29,6 +29,11 @@ static const __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		hid_info(hdev,
 			"fixing up Topre REALFORCE keyboard report descriptor\n");
 		rdesc[72] = 0x02;
+	} else if (*rsize >= 106 && rdesc[28] == 0x29 && rdesc[29] == 0xe7 &&
+				    rdesc[30] == 0x81 && rdesc[31] == 0x00) {
+		hid_info(hdev,
+			"fixing up Topre REALFORCE keyboard report descriptor\n");
+		rdesc[31] = 0x02;
 	}
 	return rdesc;
 }
@@ -38,6 +43,8 @@ static const struct hid_device_id topre_id_table[] = {
 			 USB_DEVICE_ID_TOPRE_REALFORCE_R2_108) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPRE,
 			 USB_DEVICE_ID_TOPRE_REALFORCE_R2_87) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_TOPRE,
+			 USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, topre_id_table);
diff --git a/drivers/hid/hid-winwing.c b/drivers/hid/hid-winwing.c
index 831b760c66ea..d4afbbd27807 100644
--- a/drivers/hid/hid-winwing.c
+++ b/drivers/hid/hid-winwing.c
@@ -106,6 +106,8 @@ static int winwing_init_led(struct hid_device *hdev,
 						"%s::%s",
 						dev_name(&input->dev),
 						info->led_name);
+		if (!led->cdev.name)
+			return -ENOMEM;
 
 		ret = devm_led_classdev_register(&hdev->dev, &led->cdev);
 		if (ret)
diff --git a/drivers/hid/i2c-hid/Kconfig b/drivers/hid/i2c-hid/Kconfig
index ef7c595c9403..e8d51f410cc1 100644
--- a/drivers/hid/i2c-hid/Kconfig
+++ b/drivers/hid/i2c-hid/Kconfig
@@ -2,7 +2,7 @@
 menuconfig I2C_HID
 	tristate "I2C HID support"
 	default y
-	depends on I2C && INPUT && HID
+	depends on I2C
 
 if I2C_HID
 
diff --git a/drivers/hid/intel-ish-hid/Kconfig b/drivers/hid/intel-ish-hid/Kconfig
index 253dc10d35ef..568c8688784e 100644
--- a/drivers/hid/intel-ish-hid/Kconfig
+++ b/drivers/hid/intel-ish-hid/Kconfig
@@ -6,7 +6,6 @@ config INTEL_ISH_HID
 	tristate "Intel Integrated Sensor Hub"
 	default n
 	depends on X86
-	depends on HID
 	help
 	  The Integrated Sensor Hub (ISH) enables the ability to offload
 	  sensor polling and algorithm processing to a dedicated low power
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index cdd80c653918..07e90d51f073 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -36,6 +36,8 @@
 #define PCI_DEVICE_ID_INTEL_ISH_ARL_H		0x7745
 #define PCI_DEVICE_ID_INTEL_ISH_ARL_S		0x7F78
 #define PCI_DEVICE_ID_INTEL_ISH_LNL_M		0xA845
+#define PCI_DEVICE_ID_INTEL_ISH_PTL_H		0xE345
+#define PCI_DEVICE_ID_INTEL_ISH_PTL_P		0xE445
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index 3cd53fc80634..4c861119e97a 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -517,6 +517,10 @@ static int ish_fw_reset_handler(struct ishtp_device *dev)
 	/* ISH FW is dead */
 	if (!ish_is_input_ready(dev))
 		return	-EPIPE;
+
+	/* Send clock sync at once after reset */
+	ishtp_dev->prev_sync = 0;
+
 	/*
 	 * Set HOST2ISH.ILUP. Apparently we need this BEFORE sending
 	 * RESET_NOTIFY_ACK - FW will be checking for it
@@ -577,15 +581,14 @@ static void fw_reset_work_fn(struct work_struct *work)
  */
 static void _ish_sync_fw_clock(struct ishtp_device *dev)
 {
-	static unsigned long	prev_sync;
-	uint64_t	usec;
+	struct ipc_time_update_msg time = {};
 
-	if (prev_sync && time_before(jiffies, prev_sync + 20 * HZ))
+	if (dev->prev_sync && time_before(jiffies, dev->prev_sync + 20 * HZ))
 		return;
 
-	prev_sync = jiffies;
-	usec = ktime_to_us(ktime_get_boottime());
-	ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t));
+	dev->prev_sync = jiffies;
+	/* The fields of time would be updated while sending message */
+	ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time));
 }
 
 /**
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 9e2401291a2f..ff0fc8010072 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -26,9 +26,11 @@
 enum ishtp_driver_data_index {
 	ISHTP_DRIVER_DATA_NONE,
 	ISHTP_DRIVER_DATA_LNL_M,
+	ISHTP_DRIVER_DATA_PTL,
 };
 
 #define ISH_FW_GEN_LNL_M "lnlm"
+#define ISH_FW_GEN_PTL "ptl"
 
 #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin"
 #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin"
@@ -37,6 +39,9 @@ static struct ishtp_driver_data ishtp_driver_data[] = {
 	[ISHTP_DRIVER_DATA_LNL_M] = {
 		.fw_generation = ISH_FW_GEN_LNL_M,
 	},
+	[ISHTP_DRIVER_DATA_PTL] = {
+		.fw_generation = ISH_FW_GEN_PTL,
+	},
 };
 
 static const struct pci_device_id ish_pci_tbl[] = {
@@ -63,6 +68,8 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_H)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_S)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_LNL_M), .driver_data = ISHTP_DRIVER_DATA_LNL_M},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_H), .driver_data = ISHTP_DRIVER_DATA_PTL},
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_P), .driver_data = ISHTP_DRIVER_DATA_PTL},
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
index 44eddc411e97..ec9f6e87aaf2 100644
--- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
+++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
@@ -253,6 +253,8 @@ struct ishtp_device {
 	unsigned int	ipc_tx_cnt;
 	unsigned long long	ipc_tx_bytes_cnt;
 
+	/* Time of the last clock sync */
+	unsigned long prev_sync;
 	const struct ishtp_hw_ops *ops;
 	size_t	mtu;
 	uint32_t	ishtp_msg_hdr;
diff --git a/drivers/hid/intel-thc-hid/Kconfig b/drivers/hid/intel-thc-hid/Kconfig
index 91ec84902db8..0351d1137607 100644
--- a/drivers/hid/intel-thc-hid/Kconfig
+++ b/drivers/hid/intel-thc-hid/Kconfig
@@ -7,7 +7,6 @@ menu "Intel THC HID Support"
 config INTEL_THC_HID
 	tristate "Intel Touch Host Controller"
 	depends on ACPI
-	select HID
 	help
 	  THC (Touch Host Controller) is the name of the IP block in PCH that
 	  interfaces with Touch Devices (ex: touchscreen, touchpad etc.). It
diff --git a/drivers/hid/surface-hid/Kconfig b/drivers/hid/surface-hid/Kconfig
index 7ce9b5d641eb..d0cfd0d29926 100644
--- a/drivers/hid/surface-hid/Kconfig
+++ b/drivers/hid/surface-hid/Kconfig
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0+
 menu "Surface System Aggregator Module HID support"
 	depends on SURFACE_AGGREGATOR
-	depends on INPUT
 
 config SURFACE_HID
 	tristate "HID transport driver for Surface System Aggregator Module"
@@ -39,4 +38,3 @@ endmenu
 
 config SURFACE_HID_CORE
 	tristate
-	select HID
diff --git a/drivers/hid/usbhid/Kconfig b/drivers/hid/usbhid/Kconfig
index 7c2032f7f44d..f3194767a45e 100644
--- a/drivers/hid/usbhid/Kconfig
+++ b/drivers/hid/usbhid/Kconfig
@@ -5,8 +5,7 @@ menu "USB HID support"
 config USB_HID
 	tristate "USB HID transport layer"
 	default y
-	depends on USB && INPUT
-	select HID
+	depends on HID
 	help
 	  Say Y here if you want to connect USB keyboards,
 	  mice, joysticks, graphic tablets, or any other HID based devices
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index af5d1dc451f6..f2e6f55d6ca6 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -141,7 +141,7 @@ static int sysctl_record_panic_msg = 1;
  * sysctl option to allow the user to control whether kmsg data should be
  * reported to Hyper-V on panic.
  */
-static struct ctl_table hv_ctl_table[] = {
+static const struct ctl_table hv_ctl_table[] = {
 	{
 		.procname	= "hyperv_record_panic_msg",
 		.data		= &sysctl_record_panic_msg,
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index b7c0b1e3c23b..9703d60e9bbf 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -332,7 +332,7 @@ static int hwmon_attr_base(enum hwmon_sensor_types type)
 
 static DEFINE_MUTEX(hwmon_pec_mutex);
 
-static int hwmon_match_device(struct device *dev, void *data)
+static int hwmon_match_device(struct device *dev, const void *data)
 {
 	return dev->class == &hwmon_class;
 }
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index ea38ecf26fcb..0a9380350fb5 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -75,22 +75,54 @@ struct coresight_device *coresight_get_percpu_sink(int cpu)
 }
 EXPORT_SYMBOL_GPL(coresight_get_percpu_sink);
 
+static struct coresight_device *coresight_get_source(struct list_head *path)
+{
+	struct coresight_device *csdev;
+
+	if (!path)
+		return NULL;
+
+	csdev = list_first_entry(path, struct coresight_node, link)->csdev;
+	if (!coresight_is_device_source(csdev))
+		return NULL;
+
+	return csdev;
+}
+
+/**
+ * coresight_blocks_source - checks whether the connection matches the source
+ * of path if connection is bound to specific source.
+ * @src:	The source device of the trace path
+ * @conn:	The connection of one outport
+ *
+ * Return false if the connection doesn't have a source binded or source of the
+ * path matches the source binds to connection.
+ */
+static bool coresight_blocks_source(struct coresight_device *src,
+				    struct coresight_connection *conn)
+{
+	return conn->filter_src_fwnode && (conn->filter_src_dev != src);
+}
+
 static struct coresight_connection *
-coresight_find_out_connection(struct coresight_device *src_dev,
-			      struct coresight_device *dest_dev)
+coresight_find_out_connection(struct coresight_device *csdev,
+			      struct coresight_device *out_dev,
+			      struct coresight_device *trace_src)
 {
 	int i;
 	struct coresight_connection *conn;
 
-	for (i = 0; i < src_dev->pdata->nr_outconns; i++) {
-		conn = src_dev->pdata->out_conns[i];
-		if (conn->dest_dev == dest_dev)
+	for (i = 0; i < csdev->pdata->nr_outconns; i++) {
+		conn = csdev->pdata->out_conns[i];
+		if (coresight_blocks_source(trace_src, conn))
+			continue;
+		if (conn->dest_dev == out_dev)
 			return conn;
 	}
 
-	dev_err(&src_dev->dev,
-		"couldn't find output connection, src_dev: %s, dest_dev: %s\n",
-		dev_name(&src_dev->dev), dev_name(&dest_dev->dev));
+	dev_err(&csdev->dev,
+		"couldn't find output connection, csdev: %s, out_dev: %s\n",
+		dev_name(&csdev->dev), dev_name(&out_dev->dev));
 
 	return ERR_PTR(-ENODEV);
 }
@@ -251,7 +283,8 @@ static void coresight_disable_sink(struct coresight_device *csdev)
 
 static int coresight_enable_link(struct coresight_device *csdev,
 				 struct coresight_device *parent,
-				 struct coresight_device *child)
+				 struct coresight_device *child,
+				 struct coresight_device *source)
 {
 	int link_subtype;
 	struct coresight_connection *inconn, *outconn;
@@ -259,8 +292,8 @@ static int coresight_enable_link(struct coresight_device *csdev,
 	if (!parent || !child)
 		return -EINVAL;
 
-	inconn = coresight_find_out_connection(parent, csdev);
-	outconn = coresight_find_out_connection(csdev, child);
+	inconn = coresight_find_out_connection(parent, csdev, source);
+	outconn = coresight_find_out_connection(csdev, child, source);
 	link_subtype = csdev->subtype.link_subtype;
 
 	if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG && IS_ERR(inconn))
@@ -273,15 +306,16 @@ static int coresight_enable_link(struct coresight_device *csdev,
 
 static void coresight_disable_link(struct coresight_device *csdev,
 				   struct coresight_device *parent,
-				   struct coresight_device *child)
+				   struct coresight_device *child,
+				   struct coresight_device *source)
 {
 	struct coresight_connection *inconn, *outconn;
 
 	if (!parent || !child)
 		return;
 
-	inconn = coresight_find_out_connection(parent, csdev);
-	outconn = coresight_find_out_connection(csdev, child);
+	inconn = coresight_find_out_connection(parent, csdev, source);
+	outconn = coresight_find_out_connection(csdev, child, source);
 
 	link_ops(csdev)->disable(csdev, inconn, outconn);
 }
@@ -375,7 +409,8 @@ static void coresight_disable_path_from(struct list_head *path,
 		case CORESIGHT_DEV_TYPE_LINK:
 			parent = list_prev_entry(nd, link)->csdev;
 			child = list_next_entry(nd, link)->csdev;
-			coresight_disable_link(csdev, parent, child);
+			coresight_disable_link(csdev, parent, child,
+					       coresight_get_source(path));
 			break;
 		default:
 			break;
@@ -418,7 +453,9 @@ int coresight_enable_path(struct list_head *path, enum cs_mode mode,
 	u32 type;
 	struct coresight_node *nd;
 	struct coresight_device *csdev, *parent, *child;
+	struct coresight_device *source;
 
+	source = coresight_get_source(path);
 	list_for_each_entry_reverse(nd, path, link) {
 		csdev = nd->csdev;
 		type = csdev->type;
@@ -456,7 +493,7 @@ int coresight_enable_path(struct list_head *path, enum cs_mode mode,
 		case CORESIGHT_DEV_TYPE_LINK:
 			parent = list_prev_entry(nd, link)->csdev;
 			child = list_next_entry(nd, link)->csdev;
-			ret = coresight_enable_link(csdev, parent, child);
+			ret = coresight_enable_link(csdev, parent, child, source);
 			if (ret)
 				goto err;
 			break;
@@ -619,6 +656,7 @@ static void coresight_drop_device(struct coresight_device *csdev)
 /**
  * _coresight_build_path - recursively build a path from a @csdev to a sink.
  * @csdev:	The device to start from.
+ * @source:	The trace source device of the path.
  * @sink:	The final sink we want in this path.
  * @path:	The list to add devices to.
  *
@@ -628,6 +666,7 @@ static void coresight_drop_device(struct coresight_device *csdev)
  * the source is the first device and the sink the last one.
  */
 static int _coresight_build_path(struct coresight_device *csdev,
+				 struct coresight_device *source,
 				 struct coresight_device *sink,
 				 struct list_head *path)
 {
@@ -641,7 +680,7 @@ static int _coresight_build_path(struct coresight_device *csdev,
 
 	if (coresight_is_percpu_source(csdev) && coresight_is_percpu_sink(sink) &&
 	    sink == per_cpu(csdev_sink, source_ops(csdev)->cpu_id(csdev))) {
-		if (_coresight_build_path(sink, sink, path) == 0) {
+		if (_coresight_build_path(sink, source, sink, path) == 0) {
 			found = true;
 			goto out;
 		}
@@ -652,8 +691,12 @@ static int _coresight_build_path(struct coresight_device *csdev,
 		struct coresight_device *child_dev;
 
 		child_dev = csdev->pdata->out_conns[i]->dest_dev;
+
+		if (coresight_blocks_source(source, csdev->pdata->out_conns[i]))
+			continue;
+
 		if (child_dev &&
-		    _coresight_build_path(child_dev, sink, path) == 0) {
+		    _coresight_build_path(child_dev, source, sink, path) == 0) {
 			found = true;
 			break;
 		}
@@ -698,7 +741,7 @@ struct list_head *coresight_build_path(struct coresight_device *source,
 
 	INIT_LIST_HEAD(path);
 
-	rc = _coresight_build_path(source, sink, path);
+	rc = _coresight_build_path(source, source, sink, path);
 	if (rc) {
 		kfree(path);
 		return ERR_PTR(rc);
@@ -927,6 +970,16 @@ static int coresight_orphan_match(struct device *dev, void *data)
 	for (i = 0; i < src_csdev->pdata->nr_outconns; i++) {
 		conn = src_csdev->pdata->out_conns[i];
 
+		/* Fix filter source device before skip the port */
+		if (conn->filter_src_fwnode && !conn->filter_src_dev) {
+			if (dst_csdev &&
+			    (conn->filter_src_fwnode == dst_csdev->dev.fwnode) &&
+			    !WARN_ON_ONCE(!coresight_is_device_source(dst_csdev)))
+				conn->filter_src_dev = dst_csdev;
+			else
+				still_orphan = true;
+		}
+
 		/* Skip the port if it's already connected. */
 		if (conn->dest_dev)
 			continue;
@@ -977,18 +1030,40 @@ static int coresight_fixup_orphan_conns(struct coresight_device *csdev)
 			 csdev, coresight_orphan_match);
 }
 
+static int coresight_clear_filter_source(struct device *dev, void *data)
+{
+	int i;
+	struct coresight_device *source = data;
+	struct coresight_device *csdev = to_coresight_device(dev);
+
+	for (i = 0; i < csdev->pdata->nr_outconns; ++i) {
+		if (csdev->pdata->out_conns[i]->filter_src_dev == source)
+			csdev->pdata->out_conns[i]->filter_src_dev = NULL;
+	}
+	return 0;
+}
+
 /* coresight_remove_conns - Remove other device's references to this device */
 static void coresight_remove_conns(struct coresight_device *csdev)
 {
 	int i, j;
 	struct coresight_connection *conn;
 
+	if (coresight_is_device_source(csdev))
+		bus_for_each_dev(&coresight_bustype, NULL, csdev,
+				 coresight_clear_filter_source);
+
 	/*
 	 * Remove the input connection references from the destination device
 	 * for each output connection.
 	 */
 	for (i = 0; i < csdev->pdata->nr_outconns; i++) {
 		conn = csdev->pdata->out_conns[i];
+		if (conn->filter_src_fwnode) {
+			conn->filter_src_dev = NULL;
+			fwnode_handle_put(conn->filter_src_fwnode);
+		}
+
 		if (!conn->dest_dev)
 			continue;
 
diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c
index 02ef2b945a0c..9be53be8964b 100644
--- a/drivers/hwtracing/coresight/coresight-dummy.c
+++ b/drivers/hwtracing/coresight/coresight-dummy.c
@@ -11,10 +11,12 @@
 #include <linux/pm_runtime.h>
 
 #include "coresight-priv.h"
+#include "coresight-trace-id.h"
 
 struct dummy_drvdata {
 	struct device			*dev;
 	struct coresight_device		*csdev;
+	u8				traceid;
 };
 
 DEFINE_CORESIGHT_DEVLIST(source_devs, "dummy_source");
@@ -72,6 +74,32 @@ static const struct coresight_ops dummy_sink_cs_ops = {
 	.sink_ops = &dummy_sink_ops,
 };
 
+/* User can get the trace id of dummy source from this node. */
+static ssize_t traceid_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	unsigned long val;
+	struct dummy_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+	val = drvdata->traceid;
+	return sysfs_emit(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(traceid);
+
+static struct attribute *coresight_dummy_attrs[] = {
+	&dev_attr_traceid.attr,
+	NULL,
+};
+
+static const struct attribute_group coresight_dummy_group = {
+	.attrs = coresight_dummy_attrs,
+};
+
+static const struct attribute_group *coresight_dummy_groups[] = {
+	&coresight_dummy_group,
+	NULL,
+};
+
 static int dummy_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -79,6 +107,11 @@ static int dummy_probe(struct platform_device *pdev)
 	struct coresight_platform_data *pdata;
 	struct dummy_drvdata *drvdata;
 	struct coresight_desc desc = { 0 };
+	int ret = 0, trace_id = 0;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
 
 	if (of_device_is_compatible(node, "arm,coresight-dummy-source")) {
 
@@ -90,6 +123,26 @@ static int dummy_probe(struct platform_device *pdev)
 		desc.subtype.source_subtype =
 					CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS;
 		desc.ops = &dummy_source_cs_ops;
+		desc.groups = coresight_dummy_groups;
+
+		ret = coresight_get_static_trace_id(dev, &trace_id);
+		if (!ret) {
+			/* Get the static id if id is set in device tree. */
+			ret = coresight_trace_id_get_static_system_id(trace_id);
+			if (ret < 0) {
+				dev_err(dev, "Fail to get static id.\n");
+				return ret;
+			}
+		} else {
+			/* Get next available id if id is not set in device tree. */
+			trace_id = coresight_trace_id_get_system_id();
+			if (trace_id < 0) {
+				ret = trace_id;
+				return ret;
+			}
+		}
+		drvdata->traceid = (u8)trace_id;
+
 	} else if (of_device_is_compatible(node, "arm,coresight-dummy-sink")) {
 		desc.name = coresight_alloc_device_name(&sink_devs, dev);
 		if (!desc.name)
@@ -104,27 +157,35 @@ static int dummy_probe(struct platform_device *pdev)
 	}
 
 	pdata = coresight_get_platform_data(dev);
-	if (IS_ERR(pdata))
-		return PTR_ERR(pdata);
+	if (IS_ERR(pdata)) {
+		ret = PTR_ERR(pdata);
+		goto free_id;
+	}
 	pdev->dev.platform_data = pdata;
 
-	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
-	if (!drvdata)
-		return -ENOMEM;
-
 	drvdata->dev = &pdev->dev;
 	platform_set_drvdata(pdev, drvdata);
 
 	desc.pdata = pdev->dev.platform_data;
 	desc.dev = &pdev->dev;
 	drvdata->csdev = coresight_register(&desc);
-	if (IS_ERR(drvdata->csdev))
-		return PTR_ERR(drvdata->csdev);
+	if (IS_ERR(drvdata->csdev)) {
+		ret = PTR_ERR(drvdata->csdev);
+		goto free_id;
+	}
 
 	pm_runtime_enable(dev);
 	dev_dbg(dev, "Dummy device initialized\n");
 
-	return 0;
+	ret = 0;
+	goto out;
+
+free_id:
+	if (IS_VALID_CS_TRACE_ID(drvdata->traceid))
+		coresight_trace_id_put_system_id(drvdata->traceid);
+
+out:
+	return ret;
 }
 
 static void dummy_remove(struct platform_device *pdev)
@@ -132,6 +193,8 @@ static void dummy_remove(struct platform_device *pdev)
 	struct dummy_drvdata *drvdata = platform_get_drvdata(pdev);
 	struct device *dev = &pdev->dev;
 
+	if (IS_VALID_CS_TRACE_ID(drvdata->traceid))
+		coresight_trace_id_put_system_id(drvdata->traceid);
 	pm_runtime_disable(dev);
 	coresight_unregister(drvdata->csdev);
 }
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c
index dd8c74f893db..2c1a60577728 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-core.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c
@@ -6,6 +6,7 @@
 #include <linux/acpi.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
+#include <linux/kvm_host.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/types.h>
@@ -268,10 +269,28 @@ struct etm4_enable_arg {
  */
 static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata)
 {
+	u64 trfcr;
+
 	/* If the CPU doesn't support FEAT_TRF, nothing to do */
 	if (!drvdata->trfcr)
 		return;
-	cpu_prohibit_trace();
+
+	trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE);
+
+	write_trfcr(trfcr);
+	kvm_tracing_set_el1_configuration(trfcr);
+}
+
+static u64 etm4x_get_kern_user_filter(struct etmv4_drvdata *drvdata)
+{
+	u64 trfcr = drvdata->trfcr;
+
+	if (drvdata->config.mode & ETM_MODE_EXCL_KERN)
+		trfcr &= ~TRFCR_EL1_ExTRE;
+	if (drvdata->config.mode & ETM_MODE_EXCL_USER)
+		trfcr &= ~TRFCR_EL1_E0TRE;
+
+	return trfcr;
 }
 
 /*
@@ -286,18 +305,28 @@ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata)
  */
 static void etm4x_allow_trace(struct etmv4_drvdata *drvdata)
 {
-	u64 trfcr = drvdata->trfcr;
+	u64 trfcr, guest_trfcr;
 
 	/* If the CPU doesn't support FEAT_TRF, nothing to do */
-	if (!trfcr)
+	if (!drvdata->trfcr)
 		return;
 
-	if (drvdata->config.mode & ETM_MODE_EXCL_KERN)
-		trfcr &= ~TRFCR_ELx_ExTRE;
-	if (drvdata->config.mode & ETM_MODE_EXCL_USER)
-		trfcr &= ~TRFCR_ELx_E0TRE;
+	if (drvdata->config.mode & ETM_MODE_EXCL_HOST)
+		trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE);
+	else
+		trfcr = etm4x_get_kern_user_filter(drvdata);
 
 	write_trfcr(trfcr);
+
+	/* Set filters for guests and pass to KVM */
+	if (drvdata->config.mode & ETM_MODE_EXCL_GUEST)
+		guest_trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE);
+	else
+		guest_trfcr = etm4x_get_kern_user_filter(drvdata);
+
+	/* TRFCR_EL1 doesn't have CX so mask it out. */
+	guest_trfcr &= ~TRFCR_EL2_CX;
+	kvm_tracing_set_el1_configuration(guest_trfcr);
 }
 
 #ifdef CONFIG_ETM4X_IMPDEF_FEATURE
@@ -655,6 +684,12 @@ static int etm4_parse_event_config(struct coresight_device *csdev,
 	if (attr->exclude_user)
 		config->mode = ETM_MODE_EXCL_USER;
 
+	if (attr->exclude_host)
+		config->mode |= ETM_MODE_EXCL_HOST;
+
+	if (attr->exclude_guest)
+		config->mode |= ETM_MODE_EXCL_GUEST;
+
 	/* Always start from the default config */
 	etm4_set_default_config(config);
 
@@ -1141,9 +1176,9 @@ static void cpu_detect_trace_filtering(struct etmv4_drvdata *drvdata)
 	 * tracing at the kernel EL and EL0, forcing to use the
 	 * virtual time as the timestamp.
 	 */
-	trfcr = (TRFCR_ELx_TS_VIRTUAL |
-		 TRFCR_ELx_ExTRE |
-		 TRFCR_ELx_E0TRE);
+	trfcr = (TRFCR_EL1_TS_VIRTUAL |
+		 TRFCR_EL1_ExTRE |
+		 TRFCR_EL1_E0TRE);
 
 	/* If we are running at EL2, allow tracing the CONTEXTIDR_EL2. */
 	if (is_kernel_in_hyp_mode())
diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
index a9f19629f3f8..c767f8ae4cf1 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c
@@ -2319,11 +2319,11 @@ static ssize_t ts_source_show(struct device *dev,
 		goto out;
 	}
 
-	switch (drvdata->trfcr & TRFCR_ELx_TS_MASK) {
-	case TRFCR_ELx_TS_VIRTUAL:
-	case TRFCR_ELx_TS_GUEST_PHYSICAL:
-	case TRFCR_ELx_TS_PHYSICAL:
-		val = FIELD_GET(TRFCR_ELx_TS_MASK, drvdata->trfcr);
+	switch (drvdata->trfcr & TRFCR_EL1_TS_MASK) {
+	case TRFCR_EL1_TS_VIRTUAL:
+	case TRFCR_EL1_TS_GUEST_PHYSICAL:
+	case TRFCR_EL1_TS_PHYSICAL:
+		val = FIELD_GET(TRFCR_EL1_TS_MASK, drvdata->trfcr);
 		break;
 	default:
 		val = -1;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h
index 9e9165f62e81..1119762b5cec 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.h
+++ b/drivers/hwtracing/coresight/coresight-etm4x.h
@@ -817,7 +817,7 @@ enum etm_impdef_type {
  * @s_ex_level: Secure ELs where tracing is supported.
  */
 struct etmv4_config {
-	u32				mode;
+	u64				mode;
 	u32				pe_sel;
 	u32				cfg;
 	u32				eventctrl0;
diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c
index 33efe1acbef7..8faf51469bb8 100644
--- a/drivers/hwtracing/coresight/coresight-funnel.c
+++ b/drivers/hwtracing/coresight/coresight-funnel.c
@@ -86,14 +86,14 @@ static int funnel_enable(struct coresight_device *csdev,
 	bool first_enable = false;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (atomic_read(&in->dest_refcnt) == 0) {
+	if (in->dest_refcnt == 0) {
 		if (drvdata->base)
 			rc = dynamic_funnel_enable_hw(drvdata, in->dest_port);
 		if (!rc)
 			first_enable = true;
 	}
 	if (!rc)
-		atomic_inc(&in->dest_refcnt);
+		in->dest_refcnt++;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	if (first_enable)
@@ -130,7 +130,7 @@ static void funnel_disable(struct coresight_device *csdev,
 	bool last_disable = false;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (atomic_dec_return(&in->dest_refcnt) == 0) {
+	if (--in->dest_refcnt == 0) {
 		if (drvdata->base)
 			dynamic_funnel_disable_hw(drvdata, in->dest_port);
 		last_disable = true;
diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c
index 64e171eaad82..8192ba3279f0 100644
--- a/drivers/hwtracing/coresight/coresight-platform.c
+++ b/drivers/hwtracing/coresight/coresight-platform.c
@@ -243,6 +243,27 @@ static int of_coresight_parse_endpoint(struct device *dev,
 		conn.dest_fwnode = fwnode_handle_get(rdev_fwnode);
 		conn.dest_port = rendpoint.port;
 
+		/*
+		 * Get the firmware node of the filter source through the
+		 * reference. This could be used to filter the source in
+		 * building path.
+		 */
+		conn.filter_src_fwnode =
+			fwnode_find_reference(&ep->fwnode, "filter-source", 0);
+		if (IS_ERR(conn.filter_src_fwnode)) {
+			conn.filter_src_fwnode = NULL;
+		} else {
+			conn.filter_src_dev =
+			 coresight_find_csdev_by_fwnode(conn.filter_src_fwnode);
+			if (conn.filter_src_dev &&
+			    !coresight_is_device_source(conn.filter_src_dev)) {
+				dev_warn(dev, "port %d: Filter handle is not a trace source : %s\n",
+					 conn.src_port, dev_name(&conn.filter_src_dev->dev));
+				conn.filter_src_dev = NULL;
+				conn.filter_src_fwnode = NULL;
+			}
+		}
+
 		new_conn = coresight_add_out_conn(dev, pdata, &conn);
 		if (IS_ERR_VALUE(new_conn)) {
 			fwnode_handle_put(conn.dest_fwnode);
@@ -796,6 +817,12 @@ int coresight_get_cpu(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(coresight_get_cpu);
 
+int coresight_get_static_trace_id(struct device *dev, u32 *id)
+{
+	return fwnode_property_read_u32(dev_fwnode(dev), "arm,static-trace-id", id);
+}
+EXPORT_SYMBOL_GPL(coresight_get_static_trace_id);
+
 struct coresight_platform_data *
 coresight_get_platform_data(struct device *dev)
 {
diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h
index 05f891ca6b5c..76403530f33e 100644
--- a/drivers/hwtracing/coresight/coresight-priv.h
+++ b/drivers/hwtracing/coresight/coresight-priv.h
@@ -42,6 +42,9 @@ extern const struct device_type coresight_dev_type[];
 
 #define ETM_MODE_EXCL_KERN	BIT(30)
 #define ETM_MODE_EXCL_USER	BIT(31)
+#define ETM_MODE_EXCL_HOST	BIT(32)
+#define ETM_MODE_EXCL_GUEST	BIT(33)
+
 struct cs_pair_attribute {
 	struct device_attribute attr;
 	u32 lo_off;
diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c
index 0fba87de6d1a..a1181c9048c0 100644
--- a/drivers/hwtracing/coresight/coresight-replicator.c
+++ b/drivers/hwtracing/coresight/coresight-replicator.c
@@ -126,7 +126,7 @@ static int replicator_enable(struct coresight_device *csdev,
 	bool first_enable = false;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (atomic_read(&out->src_refcnt) == 0) {
+	if (out->src_refcnt == 0) {
 		if (drvdata->base)
 			rc = dynamic_replicator_enable(drvdata, in->dest_port,
 						       out->src_port);
@@ -134,7 +134,7 @@ static int replicator_enable(struct coresight_device *csdev,
 			first_enable = true;
 	}
 	if (!rc)
-		atomic_inc(&out->src_refcnt);
+		out->src_refcnt++;
 	spin_unlock_irqrestore(&drvdata->spinlock, flags);
 
 	if (first_enable)
@@ -180,7 +180,7 @@ static void replicator_disable(struct coresight_device *csdev,
 	bool last_disable = false;
 
 	spin_lock_irqsave(&drvdata->spinlock, flags);
-	if (atomic_dec_return(&out->src_refcnt) == 0) {
+	if (--out->src_refcnt == 0) {
 		if (drvdata->base)
 			dynamic_replicator_disable(drvdata, in->dest_port,
 						   out->src_port);
diff --git a/drivers/hwtracing/coresight/coresight-self-hosted-trace.h b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h
index 53840a2c41f2..303d71911870 100644
--- a/drivers/hwtracing/coresight/coresight-self-hosted-trace.h
+++ b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h
@@ -21,13 +21,4 @@ static inline void write_trfcr(u64 val)
 	isb();
 }
 
-static inline u64 cpu_prohibit_trace(void)
-{
-	u64 trfcr = read_trfcr();
-
-	/* Prohibit tracing at EL0 & the kernel EL */
-	write_trfcr(trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE));
-	/* Return the original value of the TRFCR */
-	return trfcr;
-}
 #endif /*  __CORESIGHT_SELF_HOSTED_TRACE_H */
diff --git a/drivers/hwtracing/coresight/coresight-tpda.c b/drivers/hwtracing/coresight/coresight-tpda.c
index bfca103f9f84..189a4abc2561 100644
--- a/drivers/hwtracing/coresight/coresight-tpda.c
+++ b/drivers/hwtracing/coresight/coresight-tpda.c
@@ -24,7 +24,7 @@ DEFINE_CORESIGHT_DEVLIST(tpda_devs, "tpda");
 
 static bool coresight_device_is_tpdm(struct coresight_device *csdev)
 {
-	return (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) &&
+	return (coresight_is_device_source(csdev)) &&
 	       (csdev->subtype.source_subtype ==
 			CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM);
 }
@@ -110,6 +110,16 @@ static int tpda_get_element_size(struct tpda_drvdata *drvdata,
 		    csdev->pdata->in_conns[i]->dest_port != inport)
 			continue;
 
+		/*
+		 * If this port has a hardcoded filter, use the source
+		 * device directly.
+		 */
+		if (csdev->pdata->in_conns[i]->filter_src_fwnode) {
+			in = csdev->pdata->in_conns[i]->filter_src_dev;
+			if (!in)
+				continue;
+		}
+
 		if (coresight_device_is_tpdm(in)) {
 			if (drvdata->dsb_esize || drvdata->cmb_esize)
 				return -EEXIST;
@@ -124,7 +134,6 @@ static int tpda_get_element_size(struct tpda_drvdata *drvdata,
 		}
 	}
 
-
 	return rc;
 }
 
@@ -190,10 +199,10 @@ static int tpda_enable(struct coresight_device *csdev,
 	int ret = 0;
 
 	spin_lock(&drvdata->spinlock);
-	if (atomic_read(&in->dest_refcnt) == 0) {
+	if (in->dest_refcnt == 0) {
 		ret = __tpda_enable(drvdata, in->dest_port);
 		if (!ret) {
-			atomic_inc(&in->dest_refcnt);
+			in->dest_refcnt++;
 			csdev->refcnt++;
 			dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port);
 		}
@@ -223,7 +232,7 @@ static void tpda_disable(struct coresight_device *csdev,
 	struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
 
 	spin_lock(&drvdata->spinlock);
-	if (atomic_dec_return(&in->dest_refcnt) == 0) {
+	if (--in->dest_refcnt == 0) {
 		__tpda_disable(drvdata, in->dest_port);
 		csdev->refcnt--;
 	}
diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
index b7d99e91ab84..c38f9701665e 100644
--- a/drivers/hwtracing/coresight/coresight-tpdm.c
+++ b/drivers/hwtracing/coresight/coresight-tpdm.c
@@ -640,8 +640,7 @@ static ssize_t dsb_mode_store(struct device *dev,
 	struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent);
 	unsigned long val;
 
-	if ((kstrtoul(buf, 0, &val)) || (val < 0) ||
-			(val & ~TPDM_DSB_MODE_MASK))
+	if ((kstrtoul(buf, 0, &val)) || (val & ~TPDM_DSB_MODE_MASK))
 		return -EINVAL;
 
 	spin_lock(&drvdata->spinlock);
@@ -1308,8 +1307,8 @@ static void tpdm_remove(struct amba_device *adev)
  */
 static struct amba_id tpdm_ids[] = {
 	{
-		.id = 0x000f0e00,
-		.mask = 0x000fff00,
+		.id	= 0x001f0e00,
+		.mask	= 0x00ffff00,
 	},
 	{ 0, 0, NULL },
 };
diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c
index d98e12cb30ec..378af743be45 100644
--- a/drivers/hwtracing/coresight/coresight-trace-id.c
+++ b/drivers/hwtracing/coresight/coresight-trace-id.c
@@ -12,6 +12,12 @@
 
 #include "coresight-trace-id.h"
 
+enum trace_id_flags {
+	TRACE_ID_ANY = 0x0,
+	TRACE_ID_PREFER_ODD = 0x1,
+	TRACE_ID_REQ_STATIC = 0x2,
+};
+
 /* Default trace ID map. Used in sysfs mode and for system sources */
 static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0);
 static struct coresight_trace_id_map id_map_default = {
@@ -74,21 +80,25 @@ static int coresight_trace_id_find_odd_id(struct coresight_trace_id_map *id_map)
  * Otherwise allocate next available ID.
  */
 static int coresight_trace_id_alloc_new_id(struct coresight_trace_id_map *id_map,
-					   int preferred_id, bool prefer_odd_id)
+					   int preferred_id, unsigned int flags)
 {
 	int id = 0;
 
 	/* for backwards compatibility, cpu IDs may use preferred value */
-	if (IS_VALID_CS_TRACE_ID(preferred_id) &&
-	    !test_bit(preferred_id, id_map->used_ids)) {
-		id = preferred_id;
-		goto trace_id_allocated;
-	} else if (prefer_odd_id) {
+	if (IS_VALID_CS_TRACE_ID(preferred_id)) {
+		if (!test_bit(preferred_id, id_map->used_ids)) {
+			id = preferred_id;
+			goto trace_id_allocated;
+		} else if (flags & TRACE_ID_REQ_STATIC)
+			return -EBUSY;
+	} else if (flags & TRACE_ID_PREFER_ODD) {
 	/* may use odd ids to avoid preferred legacy cpu IDs */
 		id = coresight_trace_id_find_odd_id(id_map);
 		if (id)
 			goto trace_id_allocated;
-	}
+	} else if (!IS_VALID_CS_TRACE_ID(preferred_id) &&
+			(flags & TRACE_ID_REQ_STATIC))
+		return -EINVAL;
 
 	/*
 	 * skip reserved bit 0, look at bitmap length of
@@ -153,7 +163,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map
 	 */
 	id = coresight_trace_id_alloc_new_id(id_map,
 					     CORESIGHT_LEGACY_CPU_TRACE_ID(cpu),
-					     false);
+					     TRACE_ID_ANY);
 	if (!IS_VALID_CS_TRACE_ID(id))
 		goto get_cpu_id_out_unlock;
 
@@ -188,14 +198,14 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma
 	DUMP_ID_MAP(id_map);
 }
 
-static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map)
+static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map,
+					int preferred_id, unsigned int traceid_flags)
 {
 	unsigned long flags;
 	int id;
 
 	spin_lock_irqsave(&id_map->lock, flags);
-	/* prefer odd IDs for system components to avoid legacy CPU IDS */
-	id = coresight_trace_id_alloc_new_id(id_map, 0, true);
+	id = coresight_trace_id_alloc_new_id(id_map, preferred_id, traceid_flags);
 	spin_unlock_irqrestore(&id_map->lock, flags);
 
 	DUMP_ID(id);
@@ -255,10 +265,19 @@ EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id_map);
 
 int coresight_trace_id_get_system_id(void)
 {
-	return coresight_trace_id_map_get_system_id(&id_map_default);
+	/* prefer odd IDs for system components to avoid legacy CPU IDS */
+	return coresight_trace_id_map_get_system_id(&id_map_default, 0,
+			TRACE_ID_PREFER_ODD);
 }
 EXPORT_SYMBOL_GPL(coresight_trace_id_get_system_id);
 
+int coresight_trace_id_get_static_system_id(int trace_id)
+{
+	return coresight_trace_id_map_get_system_id(&id_map_default,
+			trace_id, TRACE_ID_REQ_STATIC);
+}
+EXPORT_SYMBOL_GPL(coresight_trace_id_get_static_system_id);
+
 void coresight_trace_id_put_system_id(int id)
 {
 	coresight_trace_id_map_put_system_id(&id_map_default, id);
diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h
index 9aae50a553ca..db68e1ec56b6 100644
--- a/drivers/hwtracing/coresight/coresight-trace-id.h
+++ b/drivers/hwtracing/coresight/coresight-trace-id.h
@@ -117,6 +117,15 @@ int coresight_trace_id_read_cpu_id_map(int cpu, struct coresight_trace_id_map *i
 int coresight_trace_id_get_system_id(void);
 
 /**
+ * Allocate a CoreSight static trace ID for a system component.
+ *
+ * Used to allocate static IDs for system trace sources such as dummy source.
+ *
+ * return: Trace ID or -EINVAL if allocation is impossible.
+ */
+int coresight_trace_id_get_static_system_id(int id);
+
+/**
  * Release an allocated system trace ID.
  *
  * Unconditionally release a trace ID allocated to a system component.
diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c
index 919804b12a67..fff67aac8418 100644
--- a/drivers/hwtracing/coresight/coresight-trbe.c
+++ b/drivers/hwtracing/coresight/coresight-trbe.c
@@ -17,6 +17,7 @@
 
 #include <asm/barrier.h>
 #include <asm/cpufeature.h>
+#include <linux/kvm_host.h>
 #include <linux/vmalloc.h>
 
 #include "coresight-self-hosted-trace.h"
@@ -221,6 +222,7 @@ static inline void set_trbe_enabled(struct trbe_cpudata *cpudata, u64 trblimitr)
 	 */
 	trblimitr |= TRBLIMITR_EL1_E;
 	write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1);
+	kvm_enable_trbe();
 
 	/* Synchronize the TRBE enable event */
 	isb();
@@ -239,6 +241,7 @@ static inline void set_trbe_disabled(struct trbe_cpudata *cpudata)
 	 */
 	trblimitr &= ~TRBLIMITR_EL1_E;
 	write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1);
+	kvm_disable_trbe();
 
 	if (trbe_needs_drain_after_disable(cpudata))
 		trbe_drain_buffer();
@@ -253,8 +256,8 @@ static void trbe_drain_and_disable_local(struct trbe_cpudata *cpudata)
 
 static void trbe_reset_local(struct trbe_cpudata *cpudata)
 {
-	trbe_drain_and_disable_local(cpudata);
 	write_sysreg_s(0, SYS_TRBLIMITR_EL1);
+	trbe_drain_buffer();
 	write_sysreg_s(0, SYS_TRBPTR_EL1);
 	write_sysreg_s(0, SYS_TRBBASER_EL1);
 	write_sysreg_s(0, SYS_TRBSR_EL1);
@@ -1110,6 +1113,16 @@ static bool is_perf_trbe(struct perf_output_handle *handle)
 	return true;
 }
 
+static u64 cpu_prohibit_trace(void)
+{
+	u64 trfcr = read_trfcr();
+
+	/* Prohibit tracing at EL0 & the kernel EL */
+	write_trfcr(trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE));
+	/* Return the original value of the TRFCR */
+	return trfcr;
+}
+
 static irqreturn_t arm_trbe_irq_handler(int irq, void *dev)
 {
 	struct perf_output_handle **handle_ptr = dev;
diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c
index d72993355473..47d9e6c3bac0 100644
--- a/drivers/hwtracing/intel_th/core.c
+++ b/drivers/hwtracing/intel_th/core.c
@@ -857,8 +857,9 @@ static irqreturn_t intel_th_irq(int irq, void *data)
 /**
  * intel_th_alloc() - allocate a new Intel TH device and its subdevices
  * @dev:	parent device
+ * @drvdata:	data private to the driver
  * @devres:	resources indexed by th_mmio_idx
- * @irq:	irq number
+ * @ndevres:	number of entries in the @devres resources
  */
 struct intel_th *
 intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata,
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index eec95c724b25..fc438f445771 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -756,6 +756,7 @@ config I2C_IMX
 config I2C_IMX_LPI2C
 	tristate "IMX Low Power I2C interface"
 	depends on ARCH_MXC || COMPILE_TEST
+	select I2C_SLAVE
 	help
 	  Say Y here if you want to use the Low Power IIC bus controller
 	  on the Freescale i.MX processors.
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index c24ccefb015e..35a221e2c11c 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -583,6 +583,9 @@ static int i2c_device_probe(struct device *dev)
 		goto err_detach_pm_domain;
 	}
 
+	client->debugfs = debugfs_create_dir(dev_name(&client->dev),
+					     client->adapter->debugfs);
+
 	if (driver->probe)
 		status = driver->probe(client);
 	else
@@ -602,6 +605,7 @@ static int i2c_device_probe(struct device *dev)
 	return 0;
 
 err_release_driver_resources:
+	debugfs_remove_recursive(client->debugfs);
 	devres_release_group(&client->dev, client->devres_group_id);
 err_detach_pm_domain:
 	dev_pm_domain_detach(&client->dev, do_power_on);
@@ -627,6 +631,8 @@ static void i2c_device_remove(struct device *dev)
 		driver->remove(client);
 	}
 
+	debugfs_remove_recursive(client->debugfs);
+
 	devres_release_group(&client->dev, client->devres_group_id);
 
 	dev_pm_domain_detach(&client->dev, true);
@@ -1015,8 +1021,6 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf
 	if (status)
 		goto out_remove_swnode;
 
-	client->debugfs = debugfs_create_dir(dev_name(&client->dev), adap->debugfs);
-
 	dev_dbg(&adap->dev, "client [%s] registered with bus id %s\n",
 		client->name, dev_name(&client->dev));
 
@@ -1061,7 +1065,6 @@ void i2c_unregister_device(struct i2c_client *client)
 	if (ACPI_COMPANION(&client->dev))
 		acpi_device_clear_enumerated(ACPI_COMPANION(&client->dev));
 
-	debugfs_remove_recursive(client->debugfs);
 	device_remove_software_node(&client->dev);
 	device_unregister(&client->dev);
 }
@@ -1297,12 +1300,14 @@ new_device_store(struct device *dev, struct device_attribute *attr,
 		info.flags |= I2C_CLIENT_SLAVE;
 	}
 
-	info.flags |= I2C_CLIENT_USER;
-
 	client = i2c_new_client_device(adap, &info);
 	if (IS_ERR(client))
 		return PTR_ERR(client);
 
+	/* Keep track of the added device */
+	mutex_lock(&adap->userspace_clients_lock);
+	list_add_tail(&client->detected, &adap->userspace_clients);
+	mutex_unlock(&adap->userspace_clients_lock);
 	dev_info(dev, "%s: Instantiated device %s at 0x%02hx\n", "new_device",
 		 info.type, info.addr);
 
@@ -1310,15 +1315,6 @@ new_device_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_WO(new_device);
 
-static int __i2c_find_user_addr(struct device *dev, void *addrp)
-{
-	struct i2c_client *client = i2c_verify_client(dev);
-	unsigned short addr = *(unsigned short *)addrp;
-
-	return client && client->flags & I2C_CLIENT_USER &&
-	       i2c_encode_flags_to_addr(client) == addr;
-}
-
 /*
  * And of course let the users delete the devices they instantiated, if
  * they got it wrong. This interface can only be used to delete devices
@@ -1333,7 +1329,7 @@ delete_device_store(struct device *dev, struct device_attribute *attr,
 		    const char *buf, size_t count)
 {
 	struct i2c_adapter *adap = to_i2c_adapter(dev);
-	struct device *child_dev;
+	struct i2c_client *client, *next;
 	unsigned short addr;
 	char end;
 	int res;
@@ -1349,19 +1345,28 @@ delete_device_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 	}
 
-	mutex_lock(&core_lock);
 	/* Make sure the device was added through sysfs */
-	child_dev = device_find_child(&adap->dev, &addr, __i2c_find_user_addr);
-	if (child_dev) {
-		i2c_unregister_device(i2c_verify_client(child_dev));
-		put_device(child_dev);
-	} else {
-		dev_err(dev, "Can't find userspace-created device at %#x\n", addr);
-		count = -ENOENT;
+	res = -ENOENT;
+	mutex_lock_nested(&adap->userspace_clients_lock,
+			  i2c_adapter_depth(adap));
+	list_for_each_entry_safe(client, next, &adap->userspace_clients,
+				 detected) {
+		if (i2c_encode_flags_to_addr(client) == addr) {
+			dev_info(dev, "%s: Deleting device %s at 0x%02hx\n",
+				 "delete_device", client->name, client->addr);
+
+			list_del(&client->detected);
+			i2c_unregister_device(client);
+			res = count;
+			break;
+		}
 	}
-	mutex_unlock(&core_lock);
+	mutex_unlock(&adap->userspace_clients_lock);
 
-	return count;
+	if (res < 0)
+		dev_err(dev, "%s: Can't find device in list\n",
+			"delete_device");
+	return res;
 }
 static DEVICE_ATTR_IGNORE_LOCKDEP(delete_device, S_IWUSR, NULL,
 				  delete_device_store);
@@ -1532,6 +1537,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 	adap->locked_flags = 0;
 	rt_mutex_init(&adap->bus_lock);
 	rt_mutex_init(&adap->mux_lock);
+	mutex_init(&adap->userspace_clients_lock);
+	INIT_LIST_HEAD(&adap->userspace_clients);
 
 	/* Set default timeout to 1 second if not already set */
 	if (adap->timeout == 0)
@@ -1697,6 +1704,23 @@ int i2c_add_numbered_adapter(struct i2c_adapter *adap)
 }
 EXPORT_SYMBOL_GPL(i2c_add_numbered_adapter);
 
+static void i2c_do_del_adapter(struct i2c_driver *driver,
+			      struct i2c_adapter *adapter)
+{
+	struct i2c_client *client, *_n;
+
+	/* Remove the devices we created ourselves as the result of hardware
+	 * probing (using a driver's detect method) */
+	list_for_each_entry_safe(client, _n, &driver->clients, detected) {
+		if (client->adapter == adapter) {
+			dev_dbg(&adapter->dev, "Removing %s at 0x%x\n",
+				client->name, client->addr);
+			list_del(&client->detected);
+			i2c_unregister_device(client);
+		}
+	}
+}
+
 static int __unregister_client(struct device *dev, void *dummy)
 {
 	struct i2c_client *client = i2c_verify_client(dev);
@@ -1712,6 +1736,12 @@ static int __unregister_dummy(struct device *dev, void *dummy)
 	return 0;
 }
 
+static int __process_removed_adapter(struct device_driver *d, void *data)
+{
+	i2c_do_del_adapter(to_i2c_driver(d), data);
+	return 0;
+}
+
 /**
  * i2c_del_adapter - unregister I2C adapter
  * @adap: the adapter being unregistered
@@ -1723,6 +1753,7 @@ static int __unregister_dummy(struct device *dev, void *dummy)
 void i2c_del_adapter(struct i2c_adapter *adap)
 {
 	struct i2c_adapter *found;
+	struct i2c_client *client, *next;
 
 	/* First make sure that this adapter was ever added */
 	mutex_lock(&core_lock);
@@ -1734,16 +1765,31 @@ void i2c_del_adapter(struct i2c_adapter *adap)
 	}
 
 	i2c_acpi_remove_space_handler(adap);
+	/* Tell drivers about this removal */
+	mutex_lock(&core_lock);
+	bus_for_each_drv(&i2c_bus_type, NULL, adap,
+			       __process_removed_adapter);
+	mutex_unlock(&core_lock);
+
+	/* Remove devices instantiated from sysfs */
+	mutex_lock_nested(&adap->userspace_clients_lock,
+			  i2c_adapter_depth(adap));
+	list_for_each_entry_safe(client, next, &adap->userspace_clients,
+				 detected) {
+		dev_dbg(&adap->dev, "Removing %s at 0x%x\n", client->name,
+			client->addr);
+		list_del(&client->detected);
+		i2c_unregister_device(client);
+	}
+	mutex_unlock(&adap->userspace_clients_lock);
 
 	/* Detach any active clients. This can't fail, thus we do not
 	 * check the returned value. This is a two-pass process, because
 	 * we can't remove the dummy devices during the first pass: they
 	 * could have been instantiated by real devices wishing to clean
 	 * them up properly, so we give them a chance to do that first. */
-	mutex_lock(&core_lock);
 	device_for_each_child(&adap->dev, NULL, __unregister_client);
 	device_for_each_child(&adap->dev, NULL, __unregister_dummy);
-	mutex_unlock(&core_lock);
 
 	/* device name is gone after device_unregister */
 	dev_dbg(&adap->dev, "adapter [%s] unregistered\n", adap->name);
@@ -1963,6 +2009,7 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 	/* add the driver to the list of i2c drivers in the driver core */
 	driver->driver.owner = owner;
 	driver->driver.bus = &i2c_bus_type;
+	INIT_LIST_HEAD(&driver->clients);
 
 	/* When registration returns, the driver core
 	 * will have called probe() for all matching-but-unbound devices.
@@ -1980,13 +2027,10 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 }
 EXPORT_SYMBOL(i2c_register_driver);
 
-static int __i2c_unregister_detected_client(struct device *dev, void *argp)
+static int __process_removed_driver(struct device *dev, void *data)
 {
-	struct i2c_client *client = i2c_verify_client(dev);
-
-	if (client && client->flags & I2C_CLIENT_AUTO)
-		i2c_unregister_device(client);
-
+	if (dev->type == &i2c_adapter_type)
+		i2c_do_del_adapter(data, to_i2c_adapter(dev));
 	return 0;
 }
 
@@ -1997,12 +2041,7 @@ static int __i2c_unregister_detected_client(struct device *dev, void *argp)
  */
 void i2c_del_driver(struct i2c_driver *driver)
 {
-	mutex_lock(&core_lock);
-	/* Satisfy __must_check, function can't fail */
-	if (driver_for_each_device(&driver->driver, NULL, NULL,
-				   __i2c_unregister_detected_client)) {
-	}
-	mutex_unlock(&core_lock);
+	i2c_for_each_dev(driver, __process_removed_driver);
 
 	driver_unregister(&driver->driver);
 	pr_debug("driver [%s] unregistered\n", driver->driver.name);
@@ -2429,7 +2468,6 @@ static int i2c_detect_address(struct i2c_client *temp_client,
 	/* Finally call the custom detection function */
 	memset(&info, 0, sizeof(struct i2c_board_info));
 	info.addr = addr;
-	info.flags = I2C_CLIENT_AUTO;
 	err = driver->detect(temp_client, &info);
 	if (err) {
 		/* -ENODEV is returned if the detection fails. We catch it
@@ -2456,7 +2494,9 @@ static int i2c_detect_address(struct i2c_client *temp_client,
 		dev_dbg(&adapter->dev, "Creating %s at 0x%02x\n",
 			info.type, info.addr);
 		client = i2c_new_client_device(adapter, &info);
-		if (IS_ERR(client))
+		if (!IS_ERR(client))
+			list_add_tail(&client->detected, &driver->clients);
+		else
 			dev_err(&adapter->dev, "Failed creating %s at 0x%02x\n",
 				info.type, info.addr);
 	}
diff --git a/drivers/iio/accel/adxl345.h b/drivers/iio/accel/adxl345.h
index 3d5c8719db3d..517e494ba555 100644
--- a/drivers/iio/accel/adxl345.h
+++ b/drivers/iio/accel/adxl345.h
@@ -9,37 +9,93 @@
 #define _ADXL345_H_
 
 #define ADXL345_REG_DEVID		0x00
+#define ADXL345_REG_THRESH_TAP		0x1D
 #define ADXL345_REG_OFSX		0x1E
 #define ADXL345_REG_OFSY		0x1F
 #define ADXL345_REG_OFSZ		0x20
 #define ADXL345_REG_OFS_AXIS(index)	(ADXL345_REG_OFSX + (index))
+
+/* Tap duration */
+#define ADXL345_REG_DUR		0x21
+/* Tap latency */
+#define ADXL345_REG_LATENT		0x22
+/* Tap window */
+#define ADXL345_REG_WINDOW		0x23
+/* Activity threshold */
+#define ADXL345_REG_THRESH_ACT		0x24
+/* Inactivity threshold */
+#define ADXL345_REG_THRESH_INACT	0x25
+/* Inactivity time */
+#define ADXL345_REG_TIME_INACT		0x26
+/* Axis enable control for activity and inactivity detection */
+#define ADXL345_REG_ACT_INACT_CTRL	0x27
+/* Free-fall threshold */
+#define ADXL345_REG_THRESH_FF		0x28
+/* Free-fall time */
+#define ADXL345_REG_TIME_FF		0x29
+/* Axis control for single tap or double tap */
+#define ADXL345_REG_TAP_AXIS		0x2A
+/* Source of single tap or double tap */
+#define ADXL345_REG_ACT_TAP_STATUS	0x2B
+/* Data rate and power mode control */
 #define ADXL345_REG_BW_RATE		0x2C
 #define ADXL345_REG_POWER_CTL		0x2D
+#define ADXL345_REG_INT_ENABLE		0x2E
+#define ADXL345_REG_INT_MAP		0x2F
+#define ADXL345_REG_INT_SOURCE		0x30
+#define ADXL345_REG_INT_SOURCE_MSK	0xFF
 #define ADXL345_REG_DATA_FORMAT		0x31
-#define ADXL345_REG_DATAX0		0x32
-#define ADXL345_REG_DATAY0		0x34
-#define ADXL345_REG_DATAZ0		0x36
-#define ADXL345_REG_DATA_AXIS(index)	\
-	(ADXL345_REG_DATAX0 + (index) * sizeof(__le16))
+#define ADXL345_REG_XYZ_BASE		0x32
+#define ADXL345_REG_DATA_AXIS(index)				\
+	(ADXL345_REG_XYZ_BASE + (index) * sizeof(__le16))
+
+#define ADXL345_REG_FIFO_CTL		0x38
+#define ADXL345_FIFO_CTL_SAMPLES_MSK	GENMASK(4, 0)
+/* 0: INT1, 1: INT2 */
+#define ADXL345_FIFO_CTL_TRIGGER_MSK	BIT(5)
+#define ADXL345_FIFO_CTL_MODE_MSK	GENMASK(7, 6)
+#define ADXL345_REG_FIFO_STATUS	0x39
+#define ADXL345_REG_FIFO_STATUS_MSK	0x3F
 
+#define ADXL345_INT_OVERRUN		BIT(0)
+#define ADXL345_INT_WATERMARK		BIT(1)
+#define ADXL345_INT_FREE_FALL		BIT(2)
+#define ADXL345_INT_INACTIVITY		BIT(3)
+#define ADXL345_INT_ACTIVITY		BIT(4)
+#define ADXL345_INT_DOUBLE_TAP		BIT(5)
+#define ADXL345_INT_SINGLE_TAP		BIT(6)
+#define ADXL345_INT_DATA_READY		BIT(7)
+
+/*
+ * BW_RATE bits - Bandwidth and output data rate. The default value is
+ * 0x0A, which translates to a 100 Hz output data rate
+ */
 #define ADXL345_BW_RATE			GENMASK(3, 0)
+#define ADXL345_BW_LOW_POWER		BIT(4)
 #define ADXL345_BASE_RATE_NANO_HZ	97656250LL
 
-#define ADXL345_POWER_CTL_MEASURE	BIT(3)
 #define ADXL345_POWER_CTL_STANDBY	0x00
+#define ADXL345_POWER_CTL_WAKEUP	GENMASK(1, 0)
+#define ADXL345_POWER_CTL_SLEEP	BIT(2)
+#define ADXL345_POWER_CTL_MEASURE	BIT(3)
+#define ADXL345_POWER_CTL_AUTO_SLEEP	BIT(4)
+#define ADXL345_POWER_CTL_LINK		BIT(5)
 
-#define ADXL345_DATA_FORMAT_RANGE	GENMASK(1, 0)	/* Set the g range */
-#define ADXL345_DATA_FORMAT_JUSTIFY	BIT(2)	/* Left-justified (MSB) mode */
-#define ADXL345_DATA_FORMAT_FULL_RES	BIT(3)	/* Up to 13-bits resolution */
-#define ADXL345_DATA_FORMAT_SPI_3WIRE	BIT(6)	/* 3-wire SPI mode */
-#define ADXL345_DATA_FORMAT_SELF_TEST	BIT(7)	/* Enable a self test */
-
+/* Set the g range */
+#define ADXL345_DATA_FORMAT_RANGE	GENMASK(1, 0)
+/* Data is left justified */
+#define ADXL345_DATA_FORMAT_JUSTIFY	BIT(2)
+/* Up to 13-bits resolution */
+#define ADXL345_DATA_FORMAT_FULL_RES	BIT(3)
+#define ADXL345_DATA_FORMAT_SPI_3WIRE	BIT(6)
+#define ADXL345_DATA_FORMAT_SELF_TEST	BIT(7)
 #define ADXL345_DATA_FORMAT_2G		0
 #define ADXL345_DATA_FORMAT_4G		1
 #define ADXL345_DATA_FORMAT_8G		2
 #define ADXL345_DATA_FORMAT_16G		3
 
 #define ADXL345_DEVID			0xE5
+#define ADXL345_FIFO_SIZE		32
 
 /*
  * In full-resolution mode, scale factor is maintained at ~4 mg/LSB
@@ -62,6 +118,7 @@ struct adxl345_chip_info {
 };
 
 int adxl345_core_probe(struct device *dev, struct regmap *regmap,
+		       bool fifo_delay_default,
 		       int (*setup)(struct device*, struct regmap*));
 
 #endif /* _ADXL345_H_ */
diff --git a/drivers/iio/accel/adxl345_core.c b/drivers/iio/accel/adxl345_core.c
index b1efab0f6404..d1b2d3985a40 100644
--- a/drivers/iio/accel/adxl345_core.c
+++ b/drivers/iio/accel/adxl345_core.c
@@ -7,6 +7,8 @@
  * Datasheet: https://www.analog.com/media/en/technical-documentation/data-sheets/ADXL345.pdf
  */
 
+#include <linux/bitfield.h>
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
@@ -14,36 +16,92 @@
 
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/kfifo_buf.h>
 
 #include "adxl345.h"
 
-struct adxl345_data {
+#define ADXL345_FIFO_BYPASS	0
+#define ADXL345_FIFO_FIFO	1
+#define ADXL345_FIFO_STREAM	2
+
+#define ADXL345_DIRS 3
+
+#define ADXL345_INT_NONE		0xff
+#define ADXL345_INT1			0
+#define ADXL345_INT2			1
+
+struct adxl345_state {
 	const struct adxl345_chip_info *info;
 	struct regmap *regmap;
+	bool fifo_delay; /* delay: delay is needed for SPI */
+	int irq;
+	u8 intio;
+	u8 int_map;
+	u8 watermark;
+	u8 fifo_mode;
+	__le16 fifo_buf[ADXL345_DIRS * ADXL345_FIFO_SIZE + 1] __aligned(IIO_DMA_MINALIGN);
 };
 
-#define ADXL345_CHANNEL(index, axis) {					\
+#define ADXL345_CHANNEL(index, reg, axis) {					\
 	.type = IIO_ACCEL,						\
 	.modified = 1,							\
 	.channel2 = IIO_MOD_##axis,					\
-	.address = index,						\
+	.address = (reg),						\
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |			\
 		BIT(IIO_CHAN_INFO_CALIBBIAS),				\
 	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE) |		\
 		BIT(IIO_CHAN_INFO_SAMP_FREQ),				\
+	.scan_index = (index),				\
+	.scan_type = {					\
+		.sign = 's',				\
+		.realbits = 13,				\
+		.storagebits = 16,			\
+		.endianness = IIO_LE,			\
+	},						\
 }
 
+enum adxl345_chans {
+	chan_x, chan_y, chan_z,
+};
+
 static const struct iio_chan_spec adxl345_channels[] = {
-	ADXL345_CHANNEL(0, X),
-	ADXL345_CHANNEL(1, Y),
-	ADXL345_CHANNEL(2, Z),
+	ADXL345_CHANNEL(0, chan_x, X),
+	ADXL345_CHANNEL(1, chan_y, Y),
+	ADXL345_CHANNEL(2, chan_z, Z),
 };
 
+static const unsigned long adxl345_scan_masks[] = {
+	BIT(chan_x) | BIT(chan_y) | BIT(chan_z),
+	0
+};
+
+static int adxl345_set_interrupts(struct adxl345_state *st)
+{
+	int ret;
+	unsigned int int_enable = st->int_map;
+	unsigned int int_map;
+
+	/*
+	 * Any bits set to 0 in the INT map register send their respective
+	 * interrupts to the INT1 pin, whereas bits set to 1 send their respective
+	 * interrupts to the INT2 pin. The intio shall convert this accordingly.
+	 */
+	int_map = FIELD_GET(ADXL345_REG_INT_SOURCE_MSK,
+			    st->intio ? st->int_map : ~st->int_map);
+
+	ret = regmap_write(st->regmap, ADXL345_REG_INT_MAP, int_map);
+	if (ret)
+		return ret;
+
+	return regmap_write(st->regmap, ADXL345_REG_INT_ENABLE, int_enable);
+}
+
 static int adxl345_read_raw(struct iio_dev *indio_dev,
 			    struct iio_chan_spec const *chan,
 			    int *val, int *val2, long mask)
 {
-	struct adxl345_data *data = iio_priv(indio_dev);
+	struct adxl345_state *st = iio_priv(indio_dev);
 	__le16 accel;
 	long long samp_freq_nhz;
 	unsigned int regval;
@@ -56,7 +114,7 @@ static int adxl345_read_raw(struct iio_dev *indio_dev,
 		 * ADXL345_REG_DATA(X0/Y0/Z0) contain the least significant byte
 		 * and ADXL345_REG_DATA(X0/Y0/Z0) + 1 the most significant byte
 		 */
-		ret = regmap_bulk_read(data->regmap,
+		ret = regmap_bulk_read(st->regmap,
 				       ADXL345_REG_DATA_AXIS(chan->address),
 				       &accel, sizeof(accel));
 		if (ret < 0)
@@ -66,10 +124,10 @@ static int adxl345_read_raw(struct iio_dev *indio_dev,
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
 		*val = 0;
-		*val2 = data->info->uscale;
+		*val2 = st->info->uscale;
 		return IIO_VAL_INT_PLUS_MICRO;
 	case IIO_CHAN_INFO_CALIBBIAS:
-		ret = regmap_read(data->regmap,
+		ret = regmap_read(st->regmap,
 				  ADXL345_REG_OFS_AXIS(chan->address), &regval);
 		if (ret < 0)
 			return ret;
@@ -81,7 +139,7 @@ static int adxl345_read_raw(struct iio_dev *indio_dev,
 
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = regmap_read(data->regmap, ADXL345_REG_BW_RATE, &regval);
+		ret = regmap_read(st->regmap, ADXL345_REG_BW_RATE, &regval);
 		if (ret < 0)
 			return ret;
 
@@ -99,7 +157,7 @@ static int adxl345_write_raw(struct iio_dev *indio_dev,
 			     struct iio_chan_spec const *chan,
 			     int val, int val2, long mask)
 {
-	struct adxl345_data *data = iio_priv(indio_dev);
+	struct adxl345_state *st = iio_priv(indio_dev);
 	s64 n;
 
 	switch (mask) {
@@ -108,14 +166,14 @@ static int adxl345_write_raw(struct iio_dev *indio_dev,
 		 * 8-bit resolution at +/- 2g, that is 4x accel data scale
 		 * factor
 		 */
-		return regmap_write(data->regmap,
+		return regmap_write(st->regmap,
 				    ADXL345_REG_OFS_AXIS(chan->address),
 				    val / 4);
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		n = div_s64(val * NANOHZ_PER_HZ + val2,
 			    ADXL345_BASE_RATE_NANO_HZ);
 
-		return regmap_update_bits(data->regmap, ADXL345_REG_BW_RATE,
+		return regmap_update_bits(st->regmap, ADXL345_REG_BW_RATE,
 					  ADXL345_BW_RATE,
 					  clamp_val(ilog2(n), 0,
 						    ADXL345_BW_RATE));
@@ -124,6 +182,24 @@ static int adxl345_write_raw(struct iio_dev *indio_dev,
 	return -EINVAL;
 }
 
+static int adxl345_set_watermark(struct iio_dev *indio_dev, unsigned int value)
+{
+	struct adxl345_state *st = iio_priv(indio_dev);
+	unsigned int fifo_mask = 0x1F;
+	int ret;
+
+	value = min(value, ADXL345_FIFO_SIZE - 1);
+
+	ret = regmap_update_bits(st->regmap, ADXL345_REG_FIFO_CTL, fifo_mask, value);
+	if (ret)
+		return ret;
+
+	st->watermark = value;
+	st->int_map |= ADXL345_INT_WATERMARK;
+
+	return 0;
+}
+
 static int adxl345_write_raw_get_fmt(struct iio_dev *indio_dev,
 				     struct iio_chan_spec const *chan,
 				     long mask)
@@ -138,6 +214,33 @@ static int adxl345_write_raw_get_fmt(struct iio_dev *indio_dev,
 	}
 }
 
+/**
+ * adxl345_set_measure_en() - Enable and disable measuring.
+ *
+ * @st: The device data.
+ * @en: Enable measurements, else standby mode.
+ *
+ * For lowest power operation, standby mode can be used. In standby mode,
+ * current consumption is supposed to be reduced to 0.1uA (typical). In this
+ * mode no measurements are made. Placing the device into standby mode
+ * preserves the contents of FIFO.
+ *
+ * Return: Returns 0 if successful, or a negative error value.
+ */
+static int adxl345_set_measure_en(struct adxl345_state *st, bool en)
+{
+	unsigned int val = en ? ADXL345_POWER_CTL_MEASURE : ADXL345_POWER_CTL_STANDBY;
+
+	return regmap_write(st->regmap, ADXL345_REG_POWER_CTL, val);
+}
+
+static void adxl345_powerdown(void *ptr)
+{
+	struct adxl345_state *st = ptr;
+
+	adxl345_set_measure_en(st, false);
+}
+
 static IIO_CONST_ATTR_SAMP_FREQ_AVAIL(
 "0.09765625 0.1953125 0.390625 0.78125 1.5625 3.125 6.25 12.5 25 50 100 200 400 800 1600 3200"
 );
@@ -151,37 +254,244 @@ static const struct attribute_group adxl345_attrs_group = {
 	.attrs = adxl345_attrs,
 };
 
-static const struct iio_info adxl345_info = {
-	.attrs		= &adxl345_attrs_group,
-	.read_raw	= adxl345_read_raw,
-	.write_raw	= adxl345_write_raw,
-	.write_raw_get_fmt	= adxl345_write_raw_get_fmt,
+static int adxl345_set_fifo(struct adxl345_state *st)
+{
+	int ret;
+
+	/* FIFO should only be configured while in standby mode */
+	ret = adxl345_set_measure_en(st, false);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(st->regmap, ADXL345_REG_FIFO_CTL,
+			   FIELD_PREP(ADXL345_FIFO_CTL_SAMPLES_MSK,
+				      st->watermark) |
+			   FIELD_PREP(ADXL345_FIFO_CTL_TRIGGER_MSK,
+				      st->intio) |
+			   FIELD_PREP(ADXL345_FIFO_CTL_MODE_MSK,
+				      st->fifo_mode));
+	if (ret < 0)
+		return ret;
+
+	return adxl345_set_measure_en(st, true);
+}
+
+/**
+ * adxl345_get_samples() - Read number of FIFO entries.
+ * @st: The initialized state instance of this driver.
+ *
+ * The sensor does not support treating any axis individually, or exclude them
+ * from measuring.
+ *
+ * Return: negative error, or value.
+ */
+static int adxl345_get_samples(struct adxl345_state *st)
+{
+	unsigned int regval = 0;
+	int ret;
+
+	ret = regmap_read(st->regmap, ADXL345_REG_FIFO_STATUS, &regval);
+	if (ret < 0)
+		return ret;
+
+	return FIELD_GET(ADXL345_REG_FIFO_STATUS_MSK, regval);
+}
+
+/**
+ * adxl345_fifo_transfer() - Read samples number of elements.
+ * @st: The instance of the state object of this sensor.
+ * @samples: The number of lines in the FIFO referred to as fifo_entry.
+ *
+ * It is recommended that a multiple-byte read of all registers be performed to
+ * prevent a change in data between reads of sequential registers. That is to
+ * read out the data registers X0, X1, Y0, Y1, Z0, Z1, i.e. 6 bytes at once.
+ *
+ * Return: 0 or error value.
+ */
+static int adxl345_fifo_transfer(struct adxl345_state *st, int samples)
+{
+	size_t count;
+	int i, ret = 0;
+
+	/* count is the 3x the fifo_buf element size, hence 6B */
+	count = sizeof(st->fifo_buf[0]) * ADXL345_DIRS;
+	for (i = 0; i < samples; i++) {
+		/* read 3x 2 byte elements from base address into next fifo_buf position */
+		ret = regmap_bulk_read(st->regmap, ADXL345_REG_XYZ_BASE,
+				       st->fifo_buf + (i * count / 2), count);
+		if (ret < 0)
+			return ret;
+
+		/*
+		 * To ensure that the FIFO has completely popped, there must be at least 5
+		 * us between the end of reading the data registers, signified by the
+		 * transition to register 0x38 from 0x37 or the CS pin going high, and the
+		 * start of new reads of the FIFO or reading the FIFO_STATUS register. For
+		 * SPI operation at 1.5 MHz or lower, the register addressing portion of the
+		 * transmission is sufficient delay to ensure the FIFO has completely
+		 * popped. It is necessary for SPI operation greater than 1.5 MHz to
+		 * de-assert the CS pin to ensure a total of 5 us, which is at most 3.4 us
+		 * at 5 MHz operation.
+		 */
+		if (st->fifo_delay && samples > 1)
+			udelay(3);
+	}
+	return ret;
+}
+
+/**
+ * adxl345_fifo_reset() - Empty the FIFO in error condition.
+ * @st: The instance to the state object of the sensor.
+ *
+ * Read all elements of the FIFO. Reading the interrupt source register
+ * resets the sensor.
+ */
+static void adxl345_fifo_reset(struct adxl345_state *st)
+{
+	int regval;
+	int samples;
+
+	adxl345_set_measure_en(st, false);
+
+	samples = adxl345_get_samples(st);
+	if (samples > 0)
+		adxl345_fifo_transfer(st, samples);
+
+	regmap_read(st->regmap, ADXL345_REG_INT_SOURCE, &regval);
+
+	adxl345_set_measure_en(st, true);
+}
+
+static int adxl345_buffer_postenable(struct iio_dev *indio_dev)
+{
+	struct adxl345_state *st = iio_priv(indio_dev);
+	int ret;
+
+	ret = adxl345_set_interrupts(st);
+	if (ret < 0)
+		return ret;
+
+	st->fifo_mode = ADXL345_FIFO_STREAM;
+	return adxl345_set_fifo(st);
+}
+
+static int adxl345_buffer_predisable(struct iio_dev *indio_dev)
+{
+	struct adxl345_state *st = iio_priv(indio_dev);
+	int ret;
+
+	st->fifo_mode = ADXL345_FIFO_BYPASS;
+	ret = adxl345_set_fifo(st);
+	if (ret < 0)
+		return ret;
+
+	st->int_map = 0x00;
+	return adxl345_set_interrupts(st);
+}
+
+static const struct iio_buffer_setup_ops adxl345_buffer_ops = {
+	.postenable = adxl345_buffer_postenable,
+	.predisable = adxl345_buffer_predisable,
 };
 
-static int adxl345_powerup(void *regmap)
+static int adxl345_get_status(struct adxl345_state *st)
 {
-	return regmap_write(regmap, ADXL345_REG_POWER_CTL, ADXL345_POWER_CTL_MEASURE);
+	int ret;
+	unsigned int regval;
+
+	ret = regmap_read(st->regmap, ADXL345_REG_INT_SOURCE, &regval);
+	if (ret < 0)
+		return ret;
+
+	return FIELD_GET(ADXL345_REG_INT_SOURCE_MSK, regval);
 }
 
-static void adxl345_powerdown(void *regmap)
+static int adxl345_fifo_push(struct iio_dev *indio_dev,
+			     int samples)
 {
-	regmap_write(regmap, ADXL345_REG_POWER_CTL, ADXL345_POWER_CTL_STANDBY);
+	struct adxl345_state *st = iio_priv(indio_dev);
+	int i, ret;
+
+	if (samples <= 0)
+		return -EINVAL;
+
+	ret = adxl345_fifo_transfer(st, samples);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ADXL345_DIRS * samples; i += ADXL345_DIRS)
+		iio_push_to_buffers(indio_dev, &st->fifo_buf[i]);
+
+	return 0;
+}
+
+/**
+ * adxl345_irq_handler() - Handle irqs of the ADXL345.
+ * @irq: The irq being handled.
+ * @p: The struct iio_device pointer for the device.
+ *
+ * Return: The interrupt was handled.
+ */
+static irqreturn_t adxl345_irq_handler(int irq, void *p)
+{
+	struct iio_dev *indio_dev = p;
+	struct adxl345_state *st = iio_priv(indio_dev);
+	int int_stat;
+	int samples;
+
+	int_stat = adxl345_get_status(st);
+	if (int_stat <= 0)
+		return IRQ_NONE;
+
+	if (int_stat & ADXL345_INT_OVERRUN)
+		goto err;
+
+	if (int_stat & ADXL345_INT_WATERMARK) {
+		samples = adxl345_get_samples(st);
+		if (samples < 0)
+			goto err;
+
+		if (adxl345_fifo_push(indio_dev, samples) < 0)
+			goto err;
+	}
+	return IRQ_HANDLED;
+
+err:
+	adxl345_fifo_reset(st);
+
+	return IRQ_HANDLED;
 }
 
+static const struct iio_info adxl345_info = {
+	.attrs		= &adxl345_attrs_group,
+	.read_raw	= adxl345_read_raw,
+	.write_raw	= adxl345_write_raw,
+	.write_raw_get_fmt	= adxl345_write_raw_get_fmt,
+	.hwfifo_set_watermark = adxl345_set_watermark,
+};
+
 /**
- * adxl345_core_probe() - probe and setup for the adxl345 accelerometer,
- *                        also covers the adlx375 accelerometer
+ * adxl345_core_probe() - Probe and setup for the accelerometer.
  * @dev:	Driver model representation of the device
  * @regmap:	Regmap instance for the device
+ * @fifo_delay_default: Using FIFO with SPI needs delay
  * @setup:	Setup routine to be executed right before the standard device
  *		setup
  *
+ * For SPI operation greater than 1.6 MHz, it is necessary to deassert the CS
+ * pin to ensure a total delay of 5 us; otherwise, the delay is not sufficient.
+ * The total delay necessary for 5 MHz operation is at most 3.4 us. This is not
+ * a concern when using I2C mode because the communication rate is low enough
+ * to ensure a sufficient delay between FIFO reads.
+ * Ref: "Retrieving Data from FIFO", p. 21 of 36, Data Sheet ADXL345 Rev. G
+ *
  * Return: 0 on success, negative errno on error
  */
 int adxl345_core_probe(struct device *dev, struct regmap *regmap,
+		       bool fifo_delay_default,
 		       int (*setup)(struct device*, struct regmap*))
 {
-	struct adxl345_data *data;
+	struct adxl345_state *st;
 	struct iio_dev *indio_dev;
 	u32 regval;
 	unsigned int data_format_mask = (ADXL345_DATA_FORMAT_RANGE |
@@ -190,30 +500,32 @@ int adxl345_core_probe(struct device *dev, struct regmap *regmap,
 					 ADXL345_DATA_FORMAT_SELF_TEST);
 	int ret;
 
-	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*st));
 	if (!indio_dev)
 		return -ENOMEM;
 
-	data = iio_priv(indio_dev);
-	data->regmap = regmap;
-	data->info = device_get_match_data(dev);
-	if (!data->info)
+	st = iio_priv(indio_dev);
+	st->regmap = regmap;
+	st->info = device_get_match_data(dev);
+	if (!st->info)
 		return -ENODEV;
+	st->fifo_delay = fifo_delay_default;
 
-	indio_dev->name = data->info->name;
+	indio_dev->name = st->info->name;
 	indio_dev->info = &adxl345_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->channels = adxl345_channels;
 	indio_dev->num_channels = ARRAY_SIZE(adxl345_channels);
+	indio_dev->available_scan_masks = adxl345_scan_masks;
 
 	if (setup) {
 		/* Perform optional initial bus specific configuration */
-		ret = setup(dev, data->regmap);
+		ret = setup(dev, st->regmap);
 		if (ret)
 			return ret;
 
 		/* Enable full-resolution mode */
-		ret = regmap_update_bits(data->regmap, ADXL345_REG_DATA_FORMAT,
+		ret = regmap_update_bits(st->regmap, ADXL345_REG_DATA_FORMAT,
 					 data_format_mask,
 					 ADXL345_DATA_FORMAT_FULL_RES);
 		if (ret)
@@ -222,14 +534,14 @@ int adxl345_core_probe(struct device *dev, struct regmap *regmap,
 
 	} else {
 		/* Enable full-resolution mode (init all data_format bits) */
-		ret = regmap_write(data->regmap, ADXL345_REG_DATA_FORMAT,
+		ret = regmap_write(st->regmap, ADXL345_REG_DATA_FORMAT,
 				   ADXL345_DATA_FORMAT_FULL_RES);
 		if (ret)
 			return dev_err_probe(dev, ret,
 					     "Failed to set data range\n");
 	}
 
-	ret = regmap_read(data->regmap, ADXL345_REG_DEVID, &regval);
+	ret = regmap_read(st->regmap, ADXL345_REG_DEVID, &regval);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Error reading device ID\n");
 
@@ -238,14 +550,43 @@ int adxl345_core_probe(struct device *dev, struct regmap *regmap,
 				     regval, ADXL345_DEVID);
 
 	/* Enable measurement mode */
-	ret = adxl345_powerup(data->regmap);
+	ret = adxl345_set_measure_en(st, true);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to enable measurement mode\n");
 
-	ret = devm_add_action_or_reset(dev, adxl345_powerdown, data->regmap);
+	ret = devm_add_action_or_reset(dev, adxl345_powerdown, st);
 	if (ret < 0)
 		return ret;
 
+	st->intio = ADXL345_INT1;
+	st->irq = fwnode_irq_get_byname(dev_fwnode(dev), "INT1");
+	if (st->irq < 0) {
+		st->intio = ADXL345_INT2;
+		st->irq = fwnode_irq_get_byname(dev_fwnode(dev), "INT2");
+		if (st->irq < 0)
+			st->intio = ADXL345_INT_NONE;
+	}
+
+	if (st->intio != ADXL345_INT_NONE) {
+		/* FIFO_STREAM mode is going to be activated later */
+		ret = devm_iio_kfifo_buffer_setup(dev, indio_dev, &adxl345_buffer_ops);
+		if (ret)
+			return ret;
+
+		ret = devm_request_threaded_irq(dev, st->irq, NULL,
+						&adxl345_irq_handler,
+						IRQF_SHARED | IRQF_ONESHOT,
+						indio_dev->name, indio_dev);
+		if (ret)
+			return ret;
+	} else {
+		ret = regmap_write(st->regmap, ADXL345_REG_FIFO_CTL,
+				   FIELD_PREP(ADXL345_FIFO_CTL_MODE_MSK,
+					      ADXL345_FIFO_BYPASS));
+		if (ret < 0)
+			return ret;
+	}
+
 	return devm_iio_device_register(dev, indio_dev);
 }
 EXPORT_SYMBOL_NS_GPL(adxl345_core_probe, "IIO_ADXL345");
diff --git a/drivers/iio/accel/adxl345_i2c.c b/drivers/iio/accel/adxl345_i2c.c
index cb23fb11fcd7..8c385dd6c01d 100644
--- a/drivers/iio/accel/adxl345_i2c.c
+++ b/drivers/iio/accel/adxl345_i2c.c
@@ -27,7 +27,7 @@ static int adxl345_i2c_probe(struct i2c_client *client)
 	if (IS_ERR(regmap))
 		return dev_err_probe(&client->dev, PTR_ERR(regmap), "Error initializing regmap\n");
 
-	return adxl345_core_probe(&client->dev, regmap, NULL);
+	return adxl345_core_probe(&client->dev, regmap, false, NULL);
 }
 
 static const struct adxl345_chip_info adxl345_i2c_info = {
diff --git a/drivers/iio/accel/adxl345_spi.c b/drivers/iio/accel/adxl345_spi.c
index 968e7b390d4b..7e518aea17bf 100644
--- a/drivers/iio/accel/adxl345_spi.c
+++ b/drivers/iio/accel/adxl345_spi.c
@@ -12,6 +12,7 @@
 #include "adxl345.h"
 
 #define ADXL345_MAX_SPI_FREQ_HZ		5000000
+#define ADXL345_MAX_FREQ_NO_FIFO_DELAY	1500000
 
 static const struct regmap_config adxl345_spi_regmap_config = {
 	.reg_bits = 8,
@@ -28,6 +29,7 @@ static int adxl345_spi_setup(struct device *dev, struct regmap *regmap)
 static int adxl345_spi_probe(struct spi_device *spi)
 {
 	struct regmap *regmap;
+	bool needs_delay;
 
 	/* Bail out if max_speed_hz exceeds 5 MHz */
 	if (spi->max_speed_hz > ADXL345_MAX_SPI_FREQ_HZ)
@@ -38,10 +40,11 @@ static int adxl345_spi_probe(struct spi_device *spi)
 	if (IS_ERR(regmap))
 		return dev_err_probe(&spi->dev, PTR_ERR(regmap), "Error initializing regmap\n");
 
+	needs_delay = spi->max_speed_hz > ADXL345_MAX_FREQ_NO_FIFO_DELAY;
 	if (spi->mode & SPI_3WIRE)
-		return adxl345_core_probe(&spi->dev, regmap, adxl345_spi_setup);
+		return adxl345_core_probe(&spi->dev, regmap, needs_delay, adxl345_spi_setup);
 	else
-		return adxl345_core_probe(&spi->dev, regmap, NULL);
+		return adxl345_core_probe(&spi->dev, regmap, needs_delay, NULL);
 }
 
 static const struct adxl345_chip_info adxl345_spi_info = {
diff --git a/drivers/iio/accel/bma220_spi.c b/drivers/iio/accel/bma220_spi.c
index 009e6243c6cb..96ba028157ee 100644
--- a/drivers/iio/accel/bma220_spi.c
+++ b/drivers/iio/accel/bma220_spi.c
@@ -66,7 +66,7 @@ struct bma220_data {
 	struct {
 		s8 chans[3];
 		/* Ensure timestamp is naturally aligned. */
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	u8 tx_buf[2] __aligned(IIO_DMA_MINALIGN);
 };
diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c
index 65aac60f1245..987212a7c038 100644
--- a/drivers/iio/accel/fxls8962af-core.c
+++ b/drivers/iio/accel/fxls8962af-core.c
@@ -129,6 +129,8 @@
 
 #define FXLS8962AF_DEVICE_ID			0x62
 #define FXLS8964AF_DEVICE_ID			0x84
+#define FXLS8974CF_DEVICE_ID			0x86
+#define FXLS8967AF_DEVICE_ID			0x87
 
 /* Raw temp channel offset */
 #define FXLS8962AF_TEMP_CENTER_VAL		25
@@ -766,6 +768,18 @@ static const struct fxls8962af_chip_info fxls_chip_info_table[] = {
 		.channels = fxls8962af_channels,
 		.num_channels = ARRAY_SIZE(fxls8962af_channels),
 	},
+	[fxls8967af] = {
+		.chip_id = FXLS8967AF_DEVICE_ID,
+		.name = "fxls8967af",
+		.channels = fxls8962af_channels,
+		.num_channels = ARRAY_SIZE(fxls8962af_channels),
+	},
+	[fxls8974cf] = {
+		.chip_id = FXLS8974CF_DEVICE_ID,
+		.name = "fxls8974cf",
+		.channels = fxls8962af_channels,
+		.num_channels = ARRAY_SIZE(fxls8962af_channels),
+	},
 };
 
 static const struct iio_info fxls8962af_info = {
diff --git a/drivers/iio/accel/fxls8962af-i2c.c b/drivers/iio/accel/fxls8962af-i2c.c
index 2e1bb43ef2a1..1b9156b6b2e3 100644
--- a/drivers/iio/accel/fxls8962af-i2c.c
+++ b/drivers/iio/accel/fxls8962af-i2c.c
@@ -30,6 +30,8 @@ static int fxls8962af_probe(struct i2c_client *client)
 static const struct i2c_device_id fxls8962af_id[] = {
 	{ "fxls8962af", fxls8962af },
 	{ "fxls8964af", fxls8964af },
+	{ "fxls8967af", fxls8967af },
+	{ "fxls8974cf", fxls8974cf },
 	{}
 };
 MODULE_DEVICE_TABLE(i2c, fxls8962af_id);
diff --git a/drivers/iio/accel/fxls8962af.h b/drivers/iio/accel/fxls8962af.h
index 6eaa2803b26f..1c9adfc8c0dc 100644
--- a/drivers/iio/accel/fxls8962af.h
+++ b/drivers/iio/accel/fxls8962af.h
@@ -11,6 +11,8 @@ struct device;
 enum {
 	fxls8962af,
 	fxls8964af,
+	fxls8967af,
+	fxls8974cf,
 };
 
 int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq);
diff --git a/drivers/iio/accel/kionix-kx022a-i2c.c b/drivers/iio/accel/kionix-kx022a-i2c.c
index b39a43ecadff..42388636ca31 100644
--- a/drivers/iio/accel/kionix-kx022a-i2c.c
+++ b/drivers/iio/accel/kionix-kx022a-i2c.c
@@ -38,7 +38,9 @@ static int kx022a_i2c_probe(struct i2c_client *i2c)
 static const struct i2c_device_id kx022a_i2c_id[] = {
 	{ .name = "kx022a", .driver_data = (kernel_ulong_t)&kx022a_chip_info },
 	{ .name = "kx132-1211", .driver_data = (kernel_ulong_t)&kx132_chip_info },
+	{ .name = "kx134-1211", .driver_data = (kernel_ulong_t)&kx134_chip_info },
 	{ .name = "kx132acr-lbz", .driver_data = (kernel_ulong_t)&kx132acr_chip_info },
+	{ .name = "kx134acr-lbz", .driver_data = (kernel_ulong_t)&kx134acr_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, kx022a_i2c_id);
@@ -46,7 +48,9 @@ MODULE_DEVICE_TABLE(i2c, kx022a_i2c_id);
 static const struct of_device_id kx022a_of_match[] = {
 	{ .compatible = "kionix,kx022a", .data = &kx022a_chip_info },
 	{ .compatible = "kionix,kx132-1211", .data = &kx132_chip_info },
+	{ .compatible = "kionix,kx134-1211", .data = &kx134_chip_info },
 	{ .compatible = "rohm,kx132acr-lbz", .data = &kx132acr_chip_info },
+	{ .compatible = "rohm,kx134acr-lbz", .data = &kx134acr_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, kx022a_of_match);
diff --git a/drivers/iio/accel/kionix-kx022a-spi.c b/drivers/iio/accel/kionix-kx022a-spi.c
index c38a47806a00..e30d21083dc8 100644
--- a/drivers/iio/accel/kionix-kx022a-spi.c
+++ b/drivers/iio/accel/kionix-kx022a-spi.c
@@ -38,7 +38,9 @@ static int kx022a_spi_probe(struct spi_device *spi)
 static const struct spi_device_id kx022a_id[] = {
 	{ .name = "kx022a", .driver_data = (kernel_ulong_t)&kx022a_chip_info },
 	{ .name = "kx132-1211", .driver_data = (kernel_ulong_t)&kx132_chip_info },
+	{ .name = "kx134-1211", .driver_data = (kernel_ulong_t)&kx134_chip_info },
 	{ .name = "kx132acr-lbz", .driver_data = (kernel_ulong_t)&kx132acr_chip_info },
+	{ .name = "kx134acr-lbz", .driver_data = (kernel_ulong_t)&kx134acr_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(spi, kx022a_id);
@@ -46,7 +48,9 @@ MODULE_DEVICE_TABLE(spi, kx022a_id);
 static const struct of_device_id kx022a_of_match[] = {
 	{ .compatible = "kionix,kx022a", .data = &kx022a_chip_info },
 	{ .compatible = "kionix,kx132-1211", .data = &kx132_chip_info },
+	{ .compatible = "kionix,kx134-1211", .data = &kx134_chip_info },
 	{ .compatible = "rohm,kx132acr-lbz", .data = &kx132acr_chip_info },
+	{ .compatible = "rohm,kx134acr-lbz", .data = &kx134acr_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, kx022a_of_match);
diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c
index 670bac21965b..5aeb3b951ac5 100644
--- a/drivers/iio/accel/kionix-kx022a.c
+++ b/drivers/iio/accel/kionix-kx022a.c
@@ -5,6 +5,7 @@
  * ROHM/KIONIX accelerometer driver
  */
 
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/interrupt.h>
@@ -407,11 +408,21 @@ static const int kx022a_scale_table[][2] = {
 	{ 0, 4788403 },
 };
 
+/* KX134ACR-LBZ ranges are (+/-) 8, 16, 32, 64 G */
+static const int kx134acr_lbz_scale_table[][2] = {
+	{ 0, 2394202 },
+	{ 0, 4788403 },
+	{ 0, 9576807 },
+	{ 0, 19153613 },
+};
+
 static int kx022a_read_avail(struct iio_dev *indio_dev,
 			     struct iio_chan_spec const *chan,
 			     const int **vals, int *type, int *length,
 			     long mask)
 {
+	struct kx022a_data *data = iio_priv(indio_dev);
+
 	switch (mask) {
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		*vals = (const int *)kx022a_accel_samp_freq_table;
@@ -420,9 +431,8 @@ static int kx022a_read_avail(struct iio_dev *indio_dev,
 		*type = IIO_VAL_INT_PLUS_MICRO;
 		return IIO_AVAIL_LIST;
 	case IIO_CHAN_INFO_SCALE:
-		*vals = (const int *)kx022a_scale_table;
-		*length = ARRAY_SIZE(kx022a_scale_table) *
-			  ARRAY_SIZE(kx022a_scale_table[0]);
+		*vals = (const int *)data->chip_info->scale_table;
+		*length = data->chip_info->scale_table_size;
 		*type = IIO_VAL_INT_PLUS_NANO;
 		return IIO_AVAIL_LIST;
 	default:
@@ -438,17 +448,17 @@ static void kx022a_reg2freq(unsigned int val,  int *val1, int *val2)
 	*val2 = kx022a_accel_samp_freq_table[val & KX022A_MASK_ODR][1];
 }
 
-static void kx022a_reg2scale(unsigned int val, unsigned int *val1,
-			     unsigned int *val2)
+static void kx022a_reg2scale(struct kx022a_data *data, unsigned int val,
+			     unsigned int *val1, unsigned int *val2)
 {
 	val &= KX022A_MASK_GSEL;
 	val >>= KX022A_GSEL_SHIFT;
 
-	*val1 = kx022a_scale_table[val][0];
-	*val2 = kx022a_scale_table[val][1];
+	*val1 = data->chip_info->scale_table[val][0];
+	*val2 = data->chip_info->scale_table[val][1];
 }
 
-static int kx022a_turn_on_off_unlocked(struct kx022a_data *data, bool on)
+static int __kx022a_turn_on_off(struct kx022a_data *data, bool on)
 {
 	int ret;
 
@@ -469,7 +479,7 @@ static int kx022a_turn_off_lock(struct kx022a_data *data)
 	int ret;
 
 	mutex_lock(&data->mutex);
-	ret = kx022a_turn_on_off_unlocked(data, false);
+	ret = __kx022a_turn_on_off(data, false);
 	if (ret)
 		mutex_unlock(&data->mutex);
 
@@ -480,7 +490,7 @@ static int kx022a_turn_on_unlock(struct kx022a_data *data)
 {
 	int ret;
 
-	ret = kx022a_turn_on_off_unlocked(data, true);
+	ret = __kx022a_turn_on_off(data, true);
 	mutex_unlock(&data->mutex);
 
 	return ret;
@@ -543,11 +553,11 @@ static int kx022a_write_raw(struct iio_dev *idev,
 		kx022a_turn_on_unlock(data);
 		break;
 	case IIO_CHAN_INFO_SCALE:
-		n = ARRAY_SIZE(kx022a_scale_table);
+		n = data->chip_info->scale_table_size / 2;
 
 		while (n-- > 0)
-			if (val == kx022a_scale_table[n][0] &&
-			    val2 == kx022a_scale_table[n][1])
+			if (val == data->chip_info->scale_table[n][0] &&
+			    val2 == data->chip_info->scale_table[n][1])
 				break;
 		if (n < 0) {
 			ret = -EINVAL;
@@ -642,7 +652,7 @@ static int kx022a_read_raw(struct iio_dev *idev,
 		if (ret < 0)
 			return ret;
 
-		kx022a_reg2scale(regval, val, val2);
+		kx022a_reg2scale(data, regval, val, val2);
 
 		return IIO_VAL_INT_PLUS_NANO;
 	}
@@ -912,18 +922,19 @@ static int kx022a_fifo_disable(struct kx022a_data *data)
 {
 	int ret = 0;
 
-	ret = kx022a_turn_off_lock(data);
+	guard(mutex)(&data->mutex);
+	ret = __kx022a_turn_on_off(data, false);
 	if (ret)
 		return ret;
 
 	ret = regmap_clear_bits(data->regmap, data->ien_reg, KX022A_MASK_WMI);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	ret = regmap_clear_bits(data->regmap, data->chip_info->buf_cntl2,
 				KX022A_MASK_BUF_EN);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	data->state &= ~KX022A_STATE_FIFO;
 
@@ -931,12 +942,7 @@ static int kx022a_fifo_disable(struct kx022a_data *data)
 
 	kfree(data->fifo_buffer);
 
-	return kx022a_turn_on_unlock(data);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return __kx022a_turn_on_off(data, true);
 }
 
 static int kx022a_buffer_predisable(struct iio_dev *idev)
@@ -959,33 +965,29 @@ static int kx022a_fifo_enable(struct kx022a_data *data)
 	if (!data->fifo_buffer)
 		return -ENOMEM;
 
-	ret = kx022a_turn_off_lock(data);
+	guard(mutex)(&data->mutex);
+	ret = __kx022a_turn_on_off(data, false);
 	if (ret)
 		return ret;
 
 	/* Update watermark to HW */
 	ret = kx022a_fifo_set_wmi(data);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	/* Enable buffer */
 	ret = regmap_set_bits(data->regmap, data->chip_info->buf_cntl2,
 			      KX022A_MASK_BUF_EN);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	data->state |= KX022A_STATE_FIFO;
 	ret = regmap_set_bits(data->regmap, data->ien_reg,
 			      KX022A_MASK_WMI);
 	if (ret)
-		goto unlock_out;
-
-	return kx022a_turn_on_unlock(data);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
+		return ret;
 
-	return ret;
+	return __kx022a_turn_on_off(data, true);
 }
 
 static int kx022a_buffer_postenable(struct iio_dev *idev)
@@ -1053,7 +1055,7 @@ static irqreturn_t kx022a_irq_thread_handler(int irq, void *private)
 	struct kx022a_data *data = iio_priv(idev);
 	irqreturn_t ret = IRQ_NONE;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (data->trigger_enabled) {
 		iio_trigger_poll_nested(data->trig);
@@ -1068,8 +1070,6 @@ static irqreturn_t kx022a_irq_thread_handler(int irq, void *private)
 			ret = IRQ_HANDLED;
 	}
 
-	mutex_unlock(&data->mutex);
-
 	return ret;
 }
 
@@ -1079,32 +1079,26 @@ static int kx022a_trigger_set_state(struct iio_trigger *trig,
 	struct kx022a_data *data = iio_trigger_get_drvdata(trig);
 	int ret = 0;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (data->trigger_enabled == state)
-		goto unlock_out;
+		return 0;
 
 	if (data->state & KX022A_STATE_FIFO) {
 		dev_warn(data->dev, "Can't set trigger when FIFO enabled\n");
-		ret = -EBUSY;
-		goto unlock_out;
+		return -EBUSY;
 	}
 
-	ret = kx022a_turn_on_off_unlocked(data, false);
+	ret = __kx022a_turn_on_off(data, false);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	data->trigger_enabled = state;
 	ret = kx022a_set_drdy_irq(data, state);
 	if (ret)
-		goto unlock_out;
-
-	ret = kx022a_turn_on_off_unlocked(data, true);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
+		return ret;
 
-	return ret;
+	return __kx022a_turn_on_off(data, true);
 }
 
 static const struct iio_trigger_ops kx022a_trigger_ops = {
@@ -1121,10 +1115,15 @@ static int kx022a_chip_init(struct kx022a_data *data)
 		return ret;
 
 	/*
-	 * I've seen I2C read failures if we poll too fast after the sensor
-	 * reset. Slight delay gives I2C block the time to recover.
+	 * According to the power-on procedure documents, there is (at least)
+	 * 2ms delay required after the software reset. This should be same for
+	 * all, KX022ACR-Z, KX132-1211, KX132ACR-LBZ and KX134ACR-LBZ.
+	 *
+	 * https://fscdn.rohm.com/kionix/en/document/AN010_KX022ACR-Z_Power-on_Procedure_E.pdf
+	 * https://fscdn.rohm.com/kionix/en/document/TN027-Power-On-Procedure.pdf
+	 * https://fscdn.rohm.com/kionix/en/document/AN011_KX134ACR-LBZ_Power-on_Procedure_E.pdf
 	 */
-	msleep(1);
+	msleep(2);
 
 	ret = regmap_read_poll_timeout(data->regmap, data->chip_info->cntl2, val,
 				       !(val & KX022A_MASK_SRST),
@@ -1158,6 +1157,9 @@ const struct kx022a_chip_info kx022a_chip_info = {
 	.regmap_config			= &kx022a_regmap_config,
 	.channels			= kx022a_channels,
 	.num_channels			= ARRAY_SIZE(kx022a_channels),
+	.scale_table			= kx022a_scale_table,
+	.scale_table_size		= ARRAY_SIZE(kx022a_scale_table) *
+					  ARRAY_SIZE(kx022a_scale_table[0]),
 	.fifo_length			= KX022A_FIFO_LENGTH,
 	.who				= KX022A_REG_WHO,
 	.id				= KX022A_ID,
@@ -1183,6 +1185,9 @@ const struct kx022a_chip_info kx132_chip_info = {
 	.regmap_config		  = &kx132_regmap_config,
 	.channels		  = kx132_channels,
 	.num_channels		  = ARRAY_SIZE(kx132_channels),
+	.scale_table			= kx022a_scale_table,
+	.scale_table_size		= ARRAY_SIZE(kx022a_scale_table) *
+					  ARRAY_SIZE(kx022a_scale_table[0]),
 	.fifo_length		  = KX132_FIFO_LENGTH,
 	.who			  = KX132_REG_WHO,
 	.id			  = KX132_ID,
@@ -1204,6 +1209,35 @@ const struct kx022a_chip_info kx132_chip_info = {
 };
 EXPORT_SYMBOL_NS_GPL(kx132_chip_info, "IIO_KX022A");
 
+const struct kx022a_chip_info kx134_chip_info = {
+	.name			  = "kx134-1211",
+	.regmap_config		  = &kx132_regmap_config,
+	.channels		  = kx132_channels,
+	.num_channels		  = ARRAY_SIZE(kx132_channels),
+	.scale_table			= kx134acr_lbz_scale_table,
+	.scale_table_size		= ARRAY_SIZE(kx134acr_lbz_scale_table) *
+					  ARRAY_SIZE(kx134acr_lbz_scale_table[0]),
+	.fifo_length		  = KX132_FIFO_LENGTH,
+	.who			  = KX132_REG_WHO,
+	.id			  = KX134_1211_ID,
+	.cntl			  = KX132_REG_CNTL,
+	.cntl2			  = KX132_REG_CNTL2,
+	.odcntl			  = KX132_REG_ODCNTL,
+	.buf_cntl1		  = KX132_REG_BUF_CNTL1,
+	.buf_cntl2		  = KX132_REG_BUF_CNTL2,
+	.buf_clear		  = KX132_REG_BUF_CLEAR,
+	.buf_status1		  = KX132_REG_BUF_STATUS_1,
+	.buf_smp_lvl_mask	  = KX132_MASK_BUF_SMP_LVL,
+	.buf_read		  = KX132_REG_BUF_READ,
+	.inc1			  = KX132_REG_INC1,
+	.inc4			  = KX132_REG_INC4,
+	.inc5			  = KX132_REG_INC5,
+	.inc6			  = KX132_REG_INC6,
+	.xout_l			  = KX132_REG_XOUT_L,
+	.get_fifo_bytes_available = kx132_get_fifo_bytes_available,
+};
+EXPORT_SYMBOL_NS_GPL(kx134_chip_info, "IIO_KX022A");
+
 /*
  * Despite the naming, KX132ACR-LBZ is not similar to KX132-1211 but it is
  * exact subset of KX022A. KX132ACR-LBZ is meant to be used for industrial
@@ -1216,6 +1250,9 @@ const struct kx022a_chip_info kx132acr_chip_info = {
 	.regmap_config			= &kx022a_regmap_config,
 	.channels			= kx022a_channels,
 	.num_channels			= ARRAY_SIZE(kx022a_channels),
+	.scale_table			= kx022a_scale_table,
+	.scale_table_size		= ARRAY_SIZE(kx022a_scale_table) *
+					  ARRAY_SIZE(kx022a_scale_table[0]),
 	.fifo_length			= KX022A_FIFO_LENGTH,
 	.who				= KX022A_REG_WHO,
 	.id				= KX132ACR_LBZ_ID,
@@ -1236,6 +1273,34 @@ const struct kx022a_chip_info kx132acr_chip_info = {
 };
 EXPORT_SYMBOL_NS_GPL(kx132acr_chip_info, "IIO_KX022A");
 
+const struct kx022a_chip_info kx134acr_chip_info = {
+	.name				= "kx134acr-lbz",
+	.regmap_config			= &kx022a_regmap_config,
+	.channels			= kx022a_channels,
+	.num_channels			= ARRAY_SIZE(kx022a_channels),
+	.scale_table			= kx134acr_lbz_scale_table,
+	.scale_table_size		= ARRAY_SIZE(kx134acr_lbz_scale_table) *
+					  ARRAY_SIZE(kx134acr_lbz_scale_table[0]),
+	.fifo_length			= KX022A_FIFO_LENGTH,
+	.who				= KX022A_REG_WHO,
+	.id				= KX134ACR_LBZ_ID,
+	.cntl				= KX022A_REG_CNTL,
+	.cntl2				= KX022A_REG_CNTL2,
+	.odcntl				= KX022A_REG_ODCNTL,
+	.buf_cntl1			= KX022A_REG_BUF_CNTL1,
+	.buf_cntl2			= KX022A_REG_BUF_CNTL2,
+	.buf_clear			= KX022A_REG_BUF_CLEAR,
+	.buf_status1			= KX022A_REG_BUF_STATUS_1,
+	.buf_read			= KX022A_REG_BUF_READ,
+	.inc1				= KX022A_REG_INC1,
+	.inc4				= KX022A_REG_INC4,
+	.inc5				= KX022A_REG_INC5,
+	.inc6				= KX022A_REG_INC6,
+	.xout_l				= KX022A_REG_XOUT_L,
+	.get_fifo_bytes_available	= kx022a_get_fifo_bytes_available,
+};
+EXPORT_SYMBOL_NS_GPL(kx134acr_chip_info, "IIO_KX022A");
+
 int kx022a_probe_internal(struct device *dev, const struct kx022a_chip_info *chip_info)
 {
 	static const char * const regulator_names[] = {"io-vdd", "vdd"};
diff --git a/drivers/iio/accel/kionix-kx022a.h b/drivers/iio/accel/kionix-kx022a.h
index 7060438ad88c..0ed54f584223 100644
--- a/drivers/iio/accel/kionix-kx022a.h
+++ b/drivers/iio/accel/kionix-kx022a.h
@@ -14,6 +14,7 @@
 #define KX022A_REG_WHO		0x0f
 #define KX022A_ID		0xc8
 #define KX132ACR_LBZ_ID		0xd8
+#define KX134ACR_LBZ_ID		0xcc
 
 #define KX022A_REG_CNTL2	0x19
 #define KX022A_MASK_SRST	BIT(7)
@@ -77,6 +78,7 @@
 
 #define KX132_REG_WHO		0x13
 #define KX132_ID		0x3d
+#define KX134_1211_ID		0x46
 
 #define KX132_FIFO_LENGTH	86
 
@@ -135,6 +137,14 @@ struct kx022a_data;
  *
  * @name:			name of the device
  * @regmap_config:		pointer to register map configuration
+ * @scale_table:		An array of tables of scaling factors for
+ *				a supported acceleration measurement range.
+ *				Each table containing a single scaling
+ *				factor consisting of two integers. The first
+ *				value in a table is the integer part, and
+ *				the second value is the	fractional part as
+ *				parts per billion.
+ * @scale_table_size:		Amount of values in tables.
  * @channels:			pointer to iio_chan_spec array
  * @num_channels:		number of iio_chan_spec channels
  * @fifo_length:		number of 16-bit samples in a full buffer
@@ -161,6 +171,8 @@ struct kx022a_data;
 struct kx022a_chip_info {
 	const char *name;
 	const struct regmap_config *regmap_config;
+	const int (*scale_table)[2];
+	const int scale_table_size;
 	const struct iio_chan_spec *channels;
 	unsigned int num_channels;
 	unsigned int fifo_length;
@@ -187,6 +199,8 @@ int kx022a_probe_internal(struct device *dev, const struct kx022a_chip_info *chi
 
 extern const struct kx022a_chip_info kx022a_chip_info;
 extern const struct kx022a_chip_info kx132_chip_info;
+extern const struct kx022a_chip_info kx134_chip_info;
 extern const struct kx022a_chip_info kx132acr_chip_info;
+extern const struct kx022a_chip_info kx134acr_chip_info;
 
 #endif
diff --git a/drivers/iio/adc/ad4000.c b/drivers/iio/adc/ad4000.c
index b3b82535f5c1..1d556a842a68 100644
--- a/drivers/iio/adc/ad4000.c
+++ b/drivers/iio/adc/ad4000.c
@@ -35,10 +35,6 @@
 
 #define AD4000_SCALE_OPTIONS		2
 
-#define AD4000_TQUIET1_NS		190
-#define AD4000_TQUIET2_NS		60
-#define AD4000_TCONV_NS			320
-
 #define __AD4000_DIFF_CHANNEL(_sign, _real_bits, _storage_bits, _reg_access)	\
 {										\
 	.type = IIO_VOLTAGE,							\
@@ -49,6 +45,7 @@
 	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |				\
 			      BIT(IIO_CHAN_INFO_SCALE),				\
 	.info_mask_separate_available = _reg_access ? BIT(IIO_CHAN_INFO_SCALE) : 0,\
+	.scan_index = 0,							\
 	.scan_type = {								\
 		.sign = _sign,							\
 		.realbits = _real_bits,						\
@@ -62,6 +59,12 @@
 	__AD4000_DIFF_CHANNEL((_sign), (_real_bits),				\
 				     ((_real_bits) > 16 ? 32 : 16), (_reg_access))
 
+#define AD4000_DIFF_CHANNELS(_sign, _real_bits, _reg_access)			\
+{										\
+	AD4000_DIFF_CHANNEL(_sign, _real_bits, _reg_access),			\
+	IIO_CHAN_SOFT_TIMESTAMP(1),						\
+}
+
 #define __AD4000_PSEUDO_DIFF_CHANNEL(_sign, _real_bits, _storage_bits, _reg_access)\
 {										\
 	.type = IIO_VOLTAGE,							\
@@ -71,6 +74,7 @@
 			      BIT(IIO_CHAN_INFO_SCALE) |			\
 			      BIT(IIO_CHAN_INFO_OFFSET),			\
 	.info_mask_separate_available = _reg_access ? BIT(IIO_CHAN_INFO_SCALE) : 0,\
+	.scan_index = 0,							\
 	.scan_type = {								\
 		.sign = _sign,							\
 		.realbits = _real_bits,						\
@@ -84,6 +88,12 @@
 	__AD4000_PSEUDO_DIFF_CHANNEL((_sign), (_real_bits),			\
 				     ((_real_bits) > 16 ? 32 : 16), (_reg_access))
 
+#define AD4000_PSEUDO_DIFF_CHANNELS(_sign, _real_bits, _reg_access)		\
+{										\
+	AD4000_PSEUDO_DIFF_CHANNEL(_sign, _real_bits, _reg_access),		\
+	IIO_CHAN_SOFT_TIMESTAMP(1),						\
+}
+
 static const char * const ad4000_power_supplies[] = {
 	"vdd", "vio"
 };
@@ -108,111 +118,280 @@ static const int ad4000_gains[] = {
 	454, 909, 1000, 1900,
 };
 
+struct ad4000_time_spec {
+	int t_conv_ns;
+	int t_quiet2_ns;
+};
+
+/*
+ * Same timing specifications for all of AD4000, AD4001, ..., AD4008, AD4010,
+ * ADAQ4001, and ADAQ4003.
+ */
+static const struct ad4000_time_spec ad4000_t_spec = {
+	.t_conv_ns = 320,
+	.t_quiet2_ns = 60,
+};
+
+/* AD4020, AD4021, AD4022 */
+static const struct ad4000_time_spec ad4020_t_spec = {
+	.t_conv_ns = 350,
+	.t_quiet2_ns = 60,
+};
+
+/* AD7983, AD7984 */
+static const struct ad4000_time_spec ad7983_t_spec = {
+	.t_conv_ns = 500,
+	.t_quiet2_ns = 0,
+};
+
+/* AD7980, AD7982 */
+static const struct ad4000_time_spec ad7980_t_spec = {
+	.t_conv_ns = 800,
+	.t_quiet2_ns = 0,
+};
+
+/* AD7946, AD7686, AD7688, AD7988-5, AD7693 */
+static const struct ad4000_time_spec ad7686_t_spec = {
+	.t_conv_ns = 1600,
+	.t_quiet2_ns = 0,
+};
+
+/* AD7690 */
+static const struct ad4000_time_spec ad7690_t_spec = {
+	.t_conv_ns = 2100,
+	.t_quiet2_ns = 0,
+};
+
+/* AD7942, AD7685, AD7687 */
+static const struct ad4000_time_spec ad7687_t_spec = {
+	.t_conv_ns = 3200,
+	.t_quiet2_ns = 0,
+};
+
+/* AD7691 */
+static const struct ad4000_time_spec ad7691_t_spec = {
+	.t_conv_ns = 3700,
+	.t_quiet2_ns = 0,
+};
+
+/* AD7988-1 */
+static const struct ad4000_time_spec ad7988_1_t_spec = {
+	.t_conv_ns = 9500,
+	.t_quiet2_ns = 0,
+};
+
 struct ad4000_chip_info {
 	const char *dev_name;
-	struct iio_chan_spec chan_spec;
-	struct iio_chan_spec reg_access_chan_spec;
+	struct iio_chan_spec chan_spec[2];
+	struct iio_chan_spec reg_access_chan_spec[2];
+	const struct ad4000_time_spec *time_spec;
 	bool has_hardware_gain;
 };
 
 static const struct ad4000_chip_info ad4000_chip_info = {
 	.dev_name = "ad4000",
-	.chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 0),
-	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 1),
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4001_chip_info = {
 	.dev_name = "ad4001",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 16, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 16, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 16, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4002_chip_info = {
 	.dev_name = "ad4002",
-	.chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 0),
-	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 1),
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 0),
+	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4003_chip_info = {
 	.dev_name = "ad4003",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4004_chip_info = {
 	.dev_name = "ad4004",
-	.chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 0),
-	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 1),
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4005_chip_info = {
 	.dev_name = "ad4005",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 16, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 16, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 16, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4006_chip_info = {
 	.dev_name = "ad4006",
-	.chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 0),
-	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 1),
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 0),
+	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4007_chip_info = {
 	.dev_name = "ad4007",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4008_chip_info = {
 	.dev_name = "ad4008",
-	.chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 0),
-	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 16, 1),
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4010_chip_info = {
 	.dev_name = "ad4010",
-	.chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 0),
-	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNEL('u', 18, 1),
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 0),
+	.reg_access_chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 18, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4011_chip_info = {
 	.dev_name = "ad4011",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1),
+	.time_spec = &ad4000_t_spec,
 };
 
 static const struct ad4000_chip_info ad4020_chip_info = {
 	.dev_name = "ad4020",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 20, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 20, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 20, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 20, 1),
+	.time_spec = &ad4020_t_spec,
 };
 
 static const struct ad4000_chip_info ad4021_chip_info = {
 	.dev_name = "ad4021",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 20, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 20, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 20, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 20, 1),
+	.time_spec = &ad4020_t_spec,
 };
 
 static const struct ad4000_chip_info ad4022_chip_info = {
 	.dev_name = "ad4022",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 20, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 20, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 20, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 20, 1),
+	.time_spec = &ad4020_t_spec,
 };
 
 static const struct ad4000_chip_info adaq4001_chip_info = {
 	.dev_name = "adaq4001",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 16, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 16, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 16, 1),
+	.time_spec = &ad4000_t_spec,
 	.has_hardware_gain = true,
 };
 
 static const struct ad4000_chip_info adaq4003_chip_info = {
 	.dev_name = "adaq4003",
-	.chan_spec = AD4000_DIFF_CHANNEL('s', 18, 0),
-	.reg_access_chan_spec = AD4000_DIFF_CHANNEL('s', 18, 1),
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.reg_access_chan_spec = AD4000_DIFF_CHANNELS('s', 18, 1),
+	.time_spec = &ad4000_t_spec,
 	.has_hardware_gain = true,
 };
 
+static const struct ad4000_chip_info ad7685_chip_info = {
+	.dev_name = "ad7685",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.time_spec = &ad7687_t_spec,
+};
+
+static const struct ad4000_chip_info ad7686_chip_info = {
+	.dev_name = "ad7686",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.time_spec = &ad7686_t_spec,
+};
+
+static const struct ad4000_chip_info ad7687_chip_info = {
+	.dev_name = "ad7687",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0),
+	.time_spec = &ad7687_t_spec,
+};
+
+static const struct ad4000_chip_info ad7688_chip_info = {
+	.dev_name = "ad7688",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0),
+	.time_spec = &ad7686_t_spec,
+};
+
+static const struct ad4000_chip_info ad7690_chip_info = {
+	.dev_name = "ad7690",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.time_spec = &ad7690_t_spec,
+};
+
+static const struct ad4000_chip_info ad7691_chip_info = {
+	.dev_name = "ad7691",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.time_spec = &ad7691_t_spec,
+};
+
+static const struct ad4000_chip_info ad7693_chip_info = {
+	.dev_name = "ad7693",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 16, 0),
+	.time_spec = &ad7686_t_spec,
+};
+
+static const struct ad4000_chip_info ad7942_chip_info = {
+	.dev_name = "ad7942",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 14, 0),
+	.time_spec = &ad7687_t_spec,
+};
+
+static const struct ad4000_chip_info ad7946_chip_info = {
+	.dev_name = "ad7946",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 14, 0),
+	.time_spec = &ad7686_t_spec,
+};
+
+static const struct ad4000_chip_info ad7980_chip_info = {
+	.dev_name = "ad7980",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.time_spec = &ad7980_t_spec,
+};
+
+static const struct ad4000_chip_info ad7982_chip_info = {
+	.dev_name = "ad7982",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.time_spec = &ad7980_t_spec,
+};
+
+static const struct ad4000_chip_info ad7983_chip_info = {
+	.dev_name = "ad7983",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.time_spec = &ad7983_t_spec,
+};
+
+static const struct ad4000_chip_info ad7984_chip_info = {
+	.dev_name = "ad7984",
+	.chan_spec = AD4000_DIFF_CHANNELS('s', 18, 0),
+	.time_spec = &ad7983_t_spec,
+};
+
+static const struct ad4000_chip_info ad7988_1_chip_info = {
+	.dev_name = "ad7988-1",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.time_spec = &ad7988_1_t_spec,
+};
+
+static const struct ad4000_chip_info ad7988_5_chip_info = {
+	.dev_name = "ad7988-5",
+	.chan_spec = AD4000_PSEUDO_DIFF_CHANNELS('u', 16, 0),
+	.time_spec = &ad7686_t_spec,
+};
+
 struct ad4000_state {
 	struct spi_device *spi;
 	struct gpio_desc *cnv_gpio;
@@ -224,6 +403,7 @@ struct ad4000_state {
 	bool span_comp;
 	u16 gain_milli;
 	int scale_tbl[AD4000_SCALE_OPTIONS][2];
+	const struct ad4000_time_spec *time_spec;
 
 	/*
 	 * DMA (thus cache coherency maintenance) requires the transfer buffers
@@ -234,7 +414,7 @@ struct ad4000_state {
 			__be16 sample_buf16;
 			__be32 sample_buf32;
 		} data;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan __aligned(IIO_DMA_MINALIGN);
 	u8 tx_buf[2];
 	u8 rx_buf[2];
@@ -488,16 +668,15 @@ static const struct iio_info ad4000_info = {
 static int ad4000_prepare_3wire_mode_message(struct ad4000_state *st,
 					     const struct iio_chan_spec *chan)
 {
-	unsigned int cnv_pulse_time = AD4000_TCONV_NS;
 	struct spi_transfer *xfers = st->xfers;
 
 	xfers[0].cs_change = 1;
-	xfers[0].cs_change_delay.value = cnv_pulse_time;
+	xfers[0].cs_change_delay.value = st->time_spec->t_conv_ns;
 	xfers[0].cs_change_delay.unit = SPI_DELAY_UNIT_NSECS;
 
 	xfers[1].rx_buf = &st->scan.data;
 	xfers[1].len = BITS_TO_BYTES(chan->scan_type.storagebits);
-	xfers[1].delay.value = AD4000_TQUIET2_NS;
+	xfers[1].delay.value = st->time_spec->t_quiet2_ns;
 	xfers[1].delay.unit = SPI_DELAY_UNIT_NSECS;
 
 	spi_message_init_with_transfers(&st->msg, st->xfers, 2);
@@ -515,7 +694,6 @@ static int ad4000_prepare_3wire_mode_message(struct ad4000_state *st,
 static int ad4000_prepare_4wire_mode_message(struct ad4000_state *st,
 					     const struct iio_chan_spec *chan)
 {
-	unsigned int cnv_to_sdi_time = AD4000_TCONV_NS;
 	struct spi_transfer *xfers = st->xfers;
 
 	/*
@@ -523,7 +701,7 @@ static int ad4000_prepare_4wire_mode_message(struct ad4000_state *st,
 	 * going low.
 	 */
 	xfers[0].cs_off = 1;
-	xfers[0].delay.value = cnv_to_sdi_time;
+	xfers[0].delay.value = st->time_spec->t_conv_ns;
 	xfers[0].delay.unit = SPI_DELAY_UNIT_NSECS;
 
 	xfers[1].rx_buf = &st->scan.data;
@@ -562,6 +740,7 @@ static int ad4000_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 	st->spi = spi;
+	st->time_spec = chip->time_spec;
 
 	ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(ad4000_power_supplies),
 					     ad4000_power_supplies);
@@ -591,7 +770,7 @@ static int ad4000_probe(struct spi_device *spi)
 	switch (st->sdi_pin) {
 	case AD4000_SDI_MOSI:
 		indio_dev->info = &ad4000_reg_access_info;
-		indio_dev->channels = &chip->reg_access_chan_spec;
+		indio_dev->channels = chip->reg_access_chan_spec;
 
 		/*
 		 * In "3-wire mode", the ADC SDI line must be kept high when
@@ -603,7 +782,7 @@ static int ad4000_probe(struct spi_device *spi)
 		if (ret < 0)
 			return ret;
 
-		ret = ad4000_prepare_3wire_mode_message(st, indio_dev->channels);
+		ret = ad4000_prepare_3wire_mode_message(st, &indio_dev->channels[0]);
 		if (ret)
 			return ret;
 
@@ -614,16 +793,16 @@ static int ad4000_probe(struct spi_device *spi)
 		break;
 	case AD4000_SDI_VIO:
 		indio_dev->info = &ad4000_info;
-		indio_dev->channels = &chip->chan_spec;
-		ret = ad4000_prepare_3wire_mode_message(st, indio_dev->channels);
+		indio_dev->channels = chip->chan_spec;
+		ret = ad4000_prepare_3wire_mode_message(st, &indio_dev->channels[0]);
 		if (ret)
 			return ret;
 
 		break;
 	case AD4000_SDI_CS:
 		indio_dev->info = &ad4000_info;
-		indio_dev->channels = &chip->chan_spec;
-		ret = ad4000_prepare_4wire_mode_message(st, indio_dev->channels);
+		indio_dev->channels = chip->chan_spec;
+		ret = ad4000_prepare_4wire_mode_message(st, &indio_dev->channels[0]);
 		if (ret)
 			return ret;
 
@@ -637,7 +816,7 @@ static int ad4000_probe(struct spi_device *spi)
 	}
 
 	indio_dev->name = chip->dev_name;
-	indio_dev->num_channels = 1;
+	indio_dev->num_channels = 2;
 
 	ret = devm_mutex_init(dev, &st->lock);
 	if (ret)
@@ -658,7 +837,7 @@ static int ad4000_probe(struct spi_device *spi)
 		}
 	}
 
-	ad4000_fill_scale_tbl(st, indio_dev->channels);
+	ad4000_fill_scale_tbl(st, &indio_dev->channels[0]);
 
 	ret = devm_iio_triggered_buffer_setup(dev, indio_dev,
 					      &iio_pollfunc_store_time,
@@ -686,6 +865,21 @@ static const struct spi_device_id ad4000_id[] = {
 	{ "ad4022", (kernel_ulong_t)&ad4022_chip_info },
 	{ "adaq4001", (kernel_ulong_t)&adaq4001_chip_info },
 	{ "adaq4003", (kernel_ulong_t)&adaq4003_chip_info },
+	{ "ad7685", (kernel_ulong_t)&ad7685_chip_info },
+	{ "ad7686", (kernel_ulong_t)&ad7686_chip_info },
+	{ "ad7687", (kernel_ulong_t)&ad7687_chip_info },
+	{ "ad7688", (kernel_ulong_t)&ad7688_chip_info },
+	{ "ad7690", (kernel_ulong_t)&ad7690_chip_info },
+	{ "ad7691", (kernel_ulong_t)&ad7691_chip_info },
+	{ "ad7693", (kernel_ulong_t)&ad7693_chip_info },
+	{ "ad7942", (kernel_ulong_t)&ad7942_chip_info },
+	{ "ad7946", (kernel_ulong_t)&ad7946_chip_info },
+	{ "ad7980", (kernel_ulong_t)&ad7980_chip_info },
+	{ "ad7982", (kernel_ulong_t)&ad7982_chip_info },
+	{ "ad7983", (kernel_ulong_t)&ad7983_chip_info },
+	{ "ad7984", (kernel_ulong_t)&ad7984_chip_info },
+	{ "ad7988-1", (kernel_ulong_t)&ad7988_1_chip_info },
+	{ "ad7988-5", (kernel_ulong_t)&ad7988_5_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(spi, ad4000_id);
@@ -707,6 +901,21 @@ static const struct of_device_id ad4000_of_match[] = {
 	{ .compatible = "adi,ad4022", .data = &ad4022_chip_info },
 	{ .compatible = "adi,adaq4001", .data = &adaq4001_chip_info },
 	{ .compatible = "adi,adaq4003", .data = &adaq4003_chip_info },
+	{ .compatible = "adi,ad7685", .data = &ad7685_chip_info },
+	{ .compatible = "adi,ad7686", .data = &ad7686_chip_info },
+	{ .compatible = "adi,ad7687", .data = &ad7687_chip_info },
+	{ .compatible = "adi,ad7688", .data = &ad7688_chip_info },
+	{ .compatible = "adi,ad7690", .data = &ad7690_chip_info },
+	{ .compatible = "adi,ad7691", .data = &ad7691_chip_info },
+	{ .compatible = "adi,ad7693", .data = &ad7693_chip_info },
+	{ .compatible = "adi,ad7942", .data = &ad7942_chip_info },
+	{ .compatible = "adi,ad7946", .data = &ad7946_chip_info },
+	{ .compatible = "adi,ad7980", .data = &ad7980_chip_info },
+	{ .compatible = "adi,ad7982", .data = &ad7982_chip_info },
+	{ .compatible = "adi,ad7983", .data = &ad7983_chip_info },
+	{ .compatible = "adi,ad7984", .data = &ad7984_chip_info },
+	{ .compatible = "adi,ad7988-1", .data = &ad7988_1_chip_info },
+	{ .compatible = "adi,ad7988-5", .data = &ad7988_5_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, ad4000_of_match);
diff --git a/drivers/iio/adc/ad4695.c b/drivers/iio/adc/ad4695.c
index 0146aed9069f..b79d135a5471 100644
--- a/drivers/iio/adc/ad4695.c
+++ b/drivers/iio/adc/ad4695.c
@@ -30,7 +30,7 @@
 #include <linux/spi/spi.h>
 #include <linux/units.h>
 
-#include <dt-bindings/iio/adi,ad4695.h>
+#include <dt-bindings/iio/adc/adi,ad4695.h>
 
 /* AD4695 registers */
 #define AD4695_REG_SPI_CONFIG_A				0x0000
diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
index 3d678c420cbf..6ae27cdd3250 100644
--- a/drivers/iio/adc/ad7124.c
+++ b/drivers/iio/adc/ad7124.c
@@ -95,6 +95,10 @@
 #define AD7124_MAX_CONFIGS	8
 #define AD7124_MAX_CHANNELS	16
 
+/* AD7124 input sources */
+#define AD7124_INPUT_TEMPSENSOR	16
+#define AD7124_INPUT_AVSS	17
+
 enum ad7124_ids {
 	ID_AD7124_4,
 	ID_AD7124_8,
@@ -360,20 +364,21 @@ static int ad7124_find_free_config_slot(struct ad7124_state *st)
 	return free_cfg_slot;
 }
 
+/* Only called during probe, so dev_err_probe() can be used */
 static int ad7124_init_config_vref(struct ad7124_state *st, struct ad7124_channel_config *cfg)
 {
+	struct device *dev = &st->sd.spi->dev;
 	unsigned int refsel = cfg->refsel;
 
 	switch (refsel) {
 	case AD7124_REFIN1:
 	case AD7124_REFIN2:
 	case AD7124_AVDD_REF:
-		if (IS_ERR(st->vref[refsel])) {
-			dev_err(&st->sd.spi->dev,
-				"Error, trying to use external voltage reference without a %s regulator.\n",
-				ad7124_ref_names[refsel]);
-			return PTR_ERR(st->vref[refsel]);
-		}
+		if (IS_ERR(st->vref[refsel]))
+			return dev_err_probe(dev, PTR_ERR(st->vref[refsel]),
+					     "Error, trying to use external voltage reference without a %s regulator.\n",
+					     ad7124_ref_names[refsel]);
+
 		cfg->vref_mv = regulator_get_voltage(st->vref[refsel]);
 		/* Conversion from uV to mV */
 		cfg->vref_mv /= 1000;
@@ -384,8 +389,7 @@ static int ad7124_init_config_vref(struct ad7124_state *st, struct ad7124_channe
 		st->adc_control |= AD7124_ADC_CTRL_REF_EN(1);
 		return 0;
 	default:
-		dev_err(&st->sd.spi->dev, "Invalid reference %d\n", refsel);
-		return -EINVAL;
+		return dev_err_probe(dev, -EINVAL, "Invalid reference %d\n", refsel);
 	}
 }
 
@@ -571,6 +575,7 @@ static const struct ad_sigma_delta_info ad7124_sigma_delta_info = {
 	.data_reg = AD7124_DATA,
 	.num_slots = 8,
 	.irq_flags = IRQF_TRIGGER_FALLING,
+	.num_resetclks = 64,
 };
 
 static int ad7124_read_raw(struct iio_dev *indio_dev,
@@ -588,26 +593,59 @@ static int ad7124_read_raw(struct iio_dev *indio_dev,
 
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SCALE:
-		mutex_lock(&st->cfgs_lock);
+		switch (chan->type) {
+		case IIO_VOLTAGE:
+			mutex_lock(&st->cfgs_lock);
 
-		idx = st->channels[chan->address].cfg.pga_bits;
-		*val = st->channels[chan->address].cfg.vref_mv;
-		if (st->channels[chan->address].cfg.bipolar)
-			*val2 = chan->scan_type.realbits - 1 + idx;
-		else
-			*val2 = chan->scan_type.realbits + idx;
+			idx = st->channels[chan->address].cfg.pga_bits;
+			*val = st->channels[chan->address].cfg.vref_mv;
+			if (st->channels[chan->address].cfg.bipolar)
+				*val2 = chan->scan_type.realbits - 1 + idx;
+			else
+				*val2 = chan->scan_type.realbits + idx;
+
+			mutex_unlock(&st->cfgs_lock);
+			return IIO_VAL_FRACTIONAL_LOG2;
+
+		case IIO_TEMP:
+			/*
+			 * According to the data sheet
+			 *   Temperature (°C)
+			 * = ((Conversion − 0x800000)/13584) − 272.5
+			 * = (Conversion − 0x800000 - 13584 * 272.5) / 13584
+			 * = (Conversion − 12090248) / 13584
+			 * So scale with 1000/13584 to yield °mC. Reduce by 8 to
+			 * 125/1698.
+			 */
+			*val = 125;
+			*val2 = 1698;
+			return IIO_VAL_FRACTIONAL;
+
+		default:
+			return -EINVAL;
+		}
 
-		mutex_unlock(&st->cfgs_lock);
-		return IIO_VAL_FRACTIONAL_LOG2;
 	case IIO_CHAN_INFO_OFFSET:
-		mutex_lock(&st->cfgs_lock);
-		if (st->channels[chan->address].cfg.bipolar)
-			*val = -(1 << (chan->scan_type.realbits - 1));
-		else
-			*val = 0;
+		switch (chan->type) {
+		case IIO_VOLTAGE:
+			mutex_lock(&st->cfgs_lock);
+			if (st->channels[chan->address].cfg.bipolar)
+				*val = -(1 << (chan->scan_type.realbits - 1));
+			else
+				*val = 0;
+
+			mutex_unlock(&st->cfgs_lock);
+			return IIO_VAL_INT;
+
+		case IIO_TEMP:
+			/* see calculation above */
+			*val = -12090248;
+			return IIO_VAL_INT;
+
+		default:
+			return -EINVAL;
+		}
 
-		mutex_unlock(&st->cfgs_lock);
-		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_SAMP_FREQ:
 		mutex_lock(&st->cfgs_lock);
 		*val = st->channels[chan->address].cfg.odr;
@@ -751,12 +789,14 @@ static const struct iio_info ad7124_info = {
 	.attrs = &ad7124_attrs_group,
 };
 
+/* Only called during probe, so dev_err_probe() can be used */
 static int ad7124_soft_reset(struct ad7124_state *st)
 {
+	struct device *dev = &st->sd.spi->dev;
 	unsigned int readval, timeout;
 	int ret;
 
-	ret = ad_sd_reset(&st->sd, 64);
+	ret = ad_sd_reset(&st->sd);
 	if (ret < 0)
 		return ret;
 
@@ -765,7 +805,7 @@ static int ad7124_soft_reset(struct ad7124_state *st)
 	do {
 		ret = ad_sd_read_reg(&st->sd, AD7124_STATUS, 1, &readval);
 		if (ret < 0)
-			return ret;
+			return dev_err_probe(dev, ret, "Error reading status register\n");
 
 		if (!(readval & AD7124_STATUS_POR_FLAG_MSK))
 			return 0;
@@ -774,39 +814,47 @@ static int ad7124_soft_reset(struct ad7124_state *st)
 		usleep_range(100, 2000);
 	} while (--timeout);
 
-	dev_err(&st->sd.spi->dev, "Soft reset failed\n");
-
-	return -EIO;
+	return dev_err_probe(dev, -EIO, "Soft reset failed\n");
 }
 
 static int ad7124_check_chip_id(struct ad7124_state *st)
 {
+	struct device *dev = &st->sd.spi->dev;
 	unsigned int readval, chip_id, silicon_rev;
 	int ret;
 
 	ret = ad_sd_read_reg(&st->sd, AD7124_ID, 1, &readval);
 	if (ret < 0)
-		return ret;
+		return dev_err_probe(dev, ret, "Failure to read ID register\n");
 
 	chip_id = AD7124_DEVICE_ID_GET(readval);
 	silicon_rev = AD7124_SILICON_REV_GET(readval);
 
-	if (chip_id != st->chip_info->chip_id) {
-		dev_err(&st->sd.spi->dev,
-			"Chip ID mismatch: expected %u, got %u\n",
-			st->chip_info->chip_id, chip_id);
-		return -ENODEV;
-	}
+	if (chip_id != st->chip_info->chip_id)
+		return dev_err_probe(dev, -ENODEV,
+				     "Chip ID mismatch: expected %u, got %u\n",
+				     st->chip_info->chip_id, chip_id);
 
-	if (silicon_rev == 0) {
-		dev_err(&st->sd.spi->dev,
-			"Silicon revision empty. Chip may not be present\n");
-		return -ENODEV;
-	}
+	if (silicon_rev == 0)
+		return dev_err_probe(dev, -ENODEV,
+				     "Silicon revision empty. Chip may not be present\n");
 
 	return 0;
 }
 
+/*
+ * Input specifiers 8 - 15 are explicitly reserved for ad7124-4
+ * while they are fine for ad7124-8. Values above 31 don't fit
+ * into the register field and so are invalid for sure.
+ */
+static bool ad7124_valid_input_select(unsigned int ain, const struct ad7124_chip_info *info)
+{
+	if (ain >= info->num_inputs && ain < 16)
+		return false;
+
+	return ain <= FIELD_MAX(AD7124_CHANNEL_AINM_MSK);
+}
+
 static int ad7124_parse_channel_config(struct iio_dev *indio_dev,
 				       struct device *dev)
 {
@@ -815,11 +863,23 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev,
 	struct ad7124_channel *channels;
 	struct iio_chan_spec *chan;
 	unsigned int ain[2], channel = 0, tmp;
+	unsigned int num_channels;
 	int ret;
 
-	st->num_channels = device_get_child_node_count(dev);
-	if (!st->num_channels)
-		return dev_err_probe(dev, -ENODEV, "no channel children\n");
+	num_channels = device_get_child_node_count(dev);
+
+	/*
+	 * The driver assigns each logical channel defined in the device tree
+	 * statically one channel register. So only accept 16 such logical
+	 * channels to not treat CONFIG_0 (i.e. the register following
+	 * CHANNEL_15) as an additional channel register. The driver could be
+	 * improved to lift this limitation.
+	 */
+	if (num_channels > AD7124_MAX_CHANNELS)
+		return dev_err_probe(dev, -EINVAL, "Too many channels defined\n");
+
+	/* Add one for temperature */
+	st->num_channels = min(num_channels + 1, AD7124_MAX_CHANNELS);
 
 	chan = devm_kcalloc(indio_dev->dev.parent, st->num_channels,
 			    sizeof(*chan), GFP_KERNEL);
@@ -838,16 +898,23 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev,
 	device_for_each_child_node_scoped(dev, child) {
 		ret = fwnode_property_read_u32(child, "reg", &channel);
 		if (ret)
-			return ret;
+			return dev_err_probe(dev, ret,
+					     "Failed to parse reg property of %pfwP\n", child);
 
-		if (channel >= indio_dev->num_channels)
+		if (channel >= num_channels)
 			return dev_err_probe(dev, -EINVAL,
-				"Channel index >= number of channels\n");
+					     "Channel index >= number of channels in %pfwP\n", child);
 
 		ret = fwnode_property_read_u32_array(child, "diff-channels",
 						     ain, 2);
 		if (ret)
-			return ret;
+			return dev_err_probe(dev, ret,
+					     "Failed to parse diff-channels property of %pfwP\n", child);
+
+		if (!ad7124_valid_input_select(ain[0], st->chip_info) ||
+		    !ad7124_valid_input_select(ain[1], st->chip_info))
+			return dev_err_probe(dev, -EINVAL,
+					     "diff-channels property of %pfwP contains invalid data\n", child);
 
 		st->channels[channel].nr = channel;
 		st->channels[channel].ain = AD7124_CHANNEL_AINP(ain[0]) |
@@ -874,17 +941,49 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev,
 		chan[channel].channel2 = ain[1];
 	}
 
+	if (num_channels < AD7124_MAX_CHANNELS) {
+		st->channels[num_channels] = (struct ad7124_channel) {
+			.nr = num_channels,
+			.ain = AD7124_CHANNEL_AINP(AD7124_INPUT_TEMPSENSOR) |
+				AD7124_CHANNEL_AINM(AD7124_INPUT_AVSS),
+			.cfg = {
+				.bipolar = true,
+			},
+		};
+
+		chan[num_channels] = (struct iio_chan_spec) {
+			.type = IIO_TEMP,
+			.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
+				BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_OFFSET) |
+				BIT(IIO_CHAN_INFO_SAMP_FREQ),
+			.scan_type = {
+				/*
+				 * You might find it strange that a bipolar
+				 * measurement yields an unsigned value, but
+				 * this matches the device's manual.
+				 */
+				.sign = 'u',
+				.realbits = 24,
+				.storagebits = 32,
+				.endianness = IIO_BE,
+			},
+			.address = num_channels,
+			.scan_index = num_channels,
+		};
+	}
+
 	return 0;
 }
 
 static int ad7124_setup(struct ad7124_state *st)
 {
+	struct device *dev = &st->sd.spi->dev;
 	unsigned int fclk, power_mode;
 	int i, ret;
 
 	fclk = clk_get_rate(st->mclk);
 	if (!fclk)
-		return -EINVAL;
+		return dev_err_probe(dev, -EINVAL, "Failed to get mclk rate\n");
 
 	/* The power mode changes the master clock frequency */
 	power_mode = ad7124_find_closest_match(ad7124_master_clk_freq_hz,
@@ -893,7 +992,7 @@ static int ad7124_setup(struct ad7124_state *st)
 	if (fclk != ad7124_master_clk_freq_hz[power_mode]) {
 		ret = clk_set_rate(st->mclk, fclk);
 		if (ret)
-			return ret;
+			return dev_err_probe(dev, ret, "Failed to set mclk rate\n");
 	}
 
 	/* Set the power mode */
@@ -924,7 +1023,7 @@ static int ad7124_setup(struct ad7124_state *st)
 
 	ret = ad_sd_write_reg(&st->sd, AD7124_ADC_CONTROL, 2, st->adc_control);
 	if (ret < 0)
-		return ret;
+		return dev_err_probe(dev, ret, "Failed to setup CONTROL register\n");
 
 	return ret;
 }
@@ -937,13 +1036,14 @@ static void ad7124_reg_disable(void *r)
 static int ad7124_probe(struct spi_device *spi)
 {
 	const struct ad7124_chip_info *info;
+	struct device *dev = &spi->dev;
 	struct ad7124_state *st;
 	struct iio_dev *indio_dev;
 	int i, ret;
 
 	info = spi_get_device_match_data(spi);
 	if (!info)
-		return -ENODEV;
+		return dev_err_probe(dev, -ENODEV, "Failed to get match data\n");
 
 	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st));
 	if (!indio_dev)
@@ -978,17 +1078,17 @@ static int ad7124_probe(struct spi_device *spi)
 
 		ret = regulator_enable(st->vref[i]);
 		if (ret)
-			return ret;
+			return dev_err_probe(dev, ret, "Failed to enable regulator #%d\n", i);
 
 		ret = devm_add_action_or_reset(&spi->dev, ad7124_reg_disable,
 					       st->vref[i]);
 		if (ret)
-			return ret;
+			return dev_err_probe(dev, ret, "Failed to register disable handler for regulator #%d\n", i);
 	}
 
 	st->mclk = devm_clk_get_enabled(&spi->dev, "mclk");
 	if (IS_ERR(st->mclk))
-		return PTR_ERR(st->mclk);
+		return dev_err_probe(dev, PTR_ERR(st->mclk), "Failed to get mclk\n");
 
 	ret = ad7124_soft_reset(st);
 	if (ret < 0)
@@ -1004,10 +1104,13 @@ static int ad7124_probe(struct spi_device *spi)
 
 	ret = devm_ad_sd_setup_buffer_and_trigger(&spi->dev, indio_dev);
 	if (ret < 0)
-		return ret;
+		return dev_err_probe(dev, ret, "Failed to setup triggers\n");
 
-	return devm_iio_device_register(&spi->dev, indio_dev);
+	ret = devm_iio_device_register(&spi->dev, indio_dev);
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Failed to register iio device\n");
 
+	return 0;
 }
 
 static const struct of_device_id ad7124_of_match[] = {
diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c
index 8b03c1e5567e..6c4ed10ae580 100644
--- a/drivers/iio/adc/ad7173.c
+++ b/drivers/iio/adc/ad7173.c
@@ -150,6 +150,11 @@
 #define AD7173_FILTER_ODR0_MASK		GENMASK(5, 0)
 #define AD7173_MAX_CONFIGS		8
 
+#define AD7173_MODE_CAL_INT_ZERO		0x4 /* Internal Zero-Scale Calibration */
+#define AD7173_MODE_CAL_INT_FULL		0x5 /* Internal Full-Scale Calibration */
+#define AD7173_MODE_CAL_SYS_ZERO		0x6 /* System Zero-Scale Calibration */
+#define AD7173_MODE_CAL_SYS_FULL		0x7 /* System Full-Scale Calibration */
+
 struct ad7173_device_info {
 	const unsigned int *sinc5_data_rates;
 	unsigned int num_sinc5_data_rates;
@@ -175,6 +180,7 @@ struct ad7173_device_info {
 	bool has_input_buf;
 	bool has_int_ref;
 	bool has_ref2;
+	bool has_internal_fs_calibration;
 	bool higher_gpio_bits;
 	u8 num_gpios;
 };
@@ -193,9 +199,9 @@ struct ad7173_channel_config {
 };
 
 struct ad7173_channel {
-	unsigned int chan_reg;
 	unsigned int ain;
 	struct ad7173_channel_config cfg;
+	u8 syscalib_mode;
 };
 
 struct ad7173_state {
@@ -273,6 +279,7 @@ static const struct ad7173_device_info ad4111_device_info = {
 	.has_input_buf = true,
 	.has_current_inputs = true,
 	.has_int_ref = true,
+	.has_internal_fs_calibration = true,
 	.clock = 2 * HZ_PER_MHZ,
 	.sinc5_data_rates = ad7173_sinc5_data_rates,
 	.num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates),
@@ -292,6 +299,7 @@ static const struct ad7173_device_info ad4112_device_info = {
 	.has_input_buf = true,
 	.has_current_inputs = true,
 	.has_int_ref = true,
+	.has_internal_fs_calibration = true,
 	.clock = 2 * HZ_PER_MHZ,
 	.sinc5_data_rates = ad7173_sinc5_data_rates,
 	.num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates),
@@ -327,6 +335,7 @@ static const struct ad7173_device_info ad4114_device_info = {
 	.has_temp = true,
 	.has_input_buf = true,
 	.has_int_ref = true,
+	.has_internal_fs_calibration = true,
 	.clock = 2 * HZ_PER_MHZ,
 	.sinc5_data_rates = ad7173_sinc5_data_rates,
 	.num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates),
@@ -344,6 +353,7 @@ static const struct ad7173_device_info ad4115_device_info = {
 	.has_temp = true,
 	.has_input_buf = true,
 	.has_int_ref = true,
+	.has_internal_fs_calibration = true,
 	.clock = 8 * HZ_PER_MHZ,
 	.sinc5_data_rates = ad4115_sinc5_data_rates,
 	.num_sinc5_data_rates = ARRAY_SIZE(ad4115_sinc5_data_rates),
@@ -361,6 +371,7 @@ static const struct ad7173_device_info ad4116_device_info = {
 	.has_temp = true,
 	.has_input_buf = true,
 	.has_int_ref = true,
+	.has_internal_fs_calibration = true,
 	.clock = 4 * HZ_PER_MHZ,
 	.sinc5_data_rates = ad4116_sinc5_data_rates,
 	.num_sinc5_data_rates = ARRAY_SIZE(ad4116_sinc5_data_rates),
@@ -506,6 +517,105 @@ static const struct regmap_config ad7173_regmap_config = {
 	.read_flag_mask = BIT(6),
 };
 
+enum {
+	AD7173_SYSCALIB_ZERO_SCALE,
+	AD7173_SYSCALIB_FULL_SCALE,
+};
+
+static const char * const ad7173_syscalib_modes[] = {
+	[AD7173_SYSCALIB_ZERO_SCALE] = "zero_scale",
+	[AD7173_SYSCALIB_FULL_SCALE] = "full_scale",
+};
+
+static int ad7173_set_syscalib_mode(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan,
+				    unsigned int mode)
+{
+	struct ad7173_state *st = iio_priv(indio_dev);
+
+	st->channels[chan->channel].syscalib_mode = mode;
+
+	return 0;
+}
+
+static int ad7173_get_syscalib_mode(struct iio_dev *indio_dev,
+				    const struct iio_chan_spec *chan)
+{
+	struct ad7173_state *st = iio_priv(indio_dev);
+
+	return st->channels[chan->channel].syscalib_mode;
+}
+
+static ssize_t ad7173_write_syscalib(struct iio_dev *indio_dev,
+				     uintptr_t private,
+				     const struct iio_chan_spec *chan,
+				     const char *buf, size_t len)
+{
+	struct ad7173_state *st = iio_priv(indio_dev);
+	bool sys_calib;
+	int ret, mode;
+
+	ret = kstrtobool(buf, &sys_calib);
+	if (ret)
+		return ret;
+
+	mode = st->channels[chan->channel].syscalib_mode;
+	if (sys_calib) {
+		if (mode == AD7173_SYSCALIB_ZERO_SCALE)
+			ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_SYS_ZERO,
+					      chan->address);
+		else
+			ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_SYS_FULL,
+					      chan->address);
+	}
+
+	return ret ? : len;
+}
+
+static const struct iio_enum ad7173_syscalib_mode_enum = {
+	.items = ad7173_syscalib_modes,
+	.num_items = ARRAY_SIZE(ad7173_syscalib_modes),
+	.set = ad7173_set_syscalib_mode,
+	.get = ad7173_get_syscalib_mode
+};
+
+static const struct iio_chan_spec_ext_info ad7173_calibsys_ext_info[] = {
+	{
+		.name = "sys_calibration",
+		.write = ad7173_write_syscalib,
+		.shared = IIO_SEPARATE,
+	},
+	IIO_ENUM("sys_calibration_mode", IIO_SEPARATE,
+		 &ad7173_syscalib_mode_enum),
+	IIO_ENUM_AVAILABLE("sys_calibration_mode", IIO_SHARED_BY_TYPE,
+			   &ad7173_syscalib_mode_enum),
+	{ }
+};
+
+static int ad7173_calibrate_all(struct ad7173_state *st, struct iio_dev *indio_dev)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < st->num_channels; i++) {
+		if (indio_dev->channels[i].type != IIO_VOLTAGE)
+			continue;
+
+		ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_INT_ZERO, st->channels[i].ain);
+		if (ret < 0)
+			return ret;
+
+		if (st->info->has_internal_fs_calibration) {
+			ret = ad_sd_calibrate(&st->sd, AD7173_MODE_CAL_INT_FULL,
+					      st->channels[i].ain);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int ad7173_mask_xlate(struct gpio_regmap *gpio, unsigned int base,
 			     unsigned int offset, unsigned int *reg,
 			     unsigned int *mask)
@@ -765,6 +875,7 @@ static const struct ad_sigma_delta_info ad7173_sigma_delta_info = {
 	.read_mask = BIT(6),
 	.status_ch_mask = GENMASK(3, 0),
 	.data_reg = AD7173_REG_DATA,
+	.num_resetclks = 64,
 };
 
 static int ad7173_setup(struct iio_dev *indio_dev)
@@ -802,6 +913,10 @@ static int ad7173_setup(struct iio_dev *indio_dev)
 	if (!st->config_cnts)
 		return -ENOMEM;
 
+	ret = ad7173_calibrate_all(st, indio_dev);
+	if (ret)
+		return ret;
+
 	/* All channels are enabled by default after a reset */
 	return ad7173_disable_all(&st->sd);
 }
@@ -1024,6 +1139,7 @@ static const struct iio_chan_spec ad7173_channel_template = {
 		.storagebits = 32,
 		.endianness = IIO_BE,
 	},
+	.ext_info = ad7173_calibsys_ext_info,
 };
 
 static const struct iio_chan_spec ad7173_temp_iio_channel_template = {
@@ -1317,7 +1433,6 @@ static int ad7173_fw_parse_channel_config(struct iio_dev *indio_dev)
 		chan->address = chan_index;
 		chan->scan_index = chan_index;
 		chan->channel = ain[0];
-		chan_st_priv->chan_reg = chan_index;
 		chan_st_priv->cfg.input_buf = st->info->has_input_buf;
 		chan_st_priv->cfg.odr = 0;
 
diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c
index 1c87db0e0460..e96a5ae92375 100644
--- a/drivers/iio/adc/ad7192.c
+++ b/drivers/iio/adc/ad7192.c
@@ -361,6 +361,7 @@ static const struct ad_sigma_delta_info ad7192_sigma_delta_info = {
 	.status_ch_mask = GENMASK(3, 0),
 	.num_slots = 4,
 	.irq_flags = IRQF_TRIGGER_FALLING,
+	.num_resetclks = 40,
 };
 
 static const struct ad_sigma_delta_info ad7194_sigma_delta_info = {
@@ -373,6 +374,7 @@ static const struct ad_sigma_delta_info ad7194_sigma_delta_info = {
 	.read_mask = BIT(6),
 	.status_ch_mask = GENMASK(3, 0),
 	.irq_flags = IRQF_TRIGGER_FALLING,
+	.num_resetclks = 40,
 };
 
 static const struct ad_sd_calib_data ad7192_calib_arr[8] = {
@@ -565,7 +567,7 @@ static int ad7192_setup(struct iio_dev *indio_dev, struct device *dev)
 	int i, ret, id;
 
 	/* reset the serial interface */
-	ret = ad_sd_reset(&st->sd, 48);
+	ret = ad_sd_reset(&st->sd);
 	if (ret < 0)
 		return ret;
 	usleep_range(500, 1000); /* Wait for at least 500us */
diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
index e35d55d03d86..d8e3c7a43678 100644
--- a/drivers/iio/adc/ad7606.c
+++ b/drivers/iio/adc/ad7606.c
@@ -175,17 +175,17 @@ static const struct iio_chan_spec ad7616_channels[] = {
 	AD7606_CHANNEL(15, 16),
 };
 
-static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st,
+static int ad7606c_18bit_chan_scale_setup(struct iio_dev *indio_dev,
 					  struct iio_chan_spec *chan, int ch);
-static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st,
+static int ad7606c_16bit_chan_scale_setup(struct iio_dev *indio_dev,
 					  struct iio_chan_spec *chan, int ch);
-static int ad7606_16bit_chan_scale_setup(struct ad7606_state *st,
+static int ad7606_16bit_chan_scale_setup(struct iio_dev *indio_dev,
 					 struct iio_chan_spec *chan, int ch);
-static int ad7607_chan_scale_setup(struct ad7606_state *st,
+static int ad7607_chan_scale_setup(struct iio_dev *indio_dev,
 				   struct iio_chan_spec *chan, int ch);
-static int ad7608_chan_scale_setup(struct ad7606_state *st,
+static int ad7608_chan_scale_setup(struct iio_dev *indio_dev,
 				   struct iio_chan_spec *chan, int ch);
-static int ad7609_chan_scale_setup(struct ad7606_state *st,
+static int ad7609_chan_scale_setup(struct iio_dev *indio_dev,
 				   struct iio_chan_spec *chan, int ch);
 
 const struct ad7606_chip_info ad7605_4_info = {
@@ -323,9 +323,10 @@ int ad7606_reset(struct ad7606_state *st)
 }
 EXPORT_SYMBOL_NS_GPL(ad7606_reset, "IIO_AD7606");
 
-static int ad7606_16bit_chan_scale_setup(struct ad7606_state *st,
+static int ad7606_16bit_chan_scale_setup(struct iio_dev *indio_dev,
 					 struct iio_chan_spec *chan, int ch)
 {
+	struct ad7606_state *st = iio_priv(indio_dev);
 	struct ad7606_chan_scale *cs = &st->chan_scales[ch];
 
 	if (!st->sw_mode_en) {
@@ -345,10 +346,12 @@ static int ad7606_16bit_chan_scale_setup(struct ad7606_state *st,
 	return 0;
 }
 
-static int ad7606_get_chan_config(struct ad7606_state *st, int ch,
+static int ad7606_get_chan_config(struct iio_dev *indio_dev, int ch,
 				  bool *bipolar, bool *differential)
 {
-	unsigned int num_channels = st->chip_info->num_channels - 1;
+	struct ad7606_state *st = iio_priv(indio_dev);
+	unsigned int num_channels = st->chip_info->num_adc_channels;
+	unsigned int offset = indio_dev->num_channels - st->chip_info->num_adc_channels;
 	struct device *dev = st->dev;
 	int ret;
 
@@ -364,7 +367,7 @@ static int ad7606_get_chan_config(struct ad7606_state *st, int ch,
 			continue;
 
 		/* channel number (here) is from 1 to num_channels */
-		if (reg == 0 || reg > num_channels) {
+		if (reg < offset || reg > num_channels) {
 			dev_warn(dev,
 				 "Invalid channel number (ignoring): %d\n", reg);
 			continue;
@@ -399,9 +402,10 @@ static int ad7606_get_chan_config(struct ad7606_state *st, int ch,
 	return 0;
 }
 
-static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st,
+static int ad7606c_18bit_chan_scale_setup(struct iio_dev *indio_dev,
 					  struct iio_chan_spec *chan, int ch)
 {
+	struct ad7606_state *st = iio_priv(indio_dev);
 	struct ad7606_chan_scale *cs = &st->chan_scales[ch];
 	bool bipolar, differential;
 	int ret;
@@ -413,7 +417,7 @@ static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st,
 		return 0;
 	}
 
-	ret = ad7606_get_chan_config(st, ch, &bipolar, &differential);
+	ret = ad7606_get_chan_config(indio_dev, ch, &bipolar, &differential);
 	if (ret)
 		return ret;
 
@@ -455,9 +459,10 @@ static int ad7606c_18bit_chan_scale_setup(struct ad7606_state *st,
 	return 0;
 }
 
-static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st,
+static int ad7606c_16bit_chan_scale_setup(struct iio_dev *indio_dev,
 					  struct iio_chan_spec *chan, int ch)
 {
+	struct ad7606_state *st = iio_priv(indio_dev);
 	struct ad7606_chan_scale *cs = &st->chan_scales[ch];
 	bool bipolar, differential;
 	int ret;
@@ -469,7 +474,7 @@ static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st,
 		return 0;
 	}
 
-	ret = ad7606_get_chan_config(st, ch, &bipolar, &differential);
+	ret = ad7606_get_chan_config(indio_dev, ch, &bipolar, &differential);
 	if (ret)
 		return ret;
 
@@ -512,9 +517,10 @@ static int ad7606c_16bit_chan_scale_setup(struct ad7606_state *st,
 	return 0;
 }
 
-static int ad7607_chan_scale_setup(struct ad7606_state *st,
+static int ad7607_chan_scale_setup(struct iio_dev *indio_dev,
 				   struct iio_chan_spec *chan, int ch)
 {
+	struct ad7606_state *st = iio_priv(indio_dev);
 	struct ad7606_chan_scale *cs = &st->chan_scales[ch];
 
 	cs->range = 0;
@@ -523,9 +529,10 @@ static int ad7607_chan_scale_setup(struct ad7606_state *st,
 	return 0;
 }
 
-static int ad7608_chan_scale_setup(struct ad7606_state *st,
+static int ad7608_chan_scale_setup(struct iio_dev *indio_dev,
 				   struct iio_chan_spec *chan, int ch)
 {
+	struct ad7606_state *st = iio_priv(indio_dev);
 	struct ad7606_chan_scale *cs = &st->chan_scales[ch];
 
 	cs->range = 0;
@@ -534,9 +541,10 @@ static int ad7608_chan_scale_setup(struct ad7606_state *st,
 	return 0;
 }
 
-static int ad7609_chan_scale_setup(struct ad7606_state *st,
+static int ad7609_chan_scale_setup(struct iio_dev *indio_dev,
 				   struct iio_chan_spec *chan, int ch)
 {
+	struct ad7606_state *st = iio_priv(indio_dev);
 	struct ad7606_chan_scale *cs = &st->chan_scales[ch];
 
 	cs->range = 0;
@@ -1146,8 +1154,8 @@ static int ad7606_sw_mode_setup(struct iio_dev *indio_dev)
 
 static int ad7606_chan_scales_setup(struct iio_dev *indio_dev)
 {
-	unsigned int num_channels = indio_dev->num_channels - 1;
 	struct ad7606_state *st = iio_priv(indio_dev);
+	unsigned int offset = indio_dev->num_channels - st->chip_info->num_adc_channels;
 	struct iio_chan_spec *chans;
 	size_t size;
 	int ch, ret;
@@ -1161,8 +1169,8 @@ static int ad7606_chan_scales_setup(struct iio_dev *indio_dev)
 	memcpy(chans, indio_dev->channels, size);
 	indio_dev->channels = chans;
 
-	for (ch = 0; ch < num_channels; ch++) {
-		ret = st->chip_info->scale_setup_cb(st, &chans[ch + 1], ch);
+	for (ch = 0; ch < st->chip_info->num_adc_channels; ch++) {
+		ret = st->chip_info->scale_setup_cb(indio_dev, &chans[ch + offset], ch);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/iio/adc/ad7606.h b/drivers/iio/adc/ad7606.h
index 998814a92b82..8778ffe515b3 100644
--- a/drivers/iio/adc/ad7606.h
+++ b/drivers/iio/adc/ad7606.h
@@ -69,7 +69,7 @@
 
 struct ad7606_state;
 
-typedef int (*ad7606_scale_setup_cb_t)(struct ad7606_state *st,
+typedef int (*ad7606_scale_setup_cb_t)(struct iio_dev *indio_dev,
 				       struct iio_chan_spec *chan, int ch);
 
 /**
diff --git a/drivers/iio/adc/ad7625.c b/drivers/iio/adc/ad7625.c
index aefe3bf75c91..afa9bf4ddf3c 100644
--- a/drivers/iio/adc/ad7625.c
+++ b/drivers/iio/adc/ad7625.c
@@ -477,12 +477,12 @@ static int devm_ad7625_pwm_get(struct device *dev,
 	ref_clk = devm_clk_get_enabled(dev, NULL);
 	if (IS_ERR(ref_clk))
 		return dev_err_probe(dev, PTR_ERR(ref_clk),
-				     "failed to get ref_clk");
+				     "failed to get ref_clk\n");
 
 	ref_clk_rate_hz = clk_get_rate(ref_clk);
 	if (!ref_clk_rate_hz)
 		return dev_err_probe(dev, -EINVAL,
-				     "failed to get ref_clk rate");
+				     "failed to get ref_clk rate\n");
 
 	st->ref_clk_rate_hz = ref_clk_rate_hz;
 
@@ -533,7 +533,7 @@ static int devm_ad7625_regulator_setup(struct device *dev,
 
 	if (!st->info->has_internal_vref && !st->have_refin && !ref_mv)
 		return dev_err_probe(dev, -EINVAL,
-				     "Need either REFIN or REF");
+				     "Need either REFIN or REF\n");
 
 	if (st->have_refin && ref_mv)
 		return dev_err_probe(dev, -EINVAL,
@@ -623,7 +623,7 @@ static int ad7625_probe(struct platform_device *pdev)
 	st->back = devm_iio_backend_get(dev, NULL);
 	if (IS_ERR(st->back))
 		return dev_err_probe(dev, PTR_ERR(st->back),
-				     "failed to get IIO backend");
+				     "failed to get IIO backend\n");
 
 	ret = devm_iio_backend_request_buffer(dev, st->back, indio_dev);
 	if (ret)
diff --git a/drivers/iio/adc/ad7791.c b/drivers/iio/adc/ad7791.c
index e1bf13fe2cd7..76118fe22db8 100644
--- a/drivers/iio/adc/ad7791.c
+++ b/drivers/iio/adc/ad7791.c
@@ -254,6 +254,7 @@ static const struct ad_sigma_delta_info ad7791_sigma_delta_info = {
 	.addr_shift = 4,
 	.read_mask = BIT(3),
 	.irq_flags = IRQF_TRIGGER_FALLING,
+	.num_resetclks = 32,
 };
 
 static int ad7791_read_raw(struct iio_dev *indio_dev,
diff --git a/drivers/iio/adc/ad7793.c b/drivers/iio/adc/ad7793.c
index d55c71566707..1b50d9643a63 100644
--- a/drivers/iio/adc/ad7793.c
+++ b/drivers/iio/adc/ad7793.c
@@ -206,6 +206,7 @@ static const struct ad_sigma_delta_info ad7793_sigma_delta_info = {
 	.addr_shift = 3,
 	.read_mask = BIT(6),
 	.irq_flags = IRQF_TRIGGER_FALLING,
+	.num_resetclks = 32,
 };
 
 static const struct ad_sd_calib_data ad7793_calib_arr[6] = {
@@ -265,7 +266,7 @@ static int ad7793_setup(struct iio_dev *indio_dev,
 		return ret;
 
 	/* reset the serial interface */
-	ret = ad_sd_reset(&st->sd, 32);
+	ret = ad_sd_reset(&st->sd);
 	if (ret < 0)
 		goto out;
 	usleep_range(500, 2000); /* Wait for at least 500us */
diff --git a/drivers/iio/adc/ad7944.c b/drivers/iio/adc/ad7944.c
index a5aea4e9f1a7..0ec9cda10f5f 100644
--- a/drivers/iio/adc/ad7944.c
+++ b/drivers/iio/adc/ad7944.c
@@ -75,7 +75,7 @@ struct ad7944_adc {
 			u16 u16;
 			u32 u32;
 		} raw;
-		u64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	 } sample __aligned(IIO_DMA_MINALIGN);
 };
 
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index 3fd200b34161..d5d81581ab34 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -29,8 +29,11 @@
 #define AD_SD_COMM_CHAN_MASK	0x3
 
 #define AD_SD_REG_COMM		0x00
+#define AD_SD_REG_STATUS	0x00
 #define AD_SD_REG_DATA		0x03
 
+#define AD_SD_REG_STATUS_RDY	0x80
+
 /**
  * ad_sd_set_comm() - Set communications register
  *
@@ -109,7 +112,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta,
 		}, {
 			.rx_buf = val,
 			.len = size,
-			.cs_change = sigma_delta->bus_locked,
+			.cs_change = sigma_delta->keep_cs_asserted,
 		},
 	};
 	struct spi_message m;
@@ -178,13 +181,12 @@ EXPORT_SYMBOL_NS_GPL(ad_sd_read_reg, "IIO_AD_SIGMA_DELTA");
  * ad_sd_reset() - Reset the serial interface
  *
  * @sigma_delta: The sigma delta device
- * @reset_length: Number of SCLKs with DIN = 1
  *
  * Returns 0 on success, an error code otherwise.
  **/
-int ad_sd_reset(struct ad_sigma_delta *sigma_delta,
-	unsigned int reset_length)
+int ad_sd_reset(struct ad_sigma_delta *sigma_delta)
 {
+	unsigned int reset_length = sigma_delta->info->num_resetclks;
 	uint8_t *buf;
 	unsigned int size;
 	int ret;
@@ -202,6 +204,107 @@ int ad_sd_reset(struct ad_sigma_delta *sigma_delta,
 }
 EXPORT_SYMBOL_NS_GPL(ad_sd_reset, "IIO_AD_SIGMA_DELTA");
 
+static bool ad_sd_disable_irq(struct ad_sigma_delta *sigma_delta)
+{
+	guard(spinlock_irqsave)(&sigma_delta->irq_lock);
+
+	/* It's already off, return false to indicate nothing was changed */
+	if (sigma_delta->irq_dis)
+		return false;
+
+	sigma_delta->irq_dis = true;
+	disable_irq_nosync(sigma_delta->irq_line);
+	return true;
+}
+
+static void ad_sd_enable_irq(struct ad_sigma_delta *sigma_delta)
+{
+	guard(spinlock_irqsave)(&sigma_delta->irq_lock);
+
+	sigma_delta->irq_dis = false;
+	enable_irq(sigma_delta->irq_line);
+}
+
+#define AD_SD_CLEAR_DATA_BUFLEN 9
+
+/* Called with `sigma_delta->bus_locked == true` only. */
+static int ad_sigma_delta_clear_pending_event(struct ad_sigma_delta *sigma_delta)
+{
+	bool pending_event;
+	unsigned int data_read_len = BITS_TO_BYTES(sigma_delta->info->num_resetclks);
+	u8 *data;
+	struct spi_transfer t[] = {
+		{
+			.len = 1,
+		}, {
+			.len = data_read_len,
+		}
+	};
+	struct spi_message m;
+	int ret;
+
+	/*
+	 * Read R̅D̅Y̅ pin (if possible) or status register to check if there is an
+	 * old event.
+	 */
+	if (sigma_delta->rdy_gpiod) {
+		pending_event = gpiod_get_value(sigma_delta->rdy_gpiod);
+	} else {
+		unsigned int status_reg;
+
+		ret = ad_sd_read_reg(sigma_delta, AD_SD_REG_STATUS, 1, &status_reg);
+		if (ret)
+			return ret;
+
+		pending_event = !(status_reg & AD_SD_REG_STATUS_RDY);
+	}
+
+	if (!pending_event)
+		return 0;
+
+	/*
+	 * In general the size of the data register is unknown. It varies from
+	 * device to device, might be one byte longer if CONTROL.DATA_STATUS is
+	 * set and even varies on some devices depending on which input is
+	 * selected. So send one byte to start reading the data register and
+	 * then just clock for some bytes with DIN (aka MOSI) high to not
+	 * confuse the register access state machine after the data register was
+	 * completely read. Note however that the sequence length must be
+	 * shorter than the reset procedure.
+	 */
+
+	data = kzalloc(data_read_len + 1, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	spi_message_init(&m);
+	if (sigma_delta->info->has_registers) {
+		unsigned int data_reg = sigma_delta->info->data_reg ?: AD_SD_REG_DATA;
+
+		data[0] = data_reg << sigma_delta->info->addr_shift;
+		data[0] |= sigma_delta->info->read_mask;
+		data[0] |= sigma_delta->comm;
+		t[0].tx_buf = data;
+		spi_message_add_tail(&t[0], &m);
+	}
+
+	/*
+	 * The first transferred byte is part of the real data register,
+	 * so this doesn't need to be 0xff. In the remaining
+	 * `data_read_len - 1` bytes are less than $num_resetclks ones.
+	 */
+	t[1].tx_buf = data + 1;
+	data[1] = 0x00;
+	memset(data + 2, 0xff, data_read_len - 1);
+	spi_message_add_tail(&t[1], &m);
+
+	ret = spi_sync_locked(sigma_delta->spi, &m);
+
+	kfree(data);
+
+	return ret;
+}
+
 int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta,
 	unsigned int mode, unsigned int channel)
 {
@@ -217,16 +320,18 @@ int ad_sd_calibrate(struct ad_sigma_delta *sigma_delta,
 	sigma_delta->keep_cs_asserted = true;
 	reinit_completion(&sigma_delta->completion);
 
+	ret = ad_sigma_delta_clear_pending_event(sigma_delta);
+	if (ret)
+		goto out;
+
 	ret = ad_sigma_delta_set_mode(sigma_delta, mode);
 	if (ret < 0)
 		goto out;
 
-	sigma_delta->irq_dis = false;
-	enable_irq(sigma_delta->irq_line);
+	ad_sd_enable_irq(sigma_delta);
 	time_left = wait_for_completion_timeout(&sigma_delta->completion, 2 * HZ);
 	if (time_left == 0) {
-		sigma_delta->irq_dis = true;
-		disable_irq_nosync(sigma_delta->irq_line);
+		ad_sd_disable_irq(sigma_delta);
 		ret = -EIO;
 	} else {
 		ret = 0;
@@ -292,10 +397,13 @@ int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev,
 	sigma_delta->keep_cs_asserted = true;
 	reinit_completion(&sigma_delta->completion);
 
+	ret = ad_sigma_delta_clear_pending_event(sigma_delta);
+	if (ret)
+		goto out_unlock;
+
 	ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_SINGLE);
 
-	sigma_delta->irq_dis = false;
-	enable_irq(sigma_delta->irq_line);
+	ad_sd_enable_irq(sigma_delta);
 	ret = wait_for_completion_interruptible_timeout(
 			&sigma_delta->completion, HZ);
 
@@ -314,14 +422,13 @@ int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev,
 		&raw_sample);
 
 out:
-	if (!sigma_delta->irq_dis) {
-		disable_irq_nosync(sigma_delta->irq_line);
-		sigma_delta->irq_dis = true;
-	}
+	ad_sd_disable_irq(sigma_delta);
 
-	sigma_delta->keep_cs_asserted = false;
 	ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE);
 	ad_sigma_delta_disable_one(sigma_delta, chan->address);
+
+out_unlock:
+	sigma_delta->keep_cs_asserted = false;
 	sigma_delta->bus_locked = false;
 	spi_bus_unlock(sigma_delta->spi->controller);
 	iio_device_release_direct_mode(indio_dev);
@@ -392,12 +499,15 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	sigma_delta->bus_locked = true;
 	sigma_delta->keep_cs_asserted = true;
 
+	ret = ad_sigma_delta_clear_pending_event(sigma_delta);
+	if (ret)
+		goto err_unlock;
+
 	ret = ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_CONTINUOUS);
 	if (ret)
 		goto err_unlock;
 
-	sigma_delta->irq_dis = false;
-	enable_irq(sigma_delta->irq_line);
+	ad_sd_enable_irq(sigma_delta);
 
 	return 0;
 
@@ -414,10 +524,7 @@ static int ad_sd_buffer_postdisable(struct iio_dev *indio_dev)
 	reinit_completion(&sigma_delta->completion);
 	wait_for_completion_timeout(&sigma_delta->completion, HZ);
 
-	if (!sigma_delta->irq_dis) {
-		disable_irq_nosync(sigma_delta->irq_line);
-		sigma_delta->irq_dis = true;
-	}
+	ad_sd_disable_irq(sigma_delta);
 
 	sigma_delta->keep_cs_asserted = false;
 	ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE);
@@ -516,8 +623,7 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 
 irq_handled:
 	iio_trigger_notify_done(indio_dev->trig);
-	sigma_delta->irq_dis = false;
-	enable_irq(sigma_delta->irq_line);
+	ad_sd_enable_irq(sigma_delta);
 
 	return IRQ_HANDLED;
 }
@@ -539,12 +645,31 @@ static irqreturn_t ad_sd_data_rdy_trig_poll(int irq, void *private)
 {
 	struct ad_sigma_delta *sigma_delta = private;
 
-	complete(&sigma_delta->completion);
-	disable_irq_nosync(irq);
-	sigma_delta->irq_dis = true;
-	iio_trigger_poll(sigma_delta->trig);
+	/*
+	 * AD7124 and a few others use the same physical line for interrupt
+	 * reporting (R̅D̅Y̅) and MISO.
+	 * As MISO toggles when reading a register, this likely results in a
+	 * pending interrupt. This has two consequences: a) The irq might
+	 * trigger immediately after it's enabled even though the conversion
+	 * isn't done yet; and b) checking the STATUS register's R̅D̅Y̅ flag is
+	 * off-limits as reading that would trigger another irq event.
+	 *
+	 * So read the MOSI line as GPIO (if available) and only trigger the irq
+	 * if the line is active. Without such a GPIO assume this is a valid
+	 * interrupt.
+	 *
+	 * Also as disable_irq_nosync() is used to disable the irq, only act if
+	 * the irq wasn't disabled before.
+	 */
+	if ((!sigma_delta->rdy_gpiod || gpiod_get_value(sigma_delta->rdy_gpiod)) &&
+	    ad_sd_disable_irq(sigma_delta)) {
+		complete(&sigma_delta->completion);
+		iio_trigger_poll(sigma_delta->trig);
 
-	return IRQ_HANDLED;
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
 }
 
 /**
@@ -674,11 +799,24 @@ int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev,
 		}
 	}
 
+	spin_lock_init(&sigma_delta->irq_lock);
+
 	if (info->irq_line)
 		sigma_delta->irq_line = info->irq_line;
 	else
 		sigma_delta->irq_line = spi->irq;
 
+	sigma_delta->rdy_gpiod = devm_gpiod_get_optional(&spi->dev, "rdy", GPIOD_IN);
+	if (IS_ERR(sigma_delta->rdy_gpiod))
+		return dev_err_probe(&spi->dev, PTR_ERR(sigma_delta->rdy_gpiod),
+				     "Failed to find rdy gpio\n");
+
+	if (sigma_delta->rdy_gpiod && !sigma_delta->irq_line) {
+		sigma_delta->irq_line = gpiod_to_irq(sigma_delta->rdy_gpiod);
+		if (sigma_delta->irq_line < 0)
+			return sigma_delta->irq_line;
+	}
+
 	iio_device_set_drvdata(indio_dev, sigma_delta);
 
 	return 0;
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index 30328626d9be..221a5fdc1eaa 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -66,8 +66,6 @@ struct dln2_adc {
 	/* Demux table */
 	unsigned int demux_count;
 	struct dln2_adc_demux_table demux[DLN2_ADC_MAX_CHANNELS];
-	/* Precomputed timestamp padding offset and length */
-	unsigned int ts_pad_offset, ts_pad_length;
 };
 
 struct dln2_adc_port_chan {
@@ -111,8 +109,6 @@ static void dln2_adc_update_demux(struct dln2_adc *dln2)
 	if (iio_get_masklength(indio_dev) &&
 	    (*indio_dev->active_scan_mask & 0xff) == 0xff) {
 		dln2_adc_add_demux(dln2, 0, 0, 16);
-		dln2->ts_pad_offset = 0;
-		dln2->ts_pad_length = 0;
 		return;
 	}
 
@@ -127,16 +123,6 @@ static void dln2_adc_update_demux(struct dln2_adc *dln2)
 		out_loc += 2;
 		in_loc += 2;
 	}
-
-	if (indio_dev->scan_timestamp) {
-		size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1;
-
-		dln2->ts_pad_offset = out_loc;
-		dln2->ts_pad_length = ts_offset * sizeof(int64_t) - out_loc;
-	} else {
-		dln2->ts_pad_offset = 0;
-		dln2->ts_pad_length = 0;
-	}
 }
 
 static int dln2_adc_get_chan_count(struct dln2_adc *dln2)
@@ -494,6 +480,8 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p)
 	if (ret < 0)
 		goto done;
 
+	memset(&data, 0, sizeof(data));
+
 	/* Demux operation */
 	for (i = 0; i < dln2->demux_count; ++i) {
 		t = &dln2->demux[i];
@@ -501,11 +489,6 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p)
 		       (void *)dev_data.values + t->from, t->length);
 	}
 
-	/* Zero padding space between values and timestamp */
-	if (dln2->ts_pad_length)
-		memset((void *)data.values + dln2->ts_pad_offset,
-		       0, dln2->ts_pad_length);
-
 	iio_push_to_buffers_with_timestamp(indio_dev, &data,
 					   iio_get_time_ns(indio_dev));
 
diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c
index 48c95e12e791..40d14faa71c5 100644
--- a/drivers/iio/adc/ina2xx-adc.c
+++ b/drivers/iio/adc/ina2xx-adc.c
@@ -150,7 +150,7 @@ struct ina2xx_chip_info {
 	/* data buffer needs space for channel data and timestamp */
 	struct {
 		u16 chan[4];
-		u64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/adc/max1118.c b/drivers/iio/adc/max1118.c
index 3d0a7d0eb7ee..565ca2e21c0c 100644
--- a/drivers/iio/adc/max1118.c
+++ b/drivers/iio/adc/max1118.c
@@ -39,7 +39,7 @@ struct max1118 {
 	/* Ensure natural alignment of buffer elements */
 	struct {
 		u8 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 
 	u8 data __aligned(IIO_DMA_MINALIGN);
diff --git a/drivers/iio/adc/max11410.c b/drivers/iio/adc/max11410.c
index f0dc4b460903..76abafd47404 100644
--- a/drivers/iio/adc/max11410.c
+++ b/drivers/iio/adc/max11410.c
@@ -143,7 +143,7 @@ struct max11410_state {
 	int irq;
 	struct {
 		u32 data __aligned(IIO_DMA_MINALIGN);
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index 9a0baea08ab6..e8d731bc34e0 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -161,6 +161,7 @@ struct max1363_chip_info {
  * @vref_uv:		Actual (external or internal) reference voltage
  * @send:		function used to send data to the chip
  * @recv:		function used to receive data from the chip
+ * @data:		buffer to store channel data and timestamp
  */
 struct max1363_state {
 	struct i2c_client		*client;
@@ -186,6 +187,10 @@ struct max1363_state {
 						const char *buf, int count);
 	int				(*recv)(const struct i2c_client *client,
 						char *buf, int count);
+	struct {
+		u8 buf[MAX1363_MAX_CHANNELS * 2];
+		aligned_s64 ts;
+	} data;
 };
 
 #define MAX1363_MODE_SINGLE(_num, _mask) {				\
@@ -1462,22 +1467,10 @@ static irqreturn_t max1363_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct max1363_state *st = iio_priv(indio_dev);
-	__u8 *rxbuf;
 	int b_sent;
-	size_t d_size;
 	unsigned long numvals = bitmap_weight(st->current_mode->modemask,
 					      MAX1363_MAX_CHANNELS);
 
-	/* Ensure the timestamp is 8 byte aligned */
-	if (st->chip_info->bits != 8)
-		d_size = numvals*2;
-	else
-		d_size = numvals;
-	if (indio_dev->scan_timestamp) {
-		d_size += sizeof(s64);
-		if (d_size % sizeof(s64))
-			d_size += sizeof(s64) - (d_size % sizeof(s64));
-	}
 	/* Monitor mode prevents reading. Whilst not currently implemented
 	 * might as well have this test in here in the meantime as it does
 	 * no harm.
@@ -1485,21 +1478,16 @@ static irqreturn_t max1363_trigger_handler(int irq, void *p)
 	if (numvals == 0)
 		goto done;
 
-	rxbuf = kmalloc(d_size,	GFP_KERNEL);
-	if (rxbuf == NULL)
-		goto done;
 	if (st->chip_info->bits != 8)
-		b_sent = st->recv(st->client, rxbuf, numvals * 2);
+		b_sent = st->recv(st->client, st->data.buf, numvals * 2);
 	else
-		b_sent = st->recv(st->client, rxbuf, numvals);
+		b_sent = st->recv(st->client, st->data.buf, numvals);
 	if (b_sent < 0)
-		goto done_free;
+		goto done;
 
-	iio_push_to_buffers_with_timestamp(indio_dev, rxbuf,
+	iio_push_to_buffers_with_timestamp(indio_dev, &st->data,
 					   iio_get_time_ns(indio_dev));
 
-done_free:
-	kfree(rxbuf);
 done:
 	iio_trigger_notify_done(indio_dev->trig);
 
diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index b097f04172c8..6748b44d568d 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -122,7 +122,7 @@ struct mcp3911 {
 	const struct mcp3911_chip_info *chip;
 	struct {
 		u32 channels[MCP39XX_MAX_NUM_CHANNELS];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 
 	u8 tx_buf __aligned(IIO_DMA_MINALIGN);
diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c
index 2d475b43e717..997def4a4d2f 100644
--- a/drivers/iio/adc/meson_saradc.c
+++ b/drivers/iio/adc/meson_saradc.c
@@ -155,10 +155,10 @@
  */
 #define MESON_SAR_ADC_REG11					0x2c
 	#define MESON_SAR_ADC_REG11_BANDGAP_EN			BIT(13)
-	#define MESON_SAR_ADC_REG11_CMV_SEL                     BIT(6)
-	#define MESON_SAR_ADC_REG11_VREF_VOLTAGE                BIT(5)
-	#define MESON_SAR_ADC_REG11_EOC                         BIT(1)
-	#define MESON_SAR_ADC_REG11_VREF_SEL                    BIT(0)
+	#define MESON_SAR_ADC_REG11_CMV_SEL			BIT(6)
+	#define MESON_SAR_ADC_REG11_VREF_VOLTAGE		BIT(5)
+	#define MESON_SAR_ADC_REG11_EOC				BIT(1)
+	#define MESON_SAR_ADC_REG11_VREF_SEL			BIT(0)
 
 #define MESON_SAR_ADC_REG13					0x34
 	#define MESON_SAR_ADC_REG13_12BIT_CALIBRATION_MASK	GENMASK(13, 8)
@@ -315,19 +315,17 @@ static const struct iio_chan_spec meson_sar_adc_and_temp_iio_channels[] = {
 struct meson_sar_adc_param {
 	bool					has_bl30_integration;
 	unsigned long				clock_rate;
-	u32					bandgap_reg;
 	unsigned int				resolution;
 	const struct regmap_config		*regmap_config;
 	u8					temperature_trimming_bits;
 	unsigned int				temperature_multiplier;
 	unsigned int				temperature_divider;
 	u8					disable_ring_counter;
-	bool					has_reg11;
 	bool					has_vref_select;
 	u8					vref_select;
 	u8					cmv_select;
 	u8					adc_eoc;
-	enum meson_sar_adc_vref_sel		vref_volatge;
+	enum meson_sar_adc_vref_sel		vref_voltage;
 };
 
 struct meson_sar_adc_data {
@@ -976,7 +974,7 @@ static int meson_sar_adc_init(struct iio_dev *indio_dev)
 			   MESON_SAR_ADC_REG3_CTRL_CONT_RING_COUNTER_EN,
 			   regval);
 
-	if (priv->param->has_reg11) {
+	if (priv->param->regmap_config->max_register >= MESON_SAR_ADC_REG11) {
 		regval = FIELD_PREP(MESON_SAR_ADC_REG11_EOC, priv->param->adc_eoc);
 		regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG11,
 				   MESON_SAR_ADC_REG11_EOC, regval);
@@ -989,7 +987,7 @@ static int meson_sar_adc_init(struct iio_dev *indio_dev)
 		}
 
 		regval = FIELD_PREP(MESON_SAR_ADC_REG11_VREF_VOLTAGE,
-				    priv->param->vref_volatge);
+				    priv->param->vref_voltage);
 		regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG11,
 				   MESON_SAR_ADC_REG11_VREF_VOLTAGE, regval);
 
@@ -1013,16 +1011,15 @@ static int meson_sar_adc_init(struct iio_dev *indio_dev)
 static void meson_sar_adc_set_bandgap(struct iio_dev *indio_dev, bool on_off)
 {
 	struct meson_sar_adc_priv *priv = iio_priv(indio_dev);
-	const struct meson_sar_adc_param *param = priv->param;
-	u32 enable_mask;
 
-	if (param->bandgap_reg == MESON_SAR_ADC_REG11)
-		enable_mask = MESON_SAR_ADC_REG11_BANDGAP_EN;
+	if (priv->param->regmap_config->max_register >= MESON_SAR_ADC_REG11)
+		regmap_update_bits(priv->regmap, MESON_SAR_ADC_REG11,
+				   MESON_SAR_ADC_REG11_BANDGAP_EN,
+				   on_off ? MESON_SAR_ADC_REG11_BANDGAP_EN : 0);
 	else
-		enable_mask = MESON_SAR_ADC_DELTA_10_TS_VBG_EN;
-
-	regmap_update_bits(priv->regmap, param->bandgap_reg, enable_mask,
-			   on_off ? enable_mask : 0);
+		regmap_update_bits(priv->regmap, MESON_SAR_ADC_DELTA_10,
+				   MESON_SAR_ADC_DELTA_10_TS_VBG_EN,
+				   on_off ? MESON_SAR_ADC_DELTA_10_TS_VBG_EN : 0);
 }
 
 static int meson_sar_adc_hw_enable(struct iio_dev *indio_dev)
@@ -1186,7 +1183,6 @@ static const struct iio_info meson_sar_adc_iio_info = {
 static const struct meson_sar_adc_param meson_sar_adc_meson8_param = {
 	.has_bl30_integration = false,
 	.clock_rate = 1150000,
-	.bandgap_reg = MESON_SAR_ADC_DELTA_10,
 	.regmap_config = &meson_sar_adc_regmap_config_meson8,
 	.resolution = 10,
 	.temperature_trimming_bits = 4,
@@ -1197,7 +1193,6 @@ static const struct meson_sar_adc_param meson_sar_adc_meson8_param = {
 static const struct meson_sar_adc_param meson_sar_adc_meson8b_param = {
 	.has_bl30_integration = false,
 	.clock_rate = 1150000,
-	.bandgap_reg = MESON_SAR_ADC_DELTA_10,
 	.regmap_config = &meson_sar_adc_regmap_config_meson8,
 	.resolution = 10,
 	.temperature_trimming_bits = 5,
@@ -1208,35 +1203,29 @@ static const struct meson_sar_adc_param meson_sar_adc_meson8b_param = {
 static const struct meson_sar_adc_param meson_sar_adc_gxbb_param = {
 	.has_bl30_integration = true,
 	.clock_rate = 1200000,
-	.bandgap_reg = MESON_SAR_ADC_REG11,
 	.regmap_config = &meson_sar_adc_regmap_config_gxbb,
 	.resolution = 10,
-	.has_reg11 = true,
-	.vref_volatge = 1,
+	.vref_voltage = 1,
 	.cmv_select = 1,
 };
 
 static const struct meson_sar_adc_param meson_sar_adc_gxl_param = {
 	.has_bl30_integration = true,
 	.clock_rate = 1200000,
-	.bandgap_reg = MESON_SAR_ADC_REG11,
 	.regmap_config = &meson_sar_adc_regmap_config_gxbb,
 	.resolution = 12,
 	.disable_ring_counter = 1,
-	.has_reg11 = true,
-	.vref_volatge = 1,
+	.vref_voltage = 1,
 	.cmv_select = 1,
 };
 
 static const struct meson_sar_adc_param meson_sar_adc_axg_param = {
 	.has_bl30_integration = true,
 	.clock_rate = 1200000,
-	.bandgap_reg = MESON_SAR_ADC_REG11,
 	.regmap_config = &meson_sar_adc_regmap_config_gxbb,
 	.resolution = 12,
 	.disable_ring_counter = 1,
-	.has_reg11 = true,
-	.vref_volatge = 1,
+	.vref_voltage = 1,
 	.has_vref_select = true,
 	.vref_select = VREF_VDDA,
 	.cmv_select = 1,
@@ -1245,11 +1234,9 @@ static const struct meson_sar_adc_param meson_sar_adc_axg_param = {
 static const struct meson_sar_adc_param meson_sar_adc_g12a_param = {
 	.has_bl30_integration = false,
 	.clock_rate = 1200000,
-	.bandgap_reg = MESON_SAR_ADC_REG11,
 	.regmap_config = &meson_sar_adc_regmap_config_gxbb,
 	.resolution = 12,
 	.disable_ring_counter = 1,
-	.has_reg11 = true,
 	.adc_eoc = 1,
 	.has_vref_select = true,
 	.vref_select = VREF_VDDA,
diff --git a/drivers/iio/adc/pac1921.c b/drivers/iio/adc/pac1921.c
index b0f6727cfe38..90f61c47b1c4 100644
--- a/drivers/iio/adc/pac1921.c
+++ b/drivers/iio/adc/pac1921.c
@@ -12,6 +12,7 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/triggered_buffer.h>
+#include <linux/limits.h>
 #include <linux/regmap.h>
 #include <linux/units.h>
 
@@ -67,6 +68,14 @@ enum pac1921_mxsl {
 #define PAC1921_DEFAULT_DI_GAIN		0 /* 2^(value): 1x gain (HW default) */
 #define PAC1921_DEFAULT_NUM_SAMPLES	0 /* 2^(value): 1 sample (HW default) */
 
+#define PAC1921_ACPI_GET_uOHMS_VALS             0
+#define PAC1921_ACPI_GET_LABEL			1
+
+/* f7bb9932-86ee-4516-a236-7a7a742e55cb */
+static const guid_t pac1921_guid =
+			GUID_INIT(0xf7bb9932, 0x86ee, 0x4516, 0xa2,
+				  0x36, 0x7a, 0x7a, 0x74, 0x2e, 0x55, 0xcb);
+
 /*
  * Pre-computed scale factors for BUS voltage
  * format: IIO_VAL_INT_PLUS_NANO
@@ -200,7 +209,7 @@ struct pac1921_priv {
 
 	struct {
 		u16 chan[PAC1921_NUM_MEAS_CHANS];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
@@ -782,7 +791,7 @@ static ssize_t pac1921_write_shunt_resistor(struct iio_dev *indio_dev,
 					    const char *buf, size_t len)
 {
 	struct pac1921_priv *priv = iio_priv(indio_dev);
-	u64 rshunt_uohm;
+	u32 rshunt_uohm;
 	int val, val_fract;
 	int ret;
 
@@ -793,10 +802,17 @@ static ssize_t pac1921_write_shunt_resistor(struct iio_dev *indio_dev,
 	if (ret)
 		return ret;
 
-	rshunt_uohm = val * MICRO + val_fract;
-	if (rshunt_uohm == 0 || rshunt_uohm > INT_MAX)
+	/*
+	 * This check validates the shunt is not zero and does not surpass
+	 * INT_MAX. The check is done before calculating in order to avoid
+	 * val * MICRO overflowing.
+	 */
+	if ((!val && !val_fract) || val > INT_MAX / MICRO ||
+	    (val == INT_MAX / MICRO && val_fract > INT_MAX % MICRO))
 		return -EINVAL;
 
+	rshunt_uohm = val * MICRO + val_fract;
+
 	guard(mutex)(&priv->lock);
 
 	priv->rshunt_uohm = rshunt_uohm;
@@ -1151,6 +1167,61 @@ static void pac1921_regulator_disable(void *data)
 	regulator_disable(regulator);
 }
 
+/*
+ * Documentation related to the ACPI device definition
+ * https://ww1.microchip.com/downloads/aemDocuments/documents/OTH/ApplicationNotes/ApplicationNotes/PAC193X-Integration-Notes-for-Microsoft-Windows-10-and-Windows-11-Driver-Support-DS00002534.pdf
+ */
+static int pac1921_match_acpi_device(struct iio_dev *indio_dev)
+{
+	acpi_handle handle;
+	union acpi_object *status;
+	char *label;
+	struct pac1921_priv *priv = iio_priv(indio_dev);
+	struct device *dev = &priv->client->dev;
+
+	handle = ACPI_HANDLE(dev);
+
+	status = acpi_evaluate_dsm(handle, &pac1921_guid, 1,
+				   PAC1921_ACPI_GET_uOHMS_VALS, NULL);
+	if (!status)
+		return dev_err_probe(dev, -EINVAL,
+				     "Could not read shunt from ACPI table\n");
+
+	priv->rshunt_uohm = status->package.elements[0].integer.value;
+	ACPI_FREE(status);
+
+	status = acpi_evaluate_dsm(handle, &pac1921_guid, 1,
+				   PAC1921_ACPI_GET_LABEL, NULL);
+	if (!status)
+		return dev_err_probe(dev, -EINVAL,
+				     "Could not read label from ACPI table\n");
+
+	label = devm_kstrdup(dev, status->package.elements[0].string.pointer,
+			     GFP_KERNEL);
+	if (!label)
+		return -ENOMEM;
+
+	indio_dev->label = label;
+	ACPI_FREE(status);
+
+	return 0;
+}
+
+static int pac1921_parse_of_fw(struct iio_dev *indio_dev)
+{
+	int ret;
+	struct pac1921_priv *priv = iio_priv(indio_dev);
+	struct device *dev = &priv->client->dev;
+
+	ret = device_property_read_u32(dev, "shunt-resistor-micro-ohms",
+				       &priv->rshunt_uohm);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "Cannot read shunt resistor property\n");
+
+	return 0;
+}
+
 static int pac1921_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
@@ -1179,11 +1250,14 @@ static int pac1921_probe(struct i2c_client *client)
 	priv->di_gain = PAC1921_DEFAULT_DI_GAIN;
 	priv->n_samples = PAC1921_DEFAULT_NUM_SAMPLES;
 
-	ret = device_property_read_u32(dev, "shunt-resistor-micro-ohms",
-				       &priv->rshunt_uohm);
+	if (is_acpi_device_node(dev->fwnode))
+		ret = pac1921_match_acpi_device(indio_dev);
+	else
+		ret = pac1921_parse_of_fw(indio_dev);
 	if (ret)
 		return dev_err_probe(dev, ret,
-				     "Cannot read shunt resistor property\n");
+				     "Parameter parsing error\n");
+
 	if (priv->rshunt_uohm == 0 || priv->rshunt_uohm > INT_MAX)
 		return dev_err_probe(dev, -EINVAL,
 				     "Invalid shunt resistor: %u\n",
@@ -1246,11 +1320,18 @@ static const struct of_device_id pac1921_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, pac1921_of_match);
 
+static const struct acpi_device_id pac1921_acpi_match[] = {
+	{ "MCHP1921" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, pac1921_acpi_match);
+
 static struct i2c_driver pac1921_driver = {
 	.driver	 = {
 		.name = "pac1921",
 		.pm = pm_sleep_ptr(&pac1921_pm_ops),
 		.of_match_table = pac1921_of_match,
+		.acpi_match_table = pac1921_acpi_match,
 	},
 	.probe = pac1921_probe,
 	.id_table = pac1921_id,
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index dfd47a6e1f4a..a29e54754c8f 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -363,7 +363,7 @@ static irqreturn_t rockchip_saradc_trigger_handler(int irq, void *p)
 	 */
 	struct {
 		u16 values[SARADC_MAX_CHANNELS];
-		int64_t timestamp;
+		aligned_s64 timestamp;
 	} data;
 	int ret;
 	int i, j = 0;
diff --git a/drivers/iio/adc/rtq6056.c b/drivers/iio/adc/rtq6056.c
index 56ed948a8ae1..337bc8b31b2c 100644
--- a/drivers/iio/adc/rtq6056.c
+++ b/drivers/iio/adc/rtq6056.c
@@ -634,7 +634,7 @@ static irqreturn_t rtq6056_buffer_trigger_handler(int irq, void *p)
 	struct device *dev = priv->dev;
 	struct {
 		u16 vals[RTQ6056_MAX_CHANNEL];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} data;
 	unsigned int raw;
 	int i = 0, bit, ret;
diff --git a/drivers/iio/adc/rzg2l_adc.c b/drivers/iio/adc/rzg2l_adc.c
index cd3a7e46ea53..883c167c0670 100644
--- a/drivers/iio/adc/rzg2l_adc.c
+++ b/drivers/iio/adc/rzg2l_adc.c
@@ -8,12 +8,13 @@
  */
 
 #include <linux/bitfield.h>
-#include <linux/clk.h>
+#include <linux/cleanup.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/iio/iio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -32,20 +33,15 @@
 #define RZG2L_ADM1_MS			BIT(2)
 #define RZG2L_ADM1_BS			BIT(4)
 #define RZG2L_ADM1_EGA_MASK		GENMASK(13, 12)
-#define RZG2L_ADM2_CHSEL_MASK		GENMASK(7, 0)
 #define RZG2L_ADM3_ADIL_MASK		GENMASK(31, 24)
 #define RZG2L_ADM3_ADCMP_MASK		GENMASK(23, 16)
-#define RZG2L_ADM3_ADCMP_E		FIELD_PREP(RZG2L_ADM3_ADCMP_MASK, 0xe)
-#define RZG2L_ADM3_ADSMP_MASK		GENMASK(15, 0)
 
 #define RZG2L_ADINT			0x20
-#define RZG2L_ADINT_INTEN_MASK		GENMASK(7, 0)
 #define RZG2L_ADINT_CSEEN		BIT(16)
 #define RZG2L_ADINT_INTS		BIT(31)
 
 #define RZG2L_ADSTS			0x24
 #define RZG2L_ADSTS_CSEST		BIT(16)
-#define RZG2L_ADSTS_INTST_MASK		GENMASK(7, 0)
 
 #define RZG2L_ADIVC			0x28
 #define RZG2L_ADIVC_DIVADC_MASK		GENMASK(8, 0)
@@ -56,12 +52,28 @@
 #define RZG2L_ADCR(n)			(0x30 + ((n) * 0x4))
 #define RZG2L_ADCR_AD_MASK		GENMASK(11, 0)
 
-#define RZG2L_ADSMP_DEFAULT_SAMPLING	0x578
-
-#define RZG2L_ADC_MAX_CHANNELS		8
-#define RZG2L_ADC_CHN_MASK		0x7
+#define RZG2L_ADC_MAX_CHANNELS		9
 #define RZG2L_ADC_TIMEOUT		usecs_to_jiffies(1 * 4)
 
+/**
+ * struct rzg2l_adc_hw_params - ADC hardware specific parameters
+ * @default_adsmp: default ADC sampling period (see ADM3 register); index 0 is
+ * used for voltage channels, index 1 is used for temperature channel
+ * @adsmp_mask: ADC sampling period mask (see ADM3 register)
+ * @adint_inten_mask: conversion end interrupt mask (see ADINT register)
+ * @default_adcmp: default ADC cmp (see ADM3 register)
+ * @num_channels: number of supported channels
+ * @adivc: specifies if ADVIC register is available
+ */
+struct rzg2l_adc_hw_params {
+	u16 default_adsmp[2];
+	u16 adsmp_mask;
+	u16 adint_inten_mask;
+	u8 default_adcmp;
+	u8 num_channels;
+	bool adivc;
+};
+
 struct rzg2l_adc_data {
 	const struct iio_chan_spec *channels;
 	u8 num_channels;
@@ -69,25 +81,36 @@ struct rzg2l_adc_data {
 
 struct rzg2l_adc {
 	void __iomem *base;
-	struct clk *pclk;
-	struct clk *adclk;
 	struct reset_control *presetn;
 	struct reset_control *adrstn;
-	struct completion completion;
 	const struct rzg2l_adc_data *data;
+	const struct rzg2l_adc_hw_params *hw_params;
+	struct completion completion;
 	struct mutex lock;
 	u16 last_val[RZG2L_ADC_MAX_CHANNELS];
+	bool was_rpm_active;
+};
+
+/**
+ * struct rzg2l_adc_channel - ADC channel descriptor
+ * @name: ADC channel name
+ * @type: ADC channel type
+ */
+struct rzg2l_adc_channel {
+	const char * const name;
+	enum iio_chan_type type;
 };
 
-static const char * const rzg2l_adc_channel_name[] = {
-	"adc0",
-	"adc1",
-	"adc2",
-	"adc3",
-	"adc4",
-	"adc5",
-	"adc6",
-	"adc7",
+static const struct rzg2l_adc_channel rzg2l_adc_channels[] = {
+	{ "adc0", IIO_VOLTAGE },
+	{ "adc1", IIO_VOLTAGE },
+	{ "adc2", IIO_VOLTAGE },
+	{ "adc3", IIO_VOLTAGE },
+	{ "adc4", IIO_VOLTAGE },
+	{ "adc5", IIO_VOLTAGE },
+	{ "adc6", IIO_VOLTAGE },
+	{ "adc7", IIO_VOLTAGE },
+	{ "adc8", IIO_TEMP },
 };
 
 static unsigned int rzg2l_adc_readl(struct rzg2l_adc *adc, u32 reg)
@@ -115,7 +138,7 @@ static void rzg2l_adc_pwr(struct rzg2l_adc *adc, bool on)
 
 static void rzg2l_adc_start_stop(struct rzg2l_adc *adc, bool start)
 {
-	int timeout = 5;
+	int ret;
 	u32 reg;
 
 	reg = rzg2l_adc_readl(adc, RZG2L_ADM(0));
@@ -128,15 +151,10 @@ static void rzg2l_adc_start_stop(struct rzg2l_adc *adc, bool start)
 	if (start)
 		return;
 
-	do {
-		usleep_range(100, 200);
-		reg = rzg2l_adc_readl(adc, RZG2L_ADM(0));
-		timeout--;
-		if (!timeout) {
-			pr_err("%s stopping ADC timed out\n", __func__);
-			break;
-		}
-	} while (((reg & RZG2L_ADM0_ADBSY) || (reg & RZG2L_ADM0_ADCE)));
+	ret = read_poll_timeout(rzg2l_adc_readl, reg, !(reg & (RZG2L_ADM0_ADBSY | RZG2L_ADM0_ADCE)),
+				200, 1000, true, adc, RZG2L_ADM(0));
+	if (ret)
+		pr_err("%s stopping ADC timed out\n", __func__);
 }
 
 static void rzg2l_set_trigger(struct rzg2l_adc *adc)
@@ -158,8 +176,18 @@ static void rzg2l_set_trigger(struct rzg2l_adc *adc)
 	rzg2l_adc_writel(adc, RZG2L_ADM(1), reg);
 }
 
+static u8 rzg2l_adc_ch_to_adsmp_index(u8 ch)
+{
+	if (rzg2l_adc_channels[ch].type == IIO_VOLTAGE)
+		return 0;
+
+	return 1;
+}
+
 static int rzg2l_adc_conversion_setup(struct rzg2l_adc *adc, u8 ch)
 {
+	const struct rzg2l_adc_hw_params *hw_params = adc->hw_params;
+	u8 index = rzg2l_adc_ch_to_adsmp_index(ch);
 	u32 reg;
 
 	if (rzg2l_adc_readl(adc, RZG2L_ADM(0)) & RZG2L_ADM0_ADBSY)
@@ -169,10 +197,15 @@ static int rzg2l_adc_conversion_setup(struct rzg2l_adc *adc, u8 ch)
 
 	/* Select analog input channel subjected to conversion. */
 	reg = rzg2l_adc_readl(adc, RZG2L_ADM(2));
-	reg &= ~RZG2L_ADM2_CHSEL_MASK;
+	reg &= ~GENMASK(hw_params->num_channels - 1, 0);
 	reg |= BIT(ch);
 	rzg2l_adc_writel(adc, RZG2L_ADM(2), reg);
 
+	reg = rzg2l_adc_readl(adc, RZG2L_ADM(3));
+	reg &= ~hw_params->adsmp_mask;
+	reg |= hw_params->default_adsmp[index];
+	rzg2l_adc_writel(adc, RZG2L_ADM(3), reg);
+
 	/*
 	 * Setup ADINT
 	 * INTS[31] - Select pulse signal
@@ -181,36 +214,26 @@ static int rzg2l_adc_conversion_setup(struct rzg2l_adc *adc, u8 ch)
 	 */
 	reg = rzg2l_adc_readl(adc, RZG2L_ADINT);
 	reg &= ~RZG2L_ADINT_INTS;
-	reg &= ~RZG2L_ADINT_INTEN_MASK;
+	reg &= ~hw_params->adint_inten_mask;
 	reg |= (RZG2L_ADINT_CSEEN | BIT(ch));
 	rzg2l_adc_writel(adc, RZG2L_ADINT, reg);
 
 	return 0;
 }
 
-static int rzg2l_adc_set_power(struct iio_dev *indio_dev, bool on)
-{
-	struct device *dev = indio_dev->dev.parent;
-
-	if (on)
-		return pm_runtime_resume_and_get(dev);
-
-	return pm_runtime_put_sync(dev);
-}
-
 static int rzg2l_adc_conversion(struct iio_dev *indio_dev, struct rzg2l_adc *adc, u8 ch)
 {
+	const struct rzg2l_adc_hw_params *hw_params = adc->hw_params;
+	struct device *dev = indio_dev->dev.parent;
 	int ret;
 
-	ret = rzg2l_adc_set_power(indio_dev, true);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
 		return ret;
 
 	ret = rzg2l_adc_conversion_setup(adc, ch);
-	if (ret) {
-		rzg2l_adc_set_power(indio_dev, false);
-		return ret;
-	}
+	if (ret)
+		goto rpm_put;
 
 	reinit_completion(&adc->completion);
 
@@ -218,13 +241,16 @@ static int rzg2l_adc_conversion(struct iio_dev *indio_dev, struct rzg2l_adc *adc
 
 	if (!wait_for_completion_timeout(&adc->completion, RZG2L_ADC_TIMEOUT)) {
 		rzg2l_adc_writel(adc, RZG2L_ADINT,
-				 rzg2l_adc_readl(adc, RZG2L_ADINT) & ~RZG2L_ADINT_INTEN_MASK);
-		rzg2l_adc_start_stop(adc, false);
-		rzg2l_adc_set_power(indio_dev, false);
-		return -ETIMEDOUT;
+				 rzg2l_adc_readl(adc, RZG2L_ADINT) & ~hw_params->adint_inten_mask);
+		ret = -ETIMEDOUT;
 	}
 
-	return rzg2l_adc_set_power(indio_dev, false);
+	rzg2l_adc_start_stop(adc, false);
+
+rpm_put:
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+	return ret;
 }
 
 static int rzg2l_adc_read_raw(struct iio_dev *indio_dev,
@@ -233,24 +259,22 @@ static int rzg2l_adc_read_raw(struct iio_dev *indio_dev,
 {
 	struct rzg2l_adc *adc = iio_priv(indio_dev);
 	int ret;
-	u8 ch;
 
 	switch (mask) {
-	case IIO_CHAN_INFO_RAW:
-		if (chan->type != IIO_VOLTAGE)
+	case IIO_CHAN_INFO_RAW: {
+		if (chan->type != IIO_VOLTAGE && chan->type != IIO_TEMP)
 			return -EINVAL;
 
-		mutex_lock(&adc->lock);
-		ch = chan->channel & RZG2L_ADC_CHN_MASK;
-		ret = rzg2l_adc_conversion(indio_dev, adc, ch);
-		if (ret) {
-			mutex_unlock(&adc->lock);
+		guard(mutex)(&adc->lock);
+
+		ret = rzg2l_adc_conversion(indio_dev, adc, chan->channel);
+		if (ret)
 			return ret;
-		}
-		*val = adc->last_val[ch];
-		mutex_unlock(&adc->lock);
+
+		*val = adc->last_val[chan->channel];
 
 		return IIO_VAL_INT;
+	}
 
 	default:
 		return -EINVAL;
@@ -261,7 +285,7 @@ static int rzg2l_adc_read_label(struct iio_dev *iio_dev,
 				const struct iio_chan_spec *chan,
 				char *label)
 {
-	return sysfs_emit(label, "%s\n", rzg2l_adc_channel_name[chan->channel]);
+	return sysfs_emit(label, "%s\n", rzg2l_adc_channels[chan->channel].name);
 }
 
 static const struct iio_info rzg2l_adc_iio_info = {
@@ -272,6 +296,7 @@ static const struct iio_info rzg2l_adc_iio_info = {
 static irqreturn_t rzg2l_adc_isr(int irq, void *dev_id)
 {
 	struct rzg2l_adc *adc = dev_id;
+	const struct rzg2l_adc_hw_params *hw_params = adc->hw_params;
 	unsigned long intst;
 	u32 reg;
 	int ch;
@@ -284,11 +309,11 @@ static irqreturn_t rzg2l_adc_isr(int irq, void *dev_id)
 		return IRQ_HANDLED;
 	}
 
-	intst = reg & RZG2L_ADSTS_INTST_MASK;
+	intst = reg & GENMASK(hw_params->num_channels - 1, 0);
 	if (!intst)
 		return IRQ_NONE;
 
-	for_each_set_bit(ch, &intst, RZG2L_ADC_MAX_CHANNELS)
+	for_each_set_bit(ch, &intst, hw_params->num_channels)
 		adc->last_val[ch] = rzg2l_adc_readl(adc, RZG2L_ADCR(ch)) & RZG2L_ADCR_AD_MASK;
 
 	/* clear the channel interrupt */
@@ -301,6 +326,7 @@ static irqreturn_t rzg2l_adc_isr(int irq, void *dev_id)
 
 static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l_adc *adc)
 {
+	const struct rzg2l_adc_hw_params *hw_params = adc->hw_params;
 	struct iio_chan_spec *chan_array;
 	struct rzg2l_adc_data *data;
 	unsigned int channel;
@@ -313,15 +339,12 @@ static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l
 		return -ENOMEM;
 
 	num_channels = device_get_child_node_count(&pdev->dev);
-	if (!num_channels) {
-		dev_err(&pdev->dev, "no channel children\n");
-		return -ENODEV;
-	}
+	if (!num_channels)
+		return dev_err_probe(&pdev->dev, -ENODEV, "no channel children\n");
 
-	if (num_channels > RZG2L_ADC_MAX_CHANNELS) {
-		dev_err(&pdev->dev, "num of channel children out of range\n");
-		return -EINVAL;
-	}
+	if (num_channels > hw_params->num_channels)
+		return dev_err_probe(&pdev->dev, -EINVAL,
+				     "num of channel children out of range\n");
 
 	chan_array = devm_kcalloc(&pdev->dev, num_channels, sizeof(*chan_array),
 				  GFP_KERNEL);
@@ -334,14 +357,14 @@ static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l
 		if (ret)
 			return ret;
 
-		if (channel >= RZG2L_ADC_MAX_CHANNELS)
+		if (channel >= hw_params->num_channels)
 			return -EINVAL;
 
-		chan_array[i].type = IIO_VOLTAGE;
+		chan_array[i].type = rzg2l_adc_channels[channel].type;
 		chan_array[i].indexed = 1;
 		chan_array[i].channel = channel;
 		chan_array[i].info_mask_separate = BIT(IIO_CHAN_INFO_RAW);
-		chan_array[i].datasheet_name = rzg2l_adc_channel_name[channel];
+		chan_array[i].datasheet_name = rzg2l_adc_channels[channel].name;
 		i++;
 	}
 
@@ -352,13 +375,13 @@ static int rzg2l_adc_parse_properties(struct platform_device *pdev, struct rzg2l
 	return 0;
 }
 
-static int rzg2l_adc_hw_init(struct rzg2l_adc *adc)
+static int rzg2l_adc_hw_init(struct device *dev, struct rzg2l_adc *adc)
 {
-	int timeout = 5;
+	const struct rzg2l_adc_hw_params *hw_params = adc->hw_params;
 	u32 reg;
 	int ret;
 
-	ret = clk_prepare_enable(adc->pclk);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret)
 		return ret;
 
@@ -367,21 +390,19 @@ static int rzg2l_adc_hw_init(struct rzg2l_adc *adc)
 	reg |= RZG2L_ADM0_SRESB;
 	rzg2l_adc_writel(adc, RZG2L_ADM(0), reg);
 
-	while (!(rzg2l_adc_readl(adc, RZG2L_ADM(0)) & RZG2L_ADM0_SRESB)) {
-		if (!timeout) {
-			ret = -EBUSY;
-			goto exit_hw_init;
-		}
-		timeout--;
-		usleep_range(100, 200);
+	ret = read_poll_timeout(rzg2l_adc_readl, reg, reg & RZG2L_ADM0_SRESB,
+				200, 1000, false, adc, RZG2L_ADM(0));
+	if (ret)
+		goto exit_hw_init;
+
+	if (hw_params->adivc) {
+		/* Only division by 4 can be set */
+		reg = rzg2l_adc_readl(adc, RZG2L_ADIVC);
+		reg &= ~RZG2L_ADIVC_DIVADC_MASK;
+		reg |= RZG2L_ADIVC_DIVADC_4;
+		rzg2l_adc_writel(adc, RZG2L_ADIVC, reg);
 	}
 
-	/* Only division by 4 can be set */
-	reg = rzg2l_adc_readl(adc, RZG2L_ADIVC);
-	reg &= ~RZG2L_ADIVC_DIVADC_MASK;
-	reg |= RZG2L_ADIVC_DIVADC_4;
-	rzg2l_adc_writel(adc, RZG2L_ADIVC, reg);
-
 	/*
 	 * Setup AMD3
 	 * ADIL[31:24] - Should be always set to 0
@@ -391,35 +412,18 @@ static int rzg2l_adc_hw_init(struct rzg2l_adc *adc)
 	reg = rzg2l_adc_readl(adc, RZG2L_ADM(3));
 	reg &= ~RZG2L_ADM3_ADIL_MASK;
 	reg &= ~RZG2L_ADM3_ADCMP_MASK;
-	reg &= ~RZG2L_ADM3_ADSMP_MASK;
-	reg |= (RZG2L_ADM3_ADCMP_E | RZG2L_ADSMP_DEFAULT_SAMPLING);
+	reg &= ~hw_params->adsmp_mask;
+	reg |= FIELD_PREP(RZG2L_ADM3_ADCMP_MASK, hw_params->default_adcmp) |
+	       hw_params->default_adsmp[0];
+
 	rzg2l_adc_writel(adc, RZG2L_ADM(3), reg);
 
 exit_hw_init:
-	clk_disable_unprepare(adc->pclk);
-
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
 	return ret;
 }
 
-static void rzg2l_adc_pm_runtime_disable(void *data)
-{
-	struct device *dev = data;
-
-	pm_runtime_disable(dev->parent);
-}
-
-static void rzg2l_adc_pm_runtime_set_suspended(void *data)
-{
-	struct device *dev = data;
-
-	pm_runtime_set_suspended(dev->parent);
-}
-
-static void rzg2l_adc_reset_assert(void *data)
-{
-	reset_control_assert(data);
-}
-
 static int rzg2l_adc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -434,6 +438,10 @@ static int rzg2l_adc_probe(struct platform_device *pdev)
 
 	adc = iio_priv(indio_dev);
 
+	adc->hw_params = device_get_match_data(dev);
+	if (!adc->hw_params || adc->hw_params->num_channels > RZG2L_ADC_MAX_CHANNELS)
+		return -EINVAL;
+
 	ret = rzg2l_adc_parse_properties(pdev, adc);
 	if (ret)
 		return ret;
@@ -444,63 +452,28 @@ static int rzg2l_adc_probe(struct platform_device *pdev)
 	if (IS_ERR(adc->base))
 		return PTR_ERR(adc->base);
 
-	adc->pclk = devm_clk_get(dev, "pclk");
-	if (IS_ERR(adc->pclk)) {
-		dev_err(dev, "Failed to get pclk");
-		return PTR_ERR(adc->pclk);
-	}
+	adc->adrstn = devm_reset_control_get_exclusive_deasserted(dev, "adrst-n");
+	if (IS_ERR(adc->adrstn))
+		return dev_err_probe(dev, PTR_ERR(adc->adrstn),
+				     "failed to get/deassert adrst-n\n");
 
-	adc->adclk = devm_clk_get(dev, "adclk");
-	if (IS_ERR(adc->adclk)) {
-		dev_err(dev, "Failed to get adclk");
-		return PTR_ERR(adc->adclk);
-	}
+	adc->presetn = devm_reset_control_get_exclusive_deasserted(dev, "presetn");
+	if (IS_ERR(adc->presetn))
+		return dev_err_probe(dev, PTR_ERR(adc->presetn),
+				     "failed to get/deassert presetn\n");
 
-	adc->adrstn = devm_reset_control_get_exclusive(dev, "adrst-n");
-	if (IS_ERR(adc->adrstn)) {
-		dev_err(dev, "failed to get adrstn\n");
-		return PTR_ERR(adc->adrstn);
-	}
-
-	adc->presetn = devm_reset_control_get_exclusive(dev, "presetn");
-	if (IS_ERR(adc->presetn)) {
-		dev_err(dev, "failed to get presetn\n");
-		return PTR_ERR(adc->presetn);
-	}
-
-	ret = reset_control_deassert(adc->adrstn);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to deassert adrstn pin, %d\n", ret);
-		return ret;
-	}
-
-	ret = devm_add_action_or_reset(&pdev->dev,
-				       rzg2l_adc_reset_assert, adc->adrstn);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register adrstn assert devm action, %d\n",
-			ret);
+	pm_runtime_set_autosuspend_delay(dev, 300);
+	pm_runtime_use_autosuspend(dev);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
 		return ret;
-	}
 
-	ret = reset_control_deassert(adc->presetn);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to deassert presetn pin, %d\n", ret);
-		return ret;
-	}
-
-	ret = devm_add_action_or_reset(&pdev->dev,
-				       rzg2l_adc_reset_assert, adc->presetn);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register presetn assert devm action, %d\n",
-			ret);
-		return ret;
-	}
+	platform_set_drvdata(pdev, indio_dev);
 
-	ret = rzg2l_adc_hw_init(adc);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to initialize ADC HW, %d\n", ret);
-		return ret;
-	}
+	ret = rzg2l_adc_hw_init(dev, adc);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "failed to initialize ADC HW\n");
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
@@ -513,72 +486,130 @@ static int rzg2l_adc_probe(struct platform_device *pdev)
 
 	init_completion(&adc->completion);
 
-	platform_set_drvdata(pdev, indio_dev);
-
 	indio_dev->name = DRIVER_NAME;
 	indio_dev->info = &rzg2l_adc_iio_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->channels = adc->data->channels;
 	indio_dev->num_channels = adc->data->num_channels;
 
-	pm_runtime_set_suspended(dev);
-	ret = devm_add_action_or_reset(&pdev->dev,
-				       rzg2l_adc_pm_runtime_set_suspended, &indio_dev->dev);
-	if (ret)
-		return ret;
-
-	pm_runtime_enable(dev);
-	ret = devm_add_action_or_reset(&pdev->dev,
-				       rzg2l_adc_pm_runtime_disable, &indio_dev->dev);
-	if (ret)
-		return ret;
-
 	return devm_iio_device_register(dev, indio_dev);
 }
 
+static const struct rzg2l_adc_hw_params rzg2l_hw_params = {
+	.num_channels = 8,
+	.default_adcmp = 0xe,
+	.default_adsmp = { 0x578 },
+	.adsmp_mask = GENMASK(15, 0),
+	.adint_inten_mask = GENMASK(7, 0),
+	.adivc = true
+};
+
+static const struct rzg2l_adc_hw_params rzg3s_hw_params = {
+	.num_channels = 9,
+	.default_adcmp = 0x1d,
+	.default_adsmp = { 0x7f, 0xff },
+	.adsmp_mask = GENMASK(7, 0),
+	.adint_inten_mask = GENMASK(11, 0),
+};
+
 static const struct of_device_id rzg2l_adc_match[] = {
-	{ .compatible = "renesas,rzg2l-adc",},
+	{ .compatible = "renesas,r9a08g045-adc", .data = &rzg3s_hw_params },
+	{ .compatible = "renesas,rzg2l-adc", .data = &rzg2l_hw_params },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, rzg2l_adc_match);
 
-static int __maybe_unused rzg2l_adc_pm_runtime_suspend(struct device *dev)
+static int rzg2l_adc_pm_runtime_suspend(struct device *dev)
 {
 	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 	struct rzg2l_adc *adc = iio_priv(indio_dev);
 
 	rzg2l_adc_pwr(adc, false);
-	clk_disable_unprepare(adc->adclk);
-	clk_disable_unprepare(adc->pclk);
 
 	return 0;
 }
 
-static int __maybe_unused rzg2l_adc_pm_runtime_resume(struct device *dev)
+static int rzg2l_adc_pm_runtime_resume(struct device *dev)
+{
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
+	struct rzg2l_adc *adc = iio_priv(indio_dev);
+
+	rzg2l_adc_pwr(adc, true);
+
+	return 0;
+}
+
+static int rzg2l_adc_suspend(struct device *dev)
 {
 	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 	struct rzg2l_adc *adc = iio_priv(indio_dev);
+	struct reset_control_bulk_data resets[] = {
+		{ .rstc = adc->presetn },
+		{ .rstc = adc->adrstn },
+	};
 	int ret;
 
-	ret = clk_prepare_enable(adc->pclk);
+	if (pm_runtime_suspended(dev)) {
+		adc->was_rpm_active = false;
+	} else {
+		ret = pm_runtime_force_suspend(dev);
+		if (ret)
+			return ret;
+		adc->was_rpm_active = true;
+	}
+
+	ret = reset_control_bulk_assert(ARRAY_SIZE(resets), resets);
 	if (ret)
-		return ret;
+		goto rpm_restore;
+
+	return 0;
+
+rpm_restore:
+	if (adc->was_rpm_active)
+		pm_runtime_force_resume(dev);
+
+	return ret;
+}
+
+static int rzg2l_adc_resume(struct device *dev)
+{
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
+	struct rzg2l_adc *adc = iio_priv(indio_dev);
+	struct reset_control_bulk_data resets[] = {
+		{ .rstc = adc->adrstn },
+		{ .rstc = adc->presetn },
+	};
+	int ret;
 
-	ret = clk_prepare_enable(adc->adclk);
-	if (ret) {
-		clk_disable_unprepare(adc->pclk);
+	ret = reset_control_bulk_deassert(ARRAY_SIZE(resets), resets);
+	if (ret)
 		return ret;
+
+	if (adc->was_rpm_active) {
+		ret = pm_runtime_force_resume(dev);
+		if (ret)
+			goto resets_restore;
 	}
 
-	rzg2l_adc_pwr(adc, true);
+	ret = rzg2l_adc_hw_init(dev, adc);
+	if (ret)
+		goto rpm_restore;
 
 	return 0;
+
+rpm_restore:
+	if (adc->was_rpm_active) {
+		pm_runtime_mark_last_busy(dev);
+		pm_runtime_put_autosuspend(dev);
+	}
+resets_restore:
+	reset_control_bulk_assert(ARRAY_SIZE(resets), resets);
+	return ret;
 }
 
 static const struct dev_pm_ops rzg2l_adc_pm_ops = {
-	SET_RUNTIME_PM_OPS(rzg2l_adc_pm_runtime_suspend,
-			   rzg2l_adc_pm_runtime_resume,
-			   NULL)
+	RUNTIME_PM_OPS(rzg2l_adc_pm_runtime_suspend, rzg2l_adc_pm_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(rzg2l_adc_suspend, rzg2l_adc_resume)
 };
 
 static struct platform_driver rzg2l_adc_driver = {
@@ -586,7 +617,7 @@ static struct platform_driver rzg2l_adc_driver = {
 	.driver		= {
 		.name		= DRIVER_NAME,
 		.of_match_table = rzg2l_adc_match,
-		.pm		= &rzg2l_adc_pm_ops,
+		.pm		= pm_ptr(&rzg2l_adc_pm_ops),
 	},
 };
 
diff --git a/drivers/iio/adc/ti-adc081c.c b/drivers/iio/adc/ti-adc081c.c
index 6c2cb3dabbbf..1af9be071d8d 100644
--- a/drivers/iio/adc/ti-adc081c.c
+++ b/drivers/iio/adc/ti-adc081c.c
@@ -37,7 +37,7 @@ struct adc081c {
 	/* Ensure natural alignment of buffer elements */
 	struct {
 		u16 channel;
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/adc/ti-adc084s021.c b/drivers/iio/adc/ti-adc084s021.c
index bf98f9bf942a..da16876c32ae 100644
--- a/drivers/iio/adc/ti-adc084s021.c
+++ b/drivers/iio/adc/ti-adc084s021.c
@@ -29,7 +29,7 @@ struct adc084s021 {
 	/* Buffer used to align data */
 	struct {
 		__be16 channels[4];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	/*
 	 * DMA (thus cache coherency maintenance) may require the
diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c
index 47fe8e16aee4..4355726b373a 100644
--- a/drivers/iio/adc/ti-ads1015.c
+++ b/drivers/iio/adc/ti-ads1015.c
@@ -448,7 +448,7 @@ static irqreturn_t ads1015_trigger_handler(int irq, void *p)
 	/* Ensure natural alignment of timestamp */
 	struct {
 		s16 chan;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	int chan, ret, res;
 
diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c
index c268e27eec12..de019b3faa48 100644
--- a/drivers/iio/adc/ti-ads1119.c
+++ b/drivers/iio/adc/ti-ads1119.c
@@ -501,7 +501,7 @@ static irqreturn_t ads1119_trigger_handler(int irq, void *private)
 	struct ads1119_state *st = iio_priv(indio_dev);
 	struct {
 		s16 sample;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	unsigned int index;
 	int ret;
diff --git a/drivers/iio/adc/ti-ads131e08.c b/drivers/iio/adc/ti-ads131e08.c
index 31f1f229d97a..91a79ebc4bde 100644
--- a/drivers/iio/adc/ti-ads131e08.c
+++ b/drivers/iio/adc/ti-ads131e08.c
@@ -102,7 +102,7 @@ struct ads131e08_state {
 	struct completion completion;
 	struct {
 		u8 data[ADS131E08_NUM_DATA_BYTES_MAX];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} tmp_buf;
 
 	u8 tx_buf[3] __aligned(IIO_DMA_MINALIGN);
diff --git a/drivers/iio/adc/ti-lmp92064.c b/drivers/iio/adc/ti-lmp92064.c
index 169e3591320b..1e4a78677fe5 100644
--- a/drivers/iio/adc/ti-lmp92064.c
+++ b/drivers/iio/adc/ti-lmp92064.c
@@ -199,7 +199,7 @@ static irqreturn_t lmp92064_trigger_handler(int irq, void *p)
 	struct lmp92064_adc_priv *priv = iio_priv(indio_dev);
 	struct {
 		u16 values[2];
-		int64_t timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} data;
 	int ret;
 
diff --git a/drivers/iio/adc/ti-tsc2046.c b/drivers/iio/adc/ti-tsc2046.c
index b56f2503f14c..7dde5713973f 100644
--- a/drivers/iio/adc/ti-tsc2046.c
+++ b/drivers/iio/adc/ti-tsc2046.c
@@ -157,7 +157,7 @@ struct tsc2046_adc_priv {
 		/* Scan data for each channel */
 		u16 data[TI_TSC2046_MAX_CHAN];
 		/* Timestamp */
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan_buf;
 
 	/*
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index 4d83c12975c5..513365d42aa5 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -173,10 +173,14 @@ struct vf610_adc {
 	/* Ensure the timestamp is naturally aligned */
 	struct {
 		u16 chan;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
+struct vf610_chip_info {
+	u8 num_channels;
+};
+
 static const u32 vf610_hw_avgs[] = { 1, 4, 8, 16, 32 };
 static const u32 vf610_lst_adder[] = { 3, 5, 7, 9, 13, 17, 21, 25 };
 
@@ -808,14 +812,31 @@ static const struct iio_info vf610_adc_iio_info = {
 	.attrs = &vf610_attribute_group,
 };
 
+static const struct vf610_chip_info vf610_chip_info = {
+	.num_channels = ARRAY_SIZE(vf610_adc_iio_channels),
+};
+
+static const struct vf610_chip_info imx6sx_chip_info = {
+	.num_channels = 4,
+};
+
 static const struct of_device_id vf610_adc_match[] = {
-	{ .compatible = "fsl,vf610-adc", },
+	{ .compatible = "fsl,imx6sx-adc", .data = &imx6sx_chip_info},
+	{ .compatible = "fsl,vf610-adc", .data = &vf610_chip_info},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, vf610_adc_match);
 
+static void vf610_adc_action_remove(void *d)
+{
+	struct vf610_adc *info = d;
+
+	regulator_disable(info->vref);
+}
+
 static int vf610_adc_probe(struct platform_device *pdev)
 {
+	const struct vf610_chip_info *chip_info;
 	struct device *dev = &pdev->dev;
 	struct vf610_adc *info;
 	struct iio_dev *indio_dev;
@@ -823,10 +844,8 @@ static int vf610_adc_probe(struct platform_device *pdev)
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(struct vf610_adc));
-	if (!indio_dev) {
-		dev_err(&pdev->dev, "Failed allocating iio device\n");
-		return -ENOMEM;
-	}
+	if (!indio_dev)
+		return dev_err_probe(&pdev->dev, -ENOMEM, "Failed allocating iio device\n");
 
 	info = iio_priv(indio_dev);
 	info->dev = &pdev->dev;
@@ -835,6 +854,8 @@ static int vf610_adc_probe(struct platform_device *pdev)
 	if (IS_ERR(info->regs))
 		return PTR_ERR(info->regs);
 
+	chip_info = device_get_match_data(dev);
+
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
 		return irq;
@@ -842,17 +863,12 @@ static int vf610_adc_probe(struct platform_device *pdev)
 	ret = devm_request_irq(info->dev, irq,
 				vf610_adc_isr, 0,
 				dev_name(&pdev->dev), indio_dev);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed requesting irq, irq = %d\n", irq);
-		return ret;
-	}
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "failed requesting irq, irq = %d\n", irq);
 
-	info->clk = devm_clk_get(&pdev->dev, "adc");
-	if (IS_ERR(info->clk)) {
-		dev_err(&pdev->dev, "failed getting clock, err = %ld\n",
-						PTR_ERR(info->clk));
-		return PTR_ERR(info->clk);
-	}
+	info->clk = devm_clk_get_enabled(&pdev->dev, "adc");
+	if (IS_ERR(info->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(info->clk), "failed getting clock\n");
 
 	info->vref = devm_regulator_get(&pdev->dev, "vref");
 	if (IS_ERR(info->vref))
@@ -862,6 +878,10 @@ static int vf610_adc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = devm_add_action_or_reset(&pdev->dev, vf610_adc_action_remove, info);
+	if (ret)
+		return ret;
+
 	info->vref_uv = regulator_get_voltage(info->vref);
 
 	device_property_read_u32_array(dev, "fsl,adck-max-frequency", info->max_adck_rate, 3);
@@ -877,54 +897,23 @@ static int vf610_adc_probe(struct platform_device *pdev)
 	indio_dev->info = &vf610_adc_iio_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->channels = vf610_adc_iio_channels;
-	indio_dev->num_channels = ARRAY_SIZE(vf610_adc_iio_channels);
-
-	ret = clk_prepare_enable(info->clk);
-	if (ret) {
-		dev_err(&pdev->dev,
-			"Could not prepare or enable the clock.\n");
-		goto error_adc_clk_enable;
-	}
+	indio_dev->num_channels = chip_info->num_channels;
 
 	vf610_adc_cfg_init(info);
 	vf610_adc_hw_init(info);
 
-	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
-					NULL, &iio_triggered_buffer_setup_ops);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Couldn't initialise the buffer\n");
-		goto error_iio_device_register;
-	}
+	ret = devm_iio_triggered_buffer_setup(&pdev->dev, indio_dev, &iio_pollfunc_store_time,
+					      NULL, &iio_triggered_buffer_setup_ops);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "Couldn't initialise the buffer\n");
 
 	mutex_init(&info->lock);
 
-	ret = iio_device_register(indio_dev);
-	if (ret) {
-		dev_err(&pdev->dev, "Couldn't register the device.\n");
-		goto error_adc_buffer_init;
-	}
+	ret = devm_iio_device_register(&pdev->dev, indio_dev);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Couldn't register the device.\n");
 
 	return 0;
-
-error_adc_buffer_init:
-	iio_triggered_buffer_cleanup(indio_dev);
-error_iio_device_register:
-	clk_disable_unprepare(info->clk);
-error_adc_clk_enable:
-	regulator_disable(info->vref);
-
-	return ret;
-}
-
-static void vf610_adc_remove(struct platform_device *pdev)
-{
-	struct iio_dev *indio_dev = platform_get_drvdata(pdev);
-	struct vf610_adc *info = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-	iio_triggered_buffer_cleanup(indio_dev);
-	regulator_disable(info->vref);
-	clk_disable_unprepare(info->clk);
 }
 
 static int vf610_adc_suspend(struct device *dev)
@@ -972,7 +961,6 @@ static DEFINE_SIMPLE_DEV_PM_OPS(vf610_adc_pm_ops, vf610_adc_suspend,
 
 static struct platform_driver vf610_adc_driver = {
 	.probe          = vf610_adc_probe,
-	.remove         = vf610_adc_remove,
 	.driver         = {
 		.name   = DRIVER_NAME,
 		.of_match_table = vf610_adc_match,
diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
index d2e1529ad8fd..614e1c4189a9 100644
--- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c
+++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
@@ -206,7 +206,7 @@ static const struct iio_dev_attr *iio_dmaengine_buffer_attrs[] = {
 
 /**
  * iio_dmaengine_buffer_alloc() - Allocate new buffer which uses DMAengine
- * @dev: Parent device for the buffer
+ * @dev: DMA channel consumer device
  * @channel: DMA channel name, typically "rx".
  *
  * This allocates a new IIO buffer which internally uses the DMAengine framework
@@ -288,6 +288,21 @@ void iio_dmaengine_buffer_free(struct iio_buffer *buffer)
 }
 EXPORT_SYMBOL_NS_GPL(iio_dmaengine_buffer_free, "IIO_DMAENGINE_BUFFER");
 
+/**
+ * iio_dmaengine_buffer_setup_ext() - Setup a DMA buffer for an IIO device
+ * @dev: DMA channel consumer device
+ * @indio_dev: IIO device to which to attach this buffer.
+ * @channel: DMA channel name, typically "rx".
+ * @dir: Direction of buffer (in or out)
+ *
+ * This allocates a new IIO buffer with devm_iio_dmaengine_buffer_alloc()
+ * and attaches it to an IIO device with iio_device_attach_buffer().
+ * It also appends the INDIO_BUFFER_HARDWARE mode to the supported modes of the
+ * IIO device.
+ *
+ * Once done using the buffer iio_dmaengine_buffer_free() should be used to
+ * release it.
+ */
 struct iio_buffer *iio_dmaengine_buffer_setup_ext(struct device *dev,
 						  struct iio_dev *indio_dev,
 						  const char *channel,
@@ -321,7 +336,7 @@ static void __devm_iio_dmaengine_buffer_free(void *buffer)
 
 /**
  * devm_iio_dmaengine_buffer_setup_ext() - Setup a DMA buffer for an IIO device
- * @dev: Parent device for the buffer
+ * @dev: Device for devm ownership and DMA channel consumer device
  * @indio_dev: IIO device to which to attach this buffer.
  * @channel: DMA channel name, typically "rx".
  * @dir: Direction of buffer (in or out)
diff --git a/drivers/iio/chemical/bme680.h b/drivers/iio/chemical/bme680.h
index 00ab89b3138b..7d86ed8b02e6 100644
--- a/drivers/iio/chemical/bme680.h
+++ b/drivers/iio/chemical/bme680.h
@@ -2,6 +2,7 @@
 #ifndef BME680_H_
 #define BME680_H_
 
+#include <linux/pm.h>
 #include <linux/regmap.h>
 
 #define BME680_REG_CHIP_ID			0xD0
@@ -80,6 +81,7 @@
 #define BME680_CALIB_RANGE_3_LEN               5
 
 extern const struct regmap_config bme680_regmap_config;
+extern const struct dev_pm_ops bme680_dev_pm_ops;
 
 int bme680_core_probe(struct device *dev, struct regmap *regmap,
 		      const char *name);
diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c
index d12270409c8a..9d73fd2cf52c 100644
--- a/drivers/iio/chemical/bme680_core.c
+++ b/drivers/iio/chemical/bme680_core.c
@@ -14,7 +14,10 @@
 #include <linux/device.h>
 #include <linux/log2.h>
 #include <linux/module.h>
+#include <linux/pm.h>
+#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/iio/buffer.h>
 #include <linux/iio/iio.h>
@@ -111,6 +114,8 @@ enum bme680_scan {
 	BME680_GAS,
 };
 
+static const char *const bme680_supply_names[] = { "vdd", "vddio" };
+
 struct bme680_data {
 	struct regmap *regmap;
 	struct bme680_calib bme680;
@@ -817,9 +822,9 @@ static int bme680_read_gas(struct bme680_data *data, int *comp_gas_res)
 	return 0;
 }
 
-static int bme680_read_raw(struct iio_dev *indio_dev,
-			   struct iio_chan_spec const *chan,
-			   int *val, int *val2, long mask)
+static int __bme680_read_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int *val, int *val2, long mask)
 {
 	struct bme680_data *data = iio_priv(indio_dev);
 	int chan_val, ret;
@@ -874,11 +879,11 @@ static int bme680_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_RAW:
 		switch (chan->type) {
 		case IIO_TEMP:
-			ret = bme680_read_temp(data, (s16 *)&chan_val);
+			ret = bme680_read_temp(data, &temp_chan_val);
 			if (ret)
 				return ret;
 
-			*val = chan_val;
+			*val = temp_chan_val;
 			return IIO_VAL_INT;
 		case IIO_PRESSURE:
 			ret = bme680_read_press(data, &chan_val);
@@ -932,14 +937,33 @@ static int bme680_read_raw(struct iio_dev *indio_dev,
 	}
 }
 
+static int bme680_read_raw(struct iio_dev *indio_dev,
+			   struct iio_chan_spec const *chan,
+			   int *val, int *val2, long mask)
+{
+	struct bme680_data *data = iio_priv(indio_dev);
+	struct device *dev = regmap_get_device(data->regmap);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
+		return ret;
+
+	ret = __bme680_read_raw(indio_dev, chan, val, val2, mask);
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
+}
+
 static bool bme680_is_valid_oversampling(int rate)
 {
 	return (rate > 0 && rate <= 16 && is_power_of_2(rate));
 }
 
-static int bme680_write_raw(struct iio_dev *indio_dev,
-			    struct iio_chan_spec const *chan,
-			    int val, int val2, long mask)
+static int __bme680_write_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int val, int val2, long mask)
 {
 	struct bme680_data *data = iio_priv(indio_dev);
 
@@ -984,6 +1008,25 @@ static int bme680_write_raw(struct iio_dev *indio_dev,
 	}
 }
 
+static int bme680_write_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan,
+			    int val, int val2, long mask)
+{
+	struct bme680_data *data = iio_priv(indio_dev);
+	struct device *dev = regmap_get_device(data->regmap);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret)
+		return ret;
+
+	ret = __bme680_write_raw(indio_dev, chan, val, val2, mask);
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
+}
+
 static const char bme680_oversampling_ratio_show[] = "1 2 4 8 16";
 
 static IIO_CONST_ATTR(oversampling_ratio_available,
@@ -1084,6 +1127,29 @@ out:
 	return IRQ_HANDLED;
 }
 
+static int bme680_buffer_preenable(struct iio_dev *indio_dev)
+{
+	struct bme680_data *data = iio_priv(indio_dev);
+	struct device *dev = regmap_get_device(data->regmap);
+
+	return pm_runtime_resume_and_get(dev);
+}
+
+static int bme680_buffer_postdisable(struct iio_dev *indio_dev)
+{
+	struct bme680_data *data = iio_priv(indio_dev);
+	struct device *dev = regmap_get_device(data->regmap);
+
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+	return 0;
+}
+
+static const struct iio_buffer_setup_ops bme680_buffer_setup_ops = {
+	.preenable = bme680_buffer_preenable,
+	.postdisable = bme680_buffer_postdisable,
+};
+
 int bme680_core_probe(struct device *dev, struct regmap *regmap,
 		      const char *name)
 {
@@ -1114,6 +1180,14 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap,
 	data->heater_dur = 150;  /* milliseconds */
 	data->preheat_curr_mA = 0;
 
+	ret = devm_regulator_bulk_get_enable(dev, ARRAY_SIZE(bme680_supply_names),
+					     bme680_supply_names);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get and enable supplies.\n");
+
+	fsleep(BME680_STARTUP_TIME_US);
+
 	ret = regmap_write(regmap, BME680_REG_SOFT_RESET, BME680_CMD_SOFTRESET);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to reset chip\n");
@@ -1149,15 +1223,47 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap,
 	ret = devm_iio_triggered_buffer_setup(dev, indio_dev,
 					      iio_pollfunc_store_time,
 					      bme680_trigger_handler,
-					      NULL);
+					      &bme680_buffer_setup_ops);
 	if (ret)
 		return dev_err_probe(dev, ret,
 				     "iio triggered buffer setup failed\n");
 
+	/* Enable runtime PM */
+	pm_runtime_set_autosuspend_delay(dev, BME680_STARTUP_TIME_US);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_active(dev);
+	ret = devm_pm_runtime_enable(dev);
+	if (ret)
+		return ret;
+
 	return devm_iio_device_register(dev, indio_dev);
 }
 EXPORT_SYMBOL_NS_GPL(bme680_core_probe, "IIO_BME680");
 
+static int bme680_runtime_suspend(struct device *dev)
+{
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
+	struct bme680_data *data = iio_priv(indio_dev);
+
+	return bme680_set_mode(data, BME680_MODE_SLEEP);
+}
+
+static int bme680_runtime_resume(struct device *dev)
+{
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
+	struct bme680_data *data = iio_priv(indio_dev);
+	int ret;
+
+	ret = bme680_chip_config(data);
+	if (ret)
+		return ret;
+
+	return bme680_gas_config(data);
+}
+
+EXPORT_RUNTIME_DEV_PM_OPS(bme680_dev_pm_ops, bme680_runtime_suspend,
+			  bme680_runtime_resume, NULL);
+
 MODULE_AUTHOR("Himanshu Jha <himanshujha199640@gmail.com>");
 MODULE_DESCRIPTION("Bosch BME680 Driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/chemical/bme680_i2c.c b/drivers/iio/chemical/bme680_i2c.c
index 7a949228b4a6..ac7763f98a6a 100644
--- a/drivers/iio/chemical/bme680_i2c.c
+++ b/drivers/iio/chemical/bme680_i2c.c
@@ -51,6 +51,7 @@ static struct i2c_driver bme680_i2c_driver = {
 	.driver = {
 		.name			= "bme680_i2c",
 		.of_match_table		= bme680_of_i2c_match,
+		.pm = pm_ptr(&bme680_dev_pm_ops),
 	},
 	.probe = bme680_i2c_probe,
 	.id_table = bme680_i2c_id,
diff --git a/drivers/iio/chemical/bme680_spi.c b/drivers/iio/chemical/bme680_spi.c
index 3916a51ba68e..ecb24ba0ebc9 100644
--- a/drivers/iio/chemical/bme680_spi.c
+++ b/drivers/iio/chemical/bme680_spi.c
@@ -154,6 +154,7 @@ static struct spi_driver bme680_spi_driver = {
 	.driver = {
 		.name			= "bme680_spi",
 		.of_match_table		= bme680_of_spi_match,
+		.pm = pm_ptr(&bme680_dev_pm_ops),
 	},
 	.probe = bme680_spi_probe,
 	.id_table = bme680_spi_id,
diff --git a/drivers/iio/chemical/ccs811.c b/drivers/iio/chemical/ccs811.c
index 17d1bc518bf2..451fb65dbe60 100644
--- a/drivers/iio/chemical/ccs811.c
+++ b/drivers/iio/chemical/ccs811.c
@@ -81,7 +81,7 @@ struct ccs811_data {
 	/* Ensures correct alignment of timestamp if present */
 	struct {
 		s16 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/chemical/ens160_core.c b/drivers/iio/chemical/ens160_core.c
index 4a89cd5894d9..48d5ad2075b6 100644
--- a/drivers/iio/chemical/ens160_core.c
+++ b/drivers/iio/chemical/ens160_core.c
@@ -60,7 +60,7 @@ struct ens160_data {
 	struct mutex mutex;
 	struct {
 		__le16 chans[2];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan __aligned(IIO_DMA_MINALIGN);
 	u8 fw_version[3];
 	__le16 buf;
diff --git a/drivers/iio/chemical/scd30_core.c b/drivers/iio/chemical/scd30_core.c
index ac3080929f0b..d613c54cb28d 100644
--- a/drivers/iio/chemical/scd30_core.c
+++ b/drivers/iio/chemical/scd30_core.c
@@ -594,7 +594,7 @@ static irqreturn_t scd30_trigger_handler(int irq, void *p)
 	struct scd30_state *state = iio_priv(indio_dev);
 	struct {
 		int data[SCD30_MEAS_COUNT];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	int ret;
 
diff --git a/drivers/iio/chemical/scd4x.c b/drivers/iio/chemical/scd4x.c
index 52cad54e8572..50e3ac44422b 100644
--- a/drivers/iio/chemical/scd4x.c
+++ b/drivers/iio/chemical/scd4x.c
@@ -665,7 +665,7 @@ static irqreturn_t scd4x_trigger_handler(int irq, void *p)
 	struct scd4x_state *state = iio_priv(indio_dev);
 	struct {
 		uint16_t data[3];
-		int64_t ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	int ret;
 
diff --git a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c
index c081b5caa475..97526ba87b93 100644
--- a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c
+++ b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c
@@ -109,8 +109,8 @@ static bool inv_update_chip_period(struct inv_sensors_timestamp *ts,
 
 static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts)
 {
-	const int64_t period_min = ts->min_period * ts->mult;
-	const int64_t period_max = ts->max_period * ts->mult;
+	const int64_t period_min = (int64_t)ts->min_period * ts->mult;
+	const int64_t period_max = (int64_t)ts->max_period * ts->mult;
 	int64_t add_max, sub_max;
 	int64_t delta, jitter;
 	int64_t adjust;
diff --git a/drivers/iio/common/ssp_sensors/ssp_iio.c b/drivers/iio/common/ssp_sensors/ssp_iio.c
index caa404edd9d0..78ac689de2fe 100644
--- a/drivers/iio/common/ssp_sensors/ssp_iio.c
+++ b/drivers/iio/common/ssp_sensors/ssp_iio.c
@@ -8,6 +8,8 @@
 #include <linux/iio/kfifo_buf.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/unaligned.h>
+#include <linux/units.h>
 #include "ssp_iio_sensor.h"
 
 /**
@@ -70,8 +72,7 @@ EXPORT_SYMBOL_NS(ssp_common_buffer_postdisable, "IIO_SSP_SENSORS");
 int ssp_common_process_data(struct iio_dev *indio_dev, void *buf,
 			    unsigned int len, int64_t timestamp)
 {
-	__le32 time;
-	int64_t calculated_time = 0;
+	int64_t calculated_time;
 	struct ssp_sensor_data *spd = iio_priv(indio_dev);
 
 	if (indio_dev->scan_bytes == 0)
@@ -82,11 +83,8 @@ int ssp_common_process_data(struct iio_dev *indio_dev, void *buf,
 	 */
 	memcpy(spd->buffer, buf, len);
 
-	if (indio_dev->scan_timestamp) {
-		memcpy(&time, &((char *)buf)[len], SSP_TIME_SIZE);
-		calculated_time =
-			timestamp + (int64_t)le32_to_cpu(time) * 1000000;
-	}
+	calculated_time = timestamp +
+		(int64_t)get_unaligned_le32(buf + len) * MEGA;
 
 	return iio_push_to_buffers_with_timestamp(indio_dev, spd->buffer,
 						  calculated_time);
diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig
index 5d01ba4edbf3..5690a37267d8 100644
--- a/drivers/iio/dac/Kconfig
+++ b/drivers/iio/dac/Kconfig
@@ -80,7 +80,7 @@ config AD5421
 	depends on SPI
 	help
 	  Say yes here to build support for Analog Devices AD5421 loop-powered
-	  digital-to-analog convertors (DAC).
+	  digital-to-analog converters (DAC).
 
 	  To compile this driver as module choose M here: the module will be called
 	  ad5421.
@@ -348,6 +348,14 @@ config AD8801
 	  To compile this driver as a module choose M here: the module will be called
 	  ad8801.
 
+config BD79703
+	tristate "ROHM Semiconductor BD79703 DAC driver"
+	depends on SPI
+	select REGMAP_SPI
+	help
+	  Say yes here to build support for ROHM Semiconductor BD79703 Digital
+	  to Analog Converter (DAC).
+
 config CIO_DAC
 	tristate "Measurement Computing CIO-DAC IIO driver"
 	depends on X86 && (ISA_BUS || PC104)
diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile
index 414c152be779..8dd6cce81ed1 100644
--- a/drivers/iio/dac/Makefile
+++ b/drivers/iio/dac/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_AD8460) += ad8460.o
 obj-$(CONFIG_AD8801) += ad8801.o
 obj-$(CONFIG_AD9739A) += ad9739a.o
 obj-$(CONFIG_ADI_AXI_DAC) += adi-axi-dac.o
+obj-$(CONFIG_BD79703) += rohm-bd79703.o
 obj-$(CONFIG_CIO_DAC) += cio-dac.o
 obj-$(CONFIG_DPOT_DAC) += dpot-dac.o
 obj-$(CONFIG_DS4424) += ds4424.o
diff --git a/drivers/iio/dac/ad3552r-common.c b/drivers/iio/dac/ad3552r-common.c
index 0f495df2e5ce..03e0864f5084 100644
--- a/drivers/iio/dac/ad3552r-common.c
+++ b/drivers/iio/dac/ad3552r-common.c
@@ -22,11 +22,10 @@ EXPORT_SYMBOL_NS_GPL(ad3552r_ch_ranges, "IIO_AD3552R");
 
 const s32 ad3542r_ch_ranges[AD3542R_MAX_RANGES][2] = {
 	[AD3542R_CH_OUTPUT_RANGE_0__2P5V]	= { 0, 2500 },
-	[AD3542R_CH_OUTPUT_RANGE_0__3V]		= { 0, 3000 },
 	[AD3542R_CH_OUTPUT_RANGE_0__5V]		= { 0, 5000 },
 	[AD3542R_CH_OUTPUT_RANGE_0__10V]	= { 0, 10000 },
-	[AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V]	= { -2500, 7500 },
-	[AD3542R_CH_OUTPUT_RANGE_NEG_5__5V]	= { -5000, 5000 }
+	[AD3542R_CH_OUTPUT_RANGE_NEG_5__5V]	= { -5000, 5000 },
+	[AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V]	= { -2500, 7500 }
 };
 EXPORT_SYMBOL_NS_GPL(ad3542r_ch_ranges, "IIO_AD3552R");
 
diff --git a/drivers/iio/dac/ad3552r-hs.c b/drivers/iio/dac/ad3552r-hs.c
index 216c634f3eaf..8974df625670 100644
--- a/drivers/iio/dac/ad3552r-hs.c
+++ b/drivers/iio/dac/ad3552r-hs.c
@@ -329,6 +329,12 @@ static int ad3552r_hs_setup(struct ad3552r_hs_state *st)
 		dev_info(st->dev, "Chip ID error. Expected 0x%x, Read 0x%x\n",
 			 AD3552R_ID, id);
 
+	/* Clear reset error flag, see ad3552r manual, rev B table 38. */
+	ret = st->data->bus_reg_write(st->back, AD3552R_REG_ADDR_ERR_STATUS,
+				      AD3552R_MASK_RESET_STATUS, 1);
+	if (ret)
+		return ret;
+
 	ret = st->data->bus_reg_write(st->back,
 				      AD3552R_REG_ADDR_SH_REFERENCE_CONFIG,
 				      0, 1);
diff --git a/drivers/iio/dac/ad3552r.h b/drivers/iio/dac/ad3552r.h
index fd5a3dfd1d1c..4b5581039ae9 100644
--- a/drivers/iio/dac/ad3552r.h
+++ b/drivers/iio/dac/ad3552r.h
@@ -131,7 +131,7 @@
 #define AD3552R_CH1_ACTIVE				BIT(1)
 
 #define AD3552R_MAX_RANGES	5
-#define AD3542R_MAX_RANGES	6
+#define AD3542R_MAX_RANGES	5
 #define AD3552R_QUAD_SPI	2
 
 extern const s32 ad3552r_ch_ranges[AD3552R_MAX_RANGES][2];
@@ -189,16 +189,14 @@ enum ad3552r_ch_vref_select {
 enum ad3542r_ch_output_range {
 	/* Range from 0 V to 2.5 V. Requires Rfb1x connection */
 	AD3542R_CH_OUTPUT_RANGE_0__2P5V,
-	/* Range from 0 V to 3 V. Requires Rfb1x connection  */
-	AD3542R_CH_OUTPUT_RANGE_0__3V,
 	/* Range from 0 V to 5 V. Requires Rfb1x connection  */
 	AD3542R_CH_OUTPUT_RANGE_0__5V,
 	/* Range from 0 V to 10 V. Requires Rfb2x connection  */
 	AD3542R_CH_OUTPUT_RANGE_0__10V,
-	/* Range from -2.5 V to 7.5 V. Requires Rfb2x connection  */
-	AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V,
 	/* Range from -5 V to 5 V. Requires Rfb2x connection  */
 	AD3542R_CH_OUTPUT_RANGE_NEG_5__5V,
+	/* Range from -2.5 V to 7.5 V. Requires Rfb2x connection  */
+	AD3542R_CH_OUTPUT_RANGE_NEG_2P5__7P5V,
 };
 
 enum ad3552r_ch_output_range {
diff --git a/drivers/iio/dac/ad5624r.h b/drivers/iio/dac/ad5624r.h
index 14a439b06eb6..098fb5a7683d 100644
--- a/drivers/iio/dac/ad5624r.h
+++ b/drivers/iio/dac/ad5624r.h
@@ -41,11 +41,9 @@ struct ad5624r_chip_info {
 };
 
 /**
- * struct ad5446_state - driver instance specific data
- * @indio_dev:		the industrial I/O device
+ * struct ad5624r_state - driver instance specific data
  * @us:			spi_device
  * @chip_info:		chip model specific constants, available modes etc
- * @reg:		supply regulator
  * @vref_mv:		actual reference voltage used
  * @pwr_down_mask	power down mask
  * @pwr_down_mode	current power down mode
diff --git a/drivers/iio/dac/ad5686-spi.c b/drivers/iio/dac/ad5686-spi.c
index 39b5dad0d6a5..9c727aa6ea18 100644
--- a/drivers/iio/dac/ad5686-spi.c
+++ b/drivers/iio/dac/ad5686-spi.c
@@ -95,11 +95,6 @@ static int ad5686_spi_probe(struct spi_device *spi)
 			    ad5686_spi_write, ad5686_spi_read);
 }
 
-static void ad5686_spi_remove(struct spi_device *spi)
-{
-	ad5686_remove(&spi->dev);
-}
-
 static const struct spi_device_id ad5686_spi_id[] = {
 	{"ad5310r", ID_AD5310R},
 	{"ad5672r", ID_AD5672R},
@@ -126,7 +121,6 @@ static struct spi_driver ad5686_spi_driver = {
 		.name = "ad5686",
 	},
 	.probe = ad5686_spi_probe,
-	.remove = ad5686_spi_remove,
 	.id_table = ad5686_spi_id,
 };
 
diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c
index 8dc578b08784..763af690c444 100644
--- a/drivers/iio/dac/ad5686.c
+++ b/drivers/iio/dac/ad5686.c
@@ -455,39 +455,28 @@ int ad5686_probe(struct device *dev,
 	struct ad5686_state *st;
 	struct iio_dev *indio_dev;
 	unsigned int val, ref_bit_msk;
+	bool has_external_vref;
 	u8 cmd;
-	int ret, i, voltage_uv = 0;
+	int ret, i;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*st));
 	if (indio_dev == NULL)
 		return  -ENOMEM;
 
 	st = iio_priv(indio_dev);
-	dev_set_drvdata(dev, indio_dev);
 
 	st->dev = dev;
 	st->write = write;
 	st->read = read;
 
-	st->reg = devm_regulator_get_optional(dev, "vcc");
-	if (!IS_ERR(st->reg)) {
-		ret = regulator_enable(st->reg);
-		if (ret)
-			return ret;
-
-		ret = regulator_get_voltage(st->reg);
-		if (ret < 0)
-			goto error_disable_reg;
-
-		voltage_uv = ret;
-	}
-
 	st->chip_info = &ad5686_chip_info_tbl[chip_type];
 
-	if (voltage_uv)
-		st->vref_mv = voltage_uv / 1000;
-	else
-		st->vref_mv = st->chip_info->int_vref_mv;
+	ret = devm_regulator_get_enable_read_voltage(dev, "vcc");
+	if (ret < 0 && ret != -ENODEV)
+		return ret;
+
+	has_external_vref = ret != -ENODEV;
+	st->vref_mv = has_external_vref ? ret / 1000 : st->chip_info->int_vref_mv;
 
 	/* Set all the power down mode for all channels to 1K pulldown */
 	for (i = 0; i < st->chip_info->num_channels; i++)
@@ -505,12 +494,12 @@ int ad5686_probe(struct device *dev,
 	case AD5310_REGMAP:
 		cmd = AD5686_CMD_CONTROL_REG;
 		ref_bit_msk = AD5310_REF_BIT_MSK;
-		st->use_internal_vref = !voltage_uv;
+		st->use_internal_vref = !has_external_vref;
 		break;
 	case AD5683_REGMAP:
 		cmd = AD5686_CMD_CONTROL_REG;
 		ref_bit_msk = AD5683_REF_BIT_MSK;
-		st->use_internal_vref = !voltage_uv;
+		st->use_internal_vref = !has_external_vref;
 		break;
 	case AD5686_REGMAP:
 		cmd = AD5686_CMD_INTERNAL_REFER_SETUP;
@@ -519,43 +508,22 @@ int ad5686_probe(struct device *dev,
 	case AD5693_REGMAP:
 		cmd = AD5686_CMD_CONTROL_REG;
 		ref_bit_msk = AD5693_REF_BIT_MSK;
-		st->use_internal_vref = !voltage_uv;
+		st->use_internal_vref = !has_external_vref;
 		break;
 	default:
-		ret = -EINVAL;
-		goto error_disable_reg;
+		return -EINVAL;
 	}
 
-	val = (voltage_uv | ref_bit_msk);
+	val = (has_external_vref | ref_bit_msk);
 
 	ret = st->write(st, cmd, 0, !!val);
 	if (ret)
-		goto error_disable_reg;
-
-	ret = iio_device_register(indio_dev);
-	if (ret)
-		goto error_disable_reg;
-
-	return 0;
+		return ret;
 
-error_disable_reg:
-	if (!IS_ERR(st->reg))
-		regulator_disable(st->reg);
-	return ret;
+	return devm_iio_device_register(dev, indio_dev);
 }
 EXPORT_SYMBOL_NS_GPL(ad5686_probe, "IIO_AD5686");
 
-void ad5686_remove(struct device *dev)
-{
-	struct iio_dev *indio_dev = dev_get_drvdata(dev);
-	struct ad5686_state *st = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-	if (!IS_ERR(st->reg))
-		regulator_disable(st->reg);
-}
-EXPORT_SYMBOL_NS_GPL(ad5686_remove, "IIO_AD5686");
-
 MODULE_AUTHOR("Michael Hennerich <michael.hennerich@analog.com>");
 MODULE_DESCRIPTION("Analog Devices AD5686/85/84 DAC");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/dac/ad5686.h b/drivers/iio/dac/ad5686.h
index 760f852911df..e7d36bae3e59 100644
--- a/drivers/iio/dac/ad5686.h
+++ b/drivers/iio/dac/ad5686.h
@@ -115,10 +115,9 @@ struct ad5686_chip_info {
 };
 
 /**
- * struct ad5446_state - driver instance specific data
+ * struct ad5686_state - driver instance specific data
  * @spi:		spi_device
  * @chip_info:		chip model specific constants, available modes etc
- * @reg:		supply regulator
  * @vref_mv:		actual reference voltage used
  * @pwr_down_mask:	power down mask
  * @pwr_down_mode:	current power down mode
@@ -130,7 +129,6 @@ struct ad5686_chip_info {
 struct ad5686_state {
 	struct device			*dev;
 	const struct ad5686_chip_info	*chip_info;
-	struct regulator		*reg;
 	unsigned short			vref_mv;
 	unsigned int			pwr_down_mask;
 	unsigned int			pwr_down_mode;
@@ -157,7 +155,5 @@ int ad5686_probe(struct device *dev,
 		 const char *name, ad5686_write_func write,
 		 ad5686_read_func read);
 
-void ad5686_remove(struct device *dev);
-
 
 #endif /* __DRIVERS_IIO_DAC_AD5686_H__ */
diff --git a/drivers/iio/dac/ad5696-i2c.c b/drivers/iio/dac/ad5696-i2c.c
index bbcda246c547..0156f32c12c8 100644
--- a/drivers/iio/dac/ad5696-i2c.c
+++ b/drivers/iio/dac/ad5696-i2c.c
@@ -65,11 +65,6 @@ static int ad5686_i2c_probe(struct i2c_client *i2c)
 			    ad5686_i2c_write, ad5686_i2c_read);
 }
 
-static void ad5686_i2c_remove(struct i2c_client *i2c)
-{
-	ad5686_remove(&i2c->dev);
-}
-
 static const struct i2c_device_id ad5686_i2c_id[] = {
 	{"ad5311r", ID_AD5311R},
 	{"ad5337r", ID_AD5337R},
@@ -116,7 +111,6 @@ static struct i2c_driver ad5686_i2c_driver = {
 		.of_match_table = ad5686_of_match,
 	},
 	.probe = ad5686_i2c_probe,
-	.remove = ad5686_i2c_remove,
 	.id_table = ad5686_i2c_id,
 };
 
diff --git a/drivers/iio/dac/ad7293.c b/drivers/iio/dac/ad7293.c
index 1d4032670482..d3f49b5337d2 100644
--- a/drivers/iio/dac/ad7293.c
+++ b/drivers/iio/dac/ad7293.c
@@ -141,8 +141,6 @@ struct ad7293_state {
 	/* Protect against concurrent accesses to the device, page selection and data content */
 	struct mutex lock;
 	struct gpio_desc *gpio_reset;
-	struct regulator *reg_avdd;
-	struct regulator *reg_vdrive;
 	u8 page_select;
 	u8 data[3] __aligned(IIO_DMA_MINALIGN);
 };
@@ -777,6 +775,15 @@ static int ad7293_reset(struct ad7293_state *st)
 static int ad7293_properties_parse(struct ad7293_state *st)
 {
 	struct spi_device *spi = st->spi;
+	int ret;
+
+	ret = devm_regulator_get_enable(&spi->dev, "avdd");
+	if (ret)
+		return dev_err_probe(&spi->dev, ret, "failed to enable AVDD\n");
+
+	ret = devm_regulator_get_enable(&spi->dev, "vdrive");
+	if (ret)
+		return dev_err_probe(&spi->dev, ret, "failed to enable VDRIVE\n");
 
 	st->gpio_reset = devm_gpiod_get_optional(&st->spi->dev, "reset",
 						 GPIOD_OUT_HIGH);
@@ -784,24 +791,9 @@ static int ad7293_properties_parse(struct ad7293_state *st)
 		return dev_err_probe(&spi->dev, PTR_ERR(st->gpio_reset),
 				     "failed to get the reset GPIO\n");
 
-	st->reg_avdd = devm_regulator_get(&spi->dev, "avdd");
-	if (IS_ERR(st->reg_avdd))
-		return dev_err_probe(&spi->dev, PTR_ERR(st->reg_avdd),
-				     "failed to get the AVDD voltage\n");
-
-	st->reg_vdrive = devm_regulator_get(&spi->dev, "vdrive");
-	if (IS_ERR(st->reg_vdrive))
-		return dev_err_probe(&spi->dev, PTR_ERR(st->reg_vdrive),
-				     "failed to get the VDRIVE voltage\n");
-
 	return 0;
 }
 
-static void ad7293_reg_disable(void *data)
-{
-	regulator_disable(data);
-}
-
 static int ad7293_init(struct ad7293_state *st)
 {
 	int ret;
@@ -816,48 +808,6 @@ static int ad7293_init(struct ad7293_state *st)
 	if (ret)
 		return ret;
 
-	ret = regulator_enable(st->reg_avdd);
-	if (ret) {
-		dev_err(&spi->dev,
-			"Failed to enable specified AVDD Voltage!\n");
-		return ret;
-	}
-
-	ret = devm_add_action_or_reset(&spi->dev, ad7293_reg_disable,
-				       st->reg_avdd);
-	if (ret)
-		return ret;
-
-	ret = regulator_enable(st->reg_vdrive);
-	if (ret) {
-		dev_err(&spi->dev,
-			"Failed to enable specified VDRIVE Voltage!\n");
-		return ret;
-	}
-
-	ret = devm_add_action_or_reset(&spi->dev, ad7293_reg_disable,
-				       st->reg_vdrive);
-	if (ret)
-		return ret;
-
-	ret = regulator_get_voltage(st->reg_avdd);
-	if (ret < 0) {
-		dev_err(&spi->dev, "Failed to read avdd regulator: %d\n", ret);
-		return ret;
-	}
-
-	if (ret > 5500000 || ret < 4500000)
-		return -EINVAL;
-
-	ret = regulator_get_voltage(st->reg_vdrive);
-	if (ret < 0) {
-		dev_err(&spi->dev,
-			"Failed to read vdrive regulator: %d\n", ret);
-		return ret;
-	}
-	if (ret > 5500000 || ret < 1700000)
-		return -EINVAL;
-
 	/* Check Chip ID */
 	ret = __ad7293_spi_read(st, AD7293_REG_DEVICE_ID, &chip_id);
 	if (ret)
diff --git a/drivers/iio/dac/ad8801.c b/drivers/iio/dac/ad8801.c
index 919e8c880697..8a362fae2eca 100644
--- a/drivers/iio/dac/ad8801.c
+++ b/drivers/iio/dac/ad8801.c
@@ -23,8 +23,6 @@ struct ad8801_state {
 	unsigned char dac_cache[8]; /* Value write on each channel */
 	unsigned int vrefh_mv;
 	unsigned int vrefl_mv;
-	struct regulator *vrefh_reg;
-	struct regulator *vrefl_reg;
 
 	__be16 data __aligned(IIO_DMA_MINALIGN);
 };
@@ -122,86 +120,34 @@ static int ad8801_probe(struct spi_device *spi)
 	state->spi = spi;
 	id = spi_get_device_id(spi);
 
-	state->vrefh_reg = devm_regulator_get(&spi->dev, "vrefh");
-	if (IS_ERR(state->vrefh_reg))
-		return dev_err_probe(&spi->dev, PTR_ERR(state->vrefh_reg),
-				     "Vrefh regulator not specified\n");
+	ret = devm_regulator_get_enable_read_voltage(&spi->dev, "vrefh");
+	if (ret < 0)
+		return dev_err_probe(&spi->dev, ret,
+				     "failed to get Vrefh voltage\n");
 
-	ret = regulator_enable(state->vrefh_reg);
-	if (ret) {
-		dev_err(&spi->dev, "Failed to enable vrefh regulator: %d\n",
-				ret);
-		return ret;
-	}
-
-	ret = regulator_get_voltage(state->vrefh_reg);
-	if (ret < 0) {
-		dev_err(&spi->dev, "Failed to read vrefh regulator: %d\n",
-				ret);
-		goto error_disable_vrefh_reg;
-	}
 	state->vrefh_mv = ret / 1000;
 
 	if (id->driver_data == ID_AD8803) {
-		state->vrefl_reg = devm_regulator_get(&spi->dev, "vrefl");
-		if (IS_ERR(state->vrefl_reg)) {
-			ret = dev_err_probe(&spi->dev, PTR_ERR(state->vrefl_reg),
-					    "Vrefl regulator not specified\n");
-			goto error_disable_vrefh_reg;
-		}
-
-		ret = regulator_enable(state->vrefl_reg);
-		if (ret) {
-			dev_err(&spi->dev, "Failed to enable vrefl regulator: %d\n",
-					ret);
-			goto error_disable_vrefh_reg;
-		}
-
-		ret = regulator_get_voltage(state->vrefl_reg);
-		if (ret < 0) {
-			dev_err(&spi->dev, "Failed to read vrefl regulator: %d\n",
-					ret);
-			goto error_disable_vrefl_reg;
-		}
+		ret = devm_regulator_get_enable_read_voltage(&spi->dev, "vrefl");
+		if (ret < 0)
+			return dev_err_probe(&spi->dev, ret,
+					     "failed to get Vrefl voltage\n");
+
 		state->vrefl_mv = ret / 1000;
-	} else {
-		state->vrefl_mv = 0;
-		state->vrefl_reg = NULL;
 	}
 
-	spi_set_drvdata(spi, indio_dev);
 	indio_dev->info = &ad8801_info;
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	indio_dev->channels = ad8801_channels;
 	indio_dev->num_channels = ARRAY_SIZE(ad8801_channels);
 	indio_dev->name = id->name;
 
-	ret = iio_device_register(indio_dev);
-	if (ret) {
-		dev_err(&spi->dev, "Failed to register iio device: %d\n",
-				ret);
-		goto error_disable_vrefl_reg;
-	}
+	ret = devm_iio_device_register(&spi->dev, indio_dev);
+	if (ret)
+		return dev_err_probe(&spi->dev, ret,
+				     "Failed to register iio device\n");
 
 	return 0;
-
-error_disable_vrefl_reg:
-	if (state->vrefl_reg)
-		regulator_disable(state->vrefl_reg);
-error_disable_vrefh_reg:
-	regulator_disable(state->vrefh_reg);
-	return ret;
-}
-
-static void ad8801_remove(struct spi_device *spi)
-{
-	struct iio_dev *indio_dev = spi_get_drvdata(spi);
-	struct ad8801_state *state = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-	if (state->vrefl_reg)
-		regulator_disable(state->vrefl_reg);
-	regulator_disable(state->vrefh_reg);
 }
 
 static const struct spi_device_id ad8801_ids[] = {
@@ -216,7 +162,6 @@ static struct spi_driver ad8801_driver = {
 		.name	= "ad8801",
 	},
 	.probe		= ad8801_probe,
-	.remove		= ad8801_remove,
 	.id_table	= ad8801_ids,
 };
 module_spi_driver(ad8801_driver);
diff --git a/drivers/iio/dac/ltc2632.c b/drivers/iio/dac/ltc2632.c
index a4fb2509c950..999348836d87 100644
--- a/drivers/iio/dac/ltc2632.c
+++ b/drivers/iio/dac/ltc2632.c
@@ -41,13 +41,11 @@ struct ltc2632_chip_info {
  * @spi_dev:			pointer to the spi_device struct
  * @powerdown_cache_mask:	used to show current channel powerdown state
  * @vref_mv:			used reference voltage (internal or external)
- * @vref_reg:		regulator for the reference voltage
  */
 struct ltc2632_state {
 	struct spi_device *spi_dev;
 	unsigned int powerdown_cache_mask;
 	int vref_mv;
-	struct regulator *vref_reg;
 };
 
 enum ltc2632_supported_device_ids {
@@ -310,6 +308,7 @@ static int ltc2632_probe(struct spi_device *spi)
 	struct ltc2632_state *st;
 	struct iio_dev *indio_dev;
 	struct ltc2632_chip_info *chip_info;
+	bool has_external_vref;
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st));
@@ -318,49 +317,31 @@ static int ltc2632_probe(struct spi_device *spi)
 
 	st = iio_priv(indio_dev);
 
-	spi_set_drvdata(spi, indio_dev);
 	st->spi_dev = spi;
 
 	chip_info = (struct ltc2632_chip_info *)
 			spi_get_device_id(spi)->driver_data;
 
-	st->vref_reg = devm_regulator_get_optional(&spi->dev, "vref");
-	if (PTR_ERR(st->vref_reg) == -ENODEV) {
-		/* use internal reference voltage */
-		st->vref_reg = NULL;
-		st->vref_mv = chip_info->vref_mv;
+	ret = devm_regulator_get_enable_read_voltage(&spi->dev, "vref");
+	if (ret < 0 && ret != -ENODEV)
+		return dev_err_probe(&spi->dev, ret,
+				     "Failed to get vref regulator voltage\n");
 
-		ret = ltc2632_spi_write(spi, LTC2632_CMD_INTERNAL_REFER,
-				0, 0, 0);
-		if (ret) {
-			dev_err(&spi->dev,
-				"Set internal reference command failed, %d\n",
-				ret);
-			return ret;
-		}
-	} else if (IS_ERR(st->vref_reg)) {
-		dev_err(&spi->dev,
-				"Error getting voltage reference regulator\n");
-		return PTR_ERR(st->vref_reg);
-	} else {
-		/* use external reference voltage */
-		ret = regulator_enable(st->vref_reg);
-		if (ret) {
-			dev_err(&spi->dev,
-				"enable reference regulator failed, %d\n",
-				ret);
-			return ret;
-		}
-		st->vref_mv = regulator_get_voltage(st->vref_reg) / 1000;
+	has_external_vref = ret != -ENODEV;
+	st->vref_mv = has_external_vref ? ret / 1000 : chip_info->vref_mv;
 
+	if (has_external_vref) {
 		ret = ltc2632_spi_write(spi, LTC2632_CMD_EXTERNAL_REFER,
-				0, 0, 0);
-		if (ret) {
-			dev_err(&spi->dev,
-				"Set external reference command failed, %d\n",
-				ret);
-			return ret;
-		}
+					0, 0, 0);
+		if (ret)
+			return dev_err_probe(&spi->dev, ret,
+				"Set external reference command failed\n");
+	} else {
+		ret = ltc2632_spi_write(spi, LTC2632_CMD_INTERNAL_REFER,
+					0, 0, 0);
+		if (ret)
+			return dev_err_probe(&spi->dev, ret,
+				"Set internal reference command failed\n");
 	}
 
 	indio_dev->name = fwnode_get_name(dev_fwnode(&spi->dev)) ?: spi_get_device_id(spi)->name;
@@ -369,18 +350,7 @@ static int ltc2632_probe(struct spi_device *spi)
 	indio_dev->channels = chip_info->channels;
 	indio_dev->num_channels = chip_info->num_channels;
 
-	return iio_device_register(indio_dev);
-}
-
-static void ltc2632_remove(struct spi_device *spi)
-{
-	struct iio_dev *indio_dev = spi_get_drvdata(spi);
-	struct ltc2632_state *st = iio_priv(indio_dev);
-
-	iio_device_unregister(indio_dev);
-
-	if (st->vref_reg)
-		regulator_disable(st->vref_reg);
+	return devm_iio_device_register(&spi->dev, indio_dev);
 }
 
 static const struct spi_device_id ltc2632_id[] = {
@@ -472,7 +442,6 @@ static struct spi_driver ltc2632_driver = {
 		.of_match_table = ltc2632_of_match,
 	},
 	.probe		= ltc2632_probe,
-	.remove		= ltc2632_remove,
 	.id_table	= ltc2632_id,
 };
 module_spi_driver(ltc2632_driver);
diff --git a/drivers/iio/dac/ltc2688.c b/drivers/iio/dac/ltc2688.c
index 376dca163c91..bdc857c7fa6d 100644
--- a/drivers/iio/dac/ltc2688.c
+++ b/drivers/iio/dac/ltc2688.c
@@ -842,7 +842,7 @@ static int ltc2688_channel_config(struct ltc2688_state *st)
 	return 0;
 }
 
-static int ltc2688_setup(struct ltc2688_state *st, struct regulator *vref)
+static int ltc2688_setup(struct ltc2688_state *st, bool has_external_vref)
 {
 	struct device *dev = &st->spi->dev;
 	struct gpio_desc *gpio;
@@ -881,18 +881,13 @@ static int ltc2688_setup(struct ltc2688_state *st, struct regulator *vref)
 	if (ret)
 		return ret;
 
-	if (!vref)
+	if (!has_external_vref)
 		return 0;
 
 	return regmap_set_bits(st->regmap, LTC2688_CMD_CONFIG,
 			       LTC2688_CONFIG_EXT_REF);
 }
 
-static void ltc2688_disable_regulator(void *regulator)
-{
-	regulator_disable(regulator);
-}
-
 static bool ltc2688_reg_readable(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -947,8 +942,8 @@ static int ltc2688_probe(struct spi_device *spi)
 	static const char * const regulators[] = { "vcc", "iovcc" };
 	struct ltc2688_state *st;
 	struct iio_dev *indio_dev;
-	struct regulator *vref_reg;
 	struct device *dev = &spi->dev;
+	bool has_external_vref;
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*st));
@@ -973,34 +968,15 @@ static int ltc2688_probe(struct spi_device *spi)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to enable regulators\n");
 
-	vref_reg = devm_regulator_get_optional(dev, "vref");
-	if (IS_ERR(vref_reg)) {
-		if (PTR_ERR(vref_reg) != -ENODEV)
-			return dev_err_probe(dev, PTR_ERR(vref_reg),
-					     "Failed to get vref regulator");
-
-		vref_reg = NULL;
-		/* internal reference */
-		st->vref = 4096;
-	} else {
-		ret = regulator_enable(vref_reg);
-		if (ret)
-			return dev_err_probe(dev, ret,
-					     "Failed to enable vref regulators\n");
-
-		ret = devm_add_action_or_reset(dev, ltc2688_disable_regulator,
-					       vref_reg);
-		if (ret)
-			return ret;
-
-		ret = regulator_get_voltage(vref_reg);
-		if (ret < 0)
-			return dev_err_probe(dev, ret, "Failed to get vref\n");
+	ret = devm_regulator_get_enable_read_voltage(dev, "vref");
+	if (ret < 0 && ret != -ENODEV)
+		return dev_err_probe(dev, ret,
+				     "Failed to get vref regulator voltage\n");
 
-		st->vref = ret / 1000;
-	}
+	has_external_vref = ret != -ENODEV;
+	st->vref = has_external_vref ? ret / 1000 : 0;
 
-	ret = ltc2688_setup(st, vref_reg);
+	ret = ltc2688_setup(st, has_external_vref);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/dac/max5821.c b/drivers/iio/dac/max5821.c
index 18ba3eaaad75..b062a18be5e7 100644
--- a/drivers/iio/dac/max5821.c
+++ b/drivers/iio/dac/max5821.c
@@ -32,7 +32,6 @@ enum max5821_device_ids {
 
 struct max5821_data {
 	struct i2c_client	*client;
-	struct regulator	*vref_reg;
 	unsigned short		vref_mv;
 	bool			powerdown[MAX5821_MAX_DAC_CHANNELS];
 	u8			powerdown_mode[MAX5821_MAX_DAC_CHANNELS];
@@ -295,11 +294,6 @@ static const struct iio_info max5821_info = {
 	.write_raw = max5821_write_raw,
 };
 
-static void max5821_regulator_disable(void *reg)
-{
-	regulator_disable(reg);
-}
-
 static int max5821_probe(struct i2c_client *client)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
@@ -321,32 +315,10 @@ static int max5821_probe(struct i2c_client *client)
 		data->powerdown_mode[tmp] = MAX5821_100KOHM_TO_GND;
 	}
 
-	data->vref_reg = devm_regulator_get(&client->dev, "vref");
-	if (IS_ERR(data->vref_reg))
-		return dev_err_probe(&client->dev, PTR_ERR(data->vref_reg),
-				     "Failed to get vref regulator\n");
-
-	ret = regulator_enable(data->vref_reg);
-	if (ret) {
-		dev_err(&client->dev,
-			"Failed to enable vref regulator: %d\n", ret);
-		return ret;
-	}
-
-	ret = devm_add_action_or_reset(&client->dev, max5821_regulator_disable,
-				       data->vref_reg);
-	if (ret) {
-		dev_err(&client->dev,
-			"Failed to add action to managed regulator: %d\n", ret);
-		return ret;
-	}
-
-	ret = regulator_get_voltage(data->vref_reg);
-	if (ret < 0) {
-		dev_err(&client->dev,
-			"Failed to get voltage on regulator: %d\n", ret);
-		return ret;
-	}
+	ret = devm_regulator_get_enable_read_voltage(&client->dev, "vref");
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "Failed to get vref regulator voltage\n");
 
 	data->vref_mv = ret / 1000;
 
diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c
index 25bb1c0490af..1337fb02ccf5 100644
--- a/drivers/iio/dac/mcp4725.c
+++ b/drivers/iio/dac/mcp4725.c
@@ -379,7 +379,7 @@ static int mcp4725_probe_dt(struct device *dev,
 			    struct mcp4725_platform_data *pdata)
 {
 	/* check if is the vref-supply defined */
-	pdata->use_vref = device_property_read_bool(dev, "vref-supply");
+	pdata->use_vref = device_property_present(dev, "vref-supply");
 	pdata->vref_buffered =
 		device_property_read_bool(dev, "microchip,vref-buffered");
 
diff --git a/drivers/iio/dac/rohm-bd79703.c b/drivers/iio/dac/rohm-bd79703.c
new file mode 100644
index 000000000000..e998ab51052e
--- /dev/null
+++ b/drivers/iio/dac/rohm-bd79703.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * BD79703 ROHM Digital to Analog converter
+ *
+ * Copyright (c) 2024, ROHM Semiconductor.
+ */
+
+#include <linux/bits.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
+#include <linux/iio/iio.h>
+
+#define BD79703_MAX_REGISTER 0xf
+#define BD79703_DAC_BITS 8
+#define BD79703_REG_OUT_ALL GENMASK(2, 0)
+
+/*
+ * The BD79703 uses 12-bit SPI commands. First four bits (high bits) define
+ * channel(s) which are operated on, and also the mode. The mode can be to set
+ * a DAC word only, or set DAC word and output. The data-sheet is not very
+ * specific on how a previously set DAC word can be 'taken in to use'. Thus
+ * this driver only uses the 'set DAC and output it' -mode.
+ *
+ * The BD79703 latches last 12-bits when the chip-select is toggled. Thus we
+ * can use 16-bit transfers which should be widely supported. To simplify this
+ * further, we treat the last 8 bits as a value, and first 8 bits as an
+ * address. This allows us to separate channels/mode by address and treat the
+ * 8-bit register value as DAC word. The highest 4 bits of address will be
+ * discarded when the transfer is latched.
+ */
+static const struct regmap_config bd79703_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = BD79703_MAX_REGISTER,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+struct bd79703_data {
+	struct regmap *regmap;
+	int vfs;
+};
+
+static int bd79703_read_raw(struct iio_dev *idev,
+			    struct iio_chan_spec const *chan, int *val,
+			    int *val2, long mask)
+{
+	struct bd79703_data *data = iio_priv(idev);
+
+	if (mask != IIO_CHAN_INFO_SCALE)
+		return -EINVAL;
+
+	*val = data->vfs / 1000;
+	*val2 = BD79703_DAC_BITS;
+
+	return IIO_VAL_FRACTIONAL_LOG2;
+}
+
+static int bd79703_write_raw(struct iio_dev *idev,
+			     struct iio_chan_spec const *chan, int val,
+			     int val2, long mask)
+{
+	struct bd79703_data *data = iio_priv(idev);
+
+	if (val < 0 || val >= 1 << BD79703_DAC_BITS)
+		return -EINVAL;
+
+	return regmap_write(data->regmap, chan->channel + 1, val);
+};
+
+static const struct iio_info bd79703_info = {
+	.read_raw = bd79703_read_raw,
+	.write_raw = bd79703_write_raw,
+};
+
+#define BD79703_CHAN(_chan) {					\
+	.type = IIO_VOLTAGE,					\
+	.indexed = 1,						\
+	.output = 1,						\
+	.channel = (_chan),					\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
+	.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),	\
+	.address = (_chan),					\
+}
+
+static const struct iio_chan_spec bd79703_channels[] = {
+	BD79703_CHAN(0),
+	BD79703_CHAN(1),
+	BD79703_CHAN(2),
+	BD79703_CHAN(3),
+	BD79703_CHAN(4),
+	BD79703_CHAN(5),
+};
+
+static int bd79703_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct bd79703_data *data;
+	struct iio_dev *idev;
+	int ret;
+
+	idev = devm_iio_device_alloc(dev, sizeof(*data));
+	if (!idev)
+		return -ENOMEM;
+
+	data = iio_priv(idev);
+
+	data->regmap = devm_regmap_init_spi(spi, &bd79703_regmap_config);
+	if (IS_ERR(data->regmap))
+		return dev_err_probe(dev, PTR_ERR(data->regmap),
+				     "Failed to initialize Regmap\n");
+
+	ret = devm_regulator_get_enable(dev, "vcc");
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable VCC\n");
+
+	ret = devm_regulator_get_enable_read_voltage(dev, "vfs");
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Failed to get Vfs\n");
+
+	data->vfs = ret;
+	idev->channels = bd79703_channels;
+	idev->num_channels = ARRAY_SIZE(bd79703_channels);
+	idev->modes = INDIO_DIRECT_MODE;
+	idev->info = &bd79703_info;
+	idev->name = "bd79703";
+
+	/* Initialize all to output zero */
+	ret = regmap_write(data->regmap, BD79703_REG_OUT_ALL, 0);
+	if (ret)
+		return ret;
+
+	return devm_iio_device_register(dev, idev);
+}
+
+static const struct spi_device_id bd79703_id[] = {
+	{ "bd79703", },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, bd79703_id);
+
+static const struct of_device_id bd79703_of_match[] = {
+	{ .compatible = "rohm,bd79703", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, bd79703_of_match);
+
+static struct spi_driver bd79703_driver = {
+	.driver = {
+		.name = "bd79703",
+		.of_match_table = bd79703_of_match,
+	},
+	.probe = bd79703_probe,
+	.id_table = bd79703_id,
+};
+module_spi_driver(bd79703_driver);
+
+MODULE_AUTHOR("Matti Vaittinen <mazziesaccount@gmail.com>");
+MODULE_DESCRIPTION("ROHM BD79703 DAC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/gyro/adxrs290.c b/drivers/iio/gyro/adxrs290.c
index 600e9725da78..223fc181109c 100644
--- a/drivers/iio/gyro/adxrs290.c
+++ b/drivers/iio/gyro/adxrs290.c
@@ -75,7 +75,7 @@ struct adxrs290_state {
 	/* Ensure correct alignment of timestamp when present */
 	struct {
 		s16 channels[3];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} buffer;
 };
 
diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c
index ba877d067afb..deb3c6459dde 100644
--- a/drivers/iio/gyro/bmg160_core.c
+++ b/drivers/iio/gyro/bmg160_core.c
@@ -99,7 +99,7 @@ struct bmg160_data {
 	/* Ensure naturally aligned timestamp */
 	struct {
 		s16 chans[3];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	u32 dps_range;
 	int ev_enable_state;
diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c
index 4cfa0d439560..a624400a239c 100644
--- a/drivers/iio/gyro/itg3200_buffer.c
+++ b/drivers/iio/gyro/itg3200_buffer.c
@@ -52,7 +52,7 @@ static irqreturn_t itg3200_trigger_handler(int irq, void *p)
 	 */
 	struct {
 		__be16 buf[ITG3200_SCAN_ELEMENTS];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 
 	int ret = itg3200_read_all_channels(st->i2c, scan.buf);
diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index b6883e8b2a8b..d66224bed8e3 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -474,7 +474,7 @@ static irqreturn_t mpu3050_trigger_handler(int irq, void *p)
 	int ret;
 	struct {
 		__be16 chans[4];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	s64 timestamp;
 	unsigned int datums_from_fifo = 0;
diff --git a/drivers/iio/humidity/am2315.c b/drivers/iio/humidity/am2315.c
index 6b0aa3a3f025..2323974b805c 100644
--- a/drivers/iio/humidity/am2315.c
+++ b/drivers/iio/humidity/am2315.c
@@ -35,7 +35,7 @@ struct am2315_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		s16 chans[2];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c
index 9b355380c9bf..a303f704b7ed 100644
--- a/drivers/iio/humidity/hdc100x.c
+++ b/drivers/iio/humidity/hdc100x.c
@@ -44,7 +44,7 @@ struct hdc100x_data {
 	/* Ensure natural alignment of timestamp */
 	struct {
 		__be16 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/humidity/hts221.h b/drivers/iio/humidity/hts221.h
index 721359e226cb..0215f11fc35e 100644
--- a/drivers/iio/humidity/hts221.h
+++ b/drivers/iio/humidity/hts221.h
@@ -40,7 +40,7 @@ struct hts221_hw {
 	/* Ensure natural alignment of timestamp */
 	struct {
 		__le16 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c
index 0a5d13d2240e..727e0a11eac1 100644
--- a/drivers/iio/imu/adis16480.c
+++ b/drivers/iio/imu/adis16480.c
@@ -878,11 +878,32 @@ static const struct iio_chan_spec adis16545_channels[] = {
 	IIO_CHAN_SOFT_TIMESTAMP(17),
 };
 
+static const struct iio_chan_spec adis16489_channels[] = {
+	ADIS16480_GYRO_CHANNEL(X),
+	ADIS16480_GYRO_CHANNEL(Y),
+	ADIS16480_GYRO_CHANNEL(Z),
+	ADIS16480_ACCEL_CHANNEL(X),
+	ADIS16480_ACCEL_CHANNEL(Y),
+	ADIS16480_ACCEL_CHANNEL(Z),
+	ADIS16480_PRESSURE_CHANNEL(),
+	ADIS16480_TEMP_CHANNEL(),
+	IIO_CHAN_SOFT_TIMESTAMP(8),
+	ADIS16480_DELTANG_CHANNEL_NO_SCAN(X),
+	ADIS16480_DELTANG_CHANNEL_NO_SCAN(Y),
+	ADIS16480_DELTANG_CHANNEL_NO_SCAN(Z),
+	ADIS16480_DELTVEL_CHANNEL_NO_SCAN(X),
+	ADIS16480_DELTVEL_CHANNEL_NO_SCAN(Y),
+	ADIS16480_DELTVEL_CHANNEL_NO_SCAN(Z),
+};
+
 enum adis16480_variant {
 	ADIS16375,
 	ADIS16480,
 	ADIS16485,
+	ADIS16486,
+	ADIS16487,
 	ADIS16488,
+	ADIS16489,
 	ADIS16490,
 	ADIS16495_1,
 	ADIS16495_2,
@@ -1038,6 +1059,38 @@ static const struct adis16480_chip_info adis16480_chip_info[] = {
 		.filter_freqs = adis16480_def_filter_freqs,
 		.adis_data = ADIS16480_DATA(16485, &adis16485_timeouts, 0, 0),
 	},
+	[ADIS16486] = {
+		.channels = adis16485_channels,
+		.num_channels = ARRAY_SIZE(adis16485_channels),
+		.gyro_max_val = 22500 << 16,
+		.gyro_max_scale = IIO_DEGREE_TO_RAD(450),
+		.accel_max_val = IIO_M_S_2_TO_G(20000 << 16),
+		.accel_max_scale = 18,
+		.temp_scale = 5650, /* 5.65 milli degree Celsius */
+		.deltang_max_val = IIO_DEGREE_TO_RAD(720),
+		.deltvel_max_val = 200,
+		.int_clk = 2460000,
+		.max_dec_rate = 2048,
+		.has_sleep_cnt = true,
+		.filter_freqs = adis16480_def_filter_freqs,
+		.adis_data = ADIS16480_DATA(16486, &adis16480_timeouts, 0, 0),
+	},
+	[ADIS16487] = {
+		.channels = adis16485_channels,
+		.num_channels = ARRAY_SIZE(adis16485_channels),
+		.gyro_max_val = 22500 << 16,
+		.gyro_max_scale = IIO_DEGREE_TO_RAD(450),
+		.accel_max_val = IIO_M_S_2_TO_G(20000 << 16),
+		.accel_max_scale = 5,
+		.temp_scale = 5650, /* 5.65 milli degree Celsius */
+		.deltang_max_val = IIO_DEGREE_TO_RAD(720),
+		.deltvel_max_val = 50,
+		.int_clk = 2460000,
+		.max_dec_rate = 2048,
+		.has_sleep_cnt = true,
+		.filter_freqs = adis16480_def_filter_freqs,
+		.adis_data = ADIS16480_DATA(16487, &adis16485_timeouts, 0, 0),
+	},
 	[ADIS16488] = {
 		.channels = adis16480_channels,
 		.num_channels = ARRAY_SIZE(adis16480_channels),
@@ -1054,6 +1107,22 @@ static const struct adis16480_chip_info adis16480_chip_info[] = {
 		.filter_freqs = adis16480_def_filter_freqs,
 		.adis_data = ADIS16480_DATA(16488, &adis16485_timeouts, 0, 0),
 	},
+	[ADIS16489] = {
+		.channels = adis16489_channels,
+		.num_channels = ARRAY_SIZE(adis16489_channels),
+		.gyro_max_val = 22500 << 16,
+		.gyro_max_scale = IIO_DEGREE_TO_RAD(450),
+		.accel_max_val = IIO_M_S_2_TO_G(20000 << 16),
+		.accel_max_scale = 18,
+		.temp_scale = 5650, /* 5.65 milli degree Celsius */
+		.deltang_max_val = IIO_DEGREE_TO_RAD(720),
+		.deltvel_max_val = 200,
+		.int_clk = 2460000,
+		.max_dec_rate = 2048,
+		.has_sleep_cnt = true,
+		.filter_freqs = adis16480_def_filter_freqs,
+		.adis_data = ADIS16480_DATA(16489, &adis16480_timeouts, 0, 0),
+	},
 	[ADIS16490] = {
 		.channels = adis16485_channels,
 		.num_channels = ARRAY_SIZE(adis16485_channels),
@@ -1741,7 +1810,10 @@ static const struct spi_device_id adis16480_ids[] = {
 	{ "adis16375", ADIS16375 },
 	{ "adis16480", ADIS16480 },
 	{ "adis16485", ADIS16485 },
+	{ "adis16486", ADIS16486 },
+	{ "adis16487", ADIS16487 },
 	{ "adis16488", ADIS16488 },
+	{ "adis16489", ADIS16489 },
 	{ "adis16490", ADIS16490 },
 	{ "adis16495-1", ADIS16495_1 },
 	{ "adis16495-2", ADIS16495_2 },
@@ -1763,7 +1835,10 @@ static const struct of_device_id adis16480_of_match[] = {
 	{ .compatible = "adi,adis16375" },
 	{ .compatible = "adi,adis16480" },
 	{ .compatible = "adi,adis16485" },
+	{ .compatible = "adi,adis16486" },
+	{ .compatible = "adi,adis16487" },
 	{ .compatible = "adi,adis16488" },
+	{ .compatible = "adi,adis16489" },
 	{ .compatible = "adi,adis16490" },
 	{ .compatible = "adi,adis16495-1" },
 	{ .compatible = "adi,adis16495-2" },
diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c
index f7d7f4442e65..7f386c5e58b4 100644
--- a/drivers/iio/imu/bmi323/bmi323_core.c
+++ b/drivers/iio/imu/bmi323/bmi323_core.c
@@ -174,7 +174,7 @@ struct bmi323_data {
 	__le16 fifo_buff[BMI323_FIFO_FULL_IN_WORDS] __aligned(IIO_DMA_MINALIGN);
 	struct {
 		__le16 channels[BMI323_CHAN_MAX];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} buffer;
 	__le16 steps_count[BMI323_STEP_LEN];
 };
diff --git a/drivers/iio/imu/bno055/bno055.c b/drivers/iio/imu/bno055/bno055.c
index 0728d38260a1..597c402b98de 100644
--- a/drivers/iio/imu/bno055/bno055.c
+++ b/drivers/iio/imu/bno055/bno055.c
@@ -207,7 +207,7 @@ struct bno055_priv {
 	bool sw_reset;
 	struct {
 		__le16 chans[BNO055_SCAN_CH_COUNT];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} buf;
 	struct dentry *debugfs;
 };
@@ -1193,7 +1193,7 @@ static ssize_t serialnumber_show(struct device *dev,
 }
 
 static ssize_t calibration_data_read(struct file *filp, struct kobject *kobj,
-				     struct bin_attribute *bin_attr, char *buf,
+				     const struct bin_attribute *bin_attr, char *buf,
 				     loff_t pos, size_t count)
 {
 	struct bno055_priv *priv = iio_priv(dev_to_iio_dev(kobj_to_dev(kobj)));
@@ -1348,16 +1348,16 @@ static struct attribute *bno055_attrs[] = {
 	NULL
 };
 
-static BIN_ATTR_RO(calibration_data, BNO055_CALDATA_LEN);
+static const BIN_ATTR_RO(calibration_data, BNO055_CALDATA_LEN);
 
-static struct bin_attribute *bno055_bin_attrs[] = {
+static const struct bin_attribute *const bno055_bin_attrs[] = {
 	&bin_attr_calibration_data,
 	NULL
 };
 
 static const struct attribute_group bno055_attrs_group = {
 	.attrs = bno055_attrs,
-	.bin_attrs = bno055_bin_attrs,
+	.bin_attrs_new = bno055_bin_attrs,
 };
 
 static const struct iio_info bno055_info = {
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
index 7968aa27f9fd..388520ec60b5 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c
@@ -178,7 +178,7 @@ static const struct iio_chan_spec inv_icm42600_accel_channels[] = {
 struct inv_icm42600_accel_buffer {
 	struct inv_icm42600_fifo_sensor_data accel;
 	int16_t temp;
-	int64_t timestamp __aligned(8);
+	aligned_s64 timestamp;
 };
 
 #define INV_ICM42600_SCAN_MASK_ACCEL_3AXIS				\
diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
index c6bb68bf5e14..591ed78a55bb 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c
@@ -78,7 +78,7 @@ static const struct iio_chan_spec inv_icm42600_gyro_channels[] = {
 struct inv_icm42600_gyro_buffer {
 	struct inv_icm42600_fifo_sensor_data gyro;
 	int16_t temp;
-	int64_t timestamp __aligned(8);
+	aligned_s64 timestamp;
 };
 
 #define INV_ICM42600_SCAN_MASK_GYRO_3AXIS				\
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 844b611b825a..5bcd5e797046 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -277,6 +277,14 @@ static const struct inv_mpu6050_hw hw_info[] = {
 		.temp = {INV_ICM20608_TEMP_OFFSET, INV_ICM20608_TEMP_SCALE},
 		.startup_time = {INV_ICM20690_GYRO_STARTUP_TIME, INV_ICM20690_ACCEL_STARTUP_TIME},
 	},
+	{	.whoami = INV_IAM20380_WHOAMI_VALUE,
+		.name = "IAM20380",
+		.reg = &reg_set_6500,
+		.config = &chip_config_6500,
+		.fifo_size = 512,
+		.temp = {INV_ICM20608_TEMP_OFFSET, INV_ICM20608_TEMP_SCALE},
+		.startup_time = {INV_MPU6500_GYRO_STARTUP_TIME, INV_MPU6500_ACCEL_STARTUP_TIME},
+	},
 	{
 		.whoami = INV_IAM20680_WHOAMI_VALUE,
 		.name = "IAM20680",
@@ -1519,6 +1527,14 @@ static const struct iio_chan_spec inv_mpu6050_channels[] = {
 	INV_MPU6050_CHAN(IIO_ACCEL, IIO_MOD_Z, INV_MPU6050_SCAN_ACCL_Z),
 };
 
+static const struct iio_chan_spec inv_iam20380_channels[] = {
+	IIO_CHAN_SOFT_TIMESTAMP(INV_MPU6050_SCAN_TIMESTAMP),
+
+	INV_MPU6050_CHAN(IIO_ANGL_VEL, IIO_MOD_X, INV_MPU6050_SCAN_GYRO_X),
+	INV_MPU6050_CHAN(IIO_ANGL_VEL, IIO_MOD_Y, INV_MPU6050_SCAN_GYRO_Y),
+	INV_MPU6050_CHAN(IIO_ANGL_VEL, IIO_MOD_Z, INV_MPU6050_SCAN_GYRO_Z),
+};
+
 static const struct iio_chan_spec inv_mpu6500_channels[] = {
 	IIO_CHAN_SOFT_TIMESTAMP(INV_MPU6050_SCAN_TIMESTAMP),
 
@@ -1623,6 +1639,10 @@ static const struct iio_chan_spec inv_mpu9250_channels[] = {
 	| BIT(INV_MPU9X50_SCAN_MAGN_Y)		\
 	| BIT(INV_MPU9X50_SCAN_MAGN_Z))
 
+static const unsigned long inv_iam20380_scan_masks[] = {
+	INV_MPU6050_SCAN_MASK_3AXIS_GYRO,
+};
+
 static const unsigned long inv_mpu9x50_scan_masks[] = {
 	/* 3-axis accel */
 	INV_MPU6050_SCAN_MASK_3AXIS_ACCEL,
@@ -2026,6 +2046,11 @@ int inv_mpu_core_probe(struct regmap *regmap, int irq, const char *name,
 		indio_dev->num_channels = ARRAY_SIZE(inv_mpu9250_channels);
 		indio_dev->available_scan_masks = inv_mpu9x50_scan_masks;
 		break;
+	case INV_IAM20380:
+		indio_dev->channels = inv_iam20380_channels;
+		indio_dev->num_channels = ARRAY_SIZE(inv_iam20380_channels);
+		indio_dev->available_scan_masks = inv_iam20380_scan_masks;
+		break;
 	case INV_ICM20600:
 	case INV_ICM20602:
 		indio_dev->channels = inv_mpu6500_channels;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c
index 307a06f4df2e..91d77f94d204 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c
@@ -34,6 +34,7 @@ static bool inv_mpu_i2c_aux_bus(struct device *dev)
 	case INV_ICM20689:
 	case INV_ICM20600:
 	case INV_ICM20602:
+	case INV_IAM20380:
 	case INV_IAM20680:
 		/* no i2c auxiliary bus on the chip */
 		return false;
@@ -187,6 +188,7 @@ static const struct i2c_device_id inv_mpu_id[] = {
 	{"icm20600", INV_ICM20600},
 	{"icm20602", INV_ICM20602},
 	{"icm20690", INV_ICM20690},
+	{"iam20380", INV_IAM20380},
 	{"iam20680", INV_IAM20680},
 	{"iam20680hp", INV_IAM20680HP},
 	{"iam20680ht", INV_IAM20680HT},
@@ -253,6 +255,10 @@ static const struct of_device_id inv_of_match[] = {
 		.data = (void *)INV_ICM20690
 	},
 	{
+		.compatible = "invensense,iam20380",
+		.data = (void *)INV_IAM20380
+	},
+	{
 		.compatible = "invensense,iam20680",
 		.data = (void *)INV_IAM20680
 	},
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
index a6862cf42639..211901f8b8eb 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
@@ -84,6 +84,7 @@ enum inv_devices {
 	INV_ICM20600,
 	INV_ICM20602,
 	INV_ICM20690,
+	INV_IAM20380,
 	INV_IAM20680,
 	INV_IAM20680HP,
 	INV_IAM20680HT,
@@ -425,6 +426,7 @@ struct inv_mpu6050_state {
 #define INV_ICM20600_WHOAMI_VALUE		0x11
 #define INV_ICM20602_WHOAMI_VALUE		0x12
 #define INV_ICM20690_WHOAMI_VALUE		0x20
+#define INV_IAM20380_WHOAMI_VALUE		0xB5
 #define INV_IAM20680_WHOAMI_VALUE		0xA9
 #define INV_IAM20680HP_WHOAMI_VALUE		0xF8
 #define INV_IAM20680HT_WHOAMI_VALUE		0xFA
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c
index ab415874d699..20de6eb5cd35 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c
@@ -79,6 +79,7 @@ static const struct spi_device_id inv_mpu_id[] = {
 	{"icm20600", INV_ICM20600},
 	{"icm20602", INV_ICM20602},
 	{"icm20690", INV_ICM20690},
+	{"iam20380", INV_IAM20380},
 	{"iam20680", INV_IAM20680},
 	{"iam20680hp", INV_IAM20680HP},
 	{"iam20680ht", INV_IAM20680HT},
@@ -141,6 +142,10 @@ static const struct of_device_id inv_of_match[] = {
 		.data = (void *)INV_ICM20690
 	},
 	{
+		.compatible = "invensense,iam20380",
+		.data = (void *)INV_IAM20380
+	},
+	{
 		.compatible = "invensense,iam20680",
 		.data = (void *)INV_IAM20680
 	},
diff --git a/drivers/iio/imu/st_lsm6dsx/Kconfig b/drivers/iio/imu/st_lsm6dsx/Kconfig
index 89d687ec3099..3cabec3b152d 100644
--- a/drivers/iio/imu/st_lsm6dsx/Kconfig
+++ b/drivers/iio/imu/st_lsm6dsx/Kconfig
@@ -6,9 +6,6 @@ config IIO_ST_LSM6DSX
 	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
 	select IIO_KFIFO_BUF
-	select IIO_ST_LSM6DSX_I2C if (I2C)
-	select IIO_ST_LSM6DSX_SPI if (SPI_MASTER)
-	select IIO_ST_LSM6DSX_I3C if (I3C)
 	help
 	  Say yes here to build support for STMicroelectronics LSM6DSx imu
 	  sensor.
@@ -42,16 +39,19 @@ config IIO_ST_LSM6DSX
 	  will be called st_lsm6dsx.
 
 config IIO_ST_LSM6DSX_I2C
-	tristate
-	depends on IIO_ST_LSM6DSX
+	tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors I2C Interface"
+	depends on I2C && IIO_ST_LSM6DSX
+	default I2C && IIO_ST_LSM6DSX
 	select REGMAP_I2C
 
 config IIO_ST_LSM6DSX_SPI
-	tristate
-	depends on IIO_ST_LSM6DSX
+	tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors SPI Interface"
+	depends on SPI_MASTER && IIO_ST_LSM6DSX
+	default SPI_MASTER && IIO_ST_LSM6DSX
 	select REGMAP_SPI
 
 config IIO_ST_LSM6DSX_I3C
-	tristate
-	depends on IIO_ST_LSM6DSX
+	tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors I3C Interface"
+	depends on I3C && IIO_ST_LSM6DSX
+	default I3C && IIO_ST_LSM6DSX
 	select REGMAP_I3C
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c
index 6952d901316f..f968f32890d1 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i3c.c
@@ -9,7 +9,6 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/i3c/device.h>
-#include <linux/i3c/master.h>
 #include <linux/slab.h>
 #include <linux/regmap.h>
 
@@ -30,15 +29,16 @@ static int st_lsm6dsx_i3c_probe(struct i3c_device *i3cdev)
 	};
 	const struct i3c_device_id *id = i3c_device_match_id(i3cdev,
 							    st_lsm6dsx_i3c_ids);
+	struct device *dev = i3cdev_to_dev(i3cdev);
 	struct regmap *regmap;
 
 	regmap = devm_regmap_init_i3c(i3cdev, &st_lsm6dsx_i3c_regmap_config);
 	if (IS_ERR(regmap)) {
-		dev_err(&i3cdev->dev, "Failed to register i3c regmap %ld\n", PTR_ERR(regmap));
+		dev_err(dev, "Failed to register i3c regmap %ld\n", PTR_ERR(regmap));
 		return PTR_ERR(regmap);
 	}
 
-	return st_lsm6dsx_probe(&i3cdev->dev, 0, (uintptr_t)id->data, regmap);
+	return st_lsm6dsx_probe(dev, 0, (uintptr_t)id->data, regmap);
 }
 
 static struct i3c_driver st_lsm6dsx_driver = {
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 2708f87df719..a80f7cc25a27 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -1137,7 +1137,7 @@ static int iio_enable_buffers(struct iio_dev *indio_dev,
 	int ret;
 
 	indio_dev->active_scan_mask = config->scan_mask;
-	indio_dev->scan_timestamp = config->scan_timestamp;
+	ACCESS_PRIVATE(indio_dev, scan_timestamp) = config->scan_timestamp;
 	indio_dev->scan_bytes = config->scan_bytes;
 	iio_dev_opaque->currentmode = config->mode;
 
diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c
index 3b5a99815062..d70ebe3bf774 100644
--- a/drivers/iio/industrialio-gts-helper.c
+++ b/drivers/iio/industrialio-gts-helper.c
@@ -915,6 +915,41 @@ int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel
 }
 EXPORT_SYMBOL_NS_GPL(iio_gts_find_gain_sel_for_scale_using_time, "IIO_GTS_HELPER");
 
+/**
+ * iio_gts_find_gain_time_sel_for_scale - Fetch gain and time selectors for scale
+ * @gts:	Gain time scale descriptor
+ * @scale_int:	Integral part of the scale (typically val1)
+ * @scale_nano:	Fractional part of the scale (nano or ppb)
+ * @gain_sel:	Pointer to value where gain selector is stored.
+ * @time_sel:	Pointer to value where time selector is stored.
+ *
+ * Wrapper around iio_gts_find_gain_for_scale_using_time() to fetch the
+ * gain and time selectors for a given scale.
+ *
+ * Return: 0 on success and -EINVAL on error.
+ */
+int iio_gts_find_gain_time_sel_for_scale(struct iio_gts *gts, int scale_int,
+					 int scale_nano, int *gain_sel,
+					 int *time_sel)
+{
+	int i, ret;
+
+	for (i = 0; i < gts->num_itime; i++) {
+		*time_sel = gts->itime_table[i].sel;
+		ret = iio_gts_find_gain_sel_for_scale_using_time(gts, *time_sel,
+								 scale_int,
+								 scale_nano,
+								 gain_sel);
+		if (ret)
+			continue;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_NS_GPL(iio_gts_find_gain_time_sel_for_scale, "IIO_GTS_HELPER");
+
 static int iio_gts_get_total_gain(struct iio_gts *gts, int gain, int time)
 {
 	const struct iio_itime_sel_mul *itime;
@@ -1086,6 +1121,48 @@ int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain,
 }
 EXPORT_SYMBOL_NS_GPL(iio_gts_find_new_gain_by_old_gain_time, "IIO_GTS_HELPER");
 
+/**
+ * iio_gts_find_new_gain_by_gain_time_min - compensate for time change
+ * @gts:	Gain time scale descriptor
+ * @old_gain:	Previously set gain
+ * @old_time:	Selector corresponding previously set time
+ * @new_time:	Selector corresponding new time to be set
+ * @new_gain:	Pointer to value where new gain is to be written
+ * @in_range:	Indicate if the @new_gain was in the range of
+ *		supported gains.
+ *
+ * Wrapper around iio_gts_find_new_gain_by_old_gain_time() that tries to
+ * set an optimal value if no exact match was found, defaulting to the
+ * minimum gain to avoid saturations if the optimal value is not in the
+ * range of supported gains.
+ *
+ * Return: 0 on success and a negative value if no gain was found.
+ */
+int iio_gts_find_new_gain_by_gain_time_min(struct iio_gts *gts, int old_gain,
+					   int old_time, int new_time,
+					   int *new_gain, bool *in_range)
+{
+	int ret;
+
+	*in_range = true;
+	ret = iio_gts_find_new_gain_by_old_gain_time(gts, old_gain, old_time,
+						     new_time, new_gain);
+	if (*new_gain < 0)
+		return -EINVAL;
+
+	if (ret) {
+		*new_gain = iio_find_closest_gain_low(gts, *new_gain, in_range);
+		if (*new_gain < 0) {
+			*new_gain = iio_gts_get_min_gain(gts);
+			if (*new_gain < 0)
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(iio_gts_find_new_gain_by_gain_time_min, "IIO_GTS_HELPER");
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Matti Vaittinen <mazziesaccount@gmail.com>");
 MODULE_DESCRIPTION("IIO light sensor gain-time-scale helpers");
diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index 9050a59129e6..c174ebb7d5e6 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -7,6 +7,7 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/minmax.h>
+#include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/property.h>
 #include <linux/slab.h>
@@ -989,6 +990,11 @@ ssize_t iio_read_channel_ext_info(struct iio_channel *chan,
 {
 	const struct iio_chan_spec_ext_info *ext_info;
 
+	if (!buf || offset_in_page(buf)) {
+		pr_err("iio: invalid ext_info read buffer\n");
+		return -EINVAL;
+	}
+
 	ext_info = iio_lookup_ext_info(chan, attr);
 	if (!ext_info)
 		return -EINVAL;
@@ -1014,6 +1020,11 @@ EXPORT_SYMBOL_GPL(iio_write_channel_ext_info);
 
 ssize_t iio_read_channel_label(struct iio_channel *chan, char *buf)
 {
+	if (!buf || offset_in_page(buf)) {
+		pr_err("iio: invalid label read buffer\n");
+		return -EINVAL;
+	}
+
 	return do_iio_read_channel_label(chan->indio_dev, chan->channel, buf);
 }
 EXPORT_SYMBOL_GPL(iio_read_channel_label);
diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index 29ffa8491927..e34e551eef3e 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -329,22 +329,6 @@ config JSA1212
 	  To compile this driver as a module, choose M here:
 	  the module will be called jsa1212.
 
-config ROHM_BU27008
-	tristate "ROHM BU27008 color (RGB+C/IR) sensor"
-	depends on I2C
-	select REGMAP_I2C
-	select IIO_GTS_HELPER
-	select IIO_BUFFER
-	select IIO_TRIGGERED_BUFFER
-	help
-	  Enable support for the ROHM BU27008 color sensor.
-	  The ROHM BU27008 is a sensor with 5 photodiodes (red, green,
-	  blue, clear and IR) with four configurable channels. Red and
-	  green being always available and two out of the rest three
-	  (blue, clear, IR) can be selected to be simultaneously measured.
-	  Typical application is adjusting LCD backlight of TVs,
-	  mobile phones and tablet PCs.
-
 config ROHM_BU27034
 	tristate "ROHM BU27034 ambient light sensor"
 	depends on I2C
@@ -491,6 +475,19 @@ config OPT4001
 	  If built as a dynamically linked module, it will be called
 	  opt4001.
 
+config OPT4060
+	tristate "Texas Instruments OPT4060 RGBW Color Sensor"
+	depends on I2C
+	select REGMAP_I2C
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+	help
+	  If you say Y or M here, you get support for Texas Instruments
+	  OPT4060 RGBW Color Sensor.
+
+	  If built as a dynamically linked module, it will be called
+	  opt4060.
+
 config PA12203001
 	tristate "TXC PA12203001 light and proximity sensor"
 	depends on I2C
@@ -672,6 +669,7 @@ config VCNL4035
 config VEML3235
 	tristate "VEML3235 ambient light sensor"
 	select REGMAP_I2C
+	select IIO_GTS_HELPER
 	depends on I2C
 	help
 	  Say Y here if you want to build a driver for the Vishay VEML3235
@@ -683,6 +681,8 @@ config VEML3235
 config VEML6030
 	tristate "VEML6030 and VEML6035 ambient light sensors"
 	select REGMAP_I2C
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
 	depends on I2C
 	help
 	  Say Y here if you want to build a driver for the Vishay VEML6030
diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile
index f14a37442712..11a4041b918a 100644
--- a/drivers/iio/light/Makefile
+++ b/drivers/iio/light/Makefile
@@ -42,8 +42,8 @@ obj-$(CONFIG_MAX44009)		+= max44009.o
 obj-$(CONFIG_NOA1305)		+= noa1305.o
 obj-$(CONFIG_OPT3001)		+= opt3001.o
 obj-$(CONFIG_OPT4001)		+= opt4001.o
+obj-$(CONFIG_OPT4060)		+= opt4060.o
 obj-$(CONFIG_PA12203001)	+= pa12203001.o
-obj-$(CONFIG_ROHM_BU27008)	+= rohm-bu27008.o
 obj-$(CONFIG_ROHM_BU27034)	+= rohm-bu27034.o
 obj-$(CONFIG_RPR0521)		+= rpr0521.o
 obj-$(CONFIG_SI1133)		+= si1133.o
diff --git a/drivers/iio/light/adjd_s311.c b/drivers/iio/light/adjd_s311.c
index c1b43053fbc7..cf96e3dd8bc6 100644
--- a/drivers/iio/light/adjd_s311.c
+++ b/drivers/iio/light/adjd_s311.c
@@ -56,7 +56,7 @@ struct adjd_s311_data {
 	struct i2c_client *client;
 	struct {
 		s16 chans[4];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/light/as73211.c b/drivers/iio/light/as73211.c
index be0068081ebb..37fffce35dd1 100644
--- a/drivers/iio/light/as73211.c
+++ b/drivers/iio/light/as73211.c
@@ -177,6 +177,12 @@ struct as73211_data {
 	BIT(AS73211_SCAN_INDEX_TEMP) | \
 	AS73211_SCAN_MASK_COLOR)
 
+static const unsigned long as73211_scan_masks[] = {
+	AS73211_SCAN_MASK_COLOR,
+	AS73211_SCAN_MASK_ALL,
+	0
+};
+
 static const struct iio_chan_spec as73211_channels[] = {
 	{
 		.type = IIO_TEMP,
@@ -636,7 +642,7 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p)
 	struct as73211_data *data = iio_priv(indio_dev);
 	struct {
 		__le16 chan[4];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	int data_result, ret;
 
@@ -672,9 +678,12 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p)
 
 		/* AS73211 starts reading at address 2 */
 		ret = i2c_master_recv(data->client,
-				(char *)&scan.chan[1], 3 * sizeof(scan.chan[1]));
+				(char *)&scan.chan[0], 3 * sizeof(scan.chan[0]));
 		if (ret < 0)
 			goto done;
+
+		/* Avoid pushing uninitialized data */
+		scan.chan[3] = 0;
 	}
 
 	if (data_result) {
@@ -682,9 +691,15 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p)
 		 * Saturate all channels (in case of overflows). Temperature channel
 		 * is not affected by overflows.
 		 */
-		scan.chan[1] = cpu_to_le16(U16_MAX);
-		scan.chan[2] = cpu_to_le16(U16_MAX);
-		scan.chan[3] = cpu_to_le16(U16_MAX);
+		if (*indio_dev->active_scan_mask == AS73211_SCAN_MASK_ALL) {
+			scan.chan[1] = cpu_to_le16(U16_MAX);
+			scan.chan[2] = cpu_to_le16(U16_MAX);
+			scan.chan[3] = cpu_to_le16(U16_MAX);
+		} else {
+			scan.chan[0] = cpu_to_le16(U16_MAX);
+			scan.chan[1] = cpu_to_le16(U16_MAX);
+			scan.chan[2] = cpu_to_le16(U16_MAX);
+		}
 	}
 
 	iio_push_to_buffers_with_timestamp(indio_dev, &scan, iio_get_time_ns(indio_dev));
@@ -758,6 +773,7 @@ static int as73211_probe(struct i2c_client *client)
 	indio_dev->channels = data->spec_dev->channels;
 	indio_dev->num_channels = data->spec_dev->num_channels;
 	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->available_scan_masks = as73211_scan_masks;
 
 	ret = i2c_smbus_read_byte_data(data->client, AS73211_REG_OSR);
 	if (ret < 0)
diff --git a/drivers/iio/light/bh1745.c b/drivers/iio/light/bh1745.c
index 63bf729df517..3b4056be54a0 100644
--- a/drivers/iio/light/bh1745.c
+++ b/drivers/iio/light/bh1745.c
@@ -739,7 +739,7 @@ static irqreturn_t bh1745_trigger_handler(int interrupt, void *p)
 	struct bh1745_data *data = iio_priv(indio_dev);
 	struct {
 		u16 chans[4];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	u16 value;
 	int ret;
diff --git a/drivers/iio/light/cm3232.c b/drivers/iio/light/cm3232.c
index b6288dd25bbf..5b00ad2a014e 100644
--- a/drivers/iio/light/cm3232.c
+++ b/drivers/iio/light/cm3232.c
@@ -89,6 +89,15 @@ static int cm3232_reg_init(struct cm3232_chip *chip)
 
 	chip->als_info = &cm3232_als_info_default;
 
+	/* Disable and reset device */
+	chip->regs_cmd = CM3232_CMD_ALS_DISABLE | CM3232_CMD_ALS_RESET;
+	ret = i2c_smbus_write_byte_data(client, CM3232_REG_ADDR_CMD,
+					chip->regs_cmd);
+	if (ret < 0) {
+		dev_err(&chip->client->dev, "Error writing reg_cmd\n");
+		return ret;
+	}
+
 	/* Identify device */
 	ret = i2c_smbus_read_word_data(client, CM3232_REG_ADDR_ID);
 	if (ret < 0) {
@@ -99,15 +108,6 @@ static int cm3232_reg_init(struct cm3232_chip *chip)
 	if ((ret & 0xFF) != chip->als_info->hw_id)
 		return -ENODEV;
 
-	/* Disable and reset device */
-	chip->regs_cmd = CM3232_CMD_ALS_DISABLE | CM3232_CMD_ALS_RESET;
-	ret = i2c_smbus_write_byte_data(client, CM3232_REG_ADDR_CMD,
-					chip->regs_cmd);
-	if (ret < 0) {
-		dev_err(&chip->client->dev, "Error writing reg_cmd\n");
-		return ret;
-	}
-
 	/* Register default value */
 	chip->regs_cmd = chip->als_info->regs_cmd_default;
 
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index c83acbd78275..7ab64f5c623c 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -94,6 +94,7 @@ static int prox_read_raw(struct iio_dev *indio_dev,
 	*val2 = 0;
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
+	case IIO_CHAN_INFO_PROCESSED:
 		if (chan->scan_index >= prox_state->num_channels)
 			return -EINVAL;
 		address = prox_state->channel2usage[chan->scan_index];
diff --git a/drivers/iio/light/isl29125.c b/drivers/iio/light/isl29125.c
index b176bf4c884b..326dc39e7929 100644
--- a/drivers/iio/light/isl29125.c
+++ b/drivers/iio/light/isl29125.c
@@ -54,7 +54,7 @@ struct isl29125_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		u16 chans[3];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 604f5f900a2e..669da0840eba 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -1280,7 +1280,7 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 	struct ltr501_data *data = iio_priv(indio_dev);
 	struct {
 		u16 channels[3];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	__le16 als_buf[2];
 	u8 mask = 0;
diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c
index b935976871a6..e8b767680133 100644
--- a/drivers/iio/light/max44000.c
+++ b/drivers/iio/light/max44000.c
@@ -78,7 +78,7 @@ struct max44000_data {
 	/* Ensure naturally aligned timestamp */
 	struct {
 		u16 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/light/opt4060.c b/drivers/iio/light/opt4060.c
new file mode 100644
index 000000000000..ab55f8d2ea0c
--- /dev/null
+++ b/drivers/iio/light/opt4060.c
@@ -0,0 +1,1343 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Axis Communications AB
+ *
+ * Datasheet: https://www.ti.com/lit/gpn/opt4060
+ *
+ * Device driver for the Texas Instruments OPT4060 RGBW Color Sensor.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/i2c.h>
+#include <linux/iio/iio.h>
+#include <linux/math64.h>
+#include <linux/units.h>
+#include <linux/limits.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include <linux/mutex.h>
+#include <linux/regulator/consumer.h>
+#include <linux/iio/events.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+
+/* OPT4060 register set */
+#define OPT4060_RED_MSB				0x00
+#define OPT4060_RED_LSB				0x01
+#define OPT4060_GREEN_MSB			0x02
+#define OPT4060_GREEN_LSB			0x03
+#define OPT4060_BLUE_MSB			0x04
+#define OPT4060_BLUE_LSB			0x05
+#define OPT4060_CLEAR_MSB			0x06
+#define OPT4060_CLEAR_LSB			0x07
+#define OPT4060_THRESHOLD_LOW			0x08
+#define OPT4060_THRESHOLD_HIGH			0x09
+#define OPT4060_CTRL				0x0a
+#define OPT4060_INT_CTRL			0x0b
+#define OPT4060_RES_CTRL			0x0c
+#define OPT4060_DEVICE_ID			0x11
+
+/* OPT4060 register mask */
+#define OPT4060_EXPONENT_MASK			GENMASK(15, 12)
+#define OPT4060_MSB_MASK			GENMASK(11, 0)
+#define OPT4060_LSB_MASK			GENMASK(15, 8)
+#define OPT4060_COUNTER_MASK			GENMASK(7, 4)
+#define OPT4060_CRC_MASK			GENMASK(3, 0)
+
+/* OPT4060 device id mask */
+#define OPT4060_DEVICE_ID_MASK			GENMASK(11, 0)
+
+/* OPT4060 control register masks */
+#define OPT4060_CTRL_QWAKE_MASK			BIT(15)
+#define OPT4060_CTRL_RANGE_MASK			GENMASK(13, 10)
+#define OPT4060_CTRL_CONV_TIME_MASK		GENMASK(9, 6)
+#define OPT4060_CTRL_OPER_MODE_MASK		GENMASK(5, 4)
+#define OPT4060_CTRL_LATCH_MASK			BIT(3)
+#define OPT4060_CTRL_INT_POL_MASK		BIT(2)
+#define OPT4060_CTRL_FAULT_COUNT_MASK		GENMASK(1, 0)
+
+/* OPT4060 interrupt control register masks */
+#define OPT4060_INT_CTRL_THRESH_SEL		GENMASK(6, 5)
+#define OPT4060_INT_CTRL_OUTPUT			BIT(4)
+#define OPT4060_INT_CTRL_INT_CFG		GENMASK(3, 2)
+#define OPT4060_INT_CTRL_THRESHOLD		0x0
+#define OPT4060_INT_CTRL_NEXT_CH		0x1
+#define OPT4060_INT_CTRL_ALL_CH			0x3
+
+/* OPT4060 result control register masks */
+#define OPT4060_RES_CTRL_OVERLOAD		BIT(3)
+#define OPT4060_RES_CTRL_CONV_READY		BIT(2)
+#define OPT4060_RES_CTRL_FLAG_H			BIT(1)
+#define OPT4060_RES_CTRL_FLAG_L			BIT(0)
+
+/* OPT4060 constants */
+#define OPT4060_DEVICE_ID_VAL			0x821
+
+/* OPT4060 operating modes */
+#define OPT4060_CTRL_OPER_MODE_OFF		0x0
+#define OPT4060_CTRL_OPER_MODE_FORCED		0x1
+#define OPT4060_CTRL_OPER_MODE_ONE_SHOT		0x2
+#define OPT4060_CTRL_OPER_MODE_CONTINUOUS	0x3
+
+/* OPT4060 conversion control register definitions */
+#define OPT4060_CTRL_CONVERSION_0_6MS		0x0
+#define OPT4060_CTRL_CONVERSION_1MS		0x1
+#define OPT4060_CTRL_CONVERSION_1_8MS		0x2
+#define OPT4060_CTRL_CONVERSION_3_4MS		0x3
+#define OPT4060_CTRL_CONVERSION_6_5MS		0x4
+#define OPT4060_CTRL_CONVERSION_12_7MS		0x5
+#define OPT4060_CTRL_CONVERSION_25MS		0x6
+#define OPT4060_CTRL_CONVERSION_50MS		0x7
+#define OPT4060_CTRL_CONVERSION_100MS		0x8
+#define OPT4060_CTRL_CONVERSION_200MS		0x9
+#define OPT4060_CTRL_CONVERSION_400MS		0xa
+#define OPT4060_CTRL_CONVERSION_800MS		0xb
+
+/* OPT4060 fault count control register definitions */
+#define OPT4060_CTRL_FAULT_COUNT_1		0x0
+#define OPT4060_CTRL_FAULT_COUNT_2		0x1
+#define OPT4060_CTRL_FAULT_COUNT_4		0x2
+#define OPT4060_CTRL_FAULT_COUNT_8		0x3
+
+/* OPT4060 scale light level range definitions */
+#define OPT4060_CTRL_LIGHT_SCALE_AUTO		12
+
+/* OPT4060 default values */
+#define OPT4060_DEFAULT_CONVERSION_TIME OPT4060_CTRL_CONVERSION_50MS
+
+/*
+ * enum opt4060_chan_type - OPT4060 channel types
+ * @OPT4060_RED:	Red channel.
+ * @OPT4060_GREEN:	Green channel.
+ * @OPT4060_BLUE:	Blue channel.
+ * @OPT4060_CLEAR:	Clear (white) channel.
+ * @OPT4060_ILLUM:	Calculated illuminance channel.
+ * @OPT4060_NUM_CHANS:	Number of channel types.
+ */
+enum opt4060_chan_type {
+	OPT4060_RED,
+	OPT4060_GREEN,
+	OPT4060_BLUE,
+	OPT4060_CLEAR,
+	OPT4060_ILLUM,
+	OPT4060_NUM_CHANS
+};
+
+struct opt4060_chip {
+	struct regmap *regmap;
+	struct device *dev;
+	struct iio_trigger *trig;
+	u8 int_time;
+	int irq;
+	/*
+	 * Mutex for protecting sensor irq settings. Switching between interrupt
+	 * on each sample and on thresholds needs to be synchronized.
+	 */
+	struct mutex irq_setting_lock;
+	/*
+	 * Mutex for protecting event enabling.
+	 */
+	struct mutex event_enabling_lock;
+	struct completion completion;
+	bool thresh_event_lo_active;
+	bool thresh_event_hi_active;
+};
+
+struct opt4060_channel_factor {
+	u32 mul;
+	u32 div;
+};
+
+static const int opt4060_int_time_available[][2] = {
+	{ 0,    600 },
+	{ 0,   1000 },
+	{ 0,   1800 },
+	{ 0,   3400 },
+	{ 0,   6500 },
+	{ 0,  12700 },
+	{ 0,  25000 },
+	{ 0,  50000 },
+	{ 0, 100000 },
+	{ 0, 200000 },
+	{ 0, 400000 },
+	{ 0, 800000 },
+};
+
+/*
+ * Conversion time is integration time + time to set register
+ * this is used as integration time.
+ */
+static const int opt4060_int_time_reg[][2] = {
+	{    600,  OPT4060_CTRL_CONVERSION_0_6MS  },
+	{   1000,  OPT4060_CTRL_CONVERSION_1MS    },
+	{   1800,  OPT4060_CTRL_CONVERSION_1_8MS  },
+	{   3400,  OPT4060_CTRL_CONVERSION_3_4MS  },
+	{   6500,  OPT4060_CTRL_CONVERSION_6_5MS  },
+	{  12700,  OPT4060_CTRL_CONVERSION_12_7MS },
+	{  25000,  OPT4060_CTRL_CONVERSION_25MS   },
+	{  50000,  OPT4060_CTRL_CONVERSION_50MS   },
+	{ 100000,  OPT4060_CTRL_CONVERSION_100MS  },
+	{ 200000,  OPT4060_CTRL_CONVERSION_200MS  },
+	{ 400000,  OPT4060_CTRL_CONVERSION_400MS  },
+	{ 800000,  OPT4060_CTRL_CONVERSION_800MS  },
+};
+
+static int opt4060_als_time_to_index(const u32 als_integration_time)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(opt4060_int_time_available); i++) {
+		if (als_integration_time == opt4060_int_time_available[i][1])
+			return i;
+	}
+
+	return -EINVAL;
+}
+
+static u8 opt4060_calculate_crc(u8 exp, u32 mantissa, u8 count)
+{
+	u8 crc;
+
+	/*
+	 * Calculates a 4-bit CRC from a 20-bit mantissa, 4-bit exponent and a 4-bit counter.
+	 * crc[0] = XOR(mantissa[19:0], exp[3:0], count[3:0])
+	 * crc[1] = XOR(mantissa[1,3,5,7,9,11,13,15,17,19], exp[1,3], count[1,3])
+	 * crc[2] = XOR(mantissa[3,7,11,15,19], exp[3], count[3])
+	 * crc[3] = XOR(mantissa[3,11,19])
+	 */
+	crc = (hweight32(mantissa) + hweight32(exp) + hweight32(count)) % 2;
+	crc |= ((hweight32(mantissa & 0xAAAAA) + hweight32(exp & 0xA)
+		 + hweight32(count & 0xA)) % 2) << 1;
+	crc |= ((hweight32(mantissa & 0x88888) + hweight32(exp & 0x8)
+		 + hweight32(count & 0x8)) % 2) << 2;
+	crc |= (hweight32(mantissa & 0x80808) % 2) << 3;
+
+	return crc;
+}
+
+static int opt4060_set_int_state(struct opt4060_chip *chip, u32 state)
+{
+	int ret;
+	unsigned int regval;
+
+	guard(mutex)(&chip->irq_setting_lock);
+
+	regval = FIELD_PREP(OPT4060_INT_CTRL_INT_CFG, state);
+	ret = regmap_update_bits(chip->regmap, OPT4060_INT_CTRL,
+				 OPT4060_INT_CTRL_INT_CFG, regval);
+	if (ret)
+		dev_err(chip->dev, "Failed to set interrupt config\n");
+	return ret;
+}
+
+static int opt4060_set_sampling_mode(struct opt4060_chip *chip,
+				     bool continuous)
+{
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(chip->regmap, OPT4060_CTRL, &reg);
+	if (ret < 0) {
+		dev_err(chip->dev, "Failed to read ctrl register\n");
+		return ret;
+	}
+	reg &= ~OPT4060_CTRL_OPER_MODE_MASK;
+	if (continuous)
+		reg |= FIELD_PREP(OPT4060_CTRL_OPER_MODE_MASK,
+				  OPT4060_CTRL_OPER_MODE_CONTINUOUS);
+	else
+		reg |= FIELD_PREP(OPT4060_CTRL_OPER_MODE_MASK,
+				  OPT4060_CTRL_OPER_MODE_ONE_SHOT);
+
+	/*
+	 * Trigger a new conversions by writing to CRTL register. It is not
+	 * possible to use regmap_update_bits() since that will only write when
+	 * data is modified.
+	 */
+	ret = regmap_write(chip->regmap, OPT4060_CTRL, reg);
+	if (ret)
+		dev_err(chip->dev, "Failed to set ctrl register\n");
+	return ret;
+}
+
+static bool opt4060_event_active(struct opt4060_chip *chip)
+{
+	return chip->thresh_event_lo_active || chip->thresh_event_hi_active;
+}
+
+static int opt4060_set_state_common(struct opt4060_chip *chip,
+				    bool continuous_sampling,
+				    bool continuous_irq)
+{
+	int ret = 0;
+
+	/* It is important to setup irq before sampling to avoid missing samples. */
+	if (continuous_irq)
+		ret = opt4060_set_int_state(chip, OPT4060_INT_CTRL_ALL_CH);
+	else
+		ret = opt4060_set_int_state(chip, OPT4060_INT_CTRL_THRESHOLD);
+	if (ret) {
+		dev_err(chip->dev, "Failed to set irq state.\n");
+		return ret;
+	}
+
+	if (continuous_sampling || opt4060_event_active(chip))
+		ret = opt4060_set_sampling_mode(chip, true);
+	else
+		ret = opt4060_set_sampling_mode(chip, false);
+	if (ret)
+		dev_err(chip->dev, "Failed to set sampling state.\n");
+	return ret;
+}
+
+/*
+ * Function for setting the driver state for sampling and irq. Either direct
+ * mode of buffer mode will be claimed during the transition to prevent races
+ * between sysfs read, buffer or events.
+ */
+static int opt4060_set_driver_state(struct iio_dev *indio_dev,
+				    bool continuous_sampling,
+				    bool continuous_irq)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	int ret = 0;
+any_mode_retry:
+	if (iio_device_claim_buffer_mode(indio_dev)) {
+		/*
+		 * This one is a *bit* hacky. If we cannot claim buffer mode,
+		 * then try direct mode so that we make sure things cannot
+		 * concurrently change. And we just keep trying until we get one
+		 * of the modes...
+		 */
+		if (iio_device_claim_direct_mode(indio_dev))
+			goto any_mode_retry;
+		/*
+		 * This path means that we managed to claim direct mode. In
+		 * this case the buffer isn't enabled and it's okay to leave
+		 * continuous mode for sampling and/or irq.
+		 */
+		ret = opt4060_set_state_common(chip, continuous_sampling,
+					       continuous_irq);
+		iio_device_release_direct_mode(indio_dev);
+	} else {
+		/*
+		 * This path means that we managed to claim buffer mode. In
+		 * this case the buffer is enabled and irq and sampling must go
+		 * to or remain continuous, but only if the trigger is from this
+		 * device.
+		 */
+		if (!iio_trigger_validate_own_device(indio_dev->trig, indio_dev))
+			ret = opt4060_set_state_common(chip, true, true);
+		else
+			ret = opt4060_set_state_common(chip, continuous_sampling,
+						       continuous_irq);
+		iio_device_release_buffer_mode(indio_dev);
+	}
+	return ret;
+}
+
+/*
+ * This function is called with framework mutex locked.
+ */
+static int opt4060_trigger_set_state(struct iio_trigger *trig, bool state)
+{
+	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+
+	return opt4060_set_state_common(chip, state, state);
+}
+
+static int opt4060_read_raw_value(struct opt4060_chip *chip,
+				  unsigned long address, u32 *raw)
+{
+	int ret;
+	u16 result[2];
+	u32 mantissa_raw;
+	u16 msb, lsb;
+	u8 exp, count, crc, calc_crc;
+
+	ret = regmap_bulk_read(chip->regmap, address, result, 2);
+	if (ret) {
+		dev_err(chip->dev, "Reading channel data failed\n");
+		return ret;
+	}
+	exp = FIELD_GET(OPT4060_EXPONENT_MASK, result[0]);
+	msb = FIELD_GET(OPT4060_MSB_MASK, result[0]);
+	count = FIELD_GET(OPT4060_COUNTER_MASK, result[1]);
+	crc = FIELD_GET(OPT4060_CRC_MASK, result[1]);
+	lsb = FIELD_GET(OPT4060_LSB_MASK, result[1]);
+	mantissa_raw = (msb << 8) + lsb;
+	calc_crc = opt4060_calculate_crc(exp, mantissa_raw, count);
+	if (calc_crc != crc)
+		return -EIO;
+	*raw = mantissa_raw << exp;
+	return 0;
+}
+
+static int opt4060_trigger_new_samples(struct iio_dev *indio_dev)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	int ret;
+
+	/*
+	 * The conversion time should be 500us startup time plus the integration time
+	 * times the number of channels. An exact timeout isn't critical, it's better
+	 * not to get incorrect errors in the log. Setting the timeout to double the
+	 * theoretical time plus and extra 100ms margin.
+	 */
+	unsigned int timeout_us = (500 + OPT4060_NUM_CHANS *
+				  opt4060_int_time_reg[chip->int_time][0]) * 2 + 100000;
+
+	/* Setting the state in one shot mode with irq on each sample. */
+	ret = opt4060_set_driver_state(indio_dev, false, true);
+	if (ret)
+		return ret;
+
+	if (chip->irq) {
+		guard(mutex)(&chip->irq_setting_lock);
+		reinit_completion(&chip->completion);
+		if (wait_for_completion_timeout(&chip->completion,
+						usecs_to_jiffies(timeout_us)) == 0) {
+			dev_err(chip->dev, "Completion timed out.\n");
+			return -ETIME;
+		}
+	} else {
+		unsigned int ready;
+
+		ret = regmap_read_poll_timeout(chip->regmap, OPT4060_RES_CTRL,
+					       ready, (ready & OPT4060_RES_CTRL_CONV_READY),
+					       1000, timeout_us);
+		if (ret)
+			dev_err(chip->dev, "Conversion ready did not finish within timeout.\n");
+	}
+	/* Setting the state in one shot mode with irq on thresholds. */
+	return opt4060_set_driver_state(indio_dev, false, false);
+}
+
+static int opt4060_read_chan_raw(struct iio_dev *indio_dev,
+				 struct iio_chan_spec const *chan, int *val)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	u32 adc_raw;
+	int ret;
+
+	ret = opt4060_trigger_new_samples(indio_dev);
+	if (ret) {
+		dev_err(chip->dev, "Failed to trigger new samples.\n");
+		return ret;
+	}
+
+	ret = opt4060_read_raw_value(chip, chan->address, &adc_raw);
+	if (ret) {
+		dev_err(chip->dev, "Reading raw channel data failed.\n");
+		return ret;
+	}
+	*val = adc_raw;
+	return IIO_VAL_INT;
+}
+
+/*
+ * Returns the scale values used for red, green and blue. Scales the raw value
+ * so that for a particular test light source, typically white, the measurement
+ * intensity is the same across different color channels.
+ */
+static int opt4060_get_chan_scale(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  int *val, int *val2)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+
+	switch (chan->scan_index) {
+	case OPT4060_RED:
+		/* 2.4 */
+		*val = 2;
+		*val2 = 400000;
+		break;
+	case OPT4060_GREEN:
+		/* 1.0 */
+		*val = 1;
+		*val2 = 0;
+		break;
+	case OPT4060_BLUE:
+		/* 1.3 */
+		*val = 1;
+		*val2 = 300000;
+		break;
+	default:
+		dev_err(chip->dev, "Unexpected channel index.\n");
+		return -EINVAL;
+	}
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static int opt4060_calc_illuminance(struct opt4060_chip *chip, int *val)
+{
+	u32 lux_raw;
+	int ret;
+
+	/* The green wide spectral channel is used for illuminance. */
+	ret = opt4060_read_raw_value(chip, OPT4060_GREEN_MSB, &lux_raw);
+	if (ret) {
+		dev_err(chip->dev, "Reading raw channel data failed\n");
+		return ret;
+	}
+
+	/* Illuminance is calculated by ADC_RAW * 2.15e-3. */
+	*val = DIV_U64_ROUND_CLOSEST((u64)(lux_raw * 215), 1000);
+	return ret;
+}
+
+static int opt4060_read_illuminance(struct iio_dev *indio_dev,
+				    struct iio_chan_spec const *chan,
+				    int *val)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	int ret;
+
+	ret = opt4060_trigger_new_samples(indio_dev);
+	if (ret) {
+		dev_err(chip->dev, "Failed to trigger new samples.\n");
+		return ret;
+	}
+	ret = opt4060_calc_illuminance(chip, val);
+	if (ret) {
+		dev_err(chip->dev, "Failed to calculate illuminance.\n");
+		return ret;
+	}
+
+	return IIO_VAL_INT;
+}
+
+static int opt4060_set_int_time(struct opt4060_chip *chip)
+{
+	unsigned int regval;
+	int ret;
+
+	regval = FIELD_PREP(OPT4060_CTRL_CONV_TIME_MASK, chip->int_time);
+	ret = regmap_update_bits(chip->regmap, OPT4060_CTRL,
+				 OPT4060_CTRL_CONV_TIME_MASK, regval);
+	if (ret)
+		dev_err(chip->dev, "Failed to set integration time.\n");
+
+	return ret;
+}
+
+static int opt4060_power_down(struct opt4060_chip *chip)
+{
+	int ret;
+
+	ret = regmap_clear_bits(chip->regmap, OPT4060_CTRL, OPT4060_CTRL_OPER_MODE_MASK);
+	if (ret)
+		dev_err(chip->dev, "Failed to power down\n");
+
+	return ret;
+}
+
+static void opt4060_chip_off_action(void *chip)
+{
+	opt4060_power_down(chip);
+}
+
+#define _OPT4060_COLOR_CHANNEL(_color, _mask, _ev_spec, _num_ev_spec)		\
+{										\
+	.type = IIO_INTENSITY,							\
+	.modified = 1,								\
+	.channel2 = IIO_MOD_LIGHT_##_color,					\
+	.info_mask_separate = _mask,						\
+	.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),			\
+	.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),	\
+	.address = OPT4060_##_color##_MSB,					\
+	.scan_index = OPT4060_##_color,						\
+	.scan_type = {								\
+		.sign = 'u',							\
+		.realbits = 32,							\
+		.storagebits = 32,						\
+		.endianness = IIO_CPU,						\
+	},									\
+	.event_spec = _ev_spec,							\
+	.num_event_specs = _num_ev_spec,					\
+}
+
+#define OPT4060_COLOR_CHANNEL(_color, _mask)					\
+	_OPT4060_COLOR_CHANNEL(_color, _mask, opt4060_event_spec,		\
+			       ARRAY_SIZE(opt4060_event_spec))			\
+
+#define OPT4060_COLOR_CHANNEL_NO_EVENTS(_color, _mask)				\
+	_OPT4060_COLOR_CHANNEL(_color, _mask, NULL, 0)				\
+
+#define OPT4060_LIGHT_CHANNEL(_channel)						\
+{										\
+	.type = IIO_LIGHT,							\
+	.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),			\
+	.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),			\
+	.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),	\
+	.scan_index = OPT4060_##_channel,					\
+	.scan_type = {								\
+		.sign = 'u',							\
+		.realbits = 32,							\
+		.storagebits = 32,						\
+		.endianness = IIO_CPU,						\
+	},									\
+}
+
+static const struct iio_event_spec opt4060_event_spec[] = {
+	{
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_RISING,
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
+				 BIT(IIO_EV_INFO_ENABLE),
+	}, {
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_FALLING,
+		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
+				 BIT(IIO_EV_INFO_ENABLE),
+	}, {
+		.type = IIO_EV_TYPE_THRESH,
+		.dir = IIO_EV_DIR_EITHER,
+		.mask_separate = BIT(IIO_EV_INFO_PERIOD),
+	},
+};
+
+static const struct iio_chan_spec opt4060_channels[] = {
+	OPT4060_COLOR_CHANNEL(RED, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)),
+	OPT4060_COLOR_CHANNEL(GREEN, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)),
+	OPT4060_COLOR_CHANNEL(BLUE, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)),
+	OPT4060_COLOR_CHANNEL(CLEAR, BIT(IIO_CHAN_INFO_RAW)),
+	OPT4060_LIGHT_CHANNEL(ILLUM),
+	IIO_CHAN_SOFT_TIMESTAMP(OPT4060_NUM_CHANS),
+};
+
+static const struct iio_chan_spec opt4060_channels_no_events[] = {
+	OPT4060_COLOR_CHANNEL_NO_EVENTS(RED, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)),
+	OPT4060_COLOR_CHANNEL_NO_EVENTS(GREEN, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)),
+	OPT4060_COLOR_CHANNEL_NO_EVENTS(BLUE, BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE)),
+	OPT4060_COLOR_CHANNEL_NO_EVENTS(CLEAR, BIT(IIO_CHAN_INFO_RAW)),
+	OPT4060_LIGHT_CHANNEL(ILLUM),
+	IIO_CHAN_SOFT_TIMESTAMP(OPT4060_NUM_CHANS),
+};
+
+static int opt4060_read_raw(struct iio_dev *indio_dev,
+			    struct iio_chan_spec const *chan,
+			    int *val, int *val2, long mask)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		return opt4060_read_chan_raw(indio_dev, chan, val);
+	case IIO_CHAN_INFO_SCALE:
+		return opt4060_get_chan_scale(indio_dev, chan, val, val2);
+	case IIO_CHAN_INFO_PROCESSED:
+		return opt4060_read_illuminance(indio_dev, chan, val);
+	case IIO_CHAN_INFO_INT_TIME:
+		*val = 0;
+		*val2 = opt4060_int_time_reg[chip->int_time][0];
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int opt4060_write_raw(struct iio_dev *indio_dev,
+			     struct iio_chan_spec const *chan,
+			     int val, int val2, long mask)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	int int_time;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		int_time = opt4060_als_time_to_index(val2);
+		if (int_time < 0)
+			return int_time;
+		chip->int_time = int_time;
+		return opt4060_set_int_time(chip);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int opt4060_write_raw_get_fmt(struct iio_dev *indio_dev,
+				     struct iio_chan_spec const *chan,
+				     long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		return IIO_VAL_INT_PLUS_MICRO;
+	default:
+		return -EINVAL;
+	}
+}
+
+static u32 opt4060_calc_th_reg(u32 adc_val)
+{
+	u32 th_val, th_exp, bits;
+	/*
+	 * The threshold registers take 4 bits of exponent and 12 bits of data
+	 * ADC = TH_VAL << (8 + TH_EXP)
+	 */
+	bits = fls(adc_val);
+
+	if (bits > 31)
+		th_exp = 11; /* Maximum exponent */
+	else if (bits > 20)
+		th_exp = bits - 20;
+	else
+		th_exp = 0;
+	th_val = (adc_val >> (8 + th_exp)) & 0xfff;
+
+	return (th_exp << 12) + th_val;
+}
+
+static u32 opt4060_calc_val_from_th_reg(u32 th_reg)
+{
+	/*
+	 * The threshold registers take 4 bits of exponent and 12 bits of data
+	 * ADC = TH_VAL << (8 + TH_EXP)
+	 */
+	u32 th_val, th_exp;
+
+	th_exp = (th_reg >> 12) & 0xf;
+	th_val = th_reg & 0xfff;
+
+	return th_val << (8 + th_exp);
+}
+
+static int opt4060_read_available(struct iio_dev *indio_dev,
+				  struct iio_chan_spec const *chan,
+				  const int **vals, int *type, int *length,
+				  long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_INT_TIME:
+		*length = ARRAY_SIZE(opt4060_int_time_available) * 2;
+		*vals = (const int *)opt4060_int_time_available;
+		*type = IIO_VAL_INT_PLUS_MICRO;
+		return IIO_AVAIL_LIST;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t opt4060_read_ev_period(struct opt4060_chip *chip, int *val,
+				      int *val2)
+{
+	int ret, pers, fault_count, int_time;
+	u64 uval;
+
+	int_time = opt4060_int_time_reg[chip->int_time][0];
+
+	ret = regmap_read(chip->regmap, OPT4060_CTRL, &fault_count);
+	if (ret < 0)
+		return ret;
+
+	fault_count = fault_count & OPT4060_CTRL_FAULT_COUNT_MASK;
+	switch (fault_count) {
+	case OPT4060_CTRL_FAULT_COUNT_2:
+		pers = 2;
+		break;
+	case OPT4060_CTRL_FAULT_COUNT_4:
+		pers = 4;
+		break;
+	case OPT4060_CTRL_FAULT_COUNT_8:
+		pers = 8;
+		break;
+
+	default:
+		pers = 1;
+		break;
+	}
+
+	uval = mul_u32_u32(int_time, pers);
+	*val = div_u64_rem(uval, MICRO, val2);
+
+	return IIO_VAL_INT_PLUS_MICRO;
+}
+
+static ssize_t opt4060_write_ev_period(struct opt4060_chip *chip, int val,
+				       int val2)
+{
+	u64 uval, int_time;
+	unsigned int regval, fault_count_val;
+
+	uval = mul_u32_u32(val, MICRO) + val2;
+	int_time = opt4060_int_time_reg[chip->int_time][0];
+
+	/* Check if the period is closest to 1, 2, 4 or 8 times integration time.*/
+	if (uval <= int_time)
+		fault_count_val = OPT4060_CTRL_FAULT_COUNT_1;
+	else if (uval <= int_time * 2)
+		fault_count_val = OPT4060_CTRL_FAULT_COUNT_2;
+	else if (uval <= int_time * 4)
+		fault_count_val = OPT4060_CTRL_FAULT_COUNT_4;
+	else
+		fault_count_val = OPT4060_CTRL_FAULT_COUNT_8;
+
+	regval = FIELD_PREP(OPT4060_CTRL_FAULT_COUNT_MASK, fault_count_val);
+	return regmap_update_bits(chip->regmap, OPT4060_CTRL,
+				 OPT4060_CTRL_FAULT_COUNT_MASK, regval);
+}
+
+static int opt4060_get_channel_sel(struct opt4060_chip *chip, int *ch_sel)
+{
+	int ret;
+	u32 regval;
+
+	ret = regmap_read(chip->regmap, OPT4060_INT_CTRL, &regval);
+	if (ret) {
+		dev_err(chip->dev, "Failed to get channel selection.\n");
+		return ret;
+	}
+	*ch_sel = FIELD_GET(OPT4060_INT_CTRL_THRESH_SEL, regval);
+	return ret;
+}
+
+static int opt4060_set_channel_sel(struct opt4060_chip *chip, int ch_sel)
+{
+	int ret;
+	u32 regval;
+
+	regval = FIELD_PREP(OPT4060_INT_CTRL_THRESH_SEL, ch_sel);
+	ret = regmap_update_bits(chip->regmap, OPT4060_INT_CTRL,
+				 OPT4060_INT_CTRL_THRESH_SEL, regval);
+	if (ret)
+		dev_err(chip->dev, "Failed to set channel selection.\n");
+	return ret;
+}
+
+static int opt4060_get_thresholds(struct opt4060_chip *chip, u32 *th_lo, u32 *th_hi)
+{
+	int ret;
+	u32 regval;
+
+	ret = regmap_read(chip->regmap, OPT4060_THRESHOLD_LOW, &regval);
+	if (ret) {
+		dev_err(chip->dev, "Failed to read THRESHOLD_LOW.\n");
+		return ret;
+	}
+	*th_lo = opt4060_calc_val_from_th_reg(regval);
+
+	ret = regmap_read(chip->regmap, OPT4060_THRESHOLD_HIGH, &regval);
+	if (ret) {
+		dev_err(chip->dev, "Failed to read THRESHOLD_LOW.\n");
+		return ret;
+	}
+	*th_hi = opt4060_calc_val_from_th_reg(regval);
+
+	return ret;
+}
+
+static int opt4060_set_thresholds(struct opt4060_chip *chip, u32 th_lo, u32 th_hi)
+{
+	int ret;
+
+	ret = regmap_write(chip->regmap, OPT4060_THRESHOLD_LOW, opt4060_calc_th_reg(th_lo));
+	if (ret) {
+		dev_err(chip->dev, "Failed to write THRESHOLD_LOW.\n");
+		return ret;
+	}
+
+	ret = regmap_write(chip->regmap, OPT4060_THRESHOLD_HIGH, opt4060_calc_th_reg(th_hi));
+	if (ret)
+		dev_err(chip->dev, "Failed to write THRESHOLD_HIGH.\n");
+
+	return ret;
+}
+
+static int opt4060_read_event(struct iio_dev *indio_dev,
+			      const struct iio_chan_spec *chan,
+			      enum iio_event_type type,
+			      enum iio_event_direction dir,
+			      enum iio_event_info info,
+			      int *val, int *val2)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	u32 th_lo, th_hi;
+	int ret;
+
+	if (chan->type != IIO_INTENSITY)
+		return -EINVAL;
+	if (type != IIO_EV_TYPE_THRESH)
+		return -EINVAL;
+
+	switch (info) {
+	case IIO_EV_INFO_VALUE:
+		ret = opt4060_get_thresholds(chip, &th_lo, &th_hi);
+		if (ret)
+			return ret;
+		if (dir == IIO_EV_DIR_FALLING) {
+			*val = th_lo;
+			ret = IIO_VAL_INT;
+		} else if (dir == IIO_EV_DIR_RISING) {
+			*val = th_hi;
+			ret = IIO_VAL_INT;
+		}
+		return ret;
+	case IIO_EV_INFO_PERIOD:
+		return opt4060_read_ev_period(chip, val, val2);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int opt4060_write_event(struct iio_dev *indio_dev,
+			       const struct iio_chan_spec *chan,
+			       enum iio_event_type type,
+			       enum iio_event_direction dir,
+			       enum iio_event_info info,
+			       int val, int val2)
+{
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	u32 th_lo, th_hi;
+	int ret;
+
+	if (chan->type != IIO_INTENSITY)
+		return -EINVAL;
+	if (type != IIO_EV_TYPE_THRESH)
+		return -EINVAL;
+
+	switch (info) {
+	case IIO_EV_INFO_VALUE:
+		ret = opt4060_get_thresholds(chip, &th_lo, &th_hi);
+		if (ret)
+			return ret;
+		if (dir == IIO_EV_DIR_FALLING)
+			th_lo = val;
+		else if (dir == IIO_EV_DIR_RISING)
+			th_hi = val;
+		return opt4060_set_thresholds(chip, th_lo, th_hi);
+	case IIO_EV_INFO_PERIOD:
+		return opt4060_write_ev_period(chip, val, val2);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int opt4060_read_event_config(struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan,
+				     enum iio_event_type type,
+				     enum iio_event_direction dir)
+{
+	int ch_sel, ch_idx = chan->scan_index;
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	int ret;
+
+	if (chan->type != IIO_INTENSITY)
+		return -EINVAL;
+	if (type != IIO_EV_TYPE_THRESH)
+		return -EINVAL;
+
+	ret = opt4060_get_channel_sel(chip, &ch_sel);
+	if (ret)
+		return ret;
+
+	if (((dir == IIO_EV_DIR_FALLING) && chip->thresh_event_lo_active) ||
+	    ((dir == IIO_EV_DIR_RISING) && chip->thresh_event_hi_active))
+		return ch_sel == ch_idx;
+
+	return ret;
+}
+
+static int opt4060_write_event_config(struct iio_dev *indio_dev,
+				      const struct iio_chan_spec *chan,
+				      enum iio_event_type type,
+				      enum iio_event_direction dir, bool state)
+{
+	int ch_sel, ch_idx = chan->scan_index;
+	struct opt4060_chip *chip = iio_priv(indio_dev);
+	int ret;
+
+	guard(mutex)(&chip->event_enabling_lock);
+
+	if (chan->type != IIO_INTENSITY)
+		return -EINVAL;
+	if (type != IIO_EV_TYPE_THRESH)
+		return -EINVAL;
+
+	ret = opt4060_get_channel_sel(chip, &ch_sel);
+	if (ret)
+		return ret;
+
+	if (state) {
+		/* Only one channel can be active at the same time */
+		if ((chip->thresh_event_lo_active || chip->thresh_event_hi_active) &&
+		    (ch_idx != ch_sel))
+			return -EBUSY;
+		if (dir == IIO_EV_DIR_FALLING)
+			chip->thresh_event_lo_active = true;
+		else if (dir == IIO_EV_DIR_RISING)
+			chip->thresh_event_hi_active = true;
+		ret = opt4060_set_channel_sel(chip, ch_idx);
+		if (ret)
+			return ret;
+	} else {
+		if (ch_idx == ch_sel) {
+			if (dir == IIO_EV_DIR_FALLING)
+				chip->thresh_event_lo_active = false;
+			else if (dir == IIO_EV_DIR_RISING)
+				chip->thresh_event_hi_active = false;
+		}
+	}
+
+	return opt4060_set_driver_state(indio_dev,
+					chip->thresh_event_hi_active |
+					chip->thresh_event_lo_active,
+					false);
+}
+
+static const struct iio_info opt4060_info = {
+	.read_raw = opt4060_read_raw,
+	.write_raw = opt4060_write_raw,
+	.write_raw_get_fmt = opt4060_write_raw_get_fmt,
+	.read_avail = opt4060_read_available,
+	.read_event_value = opt4060_read_event,
+	.write_event_value = opt4060_write_event,
+	.read_event_config = opt4060_read_event_config,
+	.write_event_config = opt4060_write_event_config,
+};
+
+static const struct iio_info opt4060_info_no_irq = {
+	.read_raw = opt4060_read_raw,
+	.write_raw = opt4060_write_raw,
+	.write_raw_get_fmt = opt4060_write_raw_get_fmt,
+	.read_avail = opt4060_read_available,
+};
+
+static int opt4060_load_defaults(struct opt4060_chip *chip)
+{
+	u16 reg;
+	int ret;
+
+	chip->int_time = OPT4060_DEFAULT_CONVERSION_TIME;
+
+	/* Set initial MIN/MAX thresholds */
+	ret = opt4060_set_thresholds(chip, 0, UINT_MAX);
+	if (ret)
+		return ret;
+
+	/*
+	 * Setting auto-range, latched window for thresholds, one-shot conversion
+	 * and quick wake-up mode as default.
+	 */
+	reg = FIELD_PREP(OPT4060_CTRL_RANGE_MASK,
+			 OPT4060_CTRL_LIGHT_SCALE_AUTO);
+	reg |= FIELD_PREP(OPT4060_CTRL_CONV_TIME_MASK, chip->int_time);
+	reg |= FIELD_PREP(OPT4060_CTRL_OPER_MODE_MASK,
+				OPT4060_CTRL_OPER_MODE_ONE_SHOT);
+	reg |= OPT4060_CTRL_QWAKE_MASK | OPT4060_CTRL_LATCH_MASK;
+
+	ret = regmap_write(chip->regmap, OPT4060_CTRL, reg);
+	if (ret)
+		dev_err(chip->dev, "Failed to set configuration\n");
+
+	return ret;
+}
+
+static bool opt4060_volatile_reg(struct device *dev, unsigned int reg)
+{
+	return reg <= OPT4060_CLEAR_LSB || reg == OPT4060_RES_CTRL;
+}
+
+static bool opt4060_writable_reg(struct device *dev, unsigned int reg)
+{
+	return reg >= OPT4060_THRESHOLD_LOW || reg >= OPT4060_INT_CTRL;
+}
+
+static bool opt4060_readonly_reg(struct device *dev, unsigned int reg)
+{
+	return reg == OPT4060_DEVICE_ID;
+}
+
+static bool opt4060_readable_reg(struct device *dev, unsigned int reg)
+{
+	/* Volatile, writable and read-only registers are readable. */
+	return opt4060_volatile_reg(dev, reg) || opt4060_writable_reg(dev, reg) ||
+	       opt4060_readonly_reg(dev, reg);
+}
+
+static const struct regmap_config opt4060_regmap_config = {
+	.name = "opt4060",
+	.reg_bits = 8,
+	.val_bits = 16,
+	.cache_type = REGCACHE_RBTREE,
+	.max_register = OPT4060_DEVICE_ID,
+	.readable_reg = opt4060_readable_reg,
+	.writeable_reg = opt4060_writable_reg,
+	.volatile_reg = opt4060_volatile_reg,
+	.val_format_endian = REGMAP_ENDIAN_BIG,
+};
+
+static const struct iio_trigger_ops opt4060_trigger_ops = {
+	.set_trigger_state = opt4060_trigger_set_state,
+};
+
+static irqreturn_t opt4060_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *idev = pf->indio_dev;
+	struct opt4060_chip *chip = iio_priv(idev);
+	struct  {
+		u32 chan[OPT4060_NUM_CHANS];
+		aligned_s64 ts;
+	} raw;
+	int i = 0;
+	int chan, ret;
+
+	/* If the trigger is not from this driver, a new sample is needed.*/
+	if (iio_trigger_validate_own_device(idev->trig, idev))
+		opt4060_trigger_new_samples(idev);
+
+	memset(&raw, 0, sizeof(raw));
+
+	iio_for_each_active_channel(idev, chan) {
+		if (chan == OPT4060_ILLUM)
+			ret = opt4060_calc_illuminance(chip, &raw.chan[i++]);
+		else
+			ret = opt4060_read_raw_value(chip,
+						     idev->channels[chan].address,
+						     &raw.chan[i++]);
+		if (ret) {
+			dev_err(chip->dev, "Reading channel data failed\n");
+			goto err_read;
+		}
+	}
+
+	iio_push_to_buffers_with_timestamp(idev, &raw, pf->timestamp);
+err_read:
+	iio_trigger_notify_done(idev->trig);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t opt4060_irq_thread(int irq, void *private)
+{
+	struct iio_dev *idev = private;
+	struct opt4060_chip *chip = iio_priv(idev);
+	int ret, dummy;
+	unsigned int int_res;
+
+	ret = regmap_read(chip->regmap, OPT4060_RES_CTRL, &int_res);
+	if (ret < 0) {
+		dev_err(chip->dev, "Failed to read interrupt reasons.\n");
+		return IRQ_NONE;
+	}
+
+	/* Read OPT4060_CTRL to clear interrupt */
+	ret = regmap_read(chip->regmap, OPT4060_CTRL, &dummy);
+	if (ret < 0) {
+		dev_err(chip->dev, "Failed to clear interrupt\n");
+		return IRQ_NONE;
+	}
+
+	/* Handle events */
+	if (int_res & (OPT4060_RES_CTRL_FLAG_H | OPT4060_RES_CTRL_FLAG_L)) {
+		u64 code;
+		int chan = 0;
+
+		ret = opt4060_get_channel_sel(chip, &chan);
+		if (ret) {
+			dev_err(chip->dev, "Failed to read threshold channel.\n");
+			return IRQ_NONE;
+		}
+
+		/* Check if the interrupt is from the lower threshold */
+		if (int_res & OPT4060_RES_CTRL_FLAG_L) {
+			code = IIO_MOD_EVENT_CODE(IIO_INTENSITY,
+						  chan,
+						  idev->channels[chan].channel2,
+						  IIO_EV_TYPE_THRESH,
+						  IIO_EV_DIR_FALLING);
+			iio_push_event(idev, code, iio_get_time_ns(idev));
+		}
+		/* Check if the interrupt is from the upper threshold */
+		if (int_res & OPT4060_RES_CTRL_FLAG_H) {
+			code = IIO_MOD_EVENT_CODE(IIO_INTENSITY,
+						  chan,
+						  idev->channels[chan].channel2,
+						  IIO_EV_TYPE_THRESH,
+						  IIO_EV_DIR_RISING);
+			iio_push_event(idev, code, iio_get_time_ns(idev));
+		}
+	}
+
+	/* Handle conversion ready */
+	if (int_res & OPT4060_RES_CTRL_CONV_READY) {
+		/* Signal completion for potentially waiting reads */
+		complete(&chip->completion);
+
+		/* Handle data ready triggers */
+		if (iio_buffer_enabled(idev))
+			iio_trigger_poll_nested(chip->trig);
+	}
+	return IRQ_HANDLED;
+}
+
+static int opt4060_setup_buffer(struct opt4060_chip *chip, struct iio_dev *idev)
+{
+	int ret;
+
+	ret = devm_iio_triggered_buffer_setup(chip->dev, idev,
+					      &iio_pollfunc_store_time,
+					      opt4060_trigger_handler, NULL);
+	if (ret)
+		return dev_err_probe(chip->dev, ret,
+				     "Buffer setup failed.\n");
+	return ret;
+}
+
+static int opt4060_setup_trigger(struct opt4060_chip *chip, struct iio_dev *idev)
+{
+	struct iio_trigger *data_trigger;
+	char *name;
+	int ret;
+
+	data_trigger = devm_iio_trigger_alloc(chip->dev, "%s-data-ready-dev%d",
+					      idev->name, iio_device_id(idev));
+	if (!data_trigger)
+		return -ENOMEM;
+
+	/*
+	 * The data trigger allows for sample capture on each new conversion
+	 * ready interrupt.
+	 */
+	chip->trig = data_trigger;
+	data_trigger->ops = &opt4060_trigger_ops;
+	iio_trigger_set_drvdata(data_trigger, idev);
+	ret = devm_iio_trigger_register(chip->dev, data_trigger);
+	if (ret)
+		return dev_err_probe(chip->dev, ret,
+				     "Data ready trigger registration failed\n");
+
+	name = devm_kasprintf(chip->dev, GFP_KERNEL, "%s-opt4060",
+			      dev_name(chip->dev));
+	if (!name)
+		return dev_err_probe(chip->dev, -ENOMEM, "Failed to alloc chip name\n");
+
+	ret = devm_request_threaded_irq(chip->dev, chip->irq, NULL, opt4060_irq_thread,
+					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					name, idev);
+	if (ret)
+		return dev_err_probe(chip->dev, ret, "Could not request IRQ\n");
+
+	init_completion(&chip->completion);
+
+	ret = devm_mutex_init(chip->dev, &chip->irq_setting_lock);
+	if (ret)
+		return ret;
+
+	ret = devm_mutex_init(chip->dev, &chip->event_enabling_lock);
+	if (ret)
+		return ret;
+
+	ret = regmap_write_bits(chip->regmap, OPT4060_INT_CTRL,
+				OPT4060_INT_CTRL_OUTPUT,
+				OPT4060_INT_CTRL_OUTPUT);
+	if (ret)
+		return dev_err_probe(chip->dev, ret,
+				     "Failed to set interrupt as output\n");
+
+	return 0;
+}
+
+static int opt4060_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct opt4060_chip *chip;
+	struct iio_dev *indio_dev;
+	int ret;
+	unsigned int regval, dev_id;
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*chip));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	chip = iio_priv(indio_dev);
+
+	ret = devm_regulator_get_enable(dev, "vdd");
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to enable vdd supply\n");
+
+	chip->regmap = devm_regmap_init_i2c(client, &opt4060_regmap_config);
+	if (IS_ERR(chip->regmap))
+		return dev_err_probe(dev, PTR_ERR(chip->regmap),
+				     "regmap initialization failed\n");
+
+	chip->dev = dev;
+	chip->irq = client->irq;
+
+	ret = regmap_reinit_cache(chip->regmap, &opt4060_regmap_config);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to reinit regmap cache\n");
+
+	ret = regmap_read(chip->regmap, OPT4060_DEVICE_ID, &regval);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+			"Failed to read the device ID register\n");
+
+	dev_id = FIELD_GET(OPT4060_DEVICE_ID_MASK, regval);
+	if (dev_id != OPT4060_DEVICE_ID_VAL)
+		dev_info(dev, "Device ID: %#04x unknown\n", dev_id);
+
+	if (chip->irq) {
+		indio_dev->info = &opt4060_info;
+		indio_dev->channels = opt4060_channels;
+		indio_dev->num_channels = ARRAY_SIZE(opt4060_channels);
+	} else {
+		indio_dev->info = &opt4060_info_no_irq;
+		indio_dev->channels = opt4060_channels_no_events;
+		indio_dev->num_channels = ARRAY_SIZE(opt4060_channels_no_events);
+	}
+	indio_dev->modes = INDIO_DIRECT_MODE;
+	indio_dev->name = "opt4060";
+
+	ret = opt4060_load_defaults(chip);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to set sensor defaults\n");
+
+	ret = devm_add_action_or_reset(dev, opt4060_chip_off_action, chip);
+	if (ret < 0)
+		return dev_err_probe(dev, ret,
+				     "Failed to setup power off action\n");
+
+	ret = opt4060_setup_buffer(chip, indio_dev);
+	if (ret)
+		return ret;
+
+	if (chip->irq) {
+		ret = opt4060_setup_trigger(chip, indio_dev);
+		if (ret)
+			return ret;
+	}
+
+	return devm_iio_device_register(dev, indio_dev);
+}
+
+static const struct i2c_device_id opt4060_id[] = {
+	{ "opt4060", },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, opt4060_id);
+
+static const struct of_device_id opt4060_of_match[] = {
+	{ .compatible = "ti,opt4060" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, opt4060_of_match);
+
+static struct i2c_driver opt4060_driver = {
+	.driver = {
+		.name = "opt4060",
+		.of_match_table = opt4060_of_match,
+	},
+	.probe = opt4060_probe,
+	.id_table = opt4060_id,
+};
+module_i2c_driver(opt4060_driver);
+
+MODULE_AUTHOR("Per-Daniel Olsson <perdaniel.olsson@axis.com>");
+MODULE_DESCRIPTION("Texas Instruments OPT4060 RGBW color sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/iio/light/rohm-bu27008.c b/drivers/iio/light/rohm-bu27008.c
deleted file mode 100644
index fa35dd32700c..000000000000
--- a/drivers/iio/light/rohm-bu27008.c
+++ /dev/null
@@ -1,1635 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ROHM Colour Sensor driver for
- * - BU27008 RGBC sensor
- * - BU27010 RGBC + Flickering sensor
- *
- * Copyright (c) 2023, ROHM Semiconductor.
- */
-
-#include <linux/bitfield.h>
-#include <linux/bitops.h>
-#include <linux/device.h>
-#include <linux/i2c.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/property.h>
-#include <linux/regmap.h>
-#include <linux/regulator/consumer.h>
-#include <linux/units.h>
-
-#include <linux/iio/iio.h>
-#include <linux/iio/iio-gts-helper.h>
-#include <linux/iio/trigger.h>
-#include <linux/iio/trigger_consumer.h>
-#include <linux/iio/triggered_buffer.h>
-
-/*
- * A word about register address and mask definitions.
- *
- * At a quick glance to the data-sheet register tables, the BU27010 has all the
- * registers that the BU27008 has. On top of that the BU27010 adds couple of new
- * ones.
- *
- * So, all definitions BU27008_REG_* are there also for BU27010 but none of the
- * BU27010_REG_* are present on BU27008. This makes sense as BU27010 just adds
- * some features (Flicker FIFO, more power control) on top of the BU27008.
- *
- * Unfortunately, some of the wheel has been re-invented. Even though the names
- * of the registers have stayed the same, pretty much all of the functionality
- * provided by the registers has changed place. Contents of all MODE_CONTROL
- * registers on BU27008 and BU27010 are different.
- *
- * Chip-specific mapping from register addresses/bits to functionality is done
- * in bu27_chip_data structures.
- */
-#define BU27008_REG_SYSTEM_CONTROL	0x40
-#define BU27008_MASK_SW_RESET		BIT(7)
-#define BU27008_MASK_PART_ID		GENMASK(5, 0)
-#define BU27008_ID			0x1a
-#define BU27008_REG_MODE_CONTROL1	0x41
-#define BU27008_MASK_MEAS_MODE		GENMASK(2, 0)
-#define BU27008_MASK_CHAN_SEL		GENMASK(3, 2)
-
-#define BU27008_REG_MODE_CONTROL2	0x42
-#define BU27008_MASK_RGBC_GAIN		GENMASK(7, 3)
-#define BU27008_MASK_IR_GAIN_LO		GENMASK(2, 0)
-#define BU27008_SHIFT_IR_GAIN		3
-
-#define BU27008_REG_MODE_CONTROL3	0x43
-#define BU27008_MASK_VALID		BIT(7)
-#define BU27008_MASK_INT_EN		BIT(1)
-#define BU27008_INT_EN			BU27008_MASK_INT_EN
-#define BU27008_INT_DIS			0
-#define BU27008_MASK_MEAS_EN		BIT(0)
-#define BU27008_MEAS_EN			BIT(0)
-#define BU27008_MEAS_DIS		0
-
-#define BU27008_REG_DATA0_LO		0x50
-#define BU27008_REG_DATA1_LO		0x52
-#define BU27008_REG_DATA2_LO		0x54
-#define BU27008_REG_DATA3_LO		0x56
-#define BU27008_REG_DATA3_HI		0x57
-#define BU27008_REG_MANUFACTURER_ID	0x92
-#define BU27008_REG_MAX BU27008_REG_MANUFACTURER_ID
-
-/* BU27010 specific definitions */
-
-#define BU27010_MASK_SW_RESET		BIT(7)
-#define BU27010_ID			0x1b
-#define BU27010_REG_POWER		0x3e
-#define BU27010_MASK_POWER		BIT(0)
-
-#define BU27010_REG_RESET		0x3f
-#define BU27010_MASK_RESET		BIT(0)
-#define BU27010_RESET_RELEASE		BU27010_MASK_RESET
-
-#define BU27010_MASK_MEAS_EN		BIT(1)
-
-#define BU27010_MASK_CHAN_SEL		GENMASK(7, 6)
-#define BU27010_MASK_MEAS_MODE		GENMASK(5, 4)
-#define BU27010_MASK_RGBC_GAIN		GENMASK(3, 0)
-
-#define BU27010_MASK_DATA3_GAIN		GENMASK(7, 6)
-#define BU27010_MASK_DATA2_GAIN		GENMASK(5, 4)
-#define BU27010_MASK_DATA1_GAIN		GENMASK(3, 2)
-#define BU27010_MASK_DATA0_GAIN		GENMASK(1, 0)
-
-#define BU27010_MASK_FLC_MODE		BIT(7)
-#define BU27010_MASK_FLC_GAIN		GENMASK(4, 0)
-
-#define BU27010_REG_MODE_CONTROL4	0x44
-/* If flicker is ever to be supported the IRQ must be handled as a field */
-#define BU27010_IRQ_DIS_ALL		GENMASK(1, 0)
-#define BU27010_DRDY_EN			BIT(0)
-#define BU27010_MASK_INT_SEL		GENMASK(1, 0)
-
-#define BU27010_REG_MODE_CONTROL5	0x45
-#define BU27010_MASK_RGB_VALID		BIT(7)
-#define BU27010_MASK_FLC_VALID		BIT(6)
-#define BU27010_MASK_WAIT_EN		BIT(3)
-#define BU27010_MASK_FIFO_EN		BIT(2)
-#define BU27010_MASK_RGB_EN		BIT(1)
-#define BU27010_MASK_FLC_EN		BIT(0)
-
-#define BU27010_REG_DATA_FLICKER_LO	0x56
-#define BU27010_MASK_DATA_FLICKER_HI	GENMASK(2, 0)
-#define BU27010_REG_FLICKER_COUNT	0x5a
-#define BU27010_REG_FIFO_LEVEL_LO	0x5b
-#define BU27010_MASK_FIFO_LEVEL_HI	BIT(0)
-#define BU27010_REG_FIFO_DATA_LO	0x5d
-#define BU27010_REG_FIFO_DATA_HI	0x5e
-#define BU27010_MASK_FIFO_DATA_HI	GENMASK(2, 0)
-#define BU27010_REG_MANUFACTURER_ID	0x92
-#define BU27010_REG_MAX BU27010_REG_MANUFACTURER_ID
-
-/**
- * enum bu27008_chan_type - BU27008 channel types
- * @BU27008_RED:	Red channel. Always via data0.
- * @BU27008_GREEN:	Green channel. Always via data1.
- * @BU27008_BLUE:	Blue channel. Via data2 (when used).
- * @BU27008_CLEAR:	Clear channel. Via data2 or data3 (when used).
- * @BU27008_IR:		IR channel. Via data3 (when used).
- * @BU27008_LUX:	Illuminance channel, computed using RGB and IR.
- * @BU27008_NUM_CHANS:	Number of channel types.
- */
-enum bu27008_chan_type {
-	BU27008_RED,
-	BU27008_GREEN,
-	BU27008_BLUE,
-	BU27008_CLEAR,
-	BU27008_IR,
-	BU27008_LUX,
-	BU27008_NUM_CHANS
-};
-
-/**
- * enum bu27008_chan - BU27008 physical data channel
- * @BU27008_DATA0:		Always red.
- * @BU27008_DATA1:		Always green.
- * @BU27008_DATA2:		Blue or clear.
- * @BU27008_DATA3:		IR or clear.
- * @BU27008_NUM_HW_CHANS:	Number of physical channels
- */
-enum bu27008_chan {
-	BU27008_DATA0,
-	BU27008_DATA1,
-	BU27008_DATA2,
-	BU27008_DATA3,
-	BU27008_NUM_HW_CHANS
-};
-
-/* We can always measure red and green at same time */
-#define ALWAYS_SCANNABLE (BIT(BU27008_RED) | BIT(BU27008_GREEN))
-
-/* We use these data channel configs. Ensure scan_masks below follow them too */
-#define BU27008_BLUE2_CLEAR3		0x0 /* buffer is R, G, B, C */
-#define BU27008_CLEAR2_IR3		0x1 /* buffer is R, G, C, IR */
-#define BU27008_BLUE2_IR3		0x2 /* buffer is R, G, B, IR */
-
-static const unsigned long bu27008_scan_masks[] = {
-	/* buffer is R, G, B, C */
-	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_CLEAR),
-	/* buffer is R, G, C, IR */
-	ALWAYS_SCANNABLE | BIT(BU27008_CLEAR) | BIT(BU27008_IR),
-	/* buffer is R, G, B, IR */
-	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR),
-	/* buffer is R, G, B, IR, LUX */
-	ALWAYS_SCANNABLE | BIT(BU27008_BLUE) | BIT(BU27008_IR) | BIT(BU27008_LUX),
-	0
-};
-
-/*
- * Available scales with gain 1x - 1024x, timings 55, 100, 200, 400 mS
- * Time impacts to gain: 1x, 2x, 4x, 8x.
- *
- * => Max total gain is HWGAIN * gain by integration time (8 * 1024) = 8192
- *
- * Max amplification is (HWGAIN * MAX integration-time multiplier) 1024 * 8
- * = 8192. With NANO scale we get rid of accuracy loss when we start with the
- * scale 16.0 for HWGAIN1, INT-TIME 55 mS. This way the nano scale for MAX
- * total gain 8192 will be 1953125
- */
-#define BU27008_SCALE_1X 16
-
-/*
- * On BU27010 available scales with gain 1x - 4096x,
- * timings 55, 100, 200, 400 mS. Time impacts to gain: 1x, 2x, 4x, 8x.
- *
- * => Max total gain is HWGAIN * gain by integration time (8 * 4096)
- *
- * Using NANO precision for scale we must use scale 64x corresponding gain 1x
- * to avoid precision loss.
- */
-#define BU27010_SCALE_1X 64
-
-/* See the data sheet for the "Gain Setting" table */
-#define BU27008_GSEL_1X		0x00
-#define BU27008_GSEL_4X		0x08
-#define BU27008_GSEL_8X		0x09
-#define BU27008_GSEL_16X	0x0a
-#define BU27008_GSEL_32X	0x0b
-#define BU27008_GSEL_64X	0x0c
-#define BU27008_GSEL_256X	0x18
-#define BU27008_GSEL_512X	0x19
-#define BU27008_GSEL_1024X	0x1a
-
-static const struct iio_gain_sel_pair bu27008_gains[] = {
-	GAIN_SCALE_GAIN(1, BU27008_GSEL_1X),
-	GAIN_SCALE_GAIN(4, BU27008_GSEL_4X),
-	GAIN_SCALE_GAIN(8, BU27008_GSEL_8X),
-	GAIN_SCALE_GAIN(16, BU27008_GSEL_16X),
-	GAIN_SCALE_GAIN(32, BU27008_GSEL_32X),
-	GAIN_SCALE_GAIN(64, BU27008_GSEL_64X),
-	GAIN_SCALE_GAIN(256, BU27008_GSEL_256X),
-	GAIN_SCALE_GAIN(512, BU27008_GSEL_512X),
-	GAIN_SCALE_GAIN(1024, BU27008_GSEL_1024X),
-};
-
-static const struct iio_gain_sel_pair bu27008_gains_ir[] = {
-	GAIN_SCALE_GAIN(2, BU27008_GSEL_1X),
-	GAIN_SCALE_GAIN(4, BU27008_GSEL_4X),
-	GAIN_SCALE_GAIN(8, BU27008_GSEL_8X),
-	GAIN_SCALE_GAIN(16, BU27008_GSEL_16X),
-	GAIN_SCALE_GAIN(32, BU27008_GSEL_32X),
-	GAIN_SCALE_GAIN(64, BU27008_GSEL_64X),
-	GAIN_SCALE_GAIN(256, BU27008_GSEL_256X),
-	GAIN_SCALE_GAIN(512, BU27008_GSEL_512X),
-	GAIN_SCALE_GAIN(1024, BU27008_GSEL_1024X),
-};
-
-#define BU27010_GSEL_1X		0x00	/* 000000 */
-#define BU27010_GSEL_4X		0x08	/* 001000 */
-#define BU27010_GSEL_16X	0x09	/* 001001 */
-#define BU27010_GSEL_64X	0x0e	/* 001110 */
-#define BU27010_GSEL_256X	0x1e	/* 011110 */
-#define BU27010_GSEL_1024X	0x2e	/* 101110 */
-#define BU27010_GSEL_4096X	0x3f	/* 111111 */
-
-static const struct iio_gain_sel_pair bu27010_gains[] = {
-	GAIN_SCALE_GAIN(1, BU27010_GSEL_1X),
-	GAIN_SCALE_GAIN(4, BU27010_GSEL_4X),
-	GAIN_SCALE_GAIN(16, BU27010_GSEL_16X),
-	GAIN_SCALE_GAIN(64, BU27010_GSEL_64X),
-	GAIN_SCALE_GAIN(256, BU27010_GSEL_256X),
-	GAIN_SCALE_GAIN(1024, BU27010_GSEL_1024X),
-	GAIN_SCALE_GAIN(4096, BU27010_GSEL_4096X),
-};
-
-static const struct iio_gain_sel_pair bu27010_gains_ir[] = {
-	GAIN_SCALE_GAIN(2, BU27010_GSEL_1X),
-	GAIN_SCALE_GAIN(4, BU27010_GSEL_4X),
-	GAIN_SCALE_GAIN(16, BU27010_GSEL_16X),
-	GAIN_SCALE_GAIN(64, BU27010_GSEL_64X),
-	GAIN_SCALE_GAIN(256, BU27010_GSEL_256X),
-	GAIN_SCALE_GAIN(1024, BU27010_GSEL_1024X),
-	GAIN_SCALE_GAIN(4096, BU27010_GSEL_4096X),
-};
-
-#define BU27008_MEAS_MODE_100MS		0x00
-#define BU27008_MEAS_MODE_55MS		0x01
-#define BU27008_MEAS_MODE_200MS		0x02
-#define BU27008_MEAS_MODE_400MS		0x04
-
-#define BU27010_MEAS_MODE_100MS		0x00
-#define BU27010_MEAS_MODE_55MS		0x03
-#define BU27010_MEAS_MODE_200MS		0x01
-#define BU27010_MEAS_MODE_400MS		0x02
-
-#define BU27008_MEAS_TIME_MAX_MS	400
-
-static const struct iio_itime_sel_mul bu27008_itimes[] = {
-	GAIN_SCALE_ITIME_US(400000, BU27008_MEAS_MODE_400MS, 8),
-	GAIN_SCALE_ITIME_US(200000, BU27008_MEAS_MODE_200MS, 4),
-	GAIN_SCALE_ITIME_US(100000, BU27008_MEAS_MODE_100MS, 2),
-	GAIN_SCALE_ITIME_US(55000, BU27008_MEAS_MODE_55MS, 1),
-};
-
-static const struct iio_itime_sel_mul bu27010_itimes[] = {
-	GAIN_SCALE_ITIME_US(400000, BU27010_MEAS_MODE_400MS, 8),
-	GAIN_SCALE_ITIME_US(200000, BU27010_MEAS_MODE_200MS, 4),
-	GAIN_SCALE_ITIME_US(100000, BU27010_MEAS_MODE_100MS, 2),
-	GAIN_SCALE_ITIME_US(55000, BU27010_MEAS_MODE_55MS, 1),
-};
-
-/*
- * All the RGBC channels share the same gain.
- * IR gain can be fine-tuned from the gain set for the RGBC by 2 bit, but this
- * would yield quite complex gain setting. Especially since not all bit
- * compinations are supported. And in any case setting GAIN for RGBC will
- * always also change the IR-gain.
- *
- * On top of this, the selector '0' which corresponds to hw-gain 1X on RGBC,
- * corresponds to gain 2X on IR. Rest of the selctors correspond to same gains
- * though. This, however, makes it not possible to use shared gain for all
- * RGBC and IR settings even though they are all changed at the one go.
- */
-#define BU27008_CHAN(color, data, separate_avail)				\
-{										\
-	.type = IIO_INTENSITY,							\
-	.modified = 1,								\
-	.channel2 = IIO_MOD_LIGHT_##color,					\
-	.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |				\
-			      BIT(IIO_CHAN_INFO_SCALE),				\
-	.info_mask_separate_available = (separate_avail),			\
-	.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME),			\
-	.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME),	\
-	.address = BU27008_REG_##data##_LO,					\
-	.scan_index = BU27008_##color,						\
-	.scan_type = {								\
-		.sign = 'u',							\
-		.realbits = 16,							\
-		.storagebits = 16,						\
-		.endianness = IIO_LE,						\
-	},									\
-}
-
-/* For raw reads we always configure DATA3 for CLEAR */
-static const struct iio_chan_spec bu27008_channels[] = {
-	BU27008_CHAN(RED, DATA0, BIT(IIO_CHAN_INFO_SCALE)),
-	BU27008_CHAN(GREEN, DATA1, BIT(IIO_CHAN_INFO_SCALE)),
-	BU27008_CHAN(BLUE, DATA2, BIT(IIO_CHAN_INFO_SCALE)),
-	BU27008_CHAN(CLEAR, DATA2, BIT(IIO_CHAN_INFO_SCALE)),
-	/*
-	 * We don't allow setting scale for IR (because of shared gain bits).
-	 * Hence we don't advertise available ones either.
-	 */
-	BU27008_CHAN(IR, DATA3, 0),
-	{
-		.type = IIO_LIGHT,
-		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
-				      BIT(IIO_CHAN_INFO_SCALE),
-		.channel = BU27008_LUX,
-		.scan_index = BU27008_LUX,
-		.scan_type = {
-			.sign = 'u',
-			.realbits = 64,
-			.storagebits = 64,
-			.endianness = IIO_CPU,
-		},
-	},
-	IIO_CHAN_SOFT_TIMESTAMP(BU27008_NUM_CHANS),
-};
-
-struct bu27008_data;
-
-struct bu27_chip_data {
-	const char *name;
-	int (*chip_init)(struct bu27008_data *data);
-	int (*get_gain_sel)(struct bu27008_data *data, int *sel);
-	int (*write_gain_sel)(struct bu27008_data *data, int sel);
-	const struct regmap_config *regmap_cfg;
-	const struct iio_gain_sel_pair *gains;
-	const struct iio_gain_sel_pair *gains_ir;
-	const struct iio_itime_sel_mul *itimes;
-	int num_gains;
-	int num_gains_ir;
-	int num_itimes;
-	int scale1x;
-
-	int drdy_en_reg;
-	int drdy_en_mask;
-	int meas_en_reg;
-	int meas_en_mask;
-	int valid_reg;
-	int chan_sel_reg;
-	int chan_sel_mask;
-	int int_time_mask;
-	u8 part_id;
-};
-
-struct bu27008_data {
-	const struct bu27_chip_data *cd;
-	struct regmap *regmap;
-	struct iio_trigger *trig;
-	struct device *dev;
-	struct iio_gts gts;
-	struct iio_gts gts_ir;
-	int irq;
-
-	/*
-	 * Prevent changing gain/time config when scale is read/written.
-	 * Similarly, protect the integration_time read/change sequence.
-	 * Prevent changing gain/time when data is read.
-	 */
-	struct mutex mutex;
-};
-
-static const struct regmap_range bu27008_volatile_ranges[] = {
-	{
-		.range_min = BU27008_REG_SYSTEM_CONTROL,	/* SWRESET */
-		.range_max = BU27008_REG_SYSTEM_CONTROL,
-	}, {
-		.range_min = BU27008_REG_MODE_CONTROL3,		/* VALID */
-		.range_max = BU27008_REG_MODE_CONTROL3,
-	}, {
-		.range_min = BU27008_REG_DATA0_LO,		/* DATA */
-		.range_max = BU27008_REG_DATA3_HI,
-	},
-};
-
-static const struct regmap_range bu27010_volatile_ranges[] = {
-	{
-		.range_min = BU27010_REG_RESET,			/* RSTB */
-		.range_max = BU27008_REG_SYSTEM_CONTROL,	/* RESET */
-	}, {
-		.range_min = BU27010_REG_MODE_CONTROL5,		/* VALID bits */
-		.range_max = BU27010_REG_MODE_CONTROL5,
-	}, {
-		.range_min = BU27008_REG_DATA0_LO,
-		.range_max = BU27010_REG_FIFO_DATA_HI,
-	},
-};
-
-static const struct regmap_access_table bu27008_volatile_regs = {
-	.yes_ranges = &bu27008_volatile_ranges[0],
-	.n_yes_ranges = ARRAY_SIZE(bu27008_volatile_ranges),
-};
-
-static const struct regmap_access_table bu27010_volatile_regs = {
-	.yes_ranges = &bu27010_volatile_ranges[0],
-	.n_yes_ranges = ARRAY_SIZE(bu27010_volatile_ranges),
-};
-
-static const struct regmap_range bu27008_read_only_ranges[] = {
-	{
-		.range_min = BU27008_REG_DATA0_LO,
-		.range_max = BU27008_REG_DATA3_HI,
-	}, {
-		.range_min = BU27008_REG_MANUFACTURER_ID,
-		.range_max = BU27008_REG_MANUFACTURER_ID,
-	},
-};
-
-static const struct regmap_range bu27010_read_only_ranges[] = {
-	{
-		.range_min = BU27008_REG_DATA0_LO,
-		.range_max = BU27010_REG_FIFO_DATA_HI,
-	}, {
-		.range_min = BU27010_REG_MANUFACTURER_ID,
-		.range_max = BU27010_REG_MANUFACTURER_ID,
-	}
-};
-
-static const struct regmap_access_table bu27008_ro_regs = {
-	.no_ranges = &bu27008_read_only_ranges[0],
-	.n_no_ranges = ARRAY_SIZE(bu27008_read_only_ranges),
-};
-
-static const struct regmap_access_table bu27010_ro_regs = {
-	.no_ranges = &bu27010_read_only_ranges[0],
-	.n_no_ranges = ARRAY_SIZE(bu27010_read_only_ranges),
-};
-
-static const struct regmap_config bu27008_regmap = {
-	.reg_bits = 8,
-	.val_bits = 8,
-	.max_register = BU27008_REG_MAX,
-	.cache_type = REGCACHE_RBTREE,
-	.volatile_table = &bu27008_volatile_regs,
-	.wr_table = &bu27008_ro_regs,
-	/*
-	 * All register writes are serialized by the mutex which protects the
-	 * scale setting/getting. This is needed because scale is combined by
-	 * gain and integration time settings and we need to ensure those are
-	 * not read / written when scale is being computed.
-	 *
-	 * As a result of this serializing, we don't need regmap locking. Note,
-	 * this is not true if we add any configurations which are not
-	 * serialized by the mutex and which may need for example a protected
-	 * read-modify-write cycle (eg. regmap_update_bits()). Please, revise
-	 * this when adding features to the driver.
-	 */
-	.disable_locking = true,
-};
-
-static const struct regmap_config bu27010_regmap = {
-	.reg_bits	= 8,
-	.val_bits	= 8,
-
-	.max_register	= BU27010_REG_MAX,
-	.cache_type	= REGCACHE_RBTREE,
-	.volatile_table = &bu27010_volatile_regs,
-	.wr_table	= &bu27010_ro_regs,
-	.disable_locking = true,
-};
-
-static int bu27008_write_gain_sel(struct bu27008_data *data, int sel)
-{
-	int regval;
-
-	regval = FIELD_PREP(BU27008_MASK_RGBC_GAIN, sel);
-
-	/*
-	 * We do always set also the LOW bits of IR-gain because othervice we
-	 * would risk resulting an invalid GAIN register value.
-	 *
-	 * We could allow setting separate gains for RGBC and IR when the
-	 * values were such that HW could support both gain settings.
-	 * Eg, when the shared bits were same for both gain values.
-	 *
-	 * This, however, has a negligible benefit compared to the increased
-	 * software complexity when we would need to go through the gains
-	 * for both channels separately when the integration time changes.
-	 * This would end up with nasty logic for computing gain values for
-	 * both channels - and rejecting them if shared bits changed.
-	 *
-	 * We should then build the logic by guessing what a user prefers.
-	 * RGBC or IR gains correctly set while other jumps to odd value?
-	 * Maybe look-up a value where both gains are somehow optimized
-	 * <what this somehow is, is ATM unknown to us>. Or maybe user would
-	 * expect us to reject changes when optimal gains can't be set to both
-	 * channels w/given integration time. At best that would result
-	 * solution that works well for a very specific subset of
-	 * configurations but causes unexpected corner-cases.
-	 *
-	 * So, we keep it simple. Always set same selector to IR and RGBC.
-	 * We disallow setting IR (as I expect that most of the users are
-	 * interested in RGBC). This way we can show the user that the scales
-	 * for RGBC and IR channels are different (1X Vs 2X with sel 0) while
-	 * still keeping the operation deterministic.
-	 */
-	regval |= FIELD_PREP(BU27008_MASK_IR_GAIN_LO, sel);
-
-	return regmap_update_bits(data->regmap, BU27008_REG_MODE_CONTROL2,
-				  BU27008_MASK_RGBC_GAIN, regval);
-}
-
-static int bu27010_write_gain_sel(struct bu27008_data *data, int sel)
-{
-	unsigned int regval;
-	int ret, chan_selector;
-
-	/*
-	 * Gain 'selector' is composed of two registers. Selector is 6bit value,
-	 * 4 high bits being the RGBC gain fieild in MODE_CONTROL1 register and
-	 * two low bits being the channel specific gain in MODE_CONTROL2.
-	 *
-	 * Let's take the 4 high bits of whole 6 bit selector, and prepare
-	 * the MODE_CONTROL1 value (RGBC gain part).
-	 */
-	regval = FIELD_PREP(BU27010_MASK_RGBC_GAIN, (sel >> 2));
-
-	ret = regmap_update_bits(data->regmap, BU27008_REG_MODE_CONTROL1,
-				  BU27010_MASK_RGBC_GAIN, regval);
-	if (ret)
-		return ret;
-
-	/*
-	 * Two low two bits of the selector must be written for all 4
-	 * channels in the MODE_CONTROL2 register. Copy these two bits for
-	 * all channels.
-	 */
-	chan_selector = sel & GENMASK(1, 0);
-
-	regval = FIELD_PREP(BU27010_MASK_DATA0_GAIN, chan_selector);
-	regval |= FIELD_PREP(BU27010_MASK_DATA1_GAIN, chan_selector);
-	regval |= FIELD_PREP(BU27010_MASK_DATA2_GAIN, chan_selector);
-	regval |= FIELD_PREP(BU27010_MASK_DATA3_GAIN, chan_selector);
-
-	return regmap_write(data->regmap, BU27008_REG_MODE_CONTROL2, regval);
-}
-
-static int bu27008_get_gain_sel(struct bu27008_data *data, int *sel)
-{
-	int ret;
-
-	/*
-	 * If we always "lock" the gain selectors for all channels to prevent
-	 * unsupported configs, then it does not matter which channel is used
-	 * we can just return selector from any of them.
-	 *
-	 * This, however is not true if we decide to support only 4X and 16X
-	 * and then individual gains for channels. Currently this is not the
-	 * case.
-	 *
-	 * If we some day decide to support individual gains, then we need to
-	 * have channel information here.
-	 */
-
-	ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL2, sel);
-	if (ret)
-		return ret;
-
-	*sel = FIELD_GET(BU27008_MASK_RGBC_GAIN, *sel);
-
-	return 0;
-}
-
-static int bu27010_get_gain_sel(struct bu27008_data *data, int *sel)
-{
-	int ret, tmp;
-
-	/*
-	 * We always "lock" the gain selectors for all channels to prevent
-	 * unsupported configs. It does not matter which channel is used
-	 * we can just return selector from any of them.
-	 *
-	 * Read the channel0 gain.
-	 */
-	ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL2, sel);
-	if (ret)
-		return ret;
-
-	*sel = FIELD_GET(BU27010_MASK_DATA0_GAIN, *sel);
-
-	/* Read the shared gain */
-	ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL1, &tmp);
-	if (ret)
-		return ret;
-
-	/*
-	 * The gain selector is made as a combination of common RGBC gain and
-	 * the channel specific gain. The channel specific gain forms the low
-	 * bits of selector and RGBC gain is appended right after it.
-	 *
-	 * Compose the selector from channel0 gain and shared RGBC gain.
-	 */
-	*sel |= FIELD_GET(BU27010_MASK_RGBC_GAIN, tmp) << fls(BU27010_MASK_DATA0_GAIN);
-
-	return ret;
-}
-
-static int bu27008_chip_init(struct bu27008_data *data)
-{
-	int ret;
-
-	ret = regmap_write_bits(data->regmap, BU27008_REG_SYSTEM_CONTROL,
-				BU27008_MASK_SW_RESET, BU27008_MASK_SW_RESET);
-	if (ret)
-		return dev_err_probe(data->dev, ret, "Sensor reset failed\n");
-
-	/*
-	 * The data-sheet does not tell how long performing the IC reset takes.
-	 * However, the data-sheet says the minimum time it takes the IC to be
-	 * able to take inputs after power is applied, is 100 uS. I'd assume
-	 * > 1 mS is enough.
-	 */
-	msleep(1);
-
-	ret = regmap_reinit_cache(data->regmap, data->cd->regmap_cfg);
-	if (ret)
-		dev_err(data->dev, "Failed to reinit reg cache\n");
-
-	return ret;
-}
-
-static int bu27010_chip_init(struct bu27008_data *data)
-{
-	int ret;
-
-	ret = regmap_write_bits(data->regmap, BU27008_REG_SYSTEM_CONTROL,
-				BU27010_MASK_SW_RESET, BU27010_MASK_SW_RESET);
-	if (ret)
-		return dev_err_probe(data->dev, ret, "Sensor reset failed\n");
-
-	msleep(1);
-
-	/* Power ON*/
-	ret = regmap_write_bits(data->regmap, BU27010_REG_POWER,
-				BU27010_MASK_POWER, BU27010_MASK_POWER);
-	if (ret)
-		return dev_err_probe(data->dev, ret, "Sensor power-on failed\n");
-
-	msleep(1);
-
-	/* Release blocks from reset */
-	ret = regmap_write_bits(data->regmap, BU27010_REG_RESET,
-				BU27010_MASK_RESET, BU27010_RESET_RELEASE);
-	if (ret)
-		return dev_err_probe(data->dev, ret, "Sensor powering failed\n");
-
-	msleep(1);
-
-	/*
-	 * The IRQ enabling on BU27010 is done in a peculiar way. The IRQ
-	 * enabling is not a bit mask where individual IRQs could be enabled but
-	 * a field which values are:
-	 * 00 => IRQs disabled
-	 * 01 => Data-ready (RGBC/IR)
-	 * 10 => Data-ready (flicker)
-	 * 11 => Flicker FIFO
-	 *
-	 * So, only one IRQ can be enabled at a time and enabling for example
-	 * flicker FIFO would automagically disable data-ready IRQ.
-	 *
-	 * Currently the driver does not support the flicker. Hence, we can
-	 * just treat the RGBC data-ready as single bit which can be enabled /
-	 * disabled. This works for as long as the second bit in the field
-	 * stays zero. Here we ensure it gets zeroed.
-	 */
-	return regmap_clear_bits(data->regmap, BU27010_REG_MODE_CONTROL4,
-				 BU27010_IRQ_DIS_ALL);
-}
-
-static const struct bu27_chip_data bu27010_chip = {
-	.name = "bu27010",
-	.chip_init = bu27010_chip_init,
-	.get_gain_sel = bu27010_get_gain_sel,
-	.write_gain_sel = bu27010_write_gain_sel,
-	.regmap_cfg = &bu27010_regmap,
-	.gains = &bu27010_gains[0],
-	.gains_ir = &bu27010_gains_ir[0],
-	.itimes = &bu27010_itimes[0],
-	.num_gains = ARRAY_SIZE(bu27010_gains),
-	.num_gains_ir = ARRAY_SIZE(bu27010_gains_ir),
-	.num_itimes = ARRAY_SIZE(bu27010_itimes),
-	.scale1x = BU27010_SCALE_1X,
-	.drdy_en_reg = BU27010_REG_MODE_CONTROL4,
-	.drdy_en_mask = BU27010_DRDY_EN,
-	.meas_en_reg = BU27010_REG_MODE_CONTROL5,
-	.meas_en_mask = BU27010_MASK_MEAS_EN,
-	.valid_reg = BU27010_REG_MODE_CONTROL5,
-	.chan_sel_reg = BU27008_REG_MODE_CONTROL1,
-	.chan_sel_mask = BU27010_MASK_CHAN_SEL,
-	.int_time_mask = BU27010_MASK_MEAS_MODE,
-	.part_id = BU27010_ID,
-};
-
-static const struct bu27_chip_data bu27008_chip = {
-	.name = "bu27008",
-	.chip_init = bu27008_chip_init,
-	.get_gain_sel = bu27008_get_gain_sel,
-	.write_gain_sel = bu27008_write_gain_sel,
-	.regmap_cfg = &bu27008_regmap,
-	.gains = &bu27008_gains[0],
-	.gains_ir = &bu27008_gains_ir[0],
-	.itimes = &bu27008_itimes[0],
-	.num_gains = ARRAY_SIZE(bu27008_gains),
-	.num_gains_ir = ARRAY_SIZE(bu27008_gains_ir),
-	.num_itimes = ARRAY_SIZE(bu27008_itimes),
-	.scale1x = BU27008_SCALE_1X,
-	.drdy_en_reg = BU27008_REG_MODE_CONTROL3,
-	.drdy_en_mask = BU27008_MASK_INT_EN,
-	.valid_reg = BU27008_REG_MODE_CONTROL3,
-	.meas_en_reg = BU27008_REG_MODE_CONTROL3,
-	.meas_en_mask = BU27008_MASK_MEAS_EN,
-	.chan_sel_reg = BU27008_REG_MODE_CONTROL3,
-	.chan_sel_mask = BU27008_MASK_CHAN_SEL,
-	.int_time_mask = BU27008_MASK_MEAS_MODE,
-	.part_id = BU27008_ID,
-};
-
-#define BU27008_MAX_VALID_RESULT_WAIT_US	50000
-#define BU27008_VALID_RESULT_WAIT_QUANTA_US	1000
-
-static int bu27008_chan_read_data(struct bu27008_data *data, int reg, int *val)
-{
-	int ret, valid;
-	__le16 tmp;
-
-	ret = regmap_read_poll_timeout(data->regmap, data->cd->valid_reg,
-				       valid, (valid & BU27008_MASK_VALID),
-				       BU27008_VALID_RESULT_WAIT_QUANTA_US,
-				       BU27008_MAX_VALID_RESULT_WAIT_US);
-	if (ret)
-		return ret;
-
-	ret = regmap_bulk_read(data->regmap, reg, &tmp, sizeof(tmp));
-	if (ret)
-		dev_err(data->dev, "Reading channel data failed\n");
-
-	*val = le16_to_cpu(tmp);
-
-	return ret;
-}
-
-static int bu27008_get_gain(struct bu27008_data *data, struct iio_gts *gts, int *gain)
-{
-	int ret, sel;
-
-	ret = data->cd->get_gain_sel(data, &sel);
-	if (ret)
-		return ret;
-
-	ret = iio_gts_find_gain_by_sel(gts, sel);
-	if (ret < 0) {
-		dev_err(data->dev, "unknown gain value 0x%x\n", sel);
-		return ret;
-	}
-
-	*gain = ret;
-
-	return 0;
-}
-
-static int bu27008_set_gain(struct bu27008_data *data, int gain)
-{
-	int ret;
-
-	ret = iio_gts_find_sel_by_gain(&data->gts, gain);
-	if (ret < 0)
-		return ret;
-
-	return data->cd->write_gain_sel(data, ret);
-}
-
-static int bu27008_get_int_time_sel(struct bu27008_data *data, int *sel)
-{
-	int ret, val;
-
-	ret = regmap_read(data->regmap, BU27008_REG_MODE_CONTROL1, &val);
-	if (ret)
-		return ret;
-
-	val &= data->cd->int_time_mask;
-	val >>= ffs(data->cd->int_time_mask) - 1;
-
-	*sel = val;
-
-	return 0;
-}
-
-static int bu27008_set_int_time_sel(struct bu27008_data *data, int sel)
-{
-	sel <<= ffs(data->cd->int_time_mask) - 1;
-
-	return regmap_update_bits(data->regmap, BU27008_REG_MODE_CONTROL1,
-				  data->cd->int_time_mask, sel);
-}
-
-static int bu27008_get_int_time_us(struct bu27008_data *data)
-{
-	int ret, sel;
-
-	ret = bu27008_get_int_time_sel(data, &sel);
-	if (ret)
-		return ret;
-
-	return iio_gts_find_int_time_by_sel(&data->gts, sel);
-}
-
-static int _bu27008_get_scale(struct bu27008_data *data, bool ir, int *val,
-			      int *val2)
-{
-	struct iio_gts *gts;
-	int gain, ret;
-
-	if (ir)
-		gts = &data->gts_ir;
-	else
-		gts = &data->gts;
-
-	ret = bu27008_get_gain(data, gts, &gain);
-	if (ret)
-		return ret;
-
-	ret = bu27008_get_int_time_us(data);
-	if (ret < 0)
-		return ret;
-
-	return iio_gts_get_scale(gts, gain, ret, val, val2);
-}
-
-static int bu27008_get_scale(struct bu27008_data *data, bool ir, int *val,
-			     int *val2)
-{
-	int ret;
-
-	mutex_lock(&data->mutex);
-	ret = _bu27008_get_scale(data, ir, val, val2);
-	mutex_unlock(&data->mutex);
-
-	return ret;
-}
-
-static int bu27008_set_int_time(struct bu27008_data *data, int time)
-{
-	int ret;
-
-	ret = iio_gts_find_sel_by_int_time(&data->gts, time);
-	if (ret < 0)
-		return ret;
-
-	return bu27008_set_int_time_sel(data, ret);
-}
-
-/* Try to change the time so that the scale is maintained */
-static int bu27008_try_set_int_time(struct bu27008_data *data, int int_time_new)
-{
-	int ret, old_time_sel, new_time_sel,  old_gain, new_gain;
-
-	mutex_lock(&data->mutex);
-
-	ret = bu27008_get_int_time_sel(data, &old_time_sel);
-	if (ret < 0)
-		goto unlock_out;
-
-	if (!iio_gts_valid_time(&data->gts, int_time_new)) {
-		dev_dbg(data->dev, "Unsupported integration time %u\n",
-			int_time_new);
-
-		ret = -EINVAL;
-		goto unlock_out;
-	}
-
-	/* If we already use requested time, then we're done */
-	new_time_sel = iio_gts_find_sel_by_int_time(&data->gts, int_time_new);
-	if (new_time_sel == old_time_sel)
-		goto unlock_out;
-
-	ret = bu27008_get_gain(data, &data->gts, &old_gain);
-	if (ret)
-		goto unlock_out;
-
-	ret = iio_gts_find_new_gain_sel_by_old_gain_time(&data->gts, old_gain,
-				old_time_sel, new_time_sel, &new_gain);
-	if (ret) {
-		int scale1, scale2;
-		bool ok;
-
-		_bu27008_get_scale(data, false, &scale1, &scale2);
-		dev_dbg(data->dev,
-			"Can't support time %u with current scale %u %u\n",
-			int_time_new, scale1, scale2);
-
-		if (new_gain < 0)
-			goto unlock_out;
-
-		/*
-		 * If caller requests for integration time change and we
-		 * can't support the scale - then the caller should be
-		 * prepared to 'pick up the pieces and deal with the
-		 * fact that the scale changed'.
-		 */
-		ret = iio_find_closest_gain_low(&data->gts, new_gain, &ok);
-		if (!ok)
-			dev_dbg(data->dev, "optimal gain out of range\n");
-
-		if (ret < 0) {
-			dev_dbg(data->dev,
-				 "Total gain increase. Risk of saturation");
-			ret = iio_gts_get_min_gain(&data->gts);
-			if (ret < 0)
-				goto unlock_out;
-		}
-		new_gain = ret;
-		dev_dbg(data->dev, "scale changed, new gain %u\n", new_gain);
-	}
-
-	ret = bu27008_set_gain(data, new_gain);
-	if (ret)
-		goto unlock_out;
-
-	ret = bu27008_set_int_time(data, int_time_new);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
-}
-
-static int bu27008_meas_set(struct bu27008_data *data, bool enable)
-{
-	if (enable)
-		return regmap_set_bits(data->regmap, data->cd->meas_en_reg,
-				       data->cd->meas_en_mask);
-	return regmap_clear_bits(data->regmap, data->cd->meas_en_reg,
-				 data->cd->meas_en_mask);
-}
-
-static int bu27008_chan_cfg(struct bu27008_data *data,
-			    struct iio_chan_spec const *chan)
-{
-	int chan_sel;
-
-	if (chan->scan_index == BU27008_BLUE)
-		chan_sel = BU27008_BLUE2_CLEAR3;
-	else
-		chan_sel = BU27008_CLEAR2_IR3;
-
-	/*
-	 * prepare bitfield for channel sel. The FIELD_PREP works only when
-	 * mask is constant. In our case the mask is assigned based on the
-	 * chip type. Hence the open-coded FIELD_PREP here. We don't bother
-	 * zeroing the irrelevant bits though - update_bits takes care of that.
-	 */
-	chan_sel <<= ffs(data->cd->chan_sel_mask) - 1;
-
-	return regmap_update_bits(data->regmap, data->cd->chan_sel_reg,
-				  BU27008_MASK_CHAN_SEL, chan_sel);
-}
-
-static int bu27008_read_one(struct bu27008_data *data, struct iio_dev *idev,
-			    struct iio_chan_spec const *chan, int *val, int *val2)
-{
-	int ret, int_time;
-
-	ret = bu27008_chan_cfg(data, chan);
-	if (ret)
-		return ret;
-
-	ret = bu27008_meas_set(data, true);
-	if (ret)
-		return ret;
-
-	ret = bu27008_get_int_time_us(data);
-	if (ret < 0)
-		int_time = BU27008_MEAS_TIME_MAX_MS;
-	else
-		int_time = ret / USEC_PER_MSEC;
-
-	msleep(int_time);
-
-	ret = bu27008_chan_read_data(data, chan->address, val);
-	if (!ret)
-		ret = IIO_VAL_INT;
-
-	if (bu27008_meas_set(data, false))
-		dev_warn(data->dev, "measurement disabling failed\n");
-
-	return ret;
-}
-
-#define BU27008_LUX_DATA_RED	0
-#define BU27008_LUX_DATA_GREEN	1
-#define BU27008_LUX_DATA_BLUE	2
-#define BU27008_LUX_DATA_IR	3
-#define LUX_DATA_SIZE (BU27008_NUM_HW_CHANS * sizeof(__le16))
-
-static int bu27008_read_lux_chans(struct bu27008_data *data, unsigned int time,
-				  __le16 *chan_data)
-{
-	int ret, chan_sel, tmpret, valid;
-
-	chan_sel = BU27008_BLUE2_IR3 << (ffs(data->cd->chan_sel_mask) - 1);
-
-	ret = regmap_update_bits(data->regmap, data->cd->chan_sel_reg,
-				 data->cd->chan_sel_mask, chan_sel);
-	if (ret)
-		return ret;
-
-	ret = bu27008_meas_set(data, true);
-	if (ret)
-		return ret;
-
-	msleep(time / USEC_PER_MSEC);
-
-	ret = regmap_read_poll_timeout(data->regmap, data->cd->valid_reg,
-				       valid, (valid & BU27008_MASK_VALID),
-				       BU27008_VALID_RESULT_WAIT_QUANTA_US,
-				       BU27008_MAX_VALID_RESULT_WAIT_US);
-	if (ret)
-		goto out;
-
-	ret = regmap_bulk_read(data->regmap, BU27008_REG_DATA0_LO, chan_data,
-			       LUX_DATA_SIZE);
-	if (ret)
-		goto out;
-out:
-	tmpret = bu27008_meas_set(data, false);
-	if (tmpret)
-		dev_warn(data->dev, "Stopping measurement failed\n");
-
-	return ret;
-}
-
-/*
- * Following equation for computing lux out of register values was given by
- * ROHM HW colleagues;
- *
- * Red = RedData*1024 / Gain * 20 / meas_mode
- * Green = GreenData* 1024 / Gain * 20 / meas_mode
- * Blue = BlueData* 1024 / Gain * 20 / meas_mode
- * IR = IrData* 1024 / Gain * 20 / meas_mode
- *
- * where meas_mode is the integration time in mS / 10
- *
- * IRratio = (IR > 0.18 * Green) ? 0 : 1
- *
- * Lx = max(c1*Red + c2*Green + c3*Blue,0)
- *
- * for
- * IRratio 0: c1 = -0.00002237, c2 = 0.0003219, c3 = -0.000120371
- * IRratio 1: c1 = -0.00001074, c2 = 0.000305415, c3 = -0.000129367
- */
-
-/*
- * The max chan data is 0xffff. When we multiply it by 1024 * 20, we'll get
- * 0x4FFFB000 which still fits in 32-bit integer. This won't overflow.
- */
-#define NORM_CHAN_DATA_FOR_LX_CALC(chan, gain, time) (le16_to_cpu(chan) * \
-				   1024 * 20 / (gain) / (time))
-static u64 bu27008_calc_nlux(struct bu27008_data *data, __le16 *lux_data,
-		unsigned int gain, unsigned int gain_ir, unsigned int time)
-{
-	unsigned int red, green, blue, ir;
-	s64 c1, c2, c3, nlux;
-
-	time /= 10000;
-	ir = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_IR], gain_ir, time);
-	red = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_RED], gain, time);
-	green = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_GREEN], gain, time);
-	blue = NORM_CHAN_DATA_FOR_LX_CALC(lux_data[BU27008_LUX_DATA_BLUE], gain, time);
-
-	if ((u64)ir * 100LLU > (u64)green * 18LLU) {
-		c1 = -22370;
-		c2 = 321900;
-		c3 = -120371;
-	} else {
-		c1 = -10740;
-		c2 = 305415;
-		c3 = -129367;
-	}
-	nlux = c1 * red + c2 * green + c3 * blue;
-
-	return max_t(s64, 0, nlux);
-}
-
-static int bu27008_get_time_n_gains(struct bu27008_data *data,
-		unsigned int *gain, unsigned int *gain_ir, unsigned int *time)
-{
-	int ret;
-
-	ret = bu27008_get_gain(data, &data->gts, gain);
-	if (ret < 0)
-		return ret;
-
-	ret = bu27008_get_gain(data, &data->gts_ir, gain_ir);
-	if (ret < 0)
-		return ret;
-
-	ret = bu27008_get_int_time_us(data);
-	if (ret < 0)
-		return ret;
-
-	/* Max integration time is 400000. Fits in signed int. */
-	*time = ret;
-
-	return 0;
-}
-
-struct bu27008_buf {
-	__le16 chan[BU27008_NUM_HW_CHANS];
-	u64 lux __aligned(8);
-	s64 ts __aligned(8);
-};
-
-static int bu27008_buffer_fill_lux(struct bu27008_data *data,
-				   struct bu27008_buf *raw)
-{
-	unsigned int gain, gain_ir, time;
-	int ret;
-
-	ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time);
-	if (ret)
-		return ret;
-
-	raw->lux = bu27008_calc_nlux(data, raw->chan, gain, gain_ir, time);
-
-	return 0;
-}
-
-static int bu27008_read_lux(struct bu27008_data *data, struct iio_dev *idev,
-			    struct iio_chan_spec const *chan,
-			    int *val, int *val2)
-{
-	__le16 lux_data[BU27008_NUM_HW_CHANS];
-	unsigned int gain, gain_ir, time;
-	u64 nlux;
-	int ret;
-
-	ret = bu27008_get_time_n_gains(data, &gain, &gain_ir, &time);
-	if (ret)
-		return ret;
-
-	ret = bu27008_read_lux_chans(data, time, lux_data);
-	if (ret)
-		return ret;
-
-	nlux = bu27008_calc_nlux(data, lux_data, gain, gain_ir, time);
-	*val = (int)nlux;
-	*val2 = nlux >> 32LLU;
-
-	return IIO_VAL_INT_64;
-}
-
-static int bu27008_read_raw(struct iio_dev *idev,
-			   struct iio_chan_spec const *chan,
-			   int *val, int *val2, long mask)
-{
-	struct bu27008_data *data = iio_priv(idev);
-	int busy, ret;
-
-	switch (mask) {
-	case IIO_CHAN_INFO_RAW:
-		busy = iio_device_claim_direct_mode(idev);
-		if (busy)
-			return -EBUSY;
-
-		mutex_lock(&data->mutex);
-		if (chan->type == IIO_LIGHT)
-			ret = bu27008_read_lux(data, idev, chan, val, val2);
-		else
-			ret = bu27008_read_one(data, idev, chan, val, val2);
-		mutex_unlock(&data->mutex);
-
-		iio_device_release_direct_mode(idev);
-
-		return ret;
-
-	case IIO_CHAN_INFO_SCALE:
-		if (chan->type == IIO_LIGHT) {
-			*val = 0;
-			*val2 = 1;
-			return IIO_VAL_INT_PLUS_NANO;
-		}
-		ret = bu27008_get_scale(data, chan->scan_index == BU27008_IR,
-					val, val2);
-		if (ret)
-			return ret;
-
-		return IIO_VAL_INT_PLUS_NANO;
-
-	case IIO_CHAN_INFO_INT_TIME:
-		ret = bu27008_get_int_time_us(data);
-		if (ret < 0)
-			return ret;
-
-		*val = 0;
-		*val2 = ret;
-
-		return IIO_VAL_INT_PLUS_MICRO;
-
-	default:
-		return -EINVAL;
-	}
-}
-
-/* Called if the new scale could not be supported with existing int-time */
-static int bu27008_try_find_new_time_gain(struct bu27008_data *data, int val,
-					  int val2, int *gain_sel)
-{
-	int i, ret, new_time_sel;
-
-	for (i = 0; i < data->gts.num_itime; i++) {
-		new_time_sel = data->gts.itime_table[i].sel;
-		ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts,
-					new_time_sel, val, val2, gain_sel);
-		if (!ret)
-			break;
-	}
-	if (i == data->gts.num_itime) {
-		dev_err(data->dev, "Can't support scale %u %u\n", val, val2);
-
-		return -EINVAL;
-	}
-
-	return bu27008_set_int_time_sel(data, new_time_sel);
-}
-
-static int bu27008_set_scale(struct bu27008_data *data,
-			     struct iio_chan_spec const *chan,
-			     int val, int val2)
-{
-	int ret, gain_sel, time_sel;
-
-	if (chan->scan_index == BU27008_IR)
-		return -EINVAL;
-
-	mutex_lock(&data->mutex);
-
-	ret = bu27008_get_int_time_sel(data, &time_sel);
-	if (ret < 0)
-		goto unlock_out;
-
-	ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel,
-						val, val2, &gain_sel);
-	if (ret) {
-		ret = bu27008_try_find_new_time_gain(data, val, val2, &gain_sel);
-		if (ret)
-			goto unlock_out;
-
-	}
-	ret = data->cd->write_gain_sel(data, gain_sel);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
-}
-
-static int bu27008_write_raw_get_fmt(struct iio_dev *indio_dev,
-				     struct iio_chan_spec const *chan,
-				     long mask)
-{
-
-	switch (mask) {
-	case IIO_CHAN_INFO_SCALE:
-		return IIO_VAL_INT_PLUS_NANO;
-	case IIO_CHAN_INFO_INT_TIME:
-		return IIO_VAL_INT_PLUS_MICRO;
-	default:
-		return -EINVAL;
-	}
-}
-
-static int bu27008_write_raw(struct iio_dev *idev,
-			     struct iio_chan_spec const *chan,
-			     int val, int val2, long mask)
-{
-	struct bu27008_data *data = iio_priv(idev);
-	int ret;
-
-	/*
-	 * Do not allow changing scale when measurement is ongoing as doing so
-	 * could make values in the buffer inconsistent.
-	 */
-	ret = iio_device_claim_direct_mode(idev);
-	if (ret)
-		return ret;
-
-	switch (mask) {
-	case IIO_CHAN_INFO_SCALE:
-		ret = bu27008_set_scale(data, chan, val, val2);
-		break;
-	case IIO_CHAN_INFO_INT_TIME:
-		if (val) {
-			ret = -EINVAL;
-			break;
-		}
-		ret = bu27008_try_set_int_time(data, val2);
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-	iio_device_release_direct_mode(idev);
-
-	return ret;
-}
-
-static int bu27008_read_avail(struct iio_dev *idev,
-			      struct iio_chan_spec const *chan, const int **vals,
-			      int *type, int *length, long mask)
-{
-	struct bu27008_data *data = iio_priv(idev);
-
-	switch (mask) {
-	case IIO_CHAN_INFO_INT_TIME:
-		return iio_gts_avail_times(&data->gts, vals, type, length);
-	case IIO_CHAN_INFO_SCALE:
-		if (chan->channel2 == IIO_MOD_LIGHT_IR)
-			return iio_gts_all_avail_scales(&data->gts_ir, vals,
-							type, length);
-		return iio_gts_all_avail_scales(&data->gts, vals, type, length);
-	default:
-		return -EINVAL;
-	}
-}
-
-static int bu27008_update_scan_mode(struct iio_dev *idev,
-				    const unsigned long *scan_mask)
-{
-	struct bu27008_data *data = iio_priv(idev);
-	int chan_sel;
-
-	/* Configure channel selection */
-	if (test_bit(BU27008_BLUE, idev->active_scan_mask)) {
-		if (test_bit(BU27008_CLEAR, idev->active_scan_mask))
-			chan_sel = BU27008_BLUE2_CLEAR3;
-		else
-			chan_sel = BU27008_BLUE2_IR3;
-	} else {
-		chan_sel = BU27008_CLEAR2_IR3;
-	}
-
-	chan_sel <<= ffs(data->cd->chan_sel_mask) - 1;
-
-	return regmap_update_bits(data->regmap, data->cd->chan_sel_reg,
-				  data->cd->chan_sel_mask, chan_sel);
-}
-
-static const struct iio_info bu27008_info = {
-	.read_raw = &bu27008_read_raw,
-	.write_raw = &bu27008_write_raw,
-	.write_raw_get_fmt = &bu27008_write_raw_get_fmt,
-	.read_avail = &bu27008_read_avail,
-	.update_scan_mode = bu27008_update_scan_mode,
-	.validate_trigger = iio_validate_own_trigger,
-};
-
-static int bu27008_trigger_set_state(struct iio_trigger *trig, bool state)
-{
-	struct bu27008_data *data = iio_trigger_get_drvdata(trig);
-	int ret;
-
-
-	if (state)
-		ret = regmap_set_bits(data->regmap, data->cd->drdy_en_reg,
-				      data->cd->drdy_en_mask);
-	else
-		ret = regmap_clear_bits(data->regmap, data->cd->drdy_en_reg,
-					data->cd->drdy_en_mask);
-	if (ret)
-		dev_err(data->dev, "Failed to set trigger state\n");
-
-	return ret;
-}
-
-static void bu27008_trigger_reenable(struct iio_trigger *trig)
-{
-	struct bu27008_data *data = iio_trigger_get_drvdata(trig);
-
-	enable_irq(data->irq);
-}
-
-static const struct iio_trigger_ops bu27008_trigger_ops = {
-	.set_trigger_state = bu27008_trigger_set_state,
-	.reenable = bu27008_trigger_reenable,
-};
-
-static irqreturn_t bu27008_trigger_handler(int irq, void *p)
-{
-	struct iio_poll_func *pf = p;
-	struct iio_dev *idev = pf->indio_dev;
-	struct bu27008_data *data = iio_priv(idev);
-	struct bu27008_buf raw;
-	int ret, dummy;
-
-	memset(&raw, 0, sizeof(raw));
-
-	/*
-	 * After some measurements, it seems reading the
-	 * BU27008_REG_MODE_CONTROL3 debounces the IRQ line
-	 */
-	ret = regmap_read(data->regmap, data->cd->valid_reg, &dummy);
-	if (ret < 0)
-		goto err_read;
-
-	ret = regmap_bulk_read(data->regmap, BU27008_REG_DATA0_LO, &raw.chan,
-			       sizeof(raw.chan));
-	if (ret < 0)
-		goto err_read;
-
-	if (test_bit(BU27008_LUX, idev->active_scan_mask)) {
-		ret = bu27008_buffer_fill_lux(data, &raw);
-		if (ret)
-			goto err_read;
-	}
-
-	iio_push_to_buffers_with_timestamp(idev, &raw, pf->timestamp);
-err_read:
-	iio_trigger_notify_done(idev->trig);
-
-	return IRQ_HANDLED;
-}
-
-static int bu27008_buffer_preenable(struct iio_dev *idev)
-{
-	struct bu27008_data *data = iio_priv(idev);
-
-	return bu27008_meas_set(data, true);
-}
-
-static int bu27008_buffer_postdisable(struct iio_dev *idev)
-{
-	struct bu27008_data *data = iio_priv(idev);
-
-	return bu27008_meas_set(data, false);
-}
-
-static const struct iio_buffer_setup_ops bu27008_buffer_ops = {
-	.preenable = bu27008_buffer_preenable,
-	.postdisable = bu27008_buffer_postdisable,
-};
-
-static irqreturn_t bu27008_data_rdy_poll(int irq, void *private)
-{
-	/*
-	 * The BU27008 keeps IRQ asserted until we read the VALID bit from
-	 * a register. We need to keep the IRQ disabled until then.
-	 */
-	disable_irq_nosync(irq);
-	iio_trigger_poll(private);
-
-	return IRQ_HANDLED;
-}
-
-static int bu27008_setup_trigger(struct bu27008_data *data, struct iio_dev *idev)
-{
-	struct iio_trigger *itrig;
-	char *name;
-	int ret;
-
-	ret = devm_iio_triggered_buffer_setup(data->dev, idev,
-					      &iio_pollfunc_store_time,
-					      bu27008_trigger_handler,
-					      &bu27008_buffer_ops);
-	if (ret)
-		return dev_err_probe(data->dev, ret,
-			     "iio_triggered_buffer_setup_ext FAIL\n");
-
-	itrig = devm_iio_trigger_alloc(data->dev, "%sdata-rdy-dev%d",
-				       idev->name, iio_device_id(idev));
-	if (!itrig)
-		return -ENOMEM;
-
-	data->trig = itrig;
-
-	itrig->ops = &bu27008_trigger_ops;
-	iio_trigger_set_drvdata(itrig, data);
-
-	name = devm_kasprintf(data->dev, GFP_KERNEL, "%s-bu27008",
-			      dev_name(data->dev));
-
-	ret = devm_request_irq(data->dev, data->irq,
-			       &bu27008_data_rdy_poll,
-			       0, name, itrig);
-	if (ret)
-		return dev_err_probe(data->dev, ret, "Could not request IRQ\n");
-
-	ret = devm_iio_trigger_register(data->dev, itrig);
-	if (ret)
-		return dev_err_probe(data->dev, ret,
-				     "Trigger registration failed\n");
-
-	/* set default trigger */
-	idev->trig = iio_trigger_get(itrig);
-
-	return 0;
-}
-
-static int bu27008_probe(struct i2c_client *i2c)
-{
-	struct device *dev = &i2c->dev;
-	struct bu27008_data *data;
-	struct regmap *regmap;
-	unsigned int part_id, reg;
-	struct iio_dev *idev;
-	int ret;
-
-	idev = devm_iio_device_alloc(dev, sizeof(*data));
-	if (!idev)
-		return -ENOMEM;
-
-	ret = devm_regulator_get_enable(dev, "vdd");
-	if (ret)
-		return dev_err_probe(dev, ret, "Failed to get regulator\n");
-
-	data = iio_priv(idev);
-
-	data->cd = device_get_match_data(&i2c->dev);
-	if (!data->cd)
-		return -ENODEV;
-
-	regmap = devm_regmap_init_i2c(i2c, data->cd->regmap_cfg);
-	if (IS_ERR(regmap))
-		return dev_err_probe(dev, PTR_ERR(regmap),
-				     "Failed to initialize Regmap\n");
-
-
-	ret = regmap_read(regmap, BU27008_REG_SYSTEM_CONTROL, &reg);
-	if (ret)
-		return dev_err_probe(dev, ret, "Failed to access sensor\n");
-
-	part_id = FIELD_GET(BU27008_MASK_PART_ID, reg);
-
-	if (part_id != data->cd->part_id)
-		dev_warn(dev, "unknown device 0x%x\n", part_id);
-
-	ret = devm_iio_init_iio_gts(dev, data->cd->scale1x, 0, data->cd->gains,
-				    data->cd->num_gains, data->cd->itimes,
-				    data->cd->num_itimes, &data->gts);
-	if (ret)
-		return ret;
-
-	ret = devm_iio_init_iio_gts(dev, data->cd->scale1x, 0, data->cd->gains_ir,
-				    data->cd->num_gains_ir, data->cd->itimes,
-				    data->cd->num_itimes, &data->gts_ir);
-	if (ret)
-		return ret;
-
-	mutex_init(&data->mutex);
-	data->regmap = regmap;
-	data->dev = dev;
-	data->irq = i2c->irq;
-
-	idev->channels = bu27008_channels;
-	idev->num_channels = ARRAY_SIZE(bu27008_channels);
-	idev->name = data->cd->name;
-	idev->info = &bu27008_info;
-	idev->modes = INDIO_DIRECT_MODE;
-	idev->available_scan_masks = bu27008_scan_masks;
-
-	ret = data->cd->chip_init(data);
-	if (ret)
-		return ret;
-
-	if (i2c->irq) {
-		ret = bu27008_setup_trigger(data, idev);
-		if (ret)
-			return ret;
-	} else {
-		dev_info(dev, "No IRQ, buffered mode disabled\n");
-	}
-
-	ret = devm_iio_device_register(dev, idev);
-	if (ret)
-		return dev_err_probe(dev, ret,
-				     "Unable to register iio device\n");
-
-	return 0;
-}
-
-static const struct of_device_id bu27008_of_match[] = {
-	{ .compatible = "rohm,bu27008", .data = &bu27008_chip },
-	{ .compatible = "rohm,bu27010", .data = &bu27010_chip },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, bu27008_of_match);
-
-static struct i2c_driver bu27008_i2c_driver = {
-	.driver = {
-		.name = "bu27008",
-		.of_match_table = bu27008_of_match,
-		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
-	},
-	.probe = bu27008_probe,
-};
-module_i2c_driver(bu27008_i2c_driver);
-
-MODULE_DESCRIPTION("ROHM BU27008 and BU27010 colour sensor driver");
-MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
-MODULE_LICENSE("GPL");
-MODULE_IMPORT_NS("IIO_GTS_HELPER");
diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c
index 4f591c2278f2..cc25596cb248 100644
--- a/drivers/iio/light/rohm-bu27034.c
+++ b/drivers/iio/light/rohm-bu27034.c
@@ -7,6 +7,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
@@ -205,7 +206,7 @@ struct bu27034_data {
 	struct {
 		u32 mlux;
 		__le16 channels[BU27034_NUM_HW_DATA_CHANS];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
@@ -395,30 +396,26 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us)
 	int numg = ARRAY_SIZE(gains);
 	int ret, int_time_old, i;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 	ret = bu27034_get_int_time(data);
 	if (ret < 0)
-		goto unlock_out;
+		return ret;
 
 	int_time_old = ret;
 
 	if (!iio_gts_valid_time(&data->gts, time_us)) {
 		dev_err(data->dev, "Unsupported integration time %u\n",
 			time_us);
-		ret = -EINVAL;
-
-		goto unlock_out;
+		return -EINVAL;
 	}
 
-	if (time_us == int_time_old) {
-		ret = 0;
-		goto unlock_out;
-	}
+	if (time_us == int_time_old)
+		return 0;
 
 	for (i = 0; i < numg; i++) {
 		ret = bu27034_get_gain(data, gains[i].chan, &gains[i].old_gain);
 		if (ret)
-			goto unlock_out;
+			return 0;
 
 		ret = iio_gts_find_new_gain_by_old_gain_time(&data->gts,
 							     gains[i].old_gain,
@@ -434,7 +431,7 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us)
 				gains[i].chan, time_us, scale1, scale2);
 
 			if (gains[i].new_gain < 0)
-				goto unlock_out;
+				return ret;
 
 			/*
 			 * If caller requests for integration time change and we
@@ -455,7 +452,7 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us)
 					 "Total gain increase. Risk of saturation");
 				ret = iio_gts_get_min_gain(&data->gts);
 				if (ret < 0)
-					goto unlock_out;
+					return ret;
 			}
 			dev_dbg(data->dev, "chan %u scale changed\n",
 				 gains[i].chan);
@@ -468,15 +465,10 @@ static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us)
 	for (i = 0; i < numg; i++) {
 		ret = bu27034_set_gain(data, gains[i].chan, gains[i].new_gain);
 		if (ret)
-			goto unlock_out;
+			return ret;
 	}
 
-	ret = bu27034_set_int_time(data, time_us);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return bu27034_set_int_time(data, time_us);
 }
 
 static int bu27034_set_scale(struct bu27034_data *data, int chan,
@@ -492,10 +484,10 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan,
 		return -EINVAL;
 	}
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 	ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL1, &time_sel);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel,
 						val, val2, &gain_sel);
@@ -518,7 +510,7 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan,
 
 		ret = bu27034_get_gain(data, gain.chan, &gain.old_gain);
 		if (ret)
-			goto unlock_out;
+			return ret;
 
 		/*
 		 * Iterate through all the times to see if we find one which
@@ -551,26 +543,20 @@ static int bu27034_set_scale(struct bu27034_data *data, int chan,
 		if (!found) {
 			dev_dbg(data->dev,
 				"Can't set scale maintaining other channel\n");
-			ret = -EINVAL;
-
-			goto unlock_out;
+			return -EINVAL;
 		}
 
 		ret = bu27034_set_gain(data, gain.chan, gain.new_gain);
 		if (ret)
-			goto unlock_out;
+			return ret;
 
 		ret = regmap_update_bits(data->regmap, BU27034_REG_MODE_CONTROL1,
 				  BU27034_MASK_MEAS_MODE, new_time_sel);
 		if (ret)
-			goto unlock_out;
+			return ret;
 	}
 
-	ret = bu27034_write_gain_sel(data, chan, gain_sel);
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return bu27034_write_gain_sel(data, chan, gain_sel);
 }
 
 /*
@@ -1221,42 +1207,33 @@ static int bu27034_buffer_enable(struct iio_dev *idev)
 	struct task_struct *task;
 	int ret;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 	ret = bu27034_meas_set(data, true);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	task = kthread_run(bu27034_buffer_thread, idev,
 				 "bu27034-buffering-%u",
 				 iio_device_id(idev));
-	if (IS_ERR(task)) {
-		ret = PTR_ERR(task);
-		goto unlock_out;
-	}
+	if (IS_ERR(task))
+		return PTR_ERR(task);
 
 	data->task = task;
 
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return 0;
 }
 
 static int bu27034_buffer_disable(struct iio_dev *idev)
 {
 	struct bu27034_data *data = iio_priv(idev);
-	int ret;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 	if (data->task) {
 		kthread_stop(data->task);
 		data->task = NULL;
 	}
 
-	ret = bu27034_meas_set(data, false);
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return bu27034_meas_set(data, false);
 }
 
 static const struct iio_buffer_setup_ops bu27034_buffer_ops = {
diff --git a/drivers/iio/light/rpr0521.c b/drivers/iio/light/rpr0521.c
index 56f5fbbf79ac..2ba917c5c138 100644
--- a/drivers/iio/light/rpr0521.c
+++ b/drivers/iio/light/rpr0521.c
@@ -203,7 +203,7 @@ struct rpr0521_data {
 	struct {
 		__le16 channels[3];
 		u8 garbage;
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/light/st_uvis25.h b/drivers/iio/light/st_uvis25.h
index 283086887caf..1f93e3dc45c2 100644
--- a/drivers/iio/light/st_uvis25.h
+++ b/drivers/iio/light/st_uvis25.h
@@ -30,7 +30,7 @@ struct st_uvis25_hw {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		u8 chan;
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/light/tcs3414.c b/drivers/iio/light/tcs3414.c
index 4fecdf10aeb1..884e43e4cda4 100644
--- a/drivers/iio/light/tcs3414.c
+++ b/drivers/iio/light/tcs3414.c
@@ -56,7 +56,7 @@ struct tcs3414_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		u16 chans[4];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
diff --git a/drivers/iio/light/tcs3472.c b/drivers/iio/light/tcs3472.c
index 4186aac04902..2bd36a344ea5 100644
--- a/drivers/iio/light/tcs3472.c
+++ b/drivers/iio/light/tcs3472.c
@@ -67,7 +67,7 @@ struct tcs3472_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		u16 chans[4];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
diff --git a/drivers/iio/light/veml3235.c b/drivers/iio/light/veml3235.c
index 66361c3012a3..77c9ae17ed47 100644
--- a/drivers/iio/light/veml3235.c
+++ b/drivers/iio/light/veml3235.c
@@ -11,6 +11,7 @@
 #include <linux/err.h>
 #include <linux/i2c.h>
 #include <linux/iio/iio.h>
+#include <linux/iio/iio-gts-helper.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
@@ -35,17 +36,33 @@ struct veml3235_data {
 	struct device *dev;
 	struct regmap *regmap;
 	struct veml3235_rf rf;
+	struct iio_gts gts;
 };
 
-static const int veml3235_it_times[][2] = {
-	{ 0, 50000 },
-	{ 0, 100000 },
-	{ 0, 200000 },
-	{ 0, 400000 },
-	{ 0, 800000 },
+static const struct iio_itime_sel_mul veml3235_it_sel[] = {
+	GAIN_SCALE_ITIME_US(50000, 0, 1),
+	GAIN_SCALE_ITIME_US(100000, 1, 2),
+	GAIN_SCALE_ITIME_US(200000, 2, 4),
+	GAIN_SCALE_ITIME_US(400000, 3, 8),
+	GAIN_SCALE_ITIME_US(800000, 4, 16),
 };
 
-static const int veml3235_scale_vals[] = { 1, 2, 4, 8 };
+/*
+ * The MSB (DG) doubles the value of the rest of the field, which leads to
+ * two possible combinations to obtain gain = 2 and gain = 4. The gain
+ * handling can be simplified by restricting DG = 1 to the only gain that
+ * really requires it, gain = 8. Note that "X10" is a reserved value.
+ */
+#define VEML3235_SEL_GAIN_X1 0
+#define VEML3235_SEL_GAIN_X2 1
+#define VEML3235_SEL_GAIN_X4 3
+#define VEML3235_SEL_GAIN_X8 7
+static const struct iio_gain_sel_pair veml3235_gain_sel[] = {
+	GAIN_SCALE_GAIN(1, VEML3235_SEL_GAIN_X1),
+	GAIN_SCALE_GAIN(2, VEML3235_SEL_GAIN_X2),
+	GAIN_SCALE_GAIN(4, VEML3235_SEL_GAIN_X4),
+	GAIN_SCALE_GAIN(8, VEML3235_SEL_GAIN_X8),
+};
 
 static int veml3235_power_on(struct veml3235_data *data)
 {
@@ -101,42 +118,58 @@ static const struct iio_chan_spec veml3235_channels[] = {
 	},
 };
 
+static const struct regmap_range veml3235_readable_ranges[] = {
+	regmap_reg_range(VEML3235_REG_CONF, VEML3235_REG_ID),
+};
+
+static const struct regmap_access_table veml3235_readable_table = {
+	.yes_ranges = veml3235_readable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(veml3235_readable_ranges),
+};
+
+static const struct regmap_range veml3235_writable_ranges[] = {
+	regmap_reg_range(VEML3235_REG_CONF, VEML3235_REG_CONF),
+};
+
+static const struct regmap_access_table veml3235_writable_table = {
+	.yes_ranges = veml3235_writable_ranges,
+	.n_yes_ranges = ARRAY_SIZE(veml3235_writable_ranges),
+};
+
+static const struct regmap_range veml3235_volatile_ranges[] = {
+	regmap_reg_range(VEML3235_REG_WH_DATA, VEML3235_REG_ALS_DATA),
+};
+
+static const struct regmap_access_table veml3235_volatile_table = {
+	.yes_ranges = veml3235_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(veml3235_volatile_ranges),
+};
+
 static const struct regmap_config veml3235_regmap_config = {
 	.name = "veml3235_regmap",
 	.reg_bits = 8,
 	.val_bits = 16,
 	.max_register = VEML3235_REG_ID,
 	.val_format_endian = REGMAP_ENDIAN_LITTLE,
+	.rd_table = &veml3235_readable_table,
+	.wr_table = &veml3235_writable_table,
+	.volatile_table = &veml3235_volatile_table,
+	.cache_type = REGCACHE_RBTREE,
 };
 
 static int veml3235_get_it(struct veml3235_data *data, int *val, int *val2)
 {
-	int ret, reg;
+	int ret, it_idx;
 
-	ret = regmap_field_read(data->rf.it, &reg);
+	ret = regmap_field_read(data->rf.it, &it_idx);
 	if (ret)
 		return ret;
 
-	switch (reg) {
-	case 0:
-		*val2 = 50000;
-		break;
-	case 1:
-		*val2 = 100000;
-		break;
-	case 2:
-		*val2 = 200000;
-		break;
-	case 3:
-		*val2 = 400000;
-		break;
-	case 4:
-		*val2 = 800000;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ret = iio_gts_find_int_time_by_sel(&data->gts, it_idx);
+	if (ret < 0)
+		return ret;
 
+	*val2 = ret;
 	*val = 0;
 
 	return IIO_VAL_INT_PLUS_MICRO;
@@ -145,78 +178,78 @@ static int veml3235_get_it(struct veml3235_data *data, int *val, int *val2)
 static int veml3235_set_it(struct iio_dev *indio_dev, int val, int val2)
 {
 	struct veml3235_data *data = iio_priv(indio_dev);
-	int ret, new_it;
+	int ret, gain_idx, it_idx, new_gain, prev_gain, prev_it;
+	bool in_range;
 
-	if (val)
+	if (val || !iio_gts_valid_time(&data->gts, val2))
 		return -EINVAL;
 
-	switch (val2) {
-	case 50000:
-		new_it = 0x00;
-		break;
-	case 100000:
-		new_it = 0x01;
-		break;
-	case 200000:
-		new_it = 0x02;
-		break;
-	case 400000:
-		new_it = 0x03;
-		break;
-	case 800000:
-		new_it = 0x04;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ret = regmap_field_read(data->rf.it, &it_idx);
+	if (ret)
+		return ret;
 
-	ret = regmap_field_write(data->rf.it, new_it);
-	if (ret) {
-		dev_err(data->dev,
-			"failed to update integration time: %d\n", ret);
+	ret = regmap_field_read(data->rf.gain, &gain_idx);
+	if (ret)
 		return ret;
-	}
 
-	return 0;
+	prev_it = iio_gts_find_int_time_by_sel(&data->gts, it_idx);
+	if (prev_it < 0)
+		return prev_it;
+
+	if (prev_it == val2)
+		return 0;
+
+	prev_gain = iio_gts_find_gain_by_sel(&data->gts, gain_idx);
+	if (prev_gain < 0)
+		return prev_gain;
+
+	ret = iio_gts_find_new_gain_by_gain_time_min(&data->gts, prev_gain, prev_it,
+						     val2, &new_gain, &in_range);
+	if (ret)
+		return ret;
+
+	if (!in_range)
+		dev_dbg(data->dev, "Optimal gain out of range\n");
+
+	ret = iio_gts_find_sel_by_int_time(&data->gts, val2);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_field_write(data->rf.it, ret);
+	if (ret)
+		return ret;
+
+	ret = iio_gts_find_sel_by_gain(&data->gts, new_gain);
+	if (ret < 0)
+		return ret;
+
+	return regmap_field_write(data->rf.gain, ret);
 }
 
-static int veml3235_set_gain(struct iio_dev *indio_dev, int val, int val2)
+static int veml3235_set_scale(struct iio_dev *indio_dev, int val, int val2)
 {
 	struct veml3235_data *data = iio_priv(indio_dev);
-	int ret, new_gain;
+	int ret, it_idx, gain_sel, time_sel;
 
-	if (val2 != 0)
-		return -EINVAL;
+	ret = regmap_field_read(data->rf.it, &it_idx);
+	if (ret)
+		return ret;
 
-	switch (val) {
-	case 1:
-		new_gain = 0x00;
-		break;
-	case 2:
-		new_gain = 0x01;
-		break;
-	case 4:
-		new_gain = 0x03;
-		break;
-	case 8:
-		new_gain = 0x07;
-		break;
-	default:
-		return -EINVAL;
-	}
+	ret = iio_gts_find_gain_time_sel_for_scale(&data->gts, val, val2,
+						   &gain_sel, &time_sel);
+	if (ret)
+		return ret;
 
-	ret = regmap_field_write(data->rf.gain, new_gain);
-	if (ret) {
-		dev_err(data->dev, "failed to set gain: %d\n", ret);
+	ret = regmap_field_write(data->rf.it, time_sel);
+	if (ret)
 		return ret;
-	}
 
-	return 0;
+	return regmap_field_write(data->rf.gain, gain_sel);
 }
 
-static int veml3235_get_gain(struct veml3235_data *data, int *val)
+static int veml3235_get_scale(struct veml3235_data *data, int *val, int *val2)
 {
-	int ret, reg;
+	int gain, it, reg, ret;
 
 	ret = regmap_field_read(data->rf.gain, &reg);
 	if (ret) {
@@ -224,25 +257,25 @@ static int veml3235_get_gain(struct veml3235_data *data, int *val)
 		return ret;
 	}
 
-	switch (reg & 0x03) {
-	case 0:
-		*val = 1;
-		break;
-	case 1:
-		*val = 2;
-		break;
-	case 3:
-		*val = 4;
-		break;
-	default:
-		return -EINVAL;
+	gain = iio_gts_find_gain_by_sel(&data->gts, reg);
+	if (gain < 0)
+		return gain;
+
+	ret = regmap_field_read(data->rf.it, &reg);
+	if (ret) {
+		dev_err(data->dev, "failed to read integration time %d\n", ret);
+		return ret;
 	}
 
-	/* Double gain */
-	if (reg & 0x04)
-		*val *= 2;
+	it = iio_gts_find_int_time_by_sel(&data->gts, reg);
+	if (it < 0)
+		return it;
+
+	ret = iio_gts_get_scale(&data->gts, gain, it, val, val2);
+	if (ret)
+		return ret;
 
-	return IIO_VAL_INT;
+	return IIO_VAL_INT_PLUS_NANO;
 }
 
 static int veml3235_read_raw(struct iio_dev *indio_dev,
@@ -276,7 +309,7 @@ static int veml3235_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_INT_TIME:
 		return veml3235_get_it(data, val, val2);
 	case IIO_CHAN_INFO_SCALE:
-		return veml3235_get_gain(data, val);
+		return veml3235_get_scale(data, val, val2);
 	default:
 		return -EINVAL;
 	}
@@ -287,17 +320,27 @@ static int veml3235_read_avail(struct iio_dev *indio_dev,
 			       const int **vals, int *type, int *length,
 			       long mask)
 {
+	struct veml3235_data *data = iio_priv(indio_dev);
+
 	switch (mask) {
 	case IIO_CHAN_INFO_INT_TIME:
-		*vals = (int *)&veml3235_it_times;
-		*length = 2 * ARRAY_SIZE(veml3235_it_times);
-		*type = IIO_VAL_INT_PLUS_MICRO;
-		return IIO_AVAIL_LIST;
+		return iio_gts_avail_times(&data->gts, vals, type, length);
+	case IIO_CHAN_INFO_SCALE:
+		return iio_gts_all_avail_scales(&data->gts, vals, type, length);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int veml3235_write_raw_get_fmt(struct iio_dev *indio_dev,
+				      struct iio_chan_spec const *chan,
+				      long mask)
+{
+	switch (mask) {
 	case IIO_CHAN_INFO_SCALE:
-		*vals = (int *)&veml3235_scale_vals;
-		*length = ARRAY_SIZE(veml3235_scale_vals);
-		*type = IIO_VAL_INT;
-		return IIO_AVAIL_LIST;
+		return IIO_VAL_INT_PLUS_NANO;
+	case IIO_CHAN_INFO_INT_TIME:
+		return IIO_VAL_INT_PLUS_MICRO;
 	default:
 		return -EINVAL;
 	}
@@ -311,7 +354,7 @@ static int veml3235_write_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_INT_TIME:
 		return veml3235_set_it(indio_dev, val, val2);
 	case IIO_CHAN_INFO_SCALE:
-		return veml3235_set_gain(indio_dev, val, val2);
+		return veml3235_set_scale(indio_dev, val, val2);
 	}
 
 	return -EINVAL;
@@ -321,7 +364,7 @@ static void veml3235_read_id(struct veml3235_data *data)
 {
 	int ret, reg;
 
-	ret = regmap_field_read(data->rf.id,  &reg);
+	ret = regmap_field_read(data->rf.id, &reg);
 	if (ret) {
 		dev_info(data->dev, "failed to read ID\n");
 		return;
@@ -371,6 +414,13 @@ static int veml3235_hw_init(struct iio_dev *indio_dev)
 	struct device *dev = data->dev;
 	int ret;
 
+	ret = devm_iio_init_iio_gts(data->dev, 0, 272640000,
+				    veml3235_gain_sel, ARRAY_SIZE(veml3235_gain_sel),
+				    veml3235_it_sel, ARRAY_SIZE(veml3235_it_sel),
+				    &data->gts);
+	if (ret)
+		return dev_err_probe(data->dev, ret, "failed to init iio gts\n");
+
 	/* Set gain to 1 and integration time to 100 ms */
 	ret = regmap_field_write(data->rf.gain, 0x00);
 	if (ret)
@@ -389,9 +439,10 @@ static int veml3235_hw_init(struct iio_dev *indio_dev)
 }
 
 static const struct iio_info veml3235_info = {
-	.read_raw  = veml3235_read_raw,
-	.read_avail  = veml3235_read_avail,
+	.read_raw = veml3235_read_raw,
+	.read_avail = veml3235_read_avail,
 	.write_raw = veml3235_write_raw,
+	.write_raw_get_fmt = veml3235_write_raw_get_fmt,
 };
 
 static int veml3235_probe(struct i2c_client *client)
@@ -493,3 +544,4 @@ module_i2c_driver(veml3235_driver);
 MODULE_AUTHOR("Javier Carrasco <javier.carrasco.cruz@gmail.com>");
 MODULE_DESCRIPTION("VEML3235 Ambient Light Sensor");
 MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("IIO_GTS_HELPER");
diff --git a/drivers/iio/light/veml6030.c b/drivers/iio/light/veml6030.c
index ccb43dfd5cf7..9b71825eea9b 100644
--- a/drivers/iio/light/veml6030.c
+++ b/drivers/iio/light/veml6030.c
@@ -28,6 +28,8 @@
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/events.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
 
 /* Device registers */
 #define VEML6030_REG_ALS_CONF   0x00
@@ -37,6 +39,7 @@
 #define VEML6030_REG_ALS_DATA   0x04
 #define VEML6030_REG_WH_DATA    0x05
 #define VEML6030_REG_ALS_INT    0x06
+#define VEML6030_REG_DATA(ch)   (VEML6030_REG_ALS_DATA + (ch))
 
 /* Bit masks for specific functionality */
 #define VEML6030_ALS_IT       GENMASK(9, 6)
@@ -56,6 +59,12 @@
 #define VEML6035_INT_CHAN     BIT(3)
 #define VEML6035_CHAN_EN      BIT(2)
 
+enum veml6030_scan {
+	VEML6030_SCAN_ALS,
+	VEML6030_SCAN_WH,
+	VEML6030_SCAN_TIMESTAMP,
+};
+
 struct veml603x_chip {
 	const char *name;
 	const int(*scale_vals)[][2];
@@ -242,6 +251,13 @@ static const struct iio_chan_spec veml6030_channels[] = {
 						     BIT(IIO_CHAN_INFO_SCALE),
 		.event_spec = veml6030_event_spec,
 		.num_event_specs = ARRAY_SIZE(veml6030_event_spec),
+		.scan_index = VEML6030_SCAN_ALS,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 16,
+			.storagebits = 16,
+			.endianness = IIO_CPU,
+		},
 	},
 	{
 		.type = IIO_INTENSITY,
@@ -253,7 +269,15 @@ static const struct iio_chan_spec veml6030_channels[] = {
 				BIT(IIO_CHAN_INFO_SCALE),
 		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME) |
 						     BIT(IIO_CHAN_INFO_SCALE),
+		.scan_index = VEML6030_SCAN_WH,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 16,
+			.storagebits = 16,
+			.endianness = IIO_CPU,
+		},
 	},
+	IIO_CHAN_SOFT_TIMESTAMP(VEML6030_SCAN_TIMESTAMP),
 };
 
 static const struct iio_chan_spec veml7700_channels[] = {
@@ -266,6 +290,13 @@ static const struct iio_chan_spec veml7700_channels[] = {
 				BIT(IIO_CHAN_INFO_SCALE),
 		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME) |
 						     BIT(IIO_CHAN_INFO_SCALE),
+		.scan_index = VEML6030_SCAN_ALS,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 16,
+			.storagebits = 16,
+			.endianness = IIO_CPU,
+		},
 	},
 	{
 		.type = IIO_INTENSITY,
@@ -277,7 +308,15 @@ static const struct iio_chan_spec veml7700_channels[] = {
 				BIT(IIO_CHAN_INFO_SCALE),
 		.info_mask_shared_by_all_available = BIT(IIO_CHAN_INFO_INT_TIME) |
 						     BIT(IIO_CHAN_INFO_SCALE),
+		.scan_index = VEML6030_SCAN_WH,
+		.scan_type = {
+			.sign = 'u',
+			.realbits = 16,
+			.storagebits = 16,
+			.endianness = IIO_CPU,
+		},
 	},
+	IIO_CHAN_SOFT_TIMESTAMP(VEML6030_SCAN_TIMESTAMP),
 };
 
 static const struct regmap_config veml6030_regmap_config = {
@@ -889,6 +928,37 @@ static irqreturn_t veml6030_event_handler(int irq, void *private)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t veml6030_trigger_handler(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *iio = pf->indio_dev;
+	struct veml6030_data *data = iio_priv(iio);
+	unsigned int reg;
+	int ch, ret, i = 0;
+	struct {
+		u16 chans[2];
+		aligned_s64 timestamp;
+	} scan;
+
+	memset(&scan, 0, sizeof(scan));
+
+	iio_for_each_active_channel(iio, ch) {
+		ret = regmap_read(data->regmap, VEML6030_REG_DATA(ch),
+				  &reg);
+		if (ret)
+			goto done;
+
+		scan.chans[i++] = reg;
+	}
+
+	iio_push_to_buffers_with_timestamp(iio, &scan, pf->timestamp);
+
+done:
+	iio_trigger_notify_done(iio->trig);
+
+	return IRQ_HANDLED;
+}
+
 static int veml6030_set_info(struct iio_dev *indio_dev)
 {
 	struct veml6030_data *data = iio_priv(indio_dev);
@@ -1077,6 +1147,12 @@ static int veml6030_probe(struct i2c_client *client)
 	if (ret < 0)
 		return ret;
 
+	ret = devm_iio_triggered_buffer_setup(&client->dev, indio_dev, NULL,
+					      veml6030_trigger_handler, NULL);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				     "Failed to register triggered buffer");
+
 	return devm_iio_device_register(&client->dev, indio_dev);
 }
 
diff --git a/drivers/iio/magnetometer/af8133j.c b/drivers/iio/magnetometer/af8133j.c
index acd291f3e792..a70bf8a3c73b 100644
--- a/drivers/iio/magnetometer/af8133j.c
+++ b/drivers/iio/magnetometer/af8133j.c
@@ -360,7 +360,7 @@ static irqreturn_t af8133j_trigger_handler(int irq, void *p)
 	s64 timestamp = iio_get_time_ns(indio_dev);
 	struct {
 		__le16 values[3];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} sample;
 	int ret;
 
diff --git a/drivers/iio/magnetometer/ak8974.c b/drivers/iio/magnetometer/ak8974.c
index 8306a18706ac..08975c60e325 100644
--- a/drivers/iio/magnetometer/ak8974.c
+++ b/drivers/iio/magnetometer/ak8974.c
@@ -197,7 +197,7 @@ struct ak8974 {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		__le16 channels[3];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 18077fb463a9..ef1363126cc2 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -426,7 +426,7 @@ struct ak8975_data {
 	/* Ensure natural alignment of timestamp */
 	struct {
 		s16 channels[3];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/magnetometer/bmc150_magn.c b/drivers/iio/magnetometer/bmc150_magn.c
index 7f545740178e..88bb673e40d8 100644
--- a/drivers/iio/magnetometer/bmc150_magn.c
+++ b/drivers/iio/magnetometer/bmc150_magn.c
@@ -140,7 +140,7 @@ struct bmc150_magn_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		s32 chans[3];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	struct iio_trigger *dready_trig;
 	bool dready_trigger_on;
diff --git a/drivers/iio/magnetometer/hmc5843.h b/drivers/iio/magnetometer/hmc5843.h
index 60fbb5431c88..ffd669b1ee7c 100644
--- a/drivers/iio/magnetometer/hmc5843.h
+++ b/drivers/iio/magnetometer/hmc5843.h
@@ -44,7 +44,7 @@ struct hmc5843_data {
 	struct iio_mount_matrix orientation;
 	struct {
 		__be16 chans[3];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c
index 5295dc0100e4..2fe8e97f2cf8 100644
--- a/drivers/iio/magnetometer/mag3110.c
+++ b/drivers/iio/magnetometer/mag3110.c
@@ -60,7 +60,7 @@ struct mag3110_data {
 	struct {
 		__be16 channels[3];
 		u8 temperature;
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/magnetometer/yamaha-yas530.c b/drivers/iio/magnetometer/yamaha-yas530.c
index c55a38650c0d..28012b20c64f 100644
--- a/drivers/iio/magnetometer/yamaha-yas530.c
+++ b/drivers/iio/magnetometer/yamaha-yas530.c
@@ -236,7 +236,7 @@ struct yas5xx {
 	 */
 	struct {
 		s32 channels[4];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/multiplexer/iio-mux.c b/drivers/iio/multiplexer/iio-mux.c
index 2953403bef53..c309d991490c 100644
--- a/drivers/iio/multiplexer/iio-mux.c
+++ b/drivers/iio/multiplexer/iio-mux.c
@@ -7,6 +7,7 @@
  * Author: Peter Rosin <peda@axentia.se>
  */
 
+#include <linux/cleanup.h>
 #include <linux/err.h>
 #include <linux/iio/consumer.h>
 #include <linux/iio/iio.h>
@@ -237,49 +238,18 @@ static ssize_t mux_write_ext_info(struct iio_dev *indio_dev, uintptr_t private,
 	return ret;
 }
 
-static int mux_configure_channel(struct device *dev, struct mux *mux,
-				 u32 state, const char *label, int idx)
+static int mux_configure_chan_ext_info(struct device *dev, struct mux *mux,
+				       int idx, int num_ext_info)
 {
 	struct mux_child *child = &mux->child[idx];
-	struct iio_chan_spec *chan = &mux->chan[idx];
 	struct iio_chan_spec const *pchan = mux->parent->channel;
-	char *page = NULL;
-	int num_ext_info;
 	int i;
 	int ret;
 
-	chan->indexed = 1;
-	chan->output = pchan->output;
-	chan->datasheet_name = label;
-	chan->ext_info = mux->ext_info;
-
-	ret = iio_get_channel_type(mux->parent, &chan->type);
-	if (ret < 0) {
-		dev_err(dev, "failed to get parent channel type\n");
-		return ret;
-	}
-
-	if (iio_channel_has_info(pchan, IIO_CHAN_INFO_RAW))
-		chan->info_mask_separate |= BIT(IIO_CHAN_INFO_RAW);
-	if (iio_channel_has_info(pchan, IIO_CHAN_INFO_SCALE))
-		chan->info_mask_separate |= BIT(IIO_CHAN_INFO_SCALE);
-
-	if (iio_channel_has_available(pchan, IIO_CHAN_INFO_RAW))
-		chan->info_mask_separate_available |= BIT(IIO_CHAN_INFO_RAW);
-
-	if (state >= mux_control_states(mux->control)) {
-		dev_err(dev, "too many channels\n");
-		return -EINVAL;
-	}
-
-	chan->channel = state;
+	char *page __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
 
-	num_ext_info = iio_get_channel_ext_info_count(mux->parent);
-	if (num_ext_info) {
-		page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-	}
 	child->ext_info_cache = devm_kcalloc(dev,
 					     num_ext_info,
 					     sizeof(*child->ext_info_cache),
@@ -318,8 +288,46 @@ static int mux_configure_channel(struct device *dev, struct mux *mux,
 		child->ext_info_cache[i].size = ret;
 	}
 
-	if (page)
-		devm_kfree(dev, page);
+	return 0;
+}
+
+static int mux_configure_channel(struct device *dev, struct mux *mux, u32 state,
+				 const char *label, int idx)
+{
+	struct iio_chan_spec *chan = &mux->chan[idx];
+	struct iio_chan_spec const *pchan = mux->parent->channel;
+	int num_ext_info;
+	int ret;
+
+	chan->indexed = 1;
+	chan->output = pchan->output;
+	chan->datasheet_name = label;
+	chan->ext_info = mux->ext_info;
+
+	ret = iio_get_channel_type(mux->parent, &chan->type);
+	if (ret < 0) {
+		dev_err(dev, "failed to get parent channel type\n");
+		return ret;
+	}
+
+	if (iio_channel_has_info(pchan, IIO_CHAN_INFO_RAW))
+		chan->info_mask_separate |= BIT(IIO_CHAN_INFO_RAW);
+	if (iio_channel_has_info(pchan, IIO_CHAN_INFO_SCALE))
+		chan->info_mask_separate |= BIT(IIO_CHAN_INFO_SCALE);
+
+	if (iio_channel_has_available(pchan, IIO_CHAN_INFO_RAW))
+		chan->info_mask_separate_available |= BIT(IIO_CHAN_INFO_RAW);
+
+	if (state >= mux_control_states(mux->control)) {
+		dev_err(dev, "too many channels\n");
+		return -EINVAL;
+	}
+
+	chan->channel = state;
+
+	num_ext_info = iio_get_channel_ext_info_count(mux->parent);
+	if (num_ext_info)
+		return mux_configure_chan_ext_info(dev, mux, idx, num_ext_info);
 
 	return 0;
 }
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 5376605b69b4..d44ab65c94cb 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -1002,7 +1002,7 @@ static int bmp280_preinit(struct bmp280_data *data)
 	 * after resetting, the device uses the complete power-on sequence so
 	 * it needs to wait for the defined start-up time.
 	 */
-	fsleep(data->start_up_time);
+	fsleep(data->start_up_time_us);
 
 	ret = regmap_read(data->regmap, BMP280_REG_STATUS, &reg);
 	if (ret)
@@ -1161,7 +1161,7 @@ const struct bmp280_chip_info bmp280_chip_info = {
 	.chip_id = bmp280_chip_ids,
 	.num_chip_id = ARRAY_SIZE(bmp280_chip_ids),
 	.regmap_config = &bmp280_regmap_config,
-	.start_up_time = 2000,
+	.start_up_time_us = 2000,
 	.channels = bmp280_channels,
 	.num_channels = ARRAY_SIZE(bmp280_channels),
 	.avail_scan_masks = bmp280_avail_scan_masks,
@@ -1347,7 +1347,7 @@ const struct bmp280_chip_info bme280_chip_info = {
 	.chip_id = bme280_chip_ids,
 	.num_chip_id = ARRAY_SIZE(bme280_chip_ids),
 	.regmap_config = &bme280_regmap_config,
-	.start_up_time = 2000,
+	.start_up_time_us = 2000,
 	.channels = bme280_channels,
 	.num_channels = ARRAY_SIZE(bme280_channels),
 	.avail_scan_masks = bme280_avail_scan_masks,
@@ -1414,7 +1414,7 @@ static int bmp380_cmd(struct bmp280_data *data, u8 cmd)
 		return ret;
 	}
 	/* Wait for 2ms for command to be processed */
-	usleep_range(data->start_up_time, data->start_up_time + 100);
+	fsleep(data->start_up_time_us);
 	/* Check for command processing error */
 	ret = regmap_read(data->regmap, BMP380_REG_ERROR, &reg);
 	if (ret) {
@@ -1806,7 +1806,7 @@ static int bmp380_chip_config(struct bmp280_data *data)
 		 * formula in datasheet section 3.9.2 with an offset of ~+15%
 		 * as it seen as well in table 3.9.1.
 		 */
-		msleep(150);
+		fsleep(150 * USEC_PER_MSEC);
 
 		/* Check config error flag */
 		ret = regmap_read(data->regmap, BMP380_REG_ERROR, &tmp);
@@ -1957,7 +1957,7 @@ const struct bmp280_chip_info bmp380_chip_info = {
 	.num_chip_id = ARRAY_SIZE(bmp380_chip_ids),
 	.regmap_config = &bmp380_regmap_config,
 	.spi_read_extra_byte = true,
-	.start_up_time = 2000,
+	.start_up_time_us = 2000,
 	.channels = bmp380_channels,
 	.num_channels = ARRAY_SIZE(bmp380_channels),
 	.avail_scan_masks = bmp280_avail_scan_masks,
@@ -2006,7 +2006,8 @@ static int bmp580_soft_reset(struct bmp280_data *data)
 		dev_err(data->dev, "failed to send reset command to device\n");
 		return ret;
 	}
-	usleep_range(2000, 2500);
+	/* From datasheet's table 4: electrical characteristics */
+	fsleep(2000);
 
 	/* Dummy read of chip_id */
 	ret = regmap_read(data->regmap, BMP580_REG_CHIP_ID, &reg);
@@ -2208,7 +2209,7 @@ static int bmp580_nvmem_read_impl(void *priv, unsigned int offset, void *val,
 		goto exit;
 	}
 	/* Wait standby transition time */
-	usleep_range(2500, 3000);
+	fsleep(2500);
 
 	while (bytes >= sizeof(*dst)) {
 		addr = bmp580_nvmem_addrs[offset / sizeof(*dst)];
@@ -2274,7 +2275,7 @@ static int bmp580_nvmem_write_impl(void *priv, unsigned int offset, void *val,
 		goto exit;
 	}
 	/* Wait standby transition time */
-	usleep_range(2500, 3000);
+	fsleep(2500);
 
 	while (bytes >= sizeof(*buf)) {
 		addr = bmp580_nvmem_addrs[offset / sizeof(*buf)];
@@ -2458,7 +2459,7 @@ static int bmp580_chip_config(struct bmp280_data *data)
 		return ret;
 	}
 	/* From datasheet's table 4: electrical characteristics */
-	usleep_range(2500, 3000);
+	fsleep(2500);
 
 	/* Set default DSP mode settings */
 	reg_val = FIELD_PREP(BMP580_DSP_COMP_MASK, BMP580_DSP_PRESS_TEMP_COMP_EN) |
@@ -2649,7 +2650,7 @@ const struct bmp280_chip_info bmp580_chip_info = {
 	.chip_id = bmp580_chip_ids,
 	.num_chip_id = ARRAY_SIZE(bmp580_chip_ids),
 	.regmap_config = &bmp580_regmap_config,
-	.start_up_time = 2000,
+	.start_up_time_us = 2000,
 	.channels = bmp580_channels,
 	.num_channels = ARRAY_SIZE(bmp580_channels),
 	.avail_scan_masks = bmp280_avail_scan_masks,
@@ -2720,7 +2721,7 @@ static int bmp180_wait_for_eoc(struct bmp280_data *data, u8 ctrl_meas)
 			delay_us =
 				conversion_time_max[data->oversampling_press];
 
-		usleep_range(delay_us, delay_us + 1000);
+		fsleep(delay_us);
 	}
 
 	ret = regmap_read(data->regmap, BMP280_REG_CTRL_MEAS, &ctrl);
@@ -2988,7 +2989,7 @@ const struct bmp280_chip_info bmp180_chip_info = {
 	.chip_id = bmp180_chip_ids,
 	.num_chip_id = ARRAY_SIZE(bmp180_chip_ids),
 	.regmap_config = &bmp180_regmap_config,
-	.start_up_time = 2000,
+	.start_up_time_us = 2000,
 	.channels = bmp280_channels,
 	.num_channels = ARRAY_SIZE(bmp280_channels),
 	.avail_scan_masks = bmp280_avail_scan_masks,
@@ -3066,7 +3067,7 @@ const struct bmp280_chip_info bmp085_chip_info = {
 	.chip_id = bmp180_chip_ids,
 	.num_chip_id = ARRAY_SIZE(bmp180_chip_ids),
 	.regmap_config = &bmp180_regmap_config,
-	.start_up_time = 2000,
+	.start_up_time_us = 2000,
 	.channels = bmp280_channels,
 	.num_channels = ARRAY_SIZE(bmp280_channels),
 	.avail_scan_masks = bmp280_avail_scan_masks,
@@ -3175,7 +3176,7 @@ int bmp280_common_probe(struct device *dev,
 	data->oversampling_temp = chip_info->oversampling_temp_default;
 	data->iir_filter_coeff = chip_info->iir_filter_coeff_default;
 	data->sampling_freq = chip_info->sampling_freq_default;
-	data->start_up_time = chip_info->start_up_time;
+	data->start_up_time_us = chip_info->start_up_time_us;
 
 	/* Bring up regulators */
 	regulator_bulk_set_supply_names(data->supplies,
@@ -3201,7 +3202,7 @@ int bmp280_common_probe(struct device *dev,
 		return ret;
 
 	/* Wait to make sure we started up properly */
-	usleep_range(data->start_up_time, data->start_up_time + 100);
+	fsleep(data->start_up_time_us);
 
 	/* Bring chip out of reset if there is an assigned GPIO line */
 	gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
@@ -3287,7 +3288,7 @@ int bmp280_common_probe(struct device *dev,
 	 * Set autosuspend to two orders of magnitude larger than the
 	 * start-up time.
 	 */
-	pm_runtime_set_autosuspend_delay(dev, data->start_up_time / 10);
+	pm_runtime_set_autosuspend_delay(dev, data->start_up_time_us / 10);
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_put(dev);
 
@@ -3306,7 +3307,7 @@ static int bmp280_runtime_suspend(struct device *dev)
 
 	data->chip_info->set_mode(data, BMP280_SLEEP);
 
-	fsleep(data->start_up_time);
+	fsleep(data->start_up_time_us);
 	return regulator_bulk_disable(BMP280_NUM_SUPPLIES, data->supplies);
 }
 
@@ -3320,7 +3321,7 @@ static int bmp280_runtime_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	usleep_range(data->start_up_time, data->start_up_time + 100);
+	fsleep(data->start_up_time_us);
 
 	ret = data->chip_info->chip_config(data);
 	if (ret)
diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h
index 2df1175b6b85..5b2ee1d0ee46 100644
--- a/drivers/iio/pressure/bmp280.h
+++ b/drivers/iio/pressure/bmp280.h
@@ -434,7 +434,7 @@ struct bmp280_data {
 		struct bmp380_calib bmp380;
 	} calib;
 	struct regulator_bulk_data supplies[BMP280_NUM_SUPPLIES];
-	unsigned int start_up_time; /* in microseconds */
+	unsigned int start_up_time_us;
 
 	/* log of base 2 of oversampling rate */
 	u8 oversampling_press;
@@ -470,8 +470,8 @@ struct bmp280_data {
 		/* Sensor data buffer */
 		u8 buf[BME280_BURST_READ_BYTES];
 		/* Calibration data buffers */
-		__le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / 2];
-		__be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / 2];
+		__le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / sizeof(__le16)];
+		__be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / sizeof(__be16)];
 		u8 bme280_humid_cal_buf[BME280_CONTIGUOUS_CALIB_REGS];
 		u8 bmp380_cal_buf[BMP380_CALIB_REG_COUNT];
 		/* Miscellaneous, endianness-aware data buffers */
@@ -490,7 +490,7 @@ struct bmp280_chip_info {
 
 	const struct iio_chan_spec *channels;
 	int num_channels;
-	unsigned int start_up_time;
+	unsigned int start_up_time_us;
 	const unsigned long *avail_scan_masks;
 
 	const int *oversampling_temp_avail;
diff --git a/drivers/iio/pressure/hsc030pa.h b/drivers/iio/pressure/hsc030pa.h
index 9b40f46f575f..5db46784f4c6 100644
--- a/drivers/iio/pressure/hsc030pa.h
+++ b/drivers/iio/pressure/hsc030pa.h
@@ -58,7 +58,7 @@ struct hsc_data {
 	s32 p_offset_dec;
 	struct {
 		__be16 chan[2];
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	u8 buffer[HSC_REG_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN);
 };
diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c
index 056c8271c49d..00c077b2a2a4 100644
--- a/drivers/iio/pressure/ms5611_core.c
+++ b/drivers/iio/pressure/ms5611_core.c
@@ -213,7 +213,7 @@ static irqreturn_t ms5611_trigger_handler(int irq, void *p)
 	/* Ensure buffer elements are naturally aligned */
 	struct {
 		s32 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	int ret;
 
diff --git a/drivers/iio/pressure/rohm-bm1390.c b/drivers/iio/pressure/rohm-bm1390.c
index f24d9f927681..9c1197f0e742 100644
--- a/drivers/iio/pressure/rohm-bm1390.c
+++ b/drivers/iio/pressure/rohm-bm1390.c
@@ -8,6 +8,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
@@ -138,7 +139,7 @@ enum {
 struct bm1390_data_buf {
 	u32 pressure;
 	__be16 temp;
-	s64 ts __aligned(8);
+	aligned_s64 ts;
 };
 
 /* BM1390 has FIFO for 4 pressure samples */
@@ -263,14 +264,14 @@ static int bm1390_read_data(struct bm1390_data *data,
 {
 	int ret, warn;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 	/*
 	 * We use 'continuous mode' even for raw read because according to the
 	 * data-sheet an one-shot mode can't be used with IIR filter.
 	 */
 	ret = bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	switch (chan->type) {
 	case IIO_PRESSURE:
@@ -287,10 +288,8 @@ static int bm1390_read_data(struct bm1390_data *data,
 	warn = bm1390_meas_set(data, BM1390_MEAS_MODE_STOP);
 	if (warn)
 		dev_warn(data->dev, "Failed to stop measurement (%d)\n", warn);
-unlock_out:
-	mutex_unlock(&data->mutex);
 
-	return ret;
+	return 0;
 }
 
 static int bm1390_read_raw(struct iio_dev *idev,
@@ -543,38 +542,33 @@ static int bm1390_fifo_enable(struct iio_dev *idev)
 	if (data->irq <= 0)
 		return -EINVAL;
 
-	mutex_lock(&data->mutex);
-	if (data->trigger_enabled) {
-		ret = -EBUSY;
-		goto unlock_out;
-	}
+	guard(mutex)(&data->mutex);
+
+	if (data->trigger_enabled)
+		return -EBUSY;
 
 	/* Update watermark to HW */
 	ret = bm1390_fifo_set_wmi(data);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	/* Enable WMI_IRQ */
 	ret = regmap_set_bits(data->regmap, BM1390_REG_MODE_CTRL,
 			      BM1390_MASK_WMI_EN);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	/* Enable FIFO */
 	ret = regmap_set_bits(data->regmap, BM1390_REG_FIFO_CTRL,
 			      BM1390_MASK_FIFO_EN);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	data->state = BM1390_STATE_FIFO;
 
 	data->old_timestamp = iio_get_time_ns(idev);
-	ret = bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS);
 
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS);
 }
 
 static int bm1390_fifo_disable(struct iio_dev *idev)
@@ -584,27 +578,22 @@ static int bm1390_fifo_disable(struct iio_dev *idev)
 
 	msleep(1);
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 	ret = bm1390_meas_set(data, BM1390_MEAS_MODE_STOP);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	/* Disable FIFO */
 	ret = regmap_clear_bits(data->regmap, BM1390_REG_FIFO_CTRL,
 				BM1390_MASK_FIFO_EN);
 	if (ret)
-		goto unlock_out;
+		return ret;
 
 	data->state = BM1390_STATE_SAMPLE;
 
 	/* Disable WMI_IRQ */
-	ret = regmap_clear_bits(data->regmap, BM1390_REG_MODE_CTRL,
+	return regmap_clear_bits(data->regmap, BM1390_REG_MODE_CTRL,
 				 BM1390_MASK_WMI_EN);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
 }
 
 static int bm1390_buffer_postenable(struct iio_dev *idev)
@@ -688,25 +677,24 @@ static irqreturn_t bm1390_irq_thread_handler(int irq, void *private)
 {
 	struct iio_dev *idev = private;
 	struct bm1390_data *data = iio_priv(idev);
-	int ret = IRQ_NONE;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (data->trigger_enabled) {
 		iio_trigger_poll_nested(data->trig);
-		ret = IRQ_HANDLED;
-	} else if (data->state == BM1390_STATE_FIFO) {
+		return IRQ_HANDLED;
+	}
+
+	if (data->state == BM1390_STATE_FIFO) {
 		int ok;
 
 		ok = __bm1390_fifo_flush(idev, BM1390_FIFO_LENGTH,
 					 data->timestamp);
 		if (ok > 0)
-			ret = IRQ_HANDLED;
+			return IRQ_HANDLED;
 	}
 
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return IRQ_NONE;
 }
 
 static int bm1390_set_drdy_irq(struct bm1390_data *data, bool en)
@@ -722,17 +710,16 @@ static int bm1390_trigger_set_state(struct iio_trigger *trig,
 				    bool state)
 {
 	struct bm1390_data *data = iio_trigger_get_drvdata(trig);
-	int ret = 0;
+	int ret;
 
-	mutex_lock(&data->mutex);
+	guard(mutex)(&data->mutex);
 
 	if (data->trigger_enabled == state)
-		goto unlock_out;
+		return 0;
 
 	if (data->state == BM1390_STATE_FIFO) {
 		dev_warn(data->dev, "Can't set trigger when FIFO enabled\n");
-		ret = -EBUSY;
-		goto unlock_out;
+		return -EBUSY;
 	}
 
 	data->trigger_enabled = state;
@@ -740,13 +727,13 @@ static int bm1390_trigger_set_state(struct iio_trigger *trig,
 	if (state) {
 		ret = bm1390_meas_set(data, BM1390_MEAS_MODE_CONTINUOUS);
 		if (ret)
-			goto unlock_out;
+			return ret;
 	} else {
 		int dummy;
 
 		ret = bm1390_meas_set(data, BM1390_MEAS_MODE_STOP);
 		if (ret)
-			goto unlock_out;
+			return ret;
 
 		/*
 		 * We need to read the status register in order to ACK the
@@ -758,12 +745,7 @@ static int bm1390_trigger_set_state(struct iio_trigger *trig,
 			dev_warn(data->dev, "status read failed\n");
 	}
 
-	ret = bm1390_set_drdy_irq(data, state);
-
-unlock_out:
-	mutex_unlock(&data->mutex);
-
-	return ret;
+	return bm1390_set_drdy_irq(data, state);
 }
 
 static const struct iio_trigger_ops bm1390_trigger_ops = {
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index 96fa97451cbf..9d3caf2bef18 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -63,7 +63,7 @@ struct as3935_state {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		u8 chan;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	u8 buf[2] __aligned(IIO_DMA_MINALIGN);
 };
diff --git a/drivers/iio/proximity/aw96103.c b/drivers/iio/proximity/aw96103.c
index cdd254da9e50..3472a2c36e44 100644
--- a/drivers/iio/proximity/aw96103.c
+++ b/drivers/iio/proximity/aw96103.c
@@ -433,7 +433,7 @@ static int aw96103_write_event_config(struct iio_dev *indio_dev,
 				  state ? BIT(chan->channel) : 0);
 }
 
-static struct iio_info iio_info = {
+static const struct iio_info iio_info = {
 	.read_raw = aw96103_read_raw,
 	.read_event_value = aw96103_read_event_val,
 	.write_event_value = aw96103_write_event_val,
diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c
index 4021feb7a7ac..e092a935dbac 100644
--- a/drivers/iio/proximity/hx9023s.c
+++ b/drivers/iio/proximity/hx9023s.c
@@ -14,6 +14,7 @@
 #include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/errno.h>
+#include <linux/firmware.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/irqreturn.h>
@@ -100,6 +101,17 @@
 #define HX9023S_INTERRUPT_MASK GENMASK(9, 0)
 #define HX9023S_PROX_DEBOUNCE_MASK GENMASK(3, 0)
 
+#define FW_VER_OFFSET 2
+#define FW_REG_CNT_OFFSET 3
+#define FW_DATA_OFFSET 16
+
+struct hx9023s_bin {
+	u16 reg_count;
+	u16 fw_size;
+	u8 fw_ver;
+	u8 data[] __counted_by(fw_size);
+};
+
 struct hx9023s_ch_data {
 	s16 raw; /* Raw Data*/
 	s16 lp; /* Low Pass Filter Data*/
@@ -134,7 +146,7 @@ struct hx9023s_data {
 
 	struct {
 		__le16 channels[HX9023S_CH_NUM];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} buffer;
 
 	/*
@@ -998,6 +1010,77 @@ static int hx9023s_id_check(struct iio_dev *indio_dev)
 	return 0;
 }
 
+static int hx9023s_bin_load(struct hx9023s_data *data, struct hx9023s_bin *bin)
+{
+	u8 *cfg_start = bin->data + FW_DATA_OFFSET;
+	u8 addr, val;
+	u16 i;
+	int ret;
+
+	for (i = 0; i < bin->reg_count; i++) {
+		addr = cfg_start[i * 2];
+		val = cfg_start[i * 2 + 1];
+		ret = regmap_write(data->regmap, addr, val);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data)
+{
+	struct hx9023s_bin *bin __free(kfree) =
+		kzalloc(fw->size + sizeof(*bin), GFP_KERNEL);
+	if (!bin)
+		return -ENOMEM;
+
+	memcpy(bin->data, fw->data, fw->size);
+	release_firmware(fw);
+
+	bin->fw_size = fw->size;
+	bin->fw_ver = bin->data[FW_VER_OFFSET];
+	bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET);
+
+	return hx9023s_bin_load(data, bin);
+}
+
+static void hx9023s_cfg_update(const struct firmware *fw, void *context)
+{
+	struct hx9023s_data *data = context;
+	struct device *dev = regmap_get_device(data->regmap);
+	int ret;
+
+	if (!fw || !fw->data) {
+		dev_warn(dev, "No firmware\n");
+		goto no_fw;
+	}
+
+	ret = hx9023s_send_cfg(fw, data);
+	if (ret) {
+		dev_warn(dev, "Firmware update failed: %d\n", ret);
+		goto no_fw;
+	}
+
+	ret = regcache_sync(data->regmap);
+	if (ret)
+		dev_err(dev, "regcache sync failed\n");
+
+	return;
+
+no_fw:
+	ret = regmap_multi_reg_write(data->regmap, hx9023s_reg_init_list,
+				     ARRAY_SIZE(hx9023s_reg_init_list));
+	if (ret) {
+		dev_err(dev, "Error loading default configuration\n");
+		return;
+	}
+
+	ret = regcache_sync(data->regmap);
+	if (ret)
+		dev_err(dev, "regcache sync failed\n");
+}
+
 static int hx9023s_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
@@ -1036,18 +1119,14 @@ static int hx9023s_probe(struct i2c_client *client)
 	indio_dev->modes = INDIO_DIRECT_MODE;
 	i2c_set_clientdata(client, indio_dev);
 
-	ret = regmap_multi_reg_write(data->regmap, hx9023s_reg_init_list,
-				     ARRAY_SIZE(hx9023s_reg_init_list));
-	if (ret)
-		return dev_err_probe(dev, ret, "device init failed\n");
-
 	ret = hx9023s_ch_cfg(data);
 	if (ret)
 		return dev_err_probe(dev, ret, "channel config failed\n");
 
-	ret = regcache_sync(data->regmap);
+	ret = request_firmware_nowait(THIS_MODULE, true, "hx9023s.bin", dev,
+				      GFP_KERNEL, data, hx9023s_cfg_update);
 	if (ret)
-		return dev_err_probe(dev, ret, "regcache sync failed\n");
+		return dev_err_probe(dev, ret, "reg config failed\n");
 
 	if (client->irq) {
 		ret = devm_request_threaded_irq(dev, client->irq,
diff --git a/drivers/iio/proximity/mb1232.c b/drivers/iio/proximity/mb1232.c
index 614e65cb9d42..cfc75d001f20 100644
--- a/drivers/iio/proximity/mb1232.c
+++ b/drivers/iio/proximity/mb1232.c
@@ -45,7 +45,7 @@ struct mb1232_data {
 	/* Ensure correct alignment of data to push to IIO buffer */
 	struct {
 		s16 distance;
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 };
 
diff --git a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c
index 5c959730aecd..f3d054b06b4c 100644
--- a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c
+++ b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c
@@ -47,7 +47,7 @@ struct lidar_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		u16 chan;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 };
 
diff --git a/drivers/iio/proximity/srf08.c b/drivers/iio/proximity/srf08.c
index a75ea5042876..86cab113ef3d 100644
--- a/drivers/iio/proximity/srf08.c
+++ b/drivers/iio/proximity/srf08.c
@@ -66,7 +66,7 @@ struct srf08_data {
 	/* Ensure timestamp is naturally aligned */
 	struct {
 		s16 chan;
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 
 	/* Sensor-Type */
diff --git a/drivers/iio/proximity/sx_common.h b/drivers/iio/proximity/sx_common.h
index fb14e6f06a6d..259b5c695233 100644
--- a/drivers/iio/proximity/sx_common.h
+++ b/drivers/iio/proximity/sx_common.h
@@ -125,7 +125,7 @@ struct sx_common_data {
 	/* Ensure correct alignment of timestamp when present. */
 	struct {
 		__be16 channels[SX_COMMON_MAX_NUM_CHANNELS];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} buffer;
 
 	unsigned int suspend_ctrl;
diff --git a/drivers/iio/resolver/ad2s1210.c b/drivers/iio/resolver/ad2s1210.c
index a414eef12e5e..b681129a99b6 100644
--- a/drivers/iio/resolver/ad2s1210.c
+++ b/drivers/iio/resolver/ad2s1210.c
@@ -164,7 +164,7 @@ struct ad2s1210_state {
 	struct {
 		__be16 chan[2];
 		/* Ensure timestamp is naturally aligned. */
-		s64 timestamp __aligned(8);
+		aligned_s64 timestamp;
 	} scan;
 	/** SPI transmit buffer. */
 	u8 rx[2];
diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c
index 02b27f471baa..1998047a1f24 100644
--- a/drivers/iio/temperature/tmp006.c
+++ b/drivers/iio/temperature/tmp006.c
@@ -248,7 +248,7 @@ static irqreturn_t tmp006_trigger_handler(int irq, void *p)
 	struct tmp006_data *data = iio_priv(indio_dev);
 	struct {
 		s16 channels[2];
-		s64 ts __aligned(8);
+		aligned_s64 ts;
 	} scan;
 	s32 ret;
 
diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c
index bb60b2d7b2ec..e41cb741253b 100644
--- a/drivers/iio/trigger/stm32-timer-trigger.c
+++ b/drivers/iio/trigger/stm32-timer-trigger.c
@@ -38,6 +38,9 @@ static const void *triggers_table[][MAX_TRIGGERS] = {
 	{ TIM15_TRGO,},
 	{ TIM16_OC1,},
 	{ TIM17_OC1,},
+	{ }, /* timer 18 */
+	{ }, /* timer 19 */
+	{ TIM20_TRGO, TIM20_TRGO2, TIM20_OC1, TIM20_OC2, TIM20_OC3, },
 };
 
 /* List the triggers accepted by each timer */
@@ -119,7 +122,7 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv,
 			     unsigned int frequency)
 {
 	unsigned long long prd, div;
-	int prescaler = 0;
+	int prescaler = 0, ret;
 	u32 ccer;
 
 	/* Period and prescaler values depends of clock rate */
@@ -150,10 +153,12 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv,
 	if (ccer & TIM_CCER_CCXE)
 		return -EBUSY;
 
-	mutex_lock(&priv->lock);
+	guard(mutex)(&priv->lock);
 	if (!priv->enabled) {
 		priv->enabled = true;
-		clk_enable(priv->clk);
+		ret = clk_enable(priv->clk);
+		if (ret)
+			return ret;
 	}
 
 	regmap_write(priv->regmap, TIM_PSC, prescaler);
@@ -173,7 +178,6 @@ static int stm32_timer_start(struct stm32_timer_trigger *priv,
 
 	/* Enable controller */
 	regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN);
-	mutex_unlock(&priv->lock);
 
 	return 0;
 }
@@ -307,7 +311,7 @@ static ssize_t stm32_tt_store_master_mode(struct device *dev,
 	struct stm32_timer_trigger *priv = dev_get_drvdata(dev);
 	struct iio_trigger *trig = to_iio_trigger(dev);
 	u32 mask, shift, master_mode_max;
-	int i;
+	int i, ret;
 
 	if (stm32_timer_is_trgo2_name(trig->name)) {
 		mask = TIM_CR2_MMS2;
@@ -322,15 +326,16 @@ static ssize_t stm32_tt_store_master_mode(struct device *dev,
 	for (i = 0; i <= master_mode_max; i++) {
 		if (!strncmp(master_mode_table[i], buf,
 			     strlen(master_mode_table[i]))) {
-			mutex_lock(&priv->lock);
+			guard(mutex)(&priv->lock);
 			if (!priv->enabled) {
 				/* Clock should be enabled first */
 				priv->enabled = true;
-				clk_enable(priv->clk);
+				ret = clk_enable(priv->clk);
+				if (ret)
+					return ret;
 			}
 			regmap_update_bits(priv->regmap, TIM_CR2, mask,
 					   i << shift);
-			mutex_unlock(&priv->lock);
 			return len;
 		}
 	}
@@ -482,6 +487,7 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev,
 				   int val, int val2, long mask)
 {
 	struct stm32_timer_trigger *priv = iio_priv(indio_dev);
+	int ret;
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
@@ -491,12 +497,14 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev,
 		/* fixed scale */
 		return -EINVAL;
 
-	case IIO_CHAN_INFO_ENABLE:
-		mutex_lock(&priv->lock);
+	case IIO_CHAN_INFO_ENABLE: {
+		guard(mutex)(&priv->lock);
 		if (val) {
 			if (!priv->enabled) {
 				priv->enabled = true;
-				clk_enable(priv->clk);
+				ret = clk_enable(priv->clk);
+				if (ret)
+					return ret;
 			}
 			regmap_set_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN);
 		} else {
@@ -506,11 +514,12 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev,
 				clk_disable(priv->clk);
 			}
 		}
-		mutex_unlock(&priv->lock);
+
 		return 0;
 	}
-
-	return -EINVAL;
+	default:
+		return -EINVAL;
+	}
 }
 
 static int stm32_counter_validate_trigger(struct iio_dev *indio_dev,
@@ -602,6 +611,7 @@ static int stm32_set_enable_mode(struct iio_dev *indio_dev,
 {
 	struct stm32_timer_trigger *priv = iio_priv(indio_dev);
 	int sms = stm32_enable_mode2sms(mode);
+	int ret;
 
 	if (sms < 0)
 		return sms;
@@ -609,12 +619,15 @@ static int stm32_set_enable_mode(struct iio_dev *indio_dev,
 	 * Triggered mode sets CEN bit automatically by hardware. So, first
 	 * enable counter clock, so it can use it. Keeps it in sync with CEN.
 	 */
-	mutex_lock(&priv->lock);
-	if (sms == 6 && !priv->enabled) {
-		clk_enable(priv->clk);
-		priv->enabled = true;
+	scoped_guard(mutex, &priv->lock) {
+		if (sms == 6 && !priv->enabled) {
+			ret = clk_enable(priv->clk);
+			if (ret)
+				return ret;
+
+			priv->enabled = true;
+		}
 	}
-	mutex_unlock(&priv->lock);
 
 	regmap_update_bits(priv->regmap, TIM_SMCR, TIM_SMCR_SMS, sms);
 
@@ -781,7 +794,7 @@ static int stm32_timer_trigger_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	/* Create an IIO device only if we have triggers to be validated */
-	if (*cfg->valids_table[index])
+	if (cfg->valids_table && *cfg->valids_table[index])
 		priv = stm32_setup_counter_device(dev);
 	else
 		priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -794,7 +807,8 @@ static int stm32_timer_trigger_probe(struct platform_device *pdev)
 	priv->clk = ddata->clk;
 	priv->max_arr = ddata->max_arr;
 	priv->triggers = triggers_table[index];
-	priv->valids = cfg->valids_table[index];
+	if (cfg->valids_table && *cfg->valids_table[index])
+		priv->valids = cfg->valids_table[index];
 	stm32_timer_detect_trgo2(priv);
 	mutex_init(&priv->lock);
 
@@ -886,6 +900,16 @@ static const struct stm32_timer_trigger_cfg stm32h7_timer_trg_cfg = {
 	.num_valids_table = ARRAY_SIZE(stm32h7_valids_table),
 };
 
+static const struct stm32_timer_trigger_cfg stm32mp25_timer_trg_cfg = {
+	/*
+	 * valids_table not used: counter framework is now superseding the deprecated IIO
+	 * counter interface (IIO_COUNT), so don't support it. num_valids_table is only
+	 * kept here to register the IIO HW triggers. valids_table should be moved at some
+	 * point to the stm32-timer-cnt driver instead.
+	 */
+	.num_valids_table = ARRAY_SIZE(triggers_table),
+};
+
 static const struct of_device_id stm32_trig_of_match[] = {
 	{
 		.compatible = "st,stm32-timer-trigger",
@@ -893,6 +917,9 @@ static const struct of_device_id stm32_trig_of_match[] = {
 	}, {
 		.compatible = "st,stm32h7-timer-trigger",
 		.data = (void *)&stm32h7_timer_trg_cfg,
+	}, {
+		.compatible = "st,stm32mp25-timer-trigger",
+		.data = (void *)&stm32mp25_timer_trg_cfg,
 	},
 	{ /* end node */ },
 };
diff --git a/drivers/infiniband/hw/hfi1/iowait.h b/drivers/infiniband/hw/hfi1/iowait.h
index 49805a24bb0a..7259f4f55700 100644
--- a/drivers/infiniband/hw/hfi1/iowait.h
+++ b/drivers/infiniband/hw/hfi1/iowait.h
@@ -92,7 +92,7 @@ struct iowait_work {
  *
  * The lock field is used by waiters to record
  * the seqlock_t that guards the list head.
- * Waiters explicity know that, but the destroy
+ * Waiters explicitly know that, but the destroy
  * code that unwaits QPs does not.
  */
 struct iowait {
diff --git a/drivers/infiniband/hw/usnic/usnic_abi.h b/drivers/infiniband/hw/usnic/usnic_abi.h
index 7fe9502ce8d3..86a82a4da0aa 100644
--- a/drivers/infiniband/hw/usnic/usnic_abi.h
+++ b/drivers/infiniband/hw/usnic/usnic_abi.h
@@ -72,7 +72,7 @@ struct usnic_ib_create_qp_resp {
 	u64				bar_bus_addr;
 	u32				bar_len;
 /*
- * WQ, RQ, CQ are explicity specified bc exposing a generic resources inteface
+ * WQ, RQ, CQ are explicitly specified bc exposing a generic resources inteface
  * expands the scope of ABI to many files.
  */
 	u32				wq_cnt;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 7289ae0b83ac..1378651735f6 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2844,7 +2844,8 @@ static int srp_target_alloc(struct scsi_target *starget)
 	return 0;
 }
 
-static int srp_slave_configure(struct scsi_device *sdev)
+static int srp_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	struct Scsi_Host *shost = sdev->host;
 	struct srp_target_port *target = host_to_target(shost);
@@ -3067,7 +3068,7 @@ static const struct scsi_host_template srp_template = {
 	.name				= "InfiniBand SRP initiator",
 	.proc_name			= DRV_NAME,
 	.target_alloc			= srp_target_alloc,
-	.slave_configure		= srp_slave_configure,
+	.sdev_configure			= srp_sdev_configure,
 	.info				= srp_target_info,
 	.init_cmd_priv			= srp_init_cmd_priv,
 	.exit_cmd_priv			= srp_exit_cmd_priv,
diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig
index 362fb9b0a198..1219f4f23d40 100644
--- a/drivers/interconnect/qcom/Kconfig
+++ b/drivers/interconnect/qcom/Kconfig
@@ -337,6 +337,15 @@ config INTERCONNECT_QCOM_SM8650
 	  This is a driver for the Qualcomm Network-on-Chip on SM8650-based
 	  platforms.
 
+config INTERCONNECT_QCOM_SM8750
+	tristate "Qualcomm SM8750 interconnect driver"
+	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
+	select INTERCONNECT_QCOM_RPMH
+	select INTERCONNECT_QCOM_BCM_VOTER
+	help
+	  This is a driver for the Qualcomm Network-on-Chip on SM8750-based
+	  platforms.
+
 config INTERCONNECT_QCOM_X1E80100
 	tristate "Qualcomm X1E80100 interconnect driver"
 	depends on INTERCONNECT_QCOM_RPMH_POSSIBLE
diff --git a/drivers/interconnect/qcom/Makefile b/drivers/interconnect/qcom/Makefile
index 9997728c02bf..7887b1e8d69b 100644
--- a/drivers/interconnect/qcom/Makefile
+++ b/drivers/interconnect/qcom/Makefile
@@ -40,6 +40,7 @@ qnoc-sm8350-objs			:= sm8350.o
 qnoc-sm8450-objs			:= sm8450.o
 qnoc-sm8550-objs			:= sm8550.o
 qnoc-sm8650-objs			:= sm8650.o
+qnoc-sm8750-objs			:= sm8750.o
 qnoc-x1e80100-objs			:= x1e80100.o
 icc-smd-rpm-objs			:= smd-rpm.o icc-rpm.o icc-rpm-clocks.o
 
@@ -80,5 +81,6 @@ obj-$(CONFIG_INTERCONNECT_QCOM_SM8350) += qnoc-sm8350.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8450) += qnoc-sm8450.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8550) += qnoc-sm8550.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SM8650) += qnoc-sm8650.o
+obj-$(CONFIG_INTERCONNECT_QCOM_SM8750) += qnoc-sm8750.o
 obj-$(CONFIG_INTERCONNECT_QCOM_X1E80100) += qnoc-x1e80100.o
 obj-$(CONFIG_INTERCONNECT_QCOM_SMD_RPM) += icc-smd-rpm.o
diff --git a/drivers/interconnect/qcom/sm8750.c b/drivers/interconnect/qcom/sm8750.c
new file mode 100644
index 000000000000..69bc22222075
--- /dev/null
+++ b/drivers/interconnect/qcom/sm8750.c
@@ -0,0 +1,1705 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/interconnect.h>
+#include <linux/interconnect-provider.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <dt-bindings/interconnect/qcom,sm8750-rpmh.h>
+
+#include "bcm-voter.h"
+#include "icc-rpmh.h"
+
+#define SM8750_MASTER_GPU_TCU				0
+#define SM8750_MASTER_SYS_TCU				1
+#define SM8750_MASTER_APPSS_PROC			2
+#define SM8750_MASTER_LLCC				3
+#define SM8750_MASTER_QDSS_BAM				4
+#define SM8750_MASTER_QSPI_0				5
+#define SM8750_MASTER_QUP_1				6
+#define SM8750_MASTER_QUP_2				7
+#define SM8750_MASTER_A1NOC_SNOC			8
+#define SM8750_MASTER_A2NOC_SNOC			9
+#define SM8750_MASTER_CAMNOC_HF				10
+#define SM8750_MASTER_CAMNOC_NRT_ICP_SF			11
+#define SM8750_MASTER_CAMNOC_RT_CDM_SF			12
+#define SM8750_MASTER_CAMNOC_SF				13
+#define SM8750_MASTER_GEM_NOC_CNOC			14
+#define SM8750_MASTER_GEM_NOC_PCIE_SNOC			15
+#define SM8750_MASTER_GFX3D				16
+#define SM8750_MASTER_LPASS_GEM_NOC			17
+#define SM8750_MASTER_LPASS_LPINOC			18
+#define SM8750_MASTER_LPIAON_NOC			19
+#define SM8750_MASTER_LPASS_PROC			20
+#define SM8750_MASTER_MDP				21
+#define SM8750_MASTER_MSS_PROC				22
+#define SM8750_MASTER_MNOC_HF_MEM_NOC			23
+#define SM8750_MASTER_MNOC_SF_MEM_NOC			24
+#define SM8750_MASTER_CDSP_PROC				25
+#define SM8750_MASTER_COMPUTE_NOC			26
+#define SM8750_MASTER_ANOC_PCIE_GEM_NOC			27
+#define SM8750_MASTER_SNOC_SF_MEM_NOC			28
+#define SM8750_MASTER_UBWC_P				29
+#define SM8750_MASTER_CDSP_HCP				30
+#define SM8750_MASTER_VIDEO_CV_PROC			31
+#define SM8750_MASTER_VIDEO_EVA				32
+#define SM8750_MASTER_VIDEO_MVP				33
+#define SM8750_MASTER_VIDEO_V_PROC			34
+#define SM8750_MASTER_CNOC_CFG				35
+#define SM8750_MASTER_CNOC_MNOC_CFG			36
+#define SM8750_MASTER_PCIE_ANOC_CFG			37
+#define SM8750_MASTER_QUP_CORE_0			38
+#define SM8750_MASTER_QUP_CORE_1			39
+#define SM8750_MASTER_QUP_CORE_2			40
+#define SM8750_MASTER_CRYPTO				41
+#define SM8750_MASTER_IPA				42
+#define SM8750_MASTER_QUP_3				43
+#define SM8750_MASTER_SOCCP_AGGR_NOC			44
+#define SM8750_MASTER_SP				45
+#define SM8750_MASTER_GIC				46
+#define SM8750_MASTER_PCIE_0				47
+#define SM8750_MASTER_QDSS_ETR				48
+#define SM8750_MASTER_QDSS_ETR_1			49
+#define SM8750_MASTER_SDCC_2				50
+#define SM8750_MASTER_SDCC_4				51
+#define SM8750_MASTER_UFS_MEM				52
+#define SM8750_MASTER_USB3_0				53
+#define SM8750_SLAVE_UBWC_P				54
+#define SM8750_SLAVE_EBI1				55
+#define SM8750_SLAVE_AHB2PHY_SOUTH			56
+#define SM8750_SLAVE_AHB2PHY_NORTH			57
+#define SM8750_SLAVE_AOSS				58
+#define SM8750_SLAVE_CAMERA_CFG				59
+#define SM8750_SLAVE_CLK_CTL				60
+#define SM8750_SLAVE_CRYPTO_0_CFG			61
+#define SM8750_SLAVE_DISPLAY_CFG			62
+#define SM8750_SLAVE_EVA_CFG				63
+#define SM8750_SLAVE_GFX3D_CFG				64
+#define SM8750_SLAVE_I2C				65
+#define SM8750_SLAVE_I3C_IBI0_CFG			66
+#define SM8750_SLAVE_I3C_IBI1_CFG			67
+#define SM8750_SLAVE_IMEM_CFG				68
+#define SM8750_SLAVE_IPA_CFG				69
+#define SM8750_SLAVE_IPC_ROUTER_CFG			70
+#define SM8750_SLAVE_CNOC_MSS				71
+#define SM8750_SLAVE_PCIE_CFG				72
+#define SM8750_SLAVE_PRNG				73
+#define SM8750_SLAVE_QDSS_CFG				74
+#define SM8750_SLAVE_QSPI_0				75
+#define SM8750_SLAVE_QUP_3				76
+#define SM8750_SLAVE_QUP_1				77
+#define SM8750_SLAVE_QUP_2				78
+#define SM8750_SLAVE_SDCC_2				79
+#define SM8750_SLAVE_SDCC_4				80
+#define SM8750_SLAVE_SOCCP				81
+#define SM8750_SLAVE_SPSS_CFG				82
+#define SM8750_SLAVE_TCSR				83
+#define SM8750_SLAVE_TLMM				84
+#define SM8750_SLAVE_TME_CFG				85
+#define SM8750_SLAVE_UFS_MEM_CFG			86
+#define SM8750_SLAVE_USB3_0				87
+#define SM8750_SLAVE_VENUS_CFG				88
+#define SM8750_SLAVE_VSENSE_CTRL_CFG			89
+#define SM8750_SLAVE_A1NOC_SNOC				90
+#define SM8750_SLAVE_A2NOC_SNOC				91
+#define SM8750_SLAVE_APPSS				92
+#define SM8750_SLAVE_GEM_NOC_CNOC			93
+#define SM8750_SLAVE_SNOC_GEM_NOC_SF			94
+#define SM8750_SLAVE_LLCC				95
+#define SM8750_SLAVE_LPASS_GEM_NOC			96
+#define SM8750_SLAVE_LPIAON_NOC_LPASS_AG_NOC		97
+#define SM8750_SLAVE_LPICX_NOC_LPIAON_NOC		98
+#define SM8750_SLAVE_MNOC_HF_MEM_NOC			99
+#define SM8750_SLAVE_MNOC_SF_MEM_NOC			100
+#define SM8750_SLAVE_CDSP_MEM_NOC			101
+#define SM8750_SLAVE_MEM_NOC_PCIE_SNOC			102
+#define SM8750_SLAVE_ANOC_PCIE_GEM_NOC			103
+#define SM8750_SLAVE_CNOC_CFG				104
+#define SM8750_SLAVE_DDRSS_CFG				105
+#define SM8750_SLAVE_CNOC_MNOC_CFG			106
+#define SM8750_SLAVE_PCIE_ANOC_CFG			107
+#define SM8750_SLAVE_QUP_CORE_0				108
+#define SM8750_SLAVE_QUP_CORE_1				109
+#define SM8750_SLAVE_QUP_CORE_2				110
+#define SM8750_SLAVE_BOOT_IMEM				111
+#define SM8750_SLAVE_IMEM				112
+#define SM8750_SLAVE_BOOT_IMEM_2			113
+#define SM8750_SLAVE_SERVICE_CNOC			114
+#define SM8750_SLAVE_SERVICE_MNOC			115
+#define SM8750_SLAVE_SERVICE_PCIE_ANOC			116
+#define SM8750_SLAVE_PCIE_0				117
+#define SM8750_SLAVE_QDSS_STM				118
+#define SM8750_SLAVE_TCU				119
+
+static struct qcom_icc_node qhm_qspi = {
+	.name = "qhm_qspi",
+	.id = SM8750_MASTER_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup1 = {
+	.name = "qhm_qup1",
+	.id = SM8750_MASTER_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_qup02 = {
+	.name = "qxm_qup02",
+	.id = SM8750_MASTER_QUP_3,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc4 = {
+	.name = "xm_sdc4",
+	.id = SM8750_MASTER_SDCC_4,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_ufs_mem = {
+	.name = "xm_ufs_mem",
+	.id = SM8750_MASTER_UFS_MEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_usb3_0 = {
+	.name = "xm_usb3_0",
+	.id = SM8750_MASTER_USB3_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qdss_bam = {
+	.name = "qhm_qdss_bam",
+	.id = SM8750_MASTER_QDSS_BAM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qhm_qup2 = {
+	.name = "qhm_qup2",
+	.id = SM8750_MASTER_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_crypto = {
+	.name = "qxm_crypto",
+	.id = SM8750_MASTER_CRYPTO,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_ipa = {
+	.name = "qxm_ipa",
+	.id = SM8750_MASTER_IPA,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_soccp = {
+	.name = "qxm_soccp",
+	.id = SM8750_MASTER_SOCCP_AGGR_NOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qxm_sp = {
+	.name = "qxm_sp",
+	.id = SM8750_MASTER_SP,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_0 = {
+	.name = "xm_qdss_etr_0",
+	.id = SM8750_MASTER_QDSS_ETR,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_qdss_etr_1 = {
+	.name = "xm_qdss_etr_1",
+	.id = SM8750_MASTER_QDSS_ETR_1,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node xm_sdc2 = {
+	.name = "xm_sdc2",
+	.id = SM8750_MASTER_SDCC_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qup0_core_master = {
+	.name = "qup0_core_master",
+	.id = SM8750_MASTER_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_QUP_CORE_0 },
+};
+
+static struct qcom_icc_node qup1_core_master = {
+	.name = "qup1_core_master",
+	.id = SM8750_MASTER_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_QUP_CORE_1 },
+};
+
+static struct qcom_icc_node qup2_core_master = {
+	.name = "qup2_core_master",
+	.id = SM8750_MASTER_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_QUP_CORE_2 },
+};
+
+static struct qcom_icc_node qsm_cfg = {
+	.name = "qsm_cfg",
+	.id = SM8750_MASTER_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 33,
+	.links = { SM8750_SLAVE_AHB2PHY_SOUTH, SM8750_SLAVE_AHB2PHY_NORTH,
+			   SM8750_SLAVE_CAMERA_CFG, SM8750_SLAVE_CLK_CTL,
+			   SM8750_SLAVE_CRYPTO_0_CFG, SM8750_SLAVE_DISPLAY_CFG,
+			   SM8750_SLAVE_EVA_CFG, SM8750_SLAVE_GFX3D_CFG,
+			   SM8750_SLAVE_I2C, SM8750_SLAVE_I3C_IBI0_CFG,
+			   SM8750_SLAVE_I3C_IBI1_CFG, SM8750_SLAVE_IMEM_CFG,
+			   SM8750_SLAVE_CNOC_MSS, SM8750_SLAVE_PCIE_CFG,
+			   SM8750_SLAVE_PRNG, SM8750_SLAVE_QDSS_CFG,
+			   SM8750_SLAVE_QSPI_0, SM8750_SLAVE_QUP_3,
+			   SM8750_SLAVE_QUP_1, SM8750_SLAVE_QUP_2,
+			   SM8750_SLAVE_SDCC_2, SM8750_SLAVE_SDCC_4,
+			   SM8750_SLAVE_SPSS_CFG, SM8750_SLAVE_TCSR,
+			   SM8750_SLAVE_TLMM, SM8750_SLAVE_UFS_MEM_CFG,
+			   SM8750_SLAVE_USB3_0, SM8750_SLAVE_VENUS_CFG,
+			   SM8750_SLAVE_VSENSE_CTRL_CFG, SM8750_SLAVE_CNOC_MNOC_CFG,
+			   SM8750_SLAVE_PCIE_ANOC_CFG, SM8750_SLAVE_QDSS_STM,
+			   SM8750_SLAVE_TCU },
+};
+
+static struct qcom_icc_node qnm_gemnoc_cnoc = {
+	.name = "qnm_gemnoc_cnoc",
+	.id = SM8750_MASTER_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 12,
+	.links = { SM8750_SLAVE_AOSS, SM8750_SLAVE_IPA_CFG,
+			   SM8750_SLAVE_IPC_ROUTER_CFG, SM8750_SLAVE_SOCCP,
+			   SM8750_SLAVE_TME_CFG, SM8750_SLAVE_APPSS,
+			   SM8750_SLAVE_CNOC_CFG, SM8750_SLAVE_DDRSS_CFG,
+			   SM8750_SLAVE_BOOT_IMEM, SM8750_SLAVE_IMEM,
+			   SM8750_SLAVE_BOOT_IMEM_2, SM8750_SLAVE_SERVICE_CNOC },
+};
+
+static struct qcom_icc_node qnm_gemnoc_pcie = {
+	.name = "qnm_gemnoc_pcie",
+	.id = SM8750_MASTER_GEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_PCIE_0 },
+};
+
+static struct qcom_icc_node alm_gpu_tcu = {
+	.name = "alm_gpu_tcu",
+	.id = SM8750_MASTER_GPU_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node alm_sys_tcu = {
+	.name = "alm_sys_tcu",
+	.id = SM8750_MASTER_SYS_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node chm_apps = {
+	.name = "chm_apps",
+	.id = SM8750_MASTER_APPSS_PROC,
+	.channels = 4,
+	.buswidth = 32,
+	.num_links = 4,
+	.links = { SM8750_SLAVE_UBWC_P, SM8750_SLAVE_GEM_NOC_CNOC,
+			   SM8750_SLAVE_LLCC, SM8750_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_gpu = {
+	.name = "qnm_gpu",
+	.id = SM8750_MASTER_GFX3D,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpass_gemnoc = {
+	.name = "qnm_lpass_gemnoc",
+	.id = SM8750_MASTER_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC,
+			   SM8750_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mdsp = {
+	.name = "qnm_mdsp",
+	.id = SM8750_MASTER_MSS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC,
+			   SM8750_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_mnoc_hf = {
+	.name = "qnm_mnoc_hf",
+	.id = SM8750_MASTER_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_mnoc_sf = {
+	.name = "qnm_mnoc_sf",
+	.id = SM8750_MASTER_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 2,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_nsp_gemnoc = {
+	.name = "qnm_nsp_gemnoc",
+	.id = SM8750_MASTER_COMPUTE_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 3,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC,
+			   SM8750_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_pcie = {
+	.name = "qnm_pcie",
+	.id = SM8750_MASTER_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 2,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_snoc_sf = {
+	.name = "qnm_snoc_sf",
+	.id = SM8750_MASTER_SNOC_SF_MEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 3,
+	.links = { SM8750_SLAVE_GEM_NOC_CNOC, SM8750_SLAVE_LLCC,
+			   SM8750_SLAVE_MEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qnm_ubwc_p = {
+	.name = "qnm_ubwc_p",
+	.id = SM8750_MASTER_UBWC_P,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node xm_gic = {
+	.name = "xm_gic",
+	.id = SM8750_MASTER_GIC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_LLCC },
+};
+
+static struct qcom_icc_node qnm_lpiaon_noc = {
+	.name = "qnm_lpiaon_noc",
+	.id = SM8750_MASTER_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_lpass_lpinoc = {
+	.name = "qnm_lpass_lpinoc",
+	.id = SM8750_MASTER_LPASS_LPINOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_LPIAON_NOC_LPASS_AG_NOC },
+};
+
+static struct qcom_icc_node qnm_lpinoc_dsp_qns4m = {
+	.name = "qnm_lpinoc_dsp_qns4m",
+	.id = SM8750_MASTER_LPASS_PROC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_LPICX_NOC_LPIAON_NOC },
+};
+
+static struct qcom_icc_node llcc_mc = {
+	.name = "llcc_mc",
+	.id = SM8750_MASTER_LLCC,
+	.channels = 4,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_EBI1 },
+};
+
+static struct qcom_icc_node qnm_camnoc_hf = {
+	.name = "qnm_camnoc_hf",
+	.id = SM8750_MASTER_CAMNOC_HF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_nrt_icp_sf = {
+	.name = "qnm_camnoc_nrt_icp_sf",
+	.id = SM8750_MASTER_CAMNOC_NRT_ICP_SF,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_rt_cdm_sf = {
+	.name = "qnm_camnoc_rt_cdm_sf",
+	.id = SM8750_MASTER_CAMNOC_RT_CDM_SF,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_camnoc_sf = {
+	.name = "qnm_camnoc_sf",
+	.id = SM8750_MASTER_CAMNOC_SF,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_mdp = {
+	.name = "qnm_mdp",
+	.id = SM8750_MASTER_MDP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_vapss_hcp = {
+	.name = "qnm_vapss_hcp",
+	.id = SM8750_MASTER_CDSP_HCP,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_cv_cpu = {
+	.name = "qnm_video_cv_cpu",
+	.id = SM8750_MASTER_VIDEO_CV_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_eva = {
+	.name = "qnm_video_eva",
+	.id = SM8750_MASTER_VIDEO_EVA,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_mvp = {
+	.name = "qnm_video_mvp",
+	.id = SM8750_MASTER_VIDEO_MVP,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qnm_video_v_cpu = {
+	.name = "qnm_video_v_cpu",
+	.id = SM8750_MASTER_VIDEO_V_PROC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_mnoc_cfg = {
+	.name = "qsm_mnoc_cfg",
+	.id = SM8750_MASTER_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_SERVICE_MNOC },
+};
+
+static struct qcom_icc_node qnm_nsp = {
+	.name = "qnm_nsp",
+	.id = SM8750_MASTER_CDSP_PROC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_CDSP_MEM_NOC },
+};
+
+static struct qcom_icc_node qsm_pcie_anoc_cfg = {
+	.name = "qsm_pcie_anoc_cfg",
+	.id = SM8750_MASTER_PCIE_ANOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_SERVICE_PCIE_ANOC },
+};
+
+static struct qcom_icc_node xm_pcie3 = {
+	.name = "xm_pcie3",
+	.id = SM8750_MASTER_PCIE_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node qnm_aggre1_noc = {
+	.name = "qnm_aggre1_noc",
+	.id = SM8750_MASTER_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qnm_aggre2_noc = {
+	.name = "qnm_aggre2_noc",
+	.id = SM8750_MASTER_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_SLAVE_SNOC_GEM_NOC_SF },
+};
+
+static struct qcom_icc_node qns_a1noc_snoc = {
+	.name = "qns_a1noc_snoc",
+	.id = SM8750_SLAVE_A1NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_A1NOC_SNOC },
+};
+
+static struct qcom_icc_node qns_a2noc_snoc = {
+	.name = "qns_a2noc_snoc",
+	.id = SM8750_SLAVE_A2NOC_SNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_A2NOC_SNOC },
+};
+
+static struct qcom_icc_node qup0_core_slave = {
+	.name = "qup0_core_slave",
+	.id = SM8750_SLAVE_QUP_CORE_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup1_core_slave = {
+	.name = "qup1_core_slave",
+	.id = SM8750_SLAVE_QUP_CORE_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qup2_core_slave = {
+	.name = "qup2_core_slave",
+	.id = SM8750_SLAVE_QUP_CORE_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy0 = {
+	.name = "qhs_ahb2phy0",
+	.id = SM8750_SLAVE_AHB2PHY_SOUTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ahb2phy1 = {
+	.name = "qhs_ahb2phy1",
+	.id = SM8750_SLAVE_AHB2PHY_NORTH,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_camera_cfg = {
+	.name = "qhs_camera_cfg",
+	.id = SM8750_SLAVE_CAMERA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_clk_ctl = {
+	.name = "qhs_clk_ctl",
+	.id = SM8750_SLAVE_CLK_CTL,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_crypto0_cfg = {
+	.name = "qhs_crypto0_cfg",
+	.id = SM8750_SLAVE_CRYPTO_0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_display_cfg = {
+	.name = "qhs_display_cfg",
+	.id = SM8750_SLAVE_DISPLAY_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_eva_cfg = {
+	.name = "qhs_eva_cfg",
+	.id = SM8750_SLAVE_EVA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_gpuss_cfg = {
+	.name = "qhs_gpuss_cfg",
+	.id = SM8750_SLAVE_GFX3D_CFG,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i2c = {
+	.name = "qhs_i2c",
+	.id = SM8750_SLAVE_I2C,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i3c_ibi0_cfg = {
+	.name = "qhs_i3c_ibi0_cfg",
+	.id = SM8750_SLAVE_I3C_IBI0_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_i3c_ibi1_cfg = {
+	.name = "qhs_i3c_ibi1_cfg",
+	.id = SM8750_SLAVE_I3C_IBI1_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_imem_cfg = {
+	.name = "qhs_imem_cfg",
+	.id = SM8750_SLAVE_IMEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_mss_cfg = {
+	.name = "qhs_mss_cfg",
+	.id = SM8750_SLAVE_CNOC_MSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_pcie_cfg = {
+	.name = "qhs_pcie_cfg",
+	.id = SM8750_SLAVE_PCIE_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_prng = {
+	.name = "qhs_prng",
+	.id = SM8750_SLAVE_PRNG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qdss_cfg = {
+	.name = "qhs_qdss_cfg",
+	.id = SM8750_SLAVE_QDSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qspi = {
+	.name = "qhs_qspi",
+	.id = SM8750_SLAVE_QSPI_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup02 = {
+	.name = "qhs_qup02",
+	.id = SM8750_SLAVE_QUP_3,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup1 = {
+	.name = "qhs_qup1",
+	.id = SM8750_SLAVE_QUP_1,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_qup2 = {
+	.name = "qhs_qup2",
+	.id = SM8750_SLAVE_QUP_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc2 = {
+	.name = "qhs_sdc2",
+	.id = SM8750_SLAVE_SDCC_2,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_sdc4 = {
+	.name = "qhs_sdc4",
+	.id = SM8750_SLAVE_SDCC_4,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_spss_cfg = {
+	.name = "qhs_spss_cfg",
+	.id = SM8750_SLAVE_SPSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tcsr = {
+	.name = "qhs_tcsr",
+	.id = SM8750_SLAVE_TCSR,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tlmm = {
+	.name = "qhs_tlmm",
+	.id = SM8750_SLAVE_TLMM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ufs_mem_cfg = {
+	.name = "qhs_ufs_mem_cfg",
+	.id = SM8750_SLAVE_UFS_MEM_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_usb3_0 = {
+	.name = "qhs_usb3_0",
+	.id = SM8750_SLAVE_USB3_0,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_venus_cfg = {
+	.name = "qhs_venus_cfg",
+	.id = SM8750_SLAVE_VENUS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_vsense_ctrl_cfg = {
+	.name = "qhs_vsense_ctrl_cfg",
+	.id = SM8750_SLAVE_VSENSE_CTRL_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_mnoc_cfg = {
+	.name = "qss_mnoc_cfg",
+	.id = SM8750_SLAVE_CNOC_MNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_MASTER_CNOC_MNOC_CFG },
+};
+
+static struct qcom_icc_node qss_pcie_anoc_cfg = {
+	.name = "qss_pcie_anoc_cfg",
+	.id = SM8750_SLAVE_PCIE_ANOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_MASTER_PCIE_ANOC_CFG },
+};
+
+static struct qcom_icc_node xs_qdss_stm = {
+	.name = "xs_qdss_stm",
+	.id = SM8750_SLAVE_QDSS_STM,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_sys_tcu_cfg = {
+	.name = "xs_sys_tcu_cfg",
+	.id = SM8750_SLAVE_TCU,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_aoss = {
+	.name = "qhs_aoss",
+	.id = SM8750_SLAVE_AOSS,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipa = {
+	.name = "qhs_ipa",
+	.id = SM8750_SLAVE_IPA_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_ipc_router = {
+	.name = "qhs_ipc_router",
+	.id = SM8750_SLAVE_IPC_ROUTER_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_soccp = {
+	.name = "qhs_soccp",
+	.id = SM8750_SLAVE_SOCCP,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qhs_tme_cfg = {
+	.name = "qhs_tme_cfg",
+	.id = SM8750_SLAVE_TME_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_apss = {
+	.name = "qns_apss",
+	.id = SM8750_SLAVE_APPSS,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qss_cfg = {
+	.name = "qss_cfg",
+	.id = SM8750_SLAVE_CNOC_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 1,
+	.links = { SM8750_MASTER_CNOC_CFG },
+};
+
+static struct qcom_icc_node qss_ddrss_cfg = {
+	.name = "qss_ddrss_cfg",
+	.id = SM8750_SLAVE_DDRSS_CFG,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_boot_imem = {
+	.name = "qxs_boot_imem",
+	.id = SM8750_SLAVE_BOOT_IMEM,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_imem = {
+	.name = "qxs_imem",
+	.id = SM8750_SLAVE_IMEM,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qxs_modem_boot_imem = {
+	.name = "qxs_modem_boot_imem",
+	.id = SM8750_SLAVE_BOOT_IMEM_2,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node srvc_cnoc_main = {
+	.name = "srvc_cnoc_main",
+	.id = SM8750_SLAVE_SERVICE_CNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node xs_pcie = {
+	.name = "xs_pcie",
+	.id = SM8750_SLAVE_PCIE_0,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node chs_ubwc_p = {
+	.name = "chs_ubwc_p",
+	.id = SM8750_SLAVE_UBWC_P,
+	.channels = 1,
+	.buswidth = 32,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gem_noc_cnoc = {
+	.name = "qns_gem_noc_cnoc",
+	.id = SM8750_SLAVE_GEM_NOC_CNOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_GEM_NOC_CNOC },
+};
+
+static struct qcom_icc_node qns_llcc = {
+	.name = "qns_llcc",
+	.id = SM8750_SLAVE_LLCC,
+	.channels = 4,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_LLCC },
+};
+
+static struct qcom_icc_node qns_pcie = {
+	.name = "qns_pcie",
+	.id = SM8750_SLAVE_MEM_NOC_PCIE_SNOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_MASTER_GEM_NOC_PCIE_SNOC },
+};
+
+static struct qcom_icc_node qns_lpass_ag_noc_gemnoc = {
+	.name = "qns_lpass_ag_noc_gemnoc",
+	.id = SM8750_SLAVE_LPASS_GEM_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_LPASS_GEM_NOC },
+};
+
+static struct qcom_icc_node qns_lpass_aggnoc = {
+	.name = "qns_lpass_aggnoc",
+	.id = SM8750_SLAVE_LPIAON_NOC_LPASS_AG_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_LPIAON_NOC },
+};
+
+static struct qcom_icc_node qns_lpi_aon_noc = {
+	.name = "qns_lpi_aon_noc",
+	.id = SM8750_SLAVE_LPICX_NOC_LPIAON_NOC,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_LPASS_LPINOC },
+};
+
+static struct qcom_icc_node ebi = {
+	.name = "ebi",
+	.id = SM8750_SLAVE_EBI1,
+	.channels = 4,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_mem_noc_hf = {
+	.name = "qns_mem_noc_hf",
+	.id = SM8750_SLAVE_MNOC_HF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_MASTER_MNOC_HF_MEM_NOC },
+};
+
+static struct qcom_icc_node qns_mem_noc_sf = {
+	.name = "qns_mem_noc_sf",
+	.id = SM8750_SLAVE_MNOC_SF_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_MASTER_MNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_node srvc_mnoc = {
+	.name = "srvc_mnoc",
+	.id = SM8750_SLAVE_SERVICE_MNOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_nsp_gemnoc = {
+	.name = "qns_nsp_gemnoc",
+	.id = SM8750_SLAVE_CDSP_MEM_NOC,
+	.channels = 2,
+	.buswidth = 32,
+	.num_links = 1,
+	.links = { SM8750_MASTER_COMPUTE_NOC },
+};
+
+static struct qcom_icc_node qns_pcie_mem_noc = {
+	.name = "qns_pcie_mem_noc",
+	.id = SM8750_SLAVE_ANOC_PCIE_GEM_NOC,
+	.channels = 1,
+	.buswidth = 8,
+	.num_links = 1,
+	.links = { SM8750_MASTER_ANOC_PCIE_GEM_NOC },
+};
+
+static struct qcom_icc_node srvc_pcie_aggre_noc = {
+	.name = "srvc_pcie_aggre_noc",
+	.id = SM8750_SLAVE_SERVICE_PCIE_ANOC,
+	.channels = 1,
+	.buswidth = 4,
+	.num_links = 0,
+};
+
+static struct qcom_icc_node qns_gemnoc_sf = {
+	.name = "qns_gemnoc_sf",
+	.id = SM8750_SLAVE_SNOC_GEM_NOC_SF,
+	.channels = 1,
+	.buswidth = 16,
+	.num_links = 1,
+	.links = { SM8750_MASTER_SNOC_SF_MEM_NOC },
+};
+
+static struct qcom_icc_bcm bcm_acv = {
+	.name = "ACV",
+	.enable_mask = BIT(0),
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_ce0 = {
+	.name = "CE0",
+	.num_nodes = 1,
+	.nodes = { &qxm_crypto },
+};
+
+static struct qcom_icc_bcm bcm_cn0 = {
+	.name = "CN0",
+	.enable_mask = BIT(0),
+	.keepalive = true,
+	.num_nodes = 44,
+	.nodes = { &qsm_cfg, &qhs_ahb2phy0,
+		   &qhs_ahb2phy1, &qhs_camera_cfg,
+		   &qhs_clk_ctl, &qhs_crypto0_cfg,
+		   &qhs_eva_cfg, &qhs_gpuss_cfg,
+		   &qhs_i3c_ibi0_cfg, &qhs_i3c_ibi1_cfg,
+		   &qhs_imem_cfg, &qhs_mss_cfg,
+		   &qhs_pcie_cfg, &qhs_prng,
+		   &qhs_qdss_cfg, &qhs_qspi,
+		   &qhs_sdc2, &qhs_sdc4,
+		   &qhs_spss_cfg, &qhs_tcsr,
+		   &qhs_tlmm, &qhs_ufs_mem_cfg,
+		   &qhs_usb3_0, &qhs_venus_cfg,
+		   &qhs_vsense_ctrl_cfg, &qss_mnoc_cfg,
+		   &qss_pcie_anoc_cfg, &xs_qdss_stm,
+		   &xs_sys_tcu_cfg, &qnm_gemnoc_cnoc,
+		   &qnm_gemnoc_pcie, &qhs_aoss,
+		   &qhs_ipa, &qhs_ipc_router,
+		   &qhs_soccp, &qhs_tme_cfg,
+		   &qns_apss, &qss_cfg,
+		   &qss_ddrss_cfg, &qxs_boot_imem,
+		   &qxs_imem, &qxs_modem_boot_imem,
+		   &srvc_cnoc_main, &xs_pcie },
+};
+
+static struct qcom_icc_bcm bcm_cn1 = {
+	.name = "CN1",
+	.num_nodes = 5,
+	.nodes = { &qhs_display_cfg, &qhs_i2c,
+		   &qhs_qup02, &qhs_qup1,
+		   &qhs_qup2 },
+};
+
+static struct qcom_icc_bcm bcm_co0 = {
+	.name = "CO0",
+	.enable_mask = BIT(0),
+	.num_nodes = 2,
+	.nodes = { &qnm_nsp, &qns_nsp_gemnoc },
+};
+
+static struct qcom_icc_bcm bcm_lp0 = {
+	.name = "LP0",
+	.num_nodes = 2,
+	.nodes = { &qnm_lpass_lpinoc, &qns_lpass_aggnoc },
+};
+
+static struct qcom_icc_bcm bcm_mc0 = {
+	.name = "MC0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &ebi },
+};
+
+static struct qcom_icc_bcm bcm_mm0 = {
+	.name = "MM0",
+	.num_nodes = 1,
+	.nodes = { &qns_mem_noc_hf },
+};
+
+static struct qcom_icc_bcm bcm_mm1 = {
+	.name = "MM1",
+	.enable_mask = BIT(0),
+	.num_nodes = 9,
+	.nodes = { &qnm_camnoc_hf, &qnm_camnoc_nrt_icp_sf,
+		   &qnm_camnoc_rt_cdm_sf, &qnm_camnoc_sf,
+		   &qnm_vapss_hcp, &qnm_video_cv_cpu,
+		   &qnm_video_mvp, &qnm_video_v_cpu,
+		   &qns_mem_noc_sf },
+};
+
+static struct qcom_icc_bcm bcm_qup0 = {
+	.name = "QUP0",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup0_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup1 = {
+	.name = "QUP1",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup1_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_qup2 = {
+	.name = "QUP2",
+	.keepalive = true,
+	.vote_scale = 1,
+	.num_nodes = 1,
+	.nodes = { &qup2_core_slave },
+};
+
+static struct qcom_icc_bcm bcm_sh0 = {
+	.name = "SH0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_llcc },
+};
+
+static struct qcom_icc_bcm bcm_sh1 = {
+	.name = "SH1",
+	.enable_mask = BIT(0),
+	.num_nodes = 14,
+	.nodes = { &alm_gpu_tcu, &alm_sys_tcu,
+		   &chm_apps, &qnm_gpu,
+		   &qnm_mdsp, &qnm_mnoc_hf,
+		   &qnm_mnoc_sf, &qnm_nsp_gemnoc,
+		   &qnm_pcie, &qnm_snoc_sf,
+		   &xm_gic, &chs_ubwc_p,
+		   &qns_gem_noc_cnoc, &qns_pcie },
+};
+
+static struct qcom_icc_bcm bcm_sn0 = {
+	.name = "SN0",
+	.keepalive = true,
+	.num_nodes = 1,
+	.nodes = { &qns_gemnoc_sf },
+};
+
+static struct qcom_icc_bcm bcm_sn2 = {
+	.name = "SN2",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre1_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn3 = {
+	.name = "SN3",
+	.num_nodes = 1,
+	.nodes = { &qnm_aggre2_noc },
+};
+
+static struct qcom_icc_bcm bcm_sn4 = {
+	.name = "SN4",
+	.num_nodes = 1,
+	.nodes = { &qns_pcie_mem_noc },
+};
+
+static struct qcom_icc_bcm bcm_ubw0 = {
+	.name = "UBW0",
+	.num_nodes = 1,
+	.nodes = { &qnm_ubwc_p },
+};
+
+static struct qcom_icc_node * const aggre1_noc_nodes[] = {
+	[MASTER_QSPI_0] = &qhm_qspi,
+	[MASTER_QUP_1] = &qhm_qup1,
+	[MASTER_QUP_3] = &qxm_qup02,
+	[MASTER_SDCC_4] = &xm_sdc4,
+	[MASTER_UFS_MEM] = &xm_ufs_mem,
+	[MASTER_USB3_0] = &xm_usb3_0,
+	[SLAVE_A1NOC_SNOC] = &qns_a1noc_snoc,
+};
+
+static const struct qcom_icc_desc sm8750_aggre1_noc = {
+	.nodes = aggre1_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre1_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const aggre2_noc_bcms[] = {
+	&bcm_ce0,
+};
+
+static struct qcom_icc_node * const aggre2_noc_nodes[] = {
+	[MASTER_QDSS_BAM] = &qhm_qdss_bam,
+	[MASTER_QUP_2] = &qhm_qup2,
+	[MASTER_CRYPTO] = &qxm_crypto,
+	[MASTER_IPA] = &qxm_ipa,
+	[MASTER_SOCCP_AGGR_NOC] = &qxm_soccp,
+	[MASTER_SP] = &qxm_sp,
+	[MASTER_QDSS_ETR] = &xm_qdss_etr_0,
+	[MASTER_QDSS_ETR_1] = &xm_qdss_etr_1,
+	[MASTER_SDCC_2] = &xm_sdc2,
+	[SLAVE_A2NOC_SNOC] = &qns_a2noc_snoc,
+};
+
+static const struct qcom_icc_desc sm8750_aggre2_noc = {
+	.nodes = aggre2_noc_nodes,
+	.num_nodes = ARRAY_SIZE(aggre2_noc_nodes),
+	.bcms = aggre2_noc_bcms,
+	.num_bcms = ARRAY_SIZE(aggre2_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const clk_virt_bcms[] = {
+	&bcm_qup0,
+	&bcm_qup1,
+	&bcm_qup2,
+};
+
+static struct qcom_icc_node * const clk_virt_nodes[] = {
+	[MASTER_QUP_CORE_0] = &qup0_core_master,
+	[MASTER_QUP_CORE_1] = &qup1_core_master,
+	[MASTER_QUP_CORE_2] = &qup2_core_master,
+	[SLAVE_QUP_CORE_0] = &qup0_core_slave,
+	[SLAVE_QUP_CORE_1] = &qup1_core_slave,
+	[SLAVE_QUP_CORE_2] = &qup2_core_slave,
+};
+
+static const struct qcom_icc_desc sm8750_clk_virt = {
+	.nodes = clk_virt_nodes,
+	.num_nodes = ARRAY_SIZE(clk_virt_nodes),
+	.bcms = clk_virt_bcms,
+	.num_bcms = ARRAY_SIZE(clk_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const config_noc_bcms[] = {
+	&bcm_cn0,
+	&bcm_cn1,
+};
+
+static struct qcom_icc_node * const config_noc_nodes[] = {
+	[MASTER_CNOC_CFG] = &qsm_cfg,
+	[SLAVE_AHB2PHY_SOUTH] = &qhs_ahb2phy0,
+	[SLAVE_AHB2PHY_NORTH] = &qhs_ahb2phy1,
+	[SLAVE_CAMERA_CFG] = &qhs_camera_cfg,
+	[SLAVE_CLK_CTL] = &qhs_clk_ctl,
+	[SLAVE_CRYPTO_0_CFG] = &qhs_crypto0_cfg,
+	[SLAVE_DISPLAY_CFG] = &qhs_display_cfg,
+	[SLAVE_EVA_CFG] = &qhs_eva_cfg,
+	[SLAVE_GFX3D_CFG] = &qhs_gpuss_cfg,
+	[SLAVE_I2C] = &qhs_i2c,
+	[SLAVE_I3C_IBI0_CFG] = &qhs_i3c_ibi0_cfg,
+	[SLAVE_I3C_IBI1_CFG] = &qhs_i3c_ibi1_cfg,
+	[SLAVE_IMEM_CFG] = &qhs_imem_cfg,
+	[SLAVE_CNOC_MSS] = &qhs_mss_cfg,
+	[SLAVE_PCIE_CFG] = &qhs_pcie_cfg,
+	[SLAVE_PRNG] = &qhs_prng,
+	[SLAVE_QDSS_CFG] = &qhs_qdss_cfg,
+	[SLAVE_QSPI_0] = &qhs_qspi,
+	[SLAVE_QUP_3] = &qhs_qup02,
+	[SLAVE_QUP_1] = &qhs_qup1,
+	[SLAVE_QUP_2] = &qhs_qup2,
+	[SLAVE_SDCC_2] = &qhs_sdc2,
+	[SLAVE_SDCC_4] = &qhs_sdc4,
+	[SLAVE_SPSS_CFG] = &qhs_spss_cfg,
+	[SLAVE_TCSR] = &qhs_tcsr,
+	[SLAVE_TLMM] = &qhs_tlmm,
+	[SLAVE_UFS_MEM_CFG] = &qhs_ufs_mem_cfg,
+	[SLAVE_USB3_0] = &qhs_usb3_0,
+	[SLAVE_VENUS_CFG] = &qhs_venus_cfg,
+	[SLAVE_VSENSE_CTRL_CFG] = &qhs_vsense_ctrl_cfg,
+	[SLAVE_CNOC_MNOC_CFG] = &qss_mnoc_cfg,
+	[SLAVE_PCIE_ANOC_CFG] = &qss_pcie_anoc_cfg,
+	[SLAVE_QDSS_STM] = &xs_qdss_stm,
+	[SLAVE_TCU] = &xs_sys_tcu_cfg,
+};
+
+static const struct qcom_icc_desc sm8750_config_noc = {
+	.nodes = config_noc_nodes,
+	.num_nodes = ARRAY_SIZE(config_noc_nodes),
+	.bcms = config_noc_bcms,
+	.num_bcms = ARRAY_SIZE(config_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const cnoc_main_bcms[] = {
+	&bcm_cn0,
+};
+
+static struct qcom_icc_node * const cnoc_main_nodes[] = {
+	[MASTER_GEM_NOC_CNOC] = &qnm_gemnoc_cnoc,
+	[MASTER_GEM_NOC_PCIE_SNOC] = &qnm_gemnoc_pcie,
+	[SLAVE_AOSS] = &qhs_aoss,
+	[SLAVE_IPA_CFG] = &qhs_ipa,
+	[SLAVE_IPC_ROUTER_CFG] = &qhs_ipc_router,
+	[SLAVE_SOCCP] = &qhs_soccp,
+	[SLAVE_TME_CFG] = &qhs_tme_cfg,
+	[SLAVE_APPSS] = &qns_apss,
+	[SLAVE_CNOC_CFG] = &qss_cfg,
+	[SLAVE_DDRSS_CFG] = &qss_ddrss_cfg,
+	[SLAVE_BOOT_IMEM] = &qxs_boot_imem,
+	[SLAVE_IMEM] = &qxs_imem,
+	[SLAVE_BOOT_IMEM_2] = &qxs_modem_boot_imem,
+	[SLAVE_SERVICE_CNOC] = &srvc_cnoc_main,
+	[SLAVE_PCIE_0] = &xs_pcie,
+};
+
+static const struct qcom_icc_desc sm8750_cnoc_main = {
+	.nodes = cnoc_main_nodes,
+	.num_nodes = ARRAY_SIZE(cnoc_main_nodes),
+	.bcms = cnoc_main_bcms,
+	.num_bcms = ARRAY_SIZE(cnoc_main_bcms),
+};
+
+static struct qcom_icc_bcm * const gem_noc_bcms[] = {
+	&bcm_sh0,
+	&bcm_sh1,
+	&bcm_ubw0,
+};
+
+static struct qcom_icc_node * const gem_noc_nodes[] = {
+	[MASTER_GPU_TCU] = &alm_gpu_tcu,
+	[MASTER_SYS_TCU] = &alm_sys_tcu,
+	[MASTER_APPSS_PROC] = &chm_apps,
+	[MASTER_GFX3D] = &qnm_gpu,
+	[MASTER_LPASS_GEM_NOC] = &qnm_lpass_gemnoc,
+	[MASTER_MSS_PROC] = &qnm_mdsp,
+	[MASTER_MNOC_HF_MEM_NOC] = &qnm_mnoc_hf,
+	[MASTER_MNOC_SF_MEM_NOC] = &qnm_mnoc_sf,
+	[MASTER_COMPUTE_NOC] = &qnm_nsp_gemnoc,
+	[MASTER_ANOC_PCIE_GEM_NOC] = &qnm_pcie,
+	[MASTER_SNOC_SF_MEM_NOC] = &qnm_snoc_sf,
+	[MASTER_UBWC_P] = &qnm_ubwc_p,
+	[MASTER_GIC] = &xm_gic,
+	[SLAVE_UBWC_P] = &chs_ubwc_p,
+	[SLAVE_GEM_NOC_CNOC] = &qns_gem_noc_cnoc,
+	[SLAVE_LLCC] = &qns_llcc,
+	[SLAVE_MEM_NOC_PCIE_SNOC] = &qns_pcie,
+};
+
+static const struct qcom_icc_desc sm8750_gem_noc = {
+	.nodes = gem_noc_nodes,
+	.num_nodes = ARRAY_SIZE(gem_noc_nodes),
+	.bcms = gem_noc_bcms,
+	.num_bcms = ARRAY_SIZE(gem_noc_bcms),
+};
+
+static struct qcom_icc_node * const lpass_ag_noc_nodes[] = {
+	[MASTER_LPIAON_NOC] = &qnm_lpiaon_noc,
+	[SLAVE_LPASS_GEM_NOC] = &qns_lpass_ag_noc_gemnoc,
+};
+
+static const struct qcom_icc_desc sm8750_lpass_ag_noc = {
+	.nodes = lpass_ag_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_ag_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const lpass_lpiaon_noc_bcms[] = {
+	&bcm_lp0,
+};
+
+static struct qcom_icc_node * const lpass_lpiaon_noc_nodes[] = {
+	[MASTER_LPASS_LPINOC] = &qnm_lpass_lpinoc,
+	[SLAVE_LPIAON_NOC_LPASS_AG_NOC] = &qns_lpass_aggnoc,
+};
+
+static const struct qcom_icc_desc sm8750_lpass_lpiaon_noc = {
+	.nodes = lpass_lpiaon_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpiaon_noc_nodes),
+	.bcms = lpass_lpiaon_noc_bcms,
+	.num_bcms = ARRAY_SIZE(lpass_lpiaon_noc_bcms),
+};
+
+static struct qcom_icc_node * const lpass_lpicx_noc_nodes[] = {
+	[MASTER_LPASS_PROC] = &qnm_lpinoc_dsp_qns4m,
+	[SLAVE_LPICX_NOC_LPIAON_NOC] = &qns_lpi_aon_noc,
+};
+
+static const struct qcom_icc_desc sm8750_lpass_lpicx_noc = {
+	.nodes = lpass_lpicx_noc_nodes,
+	.num_nodes = ARRAY_SIZE(lpass_lpicx_noc_nodes),
+};
+
+static struct qcom_icc_bcm * const mc_virt_bcms[] = {
+	&bcm_acv,
+	&bcm_mc0,
+};
+
+static struct qcom_icc_node * const mc_virt_nodes[] = {
+	[MASTER_LLCC] = &llcc_mc,
+	[SLAVE_EBI1] = &ebi,
+};
+
+static const struct qcom_icc_desc sm8750_mc_virt = {
+	.nodes = mc_virt_nodes,
+	.num_nodes = ARRAY_SIZE(mc_virt_nodes),
+	.bcms = mc_virt_bcms,
+	.num_bcms = ARRAY_SIZE(mc_virt_bcms),
+};
+
+static struct qcom_icc_bcm * const mmss_noc_bcms[] = {
+	&bcm_mm0,
+	&bcm_mm1,
+};
+
+static struct qcom_icc_node * const mmss_noc_nodes[] = {
+	[MASTER_CAMNOC_HF] = &qnm_camnoc_hf,
+	[MASTER_CAMNOC_NRT_ICP_SF] = &qnm_camnoc_nrt_icp_sf,
+	[MASTER_CAMNOC_RT_CDM_SF] = &qnm_camnoc_rt_cdm_sf,
+	[MASTER_CAMNOC_SF] = &qnm_camnoc_sf,
+	[MASTER_MDP] = &qnm_mdp,
+	[MASTER_CDSP_HCP] = &qnm_vapss_hcp,
+	[MASTER_VIDEO_CV_PROC] = &qnm_video_cv_cpu,
+	[MASTER_VIDEO_EVA] = &qnm_video_eva,
+	[MASTER_VIDEO_MVP] = &qnm_video_mvp,
+	[MASTER_VIDEO_V_PROC] = &qnm_video_v_cpu,
+	[MASTER_CNOC_MNOC_CFG] = &qsm_mnoc_cfg,
+	[SLAVE_MNOC_HF_MEM_NOC] = &qns_mem_noc_hf,
+	[SLAVE_MNOC_SF_MEM_NOC] = &qns_mem_noc_sf,
+	[SLAVE_SERVICE_MNOC] = &srvc_mnoc,
+};
+
+static const struct qcom_icc_desc sm8750_mmss_noc = {
+	.nodes = mmss_noc_nodes,
+	.num_nodes = ARRAY_SIZE(mmss_noc_nodes),
+	.bcms = mmss_noc_bcms,
+	.num_bcms = ARRAY_SIZE(mmss_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const nsp_noc_bcms[] = {
+	&bcm_co0,
+};
+
+static struct qcom_icc_node * const nsp_noc_nodes[] = {
+	[MASTER_CDSP_PROC] = &qnm_nsp,
+	[SLAVE_CDSP_MEM_NOC] = &qns_nsp_gemnoc,
+};
+
+static const struct qcom_icc_desc sm8750_nsp_noc = {
+	.nodes = nsp_noc_nodes,
+	.num_nodes = ARRAY_SIZE(nsp_noc_nodes),
+	.bcms = nsp_noc_bcms,
+	.num_bcms = ARRAY_SIZE(nsp_noc_bcms),
+};
+
+static struct qcom_icc_bcm * const pcie_anoc_bcms[] = {
+	&bcm_sn4,
+};
+
+static struct qcom_icc_node * const pcie_anoc_nodes[] = {
+	[MASTER_PCIE_ANOC_CFG] = &qsm_pcie_anoc_cfg,
+	[MASTER_PCIE_0] = &xm_pcie3,
+	[SLAVE_ANOC_PCIE_GEM_NOC] = &qns_pcie_mem_noc,
+	[SLAVE_SERVICE_PCIE_ANOC] = &srvc_pcie_aggre_noc,
+};
+
+static const struct qcom_icc_desc sm8750_pcie_anoc = {
+	.nodes = pcie_anoc_nodes,
+	.num_nodes = ARRAY_SIZE(pcie_anoc_nodes),
+	.bcms = pcie_anoc_bcms,
+	.num_bcms = ARRAY_SIZE(pcie_anoc_bcms),
+};
+
+static struct qcom_icc_bcm * const system_noc_bcms[] = {
+	&bcm_sn0,
+	&bcm_sn2,
+	&bcm_sn3,
+};
+
+static struct qcom_icc_node * const system_noc_nodes[] = {
+	[MASTER_A1NOC_SNOC] = &qnm_aggre1_noc,
+	[MASTER_A2NOC_SNOC] = &qnm_aggre2_noc,
+	[SLAVE_SNOC_GEM_NOC_SF] = &qns_gemnoc_sf,
+};
+
+static const struct qcom_icc_desc sm8750_system_noc = {
+	.nodes = system_noc_nodes,
+	.num_nodes = ARRAY_SIZE(system_noc_nodes),
+	.bcms = system_noc_bcms,
+	.num_bcms = ARRAY_SIZE(system_noc_bcms),
+};
+
+static const struct of_device_id qnoc_of_match[] = {
+	{ .compatible = "qcom,sm8750-aggre1-noc", .data = &sm8750_aggre1_noc},
+	{ .compatible = "qcom,sm8750-aggre2-noc", .data = &sm8750_aggre2_noc},
+	{ .compatible = "qcom,sm8750-clk-virt", .data = &sm8750_clk_virt},
+	{ .compatible = "qcom,sm8750-config-noc", .data = &sm8750_config_noc},
+	{ .compatible = "qcom,sm8750-cnoc-main", .data = &sm8750_cnoc_main},
+	{ .compatible = "qcom,sm8750-gem-noc", .data = &sm8750_gem_noc},
+	{ .compatible = "qcom,sm8750-lpass-ag-noc", .data = &sm8750_lpass_ag_noc},
+	{ .compatible = "qcom,sm8750-lpass-lpiaon-noc", .data = &sm8750_lpass_lpiaon_noc},
+	{ .compatible = "qcom,sm8750-lpass-lpicx-noc", .data = &sm8750_lpass_lpicx_noc},
+	{ .compatible = "qcom,sm8750-mc-virt", .data = &sm8750_mc_virt},
+	{ .compatible = "qcom,sm8750-mmss-noc", .data = &sm8750_mmss_noc},
+	{ .compatible = "qcom,sm8750-nsp-noc", .data = &sm8750_nsp_noc},
+	{ .compatible = "qcom,sm8750-pcie-anoc", .data = &sm8750_pcie_anoc},
+	{ .compatible = "qcom,sm8750-system-noc", .data = &sm8750_system_noc},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qnoc_of_match);
+
+static struct platform_driver qnoc_driver = {
+	.probe = qcom_icc_rpmh_probe,
+	.remove = qcom_icc_rpmh_remove,
+	.driver = {
+		.name = "qnoc-sm8750",
+		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
+	},
+};
+
+static int __init qnoc_driver_init(void)
+{
+	return platform_driver_register(&qnoc_driver);
+}
+core_initcall(qnoc_driver_init);
+
+static void __exit qnoc_driver_exit(void)
+{
+	platform_driver_unregister(&qnoc_driver);
+}
+module_exit(qnoc_driver_exit);
+
+MODULE_DESCRIPTION("SM8750 NoC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index be063bfb50c4..c11b9965c4ad 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -169,6 +169,7 @@ config IXP4XX_IRQ
 
 config LAN966X_OIC
 	tristate "Microchip LAN966x OIC Support"
+	depends on MCHP_LAN966X_PCI || COMPILE_TEST
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 	help
diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c
index da5250f0155c..2b1684c60e3c 100644
--- a/drivers/irqchip/irq-apple-aic.c
+++ b/drivers/irqchip/irq-apple-aic.c
@@ -577,7 +577,8 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs)
 						  AIC_FIQ_HWIRQ(AIC_TMR_EL02_VIRT));
 	}
 
-	if (read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & PMCR0_IACT) {
+	if ((read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & (PMCR0_IMODE | PMCR0_IACT)) ==
+			(FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_FIQ) | PMCR0_IACT)) {
 		int irq;
 		if (cpumask_test_cpu(smp_processor_id(),
 				     &aic_irqc->fiq_aff[AIC_CPU_PMU_P]->aff))
diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c
index b337f6c05f18..4eebed39880a 100644
--- a/drivers/irqchip/irq-mvebu-icu.c
+++ b/drivers/irqchip/irq-mvebu-icu.c
@@ -68,7 +68,8 @@ static int mvebu_icu_translate(struct irq_domain *d, struct irq_fwspec *fwspec,
 			       unsigned long *hwirq, unsigned int *type)
 {
 	unsigned int param_count = static_branch_unlikely(&legacy_bindings) ? 3 : 2;
-	struct mvebu_icu_msi_data *msi_data = d->host_data;
+	struct msi_domain_info *info = d->host_data;
+	struct mvebu_icu_msi_data *msi_data = info->chip_data;
 	struct mvebu_icu *icu = msi_data->icu;
 
 	/* Check the count of the parameters in dt */
diff --git a/drivers/irqchip/irq-partition-percpu.c b/drivers/irqchip/irq-partition-percpu.c
index 8e76d2913e6b..4441ffe149ea 100644
--- a/drivers/irqchip/irq-partition-percpu.c
+++ b/drivers/irqchip/irq-partition-percpu.c
@@ -98,7 +98,7 @@ static void partition_irq_print_chip(struct irq_data *d, struct seq_file *p)
 	struct irq_chip *chip = irq_desc_get_chip(part->chained_desc);
 	struct irq_data *data = irq_desc_get_irq_data(part->chained_desc);
 
-	seq_printf(p, " %5s-%lu", chip->name, data->hwirq);
+	seq_printf(p, "%5s-%lu", chip->name, data->hwirq);
 }
 
 static struct irq_chip partition_irq_chip = {
diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c
index c5c2e6929a2f..275df5005705 100644
--- a/drivers/irqchip/irq-riscv-imsic-early.c
+++ b/drivers/irqchip/irq-riscv-imsic-early.c
@@ -27,7 +27,7 @@ static void imsic_ipi_send(unsigned int cpu)
 {
 	struct imsic_local_config *local = per_cpu_ptr(imsic->global.local, cpu);
 
-	writel_relaxed(IMSIC_IPI_ID, local->msi_va);
+	writel(IMSIC_IPI_ID, local->msi_va);
 }
 
 static void imsic_ipi_starting_cpu(void)
diff --git a/drivers/irqchip/irq-thead-c900-aclint-sswi.c b/drivers/irqchip/irq-thead-c900-aclint-sswi.c
index b0e366ade427..8ff6e7a1363b 100644
--- a/drivers/irqchip/irq-thead-c900-aclint-sswi.c
+++ b/drivers/irqchip/irq-thead-c900-aclint-sswi.c
@@ -31,7 +31,7 @@ static DEFINE_PER_CPU(void __iomem *, sswi_cpu_regs);
 
 static void thead_aclint_sswi_ipi_send(unsigned int cpu)
 {
-	writel_relaxed(0x1, per_cpu(sswi_cpu_regs, cpu));
+	writel(0x1, per_cpu(sswi_cpu_regs, cpu));
 }
 
 static void thead_aclint_sswi_ipi_clear(void)
diff --git a/drivers/leds/leds-turris-omnia.c b/drivers/leds/leds-turris-omnia.c
index 7d3b24c8ecae..4fe1a9c0bc1b 100644
--- a/drivers/leds/leds-turris-omnia.c
+++ b/drivers/leds/leds-turris-omnia.c
@@ -438,7 +438,7 @@ static int omnia_mcu_get_features(const struct i2c_client *mcu_client)
 	return reply;
 }
 
-static int omnia_match_mcu_client(struct device *dev, void *data)
+static int omnia_match_mcu_client(struct device *dev, const void *data)
 {
 	struct i2c_client *client;
 
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index a01bc5090cdf..a1534cc6c641 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -492,11 +492,7 @@ int __init smu_init (void)
 		goto fail_np;
 	}
 
-	smu = memblock_alloc(sizeof(struct smu_device), SMP_CACHE_BYTES);
-	if (!smu)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(struct smu_device));
-
+	smu = memblock_alloc_or_panic(sizeof(struct smu_device), SMP_CACHE_BYTES);
 	spin_lock_init(&smu->lock);
 	INIT_LIST_HEAD(&smu->cmd_list);
 	INIT_LIST_HEAD(&smu->cmd_i2c_list);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 1ae2c71bb383..02a2919f4e5a 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -59,6 +59,7 @@ struct convert_context {
 	struct bio *bio_out;
 	struct bvec_iter iter_out;
 	atomic_t cc_pending;
+	unsigned int tag_offset;
 	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
@@ -1187,7 +1188,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio)
 
 	tag_len = io->cc->tuple_size * (bio_sectors(bio) >> io->cc->sector_shift);
 
-	bip->bip_iter.bi_sector = io->cc->start + io->sector;
+	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
 
 	ret = bio_integrity_add_page(bio, virt_to_page(io->integrity_metadata),
 				     tag_len, offset_in_page(io->integrity_metadata));
@@ -1256,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc,
 	if (bio_out)
 		ctx->iter_out = bio_out->bi_iter;
 	ctx->cc_sector = sector + cc->iv_offset;
+	ctx->tag_offset = 0;
 	init_completion(&ctx->restart);
 }
 
@@ -1588,7 +1590,6 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
 static blk_status_t crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx, bool atomic, bool reset_pending)
 {
-	unsigned int tag_offset = 0;
 	unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
 	int r;
 
@@ -1611,9 +1612,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		atomic_inc(&ctx->cc_pending);
 
 		if (crypt_integrity_aead(cc))
-			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset);
+			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset);
 		else
-			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, tag_offset);
+			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset);
 
 		switch (r) {
 		/*
@@ -1633,8 +1634,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 					 * exit and continue processing in a workqueue
 					 */
 					ctx->r.req = NULL;
+					ctx->tag_offset++;
 					ctx->cc_sector += sector_step;
-					tag_offset++;
 					return BLK_STS_DEV_RESOURCE;
 				}
 			} else {
@@ -1648,8 +1649,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		 */
 		case -EINPROGRESS:
 			ctx->r.req = NULL;
+			ctx->tag_offset++;
 			ctx->cc_sector += sector_step;
-			tag_offset++;
 			continue;
 		/*
 		 * The request was already processed (synchronously).
@@ -1657,7 +1658,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		case 0:
 			atomic_dec(&ctx->cc_pending);
 			ctx->cc_sector += sector_step;
-			tag_offset++;
+			ctx->tag_offset++;
 			if (!atomic)
 				cond_resched();
 			continue;
@@ -1719,6 +1720,7 @@ retry:
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
 	clone->bi_ioprio = io->base_bio->bi_ioprio;
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 
 	remaining_size = size;
 
@@ -1909,7 +1911,6 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 			crypt_dec_pending(io);
 			return 1;
 		}
-		clone->bi_iter.bi_sector = cc->start + io->sector;
 		crypt_convert_init(cc, &io->ctx, clone, clone, io->sector);
 		io->saved_bi_iter = clone->bi_iter;
 		dm_submit_bio_remap(io->base_bio, clone);
@@ -1925,13 +1926,13 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs);
 	if (!clone)
 		return 1;
+
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
 
 	crypt_inc_pending(io);
 
-	clone->bi_iter.bi_sector = cc->start + io->sector;
-
 	if (dm_crypt_integrity_io_alloc(io, clone)) {
 		crypt_dec_pending(io);
 		bio_put(clone);
@@ -2039,8 +2040,6 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 	/* crypt_convert should have filled the clone bio */
 	BUG_ON(io->ctx.iter_out.bi_size);
 
-	clone->bi_iter.bi_sector = cc->start + io->sector;
-
 	if ((likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) ||
 	    test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) {
 		dm_submit_bio_remap(io->base_bio, clone);
@@ -2092,13 +2091,12 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	struct crypt_config *cc = io->cc;
 	struct convert_context *ctx = &io->ctx;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	wait_for_completion(&ctx->restart);
 	reinit_completion(&ctx->restart);
 
-	r = crypt_convert(cc, &io->ctx, true, false);
+	r = crypt_convert(cc, &io->ctx, false, false);
 	if (r)
 		io->error = r;
 	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
@@ -2109,10 +2107,8 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 	crypt_dec_pending(io);
 }
@@ -2123,14 +2119,13 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	struct convert_context *ctx = &io->ctx;
 	struct bio *clone;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	/*
 	 * Prevent io from disappearing until this function completes.
 	 */
 	crypt_inc_pending(io);
-	crypt_convert_init(cc, ctx, NULL, io->base_bio, sector);
+	crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector);
 
 	clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
 	if (unlikely(!clone)) {
@@ -2147,8 +2142,6 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		io->ctx.iter_in = clone->bi_iter;
 	}
 
-	sector += bio_sectors(clone);
-
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, ctx,
 			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
@@ -2172,10 +2165,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 dec:
 	crypt_dec_pending(io);
@@ -2203,7 +2194,7 @@ static void kcryptd_crypt_read_continue(struct work_struct *work)
 	wait_for_completion(&io->ctx.restart);
 	reinit_completion(&io->ctx.restart);
 
-	r = crypt_convert(cc, &io->ctx, true, false);
+	r = crypt_convert(cc, &io->ctx, false, false);
 	if (r)
 		io->error = r;
 
@@ -2221,7 +2212,6 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 	crypt_inc_pending(io);
 
 	if (io->ctx.aead_recheck) {
-		io->ctx.cc_sector = io->sector + cc->iv_offset;
 		r = crypt_convert(cc, &io->ctx,
 				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
 	} else {
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index d7a8e2f40db3..c37668790577 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -379,6 +379,7 @@ static void do_region(const blk_opf_t opf, unsigned int region,
 
 		atomic_inc(&io->count);
 		submit_bio(bio);
+		WARN_ON_ONCE(opf & REQ_ATOMIC && remaining);
 	} while (remaining);
 }
 
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 49fb0f684193..66318aba4bdb 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -199,9 +199,10 @@ static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
 
 static struct target_type linear_target = {
 	.name   = "linear",
-	.version = {1, 4, 0},
+	.version = {1, 5, 0},
 	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
-		    DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO,
+		    DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO |
+		    DM_TARGET_ATOMIC_WRITES,
 	.report_zones = linear_report_zones,
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,
diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c
index 461ee6b2044d..716807e511ee 100644
--- a/drivers/md/dm-ps-io-affinity.c
+++ b/drivers/md/dm-ps-io-affinity.c
@@ -116,7 +116,7 @@ static int ioa_create(struct path_selector *ps, unsigned int argc, char **argv)
 	if (!s)
 		return -ENOMEM;
 
-	s->path_map = kzalloc(nr_cpu_ids * sizeof(struct path_info *),
+	s->path_map = kcalloc(nr_cpu_ids, sizeof(struct path_info *),
 			      GFP_KERNEL);
 	if (!s->path_map)
 		goto free_selector;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1e0d3b9b75d6..6adc55fd90d3 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3196,7 +3196,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		if (reshape_sectors || rs_is_raid1(rs)) {
 			/*
 			 * We can only prepare for a reshape here, because the
-			 * raid set needs to run to provide the repective reshape
+			 * raid set needs to run to provide the respective reshape
 			 * check functions via its MD personality instance.
 			 *
 			 * So do the reshape check after md_run() succeeded.
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9511dae5b556..8c6f1f7e6456 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -656,7 +656,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	unsigned int i;
 	struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
 	struct mirror *m;
-	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH);
+	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH | REQ_ATOMIC);
 	struct dm_io_request io_req = {
 		.bi_opf = REQ_OP_WRITE | op_flags,
 		.mem.type = DM_IO_BIO,
@@ -1483,8 +1483,9 @@ static int mirror_iterate_devices(struct dm_target *ti,
 
 static struct target_type mirror_target = {
 	.name	 = "mirror",
-	.version = {1, 14, 0},
+	.version = {1, 15, 0},
 	.module	 = THIS_MODULE,
+	.features = DM_TARGET_ATOMIC_WRITES,
 	.ctr	 = mirror_ctr,
 	.dtr	 = mirror_dtr,
 	.map	 = mirror_map,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 4112071de0be..3786ac67cefe 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -465,8 +465,9 @@ static void stripe_io_hints(struct dm_target *ti,
 
 static struct target_type stripe_target = {
 	.name   = "striped",
-	.version = {1, 6, 0},
-	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
+	.version = {1, 7, 0},
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
+		    DM_TARGET_ATOMIC_WRITES,
 	.module = THIS_MODULE,
 	.ctr    = stripe_ctr,
 	.dtr    = stripe_dtr,
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index bd8b796ae683..0ef5203387b2 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1806,6 +1806,32 @@ static bool dm_table_supports_secure_erase(struct dm_table *t)
 	return true;
 }
 
+static int device_not_atomic_write_capable(struct dm_target *ti,
+			struct dm_dev *dev, sector_t start,
+			sector_t len, void *data)
+{
+	return !bdev_can_atomic_write(dev->bdev);
+}
+
+static bool dm_table_supports_atomic_writes(struct dm_table *t)
+{
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!dm_target_supports_atomic_writes(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices)
+			return false;
+
+		if (ti->type->iterate_devices(ti,
+			device_not_atomic_write_capable, NULL)) {
+			return false;
+		}
+	}
+	return true;
+}
+
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
@@ -1854,6 +1880,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			return r;
 	}
 
+	if (dm_table_supports_atomic_writes(t))
+		limits->features |= BLK_FEAT_ATOMIC_WRITES;
+
 	r = queue_limits_set(q, limits);
 	if (r)
 		return r;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 12ecf07a3841..4d1e42891d24 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1479,12 +1479,12 @@ static void setup_split_accounting(struct clone_info *ci, unsigned int len)
 
 static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 				struct dm_target *ti, unsigned int num_bios,
-				unsigned *len, gfp_t gfp_flag)
+				unsigned *len)
 {
 	struct bio *bio;
-	int try = (gfp_flag & GFP_NOWAIT) ? 0 : 1;
+	int try;
 
-	for (; try < 2; try++) {
+	for (try = 0; try < 2; try++) {
 		int bio_nr;
 
 		if (try && num_bios > 1)
@@ -1508,8 +1508,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 }
 
 static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-					  unsigned int num_bios, unsigned int *len,
-					  gfp_t gfp_flag)
+					  unsigned int num_bios, unsigned int *len)
 {
 	struct bio_list blist = BIO_EMPTY_LIST;
 	struct bio *clone;
@@ -1526,7 +1525,7 @@ static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_targe
 	 * Using alloc_multiple_bios(), even if num_bios is 1, to consistently
 	 * support allocating using GFP_NOWAIT with GFP_NOIO fallback.
 	 */
-	alloc_multiple_bios(&blist, ci, ti, num_bios, len, gfp_flag);
+	alloc_multiple_bios(&blist, ci, ti, num_bios, len);
 	while ((clone = bio_list_pop(&blist))) {
 		if (num_bios > 1)
 			dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
@@ -1564,7 +1563,7 @@ static void __send_empty_flush(struct clone_info *ci)
 
 			atomic_add(ti->num_flush_bios, &ci->io->io_count);
 			bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios,
-						     NULL, GFP_NOWAIT);
+						     NULL);
 			atomic_sub(ti->num_flush_bios - bios, &ci->io->io_count);
 		}
 	} else {
@@ -1612,7 +1611,7 @@ static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti,
 		    __max_io_len(ti, ci->sector, max_granularity, max_sectors));
 
 	atomic_add(num_bios, &ci->io->io_count);
-	bios = __send_duplicate_bios(ci, ti, num_bios, &len, GFP_NOIO);
+	bios = __send_duplicate_bios(ci, ti, num_bios, &len);
 	/*
 	 * alloc_io() takes one extra reference for submission, so the
 	 * reference won't reach 0 without the following (+1) subtraction
@@ -1746,6 +1745,9 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 	ci->submit_as_polled = !!(ci->bio->bi_opf & REQ_POLLED);
 
 	len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count);
+	if (ci->bio->bi_opf & REQ_ATOMIC && len != ci->sector_count)
+		return BLK_STS_IOERR;
+
 	setup_split_accounting(ci, len);
 
 	if (unlikely(ci->bio->bi_opf & REQ_NOWAIT)) {
@@ -1849,7 +1851,7 @@ static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
 			 * not go crazy with the clone allocation.
 			 */
 			alloc_multiple_bios(&blist, ci, ti, min(nr_reset, 32),
-					    NULL, GFP_NOIO);
+					    NULL);
 		}
 
 		/* Get a clone and change it to a regular reset operation. */
@@ -1881,7 +1883,7 @@ static void __send_zone_reset_all_native(struct clone_info *ci,
 	unsigned int bios;
 
 	atomic_add(1, &ci->io->io_count);
-	bios = __send_duplicate_bios(ci, ti, 1, NULL, GFP_NOIO);
+	bios = __send_duplicate_bios(ci, ti, 1, NULL);
 	atomic_sub(1 - bios, &ci->io->io_count);
 
 	ci->sector_count = 0;
@@ -1969,6 +1971,15 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 
 	/* Only support nowait for normal IO */
 	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
+		/*
+		 * Don't support NOWAIT for FLUSH because it may allocate
+		 * multiple bios and there's no easy way how to undo the
+		 * allocations.
+		 */
+		if (bio->bi_opf & REQ_PREFLUSH) {
+			bio_wouldblock_error(bio);
+			return;
+		}
 		io = alloc_io(md, bio, GFP_NOWAIT);
 		if (unlikely(!io)) {
 			/* Unable to do anything without dm_io. */
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index ec4ecd96e6b1..23c09d22fcdb 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2355,7 +2355,10 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
 
 	if (!bitmap)
 		return -ENOENT;
-
+	if (bitmap->mddev->bitmap_info.external)
+		return -ENOENT;
+	if (!bitmap->storage.sb_page) /* no superblock */
+		return -EINVAL;
 	sb = kmap_local_page(bitmap->storage.sb_page);
 	stats->sync_size = le64_to_cpu(sb->sync_size);
 	kunmap_local(sb);
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index a382929ce7ba..369aed044b40 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -76,10 +76,8 @@ static int linear_set_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 866015b681af..30b3dbbce2d2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -294,7 +294,7 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)
 
 static struct ctl_table_header *raid_table_header;
 
-static struct ctl_table raid_table[] = {
+static const struct ctl_table raid_table[] = {
 	{
 		.procname	= "speed_limit_min",
 		.data		= &sysctl_speed_limit_min,
@@ -8376,6 +8376,10 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		return 0;
 
 	spin_unlock(&all_mddevs_lock);
+
+	/* prevent bitmap to be freed after checking */
+	mutex_lock(&mddev->bitmap_info.mutex);
+
 	spin_lock(&mddev->lock);
 	if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
 		seq_printf(seq, "%s : ", mdname(mddev));
@@ -8451,6 +8455,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 	spin_unlock(&mddev->lock);
+	mutex_unlock(&mddev->bitmap_info.mutex);
 	spin_lock(&all_mddevs_lock);
 
 	if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs))
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index c7ba4e6cbbc7..98c745d90f48 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/hash.h>
+#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/device-mapper.h>
 
@@ -77,7 +78,7 @@ static void prefetch_issue(struct prefetch_set *p, struct dm_block_manager *bm)
 /*----------------------------------------------------------------*/
 
 struct shadow_info {
-	struct hlist_node hlist;
+	struct rb_node node;
 	dm_block_t where;
 };
 
@@ -95,7 +96,7 @@ struct dm_transaction_manager {
 	struct dm_space_map *sm;
 
 	spinlock_t lock;
-	struct hlist_head buckets[DM_HASH_SIZE];
+	struct rb_root buckets[DM_HASH_SIZE];
 
 	struct prefetch_set prefetches;
 };
@@ -106,14 +107,22 @@ static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 {
 	int r = 0;
 	unsigned int bucket = dm_hash_block(b, DM_HASH_MASK);
-	struct shadow_info *si;
+	struct rb_node **node;
 
 	spin_lock(&tm->lock);
-	hlist_for_each_entry(si, tm->buckets + bucket, hlist)
-		if (si->where == b) {
+	node = &tm->buckets[bucket].rb_node;
+	while (*node) {
+		struct shadow_info *si =
+			rb_entry(*node, struct shadow_info, node);
+		if (b == si->where) {
 			r = 1;
 			break;
 		}
+		if (b < si->where)
+			node = &si->node.rb_left;
+		else
+			node = &si->node.rb_right;
+	}
 	spin_unlock(&tm->lock);
 
 	return r;
@@ -130,30 +139,41 @@ static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b)
 
 	si = kmalloc(sizeof(*si), GFP_NOIO);
 	if (si) {
+		struct rb_node **node, *parent;
 		si->where = b;
 		bucket = dm_hash_block(b, DM_HASH_MASK);
+
 		spin_lock(&tm->lock);
-		hlist_add_head(&si->hlist, tm->buckets + bucket);
+		node = &tm->buckets[bucket].rb_node;
+		parent = NULL;
+		while (*node) {
+			struct shadow_info *si =
+				rb_entry(*node, struct shadow_info, node);
+			parent = *node;
+			if (b < si->where)
+				node = &si->node.rb_left;
+			else
+				node = &si->node.rb_right;
+		}
+		rb_link_node(&si->node, parent, node);
+		rb_insert_color(&si->node, &tm->buckets[bucket]);
 		spin_unlock(&tm->lock);
 	}
 }
 
 static void wipe_shadow_table(struct dm_transaction_manager *tm)
 {
-	struct shadow_info *si;
-	struct hlist_node *tmp;
-	struct hlist_head *bucket;
-	int i;
+	unsigned int i;
 
 	spin_lock(&tm->lock);
 	for (i = 0; i < DM_HASH_SIZE; i++) {
-		bucket = tm->buckets + i;
-		hlist_for_each_entry_safe(si, tmp, bucket, hlist)
+		while (!RB_EMPTY_ROOT(&tm->buckets[i])) {
+			struct shadow_info *si =
+				rb_entry(tm->buckets[i].rb_node, struct shadow_info, node);
+			rb_erase(&si->node, &tm->buckets[i]);
 			kfree(si);
-
-		INIT_HLIST_HEAD(bucket);
+		}
 	}
-
 	spin_unlock(&tm->lock);
 }
 
@@ -162,7 +182,7 @@ static void wipe_shadow_table(struct dm_transaction_manager *tm)
 static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
 						   struct dm_space_map *sm)
 {
-	int i;
+	unsigned int i;
 	struct dm_transaction_manager *tm;
 
 	tm = kmalloc(sizeof(*tm), GFP_KERNEL);
@@ -176,7 +196,7 @@ static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm,
 
 	spin_lock_init(&tm->lock);
 	for (i = 0; i < DM_HASH_SIZE; i++)
-		INIT_HLIST_HEAD(tm->buckets + i);
+		tm->buckets[i] = RB_ROOT;
 
 	prefetch_init(&tm->prefetches);
 
diff --git a/drivers/media/pci/mgb4/mgb4_core.c b/drivers/media/pci/mgb4/mgb4_core.c
index 8ceaed5c1453..f90ffc4dad52 100644
--- a/drivers/media/pci/mgb4/mgb4_core.c
+++ b/drivers/media/pci/mgb4/mgb4_core.c
@@ -125,7 +125,7 @@ static const struct hwmon_chip_info temp_chip_info = {
 };
 #endif
 
-static int match_i2c_adap(struct device *dev, void *data)
+static int match_i2c_adap(struct device *dev, const void *data)
 {
 	return i2c_verify_adapter(dev) ? 1 : 0;
 }
@@ -141,7 +141,7 @@ static struct i2c_adapter *get_i2c_adap(struct platform_device *pdev)
 	return dev ? to_i2c_adapter(dev) : NULL;
 }
 
-static int match_spi_adap(struct device *dev, void *data)
+static int match_spi_adap(struct device *dev, const void *data)
 {
 	return to_spi_device(dev) ? 1 : 0;
 }
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index a10d4f4d9f95..deadbcea5e22 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -790,27 +790,14 @@ static const u8 uvc_media_transport_input_guid[16] =
 	UVC_GUID_UVC_MEDIA_TRANSPORT_INPUT;
 static const u8 uvc_processing_guid[16] = UVC_GUID_UVC_PROCESSING;
 
-static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type,
-					       u16 id, unsigned int num_pads,
-					       unsigned int extra_size)
+static struct uvc_entity *uvc_alloc_entity(u16 type, u16 id,
+		unsigned int num_pads, unsigned int extra_size)
 {
 	struct uvc_entity *entity;
 	unsigned int num_inputs;
 	unsigned int size;
 	unsigned int i;
 
-	/* Per UVC 1.1+ spec 3.7.2, the ID should be non-zero. */
-	if (id == 0) {
-		dev_err(&dev->udev->dev, "Found Unit with invalid ID 0.\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	/* Per UVC 1.1+ spec 3.7.2, the ID is unique. */
-	if (uvc_entity_by_id(dev, id)) {
-		dev_err(&dev->udev->dev, "Found multiple Units with ID %u\n", id);
-		return ERR_PTR(-EINVAL);
-	}
-
 	extra_size = roundup(extra_size, sizeof(*entity->pads));
 	if (num_pads)
 		num_inputs = type & UVC_TERM_OUTPUT ? num_pads : num_pads - 1;
@@ -820,7 +807,7 @@ static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type,
 	     + num_inputs;
 	entity = kzalloc(size, GFP_KERNEL);
 	if (entity == NULL)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	entity->id = id;
 	entity->type = type;
@@ -932,10 +919,10 @@ static int uvc_parse_vendor_control(struct uvc_device *dev,
 			break;
 		}
 
-		unit = uvc_alloc_new_entity(dev, UVC_VC_EXTENSION_UNIT,
-					    buffer[3], p + 1, 2 * n);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(UVC_VC_EXTENSION_UNIT, buffer[3],
+					p + 1, 2*n);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->guid, &buffer[4], 16);
 		unit->extension.bNumControls = buffer[20];
@@ -1044,10 +1031,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		term = uvc_alloc_new_entity(dev, type | UVC_TERM_INPUT,
-					    buffer[3], 1, n + p);
-		if (IS_ERR(term))
-			return PTR_ERR(term);
+		term = uvc_alloc_entity(type | UVC_TERM_INPUT, buffer[3],
+					1, n + p);
+		if (term == NULL)
+			return -ENOMEM;
 
 		if (UVC_ENTITY_TYPE(term) == UVC_ITT_CAMERA) {
 			term->camera.bControlSize = n;
@@ -1103,10 +1090,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return 0;
 		}
 
-		term = uvc_alloc_new_entity(dev, type | UVC_TERM_OUTPUT,
-					    buffer[3], 1, 0);
-		if (IS_ERR(term))
-			return PTR_ERR(term);
+		term = uvc_alloc_entity(type | UVC_TERM_OUTPUT, buffer[3],
+					1, 0);
+		if (term == NULL)
+			return -ENOMEM;
 
 		memcpy(term->baSourceID, &buffer[7], 1);
 
@@ -1125,10 +1112,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3],
-					    p + 1, 0);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, 0);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->baSourceID, &buffer[5], p);
 
@@ -1148,9 +1134,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], 2, n);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(buffer[2], buffer[3], 2, n);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->baSourceID, &buffer[4], 1);
 		unit->processing.wMaxMultiplier =
@@ -1177,10 +1163,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev,
 			return -EINVAL;
 		}
 
-		unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3],
-					    p + 1, n);
-		if (IS_ERR(unit))
-			return PTR_ERR(unit);
+		unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, n);
+		if (unit == NULL)
+			return -ENOMEM;
 
 		memcpy(unit->guid, &buffer[4], 16);
 		unit->extension.bNumControls = buffer[20];
@@ -1320,10 +1305,9 @@ static int uvc_gpio_parse(struct uvc_device *dev)
 		return dev_err_probe(&dev->intf->dev, irq,
 				     "No IRQ for privacy GPIO\n");
 
-	unit = uvc_alloc_new_entity(dev, UVC_EXT_GPIO_UNIT,
-				    UVC_EXT_GPIO_UNIT_ID, 0, 1);
-	if (IS_ERR(unit))
-		return PTR_ERR(unit);
+	unit = uvc_alloc_entity(UVC_EXT_GPIO_UNIT, UVC_EXT_GPIO_UNIT_ID, 0, 1);
+	if (!unit)
+		return -ENOMEM;
 
 	unit->gpio.gpio_privacy = gpio_privacy;
 	unit->gpio.irq = irq;
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index ae4e8b8e6eb7..043b9ec756ff 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -200,7 +200,7 @@ static int memstick_dummy_check(struct memstick_dev *card)
 
 /**
  * memstick_detect_change - schedule media detection on memstick host
- * @host - host to use
+ * @host: host to use
  */
 void memstick_detect_change(struct memstick_host *host)
 {
@@ -210,13 +210,15 @@ EXPORT_SYMBOL(memstick_detect_change);
 
 /**
  * memstick_next_req - called by host driver to obtain next request to process
- * @host - host to use
- * @mrq - pointer to stick the request to
+ * @host: host to use
+ * @mrq: pointer to stick the request to
  *
  * Host calls this function from idle state (*mrq == NULL) or after finishing
  * previous request (*mrq should point to it). If previous request was
- * unsuccessful, it is retried for predetermined number of times. Return value
- * of 0 means that new request was assigned to the host.
+ * unsuccessful, it is retried for predetermined number of times.
+ *
+ * Returns: value of 0 means that new request was assigned to the host.
+ * Otherwise a negative error code is returned.
  */
 int memstick_next_req(struct memstick_host *host, struct memstick_request **mrq)
 {
@@ -242,7 +244,7 @@ EXPORT_SYMBOL(memstick_next_req);
 
 /**
  * memstick_new_req - notify the host that some requests are pending
- * @host - host to use
+ * @host: host to use
  */
 void memstick_new_req(struct memstick_host *host)
 {
@@ -256,9 +258,9 @@ EXPORT_SYMBOL(memstick_new_req);
 
 /**
  * memstick_init_req_sg - set request fields needed for bulk data transfer
- * @mrq - request to use
- * @tpc - memstick Transport Protocol Command
- * @sg - TPC argument
+ * @mrq: request to use
+ * @tpc: memstick Transport Protocol Command
+ * @sg: TPC argument
  */
 void memstick_init_req_sg(struct memstick_request *mrq, unsigned char tpc,
 			  const struct scatterlist *sg)
@@ -281,10 +283,10 @@ EXPORT_SYMBOL(memstick_init_req_sg);
 
 /**
  * memstick_init_req - set request fields needed for short data transfer
- * @mrq - request to use
- * @tpc - memstick Transport Protocol Command
- * @buf - TPC argument buffer
- * @length - TPC argument size
+ * @mrq: request to use
+ * @tpc: memstick Transport Protocol Command
+ * @buf: TPC argument buffer
+ * @length: TPC argument size
  *
  * The intended use of this function (transfer of data items several bytes
  * in size) allows us to just copy the value between request structure and
@@ -360,7 +362,9 @@ static int h_memstick_set_rw_addr(struct memstick_dev *card,
 /**
  * memstick_set_rw_addr - issue SET_RW_REG_ADDR request and wait for it to
  *                        complete
- * @card - media device to use
+ * @card: media device to use
+ *
+ * Returns: error setting for the current request
  */
 int memstick_set_rw_addr(struct memstick_dev *card)
 {
@@ -487,6 +491,8 @@ out_power_off:
  * memstick_alloc_host - allocate a memstick_host structure
  * @extra: size of the user private data to allocate
  * @dev: parent device of the host
+ *
+ * Returns: %NULL on failure or the allocated &memstick_host pointer on success
  */
 struct memstick_host *memstick_alloc_host(unsigned int extra,
 					  struct device *dev)
@@ -507,7 +513,9 @@ EXPORT_SYMBOL(memstick_alloc_host);
 
 /**
  * memstick_add_host - start request processing on memstick host
- * @host - host to use
+ * @host: host to use
+ *
+ * Returns: %0 on success or a negative error code on failure
  */
 int memstick_add_host(struct memstick_host *host)
 {
@@ -543,7 +551,7 @@ EXPORT_SYMBOL(memstick_add_host);
 
 /**
  * memstick_remove_host - stop request processing on memstick host
- * @host - host to use
+ * @host: host to use
  */
 void memstick_remove_host(struct memstick_host *host)
 {
@@ -565,7 +573,7 @@ EXPORT_SYMBOL(memstick_remove_host);
 
 /**
  * memstick_free_host - free memstick host
- * @host - host to use
+ * @host: host to use
  */
 void memstick_free_host(struct memstick_host *host)
 {
@@ -576,7 +584,7 @@ EXPORT_SYMBOL(memstick_free_host);
 
 /**
  * memstick_suspend_host - notify bus driver of host suspension
- * @host - host to use
+ * @host: host to use
  */
 void memstick_suspend_host(struct memstick_host *host)
 {
@@ -588,7 +596,7 @@ EXPORT_SYMBOL(memstick_suspend_host);
 
 /**
  * memstick_resume_host - notify bus driver of host resumption
- * @host - host to use
+ * @host: host to use
  */
 void memstick_resume_host(struct memstick_host *host)
 {
diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index ee61b70aa677..8f587c0efd9d 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -96,7 +96,7 @@ static u8	mptfcTaskCtx = MPT_MAX_PROTOCOL_DRIVERS;
 static u8	mptfcInternalCtx = MPT_MAX_PROTOCOL_DRIVERS;
 
 static int mptfc_target_alloc(struct scsi_target *starget);
-static int mptfc_slave_alloc(struct scsi_device *sdev);
+static int mptfc_sdev_init(struct scsi_device *sdev);
 static int mptfc_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt);
 static void mptfc_target_destroy(struct scsi_target *starget);
 static void mptfc_set_rport_loss_tmo(struct fc_rport *rport, uint32_t timeout);
@@ -113,10 +113,10 @@ static const struct scsi_host_template mptfc_driver_template = {
 	.info				= mptscsih_info,
 	.queuecommand			= mptfc_qcmd,
 	.target_alloc			= mptfc_target_alloc,
-	.slave_alloc			= mptfc_slave_alloc,
-	.slave_configure		= mptscsih_slave_configure,
+	.sdev_init			= mptfc_sdev_init,
+	.sdev_configure			= mptscsih_sdev_configure,
 	.target_destroy			= mptfc_target_destroy,
-	.slave_destroy			= mptscsih_slave_destroy,
+	.sdev_destroy			= mptscsih_sdev_destroy,
 	.change_queue_depth 		= mptscsih_change_queue_depth,
 	.eh_timed_out			= fc_eh_timed_out,
 	.eh_abort_handler		= mptfc_abort,
@@ -503,7 +503,7 @@ mptfc_register_dev(MPT_ADAPTER *ioc, int channel, FCDevicePage0_t *pg0)
 			/*
 			 * if already mapped, remap here.  If not mapped,
 			 * target_alloc will allocate vtarget and map,
-			 * slave_alloc will fill in vdevice from vtarget.
+			 * sdev_init will fill in vdevice from vtarget.
 			 */
 			if (ri->starget) {
 				vtarget = ri->starget->hostdata;
@@ -631,7 +631,7 @@ mptfc_dump_lun_info(MPT_ADAPTER *ioc, struct fc_rport *rport, struct scsi_device
  *	Init memory once per LUN.
  */
 static int
-mptfc_slave_alloc(struct scsi_device *sdev)
+mptfc_sdev_init(struct scsi_device *sdev)
 {
 	MPT_SCSI_HOST		*hd;
 	VirtTarget		*vtarget;
@@ -651,7 +651,7 @@ mptfc_slave_alloc(struct scsi_device *sdev)
 
 	vdevice = kzalloc(sizeof(VirtDevice), GFP_KERNEL);
 	if (!vdevice) {
-		printk(MYIOC_s_ERR_FMT "slave_alloc kmalloc(%zd) FAILED!\n",
+		printk(MYIOC_s_ERR_FMT "sdev_init kmalloc(%zd) FAILED!\n",
 				ioc->name, sizeof(VirtDevice));
 		return -ENOMEM;
 	}
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index d0549a4daf76..7e79da9684ed 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1710,7 +1710,7 @@ mptsas_firmware_event_work(struct work_struct *work)
 
 
 static int
-mptsas_slave_configure(struct scsi_device *sdev)
+mptsas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct Scsi_Host	*host = sdev->host;
 	MPT_SCSI_HOST	*hd = shost_priv(host);
@@ -1736,7 +1736,7 @@ mptsas_slave_configure(struct scsi_device *sdev)
 	mptsas_add_device_component_starget(ioc, scsi_target(sdev));
 
  out:
-	return mptscsih_slave_configure(sdev);
+	return mptscsih_sdev_configure(sdev, lim);
 }
 
 static int
@@ -1867,7 +1867,7 @@ mptsas_target_destroy(struct scsi_target *starget)
 
 
 static int
-mptsas_slave_alloc(struct scsi_device *sdev)
+mptsas_sdev_init(struct scsi_device *sdev)
 {
 	struct Scsi_Host	*host = sdev->host;
 	MPT_SCSI_HOST		*hd = shost_priv(host);
@@ -1880,7 +1880,7 @@ mptsas_slave_alloc(struct scsi_device *sdev)
 
 	vdevice = kzalloc(sizeof(VirtDevice), GFP_KERNEL);
 	if (!vdevice) {
-		printk(MYIOC_s_ERR_FMT "slave_alloc kzalloc(%zd) FAILED!\n",
+		printk(MYIOC_s_ERR_FMT "sdev_init kzalloc(%zd) FAILED!\n",
 				ioc->name, sizeof(VirtDevice));
 		return -ENOMEM;
 	}
@@ -2005,10 +2005,10 @@ static const struct scsi_host_template mptsas_driver_template = {
 	.info				= mptscsih_info,
 	.queuecommand			= mptsas_qcmd,
 	.target_alloc			= mptsas_target_alloc,
-	.slave_alloc			= mptsas_slave_alloc,
-	.slave_configure		= mptsas_slave_configure,
+	.sdev_init			= mptsas_sdev_init,
+	.sdev_configure			= mptsas_sdev_configure,
 	.target_destroy			= mptsas_target_destroy,
-	.slave_destroy			= mptscsih_slave_destroy,
+	.sdev_destroy			= mptscsih_sdev_destroy,
 	.change_queue_depth 		= mptscsih_change_queue_depth,
 	.eh_timed_out			= mptsas_eh_timed_out,
 	.eh_abort_handler		= mptscsih_abort,
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index 6c3f25cc33ff..a9604ba3c805 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -1071,7 +1071,7 @@ EXPORT_SYMBOL(mptscsih_flush_running_cmds);
  *
  *	Returns: None.
  *
- *	Called from slave_destroy.
+ *	Called from sdev_destroy.
  */
 static void
 mptscsih_search_running_cmds(MPT_SCSI_HOST *hd, VirtDevice *vdevice)
@@ -2331,7 +2331,7 @@ EXPORT_SYMBOL(mptscsih_raid_id_to_num);
  *	Called if no device present or device being unloaded
  */
 void
-mptscsih_slave_destroy(struct scsi_device *sdev)
+mptscsih_sdev_destroy(struct scsi_device *sdev)
 {
 	struct Scsi_Host	*host = sdev->host;
 	MPT_SCSI_HOST		*hd = shost_priv(host);
@@ -2399,7 +2399,7 @@ mptscsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
  *	Return non-zero if fails.
  */
 int
-mptscsih_slave_configure(struct scsi_device *sdev)
+mptscsih_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct Scsi_Host	*sh = sdev->host;
 	VirtTarget		*vtarget;
@@ -3302,8 +3302,8 @@ EXPORT_SYMBOL(mptscsih_resume);
 EXPORT_SYMBOL(mptscsih_show_info);
 EXPORT_SYMBOL(mptscsih_info);
 EXPORT_SYMBOL(mptscsih_qcmd);
-EXPORT_SYMBOL(mptscsih_slave_destroy);
-EXPORT_SYMBOL(mptscsih_slave_configure);
+EXPORT_SYMBOL(mptscsih_sdev_destroy);
+EXPORT_SYMBOL(mptscsih_sdev_configure);
 EXPORT_SYMBOL(mptscsih_abort);
 EXPORT_SYMBOL(mptscsih_dev_reset);
 EXPORT_SYMBOL(mptscsih_target_reset);
diff --git a/drivers/message/fusion/mptscsih.h b/drivers/message/fusion/mptscsih.h
index e3d92c392673..ece451c575e1 100644
--- a/drivers/message/fusion/mptscsih.h
+++ b/drivers/message/fusion/mptscsih.h
@@ -116,8 +116,9 @@ extern const char * mptscsih_info(struct Scsi_Host *SChost);
 extern int mptscsih_qcmd(struct scsi_cmnd *SCpnt);
 extern int mptscsih_IssueTaskMgmt(MPT_SCSI_HOST *hd, u8 type, u8 channel,
 	u8 id, u64 lun, int ctx2abort, ulong timeout);
-extern void mptscsih_slave_destroy(struct scsi_device *device);
-extern int mptscsih_slave_configure(struct scsi_device *device);
+extern void mptscsih_sdev_destroy(struct scsi_device *device);
+extern int mptscsih_sdev_configure(struct scsi_device *device,
+				   struct queue_limits *lim);
 extern int mptscsih_abort(struct scsi_cmnd * SCpnt);
 extern int mptscsih_dev_reset(struct scsi_cmnd * SCpnt);
 extern int mptscsih_target_reset(struct scsi_cmnd * SCpnt);
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 4184d0c70ac3..a3901fbfac4f 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -713,7 +713,7 @@ static void mptspi_dv_device(struct _MPT_SCSI_HOST *hd,
 	mptspi_read_parameters(sdev->sdev_target);
 }
 
-static int mptspi_slave_alloc(struct scsi_device *sdev)
+static int mptspi_sdev_init(struct scsi_device *sdev)
 {
 	MPT_SCSI_HOST *hd = shost_priv(sdev->host);
 	VirtTarget		*vtarget;
@@ -727,7 +727,7 @@ static int mptspi_slave_alloc(struct scsi_device *sdev)
 
 	vdevice = kzalloc(sizeof(VirtDevice), GFP_KERNEL);
 	if (!vdevice) {
-		printk(MYIOC_s_ERR_FMT "slave_alloc kmalloc(%zd) FAILED!\n",
+		printk(MYIOC_s_ERR_FMT "sdev_init kmalloc(%zd) FAILED!\n",
 				ioc->name, sizeof(VirtDevice));
 		return -ENOMEM;
 	}
@@ -746,7 +746,8 @@ static int mptspi_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int mptspi_slave_configure(struct scsi_device *sdev)
+static int mptspi_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	struct _MPT_SCSI_HOST *hd = shost_priv(sdev->host);
 	VirtTarget *vtarget = scsi_target(sdev)->hostdata;
@@ -754,7 +755,7 @@ static int mptspi_slave_configure(struct scsi_device *sdev)
 
 	mptspi_initTarget(hd, vtarget, sdev);
 
-	ret = mptscsih_slave_configure(sdev);
+	ret = mptscsih_sdev_configure(sdev, lim);
 
 	if (ret)
 		return ret;
@@ -799,7 +800,7 @@ mptspi_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt)
 	return mptscsih_qcmd(SCpnt);
 }
 
-static void mptspi_slave_destroy(struct scsi_device *sdev)
+static void mptspi_sdev_destroy(struct scsi_device *sdev)
 {
 	struct scsi_target *starget = scsi_target(sdev);
 	VirtTarget *vtarget = starget->hostdata;
@@ -817,7 +818,7 @@ static void mptspi_slave_destroy(struct scsi_device *sdev)
 		mptspi_write_spi_device_pg1(starget, &pg1);
 	}
 
-	mptscsih_slave_destroy(sdev);
+	mptscsih_sdev_destroy(sdev);
 }
 
 static const struct scsi_host_template mptspi_driver_template = {
@@ -828,10 +829,10 @@ static const struct scsi_host_template mptspi_driver_template = {
 	.info				= mptscsih_info,
 	.queuecommand			= mptspi_qcmd,
 	.target_alloc			= mptspi_target_alloc,
-	.slave_alloc			= mptspi_slave_alloc,
-	.slave_configure		= mptspi_slave_configure,
+	.sdev_init			= mptspi_sdev_init,
+	.sdev_configure			= mptspi_sdev_configure,
 	.target_destroy			= mptspi_target_destroy,
-	.slave_destroy			= mptspi_slave_destroy,
+	.sdev_destroy			= mptspi_sdev_destroy,
 	.change_queue_depth 		= mptscsih_change_queue_depth,
 	.eh_abort_handler		= mptscsih_abort,
 	.eh_device_reset_handler	= mptscsih_dev_reset,
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 09cbe3f0ab1e..56bc72c7ce4a 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -517,7 +517,6 @@ config OPEN_DICE
 
 config NTSYNC
 	tristate "NT synchronization primitive emulation"
-	depends on BROKEN
 	help
 	  This module provides kernel support for emulation of Windows NT
 	  synchronization primitives. It is not a hardware driver.
@@ -613,8 +612,7 @@ config MARVELL_CN10K_DPI
 config MCHP_LAN966X_PCI
 	tristate "Microchip LAN966x PCIe Support"
 	depends on PCI
-	select OF
-	select OF_OVERLAY
+	depends on OF_OVERLAY
 	select IRQ_DOMAIN
 	help
 	  This enables the support for the LAN966x PCIe device.
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 40bf953185c7..545aad06d088 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_SENSORS_BH1770)	+= bh1770glc.o
 obj-$(CONFIG_SENSORS_APDS990X)	+= apds990x.o
 obj-$(CONFIG_ENCLOSURE_SERVICES) += enclosure.o
 obj-$(CONFIG_KGDB_TESTS)	+= kgdbts.o
+obj-$(CONFIG_TEST_MISC_MINOR)	+= misc_minor_kunit.o
 obj-$(CONFIG_SGI_XP)		+= sgi-xp/
 obj-$(CONFIG_SGI_GRU)		+= sgi-gru/
 obj-$(CONFIG_SMPRO_ERRMON)	+= smpro-errmon.o
diff --git a/drivers/misc/c2port/core.c b/drivers/misc/c2port/core.c
index 2bb1dd2511f9..fc64474b8241 100644
--- a/drivers/misc/c2port/core.c
+++ b/drivers/misc/c2port/core.c
@@ -714,7 +714,7 @@ static ssize_t __c2port_read_flash_data(struct c2port_device *dev,
 }
 
 static ssize_t c2port_read_flash_data(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *attr,
+				const struct bin_attribute *attr,
 				char *buffer, loff_t offset, size_t count)
 {
 	struct c2port_device *c2dev = dev_get_drvdata(kobj_to_dev(kobj));
@@ -829,7 +829,7 @@ static ssize_t __c2port_write_flash_data(struct c2port_device *dev,
 }
 
 static ssize_t c2port_write_flash_data(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *attr,
+				const struct bin_attribute *attr,
 				char *buffer, loff_t offset, size_t count)
 {
 	struct c2port_device *c2dev = dev_get_drvdata(kobj_to_dev(kobj));
@@ -849,8 +849,8 @@ static ssize_t c2port_write_flash_data(struct file *filp, struct kobject *kobj,
 	return ret;
 }
 /* size is computed at run-time */
-static BIN_ATTR(flash_data, 0644, c2port_read_flash_data,
-		c2port_write_flash_data, 0);
+static const BIN_ATTR(flash_data, 0644, c2port_read_flash_data,
+		      c2port_write_flash_data, 0);
 
 /*
  * Class attributes
@@ -869,14 +869,27 @@ static struct attribute *c2port_attrs[] = {
 	NULL,
 };
 
-static struct bin_attribute *c2port_bin_attrs[] = {
+static const struct bin_attribute *const c2port_bin_attrs[] = {
 	&bin_attr_flash_data,
 	NULL,
 };
 
+static size_t c2port_bin_attr_size(struct kobject *kobj,
+				   const struct bin_attribute *attr,
+				   int i)
+{
+	struct c2port_device *c2dev = dev_get_drvdata(kobj_to_dev(kobj));
+
+	if (attr == &bin_attr_flash_data)
+		return c2dev->ops->blocks_num * c2dev->ops->block_size;
+
+	return attr->size;
+}
+
 static const struct attribute_group c2port_group = {
 	.attrs = c2port_attrs,
-	.bin_attrs = c2port_bin_attrs,
+	.bin_attrs_new = c2port_bin_attrs,
+	.bin_size = c2port_bin_attr_size,
 };
 
 static const struct attribute_group *c2port_groups[] = {
@@ -912,8 +925,7 @@ struct c2port_device *c2port_device_register(char *name,
 	if (ret < 0)
 		goto error_idr_alloc;
 	c2dev->id = ret;
-
-	bin_attr_flash_data.size = ops->blocks_num * ops->block_size;
+	c2dev->ops = ops;
 
 	c2dev->dev = device_create(c2port_class, NULL, 0, c2dev,
 				   "c2port%d", c2dev->id);
@@ -924,7 +936,6 @@ struct c2port_device *c2port_device_register(char *name,
 	dev_set_drvdata(c2dev->dev, c2dev);
 
 	strscpy(c2dev->name, name, sizeof(c2dev->name));
-	c2dev->ops = ops;
 	mutex_init(&c2dev->mutex);
 
 	/* By default C2 port access is off */
diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c
index 77b0490a1b38..e0174da5e9fc 100644
--- a/drivers/misc/cardreader/rtsx_usb.c
+++ b/drivers/misc/cardreader/rtsx_usb.c
@@ -286,6 +286,7 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status)
 int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 {
 	int ret;
+	u8 interrupt_val = 0;
 	u16 *buf;
 
 	if (!status)
@@ -308,6 +309,20 @@ int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 		ret = rtsx_usb_get_status_with_bulk(ucr, status);
 	}
 
+	rtsx_usb_read_register(ucr, CARD_INT_PEND, &interrupt_val);
+	/* Cross check presence with interrupts */
+	if (*status & XD_CD)
+		if (!(interrupt_val & XD_INT))
+			*status &= ~XD_CD;
+
+	if (*status & SD_CD)
+		if (!(interrupt_val & SD_INT))
+			*status &= ~SD_CD;
+
+	if (*status & MS_CD)
+		if (!(interrupt_val & MS_INT))
+			*status &= ~MS_CD;
+
 	/* usb_control_msg may return positive when success */
 	if (ret < 0)
 		return ret;
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 409bd1c39663..b1fc6446bd4b 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -444,7 +444,7 @@ static ssize_t api_version_compatible_show(struct device *device,
 }
 
 static ssize_t afu_eb_read(struct file *filp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr, char *buf,
+			       const struct bin_attribute *bin_attr, char *buf,
 			       loff_t off, size_t count)
 {
 	struct cxl_afu *afu = to_cxl_afu(kobj_to_dev(kobj));
@@ -538,7 +538,7 @@ static ssize_t class_show(struct kobject *kobj,
 }
 
 static ssize_t afu_read_config(struct file *filp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr, char *buf,
+			       const struct bin_attribute *bin_attr, char *buf,
 			       loff_t off, size_t count)
 {
 	struct afu_config_record *cr = to_cr(kobj);
@@ -620,7 +620,7 @@ static struct afu_config_record *cxl_sysfs_afu_new_cr(struct cxl_afu *afu, int c
 	cr->config_attr.attr.name = "config";
 	cr->config_attr.attr.mode = S_IRUSR;
 	cr->config_attr.size = afu->crs_len;
-	cr->config_attr.read = afu_read_config;
+	cr->config_attr.read_new = afu_read_config;
 
 	rc = kobject_init_and_add(&cr->kobj, &afu_config_record_type,
 				  &afu->dev.kobj, "cr%i", cr->cr);
@@ -693,7 +693,7 @@ int cxl_sysfs_afu_add(struct cxl_afu *afu)
 		afu->attr_eb.attr.name = "afu_err_buff";
 		afu->attr_eb.attr.mode = S_IRUGO;
 		afu->attr_eb.size = afu->eb_len;
-		afu->attr_eb.read = afu_eb_read;
+		afu->attr_eb.read_new = afu_eb_read;
 
 		rc = device_create_bin_file(&afu->dev, &afu->attr_eb);
 		if (rc) {
diff --git a/drivers/misc/ds1682.c b/drivers/misc/ds1682.c
index 4175df7ef011..5d5a70a62e98 100644
--- a/drivers/misc/ds1682.c
+++ b/drivers/misc/ds1682.c
@@ -154,7 +154,7 @@ static const struct attribute_group ds1682_group = {
  * User data attribute
  */
 static ssize_t ds1682_eeprom_read(struct file *filp, struct kobject *kobj,
-				  struct bin_attribute *attr,
+				  const struct bin_attribute *attr,
 				  char *buf, loff_t off, size_t count)
 {
 	struct i2c_client *client = kobj_to_i2c_client(kobj);
@@ -172,7 +172,7 @@ static ssize_t ds1682_eeprom_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t ds1682_eeprom_write(struct file *filp, struct kobject *kobj,
-				   struct bin_attribute *attr,
+				   const struct bin_attribute *attr,
 				   char *buf, loff_t off, size_t count)
 {
 	struct i2c_client *client = kobj_to_i2c_client(kobj);
@@ -194,8 +194,8 @@ static const struct bin_attribute ds1682_eeprom_attr = {
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	.size = DS1682_EEPROM_SIZE,
-	.read = ds1682_eeprom_read,
-	.write = ds1682_eeprom_write,
+	.read_new = ds1682_eeprom_read,
+	.write_new = ds1682_eeprom_write,
 };
 
 static int ds1682_nvmem_read(void *priv, unsigned int offset, void *val,
diff --git a/drivers/misc/eeprom/idt_89hpesx.c b/drivers/misc/eeprom/idt_89hpesx.c
index 43421fe37d33..1fc632ebf22f 100644
--- a/drivers/misc/eeprom/idt_89hpesx.c
+++ b/drivers/misc/eeprom/idt_89hpesx.c
@@ -847,7 +847,7 @@ err_mutex_unlock:
  * @count:	Number of bytes to write
  */
 static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *attr,
+			    const struct bin_attribute *attr,
 			    char *buf, loff_t off, size_t count)
 {
 	struct idt_89hpesx_dev *pdev;
@@ -871,7 +871,7 @@ static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
  * @count:	Number of bytes to write
  */
 static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *attr,
+			   const struct bin_attribute *attr,
 			   char *buf, loff_t off, size_t count)
 {
 	struct idt_89hpesx_dev *pdev;
@@ -1017,7 +1017,7 @@ static ssize_t idt_dbgfs_csr_read(struct file *filep, char __user *ubuf,
  * NOTE Size will be changed in compliance with OF node. EEPROM attribute will
  * be read-only as well if the corresponding flag is specified in OF node.
  */
-static BIN_ATTR_RW(eeprom, EEPROM_DEF_SIZE);
+static const BIN_ATTR_RW(eeprom, EEPROM_DEF_SIZE);
 
 /*
  * csr_dbgfs_ops - CSR debugfs-node read/write operations
diff --git a/drivers/misc/eeprom/max6875.c b/drivers/misc/eeprom/max6875.c
index 6fab2ffa736b..1c36ad153e78 100644
--- a/drivers/misc/eeprom/max6875.c
+++ b/drivers/misc/eeprom/max6875.c
@@ -104,7 +104,7 @@ exit_up:
 }
 
 static ssize_t max6875_read(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr,
+			    const struct bin_attribute *bin_attr,
 			    char *buf, loff_t off, size_t count)
 {
 	struct i2c_client *client = kobj_to_i2c_client(kobj);
@@ -127,7 +127,7 @@ static const struct bin_attribute user_eeprom_attr = {
 		.mode = S_IRUGO,
 	},
 	.size = USER_EEPROM_SIZE,
-	.read = max6875_read,
+	.read_new = max6875_read,
 };
 
 static int max6875_probe(struct i2c_client *client)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 48d08eeb2d20..7b7a22c91fe4 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -139,14 +139,14 @@ struct fastrpc_mmap_rsp_msg {
 };
 
 struct fastrpc_mmap_req_msg {
-	s32 pgid;
+	s32 client_id;
 	u32 flags;
 	u64 vaddr;
 	s32 num;
 };
 
 struct fastrpc_mem_map_req_msg {
-	s32 pgid;
+	s32 client_id;
 	s32 fd;
 	s32 offset;
 	u32 flags;
@@ -156,20 +156,20 @@ struct fastrpc_mem_map_req_msg {
 };
 
 struct fastrpc_munmap_req_msg {
-	s32 pgid;
+	s32 client_id;
 	u64 vaddr;
 	u64 size;
 };
 
 struct fastrpc_mem_unmap_req_msg {
-	s32 pgid;
+	s32 client_id;
 	s32 fd;
 	u64 vaddrin;
 	u64 len;
 };
 
 struct fastrpc_msg {
-	int pid;		/* process group id */
+	int client_id;		/* process client id */
 	int tid;		/* thread id */
 	u64 ctx;		/* invoke caller context */
 	u32 handle;	/* handle to invoke */
@@ -234,7 +234,7 @@ struct fastrpc_invoke_ctx {
 	int nbufs;
 	int retval;
 	int pid;
-	int tgid;
+	int client_id;
 	u32 sc;
 	u32 *crc;
 	u64 ctxid;
@@ -299,7 +299,7 @@ struct fastrpc_user {
 	struct fastrpc_session_ctx *sctx;
 	struct fastrpc_buf *init_mem;
 
-	int tgid;
+	int client_id;
 	int pd;
 	bool is_secure_dev;
 	/* Lock for lists */
@@ -614,7 +614,7 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc(
 	ctx->sc = sc;
 	ctx->retval = -1;
 	ctx->pid = current->pid;
-	ctx->tgid = user->tgid;
+	ctx->client_id = user->client_id;
 	ctx->cctx = cctx;
 	init_completion(&ctx->work);
 	INIT_WORK(&ctx->put_work, fastrpc_context_put_wq);
@@ -992,7 +992,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 			mmap_read_lock(current->mm);
 			vma = find_vma(current->mm, ctx->args[i].ptr);
 			if (vma)
-				pages[i].addr += ctx->args[i].ptr -
+				pages[i].addr += (ctx->args[i].ptr & PAGE_MASK) -
 						 vma->vm_start;
 			mmap_read_unlock(current->mm);
 
@@ -1019,8 +1019,8 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 					(pkt_size - rlen);
 			pages[i].addr = pages[i].addr &	PAGE_MASK;
 
-			pg_start = (args & PAGE_MASK) >> PAGE_SHIFT;
-			pg_end = ((args + len - 1) & PAGE_MASK) >> PAGE_SHIFT;
+			pg_start = (rpra[i].buf.pv & PAGE_MASK) >> PAGE_SHIFT;
+			pg_end = ((rpra[i].buf.pv + len - 1) & PAGE_MASK) >> PAGE_SHIFT;
 			pages[i].size = (pg_end - pg_start + 1) * PAGE_SIZE;
 			args = args + mlen;
 			rlen -= mlen;
@@ -1115,11 +1115,11 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx,
 	int ret;
 
 	cctx = fl->cctx;
-	msg->pid = fl->tgid;
+	msg->client_id = fl->client_id;
 	msg->tid = current->pid;
 
 	if (kernel)
-		msg->pid = 0;
+		msg->client_id = 0;
 
 	msg->ctx = ctx->ctxid | fl->pd;
 	msg->handle = handle;
@@ -1244,7 +1244,7 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl,
 	int err;
 	bool scm_done = false;
 	struct {
-		int pgid;
+		int client_id;
 		u32 namelen;
 		u32 pageslen;
 	} inbuf;
@@ -1293,7 +1293,7 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl,
 		}
 	}
 
-	inbuf.pgid = fl->tgid;
+	inbuf.client_id = fl->client_id;
 	inbuf.namelen = init.namelen;
 	inbuf.pageslen = 0;
 	fl->pd = USER_PD;
@@ -1363,7 +1363,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl,
 	int memlen;
 	int err;
 	struct {
-		int pgid;
+		int client_id;
 		u32 namelen;
 		u32 filelen;
 		u32 pageslen;
@@ -1395,7 +1395,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl,
 		goto err;
 	}
 
-	inbuf.pgid = fl->tgid;
+	inbuf.client_id = fl->client_id;
 	inbuf.namelen = strlen(current->comm) + 1;
 	inbuf.filelen = init.filelen;
 	inbuf.pageslen = 1;
@@ -1469,8 +1469,9 @@ err:
 }
 
 static struct fastrpc_session_ctx *fastrpc_session_alloc(
-					struct fastrpc_channel_ctx *cctx)
+					struct fastrpc_user *fl)
 {
+	struct fastrpc_channel_ctx *cctx = fl->cctx;
 	struct fastrpc_session_ctx *session = NULL;
 	unsigned long flags;
 	int i;
@@ -1480,6 +1481,8 @@ static struct fastrpc_session_ctx *fastrpc_session_alloc(
 		if (!cctx->session[i].used && cctx->session[i].valid) {
 			cctx->session[i].used = true;
 			session = &cctx->session[i];
+			/* any non-zero ID will work, session_idx + 1 is the simplest one */
+			fl->client_id = i + 1;
 			break;
 		}
 	}
@@ -1501,12 +1504,12 @@ static void fastrpc_session_free(struct fastrpc_channel_ctx *cctx,
 static int fastrpc_release_current_dsp_process(struct fastrpc_user *fl)
 {
 	struct fastrpc_invoke_args args[1];
-	int tgid = 0;
+	int client_id = 0;
 	u32 sc;
 
-	tgid = fl->tgid;
-	args[0].ptr = (u64)(uintptr_t) &tgid;
-	args[0].length = sizeof(tgid);
+	client_id = fl->client_id;
+	args[0].ptr = (u64)(uintptr_t) &client_id;
+	args[0].length = sizeof(client_id);
 	args[0].fd = -1;
 	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_RELEASE, 1, 0);
 
@@ -1579,11 +1582,10 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp)
 	INIT_LIST_HEAD(&fl->maps);
 	INIT_LIST_HEAD(&fl->mmaps);
 	INIT_LIST_HEAD(&fl->user);
-	fl->tgid = current->tgid;
 	fl->cctx = cctx;
 	fl->is_secure_dev = fdevice->secure;
 
-	fl->sctx = fastrpc_session_alloc(cctx);
+	fl->sctx = fastrpc_session_alloc(fl);
 	if (!fl->sctx) {
 		dev_err(&cctx->rpdev->dev, "No session available\n");
 		mutex_destroy(&fl->mutex);
@@ -1647,11 +1649,11 @@ static int fastrpc_dmabuf_alloc(struct fastrpc_user *fl, char __user *argp)
 static int fastrpc_init_attach(struct fastrpc_user *fl, int pd)
 {
 	struct fastrpc_invoke_args args[1];
-	int tgid = fl->tgid;
+	int client_id = fl->client_id;
 	u32 sc;
 
-	args[0].ptr = (u64)(uintptr_t) &tgid;
-	args[0].length = sizeof(tgid);
+	args[0].ptr = (u64)(uintptr_t) &client_id;
+	args[0].length = sizeof(client_id);
 	args[0].fd = -1;
 	sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_ATTACH, 1, 0);
 	fl->pd = pd;
@@ -1803,7 +1805,7 @@ static int fastrpc_req_munmap_impl(struct fastrpc_user *fl, struct fastrpc_buf *
 	int err;
 	u32 sc;
 
-	req_msg.pgid = fl->tgid;
+	req_msg.client_id = fl->client_id;
 	req_msg.size = buf->size;
 	req_msg.vaddr = buf->raddr;
 
@@ -1889,7 +1891,7 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
 		return err;
 	}
 
-	req_msg.pgid = fl->tgid;
+	req_msg.client_id = fl->client_id;
 	req_msg.flags = req.flags;
 	req_msg.vaddr = req.vaddrin;
 	req_msg.num = sizeof(pages);
@@ -1978,7 +1980,7 @@ static int fastrpc_req_mem_unmap_impl(struct fastrpc_user *fl, struct fastrpc_me
 		return -EINVAL;
 	}
 
-	req_msg.pgid = fl->tgid;
+	req_msg.client_id = fl->client_id;
 	req_msg.len = map->len;
 	req_msg.vaddrin = map->raddr;
 	req_msg.fd = map->fd;
@@ -2031,7 +2033,7 @@ static int fastrpc_req_mem_map(struct fastrpc_user *fl, char __user *argp)
 		return err;
 	}
 
-	req_msg.pgid = fl->tgid;
+	req_msg.client_id = fl->client_id;
 	req_msg.fd = req.fd;
 	req_msg.offset = req.offset;
 	req_msg.vaddrin = req.vaddrin;
@@ -2344,7 +2346,7 @@ static int fastrpc_rpmsg_probe(struct rpmsg_device *rpdev)
 
 		err = fastrpc_device_register(rdev, data, false, domains[domain_id]);
 		if (err)
-			goto fdev_error;
+			goto populate_error;
 		break;
 	default:
 		err = -EINVAL;
diff --git a/drivers/misc/keba/cp500.c b/drivers/misc/keba/cp500.c
index 255d3022dae8..d0c6113dcff3 100644
--- a/drivers/misc/keba/cp500.c
+++ b/drivers/misc/keba/cp500.c
@@ -126,8 +126,9 @@ static struct cp500_devs cp520_devices = {
 };
 
 struct cp500_nvmem {
-	struct nvmem_device *nvmem;
+	struct nvmem_device *base_nvmem;
 	unsigned int offset;
+	struct nvmem_device *nvmem;
 };
 
 struct cp500 {
@@ -581,8 +582,8 @@ static int cp500_nvmem_read(void *priv, unsigned int offset, void *val,
 	struct cp500_nvmem *nvmem = priv;
 	int ret;
 
-	ret = nvmem_device_read(nvmem->nvmem, nvmem->offset + offset, bytes,
-				val);
+	ret = nvmem_device_read(nvmem->base_nvmem, nvmem->offset + offset,
+				bytes, val);
 	if (ret != bytes)
 		return ret;
 
@@ -595,15 +596,16 @@ static int cp500_nvmem_write(void *priv, unsigned int offset, void *val,
 	struct cp500_nvmem *nvmem = priv;
 	int ret;
 
-	ret = nvmem_device_write(nvmem->nvmem, nvmem->offset + offset, bytes,
-				 val);
+	ret = nvmem_device_write(nvmem->base_nvmem, nvmem->offset + offset,
+				 bytes, val);
 	if (ret != bytes)
 		return ret;
 
 	return 0;
 }
 
-static int cp500_nvmem_register(struct cp500 *cp500, struct nvmem_device *nvmem)
+static int cp500_nvmem_register(struct cp500 *cp500,
+				struct nvmem_device *base_nvmem)
 {
 	struct device *dev = &cp500->pci_dev->dev;
 	struct nvmem_config nvmem_config = {};
@@ -625,27 +627,52 @@ static int cp500_nvmem_register(struct cp500 *cp500, struct nvmem_device *nvmem)
 	nvmem_config.reg_read = cp500_nvmem_read;
 	nvmem_config.reg_write = cp500_nvmem_write;
 
-	cp500->nvmem_cpu.nvmem = nvmem;
+	cp500->nvmem_cpu.base_nvmem = base_nvmem;
 	cp500->nvmem_cpu.offset = CP500_EEPROM_CPU_OFFSET;
 	nvmem_config.name = CP500_EEPROM_CPU_NAME;
 	nvmem_config.size = CP500_EEPROM_CPU_SIZE;
 	nvmem_config.priv = &cp500->nvmem_cpu;
-	tmp = devm_nvmem_register(dev, &nvmem_config);
+	tmp = nvmem_register(&nvmem_config);
 	if (IS_ERR(tmp))
 		return PTR_ERR(tmp);
+	cp500->nvmem_cpu.nvmem = tmp;
 
-	cp500->nvmem_user.nvmem = nvmem;
+	cp500->nvmem_user.base_nvmem = base_nvmem;
 	cp500->nvmem_user.offset = CP500_EEPROM_USER_OFFSET;
 	nvmem_config.name = CP500_EEPROM_USER_NAME;
 	nvmem_config.size = CP500_EEPROM_USER_SIZE;
 	nvmem_config.priv = &cp500->nvmem_user;
-	tmp = devm_nvmem_register(dev, &nvmem_config);
-	if (IS_ERR(tmp))
+	tmp = nvmem_register(&nvmem_config);
+	if (IS_ERR(tmp)) {
+		nvmem_unregister(cp500->nvmem_cpu.nvmem);
+		cp500->nvmem_cpu.nvmem = NULL;
+
 		return PTR_ERR(tmp);
+	}
+	cp500->nvmem_user.nvmem = tmp;
 
 	return 0;
 }
 
+static void cp500_nvmem_unregister(struct cp500 *cp500)
+{
+	int notified;
+
+	if (cp500->nvmem_user.nvmem) {
+		nvmem_unregister(cp500->nvmem_user.nvmem);
+		cp500->nvmem_user.nvmem = NULL;
+	}
+	if (cp500->nvmem_cpu.nvmem) {
+		nvmem_unregister(cp500->nvmem_cpu.nvmem);
+		cp500->nvmem_cpu.nvmem = NULL;
+	}
+
+	/* CPU and user nvmem use the same base_nvmem, put only once */
+	notified = atomic_read(&cp500->nvmem_notified);
+	if (notified)
+		nvmem_device_put(cp500->nvmem_cpu.base_nvmem);
+}
+
 static int cp500_nvmem_match(struct device *dev, const void *data)
 {
 	const struct cp500 *cp500 = data;
@@ -663,13 +690,6 @@ static int cp500_nvmem_match(struct device *dev, const void *data)
 	return 0;
 }
 
-static void cp500_devm_nvmem_put(void *data)
-{
-	struct nvmem_device *nvmem = data;
-
-	nvmem_device_put(nvmem);
-}
-
 static int cp500_nvmem(struct notifier_block *nb, unsigned long action,
 		       void *data)
 {
@@ -698,10 +718,6 @@ static int cp500_nvmem(struct notifier_block *nb, unsigned long action,
 		return NOTIFY_DONE;
 	}
 
-	ret = devm_add_action_or_reset(dev, cp500_devm_nvmem_put, nvmem);
-	if (ret)
-		return ret;
-
 	ret = cp500_nvmem_register(cp500, nvmem);
 	if (ret)
 		return ret;
@@ -932,12 +948,17 @@ static void cp500_remove(struct pci_dev *pci_dev)
 {
 	struct cp500 *cp500 = pci_get_drvdata(pci_dev);
 
+	/*
+	 * unregister CPU and user nvmem and put base_nvmem before parent
+	 * auxiliary device of base_nvmem is unregistered
+	 */
+	nvmem_unregister_notifier(&cp500->nvmem_notifier);
+	cp500_nvmem_unregister(cp500);
+
 	cp500_unregister_auxiliary_devs(cp500);
 
 	cp500_disable(cp500);
 
-	nvmem_unregister_notifier(&cp500->nvmem_notifier);
-
 	pci_set_drvdata(pci_dev, 0);
 
 	pci_free_irq_vectors(pci_dev);
diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
index 3c1359d8d4e6..04756302b878 100644
--- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
+++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
@@ -147,6 +147,9 @@ static int pci1xxxx_gpio_set_config(struct gpio_chip *gpio, unsigned int offset,
 	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
 		pci1xxx_assign_bit(priv->reg_base, OPENDRAIN_OFFSET(offset), (offset % 32), true);
 		break;
+	case PIN_CONFIG_DRIVE_PUSH_PULL:
+		pci1xxx_assign_bit(priv->reg_base, OPENDRAIN_OFFSET(offset), (offset % 32), false);
+		break;
 	default:
 		ret = -ENOTSUPP;
 		break;
diff --git a/drivers/misc/misc_minor_kunit.c b/drivers/misc/misc_minor_kunit.c
new file mode 100644
index 000000000000..293e0fb7e43e
--- /dev/null
+++ b/drivers/misc/misc_minor_kunit.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <kunit/test.h>
+#include <kunit/test-bug.h>
+#include <linux/module.h>
+#include <linux/miscdevice.h>
+
+/* dynamic minor (2) */
+static struct miscdevice dev_dynamic_minor = {
+	.minor  = 2,
+	.name   = "dev_dynamic_minor",
+};
+
+/* static minor (LCD_MINOR) */
+static struct miscdevice dev_static_minor = {
+	.minor  = LCD_MINOR,
+	.name   = "dev_static_minor",
+};
+
+/* misc dynamic minor */
+static struct miscdevice dev_misc_dynamic_minor = {
+	.minor  = MISC_DYNAMIC_MINOR,
+	.name   = "dev_misc_dynamic_minor",
+};
+
+static void kunit_dynamic_minor(struct kunit *test)
+{
+	int ret;
+
+	ret = misc_register(&dev_dynamic_minor);
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	KUNIT_EXPECT_EQ(test, 2, dev_dynamic_minor.minor);
+	misc_deregister(&dev_dynamic_minor);
+}
+
+static void kunit_static_minor(struct kunit *test)
+{
+	int ret;
+
+	ret = misc_register(&dev_static_minor);
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	KUNIT_EXPECT_EQ(test, LCD_MINOR, dev_static_minor.minor);
+	misc_deregister(&dev_static_minor);
+}
+
+static void kunit_misc_dynamic_minor(struct kunit *test)
+{
+	int ret;
+
+	ret = misc_register(&dev_misc_dynamic_minor);
+	KUNIT_EXPECT_EQ(test, 0, ret);
+	misc_deregister(&dev_misc_dynamic_minor);
+}
+
+static struct kunit_case test_cases[] = {
+	KUNIT_CASE(kunit_dynamic_minor),
+	KUNIT_CASE(kunit_static_minor),
+	KUNIT_CASE(kunit_misc_dynamic_minor),
+	{}
+};
+
+static struct kunit_suite test_suite = {
+	.name = "misc_minor_test",
+	.test_cases = test_cases,
+};
+kunit_test_suite(test_suite);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vimal Agrawal");
+MODULE_DESCRIPTION("misc minor testing");
diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 4954553b7baa..055395cde42b 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -6,11 +6,17 @@
  */
 
 #include <linux/anon_inodes.h>
+#include <linux/atomic.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/overflow.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <uapi/linux/ntsync.h>
@@ -19,6 +25,8 @@
 
 enum ntsync_type {
 	NTSYNC_TYPE_SEM,
+	NTSYNC_TYPE_MUTEX,
+	NTSYNC_TYPE_EVENT,
 };
 
 /*
@@ -30,10 +38,13 @@ enum ntsync_type {
  *
  * Both rely on struct file for reference counting. Individual
  * ntsync_obj objects take a reference to the device when created.
+ * Wait operations take a reference to each object being waited on for
+ * the duration of the wait.
  */
 
 struct ntsync_obj {
 	spinlock_t lock;
+	int dev_locked;
 
 	enum ntsync_type type;
 
@@ -46,22 +57,344 @@ struct ntsync_obj {
 			__u32 count;
 			__u32 max;
 		} sem;
+		struct {
+			__u32 count;
+			pid_t owner;
+			bool ownerdead;
+		} mutex;
+		struct {
+			bool manual;
+			bool signaled;
+		} event;
 	} u;
+
+	/*
+	 * any_waiters is protected by the object lock, but all_waiters is
+	 * protected by the device wait_all_lock.
+	 */
+	struct list_head any_waiters;
+	struct list_head all_waiters;
+
+	/*
+	 * Hint describing how many tasks are queued on this object in a
+	 * wait-all operation.
+	 *
+	 * Any time we do a wake, we may need to wake "all" waiters as well as
+	 * "any" waiters. In order to atomically wake "all" waiters, we must
+	 * lock all of the objects, and that means grabbing the wait_all_lock
+	 * below (and, due to lock ordering rules, before locking this object).
+	 * However, wait-all is a rare operation, and grabbing the wait-all
+	 * lock for every wake would create unnecessary contention.
+	 * Therefore we first check whether all_hint is zero, and, if it is,
+	 * we skip trying to wake "all" waiters.
+	 *
+	 * Since wait requests must originate from user-space threads, we're
+	 * limited here by PID_MAX_LIMIT, so there's no risk of overflow.
+	 */
+	atomic_t all_hint;
+};
+
+struct ntsync_q_entry {
+	struct list_head node;
+	struct ntsync_q *q;
+	struct ntsync_obj *obj;
+	__u32 index;
+};
+
+struct ntsync_q {
+	struct task_struct *task;
+	__u32 owner;
+
+	/*
+	 * Protected via atomic_try_cmpxchg(). Only the thread that wins the
+	 * compare-and-swap may actually change object states and wake this
+	 * task.
+	 */
+	atomic_t signaled;
+
+	bool all;
+	bool ownerdead;
+	__u32 count;
+	struct ntsync_q_entry entries[];
 };
 
 struct ntsync_device {
+	/*
+	 * Wait-all operations must atomically grab all objects, and be totally
+	 * ordered with respect to each other and wait-any operations.
+	 * If one thread is trying to acquire several objects, another thread
+	 * cannot touch the object at the same time.
+	 *
+	 * This device-wide lock is used to serialize wait-for-all
+	 * operations, and operations on an object that is involved in a
+	 * wait-for-all.
+	 */
+	struct mutex wait_all_lock;
+
 	struct file *file;
 };
 
 /*
+ * Single objects are locked using obj->lock.
+ *
+ * Multiple objects are 'locked' while holding dev->wait_all_lock.
+ * In this case however, individual objects are not locked by holding
+ * obj->lock, but by setting obj->dev_locked.
+ *
+ * This means that in order to lock a single object, the sequence is slightly
+ * more complicated than usual. Specifically it needs to check obj->dev_locked
+ * after acquiring obj->lock, if set, it needs to drop the lock and acquire
+ * dev->wait_all_lock in order to serialize against the multi-object operation.
+ */
+
+static void dev_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	lockdep_assert_held(&dev->wait_all_lock);
+	lockdep_assert(obj->dev == dev);
+	spin_lock(&obj->lock);
+	/*
+	 * By setting obj->dev_locked inside obj->lock, it is ensured that
+	 * anyone holding obj->lock must see the value.
+	 */
+	obj->dev_locked = 1;
+	spin_unlock(&obj->lock);
+}
+
+static void dev_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	lockdep_assert_held(&dev->wait_all_lock);
+	lockdep_assert(obj->dev == dev);
+	spin_lock(&obj->lock);
+	obj->dev_locked = 0;
+	spin_unlock(&obj->lock);
+}
+
+static void obj_lock(struct ntsync_obj *obj)
+{
+	struct ntsync_device *dev = obj->dev;
+
+	for (;;) {
+		spin_lock(&obj->lock);
+		if (likely(!obj->dev_locked))
+			break;
+
+		spin_unlock(&obj->lock);
+		mutex_lock(&dev->wait_all_lock);
+		spin_lock(&obj->lock);
+		/*
+		 * obj->dev_locked should be set and released under the same
+		 * wait_all_lock section, since we now own this lock, it should
+		 * be clear.
+		 */
+		lockdep_assert(!obj->dev_locked);
+		spin_unlock(&obj->lock);
+		mutex_unlock(&dev->wait_all_lock);
+	}
+}
+
+static void obj_unlock(struct ntsync_obj *obj)
+{
+	spin_unlock(&obj->lock);
+}
+
+static bool ntsync_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	bool all;
+
+	obj_lock(obj);
+	all = atomic_read(&obj->all_hint);
+	if (unlikely(all)) {
+		obj_unlock(obj);
+		mutex_lock(&dev->wait_all_lock);
+		dev_lock_obj(dev, obj);
+	}
+
+	return all;
+}
+
+static void ntsync_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj, bool all)
+{
+	if (all) {
+		dev_unlock_obj(dev, obj);
+		mutex_unlock(&dev->wait_all_lock);
+	} else {
+		obj_unlock(obj);
+	}
+}
+
+#define ntsync_assert_held(obj) \
+	lockdep_assert((lockdep_is_held(&(obj)->lock) != LOCK_STATE_NOT_HELD) || \
+		       ((lockdep_is_held(&(obj)->dev->wait_all_lock) != LOCK_STATE_NOT_HELD) && \
+			(obj)->dev_locked))
+
+static bool is_signaled(struct ntsync_obj *obj, __u32 owner)
+{
+	ntsync_assert_held(obj);
+
+	switch (obj->type) {
+	case NTSYNC_TYPE_SEM:
+		return !!obj->u.sem.count;
+	case NTSYNC_TYPE_MUTEX:
+		if (obj->u.mutex.owner && obj->u.mutex.owner != owner)
+			return false;
+		return obj->u.mutex.count < UINT_MAX;
+	case NTSYNC_TYPE_EVENT:
+		return obj->u.event.signaled;
+	}
+
+	WARN(1, "bad object type %#x\n", obj->type);
+	return false;
+}
+
+/*
+ * "locked_obj" is an optional pointer to an object which is already locked and
+ * should not be locked again. This is necessary so that changing an object's
+ * state and waking it can be a single atomic operation.
+ */
+static void try_wake_all(struct ntsync_device *dev, struct ntsync_q *q,
+			 struct ntsync_obj *locked_obj)
+{
+	__u32 count = q->count;
+	bool can_wake = true;
+	int signaled = -1;
+	__u32 i;
+
+	lockdep_assert_held(&dev->wait_all_lock);
+	if (locked_obj)
+		lockdep_assert(locked_obj->dev_locked);
+
+	for (i = 0; i < count; i++) {
+		if (q->entries[i].obj != locked_obj)
+			dev_lock_obj(dev, q->entries[i].obj);
+	}
+
+	for (i = 0; i < count; i++) {
+		if (!is_signaled(q->entries[i].obj, q->owner)) {
+			can_wake = false;
+			break;
+		}
+	}
+
+	if (can_wake && atomic_try_cmpxchg(&q->signaled, &signaled, 0)) {
+		for (i = 0; i < count; i++) {
+			struct ntsync_obj *obj = q->entries[i].obj;
+
+			switch (obj->type) {
+			case NTSYNC_TYPE_SEM:
+				obj->u.sem.count--;
+				break;
+			case NTSYNC_TYPE_MUTEX:
+				if (obj->u.mutex.ownerdead)
+					q->ownerdead = true;
+				obj->u.mutex.ownerdead = false;
+				obj->u.mutex.count++;
+				obj->u.mutex.owner = q->owner;
+				break;
+			case NTSYNC_TYPE_EVENT:
+				if (!obj->u.event.manual)
+					obj->u.event.signaled = false;
+				break;
+			}
+		}
+		wake_up_process(q->task);
+	}
+
+	for (i = 0; i < count; i++) {
+		if (q->entries[i].obj != locked_obj)
+			dev_unlock_obj(dev, q->entries[i].obj);
+	}
+}
+
+static void try_wake_all_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+	struct ntsync_q_entry *entry;
+
+	lockdep_assert_held(&dev->wait_all_lock);
+	lockdep_assert(obj->dev_locked);
+
+	list_for_each_entry(entry, &obj->all_waiters, node)
+		try_wake_all(dev, entry->q, obj);
+}
+
+static void try_wake_any_sem(struct ntsync_obj *sem)
+{
+	struct ntsync_q_entry *entry;
+
+	ntsync_assert_held(sem);
+	lockdep_assert(sem->type == NTSYNC_TYPE_SEM);
+
+	list_for_each_entry(entry, &sem->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+		int signaled = -1;
+
+		if (!sem->u.sem.count)
+			break;
+
+		if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) {
+			sem->u.sem.count--;
+			wake_up_process(q->task);
+		}
+	}
+}
+
+static void try_wake_any_mutex(struct ntsync_obj *mutex)
+{
+	struct ntsync_q_entry *entry;
+
+	ntsync_assert_held(mutex);
+	lockdep_assert(mutex->type == NTSYNC_TYPE_MUTEX);
+
+	list_for_each_entry(entry, &mutex->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+		int signaled = -1;
+
+		if (mutex->u.mutex.count == UINT_MAX)
+			break;
+		if (mutex->u.mutex.owner && mutex->u.mutex.owner != q->owner)
+			continue;
+
+		if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) {
+			if (mutex->u.mutex.ownerdead)
+				q->ownerdead = true;
+			mutex->u.mutex.ownerdead = false;
+			mutex->u.mutex.count++;
+			mutex->u.mutex.owner = q->owner;
+			wake_up_process(q->task);
+		}
+	}
+}
+
+static void try_wake_any_event(struct ntsync_obj *event)
+{
+	struct ntsync_q_entry *entry;
+
+	ntsync_assert_held(event);
+	lockdep_assert(event->type == NTSYNC_TYPE_EVENT);
+
+	list_for_each_entry(entry, &event->any_waiters, node) {
+		struct ntsync_q *q = entry->q;
+		int signaled = -1;
+
+		if (!event->u.event.signaled)
+			break;
+
+		if (atomic_try_cmpxchg(&q->signaled, &signaled, entry->index)) {
+			if (!event->u.event.manual)
+				event->u.event.signaled = false;
+			wake_up_process(q->task);
+		}
+	}
+}
+
+/*
  * Actually change the semaphore state, returning -EOVERFLOW if it is made
  * invalid.
  */
-static int post_sem_state(struct ntsync_obj *sem, __u32 count)
+static int release_sem_state(struct ntsync_obj *sem, __u32 count)
 {
 	__u32 sum;
 
-	lockdep_assert_held(&sem->lock);
+	ntsync_assert_held(sem);
 
 	if (check_add_overflow(sem->u.sem.count, count, &sum) ||
 	    sum > sem->u.sem.max)
@@ -71,11 +404,13 @@ static int post_sem_state(struct ntsync_obj *sem, __u32 count)
 	return 0;
 }
 
-static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp)
+static int ntsync_sem_release(struct ntsync_obj *sem, void __user *argp)
 {
+	struct ntsync_device *dev = sem->dev;
 	__u32 __user *user_args = argp;
 	__u32 prev_count;
 	__u32 args;
+	bool all;
 	int ret;
 
 	if (copy_from_user(&args, argp, sizeof(args)))
@@ -84,12 +419,17 @@ static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp)
 	if (sem->type != NTSYNC_TYPE_SEM)
 		return -EINVAL;
 
-	spin_lock(&sem->lock);
+	all = ntsync_lock_obj(dev, sem);
 
 	prev_count = sem->u.sem.count;
-	ret = post_sem_state(sem, args);
+	ret = release_sem_state(sem, args);
+	if (!ret) {
+		if (all)
+			try_wake_all_obj(dev, sem);
+		try_wake_any_sem(sem);
+	}
 
-	spin_unlock(&sem->lock);
+	ntsync_unlock_obj(dev, sem, all);
 
 	if (!ret && put_user(prev_count, user_args))
 		ret = -EFAULT;
@@ -97,13 +437,229 @@ static int ntsync_sem_post(struct ntsync_obj *sem, void __user *argp)
 	return ret;
 }
 
-static int ntsync_obj_release(struct inode *inode, struct file *file)
+/*
+ * Actually change the mutex state, returning -EPERM if not the owner.
+ */
+static int unlock_mutex_state(struct ntsync_obj *mutex,
+			      const struct ntsync_mutex_args *args)
 {
-	struct ntsync_obj *obj = file->private_data;
+	ntsync_assert_held(mutex);
+
+	if (mutex->u.mutex.owner != args->owner)
+		return -EPERM;
+
+	if (!--mutex->u.mutex.count)
+		mutex->u.mutex.owner = 0;
+	return 0;
+}
+
+static int ntsync_mutex_unlock(struct ntsync_obj *mutex, void __user *argp)
+{
+	struct ntsync_mutex_args __user *user_args = argp;
+	struct ntsync_device *dev = mutex->dev;
+	struct ntsync_mutex_args args;
+	__u32 prev_count;
+	bool all;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+	if (!args.owner)
+		return -EINVAL;
+
+	if (mutex->type != NTSYNC_TYPE_MUTEX)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, mutex);
+
+	prev_count = mutex->u.mutex.count;
+	ret = unlock_mutex_state(mutex, &args);
+	if (!ret) {
+		if (all)
+			try_wake_all_obj(dev, mutex);
+		try_wake_any_mutex(mutex);
+	}
+
+	ntsync_unlock_obj(dev, mutex, all);
+
+	if (!ret && put_user(prev_count, &user_args->count))
+		ret = -EFAULT;
+
+	return ret;
+}
+
+/*
+ * Actually change the mutex state to mark its owner as dead,
+ * returning -EPERM if not the owner.
+ */
+static int kill_mutex_state(struct ntsync_obj *mutex, __u32 owner)
+{
+	ntsync_assert_held(mutex);
+
+	if (mutex->u.mutex.owner != owner)
+		return -EPERM;
+
+	mutex->u.mutex.ownerdead = true;
+	mutex->u.mutex.owner = 0;
+	mutex->u.mutex.count = 0;
+	return 0;
+}
+
+static int ntsync_mutex_kill(struct ntsync_obj *mutex, void __user *argp)
+{
+	struct ntsync_device *dev = mutex->dev;
+	__u32 owner;
+	bool all;
+	int ret;
+
+	if (get_user(owner, (__u32 __user *)argp))
+		return -EFAULT;
+	if (!owner)
+		return -EINVAL;
+
+	if (mutex->type != NTSYNC_TYPE_MUTEX)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, mutex);
+
+	ret = kill_mutex_state(mutex, owner);
+	if (!ret) {
+		if (all)
+			try_wake_all_obj(dev, mutex);
+		try_wake_any_mutex(mutex);
+	}
+
+	ntsync_unlock_obj(dev, mutex, all);
+
+	return ret;
+}
+
+static int ntsync_event_set(struct ntsync_obj *event, void __user *argp, bool pulse)
+{
+	struct ntsync_device *dev = event->dev;
+	__u32 prev_state;
+	bool all;
+
+	if (event->type != NTSYNC_TYPE_EVENT)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, event);
+
+	prev_state = event->u.event.signaled;
+	event->u.event.signaled = true;
+	if (all)
+		try_wake_all_obj(dev, event);
+	try_wake_any_event(event);
+	if (pulse)
+		event->u.event.signaled = false;
+
+	ntsync_unlock_obj(dev, event, all);
+
+	if (put_user(prev_state, (__u32 __user *)argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ntsync_event_reset(struct ntsync_obj *event, void __user *argp)
+{
+	struct ntsync_device *dev = event->dev;
+	__u32 prev_state;
+	bool all;
+
+	if (event->type != NTSYNC_TYPE_EVENT)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, event);
+
+	prev_state = event->u.event.signaled;
+	event->u.event.signaled = false;
+
+	ntsync_unlock_obj(dev, event, all);
+
+	if (put_user(prev_state, (__u32 __user *)argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ntsync_sem_read(struct ntsync_obj *sem, void __user *argp)
+{
+	struct ntsync_sem_args __user *user_args = argp;
+	struct ntsync_device *dev = sem->dev;
+	struct ntsync_sem_args args;
+	bool all;
+
+	if (sem->type != NTSYNC_TYPE_SEM)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, sem);
+
+	args.count = sem->u.sem.count;
+	args.max = sem->u.sem.max;
+
+	ntsync_unlock_obj(dev, sem, all);
+
+	if (copy_to_user(user_args, &args, sizeof(args)))
+		return -EFAULT;
+	return 0;
+}
 
+static int ntsync_mutex_read(struct ntsync_obj *mutex, void __user *argp)
+{
+	struct ntsync_mutex_args __user *user_args = argp;
+	struct ntsync_device *dev = mutex->dev;
+	struct ntsync_mutex_args args;
+	bool all;
+	int ret;
+
+	if (mutex->type != NTSYNC_TYPE_MUTEX)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, mutex);
+
+	args.count = mutex->u.mutex.count;
+	args.owner = mutex->u.mutex.owner;
+	ret = mutex->u.mutex.ownerdead ? -EOWNERDEAD : 0;
+
+	ntsync_unlock_obj(dev, mutex, all);
+
+	if (copy_to_user(user_args, &args, sizeof(args)))
+		return -EFAULT;
+	return ret;
+}
+
+static int ntsync_event_read(struct ntsync_obj *event, void __user *argp)
+{
+	struct ntsync_event_args __user *user_args = argp;
+	struct ntsync_device *dev = event->dev;
+	struct ntsync_event_args args;
+	bool all;
+
+	if (event->type != NTSYNC_TYPE_EVENT)
+		return -EINVAL;
+
+	all = ntsync_lock_obj(dev, event);
+
+	args.manual = event->u.event.manual;
+	args.signaled = event->u.event.signaled;
+
+	ntsync_unlock_obj(dev, event, all);
+
+	if (copy_to_user(user_args, &args, sizeof(args)))
+		return -EFAULT;
+	return 0;
+}
+
+static void ntsync_free_obj(struct ntsync_obj *obj)
+{
 	fput(obj->dev->file);
 	kfree(obj);
+}
 
+static int ntsync_obj_release(struct inode *inode, struct file *file)
+{
+	ntsync_free_obj(file->private_data);
 	return 0;
 }
 
@@ -114,8 +670,24 @@ static long ntsync_obj_ioctl(struct file *file, unsigned int cmd,
 	void __user *argp = (void __user *)parm;
 
 	switch (cmd) {
-	case NTSYNC_IOC_SEM_POST:
-		return ntsync_sem_post(obj, argp);
+	case NTSYNC_IOC_SEM_RELEASE:
+		return ntsync_sem_release(obj, argp);
+	case NTSYNC_IOC_SEM_READ:
+		return ntsync_sem_read(obj, argp);
+	case NTSYNC_IOC_MUTEX_UNLOCK:
+		return ntsync_mutex_unlock(obj, argp);
+	case NTSYNC_IOC_MUTEX_KILL:
+		return ntsync_mutex_kill(obj, argp);
+	case NTSYNC_IOC_MUTEX_READ:
+		return ntsync_mutex_read(obj, argp);
+	case NTSYNC_IOC_EVENT_SET:
+		return ntsync_event_set(obj, argp, false);
+	case NTSYNC_IOC_EVENT_RESET:
+		return ntsync_event_reset(obj, argp);
+	case NTSYNC_IOC_EVENT_PULSE:
+		return ntsync_event_set(obj, argp, true);
+	case NTSYNC_IOC_EVENT_READ:
+		return ntsync_event_read(obj, argp);
 	default:
 		return -ENOIOCTLCMD;
 	}
@@ -140,6 +712,9 @@ static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev,
 	obj->dev = dev;
 	get_file(dev->file);
 	spin_lock_init(&obj->lock);
+	INIT_LIST_HEAD(&obj->any_waiters);
+	INIT_LIST_HEAD(&obj->all_waiters);
+	atomic_set(&obj->all_hint, 0);
 
 	return obj;
 }
@@ -165,7 +740,6 @@ static int ntsync_obj_get_fd(struct ntsync_obj *obj)
 
 static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp)
 {
-	struct ntsync_sem_args __user *user_args = argp;
 	struct ntsync_sem_args args;
 	struct ntsync_obj *sem;
 	int fd;
@@ -182,12 +756,398 @@ static int ntsync_create_sem(struct ntsync_device *dev, void __user *argp)
 	sem->u.sem.count = args.count;
 	sem->u.sem.max = args.max;
 	fd = ntsync_obj_get_fd(sem);
-	if (fd < 0) {
-		kfree(sem);
-		return fd;
+	if (fd < 0)
+		ntsync_free_obj(sem);
+
+	return fd;
+}
+
+static int ntsync_create_mutex(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_mutex_args args;
+	struct ntsync_obj *mutex;
+	int fd;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	if (!args.owner != !args.count)
+		return -EINVAL;
+
+	mutex = ntsync_alloc_obj(dev, NTSYNC_TYPE_MUTEX);
+	if (!mutex)
+		return -ENOMEM;
+	mutex->u.mutex.count = args.count;
+	mutex->u.mutex.owner = args.owner;
+	fd = ntsync_obj_get_fd(mutex);
+	if (fd < 0)
+		ntsync_free_obj(mutex);
+
+	return fd;
+}
+
+static int ntsync_create_event(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_event_args args;
+	struct ntsync_obj *event;
+	int fd;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	event = ntsync_alloc_obj(dev, NTSYNC_TYPE_EVENT);
+	if (!event)
+		return -ENOMEM;
+	event->u.event.manual = args.manual;
+	event->u.event.signaled = args.signaled;
+	fd = ntsync_obj_get_fd(event);
+	if (fd < 0)
+		ntsync_free_obj(event);
+
+	return fd;
+}
+
+static struct ntsync_obj *get_obj(struct ntsync_device *dev, int fd)
+{
+	struct file *file = fget(fd);
+	struct ntsync_obj *obj;
+
+	if (!file)
+		return NULL;
+
+	if (file->f_op != &ntsync_obj_fops) {
+		fput(file);
+		return NULL;
+	}
+
+	obj = file->private_data;
+	if (obj->dev != dev) {
+		fput(file);
+		return NULL;
 	}
 
-	return put_user(fd, &user_args->sem);
+	return obj;
+}
+
+static void put_obj(struct ntsync_obj *obj)
+{
+	fput(obj->file);
+}
+
+static int ntsync_schedule(const struct ntsync_q *q, const struct ntsync_wait_args *args)
+{
+	ktime_t timeout = ns_to_ktime(args->timeout);
+	clockid_t clock = CLOCK_MONOTONIC;
+	ktime_t *timeout_ptr;
+	int ret = 0;
+
+	timeout_ptr = (args->timeout == U64_MAX ? NULL : &timeout);
+
+	if (args->flags & NTSYNC_WAIT_REALTIME)
+		clock = CLOCK_REALTIME;
+
+	do {
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (atomic_read(&q->signaled) != -1) {
+			ret = 0;
+			break;
+		}
+		ret = schedule_hrtimeout_range_clock(timeout_ptr, 0, HRTIMER_MODE_ABS, clock);
+	} while (ret < 0);
+	__set_current_state(TASK_RUNNING);
+
+	return ret;
+}
+
+/*
+ * Allocate and initialize the ntsync_q structure, but do not queue us yet.
+ */
+static int setup_wait(struct ntsync_device *dev,
+		      const struct ntsync_wait_args *args, bool all,
+		      struct ntsync_q **ret_q)
+{
+	int fds[NTSYNC_MAX_WAIT_COUNT + 1];
+	const __u32 count = args->count;
+	struct ntsync_q *q;
+	__u32 total_count;
+	__u32 i, j;
+
+	if (args->pad || (args->flags & ~NTSYNC_WAIT_REALTIME))
+		return -EINVAL;
+
+	if (args->count > NTSYNC_MAX_WAIT_COUNT)
+		return -EINVAL;
+
+	total_count = count;
+	if (args->alert)
+		total_count++;
+
+	if (copy_from_user(fds, u64_to_user_ptr(args->objs),
+			   array_size(count, sizeof(*fds))))
+		return -EFAULT;
+	if (args->alert)
+		fds[count] = args->alert;
+
+	q = kmalloc(struct_size(q, entries, total_count), GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+	q->task = current;
+	q->owner = args->owner;
+	atomic_set(&q->signaled, -1);
+	q->all = all;
+	q->ownerdead = false;
+	q->count = count;
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = get_obj(dev, fds[i]);
+
+		if (!obj)
+			goto err;
+
+		if (all) {
+			/* Check that the objects are all distinct. */
+			for (j = 0; j < i; j++) {
+				if (obj == q->entries[j].obj) {
+					put_obj(obj);
+					goto err;
+				}
+			}
+		}
+
+		entry->obj = obj;
+		entry->q = q;
+		entry->index = i;
+	}
+
+	*ret_q = q;
+	return 0;
+
+err:
+	for (j = 0; j < i; j++)
+		put_obj(q->entries[j].obj);
+	kfree(q);
+	return -EINVAL;
+}
+
+static void try_wake_any_obj(struct ntsync_obj *obj)
+{
+	switch (obj->type) {
+	case NTSYNC_TYPE_SEM:
+		try_wake_any_sem(obj);
+		break;
+	case NTSYNC_TYPE_MUTEX:
+		try_wake_any_mutex(obj);
+		break;
+	case NTSYNC_TYPE_EVENT:
+		try_wake_any_event(obj);
+		break;
+	}
+}
+
+static int ntsync_wait_any(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_wait_args args;
+	__u32 i, total_count;
+	struct ntsync_q *q;
+	int signaled;
+	bool all;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	ret = setup_wait(dev, &args, false, &q);
+	if (ret < 0)
+		return ret;
+
+	total_count = args.count;
+	if (args.alert)
+		total_count++;
+
+	/* queue ourselves */
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		all = ntsync_lock_obj(dev, obj);
+		list_add_tail(&entry->node, &obj->any_waiters);
+		ntsync_unlock_obj(dev, obj, all);
+	}
+
+	/*
+	 * Check if we are already signaled.
+	 *
+	 * Note that the API requires that normal objects are checked before
+	 * the alert event. Hence we queue the alert event last, and check
+	 * objects in order.
+	 */
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_obj *obj = q->entries[i].obj;
+
+		if (atomic_read(&q->signaled) != -1)
+			break;
+
+		all = ntsync_lock_obj(dev, obj);
+		try_wake_any_obj(obj);
+		ntsync_unlock_obj(dev, obj, all);
+	}
+
+	/* sleep */
+
+	ret = ntsync_schedule(q, &args);
+
+	/* and finally, unqueue */
+
+	for (i = 0; i < total_count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		all = ntsync_lock_obj(dev, obj);
+		list_del(&entry->node);
+		ntsync_unlock_obj(dev, obj, all);
+
+		put_obj(obj);
+	}
+
+	signaled = atomic_read(&q->signaled);
+	if (signaled != -1) {
+		struct ntsync_wait_args __user *user_args = argp;
+
+		/* even if we caught a signal, we need to communicate success */
+		ret = q->ownerdead ? -EOWNERDEAD : 0;
+
+		if (put_user(signaled, &user_args->index))
+			ret = -EFAULT;
+	} else if (!ret) {
+		ret = -ETIMEDOUT;
+	}
+
+	kfree(q);
+	return ret;
+}
+
+static int ntsync_wait_all(struct ntsync_device *dev, void __user *argp)
+{
+	struct ntsync_wait_args args;
+	struct ntsync_q *q;
+	int signaled;
+	__u32 i;
+	int ret;
+
+	if (copy_from_user(&args, argp, sizeof(args)))
+		return -EFAULT;
+
+	ret = setup_wait(dev, &args, true, &q);
+	if (ret < 0)
+		return ret;
+
+	/* queue ourselves */
+
+	mutex_lock(&dev->wait_all_lock);
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		atomic_inc(&obj->all_hint);
+
+		/*
+		 * obj->all_waiters is protected by dev->wait_all_lock rather
+		 * than obj->lock, so there is no need to acquire obj->lock
+		 * here.
+		 */
+		list_add_tail(&entry->node, &obj->all_waiters);
+	}
+	if (args.alert) {
+		struct ntsync_q_entry *entry = &q->entries[args.count];
+		struct ntsync_obj *obj = entry->obj;
+
+		dev_lock_obj(dev, obj);
+		list_add_tail(&entry->node, &obj->any_waiters);
+		dev_unlock_obj(dev, obj);
+	}
+
+	/* check if we are already signaled */
+
+	try_wake_all(dev, q, NULL);
+
+	mutex_unlock(&dev->wait_all_lock);
+
+	/*
+	 * Check if the alert event is signaled, making sure to do so only
+	 * after checking if the other objects are signaled.
+	 */
+
+	if (args.alert) {
+		struct ntsync_obj *obj = q->entries[args.count].obj;
+
+		if (atomic_read(&q->signaled) == -1) {
+			bool all = ntsync_lock_obj(dev, obj);
+			try_wake_any_obj(obj);
+			ntsync_unlock_obj(dev, obj, all);
+		}
+	}
+
+	/* sleep */
+
+	ret = ntsync_schedule(q, &args);
+
+	/* and finally, unqueue */
+
+	mutex_lock(&dev->wait_all_lock);
+
+	for (i = 0; i < args.count; i++) {
+		struct ntsync_q_entry *entry = &q->entries[i];
+		struct ntsync_obj *obj = entry->obj;
+
+		/*
+		 * obj->all_waiters is protected by dev->wait_all_lock rather
+		 * than obj->lock, so there is no need to acquire it here.
+		 */
+		list_del(&entry->node);
+
+		atomic_dec(&obj->all_hint);
+
+		put_obj(obj);
+	}
+
+	mutex_unlock(&dev->wait_all_lock);
+
+	if (args.alert) {
+		struct ntsync_q_entry *entry = &q->entries[args.count];
+		struct ntsync_obj *obj = entry->obj;
+		bool all;
+
+		all = ntsync_lock_obj(dev, obj);
+		list_del(&entry->node);
+		ntsync_unlock_obj(dev, obj, all);
+
+		put_obj(obj);
+	}
+
+	signaled = atomic_read(&q->signaled);
+	if (signaled != -1) {
+		struct ntsync_wait_args __user *user_args = argp;
+
+		/* even if we caught a signal, we need to communicate success */
+		ret = q->ownerdead ? -EOWNERDEAD : 0;
+
+		if (put_user(signaled, &user_args->index))
+			ret = -EFAULT;
+	} else if (!ret) {
+		ret = -ETIMEDOUT;
+	}
+
+	kfree(q);
+	return ret;
 }
 
 static int ntsync_char_open(struct inode *inode, struct file *file)
@@ -198,6 +1158,8 @@ static int ntsync_char_open(struct inode *inode, struct file *file)
 	if (!dev)
 		return -ENOMEM;
 
+	mutex_init(&dev->wait_all_lock);
+
 	file->private_data = dev;
 	dev->file = file;
 	return nonseekable_open(inode, file);
@@ -219,8 +1181,16 @@ static long ntsync_char_ioctl(struct file *file, unsigned int cmd,
 	void __user *argp = (void __user *)parm;
 
 	switch (cmd) {
+	case NTSYNC_IOC_CREATE_EVENT:
+		return ntsync_create_event(dev, argp);
+	case NTSYNC_IOC_CREATE_MUTEX:
+		return ntsync_create_mutex(dev, argp);
 	case NTSYNC_IOC_CREATE_SEM:
 		return ntsync_create_sem(dev, argp);
+	case NTSYNC_IOC_WAIT_ALL:
+		return ntsync_wait_all(dev, argp);
+	case NTSYNC_IOC_WAIT_ANY:
+		return ntsync_wait_any(dev, argp);
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c
index 07520d6e6dc5..e849641687a0 100644
--- a/drivers/misc/ocxl/sysfs.c
+++ b/drivers/misc/ocxl/sysfs.c
@@ -94,7 +94,7 @@ static struct device_attribute afu_attrs[] = {
 };
 
 static ssize_t global_mmio_read(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
+				const struct bin_attribute *bin_attr, char *buf,
 				loff_t off, size_t count)
 {
 	struct ocxl_afu *afu = to_afu(kobj_to_dev(kobj));
@@ -155,7 +155,7 @@ int ocxl_sysfs_register_afu(struct ocxl_file_info *info)
 	info->attr_global_mmio.attr.name = "global_mmio_area";
 	info->attr_global_mmio.attr.mode = 0600;
 	info->attr_global_mmio.size = info->afu->config.global_mmio_size;
-	info->attr_global_mmio.read = global_mmio_read;
+	info->attr_global_mmio.read_new = global_mmio_read;
 	info->attr_global_mmio.mmap = global_mmio_mmap;
 	rc = device_create_bin_file(&info->dev, &info->attr_global_mmio);
 	if (rc) {
diff --git a/drivers/misc/pch_phub.c b/drivers/misc/pch_phub.c
index 8d2b7135738e..6121c0940cd1 100644
--- a/drivers/misc/pch_phub.c
+++ b/drivers/misc/pch_phub.c
@@ -483,7 +483,7 @@ static int pch_phub_write_gbe_mac_addr(struct pch_phub_reg *chip, u8 *data)
 }
 
 static ssize_t pch_phub_bin_read(struct file *filp, struct kobject *kobj,
-				 struct bin_attribute *attr, char *buf,
+				 const struct bin_attribute *attr, char *buf,
 				 loff_t off, size_t count)
 {
 	unsigned int rom_signature;
@@ -553,7 +553,7 @@ return_err_nomutex:
 }
 
 static ssize_t pch_phub_bin_write(struct file *filp, struct kobject *kobj,
-				  struct bin_attribute *attr,
+				  const struct bin_attribute *attr,
 				  char *buf, loff_t off, size_t count)
 {
 	int err;
@@ -655,8 +655,8 @@ static const struct bin_attribute pch_bin_attr = {
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	.size = PCH_PHUB_OROM_SIZE + 1,
-	.read = pch_phub_bin_read,
-	.write = pch_phub_bin_write,
+	.read_new = pch_phub_bin_read,
+	.write_new = pch_phub_bin_write,
 };
 
 static int pch_phub_probe(struct pci_dev *pdev,
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index 61b66e318488..7a3c34306de9 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -93,7 +93,7 @@ int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT;
 static int xpc_disengage_min_timelimit;	/* = 0 */
 static int xpc_disengage_max_timelimit = 120;
 
-static struct ctl_table xpc_sys_xpc_hb[] = {
+static const struct ctl_table xpc_sys_xpc_hb[] = {
 	{
 	 .procname = "hb_interval",
 	 .data = &xpc_hb_interval,
@@ -111,7 +111,7 @@ static struct ctl_table xpc_sys_xpc_hb[] = {
 	 .extra1 = &xpc_hb_check_min_interval,
 	 .extra2 = &xpc_hb_check_max_interval},
 };
-static struct ctl_table xpc_sys_xpc[] = {
+static const struct ctl_table xpc_sys_xpc[] = {
 	{
 	 .procname = "disengage_timelimit",
 	 .data = &xpc_disengage_timelimit,
diff --git a/drivers/misc/sram.c b/drivers/misc/sram.c
index e40b027a88e2..e5069882457e 100644
--- a/drivers/misc/sram.c
+++ b/drivers/misc/sram.c
@@ -23,7 +23,7 @@
 #define SRAM_GRANULARITY	32
 
 static ssize_t sram_read(struct file *filp, struct kobject *kobj,
-			 struct bin_attribute *attr,
+			 const struct bin_attribute *attr,
 			 char *buf, loff_t pos, size_t count)
 {
 	struct sram_partition *part;
@@ -38,7 +38,7 @@ static ssize_t sram_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t sram_write(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *attr,
+			  const struct bin_attribute *attr,
 			  char *buf, loff_t pos, size_t count)
 {
 	struct sram_partition *part;
@@ -83,8 +83,8 @@ static int sram_add_export(struct sram_dev *sram, struct sram_reserve *block,
 		return -ENOMEM;
 
 	part->battr.attr.mode = S_IRUSR | S_IWUSR;
-	part->battr.read = sram_read;
-	part->battr.write = sram_write;
+	part->battr.read_new = sram_read;
+	part->battr.write_new = sram_write;
 	part->battr.size = block->size;
 
 	return device_create_bin_file(sram->dev, &part->battr);
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index ee7e1d908986..847c11542f02 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -404,6 +404,7 @@ out_list_del:
 int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old)
 {
 	unsigned long flags;
+	unsigned int memflags;
 
 	lockdep_assert_held(&mtd_table_mutex);
 
@@ -420,10 +421,10 @@ int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old)
 	spin_unlock_irqrestore(&old->queue_lock, flags);
 
 	/* freeze+quiesce queue to ensure all requests are flushed */
-	blk_mq_freeze_queue(old->rq);
+	memflags = blk_mq_freeze_queue(old->rq);
 	blk_mq_quiesce_queue(old->rq);
 	blk_mq_unquiesce_queue(old->rq);
-	blk_mq_unfreeze_queue(old->rq);
+	blk_mq_unfreeze_queue(old->rq, memflags);
 
 	/* If the device is currently open, tell trans driver to close it,
 		then put mtd device, and don't touch it again */
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index 30be4ed68fad..ef6a22f372f9 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -1537,7 +1537,7 @@ static int ubi_mtd_param_parse(const char *val, const struct kernel_param *kp)
 	if (token) {
 		int err = kstrtoint(token, 10, &p->ubi_num);
 
-		if (err) {
+		if (err || p->ubi_num < UBI_DEV_NUM_AUTO) {
 			pr_err("UBI error: bad value for ubi_num parameter: %s\n",
 			       token);
 			return -EINVAL;
diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c
index 6bb80d7714bc..b700a0efaa93 100644
--- a/drivers/mtd/ubi/cdev.c
+++ b/drivers/mtd/ubi/cdev.c
@@ -828,6 +828,70 @@ out_free:
 	return err;
 }
 
+static int ubi_get_ec_info(struct ubi_device *ubi, struct ubi_ecinfo_req __user *ureq)
+{
+	struct ubi_ecinfo_req req;
+	struct ubi_wl_entry *wl;
+	int read_cnt;
+	int peb;
+	int end_peb;
+
+	/* Copy the input arguments */
+	if (copy_from_user(&req, ureq, sizeof(struct ubi_ecinfo_req)))
+		return -EFAULT;
+
+	/* Check input arguments */
+	if (req.length <= 0 || req.start < 0 || req.start >= ubi->peb_count)
+		return -EINVAL;
+
+	if (check_add_overflow(req.start, req.length, &end_peb))
+		return -EINVAL;
+
+	if (end_peb > ubi->peb_count)
+		end_peb = ubi->peb_count;
+
+	/* Check access rights before filling erase_counters array */
+	if (!access_ok((void __user *)ureq->erase_counters,
+		       (end_peb-req.start) * sizeof(int32_t)))
+		return -EFAULT;
+
+	/* Fill erase counter array */
+	read_cnt = 0;
+	for (peb = req.start; peb < end_peb; read_cnt++, peb++) {
+		int ec;
+
+		if (ubi_io_is_bad(ubi, peb)) {
+			if (__put_user(UBI_UNKNOWN, ureq->erase_counters+read_cnt))
+				return -EFAULT;
+
+			continue;
+		}
+
+		spin_lock(&ubi->wl_lock);
+
+		wl = ubi->lookuptbl[peb];
+		if (wl)
+			ec = wl->ec;
+		else
+			ec = UBI_UNKNOWN;
+
+		spin_unlock(&ubi->wl_lock);
+
+		if (__put_user(ec, ureq->erase_counters+read_cnt))
+			return -EFAULT;
+
+	}
+
+	/* Return actual read length */
+	req.read_length = read_cnt;
+
+	/* Copy everything except erase counter array */
+	if (copy_to_user(ureq, &req, sizeof(struct ubi_ecinfo_req)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static long ubi_cdev_ioctl(struct file *file, unsigned int cmd,
 			   unsigned long arg)
 {
@@ -991,6 +1055,12 @@ static long ubi_cdev_ioctl(struct file *file, unsigned int cmd,
 		break;
 	}
 
+	case UBI_IOCECNFO:
+	{
+		err = ubi_get_ec_info(ubi, argp);
+		break;
+	}
+
 	default:
 		err = -ENOTTY;
 		break;
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 26cc53ad34ec..c792b9bcab9b 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -549,7 +549,6 @@ struct ubi_debug_info {
  * @peb_buf: a buffer of PEB size used for different purposes
  * @buf_mutex: protects @peb_buf
  * @ckvol_mutex: serializes static volume checking when opening
- * @wl_reboot_notifier: close all wear-leveling work before reboot
  *
  * @dbg: debugging information for this UBI device
  */
@@ -652,7 +651,6 @@ struct ubi_device {
 	void *peb_buf;
 	struct mutex buf_mutex;
 	struct mutex ckvol_mutex;
-	struct notifier_block wl_reboot_notifier;
 
 	struct ubi_debug_info dbg;
 };
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 4f6f339d8fb8..fbd399cf6503 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -89,7 +89,6 @@
 #include <linux/crc32.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
-#include <linux/reboot.h>
 #include "ubi.h"
 #include "wl.h"
 
@@ -128,8 +127,6 @@ static int self_check_in_wl_tree(const struct ubi_device *ubi,
 				 struct ubi_wl_entry *e, struct rb_root *root);
 static int self_check_in_pq(const struct ubi_device *ubi,
 			    struct ubi_wl_entry *e);
-static int ubi_wl_reboot_notifier(struct notifier_block *n,
-				  unsigned long state, void *cmd);
 
 /**
  * wl_tree_add - add a wear-leveling entry to a WL RB-tree.
@@ -1953,13 +1950,6 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 	if (!ubi->ro_mode && !ubi->fm_disabled)
 		ubi_ensure_anchor_pebs(ubi);
 #endif
-
-	if (!ubi->wl_reboot_notifier.notifier_call) {
-		ubi->wl_reboot_notifier.notifier_call = ubi_wl_reboot_notifier;
-		ubi->wl_reboot_notifier.priority = 1; /* Higher than MTD */
-		register_reboot_notifier(&ubi->wl_reboot_notifier);
-	}
-
 	return 0;
 
 out_free:
@@ -2005,17 +1995,6 @@ void ubi_wl_close(struct ubi_device *ubi)
 	kfree(ubi->lookuptbl);
 }
 
-static int ubi_wl_reboot_notifier(struct notifier_block *n,
-				  unsigned long state, void *cmd)
-{
-	struct ubi_device *ubi;
-
-	ubi = container_of(n, struct ubi_device, wl_reboot_notifier);
-	ubi_wl_close(ubi);
-
-	return NOTIFY_DONE;
-}
-
 /**
  * self_check_ec - make sure that the erase counter of a PEB is correct.
  * @ubi: UBI device description object
diff --git a/drivers/mux/core.c b/drivers/mux/core.c
index 78c0022697ec..02be4ba37257 100644
--- a/drivers/mux/core.c
+++ b/drivers/mux/core.c
@@ -42,7 +42,7 @@ struct mux_state {
 	unsigned int state;
 };
 
-static struct class mux_class = {
+static const struct class mux_class = {
 	.name = "mux",
 };
 
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index b19492a7f6ad..8adbec7c5084 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -63,13 +63,8 @@ void bond_debug_unregister(struct bonding *bond)
 
 void bond_debug_reregister(struct bonding *bond)
 {
-	struct dentry *d;
-
-	d = debugfs_rename(bonding_debug_root, bond->debug_dir,
-			   bonding_debug_root, bond->dev->name);
-	if (!IS_ERR(d)) {
-		bond->debug_dir = d;
-	} else {
+	int err = debugfs_change_name(bond->debug_dir, "%s", bond->dev->name);
+	if (err) {
 		netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n");
 		bond_debug_unregister(bond);
 	}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7b78c2bada81..e45bba240cbc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1538,17 +1538,20 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 				 NETIF_F_HIGHDMA | NETIF_F_LRO)
 
 #define BOND_ENC_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
-				 NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE)
+				 NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \
+				 NETIF_F_GSO_PARTIAL)
 
 #define BOND_MPLS_FEATURES	(NETIF_F_HW_CSUM | NETIF_F_SG | \
 				 NETIF_F_GSO_SOFTWARE)
 
+#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP)
+
 
 static void bond_compute_features(struct bonding *bond)
 {
+	netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES;
 	unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE |
 					IFF_XMIT_DST_RELEASE_PERM;
-	netdev_features_t gso_partial_features = NETIF_F_GSO_ESP;
 	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
 	netdev_features_t enc_features  = BOND_ENC_FEATURES;
 #ifdef CONFIG_XFRM_OFFLOAD
@@ -1582,8 +1585,9 @@ static void bond_compute_features(struct bonding *bond)
 							  BOND_XFRM_FEATURES);
 #endif /* CONFIG_XFRM_OFFLOAD */
 
-		if (slave->dev->hw_enc_features & NETIF_F_GSO_PARTIAL)
-			gso_partial_features &= slave->dev->gso_partial_features;
+		gso_partial_features = netdev_increment_features(gso_partial_features,
+								 slave->dev->gso_partial_features,
+								 BOND_GSO_PARTIAL_FEATURES);
 
 		mpls_features = netdev_increment_features(mpls_features,
 							  slave->dev->mpls_features,
@@ -1598,12 +1602,8 @@ static void bond_compute_features(struct bonding *bond)
 	}
 	bond_dev->hard_header_len = max_hard_header_len;
 
-	if (gso_partial_features & NETIF_F_GSO_ESP)
-		bond_dev->gso_partial_features |= NETIF_F_GSO_ESP;
-	else
-		bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP;
-
 done:
+	bond_dev->gso_partial_features = gso_partial_features;
 	bond_dev->vlan_features = vlan_features;
 	bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
 				    NETIF_F_HW_VLAN_CTAG_TX |
@@ -6046,6 +6046,7 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL;
 	bond_dev->features |= bond_dev->hw_features;
 	bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	bond_dev->features |= NETIF_F_GSO_PARTIAL;
 #ifdef CONFIG_XFRM_OFFLOAD
 	bond_dev->hw_features |= BOND_XFRM_FEATURES;
 	/* Only enable XFRM features if this is an active-backup config */
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
index b0a6c96b6ef4..b35808d3d07f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -505,21 +505,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata)
 
 void xgbe_debugfs_rename(struct xgbe_prv_data *pdata)
 {
-	char *buf;
-
-	if (!pdata->xgbe_debugfs)
-		return;
-
-	buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name);
-	if (!buf)
-		return;
-
-	if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf))
-		goto out;
-
-	debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs,
-		       pdata->xgbe_debugfs->d_parent, buf);
-
-out:
-	kfree(buf);
+	debugfs_change_name(pdata->xgbe_debugfs,
+			    "amd-xgbe-%s", pdata->netdev->name);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index fe0e3e2a8117..71e50fc65c14 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -1441,7 +1441,9 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down)
 	aq_ptp_ring_free(self);
 	aq_ptp_free(self);
 
-	if (likely(self->aq_fw_ops->deinit) && link_down) {
+	/* May be invoked during hot unplug. */
+	if (pci_device_is_present(self->pdev) &&
+	    likely(self->aq_fw_ops->deinit) && link_down) {
 		mutex_lock(&self->fwreq_mutex);
 		self->aq_fw_ops->deinit(self->aq_hw);
 		mutex_unlock(&self->fwreq_mutex);
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index d73ef262991d..6fee9a41839c 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -328,8 +328,7 @@
 #define BGMAC_RX_FRAME_OFFSET			30		/* There are 2 unused bytes between header and real data */
 #define BGMAC_RX_BUF_OFFSET			(NET_SKB_PAD + NET_IP_ALIGN - \
 						 BGMAC_RX_FRAME_OFFSET)
-/* Jumbo frame size with FCS */
-#define BGMAC_RX_MAX_FRAME_SIZE			9724
+#define BGMAC_RX_MAX_FRAME_SIZE			1536
 #define BGMAC_RX_BUF_SIZE			(BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE)
 #define BGMAC_RX_ALLOC_SIZE			(SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE + BGMAC_RX_BUF_OFFSET) + \
 						 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 0715ea5bf13e..3b082114f2e5 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -41,9 +41,12 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
+	u32 phy_wolopts = 0;
 
-	if (dev->phydev)
+	if (dev->phydev) {
 		phy_ethtool_get_wol(dev->phydev, wol);
+		phy_wolopts = wol->wolopts;
+	}
 
 	/* MAC is not wake-up capable, return what the PHY does */
 	if (!device_can_wakeup(kdev))
@@ -51,9 +54,14 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	/* Overlay MAC capabilities with that of the PHY queried before */
 	wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
-	wol->wolopts = priv->wolopts;
-	memset(wol->sopass, 0, sizeof(wol->sopass));
+	wol->wolopts |= priv->wolopts;
 
+	/* Return the PHY configured magic password */
+	if (phy_wolopts & WAKE_MAGICSECURE)
+		return;
+
+	/* Otherwise the MAC one */
+	memset(wol->sopass, 0, sizeof(wol->sopass));
 	if (wol->wolopts & WAKE_MAGICSECURE)
 		memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
@@ -70,7 +78,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	/* Try Wake-on-LAN from the PHY first */
 	if (dev->phydev) {
 		ret = phy_ethtool_set_wol(dev->phydev, wol);
-		if (ret != -EOPNOTSUPP)
+		if (ret != -EOPNOTSUPP && wol->wolopts)
 			return ret;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 9cc8db10a8d6..d9d675f1ebfe 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -55,6 +55,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/crc32poly.h>
+#include <linux/dmi.h>
 
 #include <net/checksum.h>
 #include <net/gso.h>
@@ -7424,7 +7425,7 @@ static void tg3_napi_enable(struct tg3 *tp)
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		tnapi = &tp->napi[i];
-		napi_enable(&tnapi->napi);
+		napi_enable_locked(&tnapi->napi);
 		if (tnapi->tx_buffers) {
 			netif_queue_set_napi(tp->dev, txq_idx,
 					     NETDEV_QUEUE_TYPE_TX,
@@ -7445,9 +7446,10 @@ static void tg3_napi_init(struct tg3 *tp)
 	int i;
 
 	for (i = 0; i < tp->irq_cnt; i++) {
-		netif_napi_add(tp->dev, &tp->napi[i].napi,
-			       i ? tg3_poll_msix : tg3_poll);
-		netif_napi_set_irq(&tp->napi[i].napi, tp->napi[i].irq_vec);
+		netif_napi_add_locked(tp->dev, &tp->napi[i].napi,
+				      i ? tg3_poll_msix : tg3_poll);
+		netif_napi_set_irq_locked(&tp->napi[i].napi,
+					  tp->napi[i].irq_vec);
 	}
 }
 
@@ -11259,6 +11261,8 @@ static void tg3_timer_stop(struct tg3 *tp)
 static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 	__releases(tp->lock)
 	__acquires(tp->lock)
+	__releases(tp->dev->lock)
+	__acquires(tp->dev->lock)
 {
 	int err;
 
@@ -11271,7 +11275,9 @@ static int tg3_restart_hw(struct tg3 *tp, bool reset_phy)
 		tg3_timer_stop(tp);
 		tp->irq_sync = 0;
 		tg3_napi_enable(tp);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
+		netdev_lock(tp->dev);
 		tg3_full_lock(tp, 0);
 	}
 	return err;
@@ -11299,6 +11305,7 @@ static void tg3_reset_task(struct work_struct *work)
 
 	tg3_netif_stop(tp);
 
+	netdev_lock(tp->dev);
 	tg3_full_lock(tp, 1);
 
 	if (tg3_flag(tp, TX_RECOVERY_PENDING)) {
@@ -11318,12 +11325,14 @@ static void tg3_reset_task(struct work_struct *work)
 		 * call cancel_work_sync() and wait forever.
 		 */
 		tg3_flag_clear(tp, RESET_TASK_PENDING);
+		netdev_unlock(tp->dev);
 		dev_close(tp->dev);
 		goto out;
 	}
 
 	tg3_netif_start(tp);
 	tg3_full_unlock(tp);
+	netdev_unlock(tp->dev);
 	tg3_phy_start(tp);
 	tg3_flag_clear(tp, RESET_TASK_PENDING);
 out:
@@ -11683,9 +11692,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq,
 	if (err)
 		goto out_ints_fini;
 
+	netdev_lock(dev);
 	tg3_napi_init(tp);
 
 	tg3_napi_enable(tp);
+	netdev_unlock(dev);
 
 	for (i = 0; i < tp->irq_cnt; i++) {
 		err = tg3_request_irq(tp, i);
@@ -12569,6 +12580,7 @@ static int tg3_set_ringparam(struct net_device *dev,
 		irq_sync = 1;
 	}
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, irq_sync);
 
 	tp->rx_pending = ering->rx_pending;
@@ -12597,6 +12609,7 @@ static int tg3_set_ringparam(struct net_device *dev,
 	}
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (irq_sync && !err)
 		tg3_phy_start(tp);
@@ -12678,6 +12691,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 			irq_sync = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, irq_sync);
 
 		if (epause->autoneg)
@@ -12707,6 +12721,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 	}
 
 	tp->phy_flags |= TG3_PHYFLG_USER_CONFIGURED;
@@ -13911,6 +13926,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 			data[TG3_INTERRUPT_TEST] = 1;
 		}
 
+		netdev_lock(dev);
 		tg3_full_lock(tp, 0);
 
 		tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -13922,6 +13938,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest,
 		}
 
 		tg3_full_unlock(tp);
+		netdev_unlock(dev);
 
 		if (irq_sync && !err2)
 			tg3_phy_start(tp);
@@ -14365,6 +14382,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 
 	tg3_set_mtu(dev, tp, new_mtu);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 1);
 
 	tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
@@ -14384,6 +14402,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
 		tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18164,6 +18183,7 @@ static int tg3_resume(struct device *device)
 
 	netif_device_attach(dev);
 
+	netdev_lock(dev);
 	tg3_full_lock(tp, 0);
 
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
@@ -18180,6 +18200,7 @@ static int tg3_resume(struct device *device)
 
 out:
 	tg3_full_unlock(tp);
+	netdev_unlock(dev);
 
 	if (!err)
 		tg3_phy_start(tp);
@@ -18192,6 +18213,50 @@ unlock:
 
 static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
 
+/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal
+ * PCIe AER event on the tg3 device if the tg3 device is not, or cannot
+ * be, powered down.
+ */
+static const struct dmi_system_id tg3_restart_aer_quirk_table[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"),
+		},
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"),
+		},
+	},
+	{}
+};
+
 static void tg3_shutdown(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
@@ -18208,6 +18273,19 @@ static void tg3_shutdown(struct pci_dev *pdev)
 
 	if (system_state == SYSTEM_POWER_OFF)
 		tg3_power_down(tp);
+	else if (system_state == SYSTEM_RESTART &&
+		 dmi_first_match(tg3_restart_aer_quirk_table) &&
+		 pdev->current_state != PCI_D3cold &&
+		 pdev->current_state != PCI_UNKNOWN) {
+		/* Disable PCIe AER on the tg3 to avoid a fatal
+		 * error during this system restart.
+		 */
+		pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL,
+					   PCI_EXP_DEVCTL_CERE |
+					   PCI_EXP_DEVCTL_NFERE |
+					   PCI_EXP_DEVCTL_FERE |
+					   PCI_EXP_DEVCTL_URRE);
+	}
 
 	rtnl_unlock();
 
@@ -18260,7 +18338,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
 done:
 	if (state == pci_channel_io_perm_failure) {
 		if (netdev) {
+			netdev_lock(netdev);
 			tg3_napi_enable(tp);
+			netdev_unlock(netdev);
 			dev_close(netdev);
 		}
 		err = PCI_ERS_RESULT_DISCONNECT;
@@ -18314,7 +18394,9 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev)
 
 done:
 	if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) {
+		netdev_lock(netdev);
 		tg3_napi_enable(tp);
+		netdev_unlock(netdev);
 		dev_close(netdev);
 	}
 	rtnl_unlock();
@@ -18340,12 +18422,14 @@ static void tg3_io_resume(struct pci_dev *pdev)
 	if (!netdev || !netif_running(netdev))
 		goto done;
 
+	netdev_lock(netdev);
 	tg3_full_lock(tp, 0);
 	tg3_ape_driver_state_change(tp, RESET_KIND_INIT);
 	tg3_flag_set(tp, INIT_COMPLETE);
 	err = tg3_restart_hw(tp, true);
 	if (err) {
 		tg3_full_unlock(tp);
+		netdev_unlock(netdev);
 		netdev_err(netdev, "Cannot restart hardware after reset.\n");
 		goto done;
 	}
@@ -18357,6 +18441,7 @@ static void tg3_io_resume(struct pci_dev *pdev)
 	tg3_netif_start(tp);
 
 	tg3_full_unlock(tp);
+	netdev_unlock(netdev);
 
 	tg3_phy_start(tp);
 
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 8735e333034c..b87eaf0c250c 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1777,10 +1777,11 @@ static void dm9000_drv_remove(struct platform_device *pdev)
 
 	unregister_netdev(ndev);
 	dm9000_release_board(pdev, dm);
-	free_netdev(ndev);		/* free device structure */
 	if (dm->power_supply)
 		regulator_disable(dm->power_supply);
 
+	free_netdev(ndev);		/* free device structure */
+
 	dev_dbg(&pdev->dev, "released and freed device\n");
 }
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 68725506a095..f7c4ce8e9a26 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -840,6 +840,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int hdr_len, total_len, data_left;
 	struct bufdesc *bdp = txq->bd.cur;
+	struct bufdesc *tmp_bdp;
+	struct bufdesc_ex *ebdp;
 	struct tso_t tso;
 	unsigned int index = 0;
 	int ret;
@@ -913,7 +915,34 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	return 0;
 
 err_release:
-	/* TODO: Release all used data descriptors for TSO */
+	/* Release all used data descriptors for TSO */
+	tmp_bdp = txq->bd.cur;
+
+	while (tmp_bdp != bdp) {
+		/* Unmap data buffers */
+		if (tmp_bdp->cbd_bufaddr &&
+		    !IS_TSO_HEADER(txq, fec32_to_cpu(tmp_bdp->cbd_bufaddr)))
+			dma_unmap_single(&fep->pdev->dev,
+					 fec32_to_cpu(tmp_bdp->cbd_bufaddr),
+					 fec16_to_cpu(tmp_bdp->cbd_datlen),
+					 DMA_TO_DEVICE);
+
+		/* Clear standard buffer descriptor fields */
+		tmp_bdp->cbd_sc = 0;
+		tmp_bdp->cbd_datlen = 0;
+		tmp_bdp->cbd_bufaddr = 0;
+
+		/* Handle extended descriptor if enabled */
+		if (fep->bufdesc_ex) {
+			ebdp = (struct bufdesc_ex *)tmp_bdp;
+			ebdp->cbd_esc = 0;
+		}
+
+		tmp_bdp = fec_enet_get_nextdesc(tmp_bdp, &txq->bd);
+	}
+
+	dev_kfree_skb_any(skb);
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 9a63fbc69408..b25fb400f476 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare);
  */
 static DEFINE_MUTEX(hnae3_common_lock);
 
+/* ensure the drivers being unloaded one by one */
+static DEFINE_MUTEX(hnae3_unload_lock);
+
+void hnae3_acquire_unload_lock(void)
+{
+	mutex_lock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_acquire_unload_lock);
+
+void hnae3_release_unload_lock(void)
+{
+	mutex_unlock(&hnae3_unload_lock);
+}
+EXPORT_SYMBOL(hnae3_release_unload_lock);
+
 static bool hnae3_client_match(enum hnae3_client_type client_type)
 {
 	if (client_type == HNAE3_CLIENT_KNIC ||
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 12ba380eb701..4e44f28288f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -963,4 +963,6 @@ int hnae3_register_client(struct hnae3_client *client);
 void hnae3_set_client_init_flag(struct hnae3_client *client,
 				struct hnae3_ae_dev *ae_dev,
 				unsigned int inited);
+void hnae3_acquire_unload_lock(void);
+void hnae3_release_unload_lock(void);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index a7e3b22f641c..9ff797fb36c4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -6002,9 +6002,11 @@ module_init(hns3_init_module);
  */
 static void __exit hns3_exit_module(void)
 {
+	hnae3_acquire_unload_lock();
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
 	hns3_dbg_unregister_debugfs();
+	hnae3_release_unload_lock();
 }
 module_exit(hns3_exit_module);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index db7845009252..3f17b3073e50 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -12919,9 +12919,11 @@ static int __init hclge_init(void)
 
 static void __exit hclge_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo_prepare(&ae_algo);
 	hnae3_unregister_ae_algo(&ae_algo);
 	destroy_workqueue(hclge_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclge_init);
 module_exit(hclge_exit);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 163c6e59ea4c..9ba767740a04 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -3410,8 +3410,10 @@ static int __init hclgevf_init(void)
 
 static void __exit hclgevf_exit(void)
 {
+	hnae3_acquire_unload_lock();
 	hnae3_unregister_ae_algo(&ae_algovf);
 	destroy_workqueue(hclgevf_wq);
+	hnae3_release_unload_lock();
 }
 module_init(hclgevf_init);
 module_exit(hclgevf_exit);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index cbfaaa5b7d02..2d7a18fcc3be 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -773,6 +773,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter,
 		f->state = IAVF_VLAN_ADD;
 		adapter->num_vlan_filters++;
 		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER);
+	} else if (f->state == IAVF_VLAN_REMOVE) {
+		/* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed.
+		 * We can safely only change the state here.
+		 */
+		f->state = IAVF_VLAN_ACTIVE;
 	}
 
 clearout:
@@ -793,8 +798,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan)
 
 	f = iavf_find_vlan(adapter, vlan);
 	if (f) {
-		f->state = IAVF_VLAN_REMOVE;
-		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		/* IAVF_ADD_VLAN means that VLAN wasn't even added yet.
+		 * Remove it from the list.
+		 */
+		if (f->state == IAVF_VLAN_ADD) {
+			list_del(&f->list);
+			kfree(f);
+			adapter->num_vlan_filters--;
+		} else {
+			f->state = IAVF_VLAN_REMOVE;
+			iavf_schedule_aq_request(adapter,
+						 IAVF_FLAG_AQ_DEL_VLAN_FILTER);
+		}
 	}
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index d116e2b10bce..dbdb83567364 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -981,6 +981,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv
 
 	/* preallocate memory for ice_sched_node */
 	node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL);
+	if (!node)
+		return -ENOMEM;
+
 	*priv = node;
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 01536a382e54..bdee499f991a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -1498,7 +1498,6 @@ struct ice_aqc_dnl_equa_param {
 #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT)
-#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT)
 #define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT)
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 3072634bf049..f241493a6ac8 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -710,7 +710,6 @@ static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num,
 		{ ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 },
 		{ ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf },
 		{ ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf },
-		{ ICE_AQC_RX_EQU_DRATE, rx, &ptr->rx_equ_drate },
 		{ ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf },
 		{ ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf },
 		{ ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc },
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h
index 8f2ad1c172c0..23b2cfbc9684 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.h
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h
@@ -15,7 +15,6 @@ struct ice_serdes_equalization_to_ethtool {
 	int rx_equ_post1;
 	int rx_equ_bflf;
 	int rx_equ_bfhf;
-	int rx_equ_drate;
 	int rx_equ_ctle_gainhf;
 	int rx_equ_ctle_gainlf;
 	int rx_equ_ctle_gaindc;
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 6509d807627c..4f56d53d56b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size,
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
 #define ICE_BST_TCAM_TABLE_SIZE		256
 #define ICE_BST_TCAM_KEY_SIZE		20
-#define ICE_BST_KEY_TCAM_SIZE		19
 
 /* Boost TCAM item */
 struct ice_bst_tcam_item {
@@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag);
 #define ICE_PARSER_GPR_NUM	128
 #define ICE_PARSER_FLG_NUM	64
 #define ICE_PARSER_ERR_NUM	16
-#define ICE_BST_KEY_SIZE	10
 #define ICE_MARKER_ID_SIZE	9
 #define ICE_MARKER_MAX_SIZE	\
 		(ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1)
@@ -431,13 +429,13 @@ struct ice_parser_rt {
 	u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV];
 	u16 pkt_len;
 	u16 po;
-	u8 bst_key[ICE_BST_KEY_SIZE];
+	u8 bst_key[ICE_BST_TCAM_KEY_SIZE];
 	struct ice_pg_cam_key pg_key;
+	u8 pg_prio;
 	struct ice_alu *alu0;
 	struct ice_alu *alu1;
 	struct ice_alu *alu2;
 	struct ice_pg_cam_action *action;
-	u8 pg_prio;
 	struct ice_gpr_pu pu;
 	u8 markers[ICE_MARKER_ID_SIZE];
 	bool protocols[ICE_PO_PAIR_SIZE];
diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
index dedf5e854e4b..3995d662e050 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
@@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt,
 	else
 		key[idd] = imem->b_kb.prio;
 
-	idd = ICE_BST_KEY_TCAM_SIZE - 1;
+	idd = ICE_BST_TCAM_KEY_SIZE - 2;
 	for (i = idd; i >= 0; i--) {
 		int j;
 
 		j = ho + idd - i;
 		if (j < ICE_PARSER_MAX_PKT_LEN)
-			key[i] = rt->pkt_buf[ho + idd - i];
+			key[i] = rt->pkt_buf[j];
 		else
 			key[i] = 0;
 	}
 
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n");
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
-		  key[0], key[1], key[2], key[3], key[4],
-		  key[5], key[6], key[7], key[8], key[9]);
-	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n");
+	ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER,
+				 KBUILD_MODNAME ": Generated Boost TCAM Key",
+				 key, ICE_BST_TCAM_KEY_SIZE);
 }
 
 static u16 ice_bit_rev_u16(u16 v, int len)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 5d2d7736fd5f..9c9ea4c1b93b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -527,15 +527,14 @@ err:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
- * @rx_buf: Rx buffer to store the XDP action
  * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
-static void
+static u32
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
+	    union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -574,7 +573,7 @@ out_failure:
 		ret = ICE_XDP_CONSUMED;
 	}
 exit:
-	ice_set_rx_bufs_act(xdp, rx_ring, ret);
+	return ret;
 }
 
 /**
@@ -860,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		xdp_buff_set_frags_flag(xdp);
 	}
 
-	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) {
-		ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED);
+	if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS))
 		return -ENOMEM;
-	}
 
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
@@ -924,7 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 	struct ice_rx_buf *rx_buf;
 
 	rx_buf = &rx_ring->rx_buf[ntc];
-	rx_buf->pgcnt = page_count(rx_buf->page);
 	prefetchw(rx_buf->page);
 
 	if (!size)
@@ -941,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 }
 
 /**
+ * ice_get_pgcnts - grab page_count() for gathered fragments
+ * @rx_ring: Rx descriptor ring to store the page counts on
+ *
+ * This function is intended to be called right before running XDP
+ * program so that the page recycling mechanism will be able to take
+ * a correct decision regarding underlying pages; this is done in such
+ * way as XDP program can change the refcount of page
+ */
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+{
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
+	struct ice_rx_buf *rx_buf;
+	u32 cnt = rx_ring->count;
+
+	for (int i = 0; i < nr_frags; i++) {
+		rx_buf = &rx_ring->rx_buf[idx];
+		rx_buf->pgcnt = page_count(rx_buf->page);
+
+		if (++idx == cnt)
+			idx = 0;
+	}
+}
+
+/**
  * ice_build_skb - Build skb around an existing buffer
  * @rx_ring: Rx descriptor ring to transact packets on
  * @xdp: xdp_buff pointing to the data
@@ -1051,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 				rx_buf->page_offset + headlen, size,
 				xdp->frame_sz);
 	} else {
-		/* buffer is unused, change the act that should be taken later
-		 * on; data was copied onto skb's linear part so there's no
+		/* buffer is unused, restore biased page count in Rx buffer;
+		 * data was copied onto skb's linear part so there's no
 		 * need for adjusting page offset and we can reuse this buffer
 		 * as-is
 		 */
-		rx_buf->act = ICE_SKB_CONSUMED;
+		rx_buf->pagecnt_bias++;
 	}
 
 	if (unlikely(xdp_buff_has_frags(xdp))) {
@@ -1104,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 }
 
 /**
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * @rx_ring: Rx ring with all the auxiliary data
+ * @xdp: XDP buffer carrying linear + frags part
+ * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
+ * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @verdict: return code from XDP program execution
+ *
+ * Walk through gathered fragments and satisfy internal page
+ * recycle mechanism; we take here an action related to verdict
+ * returned by XDP program;
+ */
+static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+			    u32 *xdp_xmit, u32 ntc, u32 verdict)
+{
+	u32 nr_frags = rx_ring->nr_frags + 1;
+	u32 idx = rx_ring->first_desc;
+	u32 cnt = rx_ring->count;
+	u32 post_xdp_frags = 1;
+	struct ice_rx_buf *buf;
+	int i;
+
+	if (unlikely(xdp_buff_has_frags(xdp)))
+		post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+
+	for (i = 0; i < post_xdp_frags; i++) {
+		buf = &rx_ring->rx_buf[idx];
+
+		if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+			*xdp_xmit |= verdict;
+		} else if (verdict & ICE_XDP_CONSUMED) {
+			buf->pagecnt_bias++;
+		} else if (verdict == ICE_XDP_PASS) {
+			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
+		}
+
+		ice_put_rx_buf(rx_ring, buf);
+
+		if (++idx == cnt)
+			idx = 0;
+	}
+	/* handle buffers that represented frags released by XDP prog;
+	 * for these we keep pagecnt_bias as-is; refcount from struct page
+	 * has been decremented within XDP prog and we do not have to increase
+	 * the biased refcnt
+	 */
+	for (; i < nr_frags; i++) {
+		buf = &rx_ring->rx_buf[idx];
+		ice_put_rx_buf(rx_ring, buf);
+		if (++idx == cnt)
+			idx = 0;
+	}
+
+	xdp->data = NULL;
+	rx_ring->first_desc = ntc;
+	rx_ring->nr_frags = 0;
+}
+
+/**
  * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: Rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
@@ -1120,15 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
 	unsigned int offset = rx_ring->rx_offset;
 	struct xdp_buff *xdp = &rx_ring->xdp;
-	u32 cached_ntc = rx_ring->first_desc;
 	struct ice_tx_ring *xdp_ring = NULL;
 	struct bpf_prog *xdp_prog = NULL;
 	u32 ntc = rx_ring->next_to_clean;
+	u32 cached_ntu, xdp_verdict;
 	u32 cnt = rx_ring->count;
 	u32 xdp_xmit = 0;
-	u32 cached_ntu;
 	bool failure;
-	u32 first;
 
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
@@ -1190,6 +1268,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
+			ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
 			break;
 		}
 		if (++ntc == cnt)
@@ -1199,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
-		if (rx_buf->act == ICE_XDP_PASS)
+		ice_get_pgcnts(rx_ring);
+		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
+		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
+		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
 		continue;
 construct_skb:
 		if (likely(ice_ring_uses_build_skb(rx_ring)))
@@ -1217,18 +1296,12 @@ construct_skb:
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
-			rx_buf->act = ICE_XDP_CONSUMED;
-			if (unlikely(xdp_buff_has_frags(xdp)))
-				ice_set_rx_bufs_act(xdp, rx_ring,
-						    ICE_XDP_CONSUMED);
-			xdp->data = NULL;
-			rx_ring->first_desc = ntc;
-			rx_ring->nr_frags = 0;
-			break;
+			xdp_verdict = ICE_XDP_CONSUMED;
 		}
-		xdp->data = NULL;
-		rx_ring->first_desc = ntc;
-		rx_ring->nr_frags = 0;
+		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+
+		if (!skb)
+			break;
 
 		stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S);
 		if (unlikely(ice_test_staterr(rx_desc->wb.status_error0,
@@ -1257,23 +1330,6 @@ construct_skb:
 		total_rx_pkts++;
 	}
 
-	first = rx_ring->first_desc;
-	while (cached_ntc != first) {
-		struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc];
-
-		if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			xdp_xmit |= buf->act;
-		} else if (buf->act & ICE_XDP_CONSUMED) {
-			buf->pagecnt_bias++;
-		} else if (buf->act == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
-
-		ice_put_rx_buf(rx_ring, buf);
-		if (++cached_ntc >= cnt)
-			cached_ntc = 0;
-	}
 	rx_ring->next_to_clean = ntc;
 	/* return up to cleaned_count buffers to hardware */
 	failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring));
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index cb347c852ba9..806bce701df3 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -201,7 +201,6 @@ struct ice_rx_buf {
 	struct page *page;
 	unsigned int page_offset;
 	unsigned int pgcnt;
-	unsigned int act;
 	unsigned int pagecnt_bias;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 79f960c6680d..6cf32b404127 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -6,49 +6,6 @@
 #include "ice.h"
 
 /**
- * ice_set_rx_bufs_act - propagate Rx buffer action to frags
- * @xdp: XDP buffer representing frame (linear and frags part)
- * @rx_ring: Rx ring struct
- * act: action to store onto Rx buffers related to XDP buffer parts
- *
- * Set action that should be taken before putting Rx buffer from first frag
- * to the last.
- */
-static inline void
-ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring,
-		    const unsigned int act)
-{
-	u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
-	u32 nr_frags = rx_ring->nr_frags + 1;
-	u32 idx = rx_ring->first_desc;
-	u32 cnt = rx_ring->count;
-	struct ice_rx_buf *buf;
-
-	for (int i = 0; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		buf->act = act;
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-
-	/* adjust pagecnt_bias on frags freed by XDP prog */
-	if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) {
-		u32 delta = rx_ring->nr_frags - sinfo_frags;
-
-		while (delta) {
-			if (idx == 0)
-				idx = cnt - 1;
-			else
-				idx--;
-			buf = &rx_ring->rx_buf[idx];
-			buf->pagecnt_bias--;
-			delta--;
-		}
-	}
-}
-
-/**
  * ice_test_staterr - tests bits in Rx descriptor status and error fields
  * @status_err_n: Rx descriptor status_error0 or status_error1 bits
  * @stat_err_bits: value to mask
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
index 4849590a5591..b28991dd1870 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
@@ -376,6 +376,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 		if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		/* strip off FW internal code */
 		desc_err = le16_to_cpu(desc->ret_val) & 0xff;
 
@@ -563,6 +566,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 		if (!(flags & IDPF_CTLQ_FLAG_DD))
 			break;
 
+		/* Ensure no other fields are read until DD flag is checked */
+		dma_rmb();
+
 		q_msg[i].vmvf_type = (flags &
 				      (IDPF_CTLQ_FLAG_FTYPE_VM |
 				       IDPF_CTLQ_FLAG_FTYPE_PF)) >>
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index f71d3182580b..b6c515d14cbf 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -174,7 +174,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, adapter);
 
-	adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0,
+	adapter->init_wq = alloc_workqueue("%s-%s-init",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->init_wq) {
@@ -183,7 +184,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
-	adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0,
+	adapter->serv_wq = alloc_workqueue("%s-%s-service",
+					   WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					   dev_driver_string(dev),
 					   dev_name(dev));
 	if (!adapter->serv_wq) {
@@ -192,7 +194,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_serv_wq_alloc;
 	}
 
-	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0,
+	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx",
+					  WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					  dev_driver_string(dev),
 					  dev_name(dev));
 	if (!adapter->mbx_wq) {
@@ -201,7 +204,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_mbx_wq_alloc;
 	}
 
-	adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0,
+	adapter->stats_wq = alloc_workqueue("%s-%s-stats",
+					    WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					    dev_driver_string(dev),
 					    dev_name(dev));
 	if (!adapter->stats_wq) {
@@ -210,7 +214,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_stats_wq_alloc;
 	}
 
-	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0,
+	adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event",
+					       WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
 					       dev_driver_string(dev),
 					       dev_name(dev));
 	if (!adapter->vc_event_wq) {
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index d46c95f91b0d..3d2413b8684f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -517,8 +517,10 @@ static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
 		retval = -ENXIO;
 		goto only_unlock;
 	case IDPF_VC_XN_WAITING:
-		dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n",
-				       params->vc_op, params->timeout_ms);
+		dev_notice_ratelimited(&adapter->pdev->dev,
+				       "Transaction timed-out (op:%d cookie:%04x vc_op:%d salt:%02x timeout:%dms)\n",
+				       params->vc_op, cookie, xn->vc_op,
+				       xn->salt, params->timeout_ms);
 		retval = -ETIME;
 		break;
 	case IDPF_VC_XN_COMPLETED_SUCCESS:
@@ -612,14 +614,16 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter,
 		return -EINVAL;
 	}
 	xn = &adapter->vcxn_mngr->ring[xn_idx];
+	idpf_vc_xn_lock(xn);
 	salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info);
 	if (xn->salt != salt) {
-		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n",
-				    xn->salt, salt);
+		dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (exp:%d@%02x(%d) != got:%d@%02x)\n",
+				    xn->vc_op, xn->salt, xn->state,
+				    ctlq_msg->cookie.mbx.chnl_opcode, salt);
+		idpf_vc_xn_unlock(xn);
 		return -EINVAL;
 	}
 
-	idpf_vc_xn_lock(xn);
 	switch (xn->state) {
 	case IDPF_VC_XN_WAITING:
 		/* success */
@@ -3077,12 +3081,21 @@ init_failed:
  */
 void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 {
+	bool remove_in_prog;
+
 	if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags))
 		return;
 
+	/* Avoid transaction timeouts when called during reset */
+	remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags);
+	if (!remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
 	idpf_deinit_task(adapter);
 	idpf_intr_rel(adapter);
-	idpf_vc_xn_shutdown(adapter->vcxn_mngr);
+
+	if (remove_in_prog)
+		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
 
 	cancel_delayed_work_sync(&adapter->serv_task);
 	cancel_delayed_work_sync(&adapter->mbx_task);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 82f4333fb426..4fe121b9f94b 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4432,6 +4432,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 	 */
 	if (pp->is_stopped) {
 		spin_unlock(&pp->lock);
+		netdev_unlock(port->napi.dev);
 		return 0;
 	}
 	netif_tx_stop_all_queues(pp->dev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 148144f5b61d..a1f9ec03c2ce 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -917,19 +917,18 @@ static void print_npa_qsize(struct seq_file *m, struct rvu_pfvf *pfvf)
 /* The 'qsize' entry dumps current Aura/Pool context Qsize
  * and each context's current enable/disable status in a bitmap.
  */
-static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused,
+static int rvu_dbg_qsize_display(struct seq_file *s, void *unsused,
 				 int blktype)
 {
-	void (*print_qsize)(struct seq_file *filp,
+	void (*print_qsize)(struct seq_file *s,
 			    struct rvu_pfvf *pfvf) = NULL;
-	struct dentry *current_dir;
 	struct rvu_pfvf *pfvf;
 	struct rvu *rvu;
 	int qsize_id;
 	u16 pcifunc;
 	int blkaddr;
 
-	rvu = filp->private;
+	rvu = s->private;
 	switch (blktype) {
 	case BLKTYPE_NPA:
 		qsize_id = rvu->rvu_dbg.npa_qsize_id;
@@ -945,32 +944,28 @@ static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused,
 		return -EINVAL;
 	}
 
-	if (blktype == BLKTYPE_NPA) {
+	if (blktype == BLKTYPE_NPA)
 		blkaddr = BLKADDR_NPA;
-	} else {
-		current_dir = filp->file->f_path.dentry->d_parent;
-		blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
-				   BLKADDR_NIX1 : BLKADDR_NIX0);
-	}
+	else
+		blkaddr = debugfs_get_aux_num(s->file);
 
 	if (!rvu_dbg_is_valid_lf(rvu, blkaddr, qsize_id, &pcifunc))
 		return -EINVAL;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
-	print_qsize(filp, pfvf);
+	print_qsize(s, pfvf);
 
 	return 0;
 }
 
-static ssize_t rvu_dbg_qsize_write(struct file *filp,
+static ssize_t rvu_dbg_qsize_write(struct file *file,
 				   const char __user *buffer, size_t count,
 				   loff_t *ppos, int blktype)
 {
 	char *blk_string = (blktype == BLKTYPE_NPA) ? "npa" : "nix";
-	struct seq_file *seqfile = filp->private_data;
+	struct seq_file *seqfile = file->private_data;
 	char *cmd_buf, *cmd_buf_tmp, *subtoken;
 	struct rvu *rvu = seqfile->private;
-	struct dentry *current_dir;
 	int blkaddr;
 	u16 pcifunc;
 	int ret, lf;
@@ -996,13 +991,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp,
 		goto qsize_write_done;
 	}
 
-	if (blktype == BLKTYPE_NPA) {
+	if (blktype == BLKTYPE_NPA)
 		blkaddr = BLKADDR_NPA;
-	} else {
-		current_dir = filp->f_path.dentry->d_parent;
-		blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ?
-				   BLKADDR_NIX1 : BLKADDR_NIX0);
-	}
+	else
+		blkaddr = debugfs_get_aux_num(file);
 
 	if (!rvu_dbg_is_valid_lf(rvu, blkaddr, lf, &pcifunc)) {
 		ret = -EINVAL;
@@ -2704,8 +2696,8 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr)
 			    &rvu_dbg_nix_ndc_tx_hits_miss_fops);
 	debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_ndc_rx_hits_miss_fops);
-	debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu,
-			    &rvu_dbg_nix_qsize_fops);
+	debugfs_create_file_aux_num("qsize", 0600, rvu->rvu_dbg.nix, rvu,
+			    blkaddr, &rvu_dbg_nix_qsize_fops);
 	debugfs_create_file("ingress_policer_ctx", 0600, rvu->rvu_dbg.nix, nix_hw,
 			    &rvu_dbg_nix_band_prof_ctx_fops);
 	debugfs_create_file("ingress_policer_rsrc", 0600, rvu->rvu_dbg.nix, nix_hw,
@@ -2854,28 +2846,14 @@ static int cgx_print_stats(struct seq_file *s, int lmac_id)
 	return err;
 }
 
-static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id)
+static int rvu_dbg_derive_lmacid(struct seq_file *s)
 {
-	struct dentry *current_dir;
-	char *buf;
-
-	current_dir = filp->file->f_path.dentry->d_parent;
-	buf = strrchr(current_dir->d_name.name, 'c');
-	if (!buf)
-		return -EINVAL;
-
-	return kstrtoint(buf + 1, 10, lmac_id);
+	return debugfs_get_aux_num(s->file);
 }
 
-static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_cgx_stat_display(struct seq_file *s, void *unused)
 {
-	int lmac_id, err;
-
-	err = rvu_dbg_derive_lmacid(filp, &lmac_id);
-	if (!err)
-		return cgx_print_stats(filp, lmac_id);
-
-	return err;
+	return cgx_print_stats(s, rvu_dbg_derive_lmacid(s));
 }
 
 RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL);
@@ -2933,15 +2911,9 @@ static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id)
 	return 0;
 }
 
-static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *s, void *unused)
 {
-	int err, lmac_id;
-
-	err = rvu_dbg_derive_lmacid(filp, &lmac_id);
-	if (!err)
-		return cgx_print_dmac_flt(filp, lmac_id);
-
-	return err;
+	return cgx_print_dmac_flt(s, rvu_dbg_derive_lmacid(s));
 }
 
 RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL);
@@ -2980,10 +2952,10 @@ static void rvu_dbg_cgx_init(struct rvu *rvu)
 			rvu->rvu_dbg.lmac =
 				debugfs_create_dir(dname, rvu->rvu_dbg.cgx);
 
-			debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac,
-					    cgx, &rvu_dbg_cgx_stat_fops);
-			debugfs_create_file("mac_filter", 0600,
-					    rvu->rvu_dbg.lmac, cgx,
+			debugfs_create_file_aux_num("stats", 0600, rvu->rvu_dbg.lmac,
+					    cgx, lmac_id, &rvu_dbg_cgx_stat_fops);
+			debugfs_create_file_aux_num("mac_filter", 0600,
+					    rvu->rvu_dbg.lmac, cgx, lmac_id,
 					    &rvu_dbg_cgx_dmac_flt_fops);
 		}
 	}
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 25bf6ec44289..a1bada9eaaf6 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -3742,10 +3742,7 @@ static int skge_device_event(struct notifier_block *unused,
 	skge = netdev_priv(dev);
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (skge->debugfs)
-			skge->debugfs = debugfs_rename(skge_debug,
-						       skge->debugfs,
-						       skge_debug, dev->name);
+		debugfs_change_name(skge->debugfs, "%s", dev->name);
 		break;
 
 	case NETDEV_GOING_DOWN:
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 988fa28cfb5f..d7121c836508 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4494,10 +4494,7 @@ static int sky2_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (sky2->debugfs) {
-			sky2->debugfs = debugfs_rename(sky2_debug, sky2->debugfs,
-						       sky2_debug, dev->name);
-		}
+		debugfs_change_name(sky2->debugfs, "%s", dev->name);
 		break;
 
 	case NETDEV_GOING_DOWN:
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 415d784de741..09f448f29124 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -266,11 +266,11 @@
 #define REG_GDM3_FWD_CFG		GDM3_BASE
 #define GDM3_PAD_EN_MASK		BIT(28)
 
-#define REG_GDM4_FWD_CFG		(GDM4_BASE + 0x100)
+#define REG_GDM4_FWD_CFG		GDM4_BASE
 #define GDM4_PAD_EN_MASK		BIT(28)
 #define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
 
-#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x33c)
+#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x23c)
 #define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
 #define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
 #define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bd41b75d246e..a814b63ed97e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2087,7 +2087,7 @@ static struct mlx5e_xdpsq *mlx5e_open_xdpredirect_sq(struct mlx5e_channel *c,
 	struct mlx5e_xdpsq *xdpsq;
 	int err;
 
-	xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, c->cpu);
+	xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!xdpsq)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 720f577929db..499e5e39d513 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1120,20 +1120,6 @@ static void nv_disable_hw_interrupts(struct net_device *dev, u32 mask)
 	}
 }
 
-static void nv_napi_enable(struct net_device *dev)
-{
-	struct fe_priv *np = get_nvpriv(dev);
-
-	napi_enable(&np->napi);
-}
-
-static void nv_napi_disable(struct net_device *dev)
-{
-	struct fe_priv *np = get_nvpriv(dev);
-
-	napi_disable(&np->napi);
-}
-
 #define MII_READ	(-1)
 /* mii_rw: read/write a register on the PHY.
  *
@@ -3114,7 +3100,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu)
 		 * Changing the MTU is a rare event, it shouldn't matter.
 		 */
 		nv_disable_irq(dev);
-		nv_napi_disable(dev);
+		napi_disable(&np->napi);
 		netif_tx_lock_bh(dev);
 		netif_addr_lock(dev);
 		spin_lock(&np->lock);
@@ -3143,7 +3129,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu)
 		spin_unlock(&np->lock);
 		netif_addr_unlock(dev);
 		netif_tx_unlock_bh(dev);
-		nv_napi_enable(dev);
+		napi_enable(&np->napi);
 		nv_enable_irq(dev);
 	}
 	return 0;
@@ -4731,7 +4717,7 @@ static int nv_set_ringparam(struct net_device *dev,
 
 	if (netif_running(dev)) {
 		nv_disable_irq(dev);
-		nv_napi_disable(dev);
+		napi_disable(&np->napi);
 		netif_tx_lock_bh(dev);
 		netif_addr_lock(dev);
 		spin_lock(&np->lock);
@@ -4784,7 +4770,7 @@ static int nv_set_ringparam(struct net_device *dev,
 		spin_unlock(&np->lock);
 		netif_addr_unlock(dev);
 		netif_tx_unlock_bh(dev);
-		nv_napi_enable(dev);
+		napi_enable(&np->napi);
 		nv_enable_irq(dev);
 	}
 	return 0;
@@ -5277,7 +5263,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
 		if (netif_running(dev)) {
 			netif_stop_queue(dev);
-			nv_napi_disable(dev);
+			napi_disable(&np->napi);
 			netif_tx_lock_bh(dev);
 			netif_addr_lock(dev);
 			spin_lock_irq(&np->lock);
@@ -5334,7 +5320,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64
 			/* restart rx engine */
 			nv_start_rxtx(dev);
 			netif_start_queue(dev);
-			nv_napi_enable(dev);
+			napi_enable(&np->napi);
 			nv_enable_hw_interrupts(dev, np->irqmask);
 		}
 	}
@@ -5576,6 +5562,7 @@ static int nv_open(struct net_device *dev)
 	/* ask for interrupts */
 	nv_enable_hw_interrupts(dev, np->irqmask);
 
+	netdev_lock(dev);
 	spin_lock_irq(&np->lock);
 	writel(NVREG_MCASTADDRA_FORCE, base + NvRegMulticastAddrA);
 	writel(0, base + NvRegMulticastAddrB);
@@ -5594,7 +5581,7 @@ static int nv_open(struct net_device *dev)
 	ret = nv_update_linkspeed(dev);
 	nv_start_rxtx(dev);
 	netif_start_queue(dev);
-	nv_napi_enable(dev);
+	napi_enable_locked(&np->napi);
 
 	if (ret) {
 		netif_carrier_on(dev);
@@ -5611,6 +5598,7 @@ static int nv_open(struct net_device *dev)
 			round_jiffies(jiffies + STATS_INTERVAL));
 
 	spin_unlock_irq(&np->lock);
+	netdev_unlock(dev);
 
 	/* If the loopback feature was set while the device was down, make sure
 	 * that it's set correctly now.
@@ -5632,7 +5620,7 @@ static int nv_close(struct net_device *dev)
 	spin_lock_irq(&np->lock);
 	np->in_shutdown = 1;
 	spin_unlock_irq(&np->lock);
-	nv_napi_disable(dev);
+	napi_disable(&np->napi);
 	synchronize_irq(np->pci_dev->irq);
 
 	del_timer_sync(&np->oom_kick);
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 9ce0e8a64ba8..a73dcaffa8c5 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -1684,6 +1684,7 @@ static void rtl8139_tx_timeout_task (struct work_struct *work)
 	if (tmp8 & CmdTxEnb)
 		RTL_W8 (ChipCmd, CmdRxEnb);
 
+	netdev_lock(dev);
 	spin_lock_bh(&tp->rx_lock);
 	/* Disable interrupts by clearing the interrupt mask. */
 	RTL_W16 (IntrMask, 0x0000);
@@ -1694,11 +1695,12 @@ static void rtl8139_tx_timeout_task (struct work_struct *work)
 	spin_unlock_irq(&tp->lock);
 
 	/* ...and finally, reset everything */
-	napi_enable(&tp->napi);
+	napi_enable_locked(&tp->napi);
 	rtl8139_hw_start(dev);
 	netif_wake_queue(dev);
 
 	spin_unlock_bh(&tp->rx_lock);
+	netdev_unlock(dev);
 }
 
 static void rtl8139_tx_timeout(struct net_device *dev, unsigned int txqueue)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index bc395294a32d..c9f4976a3527 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -3217,10 +3217,15 @@ static int ravb_suspend(struct device *dev)
 
 	netif_device_detach(ndev);
 
-	if (priv->wol_enabled)
-		return ravb_wol_setup(ndev);
+	rtnl_lock();
+	if (priv->wol_enabled) {
+		ret = ravb_wol_setup(ndev);
+		rtnl_unlock();
+		return ret;
+	}
 
 	ret = ravb_close(ndev);
+	rtnl_unlock();
 	if (ret)
 		return ret;
 
@@ -3245,19 +3250,20 @@ static int ravb_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
+	rtnl_lock();
 	/* If WoL is enabled restore the interface. */
-	if (priv->wol_enabled) {
+	if (priv->wol_enabled)
 		ret = ravb_wol_restore(ndev);
-		if (ret)
-			return ret;
-	} else {
+	else
 		ret = pm_runtime_force_resume(dev);
-		if (ret)
-			return ret;
+	if (ret) {
+		rtnl_unlock();
+		return ret;
 	}
 
 	/* Reopening the interface will restore the device to the working state. */
 	ret = ravb_open(ndev);
+	rtnl_unlock();
 	if (ret < 0)
 		goto out_rpm_put;
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 8887b8921009..5fc8027c92c7 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -3494,10 +3494,12 @@ static int sh_eth_suspend(struct device *dev)
 
 	netif_device_detach(ndev);
 
+	rtnl_lock();
 	if (mdp->wol_enabled)
 		ret = sh_eth_wol_setup(ndev);
 	else
 		ret = sh_eth_close(ndev);
+	rtnl_unlock();
 
 	return ret;
 }
@@ -3511,10 +3513,12 @@ static int sh_eth_resume(struct device *dev)
 	if (!netif_running(ndev))
 		return 0;
 
+	rtnl_lock();
 	if (mdp->wol_enabled)
 		ret = sh_eth_wol_restore(ndev);
 	else
 		ret = sh_eth_open(ndev);
+	rtnl_unlock();
 
 	if (ret < 0)
 		return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index edbf8994455d..b34ebb916b89 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6535,11 +6535,7 @@ static int stmmac_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_CHANGENAME:
-		if (priv->dbgfs_dir)
-			priv->dbgfs_dir = debugfs_rename(stmmac_fs_dir,
-							 priv->dbgfs_dir,
-							 stmmac_fs_dir,
-							 dev->name);
+		debugfs_change_name(priv->dbgfs_dir, "%s", dev->name);
 		break;
 	}
 done:
@@ -7221,6 +7217,36 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 	if (priv->dma_cap.tsoen)
 		dev_info(priv->device, "TSO supported\n");
 
+	if (priv->dma_cap.number_rx_queues &&
+	    priv->plat->rx_queues_to_use > priv->dma_cap.number_rx_queues) {
+		dev_warn(priv->device,
+			 "Number of Rx queues (%u) exceeds dma capability\n",
+			 priv->plat->rx_queues_to_use);
+		priv->plat->rx_queues_to_use = priv->dma_cap.number_rx_queues;
+	}
+	if (priv->dma_cap.number_tx_queues &&
+	    priv->plat->tx_queues_to_use > priv->dma_cap.number_tx_queues) {
+		dev_warn(priv->device,
+			 "Number of Tx queues (%u) exceeds dma capability\n",
+			 priv->plat->tx_queues_to_use);
+		priv->plat->tx_queues_to_use = priv->dma_cap.number_tx_queues;
+	}
+
+	if (priv->dma_cap.rx_fifo_size &&
+	    priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) {
+		dev_warn(priv->device,
+			 "Rx FIFO size (%u) exceeds dma capability\n",
+			 priv->plat->rx_fifo_size);
+		priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size;
+	}
+	if (priv->dma_cap.tx_fifo_size &&
+	    priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) {
+		dev_warn(priv->device,
+			 "Tx FIFO size (%u) exceeds dma capability\n",
+			 priv->plat->tx_fifo_size);
+		priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size;
+	}
+
 	priv->hw->vlan_fail_q_en =
 		(priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN);
 	priv->hw->vlan_fail_q = priv->plat->vlan_fail_q;
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index d7459866d24c..72177fea1cfb 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6086,7 +6086,7 @@ static void niu_enable_napi(struct niu *np)
 	int i;
 
 	for (i = 0; i < np->num_ldg; i++)
-		napi_enable(&np->ldg[i].napi);
+		napi_enable_locked(&np->ldg[i].napi);
 }
 
 static void niu_disable_napi(struct niu *np)
@@ -6116,7 +6116,9 @@ static int niu_open(struct net_device *dev)
 	if (err)
 		goto out_free_channels;
 
+	netdev_lock(dev);
 	niu_enable_napi(np);
+	netdev_unlock(dev);
 
 	spin_lock_irq(&np->lock);
 
@@ -6521,6 +6523,7 @@ static void niu_reset_task(struct work_struct *work)
 
 	niu_reset_buffers(np);
 
+	netdev_lock(np->dev);
 	spin_lock_irqsave(&np->lock, flags);
 
 	err = niu_init_hw(np);
@@ -6531,6 +6534,7 @@ static void niu_reset_task(struct work_struct *work)
 	}
 
 	spin_unlock_irqrestore(&np->lock, flags);
+	netdev_unlock(np->dev);
 }
 
 static void niu_tx_timeout(struct net_device *dev, unsigned int txqueue)
@@ -6761,7 +6765,9 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu)
 
 	niu_free_channels(np);
 
+	netdev_lock(dev);
 	niu_enable_napi(np);
+	netdev_unlock(dev);
 
 	err = niu_alloc_channels(np);
 	if (err)
@@ -9937,6 +9943,7 @@ static int __maybe_unused niu_resume(struct device *dev_d)
 
 	spin_lock_irqsave(&np->lock, flags);
 
+	netdev_lock(dev);
 	err = niu_init_hw(np);
 	if (!err) {
 		np->timer.expires = jiffies + HZ;
@@ -9945,6 +9952,7 @@ static int __maybe_unused niu_resume(struct device *dev_d)
 	}
 
 	spin_unlock_irqrestore(&np->lock, flags);
+	netdev_unlock(dev);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 894911f3d560..e56ebbdd428d 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -1568,7 +1568,7 @@ static void init_registers(struct net_device *dev)
 	if (rp->quirks & rqMgmt)
 		rhine_init_cam_filter(dev);
 
-	napi_enable(&rp->napi);
+	napi_enable_locked(&rp->napi);
 
 	iowrite16(RHINE_EVENT & 0xffff, ioaddr + IntrEnable);
 
@@ -1696,7 +1696,10 @@ static int rhine_open(struct net_device *dev)
 	rhine_power_init(dev);
 	rhine_chip_reset(dev);
 	rhine_task_enable(rp);
+
+	netdev_lock(dev);
 	init_registers(dev);
+	netdev_unlock(dev);
 
 	netif_dbg(rp, ifup, dev, "%s() Done - status %04x MII status: %04x\n",
 		  __func__, ioread16(ioaddr + ChipCmd),
@@ -1727,6 +1730,8 @@ static void rhine_reset_task(struct work_struct *work)
 
 	napi_disable(&rp->napi);
 	netif_tx_disable(dev);
+
+	netdev_lock(dev);
 	spin_lock_bh(&rp->lock);
 
 	/* clear all descriptors */
@@ -1740,6 +1745,7 @@ static void rhine_reset_task(struct work_struct *work)
 	init_registers(dev);
 
 	spin_unlock_bh(&rp->lock);
+	netdev_unlock(dev);
 
 	netif_trans_update(dev); /* prevent tx timeout */
 	dev->stats.tx_errors++;
@@ -2541,9 +2547,12 @@ static int rhine_resume(struct device *device)
 	alloc_tbufs(dev);
 	rhine_reset_rbufs(rp);
 	rhine_task_enable(rp);
+
+	netdev_lock(dev);
 	spin_lock_bh(&rp->lock);
 	init_registers(dev);
 	spin_unlock_bh(&rp->lock);
+	netdev_unlock(dev);
 
 	netif_device_attach(dev);
 
diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 3b23f3d3ca2b..5c80fbee7913 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -74,7 +74,7 @@ static void nsim_get_ringparam(struct net_device *dev,
 	memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring));
 	kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX;
 
-	if (kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
+	if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN)
 		kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED;
 }
 
diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c
index 0e58aa7f0374..66b3215db3ac 100644
--- a/drivers/net/netdevsim/hwstats.c
+++ b/drivers/net/netdevsim/hwstats.c
@@ -331,7 +331,6 @@ enum nsim_dev_hwstats_do {
 };
 
 struct nsim_dev_hwstats_fops {
-	const struct file_operations fops;
 	enum nsim_dev_hwstats_do action;
 	enum netdev_offload_xstats_type type;
 };
@@ -342,13 +341,12 @@ nsim_dev_hwstats_do_write(struct file *file,
 			  size_t count, loff_t *ppos)
 {
 	struct nsim_dev_hwstats *hwstats = file->private_data;
-	struct nsim_dev_hwstats_fops *hwsfops;
+	const struct nsim_dev_hwstats_fops *hwsfops;
 	struct list_head *hwsdev_list;
 	int ifindex;
 	int err;
 
-	hwsfops = container_of(debugfs_real_fops(file),
-			       struct nsim_dev_hwstats_fops, fops);
+	hwsfops = debugfs_get_aux(file);
 
 	err = kstrtoint_from_user(data, count, 0, &ifindex);
 	if (err)
@@ -381,14 +379,13 @@ nsim_dev_hwstats_do_write(struct file *file,
 	return count;
 }
 
+static struct debugfs_short_fops debugfs_ops = {
+	.write = nsim_dev_hwstats_do_write,
+	.llseek = generic_file_llseek,
+};
+
 #define NSIM_DEV_HWSTATS_FOPS(ACTION, TYPE)			\
 	{							\
-		.fops = {					\
-			.open = simple_open,			\
-			.write = nsim_dev_hwstats_do_write,	\
-			.llseek = generic_file_llseek,		\
-			.owner = THIS_MODULE,			\
-		},						\
 		.action = ACTION,				\
 		.type = TYPE,					\
 	}
@@ -433,12 +430,12 @@ int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev)
 		goto err_remove_hwstats_recursive;
 	}
 
-	debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats,
-			    &nsim_dev_hwstats_l3_enable_fops.fops);
-	debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats,
-			    &nsim_dev_hwstats_l3_disable_fops.fops);
-	debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats,
-			    &nsim_dev_hwstats_l3_fail_fops.fops);
+	debugfs_create_file_aux("enable_ifindex", 0200, hwstats->l3_ddir, hwstats,
+			    &nsim_dev_hwstats_l3_enable_fops, &debugfs_ops);
+	debugfs_create_file_aux("disable_ifindex", 0200, hwstats->l3_ddir, hwstats,
+			    &nsim_dev_hwstats_l3_disable_fops, &debugfs_ops);
+	debugfs_create_file_aux("fail_next_enable", 0200, hwstats->l3_ddir, hwstats,
+			    &nsim_dev_hwstats_l3_fail_fops, &debugfs_ops);
 
 	INIT_DELAYED_WORK(&hwstats->traffic_dw,
 			  &nsim_dev_hwstats_traffic_work);
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index dcf073bc4802..96d54c08043d 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -134,6 +134,7 @@ struct netdevsim {
 		u32 sleep;
 		u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS];
 		u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS];
+		struct dentry *ddir;
 		struct debugfs_u32_array dfs_ports[2];
 	} udp_ports;
 
diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c
index 02dc3123eb6c..640b4983a9a0 100644
--- a/drivers/net/netdevsim/udp_tunnels.c
+++ b/drivers/net/netdevsim/udp_tunnels.c
@@ -112,9 +112,11 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data,
 	struct net_device *dev = file->private_data;
 	struct netdevsim *ns = netdev_priv(dev);
 
-	memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
 	rtnl_lock();
-	udp_tunnel_nic_reset_ntf(dev);
+	if (dev->reg_state == NETREG_REGISTERED) {
+		memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports));
+		udp_tunnel_nic_reset_ntf(dev);
+	}
 	rtnl_unlock();
 
 	return count;
@@ -144,23 +146,23 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 	else
 		ns->udp_ports.ports = nsim_dev->udp_ports.__ports;
 
-	debugfs_create_u32("udp_ports_inject_error", 0600,
-			   ns->nsim_dev_port->ddir,
+	ns->udp_ports.ddir = debugfs_create_dir("udp_ports",
+						ns->nsim_dev_port->ddir);
+
+	debugfs_create_u32("inject_error", 0600, ns->udp_ports.ddir,
 			   &ns->udp_ports.inject_error);
 
 	ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0];
 	ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS;
-	debugfs_create_u32_array("udp_ports_table0", 0400,
-				 ns->nsim_dev_port->ddir,
+	debugfs_create_u32_array("table0", 0400, ns->udp_ports.ddir,
 				 &ns->udp_ports.dfs_ports[0]);
 
 	ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1];
 	ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS;
-	debugfs_create_u32_array("udp_ports_table1", 0400,
-				 ns->nsim_dev_port->ddir,
+	debugfs_create_u32_array("table1", 0400, ns->udp_ports.ddir,
 				 &ns->udp_ports.dfs_ports[1]);
 
-	debugfs_create_file("udp_ports_reset", 0200, ns->nsim_dev_port->ddir,
+	debugfs_create_file("reset", 0200, ns->udp_ports.ddir,
 			    dev, &nsim_udp_tunnels_info_reset_fops);
 
 	/* Note: it's not normal to allocate the info struct like this!
@@ -196,6 +198,9 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev,
 
 void nsim_udp_tunnels_info_destroy(struct net_device *dev)
 {
+	struct netdevsim *ns = netdev_priv(dev);
+
+	debugfs_remove_recursive(ns->udp_ports.ddir);
 	kfree(dev->udp_tunnel_nic_info);
 	dev->udp_tunnel_nic_info = NULL;
 }
diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 4494b3e39ce2..a3996471a1c9 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -95,6 +95,10 @@
 
 #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF			65246
 
+struct mv88q2xxx_priv {
+	bool enable_temp;
+};
+
 struct mmd_val {
 	int devad;
 	u32 regnum;
@@ -710,17 +714,12 @@ static const struct hwmon_chip_info mv88q2xxx_hwmon_chip_info = {
 
 static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv = phydev->priv;
 	struct device *dev = &phydev->mdio.dev;
 	struct device *hwmon;
 	char *hwmon_name;
-	int ret;
-
-	/* Enable temperature sense */
-	ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_TEMP_SENSOR2,
-			     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
-	if (ret < 0)
-		return ret;
 
+	priv->enable_temp = true;
 	hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev));
 	if (IS_ERR(hwmon_name))
 		return PTR_ERR(hwmon_name);
@@ -743,6 +742,14 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 
 static int mv88q2xxx_probe(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv;
+
+	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	phydev->priv = priv;
+
 	return mv88q2xxx_hwmon_probe(phydev);
 }
 
@@ -810,6 +817,18 @@ static int mv88q222x_revb1_revb2_config_init(struct phy_device *phydev)
 
 static int mv88q222x_config_init(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv = phydev->priv;
+	int ret;
+
+	/* Enable temperature sense */
+	if (priv->enable_temp) {
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     MDIO_MMD_PCS_MV_TEMP_SENSOR2,
+				     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] == PHY_ID_88Q2220_REVB0)
 		return mv88q222x_revb0_config_init(phydev);
 	else
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 323717a4821f..34231b5b9175 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1297,6 +1297,8 @@ static int nxp_c45_soft_reset(struct phy_device *phydev)
 	if (ret)
 		return ret;
 
+	usleep_range(2000, 2050);
+
 	return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
 					 VEND1_DEVICE_CONTROL, ret,
 					 !(ret & DEVICE_CONTROL_RESET), 20000,
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 28624cca91f8..acf96f262488 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -574,18 +574,14 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return ret;
 }
 
-static inline bool tun_capable(struct tun_struct *tun)
+static inline bool tun_not_capable(struct tun_struct *tun)
 {
 	const struct cred *cred = current_cred();
 	struct net *net = dev_net(tun->dev);
 
-	if (ns_capable(net->user_ns, CAP_NET_ADMIN))
-		return 1;
-	if (uid_valid(tun->owner) && uid_eq(cred->euid, tun->owner))
-		return 1;
-	if (gid_valid(tun->group) && in_egroup_p(tun->group))
-		return 1;
-	return 0;
+	return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
+		(gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
+		!ns_capable(net->user_ns, CAP_NET_ADMIN);
 }
 
 static void tun_set_real_num_queues(struct tun_struct *tun)
@@ -2782,7 +2778,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		    !!(tun->flags & IFF_MULTI_QUEUE))
 			return -EINVAL;
 
-		if (!tun_capable(tun))
+		if (tun_not_capable(tun))
 			return -EPERM;
 		err = security_tun_dev_open(tun->security);
 		if (err < 0)
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 46afb95ffabe..a19789b57190 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -61,7 +61,18 @@
 #define IPHETH_USBINTF_PROTO    1
 
 #define IPHETH_IP_ALIGN		2	/* padding at front of URB */
-#define IPHETH_NCM_HEADER_SIZE  (12 + 96) /* NCMH + NCM0 */
+/* On iOS devices, NCM headers in RX have a fixed size regardless of DPE count:
+ * - NTH16 (NCMH): 12 bytes, as per CDC NCM 1.0 spec
+ * - NDP16 (NCM0): 96 bytes, of which
+ *    - NDP16 fixed header: 8 bytes
+ *    - maximum of 22 DPEs (21 datagrams + trailer), 4 bytes each
+ */
+#define IPHETH_NDP16_MAX_DPE	22
+#define IPHETH_NDP16_HEADER_SIZE (sizeof(struct usb_cdc_ncm_ndp16) + \
+				  IPHETH_NDP16_MAX_DPE * \
+				  sizeof(struct usb_cdc_ncm_dpe16))
+#define IPHETH_NCM_HEADER_SIZE	(sizeof(struct usb_cdc_ncm_nth16) + \
+				 IPHETH_NDP16_HEADER_SIZE)
 #define IPHETH_TX_BUF_SIZE      ETH_FRAME_LEN
 #define IPHETH_RX_BUF_SIZE_LEGACY (IPHETH_IP_ALIGN + ETH_FRAME_LEN)
 #define IPHETH_RX_BUF_SIZE_NCM	65536
@@ -207,15 +218,23 @@ static int ipheth_rcvbulk_callback_legacy(struct urb *urb)
 	return ipheth_consume_skb(buf, len, dev);
 }
 
+/* In "NCM mode", the iOS device encapsulates RX (phone->computer) traffic
+ * in NCM Transfer Blocks (similarly to CDC NCM). However, unlike reverse
+ * tethering (handled by the `cdc_ncm` driver), regular tethering is not
+ * compliant with the CDC NCM spec, as the device is missing the necessary
+ * descriptors, and TX (computer->phone) traffic is not encapsulated
+ * at all. Thus `ipheth` implements a very limited subset of the spec with
+ * the sole purpose of parsing RX URBs.
+ */
 static int ipheth_rcvbulk_callback_ncm(struct urb *urb)
 {
 	struct usb_cdc_ncm_nth16 *ncmh;
 	struct usb_cdc_ncm_ndp16 *ncm0;
 	struct usb_cdc_ncm_dpe16 *dpe;
 	struct ipheth_device *dev;
+	u16 dg_idx, dg_len;
 	int retval = -EINVAL;
 	char *buf;
-	int len;
 
 	dev = urb->context;
 
@@ -226,40 +245,42 @@ static int ipheth_rcvbulk_callback_ncm(struct urb *urb)
 
 	ncmh = urb->transfer_buffer;
 	if (ncmh->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN) ||
-	    le16_to_cpu(ncmh->wNdpIndex) >= urb->actual_length) {
-		dev->net->stats.rx_errors++;
-		return retval;
-	}
+	    /* On iOS, NDP16 directly follows NTH16 */
+	    ncmh->wNdpIndex != cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16)))
+		goto rx_error;
 
-	ncm0 = urb->transfer_buffer + le16_to_cpu(ncmh->wNdpIndex);
-	if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN) ||
-	    le16_to_cpu(ncmh->wHeaderLength) + le16_to_cpu(ncm0->wLength) >=
-	    urb->actual_length) {
-		dev->net->stats.rx_errors++;
-		return retval;
-	}
+	ncm0 = urb->transfer_buffer + sizeof(struct usb_cdc_ncm_nth16);
+	if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN))
+		goto rx_error;
 
 	dpe = ncm0->dpe16;
-	while (le16_to_cpu(dpe->wDatagramIndex) != 0 &&
-	       le16_to_cpu(dpe->wDatagramLength) != 0) {
-		if (le16_to_cpu(dpe->wDatagramIndex) >= urb->actual_length ||
-		    le16_to_cpu(dpe->wDatagramIndex) +
-		    le16_to_cpu(dpe->wDatagramLength) > urb->actual_length) {
+	for (int dpe_i = 0; dpe_i < IPHETH_NDP16_MAX_DPE; ++dpe_i, ++dpe) {
+		dg_idx = le16_to_cpu(dpe->wDatagramIndex);
+		dg_len = le16_to_cpu(dpe->wDatagramLength);
+
+		/* Null DPE must be present after last datagram pointer entry
+		 * (3.3.1 USB CDC NCM spec v1.0)
+		 */
+		if (dg_idx == 0 && dg_len == 0)
+			return 0;
+
+		if (dg_idx < IPHETH_NCM_HEADER_SIZE ||
+		    dg_idx >= urb->actual_length ||
+		    dg_len > urb->actual_length - dg_idx) {
 			dev->net->stats.rx_length_errors++;
 			return retval;
 		}
 
-		buf = urb->transfer_buffer + le16_to_cpu(dpe->wDatagramIndex);
-		len = le16_to_cpu(dpe->wDatagramLength);
+		buf = urb->transfer_buffer + dg_idx;
 
-		retval = ipheth_consume_skb(buf, len, dev);
+		retval = ipheth_consume_skb(buf, dg_len, dev);
 		if (retval != 0)
 			return retval;
-
-		dpe++;
 	}
 
-	return 0;
+rx_error:
+	dev->net->stats.rx_errors++;
+	return retval;
 }
 
 static void ipheth_rcvbulk_callback(struct urb *urb)
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 01a3b2417a54..ddff6f19ff98 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -71,6 +71,14 @@
 #define MSR_SPEED		(1<<3)
 #define MSR_LINK		(1<<2)
 
+/* USB endpoints */
+enum rtl8150_usb_ep {
+	RTL8150_USB_EP_CONTROL = 0,
+	RTL8150_USB_EP_BULK_IN = 1,
+	RTL8150_USB_EP_BULK_OUT = 2,
+	RTL8150_USB_EP_INT_IN = 3,
+};
+
 /* Interrupt pipe data */
 #define INT_TSR			0x00
 #define INT_RSR			0x01
@@ -867,6 +875,13 @@ static int rtl8150_probe(struct usb_interface *intf,
 	struct usb_device *udev = interface_to_usbdev(intf);
 	rtl8150_t *dev;
 	struct net_device *netdev;
+	static const u8 bulk_ep_addr[] = {
+		RTL8150_USB_EP_BULK_IN | USB_DIR_IN,
+		RTL8150_USB_EP_BULK_OUT | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		RTL8150_USB_EP_INT_IN | USB_DIR_IN,
+		0};
 
 	netdev = alloc_etherdev(sizeof(rtl8150_t));
 	if (!netdev)
@@ -880,6 +895,13 @@ static int rtl8150_probe(struct usb_interface *intf,
 		return -ENOMEM;
 	}
 
+	/* Verify that all required endpoints are present */
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(&intf->dev, "couldn't find required endpoints\n");
+		goto out;
+	}
+
 	tasklet_setup(&dev->tl, rx_fixup);
 	spin_lock_init(&dev->rx_pool_lock);
 
diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c
index 1341374a4588..616ecc38d172 100644
--- a/drivers/net/vmxnet3/vmxnet3_xdp.c
+++ b/drivers/net/vmxnet3/vmxnet3_xdp.c
@@ -28,7 +28,7 @@ vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter)
 	if (likely(cpu < tq_number))
 		tq = &adapter->tx_queue[cpu];
 	else
-		tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)];
+		tq = &adapter->tx_queue[cpu % tq_number];
 
 	return tq;
 }
@@ -124,6 +124,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 	u32 buf_size;
 	u32 dw2;
 
+	spin_lock_irq(&tq->tx_lock);
 	dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT;
 	dw2 |= xdpf->len;
 	ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill;
@@ -134,6 +135,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 
 	if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) {
 		tq->stats.tx_ring_full++;
+		spin_unlock_irq(&tq->tx_lock);
 		return -ENOSPC;
 	}
 
@@ -142,8 +144,10 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 		tbi->dma_addr = dma_map_single(&adapter->pdev->dev,
 					       xdpf->data, buf_size,
 					       DMA_TO_DEVICE);
-		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr))
+		if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) {
+			spin_unlock_irq(&tq->tx_lock);
 			return -EFAULT;
+		}
 		tbi->map_type |= VMXNET3_MAP_SINGLE;
 	} else { /* XDP buffer from page pool */
 		page = virt_to_page(xdpf->data);
@@ -182,6 +186,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter,
 	dma_wmb();
 	gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^
 						  VMXNET3_TXD_GEN);
+	spin_unlock_irq(&tq->tx_lock);
 
 	/* No need to handle the case when tx_num_deferred doesn't reach
 	 * threshold. Backend driver at hypervisor side will poll and reset
@@ -225,6 +230,7 @@ vmxnet3_xdp_xmit(struct net_device *dev,
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(dev);
 	struct vmxnet3_tx_queue *tq;
+	struct netdev_queue *nq;
 	int i;
 
 	if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state)))
@@ -236,6 +242,9 @@ vmxnet3_xdp_xmit(struct net_device *dev,
 	if (tq->stopped)
 		return -ENETDOWN;
 
+	nq = netdev_get_tx_queue(adapter->netdev, tq->qid);
+
+	__netif_tx_lock(nq, smp_processor_id());
 	for (i = 0; i < n; i++) {
 		if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) {
 			tq->stats.xdp_xmit_err++;
@@ -243,6 +252,7 @@ vmxnet3_xdp_xmit(struct net_device *dev,
 		}
 	}
 	tq->stats.xdp_xmit += i;
+	__netif_tx_unlock(nq);
 
 	return i;
 }
diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c
index d2023e7131bd..6e6e9f05509a 100644
--- a/drivers/net/vxlan/vxlan_vnifilter.c
+++ b/drivers/net/vxlan/vxlan_vnifilter.c
@@ -411,6 +411,11 @@ static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb
 	struct tunnel_msg *tmsg;
 	struct net_device *dev;
 
+	if (cb->nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct tunnel_msg))) {
+		NL_SET_ERR_MSG(cb->extack, "Invalid msg length");
+		return -EINVAL;
+	}
+
 	tmsg = nlmsg_data(cb->nlh);
 
 	if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) {
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index 57281a135dd7..bf192529e3fe 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -178,7 +178,7 @@ static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
 	 * received 'update stats' event, we keep a 3 seconds timeout in case,
 	 * fw_stats_done is not marked yet
 	 */
-	timeout = jiffies + msecs_to_jiffies(3 * 1000);
+	timeout = jiffies + secs_to_jiffies(3);
 
 	ath11k_debugfs_fw_stats_reset(ar);
 
diff --git a/drivers/net/wireless/ath/carl9170/debug.c b/drivers/net/wireless/ath/carl9170/debug.c
index bb40889d7c72..2d734567000a 100644
--- a/drivers/net/wireless/ath/carl9170/debug.c
+++ b/drivers/net/wireless/ath/carl9170/debug.c
@@ -54,7 +54,6 @@ struct carl9170_debugfs_fops {
 	char *(*read)(struct ar9170 *ar, char *buf, size_t bufsize,
 		      ssize_t *len);
 	ssize_t (*write)(struct ar9170 *aru, const char *buf, size_t size);
-	const struct file_operations fops;
 
 	enum carl9170_device_state req_dev_state;
 };
@@ -62,7 +61,7 @@ struct carl9170_debugfs_fops {
 static ssize_t carl9170_debugfs_read(struct file *file, char __user *userbuf,
 				     size_t count, loff_t *ppos)
 {
-	struct carl9170_debugfs_fops *dfops;
+	const struct carl9170_debugfs_fops *dfops;
 	struct ar9170 *ar;
 	char *buf = NULL, *res_buf = NULL;
 	ssize_t ret = 0;
@@ -75,8 +74,7 @@ static ssize_t carl9170_debugfs_read(struct file *file, char __user *userbuf,
 
 	if (!ar)
 		return -ENODEV;
-	dfops = container_of(debugfs_real_fops(file),
-			     struct carl9170_debugfs_fops, fops);
+	dfops = debugfs_get_aux(file);
 
 	if (!dfops->read)
 		return -ENOSYS;
@@ -113,7 +111,7 @@ out_free:
 static ssize_t carl9170_debugfs_write(struct file *file,
 	const char __user *userbuf, size_t count, loff_t *ppos)
 {
-	struct carl9170_debugfs_fops *dfops;
+	const struct carl9170_debugfs_fops *dfops;
 	struct ar9170 *ar;
 	char *buf = NULL;
 	int err = 0;
@@ -128,8 +126,7 @@ static ssize_t carl9170_debugfs_write(struct file *file,
 
 	if (!ar)
 		return -ENODEV;
-	dfops = container_of(debugfs_real_fops(file),
-			     struct carl9170_debugfs_fops, fops);
+	dfops = debugfs_get_aux(file);
 
 	if (!dfops->write)
 		return -ENOSYS;
@@ -165,6 +162,11 @@ out_free:
 	return err;
 }
 
+static struct debugfs_short_fops debugfs_fops = {
+	.read	= carl9170_debugfs_read,
+	.write	= carl9170_debugfs_write,
+};
+
 #define __DEBUGFS_DECLARE_FILE(name, _read, _write, _read_bufsize,	\
 			       _attr, _dstate)				\
 static const struct carl9170_debugfs_fops carl_debugfs_##name ##_ops = {\
@@ -173,12 +175,6 @@ static const struct carl9170_debugfs_fops carl_debugfs_##name ##_ops = {\
 	.write = _write,						\
 	.attr = _attr,							\
 	.req_dev_state = _dstate,					\
-	.fops = {							\
-		.open	= simple_open,					\
-		.read	= carl9170_debugfs_read,			\
-		.write	= carl9170_debugfs_write,			\
-		.owner	= THIS_MODULE					\
-	},								\
 }
 
 #define DEBUGFS_DECLARE_FILE(name, _read, _write, _read_bufsize, _attr)	\
@@ -816,9 +812,9 @@ void carl9170_debugfs_register(struct ar9170 *ar)
 		ar->hw->wiphy->debugfsdir);
 
 #define DEBUGFS_ADD(name)						\
-	debugfs_create_file(#name, carl_debugfs_##name ##_ops.attr,	\
-			    ar->debug_dir, ar,				\
-			    &carl_debugfs_##name ## _ops.fops)
+	debugfs_create_file_aux(#name, carl_debugfs_##name ##_ops.attr,	\
+			    ar->debug_dir, ar, &carl_debugfs_##name ## _ops, \
+			    &debugfs_fops)
 
 	DEBUGFS_ADD(usb_tx_anch_urbs);
 	DEBUGFS_ADD(usb_rx_pool_urbs);
diff --git a/drivers/net/wireless/broadcom/b43/debugfs.c b/drivers/net/wireless/broadcom/b43/debugfs.c
index efa98444e3fb..5a49970afc8c 100644
--- a/drivers/net/wireless/broadcom/b43/debugfs.c
+++ b/drivers/net/wireless/broadcom/b43/debugfs.c
@@ -30,7 +30,6 @@ static struct dentry *rootdir;
 struct b43_debugfs_fops {
 	ssize_t (*read)(struct b43_wldev *dev, char *buf, size_t bufsize);
 	int (*write)(struct b43_wldev *dev, const char *buf, size_t count);
-	struct file_operations fops;
 	/* Offset of struct b43_dfs_file in struct b43_dfsentry */
 	size_t file_struct_offset;
 };
@@ -491,7 +490,7 @@ static ssize_t b43_debugfs_read(struct file *file, char __user *userbuf,
 				size_t count, loff_t *ppos)
 {
 	struct b43_wldev *dev;
-	struct b43_debugfs_fops *dfops;
+	const struct b43_debugfs_fops *dfops;
 	struct b43_dfs_file *dfile;
 	ssize_t ret;
 	char *buf;
@@ -511,8 +510,7 @@ static ssize_t b43_debugfs_read(struct file *file, char __user *userbuf,
 		goto out_unlock;
 	}
 
-	dfops = container_of(debugfs_real_fops(file),
-			     struct b43_debugfs_fops, fops);
+	dfops = debugfs_get_aux(file);
 	if (!dfops->read) {
 		err = -ENOSYS;
 		goto out_unlock;
@@ -555,7 +553,7 @@ static ssize_t b43_debugfs_write(struct file *file,
 				 size_t count, loff_t *ppos)
 {
 	struct b43_wldev *dev;
-	struct b43_debugfs_fops *dfops;
+	const struct b43_debugfs_fops *dfops;
 	char *buf;
 	int err = 0;
 
@@ -573,8 +571,7 @@ static ssize_t b43_debugfs_write(struct file *file,
 		goto out_unlock;
 	}
 
-	dfops = container_of(debugfs_real_fops(file),
-			     struct b43_debugfs_fops, fops);
+	dfops = debugfs_get_aux(file);
 	if (!dfops->write) {
 		err = -ENOSYS;
 		goto out_unlock;
@@ -602,16 +599,16 @@ out_unlock:
 }
 
 
+static struct debugfs_short_fops debugfs_ops = {
+	.read	= b43_debugfs_read,
+	.write	= b43_debugfs_write,
+	.llseek = generic_file_llseek,
+};
+
 #define B43_DEBUGFS_FOPS(name, _read, _write)			\
 	static struct b43_debugfs_fops fops_##name = {		\
 		.read	= _read,				\
 		.write	= _write,				\
-		.fops	= {					\
-			.open	= simple_open,			\
-			.read	= b43_debugfs_read,		\
-			.write	= b43_debugfs_write,		\
-			.llseek = generic_file_llseek,		\
-		},						\
 		.file_struct_offset = offsetof(struct b43_dfsentry, \
 					       file_##name),	\
 	}
@@ -703,9 +700,9 @@ void b43_debugfs_add_device(struct b43_wldev *dev)
 
 #define ADD_FILE(name, mode)	\
 	do {							\
-		debugfs_create_file(__stringify(name),		\
+		debugfs_create_file_aux(__stringify(name),	\
 				mode, e->subdir, dev,		\
-				&fops_##name.fops);		\
+				&fops_##name, &debugfs_ops);	\
 	} while (0)
 
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/debugfs.c b/drivers/net/wireless/broadcom/b43legacy/debugfs.c
index 6b0e8d117061..5d04bcc216e5 100644
--- a/drivers/net/wireless/broadcom/b43legacy/debugfs.c
+++ b/drivers/net/wireless/broadcom/b43legacy/debugfs.c
@@ -31,7 +31,6 @@ static struct dentry *rootdir;
 struct b43legacy_debugfs_fops {
 	ssize_t (*read)(struct b43legacy_wldev *dev, char *buf, size_t bufsize);
 	int (*write)(struct b43legacy_wldev *dev, const char *buf, size_t count);
-	struct file_operations fops;
 	/* Offset of struct b43legacy_dfs_file in struct b43legacy_dfsentry */
 	size_t file_struct_offset;
 	/* Take wl->irq_lock before calling read/write? */
@@ -188,7 +187,7 @@ static ssize_t b43legacy_debugfs_read(struct file *file, char __user *userbuf,
 				size_t count, loff_t *ppos)
 {
 	struct b43legacy_wldev *dev;
-	struct b43legacy_debugfs_fops *dfops;
+	const struct b43legacy_debugfs_fops *dfops;
 	struct b43legacy_dfs_file *dfile;
 	ssize_t ret;
 	char *buf;
@@ -208,8 +207,7 @@ static ssize_t b43legacy_debugfs_read(struct file *file, char __user *userbuf,
 		goto out_unlock;
 	}
 
-	dfops = container_of(debugfs_real_fops(file),
-			     struct b43legacy_debugfs_fops, fops);
+	dfops = debugfs_get_aux(file);
 	if (!dfops->read) {
 		err = -ENOSYS;
 		goto out_unlock;
@@ -257,7 +255,7 @@ static ssize_t b43legacy_debugfs_write(struct file *file,
 				 size_t count, loff_t *ppos)
 {
 	struct b43legacy_wldev *dev;
-	struct b43legacy_debugfs_fops *dfops;
+	const struct b43legacy_debugfs_fops *dfops;
 	char *buf;
 	int err = 0;
 
@@ -275,8 +273,7 @@ static ssize_t b43legacy_debugfs_write(struct file *file,
 		goto out_unlock;
 	}
 
-	dfops = container_of(debugfs_real_fops(file),
-			     struct b43legacy_debugfs_fops, fops);
+	dfops = debugfs_get_aux(file);
 	if (!dfops->write) {
 		err = -ENOSYS;
 		goto out_unlock;
@@ -308,17 +305,16 @@ out_unlock:
 	return err ? err : count;
 }
 
+static struct debugfs_short_fops debugfs_ops = {
+	.read	= b43legacy_debugfs_read,
+	.write	= b43legacy_debugfs_write,
+	.llseek = generic_file_llseek
+};
 
 #define B43legacy_DEBUGFS_FOPS(name, _read, _write, _take_irqlock)	\
 	static struct b43legacy_debugfs_fops fops_##name = {		\
 		.read	= _read,				\
 		.write	= _write,				\
-		.fops	= {					\
-			.open	= simple_open,				\
-			.read	= b43legacy_debugfs_read,		\
-			.write	= b43legacy_debugfs_write,		\
-			.llseek = generic_file_llseek,			\
-		},						\
 		.file_struct_offset = offsetof(struct b43legacy_dfsentry, \
 					       file_##name),	\
 		.take_irqlock	= _take_irqlock,		\
@@ -386,9 +382,9 @@ void b43legacy_debugfs_add_device(struct b43legacy_wldev *dev)
 
 #define ADD_FILE(name, mode)	\
 	do {							\
-		debugfs_create_file(__stringify(name), mode,	\
+		debugfs_create_file_aux(__stringify(name), mode,	\
 				    e->subdir, dev,		\
-				    &fops_##name.fops);		\
+				    &fops_##name, &debugfs_ops);	\
 	} while (0)
 
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index 0949e7975ff1..b70d20128f98 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -1810,7 +1810,7 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 			rfi->cur_idx = cur_idx;
 		}
 	} else {
-		/* explicity window move updating the expected index */
+		/* explicitly window move updating the expected index */
 		exp_idx = reorder_data[BRCMF_RXREORDER_EXPIDX_OFFSET];
 
 		brcmf_dbg(DATA, "flow-%d (0x%x): change expected: %d -> %d\n",
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index a259f4dd9540..413973d05b43 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -1479,14 +1479,13 @@ static void mt7603_mac_watchdog_reset(struct mt7603_dev *dev)
 	tasklet_enable(&dev->mt76.pre_tbtt_tasklet);
 	mt7603_beacon_set_timer(dev, -1, beacon_int);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
-	napi_schedule(&dev->mt76.tx_napi);
-
 	napi_enable(&dev->mt76.napi[0]);
-	napi_schedule(&dev->mt76.napi[0]);
-
 	napi_enable(&dev->mt76.napi[1]);
+
+	local_bh_disable();
+	napi_schedule(&dev->mt76.tx_napi);
+	napi_schedule(&dev->mt76.napi[0]);
 	napi_schedule(&dev->mt76.napi[1]);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c
index 9a278589df4e..68010e27f065 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c
@@ -164,12 +164,16 @@ static int mt7615_pci_resume(struct pci_dev *pdev)
 		dev_err(mdev->dev, "PDMA engine must be reinitialized\n");
 
 	mt76_worker_enable(&mdev->tx_worker);
-	local_bh_disable();
+
 	mt76_for_each_q_rx(mdev, i) {
 		napi_enable(&mdev->napi[i]);
-		napi_schedule(&mdev->napi[i]);
 	}
 	napi_enable(&mdev->tx_napi);
+
+	local_bh_disable();
+	mt76_for_each_q_rx(mdev, i) {
+		napi_schedule(&mdev->napi[i]);
+	}
 	napi_schedule(&mdev->tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
index a0ca3bbdfcaf..c2e4e6aabd9f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
@@ -262,12 +262,14 @@ void mt7615_mac_reset_work(struct work_struct *work)
 
 	mt76_worker_enable(&dev->mt76.tx_worker);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
-	napi_schedule(&dev->mt76.tx_napi);
-
 	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_enable(&dev->mt76.napi[i]);
+	}
+
+	local_bh_disable();
+	napi_schedule(&dev->mt76.tx_napi);
+	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_schedule(&dev->mt76.napi[i]);
 	}
 	local_bh_enable();
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 1eb955f3ca13..b456ccd00d58 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -282,14 +282,16 @@ static int mt76x0e_resume(struct pci_dev *pdev)
 
 	mt76_worker_enable(&mdev->tx_worker);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
 		mt76_queue_rx_reset(dev, i);
 		napi_enable(&mdev->napi[i]);
-		napi_schedule(&mdev->napi[i]);
 	}
-
 	napi_enable(&mdev->tx_napi);
+
+	local_bh_disable();
+	mt76_for_each_q_rx(mdev, i) {
+		napi_schedule(&mdev->napi[i]);
+	}
 	napi_schedule(&mdev->tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 7d840ad4ae65..a82c75ba26e6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -504,12 +504,14 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 	mt76_worker_enable(&dev->mt76.tx_worker);
 	tasklet_enable(&dev->mt76.pre_tbtt_tasklet);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
-	napi_schedule(&dev->mt76.tx_napi);
-
 	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_enable(&dev->mt76.napi[i]);
+	}
+
+	local_bh_disable();
+	napi_schedule(&dev->mt76.tx_napi);
+	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_schedule(&dev->mt76.napi[i]);
 	}
 	local_bh_enable();
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index 67c9d1caa0bd..727bfdd00b40 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -151,12 +151,15 @@ mt76x2e_resume(struct pci_dev *pdev)
 
 	mt76_worker_enable(&mdev->tx_worker);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
 		napi_enable(&mdev->napi[i]);
-		napi_schedule(&mdev->napi[i]);
 	}
 	napi_enable(&mdev->tx_napi);
+
+	local_bh_disable();
+	mt76_for_each_q_rx(mdev, i) {
+		napi_schedule(&mdev->napi[i]);
+	}
 	napi_schedule(&mdev->tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 13bdc0a7174c..2ba6eb3038ce 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1356,10 +1356,15 @@ mt7915_mac_restart(struct mt7915_dev *dev)
 
 	mt7915_dma_reset(dev, true);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
 		if (mdev->q_rx[i].ndesc) {
 			napi_enable(&dev->mt76.napi[i]);
+		}
+	}
+
+	local_bh_disable();
+	mt76_for_each_q_rx(mdev, i) {
+		if (mdev->q_rx[i].ndesc) {
 			napi_schedule(&dev->mt76.napi[i]);
 		}
 	}
@@ -1419,8 +1424,9 @@ out:
 	if (phy2)
 		clear_bit(MT76_RESET, &phy2->mt76->state);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
+
+	local_bh_disable();
 	napi_schedule(&dev->mt76.tx_napi);
 	local_bh_enable();
 
@@ -1570,9 +1576,12 @@ void mt7915_mac_reset_work(struct work_struct *work)
 	if (phy2)
 		clear_bit(MT76_RESET, &phy2->mt76->state);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_enable(&dev->mt76.napi[i]);
+	}
+
+	local_bh_disable();
+	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_schedule(&dev->mt76.napi[i]);
 	}
 	local_bh_enable();
@@ -1581,8 +1590,8 @@ void mt7915_mac_reset_work(struct work_struct *work)
 
 	mt76_worker_enable(&dev->mt76.tx_worker);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
+	local_bh_disable();
 	napi_schedule(&dev->mt76.tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index ba870e1b05fb..a0c9df3c2cc7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -523,12 +523,15 @@ static int mt7921_pci_resume(struct device *device)
 
 	mt76_worker_enable(&mdev->tx_worker);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
 		napi_enable(&mdev->napi[i]);
-		napi_schedule(&mdev->napi[i]);
 	}
 	napi_enable(&mdev->tx_napi);
+
+	local_bh_disable();
+	mt76_for_each_q_rx(mdev, i) {
+		napi_schedule(&mdev->napi[i]);
+	}
 	napi_schedule(&mdev->tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
index 2452b1a2d118..881812ba03ff 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c
@@ -81,9 +81,12 @@ int mt7921e_mac_reset(struct mt792x_dev *dev)
 
 	mt792x_wpdma_reset(dev, true);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_enable(&dev->mt76.napi[i]);
+	}
+
+	local_bh_disable();
+	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_schedule(&dev->mt76.napi[i]);
 	}
 	local_bh_enable();
@@ -115,8 +118,8 @@ int mt7921e_mac_reset(struct mt792x_dev *dev)
 	err = __mt7921_start(&dev->phy);
 out:
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
+	local_bh_disable();
 	napi_schedule(&dev->mt76.tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index f36893e20c61..c7b5dc1dbb34 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -556,12 +556,15 @@ static int mt7925_pci_resume(struct device *device)
 
 	mt76_worker_enable(&mdev->tx_worker);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
 		napi_enable(&mdev->napi[i]);
-		napi_schedule(&mdev->napi[i]);
 	}
 	napi_enable(&mdev->tx_napi);
+
+	local_bh_disable();
+	mt76_for_each_q_rx(mdev, i) {
+		napi_schedule(&mdev->napi[i]);
+	}
 	napi_schedule(&mdev->tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c
index faedbf766d1a..4578d16bf456 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c
@@ -101,12 +101,15 @@ int mt7925e_mac_reset(struct mt792x_dev *dev)
 
 	mt792x_wpdma_reset(dev, true);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(&dev->mt76, i) {
 		napi_enable(&dev->mt76.napi[i]);
-		napi_schedule(&dev->mt76.napi[i]);
 	}
 	napi_enable(&dev->mt76.tx_napi);
+
+	local_bh_disable();
+	mt76_for_each_q_rx(&dev->mt76, i) {
+		napi_schedule(&dev->mt76.napi[i]);
+	}
 	napi_schedule(&dev->mt76.tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index bc8cba4dca47..019c925ae600 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1695,7 +1695,6 @@ mt7996_mac_restart(struct mt7996_dev *dev)
 
 	mt7996_dma_reset(dev, true);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(mdev, i) {
 		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
 		    mt76_queue_is_wed_rro(&mdev->q_rx[i]))
@@ -1703,10 +1702,11 @@ mt7996_mac_restart(struct mt7996_dev *dev)
 
 		if (mdev->q_rx[i].ndesc) {
 			napi_enable(&dev->mt76.napi[i]);
+			local_bh_disable();
 			napi_schedule(&dev->mt76.napi[i]);
+			local_bh_enable();
 		}
 	}
-	local_bh_enable();
 	clear_bit(MT76_MCU_RESET, &dev->mphy.state);
 	clear_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state);
 
@@ -1764,8 +1764,8 @@ out:
 	if (phy3)
 		clear_bit(MT76_RESET, &phy3->mt76->state);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
+	local_bh_disable();
 	napi_schedule(&dev->mt76.tx_napi);
 	local_bh_enable();
 
@@ -1958,23 +1958,23 @@ void mt7996_mac_reset_work(struct work_struct *work)
 	if (phy3)
 		clear_bit(MT76_RESET, &phy3->mt76->state);
 
-	local_bh_disable();
 	mt76_for_each_q_rx(&dev->mt76, i) {
 		if (mtk_wed_device_active(&dev->mt76.mmio.wed) &&
 		    mt76_queue_is_wed_rro(&dev->mt76.q_rx[i]))
 			continue;
 
 		napi_enable(&dev->mt76.napi[i]);
+		local_bh_disable();
 		napi_schedule(&dev->mt76.napi[i]);
+		local_bh_enable();
 	}
-	local_bh_enable();
 
 	tasklet_schedule(&dev->mt76.irq_tasklet);
 
 	mt76_worker_enable(&dev->mt76.tx_worker);
 
-	local_bh_disable();
 	napi_enable(&dev->mt76.tx_napi);
+	local_bh_disable();
 	napi_schedule(&dev->mt76.tx_napi);
 	local_bh_enable();
 
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 2237715e42eb..0ccf4a9e523a 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -1212,7 +1212,7 @@ enum nd_ioctl_mode {
 	DIMM_IOCTL,
 };
 
-static int match_dimm(struct device *dev, void *data)
+static int match_dimm(struct device *dev, const void *data)
 {
 	long id = (long) data;
 
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 030dbde6b088..9e84ab411564 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -67,13 +67,6 @@ bool nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach,
 	return claimed;
 }
 
-static int namespace_match(struct device *dev, void *data)
-{
-	char *name = data;
-
-	return strcmp(name, dev_name(dev)) == 0;
-}
-
 static bool is_idle(struct device *dev, struct nd_namespace_common *ndns)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
@@ -168,7 +161,7 @@ ssize_t nd_namespace_store(struct device *dev,
 		goto out;
 	}
 
-	found = device_find_child(dev->parent, name, namespace_match);
+	found = device_find_child_by_name(dev->parent, name);
 	if (!found) {
 		dev_dbg(dev, "'%s' not found under %s\n", name,
 				dev_name(dev->parent));
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 76b615d4d5b9..818d4e49aab5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1700,7 +1700,13 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 
 	status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
 			&result);
-	if (status < 0)
+
+	/*
+	 * It's either a kernel error or the host observed a connection
+	 * lost. In either case it's not possible communicate with the
+	 * controller and thus enter the error code path.
+	 */
+	if (status < 0 || status == NVME_SC_HOST_PATH_ERROR)
 		return status;
 
 	/*
@@ -2132,15 +2138,16 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
 	struct queue_limits lim;
+	unsigned int memflags;
 	int ret;
 
 	lim = queue_limits_start_update(ns->disk->queue);
 	nvme_set_ctrl_limits(ns->ctrl, &lim);
 
-	blk_mq_freeze_queue(ns->disk->queue);
+	memflags = blk_mq_freeze_queue(ns->disk->queue);
 	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
-	blk_mq_unfreeze_queue(ns->disk->queue);
+	blk_mq_unfreeze_queue(ns->disk->queue, memflags);
 
 	/* Hide the block-interface for these devices */
 	if (!ret)
@@ -2155,6 +2162,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	struct nvme_id_ns_nvm *nvm = NULL;
 	struct nvme_zone_info zi = {};
 	struct nvme_id_ns *id;
+	unsigned int memflags;
 	sector_t capacity;
 	unsigned lbaf;
 	int ret;
@@ -2186,7 +2194,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 
 	lim = queue_limits_start_update(ns->disk->queue);
 
-	blk_mq_freeze_queue(ns->disk->queue);
+	memflags = blk_mq_freeze_queue(ns->disk->queue);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
 	ns->head->nuse = le64_to_cpu(id->nuse);
 	capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
@@ -2219,7 +2227,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 
 	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	if (ret) {
-		blk_mq_unfreeze_queue(ns->disk->queue);
+		blk_mq_unfreeze_queue(ns->disk->queue, memflags);
 		goto out;
 	}
 
@@ -2235,7 +2243,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		ns->head->features |= NVME_NS_DEAC;
 	set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
 	set_bit(NVME_NS_READY, &ns->flags);
-	blk_mq_unfreeze_queue(ns->disk->queue);
+	blk_mq_unfreeze_queue(ns->disk->queue, memflags);
 
 	if (blk_queue_is_zoned(ns->queue)) {
 		ret = blk_revalidate_disk_zones(ns->disk);
@@ -2291,9 +2299,10 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 	if (!ret && nvme_ns_head_multipath(ns->head)) {
 		struct queue_limits *ns_lim = &ns->disk->queue->limits;
 		struct queue_limits lim;
+		unsigned int memflags;
 
 		lim = queue_limits_start_update(ns->head->disk->queue);
-		blk_mq_freeze_queue(ns->head->disk->queue);
+		memflags = blk_mq_freeze_queue(ns->head->disk->queue);
 		/*
 		 * queue_limits mixes values that are the hardware limitations
 		 * for bio splitting with what is the device configuration.
@@ -2325,7 +2334,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns);
 
-		blk_mq_unfreeze_queue(ns->head->disk->queue);
+		blk_mq_unfreeze_queue(ns->head->disk->queue, memflags);
 	}
 
 	return ret;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 094be164ffdc..f4f1866fbd5b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -781,11 +781,19 @@ restart:
 static void
 nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 {
+	enum nvme_ctrl_state state;
+	unsigned long flags;
+
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: controller connectivity lost. Awaiting "
 		"Reconnect", ctrl->cnum);
 
-	switch (nvme_ctrl_state(&ctrl->ctrl)) {
+	spin_lock_irqsave(&ctrl->lock, flags);
+	set_bit(ASSOC_FAILED, &ctrl->flags);
+	state = nvme_ctrl_state(&ctrl->ctrl);
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	switch (state) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
 		/*
@@ -2079,7 +2087,8 @@ done:
 		nvme_fc_complete_rq(rq);
 
 check_error:
-	if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING)
+	if (terminate_assoc &&
+	    nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_RESETTING)
 		queue_work(nvme_reset_wq, &ctrl->ioerr_work);
 }
 
@@ -2533,6 +2542,8 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
 static void
 nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 {
+	enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
+
 	/*
 	 * if an error (io timeout, etc) while (re)connecting, the remote
 	 * port requested terminating of the association (disconnect_ls)
@@ -2540,9 +2551,8 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 * the controller.  Abort any ios on the association and let the
 	 * create_association error path resolve things.
 	 */
-	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
+	if (state == NVME_CTRL_CONNECTING) {
 		__nvme_fc_abort_outstanding_ios(ctrl, true);
-		set_bit(ASSOC_FAILED, &ctrl->flags);
 		dev_warn(ctrl->ctrl.device,
 			"NVME-FC{%d}: transport error during (re)connect\n",
 			ctrl->cnum);
@@ -2550,7 +2560,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	}
 
 	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
+	if (state != NVME_CTRL_LIVE)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
@@ -3167,12 +3177,18 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
-	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
-		ret = -EIO;
 	if (ret)
 		goto out_term_aen_ops;
 
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (!test_bit(ASSOC_FAILED, &ctrl->flags))
+		changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	else
+		ret = -EIO;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	if (ret)
+		goto out_term_aen_ops;
 
 	ctrl->ctrl.nr_reconnects = 0;
 
@@ -3578,8 +3594,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 	list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
 	spin_unlock_irqrestore(&rport->lock, flags);
 
-	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING) ||
-	    !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		dev_err(ctrl->ctrl.device,
 			"NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum);
 		goto fail_ctrl;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index a85d190942bd..2a7635565083 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -60,7 +60,7 @@ void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
 	lockdep_assert_held(&subsys->lock);
 	list_for_each_entry(h, &subsys->nsheads, entry)
 		if (h->disk)
-			blk_mq_unfreeze_queue(h->disk->queue);
+			blk_mq_unfreeze_queue_nomemrestore(h->disk->queue);
 }
 
 void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 278bed4e35bb..9197a5b173fd 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2153,14 +2153,6 @@ static int nvme_alloc_host_mem_multi(struct nvme_dev *dev, u64 preferred,
 	return 0;
 
 out_free_bufs:
-	while (--i >= 0) {
-		size_t size = le32_to_cpu(descs[i].size) * NVME_CTRL_PAGE_SIZE;
-
-		dma_free_attrs(dev->dev, size, bufs[i],
-			       le64_to_cpu(descs[i].addr),
-			       DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN);
-	}
-
 	kfree(bufs);
 out_free_descs:
 	dma_free_coherent(dev->dev, descs_size, descs, descs_dma);
@@ -3147,7 +3139,9 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 		 * because of high power consumption (> 2 Watt) in s2idle
 		 * sleep. Only some boards with Intel CPU are affected.
 		 */
-		if (dmi_match(DMI_BOARD_NAME, "GMxPXxx") ||
+		if (dmi_match(DMI_BOARD_NAME, "DN50Z-140HC-YD") ||
+		    dmi_match(DMI_BOARD_NAME, "GMxPXxx") ||
+		    dmi_match(DMI_BOARD_NAME, "GXxMRXx") ||
 		    dmi_match(DMI_BOARD_NAME, "PH4PG31") ||
 		    dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1") ||
 		    dmi_match(DMI_BOARD_NAME, "PH6PG01_PH6PG71"))
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index b68a9e5f1ea3..3a41b9ab0f13 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -792,7 +792,7 @@ static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj,
 	return a->mode;
 }
 
-const struct attribute_group nvme_tls_attrs_group = {
+static const struct attribute_group nvme_tls_attrs_group = {
 	.attrs		= nvme_tls_attrs,
 	.is_visible	= nvme_tls_attrs_are_visible,
 };
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index e670dc185a96..acc138bbf8f2 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -1068,6 +1068,7 @@ static void nvme_execute_identify_ns_nvm(struct nvmet_req *req)
 		goto out;
 	}
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+	kfree(id);
 out:
 	nvmet_req_complete(req, status);
 }
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index a7ff05b3be29..eb406c90c167 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -287,7 +287,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 	args.subsysnqn = d->subsysnqn;
 	args.hostnqn = d->hostnqn;
 	args.hostid = &d->hostid;
-	args.kato = c->kato;
+	args.kato = le32_to_cpu(c->kato);
 
 	ctrl = nvmet_alloc_ctrl(&args);
 	if (!ctrl)
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index c1f574fe3280..83be0657e6df 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -272,7 +272,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
 		iter_flags = SG_MITER_FROM_SG;
 	}
 
-	if (req->cmd->rw.control & NVME_RW_LR)
+	if (req->cmd->rw.control & cpu_to_le16(NVME_RW_LR))
 		opf |= REQ_FAILFAST_DEV;
 
 	if (is_pci_p2pdma_page(sg_page(req->sg)))
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index b540216c0c9a..4be8d22d2d8d 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -589,7 +589,7 @@ struct nvmet_alloc_ctrl_args {
 	const struct nvmet_fabrics_ops *ops;
 	struct device		*p2p_client;
 	u32			kato;
-	u32			result;
+	__le32			result;
 	u16			error_loc;
 	u16			status;
 };
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index d6494dfc20a7..fff85bbf0ecd 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -213,7 +213,7 @@ static struct attribute *nvmem_attrs[] = {
 };
 
 static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj,
-				   struct bin_attribute *attr, char *buf,
+				   const struct bin_attribute *attr, char *buf,
 				   loff_t pos, size_t count)
 {
 	struct device *dev;
@@ -246,7 +246,7 @@ static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj,
-				    struct bin_attribute *attr, char *buf,
+				    const struct bin_attribute *attr, char *buf,
 				    loff_t pos, size_t count)
 {
 	struct device *dev;
@@ -340,7 +340,7 @@ static struct nvmem_cell *nvmem_create_cell(struct nvmem_cell_entry *entry,
 					    const char *id, int index);
 
 static ssize_t nvmem_cell_attr_read(struct file *filp, struct kobject *kobj,
-				    struct bin_attribute *attr, char *buf,
+				    const struct bin_attribute *attr, char *buf,
 				    loff_t pos, size_t count)
 {
 	struct nvmem_cell_entry *entry;
@@ -374,22 +374,22 @@ destroy_cell:
 }
 
 /* default read/write permissions */
-static struct bin_attribute bin_attr_rw_nvmem = {
+static const struct bin_attribute bin_attr_rw_nvmem = {
 	.attr	= {
 		.name	= "nvmem",
 		.mode	= 0644,
 	},
-	.read	= bin_attr_nvmem_read,
-	.write	= bin_attr_nvmem_write,
+	.read_new	= bin_attr_nvmem_read,
+	.write_new	= bin_attr_nvmem_write,
 };
 
-static struct bin_attribute *nvmem_bin_attributes[] = {
+static const struct bin_attribute *const nvmem_bin_attributes[] = {
 	&bin_attr_rw_nvmem,
 	NULL,
 };
 
 static const struct attribute_group nvmem_bin_group = {
-	.bin_attrs	= nvmem_bin_attributes,
+	.bin_attrs_new	= nvmem_bin_attributes,
 	.attrs		= nvmem_attrs,
 	.is_bin_visible = nvmem_bin_attr_is_visible,
 	.bin_size	= nvmem_bin_attr_size,
@@ -401,12 +401,12 @@ static const struct attribute_group *nvmem_dev_groups[] = {
 	NULL,
 };
 
-static struct bin_attribute bin_attr_nvmem_eeprom_compat = {
+static const struct bin_attribute bin_attr_nvmem_eeprom_compat = {
 	.attr	= {
 		.name	= "eeprom",
 	},
-	.read	= bin_attr_nvmem_read,
-	.write	= bin_attr_nvmem_write,
+	.read_new	= bin_attr_nvmem_read,
+	.write_new	= bin_attr_nvmem_write,
 };
 
 /*
@@ -461,6 +461,7 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
 		.name	= "cells",
 	};
 	struct nvmem_cell_entry *entry;
+	const struct bin_attribute **pattrs;
 	struct bin_attribute *attrs;
 	unsigned int ncells = 0, i = 0;
 	int ret = 0;
@@ -472,9 +473,9 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
 
 	/* Allocate an array of attributes with a sentinel */
 	ncells = list_count_nodes(&nvmem->cells);
-	group.bin_attrs = devm_kcalloc(&nvmem->dev, ncells + 1,
-				       sizeof(struct bin_attribute *), GFP_KERNEL);
-	if (!group.bin_attrs) {
+	pattrs = devm_kcalloc(&nvmem->dev, ncells + 1,
+			      sizeof(struct bin_attribute *), GFP_KERNEL);
+	if (!pattrs) {
 		ret = -ENOMEM;
 		goto unlock_mutex;
 	}
@@ -494,17 +495,19 @@ static int nvmem_populate_sysfs_cells(struct nvmem_device *nvmem)
 						    entry->bit_offset);
 		attrs[i].attr.mode = 0444 & nvmem_bin_attr_get_umode(nvmem);
 		attrs[i].size = entry->bytes;
-		attrs[i].read = &nvmem_cell_attr_read;
+		attrs[i].read_new = &nvmem_cell_attr_read;
 		attrs[i].private = entry;
 		if (!attrs[i].attr.name) {
 			ret = -ENOMEM;
 			goto unlock_mutex;
 		}
 
-		group.bin_attrs[i] = &attrs[i];
+		pattrs[i] = &attrs[i];
 		i++;
 	}
 
+	group.bin_attrs_new = pattrs;
+
 	ret = device_add_group(&nvmem->dev, &group);
 	if (ret)
 		goto unlock_mutex;
@@ -1790,6 +1793,8 @@ static int __nvmem_cell_entry_write(struct nvmem_cell_entry *cell, void *buf, si
 		return -EINVAL;
 
 	if (cell->bit_offset || cell->nbits) {
+		if (len != BITS_TO_BYTES(cell->nbits) && len != cell->bytes)
+			return -EINVAL;
 		buf = nvmem_cell_prepare_write_buffer(cell, buf, len);
 		if (IS_ERR(buf))
 			return PTR_ERR(buf);
diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c
index 1ba494497698..ca6dd71d8a2e 100644
--- a/drivers/nvmem/imx-ocotp-ele.c
+++ b/drivers/nvmem/imx-ocotp-ele.c
@@ -71,13 +71,15 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	u32 *buf;
 	void *p;
 	int i;
+	u8 skipbytes;
 
-	index = offset;
-	num_bytes = round_up(bytes, 4);
-	count = num_bytes >> 2;
+	if (offset + bytes > priv->data->size)
+		bytes = priv->data->size - offset;
 
-	if (count > ((priv->data->size >> 2) - index))
-		count = (priv->data->size >> 2) - index;
+	index = offset >> 2;
+	skipbytes = offset - (index << 2);
+	num_bytes = round_up(bytes + skipbytes, 4);
+	count = num_bytes >> 2;
 
 	p = kzalloc(num_bytes, GFP_KERNEL);
 	if (!p)
@@ -100,7 +102,7 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 			*buf++ = readl_relaxed(reg + (i << 2));
 	}
 
-	memcpy(val, (u8 *)p, bytes);
+	memcpy(val, ((u8 *)p) + skipbytes, bytes);
 
 	mutex_unlock(&priv->lock);
 
@@ -109,6 +111,26 @@ static int imx_ocotp_reg_read(void *context, unsigned int offset, void *val, siz
 	return 0;
 };
 
+static int imx_ocotp_cell_pp(void *context, const char *id, int index,
+			     unsigned int offset, void *data, size_t bytes)
+{
+	u8 *buf = data;
+	int i;
+
+	/* Deal with some post processing of nvmem cell data */
+	if (id && !strcmp(id, "mac-address"))
+		for (i = 0; i < bytes / 2; i++)
+			swap(buf[i], buf[bytes - i - 1]);
+
+	return 0;
+}
+
+static void imx_ocotp_fixup_dt_cell_info(struct nvmem_device *nvmem,
+					 struct nvmem_cell_info *cell)
+{
+	cell->read_post_process = imx_ocotp_cell_pp;
+}
+
 static int imx_ele_ocotp_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -131,10 +153,12 @@ static int imx_ele_ocotp_probe(struct platform_device *pdev)
 	priv->config.owner = THIS_MODULE;
 	priv->config.size = priv->data->size;
 	priv->config.reg_read = priv->data->reg_read;
-	priv->config.word_size = 4;
+	priv->config.word_size = 1;
 	priv->config.stride = 1;
 	priv->config.priv = priv;
 	priv->config.read_only = true;
+	priv->config.add_legacy_fixed_of_cells = true;
+	priv->config.fixup_dt_cell_info = imx_ocotp_fixup_dt_cell_info;
 	mutex_init(&priv->lock);
 
 	nvmem = devm_nvmem_register(dev, &priv->config);
diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c
index 9aa8f42faa4c..4f1cca6eab71 100644
--- a/drivers/nvmem/qcom-spmi-sdam.c
+++ b/drivers/nvmem/qcom-spmi-sdam.c
@@ -144,6 +144,7 @@ static int sdam_probe(struct platform_device *pdev)
 	sdam->sdam_config.owner = THIS_MODULE;
 	sdam->sdam_config.add_legacy_fixed_of_cells = true;
 	sdam->sdam_config.stride = 1;
+	sdam->sdam_config.size = sdam->size;
 	sdam->sdam_config.word_size = 1;
 	sdam->sdam_config.reg_read = sdam_read;
 	sdam->sdam_config.reg_write = sdam_write;
diff --git a/drivers/nvmem/rmem.c b/drivers/nvmem/rmem.c
index 7f907c5a445e..b39d628cb60a 100644
--- a/drivers/nvmem/rmem.c
+++ b/drivers/nvmem/rmem.c
@@ -3,28 +3,40 @@
  * Copyright (C) 2020 Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
  */
 
+#include <linux/crc32.h>
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/nvmem-provider.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 struct rmem {
 	struct device *dev;
 	struct nvmem_device *nvmem;
 	struct reserved_mem *mem;
+};
+
+struct rmem_match_data {
+	int (*checksum)(struct rmem *priv);
+};
 
-	phys_addr_t size;
+struct __packed rmem_eyeq5_header {
+	u32 magic;
+	u32 version;
+	u32 size;
 };
 
+#define RMEM_EYEQ5_MAGIC	((u32)0xDABBAD00)
+
 static int rmem_read(void *context, unsigned int offset,
 		     void *val, size_t bytes)
 {
 	struct rmem *priv = context;
-	size_t available = priv->mem->size;
-	loff_t off = offset;
 	void *addr;
-	int count;
+
+	if ((phys_addr_t)offset + bytes > priv->mem->size)
+		return -EIO;
 
 	/*
 	 * Only map the reserved memory at this point to avoid potential rogue
@@ -36,26 +48,79 @@ static int rmem_read(void *context, unsigned int offset,
 	 * An alternative would be setting the memory as RO, set_memory_ro(),
 	 * but as of Dec 2020 this isn't possible on arm64.
 	 */
-	addr = memremap(priv->mem->base, available, MEMREMAP_WB);
+	addr = memremap(priv->mem->base, priv->mem->size, MEMREMAP_WB);
 	if (!addr) {
 		dev_err(priv->dev, "Failed to remap memory region\n");
 		return -ENOMEM;
 	}
 
-	count = memory_read_from_buffer(val, bytes, &off, addr, available);
+	memcpy(val, addr + offset, bytes);
 
 	memunmap(addr);
 
-	if (count < 0)
-		return count;
+	return 0;
+}
+
+static int rmem_eyeq5_checksum(struct rmem *priv)
+{
+	void *buf __free(kfree) = NULL;
+	struct rmem_eyeq5_header header;
+	u32 computed_crc, *target_crc;
+	size_t data_size;
+	int ret;
+
+	ret = rmem_read(priv, 0, &header, sizeof(header));
+	if (ret)
+		return ret;
+
+	if (header.magic != RMEM_EYEQ5_MAGIC)
+		return -EINVAL;
+
+	/*
+	 * Avoid massive kmalloc() if header read is invalid;
+	 * the check would be done by the next rmem_read() anyway.
+	 */
+	if (header.size > priv->mem->size)
+		return -EINVAL;
+
+	/*
+	 *           0 +-------------------+
+	 *             | Header (12 bytes) | \
+	 *             +-------------------+ |
+	 *             |                   | | data to be CRCed
+	 *             |        ...        | |
+	 *             |                   | /
+	 *   data_size +-------------------+
+	 *             |   CRC (4 bytes)   |
+	 * header.size +-------------------+
+	 */
+
+	buf = kmalloc(header.size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = rmem_read(priv, 0, buf, header.size);
+	if (ret)
+		return ret;
 
-	return count == bytes ? 0 : -EIO;
+	data_size = header.size - sizeof(*target_crc);
+	target_crc = buf + data_size;
+	computed_crc = crc32(U32_MAX, buf, data_size) ^ U32_MAX;
+
+	if (computed_crc == *target_crc)
+		return 0;
+
+	dev_err(priv->dev,
+		"checksum failed: computed %#x, expected %#x, header (%#x, %#x, %#x)\n",
+		computed_crc, *target_crc, header.magic, header.version, header.size);
+	return -EINVAL;
 }
 
 static int rmem_probe(struct platform_device *pdev)
 {
 	struct nvmem_config config = { };
 	struct device *dev = &pdev->dev;
+	const struct rmem_match_data *match_data = device_get_match_data(dev);
 	struct reserved_mem *mem;
 	struct rmem *priv;
 
@@ -78,10 +143,22 @@ static int rmem_probe(struct platform_device *pdev)
 	config.size = mem->size;
 	config.reg_read = rmem_read;
 
+	if (match_data && match_data->checksum) {
+		int ret = match_data->checksum(priv);
+
+		if (ret)
+			return ret;
+	}
+
 	return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config));
 }
 
+static const struct rmem_match_data rmem_eyeq5_match_data = {
+	.checksum = rmem_eyeq5_checksum,
+};
+
 static const struct of_device_id rmem_match[] = {
+	{ .compatible = "mobileye,eyeq5-bootloader-config", .data = &rmem_eyeq5_match_data },
 	{ .compatible = "nvmem-rmem", },
 	{ /* sentinel */ },
 };
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 6b5516ee670f..aedd0e2dcd89 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1130,13 +1130,7 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 
 static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
-	void *ptr = memblock_alloc(size, align);
-
-	if (!ptr)
-		panic("%s: Failed to allocate %llu bytes align=0x%llx\n",
-		      __func__, size, align);
-
-	return ptr;
+	return memblock_alloc_or_panic(size, align);
 }
 
 bool __init early_init_dt_verify(void *dt_virt, phys_addr_t dt_phys)
diff --git a/drivers/of/unittest-data/tests-platform.dtsi b/drivers/of/unittest-data/tests-platform.dtsi
index cd310b26b50c..4171f43cf01c 100644
--- a/drivers/of/unittest-data/tests-platform.dtsi
+++ b/drivers/of/unittest-data/tests-platform.dtsi
@@ -33,6 +33,11 @@
 					reg = <0x100>;
 				};
 			};
+
+			test-device@2 {
+				compatible = "test,rust-device";
+				reg = <0x2>;
+			};
 		};
 
 		platform-tests-2 {
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index bc3426480f3a..f88ddb1cf5d7 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -3689,13 +3689,7 @@ static struct device_node *overlay_base_root;
 
 static void * __init dt_alloc_memory(u64 size, u64 align)
 {
-	void *ptr = memblock_alloc(size, align);
-
-	if (!ptr)
-		panic("%s: Failed to allocate %llu bytes align=0x%llx\n",
-		      __func__, size, align);
-
-	return ptr;
+	return memblock_alloc_or_panic(size, align);
 }
 
 /*
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index 105de7c3274a..8fc6238b1728 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -217,7 +217,7 @@ static void opp_migrate_dentry(struct opp_device *opp_dev,
 {
 	struct opp_device *new_dev = NULL, *iter;
 	const struct device *dev;
-	struct dentry *dentry;
+	int err;
 
 	/* Look for next opp-dev */
 	list_for_each_entry(iter, &opp_table->dev_list, node)
@@ -234,16 +234,14 @@ static void opp_migrate_dentry(struct opp_device *opp_dev,
 
 	opp_set_dev_name(dev, opp_table->dentry_name);
 
-	dentry = debugfs_rename(rootdir, opp_dev->dentry, rootdir,
-				opp_table->dentry_name);
-	if (IS_ERR(dentry)) {
+	err = debugfs_change_name(opp_dev->dentry, "%s", opp_table->dentry_name);
+	if (err) {
 		dev_err(dev, "%s: Failed to rename link from: %s to %s\n",
 			__func__, dev_name(opp_dev->dev), dev_name(dev));
 		return;
 	}
 
-	new_dev->dentry = dentry;
-	opp_table->dentry = dentry;
+	new_dev->dentry = opp_table->dentry = opp_dev->dentry;
 }
 
 /**
diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c
index 3644997a8342..24d4f3a3ec3d 100644
--- a/drivers/parport/parport_serial.c
+++ b/drivers/parport/parport_serial.c
@@ -266,10 +266,14 @@ static struct pci_device_id parport_serial_pci_tbl[] = {
 	{ 0x1409, 0x7168, 0x1409, 0xd079, 0, 0, timedia_9079c },
 
 	/* WCH CARDS */
-	{ 0x4348, 0x5053, PCI_ANY_ID, PCI_ANY_ID, 0, 0, wch_ch353_1s1p},
-	{ 0x4348, 0x7053, 0x4348, 0x3253, 0, 0, wch_ch353_2s1p},
-	{ 0x1c00, 0x3050, 0x1c00, 0x3050, 0, 0, wch_ch382_0s1p},
-	{ 0x1c00, 0x3250, 0x1c00, 0x3250, 0, 0, wch_ch382_2s1p},
+	{ PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_1S1P,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, wch_ch353_1s1p },
+	{ PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_2S1P,
+	  0x4348, 0x3253, 0, 0, wch_ch353_2s1p },
+	{ PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_0S1P,
+	  0x1c00, 0x3050, 0, 0, wch_ch382_0s1p },
+	{ PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_2S1P,
+	  0x1c00, 0x3250, 0, 0, wch_ch382_2s1p },
 
 	/* BrainBoxes PX272/PX306 MIO card */
 	{ PCI_VENDOR_ID_INTASHIELD, 0x4100,
diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c
index d1d97a4bb36d..3431a7df3e0d 100644
--- a/drivers/pci/devres.c
+++ b/drivers/pci/devres.c
@@ -419,19 +419,12 @@ static void pcim_intx_restore(struct device *dev, void *data)
 	pci_intx(pdev, res->orig_intx);
 }
 
-static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev)
+static void save_orig_intx(struct pci_dev *pdev, struct pcim_intx_devres *res)
 {
-	struct pcim_intx_devres *res;
-
-	res = devres_find(dev, pcim_intx_restore, NULL, NULL);
-	if (res)
-		return res;
+	u16 pci_command;
 
-	res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL);
-	if (res)
-		devres_add(dev, res);
-
-	return res;
+	pci_read_config_word(pdev, PCI_COMMAND, &pci_command);
+	res->orig_intx = !(pci_command & PCI_COMMAND_INTX_DISABLE);
 }
 
 /**
@@ -447,12 +440,23 @@ static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev)
 int pcim_intx(struct pci_dev *pdev, int enable)
 {
 	struct pcim_intx_devres *res;
+	struct device *dev = &pdev->dev;
 
-	res = get_or_create_intx_devres(&pdev->dev);
-	if (!res)
-		return -ENOMEM;
+	/*
+	 * pcim_intx() must only restore the INTx value that existed before the
+	 * driver was loaded, i.e., before it called pcim_intx() for the
+	 * first time.
+	 */
+	res = devres_find(dev, pcim_intx_restore, NULL, NULL);
+	if (!res) {
+		res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL);
+		if (!res)
+			return -ENOMEM;
+
+		save_orig_intx(pdev, res);
+		devres_add(dev, res);
+	}
 
-	res->orig_intx = !enable;
 	pci_intx(pdev, enable);
 
 	return 0;
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index e0bc90597dca..da3e7edcf49d 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -108,9 +108,6 @@ void pci_save_aspm_l1ss_state(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cap++);
 	pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cap++);
 
-	if (parent->state_saved)
-		return;
-
 	/*
 	 * Save parent's L1 substate configuration so we have it for
 	 * pci_restore_aspm_l1ss_state(pdev) to restore.
diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
index 1e604fbbda65..07de59ca2ebf 100644
--- a/drivers/pci/tph.c
+++ b/drivers/pci/tph.c
@@ -360,7 +360,7 @@ int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag)
 		return err;
 	}
 
-	set_ctrl_reg_req_en(pdev, pdev->tph_mode);
+	set_ctrl_reg_req_en(pdev, pdev->tph_req_type);
 
 	pci_dbg(pdev, "set steering tag: %s table, index=%d, tag=%#04x\n",
 		(loc == PCI_TPH_LOC_MSIX) ? "MSI-X" : "ST", index, tag);
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index b5cc11abc962..0e360feb3432 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -1279,7 +1279,7 @@ static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int
 	return 0;
 }
 
-static struct ctl_table armv8_pmu_sysctl_table[] = {
+static const struct ctl_table armv8_pmu_sysctl_table[] = {
 	{
 		.procname       = "perf_user_access",
 		.data		= &sysctl_perf_user_access,
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 194c153e5d71..698de8ddf895 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -1317,7 +1317,7 @@ static int riscv_pmu_proc_user_access_handler(const struct ctl_table *table,
 	return 0;
 }
 
-static struct ctl_table sbi_pmu_sysctl_table[] = {
+static const struct ctl_table sbi_pmu_sysctl_table[] = {
 	{
 		.procname       = "perf_user_access",
 		.data		= &sysctl_perf_user_access,
diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index cd159a71b23c..29b8fd4b9351 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -23,7 +23,6 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/phy/phy.h>
 #include <linux/phy/phy-sun4i-usb.h>
 #include <linux/platform_device.h>
diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index d3ccf547ba1c..45004f598e4d 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -331,25 +331,17 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 {
 	u32 pclk = cfg->pixclk;
 	u32 fld_tg_code;
-	u32 pclk_khz;
-	u8 div = 1;
-
-	switch (cfg->pixclk) {
-	case  22250000 ...  47500000:
-		div = 1;
-		break;
-	case  50349650 ...  99000000:
-		div = 2;
-		break;
-	case 100699300 ... 198000000:
-		div = 4;
-		break;
-	case 205000000 ... 297000000:
-		div = 8;
-		break;
+	u32 int_pllclk;
+	u8 div;
+
+	/* Find int_pllclk speed */
+	for (div = 0; div < 4; div++) {
+		int_pllclk = pclk / (1 << div);
+		if (int_pllclk < (50 * MHZ))
+			break;
 	}
 
-	writeb(FIELD_PREP(REG12_CK_DIV_MASK, ilog2(div)), phy->regs + PHY_REG(12));
+	writeb(FIELD_PREP(REG12_CK_DIV_MASK, div), phy->regs + PHY_REG(12));
 
 	/*
 	 * Calculation for the frequency lock detector target code (fld_tg_code)
@@ -362,10 +354,8 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 	 *        settings rounding up always too. TODO: Check if that is
 	 *        correct.
 	 */
-	pclk /= div;
-	pclk_khz = pclk / 1000;
-	fld_tg_code = 256 * 1000 * 1000 / pclk_khz * 24;
-	fld_tg_code = DIV_ROUND_UP(fld_tg_code, 1000);
+
+	fld_tg_code =  DIV_ROUND_UP(24 * MHZ * 256, int_pllclk);
 
 	/* FLD_TOL and FLD_RP_CODE taken from downstream driver */
 	writeb(FIELD_PREP(REG13_TG_CODE_LOW_MASK, fld_tg_code),
@@ -406,16 +396,15 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1
 				continue;
 
 			/*
-			 * TODO: Ref Manual doesn't state the range of _m
-			 * so this should be further refined if possible.
-			 * This range was set based on the original values
-			 * in the lookup table
+			 * The Ref manual doesn't explicitly state the range of M,
+			 * but it does show it as an 8-bit value, so reject
+			 * any value above 255.
 			 */
 			tmp = (u64)fout * (_p * _s);
 			do_div(tmp, 24 * MHZ);
-			_m = tmp;
-			if (_m < 0x30 || _m > 0x7b)
+			if (tmp > 255)
 				continue;
+			_m = tmp;
 
 			/*
 			 * Rev 2 of the Ref Manual states the
@@ -440,9 +429,13 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1
 				min_delta = delta;
 				best_freq = tmp;
 			}
+
+			/* If we have an exact match, stop looking for a better value */
+			if (!delta)
+				goto done;
 		}
 	}
-
+done:
 	if (best_freq) {
 		*p = best_p;
 		*m = best_m;
diff --git a/drivers/phy/hisilicon/phy-hi3670-pcie.c b/drivers/phy/hisilicon/phy-hi3670-pcie.c
index 0ac9634b398d..dbc7dcce682b 100644
--- a/drivers/phy/hisilicon/phy-hi3670-pcie.c
+++ b/drivers/phy/hisilicon/phy-hi3670-pcie.c
@@ -16,15 +16,20 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/bits.h>
 #include <linux/clk.h>
-#include <linux/gpio.h>
-#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
 #include <linux/mfd/syscon.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
-#include <linux/of_gpio.h>
+#include <linux/of.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
+#include <linux/types.h>
 
 #define AXI_CLK_FREQ				207500000
 #define REF_CLK_FREQ				100000000
diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
index fefc02d921e6..71f9c14fb50d 100644
--- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
+++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
@@ -422,7 +422,7 @@ static int mvebu_comphy_ethernet_init_reset(struct mvebu_comphy_lane *lane)
 	/* wait until clocks are ready */
 	mdelay(1);
 
-	/* exlicitly disable 40B, the bits isn't clear on reset */
+	/* explicitly disable 40B, the bits isn't clear on reset */
 	regmap_read(priv->regmap, MVEBU_COMPHY_CONF6(lane->id), &val);
 	val &= ~MVEBU_COMPHY_CONF6_40B;
 	regmap_write(priv->regmap, MVEBU_COMPHY_CONF6(lane->id), val);
diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c
index bbfe11d6a69d..b38f3ae26b3f 100644
--- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c
+++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c
@@ -9,6 +9,8 @@
 #include <linux/module.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
 #include <linux/types.h>
 #include <linux/units.h>
 #include <linux/nvmem-consumer.h>
@@ -478,8 +480,50 @@ static int mtk_hdmi_phy_configure(struct phy *phy, union phy_configure_opts *opt
 	return ret;
 }
 
+static int mtk_hdmi_phy_pwr5v_enable(struct regulator_dev *rdev)
+{
+	struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev);
+
+	mtk_phy_set_bits(hdmi_phy->regs + HDMI_CTL_1, RG_HDMITX_PWR5V_O);
+
+	return 0;
+}
+
+static int mtk_hdmi_phy_pwr5v_disable(struct regulator_dev *rdev)
+{
+	struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev);
+
+	mtk_phy_clear_bits(hdmi_phy->regs + HDMI_CTL_1, RG_HDMITX_PWR5V_O);
+
+	return 0;
+}
+
+static int mtk_hdmi_phy_pwr5v_is_enabled(struct regulator_dev *rdev)
+{
+	struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev);
+
+	return !!(readl(hdmi_phy->regs + HDMI_CTL_1) & RG_HDMITX_PWR5V_O);
+}
+
+static const struct regulator_ops mtk_hdmi_pwr5v_regulator_ops = {
+	.enable = mtk_hdmi_phy_pwr5v_enable,
+	.disable = mtk_hdmi_phy_pwr5v_disable,
+	.is_enabled = mtk_hdmi_phy_pwr5v_is_enabled
+};
+
+static const struct regulator_desc mtk_hdmi_phy_pwr5v_desc = {
+	.name = "hdmi-pwr5v",
+	.id = -1,
+	.n_voltages = 1,
+	.fixed_uV = 5000000,
+	.ops = &mtk_hdmi_pwr5v_regulator_ops,
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+};
+
 struct mtk_hdmi_phy_conf mtk_hdmi_phy_8195_conf = {
 	.flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
+	.hdmi_phy_regulator_desc = &mtk_hdmi_phy_pwr5v_desc,
 	.hdmi_phy_clk_ops = &mtk_hdmi_pll_ops,
 	.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
 	.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,
diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h
index 22a68dc9550c..e26caaf4d104 100644
--- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h
+++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h
@@ -103,6 +103,9 @@
 #define HDMI_ANA_CTL 0x7c
 #define REG_ANA_HDMI20_FIFO_EN BIT(16)
 
+#define HDMI_CTL_1 0xc4
+#define RG_HDMITX_PWR5V_O BIT(9)
+
 #define HDMI_CTL_3 0xcc
 #define REG_HDMITXPLL_DIV GENMASK(4, 0)
 #define REG_HDMITX_REF_XTAL_SEL BIT(7)
diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.c b/drivers/phy/mediatek/phy-mtk-hdmi.c
index d2e824771f9d..52a7d525ff9b 100644
--- a/drivers/phy/mediatek/phy-mtk-hdmi.c
+++ b/drivers/phy/mediatek/phy-mtk-hdmi.c
@@ -75,6 +75,28 @@ static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy,
 	clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops;
 }
 
+static int mtk_hdmi_phy_register_regulators(struct mtk_hdmi_phy *hdmi_phy)
+{
+	const struct regulator_desc *vreg_desc = hdmi_phy->conf->hdmi_phy_regulator_desc;
+	const struct regulator_init_data vreg_init_data = {
+		.constraints = {
+			.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+		}
+	};
+	struct regulator_config vreg_config = {
+		.dev = hdmi_phy->dev,
+		.driver_data = hdmi_phy,
+		.init_data = &vreg_init_data,
+		.of_node = hdmi_phy->dev->of_node
+	};
+
+	hdmi_phy->rdev = devm_regulator_register(hdmi_phy->dev, vreg_desc, &vreg_config);
+	if (IS_ERR(hdmi_phy->rdev))
+		return PTR_ERR(hdmi_phy->rdev);
+
+	return 0;
+}
+
 static int mtk_hdmi_phy_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -150,6 +172,12 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev)
 	if (hdmi_phy->conf->pll_default_off)
 		hdmi_phy->conf->hdmi_phy_disable_tmds(hdmi_phy);
 
+	if (hdmi_phy->conf->hdmi_phy_regulator_desc) {
+		ret = mtk_hdmi_phy_register_regulators(hdmi_phy);
+		if (ret)
+			return ret;
+	}
+
 	return of_clk_add_provider(dev->of_node, of_clk_src_simple_get,
 				   hdmi_phy->pll);
 }
diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.h b/drivers/phy/mediatek/phy-mtk-hdmi.h
index 71c02d043485..99d917e0036a 100644
--- a/drivers/phy/mediatek/phy-mtk-hdmi.h
+++ b/drivers/phy/mediatek/phy-mtk-hdmi.h
@@ -13,6 +13,8 @@
 #include <linux/module.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
 #include <linux/types.h>
 
 struct mtk_hdmi_phy;
@@ -20,6 +22,7 @@ struct mtk_hdmi_phy;
 struct mtk_hdmi_phy_conf {
 	unsigned long flags;
 	bool pll_default_off;
+	const struct regulator_desc *hdmi_phy_regulator_desc;
 	const struct clk_ops *hdmi_phy_clk_ops;
 	void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
 	void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
@@ -32,6 +35,7 @@ struct mtk_hdmi_phy {
 	struct mtk_hdmi_phy_conf *conf;
 	struct clk *pll;
 	struct clk_hw pll_hw;
+	struct regulator_dev *rdev;
 	unsigned long pll_rate;
 	unsigned char drv_imp_clk;
 	unsigned char drv_imp_d2;
diff --git a/drivers/phy/mediatek/phy-mtk-tphy.c b/drivers/phy/mediatek/phy-mtk-tphy.c
index 3f7095ec5978..a496fbe3352b 100644
--- a/drivers/phy/mediatek/phy-mtk-tphy.c
+++ b/drivers/phy/mediatek/phy-mtk-tphy.c
@@ -381,17 +381,12 @@ static const char *const u3_phy_files[] = {
 static int u2_phy_params_show(struct seq_file *sf, void *unused)
 {
 	struct mtk_phy_instance *inst = sf->private;
-	const char *fname = file_dentry(sf->file)->d_iname;
 	struct u2phy_banks *u2_banks = &inst->u2_banks;
 	void __iomem *com = u2_banks->com;
 	u32 max = 0;
 	u32 tmp = 0;
 	u32 val = 0;
-	int ret;
-
-	ret = match_string(u2_phy_files, ARRAY_SIZE(u2_phy_files), fname);
-	if (ret < 0)
-		return ret;
+	int ret = debugfs_get_aux_num(sf->file);
 
 	switch (ret) {
 	case U2P_EYE_VRT:
@@ -438,7 +433,7 @@ static int u2_phy_params_show(struct seq_file *sf, void *unused)
 		break;
 	}
 
-	seq_printf(sf, "%s : %d [0, %d]\n", fname, val, max);
+	seq_printf(sf, "%s : %d [0, %d]\n", u2_phy_files[ret], val, max);
 
 	return 0;
 }
@@ -451,23 +446,18 @@ static int u2_phy_params_open(struct inode *inode, struct file *file)
 static ssize_t u2_phy_params_write(struct file *file, const char __user *ubuf,
 				   size_t count, loff_t *ppos)
 {
-	const char *fname = file_dentry(file)->d_iname;
 	struct seq_file *sf = file->private_data;
 	struct mtk_phy_instance *inst = sf->private;
 	struct u2phy_banks *u2_banks = &inst->u2_banks;
 	void __iomem *com = u2_banks->com;
 	ssize_t rc;
 	u32 val;
-	int ret;
+	int ret = debugfs_get_aux_num(file);
 
 	rc = kstrtouint_from_user(ubuf, USER_BUF_LEN(count), 0, &val);
 	if (rc)
 		return rc;
 
-	ret = match_string(u2_phy_files, ARRAY_SIZE(u2_phy_files), fname);
-	if (ret < 0)
-		return (ssize_t)ret;
-
 	switch (ret) {
 	case U2P_EYE_VRT:
 		mtk_phy_update_field(com + U3P_USBPHYACR1, PA1_RG_VRT_SEL, val);
@@ -516,23 +506,18 @@ static void u2_phy_dbgfs_files_create(struct mtk_phy_instance *inst)
 	int i;
 
 	for (i = 0; i < count; i++)
-		debugfs_create_file(u2_phy_files[i], 0644, inst->phy->debugfs,
-				    inst, &u2_phy_fops);
+		debugfs_create_file_aux_num(u2_phy_files[i], 0644, inst->phy->debugfs,
+				    inst, i,  &u2_phy_fops);
 }
 
 static int u3_phy_params_show(struct seq_file *sf, void *unused)
 {
 	struct mtk_phy_instance *inst = sf->private;
-	const char *fname = file_dentry(sf->file)->d_iname;
 	struct u3phy_banks *u3_banks = &inst->u3_banks;
 	u32 val = 0;
 	u32 max = 0;
 	u32 tmp;
-	int ret;
-
-	ret = match_string(u3_phy_files, ARRAY_SIZE(u3_phy_files), fname);
-	if (ret < 0)
-		return ret;
+	int ret = debugfs_get_aux_num(sf->file);
 
 	switch (ret) {
 	case U3P_EFUSE_EN:
@@ -564,7 +549,7 @@ static int u3_phy_params_show(struct seq_file *sf, void *unused)
 		break;
 	}
 
-	seq_printf(sf, "%s : %d [0, %d]\n", fname, val, max);
+	seq_printf(sf, "%s : %d [0, %d]\n", u3_phy_files[ret], val, max);
 
 	return 0;
 }
@@ -577,23 +562,18 @@ static int u3_phy_params_open(struct inode *inode, struct file *file)
 static ssize_t u3_phy_params_write(struct file *file, const char __user *ubuf,
 				   size_t count, loff_t *ppos)
 {
-	const char *fname = file_dentry(file)->d_iname;
 	struct seq_file *sf = file->private_data;
 	struct mtk_phy_instance *inst = sf->private;
 	struct u3phy_banks *u3_banks = &inst->u3_banks;
 	void __iomem *phyd = u3_banks->phyd;
 	ssize_t rc;
 	u32 val;
-	int ret;
+	int ret = debugfs_get_aux_num(sf->file);
 
 	rc = kstrtouint_from_user(ubuf, USER_BUF_LEN(count), 0, &val);
 	if (rc)
 		return rc;
 
-	ret = match_string(u3_phy_files, ARRAY_SIZE(u3_phy_files), fname);
-	if (ret < 0)
-		return (ssize_t)ret;
-
 	switch (ret) {
 	case U3P_EFUSE_EN:
 		mtk_phy_update_field(phyd + U3P_U3_PHYD_RSV,
@@ -636,8 +616,8 @@ static void u3_phy_dbgfs_files_create(struct mtk_phy_instance *inst)
 	int i;
 
 	for (i = 0; i < count; i++)
-		debugfs_create_file(u3_phy_files[i], 0644, inst->phy->debugfs,
-				    inst, &u3_phy_fops);
+		debugfs_create_file_aux_num(u3_phy_files[i], 0644, inst->phy->debugfs,
+				    inst, i, &u3_phy_fops);
 }
 
 static int phy_type_show(struct seq_file *sf, void *unused)
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 413f76e2d174..8dfdce605a90 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -749,8 +749,8 @@ EXPORT_SYMBOL_GPL(devm_phy_put);
 
 /**
  * of_phy_simple_xlate() - returns the phy instance from phy provider
- * @dev: the PHY provider device
- * @args: of_phandle_args (not used here)
+ * @dev: the PHY provider device (not used here)
+ * @args: of_phandle_args
  *
  * Intended to be used by phy provider for the common case where #phy-cells is
  * 0. For other cases where #phy-cells is greater than '0', the phy provider
@@ -760,21 +760,14 @@ EXPORT_SYMBOL_GPL(devm_phy_put);
 struct phy *of_phy_simple_xlate(struct device *dev,
 				const struct of_phandle_args *args)
 {
-	struct phy *phy;
-	struct class_dev_iter iter;
-
-	class_dev_iter_init(&iter, &phy_class, NULL, NULL);
-	while ((dev = class_dev_iter_next(&iter))) {
-		phy = to_phy(dev);
-		if (args->np != phy->dev.of_node)
-			continue;
+	struct device *target_dev;
 
-		class_dev_iter_exit(&iter);
-		return phy;
-	}
+	target_dev = class_find_device_by_of_node(&phy_class, args->np);
+	if (!target_dev)
+		return ERR_PTR(-ENODEV);
 
-	class_dev_iter_exit(&iter);
-	return ERR_PTR(-ENODEV);
+	put_device(target_dev);
+	return to_phy(target_dev);
 }
 EXPORT_SYMBOL_GPL(of_phy_simple_xlate);
 
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index 3bae39381fd0..b09fa00e9fe7 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -400,6 +400,57 @@ static const struct qmp_phy_init_tbl qmp_v3_usb3_pcs_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13),
 };
 
+static const struct qmp_phy_init_tbl sar2130p_usb3_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x2e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xd5),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xb7),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xb7),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x12),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE0, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xd5),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x05),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x25),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC, 0x0c),
+};
+
 static const struct qmp_phy_init_tbl sm6350_usb3_rx_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b),
 	QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f),
@@ -1730,6 +1781,51 @@ static const struct qmp_combo_offsets qmp_combo_offsets_v5 = {
 	.dp_dp_phy	= 0x2200,
 };
 
+static const struct qmp_phy_cfg sar2130p_usb3dpphy_cfg = {
+	.offsets		= &qmp_combo_offsets_v3,
+
+	.serdes_tbl		= sar2130p_usb3_serdes_tbl,
+	.serdes_tbl_num		= ARRAY_SIZE(sar2130p_usb3_serdes_tbl),
+	.tx_tbl			= sm8550_usb3_tx_tbl,
+	.tx_tbl_num		= ARRAY_SIZE(sm8550_usb3_tx_tbl),
+	.rx_tbl			= sm8550_usb3_rx_tbl,
+	.rx_tbl_num		= ARRAY_SIZE(sm8550_usb3_rx_tbl),
+	.pcs_tbl		= sm8550_usb3_pcs_tbl,
+	.pcs_tbl_num		= ARRAY_SIZE(sm8550_usb3_pcs_tbl),
+	.pcs_usb_tbl		= sm8550_usb3_pcs_usb_tbl,
+	.pcs_usb_tbl_num	= ARRAY_SIZE(sm8550_usb3_pcs_usb_tbl),
+
+	.dp_serdes_tbl		= qmp_v6_dp_serdes_tbl,
+	.dp_serdes_tbl_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl),
+	.dp_tx_tbl		= qmp_v6_dp_tx_tbl,
+	.dp_tx_tbl_num		= ARRAY_SIZE(qmp_v6_dp_tx_tbl),
+
+	.serdes_tbl_rbr		= qmp_v6_dp_serdes_tbl_rbr,
+	.serdes_tbl_rbr_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr),
+	.serdes_tbl_hbr		= qmp_v6_dp_serdes_tbl_hbr,
+	.serdes_tbl_hbr_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr),
+	.serdes_tbl_hbr2	= qmp_v6_dp_serdes_tbl_hbr2,
+	.serdes_tbl_hbr2_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2),
+	.serdes_tbl_hbr3	= qmp_v6_dp_serdes_tbl_hbr3,
+	.serdes_tbl_hbr3_num	= ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3),
+
+	.swing_hbr_rbr		= &qmp_dp_v5_voltage_swing_hbr_rbr,
+	.pre_emphasis_hbr_rbr	= &qmp_dp_v6_pre_emphasis_hbr_rbr,
+	.swing_hbr3_hbr2	= &qmp_dp_v5_voltage_swing_hbr3_hbr2,
+	.pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2,
+
+	.dp_aux_init		= qmp_v4_dp_aux_init,
+	.configure_dp_tx	= qmp_v4_configure_dp_tx,
+	.configure_dp_phy	= qmp_v4_configure_dp_phy,
+	.calibrate_dp_phy	= qmp_v4_calibrate_dp_phy,
+
+	.regs			= qmp_v6_usb3phy_regs_layout,
+	.reset_list		= msm8996_usb3phy_reset_l,
+	.num_resets		= ARRAY_SIZE(msm8996_usb3phy_reset_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+};
+
 static const struct qmp_phy_cfg sc7180_usb3dpphy_cfg = {
 	.offsets		= &qmp_combo_offsets_v3,
 
@@ -3768,6 +3864,10 @@ err_node_put:
 
 static const struct of_device_id qmp_combo_of_match_table[] = {
 	{
+		.compatible = "qcom,sar2130p-qmp-usb3-dp-phy",
+		.data = &sar2130p_usb3dpphy_cfg,
+	},
+	{
 		.compatible = "qcom,sc7180-qmp-usb3-dp-phy",
 		.data = &sc7180_usb3dpphy_cfg,
 	},
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index 873f2f9844c6..018bbb300830 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -728,6 +728,83 @@ static const struct qmp_phy_init_tbl ipq9574_gen3x2_pcie_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1),
 };
 
+static const struct qmp_phy_init_tbl qcs615_pcie_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x18),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_ENABLE1, 0x10),
+	QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0xf),
+	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x1),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x0),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x6),
+	QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0xf),
+	QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x0),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SVS_MODE_CLK_SEL, 0x1),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CORE_CLK_EN, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CORECLK_DIV, 0xa),
+	QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL, 0x20),
+	QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0x9),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x4),
+	QMP_PHY_INIT_CFG(QSERDES_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START3_MODE0, 0x3),
+	QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START2_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START1_MODE0, 0x55),
+	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP3_MODE0, 0x0),
+	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP2_MODE0, 0xd),
+	QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP1_MODE0, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_SELECT, 0x35),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SYS_CLK_CTRL, 0x2),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_BUF_ENABLE, 0x1f),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CP_CTRL_MODE0, 0x4),
+	QMP_PHY_INIT_CFG(QSERDES_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_COM_PLL_CCTRL_MODE0, 0x30),
+	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x0),
+	QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80),
+	QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x1),
+	QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0xa),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x1),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x1),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER1, 0x2),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER2, 0x0),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0x2f),
+	QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x19),
+	QMP_PHY_INIT_CFG(QSERDES_COM_CLK_EP_DIV, 0x19),
+};
+
+static const struct qmp_phy_init_tbl qcs615_pcie_rx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_ENABLES, 0x1c),
+	QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_DEGLITCH_CNTRL, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2, 0x1),
+	QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL3, 0x0),
+	QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL4, 0xdb),
+	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b),
+	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN, 0x4),
+	QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN_HALF, 0x4),
+};
+
+static const struct qmp_phy_init_tbl qcs615_pcie_tx_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_TX_HIGHZ_TRANSCEIVEREN_BIAS_DRVR_EN, 0x45),
+	QMP_PHY_INIT_CFG(QSERDES_TX_LANE_MODE, 0x6),
+	QMP_PHY_INIT_CFG(QSERDES_TX_RES_CODE_LANE_OFFSET, 0x2),
+	QMP_PHY_INIT_CFG(QSERDES_TX_RCV_DETECT_LVL_2, 0x12),
+};
+
+static const struct qmp_phy_init_tbl qcs615_pcie_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_ENDPOINT_REFCLK_DRIVE, 0x4),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_OSC_DTCT_ACTIONS, 0x0),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_MSB, 0x0),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_LSB, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME_AUXCLK_LSB, 0x0),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_LP_WAKEUP_DLY_TIME_AUXCLK, 0x40),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME, 0x73),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_SIGDET_CNTRL, 0x7),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_RX_SIGDET_LVL, 0x99),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_TXDEEMPH_M6DB_V0, 0x15),
+	QMP_PHY_INIT_CFG(QPHY_V2_PCS_TXDEEMPH_M3P5DB_V0, 0xe),
+};
+
 static const struct qmp_phy_init_tbl sdm845_qmp_pcie_serdes_tbl[] = {
 	QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x14),
 	QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30),
@@ -1773,7 +1850,7 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_rc_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00),
 };
 
-static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_misc_tbl[] = {
+static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_lane1_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00),
 	QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00),
 };
@@ -1907,6 +1984,9 @@ static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_misc_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG2, 0x0d),
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5, 0x02),
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN, 0x2e),
+};
+
+static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_lane1_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00),
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00),
 };
@@ -2582,8 +2662,6 @@ static const struct qmp_phy_init_tbl sa8775p_qmp_gen4_pcie_rc_pcs_misc_tbl[] = {
 static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_pcs_alt_tbl[] = {
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG4, 0x16),
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG5, 0x22),
-	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00),
-	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00),
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_G3S2_PRE_GAIN, 0x2e),
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_RX_SIGDET_LVL, 0x66),
 };
@@ -2724,10 +2802,106 @@ static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_ep_pcs_alt_tbl[] =
 	QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_INSIG_SW_CTRL7, 0x00),
 };
 
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x4c),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x90),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x08),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x1a),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x68),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xea),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xaa),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x34),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC_3, 0x0f),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0),
+};
+
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2, 0x01),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_LANE1_INSIG_MX_CTRL2, 0x01),
+};
+
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_tx_tbl[] = {
+	QMP_PHY_INIT_CFG_LANE(QSERDES_V6_TX_BIST_MODE_LANENO, 0x00, 2),
+};
+
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB, 0x17),
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_G3S2_PRE_GAIN, 0x2e),
+};
+
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl[] = {
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x06),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x28),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x0d),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x00),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0xff),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x09),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x19),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0xfb),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE0, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1, 0xfb),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE1, 0x03),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_MODE, 0x14),
+	QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0),
+};
+
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB, 0x17),
+};
+
+static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl[] = {
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_EQ_CONFIG1, 0x1e),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG2, 0x14),
+	QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG4, 0x07),
+};
+
 struct qmp_pcie_offsets {
 	u16 serdes;
 	u16 pcs;
 	u16 pcs_misc;
+	u16 pcs_lane1;
 	u16 tx;
 	u16 rx;
 	u16 tx2;
@@ -2752,6 +2926,8 @@ struct qmp_phy_cfg_tbls {
 	int pcs_num;
 	const struct qmp_phy_init_tbl *pcs_misc;
 	int pcs_misc_num;
+	const struct qmp_phy_init_tbl *pcs_lane1;
+	int pcs_lane1_num;
 	const struct qmp_phy_init_tbl *ln_shrd;
 	int ln_shrd_num;
 };
@@ -2811,6 +2987,7 @@ struct qmp_pcie {
 	void __iomem *serdes;
 	void __iomem *pcs;
 	void __iomem *pcs_misc;
+	void __iomem *pcs_lane1;
 	void __iomem *tx;
 	void __iomem *rx;
 	void __iomem *tx2;
@@ -2927,6 +3104,7 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v4_20 = {
 	.serdes		= 0x1000,
 	.pcs		= 0x1200,
 	.pcs_misc	= 0x1600,
+	.pcs_lane1	= 0x1e00,
 	.tx		= 0x0000,
 	.rx		= 0x0200,
 	.tx2		= 0x0800,
@@ -2957,6 +3135,7 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v5_20 = {
 	.serdes		= 0x1000,
 	.pcs		= 0x1200,
 	.pcs_misc	= 0x1400,
+	.pcs_lane1	= 0x1e00,
 	.tx		= 0x0000,
 	.rx		= 0x0200,
 	.tx2		= 0x0800,
@@ -3132,6 +3311,31 @@ static const struct qmp_phy_cfg ipq9574_gen3x2_pciephy_cfg = {
 	.pipe_clock_rate	= 250000000,
 };
 
+static const struct qmp_phy_cfg qcs615_pciephy_cfg = {
+	.lanes			= 1,
+
+	.offsets		= &qmp_pcie_offsets_v2,
+
+	.tbls = {
+		.serdes		= qcs615_pcie_serdes_tbl,
+		.serdes_num	= ARRAY_SIZE(qcs615_pcie_serdes_tbl),
+		.tx		= qcs615_pcie_tx_tbl,
+		.tx_num		= ARRAY_SIZE(qcs615_pcie_tx_tbl),
+		.rx		= qcs615_pcie_rx_tbl,
+		.rx_num		= ARRAY_SIZE(qcs615_pcie_rx_tbl),
+		.pcs		= qcs615_pcie_pcs_tbl,
+		.pcs_num	= ARRAY_SIZE(qcs615_pcie_pcs_tbl),
+	},
+	.reset_list		= sdm845_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(sdm845_pciephy_reset_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= pciephy_v2_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS,
+};
+
 static const struct qmp_phy_cfg sdm845_qmp_pciephy_cfg = {
 	.lanes			= 1,
 
@@ -3283,6 +3487,49 @@ static const struct qmp_phy_cfg msm8998_pciephy_cfg = {
 	.skip_start_delay	= true,
 };
 
+static const struct qmp_phy_cfg sar2130p_qmp_gen3x2_pciephy_cfg = {
+	.lanes = 2,
+
+	.offsets		= &qmp_pcie_offsets_v5,
+
+	.tbls = {
+		.tx		= sm8550_qmp_gen3x2_pcie_tx_tbl,
+		.tx_num		= ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_tx_tbl),
+		.rx		= sm8550_qmp_gen3x2_pcie_rx_tbl,
+		.rx_num		= ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_rx_tbl),
+		.pcs		= sm8550_qmp_gen3x2_pcie_pcs_tbl,
+		.pcs_num	= ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_pcs_tbl),
+		.pcs_lane1	= sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl,
+		.pcs_lane1_num	= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl),
+	},
+	.tbls_rc = &(const struct qmp_phy_cfg_tbls) {
+		.serdes		= sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl,
+		.serdes_num	= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl),
+		.tx		= sar2130p_qmp_gen3x2_pcie_rc_tx_tbl,
+		.tx_num		= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_tx_tbl),
+		.pcs		= sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl,
+		.pcs_num	= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl),
+		.pcs_misc	= sm8550_qmp_gen3x2_pcie_pcs_misc_tbl,
+		.pcs_misc_num	= ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_pcs_misc_tbl),
+	},
+	.tbls_ep = &(const struct qmp_phy_cfg_tbls) {
+		.serdes		= sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl,
+		.serdes_num	= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl),
+		.pcs		= sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl,
+		.pcs_num	= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl),
+		.pcs_misc	= sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl,
+		.pcs_misc_num	= ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl),
+	},
+	.reset_list		= sdm845_pciephy_reset_l,
+	.num_resets		= ARRAY_SIZE(sdm845_pciephy_reset_l),
+	.vreg_list		= qmp_phy_vreg_l,
+	.num_vregs		= ARRAY_SIZE(qmp_phy_vreg_l),
+	.regs			= pciephy_v5_regs_layout,
+
+	.pwrdn_ctrl		= SW_PWRDN | REFCLK_DRV_DSBL,
+	.phy_status		= PHYSTATUS,
+};
+
 static const struct qmp_phy_cfg sc8180x_pciephy_cfg = {
 	.lanes			= 2,
 
@@ -3440,8 +3687,8 @@ static const struct qmp_phy_cfg sdx55_qmp_pciephy_cfg = {
 	.tbls_ep = &(const struct qmp_phy_cfg_tbls) {
 		.serdes		= sdx55_qmp_pcie_ep_serdes_tbl,
 		.serdes_num	= ARRAY_SIZE(sdx55_qmp_pcie_ep_serdes_tbl),
-		.pcs_misc	= sdx55_qmp_pcie_ep_pcs_misc_tbl,
-		.pcs_misc_num	= ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_misc_tbl),
+		.pcs_lane1	= sdx55_qmp_pcie_ep_pcs_lane1_tbl,
+		.pcs_lane1_num	= ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_lane1_tbl),
 	},
 
 	.reset_list		= sdm845_pciephy_reset_l,
@@ -3540,6 +3787,8 @@ static const struct qmp_phy_cfg sdx65_qmp_pciephy_cfg = {
 			.pcs_num        = ARRAY_SIZE(sdx65_qmp_pcie_pcs_tbl),
 			.pcs_misc       = sdx65_qmp_pcie_pcs_misc_tbl,
 			.pcs_misc_num   = ARRAY_SIZE(sdx65_qmp_pcie_pcs_misc_tbl),
+			.pcs_lane1       = sdx65_qmp_pcie_pcs_lane1_tbl,
+			.pcs_lane1_num   = ARRAY_SIZE(sdx65_qmp_pcie_pcs_lane1_tbl),
 		},
 	.reset_list             = sdm845_pciephy_reset_l,
 	.num_resets             = ARRAY_SIZE(sdm845_pciephy_reset_l),
@@ -3739,6 +3988,8 @@ static const struct qmp_phy_cfg sa8775p_qmp_gen4x2_pciephy_cfg = {
 		.pcs_num		= ARRAY_SIZE(sa8775p_qmp_gen4x2_pcie_pcs_alt_tbl),
 		.pcs_misc		= sa8775p_qmp_gen4_pcie_pcs_misc_tbl,
 		.pcs_misc_num	= ARRAY_SIZE(sa8775p_qmp_gen4_pcie_pcs_misc_tbl),
+		.pcs_lane1	= sdx65_qmp_pcie_pcs_lane1_tbl,
+		.pcs_lane1_num	= ARRAY_SIZE(sdx65_qmp_pcie_pcs_lane1_tbl),
 	},
 
 	.tbls_rc = &(const struct qmp_phy_cfg_tbls) {
@@ -3945,6 +4196,7 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c
 	void __iomem *rx2 = qmp->rx2;
 	void __iomem *pcs = qmp->pcs;
 	void __iomem *pcs_misc = qmp->pcs_misc;
+	void __iomem *pcs_lane1 = qmp->pcs_lane1;
 	void __iomem *ln_shrd = qmp->ln_shrd;
 
 	if (!tbls)
@@ -3969,6 +4221,7 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c
 
 	qmp_configure(qmp->dev, pcs, tbls->pcs, tbls->pcs_num);
 	qmp_configure(qmp->dev, pcs_misc, tbls->pcs_misc, tbls->pcs_misc_num);
+	qmp_configure(qmp->dev, pcs_lane1, tbls->pcs_lane1, tbls->pcs_lane1_num);
 
 	if (cfg->lanes >= 4 && qmp->tcsr_4ln_config) {
 		qmp_configure(qmp->dev, serdes, cfg->serdes_4ln_tbl,
@@ -4420,6 +4673,14 @@ static int qmp_pcie_parse_dt_legacy(struct qmp_pcie *qmp, struct device_node *np
 		}
 	}
 
+	/*
+	 * For all platforms where legacy bindings existed, PCS_LANE1 was
+	 * mapped as a part of the PCS_MISC region.
+	 */
+	if (!IS_ERR(qmp->pcs_misc) && cfg->offsets->pcs_lane1 != 0)
+		qmp->pcs_lane1 = qmp->pcs_misc +
+			(cfg->offsets->pcs_lane1 - cfg->offsets->pcs_misc);
+
 	clk = devm_get_clk_from_child(dev, np, NULL);
 	if (IS_ERR(clk)) {
 		return dev_err_probe(dev, PTR_ERR(clk),
@@ -4487,6 +4748,7 @@ static int qmp_pcie_parse_dt(struct qmp_pcie *qmp)
 	qmp->serdes = base + offs->serdes;
 	qmp->pcs = base + offs->pcs;
 	qmp->pcs_misc = base + offs->pcs_misc;
+	qmp->pcs_lane1 = base + offs->pcs_lane1;
 	qmp->tx = base + offs->tx;
 	qmp->rx = base + offs->rx;
 
@@ -4612,12 +4874,18 @@ static const struct of_device_id qmp_pcie_of_match_table[] = {
 		.compatible = "qcom,msm8998-qmp-pcie-phy",
 		.data = &msm8998_pciephy_cfg,
 	}, {
+		.compatible = "qcom,qcs615-qmp-gen3x1-pcie-phy",
+		.data = &qcs615_pciephy_cfg,
+	}, {
 		.compatible = "qcom,sa8775p-qmp-gen4x2-pcie-phy",
 		.data = &sa8775p_qmp_gen4x2_pciephy_cfg,
 	}, {
 		.compatible = "qcom,sa8775p-qmp-gen4x4-pcie-phy",
 		.data = &sa8775p_qmp_gen4x4_pciephy_cfg,
 	}, {
+		.compatible = "qcom,sar2130p-qmp-gen3x2-pcie-phy",
+		.data = &sar2130p_qmp_gen3x2_pciephy_cfg,
+	}, {
 		.compatible = "qcom,sc8180x-qmp-pcie-phy",
 		.data = &sc8180x_pciephy_cfg,
 	}, {
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h
index ac872a9eff9a..ab892d1067c2 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h
@@ -13,7 +13,8 @@
 #define QPHY_V4_20_PCS_PCIE_G4_RXEQEVAL_TIME		0x0f4
 #define QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG2		0x0fc
 #define QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG5		0x108
-#define QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2		0x824
-#define QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2		0x828
+
+#define QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2		0x024
+#define QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2		0x028
 
 #endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h
index cdf8c04ea078..283d63c81593 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h
@@ -17,7 +17,8 @@
 #define QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5		0x108
 #define QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN			0x15c
 #define QPHY_V5_20_PCS_PCIE_RX_MARGINING_CONFIG3	0x184
-#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2		0xa24
-#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2		0xa28
+
+#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2		0x024
+#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2		0x028
 
 #endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h
index 0ca79333d942..45397cb3c0c6 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h
@@ -14,4 +14,7 @@
 #define QPHY_PCIE_V6_PCS_PCIE_ENDPOINT_REFCLK_DRIVE	0x20
 #define QPHY_PCIE_V6_PCS_PCIE_OSC_DTCT_ACTIONS		0x94
 
+#define QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2		0x024
+#define QPHY_PCIE_V6_PCS_LANE1_INSIG_MX_CTRL2		0x028
+
 #endif
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h
index bf36399d0057..1ecf4b5beba6 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h
@@ -34,6 +34,7 @@
 #define QPHY_V2_PCS_USB_PCS_STATUS			0x17c /* USB */
 #define QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME_AUXCLK_LSB	0x1a8
 #define QPHY_V2_PCS_OSC_DTCT_ACTIONS			0x1ac
+#define QPHY_V2_PCS_SIGDET_CNTRL			0x1b0
 #define QPHY_V2_PCS_RX_SIGDET_LVL			0x1d8
 #define QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_LSB	0x1dc
 #define QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_MSB	0x1e0
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h
index 08299d2b78f0..aa5afb921f12 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h
@@ -17,6 +17,8 @@
 #define QPHY_V6_PCS_LOCK_DETECT_CONFIG3		0x0cc
 #define QPHY_V6_PCS_LOCK_DETECT_CONFIG6		0x0d8
 #define QPHY_V6_PCS_REFGEN_REQ_CONFIG1		0x0dc
+#define QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB		0x168
+#define QPHY_V6_PCS_G3S2_PRE_GAIN		0x170
 #define QPHY_V6_PCS_RX_SIGDET_LVL		0x188
 #define QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L	0x190
 #define QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H	0x194
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
index 23ffcfae9efa..f47fdc9cecda 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h
@@ -6,6 +6,7 @@
 #ifndef QCOM_PHY_QMP_QSERDES_TXRX_USB_V6_H_
 #define QCOM_PHY_QMP_QSERDES_TXRX_USB_V6_H_
 
+#define QSERDES_V6_TX_BIST_MODE_LANENO				0x00
 #define QSERDES_V6_TX_CLKBUF_ENABLE				0x08
 #define QSERDES_V6_TX_TX_EMP_POST1_LVL				0x0c
 #define QSERDES_V6_TX_TX_DRV_LVL				0x14
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
index c9c337840715..787721570457 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c
@@ -2298,6 +2298,9 @@ err_node_put:
 
 static const struct of_device_id qmp_usb_of_match_table[] = {
 	{
+		.compatible = "qcom,ipq5424-qmp-usb3-phy",
+		.data = &ipq9574_usb3phy_cfg,
+	}, {
 		.compatible = "qcom,ipq6018-qmp-usb3-phy",
 		.data = &ipq6018_usb3phy_cfg,
 	}, {
diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c
index c52655a383ce..1f5f7df14d5a 100644
--- a/drivers/phy/qualcomm/phy-qcom-qusb2.c
+++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c
@@ -151,6 +151,34 @@ static const struct qusb2_phy_init_tbl ipq6018_init_tbl[] = {
 	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9F),
 };
 
+static const struct qusb2_phy_init_tbl ipq5424_init_tbl[] = {
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL, 0x14),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0x00),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0x53),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc3),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE5, 0x00),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TEST, 0x80),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f),
+};
+
+static const struct qusb2_phy_init_tbl qcs615_init_tbl[] = {
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0xc8),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0xb3),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE3, 0x83),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc0),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21),
+	QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f),
+	QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00),
+};
+
 static const unsigned int ipq6018_regs_layout[] = {
 	[QUSB2PHY_PLL_STATUS]              = 0x38,
 	[QUSB2PHY_PORT_TUNE1]              = 0x80,
@@ -331,6 +359,27 @@ static const struct qusb2_phy_cfg ipq6018_phy_cfg = {
 	.autoresume_en   = BIT(0),
 };
 
+static const struct qusb2_phy_cfg ipq5424_phy_cfg = {
+	.tbl            = ipq5424_init_tbl,
+	.tbl_num        = ARRAY_SIZE(ipq5424_init_tbl),
+	.regs           = ipq6018_regs_layout,
+
+	.disable_ctrl   = POWER_DOWN,
+	.mask_core_ready = PLL_LOCKED,
+	.autoresume_en   = BIT(0),
+};
+
+static const struct qusb2_phy_cfg qcs615_phy_cfg = {
+	.tbl            = qcs615_init_tbl,
+	.tbl_num        = ARRAY_SIZE(qcs615_init_tbl),
+	.regs           = ipq6018_regs_layout,
+
+	.disable_ctrl   = (CLAMP_N_EN | FREEZIO_N | POWER_DOWN),
+	.mask_core_ready = PLL_LOCKED,
+	/* autoresume not used */
+	.autoresume_en   = BIT(0),
+};
+
 static const struct qusb2_phy_cfg qusb2_v2_phy_cfg = {
 	.tbl		= qusb2_v2_init_tbl,
 	.tbl_num	= ARRAY_SIZE(qusb2_v2_init_tbl),
@@ -905,6 +954,9 @@ static const struct phy_ops qusb2_phy_gen_ops = {
 
 static const struct of_device_id qusb2_phy_of_match_table[] = {
 	{
+		.compatible	= "qcom,ipq5424-qusb2-phy",
+		.data		= &ipq5424_phy_cfg,
+	}, {
 		.compatible	= "qcom,ipq6018-qusb2-phy",
 		.data		= &ipq6018_phy_cfg,
 	}, {
@@ -923,6 +975,9 @@ static const struct of_device_id qusb2_phy_of_match_table[] = {
 		.compatible	= "qcom,msm8998-qusb2-phy",
 		.data		= &msm8998_phy_cfg,
 	}, {
+		.compatible	= "qcom,qcs615-qusb2-phy",
+		.data		= &qcs615_phy_cfg,
+	}, {
 		.compatible	= "qcom,qcm2290-qusb2-phy",
 		.data		= &sm6115_phy_cfg,
 	}, {
diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
index 2eb3329ca23f..a1532ef8bbe9 100644
--- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
@@ -37,6 +37,10 @@
 #define PHYREG8				0x1C
 #define PHYREG8_SSC_EN			BIT(4)
 
+#define PHYREG10			0x24
+#define PHYREG10_SSC_PCM_MASK		GENMASK(3, 0)
+#define PHYREG10_SSC_PCM_3500PPM	7
+
 #define PHYREG11			0x28
 #define PHYREG11_SU_TRIM_0_7		0xF0
 
@@ -61,17 +65,26 @@
 #define PHYREG16			0x3C
 #define PHYREG16_SSC_CNT_VALUE		0x5f
 
+#define PHYREG17			0x40
+
 #define PHYREG18			0x44
 #define PHYREG18_PLL_LOOP		0x32
 
+#define PHYREG21			0x50
+#define PHYREG21_RX_SQUELCH_VAL		0x0D
+
 #define PHYREG27			0x6C
 #define PHYREG27_RX_TRIM_RK3588		0x4C
 
+#define PHYREG30			0x74
+
 #define PHYREG32			0x7C
 #define PHYREG32_SSC_MASK		GENMASK(7, 4)
+#define PHYREG32_SSC_DIR_MASK		GENMASK(5, 4)
 #define PHYREG32_SSC_DIR_SHIFT		4
 #define PHYREG32_SSC_UPWARD		0
 #define PHYREG32_SSC_DOWNWARD		1
+#define PHYREG32_SSC_OFFSET_MASK	GENMASK(7, 6)
 #define PHYREG32_SSC_OFFSET_SHIFT	6
 #define PHYREG32_SSC_OFFSET_500PPM	1
 
@@ -79,6 +92,7 @@
 #define PHYREG33_PLL_KVCO_MASK		GENMASK(4, 2)
 #define PHYREG33_PLL_KVCO_SHIFT		2
 #define PHYREG33_PLL_KVCO_VALUE		2
+#define PHYREG33_PLL_KVCO_VALUE_RK3576	4
 
 struct rockchip_combphy_priv;
 
@@ -98,6 +112,7 @@ struct rockchip_combphy_grfcfg {
 	struct combphy_reg pipe_rxterm_set;
 	struct combphy_reg pipe_txelec_set;
 	struct combphy_reg pipe_txcomp_set;
+	struct combphy_reg pipe_clk_24m;
 	struct combphy_reg pipe_clk_25m;
 	struct combphy_reg pipe_clk_100m;
 	struct combphy_reg pipe_phymode_sel;
@@ -584,6 +599,266 @@ static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = {
 	.combphy_cfg	= rk3568_combphy_cfg,
 };
 
+static int rk3576_combphy_cfg(struct rockchip_combphy_priv *priv)
+{
+	const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg;
+	unsigned long rate;
+	u32 val;
+
+	switch (priv->type) {
+	case PHY_TYPE_PCIE:
+		/* Set SSC downward spread spectrum */
+		val = FIELD_PREP(PHYREG32_SSC_MASK, PHYREG32_SSC_DOWNWARD);
+		rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32);
+
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_pcie, true);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true);
+		break;
+
+	case PHY_TYPE_USB3:
+		/* Set SSC downward spread spectrum */
+		val = FIELD_PREP(PHYREG32_SSC_MASK, PHYREG32_SSC_DOWNWARD);
+		rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32);
+
+		/* Enable adaptive CTLE for USB3.0 Rx */
+		val = readl(priv->mmio + PHYREG15);
+		val |= PHYREG15_CTLE_EN;
+		writel(val, priv->mmio + PHYREG15);
+
+		/* Set PLL KVCO fine tuning signals */
+		rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, BIT(3), PHYREG33);
+
+		/* Set PLL LPF R1 to su_trim[10:7]=1001 */
+		writel(PHYREG12_PLL_LPF_ADJ_VALUE, priv->mmio + PHYREG12);
+
+		/* Set PLL input clock divider 1/2 */
+		val = FIELD_PREP(PHYREG6_PLL_DIV_MASK, PHYREG6_PLL_DIV_2);
+		rockchip_combphy_updatel(priv, PHYREG6_PLL_DIV_MASK, val, PHYREG6);
+
+		/* Set PLL loop divider */
+		writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18);
+
+		/* Set PLL KVCO to min and set PLL charge pump current to max */
+		writel(PHYREG11_SU_TRIM_0_7, priv->mmio + PHYREG11);
+
+		/* Set Rx squelch input filler bandwidth */
+		writel(PHYREG21_RX_SQUELCH_VAL, priv->mmio + PHYREG21);
+
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txcomp_sel, false);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txelec_sel, false);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->usb_mode_set, true);
+		break;
+
+	case PHY_TYPE_SATA:
+		/* Enable adaptive CTLE for SATA Rx */
+		val = readl(priv->mmio + PHYREG15);
+		val |= PHYREG15_CTLE_EN;
+		writel(val, priv->mmio + PHYREG15);
+
+		/* Set tx_rterm = 50 ohm and rx_rterm = 43.5 ohm */
+		val = PHYREG7_TX_RTERM_50OHM << PHYREG7_TX_RTERM_SHIFT;
+		val |= PHYREG7_RX_RTERM_44OHM << PHYREG7_RX_RTERM_SHIFT;
+		writel(val, priv->mmio + PHYREG7);
+
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_sata, true);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_sata, true);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_sata, true);
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_sata, true);
+		rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con0_for_sata, true);
+		rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con1_for_sata, true);
+		break;
+
+	default:
+		dev_err(priv->dev, "incompatible PHY type\n");
+		return -EINVAL;
+	}
+
+	rate = clk_get_rate(priv->refclk);
+
+	switch (rate) {
+	case REF_CLOCK_24MHz:
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_24m, true);
+		if (priv->type == PHY_TYPE_USB3 || priv->type == PHY_TYPE_SATA) {
+			/* Set ssc_cnt[9:0]=0101111101 & 31.5KHz */
+			val = FIELD_PREP(PHYREG15_SSC_CNT_MASK, PHYREG15_SSC_CNT_VALUE);
+			rockchip_combphy_updatel(priv, PHYREG15_SSC_CNT_MASK,
+						 val, PHYREG15);
+
+			writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16);
+		} else if (priv->type == PHY_TYPE_PCIE) {
+			/* PLL KVCO tuning fine */
+			val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576);
+			rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK,
+						 val, PHYREG33);
+
+			/* Set up rx_pck invert and rx msb to disable */
+			writel(0x00, priv->mmio + PHYREG27);
+
+			/*
+			 * Set up SU adjust signal:
+			 * su_trim[7:0],   PLL KVCO adjust bits[2:0] to min
+			 * su_trim[15:8],  PLL LPF R1 adujst bits[9:7]=3'b011
+			 * su_trim[31:24], CKDRV adjust
+			 */
+			writel(0x90, priv->mmio + PHYREG11);
+			writel(0x02, priv->mmio + PHYREG12);
+			writel(0x57, priv->mmio + PHYREG14);
+
+			writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16);
+		}
+		break;
+
+	case REF_CLOCK_25MHz:
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_25m, true);
+		break;
+
+	case REF_CLOCK_100MHz:
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_100m, true);
+		if (priv->type == PHY_TYPE_PCIE) {
+			/* gate_tx_pck_sel length select work for L1SS */
+			writel(0xc0, priv->mmio + PHYREG30);
+
+			/* PLL KVCO tuning fine */
+			val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576);
+			rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK,
+						 val, PHYREG33);
+
+			/* Set up rx_trim: PLL LPF C1 85pf R1 1.25kohm */
+			writel(0x4c, priv->mmio + PHYREG27);
+
+			/*
+			 * Set up SU adjust signal:
+			 * su_trim[7:0],   PLL KVCO adjust bits[2:0] to min
+			 * su_trim[15:8],  bypass PLL loop divider code, and
+			 *                 PLL LPF R1 adujst bits[9:7]=3'b101
+			 * su_trim[23:16], CKRCV adjust
+			 * su_trim[31:24], CKDRV adjust
+			 */
+			writel(0x90, priv->mmio + PHYREG11);
+			writel(0x43, priv->mmio + PHYREG12);
+			writel(0x88, priv->mmio + PHYREG13);
+			writel(0x56, priv->mmio + PHYREG14);
+		} else if (priv->type == PHY_TYPE_SATA) {
+			/* downward spread spectrum +500ppm */
+			val = FIELD_PREP(PHYREG32_SSC_DIR_MASK, PHYREG32_SSC_DOWNWARD);
+			val |= FIELD_PREP(PHYREG32_SSC_OFFSET_MASK, PHYREG32_SSC_OFFSET_500PPM);
+			rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32);
+
+			/* ssc ppm adjust to 3500ppm */
+			rockchip_combphy_updatel(priv, PHYREG10_SSC_PCM_MASK,
+						 PHYREG10_SSC_PCM_3500PPM,
+						 PHYREG10);
+		}
+		break;
+
+	default:
+		dev_err(priv->dev, "Unsupported rate: %lu\n", rate);
+		return -EINVAL;
+	}
+
+	if (priv->ext_refclk) {
+		rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_ext, true);
+		if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_100MHz) {
+			val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576);
+			rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK,
+						 val, PHYREG33);
+
+			/* Set up rx_trim: PLL LPF C1 85pf R1 2.5kohm */
+			writel(0x0c, priv->mmio + PHYREG27);
+
+			/*
+			 * Set up SU adjust signal:
+			 * su_trim[7:0],   PLL KVCO adjust bits[2:0] to min
+			 * su_trim[15:8],  bypass PLL loop divider code, and
+			 *                 PLL LPF R1 adujst bits[9:7]=3'b101.
+			 * su_trim[23:16], CKRCV adjust
+			 * su_trim[31:24], CKDRV adjust
+			 */
+			writel(0x90, priv->mmio + PHYREG11);
+			writel(0x43, priv->mmio + PHYREG12);
+			writel(0x88, priv->mmio + PHYREG13);
+			writel(0x56, priv->mmio + PHYREG14);
+		}
+	}
+
+	if (priv->enable_ssc) {
+		val = readl(priv->mmio + PHYREG8);
+		val |= PHYREG8_SSC_EN;
+		writel(val, priv->mmio + PHYREG8);
+
+		if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_24MHz) {
+			/* Set PLL loop divider */
+			writel(0x00, priv->mmio + PHYREG17);
+			writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18);
+
+			/* Set up rx_pck invert and rx msb to disable */
+			writel(0x00, priv->mmio + PHYREG27);
+
+			/*
+			 * Set up SU adjust signal:
+			 * su_trim[7:0],   PLL KVCO adjust bits[2:0] to min
+			 * su_trim[15:8],  PLL LPF R1 adujst bits[9:7]=3'b101
+			 * su_trim[23:16], CKRCV adjust
+			 * su_trim[31:24], CKDRV adjust
+			 */
+			writel(0x90, priv->mmio + PHYREG11);
+			writel(0x02, priv->mmio + PHYREG12);
+			writel(0x08, priv->mmio + PHYREG13);
+			writel(0x57, priv->mmio + PHYREG14);
+			writel(0x40, priv->mmio + PHYREG15);
+
+			writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16);
+
+			val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576);
+			writel(val, priv->mmio + PHYREG33);
+		}
+	}
+
+	return 0;
+}
+
+static const struct rockchip_combphy_grfcfg rk3576_combphy_grfcfgs = {
+	/* pipe-phy-grf */
+	.pcie_mode_set		= { 0x0000, 5, 0, 0x00, 0x11 },
+	.usb_mode_set		= { 0x0000, 5, 0, 0x00, 0x04 },
+	.pipe_rxterm_set	= { 0x0000, 12, 12, 0x00, 0x01 },
+	.pipe_txelec_set	= { 0x0004, 1, 1, 0x00, 0x01 },
+	.pipe_txcomp_set	= { 0x0004, 4, 4, 0x00, 0x01 },
+	.pipe_clk_24m		= { 0x0004, 14, 13, 0x00, 0x00 },
+	.pipe_clk_25m		= { 0x0004, 14, 13, 0x00, 0x01 },
+	.pipe_clk_100m		= { 0x0004, 14, 13, 0x00, 0x02 },
+	.pipe_phymode_sel	= { 0x0008, 1, 1, 0x00, 0x01 },
+	.pipe_rate_sel		= { 0x0008, 2, 2, 0x00, 0x01 },
+	.pipe_rxterm_sel	= { 0x0008, 8, 8, 0x00, 0x01 },
+	.pipe_txelec_sel	= { 0x0008, 12, 12, 0x00, 0x01 },
+	.pipe_txcomp_sel	= { 0x0008, 15, 15, 0x00, 0x01 },
+	.pipe_clk_ext		= { 0x000c, 9, 8, 0x02, 0x01 },
+	.pipe_phy_status	= { 0x0034, 6, 6, 0x01, 0x00 },
+	.con0_for_pcie		= { 0x0000, 15, 0, 0x00, 0x1000 },
+	.con1_for_pcie		= { 0x0004, 15, 0, 0x00, 0x0000 },
+	.con2_for_pcie		= { 0x0008, 15, 0, 0x00, 0x0101 },
+	.con3_for_pcie		= { 0x000c, 15, 0, 0x00, 0x0200 },
+	.con0_for_sata		= { 0x0000, 15, 0, 0x00, 0x0129 },
+	.con1_for_sata		= { 0x0004, 15, 0, 0x00, 0x0000 },
+	.con2_for_sata		= { 0x0008, 15, 0, 0x00, 0x80c1 },
+	.con3_for_sata		= { 0x000c, 15, 0, 0x00, 0x0407 },
+	/* php-grf */
+	.pipe_con0_for_sata	= { 0x001C, 2, 0, 0x00, 0x2 },
+	.pipe_con1_for_sata	= { 0x0020, 2, 0, 0x00, 0x2 },
+};
+
+static const struct rockchip_combphy_cfg rk3576_combphy_cfgs = {
+	.num_phys = 2,
+	.phy_ids = {
+		0x2b050000,
+		0x2b060000
+	},
+	.grfcfg		= &rk3576_combphy_grfcfgs,
+	.combphy_cfg	= rk3576_combphy_cfg,
+};
+
 static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv)
 {
 	const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg;
@@ -776,6 +1051,10 @@ static const struct of_device_id rockchip_combphy_of_match[] = {
 		.data = &rk3568_combphy_cfgs,
 	},
 	{
+		.compatible = "rockchip,rk3576-naneng-combphy",
+		.data = &rk3576_combphy_cfgs,
+	},
+	{
 		.compatible = "rockchip,rk3588-naneng-combphy",
 		.data = &rk3588_combphy_cfgs,
 	},
diff --git a/drivers/phy/rockchip/phy-rockchip-pcie.c b/drivers/phy/rockchip/phy-rockchip-pcie.c
index 51cc5ece0e63..bd44af36c67a 100644
--- a/drivers/phy/rockchip/phy-rockchip-pcie.c
+++ b/drivers/phy/rockchip/phy-rockchip-pcie.c
@@ -124,7 +124,7 @@ static int rockchip_pcie_phy_power_off(struct phy *phy)
 	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
 	int err = 0;
 
-	mutex_lock(&rk_phy->pcie_mutex);
+	guard(mutex)(&rk_phy->pcie_mutex);
 
 	regmap_write(rk_phy->reg_base,
 		     rk_phy->phy_data->pcie_laneoff,
@@ -132,27 +132,22 @@ static int rockchip_pcie_phy_power_off(struct phy *phy)
 				   PHY_LANE_IDLE_MASK,
 				   PHY_LANE_IDLE_A_SHIFT + inst->index));
 
-	if (--rk_phy->pwr_cnt)
-		goto err_out;
+	if (--rk_phy->pwr_cnt) {
+		return 0;
+	}
 
 	err = reset_control_assert(rk_phy->phy_rst);
 	if (err) {
 		dev_err(&phy->dev, "assert phy_rst err %d\n", err);
-		goto err_restore;
+		rk_phy->pwr_cnt++;
+		regmap_write(rk_phy->reg_base,
+			     rk_phy->phy_data->pcie_laneoff,
+			     HIWORD_UPDATE(!PHY_LANE_IDLE_OFF,
+					   PHY_LANE_IDLE_MASK,
+					   PHY_LANE_IDLE_A_SHIFT + inst->index));
+		return err;
 	}
 
-err_out:
-	mutex_unlock(&rk_phy->pcie_mutex);
-	return 0;
-
-err_restore:
-	rk_phy->pwr_cnt++;
-	regmap_write(rk_phy->reg_base,
-		     rk_phy->phy_data->pcie_laneoff,
-		     HIWORD_UPDATE(!PHY_LANE_IDLE_OFF,
-				   PHY_LANE_IDLE_MASK,
-				   PHY_LANE_IDLE_A_SHIFT + inst->index));
-	mutex_unlock(&rk_phy->pcie_mutex);
 	return err;
 }
 
@@ -162,17 +157,18 @@ static int rockchip_pcie_phy_power_on(struct phy *phy)
 	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
 	int err = 0;
 	u32 status;
-	unsigned long timeout;
 
-	mutex_lock(&rk_phy->pcie_mutex);
+	guard(mutex)(&rk_phy->pcie_mutex);
 
-	if (rk_phy->pwr_cnt++)
-		goto err_out;
+	if (rk_phy->pwr_cnt++) {
+		return 0;
+	}
 
 	err = reset_control_deassert(rk_phy->phy_rst);
 	if (err) {
 		dev_err(&phy->dev, "deassert phy_rst err %d\n", err);
-		goto err_pwr_cnt;
+		rk_phy->pwr_cnt--;
+		return err;
 	}
 
 	regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf,
@@ -191,21 +187,11 @@ static int rockchip_pcie_phy_power_on(struct phy *phy)
 	 * so we make it large enough here. And we use loop-break
 	 * method which should not be harmful.
 	 */
-	timeout = jiffies + msecs_to_jiffies(1000);
-
-	err = -EINVAL;
-	while (time_before(jiffies, timeout)) {
-		regmap_read(rk_phy->reg_base,
-			    rk_phy->phy_data->pcie_status,
-			    &status);
-		if (status & PHY_PLL_LOCKED) {
-			dev_dbg(&phy->dev, "pll locked!\n");
-			err = 0;
-			break;
-		}
-		msleep(20);
-	}
-
+	err = regmap_read_poll_timeout(rk_phy->reg_base,
+				       rk_phy->phy_data->pcie_status,
+				       status,
+				       status & PHY_PLL_LOCKED,
+				       200, 100000);
 	if (err) {
 		dev_err(&phy->dev, "pll lock timeout!\n");
 		goto err_pll_lock;
@@ -214,19 +200,11 @@ static int rockchip_pcie_phy_power_on(struct phy *phy)
 	phy_wr_cfg(rk_phy, PHY_CFG_CLK_TEST, PHY_CFG_SEPE_RATE);
 	phy_wr_cfg(rk_phy, PHY_CFG_CLK_SCC, PHY_CFG_PLL_100M);
 
-	err = -ETIMEDOUT;
-	while (time_before(jiffies, timeout)) {
-		regmap_read(rk_phy->reg_base,
-			    rk_phy->phy_data->pcie_status,
-			    &status);
-		if (!(status & PHY_PLL_OUTPUT)) {
-			dev_dbg(&phy->dev, "pll output enable done!\n");
-			err = 0;
-			break;
-		}
-		msleep(20);
-	}
-
+	err = regmap_read_poll_timeout(rk_phy->reg_base,
+				       rk_phy->phy_data->pcie_status,
+				       status,
+				       !(status & PHY_PLL_OUTPUT),
+				       200, 100000);
 	if (err) {
 		dev_err(&phy->dev, "pll output enable timeout!\n");
 		goto err_pll_lock;
@@ -236,33 +214,22 @@ static int rockchip_pcie_phy_power_on(struct phy *phy)
 		     HIWORD_UPDATE(PHY_CFG_PLL_LOCK,
 				   PHY_CFG_ADDR_MASK,
 				   PHY_CFG_ADDR_SHIFT));
-	err = -EINVAL;
-	while (time_before(jiffies, timeout)) {
-		regmap_read(rk_phy->reg_base,
-			    rk_phy->phy_data->pcie_status,
-			    &status);
-		if (status & PHY_PLL_LOCKED) {
-			dev_dbg(&phy->dev, "pll relocked!\n");
-			err = 0;
-			break;
-		}
-		msleep(20);
-	}
 
+	err = regmap_read_poll_timeout(rk_phy->reg_base,
+				       rk_phy->phy_data->pcie_status,
+				       status,
+				       status & PHY_PLL_LOCKED,
+				       200, 100000);
 	if (err) {
 		dev_err(&phy->dev, "pll relock timeout!\n");
 		goto err_pll_lock;
 	}
 
-err_out:
-	mutex_unlock(&rk_phy->pcie_mutex);
-	return 0;
+	return err;
 
 err_pll_lock:
 	reset_control_assert(rk_phy->phy_rst);
-err_pwr_cnt:
 	rk_phy->pwr_cnt--;
-	mutex_unlock(&rk_phy->pcie_mutex);
 	return err;
 }
 
@@ -272,33 +239,19 @@ static int rockchip_pcie_phy_init(struct phy *phy)
 	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
 	int err = 0;
 
-	mutex_lock(&rk_phy->pcie_mutex);
-
-	if (rk_phy->init_cnt++)
-		goto err_out;
+	guard(mutex)(&rk_phy->pcie_mutex);
 
-	err = clk_prepare_enable(rk_phy->clk_pciephy_ref);
-	if (err) {
-		dev_err(&phy->dev, "Fail to enable pcie ref clock.\n");
-		goto err_refclk;
+	if (rk_phy->init_cnt++) {
+		return 0;
 	}
 
 	err = reset_control_assert(rk_phy->phy_rst);
 	if (err) {
 		dev_err(&phy->dev, "assert phy_rst err %d\n", err);
-		goto err_reset;
+		rk_phy->init_cnt--;
+		return err;
 	}
 
-err_out:
-	mutex_unlock(&rk_phy->pcie_mutex);
-	return 0;
-
-err_reset:
-
-	clk_disable_unprepare(rk_phy->clk_pciephy_ref);
-err_refclk:
-	rk_phy->init_cnt--;
-	mutex_unlock(&rk_phy->pcie_mutex);
 	return err;
 }
 
@@ -307,15 +260,12 @@ static int rockchip_pcie_phy_exit(struct phy *phy)
 	struct phy_pcie_instance *inst = phy_get_drvdata(phy);
 	struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst);
 
-	mutex_lock(&rk_phy->pcie_mutex);
+	guard(mutex)(&rk_phy->pcie_mutex);
 
 	if (--rk_phy->init_cnt)
 		goto err_init_cnt;
 
-	clk_disable_unprepare(rk_phy->clk_pciephy_ref);
-
 err_init_cnt:
-	mutex_unlock(&rk_phy->pcie_mutex);
 	return 0;
 }
 
@@ -371,18 +321,14 @@ static int rockchip_pcie_phy_probe(struct platform_device *pdev)
 	mutex_init(&rk_phy->pcie_mutex);
 
 	rk_phy->phy_rst = devm_reset_control_get(dev, "phy");
-	if (IS_ERR(rk_phy->phy_rst)) {
-		if (PTR_ERR(rk_phy->phy_rst) != -EPROBE_DEFER)
-			dev_err(dev,
-				"missing phy property for reset controller\n");
-		return PTR_ERR(rk_phy->phy_rst);
-	}
-
-	rk_phy->clk_pciephy_ref = devm_clk_get(dev, "refclk");
-	if (IS_ERR(rk_phy->clk_pciephy_ref)) {
-		dev_err(dev, "refclk not found.\n");
-		return PTR_ERR(rk_phy->clk_pciephy_ref);
-	}
+	if (IS_ERR(rk_phy->phy_rst))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rk_phy->phy_rst),
+				     "missing phy property for reset controller\n");
+
+	rk_phy->clk_pciephy_ref = devm_clk_get_enabled(dev, "refclk");
+	if (IS_ERR(rk_phy->clk_pciephy_ref))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rk_phy->clk_pciephy_ref),
+				     "failed to get phyclk\n");
 
 	/* parse #phy-cells to see if it's legacy PHY model */
 	if (of_property_read_u32(dev->of_node, "#phy-cells", &phy_num))
diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c
index 122ae0fdc785..d9701b6106d5 100644
--- a/drivers/phy/rockchip/phy-rockchip-typec.c
+++ b/drivers/phy/rockchip/phy-rockchip-typec.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd
+ * Copyright (C) Rockchip Electronics Co., Ltd.
  * Author: Chris Zhong <zyw@rock-chips.com>
  *         Kever Yang <kever.yang@rock-chips.com>
  *
diff --git a/drivers/phy/samsung/Kconfig b/drivers/phy/samsung/Kconfig
index f10afa3d7ff5..e2330b0894d6 100644
--- a/drivers/phy/samsung/Kconfig
+++ b/drivers/phy/samsung/Kconfig
@@ -33,6 +33,7 @@ config PHY_SAMSUNG_UFS
 	tristate "Exynos SoC series UFS PHY driver"
 	depends on OF && (ARCH_EXYNOS || COMPILE_TEST)
 	select GENERIC_PHY
+	select MFD_SYSCON
 	help
 	  Enable this to support the Samsung Exynos SoC UFS PHY driver for
 	  Samsung Exynos SoCs. This driver provides the interface for UFS host
diff --git a/drivers/phy/samsung/phy-samsung-ufs.c b/drivers/phy/samsung/phy-samsung-ufs.c
index 6c5d41552649..8e9ccd39f97e 100644
--- a/drivers/phy/samsung/phy-samsung-ufs.c
+++ b/drivers/phy/samsung/phy-samsung-ufs.c
@@ -13,11 +13,11 @@
 #include <linux/of.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
-#include <linux/soc/samsung/exynos-pmu.h>
 
 #include "phy-samsung-ufs.h"
 
@@ -268,8 +268,8 @@ static int samsung_ufs_phy_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-	phy->reg_pmu = exynos_get_pmu_regmap_by_phandle(dev->of_node,
-							"samsung,pmu-syscon");
+	phy->reg_pmu = syscon_regmap_lookup_by_phandle(dev->of_node,
+						       "samsung,pmu-syscon");
 	if (IS_ERR(phy->reg_pmu)) {
 		err = PTR_ERR(phy->reg_pmu);
 		dev_err(dev, "failed syscon remap for pmu\n");
diff --git a/drivers/phy/tegra/Kconfig b/drivers/phy/tegra/Kconfig
index c591c958f1eb..f30cfb42b210 100644
--- a/drivers/phy/tegra/Kconfig
+++ b/drivers/phy/tegra/Kconfig
@@ -13,7 +13,8 @@ config PHY_TEGRA_XUSB
 
 config PHY_TEGRA194_P2U
 	tristate "NVIDIA Tegra194 PIPE2UPHY PHY driver"
-	depends on ARCH_TEGRA_194_SOC || COMPILE_TEST
+	depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || COMPILE_TEST
 	select GENERIC_PHY
 	help
-	  Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x SOCs.
+	  Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x
+	  and 234 SOCs.
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 0b13d7f17b32..42547f64453e 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -89,12 +89,12 @@ static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
 		seq_puts(s, items[i].display);
 		/* Print unit if available */
 		if (items[i].has_arg) {
-			seq_printf(s, " (0x%x",
-				   pinconf_to_config_argument(config));
+			u32 val = pinconf_to_config_argument(config);
+
 			if (items[i].format)
-				seq_printf(s, " %s)", items[i].format);
+				seq_printf(s, " (%u %s)", val, items[i].format);
 			else
-				seq_puts(s, ")");
+				seq_printf(s, " (0x%x)", val);
 		}
 	}
 }
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 0d6c2027d4c1..d73004b4a45e 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -42,7 +42,7 @@
 #define CY8C95X0_PORTSEL	0x18
 /* Port settings, write PORTSEL first */
 #define CY8C95X0_INTMASK	0x19
-#define CY8C95X0_PWMSEL		0x1A
+#define CY8C95X0_SELPWM		0x1A
 #define CY8C95X0_INVERT		0x1B
 #define CY8C95X0_DIRECTION	0x1C
 /* Drive mode register change state on writing '1' */
@@ -328,14 +328,14 @@ static int cypress_get_pin_mask(struct cy8c95x0_pinctrl *chip, unsigned int pin)
 static bool cy8c95x0_readable_register(struct device *dev, unsigned int reg)
 {
 	/*
-	 * Only 12 registers are present per port (see Table 6 in the
-	 * datasheet).
+	 * Only 12 registers are present per port (see Table 6 in the datasheet).
 	 */
-	if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) < 12)
-		return true;
+	if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) >= 12)
+		return false;
 
 	switch (reg) {
 	case 0x24 ... 0x27:
+	case 0x31 ... 0x3f:
 		return false;
 	default:
 		return true;
@@ -344,8 +344,11 @@ static bool cy8c95x0_readable_register(struct device *dev, unsigned int reg)
 
 static bool cy8c95x0_writeable_register(struct device *dev, unsigned int reg)
 {
-	if (reg >= CY8C95X0_VIRTUAL)
-		return true;
+	/*
+	 * Only 12 registers are present per port (see Table 6 in the datasheet).
+	 */
+	if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) >= 12)
+		return false;
 
 	switch (reg) {
 	case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7):
@@ -353,6 +356,7 @@ static bool cy8c95x0_writeable_register(struct device *dev, unsigned int reg)
 	case CY8C95X0_DEVID:
 		return false;
 	case 0x24 ... 0x27:
+	case 0x31 ... 0x3f:
 		return false;
 	default:
 		return true;
@@ -365,8 +369,8 @@ static bool cy8c95x0_volatile_register(struct device *dev, unsigned int reg)
 	case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7):
 	case CY8C95X0_INTSTATUS_(0) ... CY8C95X0_INTSTATUS_(7):
 	case CY8C95X0_INTMASK:
+	case CY8C95X0_SELPWM:
 	case CY8C95X0_INVERT:
-	case CY8C95X0_PWMSEL:
 	case CY8C95X0_DIRECTION:
 	case CY8C95X0_DRV_PU:
 	case CY8C95X0_DRV_PD:
@@ -395,7 +399,7 @@ static bool cy8c95x0_muxed_register(unsigned int reg)
 {
 	switch (reg) {
 	case CY8C95X0_INTMASK:
-	case CY8C95X0_PWMSEL:
+	case CY8C95X0_SELPWM:
 	case CY8C95X0_INVERT:
 	case CY8C95X0_DIRECTION:
 	case CY8C95X0_DRV_PU:
@@ -466,7 +470,11 @@ static const struct regmap_config cy8c9520_i2c_regmap = {
 	.max_register = 0,		/* Updated at runtime */
 	.num_reg_defaults_raw = 0,	/* Updated at runtime */
 	.use_single_read = true,	/* Workaround for regcache bug */
+#if IS_ENABLED(CONFIG_DEBUG_PINCTRL)
+	.disable_locking = false,
+#else
 	.disable_locking = true,
+#endif
 };
 
 static inline int cy8c95x0_regmap_update_bits_base(struct cy8c95x0_pinctrl *chip,
@@ -789,7 +797,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_DIRECTION;
 		break;
 	case PIN_CONFIG_MODE_PWM:
-		reg = CY8C95X0_PWMSEL;
+		reg = CY8C95X0_SELPWM;
 		break;
 	case PIN_CONFIG_OUTPUT:
 		reg = CY8C95X0_OUTPUT;
@@ -868,7 +876,7 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip,
 		reg = CY8C95X0_DRV_PP_FAST;
 		break;
 	case PIN_CONFIG_MODE_PWM:
-		reg = CY8C95X0_PWMSEL;
+		reg = CY8C95X0_SELPWM;
 		break;
 	case PIN_CONFIG_OUTPUT_ENABLE:
 		return cy8c95x0_pinmux_direction(chip, off, !arg);
@@ -1153,7 +1161,7 @@ static void cy8c95x0_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *
 	bitmap_zero(mask, MAX_LINE);
 	__set_bit(pin, mask);
 
-	if (cy8c95x0_read_regs_mask(chip, CY8C95X0_PWMSEL, pwm, mask)) {
+	if (cy8c95x0_read_regs_mask(chip, CY8C95X0_SELPWM, pwm, mask)) {
 		seq_puts(s, "not available");
 		return;
 	}
@@ -1198,7 +1206,7 @@ static int cy8c95x0_set_mode(struct cy8c95x0_pinctrl *chip, unsigned int off, bo
 	u8 port = cypress_get_port(chip, off);
 	u8 bit = cypress_get_pin_mask(chip, off);
 
-	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_PWMSEL, port, bit, mode ? bit : 0);
+	return cy8c95x0_regmap_write_bits(chip, CY8C95X0_SELPWM, port, bit, mode ? bit : 0);
 }
 
 static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip,
@@ -1347,7 +1355,7 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq)
 
 	ret = devm_request_threaded_irq(chip->dev, irq,
 					NULL, cy8c95x0_irq_handler,
-					IRQF_ONESHOT | IRQF_SHARED | IRQF_TRIGGER_HIGH,
+					IRQF_ONESHOT | IRQF_SHARED,
 					dev_name(chip->dev), chip);
 	if (ret) {
 		dev_err(chip->dev, "failed to request irq %d\n", irq);
@@ -1438,15 +1446,15 @@ static int cy8c95x0_probe(struct i2c_client *client)
 	switch (chip->tpin) {
 	case 20:
 		strscpy(chip->name, cy8c95x0_id[0].name);
-		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 3 * MUXED_STRIDE;
+		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 3 * MUXED_STRIDE - 1;
 		break;
 	case 40:
 		strscpy(chip->name, cy8c95x0_id[1].name);
-		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 6 * MUXED_STRIDE;
+		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 6 * MUXED_STRIDE - 1;
 		break;
 	case 60:
 		strscpy(chip->name, cy8c95x0_id[2].name);
-		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 8 * MUXED_STRIDE;
+		regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 8 * MUXED_STRIDE - 1;
 		break;
 	default:
 		return -ENODEV;
diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig
index b7dbaf77b6db..1b2f2bd09662 100644
--- a/drivers/platform/chrome/Kconfig
+++ b/drivers/platform/chrome/Kconfig
@@ -237,12 +237,19 @@ config CROS_EC_SYSFS
 	  To compile this driver as a module, choose M here: the
 	  module will be called cros_ec_sysfs.
 
+config CROS_EC_TYPEC_ALTMODES
+	bool
+	help
+	  Selectable symbol to enable altmodes.
+
 config CROS_EC_TYPEC
 	tristate "ChromeOS EC Type-C Connector Control"
 	depends on MFD_CROS_EC_DEV && TYPEC
 	depends on CROS_USBPD_NOTIFY
 	depends on USB_ROLE_SWITCH
 	default MFD_CROS_EC_DEV
+	select CROS_EC_TYPEC_ALTMODES if TYPEC_DP_ALTMODE
+	select CROS_EC_TYPEC_ALTMODES if TYPEC_TBT_ALTMODE
 	help
 	  If you say Y here, you get support for accessing Type C connector
 	  information from the Chrome OS EC.
diff --git a/drivers/platform/chrome/Makefile b/drivers/platform/chrome/Makefile
index fb8335458a22..1a5a484563cc 100644
--- a/drivers/platform/chrome/Makefile
+++ b/drivers/platform/chrome/Makefile
@@ -19,7 +19,11 @@ obj-$(CONFIG_CROS_EC_SPI)		+= cros_ec_spi.o
 obj-$(CONFIG_CROS_EC_UART)		+= cros_ec_uart.o
 cros_ec_lpcs-objs			:= cros_ec_lpc.o cros_ec_lpc_mec.o
 cros-ec-typec-objs			:= cros_ec_typec.o cros_typec_vdm.o
+ifneq ($(CONFIG_CROS_EC_TYPEC_ALTMODES),)
+	cros-ec-typec-objs		+= cros_typec_altmode.o
+endif
 obj-$(CONFIG_CROS_EC_TYPEC)		+= cros-ec-typec.o
+
 obj-$(CONFIG_CROS_EC_LPC)		+= cros_ec_lpcs.o
 obj-$(CONFIG_CROS_EC_PROTO)		+= cros_ec_proto.o cros_ec_trace.o
 obj-$(CONFIG_CROS_KBD_LED_BACKLIGHT)	+= cros_kbd_led_backlight.o
diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c
index ae2f86296954..6ee182101bc9 100644
--- a/drivers/platform/chrome/cros_ec_typec.c
+++ b/drivers/platform/chrome/cros_ec_typec.c
@@ -18,6 +18,7 @@
 
 #include "cros_ec_typec.h"
 #include "cros_typec_vdm.h"
+#include "cros_typec_altmode.h"
 
 #define DRV_NAME "cros-ec-typec"
 
@@ -290,30 +291,32 @@ static int cros_typec_register_port_altmodes(struct cros_typec_data *typec,
 	struct typec_altmode *amode;
 
 	/* All PD capable CrOS devices are assumed to support DP altmode. */
+	memset(&desc, 0, sizeof(desc));
 	desc.svid = USB_TYPEC_DP_SID;
 	desc.mode = USB_TYPEC_DP_MODE;
 	desc.vdo = DP_PORT_VDO;
-	amode = typec_port_register_altmode(port->port, &desc);
+	amode = cros_typec_register_displayport(port, &desc,
+						typec->ap_driven_altmode);
 	if (IS_ERR(amode))
 		return PTR_ERR(amode);
 	port->port_altmode[CROS_EC_ALTMODE_DP] = amode;
-	typec_altmode_set_drvdata(amode, port);
-	amode->ops = &port_amode_ops;
 
 	/*
 	 * Register TBT compatibility alt mode. The EC will not enter the mode
-	 * if it doesn't support it, so it's safe to register it unconditionally
-	 * here for now.
+	 * if it doesn't support it and it will not enter automatically by
+	 * design so we can use the |ap_driven_altmode| feature to check if we
+	 * should register it.
 	 */
-	memset(&desc, 0, sizeof(desc));
-	desc.svid = USB_TYPEC_TBT_SID;
-	desc.mode = TYPEC_ANY_MODE;
-	amode = typec_port_register_altmode(port->port, &desc);
-	if (IS_ERR(amode))
-		return PTR_ERR(amode);
-	port->port_altmode[CROS_EC_ALTMODE_TBT] = amode;
-	typec_altmode_set_drvdata(amode, port);
-	amode->ops = &port_amode_ops;
+	if (typec->ap_driven_altmode) {
+		memset(&desc, 0, sizeof(desc));
+		desc.svid = USB_TYPEC_TBT_SID;
+		desc.mode = TBT_MODE;
+		desc.inactive = true;
+		amode = cros_typec_register_thunderbolt(port, &desc);
+		if (IS_ERR(amode))
+			return PTR_ERR(amode);
+		port->port_altmode[CROS_EC_ALTMODE_TBT] = amode;
+	}
 
 	port->state.alt = NULL;
 	port->state.mode = TYPEC_STATE_USB;
@@ -576,6 +579,10 @@ static int cros_typec_enable_dp(struct cros_typec_data *typec,
 	if (!ret)
 		ret = typec_mux_set(port->mux, &port->state);
 
+	if (!ret)
+		ret = cros_typec_displayport_status_update(port->state.alt,
+							   port->state.data);
+
 	return ret;
 }
 
@@ -619,6 +626,7 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num,
 	};
 	struct ec_params_usb_pd_mux_ack mux_ack;
 	enum typec_orientation orientation;
+	struct cros_typec_altmode_node *node;
 	int ret;
 
 	ret = cros_ec_cmd(typec->ec, 0, EC_CMD_USB_PD_MUX_INFO,
@@ -677,6 +685,14 @@ static int cros_typec_configure_mux(struct cros_typec_data *typec, int port_num,
 			port->mux_flags);
 	}
 
+	/* Iterate all partner alt-modes and set the active alternate mode. */
+	list_for_each_entry(node, &port->partner_mode_list, list) {
+		typec_altmode_update_active(
+			node->amode,
+			port->state.alt &&
+				node->amode->svid == port->state.alt->svid);
+	}
+
 mux_ack:
 	if (!typec->needs_mux_ack)
 		return ret;
@@ -1244,6 +1260,8 @@ static int cros_typec_probe(struct platform_device *pdev)
 
 	typec->typec_cmd_supported = cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_CMD);
 	typec->needs_mux_ack = cros_ec_check_features(ec_dev, EC_FEATURE_TYPEC_MUX_REQUIRE_AP_ACK);
+	typec->ap_driven_altmode = cros_ec_check_features(
+		ec_dev, EC_FEATURE_TYPEC_REQUIRE_AP_MODE_ENTRY);
 
 	ret = cros_ec_cmd(typec->ec, 0, EC_CMD_USB_PD_PORTS, NULL, 0,
 			  &resp, sizeof(resp));
diff --git a/drivers/platform/chrome/cros_ec_typec.h b/drivers/platform/chrome/cros_ec_typec.h
index deda180a646f..9fd5342bb0ad 100644
--- a/drivers/platform/chrome/cros_ec_typec.h
+++ b/drivers/platform/chrome/cros_ec_typec.h
@@ -39,6 +39,7 @@ struct cros_typec_data {
 	struct work_struct port_work;
 	bool typec_cmd_supported;
 	bool needs_mux_ack;
+	bool ap_driven_altmode;
 };
 
 /* Per port data. */
diff --git a/drivers/platform/chrome/cros_typec_altmode.c b/drivers/platform/chrome/cros_typec_altmode.c
new file mode 100644
index 000000000000..557340b53af0
--- /dev/null
+++ b/drivers/platform/chrome/cros_typec_altmode.c
@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Alt-mode implementation on ChromeOS EC.
+ *
+ * Copyright 2024 Google LLC
+ * Author: Abhishek Pandit-Subedi <abhishekpandit@chromium.org>
+ */
+#include "cros_ec_typec.h"
+
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/usb/typec_dp.h>
+#include <linux/usb/typec_tbt.h>
+#include <linux/usb/pd_vdo.h>
+
+#include "cros_typec_altmode.h"
+
+struct cros_typec_altmode_data {
+	struct work_struct work;
+	struct cros_typec_port *port;
+	struct typec_altmode *alt;
+	bool ap_mode_entry;
+
+	struct mutex lock;
+	u32 header;
+	u32 *vdo_data;
+	u8 vdo_size;
+
+	u16 sid;
+	u8 mode;
+};
+
+struct cros_typec_dp_data {
+	struct cros_typec_altmode_data adata;
+	struct typec_displayport_data data;
+	bool configured;
+	bool pending_status_update;
+};
+
+static void cros_typec_altmode_work(struct work_struct *work)
+{
+	struct cros_typec_altmode_data *data =
+		container_of(work, struct cros_typec_altmode_data, work);
+
+	mutex_lock(&data->lock);
+
+	if (typec_altmode_vdm(data->alt, data->header, data->vdo_data,
+			      data->vdo_size))
+		dev_err(&data->alt->dev, "VDM 0x%x failed\n", data->header);
+
+	data->header = 0;
+	data->vdo_data = NULL;
+	data->vdo_size = 0;
+
+	mutex_unlock(&data->lock);
+}
+
+static int cros_typec_altmode_enter(struct typec_altmode *alt, u32 *vdo)
+{
+	struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt);
+	struct ec_params_typec_control req = {
+		.port = adata->port->port_num,
+		.command = TYPEC_CONTROL_COMMAND_ENTER_MODE,
+	};
+	int svdm_version;
+	int ret;
+
+	if (!adata->ap_mode_entry) {
+		dev_warn(&alt->dev,
+			 "EC does not support AP driven mode entry\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (adata->sid == USB_TYPEC_DP_SID)
+		req.mode_to_enter = CROS_EC_ALTMODE_DP;
+	else if (adata->sid == USB_TYPEC_TBT_SID)
+		req.mode_to_enter = CROS_EC_ALTMODE_TBT;
+	else
+		return -EOPNOTSUPP;
+
+	ret = cros_ec_cmd(adata->port->typec_data->ec, 0, EC_CMD_TYPEC_CONTROL,
+			  &req, sizeof(req), NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	svdm_version = typec_altmode_get_svdm_version(alt);
+	if (svdm_version < 0)
+		return svdm_version;
+
+	mutex_lock(&adata->lock);
+
+	adata->header = VDO(adata->sid, 1, svdm_version, CMD_ENTER_MODE);
+	adata->header |= VDO_OPOS(adata->mode);
+	adata->header |= VDO_CMDT(CMDT_RSP_ACK);
+	adata->vdo_data = NULL;
+	adata->vdo_size = 1;
+	schedule_work(&adata->work);
+
+	mutex_unlock(&adata->lock);
+	return ret;
+}
+
+static int cros_typec_altmode_exit(struct typec_altmode *alt)
+{
+	struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt);
+	struct ec_params_typec_control req = {
+		.port = adata->port->port_num,
+		.command = TYPEC_CONTROL_COMMAND_EXIT_MODES,
+	};
+	int svdm_version;
+	int ret;
+
+	if (!adata->ap_mode_entry) {
+		dev_warn(&alt->dev,
+			 "EC does not support AP driven mode exit\n");
+		return -EOPNOTSUPP;
+	}
+
+	ret = cros_ec_cmd(adata->port->typec_data->ec, 0, EC_CMD_TYPEC_CONTROL,
+			  &req, sizeof(req), NULL, 0);
+
+	if (ret < 0)
+		return ret;
+
+	svdm_version = typec_altmode_get_svdm_version(alt);
+	if (svdm_version < 0)
+		return svdm_version;
+
+	mutex_lock(&adata->lock);
+
+	adata->header = VDO(adata->sid, 1, svdm_version, CMD_EXIT_MODE);
+	adata->header |= VDO_OPOS(adata->mode);
+	adata->header |= VDO_CMDT(CMDT_RSP_ACK);
+	adata->vdo_data = NULL;
+	adata->vdo_size = 1;
+	schedule_work(&adata->work);
+
+	mutex_unlock(&adata->lock);
+	return ret;
+}
+
+static int cros_typec_displayport_vdm(struct typec_altmode *alt, u32 header,
+				      const u32 *data, int count)
+{
+	struct cros_typec_dp_data *dp_data = typec_altmode_get_drvdata(alt);
+	struct cros_typec_altmode_data *adata = &dp_data->adata;
+
+
+	int cmd_type = PD_VDO_CMDT(header);
+	int cmd = PD_VDO_CMD(header);
+	int svdm_version;
+
+	svdm_version = typec_altmode_get_svdm_version(alt);
+	if (svdm_version < 0)
+		return svdm_version;
+
+	mutex_lock(&adata->lock);
+
+	switch (cmd_type) {
+	case CMDT_INIT:
+		if (PD_VDO_SVDM_VER(header) < svdm_version) {
+			typec_partner_set_svdm_version(adata->port->partner,
+						       PD_VDO_SVDM_VER(header));
+			svdm_version = PD_VDO_SVDM_VER(header);
+		}
+
+		adata->header = VDO(adata->sid, 1, svdm_version, cmd);
+		adata->header |= VDO_OPOS(adata->mode);
+
+		/*
+		 * DP_CMD_CONFIGURE: We can't actually do anything with the
+		 * provided VDO yet so just send back an ACK.
+		 *
+		 * DP_CMD_STATUS_UPDATE: We wait for Mux changes to send
+		 * DPStatus Acks.
+		 */
+		switch (cmd) {
+		case DP_CMD_CONFIGURE:
+			dp_data->data.conf = *data;
+			adata->header |= VDO_CMDT(CMDT_RSP_ACK);
+			dp_data->configured = true;
+			schedule_work(&adata->work);
+			break;
+		case DP_CMD_STATUS_UPDATE:
+			dp_data->pending_status_update = true;
+			break;
+		default:
+			adata->header |= VDO_CMDT(CMDT_RSP_ACK);
+			schedule_work(&adata->work);
+			break;
+		}
+
+		break;
+	default:
+		break;
+	}
+
+	mutex_unlock(&adata->lock);
+	return 0;
+}
+
+static int cros_typec_thunderbolt_vdm(struct typec_altmode *alt, u32 header,
+				      const u32 *data, int count)
+{
+	struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt);
+
+	int cmd_type = PD_VDO_CMDT(header);
+	int cmd = PD_VDO_CMD(header);
+	int svdm_version;
+
+	svdm_version = typec_altmode_get_svdm_version(alt);
+	if (svdm_version < 0)
+		return svdm_version;
+
+	mutex_lock(&adata->lock);
+
+	switch (cmd_type) {
+	case CMDT_INIT:
+		if (PD_VDO_SVDM_VER(header) < svdm_version) {
+			typec_partner_set_svdm_version(adata->port->partner,
+						       PD_VDO_SVDM_VER(header));
+			svdm_version = PD_VDO_SVDM_VER(header);
+		}
+
+		adata->header = VDO(adata->sid, 1, svdm_version, cmd);
+		adata->header |= VDO_OPOS(adata->mode);
+
+		switch (cmd) {
+		case CMD_ENTER_MODE:
+			/* Don't respond to the enter mode vdm because it
+			 * triggers mux configuration. This is handled directly
+			 * by the cros_ec_typec driver so the Thunderbolt driver
+			 * doesn't need to be involved.
+			 */
+			break;
+		default:
+			adata->header |= VDO_CMDT(CMDT_RSP_ACK);
+			schedule_work(&adata->work);
+			break;
+		}
+
+		break;
+	default:
+		break;
+	}
+
+	mutex_unlock(&adata->lock);
+	return 0;
+}
+
+
+static int cros_typec_altmode_vdm(struct typec_altmode *alt, u32 header,
+				      const u32 *data, int count)
+{
+	struct cros_typec_altmode_data *adata = typec_altmode_get_drvdata(alt);
+
+	if (!adata->ap_mode_entry)
+		return -EOPNOTSUPP;
+
+	if (adata->sid == USB_TYPEC_DP_SID)
+		return cros_typec_displayport_vdm(alt, header, data, count);
+
+	if (adata->sid == USB_TYPEC_TBT_SID)
+		return cros_typec_thunderbolt_vdm(alt, header, data, count);
+
+	return -EINVAL;
+}
+
+static const struct typec_altmode_ops cros_typec_altmode_ops = {
+	.enter = cros_typec_altmode_enter,
+	.exit = cros_typec_altmode_exit,
+	.vdm = cros_typec_altmode_vdm,
+};
+
+#if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE)
+int cros_typec_displayport_status_update(struct typec_altmode *altmode,
+					 struct typec_displayport_data *data)
+{
+	struct cros_typec_dp_data *dp_data =
+		typec_altmode_get_drvdata(altmode);
+	struct cros_typec_altmode_data *adata = &dp_data->adata;
+
+	if (!dp_data->pending_status_update) {
+		dev_dbg(&altmode->dev,
+			"Got DPStatus without a pending request\n");
+		return 0;
+	}
+
+	if (dp_data->configured && dp_data->data.conf != data->conf)
+		dev_dbg(&altmode->dev,
+			"DP Conf doesn't match. Requested 0x%04x, Actual 0x%04x\n",
+			dp_data->data.conf, data->conf);
+
+	mutex_lock(&adata->lock);
+
+	dp_data->data = *data;
+	dp_data->pending_status_update = false;
+	adata->header |= VDO_CMDT(CMDT_RSP_ACK);
+	adata->vdo_data = &dp_data->data.status;
+	adata->vdo_size = 2;
+	schedule_work(&adata->work);
+
+	mutex_unlock(&adata->lock);
+
+	return 0;
+}
+
+struct typec_altmode *
+cros_typec_register_displayport(struct cros_typec_port *port,
+				struct typec_altmode_desc *desc,
+				bool ap_mode_entry)
+{
+	struct typec_altmode *alt;
+	struct cros_typec_dp_data *dp_data;
+	struct cros_typec_altmode_data *adata;
+
+	alt = typec_port_register_altmode(port->port, desc);
+	if (IS_ERR(alt))
+		return alt;
+
+	dp_data = devm_kzalloc(&alt->dev, sizeof(*dp_data), GFP_KERNEL);
+	if (!dp_data) {
+		typec_unregister_altmode(alt);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	adata = &dp_data->adata;
+	INIT_WORK(&adata->work, cros_typec_altmode_work);
+	mutex_init(&adata->lock);
+	adata->alt = alt;
+	adata->port = port;
+	adata->ap_mode_entry = ap_mode_entry;
+	adata->sid = desc->svid;
+	adata->mode = desc->mode;
+
+	typec_altmode_set_ops(alt, &cros_typec_altmode_ops);
+	typec_altmode_set_drvdata(alt, adata);
+
+	return alt;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_TYPEC_TBT_ALTMODE)
+struct typec_altmode *
+cros_typec_register_thunderbolt(struct cros_typec_port *port,
+				struct typec_altmode_desc *desc)
+{
+	struct typec_altmode *alt;
+	struct cros_typec_altmode_data *adata;
+
+	alt = typec_port_register_altmode(port->port, desc);
+	if (IS_ERR(alt))
+		return alt;
+
+	adata = devm_kzalloc(&alt->dev, sizeof(*adata), GFP_KERNEL);
+	if (!adata) {
+		typec_unregister_altmode(alt);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	INIT_WORK(&adata->work, cros_typec_altmode_work);
+	adata->alt = alt;
+	adata->port = port;
+	adata->ap_mode_entry = true;
+	adata->sid = desc->svid;
+	adata->mode = desc->mode;
+
+	typec_altmode_set_ops(alt, &cros_typec_altmode_ops);
+	typec_altmode_set_drvdata(alt, adata);
+
+	return alt;
+}
+#endif
diff --git a/drivers/platform/chrome/cros_typec_altmode.h b/drivers/platform/chrome/cros_typec_altmode.h
new file mode 100644
index 000000000000..3f2aa95d065a
--- /dev/null
+++ b/drivers/platform/chrome/cros_typec_altmode.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __CROS_TYPEC_ALTMODE_H__
+#define __CROS_TYPEC_ALTMODE_H__
+
+#include <linux/kconfig.h>
+#include <linux/usb/typec.h>
+
+struct cros_typec_port;
+struct typec_altmode;
+struct typec_altmode_desc;
+struct typec_displayport_data;
+
+#if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE)
+struct typec_altmode *
+cros_typec_register_displayport(struct cros_typec_port *port,
+				struct typec_altmode_desc *desc,
+				bool ap_mode_entry);
+
+int cros_typec_displayport_status_update(struct typec_altmode *altmode,
+					 struct typec_displayport_data *data);
+#else
+static inline struct typec_altmode *
+cros_typec_register_displayport(struct cros_typec_port *port,
+				struct typec_altmode_desc *desc,
+				bool ap_mode_entry)
+{
+	return typec_port_register_altmode(port->port, desc);
+}
+
+static inline int cros_typec_displayport_status_update(struct typec_altmode *altmode,
+					 struct typec_displayport_data *data)
+{
+	return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_TYPEC_TBT_ALTMODE)
+struct typec_altmode *
+cros_typec_register_thunderbolt(struct cros_typec_port *port,
+				struct typec_altmode_desc *desc);
+#else
+static inline struct typec_altmode *
+cros_typec_register_thunderbolt(struct cros_typec_port *port,
+				struct typec_altmode_desc *desc)
+{
+	return typec_port_register_altmode(port->port, desc);
+}
+#endif
+
+#endif /* __CROS_TYPEC_ALTMODE_H__ */
diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c
index 58b860b88fff..57748c3ea24f 100644
--- a/drivers/platform/x86/dell/dell-laptop.c
+++ b/drivers/platform/x86/dell/dell-laptop.c
@@ -103,15 +103,15 @@ static bool mute_led_registered;
 
 struct battery_mode_info {
 	int token;
-	const char *label;
+	enum power_supply_charge_type charge_type;
 };
 
 static const struct battery_mode_info battery_modes[] = {
-	{ BAT_PRI_AC_MODE_TOKEN,   "Trickle" },
-	{ BAT_EXPRESS_MODE_TOKEN,  "Fast" },
-	{ BAT_STANDARD_MODE_TOKEN, "Standard" },
-	{ BAT_ADAPTIVE_MODE_TOKEN, "Adaptive" },
-	{ BAT_CUSTOM_MODE_TOKEN,   "Custom" },
+	{ BAT_PRI_AC_MODE_TOKEN,   POWER_SUPPLY_CHARGE_TYPE_TRICKLE },
+	{ BAT_EXPRESS_MODE_TOKEN,  POWER_SUPPLY_CHARGE_TYPE_FAST },
+	{ BAT_STANDARD_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_STANDARD },
+	{ BAT_ADAPTIVE_MODE_TOKEN, POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE },
+	{ BAT_CUSTOM_MODE_TOKEN,   POWER_SUPPLY_CHARGE_TYPE_CUSTOM },
 };
 static u32 battery_supported_modes;
 
@@ -2261,46 +2261,42 @@ static ssize_t charge_types_show(struct device *dev,
 		struct device_attribute *attr,
 		char *buf)
 {
-	ssize_t count = 0;
+	enum power_supply_charge_type charge_type;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(battery_modes); i++) {
-		bool active;
+		charge_type = battery_modes[i].charge_type;
 
-		if (!(battery_supported_modes & BIT(i)))
+		if (!(battery_supported_modes & BIT(charge_type)))
 			continue;
 
-		active = dell_battery_mode_is_active(battery_modes[i].token);
-		count += sysfs_emit_at(buf, count, active ? "[%s] " : "%s ",
-				battery_modes[i].label);
-	}
+		if (!dell_battery_mode_is_active(battery_modes[i].token))
+			continue;
 
-	/* convert the last space to a newline */
-	if (count > 0)
-		count--;
-	count += sysfs_emit_at(buf, count, "\n");
+		return power_supply_charge_types_show(dev, battery_supported_modes,
+						      charge_type, buf);
+	}
 
-	return count;
+	/* No active mode found */
+	return -EIO;
 }
 
 static ssize_t charge_types_store(struct device *dev,
 		struct device_attribute *attr,
 		const char *buf, size_t size)
 {
-	bool matched = false;
-	int err, i;
+	int charge_type, err, i;
 
-	for (i = 0; i < ARRAY_SIZE(battery_modes); i++) {
-		if (!(battery_supported_modes & BIT(i)))
-			continue;
+	charge_type = power_supply_charge_types_parse(battery_supported_modes, buf);
+	if (charge_type < 0)
+		return charge_type;
 
-		if (sysfs_streq(battery_modes[i].label, buf)) {
-			matched = true;
+	for (i = 0; i < ARRAY_SIZE(battery_modes); i++) {
+		if (battery_modes[i].charge_type == charge_type)
 			break;
-		}
 	}
-	if (!matched)
-		return -EINVAL;
+	if (i == ARRAY_SIZE(battery_modes))
+		return -ENOENT;
 
 	err = dell_battery_set_mode(battery_modes[i].token);
 	if (err)
@@ -2430,7 +2426,7 @@ static u32 __init battery_get_supported_modes(void)
 
 	for (i = 0; i < ARRAY_SIZE(battery_modes); i++) {
 		if (dell_smbios_find_token(battery_modes[i].token))
-			modes |= BIT(i);
+			modes |= BIT(battery_modes[i].charge_type);
 	}
 
 	return modes;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index dfb5d4b8c046..30bd366d7b58 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1121,7 +1121,7 @@ static int ideapad_dytc_profile_init(struct ideapad_private *priv)
 
 	/* Create platform_profile structure and register */
 	priv->dytc->ppdev = devm_platform_profile_register(&priv->platform_device->dev,
-							   "ideapad-laptop", &priv->dytc,
+							   "ideapad-laptop", priv->dytc,
 							   &dytc_profile_ops);
 	if (IS_ERR(priv->dytc->ppdev)) {
 		err = PTR_ERR(priv->dytc->ppdev);
diff --git a/drivers/platform/x86/intel/ifs/ifs.h b/drivers/platform/x86/intel/ifs/ifs.h
index 5c3c0dfa1bf8..f369fb0d3d82 100644
--- a/drivers/platform/x86/intel/ifs/ifs.h
+++ b/drivers/platform/x86/intel/ifs/ifs.h
@@ -23,12 +23,14 @@
  * IFS Image
  * ---------
  *
- * Intel provides a firmware file containing the scan tests via
- * github [#f1]_.  Similar to microcode there is a separate file for each
+ * Intel provides firmware files containing the scan tests via the webpage [#f1]_.
+ * Look under "In-Field Scan Test Images Download" section towards the
+ * end of the page. Similar to microcode, there are separate files for each
  * family-model-stepping. IFS Images are not applicable for some test types.
  * Wherever applicable the sysfs directory would provide a "current_batch" file
  * (see below) for loading the image.
  *
+ * .. [#f1] https://intel.com/InFieldScan
  *
  * IFS Image Loading
  * -----------------
@@ -125,9 +127,6 @@
  * 2) Hardware allows for some number of cores to be tested in parallel.
  * The driver does not make use of this, it only tests one core at a time.
  *
- * .. [#f1] https://github.com/intel/TBD
- *
- *
  * Structural Based Functional Test at Field (SBAF):
  * -------------------------------------------------
  *
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 10f04b944117..1ee0fb5f8250 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -626,8 +626,8 @@ static u32 convert_ltr_scale(u32 val)
 static int pmc_core_ltr_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmcdev = s->private;
-	u64 decoded_snoop_ltr, decoded_non_snoop_ltr;
-	u32 ltr_raw_data, scale, val;
+	u64 decoded_snoop_ltr, decoded_non_snoop_ltr, val;
+	u32 ltr_raw_data, scale;
 	u16 snoop_ltr, nonsnoop_ltr;
 	unsigned int i, index, ltr_index = 0;
 
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index f5fc33a8bf44..60bf0ca64cf3 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -26,7 +26,7 @@ config POWER_RESET_AT91_POWEROFF
 config POWER_RESET_AT91_RESET
 	tristate "Atmel AT91 reset driver"
 	depends on ARCH_AT91
-	default SOC_AT91SAM9 || SOC_SAM9X60 || SOC_SAMA5
+	default SOC_AT91SAM9 || SOC_SAM9X60 || SOC_SAM9X7 || SOC_SAMA5
 	help
 	  This driver supports restart for Atmel AT91SAM9 and SAMA5
 	  SoCs
@@ -34,7 +34,7 @@ config POWER_RESET_AT91_RESET
 config POWER_RESET_AT91_SAMA5D2_SHDWC
 	tristate "Atmel AT91 SAMA5D2-Compatible shutdown controller driver"
 	depends on ARCH_AT91
-	default SOC_SAM9X60 || SOC_SAMA5
+	default SOC_SAM9X60 || SOC_SAM9X7 || SOC_SAMA5
 	help
 	  This driver supports the alternate shutdown controller for some Atmel
 	  SAMA5 SoCs. It is present for example on SAMA5D2 SoC.
diff --git a/drivers/power/reset/as3722-poweroff.c b/drivers/power/reset/as3722-poweroff.c
index bb26fa6fa67c..8075382cbc36 100644
--- a/drivers/power/reset/as3722-poweroff.c
+++ b/drivers/power/reset/as3722-poweroff.c
@@ -57,8 +57,6 @@ static int as3722_poweroff_probe(struct platform_device *pdev)
 					     SYS_OFF_PRIO_DEFAULT,
 					     as3722_pm_power_off,
 					     as3722_poweroff);
-
-	return 0;
 }
 
 static struct platform_driver as3722_poweroff_driver = {
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index edb0df86aff4..c2801bd6384d 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -326,6 +326,7 @@ static const struct of_device_id at91_pmc_ids[] = {
 	{ .compatible = "atmel,sama5d2-pmc" },
 	{ .compatible = "microchip,sam9x60-pmc" },
 	{ .compatible = "microchip,sama7g5-pmc" },
+	{ .compatible = "microchip,sam9x7-pmc" },
 	{ /* Sentinel. */ }
 };
 
diff --git a/drivers/power/reset/gpio-poweroff.c b/drivers/power/reset/gpio-poweroff.c
index 52cfeee2cb28..3eaae352ffb9 100644
--- a/drivers/power/reset/gpio-poweroff.c
+++ b/drivers/power/reset/gpio-poweroff.c
@@ -44,7 +44,13 @@ static int gpio_poweroff_do_poweroff(struct sys_off_data *data)
 	/* give it some time */
 	mdelay(gpio_poweroff->timeout_ms);
 
-	WARN_ON(1);
+	/*
+	 * If code reaches this point, it means that gpio-poweroff has failed
+	 * to actually power off the system.
+	 * Warn the user that the attempt to poweroff via gpio-poweroff
+	 * has gone wrong.
+	 */
+	WARN(1, "Failed to poweroff via gpio-poweroff mechanism\n");
 
 	return NOTIFY_DONE;
 }
diff --git a/drivers/power/reset/keystone-reset.c b/drivers/power/reset/keystone-reset.c
index cfaa54ced0d0..d9268d150e1f 100644
--- a/drivers/power/reset/keystone-reset.c
+++ b/drivers/power/reset/keystone-reset.c
@@ -87,26 +87,16 @@ static int rsctrl_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	/* get regmaps */
-	pllctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pll");
+	pllctrl_regs = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-pll",
+							    1, &rspll_offset);
 	if (IS_ERR(pllctrl_regs))
 		return PTR_ERR(pllctrl_regs);
 
-	devctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-dev");
+	devctrl_regs = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-dev",
+							    1, &rsmux_offset);
 	if (IS_ERR(devctrl_regs))
 		return PTR_ERR(devctrl_regs);
 
-	ret = of_property_read_u32_index(np, "ti,syscon-pll", 1, &rspll_offset);
-	if (ret) {
-		dev_err(dev, "couldn't read the reset pll offset!\n");
-		return -EINVAL;
-	}
-
-	ret = of_property_read_u32_index(np, "ti,syscon-dev", 1, &rsmux_offset);
-	if (ret) {
-		dev_err(dev, "couldn't read the rsmux offset!\n");
-		return -EINVAL;
-	}
-
 	/* set soft/hard reset */
 	val = of_property_read_bool(np, "ti,soft-reset");
 	val = val ? RSCFG_RSTYPE_SOFT : RSCFG_RSTYPE_HARD;
diff --git a/drivers/power/supply/88pm860x_battery.c b/drivers/power/supply/88pm860x_battery.c
index b7938fbb24a5..edae1e843c51 100644
--- a/drivers/power/supply/88pm860x_battery.c
+++ b/drivers/power/supply/88pm860x_battery.c
@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/string.h>
 #include <linux/power_supply.h>
+#include <linux/string_choices.h>
 #include <linux/mfd/88pm860x.h>
 #include <linux/delay.h>
 
@@ -503,8 +504,7 @@ static void pm860x_init_battery(struct pm860x_battery_info *info)
 	data = pm860x_reg_read(info->i2c, PM8607_POWER_UP_LOG);
 	bat_remove = data & BAT_WU_LOG;
 
-	dev_dbg(info->dev, "battery wake up? %s\n",
-		bat_remove != 0 ? "yes" : "no");
+	dev_dbg(info->dev, "battery wake up? %s\n", str_yes_no(bat_remove));
 
 	/* restore SOC from RTC domain register */
 	if (bat_remove == 0) {
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index 9f2eef6787f7..7b18358f194a 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -918,6 +918,15 @@ config FUEL_GAUGE_SC27XX
 	  Say Y here to enable support for fuel gauge with SC27XX
 	  PMIC chips.
 
+config FUEL_GAUGE_STC3117
+       tristate "STMicroelectronics STC3117 fuel gauge driver"
+       depends on CRC8
+       depends on I2C
+	select REGMAP_I2C
+       help
+         Say Y here to enable support for fuel gauge with STC3117
+         chip.
+
 config CHARGER_UCS1002
 	tristate "Microchip UCS1002 USB Port Power Controller"
 	depends on I2C
diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile
index 59c4a9f40d28..b55cc48a4c86 100644
--- a/drivers/power/supply/Makefile
+++ b/drivers/power/supply/Makefile
@@ -108,6 +108,7 @@ obj-$(CONFIG_CHARGER_CROS_USBPD)	+= cros_usbpd-charger.o
 obj-$(CONFIG_CHARGER_CROS_PCHG)	+= cros_peripheral_charger.o
 obj-$(CONFIG_CHARGER_SC2731)	+= sc2731_charger.o
 obj-$(CONFIG_FUEL_GAUGE_SC27XX)	+= sc27xx_fuel_gauge.o
+obj-$(CONFIG_FUEL_GAUGE_STC3117)       += stc3117_fuel_gauge.o
 obj-$(CONFIG_CHARGER_UCS1002)	+= ucs1002_power.o
 obj-$(CONFIG_CHARGER_BD99954)	+= bd99954-charger.o
 obj-$(CONFIG_CHARGER_WILCO)	+= wilco-charger.o
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index 37039e28fc4b..b00c84fbc33c 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -540,10 +540,9 @@ static int ab8500_btemp_get_property(struct power_supply *psy,
 	return 0;
 }
 
-static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data)
+static int ab8500_btemp_get_ext_psy_data(struct power_supply *ext, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext = dev_get_drvdata(dev);
 	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_btemp *di;
 	union power_supply_propval ret;
@@ -617,7 +616,7 @@ static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data)
  */
 static void ab8500_btemp_external_power_changed(struct power_supply *psy)
 {
-	power_supply_for_each_device(psy, ab8500_btemp_get_ext_psy_data);
+	power_supply_for_each_psy(psy, ab8500_btemp_get_ext_psy_data);
 }
 
 /* ab8500 btemp driver interrupts and their respective isr */
diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c
index 14e1b448bd39..7a8d1feb8e90 100644
--- a/drivers/power/supply/ab8500_chargalg.c
+++ b/drivers/power/supply/ab8500_chargalg.c
@@ -844,10 +844,9 @@ static void handle_maxim_chg_curr(struct ab8500_chargalg *di)
 	}
 }
 
-static int ab8500_chargalg_get_ext_psy_data(struct device *dev, void *data)
+static int ab8500_chargalg_get_ext_psy_data(struct power_supply *ext, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext = dev_get_drvdata(dev);
 	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_chargalg *di;
 	union power_supply_propval ret;
@@ -1231,7 +1230,7 @@ static void ab8500_chargalg_algorithm(struct ab8500_chargalg *di)
 	int ret;
 
 	/* Collect data from all power_supply class devices */
-	power_supply_for_each_device(di->chargalg_psy, ab8500_chargalg_get_ext_psy_data);
+	power_supply_for_each_psy(di->chargalg_psy, ab8500_chargalg_get_ext_psy_data);
 
 	ab8500_chargalg_end_of_charge(di);
 	ab8500_chargalg_check_temp(di);
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index cece8d6753ac..1042d37424f5 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -1894,10 +1894,9 @@ static int ab8500_charger_update_charger_current(struct ux500_charger *charger,
 	return ret;
 }
 
-static int ab8500_charger_get_ext_psy_data(struct device *dev, void *data)
+static int ab8500_charger_get_ext_psy_data(struct power_supply *ext, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext = dev_get_drvdata(dev);
 	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_charger *di;
 	union power_supply_propval ret;
@@ -1961,7 +1960,7 @@ static void ab8500_charger_check_vbat_work(struct work_struct *work)
 	struct ab8500_charger *di = container_of(work,
 		struct ab8500_charger, check_vbat_work.work);
 
-	power_supply_for_each_device(&di->usb_chg, ab8500_charger_get_ext_psy_data);
+	power_supply_for_each_psy(&di->usb_chg, ab8500_charger_get_ext_psy_data);
 
 	/* First run old_vbat is 0. */
 	if (di->old_vbat == 0)
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index 78871a2143de..9dd99722667a 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -2174,10 +2174,9 @@ static int ab8500_fg_get_property(struct power_supply *psy,
 	return 0;
 }
 
-static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data)
+static int ab8500_fg_get_ext_psy_data(struct power_supply *ext, void *data)
 {
 	struct power_supply *psy;
-	struct power_supply *ext = dev_get_drvdata(dev);
 	const char **supplicants = (const char **)ext->supplied_to;
 	struct ab8500_fg *di;
 	struct power_supply_battery_info *bi;
@@ -2402,7 +2401,7 @@ out:
  */
 static void ab8500_fg_external_power_changed(struct power_supply *psy)
 {
-	power_supply_for_each_device(psy, ab8500_fg_get_ext_psy_data);
+	power_supply_for_each_psy(psy, ab8500_fg_get_ext_psy_data);
 }
 
 /**
@@ -2575,7 +2574,7 @@ static ssize_t ab8505_powercut_flagtime_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2598,7 +2597,7 @@ static ssize_t ab8505_powercut_flagtime_write(struct device *dev,
 {
 	int ret;
 	int reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	if (kstrtoint(buf, 10, &reg_value))
@@ -2625,7 +2624,7 @@ static ssize_t ab8505_powercut_maxtime_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2649,7 +2648,7 @@ static ssize_t ab8505_powercut_maxtime_write(struct device *dev,
 {
 	int ret;
 	int reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	if (kstrtoint(buf, 10, &reg_value))
@@ -2676,7 +2675,7 @@ static ssize_t ab8505_powercut_restart_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2699,7 +2698,7 @@ static ssize_t ab8505_powercut_restart_write(struct device *dev,
 {
 	int ret;
 	int reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	if (kstrtoint(buf, 10, &reg_value))
@@ -2727,7 +2726,7 @@ static ssize_t ab8505_powercut_timer_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2750,7 +2749,7 @@ static ssize_t ab8505_powercut_restart_counter_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2773,7 +2772,7 @@ static ssize_t ab8505_powercut_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2794,7 +2793,7 @@ static ssize_t ab8505_powercut_write(struct device *dev,
 {
 	int ret;
 	int reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	if (kstrtoint(buf, 10, &reg_value))
@@ -2822,7 +2821,7 @@ static ssize_t ab8505_powercut_flag_read(struct device *dev,
 
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2845,7 +2844,7 @@ static ssize_t ab8505_powercut_debounce_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
@@ -2868,7 +2867,7 @@ static ssize_t ab8505_powercut_debounce_write(struct device *dev,
 {
 	int ret;
 	int reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	if (kstrtoint(buf, 10, &reg_value))
@@ -2895,7 +2894,7 @@ static ssize_t ab8505_powercut_enable_status_read(struct device *dev,
 {
 	int ret;
 	u8 reg_value;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct ab8500_fg *di = power_supply_get_drvdata(psy);
 
 	ret = abx500_get_register_interruptible(di->dev, AB8500_RTC,
diff --git a/drivers/power/supply/apm_power.c b/drivers/power/supply/apm_power.c
index 8ef1b6f1f787..9236e0078578 100644
--- a/drivers/power/supply/apm_power.c
+++ b/drivers/power/supply/apm_power.c
@@ -42,11 +42,11 @@ struct find_bat_param {
 	int max_energy;
 };
 
-static int __find_main_battery(struct device *dev, void *data)
+static int __find_main_battery(struct power_supply *psy, void *data)
 {
 	struct find_bat_param *bp = (struct find_bat_param *)data;
 
-	bp->bat = dev_get_drvdata(dev);
+	bp->bat = psy;
 
 	if (bp->bat->desc->use_for_apm) {
 		/* nice, we explicitly asked to report this battery. */
@@ -79,7 +79,7 @@ static void find_main_battery(void)
 	main_battery = NULL;
 	bp.main = main_battery;
 
-	error = power_supply_for_each_device(&bp, __find_main_battery);
+	error = power_supply_for_each_psy(&bp, __find_main_battery);
 	if (error) {
 		main_battery = bp.main;
 		return;
diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c
index 25e28dac900d..22f6a3b71632 100644
--- a/drivers/power/supply/bq2415x_charger.c
+++ b/drivers/power/supply/bq2415x_charger.c
@@ -171,6 +171,7 @@ struct bq2415x_device {
 	char *name;
 	int autotimer;	/* 1 - if driver automatically reset timer, 0 - not */
 	int automode;	/* 1 - enabled, 0 - disabled; -1 - not supported */
+	int charge_status;
 	int id;
 };
 
@@ -835,11 +836,13 @@ static int bq2415x_notifier_call(struct notifier_block *nb,
 	if (!bq2415x_update_reported_mode(bq, prop.intval))
 		return NOTIFY_OK;
 
+	power_supply_changed(bq->charger);
+
 	/* if automode is not enabled do not tell about reported_mode */
 	if (bq->automode < 1)
 		return NOTIFY_OK;
 
-	schedule_delayed_work(&bq->work, 0);
+	mod_delayed_work(system_wq, &bq->work, 0);
 
 	return NOTIFY_OK;
 }
@@ -889,12 +892,19 @@ static void bq2415x_timer_work(struct work_struct *work)
 	int ret;
 	int error;
 	int boost;
+	int charge;
 
 	if (bq->automode > 0 && (bq->reported_mode != bq->mode)) {
 		sysfs_notify(&bq->charger->dev.kobj, NULL, "reported_mode");
 		bq2415x_set_mode(bq, bq->reported_mode);
 	}
 
+	charge = bq2415x_exec_command(bq, BQ2415X_CHARGE_STATUS);
+	if (bq->charge_status != charge) {
+		power_supply_changed(bq->charger);
+		bq->charge_status = charge;
+	}
+
 	if (!bq->autotimer)
 		return;
 
@@ -1050,7 +1060,7 @@ static ssize_t bq2415x_sysfs_show_status(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	enum bq2415x_command command;
 	int ret;
@@ -1083,7 +1093,7 @@ static ssize_t bq2415x_sysfs_set_timer(struct device *dev,
 				       const char *buf,
 				       size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	int ret = 0;
 
@@ -1104,7 +1114,7 @@ static ssize_t bq2415x_sysfs_show_timer(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 
 	if (bq->timer_error)
@@ -1128,7 +1138,7 @@ static ssize_t bq2415x_sysfs_set_mode(struct device *dev,
 				      const char *buf,
 				      size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	enum bq2415x_mode mode;
 	int ret = 0;
@@ -1180,7 +1190,7 @@ static ssize_t bq2415x_sysfs_show_mode(struct device *dev,
 				       struct device_attribute *attr,
 				       char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	ssize_t ret = 0;
 
@@ -1217,7 +1227,7 @@ static ssize_t bq2415x_sysfs_show_reported_mode(struct device *dev,
 						struct device_attribute *attr,
 						char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 
 	if (bq->automode < 0)
@@ -1245,7 +1255,7 @@ static ssize_t bq2415x_sysfs_set_registers(struct device *dev,
 					   const char *buf,
 					   size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	ssize_t ret = 0;
 	unsigned int reg;
@@ -1280,7 +1290,7 @@ static ssize_t bq2415x_sysfs_show_registers(struct device *dev,
 					    struct device_attribute *attr,
 					    char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	ssize_t ret = 0;
 
@@ -1298,7 +1308,7 @@ static ssize_t bq2415x_sysfs_set_limit(struct device *dev,
 				       const char *buf,
 				       size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	long val;
 	int ret;
@@ -1329,7 +1339,7 @@ static ssize_t bq2415x_sysfs_show_limit(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	int ret;
 
@@ -1357,7 +1367,7 @@ static ssize_t bq2415x_sysfs_set_enable(struct device *dev,
 					const char *buf,
 					size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	enum bq2415x_command command;
 	long val;
@@ -1392,7 +1402,7 @@ static ssize_t bq2415x_sysfs_show_enable(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq2415x_device *bq = power_supply_get_drvdata(psy);
 	enum bq2415x_command command;
 	int ret;
diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index c47f32f152e6..b4ba01744368 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -152,6 +152,7 @@
 #define BQ24296_REG_VPRS_PN_MASK		(BIT(7) | BIT(6) | BIT(5))
 #define BQ24296_REG_VPRS_PN_SHIFT		5
 #define BQ24296_REG_VPRS_PN_24296		0x1
+#define BQ24296_REG_VPRS_PN_24297		0x3
 #define BQ24190_REG_VPRS_TS_PROFILE_MASK	BIT(2)
 #define BQ24190_REG_VPRS_TS_PROFILE_SHIFT	2
 #define BQ24190_REG_VPRS_DEV_REG_MASK		(BIT(1) | BIT(0))
@@ -208,6 +209,7 @@ enum bq24190_chip {
 	BQ24192i,
 	BQ24196,
 	BQ24296,
+	BQ24297,
 };
 
 /*
@@ -422,7 +424,7 @@ static struct bq24190_sysfs_field_info bq24190_sysfs_field_tbl[] = {
 	BQ24190_SYSFS_FIELD_RO(watchdog,	CTTC,	WATCHDOG),
 	BQ24190_SYSFS_FIELD_RW(en_timer,	CTTC,	EN_TIMER),
 	BQ24190_SYSFS_FIELD_RW(chg_timer,	CTTC,	CHG_TIMER),
-	BQ24190_SYSFS_FIELD_RW(jeta_iset,	CTTC,	JEITA_ISET),
+	BQ24190_SYSFS_FIELD_RW(jeita_iset,	CTTC,	JEITA_ISET),
 	BQ24190_SYSFS_FIELD_RW(bat_comp,	ICTRC,	BAT_COMP),
 	BQ24190_SYSFS_FIELD_RW(vclamp,		ICTRC,	VCLAMP),
 	BQ24190_SYSFS_FIELD_RW(treg,		ICTRC,	TREG),
@@ -480,7 +482,7 @@ static struct bq24190_sysfs_field_info *bq24190_sysfs_field_lookup(
 static ssize_t bq24190_sysfs_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq24190_dev_info *bdi = power_supply_get_drvdata(psy);
 	struct bq24190_sysfs_field_info *info;
 	ssize_t count;
@@ -510,7 +512,7 @@ static ssize_t bq24190_sysfs_show(struct device *dev,
 static ssize_t bq24190_sysfs_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq24190_dev_info *bdi = power_supply_get_drvdata(psy);
 	struct bq24190_sysfs_field_info *info;
 	int ret;
@@ -1319,6 +1321,7 @@ static int bq24190_charger_get_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
+	case POWER_SUPPLY_PROP_CHARGE_TYPES:
 		ret = bq24190_charger_get_charge_type(bdi, val);
 		break;
 	case POWER_SUPPLY_PROP_HEALTH:
@@ -1399,6 +1402,7 @@ static int bq24190_charger_set_property(struct power_supply *psy,
 		ret = bq24190_charger_set_temp_alert_max(bdi, val);
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
+	case POWER_SUPPLY_PROP_CHARGE_TYPES:
 		ret = bq24190_charger_set_charge_type(bdi, val);
 		break;
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT:
@@ -1427,6 +1431,7 @@ static int bq24190_charger_property_is_writeable(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_ONLINE:
 	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
 	case POWER_SUPPLY_PROP_CHARGE_TYPE:
+	case POWER_SUPPLY_PROP_CHARGE_TYPES:
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT:
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE:
 	case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT:
@@ -1475,6 +1480,7 @@ static void bq24190_charger_external_power_changed(struct power_supply *psy)
 
 static enum power_supply_property bq24190_charger_properties[] = {
 	POWER_SUPPLY_PROP_CHARGE_TYPE,
+	POWER_SUPPLY_PROP_CHARGE_TYPES,
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_ONLINE,
 	POWER_SUPPLY_PROP_STATUS,
@@ -1504,6 +1510,9 @@ static const struct power_supply_desc bq24190_charger_desc = {
 	.set_property		= bq24190_charger_set_property,
 	.property_is_writeable	= bq24190_charger_property_is_writeable,
 	.external_power_changed	= bq24190_charger_external_power_changed,
+	.charge_types		= BIT(POWER_SUPPLY_CHARGE_TYPE_NONE)    |
+				  BIT(POWER_SUPPLY_CHARGE_TYPE_TRICKLE) |
+				  BIT(POWER_SUPPLY_CHARGE_TYPE_FAST),
 };
 
 /* Battery power supply property routines */
@@ -1897,6 +1906,7 @@ static int bq24296_check_chip(struct bq24190_dev_info *bdi)
 
 	switch (v) {
 	case BQ24296_REG_VPRS_PN_24296:
+	case BQ24296_REG_VPRS_PN_24297:
 		break;
 	default:
 		dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v);
@@ -2033,6 +2043,17 @@ static const struct bq24190_chip_info bq24190_chip_info_tbl[] = {
 		.get_ntc_status = bq24296_charger_get_ntc_status,
 		.set_otg_vbus = bq24296_set_otg_vbus,
 	},
+	[BQ24297] = {
+		.ichg_array_size = BQ24296_CCC_ICHG_VALUES_LEN,
+#ifdef CONFIG_REGULATOR
+		.vbus_desc = &bq24296_vbus_desc,
+#endif
+		.check_chip = bq24296_check_chip,
+		.set_chg_config = bq24296_battery_set_chg_config,
+		.ntc_fault_mask = BQ24296_REG_F_NTC_FAULT_MASK,
+		.get_ntc_status = bq24296_charger_get_ntc_status,
+		.set_otg_vbus = bq24296_set_otg_vbus,
+	},
 };
 
 static int bq24190_probe(struct i2c_client *client)
@@ -2289,6 +2310,7 @@ static const struct i2c_device_id bq24190_i2c_ids[] = {
 	{ "bq24192i", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24192i] },
 	{ "bq24196", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24196] },
 	{ "bq24296", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24296] },
+	{ "bq24297", (kernel_ulong_t)&bq24190_chip_info_tbl[BQ24297] },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids);
@@ -2299,6 +2321,7 @@ static const struct of_device_id bq24190_of_match[] = {
 	{ .compatible = "ti,bq24192i", .data = &bq24190_chip_info_tbl[BQ24192i] },
 	{ .compatible = "ti,bq24196", .data = &bq24190_chip_info_tbl[BQ24196] },
 	{ .compatible = "ti,bq24296", .data = &bq24190_chip_info_tbl[BQ24296] },
+	{ .compatible = "ti,bq24297", .data = &bq24190_chip_info_tbl[BQ24297] },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bq24190_of_match);
diff --git a/drivers/power/supply/bq24257_charger.c b/drivers/power/supply/bq24257_charger.c
index 801d0d2c5f2e..1416586f2459 100644
--- a/drivers/power/supply/bq24257_charger.c
+++ b/drivers/power/supply/bq24257_charger.c
@@ -759,7 +759,7 @@ static ssize_t bq24257_show_ovp_voltage(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq24257_device *bq = power_supply_get_drvdata(psy);
 
 	return sysfs_emit(buf, "%u\n", bq24257_vovp_map[bq->init_data.vovp]);
@@ -769,7 +769,7 @@ static ssize_t bq24257_show_in_dpm_voltage(struct device *dev,
 					   struct device_attribute *attr,
 					   char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq24257_device *bq = power_supply_get_drvdata(psy);
 
 	return sysfs_emit(buf, "%u\n", bq24257_vindpm_map[bq->init_data.vindpm]);
@@ -779,7 +779,7 @@ static ssize_t bq24257_sysfs_show_enable(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq24257_device *bq = power_supply_get_drvdata(psy);
 	int ret;
 
@@ -801,7 +801,7 @@ static ssize_t bq24257_sysfs_set_enable(struct device *dev,
 					const char *buf,
 					size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct bq24257_device *bq = power_supply_get_drvdata(psy);
 	long val;
 	int ret;
diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 40c5ac7a1118..90a5bccfc6b9 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -123,6 +123,7 @@ enum bq27xxx_reg_index {
 	BQ27XXX_DM_BLOCK,	/* Data Block */
 	BQ27XXX_DM_DATA,	/* Block Data */
 	BQ27XXX_DM_CKSUM,	/* Block Data Checksum */
+	BQ27XXX_REG_SEDVF,	/* End-of-discharge Voltage */
 	BQ27XXX_REG_MAX,	/* sentinel */
 };
 
@@ -159,6 +160,7 @@ static u8
 		[BQ27XXX_DM_BLOCK] = INVALID_REG_ADDR,
 		[BQ27XXX_DM_DATA] = INVALID_REG_ADDR,
 		[BQ27XXX_DM_CKSUM] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SEDVF] = 0x77,
 	},
 	bq27010_regs[BQ27XXX_REG_MAX] = {
 		[BQ27XXX_REG_CTRL] = 0x00,
@@ -184,6 +186,7 @@ static u8
 		[BQ27XXX_DM_BLOCK] = INVALID_REG_ADDR,
 		[BQ27XXX_DM_DATA] = INVALID_REG_ADDR,
 		[BQ27XXX_DM_CKSUM] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SEDVF] = 0x77,
 	},
 	bq2750x_regs[BQ27XXX_REG_MAX] = {
 		[BQ27XXX_REG_CTRL] = 0x00,
@@ -579,6 +582,7 @@ static enum power_supply_property bq27000_props[] = {
 	POWER_SUPPLY_PROP_POWER_AVG,
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
 };
 
 static enum power_supply_property bq27010_props[] = {
@@ -599,6 +603,7 @@ static enum power_supply_property bq27010_props[] = {
 	POWER_SUPPLY_PROP_CYCLE_COUNT,
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
 };
 
 #define bq2750x_props bq27510g3_props
@@ -2039,6 +2044,36 @@ static int bq27xxx_battery_voltage(struct bq27xxx_device_info *di,
 	return 0;
 }
 
+/*
+ * Return the design minimum battery Voltage in microvolts
+ * Or < 0 if something fails.
+ */
+static int bq27xxx_battery_read_dmin_volt(struct bq27xxx_device_info *di,
+					  union power_supply_propval *val)
+{
+	int volt;
+
+	/* We only have to read design minimum voltage once */
+	if (di->voltage_min_design > 0) {
+		val->intval = di->voltage_min_design;
+		return 0;
+	}
+
+	volt = bq27xxx_read(di, BQ27XXX_REG_SEDVF, true);
+	if (volt < 0) {
+		dev_err(di->dev, "error reading design min voltage\n");
+		return volt;
+	}
+
+	/* SEDVF = Design EDVF / 8 - 256 */
+	val->intval = volt * 8000 + 2048000;
+
+	/* Save for later reads */
+	di->voltage_min_design = val->intval;
+
+	return 0;
+}
+
 static int bq27xxx_simple_value(int value,
 				union power_supply_propval *val)
 {
@@ -2119,8 +2154,10 @@ static int bq27xxx_battery_get_property(struct power_supply *psy,
 	 * power_supply_battery_info visible in sysfs.
 	 */
 	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
-	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
 		return -EINVAL;
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+		ret = bq27xxx_battery_read_dmin_volt(di, val);
+		break;
 	case POWER_SUPPLY_PROP_CYCLE_COUNT:
 		ret = bq27xxx_battery_read_cyct(di, val);
 		break;
diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c
index a69faef444c0..c49e0e4d02f7 100644
--- a/drivers/power/supply/charger-manager.c
+++ b/drivers/power/supply/charger-manager.c
@@ -22,6 +22,7 @@
 #include <linux/platform_device.h>
 #include <linux/power/charger-manager.h>
 #include <linux/regulator/consumer.h>
+#include <linux/string_choices.h>
 #include <linux/sysfs.h>
 #include <linux/of.h>
 #include <linux/thermal.h>
@@ -1088,7 +1089,7 @@ static ssize_t charger_state_show(struct device *dev,
 	if (!charger->externally_control)
 		state = regulator_is_enabled(charger->consumer);
 
-	return sysfs_emit(buf, "%s\n", state ? "enabled" : "disabled");
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(state));
 }
 
 static ssize_t charger_externally_control_show(struct device *dev,
diff --git a/drivers/power/supply/cpcap-charger.c b/drivers/power/supply/cpcap-charger.c
index 7781b45a67a7..6625d539d9ae 100644
--- a/drivers/power/supply/cpcap-charger.c
+++ b/drivers/power/supply/cpcap-charger.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
@@ -515,7 +516,7 @@ static void cpcap_charger_vbus_work(struct work_struct *work)
 out_err:
 	cpcap_charger_update_state(ddata, POWER_SUPPLY_STATUS_UNKNOWN);
 	dev_err(ddata->dev, "%s could not %s vbus: %i\n", __func__,
-		ddata->vbus_enabled ? "enable" : "disable", error);
+		str_enable_disable(ddata->vbus_enabled), error);
 }
 
 static int cpcap_charger_set_vbus(struct phy_companion *comparator,
diff --git a/drivers/power/supply/cros_charge-control.c b/drivers/power/supply/cros_charge-control.c
index 9b0a7500296b..02d5bdbe2e8d 100644
--- a/drivers/power/supply/cros_charge-control.c
+++ b/drivers/power/supply/cros_charge-control.c
@@ -20,13 +20,6 @@
 					 BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE)   | \
 					 BIT(POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE))
 
-enum CROS_CHCTL_ATTR {
-	CROS_CHCTL_ATTR_START_THRESHOLD,
-	CROS_CHCTL_ATTR_END_THRESHOLD,
-	CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR,
-	_CROS_CHCTL_ATTR_COUNT
-};
-
 /*
  * Semantics of data *returned* from the EC API and Linux sysfs differ
  * slightly, also the v1 API can not return any data.
@@ -38,18 +31,13 @@ enum CROS_CHCTL_ATTR {
  */
 
 struct cros_chctl_priv {
+	struct device *dev;
 	struct cros_ec_device *cros_ec;
 	struct acpi_battery_hook battery_hook;
 	struct power_supply *hooked_battery;
 	u8 cmd_version;
 
-	/* The callbacks need to access this priv structure.
-	 * As neither the struct device nor power_supply are under the drivers
-	 * control, embed the attributes within priv to use with container_of().
-	 */
-	struct device_attribute device_attrs[_CROS_CHCTL_ATTR_COUNT];
-	struct attribute *attributes[_CROS_CHCTL_ATTR_COUNT];
-	struct attribute_group group;
+	const struct power_supply_ext *psy_ext;
 
 	struct mutex lock; /* protects fields below and cros_ec */
 	enum power_supply_charge_behaviour current_behaviour;
@@ -119,26 +107,39 @@ static int cros_chctl_configure_ec(struct cros_chctl_priv *priv)
 	return cros_chctl_send_charge_control_cmd(priv->cros_ec, priv->cmd_version, &req);
 }
 
-static struct cros_chctl_priv *cros_chctl_attr_to_priv(struct attribute *attr,
-						       enum CROS_CHCTL_ATTR idx)
+static int cros_chctl_psy_ext_get_prop(struct power_supply *psy,
+				       const struct power_supply_ext *ext,
+				       void *data,
+				       enum power_supply_property psp,
+				       union power_supply_propval *val)
 {
-	struct device_attribute *dev_attr = container_of(attr, struct device_attribute, attr);
+	struct cros_chctl_priv *priv = data;
 
-	return container_of(dev_attr, struct cros_chctl_priv, device_attrs[idx]);
+	switch (psp) {
+	case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD:
+		val->intval = priv->current_start_threshold;
+		return 0;
+	case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD:
+		val->intval = priv->current_end_threshold;
+		return 0;
+	case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR:
+		val->intval = priv->current_behaviour;
+		return 0;
+	default:
+		return -EINVAL;
+	}
 }
 
-static ssize_t cros_chctl_store_threshold(struct device *dev, struct cros_chctl_priv *priv,
-					  int is_end_threshold, const char *buf, size_t count)
+static int cros_chctl_psy_ext_set_threshold(struct cros_chctl_priv *priv,
+					    enum power_supply_property psp,
+					    int val)
 {
-	int ret, val;
+	int ret;
 
-	ret = kstrtoint(buf, 10, &val);
-	if (ret < 0)
-		return ret;
 	if (val < 0 || val > 100)
 		return -EINVAL;
 
-	if (is_end_threshold) {
+	if (psp == POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD) {
 		/* Start threshold is not exposed, use fixed value */
 		if (priv->cmd_version == 2)
 			priv->current_start_threshold = val == 100 ? 0 : val;
@@ -158,93 +159,73 @@ static ssize_t cros_chctl_store_threshold(struct device *dev, struct cros_chctl_
 			return ret;
 	}
 
-	return count;
-}
-
-static ssize_t charge_control_start_threshold_show(struct device *dev,
-						   struct device_attribute *attr,
-						   char *buf)
-{
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr,
-							       CROS_CHCTL_ATTR_START_THRESHOLD);
-
-	guard(mutex)(&priv->lock);
-	return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_start_threshold);
+	return 0;
 }
 
-static ssize_t charge_control_start_threshold_store(struct device *dev,
-						    struct device_attribute *attr,
-						    const char *buf, size_t count)
-{
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr,
-							       CROS_CHCTL_ATTR_START_THRESHOLD);
-
-	guard(mutex)(&priv->lock);
-	return cros_chctl_store_threshold(dev, priv, 0, buf, count);
-}
 
-static ssize_t charge_control_end_threshold_show(struct device *dev, struct device_attribute *attr,
-						 char *buf)
+static int cros_chctl_psy_ext_set_prop(struct power_supply *psy,
+				       const struct power_supply_ext *ext,
+				       void *data,
+				       enum power_supply_property psp,
+				       const union power_supply_propval *val)
 {
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr,
-							       CROS_CHCTL_ATTR_END_THRESHOLD);
+	struct cros_chctl_priv *priv = data;
+	int ret;
 
 	guard(mutex)(&priv->lock);
-	return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_end_threshold);
-}
-
-static ssize_t charge_control_end_threshold_store(struct device *dev, struct device_attribute *attr,
-						  const char *buf, size_t count)
-{
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr,
-							       CROS_CHCTL_ATTR_END_THRESHOLD);
 
-	guard(mutex)(&priv->lock);
-	return cros_chctl_store_threshold(dev, priv, 1, buf, count);
+	switch (psp) {
+	case POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD:
+	case POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD:
+		return cros_chctl_psy_ext_set_threshold(priv, psp, val->intval);
+	case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR:
+		priv->current_behaviour = val->intval;
+		ret = cros_chctl_configure_ec(priv);
+		if (ret < 0)
+			return ret;
+		return 0;
+	default:
+		return -EINVAL;
+	}
 }
 
-static ssize_t charge_behaviour_show(struct device *dev, struct device_attribute *attr, char *buf)
+static int cros_chctl_psy_prop_is_writeable(struct power_supply *psy,
+					    const struct power_supply_ext *ext,
+					    void *data,
+					    enum power_supply_property psp)
 {
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr,
-							       CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR);
-
-	guard(mutex)(&priv->lock);
-	return power_supply_charge_behaviour_show(dev, EC_CHARGE_CONTROL_BEHAVIOURS,
-						  priv->current_behaviour, buf);
+	return true;
 }
 
-static ssize_t charge_behaviour_store(struct device *dev, struct device_attribute *attr,
-				      const char *buf, size_t count)
-{
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr,
-							       CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR);
-	int ret;
-
-	ret = power_supply_charge_behaviour_parse(EC_CHARGE_CONTROL_BEHAVIOURS, buf);
-	if (ret < 0)
-		return ret;
-
-	guard(mutex)(&priv->lock);
-	priv->current_behaviour = ret;
+#define DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(_name, ...)			\
+	static const enum power_supply_property _name ## _props[] = {		\
+		__VA_ARGS__,							\
+	};									\
+										\
+	static const struct power_supply_ext _name = {				\
+		.name			= "cros-charge-control",		\
+		.properties		= _name ## _props,			\
+		.num_properties		= ARRAY_SIZE(_name ## _props),		\
+		.charge_behaviours	= EC_CHARGE_CONTROL_BEHAVIOURS,		\
+		.get_property		= cros_chctl_psy_ext_get_prop,		\
+		.set_property		= cros_chctl_psy_ext_set_prop,		\
+		.property_is_writeable	= cros_chctl_psy_prop_is_writeable,	\
+	}
 
-	ret = cros_chctl_configure_ec(priv);
-	if (ret < 0)
-		return ret;
+DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(cros_chctl_psy_ext_v1,
+	POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR
+);
 
-	return count;
-}
+DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(cros_chctl_psy_ext_v2,
+	POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR,
+	POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD
+);
 
-static umode_t cros_chtl_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n)
-{
-	struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(attr, n);
-
-	if (n == CROS_CHCTL_ATTR_START_THRESHOLD && priv->cmd_version < 3)
-		return 0;
-	else if (n == CROS_CHCTL_ATTR_END_THRESHOLD && priv->cmd_version < 2)
-		return 0;
-
-	return attr->mode;
-}
+DEFINE_CROS_CHCTL_POWER_SUPPLY_EXTENSION(cros_chctl_psy_ext_v3,
+	POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR,
+	POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD,
+	POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD
+);
 
 static int cros_chctl_add_battery(struct power_supply *battery, struct acpi_battery_hook *hook)
 {
@@ -254,7 +235,7 @@ static int cros_chctl_add_battery(struct power_supply *battery, struct acpi_batt
 		return 0;
 
 	priv->hooked_battery = battery;
-	return device_add_group(&battery->dev, &priv->group);
+	return power_supply_register_extension(battery, priv->psy_ext, priv->dev, priv);
 }
 
 static int cros_chctl_remove_battery(struct power_supply *battery, struct acpi_battery_hook *hook)
@@ -262,7 +243,7 @@ static int cros_chctl_remove_battery(struct power_supply *battery, struct acpi_b
 	struct cros_chctl_priv *priv = container_of(hook, struct cros_chctl_priv, battery_hook);
 
 	if (priv->hooked_battery == battery) {
-		device_remove_group(&battery->dev, &priv->group);
+		power_supply_unregister_extension(battery, priv->psy_ext);
 		priv->hooked_battery = NULL;
 	}
 
@@ -288,7 +269,6 @@ static int cros_chctl_probe(struct platform_device *pdev)
 	struct cros_ec_dev *ec_dev = dev_get_drvdata(dev->parent);
 	struct cros_ec_device *cros_ec = ec_dev->ec_dev;
 	struct cros_chctl_priv *priv;
-	size_t i;
 	int ret;
 
 	ret = cros_chctl_fwk_charge_control_versions(cros_ec);
@@ -321,19 +301,15 @@ static int cros_chctl_probe(struct platform_device *pdev)
 
 	dev_dbg(dev, "Command version: %u\n", (unsigned int)priv->cmd_version);
 
+	priv->dev = dev;
 	priv->cros_ec = cros_ec;
-	priv->device_attrs[CROS_CHCTL_ATTR_START_THRESHOLD] =
-		(struct device_attribute)__ATTR_RW(charge_control_start_threshold);
-	priv->device_attrs[CROS_CHCTL_ATTR_END_THRESHOLD] =
-		(struct device_attribute)__ATTR_RW(charge_control_end_threshold);
-	priv->device_attrs[CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR] =
-		(struct device_attribute)__ATTR_RW(charge_behaviour);
-	for (i = 0; i < _CROS_CHCTL_ATTR_COUNT; i++) {
-		sysfs_attr_init(&priv->device_attrs[i].attr);
-		priv->attributes[i] = &priv->device_attrs[i].attr;
-	}
-	priv->group.is_visible = cros_chtl_attr_is_visible;
-	priv->group.attrs = priv->attributes;
+
+	if (priv->cmd_version == 1)
+		priv->psy_ext = &cros_chctl_psy_ext_v1;
+	else if (priv->cmd_version == 2)
+		priv->psy_ext = &cros_chctl_psy_ext_v2;
+	else
+		priv->psy_ext = &cros_chctl_psy_ext_v3;
 
 	priv->battery_hook.name = dev_name(dev);
 	priv->battery_hook.add_battery = cros_chctl_add_battery;
diff --git a/drivers/power/supply/da9030_battery.c b/drivers/power/supply/da9030_battery.c
index 34328f5d556e..ac2e319e9517 100644
--- a/drivers/power/supply/da9030_battery.c
+++ b/drivers/power/supply/da9030_battery.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
+#include <linux/string_choices.h>
 #include <linux/mfd/da903x.h>
 
 #include <linux/debugfs.h>
@@ -138,7 +139,7 @@ static int bat_debug_show(struct seq_file *s, void *data)
 {
 	struct da9030_charger *charger = s->private;
 
-	seq_printf(s, "charger is %s\n", charger->is_on ? "on" : "off");
+	seq_printf(s, "charger is %s\n", str_on_off(charger->is_on));
 	if (charger->chdet) {
 		seq_printf(s, "iset = %dmA, vset = %dmV\n",
 			   charger->mA, charger->mV);
diff --git a/drivers/power/supply/ds2760_battery.c b/drivers/power/supply/ds2760_battery.c
index 7cf4ea06b500..83bdec5a2bda 100644
--- a/drivers/power/supply/ds2760_battery.c
+++ b/drivers/power/supply/ds2760_battery.c
@@ -195,22 +195,22 @@ static int w1_ds2760_recall_eeprom(struct device *dev, int addr)
 }
 
 static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj,
-			     struct bin_attribute *bin_attr, char *buf,
+			     const struct bin_attribute *bin_attr, char *buf,
 			     loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
 	return w1_ds2760_read(dev, buf, off, count);
 }
 
-static BIN_ATTR_RO(w1_slave, DS2760_DATA_SIZE);
+static const BIN_ATTR_RO(w1_slave, DS2760_DATA_SIZE);
 
-static struct bin_attribute *w1_ds2760_bin_attrs[] = {
+static const struct bin_attribute *const w1_ds2760_bin_attrs[] = {
 	&bin_attr_w1_slave,
 	NULL,
 };
 
 static const struct attribute_group w1_ds2760_group = {
-	.bin_attrs = w1_ds2760_bin_attrs,
+	.bin_attrs_new = w1_ds2760_bin_attrs,
 };
 
 static const struct attribute_group *w1_ds2760_groups[] = {
diff --git a/drivers/power/supply/ds2780_battery.c b/drivers/power/supply/ds2780_battery.c
index 1e7f297f6cb1..dd9ac7a32967 100644
--- a/drivers/power/supply/ds2780_battery.c
+++ b/drivers/power/supply/ds2780_battery.c
@@ -621,7 +621,7 @@ static ssize_t ds2780_set_pio_pin(struct device *dev,
 
 static ssize_t ds2780_read_param_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -634,7 +634,7 @@ static ssize_t ds2780_read_param_eeprom_bin(struct file *filp,
 
 static ssize_t ds2780_write_param_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -654,19 +654,19 @@ static ssize_t ds2780_write_param_eeprom_bin(struct file *filp,
 	return count;
 }
 
-static struct bin_attribute ds2780_param_eeprom_bin_attr = {
+static const struct bin_attribute ds2780_param_eeprom_bin_attr = {
 	.attr = {
 		.name = "param_eeprom",
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	.size = DS2780_PARAM_EEPROM_SIZE,
-	.read = ds2780_read_param_eeprom_bin,
-	.write = ds2780_write_param_eeprom_bin,
+	.read_new = ds2780_read_param_eeprom_bin,
+	.write_new = ds2780_write_param_eeprom_bin,
 };
 
 static ssize_t ds2780_read_user_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -679,7 +679,7 @@ static ssize_t ds2780_read_user_eeprom_bin(struct file *filp,
 
 static ssize_t ds2780_write_user_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -699,14 +699,14 @@ static ssize_t ds2780_write_user_eeprom_bin(struct file *filp,
 	return count;
 }
 
-static struct bin_attribute ds2780_user_eeprom_bin_attr = {
+static const struct bin_attribute ds2780_user_eeprom_bin_attr = {
 	.attr = {
 		.name = "user_eeprom",
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	.size = DS2780_USER_EEPROM_SIZE,
-	.read = ds2780_read_user_eeprom_bin,
-	.write = ds2780_write_user_eeprom_bin,
+	.read_new = ds2780_read_user_eeprom_bin,
+	.write_new = ds2780_write_user_eeprom_bin,
 };
 
 static DEVICE_ATTR(pmod_enabled, S_IRUGO | S_IWUSR, ds2780_get_pmod_enabled,
@@ -726,7 +726,7 @@ static struct attribute *ds2780_sysfs_attrs[] = {
 	NULL
 };
 
-static struct bin_attribute *ds2780_sysfs_bin_attrs[] = {
+static const struct bin_attribute *const ds2780_sysfs_bin_attrs[] = {
 	&ds2780_param_eeprom_bin_attr,
 	&ds2780_user_eeprom_bin_attr,
 	NULL
@@ -734,7 +734,7 @@ static struct bin_attribute *ds2780_sysfs_bin_attrs[] = {
 
 static const struct attribute_group ds2780_sysfs_group = {
 	.attrs = ds2780_sysfs_attrs,
-	.bin_attrs = ds2780_sysfs_bin_attrs,
+	.bin_attrs_new = ds2780_sysfs_bin_attrs,
 };
 
 static const struct attribute_group *ds2780_sysfs_groups[] = {
diff --git a/drivers/power/supply/ds2781_battery.c b/drivers/power/supply/ds2781_battery.c
index c4f8ccc687f9..8a1f1f9835e0 100644
--- a/drivers/power/supply/ds2781_battery.c
+++ b/drivers/power/supply/ds2781_battery.c
@@ -623,7 +623,7 @@ static ssize_t ds2781_set_pio_pin(struct device *dev,
 
 static ssize_t ds2781_read_param_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -636,7 +636,7 @@ static ssize_t ds2781_read_param_eeprom_bin(struct file *filp,
 
 static ssize_t ds2781_write_param_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -656,19 +656,19 @@ static ssize_t ds2781_write_param_eeprom_bin(struct file *filp,
 	return count;
 }
 
-static struct bin_attribute ds2781_param_eeprom_bin_attr = {
+static const struct bin_attribute ds2781_param_eeprom_bin_attr = {
 	.attr = {
 		.name = "param_eeprom",
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	.size = DS2781_PARAM_EEPROM_SIZE,
-	.read = ds2781_read_param_eeprom_bin,
-	.write = ds2781_write_param_eeprom_bin,
+	.read_new = ds2781_read_param_eeprom_bin,
+	.write_new = ds2781_write_param_eeprom_bin,
 };
 
 static ssize_t ds2781_read_user_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -682,7 +682,7 @@ static ssize_t ds2781_read_user_eeprom_bin(struct file *filp,
 
 static ssize_t ds2781_write_user_eeprom_bin(struct file *filp,
 				struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -702,14 +702,14 @@ static ssize_t ds2781_write_user_eeprom_bin(struct file *filp,
 	return count;
 }
 
-static struct bin_attribute ds2781_user_eeprom_bin_attr = {
+static const struct bin_attribute ds2781_user_eeprom_bin_attr = {
 	.attr = {
 		.name = "user_eeprom",
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	.size = DS2781_USER_EEPROM_SIZE,
-	.read = ds2781_read_user_eeprom_bin,
-	.write = ds2781_write_user_eeprom_bin,
+	.read_new = ds2781_read_user_eeprom_bin,
+	.write_new = ds2781_write_user_eeprom_bin,
 };
 
 static DEVICE_ATTR(pmod_enabled, S_IRUGO | S_IWUSR, ds2781_get_pmod_enabled,
@@ -729,7 +729,7 @@ static struct attribute *ds2781_sysfs_attrs[] = {
 	NULL
 };
 
-static struct bin_attribute *ds2781_sysfs_bin_attrs[] = {
+static const struct bin_attribute *const ds2781_sysfs_bin_attrs[] = {
 	&ds2781_param_eeprom_bin_attr,
 	&ds2781_user_eeprom_bin_attr,
 	NULL,
@@ -737,7 +737,7 @@ static struct bin_attribute *ds2781_sysfs_bin_attrs[] = {
 
 static const struct attribute_group ds2781_sysfs_group = {
 	.attrs = ds2781_sysfs_attrs,
-	.bin_attrs = ds2781_sysfs_bin_attrs,
+	.bin_attrs_new = ds2781_sysfs_bin_attrs,
 
 };
 
diff --git a/drivers/power/supply/ds2782_battery.c b/drivers/power/supply/ds2782_battery.c
index 85aa9c465aa4..cae95d35d398 100644
--- a/drivers/power/supply/ds2782_battery.c
+++ b/drivers/power/supply/ds2782_battery.c
@@ -11,6 +11,7 @@
  * UEvent sending added by Evgeny Romanov <romanov@neurosoft.ru>
  */
 
+#include <linux/devm-helpers.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -57,14 +58,12 @@ struct ds278x_info {
 	struct power_supply_desc	battery_desc;
 	const struct ds278x_battery_ops *ops;
 	struct delayed_work	bat_work;
-	int			id;
 	int                     rsns;
 	int			capacity;
 	int			status;		/* State Of Charge */
 };
 
-static DEFINE_IDR(battery_id);
-static DEFINE_MUTEX(battery_lock);
+static DEFINE_IDA(battery_id);
 
 static inline int ds278x_read_reg(struct ds278x_info *info, int reg, u8 *val)
 {
@@ -312,21 +311,6 @@ static void ds278x_power_supply_init(struct power_supply_desc *battery)
 	battery->external_power_changed	= NULL;
 }
 
-static void ds278x_battery_remove(struct i2c_client *client)
-{
-	struct ds278x_info *info = i2c_get_clientdata(client);
-	int id = info->id;
-
-	power_supply_unregister(info->battery);
-	cancel_delayed_work_sync(&info->bat_work);
-	kfree(info->battery_desc.name);
-	kfree(info);
-
-	mutex_lock(&battery_lock);
-	idr_remove(&battery_id, id);
-	mutex_unlock(&battery_lock);
-}
-
 #ifdef CONFIG_PM_SLEEP
 
 static int ds278x_suspend(struct device *dev)
@@ -368,6 +352,13 @@ static const struct ds278x_battery_ops ds278x_ops[] = {
 	}
 };
 
+static void ds278x_free_ida(void *data)
+{
+	int num = (uintptr_t)data;
+
+	ida_free(&battery_id, num);
+}
+
 static int ds278x_battery_probe(struct i2c_client *client)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
@@ -387,32 +378,27 @@ static int ds278x_battery_probe(struct i2c_client *client)
 	}
 
 	/* Get an ID for this battery */
-	mutex_lock(&battery_lock);
-	ret = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL);
-	mutex_unlock(&battery_lock);
-	if (ret < 0)
-		goto fail_id;
-	num = ret;
-
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info) {
-		ret = -ENOMEM;
-		goto fail_info;
-	}
+	num = ida_alloc(&battery_id, GFP_KERNEL);
+	if (num < 0)
+		return num;
+	ret = devm_add_action_or_reset(&client->dev, ds278x_free_ida, (void *)(uintptr_t)num);
+	if (ret)
+		return ret;
 
-	info->battery_desc.name = kasprintf(GFP_KERNEL, "%s-%d",
-					    client->name, num);
-	if (!info->battery_desc.name) {
-		ret = -ENOMEM;
-		goto fail_name;
-	}
+	info = devm_kzalloc(&client->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->battery_desc.name = devm_kasprintf(&client->dev, GFP_KERNEL,
+						 "%s-%d", client->name, num);
+	if (!info->battery_desc.name)
+		return -ENOMEM;
 
 	if (id->driver_data == DS2786)
 		info->rsns = pdata->rsns;
 
 	i2c_set_clientdata(client, info);
 	info->client = client;
-	info->id = num;
 	info->ops  = &ds278x_ops[id->driver_data];
 	ds278x_power_supply_init(&info->battery_desc);
 	psy_cfg.drv_data = info;
@@ -420,30 +406,20 @@ static int ds278x_battery_probe(struct i2c_client *client)
 	info->capacity = 100;
 	info->status = POWER_SUPPLY_STATUS_FULL;
 
-	INIT_DELAYED_WORK(&info->bat_work, ds278x_bat_work);
-
-	info->battery = power_supply_register(&client->dev,
-					      &info->battery_desc, &psy_cfg);
+	info->battery = devm_power_supply_register(&client->dev,
+						   &info->battery_desc,
+						   &psy_cfg);
 	if (IS_ERR(info->battery)) {
 		dev_err(&client->dev, "failed to register battery\n");
-		ret = PTR_ERR(info->battery);
-		goto fail_register;
-	} else {
-		schedule_delayed_work(&info->bat_work, DS278x_DELAY);
+		return PTR_ERR(info->battery);
 	}
 
-	return 0;
+	ret = devm_delayed_work_autocancel(&client->dev, &info->bat_work, ds278x_bat_work);
+	if (ret)
+		return ret;
+	schedule_delayed_work(&info->bat_work, DS278x_DELAY);
 
-fail_register:
-	kfree(info->battery_desc.name);
-fail_name:
-	kfree(info);
-fail_info:
-	mutex_lock(&battery_lock);
-	idr_remove(&battery_id, num);
-	mutex_unlock(&battery_lock);
-fail_id:
-	return ret;
+	return 0;
 }
 
 static const struct i2c_device_id ds278x_id[] = {
@@ -459,7 +435,6 @@ static struct i2c_driver ds278x_battery_driver = {
 		.pm	= &ds278x_battery_pm_ops,
 	},
 	.probe		= ds278x_battery_probe,
-	.remove		= ds278x_battery_remove,
 	.id_table	= ds278x_id,
 };
 module_i2c_driver(ds278x_battery_driver);
diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c
index 6139f736ecbe..46d18ce6a739 100644
--- a/drivers/power/supply/gpio-charger.c
+++ b/drivers/power/supply/gpio-charger.c
@@ -195,6 +195,8 @@ static int init_charge_current_limit(struct device *dev,
 {
 	int i, len;
 	u32 cur_limit = U32_MAX;
+	bool set_def_limit;
+	u32 def_limit;
 
 	gpio_charger->current_limit_gpios = devm_gpiod_get_array_optional(dev,
 		"charge-current-limit", GPIOD_OUT_LOW);
@@ -228,6 +230,9 @@ static int init_charge_current_limit(struct device *dev,
 	if (len < 0)
 		return len;
 
+	set_def_limit = !device_property_read_u32(dev,
+						  "charge-current-limit-default-microamp",
+						  &def_limit);
 	for (i=0; i < gpio_charger->current_limit_map_size; i++) {
 		if (gpio_charger->current_limit_map[i].limit_ua > cur_limit) {
 			dev_err(dev, "charge-current-limit-mapping not sorted by current in descending order\n");
@@ -235,8 +240,16 @@ static int init_charge_current_limit(struct device *dev,
 		}
 
 		cur_limit = gpio_charger->current_limit_map[i].limit_ua;
+		if (set_def_limit && def_limit == cur_limit) {
+			set_charge_current_limit(gpio_charger, cur_limit);
+			return 0;
+		}
 	}
 
+	if (set_def_limit)
+		dev_warn(dev, "charge-current-limit-default-microamp %u not listed in charge-current-limit-mapping\n",
+			 def_limit);
+
 	/* default to smallest current limitation for safety reasons */
 	len = gpio_charger->current_limit_map_size - 1;
 	set_charge_current_limit(gpio_charger,
diff --git a/drivers/power/supply/ip5xxx_power.c b/drivers/power/supply/ip5xxx_power.c
index 82263646ddc6..c448e0ac0dfa 100644
--- a/drivers/power/supply/ip5xxx_power.c
+++ b/drivers/power/supply/ip5xxx_power.c
@@ -7,76 +7,154 @@
 #include <linux/power_supply.h>
 #include <linux/regmap.h>
 
-#define IP5XXX_SYS_CTL0			0x01
-#define IP5XXX_SYS_CTL0_WLED_DET_EN		BIT(4)
-#define IP5XXX_SYS_CTL0_WLED_EN			BIT(3)
-#define IP5XXX_SYS_CTL0_BOOST_EN		BIT(2)
-#define IP5XXX_SYS_CTL0_CHARGER_EN		BIT(1)
-#define IP5XXX_SYS_CTL1			0x02
-#define IP5XXX_SYS_CTL1_LIGHT_SHDN_EN		BIT(1)
-#define IP5XXX_SYS_CTL1_LOAD_PWRUP_EN		BIT(0)
-#define IP5XXX_SYS_CTL2			0x0c
-#define IP5XXX_SYS_CTL2_LIGHT_SHDN_TH		GENMASK(7, 3)
-#define IP5XXX_SYS_CTL3			0x03
-#define IP5XXX_SYS_CTL3_LONG_PRESS_TIME_SEL	GENMASK(7, 6)
-#define IP5XXX_SYS_CTL3_BTN_SHDN_EN		BIT(5)
-#define IP5XXX_SYS_CTL4			0x04
-#define IP5XXX_SYS_CTL4_SHDN_TIME_SEL		GENMASK(7, 6)
-#define IP5XXX_SYS_CTL4_VIN_PULLOUT_BOOST_EN	BIT(5)
-#define IP5XXX_SYS_CTL5			0x07
-#define IP5XXX_SYS_CTL5_NTC_DIS			BIT(6)
-#define IP5XXX_SYS_CTL5_WLED_MODE_SEL		BIT(1)
-#define IP5XXX_SYS_CTL5_BTN_SHDN_SEL		BIT(0)
-#define IP5XXX_CHG_CTL1			0x22
-#define IP5XXX_CHG_CTL1_BOOST_UVP_SEL		GENMASK(3, 2)
-#define IP5XXX_CHG_CTL2			0x24
-#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL		GENMASK(6, 5)
-#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_2V	(0x0 << 5)
-#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_3V	(0x1 << 5)
-#define IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_35V	(0x2 << 5)
-#define IP5XXX_CHG_CTL2_CONST_VOLT_SEL		GENMASK(2, 1)
-#define IP5XXX_CHG_CTL4			0x26
-#define IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN		BIT(6)
-#define IP5XXX_CHG_CTL4A		0x25
-#define IP5XXX_CHG_CTL4A_CONST_CUR_SEL		GENMASK(4, 0)
-#define IP5XXX_MFP_CTL0			0x51
-#define IP5XXX_MFP_CTL1			0x52
-#define IP5XXX_GPIO_CTL2		0x53
-#define IP5XXX_GPIO_CTL2A		0x54
-#define IP5XXX_GPIO_CTL3		0x55
-#define IP5XXX_READ0			0x71
-#define IP5XXX_READ0_CHG_STAT			GENMASK(7, 5)
-#define IP5XXX_READ0_CHG_STAT_IDLE		(0x0 << 5)
-#define IP5XXX_READ0_CHG_STAT_TRICKLE		(0x1 << 5)
-#define IP5XXX_READ0_CHG_STAT_CONST_VOLT	(0x2 << 5)
-#define IP5XXX_READ0_CHG_STAT_CONST_CUR		(0x3 << 5)
-#define IP5XXX_READ0_CHG_STAT_CONST_VOLT_STOP	(0x4 << 5)
-#define IP5XXX_READ0_CHG_STAT_FULL		(0x5 << 5)
-#define IP5XXX_READ0_CHG_STAT_TIMEOUT		(0x6 << 5)
-#define IP5XXX_READ0_CHG_OP			BIT(4)
-#define IP5XXX_READ0_CHG_END			BIT(3)
-#define IP5XXX_READ0_CONST_VOLT_TIMEOUT		BIT(2)
-#define IP5XXX_READ0_CHG_TIMEOUT		BIT(1)
-#define IP5XXX_READ0_TRICKLE_TIMEOUT		BIT(0)
-#define IP5XXX_READ0_TIMEOUT			GENMASK(2, 0)
-#define IP5XXX_READ1			0x72
-#define IP5XXX_READ1_WLED_PRESENT		BIT(7)
-#define IP5XXX_READ1_LIGHT_LOAD			BIT(6)
-#define IP5XXX_READ1_VIN_OVERVOLT		BIT(5)
-#define IP5XXX_READ2			0x77
-#define IP5XXX_READ2_BTN_PRESS			BIT(3)
-#define IP5XXX_READ2_BTN_LONG_PRESS		BIT(1)
-#define IP5XXX_READ2_BTN_SHORT_PRESS		BIT(0)
-#define IP5XXX_BATVADC_DAT0		0xa2
-#define IP5XXX_BATVADC_DAT1		0xa3
-#define IP5XXX_BATIADC_DAT0		0xa4
-#define IP5XXX_BATIADC_DAT1		0xa5
-#define IP5XXX_BATOCV_DAT0		0xa8
-#define IP5XXX_BATOCV_DAT1		0xa9
+#define IP5XXX_BAT_TYPE_4_2V			0x0
+#define IP5XXX_BAT_TYPE_4_3V			0x1
+#define IP5XXX_BAT_TYPE_4_35V			0x2
+#define IP5XXX_BAT_TYPE_4_4V			0x3
+#define IP5XXX_CHG_STAT_IDLE			0x0
+#define IP5XXX_CHG_STAT_TRICKLE		0x1
+#define IP5XXX_CHG_STAT_CONST_VOLT		0x2
+#define IP5XXX_CHG_STAT_CONST_CUR		0x3
+#define IP5XXX_CHG_STAT_CONST_VOLT_STOP	0x4
+#define IP5XXX_CHG_STAT_FULL			0x5
+#define IP5XXX_CHG_STAT_TIMEOUT		0x6
 
 struct ip5xxx {
 	struct regmap *regmap;
 	bool initialized;
+	struct {
+		struct {
+			/* Charger enable */
+			struct regmap_field *enable;
+			/* Constant voltage value */
+			struct regmap_field *const_volt_sel;
+			/* Constant current value */
+			struct regmap_field *const_curr_sel;
+			/* Charger status */
+			struct regmap_field *status;
+			/* Charging ended flag */
+			struct regmap_field *chg_end;
+			/* Timeout flags (CV, charge, trickle) */
+			struct regmap_field *timeout;
+			/* Overvoltage limit */
+			struct regmap_field *vin_overvolt;
+		} charger;
+		struct {
+			/* Boost converter enable */
+			struct regmap_field *enable;
+			struct {
+				/* Light load shutdown enable */
+				struct regmap_field *enable;
+				/* Light load shutdown current limit */
+				struct regmap_field *i_limit;
+			} light_load_shutdown;
+			/* Automatic powerup on increased load */
+			struct regmap_field *load_powerup_en;
+			/* Automatic powerup on VIN pull-out */
+			struct regmap_field *vin_pullout_en;
+			/* Undervoltage limit */
+			struct regmap_field *undervolt_limit;
+			/* Light load status flag */
+			struct regmap_field *light_load_status;
+		} boost;
+		struct {
+			/* NTC disable */
+			struct regmap_field *ntc_dis;
+			/* Battery voltage type */
+			struct regmap_field *type;
+			/* Battery voltage autoset from Vset pin */
+			struct regmap_field *vset_en;
+			struct {
+				/* Battery measurement registers */
+				struct ip5xxx_battery_adc_regs {
+					struct regmap_field *low;
+					struct regmap_field *high;
+				} volt, curr, open_volt;
+			} adc;
+		} battery;
+		struct {
+			/* Double/long press shutdown enable */
+			struct regmap_field *shdn_enable;
+			/* WLED activation: double press or long press */
+			struct regmap_field *wled_mode;
+			/* Shutdown activation: double press or long press */
+			struct regmap_field *shdn_mode;
+			/* Long press time */
+			struct regmap_field *long_press_time;
+			/* Button pressed */
+			struct regmap_field *pressed;
+			/* Button long-pressed */
+			struct regmap_field *long_pressed;
+			/* Button short-pressed */
+			struct regmap_field *short_pressed;
+		} btn;
+		struct {
+			/* WLED enable */
+			struct regmap_field *enable;
+			/* WLED detect */
+			struct regmap_field *detect_en;
+			/* WLED present */
+			struct regmap_field *present;
+		} wled;
+	} regs;
+
+	/* Maximum supported battery voltage (via regs.battery.type) */
+	int vbat_max;
+	/* Scaling constants for regs.boost.undervolt_limit */
+	struct {
+		int setpoint;
+		int microvolts_per_bit;
+	} boost_undervolt;
+	/* Scaling constants for regs.charger.const_curr_sel */
+	struct {
+		int setpoint;
+	} const_curr;
+	/* Whether regs.charger.chg_end is inverted */
+	u8 chg_end_inverted;
+};
+
+#define REG_FIELD_UNSUPPORTED { .lsb = 1 }
+/* Register fields layout. Unsupported registers marked as { .lsb = 1 } */
+struct ip5xxx_regfield_config {
+	const struct reg_field charger_enable;
+	const struct reg_field charger_const_volt_sel;
+	const struct reg_field charger_const_curr_sel;
+	const struct reg_field charger_status;
+	const struct reg_field charger_chg_end;
+	const struct reg_field charger_timeout;
+	const struct reg_field charger_vin_overvolt;
+	const struct reg_field boost_enable;
+	const struct reg_field boost_llshdn_enable;
+	const struct reg_field boost_llshdn_i_limit;
+	const struct reg_field boost_load_powerup_en;
+	const struct reg_field boost_vin_pullout_en;
+	const struct reg_field boost_undervolt_limit;
+	const struct reg_field boost_light_load_status;
+	const struct reg_field battery_ntc_dis;
+	const struct reg_field battery_type;
+	const struct reg_field battery_vset_en;
+	const struct reg_field battery_adc_volt_low;
+	const struct reg_field battery_adc_volt_high;
+	const struct reg_field battery_adc_curr_low;
+	const struct reg_field battery_adc_curr_high;
+	const struct reg_field battery_adc_ovolt_low;
+	const struct reg_field battery_adc_ovolt_high;
+	const struct reg_field btn_shdn_enable;
+	const struct reg_field btn_wled_mode;
+	const struct reg_field btn_shdn_mode;
+	const struct reg_field btn_long_press_time;
+	const struct reg_field btn_pressed;
+	const struct reg_field btn_long_pressed;
+	const struct reg_field btn_short_pressed;
+	const struct reg_field wled_enable;
+	const struct reg_field wled_detect_en;
+	const struct reg_field wled_present;
+
+	int vbat_max;
+	int boost_undervolt_setpoint;
+	int boost_undervolt_uv_per_bit;
+	int const_curr_setpoint;
+	u8  chg_end_inverted;
 };
 
 /*
@@ -87,24 +165,30 @@ struct ip5xxx {
  *  2) Attempt the initialization sequence on each subsequent register access
  *     until it succeeds.
  */
-static int ip5xxx_read(struct ip5xxx *ip5xxx, unsigned int reg,
+static int ip5xxx_read(struct ip5xxx *ip5xxx, struct regmap_field *field,
 		       unsigned int *val)
 {
 	int ret;
 
-	ret = regmap_read(ip5xxx->regmap, reg, val);
+	if (!field)
+		return -EOPNOTSUPP;
+
+	ret = regmap_field_read(field, val);
 	if (ret)
 		ip5xxx->initialized = false;
 
 	return ret;
 }
 
-static int ip5xxx_update_bits(struct ip5xxx *ip5xxx, unsigned int reg,
-			      unsigned int mask, unsigned int val)
+static int ip5xxx_write(struct ip5xxx *ip5xxx, struct regmap_field *field,
+			unsigned int val)
 {
 	int ret;
 
-	ret = regmap_update_bits(ip5xxx->regmap, reg, mask, val);
+	if (!field)
+		return -EOPNOTSUPP;
+
+	ret = regmap_field_write(field, val);
 	if (ret)
 		ip5xxx->initialized = false;
 
@@ -123,28 +207,26 @@ static int ip5xxx_initialize(struct power_supply *psy)
 	 * Disable shutdown under light load.
 	 * Enable power on when under load.
 	 */
-	ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL1,
-				 IP5XXX_SYS_CTL1_LIGHT_SHDN_EN |
-				 IP5XXX_SYS_CTL1_LOAD_PWRUP_EN,
-				 IP5XXX_SYS_CTL1_LOAD_PWRUP_EN);
+	if (ip5xxx->regs.boost.light_load_shutdown.enable) {
+		ret = ip5xxx_write(ip5xxx, ip5xxx->regs.boost.light_load_shutdown.enable, 0);
+		if (ret)
+			return ret;
+	}
+	ret = ip5xxx_write(ip5xxx, ip5xxx->regs.boost.load_powerup_en, 1);
 	if (ret)
 		return ret;
 
 	/*
 	 * Enable shutdown after a long button press (as configured below).
 	 */
-	ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL3,
-				 IP5XXX_SYS_CTL3_BTN_SHDN_EN,
-				 IP5XXX_SYS_CTL3_BTN_SHDN_EN);
+	ret = ip5xxx_write(ip5xxx, ip5xxx->regs.btn.shdn_enable, 1);
 	if (ret)
 		return ret;
 
 	/*
 	 * Power on automatically when VIN is removed.
 	 */
-	ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL4,
-				 IP5XXX_SYS_CTL4_VIN_PULLOUT_BOOST_EN,
-				 IP5XXX_SYS_CTL4_VIN_PULLOUT_BOOST_EN);
+	ret = ip5xxx_write(ip5xxx, ip5xxx->regs.boost.vin_pullout_en, 1);
 	if (ret)
 		return ret;
 
@@ -152,12 +234,15 @@ static int ip5xxx_initialize(struct power_supply *psy)
 	 * Enable the NTC.
 	 * Configure the button for two presses => LED, long press => shutdown.
 	 */
-	ret = ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL5,
-				 IP5XXX_SYS_CTL5_NTC_DIS |
-				 IP5XXX_SYS_CTL5_WLED_MODE_SEL |
-				 IP5XXX_SYS_CTL5_BTN_SHDN_SEL,
-				 IP5XXX_SYS_CTL5_WLED_MODE_SEL |
-				 IP5XXX_SYS_CTL5_BTN_SHDN_SEL);
+	if (ip5xxx->regs.battery.ntc_dis) {
+		ret = ip5xxx_write(ip5xxx, ip5xxx->regs.battery.ntc_dis, 0);
+		if (ret)
+			return ret;
+	}
+	ret = ip5xxx_write(ip5xxx, ip5xxx->regs.btn.wled_mode, 1);
+	if (ret)
+		return ret;
+	ret = ip5xxx_write(ip5xxx, ip5xxx->regs.btn.shdn_mode, 1);
 	if (ret)
 		return ret;
 
@@ -186,24 +271,37 @@ static int ip5xxx_battery_get_status(struct ip5xxx *ip5xxx, int *val)
 	unsigned int rval;
 	int ret;
 
-	ret = ip5xxx_read(ip5xxx, IP5XXX_READ0, &rval);
+	if (!ip5xxx->regs.charger.status) {
+		// Fall-back to Charging Ended bit
+		ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.chg_end, &rval);
+		if (ret)
+			return ret;
+
+		if (rval == ip5xxx->chg_end_inverted)
+			*val = POWER_SUPPLY_STATUS_CHARGING;
+		else
+			*val = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		return 0;
+	}
+
+	ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.status, &rval);
 	if (ret)
 		return ret;
 
-	switch (rval & IP5XXX_READ0_CHG_STAT) {
-	case IP5XXX_READ0_CHG_STAT_IDLE:
+	switch (rval) {
+	case IP5XXX_CHG_STAT_IDLE:
 		*val = POWER_SUPPLY_STATUS_DISCHARGING;
 		break;
-	case IP5XXX_READ0_CHG_STAT_TRICKLE:
-	case IP5XXX_READ0_CHG_STAT_CONST_CUR:
-	case IP5XXX_READ0_CHG_STAT_CONST_VOLT:
+	case IP5XXX_CHG_STAT_TRICKLE:
+	case IP5XXX_CHG_STAT_CONST_CUR:
+	case IP5XXX_CHG_STAT_CONST_VOLT:
 		*val = POWER_SUPPLY_STATUS_CHARGING;
 		break;
-	case IP5XXX_READ0_CHG_STAT_CONST_VOLT_STOP:
-	case IP5XXX_READ0_CHG_STAT_FULL:
+	case IP5XXX_CHG_STAT_CONST_VOLT_STOP:
+	case IP5XXX_CHG_STAT_FULL:
 		*val = POWER_SUPPLY_STATUS_FULL;
 		break;
-	case IP5XXX_READ0_CHG_STAT_TIMEOUT:
+	case IP5XXX_CHG_STAT_TIMEOUT:
 		*val = POWER_SUPPLY_STATUS_NOT_CHARGING;
 		break;
 	default:
@@ -218,22 +316,22 @@ static int ip5xxx_battery_get_charge_type(struct ip5xxx *ip5xxx, int *val)
 	unsigned int rval;
 	int ret;
 
-	ret = ip5xxx_read(ip5xxx, IP5XXX_READ0, &rval);
+	ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.status, &rval);
 	if (ret)
 		return ret;
 
-	switch (rval & IP5XXX_READ0_CHG_STAT) {
-	case IP5XXX_READ0_CHG_STAT_IDLE:
-	case IP5XXX_READ0_CHG_STAT_CONST_VOLT_STOP:
-	case IP5XXX_READ0_CHG_STAT_FULL:
-	case IP5XXX_READ0_CHG_STAT_TIMEOUT:
+	switch (rval) {
+	case IP5XXX_CHG_STAT_IDLE:
+	case IP5XXX_CHG_STAT_CONST_VOLT_STOP:
+	case IP5XXX_CHG_STAT_FULL:
+	case IP5XXX_CHG_STAT_TIMEOUT:
 		*val = POWER_SUPPLY_CHARGE_TYPE_NONE;
 		break;
-	case IP5XXX_READ0_CHG_STAT_TRICKLE:
+	case IP5XXX_CHG_STAT_TRICKLE:
 		*val = POWER_SUPPLY_CHARGE_TYPE_TRICKLE;
 		break;
-	case IP5XXX_READ0_CHG_STAT_CONST_CUR:
-	case IP5XXX_READ0_CHG_STAT_CONST_VOLT:
+	case IP5XXX_CHG_STAT_CONST_CUR:
+	case IP5XXX_CHG_STAT_CONST_VOLT:
 		*val = POWER_SUPPLY_CHARGE_TYPE_STANDARD;
 		break;
 	default:
@@ -248,11 +346,11 @@ static int ip5xxx_battery_get_health(struct ip5xxx *ip5xxx, int *val)
 	unsigned int rval;
 	int ret;
 
-	ret = ip5xxx_read(ip5xxx, IP5XXX_READ0, &rval);
+	ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.timeout, &rval);
 	if (ret)
 		return ret;
 
-	if (rval & IP5XXX_READ0_TIMEOUT)
+	if (rval)
 		*val = POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE;
 	else
 		*val = POWER_SUPPLY_HEALTH_GOOD;
@@ -265,7 +363,7 @@ static int ip5xxx_battery_get_voltage_max(struct ip5xxx *ip5xxx, int *val)
 	unsigned int rval;
 	int ret;
 
-	ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL2, &rval);
+	ret = ip5xxx_read(ip5xxx, ip5xxx->regs.battery.type, &rval);
 	if (ret)
 		return ret;
 
@@ -273,16 +371,19 @@ static int ip5xxx_battery_get_voltage_max(struct ip5xxx *ip5xxx, int *val)
 	 * It is not clear what this will return if
 	 * IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN is not set...
 	 */
-	switch (rval & IP5XXX_CHG_CTL2_BAT_TYPE_SEL) {
-	case IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_2V:
+	switch (rval) {
+	case IP5XXX_BAT_TYPE_4_2V:
 		*val = 4200000;
 		break;
-	case IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_3V:
+	case IP5XXX_BAT_TYPE_4_3V:
 		*val = 4300000;
 		break;
-	case IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_35V:
+	case IP5XXX_BAT_TYPE_4_35V:
 		*val = 4350000;
 		break;
+	case IP5XXX_BAT_TYPE_4_4V:
+		*val = 4400000;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -291,16 +392,16 @@ static int ip5xxx_battery_get_voltage_max(struct ip5xxx *ip5xxx, int *val)
 }
 
 static int ip5xxx_battery_read_adc(struct ip5xxx *ip5xxx,
-				   u8 lo_reg, u8 hi_reg, int *val)
+				   struct ip5xxx_battery_adc_regs *regs, int *val)
 {
 	unsigned int hi, lo;
 	int ret;
 
-	ret = ip5xxx_read(ip5xxx, lo_reg, &lo);
+	ret = ip5xxx_read(ip5xxx, regs->low, &lo);
 	if (ret)
 		return ret;
 
-	ret = ip5xxx_read(ip5xxx, hi_reg, &hi);
+	ret = ip5xxx_read(ip5xxx, regs->high, &hi);
 	if (ret)
 		return ret;
 
@@ -335,33 +436,35 @@ static int ip5xxx_battery_get_property(struct power_supply *psy,
 		return ip5xxx_battery_get_voltage_max(ip5xxx, &val->intval);
 
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
-		ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATVADC_DAT0,
-					      IP5XXX_BATVADC_DAT1, &raw);
+		ret = ip5xxx_battery_read_adc(ip5xxx, &ip5xxx->regs.battery.adc.volt, &raw);
+		if (ret)
+			return ret;
 
 		val->intval = 2600000 + DIV_ROUND_CLOSEST(raw * 26855, 100);
 		return 0;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_OCV:
-		ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATOCV_DAT0,
-					      IP5XXX_BATOCV_DAT1, &raw);
+		ret = ip5xxx_battery_read_adc(ip5xxx, &ip5xxx->regs.battery.adc.open_volt, &raw);
+		if (ret)
+			return ret;
 
 		val->intval = 2600000 + DIV_ROUND_CLOSEST(raw * 26855, 100);
 		return 0;
 
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
-		ret = ip5xxx_battery_read_adc(ip5xxx, IP5XXX_BATIADC_DAT0,
-					      IP5XXX_BATIADC_DAT1, &raw);
+		ret = ip5xxx_battery_read_adc(ip5xxx, &ip5xxx->regs.battery.adc.curr, &raw);
+		if (ret)
+			return ret;
 
 		val->intval = DIV_ROUND_CLOSEST(raw * 149197, 200);
 		return 0;
 
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT:
-		ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL4A, &rval);
+		ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.const_curr_sel, &rval);
 		if (ret)
 			return ret;
 
-		rval &= IP5XXX_CHG_CTL4A_CONST_CUR_SEL;
-		val->intval = 100000 * rval;
+		val->intval = ip5xxx->const_curr.setpoint + 100000 * rval;
 		return 0;
 
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX:
@@ -373,12 +476,11 @@ static int ip5xxx_battery_get_property(struct power_supply *psy,
 		if (ret)
 			return ret;
 
-		ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL2, &rval);
+		ret = ip5xxx_read(ip5xxx, ip5xxx->regs.charger.const_volt_sel, &rval);
 		if (ret)
 			return ret;
 
-		rval &= IP5XXX_CHG_CTL2_CONST_VOLT_SEL;
-		val->intval = vmax + 14000 * (rval >> 1);
+		val->intval = vmax + 14000 * rval;
 		return 0;
 
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
@@ -399,30 +501,36 @@ static int ip5xxx_battery_set_voltage_max(struct ip5xxx *ip5xxx, int val)
 	unsigned int rval;
 	int ret;
 
+	if (val > ip5xxx->vbat_max)
+		return -EINVAL;
+
 	switch (val) {
 	case 4200000:
-		rval = IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_2V;
+		rval = IP5XXX_BAT_TYPE_4_2V;
 		break;
 	case 4300000:
-		rval = IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_3V;
+		rval = IP5XXX_BAT_TYPE_4_3V;
 		break;
 	case 4350000:
-		rval = IP5XXX_CHG_CTL2_BAT_TYPE_SEL_4_35V;
+		rval = IP5XXX_BAT_TYPE_4_35V;
+		break;
+	case 4400000:
+		rval = IP5XXX_BAT_TYPE_4_4V;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	ret = ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL2,
-				 IP5XXX_CHG_CTL2_BAT_TYPE_SEL, rval);
+	ret = ip5xxx_write(ip5xxx, ip5xxx->regs.battery.type, rval);
 	if (ret)
 		return ret;
 
-	ret = ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL4,
-				 IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN,
-				 IP5XXX_CHG_CTL4_BAT_TYPE_SEL_EN);
-	if (ret)
-		return ret;
+	/* Don't try to auto-detect battery type, even if the IC could */
+	if (ip5xxx->regs.battery.vset_en) {
+		ret = ip5xxx_write(ip5xxx, ip5xxx->regs.battery.vset_en, 1);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
@@ -443,7 +551,7 @@ static int ip5xxx_battery_set_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_STATUS:
 		switch (val->intval) {
 		case POWER_SUPPLY_STATUS_CHARGING:
-			rval = IP5XXX_SYS_CTL0_CHARGER_EN;
+			rval = 1;
 			break;
 		case POWER_SUPPLY_STATUS_DISCHARGING:
 		case POWER_SUPPLY_STATUS_NOT_CHARGING:
@@ -452,25 +560,22 @@ static int ip5xxx_battery_set_property(struct power_supply *psy,
 		default:
 			return -EINVAL;
 		}
-		return ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL0,
-					  IP5XXX_SYS_CTL0_CHARGER_EN, rval);
+		return ip5xxx_write(ip5xxx, ip5xxx->regs.charger.enable, rval);
 
 	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
 		return ip5xxx_battery_set_voltage_max(ip5xxx, val->intval);
 
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT:
-		rval = val->intval / 100000;
-		return ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL4A,
-					  IP5XXX_CHG_CTL4A_CONST_CUR_SEL, rval);
+		rval = (val->intval - ip5xxx->const_curr.setpoint) / 100000;
+		return ip5xxx_write(ip5xxx, ip5xxx->regs.charger.const_curr_sel, rval);
 
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE:
 		ret = ip5xxx_battery_get_voltage_max(ip5xxx, &vmax);
 		if (ret)
 			return ret;
 
-		rval = ((val->intval - vmax) / 14000) << 1;
-		return ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL2,
-					  IP5XXX_CHG_CTL2_CONST_VOLT_SEL, rval);
+		rval = (val->intval - vmax) / 14000;
+		return ip5xxx_write(ip5xxx, ip5xxx->regs.charger.const_volt_sel, rval);
 
 	default:
 		return -EINVAL;
@@ -515,20 +620,20 @@ static int ip5xxx_boost_get_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
-		ret = ip5xxx_read(ip5xxx, IP5XXX_SYS_CTL0, &rval);
+		ret = ip5xxx_read(ip5xxx, ip5xxx->regs.boost.enable, &rval);
 		if (ret)
 			return ret;
 
-		val->intval = !!(rval & IP5XXX_SYS_CTL0_BOOST_EN);
+		val->intval = !!rval;
 		return 0;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-		ret = ip5xxx_read(ip5xxx, IP5XXX_CHG_CTL1, &rval);
+		ret = ip5xxx_read(ip5xxx, ip5xxx->regs.boost.undervolt_limit, &rval);
 		if (ret)
 			return ret;
 
-		rval &= IP5XXX_CHG_CTL1_BOOST_UVP_SEL;
-		val->intval = 4530000 + 100000 * (rval >> 2);
+		val->intval = ip5xxx->boost_undervolt.setpoint +
+			      ip5xxx->boost_undervolt.microvolts_per_bit * rval;
 		return 0;
 
 	default:
@@ -550,14 +655,12 @@ static int ip5xxx_boost_set_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
-		rval = val->intval ? IP5XXX_SYS_CTL0_BOOST_EN : 0;
-		return ip5xxx_update_bits(ip5xxx, IP5XXX_SYS_CTL0,
-					  IP5XXX_SYS_CTL0_BOOST_EN, rval);
+		return ip5xxx_write(ip5xxx, ip5xxx->regs.boost.enable, !!val->intval);
 
 	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-		rval = ((val->intval - 4530000) / 100000) << 2;
-		return ip5xxx_update_bits(ip5xxx, IP5XXX_CHG_CTL1,
-					  IP5XXX_CHG_CTL1_BOOST_UVP_SEL, rval);
+		rval = (val->intval - ip5xxx->boost_undervolt.setpoint) /
+			ip5xxx->boost_undervolt.microvolts_per_bit;
+		return ip5xxx_write(ip5xxx, ip5xxx->regs.boost.undervolt_limit, rval);
 
 	default:
 		return -EINVAL;
@@ -583,13 +686,152 @@ static const struct power_supply_desc ip5xxx_boost_desc = {
 static const struct regmap_config ip5xxx_regmap_config = {
 	.reg_bits		= 8,
 	.val_bits		= 8,
-	.max_register		= IP5XXX_BATOCV_DAT1,
+	.max_register		= 0xa9,
+};
+
+static struct ip5xxx_regfield_config ip51xx_fields = {
+	.charger_enable = REG_FIELD(0x01, 1, 1),
+	.charger_const_volt_sel = REG_FIELD(0x24, 1, 2),
+	.charger_const_curr_sel = REG_FIELD(0x25, 0, 4),
+	.charger_status = REG_FIELD(0x71, 5, 7),
+	.charger_chg_end = REG_FIELD(0x71, 3, 3),
+	.charger_timeout = REG_FIELD(0x71, 0, 2),
+	.charger_vin_overvolt = REG_FIELD(0x72, 5, 5),
+	.boost_enable = REG_FIELD(0x01, 2, 2),
+	.boost_llshdn_enable = REG_FIELD(0x02, 1, 1),
+	.boost_llshdn_i_limit = REG_FIELD(0x0c, 3, 7),
+	.boost_load_powerup_en = REG_FIELD(0x02, 0, 0),
+	.boost_vin_pullout_en = REG_FIELD(0x04, 5, 5),
+	.boost_undervolt_limit = REG_FIELD(0x22, 2, 3),
+	.boost_light_load_status = REG_FIELD(0x72, 6, 6),
+	.battery_ntc_dis = REG_FIELD(0x07, 6, 6),
+	.battery_type = REG_FIELD(0x24, 5, 6),
+	.battery_vset_en = REG_FIELD(0x26, 6, 6),
+	.battery_adc_volt_low = REG_FIELD(0xa2, 0, 7),
+	.battery_adc_volt_high = REG_FIELD(0xa3, 0, 5),
+	.battery_adc_curr_low = REG_FIELD(0xa4, 0, 7),
+	.battery_adc_curr_high = REG_FIELD(0xa5, 0, 5),
+	.battery_adc_ovolt_low = REG_FIELD(0xa8, 0, 7),
+	.battery_adc_ovolt_high = REG_FIELD(0xa9, 0, 5),
+	.btn_shdn_enable = REG_FIELD(0x03, 5, 5),
+	.btn_wled_mode = REG_FIELD(0x07, 1, 1),
+	.btn_shdn_mode = REG_FIELD(0x07, 0, 0),
+	.btn_long_press_time = REG_FIELD(0x03, 6, 7),
+	.btn_pressed = REG_FIELD(0x77, 3, 3),
+	.btn_long_pressed = REG_FIELD(0x77, 1, 1),
+	.btn_short_pressed = REG_FIELD(0x77, 0, 0),
+	.wled_enable = REG_FIELD(0x01, 3, 3),
+	.wled_detect_en = REG_FIELD(0x01, 4, 4),
+	.wled_present = REG_FIELD(0x72, 7, 7),
+
+	.vbat_max = 4350000,
+	.boost_undervolt_setpoint = 4530000,
+	.boost_undervolt_uv_per_bit = 100000,
+};
+
+static struct ip5xxx_regfield_config ip5306_fields = {
+	.charger_enable = REG_FIELD(0x00, 4, 4),
+	.charger_const_volt_sel = REG_FIELD(0x22, 0, 1),
+	.charger_const_curr_sel = REG_FIELD(0x24, 0, 4),
+	.charger_status = REG_FIELD_UNSUPPORTED, // other bits...
+	.charger_chg_end = REG_FIELD(0x71, 3, 3),
+	.charger_timeout = REG_FIELD_UNSUPPORTED,
+	.charger_vin_overvolt = REG_FIELD_UNSUPPORTED,
+	.boost_enable = REG_FIELD(0x00, 5, 5),
+	.boost_llshdn_enable = REG_FIELD_UNSUPPORTED,
+	.boost_llshdn_i_limit = REG_FIELD_UNSUPPORTED,
+	.boost_load_powerup_en = REG_FIELD(0x00, 2, 2),
+	.boost_vin_pullout_en = REG_FIELD(0x01, 2, 2),
+	.boost_undervolt_limit = REG_FIELD(0x21, 2, 4),
+	.boost_light_load_status = REG_FIELD(0x72, 2, 2),
+	.battery_ntc_dis = REG_FIELD_UNSUPPORTED,
+	.battery_type = REG_FIELD(0x22, 2, 3),
+	.battery_vset_en = REG_FIELD_UNSUPPORTED,
+	.battery_adc_volt_low = REG_FIELD_UNSUPPORTED,
+	.battery_adc_volt_high = REG_FIELD_UNSUPPORTED,
+	.battery_adc_curr_low = REG_FIELD_UNSUPPORTED,
+	.battery_adc_curr_high = REG_FIELD_UNSUPPORTED,
+	.battery_adc_ovolt_low = REG_FIELD_UNSUPPORTED,
+	.battery_adc_ovolt_high = REG_FIELD_UNSUPPORTED,
+	.btn_shdn_enable = REG_FIELD(0x00, 0, 0),
+	.btn_wled_mode = REG_FIELD(0x01, 6, 6),
+	.btn_shdn_mode = REG_FIELD(0x01, 7, 7),
+	.btn_long_press_time = REG_FIELD(0x02, 4, 4), // +1s
+	.btn_pressed = REG_FIELD_UNSUPPORTED,
+	/* TODO: double press */
+	.btn_long_pressed = REG_FIELD(0x77, 1, 1),
+	.btn_short_pressed = REG_FIELD(0x77, 0, 0),
+	.wled_enable = REG_FIELD_UNSUPPORTED,
+	.wled_detect_en = REG_FIELD_UNSUPPORTED,
+	.wled_present = REG_FIELD_UNSUPPORTED,
+
+	.vbat_max = 4400000,
+	.boost_undervolt_setpoint = 4450000,
+	.boost_undervolt_uv_per_bit = 50000,
+	.const_curr_setpoint = 50000,
+	.chg_end_inverted = 1,
 };
 
+#define ip5xxx_setup_reg(_field, _reg) \
+			do { \
+				if (likely(cfg->_field.lsb <= cfg->_field.msb)) { \
+					struct regmap_field *_tmp = devm_regmap_field_alloc(dev, \
+							ip5xxx->regmap, cfg->_field); \
+					if (!IS_ERR(_tmp)) \
+						ip5xxx->regs._reg = _tmp; \
+				} \
+			} while (0)
+
+static void ip5xxx_setup_regs(struct device *dev, struct ip5xxx *ip5xxx,
+			      const struct ip5xxx_regfield_config *cfg)
+{
+	ip5xxx_setup_reg(charger_enable, charger.enable);
+	ip5xxx_setup_reg(charger_const_volt_sel, charger.const_volt_sel);
+	ip5xxx_setup_reg(charger_const_curr_sel, charger.const_curr_sel);
+	ip5xxx_setup_reg(charger_status, charger.status);
+	ip5xxx_setup_reg(charger_chg_end, charger.chg_end);
+	ip5xxx_setup_reg(charger_timeout, charger.timeout);
+	ip5xxx_setup_reg(charger_vin_overvolt, charger.vin_overvolt);
+	ip5xxx_setup_reg(boost_enable, boost.enable);
+	ip5xxx_setup_reg(boost_llshdn_enable, boost.light_load_shutdown.enable);
+	ip5xxx_setup_reg(boost_llshdn_i_limit, boost.light_load_shutdown.i_limit);
+	ip5xxx_setup_reg(boost_load_powerup_en, boost.load_powerup_en);
+	ip5xxx_setup_reg(boost_vin_pullout_en, boost.vin_pullout_en);
+	ip5xxx_setup_reg(boost_undervolt_limit, boost.undervolt_limit);
+	ip5xxx_setup_reg(boost_light_load_status, boost.light_load_status);
+	ip5xxx_setup_reg(battery_ntc_dis, battery.ntc_dis);
+	ip5xxx_setup_reg(battery_type, battery.type);
+	ip5xxx_setup_reg(battery_vset_en, battery.vset_en);
+	ip5xxx_setup_reg(battery_adc_volt_low, battery.adc.volt.low);
+	ip5xxx_setup_reg(battery_adc_volt_high, battery.adc.volt.high);
+	ip5xxx_setup_reg(battery_adc_curr_low, battery.adc.curr.low);
+	ip5xxx_setup_reg(battery_adc_curr_high, battery.adc.curr.high);
+	ip5xxx_setup_reg(battery_adc_ovolt_low, battery.adc.open_volt.low);
+	ip5xxx_setup_reg(battery_adc_ovolt_high, battery.adc.open_volt.high);
+	ip5xxx_setup_reg(btn_shdn_enable, btn.shdn_enable);
+	ip5xxx_setup_reg(btn_wled_mode, btn.wled_mode);
+	ip5xxx_setup_reg(btn_shdn_mode, btn.shdn_mode);
+	ip5xxx_setup_reg(btn_long_press_time, btn.long_press_time);
+	ip5xxx_setup_reg(btn_pressed, btn.pressed);
+	ip5xxx_setup_reg(btn_long_pressed, btn.long_pressed);
+	ip5xxx_setup_reg(btn_short_pressed, btn.short_pressed);
+	ip5xxx_setup_reg(wled_enable, wled.enable);
+	ip5xxx_setup_reg(wled_detect_en, wled.detect_en);
+	ip5xxx_setup_reg(wled_present, wled.present);
+
+	ip5xxx->vbat_max = cfg->vbat_max;
+	ip5xxx->boost_undervolt.setpoint = cfg->boost_undervolt_setpoint;
+	ip5xxx->boost_undervolt.microvolts_per_bit = cfg->boost_undervolt_uv_per_bit;
+	ip5xxx->const_curr.setpoint = cfg->const_curr_setpoint;
+	ip5xxx->chg_end_inverted = cfg->chg_end_inverted;
+}
+
 static int ip5xxx_power_probe(struct i2c_client *client)
 {
+	const struct ip5xxx_regfield_config *fields = &ip51xx_fields;
 	struct power_supply_config psy_cfg = {};
 	struct device *dev = &client->dev;
+	const struct of_device_id *of_id;
 	struct power_supply *psy;
 	struct ip5xxx *ip5xxx;
 
@@ -601,6 +843,11 @@ static int ip5xxx_power_probe(struct i2c_client *client)
 	if (IS_ERR(ip5xxx->regmap))
 		return PTR_ERR(ip5xxx->regmap);
 
+	of_id = i2c_of_match_device(dev->driver->of_match_table, client);
+	if (of_id)
+		fields = (const struct ip5xxx_regfield_config *)of_id->data;
+	ip5xxx_setup_regs(dev, ip5xxx, fields);
+
 	psy_cfg.of_node = dev->of_node;
 	psy_cfg.drv_data = ip5xxx;
 
@@ -616,10 +863,11 @@ static int ip5xxx_power_probe(struct i2c_client *client)
 }
 
 static const struct of_device_id ip5xxx_power_of_match[] = {
-	{ .compatible = "injoinic,ip5108" },
-	{ .compatible = "injoinic,ip5109" },
-	{ .compatible = "injoinic,ip5207" },
-	{ .compatible = "injoinic,ip5209" },
+	{ .compatible = "injoinic,ip5108", .data = &ip51xx_fields },
+	{ .compatible = "injoinic,ip5109", .data = &ip51xx_fields },
+	{ .compatible = "injoinic,ip5207", .data = &ip51xx_fields },
+	{ .compatible = "injoinic,ip5209", .data = &ip51xx_fields },
+	{ .compatible = "injoinic,ip5306", .data = &ip5306_fields },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, ip5xxx_power_of_match);
diff --git a/drivers/power/supply/ltc4162-l-charger.c b/drivers/power/supply/ltc4162-l-charger.c
index 2e4bc74e1c4a..23eb426295db 100644
--- a/drivers/power/supply/ltc4162-l-charger.c
+++ b/drivers/power/supply/ltc4162-l-charger.c
@@ -1,9 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- *  Driver for Analog Devices (Linear Technology) LTC4162-L charger IC.
+ *  Driver for Analog Devices (Linear Technology)
+ *  LTC4162-L 35V/3.2A Multi-Cell Lithium-Ion Step-Down Battery Charger
+ *  LTC4162-F 35V/3.2A Multi-Cell LiFePO4 Step-Down Battery Charger
+ *  LTC4162-S 35V/3.2A Lead-Acid Step-Down Battery Charger
+ *  LTC4015 35V/3.2A Multichemistry Buck Battery Charger Controller
  *  Copyright (C) 2020, Topic Embedded Products
  */
 
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/of.h>
@@ -47,6 +52,20 @@
 #define LTC4162L_VBAT_FILT			0x47
 #define LTC4162L_INPUT_UNDERVOLTAGE_DAC		0x4B
 
+#define LTC4162L_CHEM_MASK			GENMASK(11, 8)
+
+enum ltc4162_chem {
+	ltc4162_lad,
+	ltc4162_l42,
+	ltc4162_l41,
+	ltc4162_l40,
+	ltc4162_fad,
+	ltc4162_ffs,
+	ltc4162_fst,
+	ltc4162_sst = 8,
+	ltc4162_sad,
+};
+
 /* Enumeration as in datasheet. Individual bits are mutually exclusive. */
 enum ltc4162l_state {
 	battery_detection = 2048,
@@ -75,10 +94,28 @@ enum ltc4162l_charge_status {
 /* Magic number to write to ARM_SHIP_MODE register */
 #define LTC4162L_ARM_SHIP_MODE_MAGIC 21325
 
+struct ltc4162l_info;
+
+struct ltc4162l_chip_info {
+	const char *name;
+	int (*get_vbat)(struct ltc4162l_info *info, unsigned int reg,
+			union power_supply_propval *val);
+	int (*get_vcharge)(struct ltc4162l_info *info, unsigned int reg,
+			   union power_supply_propval *val);
+	int (*set_vcharge)(struct ltc4162l_info *info, unsigned int reg,
+			   unsigned int value);
+	int (*get_die_temp)(struct ltc4162l_info *info,
+			    union power_supply_propval *val);
+	unsigned int ibat_resolution_pv;
+	unsigned int vin_resolution_uv;
+	u8 telemetry_mask;
+};
+
 struct ltc4162l_info {
 	struct i2c_client	*client;
 	struct regmap		*regmap;
 	struct power_supply	*charger;
+	const struct ltc4162l_chip_info *chip_info;
 	u32 rsnsb;	/* Series resistor that sets charge current, microOhm */
 	u32 rsnsi;	/* Series resistor to measure input current, microOhm */
 	u8 cell_count;	/* Number of connected cells, 0 while unknown */
@@ -108,6 +145,18 @@ static u8 ltc4162l_get_cell_count(struct ltc4162l_info *info)
 	return val;
 };
 
+static u8 ltc4162l_get_chem_type(struct ltc4162l_info *info)
+{
+	int ret;
+	unsigned int val;
+
+	ret = regmap_read(info->regmap, LTC4162L_CHEM_CELLS_REG, &val);
+	if (ret)
+		return ret;
+
+	return FIELD_GET(LTC4162L_CHEM_MASK, val);
+};
+
 /* Convert enum value to POWER_SUPPLY_STATUS value */
 static int ltc4162l_state_decode(enum ltc4162l_state value)
 {
@@ -223,25 +272,83 @@ static int ltc4162l_get_vbat(struct ltc4162l_info *info,
 				  unsigned int reg,
 				  union power_supply_propval *val)
 {
-	unsigned int regval;
+	unsigned int regval, chem_type;
 	int ret;
 
 	ret = regmap_read(info->regmap, reg, &regval);
 	if (ret)
 		return ret;
 
-	/* cell_count × 192.4μV/LSB */
-	regval *= 1924;
-	regval *= ltc4162l_get_cell_count(info);
-	regval /= 10;
-	val->intval = regval;
+	/*
+	 * cell_count × scaling factor
+	 * For ltc4162-s, it uses a cell_count value of 2 for each group of 3
+	 * physical (2V) cells, thus will return 2, 4, 6, 8 for 6V, 12V, 18V,
+	 * and 24V respectively, and has to divide by 2 to multiply the scale
+	 * factor by 1, 2, 3, or 4 to represent a 6V, 12V, 18V, or 24V battery
+	 * respectively.
+	 */
+	chem_type = ltc4162l_get_chem_type(info);
+	switch (chem_type) {
+	case ltc4162_lad ... ltc4162_fst:
+		regval *= 1924;
+		regval *= ltc4162l_get_cell_count(info);
+		regval /= 10;
+		val->intval = regval;
 
-	return 0;
+		return 0;
+	case ltc4162_sst ... ltc4162_sad:
+		regval *= 3848;
+		regval *= ltc4162l_get_cell_count(info) / 2;
+		regval /= 10;
+		val->intval = regval;
+
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ltc4015_get_vbat(struct ltc4162l_info *info,
+			    unsigned int reg,
+			    union power_supply_propval *val)
+{
+	unsigned int regval, chem_type;
+	int ret;
+
+	ret = regmap_read(info->regmap, reg, &regval);
+	if (ret)
+		return ret;
+
+	/*
+	 * cell count x scaling factor
+	 * ltc4015 lead-acid fixed and lead-acid programmable corresponds to
+	 * 0x7 and 0x8 chem respectively
+	 */
+	chem_type = ltc4162l_get_chem_type(info);
+	switch (chem_type) {
+	case ltc4162_lad ... ltc4162_fst:
+		regval *= 192264;
+		regval *= ltc4162l_get_cell_count(info);
+		regval /= 1000;
+		val->intval = regval;
+
+		return 0;
+	case ltc4162_sst - 1 ... ltc4162_sad - 1:
+		regval *= 128176;
+		regval *= ltc4162l_get_cell_count(info);
+		regval /= 1000;
+		val->intval = regval;
+
+		return 0;
+	default:
+		return -EINVAL;
+	}
 }
 
 static int ltc4162l_get_ibat(struct ltc4162l_info *info,
 			     union power_supply_propval *val)
 {
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 	unsigned int regval;
 	int ret;
 
@@ -249,9 +356,8 @@ static int ltc4162l_get_ibat(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	/* Signed 16-bit number, 1.466μV / RSNSB amperes/LSB. */
 	ret = (s16)(regval & 0xFFFF);
-	val->intval = 100 * mult_frac(ret, 14660, (int)info->rsnsb);
+	val->intval = mult_frac(ret, chip_info->ibat_resolution_pv, info->rsnsb);
 
 	return 0;
 }
@@ -260,6 +366,7 @@ static int ltc4162l_get_ibat(struct ltc4162l_info *info,
 static int ltc4162l_get_input_voltage(struct ltc4162l_info *info,
 				      union power_supply_propval *val)
 {
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 	unsigned int regval;
 	int ret;
 
@@ -267,8 +374,7 @@ static int ltc4162l_get_input_voltage(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	/* 1.649mV/LSB */
-	val->intval =  regval * 1694;
+	val->intval =  regval * chip_info->vin_resolution_uv;
 
 	return 0;
 }
@@ -276,6 +382,7 @@ static int ltc4162l_get_input_voltage(struct ltc4162l_info *info,
 static int ltc4162l_get_input_current(struct ltc4162l_info *info,
 				      union power_supply_propval *val)
 {
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 	unsigned int regval;
 	int ret;
 
@@ -283,11 +390,9 @@ static int ltc4162l_get_input_current(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	/* Signed 16-bit number, 1.466μV / RSNSI amperes/LSB. */
 	ret = (s16)(regval & 0xFFFF);
-	ret *= 14660;
+	ret *= chip_info->ibat_resolution_pv;
 	ret /= info->rsnsi;
-	ret *= 100;
 
 	val->intval = ret;
 
@@ -305,7 +410,7 @@ static int ltc4162l_get_icharge(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	regval &= BIT(6) - 1; /* Only the lower 5 bits */
+	regval &= GENMASK(5, 0);
 
 	/* The charge current servo level: (icharge_dac + 1) × 1mV/RSNSB */
 	++regval;
@@ -336,7 +441,7 @@ static int ltc4162l_get_vcharge(struct ltc4162l_info *info,
 				unsigned int reg,
 				union power_supply_propval *val)
 {
-	unsigned int regval;
+	unsigned int regval, chem_type;
 	int ret;
 	u32 voltage;
 
@@ -344,41 +449,181 @@ static int ltc4162l_get_vcharge(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	regval &= BIT(6) - 1; /* Only the lower 5 bits */
+	regval &= GENMASK(5, 0);
 
 	/*
 	 * charge voltage setting can be computed from
-	 * cell_count × (vcharge_setting × 12.5mV + 3.8125V)
-	 * where vcharge_setting ranges from 0 to 31 (4.2V max).
+	 * cell_count × (vcharge_setting × a + b)
+	 * where vcharge_setting ranges from 0 to c (d).
+	 * for ltc4162l: a = 12.5mV , b = 3.8125V, c = 31, d = 4.2Vmax
+	 * for ltc4162f: a = 12.5mV , b = 3.4125V, c = 31, d = 3.8Vmax
+	 *
+	 * for ltc4162s, the charge voltage setting can be computed from
+	 * N x (vcharge_setting x 28.571mV + 6.0V)
+	 * where N is 1, 2, 3, or 4 for 6V, 12V, 18V, or 24V battery respectively,
+	 * and vcharge_setting ranges from 0 to 31
 	 */
-	voltage = 3812500 + (regval * 12500);
-	voltage *= ltc4162l_get_cell_count(info);
-	val->intval = voltage;
+	chem_type = ltc4162l_get_chem_type(info);
+	switch (chem_type) {
+	case ltc4162_lad ... ltc4162_l40:
+		voltage = 3812500 + (regval * 12500);
+		voltage *= ltc4162l_get_cell_count(info);
+		val->intval = voltage;
 
-	return 0;
+		return 0;
+	case ltc4162_fad ... ltc4162_fst:
+		voltage = 3412500 + (regval * 12500);
+		voltage *= ltc4162l_get_cell_count(info);
+		val->intval = voltage;
+
+		return 0;
+	case ltc4162_sst ... ltc4162_sad:
+		voltage = 6000000 + (regval * 28571);
+		voltage *= ltc4162l_get_cell_count(info) / 2;
+		val->intval = voltage;
+
+		return 0;
+	default:
+		return -EINVAL;
+	}
 }
 
-static int ltc4162l_set_vcharge(struct ltc4162l_info *info,
-				unsigned int reg,
-				unsigned int value)
+static int ltc4015_get_vcharge(struct ltc4162l_info *info,
+			       unsigned int reg,
+			       union power_supply_propval *val)
 {
-	u8 cell_count = ltc4162l_get_cell_count(info);
+	unsigned int regval, chem_type;
+	int ret;
+	u32 voltage;
+
+	ret = regmap_read(info->regmap, reg, &regval);
+	if (ret)
+		return ret;
 
-	if (!cell_count)
-		return -EBUSY; /* Not available yet, try again later */
+	regval &= GENMASK(5, 0);
 
+	/*
+	 * charge voltage setting can be computed from:
+	 * cell_count × (vcharge_setting × a + b)
+	 * where vcharge_setting ranges from 0 to c (d).
+	 * Li-Ion: a = 1/80V, b = 3.8125V, c = 31, d = 4.2Vmax
+	 * LiFePO4: a = 1/80V, b = 3.4125V, c = 31, d = 3.8Vmax
+	 * Lead Acid: a = 1/105V, b = 2V, c = 35, d = 2.6Vmax
+	 */
+	chem_type = ltc4162l_get_chem_type(info);
+	switch (chem_type) {
+	case ltc4162_lad ... ltc4162_l40:
+		voltage = 3812500 + (regval * 12500);
+		voltage *= ltc4162l_get_cell_count(info);
+		val->intval = voltage;
+
+		return 0;
+	case ltc4162_fad ... ltc4162_fst:
+		voltage = 3412500 + (regval * 12500);
+		voltage *= ltc4162l_get_cell_count(info);
+		val->intval = voltage;
+
+		return 0;
+	case ltc4162_sst - 1 ... ltc4162_sad - 1:
+		voltage = 2000000 + mult_frac(regval, 1000000, 105);
+		voltage *= ltc4162l_get_cell_count(info);
+		val->intval = voltage;
+
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ltc4162l_vcharge(unsigned int base_voltage,
+			    unsigned int scale_factor,
+			    unsigned int range,
+			    unsigned int value,
+			    u8 cell_count)
+{
 	value /= cell_count;
 
-	if (value < 3812500)
+	if (value < base_voltage)
 		return -EINVAL;
 
-	value -= 3812500;
-	value /= 12500;
+	value -= base_voltage;
+	value /= scale_factor;
 
-	if (value > 31)
+	if (value > range)
 		return -EINVAL;
 
-	return regmap_write(info->regmap, reg, value);
+	return value;
+}
+
+static int ltc4162l_set_vcharge(struct ltc4162l_info *info,
+				unsigned int reg,
+				unsigned int value)
+{
+	unsigned int chem_type;
+	u8 cell_count;
+
+	chem_type = ltc4162l_get_chem_type(info);
+	switch (chem_type) {
+	case ltc4162_lad ... ltc4162_l40:
+		cell_count = ltc4162l_get_cell_count(info);
+		if (!cell_count)
+			return -EBUSY;
+
+		value = ltc4162l_vcharge(3812500, 12500, 31, value, cell_count);
+		return regmap_write(info->regmap, reg, value);
+	case ltc4162_fad ... ltc4162_fst:
+		cell_count = ltc4162l_get_cell_count(info);
+		if (!cell_count)
+			return -EBUSY;
+
+		value = ltc4162l_vcharge(3412500, 12500, 31, value, cell_count);
+		return regmap_write(info->regmap, reg, value);
+	case ltc4162_sst ... ltc4162_sad:
+		cell_count = ltc4162l_get_cell_count(info) / 2;
+		if (!cell_count)
+			return -EBUSY;
+
+		value = ltc4162l_vcharge(6000000, 28571, 31, value, cell_count);
+		return regmap_write(info->regmap, reg, value);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int ltc4015_set_vcharge(struct ltc4162l_info *info,
+			       unsigned int reg,
+			       unsigned int value)
+{
+	unsigned int chem_type;
+	u8 cell_count;
+
+	chem_type = ltc4162l_get_chem_type(info);
+	switch (chem_type) {
+	case ltc4162_lad ... ltc4162_l40:
+		cell_count = ltc4162l_get_cell_count(info);
+		if (!cell_count)
+			return -EBUSY;
+
+		value = ltc4162l_vcharge(3812500, 12500, 31, value, cell_count);
+		return regmap_write(info->regmap, reg, value);
+	case ltc4162_fad ... ltc4162_fst:
+		cell_count = ltc4162l_get_cell_count(info);
+		if (!cell_count)
+			return -EBUSY;
+
+		value = ltc4162l_vcharge(3412500, 12500, 31, value, cell_count);
+		return regmap_write(info->regmap, reg, value);
+	case ltc4162_sst - 1 ... ltc4162_sad - 1:
+		cell_count = ltc4162l_get_cell_count(info);
+		if (!cell_count)
+			return -EBUSY;
+
+		value = ltc4162l_vcharge(2000000, 1000000 / 105, 35,
+					 value, cell_count);
+		return regmap_write(info->regmap, reg, value);
+	default:
+		return -EINVAL;
+	}
 }
 
 static int ltc4162l_get_iin_limit_dac(struct ltc4162l_info *info,
@@ -391,7 +636,7 @@ static int ltc4162l_get_iin_limit_dac(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	regval &= BIT(6) - 1; /* Only 6 bits */
+	regval &= GENMASK(5, 0);
 
 	/* (iin_limit_dac + 1) × 500μV / RSNSI */
 	++regval;
@@ -437,9 +682,30 @@ static int ltc4162l_get_die_temp(struct ltc4162l_info *info,
 	return 0;
 }
 
+static int ltc4015_get_die_temp(struct ltc4162l_info *info,
+				union power_supply_propval *val)
+{
+	unsigned int regval;
+	int ret;
+
+	ret = regmap_read(info->regmap, LTC4162L_DIE_TEMPERATURE, &regval);
+	if (ret)
+		return ret;
+
+	/* (die_temp - 12010) / 45.6°C */
+	ret = (s16)(regval & 0xFFFF);
+	ret -= 12010;
+	ret *= 1000;
+	ret /= 456;
+	val->intval = ret;
+
+	return 0;
+}
+
 static int ltc4162l_get_term_current(struct ltc4162l_info *info,
 				     union power_supply_propval *val)
 {
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 	unsigned int regval;
 	int ret;
 
@@ -457,10 +723,9 @@ static int ltc4162l_get_term_current(struct ltc4162l_info *info,
 	if (ret)
 		return ret;
 
-	/* 1.466μV / RSNSB amperes/LSB */
-	regval *= 14660u;
+	regval *= chip_info->ibat_resolution_pv;
 	regval /= info->rsnsb;
-	val->intval = 100 * regval;
+	val->intval = regval;
 
 	return 0;
 }
@@ -534,10 +799,11 @@ static ssize_t vbat_show(struct device *dev,
 {
 	struct power_supply *psy = to_power_supply(dev);
 	struct ltc4162l_info *info = power_supply_get_drvdata(psy);
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 	union power_supply_propval val;
 	int ret;
 
-	ret = ltc4162l_get_vbat(info, LTC4162L_VBAT, &val);
+	ret = chip_info->get_vbat(info, LTC4162L_VBAT, &val);
 	if (ret)
 		return ret;
 
@@ -550,10 +816,11 @@ static ssize_t vbat_avg_show(struct device *dev,
 {
 	struct power_supply *psy = to_power_supply(dev);
 	struct ltc4162l_info *info = power_supply_get_drvdata(psy);
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 	union power_supply_propval val;
 	int ret;
 
-	ret = ltc4162l_get_vbat(info, LTC4162L_VBAT_FILT, &val);
+	ret = chip_info->get_vbat(info, LTC4162L_VBAT_FILT, &val);
 	if (ret)
 		return ret;
 
@@ -589,7 +856,8 @@ static ssize_t force_telemetry_show(struct device *dev,
 	if (ret)
 		return ret;
 
-	return sysfs_emit(buf, "%u\n", regval & BIT(2) ? 1 : 0);
+	return sysfs_emit(buf, "%u\n", regval &
+			  info->chip_info->telemetry_mask ? 1 : 0);
 }
 
 static ssize_t force_telemetry_store(struct device *dev,
@@ -607,7 +875,8 @@ static ssize_t force_telemetry_store(struct device *dev,
 		return ret;
 
 	ret = regmap_update_bits(info->regmap, LTC4162L_CONFIG_BITS_REG,
-				 BIT(2), value ? BIT(2) : 0);
+				 info->chip_info->telemetry_mask,
+				 value ? info->chip_info->telemetry_mask : 0);
 	if (ret < 0)
 		return ret;
 
@@ -681,6 +950,7 @@ static int ltc4162l_get_property(struct power_supply *psy,
 				 union power_supply_propval *val)
 {
 	struct ltc4162l_info *info = power_supply_get_drvdata(psy);
+	const struct ltc4162l_chip_info *chip_info = info->chip_info;
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_STATUS:
@@ -702,15 +972,13 @@ static int ltc4162l_get_property(struct power_supply *psy,
 		return ltc4162l_get_icharge(info,
 				LTC4162L_CHARGE_CURRENT_SETTING, val);
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE:
-		return ltc4162l_get_vcharge(info,
-				LTC4162L_VCHARGE_DAC, val);
+		return chip_info->get_vcharge(info, LTC4162L_VCHARGE_DAC, val);
 	case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX:
-		return ltc4162l_get_vcharge(info,
-				LTC4162L_VCHARGE_SETTING, val);
+		return chip_info->get_vcharge(info, LTC4162L_VCHARGE_SETTING, val);
 	case POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT:
 		return ltc4162l_get_iin_limit_dac(info, val);
 	case POWER_SUPPLY_PROP_TEMP:
-		return ltc4162l_get_die_temp(info, val);
+		return chip_info->get_die_temp(info, val);
 	case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT:
 		return ltc4162l_get_term_current(info, val);
 	default:
@@ -772,7 +1040,6 @@ static enum power_supply_property ltc4162l_properties[] = {
 };
 
 static const struct power_supply_desc ltc4162l_desc = {
-	.name		= "ltc4162-l",
 	.type		= POWER_SUPPLY_TYPE_MAINS,
 	.properties	= ltc4162l_properties,
 	.num_properties	= ARRAY_SIZE(ltc4162l_properties),
@@ -781,6 +1048,50 @@ static const struct power_supply_desc ltc4162l_desc = {
 	.property_is_writeable = ltc4162l_property_is_writeable,
 };
 
+static const struct ltc4162l_chip_info ltc4162l_chip_info = {
+	.name = "ltc4162-l",
+	.get_vbat = ltc4162l_get_vbat,
+	.get_vcharge = ltc4162l_get_vcharge,
+	.set_vcharge = ltc4162l_set_vcharge,
+	.get_die_temp = ltc4162l_get_die_temp,
+	.ibat_resolution_pv = 1466000,
+	.vin_resolution_uv = 1649,
+	.telemetry_mask = BIT(2),
+};
+
+static const struct ltc4162l_chip_info ltc4162f_chip_info = {
+	.name = "ltc4162-f",
+	.get_vbat = ltc4162l_get_vbat,
+	.get_vcharge = ltc4162l_get_vcharge,
+	.set_vcharge = ltc4162l_set_vcharge,
+	.get_die_temp = ltc4162l_get_die_temp,
+	.ibat_resolution_pv = 1466000,
+	.vin_resolution_uv = 1649,
+	.telemetry_mask = BIT(2),
+};
+
+static const struct ltc4162l_chip_info ltc4162s_chip_info = {
+	.name = "ltc4162-s",
+	.get_vbat = ltc4162l_get_vbat,
+	.get_vcharge = ltc4162l_get_vcharge,
+	.set_vcharge = ltc4162l_set_vcharge,
+	.get_die_temp = ltc4162l_get_die_temp,
+	.ibat_resolution_pv = 1466000,
+	.vin_resolution_uv = 1649,
+	.telemetry_mask = BIT(2),
+};
+
+static const struct ltc4162l_chip_info ltc4015_chip_info = {
+	.name = "ltc4015",
+	.get_vbat = ltc4015_get_vbat,
+	.get_vcharge = ltc4015_get_vcharge,
+	.set_vcharge = ltc4015_set_vcharge,
+	.get_die_temp = ltc4015_get_die_temp,
+	.ibat_resolution_pv = 1464870,
+	.vin_resolution_uv = 1648,
+	.telemetry_mask = BIT(4),
+};
+
 static bool ltc4162l_is_writeable_reg(struct device *dev, unsigned int reg)
 {
 	/* all registers up to this one are writeable */
@@ -825,6 +1136,8 @@ static int ltc4162l_probe(struct i2c_client *client)
 	struct device *dev = &client->dev;
 	struct ltc4162l_info *info;
 	struct power_supply_config ltc4162l_config = {};
+	struct power_supply_desc *desc;
+	const struct ltc4162l_chip_info *chip_info;
 	u32 value;
 	int ret;
 
@@ -839,6 +1152,12 @@ static int ltc4162l_probe(struct i2c_client *client)
 	info->client = client;
 	i2c_set_clientdata(client, info);
 
+	chip_info = i2c_get_match_data(client);
+	if (!chip_info)
+		return -ENODEV;
+
+	info->chip_info = chip_info;
+
 	info->regmap = devm_regmap_init_i2c(client, &ltc4162l_regmap_config);
 	if (IS_ERR(info->regmap)) {
 		dev_err(dev, "Failed to initialize register map\n");
@@ -870,8 +1189,15 @@ static int ltc4162l_probe(struct i2c_client *client)
 	ltc4162l_config.drv_data = info;
 	ltc4162l_config.attr_grp = ltc4162l_attr_groups;
 
-	info->charger = devm_power_supply_register(dev, &ltc4162l_desc,
-						   &ltc4162l_config);
+	/* Duplicate the default descriptor to set name based on chip_info. */
+	desc = devm_kmemdup(dev, &ltc4162l_desc,
+			    sizeof(struct power_supply_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	desc->name = chip_info->name;
+
+	info->charger = devm_power_supply_register(dev, desc, &ltc4162l_config);
 	if (IS_ERR(info->charger)) {
 		dev_err(dev, "Failed to register charger\n");
 		return PTR_ERR(info->charger);
@@ -903,14 +1229,20 @@ static void ltc4162l_alert(struct i2c_client *client,
 }
 
 static const struct i2c_device_id ltc4162l_i2c_id_table[] = {
-	{ "ltc4162-l" },
+	{ "ltc4015", (kernel_ulong_t)&ltc4015_chip_info },
+	{ "ltc4162-f", (kernel_ulong_t)&ltc4162f_chip_info },
+	{ "ltc4162-l", (kernel_ulong_t)&ltc4162l_chip_info },
+	{ "ltc4162-s", (kernel_ulong_t)&ltc4162s_chip_info },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, ltc4162l_i2c_id_table);
 
 static const struct of_device_id ltc4162l_of_match[] __maybe_unused = {
-	{ .compatible = "lltc,ltc4162-l", },
-	{ },
+	{ .compatible = "lltc,ltc4015", .data = &ltc4015_chip_info },
+	{ .compatible = "lltc,ltc4162-f", .data = &ltc4162f_chip_info },
+	{ .compatible = "lltc,ltc4162-l", .data = &ltc4162l_chip_info },
+	{ .compatible = "lltc,ltc4162-s", .data = &ltc4162s_chip_info },
+	{ }
 };
 MODULE_DEVICE_TABLE(of, ltc4162l_of_match);
 
diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c
index 496c3e1f2ee6..655b3f25dbd7 100644
--- a/drivers/power/supply/max17042_battery.c
+++ b/drivers/power/supply/max17042_battery.c
@@ -16,6 +16,7 @@
 #include <linux/i2c.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/mod_devicetable.h>
 #include <linux/power_supply.h>
@@ -52,13 +53,14 @@
 #define MAX17042_VMAX_TOLERANCE		50 /* 50 mV */
 
 struct max17042_chip {
-	struct i2c_client *client;
+	struct device *dev;
 	struct regmap *regmap;
 	struct power_supply *battery;
 	enum max170xx_chip_type chip_type;
 	struct max17042_platform_data *pdata;
 	struct work_struct work;
 	int    init_complete;
+	int    irq;
 };
 
 static enum power_supply_property max17042_battery_props[] = {
@@ -573,11 +575,11 @@ static inline int max17042_model_data_compare(struct max17042_chip *chip,
 	int i;
 
 	if (memcmp(data1, data2, size)) {
-		dev_err(&chip->client->dev, "%s compare failed\n", __func__);
+		dev_err(chip->dev, "%s compare failed\n", __func__);
 		for (i = 0; i < size; i++)
-			dev_info(&chip->client->dev, "0x%x, 0x%x",
+			dev_info(chip->dev, "0x%x, 0x%x",
 				data1[i], data2[i]);
-		dev_info(&chip->client->dev, "\n");
+		dev_info(chip->dev, "\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -812,14 +814,14 @@ static int max17042_init_chip(struct max17042_chip *chip)
 	/* write cell characterization data */
 	ret = max17042_init_model(chip);
 	if (ret) {
-		dev_err(&chip->client->dev, "%s init failed\n",
+		dev_err(chip->dev, "%s init failed\n",
 			__func__);
 		return -EIO;
 	}
 
 	ret = max17042_verify_model_lock(chip);
 	if (ret) {
-		dev_err(&chip->client->dev, "%s lock verify failed\n",
+		dev_err(chip->dev, "%s lock verify failed\n",
 			__func__);
 		return -EIO;
 	}
@@ -875,7 +877,7 @@ static irqreturn_t max17042_thread_handler(int id, void *dev)
 		return IRQ_HANDLED;
 
 	if ((val & STATUS_SMN_BIT) || (val & STATUS_SMX_BIT)) {
-		dev_dbg(&chip->client->dev, "SOC threshold INTR\n");
+		dev_dbg(chip->dev, "SOC threshold INTR\n");
 		max17042_set_soc_threshold(chip, 1);
 	}
 
@@ -907,7 +909,7 @@ static void max17042_init_worker(struct work_struct *work)
 static struct max17042_platform_data *
 max17042_get_of_pdata(struct max17042_chip *chip)
 {
-	struct device *dev = &chip->client->dev;
+	struct device *dev = chip->dev;
 	struct device_node *np = dev->of_node;
 	u32 prop;
 	struct max17042_platform_data *pdata;
@@ -949,7 +951,7 @@ static struct max17042_reg_data max17047_default_pdata_init_regs[] = {
 static struct max17042_platform_data *
 max17042_get_default_pdata(struct max17042_chip *chip)
 {
-	struct device *dev = &chip->client->dev;
+	struct device *dev = chip->dev;
 	struct max17042_platform_data *pdata;
 	int ret, misc_cfg;
 
@@ -990,7 +992,7 @@ max17042_get_default_pdata(struct max17042_chip *chip)
 static struct max17042_platform_data *
 max17042_get_pdata(struct max17042_chip *chip)
 {
-	struct device *dev = &chip->client->dev;
+	struct device *dev = chip->dev;
 
 #ifdef CONFIG_OF
 	if (dev->of_node)
@@ -1003,6 +1005,7 @@ max17042_get_pdata(struct max17042_chip *chip)
 }
 
 static const struct regmap_config max17042_regmap_config = {
+	.name = "max17042",
 	.reg_bits = 8,
 	.val_bits = 16,
 	.val_format_endian = REGMAP_ENDIAN_NATIVE,
@@ -1029,14 +1032,12 @@ static const struct power_supply_desc max17042_no_current_sense_psy_desc = {
 	.num_properties	= ARRAY_SIZE(max17042_battery_props) - 2,
 };
 
-static int max17042_probe(struct i2c_client *client)
+static int max17042_probe(struct i2c_client *client, struct device *dev, int irq,
+			  enum max170xx_chip_type chip_type)
 {
-	const struct i2c_device_id *id = i2c_client_get_device_id(client);
 	struct i2c_adapter *adapter = client->adapter;
 	const struct power_supply_desc *max17042_desc = &max17042_psy_desc;
 	struct power_supply_config psy_cfg = {};
-	const struct acpi_device_id *acpi_id = NULL;
-	struct device *dev = &client->dev;
 	struct max17042_chip *chip;
 	int ret;
 	int i;
@@ -1045,33 +1046,25 @@ static int max17042_probe(struct i2c_client *client)
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WORD_DATA))
 		return -EIO;
 
-	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
-	chip->client = client;
-	if (id) {
-		chip->chip_type = id->driver_data;
-	} else {
-		acpi_id = acpi_match_device(dev->driver->acpi_match_table, dev);
-		if (!acpi_id)
-			return -ENODEV;
-
-		chip->chip_type = acpi_id->driver_data;
-	}
+	chip->dev = dev;
+	chip->chip_type = chip_type;
 	chip->regmap = devm_regmap_init_i2c(client, &max17042_regmap_config);
 	if (IS_ERR(chip->regmap)) {
-		dev_err(&client->dev, "Failed to initialize regmap\n");
+		dev_err(dev, "Failed to initialize regmap\n");
 		return -EINVAL;
 	}
 
 	chip->pdata = max17042_get_pdata(chip);
 	if (!chip->pdata) {
-		dev_err(&client->dev, "no platform data provided\n");
+		dev_err(dev, "no platform data provided\n");
 		return -EINVAL;
 	}
 
-	i2c_set_clientdata(client, chip);
+	dev_set_drvdata(dev, chip);
 	psy_cfg.drv_data = chip;
 	psy_cfg.of_node = dev->of_node;
 
@@ -1095,24 +1088,17 @@ static int max17042_probe(struct i2c_client *client)
 		regmap_write(chip->regmap, MAX17042_LearnCFG, 0x0007);
 	}
 
-	chip->battery = devm_power_supply_register(&client->dev, max17042_desc,
+	chip->battery = devm_power_supply_register(dev, max17042_desc,
 						   &psy_cfg);
 	if (IS_ERR(chip->battery)) {
-		dev_err(&client->dev, "failed: power supply register\n");
+		dev_err(dev, "failed: power supply register\n");
 		return PTR_ERR(chip->battery);
 	}
 
-	if (client->irq) {
-		unsigned int flags = IRQF_ONESHOT;
-
-		/*
-		 * On ACPI systems the IRQ may be handled by ACPI-event code,
-		 * so we need to share (if the ACPI code is willing to share).
-		 */
-		if (acpi_id)
-			flags |= IRQF_SHARED | IRQF_PROBE_SHARED;
+	if (irq) {
+		unsigned int flags = IRQF_ONESHOT | IRQF_SHARED | IRQF_PROBE_SHARED;
 
-		ret = devm_request_threaded_irq(&client->dev, client->irq,
+		ret = devm_request_threaded_irq(dev, irq,
 						NULL,
 						max17042_thread_handler, flags,
 						chip->battery->desc->name,
@@ -1123,18 +1109,20 @@ static int max17042_probe(struct i2c_client *client)
 					CFG_ALRT_BIT_ENBL);
 			max17042_set_soc_threshold(chip, 1);
 		} else {
-			client->irq = 0;
+			irq = 0;
 			if (ret != -EBUSY)
-				dev_err(&client->dev, "Failed to get IRQ\n");
+				dev_err(dev, "Failed to get IRQ\n");
 		}
 	}
 	/* Not able to update the charge threshold when exceeded? -> disable */
-	if (!client->irq)
+	if (!irq)
 		regmap_write(chip->regmap, MAX17042_SALRT_Th, 0xff00);
 
+	chip->irq = irq;
+
 	regmap_read(chip->regmap, MAX17042_STATUS, &val);
 	if (val & STATUS_POR_BIT) {
-		ret = devm_work_autocancel(&client->dev, &chip->work,
+		ret = devm_work_autocancel(dev, &chip->work,
 					   max17042_init_worker);
 		if (ret)
 			return ret;
@@ -1146,6 +1134,44 @@ static int max17042_probe(struct i2c_client *client)
 	return 0;
 }
 
+static int max17042_i2c_probe(struct i2c_client *client)
+{
+	const struct i2c_device_id *id = i2c_client_get_device_id(client);
+	const struct acpi_device_id *acpi_id = NULL;
+	struct device *dev = &client->dev;
+	enum max170xx_chip_type chip_type;
+
+	if (id) {
+		chip_type = id->driver_data;
+	} else {
+		acpi_id = acpi_match_device(dev->driver->acpi_match_table, dev);
+		if (!acpi_id)
+			return -ENODEV;
+
+		chip_type = acpi_id->driver_data;
+	}
+
+	return max17042_probe(client, dev, client->irq, chip_type);
+}
+
+static int max17042_platform_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct i2c_client *i2c;
+	const struct platform_device_id *id;
+	int irq;
+
+	i2c = to_i2c_client(pdev->dev.parent);
+	if (!i2c)
+		return -EINVAL;
+
+	dev->of_node = dev->parent->of_node;
+	id = platform_get_device_id(pdev);
+	irq = platform_get_irq(pdev, 0);
+
+	return max17042_probe(i2c, dev, irq, id->driver_data);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int max17042_suspend(struct device *dev)
 {
@@ -1155,9 +1181,9 @@ static int max17042_suspend(struct device *dev)
 	 * disable the irq and enable irq_wake
 	 * capability to the interrupt line.
 	 */
-	if (chip->client->irq) {
-		disable_irq(chip->client->irq);
-		enable_irq_wake(chip->client->irq);
+	if (chip->irq) {
+		disable_irq(chip->irq);
+		enable_irq_wake(chip->irq);
 	}
 
 	return 0;
@@ -1167,9 +1193,9 @@ static int max17042_resume(struct device *dev)
 {
 	struct max17042_chip *chip = dev_get_drvdata(dev);
 
-	if (chip->client->irq) {
-		disable_irq_wake(chip->client->irq);
-		enable_irq(chip->client->irq);
+	if (chip->irq) {
+		disable_irq_wake(chip->irq);
+		enable_irq(chip->irq);
 		/* re-program the SOC thresholds to 1% change */
 		max17042_set_soc_threshold(chip, 1);
 	}
@@ -1190,12 +1216,28 @@ MODULE_DEVICE_TABLE(acpi, max17042_acpi_match);
 #endif
 
 #ifdef CONFIG_OF
-static const struct of_device_id max17042_dt_match[] = {
-	{ .compatible = "maxim,max17042" },
-	{ .compatible = "maxim,max17047" },
-	{ .compatible = "maxim,max17050" },
-	{ .compatible = "maxim,max17055" },
-	{ .compatible = "maxim,max77849-battery" },
+/*
+ * Device may be instantiated through parent MFD device and device matching is done
+ * through platform_device_id.
+ *
+ * However if device's DT node contains proper clock compatible and driver is
+ * built as a module, then the *module* matching will be done trough DT aliases.
+ * This requires of_device_id table.  In the same time this will not change the
+ * actual *device* matching so do not add .of_match_table.
+ */
+static const struct of_device_id max17042_dt_match[] __used = {
+	{ .compatible = "maxim,max17042",
+		.data = (void *) MAXIM_DEVICE_TYPE_MAX17042 },
+	{ .compatible = "maxim,max17047",
+		.data = (void *) MAXIM_DEVICE_TYPE_MAX17047 },
+	{ .compatible = "maxim,max17050",
+		.data = (void *) MAXIM_DEVICE_TYPE_MAX17050 },
+	{ .compatible = "maxim,max17055",
+		.data = (void *) MAXIM_DEVICE_TYPE_MAX17055 },
+	{ .compatible = "maxim,max77705-battery",
+		.data = (void *) MAXIM_DEVICE_TYPE_MAX17047 },
+	{ .compatible = "maxim,max77849-battery",
+		.data = (void *) MAXIM_DEVICE_TYPE_MAX17047 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, max17042_dt_match);
@@ -1211,6 +1253,17 @@ static const struct i2c_device_id max17042_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, max17042_id);
 
+static const struct platform_device_id max17042_platform_id[] = {
+	{ "max17042", MAXIM_DEVICE_TYPE_MAX17042 },
+	{ "max17047", MAXIM_DEVICE_TYPE_MAX17047 },
+	{ "max17050", MAXIM_DEVICE_TYPE_MAX17050 },
+	{ "max17055", MAXIM_DEVICE_TYPE_MAX17055 },
+	{ "max77705-battery", MAXIM_DEVICE_TYPE_MAX17047 },
+	{ "max77849-battery", MAXIM_DEVICE_TYPE_MAX17047 },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, max17042_platform_id);
+
 static struct i2c_driver max17042_i2c_driver = {
 	.driver	= {
 		.name	= "max17042",
@@ -1218,10 +1271,44 @@ static struct i2c_driver max17042_i2c_driver = {
 		.of_match_table = of_match_ptr(max17042_dt_match),
 		.pm	= &max17042_pm_ops,
 	},
-	.probe		= max17042_probe,
+	.probe		= max17042_i2c_probe,
 	.id_table	= max17042_id,
 };
-module_i2c_driver(max17042_i2c_driver);
+
+static struct platform_driver max17042_platform_driver = {
+	.driver	= {
+		.name	= "max17042",
+		.acpi_match_table = ACPI_PTR(max17042_acpi_match),
+		.pm	= &max17042_pm_ops,
+	},
+	.probe		= max17042_platform_probe,
+	.id_table	= max17042_platform_id,
+};
+
+static int __init max17042_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&max17042_platform_driver);
+	if (ret)
+		return ret;
+
+	ret = i2c_add_driver(&max17042_i2c_driver);
+	if (ret) {
+		platform_driver_unregister(&max17042_platform_driver);
+		return ret;
+	}
+
+	return 0;
+}
+module_init(max17042_init);
+
+static void __exit max17042_exit(void)
+{
+	i2c_del_driver(&max17042_i2c_driver);
+	platform_driver_unregister(&max17042_platform_driver);
+}
+module_exit(max17042_exit);
 
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
 MODULE_DESCRIPTION("MAX17042 Fuel Gauge");
diff --git a/drivers/power/supply/max1720x_battery.c b/drivers/power/supply/max1720x_battery.c
index 33105419e242..11580e414713 100644
--- a/drivers/power/supply/max1720x_battery.c
+++ b/drivers/power/supply/max1720x_battery.c
@@ -16,6 +16,11 @@
 
 #include <linux/unaligned.h>
 
+/* SBS compliant registers */
+#define MAX172XX_TEMP1			0x34
+#define MAX172XX_INT_TEMP		0x35
+#define MAX172XX_TEMP2			0x3B
+
 /* Nonvolatile registers */
 #define MAX1720X_NXTABLE0		0x80
 #define MAX1720X_NRSENSE		0xCF	/* RSense in 10^-5 Ohm */
@@ -29,6 +34,7 @@
 #define MAX172XX_TEMP			0x08	/* Temperature */
 #define MAX172XX_CURRENT		0x0A	/* Actual current */
 #define MAX172XX_AVG_CURRENT		0x0B	/* Average current */
+#define MAX172XX_FULL_CAP		0x10	/* Calculated full capacity */
 #define MAX172XX_TTE			0x11	/* Time to empty */
 #define MAX172XX_AVG_TA			0x16	/* Average temperature */
 #define MAX172XX_CYCLES			0x17
@@ -112,11 +118,15 @@ static const struct regmap_config max1720x_regmap_cfg = {
 };
 
 static const struct regmap_range max1720x_nvmem_allow[] = {
+	regmap_reg_range(MAX172XX_TEMP1, MAX172XX_INT_TEMP),
+	regmap_reg_range(MAX172XX_TEMP2, MAX172XX_TEMP2),
 	regmap_reg_range(MAX1720X_NXTABLE0, MAX1720X_NDEVICE_NAME4),
 };
 
 static const struct regmap_range max1720x_nvmem_deny[] = {
-	regmap_reg_range(0x00, 0x7F),
+	regmap_reg_range(0x00, 0x33),
+	regmap_reg_range(0x36, 0x3A),
+	regmap_reg_range(0x3C, 0x7F),
 	regmap_reg_range(0xE0, 0xFF),
 };
 
@@ -250,6 +260,7 @@ static const enum power_supply_property max1720x_battery_props[] = {
 	POWER_SUPPLY_PROP_TEMP,
 	POWER_SUPPLY_PROP_CURRENT_NOW,
 	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
 	POWER_SUPPLY_PROP_MODEL_NAME,
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
@@ -362,6 +373,10 @@ static int max1720x_battery_get_property(struct power_supply *psy,
 		ret = regmap_read(info->regmap, MAX172XX_AVG_CURRENT, &reg_val);
 		val->intval = max172xx_current_to_voltage(reg_val) / info->rsense;
 		break;
+	case POWER_SUPPLY_PROP_CHARGE_FULL:
+		ret = regmap_read(info->regmap, MAX172XX_FULL_CAP, &reg_val);
+		val->intval = max172xx_capacity_to_ps(reg_val);
+		break;
 	case POWER_SUPPLY_PROP_MODEL_NAME:
 		ret = regmap_read(info->regmap, MAX172XX_DEV_NAME, &reg_val);
 		reg_val = FIELD_GET(MAX172XX_DEV_NAME_TYPE_MASK, reg_val);
@@ -382,6 +397,54 @@ static int max1720x_battery_get_property(struct power_supply *psy,
 	return ret;
 }
 
+static int max1720x_read_temp(struct device *dev, u8 reg, char *buf)
+{
+	struct power_supply *psy = dev_get_drvdata(dev);
+	struct max1720x_device_info *info = power_supply_get_drvdata(psy);
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(info->regmap_nv, reg, &val);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Temperature in degrees Celsius starting at absolute zero, -273C or
+	 * 0K with an LSb of 0.1C
+	 */
+	return sysfs_emit(buf, "%d\n", val - 2730);
+}
+
+static ssize_t temp_ain1_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	return max1720x_read_temp(dev, MAX172XX_TEMP1, buf);
+}
+
+static ssize_t temp_ain2_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	return max1720x_read_temp(dev, MAX172XX_TEMP2, buf);
+}
+
+static ssize_t temp_int_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	return max1720x_read_temp(dev, MAX172XX_INT_TEMP, buf);
+}
+
+static DEVICE_ATTR_RO(temp_ain1);
+static DEVICE_ATTR_RO(temp_ain2);
+static DEVICE_ATTR_RO(temp_int);
+
+static struct attribute *max1720x_attrs[] = {
+	&dev_attr_temp_ain1.attr,
+	&dev_attr_temp_ain2.attr,
+	&dev_attr_temp_int.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(max1720x);
+
 static
 int max1720x_nvmem_reg_read(void *priv, unsigned int off, void *val, size_t len)
 {
@@ -482,6 +545,7 @@ static int max1720x_probe(struct i2c_client *client)
 
 	psy_cfg.drv_data = info;
 	psy_cfg.fwnode = dev_fwnode(dev);
+	psy_cfg.attr_grp = max1720x_groups;
 	i2c_set_clientdata(client, info);
 	info->regmap = devm_regmap_init_i2c(client, &max1720x_regmap_cfg);
 	if (IS_ERR(info->regmap))
diff --git a/drivers/power/supply/mm8013.c b/drivers/power/supply/mm8013.c
index 5bcfaeeda3db..4adf2acc2779 100644
--- a/drivers/power/supply/mm8013.c
+++ b/drivers/power/supply/mm8013.c
@@ -90,7 +90,7 @@ static int mm8013_get_property(struct power_supply *psy,
 			       enum power_supply_property psp,
 			       union power_supply_propval *val)
 {
-	struct mm8013_chip *chip = psy->drv_data;
+	struct mm8013_chip *chip = power_supply_get_drvdata(psy);
 	int ret = 0;
 	u32 regval;
 
diff --git a/drivers/power/supply/olpc_battery.c b/drivers/power/supply/olpc_battery.c
index 9f60094a5599..849f63e89ba0 100644
--- a/drivers/power/supply/olpc_battery.c
+++ b/drivers/power/supply/olpc_battery.c
@@ -527,7 +527,7 @@ static enum power_supply_property olpc_xo15_bat_props[] = {
 #define EEPROM_SIZE	(EEPROM_END - EEPROM_START)
 
 static ssize_t olpc_bat_eeprom_read(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr, char *buf, loff_t off, size_t count)
+		const struct bin_attribute *attr, char *buf, loff_t off, size_t count)
 {
 	uint8_t ec_byte;
 	int ret;
@@ -547,13 +547,13 @@ static ssize_t olpc_bat_eeprom_read(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute olpc_bat_eeprom = {
+static const struct bin_attribute olpc_bat_eeprom = {
 	.attr = {
 		.name = "eeprom",
 		.mode = S_IRUGO,
 	},
 	.size = EEPROM_SIZE,
-	.read = olpc_bat_eeprom_read,
+	.read_new = olpc_bat_eeprom_read,
 };
 
 /* Allow userspace to see the specific error value pulled from the EC */
@@ -584,15 +584,14 @@ static struct attribute *olpc_bat_sysfs_attrs[] = {
 	NULL
 };
 
-static struct bin_attribute *olpc_bat_sysfs_bin_attrs[] = {
+static const struct bin_attribute *const olpc_bat_sysfs_bin_attrs[] = {
 	&olpc_bat_eeprom,
 	NULL
 };
 
 static const struct attribute_group olpc_bat_sysfs_group = {
 	.attrs = olpc_bat_sysfs_attrs,
-	.bin_attrs = olpc_bat_sysfs_bin_attrs,
-
+	.bin_attrs_new = olpc_bat_sysfs_bin_attrs,
 };
 
 static const struct attribute_group *olpc_bat_sysfs_groups[] = {
diff --git a/drivers/power/supply/power_supply.h b/drivers/power/supply/power_supply.h
index 7434a6f24775..8f6a2d44b996 100644
--- a/drivers/power/supply/power_supply.h
+++ b/drivers/power/supply/power_supply.h
@@ -9,24 +9,55 @@
  *  Modified: 2004, Oct     Szabolcs Gyurko
  */
 
+#include <linux/lockdep.h>
+
 struct device;
 struct device_type;
 struct power_supply;
 
 extern int power_supply_property_is_writeable(struct power_supply *psy,
 					      enum power_supply_property psp);
+extern bool power_supply_has_property(struct power_supply *psy,
+				      enum power_supply_property psp);
+extern bool power_supply_ext_has_property(const struct power_supply_ext *ext,
+					  enum power_supply_property psp);
+
+struct power_supply_ext_registration {
+	struct list_head list_head;
+	const struct power_supply_ext *ext;
+	struct device *dev;
+	void *data;
+};
+
+/* Make sure that the macro is a single expression */
+#define power_supply_for_each_extension(pos, psy)			\
+	if ( ({ lockdep_assert_held(&(psy)->extensions_sem); 0; }) )	\
+		;							\
+	else								\
+		list_for_each_entry(pos, &(psy)->extensions, list_head)	\
 
 #ifdef CONFIG_SYSFS
 
 extern void __init power_supply_init_attrs(void);
 extern int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env);
 extern const struct attribute_group *power_supply_attr_groups[];
+extern int power_supply_sysfs_add_extension(struct power_supply *psy,
+					    const struct power_supply_ext *ext,
+					    struct device *dev);
+extern void power_supply_sysfs_remove_extension(struct power_supply *psy,
+						const struct power_supply_ext *ext);
 
 #else
 
 static inline void power_supply_init_attrs(void) {}
 #define power_supply_attr_groups NULL
 #define power_supply_uevent NULL
+static inline int power_supply_sysfs_add_extension(struct power_supply *psy,
+						   const struct power_supply_ext *ext,
+						   struct device *dev)
+{ return 0; }
+static inline void power_supply_sysfs_remove_extension(struct power_supply *psy,
+						       const struct power_supply_ext *ext) {}
 
 #endif /* CONFIG_SYSFS */
 
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 16085eff0084..d0bb52a7a036 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -66,21 +66,19 @@ static bool __power_supply_is_supplied_by(struct power_supply *supplier,
 	return false;
 }
 
-static int __power_supply_changed_work(struct device *dev, void *data)
+static int __power_supply_changed_work(struct power_supply *pst, void *data)
 {
 	struct power_supply *psy = data;
-	struct power_supply *pst = dev_get_drvdata(dev);
 
-	if (__power_supply_is_supplied_by(psy, pst)) {
-		if (pst->desc->external_power_changed)
-			pst->desc->external_power_changed(pst);
-	}
+	if (__power_supply_is_supplied_by(psy, pst))
+		power_supply_external_power_changed(pst);
 
 	return 0;
 }
 
 static void power_supply_changed_work(struct work_struct *work)
 {
+	int ret;
 	unsigned long flags;
 	struct power_supply *psy = container_of(work, struct power_supply,
 						changed_work);
@@ -88,6 +86,16 @@ static void power_supply_changed_work(struct work_struct *work)
 	dev_dbg(&psy->dev, "%s\n", __func__);
 
 	spin_lock_irqsave(&psy->changed_lock, flags);
+
+	if (unlikely(psy->update_groups)) {
+		psy->update_groups = false;
+		spin_unlock_irqrestore(&psy->changed_lock, flags);
+		ret = sysfs_update_groups(&psy->dev.kobj, power_supply_dev_type.groups);
+		if (ret)
+			dev_warn(&psy->dev, "failed to update sysfs groups: %pe\n", ERR_PTR(ret));
+		spin_lock_irqsave(&psy->changed_lock, flags);
+	}
+
 	/*
 	 * Check 'changed' here to avoid issues due to race between
 	 * power_supply_changed() and this routine. In worst case
@@ -98,7 +106,7 @@ static void power_supply_changed_work(struct work_struct *work)
 	if (likely(psy->changed)) {
 		psy->changed = false;
 		spin_unlock_irqrestore(&psy->changed_lock, flags);
-		power_supply_for_each_device(psy, __power_supply_changed_work);
+		power_supply_for_each_psy(psy, __power_supply_changed_work);
 		power_supply_update_leds(psy);
 		blocking_notifier_call_chain(&power_supply_notifier,
 				PSY_EVENT_PROP_CHANGED, psy);
@@ -116,11 +124,29 @@ static void power_supply_changed_work(struct work_struct *work)
 	spin_unlock_irqrestore(&psy->changed_lock, flags);
 }
 
-int power_supply_for_each_device(void *data, int (*fn)(struct device *dev, void *data))
+struct psy_for_each_psy_cb_data {
+	int (*fn)(struct power_supply *psy, void *data);
+	void *data;
+};
+
+static int psy_for_each_psy_cb(struct device *dev, void *data)
 {
-	return class_for_each_device(&power_supply_class, NULL, data, fn);
+	struct psy_for_each_psy_cb_data *cb_data = data;
+	struct power_supply *psy = dev_to_psy(dev);
+
+	return cb_data->fn(psy, cb_data->data);
 }
-EXPORT_SYMBOL_GPL(power_supply_for_each_device);
+
+int power_supply_for_each_psy(void *data, int (*fn)(struct power_supply *psy, void *data))
+{
+	struct psy_for_each_psy_cb_data cb_data = {
+		.fn = fn,
+		.data = data,
+	};
+
+	return class_for_each_device(&power_supply_class, NULL, &cb_data, psy_for_each_psy_cb);
+}
+EXPORT_SYMBOL_GPL(power_supply_for_each_psy);
 
 void power_supply_changed(struct power_supply *psy)
 {
@@ -166,11 +192,10 @@ static void power_supply_deferred_register_work(struct work_struct *work)
 }
 
 #ifdef CONFIG_OF
-static int __power_supply_populate_supplied_from(struct device *dev,
+static int __power_supply_populate_supplied_from(struct power_supply *epsy,
 						 void *data)
 {
 	struct power_supply *psy = data;
-	struct power_supply *epsy = dev_get_drvdata(dev);
 	struct device_node *np;
 	int i = 0;
 
@@ -197,20 +222,19 @@ static int power_supply_populate_supplied_from(struct power_supply *psy)
 {
 	int error;
 
-	error = power_supply_for_each_device(psy, __power_supply_populate_supplied_from);
+	error = power_supply_for_each_psy(psy, __power_supply_populate_supplied_from);
 
 	dev_dbg(&psy->dev, "%s %d\n", __func__, error);
 
 	return error;
 }
 
-static int  __power_supply_find_supply_from_node(struct device *dev,
+static int  __power_supply_find_supply_from_node(struct power_supply *epsy,
 						 void *data)
 {
 	struct device_node *np = data;
-	struct power_supply *epsy = dev_get_drvdata(dev);
 
-	/* returning non-zero breaks out of power_supply_for_each_device loop */
+	/* returning non-zero breaks out of power_supply_for_each_psy loop */
 	if (epsy->of_node == np)
 		return 1;
 
@@ -222,16 +246,16 @@ static int power_supply_find_supply_from_node(struct device_node *supply_node)
 	int error;
 
 	/*
-	 * power_supply_for_each_device() either returns its own errors or values
+	 * power_supply_for_each_psy() either returns its own errors or values
 	 * returned by __power_supply_find_supply_from_node().
 	 *
 	 * __power_supply_find_supply_from_node() will return 0 (no match)
 	 * or 1 (match).
 	 *
-	 * We return 0 if power_supply_for_each_device() returned 1, -EPROBE_DEFER if
+	 * We return 0 if power_supply_for_each_psy() returned 1, -EPROBE_DEFER if
 	 * it returned 0, or error as returned by it.
 	 */
-	error = power_supply_for_each_device(supply_node, __power_supply_find_supply_from_node);
+	error = power_supply_for_each_psy(supply_node, __power_supply_find_supply_from_node);
 
 	return error ? (error == 1 ? 0 : error) : -EPROBE_DEFER;
 }
@@ -316,10 +340,9 @@ struct psy_am_i_supplied_data {
 	unsigned int count;
 };
 
-static int __power_supply_am_i_supplied(struct device *dev, void *_data)
+static int __power_supply_am_i_supplied(struct power_supply *epsy, void *_data)
 {
 	union power_supply_propval ret = {0,};
-	struct power_supply *epsy = dev_get_drvdata(dev);
 	struct psy_am_i_supplied_data *data = _data;
 
 	if (__power_supply_is_supplied_by(epsy, data->psy)) {
@@ -337,7 +360,7 @@ int power_supply_am_i_supplied(struct power_supply *psy)
 	struct psy_am_i_supplied_data data = { psy, 0 };
 	int error;
 
-	error = power_supply_for_each_device(&data, __power_supply_am_i_supplied);
+	error = power_supply_for_each_psy(&data, __power_supply_am_i_supplied);
 
 	dev_dbg(&psy->dev, "%s count %u err %d\n", __func__, data.count, error);
 
@@ -348,10 +371,9 @@ int power_supply_am_i_supplied(struct power_supply *psy)
 }
 EXPORT_SYMBOL_GPL(power_supply_am_i_supplied);
 
-static int __power_supply_is_system_supplied(struct device *dev, void *data)
+static int __power_supply_is_system_supplied(struct power_supply *psy, void *data)
 {
 	union power_supply_propval ret = {0,};
-	struct power_supply *psy = dev_get_drvdata(dev);
 	unsigned int *count = data;
 
 	if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_SCOPE, &ret))
@@ -372,7 +394,7 @@ int power_supply_is_system_supplied(void)
 	int error;
 	unsigned int count = 0;
 
-	error = power_supply_for_each_device(&count, __power_supply_is_system_supplied);
+	error = power_supply_for_each_psy(&count, __power_supply_is_system_supplied);
 
 	/*
 	 * If no system scope power class device was found at all, most probably we
@@ -391,9 +413,8 @@ struct psy_get_supplier_prop_data {
 	union power_supply_propval *val;
 };
 
-static int __power_supply_get_supplier_property(struct device *dev, void *_data)
+static int __power_supply_get_supplier_property(struct power_supply *epsy, void *_data)
 {
-	struct power_supply *epsy = dev_get_drvdata(dev);
 	struct psy_get_supplier_prop_data *data = _data;
 
 	if (__power_supply_is_supplied_by(epsy, data->psy))
@@ -418,7 +439,7 @@ int power_supply_get_property_from_supplier(struct power_supply *psy,
 	 * This function is not intended for use with a supply with multiple
 	 * suppliers, we simply pick the first supply to report the psp.
 	 */
-	ret = power_supply_for_each_device(&data, __power_supply_get_supplier_property);
+	ret = power_supply_for_each_psy(&data, __power_supply_get_supplier_property);
 	if (ret < 0)
 		return ret;
 	if (ret == 0)
@@ -444,7 +465,7 @@ EXPORT_SYMBOL_GPL(power_supply_set_battery_charged);
 static int power_supply_match_device_by_name(struct device *dev, const void *data)
 {
 	const char *name = data;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 
 	return strcmp(psy->desc->name, name) == 0;
 }
@@ -467,7 +488,7 @@ struct power_supply *power_supply_get_by_name(const char *name)
 					       power_supply_match_device_by_name);
 
 	if (dev) {
-		psy = dev_get_drvdata(dev);
+		psy = dev_to_psy(dev);
 		atomic_inc(&psy->use_cnt);
 	}
 
@@ -524,7 +545,7 @@ struct power_supply *power_supply_get_by_phandle(struct device_node *np,
 	of_node_put(power_supply_np);
 
 	if (dev) {
-		psy = dev_get_drvdata(dev);
+		psy = dev_to_psy(dev);
 		atomic_inc(&psy->use_cnt);
 	}
 
@@ -1180,8 +1201,8 @@ bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info,
 }
 EXPORT_SYMBOL_GPL(power_supply_battery_bti_in_range);
 
-static bool psy_has_property(const struct power_supply_desc *psy_desc,
-			     enum power_supply_property psp)
+static bool psy_desc_has_property(const struct power_supply_desc *psy_desc,
+				  enum power_supply_property psp)
 {
 	bool found = false;
 	int i;
@@ -1196,17 +1217,57 @@ static bool psy_has_property(const struct power_supply_desc *psy_desc,
 	return found;
 }
 
+bool power_supply_ext_has_property(const struct power_supply_ext *psy_ext,
+				   enum power_supply_property psp)
+{
+	int i;
+
+	for (i = 0; i < psy_ext->num_properties; i++)
+		if (psy_ext->properties[i] == psp)
+			return true;
+
+	return false;
+}
+
+bool power_supply_has_property(struct power_supply *psy,
+			       enum power_supply_property psp)
+{
+	struct power_supply_ext_registration *reg;
+
+	if (psy_desc_has_property(psy->desc, psp))
+		return true;
+
+	if (power_supply_battery_info_has_prop(psy->battery_info, psp))
+		return true;
+
+	power_supply_for_each_extension(reg, psy) {
+		if (power_supply_ext_has_property(reg->ext, psp))
+			return true;
+	}
+
+	return false;
+}
+
 int power_supply_get_property(struct power_supply *psy,
 			    enum power_supply_property psp,
 			    union power_supply_propval *val)
 {
+	struct power_supply_ext_registration *reg;
+
 	if (atomic_read(&psy->use_cnt) <= 0) {
 		if (!psy->initialized)
 			return -EAGAIN;
 		return -ENODEV;
 	}
 
-	if (psy_has_property(psy->desc, psp))
+	scoped_guard(rwsem_read, &psy->extensions_sem) {
+		power_supply_for_each_extension(reg, psy) {
+			if (power_supply_ext_has_property(reg->ext, psp))
+				return reg->ext->get_property(psy, reg->ext, reg->data, psp, val);
+		}
+	}
+
+	if (psy_desc_has_property(psy->desc, psp))
 		return psy->desc->get_property(psy, psp, val);
 	else if (power_supply_battery_info_has_prop(psy->battery_info, psp))
 		return power_supply_battery_info_get_prop(psy->battery_info, psp, val);
@@ -1219,7 +1280,24 @@ int power_supply_set_property(struct power_supply *psy,
 			    enum power_supply_property psp,
 			    const union power_supply_propval *val)
 {
-	if (atomic_read(&psy->use_cnt) <= 0 || !psy->desc->set_property)
+	struct power_supply_ext_registration *reg;
+
+	if (atomic_read(&psy->use_cnt) <= 0)
+		return -ENODEV;
+
+	scoped_guard(rwsem_read, &psy->extensions_sem) {
+		power_supply_for_each_extension(reg, psy) {
+			if (power_supply_ext_has_property(reg->ext, psp)) {
+				if (reg->ext->set_property)
+					return reg->ext->set_property(psy, reg->ext, reg->data,
+								      psp, val);
+				else
+					return -ENODEV;
+			}
+		}
+	}
+
+	if (!psy->desc->set_property)
 		return -ENODEV;
 
 	return psy->desc->set_property(psy, psp, val);
@@ -1229,7 +1307,22 @@ EXPORT_SYMBOL_GPL(power_supply_set_property);
 int power_supply_property_is_writeable(struct power_supply *psy,
 					enum power_supply_property psp)
 {
-	return psy->desc->property_is_writeable && psy->desc->property_is_writeable(psy, psp);
+	struct power_supply_ext_registration *reg;
+
+	power_supply_for_each_extension(reg, psy) {
+		if (power_supply_ext_has_property(reg->ext, psp)) {
+			if (reg->ext->property_is_writeable)
+				return reg->ext->property_is_writeable(psy, reg->ext,
+								       reg->data, psp);
+			else
+				return 0;
+		}
+	}
+
+	if (!psy->desc->property_is_writeable)
+		return 0;
+
+	return psy->desc->property_is_writeable(psy, psp);
 }
 
 void power_supply_external_power_changed(struct power_supply *psy)
@@ -1248,6 +1341,88 @@ int power_supply_powers(struct power_supply *psy, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(power_supply_powers);
 
+static int power_supply_update_sysfs_and_hwmon(struct power_supply *psy)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&psy->changed_lock, flags);
+	psy->update_groups = true;
+	spin_unlock_irqrestore(&psy->changed_lock, flags);
+
+	power_supply_changed(psy);
+
+	power_supply_remove_hwmon_sysfs(psy);
+	return power_supply_add_hwmon_sysfs(psy);
+}
+
+int power_supply_register_extension(struct power_supply *psy, const struct power_supply_ext *ext,
+				    struct device *dev, void *data)
+{
+	struct power_supply_ext_registration *reg;
+	size_t i;
+	int ret;
+
+	if (!psy || !dev || !ext || !ext->name || !ext->properties || !ext->num_properties)
+		return -EINVAL;
+
+	guard(rwsem_write)(&psy->extensions_sem);
+
+	power_supply_for_each_extension(reg, psy)
+		if (strcmp(ext->name, reg->ext->name) == 0)
+			return -EEXIST;
+
+	for (i = 0; i < ext->num_properties; i++)
+		if (power_supply_has_property(psy, ext->properties[i]))
+			return -EEXIST;
+
+	reg = kmalloc(sizeof(*reg), GFP_KERNEL);
+	if (!reg)
+		return -ENOMEM;
+
+	reg->ext = ext;
+	reg->dev = dev;
+	reg->data = data;
+	list_add(&reg->list_head, &psy->extensions);
+
+	ret = power_supply_sysfs_add_extension(psy, ext, dev);
+	if (ret)
+		goto sysfs_add_failed;
+
+	ret = power_supply_update_sysfs_and_hwmon(psy);
+	if (ret)
+		goto sysfs_hwmon_failed;
+
+	return 0;
+
+sysfs_hwmon_failed:
+	power_supply_sysfs_remove_extension(psy, ext);
+sysfs_add_failed:
+	list_del(&reg->list_head);
+	kfree(reg);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(power_supply_register_extension);
+
+void power_supply_unregister_extension(struct power_supply *psy, const struct power_supply_ext *ext)
+{
+	struct power_supply_ext_registration *reg;
+
+	guard(rwsem_write)(&psy->extensions_sem);
+
+	power_supply_for_each_extension(reg, psy) {
+		if (reg->ext == ext) {
+			list_del(&reg->list_head);
+			power_supply_sysfs_remove_extension(psy, ext);
+			kfree(reg);
+			power_supply_update_sysfs_and_hwmon(psy);
+			return;
+		}
+	}
+
+	dev_warn(&psy->dev, "Trying to unregister invalid extension");
+}
+EXPORT_SYMBOL_GPL(power_supply_unregister_extension);
+
 static void power_supply_dev_release(struct device *dev)
 {
 	struct power_supply *psy = to_power_supply(dev);
@@ -1300,7 +1475,7 @@ static int psy_register_thermal(struct power_supply *psy)
 		return 0;
 
 	/* Register battery zone device psy reports temperature */
-	if (psy_has_property(psy->desc, POWER_SUPPLY_PROP_TEMP)) {
+	if (psy_desc_has_property(psy->desc, POWER_SUPPLY_PROP_TEMP)) {
 		/* Prefer our hwmon device and avoid duplicates */
 		struct thermal_zone_params tzp = {
 			.no_hwmon = IS_ENABLED(CONFIG_POWER_SUPPLY_HWMON)
@@ -1402,6 +1577,9 @@ __power_supply_register(struct device *parent,
 	}
 
 	spin_lock_init(&psy->changed_lock);
+	init_rwsem(&psy->extensions_sem);
+	INIT_LIST_HEAD(&psy->extensions);
+
 	rc = device_add(dev);
 	if (rc)
 		goto device_add_failed;
@@ -1414,13 +1592,15 @@ __power_supply_register(struct device *parent,
 	if (rc)
 		goto register_thermal_failed;
 
-	rc = power_supply_create_triggers(psy);
-	if (rc)
-		goto create_triggers_failed;
+	scoped_guard(rwsem_read, &psy->extensions_sem) {
+		rc = power_supply_create_triggers(psy);
+		if (rc)
+			goto create_triggers_failed;
 
-	rc = power_supply_add_hwmon_sysfs(psy);
-	if (rc)
-		goto add_hwmon_sysfs_failed;
+		rc = power_supply_add_hwmon_sysfs(psy);
+		if (rc)
+			goto add_hwmon_sysfs_failed;
+	}
 
 	/*
 	 * Update use_cnt after any uevents (most notably from device_add()).
diff --git a/drivers/power/supply/power_supply_hwmon.c b/drivers/power/supply/power_supply_hwmon.c
index 01be04903d7d..95245e6a6baa 100644
--- a/drivers/power/supply/power_supply_hwmon.c
+++ b/drivers/power/supply/power_supply_hwmon.c
@@ -349,9 +349,28 @@ static const struct hwmon_chip_info power_supply_hwmon_chip_info = {
 	.info = power_supply_hwmon_info,
 };
 
+static const enum power_supply_property power_supply_hwmon_props[] = {
+	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_CURRENT_MAX,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_POWER_NOW,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TEMP_MAX,
+	POWER_SUPPLY_PROP_TEMP_MIN,
+	POWER_SUPPLY_PROP_TEMP_ALERT_MIN,
+	POWER_SUPPLY_PROP_TEMP_ALERT_MAX,
+	POWER_SUPPLY_PROP_TEMP_AMBIENT,
+	POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN,
+	POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX,
+	POWER_SUPPLY_PROP_VOLTAGE_AVG,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN,
+	POWER_SUPPLY_PROP_VOLTAGE_MAX,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+};
+
 int power_supply_add_hwmon_sysfs(struct power_supply *psy)
 {
-	const struct power_supply_desc *desc = psy->desc;
 	struct power_supply_hwmon *psyhw;
 	struct device *dev = &psy->dev;
 	struct device *hwmon;
@@ -377,32 +396,11 @@ int power_supply_add_hwmon_sysfs(struct power_supply *psy)
 		goto error;
 	}
 
-	for (i = 0; i < desc->num_properties; i++) {
-		const enum power_supply_property prop = desc->properties[i];
-
-		switch (prop) {
-		case POWER_SUPPLY_PROP_CURRENT_AVG:
-		case POWER_SUPPLY_PROP_CURRENT_MAX:
-		case POWER_SUPPLY_PROP_CURRENT_NOW:
-		case POWER_SUPPLY_PROP_POWER_AVG:
-		case POWER_SUPPLY_PROP_POWER_NOW:
-		case POWER_SUPPLY_PROP_TEMP:
-		case POWER_SUPPLY_PROP_TEMP_MAX:
-		case POWER_SUPPLY_PROP_TEMP_MIN:
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-		case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT:
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN:
-		case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX:
-		case POWER_SUPPLY_PROP_VOLTAGE_AVG:
-		case POWER_SUPPLY_PROP_VOLTAGE_MIN:
-		case POWER_SUPPLY_PROP_VOLTAGE_MAX:
-		case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+	for (i = 0; i < ARRAY_SIZE(power_supply_hwmon_props); i++) {
+		const enum power_supply_property prop = power_supply_hwmon_props[i];
+
+		if (power_supply_has_property(psy, prop))
 			set_bit(prop, psyhw->props);
-			break;
-		default:
-			break;
-		}
 	}
 
 	name = psy->desc->name;
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index 571de43fcca9..edb058c19c9c 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -99,6 +99,7 @@ static const char * const POWER_SUPPLY_HEALTH_TEXT[] = {
 	[POWER_SUPPLY_HEALTH_OVERHEAT]		    = "Overheat",
 	[POWER_SUPPLY_HEALTH_DEAD]		    = "Dead",
 	[POWER_SUPPLY_HEALTH_OVERVOLTAGE]	    = "Over voltage",
+	[POWER_SUPPLY_HEALTH_UNDERVOLTAGE]	    = "Under voltage",
 	[POWER_SUPPLY_HEALTH_UNSPEC_FAILURE]	    = "Unspecified failure",
 	[POWER_SUPPLY_HEALTH_COLD]		    = "Cold",
 	[POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE] = "Watchdog timer expire",
@@ -182,6 +183,8 @@ static struct power_supply_attr power_supply_attrs[] __ro_after_init = {
 	POWER_SUPPLY_ATTR(CHARGE_CONTROL_START_THRESHOLD),
 	POWER_SUPPLY_ATTR(CHARGE_CONTROL_END_THRESHOLD),
 	POWER_SUPPLY_ENUM_ATTR(CHARGE_BEHAVIOUR),
+	/* Same enum value texts as "charge_type" without the 's' at the end */
+	_POWER_SUPPLY_ENUM_ATTR(CHARGE_TYPES, POWER_SUPPLY_CHARGE_TYPE_TEXT),
 	POWER_SUPPLY_ATTR(INPUT_CURRENT_LIMIT),
 	POWER_SUPPLY_ATTR(INPUT_VOLTAGE_LIMIT),
 	POWER_SUPPLY_ATTR(INPUT_POWER_LIMIT),
@@ -237,23 +240,52 @@ static enum power_supply_property dev_attr_psp(struct device_attribute *attr)
 	return  to_ps_attr(attr) - power_supply_attrs;
 }
 
+static void power_supply_escape_spaces(const char *str, char *buf, size_t bufsize)
+{
+	strscpy(buf, str, bufsize);
+	strreplace(buf, ' ', '_');
+}
+
+static int power_supply_match_string(const char * const *array, size_t n, const char *s)
+{
+	int ret;
+
+	/* First try an exact match */
+	ret = __sysfs_match_string(array, n, s);
+	if (ret >= 0)
+		return ret;
+
+	/* Second round, try matching with spaces replaced by '_' */
+	for (size_t i = 0; i < n; i++) {
+		char buf[32];
+
+		power_supply_escape_spaces(array[i], buf, sizeof(buf));
+		if (sysfs_streq(buf, s))
+			return i;
+	}
+
+	return -EINVAL;
+}
+
 static ssize_t power_supply_show_enum_with_available(
 			struct device *dev, const char * const labels[], int label_count,
 			unsigned int available_values, int value, char *buf)
 {
 	bool match = false, available, active;
+	char escaped_label[32];
 	ssize_t count = 0;
 	int i;
 
 	for (i = 0; i < label_count; i++) {
 		available = available_values & BIT(i);
 		active = i == value;
+		power_supply_escape_spaces(labels[i], escaped_label, sizeof(escaped_label));
 
 		if (available && active) {
-			count += sysfs_emit_at(buf, count, "[%s] ", labels[i]);
+			count += sysfs_emit_at(buf, count, "[%s] ", escaped_label);
 			match = true;
 		} else if (available) {
-			count += sysfs_emit_at(buf, count, "%s ", labels[i]);
+			count += sysfs_emit_at(buf, count, "%s ", escaped_label);
 		}
 	}
 
@@ -268,11 +300,34 @@ static ssize_t power_supply_show_enum_with_available(
 	return count;
 }
 
-static ssize_t power_supply_show_property(struct device *dev,
-					  struct device_attribute *attr,
-					  char *buf) {
+static ssize_t power_supply_show_charge_behaviour(struct device *dev,
+						  struct power_supply *psy,
+						  union power_supply_propval *value,
+						  char *buf)
+{
+	struct power_supply_ext_registration *reg;
+
+	scoped_guard(rwsem_read, &psy->extensions_sem) {
+		power_supply_for_each_extension(reg, psy) {
+			if (power_supply_ext_has_property(reg->ext,
+							  POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR))
+				return power_supply_charge_behaviour_show(dev,
+						reg->ext->charge_behaviours,
+						value->intval, buf);
+		}
+	}
+
+	return power_supply_charge_behaviour_show(dev, psy->desc->charge_behaviours,
+						  value->intval, buf);
+}
+
+static ssize_t power_supply_format_property(struct device *dev,
+					    bool uevent,
+					    struct device_attribute *attr,
+					    char *buf)
+{
 	ssize_t ret;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	const struct power_supply_attr *ps_attr = to_ps_attr(attr);
 	enum power_supply_property psp = dev_attr_psp(attr);
 	union power_supply_propval value;
@@ -287,7 +342,7 @@ static ssize_t power_supply_show_property(struct device *dev,
 				dev_dbg_ratelimited(dev,
 					"driver has no data for `%s' property\n",
 					attr->attr.name);
-			else if (ret != -ENODEV && ret != -EAGAIN)
+			else if (ret != -ENODEV && ret != -EAGAIN && ret != -EINVAL)
 				dev_err_ratelimited(dev,
 					"driver failed to report `%s' property: %zd\n",
 					attr->attr.name, ret);
@@ -303,13 +358,21 @@ static ssize_t power_supply_show_property(struct device *dev,
 				psy->desc->usb_types, value.intval, buf);
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR:
-		ret = power_supply_charge_behaviour_show(dev, psy->desc->charge_behaviours,
-							 value.intval, buf);
+		if (uevent) /* no possible values in uevents */
+			goto default_format;
+		ret = power_supply_show_charge_behaviour(dev, psy, &value, buf);
+		break;
+	case POWER_SUPPLY_PROP_CHARGE_TYPES:
+		if (uevent) /* no possible values in uevents */
+			goto default_format;
+		ret = power_supply_charge_types_show(dev, psy->desc->charge_types,
+						     value.intval, buf);
 		break;
 	case POWER_SUPPLY_PROP_MODEL_NAME ... POWER_SUPPLY_PROP_SERIAL_NUMBER:
 		ret = sysfs_emit(buf, "%s\n", value.strval);
 		break;
 	default:
+default_format:
 		if (ps_attr->text_values_len > 0 &&
 				value.intval < ps_attr->text_values_len && value.intval >= 0) {
 			ret = sysfs_emit(buf, "%s\n", ps_attr->text_values[value.intval]);
@@ -321,19 +384,26 @@ static ssize_t power_supply_show_property(struct device *dev,
 	return ret;
 }
 
+static ssize_t power_supply_show_property(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	return power_supply_format_property(dev, false, attr, buf);
+}
+
 static ssize_t power_supply_store_property(struct device *dev,
 					   struct device_attribute *attr,
 					   const char *buf, size_t count) {
 	ssize_t ret;
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	const struct power_supply_attr *ps_attr = to_ps_attr(attr);
 	enum power_supply_property psp = dev_attr_psp(attr);
 	union power_supply_propval value;
 
 	ret = -EINVAL;
 	if (ps_attr->text_values_len > 0) {
-		ret = __sysfs_match_string(ps_attr->text_values,
-					   ps_attr->text_values_len, buf);
+		ret = power_supply_match_string(ps_attr->text_values,
+						ps_attr->text_values_len, buf);
 	}
 
 	/*
@@ -364,9 +434,8 @@ static umode_t power_supply_attr_is_visible(struct kobject *kobj,
 					   int attrno)
 {
 	struct device *dev = kobj_to_dev(kobj);
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
-	int i;
 
 	if (!power_supply_attrs[attrno].prop_name)
 		return 0;
@@ -374,19 +443,13 @@ static umode_t power_supply_attr_is_visible(struct kobject *kobj,
 	if (attrno == POWER_SUPPLY_PROP_TYPE)
 		return mode;
 
-	for (i = 0; i < psy->desc->num_properties; i++) {
-		int property = psy->desc->properties[i];
-
-		if (property == attrno) {
-			if (power_supply_property_is_writeable(psy, property) > 0)
-				mode |= S_IWUSR;
+	guard(rwsem_read)(&psy->extensions_sem);
 
-			return mode;
-		}
-	}
-
-	if (power_supply_battery_info_has_prop(psy->battery_info, attrno))
+	if (power_supply_has_property(psy, attrno)) {
+		if (power_supply_property_is_writeable(psy, attrno) > 0)
+			mode |= S_IWUSR;
 		return mode;
+	}
 
 	return 0;
 }
@@ -396,8 +459,18 @@ static const struct attribute_group power_supply_attr_group = {
 	.is_visible = power_supply_attr_is_visible,
 };
 
+static struct attribute *power_supply_extension_attrs[] = {
+	NULL
+};
+
+static const struct attribute_group power_supply_extension_group = {
+	.name = "extensions",
+	.attrs = power_supply_extension_attrs,
+};
+
 const struct attribute_group *power_supply_attr_groups[] = {
 	&power_supply_attr_group,
+	&power_supply_extension_group,
 	NULL
 };
 
@@ -437,8 +510,8 @@ static int add_prop_uevent(const struct device *dev, struct kobj_uevent_env *env
 	pwr_attr = &power_supply_attrs[prop];
 	dev_attr = &pwr_attr->dev_attr;
 
-	ret = power_supply_show_property((struct device *)dev, dev_attr, prop_buf);
-	if (ret == -ENODEV || ret == -ENODATA) {
+	ret = power_supply_format_property((struct device *)dev, true, dev_attr, prop_buf);
+	if (ret == -ENODEV || ret == -ENODATA || ret == -EINVAL) {
 		/*
 		 * When a battery is absent, we expect -ENODEV. Don't abort;
 		 * send the uevent with at least the PRESENT=0 property
@@ -459,11 +532,7 @@ static int add_prop_uevent(const struct device *dev, struct kobj_uevent_env *env
 
 int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env)
 {
-	const struct power_supply *psy = dev_get_drvdata(dev);
-	const enum power_supply_property *battery_props =
-		power_supply_battery_info_properties;
-	unsigned long psy_drv_properties[POWER_SUPPLY_ATTR_CNT /
-					 sizeof(unsigned long) + 1] = {0};
+	const struct power_supply *psy = dev_to_psy(dev);
 	int ret = 0, j;
 	char *prop_buf;
 
@@ -491,22 +560,8 @@ int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	if (ret)
 		goto out;
 
-	for (j = 0; j < psy->desc->num_properties; j++) {
-		set_bit(psy->desc->properties[j], psy_drv_properties);
-		ret = add_prop_uevent(dev, env, psy->desc->properties[j],
-				      prop_buf);
-		if (ret)
-			goto out;
-	}
-
-	for (j = 0; j < power_supply_battery_info_properties_size; j++) {
-		if (test_bit(battery_props[j], psy_drv_properties))
-			continue;
-		if (!power_supply_battery_info_has_prop(psy->battery_info,
-				battery_props[j]))
-			continue;
-		ret = add_prop_uevent(dev, env, battery_props[j],
-			      prop_buf);
+	for (j = 0; j < POWER_SUPPLY_ATTR_CNT; j++) {
+		ret = add_prop_uevent(dev, env, j, prop_buf);
 		if (ret)
 			goto out;
 	}
@@ -542,3 +597,44 @@ int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const
 	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(power_supply_charge_behaviour_parse);
+
+ssize_t power_supply_charge_types_show(struct device *dev,
+				       unsigned int available_types,
+				       enum power_supply_charge_type current_type,
+				       char *buf)
+{
+	return power_supply_show_enum_with_available(
+				dev, POWER_SUPPLY_CHARGE_TYPE_TEXT,
+				ARRAY_SIZE(POWER_SUPPLY_CHARGE_TYPE_TEXT),
+				available_types, current_type, buf);
+}
+EXPORT_SYMBOL_GPL(power_supply_charge_types_show);
+
+int power_supply_charge_types_parse(unsigned int available_types, const char *buf)
+{
+	int i = power_supply_match_string(POWER_SUPPLY_CHARGE_TYPE_TEXT,
+					  ARRAY_SIZE(POWER_SUPPLY_CHARGE_TYPE_TEXT),
+					  buf);
+
+	if (i < 0)
+		return i;
+
+	if (available_types & BIT(i))
+		return i;
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(power_supply_charge_types_parse);
+
+int power_supply_sysfs_add_extension(struct power_supply *psy, const struct power_supply_ext *ext,
+				     struct device *dev)
+{
+	return sysfs_add_link_to_group(&psy->dev.kobj, power_supply_extension_group.name,
+				       &dev->kobj, ext->name);
+}
+
+void power_supply_sysfs_remove_extension(struct power_supply *psy,
+					 const struct power_supply_ext *ext)
+{
+	sysfs_remove_link_from_group(&psy->dev.kobj, power_supply_extension_group.name, ext->name);
+}
diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c
index a6c204c08232..6f3d0413b1c1 100644
--- a/drivers/power/supply/sbs-battery.c
+++ b/drivers/power/supply/sbs-battery.c
@@ -21,6 +21,7 @@
 #include <linux/power_supply.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
+#include <linux/string_choices.h>
 
 enum {
 	REG_MANUFACTURER_DATA,
@@ -320,8 +321,8 @@ static int sbs_update_presence(struct sbs_info *chip, bool is_present)
 		client->flags &= ~I2C_CLIENT_PEC;
 	}
 
-	dev_dbg(&client->dev, "PEC: %s\n", (client->flags & I2C_CLIENT_PEC) ?
-		"enabled" : "disabled");
+	dev_dbg(&client->dev, "PEC: %s\n",
+		str_enabled_disabled(client->flags & I2C_CLIENT_PEC));
 
 	if (!chip->is_present && is_present && !chip->charger_broadcasts)
 		sbs_disable_charger_broadcasts(chip);
diff --git a/drivers/power/supply/stc3117_fuel_gauge.c b/drivers/power/supply/stc3117_fuel_gauge.c
new file mode 100644
index 000000000000..a1bc5970370a
--- /dev/null
+++ b/drivers/power/supply/stc3117_fuel_gauge.c
@@ -0,0 +1,612 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * stc3117_fuel_gauge.c - STMicroelectronics STC3117 Fuel Gauge Driver
+ *
+ * Copyright (c) 2024 Silicon Signals Pvt Ltd.
+ * Author:      Hardevsinh Palaniya <hardevsinh.palaniya@siliconsignals.io>
+ *              Bhavin Sharma <bhavin.sharma@siliconsignals.io>
+ */
+
+#include <linux/crc8.h>
+#include <linux/devm-helpers.h>
+#include <linux/i2c.h>
+#include <linux/power_supply.h>
+#include <linux/regmap.h>
+#include <linux/workqueue.h>
+
+#define STC3117_ADDR_MODE                      0x00
+#define STC3117_ADDR_CTRL                      0x01
+#define STC3117_ADDR_SOC_L                     0x02
+#define STC3117_ADDR_SOC_H                     0x03
+#define STC3117_ADDR_COUNTER_L                 0x04
+#define STC3117_ADDR_COUNTER_H                 0x05
+#define STC3117_ADDR_CURRENT_L                 0x06
+#define STC3117_ADDR_CURRENT_H                 0x07
+#define STC3117_ADDR_VOLTAGE_L                 0x08
+#define STC3117_ADDR_VOLTAGE_H                 0x09
+#define STC3117_ADDR_TEMPERATURE               0x0A
+#define STC3117_ADDR_AVG_CURRENT_L             0x0B
+#define STC3117_ADDR_AVG_CURRENT_H             0x0C
+#define STC3117_ADDR_OCV_L                     0x0D
+#define STC3117_ADDR_OCV_H                     0x0E
+#define STC3117_ADDR_CC_CNF_L                  0x0F
+#define STC3117_ADDR_CC_CNF_H                  0x10
+#define STC3117_ADDR_VM_CNF_L                  0x11
+#define STC3117_ADDR_VM_CNF_H                  0x12
+#define STC3117_ADDR_ALARM_soc                 0x13
+#define STC3117_ADDR_ALARM_VOLTAGE             0x14
+#define STC3117_ADDR_ID                        0x18
+#define STC3117_ADDR_CC_ADJ_L			0x1B
+#define STC3117_ADDR_CC_ADJ_H			0x1C
+#define STC3117_ADDR_VM_ADJ_L			0x1D
+#define STC3117_ADDR_VM_ADJ_H			0x1E
+#define STC3117_ADDR_RAM			0x20
+#define STC3117_ADDR_OCV_TABLE			0x30
+#define STC3117_ADDR_SOC_TABLE			0x30
+
+/* Bit mask definition */
+#define STC3117_ID			        0x16
+#define STC3117_MIXED_MODE			0x00
+#define STC3117_VMODE				BIT(0)
+#define STC3117_GG_RUN				BIT(4)
+#define STC3117_CC_MODE			BIT(5)
+#define STC3117_BATFAIL			BIT(3)
+#define STC3117_PORDET				BIT(4)
+#define STC3117_RAM_SIZE			16
+#define STC3117_OCV_TABLE_SIZE			16
+#define STC3117_RAM_TESTWORD			0x53A9
+#define STC3117_SOFT_RESET                     0x11
+#define STC3117_NOMINAL_CAPACITY		2600
+
+#define VOLTAGE_LSB_VALUE			9011
+#define CURRENT_LSB_VALUE			24084
+#define APP_CUTOFF_VOLTAGE			2500
+#define MAX_HRSOC				51200
+#define MAX_SOC				1000
+#define CHG_MIN_CURRENT			200
+#define CHG_END_CURRENT			20
+#define APP_MIN_CURRENT			(-5)
+#define BATTERY_FULL				95
+#define CRC8_POLYNOMIAL			0x07
+#define CRC8_INIT				0x00
+
+DECLARE_CRC8_TABLE(stc3117_crc_table);
+
+enum stc3117_state {
+	STC3117_INIT,
+	STC3117_RUNNING,
+	STC3117_POWERDN,
+};
+
+/* Default ocv curve Li-ion battery */
+static const int ocv_value[16] = {
+	3400, 3582, 3669, 3676, 3699, 3737, 3757, 3774,
+	3804, 3844, 3936, 3984, 4028, 4131, 4246, 4320
+};
+
+union stc3117_internal_ram {
+	u8 ram_bytes[STC3117_RAM_SIZE];
+	struct {
+	u16 testword;   /* 0-1    Bytes */
+	u16 hrsoc;      /* 2-3    Bytes */
+	u16 cc_cnf;     /* 4-5    Bytes */
+	u16 vm_cnf;     /* 6-7    Bytes */
+	u8 soc;         /* 8      Byte  */
+	u8 state;       /* 9      Byte  */
+	u8 unused[5];   /* 10-14  Bytes */
+	u8 crc;         /* 15     Byte  */
+	} reg;
+};
+
+struct stc3117_battery_info {
+	int voltage_min_mv;
+	int voltage_max_mv;
+	int battery_capacity_mah;
+	int sense_resistor;
+};
+
+struct stc3117_data {
+	struct i2c_client *client;
+	struct regmap *regmap;
+	struct delayed_work update_work;
+	struct power_supply *battery;
+	union stc3117_internal_ram ram_data;
+	struct stc3117_battery_info battery_info;
+
+	u8 soc_tab[16];
+	int cc_cnf;
+	int vm_cnf;
+	int cc_adj;
+	int vm_adj;
+	int avg_current;
+	int avg_voltage;
+	int batt_current;
+	int voltage;
+	int temp;
+	int soc;
+	int ocv;
+	int hrsoc;
+	int presence;
+};
+
+static int stc3117_convert(int value, int factor)
+{
+	value = (value * factor) / 4096;
+	return value * 1000;
+}
+
+static int stc3117_get_battery_data(struct stc3117_data *data)
+{
+	u8 reg_list[16];
+	u8 data_adjust[4];
+	int value, mode;
+
+	regmap_bulk_read(data->regmap, STC3117_ADDR_MODE,
+			 reg_list, sizeof(reg_list));
+
+	/* soc */
+	value = (reg_list[3] << 8) + reg_list[2];
+	data->hrsoc = value;
+	data->soc = (value * 10 + 256) / 512;
+
+	/* current in uA*/
+	value = (reg_list[7] << 8) + reg_list[6];
+	data->batt_current = stc3117_convert(value,
+			CURRENT_LSB_VALUE / data->battery_info.sense_resistor);
+
+	/* voltage in uV */
+	value = (reg_list[9] << 8) + reg_list[8];
+	data->voltage = stc3117_convert(value, VOLTAGE_LSB_VALUE);
+
+	/* temp in 1/10 °C */
+	data->temp = reg_list[10] * 10;
+
+	/* Avg current in uA */
+	value = (reg_list[12] << 8) + reg_list[11];
+	regmap_read(data->regmap, STC3117_ADDR_MODE, &mode);
+	if (!(mode & STC3117_VMODE)) {
+		value = stc3117_convert(value,
+			CURRENT_LSB_VALUE / data->battery_info.sense_resistor);
+		value = value / 4;
+	} else {
+		value = stc3117_convert(value, 36 * STC3117_NOMINAL_CAPACITY);
+	}
+	data->avg_current = value;
+
+	/* ocv in uV */
+	value = (reg_list[14] << 8) + reg_list[13];
+	value = stc3117_convert(value, VOLTAGE_LSB_VALUE);
+	value = (value + 2) / 4;
+	data->ocv = value;
+
+	/* CC & VM adjustment counters */
+	regmap_bulk_read(data->regmap, STC3117_ADDR_CC_ADJ_L,
+			 data_adjust, sizeof(data_adjust));
+	value = (data_adjust[1] << 8) + data_adjust[0];
+	data->cc_adj = value;
+
+	value = (data_adjust[3] << 8) + data_adjust[2];
+	data->vm_adj = value;
+
+	return 0;
+}
+
+static int ram_write(struct stc3117_data *data)
+{
+	int ret;
+
+	ret = regmap_bulk_write(data->regmap, STC3117_ADDR_RAM,
+				data->ram_data.ram_bytes, STC3117_RAM_SIZE);
+	if (ret)
+		return ret;
+
+	return 0;
+};
+
+static int ram_read(struct stc3117_data *data)
+{
+	int ret;
+
+	ret = regmap_bulk_read(data->regmap, STC3117_ADDR_RAM,
+			       data->ram_data.ram_bytes, STC3117_RAM_SIZE);
+	if (ret)
+		return ret;
+
+	return 0;
+};
+
+static int stc3117_set_para(struct stc3117_data *data)
+{
+	int ret;
+
+	ret = regmap_write(data->regmap, STC3117_ADDR_MODE, STC3117_VMODE);
+
+	for (int i = 0; i < STC3117_OCV_TABLE_SIZE; i++)
+		ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_TABLE + i,
+			     ocv_value[i] * 100 / 55);
+	if (data->soc_tab[1] != 0)
+		ret |= regmap_bulk_write(data->regmap, STC3117_ADDR_SOC_TABLE,
+				  data->soc_tab, STC3117_OCV_TABLE_SIZE);
+
+	ret |= regmap_write(data->regmap, STC3117_ADDR_CC_CNF_H,
+				(data->ram_data.reg.cc_cnf >> 8) & 0xFF);
+
+	ret |= regmap_write(data->regmap, STC3117_ADDR_CC_CNF_L,
+					data->ram_data.reg.cc_cnf & 0xFF);
+
+	ret |= regmap_write(data->regmap, STC3117_ADDR_VM_CNF_H,
+				(data->ram_data.reg.vm_cnf >> 8) & 0xFF);
+
+	ret |= regmap_write(data->regmap, STC3117_ADDR_VM_CNF_L,
+					data->ram_data.reg.vm_cnf & 0xFF);
+
+	ret |= regmap_write(data->regmap, STC3117_ADDR_CTRL, 0x03);
+
+	ret |= regmap_write(data->regmap, STC3117_ADDR_MODE,
+					STC3117_MIXED_MODE | STC3117_GG_RUN);
+
+	return ret;
+};
+
+static int stc3117_init(struct stc3117_data *data)
+{
+	int id, ret;
+	int ctrl;
+	int ocv_m, ocv_l;
+
+	regmap_read(data->regmap, STC3117_ADDR_ID, &id);
+	if (id != STC3117_ID)
+		return -EINVAL;
+
+	data->cc_cnf = (data->battery_info.battery_capacity_mah *
+			data->battery_info.sense_resistor * 250 + 6194) / 12389;
+	data->vm_cnf = (data->battery_info.battery_capacity_mah
+						* 200 * 50 + 24444) / 48889;
+
+	/* Battery has not been removed */
+	data->presence = 1;
+
+	/* Read RAM data */
+	ret = ram_read(data);
+	if (ret)
+		return ret;
+
+	if (data->ram_data.reg.testword != STC3117_RAM_TESTWORD ||
+	    (crc8(stc3117_crc_table, data->ram_data.ram_bytes,
+					STC3117_RAM_SIZE, CRC8_INIT)) != 0) {
+		data->ram_data.reg.testword = STC3117_RAM_TESTWORD;
+		data->ram_data.reg.cc_cnf = data->cc_cnf;
+		data->ram_data.reg.vm_cnf = data->vm_cnf;
+		data->ram_data.reg.crc = crc8(stc3117_crc_table,
+						data->ram_data.ram_bytes,
+						STC3117_RAM_SIZE - 1, CRC8_INIT);
+
+		ret = regmap_read(data->regmap, STC3117_ADDR_OCV_H, &ocv_m);
+
+		ret |= regmap_read(data->regmap, STC3117_ADDR_OCV_L, &ocv_l);
+
+		ret |= stc3117_set_para(data);
+
+		ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_H, ocv_m);
+
+		ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_L, ocv_l);
+		if (ret)
+			return ret;
+	} else {
+		ret = regmap_read(data->regmap, STC3117_ADDR_CTRL, &ctrl);
+		if (ret)
+			return ret;
+
+		if ((ctrl & STC3117_BATFAIL) != 0  ||
+		    (ctrl & STC3117_PORDET) != 0) {
+			ret = regmap_read(data->regmap,
+					  STC3117_ADDR_OCV_H, &ocv_m);
+
+			ret |= regmap_read(data->regmap,
+						STC3117_ADDR_OCV_L, &ocv_l);
+
+			ret |= stc3117_set_para(data);
+
+			ret |= regmap_write(data->regmap,
+						STC3117_ADDR_OCV_H, ocv_m);
+
+			ret |= regmap_write(data->regmap,
+						STC3117_ADDR_OCV_L, ocv_l);
+			if (ret)
+				return ret;
+		} else {
+			ret = stc3117_set_para(data);
+			ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_H,
+				     (data->ram_data.reg.hrsoc >> 8 & 0xFF));
+			ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_L,
+				     (data->ram_data.reg.hrsoc & 0xFF));
+			if (ret)
+				return ret;
+		}
+	}
+
+	data->ram_data.reg.state = STC3117_INIT;
+	data->ram_data.reg.crc = crc8(stc3117_crc_table,
+					data->ram_data.ram_bytes,
+					STC3117_RAM_SIZE - 1, CRC8_INIT);
+	ret = ram_write(data);
+	if (ret)
+		return ret;
+
+	return 0;
+};
+
+static int stc3117_task(struct stc3117_data *data)
+{
+	int id, mode, ret;
+	int count_l, count_m;
+	int ocv_l, ocv_m;
+
+	regmap_read(data->regmap, STC3117_ADDR_ID, &id);
+	if (id != STC3117_ID) {
+		data->presence = 0;
+		return -EINVAL;
+	}
+
+	stc3117_get_battery_data(data);
+
+	/* Read RAM data */
+	ret = ram_read(data);
+	if (ret)
+		return ret;
+
+	if (data->ram_data.reg.testword != STC3117_RAM_TESTWORD ||
+	    (crc8(stc3117_crc_table, data->ram_data.ram_bytes,
+					STC3117_RAM_SIZE, CRC8_INIT) != 0)) {
+		data->ram_data.reg.testword = STC3117_RAM_TESTWORD;
+		data->ram_data.reg.cc_cnf = data->cc_cnf;
+		data->ram_data.reg.vm_cnf = data->vm_cnf;
+		data->ram_data.reg.crc = crc8(stc3117_crc_table,
+						data->ram_data.ram_bytes,
+						STC3117_RAM_SIZE - 1, CRC8_INIT);
+		data->ram_data.reg.state = STC3117_INIT;
+	}
+
+	/* check battery presence status */
+	ret = regmap_read(data->regmap, STC3117_ADDR_CTRL, &mode);
+	if ((mode & STC3117_BATFAIL) != 0) {
+		data->presence = 0;
+		data->ram_data.reg.testword = 0;
+		data->ram_data.reg.state = STC3117_INIT;
+		ret = ram_write(data);
+		ret |= regmap_write(data->regmap, STC3117_ADDR_CTRL, STC3117_PORDET);
+		if (ret)
+			return ret;
+	}
+
+	data->presence = 1;
+
+	ret = regmap_read(data->regmap, STC3117_ADDR_MODE, &mode);
+	if (ret)
+		return ret;
+	if ((mode & STC3117_GG_RUN) == 0) {
+		if (data->ram_data.reg.state > STC3117_INIT) {
+			ret = stc3117_set_para(data);
+
+			ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_H,
+					(data->ram_data.reg.hrsoc >> 8 & 0xFF));
+			ret |= regmap_write(data->regmap, STC3117_ADDR_SOC_L,
+					(data->ram_data.reg.hrsoc & 0xFF));
+			if (ret)
+				return ret;
+		} else {
+			ret = regmap_read(data->regmap, STC3117_ADDR_OCV_H, &ocv_m);
+
+			ret |= regmap_read(data->regmap, STC3117_ADDR_OCV_L, &ocv_l);
+
+			ret |= stc3117_set_para(data);
+
+			ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_H, ocv_m);
+
+			ret |= regmap_write(data->regmap, STC3117_ADDR_OCV_L, ocv_l);
+			if (ret)
+				return ret;
+		}
+		data->ram_data.reg.state = STC3117_INIT;
+	}
+
+	regmap_read(data->regmap, STC3117_ADDR_COUNTER_L, &count_l);
+	regmap_read(data->regmap, STC3117_ADDR_COUNTER_H, &count_m);
+
+	count_m = (count_m << 8) + count_l;
+
+	/* INIT state, wait for batt_current & temperature value available: */
+	if (data->ram_data.reg.state == STC3117_INIT && count_m > 4) {
+		data->avg_voltage = data->voltage;
+		data->avg_current = data->batt_current;
+		data->ram_data.reg.state = STC3117_RUNNING;
+	}
+
+	if (data->ram_data.reg.state != STC3117_RUNNING) {
+		data->batt_current = -ENODATA;
+		data->temp = -ENODATA;
+	} else {
+		if (data->voltage < APP_CUTOFF_VOLTAGE)
+			data->soc = -ENODATA;
+
+		if (mode & STC3117_VMODE) {
+			data->avg_current = -ENODATA;
+			data->batt_current = -ENODATA;
+		}
+	}
+
+	data->ram_data.reg.hrsoc = data->hrsoc;
+	data->ram_data.reg.soc = (data->soc + 5) / 10;
+	data->ram_data.reg.crc = crc8(stc3117_crc_table,
+					data->ram_data.ram_bytes,
+					STC3117_RAM_SIZE - 1, CRC8_INIT);
+
+	ret = ram_write(data);
+	if (ret)
+		return ret;
+	return 0;
+};
+
+static void fuel_gauge_update_work(struct work_struct *work)
+{
+	struct stc3117_data *data =
+		container_of(work, struct stc3117_data, update_work.work);
+
+	stc3117_task(data);
+
+	/* Schedule the work to run again in 2 seconds */
+	schedule_delayed_work(&data->update_work, msecs_to_jiffies(2000));
+}
+
+static int stc3117_get_property(struct power_supply *psy,
+	enum power_supply_property psp, union power_supply_propval *val)
+{
+	struct stc3117_data *data = power_supply_get_drvdata(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		if (data->soc > BATTERY_FULL)
+			val->intval = POWER_SUPPLY_STATUS_FULL;
+		else if (data->batt_current < 0)
+			val->intval = POWER_SUPPLY_STATUS_CHARGING;
+		else if (data->batt_current > 0)
+			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+		else
+			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		val->intval = data->voltage;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		val->intval = data->batt_current;
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_OCV:
+		val->intval = data->ocv;
+		break;
+	case POWER_SUPPLY_PROP_CURRENT_AVG:
+		val->intval = data->avg_current;
+		break;
+	case POWER_SUPPLY_PROP_CAPACITY:
+		val->intval = data->soc;
+		break;
+	case POWER_SUPPLY_PROP_TEMP:
+		val->intval = data->temp;
+		break;
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = data->presence;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static enum power_supply_property stc3117_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_VOLTAGE_OCV,
+	POWER_SUPPLY_PROP_CURRENT_AVG,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_PRESENT,
+};
+
+static const struct power_supply_desc stc3117_battery_desc = {
+	.name = "stc3117-battery",
+	.type = POWER_SUPPLY_TYPE_BATTERY,
+	.get_property = stc3117_get_property,
+	.properties = stc3117_battery_props,
+	.num_properties = ARRAY_SIZE(stc3117_battery_props),
+};
+
+static const struct regmap_config stc3117_regmap_config = {
+	.reg_bits       = 8,
+	.val_bits       = 8,
+};
+
+static int stc3117_probe(struct i2c_client *client)
+{
+	struct stc3117_data *data;
+	struct power_supply_config psy_cfg = {};
+	struct power_supply_battery_info *info;
+	int ret;
+
+	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	data->regmap = devm_regmap_init_i2c(client, &stc3117_regmap_config);
+	if (IS_ERR(data->regmap))
+		return PTR_ERR(data->regmap);
+
+	psy_cfg.drv_data = data;
+	psy_cfg.fwnode = dev_fwnode(&client->dev);
+
+	crc8_populate_msb(stc3117_crc_table, CRC8_POLYNOMIAL);
+
+	data->battery = devm_power_supply_register(&client->dev,
+					&stc3117_battery_desc, &psy_cfg);
+	if (IS_ERR(data->battery))
+		return dev_err_probe(&client->dev, PTR_ERR(data->battery),
+					"failed to register battery\n");
+
+	ret = device_property_read_u32(&client->dev, "shunt-resistor-micro-ohms",
+					&data->battery_info.sense_resistor);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				"failed to get shunt-resistor-micro-ohms\n");
+	data->battery_info.sense_resistor = data->battery_info.sense_resistor / 1000;
+
+	ret = power_supply_get_battery_info(data->battery, &info);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+					"failed to get battery information\n");
+
+	data->battery_info.battery_capacity_mah = info->charge_full_design_uah / 1000;
+	data->battery_info.voltage_min_mv = info->voltage_min_design_uv / 1000;
+	data->battery_info.voltage_max_mv = info->voltage_max_design_uv / 1000;
+
+	ret = stc3117_init(data);
+	if (ret)
+		return dev_err_probe(&client->dev, ret,
+				"failed to initialize of stc3117\n");
+
+	ret = devm_delayed_work_autocancel(&client->dev, &data->update_work,
+					   fuel_gauge_update_work);
+	if (ret)
+		return ret;
+
+	schedule_delayed_work(&data->update_work, 0);
+
+	return 0;
+}
+
+static const struct i2c_device_id stc3117_id[] = {
+	{ "stc3117", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, stc3117_id);
+
+static const struct of_device_id stc3117_of_match[] = {
+	{ .compatible = "st,stc3117" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, stc3117_of_match);
+
+static struct i2c_driver stc3117_i2c_driver = {
+	.driver = {
+		.name = "stc3117_i2c_driver",
+		.of_match_table = stc3117_of_match,
+	},
+	.probe = stc3117_probe,
+	.id_table = stc3117_id,
+};
+
+module_i2c_driver(stc3117_i2c_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Hardevsinh Palaniya <hardevsinh.palaniya@siliconsignals.io>");
+MODULE_AUTHOR("Bhavin Sharma <bhavin.sharma@siliconsignals.io>");
+MODULE_DESCRIPTION("STC3117 Fuel Gauge Driver");
diff --git a/drivers/power/supply/surface_battery.c b/drivers/power/supply/surface_battery.c
index ebd1edde28f1..c759add4df49 100644
--- a/drivers/power/supply/surface_battery.c
+++ b/drivers/power/supply/surface_battery.c
@@ -667,7 +667,7 @@ out:
 
 static ssize_t alarm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct spwr_battery_device *bat = power_supply_get_drvdata(psy);
 	int status;
 
@@ -681,7 +681,7 @@ static ssize_t alarm_show(struct device *dev, struct device_attribute *attr, cha
 static ssize_t alarm_store(struct device *dev, struct device_attribute *attr, const char *buf,
 			   size_t count)
 {
-	struct power_supply *psy = dev_get_drvdata(dev);
+	struct power_supply *psy = dev_to_psy(dev);
 	struct spwr_battery_device *bat = power_supply_get_drvdata(psy);
 	unsigned long value;
 	int status;
diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c
index 442ceb7795e1..2a975a110f48 100644
--- a/drivers/power/supply/test_power.c
+++ b/drivers/power/supply/test_power.c
@@ -37,6 +37,7 @@ static int battery_charge_counter	= -1000;
 static int battery_current		= -1600;
 static enum power_supply_charge_behaviour battery_charge_behaviour =
 	POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO;
+static bool battery_extension;
 
 static bool module_initialized;
 
@@ -238,6 +239,87 @@ static const struct power_supply_config test_power_configs[] = {
 	},
 };
 
+static int test_power_battery_extmanufacture_year = 1234;
+static int test_power_battery_exttemp_max = 1000;
+static const enum power_supply_property test_power_battery_extprops[] = {
+	POWER_SUPPLY_PROP_MANUFACTURE_YEAR,
+	POWER_SUPPLY_PROP_TEMP_MAX,
+};
+
+static int test_power_battery_extget_property(struct power_supply *psy,
+					      const struct power_supply_ext *ext,
+					      void *ext_data,
+					      enum power_supply_property psp,
+					      union power_supply_propval *val)
+{
+	switch (psp) {
+	case POWER_SUPPLY_PROP_MANUFACTURE_YEAR:
+		val->intval = test_power_battery_extmanufacture_year;
+		break;
+	case POWER_SUPPLY_PROP_TEMP_MAX:
+		val->intval = test_power_battery_exttemp_max;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int test_power_battery_extset_property(struct power_supply *psy,
+					      const struct power_supply_ext *ext,
+					      void *ext_data,
+					      enum power_supply_property psp,
+					      const union power_supply_propval *val)
+{
+	switch (psp) {
+	case POWER_SUPPLY_PROP_MANUFACTURE_YEAR:
+		test_power_battery_extmanufacture_year = val->intval;
+		break;
+	case POWER_SUPPLY_PROP_TEMP_MAX:
+		test_power_battery_exttemp_max = val->intval;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int test_power_battery_extproperty_is_writeable(struct power_supply *psy,
+						       const struct power_supply_ext *ext,
+						       void *ext_data,
+						       enum power_supply_property psp)
+{
+	return true;
+}
+
+static const struct power_supply_ext test_power_battery_ext = {
+	.name			= "test_power",
+	.properties		= test_power_battery_extprops,
+	.num_properties		= ARRAY_SIZE(test_power_battery_extprops),
+	.get_property		= test_power_battery_extget_property,
+	.set_property		= test_power_battery_extset_property,
+	.property_is_writeable	= test_power_battery_extproperty_is_writeable,
+};
+
+static void test_power_configure_battery_extension(bool enable)
+{
+	struct power_supply *psy;
+
+	psy = test_power_supplies[TEST_BATTERY];
+
+	if (enable) {
+		if (power_supply_register_extension(psy, &test_power_battery_ext, &psy->dev,
+						    NULL)) {
+			pr_err("registering battery extension failed\n");
+			return;
+		}
+	} else {
+		power_supply_unregister_extension(psy, &test_power_battery_ext);
+	}
+
+	battery_extension = enable;
+}
+
 static int __init test_power_init(void)
 {
 	int i;
@@ -258,6 +340,8 @@ static int __init test_power_init(void)
 		}
 	}
 
+	test_power_configure_battery_extension(true);
+
 	module_initialized = true;
 	return 0;
 failed:
@@ -524,6 +608,26 @@ static int param_set_battery_current(const char *key,
 
 #define param_get_battery_current param_get_int
 
+static int param_set_battery_extension(const char *key,
+				       const struct kernel_param *kp)
+{
+	bool prev_battery_extension;
+	int ret;
+
+	prev_battery_extension = battery_extension;
+
+	ret = param_set_bool(key, kp);
+	if (ret)
+		return ret;
+
+	if (prev_battery_extension != battery_extension)
+		test_power_configure_battery_extension(battery_extension);
+
+	return 0;
+}
+
+#define param_get_battery_extension param_get_bool
+
 static const struct kernel_param_ops param_ops_ac_online = {
 	.set = param_set_ac_online,
 	.get = param_get_ac_online,
@@ -574,6 +678,11 @@ static const struct kernel_param_ops param_ops_battery_current = {
 	.get = param_get_battery_current,
 };
 
+static const struct kernel_param_ops param_ops_battery_extension = {
+	.set = param_set_battery_extension,
+	.get = param_get_battery_extension,
+};
+
 #define param_check_ac_online(name, p) __param_check(name, p, void);
 #define param_check_usb_online(name, p) __param_check(name, p, void);
 #define param_check_battery_status(name, p) __param_check(name, p, void);
@@ -584,6 +693,7 @@ static const struct kernel_param_ops param_ops_battery_current = {
 #define param_check_battery_voltage(name, p) __param_check(name, p, void);
 #define param_check_battery_charge_counter(name, p) __param_check(name, p, void);
 #define param_check_battery_current(name, p) __param_check(name, p, void);
+#define param_check_battery_extension(name, p) __param_check(name, p, void);
 
 
 module_param(ac_online, ac_online, 0644);
@@ -621,6 +731,9 @@ MODULE_PARM_DESC(battery_charge_counter,
 module_param(battery_current, battery_current, 0644);
 MODULE_PARM_DESC(battery_current, "battery current (milliampere)");
 
+module_param(battery_extension, battery_extension, 0644);
+MODULE_PARM_DESC(battery_extension, "battery extension");
+
 MODULE_DESCRIPTION("Power supply driver for testing");
 MODULE_AUTHOR("Anton Vorontsov <cbouatmailru@gmail.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/ug3105_battery.c b/drivers/power/supply/ug3105_battery.c
index ccc5c4d2e230..38e23bdd4603 100644
--- a/drivers/power/supply/ug3105_battery.c
+++ b/drivers/power/supply/ug3105_battery.c
@@ -287,7 +287,6 @@ out:
 static enum power_supply_property ug3105_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
-	POWER_SUPPLY_PROP_TECHNOLOGY,
 	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
 	POWER_SUPPLY_PROP_VOLTAGE_OCV,
@@ -316,9 +315,6 @@ static int ug3105_get_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_PRESENT:
 		val->intval = 1;
 		break;
-	case POWER_SUPPLY_PROP_TECHNOLOGY:
-		val->intval = chip->info->technology;
-		break;
 	case POWER_SUPPLY_PROP_SCOPE:
 		val->intval = POWER_SUPPLY_SCOPE_SYSTEM;
 		break;
diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c
index 52c32dcbf7d8..4112a0097338 100644
--- a/drivers/powercap/powercap_sys.c
+++ b/drivers/powercap/powercap_sys.c
@@ -627,8 +627,7 @@ struct powercap_control_type *powercap_register_control_type(
 	dev_set_name(&control_type->dev, "%s", name);
 	result = device_register(&control_type->dev);
 	if (result) {
-		if (control_type->allocated)
-			kfree(control_type);
+		put_device(&control_type->dev);
 		return ERR_PTR(result);
 	}
 	idr_init(&control_type->idr);
diff --git a/drivers/pps/Makefile b/drivers/pps/Makefile
index ceaf65cc1f1d..0aea394d4e4d 100644
--- a/drivers/pps/Makefile
+++ b/drivers/pps/Makefile
@@ -6,6 +6,7 @@
 pps_core-y			:= pps.o kapi.o sysfs.o
 pps_core-$(CONFIG_NTP_PPS)	+= kc.o
 obj-$(CONFIG_PPS)		:= pps_core.o
-obj-y				+= clients/ generators/
+obj-y				+= clients/
+obj-$(CONFIG_PPS_GENERATOR)	+= generators/
 
 ccflags-$(CONFIG_PPS_DEBUG) := -DDEBUG
diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c
index 634c3b2f8c26..75c1bae30a7c 100644
--- a/drivers/pps/clients/pps-gpio.c
+++ b/drivers/pps/clients/pps-gpio.c
@@ -52,7 +52,9 @@ static irqreturn_t pps_gpio_irq_handler(int irq, void *data)
 
 	info = data;
 
-	rising_edge = gpiod_get_value(info->gpio_pin);
+	/* Small trick to bypass the check on edge's direction when capture_clear is unset */
+	rising_edge = info->capture_clear ?
+		      gpiod_get_value(info->gpio_pin) : !info->assert_falling_edge;
 	if ((rising_edge && !info->assert_falling_edge) ||
 			(!rising_edge && info->assert_falling_edge))
 		pps_event(info->pps, &ts, PPS_CAPTUREASSERT, data);
@@ -60,6 +62,8 @@ static irqreturn_t pps_gpio_irq_handler(int irq, void *data)
 			((rising_edge && info->assert_falling_edge) ||
 			(!rising_edge && !info->assert_falling_edge)))
 		pps_event(info->pps, &ts, PPS_CAPTURECLEAR, data);
+	else
+		dev_warn_ratelimited(&info->pps->dev, "IRQ did not trigger any PPS event\n");
 
 	return IRQ_HANDLED;
 }
@@ -214,8 +218,8 @@ static int pps_gpio_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	dev_info(data->pps->dev, "Registered IRQ %d as PPS source\n",
-		 data->irq);
+	dev_dbg(&data->pps->dev, "Registered IRQ %d as PPS source\n",
+		data->irq);
 
 	return 0;
 }
diff --git a/drivers/pps/clients/pps-ktimer.c b/drivers/pps/clients/pps-ktimer.c
index d33106bd7a29..2f465549b843 100644
--- a/drivers/pps/clients/pps-ktimer.c
+++ b/drivers/pps/clients/pps-ktimer.c
@@ -56,7 +56,7 @@ static struct pps_source_info pps_ktimer_info = {
 
 static void __exit pps_ktimer_exit(void)
 {
-	dev_info(pps->dev, "ktimer PPS source unregistered\n");
+	dev_dbg(&pps->dev, "ktimer PPS source unregistered\n");
 
 	del_timer_sync(&ktimer);
 	pps_unregister_source(pps);
@@ -74,7 +74,7 @@ static int __init pps_ktimer_init(void)
 	timer_setup(&ktimer, pps_ktimer_event, 0);
 	mod_timer(&ktimer, jiffies + HZ);
 
-	dev_info(pps->dev, "ktimer PPS source registered\n");
+	dev_dbg(&pps->dev, "ktimer PPS source registered\n");
 
 	return 0;
 }
diff --git a/drivers/pps/clients/pps-ldisc.c b/drivers/pps/clients/pps-ldisc.c
index 443d6bae19d1..fa5660f3c4b7 100644
--- a/drivers/pps/clients/pps-ldisc.c
+++ b/drivers/pps/clients/pps-ldisc.c
@@ -32,7 +32,7 @@ static void pps_tty_dcd_change(struct tty_struct *tty, bool active)
 	pps_event(pps, &ts, active ? PPS_CAPTUREASSERT :
 			PPS_CAPTURECLEAR, NULL);
 
-	dev_dbg(pps->dev, "PPS %s at %lu\n",
+	dev_dbg(&pps->dev, "PPS %s at %lu\n",
 			active ? "assert" : "clear", jiffies);
 }
 
@@ -69,7 +69,7 @@ static int pps_tty_open(struct tty_struct *tty)
 		goto err_unregister;
 	}
 
-	dev_info(pps->dev, "source \"%s\" added\n", info.path);
+	dev_dbg(&pps->dev, "source \"%s\" added\n", info.path);
 
 	return 0;
 
@@ -89,7 +89,7 @@ static void pps_tty_close(struct tty_struct *tty)
 	if (WARN_ON(!pps))
 		return;
 
-	dev_info(pps->dev, "removed\n");
+	dev_info(&pps->dev, "removed\n");
 	pps_unregister_source(pps);
 }
 
diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c
index abaffb4e1c1c..24db06750297 100644
--- a/drivers/pps/clients/pps_parport.c
+++ b/drivers/pps/clients/pps_parport.c
@@ -81,7 +81,7 @@ static void parport_irq(void *handle)
 	/* check the signal (no signal means the pulse is lost this time) */
 	if (!signal_is_set(port)) {
 		local_irq_restore(flags);
-		dev_err(dev->pps->dev, "lost the signal\n");
+		dev_err(&dev->pps->dev, "lost the signal\n");
 		goto out_assert;
 	}
 
@@ -98,7 +98,7 @@ static void parport_irq(void *handle)
 	/* timeout */
 	dev->cw_err++;
 	if (dev->cw_err >= CLEAR_WAIT_MAX_ERRORS) {
-		dev_err(dev->pps->dev, "disabled clear edge capture after %d"
+		dev_err(&dev->pps->dev, "disabled clear edge capture after %d"
 				" timeouts\n", dev->cw_err);
 		dev->cw = 0;
 		dev->cw_err = 0;
diff --git a/drivers/pps/generators/Kconfig b/drivers/pps/generators/Kconfig
index d615e640fcad..cd94bf3bfaf2 100644
--- a/drivers/pps/generators/Kconfig
+++ b/drivers/pps/generators/Kconfig
@@ -3,7 +3,25 @@
 # PPS generators configuration
 #
 
-comment "PPS generators support"
+menuconfig PPS_GENERATOR
+	tristate "PPS generators support"
+	help
+	  PPS generators are special hardware which are able to produce PPS
+	  (Pulse Per Second) signals.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called pps_gen_core.
+
+if PPS_GENERATOR
+
+config PPS_GENERATOR_DUMMY
+        tristate "Dummy PPS generator (Testing generator, use for debug)"
+        help
+          If you say yes here you get support for a PPS debugging generator
+          (which generates no PPS signal at all).
+
+          This driver can also be built as a module.  If so, the module
+          will be called pps_gen-dummy.
 
 config PPS_GENERATOR_PARPORT
 	tristate "Parallel port PPS signal generator"
@@ -12,3 +30,5 @@ config PPS_GENERATOR_PARPORT
 	  If you say yes here you get support for a PPS signal generator which
 	  utilizes STROBE pin of a parallel port to send PPS signals. It uses
 	  parport abstraction layer and hrtimers to precisely control the signal.
+
+endif # PPS_GENERATOR
diff --git a/drivers/pps/generators/Makefile b/drivers/pps/generators/Makefile
index 2589fd0f2481..dc1aa5a4688b 100644
--- a/drivers/pps/generators/Makefile
+++ b/drivers/pps/generators/Makefile
@@ -3,6 +3,10 @@
 # Makefile for PPS generators.
 #
 
+pps_gen_core-y			:= pps_gen.o sysfs.o
+obj-$(CONFIG_PPS_GENERATOR)	:= pps_gen_core.o
+
+obj-$(CONFIG_PPS_GENERATOR_DUMMY)   += pps_gen-dummy.o
 obj-$(CONFIG_PPS_GENERATOR_PARPORT) += pps_gen_parport.o
 
 ccflags-$(CONFIG_PPS_DEBUG) := -DDEBUG
diff --git a/drivers/pps/generators/pps_gen-dummy.c b/drivers/pps/generators/pps_gen-dummy.c
new file mode 100644
index 000000000000..b284c200cbe5
--- /dev/null
+++ b/drivers/pps/generators/pps_gen-dummy.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PPS dummy generator
+ *
+ * Copyright (C) 2024 Rodolfo Giometti <giometti@enneenne.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/timer.h>
+#include <linux/random.h>
+#include <linux/pps_gen_kernel.h>
+
+static struct pps_gen_device *pps_gen;
+static struct timer_list ktimer;
+
+static unsigned int get_random_delay(void)
+{
+	unsigned int delay = get_random_u8() & 0x0f;
+
+	return (delay + 1) * HZ;
+}
+
+/*
+ * The kernel timer
+ */
+
+static void pps_gen_ktimer_event(struct timer_list *unused)
+{
+	pps_gen_event(pps_gen, PPS_GEN_EVENT_MISSEDPULSE, NULL);
+}
+
+/*
+ * PPS Generator methods
+ */
+
+static int pps_gen_dummy_get_time(struct pps_gen_device *pps_gen,
+					struct timespec64 *time)
+{
+	struct system_time_snapshot snap;
+
+	ktime_get_snapshot(&snap);
+	*time = ktime_to_timespec64(snap.real);
+
+	return 0;
+}
+
+static int pps_gen_dummy_enable(struct pps_gen_device *pps_gen, bool enable)
+{
+	if (enable)
+		mod_timer(&ktimer, jiffies + get_random_delay());
+	else
+		del_timer_sync(&ktimer);
+
+	return 0;
+}
+
+/*
+ * The PPS info struct
+ */
+
+static struct pps_gen_source_info pps_gen_dummy_info = {
+	.use_system_clock	= true,
+	.get_time		= pps_gen_dummy_get_time,
+	.enable			= pps_gen_dummy_enable,
+};
+
+/*
+ * Module staff
+ */
+
+static void __exit pps_gen_dummy_exit(void)
+{
+	del_timer_sync(&ktimer);
+	pps_gen_unregister_source(pps_gen);
+}
+
+static int __init pps_gen_dummy_init(void)
+{
+	pps_gen = pps_gen_register_source(&pps_gen_dummy_info);
+	if (IS_ERR(pps_gen))
+		return PTR_ERR(pps_gen);
+
+	timer_setup(&ktimer, pps_gen_ktimer_event, 0);
+
+	return 0;
+}
+
+module_init(pps_gen_dummy_init);
+module_exit(pps_gen_dummy_exit);
+
+MODULE_AUTHOR("Rodolfo Giometti <giometti@enneenne.com>");
+MODULE_DESCRIPTION("LinuxPPS dummy generator");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pps/generators/pps_gen.c b/drivers/pps/generators/pps_gen.c
new file mode 100644
index 000000000000..ca592f1736f4
--- /dev/null
+++ b/drivers/pps/generators/pps_gen.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PPS generators core file
+ *
+ * Copyright (C) 2024 Rodolfo Giometti <giometti@enneenne.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/time.h>
+#include <linux/timex.h>
+#include <linux/uaccess.h>
+#include <linux/idr.h>
+#include <linux/cdev.h>
+#include <linux/poll.h>
+#include <linux/fs.h>
+#include <linux/pps_gen_kernel.h>
+#include <linux/slab.h>
+
+/*
+ * Local variables
+ */
+
+static dev_t pps_gen_devt;
+static struct class *pps_gen_class;
+
+static DEFINE_IDA(pps_gen_ida);
+
+/*
+ * Char device methods
+ */
+
+static __poll_t pps_gen_cdev_poll(struct file *file, poll_table *wait)
+{
+	struct pps_gen_device *pps_gen = file->private_data;
+
+	poll_wait(file, &pps_gen->queue, wait);
+	return EPOLLIN | EPOLLRDNORM;
+}
+
+static int pps_gen_cdev_fasync(int fd, struct file *file, int on)
+{
+	struct pps_gen_device *pps_gen = file->private_data;
+
+	return fasync_helper(fd, file, on, &pps_gen->async_queue);
+}
+
+static long pps_gen_cdev_ioctl(struct file *file,
+		unsigned int cmd, unsigned long arg)
+{
+	struct pps_gen_device *pps_gen = file->private_data;
+	void __user *uarg = (void __user *) arg;
+	unsigned int __user *uiuarg = (unsigned int __user *) arg;
+	unsigned int status;
+	int ret;
+
+	switch (cmd) {
+	case PPS_GEN_SETENABLE:
+		dev_dbg(pps_gen->dev, "PPS_GEN_SETENABLE\n");
+
+		ret = get_user(status, uiuarg);
+		if (ret)
+			return -EFAULT;
+
+		ret = pps_gen->info.enable(pps_gen, status);
+		if (ret)
+			return ret;
+		pps_gen->enabled = status;
+
+		break;
+
+	case PPS_GEN_USESYSTEMCLOCK:
+		dev_dbg(pps_gen->dev, "PPS_GEN_USESYSTEMCLOCK\n");
+
+		ret = put_user(pps_gen->info.use_system_clock, uiuarg);
+		if (ret)
+			return -EFAULT;
+
+		break;
+
+	case PPS_GEN_FETCHEVENT: {
+		struct pps_gen_event info;
+		unsigned int ev = pps_gen->last_ev;
+
+		dev_dbg(pps_gen->dev, "PPS_GEN_FETCHEVENT\n");
+
+		ret = wait_event_interruptible(pps_gen->queue,
+				ev != pps_gen->last_ev);
+		if (ret == -ERESTARTSYS) {
+			dev_dbg(pps_gen->dev, "pending signal caught\n");
+			return -EINTR;
+		}
+
+		spin_lock_irq(&pps_gen->lock);
+		info.sequence = pps_gen->sequence;
+		info.event = pps_gen->event;
+		spin_unlock_irq(&pps_gen->lock);
+
+		ret = copy_to_user(uarg, &info, sizeof(struct pps_gen_event));
+		if (ret)
+			return -EFAULT;
+
+		break;
+	}
+	default:
+		return -ENOTTY;
+	}
+
+	return 0;
+}
+
+static int pps_gen_cdev_open(struct inode *inode, struct file *file)
+{
+	struct pps_gen_device *pps_gen = container_of(inode->i_cdev,
+				struct pps_gen_device, cdev);
+
+	get_device(pps_gen->dev);
+	file->private_data = pps_gen;
+	return 0;
+}
+
+static int pps_gen_cdev_release(struct inode *inode, struct file *file)
+{
+	struct pps_gen_device *pps_gen = file->private_data;
+
+	put_device(pps_gen->dev);
+	return 0;
+}
+
+/*
+ * Char device stuff
+ */
+
+static const struct file_operations pps_gen_cdev_fops = {
+	.owner		= THIS_MODULE,
+	.poll	   = pps_gen_cdev_poll,
+	.fasync	 = pps_gen_cdev_fasync,
+	.unlocked_ioctl	= pps_gen_cdev_ioctl,
+	.open		= pps_gen_cdev_open,
+	.release	= pps_gen_cdev_release,
+};
+
+static void pps_gen_device_destruct(struct device *dev)
+{
+	struct pps_gen_device *pps_gen = dev_get_drvdata(dev);
+
+	cdev_del(&pps_gen->cdev);
+
+	pr_debug("deallocating pps-gen%d\n", pps_gen->id);
+	ida_free(&pps_gen_ida, pps_gen->id);
+
+	kfree(dev);
+	kfree(pps_gen);
+}
+
+static int pps_gen_register_cdev(struct pps_gen_device *pps_gen)
+{
+	int err;
+	dev_t devt;
+
+	err = ida_alloc_max(&pps_gen_ida, PPS_GEN_MAX_SOURCES - 1, GFP_KERNEL);
+	if (err < 0) {
+		if (err == -ENOSPC) {
+			pr_err("too many PPS sources in the system\n");
+			err = -EBUSY;
+		}
+		return err;
+	}
+	pps_gen->id = err;
+
+	devt = MKDEV(MAJOR(pps_gen_devt), pps_gen->id);
+
+	cdev_init(&pps_gen->cdev, &pps_gen_cdev_fops);
+	pps_gen->cdev.owner = pps_gen->info.owner;
+
+	err = cdev_add(&pps_gen->cdev, devt, 1);
+	if (err) {
+		pr_err("failed to add char device %d:%d\n",
+				MAJOR(pps_gen_devt), pps_gen->id);
+		goto free_ida;
+	}
+	pps_gen->dev = device_create(pps_gen_class, pps_gen->info.parent, devt,
+					pps_gen, "pps-gen%d", pps_gen->id);
+	if (IS_ERR(pps_gen->dev)) {
+		err = PTR_ERR(pps_gen->dev);
+		goto del_cdev;
+	}
+	pps_gen->dev->release = pps_gen_device_destruct;
+	dev_set_drvdata(pps_gen->dev, pps_gen);
+
+	pr_debug("generator got cdev (%d:%d)\n",
+			MAJOR(pps_gen_devt), pps_gen->id);
+
+	return 0;
+
+del_cdev:
+	cdev_del(&pps_gen->cdev);
+free_ida:
+	ida_free(&pps_gen_ida, pps_gen->id);
+	return err;
+}
+
+static void pps_gen_unregister_cdev(struct pps_gen_device *pps_gen)
+{
+	pr_debug("unregistering pps-gen%d\n", pps_gen->id);
+	device_destroy(pps_gen_class, pps_gen->dev->devt);
+}
+
+/*
+ * Exported functions
+ */
+
+/**
+ * pps_gen_register_source() - add a PPS generator in the system
+ * @info: the PPS generator info struct
+ *
+ * This function is used to register a new PPS generator in the system.
+ * When it returns successfully the new generator is up and running, and
+ * it can be managed by the userspace.
+ *
+ * Return: the PPS generator device in case of success, and ERR_PTR(errno)
+ *	 otherwise.
+ */
+struct pps_gen_device *pps_gen_register_source(struct pps_gen_source_info *info)
+{
+	struct pps_gen_device *pps_gen;
+	int err;
+
+	pps_gen = kzalloc(sizeof(struct pps_gen_device), GFP_KERNEL);
+	if (pps_gen == NULL) {
+		err = -ENOMEM;
+		goto pps_gen_register_source_exit;
+	}
+	pps_gen->info = *info;
+	pps_gen->enabled = false;
+
+	init_waitqueue_head(&pps_gen->queue);
+	spin_lock_init(&pps_gen->lock);
+
+	/* Create the char device */
+	err = pps_gen_register_cdev(pps_gen);
+	if (err < 0) {
+		pr_err(" unable to create char device\n");
+		goto kfree_pps_gen;
+	}
+
+	return pps_gen;
+
+kfree_pps_gen:
+	kfree(pps_gen);
+
+pps_gen_register_source_exit:
+	pr_err("unable to register generator\n");
+
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(pps_gen_register_source);
+
+/**
+ * pps_gen_unregister_source() - remove a PPS generator from the system
+ * @pps_gen: the PPS generator device to be removed
+ *
+ * This function is used to deregister a PPS generator from the system. When
+ * called, it disables the generator so no pulses are generated anymore.
+ */
+void pps_gen_unregister_source(struct pps_gen_device *pps_gen)
+{
+	pps_gen_unregister_cdev(pps_gen);
+}
+EXPORT_SYMBOL(pps_gen_unregister_source);
+
+/* pps_gen_event - register a PPS generator event into the system
+ * @pps: the PPS generator device
+ * @event: the event type
+ * @data: userdef pointer
+ *
+ * This function is used by each PPS generator in order to register a new
+ * PPS event into the system (it's usually called inside an IRQ handler).
+ */
+void pps_gen_event(struct pps_gen_device *pps_gen,
+			unsigned int event, void *data)
+{
+	unsigned long flags;
+
+	dev_dbg(pps_gen->dev, "PPS generator event %u\n", event);
+
+	spin_lock_irqsave(&pps_gen->lock, flags);
+
+	pps_gen->event = event;
+	pps_gen->sequence++;
+
+	pps_gen->last_ev++;
+	wake_up_interruptible_all(&pps_gen->queue);
+	kill_fasync(&pps_gen->async_queue, SIGIO, POLL_IN);
+
+	spin_unlock_irqrestore(&pps_gen->lock, flags);
+}
+EXPORT_SYMBOL(pps_gen_event);
+
+/*
+ * Module stuff
+ */
+
+static void __exit pps_gen_exit(void)
+{
+	class_destroy(pps_gen_class);
+	unregister_chrdev_region(pps_gen_devt, PPS_GEN_MAX_SOURCES);
+}
+
+static int __init pps_gen_init(void)
+{
+	int err;
+
+	pps_gen_class = class_create("pps-gen");
+	if (IS_ERR(pps_gen_class)) {
+		pr_err("failed to allocate class\n");
+		return PTR_ERR(pps_gen_class);
+	}
+	pps_gen_class->dev_groups = pps_gen_groups;
+
+	err = alloc_chrdev_region(&pps_gen_devt, 0,
+					PPS_GEN_MAX_SOURCES, "pps-gen");
+	if (err < 0) {
+		pr_err("failed to allocate char device region\n");
+		goto remove_class;
+	}
+
+	return 0;
+
+remove_class:
+	class_destroy(pps_gen_class);
+	return err;
+}
+
+subsys_initcall(pps_gen_init);
+module_exit(pps_gen_exit);
+
+MODULE_AUTHOR("Rodolfo Giometti <giometti@enneenne.com>");
+MODULE_DESCRIPTION("LinuxPPS generators support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pps/generators/sysfs.c b/drivers/pps/generators/sysfs.c
new file mode 100644
index 000000000000..faf8b1c6d202
--- /dev/null
+++ b/drivers/pps/generators/sysfs.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PPS generators sysfs support
+ *
+ * Copyright (C) 2024 Rodolfo Giometti <giometti@enneenne.com>
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/pps_gen_kernel.h>
+
+/*
+ * Attribute functions
+ */
+
+static ssize_t system_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct pps_gen_device *pps_gen = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n", pps_gen->info.use_system_clock);
+}
+static DEVICE_ATTR_RO(system);
+
+static ssize_t time_show(struct device *dev, struct device_attribute *attr,
+				char *buf)
+{
+	struct pps_gen_device *pps_gen = dev_get_drvdata(dev);
+	struct timespec64 time;
+	int ret;
+
+	ret = pps_gen->info.get_time(pps_gen, &time);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu %09lu\n", time.tv_sec, time.tv_nsec);
+}
+static DEVICE_ATTR_RO(time);
+
+static ssize_t enable_store(struct device *dev, struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct pps_gen_device *pps_gen = dev_get_drvdata(dev);
+	bool status;
+	int ret;
+
+	ret = kstrtobool(buf, &status);
+	if (ret)
+		return ret;
+
+	ret = pps_gen->info.enable(pps_gen, status);
+	if (ret)
+		return ret;
+	pps_gen->enabled = status;
+
+	return count;
+}
+static DEVICE_ATTR_WO(enable);
+
+static struct attribute *pps_gen_attrs[] = {
+	&dev_attr_enable.attr,
+	&dev_attr_time.attr,
+	&dev_attr_system.attr,
+	NULL,
+};
+
+static const struct attribute_group pps_gen_group = {
+	.attrs = pps_gen_attrs,
+};
+
+const struct attribute_group *pps_gen_groups[] = {
+	&pps_gen_group,
+	NULL,
+};
diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c
index d9d566f70ed1..92d1b62ea239 100644
--- a/drivers/pps/kapi.c
+++ b/drivers/pps/kapi.c
@@ -41,7 +41,7 @@ static void pps_add_offset(struct pps_ktime *ts, struct pps_ktime *offset)
 static void pps_echo_client_default(struct pps_device *pps, int event,
 		void *data)
 {
-	dev_info(pps->dev, "echo %s %s\n",
+	dev_info(&pps->dev, "echo %s %s\n",
 		event & PPS_CAPTUREASSERT ? "assert" : "",
 		event & PPS_CAPTURECLEAR ? "clear" : "");
 }
@@ -112,7 +112,7 @@ struct pps_device *pps_register_source(struct pps_source_info *info,
 		goto kfree_pps;
 	}
 
-	dev_info(pps->dev, "new PPS source %s\n", info->name);
+	dev_dbg(&pps->dev, "new PPS source %s\n", info->name);
 
 	return pps;
 
@@ -166,7 +166,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event,
 	/* check event type */
 	BUG_ON((event & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR)) == 0);
 
-	dev_dbg(pps->dev, "PPS event at %lld.%09ld\n",
+	dev_dbg(&pps->dev, "PPS event at %lld.%09ld\n",
 			(s64)ts->ts_real.tv_sec, ts->ts_real.tv_nsec);
 
 	timespec_to_pps_ktime(&ts_real, ts->ts_real);
@@ -188,7 +188,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event,
 		/* Save the time stamp */
 		pps->assert_tu = ts_real;
 		pps->assert_sequence++;
-		dev_dbg(pps->dev, "capture assert seq #%u\n",
+		dev_dbg(&pps->dev, "capture assert seq #%u\n",
 			pps->assert_sequence);
 
 		captured = ~0;
@@ -202,7 +202,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event,
 		/* Save the time stamp */
 		pps->clear_tu = ts_real;
 		pps->clear_sequence++;
-		dev_dbg(pps->dev, "capture clear seq #%u\n",
+		dev_dbg(&pps->dev, "capture clear seq #%u\n",
 			pps->clear_sequence);
 
 		captured = ~0;
diff --git a/drivers/pps/kc.c b/drivers/pps/kc.c
index 50dc59af45be..fbd23295afd7 100644
--- a/drivers/pps/kc.c
+++ b/drivers/pps/kc.c
@@ -43,11 +43,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args)
 			pps_kc_hardpps_mode = 0;
 			pps_kc_hardpps_dev = NULL;
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_info(pps->dev, "unbound kernel"
+			dev_info(&pps->dev, "unbound kernel"
 					" consumer\n");
 		} else {
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_err(pps->dev, "selected kernel consumer"
+			dev_err(&pps->dev, "selected kernel consumer"
 					" is not bound\n");
 			return -EINVAL;
 		}
@@ -57,11 +57,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args)
 			pps_kc_hardpps_mode = bind_args->edge;
 			pps_kc_hardpps_dev = pps;
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_info(pps->dev, "bound kernel consumer: "
+			dev_info(&pps->dev, "bound kernel consumer: "
 				"edge=0x%x\n", bind_args->edge);
 		} else {
 			spin_unlock_irq(&pps_kc_hardpps_lock);
-			dev_err(pps->dev, "another kernel consumer"
+			dev_err(&pps->dev, "another kernel consumer"
 					" is already bound\n");
 			return -EINVAL;
 		}
@@ -83,7 +83,7 @@ void pps_kc_remove(struct pps_device *pps)
 		pps_kc_hardpps_mode = 0;
 		pps_kc_hardpps_dev = NULL;
 		spin_unlock_irq(&pps_kc_hardpps_lock);
-		dev_info(pps->dev, "unbound kernel consumer"
+		dev_info(&pps->dev, "unbound kernel consumer"
 				" on device removal\n");
 	} else
 		spin_unlock_irq(&pps_kc_hardpps_lock);
diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c
index 25d47907db17..6a02245ea35f 100644
--- a/drivers/pps/pps.c
+++ b/drivers/pps/pps.c
@@ -25,7 +25,7 @@
  * Local variables
  */
 
-static dev_t pps_devt;
+static int pps_major;
 static struct class *pps_class;
 
 static DEFINE_MUTEX(pps_idr_lock);
@@ -62,7 +62,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata)
 	else {
 		unsigned long ticks;
 
-		dev_dbg(pps->dev, "timeout %lld.%09d\n",
+		dev_dbg(&pps->dev, "timeout %lld.%09d\n",
 				(long long) fdata->timeout.sec,
 				fdata->timeout.nsec);
 		ticks = fdata->timeout.sec * HZ;
@@ -80,7 +80,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata)
 
 	/* Check for pending signals */
 	if (err == -ERESTARTSYS) {
-		dev_dbg(pps->dev, "pending signal caught\n");
+		dev_dbg(&pps->dev, "pending signal caught\n");
 		return -EINTR;
 	}
 
@@ -98,7 +98,7 @@ static long pps_cdev_ioctl(struct file *file,
 
 	switch (cmd) {
 	case PPS_GETPARAMS:
-		dev_dbg(pps->dev, "PPS_GETPARAMS\n");
+		dev_dbg(&pps->dev, "PPS_GETPARAMS\n");
 
 		spin_lock_irq(&pps->lock);
 
@@ -114,7 +114,7 @@ static long pps_cdev_ioctl(struct file *file,
 		break;
 
 	case PPS_SETPARAMS:
-		dev_dbg(pps->dev, "PPS_SETPARAMS\n");
+		dev_dbg(&pps->dev, "PPS_SETPARAMS\n");
 
 		/* Check the capabilities */
 		if (!capable(CAP_SYS_TIME))
@@ -124,14 +124,14 @@ static long pps_cdev_ioctl(struct file *file,
 		if (err)
 			return -EFAULT;
 		if (!(params.mode & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR))) {
-			dev_dbg(pps->dev, "capture mode unspecified (%x)\n",
+			dev_dbg(&pps->dev, "capture mode unspecified (%x)\n",
 								params.mode);
 			return -EINVAL;
 		}
 
 		/* Check for supported capabilities */
 		if ((params.mode & ~pps->info.mode) != 0) {
-			dev_dbg(pps->dev, "unsupported capabilities (%x)\n",
+			dev_dbg(&pps->dev, "unsupported capabilities (%x)\n",
 								params.mode);
 			return -EINVAL;
 		}
@@ -144,7 +144,7 @@ static long pps_cdev_ioctl(struct file *file,
 		/* Restore the read only parameters */
 		if ((params.mode & (PPS_TSFMT_TSPEC | PPS_TSFMT_NTPFP)) == 0) {
 			/* section 3.3 of RFC 2783 interpreted */
-			dev_dbg(pps->dev, "time format unspecified (%x)\n",
+			dev_dbg(&pps->dev, "time format unspecified (%x)\n",
 								params.mode);
 			pps->params.mode |= PPS_TSFMT_TSPEC;
 		}
@@ -165,7 +165,7 @@ static long pps_cdev_ioctl(struct file *file,
 		break;
 
 	case PPS_GETCAP:
-		dev_dbg(pps->dev, "PPS_GETCAP\n");
+		dev_dbg(&pps->dev, "PPS_GETCAP\n");
 
 		err = put_user(pps->info.mode, iuarg);
 		if (err)
@@ -176,7 +176,7 @@ static long pps_cdev_ioctl(struct file *file,
 	case PPS_FETCH: {
 		struct pps_fdata fdata;
 
-		dev_dbg(pps->dev, "PPS_FETCH\n");
+		dev_dbg(&pps->dev, "PPS_FETCH\n");
 
 		err = copy_from_user(&fdata, uarg, sizeof(struct pps_fdata));
 		if (err)
@@ -206,7 +206,7 @@ static long pps_cdev_ioctl(struct file *file,
 	case PPS_KC_BIND: {
 		struct pps_bind_args bind_args;
 
-		dev_dbg(pps->dev, "PPS_KC_BIND\n");
+		dev_dbg(&pps->dev, "PPS_KC_BIND\n");
 
 		/* Check the capabilities */
 		if (!capable(CAP_SYS_TIME))
@@ -218,7 +218,7 @@ static long pps_cdev_ioctl(struct file *file,
 
 		/* Check for supported capabilities */
 		if ((bind_args.edge & ~pps->info.mode) != 0) {
-			dev_err(pps->dev, "unsupported capabilities (%x)\n",
+			dev_err(&pps->dev, "unsupported capabilities (%x)\n",
 					bind_args.edge);
 			return -EINVAL;
 		}
@@ -227,7 +227,7 @@ static long pps_cdev_ioctl(struct file *file,
 		if (bind_args.tsformat != PPS_TSFMT_TSPEC ||
 				(bind_args.edge & ~PPS_CAPTUREBOTH) != 0 ||
 				bind_args.consumer != PPS_KC_HARDPPS) {
-			dev_err(pps->dev, "invalid kernel consumer bind"
+			dev_err(&pps->dev, "invalid kernel consumer bind"
 					" parameters (%x)\n", bind_args.edge);
 			return -EINVAL;
 		}
@@ -259,7 +259,7 @@ static long pps_cdev_compat_ioctl(struct file *file,
 		struct pps_fdata fdata;
 		int err;
 
-		dev_dbg(pps->dev, "PPS_FETCH\n");
+		dev_dbg(&pps->dev, "PPS_FETCH\n");
 
 		err = copy_from_user(&compat, uarg, sizeof(struct pps_fdata_compat));
 		if (err)
@@ -296,20 +296,36 @@ static long pps_cdev_compat_ioctl(struct file *file,
 #define pps_cdev_compat_ioctl	NULL
 #endif
 
+static struct pps_device *pps_idr_get(unsigned long id)
+{
+	struct pps_device *pps;
+
+	mutex_lock(&pps_idr_lock);
+	pps = idr_find(&pps_idr, id);
+	if (pps)
+		get_device(&pps->dev);
+
+	mutex_unlock(&pps_idr_lock);
+	return pps;
+}
+
 static int pps_cdev_open(struct inode *inode, struct file *file)
 {
-	struct pps_device *pps = container_of(inode->i_cdev,
-						struct pps_device, cdev);
+	struct pps_device *pps = pps_idr_get(iminor(inode));
+
+	if (!pps)
+		return -ENODEV;
+
 	file->private_data = pps;
-	kobject_get(&pps->dev->kobj);
 	return 0;
 }
 
 static int pps_cdev_release(struct inode *inode, struct file *file)
 {
-	struct pps_device *pps = container_of(inode->i_cdev,
-						struct pps_device, cdev);
-	kobject_put(&pps->dev->kobj);
+	struct pps_device *pps = file->private_data;
+
+	WARN_ON(pps->id != iminor(inode));
+	put_device(&pps->dev);
 	return 0;
 }
 
@@ -331,22 +347,13 @@ static void pps_device_destruct(struct device *dev)
 {
 	struct pps_device *pps = dev_get_drvdata(dev);
 
-	cdev_del(&pps->cdev);
-
-	/* Now we can release the ID for re-use */
 	pr_debug("deallocating pps%d\n", pps->id);
-	mutex_lock(&pps_idr_lock);
-	idr_remove(&pps_idr, pps->id);
-	mutex_unlock(&pps_idr_lock);
-
-	kfree(dev);
 	kfree(pps);
 }
 
 int pps_register_cdev(struct pps_device *pps)
 {
 	int err;
-	dev_t devt;
 
 	mutex_lock(&pps_idr_lock);
 	/*
@@ -363,40 +370,29 @@ int pps_register_cdev(struct pps_device *pps)
 		goto out_unlock;
 	}
 	pps->id = err;
-	mutex_unlock(&pps_idr_lock);
-
-	devt = MKDEV(MAJOR(pps_devt), pps->id);
-
-	cdev_init(&pps->cdev, &pps_cdev_fops);
-	pps->cdev.owner = pps->info.owner;
 
-	err = cdev_add(&pps->cdev, devt, 1);
-	if (err) {
-		pr_err("%s: failed to add char device %d:%d\n",
-				pps->info.name, MAJOR(pps_devt), pps->id);
+	pps->dev.class = pps_class;
+	pps->dev.parent = pps->info.dev;
+	pps->dev.devt = MKDEV(pps_major, pps->id);
+	dev_set_drvdata(&pps->dev, pps);
+	dev_set_name(&pps->dev, "pps%d", pps->id);
+	err = device_register(&pps->dev);
+	if (err)
 		goto free_idr;
-	}
-	pps->dev = device_create(pps_class, pps->info.dev, devt, pps,
-							"pps%d", pps->id);
-	if (IS_ERR(pps->dev)) {
-		err = PTR_ERR(pps->dev);
-		goto del_cdev;
-	}
 
 	/* Override the release function with our own */
-	pps->dev->release = pps_device_destruct;
+	pps->dev.release = pps_device_destruct;
 
-	pr_debug("source %s got cdev (%d:%d)\n", pps->info.name,
-			MAJOR(pps_devt), pps->id);
+	pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, pps_major,
+		 pps->id);
 
+	get_device(&pps->dev);
+	mutex_unlock(&pps_idr_lock);
 	return 0;
 
-del_cdev:
-	cdev_del(&pps->cdev);
-
 free_idr:
-	mutex_lock(&pps_idr_lock);
 	idr_remove(&pps_idr, pps->id);
+	put_device(&pps->dev);
 out_unlock:
 	mutex_unlock(&pps_idr_lock);
 	return err;
@@ -406,7 +402,13 @@ void pps_unregister_cdev(struct pps_device *pps)
 {
 	pr_debug("unregistering pps%d\n", pps->id);
 	pps->lookup_cookie = NULL;
-	device_destroy(pps_class, pps->dev->devt);
+	device_destroy(pps_class, pps->dev.devt);
+
+	/* Now we can release the ID for re-use */
+	mutex_lock(&pps_idr_lock);
+	idr_remove(&pps_idr, pps->id);
+	put_device(&pps->dev);
+	mutex_unlock(&pps_idr_lock);
 }
 
 /*
@@ -426,6 +428,11 @@ void pps_unregister_cdev(struct pps_device *pps)
  * so that it will not be used again, even if the pps device cannot
  * be removed from the idr due to pending references holding the minor
  * number in use.
+ *
+ * Since pps_idr holds a reference to the device, the returned
+ * pps_device is guaranteed to be valid until pps_unregister_cdev() is
+ * called on it. But after calling pps_unregister_cdev(), it may be
+ * freed at any time.
  */
 struct pps_device *pps_lookup_dev(void const *cookie)
 {
@@ -448,13 +455,11 @@ EXPORT_SYMBOL(pps_lookup_dev);
 static void __exit pps_exit(void)
 {
 	class_destroy(pps_class);
-	unregister_chrdev_region(pps_devt, PPS_MAX_SOURCES);
+	__unregister_chrdev(pps_major, 0, PPS_MAX_SOURCES, "pps");
 }
 
 static int __init pps_init(void)
 {
-	int err;
-
 	pps_class = class_create("pps");
 	if (IS_ERR(pps_class)) {
 		pr_err("failed to allocate class\n");
@@ -462,8 +467,9 @@ static int __init pps_init(void)
 	}
 	pps_class->dev_groups = pps_groups;
 
-	err = alloc_chrdev_region(&pps_devt, 0, PPS_MAX_SOURCES, "pps");
-	if (err < 0) {
+	pps_major = __register_chrdev(0, 0, PPS_MAX_SOURCES, "pps",
+				      &pps_cdev_fops);
+	if (pps_major < 0) {
 		pr_err("failed to allocate char device region\n");
 		goto remove_class;
 	}
@@ -476,8 +482,7 @@ static int __init pps_init(void)
 
 remove_class:
 	class_destroy(pps_class);
-
-	return err;
+	return pps_major;
 }
 
 subsys_initcall(pps_init);
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index ea96a14d72d1..bf6468c56419 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2010 OMICRON electronics GmbH
  */
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/posix-clock.h>
 #include <linux/poll.h>
@@ -176,6 +177,9 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 	struct timespec64 ts;
 	int enable, err = 0;
 
+	if (in_compat_syscall() && cmd != PTP_ENABLE_PPS && cmd != PTP_ENABLE_PPS2)
+		arg = (unsigned long)compat_ptr(arg);
+
 	tsevq = pccontext->private_clkdata;
 
 	switch (cmd) {
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index b932425ddc6a..35a5994bf64f 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -217,6 +217,11 @@ static int ptp_getcycles64(struct ptp_clock_info *info, struct timespec64 *ts)
 		return info->gettime64(info, ts);
 }
 
+static int ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on)
+{
+	return -EOPNOTSUPP;
+}
+
 static void ptp_aux_kworker(struct kthread_work *work)
 {
 	struct ptp_clock *ptp = container_of(work, struct ptp_clock,
@@ -294,6 +299,9 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 			ptp->info->getcrosscycles = ptp->info->getcrosststamp;
 	}
 
+	if (!ptp->info->enable)
+		ptp->info->enable = ptp_enable;
+
 	if (ptp->info->do_aux_work) {
 		kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker);
 		ptp->kworker = kthread_run_worker(0, "ptp%d", ptp->index);
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 7f08c70d8123..b651087f426f 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -4420,7 +4420,7 @@ ptp_ocp_complete(struct ptp_ocp *bp)
 
 	pps = pps_lookup_dev(bp->ptp);
 	if (pps)
-		ptp_ocp_symlink(bp, pps->dev, "pps");
+		ptp_ocp_symlink(bp, &pps->dev, "pps");
 
 	ptp_ocp_debugfs_add_device(bp);
 
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 675b252d9c8c..ccd54c089bab 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -242,6 +242,9 @@ int pwm_round_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *
 
 	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
 
+	if (!pwmchip_supports_waveform(chip))
+		return -EOPNOTSUPP;
+
 	if (!pwm_wf_valid(wf))
 		return -EINVAL;
 
@@ -294,6 +297,9 @@ int pwm_get_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *wf
 
 	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
 
+	if (!pwmchip_supports_waveform(chip) || !ops->read_waveform)
+		return -EOPNOTSUPP;
+
 	guard(pwmchip)(chip);
 
 	if (!chip->operational)
@@ -320,6 +326,9 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
 
 	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
 
+	if (!pwmchip_supports_waveform(chip))
+		return -EOPNOTSUPP;
+
 	if (!pwm_wf_valid(wf))
 		return -EINVAL;
 
@@ -592,7 +601,7 @@ static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state)
 	    state->usage_power == pwm->state.usage_power)
 		return 0;
 
-	if (ops->write_waveform) {
+	if (pwmchip_supports_waveform(chip)) {
 		struct pwm_waveform wf;
 		char wfhw[WFHWSIZE];
 
@@ -746,7 +755,7 @@ int pwm_get_state_hw(struct pwm_device *pwm, struct pwm_state *state)
 	if (!chip->operational)
 		return -ENODEV;
 
-	if (ops->read_waveform) {
+	if (pwmchip_supports_waveform(chip) && ops->read_waveform) {
 		char wfhw[WFHWSIZE];
 		struct pwm_waveform wf;
 
@@ -1276,7 +1285,7 @@ static int pwm_export_child(struct device *pwmchip_dev, struct pwm_device *pwm)
 	return 0;
 }
 
-static int pwm_unexport_match(struct device *pwm_dev, void *data)
+static int pwm_unexport_match(struct device *pwm_dev, const void *data)
 {
 	return pwm_from_dev(pwm_dev) == data;
 }
diff --git a/drivers/pwm/pwm-microchip-core.c b/drivers/pwm/pwm-microchip-core.c
index c1f2287b8e97..12821b4bbf97 100644
--- a/drivers/pwm/pwm-microchip-core.c
+++ b/drivers/pwm/pwm-microchip-core.c
@@ -327,7 +327,7 @@ static int mchp_core_pwm_apply_locked(struct pwm_chip *chip, struct pwm_device *
 		 * mchp_core_pwm_calc_period().
 		 * The period is locked and we cannot change this, so we abort.
 		 */
-		if (hw_period_steps == MCHPCOREPWM_PERIOD_STEPS_MAX)
+		if (hw_period_steps > MCHPCOREPWM_PERIOD_STEPS_MAX)
 			return -EINVAL;
 
 		prescale = hw_prescale;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 6c0ef1182248..89578b91c468 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -5033,7 +5033,7 @@ int _regulator_bulk_get(struct device *dev, int num_consumers,
 						       consumers[i].supply, get_type);
 		if (IS_ERR(consumers[i].consumer)) {
 			ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer),
-					    "Failed to get supply '%s'",
+					    "Failed to get supply '%s'\n",
 					    consumers[i].supply);
 			consumers[i].consumer = NULL;
 			goto err;
diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c
index 97f5ce138548..c0f5f0a186a3 100644
--- a/drivers/regulator/tps6287x-regulator.c
+++ b/drivers/regulator/tps6287x-regulator.c
@@ -44,10 +44,35 @@ static const unsigned int tps6287x_voltage_range_sel[] = {
 	0x0, 0x1, 0x2, 0x3
 };
 
+static const unsigned int tps6287x_voltage_range_prefix[] = {
+	0x000, 0x100, 0x200, 0x300
+};
+
 static const unsigned int tps6287x_ramp_table[] = {
 	10000, 5000, 1250, 500
 };
 
+struct tps6287x_reg_data {
+	int range;
+};
+
+static int tps6287x_best_range(struct regulator_config *config, const struct regulator_desc *desc)
+{
+	const struct linear_range *r;
+	int i;
+
+	if (!config->init_data->constraints.apply_uV)
+		return -1;
+
+	for (i = 0; i < desc->n_linear_ranges; i++) {
+		r = &desc->linear_ranges[i];
+		if (r->min <= config->init_data->constraints.min_uV &&
+		    config->init_data->constraints.max_uV <= linear_range_get_max_value(r))
+			return i;
+	}
+	return -1;
+}
+
 static int tps6287x_set_mode(struct regulator_dev *rdev, unsigned int mode)
 {
 	unsigned int val;
@@ -91,6 +116,28 @@ static unsigned int tps6287x_of_map_mode(unsigned int mode)
 	}
 }
 
+static int tps6287x_map_voltage(struct regulator_dev *rdev, int min_uV, int max_uV)
+{
+	struct tps6287x_reg_data *data = (struct tps6287x_reg_data *)rdev->reg_data;
+	struct linear_range selected_range;
+	int selector, voltage;
+
+	if (!data || data->range == -1)
+		return regulator_map_voltage_pickable_linear_range(rdev, min_uV, max_uV);
+
+	selected_range = rdev->desc->linear_ranges[data->range];
+	selector = DIV_ROUND_UP(min_uV - selected_range.min, selected_range.step);
+	if (selector < selected_range.min_sel || selector > selected_range.max_sel)
+		return -EINVAL;
+
+	selector |= tps6287x_voltage_range_prefix[data->range];
+	voltage = rdev->desc->ops->list_voltage(rdev, selector);
+	if (voltage < min_uV || voltage > max_uV)
+		return -EINVAL;
+
+	return selector;
+}
+
 static const struct regulator_ops tps6287x_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -100,6 +147,7 @@ static const struct regulator_ops tps6287x_regulator_ops = {
 	.get_voltage_sel = regulator_get_voltage_sel_pickable_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_pickable_regmap,
 	.list_voltage = regulator_list_voltage_pickable_linear_range,
+	.map_voltage = tps6287x_map_voltage,
 	.set_ramp_delay = regulator_set_ramp_delay_regmap,
 };
 
@@ -130,8 +178,14 @@ static int tps6287x_i2c_probe(struct i2c_client *i2c)
 {
 	struct device *dev = &i2c->dev;
 	struct regulator_config config = {};
+	struct tps6287x_reg_data *reg_data;
 	struct regulator_dev *rdev;
 
+	reg_data = devm_kzalloc(dev, sizeof(struct tps6287x_reg_data), GFP_KERNEL);
+
+	if (!reg_data)
+		return -ENOMEM;
+
 	config.regmap = devm_regmap_init_i2c(i2c, &tps6287x_regmap_config);
 	if (IS_ERR(config.regmap)) {
 		dev_err(dev, "Failed to init i2c\n");
@@ -143,12 +197,15 @@ static int tps6287x_i2c_probe(struct i2c_client *i2c)
 	config.init_data = of_get_regulator_init_data(dev, dev->of_node,
 						      &tps6287x_reg);
 
+	reg_data->range = tps6287x_best_range(&config, &tps6287x_reg);
+
 	rdev = devm_regulator_register(dev, &tps6287x_reg, &config);
 	if (IS_ERR(rdev)) {
 		dev_err(dev, "Failed to register regulator\n");
 		return PTR_ERR(rdev);
 	}
 
+	rdev->reg_data = (void *)reg_data;
 	dev_dbg(dev, "Probed regulator\n");
 
 	return 0;
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index 712c06c02696..207b64c0a2fe 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -377,9 +377,9 @@ EXPORT_SYMBOL(rpmsg_get_mtu);
  * this is used to make sure we're not creating rpmsg devices for channels
  * that already exist.
  */
-static int rpmsg_device_match(struct device *dev, void *data)
+static int rpmsg_device_match(struct device *dev, const void *data)
 {
-	struct rpmsg_channel_info *chinfo = data;
+	const struct rpmsg_channel_info *chinfo = data;
 	struct rpmsg_device *rpdev = to_rpmsg_device(dev);
 
 	if (chinfo->src != RPMSG_ADDR_ANY && chinfo->src != rpdev->src)
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index a60bcc791a48..0bbbf778ecfa 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1316,7 +1316,7 @@ config RTC_DRV_SC27XX
 config RTC_DRV_SPEAR
 	tristate "SPEAR ST RTC"
 	depends on PLAT_SPEAR || COMPILE_TEST
-	default y
+	default PLAT_SPEAR
 	help
 	 If you say Y here you will get support for the RTC found on
 	 spear
diff --git a/drivers/rtc/rtc-88pm80x.c b/drivers/rtc/rtc-88pm80x.c
index 5c39cf252392..a3e52a5a708f 100644
--- a/drivers/rtc/rtc-88pm80x.c
+++ b/drivers/rtc/rtc-88pm80x.c
@@ -308,7 +308,7 @@ static int pm80x_rtc_probe(struct platform_device *pdev)
 	/* remember whether this power up is caused by PMIC RTC or not */
 	info->rtc_dev->dev.platform_data = &pdata->rtc_wakeup;
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	return 0;
 out_rtc:
diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c
index 814230d61842..964cd048fcdb 100644
--- a/drivers/rtc/rtc-88pm860x.c
+++ b/drivers/rtc/rtc-88pm860x.c
@@ -326,7 +326,7 @@ static int pm860x_rtc_probe(struct platform_device *pdev)
 	schedule_delayed_work(&info->calib_work, VRTC_CALIB_INTERVAL);
 #endif	/* VRTC_CALIBRATION */
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-amlogic-a4.c b/drivers/rtc/rtc-amlogic-a4.c
index 2278b4c98a71..09d78c2cc691 100644
--- a/drivers/rtc/rtc-amlogic-a4.c
+++ b/drivers/rtc/rtc-amlogic-a4.c
@@ -361,7 +361,7 @@ static int aml_rtc_probe(struct platform_device *pdev)
 				     "failed to get_enable rtc sys clk\n");
 	aml_rtc_init(rtc);
 
-	device_init_wakeup(dev, 1);
+	device_init_wakeup(dev, true);
 	platform_set_drvdata(pdev, rtc);
 
 	rtc->rtc_dev = devm_rtc_allocate_device(dev);
@@ -391,7 +391,7 @@ static int aml_rtc_probe(struct platform_device *pdev)
 	return 0;
 err_clk:
 	clk_disable_unprepare(rtc->sys_clk);
-	device_init_wakeup(dev, 0);
+	device_init_wakeup(dev, false);
 
 	return ret;
 }
@@ -426,7 +426,7 @@ static void aml_rtc_remove(struct platform_device *pdev)
 	struct aml_rtc_data *rtc = dev_get_drvdata(&pdev->dev);
 
 	clk_disable_unprepare(rtc->sys_clk);
-	device_init_wakeup(&pdev->dev, 0);
+	device_init_wakeup(&pdev->dev, false);
 }
 
 static const struct aml_rtc_config a5_rtc_config = {
diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index 569c1054d6b0..713fa0d077cd 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -527,7 +527,7 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, rtc);
 
 	if (rtc->irq != -1)
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 	else
 		clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features);
 
diff --git a/drivers/rtc/rtc-as3722.c b/drivers/rtc/rtc-as3722.c
index 0f21af27f4cf..9682d6457b7f 100644
--- a/drivers/rtc/rtc-as3722.c
+++ b/drivers/rtc/rtc-as3722.c
@@ -187,7 +187,7 @@ static int as3722_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	as3722_rtc->rtc = devm_rtc_device_register(&pdev->dev, "as3722-rtc",
 				&as3722_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 9b3898b8de7c..f6b0102a843a 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -528,7 +528,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	 * being wake-capable; if it didn't, do that here.
 	 */
 	if (!device_can_wakeup(&pdev->dev))
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 
 	if (at91_rtc_config->has_correction)
 		rtc->ops = &sama5d4_rtc_ops;
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index 15b21da2788f..38991cca5930 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -353,7 +353,7 @@ static int at91_rtc_probe(struct platform_device *pdev)
 
 	/* platform setup code should have handled this; sigh */
 	if (!device_can_wakeup(&pdev->dev))
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 
 	platform_set_drvdata(pdev, rtc);
 
diff --git a/drivers/rtc/rtc-cadence.c b/drivers/rtc/rtc-cadence.c
index bf2a9a1fdea7..8634eea799ab 100644
--- a/drivers/rtc/rtc-cadence.c
+++ b/drivers/rtc/rtc-cadence.c
@@ -359,7 +359,7 @@ static void cdns_rtc_remove(struct platform_device *pdev)
 	struct cdns_rtc *crtc = platform_get_drvdata(pdev);
 
 	cdns_rtc_alarm_irq_enable(&pdev->dev, 0);
-	device_init_wakeup(&pdev->dev, 0);
+	device_init_wakeup(&pdev->dev, false);
 
 	clk_disable_unprepare(crtc->pclk);
 	clk_disable_unprepare(crtc->ref_clk);
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 78f2ce12c75a..8172869bd3d7 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -151,11 +151,6 @@ static inline int hpet_set_periodic_freq(unsigned long freq)
 	return 0;
 }
 
-static inline int hpet_rtc_dropped_irq(void)
-{
-	return 0;
-}
-
 static inline int hpet_rtc_timer_init(void)
 {
 	return 0;
@@ -864,7 +859,7 @@ static void acpi_cmos_wake_setup(struct device *dev)
 		dev_info(dev, "RTC can wake from S4\n");
 
 	/* RTC always wakes from S1/S2/S3, and often S4/STD */
-	device_init_wakeup(dev, 1);
+	device_init_wakeup(dev, true);
 }
 
 static void cmos_check_acpi_rtc_status(struct device *dev,
diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c
index afc8fcba8f88..568a89e79c11 100644
--- a/drivers/rtc/rtc-cpcap.c
+++ b/drivers/rtc/rtc-cpcap.c
@@ -295,7 +295,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev)
 	}
 	disable_irq(rtc->update_irq);
 
-	err = device_init_wakeup(dev, 1);
+	err = device_init_wakeup(dev, true);
 	if (err) {
 		dev_err(dev, "wakeup initialization failed (%d)\n", err);
 		/* ignore error and continue without wakeup support */
diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c
index 60a48c3ba3ca..865c2e82c7a5 100644
--- a/drivers/rtc/rtc-cros-ec.c
+++ b/drivers/rtc/rtc-cros-ec.c
@@ -337,7 +337,7 @@ static int cros_ec_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = device_init_wakeup(&pdev->dev, 1);
+	ret = device_init_wakeup(&pdev->dev, true);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to initialize wakeup\n");
 		return ret;
diff --git a/drivers/rtc/rtc-da9055.c b/drivers/rtc/rtc-da9055.c
index 844168fcae1e..05adec6b77bf 100644
--- a/drivers/rtc/rtc-da9055.c
+++ b/drivers/rtc/rtc-da9055.c
@@ -288,7 +288,7 @@ static int da9055_rtc_probe(struct platform_device *pdev)
 	if (ret & DA9055_RTC_ALM_EN)
 		rtc->alarm_enable = 1;
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
 					&da9055_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c
index dd37b055693c..19c09c418746 100644
--- a/drivers/rtc/rtc-ds3232.c
+++ b/drivers/rtc/rtc-ds3232.c
@@ -508,7 +508,7 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq,
 		return ret;
 
 	if (ds3232->irq > 0)
-		device_init_wakeup(dev, 1);
+		device_init_wakeup(dev, true);
 
 	ds3232_hwmon_register(dev, name);
 
diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
index 7b82e4a14b7a..f71a6bb77b2a 100644
--- a/drivers/rtc/rtc-isl1208.c
+++ b/drivers/rtc/rtc-isl1208.c
@@ -830,7 +830,7 @@ static int isl1208_setup_irq(struct i2c_client *client, int irq)
 					isl1208_driver.driver.name,
 					client);
 	if (!rc) {
-		device_init_wakeup(&client->dev, 1);
+		device_init_wakeup(&client->dev, true);
 		enable_irq_wake(irq);
 	} else {
 		dev_err(&client->dev,
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index bafa7d1b9b88..44bba356268c 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -367,7 +367,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc);
 
-	device_init_wakeup(dev, 1);
+	device_init_wakeup(dev, true);
 
 	ret = dev_pm_set_wake_irq(dev, irq);
 	if (ret)
diff --git a/drivers/rtc/rtc-loongson.c b/drivers/rtc/rtc-loongson.c
index 8d713e563d7c..97e5625c064c 100644
--- a/drivers/rtc/rtc-loongson.c
+++ b/drivers/rtc/rtc-loongson.c
@@ -114,6 +114,13 @@ static irqreturn_t loongson_rtc_isr(int irq, void *id)
 	struct loongson_rtc_priv *priv = (struct loongson_rtc_priv *)id;
 
 	rtc_update_irq(priv->rtcdev, 1, RTC_AF | RTC_IRQF);
+
+	/*
+	 * The TOY_MATCH0_REG should be cleared 0 here,
+	 * otherwise the interrupt cannot be cleared.
+	 */
+	regmap_write(priv->regmap, TOY_MATCH0_REG, 0);
+
 	return IRQ_HANDLED;
 }
 
@@ -131,11 +138,7 @@ static u32 loongson_rtc_handler(void *id)
 	writel(RTC_STS, priv->pm_base + PM1_STS_REG);
 	spin_unlock(&priv->lock);
 
-	/*
-	 * The TOY_MATCH0_REG should be cleared 0 here,
-	 * otherwise the interrupt cannot be cleared.
-	 */
-	return regmap_write(priv->regmap, TOY_MATCH0_REG, 0);
+	return ACPI_INTERRUPT_HANDLED;
 }
 
 static int loongson_rtc_set_enabled(struct device *dev)
@@ -329,7 +332,7 @@ static int loongson_rtc_probe(struct platform_device *pdev)
 					     alarm_irq);
 
 		priv->pm_base = regs - priv->config->pm_offset;
-		device_init_wakeup(dev, 1);
+		device_init_wakeup(dev, true);
 
 		if (has_acpi_companion(dev))
 			acpi_install_fixed_event_handler(ACPI_EVENT_RTC,
@@ -360,7 +363,7 @@ static void loongson_rtc_remove(struct platform_device *pdev)
 		acpi_remove_fixed_event_handler(ACPI_EVENT_RTC,
 						loongson_rtc_handler);
 
-	device_init_wakeup(dev, 0);
+	device_init_wakeup(dev, false);
 	loongson_rtc_alarm_irq_enable(dev, 0);
 }
 
diff --git a/drivers/rtc/rtc-lp8788.c b/drivers/rtc/rtc-lp8788.c
index c0b8fbce1082..0793d70507f7 100644
--- a/drivers/rtc/rtc-lp8788.c
+++ b/drivers/rtc/rtc-lp8788.c
@@ -293,7 +293,7 @@ static int lp8788_rtc_probe(struct platform_device *pdev)
 	rtc->alarm = lp->pdata ? lp->pdata->alarm_sel : DEFAULT_ALARM_SEL;
 	platform_set_drvdata(pdev, rtc);
 
-	device_init_wakeup(dev, 1);
+	device_init_wakeup(dev, true);
 
 	rtc->rdev = devm_rtc_device_register(dev, "lp8788_rtc",
 					&lp8788_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c
index 76ad7031a13d..74280bffe1b0 100644
--- a/drivers/rtc/rtc-lpc32xx.c
+++ b/drivers/rtc/rtc-lpc32xx.c
@@ -257,7 +257,7 @@ static int lpc32xx_rtc_probe(struct platform_device *pdev)
 			dev_warn(&pdev->dev, "Can't request interrupt.\n");
 			rtc->irq = -1;
 		} else {
-			device_init_wakeup(&pdev->dev, 1);
+			device_init_wakeup(&pdev->dev, true);
 		}
 	}
 
diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index a8f4b645c09d..7bb044d2ac25 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -770,7 +770,7 @@ static int max77686_rtc_probe(struct platform_device *pdev)
 		goto err_rtc;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	info->rtc_dev = devm_rtc_device_register(&pdev->dev, id->name,
 					&max77686_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-max8925.c b/drivers/rtc/rtc-max8925.c
index 64bb8ac6ef62..6ce8afbeac68 100644
--- a/drivers/rtc/rtc-max8925.c
+++ b/drivers/rtc/rtc-max8925.c
@@ -270,7 +270,7 @@ static int max8925_rtc_probe(struct platform_device *pdev)
 	/* XXX - isn't this redundant? */
 	platform_set_drvdata(pdev, info);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max8925-rtc",
 					&max8925_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-max8997.c b/drivers/rtc/rtc-max8997.c
index 20e50d9fdf88..e7618d715bd8 100644
--- a/drivers/rtc/rtc-max8997.c
+++ b/drivers/rtc/rtc-max8997.c
@@ -473,7 +473,7 @@ static int max8997_rtc_probe(struct platform_device *pdev)
 	max8997_rtc_enable_wtsr(info, true);
 	max8997_rtc_enable_smpl(info, true);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max8997-rtc",
 					&max8997_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c
index 648fa362ec44..5849729f7d01 100644
--- a/drivers/rtc/rtc-meson-vrtc.c
+++ b/drivers/rtc/rtc-meson-vrtc.c
@@ -74,7 +74,7 @@ static int meson_vrtc_probe(struct platform_device *pdev)
 	if (IS_ERR(vrtc->io_alarm))
 		return PTR_ERR(vrtc->io_alarm);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	platform_set_drvdata(pdev, vrtc);
 
diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c
index 600328131603..b90f8337a7e6 100644
--- a/drivers/rtc/rtc-mpc5121.c
+++ b/drivers/rtc/rtc-mpc5121.c
@@ -303,7 +303,7 @@ static int mpc5121_rtc_probe(struct platform_device *op)
 		return PTR_ERR(rtc->regs);
 	}
 
-	device_init_wakeup(&op->dev, 1);
+	device_init_wakeup(&op->dev, true);
 
 	platform_set_drvdata(op, rtc);
 
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 152699219a2b..6979d225a78e 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -286,7 +286,7 @@ static int mtk_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	rtc->rtc_dev->ops = &mtk_rtc_ops;
 	rtc->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_1900;
diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c
index 51029c536244..c27ad626d09f 100644
--- a/drivers/rtc/rtc-mv.c
+++ b/drivers/rtc/rtc-mv.c
@@ -264,7 +264,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev)
 	}
 
 	if (pdata->irq >= 0)
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 	else
 		clear_bit(RTC_FEATURE_ALARM, pdata->rtc->features);
 
@@ -287,7 +287,7 @@ static void __exit mv_rtc_remove(struct platform_device *pdev)
 	struct rtc_plat_data *pdata = platform_get_drvdata(pdev);
 
 	if (pdata->irq >= 0)
-		device_init_wakeup(&pdev->dev, 0);
+		device_init_wakeup(&pdev->dev, false);
 
 	if (!IS_ERR(pdata->clk))
 		clk_disable_unprepare(pdata->clk);
diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c
index dbb935dbbd8a..608db97d450c 100644
--- a/drivers/rtc/rtc-mxc.c
+++ b/drivers/rtc/rtc-mxc.c
@@ -377,7 +377,7 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 	}
 
 	if (pdata->irq >= 0) {
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 		ret = dev_pm_set_wake_irq(&pdev->dev, pdata->irq);
 		if (ret)
 			dev_err(&pdev->dev, "failed to enable irq wake\n");
diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c
index 13c041bb79f1..570f27af4732 100644
--- a/drivers/rtc/rtc-mxc_v2.c
+++ b/drivers/rtc/rtc-mxc_v2.c
@@ -302,7 +302,7 @@ static int mxc_rtc_probe(struct platform_device *pdev)
 	if (pdata->irq < 0)
 		return pdata->irq;
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 	ret = dev_pm_set_wake_irq(&pdev->dev, pdata->irq);
 	if (ret)
 		dev_err(&pdev->dev, "failed to enable irq wake\n");
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index c123778e2d9b..0f90065e352c 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -920,7 +920,7 @@ static void omap_rtc_remove(struct platform_device *pdev)
 		omap_rtc_power_off_rtc = NULL;
 	}
 
-	device_init_wakeup(&pdev->dev, 0);
+	device_init_wakeup(&pdev->dev, false);
 
 	if (!IS_ERR(rtc->clk))
 		clk_disable_unprepare(rtc->clk);
diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c
index 7256a88b490c..aecada6bcf8b 100644
--- a/drivers/rtc/rtc-palmas.c
+++ b/drivers/rtc/rtc-palmas.c
@@ -287,7 +287,7 @@ static int palmas_rtc_probe(struct platform_device *pdev)
 
 	palmas_rtc->irq = platform_get_irq(pdev, 0);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 	palmas_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
 				&palmas_rtc_ops, THIS_MODULE);
 	if (IS_ERR(palmas_rtc->rtc)) {
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 9c04c4e1a49c..31c7dca8f469 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -20,6 +20,7 @@
 #include <linux/i2c.h>
 #include <linux/spi/spi.h>
 #include <linux/bcd.h>
+#include <linux/bitfield.h>
 #include <linux/rtc.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -48,6 +49,7 @@
 #define PCF2127_BIT_CTRL3_BLF			BIT(2)
 #define PCF2127_BIT_CTRL3_BF			BIT(3)
 #define PCF2127_BIT_CTRL3_BTSE			BIT(4)
+#define PCF2127_CTRL3_PM			GENMASK(7, 5)
 /* Time and date registers */
 #define PCF2127_REG_TIME_BASE		0x03
 #define PCF2127_BIT_SC_OSF			BIT(7)
@@ -331,6 +333,84 @@ static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	return 0;
 }
 
+static int pcf2127_param_get(struct device *dev, struct rtc_param *param)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	u32 value;
+	int ret;
+
+	switch (param->param) {
+	case RTC_PARAM_BACKUP_SWITCH_MODE:
+		ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &value);
+		if (ret < 0)
+			return ret;
+
+		value = FIELD_GET(PCF2127_CTRL3_PM, value);
+
+		if (value < 0x3)
+			param->uvalue = RTC_BSM_LEVEL;
+		else if (value < 0x6)
+			param->uvalue = RTC_BSM_DIRECT;
+		else
+			param->uvalue = RTC_BSM_DISABLED;
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int pcf2127_param_set(struct device *dev, struct rtc_param *param)
+{
+	struct pcf2127 *pcf2127 = dev_get_drvdata(dev);
+	u8 mode = 0;
+	u32 value;
+	int ret;
+
+	switch (param->param) {
+	case RTC_PARAM_BACKUP_SWITCH_MODE:
+		ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &value);
+		if (ret < 0)
+			return ret;
+
+		value = FIELD_GET(PCF2127_CTRL3_PM, value);
+
+		if (value > 5)
+			value -= 5;
+		else if (value > 2)
+			value -= 3;
+
+		switch (param->uvalue) {
+		case RTC_BSM_LEVEL:
+			break;
+		case RTC_BSM_DIRECT:
+			mode = 3;
+			break;
+		case RTC_BSM_DISABLED:
+			if (value == 0)
+				value = 1;
+			mode = 5;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		return regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL3,
+					  PCF2127_CTRL3_PM,
+					  FIELD_PREP(PCF2127_CTRL3_PM, mode + value));
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int pcf2127_rtc_ioctl(struct device *dev,
 				unsigned int cmd, unsigned long arg)
 {
@@ -741,6 +821,8 @@ static const struct rtc_class_ops pcf2127_rtc_ops = {
 	.read_alarm       = pcf2127_rtc_read_alarm,
 	.set_alarm        = pcf2127_rtc_set_alarm,
 	.alarm_irq_enable = pcf2127_rtc_alarm_irq_enable,
+	.param_get        = pcf2127_param_get,
+	.param_set        = pcf2127_param_set,
 };
 
 /* sysfs interface */
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index fdbc07f14036..905986c61655 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -322,7 +322,16 @@ static const struct rtc_class_ops pcf85063_rtc_ops = {
 static int pcf85063_nvmem_read(void *priv, unsigned int offset,
 			       void *val, size_t bytes)
 {
-	return regmap_read(priv, PCF85063_REG_RAM, val);
+	unsigned int tmp;
+	int ret;
+
+	ret = regmap_read(priv, PCF85063_REG_RAM, &tmp);
+	if (ret < 0)
+		return ret;
+
+	*(u8 *)val = tmp;
+
+	return 0;
 }
 
 static int pcf85063_nvmem_write(void *priv, unsigned int offset,
diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c
index bed3c27e665f..2812da2c50c5 100644
--- a/drivers/rtc/rtc-pic32.c
+++ b/drivers/rtc/rtc-pic32.c
@@ -330,7 +330,7 @@ static int pic32_rtc_probe(struct platform_device *pdev)
 
 	pic32_rtc_enable(pdata, 1);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	pdata->rtc->ops = &pic32_rtcops;
 	pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index 2f32187ecc8d..b2518aea4218 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -503,7 +503,7 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, rtc_dd);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	rtc_dd->rtc = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(rtc_dd->rtc))
diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c
index 34d8545c8e15..62ee6b8f9bcd 100644
--- a/drivers/rtc/rtc-pxa.c
+++ b/drivers/rtc/rtc-pxa.c
@@ -360,7 +360,7 @@ static int __init pxa_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	device_init_wakeup(dev, 1);
+	device_init_wakeup(dev, true);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-rc5t583.c b/drivers/rtc/rtc-rc5t583.c
index eecb49bab56a..8ba9cda74acf 100644
--- a/drivers/rtc/rtc-rc5t583.c
+++ b/drivers/rtc/rtc-rc5t583.c
@@ -245,7 +245,7 @@ static int rc5t583_rtc_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "IRQ is not free.\n");
 		return ret;
 	}
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	ricoh_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
 		&rc5t583_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-rc5t619.c b/drivers/rtc/rtc-rc5t619.c
index 711f62eecd79..74d169102074 100644
--- a/drivers/rtc/rtc-rc5t619.c
+++ b/drivers/rtc/rtc-rc5t619.c
@@ -414,7 +414,7 @@ static int rc5t619_rtc_probe(struct platform_device *pdev)
 
 		} else {
 			/* enable wake */
-			device_init_wakeup(&pdev->dev, 1);
+			device_init_wakeup(&pdev->dev, true);
 			enable_irq_wake(rtc->irq);
 		}
 	} else {
diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c
index d127933bfc8a..a056291d3887 100644
--- a/drivers/rtc/rtc-renesas-rtca3.c
+++ b/drivers/rtc/rtc-renesas-rtca3.c
@@ -768,7 +768,7 @@ static int rtca3_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	priv->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(priv->rtc_dev))
diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c
index 2d9bcb3ce1e3..59b8e9a30fe6 100644
--- a/drivers/rtc/rtc-rk808.c
+++ b/drivers/rtc/rtc-rk808.c
@@ -418,7 +418,7 @@ static int rk808_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	rk808_rtc->rtc = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(rk808_rtc->rtc))
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index c0ac3bdb2f42..58c957eb753d 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -456,7 +456,7 @@ static int s3c_rtc_probe(struct platform_device *pdev)
 	dev_dbg(&pdev->dev, "s3c2410_rtc: RTCCON=%02x\n",
 		readw(info->base + S3C2410_RTCCON));
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	info->rtc = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(info->rtc)) {
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index dad294a0ce2a..36acca5b2639 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -729,7 +729,7 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 				info->irq, ret);
 			return ret;
 		}
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 	}
 
 	return devm_rtc_register_device(info->rtc_dev);
diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c
index 13799b1abca1..1ad93648d69c 100644
--- a/drivers/rtc/rtc-sa1100.c
+++ b/drivers/rtc/rtc-sa1100.c
@@ -292,7 +292,7 @@ static int sa1100_rtc_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, info);
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	return sa1100_rtc_init(pdev, info);
 }
diff --git a/drivers/rtc/rtc-sc27xx.c b/drivers/rtc/rtc-sc27xx.c
index ce7a2ddbbc16..2b83561d4d28 100644
--- a/drivers/rtc/rtc-sc27xx.c
+++ b/drivers/rtc/rtc-sc27xx.c
@@ -613,14 +613,14 @@ static int sprd_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	rtc->rtc->ops = &sprd_rtc_ops;
 	rtc->rtc->range_min = 0;
 	rtc->rtc->range_max = 5662310399LL;
 	ret = devm_rtc_register_device(rtc->rtc);
 	if (ret) {
-		device_init_wakeup(&pdev->dev, 0);
+		device_init_wakeup(&pdev->dev, false);
 		return ret;
 	}
 
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index a5df521876ba..9ea40f40188f 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -611,7 +611,7 @@ static int __init sh_rtc_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unmap;
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 	return 0;
 
 err_unmap:
diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c
index 26eed927f8b3..959acff8faff 100644
--- a/drivers/rtc/rtc-spear.c
+++ b/drivers/rtc/rtc-spear.c
@@ -395,7 +395,7 @@ static int spear_rtc_probe(struct platform_device *pdev)
 		goto err_disable_clock;
 
 	if (!device_can_wakeup(&pdev->dev))
-		device_init_wakeup(&pdev->dev, 1);
+		device_init_wakeup(&pdev->dev, true);
 
 	return 0;
 
@@ -411,7 +411,7 @@ static void spear_rtc_remove(struct platform_device *pdev)
 
 	spear_rtc_disable_interrupt(config);
 	clk_disable_unprepare(config->clk);
-	device_init_wakeup(&pdev->dev, 0);
+	device_init_wakeup(&pdev->dev, false);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 9f1a019ec8af..a0564d443569 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -1074,26 +1074,18 @@ static int stm32_rtc_probe(struct platform_device *pdev)
 	regs = &rtc->data->regs;
 
 	if (rtc->data->need_dbp) {
-		rtc->dbp = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
-							   "st,syscfg");
+		unsigned int args[2];
+
+		rtc->dbp = syscon_regmap_lookup_by_phandle_args(pdev->dev.of_node,
+								"st,syscfg",
+								2, args);
 		if (IS_ERR(rtc->dbp)) {
 			dev_err(&pdev->dev, "no st,syscfg\n");
 			return PTR_ERR(rtc->dbp);
 		}
 
-		ret = of_property_read_u32_index(pdev->dev.of_node, "st,syscfg",
-						 1, &rtc->dbp_reg);
-		if (ret) {
-			dev_err(&pdev->dev, "can't read DBP register offset\n");
-			return ret;
-		}
-
-		ret = of_property_read_u32_index(pdev->dev.of_node, "st,syscfg",
-						 2, &rtc->dbp_mask);
-		if (ret) {
-			dev_err(&pdev->dev, "can't read DBP register mask\n");
-			return ret;
-		}
+		rtc->dbp_reg = args[0];
+		rtc->dbp_mask = args[1];
 	}
 
 	if (!rtc->data->has_pclk) {
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index e681c1745866..e5e6013d080e 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -826,7 +826,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev)
 
 	clk_prepare_enable(chip->losc);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	chip->rtc = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(chip->rtc))
diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c
index 9b1ce0e8ba27..519a06e728d6 100644
--- a/drivers/rtc/rtc-sunplus.c
+++ b/drivers/rtc/rtc-sunplus.c
@@ -269,7 +269,7 @@ static int sp_rtc_probe(struct platform_device *plat_dev)
 	if (ret)
 		goto free_reset_assert;
 
-	device_init_wakeup(&plat_dev->dev, 1);
+	device_init_wakeup(&plat_dev->dev, true);
 	dev_set_drvdata(&plat_dev->dev, sp_rtc);
 
 	sp_rtc->rtc = devm_rtc_allocate_device(&plat_dev->dev);
@@ -307,7 +307,7 @@ static void sp_rtc_remove(struct platform_device *plat_dev)
 {
 	struct sunplus_rtc *sp_rtc = dev_get_drvdata(&plat_dev->dev);
 
-	device_init_wakeup(&plat_dev->dev, 0);
+	device_init_wakeup(&plat_dev->dev, false);
 	reset_control_assert(sp_rtc->rstc);
 	clk_disable_unprepare(sp_rtc->rtcclk);
 }
diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c
index 79a3102c8354..46788db89953 100644
--- a/drivers/rtc/rtc-tegra.c
+++ b/drivers/rtc/rtc-tegra.c
@@ -319,7 +319,7 @@ static int tegra_rtc_probe(struct platform_device *pdev)
 	writel(0xffffffff, info->base + TEGRA_RTC_REG_INTR_STATUS);
 	writel(0, info->base + TEGRA_RTC_REG_INTR_MASK);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	ret = devm_request_irq(&pdev->dev, info->irq, tegra_rtc_irq_handler,
 			       IRQF_TRIGGER_HIGH, dev_name(&pdev->dev),
diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c
index 7e0d8fb26465..a68b8c884102 100644
--- a/drivers/rtc/rtc-test.c
+++ b/drivers/rtc/rtc-test.c
@@ -132,7 +132,7 @@ static int test_probe(struct platform_device *plat_dev)
 		break;
 	default:
 		rtd->rtc->ops = &test_rtc_ops;
-		device_init_wakeup(&plat_dev->dev, 1);
+		device_init_wakeup(&plat_dev->dev, true);
 	}
 
 	timer_setup(&rtd->alarm, test_rtc_alarm_handler, 0);
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index e796729fc817..54c8429b16bf 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -241,7 +241,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	platform_set_drvdata(pdev, rtc);
 	rtc->rtc = devm_rtc_allocate_device(&pdev->dev);
diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
index 2ea1bbfbbc2a..284aa2f0392b 100644
--- a/drivers/rtc/rtc-tps65910.c
+++ b/drivers/rtc/rtc-tps65910.c
@@ -418,7 +418,7 @@ static int tps65910_rtc_probe(struct platform_device *pdev)
 	tps_rtc->irq = irq;
 	if (irq != -1) {
 		if (device_property_present(tps65910->dev, "wakeup-source"))
-			device_init_wakeup(&pdev->dev, 1);
+			device_init_wakeup(&pdev->dev, true);
 		else
 			device_set_wakeup_capable(&pdev->dev, 1);
 	} else {
diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c
index e69667634137..7c6246e3f029 100644
--- a/drivers/rtc/rtc-tps6594.c
+++ b/drivers/rtc/rtc-tps6594.c
@@ -37,7 +37,7 @@
 #define MAX_OFFSET (277774)
 
 // Number of ticks per hour
-#define TICKS_PER_HOUR (32768 * 3600)
+#define TICKS_PER_HOUR (32768 * 3600LL)
 
 // Multiplier for ppb conversions
 #define PPB_MULT NANO
diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index 794429182b34..e6106e67e1f4 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -572,7 +572,7 @@ static int twl_rtc_probe(struct platform_device *pdev)
 		return ret;
 
 	platform_set_drvdata(pdev, twl_rtc);
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	twl_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
 					&twl_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c
index 640833e21057..218316be942a 100644
--- a/drivers/rtc/rtc-wm831x.c
+++ b/drivers/rtc/rtc-wm831x.c
@@ -420,7 +420,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev)
 	if (ret & WM831X_RTC_ALM_ENA)
 		wm831x_rtc->alarm_enabled = 1;
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	wm831x_rtc->rtc = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(wm831x_rtc->rtc))
diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c
index 6797eb4d2e49..3bd60d067a5e 100644
--- a/drivers/rtc/rtc-wm8350.c
+++ b/drivers/rtc/rtc-wm8350.c
@@ -420,7 +420,7 @@ static int wm8350_rtc_probe(struct platform_device *pdev)
 		}
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	wm_rtc->rtc = devm_rtc_device_register(&pdev->dev, "wm8350",
 					&wm8350_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c
index 0813ea1a03c2..6660b664e8dd 100644
--- a/drivers/rtc/rtc-xgene.c
+++ b/drivers/rtc/rtc-xgene.c
@@ -174,7 +174,7 @@ static int xgene_rtc_probe(struct platform_device *pdev)
 	/* Turn on the clock and the crystal */
 	writel(RTC_CCR_EN, pdata->csr_base + RTC_CCR);
 
-	ret = device_init_wakeup(&pdev->dev, 1);
+	ret = device_init_wakeup(&pdev->dev, true);
 	if (ret) {
 		clk_disable_unprepare(pdata->clk);
 		return ret;
@@ -197,7 +197,7 @@ static void xgene_rtc_remove(struct platform_device *pdev)
 	struct xgene_rtc_dev *pdata = platform_get_drvdata(pdev);
 
 	xgene_rtc_alarm_irq_enable(&pdev->dev, 0);
-	device_init_wakeup(&pdev->dev, 0);
+	device_init_wakeup(&pdev->dev, false);
 	clk_disable_unprepare(pdata->clk);
 }
 
diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c
index af1abb69d1e3..f39102b66eac 100644
--- a/drivers/rtc/rtc-zynqmp.c
+++ b/drivers/rtc/rtc-zynqmp.c
@@ -318,8 +318,8 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/* Getting the rtc_clk info */
-	xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc_clk");
+	/* Getting the rtc info */
+	xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc");
 	if (IS_ERR(xrtcdev->rtc_clk)) {
 		if (PTR_ERR(xrtcdev->rtc_clk) != -EPROBE_DEFER)
 			dev_warn(&pdev->dev, "Device clock not found.\n");
@@ -337,7 +337,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 
 	xlnx_init_rtc(xrtcdev);
 
-	device_init_wakeup(&pdev->dev, 1);
+	device_init_wakeup(&pdev->dev, true);
 
 	return devm_rtc_register_device(xrtcdev->rtc);
 }
@@ -345,7 +345,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev)
 static void xlnx_rtc_remove(struct platform_device *pdev)
 {
 	xlnx_rtc_alarm_irq_enable(&pdev->dev, 0);
-	device_init_wakeup(&pdev->dev, 0);
+	device_init_wakeup(&pdev->dev, false);
 }
 
 static int __maybe_unused xlnx_rtc_suspend(struct device *dev)
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index fbffd451031f..45bd001206a2 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -245,7 +245,6 @@ static void sclp_request_timeout(bool force_restart);
 static void sclp_process_queue(void);
 static void __sclp_make_read_req(void);
 static int sclp_init_mask(int calculate);
-static int sclp_init(void);
 
 static void
 __sclp_queue_read_req(void)
@@ -1251,8 +1250,7 @@ static struct platform_driver sclp_pdrv = {
 
 /* Initialize SCLP driver. Return zero if driver is operational, non-zero
  * otherwise. */
-static int
-sclp_init(void)
+int sclp_init(void)
 {
 	unsigned long flags;
 	int rc = 0;
@@ -1305,13 +1303,7 @@ fail_unlock:
 
 static __init int sclp_initcall(void)
 {
-	int rc;
-
-	rc = platform_driver_register(&sclp_pdrv);
-	if (rc)
-		return rc;
-
-	return sclp_init();
+	return platform_driver_register(&sclp_pdrv);
 }
 
 arch_initcall(sclp_initcall);
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 3dd50ac9c5b0..b2d93a6e36c4 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -123,7 +123,7 @@ static DECLARE_WAIT_QUEUE_HEAD(read_wait_queue);
  */
 
 static struct vmlogrdr_priv_t sys_ser[] = {
-	{ .system_service = "*LOGREC ",
+	{ .system_service = { '*', 'L', 'O', 'G', 'R', 'E', 'C', ' ' },
 	  .internal_name  = "logrec",
 	  .recording_name = "EREP",
 	  .minor_num      = 0,
@@ -132,7 +132,7 @@ static struct vmlogrdr_priv_t sys_ser[] = {
 	  .autorecording  = 1,
 	  .autopurge      = 1,
 	},
-	{ .system_service = "*ACCOUNT",
+	{ .system_service = { '*', 'A', 'C', 'C', 'O', 'U', 'N', 'T' },
 	  .internal_name  = "account",
 	  .recording_name = "ACCOUNT",
 	  .minor_num      = 1,
@@ -141,7 +141,7 @@ static struct vmlogrdr_priv_t sys_ser[] = {
 	  .autorecording  = 1,
 	  .autopurge      = 1,
 	},
-	{ .system_service = "*SYMPTOM",
+	{ .system_service = { '*', 'S', 'Y', 'M', 'P', 'T', 'O', 'M' },
 	  .internal_name  = "symptom",
 	  .recording_name = "SYMPTOM",
 	  .minor_num      = 2,
@@ -356,7 +356,7 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp)
 	if (connect_rc) {
 		pr_err("vmlogrdr: iucv connection to %s "
 		       "failed with rc %i \n",
-		       logptr->system_service, connect_rc);
+		       logptr->internal_name, connect_rc);
 		goto out_path;
 	}
 
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index cba2d048a96b..4a0b3f19bd8e 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -128,7 +128,7 @@ static int s390_vary_chpid(struct chp_id chpid, int on)
  * Channel measurement related functions
  */
 static ssize_t measurement_chars_read(struct file *filp, struct kobject *kobj,
-				      struct bin_attribute *bin_attr,
+				      const struct bin_attribute *bin_attr,
 				      char *buf, loff_t off, size_t count)
 {
 	struct channel_path *chp;
@@ -142,11 +142,11 @@ static ssize_t measurement_chars_read(struct file *filp, struct kobject *kobj,
 	return memory_read_from_buffer(buf, count, &off, &chp->cmg_chars,
 				       sizeof(chp->cmg_chars));
 }
-static BIN_ATTR_ADMIN_RO(measurement_chars, sizeof(struct cmg_chars));
+static const BIN_ATTR_ADMIN_RO(measurement_chars, sizeof(struct cmg_chars));
 
 static ssize_t measurement_chars_full_read(struct file *filp,
 					   struct kobject *kobj,
-					   struct bin_attribute *bin_attr,
+					   const struct bin_attribute *bin_attr,
 					   char *buf, loff_t off, size_t count)
 {
 	struct channel_path *chp = to_channelpath(kobj_to_dev(kobj));
@@ -196,22 +196,22 @@ static ssize_t chp_measurement_copy_block(void *buf, loff_t off, size_t count,
 }
 
 static ssize_t measurement_read(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	return chp_measurement_copy_block(buf, off, count, kobj, false);
 }
-static BIN_ATTR_ADMIN_RO(measurement, sizeof(struct cmg_entry));
+static const BIN_ATTR_ADMIN_RO(measurement, sizeof(struct cmg_entry));
 
 static ssize_t ext_measurement_read(struct file *filp, struct kobject *kobj,
-				    struct bin_attribute *bin_attr,
+				    const struct bin_attribute *bin_attr,
 				    char *buf, loff_t off, size_t count)
 {
 	return chp_measurement_copy_block(buf, off, count, kobj, true);
 }
-static BIN_ATTR_ADMIN_RO(ext_measurement, sizeof(struct cmg_ext_entry));
+static const BIN_ATTR_ADMIN_RO(ext_measurement, sizeof(struct cmg_ext_entry));
 
-static struct bin_attribute *measurement_attrs[] = {
+static const struct bin_attribute *measurement_attrs[] = {
 	&bin_attr_measurement_chars,
 	&bin_attr_measurement_chars_full,
 	&bin_attr_measurement,
@@ -435,7 +435,7 @@ static ssize_t speed_bps_show(struct device *dev,
 static DEVICE_ATTR_RO(speed_bps);
 
 static ssize_t util_string_read(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *attr, char *buf,
+				const struct bin_attribute *attr, char *buf,
 				loff_t off, size_t count)
 {
 	struct channel_path *chp = to_channelpath(kobj_to_dev(kobj));
@@ -448,10 +448,10 @@ static ssize_t util_string_read(struct file *filp, struct kobject *kobj,
 
 	return rc;
 }
-static BIN_ATTR_RO(util_string,
-		   sizeof(((struct channel_path_desc_fmt3 *)0)->util_str));
+static const BIN_ATTR_RO(util_string,
+			 sizeof(((struct channel_path_desc_fmt3 *)0)->util_str));
 
-static struct bin_attribute *chp_bin_attrs[] = {
+static const struct bin_attribute *const chp_bin_attrs[] = {
 	&bin_attr_util_string,
 	NULL,
 };
@@ -468,9 +468,9 @@ static struct attribute *chp_attrs[] = {
 	&dev_attr_speed_bps.attr,
 	NULL,
 };
-static struct attribute_group chp_attr_group = {
+static const struct attribute_group chp_attr_group = {
 	.attrs = chp_attrs,
-	.bin_attrs = chp_bin_attrs,
+	.bin_attrs_new = chp_bin_attrs,
 };
 static const struct attribute_group *chp_attr_groups[] = {
 	&chp_attr_group,
diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index d6516ab00437..1d50f463afe7 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -537,6 +537,11 @@ static void zfcp_fc_adisc_handler(void *data)
 	/* port is still good, nothing to do */
  out:
 	atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status);
+	/*
+	 * port ref comes from get_device() in zfcp_fc_test_link() and
+	 * work item zfcp_fc_link_test_work() passes ref via
+	 * zfcp_fc_adisc() to here, if zfcp_fc_adisc() could send ADISC
+	 */
 	put_device(&port->dev);
 	kmem_cache_free(zfcp_fc_req_cache, fc_req);
 }
@@ -603,7 +608,7 @@ void zfcp_fc_link_test_work(struct work_struct *work)
 
 	retval = zfcp_fc_adisc(port);
 	if (retval == 0)
-		return;
+		return; /* port ref passed to zfcp_fc_adisc(), no put here */
 
 	/* send of ADISC was not possible */
 	atomic_andnot(ZFCP_STATUS_PORT_LINK_TEST, &port->status);
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 22e82000334a..99d6b3f8692b 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1218,7 +1218,7 @@ static int zfcp_fsf_setup_ct_els(struct zfcp_fsf_req *req,
 /**
  * zfcp_fsf_send_ct - initiate a Generic Service request (FC-GS)
  * @wka_port: pointer to zfcp WKA port to send CT/GS to
- * @ct: pointer to struct zfcp_send_ct with data for request
+ * @ct: pointer to struct zfcp_fsf_ct_els with data for CT request
  * @pool: if non-null this mempool is used to allocate struct zfcp_fsf_req
  * @timeout: timeout that hardware should use, and a later software timeout
  */
@@ -1316,7 +1316,7 @@ skip_fsfstatus:
  * zfcp_fsf_send_els - initiate an ELS command (FC-FS)
  * @adapter: pointer to zfcp adapter
  * @d_id: N_Port_ID to send ELS to
- * @els: pointer to struct zfcp_send_els with data for the command
+ * @els: pointer to struct zfcp_fsf_ct_els with data for the ELS command
  * @timeout: timeout that hardware should use, and a later software timeout
  */
 int zfcp_fsf_send_els(struct zfcp_adapter *adapter, u32 d_id,
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index b2a8cd792266..b31f860af47b 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -37,11 +37,11 @@ static bool allow_lun_scan = true;
 module_param(allow_lun_scan, bool, 0600);
 MODULE_PARM_DESC(allow_lun_scan, "For NPIV, scan and attach all storage LUNs");
 
-static void zfcp_scsi_slave_destroy(struct scsi_device *sdev)
+static void zfcp_scsi_sdev_destroy(struct scsi_device *sdev)
 {
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev);
 
-	/* if previous slave_alloc returned early, there is nothing to do */
+	/* if previous sdev_init returned early, there is nothing to do */
 	if (!zfcp_sdev->port)
 		return;
 
@@ -49,7 +49,8 @@ static void zfcp_scsi_slave_destroy(struct scsi_device *sdev)
 	put_device(&zfcp_sdev->port->dev);
 }
 
-static int zfcp_scsi_slave_configure(struct scsi_device *sdp)
+static int zfcp_scsi_sdev_configure(struct scsi_device *sdp,
+				    struct queue_limits *lim)
 {
 	if (sdp->tagged_supported)
 		scsi_change_queue_depth(sdp, default_depth);
@@ -110,7 +111,7 @@ int zfcp_scsi_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scpnt)
 	return ret;
 }
 
-static int zfcp_scsi_slave_alloc(struct scsi_device *sdev)
+static int zfcp_scsi_sdev_init(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 	struct zfcp_adapter *adapter =
@@ -427,9 +428,9 @@ static const struct scsi_host_template zfcp_scsi_host_template = {
 	.eh_device_reset_handler = zfcp_scsi_eh_device_reset_handler,
 	.eh_target_reset_handler = zfcp_scsi_eh_target_reset_handler,
 	.eh_host_reset_handler	 = zfcp_scsi_eh_host_reset_handler,
-	.slave_alloc		 = zfcp_scsi_slave_alloc,
-	.slave_configure	 = zfcp_scsi_slave_configure,
-	.slave_destroy		 = zfcp_scsi_slave_destroy,
+	.sdev_init		 = zfcp_scsi_sdev_init,
+	.sdev_configure		 = zfcp_scsi_sdev_configure,
+	.sdev_destroy		 = zfcp_scsi_sdev_destroy,
 	.change_queue_depth	 = scsi_change_queue_depth,
 	.host_reset		 = zfcp_scsi_sysfs_host_reset,
 	.proc_name		 = "zfcp",
diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c
index 304b81bb5f90..41e36af35488 100644
--- a/drivers/s390/scsi/zfcp_sysfs.c
+++ b/drivers/s390/scsi/zfcp_sysfs.c
@@ -284,7 +284,7 @@ static bool zfcp_sysfs_port_in_use(struct zfcp_port *const port)
 		goto unlock_host_lock;
 	}
 
-	/* port is about to be removed, so no more unit_add or slave_alloc */
+	/* port is about to be removed, so no more unit_add or sdev_init */
 	zfcp_sysfs_port_set_removing(port);
 	in_use = false;
 
diff --git a/drivers/s390/scsi/zfcp_unit.c b/drivers/s390/scsi/zfcp_unit.c
index 60f2a04f0869..4ef2a635d34f 100644
--- a/drivers/s390/scsi/zfcp_unit.c
+++ b/drivers/s390/scsi/zfcp_unit.c
@@ -170,7 +170,7 @@ int zfcp_unit_add(struct zfcp_port *port, u64 fcp_lun)
 	write_unlock_irq(&port->unit_list_lock);
 	/*
 	 * lock order: shost->scan_mutex before zfcp_sysfs_port_units_mutex
-	 * due to      zfcp_unit_scsi_scan() => zfcp_scsi_slave_alloc()
+	 * due to      zfcp_unit_scsi_scan() => zfcp_scsi_sdev_init()
 	 */
 	mutex_unlock(&zfcp_sysfs_port_units_mutex);
 
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 6fb61c88ea11..883d4a12a172 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -1968,13 +1968,14 @@ static char *twa_string_lookup(twa_message_type *table, unsigned int code)
 } /* End twa_string_lookup() */
 
 /* This function gets called when a disk is coming on-line */
-static int twa_slave_configure(struct scsi_device *sdev)
+static int twa_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	/* Force 60 second timeout */
 	blk_queue_rq_timeout(sdev->request_queue, 60 * HZ);
 
 	return 0;
-} /* End twa_slave_configure() */
+} /* End twa_sdev_configure() */
 
 static const struct scsi_host_template driver_template = {
 	.module			= THIS_MODULE,
@@ -1984,7 +1985,7 @@ static const struct scsi_host_template driver_template = {
 	.bios_param		= twa_scsi_biosparam,
 	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= TW_Q_LENGTH-2,
-	.slave_configure	= twa_slave_configure,
+	.sdev_configure		= twa_sdev_configure,
 	.this_id		= -1,
 	.sg_tablesize		= TW_APACHE_MAX_SGL_LENGTH,
 	.max_sectors		= TW_MAX_SECTORS,
@@ -2260,7 +2261,7 @@ out_disable_device:
 } /* End twa_resume() */
 
 /* PCI Devices supported by this driver */
-static struct pci_device_id twa_pci_tbl[] = {
+static const struct pci_device_id twa_pci_tbl[] = {
 	{ PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_9000,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{ PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_9550SX,
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index caa6713a62a4..e057ab9c7b90 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -96,7 +96,7 @@ static int twl_reset_device_extension(TW_Device_Extension *tw_dev, int ioctl_res
 
 /* This function returns AENs through sysfs */
 static ssize_t twl_sysfs_aen_read(struct file *filp, struct kobject *kobj,
-				  struct bin_attribute *bin_attr,
+				  const struct bin_attribute *bin_attr,
 				  char *outbuf, loff_t offset, size_t count)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -116,18 +116,18 @@ static ssize_t twl_sysfs_aen_read(struct file *filp, struct kobject *kobj,
 } /* End twl_sysfs_aen_read() */
 
 /* aen_read sysfs attribute initializer */
-static struct bin_attribute twl_sysfs_aen_read_attr = {
+static const struct bin_attribute twl_sysfs_aen_read_attr = {
 	.attr = {
 		.name = "3ware_aen_read",
 		.mode = S_IRUSR,
 	},
 	.size = 0,
-	.read = twl_sysfs_aen_read
+	.read_new = twl_sysfs_aen_read
 };
 
 /* This function returns driver compatibility info through sysfs */
 static ssize_t twl_sysfs_compat_info(struct file *filp, struct kobject *kobj,
-				     struct bin_attribute *bin_attr,
+				     const struct bin_attribute *bin_attr,
 				     char *outbuf, loff_t offset, size_t count)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
@@ -147,13 +147,13 @@ static ssize_t twl_sysfs_compat_info(struct file *filp, struct kobject *kobj,
 } /* End twl_sysfs_compat_info() */
 
 /* compat_info sysfs attribute initializer */
-static struct bin_attribute twl_sysfs_compat_info_attr = {
+static const struct bin_attribute twl_sysfs_compat_info_attr = {
 	.attr = {
 		.name = "3ware_compat_info",
 		.mode = S_IRUSR,
 	},
 	.size = 0,
-	.read = twl_sysfs_compat_info
+	.read_new = twl_sysfs_compat_info
 };
 
 /* Show some statistics about the card */
@@ -1523,13 +1523,14 @@ static void twl_shutdown(struct pci_dev *pdev)
 } /* End twl_shutdown() */
 
 /* This function configures unit settings when a unit is coming on-line */
-static int twl_slave_configure(struct scsi_device *sdev)
+static int twl_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	/* Force 60 second timeout */
 	blk_queue_rq_timeout(sdev->request_queue, 60 * HZ);
 
 	return 0;
-} /* End twl_slave_configure() */
+} /* End twl_sdev_configure() */
 
 static const struct scsi_host_template driver_template = {
 	.module			= THIS_MODULE,
@@ -1539,7 +1540,7 @@ static const struct scsi_host_template driver_template = {
 	.bios_param		= twl_scsi_biosparam,
 	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= TW_Q_LENGTH-2,
-	.slave_configure	= twl_slave_configure,
+	.sdev_configure		= twl_sdev_configure,
 	.this_id		= -1,
 	.sg_tablesize		= TW_LIBERATOR_MAX_SGL_LENGTH,
 	.max_sectors		= TW_MAX_SECTORS,
@@ -1821,7 +1822,7 @@ out_disable_device:
 } /* End twl_resume() */
 
 /* PCI Devices supported by this driver */
-static struct pci_device_id twl_pci_tbl[] = {
+static const struct pci_device_id twl_pci_tbl[] = {
 	{ PCI_VDEVICE(3WARE, PCI_DEVICE_ID_3WARE_9750) },
 	{ }
 };
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 2c0fb6da0e60..89bd56f78ef9 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -172,7 +172,7 @@
                  Initialize queues correctly when loading with no valid units.
    1.02.00.034 - Fix tw_decode_bits() to handle multiple errors.
                  Add support for user configurable cmd_per_lun.
-                 Add support for sht->slave_configure().
+                 Add support for sht->sdev_configure().
    1.02.00.035 - Improve tw_allocate_memory() memory allocation.
                  Fix tw_chrdev_ioctl() to sleep correctly.
    1.02.00.036 - Increase character ioctl timeout to 60 seconds.
@@ -2221,13 +2221,13 @@ static void tw_shutdown(struct pci_dev *pdev)
 } /* End tw_shutdown() */
 
 /* This function gets called when a disk is coming online */
-static int tw_slave_configure(struct scsi_device *sdev)
+static int tw_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	/* Force 60 second timeout */
 	blk_queue_rq_timeout(sdev->request_queue, 60 * HZ);
 
 	return 0;
-} /* End tw_slave_configure() */
+} /* End tw_sdev_configure() */
 
 static const struct scsi_host_template driver_template = {
 	.module			= THIS_MODULE,
@@ -2237,7 +2237,7 @@ static const struct scsi_host_template driver_template = {
 	.bios_param		= tw_scsi_biosparam,
 	.change_queue_depth	= scsi_change_queue_depth,
 	.can_queue		= TW_Q_LENGTH-2,
-	.slave_configure	= tw_slave_configure,
+	.sdev_configure		= tw_sdev_configure,
 	.this_id		= -1,
 	.sg_tablesize		= TW_MAX_SGL_LENGTH,
 	.max_sectors		= TW_MAX_SECTORS,
@@ -2393,7 +2393,7 @@ static void tw_remove(struct pci_dev *pdev)
 } /* End tw_remove() */
 
 /* PCI Devices supported by this driver */
-static struct pci_device_id tw_pci_tbl[] = {
+static const struct pci_device_id tw_pci_tbl[] = {
 	{ PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_1000,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{ PCI_VENDOR_ID_3WARE, PCI_DEVICE_ID_3WARE_7000,
diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c
index 85439e976143..71b7ac027f48 100644
--- a/drivers/scsi/53c700.c
+++ b/drivers/scsi/53c700.c
@@ -158,9 +158,10 @@ STATIC int NCR_700_abort(struct scsi_cmnd * SCpnt);
 STATIC int NCR_700_host_reset(struct scsi_cmnd * SCpnt);
 STATIC void NCR_700_chip_setup(struct Scsi_Host *host);
 STATIC void NCR_700_chip_reset(struct Scsi_Host *host);
-STATIC int NCR_700_slave_alloc(struct scsi_device *SDpnt);
-STATIC int NCR_700_slave_configure(struct scsi_device *SDpnt);
-STATIC void NCR_700_slave_destroy(struct scsi_device *SDpnt);
+STATIC int NCR_700_sdev_init(struct scsi_device *SDpnt);
+STATIC int NCR_700_sdev_configure(struct scsi_device *SDpnt,
+				  struct queue_limits *lim);
+STATIC void NCR_700_sdev_destroy(struct scsi_device *SDpnt);
 static int NCR_700_change_queue_depth(struct scsi_device *SDpnt, int depth);
 
 STATIC const struct attribute_group *NCR_700_dev_groups[];
@@ -330,9 +331,9 @@ NCR_700_detect(struct scsi_host_template *tpnt,
 	tpnt->can_queue = NCR_700_COMMAND_SLOTS_PER_HOST;
 	tpnt->sg_tablesize = NCR_700_SG_SEGMENTS;
 	tpnt->cmd_per_lun = NCR_700_CMD_PER_LUN;
-	tpnt->slave_configure = NCR_700_slave_configure;
-	tpnt->slave_destroy = NCR_700_slave_destroy;
-	tpnt->slave_alloc = NCR_700_slave_alloc;
+	tpnt->sdev_configure = NCR_700_sdev_configure;
+	tpnt->sdev_destroy = NCR_700_sdev_destroy;
+	tpnt->sdev_init = NCR_700_sdev_init;
 	tpnt->change_queue_depth = NCR_700_change_queue_depth;
 
 	if(tpnt->name == NULL)
@@ -2017,7 +2018,7 @@ NCR_700_set_offset(struct scsi_target *STp, int offset)
 }
 
 STATIC int
-NCR_700_slave_alloc(struct scsi_device *SDp)
+NCR_700_sdev_init(struct scsi_device *SDp)
 {
 	SDp->hostdata = kzalloc(sizeof(struct NCR_700_Device_Parameters),
 				GFP_KERNEL);
@@ -2029,7 +2030,7 @@ NCR_700_slave_alloc(struct scsi_device *SDp)
 }
 
 STATIC int
-NCR_700_slave_configure(struct scsi_device *SDp)
+NCR_700_sdev_configure(struct scsi_device *SDp, struct queue_limits *lim)
 {
 	struct NCR_700_Host_Parameters *hostdata = 
 		(struct NCR_700_Host_Parameters *)SDp->host->hostdata[0];
@@ -2052,7 +2053,7 @@ NCR_700_slave_configure(struct scsi_device *SDp)
 }
 
 STATIC void
-NCR_700_slave_destroy(struct scsi_device *SDp)
+NCR_700_sdev_destroy(struct scsi_device *SDp)
 {
 	kfree(SDp->hostdata);
 	SDp->hostdata = NULL;
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index 2135a2b3e2d0..1f100270cd38 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -2153,14 +2153,15 @@ static void __init blogic_inithoststruct(struct blogic_adapter *adapter,
 }
 
 /*
-  blogic_slaveconfig will actually set the queue depth on individual
+  blogic_sdev_configure will actually set the queue depth on individual
   scsi devices as they are permanently added to the device chain.  We
   shamelessly rip off the SelectQueueDepths code to make this work mostly
   like it used to.  Since we don't get called once at the end of the scan
   but instead get called for each device, we have to do things a bit
   differently.
 */
-static int blogic_slaveconfig(struct scsi_device *dev)
+static int blogic_sdev_configure(struct scsi_device *dev,
+				 struct queue_limits *lim)
 {
 	struct blogic_adapter *adapter =
 		(struct blogic_adapter *) dev->host->hostdata;
@@ -3672,7 +3673,7 @@ static const struct scsi_host_template blogic_template = {
 	.name = "BusLogic",
 	.info = blogic_drvr_info,
 	.queuecommand = blogic_qcmd,
-	.slave_configure = blogic_slaveconfig,
+	.sdev_configure = blogic_sdev_configure,
 	.bios_param = blogic_diskparam,
 	.eh_host_reset_handler = blogic_hostreset,
 #if 0
@@ -3715,7 +3716,7 @@ static void __exit blogic_exit(void)
 __setup("BusLogic=", blogic_setup);
 
 #ifdef MODULE
-/*static struct pci_device_id blogic_pci_tbl[] = {
+/*static const struct pci_device_id blogic_pci_tbl[] = {
 	{ PCI_VENDOR_ID_BUSLOGIC, PCI_DEVICE_ID_BUSLOGIC_MULTIMASTER,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{ PCI_VENDOR_ID_BUSLOGIC, PCI_DEVICE_ID_BUSLOGIC_MULTIMASTER_NC,
diff --git a/drivers/scsi/BusLogic.h b/drivers/scsi/BusLogic.h
index 7d1ec10f2430..61bf26d4fc10 100644
--- a/drivers/scsi/BusLogic.h
+++ b/drivers/scsi/BusLogic.h
@@ -1274,7 +1274,8 @@ static inline void blogic_incszbucket(unsigned int *cmdsz_buckets,
 static const char *blogic_drvr_info(struct Scsi_Host *);
 static int blogic_qcmd(struct Scsi_Host *h, struct scsi_cmnd *);
 static int blogic_diskparam(struct scsi_device *, struct block_device *, sector_t, int *);
-static int blogic_slaveconfig(struct scsi_device *);
+static int blogic_sdev_configure(struct scsi_device *,
+				 struct queue_limits *lim);
 static void blogic_qcompleted_ccb(struct blogic_ccb *);
 static irqreturn_t blogic_inthandler(int, void *);
 static int blogic_resetadapter(struct blogic_adapter *, bool hard_reset);
diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c
index b95147fb18b0..a8979f9e30ff 100644
--- a/drivers/scsi/a100u2w.c
+++ b/drivers/scsi/a100u2w.c
@@ -1206,7 +1206,7 @@ static void inia100_remove_one(struct pci_dev *pdev)
 	scsi_host_put(shost);
 } 
 
-static struct pci_device_id inia100_pci_tbl[] = {
+static const struct pci_device_id inia100_pci_tbl[] = {
 	{PCI_VENDOR_ID_INIT, 0x1060, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{0,}
 };
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 68f4dbcfff49..91170a67cc91 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -377,15 +377,17 @@ static int aac_biosparm(struct scsi_device *sdev, struct block_device *bdev,
 }
 
 /**
- *	aac_slave_configure		-	compute queue depths
+ *	aac_sdev_configure		-	compute queue depths
  *	@sdev:	SCSI device we are considering
+ *	@lim:	Request queue limits
  *
  *	Selects queue depths for each target device based on the host adapter's
  *	total capacity and the queue depth supported by the target device.
  *	A queue depth of one automatically disables tagged queueing.
  */
 
-static int aac_slave_configure(struct scsi_device *sdev)
+static int aac_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	struct aac_dev *aac = (struct aac_dev *)sdev->host->hostdata;
 	int chn, tid;
@@ -1487,7 +1489,7 @@ static const struct scsi_host_template aac_driver_template = {
 	.queuecommand			= aac_queuecommand,
 	.bios_param			= aac_biosparm,
 	.shost_groups			= aac_host_groups,
-	.slave_configure		= aac_slave_configure,
+	.sdev_configure			= aac_sdev_configure,
 	.change_queue_depth		= aac_change_queue_depth,
 	.sdev_groups			= aac_dev_groups,
 	.eh_abort_handler		= aac_eh_abort,
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index fd4fcb37863d..3a2c336307c0 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -4496,7 +4496,7 @@ static int AdvInitAsc3550Driver(ADV_DVC_VAR *asc_dvc)
 
 	/*
 	 * Microcode operating variables for WDTR, SDTR, and command tag
-	 * queuing will be set in slave_configure() based on what a
+	 * queuing will be set in sdev_configure() based on what a
 	 * device reports it is capable of in Inquiry byte 7.
 	 *
 	 * If SCSI Bus Resets have been disabled, then directly set
@@ -5013,7 +5013,7 @@ static int AdvInitAsc38C0800Driver(ADV_DVC_VAR *asc_dvc)
 
 	/*
 	 * Microcode operating variables for WDTR, SDTR, and command tag
-	 * queuing will be set in slave_configure() based on what a
+	 * queuing will be set in sdev_configure() based on what a
 	 * device reports it is capable of in Inquiry byte 7.
 	 *
 	 * If SCSI Bus Resets have been disabled, then directly set
@@ -5508,7 +5508,7 @@ static int AdvInitAsc38C1600Driver(ADV_DVC_VAR *asc_dvc)
 
 	/*
 	 * Microcode operating variables for WDTR, SDTR, and command tag
-	 * queuing will be set in slave_configure() based on what a
+	 * queuing will be set in sdev_configure() based on what a
 	 * device reports it is capable of in Inquiry byte 7.
 	 *
 	 * If SCSI Bus Resets have been disabled, then directly set
@@ -7219,7 +7219,7 @@ static void AscAsyncFix(ASC_DVC_VAR *asc_dvc, struct scsi_device *sdev)
 }
 
 static void
-advansys_narrow_slave_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc)
+advansys_narrow_sdev_configure(struct scsi_device *sdev, ASC_DVC_VAR *asc_dvc)
 {
 	ASC_SCSI_BIT_ID_TYPE tid_bit = 1 << sdev->id;
 	ASC_SCSI_BIT_ID_TYPE orig_use_tagged_qng = asc_dvc->use_tagged_qng;
@@ -7345,7 +7345,7 @@ static void advansys_wide_enable_ppr(ADV_DVC_VAR *adv_dvc,
 }
 
 static void
-advansys_wide_slave_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc)
+advansys_wide_sdev_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc)
 {
 	AdvPortAddr iop_base = adv_dvc->iop_base;
 	unsigned short tidmask = 1 << sdev->id;
@@ -7391,16 +7391,17 @@ advansys_wide_slave_configure(struct scsi_device *sdev, ADV_DVC_VAR *adv_dvc)
  * Set the number of commands to queue per device for the
  * specified host adapter.
  */
-static int advansys_slave_configure(struct scsi_device *sdev)
+static int advansys_sdev_configure(struct scsi_device *sdev,
+				   struct queue_limits *lim)
 {
 	struct asc_board *boardp = shost_priv(sdev->host);
 
 	if (ASC_NARROW_BOARD(boardp))
-		advansys_narrow_slave_configure(sdev,
-						&boardp->dvc_var.asc_dvc_var);
+		advansys_narrow_sdev_configure(sdev,
+					       &boardp->dvc_var.asc_dvc_var);
 	else
-		advansys_wide_slave_configure(sdev,
-						&boardp->dvc_var.adv_dvc_var);
+		advansys_wide_sdev_configure(sdev,
+					     &boardp->dvc_var.adv_dvc_var);
 
 	return 0;
 }
@@ -10612,7 +10613,7 @@ static const struct scsi_host_template advansys_template = {
 	.queuecommand = advansys_queuecommand,
 	.eh_host_reset_handler = advansys_reset,
 	.bios_param = advansys_biosparam,
-	.slave_configure = advansys_slave_configure,
+	.sdev_configure = advansys_sdev_configure,
 	.cmd_size = sizeof(struct advansys_cmd),
 };
 
@@ -11408,7 +11409,7 @@ static struct eisa_driver advansys_eisa_driver = {
 };
 
 /* PCI Devices supported by this driver */
-static struct pci_device_id advansys_pci_tbl[] = {
+static const struct pci_device_id advansys_pci_tbl[] = {
 	{PCI_VENDOR_ID_ASP, PCI_DEVICE_ID_ASP_1200A,
 	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{PCI_VENDOR_ID_ASP, PCI_DEVICE_ID_ASP_ABP940,
diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c
index 4202059815a0..17dfc3c72110 100644
--- a/drivers/scsi/aic7xxx/aic79xx_osm.c
+++ b/drivers/scsi/aic7xxx/aic79xx_osm.c
@@ -672,7 +672,7 @@ ahd_linux_target_destroy(struct scsi_target *starget)
 }
 
 static int
-ahd_linux_slave_alloc(struct scsi_device *sdev)
+ahd_linux_sdev_init(struct scsi_device *sdev)
 {
 	struct	ahd_softc *ahd =
 		*((struct ahd_softc **)sdev->host->hostdata);
@@ -701,7 +701,7 @@ ahd_linux_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-ahd_linux_slave_configure(struct scsi_device *sdev)
+ahd_linux_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	if (bootverbose)
 		sdev_printk(KERN_INFO, sdev, "Slave Configure\n");
@@ -906,8 +906,8 @@ struct scsi_host_template aic79xx_driver_template = {
 	.this_id		= -1,
 	.max_sectors		= 8192,
 	.cmd_per_lun		= 2,
-	.slave_alloc		= ahd_linux_slave_alloc,
-	.slave_configure	= ahd_linux_slave_configure,
+	.sdev_init		= ahd_linux_sdev_init,
+	.sdev_configure		= ahd_linux_sdev_configure,
 	.target_alloc		= ahd_linux_target_alloc,
 	.target_destroy		= ahd_linux_target_destroy,
 };
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index b0c4f2345321..cebf8c5d0caf 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -632,7 +632,7 @@ ahc_linux_target_destroy(struct scsi_target *starget)
 }
 
 static int
-ahc_linux_slave_alloc(struct scsi_device *sdev)
+ahc_linux_sdev_init(struct scsi_device *sdev)
 {
 	struct	ahc_softc *ahc =
 		*((struct ahc_softc **)sdev->host->hostdata);
@@ -664,7 +664,7 @@ ahc_linux_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-ahc_linux_slave_configure(struct scsi_device *sdev)
+ahc_linux_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	if (bootverbose)
 		sdev_printk(KERN_INFO, sdev, "Slave Configure\n");
@@ -791,8 +791,8 @@ struct scsi_host_template aic7xxx_driver_template = {
 	.this_id		= -1,
 	.max_sectors		= 8192,
 	.cmd_per_lun		= 2,
-	.slave_alloc		= ahc_linux_slave_alloc,
-	.slave_configure	= ahc_linux_slave_configure,
+	.sdev_init		= ahc_linux_sdev_init,
+	.sdev_configure		= ahc_linux_sdev_configure,
 	.target_alloc		= ahc_linux_target_alloc,
 	.target_destroy		= ahc_linux_target_destroy,
 };
diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y
index 65182ad9cdf8..b1c9ce477cbd 100644
--- a/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y
+++ b/drivers/scsi/aic7xxx/aicasm/aicasm_gram.y
@@ -102,6 +102,7 @@ static void add_conditional(symbol_t *symbol);
 static void add_version(const char *verstring);
 static int  is_download_const(expression_t *immed);
 static int  is_location_address(symbol_t *symbol);
+int yylex();
 void yyerror(const char *string);
 
 #define SRAM_SYMNAME "SRAM_BASE"
diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y b/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y
index 8c0479865f04..5c7350eb5b5c 100644
--- a/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y
+++ b/drivers/scsi/aic7xxx/aicasm/aicasm_macro_gram.y
@@ -61,6 +61,7 @@
 static symbol_t *macro_symbol;
 
 static void add_macro_arg(const char *argtext, int position);
+int mmlex();
 void mmerror(const char *string);
 
 %}
diff --git a/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l b/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l
index c78d4f68eea5..fc7e6c58148d 100644
--- a/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l
+++ b/drivers/scsi/aic7xxx/aicasm/aicasm_scan.l
@@ -64,6 +64,9 @@ static char *string_buf_ptr;
 static int  parren_count;
 static int  quote_count;
 static char buf[255];
+void mm_switch_to_buffer(YY_BUFFER_STATE);
+void mmparse();
+void mm_delete_buffer(YY_BUFFER_STATE);
 %}
 
 PATH		([/]*[-A-Za-z0-9_.])+
diff --git a/drivers/scsi/am53c974.c b/drivers/scsi/am53c974.c
index fbb29dbb1e50..003e61831e33 100644
--- a/drivers/scsi/am53c974.c
+++ b/drivers/scsi/am53c974.c
@@ -513,7 +513,7 @@ static void pci_esp_remove_one(struct pci_dev *pdev)
 	scsi_host_put(esp->host);
 }
 
-static struct pci_device_id am53c974_pci_tbl[] = {
+static const struct pci_device_id am53c974_pci_tbl[] = {
 	{ PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_SCSI,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
 	{ }
diff --git a/drivers/scsi/arcmsr/arcmsr_attr.c b/drivers/scsi/arcmsr/arcmsr_attr.c
index baeb5e795690..8e3d4799ce93 100644
--- a/drivers/scsi/arcmsr/arcmsr_attr.c
+++ b/drivers/scsi/arcmsr/arcmsr_attr.c
@@ -60,7 +60,7 @@
 
 static ssize_t arcmsr_sysfs_iop_message_read(struct file *filp,
 					     struct kobject *kobj,
-					     struct bin_attribute *bin,
+					     const struct bin_attribute *bin,
 					     char *buf, loff_t off,
 					     size_t count)
 {
@@ -107,7 +107,7 @@ static ssize_t arcmsr_sysfs_iop_message_read(struct file *filp,
 
 static ssize_t arcmsr_sysfs_iop_message_write(struct file *filp,
 					      struct kobject *kobj,
-					      struct bin_attribute *bin,
+					      const struct bin_attribute *bin,
 					      char *buf, loff_t off,
 					      size_t count)
 {
@@ -155,7 +155,7 @@ static ssize_t arcmsr_sysfs_iop_message_write(struct file *filp,
 
 static ssize_t arcmsr_sysfs_iop_message_clear(struct file *filp,
 					      struct kobject *kobj,
-					      struct bin_attribute *bin,
+					      const struct bin_attribute *bin,
 					      char *buf, loff_t off,
 					      size_t count)
 {
@@ -194,7 +194,7 @@ static const struct bin_attribute arcmsr_sysfs_message_read_attr = {
 		.mode = S_IRUSR ,
 	},
 	.size = ARCMSR_API_DATA_BUFLEN,
-	.read = arcmsr_sysfs_iop_message_read,
+	.read_new = arcmsr_sysfs_iop_message_read,
 };
 
 static const struct bin_attribute arcmsr_sysfs_message_write_attr = {
@@ -203,7 +203,7 @@ static const struct bin_attribute arcmsr_sysfs_message_write_attr = {
 		.mode = S_IWUSR,
 	},
 	.size = ARCMSR_API_DATA_BUFLEN,
-	.write = arcmsr_sysfs_iop_message_write,
+	.write_new = arcmsr_sysfs_iop_message_write,
 };
 
 static const struct bin_attribute arcmsr_sysfs_message_clear_attr = {
@@ -212,7 +212,7 @@ static const struct bin_attribute arcmsr_sysfs_message_clear_attr = {
 		.mode = S_IWUSR,
 	},
 	.size = 1,
-	.write = arcmsr_sysfs_iop_message_clear,
+	.write_new = arcmsr_sysfs_iop_message_clear,
 };
 
 int arcmsr_alloc_sysfs_attr(struct AdapterControlBlock *acb)
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 35860c61468b..221a520e8a9b 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -143,7 +143,8 @@ static irqreturn_t arcmsr_interrupt(struct AdapterControlBlock *acb);
 static void arcmsr_free_irq(struct pci_dev *, struct AdapterControlBlock *);
 static void arcmsr_wait_firmware_ready(struct AdapterControlBlock *acb);
 static void arcmsr_set_iop_datetime(struct timer_list *);
-static int arcmsr_slave_config(struct scsi_device *sdev);
+static int arcmsr_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim);
 static int arcmsr_adjust_disk_queue_depth(struct scsi_device *sdev, int queue_depth)
 {
 	if (queue_depth > ARCMSR_MAX_CMD_PERLUN)
@@ -160,7 +161,7 @@ static const struct scsi_host_template arcmsr_scsi_host_template = {
 	.eh_abort_handler	= arcmsr_abort,
 	.eh_bus_reset_handler	= arcmsr_bus_reset,
 	.bios_param		= arcmsr_bios_param,
-	.slave_configure	= arcmsr_slave_config,
+	.sdev_configure		= arcmsr_sdev_configure,
 	.change_queue_depth	= arcmsr_adjust_disk_queue_depth,
 	.can_queue		= ARCMSR_DEFAULT_OUTSTANDING_CMD,
 	.this_id		= ARCMSR_SCSI_INITIATOR_ID,
@@ -171,7 +172,7 @@ static const struct scsi_host_template arcmsr_scsi_host_template = {
 	.no_write_same		= 1,
 };
 
-static struct pci_device_id arcmsr_device_id_table[] = {
+static const struct pci_device_id arcmsr_device_id_table[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1110),
 		.driver_data = ACB_ADAPTER_TYPE_A},
 	{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1120),
@@ -1044,7 +1045,7 @@ static void arcmsr_init_get_devmap_timer(struct AdapterControlBlock *pacb)
 static void arcmsr_init_set_datetime_timer(struct AdapterControlBlock *pacb)
 {
 	timer_setup(&pacb->refresh_timer, arcmsr_set_iop_datetime, 0);
-	pacb->refresh_timer.expires = jiffies + msecs_to_jiffies(60 * 1000);
+	pacb->refresh_timer.expires = jiffies + secs_to_jiffies(60);
 	add_timer(&pacb->refresh_timer);
 }
 
@@ -3344,7 +3345,8 @@ static int arcmsr_queue_command_lck(struct scsi_cmnd *cmd)
 
 static DEF_SCSI_QCMD(arcmsr_queue_command)
 
-static int arcmsr_slave_config(struct scsi_device *sdev)
+static int arcmsr_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	unsigned int	dev_timeout;
 
diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c
index 928151ec927a..401242912855 100644
--- a/drivers/scsi/atp870u.c
+++ b/drivers/scsi/atp870u.c
@@ -1743,7 +1743,7 @@ static const struct scsi_host_template atp870u_template = {
      .max_sectors		= ATP870U_MAX_SECTORS,
 };
 
-static struct pci_device_id atp870u_id_table[] = {
+static const struct pci_device_id atp870u_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_ARTOP, ATP885_DEVID)			  },
 	{ PCI_DEVICE(PCI_VENDOR_ID_ARTOP, ATP880_DEVID1)		  },
 	{ PCI_DEVICE(PCI_VENDOR_ID_ARTOP, ATP880_DEVID2)		  },
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index 66fb701401de..a719a18f0fbc 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -25,7 +25,7 @@ struct scsi_transport_template *bfad_im_scsi_transport_template;
 struct scsi_transport_template *bfad_im_scsi_vport_transport_template;
 static void bfad_im_itnim_work_handler(struct work_struct *work);
 static int bfad_im_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *cmnd);
-static int bfad_im_slave_alloc(struct scsi_device *sdev);
+static int bfad_im_sdev_init(struct scsi_device *sdev);
 static void bfad_im_fc_rport_add(struct bfad_im_port_s  *im_port,
 				struct bfad_itnim_s *itnim);
 
@@ -404,10 +404,10 @@ bfad_im_reset_target_handler(struct scsi_cmnd *cmnd)
 }
 
 /*
- * Scsi_Host template entry slave_destroy.
+ * Scsi_Host template entry sdev_destroy.
  */
 static void
-bfad_im_slave_destroy(struct scsi_device *sdev)
+bfad_im_sdev_destroy(struct scsi_device *sdev)
 {
 	sdev->hostdata = NULL;
 	return;
@@ -783,7 +783,7 @@ bfad_thread_workq(struct bfad_s *bfad)
  * Return non-zero if fails.
  */
 static int
-bfad_im_slave_configure(struct scsi_device *sdev)
+bfad_im_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	scsi_change_queue_depth(sdev, bfa_lun_queue_depth);
 	return 0;
@@ -800,9 +800,9 @@ struct scsi_host_template bfad_im_scsi_host_template = {
 	.eh_device_reset_handler = bfad_im_reset_lun_handler,
 	.eh_target_reset_handler = bfad_im_reset_target_handler,
 
-	.slave_alloc = bfad_im_slave_alloc,
-	.slave_configure = bfad_im_slave_configure,
-	.slave_destroy = bfad_im_slave_destroy,
+	.sdev_init = bfad_im_sdev_init,
+	.sdev_configure = bfad_im_sdev_configure,
+	.sdev_destroy = bfad_im_sdev_destroy,
 
 	.this_id = -1,
 	.sg_tablesize = BFAD_IO_MAX_SGE,
@@ -823,9 +823,9 @@ struct scsi_host_template bfad_im_vport_template = {
 	.eh_device_reset_handler = bfad_im_reset_lun_handler,
 	.eh_target_reset_handler = bfad_im_reset_target_handler,
 
-	.slave_alloc = bfad_im_slave_alloc,
-	.slave_configure = bfad_im_slave_configure,
-	.slave_destroy = bfad_im_slave_destroy,
+	.sdev_init = bfad_im_sdev_init,
+	.sdev_configure = bfad_im_sdev_configure,
+	.sdev_destroy = bfad_im_sdev_destroy,
 
 	.this_id = -1,
 	.sg_tablesize = BFAD_IO_MAX_SGE,
@@ -915,7 +915,7 @@ bfad_get_itnim(struct bfad_im_port_s *im_port, int id)
 }
 
 /*
- * Function is invoked from the SCSI Host Template slave_alloc() entry point.
+ * Function is invoked from the SCSI Host Template sdev_init() entry point.
  * Has the logic to query the LUN Mask database to check if this LUN needs to
  * be made visible to the SCSI mid-layer or not.
  *
@@ -946,10 +946,10 @@ bfad_im_check_if_make_lun_visible(struct scsi_device *sdev,
 }
 
 /*
- * Scsi_Host template entry slave_alloc
+ * Scsi_Host template entry sdev_init
  */
 static int
-bfad_im_slave_alloc(struct scsi_device *sdev)
+bfad_im_sdev_init(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 	struct bfad_itnim_data_s *itnim_data;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index f49783b89d04..5ac20c93637c 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2610,14 +2610,11 @@ static int bnx2fc_cpu_online(unsigned int cpu)
 
 	p = &per_cpu(bnx2fc_percpu, cpu);
 
-	thread = kthread_create_on_node(bnx2fc_percpu_io_thread,
-					(void *)p, cpu_to_node(cpu),
-					"bnx2fc_thread/%d", cpu);
+	thread = kthread_create_on_cpu(bnx2fc_percpu_io_thread,
+				       (void *)p, cpu, "bnx2fc_thread/%d");
 	if (IS_ERR(thread))
 		return PTR_ERR(thread);
 
-	/* bind thread to the cpu */
-	kthread_bind(thread, cpu);
 	p->iothread = thread;
 	wake_up_process(thread);
 	return 0;
@@ -2652,7 +2649,8 @@ static int bnx2fc_cpu_offline(unsigned int cpu)
 	return 0;
 }
 
-static int bnx2fc_slave_configure(struct scsi_device *sdev)
+static int bnx2fc_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	if (!bnx2fc_queue_depth)
 		return 0;
@@ -2951,7 +2949,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.eh_device_reset_handler = bnx2fc_eh_device_reset, /* lun reset */
 	.eh_target_reset_handler = bnx2fc_eh_target_reset, /* tgt reset */
 	.eh_host_reset_handler	= fc_eh_host_reset,
-	.slave_alloc		= fc_slave_alloc,
+	.sdev_init		= fc_sdev_init,
 	.change_queue_depth	= scsi_change_queue_depth,
 	.this_id		= -1,
 	.cmd_per_lun		= 3,
@@ -2959,7 +2957,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.dma_boundary           = 0x7fff,
 	.max_sectors		= 0x3fbf,
 	.track_queue_depth	= 1,
-	.slave_configure	= bnx2fc_slave_configure,
+	.sdev_configure		= bnx2fc_sdev_configure,
 	.shost_groups		= bnx2fc_host_groups,
 	.cmd_size		= sizeof(struct bnx2fc_priv),
 };
diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c
index 872ad37e2a6e..cecc3a026762 100644
--- a/drivers/scsi/bnx2i/bnx2i_init.c
+++ b/drivers/scsi/bnx2i/bnx2i_init.c
@@ -415,14 +415,11 @@ static int bnx2i_cpu_online(unsigned int cpu)
 
 	p = &per_cpu(bnx2i_percpu, cpu);
 
-	thread = kthread_create_on_node(bnx2i_percpu_io_thread, (void *)p,
-					cpu_to_node(cpu),
-					"bnx2i_thread/%d", cpu);
+	thread = kthread_create_on_cpu(bnx2i_percpu_io_thread, (void *)p,
+				       cpu, "bnx2i_thread/%d");
 	if (IS_ERR(thread))
 		return PTR_ERR(thread);
 
-	/* bind thread to the cpu */
-	kthread_bind(thread, cpu);
 	p->iothread = thread;
 	wake_up_process(thread);
 	return 0;
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 8329f0cab4e7..34bde6650fae 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -800,7 +800,7 @@ csio_scsis_io_active(struct csio_ioreq *req, enum csio_scsi_ev evt)
 			rn = req->rnode;
 			/*
 			 * FW says remote device is lost, but rnode
-			 * doesnt reflect it.
+			 * doesn't reflect it.
 			 */
 			if (csio_scsi_itnexus_loss_error(req->wr_status) &&
 						csio_is_rnode_ready(rn)) {
@@ -2224,7 +2224,7 @@ fail:
 }
 
 static int
-csio_slave_alloc(struct scsi_device *sdev)
+csio_sdev_init(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 
@@ -2237,14 +2237,14 @@ csio_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-csio_slave_configure(struct scsi_device *sdev)
+csio_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	scsi_change_queue_depth(sdev, csio_lun_qdepth);
 	return 0;
 }
 
 static void
-csio_slave_destroy(struct scsi_device *sdev)
+csio_sdev_destroy(struct scsi_device *sdev)
 {
 	sdev->hostdata = NULL;
 }
@@ -2276,9 +2276,9 @@ struct scsi_host_template csio_fcoe_shost_template = {
 	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= csio_eh_abort_handler,
 	.eh_device_reset_handler = csio_eh_lun_reset_handler,
-	.slave_alloc		= csio_slave_alloc,
-	.slave_configure	= csio_slave_configure,
-	.slave_destroy		= csio_slave_destroy,
+	.sdev_init		= csio_sdev_init,
+	.sdev_configure		= csio_sdev_configure,
+	.sdev_destroy		= csio_sdev_destroy,
 	.scan_finished		= csio_scan_finished,
 	.this_id		= -1,
 	.sg_tablesize		= CSIO_SCSI_MAX_SGE,
@@ -2295,9 +2295,9 @@ struct scsi_host_template csio_fcoe_shost_vport_template = {
 	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= csio_eh_abort_handler,
 	.eh_device_reset_handler = csio_eh_lun_reset_handler,
-	.slave_alloc		= csio_slave_alloc,
-	.slave_configure	= csio_slave_configure,
-	.slave_destroy		= csio_slave_destroy,
+	.sdev_init		= csio_sdev_init,
+	.sdev_configure		= csio_sdev_configure,
+	.sdev_destroy		= csio_sdev_destroy,
 	.scan_finished		= csio_scan_finished,
 	.this_id		= -1,
 	.sg_tablesize		= CSIO_SCSI_MAX_SGE,
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index 62806f5e32e6..ae626e389c8b 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -3177,7 +3177,7 @@ static struct dev_dependent_vals dev_briard_vals = { CXLFLASH_MAX_SECTORS,
 /*
  * PCI device binding table
  */
-static struct pci_device_id cxlflash_pci_table[] = {
+static const struct pci_device_id cxlflash_pci_table[] = {
 	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CORSA,
 	 PCI_ANY_ID, PCI_ANY_ID, 0, 0, (kernel_ulong_t)&dev_corsa_vals},
 	{PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_FLASH_GT,
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index b375509d1470..97631f48e19d 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -966,7 +966,7 @@ static int cxlflash_disk_detach(struct scsi_device *sdev, void *detach)
  *
  * This routine is the release handler for the fops registered with
  * the CXL services on an initial attach for a context. It is called
- * when a close (explicity by the user or as part of a process tear
+ * when a close (explicitly by the user or as part of a process tear
  * down) is performed on the adapter file descriptor returned to the
  * user. The user should be aware that explicitly performing a close
  * considered catastrophic and subsequent usage of the superpipe API
diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index d108a86e196e..e71de2419758 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -3715,13 +3715,13 @@ static void adapter_remove_and_free_all_devices(struct AdapterCtlBlk* acb)
 
 
 /**
- * dc395x_slave_alloc - Called by the scsi mid layer to tell us about a new
+ * dc395x_sdev_init - Called by the scsi mid layer to tell us about a new
  * scsi device that we need to deal with. We allocate a new device and then
  * insert that device into the adapters device list.
  *
  * @scsi_device: The new scsi device that we need to handle.
  **/
-static int dc395x_slave_alloc(struct scsi_device *scsi_device)
+static int dc395x_sdev_init(struct scsi_device *scsi_device)
 {
 	struct AdapterCtlBlk *acb = (struct AdapterCtlBlk *)scsi_device->host->hostdata;
 	struct DeviceCtlBlk *dcb;
@@ -3736,12 +3736,12 @@ static int dc395x_slave_alloc(struct scsi_device *scsi_device)
 
 
 /**
- * dc395x_slave_destroy - Called by the scsi mid layer to tell us about a
+ * dc395x_sdev_destroy - Called by the scsi mid layer to tell us about a
  * device that is going away.
  *
  * @scsi_device: The new scsi device that we need to handle.
  **/
-static void dc395x_slave_destroy(struct scsi_device *scsi_device)
+static void dc395x_sdev_destroy(struct scsi_device *scsi_device)
 {
 	struct AdapterCtlBlk *acb = (struct AdapterCtlBlk *)scsi_device->host->hostdata;
 	struct DeviceCtlBlk *dcb = find_dcb(acb, scsi_device->id, scsi_device->lun);
@@ -4547,8 +4547,8 @@ static const struct scsi_host_template dc395x_driver_template = {
 	.show_info              = dc395x_show_info,
 	.name                   = DC395X_BANNER " " DC395X_VERSION,
 	.queuecommand           = dc395x_queue_command,
-	.slave_alloc            = dc395x_slave_alloc,
-	.slave_destroy          = dc395x_slave_destroy,
+	.sdev_init              = dc395x_sdev_init,
+	.sdev_destroy           = dc395x_sdev_destroy,
 	.can_queue              = DC395x_MAX_CAN_QUEUE,
 	.this_id                = 7,
 	.sg_tablesize           = DC395x_MAX_SG_TABLESIZE,
@@ -4668,7 +4668,7 @@ static void dc395x_remove_one(struct pci_dev *dev)
 }
 
 
-static struct pci_device_id dc395x_pci_table[] = {
+static const struct pci_device_id dc395x_pci_table[] = {
 	{
 		.vendor		= PCI_VENDOR_ID_TEKRAM,
 		.device		= PCI_DEVICE_ID_TEKRAM_TRMS1040,
diff --git a/drivers/scsi/dmx3191d.c b/drivers/scsi/dmx3191d.c
index dfb091d34363..d6d091b2f3c7 100644
--- a/drivers/scsi/dmx3191d.c
+++ b/drivers/scsi/dmx3191d.c
@@ -127,7 +127,7 @@ static void dmx3191d_remove_one(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-static struct pci_device_id dmx3191d_pci_tbl[] = {
+static const struct pci_device_id dmx3191d_pci_tbl[] = {
 	{PCI_VENDOR_ID_DOMEX, PCI_DEVICE_ID_DOMEX_DMX3191D,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4},
 	{ }
diff --git a/drivers/scsi/elx/efct/efct_driver.c b/drivers/scsi/elx/efct/efct_driver.c
index 55d2301bfd7d..8469c156ab33 100644
--- a/drivers/scsi/elx/efct/efct_driver.c
+++ b/drivers/scsi/elx/efct/efct_driver.c
@@ -470,7 +470,7 @@ out:
 	return rc;
 }
 
-static struct pci_device_id efct_pci_table[] = {
+static const struct pci_device_id efct_pci_table[] = {
 	{PCI_DEVICE(EFCT_VENDOR_ID, EFCT_DEVICE_LANCER_G6), 0},
 	{PCI_DEVICE(EFCT_VENDOR_ID, EFCT_DEVICE_LANCER_G7), 0},
 	{}	/* terminate list */
diff --git a/drivers/scsi/esas2r/esas2r.h b/drivers/scsi/esas2r/esas2r.h
index 1e2d7c63a8e3..c48275d53aef 100644
--- a/drivers/scsi/esas2r/esas2r.h
+++ b/drivers/scsi/esas2r/esas2r.h
@@ -1411,11 +1411,11 @@ static inline void esas2r_comp_list_drain(struct esas2r_adapter *a,
 }
 
 /* sysfs handlers */
-extern struct bin_attribute bin_attr_fw;
-extern struct bin_attribute bin_attr_fs;
-extern struct bin_attribute bin_attr_vda;
-extern struct bin_attribute bin_attr_hw;
-extern struct bin_attribute bin_attr_live_nvram;
-extern struct bin_attribute bin_attr_default_nvram;
+extern const struct bin_attribute bin_attr_fw;
+extern const struct bin_attribute bin_attr_fs;
+extern const struct bin_attribute bin_attr_vda;
+extern const struct bin_attribute bin_attr_hw;
+extern const struct bin_attribute bin_attr_live_nvram;
+extern const struct bin_attribute bin_attr_default_nvram;
 
 #endif /* ESAS2R_H */
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index f700a16cd885..44871746944a 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -66,7 +66,7 @@ static struct esas2r_adapter *esas2r_adapter_from_kobj(struct kobject *kobj)
 }
 
 static ssize_t read_fw(struct file *file, struct kobject *kobj,
-		       struct bin_attribute *attr,
+		       const struct bin_attribute *attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -75,7 +75,7 @@ static ssize_t read_fw(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t write_fw(struct file *file, struct kobject *kobj,
-			struct bin_attribute *attr,
+			const struct bin_attribute *attr,
 			char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -84,7 +84,7 @@ static ssize_t write_fw(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t read_fs(struct file *file, struct kobject *kobj,
-		       struct bin_attribute *attr,
+		       const struct bin_attribute *attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -93,7 +93,7 @@ static ssize_t read_fs(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t write_fs(struct file *file, struct kobject *kobj,
-			struct bin_attribute *attr,
+			const struct bin_attribute *attr,
 			char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -109,7 +109,7 @@ static ssize_t write_fs(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t read_vda(struct file *file, struct kobject *kobj,
-			struct bin_attribute *attr,
+			const struct bin_attribute *attr,
 			char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -118,7 +118,7 @@ static ssize_t read_vda(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t write_vda(struct file *file, struct kobject *kobj,
-			 struct bin_attribute *attr,
+			 const struct bin_attribute *attr,
 			 char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -127,7 +127,7 @@ static ssize_t write_vda(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t read_live_nvram(struct file *file, struct kobject *kobj,
-			       struct bin_attribute *attr,
+			       const struct bin_attribute *attr,
 			       char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -138,7 +138,7 @@ static ssize_t read_live_nvram(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t write_live_nvram(struct file *file, struct kobject *kobj,
-				struct bin_attribute *attr,
+				const struct bin_attribute *attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -158,7 +158,7 @@ static ssize_t write_live_nvram(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t read_default_nvram(struct file *file, struct kobject *kobj,
-				  struct bin_attribute *attr,
+				  const struct bin_attribute *attr,
 				  char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -169,7 +169,7 @@ static ssize_t read_default_nvram(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t read_hw(struct file *file, struct kobject *kobj,
-		       struct bin_attribute *attr,
+		       const struct bin_attribute *attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -187,7 +187,7 @@ static ssize_t read_hw(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t write_hw(struct file *file, struct kobject *kobj,
-			struct bin_attribute *attr,
+			const struct bin_attribute *attr,
 			char *buf, loff_t off, size_t count)
 {
 	struct esas2r_adapter *a = esas2r_adapter_from_kobj(kobj);
@@ -211,12 +211,12 @@ static ssize_t write_hw(struct file *file, struct kobject *kobj,
 }
 
 #define ESAS2R_RW_BIN_ATTR(_name) \
-	struct bin_attribute bin_attr_ ## _name = { \
+	const struct bin_attribute bin_attr_ ## _name = { \
 		.attr	= \
 		{ .name = __stringify(_name), .mode  = S_IRUSR | S_IWUSR }, \
 		.size	= 0, \
-		.read	= read_ ## _name, \
-		.write	= write_ ## _name }
+		.read_new	= read_ ## _name, \
+		.write_new	= write_ ## _name }
 
 ESAS2R_RW_BIN_ATTR(fw);
 ESAS2R_RW_BIN_ATTR(fs);
@@ -224,10 +224,10 @@ ESAS2R_RW_BIN_ATTR(vda);
 ESAS2R_RW_BIN_ATTR(hw);
 ESAS2R_RW_BIN_ATTR(live_nvram);
 
-struct bin_attribute bin_attr_default_nvram = {
+const struct bin_attribute bin_attr_default_nvram = {
 	.attr	= { .name = "default_nvram", .mode = S_IRUGO },
 	.size	= 0,
-	.read	= read_default_nvram,
+	.read_new	= read_default_nvram,
 	.write	= NULL
 };
 
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 0175d2282b45..802718ffad84 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -2261,7 +2261,7 @@ static void esp_init_swstate(struct esp *esp)
 	INIT_LIST_HEAD(&esp->active_cmds);
 	INIT_LIST_HEAD(&esp->esp_cmd_pool);
 
-	/* Start with a clear state, domain validation (via ->slave_configure,
+	/* Start with a clear state, domain validation (via ->sdev_configure,
 	 * spi_dv_device()) will attempt to enable SYNC, WIDE, and tagged
 	 * commands.
 	 */
@@ -2441,7 +2441,7 @@ static void esp_target_destroy(struct scsi_target *starget)
 	tp->starget = NULL;
 }
 
-static int esp_slave_alloc(struct scsi_device *dev)
+static int esp_sdev_init(struct scsi_device *dev)
 {
 	struct esp *esp = shost_priv(dev->host);
 	struct esp_target_data *tp = &esp->target[dev->id];
@@ -2463,7 +2463,7 @@ static int esp_slave_alloc(struct scsi_device *dev)
 	return 0;
 }
 
-static int esp_slave_configure(struct scsi_device *dev)
+static int esp_sdev_configure(struct scsi_device *dev, struct queue_limits *lim)
 {
 	struct esp *esp = shost_priv(dev->host);
 	struct esp_target_data *tp = &esp->target[dev->id];
@@ -2479,7 +2479,7 @@ static int esp_slave_configure(struct scsi_device *dev)
 	return 0;
 }
 
-static void esp_slave_destroy(struct scsi_device *dev)
+static void esp_sdev_destroy(struct scsi_device *dev)
 {
 	struct esp_lun_data *lp = dev->hostdata;
 
@@ -2667,9 +2667,9 @@ const struct scsi_host_template scsi_esp_template = {
 	.queuecommand		= esp_queuecommand,
 	.target_alloc		= esp_target_alloc,
 	.target_destroy		= esp_target_destroy,
-	.slave_alloc		= esp_slave_alloc,
-	.slave_configure	= esp_slave_configure,
-	.slave_destroy		= esp_slave_destroy,
+	.sdev_init		= esp_sdev_init,
+	.sdev_configure		= esp_sdev_configure,
+	.sdev_destroy		= esp_sdev_destroy,
 	.eh_abort_handler	= esp_eh_abort_handler,
 	.eh_bus_reset_handler	= esp_eh_bus_reset_handler,
 	.eh_host_reset_handler	= esp_eh_host_reset_handler,
diff --git a/drivers/scsi/esp_scsi.h b/drivers/scsi/esp_scsi.h
index 00cd7c0ccc76..7bb0b69bff24 100644
--- a/drivers/scsi/esp_scsi.h
+++ b/drivers/scsi/esp_scsi.h
@@ -80,7 +80,7 @@
 
 /* ESP config register 4 read-write */
 #define ESP_CONFIG4_BBTE      0x01     /* Back-to-back transfers     (fsc)   */
-#define ESP_CONGIG4_TEST      0x02     /* Transfer counter test mode (fsc)   */
+#define ESP_CONFIG4_TEST      0x02     /* Transfer counter test mode (fsc)   */
 #define ESP_CONFIG4_RADE      0x04     /* Active negation   (am53c974/fsc)   */
 #define ESP_CONFIG4_RAE       0x08     /* Act. negation REQ/ACK (am53c974)   */
 #define ESP_CONFIG4_PWD       0x20     /* Reduced power feature (am53c974)   */
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 39aec710660c..038e38578676 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -269,7 +269,7 @@ static const struct scsi_host_template fcoe_shost_template = {
 	.eh_abort_handler = fc_eh_abort,
 	.eh_device_reset_handler = fc_eh_device_reset,
 	.eh_host_reset_handler = fc_eh_host_reset,
-	.slave_alloc = fc_slave_alloc,
+	.sdev_init = fc_sdev_init,
 	.change_queue_depth = scsi_change_queue_depth,
 	.this_id = -1,
 	.cmd_per_lun = 3,
diff --git a/drivers/scsi/fdomain_pci.c b/drivers/scsi/fdomain_pci.c
index 3e05ce7b89e5..c15b2ce76e9f 100644
--- a/drivers/scsi/fdomain_pci.c
+++ b/drivers/scsi/fdomain_pci.c
@@ -47,7 +47,7 @@ static void fdomain_pci_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-static struct pci_device_id fdomain_pci_table[] = {
+static const struct pci_device_id fdomain_pci_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_FD, PCI_DEVICE_ID_FD_36C70) },
 	{}
 };
diff --git a/drivers/scsi/fnic/Makefile b/drivers/scsi/fnic/Makefile
index 6214a6b2e96d..c025e875009e 100644
--- a/drivers/scsi/fnic/Makefile
+++ b/drivers/scsi/fnic/Makefile
@@ -2,11 +2,13 @@
 obj-$(CONFIG_FCOE_FNIC) += fnic.o
 
 fnic-y	:= \
+	fip.o\
 	fnic_attrs.o \
 	fnic_isr.o \
 	fnic_main.o \
 	fnic_res.o \
 	fnic_fcs.o \
+	fdls_disc.o \
 	fnic_scsi.o \
 	fnic_trace.o \
 	fnic_debugfs.o \
@@ -15,4 +17,5 @@ fnic-y	:= \
 	vnic_intr.o \
 	vnic_rq.o \
 	vnic_wq_copy.o \
-	vnic_wq.o
+	vnic_wq.o \
+	fnic_pci_subsys_devid.o
diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c
new file mode 100644
index 000000000000..11211c469583
--- /dev/null
+++ b/drivers/scsi/fnic/fdls_disc.c
@@ -0,0 +1,4997 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
+ * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
+ */
+
+#include <linux/workqueue.h>
+#include "fnic.h"
+#include "fdls_fc.h"
+#include "fnic_fdls.h"
+#include <scsi/fc/fc_fcp.h>
+#include <scsi/scsi_transport_fc.h>
+#include <linux/utsname.h>
+
+#define FC_FC4_TYPE_SCSI 0x08
+#define PORT_SPEED_BIT_8 8
+#define PORT_SPEED_BIT_9 9
+#define PORT_SPEED_BIT_14 14
+#define PORT_SPEED_BIT_15 15
+
+/* FNIC FDMI Register HBA Macros */
+#define FNIC_FDMI_NUM_PORTS 1
+#define FNIC_FDMI_NUM_HBA_ATTRS 9
+#define FNIC_FDMI_TYPE_NODE_NAME	0X1
+#define FNIC_FDMI_TYPE_MANUFACTURER	0X2
+#define FNIC_FDMI_MANUFACTURER		"Cisco Systems"
+#define FNIC_FDMI_TYPE_SERIAL_NUMBER	0X3
+#define FNIC_FDMI_TYPE_MODEL		0X4
+#define FNIC_FDMI_TYPE_MODEL_DES	0X5
+#define FNIC_FDMI_MODEL_DESCRIPTION	"Cisco Virtual Interface Card"
+#define FNIC_FDMI_TYPE_HARDWARE_VERSION	0X6
+#define FNIC_FDMI_TYPE_DRIVER_VERSION	0X7
+#define FNIC_FDMI_TYPE_ROM_VERSION	0X8
+#define FNIC_FDMI_TYPE_FIRMWARE_VERSION	0X9
+#define FNIC_FDMI_NN_LEN 8
+#define FNIC_FDMI_MANU_LEN 20
+#define FNIC_FDMI_SERIAL_LEN 16
+#define FNIC_FDMI_MODEL_LEN 12
+#define FNIC_FDMI_MODEL_DES_LEN 56
+#define FNIC_FDMI_HW_VER_LEN 16
+#define FNIC_FDMI_DR_VER_LEN 28
+#define FNIC_FDMI_ROM_VER_LEN 8
+#define FNIC_FDMI_FW_VER_LEN 16
+
+/* FNIC FDMI Register PA Macros */
+#define FNIC_FDMI_TYPE_FC4_TYPES	0X1
+#define FNIC_FDMI_TYPE_SUPPORTED_SPEEDS 0X2
+#define FNIC_FDMI_TYPE_CURRENT_SPEED	0X3
+#define FNIC_FDMI_TYPE_MAX_FRAME_SIZE	0X4
+#define FNIC_FDMI_TYPE_OS_NAME		0X5
+#define FNIC_FDMI_TYPE_HOST_NAME	0X6
+#define FNIC_FDMI_NUM_PORT_ATTRS 6
+#define FNIC_FDMI_FC4_LEN 32
+#define FNIC_FDMI_SUPP_SPEED_LEN 4
+#define FNIC_FDMI_CUR_SPEED_LEN 4
+#define FNIC_FDMI_MFS_LEN 4
+#define FNIC_FDMI_MFS 0x800
+#define FNIC_FDMI_OS_NAME_LEN 16
+#define FNIC_FDMI_HN_LEN 24
+
+#define FDLS_FDMI_PLOGI_PENDING 0x1
+#define FDLS_FDMI_REG_HBA_PENDING 0x2
+#define FDLS_FDMI_RPA_PENDING 0x4
+#define FDLS_FDMI_ABORT_PENDING 0x8
+#define FDLS_FDMI_MAX_RETRY 3
+
+#define RETRIES_EXHAUSTED(iport)      \
+	(iport->fabric.retry_counter == FABRIC_LOGO_MAX_RETRY)
+
+#define FNIC_TPORT_MAX_NEXUS_RESTART (8)
+
+#define SCHEDULE_OXID_FREE_RETRY_TIME (300)
+
+/* Private Functions */
+static void fdls_fdmi_register_hba(struct fnic_iport_s *iport);
+static void fdls_fdmi_register_pa(struct fnic_iport_s *iport);
+static void fdls_send_rpn_id(struct fnic_iport_s *iport);
+static void fdls_process_flogi_rsp(struct fnic_iport_s *iport,
+				   struct fc_frame_header *fchdr,
+				   void *rx_frame);
+static void fnic_fdls_start_plogi(struct fnic_iport_s *iport);
+static void fnic_fdls_start_flogi(struct fnic_iport_s *iport);
+static struct fnic_tport_s *fdls_create_tport(struct fnic_iport_s *iport,
+					  uint32_t fcid,
+					  uint64_t wwpn);
+static void fdls_target_restart_nexus(struct fnic_tport_s *tport);
+static void fdls_start_tport_timer(struct fnic_iport_s *iport,
+					struct fnic_tport_s *tport, int timeout);
+static void fdls_tport_timer_callback(struct timer_list *t);
+static void fdls_send_fdmi_plogi(struct fnic_iport_s *iport);
+static void fdls_start_fabric_timer(struct fnic_iport_s *iport,
+			int timeout);
+static void fdls_init_plogi_frame(uint8_t *frame, struct fnic_iport_s *iport);
+static void fdls_init_els_acc_frame(uint8_t *frame, struct fnic_iport_s *iport);
+static void fdls_init_els_rjt_frame(uint8_t *frame, struct fnic_iport_s *iport);
+static void fdls_init_logo_frame(uint8_t *frame, struct fnic_iport_s *iport);
+static void fdls_init_fabric_abts_frame(uint8_t *frame,
+						struct fnic_iport_s *iport);
+
+uint8_t *fdls_alloc_frame(struct fnic_iport_s *iport)
+{
+	struct fnic *fnic = iport->fnic;
+	uint8_t *frame = NULL;
+
+	frame = mempool_alloc(fnic->frame_pool, GFP_ATOMIC);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame");
+		return NULL;
+	}
+
+	memset(frame, 0, FNIC_FCOE_FRAME_MAXSZ);
+	return frame;
+}
+
+/**
+ * fdls_alloc_oxid - Allocate an oxid from the bitmap based oxid pool
+ * @iport: Handle to iport instance
+ * @oxid_frame_type: Type of frame to allocate
+ * @active_oxid: the oxid which is in use
+ *
+ * Called with fnic lock held
+ */
+uint16_t fdls_alloc_oxid(struct fnic_iport_s *iport, int oxid_frame_type,
+	uint16_t *active_oxid)
+{
+	struct fnic *fnic = iport->fnic;
+	struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool;
+	int idx;
+	uint16_t oxid;
+
+	lockdep_assert_held(&fnic->fnic_lock);
+
+	/*
+	 * Allocate next available oxid from bitmap
+	 */
+	idx = find_next_zero_bit(oxid_pool->bitmap, FNIC_OXID_POOL_SZ, oxid_pool->next_idx);
+	if (idx == FNIC_OXID_POOL_SZ) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Alloc oxid: all oxid slots are busy iport state:%d\n",
+			iport->state);
+		return FNIC_UNASSIGNED_OXID;
+	}
+
+	WARN_ON(test_and_set_bit(idx, oxid_pool->bitmap));
+	oxid_pool->next_idx = (idx + 1) % FNIC_OXID_POOL_SZ;	/* cycle through the bitmap */
+
+	oxid = FNIC_OXID_ENCODE(idx, oxid_frame_type);
+	*active_oxid = oxid;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+	   "alloc oxid: 0x%x, iport state: %d\n",
+	   oxid, iport->state);
+	return oxid;
+}
+
+/**
+ * fdls_free_oxid_idx - Free the oxid using the idx
+ * @iport: Handle to iport instance
+ * @oxid_idx: The index to free
+ *
+ * Free the oxid immediately and make it available for new requests
+ * Called with fnic lock held
+ */
+static void fdls_free_oxid_idx(struct fnic_iport_s *iport, uint16_t oxid_idx)
+{
+	struct fnic *fnic = iport->fnic;
+	struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool;
+
+	lockdep_assert_held(&fnic->fnic_lock);
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"free oxid idx: 0x%x\n", oxid_idx);
+
+	WARN_ON(!test_and_clear_bit(oxid_idx, oxid_pool->bitmap));
+}
+
+/**
+ * fdls_reclaim_oxid_handler - Callback handler for delayed_oxid_work
+ * @work: Handle to work_struct
+ *
+ * Scheduled when an oxid is to be freed later
+ * After freeing expired oxid(s), the handler schedules
+ * another callback with the remaining time
+ * of next unexpired entry in the reclaim list.
+ */
+void fdls_reclaim_oxid_handler(struct work_struct *work)
+{
+	struct fnic_oxid_pool_s *oxid_pool = container_of(work,
+		struct fnic_oxid_pool_s, oxid_reclaim_work.work);
+	struct fnic_iport_s *iport = container_of(oxid_pool,
+		struct fnic_iport_s, oxid_pool);
+	struct fnic *fnic = iport->fnic;
+	struct reclaim_entry_s *reclaim_entry, *next;
+	unsigned long delay_j, cur_jiffies;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"Reclaim oxid callback\n");
+
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+
+	/* Though the work was scheduled for one entry,
+	 * walk through and free the expired entries which might have been scheduled
+	 * at around the same time as the first entry
+	 */
+	list_for_each_entry_safe(reclaim_entry, next,
+		&(oxid_pool->oxid_reclaim_list), links) {
+
+		/* The list is always maintained in the order of expiry time */
+		cur_jiffies = jiffies;
+		if (time_before(cur_jiffies, reclaim_entry->expires))
+			break;
+
+		list_del(&reclaim_entry->links);
+		fdls_free_oxid_idx(iport, reclaim_entry->oxid_idx);
+		kfree(reclaim_entry);
+	}
+
+	/* schedule to free up the next entry */
+	if (!list_empty(&oxid_pool->oxid_reclaim_list)) {
+		reclaim_entry = list_first_entry(&oxid_pool->oxid_reclaim_list,
+			struct reclaim_entry_s, links);
+
+		delay_j = reclaim_entry->expires - cur_jiffies;
+		schedule_delayed_work(&oxid_pool->oxid_reclaim_work, delay_j);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Scheduling next callback at:%ld jiffies\n", delay_j);
+	}
+
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+}
+
+/**
+ * fdls_free_oxid - Helper function to free the oxid
+ * @iport: Handle to iport instance
+ * @oxid: oxid to free
+ * @active_oxid: the oxid which is in use
+ *
+ * Called with fnic lock held
+ */
+void fdls_free_oxid(struct fnic_iport_s *iport,
+		uint16_t oxid, uint16_t *active_oxid)
+{
+	fdls_free_oxid_idx(iport, FNIC_OXID_IDX(oxid));
+	*active_oxid = FNIC_UNASSIGNED_OXID;
+}
+
+/**
+ * fdls_schedule_oxid_free - Schedule oxid to be freed later
+ * @iport: Handle to iport instance
+ * @active_oxid: the oxid which is in use
+ *
+ * Gets called in a rare case scenario when both a command
+ * (fdls or target discovery) timed out and the following ABTS
+ * timed out as well, without a link change.
+ *
+ * Called with fnic lock held
+ */
+void fdls_schedule_oxid_free(struct fnic_iport_s *iport, uint16_t *active_oxid)
+{
+	struct fnic *fnic = iport->fnic;
+	struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool;
+	struct reclaim_entry_s *reclaim_entry;
+	unsigned long delay_j = msecs_to_jiffies(OXID_RECLAIM_TOV(iport));
+	int oxid_idx = FNIC_OXID_IDX(*active_oxid);
+
+	lockdep_assert_held(&fnic->fnic_lock);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"Schedule oxid free. oxid: 0x%x\n", *active_oxid);
+
+	*active_oxid = FNIC_UNASSIGNED_OXID;
+
+	reclaim_entry = (struct reclaim_entry_s *)
+		kzalloc(sizeof(struct reclaim_entry_s), GFP_ATOMIC);
+
+	if (!reclaim_entry) {
+		FNIC_FCS_DBG(KERN_WARNING, fnic->host, fnic->fnic_num,
+			"Failed to allocate memory for reclaim struct for oxid idx: %d\n",
+			oxid_idx);
+
+		/* Retry the scheduling  */
+		WARN_ON(test_and_set_bit(oxid_idx, oxid_pool->pending_schedule_free));
+		schedule_delayed_work(&oxid_pool->schedule_oxid_free_retry, 0);
+		return;
+	}
+
+	reclaim_entry->oxid_idx = oxid_idx;
+	reclaim_entry->expires = round_jiffies(jiffies + delay_j);
+
+	list_add_tail(&reclaim_entry->links, &oxid_pool->oxid_reclaim_list);
+
+	schedule_delayed_work(&oxid_pool->oxid_reclaim_work, delay_j);
+}
+
+/**
+ * fdls_schedule_oxid_free_retry_work - Thread to schedule the
+ * oxid to be freed later
+ *
+ * @work: Handle to the work struct
+ */
+void fdls_schedule_oxid_free_retry_work(struct work_struct *work)
+{
+	struct fnic_oxid_pool_s *oxid_pool = container_of(work,
+		struct fnic_oxid_pool_s, schedule_oxid_free_retry.work);
+	struct fnic_iport_s *iport = container_of(oxid_pool,
+		struct fnic_iport_s, oxid_pool);
+	struct fnic *fnic = iport->fnic;
+	struct reclaim_entry_s *reclaim_entry;
+	unsigned long delay_j = msecs_to_jiffies(OXID_RECLAIM_TOV(iport));
+	int idx;
+
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+
+	for_each_set_bit(idx, oxid_pool->pending_schedule_free, FNIC_OXID_POOL_SZ) {
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Schedule oxid free. oxid idx: %d\n", idx);
+
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+	reclaim_entry = (struct reclaim_entry_s *)
+	kzalloc(sizeof(struct reclaim_entry_s), GFP_KERNEL);
+		spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+
+		if (!reclaim_entry) {
+			FNIC_FCS_DBG(KERN_WARNING, fnic->host, fnic->fnic_num,
+				"Failed to allocate memory for reclaim struct for oxid idx: 0x%x\n",
+				idx);
+
+			schedule_delayed_work(&oxid_pool->schedule_oxid_free_retry,
+				msecs_to_jiffies(SCHEDULE_OXID_FREE_RETRY_TIME));
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			return;
+		}
+
+		if (test_and_clear_bit(idx, oxid_pool->pending_schedule_free)) {
+			reclaim_entry->oxid_idx = idx;
+			reclaim_entry->expires = round_jiffies(jiffies + delay_j);
+			list_add_tail(&reclaim_entry->links, &oxid_pool->oxid_reclaim_list);
+			schedule_delayed_work(&oxid_pool->oxid_reclaim_work, delay_j);
+		} else {
+			/* unlikely scenario, free the allocated memory and continue */
+			kfree(reclaim_entry);
+		}
+}
+
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+}
+
+static bool fdls_is_oxid_fabric_req(uint16_t oxid)
+{
+	int oxid_frame_type = FNIC_FRAME_TYPE(oxid);
+
+	switch (oxid_frame_type) {
+	case FNIC_FRAME_TYPE_FABRIC_FLOGI:
+	case FNIC_FRAME_TYPE_FABRIC_PLOGI:
+	case FNIC_FRAME_TYPE_FABRIC_RPN:
+	case FNIC_FRAME_TYPE_FABRIC_RFT:
+	case FNIC_FRAME_TYPE_FABRIC_RFF:
+	case FNIC_FRAME_TYPE_FABRIC_GPN_FT:
+	case FNIC_FRAME_TYPE_FABRIC_LOGO:
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
+static bool fdls_is_oxid_fdmi_req(uint16_t oxid)
+{
+	int oxid_frame_type = FNIC_FRAME_TYPE(oxid);
+
+	switch (oxid_frame_type) {
+	case FNIC_FRAME_TYPE_FDMI_PLOGI:
+	case FNIC_FRAME_TYPE_FDMI_RHBA:
+	case FNIC_FRAME_TYPE_FDMI_RPA:
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
+static bool fdls_is_oxid_tgt_req(uint16_t oxid)
+{
+	int oxid_frame_type = FNIC_FRAME_TYPE(oxid);
+
+	switch (oxid_frame_type) {
+	case FNIC_FRAME_TYPE_TGT_PLOGI:
+	case FNIC_FRAME_TYPE_TGT_PRLI:
+	case FNIC_FRAME_TYPE_TGT_ADISC:
+	case FNIC_FRAME_TYPE_TGT_LOGO:
+		break;
+	default:
+		return false;
+	}
+	return true;
+}
+
+static void fdls_reset_oxid_pool(struct fnic_iport_s *iport)
+{
+	struct fnic_oxid_pool_s *oxid_pool = &iport->oxid_pool;
+
+	oxid_pool->next_idx = 0;
+}
+
+void fnic_del_fabric_timer_sync(struct fnic *fnic)
+{
+	fnic->iport.fabric.del_timer_inprogress = 1;
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+	del_timer_sync(&fnic->iport.fabric.retry_timer);
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	fnic->iport.fabric.del_timer_inprogress = 0;
+}
+
+void fnic_del_tport_timer_sync(struct fnic *fnic,
+						struct fnic_tport_s *tport)
+{
+	tport->del_timer_inprogress = 1;
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+	del_timer_sync(&tport->retry_timer);
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	tport->del_timer_inprogress = 0;
+}
+
+static void
+fdls_start_fabric_timer(struct fnic_iport_s *iport, int timeout)
+{
+	u64 fabric_tov;
+	struct fnic *fnic = iport->fnic;
+
+	if (iport->fabric.timer_pending) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "iport fcid: 0x%x: Canceling fabric disc timer\n",
+					 iport->fcid);
+		fnic_del_fabric_timer_sync(fnic);
+		iport->fabric.timer_pending = 0;
+	}
+
+	if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED))
+		iport->fabric.retry_counter++;
+
+	fabric_tov = jiffies + msecs_to_jiffies(timeout);
+	mod_timer(&iport->fabric.retry_timer, round_jiffies(fabric_tov));
+	iport->fabric.timer_pending = 1;
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "fabric timer is %d ", timeout);
+}
+
+static void
+fdls_start_tport_timer(struct fnic_iport_s *iport,
+					   struct fnic_tport_s *tport, int timeout)
+{
+	u64 fabric_tov;
+	struct fnic *fnic = iport->fnic;
+
+	if (tport->timer_pending) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "tport fcid 0x%x: Canceling disc timer\n",
+					 tport->fcid);
+		fnic_del_tport_timer_sync(fnic, tport);
+		tport->timer_pending = 0;
+	}
+
+	if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED))
+		tport->retry_counter++;
+
+	fabric_tov = jiffies + msecs_to_jiffies(timeout);
+	mod_timer(&tport->retry_timer, round_jiffies(fabric_tov));
+	tport->timer_pending = 1;
+}
+
+void fdls_init_plogi_frame(uint8_t *frame,
+		struct fnic_iport_s *iport)
+{
+	struct fc_std_flogi *pplogi;
+	uint8_t s_id[3];
+
+	pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pplogi = (struct fc_std_flogi) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_d_id = {0xFF, 0xFF, 0xFC},
+		      .fh_type = FC_TYPE_ELS, .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.els = {
+		    .fl_cmd = ELS_PLOGI,
+		    .fl_csp = {.sp_hi_ver = FNIC_FC_PH_VER_HI,
+			       .sp_lo_ver = FNIC_FC_PH_VER_LO,
+			       .sp_bb_cred = cpu_to_be16(FNIC_FC_B2B_CREDIT),
+			       .sp_features = cpu_to_be16(FC_SP_FT_CIRO),
+			       .sp_bb_data = cpu_to_be16(FNIC_FC_B2B_RDF_SZ),
+			       .sp_tot_seq = cpu_to_be16(FNIC_FC_CONCUR_SEQS),
+			       .sp_rel_off = cpu_to_be16(FNIC_FC_RO_INFO),
+			       .sp_e_d_tov = cpu_to_be32(FC_DEF_E_D_TOV)},
+		    .fl_cssp[2].cp_class = cpu_to_be16(FC_CPC_VALID | FC_CPC_SEQ),
+		    .fl_cssp[2].cp_rdfs = cpu_to_be16(0x800),
+		    .fl_cssp[2].cp_con_seq = cpu_to_be16(0xFF),
+		    .fl_cssp[2].cp_open_seq = 1}
+	};
+
+	FNIC_STD_SET_NPORT_NAME(&pplogi->els.fl_wwpn, iport->wwpn);
+	FNIC_STD_SET_NODE_NAME(&pplogi->els.fl_wwnn, iport->wwnn);
+	FNIC_LOGI_SET_RDF_SIZE(pplogi->els, iport->max_payload_size);
+
+	hton24(s_id, iport->fcid);
+	FNIC_STD_SET_S_ID(pplogi->fchdr, s_id);
+}
+
+static void fdls_init_els_acc_frame(uint8_t *frame,
+		struct fnic_iport_s *iport)
+{
+	struct fc_std_els_acc_rsp *pels_acc;
+	uint8_t s_id[3];
+
+	pels_acc = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pels_acc = (struct fc_std_els_acc_rsp) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REP,
+			  .fh_type = FC_TYPE_ELS, .fh_f_ctl = {FNIC_ELS_REP_FCTL, 0, 0}},
+		.acc.la_cmd = ELS_LS_ACC,
+	};
+
+	hton24(s_id, iport->fcid);
+	FNIC_STD_SET_S_ID(pels_acc->fchdr, s_id);
+	FNIC_STD_SET_RX_ID(pels_acc->fchdr, FNIC_UNASSIGNED_RXID);
+}
+
+static void fdls_init_els_rjt_frame(uint8_t *frame,
+		struct fnic_iport_s *iport)
+{
+	struct fc_std_els_rjt_rsp *pels_rjt;
+
+	pels_rjt = (struct fc_std_els_rjt_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pels_rjt = (struct fc_std_els_rjt_rsp) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REP, .fh_type = FC_TYPE_ELS,
+			  .fh_f_ctl = {FNIC_ELS_REP_FCTL, 0, 0}},
+		.rej.er_cmd = ELS_LS_RJT,
+	};
+
+	FNIC_STD_SET_RX_ID(pels_rjt->fchdr, FNIC_UNASSIGNED_RXID);
+}
+
+static void fdls_init_logo_frame(uint8_t *frame,
+		struct fnic_iport_s *iport)
+{
+	struct fc_std_logo *plogo;
+	uint8_t s_id[3];
+
+	plogo = (struct fc_std_logo *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*plogo = (struct fc_std_logo) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_type = FC_TYPE_ELS,
+		      .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0}},
+		.els.fl_cmd = ELS_LOGO,
+	};
+
+	hton24(s_id, iport->fcid);
+	FNIC_STD_SET_S_ID(plogo->fchdr, s_id);
+	memcpy(plogo->els.fl_n_port_id, s_id, 3);
+
+	FNIC_STD_SET_NPORT_NAME(&plogo->els.fl_n_port_wwn,
+			    iport->wwpn);
+}
+
+static void fdls_init_fabric_abts_frame(uint8_t *frame,
+		struct fnic_iport_s *iport)
+{
+	struct fc_frame_header *pfabric_abts;
+
+	pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pfabric_abts = (struct fc_frame_header) {
+		.fh_r_ctl = FC_RCTL_BA_ABTS,	/* ABTS */
+		.fh_s_id = {0x00, 0x00, 0x00},
+		.fh_cs_ctl = 0x00, .fh_type = FC_TYPE_BLS,
+		.fh_f_ctl = {FNIC_REQ_ABTS_FCTL, 0, 0}, .fh_seq_id = 0x00,
+		.fh_df_ctl = 0x00, .fh_seq_cnt = 0x0000,
+		.fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID),
+		.fh_parm_offset = 0x00000000,	/* bit:0 = 0 Abort a exchange */
+	};
+}
+
+static void
+fdls_send_rscn_resp(struct fnic_iport_s *iport,
+		    struct fc_frame_header *rscn_fchdr)
+{
+	uint8_t *frame;
+	struct fc_std_els_acc_rsp *pels_acc;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_acc_rsp);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send RSCN response");
+		return;
+	}
+
+	pels_acc = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_els_acc_frame(frame, iport);
+
+	FNIC_STD_SET_D_ID(pels_acc->fchdr, rscn_fchdr->fh_s_id);
+
+	oxid = FNIC_STD_GET_OX_ID(rscn_fchdr);
+	FNIC_STD_SET_OX_ID(pels_acc->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send RSCN response with oxid: 0x%x",
+		 iport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+static void
+fdls_send_logo_resp(struct fnic_iport_s *iport,
+		    struct fc_frame_header *req_fchdr)
+{
+	uint8_t *frame;
+	struct fc_std_els_acc_rsp *plogo_resp;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_acc_rsp);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send LOGO response");
+		return;
+	}
+
+	plogo_resp = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_els_acc_frame(frame, iport);
+
+	FNIC_STD_SET_D_ID(plogo_resp->fchdr, req_fchdr->fh_s_id);
+
+	oxid = FNIC_STD_GET_OX_ID(req_fchdr);
+	FNIC_STD_SET_OX_ID(plogo_resp->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send LOGO response with oxid: 0x%x",
+		 iport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+void
+fdls_send_tport_abts(struct fnic_iport_s *iport,
+					 struct fnic_tport_s *tport)
+{
+	uint8_t *frame;
+	uint8_t s_id[3];
+	uint8_t d_id[3];
+	struct fnic *fnic = iport->fnic;
+	struct fc_frame_header *ptport_abts;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_frame_header);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send tport ABTS");
+		return;
+	}
+
+	ptport_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*ptport_abts = (struct fc_frame_header) {
+		.fh_r_ctl = FC_RCTL_BA_ABTS,	/* ABTS */
+		.fh_cs_ctl = 0x00, .fh_type = FC_TYPE_BLS,
+		.fh_f_ctl = {FNIC_REQ_ABTS_FCTL, 0, 0}, .fh_seq_id = 0x00,
+		.fh_df_ctl = 0x00, .fh_seq_cnt = 0x0000,
+		.fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID),
+		.fh_parm_offset = 0x00000000,	/* bit:0 = 0 Abort a exchange */
+	};
+
+	hton24(s_id, iport->fcid);
+	hton24(d_id, tport->fcid);
+	FNIC_STD_SET_S_ID(*ptport_abts, s_id);
+	FNIC_STD_SET_D_ID(*ptport_abts, d_id);
+	tport->flags |= FNIC_FDLS_TGT_ABORT_ISSUED;
+
+	FNIC_STD_SET_OX_ID(*ptport_abts, tport->active_oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS send tport abts: tport->state: %d ",
+				 iport->fcid, tport->state);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_tport_timer(iport, tport, 2 * iport->e_d_tov);
+}
+static void fdls_send_fabric_abts(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	uint8_t s_id[3];
+	uint8_t d_id[3];
+	struct fnic *fnic = iport->fnic;
+	struct fc_frame_header *pfabric_abts;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_frame_header);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send fabric ABTS");
+		return;
+	}
+
+	pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_fabric_abts_frame(frame, iport);
+
+	hton24(s_id, iport->fcid);
+
+	switch (iport->fabric.state) {
+	case FDLS_STATE_FABRIC_LOGO:
+		hton24(d_id, FC_FID_FLOGI);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_FABRIC_FLOGI:
+		hton24(d_id, FC_FID_FLOGI);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_FABRIC_PLOGI:
+		FNIC_STD_SET_S_ID(*pfabric_abts, s_id);
+		hton24(d_id, FC_FID_DIR_SERV);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_RPN_ID:
+		FNIC_STD_SET_S_ID(*pfabric_abts, s_id);
+		hton24(d_id, FC_FID_DIR_SERV);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_SCR:
+		FNIC_STD_SET_S_ID(*pfabric_abts, s_id);
+		hton24(d_id, FC_FID_FCTRL);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_REGISTER_FC4_TYPES:
+		FNIC_STD_SET_S_ID(*pfabric_abts, s_id);
+		hton24(d_id, FC_FID_DIR_SERV);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_REGISTER_FC4_FEATURES:
+		FNIC_STD_SET_S_ID(*pfabric_abts, s_id);
+		hton24(d_id, FC_FID_DIR_SERV);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+
+	case FDLS_STATE_GPN_FT:
+		FNIC_STD_SET_S_ID(*pfabric_abts, s_id);
+		hton24(d_id, FC_FID_DIR_SERV);
+		FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+		break;
+	default:
+		return;
+	}
+
+	oxid = iport->active_oxid_fabric_req;
+	FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send fabric abts. iport->fabric.state: %d oxid: 0x%x",
+		 iport->fcid, iport->fabric.state, oxid);
+
+	iport->fabric.flags |= FNIC_FDLS_FABRIC_ABORT_ISSUED;
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+	iport->fabric.timer_pending = 1;
+}
+
+static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	uint8_t d_id[3];
+	struct fnic *fnic = iport->fnic;
+	struct fc_frame_header *pfabric_abts;
+	unsigned long fdmi_tov;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_frame_header);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send FDMI ABTS");
+		return;
+	}
+
+	pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_fabric_abts_frame(frame, iport);
+
+	hton24(d_id, FC_FID_MGMT_SERV);
+	FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+
+	if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) {
+		oxid = iport->active_oxid_fdmi_plogi;
+		FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+		fnic_send_fcoe_frame(iport, frame, frame_size);
+	} else {
+		if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) {
+			oxid = iport->active_oxid_fdmi_rhba;
+			FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+			fnic_send_fcoe_frame(iport, frame, frame_size);
+		}
+		if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) {
+			oxid = iport->active_oxid_fdmi_rpa;
+			FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+			fnic_send_fcoe_frame(iport, frame, frame_size);
+		}
+	}
+
+	fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov);
+	mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov));
+	iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING;
+}
+
+static void fdls_send_fabric_flogi(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_flogi *pflogi;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_flogi);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send FLOGI");
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	pflogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pflogi = (struct fc_std_flogi) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_d_id = {0xFF, 0xFF, 0xFE},
+		      .fh_type = FC_TYPE_ELS, .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.els.fl_cmd = ELS_FLOGI,
+		.els.fl_csp = {.sp_hi_ver = FNIC_FC_PH_VER_HI,
+			   .sp_lo_ver = FNIC_FC_PH_VER_LO,
+			   .sp_bb_cred = cpu_to_be16(FNIC_FC_B2B_CREDIT),
+			   .sp_bb_data = cpu_to_be16(FNIC_FC_B2B_RDF_SZ)},
+		.els.fl_cssp[2].cp_class = cpu_to_be16(FC_CPC_VALID | FC_CPC_SEQ)
+	};
+
+	FNIC_STD_SET_NPORT_NAME(&pflogi->els.fl_wwpn, iport->wwpn);
+	FNIC_STD_SET_NODE_NAME(&pflogi->els.fl_wwnn, iport->wwnn);
+	FNIC_LOGI_SET_RDF_SIZE(pflogi->els, iport->max_payload_size);
+	FNIC_LOGI_SET_R_A_TOV(pflogi->els, iport->r_a_tov);
+	FNIC_LOGI_SET_E_D_TOV(pflogi->els, iport->e_d_tov);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_FLOGI,
+		&iport->active_oxid_fabric_req);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send FLOGI",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(pflogi->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send fabric FLOGI with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	atomic64_inc(&iport->iport_stats.fabric_flogi_sent);
+err_out:
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+static void fdls_send_fabric_plogi(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_flogi *pplogi;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_flogi);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send PLOGI");
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_plogi_frame(frame, iport);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_PLOGI,
+		&iport->active_oxid_fabric_req);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send fabric PLOGI",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(pplogi->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send fabric PLOGI with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	atomic64_inc(&iport->iport_stats.fabric_plogi_sent);
+
+err_out:
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+static void fdls_send_fdmi_plogi(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_flogi *pplogi;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_flogi);
+	uint8_t d_id[3];
+	u64 fdmi_tov;
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send FDMI PLOGI");
+		goto err_out;
+	}
+
+	pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_plogi_frame(frame, iport);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FDMI_PLOGI,
+		&iport->active_oxid_fdmi_plogi);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "0x%x: Failed to allocate OXID to send FDMI PLOGI",
+			     iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(pplogi->fchdr, oxid);
+
+	hton24(d_id, FC_FID_MGMT_SERV);
+	FNIC_STD_SET_D_ID(pplogi->fchdr, d_id);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: FDLS send FDMI PLOGI with oxid: 0x%x",
+		     iport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+err_out:
+	fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov);
+	mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov));
+	iport->fabric.fdmi_pending = FDLS_FDMI_PLOGI_PENDING;
+}
+
+static void fdls_send_rpn_id(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_rpn_id *prpn_id;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_rpn_id);
+	uint8_t fcid[3];
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send RPN_ID");
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	prpn_id = (struct fc_std_rpn_id *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*prpn_id = (struct fc_std_rpn_id) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL,
+		      .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT,
+		      .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR,
+			      .ct_fs_subtype = FC_NS_SUBTYPE,
+			      .ct_cmd = cpu_to_be16(FC_NS_RPN_ID)}
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(prpn_id->fchdr, fcid);
+
+	FNIC_STD_SET_PORT_ID(prpn_id->rpn_id, fcid);
+	FNIC_STD_SET_PORT_NAME(prpn_id->rpn_id, iport->wwpn);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_RPN,
+		&iport->active_oxid_fabric_req);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send RPN_ID",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(prpn_id->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send RPN ID with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+err_out:
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+static void fdls_send_scr(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_scr *pscr;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_scr);
+	uint8_t fcid[3];
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send SCR");
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	pscr = (struct fc_std_scr *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pscr = (struct fc_std_scr) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ,
+		      .fh_d_id = {0xFF, 0xFF, 0xFD}, .fh_type = FC_TYPE_ELS,
+		      .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.scr = {.scr_cmd = ELS_SCR,
+		    .scr_reg_func = ELS_SCRF_FULL}
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(pscr->fchdr, fcid);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_SCR,
+		&iport->active_oxid_fabric_req);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send SCR",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(pscr->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send SCR with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	atomic64_inc(&iport->iport_stats.fabric_scr_sent);
+
+err_out:
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+static void fdls_send_gpn_ft(struct fnic_iport_s *iport, int fdls_state)
+{
+	uint8_t *frame;
+	struct fc_std_gpn_ft *pgpn_ft;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_gpn_ft);
+	uint8_t fcid[3];
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send GPN FT");
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	pgpn_ft = (struct fc_std_gpn_ft *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pgpn_ft = (struct fc_std_gpn_ft) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL,
+		      .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT,
+		      .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR,
+			      .ct_fs_subtype = FC_NS_SUBTYPE,
+			      .ct_cmd = cpu_to_be16(FC_NS_GPN_FT)},
+		.gpn_ft.fn_fc4_type = 0x08
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(pgpn_ft->fchdr, fcid);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_GPN_FT,
+		&iport->active_oxid_fabric_req);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send GPN FT",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		iport->fabric.flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(pgpn_ft->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send GPN FT with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+err_out:
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+	fdls_set_state((&iport->fabric), fdls_state);
+}
+
+static void
+fdls_send_tgt_adisc(struct fnic_iport_s *iport, struct fnic_tport_s *tport)
+{
+	uint8_t *frame;
+	struct fc_std_els_adisc *padisc;
+	uint8_t s_id[3];
+	uint8_t d_id[3];
+	uint16_t oxid;
+	struct fnic *fnic = iport->fnic;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_adisc);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send TGT ADISC");
+		tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	padisc = (struct fc_std_els_adisc *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+
+	hton24(s_id, iport->fcid);
+	hton24(d_id, tport->fcid);
+	memcpy(padisc->els.adisc_port_id, s_id, 3);
+	FNIC_STD_SET_S_ID(padisc->fchdr, s_id);
+	FNIC_STD_SET_D_ID(padisc->fchdr, d_id);
+
+	FNIC_STD_SET_F_CTL(padisc->fchdr, FNIC_ELS_REQ_FCTL << 16);
+	FNIC_STD_SET_R_CTL(padisc->fchdr, FC_RCTL_ELS_REQ);
+	FNIC_STD_SET_TYPE(padisc->fchdr, FC_TYPE_ELS);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_ADISC, &tport->active_oxid);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "0x%x: Failed to allocate OXID to send TGT ADISC",
+					 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(padisc->fchdr, oxid);
+	FNIC_STD_SET_RX_ID(padisc->fchdr, FNIC_UNASSIGNED_RXID);
+
+	tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED;
+
+	FNIC_STD_SET_NPORT_NAME(&padisc->els.adisc_wwpn,
+				iport->wwpn);
+	FNIC_STD_SET_NODE_NAME(&padisc->els.adisc_wwnn,
+			iport->wwnn);
+
+	padisc->els.adisc_cmd = ELS_ADISC;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS send ADISC to tgt fcid: 0x%x",
+				 iport->fcid, tport->fcid);
+
+	atomic64_inc(&iport->iport_stats.tport_adisc_sent);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+err_out:
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_tport_timer(iport, tport, 2 * iport->e_d_tov);
+}
+
+bool fdls_delete_tport(struct fnic_iport_s *iport, struct fnic_tport_s *tport)
+{
+	struct fnic_tport_event_s *tport_del_evt;
+	struct fnic *fnic = iport->fnic;
+
+	if ((tport->state == FDLS_TGT_STATE_OFFLINING)
+	    || (tport->state == FDLS_TGT_STATE_OFFLINE)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "tport fcid 0x%x: tport state is offlining/offline\n",
+			     tport->fcid);
+		return false;
+	}
+
+	fdls_set_tport_state(tport, FDLS_TGT_STATE_OFFLINING);
+	/*
+	 * By setting this flag, the tport will not be seen in a look-up
+	 * in an RSCN. Even if we move to multithreaded model, this tport
+	 * will be destroyed and a new RSCN will have to create a new one
+	 */
+	tport->flags |= FNIC_FDLS_TPORT_TERMINATING;
+
+	if (tport->timer_pending) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "tport fcid 0x%x: Canceling disc timer\n",
+					 tport->fcid);
+		fnic_del_tport_timer_sync(fnic, tport);
+		tport->timer_pending = 0;
+	}
+
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+	fnic_rport_exch_reset(iport->fnic, tport->fcid);
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+
+	if (tport->flags & FNIC_FDLS_SCSI_REGISTERED) {
+		tport_del_evt =
+			kzalloc(sizeof(struct fnic_tport_event_s), GFP_ATOMIC);
+		if (!tport_del_evt) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Failed to allocate memory for tport fcid: 0x%0x\n",
+				 tport->fcid);
+			return false;
+		}
+		tport_del_evt->event = TGT_EV_RPORT_DEL;
+		tport_del_evt->arg1 = (void *) tport;
+		list_add_tail(&tport_del_evt->links, &fnic->tport_event_list);
+		queue_work(fnic_event_queue, &fnic->tport_work);
+	} else {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "tport 0x%x not reg with scsi_transport. Freeing locally",
+			 tport->fcid);
+		list_del(&tport->links);
+		kfree(tport);
+	}
+	return true;
+}
+
+static void
+fdls_send_tgt_plogi(struct fnic_iport_s *iport, struct fnic_tport_s *tport)
+{
+	uint8_t *frame;
+	struct fc_std_flogi *pplogi;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_flogi);
+	uint8_t d_id[3];
+	uint32_t timeout;
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send TGT PLOGI");
+		tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	pplogi = (struct fc_std_flogi *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_plogi_frame(frame, iport);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_PLOGI, &tport->active_oxid);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Failed to allocate oxid to send PLOGI to fcid: 0x%x",
+				 iport->fcid, tport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+	FNIC_STD_SET_OX_ID(pplogi->fchdr, oxid);
+
+	tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED;
+
+	hton24(d_id, tport->fcid);
+	FNIC_STD_SET_D_ID(pplogi->fchdr, d_id);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS send tgt PLOGI to tgt: 0x%x with oxid: 0x%x",
+				 iport->fcid, tport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	atomic64_inc(&iport->iport_stats.tport_plogi_sent);
+
+err_out:
+	timeout = max(2 * iport->e_d_tov, iport->plogi_timeout);
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_tport_timer(iport, tport, timeout);
+}
+
+static uint16_t
+fnic_fc_plogi_rsp_rdf(struct fnic_iport_s *iport,
+		      struct fc_std_flogi *plogi_rsp)
+{
+	uint16_t b2b_rdf_size =
+	    be16_to_cpu(FNIC_LOGI_RDF_SIZE(plogi_rsp->els));
+	uint16_t spc3_rdf_size =
+	    be16_to_cpu(plogi_rsp->els.fl_cssp[2].cp_rdfs) & FNIC_FC_C3_RDF;
+	struct fnic *fnic = iport->fnic;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "MFS: b2b_rdf_size: 0x%x spc3_rdf_size: 0x%x",
+			 b2b_rdf_size, spc3_rdf_size);
+
+	return min(b2b_rdf_size, spc3_rdf_size);
+}
+
+static void fdls_send_register_fc4_types(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_rft_id *prft_id;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_rft_id);
+	uint8_t fcid[3];
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send RFT");
+		return;
+	}
+
+	prft_id = (struct fc_std_rft_id *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*prft_id = (struct fc_std_rft_id) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL,
+		      .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT,
+		      .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR,
+			      .ct_fs_subtype = FC_NS_SUBTYPE,
+			      .ct_cmd = cpu_to_be16(FC_NS_RFT_ID)}
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(prft_id->fchdr, fcid);
+	FNIC_STD_SET_PORT_ID(prft_id->rft_id, fcid);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_RFT,
+		&iport->active_oxid_fabric_req);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send RFT",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(prft_id->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send RFT with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	prft_id->rft_id.fr_fts.ff_type_map[0] =
+	    cpu_to_be32(1 << FC_TYPE_FCP);
+
+	prft_id->rft_id.fr_fts.ff_type_map[1] =
+	cpu_to_be32(1 << (FC_TYPE_CT % FC_NS_BPW));
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+static void fdls_send_register_fc4_features(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_rff_id *prff_id;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_rff_id);
+	uint8_t fcid[3];
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send RFF");
+		return;
+	}
+
+	prff_id = (struct fc_std_rff_id *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*prff_id = (struct fc_std_rff_id) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL,
+		      .fh_d_id = {0xFF, 0xFF, 0xFC}, .fh_type = FC_TYPE_CT,
+		      .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+		      .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.fc_std_ct_hdr = {.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_DIR,
+			      .ct_fs_subtype = FC_NS_SUBTYPE,
+			      .ct_cmd = cpu_to_be16(FC_NS_RFF_ID)},
+		.rff_id.fr_feat = 0x2,
+		.rff_id.fr_type = FC_TYPE_FCP
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(prff_id->fchdr, fcid);
+	FNIC_STD_SET_PORT_ID(prff_id->rff_id, fcid);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_RFF,
+		&iport->active_oxid_fabric_req);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "0x%x: Failed to allocate OXID to send RFF",
+				 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(prff_id->fchdr, oxid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send RFF with oxid: 0x%x", iport->fcid,
+		 oxid);
+
+	prff_id->rff_id.fr_type = FC_TYPE_FCP;
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+static void
+fdls_send_tgt_prli(struct fnic_iport_s *iport, struct fnic_tport_s *tport)
+{
+	uint8_t *frame;
+	struct fc_std_els_prli *pprli;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_prli);
+	uint8_t s_id[3];
+	uint8_t d_id[3];
+	uint32_t timeout;
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send TGT PRLI");
+		tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	pprli = (struct fc_std_els_prli *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pprli = (struct fc_std_els_prli) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_ELS_REQ, .fh_type = FC_TYPE_ELS,
+			  .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+			  .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+		.els_prli = {.prli_cmd = ELS_PRLI,
+			     .prli_spp_len = 16,
+			     .prli_len = cpu_to_be16(0x14)},
+		.sp = {.spp_type = 0x08, .spp_flags = 0x0020,
+		       .spp_params = cpu_to_be32(0xA2)}
+	};
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_PRLI, &tport->active_oxid);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			"0x%x: Failed to allocate OXID to send TGT PRLI to 0x%x",
+			iport->fcid, tport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		goto err_out;
+	}
+
+	tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED;
+
+	hton24(s_id, iport->fcid);
+	hton24(d_id, tport->fcid);
+
+	FNIC_STD_SET_OX_ID(pprli->fchdr, oxid);
+	FNIC_STD_SET_S_ID(pprli->fchdr, s_id);
+	FNIC_STD_SET_D_ID(pprli->fchdr, d_id);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"0x%x: FDLS send PRLI to tgt: 0x%x with oxid: 0x%x",
+			iport->fcid, tport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	atomic64_inc(&iport->iport_stats.tport_prli_sent);
+
+err_out:
+	timeout = max(2 * iport->e_d_tov, iport->plogi_timeout);
+	/* Even if fnic_send_fcoe_frame() fails we want to retry after timeout */
+	fdls_start_tport_timer(iport, tport, timeout);
+}
+
+/**
+ * fdls_send_fabric_logo - Send flogo to the fcf
+ * @iport: Handle to fnic iport
+ *
+ * This function does not change or check the fabric state.
+ * It the caller's responsibility to set the appropriate iport fabric
+ * state when this is called. Normally it is FDLS_STATE_FABRIC_LOGO.
+ * Currently this assumes to be called with fnic lock held.
+ */
+void fdls_send_fabric_logo(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_logo *plogo;
+	struct fnic *fnic = iport->fnic;
+	uint8_t d_id[3];
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_logo);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send fabric LOGO");
+		return;
+	}
+
+	plogo = (struct fc_std_logo *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_logo_frame(frame, iport);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_LOGO,
+		&iport->active_oxid_fabric_req);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send fabric LOGO",
+			 iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(plogo->fchdr, oxid);
+
+	hton24(d_id, FC_FID_FLOGI);
+	FNIC_STD_SET_D_ID(plogo->fchdr, d_id);
+
+	iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED;
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send fabric LOGO with oxid: 0x%x",
+		 iport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+	fdls_start_fabric_timer(iport, 2 * iport->e_d_tov);
+}
+
+/**
+ * fdls_tgt_logout - Send plogo to the remote port
+ * @iport: Handle to fnic iport
+ * @tport: Handle to remote port
+ *
+ * This function does not change or check the fabric/tport state.
+ * It the caller's responsibility to set the appropriate tport/fabric
+ * state when this is called. Normally that is fdls_tgt_state_plogo.
+ * This could be used to send plogo to nameserver process
+ * also not just target processes
+ */
+void fdls_tgt_logout(struct fnic_iport_s *iport, struct fnic_tport_s *tport)
+{
+	uint8_t *frame;
+	struct fc_std_logo *plogo;
+	struct fnic *fnic = iport->fnic;
+	uint8_t d_id[3];
+	uint16_t oxid;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_logo);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send fabric LOGO");
+		return;
+	}
+
+	plogo = (struct fc_std_logo *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_logo_frame(frame, iport);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_TGT_LOGO, &tport->active_oxid);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "0x%x: Failed to allocate OXID to send tgt LOGO",
+		     iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(plogo->fchdr, oxid);
+
+	hton24(d_id, tport->fcid);
+	FNIC_STD_SET_D_ID(plogo->fchdr, d_id);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send tgt LOGO with oxid: 0x%x",
+		 iport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+
+	atomic64_inc(&iport->iport_stats.tport_logo_sent);
+}
+
+static void fdls_tgt_discovery_start(struct fnic_iport_s *iport)
+{
+	struct fnic_tport_s *tport, *next;
+	u32 old_link_down_cnt = iport->fnic->link_down_cnt;
+	struct fnic *fnic = iport->fnic;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Starting FDLS target discovery", iport->fcid);
+
+	list_for_each_entry_safe(tport, next, &iport->tport_list, links) {
+		if ((old_link_down_cnt != iport->fnic->link_down_cnt)
+			|| (iport->state != FNIC_IPORT_STATE_READY)) {
+			break;
+		}
+		/* if we marked the tport as deleted due to GPN_FT
+		 * We should not send ADISC anymore
+		 */
+		if ((tport->state == FDLS_TGT_STATE_OFFLINING) ||
+			(tport->state == FDLS_TGT_STATE_OFFLINE))
+			continue;
+
+		/* For tports which have received RSCN */
+		if (tport->flags & FNIC_FDLS_TPORT_SEND_ADISC) {
+			tport->retry_counter = 0;
+			fdls_set_tport_state(tport, FDLS_TGT_STATE_ADISC);
+			tport->flags &= ~FNIC_FDLS_TPORT_SEND_ADISC;
+			fdls_send_tgt_adisc(iport, tport);
+			continue;
+		}
+		if (fdls_get_tport_state(tport) != FDLS_TGT_STATE_INIT) {
+			/* Not a new port, skip  */
+			continue;
+		}
+		tport->retry_counter = 0;
+		fdls_set_tport_state(tport, FDLS_TGT_STATE_PLOGI);
+		fdls_send_tgt_plogi(iport, tport);
+	}
+	fdls_set_state((&iport->fabric), FDLS_STATE_TGT_DISCOVERY);
+}
+
+/*
+ * Function to restart the IT nexus if we received any out of
+ * sequence PLOGI/PRLI  response from the target.
+ * The memory for the new tport structure is allocated
+ * inside fdls_create_tport and added to the iport's tport list.
+ * This will get freed later during tport_offline/linkdown
+ * or module unload. The new_tport pointer will go out of scope
+ * safely since the memory it is
+ * pointing to it will be freed later
+ */
+static void fdls_target_restart_nexus(struct fnic_tport_s *tport)
+{
+	struct fnic_iport_s *iport = tport->iport;
+	struct fnic_tport_s *new_tport = NULL;
+	uint32_t fcid;
+	uint64_t wwpn;
+	int nexus_restart_count;
+	struct fnic *fnic = iport->fnic;
+	bool retval = true;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "tport fcid: 0x%x state: %d restart_count: %d",
+				 tport->fcid, tport->state, tport->nexus_restart_count);
+
+	fcid = tport->fcid;
+	wwpn = tport->wwpn;
+	nexus_restart_count = tport->nexus_restart_count;
+
+	retval = fdls_delete_tport(iport, tport);
+	if (retval != true) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			     "Error deleting tport: 0x%x", fcid);
+		return;
+	}
+
+	if (nexus_restart_count >= FNIC_TPORT_MAX_NEXUS_RESTART) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "Exceeded nexus restart retries tport: 0x%x",
+			     fcid);
+		return;
+	}
+
+	/*
+	 * Allocate memory for the new tport and add it to
+	 * iport's tport list.
+	 * This memory will be freed during tport_offline/linkdown
+	 * or module unload. The pointer new_tport is safe to go
+	 * out of scope when this function returns, since the memory
+	 * it is pointing to is guaranteed to be freed later
+	 * as mentioned above.
+	 */
+	new_tport = fdls_create_tport(iport, fcid, wwpn);
+	if (!new_tport) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Error creating new tport: 0x%x", fcid);
+		return;
+	}
+
+	new_tport->nexus_restart_count = nexus_restart_count + 1;
+	fdls_send_tgt_plogi(iport, new_tport);
+	fdls_set_tport_state(new_tport, FDLS_TGT_STATE_PLOGI);
+}
+
+struct fnic_tport_s *fnic_find_tport_by_fcid(struct fnic_iport_s *iport,
+									 uint32_t fcid)
+{
+	struct fnic_tport_s *tport, *next;
+
+	list_for_each_entry_safe(tport, next, &(iport->tport_list), links) {
+		if ((tport->fcid == fcid)
+			&& !(tport->flags & FNIC_FDLS_TPORT_TERMINATING))
+			return tport;
+	}
+	return NULL;
+}
+
+static struct fnic_tport_s *fdls_create_tport(struct fnic_iport_s *iport,
+								  uint32_t fcid, uint64_t wwpn)
+{
+	struct fnic_tport_s *tport;
+	struct fnic *fnic = iport->fnic;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "FDLS create tport: fcid: 0x%x wwpn: 0x%llx", fcid, wwpn);
+
+	tport = kzalloc(sizeof(struct fnic_tport_s), GFP_ATOMIC);
+	if (!tport) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Memory allocation failure while creating tport: 0x%x\n",
+			 fcid);
+		return NULL;
+	}
+
+	tport->max_payload_size = FNIC_FCOE_MAX_FRAME_SZ;
+	tport->r_a_tov = FC_DEF_R_A_TOV;
+	tport->e_d_tov = FC_DEF_E_D_TOV;
+	tport->fcid = fcid;
+	tport->wwpn = wwpn;
+	tport->iport = iport;
+
+	FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+				 "Need to setup tport timer callback");
+
+	timer_setup(&tport->retry_timer, fdls_tport_timer_callback, 0);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Added tport 0x%x", tport->fcid);
+	fdls_set_tport_state(tport, FDLS_TGT_STATE_INIT);
+	list_add_tail(&tport->links, &iport->tport_list);
+	atomic_set(&tport->in_flight, 0);
+	return tport;
+}
+
+struct fnic_tport_s *fnic_find_tport_by_wwpn(struct fnic_iport_s *iport,
+									 uint64_t wwpn)
+{
+	struct fnic_tport_s *tport, *next;
+
+	list_for_each_entry_safe(tport, next, &(iport->tport_list), links) {
+		if ((tport->wwpn == wwpn)
+			&& !(tport->flags & FNIC_FDLS_TPORT_TERMINATING))
+			return tport;
+	}
+	return NULL;
+}
+
+static void
+fnic_fdmi_attr_set(void *attr_start, u16 type, u16 len,
+		void *data, u32 *off)
+{
+	u16 size = len + FC_FDMI_ATTR_ENTRY_HEADER_LEN;
+	struct fc_fdmi_attr_entry *fdmi_attr = (struct fc_fdmi_attr_entry *)
+		((u8 *)attr_start + *off);
+
+	put_unaligned_be16(type, &fdmi_attr->type);
+	put_unaligned_be16(size, &fdmi_attr->len);
+	memcpy(fdmi_attr->value, data, len);
+	*off += size;
+}
+
+static void fdls_fdmi_register_hba(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_fdmi_rhba *prhba;
+	struct fc_fdmi_attr_entry *fdmi_attr;
+	uint8_t fcid[3];
+	int err;
+	struct fnic *fnic = iport->fnic;
+	struct vnic_devcmd_fw_info *fw_info = NULL;
+	uint16_t oxid;
+	u32 attr_off_bytes, len;
+	u8 data[64];
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET;
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send FDMI RHBA");
+		return;
+	}
+
+	prhba = (struct fc_std_fdmi_rhba *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*prhba = (struct fc_std_fdmi_rhba) {
+		.fchdr = {
+			.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL,
+			.fh_d_id = {0xFF, 0XFF, 0XFA},
+			.fh_type = FC_TYPE_CT,
+			.fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+			.fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)
+		},
+		.fc_std_ct_hdr = {
+			.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_MGMT,
+			.ct_fs_subtype = FC_FDMI_SUBTYPE,
+			.ct_cmd = cpu_to_be16(FC_FDMI_RHBA)
+		},
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(prhba->fchdr, fcid);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FDMI_RHBA,
+		&iport->active_oxid_fdmi_rhba);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "0x%x: Failed to allocate OXID to send FDMI RHBA",
+		     iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(prhba->fchdr, oxid);
+
+	put_unaligned_be64(iport->wwpn, &prhba->rhba.hbaid.id);
+	put_unaligned_be32(FNIC_FDMI_NUM_PORTS, &prhba->rhba.port.numport);
+	put_unaligned_be64(iport->wwpn, &prhba->rhba.port.port[0].portname);
+	put_unaligned_be32(FNIC_FDMI_NUM_HBA_ATTRS,
+			&prhba->rhba.hba_attrs.numattrs);
+
+	fdmi_attr = prhba->rhba.hba_attrs.attr;
+	attr_off_bytes = 0;
+
+	put_unaligned_be64(iport->wwnn, data);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_NODE_NAME,
+		FNIC_FDMI_NN_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"NN set, off=%d", attr_off_bytes);
+
+	strscpy_pad(data, FNIC_FDMI_MANUFACTURER, FNIC_FDMI_MANU_LEN);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MANUFACTURER,
+		FNIC_FDMI_MANU_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"MFG set <%s>, off=%d", data, attr_off_bytes);
+
+	err = vnic_dev_fw_info(fnic->vdev, &fw_info);
+	if (!err) {
+		strscpy_pad(data, fw_info->hw_serial_number,
+				FNIC_FDMI_SERIAL_LEN);
+		fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_SERIAL_NUMBER,
+			FNIC_FDMI_SERIAL_LEN, data, &attr_off_bytes);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"SERIAL set <%s>, off=%d", data, attr_off_bytes);
+
+	}
+
+	if (fnic->subsys_desc_len >= FNIC_FDMI_MODEL_LEN)
+		fnic->subsys_desc_len = FNIC_FDMI_MODEL_LEN - 1;
+	strscpy_pad(data, fnic->subsys_desc, FNIC_FDMI_MODEL_LEN);
+	data[FNIC_FDMI_MODEL_LEN - 1] = 0;
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MODEL, FNIC_FDMI_MODEL_LEN,
+		data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"MODEL set <%s>, off=%d", data, attr_off_bytes);
+
+	strscpy_pad(data, FNIC_FDMI_MODEL_DESCRIPTION, FNIC_FDMI_MODEL_DES_LEN);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MODEL_DES,
+		FNIC_FDMI_MODEL_DES_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"MODEL_DESC set <%s>, off=%d", data, attr_off_bytes);
+
+	if (!err) {
+		strscpy_pad(data, fw_info->hw_version, FNIC_FDMI_HW_VER_LEN);
+		fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_HARDWARE_VERSION,
+			FNIC_FDMI_HW_VER_LEN, data, &attr_off_bytes);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"HW_VER set <%s>, off=%d", data, attr_off_bytes);
+
+	}
+
+	strscpy_pad(data, DRV_VERSION, FNIC_FDMI_DR_VER_LEN);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_DRIVER_VERSION,
+		FNIC_FDMI_DR_VER_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"DRV_VER set <%s>, off=%d", data, attr_off_bytes);
+
+	strscpy_pad(data, "N/A", FNIC_FDMI_ROM_VER_LEN);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_ROM_VERSION,
+		FNIC_FDMI_ROM_VER_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"ROM_VER set <%s>, off=%d", data, attr_off_bytes);
+
+	if (!err) {
+		strscpy_pad(data, fw_info->fw_version, FNIC_FDMI_FW_VER_LEN);
+		fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_FIRMWARE_VERSION,
+			FNIC_FDMI_FW_VER_LEN, data, &attr_off_bytes);
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"FW_VER set <%s>, off=%d", data, attr_off_bytes);
+	}
+
+	len = sizeof(struct fc_std_fdmi_rhba) + attr_off_bytes;
+	frame_size += len;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send FDMI RHBA with oxid: 0x%x fs: %d", iport->fcid,
+		 oxid, frame_size);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	iport->fabric.fdmi_pending |= FDLS_FDMI_REG_HBA_PENDING;
+}
+
+static void fdls_fdmi_register_pa(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	struct fc_std_fdmi_rpa *prpa;
+	struct fc_fdmi_attr_entry *fdmi_attr;
+	uint8_t fcid[3];
+	struct fnic *fnic = iport->fnic;
+	u32 port_speed_bm;
+	u32 port_speed = vnic_dev_port_speed(fnic->vdev);
+	uint16_t oxid;
+	u32 attr_off_bytes, len;
+	u8 tmp_data[16], data[64];
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET;
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send FDMI RPA");
+		return;
+	}
+
+	prpa = (struct fc_std_fdmi_rpa *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*prpa = (struct fc_std_fdmi_rpa) {
+		.fchdr = {
+			.fh_r_ctl = FC_RCTL_DD_UNSOL_CTL,
+			.fh_d_id = {0xFF, 0xFF, 0xFA},
+			.fh_type = FC_TYPE_CT,
+			.fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+			.fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)
+		},
+		.fc_std_ct_hdr = {
+			.ct_rev = FC_CT_REV, .ct_fs_type = FC_FST_MGMT,
+			.ct_fs_subtype = FC_FDMI_SUBTYPE,
+			.ct_cmd = cpu_to_be16(FC_FDMI_RPA)
+		},
+	};
+
+	hton24(fcid, iport->fcid);
+	FNIC_STD_SET_S_ID(prpa->fchdr, fcid);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FDMI_RPA,
+		&iport->active_oxid_fdmi_rpa);
+
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "0x%x: Failed to allocate OXID to send FDMI RPA",
+			     iport->fcid);
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(prpa->fchdr, oxid);
+
+	put_unaligned_be64(iport->wwpn, &prpa->rpa.port.portname);
+	put_unaligned_be32(FNIC_FDMI_NUM_PORT_ATTRS,
+				&prpa->rpa.hba_attrs.numattrs);
+
+	/* MDS does not support GIGE speed.
+	 * Bit shift standard definitions from scsi_transport_fc.h to
+	 * match FC spec.
+	 */
+	switch (port_speed) {
+	case DCEM_PORTSPEED_10G:
+	case DCEM_PORTSPEED_20G:
+		/* There is no bit for 20G */
+		port_speed_bm = FC_PORTSPEED_10GBIT << PORT_SPEED_BIT_14;
+		break;
+	case DCEM_PORTSPEED_25G:
+		port_speed_bm = FC_PORTSPEED_25GBIT << PORT_SPEED_BIT_8;
+		break;
+	case DCEM_PORTSPEED_40G:
+	case DCEM_PORTSPEED_4x10G:
+		port_speed_bm = FC_PORTSPEED_40GBIT << PORT_SPEED_BIT_9;
+		break;
+	case DCEM_PORTSPEED_100G:
+		port_speed_bm = FC_PORTSPEED_100GBIT << PORT_SPEED_BIT_8;
+		break;
+	default:
+		port_speed_bm = FC_PORTSPEED_1GBIT << PORT_SPEED_BIT_15;
+		break;
+	}
+	attr_off_bytes = 0;
+
+	fdmi_attr = prpa->rpa.hba_attrs.attr;
+
+	put_unaligned_be64(iport->wwnn, data);
+
+	memset(data, 0, FNIC_FDMI_FC4_LEN);
+	data[2] = 1;
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_FC4_TYPES,
+		FNIC_FDMI_FC4_LEN, data, &attr_off_bytes);
+
+	put_unaligned_be32(port_speed_bm, data);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_SUPPORTED_SPEEDS,
+		FNIC_FDMI_SUPP_SPEED_LEN, data, &attr_off_bytes);
+
+	put_unaligned_be32(port_speed_bm, data);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_CURRENT_SPEED,
+		FNIC_FDMI_CUR_SPEED_LEN, data, &attr_off_bytes);
+
+	put_unaligned_be32(FNIC_FDMI_MFS, data);
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_MAX_FRAME_SIZE,
+		FNIC_FDMI_MFS_LEN, data, &attr_off_bytes);
+
+	snprintf(tmp_data, FNIC_FDMI_OS_NAME_LEN - 1, "host%d",
+		 fnic->host->host_no);
+	strscpy_pad(data, tmp_data, FNIC_FDMI_OS_NAME_LEN);
+	data[FNIC_FDMI_OS_NAME_LEN - 1] = 0;
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_OS_NAME,
+		FNIC_FDMI_OS_NAME_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"OS name set <%s>, off=%d", data, attr_off_bytes);
+
+	sprintf(fc_host_system_hostname(fnic->host), "%s", utsname()->nodename);
+	strscpy_pad(data, fc_host_system_hostname(fnic->host),
+					FNIC_FDMI_HN_LEN);
+	data[FNIC_FDMI_HN_LEN - 1] = 0;
+	fnic_fdmi_attr_set(fdmi_attr, FNIC_FDMI_TYPE_HOST_NAME,
+		FNIC_FDMI_HN_LEN, data, &attr_off_bytes);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Host name set <%s>, off=%d", data, attr_off_bytes);
+
+	len = sizeof(struct fc_std_fdmi_rpa) + attr_off_bytes;
+	frame_size += len;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send FDMI RPA with oxid: 0x%x fs: %d", iport->fcid,
+		 oxid, frame_size);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+	iport->fabric.fdmi_pending |= FDLS_FDMI_RPA_PENDING;
+}
+
+void fdls_fabric_timer_callback(struct timer_list *t)
+{
+	struct fnic_fdls_fabric_s *fabric = from_timer(fabric, t, retry_timer);
+	struct fnic_iport_s *iport =
+		container_of(fabric, struct fnic_iport_s, fabric);
+	struct fnic *fnic = iport->fnic;
+	unsigned long flags;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "tp: %d fab state: %d fab retry counter: %d max_flogi_retries: %d",
+		 iport->fabric.timer_pending, iport->fabric.state,
+		 iport->fabric.retry_counter, iport->max_flogi_retries);
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+
+	if (!iport->fabric.timer_pending) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+
+	if (iport->fabric.del_timer_inprogress) {
+		iport->fabric.del_timer_inprogress = 0;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "fabric_del_timer inprogress(%d). Skip timer cb",
+					 iport->fabric.del_timer_inprogress);
+		return;
+	}
+
+	iport->fabric.timer_pending = 0;
+
+	/* The fabric state indicates which frames have time out, and we retry */
+	switch (iport->fabric.state) {
+	case FDLS_STATE_FABRIC_FLOGI:
+		/* Flogi received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < iport->max_flogi_retries)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_fabric_flogi(iport);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) {
+			/* Flogi has time out 2*ed_tov send abts */
+			fdls_send_fabric_abts(iport);
+		} else {
+			/* ABTS has timed out
+			 * Mark the OXID to be freed after 2 * r_a_tov and retry the req
+			 */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			if (iport->fabric.retry_counter < iport->max_flogi_retries) {
+				iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED;
+				fdls_send_fabric_flogi(iport);
+			} else
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Exceeded max FLOGI retries");
+		}
+		break;
+	case FDLS_STATE_FABRIC_PLOGI:
+		/* Plogi received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < iport->max_plogi_retries)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_fabric_plogi(iport);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) {
+		/* Plogi has timed out 2*ed_tov send abts */
+			fdls_send_fabric_abts(iport);
+		} else {
+			/* ABTS has timed out
+			 * Mark the OXID to be freed after 2 * r_a_tov and retry the req
+			 */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			if (iport->fabric.retry_counter < iport->max_plogi_retries) {
+				iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED;
+				fdls_send_fabric_plogi(iport);
+			} else
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Exceeded max PLOGI retries");
+		}
+		break;
+	case FDLS_STATE_RPN_ID:
+		/* Rpn_id received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_rpn_id(iport);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED))
+			/* RPN has timed out. Send abts */
+			fdls_send_fabric_abts(iport);
+		else {
+			/* ABTS has timed out */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			fnic_fdls_start_plogi(iport);	/* go back to fabric Plogi */
+		}
+		break;
+	case FDLS_STATE_SCR:
+		/* scr received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_scr(iport);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED))
+			/* scr has timed out. Send abts */
+			fdls_send_fabric_abts(iport);
+		else {
+			/* ABTS has timed out */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "ABTS timed out. Starting PLOGI: %p", iport);
+			fnic_fdls_start_plogi(iport);
+		}
+		break;
+	case FDLS_STATE_REGISTER_FC4_TYPES:
+		/* scr received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_register_fc4_types(iport);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) {
+			/* RFT_ID timed out send abts */
+			fdls_send_fabric_abts(iport);
+		} else {
+			/* ABTS has timed out */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "ABTS timed out. Starting PLOGI: %p", iport);
+			fnic_fdls_start_plogi(iport);	/* go back to fabric Plogi */
+		}
+		break;
+	case FDLS_STATE_REGISTER_FC4_FEATURES:
+		/* scr received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_register_fc4_features(iport);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED))
+			/* SCR has timed out. Send abts */
+			fdls_send_fabric_abts(iport);
+		else {
+			/* ABTS has timed out */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "ABTS timed out. Starting PLOGI %p", iport);
+			fnic_fdls_start_plogi(iport);	/* go back to fabric Plogi */
+		}
+		break;
+	case FDLS_STATE_RSCN_GPN_FT:
+	case FDLS_STATE_SEND_GPNFT:
+	case FDLS_STATE_GPN_FT:
+		/* GPN_FT received a LS_RJT with busy we retry from here */
+		if ((iport->fabric.flags & FNIC_FDLS_RETRY_FRAME)
+			&& (iport->fabric.retry_counter < FDLS_RETRY_COUNT)) {
+			iport->fabric.flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_gpn_ft(iport, iport->fabric.state);
+		} else if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) {
+			/* gpn_ft has timed out. Send abts */
+			fdls_send_fabric_abts(iport);
+		} else {
+			/* ABTS has timed out */
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+			if (iport->fabric.retry_counter < FDLS_RETRY_COUNT) {
+				fdls_send_gpn_ft(iport, iport->fabric.state);
+			} else {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "ABTS timeout for fabric GPN_FT. Check name server: %p",
+					 iport);
+			}
+		}
+		break;
+	default:
+		break;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+}
+
+void fdls_fdmi_timer_callback(struct timer_list *t)
+{
+	struct fnic_fdls_fabric_s *fabric = from_timer(fabric, t, fdmi_timer);
+	struct fnic_iport_s *iport =
+		container_of(fabric, struct fnic_iport_s, fabric);
+	struct fnic *fnic = iport->fnic;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+
+	if (!iport->fabric.fdmi_pending) {
+		/* timer expired after fdmi responses received. */
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+
+	/* if not abort pending, send an abort */
+	if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) {
+		fdls_send_fdmi_abts(iport);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+
+	/* ABTS pending for an active fdmi request that is pending.
+	 * That means FDMI ABTS timed out
+	 * Schedule to free the OXID after 2*r_a_tov and proceed
+	 */
+	if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) {
+		fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_plogi);
+	} else {
+		if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rhba);
+		if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING)
+			fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rpa);
+	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+
+	iport->fabric.fdmi_pending = 0;
+	/* If max retries not exhaused, start over from fdmi plogi */
+	if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) {
+		iport->fabric.fdmi_retry++;
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "retry fdmi timer %d", iport->fabric.fdmi_retry);
+		fdls_send_fdmi_plogi(iport);
+	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+}
+
+static void fdls_send_delete_tport_msg(struct fnic_tport_s *tport)
+{
+	struct fnic_iport_s *iport = (struct fnic_iport_s *) tport->iport;
+	struct fnic *fnic = iport->fnic;
+	struct fnic_tport_event_s *tport_del_evt;
+
+	tport_del_evt = kzalloc(sizeof(struct fnic_tport_event_s), GFP_ATOMIC);
+	if (!tport_del_evt) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Failed to allocate memory for tport event fcid: 0x%x",
+			 tport->fcid);
+		return;
+	}
+	tport_del_evt->event = TGT_EV_TPORT_DELETE;
+	tport_del_evt->arg1 = (void *) tport;
+	list_add_tail(&tport_del_evt->links, &fnic->tport_event_list);
+	queue_work(fnic_event_queue, &fnic->tport_work);
+}
+
+static void fdls_tport_timer_callback(struct timer_list *t)
+{
+	struct fnic_tport_s *tport = from_timer(tport, t, retry_timer);
+	struct fnic_iport_s *iport = (struct fnic_iport_s *) tport->iport;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	if (!tport->timer_pending) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+
+	if (tport->del_timer_inprogress) {
+		tport->del_timer_inprogress = 0;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "tport_del_timer inprogress. Skip timer cb tport fcid: 0x%x\n",
+			 tport->fcid);
+		return;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "tport fcid: 0x%x timer pending: %d state: %d retry counter: %d",
+		 tport->fcid, tport->timer_pending, tport->state,
+		 tport->retry_counter);
+
+	tport->timer_pending = 0;
+	oxid = tport->active_oxid;
+
+	/* We retry plogi/prli/adisc frames depending on the tport state */
+	switch (tport->state) {
+	case FDLS_TGT_STATE_PLOGI:
+		/* PLOGI frame received a LS_RJT with busy, we retry from here */
+		if ((tport->flags & FNIC_FDLS_RETRY_FRAME)
+			&& (tport->retry_counter < iport->max_plogi_retries)) {
+			tport->flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_tgt_plogi(iport, tport);
+		} else if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) {
+			/* Plogi frame has timed out, send abts */
+			fdls_send_tport_abts(iport, tport);
+		} else if (tport->retry_counter < iport->max_plogi_retries) {
+			/*
+			 * ABTS has timed out
+			 */
+			fdls_schedule_oxid_free(iport, &tport->active_oxid);
+			fdls_send_tgt_plogi(iport, tport);
+		} else {
+			/* exceeded plogi retry count */
+			fdls_schedule_oxid_free(iport, &tport->active_oxid);
+			fdls_send_delete_tport_msg(tport);
+		}
+		break;
+	case FDLS_TGT_STATE_PRLI:
+		/* PRLI received a LS_RJT with busy , hence we retry from here */
+		if ((tport->flags & FNIC_FDLS_RETRY_FRAME)
+			&& (tport->retry_counter < FDLS_RETRY_COUNT)) {
+			tport->flags &= ~FNIC_FDLS_RETRY_FRAME;
+			fdls_send_tgt_prli(iport, tport);
+		} else if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) {
+			/* PRLI has time out, send abts */
+			fdls_send_tport_abts(iport, tport);
+		} else {
+			/* ABTS has timed out for prli, we go back to PLOGI */
+			fdls_schedule_oxid_free(iport, &tport->active_oxid);
+			fdls_send_tgt_plogi(iport, tport);
+			fdls_set_tport_state(tport, FDLS_TGT_STATE_PLOGI);
+		}
+		break;
+	case FDLS_TGT_STATE_ADISC:
+		/* ADISC timed out send an ABTS */
+		if (!(tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) {
+			fdls_send_tport_abts(iport, tport);
+		} else if ((tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)
+				   && (tport->retry_counter < FDLS_RETRY_COUNT)) {
+			/*
+			 * ABTS has timed out
+			 */
+			fdls_schedule_oxid_free(iport, &tport->active_oxid);
+			fdls_send_tgt_adisc(iport, tport);
+		} else {
+			/* exceeded retry count */
+			fdls_schedule_oxid_free(iport, &tport->active_oxid);
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "ADISC not responding. Deleting target port: 0x%x",
+					 tport->fcid);
+			fdls_send_delete_tport_msg(tport);
+		}
+		break;
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "oxid: 0x%x Unknown tport state: 0x%x", oxid, tport->state);
+		break;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+}
+
+static void fnic_fdls_start_flogi(struct fnic_iport_s *iport)
+{
+	iport->fabric.retry_counter = 0;
+	fdls_send_fabric_flogi(iport);
+	fdls_set_state((&iport->fabric), FDLS_STATE_FABRIC_FLOGI);
+	iport->fabric.flags = 0;
+}
+
+static void fnic_fdls_start_plogi(struct fnic_iport_s *iport)
+{
+	iport->fabric.retry_counter = 0;
+	fdls_send_fabric_plogi(iport);
+	fdls_set_state((&iport->fabric), FDLS_STATE_FABRIC_PLOGI);
+	iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED;
+
+	if ((fnic_fdmi_support == 1) && (!(iport->flags & FNIC_FDMI_ACTIVE))) {
+		/* we can do FDMI at the same time */
+		iport->fabric.fdmi_retry = 0;
+		timer_setup(&iport->fabric.fdmi_timer, fdls_fdmi_timer_callback,
+					0);
+		fdls_send_fdmi_plogi(iport);
+		iport->flags |= FNIC_FDMI_ACTIVE;
+	}
+}
+static void
+fdls_process_tgt_adisc_rsp(struct fnic_iport_s *iport,
+			   struct fc_frame_header *fchdr)
+{
+	uint32_t tgt_fcid;
+	struct fnic_tport_s *tport;
+	uint8_t *fcid;
+	uint64_t frame_wwnn;
+	uint64_t frame_wwpn;
+	uint16_t oxid;
+	struct fc_std_els_adisc *adisc_rsp = (struct fc_std_els_adisc *)fchdr;
+	struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr;
+	struct fnic *fnic = iport->fnic;
+
+	fcid = FNIC_STD_GET_S_ID(fchdr);
+	tgt_fcid = ntoh24(fcid);
+	tport = fnic_find_tport_by_fcid(iport, tgt_fcid);
+
+	if (!tport) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Tgt ADISC response tport not found: 0x%x", tgt_fcid);
+		return;
+	}
+	if ((iport->state != FNIC_IPORT_STATE_READY)
+		|| (tport->state != FDLS_TGT_STATE_ADISC)
+		|| (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Dropping this ADISC response");
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "iport state: %d tport state: %d Is abort issued on PRLI? %d",
+			 iport->state, tport->state,
+			 (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED));
+		return;
+	}
+	if (FNIC_STD_GET_OX_ID(fchdr) != tport->active_oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Dropping frame from target: 0x%x",
+			 tgt_fcid);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Reason: Stale ADISC/Aborted ADISC/OOO frame delivery");
+		return;
+	}
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	fdls_free_oxid(iport, oxid, &tport->active_oxid);
+
+	switch (adisc_rsp->els.adisc_cmd) {
+	case ELS_LS_ACC:
+		atomic64_inc(&iport->iport_stats.tport_adisc_ls_accepts);
+		if (tport->timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "tport 0x%p Canceling fabric disc timer\n",
+						 tport);
+			fnic_del_tport_timer_sync(fnic, tport);
+		}
+		tport->timer_pending = 0;
+		tport->retry_counter = 0;
+		frame_wwnn = get_unaligned_be64(&adisc_rsp->els.adisc_wwnn);
+		frame_wwpn = get_unaligned_be64(&adisc_rsp->els.adisc_wwpn);
+		if ((frame_wwnn == tport->wwnn) && (frame_wwpn == tport->wwpn)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "ADISC accepted from target: 0x%x. Target logged in",
+				 tgt_fcid);
+			fdls_set_tport_state(tport, FDLS_TGT_STATE_READY);
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Error mismatch frame: ADISC");
+		}
+		break;
+
+	case ELS_LS_RJT:
+		atomic64_inc(&iport->iport_stats.tport_adisc_ls_rejects);
+		if (((els_rjt->rej.er_reason == ELS_RJT_BUSY)
+		     || (els_rjt->rej.er_reason == ELS_RJT_UNAB))
+			&& (tport->retry_counter < FDLS_RETRY_COUNT)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "ADISC ret ELS_LS_RJT BUSY. Retry from timer routine: 0x%x",
+				 tgt_fcid);
+
+			/* Retry ADISC again from the timer routine. */
+			tport->flags |= FNIC_FDLS_RETRY_FRAME;
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "ADISC returned ELS_LS_RJT from target: 0x%x",
+						 tgt_fcid);
+			fdls_delete_tport(iport, tport);
+		}
+		break;
+	}
+}
+static void
+fdls_process_tgt_plogi_rsp(struct fnic_iport_s *iport,
+			   struct fc_frame_header *fchdr)
+{
+	uint32_t tgt_fcid;
+	struct fnic_tport_s *tport;
+	uint8_t *fcid;
+	uint16_t oxid;
+	struct fc_std_flogi *plogi_rsp = (struct fc_std_flogi *)fchdr;
+	struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr;
+	uint16_t max_payload_size;
+	struct fnic *fnic = iport->fnic;
+
+	fcid = FNIC_STD_GET_S_ID(fchdr);
+	tgt_fcid = ntoh24(fcid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FDLS processing target PLOGI response: tgt_fcid: 0x%x",
+				 tgt_fcid);
+
+	tport = fnic_find_tport_by_fcid(iport, tgt_fcid);
+	if (!tport) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "tport not found: 0x%x", tgt_fcid);
+		return;
+	}
+	if ((iport->state != FNIC_IPORT_STATE_READY)
+		|| (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Dropping frame! iport state: %d tport state: %d",
+					 iport->state, tport->state);
+		return;
+	}
+
+	if (tport->state != FDLS_TGT_STATE_PLOGI) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "PLOGI rsp recvd in wrong state. Drop the frame and restart nexus");
+		fdls_target_restart_nexus(tport);
+		return;
+	}
+
+	if (FNIC_STD_GET_OX_ID(fchdr) != tport->active_oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "PLOGI response from target: 0x%x. Dropping frame",
+			 tgt_fcid);
+		return;
+	}
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	fdls_free_oxid(iport, oxid, &tport->active_oxid);
+
+	switch (plogi_rsp->els.fl_cmd) {
+	case ELS_LS_ACC:
+		atomic64_inc(&iport->iport_stats.tport_plogi_ls_accepts);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PLOGI accepted by target: 0x%x", tgt_fcid);
+		break;
+
+	case ELS_LS_RJT:
+		atomic64_inc(&iport->iport_stats.tport_plogi_ls_rejects);
+		if (((els_rjt->rej.er_reason == ELS_RJT_BUSY)
+		     || (els_rjt->rej.er_reason == ELS_RJT_UNAB))
+			&& (tport->retry_counter < iport->max_plogi_retries)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "PLOGI ret ELS_LS_RJT BUSY. Retry from timer routine: 0x%x",
+				 tgt_fcid);
+			/* Retry plogi again from the timer routine. */
+			tport->flags |= FNIC_FDLS_RETRY_FRAME;
+			return;
+		}
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PLOGI returned ELS_LS_RJT from target: 0x%x",
+					 tgt_fcid);
+		fdls_delete_tport(iport, tport);
+		return;
+
+	default:
+		atomic64_inc(&iport->iport_stats.tport_plogi_misc_rejects);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PLOGI not accepted from target fcid: 0x%x",
+					 tgt_fcid);
+		return;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Found the PLOGI target: 0x%x and state: %d",
+				 (unsigned int) tgt_fcid, tport->state);
+
+	if (tport->timer_pending) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "tport fcid 0x%x: Canceling disc timer\n",
+					 tport->fcid);
+		fnic_del_tport_timer_sync(fnic, tport);
+	}
+
+	tport->timer_pending = 0;
+	tport->wwpn = get_unaligned_be64(&FNIC_LOGI_PORT_NAME(plogi_rsp->els));
+	tport->wwnn = get_unaligned_be64(&FNIC_LOGI_NODE_NAME(plogi_rsp->els));
+
+	/* Learn the Service Params */
+
+	/* Max frame size - choose the lowest */
+	max_payload_size = fnic_fc_plogi_rsp_rdf(iport, plogi_rsp);
+	tport->max_payload_size =
+		min(max_payload_size, iport->max_payload_size);
+
+	if (tport->max_payload_size < FNIC_MIN_DATA_FIELD_SIZE) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "MFS: tport max frame size below spec bounds: %d",
+			 tport->max_payload_size);
+		tport->max_payload_size = FNIC_MIN_DATA_FIELD_SIZE;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "MAX frame size: %u iport max_payload_size: %d tport mfs: %d",
+		 max_payload_size, iport->max_payload_size,
+		 tport->max_payload_size);
+
+	tport->max_concur_seqs = FNIC_FC_PLOGI_RSP_CONCUR_SEQ(plogi_rsp);
+
+	tport->retry_counter = 0;
+	fdls_set_tport_state(tport, FDLS_TGT_STATE_PRLI);
+	fdls_send_tgt_prli(iport, tport);
+}
+static void
+fdls_process_tgt_prli_rsp(struct fnic_iport_s *iport,
+			  struct fc_frame_header *fchdr)
+{
+	uint32_t tgt_fcid;
+	struct fnic_tport_s *tport;
+	uint8_t *fcid;
+	uint16_t oxid;
+	struct fc_std_els_prli *prli_rsp = (struct fc_std_els_prli *)fchdr;
+	struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr;
+	struct fnic_tport_event_s *tport_add_evt;
+	struct fnic *fnic = iport->fnic;
+	bool mismatched_tgt = false;
+
+	fcid = FNIC_STD_GET_S_ID(fchdr);
+	tgt_fcid = ntoh24(fcid);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FDLS process tgt PRLI response: 0x%x", tgt_fcid);
+
+	tport = fnic_find_tport_by_fcid(iport, tgt_fcid);
+	if (!tport) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "tport not found: 0x%x", tgt_fcid);
+		/* Handle or just drop? */
+		return;
+	}
+
+	if ((iport->state != FNIC_IPORT_STATE_READY)
+		|| (tport->flags & FNIC_FDLS_TGT_ABORT_ISSUED)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Dropping frame! iport st: %d tport st: %d tport fcid: 0x%x",
+			 iport->state, tport->state, tport->fcid);
+		return;
+	}
+
+	if (tport->state != FDLS_TGT_STATE_PRLI) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "PRLI rsp recvd in wrong state. Drop frame. Restarting nexus");
+		fdls_target_restart_nexus(tport);
+		return;
+	}
+
+	if (FNIC_STD_GET_OX_ID(fchdr) != tport->active_oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Dropping PRLI response from target: 0x%x ",
+			 tgt_fcid);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Reason: Stale PRLI response/Aborted PDISC/OOO frame delivery");
+		return;
+	}
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	fdls_free_oxid(iport, oxid, &tport->active_oxid);
+
+	switch (prli_rsp->els_prli.prli_cmd) {
+	case ELS_LS_ACC:
+		atomic64_inc(&iport->iport_stats.tport_prli_ls_accepts);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PRLI accepted from target: 0x%x", tgt_fcid);
+
+		if (prli_rsp->sp.spp_type != FC_FC4_TYPE_SCSI) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "mismatched target zoned with FC SCSI initiator: 0x%x",
+				 tgt_fcid);
+			mismatched_tgt = true;
+		}
+		if (mismatched_tgt) {
+			fdls_tgt_logout(iport, tport);
+			fdls_delete_tport(iport, tport);
+			return;
+		}
+		break;
+	case ELS_LS_RJT:
+		atomic64_inc(&iport->iport_stats.tport_prli_ls_rejects);
+		if (((els_rjt->rej.er_reason == ELS_RJT_BUSY)
+		     || (els_rjt->rej.er_reason == ELS_RJT_UNAB))
+			&& (tport->retry_counter < FDLS_RETRY_COUNT)) {
+
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "PRLI ret ELS_LS_RJT BUSY. Retry from timer routine: 0x%x",
+				 tgt_fcid);
+
+			/*Retry Plogi again from the timer routine. */
+			tport->flags |= FNIC_FDLS_RETRY_FRAME;
+			return;
+		}
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PRLI returned ELS_LS_RJT from target: 0x%x",
+					 tgt_fcid);
+
+		fdls_tgt_logout(iport, tport);
+		fdls_delete_tport(iport, tport);
+		return;
+	default:
+		atomic64_inc(&iport->iport_stats.tport_prli_misc_rejects);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PRLI not accepted from target: 0x%x", tgt_fcid);
+		return;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Found the PRLI target: 0x%x and state: %d",
+				 (unsigned int) tgt_fcid, tport->state);
+
+	if (tport->timer_pending) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "tport fcid 0x%x: Canceling disc timer\n",
+					 tport->fcid);
+		fnic_del_tport_timer_sync(fnic, tport);
+	}
+	tport->timer_pending = 0;
+
+	/* Learn Service Params */
+	tport->fcp_csp = be32_to_cpu(prli_rsp->sp.spp_params);
+	tport->retry_counter = 0;
+
+	if (tport->fcp_csp & FCP_SPPF_RETRY)
+		tport->tgt_flags |= FNIC_FC_RP_FLAGS_RETRY;
+
+	/* Check if the device plays Target Mode Function */
+	if (!(tport->fcp_csp & FCP_PRLI_FUNC_TARGET)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Remote port(0x%x): no target support. Deleting it\n",
+			 tgt_fcid);
+		fdls_tgt_logout(iport, tport);
+		fdls_delete_tport(iport, tport);
+		return;
+	}
+
+	fdls_set_tport_state(tport, FDLS_TGT_STATE_READY);
+
+	/* Inform the driver about new target added */
+	tport_add_evt = kzalloc(sizeof(struct fnic_tport_event_s), GFP_ATOMIC);
+	if (!tport_add_evt) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "tport event memory allocation failure: 0x%0x\n",
+				 tport->fcid);
+		return;
+	}
+	tport_add_evt->event = TGT_EV_RPORT_ADD;
+	tport_add_evt->arg1 = (void *) tport;
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "iport fcid: 0x%x add tport event fcid: 0x%x\n",
+			 tport->fcid, iport->fcid);
+	list_add_tail(&tport_add_evt->links, &fnic->tport_event_list);
+	queue_work(fnic_event_queue, &fnic->tport_work);
+}
+
+
+static void
+fdls_process_rff_id_rsp(struct fnic_iport_s *iport,
+			struct fc_frame_header *fchdr)
+{
+	struct fnic *fnic = iport->fnic;
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fc_std_rff_id *rff_rsp = (struct fc_std_rff_id *) fchdr;
+	uint16_t rsp;
+	uint8_t reason_code;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	if (fdls_get_state(fdls) != FDLS_STATE_REGISTER_FC4_FEATURES) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RFF_ID resp recvd in state(%d). Dropping.",
+					 fdls_get_state(fdls));
+		return;
+	}
+
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+		return;
+	}
+
+	rsp = FNIC_STD_GET_FC_CT_CMD((&rff_rsp->fc_std_ct_hdr));
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS process RFF ID response: 0x%04x", iport->fcid,
+				 (uint32_t) rsp);
+
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (rsp) {
+	case FC_FS_ACC:
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Canceling fabric disc timer %p\n", iport);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		fdls->retry_counter = 0;
+		fdls_set_state((&iport->fabric), FDLS_STATE_SCR);
+		fdls_send_scr(iport);
+		break;
+	case FC_FS_RJT:
+		reason_code = rff_rsp->fc_std_ct_hdr.ct_reason;
+		if (((reason_code == FC_FS_RJT_BSY)
+			|| (reason_code == FC_FS_RJT_UNABL))
+			&& (fdls->retry_counter < FDLS_RETRY_COUNT)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RFF_ID ret ELS_LS_RJT BUSY. Retry from timer routine %p",
+					 iport);
+
+			/* Retry again from the timer routine */
+			fdls->flags |= FNIC_FDLS_RETRY_FRAME;
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "RFF_ID returned ELS_LS_RJT. Halting discovery %p",
+			 iport);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Canceling fabric disc timer %p\n", iport);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			fdls->timer_pending = 0;
+			fdls->retry_counter = 0;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void
+fdls_process_rft_id_rsp(struct fnic_iport_s *iport,
+			struct fc_frame_header *fchdr)
+{
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fc_std_rft_id *rft_rsp = (struct fc_std_rft_id *) fchdr;
+	uint16_t rsp;
+	uint8_t reason_code;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	if (fdls_get_state(fdls) != FDLS_STATE_REGISTER_FC4_TYPES) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RFT_ID resp recvd in state(%d). Dropping.",
+					 fdls_get_state(fdls));
+		return;
+	}
+
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+		return;
+	}
+
+
+	rsp = FNIC_STD_GET_FC_CT_CMD((&rft_rsp->fc_std_ct_hdr));
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS process RFT ID response: 0x%04x", iport->fcid,
+				 (uint32_t) rsp);
+
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (rsp) {
+	case FC_FS_ACC:
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Canceling fabric disc timer %p\n", iport);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		fdls->retry_counter = 0;
+		fdls_send_register_fc4_features(iport);
+		fdls_set_state((&iport->fabric), FDLS_STATE_REGISTER_FC4_FEATURES);
+		break;
+	case FC_FS_RJT:
+		reason_code = rft_rsp->fc_std_ct_hdr.ct_reason;
+		if (((reason_code == FC_FS_RJT_BSY)
+			|| (reason_code == FC_FS_RJT_UNABL))
+			&& (fdls->retry_counter < FDLS_RETRY_COUNT)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: RFT_ID ret ELS_LS_RJT BUSY. Retry from timer routine",
+				 iport->fcid);
+
+			/* Retry again from the timer routine */
+			fdls->flags |= FNIC_FDLS_RETRY_FRAME;
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: RFT_ID REJ. Halting discovery reason %d expl %d",
+				 iport->fcid, reason_code,
+			 rft_rsp->fc_std_ct_hdr.ct_explan);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Canceling fabric disc timer %p\n", iport);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			fdls->timer_pending = 0;
+			fdls->retry_counter = 0;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void
+fdls_process_rpn_id_rsp(struct fnic_iport_s *iport,
+			struct fc_frame_header *fchdr)
+{
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fc_std_rpn_id *rpn_rsp = (struct fc_std_rpn_id *) fchdr;
+	uint16_t rsp;
+	uint8_t reason_code;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	if (fdls_get_state(fdls) != FDLS_STATE_RPN_ID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RPN_ID resp recvd in state(%d). Dropping.",
+					 fdls_get_state(fdls));
+		return;
+	}
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+		return;
+	}
+
+	rsp = FNIC_STD_GET_FC_CT_CMD((&rpn_rsp->fc_std_ct_hdr));
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS process RPN ID response: 0x%04x", iport->fcid,
+				 (uint32_t) rsp);
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (rsp) {
+	case FC_FS_ACC:
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Canceling fabric disc timer %p\n", iport);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		fdls->retry_counter = 0;
+		fdls_send_register_fc4_types(iport);
+		fdls_set_state((&iport->fabric), FDLS_STATE_REGISTER_FC4_TYPES);
+		break;
+	case FC_FS_RJT:
+		reason_code = rpn_rsp->fc_std_ct_hdr.ct_reason;
+		if (((reason_code == FC_FS_RJT_BSY)
+			|| (reason_code == FC_FS_RJT_UNABL))
+			&& (fdls->retry_counter < FDLS_RETRY_COUNT)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RPN_ID returned REJ BUSY. Retry from timer routine %p",
+					 iport);
+
+			/* Retry again from the timer routine */
+			fdls->flags |= FNIC_FDLS_RETRY_FRAME;
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "RPN_ID ELS_LS_RJT. Halting discovery %p", iport);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Canceling fabric disc timer %p\n", iport);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			fdls->timer_pending = 0;
+			fdls->retry_counter = 0;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void
+fdls_process_scr_rsp(struct fnic_iport_s *iport,
+		     struct fc_frame_header *fchdr)
+{
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fc_std_scr *scr_rsp = (struct fc_std_scr *) fchdr;
+	struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *) fchdr;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FDLS process SCR response: 0x%04x",
+		 (uint32_t) scr_rsp->scr.scr_cmd);
+
+	if (fdls_get_state(fdls) != FDLS_STATE_SCR) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "SCR resp recvd in state(%d). Dropping.",
+					 fdls_get_state(fdls));
+		return;
+	}
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+	}
+
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (scr_rsp->scr.scr_cmd) {
+	case ELS_LS_ACC:
+		atomic64_inc(&iport->iport_stats.fabric_scr_ls_accepts);
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Canceling fabric disc timer %p\n", iport);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		iport->fabric.retry_counter = 0;
+		fdls_send_gpn_ft(iport, FDLS_STATE_GPN_FT);
+		break;
+
+	case ELS_LS_RJT:
+		atomic64_inc(&iport->iport_stats.fabric_scr_ls_rejects);
+		if (((els_rjt->rej.er_reason == ELS_RJT_BUSY)
+	     || (els_rjt->rej.er_reason == ELS_RJT_UNAB))
+			&& (fdls->retry_counter < FDLS_RETRY_COUNT)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "SCR ELS_LS_RJT BUSY. Retry from timer routine %p",
+						 iport);
+			/* Retry again from the timer routine */
+			fdls->flags |= FNIC_FDLS_RETRY_FRAME;
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "SCR returned ELS_LS_RJT. Halting discovery %p",
+						 iport);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					     "Canceling fabric disc timer %p\n",
+					     iport);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			fdls->timer_pending = 0;
+			fdls->retry_counter = 0;
+		}
+		break;
+
+	default:
+		atomic64_inc(&iport->iport_stats.fabric_scr_misc_rejects);
+		break;
+	}
+}
+
+static void
+fdls_process_gpn_ft_tgt_list(struct fnic_iport_s *iport,
+			     struct fc_frame_header *fchdr, int len)
+{
+	struct fc_gpn_ft_rsp_iu *gpn_ft_tgt;
+	struct fnic_tport_s *tport, *next;
+	uint32_t fcid;
+	uint64_t wwpn;
+	int rem_len = len;
+	u32 old_link_down_cnt = iport->fnic->link_down_cnt;
+	struct fnic *fnic = iport->fnic;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS process GPN_FT tgt list", iport->fcid);
+
+	gpn_ft_tgt =
+	    (struct fc_gpn_ft_rsp_iu *)((uint8_t *) fchdr +
+					sizeof(struct fc_frame_header)
+					+ sizeof(struct fc_ct_hdr));
+	len -= sizeof(struct fc_frame_header) + sizeof(struct fc_ct_hdr);
+
+	while (rem_len > 0) {
+
+		fcid = ntoh24(gpn_ft_tgt->fcid);
+		wwpn = be64_to_cpu(gpn_ft_tgt->wwpn);
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "tport: 0x%x: ctrl:0x%x", fcid, gpn_ft_tgt->ctrl);
+
+		if (fcid == iport->fcid) {
+			if (gpn_ft_tgt->ctrl & FC_NS_FID_LAST)
+				break;
+			gpn_ft_tgt++;
+			rem_len -= sizeof(struct fc_gpn_ft_rsp_iu);
+			continue;
+		}
+
+		tport = fnic_find_tport_by_wwpn(iport, wwpn);
+		if (!tport) {
+			/*
+			 * New port registered with the switch or first time query
+			 */
+			tport = fdls_create_tport(iport, fcid, wwpn);
+			if (!tport)
+				return;
+		}
+		/*
+		 * check if this was an existing tport with same fcid
+		 * but whose wwpn has changed now ,then remove it and
+		 * create a new one
+		 */
+		if (tport->fcid != fcid) {
+			fdls_delete_tport(iport, tport);
+			tport = fdls_create_tport(iport, fcid, wwpn);
+			if (!tport)
+				return;
+		}
+
+		/*
+		 * If this GPN_FT rsp is after RSCN then mark the tports which
+		 * matches with the new GPN_FT list, if some tport is not
+		 * found in GPN_FT we went to delete that tport later.
+		 */
+		if (fdls_get_state((&iport->fabric)) == FDLS_STATE_RSCN_GPN_FT)
+			tport->flags |= FNIC_FDLS_TPORT_IN_GPN_FT_LIST;
+
+		if (gpn_ft_tgt->ctrl & FC_NS_FID_LAST)
+			break;
+
+		gpn_ft_tgt++;
+		rem_len -= sizeof(struct fc_gpn_ft_rsp_iu);
+	}
+	if (rem_len <= 0) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "GPN_FT response: malformed/corrupt frame rxlen: %d remlen: %d",
+			 len, rem_len);
+}
+
+	/*remove those ports which was not listed in GPN_FT */
+	if (fdls_get_state((&iport->fabric)) == FDLS_STATE_RSCN_GPN_FT) {
+		list_for_each_entry_safe(tport, next, &iport->tport_list, links) {
+
+			if (!(tport->flags & FNIC_FDLS_TPORT_IN_GPN_FT_LIST)) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Remove port: 0x%x not found in GPN_FT list",
+					 tport->fcid);
+				fdls_delete_tport(iport, tport);
+			} else {
+				tport->flags &= ~FNIC_FDLS_TPORT_IN_GPN_FT_LIST;
+			}
+			if ((old_link_down_cnt != iport->fnic->link_down_cnt)
+				|| (iport->state != FNIC_IPORT_STATE_READY)) {
+				return;
+			}
+		}
+	}
+}
+
+static void
+fdls_process_gpn_ft_rsp(struct fnic_iport_s *iport,
+			struct fc_frame_header *fchdr, int len)
+{
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fc_std_gpn_ft *gpn_ft_rsp = (struct fc_std_gpn_ft *) fchdr;
+	uint16_t rsp;
+	uint8_t reason_code;
+	int count = 0;
+	struct fnic_tport_s *tport, *next;
+	u32 old_link_down_cnt = iport->fnic->link_down_cnt;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FDLS process GPN_FT response: iport state: %d len: %d",
+				 iport->state, len);
+
+	/*
+	 * GPNFT response :-
+	 *  FDLS_STATE_GPN_FT      : GPNFT send after SCR state
+	 *  during fabric discovery(FNIC_IPORT_STATE_FABRIC_DISC)
+	 *  FDLS_STATE_RSCN_GPN_FT : GPNFT send in response to RSCN
+	 *  FDLS_STATE_SEND_GPNFT  : GPNFT send after deleting a Target,
+	 *  e.g. after receiving Target LOGO
+	 *  FDLS_STATE_TGT_DISCOVERY :Target discovery is currently in progress
+	 *  from previous GPNFT response,a new GPNFT response has come.
+	 */
+	if (!(((iport->state == FNIC_IPORT_STATE_FABRIC_DISC)
+		   && (fdls_get_state(fdls) == FDLS_STATE_GPN_FT))
+		  || ((iport->state == FNIC_IPORT_STATE_READY)
+			  && ((fdls_get_state(fdls) == FDLS_STATE_RSCN_GPN_FT)
+				  || (fdls_get_state(fdls) == FDLS_STATE_SEND_GPNFT)
+				  || (fdls_get_state(fdls) == FDLS_STATE_TGT_DISCOVERY))))) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "GPNFT resp recvd in fab state(%d) iport_state(%d). Dropping.",
+			 fdls_get_state(fdls), iport->state);
+		return;
+	}
+
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+	}
+
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	iport->state = FNIC_IPORT_STATE_READY;
+	rsp = FNIC_STD_GET_FC_CT_CMD((&gpn_ft_rsp->fc_std_ct_hdr));
+
+	switch (rsp) {
+
+	case FC_FS_ACC:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "0x%x: GPNFT_RSP accept", iport->fcid);
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "0x%x: Canceling fabric disc timer\n",
+						 iport->fcid);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		iport->fabric.retry_counter = 0;
+		fdls_process_gpn_ft_tgt_list(iport, fchdr, len);
+
+		/*
+		 * iport state can change only if link down event happened
+		 * We don't need to undo fdls_process_gpn_ft_tgt_list,
+		 * that will be taken care in next link up event
+		 */
+		if (iport->state != FNIC_IPORT_STATE_READY) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Halting target discovery: fab st: %d iport st: %d ",
+				 fdls_get_state(fdls), iport->state);
+			break;
+		}
+		fdls_tgt_discovery_start(iport);
+		break;
+
+	case FC_FS_RJT:
+		reason_code = gpn_ft_rsp->fc_std_ct_hdr.ct_reason;
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: GPNFT_RSP Reject reason: %d", iport->fcid, reason_code);
+
+		if (((reason_code == FC_FS_RJT_BSY)
+		     || (reason_code == FC_FS_RJT_UNABL))
+			&& (fdls->retry_counter < FDLS_RETRY_COUNT)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: GPNFT_RSP ret REJ/BSY. Retry from timer routine",
+				 iport->fcid);
+			/* Retry again from the timer routine */
+			fdls->flags |= FNIC_FDLS_RETRY_FRAME;
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "0x%x: GPNFT_RSP reject", iport->fcid);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "0x%x: Canceling fabric disc timer\n",
+							 iport->fcid);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			iport->fabric.timer_pending = 0;
+			iport->fabric.retry_counter = 0;
+			/*
+			 * If GPN_FT ls_rjt then we should delete
+			 * all existing tports
+			 */
+			count = 0;
+			list_for_each_entry_safe(tport, next, &iport->tport_list,
+									 links) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "GPN_FT_REJECT: Remove port: 0x%x",
+							 tport->fcid);
+				fdls_delete_tport(iport, tport);
+				if ((old_link_down_cnt != iport->fnic->link_down_cnt)
+					|| (iport->state != FNIC_IPORT_STATE_READY)) {
+					return;
+				}
+				count++;
+			}
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "GPN_FT_REJECT: Removed (0x%x) ports", count);
+		}
+		break;
+
+	default:
+		break;
+	}
+}
+
+/**
+ * fdls_process_fabric_logo_rsp - Handle an flogo response from the fcf
+ * @iport: Handle to fnic iport
+ * @fchdr: Incoming frame
+ */
+static void
+fdls_process_fabric_logo_rsp(struct fnic_iport_s *iport,
+			     struct fc_frame_header *fchdr)
+{
+	struct fc_std_flogi *flogo_rsp = (struct fc_std_flogi *) fchdr;
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+	}
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (flogo_rsp->els.fl_cmd) {
+	case ELS_LS_ACC:
+		if (iport->fabric.state != FDLS_STATE_FABRIC_LOGO) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Flogo response. Fabric not in LOGO state. Dropping! %p",
+				 iport);
+			return;
+		}
+
+		iport->fabric.state = FDLS_STATE_FLOGO_DONE;
+		iport->state = FNIC_IPORT_STATE_LINK_WAIT;
+
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "iport 0x%p Canceling fabric disc timer\n",
+						 iport);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Flogo response from Fabric for did: 0x%x",
+		     ntoh24(fchdr->fh_d_id));
+		return;
+
+	case ELS_LS_RJT:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Flogo response from Fabric for did: 0x%x returned ELS_LS_RJT",
+		     ntoh24(fchdr->fh_d_id));
+		return;
+
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "FLOGO response not accepted or rejected: 0x%x",
+		     flogo_rsp->els.fl_cmd);
+	}
+}
+
+static void
+fdls_process_flogi_rsp(struct fnic_iport_s *iport,
+		       struct fc_frame_header *fchdr, void *rx_frame)
+{
+	struct fnic_fdls_fabric_s *fabric = &iport->fabric;
+	struct fc_std_flogi *flogi_rsp = (struct fc_std_flogi *) fchdr;
+	uint8_t *fcid;
+	uint16_t rdf_size;
+	uint8_t fcmac[6] = { 0x0E, 0XFC, 0x00, 0x00, 0x00, 0x00 };
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS processing FLOGI response", iport->fcid);
+
+	if (fdls_get_state(fabric) != FDLS_STATE_FABRIC_FLOGI) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "FLOGI response received in state (%d). Dropping frame",
+					 fdls_get_state(fabric));
+		return;
+	}
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fabric), oxid, iport->active_oxid_fabric_req);
+		return;
+	}
+
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (flogi_rsp->els.fl_cmd) {
+	case ELS_LS_ACC:
+		atomic64_inc(&iport->iport_stats.fabric_flogi_ls_accepts);
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "iport fcid: 0x%x Canceling fabric disc timer\n",
+						 iport->fcid);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+
+		iport->fabric.timer_pending = 0;
+		iport->fabric.retry_counter = 0;
+		fcid = FNIC_STD_GET_D_ID(fchdr);
+		iport->fcid = ntoh24(fcid);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "0x%x: FLOGI response accepted", iport->fcid);
+
+		/* Learn the Service Params */
+		rdf_size = be16_to_cpu(FNIC_LOGI_RDF_SIZE(flogi_rsp->els));
+		if ((rdf_size >= FNIC_MIN_DATA_FIELD_SIZE)
+			&& (rdf_size < FNIC_FC_MAX_PAYLOAD_LEN))
+			iport->max_payload_size = min(rdf_size,
+								  iport->max_payload_size);
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "max_payload_size from fabric: %u set: %d", rdf_size,
+					 iport->max_payload_size);
+
+		iport->r_a_tov = be32_to_cpu(FNIC_LOGI_R_A_TOV(flogi_rsp->els));
+		iport->e_d_tov = be32_to_cpu(FNIC_LOGI_E_D_TOV(flogi_rsp->els));
+
+		if (FNIC_LOGI_FEATURES(flogi_rsp->els) & FNIC_FC_EDTOV_NSEC)
+			iport->e_d_tov = iport->e_d_tov / FNIC_NSEC_TO_MSEC;
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "From fabric: R_A_TOV: %d E_D_TOV: %d",
+					 iport->r_a_tov, iport->e_d_tov);
+
+		fc_host_fabric_name(iport->fnic->host) =
+		get_unaligned_be64(&FNIC_LOGI_NODE_NAME(flogi_rsp->els));
+		fc_host_port_id(iport->fnic->host) = iport->fcid;
+
+		fnic_fdls_learn_fcoe_macs(iport, rx_frame, fcid);
+
+		if (fnic_fdls_register_portid(iport, iport->fcid, rx_frame) != 0) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "0x%x: FLOGI registration failed", iport->fcid);
+			break;
+		}
+
+		memcpy(&fcmac[3], fcid, 3);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Adding vNIC device MAC addr: %02x:%02x:%02x:%02x:%02x:%02x",
+			 fcmac[0], fcmac[1], fcmac[2], fcmac[3], fcmac[4],
+			 fcmac[5]);
+		vnic_dev_add_addr(iport->fnic->vdev, fcmac);
+
+		if (fdls_get_state(fabric) == FDLS_STATE_FABRIC_FLOGI) {
+			fnic_fdls_start_plogi(iport);
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "FLOGI response received. Starting PLOGI");
+		} else {
+			/* From FDLS_STATE_FABRIC_FLOGI state fabric can only go to
+			 * FDLS_STATE_LINKDOWN
+			 * state, hence we don't have to worry about undoing:
+			 * the fnic_fdls_register_portid and vnic_dev_add_addr
+			 */
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FLOGI response received in state (%d). Dropping frame",
+				 fdls_get_state(fabric));
+		}
+		break;
+
+	case ELS_LS_RJT:
+		atomic64_inc(&iport->iport_stats.fabric_flogi_ls_rejects);
+		if (fabric->retry_counter < iport->max_flogi_retries) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FLOGI returned ELS_LS_RJT BUSY. Retry from timer routine %p",
+				 iport);
+
+			/* Retry Flogi again from the timer routine. */
+			fabric->flags |= FNIC_FDLS_RETRY_FRAME;
+
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "FLOGI returned ELS_LS_RJT. Halting discovery %p",
+			 iport);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "iport 0x%p Canceling fabric disc timer\n",
+							 iport);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			fabric->timer_pending = 0;
+			fabric->retry_counter = 0;
+		}
+		break;
+
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "FLOGI response not accepted: 0x%x",
+		     flogi_rsp->els.fl_cmd);
+		atomic64_inc(&iport->iport_stats.fabric_flogi_misc_rejects);
+		break;
+	}
+}
+
+static void
+fdls_process_fabric_plogi_rsp(struct fnic_iport_s *iport,
+			      struct fc_frame_header *fchdr)
+{
+	struct fc_std_flogi *plogi_rsp = (struct fc_std_flogi *) fchdr;
+	struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *) fchdr;
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	if (fdls_get_state((&iport->fabric)) != FDLS_STATE_FABRIC_PLOGI) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Fabric PLOGI response received in state (%d). Dropping frame",
+			 fdls_get_state(&iport->fabric));
+		return;
+	}
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fabric_req);
+		return;
+	}
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	switch (plogi_rsp->els.fl_cmd) {
+	case ELS_LS_ACC:
+		atomic64_inc(&iport->iport_stats.fabric_plogi_ls_accepts);
+		if (iport->fabric.timer_pending) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "iport fcid: 0x%x fabric PLOGI response: Accepted\n",
+				 iport->fcid);
+			fnic_del_fabric_timer_sync(fnic);
+		}
+		iport->fabric.timer_pending = 0;
+		iport->fabric.retry_counter = 0;
+		fdls_set_state(&iport->fabric, FDLS_STATE_RPN_ID);
+		fdls_send_rpn_id(iport);
+		break;
+	case ELS_LS_RJT:
+		atomic64_inc(&iport->iport_stats.fabric_plogi_ls_rejects);
+		if (((els_rjt->rej.er_reason == ELS_RJT_BUSY)
+	     || (els_rjt->rej.er_reason == ELS_RJT_UNAB))
+			&& (iport->fabric.retry_counter < iport->max_plogi_retries)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Fabric PLOGI ELS_LS_RJT BUSY. Retry from timer routine",
+				 iport->fcid);
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Fabric PLOGI ELS_LS_RJT. Halting discovery",
+				 iport->fcid);
+			if (iport->fabric.timer_pending) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "iport fcid: 0x%x Canceling fabric disc timer\n",
+							 iport->fcid);
+				fnic_del_fabric_timer_sync(fnic);
+			}
+			iport->fabric.timer_pending = 0;
+			iport->fabric.retry_counter = 0;
+			return;
+		}
+		break;
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PLOGI response not accepted: 0x%x",
+		     plogi_rsp->els.fl_cmd);
+		atomic64_inc(&iport->iport_stats.fabric_plogi_misc_rejects);
+		break;
+	}
+}
+
+static void fdls_process_fdmi_plogi_rsp(struct fnic_iport_s *iport,
+					struct fc_frame_header *fchdr)
+{
+	struct fc_std_flogi *plogi_rsp = (struct fc_std_flogi *)fchdr;
+	struct fc_std_els_rjt_rsp *els_rjt = (struct fc_std_els_rjt_rsp *)fchdr;
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fnic *fnic = iport->fnic;
+	u64 fdmi_tov;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	if (iport->active_oxid_fdmi_plogi != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. state: %d, oxid recvd: 0x%x, active oxid: 0x%x\n",
+			fdls_get_state(fdls), oxid, iport->active_oxid_fdmi_plogi);
+		return;
+	}
+
+	iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING;
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi);
+
+	if (ntoh24(fchdr->fh_s_id) == FC_FID_MGMT_SERV) {
+		del_timer_sync(&iport->fabric.fdmi_timer);
+		iport->fabric.fdmi_pending = 0;
+		switch (plogi_rsp->els.fl_cmd) {
+		case ELS_LS_ACC:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FDLS process fdmi PLOGI response status: ELS_LS_ACC\n");
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Sending fdmi registration for port 0x%x\n",
+				 iport->fcid);
+
+			fdls_fdmi_register_hba(iport);
+			fdls_fdmi_register_pa(iport);
+			fdmi_tov = jiffies + msecs_to_jiffies(5000);
+			mod_timer(&iport->fabric.fdmi_timer,
+				  round_jiffies(fdmi_tov));
+			break;
+		case ELS_LS_RJT:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Fabric FDMI PLOGI returned ELS_LS_RJT reason: 0x%x",
+				     els_rjt->rej.er_reason);
+
+			if (((els_rjt->rej.er_reason == ELS_RJT_BUSY)
+			     || (els_rjt->rej.er_reason == ELS_RJT_UNAB))
+				&& (iport->fabric.fdmi_retry < 7)) {
+				iport->fabric.fdmi_retry++;
+				fdls_send_fdmi_plogi(iport);
+			}
+			break;
+		default:
+			break;
+		}
+	}
+}
+static void fdls_process_fdmi_reg_ack(struct fnic_iport_s *iport,
+				      struct fc_frame_header *fchdr,
+				      int rsp_type)
+{
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+
+	if (!iport->fabric.fdmi_pending) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			     "Received FDMI ack while not waiting: 0x%x\n",
+			     FNIC_STD_GET_OX_ID(fchdr));
+		return;
+	}
+
+	oxid =  FNIC_STD_GET_OX_ID(fchdr);
+
+	if ((iport->active_oxid_fdmi_rhba != oxid) &&
+		(iport->active_oxid_fdmi_rpa != oxid))  {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Incorrect OXID in response. oxid recvd: 0x%x, active oxids(rhba,rpa): 0x%x, 0x%x\n",
+			oxid, iport->active_oxid_fdmi_rhba, iport->active_oxid_fdmi_rpa);
+		return;
+	}
+	if (FNIC_FRAME_TYPE(oxid) == FNIC_FRAME_TYPE_FDMI_RHBA) {
+		iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING;
+		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba);
+	} else {
+		iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING;
+		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa);
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"iport fcid: 0x%x: Received FDMI registration ack\n",
+		 iport->fcid);
+
+	if (!iport->fabric.fdmi_pending) {
+		del_timer_sync(&iport->fabric.fdmi_timer);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "iport fcid: 0x%x: Canceling FDMI timer\n",
+					 iport->fcid);
+	}
+}
+
+static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
+				       struct fc_frame_header *fchdr)
+{
+	uint32_t s_id;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+
+	s_id = ntoh24(FNIC_STD_GET_S_ID(fchdr));
+
+	if (!(s_id != FC_FID_MGMT_SERV)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "Received abts rsp with invalid SID: 0x%x. Dropping frame",
+			     s_id);
+		return;
+	}
+
+	oxid =  FNIC_STD_GET_OX_ID(fchdr);
+
+	switch (FNIC_FRAME_TYPE(oxid)) {
+	case FNIC_FRAME_TYPE_FDMI_PLOGI:
+		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi);
+		break;
+	case FNIC_FRAME_TYPE_FDMI_RHBA:
+		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba);
+		break;
+	case FNIC_FRAME_TYPE_FDMI_RPA:
+		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa);
+		break;
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received abts rsp with invalid oxid: 0x%x. Dropping frame",
+			oxid);
+		break;
+	}
+
+	del_timer_sync(&iport->fabric.fdmi_timer);
+	iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+
+	fdls_send_fdmi_plogi(iport);
+}
+
+static void
+fdls_process_fabric_abts_rsp(struct fnic_iport_s *iport,
+			     struct fc_frame_header *fchdr)
+{
+	uint32_t s_id;
+	struct fc_std_abts_ba_acc *ba_acc = (struct fc_std_abts_ba_acc *)fchdr;
+	struct fc_std_abts_ba_rjt *ba_rjt;
+	uint32_t fabric_state = iport->fabric.state;
+	struct fnic *fnic = iport->fnic;
+	int frame_type;
+	uint16_t oxid;
+
+	s_id = ntoh24(fchdr->fh_s_id);
+	ba_rjt = (struct fc_std_abts_ba_rjt *) fchdr;
+
+	if (!((s_id == FC_FID_DIR_SERV) || (s_id == FC_FID_FLOGI)
+		  || (s_id == FC_FID_FCTRL))) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Received abts rsp with invalid SID: 0x%x. Dropping frame",
+			 s_id);
+		return;
+	}
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	if (iport->active_oxid_fabric_req != oxid) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received abts rsp with invalid oxid: 0x%x. Dropping frame",
+			oxid);
+		return;
+	}
+
+	if (iport->fabric.timer_pending) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Canceling fabric disc timer %p\n", iport);
+		fnic_del_fabric_timer_sync(fnic);
+	}
+	iport->fabric.timer_pending = 0;
+	iport->fabric.flags &= ~FNIC_FDLS_FABRIC_ABORT_ISSUED;
+
+	if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Received abts rsp BA_ACC for fabric_state: %d OX_ID: 0x%x",
+		     fabric_state, be16_to_cpu(ba_acc->acc.ba_ox_id));
+	} else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "BA_RJT fs: %d OX_ID: 0x%x rc: 0x%x rce: 0x%x",
+		     fabric_state, FNIC_STD_GET_OX_ID(&ba_rjt->fchdr),
+		     ba_rjt->rjt.br_reason, ba_rjt->rjt.br_explan);
+	}
+
+	frame_type = FNIC_FRAME_TYPE(oxid);
+	fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+
+	/* currently error handling/retry logic is same for ABTS BA_ACC & BA_RJT */
+	switch (frame_type) {
+	case FNIC_FRAME_TYPE_FABRIC_FLOGI:
+		if (iport->fabric.retry_counter < iport->max_flogi_retries)
+			fdls_send_fabric_flogi(iport);
+		else
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Exceeded max FLOGI retries");
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_LOGO:
+		if (iport->fabric.retry_counter < FABRIC_LOGO_MAX_RETRY)
+			fdls_send_fabric_logo(iport);
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_PLOGI:
+		if (iport->fabric.retry_counter < iport->max_plogi_retries)
+			fdls_send_fabric_plogi(iport);
+		else
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Exceeded max PLOGI retries");
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_RPN:
+		if (iport->fabric.retry_counter < FDLS_RETRY_COUNT)
+			fdls_send_rpn_id(iport);
+		else
+			/* go back to fabric Plogi */
+			fnic_fdls_start_plogi(iport);
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_SCR:
+		if (iport->fabric.retry_counter < FDLS_RETRY_COUNT)
+			fdls_send_scr(iport);
+		else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"SCR exhausted retries. Start fabric PLOGI %p",
+				 iport);
+			fnic_fdls_start_plogi(iport);	/* go back to fabric Plogi */
+		}
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_RFT:
+		if (iport->fabric.retry_counter < FDLS_RETRY_COUNT)
+			fdls_send_register_fc4_types(iport);
+		else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"RFT exhausted retries. Start fabric PLOGI %p",
+				 iport);
+			fnic_fdls_start_plogi(iport);	/* go back to fabric Plogi */
+		}
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_RFF:
+		if (iport->fabric.retry_counter < FDLS_RETRY_COUNT)
+			fdls_send_register_fc4_features(iport);
+		else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"RFF exhausted retries. Start fabric PLOGI %p",
+				 iport);
+			fnic_fdls_start_plogi(iport);	/* go back to fabric Plogi */
+		}
+		break;
+	case FNIC_FRAME_TYPE_FABRIC_GPN_FT:
+		if (iport->fabric.retry_counter <= FDLS_RETRY_COUNT)
+			fdls_send_gpn_ft(iport, fabric_state);
+		else
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"GPN FT exhausted retries. Start fabric PLOGI %p",
+				iport);
+		break;
+	default:
+		/*
+		 * We should not be here since we already validated rx oxid with
+		 * our active_oxid_fabric_req
+		 */
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Invalid OXID/active oxid 0x%x\n", oxid);
+		WARN_ON(true);
+		return;
+	}
+}
+
+static void
+fdls_process_abts_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr)
+{
+	uint8_t *frame;
+	struct fc_std_abts_ba_acc *pba_acc;
+	uint32_t nport_id;
+	uint16_t oxid = FNIC_STD_GET_OX_ID(fchdr);
+	struct fnic_tport_s *tport;
+	struct fnic *fnic = iport->fnic;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_abts_ba_acc);
+
+	nport_id = ntoh24(fchdr->fh_s_id);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Received abort from SID 0x%8x", nport_id);
+
+	tport = fnic_find_tport_by_fcid(iport, nport_id);
+	if (tport) {
+		if (tport->active_oxid == oxid) {
+			tport->flags |= FNIC_FDLS_TGT_ABORT_ISSUED;
+			fdls_free_oxid(iport, oxid, &tport->active_oxid);
+		}
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"0x%x: Failed to allocate frame to send response for ABTS req",
+				iport->fcid);
+		return;
+	}
+
+	pba_acc = (struct fc_std_abts_ba_acc *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	*pba_acc = (struct fc_std_abts_ba_acc) {
+		.fchdr = {.fh_r_ctl = FC_RCTL_BA_ACC,
+				.fh_f_ctl = {FNIC_FCP_RSP_FCTL, 0, 0}},
+		.acc = {.ba_low_seq_cnt = 0, .ba_high_seq_cnt = cpu_to_be16(0xFFFF)}
+	};
+
+	FNIC_STD_SET_S_ID(pba_acc->fchdr, fchdr->fh_d_id);
+	FNIC_STD_SET_D_ID(pba_acc->fchdr, fchdr->fh_s_id);
+	FNIC_STD_SET_OX_ID(pba_acc->fchdr, FNIC_STD_GET_OX_ID(fchdr));
+	FNIC_STD_SET_RX_ID(pba_acc->fchdr, FNIC_STD_GET_RX_ID(fchdr));
+
+	pba_acc->acc.ba_rx_id = cpu_to_be16(FNIC_STD_GET_RX_ID(fchdr));
+	pba_acc->acc.ba_ox_id = cpu_to_be16(FNIC_STD_GET_OX_ID(fchdr));
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: FDLS send BA ACC with oxid: 0x%x",
+		 iport->fcid, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+static void
+fdls_process_unsupported_els_req(struct fnic_iport_s *iport,
+				 struct fc_frame_header *fchdr)
+{
+	uint8_t *frame;
+	struct fc_std_els_rjt_rsp *pls_rsp;
+	uint16_t oxid;
+	uint32_t d_id = ntoh24(fchdr->fh_d_id);
+	struct fnic *fnic = iport->fnic;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_rjt_rsp);
+
+	if (iport->fcid != d_id) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Dropping unsupported ELS with illegal frame bits 0x%x\n",
+			 d_id);
+		atomic64_inc(&iport->iport_stats.unsupported_frames_dropped);
+		return;
+	}
+
+	if ((iport->state != FNIC_IPORT_STATE_READY)
+		&& (iport->state != FNIC_IPORT_STATE_FABRIC_DISC)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Dropping unsupported ELS request in iport state: %d",
+			 iport->state);
+		atomic64_inc(&iport->iport_stats.unsupported_frames_dropped);
+		return;
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			"Failed to allocate frame to send response to unsupported ELS request");
+		return;
+	}
+
+	pls_rsp = (struct fc_std_els_rjt_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_els_rjt_frame(frame, iport);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Process unsupported ELS request from SID: 0x%x",
+		     iport->fcid, ntoh24(fchdr->fh_s_id));
+
+	/* We don't support this ELS request, send a reject */
+	pls_rsp->rej.er_reason = 0x0B;
+	pls_rsp->rej.er_explan = 0x0;
+	pls_rsp->rej.er_vendor = 0x0;
+
+	FNIC_STD_SET_S_ID(pls_rsp->fchdr, fchdr->fh_d_id);
+	FNIC_STD_SET_D_ID(pls_rsp->fchdr, fchdr->fh_s_id);
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	FNIC_STD_SET_OX_ID(pls_rsp->fchdr, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+static void
+fdls_process_rls_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr)
+{
+	uint8_t *frame;
+	struct fc_std_rls_acc *prls_acc_rsp;
+	uint16_t oxid;
+	struct fnic *fnic = iport->fnic;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_rls_acc);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Process RLS request %d", iport->fnic->fnic_num);
+
+	if ((iport->state != FNIC_IPORT_STATE_READY)
+		&& (iport->state != FNIC_IPORT_STATE_FABRIC_DISC)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Received RLS req in iport state: %d. Dropping the frame.",
+			 iport->state);
+		return;
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send RLS accept");
+		return;
+	}
+	prls_acc_rsp = (struct fc_std_rls_acc *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+
+	FNIC_STD_SET_S_ID(prls_acc_rsp->fchdr, fchdr->fh_d_id);
+	FNIC_STD_SET_D_ID(prls_acc_rsp->fchdr, fchdr->fh_s_id);
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	FNIC_STD_SET_OX_ID(prls_acc_rsp->fchdr, oxid);
+	FNIC_STD_SET_RX_ID(prls_acc_rsp->fchdr, FNIC_UNASSIGNED_RXID);
+
+	FNIC_STD_SET_F_CTL(prls_acc_rsp->fchdr, FNIC_ELS_REP_FCTL << 16);
+	FNIC_STD_SET_R_CTL(prls_acc_rsp->fchdr, FC_RCTL_ELS_REP);
+	FNIC_STD_SET_TYPE(prls_acc_rsp->fchdr, FC_TYPE_ELS);
+
+	prls_acc_rsp->els.rls_cmd = ELS_LS_ACC;
+	prls_acc_rsp->els.rls_lesb.lesb_link_fail =
+	    cpu_to_be32(iport->fnic->link_down_cnt);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+static void
+fdls_process_els_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr,
+					 uint32_t len)
+{
+	uint8_t *frame;
+	struct fc_std_els_acc_rsp *pels_acc;
+	uint16_t oxid;
+	uint8_t *fc_payload;
+	uint8_t type;
+	struct fnic *fnic = iport->fnic;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET;
+
+	fc_payload = (uint8_t *) fchdr + sizeof(struct fc_frame_header);
+	type = *fc_payload;
+
+	if ((iport->state != FNIC_IPORT_STATE_READY)
+		&& (iport->state != FNIC_IPORT_STATE_FABRIC_DISC)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Dropping ELS frame type: 0x%x in iport state: %d",
+				 type, iport->state);
+		return;
+	}
+	switch (type) {
+	case ELS_ECHO:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "sending LS_ACC for ECHO request %d\n",
+					 iport->fnic->fnic_num);
+		break;
+
+	case ELS_RRQ:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "sending LS_ACC for RRQ request %d\n",
+					 iport->fnic->fnic_num);
+		break;
+
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "sending LS_ACC for 0x%x ELS frame\n", type);
+		break;
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send ELS response for 0x%x",
+				type);
+		return;
+	}
+
+	if (type == ELS_ECHO) {
+		/* Brocade sends a longer payload, copy all frame back */
+		memcpy(frame, fchdr, len);
+	}
+
+	pels_acc = (struct fc_std_els_acc_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_els_acc_frame(frame, iport);
+
+	FNIC_STD_SET_D_ID(pels_acc->fchdr, fchdr->fh_s_id);
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	FNIC_STD_SET_OX_ID(pels_acc->fchdr, oxid);
+
+	if (type == ELS_ECHO)
+		frame_size += len;
+	else
+		frame_size += sizeof(struct fc_std_els_acc_rsp);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+static void
+fdls_process_tgt_abts_rsp(struct fnic_iport_s *iport,
+			  struct fc_frame_header *fchdr)
+{
+	uint32_t s_id;
+	struct fnic_tport_s *tport;
+	uint32_t tport_state;
+	struct fc_std_abts_ba_acc *ba_acc;
+	struct fc_std_abts_ba_rjt *ba_rjt;
+	uint16_t oxid;
+	struct fnic *fnic = iport->fnic;
+	int frame_type;
+
+	s_id = ntoh24(fchdr->fh_s_id);
+	ba_acc = (struct fc_std_abts_ba_acc *)fchdr;
+	ba_rjt = (struct fc_std_abts_ba_rjt *)fchdr;
+
+	tport = fnic_find_tport_by_fcid(iport, s_id);
+	if (!tport) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					 "Received tgt abts rsp with invalid SID: 0x%x", s_id);
+		return;
+	}
+	if (tport->timer_pending) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					 "tport 0x%p Canceling fabric disc timer\n", tport);
+		fnic_del_tport_timer_sync(fnic, tport);
+	}
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					 "Received tgt abts rsp in iport state(%d). Dropping.",
+					 iport->state);
+		return;
+	}
+	tport->timer_pending = 0;
+	tport->flags &= ~FNIC_FDLS_TGT_ABORT_ISSUED;
+	tport_state = tport->state;
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+
+	/*This abort rsp is for ADISC */
+	frame_type = FNIC_FRAME_TYPE(oxid);
+	switch (frame_type) {
+	case FNIC_FRAME_TYPE_TGT_ADISC:
+		if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) {
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				     "OX_ID: 0x%x tgt_fcid: 0x%x rcvd tgt adisc abts resp BA_ACC",
+				     be16_to_cpu(ba_acc->acc.ba_ox_id),
+				     tport->fcid);
+		} else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) {
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				 "ADISC BA_RJT rcvd tport_fcid: 0x%x tport_state: %d ",
+				 tport->fcid, tport_state);
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				 "reason code: 0x%x reason code explanation:0x%x ",
+				     ba_rjt->rjt.br_reason,
+				     ba_rjt->rjt.br_explan);
+		}
+		if ((tport->retry_counter < FDLS_RETRY_COUNT)
+		    && (fchdr->fh_r_ctl == FC_RCTL_BA_ACC)) {
+			fdls_free_oxid(iport, oxid, &tport->active_oxid);
+			fdls_send_tgt_adisc(iport, tport);
+			return;
+		}
+		fdls_free_oxid(iport, oxid, &tport->active_oxid);
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					 "ADISC not responding. Deleting target port: 0x%x",
+					 tport->fcid);
+		fdls_delete_tport(iport, tport);
+		/* Restart discovery of targets */
+		if ((iport->state == FNIC_IPORT_STATE_READY)
+			&& (iport->fabric.state != FDLS_STATE_SEND_GPNFT)
+			&& (iport->fabric.state != FDLS_STATE_RSCN_GPN_FT)) {
+			fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT);
+		}
+		break;
+	case FNIC_FRAME_TYPE_TGT_PLOGI:
+		if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) {
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				 "Received tgt PLOGI abts response BA_ACC tgt_fcid: 0x%x",
+				 tport->fcid);
+		} else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "PLOGI BA_RJT received for tport_fcid: 0x%x OX_ID: 0x%x",
+				     tport->fcid, FNIC_STD_GET_OX_ID(fchdr));
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "reason code: 0x%x reason code explanation: 0x%x",
+				     ba_rjt->rjt.br_reason,
+				     ba_rjt->rjt.br_explan);
+		}
+		if ((tport->retry_counter < iport->max_plogi_retries)
+		    && (fchdr->fh_r_ctl == FC_RCTL_BA_ACC)) {
+			fdls_free_oxid(iport, oxid, &tport->active_oxid);
+			fdls_send_tgt_plogi(iport, tport);
+			return;
+		}
+
+		fdls_free_oxid(iport, oxid, &tport->active_oxid);
+		fdls_delete_tport(iport, tport);
+		/* Restart discovery of targets */
+		if ((iport->state == FNIC_IPORT_STATE_READY)
+			&& (iport->fabric.state != FDLS_STATE_SEND_GPNFT)
+			&& (iport->fabric.state != FDLS_STATE_RSCN_GPN_FT)) {
+			fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT);
+		}
+		break;
+	case FNIC_FRAME_TYPE_TGT_PRLI:
+		if (fchdr->fh_r_ctl == FC_RCTL_BA_ACC) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Received tgt PRLI abts response BA_ACC",
+				 tport->fcid);
+		} else if (fchdr->fh_r_ctl == FC_RCTL_BA_RJT) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "PRLI BA_RJT received for tport_fcid: 0x%x OX_ID: 0x%x ",
+				     tport->fcid, FNIC_STD_GET_OX_ID(fchdr));
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "reason code: 0x%x reason code explanation: 0x%x",
+				     ba_rjt->rjt.br_reason,
+				     ba_rjt->rjt.br_explan);
+		}
+		if ((tport->retry_counter < FDLS_RETRY_COUNT)
+		    && (fchdr->fh_r_ctl == FC_RCTL_BA_ACC)) {
+			fdls_free_oxid(iport, oxid, &tport->active_oxid);
+			fdls_send_tgt_prli(iport, tport);
+			return;
+		}
+		fdls_free_oxid(iport, oxid, &tport->active_oxid);
+		fdls_send_tgt_plogi(iport, tport);	/* go back to plogi */
+		fdls_set_tport_state(tport, FDLS_TGT_STATE_PLOGI);
+		break;
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received ABTS response for unknown frame %p", iport);
+		break;
+	}
+
+}
+
+static void
+fdls_process_plogi_req(struct fnic_iport_s *iport,
+		       struct fc_frame_header *fchdr)
+{
+	uint8_t *frame;
+	struct fc_std_els_rjt_rsp *pplogi_rsp;
+	uint16_t oxid;
+	uint32_t d_id = ntoh24(fchdr->fh_d_id);
+	struct fnic *fnic = iport->fnic;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_rjt_rsp);
+
+	if (iport->fcid != d_id) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Received PLOGI with illegal frame bits. Dropping frame from 0x%x",
+			 d_id);
+		return;
+	}
+
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Received PLOGI request in iport state: %d Dropping frame",
+			 iport->state);
+		return;
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			"Failed to allocate frame to send response to PLOGI request");
+		return;
+	}
+
+	pplogi_rsp = (struct fc_std_els_rjt_rsp *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	fdls_init_els_rjt_frame(frame, iport);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: Process PLOGI request from SID: 0x%x",
+				 iport->fcid, ntoh24(fchdr->fh_s_id));
+
+	/* We don't support PLOGI request, send a reject */
+	pplogi_rsp->rej.er_reason = 0x0B;
+	pplogi_rsp->rej.er_explan = 0x0;
+	pplogi_rsp->rej.er_vendor = 0x0;
+
+	FNIC_STD_SET_S_ID(pplogi_rsp->fchdr, fchdr->fh_d_id);
+	FNIC_STD_SET_D_ID(pplogi_rsp->fchdr, fchdr->fh_s_id);
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	FNIC_STD_SET_OX_ID(pplogi_rsp->fchdr, oxid);
+
+	fnic_send_fcoe_frame(iport, frame, frame_size);
+}
+
+static void
+fdls_process_logo_req(struct fnic_iport_s *iport, struct fc_frame_header *fchdr)
+{
+	struct fc_std_logo *logo = (struct fc_std_logo *)fchdr;
+	uint32_t nport_id;
+	uint64_t nport_name;
+	struct fnic_tport_s *tport;
+	struct fnic *fnic = iport->fnic;
+	uint16_t oxid;
+
+	nport_id = ntoh24(logo->els.fl_n_port_id);
+	nport_name = be64_to_cpu(logo->els.fl_n_port_wwn);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Process LOGO request from fcid: 0x%x", nport_id);
+
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			 "Dropping LOGO req from 0x%x in iport state: %d",
+			 nport_id, iport->state);
+		return;
+	}
+
+	tport = fnic_find_tport_by_fcid(iport, nport_id);
+
+	if (!tport) {
+		/* We are not logged in with the nport, log and drop... */
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			 "Received LOGO from an nport not logged in: 0x%x(0x%llx)",
+			 nport_id, nport_name);
+		return;
+	}
+	if (tport->fcid != nport_id) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		 "Received LOGO with invalid target port fcid: 0x%x(0x%llx)",
+		 nport_id, nport_name);
+		return;
+	}
+	if (tport->timer_pending) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					 "tport fcid 0x%x: Canceling disc timer\n",
+					 tport->fcid);
+		fnic_del_tport_timer_sync(fnic, tport);
+		tport->timer_pending = 0;
+	}
+
+	/* got a logo in response to adisc to a target which has logged out */
+	if (tport->state == FDLS_TGT_STATE_ADISC) {
+		tport->retry_counter = 0;
+		oxid = tport->active_oxid;
+		fdls_free_oxid(iport, oxid, &tport->active_oxid);
+		fdls_delete_tport(iport, tport);
+		fdls_send_logo_resp(iport, &logo->fchdr);
+		if ((iport->state == FNIC_IPORT_STATE_READY)
+			&& (fdls_get_state(&iport->fabric) != FDLS_STATE_SEND_GPNFT)
+			&& (fdls_get_state(&iport->fabric) != FDLS_STATE_RSCN_GPN_FT)) {
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+						 "Sending GPNFT in response to LOGO from Target:0x%x",
+						 nport_id);
+			fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT);
+			return;
+		}
+	} else {
+		fdls_delete_tport(iport, tport);
+	}
+	if (iport->state == FNIC_IPORT_STATE_READY) {
+		fdls_send_logo_resp(iport, &logo->fchdr);
+		if ((fdls_get_state(&iport->fabric) != FDLS_STATE_SEND_GPNFT) &&
+			(fdls_get_state(&iport->fabric) != FDLS_STATE_RSCN_GPN_FT)) {
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+						 "Sending GPNFT in response to LOGO from Target:0x%x",
+						 nport_id);
+			fdls_send_gpn_ft(iport, FDLS_STATE_SEND_GPNFT);
+		}
+	}
+}
+
+static void
+fdls_process_rscn(struct fnic_iport_s *iport, struct fc_frame_header *fchdr)
+{
+	struct fc_std_rscn *rscn;
+	struct fc_els_rscn_page *rscn_port = NULL;
+	int num_ports;
+	struct fnic_tport_s *tport, *next;
+	uint32_t nport_id;
+	uint8_t fcid[3];
+	int newports = 0;
+	struct fnic_fdls_fabric_s *fdls = &iport->fabric;
+	struct fnic *fnic = iport->fnic;
+	int rscn_type = NOT_PC_RSCN;
+	uint32_t sid = ntoh24(fchdr->fh_s_id);
+	unsigned long reset_fnic_list_lock_flags = 0;
+	uint16_t rscn_payload_len;
+
+	atomic64_inc(&iport->iport_stats.num_rscns);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FDLS process RSCN %p", iport);
+
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "FDLS RSCN received in state(%d). Dropping",
+					 fdls_get_state(fdls));
+		return;
+	}
+
+	rscn = (struct fc_std_rscn *)fchdr;
+	rscn_payload_len = be16_to_cpu(rscn->els.rscn_plen);
+
+	/* frame validation */
+	if ((rscn_payload_len % 4 != 0) || (rscn_payload_len < 8)
+	    || (rscn_payload_len > 1024)
+	    || (rscn->els.rscn_page_len != 4)) {
+		num_ports = 0;
+		if ((rscn_payload_len == 0xFFFF)
+		    && (sid == FC_FID_FCTRL)) {
+			rscn_type = PC_RSCN;
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				     "pcrscn: PCRSCN received. sid: 0x%x payload len: 0x%x",
+				     sid, rscn_payload_len);
+		} else {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RSCN payload_len: 0x%x page_len: 0x%x",
+				     rscn_payload_len, rscn->els.rscn_page_len);
+			/* if this happens then we need to send ADISC to all the tports. */
+			list_for_each_entry_safe(tport, next, &iport->tport_list, links) {
+				if (tport->state == FDLS_TGT_STATE_READY)
+					tport->flags |= FNIC_FDLS_TPORT_SEND_ADISC;
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RSCN for port id: 0x%x", tport->fcid);
+			}
+		} /* end else */
+	} else {
+		num_ports = (rscn_payload_len - 4) / rscn->els.rscn_page_len;
+		rscn_port = (struct fc_els_rscn_page *)(rscn + 1);
+	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "RSCN received for num_ports: %d payload_len: %d page_len: %d ",
+		     num_ports, rscn_payload_len, rscn->els.rscn_page_len);
+
+	/*
+	 * RSCN have at least one Port_ID page , but may not have any port_id
+	 * in it. If no port_id is specified in the Port_ID page , we send
+	 * ADISC to all the tports
+	 */
+
+	while (num_ports) {
+
+		memcpy(fcid, rscn_port->rscn_fid, 3);
+
+		nport_id = ntoh24(fcid);
+		rscn_port++;
+		num_ports--;
+		/* if this happens then we need to send ADISC to all the tports. */
+		if (nport_id == 0) {
+			list_for_each_entry_safe(tport, next, &iport->tport_list,
+									 links) {
+				if (tport->state == FDLS_TGT_STATE_READY)
+					tport->flags |= FNIC_FDLS_TPORT_SEND_ADISC;
+
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "RSCN for port id: 0x%x", tport->fcid);
+			}
+			break;
+		}
+		tport = fnic_find_tport_by_fcid(iport, nport_id);
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "RSCN port id list: 0x%x", nport_id);
+
+		if (!tport) {
+			newports++;
+			continue;
+		}
+		if (tport->state == FDLS_TGT_STATE_READY)
+			tport->flags |= FNIC_FDLS_TPORT_SEND_ADISC;
+	}
+
+	if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON &&
+		rscn_type == PC_RSCN && fnic->role == FNIC_ROLE_FCP_INITIATOR) {
+
+		if (fnic->pc_rscn_handling_status == PC_RSCN_HANDLING_IN_PROGRESS) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "PCRSCN handling already in progress. Skip host reset: %d",
+				 iport->fnic->fnic_num);
+			return;
+		}
+
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Processing PCRSCN. Queuing fnic for host reset: %d",
+			 iport->fnic->fnic_num);
+		fnic->pc_rscn_handling_status = PC_RSCN_HANDLING_IN_PROGRESS;
+
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+
+		spin_lock_irqsave(&reset_fnic_list_lock,
+						  reset_fnic_list_lock_flags);
+		list_add_tail(&fnic->links, &reset_fnic_list);
+		spin_unlock_irqrestore(&reset_fnic_list_lock,
+							   reset_fnic_list_lock_flags);
+
+		queue_work(reset_fnic_work_queue, &reset_fnic_work);
+		spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	} else {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "FDLS process RSCN sending GPN_FT: newports: %d", newports);
+		fdls_send_gpn_ft(iport, FDLS_STATE_RSCN_GPN_FT);
+		fdls_send_rscn_resp(iport, fchdr);
+	}
+}
+
+void fnic_fdls_disc_start(struct fnic_iport_s *iport)
+{
+	struct fnic *fnic = iport->fnic;
+
+	fc_host_fabric_name(iport->fnic->host) = 0;
+	fc_host_post_event(iport->fnic->host, fc_get_event_number(),
+					   FCH_EVT_LIPRESET, 0);
+
+	if (!iport->usefip) {
+		if (iport->flags & FNIC_FIRST_LINK_UP) {
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			fnic_scsi_fcpio_reset(iport->fnic);
+			spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+
+			iport->flags &= ~FNIC_FIRST_LINK_UP;
+		}
+		fnic_fdls_start_flogi(iport);
+	} else
+		fnic_fdls_start_plogi(iport);
+}
+
+static void
+fdls_process_adisc_req(struct fnic_iport_s *iport,
+		       struct fc_frame_header *fchdr)
+{
+	struct fc_std_els_adisc *padisc_acc;
+	struct fc_std_els_adisc *adisc_req = (struct fc_std_els_adisc *)fchdr;
+	uint64_t frame_wwnn;
+	uint64_t frame_wwpn;
+	uint32_t tgt_fcid;
+	struct fnic_tport_s *tport;
+	uint8_t *fcid;
+	uint8_t *rjt_frame;
+	uint8_t *acc_frame;
+	struct fc_std_els_rjt_rsp *prjts_rsp;
+	uint16_t oxid;
+	struct fnic *fnic = iport->fnic;
+	uint16_t rjt_frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_rjt_rsp);
+	uint16_t acc_frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_std_els_adisc);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Process ADISC request %d", iport->fnic->fnic_num);
+
+	fcid = FNIC_STD_GET_S_ID(fchdr);
+	tgt_fcid = ntoh24(fcid);
+	tport = fnic_find_tport_by_fcid(iport, tgt_fcid);
+	if (!tport) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					 "tport for fcid: 0x%x not found. Dropping ADISC req.",
+					 tgt_fcid);
+		return;
+	}
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			 "Dropping ADISC req from fcid: 0x%x in iport state: %d",
+			 tgt_fcid, iport->state);
+		return;
+	}
+
+	frame_wwnn = be64_to_cpu(adisc_req->els.adisc_wwnn);
+	frame_wwpn = be64_to_cpu(adisc_req->els.adisc_wwpn);
+
+	if ((frame_wwnn != tport->wwnn) || (frame_wwpn != tport->wwpn)) {
+		/* send reject */
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			 "ADISC req from fcid: 0x%x mismatch wwpn: 0x%llx wwnn: 0x%llx",
+			 tgt_fcid, frame_wwpn, frame_wwnn);
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			 "local tport wwpn: 0x%llx wwnn: 0x%llx. Sending RJT",
+			 tport->wwpn, tport->wwnn);
+
+		rjt_frame = fdls_alloc_frame(iport);
+		if (rjt_frame == NULL) {
+			FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate rjt_frame to send response to ADISC request");
+			return;
+		}
+
+		prjts_rsp = (struct fc_std_els_rjt_rsp *) (rjt_frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+		fdls_init_els_rjt_frame(rjt_frame, iport);
+
+		prjts_rsp->rej.er_reason = 0x03;	/*  logical error */
+		prjts_rsp->rej.er_explan = 0x1E;	/*  N_port login required */
+		prjts_rsp->rej.er_vendor = 0x0;
+
+		FNIC_STD_SET_S_ID(prjts_rsp->fchdr, fchdr->fh_d_id);
+		FNIC_STD_SET_D_ID(prjts_rsp->fchdr, fchdr->fh_s_id);
+		oxid = FNIC_STD_GET_OX_ID(fchdr);
+		FNIC_STD_SET_OX_ID(prjts_rsp->fchdr, oxid);
+
+		fnic_send_fcoe_frame(iport, rjt_frame, rjt_frame_size);
+		return;
+	}
+
+	acc_frame = fdls_alloc_frame(iport);
+	if (acc_frame == NULL) {
+		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				"Failed to allocate frame to send ADISC accept");
+		return;
+	}
+
+	padisc_acc = (struct fc_std_els_adisc *) (acc_frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+
+	FNIC_STD_SET_S_ID(padisc_acc->fchdr, fchdr->fh_d_id);
+	FNIC_STD_SET_D_ID(padisc_acc->fchdr, fchdr->fh_s_id);
+
+	FNIC_STD_SET_F_CTL(padisc_acc->fchdr, FNIC_ELS_REP_FCTL << 16);
+	FNIC_STD_SET_R_CTL(padisc_acc->fchdr, FC_RCTL_ELS_REP);
+	FNIC_STD_SET_TYPE(padisc_acc->fchdr, FC_TYPE_ELS);
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	FNIC_STD_SET_OX_ID(padisc_acc->fchdr, oxid);
+	FNIC_STD_SET_RX_ID(padisc_acc->fchdr, FNIC_UNASSIGNED_RXID);
+
+	padisc_acc->els.adisc_cmd = ELS_LS_ACC;
+
+	FNIC_STD_SET_NPORT_NAME(&padisc_acc->els.adisc_wwpn,
+			iport->wwpn);
+	FNIC_STD_SET_NODE_NAME(&padisc_acc->els.adisc_wwnn,
+			iport->wwnn);
+	memcpy(padisc_acc->els.adisc_port_id, fchdr->fh_d_id, 3);
+
+	fnic_send_fcoe_frame(iport, acc_frame, acc_frame_size);
+}
+
+/*
+ * Performs a validation for all FCOE frames and return the frame type
+ */
+int
+fnic_fdls_validate_and_get_frame_type(struct fnic_iport_s *iport,
+	struct fc_frame_header *fchdr)
+{
+	uint8_t type;
+	uint8_t *fc_payload;
+	uint16_t oxid;
+	uint32_t s_id;
+	uint32_t d_id;
+	struct fnic *fnic = iport->fnic;
+	struct fnic_fdls_fabric_s *fabric = &iport->fabric;
+	int oxid_frame_type;
+
+	oxid = FNIC_STD_GET_OX_ID(fchdr);
+	fc_payload = (uint8_t *) fchdr + sizeof(struct fc_frame_header);
+	type = *fc_payload;
+	s_id = ntoh24(fchdr->fh_s_id);
+	d_id = ntoh24(fchdr->fh_d_id);
+
+	/* some common validation */
+		if (fdls_get_state(fabric) > FDLS_STATE_FABRIC_FLOGI) {
+			if ((iport->fcid != d_id) || (!FNIC_FC_FRAME_CS_CTL(fchdr))) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "invalid frame received. Dropping frame");
+				return -1;
+			}
+		}
+
+	/*  BLS ABTS response */
+	if ((fchdr->fh_r_ctl == FC_RCTL_BA_ACC)
+	|| (fchdr->fh_r_ctl == FC_RCTL_BA_RJT)) {
+		if (!(FNIC_FC_FRAME_TYPE_BLS(fchdr))) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Received ABTS invalid frame. Dropping frame");
+			return -1;
+
+		}
+		if (fdls_is_oxid_fabric_req(oxid)) {
+			if (!(iport->fabric.flags & FNIC_FDLS_FABRIC_ABORT_ISSUED)) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					"Received unexpected ABTS RSP(oxid:0x%x) from 0x%x. Dropping frame",
+					oxid, s_id);
+				return -1;
+	}
+			return FNIC_FABRIC_BLS_ABTS_RSP;
+		} else if (fdls_is_oxid_fdmi_req(oxid)) {
+			return FNIC_FDMI_BLS_ABTS_RSP;
+		} else if (fdls_is_oxid_tgt_req(oxid)) {
+			return FNIC_TPORT_BLS_ABTS_RSP;
+		}
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received ABTS rsp with unknown oxid(0x%x) from 0x%x. Dropping frame",
+			oxid, s_id);
+		return -1;
+	}
+
+	/* BLS ABTS Req */
+	if ((fchdr->fh_r_ctl == FC_RCTL_BA_ABTS)
+	&& (FNIC_FC_FRAME_TYPE_BLS(fchdr))) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Receiving Abort Request from s_id: 0x%x", s_id);
+		return FNIC_BLS_ABTS_REQ;
+	}
+
+	/* unsolicited requests frames */
+	if (FNIC_FC_FRAME_UNSOLICITED(fchdr)) {
+		switch (type) {
+		case ELS_LOGO:
+			if ((!FNIC_FC_FRAME_FCTL_FIRST_LAST_SEQINIT(fchdr))
+				|| (!FNIC_FC_FRAME_UNSOLICITED(fchdr))
+				|| (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Received LOGO invalid frame. Dropping frame");
+				return -1;
+			}
+			return FNIC_ELS_LOGO_REQ;
+		case ELS_RSCN:
+			if ((!FNIC_FC_FRAME_FCTL_FIRST_LAST_SEQINIT(fchdr))
+				|| (!FNIC_FC_FRAME_TYPE_ELS(fchdr))
+				|| (!FNIC_FC_FRAME_UNSOLICITED(fchdr))) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Received RSCN invalid FCTL. Dropping frame");
+				return -1;
+			}
+			if (s_id != FC_FID_FCTRL)
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				     "Received RSCN from target FCTL: 0x%x type: 0x%x s_id: 0x%x.",
+				     fchdr->fh_f_ctl[0], fchdr->fh_type, s_id);
+			return FNIC_ELS_RSCN_REQ;
+		case ELS_PLOGI:
+			return FNIC_ELS_PLOGI_REQ;
+		case ELS_ECHO:
+			return FNIC_ELS_ECHO_REQ;
+		case ELS_ADISC:
+			return FNIC_ELS_ADISC;
+		case ELS_RLS:
+			return FNIC_ELS_RLS;
+		case ELS_RRQ:
+			return FNIC_ELS_RRQ;
+		default:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Unsupported frame (type:0x%02x) from fcid: 0x%x",
+				 type, s_id);
+			return FNIC_ELS_UNSUPPORTED_REQ;
+		}
+	}
+
+	/* solicited response from fabric or target */
+	oxid_frame_type = FNIC_FRAME_TYPE(oxid);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"oxid frame code: 0x%x, oxid: 0x%x\n", oxid_frame_type, oxid);
+	switch (oxid_frame_type) {
+	case FNIC_FRAME_TYPE_FABRIC_FLOGI:
+		if (type == ELS_LS_ACC) {
+			if ((s_id != FC_FID_FLOGI)
+				|| (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+				return -1;
+			}
+		}
+		return FNIC_FABRIC_FLOGI_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_PLOGI:
+		if (type == ELS_LS_ACC) {
+			if ((s_id != FC_FID_DIR_SERV)
+				|| (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+				return -1;
+			}
+		}
+		return FNIC_FABRIC_PLOGI_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_SCR:
+		if (type == ELS_LS_ACC) {
+			if ((s_id != FC_FID_FCTRL)
+				|| (!FNIC_FC_FRAME_TYPE_ELS(fchdr))) {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+				return -1;
+			}
+		}
+		return FNIC_FABRIC_SCR_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_RPN:
+		if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+			return -1;
+		}
+		return FNIC_FABRIC_RPN_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_RFT:
+		if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+			return -1;
+		}
+		return FNIC_FABRIC_RFT_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_RFF:
+		if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+			return -1;
+		}
+		return FNIC_FABRIC_RFF_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_GPN_FT:
+		if ((s_id != FC_FID_DIR_SERV) || (!FNIC_FC_FRAME_TYPE_FC_GS(fchdr))) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Received unknown frame. Dropping frame");
+			return -1;
+		}
+		return FNIC_FABRIC_GPN_FT_RSP;
+
+	case FNIC_FRAME_TYPE_FABRIC_LOGO:
+		return FNIC_FABRIC_LOGO_RSP;
+	case FNIC_FRAME_TYPE_FDMI_PLOGI:
+		return FNIC_FDMI_PLOGI_RSP;
+	case FNIC_FRAME_TYPE_FDMI_RHBA:
+		return FNIC_FDMI_REG_HBA_RSP;
+	case FNIC_FRAME_TYPE_FDMI_RPA:
+		return FNIC_FDMI_RPA_RSP;
+	case FNIC_FRAME_TYPE_TGT_PLOGI:
+		return FNIC_TPORT_PLOGI_RSP;
+	case FNIC_FRAME_TYPE_TGT_PRLI:
+		return FNIC_TPORT_PRLI_RSP;
+	case FNIC_FRAME_TYPE_TGT_ADISC:
+		return FNIC_TPORT_ADISC_RSP;
+	case FNIC_FRAME_TYPE_TGT_LOGO:
+		if (!FNIC_FC_FRAME_TYPE_ELS(fchdr)) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"Dropping Unknown frame in tport solicited exchange range type: 0x%x.",
+				     fchdr->fh_type);
+			return -1;
+		}
+		return FNIC_TPORT_LOGO_RSP;
+	default:
+		/* Drop the Rx frame and log/stats it */
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Solicited response: unknown OXID: 0x%x", oxid);
+		return -1;
+	}
+
+	return -1;
+}
+
+void fnic_fdls_recv_frame(struct fnic_iport_s *iport, void *rx_frame,
+						  int len, int fchdr_offset)
+{
+	struct fc_frame_header *fchdr;
+	uint32_t s_id = 0;
+	uint32_t d_id = 0;
+	struct fnic *fnic = iport->fnic;
+	int frame_type;
+
+	fchdr = (struct fc_frame_header *) ((uint8_t *) rx_frame + fchdr_offset);
+	s_id = ntoh24(fchdr->fh_s_id);
+	d_id = ntoh24(fchdr->fh_d_id);
+
+	fnic_debug_dump_fc_frame(fnic, fchdr, len, "Incoming");
+
+	frame_type =
+		fnic_fdls_validate_and_get_frame_type(iport, fchdr);
+
+	/*if we are in flogo drop everything else */
+	if (iport->fabric.state == FDLS_STATE_FABRIC_LOGO &&
+		frame_type != FNIC_FABRIC_LOGO_RSP)
+		return;
+
+	switch (frame_type) {
+	case FNIC_FABRIC_FLOGI_RSP:
+		fdls_process_flogi_rsp(iport, fchdr, rx_frame);
+		break;
+	case FNIC_FABRIC_PLOGI_RSP:
+		fdls_process_fabric_plogi_rsp(iport, fchdr);
+		break;
+	case FNIC_FDMI_PLOGI_RSP:
+		fdls_process_fdmi_plogi_rsp(iport, fchdr);
+		break;
+	case FNIC_FABRIC_RPN_RSP:
+		fdls_process_rpn_id_rsp(iport, fchdr);
+		break;
+	case FNIC_FABRIC_RFT_RSP:
+		fdls_process_rft_id_rsp(iport, fchdr);
+		break;
+	case FNIC_FABRIC_RFF_RSP:
+		fdls_process_rff_id_rsp(iport, fchdr);
+		break;
+	case FNIC_FABRIC_SCR_RSP:
+		fdls_process_scr_rsp(iport, fchdr);
+		break;
+	case FNIC_FABRIC_GPN_FT_RSP:
+		fdls_process_gpn_ft_rsp(iport, fchdr, len);
+		break;
+	case FNIC_TPORT_PLOGI_RSP:
+		fdls_process_tgt_plogi_rsp(iport, fchdr);
+		break;
+	case FNIC_TPORT_PRLI_RSP:
+		fdls_process_tgt_prli_rsp(iport, fchdr);
+		break;
+	case FNIC_TPORT_ADISC_RSP:
+		fdls_process_tgt_adisc_rsp(iport, fchdr);
+		break;
+	case FNIC_TPORT_BLS_ABTS_RSP:
+		fdls_process_tgt_abts_rsp(iport, fchdr);
+		break;
+	case FNIC_TPORT_LOGO_RSP:
+		/* Logo response from tgt which we have deleted */
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Logo response from tgt: 0x%x",
+			     ntoh24(fchdr->fh_s_id));
+		break;
+	case FNIC_FABRIC_LOGO_RSP:
+		fdls_process_fabric_logo_rsp(iport, fchdr);
+		break;
+	case FNIC_FABRIC_BLS_ABTS_RSP:
+			fdls_process_fabric_abts_rsp(iport, fchdr);
+		break;
+	case FNIC_FDMI_BLS_ABTS_RSP:
+		fdls_process_fdmi_abts_rsp(iport, fchdr);
+		break;
+	case FNIC_BLS_ABTS_REQ:
+		fdls_process_abts_req(iport, fchdr);
+		break;
+	case FNIC_ELS_UNSUPPORTED_REQ:
+		fdls_process_unsupported_els_req(iport, fchdr);
+		break;
+	case FNIC_ELS_PLOGI_REQ:
+		fdls_process_plogi_req(iport, fchdr);
+		break;
+	case FNIC_ELS_RSCN_REQ:
+		fdls_process_rscn(iport, fchdr);
+		break;
+	case FNIC_ELS_LOGO_REQ:
+		fdls_process_logo_req(iport, fchdr);
+		break;
+	case FNIC_ELS_RRQ:
+	case FNIC_ELS_ECHO_REQ:
+		fdls_process_els_req(iport, fchdr, len);
+		break;
+	case FNIC_ELS_ADISC:
+		fdls_process_adisc_req(iport, fchdr);
+		break;
+	case FNIC_ELS_RLS:
+		fdls_process_rls_req(iport, fchdr);
+		break;
+	case FNIC_FDMI_REG_HBA_RSP:
+	case FNIC_FDMI_RPA_RSP:
+		fdls_process_fdmi_reg_ack(iport, fchdr, frame_type);
+		break;
+	default:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "s_id: 0x%x d_did: 0x%x", s_id, d_id);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Received unknown FCoE frame of len: %d. Dropping frame", len);
+		break;
+	}
+}
+
+void fnic_fdls_disc_init(struct fnic_iport_s *iport)
+{
+	fdls_reset_oxid_pool(iport);
+	fdls_set_state((&iport->fabric), FDLS_STATE_INIT);
+}
+
+void fnic_fdls_link_down(struct fnic_iport_s *iport)
+{
+	struct fnic_tport_s *tport, *next;
+	struct fnic *fnic = iport->fnic;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS processing link down", iport->fcid);
+
+	fdls_set_state((&iport->fabric), FDLS_STATE_LINKDOWN);
+	iport->fabric.flags = 0;
+
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+	fnic_scsi_fcpio_reset(iport->fnic);
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	list_for_each_entry_safe(tport, next, &iport->tport_list, links) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "removing rport: 0x%x", tport->fcid);
+		fdls_delete_tport(iport, tport);
+	}
+
+	if ((fnic_fdmi_support == 1) && (iport->fabric.fdmi_pending > 0)) {
+		del_timer_sync(&iport->fabric.fdmi_timer);
+		iport->fabric.fdmi_pending = 0;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS finish processing link down", iport->fcid);
+}
diff --git a/drivers/scsi/fnic/fdls_fc.h b/drivers/scsi/fnic/fdls_fc.h
new file mode 100644
index 000000000000..012f43afd083
--- /dev/null
+++ b/drivers/scsi/fnic/fdls_fc.h
@@ -0,0 +1,253 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
+ * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
+ */
+
+#ifndef _FDLS_FC_H_
+#define _FDLS_FC_H_
+
+/* This file contains the declarations for FC fabric services
+ * and target discovery
+ *
+ * Request and Response for
+ * 1. FLOGI
+ * 2. PLOGI to Fabric Controller
+ * 3. GPN_ID, GPN_FT
+ * 4. RSCN
+ * 5. PLOGI to Target
+ * 6. PRLI to Target
+ */
+
+#include <scsi/scsi.h>
+#include <scsi/fc/fc_els.h>
+#include <uapi/scsi/fc/fc_fs.h>
+#include <uapi/scsi/fc/fc_ns.h>
+#include <uapi/scsi/fc/fc_gs.h>
+#include <uapi/linux/if_ether.h>
+#include <scsi/fc/fc_ms.h>
+#include <linux/minmax.h>
+#include <linux/if_ether.h>
+#include <scsi/fc/fc_encaps.h>
+#include <scsi/fc/fc_fcoe.h>
+
+#define FDLS_MIN_FRAMES	(32)
+#define FDLS_MIN_FRAME_ELEM	(4)
+#define FNIC_FCP_SP_RD_XRDY_DIS 0x00000002
+#define FNIC_FCP_SP_TARGET      0x00000010
+#define FNIC_FCP_SP_INITIATOR   0x00000020
+#define FNIC_FCP_SP_CONF_CMPL   0x00000080
+#define FNIC_FCP_SP_RETRY       0x00000100
+
+#define FNIC_FC_CONCUR_SEQS    (0xFF)
+#define FNIC_FC_RO_INFO        (0x1F)
+
+/* Little Endian */
+#define FNIC_UNASSIGNED_OXID	(0xffff)
+#define FNIC_UNASSIGNED_RXID	(0xffff)
+#define FNIC_ELS_REQ_FCTL      (0x000029)
+#define FNIC_ELS_REP_FCTL      (0x000099)
+
+#define FNIC_FCP_RSP_FCTL      (0x000099)
+#define FNIC_REQ_ABTS_FCTL     (0x000009)
+
+#define FNIC_FC_PH_VER_HI      (0x20)
+#define FNIC_FC_PH_VER_LO      (0x20)
+#define FNIC_FC_PH_VER         (0x2020)
+#define FNIC_FC_B2B_CREDIT     (0x0A)
+#define FNIC_FC_B2B_RDF_SZ     (0x0800)
+
+#define FNIC_LOGI_RDF_SIZE(_logi) ((_logi).fl_csp.sp_bb_data)
+#define FNIC_LOGI_R_A_TOV(_logi) ((_logi).fl_csp.sp_r_a_tov)
+#define FNIC_LOGI_E_D_TOV(_logi) ((_logi).fl_csp.sp_e_d_tov)
+#define FNIC_LOGI_FEATURES(_logi) (be16_to_cpu((_logi).fl_csp.sp_features))
+#define FNIC_LOGI_PORT_NAME(_logi) ((_logi).fl_wwpn)
+#define FNIC_LOGI_NODE_NAME(_logi) ((_logi).fl_wwnn)
+
+#define FNIC_LOGI_SET_RDF_SIZE(_logi, _rdf_size) \
+	(FNIC_LOGI_RDF_SIZE(_logi) = cpu_to_be16(_rdf_size))
+#define FNIC_LOGI_SET_E_D_TOV(_logi, _e_d_tov) \
+	(FNIC_LOGI_E_D_TOV(_logi) = cpu_to_be32(_e_d_tov))
+#define FNIC_LOGI_SET_R_A_TOV(_logi, _r_a_tov) \
+	(FNIC_LOGI_R_A_TOV(_logi) = cpu_to_be32(_r_a_tov))
+
+#define FNIC_STD_SET_S_ID(_fchdr, _sid)        memcpy((_fchdr).fh_s_id, _sid, 3)
+#define FNIC_STD_SET_D_ID(_fchdr, _did)        memcpy((_fchdr).fh_d_id, _did, 3)
+#define FNIC_STD_SET_OX_ID(_fchdr, _oxid)      ((_fchdr).fh_ox_id = cpu_to_be16(_oxid))
+#define FNIC_STD_SET_RX_ID(_fchdr, _rxid)      ((_fchdr).fh_rx_id = cpu_to_be16(_rxid))
+
+#define FNIC_STD_SET_R_CTL(_fchdr, _rctl)	((_fchdr).fh_r_ctl = _rctl)
+#define FNIC_STD_SET_TYPE(_fchdr, _type)	((_fchdr).fh_type = _type)
+#define FNIC_STD_SET_F_CTL(_fchdr, _fctl) \
+	put_unaligned_be24(_fctl, &((_fchdr).fh_f_ctl))
+
+#define FNIC_STD_SET_NPORT_NAME(_ptr, _wwpn)	put_unaligned_be64(_wwpn, _ptr)
+#define FNIC_STD_SET_NODE_NAME(_ptr, _wwnn)	put_unaligned_be64(_wwnn, _ptr)
+#define FNIC_STD_SET_PORT_ID(__req, __portid) \
+	memcpy(__req.fr_fid.fp_fid, __portid, 3)
+#define FNIC_STD_SET_PORT_NAME(_req, _pName) \
+	(put_unaligned_be64(_pName, &_req.fr_wwn))
+
+#define FNIC_STD_GET_OX_ID(_fchdr)		(be16_to_cpu((_fchdr)->fh_ox_id))
+#define FNIC_STD_GET_RX_ID(_fchdr)		(be16_to_cpu((_fchdr)->fh_rx_id))
+#define FNIC_STD_GET_S_ID(_fchdr)		((_fchdr)->fh_s_id)
+#define FNIC_STD_GET_D_ID(_fchdr)		((_fchdr)->fh_d_id)
+#define FNIC_STD_GET_TYPE(_fchdr)		((_fchdr)->fh_type)
+#define FNIC_STD_GET_F_CTL(_fchdr)		((_fchdr)->fh_f_ctl)
+#define FNIC_STD_GET_R_CTL(_fchdr)		((_fchdr)->fh_r_ctl)
+
+#define FNIC_STD_GET_FC_CT_CMD(__fcct_hdr)  (be16_to_cpu(__fcct_hdr->ct_cmd))
+
+#define FNIC_FCOE_MAX_FRAME_SZ  (2048)
+#define FNIC_FCOE_MIN_FRAME_SZ  (280)
+#define FNIC_FC_MAX_PAYLOAD_LEN (2048)
+#define FNIC_MIN_DATA_FIELD_SIZE  (256)
+
+#define FNIC_FC_EDTOV_NSEC    (0x400)
+#define FNIC_NSEC_TO_MSEC     (0x1000000)
+#define FCP_PRLI_FUNC_TARGET	(0x0010)
+
+#define FNIC_FC_R_CTL_SOLICITED_DATA			(0x21)
+#define FNIC_FC_F_CTL_LAST_END_SEQ				(0x98)
+#define FNIC_FC_F_CTL_LAST_END_SEQ_INT			(0x99)
+#define FNIC_FC_F_CTL_FIRST_LAST_SEQINIT		(0x29)
+#define FNIC_FC_R_CTL_FC4_SCTL					(0x03)
+#define FNIC_FC_CS_CTL							(0x00)
+
+#define FNIC_FC_FRAME_UNSOLICITED(_fchdr)				\
+		(_fchdr->fh_r_ctl == FC_RCTL_ELS_REQ)
+#define FNIC_FC_FRAME_SOLICITED_DATA(_fchdr)			\
+		(_fchdr->fh_r_ctl == FNIC_FC_R_CTL_SOLICITED_DATA)
+#define FNIC_FC_FRAME_SOLICITED_CTRL_REPLY(_fchdr)		\
+		(_fchdr->fh_r_ctl == FC_RCTL_ELS_REP)
+#define FNIC_FC_FRAME_FCTL_LAST_END_SEQ(_fchdr)			\
+		(_fchdr->fh_f_ctl[0] == FNIC_FC_F_CTL_LAST_END_SEQ)
+#define FNIC_FC_FRAME_FCTL_LAST_END_SEQ_INT(_fchdr)		\
+		(_fchdr->fh_f_ctl[0] == FNIC_FC_F_CTL_LAST_END_SEQ_INT)
+#define FNIC_FC_FRAME_FCTL_FIRST_LAST_SEQINIT(_fchdr)	\
+		(_fchdr->fh_f_ctl[0] == FNIC_FC_F_CTL_FIRST_LAST_SEQINIT)
+#define FNIC_FC_FRAME_FC4_SCTL(_fchdr)					\
+		(_fchdr->fh_r_ctl == FNIC_FC_R_CTL_FC4_SCTL)
+#define FNIC_FC_FRAME_TYPE_BLS(_fchdr) (_fchdr->fh_type == FC_TYPE_BLS)
+#define FNIC_FC_FRAME_TYPE_ELS(_fchdr) (_fchdr->fh_type == FC_TYPE_ELS)
+#define FNIC_FC_FRAME_TYPE_FC_GS(_fchdr) (_fchdr->fh_type == FC_TYPE_CT)
+#define FNIC_FC_FRAME_CS_CTL(_fchdr) (_fchdr->fh_cs_ctl == FNIC_FC_CS_CTL)
+
+#define FNIC_FC_C3_RDF         (0xfff)
+#define FNIC_FC_PLOGI_RSP_RDF(_plogi_rsp) \
+	(min(_plogi_rsp->u.csp_plogi.b2b_rdf_size, \
+	(_plogi_rsp->spc3[4] & FNIC_FC_C3_RDF)))
+#define FNIC_FC_PLOGI_RSP_CONCUR_SEQ(_plogi_rsp) \
+	(min((uint16_t) (be16_to_cpu(_plogi_rsp->els.fl_csp.sp_tot_seq)), \
+	 (uint16_t) (be16_to_cpu(_plogi_rsp->els.fl_cssp[2].cp_con_seq) & 0xff)))
+
+/* FLOGI/PLOGI struct */
+struct fc_std_flogi {
+	struct fc_frame_header fchdr;
+	struct fc_els_flogi els;
+} __packed;
+
+struct fc_std_els_acc_rsp {
+	struct fc_frame_header fchdr;
+	struct fc_els_ls_acc acc;
+} __packed;
+
+struct fc_std_els_rjt_rsp {
+	struct fc_frame_header fchdr;
+	struct fc_els_ls_rjt rej;
+} __packed;
+
+struct fc_std_els_adisc {
+	struct fc_frame_header fchdr;
+	struct fc_els_adisc els;
+} __packed;
+
+struct fc_std_rls_acc {
+	struct fc_frame_header fchdr;
+	struct fc_els_rls_resp els;
+} __packed;
+
+struct fc_std_abts_ba_acc {
+	struct fc_frame_header fchdr;
+	struct fc_ba_acc acc;
+} __packed;
+
+struct fc_std_abts_ba_rjt {
+	struct fc_frame_header fchdr;
+	struct fc_ba_rjt rjt;
+} __packed;
+
+struct fc_std_els_prli {
+	struct fc_frame_header fchdr;
+	struct fc_els_prli els_prli;
+	struct fc_els_spp sp;
+}	 __packed;
+
+struct fc_std_rpn_id {
+	struct fc_frame_header fchdr;
+	struct fc_ct_hdr fc_std_ct_hdr;
+	struct fc_ns_rn_id rpn_id;
+} __packed;
+
+struct fc_std_fdmi_rhba {
+	struct fc_frame_header fchdr;
+	struct fc_ct_hdr fc_std_ct_hdr;
+	struct fc_fdmi_rhba rhba;
+} __packed;
+
+struct fc_std_fdmi_rpa {
+	struct fc_frame_header fchdr;
+	struct fc_ct_hdr fc_std_ct_hdr;
+	struct fc_fdmi_rpa rpa;
+}	 __packed;
+
+struct fc_std_rft_id {
+	struct fc_frame_header fchdr;
+	struct fc_ct_hdr fc_std_ct_hdr;
+	struct fc_ns_rft_id rft_id;
+} __packed;
+
+struct fc_std_rff_id {
+	struct fc_frame_header fchdr;
+	struct fc_ct_hdr fc_std_ct_hdr;
+	struct fc_ns_rff_id rff_id;
+} __packed;
+
+struct fc_std_gpn_ft {
+	struct fc_frame_header fchdr;
+	struct fc_ct_hdr fc_std_ct_hdr;
+	struct fc_ns_gid_ft gpn_ft;
+} __packed;
+
+/* Accept CT_IU	for	GPN_FT	*/
+struct fc_gpn_ft_rsp_iu {
+	uint8_t		ctrl;
+	uint8_t		fcid[3];
+	uint32_t	rsvd;
+	__be64		wwpn;
+} __packed;
+
+struct fc_std_rls {
+	struct fc_frame_header fchdr;
+	struct fc_els_rls els;
+} __packed;
+
+struct fc_std_scr {
+	struct fc_frame_header fchdr;
+	struct fc_els_scr scr;
+} __packed;
+
+struct fc_std_rscn {
+	struct fc_frame_header fchdr;
+	struct fc_els_rscn els;
+} __packed;
+
+struct fc_std_logo {
+	struct fc_frame_header fchdr;
+	struct fc_els_logo els;
+} __packed;
+
+#define	FNIC_ETH_FCOE_HDRS_OFFSET	\
+	(sizeof(struct ethhdr) + sizeof(struct fcoe_hdr))
+
+#endif	/*	_FDLS_FC_H	*/
diff --git a/drivers/scsi/fnic/fip.c b/drivers/scsi/fnic/fip.c
new file mode 100644
index 000000000000..7bb85949033f
--- /dev/null
+++ b/drivers/scsi/fnic/fip.c
@@ -0,0 +1,1005 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
+ * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
+ */
+#include "fnic.h"
+#include "fip.h"
+#include <linux/etherdevice.h>
+
+#define FIP_FNIC_RESET_WAIT_COUNT 15
+
+/**
+ * fnic_fcoe_reset_vlans - Free up the list of discovered vlans
+ * @fnic: Handle to fnic driver instance
+ */
+void fnic_fcoe_reset_vlans(struct fnic *fnic)
+{
+	unsigned long flags;
+	struct fcoe_vlan *vlan, *next;
+
+	spin_lock_irqsave(&fnic->vlans_lock, flags);
+	if (!list_empty(&fnic->vlan_list)) {
+		list_for_each_entry_safe(vlan, next, &fnic->vlan_list, list) {
+			list_del(&vlan->list);
+			kfree(vlan);
+		}
+	}
+
+	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "Reset vlan complete\n");
+}
+
+/**
+ * fnic_fcoe_send_vlan_req - Send FIP vlan request to all FCFs MAC
+ * @fnic: Handle to fnic driver instance
+ */
+void fnic_fcoe_send_vlan_req(struct fnic *fnic)
+{
+	uint8_t *frame;
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+	u64 vlan_tov;
+	struct fip_vlan_req *pvlan_req;
+	uint16_t frame_size = sizeof(struct fip_vlan_req);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send VLAN req");
+		return;
+	}
+
+	fnic_fcoe_reset_vlans(fnic);
+
+	fnic->set_vlan(fnic, 0);
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "set vlan done\n");
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "got MAC 0x%x:%x:%x:%x:%x:%x\n", iport->hwmac[0],
+		     iport->hwmac[1], iport->hwmac[2], iport->hwmac[3],
+		     iport->hwmac[4], iport->hwmac[5]);
+
+	pvlan_req = (struct fip_vlan_req *) frame;
+	*pvlan_req = (struct fip_vlan_req) {
+		.eth = {.h_dest = FCOE_ALL_FCFS_MAC,
+			.h_proto = cpu_to_be16(ETH_P_FIP)},
+		.fip = {.fip_ver = FIP_VER_ENCAPS(FIP_VER),
+			.fip_op = cpu_to_be16(FIP_OP_VLAN),
+			.fip_subcode = FIP_SC_REQ,
+			.fip_dl_len = cpu_to_be16(FIP_VLAN_REQ_LEN)},
+		.mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC,
+						.fip_dlen = 2}}
+	};
+
+	memcpy(pvlan_req->eth.h_source, iport->hwmac, ETH_ALEN);
+	memcpy(pvlan_req->mac_desc.fd_mac, iport->hwmac, ETH_ALEN);
+
+	atomic64_inc(&fnic_stats->vlan_stats.vlan_disc_reqs);
+
+	iport->fip.state = FDLS_FIP_VLAN_DISCOVERY_STARTED;
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "Send VLAN req\n");
+	fnic_send_fip_frame(iport, frame, frame_size);
+
+	vlan_tov = jiffies + msecs_to_jiffies(FCOE_CTLR_FIPVLAN_TOV);
+	mod_timer(&fnic->retry_fip_timer, round_jiffies(vlan_tov));
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "fip timer set\n");
+}
+
+/**
+ * fnic_fcoe_process_vlan_resp - Processes the vlan response from one FCF and
+ * populates VLAN list.
+ * @fnic: Handle to fnic driver instance
+ * @fiph: Received FIP frame
+ *
+ * Will wait for responses from multiple FCFs until timeout.
+ */
+void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct fip_header *fiph)
+{
+	struct fip_vlan_notif *vlan_notif = (struct fip_vlan_notif *)fiph;
+
+	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+	u16 vid;
+	int num_vlan = 0;
+	int cur_desc, desc_len;
+	struct fcoe_vlan *vlan;
+	struct fip_vlan_desc *vlan_desc;
+	unsigned long flags;
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "fnic 0x%p got vlan resp\n", fnic);
+
+	desc_len = be16_to_cpu(vlan_notif->fip.fip_dl_len);
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "desc_len %d\n", desc_len);
+
+	spin_lock_irqsave(&fnic->vlans_lock, flags);
+
+	cur_desc = 0;
+	while (desc_len > 0) {
+		vlan_desc =
+		    (struct fip_vlan_desc *)(((char *)vlan_notif->vlans_desc)
+					       + cur_desc * 4);
+
+		if (vlan_desc->fd_desc.fip_dtype == FIP_DT_VLAN) {
+			if (vlan_desc->fd_desc.fip_dlen != 1) {
+				FNIC_FIP_DBG(KERN_INFO, fnic->host,
+					     fnic->fnic_num,
+					     "Invalid descriptor length(%x) in VLan response\n",
+					     vlan_desc->fd_desc.fip_dlen);
+
+			}
+			num_vlan++;
+			vid = be16_to_cpu(vlan_desc->fd_vlan);
+			FNIC_FIP_DBG(KERN_INFO, fnic->host,
+				     fnic->fnic_num,
+				     "process_vlan_resp: FIP VLAN %d\n", vid);
+			vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+
+			if (!vlan) {
+				/* retry from timer */
+				FNIC_FIP_DBG(KERN_INFO, fnic->host,
+					     fnic->fnic_num,
+					     "Mem Alloc failure\n");
+				spin_unlock_irqrestore(&fnic->vlans_lock,
+						       flags);
+				goto out;
+			}
+			vlan->vid = vid & 0x0fff;
+			vlan->state = FIP_VLAN_AVAIL;
+			list_add_tail(&vlan->list, &fnic->vlan_list);
+			break;
+		}
+		FNIC_FIP_DBG(KERN_INFO, fnic->host,
+			     fnic->fnic_num,
+			     "Invalid descriptor type(%x) in VLan response\n",
+			     vlan_desc->fd_desc.fip_dtype);
+		/*
+		 * Note : received a type=2 descriptor here i.e. FIP
+		 * MAC Address Descriptor
+		 */
+		cur_desc += vlan_desc->fd_desc.fip_dlen;
+		desc_len -= vlan_desc->fd_desc.fip_dlen;
+	}
+
+	/* any VLAN descriptors present ? */
+	if (num_vlan == 0) {
+		atomic64_inc(&fnic_stats->vlan_stats.resp_withno_vlanID);
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "fnic 0x%p No VLAN descriptors in FIP VLAN response\n",
+			     fnic);
+	}
+
+	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
+
+ out:
+	return;
+}
+
+/**
+ * fnic_fcoe_start_fcf_discovery - Start FIP FCF discovery in a selected vlan
+ * @fnic: Handle to fnic driver instance
+ */
+void fnic_fcoe_start_fcf_discovery(struct fnic *fnic)
+{
+	uint8_t *frame;
+	struct fnic_iport_s *iport = &fnic->iport;
+	u64 fcs_tov;
+	struct fip_discovery *pdisc_sol;
+	uint16_t frame_size = sizeof(struct fip_discovery);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to start FCF discovery");
+		return;
+	}
+
+	memset(iport->selected_fcf.fcf_mac, 0, ETH_ALEN);
+
+	pdisc_sol = (struct fip_discovery *) frame;
+	*pdisc_sol = (struct fip_discovery) {
+		.eth = {.h_dest = FCOE_ALL_FCFS_MAC,
+			.h_proto = cpu_to_be16(ETH_P_FIP)},
+		.fip = {
+			.fip_ver = FIP_VER_ENCAPS(FIP_VER), .fip_op = cpu_to_be16(FIP_OP_DISC),
+			.fip_subcode = FIP_SC_REQ, .fip_dl_len = cpu_to_be16(FIP_DISC_SOL_LEN),
+			.fip_flags = cpu_to_be16(FIP_FL_FPMA)},
+		.mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}},
+		.name_desc = {.fd_desc = {.fip_dtype = FIP_DT_NAME, .fip_dlen = 3}},
+		.fcoe_desc = {.fd_desc = {.fip_dtype = FIP_DT_FCOE_SIZE, .fip_dlen = 1},
+			      .fd_size = cpu_to_be16(FCOE_MAX_SIZE)}
+	};
+
+	memcpy(pdisc_sol->eth.h_source, iport->hwmac, ETH_ALEN);
+	memcpy(pdisc_sol->mac_desc.fd_mac, iport->hwmac, ETH_ALEN);
+	iport->selected_fcf.fcf_priority = 0xFF;
+
+	FNIC_STD_SET_NODE_NAME(&pdisc_sol->name_desc.fd_wwn, iport->wwnn);
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "Start FCF discovery\n");
+	fnic_send_fip_frame(iport, frame, frame_size);
+
+	iport->fip.state = FDLS_FIP_FCF_DISCOVERY_STARTED;
+
+	fcs_tov = jiffies + msecs_to_jiffies(FCOE_CTLR_FCS_TOV);
+	mod_timer(&fnic->retry_fip_timer, round_jiffies(fcs_tov));
+}
+
+/**
+ * fnic_fcoe_fip_discovery_resp - Processes FCF advertisements.
+ * @fnic: Handle to fnic driver instance
+ * @fiph: Received frame
+ *
+ * FCF advertisements can be:
+ * solicited - Sent in response of a discover FCF FIP request
+ * Store the information of the FCF with highest priority.
+ * Wait until timeout in case of multiple FCFs.
+ *
+ * unsolicited - Sent periodically by the FCF for keep alive.
+ * If FLOGI is in progress or completed and the advertisement is
+ * received by our selected FCF, refresh the keep alive timer.
+ */
+void fnic_fcoe_fip_discovery_resp(struct fnic *fnic, struct fip_header *fiph)
+{
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fip_disc_adv *disc_adv = (struct fip_disc_adv *)fiph;
+	u64 fcs_ka_tov;
+	u64 tov;
+	int fka_has_changed;
+
+	switch (iport->fip.state) {
+	case FDLS_FIP_FCF_DISCOVERY_STARTED:
+		if (be16_to_cpu(disc_adv->fip.fip_flags) & FIP_FL_SOL) {
+			FNIC_FIP_DBG(KERN_INFO, fnic->host,
+				     fnic->fnic_num,
+				     "fnic 0x%p Solicited adv\n", fnic);
+
+			if ((disc_adv->prio_desc.fd_pri <
+			     iport->selected_fcf.fcf_priority)
+			    && (be16_to_cpu(disc_adv->fip.fip_flags) & FIP_FL_AVAIL)) {
+
+				FNIC_FIP_DBG(KERN_INFO, fnic->host,
+					     fnic->fnic_num,
+					     "fnic 0x%p FCF Available\n", fnic);
+				memcpy(iport->selected_fcf.fcf_mac,
+				       disc_adv->mac_desc.fd_mac, ETH_ALEN);
+				iport->selected_fcf.fcf_priority =
+				    disc_adv->prio_desc.fd_pri;
+				iport->selected_fcf.fka_adv_period =
+				    be32_to_cpu(disc_adv->fka_adv_desc.fd_fka_period);
+				FNIC_FIP_DBG(KERN_INFO, fnic->host,
+					     fnic->fnic_num, "adv time %d",
+					     iport->selected_fcf.fka_adv_period);
+				iport->selected_fcf.ka_disabled =
+				    (disc_adv->fka_adv_desc.fd_flags & 1);
+			}
+		}
+		break;
+	case FDLS_FIP_FLOGI_STARTED:
+	case FDLS_FIP_FLOGI_COMPLETE:
+		if (!(be16_to_cpu(disc_adv->fip.fip_flags) & FIP_FL_SOL)) {
+			/* same fcf */
+			if (memcmp
+			    (iport->selected_fcf.fcf_mac,
+			     disc_adv->mac_desc.fd_mac, ETH_ALEN) == 0) {
+				if (iport->selected_fcf.fka_adv_period !=
+				    be32_to_cpu(disc_adv->fka_adv_desc.fd_fka_period)) {
+					iport->selected_fcf.fka_adv_period =
+					    be32_to_cpu(disc_adv->fka_adv_desc.fd_fka_period);
+					FNIC_FIP_DBG(KERN_INFO,
+						     fnic->host,
+						     fnic->fnic_num,
+						     "change fka to %d",
+						     iport->selected_fcf.fka_adv_period);
+				}
+
+				fka_has_changed =
+				    (iport->selected_fcf.ka_disabled == 1)
+				    && ((disc_adv->fka_adv_desc.fd_flags & 1) ==
+					0);
+
+				iport->selected_fcf.ka_disabled =
+				    (disc_adv->fka_adv_desc.fd_flags & 1);
+				if (!((iport->selected_fcf.ka_disabled)
+				      || (iport->selected_fcf.fka_adv_period ==
+					  0))) {
+
+					fcs_ka_tov = jiffies
+					    + 3
+					    *
+					    msecs_to_jiffies(iport->selected_fcf.fka_adv_period);
+					mod_timer(&fnic->fcs_ka_timer,
+						  round_jiffies(fcs_ka_tov));
+				} else {
+					if (timer_pending(&fnic->fcs_ka_timer))
+						del_timer_sync(&fnic->fcs_ka_timer);
+				}
+
+				if (fka_has_changed) {
+					if (iport->selected_fcf.fka_adv_period != 0) {
+						tov =
+						 jiffies +
+						 msecs_to_jiffies(
+							 iport->selected_fcf.fka_adv_period);
+						mod_timer(&fnic->enode_ka_timer,
+							  round_jiffies(tov));
+
+						tov =
+						    jiffies +
+						    msecs_to_jiffies
+						    (FIP_VN_KA_PERIOD);
+						mod_timer(&fnic->vn_ka_timer,
+							  round_jiffies(tov));
+					}
+				}
+			}
+		}
+		break;
+	default:
+		break;
+	}			/* end switch */
+}
+
+/**
+ * fnic_fcoe_start_flogi - Send FIP FLOGI to the selected FCF
+ * @fnic: Handle to fnic driver instance
+ */
+void fnic_fcoe_start_flogi(struct fnic *fnic)
+{
+	uint8_t *frame;
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fip_flogi *pflogi_req;
+	u64 flogi_tov;
+	uint16_t oxid;
+	uint16_t frame_size = sizeof(struct fip_flogi);
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to start FIP FLOGI");
+		return;
+	}
+
+	pflogi_req = (struct fip_flogi *) frame;
+	*pflogi_req = (struct fip_flogi) {
+		.eth = {
+			.h_proto = cpu_to_be16(ETH_P_FIP)},
+		.fip = {
+			.fip_ver = FIP_VER_ENCAPS(FIP_VER),
+			.fip_op = cpu_to_be16(FIP_OP_LS),
+			.fip_subcode = FIP_SC_REQ,
+			.fip_dl_len = cpu_to_be16(FIP_FLOGI_LEN),
+			.fip_flags = cpu_to_be16(FIP_FL_FPMA)},
+		.flogi_desc = {
+				.fd_desc = {.fip_dtype = FIP_DT_FLOGI, .fip_dlen = 36},
+			       .flogi = {
+					 .fchdr = {
+						   .fh_r_ctl = FC_RCTL_ELS_REQ,
+						   .fh_d_id = {0xFF, 0xFF, 0xFE},
+						   .fh_type = FC_TYPE_ELS,
+						   .fh_f_ctl = {FNIC_ELS_REQ_FCTL, 0, 0},
+						   .fh_rx_id = cpu_to_be16(FNIC_UNASSIGNED_RXID)},
+					 .els = {
+						 .fl_cmd = ELS_FLOGI,
+						 .fl_csp = {
+							    .sp_hi_ver =
+							    FNIC_FC_PH_VER_HI,
+							    .sp_lo_ver =
+							    FNIC_FC_PH_VER_LO,
+							    .sp_bb_cred =
+							    cpu_to_be16
+							    (FNIC_FC_B2B_CREDIT),
+							    .sp_bb_data =
+							    cpu_to_be16
+							    (FNIC_FC_B2B_RDF_SZ)},
+						 .fl_cssp[2].cp_class =
+						 cpu_to_be16(FC_CPC_VALID | FC_CPC_SEQ)
+						},
+					}
+			},
+		.mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}}
+	};
+
+	memcpy(pflogi_req->eth.h_source, iport->hwmac, ETH_ALEN);
+	if (iport->usefip)
+		memcpy(pflogi_req->eth.h_dest, iport->selected_fcf.fcf_mac,
+		       ETH_ALEN);
+
+	oxid = fdls_alloc_oxid(iport, FNIC_FRAME_TYPE_FABRIC_FLOGI,
+		&iport->active_oxid_fabric_req);
+	if (oxid == FNIC_UNASSIGNED_OXID) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "Failed to allocate OXID to send FIP FLOGI");
+		mempool_free(frame, fnic->frame_pool);
+		return;
+	}
+	FNIC_STD_SET_OX_ID(pflogi_req->flogi_desc.flogi.fchdr, oxid);
+
+	FNIC_STD_SET_NPORT_NAME(&pflogi_req->flogi_desc.flogi.els.fl_wwpn,
+			iport->wwpn);
+	FNIC_STD_SET_NODE_NAME(&pflogi_req->flogi_desc.flogi.els.fl_wwnn,
+			iport->wwnn);
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "FIP start FLOGI\n");
+	fnic_send_fip_frame(iport, frame, frame_size);
+	iport->fip.flogi_retry++;
+
+	iport->fip.state = FDLS_FIP_FLOGI_STARTED;
+	flogi_tov = jiffies + msecs_to_jiffies(fnic->config.flogi_timeout);
+	mod_timer(&fnic->retry_fip_timer, round_jiffies(flogi_tov));
+}
+
+/**
+ * fnic_fcoe_process_flogi_resp - Processes FLOGI response from FCF.
+ * @fnic: Handle to fnic driver instance
+ * @fiph: Received frame
+ *
+ * If successful save assigned fc_id and MAC, program firmware
+ * and start fdls discovery, else restart vlan discovery.
+ */
+void fnic_fcoe_process_flogi_resp(struct fnic *fnic, struct fip_header *fiph)
+{
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fip_flogi_rsp *flogi_rsp = (struct fip_flogi_rsp *)fiph;
+	int desc_len;
+	uint32_t s_id;
+	int frame_type;
+	uint16_t oxid;
+
+	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+	struct fc_frame_header *fchdr = &flogi_rsp->rsp_desc.flogi.fchdr;
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "fnic 0x%p FIP FLOGI rsp\n", fnic);
+	desc_len = be16_to_cpu(flogi_rsp->fip.fip_dl_len);
+	if (desc_len != 38) {
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "Invalid Descriptor List len (%x). Dropping frame\n",
+			     desc_len);
+		return;
+	}
+
+	if (!((flogi_rsp->rsp_desc.fd_desc.fip_dtype == 7)
+	      && (flogi_rsp->rsp_desc.fd_desc.fip_dlen == 36))
+	    || !((flogi_rsp->mac_desc.fd_desc.fip_dtype == 2)
+		 && (flogi_rsp->mac_desc.fd_desc.fip_dlen == 2))) {
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "Dropping frame invalid type and len mix\n");
+		return;
+	}
+
+	frame_type = fnic_fdls_validate_and_get_frame_type(iport, fchdr);
+
+	s_id = ntoh24(fchdr->fh_s_id);
+	if ((fchdr->fh_f_ctl[0] != 0x98)
+	    || (fchdr->fh_r_ctl != 0x23)
+	    || (s_id != FC_FID_FLOGI)
+	    || (frame_type != FNIC_FABRIC_FLOGI_RSP)
+	    || (fchdr->fh_type != 0x01)) {
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "Dropping invalid frame: s_id %x F %x R %x t %x OX_ID %x\n",
+			     s_id, fchdr->fh_f_ctl[0], fchdr->fh_r_ctl,
+			     fchdr->fh_type, FNIC_STD_GET_OX_ID(fchdr));
+		return;
+	}
+
+	if (iport->fip.state == FDLS_FIP_FLOGI_STARTED) {
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "fnic 0x%p rsp for pending FLOGI\n", fnic);
+
+		oxid = FNIC_STD_GET_OX_ID(fchdr);
+		fdls_free_oxid(iport, oxid, &iport->active_oxid_fabric_req);
+		del_timer_sync(&fnic->retry_fip_timer);
+
+		if ((be16_to_cpu(flogi_rsp->fip.fip_dl_len) == FIP_FLOGI_LEN)
+		    && (flogi_rsp->rsp_desc.flogi.els.fl_cmd == ELS_LS_ACC)) {
+
+			FNIC_FIP_DBG(KERN_INFO, fnic->host,
+				     fnic->fnic_num,
+				     "fnic 0x%p FLOGI success\n", fnic);
+			memcpy(iport->fpma, flogi_rsp->mac_desc.fd_mac, ETH_ALEN);
+			iport->fcid =
+			    ntoh24(flogi_rsp->rsp_desc.flogi.fchdr.fh_d_id);
+
+			iport->r_a_tov =
+			    be32_to_cpu(flogi_rsp->rsp_desc.flogi.els.fl_csp.sp_r_a_tov);
+			iport->e_d_tov =
+			    be32_to_cpu(flogi_rsp->rsp_desc.flogi.els.fl_csp.sp_e_d_tov);
+			memcpy(fnic->iport.fcfmac, iport->selected_fcf.fcf_mac,
+			       ETH_ALEN);
+			vnic_dev_add_addr(fnic->vdev, flogi_rsp->mac_desc.fd_mac);
+
+			if (fnic_fdls_register_portid(iport, iport->fcid, NULL)
+			    != 0) {
+				FNIC_FIP_DBG(KERN_INFO, fnic->host,
+					     fnic->fnic_num,
+					     "fnic 0x%p flogi registration failed\n",
+					     fnic);
+				return;
+			}
+
+			iport->fip.state = FDLS_FIP_FLOGI_COMPLETE;
+			iport->state = FNIC_IPORT_STATE_FABRIC_DISC;
+			FNIC_FIP_DBG(KERN_INFO, fnic->host,
+				     fnic->fnic_num, "iport->state:%d\n",
+				     iport->state);
+			fnic_fdls_disc_start(iport);
+			if (!((iport->selected_fcf.ka_disabled)
+			      || (iport->selected_fcf.fka_adv_period == 0))) {
+				u64 tov;
+
+				tov = jiffies
+				    +
+				    msecs_to_jiffies(iport->selected_fcf.fka_adv_period);
+				mod_timer(&fnic->enode_ka_timer,
+					  round_jiffies(tov));
+
+				tov =
+				    jiffies +
+				    msecs_to_jiffies(FIP_VN_KA_PERIOD);
+				mod_timer(&fnic->vn_ka_timer,
+					  round_jiffies(tov));
+
+			}
+		} else {
+			/*
+			 * If there's FLOGI rejects - clear all
+			 * fcf's & restart from scratch
+			 */
+			atomic64_inc(&fnic_stats->vlan_stats.flogi_rejects);
+			/* start FCoE VLAN discovery */
+			fnic_fcoe_send_vlan_req(fnic);
+
+			iport->fip.state = FDLS_FIP_VLAN_DISCOVERY_STARTED;
+		}
+	}
+}
+
+/**
+ * fnic_common_fip_cleanup - Clean up FCF info and timers in case of
+ * link down/CVL
+ * @fnic: Handle to fnic driver instance
+ */
+void fnic_common_fip_cleanup(struct fnic *fnic)
+{
+
+	struct fnic_iport_s *iport = &fnic->iport;
+
+	if (!iport->usefip)
+		return;
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "fnic 0x%p fip cleanup\n", fnic);
+
+	iport->fip.state = FDLS_FIP_INIT;
+
+	del_timer_sync(&fnic->retry_fip_timer);
+	del_timer_sync(&fnic->fcs_ka_timer);
+	del_timer_sync(&fnic->enode_ka_timer);
+	del_timer_sync(&fnic->vn_ka_timer);
+
+	if (!is_zero_ether_addr(iport->fpma))
+		vnic_dev_del_addr(fnic->vdev, iport->fpma);
+
+	memset(iport->fpma, 0, ETH_ALEN);
+	iport->fcid = 0;
+	iport->r_a_tov = 0;
+	iport->e_d_tov = 0;
+	memset(fnic->iport.fcfmac, 0, ETH_ALEN);
+	memset(iport->selected_fcf.fcf_mac, 0, ETH_ALEN);
+	iport->selected_fcf.fcf_priority = 0;
+	iport->selected_fcf.fka_adv_period = 0;
+	iport->selected_fcf.ka_disabled = 0;
+
+	fnic_fcoe_reset_vlans(fnic);
+}
+
+/**
+ * fnic_fcoe_process_cvl - Processes Clear Virtual Link from FCF.
+ * @fnic: Handle to fnic driver instance
+ * @fiph: Received frame
+ *
+ * Verify that cvl is received from our current FCF for our assigned MAC
+ * and clean up and restart the vlan discovery.
+ */
+void fnic_fcoe_process_cvl(struct fnic *fnic, struct fip_header *fiph)
+{
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fip_cvl *cvl_msg = (struct fip_cvl *)fiph;
+	int i;
+	int found = false;
+	int max_count = 0;
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "fnic 0x%p clear virtual link handler\n", fnic);
+
+	if (!((cvl_msg->fcf_mac_desc.fd_desc.fip_dtype == 2)
+	      && (cvl_msg->fcf_mac_desc.fd_desc.fip_dlen == 2))
+	    || !((cvl_msg->name_desc.fd_desc.fip_dtype == 4)
+		 && (cvl_msg->name_desc.fd_desc.fip_dlen == 3))) {
+
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "invalid mix: ft %x fl %x ndt %x ndl %x",
+			     cvl_msg->fcf_mac_desc.fd_desc.fip_dtype,
+			     cvl_msg->fcf_mac_desc.fd_desc.fip_dlen,
+				 cvl_msg->name_desc.fd_desc.fip_dtype,
+			     cvl_msg->name_desc.fd_desc.fip_dlen);
+	}
+
+	if (memcmp
+	    (iport->selected_fcf.fcf_mac, cvl_msg->fcf_mac_desc.fd_mac, ETH_ALEN)
+	    == 0) {
+		for (i = 0; i < ((be16_to_cpu(fiph->fip_dl_len) / 5) - 1); i++) {
+			if (!((cvl_msg->vn_ports_desc[i].fd_desc.fip_dtype == 11)
+			      && (cvl_msg->vn_ports_desc[i].fd_desc.fip_dlen == 5))) {
+
+				FNIC_FIP_DBG(KERN_INFO, fnic->host,
+					     fnic->fnic_num,
+					     "Invalid type and len mix type: %d len: %d\n",
+					     cvl_msg->vn_ports_desc[i].fd_desc.fip_dtype,
+					     cvl_msg->vn_ports_desc[i].fd_desc.fip_dlen);
+			}
+			if (memcmp
+			    (iport->fpma, cvl_msg->vn_ports_desc[i].fd_mac,
+			     ETH_ALEN) == 0) {
+				found = true;
+				break;
+			}
+		}
+		if (!found)
+			return;
+		fnic_common_fip_cleanup(fnic);
+
+		while (fnic->reset_in_progress == IN_PROGRESS) {
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			wait_for_completion_timeout(&fnic->reset_completion_wait,
+							msecs_to_jiffies(5000));
+			spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+			max_count++;
+			if (max_count >= FIP_FNIC_RESET_WAIT_COUNT) {
+				FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Rthr waited too long. Skipping handle link event %p\n",
+					 fnic);
+				return;
+			}
+			FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "fnic reset in progress. Link event needs to wait %p",
+				 fnic);
+		}
+		fnic->reset_in_progress = IN_PROGRESS;
+		fnic_fdls_link_down(iport);
+		fnic->reset_in_progress = NOT_IN_PROGRESS;
+		complete(&fnic->reset_completion_wait);
+		fnic_fcoe_send_vlan_req(fnic);
+	}
+}
+
+/**
+ * fdls_fip_recv_frame - Demultiplexer for FIP frames
+ * @fnic: Handle to fnic driver instance
+ * @frame: Received ethernet frame
+ */
+int fdls_fip_recv_frame(struct fnic *fnic, void *frame)
+{
+	struct ethhdr *eth = (struct ethhdr *)frame;
+	struct fip_header *fiph;
+	u16 op;
+	u8 sub;
+	int len = 2048;
+
+	if (be16_to_cpu(eth->h_proto) == ETH_P_FIP) {
+		fiph = (struct fip_header *)(eth + 1);
+		op = be16_to_cpu(fiph->fip_op);
+		sub = fiph->fip_subcode;
+
+		fnic_debug_dump_fip_frame(fnic, eth, len, "Incoming");
+
+		if (op == FIP_OP_DISC && sub == FIP_SC_REP)
+			fnic_fcoe_fip_discovery_resp(fnic, fiph);
+		else if (op == FIP_OP_VLAN && sub == FIP_SC_REP)
+			fnic_fcoe_process_vlan_resp(fnic, fiph);
+		else if (op == FIP_OP_CTRL && sub == FIP_SC_REP)
+			fnic_fcoe_process_cvl(fnic, fiph);
+		else if (op == FIP_OP_LS && sub == FIP_SC_REP)
+			fnic_fcoe_process_flogi_resp(fnic, fiph);
+
+		/* Return true if the frame was a FIP frame */
+		return true;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		"Not a FIP Frame");
+	return false;
+}
+
+void fnic_work_on_fip_timer(struct work_struct *work)
+{
+	struct fnic *fnic = container_of(work, struct fnic, fip_timer_work);
+	struct fnic_iport_s *iport = &fnic->iport;
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "FIP timeout\n");
+
+	if (iport->fip.state == FDLS_FIP_VLAN_DISCOVERY_STARTED) {
+		fnic_vlan_discovery_timeout(fnic);
+	} else if (iport->fip.state == FDLS_FIP_FCF_DISCOVERY_STARTED) {
+		u8 zmac[ETH_ALEN] = { 0, 0, 0, 0, 0, 0 };
+
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "FCF Discovery timeout\n");
+		if (memcmp(iport->selected_fcf.fcf_mac, zmac, ETH_ALEN) != 0) {
+
+			if (iport->flags & FNIC_FIRST_LINK_UP) {
+				fnic_scsi_fcpio_reset(iport->fnic);
+				iport->flags &= ~FNIC_FIRST_LINK_UP;
+			}
+
+			fnic_fcoe_start_flogi(fnic);
+			if (!((iport->selected_fcf.ka_disabled)
+			      || (iport->selected_fcf.fka_adv_period == 0))) {
+				u64 fcf_tov;
+
+				fcf_tov = jiffies
+				    + 3
+				    *
+				    msecs_to_jiffies(iport->selected_fcf.fka_adv_period);
+				mod_timer(&fnic->fcs_ka_timer,
+					  round_jiffies(fcf_tov));
+			}
+		} else {
+			FNIC_FIP_DBG(KERN_INFO, fnic->host,
+				     fnic->fnic_num, "FCF Discovery timeout\n");
+			fnic_vlan_discovery_timeout(fnic);
+		}
+	} else if (iport->fip.state == FDLS_FIP_FLOGI_STARTED) {
+		fdls_schedule_oxid_free(iport, &iport->active_oxid_fabric_req);
+		FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			     "FLOGI timeout\n");
+		if (iport->fip.flogi_retry < fnic->config.flogi_retries)
+			fnic_fcoe_start_flogi(fnic);
+		else
+			fnic_vlan_discovery_timeout(fnic);
+	}
+}
+
+/**
+ * fnic_handle_fip_timer - Timeout handler for FIP discover phase.
+ * @t: Handle to the timer list
+ *
+ * Based on the current state, start next phase or restart discovery.
+ */
+void fnic_handle_fip_timer(struct timer_list *t)
+{
+	struct fnic *fnic = from_timer(fnic, t, retry_fip_timer);
+
+	INIT_WORK(&fnic->fip_timer_work, fnic_work_on_fip_timer);
+	queue_work(fnic_fip_queue, &fnic->fip_timer_work);
+}
+
+/**
+ * fnic_handle_enode_ka_timer - FIP node keep alive.
+ * @t: Handle to the timer list
+ */
+void fnic_handle_enode_ka_timer(struct timer_list *t)
+{
+	uint8_t *frame;
+	struct fnic *fnic = from_timer(fnic, t, enode_ka_timer);
+
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fip_enode_ka *penode_ka;
+	u64 enode_ka_tov;
+	uint16_t frame_size = sizeof(struct fip_enode_ka);
+
+	if (iport->fip.state != FDLS_FIP_FLOGI_COMPLETE)
+		return;
+
+	if ((iport->selected_fcf.ka_disabled)
+	    || (iport->selected_fcf.fka_adv_period == 0)) {
+		return;
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send enode ka");
+		return;
+	}
+
+	penode_ka = (struct fip_enode_ka *) frame;
+	*penode_ka = (struct fip_enode_ka) {
+		.eth = {
+			.h_proto = cpu_to_be16(ETH_P_FIP)},
+		.fip = {
+			.fip_ver = FIP_VER_ENCAPS(FIP_VER),
+			.fip_op = cpu_to_be16(FIP_OP_CTRL),
+			.fip_subcode = FIP_SC_REQ,
+			.fip_dl_len = cpu_to_be16(FIP_ENODE_KA_LEN)},
+		.mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}}
+	};
+
+	memcpy(penode_ka->eth.h_source, iport->hwmac, ETH_ALEN);
+	memcpy(penode_ka->eth.h_dest, iport->selected_fcf.fcf_mac, ETH_ALEN);
+	memcpy(penode_ka->mac_desc.fd_mac, iport->hwmac, ETH_ALEN);
+
+	FNIC_FIP_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		     "Handle enode KA timer\n");
+	fnic_send_fip_frame(iport, frame, frame_size);
+	enode_ka_tov = jiffies
+	    + msecs_to_jiffies(iport->selected_fcf.fka_adv_period);
+	mod_timer(&fnic->enode_ka_timer, round_jiffies(enode_ka_tov));
+}
+
+/**
+ * fnic_handle_vn_ka_timer - FIP virtual port keep alive.
+ * @t: Handle to the timer list
+ */
+void fnic_handle_vn_ka_timer(struct timer_list *t)
+{
+	uint8_t *frame;
+	struct fnic *fnic = from_timer(fnic, t, vn_ka_timer);
+
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fip_vn_port_ka *pvn_port_ka;
+	u64 vn_ka_tov;
+	uint8_t fcid[3];
+	uint16_t frame_size = sizeof(struct fip_vn_port_ka);
+
+	if (iport->fip.state != FDLS_FIP_FLOGI_COMPLETE)
+		return;
+
+	if ((iport->selected_fcf.ka_disabled)
+	    || (iport->selected_fcf.fka_adv_period == 0)) {
+		return;
+	}
+
+	frame = fdls_alloc_frame(iport);
+	if (frame == NULL) {
+		FNIC_FIP_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		     "Failed to allocate frame to send vn ka");
+		return;
+	}
+
+	pvn_port_ka = (struct fip_vn_port_ka *) frame;
+	*pvn_port_ka = (struct fip_vn_port_ka) {
+		.eth = {
+			.h_proto = cpu_to_be16(ETH_P_FIP)},
+		.fip = {
+			.fip_ver = FIP_VER_ENCAPS(FIP_VER),
+			.fip_op = cpu_to_be16(FIP_OP_CTRL),
+			.fip_subcode = FIP_SC_REQ,
+			.fip_dl_len = cpu_to_be16(FIP_VN_KA_LEN)},
+		.mac_desc = {.fd_desc = {.fip_dtype = FIP_DT_MAC, .fip_dlen = 2}},
+		.vn_port_desc = {.fd_desc = {.fip_dtype = FIP_DT_VN_ID, .fip_dlen = 5}}
+	};
+
+	memcpy(pvn_port_ka->eth.h_source, iport->fpma, ETH_ALEN);
+	memcpy(pvn_port_ka->eth.h_dest, iport->selected_fcf.fcf_mac, ETH_ALEN);
+	memcpy(pvn_port_ka->mac_desc.fd_mac, iport->hwmac, ETH_ALEN);
+	memcpy(pvn_port_ka->vn_port_desc.fd_mac, iport->fpma, ETH_ALEN);
+	hton24(fcid, iport->fcid);
+	memcpy(pvn_port_ka->vn_port_desc.fd_fc_id, fcid, 3);
+	FNIC_STD_SET_NPORT_NAME(&pvn_port_ka->vn_port_desc.fd_wwpn, iport->wwpn);
+
+	FNIC_FIP_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		     "Handle vnport KA timer\n");
+	fnic_send_fip_frame(iport, frame, frame_size);
+	vn_ka_tov = jiffies + msecs_to_jiffies(FIP_VN_KA_PERIOD);
+	mod_timer(&fnic->vn_ka_timer, round_jiffies(vn_ka_tov));
+}
+
+/**
+ * fnic_vlan_discovery_timeout - Handle vlan discovery timeout
+ * @fnic: Handle to fnic driver instance
+ *
+ * End of VLAN discovery or FCF discovery time window.
+ * Start the FCF discovery if VLAN was never used.
+ */
+void fnic_vlan_discovery_timeout(struct fnic *fnic)
+{
+	struct fcoe_vlan *vlan;
+	struct fnic_iport_s *iport = &fnic->iport;
+	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	if (fnic->stop_rx_link_events) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
+	if (!iport->usefip)
+		return;
+
+	spin_lock_irqsave(&fnic->vlans_lock, flags);
+	if (list_empty(&fnic->vlan_list)) {
+		/* no vlans available, try again */
+		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
+		fnic_fcoe_send_vlan_req(fnic);
+		return;
+	}
+
+	vlan = list_first_entry(&fnic->vlan_list, struct fcoe_vlan, list);
+
+	if (vlan->state == FIP_VLAN_SENT) {
+		if (vlan->sol_count >= FCOE_CTLR_MAX_SOL) {
+			/*
+			 * no response on this vlan, remove  from the list.
+			 * Try the next vlan
+			 */
+			list_del(&vlan->list);
+			kfree(vlan);
+			vlan = NULL;
+			if (list_empty(&fnic->vlan_list)) {
+				/* we exhausted all vlans, restart vlan disc */
+				spin_unlock_irqrestore(&fnic->vlans_lock,
+						       flags);
+				fnic_fcoe_send_vlan_req(fnic);
+				return;
+			}
+			/* check the next vlan */
+			vlan =
+			    list_first_entry(&fnic->vlan_list, struct fcoe_vlan,
+					     list);
+
+			fnic->set_vlan(fnic, vlan->vid);
+			vlan->state = FIP_VLAN_SENT;	/* sent now */
+
+		}
+		atomic64_inc(&fnic_stats->vlan_stats.sol_expiry_count);
+
+	} else {
+		fnic->set_vlan(fnic, vlan->vid);
+		vlan->state = FIP_VLAN_SENT;	/* sent now */
+	}
+	vlan->sol_count++;
+	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
+	fnic_fcoe_start_fcf_discovery(fnic);
+}
+
+/**
+ * fnic_work_on_fcs_ka_timer - Handle work on FCS keep alive timer.
+ * @work: the work queue to be serviced
+ *
+ * Finish handling fcs_ka_timer in process context.
+ * Clean up, bring the link down, and restart all FIP discovery.
+ */
+void fnic_work_on_fcs_ka_timer(struct work_struct *work)
+{
+	struct fnic
+	*fnic = container_of(work, struct fnic, fip_timer_work);
+	struct fnic_iport_s *iport = &fnic->iport;
+
+	FNIC_FIP_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		     "fnic 0x%p fcs ka timeout\n", fnic);
+
+	fnic_common_fip_cleanup(fnic);
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	fnic_fdls_link_down(iport);
+	iport->state = FNIC_IPORT_STATE_FIP;
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+
+	fnic_fcoe_send_vlan_req(fnic);
+}
+
+/**
+ * fnic_handle_fcs_ka_timer - Handle FCS keep alive timer.
+ * @t: Handle to the timer list
+ *
+ * No keep alives received from FCF. Clean up, bring the link down
+ * and restart all the FIP discovery.
+ */
+void fnic_handle_fcs_ka_timer(struct timer_list *t)
+{
+	struct fnic *fnic = from_timer(fnic, t, fcs_ka_timer);
+
+	INIT_WORK(&fnic->fip_timer_work, fnic_work_on_fcs_ka_timer);
+	queue_work(fnic_fip_queue, &fnic->fip_timer_work);
+}
diff --git a/drivers/scsi/fnic/fip.h b/drivers/scsi/fnic/fip.h
new file mode 100644
index 000000000000..79fee7628870
--- /dev/null
+++ b/drivers/scsi/fnic/fip.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
+ * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
+ */
+#ifndef _FIP_H_
+#define _FIP_H_
+
+#include "fdls_fc.h"
+#include "fnic_fdls.h"
+#include <scsi/fc/fc_fip.h>
+
+/* Drop the cast from the standard definition */
+#define FCOE_ALL_FCFS_MAC {0x01, 0x10, 0x18, 0x01, 0x00, 0x02}
+#define FCOE_MAX_SIZE 0x082E
+
+#define FCOE_CTLR_FIPVLAN_TOV (3*1000)
+#define FCOE_CTLR_FCS_TOV     (3*1000)
+#define FCOE_CTLR_MAX_SOL      (5*1000)
+
+#define FIP_DISC_SOL_LEN (6)
+#define FIP_VLAN_REQ_LEN (2)
+#define FIP_ENODE_KA_LEN (2)
+#define FIP_VN_KA_LEN (7)
+#define FIP_FLOGI_LEN (38)
+
+enum fdls_vlan_state {
+	FIP_VLAN_AVAIL,
+	FIP_VLAN_SENT
+};
+
+enum fdls_fip_state {
+	FDLS_FIP_INIT,
+	FDLS_FIP_VLAN_DISCOVERY_STARTED,
+	FDLS_FIP_FCF_DISCOVERY_STARTED,
+	FDLS_FIP_FLOGI_STARTED,
+	FDLS_FIP_FLOGI_COMPLETE,
+};
+
+/*
+ * VLAN entry.
+ */
+struct fcoe_vlan {
+	struct list_head list;
+	uint16_t vid;		/* vlan ID */
+	uint16_t sol_count;	/* no. of sols sent */
+	uint16_t state;		/* state */
+};
+
+struct fip_vlan_req {
+	struct ethhdr eth;
+	struct fip_header fip;
+	struct fip_mac_desc mac_desc;
+} __packed;
+
+struct fip_vlan_notif {
+	struct fip_header fip;
+	struct fip_vlan_desc vlans_desc[];
+} __packed;
+
+struct fip_vn_port_ka {
+	struct ethhdr eth;
+	struct fip_header fip;
+	struct fip_mac_desc mac_desc;
+	struct fip_vn_desc vn_port_desc;
+} __packed;
+
+struct fip_enode_ka {
+	struct ethhdr eth;
+	struct fip_header fip;
+	struct fip_mac_desc mac_desc;
+} __packed;
+
+struct fip_cvl {
+	struct fip_header fip;
+	struct fip_mac_desc fcf_mac_desc;
+	struct fip_wwn_desc name_desc;
+	struct fip_vn_desc vn_ports_desc[];
+} __packed;
+
+struct fip_flogi_desc {
+	struct fip_desc fd_desc;
+	uint16_t rsvd;
+	struct fc_std_flogi flogi;
+} __packed;
+
+struct fip_flogi_rsp_desc {
+	struct fip_desc fd_desc;
+	uint16_t rsvd;
+	struct fc_std_flogi flogi;
+} __packed;
+
+struct fip_flogi {
+	struct ethhdr eth;
+	struct fip_header fip;
+	struct fip_flogi_desc flogi_desc;
+	struct fip_mac_desc mac_desc;
+} __packed;
+
+struct fip_flogi_rsp {
+	struct fip_header fip;
+	struct fip_flogi_rsp_desc rsp_desc;
+	struct fip_mac_desc mac_desc;
+} __packed;
+
+struct fip_discovery {
+	struct ethhdr eth;
+	struct fip_header fip;
+	struct fip_mac_desc mac_desc;
+	struct fip_wwn_desc name_desc;
+	struct fip_size_desc fcoe_desc;
+} __packed;
+
+struct fip_disc_adv {
+	struct fip_header fip;
+	struct fip_pri_desc prio_desc;
+	struct fip_mac_desc mac_desc;
+	struct fip_wwn_desc name_desc;
+	struct fip_fab_desc fabric_desc;
+	struct fip_fka_desc fka_adv_desc;
+} __packed;
+
+void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct fip_header *fiph);
+void fnic_fcoe_fip_discovery_resp(struct fnic *fnic, struct fip_header *fiph);
+void fnic_fcoe_process_flogi_resp(struct fnic *fnic, struct fip_header *fiph);
+void fnic_work_on_fip_timer(struct work_struct *work);
+void fnic_work_on_fcs_ka_timer(struct work_struct *work);
+void fnic_fcoe_send_vlan_req(struct fnic *fnic);
+void fnic_fcoe_start_fcf_discovery(struct fnic *fnic);
+void fnic_fcoe_start_flogi(struct fnic *fnic);
+void fnic_fcoe_process_cvl(struct fnic *fnic, struct fip_header *fiph);
+void fnic_vlan_discovery_timeout(struct fnic *fnic);
+
+extern struct workqueue_struct *fnic_fip_queue;
+
+#ifdef FNIC_DEBUG
+static inline void
+fnic_debug_dump_fip_frame(struct fnic *fnic, struct ethhdr *eth,
+				int len, char *pfx)
+{
+	struct fip_header *fiph = (struct fip_header *)(eth + 1);
+	u16 op = be16_to_cpu(fiph->fip_op);
+	u8 sub = fiph->fip_subcode;
+
+	FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		"FIP %s packet contents: op: 0x%x sub: 0x%x (len = %d)",
+		pfx, op, sub, len);
+
+	fnic_debug_dump(fnic, (uint8_t *)eth, len);
+}
+
+#else /* FNIC_DEBUG */
+
+static inline void
+fnic_debug_dump_fip_frame(struct fnic *fnic, struct ethhdr *eth,
+				int len, char *pfx) {}
+#endif /* FNIC_DEBUG */
+
+#endif	/* _FIP_H_ */
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index ce73f08ee889..6c5f6046b1f5 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -10,8 +10,10 @@
 #include <linux/netdevice.h>
 #include <linux/workqueue.h>
 #include <linux/bitops.h>
-#include <scsi/libfc.h>
-#include <scsi/libfcoe.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_transport.h>
+#include <scsi/scsi_transport_fc.h>
+#include <scsi/fc_frame.h>
 #include "fnic_io.h"
 #include "fnic_res.h"
 #include "fnic_trace.h"
@@ -24,13 +26,15 @@
 #include "vnic_intr.h"
 #include "vnic_stats.h"
 #include "vnic_scsi.h"
+#include "fnic_fdls.h"
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.7.0.0"
+#define DRV_VERSION		"1.8.0.0"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 
+#define FABRIC_LOGO_MAX_RETRY 3
 #define DESC_CLEAN_LOW_WATERMARK 8
 #define FNIC_UCSM_DFLT_THROTTLE_CNT_BLD	16 /* UCSM default throttle count */
 #define FNIC_MIN_IO_REQ			256 /* Min IO throttle count */
@@ -38,6 +42,7 @@
 #define FNIC_DFLT_IO_REQ        256 /* Default scsi_cmnd tag map entries */
 #define FNIC_DFLT_QUEUE_DEPTH	256
 #define	FNIC_STATS_RATE_LIMIT	4 /* limit rate at which stats are pulled up */
+#define LUN0_DELAY_TIME			9
 
 /*
  * Tag bits used for special requests.
@@ -75,6 +80,77 @@
 #define FNIC_DEV_RST_TERM_DONE          BIT(20)
 #define FNIC_DEV_RST_ABTS_PENDING       BIT(21)
 
+#define FNIC_FW_RESET_TIMEOUT        60000	/* mSec   */
+#define FNIC_FCOE_MAX_CMD_LEN        16
+/* Retry supported by rport (returned by PRLI service parameters) */
+#define FNIC_FC_RP_FLAGS_RETRY            0x1
+
+/* Cisco vendor id */
+#define PCI_VENDOR_ID_CISCO						0x1137
+#define PCI_DEVICE_ID_CISCO_VIC_FC				0x0045	/* fc vnic */
+
+/* sereno pcie switch */
+#define PCI_DEVICE_ID_CISCO_SERENO             0x004e
+#define PCI_DEVICE_ID_CISCO_CRUZ               0x007a	/* Cruz */
+#define PCI_DEVICE_ID_CISCO_BODEGA             0x0131	/* Bodega */
+#define PCI_DEVICE_ID_CISCO_BEVERLY            0x025f	/* Beverly */
+
+/* Sereno */
+#define PCI_SUBDEVICE_ID_CISCO_VASONA			0x004f	/* vasona mezz */
+#define PCI_SUBDEVICE_ID_CISCO_COTATI			0x0084	/* cotati mlom */
+#define PCI_SUBDEVICE_ID_CISCO_LEXINGTON		0x0085	/* lexington pcie */
+#define PCI_SUBDEVICE_ID_CISCO_ICEHOUSE			0x00cd	/* Icehouse */
+#define PCI_SUBDEVICE_ID_CISCO_KIRKWOODLAKE		0x00ce	/* KirkwoodLake pcie */
+#define PCI_SUBDEVICE_ID_CISCO_SUSANVILLE		0x012e	/* Susanville MLOM */
+#define PCI_SUBDEVICE_ID_CISCO_TORRANCE			0x0139	/* Torrance MLOM */
+
+/* Cruz */
+#define PCI_SUBDEVICE_ID_CISCO_CALISTOGA		0x012c	/* Calistoga MLOM */
+#define PCI_SUBDEVICE_ID_CISCO_MOUNTAINVIEW		0x0137	/* Cruz Mezz */
+/* Cruz MountTian SIOC */
+#define PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN		0x014b
+#define PCI_SUBDEVICE_ID_CISCO_CLEARLAKE		0x014d	/* ClearLake pcie */
+/* Cruz MountTian2 SIOC */
+#define PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN2		0x0157
+#define PCI_SUBDEVICE_ID_CISCO_CLAREMONT		0x015d	/* Claremont MLOM */
+
+/* Bodega */
+/* VIC 1457 PCIe mLOM */
+#define PCI_SUBDEVICE_ID_CISCO_BRADBURY         0x0218
+#define PCI_SUBDEVICE_ID_CISCO_BRENTWOOD        0x0217	/* VIC 1455 PCIe */
+/* VIC 1487 PCIe mLOM */
+#define PCI_SUBDEVICE_ID_CISCO_BURLINGAME       0x021a
+#define PCI_SUBDEVICE_ID_CISCO_BAYSIDE          0x0219	/* VIC 1485 PCIe */
+/* VIC 1440 Mezz mLOM */
+#define PCI_SUBDEVICE_ID_CISCO_BAKERSFIELD      0x0215
+#define PCI_SUBDEVICE_ID_CISCO_BOONVILLE        0x0216	/* VIC 1480 Mezz */
+#define PCI_SUBDEVICE_ID_CISCO_BENICIA          0x024a	/* VIC 1495 */
+#define PCI_SUBDEVICE_ID_CISCO_BEAUMONT         0x024b	/* VIC 1497 */
+#define PCI_SUBDEVICE_ID_CISCO_BRISBANE         0x02af	/* VIC 1467 */
+#define PCI_SUBDEVICE_ID_CISCO_BENTON           0x02b0	/* VIC 1477 */
+#define PCI_SUBDEVICE_ID_CISCO_TWIN_RIVER       0x02cf	/* VIC 14425 */
+#define PCI_SUBDEVICE_ID_CISCO_TWIN_PEAK        0x02d0	/* VIC 14825 */
+
+/* Beverly */
+#define PCI_SUBDEVICE_ID_CISCO_BERN             0x02de	/* VIC 15420 */
+#define PCI_SUBDEVICE_ID_CISCO_STOCKHOLM        0x02dd	/* VIC 15428 */
+#define PCI_SUBDEVICE_ID_CISCO_KRAKOW           0x02dc	/* VIC 15411 */
+#define PCI_SUBDEVICE_ID_CISCO_LUCERNE          0x02db	/* VIC 15231 */
+#define PCI_SUBDEVICE_ID_CISCO_TURKU            0x02e8	/* VIC 15238 */
+#define PCI_SUBDEVICE_ID_CISCO_TURKU_PLUS       0x02f3	/* VIC 15237 */
+#define PCI_SUBDEVICE_ID_CISCO_ZURICH           0x02df	/* VIC 15230 */
+#define PCI_SUBDEVICE_ID_CISCO_RIGA             0x02e0	/* VIC 15427 */
+#define PCI_SUBDEVICE_ID_CISCO_GENEVA           0x02e1	/* VIC 15422 */
+#define PCI_SUBDEVICE_ID_CISCO_HELSINKI         0x02e4	/* VIC 15235 */
+#define PCI_SUBDEVICE_ID_CISCO_GOTHENBURG       0x02f2	/* VIC 15425 */
+
+struct fnic_pcie_device {
+	u32 device;
+	u8 *desc;
+	u32 subsystem_device;
+	u8 *subsys_desc;
+};
+
 /*
  * fnic private data per SCSI command.
  * These fields are locked by the hashed io_req_lock.
@@ -127,8 +203,38 @@ static inline u64 fnic_flags_and_state(struct scsi_cmnd *cmd)
 #define fnic_clear_state_flags(fnicp, st_flags)  \
 	__fnic_set_state_flags(fnicp, st_flags, 1)
 
+enum reset_states {
+	NOT_IN_PROGRESS = 0,
+	IN_PROGRESS,
+	RESET_ERROR
+};
+
+enum rscn_type {
+	NOT_PC_RSCN = 0,
+	PC_RSCN
+};
+
+enum pc_rscn_handling_status {
+	PC_RSCN_HANDLING_NOT_IN_PROGRESS = 0,
+	PC_RSCN_HANDLING_IN_PROGRESS
+};
+
+enum pc_rscn_handling_feature {
+	PC_RSCN_HANDLING_FEATURE_OFF = 0,
+	PC_RSCN_HANDLING_FEATURE_ON
+};
+
+extern unsigned int fnic_fdmi_support;
 extern unsigned int fnic_log_level;
 extern unsigned int io_completions;
+extern struct workqueue_struct *fnic_event_queue;
+
+extern unsigned int pc_rscn_handling_feature_flag;
+extern spinlock_t reset_fnic_list_lock;
+extern struct list_head reset_fnic_list;
+extern struct workqueue_struct *reset_fnic_work_queue;
+extern struct work_struct reset_fnic_work;
+
 
 #define FNIC_MAIN_LOGGING 0x01
 #define FNIC_FCS_LOGGING 0x02
@@ -155,6 +261,12 @@ do {								\
 				"fnic<%d>: %s: %d: " fmt, fnic_num,\
 				__func__, __LINE__, ##args);)
 
+#define FNIC_FIP_DBG(kern_level, host, fnic_num, fmt, args...)		\
+	FNIC_CHECK_LOGGING(FNIC_FCS_LOGGING,			\
+			 shost_printk(kern_level, host,			\
+				"fnic<%d>: %s: %d: " fmt, fnic_num,\
+				__func__, __LINE__, ##args);)
+
 #define FNIC_SCSI_DBG(kern_level, host, fnic_num, fmt, args...)		\
 	FNIC_CHECK_LOGGING(FNIC_SCSI_LOGGING,			\
 			 shost_printk(kern_level, host,			\
@@ -213,12 +325,26 @@ enum fnic_state {
 
 struct mempool;
 
+enum fnic_role_e {
+	FNIC_ROLE_FCP_INITIATOR = 0,
+};
+
 enum fnic_evt {
 	FNIC_EVT_START_VLAN_DISC = 1,
 	FNIC_EVT_START_FCF_DISC = 2,
 	FNIC_EVT_MAX,
 };
 
+struct fnic_frame_list {
+	/*
+	 * Link to frame lists
+	 */
+	struct list_head links;
+	void *fp;
+	int frame_len;
+	int rx_ethhdr_stripped;
+};
+
 struct fnic_event {
 	struct list_head list;
 	struct fnic *fnic;
@@ -235,8 +361,9 @@ struct fnic_cpy_wq {
 /* Per-instance private data structure */
 struct fnic {
 	int fnic_num;
-	struct fc_lport *lport;
-	struct fcoe_ctlr ctlr;		/* FIP FCoE controller structure */
+	enum fnic_role_e role;
+	struct fnic_iport_s iport;
+	struct Scsi_Host *host;
 	struct vnic_dev_bar bar0;
 
 	struct fnic_msix_entry msix[FNIC_MSIX_INTR_MAX];
@@ -255,6 +382,7 @@ struct fnic {
 	unsigned int wq_count;
 	unsigned int cq_count;
 
+	struct completion reset_completion_wait;
 	struct mutex sgreset_mutex;
 	spinlock_t sgreset_lock; /* lock for sgreset */
 	struct scsi_cmnd *sgreset_sc;
@@ -268,25 +396,27 @@ struct fnic {
 	u32 vlan_hw_insert:1;	        /* let hw insert the tag */
 	u32 in_remove:1;                /* fnic device in removal */
 	u32 stop_rx_link_events:1;      /* stop proc. rx frames, link events */
-	u32 link_events:1;              /* set when we get any link event*/
-
-	struct completion *remove_wait; /* device remove thread blocks */
 
+	struct completion *fw_reset_done;
+	u32 reset_in_progress;
 	atomic_t in_flight;		/* io counter */
 	bool internal_reset_inprogress;
 	u32 _reserved;			/* fill hole */
 	unsigned long state_flags;	/* protected by host lock */
 	enum fnic_state state;
 	spinlock_t fnic_lock;
+	unsigned long lock_flags;
 
 	u16 vlan_id;	                /* VLAN tag including priority */
 	u8 data_src_addr[ETH_ALEN];
 	u64 fcp_input_bytes;		/* internal statistic */
 	u64 fcp_output_bytes;		/* internal statistic */
 	u32 link_down_cnt;
+	u32 soft_reset_count;
 	int link_status;
 
 	struct list_head list;
+	struct list_head links;
 	struct pci_dev *pdev;
 	struct vnic_fc_config config;
 	struct vnic_dev *vdev;
@@ -306,19 +436,29 @@ struct fnic {
 	struct work_struct link_work;
 	struct work_struct frame_work;
 	struct work_struct flush_work;
-	struct sk_buff_head frame_queue;
-	struct sk_buff_head tx_queue;
+	struct list_head frame_queue;
+	struct list_head tx_queue;
+	mempool_t *frame_pool;
+	mempool_t *frame_elem_pool;
+	struct work_struct tport_work;
+	struct list_head tport_event_list;
+
+	char subsys_desc[14];
+	int subsys_desc_len;
+	int pc_rscn_handling_status;
 
 	/*** FIP related data members  -- start ***/
 	void (*set_vlan)(struct fnic *, u16 vlan);
 	struct work_struct      fip_frame_work;
-	struct sk_buff_head     fip_frame_queue;
+	struct work_struct		fip_timer_work;
+	struct list_head		fip_frame_queue;
 	struct timer_list       fip_timer;
-	struct list_head        vlans;
 	spinlock_t              vlans_lock;
-
-	struct work_struct      event_work;
-	struct list_head        evlist;
+	struct timer_list retry_fip_timer;
+	struct timer_list fcs_ka_timer;
+	struct timer_list enode_ka_timer;
+	struct timer_list vn_ka_timer;
+	struct list_head vlan_list;
 	/*** FIP related data members  -- end ***/
 
 	/* copy work queue cache line section */
@@ -341,11 +481,6 @@ struct fnic {
 	____cacheline_aligned struct vnic_intr intr[FNIC_MSIX_INTR_MAX];
 };
 
-static inline struct fnic *fnic_from_ctlr(struct fcoe_ctlr *fip)
-{
-	return container_of(fip, struct fnic, ctlr);
-}
-
 extern struct workqueue_struct *fnic_event_queue;
 extern struct workqueue_struct *fnic_fip_queue;
 extern const struct attribute_group *fnic_host_groups[];
@@ -356,29 +491,29 @@ int fnic_set_intr_mode_msix(struct fnic *fnic);
 void fnic_free_intr(struct fnic *fnic);
 int fnic_request_intr(struct fnic *fnic);
 
-int fnic_send(struct fc_lport *, struct fc_frame *);
 void fnic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf);
 void fnic_handle_frame(struct work_struct *work);
+void fnic_tport_event_handler(struct work_struct *work);
 void fnic_handle_link(struct work_struct *work);
 void fnic_handle_event(struct work_struct *work);
+void fdls_reclaim_oxid_handler(struct work_struct *work);
+void fdls_schedule_oxid_free(struct fnic_iport_s *iport, uint16_t *active_oxid);
+void fdls_schedule_oxid_free_retry_work(struct work_struct *work);
 int fnic_rq_cmpl_handler(struct fnic *fnic, int);
 int fnic_alloc_rq_frame(struct vnic_rq *rq);
 void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
 void fnic_flush_tx(struct work_struct *work);
-void fnic_eth_send(struct fcoe_ctlr *, struct sk_buff *skb);
-void fnic_set_port_id(struct fc_lport *, u32, struct fc_frame *);
-void fnic_update_mac(struct fc_lport *, u8 *new);
 void fnic_update_mac_locked(struct fnic *, u8 *new);
 
 int fnic_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 int fnic_abort_cmd(struct scsi_cmnd *);
 int fnic_device_reset(struct scsi_cmnd *);
-int fnic_host_reset(struct scsi_cmnd *);
-int fnic_reset(struct Scsi_Host *);
-void fnic_scsi_cleanup(struct fc_lport *);
-void fnic_scsi_abort_io(struct fc_lport *);
-void fnic_empty_scsi_cleanup(struct fc_lport *);
-void fnic_exch_mgr_reset(struct fc_lport *, u32, u32);
+int fnic_eh_host_reset_handler(struct scsi_cmnd *sc);
+int fnic_host_reset(struct Scsi_Host *shost);
+void fnic_reset(struct Scsi_Host *shost);
+int fnic_issue_fc_host_lip(struct Scsi_Host *shost);
+void fnic_get_host_port_state(struct Scsi_Host *shost);
+void fnic_scsi_fcpio_reset(struct fnic *fnic);
 int fnic_wq_copy_cmpl_handler(struct fnic *fnic, int copy_work_to_do, unsigned int cq_index);
 int fnic_wq_cmpl_handler(struct fnic *fnic, int);
 int fnic_flogi_reg_handler(struct fnic *fnic, u32);
@@ -390,14 +525,15 @@ const char *fnic_state_to_str(unsigned int state);
 void fnic_mq_map_queues_cpus(struct Scsi_Host *host);
 void fnic_log_q_error(struct fnic *fnic);
 void fnic_handle_link_event(struct fnic *fnic);
-
+int fnic_stats_debugfs_init(struct fnic *fnic);
+void fnic_stats_debugfs_remove(struct fnic *fnic);
 int fnic_is_abts_pending(struct fnic *, struct scsi_cmnd *);
 
 void fnic_handle_fip_frame(struct work_struct *work);
+void fnic_reset_work_handler(struct work_struct *work);
 void fnic_handle_fip_event(struct fnic *fnic);
 void fnic_fcoe_reset_vlans(struct fnic *fnic);
-void fnic_fcoe_evlist_free(struct fnic *fnic);
-extern void fnic_handle_fip_timer(struct fnic *fnic);
+extern void fnic_handle_fip_timer(struct timer_list *t);
 
 static inline int
 fnic_chk_state_flags_locked(struct fnic *fnic, unsigned long st_flags)
@@ -406,4 +542,90 @@ fnic_chk_state_flags_locked(struct fnic *fnic, unsigned long st_flags)
 }
 void __fnic_set_state_flags(struct fnic *, unsigned long, unsigned long);
 void fnic_dump_fchost_stats(struct Scsi_Host *, struct fc_host_statistics *);
+void fnic_free_txq(struct list_head *head);
+int fnic_get_desc_by_devid(struct pci_dev *pdev, char **desc,
+						   char **subsys_desc);
+void fnic_fdls_link_status_change(struct fnic *fnic, int linkup);
+void fnic_delete_fcp_tports(struct fnic *fnic);
+void fnic_flush_tport_event_list(struct fnic *fnic);
+int fnic_count_ioreqs_wq(struct fnic *fnic, u32 hwq, u32 portid);
+unsigned int fnic_count_ioreqs(struct fnic *fnic, u32 portid);
+unsigned int fnic_count_all_ioreqs(struct fnic *fnic);
+unsigned int fnic_count_lun_ioreqs_wq(struct fnic *fnic, u32 hwq,
+						  struct scsi_device *device);
+unsigned int fnic_count_lun_ioreqs(struct fnic *fnic,
+					   struct scsi_device *device);
+void fnic_scsi_unload(struct fnic *fnic);
+void fnic_scsi_unload_cleanup(struct fnic *fnic);
+int fnic_get_debug_info(struct stats_debug_info *info,
+			struct fnic *fnic);
+
+struct fnic_scsi_iter_data {
+	struct fnic *fnic;
+	void *data1;
+	void *data2;
+	bool (*fn)(struct fnic *fnic, struct scsi_cmnd *sc,
+			void *data1, void *data2);
+};
+
+static inline bool
+fnic_io_iter_handler(struct scsi_cmnd *sc, void *iter_data)
+{
+	struct fnic_scsi_iter_data *iter = iter_data;
+
+	return iter->fn(iter->fnic, sc, iter->data1, iter->data2);
+}
+
+static inline void
+fnic_scsi_io_iter(struct fnic *fnic,
+		bool (*fn)(struct fnic *fnic, struct scsi_cmnd *sc,
+				void *data1, void *data2),
+		void *data1, void *data2)
+{
+	struct fnic_scsi_iter_data iter_data = {
+		.fn = fn,
+		.fnic = fnic,
+		.data1 = data1,
+		.data2 = data2,
+	};
+	scsi_host_busy_iter(fnic->host, fnic_io_iter_handler, &iter_data);
+}
+
+#ifdef FNIC_DEBUG
+static inline void
+fnic_debug_dump(struct fnic *fnic, uint8_t *u8arr, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i = i+8) {
+		FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		    "%d: %02x %02x %02x %02x %02x %02x %02x %02x", i / 8,
+		    u8arr[i + 0], u8arr[i + 1], u8arr[i + 2], u8arr[i + 3],
+		    u8arr[i + 4], u8arr[i + 5], u8arr[i + 6], u8arr[i + 7]);
+	}
+}
+
+static inline void
+fnic_debug_dump_fc_frame(struct fnic *fnic, struct fc_frame_header *fchdr,
+				int len, char *pfx)
+{
+	uint32_t s_id, d_id;
+
+	s_id = ntoh24(fchdr->fh_s_id);
+	d_id = ntoh24(fchdr->fh_d_id);
+	FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		"%s packet contents: sid/did/type/oxid = 0x%x/0x%x/0x%x/0x%x (len = %d)\n",
+		pfx, s_id, d_id, fchdr->fh_type,
+		FNIC_STD_GET_OX_ID(fchdr), len);
+
+	fnic_debug_dump(fnic, (uint8_t *)fchdr, len);
+
+}
+#else /* FNIC_DEBUG */
+static inline void
+fnic_debug_dump(struct fnic *fnic, uint8_t *u8arr, int len) {}
+static inline void
+fnic_debug_dump_fc_frame(struct fnic *fnic, struct fc_frame_header *fchdr,
+				uint32_t len, char *pfx) {}
+#endif /* FNIC_DEBUG */
 #endif /* _FNIC_H_ */
diff --git a/drivers/scsi/fnic/fnic_attrs.c b/drivers/scsi/fnic/fnic_attrs.c
index 0c5e57c7e322..705718f0809b 100644
--- a/drivers/scsi/fnic/fnic_attrs.c
+++ b/drivers/scsi/fnic/fnic_attrs.c
@@ -11,8 +11,8 @@
 static ssize_t fnic_show_state(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
-	struct fc_lport *lp = shost_priv(class_to_shost(dev));
-	struct fnic *fnic = lport_priv(lp);
+	struct fnic *fnic =
+		*((struct fnic **) shost_priv(class_to_shost(dev)));
 
 	return sysfs_emit(buf, "%s\n", fnic_state_str[fnic->state]);
 }
@@ -26,9 +26,13 @@ static ssize_t fnic_show_drv_version(struct device *dev,
 static ssize_t fnic_show_link_state(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
-	struct fc_lport *lp = shost_priv(class_to_shost(dev));
+	struct fnic *fnic =
+		*((struct fnic **) shost_priv(class_to_shost(dev)));
 
-	return sysfs_emit(buf, "%s\n", (lp->link_up) ? "Link Up" : "Link Down");
+	return sysfs_emit(buf, "%s\n",
+					  ((fnic->iport.state != FNIC_IPORT_STATE_INIT) &&
+					   (fnic->iport.state != FNIC_IPORT_STATE_LINK_WAIT)) ?
+					  "Link Up" : "Link Down");
 }
 
 static DEVICE_ATTR(fnic_state, S_IRUGO, fnic_show_state, NULL);
diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c
index 2619a2d4f5f1..5767862ae42f 100644
--- a/drivers/scsi/fnic/fnic_debugfs.c
+++ b/drivers/scsi/fnic/fnic_debugfs.c
@@ -7,6 +7,9 @@
 #include <linux/vmalloc.h>
 #include "fnic.h"
 
+extern int fnic_get_debug_info(struct stats_debug_info *debug_buffer,
+							   struct fnic *fnic);
+
 static struct dentry *fnic_trace_debugfs_root;
 static struct dentry *fnic_trace_debugfs_file;
 static struct dentry *fnic_trace_enable;
@@ -593,6 +596,7 @@ static int fnic_stats_debugfs_open(struct inode *inode,
 	debug->buf_size = buf_size;
 	memset((void *)debug->debug_buffer, 0, buf_size);
 	debug->buffer_len = fnic_get_stats_data(debug, fnic_stats);
+	debug->buffer_len += fnic_get_debug_info(debug, fnic);
 
 	file->private_data = debug;
 
@@ -673,26 +677,25 @@ static const struct file_operations fnic_reset_debugfs_fops = {
  * It will create file stats and reset_stats under statistics/host# directory
  * to log per fnic stats.
  */
-void fnic_stats_debugfs_init(struct fnic *fnic)
+int fnic_stats_debugfs_init(struct fnic *fnic)
 {
 	char name[16];
 
-	snprintf(name, sizeof(name), "host%d", fnic->lport->host->host_no);
+	snprintf(name, sizeof(name), "host%d", fnic->host->host_no);
 
 	fnic->fnic_stats_debugfs_host = debugfs_create_dir(name,
 						fnic_stats_debugfs_root);
-
 	fnic->fnic_stats_debugfs_file = debugfs_create_file("stats",
 						S_IFREG|S_IRUGO|S_IWUSR,
 						fnic->fnic_stats_debugfs_host,
 						fnic,
 						&fnic_stats_debugfs_fops);
-
 	fnic->fnic_reset_debugfs_file = debugfs_create_file("reset_stats",
 						S_IFREG|S_IRUGO|S_IWUSR,
 						fnic->fnic_stats_debugfs_host,
 						fnic,
 						&fnic_reset_debugfs_fops);
+	return 0;
 }
 
 /*
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index a08293b2ad9f..1e8cd64f9a5c 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -14,701 +14,379 @@
 #include <linux/workqueue.h>
 #include <scsi/fc/fc_fip.h>
 #include <scsi/fc/fc_els.h>
-#include <scsi/fc/fc_fcoe.h>
 #include <scsi/fc_frame.h>
-#include <scsi/libfc.h>
+#include <linux/etherdevice.h>
+#include <scsi/scsi_transport_fc.h>
 #include "fnic_io.h"
 #include "fnic.h"
-#include "fnic_fip.h"
+#include "fnic_fdls.h"
+#include "fdls_fc.h"
 #include "cq_enet_desc.h"
 #include "cq_exch_desc.h"
+#include "fip.h"
+
+#define MAX_RESET_WAIT_COUNT    64
 
-static u8 fcoe_all_fcfs[ETH_ALEN] = FIP_ALL_FCF_MACS;
-struct workqueue_struct *fnic_fip_queue;
 struct workqueue_struct *fnic_event_queue;
 
-static void fnic_set_eth_mode(struct fnic *);
-static void fnic_fcoe_send_vlan_req(struct fnic *fnic);
-static void fnic_fcoe_start_fcf_disc(struct fnic *fnic);
-static void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct sk_buff *);
-static int fnic_fcoe_vlan_check(struct fnic *fnic, u16 flag);
-static int fnic_fcoe_handle_fip_frame(struct fnic *fnic, struct sk_buff *skb);
+static uint8_t FCOE_ALL_FCF_MAC[6] = FC_FCOE_FLOGI_MAC;
 
-void fnic_handle_link(struct work_struct *work)
+/*
+ * Internal Functions
+ * This function will initialize the src_mac address to be
+ * used in outgoing frames
+ */
+static inline void fnic_fdls_set_fcoe_srcmac(struct fnic *fnic,
+							 uint8_t *src_mac)
 {
-	struct fnic *fnic = container_of(work, struct fnic, link_work);
-	unsigned long flags;
-	int old_link_status;
-	u32 old_link_down_cnt;
-	u64 old_port_speed, new_port_speed;
-
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-
-	fnic->link_events = 1;      /* less work to just set everytime*/
-
-	if (fnic->stop_rx_link_events) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		return;
-	}
-
-	old_link_down_cnt = fnic->link_down_cnt;
-	old_link_status = fnic->link_status;
-	old_port_speed = atomic64_read(
-			&fnic->fnic_stats.misc_stats.current_port_speed);
-
-	fnic->link_status = vnic_dev_link_status(fnic->vdev);
-	fnic->link_down_cnt = vnic_dev_link_down_cnt(fnic->vdev);
-
-	new_port_speed = vnic_dev_port_speed(fnic->vdev);
-	atomic64_set(&fnic->fnic_stats.misc_stats.current_port_speed,
-			new_port_speed);
-	if (old_port_speed != new_port_speed)
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-				"Current vnic speed set to: %llu\n",
-				new_port_speed);
-
-	switch (vnic_dev_port_speed(fnic->vdev)) {
-	case DCEM_PORTSPEED_10G:
-		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_10GBIT;
-		fnic->lport->link_supported_speeds = FC_PORTSPEED_10GBIT;
-		break;
-	case DCEM_PORTSPEED_20G:
-		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_20GBIT;
-		fnic->lport->link_supported_speeds = FC_PORTSPEED_20GBIT;
-		break;
-	case DCEM_PORTSPEED_25G:
-		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_25GBIT;
-		fnic->lport->link_supported_speeds = FC_PORTSPEED_25GBIT;
-		break;
-	case DCEM_PORTSPEED_40G:
-	case DCEM_PORTSPEED_4x10G:
-		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_40GBIT;
-		fnic->lport->link_supported_speeds = FC_PORTSPEED_40GBIT;
-		break;
-	case DCEM_PORTSPEED_100G:
-		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_100GBIT;
-		fnic->lport->link_supported_speeds = FC_PORTSPEED_100GBIT;
-		break;
-	default:
-		fc_host_speed(fnic->lport->host)   = FC_PORTSPEED_UNKNOWN;
-		fnic->lport->link_supported_speeds = FC_PORTSPEED_UNKNOWN;
-		break;
-	}
-
-	if (old_link_status == fnic->link_status) {
-		if (!fnic->link_status) {
-			/* DOWN -> DOWN */
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-			fnic_fc_trace_set_data(fnic->lport->host->host_no,
-				FNIC_FC_LE, "Link Status: DOWN->DOWN",
-				strlen("Link Status: DOWN->DOWN"));
-			FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-					"down->down\n");
-		} else {
-			if (old_link_down_cnt != fnic->link_down_cnt) {
-				/* UP -> DOWN -> UP */
-				fnic->lport->host_stats.link_failure_count++;
-				spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-				fnic_fc_trace_set_data(
-					fnic->lport->host->host_no,
-					FNIC_FC_LE,
-					"Link Status:UP_DOWN_UP",
-					strlen("Link_Status:UP_DOWN_UP")
-					);
-				FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-					     "link down\n");
-				fcoe_ctlr_link_down(&fnic->ctlr);
-				if (fnic->config.flags & VFCF_FIP_CAPABLE) {
-					/* start FCoE VLAN discovery */
-					fnic_fc_trace_set_data(
-						fnic->lport->host->host_no,
-						FNIC_FC_LE,
-						"Link Status: UP_DOWN_UP_VLAN",
-						strlen(
-						"Link Status: UP_DOWN_UP_VLAN")
-						);
-					fnic_fcoe_send_vlan_req(fnic);
-					return;
-				}
-				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-						"up->down->up: Link up\n");
-				fcoe_ctlr_link_up(&fnic->ctlr);
-			} else {
-				/* UP -> UP */
-				spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-				fnic_fc_trace_set_data(
-					fnic->lport->host->host_no, FNIC_FC_LE,
-					"Link Status: UP_UP",
-					strlen("Link Status: UP_UP"));
-				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-						"up->up\n");
-			}
-		}
-	} else if (fnic->link_status) {
-		/* DOWN -> UP */
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		if (fnic->config.flags & VFCF_FIP_CAPABLE) {
-			/* start FCoE VLAN discovery */
-			fnic_fc_trace_set_data(fnic->lport->host->host_no,
-					       FNIC_FC_LE, "Link Status: DOWN_UP_VLAN",
-					       strlen("Link Status: DOWN_UP_VLAN"));
-			fnic_fcoe_send_vlan_req(fnic);
-
-			return;
-		}
-
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-				"down->up: Link up\n");
-		fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_LE,
-				       "Link Status: DOWN_UP", strlen("Link Status: DOWN_UP"));
-		fcoe_ctlr_link_up(&fnic->ctlr);
-	} else {
-		/* UP -> DOWN */
-		fnic->lport->host_stats.link_failure_count++;
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-				"up->down: Link down\n");
-		fnic_fc_trace_set_data(
-			fnic->lport->host->host_no, FNIC_FC_LE,
-			"Link Status: UP_DOWN",
-			strlen("Link Status: UP_DOWN"));
-		if (fnic->config.flags & VFCF_FIP_CAPABLE) {
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-				"deleting fip-timer during link-down\n");
-			del_timer_sync(&fnic->fip_timer);
-		}
-		fcoe_ctlr_link_down(&fnic->ctlr);
-	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Setting src mac: %02x:%02x:%02x:%02x:%02x:%02x",
+				 src_mac[0], src_mac[1], src_mac[2], src_mac[3],
+				 src_mac[4], src_mac[5]);
 
+	memcpy(fnic->iport.fpma, src_mac, 6);
 }
 
 /*
- * This function passes incoming fabric frames to libFC
+ * This function will initialize the dst_mac address to be
+ * used in outgoing frames
  */
-void fnic_handle_frame(struct work_struct *work)
+static inline  void fnic_fdls_set_fcoe_dstmac(struct fnic *fnic,
+							 uint8_t *dst_mac)
 {
-	struct fnic *fnic = container_of(work, struct fnic, frame_work);
-	struct fc_lport *lp = fnic->lport;
-	unsigned long flags;
-	struct sk_buff *skb;
-	struct fc_frame *fp;
-
-	while ((skb = skb_dequeue(&fnic->frame_queue))) {
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Setting dst mac: %02x:%02x:%02x:%02x:%02x:%02x",
+				 dst_mac[0], dst_mac[1], dst_mac[2], dst_mac[3],
+				 dst_mac[4], dst_mac[5]);
 
-		spin_lock_irqsave(&fnic->fnic_lock, flags);
-		if (fnic->stop_rx_link_events) {
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-			dev_kfree_skb(skb);
-			return;
-		}
-		fp = (struct fc_frame *)skb;
-
-		/*
-		 * If we're in a transitional state, just re-queue and return.
-		 * The queue will be serviced when we get to a stable state.
-		 */
-		if (fnic->state != FNIC_IN_FC_MODE &&
-		    fnic->state != FNIC_IN_ETH_MODE) {
-			skb_queue_head(&fnic->frame_queue, skb);
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-			return;
-		}
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-
-		fc_exch_recv(lp, fp);
-	}
+	memcpy(fnic->iport.fcfmac, dst_mac, 6);
 }
 
-void fnic_fcoe_evlist_free(struct fnic *fnic)
+void fnic_get_host_port_state(struct Scsi_Host *shost)
 {
-	struct fnic_event *fevt = NULL;
-	struct fnic_event *next = NULL;
+	struct fnic *fnic = *((struct fnic **) shost_priv(shost));
+	struct fnic_iport_s *iport = &fnic->iport;
 	unsigned long flags;
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (list_empty(&fnic->evlist)) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		return;
-	}
-
-	list_for_each_entry_safe(fevt, next, &fnic->evlist, list) {
-		list_del(&fevt->list);
-		kfree(fevt);
-	}
+	if (!fnic->link_status)
+		fc_host_port_state(shost) = FC_PORTSTATE_LINKDOWN;
+	else if (iport->state == FNIC_IPORT_STATE_READY)
+		fc_host_port_state(shost) = FC_PORTSTATE_ONLINE;
+	else
+		fc_host_port_state(shost) = FC_PORTSTATE_OFFLINE;
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 }
 
-void fnic_handle_event(struct work_struct *work)
+void fnic_fdls_link_status_change(struct fnic *fnic, int linkup)
 {
-	struct fnic *fnic = container_of(work, struct fnic, event_work);
-	struct fnic_event *fevt = NULL;
-	struct fnic_event *next = NULL;
-	unsigned long flags;
+	struct fnic_iport_s *iport = &fnic->iport;
 
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (list_empty(&fnic->evlist)) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		return;
-	}
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "link up: %d, usefip: %d", linkup, iport->usefip);
 
-	list_for_each_entry_safe(fevt, next, &fnic->evlist, list) {
-		if (fnic->stop_rx_link_events) {
-			list_del(&fevt->list);
-			kfree(fevt);
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-			return;
-		}
-		/*
-		 * If we're in a transitional state, just re-queue and return.
-		 * The queue will be serviced when we get to a stable state.
-		 */
-		if (fnic->state != FNIC_IN_FC_MODE &&
-		    fnic->state != FNIC_IN_ETH_MODE) {
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-			return;
-		}
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
 
-		list_del(&fevt->list);
-		switch (fevt->event) {
-		case FNIC_EVT_START_VLAN_DISC:
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	if (linkup) {
+		if (iport->usefip) {
+			iport->state = FNIC_IPORT_STATE_FIP;
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "link up: %d, usefip: %d", linkup, iport->usefip);
 			fnic_fcoe_send_vlan_req(fnic);
-			spin_lock_irqsave(&fnic->fnic_lock, flags);
-			break;
-		case FNIC_EVT_START_FCF_DISC:
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-				  "Start FCF Discovery\n");
-			fnic_fcoe_start_fcf_disc(fnic);
-			break;
-		default:
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-				  "Unknown event 0x%x\n", fevt->event);
-			break;
+		} else {
+			iport->state = FNIC_IPORT_STATE_FABRIC_DISC;
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "iport->state: %d", iport->state);
+			fnic_fdls_disc_start(iport);
 		}
-		kfree(fevt);
+	} else {
+		iport->state = FNIC_IPORT_STATE_LINK_WAIT;
+		if (!is_zero_ether_addr(iport->fpma))
+			vnic_dev_del_addr(fnic->vdev, iport->fpma);
+		fnic_common_fip_cleanup(fnic);
+		fnic_fdls_link_down(iport);
+
 	}
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
 }
 
-/**
- * is_fnic_fip_flogi_reject() - Check if the Received FIP FLOGI frame is rejected
- * @fip: The FCoE controller that received the frame
- * @skb: The received FIP frame
- *
- * Returns non-zero if the frame is rejected with unsupported cmd with
- * insufficient resource els explanation.
+
+/*
+ * FPMA can be either taken from ethhdr(dst_mac) or flogi resp
+ * or derive from FC_MAP and FCID combination. While it should be
+ * same, revisit this if there is any possibility of not-correct.
  */
-static inline int is_fnic_fip_flogi_reject(struct fcoe_ctlr *fip,
-					 struct sk_buff *skb)
+void fnic_fdls_learn_fcoe_macs(struct fnic_iport_s *iport, void *rx_frame,
+							   uint8_t *fcid)
 {
-	struct fc_lport *lport = fip->lp;
-	struct fip_header *fiph;
-	struct fc_frame_header *fh = NULL;
-	struct fip_desc *desc;
-	struct fip_encaps *els;
-	u16 op;
-	u8 els_op;
-	u8 sub;
-
-	size_t rlen;
-	size_t dlen = 0;
-
-	if (skb_linearize(skb))
-		return 0;
+	struct fnic *fnic = iport->fnic;
+	struct ethhdr *ethhdr = (struct ethhdr *) rx_frame;
+	uint8_t fcmac[6] = { 0x0E, 0xFC, 0x00, 0x00, 0x00, 0x00 };
 
-	if (skb->len < sizeof(*fiph))
-		return 0;
+	memcpy(&fcmac[3], fcid, 3);
 
-	fiph = (struct fip_header *)skb->data;
-	op = ntohs(fiph->fip_op);
-	sub = fiph->fip_subcode;
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "learn fcoe: dst_mac: %02x:%02x:%02x:%02x:%02x:%02x",
+				 ethhdr->h_dest[0], ethhdr->h_dest[1],
+				 ethhdr->h_dest[2], ethhdr->h_dest[3],
+				 ethhdr->h_dest[4], ethhdr->h_dest[5]);
 
-	if (op != FIP_OP_LS)
-		return 0;
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "learn fcoe: fc_mac: %02x:%02x:%02x:%02x:%02x:%02x",
+				 fcmac[0], fcmac[1], fcmac[2], fcmac[3], fcmac[4],
+				 fcmac[5]);
 
-	if (sub != FIP_SC_REP)
-		return 0;
-
-	rlen = ntohs(fiph->fip_dl_len) * 4;
-	if (rlen + sizeof(*fiph) > skb->len)
-		return 0;
-
-	desc = (struct fip_desc *)(fiph + 1);
-	dlen = desc->fip_dlen * FIP_BPW;
+	fnic_fdls_set_fcoe_srcmac(fnic, fcmac);
+	fnic_fdls_set_fcoe_dstmac(fnic, ethhdr->h_source);
+}
 
-	if (desc->fip_dtype == FIP_DT_FLOGI) {
+void fnic_fdls_init(struct fnic *fnic, int usefip)
+{
+	struct fnic_iport_s *iport = &fnic->iport;
 
-		if (dlen < sizeof(*els) + sizeof(*fh) + 1)
-			return 0;
+	/* Initialize iPort structure */
+	iport->state = FNIC_IPORT_STATE_INIT;
+	iport->fnic = fnic;
+	iport->usefip = usefip;
 
-		els = (struct fip_encaps *)desc;
-		fh = (struct fc_frame_header *)(els + 1);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "iportsrcmac: %02x:%02x:%02x:%02x:%02x:%02x",
+				 iport->hwmac[0], iport->hwmac[1], iport->hwmac[2],
+				 iport->hwmac[3], iport->hwmac[4], iport->hwmac[5]);
 
-		if (!fh)
-			return 0;
+	INIT_LIST_HEAD(&iport->tport_list);
+	INIT_LIST_HEAD(&iport->tport_list_pending_del);
 
-		/*
-		 * ELS command code, reason and explanation should be = Reject,
-		 * unsupported command and insufficient resource
-		 */
-		els_op = *(u8 *)(fh + 1);
-		if (els_op == ELS_LS_RJT) {
-			shost_printk(KERN_INFO, lport->host,
-				  "Flogi Request Rejected by Switch\n");
-			return 1;
-		}
-		shost_printk(KERN_INFO, lport->host,
-				"Flogi Request Accepted by Switch\n");
-	}
-	return 0;
+	fnic_fdls_disc_init(iport);
 }
 
-static void fnic_fcoe_send_vlan_req(struct fnic *fnic)
+void fnic_handle_link(struct work_struct *work)
 {
-	struct fcoe_ctlr *fip = &fnic->ctlr;
-	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
-	struct sk_buff *skb;
-	char *eth_fr;
-	struct fip_vlan *vlan;
-	u64 vlan_tov;
+	struct fnic *fnic = container_of(work, struct fnic, link_work);
+	int old_link_status;
+	u32 old_link_down_cnt;
+	int max_count = 0;
 
-	fnic_fcoe_reset_vlans(fnic);
-	fnic->set_vlan(fnic, 0);
+	if (vnic_dev_get_intr_mode(fnic->vdev) != VNIC_DEV_INTR_MODE_MSI)
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Interrupt mode is not MSI\n");
 
-	if (printk_ratelimit())
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-			  "Sending VLAN request...\n");
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
 
-	skb = dev_alloc_skb(sizeof(struct fip_vlan));
-	if (!skb)
+	if (fnic->stop_rx_link_events) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Stop link rx events\n");
 		return;
-
-	eth_fr = (char *)skb->data;
-	vlan = (struct fip_vlan *)eth_fr;
-
-	memset(vlan, 0, sizeof(*vlan));
-	memcpy(vlan->eth.h_source, fip->ctl_src_addr, ETH_ALEN);
-	memcpy(vlan->eth.h_dest, fcoe_all_fcfs, ETH_ALEN);
-	vlan->eth.h_proto = htons(ETH_P_FIP);
-
-	vlan->fip.fip_ver = FIP_VER_ENCAPS(FIP_VER);
-	vlan->fip.fip_op = htons(FIP_OP_VLAN);
-	vlan->fip.fip_subcode = FIP_SC_VL_REQ;
-	vlan->fip.fip_dl_len = htons(sizeof(vlan->desc) / FIP_BPW);
-
-	vlan->desc.mac.fd_desc.fip_dtype = FIP_DT_MAC;
-	vlan->desc.mac.fd_desc.fip_dlen = sizeof(vlan->desc.mac) / FIP_BPW;
-	memcpy(&vlan->desc.mac.fd_mac, fip->ctl_src_addr, ETH_ALEN);
-
-	vlan->desc.wwnn.fd_desc.fip_dtype = FIP_DT_NAME;
-	vlan->desc.wwnn.fd_desc.fip_dlen = sizeof(vlan->desc.wwnn) / FIP_BPW;
-	put_unaligned_be64(fip->lp->wwnn, &vlan->desc.wwnn.fd_wwn);
-	atomic64_inc(&fnic_stats->vlan_stats.vlan_disc_reqs);
-
-	skb_put(skb, sizeof(*vlan));
-	skb->protocol = htons(ETH_P_FIP);
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-	fip->send(fip, skb);
-
-	/* set a timer so that we can retry if there no response */
-	vlan_tov = jiffies + msecs_to_jiffies(FCOE_CTLR_FIPVLAN_TOV);
-	mod_timer(&fnic->fip_timer, round_jiffies(vlan_tov));
-}
-
-static void fnic_fcoe_process_vlan_resp(struct fnic *fnic, struct sk_buff *skb)
-{
-	struct fcoe_ctlr *fip = &fnic->ctlr;
-	struct fip_header *fiph;
-	struct fip_desc *desc;
-	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
-	u16 vid;
-	size_t rlen;
-	size_t dlen;
-	struct fcoe_vlan *vlan;
-	u64 sol_time;
-	unsigned long flags;
-
-	FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-		  "Received VLAN response...\n");
-
-	fiph = (struct fip_header *) skb->data;
-
-	FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-		  "Received VLAN response... OP 0x%x SUB_OP 0x%x\n",
-		  ntohs(fiph->fip_op), fiph->fip_subcode);
-
-	rlen = ntohs(fiph->fip_dl_len) * 4;
-	fnic_fcoe_reset_vlans(fnic);
-	spin_lock_irqsave(&fnic->vlans_lock, flags);
-	desc = (struct fip_desc *)(fiph + 1);
-	while (rlen > 0) {
-		dlen = desc->fip_dlen * FIP_BPW;
-		switch (desc->fip_dtype) {
-		case FIP_DT_VLAN:
-			vid = ntohs(((struct fip_vlan_desc *)desc)->fd_vlan);
-			shost_printk(KERN_INFO, fnic->lport->host,
-				  "process_vlan_resp: FIP VLAN %d\n", vid);
-			vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC);
-			if (!vlan) {
-				/* retry from timer */
-				spin_unlock_irqrestore(&fnic->vlans_lock,
-							flags);
-				goto out;
-			}
-			vlan->vid = vid & 0x0fff;
-			vlan->state = FIP_VLAN_AVAIL;
-			list_add_tail(&vlan->list, &fnic->vlans);
-			break;
-		}
-		desc = (struct fip_desc *)((char *)desc + dlen);
-		rlen -= dlen;
 	}
 
-	/* any VLAN descriptors present ? */
-	if (list_empty(&fnic->vlans)) {
-		/* retry from timer */
-		atomic64_inc(&fnic_stats->vlan_stats.resp_withno_vlanID);
-		FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-			  "No VLAN descriptors in FIP VLAN response\n");
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		goto out;
+	/* Do not process if the fnic is already in transitional state */
+	if ((fnic->state != FNIC_IN_ETH_MODE)
+		&& (fnic->state != FNIC_IN_FC_MODE)) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "fnic in transitional state: %d. link up: %d ignored",
+			 fnic->state, vnic_dev_link_status(fnic->vdev));
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Current link status: %d iport state: %d\n",
+			 fnic->link_status, fnic->iport.state);
+		return;
 	}
 
-	vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list);
-	fnic->set_vlan(fnic, vlan->vid);
-	vlan->state = FIP_VLAN_SENT; /* sent now */
-	vlan->sol_count++;
-	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-
-	/* start the solicitation */
-	fcoe_ctlr_link_up(fip);
-
-	sol_time = jiffies + msecs_to_jiffies(FCOE_CTLR_START_DELAY);
-	mod_timer(&fnic->fip_timer, round_jiffies(sol_time));
-out:
-	return;
-}
-
-static void fnic_fcoe_start_fcf_disc(struct fnic *fnic)
-{
-	unsigned long flags;
-	struct fcoe_vlan *vlan;
-	u64 sol_time;
-
-	spin_lock_irqsave(&fnic->vlans_lock, flags);
-	vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list);
-	fnic->set_vlan(fnic, vlan->vid);
-	vlan->state = FIP_VLAN_SENT; /* sent now */
-	vlan->sol_count = 1;
-	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-
-	/* start the solicitation */
-	fcoe_ctlr_link_up(&fnic->ctlr);
-
-	sol_time = jiffies + msecs_to_jiffies(FCOE_CTLR_START_DELAY);
-	mod_timer(&fnic->fip_timer, round_jiffies(sol_time));
-}
-
-static int fnic_fcoe_vlan_check(struct fnic *fnic, u16 flag)
-{
-	unsigned long flags;
-	struct fcoe_vlan *fvlan;
+	old_link_down_cnt = fnic->link_down_cnt;
+	old_link_status = fnic->link_status;
+	fnic->link_status = vnic_dev_link_status(fnic->vdev);
+	fnic->link_down_cnt = vnic_dev_link_down_cnt(fnic->vdev);
 
-	spin_lock_irqsave(&fnic->vlans_lock, flags);
-	if (list_empty(&fnic->vlans)) {
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		return -EINVAL;
+	while (fnic->reset_in_progress == IN_PROGRESS) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "fnic reset in progress. Link event needs to wait\n");
+
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "waiting for reset completion\n");
+		wait_for_completion_timeout(&fnic->reset_completion_wait,
+									msecs_to_jiffies(5000));
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "woken up from reset completion wait\n");
+		spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+
+		max_count++;
+		if (max_count >= MAX_RESET_WAIT_COUNT) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Rstth waited for too long. Skipping handle link event\n");
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			return;
+		}
 	}
-
-	fvlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list);
-	if (fvlan->state == FIP_VLAN_USED) {
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		return 0;
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Marking fnic reset in progress\n");
+	fnic->reset_in_progress = IN_PROGRESS;
+
+	if ((vnic_dev_get_intr_mode(fnic->vdev) != VNIC_DEV_INTR_MODE_MSI) ||
+		(fnic->link_status != old_link_status)) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "old link status: %d link status: %d\n",
+					 old_link_status, (int) fnic->link_status);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "old down count %d down count: %d\n",
+					 old_link_down_cnt, (int) fnic->link_down_cnt);
 	}
 
-	if (fvlan->state == FIP_VLAN_SENT) {
-		fvlan->state = FIP_VLAN_USED;
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		return 0;
+	if (old_link_status == fnic->link_status) {
+		if (!fnic->link_status) {
+			/* DOWN -> DOWN */
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "down->down\n");
+		} else {
+			if (old_link_down_cnt != fnic->link_down_cnt) {
+				/* UP -> DOWN -> UP */
+				spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "up->down. Link down\n");
+				fnic_fdls_link_status_change(fnic, 0);
+
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "down->up. Link up\n");
+				fnic_fdls_link_status_change(fnic, 1);
+			} else {
+				/* UP -> UP */
+				spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "up->up\n");
+			}
+		}
+	} else if (fnic->link_status) {
+		/* DOWN -> UP */
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "down->up. Link up\n");
+		fnic_fdls_link_status_change(fnic, 1);
+	} else {
+		/* UP -> DOWN */
+		spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "up->down. Link down\n");
+		fnic_fdls_link_status_change(fnic, 0);
 	}
-	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-	return -EINVAL;
-}
 
-static void fnic_event_enq(struct fnic *fnic, enum fnic_evt ev)
-{
-	struct fnic_event *fevt;
-	unsigned long flags;
-
-	fevt = kmalloc(sizeof(*fevt), GFP_ATOMIC);
-	if (!fevt)
-		return;
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	fnic->reset_in_progress = NOT_IN_PROGRESS;
+	complete(&fnic->reset_completion_wait);
 
-	fevt->fnic = fnic;
-	fevt->event = ev;
-
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	list_add_tail(&fevt->list, &fnic->evlist);
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-
-	schedule_work(&fnic->event_work);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Marking fnic reset completion\n");
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
 }
 
-static int fnic_fcoe_handle_fip_frame(struct fnic *fnic, struct sk_buff *skb)
+void fnic_handle_frame(struct work_struct *work)
 {
-	struct fip_header *fiph;
-	int ret = 1;
-	u16 op;
-	u8 sub;
+	struct fnic *fnic = container_of(work, struct fnic, frame_work);
+	struct fnic_frame_list *cur_frame, *next;
+	int fchdr_offset = 0;
 
-	if (!skb || !(skb->data))
-		return -1;
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	list_for_each_entry_safe(cur_frame, next, &fnic->frame_queue, links) {
+		if (fnic->stop_rx_link_events) {
+			list_del(&cur_frame->links);
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			kfree(cur_frame->fp);
+			mempool_free(cur_frame, fnic->frame_elem_pool);
+			return;
+		}
 
-	if (skb_linearize(skb))
-		goto drop;
+		/*
+		 * If we're in a transitional state, just re-queue and return.
+		 * The queue will be serviced when we get to a stable state.
+		 */
+		if (fnic->state != FNIC_IN_FC_MODE &&
+			fnic->state != FNIC_IN_ETH_MODE) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Cannot process frame in transitional state\n");
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			return;
+		}
 
-	fiph = (struct fip_header *)skb->data;
-	op = ntohs(fiph->fip_op);
-	sub = fiph->fip_subcode;
+		list_del(&cur_frame->links);
 
-	if (FIP_VER_DECAPS(fiph->fip_ver) != FIP_VER)
-		goto drop;
+		/* Frames from FCP_RQ will have ethhdrs stripped off */
+		fchdr_offset = (cur_frame->rx_ethhdr_stripped) ?
+			0 : FNIC_ETH_FCOE_HDRS_OFFSET;
 
-	if (ntohs(fiph->fip_dl_len) * FIP_BPW + sizeof(*fiph) > skb->len)
-		goto drop;
+		fnic_fdls_recv_frame(&fnic->iport, cur_frame->fp,
+							 cur_frame->frame_len, fchdr_offset);
 
-	if (op == FIP_OP_DISC && sub == FIP_SC_ADV) {
-		if (fnic_fcoe_vlan_check(fnic, ntohs(fiph->fip_flags)))
-			goto drop;
-		/* pass it on to fcoe */
-		ret = 1;
-	} else if (op == FIP_OP_VLAN && sub == FIP_SC_VL_NOTE) {
-		/* set the vlan as used */
-		fnic_fcoe_process_vlan_resp(fnic, skb);
-		ret = 0;
-	} else if (op == FIP_OP_CTRL && sub == FIP_SC_CLR_VLINK) {
-		/* received CVL request, restart vlan disc */
-		fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC);
-		/* pass it on to fcoe */
-		ret = 1;
+		kfree(cur_frame->fp);
+		mempool_free(cur_frame, fnic->frame_elem_pool);
 	}
-drop:
-	return ret;
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
 }
 
 void fnic_handle_fip_frame(struct work_struct *work)
 {
+	struct fnic_frame_list *cur_frame, *next;
 	struct fnic *fnic = container_of(work, struct fnic, fip_frame_work);
-	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
-	unsigned long flags;
-	struct sk_buff *skb;
-	struct ethhdr *eh;
 
-	while ((skb = skb_dequeue(&fnic->fip_frame_queue))) {
-		spin_lock_irqsave(&fnic->fnic_lock, flags);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Processing FIP frame\n");
+
+	spin_lock_irqsave(&fnic->fnic_lock, fnic->lock_flags);
+	list_for_each_entry_safe(cur_frame, next, &fnic->fip_frame_queue,
+							 links) {
 		if (fnic->stop_rx_link_events) {
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-			dev_kfree_skb(skb);
+			list_del(&cur_frame->links);
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
+			kfree(cur_frame->fp);
+			kfree(cur_frame);
 			return;
 		}
+
 		/*
 		 * If we're in a transitional state, just re-queue and return.
 		 * The queue will be serviced when we get to a stable state.
 		 */
 		if (fnic->state != FNIC_IN_FC_MODE &&
-		    fnic->state != FNIC_IN_ETH_MODE) {
-			skb_queue_head(&fnic->fip_frame_queue, skb);
-			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+			fnic->state != FNIC_IN_ETH_MODE) {
+			spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
 			return;
 		}
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		eh = (struct ethhdr *)skb->data;
-		if (eh->h_proto == htons(ETH_P_FIP)) {
-			skb_pull(skb, sizeof(*eh));
-			if (fnic_fcoe_handle_fip_frame(fnic, skb) <= 0) {
-				dev_kfree_skb(skb);
-				continue;
-			}
-			/*
-			 * If there's FLOGI rejects - clear all
-			 * fcf's & restart from scratch
-			 */
-			if (is_fnic_fip_flogi_reject(&fnic->ctlr, skb)) {
-				atomic64_inc(
-					&fnic_stats->vlan_stats.flogi_rejects);
-				shost_printk(KERN_INFO, fnic->lport->host,
-					  "Trigger a Link down - VLAN Disc\n");
-				fcoe_ctlr_link_down(&fnic->ctlr);
-				/* start FCoE VLAN discovery */
-				fnic_fcoe_send_vlan_req(fnic);
-				dev_kfree_skb(skb);
-				continue;
-			}
-			fcoe_ctlr_recv(&fnic->ctlr, skb);
-			continue;
+
+		list_del(&cur_frame->links);
+
+		if (fdls_fip_recv_frame(fnic, cur_frame->fp)) {
+			kfree(cur_frame->fp);
+			kfree(cur_frame);
 		}
 	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, fnic->lock_flags);
 }
 
 /**
  * fnic_import_rq_eth_pkt() - handle received FCoE or FIP frame.
  * @fnic:	fnic instance.
- * @skb:	Ethernet Frame.
+ * @fp:		Ethernet Frame.
  */
-static inline int fnic_import_rq_eth_pkt(struct fnic *fnic, struct sk_buff *skb)
+static inline int fnic_import_rq_eth_pkt(struct fnic *fnic, void *fp)
 {
-	struct fc_frame *fp;
 	struct ethhdr *eh;
-	struct fcoe_hdr *fcoe_hdr;
-	struct fcoe_crc_eof *ft;
+	struct fnic_frame_list *fip_fr_elem;
+	unsigned long flags;
 
-	/*
-	 * Undo VLAN encapsulation if present.
-	 */
-	eh = (struct ethhdr *)skb->data;
-	if (eh->h_proto == htons(ETH_P_8021Q)) {
-		memmove((u8 *)eh + VLAN_HLEN, eh, ETH_ALEN * 2);
-		eh = skb_pull(skb, VLAN_HLEN);
-		skb_reset_mac_header(skb);
-	}
-	if (eh->h_proto == htons(ETH_P_FIP)) {
-		if (!(fnic->config.flags & VFCF_FIP_CAPABLE)) {
-			printk(KERN_ERR "Dropped FIP frame, as firmware "
-					"uses non-FIP mode, Enable FIP "
-					"using UCSM\n");
-			goto drop;
-		}
-		if ((fnic_fc_trace_set_data(fnic->lport->host->host_no,
-			FNIC_FC_RECV|0x80, (char *)skb->data, skb->len)) != 0) {
-			printk(KERN_ERR "fnic ctlr frame trace error!!!");
-		}
-		skb_queue_tail(&fnic->fip_frame_queue, skb);
+	eh = (struct ethhdr *) fp;
+	if ((eh->h_proto == cpu_to_be16(ETH_P_FIP)) && (fnic->iport.usefip)) {
+		fip_fr_elem = (struct fnic_frame_list *)
+			kzalloc(sizeof(struct fnic_frame_list), GFP_ATOMIC);
+		if (!fip_fr_elem)
+			return 0;
+		fip_fr_elem->fp = fp;
+		spin_lock_irqsave(&fnic->fnic_lock, flags);
+		list_add_tail(&fip_fr_elem->links, &fnic->fip_frame_queue);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		queue_work(fnic_fip_queue, &fnic->fip_frame_work);
-		return 1;		/* let caller know packet was used */
-	}
-	if (eh->h_proto != htons(ETH_P_FCOE))
-		goto drop;
-	skb_set_network_header(skb, sizeof(*eh));
-	skb_pull(skb, sizeof(*eh));
-
-	fcoe_hdr = (struct fcoe_hdr *)skb->data;
-	if (FC_FCOE_DECAPS_VER(fcoe_hdr) != FC_FCOE_VER)
-		goto drop;
-
-	fp = (struct fc_frame *)skb;
-	fc_frame_init(fp);
-	fr_sof(fp) = fcoe_hdr->fcoe_sof;
-	skb_pull(skb, sizeof(struct fcoe_hdr));
-	skb_reset_transport_header(skb);
-
-	ft = (struct fcoe_crc_eof *)(skb->data + skb->len - sizeof(*ft));
-	fr_eof(fp) = ft->fcoe_eof;
-	skb_trim(skb, skb->len - sizeof(*ft));
-	return 0;
-drop:
-	dev_kfree_skb_irq(skb);
-	return -1;
+		return 1;				/* let caller know packet was used */
+	} else
+		return 0;
 }
 
 /**
@@ -720,206 +398,147 @@ drop:
  */
 void fnic_update_mac_locked(struct fnic *fnic, u8 *new)
 {
-	u8 *ctl = fnic->ctlr.ctl_src_addr;
+	struct fnic_iport_s *iport = &fnic->iport;
+	u8 *ctl = iport->hwmac;
 	u8 *data = fnic->data_src_addr;
 
 	if (is_zero_ether_addr(new))
 		new = ctl;
 	if (ether_addr_equal(data, new))
 		return;
-	FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			"update_mac %pM\n", new);
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Update MAC: %u\n", *new);
+
 	if (!is_zero_ether_addr(data) && !ether_addr_equal(data, ctl))
 		vnic_dev_del_addr(fnic->vdev, data);
+
 	memcpy(data, new, ETH_ALEN);
 	if (!ether_addr_equal(new, ctl))
 		vnic_dev_add_addr(fnic->vdev, new);
 }
 
-/**
- * fnic_update_mac() - set data MAC address and filters.
- * @lport:	local port.
- * @new:	newly-assigned FCoE MAC address.
- */
-void fnic_update_mac(struct fc_lport *lport, u8 *new)
-{
-	struct fnic *fnic = lport_priv(lport);
-
-	spin_lock_irq(&fnic->fnic_lock);
-	fnic_update_mac_locked(fnic, new);
-	spin_unlock_irq(&fnic->fnic_lock);
-}
-
-/**
- * fnic_set_port_id() - set the port_ID after successful FLOGI.
- * @lport:	local port.
- * @port_id:	assigned FC_ID.
- * @fp:		received frame containing the FLOGI accept or NULL.
- *
- * This is called from libfc when a new FC_ID has been assigned.
- * This causes us to reset the firmware to FC_MODE and setup the new MAC
- * address and FC_ID.
- *
- * It is also called with FC_ID 0 when we're logged off.
- *
- * If the FC_ID is due to point-to-point, fp may be NULL.
- */
-void fnic_set_port_id(struct fc_lport *lport, u32 port_id, struct fc_frame *fp)
-{
-	struct fnic *fnic = lport_priv(lport);
-	u8 *mac;
-	int ret;
-
-	FNIC_FCS_DBG(KERN_DEBUG, lport->host, fnic->fnic_num,
-			"set port_id 0x%x fp 0x%p\n",
-			port_id, fp);
-
-	/*
-	 * If we're clearing the FC_ID, change to use the ctl_src_addr.
-	 * Set ethernet mode to send FLOGI.
-	 */
-	if (!port_id) {
-		fnic_update_mac(lport, fnic->ctlr.ctl_src_addr);
-		fnic_set_eth_mode(fnic);
-		return;
-	}
-
-	if (fp) {
-		mac = fr_cb(fp)->granted_mac;
-		if (is_zero_ether_addr(mac)) {
-			/* non-FIP - FLOGI already accepted - ignore return */
-			fcoe_ctlr_recv_flogi(&fnic->ctlr, lport, fp);
-		}
-		fnic_update_mac(lport, mac);
-	}
-
-	/* Change state to reflect transition to FC mode */
-	spin_lock_irq(&fnic->fnic_lock);
-	if (fnic->state == FNIC_IN_ETH_MODE || fnic->state == FNIC_IN_FC_MODE)
-		fnic->state = FNIC_IN_ETH_TRANS_FC_MODE;
-	else {
-		FNIC_FCS_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
-			     "Unexpected fnic state: %s processing FLOGI response",
-				 fnic_state_to_str(fnic->state));
-		spin_unlock_irq(&fnic->fnic_lock);
-		return;
-	}
-	spin_unlock_irq(&fnic->fnic_lock);
-
-	/*
-	 * Send FLOGI registration to firmware to set up FC mode.
-	 * The new address will be set up when registration completes.
-	 */
-	ret = fnic_flogi_reg_handler(fnic, port_id);
-
-	if (ret < 0) {
-		spin_lock_irq(&fnic->fnic_lock);
-		if (fnic->state == FNIC_IN_ETH_TRANS_FC_MODE)
-			fnic->state = FNIC_IN_ETH_MODE;
-		spin_unlock_irq(&fnic->fnic_lock);
-	}
-}
-
 static void fnic_rq_cmpl_frame_recv(struct vnic_rq *rq, struct cq_desc
 				    *cq_desc, struct vnic_rq_buf *buf,
 				    int skipped __attribute__((unused)),
 				    void *opaque)
 {
 	struct fnic *fnic = vnic_dev_priv(rq->vdev);
-	struct sk_buff *skb;
-	struct fc_frame *fp;
+	uint8_t *fp;
 	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+	unsigned int ethhdr_stripped;
 	u8 type, color, eop, sop, ingress_port, vlan_stripped;
-	u8 fcoe = 0, fcoe_sof, fcoe_eof;
-	u8 fcoe_fc_crc_ok = 1, fcoe_enc_error = 0;
-	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
-	u8 ipv6, ipv4, ipv4_fragment, rss_type, csum_not_calc;
+	u8 fcoe_fnic_crc_ok = 1, fcoe_enc_error = 0;
 	u8 fcs_ok = 1, packet_error = 0;
-	u16 q_number, completed_index, bytes_written = 0, vlan, checksum;
+	u16 q_number, completed_index, vlan;
 	u32 rss_hash;
+	u16 checksum;
+	u8 csum_not_calc, rss_type, ipv4, ipv6, ipv4_fragment;
+	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
+	u8 fcoe = 0, fcoe_sof, fcoe_eof;
 	u16 exchange_id, tmpl;
 	u8 sof = 0;
 	u8 eof = 0;
 	u32 fcp_bytes_written = 0;
+	u16 enet_bytes_written = 0;
+	u32 bytes_written = 0;
 	unsigned long flags;
+	struct fnic_frame_list *frame_elem = NULL;
+	struct ethhdr *eh;
 
 	dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len,
-			 DMA_FROM_DEVICE);
-	skb = buf->os_buf;
-	fp = (struct fc_frame *)skb;
+					 DMA_FROM_DEVICE);
+	fp = (uint8_t *) buf->os_buf;
 	buf->os_buf = NULL;
 
 	cq_desc_dec(cq_desc, &type, &color, &q_number, &completed_index);
 	if (type == CQ_DESC_TYPE_RQ_FCP) {
-		cq_fcp_rq_desc_dec((struct cq_fcp_rq_desc *)cq_desc,
-				   &type, &color, &q_number, &completed_index,
-				   &eop, &sop, &fcoe_fc_crc_ok, &exchange_id,
-				   &tmpl, &fcp_bytes_written, &sof, &eof,
-				   &ingress_port, &packet_error,
-				   &fcoe_enc_error, &fcs_ok, &vlan_stripped,
-				   &vlan);
-		skb_trim(skb, fcp_bytes_written);
-		fr_sof(fp) = sof;
-		fr_eof(fp) = eof;
-
+		cq_fcp_rq_desc_dec((struct cq_fcp_rq_desc *) cq_desc, &type,
+						   &color, &q_number, &completed_index, &eop, &sop,
+						   &fcoe_fnic_crc_ok, &exchange_id, &tmpl,
+						   &fcp_bytes_written, &sof, &eof, &ingress_port,
+						   &packet_error, &fcoe_enc_error, &fcs_ok,
+						   &vlan_stripped, &vlan);
+		ethhdr_stripped = 1;
+		bytes_written = fcp_bytes_written;
 	} else if (type == CQ_DESC_TYPE_RQ_ENET) {
-		cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc,
-				    &type, &color, &q_number, &completed_index,
-				    &ingress_port, &fcoe, &eop, &sop,
-				    &rss_type, &csum_not_calc, &rss_hash,
-				    &bytes_written, &packet_error,
-				    &vlan_stripped, &vlan, &checksum,
-				    &fcoe_sof, &fcoe_fc_crc_ok,
-				    &fcoe_enc_error, &fcoe_eof,
-				    &tcp_udp_csum_ok, &udp, &tcp,
-				    &ipv4_csum_ok, &ipv6, &ipv4,
-				    &ipv4_fragment, &fcs_ok);
-		skb_trim(skb, bytes_written);
+		cq_enet_rq_desc_dec((struct cq_enet_rq_desc *) cq_desc, &type,
+					&color, &q_number, &completed_index,
+					&ingress_port, &fcoe, &eop, &sop, &rss_type,
+					&csum_not_calc, &rss_hash, &enet_bytes_written,
+					&packet_error, &vlan_stripped, &vlan,
+					&checksum, &fcoe_sof, &fcoe_fnic_crc_ok,
+					&fcoe_enc_error, &fcoe_eof, &tcp_udp_csum_ok,
+					&udp, &tcp, &ipv4_csum_ok, &ipv6, &ipv4,
+					&ipv4_fragment, &fcs_ok);
+
+		ethhdr_stripped = 0;
+		bytes_written = enet_bytes_written;
+
 		if (!fcs_ok) {
 			atomic64_inc(&fnic_stats->misc_stats.frame_errors);
-			FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-				     "fcs error.  dropping packet.\n");
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "fnic 0x%p fcs error.  Dropping packet.\n", fnic);
 			goto drop;
 		}
-		if (fnic_import_rq_eth_pkt(fnic, skb))
-			return;
+		eh = (struct ethhdr *) fp;
+		if (eh->h_proto != cpu_to_be16(ETH_P_FCOE)) {
 
+			if (fnic_import_rq_eth_pkt(fnic, fp))
+				return;
+
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "Dropping h_proto 0x%x",
+							 be16_to_cpu(eh->h_proto));
+			goto drop;
+		}
 	} else {
-		/* wrong CQ type*/
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "fnic rq_cmpl wrong cq type x%x\n", type);
+		/* wrong CQ type */
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "fnic rq_cmpl wrong cq type x%x\n", type);
 		goto drop;
 	}
 
-	if (!fcs_ok || packet_error || !fcoe_fc_crc_ok || fcoe_enc_error) {
+	if (!fcs_ok || packet_error || !fcoe_fnic_crc_ok || fcoe_enc_error) {
 		atomic64_inc(&fnic_stats->misc_stats.frame_errors);
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			     "fnic rq_cmpl fcoe x%x fcsok x%x"
-			     " pkterr x%x fcoe_fc_crc_ok x%x, fcoe_enc_err"
-			     " x%x\n",
-			     fcoe, fcs_ok, packet_error,
-			     fcoe_fc_crc_ok, fcoe_enc_error);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "fcoe %x fcsok %x pkterr %x ffco %x fee %x\n",
+			 fcoe, fcs_ok, packet_error,
+			 fcoe_fnic_crc_ok, fcoe_enc_error);
 		goto drop;
 	}
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	if (fnic->stop_rx_link_events) {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "fnic->stop_rx_link_events: %d\n",
+					 fnic->stop_rx_link_events);
 		goto drop;
 	}
-	fr_dev(fp) = fnic->lport;
+
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-	if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_RECV,
-					(char *)skb->data, skb->len)) != 0) {
-		printk(KERN_ERR "fnic ctlr frame trace error!!!");
+
+	frame_elem = mempool_alloc(fnic->frame_elem_pool,
+					GFP_ATOMIC | __GFP_ZERO);
+	if (!frame_elem) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Failed to allocate memory for frame elem");
+		goto drop;
 	}
+	frame_elem->fp = fp;
+	frame_elem->rx_ethhdr_stripped = ethhdr_stripped;
+	frame_elem->frame_len = bytes_written;
 
-	skb_queue_tail(&fnic->frame_queue, skb);
-	queue_work(fnic_event_queue, &fnic->frame_work);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	list_add_tail(&frame_elem->links, &fnic->frame_queue);
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
+	queue_work(fnic_event_queue, &fnic->frame_work);
 	return;
+
 drop:
-	dev_kfree_skb_irq(skb);
+	kfree(fp);
 }
 
 static int fnic_rq_cmpl_handler_cont(struct vnic_dev *vdev,
@@ -945,10 +564,10 @@ int fnic_rq_cmpl_handler(struct fnic *fnic, int rq_work_to_do)
 		cur_work_done = vnic_cq_service(&fnic->cq[i], rq_work_to_do,
 						fnic_rq_cmpl_handler_cont,
 						NULL);
-		if (cur_work_done) {
+		if (cur_work_done && fnic->stop_rx_link_events != 1) {
 			err = vnic_rq_fill(&fnic->rq[i], fnic_alloc_rq_frame);
 			if (err)
-				shost_printk(KERN_ERR, fnic->lport->host,
+				shost_printk(KERN_ERR, fnic->host,
 					     "fnic_alloc_rq_frame can't alloc"
 					     " frame\n");
 		}
@@ -966,218 +585,179 @@ int fnic_rq_cmpl_handler(struct fnic *fnic, int rq_work_to_do)
 int fnic_alloc_rq_frame(struct vnic_rq *rq)
 {
 	struct fnic *fnic = vnic_dev_priv(rq->vdev);
-	struct sk_buff *skb;
+	void *buf;
 	u16 len;
 	dma_addr_t pa;
-	int r;
+	int ret;
 
-	len = FC_FRAME_HEADROOM + FC_MAX_FRAME + FC_FRAME_TAILROOM;
-	skb = dev_alloc_skb(len);
-	if (!skb) {
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			     "Unable to allocate RQ sk_buff\n");
+	len = FNIC_FRAME_HT_ROOM;
+	buf = kmalloc(len, GFP_ATOMIC);
+	if (!buf) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Unable to allocate RQ buffer of size: %d\n", len);
 		return -ENOMEM;
 	}
-	skb_reset_mac_header(skb);
-	skb_reset_transport_header(skb);
-	skb_reset_network_header(skb);
-	skb_put(skb, len);
-	pa = dma_map_single(&fnic->pdev->dev, skb->data, len, DMA_FROM_DEVICE);
+
+	pa = dma_map_single(&fnic->pdev->dev, buf, len, DMA_FROM_DEVICE);
 	if (dma_mapping_error(&fnic->pdev->dev, pa)) {
-		r = -ENOMEM;
-		printk(KERN_ERR "PCI mapping failed with error %d\n", r);
-		goto free_skb;
+		ret = -ENOMEM;
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "PCI mapping failed with error %d\n", ret);
+		goto free_buf;
 	}
 
-	fnic_queue_rq_desc(rq, skb, pa, len);
+	fnic_queue_rq_desc(rq, buf, pa, len);
 	return 0;
-
-free_skb:
-	kfree_skb(skb);
-	return r;
+free_buf:
+	kfree(buf);
+	return ret;
 }
 
 void fnic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
 {
-	struct fc_frame *fp = buf->os_buf;
+	void *rq_buf = buf->os_buf;
 	struct fnic *fnic = vnic_dev_priv(rq->vdev);
 
 	dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len,
 			 DMA_FROM_DEVICE);
 
-	dev_kfree_skb(fp_skb(fp));
+	kfree(rq_buf);
 	buf->os_buf = NULL;
 }
 
-/**
- * fnic_eth_send() - Send Ethernet frame.
- * @fip:	fcoe_ctlr instance.
- * @skb:	Ethernet Frame, FIP, without VLAN encapsulation.
- */
-void fnic_eth_send(struct fcoe_ctlr *fip, struct sk_buff *skb)
-{
-	struct fnic *fnic = fnic_from_ctlr(fip);
-	struct vnic_wq *wq = &fnic->wq[0];
-	dma_addr_t pa;
-	struct ethhdr *eth_hdr;
-	struct vlan_ethhdr *vlan_hdr;
-	unsigned long flags;
-
-	if (!fnic->vlan_hw_insert) {
-		eth_hdr = (struct ethhdr *)skb_mac_header(skb);
-		vlan_hdr = skb_push(skb, sizeof(*vlan_hdr) - sizeof(*eth_hdr));
-		memcpy(vlan_hdr, eth_hdr, 2 * ETH_ALEN);
-		vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q);
-		vlan_hdr->h_vlan_encapsulated_proto = eth_hdr->h_proto;
-		vlan_hdr->h_vlan_TCI = htons(fnic->vlan_id);
-		if ((fnic_fc_trace_set_data(fnic->lport->host->host_no,
-			FNIC_FC_SEND|0x80, (char *)eth_hdr, skb->len)) != 0) {
-			printk(KERN_ERR "fnic ctlr frame trace error!!!");
-		}
-	} else {
-		if ((fnic_fc_trace_set_data(fnic->lport->host->host_no,
-			FNIC_FC_SEND|0x80, (char *)skb->data, skb->len)) != 0) {
-			printk(KERN_ERR "fnic ctlr frame trace error!!!");
-		}
-	}
-
-	pa = dma_map_single(&fnic->pdev->dev, skb->data, skb->len,
-			DMA_TO_DEVICE);
-	if (dma_mapping_error(&fnic->pdev->dev, pa)) {
-		printk(KERN_ERR "DMA mapping failed\n");
-		goto free_skb;
-	}
-
-	spin_lock_irqsave(&fnic->wq_lock[0], flags);
-	if (!vnic_wq_desc_avail(wq))
-		goto irq_restore;
-
-	fnic_queue_wq_eth_desc(wq, skb, pa, skb->len,
-			       0 /* hw inserts cos value */,
-			       fnic->vlan_id, 1);
-	spin_unlock_irqrestore(&fnic->wq_lock[0], flags);
-	return;
-
-irq_restore:
-	spin_unlock_irqrestore(&fnic->wq_lock[0], flags);
-	dma_unmap_single(&fnic->pdev->dev, pa, skb->len, DMA_TO_DEVICE);
-free_skb:
-	kfree_skb(skb);
-}
-
 /*
  * Send FC frame.
  */
-static int fnic_send_frame(struct fnic *fnic, struct fc_frame *fp)
+static int fnic_send_frame(struct fnic *fnic, void *frame, int frame_len)
 {
 	struct vnic_wq *wq = &fnic->wq[0];
-	struct sk_buff *skb;
 	dma_addr_t pa;
-	struct ethhdr *eth_hdr;
-	struct vlan_ethhdr *vlan_hdr;
-	struct fcoe_hdr *fcoe_hdr;
-	struct fc_frame_header *fh;
-	u32 tot_len, eth_hdr_len;
 	int ret = 0;
 	unsigned long flags;
 
-	fh = fc_frame_header_get(fp);
-	skb = fp_skb(fp);
+	pa = dma_map_single(&fnic->pdev->dev, frame, frame_len, DMA_TO_DEVICE);
 
-	if (unlikely(fh->fh_r_ctl == FC_RCTL_ELS_REQ) &&
-	    fcoe_ctlr_els_send(&fnic->ctlr, fnic->lport, skb))
-		return 0;
-
-	if (!fnic->vlan_hw_insert) {
-		eth_hdr_len = sizeof(*vlan_hdr) + sizeof(*fcoe_hdr);
-		vlan_hdr = skb_push(skb, eth_hdr_len);
-		eth_hdr = (struct ethhdr *)vlan_hdr;
-		vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q);
-		vlan_hdr->h_vlan_encapsulated_proto = htons(ETH_P_FCOE);
-		vlan_hdr->h_vlan_TCI = htons(fnic->vlan_id);
-		fcoe_hdr = (struct fcoe_hdr *)(vlan_hdr + 1);
-	} else {
-		eth_hdr_len = sizeof(*eth_hdr) + sizeof(*fcoe_hdr);
-		eth_hdr = skb_push(skb, eth_hdr_len);
-		eth_hdr->h_proto = htons(ETH_P_FCOE);
-		fcoe_hdr = (struct fcoe_hdr *)(eth_hdr + 1);
-	}
-
-	if (fnic->ctlr.map_dest)
-		fc_fcoe_set_mac(eth_hdr->h_dest, fh->fh_d_id);
-	else
-		memcpy(eth_hdr->h_dest, fnic->ctlr.dest_addr, ETH_ALEN);
-	memcpy(eth_hdr->h_source, fnic->data_src_addr, ETH_ALEN);
-
-	tot_len = skb->len;
-	BUG_ON(tot_len % 4);
-
-	memset(fcoe_hdr, 0, sizeof(*fcoe_hdr));
-	fcoe_hdr->fcoe_sof = fr_sof(fp);
-	if (FC_FCOE_VER)
-		FC_FCOE_ENCAPS_VER(fcoe_hdr, FC_FCOE_VER);
-
-	pa = dma_map_single(&fnic->pdev->dev, eth_hdr, tot_len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&fnic->pdev->dev, pa)) {
-		ret = -ENOMEM;
-		printk(KERN_ERR "DMA map failed with error %d\n", ret);
-		goto free_skb_on_err;
-	}
-
-	if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_SEND,
-				(char *)eth_hdr, tot_len)) != 0) {
-		printk(KERN_ERR "fnic ctlr frame trace error!!!");
+	if ((fnic_fc_trace_set_data(fnic->fnic_num,
+				FNIC_FC_SEND | 0x80, (char *) frame,
+				frame_len)) != 0) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "fnic ctlr frame trace error");
 	}
 
 	spin_lock_irqsave(&fnic->wq_lock[0], flags);
 
 	if (!vnic_wq_desc_avail(wq)) {
-		dma_unmap_single(&fnic->pdev->dev, pa, tot_len, DMA_TO_DEVICE);
+		dma_unmap_single(&fnic->pdev->dev, pa, frame_len, DMA_TO_DEVICE);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "vnic work queue descriptor is not available");
 		ret = -1;
-		goto irq_restore;
+		goto fnic_send_frame_end;
 	}
 
-	fnic_queue_wq_desc(wq, skb, pa, tot_len, fr_eof(fp),
-			   0 /* hw inserts cos value */,
-			   fnic->vlan_id, 1, 1, 1);
+	/* hw inserts cos value */
+	fnic_queue_wq_desc(wq, frame, pa, frame_len, FC_EOF_T,
+					   0, fnic->vlan_id, 1, 1, 1);
 
-irq_restore:
+fnic_send_frame_end:
 	spin_unlock_irqrestore(&fnic->wq_lock[0], flags);
-
-free_skb_on_err:
-	if (ret)
-		dev_kfree_skb_any(fp_skb(fp));
-
 	return ret;
 }
 
-/*
- * fnic_send
- * Routine to send a raw frame
+/**
+ * fdls_send_fcoe_frame - send a filled-in FC frame, filling in eth and FCoE
+ *	info. This interface is used only in the non fast path. (login, fabric
+ *	registrations etc.)
+ *
+ * @fnic:	fnic instance
+ * @frame:	frame structure with FC payload filled in
+ * @frame_size:	length of the frame to be sent
+ * @srcmac:	source mac address
+ * @dstmac:	destination mac address
+ *
+ * Called with the fnic lock held.
  */
-int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
+static int
+fdls_send_fcoe_frame(struct fnic *fnic, void *frame, int frame_size,
+					 uint8_t *srcmac, uint8_t *dstmac)
 {
-	struct fnic *fnic = lport_priv(lp);
-	unsigned long flags;
+	struct ethhdr *pethhdr;
+	struct fcoe_hdr *pfcoe_hdr;
+	struct fnic_frame_list *frame_elem;
+	int len = frame_size;
+	int ret;
+	struct fc_frame_header *fchdr = (struct fc_frame_header *) (frame +
+			FNIC_ETH_FCOE_HDRS_OFFSET);
 
-	if (fnic->in_remove) {
-		dev_kfree_skb(fp_skb(fp));
-		return -1;
-	}
+	pethhdr = (struct ethhdr *) frame;
+	pethhdr->h_proto = cpu_to_be16(ETH_P_FCOE);
+	memcpy(pethhdr->h_source, srcmac, ETH_ALEN);
+	memcpy(pethhdr->h_dest, dstmac, ETH_ALEN);
+
+	pfcoe_hdr = (struct fcoe_hdr *) (frame + sizeof(struct ethhdr));
+	pfcoe_hdr->fcoe_sof = FC_SOF_I3;
 
 	/*
 	 * Queue frame if in a transitional state.
 	 * This occurs while registering the Port_ID / MAC address after FLOGI.
 	 */
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (fnic->state != FNIC_IN_FC_MODE && fnic->state != FNIC_IN_ETH_MODE) {
-		skb_queue_tail(&fnic->tx_queue, fp_skb(fp));
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	if ((fnic->state != FNIC_IN_FC_MODE)
+		&& (fnic->state != FNIC_IN_ETH_MODE)) {
+		frame_elem = mempool_alloc(fnic->frame_elem_pool,
+						GFP_ATOMIC | __GFP_ZERO);
+		if (!frame_elem) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Failed to allocate memory for frame elem");
+			return -ENOMEM;
+		}
+
+		FNIC_FCS_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+			"Queueing FC frame: sid/did/type/oxid = 0x%x/0x%x/0x%x/0x%x\n",
+			ntoh24(fchdr->fh_s_id), ntoh24(fchdr->fh_d_id),
+			fchdr->fh_type, FNIC_STD_GET_OX_ID(fchdr));
+		frame_elem->fp = frame;
+		frame_elem->frame_len = len;
+		list_add_tail(&frame_elem->links, &fnic->tx_queue);
 		return 0;
 	}
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	return fnic_send_frame(fnic, fp);
+	fnic_debug_dump_fc_frame(fnic, fchdr, frame_size, "Outgoing");
+
+	ret = fnic_send_frame(fnic, frame, len);
+	return ret;
+}
+
+void fnic_send_fcoe_frame(struct fnic_iport_s *iport, void *frame,
+						 int frame_size)
+{
+	struct fnic *fnic = iport->fnic;
+	uint8_t *dstmac, *srcmac;
+
+	/* If module unload is in-progress, don't send */
+	if (fnic->in_remove)
+		return;
+
+	if (iport->fabric.flags & FNIC_FDLS_FPMA_LEARNT) {
+		srcmac = iport->fpma;
+		dstmac = iport->fcfmac;
+	} else {
+		srcmac = iport->hwmac;
+		dstmac = FCOE_ALL_FCF_MAC;
+	}
+
+	fdls_send_fcoe_frame(fnic, frame, frame_size, srcmac, dstmac);
+}
+
+int
+fnic_send_fip_frame(struct fnic_iport_s *iport, void *frame,
+					int frame_size)
+{
+	struct fnic *fnic = iport->fnic;
+
+	if (fnic->in_remove)
+		return -1;
+
+	fnic_debug_dump_fip_frame(fnic, frame, frame_size, "Outgoing");
+	return fnic_send_frame(fnic, frame, frame_size);
 }
 
 /**
@@ -1193,64 +773,87 @@ int fnic_send(struct fc_lport *lp, struct fc_frame *fp)
 void fnic_flush_tx(struct work_struct *work)
 {
 	struct fnic *fnic = container_of(work, struct fnic, flush_work);
-	struct sk_buff *skb;
 	struct fc_frame *fp;
+	struct fnic_frame_list *cur_frame, *next;
 
-	while ((skb = skb_dequeue(&fnic->tx_queue))) {
-		fp = (struct fc_frame *)skb;
-		fnic_send_frame(fnic, fp);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Flush queued frames");
+
+	list_for_each_entry_safe(cur_frame, next, &fnic->tx_queue, links) {
+		fp = cur_frame->fp;
+		list_del(&cur_frame->links);
+		fnic_send_frame(fnic, fp, cur_frame->frame_len);
+		mempool_free(cur_frame, fnic->frame_elem_pool);
 	}
 }
 
-/**
- * fnic_set_eth_mode() - put fnic into ethernet mode.
- * @fnic: fnic device
- *
- * Called without fnic lock held.
- */
-static void fnic_set_eth_mode(struct fnic *fnic)
+int
+fnic_fdls_register_portid(struct fnic_iport_s *iport, u32 port_id,
+						  void *fp)
 {
-	unsigned long flags;
-	enum fnic_state old_state;
+	struct fnic *fnic = iport->fnic;
+	struct ethhdr *ethhdr;
 	int ret;
 
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-again:
-	old_state = fnic->state;
-	switch (old_state) {
-	case FNIC_IN_FC_MODE:
-	case FNIC_IN_ETH_TRANS_FC_MODE:
-	default:
-		fnic->state = FNIC_IN_FC_TRANS_ETH_MODE;
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Setting port id: 0x%x fp: 0x%p fnic state: %d", port_id,
+				 fp, fnic->state);
 
-		ret = fnic_fw_reset_handler(fnic);
+	if (fp) {
+		ethhdr = (struct ethhdr *) fp;
+		vnic_dev_add_addr(fnic->vdev, ethhdr->h_dest);
+	}
 
-		spin_lock_irqsave(&fnic->fnic_lock, flags);
-		if (fnic->state != FNIC_IN_FC_TRANS_ETH_MODE)
-			goto again;
-		if (ret)
-			fnic->state = old_state;
-		break;
-
-	case FNIC_IN_FC_TRANS_ETH_MODE:
-	case FNIC_IN_ETH_MODE:
-		break;
+	/* Change state to reflect transition to FC mode */
+	if (fnic->state == FNIC_IN_ETH_MODE || fnic->state == FNIC_IN_FC_MODE)
+		fnic->state = FNIC_IN_ETH_TRANS_FC_MODE;
+	else {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "Unexpected fnic state while processing FLOGI response\n");
+		return -1;
+	}
+
+	/*
+	 * Send FLOGI registration to firmware to set up FC mode.
+	 * The new address will be set up when registration completes.
+	 */
+	ret = fnic_flogi_reg_handler(fnic, port_id);
+	if (ret < 0) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "FLOGI registration error ret: %d fnic state: %d\n",
+					 ret, fnic->state);
+		if (fnic->state == FNIC_IN_ETH_TRANS_FC_MODE)
+			fnic->state = FNIC_IN_ETH_MODE;
+
+		return -1;
+	}
+	iport->fabric.flags |= FNIC_FDLS_FPMA_LEARNT;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "FLOGI registration success\n");
+	return 0;
+}
+
+void fnic_free_txq(struct list_head *head)
+{
+	struct fnic_frame_list *cur_frame, *next;
+
+	list_for_each_entry_safe(cur_frame, next, head, links) {
+		list_del(&cur_frame->links);
+		kfree(cur_frame->fp);
+		kfree(cur_frame);
 	}
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 }
 
 static void fnic_wq_complete_frame_send(struct vnic_wq *wq,
 					struct cq_desc *cq_desc,
 					struct vnic_wq_buf *buf, void *opaque)
 {
-	struct sk_buff *skb = buf->os_buf;
-	struct fc_frame *fp = (struct fc_frame *)skb;
 	struct fnic *fnic = vnic_dev_priv(wq->vdev);
 
 	dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len,
 			 DMA_TO_DEVICE);
-	dev_kfree_skb_irq(fp_skb(fp));
+	mempool_free(buf->os_buf, fnic->frame_pool);
 	buf->os_buf = NULL;
 }
 
@@ -1288,119 +891,218 @@ int fnic_wq_cmpl_handler(struct fnic *fnic, int work_to_do)
 
 void fnic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
 {
-	struct fc_frame *fp = buf->os_buf;
 	struct fnic *fnic = vnic_dev_priv(wq->vdev);
 
 	dma_unmap_single(&fnic->pdev->dev, buf->dma_addr, buf->len,
 			 DMA_TO_DEVICE);
 
-	dev_kfree_skb(fp_skb(fp));
+	kfree(buf->os_buf);
 	buf->os_buf = NULL;
 }
 
-void fnic_fcoe_reset_vlans(struct fnic *fnic)
+void
+fnic_fdls_add_tport(struct fnic_iport_s *iport, struct fnic_tport_s *tport,
+					unsigned long flags)
+{
+	struct fnic *fnic = iport->fnic;
+	struct fc_rport *rport;
+	struct fc_rport_identifiers ids;
+	struct rport_dd_data_s *rdd_data;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Adding rport fcid: 0x%x", tport->fcid);
+
+	ids.node_name = tport->wwnn;
+	ids.port_name = tport->wwpn;
+	ids.port_id = tport->fcid;
+	ids.roles = FC_RPORT_ROLE_FCP_TARGET;
+
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	rport = fc_remote_port_add(fnic->host, 0, &ids);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	if (!rport) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Failed to add rport for tport: 0x%x", tport->fcid);
+		return;
+	}
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "Added rport fcid: 0x%x", tport->fcid);
+
+	/* Mimic these assignments in queuecommand to avoid timing issues */
+	rport->maxframe_size = FNIC_FC_MAX_PAYLOAD_LEN;
+	rport->supported_classes = FC_COS_CLASS3 | FC_RPORT_ROLE_FCP_TARGET;
+	rdd_data = rport->dd_data;
+	rdd_data->tport = tport;
+	rdd_data->iport = iport;
+	tport->rport = rport;
+	tport->flags |= FNIC_FDLS_SCSI_REGISTERED;
+}
+
+void
+fnic_fdls_remove_tport(struct fnic_iport_s *iport,
+					   struct fnic_tport_s *tport, unsigned long flags)
+{
+	struct fnic *fnic = iport->fnic;
+	struct rport_dd_data_s *rdd_data;
+
+	struct fc_rport *rport;
+
+	if (!tport)
+		return;
+
+	fdls_set_tport_state(tport, FDLS_TGT_STATE_OFFLINE);
+	rport = tport->rport;
+
+	if (rport) {
+		/* tport resource release will be done
+		 * after fnic_terminate_rport_io()
+		 */
+		tport->flags |= FNIC_FDLS_TPORT_DELETED;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
+		/* Interface to scsi_fc_transport  */
+		fc_remote_port_delete(rport);
+
+		spin_lock_irqsave(&fnic->fnic_lock, flags);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "Deregistered and freed tport fcid: 0x%x from scsi transport fc",
+		 tport->fcid);
+
+		/*
+		 * the dd_data is allocated by fc transport
+		 * of size dd_fcrport_size
+		 */
+		rdd_data = rport->dd_data;
+		rdd_data->tport = NULL;
+		rdd_data->iport = NULL;
+		list_del(&tport->links);
+		kfree(tport);
+	} else {
+		fnic_del_tport_timer_sync(fnic, tport);
+		list_del(&tport->links);
+		kfree(tport);
+	}
+}
+
+void fnic_delete_fcp_tports(struct fnic *fnic)
 {
+	struct fnic_tport_s *tport, *next;
 	unsigned long flags;
-	struct fcoe_vlan *vlan;
-	struct fcoe_vlan *next;
 
-	/*
-	 * indicate a link down to fcoe so that all fcf's are free'd
-	 * might not be required since we did this before sending vlan
-	 * discovery request
-	 */
-	spin_lock_irqsave(&fnic->vlans_lock, flags);
-	if (!list_empty(&fnic->vlans)) {
-		list_for_each_entry_safe(vlan, next, &fnic->vlans, list) {
-			list_del(&vlan->list);
-			kfree(vlan);
-		}
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	list_for_each_entry_safe(tport, next, &fnic->iport.tport_list, links) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "removing fcp rport fcid: 0x%x", tport->fcid);
+		fdls_set_tport_state(tport, FDLS_TGT_STATE_OFFLINING);
+		fnic_del_tport_timer_sync(fnic, tport);
+		fnic_fdls_remove_tport(&fnic->iport, tport, flags);
 	}
-	spin_unlock_irqrestore(&fnic->vlans_lock, flags);
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 }
 
-void fnic_handle_fip_timer(struct fnic *fnic)
+/**
+ * fnic_tport_event_handler() - Handler for remote port events
+ * in the tport_event_queue.
+ *
+ * @work: Handle to the remote port being dequeued
+ */
+void fnic_tport_event_handler(struct work_struct *work)
 {
+	struct fnic *fnic = container_of(work, struct fnic, tport_work);
+	struct fnic_tport_event_s *cur_evt, *next;
 	unsigned long flags;
-	struct fcoe_vlan *vlan;
-	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
-	u64 sol_time;
+	struct fnic_tport_s *tport;
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (fnic->stop_rx_link_events) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		return;
+	list_for_each_entry_safe(cur_evt, next, &fnic->tport_event_list, links) {
+		tport = cur_evt->arg1;
+		switch (cur_evt->event) {
+		case TGT_EV_RPORT_ADD:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Add rport event");
+			if (tport->state == FDLS_TGT_STATE_READY) {
+				fnic_fdls_add_tport(&fnic->iport,
+					(struct fnic_tport_s *) cur_evt->arg1, flags);
+			} else {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Target not ready. Add rport event dropped: 0x%x",
+					 tport->fcid);
+			}
+			break;
+		case TGT_EV_RPORT_DEL:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Remove rport event");
+			if (tport->state == FDLS_TGT_STATE_OFFLINING) {
+				fnic_fdls_remove_tport(&fnic->iport,
+					   (struct fnic_tport_s *) cur_evt->arg1, flags);
+			} else {
+				FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+							 "remove rport event dropped tport fcid: 0x%x",
+							 tport->fcid);
+			}
+			break;
+		case TGT_EV_TPORT_DELETE:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Delete tport event");
+			fdls_delete_tport(tport->iport, tport);
+			break;
+		default:
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						 "Unknown tport event");
+			break;
+		}
+		list_del(&cur_evt->links);
+		kfree(cur_evt);
 	}
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+}
 
-	if (fnic->ctlr.mode == FIP_MODE_NON_FIP)
-		return;
+void fnic_flush_tport_event_list(struct fnic *fnic)
+{
+	struct fnic_tport_event_s *cur_evt, *next;
+	unsigned long flags;
 
-	spin_lock_irqsave(&fnic->vlans_lock, flags);
-	if (list_empty(&fnic->vlans)) {
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		/* no vlans available, try again */
-		if (unlikely(fnic_log_level & FNIC_FCS_LOGGING))
-			if (printk_ratelimit())
-				shost_printk(KERN_DEBUG, fnic->lport->host,
-						"Start VLAN Discovery\n");
-		fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC);
-		return;
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	list_for_each_entry_safe(cur_evt, next, &fnic->tport_event_list, links) {
+		list_del(&cur_evt->links);
+		kfree(cur_evt);
 	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+}
 
-	vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan, list);
-	FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-		  "fip_timer: vlan %d state %d sol_count %d\n",
-		  vlan->vid, vlan->state, vlan->sol_count);
-	switch (vlan->state) {
-	case FIP_VLAN_USED:
-		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			  "FIP VLAN is selected for FC transaction\n");
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		break;
-	case FIP_VLAN_FAILED:
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		/* if all vlans are in failed state, restart vlan disc */
-		if (unlikely(fnic_log_level & FNIC_FCS_LOGGING))
-			if (printk_ratelimit())
-				shost_printk(KERN_DEBUG, fnic->lport->host,
-					  "Start VLAN Discovery\n");
-		fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC);
-		break;
-	case FIP_VLAN_SENT:
-		if (vlan->sol_count >= FCOE_CTLR_MAX_SOL) {
-			/*
-			 * no response on this vlan, remove  from the list.
-			 * Try the next vlan
-			 */
-			FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-				  "Dequeue this VLAN ID %d from list\n",
-				  vlan->vid);
-			list_del(&vlan->list);
-			kfree(vlan);
-			vlan = NULL;
-			if (list_empty(&fnic->vlans)) {
-				/* we exhausted all vlans, restart vlan disc */
-				spin_unlock_irqrestore(&fnic->vlans_lock,
-							flags);
-				FNIC_FCS_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-					  "fip_timer: vlan list empty, "
-					  "trigger vlan disc\n");
-				fnic_event_enq(fnic, FNIC_EVT_START_VLAN_DISC);
-				return;
-			}
-			/* check the next vlan */
-			vlan = list_first_entry(&fnic->vlans, struct fcoe_vlan,
-							list);
-			fnic->set_vlan(fnic, vlan->vid);
-			vlan->state = FIP_VLAN_SENT; /* sent now */
-		}
-		spin_unlock_irqrestore(&fnic->vlans_lock, flags);
-		atomic64_inc(&fnic_stats->vlan_stats.sol_expiry_count);
-		vlan->sol_count++;
-		sol_time = jiffies + msecs_to_jiffies
-					(FCOE_CTLR_START_DELAY);
-		mod_timer(&fnic->fip_timer, round_jiffies(sol_time));
-		break;
+void fnic_reset_work_handler(struct work_struct *work)
+{
+	struct fnic *cur_fnic, *next_fnic;
+	unsigned long reset_fnic_list_lock_flags;
+	int host_reset_ret_code;
+
+	/*
+	 * This is a single thread. It is per fnic module, not per fnic
+	 * All the fnics that need to be reset
+	 * have been serialized via the reset fnic list.
+	 */
+	spin_lock_irqsave(&reset_fnic_list_lock, reset_fnic_list_lock_flags);
+	list_for_each_entry_safe(cur_fnic, next_fnic, &reset_fnic_list, links) {
+		list_del(&cur_fnic->links);
+		spin_unlock_irqrestore(&reset_fnic_list_lock,
+							   reset_fnic_list_lock_flags);
+
+		dev_err(&cur_fnic->pdev->dev, "fnic: <%d>: issuing a host reset\n",
+			   cur_fnic->fnic_num);
+		host_reset_ret_code = fnic_host_reset(cur_fnic->host);
+		dev_err(&cur_fnic->pdev->dev,
+		   "fnic: <%d>: returned from host reset with status: %d\n",
+		   cur_fnic->fnic_num, host_reset_ret_code);
+
+		spin_lock_irqsave(&cur_fnic->fnic_lock, cur_fnic->lock_flags);
+		cur_fnic->pc_rscn_handling_status =
+			PC_RSCN_HANDLING_NOT_IN_PROGRESS;
+		spin_unlock_irqrestore(&cur_fnic->fnic_lock, cur_fnic->lock_flags);
+
+		spin_lock_irqsave(&reset_fnic_list_lock,
+						  reset_fnic_list_lock_flags);
 	}
+	spin_unlock_irqrestore(&reset_fnic_list_lock,
+						   reset_fnic_list_lock_flags);
 }
diff --git a/drivers/scsi/fnic/fnic_fdls.h b/drivers/scsi/fnic/fnic_fdls.h
new file mode 100644
index 000000000000..8e610b65ad57
--- /dev/null
+++ b/drivers/scsi/fnic/fnic_fdls.h
@@ -0,0 +1,434 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
+ * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
+ */
+
+#ifndef _FNIC_FDLS_H_
+#define _FNIC_FDLS_H_
+
+#include "fnic_stats.h"
+#include "fdls_fc.h"
+
+/* FDLS - Fabric discovery and login services
+ * -> VLAN discovery
+ *   -> retry every retry delay seconds until it succeeds.
+ *                        <- List of VLANs
+ *
+ * -> Solicitation
+ *                        <- Solicitation response (Advertisement)
+ *
+ * -> FCF selection & FLOGI ( FLOGI timeout - 2 * E_D_TOV)
+ *                        <- FLOGI response
+ *
+ * -> FCF keep alive
+ *                         <- FCF keep alive
+ *
+ * -> PLOGI to FFFFFC (DNS) (PLOGI timeout - 2 * R_A_TOV)
+ *    -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV)
+ *                        <- PLOGI response
+ *    -> Retry PLOGI to FFFFFC (DNS) - Number of retries from vnic.cfg
+ *
+ * -> SCR to FFFFFC (DNS) (SCR timeout - 2 * R_A_TOV)
+ *    -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV)
+ *                        <- SCR response
+ *    -> Retry SCR - Number of retries 2
+ *
+ * -> GPN_FT to FFFFFC (GPN_FT timeout - 2 * R_A_TOV)a
+ *    -> Retry on BUSY until it succeeds
+ *    -> Retry on BUSY until it succeeds
+ *    -> 2 retries on timeout
+ *
+ * -> RFT_ID to FFFFFC (DNS)        (RFT_ID timeout - 3 * R_A_TOV)
+ *    -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV)
+ *    -> Retry RFT_ID to FFFFFC (DNS) (Number of retries 2 )
+ *    -> Ignore if both retires fail.
+ *
+ *        Session establishment with targets
+ * For each PWWN
+ *   -> PLOGI to FCID of that PWWN (PLOGI timeout 2 * R_A_TOV)
+ *    -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV)
+ *                        <- PLOGI response
+ *    -> Retry PLOGI. Num retries using vnic.cfg
+ *
+ *   -> PRLI to FCID of that PWWN (PRLI timeout 2 * R_A_TOV)
+ *    -> ABTS if timeout (ABTS tomeout - 2 * R_A_TOV)
+ *                        <- PRLI response
+ *    -> Retry PRLI. Num retries using vnic.cfg
+ *
+ */
+
+#define FDLS_RETRY_COUNT 2
+
+/*
+ * OXID encoding:
+ * bits 0-8: oxid idx - allocated from poool
+ * bits 9-13: oxid frame code from fnic_oxid_frame_type_e
+ * bits 14-15: all zeros
+ */
+#define FNIC_OXID_POOL_SZ	(512)	/* always power of 2 */
+#define FNIC_OXID_ENCODE(idx, frame_type)	(frame_type | idx)
+#define FNIC_FRAME_MASK				0xFE00
+#define FNIC_FRAME_TYPE(oxid)			(oxid & FNIC_FRAME_MASK)
+#define FNIC_OXID_IDX(oxid)		((oxid) & (FNIC_OXID_POOL_SZ - 1))
+
+#define OXID_RECLAIM_TOV(iport) (2 * iport->r_a_tov) /* in milliseconds */
+
+#define FNIC_FDLS_FABRIC_ABORT_ISSUED     0x1
+#define FNIC_FDLS_FPMA_LEARNT             0x2
+
+/* tport flags */
+#define FNIC_FDLS_TPORT_IN_GPN_FT_LIST 0x1
+#define FNIC_FDLS_TGT_ABORT_ISSUED     0x2
+#define FNIC_FDLS_TPORT_SEND_ADISC     0x4
+#define FNIC_FDLS_RETRY_FRAME          0x8
+#define FNIC_FDLS_TPORT_BUSY	       0x10
+#define FNIC_FDLS_TPORT_TERMINATING      0x20
+#define FNIC_FDLS_TPORT_DELETED        0x40
+#define FNIC_FDLS_SCSI_REGISTERED      0x200
+
+/* Retry supported by rport(returned by prli service parameters) */
+#define FDLS_FC_RP_FLAGS_RETRY 0x1
+
+#define fdls_set_state(_fdls_fabric, _state)  ((_fdls_fabric)->state = _state)
+#define fdls_get_state(_fdls_fabric)          ((_fdls_fabric)->state)
+
+#define FNIC_FDMI_ACTIVE    0x8
+#define FNIC_FIRST_LINK_UP    0x2
+
+#define fdls_set_tport_state(_tport, _state)    (_tport->state = _state)
+#define fdls_get_tport_state(_tport)            (_tport->state)
+
+#define FNIC_PORTSPEED_10GBIT   1
+#define FNIC_FRAME_HT_ROOM     (2148)
+#define FNIC_FCOE_FRAME_MAXSZ   (2112)
+
+
+#define FNIC_FRAME_TYPE_FABRIC_FLOGI	0x1000
+#define FNIC_FRAME_TYPE_FABRIC_PLOGI	0x1200
+#define FNIC_FRAME_TYPE_FABRIC_RPN	0x1400
+#define FNIC_FRAME_TYPE_FABRIC_RFT	0x1600
+#define FNIC_FRAME_TYPE_FABRIC_RFF	0x1800
+#define FNIC_FRAME_TYPE_FABRIC_SCR	0x1A00
+#define FNIC_FRAME_TYPE_FABRIC_GPN_FT	0x1C00
+#define FNIC_FRAME_TYPE_FABRIC_LOGO	0x1E00
+#define FNIC_FRAME_TYPE_FDMI_PLOGI	0x2000
+#define FNIC_FRAME_TYPE_FDMI_RHBA	0x2200
+#define FNIC_FRAME_TYPE_FDMI_RPA	0x2400
+#define FNIC_FRAME_TYPE_TGT_PLOGI	0x2600
+#define FNIC_FRAME_TYPE_TGT_PRLI	0x2800
+#define FNIC_FRAME_TYPE_TGT_ADISC	0x2A00
+#define FNIC_FRAME_TYPE_TGT_LOGO	0x2C00
+
+struct fnic_fip_fcf_s {
+	uint16_t vlan_id;
+	uint8_t fcf_mac[6];
+	uint8_t fcf_priority;
+	uint32_t fka_adv_period;
+	uint8_t ka_disabled;
+};
+
+enum fnic_fdls_state_e {
+	FDLS_STATE_INIT = 0,
+	FDLS_STATE_LINKDOWN,
+	FDLS_STATE_FABRIC_LOGO,
+	FDLS_STATE_FLOGO_DONE,
+	FDLS_STATE_FABRIC_FLOGI,
+	FDLS_STATE_FABRIC_PLOGI,
+	FDLS_STATE_RPN_ID,
+	FDLS_STATE_REGISTER_FC4_TYPES,
+	FDLS_STATE_REGISTER_FC4_FEATURES,
+	FDLS_STATE_SCR,
+	FDLS_STATE_GPN_FT,
+	FDLS_STATE_TGT_DISCOVERY,
+	FDLS_STATE_RSCN_GPN_FT,
+	FDLS_STATE_SEND_GPNFT
+};
+
+struct fnic_fdls_fabric_s {
+	enum fnic_fdls_state_e state;
+	uint32_t flags;
+	struct list_head tport_list; /* List of discovered tports */
+	struct timer_list retry_timer;
+	int del_timer_inprogress;
+	int del_fdmi_timer_inprogress;
+	int retry_counter;
+	int timer_pending;
+	int fdmi_retry;
+	struct timer_list fdmi_timer;
+	int fdmi_pending;
+};
+
+struct fnic_fdls_fip_s {
+	uint32_t state;
+	uint32_t flogi_retry;
+};
+
+/* Message to tport_event_handler */
+enum fnic_tgt_msg_id {
+	TGT_EV_NONE = 0,
+	TGT_EV_RPORT_ADD,
+	TGT_EV_RPORT_DEL,
+	TGT_EV_TPORT_DELETE,
+	TGT_EV_REMOVE
+};
+
+struct fnic_tport_event_s {
+	struct list_head links;
+	enum fnic_tgt_msg_id event;
+	void *arg1;
+};
+
+enum fdls_tgt_state_e {
+	FDLS_TGT_STATE_INIT = 0,
+	FDLS_TGT_STATE_PLOGI,
+	FDLS_TGT_STATE_PRLI,
+	FDLS_TGT_STATE_READY,
+	FDLS_TGT_STATE_LOGO_RECEIVED,
+	FDLS_TGT_STATE_ADISC,
+	FDL_TGT_STATE_PLOGO,
+	FDLS_TGT_STATE_OFFLINING,
+	FDLS_TGT_STATE_OFFLINE
+};
+
+struct fnic_tport_s {
+	struct list_head links; /* To link the tports */
+	enum fdls_tgt_state_e state;
+	uint32_t flags;
+	uint32_t fcid;
+	uint64_t wwpn;
+	uint64_t wwnn;
+	uint16_t active_oxid;
+	uint16_t tgt_flags;
+	atomic_t in_flight; /* io counter */
+	uint16_t max_payload_size;
+	uint16_t r_a_tov;
+	uint16_t e_d_tov;
+	uint16_t lun0_delay;
+	int max_concur_seqs;
+	uint32_t fcp_csp;
+	struct timer_list retry_timer;
+	int del_timer_inprogress;
+	int retry_counter;
+	int timer_pending;
+	unsigned int num_pending_cmds;
+	int nexus_restart_count;
+	int exch_reset_in_progress;
+	void *iport;
+	struct work_struct tport_del_work;
+	struct completion *tport_del_done;
+	struct fc_rport *rport;
+	char str_wwpn[20];
+	char str_wwnn[20];
+};
+
+/* OXID pool related structures */
+struct reclaim_entry_s {
+	struct list_head links;
+	/* oxid that needs to be freed after 2*r_a_tov */
+	uint16_t oxid_idx;
+	/* in jiffies. Use this to waiting time */
+	unsigned long expires;
+	unsigned long *bitmap;
+};
+
+/* used for allocating oxids for fabric and fdmi requests */
+struct fnic_oxid_pool_s {
+	DECLARE_BITMAP(bitmap, FNIC_OXID_POOL_SZ);
+	int sz;			/* size of the pool or block */
+	int next_idx;		/* used for cycling through the oxid pool */
+
+	/* retry schedule free */
+	DECLARE_BITMAP(pending_schedule_free, FNIC_OXID_POOL_SZ);
+	struct delayed_work schedule_oxid_free_retry;
+
+	/* List of oxids that need to be freed and reclaimed.
+	 * This list is shared by all the oxid pools
+	 */
+	struct list_head oxid_reclaim_list;
+	/* Work associated with reclaim list */
+	struct delayed_work oxid_reclaim_work;
+};
+
+/* iport */
+enum fnic_iport_state_e {
+	FNIC_IPORT_STATE_INIT = 0,
+	FNIC_IPORT_STATE_LINK_WAIT,
+	FNIC_IPORT_STATE_FIP,
+	FNIC_IPORT_STATE_FABRIC_DISC,
+	FNIC_IPORT_STATE_READY
+};
+
+struct fnic_iport_s {
+	enum fnic_iport_state_e state;
+	struct fnic *fnic;
+	uint64_t boot_time;
+	uint32_t flags;
+	int usefip;
+	uint8_t hwmac[6]; /* HW MAC Addr */
+	uint8_t fpma[6]; /* Fabric Provided MA */
+	uint8_t fcfmac[6]; /* MAC addr of Fabric */
+	uint16_t vlan_id;
+	uint32_t fcid;
+
+	/* oxid pool */
+	struct fnic_oxid_pool_s oxid_pool;
+
+	/*
+	 * fabric reqs are serialized and only one req at a time.
+	 * Tracking the oxid for sending abort
+	 */
+	uint16_t active_oxid_fabric_req;
+	/* fdmi only */
+	uint16_t active_oxid_fdmi_plogi;
+	uint16_t active_oxid_fdmi_rhba;
+	uint16_t active_oxid_fdmi_rpa;
+
+	struct fnic_fip_fcf_s selected_fcf;
+	struct fnic_fdls_fip_s fip;
+	struct fnic_fdls_fabric_s fabric;
+	struct list_head tport_list;
+	struct list_head tport_list_pending_del;
+	/* list of tports for which we are yet to send PLOGO */
+	struct list_head inprocess_tport_list;
+	struct list_head deleted_tport_list;
+	struct work_struct tport_event_work;
+	uint32_t e_d_tov; /* msec */
+	uint32_t r_a_tov; /* msec */
+	uint32_t link_supported_speeds;
+	uint32_t max_flogi_retries;
+	uint32_t max_plogi_retries;
+	uint32_t plogi_timeout;
+	uint32_t service_params;
+	uint64_t wwpn;
+	uint64_t wwnn;
+	uint16_t max_payload_size;
+	spinlock_t deleted_tport_lst_lock;
+	struct completion *flogi_reg_done;
+	struct fnic_iport_stats iport_stats;
+	char str_wwpn[20];
+	char str_wwnn[20];
+};
+
+struct rport_dd_data_s {
+	struct fnic_tport_s *tport;
+	struct fnic_iport_s *iport;
+};
+
+enum fnic_recv_frame_type_e {
+	FNIC_FABRIC_FLOGI_RSP = 1,
+	FNIC_FABRIC_PLOGI_RSP,
+	FNIC_FABRIC_RPN_RSP,
+	FNIC_FABRIC_RFT_RSP,
+	FNIC_FABRIC_RFF_RSP,
+	FNIC_FABRIC_SCR_RSP,
+	FNIC_FABRIC_GPN_FT_RSP,
+	FNIC_FABRIC_BLS_ABTS_RSP,
+	FNIC_FDMI_PLOGI_RSP,
+	FNIC_FDMI_REG_HBA_RSP,
+	FNIC_FDMI_RPA_RSP,
+	FNIC_FDMI_BLS_ABTS_RSP,
+	FNIC_FABRIC_LOGO_RSP,
+
+	/* responses to target requests */
+	FNIC_TPORT_PLOGI_RSP,
+	FNIC_TPORT_PRLI_RSP,
+	FNIC_TPORT_ADISC_RSP,
+	FNIC_TPORT_BLS_ABTS_RSP,
+	FNIC_TPORT_LOGO_RSP,
+
+	/* unsolicited requests */
+	FNIC_BLS_ABTS_REQ,
+	FNIC_ELS_PLOGI_REQ,
+	FNIC_ELS_RSCN_REQ,
+	FNIC_ELS_LOGO_REQ,
+	FNIC_ELS_ECHO_REQ,
+	FNIC_ELS_ADISC,
+	FNIC_ELS_RLS,
+	FNIC_ELS_RRQ,
+	FNIC_ELS_UNSUPPORTED_REQ,
+};
+
+enum fnic_port_speeds {
+	DCEM_PORTSPEED_NONE = 0,
+	DCEM_PORTSPEED_1G = 1000,
+	DCEM_PORTSPEED_2G = 2000,
+	DCEM_PORTSPEED_4G = 4000,
+	DCEM_PORTSPEED_8G = 8000,
+	DCEM_PORTSPEED_10G = 10000,
+	DCEM_PORTSPEED_16G = 16000,
+	DCEM_PORTSPEED_20G = 20000,
+	DCEM_PORTSPEED_25G = 25000,
+	DCEM_PORTSPEED_32G = 32000,
+	DCEM_PORTSPEED_40G = 40000,
+	DCEM_PORTSPEED_4x10G = 41000,
+	DCEM_PORTSPEED_50G = 50000,
+	DCEM_PORTSPEED_64G = 64000,
+	DCEM_PORTSPEED_100G = 100000,
+	DCEM_PORTSPEED_128G = 128000,
+};
+
+/* Function Declarations */
+/* fdls_disc.c */
+void fnic_fdls_disc_init(struct fnic_iport_s *iport);
+void fnic_fdls_disc_start(struct fnic_iport_s *iport);
+void fnic_fdls_recv_frame(struct fnic_iport_s *iport, void *rx_frame,
+			  int len, int fchdr_offset);
+void fnic_fdls_link_down(struct fnic_iport_s *iport);
+int fdls_init_frame_pool(struct fnic_iport_s *iport);
+uint8_t *fdls_alloc_frame(struct fnic_iport_s *iport);
+uint16_t fdls_alloc_oxid(struct fnic_iport_s *iport, int oxid_frame_type,
+	uint16_t *active_oxid);
+void fdls_free_oxid(struct fnic_iport_s *iport,
+	uint16_t oxid, uint16_t *active_oxid);
+void fdls_tgt_logout(struct fnic_iport_s *iport,
+		     struct fnic_tport_s *tport);
+void fnic_del_fabric_timer_sync(struct fnic *fnic);
+void fnic_del_tport_timer_sync(struct fnic *fnic,
+							struct fnic_tport_s *tport);
+void fdls_send_fabric_logo(struct fnic_iport_s *iport);
+int fnic_fdls_validate_and_get_frame_type(struct fnic_iport_s *iport,
+	struct fc_frame_header *fchdr);
+void fdls_send_tport_abts(struct fnic_iport_s *iport,
+						struct fnic_tport_s *tport);
+bool fdls_delete_tport(struct fnic_iport_s *iport,
+		       struct fnic_tport_s *tport);
+void fdls_fdmi_timer_callback(struct timer_list *t);
+
+/* fnic_fcs.c */
+void fnic_fdls_init(struct fnic *fnic, int usefip);
+void fnic_send_fcoe_frame(struct fnic_iport_s *iport, void *frame,
+	int frame_size);
+void fnic_fcoe_send_vlan_req(struct fnic *fnic);
+int fnic_send_fip_frame(struct fnic_iport_s *iport,
+	void *frame, int frame_size);
+void fnic_fdls_learn_fcoe_macs(struct fnic_iport_s *iport, void *rx_frame,
+	uint8_t *fcid);
+void fnic_fdls_add_tport(struct fnic_iport_s *iport,
+		struct fnic_tport_s *tport, unsigned long flags);
+void fnic_fdls_remove_tport(struct fnic_iport_s *iport,
+			    struct fnic_tport_s *tport,
+			    unsigned long flags);
+
+/* fip.c */
+void fnic_fcoe_send_vlan_req(struct fnic *fnic);
+void fnic_common_fip_cleanup(struct fnic *fnic);
+int fdls_fip_recv_frame(struct fnic *fnic, void *frame);
+void fnic_handle_fcs_ka_timer(struct timer_list *t);
+void fnic_handle_enode_ka_timer(struct timer_list *t);
+void fnic_handle_vn_ka_timer(struct timer_list *t);
+void fnic_handle_fip_timer(struct timer_list *t);
+extern void fdls_fabric_timer_callback(struct timer_list *t);
+
+/* fnic_scsi.c */
+void fnic_scsi_fcpio_reset(struct fnic *fnic);
+extern void fdls_fabric_timer_callback(struct timer_list *t);
+void fnic_rport_exch_reset(struct fnic *fnic, u32 fcid);
+int fnic_fdls_register_portid(struct fnic_iport_s *iport, u32 port_id,
+		void *fp);
+struct fnic_tport_s *fnic_find_tport_by_fcid(struct fnic_iport_s *iport,
+		uint32_t fcid);
+struct fnic_tport_s *fnic_find_tport_by_wwpn(struct fnic_iport_s *iport,
+		uint64_t  wwpn);
+
+#endif /* _FNIC_FDLS_H_ */
diff --git a/drivers/scsi/fnic/fnic_fip.h b/drivers/scsi/fnic/fnic_fip.h
deleted file mode 100644
index 79f53029737b..000000000000
--- a/drivers/scsi/fnic/fnic_fip.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
- * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
- */
-
-#ifndef _FNIC_FIP_H_
-#define _FNIC_FIP_H_
-
-
-#define FCOE_CTLR_START_DELAY    2000    /* ms after first adv. to choose FCF */
-#define FCOE_CTLR_FIPVLAN_TOV    2000    /* ms after FIP VLAN disc */
-#define FCOE_CTLR_MAX_SOL        8
-
-#define FINC_MAX_FLOGI_REJECTS   8
-
-struct vlan {
-	__be16 vid;
-	__be16 type;
-};
-
-/*
- * VLAN entry.
- */
-struct fcoe_vlan {
-	struct list_head list;
-	u16 vid;		/* vlan ID */
-	u16 sol_count;		/* no. of sols sent */
-	u16 state;		/* state */
-};
-
-enum fip_vlan_state {
-	FIP_VLAN_AVAIL  = 0,	/* don't do anything */
-	FIP_VLAN_SENT   = 1,	/* sent */
-	FIP_VLAN_USED   = 2,	/* succeed */
-	FIP_VLAN_FAILED = 3,	/* failed to response */
-};
-
-struct fip_vlan {
-	struct ethhdr eth;
-	struct fip_header fip;
-	struct {
-		struct fip_mac_desc mac;
-		struct fip_wwn_desc wwnn;
-	} desc;
-};
-
-#endif  /* __FINC_FIP_H_ */
diff --git a/drivers/scsi/fnic/fnic_io.h b/drivers/scsi/fnic/fnic_io.h
index 5895ead20e14..0d974e040ab7 100644
--- a/drivers/scsi/fnic/fnic_io.h
+++ b/drivers/scsi/fnic/fnic_io.h
@@ -7,6 +7,7 @@
 #define _FNIC_IO_H_
 
 #include <scsi/fc/fc_fcp.h>
+#include "fnic_fdls.h"
 
 #define FNIC_DFLT_SG_DESC_CNT  32
 #define FNIC_MAX_SG_DESC_CNT        256     /* Maximum descriptors per sgl */
@@ -41,6 +42,8 @@ enum fnic_ioreq_state {
 };
 
 struct fnic_io_req {
+	struct fnic_iport_s *iport;
+	struct fnic_tport_s *tport;
 	struct host_sg_desc *sgl_list; /* sgl list */
 	void *sgl_list_alloc; /* sgl list address used for free */
 	dma_addr_t sense_buf_pa; /* dma address for sense buffer*/
@@ -55,15 +58,4 @@ struct fnic_io_req {
 	unsigned int tag;
 	struct scsi_cmnd *sc; /* midlayer's cmd pointer */
 };
-
-enum fnic_port_speeds {
-	DCEM_PORTSPEED_NONE = 0,
-	DCEM_PORTSPEED_1G    = 1000,
-	DCEM_PORTSPEED_10G   = 10000,
-	DCEM_PORTSPEED_20G   = 20000,
-	DCEM_PORTSPEED_25G   = 25000,
-	DCEM_PORTSPEED_40G   = 40000,
-	DCEM_PORTSPEED_4x10G = 41000,
-	DCEM_PORTSPEED_100G  = 100000,
-};
 #endif /* _FNIC_IO_H_ */
diff --git a/drivers/scsi/fnic/fnic_isr.c b/drivers/scsi/fnic/fnic_isr.c
index ff85441c6cea..7ed50b11afa6 100644
--- a/drivers/scsi/fnic/fnic_isr.c
+++ b/drivers/scsi/fnic/fnic_isr.c
@@ -7,7 +7,7 @@
 #include <linux/errno.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
-#include <scsi/libfc.h>
+#include <scsi/scsi_transport_fc.h>
 #include <scsi/fc_frame.h>
 #include "vnic_dev.h"
 #include "vnic_intr.h"
@@ -222,7 +222,7 @@ int fnic_request_intr(struct fnic *fnic)
 							fnic->msix[i].devname,
 							fnic->msix[i].devid);
 			if (err) {
-				FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 							"request_irq failed with error: %d\n",
 							err);
 				fnic_free_intr(fnic);
@@ -250,10 +250,10 @@ int fnic_set_intr_mode_msix(struct fnic *fnic)
 	 * We need n RQs, m WQs, o Copy WQs, n+m+o CQs, and n+m+o+1 INTRs
 	 * (last INTR is used for WQ/RQ errors and notification area)
 	 */
-	FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+	FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 		"rq-array size: %d wq-array size: %d copy-wq array size: %d\n",
 		n, m, o);
-	FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+	FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 		"rq_count: %d raw_wq_count: %d wq_copy_count: %d cq_count: %d\n",
 		fnic->rq_count, fnic->raw_wq_count,
 		fnic->wq_copy_count, fnic->cq_count);
@@ -265,17 +265,17 @@ int fnic_set_intr_mode_msix(struct fnic *fnic)
 
 		vec_count = pci_alloc_irq_vectors(fnic->pdev, min_irqs, vecs,
 					PCI_IRQ_MSIX | PCI_IRQ_AFFINITY);
-		FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 					"allocated %d MSI-X vectors\n",
 					vec_count);
 
 		if (vec_count > 0) {
 			if (vec_count < vecs) {
-				FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"interrupts number mismatch: vec_count: %d vecs: %d\n",
 				vec_count, vecs);
 				if (vec_count < min_irqs) {
-					FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+					FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 								"no interrupts for copy wq\n");
 					return 1;
 				}
@@ -287,7 +287,7 @@ int fnic_set_intr_mode_msix(struct fnic *fnic)
 			fnic->wq_copy_count = vec_count - n - m - 1;
 			fnic->wq_count = fnic->raw_wq_count + fnic->wq_copy_count;
 			if (fnic->cq_count != vec_count - 1) {
-				FNIC_ISR_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+				FNIC_ISR_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"CQ count: %d does not match MSI-X vector count: %d\n",
 				fnic->cq_count, vec_count);
 				fnic->cq_count = vec_count - 1;
@@ -295,23 +295,23 @@ int fnic_set_intr_mode_msix(struct fnic *fnic)
 			fnic->intr_count = vec_count;
 			fnic->err_intr_offset = fnic->rq_count + fnic->wq_count;
 
-			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 				"rq_count: %d raw_wq_count: %d copy_wq_base: %d\n",
 				fnic->rq_count,
 				fnic->raw_wq_count, fnic->copy_wq_base);
 
-			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 				"wq_copy_count: %d wq_count: %d cq_count: %d\n",
 				fnic->wq_copy_count,
 				fnic->wq_count, fnic->cq_count);
 
-			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 				"intr_count: %d err_intr_offset: %u",
 				fnic->intr_count,
 				fnic->err_intr_offset);
 
 			vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_MSIX);
-			FNIC_ISR_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			FNIC_ISR_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 					"fnic using MSI-X\n");
 			return 0;
 		}
@@ -351,7 +351,7 @@ int fnic_set_intr_mode(struct fnic *fnic)
 		fnic->intr_count = 1;
 		fnic->err_intr_offset = 0;
 
-		FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_ISR_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			     "Using MSI Interrupts\n");
 		vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_MSI);
 
@@ -377,7 +377,7 @@ int fnic_set_intr_mode(struct fnic *fnic)
 		fnic->cq_count = 3;
 		fnic->intr_count = 3;
 
-		FNIC_ISR_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_ISR_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			     "Using Legacy Interrupts\n");
 		vnic_dev_set_intr_mode(fnic->vdev, VNIC_DEV_INTR_MODE_INTX);
 
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 1cb517f731f4..0b20ac8c3f46 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -21,15 +21,15 @@
 #include <scsi/scsi_transport.h>
 #include <scsi/scsi_transport_fc.h>
 #include <scsi/scsi_tcq.h>
-#include <scsi/libfc.h>
 #include <scsi/fc_frame.h>
 
 #include "vnic_dev.h"
 #include "vnic_intr.h"
 #include "vnic_stats.h"
 #include "fnic_io.h"
-#include "fnic_fip.h"
 #include "fnic.h"
+#include "fnic_fdls.h"
+#include "fdls_fc.h"
 
 #define PCI_DEVICE_ID_CISCO_FNIC	0x0045
 
@@ -38,12 +38,18 @@
 
 static struct kmem_cache *fnic_sgl_cache[FNIC_SGL_NUM_CACHES];
 static struct kmem_cache *fnic_io_req_cache;
+static struct kmem_cache *fdls_frame_cache;
+static struct kmem_cache *fdls_frame_elem_cache;
 static LIST_HEAD(fnic_list);
 static DEFINE_SPINLOCK(fnic_list_lock);
 static DEFINE_IDA(fnic_ida);
 
+struct work_struct reset_fnic_work;
+LIST_HEAD(reset_fnic_list);
+DEFINE_SPINLOCK(reset_fnic_list_lock);
+
 /* Supported devices by fnic module */
-static struct pci_device_id fnic_id_table[] = {
+static const struct pci_device_id fnic_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CISCO, PCI_DEVICE_ID_CISCO_FNIC) },
 	{ 0, }
 };
@@ -59,6 +65,14 @@ unsigned int fnic_log_level;
 module_param(fnic_log_level, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(fnic_log_level, "bit mask of fnic logging levels");
 
+unsigned int fnic_fdmi_support = 1;
+module_param(fnic_fdmi_support, int, 0644);
+MODULE_PARM_DESC(fnic_fdmi_support, "FDMI support");
+
+static unsigned int fnic_tgt_id_binding = 1;
+module_param(fnic_tgt_id_binding, uint, 0644);
+MODULE_PARM_DESC(fnic_tgt_id_binding,
+		 "Target ID binding (0 for none. 1 for binding by WWPN (default))");
 
 unsigned int io_completions = FNIC_DFLT_IO_COMPLETIONS;
 module_param(io_completions, int, S_IRUGO|S_IWUSR);
@@ -78,15 +92,15 @@ static unsigned int fnic_max_qdepth = FNIC_DFLT_QUEUE_DEPTH;
 module_param(fnic_max_qdepth, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(fnic_max_qdepth, "Queue depth to report for each LUN");
 
-static struct libfc_function_template fnic_transport_template = {
-	.frame_send = fnic_send,
-	.lport_set_port_id = fnic_set_port_id,
-	.fcp_abort_io = fnic_empty_scsi_cleanup,
-	.fcp_cleanup = fnic_empty_scsi_cleanup,
-	.exch_mgr_reset = fnic_exch_mgr_reset
-};
+unsigned int pc_rscn_handling_feature_flag = PC_RSCN_HANDLING_FEATURE_ON;
+module_param(pc_rscn_handling_feature_flag, uint, 0644);
+MODULE_PARM_DESC(pc_rscn_handling_feature_flag,
+		 "PCRSCN handling (0 for none. 1 to handle PCRSCN (default))");
 
-static int fnic_slave_alloc(struct scsi_device *sdev)
+struct workqueue_struct *reset_fnic_work_queue;
+struct workqueue_struct *fnic_fip_queue;
+
+static int fnic_sdev_init(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 
@@ -104,8 +118,8 @@ static const struct scsi_host_template fnic_host_template = {
 	.eh_timed_out = fc_eh_timed_out,
 	.eh_abort_handler = fnic_abort_cmd,
 	.eh_device_reset_handler = fnic_device_reset,
-	.eh_host_reset_handler = fnic_host_reset,
-	.slave_alloc = fnic_slave_alloc,
+	.eh_host_reset_handler = fnic_eh_host_reset_handler,
+	.sdev_init = fnic_sdev_init,
 	.change_queue_depth = scsi_change_queue_depth,
 	.this_id = -1,
 	.cmd_per_lun = 3,
@@ -145,7 +159,7 @@ static struct fc_function_template fnic_fc_functions = {
 	.get_host_speed = fnic_get_host_speed,
 	.show_host_speed = 1,
 	.show_host_port_type = 1,
-	.get_host_port_state = fc_get_host_port_state,
+	.get_host_port_state = fnic_get_host_port_state,
 	.show_host_port_state = 1,
 	.show_host_symbolic_name = 1,
 	.show_rport_maxframe_size = 1,
@@ -156,54 +170,88 @@ static struct fc_function_template fnic_fc_functions = {
 	.show_starget_port_id = 1,
 	.show_rport_dev_loss_tmo = 1,
 	.set_rport_dev_loss_tmo = fnic_set_rport_dev_loss_tmo,
-	.issue_fc_host_lip = fnic_reset,
+	.issue_fc_host_lip = fnic_issue_fc_host_lip,
 	.get_fc_host_stats = fnic_get_stats,
 	.reset_fc_host_stats = fnic_reset_host_stats,
-	.dd_fcrport_size = sizeof(struct fc_rport_libfc_priv),
+	.dd_fcrport_size = sizeof(struct rport_dd_data_s),
 	.terminate_rport_io = fnic_terminate_rport_io,
-	.bsg_request = fc_lport_bsg_request,
+	.bsg_request = NULL,
 };
 
 static void fnic_get_host_speed(struct Scsi_Host *shost)
 {
-	struct fc_lport *lp = shost_priv(shost);
-	struct fnic *fnic = lport_priv(lp);
+	struct fnic *fnic = *((struct fnic **) shost_priv(shost));
 	u32 port_speed = vnic_dev_port_speed(fnic->vdev);
+	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
+
+	FNIC_MAIN_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "port_speed: %d Mbps", port_speed);
+	atomic64_set(&fnic_stats->misc_stats.port_speed_in_mbps, port_speed);
 
 	/* Add in other values as they get defined in fw */
 	switch (port_speed) {
+	case DCEM_PORTSPEED_1G:
+		fc_host_speed(shost) = FC_PORTSPEED_1GBIT;
+		break;
+	case DCEM_PORTSPEED_2G:
+		fc_host_speed(shost) = FC_PORTSPEED_2GBIT;
+		break;
+	case DCEM_PORTSPEED_4G:
+		fc_host_speed(shost) = FC_PORTSPEED_4GBIT;
+		break;
+	case DCEM_PORTSPEED_8G:
+		fc_host_speed(shost) = FC_PORTSPEED_8GBIT;
+		break;
 	case DCEM_PORTSPEED_10G:
 		fc_host_speed(shost) = FC_PORTSPEED_10GBIT;
 		break;
+	case DCEM_PORTSPEED_16G:
+		fc_host_speed(shost) = FC_PORTSPEED_16GBIT;
+		break;
 	case DCEM_PORTSPEED_20G:
 		fc_host_speed(shost) = FC_PORTSPEED_20GBIT;
 		break;
 	case DCEM_PORTSPEED_25G:
 		fc_host_speed(shost) = FC_PORTSPEED_25GBIT;
 		break;
+	case DCEM_PORTSPEED_32G:
+		fc_host_speed(shost) = FC_PORTSPEED_32GBIT;
+		break;
 	case DCEM_PORTSPEED_40G:
 	case DCEM_PORTSPEED_4x10G:
 		fc_host_speed(shost) = FC_PORTSPEED_40GBIT;
 		break;
+	case DCEM_PORTSPEED_50G:
+		fc_host_speed(shost) = FC_PORTSPEED_50GBIT;
+		break;
+	case DCEM_PORTSPEED_64G:
+		fc_host_speed(shost) = FC_PORTSPEED_64GBIT;
+		break;
 	case DCEM_PORTSPEED_100G:
 		fc_host_speed(shost) = FC_PORTSPEED_100GBIT;
 		break;
+	case DCEM_PORTSPEED_128G:
+		fc_host_speed(shost) = FC_PORTSPEED_128GBIT;
+		break;
 	default:
+		FNIC_MAIN_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					  "Unknown FC speed: %d Mbps", port_speed);
 		fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
 		break;
 	}
 }
 
+/* Placeholder function */
 static struct fc_host_statistics *fnic_get_stats(struct Scsi_Host *host)
 {
 	int ret;
-	struct fc_lport *lp = shost_priv(host);
-	struct fnic *fnic = lport_priv(lp);
-	struct fc_host_statistics *stats = &lp->host_stats;
+	struct fnic *fnic = *((struct fnic **) shost_priv(host));
+	struct fc_host_statistics *stats = &fnic->fnic_stats.host_stats;
 	struct vnic_stats *vs;
 	unsigned long flags;
 
-	if (time_before(jiffies, fnic->stats_time + HZ / FNIC_STATS_RATE_LIMIT))
+	if (time_before
+		(jiffies, fnic->stats_time + HZ / FNIC_STATS_RATE_LIMIT))
 		return stats;
 	fnic->stats_time = jiffies;
 
@@ -212,24 +260,22 @@ static struct fc_host_statistics *fnic_get_stats(struct Scsi_Host *host)
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	if (ret) {
-		FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			      "fnic: Get vnic stats failed"
-			      " 0x%x", ret);
+		FNIC_MAIN_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+					  "fnic: Get vnic stats failed: 0x%x", ret);
 		return stats;
 	}
 	vs = fnic->stats;
 	stats->tx_frames = vs->tx.tx_unicast_frames_ok;
-	stats->tx_words  = vs->tx.tx_unicast_bytes_ok / 4;
+	stats->tx_words = vs->tx.tx_unicast_bytes_ok / 4;
 	stats->rx_frames = vs->rx.rx_unicast_frames_ok;
-	stats->rx_words  = vs->rx.rx_unicast_bytes_ok / 4;
+	stats->rx_words = vs->rx.rx_unicast_bytes_ok / 4;
 	stats->error_frames = vs->tx.tx_errors + vs->rx.rx_errors;
 	stats->dumped_frames = vs->tx.tx_drops + vs->rx.rx_drop;
 	stats->invalid_crc_count = vs->rx.rx_crc_errors;
 	stats->seconds_since_last_reset =
-			(jiffies - fnic->stats_reset_time) / HZ;
+		(jiffies - fnic->stats_reset_time) / HZ;
 	stats->fcp_input_megabytes = div_u64(fnic->fcp_input_bytes, 1000000);
 	stats->fcp_output_megabytes = div_u64(fnic->fcp_output_bytes, 1000000);
-
 	return stats;
 }
 
@@ -310,8 +356,7 @@ void fnic_dump_fchost_stats(struct Scsi_Host *host,
 static void fnic_reset_host_stats(struct Scsi_Host *host)
 {
 	int ret;
-	struct fc_lport *lp = shost_priv(host);
-	struct fnic *fnic = lport_priv(lp);
+	struct fnic *fnic = *((struct fnic **) shost_priv(host));
 	struct fc_host_statistics *stats;
 	unsigned long flags;
 
@@ -324,7 +369,7 @@ static void fnic_reset_host_stats(struct Scsi_Host *host)
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	if (ret) {
-		FNIC_MAIN_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_MAIN_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 				"fnic: Reset vnic stats failed"
 				" 0x%x", ret);
 		return;
@@ -343,25 +388,19 @@ void fnic_log_q_error(struct fnic *fnic)
 	for (i = 0; i < fnic->raw_wq_count; i++) {
 		error_status = ioread32(&fnic->wq[i].ctrl->error_status);
 		if (error_status)
-			shost_printk(KERN_ERR, fnic->lport->host,
-				     "WQ[%d] error_status"
-				     " %d\n", i, error_status);
+			dev_err(&fnic->pdev->dev, "WQ[%d] error_status %d\n", i, error_status);
 	}
 
 	for (i = 0; i < fnic->rq_count; i++) {
 		error_status = ioread32(&fnic->rq[i].ctrl->error_status);
 		if (error_status)
-			shost_printk(KERN_ERR, fnic->lport->host,
-				     "RQ[%d] error_status"
-				     " %d\n", i, error_status);
+			dev_err(&fnic->pdev->dev, "RQ[%d] error_status %d\n", i, error_status);
 	}
 
 	for (i = 0; i < fnic->wq_copy_count; i++) {
 		error_status = ioread32(&fnic->hw_copy_wq[i].ctrl->error_status);
 		if (error_status)
-			shost_printk(KERN_ERR, fnic->lport->host,
-				     "CWQ[%d] error_status"
-				     " %d\n", i, error_status);
+			dev_err(&fnic->pdev->dev, "CWQ[%d] error_status %d\n", i, error_status);
 	}
 }
 
@@ -395,8 +434,7 @@ static int fnic_notify_set(struct fnic *fnic)
 		err = vnic_dev_notify_set(fnic->vdev, fnic->wq_copy_count + fnic->copy_wq_base);
 		break;
 	default:
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Interrupt mode should be set up"
+		dev_err(&fnic->pdev->dev, "Interrupt mode should be set up"
 			     " before devcmd notify set %d\n",
 			     vnic_dev_get_intr_mode(fnic->vdev));
 		err = -1;
@@ -415,13 +453,6 @@ static void fnic_notify_timer(struct timer_list *t)
 		  round_jiffies(jiffies + FNIC_NOTIFY_TIMER_PERIOD));
 }
 
-static void fnic_fip_notify_timer(struct timer_list *t)
-{
-	struct fnic *fnic = from_timer(fnic, t, fip_timer);
-
-	fnic_handle_fip_timer(fnic);
-}
-
 static void fnic_notify_timer_start(struct fnic *fnic)
 {
 	switch (vnic_dev_get_intr_mode(fnic->vdev)) {
@@ -521,6 +552,8 @@ static int fnic_cleanup(struct fnic *fnic)
 		vnic_intr_clean(&fnic->intr[i]);
 
 	mempool_destroy(fnic->io_req_pool);
+	mempool_destroy(fnic->frame_pool);
+	mempool_destroy(fnic->frame_elem_pool);
 	for (i = 0; i < FNIC_SGL_NUM_CACHES; i++)
 		mempool_destroy(fnic->io_sgl_pool[i]);
 
@@ -533,25 +566,36 @@ static void fnic_iounmap(struct fnic *fnic)
 		iounmap(fnic->bar0.vaddr);
 }
 
-/**
- * fnic_get_mac() - get assigned data MAC address for FIP code.
- * @lport: 	local port.
- */
-static u8 *fnic_get_mac(struct fc_lport *lport)
+static void fnic_set_vlan(struct fnic *fnic, u16 vlan_id)
 {
-	struct fnic *fnic = lport_priv(lport);
+	vnic_dev_set_default_vlan(fnic->vdev, vlan_id);
+}
 
-	return fnic->data_src_addr;
+static void fnic_scsi_init(struct fnic *fnic)
+{
+	struct Scsi_Host *host = fnic->host;
+
+	snprintf(fnic->name, sizeof(fnic->name) - 1, "%s%d", DRV_NAME,
+			 host->host_no);
+
+	host->transportt = fnic_fc_transport;
 }
 
-static void fnic_set_vlan(struct fnic *fnic, u16 vlan_id)
+static void fnic_free_ioreq_tables_mq(struct fnic *fnic)
 {
-	vnic_dev_set_default_vlan(fnic->vdev, vlan_id);
+	int hwq;
+
+	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++)
+		kfree(fnic->sw_copy_wq[hwq].io_req_table);
 }
 
 static int fnic_scsi_drv_init(struct fnic *fnic)
 {
-	struct Scsi_Host *host = fnic->lport->host;
+	struct Scsi_Host *host = fnic->host;
+	int err;
+	struct pci_dev *pdev = fnic->pdev;
+	struct fnic_iport_s *iport = &fnic->iport;
+	int hwq;
 
 	/* Configure maximum outstanding IO reqs*/
 	if (fnic->config.io_throttle_count != FNIC_UCSM_DFLT_THROTTLE_CNT_BLD)
@@ -562,40 +606,92 @@ static int fnic_scsi_drv_init(struct fnic *fnic)
 	fnic->fnic_max_tag_id = host->can_queue;
 	host->max_lun = fnic->config.luns_per_tgt;
 	host->max_id = FNIC_MAX_FCP_TARGET;
-	host->max_cmd_len = FCOE_MAX_CMD_LEN;
+	host->max_cmd_len = FNIC_FCOE_MAX_CMD_LEN;
 
 	host->nr_hw_queues = fnic->wq_copy_count;
 
-	shost_printk(KERN_INFO, host,
-			"fnic: can_queue: %d max_lun: %llu",
+	dev_info(&fnic->pdev->dev, "fnic: can_queue: %d max_lun: %llu",
 			host->can_queue, host->max_lun);
 
-	shost_printk(KERN_INFO, host,
-			"fnic: max_id: %d max_cmd_len: %d nr_hw_queues: %d",
+	dev_info(&fnic->pdev->dev, "fnic: max_id: %d max_cmd_len: %d nr_hw_queues: %d",
 			host->max_id, host->max_cmd_len, host->nr_hw_queues);
 
+	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) {
+		fnic->sw_copy_wq[hwq].ioreq_table_size = fnic->fnic_max_tag_id;
+		fnic->sw_copy_wq[hwq].io_req_table =
+			kzalloc((fnic->sw_copy_wq[hwq].ioreq_table_size + 1) *
+					sizeof(struct fnic_io_req *), GFP_KERNEL);
+
+		if (!fnic->sw_copy_wq[hwq].io_req_table) {
+			fnic_free_ioreq_tables_mq(fnic);
+			return -ENOMEM;
+		}
+	}
+
+	dev_info(&fnic->pdev->dev, "fnic copy wqs: %d, Q0 ioreq table size: %d\n",
+			fnic->wq_copy_count, fnic->sw_copy_wq[0].ioreq_table_size);
+
+	fnic_scsi_init(fnic);
+
+	err = scsi_add_host(fnic->host, &pdev->dev);
+	if (err) {
+		dev_err(&fnic->pdev->dev, "fnic: scsi add host failed: aborting\n");
+		return err;
+	}
+	fc_host_maxframe_size(fnic->host) = iport->max_payload_size;
+	fc_host_dev_loss_tmo(fnic->host) =
+		fnic->config.port_down_timeout / 1000;
+	sprintf(fc_host_symbolic_name(fnic->host),
+			DRV_NAME " v" DRV_VERSION " over %s", fnic->name);
+	fc_host_port_type(fnic->host) = FC_PORTTYPE_NPORT;
+	fc_host_node_name(fnic->host) = iport->wwnn;
+	fc_host_port_name(fnic->host) = iport->wwpn;
+	fc_host_supported_classes(fnic->host) = FC_COS_CLASS3;
+	memset(fc_host_supported_fc4s(fnic->host), 0,
+		   sizeof(fc_host_supported_fc4s(fnic->host)));
+	fc_host_supported_fc4s(fnic->host)[2] = 1;
+	fc_host_supported_fc4s(fnic->host)[7] = 1;
+	fc_host_supported_speeds(fnic->host) = 0;
+	fc_host_supported_speeds(fnic->host) |= FC_PORTSPEED_8GBIT;
+
+	dev_info(&fnic->pdev->dev, "shost_data: 0x%p\n", fnic->host->shost_data);
+	if (fnic->host->shost_data != NULL) {
+		if (fnic_tgt_id_binding == 0) {
+			dev_info(&fnic->pdev->dev, "Setting target binding to NONE\n");
+			fc_host_tgtid_bind_type(fnic->host) = FC_TGTID_BIND_NONE;
+		} else {
+			dev_info(&fnic->pdev->dev, "Setting target binding to WWPN\n");
+			fc_host_tgtid_bind_type(fnic->host) = FC_TGTID_BIND_BY_WWPN;
+		}
+	}
+
+	fnic->io_req_pool = mempool_create_slab_pool(2, fnic_io_req_cache);
+	if (!fnic->io_req_pool) {
+		scsi_remove_host(fnic->host);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
 void fnic_mq_map_queues_cpus(struct Scsi_Host *host)
 {
-	struct fc_lport *lp = shost_priv(host);
-	struct fnic *fnic = lport_priv(lp);
+	struct fnic *fnic = *((struct fnic **) shost_priv(host));
 	struct pci_dev *l_pdev = fnic->pdev;
 	int intr_mode = fnic->config.intr_mode;
 	struct blk_mq_queue_map *qmap = &host->tag_set.map[HCTX_TYPE_DEFAULT];
 
 	if (intr_mode == VNIC_DEV_INTR_MODE_MSI || intr_mode == VNIC_DEV_INTR_MODE_INTX) {
-		FNIC_MAIN_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_MAIN_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"intr_mode is not msix\n");
 		return;
 	}
 
-	FNIC_MAIN_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+	FNIC_MAIN_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			"qmap->nr_queues: %d\n", qmap->nr_queues);
 
 	if (l_pdev == NULL) {
-		FNIC_MAIN_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_MAIN_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 						"l_pdev is null\n");
 		return;
 	}
@@ -605,60 +701,65 @@ void fnic_mq_map_queues_cpus(struct Scsi_Host *host)
 
 static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	struct Scsi_Host *host;
-	struct fc_lport *lp;
+	struct Scsi_Host *host = NULL;
 	struct fnic *fnic;
 	mempool_t *pool;
+	struct fnic_iport_s *iport;
 	int err = 0;
 	int fnic_id = 0;
 	int i;
 	unsigned long flags;
-	int hwq;
+	char *desc, *subsys_desc;
+	int len;
 
 	/*
-	 * Allocate SCSI Host and set up association between host,
-	 * local port, and fnic
+	 * Allocate fnic
 	 */
-	lp = libfc_host_alloc(&fnic_host_template, sizeof(struct fnic));
-	if (!lp) {
-		printk(KERN_ERR PFX "Unable to alloc libfc local port\n");
+	fnic = kzalloc(sizeof(struct fnic), GFP_KERNEL);
+	if (!fnic) {
 		err = -ENOMEM;
-		goto err_out;
+		goto err_out_fnic_alloc;
 	}
 
-	host = lp->host;
-	fnic = lport_priv(lp);
+	iport = &fnic->iport;
 
 	fnic_id = ida_alloc(&fnic_ida, GFP_KERNEL);
 	if (fnic_id < 0) {
-		pr_err("Unable to alloc fnic ID\n");
+		dev_err(&pdev->dev, "Unable to alloc fnic ID\n");
 		err = fnic_id;
 		goto err_out_ida_alloc;
 	}
-	fnic->lport = lp;
-	fnic->ctlr.lp = lp;
-	fnic->link_events = 0;
-	fnic->pdev = pdev;
-
-	snprintf(fnic->name, sizeof(fnic->name) - 1, "%s%d", DRV_NAME,
-		 host->host_no);
 
-	host->transportt = fnic_fc_transport;
+	fnic->pdev = pdev;
 	fnic->fnic_num = fnic_id;
-	fnic_stats_debugfs_init(fnic);
+
+	/* Find model name from PCIe subsys ID */
+	if (fnic_get_desc_by_devid(pdev, &desc, &subsys_desc) == 0) {
+		dev_info(&fnic->pdev->dev, "Model: %s\n", subsys_desc);
+
+		/* Update FDMI model */
+		fnic->subsys_desc_len = strlen(subsys_desc);
+		len = ARRAY_SIZE(fnic->subsys_desc);
+		if (fnic->subsys_desc_len > len)
+			fnic->subsys_desc_len = len;
+		memcpy(fnic->subsys_desc, subsys_desc, fnic->subsys_desc_len);
+		dev_info(&fnic->pdev->dev, "FDMI Model: %s\n", fnic->subsys_desc);
+	} else {
+		fnic->subsys_desc_len = 0;
+		dev_info(&fnic->pdev->dev, "Model: %s subsys_id: 0x%04x\n", "Unknown",
+				pdev->subsystem_device);
+	}
 
 	err = pci_enable_device(pdev);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Cannot enable PCI device, aborting.\n");
-		goto err_out_free_hba;
+		dev_err(&fnic->pdev->dev, "Cannot enable PCI device, aborting.\n");
+		goto err_out_pci_enable_device;
 	}
 
 	err = pci_request_regions(pdev, DRV_NAME);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Cannot enable PCI resources, aborting\n");
-		goto err_out_disable_device;
+		dev_err(&fnic->pdev->dev, "Cannot enable PCI resources, aborting\n");
+		goto err_out_pci_request_regions;
 	}
 
 	pci_set_master(pdev);
@@ -671,19 +772,17 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
-			shost_printk(KERN_ERR, fnic->lport->host,
-				     "No usable DMA configuration "
+			dev_err(&fnic->pdev->dev, "No usable DMA configuration "
 				     "aborting\n");
-			goto err_out_release_regions;
+			goto err_out_set_dma_mask;
 		}
 	}
 
 	/* Map vNIC resources from BAR0 */
 	if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "BAR0 not memory-map'able, aborting.\n");
+		dev_err(&fnic->pdev->dev, "BAR0 not memory-map'able, aborting.\n");
 		err = -ENODEV;
-		goto err_out_release_regions;
+		goto err_out_map_bar;
 	}
 
 	fnic->bar0.vaddr = pci_iomap(pdev, 0, 0);
@@ -691,61 +790,79 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	fnic->bar0.len = pci_resource_len(pdev, 0);
 
 	if (!fnic->bar0.vaddr) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Cannot memory-map BAR0 res hdr, "
+		dev_err(&fnic->pdev->dev, "Cannot memory-map BAR0 res hdr, "
 			     "aborting.\n");
 		err = -ENODEV;
-		goto err_out_release_regions;
+		goto err_out_fnic_map_bar;
 	}
 
 	fnic->vdev = vnic_dev_register(NULL, fnic, pdev, &fnic->bar0);
 	if (!fnic->vdev) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "vNIC registration failed, "
+		dev_err(&fnic->pdev->dev, "vNIC registration failed, "
 			     "aborting.\n");
 		err = -ENODEV;
-		goto err_out_iounmap;
+		goto err_out_dev_register;
 	}
 
 	err = vnic_dev_cmd_init(fnic->vdev);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-				"vnic_dev_cmd_init() returns %d, aborting\n",
+		dev_err(&fnic->pdev->dev, "vnic_dev_cmd_init() returns %d, aborting\n",
 				err);
-		goto err_out_vnic_unregister;
+		goto err_out_dev_cmd_init;
 	}
 
 	err = fnic_dev_wait(fnic->vdev, vnic_dev_open,
 			    vnic_dev_open_done, CMD_OPENF_RQ_ENABLE_THEN_POST);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "vNIC dev open failed, aborting.\n");
-		goto err_out_dev_cmd_deinit;
+		dev_err(&fnic->pdev->dev, "vNIC dev open failed, aborting.\n");
+		goto err_out_dev_open;
 	}
 
 	err = vnic_dev_init(fnic->vdev, 0);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "vNIC dev init failed, aborting.\n");
-		goto err_out_dev_close;
+		dev_err(&fnic->pdev->dev, "vNIC dev init failed, aborting.\n");
+		goto err_out_dev_init;
 	}
 
-	err = vnic_dev_mac_addr(fnic->vdev, fnic->ctlr.ctl_src_addr);
+	err = vnic_dev_mac_addr(fnic->vdev, iport->hwmac);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "vNIC get MAC addr failed \n");
-		goto err_out_dev_close;
+		dev_err(&fnic->pdev->dev, "vNIC get MAC addr failed\n");
+		goto err_out_dev_mac_addr;
 	}
 	/* set data_src for point-to-point mode and to keep it non-zero */
-	memcpy(fnic->data_src_addr, fnic->ctlr.ctl_src_addr, ETH_ALEN);
+	memcpy(fnic->data_src_addr, iport->hwmac, ETH_ALEN);
 
 	/* Get vNIC configuration */
 	err = fnic_get_vnic_config(fnic);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Get vNIC configuration failed, "
+		dev_err(&fnic->pdev->dev, "Get vNIC configuration failed, "
 			     "aborting.\n");
-		goto err_out_dev_close;
+		goto err_out_fnic_get_config;
+	}
+
+	switch (fnic->config.flags & 0xff0) {
+	case VFCF_FC_INITIATOR:
+		{
+			host =
+				scsi_host_alloc(&fnic_host_template,
+								sizeof(struct fnic *));
+			if (!host) {
+				dev_err(&fnic->pdev->dev, "Unable to allocate scsi host\n");
+				err = -ENOMEM;
+				goto err_out_scsi_host_alloc;
+			}
+			*((struct fnic **) shost_priv(host)) = fnic;
+
+			fnic->host = host;
+			fnic->role = FNIC_ROLE_FCP_INITIATOR;
+			dev_info(&fnic->pdev->dev, "fnic: %d is scsi initiator\n",
+					fnic->fnic_num);
+		}
+		break;
+	default:
+		dev_info(&fnic->pdev->dev, "fnic: %d has no role defined\n", fnic->fnic_num);
+		err = -EINVAL;
+		goto err_out_fnic_role;
 	}
 
 	/* Setup PCI resources */
@@ -755,29 +872,18 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	err = fnic_set_intr_mode(fnic);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Failed to set intr mode, "
+		dev_err(&fnic->pdev->dev, "Failed to set intr mode, "
 			     "aborting.\n");
-		goto err_out_dev_close;
+		goto err_out_fnic_set_intr_mode;
 	}
 
 	err = fnic_alloc_vnic_resources(fnic);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Failed to alloc vNIC resources, "
+		dev_err(&fnic->pdev->dev, "Failed to alloc vNIC resources, "
 			     "aborting.\n");
-		goto err_out_clear_intr;
+		goto err_out_fnic_alloc_vnic_res;
 	}
-
-	fnic_scsi_drv_init(fnic);
-
-	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++) {
-		fnic->sw_copy_wq[hwq].ioreq_table_size = fnic->fnic_max_tag_id;
-		fnic->sw_copy_wq[hwq].io_req_table =
-					kzalloc((fnic->sw_copy_wq[hwq].ioreq_table_size + 1) *
-					sizeof(struct fnic_io_req *), GFP_KERNEL);
-	}
-	shost_printk(KERN_INFO, fnic->lport->host, "fnic copy wqs: %d, Q0 ioreq table size: %d\n",
+	dev_info(&fnic->pdev->dev, "fnic copy wqs: %d, Q0 ioreq table size: %d\n",
 			fnic->wq_copy_count, fnic->sw_copy_wq[0].ioreq_table_size);
 
 	/* initialize all fnic locks */
@@ -793,50 +899,56 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		fnic->fw_ack_index[i] = -1;
 	}
 
-	err = -ENOMEM;
-	fnic->io_req_pool = mempool_create_slab_pool(2, fnic_io_req_cache);
-	if (!fnic->io_req_pool)
-		goto err_out_free_resources;
-
 	pool = mempool_create_slab_pool(2, fnic_sgl_cache[FNIC_SGL_CACHE_DFLT]);
-	if (!pool)
-		goto err_out_free_ioreq_pool;
+	if (!pool) {
+		err = -ENOMEM;
+		goto err_out_free_resources;
+	}
 	fnic->io_sgl_pool[FNIC_SGL_CACHE_DFLT] = pool;
 
 	pool = mempool_create_slab_pool(2, fnic_sgl_cache[FNIC_SGL_CACHE_MAX]);
-	if (!pool)
+	if (!pool) {
+		err = -ENOMEM;
 		goto err_out_free_dflt_pool;
+	}
 	fnic->io_sgl_pool[FNIC_SGL_CACHE_MAX] = pool;
 
+	pool = mempool_create_slab_pool(FDLS_MIN_FRAMES, fdls_frame_cache);
+	if (!pool) {
+		err = -ENOMEM;
+		goto err_out_fdls_frame_pool;
+	}
+	fnic->frame_pool = pool;
+
+	pool = mempool_create_slab_pool(FDLS_MIN_FRAME_ELEM,
+						fdls_frame_elem_cache);
+	if (!pool) {
+		err = -ENOMEM;
+		goto err_out_fdls_frame_elem_pool;
+	}
+	fnic->frame_elem_pool = pool;
+
 	/* setup vlan config, hw inserts vlan header */
 	fnic->vlan_hw_insert = 1;
 	fnic->vlan_id = 0;
 
-	/* Initialize the FIP fcoe_ctrl struct */
-	fnic->ctlr.send = fnic_eth_send;
-	fnic->ctlr.update_mac = fnic_update_mac;
-	fnic->ctlr.get_src_addr = fnic_get_mac;
 	if (fnic->config.flags & VFCF_FIP_CAPABLE) {
-		shost_printk(KERN_INFO, fnic->lport->host,
-			     "firmware supports FIP\n");
+		dev_info(&fnic->pdev->dev, "firmware supports FIP\n");
 		/* enable directed and multicast */
 		vnic_dev_packet_filter(fnic->vdev, 1, 1, 0, 0, 0);
 		vnic_dev_add_addr(fnic->vdev, FIP_ALL_ENODE_MACS);
-		vnic_dev_add_addr(fnic->vdev, fnic->ctlr.ctl_src_addr);
-		fnic->set_vlan = fnic_set_vlan;
-		fcoe_ctlr_init(&fnic->ctlr, FIP_MODE_AUTO);
-		timer_setup(&fnic->fip_timer, fnic_fip_notify_timer, 0);
+		vnic_dev_add_addr(fnic->vdev, iport->hwmac);
 		spin_lock_init(&fnic->vlans_lock);
 		INIT_WORK(&fnic->fip_frame_work, fnic_handle_fip_frame);
-		INIT_WORK(&fnic->event_work, fnic_handle_event);
-		skb_queue_head_init(&fnic->fip_frame_queue);
-		INIT_LIST_HEAD(&fnic->evlist);
-		INIT_LIST_HEAD(&fnic->vlans);
+		INIT_LIST_HEAD(&fnic->fip_frame_queue);
+		INIT_LIST_HEAD(&fnic->vlan_list);
+		timer_setup(&fnic->retry_fip_timer, fnic_handle_fip_timer, 0);
+		timer_setup(&fnic->fcs_ka_timer, fnic_handle_fcs_ka_timer, 0);
+		timer_setup(&fnic->enode_ka_timer, fnic_handle_enode_ka_timer, 0);
+		timer_setup(&fnic->vn_ka_timer, fnic_handle_vn_ka_timer, 0);
+		fnic->set_vlan = fnic_set_vlan;
 	} else {
-		shost_printk(KERN_INFO, fnic->lport->host,
-			     "firmware uses non-FIP mode\n");
-		fcoe_ctlr_init(&fnic->ctlr, FIP_MODE_NON_FIP);
-		fnic->ctlr.state = FIP_ST_NON_FIP;
+		dev_info(&fnic->pdev->dev, "firmware uses non-FIP mode\n");
 	}
 	fnic->state = FNIC_IN_FC_MODE;
 
@@ -849,9 +961,8 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup notification buffer area */
 	err = fnic_notify_set(fnic);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Failed to alloc notify buffer, aborting.\n");
-		goto err_out_free_max_pool;
+		dev_err(&fnic->pdev->dev, "Failed to alloc notify buffer, aborting.\n");
+		goto err_out_fnic_notify_set;
 	}
 
 	/* Setup notify timer when using MSI interrupts */
@@ -862,13 +973,62 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	for (i = 0; i < fnic->rq_count; i++) {
 		err = vnic_rq_fill(&fnic->rq[i], fnic_alloc_rq_frame);
 		if (err) {
-			shost_printk(KERN_ERR, fnic->lport->host,
-				     "fnic_alloc_rq_frame can't alloc "
+			dev_err(&fnic->pdev->dev, "fnic_alloc_rq_frame can't alloc "
 				     "frame\n");
-			goto err_out_rq_buf;
+			goto err_out_alloc_rq_buf;
 		}
 	}
 
+	init_completion(&fnic->reset_completion_wait);
+
+	/* Start local port initialization */
+	iport->max_flogi_retries = fnic->config.flogi_retries;
+	iport->max_plogi_retries = fnic->config.plogi_retries;
+	iport->plogi_timeout = fnic->config.plogi_timeout;
+	iport->service_params =
+		(FNIC_FCP_SP_INITIATOR | FNIC_FCP_SP_RD_XRDY_DIS |
+		 FNIC_FCP_SP_CONF_CMPL);
+	if (fnic->config.flags & VFCF_FCP_SEQ_LVL_ERR)
+		iport->service_params |= FNIC_FCP_SP_RETRY;
+
+	iport->boot_time = jiffies;
+	iport->e_d_tov = fnic->config.ed_tov;
+	iport->r_a_tov = fnic->config.ra_tov;
+	iport->link_supported_speeds = FNIC_PORTSPEED_10GBIT;
+	iport->wwpn = fnic->config.port_wwn;
+	iport->wwnn = fnic->config.node_wwn;
+
+	iport->max_payload_size = fnic->config.maxdatafieldsize;
+
+	if ((iport->max_payload_size < FNIC_MIN_DATA_FIELD_SIZE) ||
+		(iport->max_payload_size > FNIC_FC_MAX_PAYLOAD_LEN) ||
+		((iport->max_payload_size % 4) != 0)) {
+		iport->max_payload_size = FNIC_FC_MAX_PAYLOAD_LEN;
+	}
+
+	iport->flags |= FNIC_FIRST_LINK_UP;
+
+	timer_setup(&(iport->fabric.retry_timer), fdls_fabric_timer_callback,
+				0);
+
+	fnic->stats_reset_time = jiffies;
+
+	INIT_WORK(&fnic->link_work, fnic_handle_link);
+	INIT_WORK(&fnic->frame_work, fnic_handle_frame);
+	INIT_WORK(&fnic->tport_work, fnic_tport_event_handler);
+	INIT_WORK(&fnic->flush_work, fnic_flush_tx);
+
+	INIT_LIST_HEAD(&fnic->frame_queue);
+	INIT_LIST_HEAD(&fnic->tx_queue);
+	INIT_LIST_HEAD(&fnic->tport_event_list);
+
+	INIT_DELAYED_WORK(&iport->oxid_pool.schedule_oxid_free_retry,
+	fdls_schedule_oxid_free_retry_work);
+
+	/* Initialize the oxid reclaim list and work struct */
+	INIT_LIST_HEAD(&iport->oxid_pool.oxid_reclaim_list);
+	INIT_DELAYED_WORK(&iport->oxid_pool.oxid_reclaim_work, fdls_reclaim_oxid_handler);
+
 	/* Enable all queues */
 	for (i = 0; i < fnic->raw_wq_count; i++)
 		vnic_wq_enable(&fnic->wq[i]);
@@ -879,180 +1039,131 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	for (i = 0; i < fnic->wq_copy_count; i++)
 		vnic_wq_copy_enable(&fnic->hw_copy_wq[i]);
 
-	err = fnic_request_intr(fnic);
-	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Unable to request irq.\n");
-		goto err_out_request_intr;
-	}
+	vnic_dev_enable(fnic->vdev);
 
-	/*
-	 * Initialization done with PCI system, hardware, firmware.
-	 * Add host to SCSI
-	 */
-	err = scsi_add_host(lp->host, &pdev->dev);
+	err = fnic_request_intr(fnic);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "fnic: scsi_add_host failed...exiting\n");
-		goto err_out_scsi_add_host;
+		dev_err(&fnic->pdev->dev, "Unable to request irq.\n");
+		goto err_out_fnic_request_intr;
 	}
 
+	fnic_notify_timer_start(fnic);
 
-	/* Start local port initiatialization */
-
-	lp->link_up = 0;
-
-	lp->max_retry_count = fnic->config.flogi_retries;
-	lp->max_rport_retry_count = fnic->config.plogi_retries;
-	lp->service_params = (FCP_SPPF_INIT_FCN | FCP_SPPF_RD_XRDY_DIS |
-			      FCP_SPPF_CONF_COMPL);
-	if (fnic->config.flags & VFCF_FCP_SEQ_LVL_ERR)
-		lp->service_params |= FCP_SPPF_RETRY;
-
-	lp->boot_time = jiffies;
-	lp->e_d_tov = fnic->config.ed_tov;
-	lp->r_a_tov = fnic->config.ra_tov;
-	lp->link_supported_speeds = FC_PORTSPEED_10GBIT;
-	fc_set_wwnn(lp, fnic->config.node_wwn);
-	fc_set_wwpn(lp, fnic->config.port_wwn);
-
-	fcoe_libfc_config(lp, &fnic->ctlr, &fnic_transport_template, 0);
-
-	if (!fc_exch_mgr_alloc(lp, FC_CLASS_3, FCPIO_HOST_EXCH_RANGE_START,
-			       FCPIO_HOST_EXCH_RANGE_END, NULL)) {
-		err = -ENOMEM;
-		goto err_out_fc_exch_mgr_alloc;
-	}
-
-	fc_lport_init_stats(lp);
-	fnic->stats_reset_time = jiffies;
+	fnic_fdls_init(fnic, (fnic->config.flags & VFCF_FIP_CAPABLE));
 
-	fc_lport_config(lp);
+	err = fnic_scsi_drv_init(fnic);
+	if (err)
+		goto err_out_scsi_drv_init;
 
-	if (fc_set_mfs(lp, fnic->config.maxdatafieldsize +
-		       sizeof(struct fc_frame_header))) {
-		err = -EINVAL;
-		goto err_out_free_exch_mgr;
+	err = fnic_stats_debugfs_init(fnic);
+	if (err) {
+		dev_err(&fnic->pdev->dev, "Failed to initialize debugfs for stats\n");
+		goto err_out_free_stats_debugfs;
 	}
-	fc_host_maxframe_size(lp->host) = lp->mfs;
-	fc_host_dev_loss_tmo(lp->host) = fnic->config.port_down_timeout / 1000;
 
-	sprintf(fc_host_symbolic_name(lp->host),
-		DRV_NAME " v" DRV_VERSION " over %s", fnic->name);
+	for (i = 0; i < fnic->intr_count; i++)
+		vnic_intr_unmask(&fnic->intr[i]);
 
 	spin_lock_irqsave(&fnic_list_lock, flags);
 	list_add_tail(&fnic->list, &fnic_list);
 	spin_unlock_irqrestore(&fnic_list_lock, flags);
 
-	INIT_WORK(&fnic->link_work, fnic_handle_link);
-	INIT_WORK(&fnic->frame_work, fnic_handle_frame);
-	INIT_WORK(&fnic->flush_work, fnic_flush_tx);
-	skb_queue_head_init(&fnic->frame_queue);
-	skb_queue_head_init(&fnic->tx_queue);
-
-	fc_fabric_login(lp);
-
-	vnic_dev_enable(fnic->vdev);
-
-	for (i = 0; i < fnic->intr_count; i++)
-		vnic_intr_unmask(&fnic->intr[i]);
-
-	fnic_notify_timer_start(fnic);
-
 	return 0;
 
-err_out_free_exch_mgr:
-	fc_exch_mgr_free(lp);
-err_out_fc_exch_mgr_alloc:
-	fc_remove_host(lp->host);
-	scsi_remove_host(lp->host);
-err_out_scsi_add_host:
+err_out_free_stats_debugfs:
+	fnic_stats_debugfs_remove(fnic);
+	fnic_free_ioreq_tables_mq(fnic);
+	scsi_remove_host(fnic->host);
+err_out_scsi_drv_init:
 	fnic_free_intr(fnic);
-err_out_request_intr:
-	for (i = 0; i < fnic->rq_count; i++)
+err_out_fnic_request_intr:
+err_out_alloc_rq_buf:
+	for (i = 0; i < fnic->rq_count; i++) {
+		if (ioread32(&fnic->rq[i].ctrl->enable))
+			vnic_rq_disable(&fnic->rq[i]);
 		vnic_rq_clean(&fnic->rq[i], fnic_free_rq_buf);
-err_out_rq_buf:
+	}
 	vnic_dev_notify_unset(fnic->vdev);
-err_out_free_max_pool:
+err_out_fnic_notify_set:
+	mempool_destroy(fnic->frame_elem_pool);
+err_out_fdls_frame_elem_pool:
+	mempool_destroy(fnic->frame_pool);
+err_out_fdls_frame_pool:
 	mempool_destroy(fnic->io_sgl_pool[FNIC_SGL_CACHE_MAX]);
 err_out_free_dflt_pool:
 	mempool_destroy(fnic->io_sgl_pool[FNIC_SGL_CACHE_DFLT]);
-err_out_free_ioreq_pool:
-	mempool_destroy(fnic->io_req_pool);
 err_out_free_resources:
-	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++)
-		kfree(fnic->sw_copy_wq[hwq].io_req_table);
 	fnic_free_vnic_resources(fnic);
-err_out_clear_intr:
+err_out_fnic_alloc_vnic_res:
 	fnic_clear_intr_mode(fnic);
-err_out_dev_close:
+err_out_fnic_set_intr_mode:
+	scsi_host_put(fnic->host);
+err_out_fnic_role:
+err_out_scsi_host_alloc:
+err_out_fnic_get_config:
+err_out_dev_mac_addr:
+err_out_dev_init:
 	vnic_dev_close(fnic->vdev);
-err_out_dev_cmd_deinit:
-err_out_vnic_unregister:
+err_out_dev_open:
+err_out_dev_cmd_init:
 	vnic_dev_unregister(fnic->vdev);
-err_out_iounmap:
+err_out_dev_register:
 	fnic_iounmap(fnic);
-err_out_release_regions:
+err_out_fnic_map_bar:
+err_out_map_bar:
+err_out_set_dma_mask:
 	pci_release_regions(pdev);
-err_out_disable_device:
+err_out_pci_request_regions:
 	pci_disable_device(pdev);
-err_out_free_hba:
-	fnic_stats_debugfs_remove(fnic);
+err_out_pci_enable_device:
 	ida_free(&fnic_ida, fnic->fnic_num);
 err_out_ida_alloc:
-	scsi_host_put(lp->host);
-err_out:
+	kfree(fnic);
+err_out_fnic_alloc:
 	return err;
 }
 
 static void fnic_remove(struct pci_dev *pdev)
 {
 	struct fnic *fnic = pci_get_drvdata(pdev);
-	struct fc_lport *lp = fnic->lport;
 	unsigned long flags;
-	int hwq;
 
 	/*
-	 * Mark state so that the workqueue thread stops forwarding
-	 * received frames and link events to the local port. ISR and
-	 * other threads that can queue work items will also stop
-	 * creating work items on the fnic workqueue
+	 * Sometimes when probe() fails and do not exit with an error code,
+	 * remove() gets called with 'drvdata' not set. Avoid a crash by
+	 * adding a defensive check.
 	 */
+	if (!fnic)
+		return;
+
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	fnic->stop_rx_link_events = 1;
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	if (vnic_dev_get_intr_mode(fnic->vdev) == VNIC_DEV_INTR_MODE_MSI)
-		del_timer_sync(&fnic->notify_timer);
-
 	/*
 	 * Flush the fnic event queue. After this call, there should
 	 * be no event queued for this fnic device in the workqueue
 	 */
 	flush_workqueue(fnic_event_queue);
-	skb_queue_purge(&fnic->frame_queue);
-	skb_queue_purge(&fnic->tx_queue);
+
+	fnic_scsi_unload(fnic);
+
+	if (vnic_dev_get_intr_mode(fnic->vdev) == VNIC_DEV_INTR_MODE_MSI)
+		del_timer_sync(&fnic->notify_timer);
 
 	if (fnic->config.flags & VFCF_FIP_CAPABLE) {
-		del_timer_sync(&fnic->fip_timer);
-		skb_queue_purge(&fnic->fip_frame_queue);
+		del_timer_sync(&fnic->retry_fip_timer);
+		del_timer_sync(&fnic->fcs_ka_timer);
+		del_timer_sync(&fnic->enode_ka_timer);
+		del_timer_sync(&fnic->vn_ka_timer);
+
+		fnic_free_txq(&fnic->fip_frame_queue);
 		fnic_fcoe_reset_vlans(fnic);
-		fnic_fcoe_evlist_free(fnic);
 	}
 
-	/*
-	 * Log off the fabric. This stops all remote ports, dns port,
-	 * logs off the fabric. This flushes all rport, disc, lport work
-	 * before returning
-	 */
-	fc_fabric_logoff(fnic->lport);
-
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	fnic->in_remove = 1;
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	if ((fnic_fdmi_support == 1) && (fnic->iport.fabric.fdmi_pending > 0))
+		del_timer_sync(&fnic->iport.fabric.fdmi_timer);
 
-	fcoe_ctlr_destroy(&fnic->ctlr);
-	fc_lport_destroy(lp);
 	fnic_stats_debugfs_remove(fnic);
 
 	/*
@@ -1062,18 +1173,13 @@ static void fnic_remove(struct pci_dev *pdev)
 	 */
 	fnic_cleanup(fnic);
 
-	BUG_ON(!skb_queue_empty(&fnic->frame_queue));
-	BUG_ON(!skb_queue_empty(&fnic->tx_queue));
-
 	spin_lock_irqsave(&fnic_list_lock, flags);
 	list_del(&fnic->list);
 	spin_unlock_irqrestore(&fnic_list_lock, flags);
 
-	fc_remove_host(fnic->lport->host);
-	scsi_remove_host(fnic->lport->host);
-	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++)
-		kfree(fnic->sw_copy_wq[hwq].io_req_table);
-	fc_exch_mgr_free(fnic->lport);
+	fnic_free_txq(&fnic->frame_queue);
+	fnic_free_txq(&fnic->tx_queue);
+
 	vnic_dev_notify_unset(fnic->vdev);
 	fnic_free_intr(fnic);
 	fnic_free_vnic_resources(fnic);
@@ -1083,8 +1189,11 @@ static void fnic_remove(struct pci_dev *pdev)
 	fnic_iounmap(fnic);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
 	ida_free(&fnic_ida, fnic->fnic_num);
-	scsi_host_put(lp->host);
+	fnic_scsi_unload_cleanup(fnic);
+	scsi_host_put(fnic->host);
+	kfree(fnic);
 }
 
 static struct pci_driver fnic_driver = {
@@ -1160,6 +1269,24 @@ static int __init fnic_init_module(void)
 		goto err_create_fnic_ioreq_slab;
 	}
 
+	fdls_frame_cache = kmem_cache_create("fdls_frames",
+					FNIC_FCOE_FRAME_MAXSZ,
+					0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!fdls_frame_cache) {
+		pr_err("fnic fdls frame cache create failed\n");
+		err = -ENOMEM;
+		goto err_create_fdls_frame_cache;
+	}
+
+	fdls_frame_elem_cache = kmem_cache_create("fdls_frame_elem",
+					sizeof(struct fnic_frame_list),
+					0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!fdls_frame_elem_cache) {
+		pr_err("fnic fdls frame elem cache create failed\n");
+		err = -ENOMEM;
+		goto err_create_fdls_frame_cache_elem;
+	}
+
 	fnic_event_queue =
 		alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, "fnic_event_wq");
 	if (!fnic_event_queue) {
@@ -1176,6 +1303,19 @@ static int __init fnic_init_module(void)
 		goto err_create_fip_workq;
 	}
 
+	if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON) {
+		reset_fnic_work_queue =
+			create_singlethread_workqueue("reset_fnic_work_queue");
+		if (!reset_fnic_work_queue) {
+			pr_err("reset fnic work queue create failed\n");
+			err = -ENOMEM;
+			goto err_create_reset_fnic_workq;
+		}
+		spin_lock_init(&reset_fnic_list_lock);
+		INIT_LIST_HEAD(&reset_fnic_list);
+		INIT_WORK(&reset_fnic_work, fnic_reset_work_handler);
+	}
+
 	fnic_fc_transport = fc_attach_transport(&fnic_fc_functions);
 	if (!fnic_fc_transport) {
 		printk(KERN_ERR PFX "fc_attach_transport error\n");
@@ -1196,8 +1336,15 @@ err_pci_register:
 err_fc_transport:
 	destroy_workqueue(fnic_fip_queue);
 err_create_fip_workq:
+	if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON)
+		destroy_workqueue(reset_fnic_work_queue);
+err_create_reset_fnic_workq:
 	destroy_workqueue(fnic_event_queue);
 err_create_fnic_workq:
+	kmem_cache_destroy(fdls_frame_elem_cache);
+err_create_fdls_frame_cache_elem:
+	kmem_cache_destroy(fdls_frame_cache);
+err_create_fdls_frame_cache:
 	kmem_cache_destroy(fnic_io_req_cache);
 err_create_fnic_ioreq_slab:
 	kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_MAX]);
@@ -1214,11 +1361,18 @@ static void __exit fnic_cleanup_module(void)
 {
 	pci_unregister_driver(&fnic_driver);
 	destroy_workqueue(fnic_event_queue);
-	if (fnic_fip_queue)
+
+	if (pc_rscn_handling_feature_flag == PC_RSCN_HANDLING_FEATURE_ON)
+		destroy_workqueue(reset_fnic_work_queue);
+
+	if (fnic_fip_queue) {
+		flush_workqueue(fnic_fip_queue);
 		destroy_workqueue(fnic_fip_queue);
+	}
 	kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_MAX]);
 	kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_DFLT]);
 	kmem_cache_destroy(fnic_io_req_cache);
+	kmem_cache_destroy(fdls_frame_cache);
 	fc_release_transport(fnic_fc_transport);
 	fnic_trace_free();
 	fnic_fc_trace_free();
diff --git a/drivers/scsi/fnic/fnic_pci_subsys_devid.c b/drivers/scsi/fnic/fnic_pci_subsys_devid.c
new file mode 100644
index 000000000000..36a2c1268422
--- /dev/null
+++ b/drivers/scsi/fnic/fnic_pci_subsys_devid.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2008 Cisco Systems, Inc.  All rights reserved.
+ * Copyright 2007 Nuova Systems, Inc.  All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/mempool.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/if_ether.h>
+#include "fnic.h"
+
+static struct fnic_pcie_device fnic_pcie_device_table[] = {
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_VASONA,
+	 "VIC 1280"},
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_COTATI,
+	 "VIC 1240"},
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno",
+	 PCI_SUBDEVICE_ID_CISCO_LEXINGTON, "VIC 1225"},
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_ICEHOUSE,
+	 "VIC 1285"},
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno",
+	 PCI_SUBDEVICE_ID_CISCO_KIRKWOODLAKE, "VIC 1225T"},
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno",
+	 PCI_SUBDEVICE_ID_CISCO_SUSANVILLE, "VIC 1227"},
+	{PCI_DEVICE_ID_CISCO_SERENO, "Sereno", PCI_SUBDEVICE_ID_CISCO_TORRANCE,
+	 "VIC 1227T"},
+
+	{PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_CALISTOGA,
+	 "VIC 1340"},
+	{PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_MOUNTAINVIEW,
+	 "VIC 1380"},
+	{PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN,
+	 "C3260-SIOC"},
+	{PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_CLEARLAKE,
+	 "VIC 1385"},
+	{PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_MOUNTTIAN2,
+	 "C3260-SIOC"},
+	{PCI_DEVICE_ID_CISCO_CRUZ, "Cruz", PCI_SUBDEVICE_ID_CISCO_CLAREMONT,
+	 "VIC 1387"},
+
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BRADBURY,
+	 "VIC 1457"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega",
+	 PCI_SUBDEVICE_ID_CISCO_BRENTWOOD, "VIC 1455"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega",
+	 PCI_SUBDEVICE_ID_CISCO_BURLINGAME, "VIC 1487"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BAYSIDE,
+	 "VIC 1485"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega",
+	 PCI_SUBDEVICE_ID_CISCO_BAKERSFIELD, "VIC 1440"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega",
+	 PCI_SUBDEVICE_ID_CISCO_BOONVILLE, "VIC 1480"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BENICIA,
+	 "VIC 1495"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BEAUMONT,
+	 "VIC 1497"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BRISBANE,
+	 "VIC 1467"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega", PCI_SUBDEVICE_ID_CISCO_BENTON,
+	 "VIC 1477"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega",
+	 PCI_SUBDEVICE_ID_CISCO_TWIN_RIVER, "VIC 14425"},
+	{PCI_DEVICE_ID_CISCO_BODEGA, "Bodega",
+	 PCI_SUBDEVICE_ID_CISCO_TWIN_PEAK, "VIC 14825"},
+
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_BERN,
+	 "VIC 15420"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly",
+	 PCI_SUBDEVICE_ID_CISCO_STOCKHOLM, "VIC 15428"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_KRAKOW,
+	 "VIC 15411"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly",
+	 PCI_SUBDEVICE_ID_CISCO_LUCERNE, "VIC 15231"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_TURKU,
+	 "VIC 15238"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_GENEVA,
+	 "VIC 15422"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly",
+	 PCI_SUBDEVICE_ID_CISCO_HELSINKI, "VIC 15235"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly",
+	 PCI_SUBDEVICE_ID_CISCO_GOTHENBURG, "VIC 15425"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly",
+	 PCI_SUBDEVICE_ID_CISCO_TURKU_PLUS, "VIC 15237"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_ZURICH,
+	 "VIC 15230"},
+	{PCI_DEVICE_ID_CISCO_BEVERLY, "Beverly", PCI_SUBDEVICE_ID_CISCO_RIGA,
+	 "VIC 15427"},
+
+	{0,}
+};
+
+int fnic_get_desc_by_devid(struct pci_dev *pdev, char **desc,
+						   char **subsys_desc)
+{
+	unsigned short device = PCI_DEVICE_ID_CISCO_VIC_FC;
+	int max = ARRAY_SIZE(fnic_pcie_device_table);
+	struct fnic_pcie_device *t = fnic_pcie_device_table;
+	int index = 0;
+
+	if (pdev->device != device)
+		return 1;
+
+	while (t->device != 0) {
+		if (memcmp
+			((char *) &pdev->subsystem_device,
+			 (char *) &t->subsystem_device, sizeof(short)) == 0)
+			break;
+		t++;
+		index++;
+	}
+
+	if (index >= max - 1) {
+		*desc = NULL;
+		*subsys_desc = NULL;
+		return 1;
+	}
+
+	*desc = fnic_pcie_device_table[index].desc;
+	*subsys_desc = fnic_pcie_device_table[index].subsys_desc;
+	return 0;
+}
diff --git a/drivers/scsi/fnic/fnic_res.c b/drivers/scsi/fnic/fnic_res.c
index 33dd27f6f24e..763475587b7f 100644
--- a/drivers/scsi/fnic/fnic_res.c
+++ b/drivers/scsi/fnic/fnic_res.c
@@ -30,9 +30,7 @@ int fnic_get_vnic_config(struct fnic *fnic)
 				    offsetof(struct vnic_fc_config, m), \
 				    sizeof(c->m), &c->m); \
 		if (err) { \
-			shost_printk(KERN_ERR, fnic->lport->host, \
-				     "Error getting %s, %d\n", #m, \
-				     err); \
+			dev_err(&fnic->pdev->dev, "Error getting %s, %d\n", #m, err); \
 			return err; \
 		} \
 	} while (0);
@@ -60,6 +58,11 @@ int fnic_get_vnic_config(struct fnic *fnic)
 	GET_CONFIG(intr_mode);
 	GET_CONFIG(wq_copy_count);
 
+	if ((c->flags & (VFCF_FC_INITIATOR)) == 0) {
+		dev_info(&fnic->pdev->dev, "vNIC role not defined (def role: FC Init)\n");
+		c->flags |= VFCF_FC_INITIATOR;
+	}
+
 	c->wq_enet_desc_count =
 		min_t(u32, VNIC_FNIC_WQ_DESCS_MAX,
 		      max_t(u32, VNIC_FNIC_WQ_DESCS_MIN,
@@ -139,40 +142,28 @@ int fnic_get_vnic_config(struct fnic *fnic)
 
 	c->wq_copy_count = min_t(u16, FNIC_WQ_COPY_MAX, c->wq_copy_count);
 
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC MAC addr %pM "
-		     "wq/wq_copy/rq %d/%d/%d\n",
-		     fnic->ctlr.ctl_src_addr,
+	dev_info(&fnic->pdev->dev, "fNIC MAC addr %p wq/wq_copy/rq %d/%d/%d\n",
+			fnic->data_src_addr,
 		     c->wq_enet_desc_count, c->wq_copy_desc_count,
 		     c->rq_desc_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC node wwn %llx port wwn %llx\n",
+	dev_info(&fnic->pdev->dev, "fNIC node wwn 0x%llx port wwn 0x%llx\n",
 		     c->node_wwn, c->port_wwn);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC ed_tov %d ra_tov %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC ed_tov %d ra_tov %d\n",
 		     c->ed_tov, c->ra_tov);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC mtu %d intr timer %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC mtu %d intr timer %d\n",
 		     c->maxdatafieldsize, c->intr_timer);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC flags 0x%x luns per tgt %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC flags 0x%x luns per tgt %d\n",
 		     c->flags, c->luns_per_tgt);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC flogi_retries %d flogi timeout %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC flogi_retries %d flogi timeout %d\n",
 		     c->flogi_retries, c->flogi_timeout);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC plogi retries %d plogi timeout %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC plogi retries %d plogi timeout %d\n",
 		     c->plogi_retries, c->plogi_timeout);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC io throttle count %d link dn timeout %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC io throttle count %d link dn timeout %d\n",
 		     c->io_throttle_count, c->link_down_timeout);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		     "vNIC port dn io retries %d port dn timeout %d\n",
+	dev_info(&fnic->pdev->dev, "fNIC port dn io retries %d port dn timeout %d\n",
 		     c->port_down_io_retries, c->port_down_timeout);
-	shost_printk(KERN_INFO, fnic->lport->host,
-			"vNIC wq_copy_count: %d\n", c->wq_copy_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-			"vNIC intr mode: %d\n", c->intr_mode);
+	dev_info(&fnic->pdev->dev, "fNIC wq_copy_count: %d\n", c->wq_copy_count);
+	dev_info(&fnic->pdev->dev, "fNIC intr mode: %d\n", c->intr_mode);
 
 	return 0;
 }
@@ -206,18 +197,12 @@ void fnic_get_res_counts(struct fnic *fnic)
 	fnic->intr_count = vnic_dev_get_res_count(fnic->vdev,
 		RES_TYPE_INTR_CTRL);
 
-	shost_printk(KERN_INFO, fnic->lport->host,
-		"vNIC fw resources wq_count: %d\n", fnic->wq_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		"vNIC fw resources raw_wq_count: %d\n", fnic->raw_wq_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		"vNIC fw resources wq_copy_count: %d\n", fnic->wq_copy_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		"vNIC fw resources rq_count: %d\n", fnic->rq_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		"vNIC fw resources cq_count: %d\n", fnic->cq_count);
-	shost_printk(KERN_INFO, fnic->lport->host,
-		"vNIC fw resources intr_count: %d\n", fnic->intr_count);
+	dev_info(&fnic->pdev->dev, "vNIC fw resources wq_count: %d\n", fnic->wq_count);
+	dev_info(&fnic->pdev->dev, "vNIC fw resources raw_wq_count: %d\n", fnic->raw_wq_count);
+	dev_info(&fnic->pdev->dev, "vNIC fw resources wq_copy_count: %d\n", fnic->wq_copy_count);
+	dev_info(&fnic->pdev->dev, "vNIC fw resources rq_count: %d\n", fnic->rq_count);
+	dev_info(&fnic->pdev->dev, "vNIC fw resources cq_count: %d\n", fnic->cq_count);
+	dev_info(&fnic->pdev->dev, "vNIC fw resources intr_count: %d\n", fnic->intr_count);
 }
 
 void fnic_free_vnic_resources(struct fnic *fnic)
@@ -253,19 +238,17 @@ int fnic_alloc_vnic_resources(struct fnic *fnic)
 
 	intr_mode = vnic_dev_get_intr_mode(fnic->vdev);
 
-	shost_printk(KERN_INFO, fnic->lport->host, "vNIC interrupt mode: %s\n",
+	dev_info(&fnic->pdev->dev, "vNIC interrupt mode: %s\n",
 		     intr_mode == VNIC_DEV_INTR_MODE_INTX ? "legacy PCI INTx" :
 		     intr_mode == VNIC_DEV_INTR_MODE_MSI ? "MSI" :
 		     intr_mode == VNIC_DEV_INTR_MODE_MSIX ?
 		     "MSI-X" : "unknown");
 
-	shost_printk(KERN_INFO, fnic->lport->host,
-			"vNIC resources avail: wq %d cp_wq %d raw_wq %d rq %d",
+	dev_info(&fnic->pdev->dev, "res avail: wq %d cp_wq %d raw_wq %d rq %d",
 			fnic->wq_count, fnic->wq_copy_count,
 			fnic->raw_wq_count, fnic->rq_count);
 
-	shost_printk(KERN_INFO, fnic->lport->host,
-			"vNIC resources avail: cq %d intr %d cpy-wq desc count %d\n",
+	dev_info(&fnic->pdev->dev, "res avail: cq %d intr %d cpy-wq desc count %d\n",
 			fnic->cq_count, fnic->intr_count,
 			fnic->config.wq_copy_desc_count);
 
@@ -340,8 +323,7 @@ int fnic_alloc_vnic_resources(struct fnic *fnic)
 				RES_TYPE_INTR_PBA_LEGACY, 0);
 
 	if (!fnic->legacy_pba && intr_mode == VNIC_DEV_INTR_MODE_INTX) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "Failed to hook legacy pba resource\n");
+		dev_err(&fnic->pdev->dev, "Failed to hook legacy pba resource\n");
 		err = -ENODEV;
 		goto err_out_cleanup;
 	}
@@ -444,8 +426,7 @@ int fnic_alloc_vnic_resources(struct fnic *fnic)
 	/* init the stats memory by making the first call here */
 	err = vnic_dev_stats_dump(fnic->vdev, &fnic->stats);
 	if (err) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "vnic_dev_stats_dump failed - x%x\n", err);
+		dev_err(&fnic->pdev->dev, "vnic_dev_stats_dump failed - x%x\n", err);
 		goto err_out_cleanup;
 	}
 
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 2ba61dba4569..7133b254cbe4 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -23,11 +23,13 @@
 #include <scsi/scsi_tcq.h>
 #include <scsi/fc/fc_els.h>
 #include <scsi/fc/fc_fcoe.h>
-#include <scsi/libfc.h>
 #include <scsi/fc_frame.h>
+#include <scsi/scsi_transport_fc.h>
 #include "fnic_io.h"
 #include "fnic.h"
 
+static void fnic_cleanup_io(struct fnic *fnic, int exclude_id);
+
 const char *fnic_state_str[] = {
 	[FNIC_IN_FC_MODE] =           "FNIC_IN_FC_MODE",
 	[FNIC_IN_FC_TRANS_ETH_MODE] = "FNIC_IN_FC_TRANS_ETH_MODE",
@@ -65,6 +67,18 @@ static const char *fcpio_status_str[] =  {
 	[FCPIO_LUNMAP_CHNG_PEND] = "FCPIO_LUNHMAP_CHNG_PEND",
 };
 
+enum terminate_io_return {
+	TERM_SUCCESS = 0,
+	TERM_NO_SC = 1,
+	TERM_IO_REQ_NOT_FOUND,
+	TERM_ANOTHER_PORT,
+	TERM_GSTATE,
+	TERM_IO_BLOCKED,
+	TERM_OUT_OF_WQ_DESC,
+	TERM_TIMED_OUT,
+	TERM_MISC,
+};
+
 const char *fnic_state_to_str(unsigned int state)
 {
 	if (state >= ARRAY_SIZE(fnic_state_str) || !fnic_state_str[state])
@@ -90,8 +104,6 @@ static const char *fnic_fcpio_status_to_str(unsigned int status)
 	return fcpio_status_str[status];
 }
 
-static void fnic_cleanup_io(struct fnic *fnic);
-
 /*
  * Unmap the data buffer and sense buffer for an io_req,
  * also unmap and free the device-private scatter/gather list.
@@ -114,6 +126,65 @@ static void fnic_release_ioreq_buf(struct fnic *fnic,
 				 SCSI_SENSE_BUFFERSIZE, DMA_FROM_DEVICE);
 }
 
+static bool
+fnic_count_portid_ioreqs_iter(struct fnic *fnic, struct scsi_cmnd *sc,
+				void *data1, void *data2)
+{
+	u32 *portid = data1;
+	unsigned int *count = data2;
+	struct fnic_io_req *io_req = fnic_priv(sc)->io_req;
+
+	if (!io_req || (*portid && (io_req->port_id != *portid)))
+		return true;
+
+	*count += 1;
+	return true;
+}
+
+unsigned int fnic_count_ioreqs(struct fnic *fnic, u32 portid)
+{
+	unsigned int count = 0;
+
+	fnic_scsi_io_iter(fnic, fnic_count_portid_ioreqs_iter,
+				&portid, &count);
+
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		      "portid = 0x%x count = %u\n", portid, count);
+	return count;
+}
+
+unsigned int fnic_count_all_ioreqs(struct fnic *fnic)
+{
+	return fnic_count_ioreqs(fnic, 0);
+}
+
+static bool
+fnic_count_lun_ioreqs_iter(struct fnic *fnic, struct scsi_cmnd *sc,
+				void *data1, void *data2)
+{
+	struct scsi_device *scsi_device = data1;
+	unsigned int *count = data2;
+
+	if (sc->device != scsi_device || !fnic_priv(sc)->io_req)
+		return true;
+
+	*count += 1;
+	return true;
+}
+
+unsigned int
+fnic_count_lun_ioreqs(struct fnic *fnic, struct scsi_device *scsi_device)
+{
+	unsigned int count = 0;
+
+	fnic_scsi_io_iter(fnic, fnic_count_lun_ioreqs_iter,
+				scsi_device, &count);
+
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		      "lun = %p count = %u\n", scsi_device, count);
+	return count;
+}
+
 /* Free up Copy Wq descriptors. Called with copy_wq lock held */
 static int free_wq_copy_descs(struct fnic *fnic, struct vnic_wq_copy *wq, unsigned int hwq)
 {
@@ -179,12 +250,11 @@ int fnic_fw_reset_handler(struct fnic *fnic)
 	struct vnic_wq_copy *wq = &fnic->hw_copy_wq[0];
 	int ret = 0;
 	unsigned long flags;
+	unsigned int ioreq_count;
 
 	/* indicate fwreset to io path */
 	fnic_set_state_flags(fnic, FNIC_FLAGS_FWRESET);
-
-	skb_queue_purge(&fnic->frame_queue);
-	skb_queue_purge(&fnic->tx_queue);
+	ioreq_count = fnic_count_all_ioreqs(fnic);
 
 	/* wait for io cmpl */
 	while (atomic_read(&fnic->in_flight))
@@ -198,6 +268,8 @@ int fnic_fw_reset_handler(struct fnic *fnic)
 	if (!vnic_wq_copy_desc_avail(wq))
 		ret = -EAGAIN;
 	else {
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			  "ioreq_count: %u\n", ioreq_count);
 		fnic_queue_wq_copy_desc_fw_reset(wq, SCSI_NO_TAG);
 		atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs);
 		if (atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs) >
@@ -211,11 +283,11 @@ int fnic_fw_reset_handler(struct fnic *fnic)
 
 	if (!ret) {
 		atomic64_inc(&fnic->fnic_stats.reset_stats.fw_resets);
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 				"Issued fw reset\n");
 	} else {
 		fnic_clear_state_flags(fnic, FNIC_FLAGS_FWRESET);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"Failed to issue fw reset\n");
 	}
 
@@ -231,10 +303,10 @@ int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id)
 {
 	struct vnic_wq_copy *wq = &fnic->hw_copy_wq[0];
 	enum fcpio_flogi_reg_format_type format;
-	struct fc_lport *lp = fnic->lport;
 	u8 gw_mac[ETH_ALEN];
 	int ret = 0;
 	unsigned long flags;
+	struct fnic_iport_s *iport = &fnic->iport;
 
 	spin_lock_irqsave(&fnic->wq_copy_lock[0], flags);
 
@@ -246,28 +318,23 @@ int fnic_flogi_reg_handler(struct fnic *fnic, u32 fc_id)
 		goto flogi_reg_ioreq_end;
 	}
 
-	if (fnic->ctlr.map_dest) {
-		eth_broadcast_addr(gw_mac);
-		format = FCPIO_FLOGI_REG_DEF_DEST;
-	} else {
-		memcpy(gw_mac, fnic->ctlr.dest_addr, ETH_ALEN);
-		format = FCPIO_FLOGI_REG_GW_DEST;
-	}
+	memcpy(gw_mac, fnic->iport.fcfmac, ETH_ALEN);
+	format = FCPIO_FLOGI_REG_GW_DEST;
 
-	if ((fnic->config.flags & VFCF_FIP_CAPABLE) && !fnic->ctlr.map_dest) {
+	if (fnic->config.flags & VFCF_FIP_CAPABLE) {
 		fnic_queue_wq_copy_desc_fip_reg(wq, SCSI_NO_TAG,
 						fc_id, gw_mac,
-						fnic->data_src_addr,
-						lp->r_a_tov, lp->e_d_tov);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			      "FLOGI FIP reg issued fcid %x src %pM dest %pM\n",
-			      fc_id, fnic->data_src_addr, gw_mac);
+						fnic->iport.fpma,
+						iport->r_a_tov, iport->e_d_tov);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			      "FLOGI FIP reg issued fcid: 0x%x src %p dest %p\n",
+				  fc_id, fnic->iport.fpma, gw_mac);
 	} else {
 		fnic_queue_wq_copy_desc_flogi_reg(wq, SCSI_NO_TAG,
 						  format, fc_id, gw_mac);
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-			"FLOGI reg issued fcid 0x%x map %d dest 0x%p\n",
-			fc_id, fnic->ctlr.map_dest, gw_mac);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"FLOGI reg issued fcid 0x%x dest %p\n",
+			fc_id, gw_mac);
 	}
 
 	atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs);
@@ -295,13 +362,17 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 {
 	struct scatterlist *sg;
 	struct fc_rport *rport = starget_to_rport(scsi_target(sc->device));
-	struct fc_rport_libfc_priv *rp = rport->dd_data;
 	struct host_sg_desc *desc;
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	unsigned int i;
 	int flags;
 	u8 exch_flags;
 	struct scsi_lun fc_lun;
+	struct fnic_tport_s *tport;
+	struct rport_dd_data_s *rdd_data;
+
+	rdd_data = rport->dd_data;
+	tport = rdd_data->tport;
 
 	if (sg_count) {
 		/* For each SGE, create a device desc entry */
@@ -342,7 +413,7 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 		free_wq_copy_descs(fnic, wq, hwq);
 
 	if (unlikely(!vnic_wq_copy_desc_avail(wq))) {
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			  "fnic_queue_wq_copy_desc failure - no descriptors\n");
 		atomic64_inc(&misc_stats->io_cpwq_alloc_failures);
 		return SCSI_MLQUEUE_HOST_BUSY;
@@ -356,7 +427,7 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 
 	exch_flags = 0;
 	if ((fnic->config.flags & VFCF_FCP_SEQ_LVL_ERR) &&
-	    (rp->flags & FC_RP_FLAGS_RETRY))
+		(tport->tgt_flags & FDLS_FC_RP_FLAGS_RETRY))
 		exch_flags |= FCPIO_ICMND_SRFLAG_RETRY;
 
 	fnic_queue_wq_copy_desc_icmnd_16(wq, mqtag,
@@ -371,8 +442,8 @@ static inline int fnic_queue_wq_copy_desc(struct fnic *fnic,
 					 sc->cmnd, sc->cmd_len,
 					 scsi_bufflen(sc),
 					 fc_lun.scsi_lun, io_req->port_id,
-					 rport->maxframe_size, rp->r_a_tov,
-					 rp->e_d_tov);
+					 tport->max_payload_size,
+					 tport->r_a_tov, tport->e_d_tov);
 
 	atomic64_inc(&fnic->fnic_stats.fw_stats.active_fw_reqs);
 	if (atomic64_read(&fnic->fnic_stats.fw_stats.active_fw_reqs) >
@@ -388,10 +459,10 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 	struct request *const rq = scsi_cmd_to_rq(sc);
 	uint32_t mqtag = 0;
 	void (*done)(struct scsi_cmnd *) = scsi_done;
-	struct fc_lport *lp = shost_priv(sc->device->host);
 	struct fc_rport *rport;
 	struct fnic_io_req *io_req = NULL;
-	struct fnic *fnic = lport_priv(lp);
+	struct fnic *fnic = *((struct fnic **) shost_priv(sc->device->host));
+	struct fnic_iport_s *iport = NULL;
 	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
 	struct vnic_wq_copy *wq;
 	int ret = 1;
@@ -400,32 +471,14 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 	unsigned long flags = 0;
 	unsigned long ptr;
 	int io_lock_acquired = 0;
-	struct fc_rport_libfc_priv *rp;
 	uint16_t hwq = 0;
-
-	mqtag = blk_mq_unique_tag(rq);
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-
-	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
-			"fnic IO blocked flags: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n",
-			fnic->state_flags);
-		return SCSI_MLQUEUE_HOST_BUSY;
-	}
-
-	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET))) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
-			"fnic flags: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n",
-			fnic->state_flags);
-		return SCSI_MLQUEUE_HOST_BUSY;
-	}
+	struct fnic_tport_s *tport = NULL;
+	struct rport_dd_data_s *rdd_data;
+	uint16_t lun0_delay = 0;
 
 	rport = starget_to_rport(scsi_target(sc->device));
 	if (!rport) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"returning DID_NO_CONNECT for IO as rport is NULL\n");
 		sc->result = DID_NO_CONNECT << 16;
 		done(sc);
@@ -434,50 +487,96 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 
 	ret = fc_remote_port_chkready(rport);
 	if (ret) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"rport is not ready\n");
-		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
+		atomic64_inc(&fnic_stats->misc_stats.tport_not_ready);
 		sc->result = ret;
 		done(sc);
 		return 0;
 	}
 
-	rp = rport->dd_data;
-	if (!rp || rp->rp_state == RPORT_ST_DELETE) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			"rport 0x%x removed, returning DID_NO_CONNECT\n",
-			rport->port_id);
+	mqtag = blk_mq_unique_tag(rq);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	iport = &fnic->iport;
 
-		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
-		sc->result = DID_NO_CONNECT<<16;
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "returning DID_NO_CONNECT for IO as iport state: %d\n",
+					  iport->state);
+		sc->result = DID_NO_CONNECT << 16;
 		done(sc);
 		return 0;
 	}
 
-	if (rp->rp_state != RPORT_ST_READY) {
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			"rport 0x%x in state 0x%x, returning DID_IMM_RETRY\n",
-			rport->port_id, rp->rp_state);
+	/* fc_remote_port_add() may have added the tport to
+	 * fc_transport but dd_data not yet set
+	 */
+	rdd_data = rport->dd_data;
+	tport = rdd_data->tport;
+	if (!tport || (rdd_data->iport != iport)) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "dd_data not yet set in SCSI for rport portid: 0x%x\n",
+					  rport->port_id);
+		tport = fnic_find_tport_by_fcid(iport, rport->port_id);
+		if (!tport) {
+			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+			FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+						  "returning DID_BUS_BUSY for IO as tport not found for: 0x%x\n",
+						  rport->port_id);
+			sc->result = DID_BUS_BUSY << 16;
+			done(sc);
+			return 0;
+		}
+
+		/* Re-assign same params as in fnic_fdls_add_tport */
+		rport->maxframe_size = FNIC_FC_MAX_PAYLOAD_LEN;
+		rport->supported_classes =
+			FC_COS_CLASS3 | FC_RPORT_ROLE_FCP_TARGET;
+		/* the dd_data is allocated by fctransport of size dd_fcrport_size */
+		rdd_data = rport->dd_data;
+		rdd_data->tport = tport;
+		rdd_data->iport = iport;
+		tport->rport = rport;
+		tport->flags |= FNIC_FDLS_SCSI_REGISTERED;
+	}
 
-		sc->result = DID_IMM_RETRY << 16;
+	if ((tport->state != FDLS_TGT_STATE_READY)
+		&& (tport->state != FDLS_TGT_STATE_ADISC)) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "returning DID_NO_CONNECT for IO as tport state: %d\n",
+					  tport->state);
+		sc->result = DID_NO_CONNECT << 16;
 		done(sc);
 		return 0;
 	}
 
-	if (lp->state != LPORT_ST_READY || !(lp->link_up)) {
+	atomic_inc(&fnic->in_flight);
+	atomic_inc(&tport->in_flight);
+
+	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) {
+		atomic_dec(&fnic->in_flight);
+		atomic_dec(&tport->in_flight);
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
-			"state not ready: %d/link not up: %d Returning HOST_BUSY\n",
-			lp->state, lp->link_up);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
-	atomic_inc(&fnic->in_flight);
+	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_FWRESET))) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		  "fnic flags FW reset: 0x%lx. Returning SCSI_MLQUEUE_HOST_BUSY\n",
+		  fnic->state_flags);
+		return SCSI_MLQUEUE_HOST_BUSY;
+	}
+
+	if (!tport->lun0_delay) {
+		lun0_delay = 1;
+		tport->lun0_delay++;
+	}
 
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
 	fnic_priv(sc)->state = FNIC_IOREQ_NOT_INITED;
 	fnic_priv(sc)->flags = FNIC_NO_FLAGS;
 
@@ -499,6 +598,7 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 		goto out;
 	}
 
+	io_req->tport = tport;
 	/* Determine the type of scatter/gather list we need */
 	io_req->sgl_cnt = sg_count;
 	io_req->sgl_type = FNIC_SGL_CACHE_DFLT;
@@ -575,6 +675,7 @@ int fnic_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc)
 			mempool_free(io_req, fnic->io_req_pool);
 		}
 		atomic_dec(&fnic->in_flight);
+		atomic_dec(&tport->in_flight);
 		return ret;
 	} else {
 		atomic64_inc(&fnic_stats->io_stats.active_ios);
@@ -602,6 +703,14 @@ out:
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	atomic_dec(&fnic->in_flight);
+	atomic_dec(&tport->in_flight);
+
+	if (lun0_delay) {
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					  "LUN0 delay\n");
+		mdelay(LUN0_DELAY_TIME);
+	}
+
 	return ret;
 }
 
@@ -625,7 +734,7 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 	atomic64_inc(&reset_stats->fw_reset_completions);
 
 	/* Clean up all outstanding io requests */
-	fnic_cleanup_io(fnic);
+	fnic_cleanup_io(fnic, SCSI_NO_TAG);
 
 	atomic64_set(&fnic->fnic_stats.fw_stats.active_fw_reqs, 0);
 	atomic64_set(&fnic->fnic_stats.io_stats.active_ios, 0);
@@ -637,44 +746,37 @@ static int fnic_fcpio_fw_reset_cmpl_handler(struct fnic *fnic,
 	if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) {
 		/* Check status of reset completion */
 		if (!hdr_status) {
-			FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 					"reset cmpl success\n");
 			/* Ready to send flogi out */
 			fnic->state = FNIC_IN_ETH_MODE;
 		} else {
-			FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+			FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"reset failed with header status: %s\n",
 				fnic_fcpio_status_to_str(hdr_status));
 
-			/*
-			 * Unable to change to eth mode, cannot send out flogi
-			 * Change state to fc mode, so that subsequent Flogi
-			 * requests from libFC will cause more attempts to
-			 * reset the firmware. Free the cached flogi
-			 */
 			fnic->state = FNIC_IN_FC_MODE;
 			atomic64_inc(&reset_stats->fw_reset_failures);
 			ret = -1;
 		}
 	} else {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"Unexpected state while processing reset completion: %s\n",
 			fnic_state_to_str(fnic->state));
 		atomic64_inc(&reset_stats->fw_reset_failures);
 		ret = -1;
 	}
 
-	/* Thread removing device blocks till firmware reset is complete */
-	if (fnic->remove_wait)
-		complete(fnic->remove_wait);
+	if (fnic->fw_reset_done)
+		complete(fnic->fw_reset_done);
 
 	/*
 	 * If fnic is being removed, or fw reset failed
 	 * free the flogi frame. Else, send it out
 	 */
-	if (fnic->remove_wait || ret) {
+	if (ret) {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		skb_queue_purge(&fnic->tx_queue);
+		fnic_free_txq(&fnic->tx_queue);
 		goto reset_cmpl_handler_end;
 	}
 
@@ -710,19 +812,19 @@ static int fnic_fcpio_flogi_reg_cmpl_handler(struct fnic *fnic,
 
 		/* Check flogi registration completion status */
 		if (!hdr_status) {
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-				      "flog reg succeeded\n");
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+				      "FLOGI reg succeeded\n");
 			fnic->state = FNIC_IN_FC_MODE;
 		} else {
 			FNIC_SCSI_DBG(KERN_DEBUG,
-				      fnic->lport->host, fnic->fnic_num,
-				      "fnic flogi reg :failed %s\n",
+				      fnic->host, fnic->fnic_num,
+				      "fnic flogi reg failed: %s\n",
 				      fnic_fcpio_status_to_str(hdr_status));
 			fnic->state = FNIC_IN_ETH_MODE;
 			ret = -1;
 		}
 	} else {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			      "Unexpected fnic state %s while"
 			      " processing flogi reg completion\n",
 			      fnic_state_to_str(fnic->state));
@@ -795,7 +897,7 @@ static inline void fnic_fcpio_ack_handler(struct fnic *fnic,
 
 	spin_unlock_irqrestore(&fnic->wq_copy_lock[wq_index], flags);
 	FNIC_TRACE(fnic_fcpio_ack_handler,
-		  fnic->lport->host->host_no, 0, 0, ox_id_tag[2], ox_id_tag[3],
+		  fnic->host->host_no, 0, 0, ox_id_tag[2], ox_id_tag[3],
 		  ox_id_tag[4], ox_id_tag[5]);
 }
 
@@ -833,36 +935,36 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 	hwq = blk_mq_unique_tag_to_hwq(mqtag);
 
 	if (hwq != cq_index) {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
 			hwq, mqtag, tag, cq_index);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hdr status: %s icmnd completion on the wrong queue\n",
 			fnic_fcpio_status_to_str(hdr_status));
 	}
 
 	if (tag >= fnic->fnic_max_tag_id) {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
 			hwq, mqtag, tag, cq_index);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hdr status: %s Out of range tag\n",
 			fnic_fcpio_status_to_str(hdr_status));
 		return;
 	}
 	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 
-	sc = scsi_host_find_tag(fnic->lport->host, id);
+	sc = scsi_host_find_tag(fnic->host, id);
 	WARN_ON_ONCE(!sc);
 	if (!sc) {
 		atomic64_inc(&fnic_stats->io_stats.sc_null);
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-		shost_printk(KERN_ERR, fnic->lport->host,
+		shost_printk(KERN_ERR, fnic->host,
 			  "icmnd_cmpl sc is null - "
 			  "hdr status = %s tag = 0x%x desc = 0x%p\n",
 			  fnic_fcpio_status_to_str(hdr_status), id, desc);
 		FNIC_TRACE(fnic_fcpio_icmnd_cmpl_handler,
-			  fnic->lport->host->host_no, id,
+			  fnic->host->host_no, id,
 			  ((u64)icmnd_cmpl->_resvd0[1] << 16 |
 			  (u64)icmnd_cmpl->_resvd0[0]),
 			  ((u64)hdr_status << 16 |
@@ -885,7 +987,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 		atomic64_inc(&fnic_stats->io_stats.ioreq_null);
 		fnic_priv(sc)->flags |= FNIC_IO_REQ_NULL;
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-		shost_printk(KERN_ERR, fnic->lport->host,
+		shost_printk(KERN_ERR, fnic->host,
 			  "icmnd_cmpl io_req is null - "
 			  "hdr status = %s tag = 0x%x sc 0x%p\n",
 			  fnic_fcpio_status_to_str(hdr_status), id, sc);
@@ -912,7 +1014,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 		if(FCPIO_ABORTED == hdr_status)
 			fnic_priv(sc)->flags |= FNIC_IO_ABORTED;
 
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			"icmnd_cmpl abts pending "
 			  "hdr status = %s tag = 0x%x sc = 0x%p "
 			  "scsi_status = %x residual = %d\n",
@@ -943,6 +1045,9 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 
 		if (icmnd_cmpl->scsi_status == SAM_STAT_TASK_SET_FULL)
 			atomic64_inc(&fnic_stats->misc_stats.queue_fulls);
+
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				"xfer_len: %llu", xfer_len);
 		break;
 
 	case FCPIO_TIMEOUT:          /* request was timed out */
@@ -1004,7 +1109,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 
 	if (hdr_status != FCPIO_SUCCESS) {
 		atomic64_inc(&fnic_stats->io_stats.io_failures);
-		shost_printk(KERN_ERR, fnic->lport->host, "hdr status = %s\n",
+		shost_printk(KERN_ERR, fnic->host, "hdr status = %s\n",
 			     fnic_fcpio_status_to_str(hdr_status));
 	}
 
@@ -1024,13 +1129,13 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 		  desc, cmd_trace, fnic_flags_and_state(sc));
 
 	if (sc->sc_data_direction == DMA_FROM_DEVICE) {
-		fnic->lport->host_stats.fcp_input_requests++;
+		fnic_stats->host_stats.fcp_input_requests++;
 		fnic->fcp_input_bytes += xfer_len;
 	} else if (sc->sc_data_direction == DMA_TO_DEVICE) {
-		fnic->lport->host_stats.fcp_output_requests++;
+		fnic_stats->host_stats.fcp_output_requests++;
 		fnic->fcp_output_bytes += xfer_len;
 	} else
-		fnic->lport->host_stats.fcp_control_requests++;
+		fnic_stats->host_stats.fcp_control_requests++;
 
 	/* Call SCSI completion function to complete the IO */
 	scsi_done(sc);
@@ -1097,27 +1202,27 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 	hwq = blk_mq_unique_tag_to_hwq(id & FNIC_TAG_MASK);
 
 	if (hwq != cq_index) {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
 			hwq, mqtag, tag, cq_index);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hdr status: %s ITMF completion on the wrong queue\n",
 			fnic_fcpio_status_to_str(hdr_status));
 	}
 
 	if (tag > fnic->fnic_max_tag_id) {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
 			hwq, mqtag, tag, cq_index);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hdr status: %s Tag out of range\n",
 			fnic_fcpio_status_to_str(hdr_status));
 		return;
 	}  else if ((tag == fnic->fnic_max_tag_id) && !(id & FNIC_TAG_DEV_RST)) {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x cq index: %d ",
 			hwq, mqtag, tag, cq_index);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hdr status: %s Tag out of range\n",
 			fnic_fcpio_status_to_str(hdr_status));
 		return;
@@ -1133,14 +1238,14 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		if (io_req)
 			sc = io_req->sc;
 	} else {
-		sc = scsi_host_find_tag(fnic->lport->host, id & FNIC_TAG_MASK);
+		sc = scsi_host_find_tag(fnic->host, id & FNIC_TAG_MASK);
 	}
 
 	WARN_ON_ONCE(!sc);
 	if (!sc) {
 		atomic64_inc(&fnic_stats->io_stats.sc_null);
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-		shost_printk(KERN_ERR, fnic->lport->host,
+		shost_printk(KERN_ERR, fnic->host,
 			  "itmf_cmpl sc is null - hdr status = %s tag = 0x%x\n",
 			  fnic_fcpio_status_to_str(hdr_status), tag);
 		return;
@@ -1152,7 +1257,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		atomic64_inc(&fnic_stats->io_stats.ioreq_null);
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		fnic_priv(sc)->flags |= FNIC_IO_ABT_TERM_REQ_NULL;
-		shost_printk(KERN_ERR, fnic->lport->host,
+		shost_printk(KERN_ERR, fnic->host,
 			  "itmf_cmpl io_req is null - "
 			  "hdr status = %s tag = 0x%x sc 0x%p\n",
 			  fnic_fcpio_status_to_str(hdr_status), tag, sc);
@@ -1163,7 +1268,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 	if ((id & FNIC_TAG_ABORT) && (id & FNIC_TAG_DEV_RST)) {
 		/* Abort and terminate completion of device reset req */
 		/* REVISIT : Add asserts about various flags */
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Abt/term completion received\n",
 			hwq, mqtag, tag,
 			fnic_fcpio_status_to_str(hdr_status));
@@ -1175,7 +1280,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	} else if (id & FNIC_TAG_ABORT) {
 		/* Completion of abort cmd */
-		shost_printk(KERN_DEBUG, fnic->lport->host,
+		shost_printk(KERN_DEBUG, fnic->host,
 			"hwq: %d mqtag: 0x%x tag: 0x%x Abort header status: %s\n",
 			hwq, mqtag, tag,
 			fnic_fcpio_status_to_str(hdr_status));
@@ -1190,7 +1295,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 					&term_stats->terminate_fw_timeouts);
 			break;
 		case FCPIO_ITMF_REJECTED:
-			FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+			FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 				"abort reject recd. id %d\n",
 				(int)(id & FNIC_TAG_MASK));
 			break;
@@ -1225,7 +1330,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		if (!(fnic_priv(sc)->flags & (FNIC_IO_ABORTED | FNIC_IO_DONE)))
 			atomic64_inc(&misc_stats->no_icmnd_itmf_cmpls);
 
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			      "abts cmpl recd. id %d status %s\n",
 			      (int)(id & FNIC_TAG_MASK),
 			      fnic_fcpio_status_to_str(hdr_status));
@@ -1238,11 +1343,11 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		if (io_req->abts_done) {
 			complete(io_req->abts_done);
 			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-			shost_printk(KERN_INFO, fnic->lport->host,
+			shost_printk(KERN_INFO, fnic->host,
 					"hwq: %d mqtag: 0x%x tag: 0x%x Waking up abort thread\n",
 					hwq, mqtag, tag);
 		} else {
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 				"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Completing IO\n",
 				hwq, mqtag,
 				tag, fnic_fcpio_status_to_str(hdr_status));
@@ -1273,7 +1378,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		}
 	} else if (id & FNIC_TAG_DEV_RST) {
 		/* Completion of device reset */
-		shost_printk(KERN_INFO, fnic->lport->host,
+		shost_printk(KERN_INFO, fnic->host,
 			"hwq: %d mqtag: 0x%x tag: 0x%x DR hst: %s\n",
 			hwq, mqtag,
 			tag, fnic_fcpio_status_to_str(hdr_status));
@@ -1285,7 +1390,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 				  sc->device->host->host_no, id, sc,
 				  jiffies_to_msecs(jiffies - start_time),
 				  desc, 0, fnic_flags_and_state(sc));
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 				"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s Terminate pending\n",
 				hwq, mqtag,
 				tag, fnic_fcpio_status_to_str(hdr_status));
@@ -1298,7 +1403,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 				  sc->device->host->host_no, id, sc,
 				  jiffies_to_msecs(jiffies - start_time),
 				  desc, 0, fnic_flags_and_state(sc));
-			FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+			FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 				"dev reset cmpl recd after time out. "
 				"id %d status %s\n",
 				(int)(id & FNIC_TAG_MASK),
@@ -1307,7 +1412,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		}
 		fnic_priv(sc)->state = FNIC_IOREQ_CMD_COMPLETE;
 		fnic_priv(sc)->flags |= FNIC_DEV_RST_DONE;
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x hst: %s DR completion received\n",
 			hwq, mqtag,
 			tag, fnic_fcpio_status_to_str(hdr_status));
@@ -1316,7 +1421,7 @@ static void fnic_fcpio_itmf_cmpl_handler(struct fnic *fnic, unsigned int cq_inde
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	} else {
-		shost_printk(KERN_ERR, fnic->lport->host,
+		shost_printk(KERN_ERR, fnic->host,
 			"%s: Unexpected itmf io state: hwq: %d tag 0x%x %s\n",
 			__func__, hwq, id, fnic_ioreq_state_to_str(fnic_priv(sc)->state));
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
@@ -1371,7 +1476,7 @@ static int fnic_fcpio_cmpl_handler(struct vnic_dev *vdev,
 		break;
 
 	default:
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			      "firmware completion type %d\n",
 			      desc->hdr.type);
 		break;
@@ -1414,8 +1519,8 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 	struct request *const rq = scsi_cmd_to_rq(sc);
 	struct fnic *fnic = data;
 	struct fnic_io_req *io_req;
-	unsigned long flags = 0;
 	unsigned long start_time = 0;
+	unsigned long flags;
 	struct fnic_stats *fnic_stats = &fnic->fnic_stats;
 	uint16_t hwq = 0;
 	int tag;
@@ -1432,14 +1537,14 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d mqtag: 0x%x tag: 0x%x flags: 0x%x No ioreq. Returning\n",
 			hwq, mqtag, tag, fnic_priv(sc)->flags);
 		return true;
 	}
 
 	if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) &&
-	    !(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) {
+		!(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) {
 		/*
 		 * We will be here only when FW completes reset
 		 * without sending completions for outstanding ios.
@@ -1449,6 +1554,7 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 			complete(io_req->dr_done);
 		else if (io_req && io_req->abts_done)
 			complete(io_req->abts_done);
+
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	} else if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) {
@@ -1458,19 +1564,19 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 
 	fnic_priv(sc)->io_req = NULL;
 	io_req->sc = NULL;
+	start_time = io_req->start_time;
 	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
 	/*
 	 * If there is a scsi_cmnd associated with this io_req, then
 	 * free the corresponding state
 	 */
-	start_time = io_req->start_time;
 	fnic_release_ioreq_buf(fnic, io_req, sc);
 	mempool_free(io_req, fnic->io_req_pool);
 
 	sc->result = DID_TRANSPORT_DISRUPTED << 16;
-	FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
-		"mqtag:0x%x tag: 0x%x sc:0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n",
+	FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+	"mqtag: 0x%x tag: 0x%x sc: 0x%p duration = %lu DID_TRANSPORT_DISRUPTED\n",
 		mqtag, tag, sc, (jiffies - start_time));
 
 	if (atomic64_read(&fnic->io_cmpl_skip))
@@ -1479,23 +1585,60 @@ static bool fnic_cleanup_io_iter(struct scsi_cmnd *sc, void *data)
 		atomic64_inc(&fnic_stats->io_stats.io_completions);
 
 	FNIC_TRACE(fnic_cleanup_io,
-		   sc->device->host->host_no, tag, sc,
-		   jiffies_to_msecs(jiffies - start_time),
-		   0, ((u64)sc->cmnd[0] << 32 |
-		       (u64)sc->cmnd[2] << 24 |
-		       (u64)sc->cmnd[3] << 16 |
-		       (u64)sc->cmnd[4] << 8 | sc->cmnd[5]),
-		   fnic_flags_and_state(sc));
-
+			   sc->device->host->host_no, tag, sc,
+			   jiffies_to_msecs(jiffies - start_time),
+			   0, ((u64) sc->cmnd[0] << 32 |
+				   (u64) sc->cmnd[2] << 24 |
+				   (u64) sc->cmnd[3] << 16 |
+				   (u64) sc->cmnd[4] << 8 | sc->cmnd[5]),
+			   (((u64) fnic_priv(sc)->flags << 32) | fnic_priv(sc)->
+				state));
+
+	/* Complete the command to SCSI */
 	scsi_done(sc);
-
 	return true;
 }
 
-static void fnic_cleanup_io(struct fnic *fnic)
+static void fnic_cleanup_io(struct fnic *fnic, int exclude_id)
 {
-	scsi_host_busy_iter(fnic->lport->host,
-			    fnic_cleanup_io_iter, fnic);
+	unsigned int io_count = 0;
+	unsigned long flags;
+	struct fnic_io_req *io_req = NULL;
+	struct scsi_cmnd *sc = NULL;
+
+	io_count = fnic_count_all_ioreqs(fnic);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+				  "Outstanding ioreq count: %d active io count: %lld Waiting\n",
+				  io_count,
+				  atomic64_read(&fnic->fnic_stats.io_stats.active_ios));
+
+	scsi_host_busy_iter(fnic->host,
+						fnic_cleanup_io_iter, fnic);
+
+	/* with sg3utils device reset, SC needs to be retrieved from ioreq */
+	spin_lock_irqsave(&fnic->wq_copy_lock[0], flags);
+	io_req = fnic->sw_copy_wq[0].io_req_table[fnic->fnic_max_tag_id];
+	if (io_req) {
+		sc = io_req->sc;
+		if (sc) {
+			if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET)
+				&& !(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) {
+				fnic_priv(sc)->flags |= FNIC_DEV_RST_DONE;
+				if (io_req && io_req->dr_done)
+					complete(io_req->dr_done);
+			}
+		}
+	}
+	spin_unlock_irqrestore(&fnic->wq_copy_lock[0], flags);
+
+	while ((io_count = fnic_count_all_ioreqs(fnic))) {
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		  "Outstanding ioreq count: %d active io count: %lld Waiting\n",
+		  io_count,
+		  atomic64_read(&fnic->fnic_stats.io_stats.active_ios));
+
+		schedule_timeout(msecs_to_jiffies(100));
+	}
 }
 
 void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
@@ -1516,7 +1659,7 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 	if (id >= fnic->fnic_max_tag_id)
 		return;
 
-	sc = scsi_host_find_tag(fnic->lport->host, id);
+	sc = scsi_host_find_tag(fnic->host, id);
 	if (!sc)
 		return;
 
@@ -1545,7 +1688,7 @@ void fnic_wq_copy_cleanup_handler(struct vnic_wq_copy *wq,
 
 wq_copy_cleanup_scsi_cmd:
 	sc->result = DID_NO_CONNECT << 16;
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, "wq_copy_cleanup_handler:"
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "wq_copy_cleanup_handler:"
 		      " DID_NO_CONNECT\n");
 
 	FNIC_TRACE(fnic_wq_copy_cleanup_handler,
@@ -1567,10 +1710,13 @@ static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag,
 	struct vnic_wq_copy *wq = &fnic->hw_copy_wq[hwq];
 	struct misc_stats *misc_stats = &fnic->fnic_stats.misc_stats;
 	unsigned long flags;
+	struct fnic_tport_s *tport = io_req->tport;
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
 	if (unlikely(fnic_chk_state_flags_locked(fnic,
 						FNIC_FLAGS_IO_BLOCKED))) {
+		atomic_dec(&fnic->in_flight);
+		atomic_dec(&tport->in_flight);
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		return 1;
 	} else
@@ -1585,7 +1731,8 @@ static inline int fnic_queue_abort_io_req(struct fnic *fnic, int tag,
 	if (!vnic_wq_copy_desc_avail(wq)) {
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		atomic_dec(&fnic->in_flight);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		atomic_dec(&tport->in_flight);
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			"fnic_queue_abort_io_req: failure: no descriptors\n");
 		atomic64_inc(&misc_stats->abts_cpwq_alloc_failures);
 		return 1;
@@ -1619,20 +1766,24 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 	struct fnic *fnic = iter_data->fnic;
 	int abt_tag = 0;
 	struct fnic_io_req *io_req;
-	unsigned long flags;
 	struct reset_stats *reset_stats = &fnic->fnic_stats.reset_stats;
 	struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats;
 	struct scsi_lun fc_lun;
 	enum fnic_ioreq_state old_ioreq_state;
 	uint16_t hwq = 0;
+	unsigned long flags;
 
 	abt_tag = blk_mq_unique_tag(rq);
 	hwq = blk_mq_unique_tag_to_hwq(abt_tag);
 
-	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
+	if (!sc) {
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+					  "sc is NULL abt_tag: 0x%x hwq: %d\n", abt_tag, hwq);
+		return true;
+	}
 
+	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
-
 	if (!io_req || io_req->port_id != iter_data->port_id) {
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
@@ -1640,7 +1791,7 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 
 	if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) &&
 	    !(fnic_priv(sc)->flags & FNIC_DEV_RST_ISSUED)) {
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d abt_tag: 0x%x flags: 0x%x Device reset is not pending\n",
 			hwq, abt_tag, fnic_priv(sc)->flags);
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
@@ -1655,37 +1806,40 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
+
 	if (io_req->abts_done) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			"fnic_rport_exch_reset: io_req->abts_done is set "
-			"state is %s\n",
+		shost_printk(KERN_ERR, fnic->host,
+			"fnic_rport_exch_reset: io_req->abts_done is set state is %s\n",
 			fnic_ioreq_state_to_str(fnic_priv(sc)->state));
 	}
 
 	if (!(fnic_priv(sc)->flags & FNIC_IO_ISSUED)) {
-		shost_printk(KERN_ERR, fnic->lport->host,
-			     "rport_exch_reset "
-			     "IO not yet issued %p tag 0x%x flags "
-			     "%x state %d\n",
-			     sc, abt_tag, fnic_priv(sc)->flags, fnic_priv(sc)->state);
+		shost_printk(KERN_ERR, fnic->host,
+			"rport_exch_reset IO not yet issued %p abt_tag 0x%x",
+			sc, abt_tag);
+		shost_printk(KERN_ERR, fnic->host,
+			"flags %x state %d\n", fnic_priv(sc)->flags,
+			fnic_priv(sc)->state);
 	}
 	old_ioreq_state = fnic_priv(sc)->state;
 	fnic_priv(sc)->state = FNIC_IOREQ_ABTS_PENDING;
 	fnic_priv(sc)->abts_status = FCPIO_INVALID_CODE;
+
 	if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) {
 		atomic64_inc(&reset_stats->device_reset_terminates);
 		abt_tag |= FNIC_TAG_DEV_RST;
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+					  "dev reset sc 0x%p\n", sc);
 	}
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-		      "fnic_rport_exch_reset dev rst sc 0x%p\n", sc);
-	BUG_ON(io_req->abts_done);
-
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		      "fnic_rport_exch_reset: dev rst sc 0x%p\n", sc);
+	WARN_ON_ONCE(io_req->abts_done);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 		      "fnic_rport_reset_exch: Issuing abts\n");
 
 	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
-	/* Now queue the abort command to firmware */
+	/* Queue the abort command to firmware */
 	int_to_scsilun(sc->device->lun, &fc_lun);
 
 	if (fnic_queue_abort_io_req(fnic, abt_tag,
@@ -1698,7 +1852,7 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 		 * lun reset
 		 */
 		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d abt_tag: 0x%x flags: 0x%x Queuing abort failed\n",
 			hwq, abt_tag, fnic_priv(sc)->flags);
 		if (fnic_priv(sc)->state == FNIC_IOREQ_ABTS_PENDING)
@@ -1714,11 +1868,14 @@ static bool fnic_rport_abort_io_iter(struct scsi_cmnd *sc, void *data)
 		atomic64_inc(&term_stats->terminates);
 		iter_data->term_cnt++;
 	}
+
 	return true;
 }
 
-static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id)
+void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id)
 {
+	unsigned int io_count = 0;
+	unsigned long flags;
 	struct terminate_stats *term_stats = &fnic->fnic_stats.term_stats;
 	struct fnic_rport_abort_io_iter_data iter_data = {
 		.fnic = fnic,
@@ -1726,53 +1883,115 @@ static void fnic_rport_exch_reset(struct fnic *fnic, u32 port_id)
 		.term_cnt = 0,
 	};
 
-	FNIC_SCSI_DBG(KERN_DEBUG,
-		      fnic->lport->host, fnic->fnic_num,
-		      "fnic_rport_exch_reset called portid 0x%06x\n",
-		      port_id);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+				  "fnic rport exchange reset for tport: 0x%06x\n",
+				  port_id);
 
 	if (fnic->in_remove)
 		return;
 
-	scsi_host_busy_iter(fnic->lport->host, fnic_rport_abort_io_iter,
+	io_count = fnic_count_ioreqs(fnic, port_id);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+				  "Starting terminates: rport:0x%x  portid-io-count: %d active-io-count: %lld\n",
+				  port_id, io_count,
+				  atomic64_read(&fnic->fnic_stats.io_stats.active_ios));
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	/* Bump in_flight counter to hold off fnic_fw_reset_handler. */
+	atomic_inc(&fnic->in_flight);
+	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED))) {
+		atomic_dec(&fnic->in_flight);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		return;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
+	scsi_host_busy_iter(fnic->host, fnic_rport_abort_io_iter,
 			    &iter_data);
+
 	if (iter_data.term_cnt > atomic64_read(&term_stats->max_terminates))
 		atomic64_set(&term_stats->max_terminates, iter_data.term_cnt);
 
+	atomic_dec(&fnic->in_flight);
+
+	while ((io_count = fnic_count_ioreqs(fnic, port_id)))
+		schedule_timeout(msecs_to_jiffies(1000));
+
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+				  "rport: 0x%x remaining portid-io-count: %d ",
+				  port_id, io_count);
 }
 
 void fnic_terminate_rport_io(struct fc_rport *rport)
 {
-	struct fc_rport_libfc_priv *rdata;
-	struct fc_lport *lport;
-	struct fnic *fnic;
+	struct fnic_tport_s *tport;
+	struct rport_dd_data_s *rdd_data;
+	struct fnic_iport_s *iport = NULL;
+	struct fnic *fnic = NULL;
 
 	if (!rport) {
-		printk(KERN_ERR "fnic_terminate_rport_io: rport is NULL\n");
+		pr_err("rport is NULL\n");
 		return;
 	}
-	rdata = rport->dd_data;
 
-	if (!rdata) {
-		printk(KERN_ERR "fnic_terminate_rport_io: rdata is NULL\n");
-		return;
+	rdd_data = rport->dd_data;
+	if (rdd_data) {
+		tport = rdd_data->tport;
+		if (!tport) {
+			pr_err(
+			"term rport io called after tport is deleted. Returning 0x%8x\n",
+		   rport->port_id);
+		} else {
+			pr_err(
+			   "term rport io called after tport is set 0x%8x\n",
+			   rport->port_id);
+			pr_err(
+			   "tport maybe rediscovered\n");
+
+			iport = (struct fnic_iport_s *) tport->iport;
+			fnic = iport->fnic;
+			fnic_rport_exch_reset(fnic, rport->port_id);
+		}
 	}
-	lport = rdata->local_port;
+}
 
-	if (!lport) {
-		printk(KERN_ERR "fnic_terminate_rport_io: lport is NULL\n");
-		return;
-	}
-	fnic = lport_priv(lport);
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-		      "wwpn 0x%llx, wwnn0x%llx, rport 0x%p, portid 0x%06x\n",
-		      rport->port_name, rport->node_name, rport,
-		      rport->port_id);
+/*
+ * FCP-SCSI specific handling for module unload
+ *
+ */
+void fnic_scsi_unload(struct fnic *fnic)
+{
+	unsigned long flags;
 
-	if (fnic->in_remove)
-		return;
+	/*
+	 * Mark state so that the workqueue thread stops forwarding
+	 * received frames and link events to the local port. ISR and
+	 * other threads that can queue work items will also stop
+	 * creating work items on the fnic workqueue
+	 */
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	fnic->iport.state = FNIC_IPORT_STATE_LINK_WAIT;
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
+	if (fdls_get_state(&fnic->iport.fabric) != FDLS_STATE_INIT)
+		fnic_scsi_fcpio_reset(fnic);
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	fnic->in_remove = 1;
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
+	fnic_flush_tport_event_list(fnic);
+	fnic_delete_fcp_tports(fnic);
+}
 
-	fnic_rport_exch_reset(fnic, rport->port_id);
+void fnic_scsi_unload_cleanup(struct fnic *fnic)
+{
+	int hwq = 0;
+
+	fc_remove_host(fnic->host);
+	scsi_remove_host(fnic->host);
+	for (hwq = 0; hwq < fnic->wq_copy_count; hwq++)
+		kfree(fnic->sw_copy_wq[hwq].io_req_table);
 }
 
 /*
@@ -1783,10 +2002,12 @@ void fnic_terminate_rport_io(struct fc_rport *rport)
 int fnic_abort_cmd(struct scsi_cmnd *sc)
 {
 	struct request *const rq = scsi_cmd_to_rq(sc);
-	struct fc_lport *lp;
+	struct fnic_iport_s *iport;
+	struct fnic_tport_s *tport;
 	struct fnic *fnic;
 	struct fnic_io_req *io_req = NULL;
 	struct fc_rport *rport;
+	struct rport_dd_data_s *rdd_data;
 	unsigned long flags;
 	unsigned long start_time = 0;
 	int ret = SUCCESS;
@@ -1806,11 +2027,11 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	fc_block_scsi_eh(sc);
 
 	/* Get local-port, check ready and link up */
-	lp = shost_priv(sc->device->host);
-
-	fnic = lport_priv(lp);
+	fnic = *((struct fnic **) shost_priv(sc->device->host));
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	iport = &fnic->iport;
+
 	fnic_stats = &fnic->fnic_stats;
 	abts_stats = &fnic->fnic_stats.abts_stats;
 	term_stats = &fnic->fnic_stats.term_stats;
@@ -1821,7 +2042,44 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 
 	fnic_priv(sc)->flags = FNIC_NO_FLAGS;
 
-	if (lp->state != LPORT_ST_READY || !(lp->link_up)) {
+	rdd_data = rport->dd_data;
+	tport = rdd_data->tport;
+
+	if (!tport) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			  "Abort cmd called after tport delete! rport fcid: 0x%x",
+			  rport->port_id);
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+			  "lun: %llu hwq: 0x%x mqtag: 0x%x Op: 0x%x flags: 0x%x\n",
+			  sc->device->lun, hwq, mqtag,
+			  sc->cmnd[0], fnic_priv(sc)->flags);
+		ret = FAILED;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		goto fnic_abort_cmd_end;
+	}
+
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+	  "Abort cmd called rport fcid: 0x%x lun: %llu hwq: 0x%x mqtag: 0x%x",
+	  rport->port_id, sc->device->lun, hwq, mqtag);
+
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "Op: 0x%x flags: 0x%x\n",
+				  sc->cmnd[0],
+				  fnic_priv(sc)->flags);
+
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		atomic64_inc(&fnic_stats->misc_stats.iport_not_ready);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					  "iport NOT in READY state");
+		ret = FAILED;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		goto fnic_abort_cmd_end;
+	}
+
+	if ((tport->state != FDLS_TGT_STATE_READY) &&
+		(tport->state != FDLS_TGT_STATE_ADISC)) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "tport state: %d\n", tport->state);
 		ret = FAILED;
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		goto fnic_abort_cmd_end;
@@ -1843,6 +2101,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
+		ret = FAILED;
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		goto fnic_abort_cmd_end;
 	}
@@ -1870,7 +2129,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	else
 		atomic64_inc(&abts_stats->abort_issued_greater_than_60_sec);
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 		"CDB Opcode: 0x%02x Abort issued time: %lu msec\n",
 		sc->cmnd[0], abt_issued_time);
 	/*
@@ -1893,7 +2152,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	if (fc_remote_port_chkready(rport) == 0)
 		task_req = FCPIO_ITMF_ABT_TASK;
 	else {
-		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
+		atomic64_inc(&fnic_stats->misc_stats.tport_not_ready);
 		task_req = FCPIO_ITMF_ABT_TASK_TERM;
 	}
 
@@ -1961,7 +2220,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 
 	if (!(fnic_priv(sc)->flags & (FNIC_IO_ABORTED | FNIC_IO_DONE))) {
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			      "Issuing host reset due to out of order IO\n");
 
 		ret = FAILED;
@@ -2009,7 +2268,7 @@ fnic_abort_cmd_end:
 		  (u64)sc->cmnd[4] << 8 | sc->cmnd[5]),
 		  fnic_flags_and_state(sc));
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 		      "Returning from abort cmd type %x %s\n", task_req,
 		      (ret == SUCCESS) ?
 		      "SUCCESS" : "FAILED");
@@ -2027,6 +2286,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic,
 	unsigned long flags;
 	uint16_t hwq = 0;
 	uint32_t tag = 0;
+	struct fnic_tport_s *tport = io_req->tport;
 
 	tag = io_req->tag;
 	hwq = blk_mq_unique_tag_to_hwq(tag);
@@ -2037,8 +2297,10 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic,
 						FNIC_FLAGS_IO_BLOCKED))) {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		return FAILED;
-	} else
+	} else {
 		atomic_inc(&fnic->in_flight);
+		atomic_inc(&tport->in_flight);
+	}
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
@@ -2047,7 +2309,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic,
 		free_wq_copy_descs(fnic, wq, hwq);
 
 	if (!vnic_wq_copy_desc_avail(wq)) {
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			  "queue_dr_io_req failure - no descriptors\n");
 		atomic64_inc(&misc_stats->devrst_cpwq_alloc_failures);
 		ret = -EAGAIN;
@@ -2072,6 +2334,7 @@ static inline int fnic_queue_dr_io_req(struct fnic *fnic,
 lr_io_req_end:
 	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	atomic_dec(&fnic->in_flight);
+	atomic_dec(&tport->in_flight);
 
 	return ret;
 }
@@ -2114,7 +2377,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	 * Found IO that is still pending with firmware and
 	 * belongs to the LUN that we are resetting
 	 */
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 		      "Found IO in %s on lun\n",
 		      fnic_ioreq_state_to_str(fnic_priv(sc)->state));
 
@@ -2124,14 +2387,14 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	}
 	if ((fnic_priv(sc)->flags & FNIC_DEVICE_RESET) &&
 	    (!(fnic_priv(sc)->flags & FNIC_DEV_RST_ISSUED))) {
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			      "dev rst not pending sc 0x%p\n", sc);
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		return true;
 	}
 
 	if (io_req->abts_done)
-		shost_printk(KERN_ERR, fnic->lport->host,
+		shost_printk(KERN_ERR, fnic->host,
 			     "%s: io_req->abts_done is set state is %s\n",
 			     __func__, fnic_ioreq_state_to_str(fnic_priv(sc)->state));
 	old_ioreq_state = fnic_priv(sc)->state;
@@ -2147,7 +2410,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 	BUG_ON(io_req->abts_done);
 
 	if (fnic_priv(sc)->flags & FNIC_DEVICE_RESET) {
-		FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			      "dev rst sc 0x%p\n", sc);
 	}
 
@@ -2169,7 +2432,7 @@ static bool fnic_pending_aborts_iter(struct scsi_cmnd *sc, void *data)
 			fnic_priv(sc)->state = old_ioreq_state;
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		iter_data->ret = FAILED;
-		FNIC_SCSI_DBG(KERN_ERR, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 			"hwq: %d abt_tag: 0x%lx Abort could not be queued\n",
 			hwq, abt_tag);
 		return false;
@@ -2248,7 +2511,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic,
 
 	iter_data.lr_sc = lr_sc;
 
-	scsi_host_busy_iter(fnic->lport->host,
+	scsi_host_busy_iter(fnic->host,
 			    fnic_pending_aborts_iter, &iter_data);
 	if (iter_data.ret == FAILED) {
 		ret = iter_data.ret;
@@ -2261,7 +2524,7 @@ static int fnic_clean_pending_aborts(struct fnic *fnic,
 		ret = 1;
 
 clean_pending_aborts_end:
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 			"exit status: %d\n", ret);
 	return ret;
 }
@@ -2274,11 +2537,11 @@ clean_pending_aborts_end:
 int fnic_device_reset(struct scsi_cmnd *sc)
 {
 	struct request *rq = scsi_cmd_to_rq(sc);
-	struct fc_lport *lp;
 	struct fnic *fnic;
 	struct fnic_io_req *io_req = NULL;
 	struct fc_rport *rport;
 	int status;
+	int count = 0;
 	int ret = FAILED;
 	unsigned long flags;
 	unsigned long start_time = 0;
@@ -2289,31 +2552,63 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	DECLARE_COMPLETION_ONSTACK(tm_done);
 	bool new_sc = 0;
 	uint16_t hwq = 0;
+	struct fnic_iport_s *iport = NULL;
+	struct rport_dd_data_s *rdd_data;
+	struct fnic_tport_s *tport;
+	u32 old_soft_reset_count;
+	u32 old_link_down_cnt;
+	int exit_dr = 0;
 
 	/* Wait for rport to unblock */
 	fc_block_scsi_eh(sc);
 
 	/* Get local-port, check ready and link up */
-	lp = shost_priv(sc->device->host);
+	fnic = *((struct fnic **) shost_priv(sc->device->host));
+	iport = &fnic->iport;
 
-	fnic = lport_priv(lp);
 	fnic_stats = &fnic->fnic_stats;
-	reset_stats = &fnic->fnic_stats.reset_stats;
+	reset_stats = &fnic_stats->reset_stats;
 
 	atomic64_inc(&reset_stats->device_resets);
 
 	rport = starget_to_rport(scsi_target(sc->device));
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-		"fcid: 0x%x lun: 0x%llx hwq: %d mqtag: 0x%x flags: 0x%x Device reset\n",
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+		"fcid: 0x%x lun: %llu hwq: %d mqtag: 0x%x flags: 0x%x Device reset\n",
 		rport->port_id, sc->device->lun, hwq, mqtag,
 		fnic_priv(sc)->flags);
 
-	if (lp->state != LPORT_ST_READY || !(lp->link_up))
+	rdd_data = rport->dd_data;
+	tport = rdd_data->tport;
+	if (!tport) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+		  "Dev rst called after tport delete! rport fcid: 0x%x lun: %llu\n",
+		  rport->port_id, sc->device->lun);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		goto fnic_device_reset_end;
+	}
+
+	if (iport->state != FNIC_IPORT_STATE_READY) {
+		atomic64_inc(&fnic_stats->misc_stats.iport_not_ready);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					  "iport NOT in READY state");
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		goto fnic_device_reset_end;
+	}
+
+	if ((tport->state != FDLS_TGT_STATE_READY) &&
+		(tport->state != FDLS_TGT_STATE_ADISC)) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "tport state: %d\n", tport->state);
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		goto fnic_device_reset_end;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
 	/* Check if remote port up */
 	if (fc_remote_port_chkready(rport)) {
-		atomic64_inc(&fnic_stats->misc_stats.rport_not_ready);
+		atomic64_inc(&fnic_stats->misc_stats.tport_not_ready);
 		goto fnic_device_reset_end;
 	}
 
@@ -2352,6 +2647,7 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 		io_req->port_id = rport->port_id;
 		io_req->tag = mqtag;
 		fnic_priv(sc)->io_req = io_req;
+		io_req->tport = tport;
 		io_req->sc = sc;
 
 		if (fnic->sw_copy_wq[hwq].io_req_table[blk_mq_unique_tag_to_tag(mqtag)] != NULL)
@@ -2366,7 +2662,7 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	fnic_priv(sc)->lr_status = FCPIO_INVALID_CODE;
 	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num, "TAG %x\n", mqtag);
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num, "TAG %x\n", mqtag);
 
 	/*
 	 * issue the device reset, if enqueue failed, clean up the ioreq
@@ -2383,6 +2679,11 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	fnic_priv(sc)->flags |= FNIC_DEV_RST_ISSUED;
 	spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	old_link_down_cnt = iport->fnic->link_down_cnt;
+	old_soft_reset_count = fnic->soft_reset_count;
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
 	/*
 	 * Wait on the local completion for LUN reset.  The io_req may be
 	 * freed while we wait since we hold no lock.
@@ -2390,14 +2691,39 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	wait_for_completion_timeout(&tm_done,
 				    msecs_to_jiffies(FNIC_LUN_RESET_TIMEOUT));
 
+	/*
+	 * Wake up can be due to the following reasons:
+	 * 1) The device reset completed from target.
+	 * 2) Device reset timed out.
+	 * 3) A link-down/host_reset may have happened in between.
+	 * 4) The device reset was aborted and io_req->dr_done was called.
+	 */
+
+	exit_dr = 0;
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	if ((old_link_down_cnt != fnic->link_down_cnt) ||
+		(fnic->reset_in_progress) ||
+		(fnic->soft_reset_count != old_soft_reset_count) ||
+		(iport->state != FNIC_IPORT_STATE_READY))
+		exit_dr = 1;
+
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
 	spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 	io_req = fnic_priv(sc)->io_req;
 	if (!io_req) {
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 				"io_req is null mqtag 0x%x sc 0x%p\n", mqtag, sc);
 		goto fnic_device_reset_end;
 	}
+
+	if (exit_dr) {
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "Host reset called for fnic. Exit device reset\n");
+		io_req->dr_done = NULL;
+		goto fnic_device_reset_clean;
+	}
 	io_req->dr_done = NULL;
 
 	status = fnic_priv(sc)->lr_status;
@@ -2408,53 +2734,11 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	 */
 	if (status == FCPIO_INVALID_CODE) {
 		atomic64_inc(&reset_stats->device_reset_timeouts);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 			      "Device reset timed out\n");
 		fnic_priv(sc)->flags |= FNIC_DEV_RST_TIMED_OUT;
-		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 		int_to_scsilun(sc->device->lun, &fc_lun);
-		/*
-		 * Issue abort and terminate on device reset request.
-		 * If q'ing of terminate fails, retry it after a delay.
-		 */
-		while (1) {
-			spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
-			if (fnic_priv(sc)->flags & FNIC_DEV_RST_TERM_ISSUED) {
-				spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-				break;
-			}
-			spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-			if (fnic_queue_abort_io_req(fnic,
-				mqtag | FNIC_TAG_DEV_RST,
-				FCPIO_ITMF_ABT_TASK_TERM,
-				fc_lun.scsi_lun, io_req, hwq)) {
-				wait_for_completion_timeout(&tm_done,
-				msecs_to_jiffies(FNIC_ABT_TERM_DELAY_TIMEOUT));
-			} else {
-				spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
-				fnic_priv(sc)->flags |= FNIC_DEV_RST_TERM_ISSUED;
-				fnic_priv(sc)->state = FNIC_IOREQ_ABTS_PENDING;
-				io_req->abts_done = &tm_done;
-				spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-				FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-				"Abort and terminate issued on Device reset mqtag 0x%x sc 0x%p\n",
-				mqtag, sc);
-				break;
-			}
-		}
-		while (1) {
-			spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
-			if (!(fnic_priv(sc)->flags & FNIC_DEV_RST_DONE)) {
-				spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
-				wait_for_completion_timeout(&tm_done,
-				msecs_to_jiffies(FNIC_LUN_RESET_TIMEOUT));
-				break;
-			} else {
-				io_req = fnic_priv(sc)->io_req;
-				io_req->abts_done = NULL;
-				goto fnic_device_reset_clean;
-			}
-		}
+		goto fnic_device_reset_clean;
 	} else {
 		spin_unlock_irqrestore(&fnic->wq_copy_lock[hwq], flags);
 	}
@@ -2463,7 +2747,7 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	if (status != FCPIO_SUCCESS) {
 		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		FNIC_SCSI_DBG(KERN_DEBUG,
-			      fnic->lport->host, fnic->fnic_num,
+			      fnic->host, fnic->fnic_num,
 			      "Device reset completed - failed\n");
 		io_req = fnic_priv(sc)->io_req;
 		goto fnic_device_reset_clean;
@@ -2479,9 +2763,8 @@ int fnic_device_reset(struct scsi_cmnd *sc)
 	if (fnic_clean_pending_aborts(fnic, sc, new_sc)) {
 		spin_lock_irqsave(&fnic->wq_copy_lock[hwq], flags);
 		io_req = fnic_priv(sc)->io_req;
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			      "Device reset failed"
-			      " since could not abort all IOs\n");
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
+					  "Device reset failed: Cannot abort all IOs\n");
 		goto fnic_device_reset_clean;
 	}
 
@@ -2507,6 +2790,15 @@ fnic_device_reset_clean:
 		mempool_free(io_req, fnic->io_req_pool);
 	}
 
+	/*
+	 * If link-event is seen while LUN reset is issued we need
+	 * to complete the LUN reset here
+	 */
+	if (!new_sc) {
+		sc->result = DID_RESET << 16;
+		scsi_done(sc);
+	}
+
 fnic_device_reset_end:
 	FNIC_TRACE(fnic_device_reset, sc->device->host->host_no, rq->tag, sc,
 		  jiffies_to_msecs(jiffies - start_time),
@@ -2520,7 +2812,18 @@ fnic_device_reset_end:
 		mutex_unlock(&fnic->sgreset_mutex);
 	}
 
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
+	while ((ret == SUCCESS) && fnic_count_lun_ioreqs(fnic, sc->device)) {
+		if (count >= 2) {
+			ret = FAILED;
+			break;
+		}
+		FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+					  "Cannot clean up all IOs for the LUN\n");
+		schedule_timeout(msecs_to_jiffies(1000));
+		count++;
+	}
+
+	FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 		      "Returning from device reset %s\n",
 		      (ret == SUCCESS) ?
 		      "SUCCESS" : "FAILED");
@@ -2531,67 +2834,78 @@ fnic_device_reset_end:
 	return ret;
 }
 
-/* Clean up all IOs, clean up libFC local port */
-int fnic_reset(struct Scsi_Host *shost)
+static void fnic_post_flogo_linkflap(struct fnic *fnic)
+{
+	unsigned long flags;
+
+	fnic_fdls_link_status_change(fnic, 0);
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+
+	if (fnic->link_status) {
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		fnic_fdls_link_status_change(fnic, 1);
+		return;
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+}
+
+/* Logout from all the targets and simulate link flap */
+void fnic_reset(struct Scsi_Host *shost)
 {
-	struct fc_lport *lp;
 	struct fnic *fnic;
-	int ret = 0;
 	struct reset_stats *reset_stats;
 
-	lp = shost_priv(shost);
-	fnic = lport_priv(lp);
+	fnic = *((struct fnic **) shost_priv(shost));
 	reset_stats = &fnic->fnic_stats.reset_stats;
 
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-			"Issuing fnic reset\n");
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "Issuing fnic reset\n");
 
 	atomic64_inc(&reset_stats->fnic_resets);
+	fnic_post_flogo_linkflap(fnic);
 
-	/*
-	 * Reset local port, this will clean up libFC exchanges,
-	 * reset remote port sessions, and if link is up, begin flogi
-	 */
-	ret = fc_lport_reset(lp);
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "Returning from fnic reset");
 
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
-		"Returning from fnic reset with: %s\n",
-		(ret == 0) ? "SUCCESS" : "FAILED");
+	atomic64_inc(&reset_stats->fnic_reset_completions);
+}
 
-	if (ret == 0)
-		atomic64_inc(&reset_stats->fnic_reset_completions);
-	else
-		atomic64_inc(&reset_stats->fnic_reset_failures);
+int fnic_issue_fc_host_lip(struct Scsi_Host *shost)
+{
+	int ret = 0;
+	struct fnic *fnic = *((struct fnic **) shost_priv(shost));
+
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "FC host lip issued");
 
+	ret = fnic_host_reset(shost);
 	return ret;
 }
 
-/*
- * SCSI Error handling calls driver's eh_host_reset if all prior
- * error handling levels return FAILED. If host reset completes
- * successfully, and if link is up, then Fabric login begins.
- *
- * Host Reset is the highest level of error recovery. If this fails, then
- * host is offlined by SCSI.
- *
- */
-int fnic_host_reset(struct scsi_cmnd *sc)
+int fnic_host_reset(struct Scsi_Host *shost)
 {
-	int ret;
+	int ret = SUCCESS;
 	unsigned long wait_host_tmo;
-	struct Scsi_Host *shost = sc->device->host;
-	struct fc_lport *lp = shost_priv(shost);
-	struct fnic *fnic = lport_priv(lp);
+	struct fnic *fnic = *((struct fnic **) shost_priv(shost));
 	unsigned long flags;
+	struct fnic_iport_s *iport = &fnic->iport;
 
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (!fnic->internal_reset_inprogress) {
-		fnic->internal_reset_inprogress = true;
+	if (fnic->reset_in_progress == NOT_IN_PROGRESS) {
+		fnic->reset_in_progress = IN_PROGRESS;
 	} else {
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-			"host reset in progress skipping another host reset\n");
-		return SUCCESS;
+		wait_for_completion_timeout(&fnic->reset_completion_wait,
+									msecs_to_jiffies(10000));
+
+		spin_lock_irqsave(&fnic->fnic_lock, flags);
+		if (fnic->reset_in_progress == IN_PROGRESS) {
+			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+			FNIC_SCSI_DBG(KERN_WARNING, fnic->host, fnic->fnic_num,
+			  "Firmware reset in progress. Skipping another host reset\n");
+			return SUCCESS;
+		}
+		fnic->reset_in_progress = IN_PROGRESS;
 	}
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
@@ -2600,140 +2914,34 @@ int fnic_host_reset(struct scsi_cmnd *sc)
 	 * scsi-ml tries to send a TUR to every device if host reset is
 	 * successful, so before returning to scsi, fabric should be up
 	 */
-	ret = (fnic_reset(shost) == 0) ? SUCCESS : FAILED;
-	if (ret == SUCCESS) {
+	fnic_reset(shost);
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	fnic->reset_in_progress = NOT_IN_PROGRESS;
+	complete(&fnic->reset_completion_wait);
+	fnic->soft_reset_count++;
+
+	/* wait till the link is up */
+	if (fnic->link_status) {
 		wait_host_tmo = jiffies + FNIC_HOST_RESET_SETTLE_TIME * HZ;
 		ret = FAILED;
 		while (time_before(jiffies, wait_host_tmo)) {
-			if ((lp->state == LPORT_ST_READY) &&
-			    (lp->link_up)) {
+			if (iport->state != FNIC_IPORT_STATE_READY
+				&& fnic->link_status) {
+				spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+				ssleep(1);
+				spin_lock_irqsave(&fnic->fnic_lock, flags);
+			} else {
 				ret = SUCCESS;
 				break;
 			}
-			ssleep(1);
 		}
 	}
-
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	fnic->internal_reset_inprogress = false;
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-	return ret;
-}
-
-/*
- * This fxn is called from libFC when host is removed
- */
-void fnic_scsi_abort_io(struct fc_lport *lp)
-{
-	int err = 0;
-	unsigned long flags;
-	enum fnic_state old_state;
-	struct fnic *fnic = lport_priv(lp);
-	DECLARE_COMPLETION_ONSTACK(remove_wait);
-
-	/* Issue firmware reset for fnic, wait for reset to complete */
-retry_fw_reset:
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (unlikely(fnic->state == FNIC_IN_FC_TRANS_ETH_MODE) &&
-		     fnic->link_events) {
-		/* fw reset is in progress, poll for its completion */
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		schedule_timeout(msecs_to_jiffies(100));
-		goto retry_fw_reset;
-	}
-
-	fnic->remove_wait = &remove_wait;
-	old_state = fnic->state;
-	fnic->state = FNIC_IN_FC_TRANS_ETH_MODE;
-	fnic_update_mac_locked(fnic, fnic->ctlr.ctl_src_addr);
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 
-	err = fnic_fw_reset_handler(fnic);
-	if (err) {
-		spin_lock_irqsave(&fnic->fnic_lock, flags);
-		if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)
-			fnic->state = old_state;
-		fnic->remove_wait = NULL;
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		return;
-	}
-
-	/* Wait for firmware reset to complete */
-	wait_for_completion_timeout(&remove_wait,
-				    msecs_to_jiffies(FNIC_RMDEVICE_TIMEOUT));
-
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	fnic->remove_wait = NULL;
-	FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, fnic->fnic_num,
-		      "fnic_scsi_abort_io %s\n",
-		      (fnic->state == FNIC_IN_ETH_MODE) ?
-		      "SUCCESS" : "FAILED");
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-
-}
-
-/*
- * This fxn called from libFC to clean up driver IO state on link down
- */
-void fnic_scsi_cleanup(struct fc_lport *lp)
-{
-	unsigned long flags;
-	enum fnic_state old_state;
-	struct fnic *fnic = lport_priv(lp);
-
-	/* issue fw reset */
-retry_fw_reset:
-	spin_lock_irqsave(&fnic->fnic_lock, flags);
-	if (unlikely(fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)) {
-		/* fw reset is in progress, poll for its completion */
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		schedule_timeout(msecs_to_jiffies(100));
-		goto retry_fw_reset;
-	}
-	old_state = fnic->state;
-	fnic->state = FNIC_IN_FC_TRANS_ETH_MODE;
-	fnic_update_mac_locked(fnic, fnic->ctlr.ctl_src_addr);
-	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-
-	if (fnic_fw_reset_handler(fnic)) {
-		spin_lock_irqsave(&fnic->fnic_lock, flags);
-		if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)
-			fnic->state = old_state;
-		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-	}
-
-}
-
-void fnic_empty_scsi_cleanup(struct fc_lport *lp)
-{
-}
-
-void fnic_exch_mgr_reset(struct fc_lport *lp, u32 sid, u32 did)
-{
-	struct fnic *fnic = lport_priv(lp);
-
-	/* Non-zero sid, nothing to do */
-	if (sid)
-		goto call_fc_exch_mgr_reset;
-
-	if (did) {
-		fnic_rport_exch_reset(fnic, did);
-		goto call_fc_exch_mgr_reset;
-	}
-
-	/*
-	 * sid = 0, did = 0
-	 * link down or device being removed
-	 */
-	if (!fnic->in_remove)
-		fnic_scsi_cleanup(lp);
-	else
-		fnic_scsi_abort_io(lp);
-
-	/* call libFC exch mgr reset to reset its exchanges */
-call_fc_exch_mgr_reset:
-	fc_exch_mgr_reset(lp, sid, did);
-
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "host reset return status: %d\n", ret);
+	return ret;
 }
 
 static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data)
@@ -2771,7 +2979,7 @@ static bool fnic_abts_pending_iter(struct scsi_cmnd *sc, void *data)
 	 * Found IO that is still pending with firmware and
 	 * belongs to the LUN that we are resetting
 	 */
-	FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host, fnic->fnic_num,
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 		"hwq: %d tag: 0x%x Found IO in state: %s on lun\n",
 		hwq, tag,
 		fnic_ioreq_state_to_str(fnic_priv(sc)->state));
@@ -2804,8 +3012,81 @@ int fnic_is_abts_pending(struct fnic *fnic, struct scsi_cmnd *lr_sc)
 	}
 
 	/* walk again to check, if IOs are still pending in fw */
-	scsi_host_busy_iter(fnic->lport->host,
+	scsi_host_busy_iter(fnic->host,
 			    fnic_abts_pending_iter, &iter_data);
 
 	return iter_data.ret;
 }
+
+/*
+ * SCSI Error handling calls driver's eh_host_reset if all prior
+ * error handling levels return FAILED. If host reset completes
+ * successfully, and if link is up, then Fabric login begins.
+ *
+ * Host Reset is the highest level of error recovery. If this fails, then
+ * host is offlined by SCSI.
+ *
+ */
+int fnic_eh_host_reset_handler(struct scsi_cmnd *sc)
+{
+	int ret = 0;
+	struct Scsi_Host *shost = sc->device->host;
+	struct fnic *fnic = *((struct fnic **) shost_priv(shost));
+
+	FNIC_SCSI_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
+				  "SCSI error handling: fnic host reset");
+
+	ret = fnic_host_reset(shost);
+	return ret;
+}
+
+
+void fnic_scsi_fcpio_reset(struct fnic *fnic)
+{
+	unsigned long flags;
+	enum fnic_state old_state;
+	struct fnic_iport_s *iport = &fnic->iport;
+	DECLARE_COMPLETION_ONSTACK(fw_reset_done);
+	int time_remain;
+
+	/* issue fw reset */
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	if (unlikely(fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)) {
+		/* fw reset is in progress, poll for its completion */
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			  "fnic is in unexpected state: %d for fw_reset\n",
+			  fnic->state);
+		return;
+	}
+
+	old_state = fnic->state;
+	fnic->state = FNIC_IN_FC_TRANS_ETH_MODE;
+
+	fnic_update_mac_locked(fnic, iport->hwmac);
+	fnic->fw_reset_done = &fw_reset_done;
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+
+	FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "Issuing fw reset\n");
+	if (fnic_fw_reset_handler(fnic)) {
+		spin_lock_irqsave(&fnic->fnic_lock, flags);
+		if (fnic->state == FNIC_IN_FC_TRANS_ETH_MODE)
+			fnic->state = old_state;
+		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	} else {
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					  "Waiting for fw completion\n");
+		time_remain = wait_for_completion_timeout(&fw_reset_done,
+						  msecs_to_jiffies(FNIC_FW_RESET_TIMEOUT));
+		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					  "Woken up after fw completion timeout\n");
+		if (time_remain == 0) {
+			FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				  "FW reset completion timed out after %d ms)\n",
+				  FNIC_FW_RESET_TIMEOUT);
+		}
+		atomic64_inc(&fnic->fnic_stats.reset_stats.fw_reset_timeouts);
+	}
+	fnic->fw_reset_done = NULL;
+}
diff --git a/drivers/scsi/fnic/fnic_stats.h b/drivers/scsi/fnic/fnic_stats.h
index 9d7f98c452dd..8ddd20401a59 100644
--- a/drivers/scsi/fnic/fnic_stats.h
+++ b/drivers/scsi/fnic/fnic_stats.h
@@ -3,6 +3,7 @@
 #ifndef _FNIC_STATS_H_
 #define _FNIC_STATS_H_
 #define FNIC_MQ_MAX_QUEUES 64
+#include <scsi/scsi_transport_fc.h>
 
 struct stats_timestamps {
 	struct timespec64 last_reset_time;
@@ -63,6 +64,7 @@ struct reset_stats {
 	atomic64_t fw_resets;
 	atomic64_t fw_reset_completions;
 	atomic64_t fw_reset_failures;
+	atomic64_t fw_reset_timeouts;
 	atomic64_t fnic_resets;
 	atomic64_t fnic_reset_completions;
 	atomic64_t fnic_reset_failures;
@@ -102,10 +104,51 @@ struct misc_stats {
 	atomic64_t no_icmnd_itmf_cmpls;
 	atomic64_t check_condition;
 	atomic64_t queue_fulls;
-	atomic64_t rport_not_ready;
+	atomic64_t tport_not_ready;
+	atomic64_t iport_not_ready;
 	atomic64_t frame_errors;
 	atomic64_t current_port_speed;
 	atomic64_t intx_dummy;
+	atomic64_t port_speed_in_mbps;
+};
+
+struct fnic_iport_stats {
+	atomic64_t num_linkdn;
+	atomic64_t num_linkup;
+	atomic64_t link_failure_count;
+	atomic64_t num_rscns;
+	atomic64_t rscn_redisc;
+	atomic64_t rscn_not_redisc;
+	atomic64_t frame_err;
+	atomic64_t num_rnid;
+	atomic64_t fabric_flogi_sent;
+	atomic64_t fabric_flogi_ls_accepts;
+	atomic64_t fabric_flogi_ls_rejects;
+	atomic64_t fabric_flogi_misc_rejects;
+	atomic64_t fabric_plogi_sent;
+	atomic64_t fabric_plogi_ls_accepts;
+	atomic64_t fabric_plogi_ls_rejects;
+	atomic64_t fabric_plogi_misc_rejects;
+	atomic64_t fabric_scr_sent;
+	atomic64_t fabric_scr_ls_accepts;
+	atomic64_t fabric_scr_ls_rejects;
+	atomic64_t fabric_scr_misc_rejects;
+	atomic64_t fabric_logo_sent;
+	atomic64_t tport_alive;
+	atomic64_t tport_plogi_sent;
+	atomic64_t tport_plogi_ls_accepts;
+	atomic64_t tport_plogi_ls_rejects;
+	atomic64_t tport_plogi_misc_rejects;
+	atomic64_t tport_prli_sent;
+	atomic64_t tport_prli_ls_accepts;
+	atomic64_t tport_prli_ls_rejects;
+	atomic64_t tport_prli_misc_rejects;
+	atomic64_t tport_adisc_sent;
+	atomic64_t tport_adisc_ls_accepts;
+	atomic64_t tport_adisc_ls_rejects;
+	atomic64_t tport_logo_sent;
+	atomic64_t unsupported_frames_ls_rejects;
+	atomic64_t unsupported_frames_dropped;
 };
 
 struct fnic_stats {
@@ -116,6 +159,7 @@ struct fnic_stats {
 	struct reset_stats reset_stats;
 	struct fw_stats fw_stats;
 	struct vlan_stats vlan_stats;
+	struct fc_host_statistics host_stats;
 	struct misc_stats misc_stats;
 };
 
@@ -127,6 +171,5 @@ struct stats_debug_info {
 };
 
 int fnic_get_stats_data(struct stats_debug_info *, struct fnic_stats *);
-void fnic_stats_debugfs_init(struct fnic *);
-void fnic_stats_debugfs_remove(struct fnic *);
+const char *fnic_role_to_str(unsigned int role);
 #endif /* _FNIC_STATS_H_ */
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index aaa4ea02fb7c..cdc6b12b1ec2 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -8,6 +8,7 @@
 #include <linux/kallsyms.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
+#include <scsi/scsi_transport_fc.h>
 #include "fnic_io.h"
 #include "fnic.h"
 
@@ -29,6 +30,17 @@ int fnic_fc_tracing_enabled = 1;
 int fnic_fc_trace_cleared = 1;
 static DEFINE_SPINLOCK(fnic_fc_trace_lock);
 
+static const char * const fnic_role_str[] = {
+	[FNIC_ROLE_FCP_INITIATOR] = "FCP_Initiator",
+};
+
+const char *fnic_role_to_str(unsigned int role)
+{
+	if (role >= ARRAY_SIZE(fnic_role_str) || !fnic_role_str[role])
+		return "Unknown";
+
+	return fnic_role_str[role];
+}
 
 /*
  * fnic_trace_get_buf - Give buffer pointer to user to fill up trace information
@@ -423,7 +435,8 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
 		  "Number of Check Conditions encountered: %lld\n"
 		  "Number of QUEUE Fulls: %lld\n"
 		  "Number of rport not ready: %lld\n"
-		  "Number of receive frame errors: %lld\n",
+		 "Number of receive frame errors: %lld\n"
+		 "Port speed (in Mbps): %lld\n",
 		  (u64)stats->misc_stats.last_isr_time,
 		  (s64)val1.tv_sec, val1.tv_nsec,
 		  (u64)stats->misc_stats.last_ack_time,
@@ -446,18 +459,68 @@ int fnic_get_stats_data(struct stats_debug_info *debug,
 		  (u64)atomic64_read(&stats->misc_stats.no_icmnd_itmf_cmpls),
 		  (u64)atomic64_read(&stats->misc_stats.check_condition),
 		  (u64)atomic64_read(&stats->misc_stats.queue_fulls),
-		  (u64)atomic64_read(&stats->misc_stats.rport_not_ready),
-		  (u64)atomic64_read(&stats->misc_stats.frame_errors));
-
-	len += scnprintf(debug->debug_buffer + len, buf_size - len,
-			"Firmware reported port speed: %llu\n",
-			(u64)atomic64_read(
-				&stats->misc_stats.current_port_speed));
+		  (u64)atomic64_read(&stats->misc_stats.tport_not_ready),
+		  (u64)atomic64_read(&stats->misc_stats.frame_errors),
+		  (u64)atomic64_read(&stats->misc_stats.port_speed_in_mbps));
 
 	return len;
 
 }
 
+int fnic_get_debug_info(struct stats_debug_info *info, struct fnic *fnic)
+{
+	struct fnic_iport_s *iport = &fnic->iport;
+	int buf_size = info->buf_size;
+	int len = info->buffer_len;
+	struct fnic_tport_s *tport, *next;
+	unsigned long flags;
+
+	len += snprintf(info->debug_buffer + len, buf_size - len,
+					"------------------------------------------\n"
+					"\t\t Debug Info\n"
+					"------------------------------------------\n");
+	len += snprintf(info->debug_buffer + len, buf_size - len,
+					"fnic Name:%s number:%d Role:%s State:%s\n",
+					fnic->name, fnic->fnic_num,
+					fnic_role_to_str(fnic->role),
+					fnic_state_to_str(fnic->state));
+	len +=
+		snprintf(info->debug_buffer + len, buf_size - len,
+			 "iport State:%d Flags:0x%x vlan_id:%d fcid:0x%x\n",
+			 iport->state, iport->flags, iport->vlan_id, iport->fcid);
+	len +=
+		snprintf(info->debug_buffer + len, buf_size - len,
+			 "usefip:%d fip_state:%d fip_flogi_retry:%d\n",
+			 iport->usefip, iport->fip.state, iport->fip.flogi_retry);
+	len +=
+		snprintf(info->debug_buffer + len, buf_size - len,
+				 "fpma %02x:%02x:%02x:%02x:%02x:%02x",
+				 iport->fpma[5], iport->fpma[4], iport->fpma[3],
+				 iport->fpma[2], iport->fpma[1], iport->fpma[0]);
+	len +=
+		snprintf(info->debug_buffer + len, buf_size - len,
+				"fcfmac %02x:%02x:%02x:%02x:%02x:%02x\n",
+				iport->fcfmac[5], iport->fcfmac[4], iport->fcfmac[3],
+				iport->fcfmac[2], iport->fcfmac[1], iport->fcfmac[0]);
+	len +=
+		snprintf(info->debug_buffer + len, buf_size - len,
+		 "fabric state:%d flags:0x%x retry_counter:%d e_d_tov:%d r_a_tov:%d\n",
+		 iport->fabric.state, iport->fabric.flags,
+		 iport->fabric.retry_counter, iport->e_d_tov,
+		 iport->r_a_tov);
+
+	spin_lock_irqsave(&fnic->fnic_lock, flags);
+	list_for_each_entry_safe(tport, next, &iport->tport_list, links) {
+		len += snprintf(info->debug_buffer + len, buf_size - len,
+		"tport fcid:0x%x state:%d flags:0x%x inflight:%d retry_counter:%d\n",
+		tport->fcid, tport->state, tport->flags,
+		atomic_read(&tport->in_flight),
+		tport->retry_counter);
+	}
+	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	return len;
+}
+
 /*
  * fnic_trace_buf_init - Initialize fnic trace buffer logging facility
  *
@@ -485,8 +548,7 @@ int fnic_trace_buf_init(void)
 	}
 
 	fnic_trace_entries.page_offset =
-		vmalloc(array_size(fnic_max_trace_entries,
-				   sizeof(unsigned long)));
+		vcalloc(fnic_max_trace_entries, sizeof(unsigned long));
 	if (!fnic_trace_entries.page_offset) {
 		printk(KERN_ERR PFX "Failed to allocate memory for"
 				  " page_offset\n");
@@ -497,8 +559,6 @@ int fnic_trace_buf_init(void)
 		err = -ENOMEM;
 		goto err_fnic_trace_buf_init;
 	}
-	memset((void *)fnic_trace_entries.page_offset, 0,
-		  (fnic_max_trace_entries * sizeof(unsigned long)));
 	fnic_trace_entries.wr_idx = fnic_trace_entries.rd_idx = 0;
 	fnic_buf_head = fnic_trace_buf_p;
 
@@ -559,8 +619,7 @@ int fnic_fc_trace_init(void)
 	fc_trace_max_entries = (fnic_fc_trace_max_pages * PAGE_SIZE)/
 				FC_TRC_SIZE_BYTES;
 	fnic_fc_ctlr_trace_buf_p =
-		(unsigned long)vmalloc(array_size(PAGE_SIZE,
-						  fnic_fc_trace_max_pages));
+		(unsigned long)vcalloc(fnic_fc_trace_max_pages, PAGE_SIZE);
 	if (!fnic_fc_ctlr_trace_buf_p) {
 		pr_err("fnic: Failed to allocate memory for "
 		       "FC Control Trace Buf\n");
@@ -568,13 +627,9 @@ int fnic_fc_trace_init(void)
 		goto err_fnic_fc_ctlr_trace_buf_init;
 	}
 
-	memset((void *)fnic_fc_ctlr_trace_buf_p, 0,
-			fnic_fc_trace_max_pages * PAGE_SIZE);
-
 	/* Allocate memory for page offset */
 	fc_trace_entries.page_offset =
-		vmalloc(array_size(fc_trace_max_entries,
-				   sizeof(unsigned long)));
+		vcalloc(fc_trace_max_entries, sizeof(unsigned long));
 	if (!fc_trace_entries.page_offset) {
 		pr_err("fnic:Failed to allocate memory for page_offset\n");
 		if (fnic_fc_ctlr_trace_buf_p) {
@@ -585,8 +640,6 @@ int fnic_fc_trace_init(void)
 		err = -ENOMEM;
 		goto err_fnic_fc_ctlr_trace_buf_init;
 	}
-	memset((void *)fc_trace_entries.page_offset, 0,
-	       (fc_trace_max_entries * sizeof(unsigned long)));
 
 	fc_trace_entries.rd_idx = fc_trace_entries.wr_idx = 0;
 	fc_trace_buf_head = fnic_fc_ctlr_trace_buf_p;
@@ -688,7 +741,7 @@ int fnic_fc_trace_set_data(u32 host_no, u8 frame_type,
 	 */
 	if (frame_type == FNIC_FC_RECV) {
 		eth_fcoe_hdr_len = sizeof(struct ethhdr) +
-					sizeof(struct fcoe_hdr);
+							sizeof(struct fcoe_hdr);
 		memset((char *)fc_trace, 0xff, eth_fcoe_hdr_len);
 		/* Copy the rest of data frame */
 		memcpy((char *)(fc_trace + eth_fcoe_hdr_len), (void *)frame,
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 4101447bb8eb..2d438d722d0b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -643,9 +643,8 @@ extern int hisi_sas_probe(struct platform_device *pdev,
 			  const struct hisi_sas_hw *ops);
 extern void hisi_sas_remove(struct platform_device *pdev);
 
-int hisi_sas_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim);
-extern int hisi_sas_slave_alloc(struct scsi_device *sdev);
+int hisi_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim);
+extern int hisi_sas_sdev_init(struct scsi_device *sdev);
 extern int hisi_sas_scan_finished(struct Scsi_Host *shost, unsigned long time);
 extern void hisi_sas_scan_start(struct Scsi_Host *shost);
 extern int hisi_sas_host_reset(struct Scsi_Host *shost, int reset_type);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 53cb15f6714b..da4a2ed8ee86 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -805,13 +805,13 @@ static int hisi_sas_init_device(struct domain_device *device)
 	return rc;
 }
 
-int hisi_sas_slave_alloc(struct scsi_device *sdev)
+int hisi_sas_sdev_init(struct scsi_device *sdev)
 {
 	struct domain_device *ddev = sdev_to_domain_dev(sdev);
 	struct hisi_sas_device *sas_dev = ddev->lldd_dev;
 	int rc;
 
-	rc = sas_slave_alloc(sdev);
+	rc = sas_sdev_init(sdev);
 	if (rc)
 		return rc;
 
@@ -821,7 +821,7 @@ int hisi_sas_slave_alloc(struct scsi_device *sdev)
 	sas_dev->dev_status = HISI_SAS_DEV_NORMAL;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(hisi_sas_slave_alloc);
+EXPORT_SYMBOL_GPL(hisi_sas_sdev_init);
 
 static int hisi_sas_dev_found(struct domain_device *device)
 {
@@ -868,11 +868,10 @@ err_out:
 	return rc;
 }
 
-int hisi_sas_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+int hisi_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct domain_device *dev = sdev_to_domain_dev(sdev);
-	int ret = sas_device_configure(sdev, lim);
+	int ret = sas_sdev_configure(sdev, lim);
 
 	if (ret)
 		return ret;
@@ -881,7 +880,7 @@ int hisi_sas_device_configure(struct scsi_device *sdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(hisi_sas_device_configure);
+EXPORT_SYMBOL_GPL(hisi_sas_sdev_configure);
 
 void hisi_sas_scan_start(struct Scsi_Host *shost)
 {
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index c3e571be2222..bb78e53c66e2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1753,11 +1753,11 @@ static int check_fw_info_v1_hw(struct hisi_hba *hisi_hba)
 
 static const struct scsi_host_template sht_v1_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
-	.device_configure	= hisi_sas_device_configure,
+	.sdev_configure		= hisi_sas_sdev_configure,
 	.scan_finished		= hisi_sas_scan_finished,
 	.scan_start		= hisi_sas_scan_start,
 	.sg_tablesize		= HISI_SAS_SGE_PAGE_CNT,
-	.slave_alloc		= hisi_sas_slave_alloc,
+	.sdev_init		= hisi_sas_sdev_init,
 	.shost_groups		= host_v1_hw_groups,
 	.host_reset             = hisi_sas_host_reset,
 };
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 1a62b5d15eca..71cd5b4450c2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3585,11 +3585,11 @@ static int check_fw_info_v2_hw(struct hisi_hba *hisi_hba)
 
 static const struct scsi_host_template sht_v2_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
-	.device_configure	= hisi_sas_device_configure,
+	.sdev_configure		= hisi_sas_sdev_configure,
 	.scan_finished		= hisi_sas_scan_finished,
 	.scan_start		= hisi_sas_scan_start,
 	.sg_tablesize		= HISI_SAS_SGE_PAGE_CNT,
-	.slave_alloc		= hisi_sas_slave_alloc,
+	.sdev_init		= hisi_sas_sdev_init,
 	.shost_groups		= host_v2_hw_groups,
 	.sdev_groups		= sdev_groups_v2_hw,
 	.host_reset		= hisi_sas_host_reset,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 35501d0aa655..48b95d9a7927 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2908,12 +2908,12 @@ static ssize_t iopoll_q_cnt_v3_hw_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(iopoll_q_cnt_v3_hw);
 
-static int device_configure_v3_hw(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int sdev_configure_v3_hw(struct scsi_device *sdev,
+				struct queue_limits *lim)
 {
 	struct Scsi_Host *shost = dev_to_shost(&sdev->sdev_gendev);
 	struct hisi_hba *hisi_hba = shost_priv(shost);
-	int ret = hisi_sas_device_configure(sdev, lim);
+	int ret = hisi_sas_sdev_configure(sdev, lim);
 	struct device *dev = hisi_hba->dev;
 
 	if (ret)
@@ -3336,13 +3336,13 @@ static void hisi_sas_map_queues(struct Scsi_Host *shost)
 
 static const struct scsi_host_template sht_v3_hw = {
 	LIBSAS_SHT_BASE_NO_SLAVE_INIT
-	.device_configure	= device_configure_v3_hw,
+	.sdev_configure		= sdev_configure_v3_hw,
 	.scan_finished		= hisi_sas_scan_finished,
 	.scan_start		= hisi_sas_scan_start,
 	.map_queues		= hisi_sas_map_queues,
 	.sg_tablesize		= HISI_SAS_SGE_PAGE_CNT,
 	.sg_prot_tablesize	= HISI_SAS_SGE_PAGE_CNT,
-	.slave_alloc		= hisi_sas_slave_alloc,
+	.sdev_init		= hisi_sas_sdev_init,
 	.shost_groups		= host_v3_hw_groups,
 	.sdev_groups		= sdev_groups_v3_hw,
 	.tag_alloc_policy_rr	= true,
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 0c49414c1f35..84d8de07b7ae 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -283,9 +283,10 @@ static int hpsa_scan_finished(struct Scsi_Host *sh,
 static int hpsa_change_queue_depth(struct scsi_device *sdev, int qdepth);
 
 static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd);
-static int hpsa_slave_alloc(struct scsi_device *sdev);
-static int hpsa_slave_configure(struct scsi_device *sdev);
-static void hpsa_slave_destroy(struct scsi_device *sdev);
+static int hpsa_sdev_init(struct scsi_device *sdev);
+static int hpsa_sdev_configure(struct scsi_device *sdev,
+			       struct queue_limits *lim);
+static void hpsa_sdev_destroy(struct scsi_device *sdev);
 
 static void hpsa_update_scsi_devices(struct ctlr_info *h);
 static int check_for_unit_attention(struct ctlr_info *h,
@@ -978,9 +979,9 @@ static const struct scsi_host_template hpsa_driver_template = {
 	.this_id		= -1,
 	.eh_device_reset_handler = hpsa_eh_device_reset_handler,
 	.ioctl			= hpsa_ioctl,
-	.slave_alloc		= hpsa_slave_alloc,
-	.slave_configure	= hpsa_slave_configure,
-	.slave_destroy		= hpsa_slave_destroy,
+	.sdev_init		= hpsa_sdev_init,
+	.sdev_configure		= hpsa_sdev_configure,
+	.sdev_destroy		= hpsa_sdev_destroy,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl		= hpsa_compat_ioctl,
 #endif
@@ -2107,7 +2108,7 @@ static struct hpsa_scsi_dev_t *lookup_hpsa_scsi_dev(struct ctlr_info *h,
 	return NULL;
 }
 
-static int hpsa_slave_alloc(struct scsi_device *sdev)
+static int hpsa_sdev_init(struct scsi_device *sdev)
 {
 	struct hpsa_scsi_dev_t *sd = NULL;
 	unsigned long flags;
@@ -2142,7 +2143,8 @@ static int hpsa_slave_alloc(struct scsi_device *sdev)
 
 /* configure scsi device based on internal per-device structure */
 #define CTLR_TIMEOUT (120 * HZ)
-static int hpsa_slave_configure(struct scsi_device *sdev)
+static int hpsa_sdev_configure(struct scsi_device *sdev,
+			       struct queue_limits *lim)
 {
 	struct hpsa_scsi_dev_t *sd;
 	int queue_depth;
@@ -2173,7 +2175,7 @@ static int hpsa_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
-static void hpsa_slave_destroy(struct scsi_device *sdev)
+static void hpsa_sdev_destroy(struct scsi_device *sdev)
 {
 	struct hpsa_scsi_dev_t *hdev = NULL;
 
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index e889f268601b..21f1d9871a33 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -1151,8 +1151,8 @@ static struct attribute *hptiop_host_attrs[] = {
 
 ATTRIBUTE_GROUPS(hptiop_host);
 
-static int hptiop_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int hptiop_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	if (sdev->type == TYPE_TAPE)
 		lim->max_hw_sectors = 8192;
@@ -1168,7 +1168,7 @@ static const struct scsi_host_template driver_template = {
 	.emulated                   = 0,
 	.proc_name                  = driver_name,
 	.shost_groups		    = hptiop_host_groups,
-	.device_configure	    = hptiop_device_configure,
+	.sdev_configure		    = hptiop_sdev_configure,
 	.this_id                    = -1,
 	.change_queue_depth         = hptiop_adjust_disk_queue_depth,
 	.cmd_size		    = sizeof(struct hpt_cmd_priv),
@@ -1634,7 +1634,7 @@ static struct hptiop_adapter_ops hptiop_mvfrey_ops = {
 	.host_phy_flag     = cpu_to_le64(1),
 };
 
-static struct pci_device_id hptiop_id_table[] = {
+static const struct pci_device_id hptiop_id_table[] = {
 	{ PCI_VDEVICE(TTI, 0x3220), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x3320), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x3410), (kernel_ulong_t)&hptiop_itl_ops },
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index e66c3ef74267..773ec2f31bc4 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3393,7 +3393,7 @@ static int ibmvfc_scan_finished(struct Scsi_Host *shost, unsigned long time)
 }
 
 /**
- * ibmvfc_slave_alloc - Setup the device's task set value
+ * ibmvfc_sdev_init - Setup the device's task set value
  * @sdev:	struct scsi_device device to configure
  *
  * Set the device's task set value so that error handling works as
@@ -3402,7 +3402,7 @@ static int ibmvfc_scan_finished(struct Scsi_Host *shost, unsigned long time)
  * Returns:
  *	0 on success / -ENXIO if device does not exist
  **/
-static int ibmvfc_slave_alloc(struct scsi_device *sdev)
+static int ibmvfc_sdev_init(struct scsi_device *sdev)
 {
 	struct Scsi_Host *shost = sdev->host;
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
@@ -3441,8 +3441,9 @@ static int ibmvfc_target_alloc(struct scsi_target *starget)
 }
 
 /**
- * ibmvfc_slave_configure - Configure the device
+ * ibmvfc_sdev_configure - Configure the device
  * @sdev:	struct scsi_device device to configure
+ * @lim:	Request queue limits
  *
  * Enable allow_restart for a device if it is a disk. Adjust the
  * queue_depth here also.
@@ -3450,7 +3451,8 @@ static int ibmvfc_target_alloc(struct scsi_target *starget)
  * Returns:
  *	0
  **/
-static int ibmvfc_slave_configure(struct scsi_device *sdev)
+static int ibmvfc_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	struct Scsi_Host *shost = sdev->host;
 	unsigned long flags = 0;
@@ -3639,7 +3641,7 @@ static DEVICE_ATTR(nr_scsi_channels, S_IRUGO | S_IWUSR,
  *	number of bytes printed to buffer
  **/
 static ssize_t ibmvfc_read_trace(struct file *filp, struct kobject *kobj,
-				 struct bin_attribute *bin_attr,
+				 const struct bin_attribute *bin_attr,
 				 char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -3662,13 +3664,13 @@ static ssize_t ibmvfc_read_trace(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute ibmvfc_trace_attr = {
+static const struct bin_attribute ibmvfc_trace_attr = {
 	.attr =	{
 		.name = "trace",
 		.mode = S_IRUGO,
 	},
 	.size = 0,
-	.read = ibmvfc_read_trace,
+	.read_new = ibmvfc_read_trace,
 };
 #endif
 
@@ -3696,8 +3698,8 @@ static const struct scsi_host_template driver_template = {
 	.eh_device_reset_handler = ibmvfc_eh_device_reset_handler,
 	.eh_target_reset_handler = ibmvfc_eh_target_reset_handler,
 	.eh_host_reset_handler = ibmvfc_eh_host_reset_handler,
-	.slave_alloc = ibmvfc_slave_alloc,
-	.slave_configure = ibmvfc_slave_configure,
+	.sdev_init = ibmvfc_sdev_init,
+	.sdev_configure = ibmvfc_sdev_configure,
 	.target_alloc = ibmvfc_target_alloc,
 	.scan_finished = ibmvfc_scan_finished,
 	.change_queue_depth = ibmvfc_change_queue_depth,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 71f3e9563520..16a1aac11911 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -1860,14 +1860,16 @@ static void ibmvscsi_handle_crq(struct viosrp_crq *crq,
 }
 
 /**
- * ibmvscsi_slave_configure: Set the "allow_restart" flag for each disk.
+ * ibmvscsi_sdev_configure: Set the "allow_restart" flag for each disk.
  * @sdev:	struct scsi_device device to configure
+ * @lim:	Request queue limits
  *
  * Enable allow_restart for a device if it is a disk.  Adjust the
  * queue_depth here also as is required by the documentation for
  * struct scsi_host_template.
  */
-static int ibmvscsi_slave_configure(struct scsi_device *sdev)
+static int ibmvscsi_sdev_configure(struct scsi_device *sdev,
+				   struct queue_limits *lim)
 {
 	struct Scsi_Host *shost = sdev->host;
 	unsigned long lock_flags = 0;
@@ -2091,7 +2093,7 @@ static struct scsi_host_template driver_template = {
 	.eh_abort_handler = ibmvscsi_eh_abort_handler,
 	.eh_device_reset_handler = ibmvscsi_eh_device_reset_handler,
 	.eh_host_reset_handler = ibmvscsi_eh_host_reset_handler,
-	.slave_configure = ibmvscsi_slave_configure,
+	.sdev_configure = ibmvscsi_sdev_configure,
 	.change_queue_depth = ibmvscsi_change_queue_depth,
 	.host_reset = ibmvscsi_host_reset,
 	.cmd_per_lun = IBMVSCSI_CMDS_PER_LUN_DEFAULT,
diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index 625fd547ee60..8648bd965287 100644
--- a/drivers/scsi/initio.c
+++ b/drivers/scsi/initio.c
@@ -2941,7 +2941,7 @@ static void initio_remove_one(struct pci_dev *pdev)
 
 MODULE_LICENSE("GPL");
 
-static struct pci_device_id initio_pci_tbl[] = {
+static const struct pci_device_id initio_pci_tbl[] = {
 	{PCI_VENDOR_ID_INIT, 0x9500, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{PCI_VENDOR_ID_INIT, 0x9400, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{PCI_VENDOR_ID_INIT, 0x9401, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 31cf2d31cceb..3bfafd43e42a 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -3366,7 +3366,7 @@ static void ipr_worker_thread(struct work_struct *work)
  *	number of bytes printed to buffer
  **/
 static ssize_t ipr_read_trace(struct file *filp, struct kobject *kobj,
-			      struct bin_attribute *bin_attr,
+			      const struct bin_attribute *bin_attr,
 			      char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -3383,13 +3383,13 @@ static ssize_t ipr_read_trace(struct file *filp, struct kobject *kobj,
 	return ret;
 }
 
-static struct bin_attribute ipr_trace_attr = {
+static const struct bin_attribute ipr_trace_attr = {
 	.attr =	{
 		.name = "trace",
 		.mode = S_IRUGO,
 	},
 	.size = 0,
-	.read = ipr_read_trace,
+	.read_new = ipr_read_trace,
 };
 #endif
 
@@ -4087,7 +4087,7 @@ static struct device_attribute ipr_ioa_fw_type_attr = {
 };
 
 static ssize_t ipr_read_async_err_log(struct file *filep, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
+				const struct bin_attribute *bin_attr, char *buf,
 				loff_t off, size_t count)
 {
 	struct device *cdev = kobj_to_dev(kobj);
@@ -4111,7 +4111,7 @@ static ssize_t ipr_read_async_err_log(struct file *filep, struct kobject *kobj,
 }
 
 static ssize_t ipr_next_async_err_log(struct file *filep, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
+				const struct bin_attribute *bin_attr, char *buf,
 				loff_t off, size_t count)
 {
 	struct device *cdev = kobj_to_dev(kobj);
@@ -4134,14 +4134,14 @@ static ssize_t ipr_next_async_err_log(struct file *filep, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute ipr_ioa_async_err_log = {
+static const struct bin_attribute ipr_ioa_async_err_log = {
 	.attr = {
 		.name =		"async_err_log",
 		.mode =		S_IRUGO | S_IWUSR,
 	},
 	.size = 0,
-	.read = ipr_read_async_err_log,
-	.write = ipr_next_async_err_log
+	.read_new = ipr_read_async_err_log,
+	.write_new = ipr_next_async_err_log
 };
 
 static struct attribute *ipr_ioa_attrs[] = {
@@ -4172,7 +4172,7 @@ ATTRIBUTE_GROUPS(ipr_ioa);
  *	number of bytes printed to buffer
  **/
 static ssize_t ipr_read_dump(struct file *filp, struct kobject *kobj,
-			     struct bin_attribute *bin_attr,
+			     const struct bin_attribute *bin_attr,
 			     char *buf, loff_t off, size_t count)
 {
 	struct device *cdev = kobj_to_dev(kobj);
@@ -4361,7 +4361,7 @@ static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg)
  *	number of bytes printed to buffer
  **/
 static ssize_t ipr_write_dump(struct file *filp, struct kobject *kobj,
-			      struct bin_attribute *bin_attr,
+			      const struct bin_attribute *bin_attr,
 			      char *buf, loff_t off, size_t count)
 {
 	struct device *cdev = kobj_to_dev(kobj);
@@ -4385,14 +4385,14 @@ static ssize_t ipr_write_dump(struct file *filp, struct kobject *kobj,
 		return count;
 }
 
-static struct bin_attribute ipr_dump_attr = {
+static const struct bin_attribute ipr_dump_attr = {
 	.attr =	{
 		.name = "dump",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 0,
-	.read = ipr_read_dump,
-	.write = ipr_write_dump
+	.read_new = ipr_read_dump,
+	.write_new = ipr_write_dump
 };
 #else
 static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) { return 0; };
@@ -4745,13 +4745,13 @@ static struct ipr_resource_entry *ipr_find_sdev(struct scsi_device *sdev)
 }
 
 /**
- * ipr_slave_destroy - Unconfigure a SCSI device
+ * ipr_sdev_destroy - Unconfigure a SCSI device
  * @sdev:	scsi device struct
  *
  * Return value:
  * 	nothing
  **/
-static void ipr_slave_destroy(struct scsi_device *sdev)
+static void ipr_sdev_destroy(struct scsi_device *sdev)
 {
 	struct ipr_resource_entry *res;
 	struct ipr_ioa_cfg *ioa_cfg;
@@ -4769,7 +4769,7 @@ static void ipr_slave_destroy(struct scsi_device *sdev)
 }
 
 /**
- * ipr_device_configure - Configure a SCSI device
+ * ipr_sdev_configure - Configure a SCSI device
  * @sdev:	scsi device struct
  * @lim:	queue limits
  *
@@ -4778,8 +4778,8 @@ static void ipr_slave_destroy(struct scsi_device *sdev)
  * Return value:
  * 	0 on success
  **/
-static int ipr_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int ipr_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) sdev->host->hostdata;
 	struct ipr_resource_entry *res;
@@ -4815,7 +4815,7 @@ static int ipr_device_configure(struct scsi_device *sdev,
 }
 
 /**
- * ipr_slave_alloc - Prepare for commands to a device.
+ * ipr_sdev_init - Prepare for commands to a device.
  * @sdev:	scsi device struct
  *
  * This function saves a pointer to the resource entry
@@ -4826,7 +4826,7 @@ static int ipr_device_configure(struct scsi_device *sdev,
  * Return value:
  * 	0 on success / -ENXIO if device does not exist
  **/
-static int ipr_slave_alloc(struct scsi_device *sdev)
+static int ipr_sdev_init(struct scsi_device *sdev)
 {
 	struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) sdev->host->hostdata;
 	struct ipr_resource_entry *res;
@@ -6398,9 +6398,9 @@ static const struct scsi_host_template driver_template = {
 	.eh_abort_handler = ipr_eh_abort,
 	.eh_device_reset_handler = ipr_eh_dev_reset,
 	.eh_host_reset_handler = ipr_eh_host_reset,
-	.slave_alloc = ipr_slave_alloc,
-	.device_configure = ipr_device_configure,
-	.slave_destroy = ipr_slave_destroy,
+	.sdev_init = ipr_sdev_init,
+	.sdev_configure = ipr_sdev_configure,
+	.sdev_destroy = ipr_sdev_destroy,
 	.scan_finished = ipr_scan_finished,
 	.target_destroy = ipr_target_destroy,
 	.change_queue_depth = ipr_change_queue_depth,
@@ -9844,7 +9844,7 @@ static void ipr_shutdown(struct pci_dev *pdev)
 	}
 }
 
-static struct pci_device_id ipr_pci_table[] = {
+static const struct pci_device_id ipr_pci_table[] = {
 	{ PCI_VENDOR_ID_MYLEX, PCI_DEVICE_ID_IBM_GEMSTONE,
 		PCI_VENDOR_ID_IBM, IPR_SUBS_DEV_ID_5702, 0, 0, 0 },
 	{ PCI_VENDOR_ID_MYLEX, PCI_DEVICE_ID_IBM_GEMSTONE,
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 10cf5775a939..cce6c6b409ad 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -364,7 +364,7 @@ static struct scsi_host_template ips_driver_template = {
 	.proc_name		= "ips",
 	.show_info		= ips_show_info,
 	.write_info		= ips_write_info,
-	.slave_configure	= ips_slave_configure,
+	.sdev_configure		= ips_sdev_configure,
 	.bios_param		= ips_biosparam,
 	.this_id		= -1,
 	.sg_tablesize		= IPS_MAX_SG,
@@ -1166,7 +1166,7 @@ static int ips_biosparam(struct scsi_device *sdev, struct block_device *bdev,
 
 /****************************************************************************/
 /*                                                                          */
-/* Routine Name: ips_slave_configure                                        */
+/* Routine Name: ips_sdev_configure                                         */
 /*                                                                          */
 /* Routine Description:                                                     */
 /*                                                                          */
@@ -1174,7 +1174,7 @@ static int ips_biosparam(struct scsi_device *sdev, struct block_device *bdev,
 /*                                                                          */
 /****************************************************************************/
 static int
-ips_slave_configure(struct scsi_device * SDptr)
+ips_sdev_configure(struct scsi_device *SDptr, struct queue_limits *lim)
 {
 	ips_ha_t *ha;
 	int min;
diff --git a/drivers/scsi/ips.h b/drivers/scsi/ips.h
index 65edf000e447..8ac932ec4444 100644
--- a/drivers/scsi/ips.h
+++ b/drivers/scsi/ips.h
@@ -400,7 +400,8 @@
     */
    static int ips_biosparam(struct scsi_device *sdev, struct block_device *bdev,
 		sector_t capacity, int geom[]);
-   static int ips_slave_configure(struct scsi_device *SDptr);
+   static int ips_sdev_configure(struct scsi_device *SDptr,
+				 struct queue_limits *lim);
 
 /*
  * Raid Command Formats
diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c
index 866950a02965..287e1ba8ddd7 100644
--- a/drivers/scsi/isci/remote_device.c
+++ b/drivers/scsi/isci/remote_device.c
@@ -422,21 +422,6 @@ enum sci_status sci_remote_device_reset(struct isci_remote_device *idev)
 	}
 }
 
-enum sci_status sci_remote_device_reset_complete(struct isci_remote_device *idev)
-{
-	struct sci_base_state_machine *sm = &idev->sm;
-	enum sci_remote_device_states state = sm->current_state_id;
-
-	if (state != SCI_DEV_RESETTING) {
-		dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %s\n",
-			 __func__, dev_state_name(state));
-		return SCI_FAILURE_INVALID_STATE;
-	}
-
-	sci_change_state(sm, SCI_DEV_READY);
-	return SCI_SUCCESS;
-}
-
 enum sci_status sci_remote_device_frame_handler(struct isci_remote_device *idev,
 						     u32 frame_index)
 {
@@ -1694,20 +1679,6 @@ enum sci_status sci_remote_device_abort_requests_pending_abort(
 	return sci_remote_device_terminate_reqs_checkabort(idev, 1);
 }
 
-enum sci_status isci_remote_device_reset_complete(
-	struct isci_host *ihost,
-	struct isci_remote_device *idev)
-{
-	unsigned long flags;
-	enum sci_status status;
-
-	spin_lock_irqsave(&ihost->scic_lock, flags);
-	status = sci_remote_device_reset_complete(idev);
-	spin_unlock_irqrestore(&ihost->scic_lock, flags);
-
-	return status;
-}
-
 void isci_dev_set_hang_detection_timeout(
 	struct isci_remote_device *idev,
 	u32 timeout)
diff --git a/drivers/scsi/isci/remote_device.h b/drivers/scsi/isci/remote_device.h
index 3ad681c4c20a..27ae45332704 100644
--- a/drivers/scsi/isci/remote_device.h
+++ b/drivers/scsi/isci/remote_device.h
@@ -175,19 +175,6 @@ enum sci_status sci_remote_device_reset(
 	struct isci_remote_device *idev);
 
 /**
- * sci_remote_device_reset_complete() - This method informs the device object
- *    that the reset operation is complete and the device can resume operation
- *    again.
- * @remote_device: This parameter specifies the device which is to be informed
- *    of the reset complete operation.
- *
- * An indication that the device is resuming operation. SCI_SUCCESS the device
- * is resuming operation.
- */
-enum sci_status sci_remote_device_reset_complete(
-	struct isci_remote_device *idev);
-
-/**
  * enum sci_remote_device_states - This enumeration depicts all the states
  *    for the common remote device state machine.
  * @SCI_DEV_INITIAL: Simply the initial state for the base remote device
@@ -364,10 +351,6 @@ enum sci_status isci_remote_device_reset(
 	struct isci_host *ihost,
 	struct isci_remote_device *idev);
 
-enum sci_status isci_remote_device_reset_complete(
-	struct isci_host *ihost,
-	struct isci_remote_device *idev);
-
 enum sci_status isci_remote_device_suspend_terminate(
 	struct isci_host *ihost,
 	struct isci_remote_device *idev,
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index c708e1059638..e81f60985193 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -1057,8 +1057,8 @@ static umode_t iscsi_sw_tcp_attr_is_visible(int param_type, int param)
 	return 0;
 }
 
-static int iscsi_sw_tcp_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int iscsi_sw_tcp_sdev_configure(struct scsi_device *sdev,
+				       struct queue_limits *lim)
 {
 	struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(sdev->host);
 	struct iscsi_session *session = tcp_sw_host->session;
@@ -1083,7 +1083,7 @@ static const struct scsi_host_template iscsi_sw_tcp_sht = {
 	.eh_device_reset_handler= iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
 	.dma_boundary		= PAGE_SIZE - 1,
-	.device_configure	= iscsi_sw_tcp_device_configure,
+	.sdev_configure		= iscsi_sw_tcp_sdev_configure,
 	.proc_name		= "iscsi_tcp",
 	.this_id		= -1,
 	.track_queue_depth	= 1,
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index 80be3a936d92..fd1ef06655cb 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -2222,13 +2222,13 @@ int fc_eh_host_reset(struct scsi_cmnd *sc_cmd)
 EXPORT_SYMBOL(fc_eh_host_reset);
 
 /**
- * fc_slave_alloc() - Configure the queue depth of a Scsi_Host
+ * fc_sdev_init() - Configure the queue depth of a Scsi_Host
  * @sdev: The SCSI device that identifies the SCSI host
  *
  * Configures queue depth based on host's cmd_per_len. If not set
  * then we use the libfc default.
  */
-int fc_slave_alloc(struct scsi_device *sdev)
+int fc_sdev_init(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 
@@ -2238,7 +2238,7 @@ int fc_slave_alloc(struct scsi_device *sdev)
 	scsi_change_queue_depth(sdev, FC_FCP_DFLT_QUEUE_DEPTH);
 	return 0;
 }
-EXPORT_SYMBOL(fc_slave_alloc);
+EXPORT_SYMBOL(fc_sdev_init);
 
 /**
  * fc_fcp_destroy() - Tear down the FCP layer for a given local port
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index da11d32840e2..55ce7892f217 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -804,15 +804,14 @@ EXPORT_SYMBOL_GPL(sas_target_alloc);
 
 #define SAS_DEF_QD 256
 
-int sas_device_configure(struct scsi_device *scsi_dev,
-		struct queue_limits *lim)
+int sas_sdev_configure(struct scsi_device *scsi_dev, struct queue_limits *lim)
 {
 	struct domain_device *dev = sdev_to_domain_dev(scsi_dev);
 
 	BUG_ON(dev->rphy->identify.device_type != SAS_END_DEVICE);
 
 	if (dev_is_sata(dev)) {
-		ata_sas_device_configure(scsi_dev, lim, dev->sata_dev.ap);
+		ata_sas_sdev_configure(scsi_dev, lim, dev->sata_dev.ap);
 		return 0;
 	}
 
@@ -830,7 +829,7 @@ int sas_device_configure(struct scsi_device *scsi_dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sas_device_configure);
+EXPORT_SYMBOL_GPL(sas_sdev_configure);
 
 int sas_change_queue_depth(struct scsi_device *sdev, int depth)
 {
@@ -1194,14 +1193,14 @@ void sas_task_abort(struct sas_task *task)
 }
 EXPORT_SYMBOL_GPL(sas_task_abort);
 
-int sas_slave_alloc(struct scsi_device *sdev)
+int sas_sdev_init(struct scsi_device *sdev)
 {
 	if (dev_is_sata(sdev_to_domain_dev(sdev)) && sdev->lun)
 		return -ENXIO;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sas_slave_alloc);
+EXPORT_SYMBOL_GPL(sas_sdev_init);
 
 void sas_target_destroy(struct scsi_target *starget)
 {
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 39b504164ecc..0d0213bba35d 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -6185,7 +6185,7 @@ const struct attribute_group *lpfc_vport_groups[] = {
  **/
 static ssize_t
 sysfs_ctlreg_write(struct file *filp, struct kobject *kobj,
-		   struct bin_attribute *bin_attr,
+		   const struct bin_attribute *bin_attr,
 		   char *buf, loff_t off, size_t count)
 {
 	size_t buf_off;
@@ -6244,7 +6244,7 @@ sysfs_ctlreg_write(struct file *filp, struct kobject *kobj,
  **/
 static ssize_t
 sysfs_ctlreg_read(struct file *filp, struct kobject *kobj,
-		  struct bin_attribute *bin_attr,
+		  const struct bin_attribute *bin_attr,
 		  char *buf, loff_t off, size_t count)
 {
 	size_t buf_off;
@@ -6280,14 +6280,14 @@ sysfs_ctlreg_read(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_ctlreg_attr = {
+static const struct bin_attribute sysfs_ctlreg_attr = {
 	.attr = {
 		.name = "ctlreg",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 256,
-	.read = sysfs_ctlreg_read,
-	.write = sysfs_ctlreg_write,
+	.read_new = sysfs_ctlreg_read,
+	.write_new = sysfs_ctlreg_write,
 };
 
 /**
@@ -6308,7 +6308,7 @@ static struct bin_attribute sysfs_ctlreg_attr = {
  **/
 static ssize_t
 sysfs_mbox_write(struct file *filp, struct kobject *kobj,
-		 struct bin_attribute *bin_attr,
+		 const struct bin_attribute *bin_attr,
 		 char *buf, loff_t off, size_t count)
 {
 	return -EPERM;
@@ -6332,20 +6332,20 @@ sysfs_mbox_write(struct file *filp, struct kobject *kobj,
  **/
 static ssize_t
 sysfs_mbox_read(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *bin_attr,
+		const struct bin_attribute *bin_attr,
 		char *buf, loff_t off, size_t count)
 {
 	return -EPERM;
 }
 
-static struct bin_attribute sysfs_mbox_attr = {
+static const struct bin_attribute sysfs_mbox_attr = {
 	.attr = {
 		.name = "mbox",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = MAILBOX_SYSFS_MAX,
-	.read = sysfs_mbox_read,
-	.write = sysfs_mbox_write,
+	.read_new = sysfs_mbox_read,
+	.write_new = sysfs_mbox_write,
 };
 
 /**
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index 1c6b024160da..c8f8496bbdf8 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -120,6 +120,16 @@ enum ELX_LOOPBACK_CMD {
 #define ELX_LOOPBACK_HEADER_SZ \
 	(size_t)(&((struct lpfc_sli_ct_request *)NULL)->un)
 
+/* For non-embedded read object command */
+#define READ_OBJ_EMB0_SCHEME_0 {1, 10, 256, 128}
+#define READ_OBJ_EMB0_SCHEME_1 {11, LPFC_EMB0_MAX_RD_OBJ_HBD_CNT, 512, 192}
+static const struct lpfc_read_object_cmd_scheme {
+	u32 min_hbd_cnt;
+	u32 max_hbd_cnt;
+	u32 cmd_size;
+	u32 payload_word_offset;
+}  rd_obj_scheme[2] = {READ_OBJ_EMB0_SCHEME_0, READ_OBJ_EMB0_SCHEME_1};
+
 struct lpfc_dmabufext {
 	struct lpfc_dmabuf dma;
 	uint32_t size;
@@ -3539,6 +3549,103 @@ lpfc_bsg_mbox_ext_session_reset(struct lpfc_hba *phba)
 }
 
 /**
+ * lpfc_rd_obj_emb0_handle_job - Handles completion for non-embedded
+ *                               READ_OBJECT_V0 mailbox commands
+ * @phba: pointer to lpfc_hba data struct
+ * @pmb_buf: pointer to mailbox buffer
+ * @sli_cfg_mbx: pointer to SLI_CONFIG mailbox memory region
+ * @job: pointer to bsg_job struct
+ * @bsg_reply: point to bsg_reply struct
+ *
+ * Given a non-embedded READ_OBJECT_V0's HBD_CNT, this routine copies
+ * a READ_OBJECT_V0 mailbox command's read data payload into a bsg_job
+ * structure for passing back to application layer.
+ *
+ * Return codes
+ *      0 - successful
+ *      -EINVAL - invalid HBD_CNT
+ *      -ENODEV - pointer to bsg_job struct is NULL
+ **/
+static int
+lpfc_rd_obj_emb0_handle_job(struct lpfc_hba *phba, u8 *pmb_buf,
+			    struct lpfc_sli_config_mbox *sli_cfg_mbx,
+			    struct bsg_job *job,
+			    struct fc_bsg_reply *bsg_reply)
+{
+	struct lpfc_dmabuf *curr_dmabuf, *next_dmabuf;
+	struct lpfc_sli_config_emb0_subsys *emb0_subsys;
+	u32 hbd_cnt;
+	u32 dma_buf_len;
+	u8 i = 0;
+	size_t extra_bytes;
+	off_t skip = 0;
+
+	if (!job) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2496 NULL job\n");
+		return -ENODEV;
+	}
+
+	if (!bsg_reply) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2498 NULL bsg_reply\n");
+		return -ENODEV;
+	}
+
+	emb0_subsys = &sli_cfg_mbx->un.sli_config_emb0_subsys;
+
+	hbd_cnt = bsg_bf_get(lpfc_emb0_subcmnd_rd_obj_hbd_cnt,
+			     emb0_subsys);
+
+	/* Calculate where the read object's read data payload is located based
+	 * on HBD count scheme.
+	 */
+	if (hbd_cnt >= rd_obj_scheme[0].min_hbd_cnt &&
+	    hbd_cnt <= rd_obj_scheme[0].max_hbd_cnt) {
+		skip = rd_obj_scheme[0].payload_word_offset * 4;
+	} else if (hbd_cnt >= rd_obj_scheme[1].min_hbd_cnt &&
+		   hbd_cnt <= rd_obj_scheme[1].max_hbd_cnt) {
+		skip = rd_obj_scheme[1].payload_word_offset * 4;
+	} else {
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2497 bad hbd_count 0x%08x\n",
+				hbd_cnt);
+		return -EINVAL;
+	}
+
+	/* Copy SLI_CONFIG command and READ_OBJECT response first */
+	bsg_reply->reply_payload_rcv_len =
+		sg_copy_from_buffer(job->reply_payload.sg_list,
+				    job->reply_payload.sg_cnt,
+				    pmb_buf, skip);
+
+	/* Copy data from hbds */
+	list_for_each_entry_safe(curr_dmabuf, next_dmabuf,
+				 &phba->mbox_ext_buf_ctx.ext_dmabuf_list,
+				 list) {
+		dma_buf_len = emb0_subsys->hbd[i].buf_len;
+
+		/* Use sg_copy_buffer to specify a skip offset */
+		extra_bytes = sg_copy_buffer(job->reply_payload.sg_list,
+					     job->reply_payload.sg_cnt,
+					     curr_dmabuf->virt,
+					     dma_buf_len, skip, false);
+
+		bsg_reply->reply_payload_rcv_len += extra_bytes;
+
+		skip += extra_bytes;
+
+		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+				"2499 copied hbd[%d] "
+				"0x%zx bytes\n",
+				i, extra_bytes);
+		i++;
+	}
+
+	return 0;
+}
+
+/**
  * lpfc_bsg_issue_mbox_ext_handle_job - job handler for multi-buffer mbox cmpl
  * @phba: Pointer to HBA context object.
  * @pmboxq: Pointer to mailbox command.
@@ -3551,10 +3658,10 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 {
 	struct bsg_job_data *dd_data;
 	struct bsg_job *job;
-	struct fc_bsg_reply *bsg_reply;
+	struct fc_bsg_reply *bsg_reply = NULL;
 	uint8_t *pmb, *pmb_buf;
 	unsigned long flags;
-	uint32_t size;
+	u32 size, opcode;
 	int rc = 0;
 	struct lpfc_dmabuf *dmabuf;
 	struct lpfc_sli_config_mbox *sli_cfg_mbx;
@@ -3591,6 +3698,24 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 		lpfc_sli_pcimem_bcopy(&pmbx[sizeof(MAILBOX_t)],
 			&pmbx[sizeof(MAILBOX_t)],
 			sli_cfg_mbx->un.sli_config_emb0_subsys.mse[0].buf_len);
+
+		/* Special handling for non-embedded READ_OBJECT */
+		opcode = bsg_bf_get(lpfc_emb0_subcmnd_opcode,
+				    &sli_cfg_mbx->un.sli_config_emb0_subsys);
+		switch (opcode) {
+		case COMN_OPCODE_READ_OBJECT:
+			if (job) {
+				rc = lpfc_rd_obj_emb0_handle_job(phba, pmb_buf,
+								 sli_cfg_mbx,
+								 job,
+								 bsg_reply);
+				bsg_reply->result = rc;
+				goto done;
+			}
+			break;
+		default:
+			break;
+		}
 	}
 
 	/* Complete the job if the job is still active */
@@ -3604,12 +3729,14 @@ lpfc_bsg_issue_mbox_ext_handle_job(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq)
 
 		/* result for successful */
 		bsg_reply->result = 0;
+done:
 
 		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
 				"2937 SLI_CONFIG ext-buffer mailbox command "
 				"(x%x/x%x) complete bsg job done, bsize:%d\n",
 				phba->mbox_ext_buf_ctx.nembType,
-				phba->mbox_ext_buf_ctx.mboxType, size);
+				phba->mbox_ext_buf_ctx.mboxType,
+				job->reply_payload.payload_len);
 		lpfc_idiag_mbxacc_dump_bsg_mbox(phba,
 					phba->mbox_ext_buf_ctx.nembType,
 					phba->mbox_ext_buf_ctx.mboxType,
@@ -3819,14 +3946,16 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job,
 {
 	struct fc_bsg_request *bsg_request = job->request;
 	struct lpfc_sli_config_mbox *sli_cfg_mbx;
+	struct lpfc_sli_config_emb0_subsys *emb0_subsys;
+	struct list_head *ext_dmabuf_list;
 	struct dfc_mbox_req *mbox_req;
 	struct lpfc_dmabuf *curr_dmabuf, *next_dmabuf;
-	uint32_t ext_buf_cnt, ext_buf_index;
+	u32 ext_buf_cnt, ext_buf_index, hbd_cnt;
 	struct lpfc_dmabuf *ext_dmabuf = NULL;
 	struct bsg_job_data *dd_data = NULL;
 	LPFC_MBOXQ_t *pmboxq = NULL;
 	MAILBOX_t *pmb;
-	uint8_t *pmbx;
+	u8 *pmbx, opcode;
 	int rc, i;
 
 	mbox_req =
@@ -3836,8 +3965,9 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job,
 	sli_cfg_mbx = (struct lpfc_sli_config_mbox *)dmabuf->virt;
 
 	if (nemb_tp == nemb_mse) {
+		emb0_subsys = &sli_cfg_mbx->un.sli_config_emb0_subsys;
 		ext_buf_cnt = bsg_bf_get(lpfc_mbox_hdr_mse_cnt,
-			&sli_cfg_mbx->un.sli_config_emb0_subsys.sli_config_hdr);
+			&emb0_subsys->sli_config_hdr);
 		if (ext_buf_cnt > LPFC_MBX_SLI_CONFIG_MAX_MSE) {
 			lpfc_printf_log(phba, KERN_ERR, LOG_LIBDFC,
 					"2945 Handled SLI_CONFIG(mse) rd, "
@@ -3847,6 +3977,57 @@ lpfc_bsg_sli_cfg_read_cmd_ext(struct lpfc_hba *phba, struct bsg_job *job,
 			rc = -ERANGE;
 			goto job_error;
 		}
+
+		/* Special handling for non-embedded READ_OBJECT */
+		opcode = bsg_bf_get(lpfc_emb0_subcmnd_opcode, emb0_subsys);
+		switch (opcode) {
+		case COMN_OPCODE_READ_OBJECT:
+			hbd_cnt = bsg_bf_get(lpfc_emb0_subcmnd_rd_obj_hbd_cnt,
+					     emb0_subsys);
+			lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+					"2449 SLI_CONFIG(mse) rd non-embedded "
+					"hbd count = %d\n",
+					hbd_cnt);
+
+			ext_dmabuf_list =
+					&phba->mbox_ext_buf_ctx.ext_dmabuf_list;
+
+			/* Allocate hbds */
+			for (i = 0; i < hbd_cnt; i++) {
+				ext_dmabuf = lpfc_bsg_dma_page_alloc(phba);
+				if (!ext_dmabuf) {
+					rc = -ENOMEM;
+					goto job_error;
+				}
+				list_add_tail(&ext_dmabuf->list,
+					      ext_dmabuf_list);
+			}
+
+			/* Fill out the physical memory addresses for the
+			 * hbds
+			 */
+			i = 0;
+			list_for_each_entry_safe(curr_dmabuf, next_dmabuf,
+						 ext_dmabuf_list, list) {
+				emb0_subsys->hbd[i].pa_hi =
+					putPaddrHigh(curr_dmabuf->phys);
+				emb0_subsys->hbd[i].pa_lo =
+					putPaddrLow(curr_dmabuf->phys);
+
+				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
+						"2495 SLI_CONFIG(hbd)[%d], "
+						"bufLen:%d, addrHi:x%x, "
+						"addrLo:x%x\n", i,
+						emb0_subsys->hbd[i].buf_len,
+						emb0_subsys->hbd[i].pa_hi,
+						emb0_subsys->hbd[i].pa_lo);
+				i++;
+			}
+			break;
+		default:
+			break;
+		}
+
 		lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
 				"2941 Handled SLI_CONFIG(mse) rd, "
 				"ext_buf_cnt:%d\n", ext_buf_cnt);
@@ -4223,6 +4404,7 @@ lpfc_bsg_handle_sli_cfg_mbox(struct lpfc_hba *phba, struct bsg_job *job,
 			case COMN_OPCODE_GET_CNTL_ATTRIBUTES:
 			case COMN_OPCODE_GET_PROFILE_CONFIG:
 			case COMN_OPCODE_SET_FEATURES:
+			case COMN_OPCODE_READ_OBJECT:
 				lpfc_printf_log(phba, KERN_INFO, LOG_LIBDFC,
 						"3106 Handled SLI_CONFIG "
 						"subsys_comn, opcode:x%x\n",
@@ -4665,8 +4847,7 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct bsg_job *job,
 	bsg_reply->reply_payload_rcv_len = 0;
 
 	/* sanity check to protect driver */
-	if (job->reply_payload.payload_len > BSG_MBOX_SIZE ||
-	    job->request_payload.payload_len > BSG_MBOX_SIZE) {
+	if (job->request_payload.payload_len > BSG_MBOX_SIZE) {
 		rc = -ERANGE;
 		goto job_done;
 	}
@@ -4737,6 +4918,19 @@ lpfc_bsg_issue_mbox(struct lpfc_hba *phba, struct bsg_job *job,
 	pmb->mbxOwner = OWN_HOST;
 	pmboxq->vport = vport;
 
+	/* non-embedded SLI_CONFIG requests already parsed, check others */
+	if (unlikely(job->reply_payload.payload_len > BSG_MBOX_SIZE)) {
+		lpfc_printf_log(phba, KERN_WARNING, LOG_LIBDFC,
+				"2729 Cmd x%x (x%x/x%x) request has "
+				"out-of-range reply payload length x%x\n",
+				pmb->mbxCommand,
+				lpfc_sli_config_mbox_subsys_get(phba, pmboxq),
+				lpfc_sli_config_mbox_opcode_get(phba, pmboxq),
+				job->reply_payload.payload_len);
+		rc = -ERANGE;
+		goto job_done;
+	}
+
 	/* If HBA encountered an error attention, allow only DUMP
 	 * or RESTART mailbox commands until the HBA is restarted.
 	 */
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index 3c04ca2d7455..27e7a033b53d 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2022 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term *
  * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2010-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
@@ -239,12 +239,27 @@ struct lpfc_sli_config_emb0_subsys {
 	uint32_t timeout;		/* comn_set_feature timeout */
 	uint32_t request_length;	/* comn_set_feature request len */
 	uint32_t version;		/* comn_set_feature version */
-	uint32_t csf_feature;		/* comn_set_feature feature */
+	uint32_t word68;		/* comn_set_feature feature */
+#define lpfc_emb0_subcmnd_csf_feat_SHIFT		0
+#define lpfc_emb0_subcmnd_csf_feat_MASK			0xffffffff
+#define lpfc_emb0_subcmnd_csf_feat_WORD			word68
+#define lpfc_emb0_subcmnd_rd_obj_des_rd_len_SHIFT	0
+#define lpfc_emb0_subcmnd_rd_obj_des_rd_len_MASK	0x00ffffff
+#define lpfc_emb0_subcmnd_rd_obj_des_rd_len_WORD	word68
 	uint32_t word69;		/* comn_set_feature parameter len */
 	uint32_t word70;		/* comn_set_feature parameter val0 */
 #define lpfc_emb0_subcmnd_csf_p0_SHIFT	0
 #define lpfc_emb0_subcmnd_csf_p0_MASK	0x3
 #define lpfc_emb0_subcmnd_csf_p0_WORD	word70
+	uint32_t reserved71[25];
+	uint32_t word96;		/* rd_obj hbd_count */
+#define lpfc_emb0_subcmnd_rd_obj_hbd_cnt_SHIFT	0
+#define lpfc_emb0_subcmnd_rd_obj_hbd_cnt_MASK	0xffffffff
+#define lpfc_emb0_subcmnd_rd_obj_hbd_cnt_WORD	word96
+#define LPFC_EMB0_MAX_RD_OBJ_HBD_CNT		31
+	struct lpfc_sli_config_hbd hbd[LPFC_EMB0_MAX_RD_OBJ_HBD_CNT];
+	uint32_t word190;
+	uint32_t word191;
 };
 
 struct lpfc_sli_config_emb1_subsys {
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 30891ad17e2a..12c67cdd7c19 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1646,14 +1646,12 @@ out:
 	/* If the caller wanted a synchronous DA_ID completion, signal the
 	 * wait obj and clear flag to reset the vport.
 	 */
-	if (ndlp->save_flags & NLP_WAIT_FOR_DA_ID) {
+	if (test_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags)) {
 		if (ndlp->da_id_waitq)
 			wake_up(ndlp->da_id_waitq);
 	}
 
-	spin_lock_irq(&ndlp->lock);
-	ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags);
 
 	lpfc_ct_free_iocb(phba, cmdiocb);
 	lpfc_nlp_put(ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 3e173b5d00e0..3d47dc7458d1 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -85,13 +85,13 @@ enum lpfc_fc4_xpt_flags {
 	NLP_XPT_HAS_HH		= 0x10
 };
 
-enum lpfc_nlp_save_flags {
+enum lpfc_nlp_save_flags { /* mask bits */
 	/* devloss occurred during recovery */
-	NLP_IN_RECOV_POST_DEV_LOSS	= 0x1,
+	NLP_IN_RECOV_POST_DEV_LOSS,
 	/* wait for outstanding LOGO to cmpl */
-	NLP_WAIT_FOR_LOGO		= 0x2,
+	NLP_WAIT_FOR_LOGO,
 	/* wait for outstanding DA_ID to finish */
-	NLP_WAIT_FOR_DA_ID              = 0x4
+	NLP_WAIT_FOR_DA_ID
 };
 
 struct lpfc_nodelist {
@@ -154,7 +154,7 @@ struct lpfc_nodelist {
 	uint32_t fc4_prli_sent;
 
 	/* flags to keep ndlp alive until special conditions are met */
-	enum lpfc_nlp_save_flags save_flags;
+	unsigned long save_flags;
 
 	enum lpfc_fc4_xpt_flags fc4_xpt_flags;
 
@@ -208,7 +208,6 @@ enum lpfc_nlp_flag {
 					   NPR list */
 	NLP_RM_DFLT_RPI    = 26,        /* need to remove leftover dflt RPI */
 	NLP_NODEV_REMOVE   = 27,        /* Defer removal till discovery ends */
-	NLP_TARGET_REMOVE  = 28,        /* Target remove in process */
 	NLP_SC_REQ         = 29,        /* Target requires authentication */
 	NLP_FIRSTBURST     = 30,        /* Target supports FirstBurst */
 	NLP_RPI_REGISTERED = 31         /* nlp_rpi is valid */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 37f0a930d469..1d7db49a8fe4 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2988,12 +2988,8 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	}
 
 	clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
-	spin_lock_irq(&ndlp->lock);
-	if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) {
+	if (test_and_clear_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags))
 		wake_up_waiter = 1;
-		ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
-	}
-	spin_unlock_irq(&ndlp->lock);
 
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"LOGO cmpl:       status:x%x/x%x did:x%x",
@@ -3035,19 +3031,6 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	/* Call state machine. This will unregister the rpi if needed. */
 	lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_CMPL_LOGO);
 
-	if (skip_recovery)
-		goto out;
-
-	/* The driver sets this flag for an NPIV instance that doesn't want to
-	 * log into the remote port.
-	 */
-	if (test_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag)) {
-		clear_bit(NLP_NPR_2B_DISC, &ndlp->nlp_flag);
-		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
-					NLP_EVT_DEVICE_RM);
-		goto out_rsrc_free;
-	}
-
 out:
 	/* At this point, the LOGO processing is complete. NOTE: For a
 	 * pt2pt topology, we are assuming the NPortID will only change
@@ -3091,7 +3074,7 @@ out:
 		lpfc_disc_state_machine(vport, ndlp, cmdiocb,
 					NLP_EVT_DEVICE_RM);
 	}
-out_rsrc_free:
+
 	/* Driver is done with the I/O. */
 	lpfc_els_free_iocb(phba, cmdiocb);
 	lpfc_nlp_put(ndlp);
@@ -4583,6 +4566,7 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 	int link_reset = 0, rc;
 	u32 ulp_status = get_job_ulpstatus(phba, rspiocb);
 	u32 ulp_word4 = get_job_word4(phba, rspiocb);
+	u8 rsn_code_exp = 0;
 
 
 	/* Note: cmd_dmabuf may be 0 for internal driver abort
@@ -4798,11 +4782,22 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 			break;
 
 		case LSRJT_LOGICAL_BSY:
+			rsn_code_exp = stat.un.b.lsRjtRsnCodeExp;
 			if ((cmd == ELS_CMD_PLOGI) ||
 			    (cmd == ELS_CMD_PRLI) ||
 			    (cmd == ELS_CMD_NVMEPRLI)) {
 				delay = 1000;
 				maxretry = 48;
+
+				/* An authentication LS_RJT reason code
+				 * explanation means some error in the
+				 * security settings end-to-end.  Reduce
+				 * the retry count to allow lpfc to clear
+				 * RSCN mode and not race with dev_loss.
+				 */
+				if (cmd == ELS_CMD_PLOGI &&
+				    rsn_code_exp == LSEXP_AUTH_REQ)
+					maxretry = 8;
 			} else if (cmd == ELS_CMD_FDISC) {
 				/* FDISC retry policy */
 				maxretry = 48;
@@ -4831,6 +4826,20 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 					      "0820 FLOGI (x%x). "
 					      "BBCredit Not Supported\n",
 					      stat.un.lsRjtError);
+			} else if (cmd == ELS_CMD_PLOGI) {
+				rsn_code_exp = stat.un.b.lsRjtRsnCodeExp;
+
+				/* An authentication LS_RJT reason code
+				 * explanation means some error in the
+				 * security settings end-to-end.  Reduce
+				 * the retry count to allow lpfc to clear
+				 * RSCN mode and not race with dev_loss.
+				 */
+				if (rsn_code_exp == LSEXP_AUTH_REQ) {
+					delay = 1000;
+					retry = 1;
+					maxretry = 8;
+				}
 			}
 			break;
 
@@ -10411,8 +10420,6 @@ lpfc_els_unsol_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 			}
 		}
 
-		clear_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag);
-
 		lpfc_disc_state_machine(vport, ndlp, elsiocb,
 					NLP_EVT_RCV_PLOGI);
 
@@ -11498,15 +11505,13 @@ lpfc_cmpl_els_npiv_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		lpfc_can_disctmo(vport);
 	}
 
-	if (ndlp->save_flags & NLP_WAIT_FOR_LOGO) {
+	if (test_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags)) {
 		/* Wake up lpfc_vport_delete if waiting...*/
 		if (ndlp->logo_waitq)
 			wake_up(ndlp->logo_waitq);
 		clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
 		clear_bit(NLP_LOGO_SND, &ndlp->nlp_flag);
-		spin_lock_irq(&ndlp->lock);
-		ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
-		spin_unlock_irq(&ndlp->lock);
+		clear_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags);
 	}
 
 	/* Safe to release resources now. */
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 4036a9838bb5..36e66df36a18 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -414,12 +414,7 @@ void
 lpfc_check_nlp_post_devloss(struct lpfc_vport *vport,
 			    struct lpfc_nodelist *ndlp)
 {
-	unsigned long iflags;
-
-	spin_lock_irqsave(&ndlp->lock, iflags);
-	if (ndlp->save_flags & NLP_IN_RECOV_POST_DEV_LOSS) {
-		ndlp->save_flags &= ~NLP_IN_RECOV_POST_DEV_LOSS;
-		spin_unlock_irqrestore(&ndlp->lock, iflags);
+	if (test_and_clear_bit(NLP_IN_RECOV_POST_DEV_LOSS, &ndlp->save_flags)) {
 		lpfc_nlp_get(ndlp);
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE,
 				 "8438 Devloss timeout reversed on DID x%x "
@@ -427,9 +422,7 @@ lpfc_check_nlp_post_devloss(struct lpfc_vport *vport,
 				 "port_state = x%x\n",
 				 ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp,
 				 ndlp->nlp_flag, vport->port_state);
-		return;
 	}
-	spin_unlock_irqrestore(&ndlp->lock, iflags);
 }
 
 /**
@@ -546,9 +539,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp)
 					 ndlp->nlp_DID, kref_read(&ndlp->kref),
 					 ndlp, ndlp->nlp_flag,
 					 vport->port_state);
-			spin_lock_irqsave(&ndlp->lock, iflags);
-			ndlp->save_flags |= NLP_IN_RECOV_POST_DEV_LOSS;
-			spin_unlock_irqrestore(&ndlp->lock, iflags);
+			set_bit(NLP_IN_RECOV_POST_DEV_LOSS, &ndlp->save_flags);
 			return fcf_inuse;
 		} else if (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) {
 			/* Fabric node fully recovered before this dev_loss_tmo
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index d5c15742f7f2..32298285ea5e 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017-2023 Broadcom. All Rights Reserved. The term *
+ * Copyright (C) 2017-2024 Broadcom. All Rights Reserved. The term *
  * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
@@ -724,6 +724,7 @@ struct ls_rjt {	/* Structure is in Big Endian format */
 #define LSEXP_OUT_OF_RESOURCE   0x29
 #define LSEXP_CANT_GIVE_DATA    0x2A
 #define LSEXP_REQ_UNSUPPORTED   0x2C
+#define LSEXP_AUTH_REQ          0x48
 #define LSEXP_NO_RSRC_ASSIGN    0x52
 			uint8_t vendorUnique;	/* FC Word 0, bit  0: 7 */
 		} b;
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 26e1313ebb21..2dedb273b091 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1907,22 +1907,22 @@ struct lpfc_mbx_query_fw_config {
 		uint32_t asic_revision;
 		uint32_t physical_port;
 		uint32_t function_mode;
-#define LPFC_FCOE_INI_MODE	0x00000040
-#define LPFC_FCOE_TGT_MODE	0x00000080
+#define LPFC_FC_INI_MODE	0x00000040
+#define LPFC_FC_TGT_MODE	0x00000080
 #define LPFC_DUA_MODE		0x00000800
-		uint32_t ulp0_mode;
-#define LPFC_ULP_FCOE_INIT_MODE	0x00000040
-#define LPFC_ULP_FCOE_TGT_MODE	0x00000080
-		uint32_t ulp0_nap_words[12];
-		uint32_t ulp1_mode;
-		uint32_t ulp1_nap_words[12];
+		uint32_t oper_mode;
+		uint32_t rsvd9[2];
+		uint32_t wqid_base;
+		uint32_t wqid_tot;
+		uint32_t rqid_base;
+		uint32_t rqid_tot;
+		uint32_t rsvd15[19];
 		uint32_t function_capabilities;
 		uint32_t cqid_base;
 		uint32_t cqid_tot;
 		uint32_t eqid_base;
 		uint32_t eqid_tot;
-		uint32_t ulp0_nap2_words[2];
-		uint32_t ulp1_nap2_words[2];
+		uint32_t rsvd39[4];
 	} rsp;
 };
 
@@ -3778,25 +3778,22 @@ struct lpfc_mbx_get_prof_cfg {
 struct lpfc_controller_attribute {
 	uint32_t version_string[8];
 	uint32_t manufacturer_name[8];
-	uint32_t supported_modes;
+	uint32_t rsvd16;
 	uint32_t word17;
-#define lpfc_cntl_attr_eprom_ver_lo_SHIFT	0
-#define lpfc_cntl_attr_eprom_ver_lo_MASK	0x000000ff
-#define lpfc_cntl_attr_eprom_ver_lo_WORD	word17
-#define lpfc_cntl_attr_eprom_ver_hi_SHIFT	8
-#define lpfc_cntl_attr_eprom_ver_hi_MASK	0x000000ff
-#define lpfc_cntl_attr_eprom_ver_hi_WORD	word17
 #define lpfc_cntl_attr_flash_id_SHIFT		16
 #define lpfc_cntl_attr_flash_id_MASK		0x000000ff
 #define lpfc_cntl_attr_flash_id_WORD		word17
-	uint32_t mbx_da_struct_ver;
-	uint32_t ep_fw_da_struct_ver;
+#define lpfc_cntl_attr_boot_enable_SHIFT	24
+#define lpfc_cntl_attr_boot_enable_MASK		0x00000001
+#define lpfc_cntl_attr_boot_enable_WORD		word17
+	uint32_t rsvd18[2];
 	uint32_t ncsi_ver_str[3];
-	uint32_t dflt_ext_timeout;
+	uint32_t rsvd23;
 	uint32_t model_number[8];
 	uint32_t description[16];
 	uint32_t serial_number[8];
-	uint32_t ip_ver_str[8];
+	uint32_t ipl_name[5];
+	uint32_t rsvd61[3];
 	uint32_t fw_ver_str[8];
 	uint32_t bios_ver_str[8];
 	uint32_t redboot_ver_str[8];
@@ -3804,53 +3801,31 @@ struct lpfc_controller_attribute {
 	uint32_t flash_fw_ver_str[8];
 	uint32_t functionality;
 	uint32_t word105;
-#define lpfc_cntl_attr_max_cbd_len_SHIFT	0
-#define lpfc_cntl_attr_max_cbd_len_MASK		0x0000ffff
-#define lpfc_cntl_attr_max_cbd_len_WORD		word105
 #define lpfc_cntl_attr_asic_rev_SHIFT		16
 #define lpfc_cntl_attr_asic_rev_MASK		0x000000ff
 #define lpfc_cntl_attr_asic_rev_WORD		word105
-#define lpfc_cntl_attr_gen_guid0_SHIFT		24
-#define lpfc_cntl_attr_gen_guid0_MASK		0x000000ff
-#define lpfc_cntl_attr_gen_guid0_WORD		word105
-	uint32_t gen_guid1_12[3];
+	uint32_t rsvd106[3];
 	uint32_t word109;
-#define lpfc_cntl_attr_gen_guid13_14_SHIFT	0
-#define lpfc_cntl_attr_gen_guid13_14_MASK	0x0000ffff
-#define lpfc_cntl_attr_gen_guid13_14_WORD	word109
-#define lpfc_cntl_attr_gen_guid15_SHIFT		16
-#define lpfc_cntl_attr_gen_guid15_MASK		0x000000ff
-#define lpfc_cntl_attr_gen_guid15_WORD		word109
 #define lpfc_cntl_attr_hba_port_cnt_SHIFT	24
 #define lpfc_cntl_attr_hba_port_cnt_MASK	0x000000ff
 #define lpfc_cntl_attr_hba_port_cnt_WORD	word109
-	uint32_t word110;
-#define lpfc_cntl_attr_dflt_lnk_tmo_SHIFT	0
-#define lpfc_cntl_attr_dflt_lnk_tmo_MASK	0x0000ffff
-#define lpfc_cntl_attr_dflt_lnk_tmo_WORD	word110
-#define lpfc_cntl_attr_multi_func_dev_SHIFT	24
-#define lpfc_cntl_attr_multi_func_dev_MASK	0x000000ff
-#define lpfc_cntl_attr_multi_func_dev_WORD	word110
+	uint32_t rsvd110;
 	uint32_t word111;
-#define lpfc_cntl_attr_cache_valid_SHIFT	0
-#define lpfc_cntl_attr_cache_valid_MASK		0x000000ff
-#define lpfc_cntl_attr_cache_valid_WORD		word111
 #define lpfc_cntl_attr_hba_status_SHIFT		8
 #define lpfc_cntl_attr_hba_status_MASK		0x000000ff
 #define lpfc_cntl_attr_hba_status_WORD		word111
-#define lpfc_cntl_attr_max_domain_SHIFT		16
-#define lpfc_cntl_attr_max_domain_MASK		0x000000ff
-#define lpfc_cntl_attr_max_domain_WORD		word111
 #define lpfc_cntl_attr_lnk_numb_SHIFT		24
 #define lpfc_cntl_attr_lnk_numb_MASK		0x0000003f
 #define lpfc_cntl_attr_lnk_numb_WORD		word111
 #define lpfc_cntl_attr_lnk_type_SHIFT		30
 #define lpfc_cntl_attr_lnk_type_MASK		0x00000003
 #define lpfc_cntl_attr_lnk_type_WORD		word111
-	uint32_t fw_post_status;
-	uint32_t hba_mtu[8];
+	uint32_t rsvd112[9];
 	uint32_t word121;
-	uint32_t reserved1[3];
+#define lpfc_cntl_attr_asic_gen_SHIFT		8
+#define lpfc_cntl_attr_asic_gen_MASK		0x000000ff
+#define lpfc_cntl_attr_asic_gen_WORD		word121
+	uint32_t rsvd122[3];
 	uint32_t word125;
 #define lpfc_cntl_attr_pci_vendor_id_SHIFT	0
 #define lpfc_cntl_attr_pci_vendor_id_MASK	0x0000ffff
@@ -3875,15 +3850,7 @@ struct lpfc_controller_attribute {
 #define lpfc_cntl_attr_pci_fnc_num_SHIFT	16
 #define lpfc_cntl_attr_pci_fnc_num_MASK		0x000000ff
 #define lpfc_cntl_attr_pci_fnc_num_WORD		word127
-#define lpfc_cntl_attr_inf_type_SHIFT		24
-#define lpfc_cntl_attr_inf_type_MASK		0x000000ff
-#define lpfc_cntl_attr_inf_type_WORD		word127
-	uint32_t unique_id[2];
-	uint32_t word130;
-#define lpfc_cntl_attr_num_netfil_SHIFT		0
-#define lpfc_cntl_attr_num_netfil_MASK		0x000000ff
-#define lpfc_cntl_attr_num_netfil_WORD		word130
-	uint32_t reserved2[4];
+	uint32_t rsvd128[7];
 };
 
 struct lpfc_mbx_get_cntl_attributes {
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 7f57397d91a9..bcadf11414c8 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -598,7 +598,7 @@ lpfc_config_port_post(struct lpfc_hba *phba)
 		  jiffies + msecs_to_jiffies(1000 * timeout));
 	/* Set up heart beat (HB) timer */
 	mod_timer(&phba->hb_tmofunc,
-		  jiffies + msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL));
+		  jiffies + secs_to_jiffies(LPFC_HB_MBOX_INTERVAL));
 	clear_bit(HBA_HBEAT_INP, &phba->hba_flag);
 	clear_bit(HBA_HBEAT_TMO, &phba->hba_flag);
 	phba->last_completion_time = jiffies;
@@ -1267,7 +1267,7 @@ lpfc_hb_mbox_cmpl(struct lpfc_hba * phba, LPFC_MBOXQ_t * pmboxq)
 	    !test_bit(FC_UNLOADING, &phba->pport->load_flag))
 		mod_timer(&phba->hb_tmofunc,
 			  jiffies +
-			  msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL));
+			  secs_to_jiffies(LPFC_HB_MBOX_INTERVAL));
 	return;
 }
 
@@ -1555,7 +1555,7 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba)
 		/* If IOs are completing, no need to issue a MBX_HEARTBEAT */
 		spin_lock_irq(&phba->pport->work_port_lock);
 		if (time_after(phba->last_completion_time +
-				msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL),
+				secs_to_jiffies(LPFC_HB_MBOX_INTERVAL),
 				jiffies)) {
 			spin_unlock_irq(&phba->pport->work_port_lock);
 			if (test_bit(HBA_HBEAT_INP, &phba->hba_flag))
@@ -3354,7 +3354,7 @@ lpfc_block_mgmt_io(struct lpfc_hba *phba, int mbx_action)
 	spin_unlock_irqrestore(&phba->hbalock, iflag);
 	if (mbx_action == LPFC_MBX_NO_WAIT)
 		return;
-	timeout = msecs_to_jiffies(LPFC_MBOX_TMO * 1000) + jiffies;
+	timeout = secs_to_jiffies(LPFC_MBOX_TMO) + jiffies;
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	if (phba->sli.mbox_active) {
 		actcmd = phba->sli.mbox_active->u.mb.mbxCommand;
@@ -3847,8 +3847,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action)
 					 * Otherwise, let dev_loss take care of
 					 * the node.
 					 */
-					if (!(ndlp->save_flags &
-					      NLP_IN_RECOV_POST_DEV_LOSS) &&
+					if (!test_bit(NLP_IN_RECOV_POST_DEV_LOSS,
+						      &ndlp->save_flags) &&
 					    !(ndlp->fc4_xpt_flags &
 					      (NVME_XPT_REGD | SCSI_XPT_REGD)))
 						lpfc_disc_state_machine
@@ -4924,14 +4924,14 @@ int lpfc_scan_finished(struct Scsi_Host *shost, unsigned long time)
 		stat = 1;
 		goto finished;
 	}
-	if (time >= msecs_to_jiffies(30 * 1000)) {
+	if (time >= secs_to_jiffies(30)) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0461 Scanning longer than 30 "
 				"seconds.  Continuing initialization\n");
 		stat = 1;
 		goto finished;
 	}
-	if (time >= msecs_to_jiffies(15 * 1000) &&
+	if (time >= secs_to_jiffies(15) &&
 	    phba->link_state <= LPFC_LINK_DOWN) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 				"0465 Link down longer than 15 "
@@ -4945,7 +4945,7 @@ int lpfc_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	if (vport->num_disc_nodes || vport->fc_prli_sent)
 		goto finished;
 	if (!atomic_read(&vport->fc_map_cnt) &&
-	    time < msecs_to_jiffies(2 * 1000))
+	    time < secs_to_jiffies(2))
 		goto finished;
 	if ((phba->sli.sli_flag & LPFC_SLI_MBOX_ACTIVE) != 0)
 		goto finished;
@@ -5179,8 +5179,8 @@ lpfc_vmid_poll(struct timer_list *t)
 		lpfc_worker_wake_up(phba);
 
 	/* restart the timer for the next iteration */
-	mod_timer(&phba->inactive_vmid_poll, jiffies + msecs_to_jiffies(1000 *
-							LPFC_VMID_TIMER));
+	mod_timer(&phba->inactive_vmid_poll,
+		  jiffies + secs_to_jiffies(LPFC_VMID_TIMER));
 }
 
 /**
@@ -11109,14 +11109,11 @@ lpfc_sli4_queue_setup(struct lpfc_hba *phba)
 
 	phba->sli4_hba.fw_func_mode =
 			mboxq->u.mqe.un.query_fw_cfg.rsp.function_mode;
-	phba->sli4_hba.ulp0_mode = mboxq->u.mqe.un.query_fw_cfg.rsp.ulp0_mode;
-	phba->sli4_hba.ulp1_mode = mboxq->u.mqe.un.query_fw_cfg.rsp.ulp1_mode;
 	phba->sli4_hba.physical_port =
 			mboxq->u.mqe.un.query_fw_cfg.rsp.physical_port;
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
-			"3251 QUERY_FW_CFG: func_mode:x%x, ulp0_mode:x%x, "
-			"ulp1_mode:x%x\n", phba->sli4_hba.fw_func_mode,
-			phba->sli4_hba.ulp0_mode, phba->sli4_hba.ulp1_mode);
+			"3251 QUERY_FW_CFG: func_mode:x%x\n",
+			phba->sli4_hba.fw_func_mode);
 
 	mempool_free(mboxq, phba->mbox_mem_pool);
 
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index e98f1c2b2220..fb6dbcb86c09 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2524,8 +2524,10 @@ lpfc_reg_fcfi(struct lpfc_hba *phba, struct lpfcMboxq *mbox)
 		bf_set(lpfc_reg_fcfi_rq_id1, reg_fcfi, REG_FCF_INVALID_QID);
 
 		/* addr mode is bit wise inverted value of fcf addr_mode */
-		bf_set(lpfc_reg_fcfi_mam, reg_fcfi,
-		       (~phba->fcf.addr_mode) & 0x3);
+		if (test_bit(HBA_FCOE_MODE, &phba->hba_flag)) {
+			bf_set(lpfc_reg_fcfi_mam, reg_fcfi,
+			       (~phba->fcf.addr_mode) & 0x3);
+		}
 	} else {
 		/* This is ONLY for NVMET MRQ == 1 */
 		if (phba->cfg_nvmet_mrq != 1)
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 4d88cfe71cae..a596b80d03d4 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -64,9 +64,6 @@ static int
 lpfc_check_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		 struct lpfc_name *nn, struct lpfc_name *pn)
 {
-	/* First, we MUST have a RPI registered */
-	if (!test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag))
-		return 0;
 
 	/* Compare the ADISC rsp WWNN / WWPN matches our internal node
 	 * table entry for that node.
@@ -735,6 +732,7 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	ADISC *ap;
 	uint32_t *lp;
 	uint32_t cmd;
+	int rc;
 
 	pcmd = cmdiocb->cmd_dmabuf;
 	lp = (uint32_t *) pcmd->virt;
@@ -759,21 +757,29 @@ lpfc_rcv_padisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		 * resume the RPI before the ACC goes out.
 		 */
 		if (vport->phba->sli_rev == LPFC_SLI_REV4) {
-			elsiocb = kmalloc(sizeof(struct lpfc_iocbq),
-				GFP_KERNEL);
-			if (elsiocb) {
-				/* Save info from cmd IOCB used in rsp */
-				memcpy((uint8_t *)elsiocb, (uint8_t *)cmdiocb,
-					sizeof(struct lpfc_iocbq));
-
-				/* Save the ELS cmd */
-				elsiocb->drvrTimeout = cmd;
-
-				if (lpfc_sli4_resume_rpi(ndlp,
-						lpfc_mbx_cmpl_resume_rpi,
-						elsiocb))
-					kfree(elsiocb);
-				goto out;
+			/* Don't resume an unregistered RPI - unnecessary
+			 * mailbox. Just send the ACC when the RPI is not
+			 * registered.
+			 */
+			if (test_bit(NLP_RPI_REGISTERED, &ndlp->nlp_flag)) {
+				elsiocb = kmalloc(sizeof(*elsiocb), GFP_KERNEL);
+				if (elsiocb) {
+					/* Save info from cmd IOCB used in
+					 * rsp
+					 */
+					memcpy(elsiocb, cmdiocb,
+					       sizeof(*elsiocb));
+
+					elsiocb->drvrTimeout = cmd;
+
+					rc = lpfc_sli4_resume_rpi(ndlp,
+								  lpfc_mbx_cmpl_resume_rpi,
+								  elsiocb);
+					if (rc)
+						kfree(elsiocb);
+
+					goto out;
+				}
 			}
 		}
 
@@ -815,7 +821,6 @@ out:
 	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	ndlp->nlp_prev_state = ndlp->nlp_state;
-	lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 	return 0;
 }
 
@@ -906,7 +911,7 @@ lpfc_rcv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		    (ndlp->nlp_state >= NLP_STE_ADISC_ISSUE ||
 		     ndlp->nlp_state <= NLP_STE_PRLI_ISSUE)) {
 			mod_timer(&ndlp->nlp_delayfunc,
-				  jiffies + msecs_to_jiffies(1000 * 1));
+				  jiffies + secs_to_jiffies(1));
 			set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 			ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 			lpfc_printf_vlog(vport, KERN_INFO,
@@ -1332,7 +1337,7 @@ lpfc_rcv_els_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	}
 
 	/* Put ndlp in npr state set plogi timer for 1 sec */
-	mod_timer(&ndlp->nlp_delayfunc, jiffies + msecs_to_jiffies(1000 * 1));
+	mod_timer(&ndlp->nlp_delayfunc, jiffies + secs_to_jiffies(1));
 	set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 	ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 	ndlp->nlp_prev_state = NLP_STE_PLOGI_ISSUE;
@@ -1936,7 +1941,7 @@ lpfc_cmpl_reglogin_reglogin_issue(struct lpfc_vport *vport,
 
 		/* Put ndlp in npr state set plogi timer for 1 sec */
 		mod_timer(&ndlp->nlp_delayfunc,
-			  jiffies + msecs_to_jiffies(1000 * 1));
+			  jiffies + secs_to_jiffies(1));
 		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
 
@@ -2255,11 +2260,13 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	    (vport->port_type == LPFC_NPIV_PORT) &&
 	     vport->cfg_restrict_login) {
 out:
-		set_bit(NLP_TARGET_REMOVE, &ndlp->nlp_flag);
+		lpfc_printf_vlog(vport, KERN_INFO,
+				 LOG_ELS | LOG_DISCOVERY | LOG_NODE,
+				 "6228 Sending LOGO, determined nlp_type "
+				 "0x%x nlp_flag x%lx refcnt %u\n",
+				 ndlp->nlp_type, ndlp->nlp_flag,
+				 kref_read(&ndlp->kref));
 		lpfc_issue_els_logo(vport, ndlp, 0);
-
-		ndlp->nlp_prev_state = NLP_STE_PRLI_ISSUE;
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
 		return ndlp->nlp_state;
 	}
 
@@ -2743,7 +2750,7 @@ lpfc_rcv_prlo_npr_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
 	if (!test_bit(NLP_DELAY_TMO, &ndlp->nlp_flag)) {
 		mod_timer(&ndlp->nlp_delayfunc,
-			  jiffies + msecs_to_jiffies(1000 * 1));
+			  jiffies + secs_to_jiffies(1));
 		set_bit(NLP_DELAY_TMO, &ndlp->nlp_flag);
 		clear_bit(NLP_NPR_ADISC, &ndlp->nlp_flag);
 		ndlp->nlp_last_elscmd = ELS_CMD_PLOGI;
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 43dc1da4a156..b1adb9f59097 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -2237,7 +2237,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport,
 	 * wait. Print a message if a 10 second wait expires and renew the
 	 * wait. This is unexpected.
 	 */
-	wait_tmo = msecs_to_jiffies(LPFC_NVME_WAIT_TMO * 1000);
+	wait_tmo = secs_to_jiffies(LPFC_NVME_WAIT_TMO);
 	while (true) {
 		ret = wait_for_completion_timeout(lport_unreg_cmp, wait_tmo);
 		if (unlikely(!ret)) {
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 905026a4782c..055ed632c14d 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5136,6 +5136,12 @@ lpfc_info(struct Scsi_Host *host)
 				goto buffer_done;
 		}
 
+		/* Support for BSG ioctls */
+		scnprintf(tmp, sizeof(tmp), " BSG");
+		if (strlcat(lpfcinfobuf, tmp, sizeof(lpfcinfobuf)) >=
+		    sizeof(lpfcinfobuf))
+			goto buffer_done;
+
 		/* PCI resettable */
 		if (!lpfc_check_pci_resettable(phba)) {
 			scnprintf(tmp, sizeof(tmp), " PCI resettable");
@@ -6120,31 +6126,28 @@ lpfc_target_reset_handler(struct scsi_cmnd *cmnd)
 
 		/* Issue LOGO, if no LOGO is outstanding */
 		spin_lock_irqsave(&pnode->lock, flags);
-		if (!(pnode->save_flags & NLP_WAIT_FOR_LOGO) &&
+		if (!test_bit(NLP_WAIT_FOR_LOGO, &pnode->save_flags) &&
 		    !pnode->logo_waitq) {
 			pnode->logo_waitq = &waitq;
 			pnode->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
-			set_bit(NLP_ISSUE_LOGO, &pnode->nlp_flag);
-			pnode->save_flags |= NLP_WAIT_FOR_LOGO;
 			spin_unlock_irqrestore(&pnode->lock, flags);
+			set_bit(NLP_ISSUE_LOGO, &pnode->nlp_flag);
+			set_bit(NLP_WAIT_FOR_LOGO, &pnode->save_flags);
 			lpfc_unreg_rpi(vport, pnode);
 			wait_event_timeout(waitq,
-					   (!(pnode->save_flags &
-					      NLP_WAIT_FOR_LOGO)),
+					   !test_bit(NLP_WAIT_FOR_LOGO,
+						     &pnode->save_flags),
 					   msecs_to_jiffies(dev_loss_tmo *
 							    1000));
 
-			if (pnode->save_flags & NLP_WAIT_FOR_LOGO) {
+			if (test_and_clear_bit(NLP_WAIT_FOR_LOGO,
+					       &pnode->save_flags))
 				lpfc_printf_vlog(vport, KERN_ERR, logit,
 						 "0725 SCSI layer TGTRST "
 						 "failed & LOGO TMO (%d, %llu) "
 						 "return x%x\n",
 						 tgt_id, lun_id, status);
-				spin_lock_irqsave(&pnode->lock, flags);
-				pnode->save_flags &= ~NLP_WAIT_FOR_LOGO;
-			} else {
-				spin_lock_irqsave(&pnode->lock, flags);
-			}
+			spin_lock_irqsave(&pnode->lock, flags);
 			pnode->logo_waitq = NULL;
 			spin_unlock_irqrestore(&pnode->lock, flags);
 			status = SUCCESS;
@@ -6226,7 +6229,7 @@ error:
 }
 
 /**
- * lpfc_slave_alloc - scsi_host_template slave_alloc entry point
+ * lpfc_sdev_init - scsi_host_template sdev_init entry point
  * @sdev: Pointer to scsi_device.
  *
  * This routine populates the cmds_per_lun count + 2 scsi_bufs into  this host's
@@ -6239,7 +6242,7 @@ error:
  *   0 - Success
  **/
 static int
-lpfc_slave_alloc(struct scsi_device *sdev)
+lpfc_sdev_init(struct scsi_device *sdev)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
@@ -6342,8 +6345,9 @@ lpfc_slave_alloc(struct scsi_device *sdev)
 }
 
 /**
- * lpfc_slave_configure - scsi_host_template slave_configure entry point
+ * lpfc_sdev_configure - scsi_host_template sdev_configure entry point
  * @sdev: Pointer to scsi_device.
+ * @lim: Request queue limits.
  *
  * This routine configures following items
  *   - Tag command queuing support for @sdev if supported.
@@ -6353,7 +6357,7 @@ lpfc_slave_alloc(struct scsi_device *sdev)
  *   0 - Success
  **/
 static int
-lpfc_slave_configure(struct scsi_device *sdev)
+lpfc_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
@@ -6371,13 +6375,13 @@ lpfc_slave_configure(struct scsi_device *sdev)
 }
 
 /**
- * lpfc_slave_destroy - slave_destroy entry point of SHT data structure
+ * lpfc_sdev_destroy - sdev_destroy entry point of SHT data structure
  * @sdev: Pointer to scsi_device.
  *
  * This routine sets @sdev hostatdata filed to null.
  **/
 static void
-lpfc_slave_destroy(struct scsi_device *sdev)
+lpfc_sdev_destroy(struct scsi_device *sdev)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *) sdev->host->hostdata;
 	struct lpfc_hba   *phba = vport->phba;
@@ -6422,7 +6426,7 @@ lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 {
 
 	struct lpfc_device_data *lun_info;
-	int memory_flags;
+	gfp_t memory_flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn  ||
 	    !(phba->cfg_fof))
@@ -6737,7 +6741,13 @@ lpfc_no_command(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 }
 
 static int
-lpfc_no_slave(struct scsi_device *sdev)
+lpfc_init_no_sdev(struct scsi_device *sdev)
+{
+	return -ENODEV;
+}
+
+static int
+lpfc_config_no_sdev(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	return -ENODEV;
 }
@@ -6748,8 +6758,8 @@ struct scsi_host_template lpfc_template_nvme = {
 	.proc_name		= LPFC_DRIVER_NAME,
 	.info			= lpfc_info,
 	.queuecommand		= lpfc_no_command,
-	.slave_alloc		= lpfc_no_slave,
-	.slave_configure	= lpfc_no_slave,
+	.sdev_init		= lpfc_init_no_sdev,
+	.sdev_configure		= lpfc_config_no_sdev,
 	.scan_finished		= lpfc_scan_finished,
 	.this_id		= -1,
 	.sg_tablesize		= 1,
@@ -6772,9 +6782,9 @@ struct scsi_host_template lpfc_template = {
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
 	.eh_host_reset_handler  = lpfc_host_reset_handler,
-	.slave_alloc		= lpfc_slave_alloc,
-	.slave_configure	= lpfc_slave_configure,
-	.slave_destroy		= lpfc_slave_destroy,
+	.sdev_init		= lpfc_sdev_init,
+	.sdev_configure		= lpfc_sdev_configure,
+	.sdev_destroy		= lpfc_sdev_destroy,
 	.scan_finished		= lpfc_scan_finished,
 	.this_id		= -1,
 	.sg_tablesize		= LPFC_DEFAULT_SG_SEG_CNT,
@@ -6799,9 +6809,9 @@ struct scsi_host_template lpfc_vport_template = {
 	.eh_target_reset_handler = lpfc_target_reset_handler,
 	.eh_bus_reset_handler	= NULL,
 	.eh_host_reset_handler	= NULL,
-	.slave_alloc		= lpfc_slave_alloc,
-	.slave_configure	= lpfc_slave_configure,
-	.slave_destroy		= lpfc_slave_destroy,
+	.sdev_init		= lpfc_sdev_init,
+	.sdev_configure		= lpfc_sdev_configure,
+	.sdev_destroy		= lpfc_sdev_destroy,
 	.scan_finished		= lpfc_scan_finished,
 	.this_id		= -1,
 	.sg_tablesize		= LPFC_DEFAULT_SG_SEG_CNT,
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 874644b31a3e..3fd9723cd271 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -9012,7 +9012,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
 
 	/* Start heart beat timer */
 	mod_timer(&phba->hb_tmofunc,
-		  jiffies + msecs_to_jiffies(1000 * LPFC_HB_MBOX_INTERVAL));
+		  jiffies + secs_to_jiffies(LPFC_HB_MBOX_INTERVAL));
 	clear_bit(HBA_HBEAT_INP, &phba->hba_flag);
 	clear_bit(HBA_HBEAT_TMO, &phba->hba_flag);
 	phba->last_completion_time = jiffies;
@@ -13323,7 +13323,7 @@ lpfc_sli_mbox_sys_shutdown(struct lpfc_hba *phba, int mbx_action)
 		lpfc_sli_mbox_sys_flush(phba);
 		return;
 	}
-	timeout = msecs_to_jiffies(LPFC_MBOX_TMO * 1000) + jiffies;
+	timeout = secs_to_jiffies(LPFC_MBOX_TMO) + jiffies;
 
 	/* Disable softirqs, including timers from obtaining phba->hbalock */
 	local_bh_disable();
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index c1e9ec0243ba..9be3da91c923 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -865,8 +865,6 @@ struct lpfc_sli4_hba {
 	struct lpfc_name wwpn;
 
 	uint32_t fw_func_mode;	/* FW function protocol mode */
-	uint32_t ulp0_mode;	/* ULP0 protocol mode */
-	uint32_t ulp1_mode;	/* ULP1 protocol mode */
 
 	/* Optimized Access Storage specific queues/structures */
 	uint64_t oas_next_lun;
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 61fe1220f8ad..c35f7225058e 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "14.4.0.6"
+#define LPFC_DRIVER_VERSION "14.4.0.7"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vmid.c b/drivers/scsi/lpfc/lpfc_vmid.c
index cc3e4736f2fe..14dbfe954e42 100644
--- a/drivers/scsi/lpfc/lpfc_vmid.c
+++ b/drivers/scsi/lpfc/lpfc_vmid.c
@@ -278,7 +278,7 @@ int lpfc_vmid_get_appid(struct lpfc_vport *vport, char *uuid,
 		if (!(vport->phba->pport->vmid_flag & LPFC_VMID_TIMER_ENBLD)) {
 			mod_timer(&vport->phba->inactive_vmid_poll,
 				  jiffies +
-				  msecs_to_jiffies(1000 * LPFC_VMID_TIMER));
+				  secs_to_jiffies(LPFC_VMID_TIMER));
 			vport->phba->pport->vmid_flag |= LPFC_VMID_TIMER_ENBLD;
 		}
 	}
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 9e0e35763377..3d70cc517573 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -492,21 +492,22 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
 
 	spin_lock_irq(&ndlp->lock);
-	if (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO) &&
+	if (!test_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags) &&
 	    !ndlp->logo_waitq) {
 		ndlp->logo_waitq = &waitq;
 		ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
 		set_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
-		ndlp->save_flags |= NLP_WAIT_FOR_LOGO;
+		set_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags);
 	}
 	spin_unlock_irq(&ndlp->lock);
 	rc = lpfc_issue_els_npiv_logo(vport, ndlp);
 	if (!rc) {
 		wait_event_timeout(waitq,
-				   (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO)),
+				   !test_bit(NLP_WAIT_FOR_LOGO,
+					     &ndlp->save_flags),
 				   msecs_to_jiffies(phba->fc_ratov * 2000));
 
-		if (!(ndlp->save_flags & NLP_WAIT_FOR_LOGO))
+		if (!test_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags))
 			goto logo_cmpl;
 		/* LOGO wait failed.  Correct status. */
 		rc = -EINTR;
@@ -516,9 +517,7 @@ lpfc_send_npiv_logo(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 	/* Error - clean up node flags. */
 	clear_bit(NLP_ISSUE_LOGO, &ndlp->nlp_flag);
-	spin_lock_irq(&ndlp->lock);
-	ndlp->save_flags &= ~NLP_WAIT_FOR_LOGO;
-	spin_unlock_irq(&ndlp->lock);
+	clear_bit(NLP_WAIT_FOR_LOGO, &ndlp->save_flags);
 
  logo_cmpl:
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT,
@@ -696,19 +695,20 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
 
 			spin_lock_irq(&ndlp->lock);
 			ndlp->da_id_waitq = &waitq;
-			ndlp->save_flags |= NLP_WAIT_FOR_DA_ID;
 			spin_unlock_irq(&ndlp->lock);
+			set_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags);
 
 			rc = lpfc_ns_cmd(vport, SLI_CTNS_DA_ID, 0, 0);
 			if (!rc) {
 				wait_event_timeout(waitq,
-				   !(ndlp->save_flags & NLP_WAIT_FOR_DA_ID),
+				   !test_bit(NLP_WAIT_FOR_DA_ID,
+					     &ndlp->save_flags),
 				   msecs_to_jiffies(phba->fc_ratov * 2000));
 			}
 
 			lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT | LOG_ELS,
 					 "1829 DA_ID issue status %d. "
-					 "SFlag x%x NState x%x, NFlag x%lx "
+					 "SFlag x%lx NState x%x, NFlag x%lx "
 					 "Rpi x%x\n",
 					 rc, ndlp->save_flags, ndlp->nlp_state,
 					 ndlp->nlp_flag, ndlp->nlp_rpi);
@@ -718,8 +718,8 @@ lpfc_vport_delete(struct fc_vport *fc_vport)
 			 */
 			spin_lock_irq(&ndlp->lock);
 			ndlp->da_id_waitq = NULL;
-			ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID;
 			spin_unlock_irq(&ndlp->lock);
+			clear_bit(NLP_WAIT_FOR_DA_ID, &ndlp->save_flags);
 		}
 
 issue_logo:
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 38976f94453e..adab151663dd 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -4551,7 +4551,7 @@ megaraid_shutdown(struct pci_dev *pdev)
 	__megaraid_shutdown(adapter);
 }
 
-static struct pci_device_id megaraid_pci_tbl[] = {
+static const struct pci_device_id megaraid_pci_tbl[] = {
 	{PCI_VENDOR_ID_AMI, PCI_DEVICE_ID_AMI_MEGARAID,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{PCI_VENDOR_ID_AMI, PCI_DEVICE_ID_AMI_MEGARAID2,
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index bc867da650b6..60cc3372991f 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -199,7 +199,7 @@ MODULE_PARM_DESC(debug_level, "Debug level for driver (default=0)");
 /*
  * PCI table for all supported controllers.
  */
-static struct pci_device_id pci_id_table_g[] =  {
+static const struct pci_device_id pci_id_table_g[] =  {
 	{
 		PCI_VENDOR_ID_DELL,
 		PCI_DEVICE_ID_PERC4_DI_DISCOVERY,
@@ -621,7 +621,7 @@ megaraid_io_attach(adapter_t *adapter)
 	host = scsi_host_alloc(&megaraid_template_g, 8);
 	if (!host) {
 		con_log(CL_ANN, (KERN_WARNING
-			"megaraid mbox: scsi_register failed\n"));
+			"megaraid mbox: scsi_host_alloc failed\n"));
 
 		return -1;
 	}
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 49abd7dd75a7..d85f990aec88 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -146,7 +146,7 @@ megasas_set_ld_removed_by_fw(struct megasas_instance *instance);
 /*
  * PCI ID table for all supported controllers
  */
-static struct pci_device_id megasas_pci_table[] = {
+static const struct pci_device_id megasas_pci_table[] = {
 
 	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_SAS1064R)},
 	/* xscale IOP */
@@ -2067,8 +2067,8 @@ static void megasas_set_static_target_properties(struct scsi_device *sdev,
 }
 
 
-static int megasas_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int megasas_sdev_configure(struct scsi_device *sdev,
+				  struct queue_limits *lim)
 {
 	u16 pd_index = 0;
 	struct megasas_instance *instance;
@@ -2108,7 +2108,7 @@ static int megasas_device_configure(struct scsi_device *sdev,
 	return 0;
 }
 
-static int megasas_slave_alloc(struct scsi_device *sdev)
+static int megasas_sdev_init(struct scsi_device *sdev)
 {
 	u16 pd_index = 0, ld_tgt_id;
 	struct megasas_instance *instance ;
@@ -2153,7 +2153,7 @@ scan_target:
 	return 0;
 }
 
-static void megasas_slave_destroy(struct scsi_device *sdev)
+static void megasas_sdev_destroy(struct scsi_device *sdev)
 {
 	u16 ld_tgt_id;
 	struct megasas_instance *instance;
@@ -3509,9 +3509,9 @@ static const struct scsi_host_template megasas_template = {
 	.module = THIS_MODULE,
 	.name = "Avago SAS based MegaRAID driver",
 	.proc_name = "megaraid_sas",
-	.device_configure = megasas_device_configure,
-	.slave_alloc = megasas_slave_alloc,
-	.slave_destroy = megasas_slave_destroy,
+	.sdev_configure = megasas_sdev_configure,
+	.sdev_init = megasas_sdev_init,
+	.sdev_destroy = megasas_sdev_destroy,
 	.queuecommand = megasas_queue_command,
 	.eh_target_reset_handler = megasas_reset_target,
 	.eh_abort_handler = megasas_task_abort,
diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c
index 10b8e4dc64f8..7589f48aebc8 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_app.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_app.c
@@ -2951,6 +2951,7 @@ void mpi3mr_bsg_init(struct mpi3mr_ioc *mrioc)
 		.max_hw_sectors		= MPI3MR_MAX_APP_XFER_SECTORS,
 		.max_segments		= MPI3MR_MAX_APP_XFER_SEGMENTS,
 	};
+	struct request_queue *q;
 
 	device_initialize(bsg_dev);
 
@@ -2966,14 +2967,17 @@ void mpi3mr_bsg_init(struct mpi3mr_ioc *mrioc)
 		return;
 	}
 
-	mrioc->bsg_queue = bsg_setup_queue(bsg_dev, dev_name(bsg_dev), &lim,
+	q = bsg_setup_queue(bsg_dev, dev_name(bsg_dev), &lim,
 			mpi3mr_bsg_request, NULL, 0);
-	if (IS_ERR(mrioc->bsg_queue)) {
+	if (IS_ERR(q)) {
 		ioc_err(mrioc, "%s: bsg registration failed\n",
 		    dev_name(bsg_dev));
 		device_del(bsg_dev);
 		put_device(bsg_dev);
+		return;
 	}
+
+	mrioc->bsg_queue = q;
 }
 
 /**
diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index 1e8735538b23..b9a51d3f2024 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -4465,14 +4465,14 @@ static int mpi3mr_scan_finished(struct Scsi_Host *shost,
 }
 
 /**
- * mpi3mr_slave_destroy - Slave destroy callback handler
+ * mpi3mr_sdev_destroy - Slave destroy callback handler
  * @sdev: SCSI device reference
  *
  * Cleanup and free per device(lun) private data.
  *
  * Return: Nothing.
  */
-static void mpi3mr_slave_destroy(struct scsi_device *sdev)
+static void mpi3mr_sdev_destroy(struct scsi_device *sdev)
 {
 	struct Scsi_Host *shost;
 	struct mpi3mr_ioc *mrioc;
@@ -4552,7 +4552,7 @@ static void mpi3mr_target_destroy(struct scsi_target *starget)
 }
 
 /**
- * mpi3mr_device_configure - Slave configure callback handler
+ * mpi3mr_sdev_configure - Slave configure callback handler
  * @sdev: SCSI device reference
  * @lim: queue limits
  *
@@ -4561,8 +4561,8 @@ static void mpi3mr_target_destroy(struct scsi_target *starget)
  *
  * Return: 0 always.
  */
-static int mpi3mr_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int mpi3mr_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	struct scsi_target *starget;
 	struct Scsi_Host *shost;
@@ -4599,14 +4599,14 @@ static int mpi3mr_device_configure(struct scsi_device *sdev,
 }
 
 /**
- * mpi3mr_slave_alloc -Slave alloc callback handler
+ * mpi3mr_sdev_init -Slave alloc callback handler
  * @sdev: SCSI device reference
  *
  * Allocate per device(lun) private data and initialize it.
  *
  * Return: 0 on success -ENOMEM on memory allocation failure.
  */
-static int mpi3mr_slave_alloc(struct scsi_device *sdev)
+static int mpi3mr_sdev_init(struct scsi_device *sdev)
 {
 	struct Scsi_Host *shost;
 	struct mpi3mr_ioc *mrioc;
@@ -5062,10 +5062,10 @@ static const struct scsi_host_template mpi3mr_driver_template = {
 	.proc_name			= MPI3MR_DRIVER_NAME,
 	.queuecommand			= mpi3mr_qcmd,
 	.target_alloc			= mpi3mr_target_alloc,
-	.slave_alloc			= mpi3mr_slave_alloc,
-	.device_configure		= mpi3mr_device_configure,
+	.sdev_init			= mpi3mr_sdev_init,
+	.sdev_configure			= mpi3mr_sdev_configure,
 	.target_destroy			= mpi3mr_target_destroy,
-	.slave_destroy			= mpi3mr_slave_destroy,
+	.sdev_destroy			= mpi3mr_sdev_destroy,
 	.scan_finished			= mpi3mr_scan_finished,
 	.scan_start			= mpi3mr_scan_start,
 	.change_queue_depth		= mpi3mr_change_queue_depth,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 16ac2267c71e..dc43cfa83088 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -5627,10 +5627,9 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
 	if (rc)
 		return rc;
 	if (!ioc->is_gen35_ioc && ioc->manu_pg11.EEDPTagMode == 0) {
-		pr_err("%s: overriding NVDATA EEDPTagMode setting\n",
+		pr_err("%s: overriding NVDATA EEDPTagMode setting from 0 to 1\n",
 		    ioc->name);
-		ioc->manu_pg11.EEDPTagMode &= ~0x3;
-		ioc->manu_pg11.EEDPTagMode |= 0x1;
+		ioc->manu_pg11.EEDPTagMode = 0x1;
 		mpt3sas_config_set_manufacturing_pg11(ioc, &mpi_reply,
 		    &ioc->manu_pg11);
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 9599d7a50028..a456e5ec74d8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2025,14 +2025,14 @@ scsih_target_destroy(struct scsi_target *starget)
 }
 
 /**
- * scsih_slave_alloc - device add routine
+ * scsih_sdev_init - device add routine
  * @sdev: scsi device struct
  *
  * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
-scsih_slave_alloc(struct scsi_device *sdev)
+scsih_sdev_init(struct scsi_device *sdev)
 {
 	struct Scsi_Host *shost;
 	struct MPT3SAS_ADAPTER *ioc;
@@ -2107,11 +2107,11 @@ scsih_slave_alloc(struct scsi_device *sdev)
 }
 
 /**
- * scsih_slave_destroy - device destroy routine
+ * scsih_sdev_destroy - device destroy routine
  * @sdev: scsi device struct
  */
 static void
-scsih_slave_destroy(struct scsi_device *sdev)
+scsih_sdev_destroy(struct scsi_device *sdev)
 {
 	struct MPT3SAS_TARGET *sas_target_priv_data;
 	struct scsi_target *starget;
@@ -2496,7 +2496,7 @@ _scsih_enable_tlr(struct MPT3SAS_ADAPTER *ioc, struct scsi_device *sdev)
 }
 
 /**
- * scsih_device_configure - device configure routine.
+ * scsih_sdev_configure - device configure routine.
  * @sdev: scsi device struct
  * @lim: queue limits
  *
@@ -2504,7 +2504,7 @@ _scsih_enable_tlr(struct MPT3SAS_ADAPTER *ioc, struct scsi_device *sdev)
  * the device is ignored.
  */
 static int
-scsih_device_configure(struct scsi_device *sdev, struct queue_limits *lim)
+scsih_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct Scsi_Host *shost = sdev->host;
 	struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
@@ -11904,10 +11904,10 @@ static const struct scsi_host_template mpt2sas_driver_template = {
 	.proc_name			= MPT2SAS_DRIVER_NAME,
 	.queuecommand			= scsih_qcmd,
 	.target_alloc			= scsih_target_alloc,
-	.slave_alloc			= scsih_slave_alloc,
-	.device_configure		= scsih_device_configure,
+	.sdev_init			= scsih_sdev_init,
+	.sdev_configure			= scsih_sdev_configure,
 	.target_destroy			= scsih_target_destroy,
-	.slave_destroy			= scsih_slave_destroy,
+	.sdev_destroy			= scsih_sdev_destroy,
 	.scan_finished			= scsih_scan_finished,
 	.scan_start			= scsih_scan_start,
 	.change_queue_depth		= scsih_change_queue_depth,
@@ -11942,10 +11942,10 @@ static const struct scsi_host_template mpt3sas_driver_template = {
 	.proc_name			= MPT3SAS_DRIVER_NAME,
 	.queuecommand			= scsih_qcmd,
 	.target_alloc			= scsih_target_alloc,
-	.slave_alloc			= scsih_slave_alloc,
-	.device_configure		= scsih_device_configure,
+	.sdev_init			= scsih_sdev_init,
+	.sdev_configure			= scsih_sdev_configure,
 	.target_destroy			= scsih_target_destroy,
-	.slave_destroy			= scsih_slave_destroy,
+	.sdev_destroy			= scsih_sdev_destroy,
 	.scan_finished			= scsih_scan_finished,
 	.scan_start			= scsih_scan_start,
 	.change_queue_depth		= scsih_change_queue_depth,
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index 020037cbf0d9..2c72da6b8cf0 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -609,7 +609,7 @@ static void mvs_pci_remove(struct pci_dev *pdev)
 	return;
 }
 
-static struct pci_device_id mvs_pci_table[] = {
+static const struct pci_device_id mvs_pci_table[] = {
 	{ PCI_VDEVICE(MARVELL, 0x6320), chip_6320 },
 	{ PCI_VDEVICE(MARVELL, 0x6340), chip_6440 },
 	{
diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c
index d9d366ec17dc..96549e7f5705 100644
--- a/drivers/scsi/mvumi.c
+++ b/drivers/scsi/mvumi.c
@@ -2000,7 +2000,8 @@ static struct mvumi_instance_template mvumi_instance_9580 = {
 	.reset_host = mvumi_reset_host_9580,
 };
 
-static int mvumi_slave_configure(struct scsi_device *sdev)
+static int mvumi_sdev_configure(struct scsi_device *sdev,
+				struct queue_limits *lim)
 {
 	struct mvumi_hba *mhba;
 	unsigned char bitcount = sizeof(unsigned char) * 8;
@@ -2172,7 +2173,7 @@ static const struct scsi_host_template mvumi_template = {
 
 	.module = THIS_MODULE,
 	.name = "Marvell Storage Controller",
-	.slave_configure = mvumi_slave_configure,
+	.sdev_configure = mvumi_sdev_configure,
 	.queuecommand = mvumi_queue_command,
 	.eh_timed_out = mvumi_timed_out,
 	.eh_host_reset_handler = mvumi_host_reset,
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index a7e64b867c8e..dc4bd422b601 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -1619,7 +1619,7 @@ static int myrb_queuecommand(struct Scsi_Host *shost,
 	return myrb_pthru_queuecommand(shost, scmd);
 }
 
-static int myrb_ldev_slave_alloc(struct scsi_device *sdev)
+static int myrb_ldev_sdev_init(struct scsi_device *sdev)
 {
 	struct myrb_hba *cb = shost_priv(sdev->host);
 	struct myrb_ldev_info *ldev_info;
@@ -1627,8 +1627,6 @@ static int myrb_ldev_slave_alloc(struct scsi_device *sdev)
 	enum raid_level level;
 
 	ldev_info = cb->ldev_info_buf + ldev_num;
-	if (!ldev_info)
-		return -ENXIO;
 
 	sdev->hostdata = kzalloc(sizeof(*ldev_info), GFP_KERNEL);
 	if (!sdev->hostdata)
@@ -1665,7 +1663,7 @@ static int myrb_ldev_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int myrb_pdev_slave_alloc(struct scsi_device *sdev)
+static int myrb_pdev_sdev_init(struct scsi_device *sdev)
 {
 	struct myrb_hba *cb = shost_priv(sdev->host);
 	struct myrb_pdev_state *pdev_info;
@@ -1701,7 +1699,7 @@ static int myrb_pdev_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int myrb_slave_alloc(struct scsi_device *sdev)
+static int myrb_sdev_init(struct scsi_device *sdev)
 {
 	if (sdev->channel > myrb_logical_channel(sdev->host))
 		return -ENXIO;
@@ -1710,12 +1708,13 @@ static int myrb_slave_alloc(struct scsi_device *sdev)
 		return -ENXIO;
 
 	if (sdev->channel == myrb_logical_channel(sdev->host))
-		return myrb_ldev_slave_alloc(sdev);
+		return myrb_ldev_sdev_init(sdev);
 
-	return myrb_pdev_slave_alloc(sdev);
+	return myrb_pdev_sdev_init(sdev);
 }
 
-static int myrb_slave_configure(struct scsi_device *sdev)
+static int myrb_sdev_configure(struct scsi_device *sdev,
+			       struct queue_limits *lim)
 {
 	struct myrb_ldev_info *ldev_info;
 
@@ -1741,7 +1740,7 @@ static int myrb_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
-static void myrb_slave_destroy(struct scsi_device *sdev)
+static void myrb_sdev_destroy(struct scsi_device *sdev)
 {
 	kfree(sdev->hostdata);
 }
@@ -2208,9 +2207,9 @@ static const struct scsi_host_template myrb_template = {
 	.proc_name		= "myrb",
 	.queuecommand		= myrb_queuecommand,
 	.eh_host_reset_handler	= myrb_host_reset,
-	.slave_alloc		= myrb_slave_alloc,
-	.slave_configure	= myrb_slave_configure,
-	.slave_destroy		= myrb_slave_destroy,
+	.sdev_init		= myrb_sdev_init,
+	.sdev_configure		= myrb_sdev_configure,
+	.sdev_destroy		= myrb_sdev_destroy,
 	.bios_param		= myrb_biosparam,
 	.cmd_size		= sizeof(struct myrb_cmdblk),
 	.shost_groups		= myrb_shost_groups,
diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c
index 1469d0c54e45..95af3bb03834 100644
--- a/drivers/scsi/myrs.c
+++ b/drivers/scsi/myrs.c
@@ -1786,7 +1786,7 @@ static unsigned short myrs_translate_ldev(struct myrs_hba *cs,
 	return ldev_num;
 }
 
-static int myrs_slave_alloc(struct scsi_device *sdev)
+static int myrs_sdev_init(struct scsi_device *sdev)
 {
 	struct myrs_hba *cs = shost_priv(sdev->host);
 	unsigned char status;
@@ -1882,7 +1882,8 @@ static int myrs_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int myrs_slave_configure(struct scsi_device *sdev)
+static int myrs_sdev_configure(struct scsi_device *sdev,
+			       struct queue_limits *lim)
 {
 	struct myrs_hba *cs = shost_priv(sdev->host);
 	struct myrs_ldev_info *ldev_info;
@@ -1910,7 +1911,7 @@ static int myrs_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
-static void myrs_slave_destroy(struct scsi_device *sdev)
+static void myrs_sdev_destroy(struct scsi_device *sdev)
 {
 	kfree(sdev->hostdata);
 }
@@ -1921,9 +1922,9 @@ static const struct scsi_host_template myrs_template = {
 	.proc_name		= "myrs",
 	.queuecommand		= myrs_queuecommand,
 	.eh_host_reset_handler	= myrs_host_reset,
-	.slave_alloc		= myrs_slave_alloc,
-	.slave_configure	= myrs_slave_configure,
-	.slave_destroy		= myrs_slave_destroy,
+	.sdev_init		= myrs_sdev_init,
+	.sdev_configure		= myrs_sdev_configure,
+	.sdev_destroy		= myrs_sdev_destroy,
 	.cmd_size		= sizeof(struct myrs_cmdblk),
 	.shost_groups		= myrs_shost_groups,
 	.sdev_groups		= myrs_sdev_groups,
diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index 35869b4f9329..14ac81ec0aa0 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -7786,7 +7786,7 @@ static void __init ncr_getclock (struct ncb *np, int mult)
 
 /*===================== LINUX ENTRY POINTS SECTION ==========================*/
 
-static int ncr53c8xx_slave_alloc(struct scsi_device *device)
+static int ncr53c8xx_sdev_init(struct scsi_device *device)
 {
 	struct Scsi_Host *host = device->host;
 	struct ncb *np = ((struct host_data *) host->hostdata)->ncb;
@@ -7796,7 +7796,8 @@ static int ncr53c8xx_slave_alloc(struct scsi_device *device)
 	return 0;
 }
 
-static int ncr53c8xx_slave_configure(struct scsi_device *device)
+static int ncr53c8xx_sdev_configure(struct scsi_device *device,
+				    struct queue_limits *lim)
 {
 	struct Scsi_Host *host = device->host;
 	struct ncb *np = ((struct host_data *) host->hostdata)->ncb;
@@ -8093,8 +8094,8 @@ struct Scsi_Host * __init ncr_attach(struct scsi_host_template *tpnt,
 		tpnt->shost_groups = ncr53c8xx_host_groups;
 
 	tpnt->queuecommand	= ncr53c8xx_queue_command;
-	tpnt->slave_configure	= ncr53c8xx_slave_configure;
-	tpnt->slave_alloc	= ncr53c8xx_slave_alloc;
+	tpnt->sdev_configure	= ncr53c8xx_sdev_configure;
+	tpnt->sdev_init		= ncr53c8xx_sdev_init;
 	tpnt->eh_bus_reset_handler = ncr53c8xx_bus_reset;
 	tpnt->can_queue		= SCSI_NCR_CAN_QUEUE;
 	tpnt->this_id		= 7;
diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c
index b7987019686e..abc4ce9eae74 100644
--- a/drivers/scsi/nsp32.c
+++ b/drivers/scsi/nsp32.c
@@ -66,7 +66,7 @@ static const char *nsp32_release_version = "1.2";
 /****************************************************************************
  * Supported hardware
  */
-static struct pci_device_id nsp32_pci_table[] = {
+static const struct pci_device_id nsp32_pci_table[] = {
 	{
 		.vendor      = PCI_VENDOR_ID_IODATA,
 		.device      = PCI_DEVICE_ID_NINJASCSI_32BI_CBSC_II,
diff --git a/drivers/scsi/pm8001/pm8001_defs.h b/drivers/scsi/pm8001/pm8001_defs.h
index 7871e29a820a..4e19d61dffbb 100644
--- a/drivers/scsi/pm8001/pm8001_defs.h
+++ b/drivers/scsi/pm8001/pm8001_defs.h
@@ -90,7 +90,7 @@ enum port_type {
 #define	PM8001_MAX_PORTS	 16	/* max. possible ports */
 #define	PM8001_MAX_DEVICES	 2048	/* max supported device */
 #define	PM8001_MAX_MSIX_VEC	 64	/* max msi-x int for spcv/ve */
-#define	PM8001_RESERVE_SLOT	 8
+#define	PM8001_RESERVE_SLOT	 128
 
 #define PM8001_SECTOR_SIZE	512
 #define PM8001_PAGE_SIZE_4K	4096
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index dec1e2d380f1..42a4eeac24c9 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -3472,12 +3472,13 @@ int pm8001_mpi_task_abort_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
 			   status, tag, scp);
 	switch (status) {
 	case IO_SUCCESS:
-		pm8001_dbg(pm8001_ha, EH, "IO_SUCCESS\n");
+		pm8001_dbg(pm8001_ha, FAIL, "ABORT IO_SUCCESS for tag %#x\n",
+			   tag);
 		ts->resp = SAS_TASK_COMPLETE;
 		ts->stat = SAS_SAM_STAT_GOOD;
 		break;
 	case IO_NOT_VALID:
-		pm8001_dbg(pm8001_ha, EH, "IO_NOT_VALID\n");
+		pm8001_dbg(pm8001_ha, FAIL, "IO_NOT_VALID for tag %#x\n", tag);
 		ts->resp = TMF_RESP_FUNC_FAILED;
 		break;
 	}
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 2a7822fd613e..599410bcdfea 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -736,7 +736,7 @@ static int pm8001_init_sas_add(struct pm8001_hba_info *pm8001_ha)
 		return -EIO;
 	}
 	time_remaining = wait_for_completion_timeout(&completion,
-				msecs_to_jiffies(60*1000)); // 1 min
+				secs_to_jiffies(60)); // 1 min
 	if (!time_remaining) {
 		kfree(payload.func_specific);
 		pm8001_dbg(pm8001_ha, FAIL, "get_nvmd_req timeout\n");
@@ -1435,7 +1435,7 @@ err_out_disable:
 /* update of pci device, vendor id and driver data with
  * unique value for each of the controller
  */
-static struct pci_device_id pm8001_pci_table[] = {
+static const struct pci_device_id pm8001_pci_table[] = {
 	{ PCI_VDEVICE(PMC_Sierra, 0x8001), chip_8001 },
 	{ PCI_VDEVICE(PMC_Sierra, 0x8006), chip_8006 },
 	{ PCI_VDEVICE(ADAPTEC2, 0x8006), chip_8006 },
diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
index d80cffd25a6e..183ce00aa671 100644
--- a/drivers/scsi/pm8001/pm8001_sas.c
+++ b/drivers/scsi/pm8001/pm8001_sas.c
@@ -101,6 +101,63 @@ int pm8001_tag_alloc(struct pm8001_hba_info *pm8001_ha, u32 *tag_out)
 	return 0;
 }
 
+static void pm80xx_get_tag_opcodes(struct sas_task *task, int *ata_op,
+								   int *ata_tag, bool *task_aborted)
+{
+	unsigned long flags;
+	struct ata_queued_cmd *qc = NULL;
+
+	*ata_op = 0;
+	*ata_tag = -1;
+	*task_aborted = false;
+
+	if (!task)
+		return;
+
+	spin_lock_irqsave(&task->task_state_lock, flags);
+	if (unlikely((task->task_state_flags & SAS_TASK_STATE_ABORTED)))
+		*task_aborted = true;
+	spin_unlock_irqrestore(&task->task_state_lock, flags);
+
+	if (task->task_proto == SAS_PROTOCOL_STP) {
+		// sas_ata_qc_issue path uses SAS_PROTOCOL_STP.
+		// This only works for scsi + libsas + libata users.
+		qc = task->uldd_task;
+		if (qc) {
+			*ata_op = qc->tf.command;
+			*ata_tag = qc->tag;
+		}
+	}
+}
+
+void pm80xx_show_pending_commands(struct pm8001_hba_info *pm8001_ha,
+				  struct pm8001_device *target_pm8001_dev)
+{
+	int i = 0, ata_op = 0, ata_tag = -1;
+	struct pm8001_ccb_info *ccb = NULL;
+	struct sas_task *task = NULL;
+	struct pm8001_device *pm8001_dev = NULL;
+	bool task_aborted;
+
+	for (i = 0; i < pm8001_ha->ccb_count; i++) {
+		ccb = &pm8001_ha->ccb_info[i];
+		if (ccb->ccb_tag == PM8001_INVALID_TAG)
+			continue;
+		pm8001_dev = ccb->device;
+		if (target_pm8001_dev && pm8001_dev &&
+		    target_pm8001_dev != pm8001_dev)
+			continue;
+		task = ccb->task;
+		pm80xx_get_tag_opcodes(task, &ata_op, &ata_tag, &task_aborted);
+		pm8001_dbg(pm8001_ha, FAIL,
+			"tag %#x, device %#x task %p task aborted %d ata opcode %#x ata tag %d\n",
+			ccb->ccb_tag,
+			(pm8001_dev ? pm8001_dev->device_id : 0),
+			task, task_aborted,
+			ata_op, ata_tag);
+	}
+}
+
 /**
  * pm8001_mem_alloc - allocate memory for pm8001.
  * @pdev: pci device.
@@ -374,23 +431,6 @@ static int pm8001_task_prep_ssp(struct pm8001_hba_info *pm8001_ha,
 	return PM8001_CHIP_DISP->ssp_io_req(pm8001_ha, ccb);
 }
 
- /* Find the local port id that's attached to this device */
-static int sas_find_local_port_id(struct domain_device *dev)
-{
-	struct domain_device *pdev = dev->parent;
-
-	/* Directly attached device */
-	if (!pdev)
-		return dev->port->id;
-	while (pdev) {
-		struct domain_device *pdev_p = pdev->parent;
-		if (!pdev_p)
-			return pdev->port->id;
-		pdev = pdev->parent;
-	}
-	return 0;
-}
-
 #define DEV_IS_GONE(pm8001_dev)	\
 	((!pm8001_dev || (pm8001_dev->dev_type == SAS_PHY_UNUSED)))
 
@@ -463,10 +503,10 @@ int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags)
 	spin_lock_irqsave(&pm8001_ha->lock, flags);
 
 	pm8001_dev = dev->lldd_dev;
-	port = &pm8001_ha->port[sas_find_local_port_id(dev)];
+	port = pm8001_ha->phy[pm8001_dev->attached_phy].port;
 
 	if (!internal_abort &&
-	    (DEV_IS_GONE(pm8001_dev) || !port->port_attached)) {
+	    (DEV_IS_GONE(pm8001_dev) || !port || !port->port_attached)) {
 		ts->resp = SAS_TASK_UNDELIVERED;
 		ts->stat = SAS_PHY_DOWN;
 		if (sas_protocol_ata(task_proto)) {
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index d3bd8683f344..315f6a7523f0 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -786,6 +786,8 @@ static inline void pm8001_ccb_task_free_done(struct pm8001_hba_info *pm8001_ha,
 }
 void pm8001_setds_completion(struct domain_device *dev);
 void pm8001_tmf_aborted(struct sas_task *task);
+void pm80xx_show_pending_commands(struct pm8001_hba_info *pm8001_ha,
+				  struct pm8001_device *dev);
 
 #endif
 
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index e65951dd2024..5b373c53c036 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -2246,7 +2246,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha,
 	u32 param;
 	u32 status;
 	u32 tag;
-	int i, j;
+	int i, j, ata_tag = -1;
 	u8 sata_addr_low[4];
 	u32 temp_sata_addr_low, temp_sata_addr_hi;
 	u8 sata_addr_hi[4];
@@ -2256,6 +2256,7 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha,
 	u32 *sata_resp;
 	struct pm8001_device *pm8001_dev;
 	unsigned long flags;
+	struct ata_queued_cmd *qc;
 
 	psataPayload = (struct sata_completion_resp *)(piomb + 4);
 	status = le32_to_cpu(psataPayload->status);
@@ -2267,8 +2268,11 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha,
 	pm8001_dev = ccb->device;
 
 	if (t) {
-		if (t->dev && (t->dev->lldd_dev))
+		if (t->dev && (t->dev->lldd_dev)) {
 			pm8001_dev = t->dev->lldd_dev;
+			qc = t->uldd_task;
+			ata_tag = qc ? qc->tag : -1;
+		}
 	} else {
 		pm8001_dbg(pm8001_ha, FAIL, "task null, freeing CCB tag %d\n",
 			   ccb->ccb_tag);
@@ -2276,16 +2280,14 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha,
 		return;
 	}
 
-
 	if (pm8001_dev && unlikely(!t->lldd_task || !t->dev))
 		return;
 
 	ts = &t->task_status;
-
 	if (status != IO_SUCCESS) {
 		pm8001_dbg(pm8001_ha, FAIL,
-			"IO failed device_id %u status 0x%x tag %d\n",
-			pm8001_dev->device_id, status, tag);
+			"IO failed status %#x pm80xx tag %#x ata tag %d\n",
+			status, tag, ata_tag);
 	}
 
 	/* Print sas address of IO failed device */
@@ -2667,13 +2669,19 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha,
 
 	/* Check if this is NCQ error */
 	if (event == IO_XFER_ERROR_ABORTED_NCQ_MODE) {
+		/* tag value is invalid with this event */
+		pm8001_dbg(pm8001_ha, FAIL, "NCQ ERROR for device %#x tag %#x\n",
+			dev_id, tag);
+
 		/* find device using device id */
 		pm8001_dev = pm8001_find_dev(pm8001_ha, dev_id);
 		/* send read log extension by aborting the link - libata does what we want */
-		if (pm8001_dev)
+		if (pm8001_dev) {
+			pm80xx_show_pending_commands(pm8001_ha, pm8001_dev);
 			pm8001_handle_event(pm8001_ha,
 				pm8001_dev,
 				IO_XFER_ERROR_ABORTED_NCQ_MODE);
+		}
 		return;
 	}
 
@@ -3336,10 +3344,11 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	u32 phy_id =
 		le32_to_cpu(pPayload->phyid) & 0xFF;
 	struct pm8001_phy *phy = &pm8001_ha->phy[phy_id];
+	u32 tag = le32_to_cpu(pPayload->tag);
 
 	pm8001_dbg(pm8001_ha, INIT,
-		   "phy start resp status:0x%x, phyid:0x%x\n",
-		   status, phy_id);
+		   "phy start resp status:0x%x, phyid:0x%x, tag 0x%x\n",
+		   status, phy_id, tag);
 	if (status == 0)
 		phy->phy_state = PHY_LINK_DOWN;
 
@@ -3348,6 +3357,8 @@ static int mpi_phy_start_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		complete(phy->enable_completion);
 		phy->enable_completion = NULL;
 	}
+
+	pm8001_tag_free(pm8001_ha, tag);
 	return 0;
 
 }
@@ -3628,8 +3639,10 @@ static int mpi_phy_stop_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	u32 phyid =
 		le32_to_cpu(pPayload->phyid) & 0xFF;
 	struct pm8001_phy *phy = &pm8001_ha->phy[phyid];
-	pm8001_dbg(pm8001_ha, MSG, "phy:0x%x status:0x%x\n",
-		   phyid, status);
+	u32 tag = le32_to_cpu(pPayload->tag);
+
+	pm8001_dbg(pm8001_ha, MSG, "phy:0x%x status:0x%x tag 0x%x\n", phyid,
+		   status, tag);
 	if (status == PHY_STOP_SUCCESS ||
 		status == PHY_STOP_ERR_DEVICE_ATTACHED) {
 		phy->phy_state = PHY_LINK_DISABLE;
@@ -3637,6 +3650,7 @@ static int mpi_phy_stop_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		phy->sas_phy.linkrate = SAS_PHY_DISABLED;
 	}
 
+	pm8001_tag_free(pm8001_ha, tag);
 	return 0;
 }
 
@@ -3655,10 +3669,9 @@ static int mpi_set_controller_config_resp(struct pm8001_hba_info *pm8001_ha,
 	u32 tag = le32_to_cpu(pPayload->tag);
 
 	pm8001_dbg(pm8001_ha, MSG,
-		   "SET CONTROLLER RESP: status 0x%x qlfr_pgcd 0x%x\n",
-		   status, err_qlfr_pgcd);
+		   "SET CONTROLLER RESP: status 0x%x qlfr_pgcd 0x%x tag 0x%x\n",
+		   status, err_qlfr_pgcd, tag);
 	pm8001_tag_free(pm8001_ha, tag);
-
 	return 0;
 }
 
@@ -4632,9 +4645,16 @@ static int
 pm80xx_chip_phy_start_req(struct pm8001_hba_info *pm8001_ha, u8 phy_id)
 {
 	struct phy_start_req payload;
-	u32 tag = 0x01;
+	int ret;
+	u32 tag;
 	u32 opcode = OPC_INB_PHYSTART;
 
+	ret = pm8001_tag_alloc(pm8001_ha, &tag);
+	if (ret) {
+		pm8001_dbg(pm8001_ha, FAIL, "Tag allocation failed\n");
+		return ret;
+	}
+
 	memset(&payload, 0, sizeof(payload));
 	payload.tag = cpu_to_le32(tag);
 
@@ -4670,9 +4690,16 @@ static int pm80xx_chip_phy_stop_req(struct pm8001_hba_info *pm8001_ha,
 	u8 phy_id)
 {
 	struct phy_stop_req payload;
-	u32 tag = 0x01;
+	int ret;
+	u32 tag;
 	u32 opcode = OPC_INB_PHYSTOP;
 
+	ret = pm8001_tag_alloc(pm8001_ha, &tag);
+	if (ret) {
+		pm8001_dbg(pm8001_ha, FAIL, "Tag allocation failed\n");
+		return ret;
+	}
+
 	memset(&payload, 0, sizeof(payload));
 	payload.tag = cpu_to_le32(tag);
 	payload.phy_id = cpu_to_le32(phy_id);
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 4c5881917d76..3ba53916fd86 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -113,7 +113,7 @@ static struct pmcraid_chip_details pmcraid_chip_cfg[] = {
 /*
  * PCI device ids supported by pmcraid driver
  */
-static struct pci_device_id pmcraid_pci_table[] = {
+static const struct pci_device_id pmcraid_pci_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_PMC, PCI_DEVICE_ID_PMC_MAXRAID),
 	  0, 0, (kernel_ulong_t)&pmcraid_chip_cfg[0]
 	},
@@ -125,7 +125,7 @@ MODULE_DEVICE_TABLE(pci, pmcraid_pci_table);
 
 
 /**
- * pmcraid_slave_alloc - Prepare for commands to a device
+ * pmcraid_sdev_init - Prepare for commands to a device
  * @scsi_dev: scsi device struct
  *
  * This function is called by mid-layer prior to sending any command to the new
@@ -136,7 +136,7 @@ MODULE_DEVICE_TABLE(pci, pmcraid_pci_table);
  * Return value:
  *	  0 on success / -ENXIO if device does not exist
  */
-static int pmcraid_slave_alloc(struct scsi_device *scsi_dev)
+static int pmcraid_sdev_init(struct scsi_device *scsi_dev)
 {
 	struct pmcraid_resource_entry *temp, *res = NULL;
 	struct pmcraid_instance *pinstance;
@@ -197,7 +197,7 @@ static int pmcraid_slave_alloc(struct scsi_device *scsi_dev)
 }
 
 /**
- * pmcraid_device_configure - Configures a SCSI device
+ * pmcraid_sdev_configure - Configures a SCSI device
  * @scsi_dev: scsi device struct
  * @lim: queue limits
  *
@@ -210,8 +210,8 @@ static int pmcraid_slave_alloc(struct scsi_device *scsi_dev)
  * Return value:
  *	  0 on success
  */
-static int pmcraid_device_configure(struct scsi_device *scsi_dev,
-		struct queue_limits *lim)
+static int pmcraid_sdev_configure(struct scsi_device *scsi_dev,
+				  struct queue_limits *lim)
 {
 	struct pmcraid_resource_entry *res = scsi_dev->hostdata;
 
@@ -248,17 +248,17 @@ static int pmcraid_device_configure(struct scsi_device *scsi_dev,
 }
 
 /**
- * pmcraid_slave_destroy - Unconfigure a SCSI device before removing it
+ * pmcraid_sdev_destroy - Unconfigure a SCSI device before removing it
  *
  * @scsi_dev: scsi device struct
  *
  * This is called by mid-layer before removing a device. Pointer assignments
- * done in pmcraid_slave_alloc will be reset to NULL here.
+ * done in pmcraid_sdev_init will be reset to NULL here.
  *
  * Return value
  *   none
  */
-static void pmcraid_slave_destroy(struct scsi_device *scsi_dev)
+static void pmcraid_sdev_destroy(struct scsi_device *scsi_dev)
 {
 	struct pmcraid_resource_entry *res;
 
@@ -3668,9 +3668,9 @@ static const struct scsi_host_template pmcraid_host_template = {
 	.eh_device_reset_handler = pmcraid_eh_device_reset_handler,
 	.eh_host_reset_handler = pmcraid_eh_host_reset_handler,
 
-	.slave_alloc = pmcraid_slave_alloc,
-	.device_configure = pmcraid_device_configure,
-	.slave_destroy = pmcraid_slave_destroy,
+	.sdev_init = pmcraid_sdev_init,
+	.sdev_configure = pmcraid_sdev_configure,
+	.sdev_destroy = pmcraid_sdev_destroy,
 	.change_queue_depth = pmcraid_change_queue_depth,
 	.can_queue = PMCRAID_MAX_IO_CMD,
 	.this_id = -1,
diff --git a/drivers/scsi/ps3rom.c b/drivers/scsi/ps3rom.c
index 90495a832f34..92fe5c5c5bb0 100644
--- a/drivers/scsi/ps3rom.c
+++ b/drivers/scsi/ps3rom.c
@@ -61,7 +61,8 @@ enum lv1_atapi_in_out {
 };
 
 
-static int ps3rom_slave_configure(struct scsi_device *scsi_dev)
+static int ps3rom_sdev_configure(struct scsi_device *scsi_dev,
+				 struct queue_limits *lim)
 {
 	struct ps3rom_private *priv = shost_priv(scsi_dev->host);
 	struct ps3_storage_device *dev = priv->dev;
@@ -325,7 +326,7 @@ done:
 
 static const struct scsi_host_template ps3rom_host_template = {
 	.name =			DEVICE_NAME,
-	.slave_configure =	ps3rom_slave_configure,
+	.sdev_configure =	ps3rom_sdev_configure,
 	.queuecommand =		ps3rom_queuecommand,
 	.can_queue =		1,
 	.this_id =		7,
diff --git a/drivers/scsi/qedf/qedf_attr.c b/drivers/scsi/qedf/qedf_attr.c
index 8d8c760eee43..769da92ee20d 100644
--- a/drivers/scsi/qedf/qedf_attr.c
+++ b/drivers/scsi/qedf/qedf_attr.c
@@ -104,7 +104,7 @@ void qedf_capture_grc_dump(struct qedf_ctx *qedf)
 
 static ssize_t
 qedf_sysfs_read_grcdump(struct file *filep, struct kobject *kobj,
-			struct bin_attribute *ba, char *buf, loff_t off,
+			const struct bin_attribute *ba, char *buf, loff_t off,
 			size_t count)
 {
 	ssize_t ret = 0;
@@ -124,7 +124,7 @@ qedf_sysfs_read_grcdump(struct file *filep, struct kobject *kobj,
 
 static ssize_t
 qedf_sysfs_write_grcdump(struct file *filep, struct kobject *kobj,
-			struct bin_attribute *ba, char *buf, loff_t off,
+			const struct bin_attribute *ba, char *buf, loff_t off,
 			size_t count)
 {
 	struct fc_lport *lport = NULL;
@@ -160,14 +160,14 @@ qedf_sysfs_write_grcdump(struct file *filep, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_grcdump_attr = {
+static const struct bin_attribute sysfs_grcdump_attr = {
 	.attr = {
 		.name = "grcdump",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 0,
-	.read = qedf_sysfs_read_grcdump,
-	.write = qedf_sysfs_write_grcdump,
+	.read_new = qedf_sysfs_read_grcdump,
+	.write_new = qedf_sysfs_write_grcdump,
 };
 
 static struct sysfs_bin_attrs bin_file_entries[] = {
diff --git a/drivers/scsi/qedf/qedf_dbg.h b/drivers/scsi/qedf/qedf_dbg.h
index 5ec2b817c694..eeb6c841dacb 100644
--- a/drivers/scsi/qedf/qedf_dbg.h
+++ b/drivers/scsi/qedf/qedf_dbg.h
@@ -100,7 +100,7 @@ struct Scsi_Host;
 
 struct sysfs_bin_attrs {
 	char *name;
-	struct bin_attribute *attr;
+	const struct bin_attribute *attr;
 };
 
 extern int qedf_alloc_grc_dump_buf(uint8_t **buf, uint32_t len);
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index d2f47dc31dbf..436bd29d5eba 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -982,7 +982,8 @@ static int qedf_eh_host_reset(struct scsi_cmnd *sc_cmd)
 	return SUCCESS;
 }
 
-static int qedf_slave_configure(struct scsi_device *sdev)
+static int qedf_sdev_configure(struct scsi_device *sdev,
+			       struct queue_limits *lim)
 {
 	if (qedf_queue_depth) {
 		scsi_change_queue_depth(sdev, qedf_queue_depth);
@@ -1003,7 +1004,7 @@ static const struct scsi_host_template qedf_host_template = {
 	.eh_device_reset_handler = qedf_eh_device_reset, /* lun reset */
 	.eh_target_reset_handler = qedf_eh_target_reset, /* target reset */
 	.eh_host_reset_handler  = qedf_eh_host_reset,
-	.slave_configure	= qedf_slave_configure,
+	.sdev_configure	= qedf_sdev_configure,
 	.dma_boundary = QED_HW_DMA_BOUNDARY,
 	.sg_tablesize = QEDF_MAX_BDS_PER_CMD,
 	.can_queue = FCOE_PARAMS_NUM_TASKS,
diff --git a/drivers/scsi/qedi/qedi_dbg.h b/drivers/scsi/qedi/qedi_dbg.h
index fdda12ef13b0..5a1ec4542183 100644
--- a/drivers/scsi/qedi/qedi_dbg.h
+++ b/drivers/scsi/qedi/qedi_dbg.h
@@ -91,7 +91,7 @@ struct Scsi_Host;
 
 struct sysfs_bin_attrs {
 	char *name;
-	struct bin_attribute *attr;
+	const struct bin_attribute *attr;
 };
 
 int qedi_create_sysfs_attr(struct Scsi_Host *shost,
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index 628d59dda20c..c9539897048a 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1961,13 +1961,11 @@ static int qedi_cpu_online(unsigned int cpu)
 	struct qedi_percpu_s *p = this_cpu_ptr(&qedi_percpu);
 	struct task_struct *thread;
 
-	thread = kthread_create_on_node(qedi_percpu_io_thread, (void *)p,
-					cpu_to_node(cpu),
-					"qedi_thread/%d", cpu);
+	thread = kthread_create_on_cpu(qedi_percpu_io_thread, (void *)p,
+				       cpu, "qedi_thread/%d");
 	if (IS_ERR(thread))
 		return PTR_ERR(thread);
 
-	kthread_bind(thread, cpu);
 	p->iothread = thread;
 	wake_up_process(thread);
 	return 0;
@@ -2869,7 +2867,7 @@ static void qedi_remove(struct pci_dev *pdev)
 	__qedi_remove(pdev, QEDI_MODE_NORMAL);
 }
 
-static struct pci_device_id qedi_pci_tbl[] = {
+static const struct pci_device_id qedi_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x165E) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, 0x8084) },
 	{ 0 },
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 8958547ac111..47d74f881948 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -501,7 +501,7 @@ struct qla_boards {
 };
 
 /* NOTE: the last argument in each entry is used to index ql1280_board_tbl */
-static struct pci_device_id qla1280_pci_tbl[] = {
+static const struct pci_device_id qla1280_pci_tbl[] = {
 	{PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP12160,
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
 	{PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP1020,
@@ -1159,7 +1159,7 @@ qla1280_set_target_parameters(struct scsi_qla_host *ha, int bus, int target)
 
 
 /**************************************************************************
- *   qla1280_slave_configure
+ *   qla1280_sdev_configure
  *
  * Description:
  *   Determines the queue depth for a given device.  There are two ways
@@ -1170,7 +1170,7 @@ qla1280_set_target_parameters(struct scsi_qla_host *ha, int bus, int target)
  *   default queue depth (dependent on the number of hardware SCBs).
  **************************************************************************/
 static int
-qla1280_slave_configure(struct scsi_device *device)
+qla1280_sdev_configure(struct scsi_device *device, struct queue_limits *lim)
 {
 	struct scsi_qla_host *ha;
 	int default_depth = 3;
@@ -2867,7 +2867,7 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 			dprintk(3, "S/G Segment phys_addr=%x %x, len=0x%x\n",
 				cpu_to_le32(upper_32_bits(dma_handle)),
 				cpu_to_le32(lower_32_bits(dma_handle)),
-				cpu_to_le32(sg_dma_len(sg_next(s))));
+				cpu_to_le32(sg_dma_len(s)));
 			remseg--;
 		}
 		dprintk(5, "qla1280_64bit_start_scsi: Scatter/gather "
@@ -4121,7 +4121,7 @@ static const struct scsi_host_template qla1280_driver_template = {
 	.proc_name		= "qla1280",
 	.name			= "Qlogic ISP 1280/12160",
 	.info			= qla1280_info,
-	.slave_configure	= qla1280_slave_configure,
+	.sdev_configure		= qla1280_sdev_configure,
 	.queuecommand		= qla1280_queuecommand,
 	.eh_abort_handler	= qla1280_eh_abort,
 	.eh_device_reset_handler= qla1280_eh_device_reset,
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index e6ece30c4348..dcb0c2af1fa7 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -17,7 +17,7 @@ static int qla24xx_vport_disable(struct fc_vport *, bool);
 
 static ssize_t
 qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr,
+			   const struct bin_attribute *bin_attr,
 			   char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -58,7 +58,7 @@ qla2x00_sysfs_read_fw_dump(struct file *filp, struct kobject *kobj,
 
 static ssize_t
 qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr,
+			    const struct bin_attribute *bin_attr,
 			    char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -168,19 +168,19 @@ qla2x00_sysfs_write_fw_dump(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_fw_dump_attr = {
+static const struct bin_attribute sysfs_fw_dump_attr = {
 	.attr = {
 		.name = "fw_dump",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 0,
-	.read = qla2x00_sysfs_read_fw_dump,
-	.write = qla2x00_sysfs_write_fw_dump,
+	.read_new = qla2x00_sysfs_read_fw_dump,
+	.write_new = qla2x00_sysfs_write_fw_dump,
 };
 
 static ssize_t
 qla2x00_sysfs_read_nvram(struct file *filp, struct kobject *kobj,
-			 struct bin_attribute *bin_attr,
+			 const struct bin_attribute *bin_attr,
 			 char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -220,7 +220,7 @@ skip:
 
 static ssize_t
 qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr,
+			  const struct bin_attribute *bin_attr,
 			  char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -282,19 +282,19 @@ qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_nvram_attr = {
+static const struct bin_attribute sysfs_nvram_attr = {
 	.attr = {
 		.name = "nvram",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 512,
-	.read = qla2x00_sysfs_read_nvram,
-	.write = qla2x00_sysfs_write_nvram,
+	.read_new = qla2x00_sysfs_read_nvram,
+	.write_new = qla2x00_sysfs_write_nvram,
 };
 
 static ssize_t
 qla2x00_sysfs_read_optrom(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr,
+			  const struct bin_attribute *bin_attr,
 			  char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -318,7 +318,7 @@ out:
 
 static ssize_t
 qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr,
+			   const struct bin_attribute *bin_attr,
 			   char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -344,19 +344,19 @@ qla2x00_sysfs_write_optrom(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_optrom_attr = {
+static const struct bin_attribute sysfs_optrom_attr = {
 	.attr = {
 		.name = "optrom",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 0,
-	.read = qla2x00_sysfs_read_optrom,
-	.write = qla2x00_sysfs_write_optrom,
+	.read_new = qla2x00_sysfs_read_optrom,
+	.write_new = qla2x00_sysfs_write_optrom,
 };
 
 static ssize_t
 qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr,
+			       const struct bin_attribute *bin_attr,
 			       char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -529,18 +529,18 @@ out:
 	return rval;
 }
 
-static struct bin_attribute sysfs_optrom_ctl_attr = {
+static const struct bin_attribute sysfs_optrom_ctl_attr = {
 	.attr = {
 		.name = "optrom_ctl",
 		.mode = S_IWUSR,
 	},
 	.size = 0,
-	.write = qla2x00_sysfs_write_optrom_ctl,
+	.write_new = qla2x00_sysfs_write_optrom_ctl,
 };
 
 static ssize_t
 qla2x00_sysfs_read_vpd(struct file *filp, struct kobject *kobj,
-		       struct bin_attribute *bin_attr,
+		       const struct bin_attribute *bin_attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -587,7 +587,7 @@ skip:
 
 static ssize_t
 qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr,
+			const struct bin_attribute *bin_attr,
 			char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -642,19 +642,19 @@ qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_vpd_attr = {
+static const struct bin_attribute sysfs_vpd_attr = {
 	.attr = {
 		.name = "vpd",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 0,
-	.read = qla2x00_sysfs_read_vpd,
-	.write = qla2x00_sysfs_write_vpd,
+	.read_new = qla2x00_sysfs_read_vpd,
+	.write_new = qla2x00_sysfs_write_vpd,
 };
 
 static ssize_t
 qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj,
-		       struct bin_attribute *bin_attr,
+		       const struct bin_attribute *bin_attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -679,18 +679,18 @@ qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_sfp_attr = {
+static const struct bin_attribute sysfs_sfp_attr = {
 	.attr = {
 		.name = "sfp",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = SFP_DEV_SIZE,
-	.read = qla2x00_sysfs_read_sfp,
+	.read_new = qla2x00_sysfs_read_sfp,
 };
 
 static ssize_t
 qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr,
+			const struct bin_attribute *bin_attr,
 			char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -823,19 +823,19 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_reset_attr = {
+static const struct bin_attribute sysfs_reset_attr = {
 	.attr = {
 		.name = "reset",
 		.mode = S_IWUSR,
 	},
 	.size = 0,
-	.write = qla2x00_sysfs_write_reset,
+	.write_new = qla2x00_sysfs_write_reset,
 };
 
 static ssize_t
 qla2x00_issue_logo(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr,
-			char *buf, loff_t off, size_t count)
+		   const struct bin_attribute *bin_attr,
+		   char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
 	    struct device, kobj)));
@@ -866,18 +866,18 @@ qla2x00_issue_logo(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_issue_logo_attr = {
+static const struct bin_attribute sysfs_issue_logo_attr = {
 	.attr = {
 		.name = "issue_logo",
 		.mode = S_IWUSR,
 	},
 	.size = 0,
-	.write = qla2x00_issue_logo,
+	.write_new = qla2x00_issue_logo,
 };
 
 static ssize_t
 qla2x00_sysfs_read_xgmac_stats(struct file *filp, struct kobject *kobj,
-		       struct bin_attribute *bin_attr,
+		       const struct bin_attribute *bin_attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -929,18 +929,18 @@ do_read:
 	return count;
 }
 
-static struct bin_attribute sysfs_xgmac_stats_attr = {
+static const struct bin_attribute sysfs_xgmac_stats_attr = {
 	.attr = {
 		.name = "xgmac_stats",
 		.mode = S_IRUSR,
 	},
 	.size = 0,
-	.read = qla2x00_sysfs_read_xgmac_stats,
+	.read_new = qla2x00_sysfs_read_xgmac_stats,
 };
 
 static ssize_t
 qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj,
-		       struct bin_attribute *bin_attr,
+		       const struct bin_attribute *bin_attr,
 		       char *buf, loff_t off, size_t count)
 {
 	struct scsi_qla_host *vha = shost_priv(dev_to_shost(container_of(kobj,
@@ -987,18 +987,18 @@ do_read:
 	return count;
 }
 
-static struct bin_attribute sysfs_dcbx_tlv_attr = {
+static const struct bin_attribute sysfs_dcbx_tlv_attr = {
 	.attr = {
 		.name = "dcbx_tlv",
 		.mode = S_IRUSR,
 	},
 	.size = 0,
-	.read = qla2x00_sysfs_read_dcbx_tlv,
+	.read_new = qla2x00_sysfs_read_dcbx_tlv,
 };
 
 static struct sysfs_entry {
 	char *name;
-	struct bin_attribute *attr;
+	const struct bin_attribute *attr;
 	int type;
 } bin_file_entries[] = {
 	{ "fw_dump", &sysfs_fw_dump_attr, },
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 15066c112817..cb95b7b12051 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4098,6 +4098,8 @@ struct qla_hw_data {
 		uint32_t	npiv_supported		:1;
 		uint32_t	pci_channel_io_perm_failure	:1;
 		uint32_t	fce_enabled		:1;
+		uint32_t	user_enabled_fce	:1;
+		uint32_t	fce_dump_buf_alloced	:1;
 		uint32_t	fac_supported		:1;
 
 		uint32_t	chip_reset_done		:1;
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index a1545dad0c0c..08273520c777 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -409,26 +409,31 @@ qla2x00_dfs_fce_show(struct seq_file *s, void *unused)
 
 	mutex_lock(&ha->fce_mutex);
 
-	seq_puts(s, "FCE Trace Buffer\n");
-	seq_printf(s, "In Pointer = %llx\n\n", (unsigned long long)ha->fce_wr);
-	seq_printf(s, "Base = %llx\n\n", (unsigned long long) ha->fce_dma);
-	seq_puts(s, "FCE Enable Registers\n");
-	seq_printf(s, "%08x %08x %08x %08x %08x %08x\n",
-	    ha->fce_mb[0], ha->fce_mb[2], ha->fce_mb[3], ha->fce_mb[4],
-	    ha->fce_mb[5], ha->fce_mb[6]);
-
-	fce = (uint32_t *) ha->fce;
-	fce_start = (unsigned long long) ha->fce_dma;
-	for (cnt = 0; cnt < fce_calc_size(ha->fce_bufs) / 4; cnt++) {
-		if (cnt % 8 == 0)
-			seq_printf(s, "\n%llx: ",
-			    (unsigned long long)((cnt * 4) + fce_start));
-		else
-			seq_putc(s, ' ');
-		seq_printf(s, "%08x", *fce++);
-	}
+	if (ha->flags.user_enabled_fce) {
+		seq_puts(s, "FCE Trace Buffer\n");
+		seq_printf(s, "In Pointer = %llx\n\n", (unsigned long long)ha->fce_wr);
+		seq_printf(s, "Base = %llx\n\n", (unsigned long long)ha->fce_dma);
+		seq_puts(s, "FCE Enable Registers\n");
+		seq_printf(s, "%08x %08x %08x %08x %08x %08x\n",
+			   ha->fce_mb[0], ha->fce_mb[2], ha->fce_mb[3], ha->fce_mb[4],
+			   ha->fce_mb[5], ha->fce_mb[6]);
+
+		fce = (uint32_t *)ha->fce;
+		fce_start = (unsigned long long)ha->fce_dma;
+		for (cnt = 0; cnt < fce_calc_size(ha->fce_bufs) / 4; cnt++) {
+			if (cnt % 8 == 0)
+				seq_printf(s, "\n%llx: ",
+					   (unsigned long long)((cnt * 4) + fce_start));
+			else
+				seq_putc(s, ' ');
+			seq_printf(s, "%08x", *fce++);
+		}
 
-	seq_puts(s, "\nEnd\n");
+		seq_puts(s, "\nEnd\n");
+	} else {
+		seq_puts(s, "FCE Trace is currently not enabled\n");
+		seq_puts(s, "\techo [ 1 | 0 ] > fce\n");
+	}
 
 	mutex_unlock(&ha->fce_mutex);
 
@@ -467,7 +472,7 @@ qla2x00_dfs_fce_release(struct inode *inode, struct file *file)
 	struct qla_hw_data *ha = vha->hw;
 	int rval;
 
-	if (ha->flags.fce_enabled)
+	if (ha->flags.fce_enabled || !ha->fce)
 		goto out;
 
 	mutex_lock(&ha->fce_mutex);
@@ -488,11 +493,88 @@ out:
 	return single_release(inode, file);
 }
 
+static ssize_t
+qla2x00_dfs_fce_write(struct file *file, const char __user *buffer,
+		      size_t count, loff_t *pos)
+{
+	struct seq_file *s = file->private_data;
+	struct scsi_qla_host *vha = s->private;
+	struct qla_hw_data *ha = vha->hw;
+	char *buf;
+	int rc = 0;
+	unsigned long enable;
+
+	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
+	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha)) {
+		ql_dbg(ql_dbg_user, vha, 0xd034,
+		       "this adapter does not support FCE.");
+		return -EINVAL;
+	}
+
+	buf = memdup_user_nul(buffer, count);
+	if (IS_ERR(buf)) {
+		ql_dbg(ql_dbg_user, vha, 0xd037,
+		    "fail to copy user buffer.");
+		return PTR_ERR(buf);
+	}
+
+	enable = kstrtoul(buf, 0, 0);
+	rc = count;
+
+	mutex_lock(&ha->fce_mutex);
+
+	if (enable) {
+		if (ha->flags.user_enabled_fce) {
+			mutex_unlock(&ha->fce_mutex);
+			goto out_free;
+		}
+		ha->flags.user_enabled_fce = 1;
+		if (!ha->fce) {
+			rc = qla2x00_alloc_fce_trace(vha);
+			if (rc) {
+				ha->flags.user_enabled_fce = 0;
+				mutex_unlock(&ha->fce_mutex);
+				goto out_free;
+			}
+
+			/* adjust fw dump buffer to take into account of this feature */
+			if (!ha->flags.fce_dump_buf_alloced)
+				qla2x00_alloc_fw_dump(vha);
+		}
+
+		if (!ha->flags.fce_enabled)
+			qla_enable_fce_trace(vha);
+
+		ql_dbg(ql_dbg_user, vha, 0xd045, "User enabled FCE .\n");
+	} else {
+		if (!ha->flags.user_enabled_fce) {
+			mutex_unlock(&ha->fce_mutex);
+			goto out_free;
+		}
+		ha->flags.user_enabled_fce = 0;
+		if (ha->flags.fce_enabled) {
+			qla2x00_disable_fce_trace(vha, NULL, NULL);
+			ha->flags.fce_enabled = 0;
+		}
+
+		qla2x00_free_fce_trace(ha);
+		/* no need to re-adjust fw dump buffer */
+
+		ql_dbg(ql_dbg_user, vha, 0xd04f, "User disabled FCE .\n");
+	}
+
+	mutex_unlock(&ha->fce_mutex);
+out_free:
+	kfree(buf);
+	return rc;
+}
+
 static const struct file_operations dfs_fce_ops = {
 	.open		= qla2x00_dfs_fce_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= qla2x00_dfs_fce_release,
+	.write		= qla2x00_dfs_fce_write,
 };
 
 static int
@@ -626,8 +708,6 @@ qla2x00_dfs_setup(scsi_qla_host_t *vha)
 	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
 	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
 		goto out;
-	if (!ha->fce)
-		goto out;
 
 	if (qla2x00_dfs_root)
 		goto create_dir;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index cededfda9d0e..e556f57c91af 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -11,6 +11,9 @@
 /*
  * Global Function Prototypes in qla_init.c source file.
  */
+int  qla2x00_alloc_fce_trace(scsi_qla_host_t *);
+void qla2x00_free_fce_trace(struct qla_hw_data *ha);
+void qla_enable_fce_trace(scsi_qla_host_t *);
 extern int qla2x00_initialize_adapter(scsi_qla_host_t *);
 extern int qla24xx_post_prli_work(struct scsi_qla_host *vha, fc_port_t *fcport);
 
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 31fc6a0eca3e..79cdfec2bca3 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -2681,7 +2681,7 @@ exit:
 	return rval;
 }
 
-static void qla_enable_fce_trace(scsi_qla_host_t *vha)
+void qla_enable_fce_trace(scsi_qla_host_t *vha)
 {
 	int rval;
 	struct qla_hw_data *ha = vha->hw;
@@ -3717,25 +3717,24 @@ qla24xx_chip_diag(scsi_qla_host_t *vha)
 	return rval;
 }
 
-static void
-qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
+int qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 {
 	dma_addr_t tc_dma;
 	void *tc;
 	struct qla_hw_data *ha = vha->hw;
 
 	if (!IS_FWI2_CAPABLE(ha))
-		return;
+		return -EINVAL;
 
 	if (!IS_QLA25XX(ha) && !IS_QLA81XX(ha) && !IS_QLA83XX(ha) &&
 	    !IS_QLA27XX(ha) && !IS_QLA28XX(ha))
-		return;
+		return -EINVAL;
 
 	if (ha->fce) {
 		ql_dbg(ql_dbg_init, vha, 0x00bd,
 		       "%s: FCE Mem is already allocated.\n",
 		       __func__);
-		return;
+		return -EIO;
 	}
 
 	/* Allocate memory for Fibre Channel Event Buffer. */
@@ -3745,7 +3744,7 @@ qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 		ql_log(ql_log_warn, vha, 0x00be,
 		       "Unable to allocate (%d KB) for FCE.\n",
 		       FCE_SIZE / 1024);
-		return;
+		return -ENOMEM;
 	}
 
 	ql_dbg(ql_dbg_init, vha, 0x00c0,
@@ -3754,6 +3753,16 @@ qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 	ha->fce_dma = tc_dma;
 	ha->fce = tc;
 	ha->fce_bufs = FCE_NUM_BUFFERS;
+	return 0;
+}
+
+void qla2x00_free_fce_trace(struct qla_hw_data *ha)
+{
+	if (!ha->fce)
+		return;
+	dma_free_coherent(&ha->pdev->dev, FCE_SIZE, ha->fce, ha->fce_dma);
+	ha->fce = NULL;
+	ha->fce_dma = 0;
 }
 
 static void
@@ -3844,9 +3853,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 		if (ha->tgt.atio_ring)
 			mq_size += ha->tgt.atio_q_length * sizeof(request_t);
 
-		qla2x00_alloc_fce_trace(vha);
-		if (ha->fce)
+		if (ha->fce) {
 			fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE;
+			ha->flags.fce_dump_buf_alloced = 1;
+		}
 		qla2x00_alloc_eft_trace(vha);
 		if (ha->eft)
 			eft_size = EFT_SIZE;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 31535beaaa16..6b9b8218b512 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1933,7 +1933,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 }
 
 static int
-qla2xxx_slave_alloc(struct scsi_device *sdev)
+qla2xxx_sdev_init(struct scsi_device *sdev)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(sdev));
 
@@ -1946,7 +1946,7 @@ qla2xxx_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-qla2xxx_slave_configure(struct scsi_device *sdev)
+qla2xxx_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	scsi_qla_host_t *vha = shost_priv(sdev->host);
 	struct req_que *req = vha->req;
@@ -1956,7 +1956,7 @@ qla2xxx_slave_configure(struct scsi_device *sdev)
 }
 
 static void
-qla2xxx_slave_destroy(struct scsi_device *sdev)
+qla2xxx_sdev_destroy(struct scsi_device *sdev)
 {
 	sdev->hostdata = NULL;
 }
@@ -8087,10 +8087,10 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.eh_bus_reset_handler	= qla2xxx_eh_bus_reset,
 	.eh_host_reset_handler	= qla2xxx_eh_host_reset,
 
-	.slave_configure	= qla2xxx_slave_configure,
+	.sdev_configure		= qla2xxx_sdev_configure,
 
-	.slave_alloc		= qla2xxx_slave_alloc,
-	.slave_destroy		= qla2xxx_slave_destroy,
+	.sdev_init		= qla2xxx_sdev_init,
+	.sdev_destroy		= qla2xxx_sdev_destroy,
 	.scan_finished		= qla2xxx_scan_finished,
 	.scan_start		= qla2xxx_scan_start,
 	.change_queue_depth	= scsi_change_queue_depth,
@@ -8116,7 +8116,7 @@ static const struct pci_error_handlers qla2xxx_err_handler = {
 	.reset_done = qla_pci_reset_done,
 };
 
-static struct pci_device_id qla2xxx_pci_tbl[] = {
+static const struct pci_device_id qla2xxx_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2100) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2200) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2300) },
diff --git a/drivers/scsi/qla4xxx/ql4_attr.c b/drivers/scsi/qla4xxx/ql4_attr.c
index abfa6ef60480..e3f85d6ea0db 100644
--- a/drivers/scsi/qla4xxx/ql4_attr.c
+++ b/drivers/scsi/qla4xxx/ql4_attr.c
@@ -10,7 +10,7 @@
 
 static ssize_t
 qla4_8xxx_sysfs_read_fw_dump(struct file *filep, struct kobject *kobj,
-			     struct bin_attribute *ba, char *buf, loff_t off,
+			     const struct bin_attribute *ba, char *buf, loff_t off,
 			     size_t count)
 {
 	struct scsi_qla_host *ha = to_qla_host(dev_to_shost(container_of(kobj,
@@ -28,7 +28,7 @@ qla4_8xxx_sysfs_read_fw_dump(struct file *filep, struct kobject *kobj,
 
 static ssize_t
 qla4_8xxx_sysfs_write_fw_dump(struct file *filep, struct kobject *kobj,
-			      struct bin_attribute *ba, char *buf, loff_t off,
+			      const struct bin_attribute *ba, char *buf, loff_t off,
 			      size_t count)
 {
 	struct scsi_qla_host *ha = to_qla_host(dev_to_shost(container_of(kobj,
@@ -104,19 +104,19 @@ qla4_8xxx_sysfs_write_fw_dump(struct file *filep, struct kobject *kobj,
 	return count;
 }
 
-static struct bin_attribute sysfs_fw_dump_attr = {
+static const struct bin_attribute sysfs_fw_dump_attr = {
 	.attr = {
 		.name = "fw_dump",
 		.mode = S_IRUSR | S_IWUSR,
 	},
 	.size = 0,
-	.read = qla4_8xxx_sysfs_read_fw_dump,
-	.write = qla4_8xxx_sysfs_write_fw_dump,
+	.read_new = qla4_8xxx_sysfs_read_fw_dump,
+	.write_new = qla4_8xxx_sysfs_write_fw_dump,
 };
 
 static struct sysfs_entry {
 	char *name;
-	struct bin_attribute *attr;
+	const struct bin_attribute *attr;
 } bin_file_entries[] = {
 	{ "fw_dump", &sysfs_fw_dump_attr },
 	{ NULL },
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index d91f54a6e752..6b0e6b4cd8af 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -160,7 +160,7 @@ static int qla4xxx_eh_abort(struct scsi_cmnd *cmd);
 static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd);
 static int qla4xxx_eh_target_reset(struct scsi_cmnd *cmd);
 static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd);
-static int qla4xxx_slave_alloc(struct scsi_device *device);
+static int qla4xxx_sdev_init(struct scsi_device *device);
 static umode_t qla4_attr_is_visible(int param_type, int param);
 static int qla4xxx_host_reset(struct Scsi_Host *shost, int reset_type);
 
@@ -234,7 +234,7 @@ static struct scsi_host_template qla4xxx_driver_template = {
 	.eh_host_reset_handler	= qla4xxx_eh_host_reset,
 	.eh_timed_out		= qla4xxx_eh_cmd_timed_out,
 
-	.slave_alloc		= qla4xxx_slave_alloc,
+	.sdev_init		= qla4xxx_sdev_init,
 	.change_queue_depth	= scsi_change_queue_depth,
 
 	.this_id		= -1,
@@ -7189,7 +7189,8 @@ exit_new_nt_list:
  *	1: if flashnode entry is non-persistent
  *	0: if flashnode entry is persistent
  **/
-static int qla4xxx_sysfs_ddb_is_non_persistent(struct device *dev, void *data)
+static int qla4xxx_sysfs_ddb_is_non_persistent(struct device *dev,
+					       const void *data)
 {
 	struct iscsi_bus_flash_session *fnode_sess;
 
@@ -9052,7 +9053,7 @@ static void qla4xxx_config_dma_addressing(struct scsi_qla_host *ha)
 	}
 }
 
-static int qla4xxx_slave_alloc(struct scsi_device *sdev)
+static int qla4xxx_sdev_init(struct scsi_device *sdev)
 {
 	struct iscsi_cls_session *cls_sess;
 	struct iscsi_session *sess;
@@ -9846,7 +9847,7 @@ static const struct pci_error_handlers qla4xxx_err_handler = {
 	.resume = qla4xxx_pci_resume,
 };
 
-static struct pci_device_id qla4xxx_pci_tbl[] = {
+static const struct pci_device_id qla4xxx_pci_tbl[] = {
 	{
 		.vendor		= PCI_VENDOR_ID_QLOGIC,
 		.device		= PCI_DEVICE_ID_QLOGIC_ISP4010,
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 74866b9f2b14..c9984ef57f26 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -975,7 +975,8 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int
 	host->sg_tablesize = QLOGICPTI_MAX_SG(num_free);
 }
 
-static int qlogicpti_slave_configure(struct scsi_device *sdev)
+static int qlogicpti_sdev_configure(struct scsi_device *sdev,
+				    struct queue_limits *lim)
 {
 	struct qlogicpti *qpti = shost_priv(sdev->host);
 	int tgt = sdev->id;
@@ -1292,7 +1293,7 @@ static const struct scsi_host_template qpti_template = {
 	.name			= "qlogicpti",
 	.info			= qlogicpti_info,
 	.queuecommand		= qlogicpti_queuecommand,
-	.slave_configure	= qlogicpti_slave_configure,
+	.sdev_configure		= qlogicpti_sdev_configure,
 	.eh_abort_handler	= qlogicpti_abort,
 	.eh_host_reset_handler	= qlogicpti_reset,
 	.can_queue		= QLOGICPTI_REQ_QUEUE_LEN,
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 680ba180a672..5ceaa4665e5d 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5879,23 +5879,24 @@ static struct sdebug_dev_info *find_build_dev_info(struct scsi_device *sdev)
 	return open_devip;
 }
 
-static int scsi_debug_slave_alloc(struct scsi_device *sdp)
+static int scsi_debug_sdev_init(struct scsi_device *sdp)
 {
 	if (sdebug_verbose)
-		pr_info("slave_alloc <%u %u %u %llu>\n",
+		pr_info("sdev_init <%u %u %u %llu>\n",
 		       sdp->host->host_no, sdp->channel, sdp->id, sdp->lun);
 
 	return 0;
 }
 
-static int scsi_debug_slave_configure(struct scsi_device *sdp)
+static int scsi_debug_sdev_configure(struct scsi_device *sdp,
+				     struct queue_limits *lim)
 {
 	struct sdebug_dev_info *devip =
 			(struct sdebug_dev_info *)sdp->hostdata;
 	struct dentry *dentry;
 
 	if (sdebug_verbose)
-		pr_info("slave_configure <%u %u %u %llu>\n",
+		pr_info("sdev_configure <%u %u %u %llu>\n",
 		       sdp->host->host_no, sdp->channel, sdp->id, sdp->lun);
 	if (sdp->host->max_cmd_len != SDEBUG_MAX_CMD_LEN)
 		sdp->host->max_cmd_len = SDEBUG_MAX_CMD_LEN;
@@ -5927,14 +5928,14 @@ static int scsi_debug_slave_configure(struct scsi_device *sdp)
 	return 0;
 }
 
-static void scsi_debug_slave_destroy(struct scsi_device *sdp)
+static void scsi_debug_sdev_destroy(struct scsi_device *sdp)
 {
 	struct sdebug_dev_info *devip =
 		(struct sdebug_dev_info *)sdp->hostdata;
 	struct sdebug_err_inject *err;
 
 	if (sdebug_verbose)
-		pr_info("slave_destroy <%u %u %u %llu>\n",
+		pr_info("sdev_destroy <%u %u %u %llu>\n",
 		       sdp->host->host_no, sdp->channel, sdp->id, sdp->lun);
 
 	if (!devip)
@@ -8706,15 +8707,15 @@ static int sdebug_init_cmd_priv(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
 	return 0;
 }
 
-static struct scsi_host_template sdebug_driver_template = {
+static const struct scsi_host_template sdebug_driver_template = {
 	.show_info =		scsi_debug_show_info,
 	.write_info =		scsi_debug_write_info,
 	.proc_name =		sdebug_proc_name,
 	.name =			"SCSI DEBUG",
 	.info =			scsi_debug_info,
-	.slave_alloc =		scsi_debug_slave_alloc,
-	.slave_configure =	scsi_debug_slave_configure,
-	.slave_destroy =	scsi_debug_slave_destroy,
+	.sdev_init =		scsi_debug_sdev_init,
+	.sdev_configure =	scsi_debug_sdev_configure,
+	.sdev_destroy =		scsi_debug_sdev_destroy,
 	.ioctl =		scsi_debug_ioctl,
 	.queuecommand =		scsi_debug_queuecommand,
 	.change_queue_depth =	sdebug_change_qdepth,
@@ -8732,6 +8733,7 @@ static struct scsi_host_template sdebug_driver_template = {
 	.max_sectors =		-1U,
 	.max_segment_size =	-1U,
 	.module =		THIS_MODULE,
+	.skip_settle_delay =	1,
 	.track_queue_depth =	1,
 	.cmd_size = sizeof(struct sdebug_scsi_cmd),
 	.init_cmd_priv = sdebug_init_cmd_priv,
@@ -8748,17 +8750,17 @@ static int sdebug_driver_probe(struct device *dev)
 
 	sdbg_host = dev_to_sdebug_host(dev);
 
-	sdebug_driver_template.can_queue = sdebug_max_queue;
-	sdebug_driver_template.cmd_per_lun = sdebug_max_queue;
-	if (!sdebug_clustering)
-		sdebug_driver_template.dma_boundary = PAGE_SIZE - 1;
-
 	hpnt = scsi_host_alloc(&sdebug_driver_template, 0);
 	if (NULL == hpnt) {
 		pr_err("scsi_host_alloc failed\n");
 		error = -ENODEV;
 		return error;
 	}
+	hpnt->can_queue = sdebug_max_queue;
+	hpnt->cmd_per_lun = sdebug_max_queue;
+	if (!sdebug_clustering)
+		hpnt->dma_boundary = PAGE_SIZE - 1;
+
 	if (submit_queues > nr_cpu_ids) {
 		pr_warn("%s: trim submit_queues (was %d) to nr_cpu_ids=%u\n",
 			my_name, submit_queues, nr_cpu_ids);
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 10154d78e336..815e7d63f3e2 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2363,14 +2363,14 @@ int scsi_error_handler(void *data)
 	return 0;
 }
 
-/*
- * Function:    scsi_report_bus_reset()
+/**
+ * scsi_report_bus_reset() - report bus reset observed
  *
- * Purpose:     Utility function used by low-level drivers to report that
- *		they have observed a bus reset on the bus being handled.
+ * Utility function used by low-level drivers to report that
+ * they have observed a bus reset on the bus being handled.
  *
- * Arguments:   shost       - Host in question
- *		channel     - channel on which reset was observed.
+ * @shost:      Host in question
+ * @channel:    channel on which reset was observed.
  *
  * Returns:     Nothing
  *
@@ -2395,15 +2395,15 @@ void scsi_report_bus_reset(struct Scsi_Host *shost, int channel)
 }
 EXPORT_SYMBOL(scsi_report_bus_reset);
 
-/*
- * Function:    scsi_report_device_reset()
+/**
+ * scsi_report_device_reset() - report device reset observed
  *
- * Purpose:     Utility function used by low-level drivers to report that
- *		they have observed a device reset on the device being handled.
+ * Utility function used by low-level drivers to report that
+ * they have observed a device reset on the device being handled.
  *
- * Arguments:   shost       - Host in question
- *		channel     - channel on which reset was observed
- *		target	    - target on which reset was observed
+ * @shost:      Host in question
+ * @channel:    channel on which reset was observed
+ * @target:     target on which reset was observed
  *
  * Returns:     Nothing
  *
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 6f6c5973c3ea..2fa45556e1ea 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -37,8 +37,10 @@
  * @host:	host to identify
  * @buffer:	userspace buffer for identification
  *
- * Return an identifying string at @buffer, if @buffer is non-NULL, filling
- * to the length stored at * (int *) @buffer.
+ * Return:
+ * * if successful, %1 and an identifying string at @buffer, if @buffer
+ * is non-NULL, filling to the length stored at * (int *) @buffer.
+ * * <0 error code on failure.
  */
 static int ioctl_probe(struct Scsi_Host *host, void __user *buffer)
 {
@@ -121,6 +123,16 @@ out:
 	return result;
 }
 
+/**
+ * scsi_set_medium_removal() - send command to allow or prevent medium removal
+ * @sdev: target scsi device
+ * @state: removal state to set (prevent or allow)
+ *
+ * Returns:
+ * * %0 if @sdev is not removable or not lockable or successful.
+ * * non-%0 is a SCSI result code if > 0 or kernel error code if < 0.
+ * * Sets @sdev->locked to the new state on success.
+ */
 int scsi_set_medium_removal(struct scsi_device *sdev, char state)
 {
 	char scsi_cmd[MAX_COMMAND_SIZE];
@@ -242,11 +254,15 @@ static int scsi_send_start_stop(struct scsi_device *sdev, int data)
 				      NORMAL_RETRIES);
 }
 
-/*
- * Check if the given command is allowed.
+/**
+ * scsi_cmd_allowed() - Check if the given command is allowed.
+ * @cmd:            SCSI command to check
+ * @open_for_write: is the file / block device opened for writing?
  *
  * Only a subset of commands are allowed for unprivileged users. Commands used
  * to format the media, update the firmware, etc. are not permitted.
+ *
+ * Return: %true if the cmd is allowed, otherwise @false.
  */
 bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write)
 {
@@ -859,6 +875,8 @@ static int scsi_ioctl_sg_io(struct scsi_device *sdev, bool open_for_write,
  * Description: The scsi_ioctl() function differs from most ioctls in that it
  * does not take a major/minor number as the dev field.  Rather, it takes
  * a pointer to a &struct scsi_device.
+ *
+ * Return: varies depending on the @cmd
  */
 int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd,
 		void __user *arg)
@@ -941,8 +959,15 @@ int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd,
 }
 EXPORT_SYMBOL(scsi_ioctl);
 
-/*
+/**
+ * scsi_ioctl_block_when_processing_errors - prevent commands from being queued
+ * @sdev: target scsi device
+ * @cmd: which ioctl is it
+ * @ndelay: no delay (non-blocking)
+ *
  * We can process a reset even when a device isn't fully operable.
+ *
+ * Return: %0 on success, <0 error code.
  */
 int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd,
 		bool ndelay)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 4411426a7894..be0890e4e706 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -184,6 +184,10 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 	__scsi_queue_insert(cmd, reason, true);
 }
 
+/**
+ * scsi_failures_reset_retries - reset all failures to zero
+ * @failures: &struct scsi_failures with specific failure modes set
+ */
 void scsi_failures_reset_retries(struct scsi_failures *failures)
 {
 	struct scsi_failure *failure;
@@ -868,13 +872,18 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 				case 0x1a: /* start stop unit in progress */
 				case 0x1b: /* sanitize in progress */
 				case 0x1d: /* configuration in progress */
-				case 0x24: /* depopulation in progress */
-				case 0x25: /* depopulation restore in progress */
 					action = ACTION_DELAYED_RETRY;
 					break;
 				case 0x0a: /* ALUA state transition */
 					action = ACTION_DELAYED_REPREP;
 					break;
+				/*
+				 * Depopulation might take many hours,
+				 * thus it is not worthwhile to retry.
+				 */
+				case 0x24: /* depopulation in progress */
+				case 0x25: /* depopulation restore in progress */
+					fallthrough;
 				default:
 					action = ACTION_FAIL;
 					break;
@@ -1217,6 +1226,15 @@ static void scsi_initialize_rq(struct request *rq)
 	cmd->retries = 0;
 }
 
+/**
+ * scsi_alloc_request - allocate a block request and partially
+ *                      initialize its &scsi_cmnd
+ * @q: the device's request queue
+ * @opf: the request operation code
+ * @flags: block layer allocation flags
+ *
+ * Return: &struct request pointer on success or %NULL on failure
+ */
 struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf,
 				   blk_mq_req_flags_t flags)
 {
@@ -2723,6 +2741,7 @@ int
 scsi_device_quiesce(struct scsi_device *sdev)
 {
 	struct request_queue *q = sdev->request_queue;
+	unsigned int memflags;
 	int err;
 
 	/*
@@ -2737,7 +2756,7 @@ scsi_device_quiesce(struct scsi_device *sdev)
 
 	blk_set_pm_only(q);
 
-	blk_mq_freeze_queue(q);
+	memflags = blk_mq_freeze_queue(q);
 	/*
 	 * Ensure that the effect of blk_set_pm_only() will be visible
 	 * for percpu_ref_tryget() callers that occur after the queue
@@ -2745,7 +2764,7 @@ scsi_device_quiesce(struct scsi_device *sdev)
 	 * was called. See also https://lwn.net/Articles/573497/.
 	 */
 	synchronize_rcu();
-	blk_mq_unfreeze_queue(q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	mutex_lock(&sdev->state_mutex);
 	err = scsi_device_set_state(sdev, SDEV_QUIESCE);
@@ -3367,14 +3386,16 @@ int scsi_vpd_lun_id(struct scsi_device *sdev, char *id, size_t id_len)
 }
 EXPORT_SYMBOL(scsi_vpd_lun_id);
 
-/*
+/**
  * scsi_vpd_tpg_id - return a target port group identifier
  * @sdev: SCSI device
+ * @rel_id: pointer to return relative target port in if not %NULL
  *
  * Returns the Target Port Group identifier from the information
- * froom VPD page 0x83 of the device.
+ * from VPD page 0x83 of the device.
+ * Optionally sets @rel_id to the relative target port on success.
  *
- * Returns the identifier or error on failure.
+ * Return: the identifier or error on failure.
  */
 int scsi_vpd_tpg_id(struct scsi_device *sdev, int *rel_id)
 {
diff --git a/drivers/scsi/scsi_lib_test.c b/drivers/scsi/scsi_lib_test.c
index 99834426a100..ae8af0e0047a 100644
--- a/drivers/scsi/scsi_lib_test.c
+++ b/drivers/scsi/scsi_lib_test.c
@@ -67,6 +67,13 @@ static void scsi_lib_test_multiple_sense(struct kunit *test)
 	};
 	int i;
 
+	/* Success */
+	sc.result = 0;
+	KUNIT_EXPECT_EQ(test, 0, scsi_check_passthrough(&sc, &failures));
+	KUNIT_EXPECT_EQ(test, 0, scsi_check_passthrough(&sc, NULL));
+	/* Command failed but caller did not pass in a failures array */
+	scsi_build_sense(&sc, 0, ILLEGAL_REQUEST, 0x91, 0x36);
+	KUNIT_EXPECT_EQ(test, 0, scsi_check_passthrough(&sc, NULL));
 	/* Match end of array */
 	scsi_build_sense(&sc, 0, ILLEGAL_REQUEST, 0x91, 0x36);
 	KUNIT_EXPECT_EQ(test, -EAGAIN, scsi_check_passthrough(&sc, &failures));
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 042329b74c6e..96d7e1a9a7c7 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -220,6 +220,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 	int new_shift = sbitmap_calculate_shift(depth);
 	bool need_alloc = !sdev->budget_map.map;
 	bool need_free = false;
+	unsigned int memflags;
 	int ret;
 	struct sbitmap sb_backup;
 
@@ -227,7 +228,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 
 	/*
 	 * realloc if new shift is calculated, which is caused by setting
-	 * up one new default queue depth after calling ->device_configure
+	 * up one new default queue depth after calling ->sdev_configure
 	 */
 	if (!need_alloc && new_shift != sdev->budget_map.shift)
 		need_alloc = need_free = true;
@@ -240,12 +241,12 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 	 * and here disk isn't added yet, so freezing is pretty fast
 	 */
 	if (need_free) {
-		blk_mq_freeze_queue(sdev->request_queue);
+		memflags = blk_mq_freeze_queue(sdev->request_queue);
 		sb_backup = sdev->budget_map;
 	}
 	ret = sbitmap_init_node(&sdev->budget_map,
 				scsi_device_max_queue_depth(sdev),
-				new_shift, GFP_KERNEL,
+				new_shift, GFP_NOIO,
 				sdev->request_queue->node, false, true);
 	if (!ret)
 		sbitmap_resize(&sdev->budget_map, depth);
@@ -256,7 +257,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
 		else
 			sbitmap_free(&sb_backup);
 		ret = 0;
-		blk_mq_unfreeze_queue(sdev->request_queue);
+		blk_mq_unfreeze_queue(sdev->request_queue, memflags);
 	}
 	return ret;
 }
@@ -265,7 +266,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev,
  * scsi_alloc_sdev - allocate and setup a scsi_Device
  * @starget: which target to allocate a &scsi_device for
  * @lun: which lun
- * @hostdata: usually NULL and set by ->slave_alloc instead
+ * @hostdata: usually NULL and set by ->sdev_init instead
  *
  * Description:
  *     Allocate, initialize for io, and return a pointer to a scsi_Device.
@@ -312,11 +313,11 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	sdev->sdev_gendev.parent = get_device(&starget->dev);
 	sdev->sdev_target = starget;
 
-	/* usually NULL and set by ->slave_alloc instead */
+	/* usually NULL and set by ->sdev_init instead */
 	sdev->hostdata = hostdata;
 
 	/* if the device needs this changing, it may do so in the
-	 * slave_configure function */
+	 * sdev_configure function */
 	sdev->max_device_blocked = SCSI_DEFAULT_DEVICE_BLOCKED;
 
 	/*
@@ -363,8 +364,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 
 	scsi_sysfs_device_initialize(sdev);
 
-	if (shost->hostt->slave_alloc) {
-		ret = shost->hostt->slave_alloc(sdev);
+	if (shost->hostt->sdev_init) {
+		ret = shost->hostt->sdev_init(sdev);
 		if (ret) {
 			/*
 			 * if LLDD reports slave not present, don't clutter
@@ -1074,10 +1075,8 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	else if (*bflags & BLIST_MAX_1024)
 		lim.max_hw_sectors = 1024;
 
-	if (hostt->device_configure)
-		ret = hostt->device_configure(sdev, &lim);
-	else if (hostt->slave_configure)
-		ret = hostt->slave_configure(sdev);
+	if (hostt->sdev_configure)
+		ret = hostt->sdev_configure(sdev, &lim);
 	if (ret) {
 		queue_limits_cancel_update(sdev->request_queue);
 		/*
@@ -1097,12 +1096,12 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	}
 
 	/*
-	 * The queue_depth is often changed in ->device_configure.
+	 * The queue_depth is often changed in ->sdev_configure.
 	 *
 	 * Set up budget map again since memory consumption of the map depends
 	 * on actual queue depth.
 	 */
-	if (hostt->device_configure || hostt->slave_configure)
+	if (hostt->sdev_configure)
 		scsi_realloc_sdev_budget_map(sdev, sdev->queue_depth);
 
 	if (sdev->scsi_level >= SCSI_3)
@@ -1636,6 +1635,24 @@ struct scsi_device *__scsi_add_device(struct Scsi_Host *shost, uint channel,
 }
 EXPORT_SYMBOL(__scsi_add_device);
 
+/**
+ * scsi_add_device - creates a new SCSI (LU) instance
+ * @host: the &Scsi_Host instance where the device is located
+ * @channel: target channel number (rarely other than %0)
+ * @target: target id number
+ * @lun: LUN of target device
+ *
+ * Probe for a specific LUN and add it if found.
+ *
+ * Notes: This call is usually performed internally during a SCSI
+ * bus scan when an HBA is added (i.e. scsi_scan_host()). So it
+ * should only be called if the HBA becomes aware of a new SCSI
+ * device (LU) after scsi_scan_host() has completed. If successful
+ * this call can lead to sdev_init() and sdev_configure() callbacks
+ * into the LLD.
+ *
+ * Return: %0 on success or negative error code on failure
+ */
 int scsi_add_device(struct Scsi_Host *host, uint channel,
 		    uint target, u64 lun)
 {
@@ -2027,6 +2044,8 @@ static void do_scan_async(void *_data, async_cookie_t c)
 /**
  * scsi_scan_host - scan the given adapter
  * @shost:	adapter to scan
+ *
+ * Notes: Should be called after scsi_add_host()
  **/
 void scsi_scan_host(struct Scsi_Host *shost)
 {
diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c
index 093774d77534..be4aef0f4f99 100644
--- a/drivers/scsi/scsi_sysctl.c
+++ b/drivers/scsi/scsi_sysctl.c
@@ -12,7 +12,7 @@
 #include "scsi_priv.h"
 
 
-static struct ctl_table scsi_table[] = {
+static const struct ctl_table scsi_table[] = {
 	{ .procname	= "logging_level",
 	  .data		= &scsi_logging_level,
 	  .maxlen	= sizeof(scsi_logging_level),
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index f3a1ecb42128..d772258e29ad 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -898,7 +898,7 @@ static DEVICE_ATTR(queue_type, S_IRUGO | S_IWUSR, show_queue_type_field,
 #define sdev_vpd_pg_attr(_page)						\
 static ssize_t							\
 show_vpd_##_page(struct file *filp, struct kobject *kobj,	\
-		 struct bin_attribute *bin_attr,			\
+		 const struct bin_attribute *bin_attr,			\
 		 char *buf, loff_t off, size_t count)			\
 {									\
 	struct device *dev = kobj_to_dev(kobj);				\
@@ -914,10 +914,10 @@ show_vpd_##_page(struct file *filp, struct kobject *kobj,	\
 	rcu_read_unlock();						\
 	return ret;							\
 }									\
-static struct bin_attribute dev_attr_vpd_##_page = {		\
+static const struct bin_attribute dev_attr_vpd_##_page = {		\
 	.attr =	{.name = __stringify(vpd_##_page), .mode = S_IRUGO },	\
 	.size = 0,							\
-	.read = show_vpd_##_page,					\
+	.read_new = show_vpd_##_page,					\
 };
 
 sdev_vpd_pg_attr(pg83);
@@ -930,7 +930,7 @@ sdev_vpd_pg_attr(pgb7);
 sdev_vpd_pg_attr(pg0);
 
 static ssize_t show_inquiry(struct file *filep, struct kobject *kobj,
-			    struct bin_attribute *bin_attr,
+			    const struct bin_attribute *bin_attr,
 			    char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -943,13 +943,13 @@ static ssize_t show_inquiry(struct file *filep, struct kobject *kobj,
 				       sdev->inquiry_len);
 }
 
-static struct bin_attribute dev_attr_inquiry = {
+static const struct bin_attribute dev_attr_inquiry = {
 	.attr = {
 		.name = "inquiry",
 		.mode = S_IRUGO,
 	},
 	.size = 0,
-	.read = show_inquiry,
+	.read_new = show_inquiry,
 };
 
 static ssize_t
@@ -1348,7 +1348,7 @@ static struct attribute *scsi_sdev_attrs[] = {
 	NULL
 };
 
-static struct bin_attribute *scsi_sdev_bin_attrs[] = {
+static const struct bin_attribute *const scsi_sdev_bin_attrs[] = {
 	&dev_attr_vpd_pg0,
 	&dev_attr_vpd_pg83,
 	&dev_attr_vpd_pg80,
@@ -1362,7 +1362,7 @@ static struct bin_attribute *scsi_sdev_bin_attrs[] = {
 };
 static struct attribute_group scsi_sdev_attr_group = {
 	.attrs =	scsi_sdev_attrs,
-	.bin_attrs =	scsi_sdev_bin_attrs,
+	.bin_attrs_new = scsi_sdev_bin_attrs,
 	.is_visible =	scsi_sdev_attr_is_visible,
 	.is_bin_visible = scsi_sdev_bin_attr_is_visible,
 };
@@ -1513,8 +1513,8 @@ void __scsi_remove_device(struct scsi_device *sdev)
 	kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
 	cancel_work_sync(&sdev->requeue_work);
 
-	if (sdev->host->hostt->slave_destroy)
-		sdev->host->hostt->slave_destroy(sdev);
+	if (sdev->host->hostt->sdev_destroy)
+		sdev->host->hostt->sdev_destroy(sdev);
 	transport_destroy_device(dev);
 
 	/*
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 9b47f91c5b97..9c347c64c315 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1324,7 +1324,7 @@ EXPORT_SYMBOL_GPL(iscsi_create_flashnode_conn);
  *  1 on success
  *  0 on failure
  */
-static int iscsi_is_flashnode_conn_dev(struct device *dev, void *data)
+static int iscsi_is_flashnode_conn_dev(struct device *dev, const void *data)
 {
 	return dev->bus == &iscsi_flashnode_bus;
 }
@@ -1335,7 +1335,7 @@ static int iscsi_destroy_flashnode_conn(struct iscsi_bus_flash_conn *fnode_conn)
 	return 0;
 }
 
-static int flashnode_match_index(struct device *dev, void *data)
+static int flashnode_match_index(struct device *dev, const void *data)
 {
 	struct iscsi_bus_flash_session *fnode_sess = NULL;
 	int ret = 0;
@@ -1344,7 +1344,7 @@ static int flashnode_match_index(struct device *dev, void *data)
 		goto exit_match_index;
 
 	fnode_sess = iscsi_dev_to_flash_session(dev);
-	ret = (fnode_sess->target_id == *((int *)data)) ? 1 : 0;
+	ret = (fnode_sess->target_id == *((const int *)data)) ? 1 : 0;
 
 exit_match_index:
 	return ret;
@@ -1389,8 +1389,8 @@ iscsi_get_flashnode_by_index(struct Scsi_Host *shost, uint32_t idx)
  *  %NULL on failure
  */
 struct device *
-iscsi_find_flashnode_sess(struct Scsi_Host *shost, void *data,
-			  int (*fn)(struct device *dev, void *data))
+iscsi_find_flashnode_sess(struct Scsi_Host *shost, const void *data,
+			  device_match_t fn)
 {
 	return device_find_child(&shost->shost_gendev, data, fn);
 }
@@ -2122,33 +2122,6 @@ destroy_wq:
 }
 EXPORT_SYMBOL_GPL(iscsi_add_session);
 
-/**
- * iscsi_create_session - create iscsi class session
- * @shost: scsi host
- * @transport: iscsi transport
- * @dd_size: private driver data size
- * @target_id: which target
- *
- * This can be called from a LLD or iscsi_transport.
- */
-struct iscsi_cls_session *
-iscsi_create_session(struct Scsi_Host *shost, struct iscsi_transport *transport,
-		     int dd_size, unsigned int target_id)
-{
-	struct iscsi_cls_session *session;
-
-	session = iscsi_alloc_session(shost, transport, dd_size);
-	if (!session)
-		return NULL;
-
-	if (iscsi_add_session(session, target_id)) {
-		iscsi_free_session(session);
-		return NULL;
-	}
-	return session;
-}
-EXPORT_SYMBOL_GPL(iscsi_create_session);
-
 static void iscsi_conn_release(struct device *dev)
 {
 	struct iscsi_cls_conn *conn = iscsi_dev_to_conn(dev);
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 4e33f1661e4c..351b028ef893 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -888,7 +888,8 @@ static void sas_port_delete_link(struct sas_port *port,
 	sysfs_remove_link(&phy->dev.kobj, "port");
 }
 
-/** sas_port_alloc - allocate and initialize a SAS port structure
+/**
+ * sas_port_alloc - allocate and initialize a SAS port structure
  *
  * @parent:	parent device
  * @port_id:	port number
@@ -897,7 +898,7 @@ static void sas_port_delete_link(struct sas_port *port,
  * below the device specified by @parent which must be either a Scsi_Host
  * or a sas_expander_device.
  *
- * Returns %NULL on error
+ * Returns: %NULL on error
  */
 struct sas_port *sas_port_alloc(struct device *parent, int port_id)
 {
@@ -932,7 +933,8 @@ struct sas_port *sas_port_alloc(struct device *parent, int port_id)
 }
 EXPORT_SYMBOL(sas_port_alloc);
 
-/** sas_port_alloc_num - allocate and initialize a SAS port structure
+/**
+ * sas_port_alloc_num - allocate and initialize a SAS port structure
  *
  * @parent:	parent device
  *
@@ -942,7 +944,7 @@ EXPORT_SYMBOL(sas_port_alloc);
  * the device tree below the device specified by @parent which must be
  * either a Scsi_Host or a sas_expander_device.
  *
- * Returns %NULL on error
+ * Returns: %NULL on error
  */
 struct sas_port *sas_port_alloc_num(struct device *parent)
 {
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index 64852e6df3e3..fe47850a8258 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -985,7 +985,8 @@ spi_dv_device_internal(struct scsi_device *sdev, u8 *buffer)
 }
 
 
-/**	spi_dv_device - Do Domain Validation on the device
+/**
+ *	spi_dv_device - Do Domain Validation on the device
  *	@sdev:		scsi device to validate
  *
  *	Performs the domain validation on the given device in the
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 94127868bedf..effb7e768165 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1639,7 +1639,7 @@ MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))");
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 
-static struct ctl_table sg_sysctls[] = {
+static const struct ctl_table sg_sysctls[] = {
 	{
 		.procname	= "sg-big-buff",
 		.data		= &sg_big_buff,
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 04fb24d77e9b..0da7be40c925 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -6489,7 +6489,7 @@ out:
 	return SUCCESS;
 }
 
-static int pqi_slave_alloc(struct scsi_device *sdev)
+static int pqi_sdev_init(struct scsi_device *sdev)
 {
 	struct pqi_scsi_dev *device;
 	unsigned long flags;
@@ -6557,7 +6557,8 @@ static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device)
 	return device->devtype == TYPE_TAPE || device->devtype == TYPE_MEDIUM_CHANGER;
 }
 
-static int pqi_slave_configure(struct scsi_device *sdev)
+static int pqi_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	int rc = 0;
 	struct pqi_scsi_dev *device;
@@ -6573,7 +6574,7 @@ static int pqi_slave_configure(struct scsi_device *sdev)
 	return rc;
 }
 
-static void pqi_slave_destroy(struct scsi_device *sdev)
+static void pqi_sdev_destroy(struct scsi_device *sdev)
 {
 	struct pqi_ctrl_info *ctrl_info;
 	struct pqi_scsi_dev *device;
@@ -7548,9 +7549,9 @@ static const struct scsi_host_template pqi_driver_template = {
 	.eh_device_reset_handler = pqi_eh_device_reset_handler,
 	.eh_abort_handler = pqi_eh_abort_handler,
 	.ioctl = pqi_ioctl,
-	.slave_alloc = pqi_slave_alloc,
-	.slave_configure = pqi_slave_configure,
-	.slave_destroy = pqi_slave_destroy,
+	.sdev_init = pqi_sdev_init,
+	.sdev_configure = pqi_sdev_configure,
+	.sdev_destroy = pqi_sdev_destroy,
 	.map_queues = pqi_map_queues,
 	.sdev_groups = pqi_sdev_groups,
 	.shost_groups = pqi_shost_groups,
diff --git a/drivers/scsi/snic/snic_main.c b/drivers/scsi/snic/snic_main.c
index 9be3f0193145..1c24517e4e65 100644
--- a/drivers/scsi/snic/snic_main.c
+++ b/drivers/scsi/snic/snic_main.c
@@ -21,7 +21,7 @@
 #define PCI_DEVICE_ID_CISCO_SNIC	0x0046
 
 /* Supported devices by snic module */
-static struct pci_device_id snic_id_table[] = {
+static const struct pci_device_id snic_id_table[] = {
 	{PCI_DEVICE(0x1137, PCI_DEVICE_ID_CISCO_SNIC) },
 	{ 0, }	/* end of table */
 };
@@ -42,11 +42,11 @@ module_param(snic_max_qdepth, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(snic_max_qdepth, "Queue depth to report for each LUN");
 
 /*
- * snic_slave_alloc : callback function to SCSI Mid Layer, called on
+ * snic_sdev_init : callback function to SCSI Mid Layer, called on
  * scsi device initialization.
  */
 static int
-snic_slave_alloc(struct scsi_device *sdev)
+snic_sdev_init(struct scsi_device *sdev)
 {
 	struct snic_tgt *tgt = starget_to_tgt(scsi_target(sdev));
 
@@ -57,11 +57,11 @@ snic_slave_alloc(struct scsi_device *sdev)
 }
 
 /*
- * snic_slave_configure : callback function to SCSI Mid Layer, called on
+ * snic_sdev_configure : callback function to SCSI Mid Layer, called on
  * scsi device initialization.
  */
 static int
-snic_slave_configure(struct scsi_device *sdev)
+snic_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct snic *snic = shost_priv(sdev->host);
 	u32 qdepth = 0, max_ios = 0;
@@ -107,8 +107,8 @@ static const struct scsi_host_template snic_host_template = {
 	.eh_abort_handler = snic_abort_cmd,
 	.eh_device_reset_handler = snic_device_reset,
 	.eh_host_reset_handler = snic_host_reset,
-	.slave_alloc = snic_slave_alloc,
-	.slave_configure = snic_slave_configure,
+	.sdev_init = snic_sdev_init,
+	.sdev_configure = snic_sdev_configure,
 	.change_queue_depth = snic_change_queue_depth,
 	.this_id = -1,
 	.cmd_per_lun = SNIC_DFLT_QUEUE_DEPTH,
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e8ef27d7ef61..ebbd50ec0cda 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -1030,6 +1030,11 @@ static int test_ready(struct scsi_tape *STp, int do_wait)
 			retval = new_session ? CHKRES_NEW_SESSION : CHKRES_READY;
 		break;
 	}
+	if (STp->first_tur) {
+		/* Don't set pos_unknown right after device recognition */
+		STp->pos_unknown = 0;
+		STp->first_tur = 0;
+	}
 
 	if (SRpnt != NULL)
 		st_release_request(SRpnt);
@@ -4328,6 +4333,7 @@ static int st_probe(struct device *dev)
 	blk_queue_rq_timeout(tpnt->device->request_queue, ST_TIMEOUT);
 	tpnt->long_timeout = ST_LONG_TIMEOUT;
 	tpnt->try_dio = try_direct_io;
+	tpnt->first_tur = 1;
 
 	for (i = 0; i < ST_NBR_MODES; i++) {
 		STm = &(tpnt->modes[i]);
diff --git a/drivers/scsi/st.h b/drivers/scsi/st.h
index 7a68eaba7e81..1aaaf5369a40 100644
--- a/drivers/scsi/st.h
+++ b/drivers/scsi/st.h
@@ -170,6 +170,7 @@ struct scsi_tape {
 	unsigned char rew_at_close;  /* rewind necessary at close */
 	unsigned char inited;
 	unsigned char cleaning_req;  /* cleaning requested? */
+	unsigned char first_tur;     /* first TEST UNIT READY */
 	int block_size;
 	int min_block;
 	int max_block;
diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c
index 0e81125df8c7..63ed7f9aaa93 100644
--- a/drivers/scsi/stex.c
+++ b/drivers/scsi/stex.c
@@ -584,7 +584,7 @@ static void return_abnormal_state(struct st_hba *hba, int status)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 static int
-stex_slave_config(struct scsi_device *sdev)
+stex_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	sdev->use_10_for_rw = 1;
 	sdev->use_10_for_ms = 1;
@@ -1481,14 +1481,14 @@ static const struct scsi_host_template driver_template = {
 	.proc_name			= DRV_NAME,
 	.bios_param			= stex_biosparam,
 	.queuecommand			= stex_queuecommand,
-	.slave_configure		= stex_slave_config,
+	.sdev_configure			= stex_sdev_configure,
 	.eh_abort_handler		= stex_abort,
 	.eh_host_reset_handler		= stex_reset,
 	.this_id			= -1,
 	.dma_boundary			= PAGE_SIZE - 1,
 };
 
-static struct pci_device_id stex_pci_tbl[] = {
+static const struct pci_device_id stex_pci_tbl[] = {
 	/* st_shasta */
 	{ 0x105a, 0x8350, PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		st_shasta }, /* SuperTrak EX8350/8300/16350/16300 */
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index d0b55c1fa908..a8614e54544e 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -171,6 +171,12 @@ do {								\
 		dev_warn(&(dev)->device, fmt, ##__VA_ARGS__);	\
 } while (0)
 
+#define storvsc_log_ratelimited(dev, level, fmt, ...)				\
+do {										\
+	if (do_logging(level))							\
+		dev_warn_ratelimited(&(dev)->device, fmt, ##__VA_ARGS__);	\
+} while (0)
+
 struct vmscsi_request {
 	u16 length;
 	u8 srb_status;
@@ -917,14 +923,13 @@ static int storvsc_channel_init(struct hv_device *device, bool is_fc)
 
 	/*
 	 * Allocate state to manage the sub-channels.
-	 * We allocate an array based on the numbers of possible CPUs
-	 * (Hyper-V does not support cpu online/offline).
-	 * This Array will be sparseley populated with unique
-	 * channels - primary + sub-channels.
-	 * We will however populate all the slots to evenly distribute
-	 * the load.
+	 * We allocate an array based on the number of CPU ids. This array
+	 * is initially sparsely populated for the CPUs assigned to channels:
+	 * primary + sub-channels. As I/Os are initiated by different CPUs,
+	 * the slots for all online CPUs are populated to evenly distribute
+	 * the load across all channels.
 	 */
-	stor_device->stor_chns = kcalloc(num_possible_cpus(), sizeof(void *),
+	stor_device->stor_chns = kcalloc(nr_cpu_ids, sizeof(void *),
 					 GFP_KERNEL);
 	if (stor_device->stor_chns == NULL)
 		return -ENOMEM;
@@ -1177,7 +1182,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device,
 		int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ?
 			STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR;
 
-		storvsc_log(device, loglevel,
+		storvsc_log_ratelimited(device, loglevel,
 			"tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n",
 			scsi_cmd_to_rq(request->cmd)->tag,
 			stor_pkt->vm_srb.cdb[0],
@@ -1579,7 +1584,8 @@ static int storvsc_device_alloc(struct scsi_device *sdevice)
 	return 0;
 }
 
-static int storvsc_device_configure(struct scsi_device *sdevice)
+static int storvsc_sdev_configure(struct scsi_device *sdevice,
+				  struct queue_limits *lim)
 {
 	blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ));
 
@@ -1794,6 +1800,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 
 	length = scsi_bufflen(scmnd);
 	payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb;
+	payload->range.len = 0;
 	payload_sz = 0;
 
 	if (scsi_sg_count(scmnd)) {
@@ -1880,8 +1887,8 @@ static struct scsi_host_template scsi_driver = {
 	.eh_host_reset_handler =	storvsc_host_reset_handler,
 	.proc_name =		"storvsc_host",
 	.eh_timed_out =		storvsc_eh_timed_out,
-	.slave_alloc =		storvsc_device_alloc,
-	.slave_configure =	storvsc_device_configure,
+	.sdev_init =		storvsc_device_alloc,
+	.sdev_configure =	storvsc_sdev_configure,
 	.cmd_per_lun =		2048,
 	.this_id =		-1,
 	/* Ensure there are no gaps in presented sgls */
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index a2560cc807d3..212d89d0d23e 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -765,7 +765,7 @@ static void sym_tune_dev_queuing(struct sym_tcb *tp, int lun, u_short reqtags)
 	}
 }
 
-static int sym53c8xx_slave_alloc(struct scsi_device *sdev)
+static int sym53c8xx_sdev_init(struct scsi_device *sdev)
 {
 	struct sym_hcb *np = sym_get_hcb(sdev->host);
 	struct sym_tcb *tp = &np->target[sdev->id];
@@ -825,7 +825,8 @@ out:
 /*
  * Linux entry point for device queue sizing.
  */
-static int sym53c8xx_slave_configure(struct scsi_device *sdev)
+static int sym53c8xx_sdev_configure(struct scsi_device *sdev,
+				    struct queue_limits *lim)
 {
 	struct sym_hcb *np = sym_get_hcb(sdev->host);
 	struct sym_tcb *tp = &np->target[sdev->id];
@@ -861,14 +862,14 @@ static int sym53c8xx_slave_configure(struct scsi_device *sdev)
 	return 0;
 }
 
-static void sym53c8xx_slave_destroy(struct scsi_device *sdev)
+static void sym53c8xx_sdev_destroy(struct scsi_device *sdev)
 {
 	struct sym_hcb *np = sym_get_hcb(sdev->host);
 	struct sym_tcb *tp = &np->target[sdev->id];
 	struct sym_lcb *lp = sym_lp(tp, sdev->lun);
 	unsigned long flags;
 
-	/* if slave_alloc returned before allocating a sym_lcb, return */
+	/* if sdev_init returned before allocating a sym_lcb, return */
 	if (!lp)
 		return;
 
@@ -1684,9 +1685,9 @@ static const struct scsi_host_template sym2_template = {
 	.info			= sym53c8xx_info, 
 	.cmd_size		= sizeof(struct sym_ucmd),
 	.queuecommand		= sym53c8xx_queue_command,
-	.slave_alloc		= sym53c8xx_slave_alloc,
-	.slave_configure	= sym53c8xx_slave_configure,
-	.slave_destroy		= sym53c8xx_slave_destroy,
+	.sdev_init		= sym53c8xx_sdev_init,
+	.sdev_configure		= sym53c8xx_sdev_configure,
+	.sdev_destroy		= sym53c8xx_sdev_destroy,
 	.eh_abort_handler	= sym53c8xx_eh_abort_handler,
 	.eh_target_reset_handler = sym53c8xx_eh_target_reset_handler,
 	.eh_bus_reset_handler	= sym53c8xx_eh_bus_reset_handler,
@@ -2030,7 +2031,7 @@ static struct spi_function_template sym2_transport_functions = {
 	.get_signalling	= sym2_get_signalling,
 };
 
-static struct pci_device_id sym2_id_table[] = {
+static const struct pci_device_id sym2_id_table[] = {
 	{ PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_NCR_53C810,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0UL },
 	{ PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_NCR_53C820,
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 60be1a0c6183..21ce3e940192 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -800,7 +800,7 @@ static const struct scsi_host_template virtscsi_host_template = {
 	.eh_abort_handler = virtscsi_abort,
 	.eh_device_reset_handler = virtscsi_device_reset,
 	.eh_timed_out = virtscsi_eh_timed_out,
-	.slave_alloc = virtscsi_device_alloc,
+	.sdev_init = virtscsi_device_alloc,
 
 	.dma_boundary = UINT_MAX,
 	.map_queues = virtscsi_map_queues,
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index 9ec55ddc1204..924025305753 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -735,7 +735,8 @@ static int scsifront_dev_reset_handler(struct scsi_cmnd *sc)
 	return scsifront_action_handler(sc, VSCSIIF_ACT_SCSI_RESET);
 }
 
-static int scsifront_sdev_configure(struct scsi_device *sdev)
+static int scsifront_sdev_configure(struct scsi_device *sdev,
+				    struct queue_limits *lim)
 {
 	struct vscsifrnt_info *info = shost_priv(sdev->host);
 	int err;
@@ -776,8 +777,8 @@ static const struct scsi_host_template scsifront_sht = {
 	.queuecommand		= scsifront_queuecommand,
 	.eh_abort_handler	= scsifront_eh_abort_handler,
 	.eh_device_reset_handler = scsifront_dev_reset_handler,
-	.slave_configure	= scsifront_sdev_configure,
-	.slave_destroy		= scsifront_sdev_destroy,
+	.sdev_configure		= scsifront_sdev_configure,
+	.sdev_destroy		= scsifront_sdev_destroy,
 	.cmd_per_lun		= VSCSIIF_DEFAULT_CMD_PER_LUN,
 	.can_queue		= VSCSIIF_MAX_REQS,
 	.this_id		= -1,
@@ -1074,8 +1075,8 @@ static void scsifront_do_lun_hotplug(struct vscsifrnt_info *info, int op)
 			continue;
 
 		/*
-		 * Front device state path, used in slave_configure called
-		 * on successfull scsi_add_device, and in slave_destroy called
+		 * Front device state path, used in sdev_configure called
+		 * on successfull scsi_add_device, and in sdev_destroy called
 		 * on remove of a device.
 		 */
 		snprintf(info->dev_state_path, sizeof(info->dev_state_path),
diff --git a/drivers/slimbus/core.c b/drivers/slimbus/core.c
index 65e5515f7555..005fa2ef100f 100644
--- a/drivers/slimbus/core.c
+++ b/drivers/slimbus/core.c
@@ -328,7 +328,8 @@ void slim_report_absent(struct slim_device *sbdev)
 }
 EXPORT_SYMBOL_GPL(slim_report_absent);
 
-static bool slim_eaddr_equal(struct slim_eaddr *a, struct slim_eaddr *b)
+static bool slim_eaddr_equal(const struct slim_eaddr *a,
+			     const struct slim_eaddr *b)
 {
 	return (a->manf_id == b->manf_id &&
 		a->prod_code == b->prod_code &&
@@ -336,9 +337,9 @@ static bool slim_eaddr_equal(struct slim_eaddr *a, struct slim_eaddr *b)
 		a->instance == b->instance);
 }
 
-static int slim_match_dev(struct device *dev, void *data)
+static int slim_match_dev(struct device *dev, const void *data)
 {
-	struct slim_eaddr *e_addr = data;
+	const struct slim_eaddr *e_addr = data;
 	struct slim_device *sbdev = to_slim_device(dev);
 
 	return slim_eaddr_equal(&sbdev->e_addr, e_addr);
@@ -384,21 +385,13 @@ struct slim_device *slim_get_device(struct slim_controller *ctrl,
 }
 EXPORT_SYMBOL_GPL(slim_get_device);
 
-static int of_slim_match_dev(struct device *dev, void *data)
-{
-	struct device_node *np = data;
-	struct slim_device *sbdev = to_slim_device(dev);
-
-	return (sbdev->dev.of_node == np);
-}
-
 static struct slim_device *of_find_slim_device(struct slim_controller *ctrl,
 					       struct device_node *np)
 {
 	struct slim_device *sbdev;
 	struct device *dev;
 
-	dev = device_find_child(ctrl->dev, np, of_slim_match_dev);
+	dev = device_find_child(ctrl->dev, np, device_match_of_node);
 	if (dev) {
 		sbdev = to_slim_device(dev);
 		return sbdev;
diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c
index 242570a5e565..e7aa9bd4b44b 100644
--- a/drivers/slimbus/messaging.c
+++ b/drivers/slimbus/messaging.c
@@ -13,8 +13,8 @@
  *
  * @ctrl: Controller handle
  * @reply: Reply received from the device
- * @len: Length of the reply
  * @tid: Transaction ID received with which framework can associate reply.
+ * @len: Length of the reply
  *
  * Called by controller to inform framework about the response received.
  * This helps in making the API asynchronous, and controller-driver doesn't need
diff --git a/drivers/soc/qcom/smp2p.c b/drivers/soc/qcom/smp2p.c
index 4783ab1adb8d..a3e88ced328a 100644
--- a/drivers/soc/qcom/smp2p.c
+++ b/drivers/soc/qcom/smp2p.c
@@ -365,7 +365,7 @@ static void smp2p_irq_print_chip(struct irq_data *irqd, struct seq_file *p)
 {
 	struct smp2p_entry *entry = irq_data_get_irq_chip_data(irqd);
 
-	seq_printf(p, " %8s", dev_name(entry->smp2p->dev));
+	seq_printf(p, "%8s", dev_name(entry->smp2p->dev));
 }
 
 static struct irq_chip smp2p_irq_chip = {
diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 96a7f9709720..5a54b10daf77 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -384,7 +384,7 @@ static u32 amd_sdw_read_ping_status(struct sdw_bus *bus)
 	return slave_stat;
 }
 
-static int amd_sdw_compute_params(struct sdw_bus *bus)
+static int amd_sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream)
 {
 	struct sdw_transport_data t_data = {0};
 	struct sdw_master_runtime *m_rt;
@@ -410,7 +410,7 @@ static int amd_sdw_compute_params(struct sdw_bus *bus)
 			sdw_fill_xport_params(&p_rt->transport_params, p_rt->num,
 					      false, SDW_BLK_GRP_CNT_1, sample_int,
 					      port_bo, port_bo >> 8, hstart, hstop,
-					      SDW_BLK_PKG_PER_PORT, 0x0);
+					      SDW_BLK_PKG_PER_PORT, p_rt->lane);
 
 			sdw_fill_port_params(&p_rt->port_params,
 					     p_rt->num, bps,
@@ -1190,6 +1190,7 @@ static int __maybe_unused amd_resume_runtime(struct device *dev)
 	if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) {
 		return amd_sdw_clock_stop_exit(amd_manager);
 	} else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) {
+		writel(0x00, amd_manager->acp_mmio + ACP_SW_WAKE_EN(amd_manager->instance));
 		val = readl(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL);
 		if (val) {
 			val |= AMD_SDW_CLK_RESUME_REQ;
diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c
index d1dc62c34f1c..9b295fc9acd5 100644
--- a/drivers/soundwire/bus.c
+++ b/drivers/soundwire/bus.c
@@ -813,6 +813,16 @@ void sdw_extract_slave_id(struct sdw_bus *bus,
 }
 EXPORT_SYMBOL(sdw_extract_slave_id);
 
+bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave)
+{
+	/*
+	 * Dynamic scaling is a defined by SDCA. However, some devices expose the class ID but
+	 * can't support dynamic scaling. We might need a quirk to handle such devices.
+	 */
+	return slave->id.class_id;
+}
+EXPORT_SYMBOL(is_clock_scaling_supported_by_slave);
+
 static int sdw_program_device_num(struct sdw_bus *bus, bool *programmed)
 {
 	u8 buf[SDW_NUM_DEV_ID_REGISTERS] = {0};
@@ -1276,23 +1286,12 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave,
 	return ret;
 }
 
-static int sdw_slave_set_frequency(struct sdw_slave *slave)
+int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base)
 {
 	u32 mclk_freq = slave->bus->prop.mclk_freq;
 	u32 curr_freq = slave->bus->params.curr_dr_freq >> 1;
 	unsigned int scale;
 	u8 scale_index;
-	u8 base;
-	int ret;
-
-	/*
-	 * frequency base and scale registers are required for SDCA
-	 * devices. They may also be used for 1.2+/non-SDCA devices.
-	 * Driver can set the property, we will need a DisCo property
-	 * to discover this case from platform firmware.
-	 */
-	if (!slave->id.class_id && !slave->prop.clock_reg_supported)
-		return 0;
 
 	if (!mclk_freq) {
 		dev_err(&slave->dev,
@@ -1311,19 +1310,19 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave)
 	 */
 	if (!(19200000 % mclk_freq)) {
 		mclk_freq = 19200000;
-		base = SDW_SCP_BASE_CLOCK_19200000_HZ;
+		*base = SDW_SCP_BASE_CLOCK_19200000_HZ;
 	} else if (!(22579200 % mclk_freq)) {
 		mclk_freq = 22579200;
-		base = SDW_SCP_BASE_CLOCK_22579200_HZ;
+		*base = SDW_SCP_BASE_CLOCK_22579200_HZ;
 	} else if (!(24576000 % mclk_freq)) {
 		mclk_freq = 24576000;
-		base = SDW_SCP_BASE_CLOCK_24576000_HZ;
+		*base = SDW_SCP_BASE_CLOCK_24576000_HZ;
 	} else if (!(32000000 % mclk_freq)) {
 		mclk_freq = 32000000;
-		base = SDW_SCP_BASE_CLOCK_32000000_HZ;
+		*base = SDW_SCP_BASE_CLOCK_32000000_HZ;
 	} else if (!(96000000 % mclk_freq)) {
 		mclk_freq = 24000000;
-		base = SDW_SCP_BASE_CLOCK_24000000_HZ;
+		*base = SDW_SCP_BASE_CLOCK_24000000_HZ;
 	} else {
 		dev_err(&slave->dev,
 			"Unsupported clock base, mclk %d\n",
@@ -1354,6 +1353,34 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave)
 	}
 	scale_index++;
 
+	dev_dbg(&slave->dev,
+		"Configured bus base %d, scale %d, mclk %d, curr_freq %d\n",
+		*base, scale_index, mclk_freq, curr_freq);
+
+	return scale_index;
+}
+EXPORT_SYMBOL(sdw_slave_get_scale_index);
+
+static int sdw_slave_set_frequency(struct sdw_slave *slave)
+{
+	int scale_index;
+	u8 base;
+	int ret;
+
+	/*
+	 * frequency base and scale registers are required for SDCA
+	 * devices. They may also be used for 1.2+/non-SDCA devices.
+	 * Driver can set the property directly, for now there's no
+	 * DisCo property to discover support for the scaling registers
+	 * from platform firmware.
+	 */
+	if (!slave->id.class_id && !slave->prop.clock_reg_supported)
+		return 0;
+
+	scale_index = sdw_slave_get_scale_index(slave, &base);
+	if (scale_index < 0)
+		return scale_index;
+
 	ret = sdw_write_no_pm(slave, SDW_SCP_BUS_CLOCK_BASE, base);
 	if (ret < 0) {
 		dev_err(&slave->dev,
@@ -1373,10 +1400,6 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave)
 		dev_err(&slave->dev,
 			"SDW_SCP_BUSCLOCK_SCALE_B1 write failed:%d\n", ret);
 
-	dev_dbg(&slave->dev,
-		"Configured bus base %d, scale %d, mclk %d, curr_freq %d\n",
-		base, scale_index, mclk_freq, curr_freq);
-
 	return ret;
 }
 
diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h
index fda6b24ac2da..fc990171b3f7 100644
--- a/drivers/soundwire/bus.h
+++ b/drivers/soundwire/bus.h
@@ -90,6 +90,7 @@ int sdw_find_col_index(int col);
  * @transport_params: Transport parameters
  * @port_params: Port parameters
  * @port_node: List node for Master or Slave port_list
+ * @lane: Which lane is used
  *
  * SoundWire spec has no mention of ports for Master interface but the
  * concept is logically extended.
@@ -100,6 +101,7 @@ struct sdw_port_runtime {
 	struct sdw_transport_params transport_params;
 	struct sdw_port_params port_params;
 	struct list_head port_node;
+	unsigned int lane;
 };
 
 /**
@@ -149,6 +151,7 @@ struct sdw_transport_data {
 	int hstop;
 	int block_offset;
 	int sub_block_offset;
+	unsigned int lane;
 };
 
 struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index 77dc094075e1..e98d5db81b1c 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -167,9 +167,6 @@ static int sdw_drv_remove(struct device *dev)
 
 	slave->probed = false;
 
-	if (slave->prop.use_domain_irq)
-		sdw_irq_dispose_mapping(slave);
-
 	mutex_unlock(&slave->sdw_dev_lock);
 
 	if (drv->remove)
diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c
index b9316207c3ab..59965f43c2fb 100644
--- a/drivers/soundwire/generic_bandwidth_allocation.c
+++ b/drivers/soundwire/generic_bandwidth_allocation.c
@@ -18,6 +18,7 @@
 
 struct sdw_group_params {
 	unsigned int rate;
+	unsigned int lane;
 	int full_bw;
 	int payload_bw;
 	int hwidth;
@@ -27,6 +28,7 @@ struct sdw_group {
 	unsigned int count;
 	unsigned int max_size;
 	unsigned int *rates;
+	unsigned int *lanes;
 };
 
 void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
@@ -48,6 +50,9 @@ void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
 		slave_total_ch = 0;
 
 		list_for_each_entry(p_rt, &s_rt->port_list, port_node) {
+			if (p_rt->lane != t_data->lane)
+				continue;
+
 			ch = hweight32(p_rt->ch_mask);
 
 			sdw_fill_xport_params(&p_rt->transport_params,
@@ -56,7 +61,7 @@ void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt,
 					      sample_int, port_bo, port_bo >> 8,
 					      t_data->hstart,
 					      t_data->hstop,
-					      SDW_BLK_PKG_PER_PORT, 0x0);
+					      SDW_BLK_PKG_PER_PORT, p_rt->lane);
 
 			sdw_fill_port_params(&p_rt->port_params,
 					     p_rt->num, bps,
@@ -105,11 +110,13 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 	t_data.hstart = hstart;
 
 	list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+		if (p_rt->lane != params->lane)
+			continue;
 
 		sdw_fill_xport_params(&p_rt->transport_params, p_rt->num,
 				      false, SDW_BLK_GRP_CNT_1, sample_int,
 				      *port_bo, (*port_bo) >> 8, hstart, hstop,
-				      SDW_BLK_PKG_PER_PORT, 0x0);
+				      SDW_BLK_PKG_PER_PORT, p_rt->lane);
 
 		sdw_fill_port_params(&p_rt->port_params,
 				     p_rt->num, bps,
@@ -131,6 +138,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt,
 		(*port_bo) += bps * ch;
 	}
 
+	t_data.lane = params->lane;
 	sdw_compute_slave_ports(m_rt, &t_data);
 }
 
@@ -138,69 +146,107 @@ static void _sdw_compute_port_params(struct sdw_bus *bus,
 				     struct sdw_group_params *params, int count)
 {
 	struct sdw_master_runtime *m_rt;
-	int hstop = bus->params.col - 1;
-	int port_bo, i;
+	int port_bo, i, l;
+	int hstop;
 
 	/* Run loop for all groups to compute transport parameters */
-	for (i = 0; i < count; i++) {
-		port_bo = 1;
+	for (l = 0; l < SDW_MAX_LANES; l++) {
+		if (l > 0 && !bus->lane_used_bandwidth[l])
+			continue;
+		/* reset hstop for each lane */
+		hstop = bus->params.col - 1;
+		for (i = 0; i < count; i++) {
+			if (params[i].lane != l)
+				continue;
+			port_bo = 1;
 
-		list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
-			sdw_compute_master_ports(m_rt, &params[i], &port_bo, hstop);
-		}
+			list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+				sdw_compute_master_ports(m_rt, &params[i], &port_bo, hstop);
+			}
 
-		hstop = hstop - params[i].hwidth;
+			hstop = hstop - params[i].hwidth;
+		}
 	}
 }
 
 static int sdw_compute_group_params(struct sdw_bus *bus,
+				    struct sdw_stream_runtime *stream,
 				    struct sdw_group_params *params,
-				    int *rates, int count)
+				    struct sdw_group *group)
 {
 	struct sdw_master_runtime *m_rt;
+	struct sdw_port_runtime *p_rt;
 	int sel_col = bus->params.col;
 	unsigned int rate, bps, ch;
-	int i, column_needed = 0;
+	int i, l, column_needed;
 
 	/* Calculate bandwidth per group */
-	for (i = 0; i < count; i++) {
-		params[i].rate = rates[i];
+	for (i = 0; i < group->count; i++) {
+		params[i].rate = group->rates[i];
+		params[i].lane = group->lanes[i];
 		params[i].full_bw = bus->params.curr_dr_freq / params[i].rate;
 	}
 
 	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
-		rate = m_rt->stream->params.rate;
-		bps = m_rt->stream->params.bps;
-		ch = m_rt->ch_count;
+		if (m_rt->stream == stream) {
+			/* Only runtime during prepare should be added */
+			if (stream->state != SDW_STREAM_CONFIGURED)
+				continue;
+		} else {
+			/*
+			 * Include runtimes with running (ENABLED state) and paused (DISABLED state)
+			 * streams
+			 */
+			if (m_rt->stream->state != SDW_STREAM_ENABLED &&
+			    m_rt->stream->state != SDW_STREAM_DISABLED)
+				continue;
+		}
+		list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+			rate = m_rt->stream->params.rate;
+			bps = m_rt->stream->params.bps;
+			ch = hweight32(p_rt->ch_mask);
 
-		for (i = 0; i < count; i++) {
-			if (rate == params[i].rate)
-				params[i].payload_bw += bps * ch;
+			for (i = 0; i < group->count; i++) {
+				if (rate == params[i].rate && p_rt->lane == params[i].lane)
+					params[i].payload_bw += bps * ch;
+			}
 		}
 	}
 
-	for (i = 0; i < count; i++) {
-		params[i].hwidth = (sel_col *
-			params[i].payload_bw + params[i].full_bw - 1) /
-			params[i].full_bw;
+	for (l = 0; l < SDW_MAX_LANES; l++) {
+		if (l > 0 && !bus->lane_used_bandwidth[l])
+			continue;
+		/* reset column_needed for each lane */
+		column_needed = 0;
+		for (i = 0; i < group->count; i++) {
+			if (params[i].lane != l)
+				continue;
+
+			params[i].hwidth = (sel_col * params[i].payload_bw +
+					    params[i].full_bw - 1) / params[i].full_bw;
 
-		column_needed += params[i].hwidth;
+			column_needed += params[i].hwidth;
+			/* There is no control column for lane 1 and above */
+			if (column_needed > sel_col)
+				return -EINVAL;
+			/* Column 0 is control column on lane 0 */
+			if (params[i].lane == 0 && column_needed > sel_col - 1)
+				return -EINVAL;
+		}
 	}
 
-	if (column_needed > sel_col - 1)
-		return -EINVAL;
 
 	return 0;
 }
 
 static int sdw_add_element_group_count(struct sdw_group *group,
-				       unsigned int rate)
+				       unsigned int rate, unsigned int lane)
 {
 	int num = group->count;
 	int i;
 
 	for (i = 0; i <= num; i++) {
-		if (rate == group->rates[i])
+		if (rate == group->rates[i] && lane == group->lanes[i])
 			break;
 
 		if (i != num)
@@ -208,6 +254,7 @@ static int sdw_add_element_group_count(struct sdw_group *group,
 
 		if (group->count >= group->max_size) {
 			unsigned int *rates;
+			unsigned int *lanes;
 
 			group->max_size += 1;
 			rates = krealloc(group->rates,
@@ -215,10 +262,20 @@ static int sdw_add_element_group_count(struct sdw_group *group,
 					 GFP_KERNEL);
 			if (!rates)
 				return -ENOMEM;
+
 			group->rates = rates;
+
+			lanes = krealloc(group->lanes,
+					 (sizeof(int) * group->max_size),
+					 GFP_KERNEL);
+			if (!lanes)
+				return -ENOMEM;
+
+			group->lanes = lanes;
 		}
 
-		group->rates[group->count++] = rate;
+		group->rates[group->count] = rate;
+		group->lanes[group->count++] = lane;
 	}
 
 	return 0;
@@ -228,6 +285,7 @@ static int sdw_get_group_count(struct sdw_bus *bus,
 			       struct sdw_group *group)
 {
 	struct sdw_master_runtime *m_rt;
+	struct sdw_port_runtime *p_rt;
 	unsigned int rate;
 	int ret = 0;
 
@@ -237,17 +295,32 @@ static int sdw_get_group_count(struct sdw_bus *bus,
 	if (!group->rates)
 		return -ENOMEM;
 
+	group->lanes = kcalloc(group->max_size, sizeof(int), GFP_KERNEL);
+	if (!group->lanes) {
+		kfree(group->rates);
+		group->rates = NULL;
+		return -ENOMEM;
+	}
+
 	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+		if (m_rt->stream->state == SDW_STREAM_DEPREPARED)
+			continue;
+
 		rate = m_rt->stream->params.rate;
 		if (m_rt == list_first_entry(&bus->m_rt_list,
 					     struct sdw_master_runtime,
 					     bus_node)) {
 			group->rates[group->count++] = rate;
-
-		} else {
-			ret = sdw_add_element_group_count(group, rate);
+		}
+		/*
+		 * Different ports could use different lane, add group element
+		 * even if m_rt is the first entry
+		 */
+		list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+			ret = sdw_add_element_group_count(group, rate, p_rt->lane);
 			if (ret < 0) {
 				kfree(group->rates);
+				kfree(group->lanes);
 				return ret;
 			}
 		}
@@ -260,8 +333,9 @@ static int sdw_get_group_count(struct sdw_bus *bus,
  * sdw_compute_port_params: Compute transport and port parameters
  *
  * @bus: SDW Bus instance
+ * @stream: Soundwire stream
  */
-static int sdw_compute_port_params(struct sdw_bus *bus)
+static int sdw_compute_port_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream)
 {
 	struct sdw_group_params *params = NULL;
 	struct sdw_group group;
@@ -281,8 +355,7 @@ static int sdw_compute_port_params(struct sdw_bus *bus)
 	}
 
 	/* Compute transport parameters for grouped streams */
-	ret = sdw_compute_group_params(bus, params,
-				       &group.rates[0], group.count);
+	ret = sdw_compute_group_params(bus, stream, params, &group);
 	if (ret < 0)
 		goto free_params;
 
@@ -292,6 +365,7 @@ free_params:
 	kfree(params);
 out:
 	kfree(group.rates);
+	kfree(group.lanes);
 
 	return ret;
 }
@@ -299,7 +373,6 @@ out:
 static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
 {
 	struct sdw_master_prop *prop = &bus->prop;
-	int frame_int, frame_freq;
 	int r, c;
 
 	for (c = 0; c < SDW_FRAME_COLS; c++) {
@@ -308,11 +381,8 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
 			    sdw_cols[c] != prop->default_col)
 				continue;
 
-			frame_int = sdw_rows[r] * sdw_cols[c];
-			frame_freq = clk_freq / frame_int;
-
-			if ((clk_freq - (frame_freq * SDW_FRAME_CTRL_BITS)) <
-			    bus->params.bandwidth)
+			if (clk_freq * (sdw_cols[c] - 1) <
+			    bus->params.bandwidth * sdw_cols[c])
 				continue;
 
 			bus->params.row = sdw_rows[r];
@@ -324,6 +394,95 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
 	return -EINVAL;
 }
 
+static bool is_clock_scaling_supported(struct sdw_bus *bus)
+{
+	struct sdw_master_runtime *m_rt;
+	struct sdw_slave_runtime *s_rt;
+
+	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node)
+		list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node)
+			if (!is_clock_scaling_supported_by_slave(s_rt->slave))
+				return false;
+
+	return true;
+}
+
+/**
+ * is_lane_connected_to_all_peripherals: Check if the given manager lane connects to all peripherals
+ * So that all peripherals can use the manager lane.
+ *
+ * @m_rt: Manager runtime
+ * @lane: Lane number
+ */
+static bool is_lane_connected_to_all_peripherals(struct sdw_master_runtime *m_rt, unsigned int lane)
+{
+	struct sdw_slave_prop *slave_prop;
+	struct sdw_slave_runtime *s_rt;
+	int i;
+
+	list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+		slave_prop = &s_rt->slave->prop;
+		for (i = 1; i < SDW_MAX_LANES; i++) {
+			if (slave_prop->lane_maps[i] == lane) {
+				dev_dbg(&s_rt->slave->dev,
+					"M lane %d is connected to P lane %d\n",
+					lane, i);
+				break;
+			}
+		}
+		if (i == SDW_MAX_LANES) {
+			dev_dbg(&s_rt->slave->dev, "M lane %d is not connected\n", lane);
+			return false;
+		}
+	}
+	return true;
+}
+
+static int get_manager_lane(struct sdw_bus *bus, struct sdw_master_runtime *m_rt,
+			    struct sdw_slave_runtime *s_rt, unsigned int curr_dr_freq)
+{
+	struct sdw_slave_prop *slave_prop = &s_rt->slave->prop;
+	struct sdw_port_runtime *m_p_rt;
+	unsigned int required_bandwidth;
+	int m_lane;
+	int l;
+
+	for (l = 1; l < SDW_MAX_LANES; l++) {
+		if (!slave_prop->lane_maps[l])
+			continue;
+
+		required_bandwidth = 0;
+		list_for_each_entry(m_p_rt, &m_rt->port_list, port_node) {
+			required_bandwidth += m_rt->stream->params.rate *
+					      hweight32(m_p_rt->ch_mask) *
+					      m_rt->stream->params.bps;
+		}
+		if (required_bandwidth <=
+		    curr_dr_freq - bus->lane_used_bandwidth[l]) {
+			/* Check if m_lane is connected to all Peripherals */
+			if (!is_lane_connected_to_all_peripherals(m_rt,
+				slave_prop->lane_maps[l])) {
+				dev_dbg(bus->dev,
+					"Not all Peripherals are connected to M lane %d\n",
+					slave_prop->lane_maps[l]);
+				continue;
+			}
+			m_lane = slave_prop->lane_maps[l];
+			dev_dbg(&s_rt->slave->dev, "M lane %d is used\n", m_lane);
+			bus->lane_used_bandwidth[l] += required_bandwidth;
+			/*
+			 * Use non-zero manager lane, subtract the lane 0
+			 * bandwidth that is already calculated
+			 */
+			bus->params.bandwidth -= required_bandwidth;
+			return m_lane;
+		}
+	}
+
+	/* No available multi lane found, only lane 0 can be used */
+	return 0;
+}
+
 /**
  * sdw_compute_bus_params: Compute bus parameters
  *
@@ -331,10 +490,16 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq)
  */
 static int sdw_compute_bus_params(struct sdw_bus *bus)
 {
-	unsigned int curr_dr_freq = 0;
 	struct sdw_master_prop *mstr_prop = &bus->prop;
-	int i, clk_values, ret;
+	struct sdw_slave_prop *slave_prop;
+	struct sdw_port_runtime *m_p_rt;
+	struct sdw_port_runtime *s_p_rt;
+	struct sdw_master_runtime *m_rt;
+	struct sdw_slave_runtime *s_rt;
+	unsigned int curr_dr_freq = 0;
+	int i, l, clk_values, ret;
 	bool is_gear = false;
+	int m_lane = 0;
 	u32 *clk_buf;
 
 	if (mstr_prop->num_clk_gears) {
@@ -349,6 +514,10 @@ static int sdw_compute_bus_params(struct sdw_bus *bus)
 		clk_buf = NULL;
 	}
 
+	/* If dynamic scaling is not supported, don't try higher freq */
+	if (!is_clock_scaling_supported(bus))
+		clk_values = 1;
+
 	for (i = 0; i < clk_values; i++) {
 		if (!clk_buf)
 			curr_dr_freq = bus->params.max_dr_freq;
@@ -357,10 +526,26 @@ static int sdw_compute_bus_params(struct sdw_bus *bus)
 				(bus->params.max_dr_freq >>  clk_buf[i]) :
 				clk_buf[i] * SDW_DOUBLE_RATE_FACTOR;
 
-		if (curr_dr_freq <= bus->params.bandwidth)
-			continue;
+		if (curr_dr_freq * (mstr_prop->default_col - 1) >=
+		    bus->params.bandwidth * mstr_prop->default_col)
+			break;
 
-		break;
+		list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
+			/*
+			 * Get the first s_rt that will be used to find the available lane that
+			 * can be used. No need to check all Peripherals because we can't use
+			 * multi-lane if we can't find any available lane for the first Peripheral.
+			 */
+			s_rt = list_first_entry(&m_rt->slave_rt_list,
+						struct sdw_slave_runtime, m_rt_node);
+
+			/*
+			 * Find the available Manager lane that connected to the first Peripheral.
+			 */
+			m_lane = get_manager_lane(bus, m_rt, s_rt, curr_dr_freq);
+			if (m_lane > 0)
+				goto out;
+		}
 
 		/*
 		 * TODO: Check all the Slave(s) port(s) audio modes and find
@@ -374,6 +559,38 @@ static int sdw_compute_bus_params(struct sdw_bus *bus)
 			__func__, bus->params.bandwidth);
 		return -EINVAL;
 	}
+out:
+	/* multilane can be used */
+	if (m_lane > 0) {
+		/* Set Peripheral lanes */
+		list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) {
+			slave_prop = &s_rt->slave->prop;
+			for (l = 1; l < SDW_MAX_LANES; l++) {
+				if (slave_prop->lane_maps[l] == m_lane) {
+					list_for_each_entry(s_p_rt, &s_rt->port_list, port_node) {
+						s_p_rt->lane = l;
+						dev_dbg(&s_rt->slave->dev,
+							"Set P lane %d for port %d\n",
+							l, s_p_rt->num);
+					}
+					break;
+				}
+			}
+		}
+		/*
+		 * Set Manager lanes. Configure the last m_rt in bus->m_rt_list only since
+		 * we don't want to touch other m_rts that are already working.
+		 */
+		list_for_each_entry(m_p_rt, &m_rt->port_list, port_node) {
+			m_p_rt->lane = m_lane;
+		}
+	}
+
+	if (!mstr_prop->default_frame_rate || !mstr_prop->default_row)
+		return -EINVAL;
+
+	mstr_prop->default_col = curr_dr_freq / mstr_prop->default_frame_rate /
+				 mstr_prop->default_row;
 
 	ret = sdw_select_row_col(bus, curr_dr_freq);
 	if (ret < 0) {
@@ -390,8 +607,9 @@ static int sdw_compute_bus_params(struct sdw_bus *bus)
  * sdw_compute_params: Compute bus, transport and port parameters
  *
  * @bus: SDW Bus instance
+ * @stream: Soundwire stream
  */
-int sdw_compute_params(struct sdw_bus *bus)
+int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream)
 {
 	int ret;
 
@@ -401,7 +619,7 @@ int sdw_compute_params(struct sdw_bus *bus)
 		return ret;
 
 	/* Compute transport and port params */
-	ret = sdw_compute_port_params(bus);
+	ret = sdw_compute_port_params(bus, stream);
 	if (ret < 0) {
 		dev_err(bus->dev, "Compute transport params failed: %d\n", ret);
 		return ret;
diff --git a/drivers/soundwire/irq.c b/drivers/soundwire/irq.c
index 0c08cebb1235..c237e6d0766b 100644
--- a/drivers/soundwire/irq.c
+++ b/drivers/soundwire/irq.c
@@ -46,14 +46,18 @@ void sdw_irq_delete(struct sdw_bus *bus)
 	irq_domain_remove(bus->domain);
 }
 
+static void sdw_irq_dispose_mapping(void *data)
+{
+	struct sdw_slave *slave = data;
+
+	irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num));
+}
+
 void sdw_irq_create_mapping(struct sdw_slave *slave)
 {
 	slave->irq = irq_create_mapping(slave->bus->domain, slave->dev_num);
 	if (!slave->irq)
 		dev_warn(&slave->dev, "Failed to map IRQ\n");
-}
 
-void sdw_irq_dispose_mapping(struct sdw_slave *slave)
-{
-	irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num));
+	devm_add_action_or_reset(&slave->dev, sdw_irq_dispose_mapping, slave);
 }
diff --git a/drivers/soundwire/irq.h b/drivers/soundwire/irq.h
index 58a58046d92b..86e2318409da 100644
--- a/drivers/soundwire/irq.h
+++ b/drivers/soundwire/irq.h
@@ -16,7 +16,6 @@ int sdw_irq_create(struct sdw_bus *bus,
 		   struct fwnode_handle *fwnode);
 void sdw_irq_delete(struct sdw_bus *bus);
 void sdw_irq_create_mapping(struct sdw_slave *slave);
-void sdw_irq_dispose_mapping(struct sdw_slave *slave);
 
 #else /* CONFIG_IRQ_DOMAIN */
 
@@ -34,10 +33,6 @@ static inline void sdw_irq_create_mapping(struct sdw_slave *slave)
 {
 }
 
-static inline void sdw_irq_dispose_mapping(struct sdw_slave *slave)
-{
-}
-
 #endif /* CONFIG_IRQ_DOMAIN */
 
 #endif /* __SDW_IRQ_H */
diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c
index 9d59f486edbe..65afb28ef8fa 100644
--- a/drivers/soundwire/mipi_disco.c
+++ b/drivers/soundwire/mipi_disco.c
@@ -366,6 +366,44 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave,
 	return 0;
 }
 
+/*
+ * In MIPI DisCo spec for SoundWire, lane mapping for a slave device is done with
+ * mipi-sdw-lane-x-mapping properties, where x is 1..7, and the values for those
+ * properties are mipi-sdw-manager-lane-x or mipi-sdw-peripheral-link-y, where x
+ * is an integer between 1 to 7 if the lane is connected to a manager lane, y is a
+ * character between A to E if the lane is connected to another peripheral lane.
+ */
+int sdw_slave_read_lane_mapping(struct sdw_slave *slave)
+{
+	struct sdw_slave_prop *prop = &slave->prop;
+	struct device *dev = &slave->dev;
+	char prop_name[30];
+	const char *prop_val;
+	size_t len;
+	int ret, i;
+	u8 lane;
+
+	for (i = 0; i < SDW_MAX_LANES; i++) {
+		snprintf(prop_name, sizeof(prop_name), "mipi-sdw-lane-%d-mapping", i);
+		ret = device_property_read_string(dev, prop_name, &prop_val);
+		if (ret)
+			continue;
+
+		len = strlen(prop_val);
+		if (len < 1)
+			return -EINVAL;
+
+		/* The last character is enough to identify the connection */
+		ret = kstrtou8(&prop_val[len - 1], 10, &lane);
+		if (ret)
+			return ret;
+		if (in_range(lane, 1, SDW_MAX_LANES - 1))
+			prop->lane_maps[i] = lane;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(sdw_slave_read_lane_mapping);
+
 /**
  * sdw_slave_read_prop() - Read Slave properties
  * @slave: SDW Slave
@@ -486,6 +524,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave)
 	sdw_slave_read_dpn(slave, prop->sink_dpn_prop, nval,
 			   prop->sink_ports, "sink");
 
-	return 0;
+	return sdw_slave_read_lane_mapping(slave);
 }
 EXPORT_SYMBOL(sdw_slave_read_prop);
diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c
index e00c5ac496a6..0f45e3404756 100644
--- a/drivers/soundwire/qcom.c
+++ b/drivers/soundwire/qcom.c
@@ -1072,7 +1072,7 @@ static const struct sdw_master_ops qcom_swrm_ops = {
 	.pre_bank_switch = qcom_swrm_pre_bank_switch,
 };
 
-static int qcom_swrm_compute_params(struct sdw_bus *bus)
+static int qcom_swrm_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream)
 {
 	struct qcom_swrm_ctrl *ctrl = to_qcom_sdw(bus);
 	struct sdw_master_runtime *m_rt;
diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
index 7aa4900dcf31..e9df503332bb 100644
--- a/drivers/soundwire/stream.c
+++ b/drivers/soundwire/stream.c
@@ -629,8 +629,44 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt)
 static int sdw_program_params(struct sdw_bus *bus, bool prepare)
 {
 	struct sdw_master_runtime *m_rt;
+	struct sdw_slave *slave;
 	int ret = 0;
+	u32 addr1;
+
+	/* Check if all Peripherals comply with SDCA */
+	list_for_each_entry(slave, &bus->slaves, node) {
+		if (!slave->dev_num_sticky)
+			continue;
+		if (!is_clock_scaling_supported_by_slave(slave)) {
+			dev_dbg(&slave->dev, "The Peripheral doesn't comply with SDCA\n");
+			goto manager_runtime;
+		}
+	}
+
+	if (bus->params.next_bank)
+		addr1 = SDW_SCP_BUSCLOCK_SCALE_B1;
+	else
+		addr1 = SDW_SCP_BUSCLOCK_SCALE_B0;
+
+	/* Program SDW_SCP_BUSCLOCK_SCALE if all Peripherals comply with SDCA */
+	list_for_each_entry(slave, &bus->slaves, node) {
+		int scale_index;
+		u8 base;
+
+		if (!slave->dev_num_sticky)
+			continue;
+		scale_index = sdw_slave_get_scale_index(slave, &base);
+		if (scale_index < 0)
+			return scale_index;
+
+		ret = sdw_write_no_pm(slave, addr1, scale_index);
+		if (ret < 0) {
+			dev_err(&slave->dev, "SDW_SCP_BUSCLOCK_SCALE register write failed\n");
+			return ret;
+		}
+	}
 
+manager_runtime:
 	list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) {
 
 		/*
@@ -1383,7 +1419,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream,
 
 			/* Compute params */
 			if (bus->compute_params) {
-				ret = bus->compute_params(bus);
+				ret = bus->compute_params(bus, stream);
 				if (ret < 0) {
 					dev_err(bus->dev, "Compute params failed: %d\n",
 						ret);
@@ -1642,9 +1678,19 @@ EXPORT_SYMBOL(sdw_disable_stream);
 static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream)
 {
 	struct sdw_master_runtime *m_rt;
+	struct sdw_port_runtime *p_rt;
+	unsigned int multi_lane_bandwidth;
+	unsigned int bandwidth;
 	struct sdw_bus *bus;
+	int state = stream->state;
 	int ret = 0;
 
+	/*
+	 * first mark the state as DEPREPARED so that it is not taken into account
+	 * for bit allocation
+	 */
+	stream->state = SDW_STREAM_DEPREPARED;
+
 	list_for_each_entry(m_rt, &stream->master_list, stream_node) {
 		bus = m_rt->bus;
 		/* De-prepare port(s) */
@@ -1652,19 +1698,34 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream)
 		if (ret < 0) {
 			dev_err(bus->dev,
 				"De-prepare port(s) failed: %d\n", ret);
+			stream->state = state;
 			return ret;
 		}
 
+		multi_lane_bandwidth = 0;
+
+		list_for_each_entry(p_rt, &m_rt->port_list, port_node) {
+			if (!p_rt->lane)
+				continue;
+
+			bandwidth = m_rt->stream->params.rate * hweight32(p_rt->ch_mask) *
+				    m_rt->stream->params.bps;
+			multi_lane_bandwidth += bandwidth;
+			bus->lane_used_bandwidth[p_rt->lane] -= bandwidth;
+			if (!bus->lane_used_bandwidth[p_rt->lane])
+				p_rt->lane = 0;
+		}
 		/* TODO: Update this during Device-Device support */
-		bus->params.bandwidth -= m_rt->stream->params.rate *
-			m_rt->ch_count * m_rt->stream->params.bps;
+		bandwidth = m_rt->stream->params.rate * m_rt->ch_count * m_rt->stream->params.bps;
+		bus->params.bandwidth -= bandwidth - multi_lane_bandwidth;
 
 		/* Compute params */
 		if (bus->compute_params) {
-			ret = bus->compute_params(bus);
+			ret = bus->compute_params(bus, stream);
 			if (ret < 0) {
 				dev_err(bus->dev, "Compute params failed: %d\n",
 					ret);
+				stream->state = state;
 				return ret;
 			}
 		}
@@ -1673,11 +1734,11 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream)
 		ret = sdw_program_params(bus, false);
 		if (ret < 0) {
 			dev_err(bus->dev, "%s: Program params failed: %d\n", __func__, ret);
+			stream->state = state;
 			return ret;
 		}
 	}
 
-	stream->state = SDW_STREAM_DEPREPARED;
 	return do_bank_switch(stream);
 }
 
diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c
index 3cafdf22c909..122140b97579 100644
--- a/drivers/spmi/hisi-spmi-controller.c
+++ b/drivers/spmi/hisi-spmi-controller.c
@@ -300,9 +300,6 @@ static int spmi_controller_probe(struct platform_device *pdev)
 
 	spin_lock_init(&spmi_controller->lock);
 
-	ctrl->dev.parent = pdev->dev.parent;
-	ctrl->dev.of_node = of_node_get(pdev->dev.of_node);
-
 	/* Callbacks */
 	ctrl->read_cmd = spmi_read_cmd;
 	ctrl->write_cmd = spmi_write_cmd;
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
index fb0101da1485..3cf8d9bd4566 100644
--- a/drivers/spmi/spmi.c
+++ b/drivers/spmi/spmi.c
@@ -517,7 +517,7 @@ static void of_spmi_register_devices(struct spmi_controller *ctrl)
 		if (!sdev)
 			continue;
 
-		sdev->dev.of_node = node;
+		device_set_node(&sdev->dev, of_fwnode_handle(node));
 		sdev->usid = (u8)reg[0];
 
 		err = spmi_device_add(sdev);
diff --git a/drivers/staging/fbtft/fb_ssd1351.c b/drivers/staging/fbtft/fb_ssd1351.c
index f6db2933ebba..6736b09b2f45 100644
--- a/drivers/staging/fbtft/fb_ssd1351.c
+++ b/drivers/staging/fbtft/fb_ssd1351.c
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/spi/spi.h>
 #include <linux/delay.h>
+#include <linux/string_choices.h>
 
 #include "fbtft.h"
 
@@ -162,7 +163,7 @@ static int set_gamma(struct fbtft_par *par, u32 *curves)
 static int blank(struct fbtft_par *par, bool on)
 {
 	fbtft_par_dbg(DEBUG_BLANK, par, "(%s=%s)\n",
-		      __func__, on ? "true" : "false");
+		      __func__, str_true_false(on));
 	if (on)
 		write_reg(par, 0xAE);
 	else
diff --git a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c
index 8e2334fe5c9b..3f4f95b7fe34 100644
--- a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c
+++ b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c
@@ -30,11 +30,8 @@ int agilent_82350b_accel_read(gpib_board_t *board, uint8_t *buffer, size_t lengt
 	unsigned short event_status;
 	int i, num_fifo_bytes;
 	//hardware doesn't support checking for end-of-string character when using fifo
-	if (tms_priv->eos_flags & REOS) {
-		//pr_info("ag-rd: using tms9914 read for REOS %x EOS %x\n",tms_priv->eos_flags,
-		// tms_priv->eos);
+	if (tms_priv->eos_flags & REOS)
 		return tms9914_read(board, tms_priv, buffer, length, end, bytes_read);
-	}
 
 	clear_bit(DEV_CLEAR_BN, &tms_priv->state);
 
@@ -811,15 +808,15 @@ void agilent_82350b_detach(gpib_board_t *board)
 		if (a_priv->gpib_base) {
 			tms9914_board_reset(tms_priv);
 			if (a_priv->misc_base)
-				iounmap((void *)a_priv->misc_base);
+				iounmap(a_priv->misc_base);
 			if (a_priv->borg_base)
-				iounmap((void *)a_priv->borg_base);
+				iounmap(a_priv->borg_base);
 			if (a_priv->sram_base)
-				iounmap((void *)a_priv->sram_base);
+				iounmap(a_priv->sram_base);
 			if (a_priv->gpib_base)
-				iounmap((void *)a_priv->gpib_base);
+				iounmap(a_priv->gpib_base);
 			if (a_priv->plx_base)
-				iounmap((void *)a_priv->plx_base);
+				iounmap(a_priv->plx_base);
 			pci_release_regions(a_priv->pci_device);
 		}
 		if (a_priv->pci_device)
@@ -828,58 +825,58 @@ void agilent_82350b_detach(gpib_board_t *board)
 	agilent_82350b_free_private(board);
 }
 
-gpib_interface_t agilent_82350b_unaccel_interface = {
-name: "agilent_82350b_unaccel",
-attach : agilent_82350b_unaccel_attach,
-detach : agilent_82350b_detach,
-read : agilent_82350b_read,
-write : agilent_82350b_write,
-command : agilent_82350b_command,
-request_system_control : agilent_82350b_request_system_control,
-take_control : agilent_82350b_take_control,
-go_to_standby : agilent_82350b_go_to_standby,
-interface_clear : agilent_82350b_interface_clear,
-remote_enable : agilent_82350b_remote_enable,
-enable_eos : agilent_82350b_enable_eos,
-disable_eos : agilent_82350b_disable_eos,
-parallel_poll : agilent_82350b_parallel_poll,
-parallel_poll_configure : agilent_82350b_parallel_poll_configure,
-parallel_poll_response : agilent_82350b_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : agilent_82350b_line_status,
-update_status : agilent_82350b_update_status,
-primary_address : agilent_82350b_primary_address,
-secondary_address : agilent_82350b_secondary_address,
-serial_poll_response : agilent_82350b_serial_poll_response,
-t1_delay : agilent_82350b_t1_delay,
-return_to_local : agilent_82350b_return_to_local,
+static gpib_interface_t agilent_82350b_unaccel_interface = {
+	.name = "agilent_82350b_unaccel",
+	.attach = agilent_82350b_unaccel_attach,
+	.detach = agilent_82350b_detach,
+	.read = agilent_82350b_read,
+	.write = agilent_82350b_write,
+	.command = agilent_82350b_command,
+	.request_system_control = agilent_82350b_request_system_control,
+	.take_control = agilent_82350b_take_control,
+	.go_to_standby = agilent_82350b_go_to_standby,
+	.interface_clear = agilent_82350b_interface_clear,
+	.remote_enable = agilent_82350b_remote_enable,
+	.enable_eos = agilent_82350b_enable_eos,
+	.disable_eos = agilent_82350b_disable_eos,
+	.parallel_poll = agilent_82350b_parallel_poll,
+	.parallel_poll_configure = agilent_82350b_parallel_poll_configure,
+	.parallel_poll_response = agilent_82350b_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = agilent_82350b_line_status,
+	.update_status = agilent_82350b_update_status,
+	.primary_address = agilent_82350b_primary_address,
+	.secondary_address = agilent_82350b_secondary_address,
+	.serial_poll_response = agilent_82350b_serial_poll_response,
+	.t1_delay = agilent_82350b_t1_delay,
+	.return_to_local = agilent_82350b_return_to_local,
 };
 
-gpib_interface_t agilent_82350b_interface = {
-name: "agilent_82350b",
-attach : agilent_82350b_accel_attach,
-detach : agilent_82350b_detach,
-read : agilent_82350b_accel_read,
-write : agilent_82350b_accel_write,
-command : agilent_82350b_command,
-request_system_control : agilent_82350b_request_system_control,
-take_control : agilent_82350b_take_control,
-go_to_standby : agilent_82350b_go_to_standby,
-interface_clear : agilent_82350b_interface_clear,
-remote_enable : agilent_82350b_remote_enable,
-enable_eos : agilent_82350b_enable_eos,
-disable_eos : agilent_82350b_disable_eos,
-parallel_poll : agilent_82350b_parallel_poll,
-parallel_poll_configure : agilent_82350b_parallel_poll_configure,
-parallel_poll_response : agilent_82350b_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : agilent_82350b_line_status,
-update_status : agilent_82350b_update_status,
-primary_address : agilent_82350b_primary_address,
-secondary_address : agilent_82350b_secondary_address,
-serial_poll_response : agilent_82350b_serial_poll_response,
-t1_delay : agilent_82350b_t1_delay,
-return_to_local : agilent_82350b_return_to_local,
+static gpib_interface_t agilent_82350b_interface = {
+	.name = "agilent_82350b",
+	.attach = agilent_82350b_accel_attach,
+	.detach = agilent_82350b_detach,
+	.read = agilent_82350b_accel_read,
+	.write = agilent_82350b_accel_write,
+	.command = agilent_82350b_command,
+	.request_system_control = agilent_82350b_request_system_control,
+	.take_control = agilent_82350b_take_control,
+	.go_to_standby = agilent_82350b_go_to_standby,
+	.interface_clear = agilent_82350b_interface_clear,
+	.remote_enable = agilent_82350b_remote_enable,
+	.enable_eos = agilent_82350b_enable_eos,
+	.disable_eos = agilent_82350b_disable_eos,
+	.parallel_poll = agilent_82350b_parallel_poll,
+	.parallel_poll_configure = agilent_82350b_parallel_poll_configure,
+	.parallel_poll_response = agilent_82350b_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = agilent_82350b_line_status,
+	.update_status = agilent_82350b_update_status,
+	.primary_address = agilent_82350b_primary_address,
+	.secondary_address = agilent_82350b_secondary_address,
+	.serial_poll_response = agilent_82350b_serial_poll_response,
+	.t1_delay = agilent_82350b_t1_delay,
+	.return_to_local = agilent_82350b_return_to_local,
 };
 
 static int agilent_82350b_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
@@ -910,13 +907,30 @@ static int __init agilent_82350b_init_module(void)
 
 	result = pci_register_driver(&agilent_82350b_pci_driver);
 	if (result) {
-		pr_err("agilent_82350b: pci_driver_register failed!\n");
+		pr_err("agilent_82350b: pci_register_driver failed: error = %d\n", result);
 		return result;
 	}
 
-	gpib_register_driver(&agilent_82350b_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&agilent_82350b_interface, THIS_MODULE);
+	result = gpib_register_driver(&agilent_82350b_unaccel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("agilent_82350b: gpib_register_driver failed: error = %d\n", result);
+		goto err_unaccel;
+	}
+
+	result = gpib_register_driver(&agilent_82350b_interface, THIS_MODULE);
+	if (result) {
+		pr_err("agilent_82350b: gpib_register_driver failed: error = %d\n", result);
+		goto err_interface;
+	}
+
 	return 0;
+
+err_interface:
+	gpib_unregister_driver(&agilent_82350b_unaccel_interface);
+err_unaccel:
+	pci_unregister_driver(&agilent_82350b_pci_driver);
+
+	return result;
 }
 
 static void __exit agilent_82350b_exit_module(void)
diff --git a/drivers/staging/gpib/agilent_82350b/agilent_82350b.h b/drivers/staging/gpib/agilent_82350b/agilent_82350b.h
index 30683d67d170..32b322113c10 100644
--- a/drivers/staging/gpib/agilent_82350b/agilent_82350b.h
+++ b/drivers/staging/gpib/agilent_82350b/agilent_82350b.h
@@ -45,11 +45,11 @@ enum board_model {
 struct agilent_82350b_priv {
 	struct tms9914_priv tms9914_priv;
 	struct pci_dev *pci_device;
-	void *plx_base;	//82350a only
-	void *gpib_base;
-	void *sram_base;
-	void *misc_base;
-	void *borg_base;
+	void __iomem *plx_base;	//82350a only
+	void __iomem *gpib_base;
+	void __iomem *sram_base;
+	void __iomem *misc_base;
+	void __iomem *borg_base;
 	int irq;
 	unsigned short card_mode_bits;
 	unsigned short event_status_bits;
@@ -60,8 +60,6 @@ struct agilent_82350b_priv {
 // driver name
 extern const char *driver_name;
 
-// interfaces
-extern gpib_interface_t agilent_82350b_interface;
 // init functions
 
 int agilent_82350b_unaccel_attach(gpib_board_t *board, const gpib_board_config_t *config);
diff --git a/drivers/staging/gpib/agilent_82357a/agilent_82357a.c b/drivers/staging/gpib/agilent_82357a/agilent_82357a.c
index bf05fb4a736b..69f0e490d401 100644
--- a/drivers/staging/gpib/agilent_82357a/agilent_82357a.c
+++ b/drivers/staging/gpib/agilent_82357a/agilent_82357a.c
@@ -19,7 +19,7 @@ MODULE_DESCRIPTION("GPIB driver for Agilent 82357A/B usb adapters");
 
 #define MAX_NUM_82357A_INTERFACES 128
 static struct usb_interface *agilent_82357a_driver_interfaces[MAX_NUM_82357A_INTERFACES];
-DEFINE_MUTEX(agilent_82357a_hotplug_lock); // protect board insertion and removal
+static DEFINE_MUTEX(agilent_82357a_hotplug_lock); // protect board insertion and removal
 
 static unsigned int agilent_82357a_update_status(gpib_board_t *board, unsigned int clear_mask);
 
@@ -1146,25 +1146,6 @@ setup_exit:
 	return retval;
 }
 
-#ifdef RESET_USB_CONFIG
-static int agilent_82357a_reset_usb_configuration(gpib_board_t *board)
-{
-	struct agilent_82357a_priv *a_priv = board->private_data;
-	struct usb_device *usb_dev = interface_to_usbdev(a_priv->bus_interface);
-	struct usb_device *usb_dev;
-	int retval;
-
-	if (!a_priv->bus_interface)
-		return -ENODEV;
-	usb_dev = interface_to_usbdev(a_priv->bus_interface);
-	retval = usb_reset_configuration(usb_dev);
-	if (retval)
-		dev_err(&usb_dev->dev, "%s: usb_reset_configuration() returned %i\n",
-			__func__, retval);
-	return retval;
-}
-#endif
-
 static void agilent_82357a_cleanup_urbs(struct agilent_82357a_priv *a_priv)
 {
 	if (a_priv && a_priv->bus_interface) {
@@ -1175,15 +1156,23 @@ static void agilent_82357a_cleanup_urbs(struct agilent_82357a_priv *a_priv)
 	}
 };
 
+static void agilent_82357a_release_urbs(struct agilent_82357a_priv *a_priv)
+{
+	if (a_priv) {
+		usb_free_urb(a_priv->interrupt_urb);
+		a_priv->interrupt_urb = NULL;
+		kfree(a_priv->interrupt_buffer);
+	}
+}
+
 static int agilent_82357a_allocate_private(gpib_board_t *board)
 {
 	struct agilent_82357a_priv *a_priv;
 
-	board->private_data = kmalloc(sizeof(struct agilent_82357a_priv), GFP_KERNEL);
+	board->private_data = kzalloc(sizeof(struct agilent_82357a_priv), GFP_KERNEL);
 	if (!board->private_data)
 		return -ENOMEM;
 	a_priv = board->private_data;
-	memset(a_priv, 0, sizeof(struct agilent_82357a_priv));
 	mutex_init(&a_priv->bulk_transfer_lock);
 	mutex_init(&a_priv->bulk_alloc_lock);
 	mutex_init(&a_priv->control_alloc_lock);
@@ -1191,11 +1180,11 @@ static int agilent_82357a_allocate_private(gpib_board_t *board)
 	return 0;
 }
 
-static void agilent_82357a_free_private(struct agilent_82357a_priv *a_priv)
+static void agilent_82357a_free_private(gpib_board_t *board)
 {
-	usb_free_urb(a_priv->interrupt_urb);
-	kfree(a_priv->interrupt_buffer);
-	kfree(a_priv);
+	kfree(board->private_data);
+	board->private_data = NULL;
+
 }
 
 static int agilent_82357a_init(gpib_board_t *board)
@@ -1342,16 +1331,14 @@ static int agilent_82357a_attach(gpib_board_t *board, const gpib_board_config_t
 			a_priv->bus_interface = agilent_82357a_driver_interfaces[i];
 			usb_set_intfdata(agilent_82357a_driver_interfaces[i], board);
 			usb_dev = interface_to_usbdev(a_priv->bus_interface);
-			dev_info(&usb_dev->dev,
-				 "bus %d dev num %d attached to gpib minor %d, agilent usb interface %i\n",
-				 usb_dev->bus->busnum, usb_dev->devnum, board->minor, i);
 			break;
 		}
 	}
 	if (i == MAX_NUM_82357A_INTERFACES) {
-		mutex_unlock(&agilent_82357a_hotplug_lock);
-		pr_err("No Agilent 82357 gpib adapters found, have you loaded its firmware?\n");
-		return -ENODEV;
+		dev_err(board->gpib_dev,
+			"No Agilent 82357 gpib adapters found, have you loaded its firmware?\n");
+		retval = -ENODEV;
+		goto attach_fail;
 	}
 	product_id = le16_to_cpu(interface_to_usbdev(a_priv->bus_interface)->descriptor.idProduct);
 	switch (product_id) {
@@ -1365,20 +1352,13 @@ static int agilent_82357a_attach(gpib_board_t *board, const gpib_board_config_t
 		break;
 	default:
 		dev_err(&usb_dev->dev, "bug, unhandled product_id in switch?\n");
-		return -EIO;
-	}
-#ifdef RESET_USB_CONFIG
-	retval = agilent_82357a_reset_usb_configuration(board);
-	if (retval < 0)	{
-		mutex_unlock(&agilent_82357a_hotplug_lock);
-		return retval;
+		retval = -EIO;
+		goto attach_fail;
 	}
-#endif
+
 	retval = agilent_82357a_setup_urbs(board);
-	if (retval < 0)	{
-		mutex_unlock(&agilent_82357a_hotplug_lock);
-		return retval;
-	}
+	if (retval < 0)
+		goto attach_fail;
 
 	timer_setup(&a_priv->bulk_timer, agilent_82357a_timeout_handler, 0);
 
@@ -1387,11 +1367,19 @@ static int agilent_82357a_attach(gpib_board_t *board, const gpib_board_config_t
 	retval = agilent_82357a_init(board);
 
 	if (retval < 0)	{
-		mutex_unlock(&agilent_82357a_hotplug_lock);
-		return retval;
+		agilent_82357a_cleanup_urbs(a_priv);
+		agilent_82357a_release_urbs(a_priv);
+		goto attach_fail;
 	}
 
-	dev_info(&usb_dev->dev, "%s: attached\n", __func__);
+	dev_info(&usb_dev->dev,
+		 "bus %d dev num %d attached to gpib minor %d, agilent usb interface %i\n",
+		 usb_dev->bus->busnum, usb_dev->devnum, board->minor, i);
+	mutex_unlock(&agilent_82357a_hotplug_lock);
+	return retval;
+
+attach_fail:
+	agilent_82357a_free_private(board);
 	mutex_unlock(&agilent_82357a_hotplug_lock);
 	return retval;
 }
@@ -1441,12 +1429,10 @@ static int agilent_82357a_go_idle(gpib_board_t *board)
 static void agilent_82357a_detach(gpib_board_t *board)
 {
 	struct agilent_82357a_priv *a_priv;
-	struct usb_device *usb_dev;
 
 	mutex_lock(&agilent_82357a_hotplug_lock);
 
 	a_priv = board->private_data;
-	usb_dev = interface_to_usbdev(a_priv->bus_interface);
 	if (a_priv) {
 		if (a_priv->bus_interface) {
 			agilent_82357a_go_idle(board);
@@ -1456,40 +1442,41 @@ static void agilent_82357a_detach(gpib_board_t *board)
 		mutex_lock(&a_priv->bulk_alloc_lock);
 		mutex_lock(&a_priv->interrupt_alloc_lock);
 		agilent_82357a_cleanup_urbs(a_priv);
-		agilent_82357a_free_private(a_priv);
+		agilent_82357a_release_urbs(a_priv);
+		agilent_82357a_free_private(board);
 	}
-	dev_info(&usb_dev->dev, "%s: detached\n", __func__);
+	dev_info(board->gpib_dev, "%s: detached\n", __func__);
 	mutex_unlock(&agilent_82357a_hotplug_lock);
 }
 
-gpib_interface_t agilent_82357a_gpib_interface = {
-name: "agilent_82357a",
-attach : agilent_82357a_attach,
-detach : agilent_82357a_detach,
-read : agilent_82357a_read,
-write : agilent_82357a_write,
-command : agilent_82357a_command,
-take_control : agilent_82357a_take_control,
-go_to_standby : agilent_82357a_go_to_standby,
-request_system_control : agilent_82357a_request_system_control,
-interface_clear : agilent_82357a_interface_clear,
-remote_enable : agilent_82357a_remote_enable,
-enable_eos : agilent_82357a_enable_eos,
-disable_eos : agilent_82357a_disable_eos,
-parallel_poll : agilent_82357a_parallel_poll,
-parallel_poll_configure : agilent_82357a_parallel_poll_configure,
-parallel_poll_response : agilent_82357a_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : agilent_82357a_line_status,
-update_status : agilent_82357a_update_status,
-primary_address : agilent_82357a_primary_address,
-secondary_address : agilent_82357a_secondary_address,
-serial_poll_response : agilent_82357a_serial_poll_response,
-serial_poll_status : agilent_82357a_serial_poll_status,
-t1_delay : agilent_82357a_t1_delay,
-return_to_local : agilent_82357a_return_to_local,
-no_7_bit_eos : 1,
-skip_check_for_command_acceptors : 1
+static gpib_interface_t agilent_82357a_gpib_interface = {
+	.name = "agilent_82357a",
+	.attach = agilent_82357a_attach,
+	.detach = agilent_82357a_detach,
+	.read = agilent_82357a_read,
+	.write = agilent_82357a_write,
+	.command = agilent_82357a_command,
+	.take_control = agilent_82357a_take_control,
+	.go_to_standby = agilent_82357a_go_to_standby,
+	.request_system_control = agilent_82357a_request_system_control,
+	.interface_clear = agilent_82357a_interface_clear,
+	.remote_enable = agilent_82357a_remote_enable,
+	.enable_eos = agilent_82357a_enable_eos,
+	.disable_eos = agilent_82357a_disable_eos,
+	.parallel_poll = agilent_82357a_parallel_poll,
+	.parallel_poll_configure = agilent_82357a_parallel_poll_configure,
+	.parallel_poll_response = agilent_82357a_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = agilent_82357a_line_status,
+	.update_status = agilent_82357a_update_status,
+	.primary_address = agilent_82357a_primary_address,
+	.secondary_address = agilent_82357a_secondary_address,
+	.serial_poll_response = agilent_82357a_serial_poll_response,
+	.serial_poll_status = agilent_82357a_serial_poll_status,
+	.t1_delay = agilent_82357a_t1_delay,
+	.return_to_local = agilent_82357a_return_to_local,
+	.no_7_bit_eos = 1,
+	.skip_check_for_command_acceptors = 1
 };
 
 // Table with the USB-devices: just now only testing IDs
@@ -1691,12 +1678,24 @@ static struct usb_driver agilent_82357a_bus_driver = {
 static int __init agilent_82357a_init_module(void)
 {
 	int i;
+	int ret;
 
 	pr_info("agilent_82357a_gpib driver loading");
 	for (i = 0; i < MAX_NUM_82357A_INTERFACES; ++i)
 		agilent_82357a_driver_interfaces[i] = NULL;
-	usb_register(&agilent_82357a_bus_driver);
-	gpib_register_driver(&agilent_82357a_gpib_interface, THIS_MODULE);
+
+	ret = usb_register(&agilent_82357a_bus_driver);
+	if (ret) {
+		pr_err("agilent_82357a: usb_register failed: error = %d\n", ret);
+		return ret;
+	}
+
+	ret = gpib_register_driver(&agilent_82357a_gpib_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("agilent_82357a: gpib_register_driver failed: error = %d\n", ret);
+		usb_deregister(&agilent_82357a_bus_driver);
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/staging/gpib/cb7210/cb7210.c b/drivers/staging/gpib/cb7210/cb7210.c
index 59e41c97f518..4d22f647a453 100644
--- a/drivers/staging/gpib/cb7210/cb7210.c
+++ b/drivers/staging/gpib/cb7210/cb7210.c
@@ -683,170 +683,170 @@ void cb7210_return_to_local(gpib_board_t *board)
 	write_byte(nec_priv, AUX_RTL, AUXMR);
 }
 
-gpib_interface_t cb_pci_unaccel_interface = {
-name: "cbi_pci_unaccel",
-attach : cb_pci_attach,
-detach : cb_pci_detach,
-read : cb7210_read,
-write : cb7210_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_pci_unaccel_interface = {
+	.name = "cbi_pci_unaccel",
+	.attach = cb_pci_attach,
+	.detach = cb_pci_detach,
+	.read = cb7210_read,
+	.write = cb7210_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_pci_accel_interface = {
-name: "cbi_pci_accel",
-attach : cb_pci_attach,
-detach : cb_pci_detach,
-read : cb7210_accel_read,
-write : cb7210_accel_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_pci_accel_interface = {
+	.name = "cbi_pci_accel",
+	.attach = cb_pci_attach,
+	.detach = cb_pci_detach,
+	.read = cb7210_accel_read,
+	.write = cb7210_accel_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_pci_interface = {
-name: "cbi_pci",
-attach : cb_pci_attach,
-detach : cb_pci_detach,
-read : cb7210_accel_read,
-write : cb7210_accel_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_pci_interface = {
+	.name = "cbi_pci",
+	.attach = cb_pci_attach,
+	.detach = cb_pci_detach,
+	.read = cb7210_accel_read,
+	.write = cb7210_accel_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_isa_unaccel_interface = {
-name: "cbi_isa_unaccel",
-attach : cb_isa_attach,
-detach : cb_isa_detach,
-read : cb7210_read,
-write : cb7210_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_isa_unaccel_interface = {
+	.name = "cbi_isa_unaccel",
+	.attach = cb_isa_attach,
+	.detach = cb_isa_detach,
+	.read = cb7210_read,
+	.write = cb7210_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_isa_interface = {
-name: "cbi_isa",
-attach : cb_isa_attach,
-detach : cb_isa_detach,
-read : cb7210_accel_read,
-write : cb7210_accel_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_isa_interface = {
+	.name = "cbi_isa",
+	.attach = cb_isa_attach,
+	.detach = cb_isa_detach,
+	.read = cb7210_accel_read,
+	.write = cb7210_accel_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_isa_accel_interface = {
-name: "cbi_isa_accel",
-attach : cb_isa_attach,
-detach : cb_isa_detach,
-read : cb7210_accel_read,
-write : cb7210_accel_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_isa_accel_interface = {
+	.name = "cbi_isa_accel",
+	.attach = cb_isa_attach,
+	.detach = cb_isa_detach,
+	.read = cb7210_accel_read,
+	.write = cb7210_accel_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
 static int cb7210_allocate_private(gpib_board_t *board)
@@ -1040,8 +1040,8 @@ int cb_isa_attach(gpib_board_t *board, const gpib_board_config_t *config)
 		return retval;
 	cb_priv = board->private_data;
 	nec_priv = &cb_priv->nec7210_priv;
-	if (request_region(config->ibbase, cb7210_iosize, "cb7210") == 0) {
-		pr_err("gpib: ioports starting at 0x%u are already in use\n", config->ibbase);
+	if (!request_region(config->ibbase, cb7210_iosize, "cb7210")) {
+		pr_err("gpib: ioports starting at 0x%x are already in use\n", config->ibbase);
 		return -EIO;
 	}
 	nec_priv->iobase = config->ibbase;
@@ -1351,100 +1351,94 @@ static struct pcmcia_driver cb_gpib_cs_driver = {
 	.resume		= cb_gpib_resume,
 };
 
-int cb_pcmcia_init_module(void)
-{
-	pcmcia_register_driver(&cb_gpib_cs_driver);
-	return 0;
-}
-
 void cb_pcmcia_cleanup_module(void)
 {
 	DEBUG(0, "cb_gpib_cs: unloading\n");
 	pcmcia_unregister_driver(&cb_gpib_cs_driver);
 }
 
-gpib_interface_t cb_pcmcia_unaccel_interface = {
-name: "cbi_pcmcia_unaccel",
-attach : cb_pcmcia_attach,
-detach : cb_pcmcia_detach,
-read : cb7210_read,
-write : cb7210_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_pcmcia_unaccel_interface = {
+	.name = "cbi_pcmcia_unaccel",
+	.attach = cb_pcmcia_attach,
+	.detach = cb_pcmcia_detach,
+	.read = cb7210_read,
+	.write = cb7210_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_pcmcia_interface = {
-name: "cbi_pcmcia",
-attach : cb_pcmcia_attach,
-detach : cb_pcmcia_detach,
-read : cb7210_accel_read,
-write : cb7210_accel_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_pcmcia_interface = {
+	.name = "cbi_pcmcia",
+	.attach = cb_pcmcia_attach,
+	.detach = cb_pcmcia_detach,
+	.read = cb7210_accel_read,
+	.write = cb7210_accel_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
-gpib_interface_t cb_pcmcia_accel_interface = {
-name: "cbi_pcmcia_accel",
-attach : cb_pcmcia_attach,
-detach : cb_pcmcia_detach,
-read : cb7210_accel_read,
-write : cb7210_accel_write,
-command : cb7210_command,
-take_control : cb7210_take_control,
-go_to_standby : cb7210_go_to_standby,
-request_system_control : cb7210_request_system_control,
-interface_clear : cb7210_interface_clear,
-remote_enable : cb7210_remote_enable,
-enable_eos : cb7210_enable_eos,
-disable_eos : cb7210_disable_eos,
-parallel_poll : cb7210_parallel_poll,
-parallel_poll_configure : cb7210_parallel_poll_configure,
-parallel_poll_response : cb7210_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : cb7210_line_status,
-update_status : cb7210_update_status,
-primary_address : cb7210_primary_address,
-secondary_address : cb7210_secondary_address,
-serial_poll_response : cb7210_serial_poll_response,
-serial_poll_status : cb7210_serial_poll_status,
-t1_delay : cb7210_t1_delay,
-return_to_local : cb7210_return_to_local,
+static gpib_interface_t cb_pcmcia_accel_interface = {
+	.name = "cbi_pcmcia_accel",
+	.attach = cb_pcmcia_attach,
+	.detach = cb_pcmcia_detach,
+	.read = cb7210_accel_read,
+	.write = cb7210_accel_write,
+	.command = cb7210_command,
+	.take_control = cb7210_take_control,
+	.go_to_standby = cb7210_go_to_standby,
+	.request_system_control = cb7210_request_system_control,
+	.interface_clear = cb7210_interface_clear,
+	.remote_enable = cb7210_remote_enable,
+	.enable_eos = cb7210_enable_eos,
+	.disable_eos = cb7210_disable_eos,
+	.parallel_poll = cb7210_parallel_poll,
+	.parallel_poll_configure = cb7210_parallel_poll_configure,
+	.parallel_poll_response = cb7210_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = cb7210_line_status,
+	.update_status = cb7210_update_status,
+	.primary_address = cb7210_primary_address,
+	.secondary_address = cb7210_secondary_address,
+	.serial_poll_response = cb7210_serial_poll_response,
+	.serial_poll_status = cb7210_serial_poll_status,
+	.t1_delay = cb7210_t1_delay,
+	.return_to_local = cb7210_return_to_local,
 };
 
 int cb_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config)
@@ -1465,8 +1459,8 @@ int cb_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config)
 	cb_priv = board->private_data;
 	nec_priv = &cb_priv->nec7210_priv;
 
-	if (request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]),
-			   "cb7210") == 0)	{
+	if (!request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]),
+			    "cb7210"))	{
 		pr_err("gpib: ioports starting at 0x%lx are already in use\n",
 		       (unsigned long)curr_dev->resource[0]->start);
 		return -EIO;
@@ -1506,32 +1500,102 @@ void cb_pcmcia_detach(gpib_board_t *board)
 
 static int __init cb7210_init_module(void)
 {
-	int err = 0;
-	int result;
+	int ret;
+
+	ret = pci_register_driver(&cb7210_pci_driver);
+	if (ret) {
+		pr_err("cb7210: pci_register_driver failed: error = %d\n", ret);
+		return ret;
+	}
+
+	ret = gpib_register_driver(&cb_pci_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pci;
+	}
+
+	ret = gpib_register_driver(&cb_isa_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_isa;
+	}
 
-	result = pci_register_driver(&cb7210_pci_driver);
-	if (result) {
-		pr_err("cb7210: pci_driver_register failed!\n");
-		return result;
+	ret = gpib_register_driver(&cb_pci_accel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pci_accel;
 	}
 
-	gpib_register_driver(&cb_pci_interface, THIS_MODULE);
-	gpib_register_driver(&cb_isa_interface, THIS_MODULE);
-	gpib_register_driver(&cb_pci_accel_interface, THIS_MODULE);
-	gpib_register_driver(&cb_pci_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&cb_isa_accel_interface, THIS_MODULE);
-	gpib_register_driver(&cb_isa_unaccel_interface, THIS_MODULE);
-
-#ifdef GPIB__PCMCIA
-	gpib_register_driver(&cb_pcmcia_interface, THIS_MODULE);
-	gpib_register_driver(&cb_pcmcia_accel_interface, THIS_MODULE);
-	gpib_register_driver(&cb_pcmcia_unaccel_interface, THIS_MODULE);
-	err += cb_pcmcia_init_module();
+	ret = gpib_register_driver(&cb_pci_unaccel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pci_unaccel;
+	}
+
+	ret = gpib_register_driver(&cb_isa_accel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_isa_accel;
+	}
+
+	ret = gpib_register_driver(&cb_isa_unaccel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_isa_unaccel;
+	}
+
+#ifdef GPIB_PCMCIA
+	ret = gpib_register_driver(&cb_pcmcia_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia;
+	}
+
+	ret = gpib_register_driver(&cb_pcmcia_accel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia_accel;
+	}
+
+	ret = gpib_register_driver(&cb_pcmcia_unaccel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("cb7210: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia_unaccel;
+	}
+
+	ret = pcmcia_register_driver(&cb_gpib_cs_driver);
+	if (ret) {
+		pr_err("cb7210: pcmcia_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia_driver;
+	}
 #endif
-	if (err)
-		return -1;
 
 	return 0;
+
+#ifdef GPIB_PCMCIA
+err_pcmcia_driver:
+	gpib_unregister_driver(&cb_pcmcia_unaccel_interface);
+err_pcmcia_unaccel:
+	gpib_unregister_driver(&cb_pcmcia_accel_interface);
+err_pcmcia_accel:
+	gpib_unregister_driver(&cb_pcmcia_interface);
+err_pcmcia:
+#endif
+	gpib_unregister_driver(&cb_isa_unaccel_interface);
+err_isa_unaccel:
+	gpib_unregister_driver(&cb_isa_accel_interface);
+err_isa_accel:
+	gpib_unregister_driver(&cb_pci_unaccel_interface);
+err_pci_unaccel:
+	gpib_unregister_driver(&cb_pci_accel_interface);
+err_pci_accel:
+	gpib_unregister_driver(&cb_isa_interface);
+err_isa:
+	gpib_unregister_driver(&cb_pci_interface);
+err_pci:
+	pci_unregister_driver(&cb7210_pci_driver);
+
+	return ret;
 }
 
 static void __exit cb7210_exit_module(void)
diff --git a/drivers/staging/gpib/cb7210/cb7210.h b/drivers/staging/gpib/cb7210/cb7210.h
index c17cb22585f7..d56cd905cc8c 100644
--- a/drivers/staging/gpib/cb7210/cb7210.h
+++ b/drivers/staging/gpib/cb7210/cb7210.h
@@ -36,11 +36,6 @@ struct cb7210_priv {
 	unsigned in_fifo_half_full : 1;
 };
 
-// interfaces
-extern gpib_interface_t cb_pcmcia_interface;
-extern gpib_interface_t cb_pcmcia_accel_interface;
-extern gpib_interface_t cb_pcmcia_unaccel_interface;
-
 // interrupt service routines
 irqreturn_t cb_pci_interrupt(int irq, void *arg);
 irqreturn_t cb7210_interrupt(int irq, void *arg);
diff --git a/drivers/staging/gpib/cec/cec.h b/drivers/staging/gpib/cec/cec.h
index 352cf83d8328..040ca70ed708 100644
--- a/drivers/staging/gpib/cec/cec.h
+++ b/drivers/staging/gpib/cec/cec.h
@@ -16,10 +16,6 @@ struct cec_priv  {
 	unsigned int irq;
 };
 
-// interfaces
-extern gpib_interface_t cec_pci_interface;
-extern gpib_interface_t cec_pcmcia_interface;
-
 // interface functions
 int cec_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, size_t *bytes_read);
 int cec_write(gpib_board_t *board, uint8_t *buffer, size_t length, int send_eoi,
diff --git a/drivers/staging/gpib/cec/cec_gpib.c b/drivers/staging/gpib/cec/cec_gpib.c
index 9c00a874468c..d056cd1d6b3e 100644
--- a/drivers/staging/gpib/cec/cec_gpib.c
+++ b/drivers/staging/gpib/cec/cec_gpib.c
@@ -182,32 +182,32 @@ void cec_return_to_local(gpib_board_t *board)
 	nec7210_return_to_local(board, &priv->nec7210_priv);
 }
 
-gpib_interface_t cec_pci_interface = {
-name: "cec_pci",
-attach : cec_pci_attach,
-detach : cec_pci_detach,
-read : cec_read,
-write : cec_write,
-command : cec_command,
-take_control : cec_take_control,
-go_to_standby : cec_go_to_standby,
-request_system_control : cec_request_system_control,
-interface_clear : cec_interface_clear,
-remote_enable : cec_remote_enable,
-enable_eos : cec_enable_eos,
-disable_eos : cec_disable_eos,
-parallel_poll : cec_parallel_poll,
-parallel_poll_configure : cec_parallel_poll_configure,
-parallel_poll_response : cec_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : NULL,	//XXX
-update_status : cec_update_status,
-primary_address : cec_primary_address,
-secondary_address : cec_secondary_address,
-serial_poll_response : cec_serial_poll_response,
-serial_poll_status : cec_serial_poll_status,
-t1_delay : cec_t1_delay,
-return_to_local : cec_return_to_local,
+static gpib_interface_t cec_pci_interface = {
+	.name = "cec_pci",
+	.attach = cec_pci_attach,
+	.detach = cec_pci_detach,
+	.read = cec_read,
+	.write = cec_write,
+	.command = cec_command,
+	.take_control = cec_take_control,
+	.go_to_standby = cec_go_to_standby,
+	.request_system_control = cec_request_system_control,
+	.interface_clear = cec_interface_clear,
+	.remote_enable = cec_remote_enable,
+	.enable_eos = cec_enable_eos,
+	.disable_eos = cec_disable_eos,
+	.parallel_poll = cec_parallel_poll,
+	.parallel_poll_configure = cec_parallel_poll_configure,
+	.parallel_poll_response = cec_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = NULL,	//XXX
+	.update_status = cec_update_status,
+	.primary_address = cec_primary_address,
+	.secondary_address = cec_secondary_address,
+	.serial_poll_response = cec_serial_poll_response,
+	.serial_poll_status = cec_serial_poll_status,
+	.t1_delay = cec_t1_delay,
+	.return_to_local = cec_return_to_local,
 };
 
 static int cec_allocate_private(gpib_board_t *board)
@@ -365,11 +365,15 @@ static int __init cec_init_module(void)
 
 	result = pci_register_driver(&cec_pci_driver);
 	if (result) {
-		pr_err("cec_gpib: pci_driver_register failed!\n");
+		pr_err("cec_gpib: pci_register_driver failed: error = %d\n", result);
 		return result;
 	}
 
-	gpib_register_driver(&cec_pci_interface, THIS_MODULE);
+	result = gpib_register_driver(&cec_pci_interface, THIS_MODULE);
+	if (result) {
+		pr_err("cec_gpib: gpib_register_driver failed: error = %d\n", result);
+		return result;
+	}
 
 	return 0;
 }
diff --git a/drivers/staging/gpib/common/gpib_os.c b/drivers/staging/gpib/common/gpib_os.c
index 0962729d7dfe..4901e660242e 100644
--- a/drivers/staging/gpib/common/gpib_os.c
+++ b/drivers/staging/gpib/common/gpib_os.c
@@ -835,7 +835,7 @@ static int board_type_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 		return -EBUSY;
 	}
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(board_type_ioctl_t));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(board_type_ioctl_t));
 	if (retval)
 		return retval;
 
@@ -879,7 +879,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 		      unsigned long arg)
 {
 	read_write_ioctl_t read_cmd;
-	u8 *userbuf;
+	u8 __user *userbuf;
 	unsigned long remain;
 	int end_flag = 0;
 	int retval;
@@ -887,7 +887,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	gpib_descriptor_t *desc;
 	size_t nbytes;
 
-	retval = copy_from_user(&read_cmd, (void *)arg, sizeof(read_cmd));
+	retval = copy_from_user(&read_cmd, (void __user *)arg, sizeof(read_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -901,7 +901,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	if (WARN_ON_ONCE(sizeof(userbuf) > sizeof(read_cmd.buffer_ptr)))
 		return -EFAULT;
 
-	userbuf = (u8 *)(unsigned long)read_cmd.buffer_ptr;
+	userbuf = (u8 __user *)(unsigned long)read_cmd.buffer_ptr;
 	userbuf += read_cmd.completed_transfer_count;
 
 	remain = read_cmd.requested_transfer_count - read_cmd.completed_transfer_count;
@@ -939,7 +939,7 @@ static int read_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	if (remain == 0 || end_flag)
 		read_ret = 0;
 	if (retval == 0)
-		retval = copy_to_user((void *)arg, &read_cmd, sizeof(read_cmd));
+		retval = copy_to_user((void __user *)arg, &read_cmd, sizeof(read_cmd));
 
 	atomic_set(&desc->io_in_progress, 0);
 
@@ -954,7 +954,7 @@ static int command_ioctl(gpib_file_private_t *file_priv,
 			 gpib_board_t *board, unsigned long arg)
 {
 	read_write_ioctl_t cmd;
-	u8 *userbuf;
+	u8 __user *userbuf;
 	unsigned long remain;
 	int retval;
 	int fault = 0;
@@ -962,7 +962,7 @@ static int command_ioctl(gpib_file_private_t *file_priv,
 	size_t bytes_written;
 	int no_clear_io_in_prog;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -973,7 +973,7 @@ static int command_ioctl(gpib_file_private_t *file_priv,
 	if (!desc)
 		return -EINVAL;
 
-	userbuf = (u8 *)(unsigned long)cmd.buffer_ptr;
+	userbuf = (u8 __user *)(unsigned long)cmd.buffer_ptr;
 	userbuf += cmd.completed_transfer_count;
 
 	no_clear_io_in_prog = cmd.end;
@@ -1016,7 +1016,7 @@ static int command_ioctl(gpib_file_private_t *file_priv,
 	cmd.completed_transfer_count = cmd.requested_transfer_count - remain;
 
 	if (fault == 0)
-		fault = copy_to_user((void *)arg, &cmd, sizeof(cmd));
+		fault = copy_to_user((void __user *)arg, &cmd, sizeof(cmd));
 
 	/*
 	 * no_clear_io_in_prog (cmd.end) is true when io_in_progress should
@@ -1038,13 +1038,13 @@ static int write_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 		       unsigned long arg)
 {
 	read_write_ioctl_t write_cmd;
-	u8 *userbuf;
+	u8 __user *userbuf;
 	unsigned long remain;
 	int retval = 0;
 	int fault;
 	gpib_descriptor_t *desc;
 
-	fault = copy_from_user(&write_cmd, (void *)arg, sizeof(write_cmd));
+	fault = copy_from_user(&write_cmd, (void __user *)arg, sizeof(write_cmd));
 	if (fault)
 		return -EFAULT;
 
@@ -1055,7 +1055,7 @@ static int write_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	if (!desc)
 		return -EINVAL;
 
-	userbuf = (u8 *)(unsigned long)write_cmd.buffer_ptr;
+	userbuf = (u8 __user *)(unsigned long)write_cmd.buffer_ptr;
 	userbuf += write_cmd.completed_transfer_count;
 
 	remain = write_cmd.requested_transfer_count - write_cmd.completed_transfer_count;
@@ -1094,7 +1094,7 @@ static int write_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	if (remain == 0)
 		retval = 0;
 	if (fault == 0)
-		fault = copy_to_user((void *)arg, &write_cmd, sizeof(write_cmd));
+		fault = copy_to_user((void __user *)arg, &write_cmd, sizeof(write_cmd));
 
 	atomic_set(&desc->io_in_progress, 0);
 
@@ -1111,7 +1111,7 @@ static int status_bytes_ioctl(gpib_board_t *board, unsigned long arg)
 	spoll_bytes_ioctl_t cmd;
 	int retval;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1121,7 +1121,7 @@ static int status_bytes_ioctl(gpib_board_t *board, unsigned long arg)
 	else
 		cmd.num_bytes = num_status_bytes(device);
 
-	retval = copy_to_user((void *)arg, &cmd, sizeof(cmd));
+	retval = copy_to_user((void __user *)arg, &cmd, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1231,7 +1231,7 @@ static int open_dev_ioctl(struct file *filep, gpib_board_t *board, unsigned long
 	gpib_file_private_t *file_priv = filep->private_data;
 	int i;
 
-	retval = copy_from_user(&open_dev_cmd, (void *)arg, sizeof(open_dev_cmd));
+	retval = copy_from_user(&open_dev_cmd, (void __user *)arg, sizeof(open_dev_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1267,7 +1267,7 @@ static int open_dev_ioctl(struct file *filep, gpib_board_t *board, unsigned long
 	atomic_set(&board->stuck_srq, 0);
 
 	open_dev_cmd.handle = i;
-	retval = copy_to_user((void *)arg, &open_dev_cmd, sizeof(open_dev_cmd));
+	retval = copy_to_user((void __user *)arg, &open_dev_cmd, sizeof(open_dev_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1280,7 +1280,7 @@ static int close_dev_ioctl(struct file *filep, gpib_board_t *board, unsigned lon
 	gpib_file_private_t *file_priv = filep->private_data;
 	int retval;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1308,7 +1308,7 @@ static int serial_poll_ioctl(gpib_board_t *board, unsigned long arg)
 
 	dev_dbg(board->gpib_dev, "pid %i, entering %s()\n", current->pid, __func__);
 
-	retval = copy_from_user(&serial_cmd, (void *)arg, sizeof(serial_cmd));
+	retval = copy_from_user(&serial_cmd, (void __user *)arg, sizeof(serial_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1317,7 +1317,7 @@ static int serial_poll_ioctl(gpib_board_t *board, unsigned long arg)
 	if (retval < 0)
 		return retval;
 
-	retval = copy_to_user((void *)arg, &serial_cmd, sizeof(serial_cmd));
+	retval = copy_to_user((void __user *)arg, &serial_cmd, sizeof(serial_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1331,7 +1331,7 @@ static int wait_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	int retval;
 	gpib_descriptor_t *desc;
 
-	retval = copy_from_user(&wait_cmd, (void *)arg, sizeof(wait_cmd));
+	retval = copy_from_user(&wait_cmd, (void __user *)arg, sizeof(wait_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1344,7 +1344,7 @@ static int wait_ioctl(gpib_file_private_t *file_priv, gpib_board_t *board,
 	if (retval < 0)
 		return retval;
 
-	retval = copy_to_user((void *)arg, &wait_cmd, sizeof(wait_cmd));
+	retval = copy_to_user((void __user *)arg, &wait_cmd, sizeof(wait_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1360,7 +1360,7 @@ static int parallel_poll_ioctl(gpib_board_t *board, unsigned long arg)
 	if (retval < 0)
 		return retval;
 
-	retval = copy_to_user((void *)arg, &poll_byte, sizeof(poll_byte));
+	retval = copy_to_user((void __user *)arg, &poll_byte, sizeof(poll_byte));
 	if (retval)
 		return -EFAULT;
 
@@ -1371,14 +1371,14 @@ static int online_ioctl(gpib_board_t *board, unsigned long arg)
 {
 	online_ioctl_t online_cmd;
 	int retval;
-	void *init_data = NULL;
+	void __user *init_data = NULL;
 
 	board->config.init_data = NULL;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	retval = copy_from_user(&online_cmd, (void *)arg, sizeof(online_cmd));
+	retval = copy_from_user(&online_cmd, (void __user *)arg, sizeof(online_cmd));
 	if (retval)
 		return -EFAULT;
 	if (online_cmd.init_data_length > 0) {
@@ -1387,7 +1387,7 @@ static int online_ioctl(gpib_board_t *board, unsigned long arg)
 			return -ENOMEM;
 		if (WARN_ON_ONCE(sizeof(init_data) > sizeof(online_cmd.init_data_ptr)))
 			return -EFAULT;
-		init_data = (void *)(unsigned long)(online_cmd.init_data_ptr);
+		init_data = (void __user *)(unsigned long)(online_cmd.init_data_ptr);
 		retval = copy_from_user(board->config.init_data, init_data,
 					online_cmd.init_data_length);
 		if (retval) {
@@ -1416,7 +1416,7 @@ static int remote_enable_ioctl(gpib_board_t *board, unsigned long arg)
 	int enable;
 	int retval;
 
-	retval = copy_from_user(&enable, (void *)arg, sizeof(enable));
+	retval = copy_from_user(&enable, (void __user *)arg, sizeof(enable));
 	if (retval)
 		return -EFAULT;
 
@@ -1428,7 +1428,7 @@ static int take_control_ioctl(gpib_board_t *board, unsigned long arg)
 	int synchronous;
 	int retval;
 
-	retval = copy_from_user(&synchronous, (void *)arg, sizeof(synchronous));
+	retval = copy_from_user(&synchronous, (void __user *)arg, sizeof(synchronous));
 	if (retval)
 		return -EFAULT;
 
@@ -1444,7 +1444,7 @@ static int line_status_ioctl(gpib_board_t *board, unsigned long arg)
 	if (retval < 0)
 		return retval;
 
-	retval = copy_to_user((void *)arg, &lines, sizeof(lines));
+	retval = copy_to_user((void __user *)arg, &lines, sizeof(lines));
 	if (retval)
 		return -EFAULT;
 
@@ -1458,7 +1458,7 @@ static int pad_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv,
 	int retval;
 	gpib_descriptor_t *desc;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1494,7 +1494,7 @@ static int sad_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv,
 	int retval;
 	gpib_descriptor_t *desc;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1527,7 +1527,7 @@ static int eos_ioctl(gpib_board_t *board, unsigned long arg)
 	eos_ioctl_t eos_cmd;
 	int retval;
 
-	retval = copy_from_user(&eos_cmd, (void *)arg, sizeof(eos_cmd));
+	retval = copy_from_user(&eos_cmd, (void __user *)arg, sizeof(eos_cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1539,7 +1539,7 @@ static int request_service_ioctl(gpib_board_t *board, unsigned long arg)
 	u8 status_byte;
 	int retval;
 
-	retval = copy_from_user(&status_byte, (void *)arg, sizeof(status_byte));
+	retval = copy_from_user(&status_byte, (void __user *)arg, sizeof(status_byte));
 	if (retval)
 		return -EFAULT;
 
@@ -1551,7 +1551,8 @@ static int request_service2_ioctl(gpib_board_t *board, unsigned long arg)
 	request_service2_t request_service2_cmd;
 	int retval;
 
-	retval = copy_from_user(&request_service2_cmd, (void *)arg, sizeof(request_service2_t));
+	retval = copy_from_user(&request_service2_cmd, (void __user *)arg,
+				sizeof(request_service2_t));
 	if (retval)
 		return -EFAULT;
 
@@ -1567,7 +1568,7 @@ static int iobase_ioctl(gpib_board_config_t *config, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	retval = copy_from_user(&base_addr, (void *)arg, sizeof(base_addr));
+	retval = copy_from_user(&base_addr, (void __user *)arg, sizeof(base_addr));
 	if (retval)
 		return -EFAULT;
 
@@ -1586,7 +1587,7 @@ static int irq_ioctl(gpib_board_config_t *config, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	retval = copy_from_user(&irq, (void *)arg, sizeof(irq));
+	retval = copy_from_user(&irq, (void __user *)arg, sizeof(irq));
 	if (retval)
 		return -EFAULT;
 
@@ -1603,7 +1604,7 @@ static int dma_ioctl(gpib_board_config_t *config, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	retval = copy_from_user(&dma_channel, (void *)arg, sizeof(dma_channel));
+	retval = copy_from_user(&dma_channel, (void __user *)arg, sizeof(dma_channel));
 	if (retval)
 		return -EFAULT;
 
@@ -1619,7 +1620,7 @@ static int autospoll_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv,
 	int retval;
 	gpib_descriptor_t *desc;
 
-	retval = copy_from_user(&enable, (void *)arg, sizeof(enable));
+	retval = copy_from_user(&enable, (void __user *)arg, sizeof(enable));
 	if (retval)
 		return -EFAULT;
 
@@ -1654,7 +1655,7 @@ static int mutex_ioctl(gpib_board_t *board, gpib_file_private_t *file_priv,
 {
 	int retval, lock_mutex;
 
-	retval = copy_from_user(&lock_mutex, (void *)arg, sizeof(lock_mutex));
+	retval = copy_from_user(&lock_mutex, (void __user *)arg, sizeof(lock_mutex));
 	if (retval)
 		return -EFAULT;
 
@@ -1698,7 +1699,7 @@ static int timeout_ioctl(gpib_board_t *board, unsigned long arg)
 	unsigned int timeout;
 	int retval;
 
-	retval = copy_from_user(&timeout, (void *)arg, sizeof(timeout));
+	retval = copy_from_user(&timeout, (void __user *)arg, sizeof(timeout));
 	if (retval)
 		return -EFAULT;
 
@@ -1713,7 +1714,7 @@ static int ppc_ioctl(gpib_board_t *board, unsigned long arg)
 	ppoll_config_ioctl_t cmd;
 	int retval;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1739,7 +1740,7 @@ static int set_local_ppoll_mode_ioctl(gpib_board_t *board, unsigned long arg)
 	local_ppoll_mode_ioctl_t cmd;
 	int retval;
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1759,7 +1760,7 @@ static int get_local_ppoll_mode_ioctl(gpib_board_t *board, unsigned long arg)
 	int retval;
 
 	cmd = board->local_ppoll_mode;
-	retval = copy_to_user((void *)arg, &cmd, sizeof(cmd));
+	retval = copy_to_user((void __user *)arg, &cmd, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -1773,7 +1774,7 @@ static int query_board_rsv_ioctl(gpib_board_t *board, unsigned long arg)
 
 	status = board->interface->serial_poll_status(board);
 
-	retval = copy_to_user((void *)arg, &status, sizeof(status));
+	retval = copy_to_user((void __user *)arg, &status, sizeof(status));
 	if (retval)
 		return -EFAULT;
 
@@ -1796,7 +1797,7 @@ static int board_info_ioctl(const gpib_board_t *board, unsigned long arg)
 	info.t1_delay = board->t1_nano_sec;
 	info.ist = board->ist;
 	info.no_7_bit_eos = board->interface->no_7_bit_eos;
-	retval = copy_to_user((void *)arg, &info, sizeof(info));
+	retval = copy_to_user((void __user *)arg, &info, sizeof(info));
 	if (retval)
 		return -EFAULT;
 
@@ -1808,7 +1809,7 @@ static int interface_clear_ioctl(gpib_board_t *board, unsigned long arg)
 	unsigned int usec_duration;
 	int retval;
 
-	retval = copy_from_user(&usec_duration, (void *)arg, sizeof(usec_duration));
+	retval = copy_from_user(&usec_duration, (void __user *)arg, sizeof(usec_duration));
 	if (retval)
 		return -EFAULT;
 
@@ -1823,7 +1824,7 @@ static int select_pci_ioctl(gpib_board_config_t *config, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	retval = copy_from_user(&selection, (void *)arg, sizeof(selection));
+	retval = copy_from_user(&selection, (void __user *)arg, sizeof(selection));
 	if (retval)
 		return -EFAULT;
 
@@ -1845,7 +1846,7 @@ static int select_device_path_ioctl(gpib_board_config_t *config, unsigned long a
 	if (!selection)
 		return -ENOMEM;
 
-	retval = copy_from_user(selection, (void *)arg, sizeof(select_device_path_ioctl_t));
+	retval = copy_from_user(selection, (void __user *)arg, sizeof(select_device_path_ioctl_t));
 	if (retval) {
 		vfree(selection);
 		return -EFAULT;
@@ -1979,7 +1980,7 @@ static int event_ioctl(gpib_board_t *board, unsigned long arg)
 
 	user_event = event;
 
-	retval = copy_to_user((void *)arg, &user_event, sizeof(user_event));
+	retval = copy_to_user((void __user *)arg, &user_event, sizeof(user_event));
 	if (retval)
 		return -EFAULT;
 
@@ -1991,7 +1992,7 @@ static int request_system_control_ioctl(gpib_board_t *board, unsigned long arg)
 	rsc_ioctl_t request_control;
 	int retval;
 
-	retval = copy_from_user(&request_control, (void *)arg, sizeof(request_control));
+	retval = copy_from_user(&request_control, (void __user *)arg, sizeof(request_control));
 	if (retval)
 		return -EFAULT;
 
@@ -2011,7 +2012,7 @@ static int t1_delay_ioctl(gpib_board_t *board, unsigned long arg)
 		return -EIO;
 	}
 
-	retval = copy_from_user(&cmd, (void *)arg, sizeof(cmd));
+	retval = copy_from_user(&cmd, (void __user *)arg, sizeof(cmd));
 	if (retval)
 		return -EFAULT;
 
@@ -2022,13 +2023,13 @@ static int t1_delay_ioctl(gpib_board_t *board, unsigned long arg)
 	return 0;
 }
 
-const struct file_operations ib_fops = {
-owner: THIS_MODULE,
-llseek : NULL,
-unlocked_ioctl : &ibioctl,
-compat_ioctl : &ibioctl,
-open : &ibopen,
-release : &ibclose,
+static const struct file_operations ib_fops = {
+	.owner = THIS_MODULE,
+	.llseek = NULL,
+	.unlocked_ioctl = &ibioctl,
+	.compat_ioctl = &ibioctl,
+	.open = &ibopen,
+	.release = &ibclose,
 };
 
 gpib_board_t board_array[GPIB_MAX_NUM_BOARDS];
@@ -2044,18 +2045,19 @@ void init_gpib_descriptor(gpib_descriptor_t *desc)
 	atomic_set(&desc->io_in_progress, 0);
 }
 
-void gpib_register_driver(gpib_interface_t *interface, struct module *provider_module)
+int gpib_register_driver(gpib_interface_t *interface, struct module *provider_module)
 {
 	struct gpib_interface_list_struct *entry;
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
-		return;
+		return -ENOMEM;
 
 	entry->interface = interface;
 	entry->module = provider_module;
 	list_add(&entry->list, &registered_drivers);
-	pr_info("gpib: registered %s interface\n", interface->name);
+
+	return 0;
 }
 EXPORT_SYMBOL(gpib_register_driver);
 
@@ -2195,7 +2197,7 @@ static int __init gpib_common_init_module(void)
 		return PTR_ERR(gpib_class);
 	}
 	for (i = 0; i < GPIB_MAX_NUM_BOARDS; ++i)
-		board_array[i].gpib_dev = device_create(gpib_class, 0,
+		board_array[i].gpib_dev = device_create(gpib_class, NULL,
 							MKDEV(GPIB_CODE, i), NULL, "gpib%i", i);
 
 	return 0;
diff --git a/drivers/staging/gpib/common/iblib.c b/drivers/staging/gpib/common/iblib.c
index db1911cc1b26..5f6fa135f505 100644
--- a/drivers/staging/gpib/common/iblib.c
+++ b/drivers/staging/gpib/common/iblib.c
@@ -695,7 +695,7 @@ int ibwait(gpib_board_t *board, int wait_mask, int clear_mask, int set_mask,
 
 	/* make sure we only clear status bits that we are reporting */
 	if (*status & clear_mask || set_mask)
-		general_ibstatus(board, status_queue, *status & clear_mask, set_mask, 0);
+		general_ibstatus(board, status_queue, *status & clear_mask, set_mask, NULL);
 
 	return 0;
 }
diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.c b/drivers/staging/gpib/eastwood/fluke_gpib.c
index 5e59d38beb35..0304c5de4ccd 100644
--- a/drivers/staging/gpib/eastwood/fluke_gpib.c
+++ b/drivers/staging/gpib/eastwood/fluke_gpib.c
@@ -720,31 +720,31 @@ static int fluke_accel_read(gpib_board_t *board, uint8_t *buffer, size_t length,
 	return retval;
 }
 
-gpib_interface_t fluke_unaccel_interface = {
-name: "fluke_unaccel",
-attach : fluke_attach_holdoff_all,
-detach : fluke_detach,
-read : fluke_read,
-write : fluke_write,
-command : fluke_command,
-take_control : fluke_take_control,
-go_to_standby : fluke_go_to_standby,
-request_system_control : fluke_request_system_control,
-interface_clear : fluke_interface_clear,
-remote_enable : fluke_remote_enable,
-enable_eos : fluke_enable_eos,
-disable_eos : fluke_disable_eos,
-parallel_poll : fluke_parallel_poll,
-parallel_poll_configure : fluke_parallel_poll_configure,
-parallel_poll_response : fluke_parallel_poll_response,
-line_status : fluke_line_status,
-update_status : fluke_update_status,
-primary_address : fluke_primary_address,
-secondary_address : fluke_secondary_address,
-serial_poll_response : fluke_serial_poll_response,
-serial_poll_status : fluke_serial_poll_status,
-t1_delay : fluke_t1_delay,
-return_to_local : fluke_return_to_local,
+static gpib_interface_t fluke_unaccel_interface = {
+	.name = "fluke_unaccel",
+	.attach = fluke_attach_holdoff_all,
+	.detach = fluke_detach,
+	.read = fluke_read,
+	.write = fluke_write,
+	.command = fluke_command,
+	.take_control = fluke_take_control,
+	.go_to_standby = fluke_go_to_standby,
+	.request_system_control = fluke_request_system_control,
+	.interface_clear = fluke_interface_clear,
+	.remote_enable = fluke_remote_enable,
+	.enable_eos = fluke_enable_eos,
+	.disable_eos = fluke_disable_eos,
+	.parallel_poll = fluke_parallel_poll,
+	.parallel_poll_configure = fluke_parallel_poll_configure,
+	.parallel_poll_response = fluke_parallel_poll_response,
+	.line_status = fluke_line_status,
+	.update_status = fluke_update_status,
+	.primary_address = fluke_primary_address,
+	.secondary_address = fluke_secondary_address,
+	.serial_poll_response = fluke_serial_poll_response,
+	.serial_poll_status = fluke_serial_poll_status,
+	.t1_delay = fluke_t1_delay,
+	.return_to_local = fluke_return_to_local,
 };
 
 /* fluke_hybrid uses dma for writes but not for reads.  Added
@@ -755,58 +755,58 @@ return_to_local : fluke_return_to_local,
  * register just as the dma controller is also doing a read.
  */
 
-gpib_interface_t fluke_hybrid_interface = {
-name: "fluke_hybrid",
-attach : fluke_attach_holdoff_all,
-detach : fluke_detach,
-read : fluke_read,
-write : fluke_accel_write,
-command : fluke_command,
-take_control : fluke_take_control,
-go_to_standby : fluke_go_to_standby,
-request_system_control : fluke_request_system_control,
-interface_clear : fluke_interface_clear,
-remote_enable : fluke_remote_enable,
-enable_eos : fluke_enable_eos,
-disable_eos : fluke_disable_eos,
-parallel_poll : fluke_parallel_poll,
-parallel_poll_configure : fluke_parallel_poll_configure,
-parallel_poll_response : fluke_parallel_poll_response,
-line_status : fluke_line_status,
-update_status : fluke_update_status,
-primary_address : fluke_primary_address,
-secondary_address : fluke_secondary_address,
-serial_poll_response : fluke_serial_poll_response,
-serial_poll_status : fluke_serial_poll_status,
-t1_delay : fluke_t1_delay,
-return_to_local : fluke_return_to_local,
+static gpib_interface_t fluke_hybrid_interface = {
+	.name = "fluke_hybrid",
+	.attach = fluke_attach_holdoff_all,
+	.detach = fluke_detach,
+	.read = fluke_read,
+	.write = fluke_accel_write,
+	.command = fluke_command,
+	.take_control = fluke_take_control,
+	.go_to_standby = fluke_go_to_standby,
+	.request_system_control = fluke_request_system_control,
+	.interface_clear = fluke_interface_clear,
+	.remote_enable = fluke_remote_enable,
+	.enable_eos = fluke_enable_eos,
+	.disable_eos = fluke_disable_eos,
+	.parallel_poll = fluke_parallel_poll,
+	.parallel_poll_configure = fluke_parallel_poll_configure,
+	.parallel_poll_response = fluke_parallel_poll_response,
+	.line_status = fluke_line_status,
+	.update_status = fluke_update_status,
+	.primary_address = fluke_primary_address,
+	.secondary_address = fluke_secondary_address,
+	.serial_poll_response = fluke_serial_poll_response,
+	.serial_poll_status = fluke_serial_poll_status,
+	.t1_delay = fluke_t1_delay,
+	.return_to_local = fluke_return_to_local,
 };
 
-gpib_interface_t fluke_interface = {
-name: "fluke",
-attach : fluke_attach_holdoff_end,
-detach : fluke_detach,
-read : fluke_accel_read,
-write : fluke_accel_write,
-command : fluke_command,
-take_control : fluke_take_control,
-go_to_standby : fluke_go_to_standby,
-request_system_control : fluke_request_system_control,
-interface_clear : fluke_interface_clear,
-remote_enable : fluke_remote_enable,
-enable_eos : fluke_enable_eos,
-disable_eos : fluke_disable_eos,
-parallel_poll : fluke_parallel_poll,
-parallel_poll_configure : fluke_parallel_poll_configure,
-parallel_poll_response : fluke_parallel_poll_response,
-line_status : fluke_line_status,
-update_status : fluke_update_status,
-primary_address : fluke_primary_address,
-secondary_address : fluke_secondary_address,
-serial_poll_response : fluke_serial_poll_response,
-serial_poll_status : fluke_serial_poll_status,
-t1_delay : fluke_t1_delay,
-return_to_local : fluke_return_to_local,
+static gpib_interface_t fluke_interface = {
+	.name = "fluke",
+	.attach = fluke_attach_holdoff_end,
+	.detach = fluke_detach,
+	.read = fluke_accel_read,
+	.write = fluke_accel_write,
+	.command = fluke_command,
+	.take_control = fluke_take_control,
+	.go_to_standby = fluke_go_to_standby,
+	.request_system_control = fluke_request_system_control,
+	.interface_clear = fluke_interface_clear,
+	.remote_enable = fluke_remote_enable,
+	.enable_eos = fluke_enable_eos,
+	.disable_eos = fluke_disable_eos,
+	.parallel_poll = fluke_parallel_poll,
+	.parallel_poll_configure = fluke_parallel_poll_configure,
+	.parallel_poll_response = fluke_parallel_poll_response,
+	.line_status = fluke_line_status,
+	.update_status = fluke_update_status,
+	.primary_address = fluke_primary_address,
+	.secondary_address = fluke_secondary_address,
+	.serial_poll_response = fluke_serial_poll_response,
+	.serial_poll_status = fluke_serial_poll_status,
+	.t1_delay = fluke_t1_delay,
+	.return_to_local = fluke_return_to_local,
 };
 
 irqreturn_t fluke_gpib_internal_interrupt(gpib_board_t *board)
@@ -1155,16 +1155,38 @@ static int __init fluke_init_module(void)
 
 	result = platform_driver_register(&fluke_gpib_platform_driver);
 	if (result) {
-		pr_err("fluke_gpib: platform_driver_register failed!\n");
+		pr_err("fluke_gpib: platform_driver_register failed: error = %d\n", result);
 		return result;
 	}
 
-	gpib_register_driver(&fluke_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&fluke_hybrid_interface, THIS_MODULE);
-	gpib_register_driver(&fluke_interface, THIS_MODULE);
+	result = gpib_register_driver(&fluke_unaccel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fluke_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_unaccel;
+	}
+
+	result = gpib_register_driver(&fluke_hybrid_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fluke_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_hybrid;
+	}
+
+	result = gpib_register_driver(&fluke_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fluke_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_interface;
+	}
 
-	pr_info("fluke_gpib\n");
 	return 0;
+
+err_interface:
+	gpib_unregister_driver(&fluke_hybrid_interface);
+err_hybrid:
+	gpib_unregister_driver(&fluke_unaccel_interface);
+err_unaccel:
+	platform_driver_unregister(&fluke_gpib_platform_driver);
+
+	return result;
 }
 
 static void __exit fluke_exit_module(void)
diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.h b/drivers/staging/gpib/eastwood/fluke_gpib.h
index 4e2144d45270..3e4348196b42 100644
--- a/drivers/staging/gpib/eastwood/fluke_gpib.h
+++ b/drivers/staging/gpib/eastwood/fluke_gpib.h
@@ -21,7 +21,7 @@ struct fluke_priv {
 	struct dma_chan *dma_channel;
 	u8 *dma_buffer;
 	int dma_buffer_size;
-	void *write_transfer_counter;
+	void __iomem *write_transfer_counter;
 };
 
 // cb7210 specific registers and bits
diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c
index 0662b20a45e7..f950e7cdd8f8 100644
--- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c
+++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c
@@ -1040,116 +1040,116 @@ static int fmh_gpib_fifo_read(gpib_board_t *board, uint8_t *buffer, size_t lengt
 	return retval;
 }
 
-gpib_interface_t fmh_gpib_unaccel_interface = {
-name: "fmh_gpib_unaccel",
-attach : fmh_gpib_attach_holdoff_all,
-detach : fmh_gpib_detach,
-read : fmh_gpib_read,
-write : fmh_gpib_write,
-command : fmh_gpib_command,
-take_control : fmh_gpib_take_control,
-go_to_standby : fmh_gpib_go_to_standby,
-request_system_control : fmh_gpib_request_system_control,
-interface_clear : fmh_gpib_interface_clear,
-remote_enable : fmh_gpib_remote_enable,
-enable_eos : fmh_gpib_enable_eos,
-disable_eos : fmh_gpib_disable_eos,
-parallel_poll : fmh_gpib_parallel_poll,
-parallel_poll_configure : fmh_gpib_parallel_poll_configure,
-parallel_poll_response : fmh_gpib_parallel_poll_response,
-local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode,
-line_status : fmh_gpib_line_status,
-update_status : fmh_gpib_update_status,
-primary_address : fmh_gpib_primary_address,
-secondary_address : fmh_gpib_secondary_address,
-serial_poll_response2 : fmh_gpib_serial_poll_response2,
-serial_poll_status : fmh_gpib_serial_poll_status,
-t1_delay : fmh_gpib_t1_delay,
-return_to_local : fmh_gpib_return_to_local,
+static gpib_interface_t fmh_gpib_unaccel_interface = {
+	.name = "fmh_gpib_unaccel",
+	.attach = fmh_gpib_attach_holdoff_all,
+	.detach = fmh_gpib_detach,
+	.read = fmh_gpib_read,
+	.write = fmh_gpib_write,
+	.command = fmh_gpib_command,
+	.take_control = fmh_gpib_take_control,
+	.go_to_standby = fmh_gpib_go_to_standby,
+	.request_system_control = fmh_gpib_request_system_control,
+	.interface_clear = fmh_gpib_interface_clear,
+	.remote_enable = fmh_gpib_remote_enable,
+	.enable_eos = fmh_gpib_enable_eos,
+	.disable_eos = fmh_gpib_disable_eos,
+	.parallel_poll = fmh_gpib_parallel_poll,
+	.parallel_poll_configure = fmh_gpib_parallel_poll_configure,
+	.parallel_poll_response = fmh_gpib_parallel_poll_response,
+	.local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode,
+	.line_status = fmh_gpib_line_status,
+	.update_status = fmh_gpib_update_status,
+	.primary_address = fmh_gpib_primary_address,
+	.secondary_address = fmh_gpib_secondary_address,
+	.serial_poll_response2 = fmh_gpib_serial_poll_response2,
+	.serial_poll_status = fmh_gpib_serial_poll_status,
+	.t1_delay = fmh_gpib_t1_delay,
+	.return_to_local = fmh_gpib_return_to_local,
 };
 
-gpib_interface_t fmh_gpib_interface = {
-name: "fmh_gpib",
-attach : fmh_gpib_attach_holdoff_end,
-detach : fmh_gpib_detach,
-read : fmh_gpib_accel_read,
-write : fmh_gpib_accel_write,
-command : fmh_gpib_command,
-take_control : fmh_gpib_take_control,
-go_to_standby : fmh_gpib_go_to_standby,
-request_system_control : fmh_gpib_request_system_control,
-interface_clear : fmh_gpib_interface_clear,
-remote_enable : fmh_gpib_remote_enable,
-enable_eos : fmh_gpib_enable_eos,
-disable_eos : fmh_gpib_disable_eos,
-parallel_poll : fmh_gpib_parallel_poll,
-parallel_poll_configure : fmh_gpib_parallel_poll_configure,
-parallel_poll_response : fmh_gpib_parallel_poll_response,
-local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode,
-line_status : fmh_gpib_line_status,
-update_status : fmh_gpib_update_status,
-primary_address : fmh_gpib_primary_address,
-secondary_address : fmh_gpib_secondary_address,
-serial_poll_response2 : fmh_gpib_serial_poll_response2,
-serial_poll_status : fmh_gpib_serial_poll_status,
-t1_delay : fmh_gpib_t1_delay,
-return_to_local : fmh_gpib_return_to_local,
+static gpib_interface_t fmh_gpib_interface = {
+	.name = "fmh_gpib",
+	.attach = fmh_gpib_attach_holdoff_end,
+	.detach = fmh_gpib_detach,
+	.read = fmh_gpib_accel_read,
+	.write = fmh_gpib_accel_write,
+	.command = fmh_gpib_command,
+	.take_control = fmh_gpib_take_control,
+	.go_to_standby = fmh_gpib_go_to_standby,
+	.request_system_control = fmh_gpib_request_system_control,
+	.interface_clear = fmh_gpib_interface_clear,
+	.remote_enable = fmh_gpib_remote_enable,
+	.enable_eos = fmh_gpib_enable_eos,
+	.disable_eos = fmh_gpib_disable_eos,
+	.parallel_poll = fmh_gpib_parallel_poll,
+	.parallel_poll_configure = fmh_gpib_parallel_poll_configure,
+	.parallel_poll_response = fmh_gpib_parallel_poll_response,
+	.local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode,
+	.line_status = fmh_gpib_line_status,
+	.update_status = fmh_gpib_update_status,
+	.primary_address = fmh_gpib_primary_address,
+	.secondary_address = fmh_gpib_secondary_address,
+	.serial_poll_response2 = fmh_gpib_serial_poll_response2,
+	.serial_poll_status = fmh_gpib_serial_poll_status,
+	.t1_delay = fmh_gpib_t1_delay,
+	.return_to_local = fmh_gpib_return_to_local,
 };
 
-gpib_interface_t fmh_gpib_pci_interface = {
-name: "fmh_gpib_pci",
-attach : fmh_gpib_pci_attach_holdoff_end,
-detach : fmh_gpib_pci_detach,
-read : fmh_gpib_fifo_read,
-write : fmh_gpib_fifo_write,
-command : fmh_gpib_command,
-take_control : fmh_gpib_take_control,
-go_to_standby : fmh_gpib_go_to_standby,
-request_system_control : fmh_gpib_request_system_control,
-interface_clear : fmh_gpib_interface_clear,
-remote_enable : fmh_gpib_remote_enable,
-enable_eos : fmh_gpib_enable_eos,
-disable_eos : fmh_gpib_disable_eos,
-parallel_poll : fmh_gpib_parallel_poll,
-parallel_poll_configure : fmh_gpib_parallel_poll_configure,
-parallel_poll_response : fmh_gpib_parallel_poll_response,
-local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode,
-line_status : fmh_gpib_line_status,
-update_status : fmh_gpib_update_status,
-primary_address : fmh_gpib_primary_address,
-secondary_address : fmh_gpib_secondary_address,
-serial_poll_response2 : fmh_gpib_serial_poll_response2,
-serial_poll_status : fmh_gpib_serial_poll_status,
-t1_delay : fmh_gpib_t1_delay,
-return_to_local : fmh_gpib_return_to_local,
+static gpib_interface_t fmh_gpib_pci_interface = {
+	.name = "fmh_gpib_pci",
+	.attach = fmh_gpib_pci_attach_holdoff_end,
+	.detach = fmh_gpib_pci_detach,
+	.read = fmh_gpib_fifo_read,
+	.write = fmh_gpib_fifo_write,
+	.command = fmh_gpib_command,
+	.take_control = fmh_gpib_take_control,
+	.go_to_standby = fmh_gpib_go_to_standby,
+	.request_system_control = fmh_gpib_request_system_control,
+	.interface_clear = fmh_gpib_interface_clear,
+	.remote_enable = fmh_gpib_remote_enable,
+	.enable_eos = fmh_gpib_enable_eos,
+	.disable_eos = fmh_gpib_disable_eos,
+	.parallel_poll = fmh_gpib_parallel_poll,
+	.parallel_poll_configure = fmh_gpib_parallel_poll_configure,
+	.parallel_poll_response = fmh_gpib_parallel_poll_response,
+	.local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode,
+	.line_status = fmh_gpib_line_status,
+	.update_status = fmh_gpib_update_status,
+	.primary_address = fmh_gpib_primary_address,
+	.secondary_address = fmh_gpib_secondary_address,
+	.serial_poll_response2 = fmh_gpib_serial_poll_response2,
+	.serial_poll_status = fmh_gpib_serial_poll_status,
+	.t1_delay = fmh_gpib_t1_delay,
+	.return_to_local = fmh_gpib_return_to_local,
 };
 
-gpib_interface_t fmh_gpib_pci_unaccel_interface = {
-name: "fmh_gpib_pci_unaccel",
-attach : fmh_gpib_pci_attach_holdoff_all,
-detach : fmh_gpib_pci_detach,
-read : fmh_gpib_read,
-write : fmh_gpib_write,
-command : fmh_gpib_command,
-take_control : fmh_gpib_take_control,
-go_to_standby : fmh_gpib_go_to_standby,
-request_system_control : fmh_gpib_request_system_control,
-interface_clear : fmh_gpib_interface_clear,
-remote_enable : fmh_gpib_remote_enable,
-enable_eos : fmh_gpib_enable_eos,
-disable_eos : fmh_gpib_disable_eos,
-parallel_poll : fmh_gpib_parallel_poll,
-parallel_poll_configure : fmh_gpib_parallel_poll_configure,
-parallel_poll_response : fmh_gpib_parallel_poll_response,
-local_parallel_poll_mode : fmh_gpib_local_parallel_poll_mode,
-line_status : fmh_gpib_line_status,
-update_status : fmh_gpib_update_status,
-primary_address : fmh_gpib_primary_address,
-secondary_address : fmh_gpib_secondary_address,
-serial_poll_response2 : fmh_gpib_serial_poll_response2,
-serial_poll_status : fmh_gpib_serial_poll_status,
-t1_delay : fmh_gpib_t1_delay,
-return_to_local : fmh_gpib_return_to_local,
+static gpib_interface_t fmh_gpib_pci_unaccel_interface = {
+	.name = "fmh_gpib_pci_unaccel",
+	.attach = fmh_gpib_pci_attach_holdoff_all,
+	.detach = fmh_gpib_pci_detach,
+	.read = fmh_gpib_read,
+	.write = fmh_gpib_write,
+	.command = fmh_gpib_command,
+	.take_control = fmh_gpib_take_control,
+	.go_to_standby = fmh_gpib_go_to_standby,
+	.request_system_control = fmh_gpib_request_system_control,
+	.interface_clear = fmh_gpib_interface_clear,
+	.remote_enable = fmh_gpib_remote_enable,
+	.enable_eos = fmh_gpib_enable_eos,
+	.disable_eos = fmh_gpib_disable_eos,
+	.parallel_poll = fmh_gpib_parallel_poll,
+	.parallel_poll_configure = fmh_gpib_parallel_poll_configure,
+	.parallel_poll_response = fmh_gpib_parallel_poll_response,
+	.local_parallel_poll_mode = fmh_gpib_local_parallel_poll_mode,
+	.line_status = fmh_gpib_line_status,
+	.update_status = fmh_gpib_update_status,
+	.primary_address = fmh_gpib_primary_address,
+	.secondary_address = fmh_gpib_secondary_address,
+	.serial_poll_response2 = fmh_gpib_serial_poll_response2,
+	.serial_poll_status = fmh_gpib_serial_poll_status,
+	.t1_delay = fmh_gpib_t1_delay,
+	.return_to_local = fmh_gpib_return_to_local,
 };
 
 irqreturn_t fmh_gpib_internal_interrupt(gpib_board_t *board)
@@ -1692,23 +1692,54 @@ static int __init fmh_gpib_init_module(void)
 
 	result = platform_driver_register(&fmh_gpib_platform_driver);
 	if (result) {
-		pr_err("fmh_gpib: platform_driver_register failed!\n");
+		pr_err("fmh_gpib: platform_driver_register failed: error = %d\n", result);
 		return result;
 	}
 
 	result = pci_register_driver(&fmh_gpib_pci_driver);
 	if (result) {
-		pr_err("fmh_gpib: pci_driver_register failed!\n");
-		return result;
+		pr_err("fmh_gpib: pci_register_driver failed: error = %d\n", result);
+		goto err_pci_driver;
+	}
+
+	result = gpib_register_driver(&fmh_gpib_unaccel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_unaccel;
+	}
+
+	result = gpib_register_driver(&fmh_gpib_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_interface;
+	}
+
+	result = gpib_register_driver(&fmh_gpib_pci_unaccel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_pci_unaccel;
 	}
 
-	gpib_register_driver(&fmh_gpib_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&fmh_gpib_interface, THIS_MODULE);
-	gpib_register_driver(&fmh_gpib_pci_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&fmh_gpib_pci_interface, THIS_MODULE);
+	result = gpib_register_driver(&fmh_gpib_pci_interface, THIS_MODULE);
+	if (result) {
+		pr_err("fmh_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_pci;
+	}
 
-	pr_info("fmh_gpib\n");
 	return 0;
+
+err_pci:
+	gpib_unregister_driver(&fmh_gpib_pci_unaccel_interface);
+err_pci_unaccel:
+	gpib_unregister_driver(&fmh_gpib_interface);
+err_interface:
+	gpib_unregister_driver(&fmh_gpib_unaccel_interface);
+err_unaccel:
+	pci_unregister_driver(&fmh_gpib_pci_driver);
+err_pci_driver:
+	platform_driver_unregister(&fmh_gpib_platform_driver);
+
+	return result;
 }
 
 static void __exit fmh_gpib_exit_module(void)
diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h
index 60b1bd6d3c15..de6fd2164414 100644
--- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h
+++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h
@@ -33,7 +33,7 @@ struct fmh_priv {
 	u8 *dma_buffer;
 	int dma_buffer_size;
 	int dma_burst_length;
-	void *fifo_base;
+	void __iomem *fifo_base;
 	unsigned supports_fifo_interrupts : 1;
 };
 
diff --git a/drivers/staging/gpib/gpio/gpib_bitbang.c b/drivers/staging/gpib/gpio/gpib_bitbang.c
index 23550502e012..828c99ea613f 100644
--- a/drivers/staging/gpib/gpio/gpib_bitbang.c
+++ b/drivers/staging/gpib/gpio/gpib_bitbang.c
@@ -147,7 +147,7 @@ DEFINE_LED_TRIGGER(ledtrig_gpib);
 			led_trigger_event(ledtrig_gpib, LED_OFF); }	\
 	while (0)
 
-struct gpio_desc *all_descriptors[GPIB_PINS + SN7516X_PINS];
+static struct gpio_desc *all_descriptors[GPIB_PINS + SN7516X_PINS];
 
 #define D01 all_descriptors[0]
 #define D02 all_descriptors[1]
@@ -175,7 +175,7 @@ struct gpio_desc *all_descriptors[GPIB_PINS + SN7516X_PINS];
 /* YOGA dapter uses a global enable for the buffer chips, re-using the TE pin */
 #define YOGA_ENABLE TE
 
-int gpios_vector[] = {
+static int gpios_vector[] = {
 	D01_pin_nr,
 	D02_pin_nr,
 	D03_pin_nr,
@@ -265,7 +265,7 @@ static struct gpiod_lookup_table gpib_gpio_table_0 = {
 static struct gpiod_lookup_table *lookup_tables[] = {
 	&gpib_gpio_table_0,
 	&gpib_gpio_table_1,
-	0
+	NULL
 };
 
 /* struct which defines private_data for gpio driver */
@@ -1119,7 +1119,7 @@ static void release_gpios(void)
 	for (j = 0 ; j < NUM_PINS ; j++) {
 		if (all_descriptors[j]) {
 			gpiod_put(all_descriptors[j]);
-			all_descriptors[j] = 0;
+			all_descriptors[j] = NULL;
 		}
 	}
 }
@@ -1312,36 +1312,41 @@ bb_attach_out:
 	return retval;
 }
 
-gpib_interface_t bb_interface = {
-name:			  NAME,
-attach : bb_attach,
-detach : bb_detach,
-read : bb_read,
-write : bb_write,
-command : bb_command,
-take_control : bb_take_control,
-go_to_standby : bb_go_to_standby,
-request_system_control : bb_request_system_control,
-interface_clear : bb_interface_clear,
-remote_enable : bb_remote_enable,
-enable_eos : bb_enable_eos,
-disable_eos : bb_disable_eos,
-parallel_poll : bb_parallel_poll,
-parallel_poll_configure : bb_parallel_poll_configure,
-parallel_poll_response : bb_parallel_poll_response,
-line_status : bb_line_status,
-update_status : bb_update_status,
-primary_address : bb_primary_address,
-secondary_address : bb_secondary_address,
-serial_poll_response : bb_serial_poll_response,
-serial_poll_status : bb_serial_poll_status,
-t1_delay : bb_t1_delay,
-return_to_local : bb_return_to_local,
+static gpib_interface_t bb_interface = {
+	.name =	NAME,
+	.attach = bb_attach,
+	.detach = bb_detach,
+	.read = bb_read,
+	.write = bb_write,
+	.command = bb_command,
+	.take_control = bb_take_control,
+	.go_to_standby = bb_go_to_standby,
+	.request_system_control = bb_request_system_control,
+	.interface_clear = bb_interface_clear,
+	.remote_enable = bb_remote_enable,
+	.enable_eos = bb_enable_eos,
+	.disable_eos = bb_disable_eos,
+	.parallel_poll = bb_parallel_poll,
+	.parallel_poll_configure = bb_parallel_poll_configure,
+	.parallel_poll_response = bb_parallel_poll_response,
+	.line_status = bb_line_status,
+	.update_status = bb_update_status,
+	.primary_address = bb_primary_address,
+	.secondary_address = bb_secondary_address,
+	.serial_poll_response = bb_serial_poll_response,
+	.serial_poll_status = bb_serial_poll_status,
+	.t1_delay = bb_t1_delay,
+	.return_to_local = bb_return_to_local,
 };
 
 static int __init bb_init_module(void)
 {
-	gpib_register_driver(&bb_interface, THIS_MODULE);
+	int result = gpib_register_driver(&bb_interface, THIS_MODULE);
+
+	if (result) {
+		pr_err("gpib_bitbang: gpib_register_driver failed: error = %d\n", result);
+		return result;
+	}
 
 	dbg_printk(0, "module loaded with pin map \"%s\"%s\n",
 		   pin_map, (sn7516x_used) ? " and SN7516x driver support" : "");
diff --git a/drivers/staging/gpib/hp_82335/hp82335.c b/drivers/staging/gpib/hp_82335/hp82335.c
index ea78143c7ab6..700d1ba029d2 100644
--- a/drivers/staging/gpib/hp_82335/hp82335.c
+++ b/drivers/staging/gpib/hp_82335/hp82335.c
@@ -173,32 +173,32 @@ void hp82335_return_to_local(gpib_board_t *board)
 	tms9914_return_to_local(board, &priv->tms9914_priv);
 }
 
-gpib_interface_t hp82335_interface = {
-name: "hp82335",
-attach : hp82335_attach,
-detach : hp82335_detach,
-read : hp82335_read,
-write : hp82335_write,
-command : hp82335_command,
-request_system_control : hp82335_request_system_control,
-take_control : hp82335_take_control,
-go_to_standby : hp82335_go_to_standby,
-interface_clear : hp82335_interface_clear,
-remote_enable : hp82335_remote_enable,
-enable_eos : hp82335_enable_eos,
-disable_eos : hp82335_disable_eos,
-parallel_poll : hp82335_parallel_poll,
-parallel_poll_configure : hp82335_parallel_poll_configure,
-parallel_poll_response : hp82335_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : hp82335_line_status,
-update_status : hp82335_update_status,
-primary_address : hp82335_primary_address,
-secondary_address : hp82335_secondary_address,
-serial_poll_response : hp82335_serial_poll_response,
-serial_poll_status : hp82335_serial_poll_status,
-t1_delay : hp82335_t1_delay,
-return_to_local : hp82335_return_to_local,
+static gpib_interface_t hp82335_interface = {
+	.name = "hp82335",
+	.attach = hp82335_attach,
+	.detach = hp82335_detach,
+	.read = hp82335_read,
+	.write = hp82335_write,
+	.command = hp82335_command,
+	.request_system_control = hp82335_request_system_control,
+	.take_control = hp82335_take_control,
+	.go_to_standby = hp82335_go_to_standby,
+	.interface_clear = hp82335_interface_clear,
+	.remote_enable = hp82335_remote_enable,
+	.enable_eos = hp82335_enable_eos,
+	.disable_eos = hp82335_disable_eos,
+	.parallel_poll = hp82335_parallel_poll,
+	.parallel_poll_configure = hp82335_parallel_poll_configure,
+	.parallel_poll_response = hp82335_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = hp82335_line_status,
+	.update_status = hp82335_update_status,
+	.primary_address = hp82335_primary_address,
+	.secondary_address = hp82335_secondary_address,
+	.serial_poll_response = hp82335_serial_poll_response,
+	.serial_poll_status = hp82335_serial_poll_status,
+	.t1_delay = hp82335_t1_delay,
+	.return_to_local = hp82335_return_to_local,
 };
 
 int hp82335_allocate_private(gpib_board_t *board)
@@ -326,7 +326,13 @@ void hp82335_detach(gpib_board_t *board)
 
 static int __init hp82335_init_module(void)
 {
-	gpib_register_driver(&hp82335_interface, THIS_MODULE);
+	int result = gpib_register_driver(&hp82335_interface, THIS_MODULE);
+
+	if (result) {
+		pr_err("hp82335: gpib_register_driver failed: error = %d\n", result);
+		return result;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/staging/gpib/hp_82335/hp82335.h b/drivers/staging/gpib/hp_82335/hp82335.h
index 5e5297af731a..4b185d7c5188 100644
--- a/drivers/staging/gpib/hp_82335/hp82335.h
+++ b/drivers/staging/gpib/hp_82335/hp82335.h
@@ -17,9 +17,6 @@ struct hp82335_priv  {
 	unsigned long raw_iobase;
 };
 
-// interfaces
-extern gpib_interface_t hp82335_interface;
-
 // interface functions
 int hp82335_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, size_t *bytes_read);
 int hp82335_write(gpib_board_t *board, uint8_t *buffer, size_t length,
diff --git a/drivers/staging/gpib/hp_82341/hp_82341.c b/drivers/staging/gpib/hp_82341/hp_82341.c
index 71d481e88bd9..0ddae295912f 100644
--- a/drivers/staging/gpib/hp_82341/hp_82341.c
+++ b/drivers/staging/gpib/hp_82341/hp_82341.c
@@ -402,59 +402,59 @@ void hp_82341_return_to_local(gpib_board_t *board)
 	tms9914_return_to_local(board, &priv->tms9914_priv);
 }
 
-gpib_interface_t hp_82341_unaccel_interface = {
-name: "hp_82341_unaccel",
-attach : hp_82341_attach,
-detach : hp_82341_detach,
-read : hp_82341_read,
-write : hp_82341_write,
-command : hp_82341_command,
-request_system_control : hp_82341_request_system_control,
-take_control : hp_82341_take_control,
-go_to_standby : hp_82341_go_to_standby,
-interface_clear : hp_82341_interface_clear,
-remote_enable : hp_82341_remote_enable,
-enable_eos : hp_82341_enable_eos,
-disable_eos : hp_82341_disable_eos,
-parallel_poll : hp_82341_parallel_poll,
-parallel_poll_configure : hp_82341_parallel_poll_configure,
-parallel_poll_response : hp_82341_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : hp_82341_line_status,
-update_status : hp_82341_update_status,
-primary_address : hp_82341_primary_address,
-secondary_address : hp_82341_secondary_address,
-serial_poll_response : hp_82341_serial_poll_response,
-serial_poll_status : hp_82341_serial_poll_status,
-t1_delay : hp_82341_t1_delay,
-return_to_local : hp_82341_return_to_local,
+static gpib_interface_t hp_82341_unaccel_interface = {
+	.name = "hp_82341_unaccel",
+	.attach = hp_82341_attach,
+	.detach = hp_82341_detach,
+	.read = hp_82341_read,
+	.write = hp_82341_write,
+	.command = hp_82341_command,
+	.request_system_control = hp_82341_request_system_control,
+	.take_control = hp_82341_take_control,
+	.go_to_standby = hp_82341_go_to_standby,
+	.interface_clear = hp_82341_interface_clear,
+	.remote_enable = hp_82341_remote_enable,
+	.enable_eos = hp_82341_enable_eos,
+	.disable_eos = hp_82341_disable_eos,
+	.parallel_poll = hp_82341_parallel_poll,
+	.parallel_poll_configure = hp_82341_parallel_poll_configure,
+	.parallel_poll_response = hp_82341_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = hp_82341_line_status,
+	.update_status = hp_82341_update_status,
+	.primary_address = hp_82341_primary_address,
+	.secondary_address = hp_82341_secondary_address,
+	.serial_poll_response = hp_82341_serial_poll_response,
+	.serial_poll_status = hp_82341_serial_poll_status,
+	.t1_delay = hp_82341_t1_delay,
+	.return_to_local = hp_82341_return_to_local,
 };
 
-gpib_interface_t hp_82341_interface = {
-name: "hp_82341",
-attach : hp_82341_attach,
-detach : hp_82341_detach,
-read : hp_82341_accel_read,
-write : hp_82341_accel_write,
-command : hp_82341_command,
-request_system_control : hp_82341_request_system_control,
-take_control : hp_82341_take_control,
-go_to_standby : hp_82341_go_to_standby,
-interface_clear : hp_82341_interface_clear,
-remote_enable : hp_82341_remote_enable,
-enable_eos : hp_82341_enable_eos,
-disable_eos : hp_82341_disable_eos,
-parallel_poll : hp_82341_parallel_poll,
-parallel_poll_configure : hp_82341_parallel_poll_configure,
-parallel_poll_response : hp_82341_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : hp_82341_line_status,
-update_status : hp_82341_update_status,
-primary_address : hp_82341_primary_address,
-secondary_address : hp_82341_secondary_address,
-serial_poll_response : hp_82341_serial_poll_response,
-t1_delay : hp_82341_t1_delay,
-return_to_local : hp_82341_return_to_local,
+static gpib_interface_t hp_82341_interface = {
+	.name = "hp_82341",
+	.attach = hp_82341_attach,
+	.detach = hp_82341_detach,
+	.read = hp_82341_accel_read,
+	.write = hp_82341_accel_write,
+	.command = hp_82341_command,
+	.request_system_control = hp_82341_request_system_control,
+	.take_control = hp_82341_take_control,
+	.go_to_standby = hp_82341_go_to_standby,
+	.interface_clear = hp_82341_interface_clear,
+	.remote_enable = hp_82341_remote_enable,
+	.enable_eos = hp_82341_enable_eos,
+	.disable_eos = hp_82341_disable_eos,
+	.parallel_poll = hp_82341_parallel_poll,
+	.parallel_poll_configure = hp_82341_parallel_poll_configure,
+	.parallel_poll_response = hp_82341_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = hp_82341_line_status,
+	.update_status = hp_82341_update_status,
+	.primary_address = hp_82341_primary_address,
+	.secondary_address = hp_82341_secondary_address,
+	.serial_poll_response = hp_82341_serial_poll_response,
+	.t1_delay = hp_82341_t1_delay,
+	.return_to_local = hp_82341_return_to_local,
 };
 
 int hp_82341_allocate_private(gpib_board_t *board)
@@ -807,8 +807,21 @@ MODULE_DEVICE_TABLE(pnp, hp_82341_pnp_table);
 
 static int __init hp_82341_init_module(void)
 {
-	gpib_register_driver(&hp_82341_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&hp_82341_interface, THIS_MODULE);
+	int ret;
+
+	ret = gpib_register_driver(&hp_82341_unaccel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("hp_82341: gpib_register_driver failed: error = %d\n", ret);
+		return ret;
+	}
+
+	ret = gpib_register_driver(&hp_82341_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("hp_82341: gpib_register_driver failed: error = %d\n", ret);
+		gpib_unregister_driver(&hp_82341_unaccel_interface);
+		return ret;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/staging/gpib/hp_82341/hp_82341.h b/drivers/staging/gpib/hp_82341/hp_82341.h
index 7c391860b399..0065ebd9747c 100644
--- a/drivers/staging/gpib/hp_82341/hp_82341.h
+++ b/drivers/staging/gpib/hp_82341/hp_82341.h
@@ -26,8 +26,6 @@ struct hp_82341_priv {
 	enum hp_82341_hardware_version hw_version;
 };
 
-// interfaces
-extern gpib_interface_t hp_82341_interface;
 
 // interface functions
 int hp_82341_accel_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end,
diff --git a/drivers/staging/gpib/include/amcc5920.h b/drivers/staging/gpib/include/amcc5920.h
index 766b3799223f..7a88bd282feb 100644
--- a/drivers/staging/gpib/include/amcc5920.h
+++ b/drivers/staging/gpib/include/amcc5920.h
@@ -22,7 +22,7 @@ static const int bits_per_region = 8;
 
 static inline uint32_t amcc_wait_state_bits(unsigned int region, unsigned int num_wait_states)
 {
-	return (num_wait_states & 0x7) << (-region * bits_per_region);
+	return (num_wait_states & 0x7) << (--region * bits_per_region);
 };
 
 enum amcc_prefetch_bits {
diff --git a/drivers/staging/gpib/include/gpibP.h b/drivers/staging/gpib/include/gpibP.h
index b97da577ba33..d35fdd391f7e 100644
--- a/drivers/staging/gpib/include/gpibP.h
+++ b/drivers/staging/gpib/include/gpibP.h
@@ -18,7 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 
-void gpib_register_driver(gpib_interface_t *interface, struct module *mod);
+int gpib_register_driver(gpib_interface_t *interface, struct module *mod);
 void gpib_unregister_driver(gpib_interface_t *interface);
 struct pci_dev *gpib_pci_get_device(const gpib_board_config_t *config, unsigned int vendor_id,
 				    unsigned int device_id, struct pci_dev *from);
diff --git a/drivers/staging/gpib/ines/ines.h b/drivers/staging/gpib/ines/ines.h
index eed038fd3f28..3918737fa21a 100644
--- a/drivers/staging/gpib/ines/ines.h
+++ b/drivers/staging/gpib/ines/ines.h
@@ -35,13 +35,6 @@ struct ines_priv {
 	u8 extend_mode_bits;
 };
 
-// interfaces
-extern gpib_interface_t ines_pci_interface;
-extern gpib_interface_t ines_pci_accel_interface;
-extern gpib_interface_t ines_pcmcia_interface;
-extern gpib_interface_t ines_pcmcia_accel_interface;
-extern gpib_interface_t ines_pcmcia_unaccel_interface;
-
 // interface functions
 int ines_read(gpib_board_t *board, uint8_t *buffer, size_t length, int *end, size_t *bytes_read);
 int ines_write(gpib_board_t *board, uint8_t *buffer, size_t length,
diff --git a/drivers/staging/gpib/ines/ines_gpib.c b/drivers/staging/gpib/ines/ines_gpib.c
index e18455ba842f..22a05a287bce 100644
--- a/drivers/staging/gpib/ines/ines_gpib.c
+++ b/drivers/staging/gpib/ines/ines_gpib.c
@@ -357,38 +357,38 @@ struct ines_pci_id {
 	enum ines_pci_chip pci_chip_type;
 };
 
-struct ines_pci_id pci_ids[] = {
-	{vendor_id: PCI_VENDOR_ID_PLX,
-	 device_id : PCI_DEVICE_ID_PLX_9050,
-	 subsystem_vendor_id : PCI_VENDOR_ID_PLX,
-	 subsystem_device_id : PCI_SUBDEVICE_ID_INES_GPIB,
-	 gpib_region : 2,
-	 io_offset : 1,
-	 pci_chip_type : PCI_CHIP_PLX9050,
+static struct ines_pci_id pci_ids[] = {
+	{.vendor_id = PCI_VENDOR_ID_PLX,
+	 .device_id = PCI_DEVICE_ID_PLX_9050,
+	 .subsystem_vendor_id = PCI_VENDOR_ID_PLX,
+	 .subsystem_device_id = PCI_SUBDEVICE_ID_INES_GPIB,
+	 .gpib_region = 2,
+	 .io_offset = 1,
+	 .pci_chip_type = PCI_CHIP_PLX9050,
 	},
-	{vendor_id: PCI_VENDOR_ID_AMCC,
-	 device_id : PCI_DEVICE_ID_INES_GPIB_AMCC,
-	 subsystem_vendor_id : PCI_VENDOR_ID_AMCC,
-	 subsystem_device_id : PCI_SUBDEVICE_ID_INES_GPIB,
-	 gpib_region : 1,
-	 io_offset : 1,
-	 pci_chip_type : PCI_CHIP_AMCC5920,
+	{.vendor_id = PCI_VENDOR_ID_AMCC,
+	 .device_id = PCI_DEVICE_ID_INES_GPIB_AMCC,
+	 .subsystem_vendor_id = PCI_VENDOR_ID_AMCC,
+	 .subsystem_device_id = PCI_SUBDEVICE_ID_INES_GPIB,
+	 .gpib_region = 1,
+	 .io_offset = 1,
+	 .pci_chip_type = PCI_CHIP_AMCC5920,
 	},
-	{vendor_id: PCI_VENDOR_ID_INES_QUICKLOGIC,
-	 device_id : PCI_DEVICE_ID_INES_GPIB_QL5030,
-	 subsystem_vendor_id : PCI_VENDOR_ID_INES_QUICKLOGIC,
-	 subsystem_device_id : PCI_DEVICE_ID_INES_GPIB_QL5030,
-	 gpib_region : 1,
-	 io_offset : 1,
-	 pci_chip_type : PCI_CHIP_QUICKLOGIC5030,
+	{.vendor_id = PCI_VENDOR_ID_INES_QUICKLOGIC,
+	 .device_id = PCI_DEVICE_ID_INES_GPIB_QL5030,
+	 .subsystem_vendor_id = PCI_VENDOR_ID_INES_QUICKLOGIC,
+	 .subsystem_device_id = PCI_DEVICE_ID_INES_GPIB_QL5030,
+	 .gpib_region = 1,
+	 .io_offset = 1,
+	 .pci_chip_type = PCI_CHIP_QUICKLOGIC5030,
 	},
-	{vendor_id: PCI_VENDOR_ID_QUANCOM,
-	 device_id : PCI_DEVICE_ID_QUANCOM_GPIB,
-	 subsystem_vendor_id : -1,
-	 subsystem_device_id : -1,
-	 gpib_region : 0,
-	 io_offset : 4,
-	 pci_chip_type : PCI_CHIP_QUANCOM,
+	{.vendor_id = PCI_VENDOR_ID_QUANCOM,
+	 .device_id = PCI_DEVICE_ID_QUANCOM_GPIB,
+	 .subsystem_vendor_id = -1,
+	 .subsystem_device_id = -1,
+	 .gpib_region = 0,
+	 .io_offset = 4,
+	 .pci_chip_type = PCI_CHIP_QUANCOM,
 	},
 };
 
@@ -540,116 +540,116 @@ void ines_return_to_local(gpib_board_t *board)
 	nec7210_return_to_local(board, &priv->nec7210_priv);
 }
 
-gpib_interface_t ines_pci_unaccel_interface = {
-name: "ines_pci_unaccel",
-attach : ines_pci_attach,
-detach : ines_pci_detach,
-read : ines_read,
-write : ines_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_pci_unaccel_interface = {
+	.name = "ines_pci_unaccel",
+	.attach = ines_pci_attach,
+	.detach = ines_pci_detach,
+	.read = ines_read,
+	.write = ines_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
-gpib_interface_t ines_pci_interface = {
-name: "ines_pci",
-attach : ines_pci_accel_attach,
-detach : ines_pci_detach,
-read : ines_accel_read,
-write : ines_accel_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_pci_interface = {
+	.name = "ines_pci",
+	.attach = ines_pci_accel_attach,
+	.detach = ines_pci_detach,
+	.read = ines_accel_read,
+	.write = ines_accel_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
-gpib_interface_t ines_pci_accel_interface = {
-name: "ines_pci_accel",
-attach : ines_pci_accel_attach,
-detach : ines_pci_detach,
-read : ines_accel_read,
-write : ines_accel_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_pci_accel_interface = {
+	.name = "ines_pci_accel",
+	.attach = ines_pci_accel_attach,
+	.detach = ines_pci_detach,
+	.read = ines_accel_read,
+	.write = ines_accel_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
-gpib_interface_t ines_isa_interface = {
-name: "ines_isa",
-attach : ines_isa_attach,
-detach : ines_isa_detach,
-read : ines_accel_read,
-write : ines_accel_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_isa_interface = {
+	.name = "ines_isa",
+	.attach = ines_isa_attach,
+	.detach = ines_isa_detach,
+	.read = ines_accel_read,
+	.write = ines_accel_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
 static int ines_allocate_private(gpib_board_t *board)
@@ -1122,7 +1122,7 @@ static int ines_gpib_config(struct pcmcia_device *link)
 {
 	struct local_info *dev;
 	int retval;
-	void *virt;
+	void __iomem *virt;
 
 	dev = link->priv;
 	DEBUG(0, "%s(0x%p)\n", __func__, link);
@@ -1156,7 +1156,7 @@ static int ines_gpib_config(struct pcmcia_device *link)
 	}
 	virt = ioremap(link->resource[2]->start, resource_size(link->resource[2]));
 	writeb((link->resource[2]->start >> 2) & 0xff, virt + 0xf0); // IOWindow base
-	iounmap((void *)virt);
+	iounmap(virt);
 
 	/*
 	 * This actually configures the PCMCIA socket -- setting up
@@ -1227,100 +1227,94 @@ static struct pcmcia_driver ines_gpib_cs_driver = {
 	.resume		= ines_gpib_resume,
 };
 
-int ines_pcmcia_init_module(void)
-{
-	pcmcia_register_driver(&ines_gpib_cs_driver);
-	return 0;
-}
-
 void ines_pcmcia_cleanup_module(void)
 {
 	DEBUG(0, "ines_cs: unloading\n");
 	pcmcia_unregister_driver(&ines_gpib_cs_driver);
 }
 
-gpib_interface_t ines_pcmcia_unaccel_interface = {
-name: "ines_pcmcia_unaccel",
-attach : ines_pcmcia_attach,
-detach : ines_pcmcia_detach,
-read : ines_read,
-write : ines_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_pcmcia_unaccel_interface = {
+	.name = "ines_pcmcia_unaccel",
+	.attach = ines_pcmcia_attach,
+	.detach = ines_pcmcia_detach,
+	.read = ines_read,
+	.write = ines_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
-gpib_interface_t ines_pcmcia_accel_interface = {
-name: "ines_pcmcia_accel",
-attach : ines_pcmcia_accel_attach,
-detach : ines_pcmcia_detach,
-read : ines_accel_read,
-write : ines_accel_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_pcmcia_accel_interface = {
+	.name = "ines_pcmcia_accel",
+	.attach = ines_pcmcia_accel_attach,
+	.detach = ines_pcmcia_detach,
+	.read = ines_accel_read,
+	.write = ines_accel_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
-gpib_interface_t ines_pcmcia_interface = {
-name: "ines_pcmcia",
-attach : ines_pcmcia_accel_attach,
-detach : ines_pcmcia_detach,
-read : ines_accel_read,
-write : ines_accel_write,
-command : ines_command,
-take_control : ines_take_control,
-go_to_standby : ines_go_to_standby,
-request_system_control : ines_request_system_control,
-interface_clear : ines_interface_clear,
-remote_enable : ines_remote_enable,
-enable_eos : ines_enable_eos,
-disable_eos : ines_disable_eos,
-parallel_poll : ines_parallel_poll,
-parallel_poll_configure : ines_parallel_poll_configure,
-parallel_poll_response : ines_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ines_line_status,
-update_status : ines_update_status,
-primary_address : ines_primary_address,
-secondary_address : ines_secondary_address,
-serial_poll_response : ines_serial_poll_response,
-serial_poll_status : ines_serial_poll_status,
-t1_delay : ines_t1_delay,
-return_to_local : ines_return_to_local,
+static gpib_interface_t ines_pcmcia_interface = {
+	.name = "ines_pcmcia",
+	.attach = ines_pcmcia_accel_attach,
+	.detach = ines_pcmcia_detach,
+	.read = ines_accel_read,
+	.write = ines_accel_write,
+	.command = ines_command,
+	.take_control = ines_take_control,
+	.go_to_standby = ines_go_to_standby,
+	.request_system_control = ines_request_system_control,
+	.interface_clear = ines_interface_clear,
+	.remote_enable = ines_remote_enable,
+	.enable_eos = ines_enable_eos,
+	.disable_eos = ines_disable_eos,
+	.parallel_poll = ines_parallel_poll,
+	.parallel_poll_configure = ines_parallel_poll_configure,
+	.parallel_poll_response = ines_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ines_line_status,
+	.update_status = ines_update_status,
+	.primary_address = ines_primary_address,
+	.secondary_address = ines_secondary_address,
+	.serial_poll_response = ines_serial_poll_response,
+	.serial_poll_status = ines_serial_poll_status,
+	.t1_delay = ines_t1_delay,
+	.return_to_local = ines_return_to_local,
 };
 
 irqreturn_t ines_pcmcia_interrupt(int irq, void *arg)
@@ -1348,8 +1342,8 @@ int ines_common_pcmcia_attach(gpib_board_t *board)
 	ines_priv = board->private_data;
 	nec_priv = &ines_priv->nec7210_priv;
 
-	if (request_region(curr_dev->resource[0]->start,
-			   resource_size(curr_dev->resource[0]), "ines_gpib") == 0) {
+	if (!request_region(curr_dev->resource[0]->start,
+			    resource_size(curr_dev->resource[0]), "ines_gpib")) {
 		pr_err("ines_gpib: ioports at 0x%lx already in use\n",
 		       (unsigned long)(curr_dev->resource[0]->start));
 		return -1;
@@ -1420,28 +1414,86 @@ void ines_pcmcia_detach(gpib_board_t *board)
 
 static int __init ines_init_module(void)
 {
-	int err = 0;
+	int ret;
+
+	ret = pci_register_driver(&ines_pci_driver);
+	if (ret) {
+		pr_err("ines_gpib: pci_register_driver failed: error = %d\n", ret);
+		return ret;
+	}
+
+	ret = gpib_register_driver(&ines_pci_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pci;
+	}
 
-	err = pci_register_driver(&ines_pci_driver);
-	if (err) {
-		pr_err("ines_gpib: pci_driver_register failed!\n");
-		return err;
+	ret = gpib_register_driver(&ines_pci_unaccel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pci_unaccel;
+	}
+
+	ret = gpib_register_driver(&ines_pci_accel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pci_accel;
+	}
+
+	ret = gpib_register_driver(&ines_isa_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_isa;
 	}
 
-	gpib_register_driver(&ines_pci_interface, THIS_MODULE);
-	gpib_register_driver(&ines_pci_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&ines_pci_accel_interface, THIS_MODULE);
-	gpib_register_driver(&ines_isa_interface, THIS_MODULE);
 #ifdef GPIB_PCMCIA
-	gpib_register_driver(&ines_pcmcia_interface, THIS_MODULE);
-	gpib_register_driver(&ines_pcmcia_unaccel_interface, THIS_MODULE);
-	gpib_register_driver(&ines_pcmcia_accel_interface, THIS_MODULE);
-	err += ines_pcmcia_init_module();
+	ret = gpib_register_driver(&ines_pcmcia_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia;
+	}
+
+	ret = gpib_register_driver(&ines_pcmcia_unaccel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia_unaccel;
+	}
+
+	ret = gpib_register_driver(&ines_pcmcia_accel_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ines_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia_accel;
+	}
+
+	ret = pcmcia_register_driver(&ines_gpib_cs_driver);
+	if (ret) {
+		pr_err("ines_gpib: pcmcia_register_driver failed: error = %d\n", ret);
+		goto err_pcmcia_driver;
+	}
 #endif
-	if (err)
-		return -1;
 
 	return 0;
+
+#ifdef GPIB_PCMCIA
+err_pcmcia_driver:
+	gpib_unregister_driver(&ines_pcmcia_accel_interface);
+err_pcmcia_accel:
+	gpib_unregister_driver(&ines_pcmcia_unaccel_interface);
+err_pcmcia_unaccel:
+	gpib_unregister_driver(&ines_pcmcia_interface);
+err_pcmcia:
+#endif
+	gpib_unregister_driver(&ines_isa_interface);
+err_isa:
+	gpib_unregister_driver(&ines_pci_accel_interface);
+err_pci_accel:
+	gpib_unregister_driver(&ines_pci_unaccel_interface);
+err_pci_unaccel:
+	gpib_unregister_driver(&ines_pci_interface);
+err_pci:
+	pci_unregister_driver(&ines_pci_driver);
+
+	return ret;
 }
 
 static void __exit ines_exit_module(void)
diff --git a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
index 93a05c792816..85322af62c23 100644
--- a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
+++ b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c
@@ -10,7 +10,6 @@
 
 /* base module includes */
 
-#include <linux/version.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/init.h>
@@ -25,7 +24,6 @@
 #include <linux/timer.h>
 #include <linux/delay.h>
 #include <linux/sched/signal.h>
-#include <linux/uaccess.h>
 #include <linux/usb.h>
 
 #include "gpibP.h"
@@ -1133,33 +1131,33 @@ static unsigned int usb_gpib_t1_delay(gpib_board_t *board, unsigned int nano_sec
  *   ***  module dispatch table and init/exit functions	 ***
  */
 
-gpib_interface_t usb_gpib_interface = {
-name: NAME,
-attach : usb_gpib_attach,
-detach : usb_gpib_detach,
-read : usb_gpib_read,
-write : usb_gpib_write,
-command : usb_gpib_command,
-take_control : usb_gpib_take_control,
-go_to_standby : usb_gpib_go_to_standby,
-request_system_control : usb_gpib_request_system_control,
-interface_clear : usb_gpib_interface_clear,
-remote_enable : usb_gpib_remote_enable,
-enable_eos : usb_gpib_enable_eos,
-disable_eos : usb_gpib_disable_eos,
-parallel_poll : usb_gpib_parallel_poll,
-parallel_poll_configure : usb_gpib_parallel_poll_configure,
-parallel_poll_response : usb_gpib_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : usb_gpib_line_status,
-update_status : usb_gpib_update_status,
-primary_address : usb_gpib_primary_address,
-secondary_address : usb_gpib_secondary_address,
-serial_poll_response : usb_gpib_serial_poll_response,
-serial_poll_status : usb_gpib_serial_poll_status,
-t1_delay : usb_gpib_t1_delay,
-return_to_local : usb_gpib_return_to_local,
-skip_check_for_command_acceptors : 1
+static gpib_interface_t usb_gpib_interface = {
+	.name = NAME,
+	.attach = usb_gpib_attach,
+	.detach = usb_gpib_detach,
+	.read = usb_gpib_read,
+	.write = usb_gpib_write,
+	.command = usb_gpib_command,
+	.take_control = usb_gpib_take_control,
+	.go_to_standby = usb_gpib_go_to_standby,
+	.request_system_control = usb_gpib_request_system_control,
+	.interface_clear = usb_gpib_interface_clear,
+	.remote_enable = usb_gpib_remote_enable,
+	.enable_eos = usb_gpib_enable_eos,
+	.disable_eos = usb_gpib_disable_eos,
+	.parallel_poll = usb_gpib_parallel_poll,
+	.parallel_poll_configure = usb_gpib_parallel_poll_configure,
+	.parallel_poll_response = usb_gpib_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = usb_gpib_line_status,
+	.update_status = usb_gpib_update_status,
+	.primary_address = usb_gpib_primary_address,
+	.secondary_address = usb_gpib_secondary_address,
+	.serial_poll_response = usb_gpib_serial_poll_response,
+	.serial_poll_status = usb_gpib_serial_poll_status,
+	.t1_delay = usb_gpib_t1_delay,
+	.return_to_local = usb_gpib_return_to_local,
+	.skip_check_for_command_acceptors = 1
 };
 
 /*
@@ -1181,7 +1179,11 @@ static int usb_gpib_init_module(struct usb_interface *interface)
 		return rv;
 
 	if (!assigned_usb_minors) {
-		gpib_register_driver(&usb_gpib_interface, THIS_MODULE);
+		rv = gpib_register_driver(&usb_gpib_interface, THIS_MODULE);
+		if (rv) {
+			pr_err("lpvo_usb_gpib: gpib_register_driver failed: error = %d\n", rv);
+			goto exit;
+		}
 	} else {
 		/* check if minor is already registered - maybe useless, but if
 		 *  it happens the code is inconsistent somewhere
@@ -1878,7 +1880,7 @@ static int skel_release(struct inode *inode, struct file *file)
  *  user space access to read function
  */
 
-static ssize_t skel_read(struct file *file, char *buffer, size_t count,
+static ssize_t skel_read(struct file *file, char __user *buffer, size_t count,
 			 loff_t *ppos)
 {
 	struct usb_skel *dev;
@@ -1909,7 +1911,7 @@ static ssize_t skel_read(struct file *file, char *buffer, size_t count,
  *  user space access to write function
  */
 
-static ssize_t skel_write(struct file *file, const char *user_buffer,
+static ssize_t skel_write(struct file *file, const char __user *user_buffer,
 			  size_t count, loff_t *ppos)
 {
 	struct usb_skel *dev;
diff --git a/drivers/staging/gpib/ni_usb/ni_usb_gpib.c b/drivers/staging/gpib/ni_usb/ni_usb_gpib.c
index b7b6fb1be379..d0656dc520f5 100644
--- a/drivers/staging/gpib/ni_usb/ni_usb_gpib.c
+++ b/drivers/staging/gpib/ni_usb/ni_usb_gpib.c
@@ -85,7 +85,7 @@ static void ni_usb_bulk_complete(struct urb *urb)
 
 //	printk("debug: %s: status=0x%x, error_count=%i, actual_length=%i\n",  __func__,
 //		urb->status, urb->error_count, urb->actual_length);
-	up(&context->complete);
+	complete(&context->complete);
 }
 
 static void ni_usb_timeout_handler(struct timer_list *t)
@@ -94,7 +94,7 @@ static void ni_usb_timeout_handler(struct timer_list *t)
 	struct ni_usb_urb_ctx *context = &ni_priv->context;
 
 	context->timed_out = 1;
-	up(&context->complete);
+	complete(&context->complete);
 };
 
 // I'm using nonblocking loosely here, it only means -EAGAIN can be returned in certain cases
@@ -124,7 +124,7 @@ static int ni_usb_nonblocking_send_bulk_msg(struct ni_usb_priv *ni_priv, void *d
 	}
 	usb_dev = interface_to_usbdev(ni_priv->bus_interface);
 	out_pipe = usb_sndbulkpipe(usb_dev, ni_priv->bulk_out_endpoint);
-	sema_init(&context->complete, 0);
+	init_completion(&context->complete);
 	context->timed_out = 0;
 	usb_fill_bulk_urb(ni_priv->bulk_urb, usb_dev, out_pipe, data, data_length,
 			  &ni_usb_bulk_complete, context);
@@ -143,7 +143,7 @@ static int ni_usb_nonblocking_send_bulk_msg(struct ni_usb_priv *ni_priv, void *d
 		return retval;
 	}
 	mutex_unlock(&ni_priv->bulk_transfer_lock);
-	down(&context->complete);    // wait for ni_usb_bulk_complete
+	wait_for_completion(&context->complete);    // wait for ni_usb_bulk_complete
 	if (context->timed_out) {
 		usb_kill_urb(ni_priv->bulk_urb);
 		dev_err(&usb_dev->dev, "%s: killed urb due to timeout\n", __func__);
@@ -210,7 +210,7 @@ static int ni_usb_nonblocking_receive_bulk_msg(struct ni_usb_priv *ni_priv,
 	}
 	usb_dev = interface_to_usbdev(ni_priv->bus_interface);
 	in_pipe = usb_rcvbulkpipe(usb_dev, ni_priv->bulk_in_endpoint);
-	sema_init(&context->complete, 0);
+	init_completion(&context->complete);
 	context->timed_out = 0;
 	usb_fill_bulk_urb(ni_priv->bulk_urb, usb_dev, in_pipe, data, data_length,
 			  &ni_usb_bulk_complete, context);
@@ -231,7 +231,7 @@ static int ni_usb_nonblocking_receive_bulk_msg(struct ni_usb_priv *ni_priv,
 	}
 	mutex_unlock(&ni_priv->bulk_transfer_lock);
 	if (interruptible) {
-		if (down_interruptible(&context->complete)) {
+		if (wait_for_completion_interruptible(&context->complete)) {
 			/* If we got interrupted by a signal while
 			 * waiting for the usb gpib to respond, we
 			 * should send a stop command so it will
@@ -243,10 +243,10 @@ static int ni_usb_nonblocking_receive_bulk_msg(struct ni_usb_priv *ni_priv,
 			/* now do an uninterruptible wait, it shouldn't take long
 			 *	for the board to respond now.
 			 */
-			down(&context->complete);
+			wait_for_completion(&context->complete);
 		}
 	} else {
-		down(&context->complete);
+		wait_for_completion(&context->complete);
 	}
 	if (context->timed_out) {
 		usb_kill_urb(ni_priv->bulk_urb);
@@ -783,8 +783,10 @@ static int ni_usb_write(gpib_board_t *board, uint8_t *buffer, size_t length,
 	}
 
 	in_data = kmalloc(in_data_length, GFP_KERNEL);
-	if (!in_data)
+	if (!in_data) {
+		mutex_unlock(&ni_priv->addressed_transfer_lock);
 		return -ENOMEM;
+	}
 	retval = ni_usb_receive_bulk_msg(ni_priv, in_data, in_data_length, &usb_bytes_read,
 					 ni_usb_timeout_msecs(board->usec_timeout), 1);
 
@@ -2351,33 +2353,33 @@ static void ni_usb_detach(gpib_board_t *board)
 	mutex_unlock(&ni_usb_hotplug_lock);
 }
 
-gpib_interface_t ni_usb_gpib_interface = {
-name: "ni_usb_b",
-attach : ni_usb_attach,
-detach : ni_usb_detach,
-read : ni_usb_read,
-write : ni_usb_write,
-command : ni_usb_command,
-take_control : ni_usb_take_control,
-go_to_standby : ni_usb_go_to_standby,
-request_system_control : ni_usb_request_system_control,
-interface_clear : ni_usb_interface_clear,
-remote_enable : ni_usb_remote_enable,
-enable_eos : ni_usb_enable_eos,
-disable_eos : ni_usb_disable_eos,
-parallel_poll : ni_usb_parallel_poll,
-parallel_poll_configure : ni_usb_parallel_poll_configure,
-parallel_poll_response : ni_usb_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : ni_usb_line_status,
-update_status : ni_usb_update_status,
-primary_address : ni_usb_primary_address,
-secondary_address : ni_usb_secondary_address,
-serial_poll_response : ni_usb_serial_poll_response,
-serial_poll_status : ni_usb_serial_poll_status,
-t1_delay : ni_usb_t1_delay,
-return_to_local : ni_usb_return_to_local,
-skip_check_for_command_acceptors : 1
+static gpib_interface_t ni_usb_gpib_interface = {
+	.name = "ni_usb_b",
+	.attach = ni_usb_attach,
+	.detach = ni_usb_detach,
+	.read = ni_usb_read,
+	.write = ni_usb_write,
+	.command = ni_usb_command,
+	.take_control = ni_usb_take_control,
+	.go_to_standby = ni_usb_go_to_standby,
+	.request_system_control = ni_usb_request_system_control,
+	.interface_clear = ni_usb_interface_clear,
+	.remote_enable = ni_usb_remote_enable,
+	.enable_eos = ni_usb_enable_eos,
+	.disable_eos = ni_usb_disable_eos,
+	.parallel_poll = ni_usb_parallel_poll,
+	.parallel_poll_configure = ni_usb_parallel_poll_configure,
+	.parallel_poll_response = ni_usb_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = ni_usb_line_status,
+	.update_status = ni_usb_update_status,
+	.primary_address = ni_usb_primary_address,
+	.secondary_address = ni_usb_secondary_address,
+	.serial_poll_response = ni_usb_serial_poll_response,
+	.serial_poll_status = ni_usb_serial_poll_status,
+	.t1_delay = ni_usb_t1_delay,
+	.return_to_local = ni_usb_return_to_local,
+	.skip_check_for_command_acceptors = 1
 };
 
 // Table with the USB-devices: just now only testing IDs
@@ -2619,12 +2621,23 @@ static struct usb_driver ni_usb_bus_driver = {
 static int __init ni_usb_init_module(void)
 {
 	int i;
+	int ret;
 
 	pr_info("ni_usb_gpib driver loading\n");
 	for (i = 0; i < MAX_NUM_NI_USB_INTERFACES; i++)
 		ni_usb_driver_interfaces[i] = NULL;
-	usb_register(&ni_usb_bus_driver);
-	gpib_register_driver(&ni_usb_gpib_interface, THIS_MODULE);
+
+	ret = usb_register(&ni_usb_bus_driver);
+	if (ret) {
+		pr_err("ni_usb_gpib: usb_register failed: error = %d\n", ret);
+		return ret;
+	}
+
+	ret = gpib_register_driver(&ni_usb_gpib_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("ni_usb_gpib: gpib_register_driver failed: error = %d\n", ret);
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/drivers/staging/gpib/ni_usb/ni_usb_gpib.h b/drivers/staging/gpib/ni_usb/ni_usb_gpib.h
index 9b21dfa0f3f6..4b297db09a9b 100644
--- a/drivers/staging/gpib/ni_usb/ni_usb_gpib.h
+++ b/drivers/staging/gpib/ni_usb/ni_usb_gpib.h
@@ -56,7 +56,7 @@ enum hs_plus_endpoint_addresses {
 };
 
 struct ni_usb_urb_ctx {
-	struct semaphore complete;
+	struct completion complete;
 	unsigned timed_out : 1;
 };
 
diff --git a/drivers/staging/gpib/pc2/pc2_gpib.c b/drivers/staging/gpib/pc2/pc2_gpib.c
index d22af25125b1..c0b07cb63d9a 100644
--- a/drivers/staging/gpib/pc2/pc2_gpib.c
+++ b/drivers/staging/gpib/pc2/pc2_gpib.c
@@ -238,116 +238,116 @@ static void pc2_return_to_local(gpib_board_t *board)
 	nec7210_return_to_local(board, &priv->nec7210_priv);
 }
 
-gpib_interface_t pc2_interface = {
-name:	"pcII",
-attach :	pc2_attach,
-detach :	pc2_detach,
-read :	pc2_read,
-write :	pc2_write,
-command :	pc2_command,
-take_control :	pc2_take_control,
-go_to_standby :	pc2_go_to_standby,
-request_system_control :	pc2_request_system_control,
-interface_clear :	pc2_interface_clear,
-remote_enable :	pc2_remote_enable,
-enable_eos :	pc2_enable_eos,
-disable_eos :	pc2_disable_eos,
-parallel_poll :	pc2_parallel_poll,
-parallel_poll_configure :	pc2_parallel_poll_configure,
-parallel_poll_response :	pc2_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status :	NULL,
-update_status :	pc2_update_status,
-primary_address :	pc2_primary_address,
-secondary_address :	pc2_secondary_address,
-serial_poll_response :	pc2_serial_poll_response,
-serial_poll_status :	pc2_serial_poll_status,
-t1_delay : pc2_t1_delay,
-return_to_local : pc2_return_to_local,
+static gpib_interface_t pc2_interface = {
+	.name =	"pcII",
+	.attach =	pc2_attach,
+	.detach =	pc2_detach,
+	.read =	pc2_read,
+	.write =	pc2_write,
+	.command =	pc2_command,
+	.take_control =	pc2_take_control,
+	.go_to_standby =	pc2_go_to_standby,
+	.request_system_control =	pc2_request_system_control,
+	.interface_clear =	pc2_interface_clear,
+	.remote_enable =	pc2_remote_enable,
+	.enable_eos =	pc2_enable_eos,
+	.disable_eos =	pc2_disable_eos,
+	.parallel_poll =	pc2_parallel_poll,
+	.parallel_poll_configure =	pc2_parallel_poll_configure,
+	.parallel_poll_response =	pc2_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status =	NULL,
+	.update_status =	pc2_update_status,
+	.primary_address =	pc2_primary_address,
+	.secondary_address =	pc2_secondary_address,
+	.serial_poll_response =	pc2_serial_poll_response,
+	.serial_poll_status =	pc2_serial_poll_status,
+	.t1_delay = pc2_t1_delay,
+	.return_to_local = pc2_return_to_local,
 };
 
-gpib_interface_t pc2a_interface = {
-name:	"pcIIa",
-attach :	pc2a_attach,
-detach :	pc2a_detach,
-read :	pc2_read,
-write :	pc2_write,
-command :	pc2_command,
-take_control :	pc2_take_control,
-go_to_standby :	pc2_go_to_standby,
-request_system_control :	pc2_request_system_control,
-interface_clear :	pc2_interface_clear,
-remote_enable :	pc2_remote_enable,
-enable_eos :	pc2_enable_eos,
-disable_eos :	pc2_disable_eos,
-parallel_poll :	pc2_parallel_poll,
-parallel_poll_configure :	pc2_parallel_poll_configure,
-parallel_poll_response :	pc2_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status :	NULL,
-update_status :	pc2_update_status,
-primary_address :	pc2_primary_address,
-secondary_address :	pc2_secondary_address,
-serial_poll_response :	pc2_serial_poll_response,
-serial_poll_status :	pc2_serial_poll_status,
-t1_delay : pc2_t1_delay,
-return_to_local : pc2_return_to_local,
+static gpib_interface_t pc2a_interface = {
+	.name =	"pcIIa",
+	.attach =	pc2a_attach,
+	.detach =	pc2a_detach,
+	.read =	pc2_read,
+	.write =	pc2_write,
+	.command =	pc2_command,
+	.take_control =	pc2_take_control,
+	.go_to_standby =	pc2_go_to_standby,
+	.request_system_control =	pc2_request_system_control,
+	.interface_clear =	pc2_interface_clear,
+	.remote_enable =	pc2_remote_enable,
+	.enable_eos =	pc2_enable_eos,
+	.disable_eos =	pc2_disable_eos,
+	.parallel_poll =	pc2_parallel_poll,
+	.parallel_poll_configure =	pc2_parallel_poll_configure,
+	.parallel_poll_response =	pc2_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status =	NULL,
+	.update_status =	pc2_update_status,
+	.primary_address =	pc2_primary_address,
+	.secondary_address =	pc2_secondary_address,
+	.serial_poll_response =	pc2_serial_poll_response,
+	.serial_poll_status =	pc2_serial_poll_status,
+	.t1_delay = pc2_t1_delay,
+	.return_to_local = pc2_return_to_local,
 };
 
-gpib_interface_t pc2a_cb7210_interface = {
-name:	"pcIIa_cb7210",
-attach :	pc2a_cb7210_attach,
-detach :	pc2a_detach,
-read :	pc2_read,
-write :	pc2_write,
-command :	pc2_command,
-take_control :	pc2_take_control,
-go_to_standby :	pc2_go_to_standby,
-request_system_control :	pc2_request_system_control,
-interface_clear :	pc2_interface_clear,
-remote_enable :	pc2_remote_enable,
-enable_eos :	pc2_enable_eos,
-disable_eos :	pc2_disable_eos,
-parallel_poll :	pc2_parallel_poll,
-parallel_poll_configure :	pc2_parallel_poll_configure,
-parallel_poll_response :	pc2_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status :	NULL, //XXX
-update_status :	pc2_update_status,
-primary_address :	pc2_primary_address,
-secondary_address :	pc2_secondary_address,
-serial_poll_response :	pc2_serial_poll_response,
-serial_poll_status :	pc2_serial_poll_status,
-t1_delay : pc2_t1_delay,
-return_to_local : pc2_return_to_local,
+static gpib_interface_t pc2a_cb7210_interface = {
+	.name =	"pcIIa_cb7210",
+	.attach =	pc2a_cb7210_attach,
+	.detach =	pc2a_detach,
+	.read =	pc2_read,
+	.write =	pc2_write,
+	.command =	pc2_command,
+	.take_control =	pc2_take_control,
+	.go_to_standby =	pc2_go_to_standby,
+	.request_system_control =	pc2_request_system_control,
+	.interface_clear =	pc2_interface_clear,
+	.remote_enable =	pc2_remote_enable,
+	.enable_eos =	pc2_enable_eos,
+	.disable_eos =	pc2_disable_eos,
+	.parallel_poll =	pc2_parallel_poll,
+	.parallel_poll_configure =	pc2_parallel_poll_configure,
+	.parallel_poll_response =	pc2_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status =	NULL, //XXX
+	.update_status =	pc2_update_status,
+	.primary_address =	pc2_primary_address,
+	.secondary_address =	pc2_secondary_address,
+	.serial_poll_response =	pc2_serial_poll_response,
+	.serial_poll_status =	pc2_serial_poll_status,
+	.t1_delay = pc2_t1_delay,
+	.return_to_local = pc2_return_to_local,
 };
 
-gpib_interface_t pc2_2a_interface = {
-name:	"pcII_IIa",
-attach :	pc2_2a_attach,
-detach :	pc2_2a_detach,
-read :	pc2_read,
-write :	pc2_write,
-command :	pc2_command,
-take_control :	pc2_take_control,
-go_to_standby :	pc2_go_to_standby,
-request_system_control :	pc2_request_system_control,
-interface_clear :	pc2_interface_clear,
-remote_enable :	pc2_remote_enable,
-enable_eos :	pc2_enable_eos,
-disable_eos :	pc2_disable_eos,
-parallel_poll :	pc2_parallel_poll,
-parallel_poll_configure :	pc2_parallel_poll_configure,
-parallel_poll_response :	pc2_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status :	NULL,
-update_status :	pc2_update_status,
-primary_address :	pc2_primary_address,
-secondary_address :	pc2_secondary_address,
-serial_poll_response :	pc2_serial_poll_response,
-serial_poll_status :	pc2_serial_poll_status,
-t1_delay : pc2_t1_delay,
-return_to_local : pc2_return_to_local,
+static gpib_interface_t pc2_2a_interface = {
+	.name =	"pcII_IIa",
+	.attach =	pc2_2a_attach,
+	.detach =	pc2_2a_detach,
+	.read =	pc2_read,
+	.write =	pc2_write,
+	.command =	pc2_command,
+	.take_control =	pc2_take_control,
+	.go_to_standby =	pc2_go_to_standby,
+	.request_system_control =	pc2_request_system_control,
+	.interface_clear =	pc2_interface_clear,
+	.remote_enable =	pc2_remote_enable,
+	.enable_eos =	pc2_enable_eos,
+	.disable_eos =	pc2_disable_eos,
+	.parallel_poll =	pc2_parallel_poll,
+	.parallel_poll_configure =	pc2_parallel_poll_configure,
+	.parallel_poll_response =	pc2_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status =	NULL,
+	.update_status =	pc2_update_status,
+	.primary_address =	pc2_primary_address,
+	.secondary_address =	pc2_secondary_address,
+	.serial_poll_response =	pc2_serial_poll_response,
+	.serial_poll_status =	pc2_serial_poll_status,
+	.t1_delay = pc2_t1_delay,
+	.return_to_local = pc2_return_to_local,
 };
 
 static int allocate_private(gpib_board_t *board)
@@ -426,7 +426,7 @@ int pc2_attach(gpib_board_t *board, const gpib_board_config_t *config)
 	nec_priv = &pc2_priv->nec7210_priv;
 	nec_priv->offset = pc2_reg_offset;
 
-	if (request_region(config->ibbase, pc2_iosize, "pc2") == 0) {
+	if (!request_region(config->ibbase, pc2_iosize, "pc2")) {
 		pr_err("gpib: ioports are already in use\n");
 		return -1;
 	}
@@ -635,12 +635,42 @@ void pc2_2a_detach(gpib_board_t *board)
 
 static int __init pc2_init_module(void)
 {
-	gpib_register_driver(&pc2_interface, THIS_MODULE);
-	gpib_register_driver(&pc2a_interface, THIS_MODULE);
-	gpib_register_driver(&pc2a_cb7210_interface, THIS_MODULE);
-	gpib_register_driver(&pc2_2a_interface, THIS_MODULE);
+	int ret;
+
+	ret = gpib_register_driver(&pc2_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret);
+		return ret;
+	}
+
+	ret = gpib_register_driver(&pc2a_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pc2a;
+	}
+
+	ret = gpib_register_driver(&pc2a_cb7210_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_cb7210;
+	}
+
+	ret = gpib_register_driver(&pc2_2a_interface, THIS_MODULE);
+	if (ret) {
+		pr_err("pc2_gpib: gpib_register_driver failed: error = %d\n", ret);
+		goto err_pc2_2a;
+	}
 
 	return 0;
+
+err_pc2_2a:
+	gpib_unregister_driver(&pc2a_cb7210_interface);
+err_cb7210:
+	gpib_unregister_driver(&pc2a_interface);
+err_pc2a:
+	gpib_unregister_driver(&pc2_interface);
+
+	return ret;
 }
 
 static void __exit pc2_exit_module(void)
diff --git a/drivers/staging/gpib/tnt4882/mite.c b/drivers/staging/gpib/tnt4882/mite.c
index 4bd352967616..ea64dde46bcb 100644
--- a/drivers/staging/gpib/tnt4882/mite.c
+++ b/drivers/staging/gpib/tnt4882/mite.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2
+// SPDX-License-Identifier: GPL-2.0-only
 
 /*
  *	Hardware driver for NI Mite PCI interface chip,
diff --git a/drivers/staging/gpib/tnt4882/mite.h b/drivers/staging/gpib/tnt4882/mite.h
index edb873435b51..522d6b56cb7d 100644
--- a/drivers/staging/gpib/tnt4882/mite.h
+++ b/drivers/staging/gpib/tnt4882/mite.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2 */
+/* SPDX-License-Identifier: GPL-2.0-only */
 
 /*
  *   Hardware driver for NI Mite PCI interface chip
diff --git a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c
index ce91c3eb768c..b39ab2abe495 100644
--- a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c
+++ b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c
@@ -116,7 +116,7 @@ static inline void tnt_paged_writeb(struct tnt4882_priv *priv, unsigned int valu
 /* readb/writeb wrappers */
 static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long offset)
 {
-	void *address = priv->nec7210_priv.mmiobase + offset;
+	void __iomem *address = priv->nec7210_priv.mmiobase + offset;
 	unsigned long flags;
 	unsigned short retval;
 	spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock;
@@ -154,7 +154,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long
 
 static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, unsigned long offset)
 {
-	void *address = priv->nec7210_priv.mmiobase + offset;
+	void __iomem *address = priv->nec7210_priv.mmiobase + offset;
 	unsigned long flags;
 	spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock;
 
@@ -890,285 +890,285 @@ void tnt4882_return_to_local(gpib_board_t *board)
 	nec7210_return_to_local(board, &priv->nec7210_priv);
 }
 
-gpib_interface_t ni_pci_interface = {
-name: "ni_pci",
-attach :  ni_pci_attach,
-detach :  ni_pci_detach,
-read :  tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response2 : tnt4882_serial_poll_response2,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_pci_interface = {
+	.name = "ni_pci",
+	.attach = ni_pci_attach,
+	.detach = ni_pci_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response2 = tnt4882_serial_poll_response2,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_pci_accel_interface = {
-name: "ni_pci_accel",
-attach : ni_pci_attach,
-detach : ni_pci_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response2 : tnt4882_serial_poll_response2,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_pci_accel_interface = {
+	.name = "ni_pci_accel",
+	.attach = ni_pci_attach,
+	.detach = ni_pci_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response2 = tnt4882_serial_poll_response2,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_isa_interface = {
-name: "ni_isa",
-attach : ni_tnt_isa_attach,
-detach : ni_isa_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response2 : tnt4882_serial_poll_response2,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_isa_interface = {
+	.name = "ni_isa",
+	.attach = ni_tnt_isa_attach,
+	.detach = ni_isa_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response2 = tnt4882_serial_poll_response2,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_nat4882_isa_interface = {
-name: "ni_nat4882_isa",
-attach : ni_nat4882_isa_attach,
-detach : ni_isa_detach,
-read : tnt4882_read,
-write : tnt4882_write,
-command : tnt4882_command_unaccel,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response2 : tnt4882_serial_poll_response2,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_nat4882_isa_interface = {
+	.name = "ni_nat4882_isa",
+	.attach = ni_nat4882_isa_attach,
+	.detach = ni_isa_detach,
+	.read = tnt4882_read,
+	.write = tnt4882_write,
+	.command = tnt4882_command_unaccel,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response2 = tnt4882_serial_poll_response2,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_nec_isa_interface = {
-name: "ni_nec_isa",
-attach : ni_nec_isa_attach,
-detach : ni_isa_detach,
-read : tnt4882_read,
-write : tnt4882_write,
-command : tnt4882_command_unaccel,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : NULL,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response : tnt4882_serial_poll_response,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_nec_isa_interface = {
+	.name = "ni_nec_isa",
+	.attach = ni_nec_isa_attach,
+	.detach = ni_isa_detach,
+	.read = tnt4882_read,
+	.write = tnt4882_write,
+	.command = tnt4882_command_unaccel,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = NULL,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response = tnt4882_serial_poll_response,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_isa_accel_interface = {
-name: "ni_isa_accel",
-attach : ni_tnt_isa_attach,
-detach : ni_isa_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response2 : tnt4882_serial_poll_response2,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_isa_accel_interface = {
+	.name = "ni_isa_accel",
+	.attach = ni_tnt_isa_attach,
+	.detach = ni_isa_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response2 = tnt4882_serial_poll_response2,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_nat4882_isa_accel_interface = {
-name: "ni_nat4882_isa_accel",
-attach : ni_nat4882_isa_attach,
-detach : ni_isa_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command_unaccel,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response2 : tnt4882_serial_poll_response2,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_nat4882_isa_accel_interface = {
+	.name = "ni_nat4882_isa_accel",
+	.attach = ni_nat4882_isa_attach,
+	.detach = ni_isa_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command_unaccel,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response2 = tnt4882_serial_poll_response2,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_nec_isa_accel_interface = {
-name: "ni_nec_isa_accel",
-attach : ni_nec_isa_attach,
-detach : ni_isa_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command_unaccel,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : NULL,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response : tnt4882_serial_poll_response,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_nec_isa_accel_interface = {
+	.name = "ni_nec_isa_accel",
+	.attach = ni_nec_isa_attach,
+	.detach = ni_isa_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command_unaccel,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = NULL,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response = tnt4882_serial_poll_response,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
 #ifdef GPIB_PCMCIA
-gpib_interface_t ni_pcmcia_interface = {
-name: "ni_pcmcia",
-attach : ni_pcmcia_attach,
-detach : ni_pcmcia_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response : tnt4882_serial_poll_response,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_pcmcia_interface = {
+	.name = "ni_pcmcia",
+	.attach = ni_pcmcia_attach,
+	.detach = ni_pcmcia_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response = tnt4882_serial_poll_response,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 
-gpib_interface_t ni_pcmcia_accel_interface = {
-name: "ni_pcmcia_accel",
-attach : ni_pcmcia_attach,
-detach : ni_pcmcia_detach,
-read : tnt4882_accel_read,
-write : tnt4882_accel_write,
-command : tnt4882_command,
-take_control : tnt4882_take_control,
-go_to_standby : tnt4882_go_to_standby,
-request_system_control : tnt4882_request_system_control,
-interface_clear : tnt4882_interface_clear,
-remote_enable : tnt4882_remote_enable,
-enable_eos : tnt4882_enable_eos,
-disable_eos : tnt4882_disable_eos,
-parallel_poll : tnt4882_parallel_poll,
-parallel_poll_configure : tnt4882_parallel_poll_configure,
-parallel_poll_response : tnt4882_parallel_poll_response,
-local_parallel_poll_mode : NULL, // XXX
-line_status : tnt4882_line_status,
-update_status : tnt4882_update_status,
-primary_address : tnt4882_primary_address,
-secondary_address : tnt4882_secondary_address,
-serial_poll_response : tnt4882_serial_poll_response,
-serial_poll_status : tnt4882_serial_poll_status,
-t1_delay : tnt4882_t1_delay,
-return_to_local : tnt4882_return_to_local,
+static gpib_interface_t ni_pcmcia_accel_interface = {
+	.name = "ni_pcmcia_accel",
+	.attach = ni_pcmcia_attach,
+	.detach = ni_pcmcia_detach,
+	.read = tnt4882_accel_read,
+	.write = tnt4882_accel_write,
+	.command = tnt4882_command,
+	.take_control = tnt4882_take_control,
+	.go_to_standby = tnt4882_go_to_standby,
+	.request_system_control = tnt4882_request_system_control,
+	.interface_clear = tnt4882_interface_clear,
+	.remote_enable = tnt4882_remote_enable,
+	.enable_eos = tnt4882_enable_eos,
+	.disable_eos = tnt4882_disable_eos,
+	.parallel_poll = tnt4882_parallel_poll,
+	.parallel_poll_configure = tnt4882_parallel_poll_configure,
+	.parallel_poll_response = tnt4882_parallel_poll_response,
+	.local_parallel_poll_mode = NULL, // XXX
+	.line_status = tnt4882_line_status,
+	.update_status = tnt4882_update_status,
+	.primary_address = tnt4882_primary_address,
+	.secondary_address = tnt4882_secondary_address,
+	.serial_poll_response = tnt4882_serial_poll_response,
+	.serial_poll_status = tnt4882_serial_poll_status,
+	.t1_delay = tnt4882_t1_delay,
+	.return_to_local = tnt4882_return_to_local,
 };
 #endif
 
@@ -1516,29 +1516,109 @@ static int __init tnt4882_init_module(void)
 
 	result = pci_register_driver(&tnt4882_pci_driver);
 	if (result) {
-		pr_err("tnt4882: pci_driver_register failed!\n");
+		pr_err("tnt4882_gpib: pci_register_driver failed: error = %d\n", result);
 		return result;
 	}
 
-	gpib_register_driver(&ni_isa_interface, THIS_MODULE);
-	gpib_register_driver(&ni_isa_accel_interface, THIS_MODULE);
-	gpib_register_driver(&ni_nat4882_isa_interface, THIS_MODULE);
-	gpib_register_driver(&ni_nat4882_isa_accel_interface, THIS_MODULE);
-	gpib_register_driver(&ni_nec_isa_interface, THIS_MODULE);
-	gpib_register_driver(&ni_nec_isa_accel_interface, THIS_MODULE);
-	gpib_register_driver(&ni_pci_interface, THIS_MODULE);
-	gpib_register_driver(&ni_pci_accel_interface, THIS_MODULE);
+	result = gpib_register_driver(&ni_isa_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_isa;
+	}
+
+	result = gpib_register_driver(&ni_isa_accel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_isa_accel;
+	}
+
+	result = gpib_register_driver(&ni_nat4882_isa_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_nat4882_isa;
+	}
+
+	result = gpib_register_driver(&ni_nat4882_isa_accel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_nat4882_isa_accel;
+	}
+
+	result = gpib_register_driver(&ni_nec_isa_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_nec_isa;
+	}
+
+	result = gpib_register_driver(&ni_nec_isa_accel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_nec_isa_accel;
+	}
+
+	result = gpib_register_driver(&ni_pci_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_pci;
+	}
+
+	result = gpib_register_driver(&ni_pci_accel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_pci_accel;
+	}
+
 #ifdef GPIB_PCMCIA
-	gpib_register_driver(&ni_pcmcia_interface, THIS_MODULE);
-	gpib_register_driver(&ni_pcmcia_accel_interface, THIS_MODULE);
-	if (init_ni_gpib_cs() < 0)
-		return -1;
+	result = gpib_register_driver(&ni_pcmcia_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_pcmcia;
+	}
+
+	result = gpib_register_driver(&ni_pcmcia_accel_interface, THIS_MODULE);
+	if (result) {
+		pr_err("tnt4882_gpib: gpib_register_driver failed: error = %d\n", result);
+		goto err_pcmcia_accel;
+	}
+
+	result = init_ni_gpib_cs();
+	if (result) {
+		pr_err("tnt4882_gpib: pcmcia_register_driver failed: error = %d\n", result);
+		goto err_pcmcia_driver;
+	}
 #endif
 
 	mite_init();
 	mite_list_devices();
 
 	return 0;
+
+#ifdef GPIB_PCMCIA
+err_pcmcia_driver:
+	gpib_unregister_driver(&ni_pcmcia_accel_interface);
+err_pcmcia_accel:
+	gpib_unregister_driver(&ni_pcmcia_interface);
+err_pcmcia:
+#endif
+	gpib_unregister_driver(&ni_pci_accel_interface);
+err_pci_accel:
+	gpib_unregister_driver(&ni_pci_interface);
+err_pci:
+	gpib_unregister_driver(&ni_nec_isa_accel_interface);
+err_nec_isa_accel:
+	gpib_unregister_driver(&ni_nec_isa_interface);
+err_nec_isa:
+	gpib_unregister_driver(&ni_nat4882_isa_accel_interface);
+err_nat4882_isa_accel:
+	gpib_unregister_driver(&ni_nat4882_isa_interface);
+err_nat4882_isa:
+	gpib_unregister_driver(&ni_isa_accel_interface);
+err_isa_accel:
+	gpib_unregister_driver(&ni_isa_interface);
+err_isa:
+	pci_unregister_driver(&tnt4882_pci_driver);
+
+	return result;
 }
 
 static void __exit tnt4882_exit_module(void)
@@ -1816,8 +1896,8 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config)
 	nec_priv->offset = atgpib_reg_offset;
 
 	DEBUG(0, "ioport1 window attributes: 0x%lx\n", curr_dev->resource[0]->flags);
-	if (request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]),
-			   "tnt4882") == 0) {
+	if (!request_region(curr_dev->resource[0]->start, resource_size(curr_dev->resource[0]),
+			    "tnt4882")) {
 		pr_err("gpib: ioports starting at 0x%lx are already in use\n",
 		       (unsigned long)curr_dev->resource[0]->start);
 		return -EIO;
diff --git a/drivers/staging/greybus/camera.c b/drivers/staging/greybus/camera.c
index ca71023df447..5d80ace41d8e 100644
--- a/drivers/staging/greybus/camera.c
+++ b/drivers/staging/greybus/camera.c
@@ -1128,18 +1128,7 @@ done:
 
 static int gb_camera_debugfs_open(struct inode *inode, struct file *file)
 {
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(gb_camera_debugfs_entries); ++i) {
-		const struct gb_camera_debugfs_entry *entry =
-			&gb_camera_debugfs_entries[i];
-
-		if (!strcmp(file->f_path.dentry->d_iname, entry->name)) {
-			file->private_data = (void *)entry;
-			break;
-		}
-	}
-
+	file->private_data = (void *)debugfs_get_aux(file);
 	return 0;
 }
 
@@ -1175,8 +1164,8 @@ static int gb_camera_debugfs_init(struct gb_camera *gcam)
 
 		gcam->debugfs.buffers[i].length = 0;
 
-		debugfs_create_file(entry->name, entry->mask,
-				    gcam->debugfs.root, gcam,
+		debugfs_create_file_aux(entry->name, entry->mask,
+				    gcam->debugfs.root, gcam, entry,
 				    &gb_camera_debugfs_ops);
 	}
 
diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
index 07ed33464d71..224ca8d42721 100644
--- a/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
+++ b/drivers/staging/media/atomisp/pci/hmm/hmm_bo.c
@@ -624,10 +624,10 @@ static int alloc_private_pages(struct hmm_buffer_object *bo)
 	const gfp_t gfp = __GFP_NOWARN | __GFP_RECLAIM | __GFP_FS;
 	int ret;
 
-	ret = alloc_pages_bulk_array(gfp, bo->pgnr, bo->pages);
+	ret = alloc_pages_bulk(gfp, bo->pgnr, bo->pages);
 	if (ret != bo->pgnr) {
 		free_pages_bulk_array(ret, bo->pages);
-		dev_err(atomisp_dev, "alloc_pages_bulk_array() failed\n");
+		dev_err(atomisp_dev, "alloc_pages_bulk() failed\n");
 		return -ENOMEM;
 	}
 
diff --git a/drivers/staging/rtl8723bs/Makefile b/drivers/staging/rtl8723bs/Makefile
index ba200ee669f3..8560b84a3146 100644
--- a/drivers/staging/rtl8723bs/Makefile
+++ b/drivers/staging/rtl8723bs/Makefile
@@ -48,7 +48,6 @@ r8723bs-y = \
 		hal/HalHWImg8723B_RF.o \
 		hal/HalPhyRf_8723B.o \
 		os_dep/ioctl_cfg80211.o \
-		os_dep/ioctl_linux.o \
 		os_dep/mlme_linux.o \
 		os_dep/osdep_service.o \
 		os_dep/os_intfs.o \
diff --git a/drivers/staging/rtl8723bs/core/rtw_io.c b/drivers/staging/rtl8723bs/core/rtw_io.c
index fcda9db6ebb5..79d543d88278 100644
--- a/drivers/staging/rtl8723bs/core/rtw_io.c
+++ b/drivers/staging/rtl8723bs/core/rtw_io.c
@@ -141,12 +141,12 @@ int rtw_init_io_priv(struct adapter *padapter, void (*set_intf_ops)(struct adapt
 */
 int rtw_inc_and_chk_continual_io_error(struct dvobj_priv *dvobj)
 {
-	int ret = false;
-	int value = atomic_inc_return(&dvobj->continual_io_error);
-	if (value > MAX_CONTINUAL_IO_ERR)
-		ret = true;
+	int error_count = atomic_inc_return(&dvobj->continual_io_error);
 
-	return ret;
+	if (error_count > MAX_CONTINUAL_IO_ERR)
+		return true;
+
+	return false;
 }
 
 /*
diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c
index 317f3db19397..952ce6dd5af9 100644
--- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c
+++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c
@@ -4959,7 +4959,6 @@ void _linked_info_dump(struct adapter *padapter)
 					rtw_hal_get_def_var(padapter, HW_DEF_RA_INFO_DUMP, &i);
 			}
 		}
-		rtw_hal_set_def_var(padapter, HAL_DEF_DBG_RX_INFO_DUMP, NULL);
 	}
 }
 
diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c
index 699cff7b0ac9..297c93d65315 100644
--- a/drivers/staging/rtl8723bs/core/rtw_xmit.c
+++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c
@@ -1467,7 +1467,8 @@ struct xmit_buf *rtw_alloc_xmitbuf_ext(struct xmit_priv *pxmitpriv)
 		pxmitbuf->priv_data = NULL;
 
 		pxmitbuf->len = 0;
-		pxmitbuf->pdata = pxmitbuf->ptail = pxmitbuf->phead;
+		pxmitbuf->pdata = pxmitbuf->phead;
+		pxmitbuf->ptail = pxmitbuf->phead;
 		pxmitbuf->agg_num = 1;
 
 		if (pxmitbuf->sctx)
@@ -1526,7 +1527,8 @@ struct xmit_buf *rtw_alloc_xmitbuf(struct xmit_priv *pxmitpriv)
 		pxmitbuf->priv_data = NULL;
 
 		pxmitbuf->len = 0;
-		pxmitbuf->pdata = pxmitbuf->ptail = pxmitbuf->phead;
+		pxmitbuf->pdata = pxmitbuf->phead;
+		pxmitbuf->ptail = pxmitbuf->phead;
 		pxmitbuf->agg_num = 0;
 		pxmitbuf->pg_num = 0;
 
diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c
index 95fb38283c58..b41ec89932af 100644
--- a/drivers/staging/rtl8723bs/hal/hal_com.c
+++ b/drivers/staging/rtl8723bs/hal/hal_com.c
@@ -682,14 +682,6 @@ u8 SetHalDefVar(
 	u8 bResult = _SUCCESS;
 
 	switch (variable) {
-	case HAL_DEF_DBG_RX_INFO_DUMP:
-
-		if (odm->bLinked) {
-			#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA
-			rtw_dump_raw_rssi_info(adapter);
-			#endif
-		}
-		break;
 	case HW_DEF_ODM_DBG_FLAG:
 		ODM_CmnInfoUpdate(odm, ODM_CMNINFO_DBG_COMP, *((u64 *)value));
 		break;
@@ -879,53 +871,6 @@ void rtw_hal_check_rxfifo_full(struct adapter *adapter)
 	}
 }
 
-#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA
-void rtw_dump_raw_rssi_info(struct adapter *padapter)
-{
-	u8 isCCKrate, rf_path;
-	struct hal_com_data *pHalData =  GET_HAL_DATA(padapter);
-	struct rx_raw_rssi *psample_pkt_rssi = &padapter->recvpriv.raw_rssi_info;
-
-	isCCKrate = psample_pkt_rssi->data_rate <= DESC_RATE11M;
-
-	if (isCCKrate)
-		psample_pkt_rssi->mimo_signal_strength[0] = psample_pkt_rssi->pwdball;
-
-	for (rf_path = 0; rf_path < pHalData->NumTotalRFPath; rf_path++) {
-		if (!isCCKrate) {
-			netdev_dbg(padapter->pnetdev, ", rx_ofdm_pwr:%d(dBm), rx_ofdm_snr:%d(dB)\n",
-				   psample_pkt_rssi->ofdm_pwr[rf_path],
-				   psample_pkt_rssi->ofdm_snr[rf_path]);
-		}
-	}
-}
-
-void rtw_store_phy_info(struct adapter *padapter, union recv_frame *prframe)
-{
-	u8 isCCKrate, rf_path;
-	struct hal_com_data *pHalData =  GET_HAL_DATA(padapter);
-	struct rx_pkt_attrib *pattrib = &prframe->u.hdr.attrib;
-
-	struct odm_phy_info *pPhyInfo  = (PODM_PHY_INFO_T)(&pattrib->phy_info);
-	struct rx_raw_rssi *psample_pkt_rssi = &padapter->recvpriv.raw_rssi_info;
-
-	psample_pkt_rssi->data_rate = pattrib->data_rate;
-	isCCKrate = pattrib->data_rate <= DESC_RATE11M;
-
-	psample_pkt_rssi->pwdball = pPhyInfo->rx_pwd_ba11;
-	psample_pkt_rssi->pwr_all = pPhyInfo->recv_signal_power;
-
-	for (rf_path = 0; rf_path < pHalData->NumTotalRFPath; rf_path++) {
-		psample_pkt_rssi->mimo_signal_strength[rf_path] = pPhyInfo->rx_mimo_signal_strength[rf_path];
-		psample_pkt_rssi->mimo_signal_quality[rf_path] = pPhyInfo->rx_mimo_signal_quality[rf_path];
-		if (!isCCKrate) {
-			psample_pkt_rssi->ofdm_pwr[rf_path] = pPhyInfo->RxPwr[rf_path];
-			psample_pkt_rssi->ofdm_snr[rf_path] = pPhyInfo->RxSNR[rf_path];
-		}
-	}
-}
-#endif
-
 static u32 Array_kfreemap[] = {
 	0xf8, 0xe,
 	0xf6, 0xc,
diff --git a/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c b/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c
index 717faebf8aca..db3d7d72bffa 100644
--- a/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c
+++ b/drivers/staging/rtl8723bs/hal/rtl8723b_rxdesc.c
@@ -67,8 +67,4 @@ void rtl8723b_process_phy_info(struct adapter *padapter, void *prframe)
 	/*  Check EVM */
 	/*  */
 	process_link_qual(padapter,  precvframe);
-	#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA
-	rtw_store_phy_info(padapter, prframe);
-	#endif
-
 }
diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h
index 4db93484725f..258a74076dd9 100644
--- a/drivers/staging/rtl8723bs/include/hal_com.h
+++ b/drivers/staging/rtl8723bs/include/hal_com.h
@@ -149,11 +149,6 @@ bool eqNByte(u8 *str1, u8 *str2, u32 num);
 
 bool GetU1ByteIntegerFromStringInDecimal(char *str, u8 *in);
 
-#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA
-void rtw_store_phy_info(struct adapter *padapter, union recv_frame *prframe);
-void rtw_dump_raw_rssi_info(struct adapter *padapter);
-#endif
-
 #define		HWSET_MAX_SIZE			512
 
 void rtw_bb_rf_gain_offset(struct adapter *padapter);
diff --git a/drivers/staging/rtl8723bs/include/hal_intf.h b/drivers/staging/rtl8723bs/include/hal_intf.h
index 282e141616b0..85de862823c2 100644
--- a/drivers/staging/rtl8723bs/include/hal_intf.h
+++ b/drivers/staging/rtl8723bs/include/hal_intf.h
@@ -144,7 +144,6 @@ enum hal_def_variable {
 	HAL_DEF_PCI_AMD_L1_SUPPORT,
 	HAL_DEF_PCI_ASPM_OSC, /*  Support for ASPM OSC, added by Roger, 2013.03.27. */
 	HAL_DEF_MACID_SLEEP, /*  Support for MACID sleep */
-	HAL_DEF_DBG_RX_INFO_DUMP,
 };
 
 enum hal_odm_variable {
diff --git a/drivers/staging/rtl8723bs/include/osdep_intf.h b/drivers/staging/rtl8723bs/include/osdep_intf.h
index 215ece612f71..73199be78139 100644
--- a/drivers/staging/rtl8723bs/include/osdep_intf.h
+++ b/drivers/staging/rtl8723bs/include/osdep_intf.h
@@ -47,8 +47,6 @@ u32 rtw_start_drv_threads(struct adapter *padapter);
 void rtw_stop_drv_threads(struct adapter *padapter);
 void rtw_cancel_all_timer(struct adapter *padapter);
 
-int rtw_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
-
 int rtw_init_netdev_name(struct net_device *pnetdev, const char *ifname);
 struct net_device *rtw_init_netdev(struct adapter *padapter);
 void rtw_unregister_netdevs(struct dvobj_priv *dvobj);
diff --git a/drivers/staging/rtl8723bs/include/rtw_recv.h b/drivers/staging/rtl8723bs/include/rtw_recv.h
index 18dd1464e0c2..aa9f9d5ecd01 100644
--- a/drivers/staging/rtl8723bs/include/rtw_recv.h
+++ b/drivers/staging/rtl8723bs/include/rtw_recv.h
@@ -89,21 +89,6 @@ struct phy_info {
 	u8 btCoexPwrAdjust;
 };
 
-#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA
-struct rx_raw_rssi {
-	u8 data_rate;
-	u8 pwdball;
-	s8 pwr_all;
-
-	u8 mimo_signal_strength[4];/*  in 0~100 index */
-	u8 mimo_signal_quality[4];
-
-	s8 ofdm_pwr[4];
-	u8 ofdm_snr[4];
-
-};
-#endif
-
 struct rx_pkt_attrib	{
 	u16 pkt_len;
 	u8 physt;
@@ -221,9 +206,6 @@ struct recv_priv {
 	u8 signal_strength;
 	u8 signal_qual;
 	s8 rssi;	/* translate_percentage_to_dbm(ptarget_wlan->network.PhyInfo.SignalStrength); */
-	#ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA
-	struct rx_raw_rssi raw_rssi_info;
-	#endif
 	/* s8 rxpwdb; */
 	s16 noise;
 	/* int RxSNRdB[2]; */
diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c
deleted file mode 100644
index 793b051536f3..000000000000
--- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c
+++ /dev/null
@@ -1,1286 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/******************************************************************************
- *
- * Copyright(c) 2007 - 2012 Realtek Corporation. All rights reserved.
- *
- ******************************************************************************/
-
-#include <linux/etherdevice.h>
-#include <drv_types.h>
-#include <rtw_mp.h>
-#include <hal_btcoex.h>
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-
-#define RTL_IOCTL_WPA_SUPPLICANT	(SIOCIWFIRSTPRIV + 30)
-
-static int wpa_set_auth_algs(struct net_device *dev, u32 value)
-{
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	int ret = 0;
-
-	if ((value & IW_AUTH_ALG_SHARED_KEY) && (value & IW_AUTH_ALG_OPEN_SYSTEM)) {
-		padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-		padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeAutoSwitch;
-		padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_Auto;
-	} else if (value & IW_AUTH_ALG_SHARED_KEY)	{
-		padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-
-		padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeShared;
-		padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_Shared;
-	} else if (value & IW_AUTH_ALG_OPEN_SYSTEM) {
-		/* padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled; */
-		if (padapter->securitypriv.ndisauthtype < Ndis802_11AuthModeWPAPSK) {
-			padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeOpen;
-			padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_Open;
-		}
-	} else {
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-static int wpa_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len)
-{
-	int ret = 0;
-	u8 max_idx;
-	u32 wep_key_idx, wep_key_len, wep_total_len;
-	struct ndis_802_11_wep	 *pwep = NULL;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct security_priv *psecuritypriv = &padapter->securitypriv;
-
-	param->u.crypt.err = 0;
-	param->u.crypt.alg[IEEE_CRYPT_ALG_NAME_LEN - 1] = '\0';
-
-	if (param_len < (u32)((u8 *)param->u.crypt.key - (u8 *)param) + param->u.crypt.key_len) {
-		ret =  -EINVAL;
-		goto exit;
-	}
-
-	if (param->sta_addr[0] != 0xff || param->sta_addr[1] != 0xff ||
-	    param->sta_addr[2] != 0xff || param->sta_addr[3] != 0xff ||
-	    param->sta_addr[4] != 0xff || param->sta_addr[5] != 0xff) {
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	if (strcmp(param->u.crypt.alg, "WEP") == 0)
-		max_idx = WEP_KEYS - 1;
-	else
-		max_idx = BIP_MAX_KEYID;
-
-	if (param->u.crypt.idx > max_idx) {
-		netdev_err(dev, "Error crypt.idx %d > %d\n", param->u.crypt.idx, max_idx);
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	if (strcmp(param->u.crypt.alg, "WEP") == 0) {
-		padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-		padapter->securitypriv.dot11PrivacyAlgrthm = _WEP40_;
-		padapter->securitypriv.dot118021XGrpPrivacy = _WEP40_;
-
-		wep_key_idx = param->u.crypt.idx;
-		wep_key_len = param->u.crypt.key_len;
-
-		if (wep_key_len > 0) {
-			wep_key_len = wep_key_len <= 5 ? 5 : 13;
-			wep_total_len = wep_key_len + FIELD_OFFSET(struct ndis_802_11_wep, key_material);
-			/* Allocate a full structure to avoid potentially running off the end. */
-			pwep = kzalloc(sizeof(*pwep), GFP_KERNEL);
-			if (!pwep) {
-				ret = -ENOMEM;
-				goto exit;
-			}
-
-			pwep->key_length = wep_key_len;
-			pwep->length = wep_total_len;
-
-			if (wep_key_len == 13) {
-				padapter->securitypriv.dot11PrivacyAlgrthm = _WEP104_;
-				padapter->securitypriv.dot118021XGrpPrivacy = _WEP104_;
-			}
-		} else {
-			ret = -EINVAL;
-			goto exit;
-		}
-
-		pwep->key_index = wep_key_idx;
-		pwep->key_index |= 0x80000000;
-
-		memcpy(pwep->key_material,  param->u.crypt.key, pwep->key_length);
-
-		if (param->u.crypt.set_tx) {
-			if (rtw_set_802_11_add_wep(padapter, pwep) == (u8)_FAIL)
-				ret = -EOPNOTSUPP;
-		} else {
-			/* don't update "psecuritypriv->dot11PrivacyAlgrthm" and */
-			/* psecuritypriv->dot11PrivacyKeyIndex =keyid", but can rtw_set_key to fw/cam */
-
-			if (wep_key_idx >= WEP_KEYS) {
-				ret = -EOPNOTSUPP;
-				goto exit;
-			}
-
-			memcpy(&psecuritypriv->dot11DefKey[wep_key_idx].skey[0], pwep->key_material, pwep->key_length);
-			psecuritypriv->dot11DefKeylen[wep_key_idx] = pwep->key_length;
-			rtw_set_key(padapter, psecuritypriv, wep_key_idx, 0, true);
-		}
-
-		goto exit;
-	}
-
-	if (padapter->securitypriv.dot11AuthAlgrthm == dot11AuthAlgrthm_8021X) { /*  802_1x */
-		struct sta_info *psta, *pbcmc_sta;
-		struct sta_priv *pstapriv = &padapter->stapriv;
-
-		if (check_fwstate(pmlmepriv, WIFI_STATION_STATE | WIFI_MP_STATE) == true) { /* sta mode */
-			psta = rtw_get_stainfo(pstapriv, get_bssid(pmlmepriv));
-			if (psta) {
-				/* Jeff: don't disable ieee8021x_blocked while clearing key */
-				if (strcmp(param->u.crypt.alg, "none") != 0)
-					psta->ieee8021x_blocked = false;
-
-				if ((padapter->securitypriv.ndisencryptstatus == Ndis802_11Encryption2Enabled) ||
-				    (padapter->securitypriv.ndisencryptstatus ==  Ndis802_11Encryption3Enabled)) {
-					psta->dot118021XPrivacy = padapter->securitypriv.dot11PrivacyAlgrthm;
-				}
-
-				if (param->u.crypt.set_tx == 1) { /* pairwise key */
-					memcpy(psta->dot118021x_UncstKey.skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-
-					if (strcmp(param->u.crypt.alg, "TKIP") == 0) { /* set mic key */
-						memcpy(psta->dot11tkiptxmickey.skey, &param->u.crypt.key[16], 8);
-						memcpy(psta->dot11tkiprxmickey.skey, &param->u.crypt.key[24], 8);
-
-						padapter->securitypriv.busetkipkey = false;
-						/* _set_timer(&padapter->securitypriv.tkip_timer, 50); */
-					}
-
-					rtw_setstakey_cmd(padapter, psta, true, true);
-				} else { /* group key */
-					if (strcmp(param->u.crypt.alg, "TKIP") == 0 || strcmp(param->u.crypt.alg, "CCMP") == 0) {
-						memcpy(padapter->securitypriv.dot118021XGrpKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-						/* only TKIP group key need to install this */
-						if (param->u.crypt.key_len > 16) {
-							memcpy(padapter->securitypriv.dot118021XGrptxmickey[param->u.crypt.idx].skey, &param->u.crypt.key[16], 8);
-							memcpy(padapter->securitypriv.dot118021XGrprxmickey[param->u.crypt.idx].skey, &param->u.crypt.key[24], 8);
-						}
-						padapter->securitypriv.binstallGrpkey = true;
-
-						padapter->securitypriv.dot118021XGrpKeyid = param->u.crypt.idx;
-
-						rtw_set_key(padapter, &padapter->securitypriv, param->u.crypt.idx, 1, true);
-					} else if (strcmp(param->u.crypt.alg, "BIP") == 0) {
-						/* save the IGTK key, length 16 bytes */
-						memcpy(padapter->securitypriv.dot11wBIPKey[param->u.crypt.idx].skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-						padapter->securitypriv.dot11wBIPKeyid = param->u.crypt.idx;
-						padapter->securitypriv.binstallBIPkey = true;
-					}
-				}
-			}
-
-			pbcmc_sta = rtw_get_bcmc_stainfo(padapter);
-			if (pbcmc_sta) {
-				/* Jeff: don't disable ieee8021x_blocked while clearing key */
-				if (strcmp(param->u.crypt.alg, "none") != 0)
-					pbcmc_sta->ieee8021x_blocked = false;
-
-				if ((padapter->securitypriv.ndisencryptstatus == Ndis802_11Encryption2Enabled) ||
-				    (padapter->securitypriv.ndisencryptstatus ==  Ndis802_11Encryption3Enabled)) {
-					pbcmc_sta->dot118021XPrivacy = padapter->securitypriv.dot11PrivacyAlgrthm;
-				}
-			}
-		} else if (check_fwstate(pmlmepriv, WIFI_ADHOC_STATE)) {
-			/* adhoc mode */
-		}
-	}
-
-exit:
-
-	kfree(pwep);
-	return ret;
-}
-
-static int rtw_set_wpa_ie(struct adapter *padapter, char *pie, unsigned short ielen)
-{
-	u8 *buf = NULL;
-	int group_cipher = 0, pairwise_cipher = 0;
-	int ret = 0;
-	u8 null_addr[] = {0, 0, 0, 0, 0, 0};
-
-	if (ielen > MAX_WPA_IE_LEN || !pie) {
-		_clr_fwstate_(&padapter->mlmepriv, WIFI_UNDER_WPS);
-		if (!pie)
-			return ret;
-		else
-			return -EINVAL;
-	}
-
-	if (ielen) {
-		buf = rtw_zmalloc(ielen);
-		if (!buf) {
-			ret =  -ENOMEM;
-			goto exit;
-		}
-
-		memcpy(buf, pie, ielen);
-
-		if (ielen < RSN_HEADER_LEN) {
-			ret  = -1;
-			goto exit;
-		}
-
-		if (rtw_parse_wpa_ie(buf, ielen, &group_cipher, &pairwise_cipher, NULL) == _SUCCESS) {
-			padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_8021X;
-			padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPAPSK;
-			memcpy(padapter->securitypriv.supplicant_ie, &buf[0], ielen);
-		}
-
-		if (rtw_parse_wpa2_ie(buf, ielen, &group_cipher, &pairwise_cipher, NULL) == _SUCCESS) {
-			padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_8021X;
-			padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPA2PSK;
-			memcpy(padapter->securitypriv.supplicant_ie, &buf[0], ielen);
-		}
-
-		if (group_cipher == 0)
-			group_cipher = WPA_CIPHER_NONE;
-		if (pairwise_cipher == 0)
-			pairwise_cipher = WPA_CIPHER_NONE;
-
-		switch (group_cipher) {
-		case WPA_CIPHER_NONE:
-			padapter->securitypriv.dot118021XGrpPrivacy = _NO_PRIVACY_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled;
-			break;
-		case WPA_CIPHER_WEP40:
-			padapter->securitypriv.dot118021XGrpPrivacy = _WEP40_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-			break;
-		case WPA_CIPHER_TKIP:
-			padapter->securitypriv.dot118021XGrpPrivacy = _TKIP_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
-			break;
-		case WPA_CIPHER_CCMP:
-			padapter->securitypriv.dot118021XGrpPrivacy = _AES_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
-			break;
-		case WPA_CIPHER_WEP104:
-			padapter->securitypriv.dot118021XGrpPrivacy = _WEP104_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-			break;
-		}
-
-		switch (pairwise_cipher) {
-		case WPA_CIPHER_NONE:
-			padapter->securitypriv.dot11PrivacyAlgrthm = _NO_PRIVACY_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11EncryptionDisabled;
-			break;
-		case WPA_CIPHER_WEP40:
-			padapter->securitypriv.dot11PrivacyAlgrthm = _WEP40_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-			break;
-		case WPA_CIPHER_TKIP:
-			padapter->securitypriv.dot11PrivacyAlgrthm = _TKIP_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
-			break;
-		case WPA_CIPHER_CCMP:
-			padapter->securitypriv.dot11PrivacyAlgrthm = _AES_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
-			break;
-		case WPA_CIPHER_WEP104:
-			padapter->securitypriv.dot11PrivacyAlgrthm = _WEP104_;
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption1Enabled;
-			break;
-		}
-
-		_clr_fwstate_(&padapter->mlmepriv, WIFI_UNDER_WPS);
-		{/* set wps_ie */
-			u16 cnt = 0;
-			u8 eid, wps_oui[4] = {0x0, 0x50, 0xf2, 0x04};
-
-			while (cnt < ielen) {
-				eid = buf[cnt];
-
-				if ((eid == WLAN_EID_VENDOR_SPECIFIC) && (!memcmp(&buf[cnt + 2], wps_oui, 4))) {
-					padapter->securitypriv.wps_ie_len = ((buf[cnt + 1] + 2) < MAX_WPS_IE_LEN) ? (buf[cnt + 1] + 2) : MAX_WPS_IE_LEN;
-
-					memcpy(padapter->securitypriv.wps_ie, &buf[cnt], padapter->securitypriv.wps_ie_len);
-
-					set_fwstate(&padapter->mlmepriv, WIFI_UNDER_WPS);
-
-					cnt += buf[cnt + 1] + 2;
-
-					break;
-				} else {
-					cnt += buf[cnt + 1] + 2; /* goto next */
-				}
-			}
-		}
-	}
-
-	/* TKIP and AES disallow multicast packets until installing group key */
-	if (padapter->securitypriv.dot11PrivacyAlgrthm == _TKIP_ ||
-	    padapter->securitypriv.dot11PrivacyAlgrthm == _TKIP_WTMIC_ ||
-	    padapter->securitypriv.dot11PrivacyAlgrthm == _AES_)
-		/* WPS open need to enable multicast */
-		/*  check_fwstate(&padapter->mlmepriv, WIFI_UNDER_WPS) == true) */
-		rtw_hal_set_hwreg(padapter, HW_VAR_OFF_RCR_AM, null_addr);
-
-exit:
-
-	kfree(buf);
-
-	return ret;
-}
-
-static int wpa_set_param(struct net_device *dev, u8 name, u32 value)
-{
-	uint ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-
-	switch (name) {
-	case IEEE_PARAM_WPA_ENABLED:
-
-		padapter->securitypriv.dot11AuthAlgrthm = dot11AuthAlgrthm_8021X; /* 802.1x */
-
-		/* ret = ieee80211_wpa_enable(ieee, value); */
-
-		switch ((value) & 0xff) {
-		case 1: /* WPA */
-			padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPAPSK; /* WPA_PSK */
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption2Enabled;
-			break;
-		case 2: /* WPA2 */
-			padapter->securitypriv.ndisauthtype = Ndis802_11AuthModeWPA2PSK; /* WPA2_PSK */
-			padapter->securitypriv.ndisencryptstatus = Ndis802_11Encryption3Enabled;
-			break;
-		}
-
-		break;
-
-	case IEEE_PARAM_TKIP_COUNTERMEASURES:
-		/* ieee->tkip_countermeasures =value; */
-		break;
-
-	case IEEE_PARAM_DROP_UNENCRYPTED:
-	{
-		/* HACK:
-		 *
-		 * wpa_supplicant calls set_wpa_enabled when the driver
-		 * is loaded and unloaded, regardless of if WPA is being
-		 * used.  No other calls are made which can be used to
-		 * determine if encryption will be used or not prior to
-		 * association being expected.  If encryption is not being
-		 * used, drop_unencrypted is set to false, else true -- we
-		 * can use this to determine if the CAP_PRIVACY_ON bit should
-		 * be set.
-		 */
-		break;
-	}
-	case IEEE_PARAM_PRIVACY_INVOKED:
-
-		/* ieee->privacy_invoked =value; */
-
-		break;
-
-	case IEEE_PARAM_AUTH_ALGS:
-
-		ret = wpa_set_auth_algs(dev, value);
-
-		break;
-
-	case IEEE_PARAM_IEEE_802_1X:
-
-		/* ieee->ieee802_1x =value; */
-
-		break;
-
-	case IEEE_PARAM_WPAX_SELECT:
-
-		/*  added for WPA2 mixed mode */
-		/*
-		spin_lock_irqsave(&ieee->wpax_suitlist_lock, flags);
-		ieee->wpax_type_set = 1;
-		ieee->wpax_type_notify = value;
-		spin_unlock_irqrestore(&ieee->wpax_suitlist_lock, flags);
-		*/
-
-		break;
-
-	default:
-
-		ret = -EOPNOTSUPP;
-
-		break;
-	}
-
-	return ret;
-}
-
-static int wpa_mlme(struct net_device *dev, u32 command, u32 reason)
-{
-	int ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-
-	switch (command) {
-	case IEEE_MLME_STA_DEAUTH:
-
-		if (!rtw_set_802_11_disassociate(padapter))
-			ret = -1;
-
-		break;
-
-	case IEEE_MLME_STA_DISASSOC:
-
-		if (!rtw_set_802_11_disassociate(padapter))
-			ret = -1;
-
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	return ret;
-}
-
-static int wpa_supplicant_ioctl(struct net_device *dev, struct iw_point *p)
-{
-	struct ieee_param *param;
-	uint ret = 0;
-
-	/* down(&ieee->wx_sem); */
-
-	if (!p->pointer || p->length != sizeof(struct ieee_param))
-		return -EINVAL;
-
-	param = rtw_malloc(p->length);
-	if (!param)
-		return -ENOMEM;
-
-	if (copy_from_user(param, p->pointer, p->length)) {
-		kfree(param);
-		return -EFAULT;
-	}
-
-	switch (param->cmd) {
-	case IEEE_CMD_SET_WPA_PARAM:
-		ret = wpa_set_param(dev, param->u.wpa_param.name, param->u.wpa_param.value);
-		break;
-
-	case IEEE_CMD_SET_WPA_IE:
-		/* ret = wpa_set_wpa_ie(dev, param, p->length); */
-		ret =  rtw_set_wpa_ie(rtw_netdev_priv(dev), (char *)param->u.wpa_ie.data, (u16)param->u.wpa_ie.len);
-		break;
-
-	case IEEE_CMD_SET_ENCRYPTION:
-		ret = wpa_set_encryption(dev, param, p->length);
-		break;
-
-	case IEEE_CMD_MLME:
-		ret = wpa_mlme(dev, param->u.mlme.command, param->u.mlme.reason_code);
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	if (ret == 0 && copy_to_user(p->pointer, param, p->length))
-		ret = -EFAULT;
-
-	kfree(param);
-
-	/* up(&ieee->wx_sem); */
-	return ret;
-}
-
-static int rtw_set_encryption(struct net_device *dev, struct ieee_param *param, u32 param_len)
-{
-	int ret = 0;
-	u32 wep_key_idx, wep_key_len, wep_total_len;
-	struct ndis_802_11_wep	 *pwep = NULL;
-	struct sta_info *psta = NULL, *pbcmc_sta = NULL;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct security_priv *psecuritypriv = &padapter->securitypriv;
-	struct sta_priv *pstapriv = &padapter->stapriv;
-	char *txkey = padapter->securitypriv.dot118021XGrptxmickey[param->u.crypt.idx].skey;
-	char *rxkey = padapter->securitypriv.dot118021XGrprxmickey[param->u.crypt.idx].skey;
-	char *grpkey = psecuritypriv->dot118021XGrpKey[param->u.crypt.idx].skey;
-
-	param->u.crypt.err = 0;
-	param->u.crypt.alg[IEEE_CRYPT_ALG_NAME_LEN - 1] = '\0';
-
-	/* sizeof(struct ieee_param) = 64 bytes; */
-	/* if (param_len !=  (u32) ((u8 *) param->u.crypt.key - (u8 *) param) + param->u.crypt.key_len) */
-	if (param_len !=  sizeof(struct ieee_param) + param->u.crypt.key_len) {
-		ret =  -EINVAL;
-		goto exit;
-	}
-
-	if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff &&
-	    param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff &&
-	    param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) {
-		if (param->u.crypt.idx >= WEP_KEYS) {
-			ret = -EINVAL;
-			goto exit;
-		}
-	} else {
-		psta = rtw_get_stainfo(pstapriv, param->sta_addr);
-		if (!psta)
-			/* ret = -EINVAL; */
-			goto exit;
-	}
-
-	if (strcmp(param->u.crypt.alg, "none") == 0 && !psta) {
-		/* todo:clear default encryption keys */
-
-		psecuritypriv->dot11AuthAlgrthm = dot11AuthAlgrthm_Open;
-		psecuritypriv->ndisencryptstatus = Ndis802_11EncryptionDisabled;
-		psecuritypriv->dot11PrivacyAlgrthm = _NO_PRIVACY_;
-		psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_;
-
-		goto exit;
-	}
-
-	if (strcmp(param->u.crypt.alg, "WEP") == 0 && !psta) {
-		wep_key_idx = param->u.crypt.idx;
-		wep_key_len = param->u.crypt.key_len;
-
-		if ((wep_key_idx >= WEP_KEYS) || (wep_key_len <= 0)) {
-			ret = -EINVAL;
-			goto exit;
-		}
-
-		if (wep_key_len > 0) {
-			wep_key_len = wep_key_len <= 5 ? 5 : 13;
-			wep_total_len = wep_key_len + FIELD_OFFSET(struct ndis_802_11_wep, key_material);
-			/* Allocate a full structure to avoid potentially running off the end. */
-			pwep = kzalloc(sizeof(*pwep), GFP_KERNEL);
-			if (!pwep)
-				goto exit;
-
-			pwep->key_length = wep_key_len;
-			pwep->length = wep_total_len;
-		}
-
-		pwep->key_index = wep_key_idx;
-
-		memcpy(pwep->key_material,  param->u.crypt.key, pwep->key_length);
-
-		if (param->u.crypt.set_tx) {
-			psecuritypriv->dot11AuthAlgrthm = dot11AuthAlgrthm_Auto;
-			psecuritypriv->ndisencryptstatus = Ndis802_11Encryption1Enabled;
-			psecuritypriv->dot11PrivacyAlgrthm = _WEP40_;
-			psecuritypriv->dot118021XGrpPrivacy = _WEP40_;
-
-			if (pwep->key_length == 13) {
-				psecuritypriv->dot11PrivacyAlgrthm = _WEP104_;
-				psecuritypriv->dot118021XGrpPrivacy = _WEP104_;
-			}
-
-			psecuritypriv->dot11PrivacyKeyIndex = wep_key_idx;
-
-			memcpy(&psecuritypriv->dot11DefKey[wep_key_idx].skey[0], pwep->key_material, pwep->key_length);
-
-			psecuritypriv->dot11DefKeylen[wep_key_idx] = pwep->key_length;
-
-			rtw_ap_set_wep_key(padapter, pwep->key_material, pwep->key_length, wep_key_idx, 1);
-		} else {
-			/* don't update "psecuritypriv->dot11PrivacyAlgrthm" and */
-			/* psecuritypriv->dot11PrivacyKeyIndex =keyid", but can rtw_set_key to cam */
-
-			memcpy(&psecuritypriv->dot11DefKey[wep_key_idx].skey[0], pwep->key_material, pwep->key_length);
-
-			psecuritypriv->dot11DefKeylen[wep_key_idx] = pwep->key_length;
-
-			rtw_ap_set_wep_key(padapter, pwep->key_material, pwep->key_length, wep_key_idx, 0);
-		}
-
-		goto exit;
-	}
-
-	if (!psta && check_fwstate(pmlmepriv, WIFI_AP_STATE)) { /*  group key */
-		if (param->u.crypt.set_tx == 1) {
-			if (strcmp(param->u.crypt.alg, "WEP") == 0) {
-				memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-
-				psecuritypriv->dot118021XGrpPrivacy = _WEP40_;
-				if (param->u.crypt.key_len == 13)
-					psecuritypriv->dot118021XGrpPrivacy = _WEP104_;
-
-			} else if (strcmp(param->u.crypt.alg, "TKIP") == 0) {
-				psecuritypriv->dot118021XGrpPrivacy = _TKIP_;
-
-				memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-
-				/* set mic key */
-				memcpy(txkey, &param->u.crypt.key[16], 8);
-				memcpy(psecuritypriv->dot118021XGrprxmickey[param->u.crypt.idx].skey, &param->u.crypt.key[24], 8);
-
-				psecuritypriv->busetkipkey = true;
-
-			} else if (strcmp(param->u.crypt.alg, "CCMP") == 0) {
-				psecuritypriv->dot118021XGrpPrivacy = _AES_;
-
-				memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-			} else {
-				psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_;
-			}
-
-			psecuritypriv->dot118021XGrpKeyid = param->u.crypt.idx;
-
-			psecuritypriv->binstallGrpkey = true;
-
-			psecuritypriv->dot11PrivacyAlgrthm = psecuritypriv->dot118021XGrpPrivacy;/*  */
-
-			rtw_ap_set_group_key(padapter, param->u.crypt.key, psecuritypriv->dot118021XGrpPrivacy, param->u.crypt.idx);
-
-			pbcmc_sta = rtw_get_bcmc_stainfo(padapter);
-			if (pbcmc_sta) {
-				pbcmc_sta->ieee8021x_blocked = false;
-				pbcmc_sta->dot118021XPrivacy = psecuritypriv->dot118021XGrpPrivacy;/* rx will use bmc_sta's dot118021XPrivacy */
-			}
-		}
-
-		goto exit;
-	}
-
-	if (psecuritypriv->dot11AuthAlgrthm == dot11AuthAlgrthm_8021X && psta) { /*  psk/802_1x */
-		if (check_fwstate(pmlmepriv, WIFI_AP_STATE)) {
-			if (param->u.crypt.set_tx == 1)	{
-				memcpy(psta->dot118021x_UncstKey.skey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-
-				if (strcmp(param->u.crypt.alg, "WEP") == 0) {
-					psta->dot118021XPrivacy = _WEP40_;
-					if (param->u.crypt.key_len == 13)
-						psta->dot118021XPrivacy = _WEP104_;
-				} else if (strcmp(param->u.crypt.alg, "TKIP") == 0) {
-					psta->dot118021XPrivacy = _TKIP_;
-
-					/* set mic key */
-					memcpy(psta->dot11tkiptxmickey.skey, &param->u.crypt.key[16], 8);
-					memcpy(psta->dot11tkiprxmickey.skey, &param->u.crypt.key[24], 8);
-
-					psecuritypriv->busetkipkey = true;
-
-				} else if (strcmp(param->u.crypt.alg, "CCMP") == 0) {
-					psta->dot118021XPrivacy = _AES_;
-				} else {
-					psta->dot118021XPrivacy = _NO_PRIVACY_;
-				}
-
-				rtw_ap_set_pairwise_key(padapter, psta);
-
-				psta->ieee8021x_blocked = false;
-
-			} else { /* group key??? */
-				if (strcmp(param->u.crypt.alg, "WEP") == 0) {
-					memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-
-					psecuritypriv->dot118021XGrpPrivacy = _WEP40_;
-					if (param->u.crypt.key_len == 13)
-						psecuritypriv->dot118021XGrpPrivacy = _WEP104_;
-				} else if (strcmp(param->u.crypt.alg, "TKIP") == 0) {
-					psecuritypriv->dot118021XGrpPrivacy = _TKIP_;
-
-					memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-
-					/* set mic key */
-					memcpy(txkey, &param->u.crypt.key[16], 8);
-					memcpy(rxkey, &param->u.crypt.key[24], 8);
-
-					psecuritypriv->busetkipkey = true;
-
-				} else if (strcmp(param->u.crypt.alg, "CCMP") == 0) {
-					psecuritypriv->dot118021XGrpPrivacy = _AES_;
-
-					memcpy(grpkey, param->u.crypt.key, (param->u.crypt.key_len > 16 ? 16 : param->u.crypt.key_len));
-				} else {
-					psecuritypriv->dot118021XGrpPrivacy = _NO_PRIVACY_;
-				}
-
-				psecuritypriv->dot118021XGrpKeyid = param->u.crypt.idx;
-
-				psecuritypriv->binstallGrpkey = true;
-
-				psecuritypriv->dot11PrivacyAlgrthm = psecuritypriv->dot118021XGrpPrivacy;/*  */
-
-				rtw_ap_set_group_key(padapter, param->u.crypt.key, psecuritypriv->dot118021XGrpPrivacy, param->u.crypt.idx);
-
-				pbcmc_sta = rtw_get_bcmc_stainfo(padapter);
-				if (pbcmc_sta) {
-					pbcmc_sta->ieee8021x_blocked = false;
-					pbcmc_sta->dot118021XPrivacy = psecuritypriv->dot118021XGrpPrivacy;/* rx will use bmc_sta's dot118021XPrivacy */
-				}
-			}
-		}
-	}
-
-exit:
-	kfree(pwep);
-
-	return ret;
-}
-
-static int rtw_set_beacon(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct sta_priv *pstapriv = &padapter->stapriv;
-	unsigned char *pbuf = param->u.bcn_ie.buf;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	memcpy(&pstapriv->max_num_sta, param->u.bcn_ie.reserved, 2);
-
-	if ((pstapriv->max_num_sta > NUM_STA) || (pstapriv->max_num_sta <= 0))
-		pstapriv->max_num_sta = NUM_STA;
-
-	if (rtw_check_beacon_data(padapter, pbuf,  (len - 12 - 2)) == _SUCCESS)/*  12 = param header, 2:no packed */
-		ret = 0;
-	else
-		ret = -EINVAL;
-
-	return ret;
-}
-
-static void rtw_hostapd_sta_flush(struct net_device *dev)
-{
-	/* _irqL irqL; */
-	/* struct list_head	*phead, *plist; */
-	/* struct sta_info *psta = NULL; */
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	/* struct sta_priv *pstapriv = &padapter->stapriv; */
-
-	flush_all_cam_entry(padapter);	/* clear CAM */
-
-	rtw_sta_flush(padapter);
-}
-
-static int rtw_add_sta(struct net_device *dev, struct ieee_param *param)
-{
-	int ret = 0;
-	struct sta_info *psta = NULL;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct sta_priv *pstapriv = &padapter->stapriv;
-
-	if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true)
-		return -EINVAL;
-
-	if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff &&
-	    param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff &&
-	    param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) {
-		return -EINVAL;
-	}
-
-/*
-	psta = rtw_get_stainfo(pstapriv, param->sta_addr);
-	if (psta)
-	{
-		rtw_free_stainfo(padapter,  psta);
-
-		psta = NULL;
-	}
-*/
-	/* psta = rtw_alloc_stainfo(pstapriv, param->sta_addr); */
-	psta = rtw_get_stainfo(pstapriv, param->sta_addr);
-	if (psta) {
-		int flags = param->u.add_sta.flags;
-
-		psta->aid = param->u.add_sta.aid;/* aid = 1~2007 */
-
-		memcpy(psta->bssrateset, param->u.add_sta.tx_supp_rates, 16);
-
-		/* check wmm cap. */
-		if (WLAN_STA_WME & flags)
-			psta->qos_option = 1;
-		else
-			psta->qos_option = 0;
-
-		if (pmlmepriv->qospriv.qos_option == 0)
-			psta->qos_option = 0;
-
-		/* chec 802.11n ht cap. */
-		if (WLAN_STA_HT & flags) {
-			psta->htpriv.ht_option = true;
-			psta->qos_option = 1;
-			memcpy((void *)&psta->htpriv.ht_cap, (void *)&param->u.add_sta.ht_cap, sizeof(struct ieee80211_ht_cap));
-		} else {
-			psta->htpriv.ht_option = false;
-		}
-
-		if (!pmlmepriv->htpriv.ht_option)
-			psta->htpriv.ht_option = false;
-
-		update_sta_info_apmode(padapter, psta);
-
-	} else {
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
-static int rtw_del_sta(struct net_device *dev, struct ieee_param *param)
-{
-	int ret = 0;
-	struct sta_info *psta = NULL;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct sta_priv *pstapriv = &padapter->stapriv;
-
-	if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true)
-		return -EINVAL;
-
-	if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff &&
-	    param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff &&
-	    param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) {
-		return -EINVAL;
-	}
-
-	psta = rtw_get_stainfo(pstapriv, param->sta_addr);
-	if (psta) {
-		u8 updated = false;
-
-		spin_lock_bh(&pstapriv->asoc_list_lock);
-		if (list_empty(&psta->asoc_list) == false) {
-			list_del_init(&psta->asoc_list);
-			pstapriv->asoc_list_cnt--;
-			updated = ap_free_sta(padapter, psta, true, WLAN_REASON_DEAUTH_LEAVING);
-		}
-		spin_unlock_bh(&pstapriv->asoc_list_lock);
-
-		associated_clients_update(padapter, updated);
-
-		psta = NULL;
-	}
-
-	return ret;
-}
-
-static int rtw_ioctl_get_sta_data(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	struct sta_info *psta = NULL;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct sta_priv *pstapriv = &padapter->stapriv;
-	struct ieee_param_ex *param_ex = (struct ieee_param_ex *)param;
-	struct sta_data *psta_data = (struct sta_data *)param_ex->data;
-
-	if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true)
-		return -EINVAL;
-
-	if (param_ex->sta_addr[0] == 0xff && param_ex->sta_addr[1] == 0xff &&
-	    param_ex->sta_addr[2] == 0xff && param_ex->sta_addr[3] == 0xff &&
-	    param_ex->sta_addr[4] == 0xff && param_ex->sta_addr[5] == 0xff) {
-		return -EINVAL;
-	}
-
-	psta = rtw_get_stainfo(pstapriv, param_ex->sta_addr);
-	if (psta) {
-		psta_data->aid = (u16)psta->aid;
-		psta_data->capability = psta->capability;
-		psta_data->flags = psta->flags;
-
-/*
-		nonerp_set : BIT(0)
-		no_short_slot_time_set : BIT(1)
-		no_short_preamble_set : BIT(2)
-		no_ht_gf_set : BIT(3)
-		no_ht_set : BIT(4)
-		ht_20mhz_set : BIT(5)
-*/
-
-		psta_data->sta_set = ((psta->nonerp_set) |
-							 (psta->no_short_slot_time_set << 1) |
-							 (psta->no_short_preamble_set << 2) |
-							 (psta->no_ht_gf_set << 3) |
-							 (psta->no_ht_set << 4) |
-							 (psta->ht_20mhz_set << 5));
-
-		psta_data->tx_supp_rates_len =  psta->bssratelen;
-		memcpy(psta_data->tx_supp_rates, psta->bssrateset, psta->bssratelen);
-		memcpy(&psta_data->ht_cap, &psta->htpriv.ht_cap, sizeof(struct ieee80211_ht_cap));
-		psta_data->rx_pkts = psta->sta_stats.rx_data_pkts;
-		psta_data->rx_bytes = psta->sta_stats.rx_bytes;
-		psta_data->rx_drops = psta->sta_stats.rx_drops;
-
-		psta_data->tx_pkts = psta->sta_stats.tx_pkts;
-		psta_data->tx_bytes = psta->sta_stats.tx_bytes;
-		psta_data->tx_drops = psta->sta_stats.tx_drops;
-
-	} else {
-		ret = -1;
-	}
-
-	return ret;
-}
-
-static int rtw_get_sta_wpaie(struct net_device *dev, struct ieee_param *param)
-{
-	int ret = 0;
-	struct sta_info *psta = NULL;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct sta_priv *pstapriv = &padapter->stapriv;
-
-	if (check_fwstate(pmlmepriv, (_FW_LINKED | WIFI_AP_STATE)) != true)
-		return -EINVAL;
-
-	if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff &&
-	    param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff &&
-	    param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) {
-		return -EINVAL;
-	}
-
-	psta = rtw_get_stainfo(pstapriv, param->sta_addr);
-	if (psta) {
-		if ((psta->wpa_ie[0] == WLAN_EID_RSN) || (psta->wpa_ie[0] == WLAN_EID_VENDOR_SPECIFIC)) {
-			int wpa_ie_len;
-			int copy_len;
-
-			wpa_ie_len = psta->wpa_ie[1];
-
-			copy_len = ((wpa_ie_len + 2) > sizeof(psta->wpa_ie)) ? (sizeof(psta->wpa_ie)) : (wpa_ie_len + 2);
-
-			param->u.wpa_ie.len = copy_len;
-
-			memcpy(param->u.wpa_ie.reserved, psta->wpa_ie, copy_len);
-		}
-	} else {
-		ret = -1;
-	}
-
-	return ret;
-}
-
-static int rtw_set_wps_beacon(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	unsigned char wps_oui[4] = {0x0, 0x50, 0xf2, 0x04};
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	struct mlme_ext_priv *pmlmeext = &padapter->mlmeextpriv;
-	int ie_len;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	ie_len = len - 12 - 2;/*  12 = param header, 2:no packed */
-
-	kfree(pmlmepriv->wps_beacon_ie);
-	pmlmepriv->wps_beacon_ie = NULL;
-
-	if (ie_len > 0) {
-		pmlmepriv->wps_beacon_ie = rtw_malloc(ie_len);
-		pmlmepriv->wps_beacon_ie_len = ie_len;
-		if (!pmlmepriv->wps_beacon_ie)
-			return -EINVAL;
-
-		memcpy(pmlmepriv->wps_beacon_ie, param->u.bcn_ie.buf, ie_len);
-
-		update_beacon(padapter, WLAN_EID_VENDOR_SPECIFIC, wps_oui, true);
-
-		pmlmeext->bstart_bss = true;
-	}
-
-	return ret;
-}
-
-static int rtw_set_wps_probe_resp(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	int ie_len;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	ie_len = len - 12 - 2;/*  12 = param header, 2:no packed */
-
-	kfree(pmlmepriv->wps_probe_resp_ie);
-	pmlmepriv->wps_probe_resp_ie = NULL;
-
-	if (ie_len > 0) {
-		pmlmepriv->wps_probe_resp_ie = rtw_malloc(ie_len);
-		pmlmepriv->wps_probe_resp_ie_len = ie_len;
-		if (!pmlmepriv->wps_probe_resp_ie)
-			return -EINVAL;
-
-		memcpy(pmlmepriv->wps_probe_resp_ie, param->u.bcn_ie.buf, ie_len);
-	}
-
-	return ret;
-}
-
-static int rtw_set_wps_assoc_resp(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-	int ie_len;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	ie_len = len - 12 - 2;/*  12 = param header, 2:no packed */
-
-	kfree(pmlmepriv->wps_assoc_resp_ie);
-	pmlmepriv->wps_assoc_resp_ie = NULL;
-
-	if (ie_len > 0) {
-		pmlmepriv->wps_assoc_resp_ie = rtw_malloc(ie_len);
-		pmlmepriv->wps_assoc_resp_ie_len = ie_len;
-		if (!pmlmepriv->wps_assoc_resp_ie)
-			return -EINVAL;
-
-		memcpy(pmlmepriv->wps_assoc_resp_ie, param->u.bcn_ie.buf, ie_len);
-	}
-
-	return ret;
-}
-
-static int rtw_set_hidden_ssid(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	struct adapter *adapter = rtw_netdev_priv(dev);
-	struct mlme_priv *mlmepriv = &adapter->mlmepriv;
-	struct mlme_ext_priv *mlmeext = &adapter->mlmeextpriv;
-	struct mlme_ext_info *mlmeinfo = &mlmeext->mlmext_info;
-	int ie_len;
-	u8 *ssid_ie;
-	char ssid[NDIS_802_11_LENGTH_SSID + 1];
-	signed int ssid_len;
-	u8 ignore_broadcast_ssid;
-
-	if (check_fwstate(mlmepriv, WIFI_AP_STATE) != true)
-		return -EPERM;
-
-	if (param->u.bcn_ie.reserved[0] != 0xea)
-		return -EINVAL;
-
-	mlmeinfo->hidden_ssid_mode = ignore_broadcast_ssid = param->u.bcn_ie.reserved[1];
-
-	ie_len = len - 12 - 2;/*  12 = param header, 2:no packed */
-	ssid_ie = rtw_get_ie(param->u.bcn_ie.buf,  WLAN_EID_SSID, &ssid_len, ie_len);
-
-	if (ssid_ie && ssid_len > 0 && ssid_len <= NDIS_802_11_LENGTH_SSID) {
-		struct wlan_bssid_ex *pbss_network = &mlmepriv->cur_network.network;
-		struct wlan_bssid_ex *pbss_network_ext = &mlmeinfo->network;
-
-		memcpy(ssid, ssid_ie + 2, ssid_len);
-		ssid[ssid_len] = 0x0;
-
-		memcpy(pbss_network->ssid.ssid, (void *)ssid, ssid_len);
-		pbss_network->ssid.ssid_length = ssid_len;
-		memcpy(pbss_network_ext->ssid.ssid, (void *)ssid, ssid_len);
-		pbss_network_ext->ssid.ssid_length = ssid_len;
-	}
-
-	return ret;
-}
-
-static int rtw_ioctl_acl_remove_sta(struct net_device *dev, struct ieee_param *param, int len)
-{
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff &&
-	    param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff &&
-	    param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) {
-		return -EINVAL;
-	}
-
-	rtw_acl_remove_sta(padapter, param->sta_addr);
-	return 0;
-}
-
-static int rtw_ioctl_acl_add_sta(struct net_device *dev, struct ieee_param *param, int len)
-{
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	if (param->sta_addr[0] == 0xff && param->sta_addr[1] == 0xff &&
-	    param->sta_addr[2] == 0xff && param->sta_addr[3] == 0xff &&
-	    param->sta_addr[4] == 0xff && param->sta_addr[5] == 0xff) {
-		return -EINVAL;
-	}
-
-	return rtw_acl_add_sta(padapter, param->sta_addr);
-}
-
-static int rtw_ioctl_set_macaddr_acl(struct net_device *dev, struct ieee_param *param, int len)
-{
-	int ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
-
-	if (check_fwstate(pmlmepriv, WIFI_AP_STATE) != true)
-		return -EINVAL;
-
-	rtw_set_macaddr_acl(padapter, param->u.mlme.command);
-
-	return ret;
-}
-
-static int rtw_hostapd_ioctl(struct net_device *dev, struct iw_point *p)
-{
-	struct ieee_param *param;
-	int ret = 0;
-	struct adapter *padapter = rtw_netdev_priv(dev);
-
-	/*
-	 * this function is expect to call in master mode, which allows no power saving
-	 * so, we just check hw_init_completed
-	 */
-
-	if (!padapter->hw_init_completed)
-		return -EPERM;
-
-	if (!p->pointer || p->length != sizeof(*param))
-		return -EINVAL;
-
-	param = rtw_malloc(p->length);
-	if (!param)
-		return -ENOMEM;
-
-	if (copy_from_user(param, p->pointer, p->length)) {
-		kfree(param);
-		return -EFAULT;
-	}
-
-	switch (param->cmd) {
-	case RTL871X_HOSTAPD_FLUSH:
-
-		rtw_hostapd_sta_flush(dev);
-
-		break;
-
-	case RTL871X_HOSTAPD_ADD_STA:
-
-		ret = rtw_add_sta(dev, param);
-
-		break;
-
-	case RTL871X_HOSTAPD_REMOVE_STA:
-
-		ret = rtw_del_sta(dev, param);
-
-		break;
-
-	case RTL871X_HOSTAPD_SET_BEACON:
-
-		ret = rtw_set_beacon(dev, param, p->length);
-
-		break;
-
-	case RTL871X_SET_ENCRYPTION:
-
-		ret = rtw_set_encryption(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_GET_WPAIE_STA:
-
-		ret = rtw_get_sta_wpaie(dev, param);
-
-		break;
-
-	case RTL871X_HOSTAPD_SET_WPS_BEACON:
-
-		ret = rtw_set_wps_beacon(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_SET_WPS_PROBE_RESP:
-
-		ret = rtw_set_wps_probe_resp(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_SET_WPS_ASSOC_RESP:
-
-		ret = rtw_set_wps_assoc_resp(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_SET_HIDDEN_SSID:
-
-		ret = rtw_set_hidden_ssid(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_GET_INFO_STA:
-
-		ret = rtw_ioctl_get_sta_data(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_SET_MACADDR_ACL:
-
-		ret = rtw_ioctl_set_macaddr_acl(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_ACL_ADD_STA:
-
-		ret = rtw_ioctl_acl_add_sta(dev, param, p->length);
-
-		break;
-
-	case RTL871X_HOSTAPD_ACL_REMOVE_STA:
-
-		ret = rtw_ioctl_acl_remove_sta(dev, param, p->length);
-
-		break;
-
-	default:
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	if (ret == 0 && copy_to_user(p->pointer, param, p->length))
-		ret = -EFAULT;
-
-	kfree(param);
-	return ret;
-}
-
-/*  copy from net/wireless/wext.c end */
-
-int rtw_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
-{
-	struct iwreq *wrq = (struct iwreq *)rq;
-	int ret = 0;
-
-	switch (cmd) {
-	case RTL_IOCTL_WPA_SUPPLICANT:
-		ret = wpa_supplicant_ioctl(dev, &wrq->u.data);
-		break;
-	case RTL_IOCTL_HOSTAPD:
-		ret = rtw_hostapd_ioctl(dev, &wrq->u.data);
-		break;
-	default:
-		ret = -EOPNOTSUPP;
-		break;
-	}
-
-	return ret;
-}
diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
index 4e1917c05402..738a601c55bb 100644
--- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
@@ -407,7 +407,6 @@ static const struct net_device_ops rtw_netdev_ops = {
 	.ndo_select_queue	= rtw_select_queue,
 	.ndo_set_mac_address = rtw_net_set_mac_address,
 	.ndo_get_stats = rtw_net_get_stats,
-	.ndo_do_ioctl = rtw_ioctl,
 };
 
 int rtw_init_netdev_name(struct net_device *pnetdev, const char *ifname)
diff --git a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
index dc0d715ed970..0dbe76ee5570 100644
--- a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
+++ b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
@@ -59,7 +59,7 @@ static int bcm2835_audio_send_msg_locked(struct bcm2835_audio_instance *instance
 
 	if (wait) {
 		if (!wait_for_completion_timeout(&instance->msg_avail_comp,
-						 msecs_to_jiffies(10 * 1000))) {
+						 secs_to_jiffies(10))) {
 			dev_err(instance->dev,
 				"vchi message timeout, msg=%d\n", m->type);
 			return -ETIMEDOUT;
diff --git a/drivers/staging/vme_user/vme_tsi148.c b/drivers/staging/vme_user/vme_tsi148.c
index 31a44025e08f..733594dde9ae 100644
--- a/drivers/staging/vme_user/vme_tsi148.c
+++ b/drivers/staging/vme_user/vme_tsi148.c
@@ -761,8 +761,7 @@ static int tsi148_alloc_resource(struct vme_master_resource *image,
 		goto err_resource;
 	}
 
-	image->kern_base = ioremap(
-		image->bus_resource.start, size);
+	image->kern_base = ioremap(image->bus_resource.start, size);
 	if (!image->kern_base) {
 		dev_err(tsi148_bridge->parent, "Failed to remap resource\n");
 		retval = -ENOMEM;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 091c1efccfb7..1244ef3aa86c 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -4664,21 +4664,6 @@ int iscsit_logout_post_handler(
 }
 EXPORT_SYMBOL(iscsit_logout_post_handler);
 
-void iscsit_fail_session(struct iscsit_session *sess)
-{
-	struct iscsit_conn *conn;
-
-	spin_lock_bh(&sess->conn_lock);
-	list_for_each_entry(conn, &sess->sess_conn_list, conn_list) {
-		pr_debug("Moving to TARG_CONN_STATE_CLEANUP_WAIT.\n");
-		conn->conn_state = TARG_CONN_STATE_CLEANUP_WAIT;
-	}
-	spin_unlock_bh(&sess->conn_lock);
-
-	pr_debug("Moving to TARG_SESS_STATE_FAILED.\n");
-	sess->session_state = TARG_SESS_STATE_FAILED;
-}
-
 void iscsit_stop_session(
 	struct iscsit_session *sess,
 	int session_sleep,
diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h
index 873411e95ed2..f4addae2aae4 100644
--- a/drivers/target/iscsi/iscsi_target.h
+++ b/drivers/target/iscsi/iscsi_target.h
@@ -40,7 +40,6 @@ extern int iscsi_target_tx_thread(void *);
 extern int iscsi_target_rx_thread(void *);
 extern int iscsit_close_connection(struct iscsit_conn *);
 extern int iscsit_close_session(struct iscsit_session *, bool can_sleep);
-extern void iscsit_fail_session(struct iscsit_session *);
 extern void iscsit_stop_session(struct iscsit_session *, int, int);
 extern int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *, int);
 
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 18e88d2ea5fd..56d78af7cec7 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -25,54 +25,6 @@
 /*
  *	FIXME: Does RData SNACK apply here as well?
  */
-void iscsit_create_conn_recovery_datain_values(
-	struct iscsit_cmd *cmd,
-	__be32 exp_data_sn)
-{
-	u32 data_sn = 0;
-	struct iscsit_conn *conn = cmd->conn;
-
-	cmd->next_burst_len = 0;
-	cmd->read_data_done = 0;
-
-	while (be32_to_cpu(exp_data_sn) > data_sn) {
-		if ((cmd->next_burst_len +
-		     conn->conn_ops->MaxRecvDataSegmentLength) <
-		     conn->sess->sess_ops->MaxBurstLength) {
-			cmd->read_data_done +=
-			       conn->conn_ops->MaxRecvDataSegmentLength;
-			cmd->next_burst_len +=
-			       conn->conn_ops->MaxRecvDataSegmentLength;
-		} else {
-			cmd->read_data_done +=
-				(conn->sess->sess_ops->MaxBurstLength -
-				cmd->next_burst_len);
-			cmd->next_burst_len = 0;
-		}
-		data_sn++;
-	}
-}
-
-void iscsit_create_conn_recovery_dataout_values(
-	struct iscsit_cmd *cmd)
-{
-	u32 write_data_done = 0;
-	struct iscsit_conn *conn = cmd->conn;
-
-	cmd->data_sn = 0;
-	cmd->next_burst_len = 0;
-
-	while (cmd->write_data_done > write_data_done) {
-		if ((write_data_done + conn->sess->sess_ops->MaxBurstLength) <=
-		     cmd->write_data_done)
-			write_data_done += conn->sess->sess_ops->MaxBurstLength;
-		else
-			break;
-	}
-
-	cmd->write_data_done = write_data_done;
-}
-
 static int iscsit_attach_active_connection_recovery_entry(
 	struct iscsit_session *sess,
 	struct iscsi_conn_recovery *cr)
diff --git a/drivers/target/iscsi/iscsi_target_erl2.h b/drivers/target/iscsi/iscsi_target_erl2.h
index 6655e4bcf893..9064c74eef7a 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.h
+++ b/drivers/target/iscsi/iscsi_target_erl2.h
@@ -9,8 +9,6 @@ struct iscsit_conn;
 struct iscsi_conn_recovery;
 struct iscsit_session;
 
-extern void iscsit_create_conn_recovery_datain_values(struct iscsit_cmd *, __be32);
-extern void iscsit_create_conn_recovery_dataout_values(struct iscsit_cmd *);
 extern struct iscsi_conn_recovery *iscsit_get_inactive_connection_recovery_entry(
 			struct iscsit_session *, u16);
 extern void iscsit_free_connection_recovery_entries(struct iscsit_session *);
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 5b90c22ee3dc..1d4e1788e073 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -67,54 +67,6 @@ int iscsi_login_tx_data(
 	return 0;
 }
 
-void iscsi_dump_conn_ops(struct iscsi_conn_ops *conn_ops)
-{
-	pr_debug("HeaderDigest: %s\n", (conn_ops->HeaderDigest) ?
-				"CRC32C" : "None");
-	pr_debug("DataDigest: %s\n", (conn_ops->DataDigest) ?
-				"CRC32C" : "None");
-	pr_debug("MaxRecvDataSegmentLength: %u\n",
-				conn_ops->MaxRecvDataSegmentLength);
-}
-
-void iscsi_dump_sess_ops(struct iscsi_sess_ops *sess_ops)
-{
-	pr_debug("InitiatorName: %s\n", sess_ops->InitiatorName);
-	pr_debug("InitiatorAlias: %s\n", sess_ops->InitiatorAlias);
-	pr_debug("TargetName: %s\n", sess_ops->TargetName);
-	pr_debug("TargetAlias: %s\n", sess_ops->TargetAlias);
-	pr_debug("TargetPortalGroupTag: %hu\n",
-			sess_ops->TargetPortalGroupTag);
-	pr_debug("MaxConnections: %hu\n", sess_ops->MaxConnections);
-	pr_debug("InitialR2T: %s\n",
-			(sess_ops->InitialR2T) ? "Yes" : "No");
-	pr_debug("ImmediateData: %s\n", (sess_ops->ImmediateData) ?
-			"Yes" : "No");
-	pr_debug("MaxBurstLength: %u\n", sess_ops->MaxBurstLength);
-	pr_debug("FirstBurstLength: %u\n", sess_ops->FirstBurstLength);
-	pr_debug("DefaultTime2Wait: %hu\n", sess_ops->DefaultTime2Wait);
-	pr_debug("DefaultTime2Retain: %hu\n",
-			sess_ops->DefaultTime2Retain);
-	pr_debug("MaxOutstandingR2T: %hu\n",
-			sess_ops->MaxOutstandingR2T);
-	pr_debug("DataPDUInOrder: %s\n",
-			(sess_ops->DataPDUInOrder) ? "Yes" : "No");
-	pr_debug("DataSequenceInOrder: %s\n",
-			(sess_ops->DataSequenceInOrder) ? "Yes" : "No");
-	pr_debug("ErrorRecoveryLevel: %hu\n",
-			sess_ops->ErrorRecoveryLevel);
-	pr_debug("SessionType: %s\n", (sess_ops->SessionType) ?
-			"Discovery" : "Normal");
-}
-
-void iscsi_print_params(struct iscsi_param_list *param_list)
-{
-	struct iscsi_param *param;
-
-	list_for_each_entry(param, &param_list->param_list, p_list)
-		pr_debug("%s: %s\n", param->name, param->value);
-}
-
 static struct iscsi_param *iscsi_set_default_param(struct iscsi_param_list *param_list,
 		char *name, char *value, u8 phase, u8 scope, u8 sender,
 		u16 type_range, u8 use)
diff --git a/drivers/target/iscsi/iscsi_target_parameters.h b/drivers/target/iscsi/iscsi_target_parameters.h
index 00fbbebb8c75..c672a971fcb7 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.h
+++ b/drivers/target/iscsi/iscsi_target_parameters.h
@@ -32,9 +32,6 @@ struct iscsi_sess_ops;
 
 extern int iscsi_login_rx_data(struct iscsit_conn *, char *, int);
 extern int iscsi_login_tx_data(struct iscsit_conn *, char *, char *, int);
-extern void iscsi_dump_conn_ops(struct iscsi_conn_ops *);
-extern void iscsi_dump_sess_ops(struct iscsi_sess_ops *);
-extern void iscsi_print_params(struct iscsi_param_list *);
 extern int iscsi_create_default_params(struct iscsi_param_list **);
 extern int iscsi_set_keys_to_negotiate(struct iscsi_param_list *, bool);
 extern int iscsi_set_keys_irrelevant_for_discovery(struct iscsi_param_list *);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index f7bac98fd4fe..bf06cfdfb012 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -200,11 +200,6 @@ static void iscsit_clear_tpg_np_login_threads(
 	spin_unlock(&tpg->tpg_np_lock);
 }
 
-void iscsit_tpg_dump_params(struct iscsi_portal_group *tpg)
-{
-	iscsi_print_params(tpg->param_list);
-}
-
 static void iscsit_set_default_tpg_attribs(struct iscsi_portal_group *tpg)
 {
 	struct iscsi_tpg_attrib *a = &tpg->tpg_attrib;
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index d44d09f2dde9..1155b7b3164a 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -18,7 +18,6 @@ extern struct iscsi_portal_group *iscsit_get_tpg_from_np(struct iscsi_tiqn *,
 			struct iscsi_np *, struct iscsi_tpg_np **);
 extern int iscsit_get_tpg(struct iscsi_portal_group *);
 extern void iscsit_put_tpg(struct iscsi_portal_group *);
-extern void iscsit_tpg_dump_params(struct iscsi_portal_group *);
 extern int iscsit_tpg_add_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *);
 extern int iscsit_tpg_del_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *,
 			int);
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 91a75a4a7cc1..ed2dadb21f75 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -333,50 +333,6 @@ int iscsit_sequence_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd,
 }
 EXPORT_SYMBOL(iscsit_sequence_cmd);
 
-int iscsit_check_unsolicited_dataout(struct iscsit_cmd *cmd, unsigned char *buf)
-{
-	struct iscsit_conn *conn = cmd->conn;
-	struct se_cmd *se_cmd = &cmd->se_cmd;
-	struct iscsi_data *hdr = (struct iscsi_data *) buf;
-	u32 payload_length = ntoh24(hdr->dlength);
-
-	if (conn->sess->sess_ops->InitialR2T) {
-		pr_err("Received unexpected unsolicited data"
-			" while InitialR2T=Yes, protocol error.\n");
-		transport_send_check_condition_and_sense(se_cmd,
-				TCM_UNEXPECTED_UNSOLICITED_DATA, 0);
-		return -1;
-	}
-
-	if ((cmd->first_burst_len + payload_length) >
-	     conn->sess->sess_ops->FirstBurstLength) {
-		pr_err("Total %u bytes exceeds FirstBurstLength: %u"
-			" for this Unsolicited DataOut Burst.\n",
-			(cmd->first_burst_len + payload_length),
-				conn->sess->sess_ops->FirstBurstLength);
-		transport_send_check_condition_and_sense(se_cmd,
-				TCM_INCORRECT_AMOUNT_OF_DATA, 0);
-		return -1;
-	}
-
-	if (!(hdr->flags & ISCSI_FLAG_CMD_FINAL))
-		return 0;
-
-	if (((cmd->first_burst_len + payload_length) != cmd->se_cmd.data_length) &&
-	    ((cmd->first_burst_len + payload_length) !=
-	      conn->sess->sess_ops->FirstBurstLength)) {
-		pr_err("Unsolicited non-immediate data received %u"
-			" does not equal FirstBurstLength: %u, and does"
-			" not equal ExpXferLen %u.\n",
-			(cmd->first_burst_len + payload_length),
-			conn->sess->sess_ops->FirstBurstLength, cmd->se_cmd.data_length);
-		transport_send_check_condition_and_sense(se_cmd,
-				TCM_INCORRECT_AMOUNT_OF_DATA, 0);
-		return -1;
-	}
-	return 0;
-}
-
 struct iscsit_cmd *iscsit_find_cmd_from_itt(
 	struct iscsit_conn *conn,
 	itt_t init_task_tag)
@@ -1252,20 +1208,6 @@ int iscsit_tx_login_rsp(struct iscsit_conn *conn, u8 status_class, u8 status_det
 	return conn->conn_transport->iscsit_put_login_tx(conn, login, 0);
 }
 
-void iscsit_print_session_params(struct iscsit_session *sess)
-{
-	struct iscsit_conn *conn;
-
-	pr_debug("-----------------------------[Session Params for"
-		" SID: %u]-----------------------------\n", sess->sid);
-	spin_lock_bh(&sess->conn_lock);
-	list_for_each_entry(conn, &sess->sess_conn_list, conn_list)
-		iscsi_dump_conn_ops(conn->conn_ops);
-	spin_unlock_bh(&sess->conn_lock);
-
-	iscsi_dump_sess_ops(sess->sess_ops);
-}
-
 int rx_data(
 	struct iscsit_conn *conn,
 	struct kvec *iov,
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index 336da4fb0a77..7ae48a8a5cbf 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -23,7 +23,6 @@ extern struct iscsi_seq *iscsit_get_seq_holder_for_r2t(struct iscsit_cmd *);
 extern struct iscsi_r2t *iscsit_get_holder_for_r2tsn(struct iscsit_cmd *, u32);
 extern int iscsit_sequence_cmd(struct iscsit_conn *conn, struct iscsit_cmd *cmd,
 			       unsigned char * ,__be32 cmdsn);
-extern int iscsit_check_unsolicited_dataout(struct iscsit_cmd *, unsigned char *);
 extern struct iscsit_cmd *iscsit_find_cmd_from_itt_or_dump(struct iscsit_conn *,
 			itt_t, u32);
 extern struct iscsit_cmd *iscsit_find_cmd_from_ttt(struct iscsit_conn *, u32);
@@ -61,7 +60,6 @@ extern int iscsit_set_login_timer_kworker(struct iscsit_conn *, struct task_stru
 extern int iscsit_send_tx_data(struct iscsit_cmd *, struct iscsit_conn *, int);
 extern int iscsit_fe_sendpage_sg(struct iscsit_cmd *, struct iscsit_conn *);
 extern int iscsit_tx_login_rsp(struct iscsit_conn *, u8, u8);
-extern void iscsit_print_session_params(struct iscsit_session *);
 extern int rx_data(struct iscsit_conn *, struct kvec *, int, int);
 extern int tx_data(struct iscsit_conn *, struct kvec *, int, int);
 extern void iscsit_collect_login_stats(struct iscsit_conn *, u8, u8);
diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c
index c42cbde8a31b..210648a0092e 100644
--- a/drivers/target/target_core_stat.c
+++ b/drivers/target/target_core_stat.c
@@ -117,9 +117,9 @@ static ssize_t target_stat_tgt_status_show(struct config_item *item,
 		char *page)
 {
 	if (to_stat_tgt_dev(item)->export_count)
-		return snprintf(page, PAGE_SIZE, "activated");
+		return snprintf(page, PAGE_SIZE, "activated\n");
 	else
-		return snprintf(page, PAGE_SIZE, "deactivated");
+		return snprintf(page, PAGE_SIZE, "deactivated\n");
 }
 
 static ssize_t target_stat_tgt_non_access_lus_show(struct config_item *item,
diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c
index 4bdb2d45e0bf..dc1f456736dc 100644
--- a/drivers/thunderbolt/ctl.c
+++ b/drivers/thunderbolt/ctl.c
@@ -70,6 +70,9 @@ struct tb_ctl {
 #define tb_ctl_dbg(ctl, format, arg...) \
 	dev_dbg(&(ctl)->nhi->pdev->dev, format, ## arg)
 
+#define tb_ctl_dbg_once(ctl, format, arg...) \
+	dev_dbg_once(&(ctl)->nhi->pdev->dev, format, ## arg)
+
 static DECLARE_WAIT_QUEUE_HEAD(tb_cfg_request_cancel_queue);
 /* Serializes access to request kref_get/put */
 static DEFINE_MUTEX(tb_cfg_request_lock);
@@ -265,7 +268,7 @@ static struct tb_cfg_result parse_header(const struct ctl_pkg *pkg, u32 len,
 	return res;
 }
 
-static void tb_cfg_print_error(struct tb_ctl *ctl,
+static void tb_cfg_print_error(struct tb_ctl *ctl, enum tb_cfg_space space,
 			       const struct tb_cfg_result *res)
 {
 	WARN_ON(res->err != 1);
@@ -279,8 +282,8 @@ static void tb_cfg_print_error(struct tb_ctl *ctl,
 		 * Invalid cfg_space/offset/length combination in
 		 * cfg_read/cfg_write.
 		 */
-		tb_ctl_dbg(ctl, "%llx:%x: invalid config space or offset\n",
-			   res->response_route, res->response_port);
+		tb_ctl_dbg_once(ctl, "%llx:%x: invalid config space (%u) or offset\n",
+				res->response_route, res->response_port, space);
 		return;
 	case TB_CFG_ERROR_NO_SUCH_PORT:
 		/*
@@ -1072,7 +1075,7 @@ static int tb_cfg_get_error(struct tb_ctl *ctl, enum tb_cfg_space space,
 	    res->tb_error == TB_CFG_ERROR_INVALID_CONFIG_SPACE)
 		return -ENODEV;
 
-	tb_cfg_print_error(ctl, res);
+	tb_cfg_print_error(ctl, space, res);
 
 	if (res->tb_error == TB_CFG_ERROR_LOCK)
 		return -EACCES;
diff --git a/drivers/thunderbolt/ctl.h b/drivers/thunderbolt/ctl.h
index bf930a191472..7e08ca8f0895 100644
--- a/drivers/thunderbolt/ctl.h
+++ b/drivers/thunderbolt/ctl.h
@@ -140,5 +140,4 @@ int tb_cfg_write(struct tb_ctl *ctl, const void *buffer, u64 route, u32 port,
 		 enum tb_cfg_space space, u32 offset, u32 length);
 int tb_cfg_get_upstream_port(struct tb_ctl *ctl, u64 route);
 
-
 #endif
diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c
index a1d0d8a33f20..f8328ca7e22e 100644
--- a/drivers/thunderbolt/debugfs.c
+++ b/drivers/thunderbolt/debugfs.c
@@ -168,6 +168,13 @@ static bool parse_line(char **line, u32 *offs, u32 *val, int short_fmt_len,
 	 * offset relative_offset cap_id vs_cap_id value\n
 	 * v[0]   v[1]            v[2]   v[3]      v[4]
 	 *
+	 * For Path configuration space:
+	 * Short format is: offset value\n
+	 *		    v[0]   v[1]
+	 * Long format as produced from the read side:
+	 * offset relative_offset in_hop_id value\n
+	 * v[0]   v[1]            v[2]      v[3]
+	 *
 	 * For Counter configuration space:
 	 * Short format is: offset\n
 	 *		    v[0]
@@ -191,14 +198,33 @@ static bool parse_line(char **line, u32 *offs, u32 *val, int short_fmt_len,
 }
 
 #if IS_ENABLED(CONFIG_USB4_DEBUGFS_WRITE)
+/*
+ * Path registers need to be written in double word pairs and they both must be
+ * read before written. This writes one double word in patch config space
+ * following the spec flow.
+ */
+static int path_write_one(struct tb_port *port, u32 val, u32 offset)
+{
+	u32 index = offset % PATH_LEN;
+	u32 offs = offset - index;
+	u32 data[PATH_LEN];
+	int ret;
+
+	ret = tb_port_read(port, data, TB_CFG_HOPS, offs, PATH_LEN);
+	if (ret)
+		return ret;
+	data[index] = val;
+	return tb_port_write(port, data, TB_CFG_HOPS, offs, PATH_LEN);
+}
+
 static ssize_t regs_write(struct tb_switch *sw, struct tb_port *port,
-			  const char __user *user_buf, size_t count,
-			  loff_t *ppos)
+			  enum tb_cfg_space space, const char __user *user_buf,
+			  size_t count, loff_t *ppos)
 {
+	int long_fmt_len, ret = 0;
 	struct tb *tb = sw->tb;
 	char *line, *buf;
 	u32 val, offset;
-	int ret = 0;
 
 	buf = validate_and_copy_from_user(user_buf, &count);
 	if (IS_ERR(buf))
@@ -214,12 +240,21 @@ static ssize_t regs_write(struct tb_switch *sw, struct tb_port *port,
 	/* User did hardware changes behind the driver's back */
 	add_taint(TAINT_USER, LOCKDEP_STILL_OK);
 
+	if (space == TB_CFG_HOPS)
+		long_fmt_len = 4;
+	else
+		long_fmt_len = 5;
+
 	line = buf;
-	while (parse_line(&line, &offset, &val, 2, 5)) {
-		if (port)
-			ret = tb_port_write(port, &val, TB_CFG_PORT, offset, 1);
-		else
+	while (parse_line(&line, &offset, &val, 2, long_fmt_len)) {
+		if (port) {
+			if (space == TB_CFG_HOPS)
+				ret = path_write_one(port, val, offset);
+			else
+				ret = tb_port_write(port, &val, space, offset, 1);
+		} else {
 			ret = tb_sw_write(sw, &val, TB_CFG_SWITCH, offset, 1);
+		}
 		if (ret)
 			break;
 	}
@@ -240,7 +275,16 @@ static ssize_t port_regs_write(struct file *file, const char __user *user_buf,
 	struct seq_file *s = file->private_data;
 	struct tb_port *port = s->private;
 
-	return regs_write(port->sw, port, user_buf, count, ppos);
+	return regs_write(port->sw, port, TB_CFG_PORT, user_buf, count, ppos);
+}
+
+static ssize_t path_write(struct file *file, const char __user *user_buf,
+			  size_t count, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct tb_port *port = s->private;
+
+	return regs_write(port->sw, port, TB_CFG_HOPS, user_buf, count, ppos);
 }
 
 static ssize_t switch_regs_write(struct file *file, const char __user *user_buf,
@@ -249,7 +293,7 @@ static ssize_t switch_regs_write(struct file *file, const char __user *user_buf,
 	struct seq_file *s = file->private_data;
 	struct tb_switch *sw = s->private;
 
-	return regs_write(sw, NULL, user_buf, count, ppos);
+	return regs_write(sw, NULL, TB_CFG_SWITCH, user_buf, count, ppos);
 }
 
 static bool parse_sb_line(char **line, u8 *reg, u8 *data, size_t data_size,
@@ -401,6 +445,7 @@ out:
 #define DEBUGFS_MODE		0600
 #else
 #define port_regs_write		NULL
+#define path_write		NULL
 #define switch_regs_write	NULL
 #define port_sb_regs_write	NULL
 #define retimer_sb_regs_write	NULL
@@ -2243,7 +2288,7 @@ out_rpm_put:
 
 	return ret;
 }
-DEBUGFS_ATTR_RO(path);
+DEBUGFS_ATTR_RW(path);
 
 static int counter_set_regs_show(struct tb_port *port, struct seq_file *s,
 				 int counter)
@@ -2368,6 +2413,8 @@ void tb_switch_debugfs_init(struct tb_switch *sw)
 	sw->debugfs_dir = debugfs_dir;
 	debugfs_create_file("regs", DEBUGFS_MODE, debugfs_dir, sw,
 			    &switch_regs_fops);
+	if (sw->drom)
+		debugfs_create_blob("drom", 0400, debugfs_dir, &sw->drom_blob);
 
 	tb_switch_for_each_port(sw, port) {
 		struct dentry *debugfs_dir;
diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c
index eb241b270f79..9c1d65d26553 100644
--- a/drivers/thunderbolt/eeprom.c
+++ b/drivers/thunderbolt/eeprom.c
@@ -435,6 +435,29 @@ static int tb_drom_parse_entries(struct tb_switch *sw, size_t header_size)
 	return 0;
 }
 
+static int tb_switch_drom_alloc(struct tb_switch *sw, size_t size)
+{
+	sw->drom = kzalloc(size, GFP_KERNEL);
+	if (!sw->drom)
+		return -ENOMEM;
+
+#ifdef CONFIG_DEBUG_FS
+	sw->drom_blob.data = sw->drom;
+	sw->drom_blob.size = size;
+#endif
+	return 0;
+}
+
+static void tb_switch_drom_free(struct tb_switch *sw)
+{
+#ifdef CONFIG_DEBUG_FS
+	sw->drom_blob.data = NULL;
+	sw->drom_blob.size = 0;
+#endif
+	kfree(sw->drom);
+	sw->drom = NULL;
+}
+
 /*
  * tb_drom_copy_efi - copy drom supplied by EFI to sw->drom if present
  */
@@ -447,9 +470,9 @@ static int tb_drom_copy_efi(struct tb_switch *sw, u16 *size)
 	if (len < 0 || len < sizeof(struct tb_drom_header))
 		return -EINVAL;
 
-	sw->drom = kmalloc(len, GFP_KERNEL);
-	if (!sw->drom)
-		return -ENOMEM;
+	res = tb_switch_drom_alloc(sw, len);
+	if (res)
+		return res;
 
 	res = device_property_read_u8_array(dev, "ThunderboltDROM", sw->drom,
 									len);
@@ -464,8 +487,7 @@ static int tb_drom_copy_efi(struct tb_switch *sw, u16 *size)
 	return 0;
 
 err:
-	kfree(sw->drom);
-	sw->drom = NULL;
+	tb_switch_drom_free(sw);
 	return -EINVAL;
 }
 
@@ -491,13 +513,15 @@ static int tb_drom_copy_nvm(struct tb_switch *sw, u16 *size)
 
 	/* Size includes CRC8 + UID + CRC32 */
 	*size += 1 + 8 + 4;
-	sw->drom = kzalloc(*size, GFP_KERNEL);
-	if (!sw->drom)
-		return -ENOMEM;
+	ret = tb_switch_drom_alloc(sw, *size);
+	if (ret)
+		return ret;
 
 	ret = dma_port_flash_read(sw->dma_port, drom_offset, sw->drom, *size);
-	if (ret)
-		goto err_free;
+	if (ret) {
+		tb_switch_drom_free(sw);
+		return ret;
+	}
 
 	/*
 	 * Read UID from the minimal DROM because the one in NVM is just
@@ -505,11 +529,6 @@ static int tb_drom_copy_nvm(struct tb_switch *sw, u16 *size)
 	 */
 	tb_drom_read_uid_only(sw, &sw->uid);
 	return 0;
-
-err_free:
-	kfree(sw->drom);
-	sw->drom = NULL;
-	return ret;
 }
 
 static int usb4_copy_drom(struct tb_switch *sw, u16 *size)
@@ -522,15 +541,13 @@ static int usb4_copy_drom(struct tb_switch *sw, u16 *size)
 
 	/* Size includes CRC8 + UID + CRC32 */
 	*size += 1 + 8 + 4;
-	sw->drom = kzalloc(*size, GFP_KERNEL);
-	if (!sw->drom)
-		return -ENOMEM;
+	ret = tb_switch_drom_alloc(sw, *size);
+	if (ret)
+		return ret;
 
 	ret = usb4_switch_drom_read(sw, 0, sw->drom, *size);
-	if (ret) {
-		kfree(sw->drom);
-		sw->drom = NULL;
-	}
+	if (ret)
+		tb_switch_drom_free(sw);
 
 	return ret;
 }
@@ -552,19 +569,14 @@ static int tb_drom_bit_bang(struct tb_switch *sw, u16 *size)
 		return -EIO;
 	}
 
-	sw->drom = kzalloc(*size, GFP_KERNEL);
-	if (!sw->drom)
-		return -ENOMEM;
+	ret = tb_switch_drom_alloc(sw, *size);
+	if (ret)
+		return ret;
 
 	ret = tb_eeprom_read_n(sw, 0, sw->drom, *size);
 	if (ret)
-		goto err;
-
-	return 0;
+		tb_switch_drom_free(sw);
 
-err:
-	kfree(sw->drom);
-	sw->drom = NULL;
 	return ret;
 }
 
@@ -646,9 +658,7 @@ static int tb_drom_parse(struct tb_switch *sw, u16 size)
 	return 0;
 
 err:
-	kfree(sw->drom);
-	sw->drom = NULL;
-
+	tb_switch_drom_free(sw);
 	return ret;
 }
 
diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c
index f760e54cd9bd..e1a5f6e3d0b6 100644
--- a/drivers/thunderbolt/path.c
+++ b/drivers/thunderbolt/path.c
@@ -581,10 +581,10 @@ int tb_path_activate(struct tb_path *path)
 		}
 	}
 	path->activated = true;
-	tb_dbg(path->tb, "path activation complete\n");
+	tb_dbg(path->tb, "%s path activation complete\n", path->name);
 	return 0;
 err:
-	tb_WARN(path->tb, "path activation failed\n");
+	tb_WARN(path->tb, "%s path activation failed\n", path->name);
 	return res;
 }
 
diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index eeb64433ebbc..1f25529fe05d 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -472,7 +472,7 @@ struct tb_retimer_lookup {
 	u8 index;
 };
 
-static int retimer_match(struct device *dev, void *data)
+static int retimer_match(struct device *dev, const void *data)
 {
 	const struct tb_retimer_lookup *lookup = data;
 	struct tb_retimer *rt = tb_to_retimer(dev);
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index a7c6919fbf97..390abcfe7188 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -20,6 +20,12 @@
 #define TB_RELEASE_BW_TIMEOUT	10000	/* ms */
 
 /*
+ * How many time bandwidth allocation request from graphics driver is
+ * retried if the DP tunnel is still activating.
+ */
+#define TB_BW_ALLOC_RETRIES	3
+
+/*
  * Minimum bandwidth (in Mb/s) that is needed in the single transmitter/receiver
  * direction. This is 40G - 10% guard band bandwidth.
  */
@@ -69,14 +75,20 @@ static inline struct tb *tcm_to_tb(struct tb_cm *tcm)
 }
 
 struct tb_hotplug_event {
-	struct work_struct work;
+	struct delayed_work work;
 	struct tb *tb;
 	u64 route;
 	u8 port;
 	bool unplug;
+	int retry;
 };
 
+static void tb_scan_port(struct tb_port *port);
 static void tb_handle_hotplug(struct work_struct *work);
+static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port,
+				       const char *reason);
+static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port,
+					  int retry, unsigned long delay);
 
 static void tb_queue_hotplug(struct tb *tb, u64 route, u8 port, bool unplug)
 {
@@ -90,8 +102,8 @@ static void tb_queue_hotplug(struct tb *tb, u64 route, u8 port, bool unplug)
 	ev->route = route;
 	ev->port = port;
 	ev->unplug = unplug;
-	INIT_WORK(&ev->work, tb_handle_hotplug);
-	queue_work(tb->wq, &ev->work);
+	INIT_DELAYED_WORK(&ev->work, tb_handle_hotplug);
+	queue_delayed_work(tb->wq, &ev->work, 0);
 }
 
 /* enumeration & hot plug handling */
@@ -961,7 +973,7 @@ static int tb_tunnel_usb3(struct tb *tb, struct tb_switch *sw)
 	return 0;
 
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 err_reclaim:
 	if (tb_route(parent))
 		tb_reclaim_usb3_bandwidth(tb, down, up);
@@ -1238,8 +1250,6 @@ static void tb_configure_link(struct tb_port *down, struct tb_port *up,
 	tb_switch_configure_link(sw);
 }
 
-static void tb_scan_port(struct tb_port *port);
-
 /*
  * tb_scan_switch() - scan for and initialize downstream switches
  */
@@ -1727,7 +1737,7 @@ static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel)
 		break;
 	}
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 /*
@@ -1864,12 +1874,76 @@ static struct tb_port *tb_find_dp_out(struct tb *tb, struct tb_port *in)
 	return NULL;
 }
 
-static bool tb_tunnel_one_dp(struct tb *tb, struct tb_port *in,
+static void tb_dp_tunnel_active(struct tb_tunnel *tunnel, void *data)
+{
+	struct tb_port *in = tunnel->src_port;
+	struct tb_port *out = tunnel->dst_port;
+	struct tb *tb = data;
+
+	mutex_lock(&tb->lock);
+	if (tb_tunnel_is_active(tunnel)) {
+		int consumed_up, consumed_down, ret;
+
+		tb_tunnel_dbg(tunnel, "DPRX capabilities read completed\n");
+
+		/* If fail reading tunnel's consumed bandwidth, tear it down */
+		ret = tb_tunnel_consumed_bandwidth(tunnel, &consumed_up,
+						   &consumed_down);
+		if (ret) {
+			tb_tunnel_warn(tunnel,
+				       "failed to read consumed bandwidth, tearing down\n");
+			tb_deactivate_and_free_tunnel(tunnel);
+		} else {
+			tb_reclaim_usb3_bandwidth(tb, in, out);
+			/*
+			 * Transition the links to asymmetric if the
+			 * consumption exceeds the threshold.
+			 */
+			tb_configure_asym(tb, in, out, consumed_up,
+					  consumed_down);
+			/*
+			 * Update the domain with the new bandwidth
+			 * estimation.
+			 */
+			tb_recalc_estimated_bandwidth(tb);
+			/*
+			 * In case of DP tunnel exists, change host
+			 * router's 1st children TMU mode to HiFi for
+			 * CL0s to work.
+			 */
+			tb_increase_tmu_accuracy(tunnel);
+		}
+	} else {
+		struct tb_port *in = tunnel->src_port;
+
+		/*
+		 * This tunnel failed to establish. This means DPRX
+		 * negotiation most likely did not complete which
+		 * happens either because there is no graphics driver
+		 * loaded or not all DP cables where connected to the
+		 * discrete router.
+		 *
+		 * In both cases we remove the DP IN adapter from the
+		 * available resources as it is not usable. This will
+		 * also tear down the tunnel and try to re-use the
+		 * released DP OUT.
+		 *
+		 * It will be added back only if there is hotplug for
+		 * the DP IN again.
+		 */
+		tb_tunnel_warn(tunnel, "not active, tearing down\n");
+		tb_dp_resource_unavailable(tb, in, "DPRX negotiation failed");
+	}
+	mutex_unlock(&tb->lock);
+
+	tb_domain_put(tb);
+}
+
+static void tb_tunnel_one_dp(struct tb *tb, struct tb_port *in,
 			     struct tb_port *out)
 {
 	int available_up, available_down, ret, link_nr;
 	struct tb_cm *tcm = tb_priv(tb);
-	int consumed_up, consumed_down;
 	struct tb_tunnel *tunnel;
 
 	/*
@@ -1921,47 +1995,29 @@ static bool tb_tunnel_one_dp(struct tb *tb, struct tb_port *in,
 	       available_up, available_down);
 
 	tunnel = tb_tunnel_alloc_dp(tb, in, out, link_nr, available_up,
-				    available_down);
+				    available_down, tb_dp_tunnel_active,
+				    tb_domain_get(tb));
 	if (!tunnel) {
 		tb_port_dbg(out, "could not allocate DP tunnel\n");
 		goto err_reclaim_usb;
 	}
 
-	if (tb_tunnel_activate(tunnel)) {
+	list_add_tail(&tunnel->list, &tcm->tunnel_list);
+
+	ret = tb_tunnel_activate(tunnel);
+	if (ret && ret != -EINPROGRESS) {
 		tb_port_info(out, "DP tunnel activation failed, aborting\n");
+		list_del(&tunnel->list);
 		goto err_free;
 	}
 
-	/* If fail reading tunnel's consumed bandwidth, tear it down */
-	ret = tb_tunnel_consumed_bandwidth(tunnel, &consumed_up, &consumed_down);
-	if (ret)
-		goto err_deactivate;
-
-	list_add_tail(&tunnel->list, &tcm->tunnel_list);
-
-	tb_reclaim_usb3_bandwidth(tb, in, out);
-	/*
-	 * Transition the links to asymmetric if the consumption exceeds
-	 * the threshold.
-	 */
-	tb_configure_asym(tb, in, out, consumed_up, consumed_down);
-
-	/* Update the domain with the new bandwidth estimation */
-	tb_recalc_estimated_bandwidth(tb);
-
-	/*
-	 * In case of DP tunnel exists, change host router's 1st children
-	 * TMU mode to HiFi for CL0s to work.
-	 */
-	tb_increase_tmu_accuracy(tunnel);
-	return true;
+	return;
 
-err_deactivate:
-	tb_tunnel_deactivate(tunnel);
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 err_reclaim_usb:
 	tb_reclaim_usb3_bandwidth(tb, in, out);
+	tb_domain_put(tb);
 err_detach_group:
 	tb_detach_bandwidth_group(in);
 err_dealloc_dp:
@@ -1971,8 +2027,6 @@ err_rpm_put:
 	pm_runtime_put_autosuspend(&out->sw->dev);
 	pm_runtime_mark_last_busy(&in->sw->dev);
 	pm_runtime_put_autosuspend(&in->sw->dev);
-
-	return false;
 }
 
 static void tb_tunnel_dp(struct tb *tb)
@@ -2090,17 +2144,18 @@ static void tb_switch_exit_redrive(struct tb_switch *sw)
 	}
 }
 
-static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port)
+static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port,
+				       const char *reason)
 {
 	struct tb_port *in, *out;
 	struct tb_tunnel *tunnel;
 
 	if (tb_port_is_dpin(port)) {
-		tb_port_dbg(port, "DP IN resource unavailable\n");
+		tb_port_dbg(port, "DP IN resource unavailable: %s\n", reason);
 		in = port;
 		out = NULL;
 	} else {
-		tb_port_dbg(port, "DP OUT resource unavailable\n");
+		tb_port_dbg(port, "DP OUT resource unavailable: %s\n", reason);
 		in = NULL;
 		out = port;
 	}
@@ -2182,7 +2237,7 @@ static int tb_disconnect_pci(struct tb *tb, struct tb_switch *sw)
 
 	tb_tunnel_deactivate(tunnel);
 	list_del(&tunnel->list);
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 	return 0;
 }
 
@@ -2212,7 +2267,7 @@ static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw)
 	if (tb_tunnel_activate(tunnel)) {
 		tb_port_info(up,
 			     "PCIe tunnel activation failed, aborting\n");
-		tb_tunnel_free(tunnel);
+		tb_tunnel_put(tunnel);
 		return -EIO;
 	}
 
@@ -2271,7 +2326,7 @@ static int tb_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd,
 	return 0;
 
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 err_clx:
 	tb_enable_clx(sw);
 	mutex_unlock(&tb->lock);
@@ -2334,7 +2389,7 @@ static int tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd,
  */
 static void tb_handle_hotplug(struct work_struct *work)
 {
-	struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work);
+	struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work.work);
 	struct tb *tb = ev->tb;
 	struct tb_cm *tcm = tb_priv(tb);
 	struct tb_switch *sw;
@@ -2406,7 +2461,7 @@ static void tb_handle_hotplug(struct work_struct *work)
 			tb_xdomain_put(xd);
 			tb_port_unconfigure_xdomain(port);
 		} else if (tb_port_is_dpout(port) || tb_port_is_dpin(port)) {
-			tb_dp_resource_unavailable(tb, port);
+			tb_dp_resource_unavailable(tb, port, "adapter unplug");
 		} else if (!port->port) {
 			tb_sw_dbg(sw, "xHCI disconnect request\n");
 			tb_switch_xhci_disconnect(sw);
@@ -2639,7 +2694,7 @@ fail:
 
 static void tb_handle_dp_bandwidth_request(struct work_struct *work)
 {
-	struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work);
+	struct tb_hotplug_event *ev = container_of(work, typeof(*ev), work.work);
 	int requested_bw, requested_up, requested_down, ret;
 	struct tb_tunnel *tunnel;
 	struct tb *tb = ev->tb;
@@ -2666,7 +2721,7 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work)
 		goto put_sw;
 	}
 
-	tb_port_dbg(in, "handling bandwidth allocation request\n");
+	tb_port_dbg(in, "handling bandwidth allocation request, retry %d\n", ev->retry);
 
 	tunnel = tb_find_tunnel(tb, TB_TUNNEL_DP, in, NULL);
 	if (!tunnel) {
@@ -2719,12 +2774,33 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work)
 
 	ret = tb_alloc_dp_bandwidth(tunnel, &requested_up, &requested_down);
 	if (ret) {
-		if (ret == -ENOBUFS)
+		if (ret == -ENOBUFS) {
 			tb_tunnel_warn(tunnel,
 				       "not enough bandwidth available\n");
-		else
+		} else if (ret == -ENOTCONN) {
+			tb_tunnel_dbg(tunnel, "not active yet\n");
+			/*
+			 * We got bandwidth allocation request but the
+			 * tunnel is not yet active. This means that
+			 * tb_dp_tunnel_active() is not yet called for
+			 * this tunnel. Allow it some time and retry
+			 * this request a couple of times.
+			 */
+			if (ev->retry < TB_BW_ALLOC_RETRIES) {
+				tb_tunnel_dbg(tunnel,
+					      "retrying bandwidth allocation request\n");
+				tb_queue_dp_bandwidth_request(tb, ev->route,
+							      ev->port,
+							      ev->retry + 1,
+							      msecs_to_jiffies(50));
+			} else {
+				tb_tunnel_dbg(tunnel,
+					      "run out of retries, failing the request");
+			}
+		} else {
 			tb_tunnel_warn(tunnel,
 				       "failed to change bandwidth allocation\n");
+		}
 	} else {
 		tb_tunnel_dbg(tunnel,
 			      "bandwidth allocation changed to %d/%d Mb/s\n",
@@ -2745,7 +2821,8 @@ unlock:
 	kfree(ev);
 }
 
-static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port)
+static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port,
+					  int retry, unsigned long delay)
 {
 	struct tb_hotplug_event *ev;
 
@@ -2756,8 +2833,9 @@ static void tb_queue_dp_bandwidth_request(struct tb *tb, u64 route, u8 port)
 	ev->tb = tb;
 	ev->route = route;
 	ev->port = port;
-	INIT_WORK(&ev->work, tb_handle_dp_bandwidth_request);
-	queue_work(tb->wq, &ev->work);
+	ev->retry = retry;
+	INIT_DELAYED_WORK(&ev->work, tb_handle_dp_bandwidth_request);
+	queue_delayed_work(tb->wq, &ev->work, delay);
 }
 
 static void tb_handle_notification(struct tb *tb, u64 route,
@@ -2777,7 +2855,7 @@ static void tb_handle_notification(struct tb *tb, u64 route,
 		if (tb_cfg_ack_notification(tb->ctl, route, error))
 			tb_warn(tb, "could not ack notification on %llx\n",
 				route);
-		tb_queue_dp_bandwidth_request(tb, route, error->port);
+		tb_queue_dp_bandwidth_request(tb, route, error->port, 0, 0);
 		break;
 
 	default:
@@ -2832,7 +2910,7 @@ static void tb_stop(struct tb *tb)
 		 */
 		if (tb_tunnel_is_dma(tunnel))
 			tb_tunnel_deactivate(tunnel);
-		tb_tunnel_free(tunnel);
+		tb_tunnel_put(tunnel);
 	}
 	tb_switch_remove(tb->root_switch);
 	tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */
@@ -3028,7 +3106,7 @@ static int tb_resume_noirq(struct tb *tb)
 		if (tb_tunnel_is_usb3(tunnel))
 			usb3_delay = 500;
 		tb_tunnel_deactivate(tunnel);
-		tb_tunnel_free(tunnel);
+		tb_tunnel_put(tunnel);
 	}
 
 	/* Re-create our tunnels now */
@@ -3039,7 +3117,7 @@ static int tb_resume_noirq(struct tb *tb)
 			/* Only need to do it once */
 			usb3_delay = 0;
 		}
-		tb_tunnel_restart(tunnel);
+		tb_tunnel_activate(tunnel);
 	}
 	if (!list_empty(&tcm->tunnel_list)) {
 		/*
@@ -3149,7 +3227,7 @@ static int tb_runtime_resume(struct tb *tb)
 	tb_free_invalid_tunnels(tb);
 	tb_restore_children(tb->root_switch);
 	list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list)
-		tb_tunnel_restart(tunnel);
+		tb_tunnel_activate(tunnel);
 	tb_switch_enter_redrive(tb->root_switch);
 	tcm->hotplug_active = true;
 	mutex_unlock(&tb->lock);
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index ddbf0cd78377..b54147a1ba87 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -9,6 +9,7 @@
 #ifndef TB_H_
 #define TB_H_
 
+#include <linux/debugfs.h>
 #include <linux/nvmem-provider.h>
 #include <linux/pci.h>
 #include <linux/thunderbolt.h>
@@ -160,6 +161,7 @@ struct tb_switch_tmu {
  * @max_pcie_credits: Router preferred number of buffers for PCIe
  * @max_dma_credits: Router preferred number of buffers for DMA/P2P
  * @clx: CLx states on the upstream link of the router
+ * @drom_blob: DROM debugfs blob wrapper
  *
  * When the switch is being added or removed to the domain (other
  * switches) you need to have domain lock held.
@@ -212,6 +214,9 @@ struct tb_switch {
 	unsigned int max_pcie_credits;
 	unsigned int max_dma_credits;
 	unsigned int clx;
+#ifdef CONFIG_DEBUG_FS
+	struct debugfs_blob_wrapper drom_blob;
+#endif
 };
 
 /**
diff --git a/drivers/thunderbolt/test.c b/drivers/thunderbolt/test.c
index 9475c6698c7d..1f4318249c22 100644
--- a/drivers/thunderbolt/test.c
+++ b/drivers/thunderbolt/test.c
@@ -1382,8 +1382,8 @@ static void tb_test_tunnel_pcie(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[0].in_port, up);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[1].out_port, down);
 
-	tb_tunnel_free(tunnel2);
-	tb_tunnel_free(tunnel1);
+	tb_tunnel_put(tunnel2);
+	tb_tunnel_put(tunnel1);
 }
 
 static void tb_test_tunnel_dp(struct kunit *test)
@@ -1406,7 +1406,7 @@ static void tb_test_tunnel_dp(struct kunit *test)
 	in = &host->ports[5];
 	out = &dev->ports[13];
 
-	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
 	KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in);
@@ -1421,7 +1421,7 @@ static void tb_test_tunnel_dp(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, tunnel->paths[2]->path_length, 2);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[0].in_port, out);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[1].out_port, in);
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dp_chain(struct kunit *test)
@@ -1452,7 +1452,7 @@ static void tb_test_tunnel_dp_chain(struct kunit *test)
 	in = &host->ports[5];
 	out = &dev4->ports[14];
 
-	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
 	KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in);
@@ -1467,7 +1467,7 @@ static void tb_test_tunnel_dp_chain(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, tunnel->paths[2]->path_length, 3);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[0].in_port, out);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[2].out_port, in);
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dp_tree(struct kunit *test)
@@ -1502,7 +1502,7 @@ static void tb_test_tunnel_dp_tree(struct kunit *test)
 	in = &dev2->ports[13];
 	out = &dev5->ports[13];
 
-	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
 	KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in);
@@ -1517,7 +1517,7 @@ static void tb_test_tunnel_dp_tree(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, tunnel->paths[2]->path_length, 4);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[0].in_port, out);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[3].out_port, in);
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dp_max_length(struct kunit *test)
@@ -1567,7 +1567,7 @@ static void tb_test_tunnel_dp_max_length(struct kunit *test)
 	in = &dev6->ports[13];
 	out = &dev12->ports[13];
 
-	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
 	KUNIT_EXPECT_EQ(test, tunnel->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->src_port, in);
@@ -1597,7 +1597,7 @@ static void tb_test_tunnel_dp_max_length(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[6].out_port,
 			    &host->ports[1]);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[2]->hops[12].out_port, in);
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_3dp(struct kunit *test)
@@ -1637,7 +1637,7 @@ static void tb_test_tunnel_3dp(struct kunit *test)
 	out2 = &dev5->ports[13];
 	out3 = &dev4->ports[14];
 
-	tunnel1 = tb_tunnel_alloc_dp(NULL, in1, out1, 1, 0, 0);
+	tunnel1 = tb_tunnel_alloc_dp(NULL, in1, out1, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_TRUE(test, tunnel1 != NULL);
 	KUNIT_EXPECT_EQ(test, tunnel1->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel1->src_port, in1);
@@ -1645,7 +1645,7 @@ static void tb_test_tunnel_3dp(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, tunnel1->npaths, 3);
 	KUNIT_ASSERT_EQ(test, tunnel1->paths[0]->path_length, 3);
 
-	tunnel2 = tb_tunnel_alloc_dp(NULL, in2, out2, 1, 0, 0);
+	tunnel2 = tb_tunnel_alloc_dp(NULL, in2, out2, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_TRUE(test, tunnel2 != NULL);
 	KUNIT_EXPECT_EQ(test, tunnel2->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel2->src_port, in2);
@@ -1653,7 +1653,7 @@ static void tb_test_tunnel_3dp(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, tunnel2->npaths, 3);
 	KUNIT_ASSERT_EQ(test, tunnel2->paths[0]->path_length, 4);
 
-	tunnel3 = tb_tunnel_alloc_dp(NULL, in3, out3, 1, 0, 0);
+	tunnel3 = tb_tunnel_alloc_dp(NULL, in3, out3, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_TRUE(test, tunnel3 != NULL);
 	KUNIT_EXPECT_EQ(test, tunnel3->type, TB_TUNNEL_DP);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel3->src_port, in3);
@@ -1661,8 +1661,8 @@ static void tb_test_tunnel_3dp(struct kunit *test)
 	KUNIT_ASSERT_EQ(test, tunnel3->npaths, 3);
 	KUNIT_ASSERT_EQ(test, tunnel3->paths[0]->path_length, 3);
 
-	tb_tunnel_free(tunnel2);
-	tb_tunnel_free(tunnel1);
+	tb_tunnel_put(tunnel2);
+	tb_tunnel_put(tunnel1);
 }
 
 static void tb_test_tunnel_usb3(struct kunit *test)
@@ -1716,8 +1716,8 @@ static void tb_test_tunnel_usb3(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[0].in_port, up);
 	KUNIT_EXPECT_PTR_EQ(test, tunnel2->paths[1]->hops[1].out_port, down);
 
-	tb_tunnel_free(tunnel2);
-	tb_tunnel_free(tunnel1);
+	tb_tunnel_put(tunnel2);
+	tb_tunnel_put(tunnel1);
 }
 
 static void tb_test_tunnel_port_on_path(struct kunit *test)
@@ -1750,7 +1750,7 @@ static void tb_test_tunnel_port_on_path(struct kunit *test)
 	in = &dev2->ports[13];
 	out = &dev5->ports[13];
 
-	dp_tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	dp_tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, dp_tunnel);
 
 	KUNIT_EXPECT_TRUE(test, tb_tunnel_port_on_path(dp_tunnel, in));
@@ -1783,7 +1783,7 @@ static void tb_test_tunnel_port_on_path(struct kunit *test)
 	port = &dev4->ports[1];
 	KUNIT_EXPECT_FALSE(test, tb_tunnel_port_on_path(dp_tunnel, port));
 
-	tb_tunnel_free(dp_tunnel);
+	tb_tunnel_put(dp_tunnel);
 }
 
 static void tb_test_tunnel_dma(struct kunit *test)
@@ -1826,7 +1826,7 @@ static void tb_test_tunnel_dma(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[1]->hops[0].out_port, port);
 	KUNIT_EXPECT_EQ(test, tunnel->paths[1]->hops[0].next_hop_index, 8);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dma_rx(struct kunit *test)
@@ -1863,7 +1863,7 @@ static void tb_test_tunnel_dma_rx(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[0]->hops[0].out_port, nhi);
 	KUNIT_EXPECT_EQ(test, tunnel->paths[0]->hops[0].next_hop_index, 2);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dma_tx(struct kunit *test)
@@ -1900,7 +1900,7 @@ static void tb_test_tunnel_dma_tx(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[0]->hops[0].out_port, port);
 	KUNIT_EXPECT_EQ(test, tunnel->paths[0]->hops[0].next_hop_index, 15);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dma_chain(struct kunit *test)
@@ -1966,7 +1966,7 @@ static void tb_test_tunnel_dma_chain(struct kunit *test)
 	KUNIT_EXPECT_PTR_EQ(test, tunnel->paths[1]->hops[2].out_port, port);
 	KUNIT_EXPECT_EQ(test, tunnel->paths[1]->hops[2].next_hop_index, 8);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_tunnel_dma_match(struct kunit *test)
@@ -1993,7 +1993,7 @@ static void tb_test_tunnel_dma_match(struct kunit *test)
 	KUNIT_ASSERT_TRUE(test, tb_tunnel_match_dma(tunnel, -1, -1, -1, -1));
 	KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, 8, -1, 8, -1));
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 
 	tunnel = tb_tunnel_alloc_dma(NULL, nhi, port, 15, 1, -1, -1);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
@@ -2005,7 +2005,7 @@ static void tb_test_tunnel_dma_match(struct kunit *test)
 	KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, -1, -1, 15, 1));
 	KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, 15, 11, -1, -1));
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 
 	tunnel = tb_tunnel_alloc_dma(NULL, nhi, port, -1, -1, 15, 11);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
@@ -2017,7 +2017,7 @@ static void tb_test_tunnel_dma_match(struct kunit *test)
 	KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, -1, -1, 10, 11));
 	KUNIT_ASSERT_FALSE(test, tb_tunnel_match_dma(tunnel, 15, 11, -1, -1));
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_legacy_not_bonded(struct kunit *test)
@@ -2050,7 +2050,7 @@ static void tb_test_credit_alloc_legacy_not_bonded(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 16U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_legacy_bonded(struct kunit *test)
@@ -2083,7 +2083,7 @@ static void tb_test_credit_alloc_legacy_bonded(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 32U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_pcie(struct kunit *test)
@@ -2116,7 +2116,7 @@ static void tb_test_credit_alloc_pcie(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 64U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_without_dp(struct kunit *test)
@@ -2166,7 +2166,7 @@ static void tb_test_credit_alloc_without_dp(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 64U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_dp(struct kunit *test)
@@ -2182,7 +2182,7 @@ static void tb_test_credit_alloc_dp(struct kunit *test)
 	in = &host->ports[5];
 	out = &dev->ports[14];
 
-	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	tunnel = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel);
 	KUNIT_ASSERT_EQ(test, tunnel->npaths, (size_t)3);
 
@@ -2210,7 +2210,7 @@ static void tb_test_credit_alloc_dp(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 1U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_usb3(struct kunit *test)
@@ -2243,7 +2243,7 @@ static void tb_test_credit_alloc_usb3(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 32U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_dma(struct kunit *test)
@@ -2279,7 +2279,7 @@ static void tb_test_credit_alloc_dma(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 14U);
 
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 }
 
 static void tb_test_credit_alloc_dma_multiple(struct kunit *test)
@@ -2356,7 +2356,7 @@ static void tb_test_credit_alloc_dma_multiple(struct kunit *test)
 	 * Release the first DMA tunnel. That should make 14 buffers
 	 * available for the next tunnel.
 	 */
-	tb_tunnel_free(tunnel1);
+	tb_tunnel_put(tunnel1);
 
 	tunnel3 = tb_tunnel_alloc_dma(NULL, nhi, port, 10, 3, 10, 3);
 	KUNIT_ASSERT_NOT_NULL(test, tunnel3);
@@ -2375,8 +2375,8 @@ static void tb_test_credit_alloc_dma_multiple(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, path->hops[1].nfc_credits, 0U);
 	KUNIT_EXPECT_EQ(test, path->hops[1].initial_credits, 14U);
 
-	tb_tunnel_free(tunnel3);
-	tb_tunnel_free(tunnel2);
+	tb_tunnel_put(tunnel3);
+	tb_tunnel_put(tunnel2);
 }
 
 static struct tb_tunnel *TB_TEST_PCIE_TUNNEL(struct kunit *test,
@@ -2418,7 +2418,7 @@ static struct tb_tunnel *TB_TEST_DP_TUNNEL1(struct kunit *test,
 
 	in = &host->ports[5];
 	out = &dev->ports[13];
-	dp_tunnel1 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	dp_tunnel1 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, dp_tunnel1);
 	KUNIT_ASSERT_EQ(test, dp_tunnel1->npaths, (size_t)3);
 
@@ -2455,7 +2455,7 @@ static struct tb_tunnel *TB_TEST_DP_TUNNEL2(struct kunit *test,
 
 	in = &host->ports[6];
 	out = &dev->ports[14];
-	dp_tunnel2 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0);
+	dp_tunnel2 = tb_tunnel_alloc_dp(NULL, in, out, 1, 0, 0, NULL, NULL);
 	KUNIT_ASSERT_NOT_NULL(test, dp_tunnel2);
 	KUNIT_ASSERT_EQ(test, dp_tunnel2->npaths, (size_t)3);
 
@@ -2595,12 +2595,12 @@ static void tb_test_credit_alloc_all(struct kunit *test)
 	dma_tunnel1 = TB_TEST_DMA_TUNNEL1(test, host, dev);
 	dma_tunnel2 = TB_TEST_DMA_TUNNEL2(test, host, dev);
 
-	tb_tunnel_free(dma_tunnel2);
-	tb_tunnel_free(dma_tunnel1);
-	tb_tunnel_free(usb3_tunnel);
-	tb_tunnel_free(dp_tunnel2);
-	tb_tunnel_free(dp_tunnel1);
-	tb_tunnel_free(pcie_tunnel);
+	tb_tunnel_put(dma_tunnel2);
+	tb_tunnel_put(dma_tunnel1);
+	tb_tunnel_put(usb3_tunnel);
+	tb_tunnel_put(dp_tunnel2);
+	tb_tunnel_put(dp_tunnel1);
+	tb_tunnel_put(pcie_tunnel);
 }
 
 static const u32 root_directory[] = {
diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 41cf6378ad25..8229a6fbda5a 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -70,6 +70,24 @@
 #define USB4_V2_PCI_MIN_BANDWIDTH	(1500 * TB_PCI_WEIGHT)
 #define USB4_V2_USB3_MIN_BANDWIDTH	(1500 * TB_USB3_WEIGHT)
 
+/*
+ * According to VESA spec, the DPRX negotiation shall compete in 5
+ * seconds after tunnel is established. Since at least i915 can runtime
+ * suspend if there is nothing connected, and that it polls any new
+ * connections every 10 seconds, we use 12 seconds here.
+ *
+ * These are in ms.
+ */
+#define TB_DPRX_TIMEOUT			12000
+#define TB_DPRX_WAIT_TIMEOUT		25
+#define TB_DPRX_POLL_DELAY		50
+
+static int dprx_timeout = TB_DPRX_TIMEOUT;
+module_param(dprx_timeout, int, 0444);
+MODULE_PARM_DESC(dprx_timeout,
+		 "DPRX capability read timeout in ms, -1 waits forever (default: "
+		 __MODULE_STRING(TB_DPRX_TIMEOUT) ")");
+
 static unsigned int dma_credits = TB_DMA_CREDITS;
 module_param(dma_credits, uint, 0444);
 MODULE_PARM_DESC(dma_credits, "specify custom credits for DMA tunnels (default: "
@@ -82,6 +100,9 @@ MODULE_PARM_DESC(bw_alloc_mode,
 
 static const char * const tb_tunnel_names[] = { "PCI", "DP", "DMA", "USB3" };
 
+/* Synchronizes kref_get()/put() of struct tb_tunnel */
+static DEFINE_MUTEX(tb_tunnel_lock);
+
 static inline unsigned int tb_usable_credits(const struct tb_port *port)
 {
 	return port->total_credits - port->ctl_credits;
@@ -155,7 +176,7 @@ static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths,
 
 	tunnel->paths = kcalloc(npaths, sizeof(tunnel->paths[0]), GFP_KERNEL);
 	if (!tunnel->paths) {
-		tb_tunnel_free(tunnel);
+		kfree(tunnel);
 		return NULL;
 	}
 
@@ -163,10 +184,42 @@ static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths,
 	tunnel->tb = tb;
 	tunnel->npaths = npaths;
 	tunnel->type = type;
+	kref_init(&tunnel->kref);
 
 	return tunnel;
 }
 
+static void tb_tunnel_get(struct tb_tunnel *tunnel)
+{
+	mutex_lock(&tb_tunnel_lock);
+	kref_get(&tunnel->kref);
+	mutex_unlock(&tb_tunnel_lock);
+}
+
+static void tb_tunnel_destroy(struct kref *kref)
+{
+	struct tb_tunnel *tunnel = container_of(kref, typeof(*tunnel), kref);
+	int i;
+
+	if (tunnel->destroy)
+		tunnel->destroy(tunnel);
+
+	for (i = 0; i < tunnel->npaths; i++) {
+		if (tunnel->paths[i])
+			tb_path_free(tunnel->paths[i]);
+	}
+
+	kfree(tunnel->paths);
+	kfree(tunnel);
+}
+
+void tb_tunnel_put(struct tb_tunnel *tunnel)
+{
+	mutex_lock(&tb_tunnel_lock);
+	kref_put(&tunnel->kref, tb_tunnel_destroy);
+	mutex_unlock(&tb_tunnel_lock);
+}
+
 static int tb_pci_set_ext_encapsulation(struct tb_tunnel *tunnel, bool enable)
 {
 	struct tb_port *port = tb_upstream_port(tunnel->dst_port->sw);
@@ -355,7 +408,7 @@ struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down,
 err_deactivate:
 	tb_tunnel_deactivate(tunnel);
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 
 	return NULL;
 }
@@ -404,7 +457,7 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up,
 	return tunnel;
 
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 	return NULL;
 }
 
@@ -851,7 +904,7 @@ static int tb_dp_bandwidth_alloc_mode_enable(struct tb_tunnel *tunnel)
 	return 0;
 }
 
-static int tb_dp_init(struct tb_tunnel *tunnel)
+static int tb_dp_pre_activate(struct tb_tunnel *tunnel)
 {
 	struct tb_port *in = tunnel->src_port;
 	struct tb_switch *sw = in->sw;
@@ -877,7 +930,7 @@ static int tb_dp_init(struct tb_tunnel *tunnel)
 	return tb_dp_bandwidth_alloc_mode_enable(tunnel);
 }
 
-static void tb_dp_deinit(struct tb_tunnel *tunnel)
+static void tb_dp_post_deactivate(struct tb_tunnel *tunnel)
 {
 	struct tb_port *in = tunnel->src_port;
 
@@ -889,6 +942,90 @@ static void tb_dp_deinit(struct tb_tunnel *tunnel)
 	}
 }
 
+static ktime_t dprx_timeout_to_ktime(int timeout_msec)
+{
+	return timeout_msec >= 0 ?
+		ktime_add_ms(ktime_get(), timeout_msec) : KTIME_MAX;
+}
+
+static int tb_dp_wait_dprx(struct tb_tunnel *tunnel, int timeout_msec)
+{
+	ktime_t timeout = dprx_timeout_to_ktime(timeout_msec);
+	struct tb_port *in = tunnel->src_port;
+
+	/*
+	 * Wait for DPRX done. Normally it should be already set for
+	 * active tunnel.
+	 */
+	do {
+		u32 val;
+		int ret;
+
+		ret = tb_port_read(in, &val, TB_CFG_PORT,
+				   in->cap_adap + DP_COMMON_CAP, 1);
+		if (ret)
+			return ret;
+
+		if (val & DP_COMMON_CAP_DPRX_DONE)
+			return 0;
+
+		usleep_range(100, 150);
+	} while (ktime_before(ktime_get(), timeout));
+
+	tb_tunnel_dbg(tunnel, "DPRX read timeout\n");
+	return -ETIMEDOUT;
+}
+
+static void tb_dp_dprx_work(struct work_struct *work)
+{
+	struct tb_tunnel *tunnel = container_of(work, typeof(*tunnel), dprx_work.work);
+	struct tb *tb = tunnel->tb;
+
+	if (!tunnel->dprx_canceled) {
+		mutex_lock(&tb->lock);
+		if (tb_dp_is_usb4(tunnel->src_port->sw) &&
+		    tb_dp_wait_dprx(tunnel, TB_DPRX_WAIT_TIMEOUT)) {
+			if (ktime_before(ktime_get(), tunnel->dprx_timeout)) {
+				queue_delayed_work(tb->wq, &tunnel->dprx_work,
+						   msecs_to_jiffies(TB_DPRX_POLL_DELAY));
+				mutex_unlock(&tb->lock);
+				return;
+			}
+		} else {
+			tunnel->state = TB_TUNNEL_ACTIVE;
+		}
+		mutex_unlock(&tb->lock);
+	}
+
+	if (tunnel->callback)
+		tunnel->callback(tunnel, tunnel->callback_data);
+}
+
+static int tb_dp_dprx_start(struct tb_tunnel *tunnel)
+{
+	/*
+	 * Bump up the reference to keep the tunnel around. It will be
+	 * dropped in tb_dp_dprx_stop() once the tunnel is deactivated.
+	 */
+	tb_tunnel_get(tunnel);
+
+	if (tunnel->callback) {
+		tunnel->dprx_timeout = dprx_timeout_to_ktime(dprx_timeout);
+		queue_delayed_work(tunnel->tb->wq, &tunnel->dprx_work, 0);
+		return -EINPROGRESS;
+	}
+
+	return tb_dp_is_usb4(tunnel->src_port->sw) ?
+		tb_dp_wait_dprx(tunnel, dprx_timeout) : 0;
+}
+
+static void tb_dp_dprx_stop(struct tb_tunnel *tunnel)
+{
+	tunnel->dprx_canceled = true;
+	cancel_delayed_work(&tunnel->dprx_work);
+	tb_tunnel_put(tunnel);
+}
+
 static int tb_dp_activate(struct tb_tunnel *tunnel, bool active)
 {
 	int ret;
@@ -910,6 +1047,7 @@ static int tb_dp_activate(struct tb_tunnel *tunnel, bool active)
 			paths[TB_DP_AUX_PATH_IN]->hops[0].in_hop_index,
 			paths[TB_DP_AUX_PATH_OUT]->hops[last].next_hop_index);
 	} else {
+		tb_dp_dprx_stop(tunnel);
 		tb_dp_port_hpd_clear(tunnel->src_port);
 		tb_dp_port_set_hops(tunnel->src_port, 0, 0, 0);
 		if (tb_port_is_dpout(tunnel->dst_port))
@@ -920,10 +1058,13 @@ static int tb_dp_activate(struct tb_tunnel *tunnel, bool active)
 	if (ret)
 		return ret;
 
-	if (tb_port_is_dpout(tunnel->dst_port))
-		return tb_dp_port_enable(tunnel->dst_port, active);
+	if (tb_port_is_dpout(tunnel->dst_port)) {
+		ret = tb_dp_port_enable(tunnel->dst_port, active);
+		if (ret)
+			return ret;
+	}
 
-	return 0;
+	return active ? tb_dp_dprx_start(tunnel) : 0;
 }
 
 /**
@@ -1076,35 +1217,6 @@ static int tb_dp_alloc_bandwidth(struct tb_tunnel *tunnel, int *alloc_up,
 	return 0;
 }
 
-static int tb_dp_wait_dprx(struct tb_tunnel *tunnel, int timeout_msec)
-{
-	ktime_t timeout = ktime_add_ms(ktime_get(), timeout_msec);
-	struct tb_port *in = tunnel->src_port;
-
-	/*
-	 * Wait for DPRX done. Normally it should be already set for
-	 * active tunnel.
-	 */
-	do {
-		u32 val;
-		int ret;
-
-		ret = tb_port_read(in, &val, TB_CFG_PORT,
-				   in->cap_adap + DP_COMMON_CAP, 1);
-		if (ret)
-			return ret;
-
-		if (val & DP_COMMON_CAP_DPRX_DONE) {
-			tb_tunnel_dbg(tunnel, "DPRX read done\n");
-			return 0;
-		}
-		usleep_range(100, 150);
-	} while (ktime_before(ktime_get(), timeout));
-
-	tb_tunnel_dbg(tunnel, "DPRX read timeout\n");
-	return -ETIMEDOUT;
-}
-
 /* Read cap from tunnel DP IN */
 static int tb_dp_read_cap(struct tb_tunnel *tunnel, unsigned int cap, u32 *rate,
 			  u32 *lanes)
@@ -1168,32 +1280,39 @@ static int tb_dp_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up,
 	int ret;
 
 	if (tb_dp_is_usb4(sw)) {
-		/*
-		 * On USB4 routers check if the bandwidth allocation
-		 * mode is enabled first and then read the bandwidth
-		 * through those registers.
-		 */
-		ret = tb_dp_bandwidth_mode_consumed_bandwidth(tunnel, consumed_up,
-							      consumed_down);
-		if (ret < 0) {
-			if (ret != -EOPNOTSUPP)
+		ret = tb_dp_wait_dprx(tunnel, 0);
+		if (ret) {
+			if (ret == -ETIMEDOUT) {
+				/*
+				 * While we wait for DPRX complete the
+				 * tunnel consumes as much as it had
+				 * been reserved initially.
+				 */
+				ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP,
+						     &rate, &lanes);
+				if (ret)
+					return ret;
+			} else {
+				return ret;
+			}
+		} else {
+			/*
+			 * On USB4 routers check if the bandwidth allocation
+			 * mode is enabled first and then read the bandwidth
+			 * through those registers.
+			 */
+			ret = tb_dp_bandwidth_mode_consumed_bandwidth(tunnel, consumed_up,
+								      consumed_down);
+			if (ret < 0) {
+				if (ret != -EOPNOTSUPP)
+					return ret;
+			} else if (!ret) {
+				return 0;
+			}
+			ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes);
+			if (ret)
 				return ret;
-		} else if (!ret) {
-			return 0;
 		}
-		/*
-		 * Then see if the DPRX negotiation is ready and if yes
-		 * return that bandwidth (it may be smaller than the
-		 * reduced one). According to VESA spec, the DPRX
-		 * negotiation shall compete in 5 seconds after tunnel
-		 * established. We give it 100ms extra just in case.
-		 */
-		ret = tb_dp_wait_dprx(tunnel, 5100);
-		if (ret)
-			return ret;
-		ret = tb_dp_read_cap(tunnel, DP_COMMON_CAP, &rate, &lanes);
-		if (ret)
-			return ret;
 	} else if (sw->generation >= 2) {
 		ret = tb_dp_read_cap(tunnel, DP_REMOTE_CAP, &rate, &lanes);
 		if (ret)
@@ -1365,9 +1484,9 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in,
 	if (!tunnel)
 		return NULL;
 
-	tunnel->init = tb_dp_init;
-	tunnel->deinit = tb_dp_deinit;
+	tunnel->pre_activate = tb_dp_pre_activate;
 	tunnel->activate = tb_dp_activate;
+	tunnel->post_deactivate = tb_dp_post_deactivate;
 	tunnel->maximum_bandwidth = tb_dp_maximum_bandwidth;
 	tunnel->allocated_bandwidth = tb_dp_allocated_bandwidth;
 	tunnel->alloc_bandwidth = tb_dp_alloc_bandwidth;
@@ -1424,7 +1543,7 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in,
 err_deactivate:
 	tb_tunnel_deactivate(tunnel);
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 
 	return NULL;
 }
@@ -1439,15 +1558,24 @@ err_free:
  *	    %0 if no available bandwidth.
  * @max_down: Maximum available downstream bandwidth for the DP tunnel.
  *	      %0 if no available bandwidth.
+ * @callback: Optional callback that is called when the DP tunnel is
+ *	      fully activated (or there is an error)
+ * @callback_data: Optional data for @callback
  *
  * Allocates a tunnel between @in and @out that is capable of tunneling
- * Display Port traffic.
+ * Display Port traffic. If @callback is not %NULL it will be called
+ * after tb_tunnel_activate() once the tunnel has been fully activated.
+ * It can call tb_tunnel_is_active() to check if activation was
+ * successful (or if it returns %false there was some sort of issue).
+ * The @callback is called without @tb->lock held.
  *
- * Return: Returns a tb_tunnel on success or NULL on failure.
+ * Return: Returns a tb_tunnel on success or &NULL on failure.
  */
 struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
 				     struct tb_port *out, int link_nr,
-				     int max_up, int max_down)
+				     int max_up, int max_down,
+				     void (*callback)(struct tb_tunnel *, void *),
+				     void *callback_data)
 {
 	struct tb_tunnel *tunnel;
 	struct tb_path **paths;
@@ -1461,9 +1589,9 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
 	if (!tunnel)
 		return NULL;
 
-	tunnel->init = tb_dp_init;
-	tunnel->deinit = tb_dp_deinit;
+	tunnel->pre_activate = tb_dp_pre_activate;
 	tunnel->activate = tb_dp_activate;
+	tunnel->post_deactivate = tb_dp_post_deactivate;
 	tunnel->maximum_bandwidth = tb_dp_maximum_bandwidth;
 	tunnel->allocated_bandwidth = tb_dp_allocated_bandwidth;
 	tunnel->alloc_bandwidth = tb_dp_alloc_bandwidth;
@@ -1472,6 +1600,9 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
 	tunnel->dst_port = out;
 	tunnel->max_up = max_up;
 	tunnel->max_down = max_down;
+	tunnel->callback = callback;
+	tunnel->callback_data = callback_data;
+	INIT_DELAYED_WORK(&tunnel->dprx_work, tb_dp_dprx_work);
 
 	paths = tunnel->paths;
 	pm_support = usb4_switch_version(in->sw) >= 2;
@@ -1500,7 +1631,7 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
 	return tunnel;
 
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 	return NULL;
 }
 
@@ -1620,7 +1751,7 @@ static void tb_dma_release_credits(struct tb_path_hop *hop)
 	}
 }
 
-static void tb_dma_deinit_path(struct tb_path *path)
+static void tb_dma_destroy_path(struct tb_path *path)
 {
 	struct tb_path_hop *hop;
 
@@ -1628,14 +1759,14 @@ static void tb_dma_deinit_path(struct tb_path *path)
 		tb_dma_release_credits(hop);
 }
 
-static void tb_dma_deinit(struct tb_tunnel *tunnel)
+static void tb_dma_destroy(struct tb_tunnel *tunnel)
 {
 	int i;
 
 	for (i = 0; i < tunnel->npaths; i++) {
 		if (!tunnel->paths[i])
 			continue;
-		tb_dma_deinit_path(tunnel->paths[i]);
+		tb_dma_destroy_path(tunnel->paths[i]);
 	}
 }
 
@@ -1681,7 +1812,7 @@ struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi,
 
 	tunnel->src_port = nhi;
 	tunnel->dst_port = dst;
-	tunnel->deinit = tb_dma_deinit;
+	tunnel->destroy = tb_dma_destroy;
 
 	credits = min_not_zero(dma_credits, nhi->sw->max_dma_credits);
 
@@ -1712,7 +1843,7 @@ struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi,
 	return tunnel;
 
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 	return NULL;
 }
 
@@ -1793,7 +1924,7 @@ static int tb_usb3_max_link_rate(struct tb_port *up, struct tb_port *down)
 	return min(up_max_rate, down_max_rate);
 }
 
-static int tb_usb3_init(struct tb_tunnel *tunnel)
+static int tb_usb3_pre_activate(struct tb_tunnel *tunnel)
 {
 	tb_tunnel_dbg(tunnel, "allocating initial bandwidth %d/%d Mb/s\n",
 		      tunnel->allocated_up, tunnel->allocated_down);
@@ -2024,7 +2155,7 @@ struct tb_tunnel *tb_tunnel_discover_usb3(struct tb *tb, struct tb_port *down,
 		tb_tunnel_dbg(tunnel, "currently allocated bandwidth %d/%d Mb/s\n",
 			      tunnel->allocated_up, tunnel->allocated_down);
 
-		tunnel->init = tb_usb3_init;
+		tunnel->pre_activate = tb_usb3_pre_activate;
 		tunnel->consumed_bandwidth = tb_usb3_consumed_bandwidth;
 		tunnel->release_unused_bandwidth =
 			tb_usb3_release_unused_bandwidth;
@@ -2038,7 +2169,7 @@ struct tb_tunnel *tb_tunnel_discover_usb3(struct tb *tb, struct tb_port *down,
 err_deactivate:
 	tb_tunnel_deactivate(tunnel);
 err_free:
-	tb_tunnel_free(tunnel);
+	tb_tunnel_put(tunnel);
 
 	return NULL;
 }
@@ -2094,7 +2225,7 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up,
 	path = tb_path_alloc(tb, down, TB_USB3_HOPID, up, TB_USB3_HOPID, 0,
 			     "USB3 Down");
 	if (!path) {
-		tb_tunnel_free(tunnel);
+		tb_tunnel_put(tunnel);
 		return NULL;
 	}
 	tb_usb3_init_path(path);
@@ -2103,7 +2234,7 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up,
 	path = tb_path_alloc(tb, up, TB_USB3_HOPID, down, TB_USB3_HOPID, 0,
 			     "USB3 Up");
 	if (!path) {
-		tb_tunnel_free(tunnel);
+		tb_tunnel_put(tunnel);
 		return NULL;
 	}
 	tb_usb3_init_path(path);
@@ -2113,7 +2244,7 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up,
 		tunnel->allocated_up = min(max_rate, max_up);
 		tunnel->allocated_down = min(max_rate, max_down);
 
-		tunnel->init = tb_usb3_init;
+		tunnel->pre_activate = tb_usb3_pre_activate;
 		tunnel->consumed_bandwidth = tb_usb3_consumed_bandwidth;
 		tunnel->release_unused_bandwidth =
 			tb_usb3_release_unused_bandwidth;
@@ -2125,31 +2256,6 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up,
 }
 
 /**
- * tb_tunnel_free() - free a tunnel
- * @tunnel: Tunnel to be freed
- *
- * Frees a tunnel. The tunnel does not need to be deactivated.
- */
-void tb_tunnel_free(struct tb_tunnel *tunnel)
-{
-	int i;
-
-	if (!tunnel)
-		return;
-
-	if (tunnel->deinit)
-		tunnel->deinit(tunnel);
-
-	for (i = 0; i < tunnel->npaths; i++) {
-		if (tunnel->paths[i])
-			tb_path_free(tunnel->paths[i]);
-	}
-
-	kfree(tunnel->paths);
-	kfree(tunnel);
-}
-
-/**
  * tb_tunnel_is_invalid - check whether an activated path is still valid
  * @tunnel: Tunnel to check
  */
@@ -2167,12 +2273,15 @@ bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel)
 }
 
 /**
- * tb_tunnel_restart() - activate a tunnel after a hardware reset
- * @tunnel: Tunnel to restart
+ * tb_tunnel_activate() - activate a tunnel
+ * @tunnel: Tunnel to activate
  *
- * Return: 0 on success and negative errno in case if failure
+ * Return: 0 on success and negative errno in case if failure.
+ * Specifically returns %-EINPROGRESS if the tunnel activation is still
+ * in progress (that's for DP tunnels to complete DPRX capabilities
+ * read).
  */
-int tb_tunnel_restart(struct tb_tunnel *tunnel)
+int tb_tunnel_activate(struct tb_tunnel *tunnel)
 {
 	int res, i;
 
@@ -2189,8 +2298,10 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel)
 		}
 	}
 
-	if (tunnel->init) {
-		res = tunnel->init(tunnel);
+	tunnel->state = TB_TUNNEL_ACTIVATING;
+
+	if (tunnel->pre_activate) {
+		res = tunnel->pre_activate(tunnel);
 		if (res)
 			return res;
 	}
@@ -2203,10 +2314,14 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel)
 
 	if (tunnel->activate) {
 		res = tunnel->activate(tunnel, true);
-		if (res)
+		if (res) {
+			if (res == -EINPROGRESS)
+				return res;
 			goto err;
+		}
 	}
 
+	tunnel->state = TB_TUNNEL_ACTIVE;
 	return 0;
 
 err:
@@ -2216,27 +2331,6 @@ err:
 }
 
 /**
- * tb_tunnel_activate() - activate a tunnel
- * @tunnel: Tunnel to activate
- *
- * Return: Returns 0 on success or an error code on failure.
- */
-int tb_tunnel_activate(struct tb_tunnel *tunnel)
-{
-	int i;
-
-	for (i = 0; i < tunnel->npaths; i++) {
-		if (tunnel->paths[i]->activated) {
-			tb_tunnel_WARN(tunnel,
-				       "trying to activate an already activated tunnel\n");
-			return -EINVAL;
-		}
-	}
-
-	return tb_tunnel_restart(tunnel);
-}
-
-/**
  * tb_tunnel_deactivate() - deactivate a tunnel
  * @tunnel: Tunnel to deactivate
  */
@@ -2253,6 +2347,11 @@ void tb_tunnel_deactivate(struct tb_tunnel *tunnel)
 		if (tunnel->paths[i] && tunnel->paths[i]->activated)
 			tb_path_deactivate(tunnel->paths[i]);
 	}
+
+	if (tunnel->post_deactivate)
+		tunnel->post_deactivate(tunnel);
+
+	tunnel->state = TB_TUNNEL_INACTIVE;
 }
 
 /**
@@ -2279,18 +2378,10 @@ bool tb_tunnel_port_on_path(const struct tb_tunnel *tunnel,
 	return false;
 }
 
-static bool tb_tunnel_is_active(const struct tb_tunnel *tunnel)
+// Is tb_tunnel_activate() called for the tunnel
+static bool tb_tunnel_is_activated(const struct tb_tunnel *tunnel)
 {
-	int i;
-
-	for (i = 0; i < tunnel->npaths; i++) {
-		if (!tunnel->paths[i])
-			return false;
-		if (!tunnel->paths[i]->activated)
-			return false;
-	}
-
-	return true;
+	return tunnel->state == TB_TUNNEL_ACTIVATING || tb_tunnel_is_active(tunnel);
 }
 
 /**
@@ -2307,7 +2398,7 @@ int tb_tunnel_maximum_bandwidth(struct tb_tunnel *tunnel, int *max_up,
 				int *max_down)
 {
 	if (!tb_tunnel_is_active(tunnel))
-		return -EINVAL;
+		return -ENOTCONN;
 
 	if (tunnel->maximum_bandwidth)
 		return tunnel->maximum_bandwidth(tunnel, max_up, max_down);
@@ -2328,7 +2419,7 @@ int tb_tunnel_allocated_bandwidth(struct tb_tunnel *tunnel, int *allocated_up,
 				  int *allocated_down)
 {
 	if (!tb_tunnel_is_active(tunnel))
-		return -EINVAL;
+		return -ENOTCONN;
 
 	if (tunnel->allocated_bandwidth)
 		return tunnel->allocated_bandwidth(tunnel, allocated_up,
@@ -2351,7 +2442,7 @@ int tb_tunnel_alloc_bandwidth(struct tb_tunnel *tunnel, int *alloc_up,
 			      int *alloc_down)
 {
 	if (!tb_tunnel_is_active(tunnel))
-		return -EINVAL;
+		return -ENOTCONN;
 
 	if (tunnel->alloc_bandwidth)
 		return tunnel->alloc_bandwidth(tunnel, alloc_up, alloc_down);
@@ -2376,26 +2467,27 @@ int tb_tunnel_consumed_bandwidth(struct tb_tunnel *tunnel, int *consumed_up,
 {
 	int up_bw = 0, down_bw = 0;
 
-	if (!tb_tunnel_is_active(tunnel))
-		goto out;
-
-	if (tunnel->consumed_bandwidth) {
+	/*
+	 * Here we need to distinguish between not active tunnel from
+	 * tunnels that are either fully active or activation started.
+	 * The latter is true for DP tunnels where we must report the
+	 * consumed to be the maximum we gave it until DPRX capabilities
+	 * read is done by the graphics driver.
+	 */
+	if (tb_tunnel_is_activated(tunnel) && tunnel->consumed_bandwidth) {
 		int ret;
 
 		ret = tunnel->consumed_bandwidth(tunnel, &up_bw, &down_bw);
 		if (ret)
 			return ret;
-
-		tb_tunnel_dbg(tunnel, "consumed bandwidth %d/%d Mb/s\n", up_bw,
-			      down_bw);
 	}
 
-out:
 	if (consumed_up)
 		*consumed_up = up_bw;
 	if (consumed_down)
 		*consumed_down = down_bw;
 
+	tb_tunnel_dbg(tunnel, "consumed bandwidth %d/%d Mb/s\n", up_bw, down_bw);
 	return 0;
 }
 
@@ -2411,7 +2503,7 @@ out:
 int tb_tunnel_release_unused_bandwidth(struct tb_tunnel *tunnel)
 {
 	if (!tb_tunnel_is_active(tunnel))
-		return 0;
+		return -ENOTCONN;
 
 	if (tunnel->release_unused_bandwidth) {
 		int ret;
diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h
index 1a27ccd08b86..7f6d3a18a41e 100644
--- a/drivers/thunderbolt/tunnel.h
+++ b/drivers/thunderbolt/tunnel.h
@@ -19,16 +19,33 @@ enum tb_tunnel_type {
 };
 
 /**
+ * enum tb_tunnel_state - State of a tunnel
+ * @TB_TUNNEL_INACTIVE: tb_tunnel_activate() is not called for the tunnel
+ * @TB_TUNNEL_ACTIVATING: tb_tunnel_activate() returned successfully for the tunnel
+ * @TB_TUNNEL_ACTIVE: The tunnel is fully active
+ */
+enum tb_tunnel_state {
+	TB_TUNNEL_INACTIVE,
+	TB_TUNNEL_ACTIVATING,
+	TB_TUNNEL_ACTIVE,
+};
+
+/**
  * struct tb_tunnel - Tunnel between two ports
+ * @kref: Reference count
  * @tb: Pointer to the domain
  * @src_port: Source port of the tunnel
  * @dst_port: Destination port of the tunnel. For discovered incomplete
  *	      tunnels may be %NULL or null adapter port instead.
  * @paths: All paths required by the tunnel
  * @npaths: Number of paths in @paths
- * @init: Optional tunnel specific initialization
- * @deinit: Optional tunnel specific de-initialization
+ * @pre_activate: Optional tunnel specific initialization called before
+ *		  activation. Can touch hardware.
  * @activate: Optional tunnel specific activation/deactivation
+ * @post_deactivate: Optional tunnel specific de-initialization called
+ *		     after deactivation. Can touch hardware.
+ * @destroy: Optional tunnel specific callback called when the tunnel
+ *	     memory is being released. Should not touch hardware.
  * @maximum_bandwidth: Returns maximum possible bandwidth for this tunnel
  * @allocated_bandwidth: Return how much bandwidth is allocated for the tunnel
  * @alloc_bandwidth: Change tunnel bandwidth allocation
@@ -37,6 +54,7 @@ enum tb_tunnel_type {
  * @reclaim_available_bandwidth: Reclaim back available bandwidth
  * @list: Tunnels are linked using this field
  * @type: Type of the tunnel
+ * @state: Current state of the tunnel
  * @max_up: Maximum upstream bandwidth (Mb/s) available for the tunnel.
  *	    Only set if the bandwidth needs to be limited.
  * @max_down: Maximum downstream bandwidth (Mb/s) available for the tunnel.
@@ -45,16 +63,23 @@ enum tb_tunnel_type {
  * @allocated_down: Allocated downstream bandwidth (only for USB3)
  * @bw_mode: DP bandwidth allocation mode registers can be used to
  *	     determine consumed and allocated bandwidth
+ * @dprx_canceled: Was DPRX capabilities read poll canceled
+ * @dprx_timeout: If set DPRX capabilities read poll work will timeout after this passes
+ * @dprx_work: Worker that is scheduled to poll completion of DPRX capabilities read
+ * @callback: Optional callback called when DP tunnel is fully activated
+ * @callback_data: Optional data for @callback
  */
 struct tb_tunnel {
+	struct kref kref;
 	struct tb *tb;
 	struct tb_port *src_port;
 	struct tb_port *dst_port;
 	struct tb_path **paths;
 	size_t npaths;
-	int (*init)(struct tb_tunnel *tunnel);
-	void (*deinit)(struct tb_tunnel *tunnel);
+	int (*pre_activate)(struct tb_tunnel *tunnel);
 	int (*activate)(struct tb_tunnel *tunnel, bool activate);
+	void (*post_deactivate)(struct tb_tunnel *tunnel);
+	void (*destroy)(struct tb_tunnel *tunnel);
 	int (*maximum_bandwidth)(struct tb_tunnel *tunnel, int *max_up,
 				 int *max_down);
 	int (*allocated_bandwidth)(struct tb_tunnel *tunnel, int *allocated_up,
@@ -69,11 +94,17 @@ struct tb_tunnel {
 					    int *available_down);
 	struct list_head list;
 	enum tb_tunnel_type type;
+	enum tb_tunnel_state state;
 	int max_up;
 	int max_down;
 	int allocated_up;
 	int allocated_down;
 	bool bw_mode;
+	bool dprx_canceled;
+	ktime_t dprx_timeout;
+	struct delayed_work dprx_work;
+	void (*callback)(struct tb_tunnel *tunnel, void *data);
+	void *callback_data;
 };
 
 struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down,
@@ -86,7 +117,9 @@ struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in,
 					bool alloc_hopid);
 struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in,
 				     struct tb_port *out, int link_nr,
-				     int max_up, int max_down);
+				     int max_up, int max_down,
+				     void (*callback)(struct tb_tunnel *, void *),
+				     void *callback_data);
 struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi,
 				      struct tb_port *dst, int transmit_path,
 				      int transmit_ring, int receive_path,
@@ -99,10 +132,24 @@ struct tb_tunnel *tb_tunnel_alloc_usb3(struct tb *tb, struct tb_port *up,
 				       struct tb_port *down, int max_up,
 				       int max_down);
 
-void tb_tunnel_free(struct tb_tunnel *tunnel);
+void tb_tunnel_put(struct tb_tunnel *tunnel);
 int tb_tunnel_activate(struct tb_tunnel *tunnel);
-int tb_tunnel_restart(struct tb_tunnel *tunnel);
 void tb_tunnel_deactivate(struct tb_tunnel *tunnel);
+
+/**
+ * tb_tunnel_is_active() - Is tunnel fully activated
+ * @tunnel: Tunnel to check
+ *
+ * Returns %true if @tunnel is fully activated. For other than DP
+ * tunnels this is pretty much once tb_tunnel_activate() returns
+ * successfully. However, for DP tunnels this returns %true only once the
+ * DPRX capabilities read has been issued successfully.
+ */
+static inline bool tb_tunnel_is_active(const struct tb_tunnel *tunnel)
+{
+	return tunnel->state == TB_TUNNEL_ACTIVE;
+}
+
 bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel);
 bool tb_tunnel_port_on_path(const struct tb_tunnel *tunnel,
 			    const struct tb_port *port);
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index 11a50c86a1e4..b0630e6d9472 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -1026,7 +1026,7 @@ static int remove_missing_service(struct device *dev, void *data)
 	return 0;
 }
 
-static int find_service(struct device *dev, void *data)
+static int find_service(struct device *dev, const void *data)
 {
 	const struct tb_property *p = data;
 	struct tb_service *svc;
diff --git a/drivers/tty/mips_ejtag_fdc.c b/drivers/tty/mips_ejtag_fdc.c
index afbf7738c7c4..58b28be63c79 100644
--- a/drivers/tty/mips_ejtag_fdc.c
+++ b/drivers/tty/mips_ejtag_fdc.c
@@ -1154,7 +1154,7 @@ static char kgdbfdc_rbuf[4];
 
 /* write buffer to allow compaction */
 static unsigned int kgdbfdc_wbuflen;
-static char kgdbfdc_wbuf[4];
+static u8 kgdbfdc_wbuf[4];
 
 static void __iomem *kgdbfdc_setup(void)
 {
@@ -1215,7 +1215,7 @@ static int kgdbfdc_read_char(void)
 /* push an FDC word from write buffer to TX FIFO */
 static void kgdbfdc_push_one(void)
 {
-	const char *bufs[1] = { kgdbfdc_wbuf };
+	const u8 *bufs[1] = { kgdbfdc_wbuf };
 	struct fdc_word word;
 	void __iomem *regs;
 	unsigned int i;
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 252849910588..363afe11974f 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2224,7 +2224,7 @@ static int gsm_dlci_negotiate(struct gsm_dlci *dlci)
  *
  *	Some control dlci can stay in ADM mode with other dlci working just
  *	fine. In that case we can just keep the control dlci open after the
- *	DLCI_OPENING retries time out.
+ *	DLCI_OPENING receives DM.
  */
 
 static void gsm_dlci_t1(struct timer_list *t)
@@ -2243,16 +2243,19 @@ static void gsm_dlci_t1(struct timer_list *t)
 		}
 		break;
 	case DLCI_OPENING:
-		if (dlci->retries) {
-			dlci->retries--;
-			gsm_command(dlci->gsm, dlci->addr, SABM|PF);
-			mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100);
-		} else if (!dlci->addr && gsm->control == (DM | PF)) {
+		if (!dlci->addr && gsm->control == (DM | PF)) {
 			if (debug & DBG_ERRORS)
-				pr_info("DLCI %d opening in ADM mode.\n",
-					dlci->addr);
+				pr_info("DLCI 0 opening in ADM mode.\n");
 			dlci->mode = DLCI_MODE_ADM;
 			gsm_dlci_open(dlci);
+		} else if (dlci->retries) {
+			if (!dlci->addr || !gsm->dlci[0] ||
+			    gsm->dlci[0]->state != DLCI_OPENING) {
+				dlci->retries--;
+				gsm_command(dlci->gsm, dlci->addr, SABM|PF);
+			}
+
+			mod_timer(&dlci->t1, jiffies + gsm->t1 * HZ / 100);
 		} else {
 			gsm->open_error++;
 			gsm_dlci_begin_close(dlci); /* prevent half open link */
@@ -2308,7 +2311,9 @@ static void gsm_dlci_begin_open(struct gsm_dlci *dlci)
 		dlci->retries = gsm->n2;
 		if (!need_pn) {
 			dlci->state = DLCI_OPENING;
-			gsm_command(gsm, dlci->addr, SABM|PF);
+			if (!dlci->addr || !gsm->dlci[0] ||
+			    gsm->dlci[0]->state != DLCI_OPENING)
+				gsm_command(gsm, dlci->addr, SABM|PF);
 		} else {
 			/* Configure DLCI before setup */
 			dlci->state = DLCI_CONFIGURE;
@@ -4251,7 +4256,7 @@ static const struct tty_port_operations gsm_port_ops = {
 static int gsmtty_install(struct tty_driver *driver, struct tty_struct *tty)
 {
 	struct gsm_mux *gsm;
-	struct gsm_dlci *dlci;
+	struct gsm_dlci *dlci, *dlci0;
 	unsigned int line = tty->index;
 	unsigned int mux = mux_line_to_num(line);
 	bool alloc = false;
@@ -4274,10 +4279,20 @@ static int gsmtty_install(struct tty_driver *driver, struct tty_struct *tty)
 	perspective as we don't have to worry about this
 	if DLCI0 is lost */
 	mutex_lock(&gsm->mutex);
-	if (gsm->dlci[0] && gsm->dlci[0]->state != DLCI_OPEN) {
+
+	dlci0 = gsm->dlci[0];
+	if (dlci0 && dlci0->state != DLCI_OPEN) {
 		mutex_unlock(&gsm->mutex);
-		return -EL2NSYNC;
+
+		if (dlci0->state == DLCI_OPENING)
+			wait_event(gsm->event, dlci0->state != DLCI_OPENING);
+
+		if (dlci0->state != DLCI_OPEN)
+			return -EL2NSYNC;
+
+		mutex_lock(&gsm->mutex);
 	}
+
 	dlci = gsm->dlci[line];
 	if (dlci == NULL) {
 		alloc = true;
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index df08f13052ff..8bb1a01fef2a 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -798,7 +798,7 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	nonseekable_open(inode, filp);
 
 	/* We refuse fsnotify events on ptmx, since it's a shared resource */
-	filp->f_mode |= FMODE_NONOTIFY;
+	file_set_fsnotify_mode(filp, FMODE_NONOTIFY);
 
 	retval = tty_alloc_file(filp);
 	if (retval)
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index e5310c65cf52..11e05aa014e5 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -231,8 +231,8 @@ void serial8250_rpm_put_tx(struct uart_8250_port *p);
 
 int serial8250_em485_config(struct uart_port *port, struct ktermios *termios,
 			    struct serial_rs485 *rs485);
-void serial8250_em485_start_tx(struct uart_8250_port *p);
-void serial8250_em485_stop_tx(struct uart_8250_port *p);
+void serial8250_em485_start_tx(struct uart_8250_port *p, bool toggle_ier);
+void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier);
 void serial8250_em485_destroy(struct uart_8250_port *p);
 extern struct serial_rs485 serial8250_em485_supported;
 
diff --git a/drivers/tty/serial/8250/8250_bcm2835aux.c b/drivers/tty/serial/8250/8250_bcm2835aux.c
index fdb53b54e99e..0609582a62f7 100644
--- a/drivers/tty/serial/8250/8250_bcm2835aux.c
+++ b/drivers/tty/serial/8250/8250_bcm2835aux.c
@@ -46,7 +46,7 @@ struct bcm2835aux_data {
 	u32 cntl;
 };
 
-static void bcm2835aux_rs485_start_tx(struct uart_8250_port *up)
+static void bcm2835aux_rs485_start_tx(struct uart_8250_port *up, bool toggle_ier)
 {
 	if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX)) {
 		struct bcm2835aux_data *data = dev_get_drvdata(up->port.dev);
@@ -65,7 +65,7 @@ static void bcm2835aux_rs485_start_tx(struct uart_8250_port *up)
 		serial8250_out_MCR(up, UART_MCR_RTS);
 }
 
-static void bcm2835aux_rs485_stop_tx(struct uart_8250_port *up)
+static void bcm2835aux_rs485_stop_tx(struct uart_8250_port *up, bool toggle_ier)
 {
 	if (up->port.rs485.flags & SER_RS485_RTS_AFTER_SEND)
 		serial8250_out_MCR(up, 0);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 68baf75bdadc..6f676bb37ac3 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -675,7 +675,6 @@ static void serial_8250_overrun_backoff_work(struct work_struct *work)
 
 	uart_port_lock_irqsave(port, &flags);
 	up->ier |= UART_IER_RLSI | UART_IER_RDI;
-	up->port.read_status_mask |= UART_LSR_DR;
 	serial_out(up, UART_IER, up->ier);
 	uart_port_unlock_irqrestore(port, flags);
 }
diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index 9eb9aa766811..c2b75e3f106d 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -365,7 +365,7 @@ static void omap8250_restore_regs(struct uart_8250_port *up)
 
 	if (up->port.rs485.flags & SER_RS485_ENABLED &&
 	    up->port.rs485_config == serial8250_em485_config)
-		serial8250_em485_stop_tx(up);
+		serial8250_em485_stop_tx(up, true);
 }
 
 /*
@@ -412,7 +412,13 @@ static void omap_8250_set_termios(struct uart_port *port,
 	 */
 	uart_update_timeout(port, termios->c_cflag, baud);
 
-	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
+	/*
+	 * Specify which conditions may be considered for error
+	 * handling and the ignoring of characters. The actual
+	 * ignoring of characters only occurs if the bit is set
+	 * in @ignore_status_mask as well.
+	 */
+	up->port.read_status_mask = UART_LSR_OE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
 	if (termios->c_iflag & (IGNBRK | PARMRK))
@@ -838,7 +844,6 @@ static void omap_8250_unthrottle(struct uart_port *port)
 	if (up->dma)
 		up->dma->rx_dma(up);
 	up->ier |= UART_IER_RLSI | UART_IER_RDI;
-	port->read_status_mask |= UART_LSR_DR;
 	serial_out(up, UART_IER, up->ier);
 	uart_port_unlock_irqrestore(port, flags);
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 3c3f7c926afb..df4d0d832e54 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -64,23 +64,17 @@
 #define PCIE_DEVICE_ID_NEO_2_OX_IBM	0x00F6
 #define PCI_DEVICE_ID_PLX_CRONYX_OMEGA	0xc001
 #define PCI_DEVICE_ID_INTEL_PATSBURG_KT 0x1d3d
-#define PCI_VENDOR_ID_WCH		0x4348
-#define PCI_DEVICE_ID_WCH_CH352_2S	0x3253
-#define PCI_DEVICE_ID_WCH_CH353_4S	0x3453
-#define PCI_DEVICE_ID_WCH_CH353_2S1PF	0x5046
-#define PCI_DEVICE_ID_WCH_CH353_1S1P	0x5053
-#define PCI_DEVICE_ID_WCH_CH353_2S1P	0x7053
-#define PCI_DEVICE_ID_WCH_CH355_4S	0x7173
+
+#define PCI_DEVICE_ID_WCHCN_CH352_2S	0x3253
+#define PCI_DEVICE_ID_WCHCN_CH355_4S	0x7173
+
 #define PCI_VENDOR_ID_AGESTAR		0x5372
 #define PCI_DEVICE_ID_AGESTAR_9375	0x6872
 #define PCI_DEVICE_ID_BROADCOM_TRUMANAGE 0x160a
 #define PCI_DEVICE_ID_AMCC_ADDIDATA_APCI7800 0x818e
 
-#define PCIE_VENDOR_ID_WCH		0x1c00
-#define PCIE_DEVICE_ID_WCH_CH382_2S1P	0x3250
-#define PCIE_DEVICE_ID_WCH_CH384_4S	0x3470
-#define PCIE_DEVICE_ID_WCH_CH384_8S	0x3853
-#define PCIE_DEVICE_ID_WCH_CH382_2S	0x3253
+#define PCI_DEVICE_ID_WCHIC_CH384_4S	0x3470
+#define PCI_DEVICE_ID_WCHIC_CH384_8S	0x3853
 
 #define PCI_DEVICE_ID_MOXA_CP102E	0x1024
 #define PCI_DEVICE_ID_MOXA_CP102EL	0x1025
@@ -2817,80 +2811,80 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 	},
 	/* WCH CH353 1S1P card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_1S1P,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_1S1P,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH353 2S1P card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_2S1P,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_2S1P,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH353 4S card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_4S,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_4S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH353 2S1PF card (16550 clone) */
 	{
-		.vendor         = PCI_VENDOR_ID_WCH,
-		.device         = PCI_DEVICE_ID_WCH_CH353_2S1PF,
+		.vendor         = PCI_VENDOR_ID_WCHCN,
+		.device         = PCI_DEVICE_ID_WCHCN_CH353_2S1PF,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch353_setup,
 	},
 	/* WCH CH352 2S card (16550 clone) */
 	{
-		.vendor		= PCI_VENDOR_ID_WCH,
-		.device		= PCI_DEVICE_ID_WCH_CH352_2S,
+		.vendor		= PCI_VENDOR_ID_WCHCN,
+		.device		= PCI_DEVICE_ID_WCHCN_CH352_2S,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch353_setup,
 	},
 	/* WCH CH355 4S card (16550 clone) */
 	{
-		.vendor		= PCI_VENDOR_ID_WCH,
-		.device		= PCI_DEVICE_ID_WCH_CH355_4S,
+		.vendor		= PCI_VENDOR_ID_WCHCN,
+		.device		= PCI_DEVICE_ID_WCHCN_CH355_4S,
 		.subvendor	= PCI_ANY_ID,
 		.subdevice	= PCI_ANY_ID,
 		.setup		= pci_wch_ch355_setup,
 	},
 	/* WCH CH382 2S card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH382_2S,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH382_2S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch38x_setup,
 	},
 	/* WCH CH382 2S1P card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH382_2S1P,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH382_2S1P,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch38x_setup,
 	},
 	/* WCH CH384 4S card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH384_4S,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH384_4S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.setup          = pci_wch_ch38x_setup,
 	},
 	/* WCH CH384 8S card (16850 clone) */
 	{
-		.vendor         = PCIE_VENDOR_ID_WCH,
-		.device         = PCIE_DEVICE_ID_WCH_CH384_8S,
+		.vendor         = PCI_VENDOR_ID_WCHIC,
+		.device         = PCI_DEVICE_ID_WCHIC_CH384_8S,
 		.subvendor      = PCI_ANY_ID,
 		.subdevice      = PCI_ANY_ID,
 		.init           = pci_wch_ch38x_init,
@@ -3967,11 +3961,11 @@ static const struct pci_device_id blacklist[] = {
 
 	/* multi-io cards handled by parport_serial */
 	/* WCH CH353 2S1P */
-	{ PCI_DEVICE(0x4348, 0x7053), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), },
+	{ PCI_VDEVICE(WCHCN, 0x7053), REPORT_CONFIG(PARPORT_SERIAL), },
 	/* WCH CH353 1S1P */
-	{ PCI_DEVICE(0x4348, 0x5053), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), },
+	{ PCI_VDEVICE(WCHCN, 0x5053), REPORT_CONFIG(PARPORT_SERIAL), },
 	/* WCH CH382 2S1P */
-	{ PCI_DEVICE(0x1c00, 0x3250), 0, 0, REPORT_CONFIG(PARPORT_SERIAL), },
+	{ PCI_VDEVICE(WCHIC, 0x3250), REPORT_CONFIG(PARPORT_SERIAL), },
 
 	/* Intel platforms with MID UART */
 	{ PCI_VDEVICE(INTEL, 0x081b), REPORT_8250_CONFIG(MID), },
@@ -6044,27 +6038,27 @@ static const struct pci_device_id serial_pci_tbl[] = {
 	 * WCH CH353 series devices: The 2S1P is handled by parport_serial
 	 * so not listed here.
 	 */
-	{	PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH353_4S,
+	{	PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_4_115200 },
 
-	{	PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH353_2S1PF,
+	{	PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH353_2S1PF,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_2_115200 },
 
-	{	PCI_VENDOR_ID_WCH, PCI_DEVICE_ID_WCH_CH355_4S,
+	{	PCI_VENDOR_ID_WCHCN, PCI_DEVICE_ID_WCHCN_CH355_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_b0_bt_4_115200 },
 
-	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S,
+	{	PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH382_2S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch382_2 },
 
-	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S,
+	{	PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH384_4S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_4 },
 
-	{	PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_8S,
+	{	PCI_VENDOR_ID_WCHIC, PCI_DEVICE_ID_WCHIC_CH384_8S,
 		PCI_ANY_ID, PCI_ANY_ID,
 		0, 0, pbn_wch384_8 },
 	/*
diff --git a/drivers/tty/serial/8250/8250_pci1xxxx.c b/drivers/tty/serial/8250/8250_pci1xxxx.c
index 838f181f929b..e9c51d4e447d 100644
--- a/drivers/tty/serial/8250/8250_pci1xxxx.c
+++ b/drivers/tty/serial/8250/8250_pci1xxxx.c
@@ -78,6 +78,12 @@
 #define UART_TX_BYTE_FIFO			0x00
 #define UART_FIFO_CTL				0x02
 
+#define UART_MODEM_CTL_REG			0x04
+#define UART_MODEM_CTL_RTS_SET			BIT(1)
+
+#define UART_LINE_STAT_REG			0x05
+#define UART_LINE_XMIT_CHECK_MASK		GENMASK(6, 5)
+
 #define UART_ACTV_REG				0x11
 #define UART_BLOCK_SET_ACTIVE			BIT(0)
 
@@ -94,6 +100,7 @@
 #define UART_BIT_SAMPLE_CNT_16			16
 #define BAUD_CLOCK_DIV_INT_MSK			GENMASK(31, 8)
 #define ADCL_CFG_RTS_DELAY_MASK			GENMASK(11, 8)
+#define FRAC_DIV_TX_END_POINT_MASK		GENMASK(23, 20)
 
 #define UART_WAKE_REG				0x8C
 #define UART_WAKE_MASK_REG			0x90
@@ -134,6 +141,11 @@
 #define UART_BST_STAT_LSR_FRAME_ERR		0x8000000
 #define UART_BST_STAT_LSR_THRE			0x20000000
 
+#define GET_MODEM_CTL_RTS_STATUS(reg)		((reg) & UART_MODEM_CTL_RTS_SET)
+#define GET_RTS_PIN_STATUS(val)			(((val) & TIOCM_RTS) >> 1)
+#define RTS_TOGGLE_STATUS_MASK(val, reg)	(GET_MODEM_CTL_RTS_STATUS(reg) \
+						 != GET_RTS_PIN_STATUS(val))
+
 struct pci1xxxx_8250 {
 	unsigned int nr;
 	u8 dev_rev;
@@ -254,6 +266,47 @@ static void pci1xxxx_set_divisor(struct uart_port *port, unsigned int baud,
 	       port->membase + UART_BAUD_CLK_DIVISOR_REG);
 }
 
+static void pci1xxxx_set_mctrl(struct uart_port *port, unsigned int mctrl)
+{
+	u32 fract_div_cfg_reg;
+	u32 line_stat_reg;
+	u32 modem_ctl_reg;
+	u32 adcl_cfg_reg;
+
+	adcl_cfg_reg = readl(port->membase + ADCL_CFG_REG);
+
+	/* HW is responsible in ADCL_EN case */
+	if ((adcl_cfg_reg & (ADCL_CFG_EN | ADCL_CFG_PIN_SEL)))
+		return;
+
+	modem_ctl_reg = readl(port->membase + UART_MODEM_CTL_REG);
+
+	serial8250_do_set_mctrl(port, mctrl);
+
+	if (RTS_TOGGLE_STATUS_MASK(mctrl, modem_ctl_reg)) {
+		line_stat_reg = readl(port->membase + UART_LINE_STAT_REG);
+		if (line_stat_reg & UART_LINE_XMIT_CHECK_MASK) {
+			fract_div_cfg_reg = readl(port->membase +
+						  FRAC_DIV_CFG_REG);
+
+			writel((fract_div_cfg_reg &
+			       ~(FRAC_DIV_TX_END_POINT_MASK)),
+			       port->membase + FRAC_DIV_CFG_REG);
+
+			/* Enable ADC and set the nRTS pin */
+			writel((adcl_cfg_reg | (ADCL_CFG_EN |
+			       ADCL_CFG_PIN_SEL)),
+			       port->membase + ADCL_CFG_REG);
+
+			/* Revert to the original settings */
+			writel(adcl_cfg_reg, port->membase + ADCL_CFG_REG);
+
+			writel(fract_div_cfg_reg, port->membase +
+			       FRAC_DIV_CFG_REG);
+		}
+	}
+}
+
 static int pci1xxxx_rs485_config(struct uart_port *port,
 				 struct ktermios *termios,
 				 struct serial_rs485 *rs485)
@@ -631,9 +684,14 @@ static int pci1xxxx_setup(struct pci_dev *pdev,
 	port->port.rs485_config = pci1xxxx_rs485_config;
 	port->port.rs485_supported = pci1xxxx_rs485_supported;
 
-	/* From C0 rev Burst operation is supported */
+	/*
+	 * C0 and later revisions support Burst operation.
+	 * RTS workaround in mctrl is applicable only to B0.
+	 */
 	if (rev >= 0xC0)
 		port->port.handle_irq = pci1xxxx_handle_irq;
+	else if (rev == 0xB0)
+		port->port.set_mctrl = pci1xxxx_set_mctrl;
 
 	ret = serial8250_pci_setup_port(pdev, port, 0, PORT_OFFSET * port_idx, 0);
 	if (ret < 0)
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 649e74e9b52f..d7976a21cca9 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -578,7 +578,7 @@ static int serial8250_em485_init(struct uart_8250_port *p)
 
 deassert_rts:
 	if (p->em485->tx_stopped)
-		p->rs485_stop_tx(p);
+		p->rs485_stop_tx(p, true);
 
 	return 0;
 }
@@ -1390,7 +1390,6 @@ static void serial8250_stop_rx(struct uart_port *port)
 	serial8250_rpm_get(up);
 
 	up->ier &= ~(UART_IER_RLSI | UART_IER_RDI);
-	up->port.read_status_mask &= ~UART_LSR_DR;
 	serial_port_out(port, UART_IER, up->ier);
 
 	serial8250_rpm_put(up);
@@ -1399,10 +1398,11 @@ static void serial8250_stop_rx(struct uart_port *port)
 /**
  * serial8250_em485_stop_tx() - generic ->rs485_stop_tx() callback
  * @p: uart 8250 port
+ * @toggle_ier: true to allow enabling receive interrupts
  *
  * Generic callback usable by 8250 uart drivers to stop rs485 transmission.
  */
-void serial8250_em485_stop_tx(struct uart_8250_port *p)
+void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier)
 {
 	unsigned char mcr = serial8250_in_MCR(p);
 
@@ -1423,8 +1423,10 @@ void serial8250_em485_stop_tx(struct uart_8250_port *p)
 	if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) {
 		serial8250_clear_and_reinit_fifos(p);
 
-		p->ier |= UART_IER_RLSI | UART_IER_RDI;
-		serial_port_out(&p->port, UART_IER, p->ier);
+		if (toggle_ier) {
+			p->ier |= UART_IER_RLSI | UART_IER_RDI;
+			serial_port_out(&p->port, UART_IER, p->ier);
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(serial8250_em485_stop_tx);
@@ -1439,7 +1441,7 @@ static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t)
 	serial8250_rpm_get(p);
 	uart_port_lock_irqsave(&p->port, &flags);
 	if (em485->active_timer == &em485->stop_tx_timer) {
-		p->rs485_stop_tx(p);
+		p->rs485_stop_tx(p, true);
 		em485->active_timer = NULL;
 		em485->tx_stopped = true;
 	}
@@ -1471,7 +1473,7 @@ static void __stop_tx_rs485(struct uart_8250_port *p, u64 stop_delay)
 		em485->active_timer = &em485->stop_tx_timer;
 		hrtimer_start(&em485->stop_tx_timer, ns_to_ktime(stop_delay), HRTIMER_MODE_REL);
 	} else {
-		p->rs485_stop_tx(p);
+		p->rs485_stop_tx(p, true);
 		em485->active_timer = NULL;
 		em485->tx_stopped = true;
 	}
@@ -1560,6 +1562,7 @@ static inline void __start_tx(struct uart_port *port)
 /**
  * serial8250_em485_start_tx() - generic ->rs485_start_tx() callback
  * @up: uart 8250 port
+ * @toggle_ier: true to allow disabling receive interrupts
  *
  * Generic callback usable by 8250 uart drivers to start rs485 transmission.
  * Assumes that setting the RTS bit in the MCR register means RTS is high.
@@ -1567,11 +1570,11 @@ static inline void __start_tx(struct uart_port *port)
  * stoppable by disabling the UART_IER_RDI interrupt.  (Some chips set the
  * UART_LSR_DR bit even when UART_IER_RDI is disabled, foiling this approach.)
  */
-void serial8250_em485_start_tx(struct uart_8250_port *up)
+void serial8250_em485_start_tx(struct uart_8250_port *up, bool toggle_ier)
 {
 	unsigned char mcr = serial8250_in_MCR(up);
 
-	if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX))
+	if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX) && toggle_ier)
 		serial8250_stop_rx(&up->port);
 
 	if (up->port.rs485.flags & SER_RS485_RTS_ON_SEND)
@@ -1605,7 +1608,7 @@ static bool start_tx_rs485(struct uart_port *port)
 	if (em485->tx_stopped) {
 		em485->tx_stopped = false;
 
-		up->rs485_start_tx(up);
+		up->rs485_start_tx(up, true);
 
 		if (up->port.rs485.delay_rts_before_send > 0) {
 			em485->active_timer = &em485->start_tx_timer;
@@ -1931,7 +1934,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)
 	 */
 	if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) &&
 	    (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) &&
-	    !(port->read_status_mask & UART_LSR_DR))
+	    !(up->ier & (UART_IER_RLSI | UART_IER_RDI)))
 		skip_rx = true;
 
 	if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) {
@@ -2079,11 +2082,20 @@ static void serial8250_break_ctl(struct uart_port *port, int break_state)
 	serial8250_rpm_put(up);
 }
 
-static void wait_for_lsr(struct uart_8250_port *up, int bits)
+/* Returns true if @bits were set, false on timeout */
+static bool wait_for_lsr(struct uart_8250_port *up, int bits)
 {
-	unsigned int status, tmout = 10000;
+	unsigned int status, tmout;
+
+	/*
+	 * Wait for a character to be sent. Fallback to a safe default
+	 * timeout value if @frame_time is not available.
+	 */
+	if (up->port.frame_time)
+		tmout = up->port.frame_time * 2 / NSEC_PER_USEC;
+	else
+		tmout = 10000;
 
-	/* Wait up to 10ms for the character(s) to be sent. */
 	for (;;) {
 		status = serial_lsr_in(up);
 
@@ -2094,11 +2106,11 @@ static void wait_for_lsr(struct uart_8250_port *up, int bits)
 		udelay(1);
 		touch_nmi_watchdog();
 	}
+
+	return (tmout != 0);
 }
 
-/*
- *	Wait for transmitter & holding register to empty
- */
+/* Wait for transmitter and holding register to empty with timeout */
 static void wait_for_xmitr(struct uart_8250_port *up, int bits)
 {
 	unsigned int tmout;
@@ -2786,7 +2798,13 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 	 */
 	uart_update_timeout(port, termios->c_cflag, baud);
 
-	port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
+	/*
+	 * Specify which conditions may be considered for error
+	 * handling and the ignoring of characters. The actual
+	 * ignoring of characters only occurs if the bit is set
+	 * in @ignore_status_mask as well.
+	 */
+	port->read_status_mask = UART_LSR_OE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
 	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
@@ -3250,7 +3268,7 @@ void serial8250_init_port(struct uart_8250_port *up)
 	port->ops = &serial8250_pops;
 	port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE);
 
-	up->cur_iotype = 0xFF;
+	up->cur_iotype = UPIO_UNKNOWN;
 }
 EXPORT_SYMBOL_GPL(serial8250_init_port);
 
@@ -3285,10 +3303,15 @@ EXPORT_SYMBOL_GPL(serial8250_set_defaults);
 
 static void serial8250_console_putchar(struct uart_port *port, unsigned char ch)
 {
+	serial_port_out(port, UART_TX, ch);
+}
+
+static void serial8250_console_wait_putchar(struct uart_port *port, unsigned char ch)
+{
 	struct uart_8250_port *up = up_to_u8250p(port);
 
 	wait_for_xmitr(up, UART_LSR_THRE);
-	serial_port_out(port, UART_TX, ch);
+	serial8250_console_putchar(port, ch);
 }
 
 /*
@@ -3317,6 +3340,16 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 	serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS);
 }
 
+static void fifo_wait_for_lsr(struct uart_8250_port *up, unsigned int count)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		if (wait_for_lsr(up, UART_LSR_THRE))
+			return;
+	}
+}
+
 /*
  * Print a string to the serial port using the device FIFO
  *
@@ -3326,24 +3359,34 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 static void serial8250_console_fifo_write(struct uart_8250_port *up,
 					  const char *s, unsigned int count)
 {
-	int i;
 	const char *end = s + count;
 	unsigned int fifosize = up->tx_loadsz;
+	struct uart_port *port = &up->port;
+	unsigned int tx_count = 0;
 	bool cr_sent = false;
+	unsigned int i;
 
 	while (s != end) {
-		wait_for_lsr(up, UART_LSR_THRE);
+		/* Allow timeout for each byte of a possibly full FIFO */
+		fifo_wait_for_lsr(up, fifosize);
 
 		for (i = 0; i < fifosize && s != end; ++i) {
 			if (*s == '\n' && !cr_sent) {
-				serial_out(up, UART_TX, '\r');
+				serial8250_console_putchar(port, '\r');
 				cr_sent = true;
 			} else {
-				serial_out(up, UART_TX, *s++);
+				serial8250_console_putchar(port, *s++);
 				cr_sent = false;
 			}
 		}
+		tx_count = i;
 	}
+
+	/*
+	 * Allow timeout for each byte written since the caller will only wait
+	 * for UART_LSR_BOTH_EMPTY using the timeout of a single character
+	 */
+	fifo_wait_for_lsr(up, tx_count);
 }
 
 /*
@@ -3385,7 +3428,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 
 	if (em485) {
 		if (em485->tx_stopped)
-			up->rs485_start_tx(up);
+			up->rs485_start_tx(up, false);
 		mdelay(port->rs485.delay_rts_before_send);
 	}
 
@@ -3412,7 +3455,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 	if (likely(use_fifo))
 		serial8250_console_fifo_write(up, s, count);
 	else
-		uart_console_write(port, s, count, serial8250_console_putchar);
+		uart_console_write(port, s, count, serial8250_console_wait_putchar);
 
 	/*
 	 *	Finally, wait for transmitter to become empty
@@ -3423,7 +3466,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 	if (em485) {
 		mdelay(port->rs485.delay_rts_after_send);
 		if (em485->tx_stopped)
-			up->rs485_stop_tx(up);
+			up->rs485_stop_tx(up, false);
 	}
 
 	serial_port_out(port, UART_IER, ier);
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 45f0f779fbf9..976dae3bb1bb 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -128,7 +128,7 @@ config SERIAL_SB1250_DUART_CONSOLE
 config SERIAL_ATMEL
 	bool "AT91 on-chip serial port support"
 	depends on COMMON_CLK
-	depends on ARCH_AT91 || COMPILE_TEST
+	depends on ARCH_AT91 || ARCH_LAN969X || COMPILE_TEST
 	select SERIAL_CORE
 	select SERIAL_MCTRL_GPIO if GPIOLIB
 	select MFD_AT91_USART
diff --git a/drivers/tty/serial/altera_jtaguart.c b/drivers/tty/serial/altera_jtaguart.c
index b9c3c3bed0c1..d47a62d1c9f7 100644
--- a/drivers/tty/serial/altera_jtaguart.c
+++ b/drivers/tty/serial/altera_jtaguart.c
@@ -24,8 +24,6 @@
 #include <linux/io.h>
 #include <linux/altera_jtaguart.h>
 
-#define DRV_NAME "altera_jtaguart"
-
 /*
  * Altera JTAG UART register definitions according to the Altera JTAG UART
  * datasheet: https://www.altera.com/literature/hb/nios2/n2cpu_nii51009.pdf
@@ -173,7 +171,7 @@ static int altera_jtaguart_startup(struct uart_port *port)
 	int ret;
 
 	ret = request_irq(port->irq, altera_jtaguart_interrupt, 0,
-			DRV_NAME, port);
+			dev_name(port->dev), port);
 	if (ret) {
 		dev_err(port->dev, "unable to attach Altera JTAG UART %d interrupt vector=%d\n",
 			port->line, port->irq);
@@ -365,7 +363,7 @@ OF_EARLYCON_DECLARE(juart, "altr,juart-1.0", altera_jtaguart_earlycon_setup);
 
 static struct uart_driver altera_jtaguart_driver = {
 	.owner		= THIS_MODULE,
-	.driver_name	= "altera_jtaguart",
+	.driver_name	= KBUILD_MODNAME,
 	.dev_name	= "ttyJ",
 	.major		= ALTERA_JTAGUART_MAJOR,
 	.minor		= ALTERA_JTAGUART_MINOR,
@@ -451,7 +449,7 @@ static struct platform_driver altera_jtaguart_platform_driver = {
 	.probe	= altera_jtaguart_probe,
 	.remove = altera_jtaguart_remove,
 	.driver	= {
-		.name		= DRV_NAME,
+		.name		= KBUILD_MODNAME,
 		.of_match_table	= of_match_ptr(altera_jtaguart_match),
 	},
 };
@@ -481,4 +479,4 @@ module_exit(altera_jtaguart_exit);
 MODULE_DESCRIPTION("Altera JTAG UART driver");
 MODULE_AUTHOR("Thomas Chou <thomas@wytron.com.tw>");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_ALIAS("platform:" KBUILD_MODNAME);
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index c94655453c33..1759137121cc 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -24,7 +24,6 @@
 #include <linux/io.h>
 #include <linux/altera_uart.h>
 
-#define DRV_NAME "altera_uart"
 #define SERIAL_ALTERA_MAJOR 204
 #define SERIAL_ALTERA_MINOR 213
 
@@ -518,7 +517,7 @@ OF_EARLYCON_DECLARE(uart, "altr,uart-1.0", altera_uart_earlycon_setup);
  */
 static struct uart_driver altera_uart_driver = {
 	.owner		= THIS_MODULE,
-	.driver_name	= DRV_NAME,
+	.driver_name	= KBUILD_MODNAME,
 	.dev_name	= "ttyAL",
 	.major		= SERIAL_ALTERA_MAJOR,
 	.minor		= SERIAL_ALTERA_MINOR,
@@ -619,7 +618,7 @@ static struct platform_driver altera_uart_platform_driver = {
 	.probe	= altera_uart_probe,
 	.remove = altera_uart_remove,
 	.driver	= {
-		.name		= DRV_NAME,
+		.name		= KBUILD_MODNAME,
 		.of_match_table	= of_match_ptr(altera_uart_match),
 	},
 };
@@ -649,5 +648,5 @@ module_exit(altera_uart_exit);
 MODULE_DESCRIPTION("Altera UART driver");
 MODULE_AUTHOR("Thomas Chou <thomas@wytron.com.tw>");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_ALIAS("platform:" KBUILD_MODNAME);
 MODULE_ALIAS_CHARDEV_MAJOR(SERIAL_ALTERA_MAJOR);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 69b7a3e1e418..04212c823a91 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -248,6 +248,13 @@ struct pl011_dmatx_data {
 	bool			queued;
 };
 
+enum pl011_rs485_tx_state {
+	OFF,
+	WAIT_AFTER_RTS,
+	SEND,
+	WAIT_AFTER_SEND,
+};
+
 /*
  * We wrap our port structure around the generic uart_port.
  */
@@ -261,8 +268,10 @@ struct uart_amba_port {
 	unsigned int		fifosize;	/* vendor-specific */
 	unsigned int		fixed_baud;	/* vendor-set fixed baud rate */
 	char			type[12];
-	bool			rs485_tx_started;
-	unsigned int		rs485_tx_drain_interval; /* usecs */
+	ktime_t			rs485_tx_drain_interval; /* nano */
+	enum pl011_rs485_tx_state	rs485_tx_state;
+	struct hrtimer		trigger_start_tx;
+	struct hrtimer		trigger_stop_tx;
 #ifdef CONFIG_DMA_ENGINE
 	/* DMA stuff */
 	unsigned int		dmacr;		/* dma control reg */
@@ -1260,30 +1269,31 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap)
 
 static void pl011_rs485_tx_stop(struct uart_amba_port *uap)
 {
-	/*
-	 * To be on the safe side only time out after twice as many iterations
-	 * as fifo size.
-	 */
-	const int MAX_TX_DRAIN_ITERS = uap->port.fifosize * 2;
 	struct uart_port *port = &uap->port;
-	int i = 0;
 	u32 cr;
 
-	/* Wait until hardware tx queue is empty */
-	while (!pl011_tx_empty(port)) {
-		if (i > MAX_TX_DRAIN_ITERS) {
-			dev_warn(port->dev,
-				 "timeout while draining hardware tx queue\n");
-			break;
-		}
+	if (uap->rs485_tx_state == SEND)
+		uap->rs485_tx_state = WAIT_AFTER_SEND;
 
-		udelay(uap->rs485_tx_drain_interval);
-		i++;
+	if (uap->rs485_tx_state == WAIT_AFTER_SEND) {
+		/* Schedule hrtimer if tx queue not empty */
+		if (!pl011_tx_empty(port)) {
+			hrtimer_start(&uap->trigger_stop_tx,
+				      uap->rs485_tx_drain_interval,
+				      HRTIMER_MODE_REL);
+			return;
+		}
+		if (port->rs485.delay_rts_after_send > 0) {
+			hrtimer_start(&uap->trigger_stop_tx,
+				      ms_to_ktime(port->rs485.delay_rts_after_send),
+				      HRTIMER_MODE_REL);
+			return;
+		}
+		/* Continue without any delay */
+	} else if (uap->rs485_tx_state == WAIT_AFTER_RTS) {
+		hrtimer_try_to_cancel(&uap->trigger_start_tx);
 	}
 
-	if (port->rs485.delay_rts_after_send)
-		mdelay(port->rs485.delay_rts_after_send);
-
 	cr = pl011_read(uap, REG_CR);
 
 	if (port->rs485.flags & SER_RS485_RTS_AFTER_SEND)
@@ -1296,7 +1306,7 @@ static void pl011_rs485_tx_stop(struct uart_amba_port *uap)
 	cr |= UART011_CR_RXE;
 	pl011_write(cr, uap, REG_CR);
 
-	uap->rs485_tx_started = false;
+	uap->rs485_tx_state = OFF;
 }
 
 static void pl011_stop_tx(struct uart_port *port)
@@ -1304,11 +1314,18 @@ static void pl011_stop_tx(struct uart_port *port)
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
+	if (port->rs485.flags & SER_RS485_ENABLED &&
+	    uap->rs485_tx_state == WAIT_AFTER_RTS) {
+		pl011_rs485_tx_stop(uap);
+		return;
+	}
+
 	uap->im &= ~UART011_TXIM;
 	pl011_write(uap->im, uap, REG_IMSC);
 	pl011_dma_tx_stop(uap);
 
-	if ((port->rs485.flags & SER_RS485_ENABLED) && uap->rs485_tx_started)
+	if (port->rs485.flags & SER_RS485_ENABLED &&
+	    uap->rs485_tx_state != OFF)
 		pl011_rs485_tx_stop(uap);
 }
 
@@ -1328,10 +1345,19 @@ static void pl011_rs485_tx_start(struct uart_amba_port *uap)
 	struct uart_port *port = &uap->port;
 	u32 cr;
 
+	if (uap->rs485_tx_state == WAIT_AFTER_RTS) {
+		uap->rs485_tx_state = SEND;
+		return;
+	}
+	if (uap->rs485_tx_state == WAIT_AFTER_SEND) {
+		hrtimer_try_to_cancel(&uap->trigger_stop_tx);
+		uap->rs485_tx_state = SEND;
+		return;
+	}
+	/* uap->rs485_tx_state == OFF */
 	/* Enable transmitter */
 	cr = pl011_read(uap, REG_CR);
 	cr |= UART011_CR_TXE;
-
 	/* Disable receiver if half-duplex */
 	if (!(port->rs485.flags & SER_RS485_RX_DURING_TX))
 		cr &= ~UART011_CR_RXE;
@@ -1343,10 +1369,14 @@ static void pl011_rs485_tx_start(struct uart_amba_port *uap)
 
 	pl011_write(cr, uap, REG_CR);
 
-	if (port->rs485.delay_rts_before_send)
-		mdelay(port->rs485.delay_rts_before_send);
-
-	uap->rs485_tx_started = true;
+	if (port->rs485.delay_rts_before_send > 0) {
+		uap->rs485_tx_state = WAIT_AFTER_RTS;
+		hrtimer_start(&uap->trigger_start_tx,
+			      ms_to_ktime(port->rs485.delay_rts_before_send),
+			      HRTIMER_MODE_REL);
+	} else {
+		uap->rs485_tx_state = SEND;
+	}
 }
 
 static void pl011_start_tx(struct uart_port *port)
@@ -1355,13 +1385,44 @@ static void pl011_start_tx(struct uart_port *port)
 	    container_of(port, struct uart_amba_port, port);
 
 	if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
-	    !uap->rs485_tx_started)
+	    uap->rs485_tx_state != SEND) {
 		pl011_rs485_tx_start(uap);
+		if (uap->rs485_tx_state == WAIT_AFTER_RTS)
+			return;
+	}
 
 	if (!pl011_dma_tx_start(uap))
 		pl011_start_tx_pio(uap);
 }
 
+static enum hrtimer_restart pl011_trigger_start_tx(struct hrtimer *t)
+{
+	struct uart_amba_port *uap =
+	    container_of(t, struct uart_amba_port, trigger_start_tx);
+	unsigned long flags;
+
+	uart_port_lock_irqsave(&uap->port, &flags);
+	if (uap->rs485_tx_state == WAIT_AFTER_RTS)
+		pl011_start_tx(&uap->port);
+	uart_port_unlock_irqrestore(&uap->port, flags);
+
+	return HRTIMER_NORESTART;
+}
+
+static enum hrtimer_restart pl011_trigger_stop_tx(struct hrtimer *t)
+{
+	struct uart_amba_port *uap =
+	    container_of(t, struct uart_amba_port, trigger_stop_tx);
+	unsigned long flags;
+
+	uart_port_lock_irqsave(&uap->port, &flags);
+	if (uap->rs485_tx_state == WAIT_AFTER_SEND)
+		pl011_rs485_tx_stop(uap);
+	uart_port_unlock_irqrestore(&uap->port, flags);
+
+	return HRTIMER_NORESTART;
+}
+
 static void pl011_stop_rx(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
@@ -1953,7 +2014,7 @@ static void pl011_shutdown(struct uart_port *port)
 
 	pl011_dma_shutdown(uap);
 
-	if ((port->rs485.flags & SER_RS485_ENABLED) && uap->rs485_tx_started)
+	if ((port->rs485.flags & SER_RS485_ENABLED && uap->rs485_tx_state != OFF))
 		pl011_rs485_tx_stop(uap);
 
 	free_irq(uap->port.irq, uap);
@@ -2098,7 +2159,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 	 * with the given baud rate. We use this as the poll interval when we
 	 * wait for the tx queue to empty.
 	 */
-	uap->rs485_tx_drain_interval = DIV_ROUND_UP(bits * 1000 * 1000, baud);
+	uap->rs485_tx_drain_interval = ns_to_ktime(DIV_ROUND_UP(bits * NSEC_PER_SEC, baud));
 
 	pl011_setup_status_masks(port, termios);
 
@@ -2807,6 +2868,11 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id)
 		}
 	}
 
+	hrtimer_init(&uap->trigger_start_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&uap->trigger_stop_tx, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	uap->trigger_start_tx.function = pl011_trigger_start_tx;
+	uap->trigger_stop_tx.function = pl011_trigger_stop_tx;
+
 	ret = pl011_setup_port(&dev->dev, uap, &dev->res, portnr);
 	if (ret)
 		return ret;
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 0cf05ac18993..f44f9d20a974 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1727,26 +1727,16 @@ static void atmel_init_property(struct atmel_uart_port *atmel_port,
 
 	/* DMA/PDC usage specification */
 	if (of_property_read_bool(np, "atmel,use-dma-rx")) {
-		if (of_property_read_bool(np, "dmas")) {
-			atmel_port->use_dma_rx  = true;
-			atmel_port->use_pdc_rx  = false;
-		} else {
-			atmel_port->use_dma_rx  = false;
-			atmel_port->use_pdc_rx  = true;
-		}
+		atmel_port->use_dma_rx = of_property_present(np, "dmas");
+		atmel_port->use_pdc_rx = !atmel_port->use_dma_rx;
 	} else {
 		atmel_port->use_dma_rx  = false;
 		atmel_port->use_pdc_rx  = false;
 	}
 
 	if (of_property_read_bool(np, "atmel,use-dma-tx")) {
-		if (of_property_read_bool(np, "dmas")) {
-			atmel_port->use_dma_tx  = true;
-			atmel_port->use_pdc_tx  = false;
-		} else {
-			atmel_port->use_dma_tx  = false;
-			atmel_port->use_pdc_tx  = true;
-		}
+		atmel_port->use_dma_tx = of_property_present(np, "dmas");
+		atmel_port->use_pdc_tx = !atmel_port->use_dma_tx;
 	} else {
 		atmel_port->use_dma_tx  = false;
 		atmel_port->use_pdc_tx  = false;
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 57b0632a3db6..c91b9d9818cd 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -245,7 +245,7 @@
 
 #define DRIVER_NAME	"fsl-lpuart"
 #define DEV_NAME	"ttyLP"
-#define UART_NR		8
+#define UART_NR		12
 
 /* IMX lpuart has four extra unused regs located at the beginning */
 #define IMX_REG_OFF	0x10
@@ -1965,6 +1965,11 @@ static void lpuart32_shutdown(struct uart_port *port)
 			UARTCTRL_TIE | UARTCTRL_TCIE | UARTCTRL_RIE | UARTCTRL_SBK);
 	lpuart32_write(port, temp, UARTCTRL);
 
+	/* flush Rx/Tx FIFO */
+	temp = lpuart32_read(port, UARTFIFO);
+	temp |= UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH;
+	lpuart32_write(port, temp, UARTFIFO);
+
 	uart_port_unlock_irqrestore(port, flags);
 
 	lpuart_dma_shutdown(sport);
diff --git a/drivers/tty/serial/kgdb_nmi.c b/drivers/tty/serial/kgdb_nmi.c
index e93850f6447a..2833708e369f 100644
--- a/drivers/tty/serial/kgdb_nmi.c
+++ b/drivers/tty/serial/kgdb_nmi.c
@@ -27,18 +27,6 @@
 #include <linux/kgdb.h>
 #include <linux/kdb.h>
 
-static int kgdb_nmi_knock = 1;
-module_param_named(knock, kgdb_nmi_knock, int, 0600);
-MODULE_PARM_DESC(knock, "if set to 1 (default), the special '$3#33' command " \
-			"must be used to enter the debugger; when set to 0, " \
-			"hitting return key is enough to enter the debugger; " \
-			"when set to -1, the debugger is entered immediately " \
-			"upon NMI");
-
-static char *kgdb_nmi_magic = "$3#33";
-module_param_named(magic, kgdb_nmi_magic, charp, 0600);
-MODULE_PARM_DESC(magic, "magic sequence to enter NMI debugger (default $3#33)");
-
 static atomic_t kgdb_nmi_num_readers = ATOMIC_INIT(0);
 
 static int kgdb_nmi_console_setup(struct console *co, char *options)
@@ -95,95 +83,6 @@ struct kgdb_nmi_tty_priv {
 
 static struct tty_port *kgdb_nmi_port;
 
-static void kgdb_tty_recv(int ch)
-{
-	struct kgdb_nmi_tty_priv *priv;
-	char c = ch;
-
-	if (!kgdb_nmi_port || ch < 0)
-		return;
-	/*
-	 * Can't use port->tty->driver_data as tty might be not there. Timer
-	 * will check for tty and will get the ref, but here we don't have to
-	 * do that, and actually, we can't: we're in NMI context, no locks are
-	 * possible.
-	 */
-	priv = container_of(kgdb_nmi_port, struct kgdb_nmi_tty_priv, port);
-	kfifo_in(&priv->fifo, &c, 1);
-}
-
-static int kgdb_nmi_poll_one_knock(void)
-{
-	static int n;
-	int c;
-	const char *magic = kgdb_nmi_magic;
-	size_t m = strlen(magic);
-	bool printch = false;
-
-	c = dbg_io_ops->read_char();
-	if (c == NO_POLL_CHAR)
-		return c;
-
-	if (!kgdb_nmi_knock && (c == '\r' || c == '\n')) {
-		return 1;
-	} else if (c == magic[n]) {
-		n = (n + 1) % m;
-		if (!n)
-			return 1;
-		printch = true;
-	} else {
-		n = 0;
-	}
-
-	if (atomic_read(&kgdb_nmi_num_readers)) {
-		kgdb_tty_recv(c);
-		return 0;
-	}
-
-	if (printch) {
-		kdb_printf("%c", c);
-		return 0;
-	}
-
-	kdb_printf("\r%s %s to enter the debugger> %*s",
-		   kgdb_nmi_knock ? "Type" : "Hit",
-		   kgdb_nmi_knock ? magic  : "<return>", (int)m, "");
-	while (m--)
-		kdb_printf("\b");
-	return 0;
-}
-
-/**
- * kgdb_nmi_poll_knock - Check if it is time to enter the debugger
- *
- * "Serial ports are often noisy, especially when muxed over another port (we
- * often use serial over the headset connector). Noise on the async command
- * line just causes characters that are ignored, on a command line that blocked
- * execution noise would be catastrophic." -- Colin Cross
- *
- * So, this function implements KGDB/KDB knocking on the serial line: we won't
- * enter the debugger until we receive a known magic phrase (which is actually
- * "$3#33", known as "escape to KDB" command. There is also a relaxed variant
- * of knocking, i.e. just pressing the return key is enough to enter the
- * debugger. And if knocking is disabled, the function always returns 1.
- */
-bool kgdb_nmi_poll_knock(void)
-{
-	if (kgdb_nmi_knock < 0)
-		return true;
-
-	while (1) {
-		int ret;
-
-		ret = kgdb_nmi_poll_one_knock();
-		if (ret == NO_POLL_CHAR)
-			return false;
-		else if (ret == 1)
-			break;
-	}
-	return true;
-}
-
 /*
  * The tasklet is cheap, it does not cause wakeups when reschedules itself,
  * instead it waits for the next tick.
diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c
index f55aa353aed9..2204cc3e3b07 100644
--- a/drivers/tty/serial/mpc52xx_uart.c
+++ b/drivers/tty/serial/mpc52xx_uart.c
@@ -1621,7 +1621,7 @@ mpc52xx_console_setup(struct console *co, char *options)
 		 (void *)port->mapbase, port->membase,
 		 port->irq, port->uartclk);
 
-	/* Setup the port parameters accoding to options */
+	/* Setup the port parameters according to options */
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
 	else
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index a3093e09309f..7b51cdc274fd 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -314,6 +314,7 @@
 #define SC16IS7XX_FIFO_SIZE		(64)
 #define SC16IS7XX_GPIOS_PER_BANK	4
 
+#define SC16IS7XX_POLL_PERIOD_MS	10
 #define SC16IS7XX_RECONF_MD		BIT(0)
 #define SC16IS7XX_RECONF_IER		BIT(1)
 #define SC16IS7XX_RECONF_RS485		BIT(2)
@@ -348,6 +349,8 @@ struct sc16is7xx_port {
 	u8				mctrl_mask;
 	struct kthread_worker		kworker;
 	struct task_struct		*kworker_task;
+	struct kthread_delayed_work	poll_work;
+	bool				polling;
 	struct sc16is7xx_one		p[];
 };
 
@@ -861,6 +864,18 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void sc16is7xx_poll_proc(struct kthread_work *ws)
+{
+	struct sc16is7xx_port *s = container_of(ws, struct sc16is7xx_port, poll_work.work);
+
+	/* Reuse standard IRQ handler. Interrupt ID is unused in this context. */
+	sc16is7xx_irq(0, s);
+
+	/* Setup delay based on SC16IS7XX_POLL_PERIOD_MS */
+	kthread_queue_delayed_work(&s->kworker, &s->poll_work,
+				   msecs_to_jiffies(SC16IS7XX_POLL_PERIOD_MS));
+}
+
 static void sc16is7xx_tx_proc(struct kthread_work *ws)
 {
 	struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port);
@@ -1149,6 +1164,7 @@ static int sc16is7xx_config_rs485(struct uart_port *port, struct ktermios *termi
 static int sc16is7xx_startup(struct uart_port *port)
 {
 	struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
 	unsigned int val;
 	unsigned long flags;
 
@@ -1211,6 +1227,10 @@ static int sc16is7xx_startup(struct uart_port *port)
 	sc16is7xx_enable_ms(port);
 	uart_port_unlock_irqrestore(port, flags);
 
+	if (s->polling)
+		kthread_queue_delayed_work(&s->kworker, &s->poll_work,
+					   msecs_to_jiffies(SC16IS7XX_POLL_PERIOD_MS));
+
 	return 0;
 }
 
@@ -1232,6 +1252,9 @@ static void sc16is7xx_shutdown(struct uart_port *port)
 
 	sc16is7xx_power(port, 0);
 
+	if (s->polling)
+		kthread_cancel_delayed_work_sync(&s->poll_work);
+
 	kthread_flush_worker(&s->kworker);
 }
 
@@ -1538,6 +1561,11 @@ int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype,
 	/* Always ask for fixed clock rate from a property. */
 	device_property_read_u32(dev, "clock-frequency", &uartclk);
 
+	s->polling = !!irq;
+	if (s->polling)
+		dev_dbg(dev,
+			"No interrupt pin definition, falling back to polling mode\n");
+
 	s->clk = devm_clk_get_optional(dev, NULL);
 	if (IS_ERR(s->clk))
 		return PTR_ERR(s->clk);
@@ -1665,6 +1693,12 @@ int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype,
 		goto out_ports;
 #endif
 
+	if (s->polling) {
+		/* Initialize kernel thread for polling */
+		kthread_init_delayed_work(&s->poll_work, sc16is7xx_poll_proc);
+		return 0;
+	}
+
 	/*
 	 * Setup interrupt. We first try to acquire the IRQ line as level IRQ.
 	 * If that succeeds, we can allow sharing the interrupt as well.
@@ -1724,6 +1758,9 @@ void sc16is7xx_remove(struct device *dev)
 		sc16is7xx_power(&s->p[i].port, 0);
 	}
 
+	if (s->polling)
+		kthread_cancel_delayed_work_sync(&s->poll_work);
+
 	kthread_flush_worker(&s->kworker);
 	kthread_stop(s->kworker_task);
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 74fa02b23772..92f7e752f862 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -790,7 +790,6 @@ static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo)
 {
 	struct uart_state *state = container_of(port, struct uart_state, port);
 	struct uart_port *uport;
-	int ret = -ENODEV;
 
 	/* Initialize structure in case we error out later to prevent any stack info leakage. */
 	*retinfo = (struct serial_struct){};
@@ -799,10 +798,10 @@ static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo)
 	 * Ensure the state we copy is consistent and no hardware changes
 	 * occur as we go
 	 */
-	mutex_lock(&port->mutex);
+	guard(mutex)(&port->mutex);
 	uport = uart_port_check(state);
 	if (!uport)
-		goto out;
+		return -ENODEV;
 
 	retinfo->type	    = uport->type;
 	retinfo->line	    = uport->line;
@@ -823,10 +822,7 @@ static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo)
 	retinfo->iomem_reg_shift = uport->regshift;
 	retinfo->iomem_base      = (void *)(unsigned long)uport->mapbase;
 
-	ret = 0;
-out:
-	mutex_unlock(&port->mutex);
-	return ret;
+	return 0;
 }
 
 static int uart_get_info_user(struct tty_struct *tty,
@@ -838,6 +834,61 @@ static int uart_get_info_user(struct tty_struct *tty,
 	return uart_get_info(port, ss) < 0 ? -EIO : 0;
 }
 
+static int uart_change_port(struct uart_port *uport,
+			    const struct serial_struct *new_info,
+			    unsigned long new_port)
+{
+	unsigned long old_iobase, old_mapbase;
+	unsigned int old_type, old_iotype, old_hub6, old_shift;
+	int retval;
+
+	old_iobase = uport->iobase;
+	old_mapbase = uport->mapbase;
+	old_type = uport->type;
+	old_hub6 = uport->hub6;
+	old_iotype = uport->iotype;
+	old_shift = uport->regshift;
+
+	if (old_type != PORT_UNKNOWN && uport->ops->release_port)
+		uport->ops->release_port(uport);
+
+	uport->iobase = new_port;
+	uport->type = new_info->type;
+	uport->hub6 = new_info->hub6;
+	uport->iotype = new_info->io_type;
+	uport->regshift = new_info->iomem_reg_shift;
+	uport->mapbase = (unsigned long)new_info->iomem_base;
+
+	if (uport->type == PORT_UNKNOWN || !uport->ops->request_port)
+		return 0;
+
+	retval = uport->ops->request_port(uport);
+	if (retval == 0)
+		return 0; /* succeeded => done */
+
+	/*
+	 * If we fail to request resources for the new port, try to restore the
+	 * old settings.
+	 */
+	uport->iobase = old_iobase;
+	uport->type = old_type;
+	uport->hub6 = old_hub6;
+	uport->iotype = old_iotype;
+	uport->regshift = old_shift;
+	uport->mapbase = old_mapbase;
+
+	if (old_type == PORT_UNKNOWN)
+		return retval;
+
+	retval = uport->ops->request_port(uport);
+	/* If we failed to restore the old settings, we fail like this. */
+	if (retval)
+		uport->type = PORT_UNKNOWN;
+
+	/* We failed anyway. */
+	return -EBUSY;
+}
+
 static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 			 struct uart_state *state,
 			 struct serial_struct *new_info)
@@ -847,7 +898,7 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 	unsigned int change_irq, change_port, closing_wait;
 	unsigned int old_custom_divisor, close_delay;
 	upf_t old_flags, new_flags;
-	int retval = 0;
+	int retval;
 
 	if (!uport)
 		return -EIO;
@@ -886,13 +937,10 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 	if (!(uport->flags & UPF_FIXED_PORT)) {
 		unsigned int uartclk = new_info->baud_base * 16;
 		/* check needs to be done here before other settings made */
-		if (uartclk == 0) {
-			retval = -EINVAL;
-			goto exit;
-		}
+		if (uartclk == 0)
+			return -EINVAL;
 	}
 	if (!capable(CAP_SYS_ADMIN)) {
-		retval = -EPERM;
 		if (change_irq || change_port ||
 		    (new_info->baud_base != uport->uartclk / 16) ||
 		    (close_delay != port->close_delay) ||
@@ -900,7 +948,7 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 		    (new_info->xmit_fifo_size &&
 		     new_info->xmit_fifo_size != uport->fifosize) ||
 		    (((new_flags ^ old_flags) & ~UPF_USR_MASK) != 0))
-			goto exit;
+			return -EPERM;
 		uport->flags = ((uport->flags & ~UPF_USR_MASK) |
 			       (new_flags & UPF_USR_MASK));
 		uport->custom_divisor = new_info->custom_divisor;
@@ -910,30 +958,24 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 	if (change_irq || change_port) {
 		retval = security_locked_down(LOCKDOWN_TIOCSSERIAL);
 		if (retval)
-			goto exit;
+			return retval;
 	}
 
-	/*
-	 * Ask the low level driver to verify the settings.
-	 */
-	if (uport->ops->verify_port)
+	 /* Ask the low level driver to verify the settings. */
+	if (uport->ops->verify_port) {
 		retval = uport->ops->verify_port(uport, new_info);
+		if (retval)
+			return retval;
+	}
 
 	if ((new_info->irq >= irq_get_nr_irqs()) || (new_info->irq < 0) ||
 	    (new_info->baud_base < 9600))
-		retval = -EINVAL;
-
-	if (retval)
-		goto exit;
+		return -EINVAL;
 
 	if (change_port || change_irq) {
-		retval = -EBUSY;
-
-		/*
-		 * Make sure that we are the sole user of this port.
-		 */
+		 /* Make sure that we are the sole user of this port. */
 		if (tty_port_users(port) > 1)
-			goto exit;
+			return -EBUSY;
 
 		/*
 		 * We need to shutdown the serial port at the old
@@ -943,69 +985,9 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 	}
 
 	if (change_port) {
-		unsigned long old_iobase, old_mapbase;
-		unsigned int old_type, old_iotype, old_hub6, old_shift;
-
-		old_iobase = uport->iobase;
-		old_mapbase = uport->mapbase;
-		old_type = uport->type;
-		old_hub6 = uport->hub6;
-		old_iotype = uport->iotype;
-		old_shift = uport->regshift;
-
-		/*
-		 * Free and release old regions
-		 */
-		if (old_type != PORT_UNKNOWN && uport->ops->release_port)
-			uport->ops->release_port(uport);
-
-		uport->iobase = new_port;
-		uport->type = new_info->type;
-		uport->hub6 = new_info->hub6;
-		uport->iotype = new_info->io_type;
-		uport->regshift = new_info->iomem_reg_shift;
-		uport->mapbase = (unsigned long)new_info->iomem_base;
-
-		/*
-		 * Claim and map the new regions
-		 */
-		if (uport->type != PORT_UNKNOWN && uport->ops->request_port) {
-			retval = uport->ops->request_port(uport);
-		} else {
-			/* Always success - Jean II */
-			retval = 0;
-		}
-
-		/*
-		 * If we fail to request resources for the
-		 * new port, try to restore the old settings.
-		 */
-		if (retval) {
-			uport->iobase = old_iobase;
-			uport->type = old_type;
-			uport->hub6 = old_hub6;
-			uport->iotype = old_iotype;
-			uport->regshift = old_shift;
-			uport->mapbase = old_mapbase;
-
-			if (old_type != PORT_UNKNOWN) {
-				retval = uport->ops->request_port(uport);
-				/*
-				 * If we failed to restore the old settings,
-				 * we fail like this.
-				 */
-				if (retval)
-					uport->type = PORT_UNKNOWN;
-
-				/*
-				 * We failed anyway.
-				 */
-				retval = -EBUSY;
-			}
-
-			/* Added to return the correct error -Ram Gupta */
-			goto exit;
-		}
+		retval = uart_change_port(uport, new_info, new_port);
+		if (retval)
+			return retval;
 	}
 
 	if (change_irq)
@@ -1021,9 +1003,9 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 		uport->fifosize = new_info->xmit_fifo_size;
 
  check_and_exit:
-	retval = 0;
 	if (uport->type == PORT_UNKNOWN)
-		goto exit;
+		return 0;
+
 	if (tty_port_initialized(port)) {
 		if (((old_flags ^ uport->flags) & UPF_SPD_MASK) ||
 		    old_custom_divisor != uport->custom_divisor) {
@@ -1039,15 +1021,17 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
 			}
 			uart_change_line_settings(tty, state, NULL);
 		}
-	} else {
-		retval = uart_startup(tty, state, true);
-		if (retval == 0)
-			tty_port_set_initialized(port, true);
-		if (retval > 0)
-			retval = 0;
+
+		return 0;
 	}
- exit:
-	return retval;
+
+	retval = uart_startup(tty, state, true);
+	if (retval < 0)
+		return retval;
+	if (retval == 0)
+		tty_port_set_initialized(port, true);
+
+	return 0;
 }
 
 static int uart_set_info_user(struct tty_struct *tty, struct serial_struct *ss)
@@ -2365,9 +2349,9 @@ struct uart_match {
 	struct uart_driver *driver;
 };
 
-static int serial_match_port(struct device *dev, void *data)
+static int serial_match_port(struct device *dev, const void *data)
 {
-	struct uart_match *match = data;
+	const struct uart_match *match = data;
 	struct tty_driver *tty_drv = match->driver->tty_driver;
 	dev_t devt = MKDEV(tty_drv->major, tty_drv->minor_start) +
 		match->port->line;
@@ -3061,26 +3045,25 @@ static ssize_t console_store(struct device *dev,
 	if (ret)
 		return ret;
 
-	mutex_lock(&port->mutex);
+	guard(mutex)(&port->mutex);
 	uport = uart_port_check(state);
-	if (uport) {
-		oldconsole = uart_console_registered(uport);
-		if (oldconsole && !newconsole) {
-			ret = unregister_console(uport->cons);
-		} else if (!oldconsole && newconsole) {
-			if (uart_console(uport)) {
-				uport->console_reinit = 1;
-				register_console(uport->cons);
-			} else {
-				ret = -ENOENT;
-			}
-		}
-	} else {
-		ret = -ENXIO;
+	if (!uport)
+		return -ENXIO;
+
+	oldconsole = uart_console_registered(uport);
+	if (oldconsole && !newconsole) {
+		ret = unregister_console(uport->cons);
+		if (ret < 0)
+			return ret;
+	} else if (!oldconsole && newconsole) {
+		if (!uart_console(uport))
+			return -ENOENT;
+
+		uport->console_reinit = 1;
+		register_console(uport->cons);
 	}
-	mutex_unlock(&port->mutex);
 
-	return ret < 0 ? ret : count;
+	return count;
 }
 
 static DEVICE_ATTR_RO(uartclk);
@@ -3136,7 +3119,6 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 {
 	struct uart_state *state;
 	struct tty_port *port;
-	int ret = 0;
 	struct device *tty_dev;
 	int num_groups;
 
@@ -3146,11 +3128,9 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 	state = drv->state + uport->line;
 	port = &state->port;
 
-	mutex_lock(&port->mutex);
-	if (state->uart_port) {
-		ret = -EINVAL;
-		goto out;
-	}
+	guard(mutex)(&port->mutex);
+	if (state->uart_port)
+		return -EINVAL;
 
 	/* Link the port to the driver state table and vice versa */
 	atomic_set(&state->refcount, 1);
@@ -3170,10 +3150,8 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 	uport->minor = drv->tty_driver->minor_start + uport->line;
 	uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name,
 				drv->tty_driver->name_base + uport->line);
-	if (!uport->name) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!uport->name)
+		return -ENOMEM;
 
 	if (uport->cons && uport->dev)
 		of_console_check(uport->dev->of_node, uport->cons->name, uport->line);
@@ -3189,10 +3167,9 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 
 	uport->tty_groups = kcalloc(num_groups, sizeof(*uport->tty_groups),
 				    GFP_KERNEL);
-	if (!uport->tty_groups) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!uport->tty_groups)
+		return -ENOMEM;
+
 	uport->tty_groups[0] = &tty_dev_attr_group;
 	if (uport->attr_group)
 		uport->tty_groups[1] = uport->attr_group;
@@ -3215,10 +3192,7 @@ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *u
 		       uport->line);
 	}
 
- out:
-	mutex_unlock(&port->mutex);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -3384,7 +3358,7 @@ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port)
 	struct serial_ctrl_device *ctrl_dev, *new_ctrl_dev = NULL;
 	int ret;
 
-	mutex_lock(&port_mutex);
+	guard(mutex)(&port_mutex);
 
 	/*
 	 * Prevent serial_port_runtime_resume() from trying to use the port
@@ -3396,10 +3370,8 @@ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port)
 	ctrl_dev = serial_core_ctrl_find(drv, port->dev, port->ctrl_id);
 	if (!ctrl_dev) {
 		new_ctrl_dev = serial_core_ctrl_device_add(port);
-		if (IS_ERR(new_ctrl_dev)) {
-			ret = PTR_ERR(new_ctrl_dev);
-			goto err_unlock;
-		}
+		if (IS_ERR(new_ctrl_dev))
+			return PTR_ERR(new_ctrl_dev);
 		ctrl_dev = new_ctrl_dev;
 	}
 
@@ -3420,8 +3392,6 @@ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port)
 	if (ret)
 		goto err_unregister_port_dev;
 
-	mutex_unlock(&port_mutex);
-
 	return 0;
 
 err_unregister_port_dev:
@@ -3430,9 +3400,6 @@ err_unregister_port_dev:
 err_unregister_ctrl_dev:
 	serial_base_ctrl_device_remove(new_ctrl_dev);
 
-err_unlock:
-	mutex_unlock(&port_mutex);
-
 	return ret;
 }
 
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 924b803af440..b1ea48f38248 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -165,6 +165,8 @@ struct sci_port {
 static struct sci_port sci_ports[SCI_NPORTS];
 static unsigned long sci_ports_in_use;
 static struct uart_driver sci_uart_driver;
+static bool sci_uart_earlycon;
+static bool sci_uart_earlycon_dev_probing;
 
 static inline struct sci_port *
 to_sci_port(struct uart_port *uart)
@@ -3056,10 +3058,6 @@ static int sci_init_single(struct platform_device *dev,
 		ret = sci_init_clocks(sci_port, &dev->dev);
 		if (ret < 0)
 			return ret;
-
-		port->dev = &dev->dev;
-
-		pm_runtime_enable(&dev->dev);
 	}
 
 	port->type		= p->type;
@@ -3086,11 +3084,6 @@ static int sci_init_single(struct platform_device *dev,
 	return 0;
 }
 
-static void sci_cleanup_single(struct sci_port *port)
-{
-	pm_runtime_disable(port->port.dev);
-}
-
 #if defined(CONFIG_SERIAL_SH_SCI_CONSOLE) || \
     defined(CONFIG_SERIAL_SH_SCI_EARLYCON)
 static void serial_console_putchar(struct uart_port *port, unsigned char ch)
@@ -3260,8 +3253,6 @@ static void sci_remove(struct platform_device *dev)
 	sci_ports_in_use &= ~BIT(port->port.line);
 	uart_remove_one_port(&sci_uart_driver, &port->port);
 
-	sci_cleanup_single(port);
-
 	if (port->port.fifosize > 1)
 		device_remove_file(&dev->dev, &dev_attr_rx_fifo_trigger);
 	if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF)
@@ -3396,7 +3387,8 @@ static struct plat_sci_port *sci_parse_dt(struct platform_device *pdev,
 static int sci_probe_single(struct platform_device *dev,
 				      unsigned int index,
 				      struct plat_sci_port *p,
-				      struct sci_port *sciport)
+				      struct sci_port *sciport,
+				      struct resource *sci_res)
 {
 	int ret;
 
@@ -3425,6 +3417,11 @@ static int sci_probe_single(struct platform_device *dev,
 	if (ret)
 		return ret;
 
+	sciport->port.dev = &dev->dev;
+	ret = devm_pm_runtime_enable(&dev->dev);
+	if (ret)
+		return ret;
+
 	sciport->gpios = mctrl_gpio_init(&sciport->port, 0);
 	if (IS_ERR(sciport->gpios))
 		return PTR_ERR(sciport->gpios);
@@ -3438,18 +3435,37 @@ static int sci_probe_single(struct platform_device *dev,
 		sciport->port.flags |= UPF_HARD_FLOW;
 	}
 
-	ret = uart_add_one_port(&sci_uart_driver, &sciport->port);
-	if (ret) {
-		sci_cleanup_single(sciport);
-		return ret;
+	if (sci_uart_earlycon && sci_ports[0].port.mapbase == sci_res->start) {
+		/*
+		 * In case:
+		 * - this is the earlycon port (mapped on index 0 in sci_ports[]) and
+		 * - it now maps to an alias other than zero and
+		 * - the earlycon is still alive (e.g., "earlycon keep_bootcon" is
+		 *   available in bootargs)
+		 *
+		 * we need to avoid disabling clocks and PM domains through the runtime
+		 * PM APIs called in __device_attach(). For this, increment the runtime
+		 * PM reference counter (the clocks and PM domains were already enabled
+		 * by the bootloader). Otherwise the earlycon may access the HW when it
+		 * has no clocks enabled leading to failures (infinite loop in
+		 * sci_poll_put_char()).
+		 */
+		pm_runtime_get_noresume(&dev->dev);
+
+		/*
+		 * Skip cleanup the sci_port[0] in early_console_exit(), this
+		 * port is the same as the earlycon one.
+		 */
+		sci_uart_earlycon_dev_probing = true;
 	}
 
-	return 0;
+	return uart_add_one_port(&sci_uart_driver, &sciport->port);
 }
 
 static int sci_probe(struct platform_device *dev)
 {
 	struct plat_sci_port *p;
+	struct resource *res;
 	struct sci_port *sp;
 	unsigned int dev_id;
 	int ret;
@@ -3479,9 +3495,29 @@ static int sci_probe(struct platform_device *dev)
 	}
 
 	sp = &sci_ports[dev_id];
+
+	/*
+	 * In case:
+	 * - the probed port alias is zero (as the one used by earlycon), and
+	 * - the earlycon is still active (e.g., "earlycon keep_bootcon" in
+	 *   bootargs)
+	 *
+	 * defer the probe of this serial. This is a debug scenario and the user
+	 * must be aware of it.
+	 *
+	 * Except when the probed port is the same as the earlycon port.
+	 */
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
+	if (sci_uart_earlycon && sp == &sci_ports[0] && sp->port.mapbase != res->start)
+		return dev_err_probe(&dev->dev, -EBUSY, "sci_port[0] is used by earlycon!\n");
+
 	platform_set_drvdata(dev, sp);
 
-	ret = sci_probe_single(dev, dev_id, p, sp);
+	ret = sci_probe_single(dev, dev_id, p, sp, res);
 	if (ret)
 		return ret;
 
@@ -3562,7 +3598,23 @@ sh_early_platform_init_buffer("earlyprintk", &sci_driver,
 			   early_serial_buf, ARRAY_SIZE(early_serial_buf));
 #endif
 #ifdef CONFIG_SERIAL_SH_SCI_EARLYCON
-static struct plat_sci_port port_cfg __initdata;
+static struct plat_sci_port port_cfg;
+
+static int early_console_exit(struct console *co)
+{
+	struct sci_port *sci_port = &sci_ports[0];
+
+	/*
+	 * Clean the slot used by earlycon. A new SCI device might
+	 * map to this slot.
+	 */
+	if (!sci_uart_earlycon_dev_probing) {
+		memset(sci_port, 0, sizeof(*sci_port));
+		sci_uart_earlycon = false;
+	}
+
+	return 0;
+}
 
 static int __init early_console_setup(struct earlycon_device *device,
 				      int type)
@@ -3571,15 +3623,18 @@ static int __init early_console_setup(struct earlycon_device *device,
 		return -ENODEV;
 
 	device->port.type = type;
-	memcpy(&sci_ports[0].port, &device->port, sizeof(struct uart_port));
+	sci_ports[0].port = device->port;
 	port_cfg.type = type;
 	sci_ports[0].cfg = &port_cfg;
 	sci_ports[0].params = sci_probe_regmap(&port_cfg);
+	sci_uart_earlycon = true;
 	port_cfg.scscr = sci_serial_in(&sci_ports[0].port, SCSCR);
 	sci_serial_out(&sci_ports[0].port, SCSCR,
 		       SCSCR_RE | SCSCR_TE | port_cfg.scscr);
 
 	device->con->write = serial_console_write;
+	device->con->exit = early_console_exit;
+
 	return 0;
 }
 static int __init sci_early_console_setup(struct earlycon_device *device,
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index beb151be4d32..92ec51870d1d 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -287,7 +287,7 @@ static void cdns_uart_handle_rx(void *dev_id, unsigned int isrstatus)
 				continue;
 		}
 
-		if (uart_handle_sysrq_char(port, data))
+		if (uart_prepare_sysrq_char(port, data))
 			continue;
 
 		if (is_rxbs_support) {
@@ -495,7 +495,7 @@ static irqreturn_t cdns_uart_isr(int irq, void *dev_id)
 	    !(readl(port->membase + CDNS_UART_CR) & CDNS_UART_CR_RX_DIS))
 		cdns_uart_handle_rx(dev_id, isrstatus);
 
-	uart_port_unlock(port);
+	uart_unlock_and_check_sysrq(port);
 	return IRQ_HANDLED;
 }
 
@@ -1380,9 +1380,7 @@ static void cdns_uart_console_write(struct console *co, const char *s,
 	unsigned int imr, ctrl;
 	int locked = 1;
 
-	if (port->sysrq)
-		locked = 0;
-	else if (oops_in_progress)
+	if (oops_in_progress)
 		locked = uart_port_trylock_irqsave(port, &flags);
 	else
 		uart_port_lock_irqsave(port, &flags);
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index dcb1769c3625..449dbd216460 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2622,14 +2622,13 @@ static int tty_tiocgicount(struct tty_struct *tty, void __user *arg)
 
 static int tty_set_serial(struct tty_struct *tty, struct serial_struct *ss)
 {
-	char comm[TASK_COMM_LEN];
 	int flags;
 
 	flags = ss->flags & ASYNC_DEPRECATED;
 
 	if (flags)
 		pr_warn_ratelimited("%s: '%s' is using deprecated serial flags (with no effect): %.8x\n",
-				__func__, get_task_comm(comm, current), flags);
+				__func__, current->comm, flags);
 
 	if (!tty->ops->set_serial)
 		return -ENOTTY;
@@ -3618,7 +3617,7 @@ void console_sysfs_notify(void)
 		sysfs_notify(&consdev->kobj, NULL, "active");
 }
 
-static struct ctl_table tty_table[] = {
+static const struct ctl_table tty_table[] = {
 	{
 		.procname	= "legacy_tiocsti",
 		.data		= &tty_legacy_tiocsti,
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 564341f1a74f..0bd6544e30a6 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -192,6 +192,20 @@ int set_selection_user(const struct tiocl_selection __user *sel,
 	if (copy_from_user(&v, sel, sizeof(*sel)))
 		return -EFAULT;
 
+	/*
+	 * TIOCL_SELCLEAR, TIOCL_SELPOINTER and TIOCL_SELMOUSEREPORT are OK to
+	 * use without CAP_SYS_ADMIN as they do not modify the selection.
+	 */
+	switch (v.sel_mode) {
+	case TIOCL_SELCLEAR:
+	case TIOCL_SELPOINTER:
+	case TIOCL_SELMOUSEREPORT:
+		break;
+	default:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	}
+
 	return set_selection_kernel(&v, tty);
 }
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 96842ce817af..be5564ed8c01 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3345,8 +3345,6 @@ int tioclinux(struct tty_struct *tty, unsigned long arg)
 
 	switch (type) {
 	case TIOCL_SETSEL:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
 		return set_selection_user(param, tty);
 	case TIOCL_PASTESEL:
 		if (!capable(CAP_SYS_ADMIN))
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index 796e37a1d859..3438269a5440 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -1439,6 +1439,7 @@ static ssize_t max_number_of_rtt_store(struct device *dev,
 	struct ufs_hba *hba = dev_get_drvdata(dev);
 	struct ufs_dev_info *dev_info = &hba->dev_info;
 	struct scsi_device *sdev;
+	unsigned int memflags;
 	unsigned int rtt;
 	int ret;
 
@@ -1458,14 +1459,16 @@ static ssize_t max_number_of_rtt_store(struct device *dev,
 
 	ufshcd_rpm_get_sync(hba);
 
+	memflags = memalloc_noio_save();
 	shost_for_each_device(sdev, hba->host)
-		blk_mq_freeze_queue(sdev->request_queue);
+		blk_mq_freeze_queue_nomemsave(sdev->request_queue);
 
 	ret = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR,
 		QUERY_ATTR_IDN_MAX_NUM_OF_RTT, 0, 0, &rtt);
 
 	shost_for_each_device(sdev, hba->host)
-		blk_mq_unfreeze_queue(sdev->request_queue);
+		blk_mq_unfreeze_queue_nomemrestore(sdev->request_queue);
+	memalloc_noio_restore(memflags);
 
 	ufshcd_rpm_put_sync(hba);
 
diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 6c09d97ae006..8d4ad0a3f2cf 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -216,6 +216,7 @@ void ufs_bsg_remove(struct ufs_hba *hba)
 		return;
 
 	bsg_remove_queue(hba->bsg_queue);
+	hba->bsg_queue = NULL;
 
 	device_del(bsg_dev);
 	put_device(bsg_dev);
@@ -257,6 +258,7 @@ int ufs_bsg_probe(struct ufs_hba *hba)
 			NULL, 0);
 	if (IS_ERR(q)) {
 		ret = PTR_ERR(q);
+		device_del(bsg_dev);
 		goto out;
 	}
 
diff --git a/drivers/ufs/core/ufshcd-crypto.c b/drivers/ufs/core/ufshcd-crypto.c
index a714dad82cd1..694ff7578fc1 100644
--- a/drivers/ufs/core/ufshcd-crypto.c
+++ b/drivers/ufs/core/ufshcd-crypto.c
@@ -17,20 +17,14 @@ static const struct ufs_crypto_alg_entry {
 	},
 };
 
-static int ufshcd_program_key(struct ufs_hba *hba,
-			      const union ufs_crypto_cfg_entry *cfg, int slot)
+static void ufshcd_program_key(struct ufs_hba *hba,
+			       const union ufs_crypto_cfg_entry *cfg, int slot)
 {
 	int i;
 	u32 slot_offset = hba->crypto_cfg_register + slot * sizeof(*cfg);
-	int err = 0;
 
 	ufshcd_hold(hba);
 
-	if (hba->vops && hba->vops->program_key) {
-		err = hba->vops->program_key(hba, cfg, slot);
-		goto out;
-	}
-
 	/* Ensure that CFGE is cleared before programming the key */
 	ufshcd_writel(hba, 0, slot_offset + 16 * sizeof(cfg->reg_val[0]));
 	for (i = 0; i < 16; i++) {
@@ -43,17 +37,14 @@ static int ufshcd_program_key(struct ufs_hba *hba,
 	/* Dword 16 must be written last */
 	ufshcd_writel(hba, le32_to_cpu(cfg->reg_val[16]),
 		      slot_offset + 16 * sizeof(cfg->reg_val[0]));
-out:
 	ufshcd_release(hba);
-	return err;
 }
 
 static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile,
 					 const struct blk_crypto_key *key,
 					 unsigned int slot)
 {
-	struct ufs_hba *hba =
-		container_of(profile, struct ufs_hba, crypto_profile);
+	struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile);
 	const union ufs_crypto_cap_entry *ccap_array = hba->crypto_cap_array;
 	const struct ufs_crypto_alg_entry *alg =
 			&ufs_crypto_algs[key->crypto_cfg.crypto_mode];
@@ -61,7 +52,6 @@ static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile,
 	int i;
 	int cap_idx = -1;
 	union ufs_crypto_cfg_entry cfg = {};
-	int err;
 
 	BUILD_BUG_ON(UFS_CRYPTO_KEY_SIZE_INVALID != 0);
 	for (i = 0; i < hba->crypto_capabilities.num_crypto_cap; i++) {
@@ -89,25 +79,25 @@ static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile,
 		memcpy(cfg.crypto_key, key->raw, key->size);
 	}
 
-	err = ufshcd_program_key(hba, &cfg, slot);
+	ufshcd_program_key(hba, &cfg, slot);
 
 	memzero_explicit(&cfg, sizeof(cfg));
-	return err;
+	return 0;
 }
 
 static int ufshcd_crypto_keyslot_evict(struct blk_crypto_profile *profile,
 				       const struct blk_crypto_key *key,
 				       unsigned int slot)
 {
-	struct ufs_hba *hba =
-		container_of(profile, struct ufs_hba, crypto_profile);
+	struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile);
 	/*
 	 * Clear the crypto cfg on the device. Clearing CFGE
 	 * might not be sufficient, so just clear the entire cfg.
 	 */
 	union ufs_crypto_cfg_entry cfg = {};
 
-	return ufshcd_program_key(hba, &cfg, slot);
+	ufshcd_program_key(hba, &cfg, slot);
+	return 0;
 }
 
 /*
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 3094f3c89e82..1893a7ad9531 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -258,10 +258,15 @@ ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
 	return UFS_PM_LVL_0;
 }
 
+static bool ufshcd_has_pending_tasks(struct ufs_hba *hba)
+{
+	return hba->outstanding_tasks || hba->active_uic_cmd ||
+	       hba->uic_async_done;
+}
+
 static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba)
 {
-	return (hba->clk_gating.active_reqs || hba->outstanding_reqs || hba->outstanding_tasks ||
-		hba->active_uic_cmd || hba->uic_async_done);
+	return hba->outstanding_reqs || ufshcd_has_pending_tasks(hba);
 }
 
 static const struct ufs_dev_quirk ufs_fixups[] = {
@@ -1447,16 +1452,16 @@ static void ufshcd_clk_scaling_suspend_work(struct work_struct *work)
 {
 	struct ufs_hba *hba = container_of(work, struct ufs_hba,
 					   clk_scaling.suspend_work);
-	unsigned long irq_flags;
 
-	spin_lock_irqsave(hba->host->host_lock, irq_flags);
-	if (hba->clk_scaling.active_reqs || hba->clk_scaling.is_suspended) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		return;
+	scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock)
+	{
+		if (hba->clk_scaling.active_reqs ||
+		    hba->clk_scaling.is_suspended)
+			return;
+
+		hba->clk_scaling.is_suspended = true;
+		hba->clk_scaling.window_start_t = 0;
 	}
-	hba->clk_scaling.is_suspended = true;
-	hba->clk_scaling.window_start_t = 0;
-	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
 
 	devfreq_suspend_device(hba->devfreq);
 }
@@ -1465,15 +1470,13 @@ static void ufshcd_clk_scaling_resume_work(struct work_struct *work)
 {
 	struct ufs_hba *hba = container_of(work, struct ufs_hba,
 					   clk_scaling.resume_work);
-	unsigned long irq_flags;
 
-	spin_lock_irqsave(hba->host->host_lock, irq_flags);
-	if (!hba->clk_scaling.is_suspended) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		return;
+	scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock)
+	{
+		if (!hba->clk_scaling.is_suspended)
+			return;
+		hba->clk_scaling.is_suspended = false;
 	}
-	hba->clk_scaling.is_suspended = false;
-	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
 
 	devfreq_resume_device(hba->devfreq);
 }
@@ -1487,7 +1490,6 @@ static int ufshcd_devfreq_target(struct device *dev,
 	bool scale_up = false, sched_clk_scaling_suspend_work = false;
 	struct list_head *clk_list = &hba->clk_list_head;
 	struct ufs_clk_info *clki;
-	unsigned long irq_flags;
 
 	if (!ufshcd_is_clkscaling_supported(hba))
 		return -EINVAL;
@@ -1508,43 +1510,38 @@ static int ufshcd_devfreq_target(struct device *dev,
 		*freq =	(unsigned long) clk_round_rate(clki->clk, *freq);
 	}
 
-	spin_lock_irqsave(hba->host->host_lock, irq_flags);
-	if (ufshcd_eh_in_progress(hba)) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		return 0;
-	}
+	scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock)
+	{
+		if (ufshcd_eh_in_progress(hba))
+			return 0;
 
-	/* Skip scaling clock when clock scaling is suspended */
-	if (hba->clk_scaling.is_suspended) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		dev_warn(hba->dev, "clock scaling is suspended, skip");
-		return 0;
-	}
+		/* Skip scaling clock when clock scaling is suspended */
+		if (hba->clk_scaling.is_suspended) {
+			dev_warn(hba->dev, "clock scaling is suspended, skip");
+			return 0;
+		}
 
-	if (!hba->clk_scaling.active_reqs)
-		sched_clk_scaling_suspend_work = true;
+		if (!hba->clk_scaling.active_reqs)
+			sched_clk_scaling_suspend_work = true;
 
-	if (list_empty(clk_list)) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		goto out;
-	}
+		if (list_empty(clk_list))
+			goto out;
 
-	/* Decide based on the target or rounded-off frequency and update */
-	if (hba->use_pm_opp)
-		scale_up = *freq > hba->clk_scaling.target_freq;
-	else
-		scale_up = *freq == clki->max_freq;
+		/* Decide based on the target or rounded-off frequency and update */
+		if (hba->use_pm_opp)
+			scale_up = *freq > hba->clk_scaling.target_freq;
+		else
+			scale_up = *freq == clki->max_freq;
 
-	if (!hba->use_pm_opp && !scale_up)
-		*freq = clki->min_freq;
+		if (!hba->use_pm_opp && !scale_up)
+			*freq = clki->min_freq;
 
-	/* Update the frequency */
-	if (!ufshcd_is_devfreq_scaling_required(hba, *freq, scale_up)) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		ret = 0;
-		goto out; /* no state change required */
+		/* Update the frequency */
+		if (!ufshcd_is_devfreq_scaling_required(hba, *freq, scale_up)) {
+			ret = 0;
+			goto out; /* no state change required */
+		}
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
 
 	start = ktime_get();
 	ret = ufshcd_devfreq_scale(hba, *freq, scale_up);
@@ -1569,7 +1566,6 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 {
 	struct ufs_hba *hba = dev_get_drvdata(dev);
 	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
-	unsigned long flags;
 	ktime_t curr_t;
 
 	if (!ufshcd_is_clkscaling_supported(hba))
@@ -1577,7 +1573,8 @@ static int ufshcd_devfreq_get_dev_status(struct device *dev,
 
 	memset(stat, 0, sizeof(*stat));
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_scaling.lock);
+
 	curr_t = ktime_get();
 	if (!scaling->window_start_t)
 		goto start_window;
@@ -1613,7 +1610,7 @@ start_window:
 		scaling->busy_start_t = 0;
 		scaling->is_busy_started = false;
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
 	return 0;
 }
 
@@ -1677,19 +1674,19 @@ static void ufshcd_devfreq_remove(struct ufs_hba *hba)
 
 static void ufshcd_suspend_clkscaling(struct ufs_hba *hba)
 {
-	unsigned long flags;
 	bool suspend = false;
 
 	cancel_work_sync(&hba->clk_scaling.suspend_work);
 	cancel_work_sync(&hba->clk_scaling.resume_work);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (!hba->clk_scaling.is_suspended) {
-		suspend = true;
-		hba->clk_scaling.is_suspended = true;
-		hba->clk_scaling.window_start_t = 0;
+	scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock)
+	{
+		if (!hba->clk_scaling.is_suspended) {
+			suspend = true;
+			hba->clk_scaling.is_suspended = true;
+			hba->clk_scaling.window_start_t = 0;
+		}
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	if (suspend)
 		devfreq_suspend_device(hba->devfreq);
@@ -1697,15 +1694,15 @@ static void ufshcd_suspend_clkscaling(struct ufs_hba *hba)
 
 static void ufshcd_resume_clkscaling(struct ufs_hba *hba)
 {
-	unsigned long flags;
 	bool resume = false;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->clk_scaling.is_suspended) {
-		resume = true;
-		hba->clk_scaling.is_suspended = false;
+	scoped_guard(spinlock_irqsave, &hba->clk_scaling.lock)
+	{
+		if (hba->clk_scaling.is_suspended) {
+			resume = true;
+			hba->clk_scaling.is_suspended = false;
+		}
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	if (resume)
 		devfreq_resume_device(hba->devfreq);
@@ -1791,6 +1788,8 @@ static void ufshcd_init_clk_scaling(struct ufs_hba *hba)
 	INIT_WORK(&hba->clk_scaling.resume_work,
 		  ufshcd_clk_scaling_resume_work);
 
+	spin_lock_init(&hba->clk_scaling.lock);
+
 	hba->clk_scaling.workq = alloc_ordered_workqueue(
 		"ufs_clkscaling_%d", WQ_MEM_RECLAIM, hba->host->host_no);
 
@@ -1811,19 +1810,16 @@ static void ufshcd_exit_clk_scaling(struct ufs_hba *hba)
 static void ufshcd_ungate_work(struct work_struct *work)
 {
 	int ret;
-	unsigned long flags;
 	struct ufs_hba *hba = container_of(work, struct ufs_hba,
 			clk_gating.ungate_work);
 
 	cancel_delayed_work_sync(&hba->clk_gating.gate_work);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->clk_gating.state == CLKS_ON) {
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
-		return;
+	scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) {
+		if (hba->clk_gating.state == CLKS_ON)
+			return;
 	}
 
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	ufshcd_hba_vreg_set_hpm(hba);
 	ufshcd_setup_clocks(hba, true);
 
@@ -1858,7 +1854,7 @@ void ufshcd_hold(struct ufs_hba *hba)
 	if (!ufshcd_is_clkgating_allowed(hba) ||
 	    !hba->clk_gating.is_initialized)
 		return;
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	spin_lock_irqsave(&hba->clk_gating.lock, flags);
 	hba->clk_gating.active_reqs++;
 
 start:
@@ -1874,11 +1870,11 @@ start:
 		 */
 		if (ufshcd_can_hibern8_during_gating(hba) &&
 		    ufshcd_is_link_hibern8(hba)) {
-			spin_unlock_irqrestore(hba->host->host_lock, flags);
+			spin_unlock_irqrestore(&hba->clk_gating.lock, flags);
 			flush_result = flush_work(&hba->clk_gating.ungate_work);
 			if (hba->clk_gating.is_suspended && !flush_result)
 				return;
-			spin_lock_irqsave(hba->host->host_lock, flags);
+			spin_lock_irqsave(&hba->clk_gating.lock, flags);
 			goto start;
 		}
 		break;
@@ -1907,17 +1903,17 @@ start:
 		 */
 		fallthrough;
 	case REQ_CLKS_ON:
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		spin_unlock_irqrestore(&hba->clk_gating.lock, flags);
 		flush_work(&hba->clk_gating.ungate_work);
 		/* Make sure state is CLKS_ON before returning */
-		spin_lock_irqsave(hba->host->host_lock, flags);
+		spin_lock_irqsave(&hba->clk_gating.lock, flags);
 		goto start;
 	default:
 		dev_err(hba->dev, "%s: clk gating is in invalid state %d\n",
 				__func__, hba->clk_gating.state);
 		break;
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	spin_unlock_irqrestore(&hba->clk_gating.lock, flags);
 }
 EXPORT_SYMBOL_GPL(ufshcd_hold);
 
@@ -1925,28 +1921,32 @@ static void ufshcd_gate_work(struct work_struct *work)
 {
 	struct ufs_hba *hba = container_of(work, struct ufs_hba,
 			clk_gating.gate_work.work);
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	/*
-	 * In case you are here to cancel this work the gating state
-	 * would be marked as REQ_CLKS_ON. In this case save time by
-	 * skipping the gating work and exit after changing the clock
-	 * state to CLKS_ON.
-	 */
-	if (hba->clk_gating.is_suspended ||
-		(hba->clk_gating.state != REQ_CLKS_OFF)) {
-		hba->clk_gating.state = CLKS_ON;
-		trace_ufshcd_clk_gating(dev_name(hba->dev),
-					hba->clk_gating.state);
-		goto rel_lock;
-	}
+	scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) {
+		/*
+		 * In case you are here to cancel this work the gating state
+		 * would be marked as REQ_CLKS_ON. In this case save time by
+		 * skipping the gating work and exit after changing the clock
+		 * state to CLKS_ON.
+		 */
+		if (hba->clk_gating.is_suspended ||
+		    hba->clk_gating.state != REQ_CLKS_OFF) {
+			hba->clk_gating.state = CLKS_ON;
+			trace_ufshcd_clk_gating(dev_name(hba->dev),
+						hba->clk_gating.state);
+			return;
+		}
 
-	if (ufshcd_is_ufs_dev_busy(hba) || hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
-		goto rel_lock;
+		if (hba->clk_gating.active_reqs)
+			return;
+	}
 
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	scoped_guard(spinlock_irqsave, hba->host->host_lock) {
+		if (ufshcd_is_ufs_dev_busy(hba) ||
+		    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
+			return;
+	}
 
 	/* put the link into hibern8 mode before turning off clocks */
 	if (ufshcd_can_hibern8_during_gating(hba)) {
@@ -1957,7 +1957,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 					__func__, ret);
 			trace_ufshcd_clk_gating(dev_name(hba->dev),
 						hba->clk_gating.state);
-			goto out;
+			return;
 		}
 		ufshcd_set_link_hibern8(hba);
 	}
@@ -1977,33 +1977,34 @@ static void ufshcd_gate_work(struct work_struct *work)
 	 * prevent from doing cancel work multiple times when there are
 	 * new requests arriving before the current cancel work is done.
 	 */
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
 	if (hba->clk_gating.state == REQ_CLKS_OFF) {
 		hba->clk_gating.state = CLKS_OFF;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
 	}
-rel_lock:
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-out:
-	return;
 }
 
-/* host lock must be held before calling this variant */
 static void __ufshcd_release(struct ufs_hba *hba)
 {
+	lockdep_assert_held(&hba->clk_gating.lock);
+
 	if (!ufshcd_is_clkgating_allowed(hba))
 		return;
 
 	hba->clk_gating.active_reqs--;
 
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended ||
-	    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL ||
-	    hba->outstanding_tasks || !hba->clk_gating.is_initialized ||
-	    hba->active_uic_cmd || hba->uic_async_done ||
+	    !hba->clk_gating.is_initialized ||
 	    hba->clk_gating.state == CLKS_OFF)
 		return;
 
+	scoped_guard(spinlock_irqsave, hba->host->host_lock) {
+		if (ufshcd_has_pending_tasks(hba) ||
+		    hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
+			return;
+	}
+
 	hba->clk_gating.state = REQ_CLKS_OFF;
 	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
 	queue_delayed_work(hba->clk_gating.clk_gating_workq,
@@ -2013,11 +2014,8 @@ static void __ufshcd_release(struct ufs_hba *hba)
 
 void ufshcd_release(struct ufs_hba *hba)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
 	__ufshcd_release(hba);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 EXPORT_SYMBOL_GPL(ufshcd_release);
 
@@ -2032,11 +2030,9 @@ static ssize_t ufshcd_clkgate_delay_show(struct device *dev,
 void ufshcd_clkgate_delay_set(struct device *dev, unsigned long value)
 {
 	struct ufs_hba *hba = dev_get_drvdata(dev);
-	unsigned long flags;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
 	hba->clk_gating.delay_ms = value;
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 EXPORT_SYMBOL_GPL(ufshcd_clkgate_delay_set);
 
@@ -2064,7 +2060,6 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct ufs_hba *hba = dev_get_drvdata(dev);
-	unsigned long flags;
 	u32 value;
 
 	if (kstrtou32(buf, 0, &value))
@@ -2072,9 +2067,10 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 
 	value = !!value;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_gating.lock);
+
 	if (value == hba->clk_gating.is_enabled)
-		goto out;
+		return count;
 
 	if (value)
 		__ufshcd_release(hba);
@@ -2082,8 +2078,7 @@ static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
 		hba->clk_gating.active_reqs++;
 
 	hba->clk_gating.is_enabled = value;
-out:
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
 	return count;
 }
 
@@ -2154,19 +2149,17 @@ static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba)
 {
 	bool queue_resume_work = false;
 	ktime_t curr_t = ktime_get();
-	unsigned long flags;
 
 	if (!ufshcd_is_clkscaling_supported(hba))
 		return;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_scaling.lock);
+
 	if (!hba->clk_scaling.active_reqs++)
 		queue_resume_work = true;
 
-	if (!hba->clk_scaling.is_enabled || hba->pm_op_in_progress) {
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
+	if (!hba->clk_scaling.is_enabled || hba->pm_op_in_progress)
 		return;
-	}
 
 	if (queue_resume_work)
 		queue_work(hba->clk_scaling.workq,
@@ -2182,18 +2175,17 @@ static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba)
 		hba->clk_scaling.busy_start_t = curr_t;
 		hba->clk_scaling.is_busy_started = true;
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 
 static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 {
 	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
-	unsigned long flags;
 
 	if (!ufshcd_is_clkscaling_supported(hba))
 		return;
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	guard(spinlock_irqsave)(&hba->clk_scaling.lock);
+
 	hba->clk_scaling.active_reqs--;
 	if (!scaling->active_reqs && scaling->is_busy_started) {
 		scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(),
@@ -2201,7 +2193,6 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 		scaling->busy_start_t = 0;
 		scaling->is_busy_started = false;
 	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
 }
 
 static inline int ufshcd_monitor_opcode2dir(u8 opcode)
@@ -2418,12 +2409,7 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba)
 	else
 		hba->lsdb_sup = true;
 
-	if (!hba->mcq_sup)
-		return 0;
-
 	hba->mcq_capabilities = ufshcd_readl(hba, REG_MCQCAP);
-	hba->ext_iid_sup = FIELD_GET(MASK_EXT_IID_SUPPORT,
-				     hba->mcq_capabilities);
 
 	return 0;
 }
@@ -3118,8 +3104,13 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	case UPIU_TRANSACTION_QUERY_RSP: {
 		u8 response = lrbp->ucd_rsp_ptr->header.response;
 
-		if (response == 0)
+		if (response == 0) {
 			err = ufshcd_copy_query_response(hba, lrbp);
+		} else {
+			err = -EINVAL;
+			dev_err(hba->dev, "%s: unexpected response in Query RSP: %x\n",
+					__func__, response);
+		}
 		break;
 	}
 	case UPIU_TRANSACTION_REJECT_UPIU:
@@ -4812,20 +4803,14 @@ EXPORT_SYMBOL_GPL(ufshcd_make_hba_operational);
  */
 void ufshcd_hba_stop(struct ufs_hba *hba)
 {
-	unsigned long flags;
 	int err;
 
-	/*
-	 * Obtain the host lock to prevent that the controller is disabled
-	 * while the UFS interrupt handler is active on another CPU.
-	 */
-	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_disable_irq(hba);
 	ufshcd_writel(hba, CONTROLLER_DISABLE,  REG_CONTROLLER_ENABLE);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-
 	err = ufshcd_wait_for_register(hba, REG_CONTROLLER_ENABLE,
 					CONTROLLER_ENABLE, CONTROLLER_DISABLE,
 					10, 1);
+	ufshcd_enable_irq(hba);
 	if (err)
 		dev_err(hba->dev, "%s: Controller disable failed\n", __func__);
 }
@@ -5195,12 +5180,12 @@ set_qdepth:
 }
 
 /**
- * ufshcd_slave_alloc - handle initial SCSI device configurations
+ * ufshcd_sdev_init - handle initial SCSI device configurations
  * @sdev: pointer to SCSI device
  *
  * Return: success.
  */
-static int ufshcd_slave_alloc(struct scsi_device *sdev)
+static int ufshcd_sdev_init(struct scsi_device *sdev)
 {
 	struct ufs_hba *hba;
 
@@ -5243,14 +5228,14 @@ static int ufshcd_change_queue_depth(struct scsi_device *sdev, int depth)
 }
 
 /**
- * ufshcd_device_configure - adjust SCSI device configurations
+ * ufshcd_sdev_configure - adjust SCSI device configurations
  * @sdev: pointer to SCSI device
  * @lim: queue limits
  *
  * Return: 0 (success).
  */
-static int ufshcd_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int ufshcd_sdev_configure(struct scsi_device *sdev,
+				 struct queue_limits *lim)
 {
 	struct ufs_hba *hba = shost_priv(sdev->host);
 	struct request_queue *q = sdev->request_queue;
@@ -5281,10 +5266,10 @@ static int ufshcd_device_configure(struct scsi_device *sdev,
 }
 
 /**
- * ufshcd_slave_destroy - remove SCSI device configurations
+ * ufshcd_sdev_destroy - remove SCSI device configurations
  * @sdev: pointer to SCSI device
  */
-static void ufshcd_slave_destroy(struct scsi_device *sdev)
+static void ufshcd_sdev_destroy(struct scsi_device *sdev)
 {
 	struct ufs_hba *hba;
 	unsigned long flags;
@@ -5994,24 +5979,6 @@ out:
 				__func__, err);
 }
 
-static void ufshcd_temp_exception_event_handler(struct ufs_hba *hba, u16 status)
-{
-	u32 value;
-
-	if (ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
-				QUERY_ATTR_IDN_CASE_ROUGH_TEMP, 0, 0, &value))
-		return;
-
-	dev_info(hba->dev, "exception Tcase %d\n", value - 80);
-
-	ufs_hwmon_notify_event(hba, status & MASK_EE_URGENT_TEMP);
-
-	/*
-	 * A placeholder for the platform vendors to add whatever additional
-	 * steps required
-	 */
-}
-
 static int __ufshcd_wb_toggle(struct ufs_hba *hba, bool set, enum flag_idn idn)
 {
 	u8 index;
@@ -6232,7 +6199,7 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
 		ufshcd_bkops_exception_event_handler(hba);
 
 	if (status & hba->ee_drv_mask & MASK_EE_URGENT_TEMP)
-		ufshcd_temp_exception_event_handler(hba, status);
+		ufs_hwmon_notify_event(hba, status & MASK_EE_URGENT_TEMP);
 
 	ufs_debugfs_exception_event(hba, status);
 }
@@ -8133,31 +8100,6 @@ static void ufshcd_temp_notif_probe(struct ufs_hba *hba, const u8 *desc_buf)
 	}
 }
 
-static void ufshcd_ext_iid_probe(struct ufs_hba *hba, u8 *desc_buf)
-{
-	struct ufs_dev_info *dev_info = &hba->dev_info;
-	u32 ext_ufs_feature;
-	u32 ext_iid_en = 0;
-	int err;
-
-	/* Only UFS-4.0 and above may support EXT_IID */
-	if (dev_info->wspecversion < 0x400)
-		goto out;
-
-	ext_ufs_feature = get_unaligned_be32(desc_buf +
-				     DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP);
-	if (!(ext_ufs_feature & UFS_DEV_EXT_IID_SUP))
-		goto out;
-
-	err = ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR,
-				      QUERY_ATTR_IDN_EXT_IID_EN, 0, 0, &ext_iid_en);
-	if (err)
-		dev_err(hba->dev, "failed reading bEXTIIDEn. err = %d\n", err);
-
-out:
-	dev_info->b_ext_iid_en = ext_iid_en;
-}
-
 static void ufshcd_set_rtt(struct ufs_hba *hba)
 {
 	struct ufs_dev_info *dev_info = &hba->dev_info;
@@ -8259,7 +8201,9 @@ static void ufshcd_rtc_work(struct work_struct *work)
 	hba = container_of(to_delayed_work(work), struct ufs_hba, ufs_rtc_update_work);
 
 	 /* Update RTC only when there are no requests in progress and UFSHCI is operational */
-	if (!ufshcd_is_ufs_dev_busy(hba) && hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL)
+	if (!ufshcd_is_ufs_dev_busy(hba) &&
+	    hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL &&
+	    !hba->clk_gating.active_reqs)
 		ufshcd_update_rtc(hba);
 
 	if (ufshcd_is_ufs_dev_active(hba) && hba->dev_info.rtc_update_period)
@@ -8351,9 +8295,6 @@ static int ufs_get_device_desc(struct ufs_hba *hba)
 
 	ufs_init_rtc(hba, desc_buf);
 
-	if (hba->ext_iid_sup)
-		ufshcd_ext_iid_probe(hba, desc_buf);
-
 	/*
 	 * ufshcd_read_string_desc returns size of the string
 	 * reset the error value
@@ -8967,9 +8908,9 @@ static const struct scsi_host_template ufshcd_driver_template = {
 	.map_queues		= ufshcd_map_queues,
 	.queuecommand		= ufshcd_queuecommand,
 	.mq_poll		= ufshcd_poll,
-	.slave_alloc		= ufshcd_slave_alloc,
-	.device_configure	= ufshcd_device_configure,
-	.slave_destroy		= ufshcd_slave_destroy,
+	.sdev_init		= ufshcd_sdev_init,
+	.sdev_configure		= ufshcd_sdev_configure,
+	.sdev_destroy		= ufshcd_sdev_destroy,
 	.change_queue_depth	= ufshcd_change_queue_depth,
 	.eh_abort_handler	= ufshcd_abort,
 	.eh_device_reset_handler = ufshcd_eh_device_reset_handler,
@@ -9155,7 +9096,6 @@ static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on)
 	int ret = 0;
 	struct ufs_clk_info *clki;
 	struct list_head *head = &hba->clk_list_head;
-	unsigned long flags;
 	ktime_t start = ktime_get();
 	bool clk_state_changed = false;
 
@@ -9205,12 +9145,11 @@ out:
 			if (!IS_ERR_OR_NULL(clki->clk) && clki->enabled)
 				clk_disable_unprepare(clki->clk);
 		}
-	} else if (!ret && on) {
-		spin_lock_irqsave(hba->host->host_lock, flags);
-		hba->clk_gating.state = CLKS_ON;
+	} else if (!ret && on && hba->clk_gating.is_initialized) {
+		scoped_guard(spinlock_irqsave, &hba->clk_gating.lock)
+			hba->clk_gating.state = CLKS_ON;
 		trace_ufshcd_clk_gating(dev_name(hba->dev),
 					hba->clk_gating.state);
-		spin_unlock_irqrestore(hba->host->host_lock, flags);
 	}
 
 	if (clk_state_changed)
@@ -10293,16 +10232,6 @@ EXPORT_SYMBOL_GPL(ufshcd_system_thaw);
 #endif /* CONFIG_PM_SLEEP  */
 
 /**
- * ufshcd_dealloc_host - deallocate Host Bus Adapter (HBA)
- * @hba: pointer to Host Bus Adapter (HBA)
- */
-void ufshcd_dealloc_host(struct ufs_hba *hba)
-{
-	scsi_host_put(hba->host);
-}
-EXPORT_SYMBOL_GPL(ufshcd_dealloc_host);
-
-/**
  * ufshcd_set_dma_mask - Set dma mask based on the controller
  *			 addressing capability
  * @hba: per adapter instance
@@ -10321,11 +10250,25 @@ static int ufshcd_set_dma_mask(struct ufs_hba *hba)
 }
 
 /**
+ * ufshcd_devres_release - devres cleanup handler, invoked during release of
+ *			   hba->dev
+ * @host: pointer to SCSI host
+ */
+static void ufshcd_devres_release(void *host)
+{
+	scsi_host_put(host);
+}
+
+/**
  * ufshcd_alloc_host - allocate Host Bus Adapter (HBA)
  * @dev: pointer to device handle
  * @hba_handle: driver private handle
  *
  * Return: 0 on success, non-zero value on failure.
+ *
+ * NOTE: There is no corresponding ufshcd_dealloc_host() because this function
+ * keeps track of its allocations using devres and deallocates everything on
+ * device removal automatically.
  */
 int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle)
 {
@@ -10347,6 +10290,13 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle)
 		err = -ENOMEM;
 		goto out_error;
 	}
+
+	err = devm_add_action_or_reset(dev, ufshcd_devres_release,
+				       host);
+	if (err)
+		return dev_err_probe(dev, err,
+				     "failed to add ufshcd dealloc action\n");
+
 	host->nr_maps = HCTX_TYPE_POLL + 1;
 	hba = shost_priv(host);
 	hba->host = host;
@@ -10475,6 +10425,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	hba->irq = irq;
 	hba->vps = &ufs_hba_vps;
 
+	/*
+	 * Initialize clk_gating.lock early since it is being used in
+	 * ufshcd_setup_clocks()
+	 */
+	spin_lock_init(&hba->clk_gating.lock);
+
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 91e94fe990b4..23b9f6efa047 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -112,11 +112,18 @@ static inline void ufs_qcom_ice_enable(struct ufs_qcom_host *host)
 		qcom_ice_enable(host->ice);
 }
 
+static const struct blk_crypto_ll_ops ufs_qcom_crypto_ops; /* forward decl */
+
 static int ufs_qcom_ice_init(struct ufs_qcom_host *host)
 {
 	struct ufs_hba *hba = host->hba;
+	struct blk_crypto_profile *profile = &hba->crypto_profile;
 	struct device *dev = hba->dev;
 	struct qcom_ice *ice;
+	union ufs_crypto_capabilities caps;
+	union ufs_crypto_cap_entry cap;
+	int err;
+	int i;
 
 	ice = of_qcom_ice_get(dev);
 	if (ice == ERR_PTR(-EOPNOTSUPP)) {
@@ -128,8 +135,38 @@ static int ufs_qcom_ice_init(struct ufs_qcom_host *host)
 		return PTR_ERR_OR_ZERO(ice);
 
 	host->ice = ice;
-	hba->caps |= UFSHCD_CAP_CRYPTO;
 
+	/* Initialize the blk_crypto_profile */
+
+	caps.reg_val = cpu_to_le32(ufshcd_readl(hba, REG_UFS_CCAP));
+
+	/* The number of keyslots supported is (CFGC+1) */
+	err = devm_blk_crypto_profile_init(dev, profile, caps.config_count + 1);
+	if (err)
+		return err;
+
+	profile->ll_ops = ufs_qcom_crypto_ops;
+	profile->max_dun_bytes_supported = 8;
+	profile->dev = dev;
+
+	/*
+	 * Currently this driver only supports AES-256-XTS.  All known versions
+	 * of ICE support it, but to be safe make sure it is really declared in
+	 * the crypto capability registers.  The crypto capability registers
+	 * also give the supported data unit size(s).
+	 */
+	for (i = 0; i < caps.num_crypto_cap; i++) {
+		cap.reg_val = cpu_to_le32(ufshcd_readl(hba,
+						       REG_UFS_CRYPTOCAP +
+						       i * sizeof(__le32)));
+		if (cap.algorithm_id == UFS_CRYPTO_ALG_AES_XTS &&
+		    cap.key_size == UFS_CRYPTO_KEY_SIZE_256)
+			profile->modes_supported[BLK_ENCRYPTION_MODE_AES_256_XTS] |=
+				cap.sdus_mask * 512;
+	}
+
+	hba->caps |= UFSHCD_CAP_CRYPTO;
+	hba->quirks |= UFSHCD_QUIRK_CUSTOM_CRYPTO_PROFILE;
 	return 0;
 }
 
@@ -149,34 +186,49 @@ static inline int ufs_qcom_ice_suspend(struct ufs_qcom_host *host)
 	return 0;
 }
 
-static int ufs_qcom_ice_program_key(struct ufs_hba *hba,
-				    const union ufs_crypto_cfg_entry *cfg,
-				    int slot)
+static int ufs_qcom_ice_keyslot_program(struct blk_crypto_profile *profile,
+					const struct blk_crypto_key *key,
+					unsigned int slot)
 {
+	struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile);
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
-	union ufs_crypto_cap_entry cap;
-	bool config_enable =
-		cfg->config_enable & UFS_CRYPTO_CONFIGURATION_ENABLE;
+	int err;
 
 	/* Only AES-256-XTS has been tested so far. */
-	cap = hba->crypto_cap_array[cfg->crypto_cap_idx];
-	if (cap.algorithm_id != UFS_CRYPTO_ALG_AES_XTS ||
-	    cap.key_size != UFS_CRYPTO_KEY_SIZE_256)
+	if (key->crypto_cfg.crypto_mode != BLK_ENCRYPTION_MODE_AES_256_XTS)
 		return -EOPNOTSUPP;
 
-	if (config_enable)
-		return qcom_ice_program_key(host->ice,
-					    QCOM_ICE_CRYPTO_ALG_AES_XTS,
-					    QCOM_ICE_CRYPTO_KEY_SIZE_256,
-					    cfg->crypto_key,
-					    cfg->data_unit_size, slot);
-	else
-		return qcom_ice_evict_key(host->ice, slot);
+	ufshcd_hold(hba);
+	err = qcom_ice_program_key(host->ice,
+				   QCOM_ICE_CRYPTO_ALG_AES_XTS,
+				   QCOM_ICE_CRYPTO_KEY_SIZE_256,
+				   key->raw,
+				   key->crypto_cfg.data_unit_size / 512,
+				   slot);
+	ufshcd_release(hba);
+	return err;
 }
 
-#else
+static int ufs_qcom_ice_keyslot_evict(struct blk_crypto_profile *profile,
+				      const struct blk_crypto_key *key,
+				      unsigned int slot)
+{
+	struct ufs_hba *hba = ufs_hba_from_crypto_profile(profile);
+	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+	int err;
+
+	ufshcd_hold(hba);
+	err = qcom_ice_evict_key(host->ice, slot);
+	ufshcd_release(hba);
+	return err;
+}
 
-#define ufs_qcom_ice_program_key NULL
+static const struct blk_crypto_ll_ops ufs_qcom_crypto_ops = {
+	.keyslot_program	= ufs_qcom_ice_keyslot_program,
+	.keyslot_evict		= ufs_qcom_ice_keyslot_evict,
+};
+
+#else
 
 static inline void ufs_qcom_ice_enable(struct ufs_qcom_host *host)
 {
@@ -1826,7 +1878,6 @@ static const struct ufs_hba_variant_ops ufs_hba_qcom_vops = {
 	.dbg_register_dump	= ufs_qcom_dump_dbg_regs,
 	.device_reset		= ufs_qcom_device_reset,
 	.config_scaling_param = ufs_qcom_config_scaling_param,
-	.program_key		= ufs_qcom_ice_program_key,
 	.mcq_config_resource	= ufs_qcom_mcq_config_resource,
 	.get_hba_mac		= ufs_qcom_get_hba_mac,
 	.op_runtime_config	= ufs_qcom_op_runtime_config,
diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c
index ea39c5d5b8cf..9cfcaad23cf9 100644
--- a/drivers/ufs/host/ufshcd-pci.c
+++ b/drivers/ufs/host/ufshcd-pci.c
@@ -562,7 +562,6 @@ static void ufshcd_pci_remove(struct pci_dev *pdev)
 	pm_runtime_forbid(&pdev->dev);
 	pm_runtime_get_noresume(&pdev->dev);
 	ufshcd_remove(hba);
-	ufshcd_dealloc_host(hba);
 }
 
 /**
@@ -605,7 +604,6 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	err = ufshcd_init(hba, mmio_base, pdev->irq);
 	if (err) {
 		dev_err(&pdev->dev, "Initialization failed\n");
-		ufshcd_dealloc_host(hba);
 		return err;
 	}
 
diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c
index 505572d4fa87..ffe5d1d2b215 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.c
+++ b/drivers/ufs/host/ufshcd-pltfrm.c
@@ -465,21 +465,17 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 
 	mmio_base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(mmio_base)) {
-		err = PTR_ERR(mmio_base);
-		goto out;
-	}
+	if (IS_ERR(mmio_base))
+		return PTR_ERR(mmio_base);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		err = irq;
-		goto out;
-	}
+	if (irq < 0)
+		return irq;
 
 	err = ufshcd_alloc_host(dev, &hba);
 	if (err) {
 		dev_err(dev, "Allocation failed\n");
-		goto out;
+		return err;
 	}
 
 	hba->vops = vops;
@@ -488,13 +484,13 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 	if (err) {
 		dev_err(dev, "%s: clock parse failed %d\n",
 				__func__, err);
-		goto dealloc_host;
+		return err;
 	}
 	err = ufshcd_parse_regulator_info(hba);
 	if (err) {
 		dev_err(dev, "%s: regulator init failed %d\n",
 				__func__, err);
-		goto dealloc_host;
+		return err;
 	}
 
 	ufshcd_init_lanes_per_dir(hba);
@@ -502,25 +498,20 @@ int ufshcd_pltfrm_init(struct platform_device *pdev,
 	err = ufshcd_parse_operating_points(hba);
 	if (err) {
 		dev_err(dev, "%s: OPP parse failed %d\n", __func__, err);
-		goto dealloc_host;
+		return err;
 	}
 
 	err = ufshcd_init(hba, mmio_base, irq);
 	if (err) {
 		dev_err_probe(dev, err, "Initialization failed with error %d\n",
 			      err);
-		goto dealloc_host;
+		return err;
 	}
 
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
 	return 0;
-
-dealloc_host:
-	ufshcd_dealloc_host(hba);
-out:
-	return err;
 }
 EXPORT_SYMBOL_GPL(ufshcd_pltfrm_init);
 
@@ -534,7 +525,6 @@ void ufshcd_pltfrm_remove(struct platform_device *pdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 	ufshcd_remove(hba);
-	ufshcd_dealloc_host(hba);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
 }
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index 004a549c6c7d..d93ed4e86a17 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -565,7 +565,7 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait)
 
 	mutex_lock(&idev->info_lock);
 	if (!idev->info || !idev->info->irq)
-		ret = -EIO;
+		ret = EPOLLERR;
 	mutex_unlock(&idev->info_lock);
 
 	if (ret)
diff --git a/drivers/uio/uio_dmem_genirq.c b/drivers/uio/uio_dmem_genirq.c
index c70dd81bfc61..31aa75110ba5 100644
--- a/drivers/uio/uio_dmem_genirq.c
+++ b/drivers/uio/uio_dmem_genirq.c
@@ -167,6 +167,8 @@ static int uio_dmem_genirq_probe(struct platform_device *pdev)
 		}
 		uioinfo->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%pOFn",
 					       pdev->dev.of_node);
+		if (!uioinfo->name)
+			return -ENOMEM;
 		uioinfo->version = "devicetree";
 	}
 
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index 4a3f0f958256..97edf767ecee 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -15,6 +15,7 @@
 #include <linux/delay.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/pci.h>
 #include <linux/irq.h>
 #include <linux/dmi.h>
@@ -1671,12 +1672,12 @@ static int cdnsp_gadget_init_endpoints(struct cdnsp_device *pdev)
 			"CTRL: %s, INT: %s, BULK: %s, ISOC %s, "
 			"SupDir IN: %s, OUT: %s\n",
 			pep->name, 1024,
-			(pep->endpoint.caps.type_control) ? "yes" : "no",
-			(pep->endpoint.caps.type_int) ? "yes" : "no",
-			(pep->endpoint.caps.type_bulk) ? "yes" : "no",
-			(pep->endpoint.caps.type_iso) ? "yes" : "no",
-			(pep->endpoint.caps.dir_in) ? "yes" : "no",
-			(pep->endpoint.caps.dir_out) ? "yes" : "no");
+			str_yes_no(pep->endpoint.caps.type_control),
+			str_yes_no(pep->endpoint.caps.type_int),
+			str_yes_no(pep->endpoint.caps.type_bulk),
+			str_yes_no(pep->endpoint.caps.type_iso),
+			str_yes_no(pep->endpoint.caps.dir_in),
+			str_yes_no(pep->endpoint.caps.dir_out));
 
 		INIT_LIST_HEAD(&pep->pending_list);
 	}
diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c
index 465e9267b49c..98980a23e1c2 100644
--- a/drivers/usb/cdns3/core.c
+++ b/drivers/usb/cdns3/core.c
@@ -529,9 +529,7 @@ int cdns_resume(struct cdns *cdns)
 	int ret = 0;
 
 	if (cdns_power_is_lost(cdns)) {
-		if (cdns->role_sw) {
-			cdns->role = cdns_role_get(cdns->role_sw);
-		} else {
+		if (!cdns->role_sw) {
 			real_role = cdns_hw_role_state_machine(cdns);
 			if (real_role != cdns->role) {
 				ret = cdns_hw_role_switch(cdns);
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 0cce19208370..ced6076a8248 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -13,6 +13,7 @@
 #include <linux/usb/hcd.h>
 #include <linux/usb/chipidea.h>
 #include <linux/regulator/consumer.h>
+#include <linux/string_choices.h>
 #include <linux/pinctrl/consumer.h>
 
 #include "../host/ehci.h"
@@ -56,7 +57,7 @@ static int ehci_ci_portpower(struct usb_hcd *hcd, int portnum, bool enable)
 		if (ret) {
 			dev_err(dev,
 				"Failed to %s vbus regulator, ret=%d\n",
-				enable ? "enable" : "disable", ret);
+				str_enable_disable(enable), ret);
 			return ret;
 		}
 		priv->enabled = enable;
@@ -256,8 +257,14 @@ static int ci_ehci_hub_control(
 	struct device *dev = hcd->self.controller;
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
 
-	port_index = wIndex & 0xff;
-	port_index -= (port_index > 0);
+	/*
+	 * Avoid out-of-bounds values while calculating the port index
+	 * from wIndex. The compiler doesn't like pointers to invalid
+	 * addresses, even if they are never used.
+	 */
+	port_index = (wIndex - 1) & 0xff;
+	if (port_index >= HCS_N_PORTS_MAX)
+		port_index = 0;
 	status_reg = &ehci->regs->port_status[port_index];
 
 	spin_lock_irqsave(&ehci->lock, flags);
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index ff1a941fd2ed..e2527faa6592 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -87,7 +87,7 @@
 /* Get two-int array: [0]=vendor ID, [1]=product ID: */
 #define LPIOC_GET_VID_PID(len) _IOC(_IOC_READ, 'P', IOCNR_GET_VID_PID, len)
 /* Perform class specific soft reset */
-#define LPIOC_SOFT_RESET _IOC(_IOC_NONE, 'P', IOCNR_SOFT_RESET, 0);
+#define LPIOC_SOFT_RESET _IOC(_IOC_NONE, 'P', IOCNR_SOFT_RESET, 0)
 
 /*
  * A DEVICE_ID string may include the printer's serial number.
diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c
index 871cf199b6bf..fc0845f681be 100644
--- a/drivers/usb/common/common.c
+++ b/drivers/usb/common/common.c
@@ -41,6 +41,12 @@ const char *usb_ep_type_string(int ep_type)
 }
 EXPORT_SYMBOL_GPL(usb_ep_type_string);
 
+/**
+ * usb_otg_state_string() - returns human readable name of OTG state.
+ * @state: the OTG state to return the human readable name of. If it's not
+ *    any of the states defined in usb_otg_state enum, 'UNDEFINED' will be
+ *    returned.
+ */
 const char *usb_otg_state_string(enum usb_otg_state state)
 {
 	static const char *const names[] = {
@@ -179,6 +185,14 @@ static const char *const usb_dr_modes[] = {
 	[USB_DR_MODE_OTG]		= "otg",
 };
 
+/**
+ * usb_get_dr_mode_from_string() - Get dual role mode for given string
+ * @str: String to find the corresponding dual role mode for
+ *
+ * This function performs a lookup for the given string and returns the
+ * corresponding enum usb_dr_mode. If no match for the string could be found,
+ * 'USB_DR_MODE_UNKNOWN' is returned.
+ */
 static enum usb_dr_mode usb_get_dr_mode_from_string(const char *str)
 {
 	int ret;
diff --git a/drivers/usb/common/usb-conn-gpio.c b/drivers/usb/common/usb-conn-gpio.c
index c84b4a700084..aa710b50791b 100644
--- a/drivers/usb/common/usb-conn-gpio.c
+++ b/drivers/usb/common/usb-conn-gpio.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/regulator/consumer.h>
+#include <linux/string_choices.h>
 #include <linux/usb/role.h>
 
 #define USB_GPIO_DEB_MS		20	/* ms */
@@ -111,7 +112,7 @@ static void usb_conn_detect_cable(struct work_struct *work)
 
 	if (info->vbus)
 		dev_dbg(info->dev, "vbus regulator is %s\n",
-			regulator_is_enabled(info->vbus) ? "enabled" : "disabled");
+			str_enabled_disabled(regulator_is_enabled(info->vbus)));
 
 	power_supply_changed(info->charger);
 }
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 25a00f974934..f7bf8d1de3ad 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -9,6 +9,7 @@
 #include <linux/usb/quirks.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/device.h>
 #include <asm/byteorder.h>
 #include "usb.h"
@@ -18,12 +19,6 @@
 
 #define USB_MAXCONFIG			8	/* Arbitrary limit */
 
-
-static inline const char *plural(int n)
-{
-	return (n == 1 ? "" : "s");
-}
-
 static int find_next_descriptor(unsigned char *buffer, int size,
     int dt1, int dt2, int *num_skipped)
 {
@@ -484,7 +479,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno,
 	retval = buffer - buffer0 + i;
 	if (n > 0)
 		dev_dbg(ddev, "skipped %d descriptor%s after %s\n",
-		    n, plural(n), "endpoint");
+		    n, str_plural(n), "endpoint");
 	return retval;
 
 skip_to_next_endpoint_or_interface_descriptor:
@@ -563,7 +558,7 @@ static int usb_parse_interface(struct device *ddev, int cfgno,
 	alt->extralen = i;
 	if (n > 0)
 		dev_dbg(ddev, "skipped %d descriptor%s after %s\n",
-		    n, plural(n), "interface");
+		    n, str_plural(n), "interface");
 	buffer += i;
 	size -= i;
 
@@ -605,7 +600,7 @@ static int usb_parse_interface(struct device *ddev, int cfgno,
 		dev_notice(ddev, "config %d interface %d altsetting %d has %d "
 		    "endpoint descriptor%s, different from the interface "
 		    "descriptor's value: %d\n",
-		    cfgno, inum, asnum, n, plural(n), num_ep_orig);
+		    cfgno, inum, asnum, n, str_plural(n), num_ep_orig);
 	return buffer - buffer0;
 
 skip_to_next_interface_descriptor:
@@ -664,7 +659,7 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx,
 		if (size2 < sizeof(struct usb_descriptor_header)) {
 			dev_notice(ddev, "config %d descriptor has %d excess "
 			    "byte%s, ignoring\n",
-			    cfgno, size2, plural(size2));
+			    cfgno, size2, str_plural(size2));
 			break;
 		}
 
@@ -754,7 +749,7 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx,
 	if (n != nintf)
 		dev_notice(ddev, "config %d has %d interface%s, different from "
 		    "the descriptor's value: %d\n",
-		    cfgno, n, plural(n), nintf_orig);
+		    cfgno, n, str_plural(n), nintf_orig);
 	else if (n == 0)
 		dev_notice(ddev, "config %d has no interfaces?\n", cfgno);
 	config->desc.bNumInterfaces = nintf = n;
@@ -798,7 +793,7 @@ static int usb_parse_configuration(struct usb_device *dev, int cfgidx,
 	config->extralen = i;
 	if (n > 0)
 		dev_dbg(ddev, "skipped %d descriptor%s after %s\n",
-		    n, plural(n), "configuration");
+		    n, str_plural(n), "configuration");
 	buffer += i;
 	size -= i;
 
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index f203fdbfb6f6..460d4dde5994 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -1086,15 +1086,14 @@ int usb_register_driver(struct usb_driver *new_driver, struct module *owner,
 	pr_info("%s: registered new interface driver %s\n",
 			usbcore_name, new_driver->name);
 
-out:
-	return retval;
+	return 0;
 
 out_newid:
 	driver_unregister(&new_driver->driver);
-
+out:
 	pr_err("%s: error %d registering interface driver %s\n",
 		usbcore_name, retval, new_driver->name);
-	goto out;
+	return retval;
 }
 EXPORT_SYMBOL_GPL(usb_register_driver);
 
diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index b134bff5c3fe..9c6ae5e1198b 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -21,14 +21,10 @@
 
 #include <linux/usb.h>
 #include <linux/usb/hcd.h>
+#include <linux/string_choices.h>
 #include <uapi/linux/usb/audio.h>
 #include "usb.h"
 
-static inline const char *plural(int n)
-{
-	return (n == 1 ? "" : "s");
-}
-
 static int is_rndis(struct usb_interface_descriptor *desc)
 {
 	return desc->bInterfaceClass == USB_CLASS_COMM
@@ -194,18 +190,18 @@ int usb_choose_configuration(struct usb_device *udev)
 	if (insufficient_power > 0)
 		dev_info(&udev->dev, "rejected %d configuration%s "
 			"due to insufficient available bus power\n",
-			insufficient_power, plural(insufficient_power));
+			insufficient_power, str_plural(insufficient_power));
 
 	if (best) {
 		i = best->desc.bConfigurationValue;
 		dev_dbg(&udev->dev,
 			"configuration #%d chosen from %d choice%s\n",
-			i, num_configs, plural(num_configs));
+			i, num_configs, str_plural(num_configs));
 	} else {
 		i = -1;
 		dev_warn(&udev->dev,
 			"no configuration chosen from %d choice%s\n",
-			num_configs, plural(num_configs));
+			num_configs, str_plural(num_configs));
 	}
 	return i;
 }
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index a08f3f228e6d..56b534f59907 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -422,7 +422,12 @@ static int suspend_common(struct device *dev, pm_message_t msg)
 	bool			do_wakeup;
 	int			retval;
 
-	do_wakeup = PMSG_IS_AUTO(msg) ? true : device_may_wakeup(dev);
+	if (PMSG_IS_AUTO(msg))
+		do_wakeup = true;
+	else if (PMSG_NO_WAKEUP(msg))
+		do_wakeup = false;
+	else
+		do_wakeup = device_may_wakeup(dev);
 
 	/* Root hub suspend should have stopped all downstream traffic,
 	 * and all bus master traffic.  And done so for both the interface
@@ -521,6 +526,11 @@ static int hcd_pci_suspend(struct device *dev)
 	return suspend_common(dev, PMSG_SUSPEND);
 }
 
+static int hcd_pci_freeze(struct device *dev)
+{
+	return suspend_common(dev, PMSG_FREEZE);
+}
+
 static int hcd_pci_suspend_noirq(struct device *dev)
 {
 	struct pci_dev		*pci_dev = to_pci_dev(dev);
@@ -590,6 +600,7 @@ static int hcd_pci_restore(struct device *dev)
 #else
 
 #define hcd_pci_suspend		NULL
+#define hcd_pci_freeze			NULL
 #define hcd_pci_suspend_noirq	NULL
 #define hcd_pci_poweroff_late	NULL
 #define hcd_pci_resume_noirq	NULL
@@ -624,7 +635,7 @@ const struct dev_pm_ops usb_hcd_pci_pm_ops = {
 	.suspend_noirq	= hcd_pci_suspend_noirq,
 	.resume_noirq	= hcd_pci_resume_noirq,
 	.resume		= hcd_pci_resume,
-	.freeze		= hcd_pci_suspend,
+	.freeze		= hcd_pci_freeze,
 	.freeze_noirq	= check_root_hub_suspended,
 	.thaw_noirq	= NULL,
 	.thaw		= hcd_pci_resume,
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 0b2490347b9f..a75cf1f6d741 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -415,7 +415,7 @@ ascii2desc(char const *s, u8 *buf, unsigned len)
 static unsigned
 rh_string(int id, struct usb_hcd const *hcd, u8 *data, unsigned len)
 {
-	char buf[100];
+	char buf[160];
 	char const *s;
 	static char const langids[4] = {4, USB_DT_STRING, 0x09, 0x04};
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 21ac9b464696..c3f839637cb5 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -18,6 +18,7 @@
 #include <linux/sched/mm.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/kcov.h>
 #include <linux/ioctl.h>
 #include <linux/usb.h>
@@ -1496,7 +1497,7 @@ static int hub_configure(struct usb_hub *hub,
 
 	maxchild = hub->descriptor->bNbrPorts;
 	dev_info(hub_dev, "%d port%s detected\n", maxchild,
-			(maxchild == 1) ? "" : "s");
+			str_plural(maxchild));
 
 	hub->ports = kcalloc(maxchild, sizeof(struct usb_port *), GFP_KERNEL);
 	if (!hub->ports) {
@@ -4139,14 +4140,14 @@ static int usb_set_device_initiated_lpm(struct usb_device *udev,
 		break;
 	default:
 		dev_warn(&udev->dev, "%s: Can't %s non-U1 or U2 state.\n",
-				__func__, enable ? "enable" : "disable");
+				__func__, str_enable_disable(enable));
 		return -EINVAL;
 	}
 
 	if (udev->state != USB_STATE_CONFIGURED) {
 		dev_dbg(&udev->dev, "%s: Can't %s %s state "
 				"for unconfigured device.\n",
-				__func__, enable ? "enable" : "disable",
+				__func__, str_enable_disable(enable),
 				usb3_lpm_names[state]);
 		return 0;
 	}
@@ -4172,8 +4173,7 @@ static int usb_set_device_initiated_lpm(struct usb_device *udev,
 	}
 	if (ret < 0) {
 		dev_warn(&udev->dev, "%s of device-initiated %s failed.\n",
-				enable ? "Enable" : "Disable",
-				usb3_lpm_names[state]);
+			 str_enable_disable(enable), usb3_lpm_names[state]);
 		return -EBUSY;
 	}
 	return 0;
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index e857e532b35a..f54198171b6a 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -9,6 +9,7 @@
 
 #include <linux/kstrtox.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/sysfs.h>
 #include <linux/pm_qos.h>
 #include <linux/component.h>
@@ -25,7 +26,7 @@ static ssize_t early_stop_show(struct device *dev,
 {
 	struct usb_port *port_dev = to_usb_port(dev);
 
-	return sysfs_emit(buf, "%s\n", port_dev->early_stop ? "yes" : "no");
+	return sysfs_emit(buf, "%s\n", str_yes_no(port_dev->early_stop));
 }
 
 static ssize_t early_stop_store(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 13171454f959..67732c791c93 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -394,6 +394,9 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Kingston DataTraveler 3.0 */
 	{ USB_DEVICE(0x0951, 0x1666), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* TOSHIBA TransMemory-Mx */
+	{ USB_DEVICE(0x0930, 0x1408), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* NVIDIA Jetson devices in Force Recovery mode */
 	{ USB_DEVICE(0x0955, 0x7018), .driver_info = USB_QUIRK_RESET_RESUME },
 	{ USB_DEVICE(0x0955, 0x7019), .driver_info = USB_QUIRK_RESET_RESUME },
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index b4cba23831ac..23f3cb1989f4 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -854,7 +854,7 @@ static const struct attribute_group dev_string_attr_grp = {
 
 static ssize_t
 descriptors_read(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
+		const struct bin_attribute *attr,
 		char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -890,11 +890,11 @@ descriptors_read(struct file *filp, struct kobject *kobj,
 	}
 	return count - nleft;
 }
-static BIN_ATTR_RO(descriptors, 18 + 65535); /* dev descr + max-size raw descriptor */
+static const BIN_ATTR_RO(descriptors, 18 + 65535); /* dev descr + max-size raw descriptor */
 
 static ssize_t
 bos_descriptors_read(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr,
+		const struct bin_attribute *attr,
 		char *buf, loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -913,12 +913,12 @@ bos_descriptors_read(struct file *filp, struct kobject *kobj,
 	}
 	return n;
 }
-static BIN_ATTR_RO(bos_descriptors, 65535); /* max-size BOS */
+static const BIN_ATTR_RO(bos_descriptors, 65535); /* max-size BOS */
 
 /* When modifying this list, be sure to modify dev_bin_attrs_are_visible()
  * accordingly.
  */
-static struct bin_attribute *dev_bin_attrs[] = {
+static const struct bin_attribute *const dev_bin_attrs[] = {
 	&bin_attr_descriptors,
 	&bin_attr_bos_descriptors,
 	NULL
@@ -944,7 +944,7 @@ static umode_t dev_bin_attrs_are_visible(struct kobject *kobj,
 }
 
 static const struct attribute_group dev_bin_attr_grp = {
-	.bin_attrs =		dev_bin_attrs,
+	.bin_attrs_new =	dev_bin_attrs,
 	.is_bin_visible =	dev_bin_attrs_are_visible,
 };
 
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index f219c82e9619..dfa1b5fe48dc 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1479,6 +1479,26 @@ static int dwc3_core_init(struct dwc3 *dwc)
 		}
 	}
 
+	/*
+	 * STAR 9001346572: This issue affects DWC_usb31 versions 1.80a and
+	 * prior. When an active endpoint not currently cached in the host
+	 * controller is chosen to be cached to the same index as an endpoint
+	 * receiving NAKs, the endpoint receiving NAKs enters continuous
+	 * retry mode. This prevents it from being evicted from the host
+	 * controller cache, blocking the new endpoint from being cached and
+	 * serviced.
+	 *
+	 * To resolve this, for controller versions 1.70a and 1.80a, set the
+	 * GUCTL3 bit[16] (USB2.0 Internal Retry Disable) to 1. This bit
+	 * disables the USB2.0 internal retry feature. The GUCTL3[16] register
+	 * function is available only from version 1.70a.
+	 */
+	if (DWC3_VER_IS_WITHIN(DWC31, 170A, 180A)) {
+		reg = dwc3_readl(dwc->regs, DWC3_GUCTL3);
+		reg |= DWC3_GUCTL3_USB20_RETRY_DISABLE;
+		dwc3_writel(dwc->regs, DWC3_GUCTL3, reg);
+	}
+
 	return 0;
 
 err_power_off_phy:
@@ -1664,8 +1684,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 	u8			tx_thr_num_pkt_prd = 0;
 	u8			tx_max_burst_prd = 0;
 	u8			tx_fifo_resize_max_num;
-	const char		*usb_psy_name;
-	int			ret;
 
 	/* default to highest possible threshold */
 	lpm_nyet_threshold = 0xf;
@@ -1700,13 +1718,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 
 	dwc->sys_wakeup = device_may_wakeup(dwc->sysdev);
 
-	ret = device_property_read_string(dev, "usb-psy-name", &usb_psy_name);
-	if (ret >= 0) {
-		dwc->usb_psy = power_supply_get_by_name(usb_psy_name);
-		if (!dwc->usb_psy)
-			dev_err(dev, "couldn't get usb power supply\n");
-	}
-
 	dwc->has_lpm_erratum = device_property_read_bool(dev,
 				"snps,has-lpm-erratum");
 	device_property_read_u8(dev, "snps,lpm-nyet-threshold",
@@ -2109,6 +2120,23 @@ static int dwc3_get_num_ports(struct dwc3 *dwc)
 	return 0;
 }
 
+static struct power_supply *dwc3_get_usb_power_supply(struct dwc3 *dwc)
+{
+	struct power_supply *usb_psy;
+	const char *usb_psy_name;
+	int ret;
+
+	ret = device_property_read_string(dwc->dev, "usb-psy-name", &usb_psy_name);
+	if (ret < 0)
+		return NULL;
+
+	usb_psy = power_supply_get_by_name(usb_psy_name);
+	if (!usb_psy)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	return usb_psy;
+}
+
 static int dwc3_probe(struct platform_device *pdev)
 {
 	struct device		*dev = &pdev->dev;
@@ -2165,6 +2193,10 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	dwc3_get_software_properties(dwc);
 
+	dwc->usb_psy = dwc3_get_usb_power_supply(dwc);
+	if (IS_ERR(dwc->usb_psy))
+		return dev_err_probe(dev, PTR_ERR(dwc->usb_psy), "couldn't get usb power supply\n");
+
 	dwc->reset = devm_reset_control_array_get_optional_shared(dev);
 	if (IS_ERR(dwc->reset)) {
 		ret = PTR_ERR(dwc->reset);
@@ -2589,12 +2621,15 @@ static int dwc3_resume(struct device *dev)
 	pinctrl_pm_select_default_state(dev);
 
 	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
+	ret = pm_runtime_set_active(dev);
+	if (ret)
+		goto out;
 
 	ret = dwc3_resume_common(dwc, PMSG_RESUME);
 	if (ret)
 		pm_runtime_set_suspended(dev);
 
+out:
 	pm_runtime_enable(dev);
 
 	return ret;
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index f11570c8ffd0..ac7c730f81ac 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -425,6 +425,7 @@
 
 /* Global User Control Register 3 */
 #define DWC3_GUCTL3_SPLITDISABLE		BIT(14)
+#define DWC3_GUCTL3_USB20_RETRY_DISABLE		BIT(16)
 
 /* Device Configuration Register */
 #define DWC3_DCFG_NUMLANES(n)	(((n) & 0x3) << 30) /* DWC_usb32 only */
@@ -742,6 +743,7 @@ struct dwc3_event_buffer {
  */
 struct dwc3_ep {
 	struct usb_ep		endpoint;
+	struct delayed_work	nostream_work;
 	struct list_head	cancelled_list;
 	struct list_head	pending_list;
 	struct list_head	started_list;
@@ -764,7 +766,7 @@ struct dwc3_ep {
 #define DWC3_EP_WAIT_TRANSFER_COMPLETE	BIT(7)
 #define DWC3_EP_IGNORE_NEXT_NOSTREAM	BIT(8)
 #define DWC3_EP_FORCE_RESTART_STREAM	BIT(9)
-#define DWC3_EP_FIRST_STREAM_PRIMED	BIT(10)
+#define DWC3_EP_STREAM_PRIMED		BIT(10)
 #define DWC3_EP_PENDING_CLEAR_STALL	BIT(11)
 #define DWC3_EP_TXFIFO_RESIZED		BIT(12)
 #define DWC3_EP_DELAY_STOP             BIT(13)
@@ -957,7 +959,6 @@ struct dwc3_request {
 	struct usb_request	request;
 	struct list_head	list;
 	struct dwc3_ep		*dep;
-	struct scatterlist	*sg;
 	struct scatterlist	*start_sg;
 
 	unsigned int		num_pending_sgs;
diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c
index 7d43da5f2897..c158364bc03e 100644
--- a/drivers/usb/dwc3/dwc3-am62.c
+++ b/drivers/usb/dwc3/dwc3-am62.c
@@ -108,6 +108,9 @@
 
 #define DWC3_AM62_AUTOSUSPEND_DELAY	100
 
+#define USBSS_DEBUG_CFG_OFF		0x0
+#define USBSS_DEBUG_CFG_DISABLED	0x7
+
 struct dwc3_am62 {
 	struct device *dev;
 	void __iomem *usbss;
@@ -117,6 +120,7 @@ struct dwc3_am62 {
 	unsigned int offset;
 	unsigned int vbus_divider;
 	u32 wakeup_stat;
+	void __iomem *phy_regs;
 };
 
 static const int dwc3_ti_rate_table[] = {	/* in KHZ */
@@ -166,6 +170,7 @@ static int phy_syscon_pll_refclk(struct dwc3_am62 *am62)
 	if (ret)
 		return ret;
 
+	of_node_put(args.np);
 	am62->offset = args.args[0];
 
 	/* Core voltage. PHY_CORE_VOLTAGE bit Recommended to be 0 always */
@@ -184,15 +189,47 @@ static int phy_syscon_pll_refclk(struct dwc3_am62 *am62)
 	return 0;
 }
 
+static int dwc3_ti_init(struct dwc3_am62 *am62)
+{
+	int ret;
+	u32 reg;
+
+	/* Read the syscon property and set the rate code */
+	ret = phy_syscon_pll_refclk(am62);
+	if (ret)
+		return ret;
+
+	/* Workaround Errata i2409 */
+	if (am62->phy_regs) {
+		reg = readl(am62->phy_regs + USB_PHY_PLL_REG12);
+		reg |= USB_PHY_PLL_LDO_REF_EN | USB_PHY_PLL_LDO_REF_EN_EN;
+		writel(reg, am62->phy_regs + USB_PHY_PLL_REG12);
+	}
+
+	/* VBUS divider select */
+	reg = dwc3_ti_readl(am62, USBSS_PHY_CONFIG);
+	if (am62->vbus_divider)
+		reg |= 1 << USBSS_PHY_VBUS_SEL_SHIFT;
+
+	dwc3_ti_writel(am62, USBSS_PHY_CONFIG, reg);
+
+	clk_prepare_enable(am62->usb2_refclk);
+
+	/* Set mode valid bit to indicate role is valid */
+	reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL);
+	reg |= USBSS_MODE_VALID;
+	dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg);
+
+	return 0;
+}
+
 static int dwc3_ti_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *node = pdev->dev.of_node;
 	struct dwc3_am62 *am62;
 	unsigned long rate;
-	void __iomem *phy;
 	int i, ret;
-	u32 reg;
 
 	am62 = devm_kzalloc(dev, sizeof(*am62), GFP_KERNEL);
 	if (!am62)
@@ -228,29 +265,17 @@ static int dwc3_ti_probe(struct platform_device *pdev)
 
 	am62->rate_code = i;
 
-	/* Read the syscon property and set the rate code */
-	ret = phy_syscon_pll_refclk(am62);
-	if (ret)
-		return ret;
-
-	/* Workaround Errata i2409 */
-	phy = devm_platform_ioremap_resource(pdev, 1);
-	if (IS_ERR(phy)) {
+	am62->phy_regs = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(am62->phy_regs)) {
 		dev_err(dev, "can't map PHY IOMEM resource. Won't apply i2409 fix.\n");
-		phy = NULL;
-	} else {
-		reg = readl(phy + USB_PHY_PLL_REG12);
-		reg |= USB_PHY_PLL_LDO_REF_EN | USB_PHY_PLL_LDO_REF_EN_EN;
-		writel(reg, phy + USB_PHY_PLL_REG12);
+		am62->phy_regs = NULL;
 	}
 
-	/* VBUS divider select */
 	am62->vbus_divider = device_property_read_bool(dev, "ti,vbus-divider");
-	reg = dwc3_ti_readl(am62, USBSS_PHY_CONFIG);
-	if (am62->vbus_divider)
-		reg |= 1 << USBSS_PHY_VBUS_SEL_SHIFT;
 
-	dwc3_ti_writel(am62, USBSS_PHY_CONFIG, reg);
+	ret = dwc3_ti_init(am62);
+	if (ret)
+		return ret;
 
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
@@ -258,7 +283,6 @@ static int dwc3_ti_probe(struct platform_device *pdev)
 	 * Don't ignore its dependencies with its children
 	 */
 	pm_suspend_ignore_children(dev, false);
-	clk_prepare_enable(am62->usb2_refclk);
 	pm_runtime_get_noresume(dev);
 
 	ret = of_platform_populate(node, NULL, NULL, dev);
@@ -267,11 +291,6 @@ static int dwc3_ti_probe(struct platform_device *pdev)
 		goto err_pm_disable;
 	}
 
-	/* Set mode valid bit to indicate role is valid */
-	reg = dwc3_ti_readl(am62, USBSS_MODE_CONTROL);
-	reg |= USBSS_MODE_VALID;
-	dwc3_ti_writel(am62, USBSS_MODE_CONTROL, reg);
-
 	/* Device has capability to wakeup system from sleep */
 	device_set_wakeup_capable(dev, true);
 	ret = device_wakeup_enable(dev);
@@ -339,6 +358,9 @@ static int dwc3_ti_suspend_common(struct device *dev)
 		dwc3_ti_writel(am62, USBSS_WAKEUP_STAT, USBSS_WAKEUP_STAT_CLR);
 	}
 
+	/* just to track if module resets on suspend */
+	dwc3_ti_writel(am62, USBSS_DEBUG_CFG, USBSS_DEBUG_CFG_DISABLED);
+
 	clk_disable_unprepare(am62->usb2_refclk);
 
 	return 0;
@@ -349,7 +371,14 @@ static int dwc3_ti_resume_common(struct device *dev)
 	struct dwc3_am62 *am62 = dev_get_drvdata(dev);
 	u32 reg;
 
-	clk_prepare_enable(am62->usb2_refclk);
+	reg = dwc3_ti_readl(am62, USBSS_DEBUG_CFG);
+	if (reg != USBSS_DEBUG_CFG_DISABLED) {
+		/* lost power/context */
+		dwc3_ti_init(am62);
+	} else {
+		dwc3_ti_writel(am62, USBSS_DEBUG_CFG, USBSS_DEBUG_CFG_OFF);
+		clk_prepare_enable(am62->usb2_refclk);
+	}
 
 	if (device_may_wakeup(dev)) {
 		/* Clear wakeup config enable bits */
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index b261c46124c6..fe74d11bb629 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -457,7 +457,7 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 
 	struct dwc3_omap	*omap;
 	struct device		*dev = &pdev->dev;
-	struct regulator	*vbus_reg = NULL;
+	struct regulator	*vbus_reg;
 
 	int			ret;
 	int			irq;
@@ -483,12 +483,11 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	if (of_property_read_bool(node, "vbus-supply")) {
-		vbus_reg = devm_regulator_get(dev, "vbus");
-		if (IS_ERR(vbus_reg)) {
-			dev_err(dev, "vbus init failed\n");
-			return PTR_ERR(vbus_reg);
-		}
+	vbus_reg = devm_regulator_get_optional(dev, "vbus");
+	if (IS_ERR(vbus_reg)) {
+		if (PTR_ERR(vbus_reg) != -ENODEV)
+			return dev_err_probe(dev, PTR_ERR(vbus_reg), "vbus init failed\n");
+		vbus_reg = NULL;
 	}
 
 	omap->dev	= dev;
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index e16c3237180e..ef7c43008946 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -309,7 +309,6 @@ static void st_dwc3_remove(struct platform_device *pdev)
 	reset_control_assert(dwc3_data->rstc_rst);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int st_dwc3_suspend(struct device *dev)
 {
 	struct st_dwc3 *dwc3_data = dev_get_drvdata(dev);
@@ -343,9 +342,8 @@ static int st_dwc3_resume(struct device *dev)
 
 	return 0;
 }
-#endif /* CONFIG_PM_SLEEP */
 
-static SIMPLE_DEV_PM_OPS(st_dwc3_dev_pm_ops, st_dwc3_suspend, st_dwc3_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(st_dwc3_dev_pm_ops, st_dwc3_suspend, st_dwc3_resume);
 
 static const struct of_device_id st_dwc3_match[] = {
 	{ .compatible = "st,stih407-dwc3" },
@@ -360,7 +358,7 @@ static struct platform_driver st_dwc3_driver = {
 	.driver = {
 		.name = "usb-st-dwc3",
 		.of_match_table = st_dwc3_match,
-		.pm = &st_dwc3_dev_pm_ops,
+		.pm = pm_sleep_ptr(&st_dwc3_dev_pm_ops),
 	},
 };
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 31a654c6f15b..d27af65eb08a 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -996,8 +996,7 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, unsigned int action)
 
 			/*
 			 * All stream eps will reinitiate stream on NoStream
-			 * rejection until we can determine that the host can
-			 * prime after the first transfer.
+			 * rejection.
 			 *
 			 * However, if the controller is capable of
 			 * TXF_FLUSH_BYPASS, then IN direction endpoints will
@@ -2740,6 +2739,8 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc)
 	__dwc3_gadget_stop(dwc);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
+	usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED);
+
 	return ret;
 }
 
@@ -3298,6 +3299,50 @@ static int dwc3_gadget_init_out_endpoint(struct dwc3_ep *dep)
 	return dwc3_alloc_trb_pool(dep);
 }
 
+#define nostream_work_to_dep(w) (container_of(to_delayed_work(w), struct dwc3_ep, nostream_work))
+static void dwc3_nostream_work(struct work_struct *work)
+{
+	struct dwc3_ep	*dep = nostream_work_to_dep(work);
+	struct dwc3	*dwc = dep->dwc;
+	unsigned long   flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	if (dep->flags & DWC3_EP_STREAM_PRIMED)
+		goto out;
+
+	if ((dep->flags & DWC3_EP_IGNORE_NEXT_NOSTREAM) ||
+	    (!DWC3_MST_CAPABLE(&dwc->hwparams) &&
+	     !(dep->flags & DWC3_EP_WAIT_TRANSFER_COMPLETE)))
+		goto out;
+	/*
+	 * If the host rejects a stream due to no active stream, by the
+	 * USB and xHCI spec, the endpoint will be put back to idle
+	 * state. When the host is ready (buffer added/updated), it will
+	 * prime the endpoint to inform the usb device controller. This
+	 * triggers the device controller to issue ERDY to restart the
+	 * stream. However, some hosts don't follow this and keep the
+	 * endpoint in the idle state. No prime will come despite host
+	 * streams are updated, and the device controller will not be
+	 * triggered to generate ERDY to move the next stream data. To
+	 * workaround this and maintain compatibility with various
+	 * hosts, force to reinitiate the stream until the host is ready
+	 * instead of waiting for the host to prime the endpoint.
+	 */
+	if (DWC3_VER_IS_WITHIN(DWC32, 100A, ANY)) {
+		unsigned int cmd = DWC3_DGCMD_SET_ENDPOINT_PRIME;
+
+		dwc3_send_gadget_generic_command(dwc, cmd, dep->number);
+	} else {
+		dep->flags |= DWC3_EP_DELAY_START;
+		dwc3_stop_active_transfer(dep, true, true);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		return;
+	}
+out:
+	dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM;
+	spin_unlock_irqrestore(&dwc->lock, flags);
+}
+
 static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum)
 {
 	struct dwc3_ep			*dep;
@@ -3343,6 +3388,7 @@ static int dwc3_gadget_init_endpoint(struct dwc3 *dwc, u8 epnum)
 	INIT_LIST_HEAD(&dep->pending_list);
 	INIT_LIST_HEAD(&dep->started_list);
 	INIT_LIST_HEAD(&dep->cancelled_list);
+	INIT_DELAYED_WORK(&dep->nostream_work, dwc3_nostream_work);
 
 	dwc3_debugfs_create_endpoint_dir(dep);
 
@@ -3742,66 +3788,27 @@ static void dwc3_gadget_endpoint_command_complete(struct dwc3_ep *dep,
 static void dwc3_gadget_endpoint_stream_event(struct dwc3_ep *dep,
 		const struct dwc3_event_depevt *event)
 {
-	struct dwc3 *dwc = dep->dwc;
-
 	if (event->status == DEPEVT_STREAMEVT_FOUND) {
-		dep->flags |= DWC3_EP_FIRST_STREAM_PRIMED;
-		goto out;
+		cancel_delayed_work(&dep->nostream_work);
+		dep->flags |= DWC3_EP_STREAM_PRIMED;
+		dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM;
+		return;
 	}
 
 	/* Note: NoStream rejection event param value is 0 and not 0xFFFF */
 	switch (event->parameters) {
 	case DEPEVT_STREAM_PRIME:
-		/*
-		 * If the host can properly transition the endpoint state from
-		 * idle to prime after a NoStream rejection, there's no need to
-		 * force restarting the endpoint to reinitiate the stream. To
-		 * simplify the check, assume the host follows the USB spec if
-		 * it primed the endpoint more than once.
-		 */
-		if (dep->flags & DWC3_EP_FORCE_RESTART_STREAM) {
-			if (dep->flags & DWC3_EP_FIRST_STREAM_PRIMED)
-				dep->flags &= ~DWC3_EP_FORCE_RESTART_STREAM;
-			else
-				dep->flags |= DWC3_EP_FIRST_STREAM_PRIMED;
-		}
-
+		cancel_delayed_work(&dep->nostream_work);
+		dep->flags |= DWC3_EP_STREAM_PRIMED;
+		dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM;
 		break;
 	case DEPEVT_STREAM_NOSTREAM:
-		if ((dep->flags & DWC3_EP_IGNORE_NEXT_NOSTREAM) ||
-		    !(dep->flags & DWC3_EP_FORCE_RESTART_STREAM) ||
-		    (!DWC3_MST_CAPABLE(&dwc->hwparams) &&
-		     !(dep->flags & DWC3_EP_WAIT_TRANSFER_COMPLETE)))
-			break;
-
-		/*
-		 * If the host rejects a stream due to no active stream, by the
-		 * USB and xHCI spec, the endpoint will be put back to idle
-		 * state. When the host is ready (buffer added/updated), it will
-		 * prime the endpoint to inform the usb device controller. This
-		 * triggers the device controller to issue ERDY to restart the
-		 * stream. However, some hosts don't follow this and keep the
-		 * endpoint in the idle state. No prime will come despite host
-		 * streams are updated, and the device controller will not be
-		 * triggered to generate ERDY to move the next stream data. To
-		 * workaround this and maintain compatibility with various
-		 * hosts, force to reinitiate the stream until the host is ready
-		 * instead of waiting for the host to prime the endpoint.
-		 */
-		if (DWC3_VER_IS_WITHIN(DWC32, 100A, ANY)) {
-			unsigned int cmd = DWC3_DGCMD_SET_ENDPOINT_PRIME;
-
-			dwc3_send_gadget_generic_command(dwc, cmd, dep->number);
-		} else {
-			dep->flags |= DWC3_EP_DELAY_START;
-			dwc3_stop_active_transfer(dep, true, true);
-			return;
-		}
+		dep->flags &= ~DWC3_EP_STREAM_PRIMED;
+		if (dep->flags & DWC3_EP_FORCE_RESTART_STREAM)
+			queue_delayed_work(system_wq, &dep->nostream_work,
+					   msecs_to_jiffies(100));
 		break;
 	}
-
-out:
-	dep->flags &= ~DWC3_EP_IGNORE_NEXT_NOSTREAM;
 }
 
 static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
diff --git a/drivers/usb/fotg210/fotg210-core.c b/drivers/usb/fotg210/fotg210-core.c
index 49f25a70b32e..7fb4d4715e9f 100644
--- a/drivers/usb/fotg210/fotg210-core.c
+++ b/drivers/usb/fotg210/fotg210-core.c
@@ -13,6 +13,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
+#include <linux/string_choices.h>
 #include <linux/usb.h>
 #include <linux/usb/otg.h>
 
@@ -119,8 +120,8 @@ void fotg210_vbus(struct fotg210 *fotg, bool enable)
 	ret = regmap_update_bits(fotg->map, GEMINI_GLOBAL_MISC_CTRL, mask, val);
 	if (ret)
 		dev_err(fotg->dev, "failed to %s VBUS\n",
-			enable ? "enable" : "disable");
-	dev_info(fotg->dev, "%s: %s VBUS\n", __func__, enable ? "enable" : "disable");
+			str_enable_disable(enable));
+	dev_info(fotg->dev, "%s: %s VBUS\n", __func__, str_enable_disable(enable));
 }
 
 static int fotg210_probe(struct platform_device *pdev)
diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c
index 6cb7771e8a69..80841de845b0 100644
--- a/drivers/usb/gadget/function/f_ecm.c
+++ b/drivers/usb/gadget/function/f_ecm.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/etherdevice.h>
+#include <linux/string_choices.h>
 
 #include "u_ether.h"
 #include "u_ether_configfs.h"
@@ -387,8 +388,7 @@ static void ecm_do_notify(struct f_ecm *ecm)
 		event->wLength = 0;
 		req->length = sizeof *event;
 
-		DBG(cdev, "notify connect %s\n",
-				ecm->is_open ? "true" : "false");
+		DBG(cdev, "notify connect %s\n", str_true_false(ecm->is_open));
 		ecm->notify_state = ECM_NOTIFY_SPEED;
 		break;
 
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 8e761249d672..f60576a65ca6 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -17,6 +17,7 @@
 #include <linux/device.h>
 #include <linux/etherdevice.h>
 #include <linux/crc32.h>
+#include <linux/string_choices.h>
 
 #include <linux/usb/cdc.h>
 
@@ -558,7 +559,7 @@ static void ncm_do_notify(struct f_ncm *ncm)
 		req->length = sizeof *event;
 
 		DBG(cdev, "notify connect %s\n",
-				ncm->is_open ? "true" : "false");
+				str_true_false(ncm->is_open));
 		ncm->notify_state = NCM_NOTIFY_NONE;
 		break;
 
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 15bb3aa12aa8..5a2e1237f85c 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/configfs.h>
 #include <linux/ctype.h>
+#include <linux/delay.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/composite.h>
 #include <linux/usb/gadget.h>
@@ -50,7 +51,7 @@ static int bot_enqueue_cmd_cbw(struct f_uas *fu)
 	if (fu->flags & USBG_BOT_CMD_PEND)
 		return 0;
 
-	ret = usb_ep_queue(fu->ep_out, fu->cmd.req, GFP_ATOMIC);
+	ret = usb_ep_queue(fu->ep_out, fu->cmd[0].req, GFP_ATOMIC);
 	if (!ret)
 		fu->flags |= USBG_BOT_CMD_PEND;
 	return ret;
@@ -62,10 +63,11 @@ static void bot_status_complete(struct usb_ep *ep, struct usb_request *req)
 	struct f_uas *fu = cmd->fu;
 
 	transport_generic_free_cmd(&cmd->se_cmd, 0);
-	if (req->status < 0) {
-		pr_err("ERR %s(%d)\n", __func__, __LINE__);
+	if (req->status == -ESHUTDOWN)
 		return;
-	}
+
+	if (req->status < 0)
+		pr_err("ERR %s(%d)\n", __func__, __LINE__);
 
 	/* CSW completed, wait for next CBW */
 	bot_enqueue_cmd_cbw(fu);
@@ -136,7 +138,7 @@ static void bot_send_bad_status(struct usbg_cmd *cmd)
 		}
 		req->complete = bot_err_compl;
 		req->context = cmd;
-		req->buf = fu->cmd.buf;
+		req->buf = fu->cmd[0].buf;
 		usb_ep_queue(ep, req, GFP_KERNEL);
 	} else {
 		bot_enqueue_sense_code(fu, cmd);
@@ -196,6 +198,11 @@ static void bot_read_compl(struct usb_ep *ep, struct usb_request *req)
 	if (req->status < 0)
 		pr_err("ERR %s(%d)\n", __func__, __LINE__);
 
+	if (req->status == -ESHUTDOWN) {
+		transport_generic_free_cmd(&cmd->se_cmd, 0);
+		return;
+	}
+
 	bot_send_status(cmd, true);
 }
 
@@ -244,11 +251,8 @@ static int usbg_prepare_w_request(struct usbg_cmd *, struct usb_request *);
 static int bot_send_write_request(struct usbg_cmd *cmd)
 {
 	struct f_uas *fu = cmd->fu;
-	struct se_cmd *se_cmd = &cmd->se_cmd;
-	struct usb_gadget *gadget = fuas_to_gadget(fu);
 	int ret;
 
-	init_completion(&cmd->write_complete);
 	cmd->fu = fu;
 
 	if (!cmd->data_len) {
@@ -256,22 +260,6 @@ static int bot_send_write_request(struct usbg_cmd *cmd)
 		return -EINVAL;
 	}
 
-	if (!gadget->sg_supported) {
-		cmd->data_buf = kmalloc(se_cmd->data_length, GFP_KERNEL);
-		if (!cmd->data_buf)
-			return -ENOMEM;
-
-		fu->bot_req_out->buf = cmd->data_buf;
-	} else {
-		fu->bot_req_out->buf = NULL;
-		fu->bot_req_out->num_sgs = se_cmd->t_data_nents;
-		fu->bot_req_out->sg = se_cmd->t_data_sg;
-	}
-
-	fu->bot_req_out->complete = usbg_data_write_cmpl;
-	fu->bot_req_out->length = se_cmd->data_length;
-	fu->bot_req_out->context = cmd;
-
 	ret = usbg_prepare_w_request(cmd, fu->bot_req_out);
 	if (ret)
 		goto cleanup;
@@ -279,8 +267,6 @@ static int bot_send_write_request(struct usbg_cmd *cmd)
 	if (ret)
 		pr_err("%s(%d)\n", __func__, __LINE__);
 
-	wait_for_completion(&cmd->write_complete);
-	target_execute_cmd(se_cmd);
 cleanup:
 	return ret;
 }
@@ -292,14 +278,31 @@ static void bot_cmd_complete(struct usb_ep *ep, struct usb_request *req)
 	struct f_uas *fu = req->context;
 	int ret;
 
+	if (req->status == -ESHUTDOWN)
+		return;
+
 	fu->flags &= ~USBG_BOT_CMD_PEND;
 
-	if (req->status < 0)
+	if (req->status < 0) {
+		struct usb_gadget *gadget = fuas_to_gadget(fu);
+
+		dev_err(&gadget->dev, "BOT command req err (%d)\n", req->status);
+		bot_enqueue_cmd_cbw(fu);
 		return;
+	}
 
 	ret = bot_submit_command(fu, req->buf, req->actual);
-	if (ret)
+	if (ret) {
 		pr_err("%s(%d): %d\n", __func__, __LINE__, ret);
+		if (!(fu->flags & USBG_BOT_WEDGED))
+			usb_ep_set_wedge(fu->ep_in);
+
+		fu->flags |= USBG_BOT_WEDGED;
+		bot_enqueue_cmd_cbw(fu);
+	} else if (fu->flags & USBG_BOT_WEDGED) {
+		fu->flags &= ~USBG_BOT_WEDGED;
+		usb_ep_clear_halt(fu->ep_in);
+	}
 }
 
 static int bot_prepare_reqs(struct f_uas *fu)
@@ -314,8 +317,8 @@ static int bot_prepare_reqs(struct f_uas *fu)
 	if (!fu->bot_req_out)
 		goto err_out;
 
-	fu->cmd.req = usb_ep_alloc_request(fu->ep_out, GFP_KERNEL);
-	if (!fu->cmd.req)
+	fu->cmd[0].req = usb_ep_alloc_request(fu->ep_out, GFP_KERNEL);
+	if (!fu->cmd[0].req)
 		goto err_cmd;
 
 	fu->bot_status.req = usb_ep_alloc_request(fu->ep_in, GFP_KERNEL);
@@ -327,27 +330,27 @@ static int bot_prepare_reqs(struct f_uas *fu)
 	fu->bot_status.req->complete = bot_status_complete;
 	fu->bot_status.csw.Signature = cpu_to_le32(US_BULK_CS_SIGN);
 
-	fu->cmd.buf = kmalloc(fu->ep_out->maxpacket, GFP_KERNEL);
-	if (!fu->cmd.buf)
+	fu->cmd[0].buf = kmalloc(fu->ep_out->maxpacket, GFP_KERNEL);
+	if (!fu->cmd[0].buf)
 		goto err_buf;
 
-	fu->cmd.req->complete = bot_cmd_complete;
-	fu->cmd.req->buf = fu->cmd.buf;
-	fu->cmd.req->length = fu->ep_out->maxpacket;
-	fu->cmd.req->context = fu;
+	fu->cmd[0].req->complete = bot_cmd_complete;
+	fu->cmd[0].req->buf = fu->cmd[0].buf;
+	fu->cmd[0].req->length = fu->ep_out->maxpacket;
+	fu->cmd[0].req->context = fu;
 
 	ret = bot_enqueue_cmd_cbw(fu);
 	if (ret)
 		goto err_queue;
 	return 0;
 err_queue:
-	kfree(fu->cmd.buf);
-	fu->cmd.buf = NULL;
+	kfree(fu->cmd[0].buf);
+	fu->cmd[0].buf = NULL;
 err_buf:
 	usb_ep_free_request(fu->ep_in, fu->bot_status.req);
 err_sts:
-	usb_ep_free_request(fu->ep_out, fu->cmd.req);
-	fu->cmd.req = NULL;
+	usb_ep_free_request(fu->ep_out, fu->cmd[0].req);
+	fu->cmd[0].req = NULL;
 err_cmd:
 	usb_ep_free_request(fu->ep_out, fu->bot_req_out);
 	fu->bot_req_out = NULL;
@@ -372,16 +375,16 @@ static void bot_cleanup_old_alt(struct f_uas *fu)
 
 	usb_ep_free_request(fu->ep_in, fu->bot_req_in);
 	usb_ep_free_request(fu->ep_out, fu->bot_req_out);
-	usb_ep_free_request(fu->ep_out, fu->cmd.req);
+	usb_ep_free_request(fu->ep_out, fu->cmd[0].req);
 	usb_ep_free_request(fu->ep_in, fu->bot_status.req);
 
-	kfree(fu->cmd.buf);
+	kfree(fu->cmd[0].buf);
 
 	fu->bot_req_in = NULL;
 	fu->bot_req_out = NULL;
-	fu->cmd.req = NULL;
+	fu->cmd[0].req = NULL;
 	fu->bot_status.req = NULL;
-	fu->cmd.buf = NULL;
+	fu->cmd[0].buf = NULL;
 }
 
 static void bot_set_alt(struct f_uas *fu)
@@ -441,14 +444,10 @@ static int usbg_bot_setup(struct usb_function *f,
 			pr_err("No LUNs configured?\n");
 			return -EINVAL;
 		}
-		/*
-		 * If 4 LUNs are present we return 3 i.e. LUN 0..3 can be
-		 * accessed. The upper limit is 0xf
-		 */
 		luns--;
-		if (luns > 0xf) {
+		if (luns > US_BULK_MAX_LUN_LIMIT) {
 			pr_info_once("Limiting the number of luns to 16\n");
-			luns = 0xf;
+			luns = US_BULK_MAX_LUN_LIMIT;
 		}
 		ret_lun = cdev->req->buf;
 		*ret_lun = luns;
@@ -457,6 +456,11 @@ static int usbg_bot_setup(struct usb_function *f,
 
 	case US_BULK_RESET_REQUEST:
 		/* XXX maybe we should remove previous requests for IN + OUT */
+		if (fu->flags & USBG_BOT_WEDGED) {
+			fu->flags &= ~USBG_BOT_WEDGED;
+			usb_ep_clear_halt(fu->ep_in);
+		}
+
 		bot_enqueue_cmd_cbw(fu);
 		return 0;
 	}
@@ -465,6 +469,45 @@ static int usbg_bot_setup(struct usb_function *f,
 
 /* Start uas.c code */
 
+static int tcm_to_uasp_response(enum tcm_tmrsp_table code)
+{
+	switch (code) {
+	case TMR_FUNCTION_FAILED:
+		return RC_TMF_FAILED;
+	case TMR_FUNCTION_COMPLETE:
+	case TMR_TASK_DOES_NOT_EXIST:
+		return RC_TMF_COMPLETE;
+	case TMR_LUN_DOES_NOT_EXIST:
+		return RC_INCORRECT_LUN;
+	case TMR_FUNCTION_REJECTED:
+	case TMR_TASK_MGMT_FUNCTION_NOT_SUPPORTED:
+	default:
+		return RC_TMF_NOT_SUPPORTED;
+	}
+}
+
+static unsigned char uasp_to_tcm_func(int code)
+{
+	switch (code) {
+	case TMF_ABORT_TASK:
+		return TMR_ABORT_TASK;
+	case TMF_ABORT_TASK_SET:
+		return TMR_ABORT_TASK_SET;
+	case TMF_CLEAR_TASK_SET:
+		return TMR_CLEAR_TASK_SET;
+	case TMF_LOGICAL_UNIT_RESET:
+		return TMR_LUN_RESET;
+	case TMF_CLEAR_ACA:
+		return TMR_CLEAR_ACA;
+	case TMF_I_T_NEXUS_RESET:
+	case TMF_QUERY_TASK:
+	case TMF_QUERY_TASK_SET:
+	case TMF_QUERY_ASYNC_EVENT:
+	default:
+		return TMR_UNKNOWN;
+	}
+}
+
 static void uasp_cleanup_one_stream(struct f_uas *fu, struct uas_stream *stream)
 {
 	/* We have either all three allocated or none */
@@ -482,10 +525,14 @@ static void uasp_cleanup_one_stream(struct f_uas *fu, struct uas_stream *stream)
 
 static void uasp_free_cmdreq(struct f_uas *fu)
 {
-	usb_ep_free_request(fu->ep_cmd, fu->cmd.req);
-	kfree(fu->cmd.buf);
-	fu->cmd.req = NULL;
-	fu->cmd.buf = NULL;
+	int i;
+
+	for (i = 0; i < USBG_NUM_CMDS; i++) {
+		usb_ep_free_request(fu->ep_cmd, fu->cmd[i].req);
+		kfree(fu->cmd[i].buf);
+		fu->cmd[i].req = NULL;
+		fu->cmd[i].buf = NULL;
+	}
 }
 
 static void uasp_cleanup_old_alt(struct f_uas *fu)
@@ -500,7 +547,7 @@ static void uasp_cleanup_old_alt(struct f_uas *fu)
 	usb_ep_disable(fu->ep_status);
 	usb_ep_disable(fu->ep_cmd);
 
-	for (i = 0; i < UASP_SS_EP_COMP_NUM_STREAMS; i++)
+	for (i = 0; i < USBG_NUM_CMDS; i++)
 		uasp_cleanup_one_stream(fu, &fu->stream[i]);
 	uasp_free_cmdreq(fu);
 }
@@ -512,7 +559,7 @@ static int uasp_prepare_r_request(struct usbg_cmd *cmd)
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 	struct f_uas *fu = cmd->fu;
 	struct usb_gadget *gadget = fuas_to_gadget(fu);
-	struct uas_stream *stream = cmd->stream;
+	struct uas_stream *stream = &fu->stream[se_cmd->map_tag];
 
 	if (!gadget->sg_supported) {
 		cmd->data_buf = kmalloc(se_cmd->data_length, GFP_ATOMIC);
@@ -532,6 +579,7 @@ static int uasp_prepare_r_request(struct usbg_cmd *cmd)
 	}
 
 	stream->req_in->is_last = 1;
+	stream->req_in->stream_id = cmd->tag;
 	stream->req_in->complete = uasp_status_data_cmpl;
 	stream->req_in->length = se_cmd->data_length;
 	stream->req_in->context = cmd;
@@ -544,7 +592,7 @@ static void uasp_prepare_status(struct usbg_cmd *cmd)
 {
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 	struct sense_iu *iu = &cmd->sense_iu;
-	struct uas_stream *stream = cmd->stream;
+	struct uas_stream *stream = &cmd->fu->stream[se_cmd->map_tag];
 
 	cmd->state = UASP_QUEUE_COMMAND;
 	iu->iu_id = IU_ID_STATUS;
@@ -556,20 +604,76 @@ static void uasp_prepare_status(struct usbg_cmd *cmd)
 	iu->len = cpu_to_be16(se_cmd->scsi_sense_length);
 	iu->status = se_cmd->scsi_status;
 	stream->req_status->is_last = 1;
+	stream->req_status->stream_id = cmd->tag;
 	stream->req_status->context = cmd;
 	stream->req_status->length = se_cmd->scsi_sense_length + 16;
 	stream->req_status->buf = iu;
 	stream->req_status->complete = uasp_status_data_cmpl;
 }
 
+static void uasp_prepare_response(struct usbg_cmd *cmd)
+{
+	struct se_cmd *se_cmd = &cmd->se_cmd;
+	struct response_iu *rsp_iu = &cmd->response_iu;
+	struct uas_stream *stream = &cmd->fu->stream[se_cmd->map_tag];
+
+	cmd->state = UASP_QUEUE_COMMAND;
+	rsp_iu->iu_id = IU_ID_RESPONSE;
+	rsp_iu->tag = cpu_to_be16(cmd->tag);
+
+	if (cmd->tmr_rsp != RC_RESPONSE_UNKNOWN)
+		rsp_iu->response_code = cmd->tmr_rsp;
+	else
+		rsp_iu->response_code =
+			tcm_to_uasp_response(se_cmd->se_tmr_req->response);
+
+	/*
+	 * The UASP driver must support all the task management functions listed
+	 * in Table 20 of UAS-r04. To remain compliant while indicate that the
+	 * TMR did not go through, report RC_TMF_FAILED instead of
+	 * RC_TMF_NOT_SUPPORTED and print a warning to the user.
+	 */
+	switch (cmd->tmr_func) {
+	case TMF_ABORT_TASK:
+	case TMF_ABORT_TASK_SET:
+	case TMF_CLEAR_TASK_SET:
+	case TMF_LOGICAL_UNIT_RESET:
+	case TMF_CLEAR_ACA:
+	case TMF_I_T_NEXUS_RESET:
+	case TMF_QUERY_TASK:
+	case TMF_QUERY_TASK_SET:
+	case TMF_QUERY_ASYNC_EVENT:
+		if (rsp_iu->response_code == RC_TMF_NOT_SUPPORTED) {
+			struct usb_gadget *gadget = fuas_to_gadget(cmd->fu);
+
+			dev_warn(&gadget->dev, "TMF function %d not supported\n",
+				 cmd->tmr_func);
+			rsp_iu->response_code = RC_TMF_FAILED;
+		}
+		break;
+	default:
+		break;
+	}
+
+	stream->req_status->is_last = 1;
+	stream->req_status->stream_id = cmd->tag;
+	stream->req_status->context = cmd;
+	stream->req_status->length = sizeof(struct response_iu);
+	stream->req_status->buf = rsp_iu;
+	stream->req_status->complete = uasp_status_data_cmpl;
+}
+
+static void usbg_release_cmd(struct se_cmd *se_cmd);
+static int uasp_send_tm_response(struct usbg_cmd *cmd);
+
 static void uasp_status_data_cmpl(struct usb_ep *ep, struct usb_request *req)
 {
 	struct usbg_cmd *cmd = req->context;
-	struct uas_stream *stream = cmd->stream;
 	struct f_uas *fu = cmd->fu;
+	struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag];
 	int ret;
 
-	if (req->status < 0)
+	if (req->status == -ESHUTDOWN)
 		goto cleanup;
 
 	switch (cmd->state) {
@@ -600,8 +704,37 @@ static void uasp_status_data_cmpl(struct usb_ep *ep, struct usb_request *req)
 		break;
 
 	case UASP_QUEUE_COMMAND:
-		transport_generic_free_cmd(&cmd->se_cmd, 0);
-		usb_ep_queue(fu->ep_cmd, fu->cmd.req, GFP_ATOMIC);
+		/*
+		 * Overlapped command detected and cancelled.
+		 * So send overlapped attempted status.
+		 */
+		if (cmd->tmr_rsp == RC_OVERLAPPED_TAG &&
+		    req->status == -ECONNRESET) {
+			uasp_send_tm_response(cmd);
+			return;
+		}
+
+		hash_del(&stream->node);
+
+		/*
+		 * If no command submitted to target core here, just free the
+		 * bitmap index. This is for the cases where f_tcm handles
+		 * status response instead of the target core.
+		 */
+		if (cmd->tmr_rsp != RC_OVERLAPPED_TAG &&
+		    cmd->tmr_rsp != RC_RESPONSE_UNKNOWN) {
+			struct se_session *se_sess;
+
+			se_sess = fu->tpg->tpg_nexus->tvn_se_sess;
+			sbitmap_queue_clear(&se_sess->sess_tag_pool,
+					    cmd->se_cmd.map_tag,
+					    cmd->se_cmd.map_cpu);
+		} else {
+			transport_generic_free_cmd(&cmd->se_cmd, 0);
+		}
+
+		usb_ep_queue(fu->ep_cmd, cmd->req, GFP_ATOMIC);
+		complete(&stream->cmd_completion);
 		break;
 
 	default:
@@ -610,27 +743,38 @@ static void uasp_status_data_cmpl(struct usb_ep *ep, struct usb_request *req)
 	return;
 
 cleanup:
+	hash_del(&stream->node);
 	transport_generic_free_cmd(&cmd->se_cmd, 0);
 }
 
 static int uasp_send_status_response(struct usbg_cmd *cmd)
 {
 	struct f_uas *fu = cmd->fu;
-	struct uas_stream *stream = cmd->stream;
+	struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag];
 	struct sense_iu *iu = &cmd->sense_iu;
 
 	iu->tag = cpu_to_be16(cmd->tag);
-	stream->req_status->complete = uasp_status_data_cmpl;
-	stream->req_status->context = cmd;
 	cmd->fu = fu;
 	uasp_prepare_status(cmd);
 	return usb_ep_queue(fu->ep_status, stream->req_status, GFP_ATOMIC);
 }
 
+static int uasp_send_tm_response(struct usbg_cmd *cmd)
+{
+	struct f_uas *fu = cmd->fu;
+	struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag];
+	struct response_iu *iu = &cmd->response_iu;
+
+	iu->tag = cpu_to_be16(cmd->tag);
+	cmd->fu = fu;
+	uasp_prepare_response(cmd);
+	return usb_ep_queue(fu->ep_status, stream->req_status, GFP_ATOMIC);
+}
+
 static int uasp_send_read_response(struct usbg_cmd *cmd)
 {
 	struct f_uas *fu = cmd->fu;
-	struct uas_stream *stream = cmd->stream;
+	struct uas_stream *stream = &fu->stream[cmd->se_cmd.map_tag];
 	struct sense_iu *iu = &cmd->sense_iu;
 	int ret;
 
@@ -674,11 +818,10 @@ static int uasp_send_write_request(struct usbg_cmd *cmd)
 {
 	struct f_uas *fu = cmd->fu;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
-	struct uas_stream *stream = cmd->stream;
+	struct uas_stream *stream = &fu->stream[se_cmd->map_tag];
 	struct sense_iu *iu = &cmd->sense_iu;
 	int ret;
 
-	init_completion(&cmd->write_complete);
 	cmd->fu = fu;
 
 	iu->tag = cpu_to_be16(cmd->tag);
@@ -710,36 +853,31 @@ static int uasp_send_write_request(struct usbg_cmd *cmd)
 			pr_err("%s(%d)\n", __func__, __LINE__);
 	}
 
-	wait_for_completion(&cmd->write_complete);
-	target_execute_cmd(se_cmd);
 cleanup:
 	return ret;
 }
 
-static int usbg_submit_command(struct f_uas *, void *, unsigned int);
+static int usbg_submit_command(struct f_uas *, struct usb_request *);
 
 static void uasp_cmd_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	struct f_uas *fu = req->context;
-	int ret;
 
-	if (req->status < 0)
+	if (req->status == -ESHUTDOWN)
 		return;
 
-	ret = usbg_submit_command(fu, req->buf, req->actual);
-	/*
-	 * Once we tune for performance enqueue the command req here again so
-	 * we can receive a second command while we processing this one. Pay
-	 * attention to properly sync STAUS endpoint with DATA IN + OUT so you
-	 * don't break HS.
-	 */
-	if (!ret)
+	if (req->status < 0) {
+		usb_ep_queue(fu->ep_cmd, req, GFP_ATOMIC);
 		return;
-	usb_ep_queue(fu->ep_cmd, fu->cmd.req, GFP_ATOMIC);
+	}
+
+	usbg_submit_command(fu, req);
 }
 
 static int uasp_alloc_stream_res(struct f_uas *fu, struct uas_stream *stream)
 {
+	init_completion(&stream->cmd_completion);
+
 	stream->req_in = usb_ep_alloc_request(fu->ep_in, GFP_KERNEL);
 	if (!stream->req_in)
 		goto out;
@@ -764,66 +902,48 @@ out:
 	return -ENOMEM;
 }
 
-static int uasp_alloc_cmd(struct f_uas *fu)
+static int uasp_alloc_cmd(struct f_uas *fu, int i)
 {
-	fu->cmd.req = usb_ep_alloc_request(fu->ep_cmd, GFP_KERNEL);
-	if (!fu->cmd.req)
+	fu->cmd[i].req = usb_ep_alloc_request(fu->ep_cmd, GFP_KERNEL);
+	if (!fu->cmd[i].req)
 		goto err;
 
-	fu->cmd.buf = kmalloc(fu->ep_cmd->maxpacket, GFP_KERNEL);
-	if (!fu->cmd.buf)
+	fu->cmd[i].buf = kmalloc(fu->ep_cmd->maxpacket, GFP_KERNEL);
+	if (!fu->cmd[i].buf)
 		goto err_buf;
 
-	fu->cmd.req->complete = uasp_cmd_complete;
-	fu->cmd.req->buf = fu->cmd.buf;
-	fu->cmd.req->length = fu->ep_cmd->maxpacket;
-	fu->cmd.req->context = fu;
+	fu->cmd[i].req->complete = uasp_cmd_complete;
+	fu->cmd[i].req->buf = fu->cmd[i].buf;
+	fu->cmd[i].req->length = fu->ep_cmd->maxpacket;
+	fu->cmd[i].req->context = fu;
 	return 0;
 
 err_buf:
-	usb_ep_free_request(fu->ep_cmd, fu->cmd.req);
+	usb_ep_free_request(fu->ep_cmd, fu->cmd[i].req);
 err:
 	return -ENOMEM;
 }
 
-static void uasp_setup_stream_res(struct f_uas *fu, int max_streams)
-{
-	int i;
-
-	for (i = 0; i < max_streams; i++) {
-		struct uas_stream *s = &fu->stream[i];
-
-		s->req_in->stream_id = i + 1;
-		s->req_out->stream_id = i + 1;
-		s->req_status->stream_id = i + 1;
-	}
-}
-
 static int uasp_prepare_reqs(struct f_uas *fu)
 {
 	int ret;
 	int i;
-	int max_streams;
 
-	if (fu->flags & USBG_USE_STREAMS)
-		max_streams = UASP_SS_EP_COMP_NUM_STREAMS;
-	else
-		max_streams = 1;
-
-	for (i = 0; i < max_streams; i++) {
+	for (i = 0; i < USBG_NUM_CMDS; i++) {
 		ret = uasp_alloc_stream_res(fu, &fu->stream[i]);
 		if (ret)
 			goto err_cleanup;
 	}
 
-	ret = uasp_alloc_cmd(fu);
-	if (ret)
-		goto err_free_stream;
-	uasp_setup_stream_res(fu, max_streams);
+	for (i = 0; i < USBG_NUM_CMDS; i++) {
+		ret = uasp_alloc_cmd(fu, i);
+		if (ret)
+			goto err_free_stream;
 
-	ret = usb_ep_queue(fu->ep_cmd, fu->cmd.req, GFP_ATOMIC);
-	if (ret)
-		goto err_free_stream;
+		ret = usb_ep_queue(fu->ep_cmd, fu->cmd[i].req, GFP_ATOMIC);
+		if (ret)
+			goto err_free_stream;
+	}
 
 	return 0;
 
@@ -914,6 +1034,8 @@ static int get_cmd_dir(const unsigned char *cdb)
 	case READ_TOC:
 	case READ_FORMAT_CAPACITIES:
 	case REQUEST_SENSE:
+	case ATA_12:
+	case ATA_16:
 		ret = DMA_FROM_DEVICE;
 		break;
 
@@ -957,7 +1079,18 @@ static void usbg_data_write_cmpl(struct usb_ep *ep, struct usb_request *req)
 	struct usbg_cmd *cmd = req->context;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 
-	if (req->status < 0) {
+	cmd->state = UASP_QUEUE_COMMAND;
+
+	if (req->status == -ESHUTDOWN) {
+		struct uas_stream *stream = &cmd->fu->stream[se_cmd->map_tag];
+
+		hash_del(&stream->node);
+		target_put_sess_cmd(se_cmd);
+		transport_generic_free_cmd(&cmd->se_cmd, 0);
+		return;
+	}
+
+	if (req->status) {
 		pr_err("%s() state %d transfer failed\n", __func__, cmd->state);
 		goto cleanup;
 	}
@@ -969,11 +1102,22 @@ static void usbg_data_write_cmpl(struct usb_ep *ep, struct usb_request *req)
 				se_cmd->data_length);
 	}
 
-	complete(&cmd->write_complete);
+	cmd->flags |= USBG_CMD_PENDING_DATA_WRITE;
+	queue_work(cmd->fu->tpg->workqueue, &cmd->work);
 	return;
 
 cleanup:
-	transport_generic_free_cmd(&cmd->se_cmd, 0);
+	target_put_sess_cmd(se_cmd);
+
+	/* Command was aborted due to overlapped tag */
+	if (cmd->state == UASP_QUEUE_COMMAND &&
+	    cmd->tmr_rsp == RC_OVERLAPPED_TAG) {
+		uasp_send_tm_response(cmd);
+		return;
+	}
+
+	transport_send_check_condition_and_sense(se_cmd,
+			TCM_CHECK_CONDITION_ABORT_CMD, 0);
 }
 
 static int usbg_prepare_w_request(struct usbg_cmd *cmd, struct usb_request *req)
@@ -995,9 +1139,12 @@ static int usbg_prepare_w_request(struct usbg_cmd *cmd, struct usb_request *req)
 	}
 
 	req->is_last = 1;
+	req->stream_id = cmd->tag;
 	req->complete = usbg_data_write_cmpl;
 	req->length = se_cmd->data_length;
 	req->context = cmd;
+
+	cmd->state = UASP_SEND_STATUS;
 	return 0;
 }
 
@@ -1037,36 +1184,153 @@ static int usbg_send_read_response(struct se_cmd *se_cmd)
 		return uasp_send_read_response(cmd);
 }
 
-static void usbg_cmd_work(struct work_struct *work)
+static void usbg_aborted_task(struct se_cmd *se_cmd);
+
+static void usbg_submit_tmr(struct usbg_cmd *cmd)
+{
+	struct se_session *se_sess;
+	struct se_cmd *se_cmd;
+	int flags = TARGET_SCF_ACK_KREF;
+
+	se_cmd = &cmd->se_cmd;
+	se_sess = cmd->fu->tpg->tpg_nexus->tvn_se_sess;
+
+	target_submit_tmr(se_cmd, se_sess,
+			  cmd->response_iu.add_response_info,
+			  cmd->unpacked_lun, NULL, uasp_to_tcm_func(cmd->tmr_func),
+			  GFP_ATOMIC, cmd->tag, flags);
+}
+
+static void usbg_submit_cmd(struct usbg_cmd *cmd)
 {
-	struct usbg_cmd *cmd = container_of(work, struct usbg_cmd, work);
 	struct se_cmd *se_cmd;
 	struct tcm_usbg_nexus *tv_nexus;
 	struct usbg_tpg *tpg;
 	int dir, flags = (TARGET_SCF_UNKNOWN_SIZE | TARGET_SCF_ACK_KREF);
 
+	/*
+	 * Note: each command will spawn its own process, and each stage of the
+	 * command is processed sequentially. Should this no longer be the case,
+	 * locking is needed.
+	 */
+	if (cmd->flags & USBG_CMD_PENDING_DATA_WRITE) {
+		target_execute_cmd(&cmd->se_cmd);
+		cmd->flags &= ~USBG_CMD_PENDING_DATA_WRITE;
+		return;
+	}
+
 	se_cmd = &cmd->se_cmd;
 	tpg = cmd->fu->tpg;
 	tv_nexus = tpg->tpg_nexus;
 	dir = get_cmd_dir(cmd->cmd_buf);
-	if (dir < 0) {
-		__target_init_cmd(se_cmd,
-				  tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo,
-				  tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE,
-				  cmd->prio_attr, cmd->sense_iu.sense,
-				  cmd->unpacked_lun, NULL);
+	if (dir < 0)
 		goto out;
-	}
 
 	target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess, cmd->cmd_buf,
 			  cmd->sense_iu.sense, cmd->unpacked_lun, 0,
 			  cmd->prio_attr, dir, flags);
+
 	return;
 
 out:
+	__target_init_cmd(se_cmd,
+			  tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo,
+			  tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE,
+			  cmd->prio_attr, cmd->sense_iu.sense,
+			  cmd->unpacked_lun, NULL);
 	transport_send_check_condition_and_sense(se_cmd,
-			TCM_UNSUPPORTED_SCSI_OPCODE, 1);
-	transport_generic_free_cmd(&cmd->se_cmd, 0);
+			TCM_UNSUPPORTED_SCSI_OPCODE, 0);
+}
+
+static void usbg_cmd_work(struct work_struct *work)
+{
+	struct usbg_cmd *cmd = container_of(work, struct usbg_cmd, work);
+
+	/*
+	 * Failure is detected by f_tcm here. Skip submitting the command to the
+	 * target core if we already know the failing response and send the usb
+	 * response to the host directly.
+	 */
+	if (cmd->tmr_rsp != RC_RESPONSE_UNKNOWN)
+		goto skip;
+
+	if (cmd->tmr_func)
+		usbg_submit_tmr(cmd);
+	else
+		usbg_submit_cmd(cmd);
+
+	return;
+
+skip:
+	if (cmd->tmr_rsp == RC_OVERLAPPED_TAG) {
+		struct f_uas *fu = cmd->fu;
+		struct se_session *se_sess;
+		struct uas_stream *stream = NULL;
+		struct hlist_node *tmp;
+		struct usbg_cmd *active_cmd = NULL;
+
+		se_sess = cmd->fu->tpg->tpg_nexus->tvn_se_sess;
+
+		hash_for_each_possible_safe(fu->stream_hash, stream, tmp, node, cmd->tag) {
+			int i = stream - &fu->stream[0];
+
+			active_cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[i];
+			if (active_cmd->tag == cmd->tag)
+				break;
+		}
+
+		/* Sanity check */
+		if (!stream || (active_cmd && active_cmd->tag != cmd->tag)) {
+			usbg_submit_command(cmd->fu, cmd->req);
+			return;
+		}
+
+		reinit_completion(&stream->cmd_completion);
+
+		/*
+		 * A UASP command consists of the command, data, and status
+		 * stages, each operating sequentially from different endpoints.
+		 *
+		 * Each USB endpoint operates independently, and depending on
+		 * hardware implementation, a completion callback for a transfer
+		 * from one endpoint may not reflect the order of completion on
+		 * the wire. This is particularly true for devices with
+		 * endpoints that have independent interrupts and event buffers.
+		 *
+		 * The driver must still detect misbehaving hosts and respond
+		 * with an overlap status. To reduce false overlap failures,
+		 * allow the active and matching stream ID a brief 1ms to
+		 * complete before responding with an overlap command failure.
+		 * Overlap failure should be rare.
+		 */
+		wait_for_completion_timeout(&stream->cmd_completion, msecs_to_jiffies(1));
+
+		/* If the previous stream is completed, retry the command. */
+		if (!hash_hashed(&stream->node)) {
+			usbg_submit_command(cmd->fu, cmd->req);
+			return;
+		}
+
+		/*
+		 * The command isn't submitted to the target core, so we're safe
+		 * to remove the bitmap index from the session tag pool.
+		 */
+		sbitmap_queue_clear(&se_sess->sess_tag_pool,
+				    cmd->se_cmd.map_tag,
+				    cmd->se_cmd.map_cpu);
+
+		/*
+		 * Overlap command tag detected. Cancel any pending transfer of
+		 * the command submitted to target core.
+		 */
+		active_cmd->tmr_rsp = RC_OVERLAPPED_TAG;
+		usbg_aborted_task(&active_cmd->se_cmd);
+
+		/* Send the response after the transfer is aborted. */
+		return;
+	}
+
+	uasp_send_tm_response(cmd);
 }
 
 static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
@@ -1084,6 +1348,7 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->se_cmd.map_tag = tag;
 	cmd->se_cmd.map_cpu = cpu;
+	cmd->se_cmd.cpuid = cpu;
 	cmd->se_cmd.tag = cmd->tag = scsi_tag;
 	cmd->fu = fu;
 
@@ -1092,50 +1357,82 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
 
 static void usbg_release_cmd(struct se_cmd *);
 
-static int usbg_submit_command(struct f_uas *fu,
-		void *cmdbuf, unsigned int len)
+static int usbg_submit_command(struct f_uas *fu, struct usb_request *req)
 {
-	struct command_iu *cmd_iu = cmdbuf;
+	struct iu *iu = req->buf;
 	struct usbg_cmd *cmd;
 	struct usbg_tpg *tpg = fu->tpg;
 	struct tcm_usbg_nexus *tv_nexus;
+	struct uas_stream *stream;
+	struct hlist_node *tmp;
+	struct command_iu *cmd_iu;
 	u32 cmd_len;
 	u16 scsi_tag;
 
-	if (cmd_iu->iu_id != IU_ID_COMMAND) {
-		pr_err("Unsupported type %d\n", cmd_iu->iu_id);
-		return -EINVAL;
-	}
-
 	tv_nexus = tpg->tpg_nexus;
 	if (!tv_nexus) {
 		pr_err("Missing nexus, ignoring command\n");
 		return -EINVAL;
 	}
 
-	cmd_len = (cmd_iu->len & ~0x3) + 16;
-	if (cmd_len > USBG_MAX_CMD)
-		return -EINVAL;
-
-	scsi_tag = be16_to_cpup(&cmd_iu->tag);
+	scsi_tag = be16_to_cpup(&iu->tag);
 	cmd = usbg_get_cmd(fu, tv_nexus, scsi_tag);
 	if (IS_ERR(cmd)) {
 		pr_err("usbg_get_cmd failed\n");
 		return -ENOMEM;
 	}
-	memcpy(cmd->cmd_buf, cmd_iu->cdb, cmd_len);
 
-	if (fu->flags & USBG_USE_STREAMS) {
-		if (cmd->tag > UASP_SS_EP_COMP_NUM_STREAMS)
-			goto err;
-		if (!cmd->tag)
-			cmd->stream = &fu->stream[0];
-		else
-			cmd->stream = &fu->stream[cmd->tag - 1];
-	} else {
-		cmd->stream = &fu->stream[0];
+	cmd->req = req;
+	cmd->fu = fu;
+	cmd->tag = scsi_tag;
+	cmd->se_cmd.tag = scsi_tag;
+	cmd->tmr_func = 0;
+	cmd->tmr_rsp = RC_RESPONSE_UNKNOWN;
+	cmd->flags = 0;
+
+	cmd_iu = (struct command_iu *)iu;
+
+	/* Command and Task Management IUs share the same LUN offset */
+	cmd->unpacked_lun = scsilun_to_int(&cmd_iu->lun);
+
+	if (iu->iu_id != IU_ID_COMMAND && iu->iu_id != IU_ID_TASK_MGMT) {
+		cmd->tmr_rsp = RC_INVALID_INFO_UNIT;
+		goto skip;
+	}
+
+	hash_for_each_possible_safe(fu->stream_hash, stream, tmp, node, scsi_tag) {
+		struct usbg_cmd *active_cmd;
+		struct se_session *se_sess;
+		int i = stream - &fu->stream[0];
+
+		se_sess = cmd->fu->tpg->tpg_nexus->tvn_se_sess;
+		active_cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[i];
+
+		if (active_cmd->tag == scsi_tag) {
+			cmd->tmr_rsp = RC_OVERLAPPED_TAG;
+			goto skip;
+		}
 	}
 
+	stream = &fu->stream[cmd->se_cmd.map_tag];
+	hash_add(fu->stream_hash, &stream->node, scsi_tag);
+
+	if (iu->iu_id == IU_ID_TASK_MGMT) {
+		struct task_mgmt_iu *tm_iu;
+
+		tm_iu = (struct task_mgmt_iu *)iu;
+		cmd->tmr_func = tm_iu->function;
+		goto skip;
+	}
+
+	cmd_len = (cmd_iu->len & ~0x3) + 16;
+	if (cmd_len > USBG_MAX_CMD) {
+		target_free_tag(tv_nexus->tvn_se_sess, &cmd->se_cmd);
+		hash_del(&stream->node);
+		return -EINVAL;
+	}
+	memcpy(cmd->cmd_buf, cmd_iu->cdb, cmd_len);
+
 	switch (cmd_iu->prio_attr & 0x7) {
 	case UAS_HEAD_TAG:
 		cmd->prio_attr = TCM_HEAD_TAG;
@@ -1155,15 +1452,11 @@ static int usbg_submit_command(struct f_uas *fu,
 		break;
 	}
 
-	cmd->unpacked_lun = scsilun_to_int(&cmd_iu->lun);
-
+skip:
 	INIT_WORK(&cmd->work, usbg_cmd_work);
 	queue_work(tpg->workqueue, &cmd->work);
 
 	return 0;
-err:
-	usbg_release_cmd(&cmd->se_cmd);
-	return -EINVAL;
 }
 
 static void bot_cmd_work(struct work_struct *work)
@@ -1172,30 +1465,40 @@ static void bot_cmd_work(struct work_struct *work)
 	struct se_cmd *se_cmd;
 	struct tcm_usbg_nexus *tv_nexus;
 	struct usbg_tpg *tpg;
+	int flags = TARGET_SCF_ACK_KREF;
 	int dir;
 
+	/*
+	 * Note: each command will spawn its own process, and each stage of the
+	 * command is processed sequentially. Should this no longer be the case,
+	 * locking is needed.
+	 */
+	if (cmd->flags & USBG_CMD_PENDING_DATA_WRITE) {
+		target_execute_cmd(&cmd->se_cmd);
+		cmd->flags &= ~USBG_CMD_PENDING_DATA_WRITE;
+		return;
+	}
+
 	se_cmd = &cmd->se_cmd;
 	tpg = cmd->fu->tpg;
 	tv_nexus = tpg->tpg_nexus;
 	dir = get_cmd_dir(cmd->cmd_buf);
-	if (dir < 0) {
-		__target_init_cmd(se_cmd,
-				  tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo,
-				  tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE,
-				  cmd->prio_attr, cmd->sense_iu.sense,
-				  cmd->unpacked_lun, NULL);
+	if (dir < 0)
 		goto out;
-	}
 
 	target_submit_cmd(se_cmd, tv_nexus->tvn_se_sess,
 			  cmd->cmd_buf, cmd->sense_iu.sense, cmd->unpacked_lun,
-			  cmd->data_len, cmd->prio_attr, dir, 0);
+			  cmd->data_len, cmd->prio_attr, dir, flags);
 	return;
 
 out:
+	__target_init_cmd(se_cmd,
+			  tv_nexus->tvn_se_sess->se_tpg->se_tpg_tfo,
+			  tv_nexus->tvn_se_sess, cmd->data_len, DMA_NONE,
+			  cmd->prio_attr, cmd->sense_iu.sense,
+			  cmd->unpacked_lun, NULL);
 	transport_send_check_condition_and_sense(se_cmd,
-				TCM_UNSUPPORTED_SCSI_OPCODE, 1);
-	transport_generic_free_cmd(&cmd->se_cmd, 0);
+				TCM_UNSUPPORTED_SCSI_OPCODE, 0);
 }
 
 static int bot_submit_command(struct f_uas *fu,
@@ -1239,6 +1542,7 @@ static int bot_submit_command(struct f_uas *fu,
 	cmd->is_read = cbw->Flags & US_BULK_FLAG_IN ? 1 : 0;
 	cmd->data_len = le32_to_cpu(cbw->DataTransferLength);
 	cmd->se_cmd.tag = le32_to_cpu(cmd->bot_tag);
+	cmd->flags = 0;
 
 	INIT_WORK(&cmd->work, bot_cmd_work);
 	queue_work(tpg->workqueue, &cmd->work);
@@ -1275,16 +1579,38 @@ static void usbg_release_cmd(struct se_cmd *se_cmd)
 			se_cmd);
 	struct se_session *se_sess = se_cmd->se_sess;
 
+	cmd->tag = 0;
 	kfree(cmd->data_buf);
 	target_free_tag(se_sess, se_cmd);
 }
 
 static void usbg_queue_tm_rsp(struct se_cmd *se_cmd)
 {
+	struct usbg_cmd *cmd = container_of(se_cmd, struct usbg_cmd, se_cmd);
+
+	uasp_send_tm_response(cmd);
 }
 
 static void usbg_aborted_task(struct se_cmd *se_cmd)
 {
+	struct usbg_cmd *cmd = container_of(se_cmd, struct usbg_cmd, se_cmd);
+	struct f_uas *fu = cmd->fu;
+	struct usb_gadget *gadget = fuas_to_gadget(fu);
+	struct uas_stream *stream = &fu->stream[se_cmd->map_tag];
+	int ret = 0;
+
+	if (stream->req_out->status == -EINPROGRESS)
+		ret = usb_ep_dequeue(fu->ep_out, stream->req_out);
+	else if (stream->req_in->status == -EINPROGRESS)
+		ret = usb_ep_dequeue(fu->ep_in, stream->req_in);
+	else if (stream->req_status->status == -EINPROGRESS)
+		ret = usb_ep_dequeue(fu->ep_status, stream->req_status);
+
+	if (ret)
+		dev_err(&gadget->dev, "Failed to abort cmd tag %d, (%d)\n",
+			cmd->tag, ret);
+
+	cmd->state = UASP_QUEUE_COMMAND;
 }
 
 static const char *usbg_check_wwn(const char *name)
@@ -1355,7 +1681,8 @@ static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn,
 		goto unref_dep;
 	mutex_init(&tpg->tpg_mutex);
 	atomic_set(&tpg->tpg_port_count, 0);
-	tpg->workqueue = alloc_workqueue("tcm_usb_gadget", 0, 1);
+	tpg->workqueue = alloc_workqueue("tcm_usb_gadget",
+					 WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE);
 	if (!tpg->workqueue)
 		goto free_tpg;
 
@@ -1746,7 +2073,7 @@ static struct usb_endpoint_descriptor uasp_ss_bi_desc = {
 static struct usb_ss_ep_comp_descriptor uasp_bi_ep_comp_desc = {
 	.bLength =		sizeof(uasp_bi_ep_comp_desc),
 	.bDescriptorType =	USB_DT_SS_ENDPOINT_COMP,
-	.bMaxBurst =		0,
+	.bMaxBurst =		15,
 	.bmAttributes =		UASP_SS_EP_COMP_LOG_STREAMS,
 	.wBytesPerInterval =	0,
 };
@@ -1754,7 +2081,7 @@ static struct usb_ss_ep_comp_descriptor uasp_bi_ep_comp_desc = {
 static struct usb_ss_ep_comp_descriptor bot_bi_ep_comp_desc = {
 	.bLength =		sizeof(bot_bi_ep_comp_desc),
 	.bDescriptorType =	USB_DT_SS_ENDPOINT_COMP,
-	.bMaxBurst =		0,
+	.bMaxBurst =		15,
 };
 
 static struct usb_endpoint_descriptor uasp_bo_desc = {
@@ -1789,12 +2116,14 @@ static struct usb_endpoint_descriptor uasp_ss_bo_desc = {
 static struct usb_ss_ep_comp_descriptor uasp_bo_ep_comp_desc = {
 	.bLength =		sizeof(uasp_bo_ep_comp_desc),
 	.bDescriptorType =	USB_DT_SS_ENDPOINT_COMP,
+	.bMaxBurst =		15,
 	.bmAttributes =		UASP_SS_EP_COMP_LOG_STREAMS,
 };
 
 static struct usb_ss_ep_comp_descriptor bot_bo_ep_comp_desc = {
 	.bLength =		sizeof(bot_bo_ep_comp_desc),
 	.bDescriptorType =	USB_DT_SS_ENDPOINT_COMP,
+	.bMaxBurst =		15,
 };
 
 static struct usb_endpoint_descriptor uasp_status_desc = {
@@ -1971,43 +2300,39 @@ static int tcm_bind(struct usb_configuration *c, struct usb_function *f)
 	bot_intf_desc.bInterfaceNumber = iface;
 	uasp_intf_desc.bInterfaceNumber = iface;
 	fu->iface = iface;
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_bi_desc,
-			&uasp_bi_ep_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_bi_desc);
 	if (!ep)
 		goto ep_fail;
 
 	fu->ep_in = ep;
 
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_bo_desc,
-			&uasp_bo_ep_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_bo_desc);
 	if (!ep)
 		goto ep_fail;
 	fu->ep_out = ep;
 
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_status_desc,
-			&uasp_status_in_ep_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_status_desc);
 	if (!ep)
 		goto ep_fail;
 	fu->ep_status = ep;
 
-	ep = usb_ep_autoconfig_ss(gadget, &uasp_ss_cmd_desc,
-			&uasp_cmd_comp_desc);
+	ep = usb_ep_autoconfig(gadget, &uasp_fs_cmd_desc);
 	if (!ep)
 		goto ep_fail;
 	fu->ep_cmd = ep;
 
 	/* Assume endpoint addresses are the same for both speeds */
-	uasp_bi_desc.bEndpointAddress =	uasp_ss_bi_desc.bEndpointAddress;
-	uasp_bo_desc.bEndpointAddress = uasp_ss_bo_desc.bEndpointAddress;
+	uasp_bi_desc.bEndpointAddress =	uasp_fs_bi_desc.bEndpointAddress;
+	uasp_bo_desc.bEndpointAddress = uasp_fs_bo_desc.bEndpointAddress;
 	uasp_status_desc.bEndpointAddress =
-		uasp_ss_status_desc.bEndpointAddress;
-	uasp_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress;
+		uasp_fs_status_desc.bEndpointAddress;
+	uasp_cmd_desc.bEndpointAddress = uasp_fs_cmd_desc.bEndpointAddress;
 
-	uasp_fs_bi_desc.bEndpointAddress = uasp_ss_bi_desc.bEndpointAddress;
-	uasp_fs_bo_desc.bEndpointAddress = uasp_ss_bo_desc.bEndpointAddress;
-	uasp_fs_status_desc.bEndpointAddress =
-		uasp_ss_status_desc.bEndpointAddress;
-	uasp_fs_cmd_desc.bEndpointAddress = uasp_ss_cmd_desc.bEndpointAddress;
+	uasp_ss_bi_desc.bEndpointAddress = uasp_fs_bi_desc.bEndpointAddress;
+	uasp_ss_bo_desc.bEndpointAddress = uasp_fs_bo_desc.bEndpointAddress;
+	uasp_ss_status_desc.bEndpointAddress =
+		uasp_fs_status_desc.bEndpointAddress;
+	uasp_ss_cmd_desc.bEndpointAddress = uasp_fs_cmd_desc.bEndpointAddress;
 
 	ret = usb_assign_descriptors(f, uasp_fs_function_desc,
 			uasp_hs_function_desc, uasp_ss_function_desc,
@@ -2051,9 +2376,14 @@ static void tcm_delayed_set_alt(struct work_struct *wq)
 
 static int tcm_get_alt(struct usb_function *f, unsigned intf)
 {
-	if (intf == bot_intf_desc.bInterfaceNumber)
+	struct f_uas *fu = to_f_uas(f);
+
+	if (fu->iface != intf)
+		return -EOPNOTSUPP;
+
+	if (fu->flags & USBG_IS_BOT)
 		return USB_G_ALT_INT_BBB;
-	if (intf == uasp_intf_desc.bInterfaceNumber)
+	else if (fu->flags & USBG_IS_UAS)
 		return USB_G_ALT_INT_UAS;
 
 	return -EOPNOTSUPP;
@@ -2063,6 +2393,9 @@ static int tcm_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 {
 	struct f_uas *fu = to_f_uas(f);
 
+	if (fu->iface != intf)
+		return -EOPNOTSUPP;
+
 	if ((alt == USB_G_ALT_INT_BBB) || (alt == USB_G_ALT_INT_UAS)) {
 		struct guas_setup_wq *work;
 
@@ -2271,6 +2604,8 @@ static struct usb_function *tcm_alloc(struct usb_function_instance *fi)
 	fu->function.disable = tcm_disable;
 	fu->function.free_func = tcm_free;
 	fu->tpg = tpg_instances[i].tpg;
+
+	hash_init(fu->stream_hash);
 	mutex_unlock(&tpg_instances_lock);
 
 	return &fu->function;
diff --git a/drivers/usb/gadget/function/storage_common.h b/drivers/usb/gadget/function/storage_common.h
index ced5d2b09234..11ac785d5eee 100644
--- a/drivers/usb/gadget/function/storage_common.h
+++ b/drivers/usb/gadget/function/storage_common.h
@@ -131,7 +131,7 @@ static inline bool fsg_lun_is_open(struct fsg_lun *curlun)
 #define FSG_BUFLEN	((u32)16384)
 
 /* Maximal number of LUNs supported in mass storage function */
-#define FSG_MAX_LUNS	16
+#define FSG_MAX_LUNS	(US_BULK_MAX_LUN_LIMIT + 1)
 
 enum fsg_buffer_state {
 	BUF_STATE_SENDING = -2,
diff --git a/drivers/usb/gadget/function/tcm.h b/drivers/usb/gadget/function/tcm.h
index 3cd565794ad7..009974d81d66 100644
--- a/drivers/usb/gadget/function/tcm.h
+++ b/drivers/usb/gadget/function/tcm.h
@@ -4,6 +4,7 @@
 
 #include <linux/kref.h>
 /* #include <linux/usb/uas.h> */
+#include <linux/hashtable.h>
 #include <linux/usb/composite.h>
 #include <linux/usb/uas.h>
 #include <linux/usb/storage.h>
@@ -13,9 +14,11 @@
 #define USBG_NAMELEN 32
 
 #define fuas_to_gadget(f)	(f->function.config->cdev->gadget)
-#define UASP_SS_EP_COMP_LOG_STREAMS 4
+#define UASP_SS_EP_COMP_LOG_STREAMS 5
 #define UASP_SS_EP_COMP_NUM_STREAMS (1 << UASP_SS_EP_COMP_LOG_STREAMS)
 
+#define USBG_NUM_CMDS		(UASP_SS_EP_COMP_NUM_STREAMS + 1)
+
 enum {
 	USB_G_STR_INT_UAS = 0,
 	USB_G_STR_INT_BBB,
@@ -24,7 +27,7 @@ enum {
 #define USB_G_ALT_INT_BBB       0
 #define USB_G_ALT_INT_UAS       1
 
-#define USB_G_DEFAULT_SESSION_TAGS	128
+#define USB_G_DEFAULT_SESSION_TAGS	USBG_NUM_CMDS
 
 struct tcm_usbg_nexus {
 	struct se_session *tvn_se_sess;
@@ -72,15 +75,23 @@ struct usbg_cmd {
 	struct se_cmd se_cmd;
 	void *data_buf; /* used if no sg support available */
 	struct f_uas *fu;
-	struct completion write_complete;
 	struct kref ref;
 
+	struct usb_request *req;
+
+	u32 flags;
+#define USBG_CMD_PENDING_DATA_WRITE	BIT(0)
+
 	/* UAS only */
 	u16 tag;
 	u16 prio_attr;
 	struct sense_iu sense_iu;
+	struct response_iu response_iu;
 	enum uas_state state;
-	struct uas_stream *stream;
+
+	int tmr_func;
+	int tmr_rsp;
+#define	RC_RESPONSE_UNKNOWN	0xff
 
 	/* BOT only */
 	__le32 bot_tag;
@@ -93,6 +104,9 @@ struct uas_stream {
 	struct usb_request	*req_in;
 	struct usb_request	*req_out;
 	struct usb_request	*req_status;
+
+	struct completion	cmd_completion;
+	struct hlist_node	node;
 };
 
 struct usbg_cdb {
@@ -116,15 +130,17 @@ struct f_uas {
 #define USBG_USE_STREAMS	(1 << 2)
 #define USBG_IS_BOT		(1 << 3)
 #define USBG_BOT_CMD_PEND	(1 << 4)
+#define USBG_BOT_WEDGED		(1 << 5)
 
-	struct usbg_cdb		cmd;
+	struct usbg_cdb		cmd[USBG_NUM_CMDS];
 	struct usb_ep		*ep_in;
 	struct usb_ep		*ep_out;
 
 	/* UAS */
 	struct usb_ep		*ep_status;
 	struct usb_ep		*ep_cmd;
-	struct uas_stream	stream[UASP_SS_EP_COMP_NUM_STREAMS];
+	struct uas_stream	stream[USBG_NUM_CMDS];
+	DECLARE_HASHTABLE(stream_hash, UASP_SS_EP_COMP_LOG_STREAMS);
 
 	/* BOT */
 	struct bot_status	bot_status;
diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index bc143a86c2dd..36fff45e8c9b 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -21,6 +21,7 @@
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/console.h>
@@ -1420,10 +1421,6 @@ void gserial_disconnect(struct gserial *gser)
 	/* REVISIT as above: how best to track this? */
 	port->port_line_coding = gser->port_line_coding;
 
-	/* disable endpoints, aborting down any active I/O */
-	usb_ep_disable(gser->out);
-	usb_ep_disable(gser->in);
-
 	port->port_usb = NULL;
 	gser->ioport = NULL;
 	if (port->port.count > 0) {
@@ -1435,6 +1432,10 @@ void gserial_disconnect(struct gserial *gser)
 	spin_unlock(&port->port_lock);
 	spin_unlock_irqrestore(&serial_port_lock, flags);
 
+	/* disable endpoints, aborting down any active I/O */
+	usb_ep_disable(gser->out);
+	usb_ep_disable(gser->in);
+
 	/* finally, free any unused/unusable I/O buffers */
 	spin_lock_irqsave(&port->port_lock, flags);
 	if (port->port.count == 0)
@@ -1545,7 +1546,7 @@ static int __init userial_init(void)
 
 	pr_debug("%s: registered %d ttyGS* device%s\n", __func__,
 			MAX_U_SERIAL_PORTS,
-			(MAX_U_SERIAL_PORTS == 1) ? "" : "s");
+			str_plural(MAX_U_SERIAL_PORTS));
 
 	return status;
 fail:
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 9c7381661016..b6a30d88a800 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -20,6 +20,7 @@
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/poll.h>
 #include <linux/kthread.h>
 #include <linux/aio.h>
@@ -1182,7 +1183,7 @@ ep0_fasync (int f, struct file *fd, int on)
 {
 	struct dev_data		*dev = fd->private_data;
 	// caller must F_SETOWN before signal delivery happens
-	VDEBUG (dev, "%s %s\n", __func__, on ? "on" : "off");
+	VDEBUG(dev, "%s %s\n", __func__, str_on_off(on));
 	return fasync_helper (f, fd, on, &dev->fasync);
 }
 
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c
index a63e4af60a56..02fe1a08d575 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/hub.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c
@@ -22,6 +22,7 @@
 #include <linux/usb/gadget.h>
 #include <linux/of.h>
 #include <linux/regmap.h>
+#include <linux/string_choices.h>
 #include <linux/dma-mapping.h>
 #include <linux/bcd.h>
 #include <linux/version.h>
@@ -219,7 +220,7 @@ static int ast_vhub_hub_dev_feature(struct ast_vhub_ep *ep,
 	if (wValue == USB_DEVICE_REMOTE_WAKEUP) {
 		ep->vhub->wakeup_en = is_set;
 		EPDBG(ep, "Hub remote wakeup %s\n",
-		      is_set ? "enabled" : "disabled");
+		      str_enabled_disabled(is_set));
 		return std_req_complete;
 	}
 
diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c
index e3af4ec3794e..aa4c61094dc6 100644
--- a/drivers/usb/gadget/udc/at91_udc.c
+++ b/drivers/usb/gadget/udc/at91_udc.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/errno.h>
 #include <linux/list.h>
 #include <linux/interrupt.h>
@@ -131,7 +132,7 @@ static void proc_ep_show(struct seq_file *s, struct at91_ep *ep)
 	seq_printf(s, "csr %08x rxbytes=%d %s %s %s" EIGHTBITS "\n",
 		csr,
 		(csr & 0x07ff0000) >> 16,
-		(csr & (1 << 15)) ? "enabled" : "disabled",
+		str_enabled_disabled(csr & (1 << 15)),
 		(csr & (1 << 11)) ? "DATA1" : "DATA0",
 		types[(csr & 0x700) >> 8],
 
diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c
index 62fce42ef2da..7e69944ef18a 100644
--- a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c
+++ b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c
@@ -29,6 +29,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/interrupt.h>
 #include <linux/property.h>
+#include <linux/string_choices.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
 
@@ -2233,12 +2234,12 @@ static int cdns2_init_eps(struct cdns2_device *pdev)
 		dev_dbg(pdev->dev, "Init %s, SupType: CTRL: %s, INT: %s, "
 			"BULK: %s, ISOC %s, SupDir IN: %s, OUT: %s\n",
 			pep->name,
-			(pep->endpoint.caps.type_control) ? "yes" : "no",
-			(pep->endpoint.caps.type_int) ? "yes" : "no",
-			(pep->endpoint.caps.type_bulk) ? "yes" : "no",
-			(pep->endpoint.caps.type_iso) ? "yes" : "no",
-			(pep->endpoint.caps.dir_in) ? "yes" : "no",
-			(pep->endpoint.caps.dir_out) ? "yes" : "no");
+			str_yes_no(pep->endpoint.caps.type_control),
+			str_yes_no(pep->endpoint.caps.type_int),
+			str_yes_no(pep->endpoint.caps.type_bulk),
+			str_yes_no(pep->endpoint.caps.type_iso),
+			str_yes_no(pep->endpoint.caps.dir_in),
+			str_yes_no(pep->endpoint.caps.dir_out));
 
 		INIT_LIST_HEAD(&pep->pending_list);
 		INIT_LIST_HEAD(&pep->deferred_list);
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index a7e8fa45776b..bda08c5ba7c0 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -28,6 +28,7 @@
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/hrtimer.h>
@@ -625,7 +626,7 @@ static int dummy_enable(struct usb_ep *_ep,
 		desc->bEndpointAddress & 0x0f,
 		(desc->bEndpointAddress & USB_DIR_IN) ? "in" : "out",
 		usb_ep_type_string(usb_endpoint_type(desc)),
-		max, ep->stream_en ? "enabled" : "disabled");
+		max, str_enabled_disabled(ep->stream_en));
 
 	/* at this point real hardware should be NAKing transfers
 	 * to that endpoint, until a buffer is queued to it.
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 8b7f7f961774..4dea8bc30cf6 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -22,6 +22,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/interrupt.h>
@@ -1181,7 +1182,7 @@ static int fsl_vbus_session(struct usb_gadget *gadget, int is_active)
 
 	udc = container_of(gadget, struct fsl_udc, gadget);
 	spin_lock_irqsave(&udc->lock, flags);
-	dev_vdbg(&gadget->dev, "VBUS %s\n", is_active ? "on" : "off");
+	dev_vdbg(&gadget->dev, "VBUS %s\n", str_on_off(is_active));
 	udc->vbus_active = (is_active != 0);
 	if (can_pullup(udc))
 		fsl_writel((fsl_readl(&dr_regs->usbcmd) | USB_CMD_RUN_STOP),
diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c
index 698463bf697b..8902abe3ca76 100644
--- a/drivers/usb/gadget/udc/omap_udc.c
+++ b/drivers/usb/gadget/udc/omap_udc.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/timer.h>
 #include <linux/list.h>
 #include <linux/interrupt.h>
@@ -1252,7 +1253,7 @@ static int omap_vbus_session(struct usb_gadget *gadget, int is_active)
 
 	udc = container_of(gadget, struct omap_udc, gadget);
 	spin_lock_irqsave(&udc->lock, flags);
-	VDBG("VBUS %s\n", is_active ? "on" : "off");
+	VDBG("VBUS %s\n", str_on_off(is_active));
 	udc->vbus_active = (is_active != 0);
 	if (cpu_is_omap15xx()) {
 		/* "software" detect, ignored if !VBUS_MODE_1510 */
diff --git a/drivers/usb/gadget/udc/pxa27x_udc.c b/drivers/usb/gadget/udc/pxa27x_udc.c
index f9a55d4f189f..897f53601b5b 100644
--- a/drivers/usb/gadget/udc/pxa27x_udc.c
+++ b/drivers/usb/gadget/udc/pxa27x_udc.c
@@ -20,6 +20,7 @@
 #include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/prefetch.h>
 #include <linux/byteorder/generic.h>
 #include <linux/platform_data/pxa2xx_udc.h>
@@ -1083,7 +1084,7 @@ static int pxa_ep_queue(struct usb_ep *_ep, struct usb_request *_req,
 
 	is_first_req = list_empty(&ep->queue);
 	ep_dbg(ep, "queue req %p(first=%s), len %d buf %p\n",
-			_req, is_first_req ? "yes" : "no",
+			_req, str_yes_no(is_first_req),
 			_req->length, _req->buf);
 
 	if (!ep->enabled) {
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index a6c20facf945..fce800ba4c61 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -15,6 +15,7 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
 #include <linux/list.h>
@@ -2756,7 +2757,7 @@ static void ehci_port_power(struct oxu_hcd *oxu, int is_on)
 	if (!HCS_PPC(oxu->hcs_params))
 		return;
 
-	oxu_dbg(oxu, "...power%s ports...\n", is_on ? "up" : "down");
+	oxu_dbg(oxu, "...power%s ports...\n", str_up_down(is_on));
 	for (port = HCS_N_PORTS(oxu->hcs_params); port > 0; ) {
 		if (is_on)
 			oxu_hub_control(oxu_to_hcd(oxu), SetPortFeature,
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index 036f5fd6d159..fa2e4badd288 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -48,6 +48,7 @@
 #include <linux/usb/hcd.h>
 #include <linux/platform_device.h>
 #include <linux/prefetch.h>
+#include <linux/string_choices.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
@@ -98,7 +99,7 @@ static void port_power(struct sl811 *sl811, int is_on)
 	if (sl811->board && sl811->board->port_power) {
 		/* switch VBUS, at 500mA unless hub power budget gets set */
 		dev_dbg(hcd->self.controller, "power %s\n",
-			is_on ? "on" : "off");
+			str_on_off(is_on));
 		sl811->board->port_power(hcd->self.controller, is_on);
 	}
 
diff --git a/drivers/usb/host/xhci-caps.h b/drivers/usb/host/xhci-caps.h
index 9e94cebf4a56..f6b9a00a0ab9 100644
--- a/drivers/usb/host/xhci-caps.h
+++ b/drivers/usb/host/xhci-caps.h
@@ -83,3 +83,9 @@
 #define	HCC2_CIC(p)		((p) & (1 << 5))
 /* true: HC support Extended TBC Capability, Isoc burst count > 65535 */
 #define	HCC2_ETC(p)		((p) & (1 << 6))
+/* true: HC support Extended TBC TRB Status Capability */
+#define HCC2_ETC_TSC(p)         ((p) & (1 << 7))
+/* true: HC support Get/Set Extended Property Capability */
+#define HCC2_GSC(p)             ((p) & (1 << 8))
+/* true: HC support Virtualization Based Trusted I/O Capability */
+#define HCC2_VTC(p)             ((p) & (1 << 9))
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 227e513867dd..fd7895b24367 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -957,7 +957,7 @@ static void xhci_dbc_handle_events(struct work_struct *work)
 		/* set fast poll rate if there are pending data transfers */
 		if (!list_empty(&dbc->eps[BULK_OUT].list_pending) ||
 		    !list_empty(&dbc->eps[BULK_IN].list_pending))
-			poll_interval = 1;
+			poll_interval = 0;
 		break;
 	default:
 		dev_info(dbc->dev, "stop handling dbc events\n");
diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c
index d719c16ea30b..60ed753c85bb 100644
--- a/drivers/usb/host/xhci-dbgtty.c
+++ b/drivers/usb/host/xhci-dbgtty.c
@@ -110,15 +110,74 @@ static void dbc_start_rx(struct dbc_port *port)
 	}
 }
 
+/*
+ * Queue received data to tty buffer and push it.
+ *
+ * Returns nr of remaining bytes that didn't fit tty buffer, i.e. 0 if all
+ * bytes sucessfullt moved. In case of error returns negative errno.
+ * Call with lock held
+ */
+static int dbc_rx_push_buffer(struct dbc_port *port, struct dbc_request *req)
+{
+	char		*packet = req->buf;
+	unsigned int	n, size = req->actual;
+	int		count;
+
+	if (!req->actual)
+		return 0;
+
+	/* if n_read is set then request was partially moved to tty buffer */
+	n = port->n_read;
+	if (n) {
+		packet += n;
+		size -= n;
+	}
+
+	count = tty_insert_flip_string(&port->port, packet, size);
+	if (count)
+		tty_flip_buffer_push(&port->port);
+	if (count != size) {
+		port->n_read += count;
+		return size - count;
+	}
+
+	port->n_read = 0;
+	return 0;
+}
+
 static void
 dbc_read_complete(struct xhci_dbc *dbc, struct dbc_request *req)
 {
 	unsigned long		flags;
 	struct dbc_port		*port = dbc_to_port(dbc);
+	struct tty_struct	*tty;
+	int			untransferred;
+
+	tty = port->port.tty;
 
 	spin_lock_irqsave(&port->port_lock, flags);
+
+	/*
+	 * Only defer copyig data to tty buffer in case:
+	 * - !list_empty(&port->read_queue), there are older pending data
+	 * - tty is throttled
+	 * - failed to copy all data to buffer, defer remaining part
+	 */
+
+	if (list_empty(&port->read_queue) && tty && !tty_throttled(tty)) {
+		untransferred = dbc_rx_push_buffer(port, req);
+		if (untransferred == 0) {
+			list_add_tail(&req->list_pool, &port->read_pool);
+			if (req->status != -ESHUTDOWN)
+				dbc_start_rx(port);
+			goto out;
+		}
+	}
+
+	/* defer moving data from req to tty buffer to a tasklet */
 	list_add_tail(&req->list_pool, &port->read_queue);
 	tasklet_schedule(&port->push);
+out:
 	spin_unlock_irqrestore(&port->port_lock, flags);
 }
 
@@ -331,10 +390,10 @@ static void dbc_rx_push(struct tasklet_struct *t)
 	struct dbc_request	*req;
 	struct tty_struct	*tty;
 	unsigned long		flags;
-	bool			do_push = false;
 	bool			disconnect = false;
 	struct dbc_port		*port = from_tasklet(port, t, push);
 	struct list_head	*queue = &port->read_queue;
+	int			untransferred;
 
 	spin_lock_irqsave(&port->port_lock, flags);
 	tty = port->port.tty;
@@ -356,42 +415,15 @@ static void dbc_rx_push(struct tasklet_struct *t)
 			break;
 		}
 
-		if (req->actual) {
-			char		*packet = req->buf;
-			unsigned int	n, size = req->actual;
-			int		count;
-
-			n = port->n_read;
-			if (n) {
-				packet += n;
-				size -= n;
-			}
-
-			count = tty_insert_flip_string(&port->port, packet,
-						       size);
-			if (count)
-				do_push = true;
-			if (count != size) {
-				port->n_read += count;
-				break;
-			}
-			port->n_read = 0;
-		}
+		untransferred = dbc_rx_push_buffer(port, req);
+		if (untransferred > 0)
+			break;
 
 		list_move_tail(&req->list_pool, &port->read_pool);
 	}
 
-	if (do_push)
-		tty_flip_buffer_push(&port->port);
-
-	if (!list_empty(queue) && tty) {
-		if (!tty_throttled(tty)) {
-			if (do_push)
-				tasklet_schedule(&port->push);
-			else
-				pr_warn("ttyDBC0: RX not scheduled?\n");
-		}
-	}
+	if (!list_empty(queue))
+		tasklet_schedule(&port->push);
 
 	if (!disconnect)
 		dbc_start_rx(port);
diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 4f0c1b96e208..1f5ef174abea 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -232,16 +232,7 @@ static struct xhci_file_map ring_files[] = {
 
 static int xhci_ring_open(struct inode *inode, struct file *file)
 {
-	int			i;
-	struct xhci_file_map	*f_map;
-	const char		*file_name = file_dentry(file)->d_iname;
-
-	for (i = 0; i < ARRAY_SIZE(ring_files); i++) {
-		f_map = &ring_files[i];
-
-		if (strcmp(f_map->name, file_name) == 0)
-			break;
-	}
+	const struct xhci_file_map *f_map = debugfs_get_aux(file);
 
 	return single_open(file, f_map->show, inode->i_private);
 }
@@ -318,16 +309,7 @@ static struct xhci_file_map context_files[] = {
 
 static int xhci_context_open(struct inode *inode, struct file *file)
 {
-	int			i;
-	struct xhci_file_map	*f_map;
-	const char		*file_name = file_dentry(file)->d_iname;
-
-	for (i = 0; i < ARRAY_SIZE(context_files); i++) {
-		f_map = &context_files[i];
-
-		if (strcmp(f_map->name, file_name) == 0)
-			break;
-	}
+	const struct xhci_file_map *f_map = debugfs_get_aux(file);
 
 	return single_open(file, f_map->show, inode->i_private);
 }
@@ -410,7 +392,8 @@ static void xhci_debugfs_create_files(struct xhci_hcd *xhci,
 	int			i;
 
 	for (i = 0; i < nentries; i++)
-		debugfs_create_file(files[i].name, 0444, parent, data, fops);
+		debugfs_create_file_aux(files[i].name, 0444, parent,
+					data, &files[i], fops);
 }
 
 static struct dentry *xhci_debugfs_create_ring_dir(struct xhci_hcd *xhci,
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index db109b570c5c..d85ffa9ffaa7 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -330,6 +330,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 		usb3_hcd->can_do_streams = 1;
 
 	if (xhci->shared_hcd) {
+		xhci->shared_hcd->rsrc_start = hcd->rsrc_start;
+		xhci->shared_hcd->rsrc_len = hcd->rsrc_len;
 		ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
 		if (ret)
 			goto put_usb3_hcd;
@@ -567,6 +569,7 @@ EXPORT_SYMBOL_GPL(xhci_plat_pm_ops);
 static const struct acpi_device_id usb_xhci_acpi_match[] = {
 	/* XHCI-compliant USB Controller */
 	{ "PNP0D10", },
+	{ "PNP0D15", },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, usb_xhci_acpi_match);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 09b05a62375e..965bffce301e 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -55,6 +55,7 @@
 #include <linux/jiffies.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/dma-mapping.h>
 #include "xhci.h"
 #include "xhci-trace.h"
@@ -422,7 +423,8 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 	if ((xhci->cmd_ring->dequeue != xhci->cmd_ring->enqueue) &&
 	    !(xhci->xhc_state & XHCI_STATE_DYING)) {
 		xhci->current_cmd = cur_cmd;
-		xhci_mod_cmd_timer(xhci);
+		if (cur_cmd)
+			xhci_mod_cmd_timer(xhci);
 		xhci_ring_cmd_db(xhci);
 	}
 }
@@ -1649,12 +1651,13 @@ static void xhci_handle_cmd_nec_get_fw(struct xhci_hcd *xhci,
 			NEC_FW_MINOR(le32_to_cpu(event->status)));
 }
 
-static void xhci_complete_del_and_free_cmd(struct xhci_command *cmd, u32 status)
+static void xhci_complete_del_and_free_cmd(struct xhci_command *cmd, u32 comp_code, u32 comp_param)
 {
 	list_del(&cmd->cmd_list);
 
 	if (cmd->completion) {
-		cmd->status = status;
+		cmd->status = comp_code;
+		cmd->comp_param = comp_param;
 		complete(cmd->completion);
 	} else {
 		kfree(cmd);
@@ -1666,7 +1669,7 @@ void xhci_cleanup_command_queue(struct xhci_hcd *xhci)
 	struct xhci_command *cur_cmd, *tmp_cmd;
 	xhci->current_cmd = NULL;
 	list_for_each_entry_safe(cur_cmd, tmp_cmd, &xhci->cmd_list, cmd_list)
-		xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED);
+		xhci_complete_del_and_free_cmd(cur_cmd, COMP_COMMAND_ABORTED, 0);
 }
 
 void xhci_handle_command_timeout(struct work_struct *work)
@@ -1751,6 +1754,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 		struct xhci_event_cmd *event)
 {
 	unsigned int slot_id = TRB_TO_SLOT_ID(le32_to_cpu(event->flags));
+	u32 status = le32_to_cpu(event->status);
 	u64 cmd_dma;
 	dma_addr_t cmd_dequeue_dma;
 	u32 cmd_comp_code;
@@ -1879,7 +1883,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 	}
 
 event_handled:
-	xhci_complete_del_and_free_cmd(cmd, cmd_comp_code);
+	xhci_complete_del_and_free_cmd(cmd, cmd_comp_code, COMP_PARAM(status));
 
 	inc_deq(xhci, xhci->cmd_ring);
 }
@@ -3438,8 +3442,8 @@ static void check_interval(struct urb *urb, struct xhci_ep_ctx *ep_ctx)
 	if (xhci_interval != ep_interval) {
 		dev_dbg_ratelimited(&urb->dev->dev,
 				"Driver uses different interval (%d microframe%s) than xHCI (%d microframe%s)\n",
-				ep_interval, ep_interval == 1 ? "" : "s",
-				xhci_interval, xhci_interval == 1 ? "" : "s");
+				ep_interval, str_plural(ep_interval),
+				xhci_interval, str_plural(xhci_interval));
 		urb->interval = xhci_interval;
 		/* Convert back to frames for LS/FS devices */
 		if (urb->dev->speed == USB_SPEED_LOW ||
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 06ae193ec874..22dc86fb5254 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -26,6 +26,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/usb/otg.h>
 #include <linux/usb/phy.h>
 #include <linux/usb/role.h>
@@ -724,7 +725,7 @@ static void tegra_xusb_mbox_handle(struct tegra_xusb *tegra,
 		if (err < 0) {
 			dev_err(dev,
 				"failed to %s LFPS detection on USB3#%u: %d\n",
-				enable ? "enable" : "disable", port, err);
+				str_enable_disable(enable), port, err);
 			rsp.cmd = MBOX_CMD_NAK;
 		} else {
 			rsp.cmd = MBOX_CMD_ACK;
@@ -1349,7 +1350,7 @@ static void tegra_xhci_id_work(struct work_struct *work)
 	u32 status;
 	int ret;
 
-	dev_dbg(tegra->dev, "host mode %s\n", tegra->host_mode ? "on" : "off");
+	dev_dbg(tegra->dev, "host mode %s\n", str_on_off(tegra->host_mode));
 
 	mutex_lock(&tegra->lock);
 
@@ -1667,7 +1668,7 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 		goto put_padctl;
 	}
 
-	if (!of_property_read_bool(pdev->dev.of_node, "power-domains")) {
+	if (!of_property_present(pdev->dev.of_node, "power-domains")) {
 		tegra->host_rst = devm_reset_control_get(&pdev->dev,
 							 "xusb_host");
 		if (IS_ERR(tegra->host_rst)) {
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 5ebde8cae4fc..45653114ccd7 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/dmi.h>
 #include <linux/dma-mapping.h>
 
@@ -4523,7 +4524,7 @@ static int xhci_set_usb2_hardware_lpm(struct usb_hcd *hcd,
 	hlpm_addr = ports[port_num]->addr + PORTHLPMC;
 
 	xhci_dbg(xhci, "%s port %d USB2 hardware LPM\n",
-			enable ? "enable" : "disable", port_num + 1);
+		 str_enable_disable(enable), port_num + 1);
 
 	if (enable) {
 		/* Host supports BESL timeout instead of HIRD */
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 4914f0a10cff..8c164340a2c3 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -529,6 +529,7 @@ struct xhci_command {
 	/* Input context for changing device state */
 	struct xhci_container_ctx	*in_ctx;
 	u32				status;
+	u32				comp_param;
 	int				slot_id;
 	/* If completion is null, no one is waiting on this command
 	 * and the structure can be freed after the command completes.
@@ -959,6 +960,9 @@ struct xhci_event_cmd {
 	__le32 flags;
 };
 
+/* status bitmasks */
+#define COMP_PARAM(p)	((p) & 0xffffff) /* Command Completion Parameter */
+
 /* Address device - disable SetAddress */
 #define TRB_BSR		(1<<9)
 
diff --git a/drivers/usb/image/microtek.c b/drivers/usb/image/microtek.c
index 9f758241d9d3..934ec5310fb9 100644
--- a/drivers/usb/image/microtek.c
+++ b/drivers/usb/image/microtek.c
@@ -322,7 +322,7 @@ static inline void mts_urb_abort(struct mts_desc* desc) {
 	usb_kill_urb( desc->urb );
 }
 
-static int mts_slave_alloc (struct scsi_device *s)
+static int mts_sdev_init (struct scsi_device *s)
 {
 	s->inquiry_len = 0x24;
 	return 0;
@@ -626,7 +626,7 @@ static const struct scsi_host_template mts_scsi_host_template = {
 	.this_id =		-1,
 	.emulated =		1,
 	.dma_alignment =	511,
-	.slave_alloc =		mts_slave_alloc,
+	.sdev_init =		mts_sdev_init,
 	.max_sectors=		256, /* 128 K */
 };
 
diff --git a/drivers/usb/mtu3/mtu3_debugfs.c b/drivers/usb/mtu3/mtu3_debugfs.c
index f0de99858353..c003049bafbf 100644
--- a/drivers/usb/mtu3/mtu3_debugfs.c
+++ b/drivers/usb/mtu3/mtu3_debugfs.c
@@ -7,6 +7,7 @@
  * Author: Chunfeng Yun <chunfeng.yun@mediatek.com>
  */
 
+#include <linux/string_choices.h>
 #include <linux/uaccess.h>
 
 #include "mtu3.h"
@@ -256,16 +257,7 @@ static const struct mtu3_file_map mtu3_ep_files[] = {
 
 static int mtu3_ep_open(struct inode *inode, struct file *file)
 {
-	const char *file_name = file_dentry(file)->d_iname;
-	const struct mtu3_file_map *f_map;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mtu3_ep_files); i++) {
-		f_map = &mtu3_ep_files[i];
-
-		if (strcmp(f_map->name, file_name) == 0)
-			break;
-	}
+	const struct mtu3_file_map *f_map = debugfs_get_aux(file);
 
 	return single_open(file, f_map->show, inode->i_private);
 }
@@ -288,17 +280,8 @@ static const struct debugfs_reg32 mtu3_prb_regs[] = {
 
 static int mtu3_probe_show(struct seq_file *sf, void *unused)
 {
-	const char *file_name = file_dentry(sf->file)->d_iname;
 	struct mtu3 *mtu = sf->private;
-	const struct debugfs_reg32 *regs;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(mtu3_prb_regs); i++) {
-		regs = &mtu3_prb_regs[i];
-
-		if (strcmp(regs->name, file_name) == 0)
-			break;
-	}
+	const struct debugfs_reg32 *regs = debugfs_get_aux(sf->file);
 
 	seq_printf(sf, "0x%04x - 0x%08x\n", (u32)regs->offset,
 		   mtu3_readl(mtu->ippc_base, (u32)regs->offset));
@@ -314,13 +297,11 @@ static int mtu3_probe_open(struct inode *inode, struct file *file)
 static ssize_t mtu3_probe_write(struct file *file, const char __user *ubuf,
 				size_t count, loff_t *ppos)
 {
-	const char *file_name = file_dentry(file)->d_iname;
 	struct seq_file *sf = file->private_data;
 	struct mtu3 *mtu = sf->private;
-	const struct debugfs_reg32 *regs;
+	const struct debugfs_reg32 *regs = debugfs_get_aux(file);
 	char buf[32];
 	u32 val;
-	int i;
 
 	if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count)))
 		return -EFAULT;
@@ -328,12 +309,6 @@ static ssize_t mtu3_probe_write(struct file *file, const char __user *ubuf,
 	if (kstrtou32(buf, 0, &val))
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(mtu3_prb_regs); i++) {
-		regs = &mtu3_prb_regs[i];
-
-		if (strcmp(regs->name, file_name) == 0)
-			break;
-	}
 	mtu3_writel(mtu->ippc_base, (u32)regs->offset, val);
 
 	return count;
@@ -358,8 +333,8 @@ static void mtu3_debugfs_create_prb_files(struct mtu3 *mtu)
 
 	for (i = 0; i < ARRAY_SIZE(mtu3_prb_regs); i++) {
 		regs = &mtu3_prb_regs[i];
-		debugfs_create_file(regs->name, 0644, dir_prb,
-				    mtu, &mtu3_probe_fops);
+		debugfs_create_file_aux(regs->name, 0644, dir_prb,
+				    mtu, regs, &mtu3_probe_fops);
 	}
 
 	mtu3_debugfs_regset(mtu, mtu->ippc_base, mtu3_prb_regs,
@@ -379,8 +354,8 @@ static void mtu3_debugfs_create_ep_dir(struct mtu3_ep *mep,
 	for (i = 0; i < ARRAY_SIZE(mtu3_ep_files); i++) {
 		files = &mtu3_ep_files[i];
 
-		debugfs_create_file(files->name, 0444, dir_ep,
-				    mep, &mtu3_ep_fops);
+		debugfs_create_file_aux(files->name, 0444, dir_ep,
+				    mep, files, &mtu3_ep_fops);
 	}
 }
 
@@ -479,7 +454,7 @@ static int ssusb_vbus_show(struct seq_file *sf, void *unused)
 	struct otg_switch_mtk *otg_sx = &ssusb->otg_switch;
 
 	seq_printf(sf, "vbus state: %s\n(echo on/off)\n",
-		   regulator_is_enabled(otg_sx->vbus) ? "on" : "off");
+		   str_on_off(regulator_is_enabled(otg_sx->vbus)));
 
 	return 0;
 }
diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c
index 8191b7ed3852..ffa5b9401dad 100644
--- a/drivers/usb/mtu3/mtu3_dr.c
+++ b/drivers/usb/mtu3/mtu3_dr.c
@@ -7,6 +7,7 @@
  * Author: Chunfeng Yun <chunfeng.yun@mediatek.com>
  */
 
+#include <linux/string_choices.h>
 #include "mtu3.h"
 #include "mtu3_dr.h"
 #include "mtu3_debug.h"
@@ -109,7 +110,7 @@ int ssusb_set_vbus(struct otg_switch_mtk *otg_sx, int is_on)
 	if (!vbus)
 		return 0;
 
-	dev_dbg(ssusb->dev, "%s: turn %s\n", __func__, is_on ? "on" : "off");
+	dev_dbg(ssusb->dev, "%s: turn %s\n", __func__, str_on_off(is_on));
 
 	if (is_on) {
 		ret = regulator_enable(vbus);
diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c
index ad0eeac4332d..bf73fbc29976 100644
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -7,6 +7,7 @@
  * Author: Chunfeng Yun <chunfeng.yun@mediatek.com>
  */
 
+#include <linux/string_choices.h>
 #include "mtu3.h"
 #include "mtu3_trace.h"
 
@@ -490,7 +491,7 @@ static int mtu3_gadget_pullup(struct usb_gadget *gadget, int is_on)
 	unsigned long flags;
 
 	dev_dbg(mtu->dev, "%s (%s) for %sactive device\n", __func__,
-		is_on ? "on" : "off", mtu->is_active ? "" : "in");
+		str_on_off(is_on), mtu->is_active ? "" : "in");
 
 	pm_runtime_get_sync(mtu->dev);
 
diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c
index f772aa272bea..26fd71a5f9b2 100644
--- a/drivers/usb/musb/da8xx.c
+++ b/drivers/usb/musb/da8xx.c
@@ -21,6 +21,7 @@
 #include <linux/of_platform.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/string_choices.h>
 #include <linux/dma-mapping.h>
 #include <linux/usb/usb_phy_generic.h>
 
@@ -306,7 +307,7 @@ static irqreturn_t da8xx_musb_interrupt(int irq, void *hci)
 		}
 
 		dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n",
-				drvvbus ? "on" : "off",
+				str_on_off(drvvbus),
 				usb_otg_state_string(musb->xceiv->otg->state),
 				err ? " ERROR" : "",
 				devctl);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 03b1154a6014..7f349f5e781d 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -72,6 +72,7 @@
 #include <linux/kobject.h>
 #include <linux/prefetch.h>
 #include <linux/platform_device.h>
+#include <linux/string_choices.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
 #include <linux/dma-mapping.h>
@@ -1937,7 +1938,7 @@ vbus_show(struct device *dev, struct device_attribute *attr, char *buf)
 	pm_runtime_put_sync(dev);
 
 	return sprintf(buf, "Vbus %s, timeout %lu msec\n",
-			vbus ? "on" : "off", val);
+			str_on_off(vbus), val);
 }
 static DEVICE_ATTR_RW(vbus);
 
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 2542239ec64e..f877faf5a930 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -24,6 +24,7 @@
 #include <linux/usb/usb_phy_generic.h>
 #include <linux/platform_data/usb-omap.h>
 #include <linux/sizes.h>
+#include <linux/string_choices.h>
 
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -378,7 +379,7 @@ static irqreturn_t dsps_interrupt(int irq, void *hci)
 
 		/* NOTE: this must complete power-on within 100 ms. */
 		dev_dbg(musb->controller, "VBUS %s (%s)%s, devctl %02x\n",
-				drvvbus ? "on" : "off",
+				str_on_off(drvvbus),
 				usb_otg_state_string(musb->xceiv->otg->state),
 				err ? " ERROR" : "",
 				devctl);
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index c6076df0d50c..6869c58367f2 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/smp.h>
 #include <linux/spinlock.h>
+#include <linux/string_choices.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
@@ -1606,7 +1607,7 @@ static void musb_pullup(struct musb *musb, int is_on)
 	/* FIXME if on, HdrcStart; if off, HdrcStop */
 
 	musb_dbg(musb, "gadget D+ pullup %s",
-		is_on ? "on" : "off");
+		str_on_off(is_on));
 	musb_writeb(musb->mregs, MUSB_POWER, power);
 }
 
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index 732ba981e607..6b4481a867c5 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/errno.h>
 #include <linux/list.h>
 #include <linux/dma-mapping.h>
@@ -1028,7 +1029,7 @@ static bool musb_h_ep0_continue(struct musb *musb, u16 len, struct urb *urb)
 					+ urb->actual_length);
 			musb_dbg(musb, "Sending %d byte%s to ep0 fifo %p",
 					fifo_count,
-					(fifo_count == 1) ? "" : "s",
+					str_plural(fifo_count),
 					fifo_dest);
 			musb_write_fifo(hw_ep, fifo_count, fifo_dest);
 
diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c
index 42c42e193232..40ac68e52cee 100644
--- a/drivers/usb/phy/phy-fsl-usb.c
+++ b/drivers/usb/phy/phy-fsl-usb.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/proc_fs.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
@@ -529,7 +530,7 @@ int fsl_otg_start_gadget(struct otg_fsm *fsm, int on)
 	if (!otg->gadget || !otg->gadget->dev.parent)
 		return -ENODEV;
 
-	VDBG("gadget %s\n", on ? "on" : "off");
+	VDBG("gadget %s\n", str_on_off(on));
 	dev = otg->gadget->dev.parent;
 
 	if (on) {
diff --git a/drivers/usb/phy/phy-mv-usb.c b/drivers/usb/phy/phy-mv-usb.c
index a7a102f2e163..30d6c8840a5e 100644
--- a/drivers/usb/phy/phy-mv-usb.c
+++ b/drivers/usb/phy/phy-mv-usb.c
@@ -15,6 +15,7 @@
 #include <linux/clk.h>
 #include <linux/workqueue.h>
 #include <linux/platform_device.h>
+#include <linux/string_choices.h>
 
 #include <linux/usb.h>
 #include <linux/usb/ch9.h>
@@ -217,7 +218,7 @@ static void mv_otg_start_periphrals(struct mv_otg *mvotg, int on)
 	if (!otg->gadget)
 		return;
 
-	dev_info(mvotg->phy.dev, "gadget %s\n", on ? "on" : "off");
+	dev_info(mvotg->phy.dev, "gadget %s\n", str_on_off(on));
 
 	if (on)
 		usb_gadget_vbus_connect(otg->gadget);
diff --git a/drivers/usb/phy/phy-tahvo.c b/drivers/usb/phy/phy-tahvo.c
index ae7bf3ff89ee..88607d0edb01 100644
--- a/drivers/usb/phy/phy-tahvo.c
+++ b/drivers/usb/phy/phy-tahvo.c
@@ -18,6 +18,7 @@
 #include <linux/extcon-provider.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/string_choices.h>
 #include <linux/usb/otg.h>
 #include <linux/mfd/retu.h>
 #include <linux/usb/gadget.h>
@@ -63,7 +64,7 @@ static ssize_t vbus_show(struct device *device,
 			       struct device_attribute *attr, char *buf)
 {
 	struct tahvo_usb *tu = dev_get_drvdata(device);
-	return sprintf(buf, "%s\n", tu->vbus_state ? "on" : "off");
+	return sprintf(buf, "%s\n", str_on_off(tu->vbus_state));
 }
 static DEVICE_ATTR_RO(vbus);
 
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index 1ce134505cee..e1435bc59662 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -346,13 +346,6 @@ static void devm_usb_phy_release2(struct device *dev, void *_res)
 	usb_put_phy(res->phy);
 }
 
-static int devm_usb_phy_match(struct device *dev, void *res, void *match_data)
-{
-	struct usb_phy **phy = res;
-
-	return *phy == match_data;
-}
-
 static void usb_charger_init(struct usb_phy *usb_phy)
 {
 	usb_phy->chg_type = UNKNOWN_TYPE;
@@ -615,25 +608,6 @@ struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev,
 EXPORT_SYMBOL_GPL(devm_usb_get_phy_by_phandle);
 
 /**
- * devm_usb_put_phy - release the USB PHY
- * @dev: device that wants to release this phy
- * @phy: the phy returned by devm_usb_get_phy()
- *
- * destroys the devres associated with this phy and invokes usb_put_phy
- * to release the phy.
- *
- * For use by USB host and peripheral drivers.
- */
-void devm_usb_put_phy(struct device *dev, struct usb_phy *phy)
-{
-	int r;
-
-	r = devres_release(dev, devm_usb_phy_release, devm_usb_phy_match, phy);
-	dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n");
-}
-EXPORT_SYMBOL_GPL(devm_usb_put_phy);
-
-/**
  * usb_put_phy - release the USB PHY
  * @x: the phy returned by usb_get_phy()
  *
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index d10e4c4848a0..7cc36f84821f 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -63,6 +63,7 @@
 #define CH341_REG_DIVISOR      0x13
 #define CH341_REG_LCR          0x18
 #define CH341_REG_LCR2         0x25
+#define CH341_REG_FLOW_CTL     0x27
 
 #define CH341_NBREAK_BITS      0x01
 
@@ -77,6 +78,9 @@
 #define CH341_LCR_CS6          0x01
 #define CH341_LCR_CS5          0x00
 
+#define CH341_FLOW_CTL_NONE    0x00
+#define CH341_FLOW_CTL_RTSCTS  0x01
+
 #define CH341_QUIRK_LIMITED_PRESCALER	BIT(0)
 #define CH341_QUIRK_SIMULATE_BREAK	BIT(1)
 
@@ -478,6 +482,28 @@ err_kill_interrupt_urb:
 	return r;
 }
 
+static void ch341_set_flow_control(struct tty_struct *tty,
+				   struct usb_serial_port *port,
+				   const struct ktermios *old_termios)
+{
+	u16 flow_ctl;
+	int r;
+
+	if (C_CRTSCTS(tty))
+		flow_ctl = CH341_FLOW_CTL_RTSCTS;
+	else
+		flow_ctl = CH341_FLOW_CTL_NONE;
+
+	r = ch341_control_out(port->serial->dev,
+			      CH341_REQ_WRITE_REG,
+			      (CH341_REG_FLOW_CTL << 8) | CH341_REG_FLOW_CTL,
+			      (flow_ctl << 8) | flow_ctl);
+	if (r < 0 && old_termios) {
+		tty->termios.c_cflag &= ~CRTSCTS;
+		tty->termios.c_cflag |= (old_termios->c_cflag & CRTSCTS);
+	}
+}
+
 /* Old_termios contains the original termios settings and
  * tty->termios contains the new setting to be used.
  */
@@ -546,6 +572,8 @@ static void ch341_set_termios(struct tty_struct *tty,
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	ch341_set_handshake(port->serial->dev, priv->mcr);
+
+	ch341_set_flow_control(tty, port, old_termios);
 }
 
 /*
@@ -632,13 +660,12 @@ restore:
 
 static int ch341_break_ctl(struct tty_struct *tty, int break_state)
 {
-	const uint16_t ch341_break_reg =
-			((uint16_t) CH341_REG_LCR << 8) | CH341_REG_BREAK;
+	const u16 ch341_break_reg = (CH341_REG_LCR << 8) | CH341_REG_BREAK;
 	struct usb_serial_port *port = tty->driver_data;
 	struct ch341_private *priv = usb_get_serial_port_data(port);
+	u16 reg_contents;
+	u8 break_reg[2];
 	int r;
-	uint16_t reg_contents;
-	uint8_t break_reg[2];
 
 	if (priv->quirks & CH341_QUIRK_SIMULATE_BREAK)
 		return ch341_simulate_break(tty, break_state);
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
index a317bdbd00ad..72fe83a6c978 100644
--- a/drivers/usb/serial/quatech2.c
+++ b/drivers/usb/serial/quatech2.c
@@ -503,7 +503,7 @@ static void qt2_process_read_urb(struct urb *urb)
 
 				newport = *(ch + 3);
 
-				if (newport > serial->num_ports) {
+				if (newport >= serial->num_ports) {
 					dev_err(&port->dev,
 						"%s - port change to invalid port: %i\n",
 						__func__, newport);
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index d17b60a644ef..4be1d617d63d 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -3,8 +3,7 @@
 # USB Storage driver configuration
 #
 
-comment "NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may"
-comment "also be needed; see USB_STORAGE Help for more info"
+comment "NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed; see USB_STORAGE Help for more info"
 
 config USB_STORAGE
 	tristate "USB Mass Storage support"
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index dc98ceecb724..d2f476e48d0c 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -64,7 +64,7 @@ static const char* host_info(struct Scsi_Host *host)
 	return us->scsi_name;
 }
 
-static int slave_alloc (struct scsi_device *sdev)
+static int sdev_init (struct scsi_device *sdev)
 {
 	struct us_data *us = host_to_us(sdev->host);
 
@@ -88,7 +88,7 @@ static int slave_alloc (struct scsi_device *sdev)
 	return 0;
 }
 
-static int device_configure(struct scsi_device *sdev, struct queue_limits *lim)
+static int sdev_configure(struct scsi_device *sdev, struct queue_limits *lim)
 {
 	struct us_data *us = host_to_us(sdev->host);
 	struct device *dev = us->pusb_dev->bus->sysdev;
@@ -127,7 +127,7 @@ static int device_configure(struct scsi_device *sdev, struct queue_limits *lim)
 		lim->max_hw_sectors, dma_max_mapping_size(dev) >> SECTOR_SHIFT);
 
 	/*
-	 * We can't put these settings in slave_alloc() because that gets
+	 * We can't put these settings in sdev_init() because that gets
 	 * called before the device type is known.  Consequently these
 	 * settings can't be overridden via the scsi devinfo mechanism.
 	 */
@@ -634,8 +634,8 @@ static const struct scsi_host_template usb_stor_host_template = {
 	/* unknown initiator id */
 	.this_id =			-1,
 
-	.slave_alloc =			slave_alloc,
-	.device_configure =		device_configure,
+	.sdev_init =			sdev_init,
+	.sdev_configure =		sdev_configure,
 	.target_alloc =			target_alloc,
 
 	/* lots of sg segments can be handled */
diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c
index 087c706bb315..c33cbf177e6f 100644
--- a/drivers/usb/storage/shuttle_usbat.c
+++ b/drivers/usb/storage/shuttle_usbat.c
@@ -32,6 +32,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/cdrom.h>
 
 #include <scsi/scsi.h>
@@ -651,8 +652,7 @@ static int usbat_hp8200e_rw_block_test(struct us_data *us,
 				return USB_STOR_TRANSPORT_FAILED;
 
 			usb_stor_dbg(us, "Redoing %s\n",
-				     direction == DMA_TO_DEVICE
-				     ? "write" : "read");
+				     str_write_read(direction == DMA_TO_DEVICE));
 
 		} else if (result != USB_STOR_XFER_GOOD)
 			return USB_STOR_TRANSPORT_ERROR;
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 9d767f6bf722..e6bc8ecaecbb 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -1087,13 +1087,9 @@ int usb_stor_Bulk_max_lun(struct us_data *us)
 	usb_stor_dbg(us, "GetMaxLUN command result is %d, data is %d\n",
 		     result, us->iobuf[0]);
 
-	/*
-	 * If we have a successful request, return the result if valid. The
-	 * CBW LUN field is 4 bits wide, so the value reported by the device
-	 * should fit into that.
-	 */
+	/* If we have a successful request, return the result if valid. */
 	if (result > 0) {
-		if (us->iobuf[0] < 16) {
+		if (us->iobuf[0] <= US_BULK_MAX_LUN_LIMIT) {
 			return us->iobuf[0];
 		} else {
 			dev_info(&us->pusb_intf->dev,
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index f9ad90ce7af4..4ed0dc19afe0 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -817,7 +817,7 @@ static int uas_target_alloc(struct scsi_target *starget)
 	return 0;
 }
 
-static int uas_slave_alloc(struct scsi_device *sdev)
+static int uas_sdev_init(struct scsi_device *sdev)
 {
 	struct uas_dev_info *devinfo =
 		(struct uas_dev_info *)sdev->host->hostdata;
@@ -832,8 +832,8 @@ static int uas_slave_alloc(struct scsi_device *sdev)
 	return 0;
 }
 
-static int uas_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim)
+static int uas_sdev_configure(struct scsi_device *sdev,
+			      struct queue_limits *lim)
 {
 	struct uas_dev_info *devinfo = sdev->hostdata;
 
@@ -905,8 +905,8 @@ static const struct scsi_host_template uas_host_template = {
 	.name = "uas",
 	.queuecommand = uas_queuecommand,
 	.target_alloc = uas_target_alloc,
-	.slave_alloc = uas_slave_alloc,
-	.device_configure = uas_device_configure,
+	.sdev_init = uas_sdev_init,
+	.sdev_configure = uas_sdev_configure,
 	.eh_abort_handler = uas_eh_abort_handler,
 	.eh_device_reset_handler = uas_eh_device_reset_handler,
 	.this_id = -1,
diff --git a/drivers/usb/typec/altmodes/Kconfig b/drivers/usb/typec/altmodes/Kconfig
index 1a6b5e872b0d..7867fa7c405d 100644
--- a/drivers/usb/typec/altmodes/Kconfig
+++ b/drivers/usb/typec/altmodes/Kconfig
@@ -23,4 +23,13 @@ config TYPEC_NVIDIA_ALTMODE
 	  To compile this driver as a module, choose M here: the
 	  module will be called typec_nvidia.
 
+config TYPEC_TBT_ALTMODE
+	tristate "Thunderbolt3 Alternate Mode driver"
+	help
+	  Select this option if you have Thunderbolt3 hardware on your
+	  system.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called typec_thunderbolt.
+
 endmenu
diff --git a/drivers/usb/typec/altmodes/Makefile b/drivers/usb/typec/altmodes/Makefile
index 45717548b396..508a68351bd2 100644
--- a/drivers/usb/typec/altmodes/Makefile
+++ b/drivers/usb/typec/altmodes/Makefile
@@ -4,3 +4,5 @@ obj-$(CONFIG_TYPEC_DP_ALTMODE)		+= typec_displayport.o
 typec_displayport-y			:= displayport.o
 obj-$(CONFIG_TYPEC_NVIDIA_ALTMODE)	+= typec_nvidia.o
 typec_nvidia-y				:= nvidia.o
+obj-$(CONFIG_TYPEC_TBT_ALTMODE)		+= typec_thunderbolt.o
+typec_thunderbolt-y			:= thunderbolt.o
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index 2f03190a9873..ac84a6d64c2f 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -252,7 +252,7 @@ static void dp_altmode_work(struct work_struct *work)
 	case DP_STATE_ENTER:
 		ret = typec_altmode_enter(dp->alt, NULL);
 		if (ret && ret != -EBUSY)
-			dev_err(&dp->alt->dev, "failed to enter mode\n");
+			dev_err(&dp->alt->dev, "failed to enter mode: %d\n", ret);
 		break;
 	case DP_STATE_ENTER_PRIME:
 		ret = typec_cable_altmode_enter(dp->alt, TYPEC_PLUG_SOP_P, NULL);
@@ -791,7 +791,7 @@ void dp_altmode_remove(struct typec_altmode *alt)
 EXPORT_SYMBOL_GPL(dp_altmode_remove);
 
 static const struct typec_device_id dp_typec_id[] = {
-	{ USB_TYPEC_DP_SID, USB_TYPEC_DP_MODE },
+	{ USB_TYPEC_DP_SID },
 	{ },
 };
 MODULE_DEVICE_TABLE(typec, dp_typec_id);
diff --git a/drivers/usb/typec/altmodes/nvidia.c b/drivers/usb/typec/altmodes/nvidia.c
index fe70b36f078f..2b77d931e494 100644
--- a/drivers/usb/typec/altmodes/nvidia.c
+++ b/drivers/usb/typec/altmodes/nvidia.c
@@ -24,7 +24,7 @@ static void nvidia_altmode_remove(struct typec_altmode *alt)
 }
 
 static const struct typec_device_id nvidia_typec_id[] = {
-	{ USB_TYPEC_NVIDIA_VLINK_SID, TYPEC_ANY_MODE },
+	{ USB_TYPEC_NVIDIA_VLINK_SID },
 	{ },
 };
 MODULE_DEVICE_TABLE(typec, nvidia_typec_id);
diff --git a/drivers/usb/typec/altmodes/thunderbolt.c b/drivers/usb/typec/altmodes/thunderbolt.c
new file mode 100644
index 000000000000..1b475b1d98e7
--- /dev/null
+++ b/drivers/usb/typec/altmodes/thunderbolt.c
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * USB Typec-C Thunderbolt3 Alternate Mode driver
+ *
+ * Copyright (C) 2019 Intel Corporation
+ * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com>
+ */
+
+#include <linux/lockdep.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/usb/pd_vdo.h>
+#include <linux/usb/typec_altmode.h>
+#include <linux/usb/typec_tbt.h>
+
+enum tbt_state {
+	TBT_STATE_IDLE,
+	TBT_STATE_SOP_P_ENTER,
+	TBT_STATE_SOP_PP_ENTER,
+	TBT_STATE_ENTER,
+	TBT_STATE_EXIT,
+	TBT_STATE_SOP_PP_EXIT,
+	TBT_STATE_SOP_P_EXIT
+};
+
+struct tbt_altmode {
+	enum tbt_state state;
+	struct typec_cable *cable;
+	struct typec_altmode *alt;
+	struct typec_altmode *plug[2];
+	u32 enter_vdo;
+
+	struct work_struct work;
+	struct mutex lock; /* device lock */
+};
+
+static bool tbt_ready(struct typec_altmode *alt);
+
+static int tbt_enter_mode(struct tbt_altmode *tbt)
+{
+	struct typec_altmode *plug = tbt->plug[TYPEC_PLUG_SOP_P];
+	u32 vdo;
+
+	vdo = tbt->alt->vdo & (TBT_VENDOR_SPECIFIC_B0 | TBT_VENDOR_SPECIFIC_B1);
+	vdo |= tbt->alt->vdo & TBT_INTEL_SPECIFIC_B0;
+	vdo |= TBT_MODE;
+
+	if (plug) {
+		if (typec_cable_is_active(tbt->cable))
+			vdo |= TBT_ENTER_MODE_ACTIVE_CABLE;
+
+		vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_SPEED(plug->vdo));
+		vdo |= plug->vdo & TBT_CABLE_ROUNDED;
+		vdo |= plug->vdo & TBT_CABLE_OPTICAL;
+		vdo |= plug->vdo & TBT_CABLE_RETIMER;
+		vdo |= plug->vdo & TBT_CABLE_LINK_TRAINING;
+	} else {
+		vdo |= TBT_ENTER_MODE_CABLE_SPEED(TBT_CABLE_USB3_PASSIVE);
+	}
+
+	tbt->enter_vdo = vdo;
+	return typec_altmode_enter(tbt->alt, &vdo);
+}
+
+static void tbt_altmode_work(struct work_struct *work)
+{
+	struct tbt_altmode *tbt = container_of(work, struct tbt_altmode, work);
+	int ret;
+
+	mutex_lock(&tbt->lock);
+
+	switch (tbt->state) {
+	case TBT_STATE_SOP_P_ENTER:
+		ret = typec_cable_altmode_enter(tbt->alt, TYPEC_PLUG_SOP_P, NULL);
+		if (ret) {
+			dev_dbg(&tbt->plug[TYPEC_PLUG_SOP_P]->dev,
+				"failed to enter mode (%d)\n", ret);
+			goto disable_plugs;
+		}
+		break;
+	case TBT_STATE_SOP_PP_ENTER:
+		ret = typec_cable_altmode_enter(tbt->alt, TYPEC_PLUG_SOP_PP,  NULL);
+		if (ret) {
+			dev_dbg(&tbt->plug[TYPEC_PLUG_SOP_PP]->dev,
+				"failed to enter mode (%d)\n", ret);
+			goto disable_plugs;
+		}
+		break;
+	case TBT_STATE_ENTER:
+		ret = tbt_enter_mode(tbt);
+		if (ret)
+			dev_dbg(&tbt->alt->dev, "failed to enter mode (%d)\n",
+				ret);
+		break;
+	case TBT_STATE_EXIT:
+		typec_altmode_exit(tbt->alt);
+		break;
+	case TBT_STATE_SOP_PP_EXIT:
+		typec_cable_altmode_exit(tbt->alt, TYPEC_PLUG_SOP_PP);
+		break;
+	case TBT_STATE_SOP_P_EXIT:
+		typec_cable_altmode_exit(tbt->alt, TYPEC_PLUG_SOP_P);
+		break;
+	default:
+		break;
+	}
+
+	tbt->state = TBT_STATE_IDLE;
+
+	mutex_unlock(&tbt->lock);
+	return;
+
+disable_plugs:
+	for (int i = TYPEC_PLUG_SOP_PP; i > 0; --i) {
+		if (tbt->plug[i])
+			typec_altmode_put_plug(tbt->plug[i]);
+
+		tbt->plug[i] = NULL;
+	}
+
+	tbt->state = TBT_STATE_ENTER;
+	schedule_work(&tbt->work);
+	mutex_unlock(&tbt->lock);
+}
+
+/*
+ * If SOP' is available, enter that first (which will trigger a VDM response
+ * that will enter SOP" if available and then the port). If entering SOP' fails,
+ * stop attempting to enter either cable altmode (probably not supported) and
+ * directly enter the port altmode.
+ */
+static int tbt_enter_modes_ordered(struct typec_altmode *alt)
+{
+	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
+	int ret = 0;
+
+	lockdep_assert_held(&tbt->lock);
+
+	if (!tbt_ready(tbt->alt))
+		return -ENODEV;
+
+	if (tbt->plug[TYPEC_PLUG_SOP_P]) {
+		ret = typec_cable_altmode_enter(alt, TYPEC_PLUG_SOP_P, NULL);
+		if (ret < 0) {
+			for (int i = TYPEC_PLUG_SOP_PP; i > 0; --i) {
+				if (tbt->plug[i])
+					typec_altmode_put_plug(tbt->plug[i]);
+
+				tbt->plug[i] = NULL;
+			}
+		} else {
+			return ret;
+		}
+	}
+
+	return tbt_enter_mode(tbt);
+}
+
+static int tbt_cable_altmode_vdm(struct typec_altmode *alt,
+				 enum typec_plug_index sop, const u32 hdr,
+				 const u32 *vdo, int count)
+{
+	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
+	int cmd_type = PD_VDO_CMDT(hdr);
+	int cmd = PD_VDO_CMD(hdr);
+
+	mutex_lock(&tbt->lock);
+
+	if (tbt->state != TBT_STATE_IDLE) {
+		mutex_unlock(&tbt->lock);
+		return -EBUSY;
+	}
+
+	switch (cmd_type) {
+	case CMDT_RSP_ACK:
+		switch (cmd) {
+		case CMD_ENTER_MODE:
+			/*
+			 * Following the order described in USB Type-C Spec
+			 * R2.0 Section 6.7.3: SOP', SOP", then port.
+			 */
+			if (sop == TYPEC_PLUG_SOP_P) {
+				if (tbt->plug[TYPEC_PLUG_SOP_PP])
+					tbt->state = TBT_STATE_SOP_PP_ENTER;
+				else
+					tbt->state = TBT_STATE_ENTER;
+			} else if (sop == TYPEC_PLUG_SOP_PP)
+				tbt->state = TBT_STATE_ENTER;
+
+			break;
+		case CMD_EXIT_MODE:
+			/* Exit in opposite order: Port, SOP", then SOP'. */
+			if (sop == TYPEC_PLUG_SOP_PP)
+				tbt->state = TBT_STATE_SOP_P_EXIT;
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	if (tbt->state != TBT_STATE_IDLE)
+		schedule_work(&tbt->work);
+
+	mutex_unlock(&tbt->lock);
+	return 0;
+}
+
+static int tbt_altmode_vdm(struct typec_altmode *alt,
+			   const u32 hdr, const u32 *vdo, int count)
+{
+	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
+	struct typec_thunderbolt_data data;
+	int cmd_type = PD_VDO_CMDT(hdr);
+	int cmd = PD_VDO_CMD(hdr);
+
+	mutex_lock(&tbt->lock);
+
+	if (tbt->state != TBT_STATE_IDLE) {
+		mutex_unlock(&tbt->lock);
+		return -EBUSY;
+	}
+
+	switch (cmd_type) {
+	case CMDT_RSP_ACK:
+		/* Port altmode is last to enter and first to exit. */
+		switch (cmd) {
+		case CMD_ENTER_MODE:
+			memset(&data, 0, sizeof(data));
+
+			data.device_mode = tbt->alt->vdo;
+			data.enter_vdo = tbt->enter_vdo;
+			if (tbt->plug[TYPEC_PLUG_SOP_P])
+				data.cable_mode = tbt->plug[TYPEC_PLUG_SOP_P]->vdo;
+
+			typec_altmode_notify(alt, TYPEC_STATE_MODAL, &data);
+			break;
+		case CMD_EXIT_MODE:
+			if (tbt->plug[TYPEC_PLUG_SOP_PP])
+				tbt->state = TBT_STATE_SOP_PP_EXIT;
+			else if (tbt->plug[TYPEC_PLUG_SOP_P])
+				tbt->state = TBT_STATE_SOP_P_EXIT;
+			break;
+		}
+		break;
+	case CMDT_RSP_NAK:
+		switch (cmd) {
+		case CMD_ENTER_MODE:
+			dev_warn(&alt->dev, "Enter Mode refused\n");
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	if (tbt->state != TBT_STATE_IDLE)
+		schedule_work(&tbt->work);
+
+	mutex_unlock(&tbt->lock);
+
+	return 0;
+}
+
+static int tbt_altmode_activate(struct typec_altmode *alt, int activate)
+{
+	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
+	int ret;
+
+	mutex_lock(&tbt->lock);
+
+	if (activate)
+		ret = tbt_enter_modes_ordered(alt);
+	else
+		ret = typec_altmode_exit(alt);
+
+	mutex_unlock(&tbt->lock);
+
+	return ret;
+}
+
+static const struct typec_altmode_ops tbt_altmode_ops = {
+	.vdm		= tbt_altmode_vdm,
+	.activate	= tbt_altmode_activate
+};
+
+static const struct typec_cable_ops tbt_cable_ops = {
+	.vdm		= tbt_cable_altmode_vdm,
+};
+
+static int tbt_altmode_probe(struct typec_altmode *alt)
+{
+	struct tbt_altmode *tbt;
+
+	tbt = devm_kzalloc(&alt->dev, sizeof(*tbt), GFP_KERNEL);
+	if (!tbt)
+		return -ENOMEM;
+
+	INIT_WORK(&tbt->work, tbt_altmode_work);
+	mutex_init(&tbt->lock);
+	tbt->alt = alt;
+
+	alt->desc = "Thunderbolt3";
+	typec_altmode_set_drvdata(alt, tbt);
+	typec_altmode_set_ops(alt, &tbt_altmode_ops);
+
+	if (tbt_ready(alt)) {
+		if (tbt->plug[TYPEC_PLUG_SOP_P])
+			tbt->state = TBT_STATE_SOP_P_ENTER;
+		else if (tbt->plug[TYPEC_PLUG_SOP_PP])
+			tbt->state = TBT_STATE_SOP_PP_ENTER;
+		else
+			tbt->state = TBT_STATE_ENTER;
+		schedule_work(&tbt->work);
+	}
+
+	return 0;
+}
+
+static void tbt_altmode_remove(struct typec_altmode *alt)
+{
+	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
+
+	for (int i = TYPEC_PLUG_SOP_PP; i > 0; --i) {
+		if (tbt->plug[i])
+			typec_altmode_put_plug(tbt->plug[i]);
+	}
+
+	if (tbt->cable)
+		typec_cable_put(tbt->cable);
+}
+
+static bool tbt_ready(struct typec_altmode *alt)
+{
+	struct tbt_altmode *tbt = typec_altmode_get_drvdata(alt);
+	struct typec_altmode *plug;
+
+	if (tbt->cable)
+		return true;
+
+	/* Thunderbolt 3 requires a cable with eMarker */
+	tbt->cable = typec_cable_get(typec_altmode2port(tbt->alt));
+	if (!tbt->cable)
+		return false;
+
+	/* We accept systems without SOP' or SOP''. This means the port altmode
+	 * driver will be responsible for properly ordering entry/exit.
+	 */
+	for (int i = 0; i < TYPEC_PLUG_SOP_PP + 1; i++) {
+		plug = typec_altmode_get_plug(tbt->alt, i);
+		if (IS_ERR(plug))
+			continue;
+
+		if (!plug || plug->svid != USB_TYPEC_TBT_SID)
+			break;
+
+		plug->desc = "Thunderbolt3";
+		plug->cable_ops = &tbt_cable_ops;
+		typec_altmode_set_drvdata(plug, tbt);
+
+		tbt->plug[i] = plug;
+	}
+
+	return true;
+}
+
+static const struct typec_device_id tbt_typec_id[] = {
+	{ USB_TYPEC_TBT_SID },
+	{ }
+};
+MODULE_DEVICE_TABLE(typec, tbt_typec_id);
+
+static struct typec_altmode_driver tbt_altmode_driver = {
+	.id_table = tbt_typec_id,
+	.probe = tbt_altmode_probe,
+	.remove = tbt_altmode_remove,
+	.driver = {
+		.name = "typec-thunderbolt",
+	}
+};
+module_typec_altmode_driver(tbt_altmode_driver);
+
+MODULE_AUTHOR("Heikki Krogerus <heikki.krogerus@linux.intel.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Thunderbolt3 USB Type-C Alternate Mode");
diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c
index aa879253d3b8..ae90688d23e4 100644
--- a/drivers/usb/typec/bus.c
+++ b/drivers/usb/typec/bus.c
@@ -454,8 +454,7 @@ static int typec_match(struct device *dev, const struct device_driver *driver)
 	const struct typec_device_id *id;
 
 	for (id = drv->id_table; id->svid; id++)
-		if (id->svid == altmode->svid &&
-		    (id->mode == TYPEC_ANY_MODE || id->mode == altmode->mode))
+		if (id->svid == altmode->svid)
 			return 1;
 	return 0;
 }
@@ -470,8 +469,7 @@ static int typec_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	if (add_uevent_var(env, "MODE=%u", altmode->mode))
 		return -ENOMEM;
 
-	return add_uevent_var(env, "MODALIAS=typec:id%04Xm%02X",
-			      altmode->svid, altmode->mode);
+	return add_uevent_var(env, "MODALIAS=typec:id%04X", altmode->svid);
 }
 
 static int typec_altmode_create_links(struct altmode *alt)
diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c
index 4b3047e055a3..9c76c3d0c6cf 100644
--- a/drivers/usb/typec/class.c
+++ b/drivers/usb/typec/class.c
@@ -10,6 +10,7 @@
 #include <linux/mutex.h>
 #include <linux/property.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/usb/pd_vdo.h>
 #include <linux/usb/typec_mux.h>
 #include <linux/usb/typec_retimer.h>
@@ -229,21 +230,21 @@ static const char * const usb_modes[] = {
 /* ------------------------------------------------------------------------- */
 /* Alternate Modes */
 
-static int altmode_match(struct device *dev, void *data)
+static int altmode_match(struct device *dev, const void *data)
 {
 	struct typec_altmode *adev = to_typec_altmode(dev);
-	struct typec_device_id *id = data;
+	const struct typec_device_id *id = data;
 
 	if (!is_typec_altmode(dev))
 		return 0;
 
-	return ((adev->svid == id->svid) && (adev->mode == id->mode));
+	return (adev->svid == id->svid);
 }
 
 static void typec_altmode_set_partner(struct altmode *altmode)
 {
 	struct typec_altmode *adev = &altmode->adev;
-	struct typec_device_id id = { adev->svid, adev->mode, };
+	struct typec_device_id id = { adev->svid };
 	struct typec_port *port = typec_altmode2port(adev);
 	struct altmode *partner;
 	struct device *dev;
@@ -361,7 +362,7 @@ active_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct typec_altmode *alt = to_typec_altmode(dev);
 
-	return sprintf(buf, "%s\n", alt->active ? "yes" : "no");
+	return sprintf(buf, "%s\n", str_yes_no(alt->active));
 }
 
 static ssize_t active_store(struct device *dev, struct device_attribute *attr,
@@ -458,7 +459,8 @@ static umode_t typec_altmode_attr_is_visible(struct kobject *kobj,
 	struct typec_altmode *adev = to_typec_altmode(kobj_to_dev(kobj));
 
 	if (attr == &dev_attr_active.attr)
-		if (!adev->ops || !adev->ops->activate)
+		if (!is_typec_port(adev->dev.parent) &&
+		    (!adev->ops || !adev->ops->activate))
 			return 0444;
 
 	return attr->mode;
@@ -563,7 +565,7 @@ typec_register_altmode(struct device *parent,
 
 	if (is_port) {
 		alt->attrs[3] = &dev_attr_supported_roles.attr;
-		alt->adev.active = true; /* Enabled by default */
+		alt->adev.active = !desc->inactive; /* Enabled by default */
 	}
 
 	sprintf(alt->group_name, "mode%d", desc->mode);
@@ -706,7 +708,7 @@ static ssize_t supports_usb_power_delivery_show(struct device *dev,
 {
 	struct typec_partner *p = to_typec_partner(dev);
 
-	return sprintf(buf, "%s\n", p->usb_pd ? "yes" : "no");
+	return sprintf(buf, "%s\n", str_yes_no(p->usb_pd));
 }
 static DEVICE_ATTR_RO(supports_usb_power_delivery);
 
@@ -1282,11 +1284,6 @@ const struct device_type typec_cable_dev_type = {
 	.release = typec_cable_release,
 };
 
-static int cable_match(struct device *dev, void *data)
-{
-	return is_typec_cable(dev);
-}
-
 /**
  * typec_cable_get - Get a reference to the USB Type-C cable
  * @port: The USB Type-C Port the cable is connected to
@@ -1298,7 +1295,8 @@ struct typec_cable *typec_cable_get(struct typec_port *port)
 {
 	struct device *dev;
 
-	dev = device_find_child(&port->dev, NULL, cable_match);
+	dev = device_find_child(&port->dev, &typec_cable_dev_type,
+				device_match_type);
 	if (!dev)
 		return NULL;
 
@@ -1858,7 +1856,7 @@ static ssize_t vconn_source_show(struct device *dev,
 	struct typec_port *port = to_typec_port(dev);
 
 	return sprintf(buf, "%s\n",
-		       port->vconn_role == TYPEC_SOURCE ? "yes" : "no");
+		       str_yes_no(port->vconn_role == TYPEC_SOURCE));
 }
 static DEVICE_ATTR_RW(vconn_source);
 
@@ -2028,16 +2026,12 @@ const struct device_type typec_port_dev_type = {
 /* --------------------------------------- */
 /* Driver callbacks to report role updates */
 
-static int partner_match(struct device *dev, void *data)
-{
-	return is_typec_partner(dev);
-}
-
 static struct typec_partner *typec_get_partner(struct typec_port *port)
 {
 	struct device *dev;
 
-	dev = device_find_child(&port->dev, NULL, partner_match);
+	dev = device_find_child(&port->dev, &typec_partner_dev_type,
+				device_match_type);
 	if (!dev)
 		return NULL;
 
@@ -2170,7 +2164,9 @@ void typec_set_pwr_opmode(struct typec_port *port,
 	sysfs_notify(&port->dev.kobj, NULL, "power_operation_mode");
 	kobject_uevent(&port->dev.kobj, KOBJ_CHANGE);
 
-	partner_dev = device_find_child(&port->dev, NULL, partner_match);
+	partner_dev = device_find_child(&port->dev,
+					&typec_partner_dev_type,
+					device_match_type);
 	if (partner_dev) {
 		struct typec_partner *partner = to_typec_partner(partner_dev);
 
@@ -2334,7 +2330,9 @@ int typec_get_negotiated_svdm_version(struct typec_port *port)
 	enum usb_pd_svdm_ver svdm_version;
 	struct device *partner_dev;
 
-	partner_dev = device_find_child(&port->dev, NULL, partner_match);
+	partner_dev = device_find_child(&port->dev,
+					&typec_partner_dev_type,
+					device_match_type);
 	if (!partner_dev)
 		return -ENODEV;
 
@@ -2361,7 +2359,8 @@ int typec_get_cable_svdm_version(struct typec_port *port)
 	enum usb_pd_svdm_ver svdm_version;
 	struct device *cable_dev;
 
-	cable_dev = device_find_child(&port->dev, NULL, cable_match);
+	cable_dev = device_find_child(&port->dev, &typec_cable_dev_type,
+				      device_match_type);
 	if (!cable_dev)
 		return -ENODEV;
 
diff --git a/drivers/usb/typec/hd3ss3220.c b/drivers/usb/typec/hd3ss3220.c
index fb1242e82ffd..3ecc688dda82 100644
--- a/drivers/usb/typec/hd3ss3220.c
+++ b/drivers/usb/typec/hd3ss3220.c
@@ -16,10 +16,17 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 
+#define HD3SS3220_REG_CN_STAT		0x08
 #define HD3SS3220_REG_CN_STAT_CTRL	0x09
 #define HD3SS3220_REG_GEN_CTRL		0x0A
 #define HD3SS3220_REG_DEV_REV		0xA0
 
+/* Register HD3SS3220_REG_CN_STAT */
+#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_MASK		(BIT(7) | BIT(6))
+#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_DEFAULT	0x00
+#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_MID		BIT(6)
+#define HD3SS3220_REG_CN_STAT_CURRENT_MODE_HIGH		BIT(7)
+
 /* Register HD3SS3220_REG_CN_STAT_CTRL*/
 #define HD3SS3220_REG_CN_STAT_CTRL_ATTACHED_STATE_MASK	(BIT(7) | BIT(6))
 #define HD3SS3220_REG_CN_STAT_CTRL_AS_DFP		BIT(6)
@@ -28,10 +35,16 @@
 #define HD3SS3220_REG_CN_STAT_CTRL_INT_STATUS		BIT(4)
 
 /* Register HD3SS3220_REG_GEN_CTRL*/
+#define HD3SS3220_REG_GEN_CTRL_DISABLE_TERM		BIT(0)
 #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_MASK		(BIT(2) | BIT(1))
 #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT	0x00
 #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SNK	BIT(1)
 #define HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SRC	(BIT(2) | BIT(1))
+#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_MASK		(BIT(5) | BIT(4))
+#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DEFAULT	0x00
+#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DFP		BIT(5)
+#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_UFP		BIT(4)
+#define HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DRP		(BIT(5) | BIT(4))
 
 struct hd3ss3220 {
 	struct device *dev;
@@ -43,8 +56,96 @@ struct hd3ss3220 {
 	bool poll;
 };
 
-static int hd3ss3220_set_source_pref(struct hd3ss3220 *hd3ss3220, int src_pref)
+static int hd3ss3220_set_power_opmode(struct hd3ss3220 *hd3ss3220, int power_opmode)
+{
+	int current_mode;
+
+	switch (power_opmode) {
+	case TYPEC_PWR_MODE_USB:
+		current_mode = HD3SS3220_REG_CN_STAT_CURRENT_MODE_DEFAULT;
+		break;
+	case TYPEC_PWR_MODE_1_5A:
+		current_mode = HD3SS3220_REG_CN_STAT_CURRENT_MODE_MID;
+		break;
+	case TYPEC_PWR_MODE_3_0A:
+		current_mode = HD3SS3220_REG_CN_STAT_CURRENT_MODE_HIGH;
+		break;
+	case TYPEC_PWR_MODE_PD: /* Power delivery not supported */
+	default:
+		dev_err(hd3ss3220->dev, "bad power operation mode: %d\n", power_opmode);
+		return -EINVAL;
+	}
+
+	return regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_CN_STAT,
+				  HD3SS3220_REG_CN_STAT_CURRENT_MODE_MASK,
+				  current_mode);
+}
+
+static int hd3ss3220_set_port_type(struct hd3ss3220 *hd3ss3220, int type)
+{
+	int mode_select, err;
+
+	switch (type) {
+	case TYPEC_PORT_SRC:
+		mode_select = HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DFP;
+		break;
+	case TYPEC_PORT_SNK:
+		mode_select = HD3SS3220_REG_GEN_CTRL_MODE_SELECT_UFP;
+		break;
+	case TYPEC_PORT_DRP:
+		mode_select = HD3SS3220_REG_GEN_CTRL_MODE_SELECT_DRP;
+		break;
+	default:
+		dev_err(hd3ss3220->dev, "bad port type: %d\n", type);
+		return -EINVAL;
+	}
+
+	/* Disable termination before changing MODE_SELECT as required by datasheet */
+	err = regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL,
+				 HD3SS3220_REG_GEN_CTRL_DISABLE_TERM,
+				 HD3SS3220_REG_GEN_CTRL_DISABLE_TERM);
+	if (err < 0) {
+		dev_err(hd3ss3220->dev, "Failed to disable port for mode change: %d\n", err);
+		return err;
+	}
+
+	err = regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL,
+				 HD3SS3220_REG_GEN_CTRL_MODE_SELECT_MASK,
+				 mode_select);
+	if (err < 0) {
+		dev_err(hd3ss3220->dev, "Failed to change mode: %d\n", err);
+		regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL,
+				   HD3SS3220_REG_GEN_CTRL_DISABLE_TERM, 0);
+		return err;
+	}
+
+	err = regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL,
+				 HD3SS3220_REG_GEN_CTRL_DISABLE_TERM, 0);
+	if (err < 0)
+		dev_err(hd3ss3220->dev, "Failed to re-enable port after mode change: %d\n", err);
+
+	return err;
+}
+
+static int hd3ss3220_set_source_pref(struct hd3ss3220 *hd3ss3220, int prefer_role)
 {
+	int src_pref;
+
+	switch (prefer_role) {
+	case TYPEC_NO_PREFERRED_ROLE:
+		src_pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT;
+		break;
+	case TYPEC_SINK:
+		src_pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SNK;
+		break;
+	case TYPEC_SOURCE:
+		src_pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SRC;
+		break;
+	default:
+		dev_err(hd3ss3220->dev, "bad role preference: %d\n", prefer_role);
+		return -EINVAL;
+	}
+
 	return regmap_update_bits(hd3ss3220->regmap, HD3SS3220_REG_GEN_CTRL,
 				  HD3SS3220_REG_GEN_CTRL_SRC_PREF_MASK,
 				  src_pref);
@@ -76,31 +177,23 @@ static enum usb_role hd3ss3220_get_attached_state(struct hd3ss3220 *hd3ss3220)
 	return attached_state;
 }
 
-static int hd3ss3220_dr_set(struct typec_port *port, enum typec_data_role role)
+static int hd3ss3220_try_role(struct typec_port *port, int role)
 {
 	struct hd3ss3220 *hd3ss3220 = typec_get_drvdata(port);
-	enum usb_role role_val;
-	int pref, ret = 0;
 
-	if (role == TYPEC_HOST) {
-		role_val = USB_ROLE_HOST;
-		pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SRC;
-	} else {
-		role_val = USB_ROLE_DEVICE;
-		pref = HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_TRY_SNK;
-	}
-
-	ret = hd3ss3220_set_source_pref(hd3ss3220, pref);
-	usleep_range(10, 100);
+	return hd3ss3220_set_source_pref(hd3ss3220, role);
+}
 
-	usb_role_switch_set_role(hd3ss3220->role_sw, role_val);
-	typec_set_data_role(hd3ss3220->port, role);
+static int hd3ss3220_port_type_set(struct typec_port *port, enum typec_port_type type)
+{
+	struct hd3ss3220 *hd3ss3220 = typec_get_drvdata(port);
 
-	return ret;
+	return hd3ss3220_set_port_type(hd3ss3220, type);
 }
 
 static const struct typec_operations hd3ss3220_ops = {
-	.dr_set = hd3ss3220_dr_set
+	.try_role = hd3ss3220_try_role,
+	.port_type_set = hd3ss3220_port_type_set,
 };
 
 static void hd3ss3220_set_role(struct hd3ss3220 *hd3ss3220)
@@ -108,9 +201,6 @@ static void hd3ss3220_set_role(struct hd3ss3220 *hd3ss3220)
 	enum usb_role role_state = hd3ss3220_get_attached_state(hd3ss3220);
 
 	usb_role_switch_set_role(hd3ss3220->role_sw, role_state);
-	if (role_state == USB_ROLE_NONE)
-		hd3ss3220_set_source_pref(hd3ss3220,
-				HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT);
 
 	switch (role_state) {
 	case USB_ROLE_HOST:
@@ -162,6 +252,67 @@ static irqreturn_t hd3ss3220_irq_handler(int irq, void *data)
 	return hd3ss3220_irq(hd3ss3220);
 }
 
+static int hd3ss3220_configure_power_opmode(struct hd3ss3220 *hd3ss3220,
+					    struct fwnode_handle *connector)
+{
+	/*
+	 * Supported power operation mode can be configured through device tree
+	 */
+	const char *cap_str;
+	int ret, power_opmode;
+
+	ret = fwnode_property_read_string(connector, "typec-power-opmode", &cap_str);
+	if (ret)
+		return 0;
+
+	power_opmode = typec_find_pwr_opmode(cap_str);
+	return hd3ss3220_set_power_opmode(hd3ss3220, power_opmode);
+}
+
+static int hd3ss3220_configure_port_type(struct hd3ss3220 *hd3ss3220,
+					 struct fwnode_handle *connector,
+					 struct typec_capability *cap)
+{
+	/*
+	 * Port type can be configured through device tree
+	 */
+	const char *cap_str;
+	int ret;
+
+	ret = fwnode_property_read_string(connector, "power-role", &cap_str);
+	if (ret)
+		return 0;
+
+	ret = typec_find_port_power_role(cap_str);
+	if (ret < 0)
+		return ret;
+
+	cap->type = ret;
+	return hd3ss3220_set_port_type(hd3ss3220, cap->type);
+}
+
+static int hd3ss3220_configure_source_pref(struct hd3ss3220 *hd3ss3220,
+					   struct fwnode_handle *connector,
+					   struct typec_capability *cap)
+{
+	/*
+	 * Preferred role can be configured through device tree
+	 */
+	const char *cap_str;
+	int ret;
+
+	ret = fwnode_property_read_string(connector, "try-power-role", &cap_str);
+	if (ret)
+		return 0;
+
+	ret = typec_find_power_role(cap_str);
+	if (ret < 0)
+		return ret;
+
+	cap->prefer_role = ret;
+	return hd3ss3220_set_source_pref(hd3ss3220, cap->prefer_role);
+}
+
 static const struct regmap_config config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -188,8 +339,6 @@ static int hd3ss3220_probe(struct i2c_client *client)
 	if (IS_ERR(hd3ss3220->regmap))
 		return PTR_ERR(hd3ss3220->regmap);
 
-	hd3ss3220_set_source_pref(hd3ss3220,
-				  HD3SS3220_REG_GEN_CTRL_SRC_PREF_DRP_DEFAULT);
 	/* For backward compatibility check the connector child node first */
 	connector = device_get_named_child_node(hd3ss3220->dev, "connector");
 	if (connector) {
@@ -217,12 +366,24 @@ static int hd3ss3220_probe(struct i2c_client *client)
 	typec_cap.ops = &hd3ss3220_ops;
 	typec_cap.fwnode = connector;
 
+	ret = hd3ss3220_configure_source_pref(hd3ss3220, connector, &typec_cap);
+	if (ret < 0)
+		goto err_put_role;
+
+	ret = hd3ss3220_configure_port_type(hd3ss3220, connector, &typec_cap);
+	if (ret < 0)
+		goto err_put_role;
+
 	hd3ss3220->port = typec_register_port(&client->dev, &typec_cap);
 	if (IS_ERR(hd3ss3220->port)) {
 		ret = PTR_ERR(hd3ss3220->port);
 		goto err_put_role;
 	}
 
+	ret = hd3ss3220_configure_power_opmode(hd3ss3220, connector);
+	if (ret < 0)
+		goto err_unreg_port;
+
 	hd3ss3220_set_role(hd3ss3220);
 	ret = regmap_read(hd3ss3220->regmap, HD3SS3220_REG_CN_STAT_CTRL, &data);
 	if (ret < 0)
diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c
index 5dfe95754394..65dda9183e6f 100644
--- a/drivers/usb/typec/mux/intel_pmc_mux.c
+++ b/drivers/usb/typec/mux/intel_pmc_mux.c
@@ -718,7 +718,7 @@ DEFINE_SHOW_ATTRIBUTE(port_iom_status);
 static void pmc_mux_port_debugfs_init(struct pmc_usb_port *port)
 {
 	struct dentry *debugfs_dir;
-	char name[6];
+	char name[8];
 
 	snprintf(name, sizeof(name), "port%d", port->usb3_port - 1);
 
diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c
index e2fe479e16ad..f15c63d3a8f4 100644
--- a/drivers/usb/typec/tcpm/fusb302.c
+++ b/drivers/usb/typec/tcpm/fusb302.c
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/types.h>
 #include <linux/usb.h>
 #include <linux/usb/typec.h>
@@ -733,7 +734,7 @@ static int tcpm_set_vconn(struct tcpc_dev *dev, bool on)
 
 	mutex_lock(&chip->lock);
 	if (chip->vconn_on == on) {
-		fusb302_log(chip, "vconn is already %s", on ? "On" : "Off");
+		fusb302_log(chip, "vconn is already %s", str_on_off(on));
 		goto done;
 	}
 	if (on) {
@@ -746,7 +747,7 @@ static int tcpm_set_vconn(struct tcpc_dev *dev, bool on)
 	if (ret < 0)
 		goto done;
 	chip->vconn_on = on;
-	fusb302_log(chip, "vconn := %s", on ? "On" : "Off");
+	fusb302_log(chip, "vconn := %s", str_on_off(on));
 done:
 	mutex_unlock(&chip->lock);
 
@@ -761,7 +762,7 @@ static int tcpm_set_vbus(struct tcpc_dev *dev, bool on, bool charge)
 
 	mutex_lock(&chip->lock);
 	if (chip->vbus_on == on) {
-		fusb302_log(chip, "vbus is already %s", on ? "On" : "Off");
+		fusb302_log(chip, "vbus is already %s", str_on_off(on));
 	} else {
 		if (on)
 			ret = regulator_enable(chip->vbus);
@@ -769,15 +770,14 @@ static int tcpm_set_vbus(struct tcpc_dev *dev, bool on, bool charge)
 			ret = regulator_disable(chip->vbus);
 		if (ret < 0) {
 			fusb302_log(chip, "cannot %s vbus regulator, ret=%d",
-				    on ? "enable" : "disable", ret);
+				    str_enable_disable(on), ret);
 			goto done;
 		}
 		chip->vbus_on = on;
-		fusb302_log(chip, "vbus := %s", on ? "On" : "Off");
+		fusb302_log(chip, "vbus := %s", str_on_off(on));
 	}
 	if (chip->charge_on == charge)
-		fusb302_log(chip, "charge is already %s",
-			    charge ? "On" : "Off");
+		fusb302_log(chip, "charge is already %s", str_on_off(charge));
 	else
 		chip->charge_on = charge;
 
@@ -854,16 +854,16 @@ static int tcpm_set_pd_rx(struct tcpc_dev *dev, bool on)
 	ret = fusb302_pd_set_auto_goodcrc(chip, on);
 	if (ret < 0) {
 		fusb302_log(chip, "cannot turn %s auto GCRC, ret=%d",
-			    on ? "on" : "off", ret);
+			    str_on_off(on), ret);
 		goto done;
 	}
 	ret = fusb302_pd_set_interrupts(chip, on);
 	if (ret < 0) {
 		fusb302_log(chip, "cannot turn %s pd interrupts, ret=%d",
-			    on ? "on" : "off", ret);
+			    str_on_off(on), ret);
 		goto done;
 	}
-	fusb302_log(chip, "pd := %s", on ? "on" : "off");
+	fusb302_log(chip, "pd := %s", str_on_off(on));
 done:
 	mutex_unlock(&chip->lock);
 
@@ -1531,7 +1531,7 @@ static void fusb302_irq_work(struct work_struct *work)
 	if (interrupt & FUSB_REG_INTERRUPT_VBUSOK) {
 		vbus_present = !!(status0 & FUSB_REG_STATUS0_VBUSOK);
 		fusb302_log(chip, "IRQ: VBUS_OK, vbus=%s",
-			    vbus_present ? "On" : "Off");
+			    str_on_off(vbus_present));
 		if (vbus_present != chip->vbus_present) {
 			chip->vbus_present = vbus_present;
 			tcpm_vbus_change(chip->tcpm_port);
@@ -1562,7 +1562,7 @@ static void fusb302_irq_work(struct work_struct *work)
 	if ((interrupt & FUSB_REG_INTERRUPT_COMP_CHNG) && intr_comp_chng) {
 		comp_result = !!(status0 & FUSB_REG_STATUS0_COMP);
 		fusb302_log(chip, "IRQ: COMP_CHNG, comp=%s",
-			    comp_result ? "true" : "false");
+			    str_true_false(comp_result));
 		if (comp_result) {
 			/* cc level > Rd_threshold, detach */
 			chip->cc1 = TYPEC_CC_OPEN;
diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c
index 726423684bae..18303b34594b 100644
--- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c
+++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c
@@ -12,6 +12,7 @@
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/usb/pd.h>
 #include <linux/usb/tcpm.h>
 #include "qcom_pmic_typec.h"
@@ -418,7 +419,7 @@ static int qcom_pmic_typec_pdphy_set_pd_rx(struct tcpc_dev *tcpc, bool on)
 
 	spin_unlock_irqrestore(&pmic_typec_pdphy->lock, flags);
 
-	dev_dbg(pmic_typec_pdphy->dev, "set_pd_rx: %s\n", on ? "on" : "off");
+	dev_dbg(pmic_typec_pdphy->dev, "set_pd_rx: %s\n", str_on_off(on));
 
 	return ret;
 }
diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c
index df79059cda67..8fac171778da 100644
--- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c
+++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy_stub.c
@@ -12,6 +12,7 @@
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/usb/pd.h>
 #include <linux/usb/tcpm.h>
 #include "qcom_pmic_typec.h"
@@ -38,7 +39,7 @@ static int qcom_pmic_typec_pdphy_stub_set_pd_rx(struct tcpc_dev *tcpc, bool on)
 	struct pmic_typec *tcpm = tcpc_to_tcpm(tcpc);
 	struct device *dev = tcpm->dev;
 
-	dev_dbg(dev, "set_pd_rx: %s\n", on ? "on" : "off");
+	dev_dbg(dev, "set_pd_rx: %s\n", str_on_off(on));
 
 	return 0;
 }
diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c
index c37dede62e12..4fc83dcfae64 100644
--- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c
+++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_port.c
@@ -13,6 +13,7 @@
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <linux/usb/tcpm.h>
 #include <linux/usb/typec_mux.h>
 #include <linux/workqueue.h>
@@ -562,7 +563,8 @@ done:
 	spin_unlock_irqrestore(&pmic_typec_port->lock, flags);
 
 	dev_dbg(dev, "set_vconn: orientation %d control 0x%08x state %s cc %s vconn %s\n",
-		orientation, value, on ? "on" : "off", misc_to_vconn(misc), misc_to_cc(misc));
+		orientation, value, str_on_off(on), misc_to_vconn(misc),
+		misc_to_cc(misc));
 
 	return ret;
 }
diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c
index 24a6a4354df8..19ab6647af70 100644
--- a/drivers/usb/typec/tcpm/tcpci.c
+++ b/drivers/usb/typec/tcpm/tcpci.c
@@ -27,6 +27,7 @@
 #define	VPPS_NEW_MIN_PERCENT			95
 #define	VPPS_VALID_MIN_MV			100
 #define	VSINKDISCONNECT_PD_MIN_PERCENT		90
+#define	VPPS_SHUTDOWN_MIN_PERCENT		85
 
 struct tcpci {
 	struct device *dev;
@@ -282,7 +283,7 @@ static int tcpci_set_polarity(struct tcpc_dev *tcpc,
 			if (cc2 == TYPEC_CC_RD)
 				/* Role control would have the Rp setting when DRP was enabled */
 				reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RP);
-			else
+			else if (cc2 >= TYPEC_CC_RP_DEF)
 				reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC2, TCPC_ROLE_CTRL_CC_RD);
 		} else {
 			reg &= ~TCPC_ROLE_CTRL_CC1;
@@ -290,7 +291,7 @@ static int tcpci_set_polarity(struct tcpc_dev *tcpc,
 			if (cc1 == TYPEC_CC_RD)
 				/* Role control would have the Rp setting when DRP was enabled */
 				reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RP);
-			else
+			else if (cc1 >= TYPEC_CC_RP_DEF)
 				reg |= FIELD_PREP(TCPC_ROLE_CTRL_CC1, TCPC_ROLE_CTRL_CC_RD);
 		}
 	}
@@ -366,7 +367,8 @@ static int tcpci_enable_auto_vbus_discharge(struct tcpc_dev *dev, bool enable)
 }
 
 static int tcpci_set_auto_vbus_discharge_threshold(struct tcpc_dev *dev, enum typec_pwr_opmode mode,
-						   bool pps_active, u32 requested_vbus_voltage_mv)
+						   bool pps_active, u32 requested_vbus_voltage_mv,
+						   u32 apdo_min_voltage_mv)
 {
 	struct tcpci *tcpci = tcpc_to_tcpci(dev);
 	unsigned int pwr_ctrl, threshold = 0;
@@ -388,9 +390,12 @@ static int tcpci_set_auto_vbus_discharge_threshold(struct tcpc_dev *dev, enum ty
 		threshold = AUTO_DISCHARGE_DEFAULT_THRESHOLD_MV;
 	} else if (mode == TYPEC_PWR_MODE_PD) {
 		if (pps_active)
-			threshold = ((VPPS_NEW_MIN_PERCENT * requested_vbus_voltage_mv / 100) -
-				     VSINKPD_MIN_IR_DROP_MV - VPPS_VALID_MIN_MV) *
-				     VSINKDISCONNECT_PD_MIN_PERCENT / 100;
+			/*
+			 * To prevent disconnect when the source is in Current Limit Mode.
+			 * Set the threshold to the lowest possible voltage vPpsShutdown (min)
+			 */
+			threshold = VPPS_SHUTDOWN_MIN_PERCENT * apdo_min_voltage_mv / 100 -
+				    VSINKPD_MIN_IR_DROP_MV;
 		else
 			threshold = ((VSRC_NEW_MIN_PERCENT * requested_vbus_voltage_mv / 100) -
 				     VSINKPD_MIN_IR_DROP_MV - VSRC_VALID_MIN_MV) *
diff --git a/drivers/usb/typec/tcpm/tcpci_mt6370.c b/drivers/usb/typec/tcpm/tcpci_mt6370.c
index 1479f961772d..ed822f438a09 100644
--- a/drivers/usb/typec/tcpm/tcpci_mt6370.c
+++ b/drivers/usb/typec/tcpm/tcpci_mt6370.c
@@ -11,7 +11,6 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/pm_wakeup.h>
 #include <linux/pm_wakeirq.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 95c0c63119ac..47be450d2be3 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -21,6 +21,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/string_choices.h>
 #include <linux/usb.h>
 #include <linux/usb/pd.h>
 #include <linux/usb/pd_ado.h>
@@ -185,7 +186,8 @@
 	S(UNSTRUCTURED_VDMS),			\
 	S(STRUCTURED_VDMS),			\
 	S(COUNTRY_INFO),			\
-	S(COUNTRY_CODES)
+	S(COUNTRY_CODES),			\
+	S(REVISION_INFORMATION)
 
 #define GENERATE_ENUM(e)	e
 #define GENERATE_STRING(s)	#s
@@ -225,6 +227,7 @@ enum pd_msg_request {
 	PD_MSG_CTRL_NOT_SUPP,
 	PD_MSG_DATA_SINK_CAP,
 	PD_MSG_DATA_SOURCE_CAP,
+	PD_MSG_DATA_REV,
 };
 
 enum adev_actions {
@@ -310,6 +313,13 @@ struct pd_data {
 	unsigned int operating_snk_mw;
 };
 
+struct pd_revision_info {
+	u8 rev_major;
+	u8 rev_minor;
+	u8 ver_major;
+	u8 ver_minor;
+};
+
 /*
  * @sink_wait_cap_time: Deadline (in ms) for tTypeCSinkWaitCap timer
  * @ps_src_wait_off_time: Deadline (in ms) for tPSSourceOff timer
@@ -567,6 +577,9 @@ struct tcpm_port {
 
 	/* Timer deadline values configured at runtime */
 	struct pd_timings timings;
+
+	/* Indicates maximum (revision, version) supported */
+	struct pd_revision_info pd_rev;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
 	struct mutex logbuffer_lock;	/* log buffer access lock */
@@ -880,8 +893,8 @@ static int tcpm_enable_auto_vbus_discharge(struct tcpm_port *port, bool enable)
 
 	if (port->tcpc->enable_auto_vbus_discharge) {
 		ret = port->tcpc->enable_auto_vbus_discharge(port->tcpc, enable);
-		tcpm_log_force(port, "%s vbus discharge ret:%d", enable ? "enable" : "disable",
-			       ret);
+		tcpm_log_force(port, "%s vbus discharge ret:%d",
+			       str_enable_disable(enable), ret);
 		if (!ret)
 			port->auto_vbus_discharge_enabled = enable;
 	}
@@ -1234,6 +1247,24 @@ static u32 tcpm_forge_legacy_pdo(struct tcpm_port *port, u32 pdo, enum typec_rol
 	}
 }
 
+static int tcpm_pd_send_revision(struct tcpm_port *port)
+{
+	struct pd_message msg;
+	u32 rmdo;
+
+	memset(&msg, 0, sizeof(msg));
+	rmdo = RMDO(port->pd_rev.rev_major, port->pd_rev.rev_minor,
+		    port->pd_rev.ver_major, port->pd_rev.ver_minor);
+	msg.payload[0] = cpu_to_le32(rmdo);
+	msg.header = PD_HEADER_LE(PD_DATA_REVISION,
+				  port->pwr_role,
+				  port->data_role,
+				  port->negotiated_rev,
+				  port->message_id,
+				  1);
+	return tcpm_pd_transmit(port, TCPC_TX_SOP, &msg);
+}
+
 static int tcpm_pd_send_source_caps(struct tcpm_port *port)
 {
 	struct pd_message msg;
@@ -2943,10 +2974,12 @@ static int tcpm_set_auto_vbus_discharge_threshold(struct tcpm_port *port,
 		return 0;
 
 	ret = port->tcpc->set_auto_vbus_discharge_threshold(port->tcpc, mode, pps_active,
-							    requested_vbus_voltage);
+							    requested_vbus_voltage,
+							    port->pps_data.min_volt);
 	tcpm_log_force(port,
-		       "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u ret:%d",
-		       mode, pps_active ? 'y' : 'n', requested_vbus_voltage, ret);
+		       "set_auto_vbus_discharge_threshold mode:%d pps_active:%c vbus:%u pps_apdo_min_volt:%u ret:%d",
+		       mode, pps_active ? 'y' : 'n', requested_vbus_voltage,
+		       port->pps_data.min_volt, ret);
 
 	return ret;
 }
@@ -3537,6 +3570,17 @@ static void tcpm_pd_ctrl_request(struct tcpm_port *port,
 				   PD_MSG_CTRL_NOT_SUPP,
 				   NONE_AMS);
 		break;
+	case PD_CTRL_GET_REVISION:
+		if (port->negotiated_rev >= PD_REV30 && port->pd_rev.rev_major)
+			tcpm_pd_handle_msg(port, PD_MSG_DATA_REV,
+					   REVISION_INFORMATION);
+		else
+			tcpm_pd_handle_msg(port,
+					   port->negotiated_rev < PD_REV30 ?
+					   PD_MSG_CTRL_REJECT :
+					   PD_MSG_CTRL_NOT_SUPP,
+					   NONE_AMS);
+		break;
 	default:
 		tcpm_pd_handle_msg(port,
 				   port->negotiated_rev < PD_REV30 ?
@@ -3781,6 +3825,14 @@ static bool tcpm_send_queued_message(struct tcpm_port *port)
 				tcpm_ams_finish(port);
 			}
 			break;
+		case PD_MSG_DATA_REV:
+			ret = tcpm_pd_send_revision(port);
+			if (ret)
+				tcpm_log(port,
+					 "Unable to send revision msg, ret=%d",
+					 ret);
+			tcpm_ams_finish(port);
+			break;
 		default:
 			break;
 		}
@@ -4390,7 +4442,7 @@ static void tcpm_unregister_altmodes(struct tcpm_port *port)
 
 static void tcpm_set_partner_usb_comm_capable(struct tcpm_port *port, bool capable)
 {
-	tcpm_log(port, "Setting usb_comm capable %s", capable ? "true" : "false");
+	tcpm_log(port, "Setting usb_comm capable %s", str_true_false(capable));
 
 	if (port->tcpc->set_partner_usb_comm_capable)
 		port->tcpc->set_partner_usb_comm_capable(port->tcpc, capable);
@@ -4772,7 +4824,7 @@ static void run_state_machine(struct tcpm_port *port)
 			port->caps_count = 0;
 			port->pd_capable = true;
 			tcpm_set_state_cond(port, SRC_SEND_CAPABILITIES_TIMEOUT,
-					    PD_T_SEND_SOURCE_CAP);
+					    PD_T_SENDER_RESPONSE);
 		}
 		break;
 	case SRC_SEND_CAPABILITIES_TIMEOUT:
@@ -7036,7 +7088,9 @@ static void tcpm_port_unregister_pd(struct tcpm_port *port)
 
 static int tcpm_port_register_pd(struct tcpm_port *port)
 {
-	struct usb_power_delivery_desc desc = { port->typec_caps.pd_revision };
+	u16 pd_revision = port->typec_caps.pd_revision;
+	u16 pd_version = port->pd_rev.ver_major << 8 | port->pd_rev.ver_minor;
+	struct usb_power_delivery_desc desc = { pd_revision, pd_version };
 	struct usb_power_delivery_capabilities *cap;
 	int ret, i;
 
@@ -7331,6 +7385,29 @@ static int tcpm_fw_get_snk_vdos(struct tcpm_port *port, struct fwnode_handle *fw
 	return 0;
 }
 
+static void tcpm_fw_get_pd_revision(struct tcpm_port *port, struct fwnode_handle *fwnode)
+{
+	int ret;
+	u8 val[4];
+
+	ret = fwnode_property_count_u8(fwnode, "pd-revision");
+	if (!ret || ret != 4) {
+		tcpm_log(port, "Unable to find pd-revision property or incorrect array size");
+		return;
+	}
+
+	ret = fwnode_property_read_u8_array(fwnode, "pd-revision", val, 4);
+	if (ret) {
+		tcpm_log(port, "Failed to parse pd-revision, ret:(%d)", ret);
+		return;
+	}
+
+	port->pd_rev.rev_major = val[0];
+	port->pd_rev.rev_minor = val[1];
+	port->pd_rev.ver_major = val[2];
+	port->pd_rev.ver_minor = val[3];
+}
+
 /* Power Supply access to expose source power information */
 enum tcpm_psy_online_states {
 	TCPM_PSY_OFFLINE = 0,
@@ -7669,11 +7746,18 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 		goto out_destroy_wq;
 
 	tcpm_fw_get_timings(port, tcpc->fwnode);
+	tcpm_fw_get_pd_revision(port, tcpc->fwnode);
 
 	port->try_role = port->typec_caps.prefer_role;
 
 	port->typec_caps.revision = 0x0120;	/* Type-C spec release 1.2 */
-	port->typec_caps.pd_revision = 0x0300;	/* USB-PD spec release 3.0 */
+
+	if (port->pd_rev.rev_major)
+		port->typec_caps.pd_revision = port->pd_rev.rev_major << 8 |
+					       port->pd_rev.rev_minor;
+	else
+		port->typec_caps.pd_revision = 0x0300;	/* USB-PD spec release 3.0 */
+
 	port->typec_caps.svdm_version = SVDM_VER_2_0;
 	port->typec_caps.driver_data = port;
 	port->typec_caps.ops = &tcpm_ops;
diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig
index 680e1b87b152..75559601fe8f 100644
--- a/drivers/usb/typec/ucsi/Kconfig
+++ b/drivers/usb/typec/ucsi/Kconfig
@@ -69,6 +69,19 @@ config UCSI_PMIC_GLINK
 	  To compile the driver as a module, choose M here: the module will be
 	  called ucsi_glink.
 
+config CROS_EC_UCSI
+	tristate "UCSI Driver for ChromeOS EC"
+	depends on MFD_CROS_EC_DEV
+	depends on CROS_USBPD_NOTIFY
+	depends on !EXTCON_TCSS_CROS_EC
+	default MFD_CROS_EC_DEV
+	help
+	  This driver enables UCSI support for a ChromeOS EC. The EC is
+	  expected to implement a PPM.
+
+	  To compile the driver as a module, choose M here: the module
+	  will be called cros_ec_ucsi.
+
 config UCSI_LENOVO_YOGA_C630
 	tristate "UCSI Interface Driver for Lenovo Yoga C630"
 	depends on EC_LENOVO_YOGA_C630
diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile
index aed41d23887b..be98a879104d 100644
--- a/drivers/usb/typec/ucsi/Makefile
+++ b/drivers/usb/typec/ucsi/Makefile
@@ -21,4 +21,5 @@ obj-$(CONFIG_UCSI_ACPI)			+= ucsi_acpi.o
 obj-$(CONFIG_UCSI_CCG)			+= ucsi_ccg.o
 obj-$(CONFIG_UCSI_STM32G0)		+= ucsi_stm32g0.o
 obj-$(CONFIG_UCSI_PMIC_GLINK)		+= ucsi_glink.o
+obj-$(CONFIG_CROS_EC_UCSI)		+= cros_ec_ucsi.o
 obj-$(CONFIG_UCSI_LENOVO_YOGA_C630)	+= ucsi_yoga_c630.o
diff --git a/drivers/usb/typec/ucsi/cros_ec_ucsi.c b/drivers/usb/typec/ucsi/cros_ec_ucsi.c
new file mode 100644
index 000000000000..c605c8616726
--- /dev/null
+++ b/drivers/usb/typec/ucsi/cros_ec_ucsi.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * UCSI driver for ChromeOS EC
+ *
+ * Copyright 2024 Google LLC.
+ */
+
+#include <linux/container_of.h>
+#include <linux/dev_printk.h>
+#include <linux/jiffies.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_data/cros_ec_commands.h>
+#include <linux/platform_data/cros_usbpd_notify.h>
+#include <linux/platform_data/cros_ec_proto.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+
+#include "ucsi.h"
+
+/*
+ * Maximum size in bytes of a UCSI message between AP and EC
+ */
+#define MAX_EC_DATA_SIZE	256
+
+/*
+ * Maximum time in milliseconds the cros_ec_ucsi driver
+ * will wait for a response to a command or and ack.
+ */
+#define WRITE_TMO_MS		5000
+
+/* Number of times to attempt recovery from a write timeout before giving up. */
+#define WRITE_TMO_CTR_MAX	5
+
+struct cros_ucsi_data {
+	struct device *dev;
+	struct ucsi *ucsi;
+
+	struct cros_ec_device *ec;
+	struct notifier_block nb;
+	struct work_struct work;
+	struct delayed_work write_tmo;
+	int tmo_counter;
+
+	struct completion complete;
+	unsigned long flags;
+};
+
+static int cros_ucsi_read(struct ucsi *ucsi, unsigned int offset, void *val,
+			  size_t val_len)
+{
+	struct cros_ucsi_data *udata = ucsi_get_drvdata(ucsi);
+	struct ec_params_ucsi_ppm_get req = {
+		.offset = offset,
+		.size = val_len,
+	};
+	int ret;
+
+	if (val_len > MAX_EC_DATA_SIZE) {
+		dev_err(udata->dev, "Can't read %zu bytes. Too big.\n", val_len);
+		return -EINVAL;
+	}
+
+	ret = cros_ec_cmd(udata->ec, 0, EC_CMD_UCSI_PPM_GET,
+			  &req, sizeof(req), val, val_len);
+	if (ret < 0) {
+		dev_warn(udata->dev, "Failed to send EC message UCSI_PPM_GET: error=%d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int cros_ucsi_read_version(struct ucsi *ucsi, u16 *version)
+{
+	return cros_ucsi_read(ucsi, UCSI_VERSION, version, sizeof(*version));
+}
+
+static int cros_ucsi_read_cci(struct ucsi *ucsi, u32 *cci)
+{
+	return cros_ucsi_read(ucsi, UCSI_CCI, cci, sizeof(*cci));
+}
+
+static int cros_ucsi_read_message_in(struct ucsi *ucsi, void *val,
+				     size_t val_len)
+{
+	return cros_ucsi_read(ucsi, UCSI_MESSAGE_IN, val, val_len);
+}
+
+static int cros_ucsi_async_control(struct ucsi *ucsi, u64 cmd)
+{
+	struct cros_ucsi_data *udata = ucsi_get_drvdata(ucsi);
+	u8 ec_buf[sizeof(struct ec_params_ucsi_ppm_set) + sizeof(cmd)];
+	struct ec_params_ucsi_ppm_set *req = (struct ec_params_ucsi_ppm_set *) ec_buf;
+	int ret;
+
+	req->offset = UCSI_CONTROL;
+	memcpy(req->data, &cmd, sizeof(cmd));
+	ret = cros_ec_cmd(udata->ec, 0, EC_CMD_UCSI_PPM_SET,
+			  req, sizeof(ec_buf), NULL, 0);
+	if (ret < 0) {
+		dev_warn(udata->dev, "Failed to send EC message UCSI_PPM_SET: error=%d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int cros_ucsi_sync_control(struct ucsi *ucsi, u64 cmd)
+{
+	struct cros_ucsi_data *udata = ucsi_get_drvdata(ucsi);
+	int ret;
+
+	ret = ucsi_sync_control_common(ucsi, cmd);
+	switch (ret) {
+	case -EBUSY:
+		/* EC may return -EBUSY if CCI.busy is set.
+		 * Convert this to a timeout.
+		 */
+	case -ETIMEDOUT:
+		/* Schedule recovery attempt when we timeout
+		 * or tried to send a command while still busy.
+		 */
+		cancel_delayed_work_sync(&udata->write_tmo);
+		schedule_delayed_work(&udata->write_tmo,
+				      msecs_to_jiffies(WRITE_TMO_MS));
+		break;
+	case 0:
+		/* Successful write. Cancel any pending recovery work. */
+		cancel_delayed_work_sync(&udata->write_tmo);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct ucsi_operations cros_ucsi_ops = {
+	.read_version = cros_ucsi_read_version,
+	.read_cci = cros_ucsi_read_cci,
+	.read_message_in = cros_ucsi_read_message_in,
+	.async_control = cros_ucsi_async_control,
+	.sync_control = cros_ucsi_sync_control,
+};
+
+static void cros_ucsi_work(struct work_struct *work)
+{
+	struct cros_ucsi_data *udata = container_of(work, struct cros_ucsi_data, work);
+	u32 cci;
+
+	if (cros_ucsi_read_cci(udata->ucsi, &cci))
+		return;
+
+	ucsi_notify_common(udata->ucsi, cci);
+}
+
+static void cros_ucsi_write_timeout(struct work_struct *work)
+{
+	struct cros_ucsi_data *udata =
+		container_of(work, struct cros_ucsi_data, write_tmo.work);
+	u32 cci;
+	u64 cmd;
+
+	if (cros_ucsi_read(udata->ucsi, UCSI_CCI, &cci, sizeof(cci))) {
+		dev_err(udata->dev,
+			"Reading CCI failed; no write timeout recovery possible.\n");
+		return;
+	}
+
+	if (cci & UCSI_CCI_BUSY) {
+		udata->tmo_counter++;
+
+		if (udata->tmo_counter <= WRITE_TMO_CTR_MAX)
+			schedule_delayed_work(&udata->write_tmo,
+					      msecs_to_jiffies(WRITE_TMO_MS));
+		else
+			dev_err(udata->dev,
+				"PPM unresponsive - too many write timeouts.\n");
+
+		return;
+	}
+
+	/* No longer busy means we can reset our timeout counter. */
+	udata->tmo_counter = 0;
+
+	/* Need to ack previous command which may have timed out. */
+	if (cci & UCSI_CCI_COMMAND_COMPLETE) {
+		cmd = UCSI_ACK_CC_CI | UCSI_ACK_COMMAND_COMPLETE;
+		cros_ucsi_async_control(udata->ucsi, cmd);
+
+		/* Check again after a few seconds that the system has
+		 * recovered to make sure our async write above was successful.
+		 */
+		schedule_delayed_work(&udata->write_tmo,
+				      msecs_to_jiffies(WRITE_TMO_MS));
+		return;
+	}
+
+	/* We recovered from a previous timeout. Treat this as a recovery from
+	 * suspend and call resume.
+	 */
+	ucsi_resume(udata->ucsi);
+}
+
+static int cros_ucsi_event(struct notifier_block *nb,
+			   unsigned long host_event, void *_notify)
+{
+	struct cros_ucsi_data *udata = container_of(nb, struct cros_ucsi_data, nb);
+
+	if (!(host_event & PD_EVENT_PPM))
+		return NOTIFY_OK;
+
+	dev_dbg(udata->dev, "UCSI notification received\n");
+	flush_work(&udata->work);
+	schedule_work(&udata->work);
+
+	return NOTIFY_OK;
+}
+
+static void cros_ucsi_destroy(struct cros_ucsi_data *udata)
+{
+	cros_usbpd_unregister_notify(&udata->nb);
+	cancel_delayed_work_sync(&udata->write_tmo);
+	cancel_work_sync(&udata->work);
+	ucsi_destroy(udata->ucsi);
+}
+
+static int cros_ucsi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct cros_ec_dev *ec_data = dev_get_drvdata(dev->parent);
+	struct cros_ucsi_data *udata;
+	int ret;
+
+	udata = devm_kzalloc(dev, sizeof(*udata), GFP_KERNEL);
+	if (!udata)
+		return -ENOMEM;
+
+	udata->dev = dev;
+
+	udata->ec = ec_data->ec_dev;
+	if (!udata->ec)
+		return dev_err_probe(dev, -ENODEV, "couldn't find parent EC device\n");
+
+	platform_set_drvdata(pdev, udata);
+
+	INIT_WORK(&udata->work, cros_ucsi_work);
+	INIT_DELAYED_WORK(&udata->write_tmo, cros_ucsi_write_timeout);
+	init_completion(&udata->complete);
+
+	udata->ucsi = ucsi_create(dev, &cros_ucsi_ops);
+	if (IS_ERR(udata->ucsi))
+		return dev_err_probe(dev, PTR_ERR(udata->ucsi), "failed to allocate UCSI instance\n");
+
+	ucsi_set_drvdata(udata->ucsi, udata);
+
+	udata->nb.notifier_call = cros_ucsi_event;
+	ret = cros_usbpd_register_notify(&udata->nb);
+	if (ret) {
+		dev_err_probe(dev, ret, "failed to register notifier\n");
+		ucsi_destroy(udata->ucsi);
+		return ret;
+	}
+
+	ret = ucsi_register(udata->ucsi);
+	if (ret) {
+		dev_err_probe(dev, ret, "failed to register UCSI\n");
+		cros_ucsi_destroy(udata);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void cros_ucsi_remove(struct platform_device *dev)
+{
+	struct cros_ucsi_data *udata = platform_get_drvdata(dev);
+
+	ucsi_unregister(udata->ucsi);
+	cros_ucsi_destroy(udata);
+}
+
+static int __maybe_unused cros_ucsi_suspend(struct device *dev)
+{
+	struct cros_ucsi_data *udata = dev_get_drvdata(dev);
+
+	cancel_delayed_work_sync(&udata->write_tmo);
+	cancel_work_sync(&udata->work);
+
+	return 0;
+}
+
+static void __maybe_unused cros_ucsi_complete(struct device *dev)
+{
+	struct cros_ucsi_data *udata = dev_get_drvdata(dev);
+
+	ucsi_resume(udata->ucsi);
+}
+
+/*
+ * UCSI protocol is also used on ChromeOS platforms which reply on
+ * cros_ec_lpc.c driver for communication with embedded controller (EC).
+ * On such platforms communication with the EC is not available until
+ * the .complete() callback of the cros_ec_lpc driver is executed.
+ * For this reason we delay ucsi_resume() until the .complete() stage
+ * otherwise UCSI SET_NOTIFICATION_ENABLE command will fail and we won't
+ * receive any UCSI notifications from the EC where PPM is implemented.
+ */
+static const struct dev_pm_ops cros_ucsi_pm_ops = {
+#ifdef CONFIG_PM_SLEEP
+	.suspend = cros_ucsi_suspend,
+	.complete = cros_ucsi_complete,
+#endif
+};
+
+static const struct platform_device_id cros_ucsi_id[] = {
+	{ KBUILD_MODNAME, 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(platform, cros_ucsi_id);
+
+static struct platform_driver cros_ucsi_driver = {
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.pm = &cros_ucsi_pm_ops,
+	},
+	.id_table = cros_ucsi_id,
+	.probe = cros_ucsi_probe,
+	.remove = cros_ucsi_remove,
+};
+
+module_platform_driver(cros_ucsi_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UCSI driver for ChromeOS EC");
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 5ff369c24a2f..82735eb34f0e 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -30,6 +30,7 @@ struct dentry;
 #define UCSIv2_MESSAGE_OUT		272
 
 /* UCSI versions */
+#define UCSI_VERSION_1_0	0x0100
 #define UCSI_VERSION_1_1	0x0110
 #define UCSI_VERSION_1_2	0x0120
 #define UCSI_VERSION_2_0	0x0200
diff --git a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
index f3a5e24ea84d..4cae85c0dc12 100644
--- a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
+++ b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
@@ -71,7 +71,7 @@ static int yoga_c630_ucsi_async_control(struct ucsi *ucsi, u64 command)
 	return yoga_c630_ec_ucsi_write(uec->ec, (u8*)&command);
 }
 
-const struct ucsi_operations yoga_c630_ucsi_ops = {
+static const struct ucsi_operations yoga_c630_ucsi_ops = {
 	.read_version = yoga_c630_ucsi_read_version,
 	.read_cci = yoga_c630_ucsi_read_cci,
 	.read_message_in = yoga_c630_ucsi_read_message_in,
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 6338d818bc8b..9aa30ef76f3b 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -269,7 +269,7 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
 		return 0;
 	}
 
-	usbip_dbg_stub_rx("seqnum %d is not pending\n",
+	usbip_dbg_stub_rx("seqnum %u is not pending\n",
 			  pdu->u.cmd_unlink.seqnum);
 
 	/*
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
index b1c2f6781cb3..7eb2e074012a 100644
--- a/drivers/usb/usbip/stub_tx.c
+++ b/drivers/usb/usbip/stub_tx.c
@@ -201,7 +201,7 @@ static int stub_send_ret_submit(struct stub_device *sdev)
 
 		/* 1. setup usbip_header */
 		setup_ret_submit_pdu(&pdu_header, urb);
-		usbip_dbg_stub_tx("setup txdata seqnum: %d\n",
+		usbip_dbg_stub_tx("setup txdata seqnum: %u\n",
 				  pdu_header.base.seqnum);
 
 		if (priv->sgl) {
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index b03e5021c25b..e70fba9f55d6 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 
 #include "usbip_common.h"
 #include "vhci.h"
@@ -675,7 +676,7 @@ static void vhci_tx_urb(struct urb *urb, struct vhci_device *vdev)
 
 	spin_lock_irqsave(&vdev->priv_lock, flags);
 
-	priv->seqnum = atomic_inc_return(&vhci_hcd->seqnum);
+	priv->seqnum = (u32)atomic_inc_return(&vhci_hcd->seqnum);
 	if (priv->seqnum == 0xffff)
 		dev_info(&urb->dev->dev, "seqnum max\n");
 
@@ -1161,12 +1162,8 @@ static int vhci_setup(struct usb_hcd *hcd)
 		hcd->self.root_hub->speed = USB_SPEED_SUPER_PLUS;
 	}
 
-	/*
-	 * Support SG.
-	 * sg_tablesize is an arbitrary value to alleviate memory pressure
-	 * on the host.
-	 */
-	hcd->self.sg_tablesize = 32;
+	/* accept arbitrarily long scatter-gather lists */
+	hcd->self.sg_tablesize = ~0;
 	hcd->self.no_sg_constraint = 1;
 
 	return 0;
@@ -1453,7 +1450,7 @@ static int vhci_hcd_suspend(struct platform_device *pdev, pm_message_t state)
 	if (connected > 0) {
 		dev_info(&pdev->dev,
 			 "We have %d active connection%s. Do not suspend.\n",
-			 connected, (connected == 1 ? "" : "s"));
+			 connected, str_plural(connected));
 		ret =  -EBUSY;
 	} else {
 		dev_info(&pdev->dev, "suspend vhci_hcd");
diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
index 7f2d1c241559..a75f4a898a41 100644
--- a/drivers/usb/usbip/vhci_rx.c
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -66,7 +66,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
 	spin_unlock_irqrestore(&vdev->priv_lock, flags);
 
 	if (!urb) {
-		pr_err("cannot find a urb of seqnum %u max seqnum %d\n",
+		pr_err("cannot find a urb of seqnum %u max seqnum %u\n",
 			pdu->base.seqnum,
 			atomic_read(&vhci_hcd->seqnum));
 		usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
@@ -162,10 +162,10 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
 		 * already received the result of its submit result and gave
 		 * back the URB.
 		 */
-		pr_info("the urb (seqnum %d) was already given back\n",
+		pr_info("the urb (seqnum %u) was already given back\n",
 			pdu->base.seqnum);
 	} else {
-		usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum);
+		usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum);
 
 		/* If unlink is successful, status is -ECONNRESET */
 		urb->status = pdu->u.ret_unlink.status;
diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c
index 907a43a00896..2aae3edfc813 100644
--- a/drivers/usb/usbip/vudc_sysfs.c
+++ b/drivers/usb/usbip/vudc_sysfs.c
@@ -67,7 +67,7 @@ out:
  * Exposes device descriptor from the gadget driver.
  */
 static ssize_t dev_desc_read(struct file *file, struct kobject *kobj,
-			     struct bin_attribute *attr, char *out,
+			     const struct bin_attribute *attr, char *out,
 			     loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -88,7 +88,7 @@ unlock:
 	spin_unlock_irqrestore(&udc->lock, flags);
 	return ret;
 }
-static BIN_ATTR_RO(dev_desc, sizeof(struct usb_device_descriptor));
+static const BIN_ATTR_RO(dev_desc, sizeof(struct usb_device_descriptor));
 
 static ssize_t usbip_sockfd_store(struct device *dev,
 				  struct device_attribute *attr,
@@ -252,14 +252,14 @@ static struct attribute *dev_attrs[] = {
 	NULL,
 };
 
-static struct bin_attribute *dev_bin_attrs[] = {
+static const struct bin_attribute *const dev_bin_attrs[] = {
 	&bin_attr_dev_desc,
 	NULL,
 };
 
 static const struct attribute_group vudc_attr_group = {
 	.attrs = dev_attrs,
-	.bin_attrs = dev_bin_attrs,
+	.bin_attrs_new = dev_bin_attrs,
 };
 
 const struct attribute_group *vudc_groups[] = {
diff --git a/drivers/usb/usbip/vudc_tx.c b/drivers/usb/usbip/vudc_tx.c
index 3ccb17c3e840..30c11bf9f4e7 100644
--- a/drivers/usb/usbip/vudc_tx.c
+++ b/drivers/usb/usbip/vudc_tx.c
@@ -107,7 +107,7 @@ static int v_send_ret_submit(struct vudc *udc, struct urbp *urb_p)
 
 	/* 1. setup usbip_header */
 	setup_ret_submit_pdu(&pdu_header, urb_p);
-	usbip_dbg_stub_tx("setup txdata seqnum: %d\n",
+	usbip_dbg_stub_tx("setup txdata seqnum: %u\n",
 			  pdu_header.base.seqnum);
 	usbip_header_correct_endian(&pdu_header, 1);
 
diff --git a/drivers/vdpa/octeon_ep/octep_vdpa.h b/drivers/vdpa/octeon_ep/octep_vdpa.h
index 046710ec4d42..53b020b019f7 100644
--- a/drivers/vdpa/octeon_ep/octep_vdpa.h
+++ b/drivers/vdpa/octeon_ep/octep_vdpa.h
@@ -8,6 +8,7 @@
 #include <linux/pci_regs.h>
 #include <linux/vdpa.h>
 #include <linux/virtio_pci_modern.h>
+#include <uapi/linux/virtio_crypto.h>
 #include <uapi/linux/virtio_net.h>
 #include <uapi/linux/virtio_blk.h>
 #include <uapi/linux/virtio_config.h>
@@ -29,12 +30,12 @@
 #define OCTEP_EPF_RINFO(x) (0x000209f0 | ((x) << 25))
 #define OCTEP_VF_MBOX_DATA(x) (0x00010210 | ((x) << 17))
 #define OCTEP_PF_MBOX_DATA(x) (0x00022000 | ((x) << 4))
-
-#define OCTEP_EPF_RINFO_RPVF(val) (((val) >> 32) & 0xF)
-#define OCTEP_EPF_RINFO_NVFS(val) (((val) >> 48) & 0x7F)
+#define OCTEP_VF_IN_CTRL(x)        (0x00010000 | ((x) << 17))
+#define OCTEP_VF_IN_CTRL_RPVF(val) (((val) >> 48) & 0xF)
 
 #define OCTEP_FW_READY_SIGNATURE0  0xFEEDFEED
 #define OCTEP_FW_READY_SIGNATURE1  0x3355ffaa
+#define OCTEP_MAX_CB_INTR          8
 
 enum octep_vdpa_dev_status {
 	OCTEP_VDPA_DEV_STATUS_INVALID,
@@ -48,9 +49,26 @@ enum octep_vdpa_dev_status {
 struct octep_vring_info {
 	struct vdpa_callback cb;
 	void __iomem *notify_addr;
-	u32 __iomem *cb_notify_addr;
+	void __iomem *cb_notify_addr;
 	phys_addr_t notify_pa;
-	char msix_name[256];
+};
+
+enum octep_pci_vndr_cfg_type {
+	OCTEP_PCI_VNDR_CFG_TYPE_VIRTIO_ID,
+	OCTEP_PCI_VNDR_CFG_TYPE_MAX,
+};
+
+struct octep_pci_vndr_data {
+	struct virtio_pci_vndr_data hdr;
+	u8 id;
+	u8 bar;
+	union {
+		u64 data;
+		struct {
+			u32 offset;
+			u32 length;
+		};
+	};
 };
 
 struct octep_hw {
@@ -68,7 +86,9 @@ struct octep_hw {
 	u64 features;
 	u16 nr_vring;
 	u32 config_size;
-	int irq;
+	int nb_irqs;
+	int *irqs;
+	u8 dev_id;
 };
 
 u8 octep_hw_get_status(struct octep_hw *oct_hw);
diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c
index 1d4767b33315..74240101c505 100644
--- a/drivers/vdpa/octeon_ep/octep_vdpa_hw.c
+++ b/drivers/vdpa/octeon_ep/octep_vdpa_hw.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2024 Marvell. */
 
 #include <linux/iopoll.h>
+#include <linux/build_bug.h>
 
 #include "octep_vdpa.h"
 
@@ -358,7 +359,14 @@ u16 octep_get_vq_size(struct octep_hw *oct_hw)
 
 static u32 octep_get_config_size(struct octep_hw *oct_hw)
 {
-	return sizeof(struct virtio_net_config);
+	switch (oct_hw->dev_id) {
+	case VIRTIO_ID_NET:
+		return sizeof(struct virtio_net_config);
+	case VIRTIO_ID_CRYPTO:
+		return sizeof(struct virtio_crypto_config);
+	default:
+		return 0;
+	}
 }
 
 static void __iomem *octep_get_cap_addr(struct octep_hw *oct_hw, struct virtio_pci_cap *cap)
@@ -416,8 +424,25 @@ static int octep_pci_signature_verify(struct octep_hw *oct_hw)
 	return 0;
 }
 
+static void octep_vndr_data_process(struct octep_hw *oct_hw,
+				    struct octep_pci_vndr_data *vndr_data)
+{
+	BUILD_BUG_ON(sizeof(struct octep_pci_vndr_data) % 4 != 0);
+
+	switch (vndr_data->id) {
+	case OCTEP_PCI_VNDR_CFG_TYPE_VIRTIO_ID:
+		oct_hw->dev_id = (u8)vndr_data->data;
+		break;
+	default:
+		dev_err(&oct_hw->pdev->dev, "Invalid vendor data id %u\n",
+			vndr_data->id);
+		break;
+	}
+}
+
 int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev)
 {
+	struct octep_pci_vndr_data vndr_data;
 	struct octep_mbox __iomem *mbox;
 	struct device *dev = &pdev->dev;
 	struct virtio_pci_cap cap;
@@ -466,6 +491,15 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev)
 		case VIRTIO_PCI_CAP_ISR_CFG:
 			oct_hw->isr = octep_get_cap_addr(oct_hw, &cap);
 			break;
+		case VIRTIO_PCI_CAP_VENDOR_CFG:
+			octep_pci_caps_read(oct_hw, &vndr_data, sizeof(vndr_data), pos);
+			if (vndr_data.hdr.vendor_id != PCI_VENDOR_ID_CAVIUM) {
+				dev_err(dev, "Invalid vendor data\n");
+				return -EINVAL;
+			}
+
+			octep_vndr_data_process(oct_hw, &vndr_data);
+			break;
 		}
 
 		pos = cap.cap_next;
@@ -495,8 +529,6 @@ int octep_hw_caps_read(struct octep_hw *oct_hw, struct pci_dev *pdev)
 	if (!oct_hw->vqs)
 		return -ENOMEM;
 
-	oct_hw->irq = -1;
-
 	dev_info(&pdev->dev, "Device features : %llx\n", oct_hw->features);
 	dev_info(&pdev->dev, "Maximum queues : %u\n", oct_hw->nr_vring);
 
diff --git a/drivers/vdpa/octeon_ep/octep_vdpa_main.c b/drivers/vdpa/octeon_ep/octep_vdpa_main.c
index cd55b1aac151..f3d4dda4e04c 100644
--- a/drivers/vdpa/octeon_ep/octep_vdpa_main.c
+++ b/drivers/vdpa/octeon_ep/octep_vdpa_main.c
@@ -49,58 +49,89 @@ static irqreturn_t octep_vdpa_intr_handler(int irq, void *data)
 	struct octep_hw *oct_hw = data;
 	int i;
 
-	for (i = 0; i < oct_hw->nr_vring; i++) {
-		if (oct_hw->vqs[i].cb.callback && ioread32(oct_hw->vqs[i].cb_notify_addr)) {
-			/* Acknowledge the per queue notification to the device */
-			iowrite32(0, oct_hw->vqs[i].cb_notify_addr);
-			oct_hw->vqs[i].cb.callback(oct_hw->vqs[i].cb.private);
+	/* Each device has multiple interrupts (nb_irqs) shared among rings
+	 * (nr_vring). Device interrupts are mapped to the rings in a
+	 * round-robin fashion.
+	 *
+	 * For example, if nb_irqs = 8 and nr_vring = 64:
+	 * 0 -> 0, 8, 16, 24, 32, 40, 48, 56;
+	 * 1 -> 1, 9, 17, 25, 33, 41, 49, 57;
+	 * ...
+	 * 7 -> 7, 15, 23, 31, 39, 47, 55, 63;
+	 */
+
+	for (i = irq - oct_hw->irqs[0]; i < oct_hw->nr_vring; i += oct_hw->nb_irqs) {
+		if (ioread8(oct_hw->vqs[i].cb_notify_addr)) {
+			/* Acknowledge the per ring notification to the device */
+			iowrite8(0, oct_hw->vqs[i].cb_notify_addr);
+
+			if (likely(oct_hw->vqs[i].cb.callback))
+				oct_hw->vqs[i].cb.callback(oct_hw->vqs[i].cb.private);
+			break;
 		}
 	}
 
+	/* Check for config interrupt. Config uses the first interrupt */
+	if (unlikely(irq == oct_hw->irqs[0] && ioread8(oct_hw->isr))) {
+		iowrite8(0, oct_hw->isr);
+
+		if (oct_hw->config_cb.callback)
+			oct_hw->config_cb.callback(oct_hw->config_cb.private);
+	}
+
 	return IRQ_HANDLED;
 }
 
 static void octep_free_irqs(struct octep_hw *oct_hw)
 {
 	struct pci_dev *pdev = oct_hw->pdev;
+	int irq;
 
-	if (oct_hw->irq != -1) {
-		devm_free_irq(&pdev->dev, oct_hw->irq, oct_hw);
-		oct_hw->irq = -1;
+	if (!oct_hw->irqs)
+		return;
+
+	for (irq = 0; irq < oct_hw->nb_irqs; irq++) {
+		if (!oct_hw->irqs[irq])
+			break;
+
+		devm_free_irq(&pdev->dev, oct_hw->irqs[irq], oct_hw);
 	}
+
 	pci_free_irq_vectors(pdev);
+	devm_kfree(&pdev->dev, oct_hw->irqs);
+	oct_hw->irqs = NULL;
 }
 
 static int octep_request_irqs(struct octep_hw *oct_hw)
 {
 	struct pci_dev *pdev = oct_hw->pdev;
-	int ret, irq;
+	int ret, irq, idx;
 
-	/* Currently HW device provisions one IRQ per VF, hence
-	 * allocate one IRQ for all virtqueues call interface.
-	 */
-	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
+	oct_hw->irqs = devm_kcalloc(&pdev->dev, oct_hw->nb_irqs, sizeof(int), GFP_KERNEL);
+	if (!oct_hw->irqs)
+		return -ENOMEM;
+
+	ret = pci_alloc_irq_vectors(pdev, 1, oct_hw->nb_irqs, PCI_IRQ_MSIX);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to alloc msix vector");
 		return ret;
 	}
 
-	snprintf(oct_hw->vqs->msix_name, sizeof(oct_hw->vqs->msix_name),
-		 OCTEP_VDPA_DRIVER_NAME "-vf-%d", pci_iov_vf_id(pdev));
-
-	irq = pci_irq_vector(pdev, 0);
-	ret = devm_request_irq(&pdev->dev, irq, octep_vdpa_intr_handler, 0,
-			       oct_hw->vqs->msix_name, oct_hw);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to register interrupt handler\n");
-		goto free_irq_vec;
+	for (idx = 0; idx < oct_hw->nb_irqs; idx++) {
+		irq = pci_irq_vector(pdev, idx);
+		ret = devm_request_irq(&pdev->dev, irq, octep_vdpa_intr_handler, 0,
+				       dev_name(&pdev->dev), oct_hw);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to register interrupt handler\n");
+			goto free_irqs;
+		}
+		oct_hw->irqs[idx] = irq;
 	}
-	oct_hw->irq = irq;
 
 	return 0;
 
-free_irq_vec:
-	pci_free_irq_vectors(pdev);
+free_irqs:
+	octep_free_irqs(oct_hw);
 	return ret;
 }
 
@@ -271,7 +302,9 @@ static u32 octep_vdpa_get_generation(struct vdpa_device *vdpa_dev)
 
 static u32 octep_vdpa_get_device_id(struct vdpa_device *vdpa_dev)
 {
-	return VIRTIO_ID_NET;
+	struct octep_hw *oct_hw = vdpa_to_octep_hw(vdpa_dev);
+
+	return oct_hw->dev_id;
 }
 
 static u32 octep_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev)
@@ -559,6 +592,7 @@ static void octep_vdpa_setup_task(struct work_struct *work)
 	struct device *dev = &pdev->dev;
 	struct octep_hw *oct_hw;
 	unsigned long timeout;
+	u64 val;
 	int ret;
 
 	oct_hw = &mgmt_dev->oct_hw;
@@ -590,6 +624,13 @@ static void octep_vdpa_setup_task(struct work_struct *work)
 	if (ret)
 		return;
 
+	val = readq(oct_hw->base[OCTEP_HW_MBOX_BAR] + OCTEP_VF_IN_CTRL(0));
+	oct_hw->nb_irqs = OCTEP_VF_IN_CTRL_RPVF(val);
+	if (!oct_hw->nb_irqs || oct_hw->nb_irqs > OCTEP_MAX_CB_INTR) {
+		dev_err(dev, "Invalid number of interrupts %d\n", oct_hw->nb_irqs);
+		goto unmap_region;
+	}
+
 	ret = octep_hw_caps_read(oct_hw, pdev);
 	if (ret < 0)
 		goto unmap_region;
@@ -768,12 +809,6 @@ static int octep_vdpa_pf_setup(struct octep_pf *octpf)
 		return -EINVAL;
 	}
 
-	if (OCTEP_EPF_RINFO_RPVF(val) != BIT_ULL(0)) {
-		val &= ~GENMASK_ULL(35, 32);
-		val |= BIT_ULL(32);
-		writeq(val, addr + OCTEP_EPF_RINFO(0));
-	}
-
 	len = pci_resource_len(pdev, OCTEP_HW_CAPS_BAR);
 
 	octpf->vf_stride = len / totalvfs;
diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c
index c8b74980dbd1..55ec51c17ab3 100644
--- a/drivers/vdpa/solidrun/snet_main.c
+++ b/drivers/vdpa/solidrun/snet_main.c
@@ -556,36 +556,38 @@ static const struct vdpa_config_ops snet_config_ops = {
 static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 {
 	char *name;
-	int ret, i, mask = 0;
+	unsigned short i;
+	bool bars_found = false;
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev));
+	if (!name)
+		return -ENOMEM;
+
 	/* We don't know which BAR will be used to communicate..
 	 * We will map every bar with len > 0.
 	 *
 	 * Later, we will discover the BAR and unmap all other BARs.
 	 */
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (pci_resource_len(pdev, i))
-			mask |= (1 << i);
-	}
+		void __iomem *io;
 
-	/* No BAR can be used.. */
-	if (!mask) {
-		SNET_ERR(pdev, "Failed to find a PCI BAR\n");
-		return -ENODEV;
-	}
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
 
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "psnet[%s]-bars", pci_name(pdev));
-	if (!name)
-		return -ENOMEM;
+		io = pcim_iomap_region(pdev, i, name);
+		if (IS_ERR(io)) {
+			SNET_ERR(pdev, "Failed to request and map PCI BARs\n");
+			return PTR_ERR(io);
+		}
 
-	ret = pcim_iomap_regions(pdev, mask, name);
-	if (ret) {
-		SNET_ERR(pdev, "Failed to request and map PCI BARs\n");
-		return ret;
+		psnet->bars[i] = io;
+		bars_found = true;
 	}
 
-	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
-		if (mask & (1 << i))
-			psnet->bars[i] = pcim_iomap_table(pdev)[i];
+	/* No BAR can be used.. */
+	if (!bars_found) {
+		SNET_ERR(pdev, "Failed to find a PCI BAR\n");
+		return -ENODEV;
 	}
 
 	return 0;
@@ -594,20 +596,20 @@ static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet)
 static int snet_open_vf_bar(struct pci_dev *pdev, struct snet *snet)
 {
 	char *name;
-	int ret;
+	void __iomem *io;
 
 	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "snet[%s]-bars", pci_name(pdev));
 	if (!name)
 		return -ENOMEM;
 
 	/* Request and map BAR */
-	ret = pcim_iomap_regions(pdev, BIT(snet->psnet->cfg.vf_bar), name);
-	if (ret) {
+	io = pcim_iomap_region(pdev, snet->psnet->cfg.vf_bar, name);
+	if (IS_ERR(io)) {
 		SNET_ERR(pdev, "Failed to request and map PCI BAR for a VF\n");
-		return ret;
+		return PTR_ERR(io);
 	}
 
-	snet->bar = pcim_iomap_table(pdev)[snet->psnet->cfg.vf_bar];
+	snet->bar = io;
 
 	return 0;
 }
@@ -656,15 +658,12 @@ static int psnet_detect_bar(struct psnet *psnet, u32 off)
 
 static void psnet_unmap_unused_bars(struct pci_dev *pdev, struct psnet *psnet)
 {
-	int i, mask = 0;
+	unsigned short i;
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (psnet->bars[i] && i != psnet->barno)
-			mask |= (1 << i);
+			pcim_iounmap_region(pdev, i);
 	}
-
-	if (mask)
-		pcim_iounmap_regions(pdev, mask);
 }
 
 /* Read SNET config from PCI BAR */
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index 16380764275e..8787407f75b0 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -367,6 +367,14 @@ static void vp_vdpa_kick_vq(struct vdpa_device *vdpa, u16 qid)
 	vp_iowrite16(qid, vp_vdpa->vring[qid].notify);
 }
 
+static void vp_vdpa_kick_vq_with_data(struct vdpa_device *vdpa, u32 data)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	u16 qid = data & 0xFFFF;
+
+	vp_iowrite32(data, vp_vdpa->vring[qid].notify);
+}
+
 static u32 vp_vdpa_get_generation(struct vdpa_device *vdpa)
 {
 	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
@@ -472,6 +480,7 @@ static const struct vdpa_config_ops vp_vdpa_ops = {
 	.get_vq_size	= vp_vdpa_get_vq_size,
 	.set_vq_address	= vp_vdpa_set_vq_address,
 	.kick_vq	= vp_vdpa_kick_vq,
+	.kick_vq_with_data      = vp_vdpa_kick_vq_with_data,
 	.get_generation	= vp_vdpa_get_generation,
 	.get_device_id	= vp_vdpa_get_device_id,
 	.get_vendor_id	= vp_vdpa_get_vendor_id,
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index ed4737de4528..f2e686f8f1ef 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -76,7 +76,7 @@ int mdev_register_parent(struct mdev_parent *parent, struct device *dev,
 	if (ret)
 		return ret;
 
-	ret = class_compat_create_link(mdev_bus_compat_class, dev, NULL);
+	ret = class_compat_create_link(mdev_bus_compat_class, dev);
 	if (ret)
 		dev_warn(dev, "Failed to create compatibility class link\n");
 
@@ -98,7 +98,7 @@ void mdev_unregister_parent(struct mdev_parent *parent)
 	dev_info(parent->dev, "MDEV: Unregistering\n");
 
 	down_write(&parent->unreg_sem);
-	class_compat_remove_link(mdev_bus_compat_class, parent->dev, NULL);
+	class_compat_remove_link(mdev_bus_compat_class, parent->dev);
 	device_for_each_child(parent->dev, NULL, mdev_device_remove_cb);
 	parent_remove_sysfs_files(parent);
 	up_write(&parent->unreg_sem);
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index eb7387ee6ebd..11eda6b207f1 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -408,7 +408,7 @@ void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf)
 				  buf->dma_dir, 0);
 	}
 
-	/* Undo alloc_pages_bulk_array() */
+	/* Undo alloc_pages_bulk() */
 	for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0)
 		__free_page(sg_page_iter_page(&sg_iter));
 	sg_free_append_table(&buf->table);
@@ -431,8 +431,8 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 		return -ENOMEM;
 
 	do {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill,
-						page_list);
+		filled = alloc_pages_bulk(GFP_KERNEL_ACCOUNT, to_fill,
+					  page_list);
 		if (!filled) {
 			ret = -ENOMEM;
 			goto err;
@@ -1342,7 +1342,7 @@ static void free_recv_pages(struct mlx5_vhca_recv_buf *recv_buf)
 {
 	int i;
 
-	/* Undo alloc_pages_bulk_array() */
+	/* Undo alloc_pages_bulk() */
 	for (i = 0; i < recv_buf->npages; i++)
 		__free_page(recv_buf->page_list[i]);
 
@@ -1361,9 +1361,9 @@ static int alloc_recv_pages(struct mlx5_vhca_recv_buf *recv_buf,
 		return -ENOMEM;
 
 	for (;;) {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT,
-						npages - done,
-						recv_buf->page_list + done);
+		filled = alloc_pages_bulk(GFP_KERNEL_ACCOUNT,
+					  npages - done,
+					  recv_buf->page_list + done);
 		if (!filled)
 			goto err;
 
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index a467085038f0..e5ac39c4cc6b 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -5,6 +5,8 @@
 
 #include <linux/sizes.h>
 #include <linux/vfio_pci_core.h>
+#include <linux/delay.h>
+#include <linux/jiffies.h>
 
 /*
  * The device memory usable to the workloads running in the VM is cached
@@ -17,12 +19,21 @@
 #define RESMEM_REGION_INDEX VFIO_PCI_BAR2_REGION_INDEX
 #define USEMEM_REGION_INDEX VFIO_PCI_BAR4_REGION_INDEX
 
-/* Memory size expected as non cached and reserved by the VM driver */
-#define RESMEM_SIZE SZ_1G
-
 /* A hardwired and constant ABI value between the GPU FW and VFIO driver. */
 #define MEMBLK_SIZE SZ_512M
 
+#define DVSEC_BITMAP_OFFSET 0xA
+#define MIG_SUPPORTED_WITH_CACHED_RESMEM BIT(0)
+
+#define GPU_CAP_DVSEC_REGISTER 3
+
+#define C2C_LINK_BAR0_OFFSET 0x1498
+#define HBM_TRAINING_BAR0_OFFSET 0x200BC
+#define STATUS_READY 0xFF
+
+#define POLL_QUANTUM_MS 1000
+#define POLL_TIMEOUT_MS (30 * 1000)
+
 /*
  * The state of the two device memory region - resmem and usemem - is
  * saved as struct mem_region.
@@ -46,6 +57,7 @@ struct nvgrace_gpu_pci_core_device {
 	struct mem_region resmem;
 	/* Lock to control device memory kernel mapping */
 	struct mutex remap_lock;
+	bool has_mig_hw_bug;
 };
 
 static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev)
@@ -66,7 +78,7 @@ nvgrace_gpu_memregion(int index,
 	if (index == USEMEM_REGION_INDEX)
 		return &nvdev->usemem;
 
-	if (index == RESMEM_REGION_INDEX)
+	if (nvdev->resmem.memlength && index == RESMEM_REGION_INDEX)
 		return &nvdev->resmem;
 
 	return NULL;
@@ -751,40 +763,67 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
 			      u64 memphys, u64 memlength)
 {
 	int ret = 0;
+	u64 resmem_size = 0;
 
 	/*
-	 * The VM GPU device driver needs a non-cacheable region to support
-	 * the MIG feature. Since the device memory is mapped as NORMAL cached,
-	 * carve out a region from the end with a different NORMAL_NC
-	 * property (called as reserved memory and represented as resmem). This
-	 * region then is exposed as a 64b BAR (region 2 and 3) to the VM, while
-	 * exposing the rest (termed as usable memory and represented using usemem)
-	 * as cacheable 64b BAR (region 4 and 5).
+	 * On Grace Hopper systems, the VM GPU device driver needs a non-cacheable
+	 * region to support the MIG feature owing to a hardware bug. Since the
+	 * device memory is mapped as NORMAL cached, carve out a region from the end
+	 * with a different NORMAL_NC property (called as reserved memory and
+	 * represented as resmem). This region then is exposed as a 64b BAR
+	 * (region 2 and 3) to the VM, while exposing the rest (termed as usable
+	 * memory and represented using usemem) as cacheable 64b BAR (region 4 and 5).
 	 *
 	 *               devmem (memlength)
 	 * |-------------------------------------------------|
 	 * |                                           |
 	 * usemem.memphys                              resmem.memphys
+	 *
+	 * This hardware bug is fixed on the Grace Blackwell platforms and the
+	 * presence of the bug can be determined through nvdev->has_mig_hw_bug.
+	 * Thus on systems with the hardware fix, there is no need to partition
+	 * the GPU device memory and the entire memory is usable and mapped as
+	 * NORMAL cached (i.e. resmem size is 0).
 	 */
+	if (nvdev->has_mig_hw_bug)
+		resmem_size = SZ_1G;
+
 	nvdev->usemem.memphys = memphys;
 
 	/*
 	 * The device memory exposed to the VM is added to the kernel by the
-	 * VM driver module in chunks of memory block size. Only the usable
-	 * memory (usemem) is added to the kernel for usage by the VM
-	 * workloads. Make the usable memory size memblock aligned.
+	 * VM driver module in chunks of memory block size. Note that only the
+	 * usable memory (usemem) is added to the kernel for usage by the VM
+	 * workloads.
 	 */
-	if (check_sub_overflow(memlength, RESMEM_SIZE,
+	if (check_sub_overflow(memlength, resmem_size,
 			       &nvdev->usemem.memlength)) {
 		ret = -EOVERFLOW;
 		goto done;
 	}
 
 	/*
-	 * The USEMEM part of the device memory has to be MEMBLK_SIZE
-	 * aligned. This is a hardwired ABI value between the GPU FW and
-	 * VFIO driver. The VM device driver is also aware of it and make
-	 * use of the value for its calculation to determine USEMEM size.
+	 * The usemem region is exposed as a 64B Bar composed of region 4 and 5.
+	 * Calculate and save the BAR size for the region.
+	 */
+	nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength);
+
+	/*
+	 * If the hardware has the fix for MIG, there is no requirement
+	 * for splitting the device memory to create RESMEM. The entire
+	 * device memory is usable and will be USEMEM. Return here for
+	 * such case.
+	 */
+	if (!nvdev->has_mig_hw_bug)
+		goto done;
+
+	/*
+	 * When the device memory is split to workaround the MIG bug on
+	 * Grace Hopper, the USEMEM part of the device memory has to be
+	 * MEMBLK_SIZE aligned. This is a hardwired ABI value between the
+	 * GPU FW and VFIO driver. The VM device driver is also aware of it
+	 * and make use of the value for its calculation to determine USEMEM
+	 * size. Note that the device memory may not be 512M aligned.
 	 */
 	nvdev->usemem.memlength = round_down(nvdev->usemem.memlength,
 					     MEMBLK_SIZE);
@@ -803,15 +842,93 @@ nvgrace_gpu_init_nvdev_struct(struct pci_dev *pdev,
 	}
 
 	/*
-	 * The memory regions are exposed as BARs. Calculate and save
-	 * the BAR size for them.
+	 * The resmem region is exposed as a 64b BAR composed of region 2 and 3
+	 * for Grace Hopper. Calculate and save the BAR size for the region.
 	 */
-	nvdev->usemem.bar_size = roundup_pow_of_two(nvdev->usemem.memlength);
 	nvdev->resmem.bar_size = roundup_pow_of_two(nvdev->resmem.memlength);
 done:
 	return ret;
 }
 
+static bool nvgrace_gpu_has_mig_hw_bug(struct pci_dev *pdev)
+{
+	int pcie_dvsec;
+	u16 dvsec_ctrl16;
+
+	pcie_dvsec = pci_find_dvsec_capability(pdev, PCI_VENDOR_ID_NVIDIA,
+					       GPU_CAP_DVSEC_REGISTER);
+
+	if (pcie_dvsec) {
+		pci_read_config_word(pdev,
+				     pcie_dvsec + DVSEC_BITMAP_OFFSET,
+				     &dvsec_ctrl16);
+
+		if (dvsec_ctrl16 & MIG_SUPPORTED_WITH_CACHED_RESMEM)
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * To reduce the system bootup time, the HBM training has
+ * been moved out of the UEFI on the Grace-Blackwell systems.
+ *
+ * The onus of checking whether the HBM training has completed
+ * thus falls on the module. The HBM training status can be
+ * determined from a BAR0 register.
+ *
+ * Similarly, another BAR0 register exposes the status of the
+ * CPU-GPU chip-to-chip (C2C) cache coherent interconnect.
+ *
+ * Poll these register and check for 30s. If the HBM training is
+ * not complete or if the C2C link is not ready, fail the probe.
+ *
+ * While the wait is not required on Grace Hopper systems, it
+ * is beneficial to make the check to ensure the device is in an
+ * expected state.
+ *
+ * Ensure that the BAR0 region is enabled before accessing the
+ * registers.
+ */
+static int nvgrace_gpu_wait_device_ready(struct pci_dev *pdev)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(POLL_TIMEOUT_MS);
+	void __iomem *io;
+	int ret = -ETIME;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	ret = pci_request_selected_regions(pdev, 1 << 0, KBUILD_MODNAME);
+	if (ret)
+		goto request_region_exit;
+
+	io = pci_iomap(pdev, 0, 0);
+	if (!io) {
+		ret = -ENOMEM;
+		goto iomap_exit;
+	}
+
+	do {
+		if ((ioread32(io + C2C_LINK_BAR0_OFFSET) == STATUS_READY) &&
+		    (ioread32(io + HBM_TRAINING_BAR0_OFFSET) == STATUS_READY)) {
+			ret = 0;
+			goto reg_check_exit;
+		}
+		msleep(POLL_QUANTUM_MS);
+	} while (!time_after(jiffies, timeout));
+
+reg_check_exit:
+	pci_iounmap(pdev, io);
+iomap_exit:
+	pci_release_selected_regions(pdev, 1 << 0);
+request_region_exit:
+	pci_disable_device(pdev);
+	return ret;
+}
+
 static int nvgrace_gpu_probe(struct pci_dev *pdev,
 			     const struct pci_device_id *id)
 {
@@ -820,6 +937,10 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev,
 	u64 memphys, memlength;
 	int ret;
 
+	ret = nvgrace_gpu_wait_device_ready(pdev);
+	if (ret)
+		return ret;
+
 	ret = nvgrace_gpu_fetch_memory_property(pdev, &memphys, &memlength);
 	if (!ret)
 		ops = &nvgrace_gpu_pci_ops;
@@ -832,6 +953,8 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev,
 	dev_set_drvdata(&pdev->dev, &nvdev->core_device);
 
 	if (ops == &nvgrace_gpu_pci_ops) {
+		nvdev->has_mig_hw_bug = nvgrace_gpu_has_mig_hw_bug(pdev);
+
 		/*
 		 * Device memory properties are identified in the host ACPI
 		 * table. Set the nvgrace_gpu_pci_core_device structure.
@@ -868,6 +991,8 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = {
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2345) },
 	/* GH200 SKU */
 	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2348) },
+	/* GB200 SKU */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_NVIDIA, 0x2941) },
 	{}
 };
 
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 5572fd99b921..94142581c98c 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -511,13 +511,13 @@ static void vfio_bar_fixup(struct vfio_pci_core_device *vdev)
 		mask = ~(pci_resource_len(pdev, PCI_ROM_RESOURCE) - 1);
 		mask |= PCI_ROM_ADDRESS_ENABLE;
 		*vbar &= cpu_to_le32((u32)mask);
-	} else if (pdev->resource[PCI_ROM_RESOURCE].flags &
-					IORESOURCE_ROM_SHADOW) {
-		mask = ~(0x20000 - 1);
+	} else if (pdev->rom && pdev->romlen) {
+		mask = ~(roundup_pow_of_two(pdev->romlen) - 1);
 		mask |= PCI_ROM_ADDRESS_ENABLE;
 		*vbar &= cpu_to_le32((u32)mask);
-	} else
+	} else {
 		*vbar = 0;
+	}
 
 	vdev->bardirty = false;
 }
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 1a4ed5a357d3..586e49efb81b 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1054,31 +1054,27 @@ static int vfio_pci_ioctl_get_region_info(struct vfio_pci_core_device *vdev,
 
 		info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
 		info.flags = 0;
+		info.size = 0;
 
-		/* Report the BAR size, not the ROM size */
-		info.size = pci_resource_len(pdev, info.index);
-		if (!info.size) {
-			/* Shadow ROMs appear as PCI option ROMs */
-			if (pdev->resource[PCI_ROM_RESOURCE].flags &
-			    IORESOURCE_ROM_SHADOW)
-				info.size = 0x20000;
-			else
-				break;
-		}
-
-		/*
-		 * Is it really there?  Enable memory decode for implicit access
-		 * in pci_map_rom().
-		 */
-		cmd = vfio_pci_memory_lock_and_enable(vdev);
-		io = pci_map_rom(pdev, &size);
-		if (io) {
+		if (pci_resource_start(pdev, PCI_ROM_RESOURCE)) {
+			/*
+			 * Check ROM content is valid. Need to enable memory
+			 * decode for ROM access in pci_map_rom().
+			 */
+			cmd = vfio_pci_memory_lock_and_enable(vdev);
+			io = pci_map_rom(pdev, &size);
+			if (io) {
+				info.flags = VFIO_REGION_INFO_FLAG_READ;
+				/* Report the BAR size, not the ROM size. */
+				info.size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+				pci_unmap_rom(pdev, io);
+			}
+			vfio_pci_memory_unlock_and_restore(vdev, cmd);
+		} else if (pdev->rom && pdev->romlen) {
 			info.flags = VFIO_REGION_INFO_FLAG_READ;
-			pci_unmap_rom(pdev, io);
-		} else {
-			info.size = 0;
+			/* Report BAR size as power of two. */
+			info.size = roundup_pow_of_two(pdev->romlen);
 		}
-		vfio_pci_memory_unlock_and_restore(vdev, cmd);
 
 		break;
 	}
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 66b72c289284..6192788c8ba3 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "vfio_pci_priv.h"
 
@@ -61,9 +62,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_iowrite##size);
 VFIO_IOWRITE(8)
 VFIO_IOWRITE(16)
 VFIO_IOWRITE(32)
-#ifdef iowrite64
 VFIO_IOWRITE(64)
-#endif
 
 #define VFIO_IOREAD(size) \
 int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev,	\
@@ -89,9 +88,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_ioread##size);
 VFIO_IOREAD(8)
 VFIO_IOREAD(16)
 VFIO_IOREAD(32)
-#ifdef ioread64
 VFIO_IOREAD(64)
-#endif
 
 #define VFIO_IORDWR(size)						\
 static int vfio_pci_iordwr##size(struct vfio_pci_core_device *vdev,\
@@ -127,9 +124,7 @@ static int vfio_pci_iordwr##size(struct vfio_pci_core_device *vdev,\
 VFIO_IORDWR(8)
 VFIO_IORDWR(16)
 VFIO_IORDWR(32)
-#if defined(ioread64) && defined(iowrite64)
 VFIO_IORDWR(64)
-#endif
 
 /*
  * Read or write from an __iomem region (MMIO or I/O port) with an excluded
@@ -155,7 +150,6 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 		else
 			fillable = 0;
 
-#if defined(ioread64) && defined(iowrite64)
 		if (fillable >= 8 && !(off % 8)) {
 			ret = vfio_pci_iordwr64(vdev, iswrite, test_mem,
 						io, buf, off, &filled);
@@ -163,7 +157,6 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 				return ret;
 
 		} else
-#endif
 		if (fillable >= 4 && !(off % 4)) {
 			ret = vfio_pci_iordwr32(vdev, iswrite, test_mem,
 						io, buf, off, &filled);
@@ -244,9 +237,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 
 	if (pci_resource_start(pdev, bar))
 		end = pci_resource_len(pdev, bar);
-	else if (bar == PCI_ROM_RESOURCE &&
-		 pdev->resource[bar].flags & IORESOURCE_ROM_SHADOW)
-		end = 0x20000;
+	else if (bar == PCI_ROM_RESOURCE && pdev->rom && pdev->romlen)
+		end = roundup_pow_of_two(pdev->romlen);
 	else
 		return -EINVAL;
 
@@ -261,11 +253,14 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 		 * excluded range at the end of the actual ROM.  This makes
 		 * filling large ROM BARs much faster.
 		 */
-		io = pci_map_rom(pdev, &x_start);
-		if (!io) {
-			done = -ENOMEM;
-			goto out;
+		if (pci_resource_start(pdev, bar)) {
+			io = pci_map_rom(pdev, &x_start);
+		} else {
+			io = ioremap(pdev->rom, pdev->romlen);
+			x_start = pdev->romlen;
 		}
+		if (!io)
+			return -ENOMEM;
 		x_end = end;
 	} else {
 		int ret = vfio_pci_core_setup_barmap(vdev, bar);
@@ -288,8 +283,13 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf,
 	if (done >= 0)
 		*ppos += done;
 
-	if (bar == PCI_ROM_RESOURCE)
-		pci_unmap_rom(pdev, io);
+	if (bar == PCI_ROM_RESOURCE) {
+		if (pci_resource_start(pdev, bar))
+			pci_unmap_rom(pdev, io);
+		else
+			iounmap(io);
+	}
+
 out:
 	return done;
 }
@@ -381,12 +381,10 @@ static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
 		vfio_pci_core_iowrite32(ioeventfd->vdev, test_mem,
 					ioeventfd->data, ioeventfd->addr);
 		break;
-#ifdef iowrite64
 	case 8:
 		vfio_pci_core_iowrite64(ioeventfd->vdev, test_mem,
 					ioeventfd->data, ioeventfd->addr);
 		break;
-#endif
 	}
 }
 
@@ -440,10 +438,8 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 	      pos >= vdev->msix_offset + vdev->msix_size))
 		return -EINVAL;
 
-#ifndef iowrite64
 	if (count == 8)
 		return -EINVAL;
-#endif
 
 	ret = vfio_pci_core_setup_barmap(vdev, bar);
 	if (ret)
diff --git a/drivers/vfio/pci/virtio/migrate.c b/drivers/vfio/pci/virtio/migrate.c
index ee54f4c17857..ba92bb4e9af9 100644
--- a/drivers/vfio/pci/virtio/migrate.c
+++ b/drivers/vfio/pci/virtio/migrate.c
@@ -77,8 +77,8 @@ static int virtiovf_add_migration_pages(struct virtiovf_data_buffer *buf,
 		return -ENOMEM;
 
 	do {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill,
-						page_list);
+		filled = alloc_pages_bulk(GFP_KERNEL_ACCOUNT, to_fill,
+					  page_list);
 		if (!filled) {
 			ret = -ENOMEM;
 			goto err;
@@ -112,7 +112,7 @@ static void virtiovf_free_data_buffer(struct virtiovf_data_buffer *buf)
 {
 	struct sg_page_iter sg_iter;
 
-	/* Undo alloc_pages_bulk_array() */
+	/* Undo alloc_pages_bulk() */
 	for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0)
 		__free_page(sg_page_iter_page(&sg_iter));
 	sg_free_append_table(&buf->table);
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index e53757d1d095..3bf1043cd795 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -388,6 +388,11 @@ static ssize_t vfio_platform_read_mmio(struct vfio_platform_region *reg,
 {
 	unsigned int done = 0;
 
+	if (off >= reg->size)
+		return -EINVAL;
+
+	count = min_t(size_t, count, reg->size - off);
+
 	if (!reg->ioaddr) {
 		reg->ioaddr =
 			ioremap(reg->addr, reg->size);
@@ -467,6 +472,11 @@ static ssize_t vfio_platform_write_mmio(struct vfio_platform_region *reg,
 {
 	unsigned int done = 0;
 
+	if (off >= reg->size)
+		return -EINVAL;
+
+	count = min_t(size_t, count, reg->size - off);
+
 	if (!reg->ioaddr) {
 		reg->ioaddr =
 			ioremap(reg->addr, reg->size);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9ad37c012189..b9b9e9d40951 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1107,6 +1107,7 @@ static void handle_rx(struct vhost_net *net)
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	bool busyloop_intr = false;
+	bool set_num_buffers;
 	struct socket *sock;
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
@@ -1129,6 +1130,8 @@ static void handle_rx(struct vhost_net *net)
 	vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ?
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
+	set_num_buffers = mergeable ||
+			  vhost_has_feature(vq, VIRTIO_F_VERSION_1);
 
 	do {
 		sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
@@ -1205,7 +1208,7 @@ static void handle_rx(struct vhost_net *net)
 		/* TODO: Should check and handle checksum. */
 
 		num_buffers = cpu_to_vhost16(vq, headcount);
-		if (likely(mergeable) &&
+		if (likely(set_num_buffers) &&
 		    copy_to_iter(&num_buffers, sizeof num_buffers,
 				 &fixup) != sizeof num_buffers) {
 			vq_err(vq, "Failed num_buffers write");
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index b10ed9f5b543..ba37665188b5 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -546,29 +546,7 @@ void unregister_virtio_device(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_device);
 
-#ifdef CONFIG_PM_SLEEP
-int virtio_device_freeze(struct virtio_device *dev)
-{
-	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
-	int ret;
-
-	virtio_config_core_disable(dev);
-
-	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
-
-	if (drv && drv->freeze) {
-		ret = drv->freeze(dev);
-		if (ret) {
-			virtio_config_core_enable(dev);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(virtio_device_freeze);
-
-int virtio_device_restore(struct virtio_device *dev)
+static int virtio_device_restore_priv(struct virtio_device *dev, bool restore)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	int ret;
@@ -599,8 +577,14 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (ret)
 		goto err;
 
-	if (drv->restore) {
-		ret = drv->restore(dev);
+	if (restore) {
+		if (drv->restore) {
+			ret = drv->restore(dev);
+			if (ret)
+				goto err;
+		}
+	} else {
+		ret = drv->reset_done(dev);
 		if (ret)
 			goto err;
 	}
@@ -617,9 +601,69 @@ err:
 	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return ret;
 }
+
+#ifdef CONFIG_PM_SLEEP
+int virtio_device_freeze(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	virtio_config_core_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	if (drv && drv->freeze) {
+		ret = drv->freeze(dev);
+		if (ret) {
+			virtio_config_core_enable(dev);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_freeze);
+
+int virtio_device_restore(struct virtio_device *dev)
+{
+	return virtio_device_restore_priv(dev, true);
+}
 EXPORT_SYMBOL_GPL(virtio_device_restore);
 #endif
 
+int virtio_device_reset_prepare(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+	int ret;
+
+	if (!drv || !drv->reset_prepare)
+		return -EOPNOTSUPP;
+
+	virtio_config_core_disable(dev);
+
+	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
+
+	ret = drv->reset_prepare(dev);
+	if (ret) {
+		virtio_config_core_enable(dev);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_device_reset_prepare);
+
+int virtio_device_reset_done(struct virtio_device *dev)
+{
+	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
+
+	if (!drv || !drv->reset_done)
+		return -EOPNOTSUPP;
+
+	return virtio_device_restore_priv(dev, false);
+}
+EXPORT_SYMBOL_GPL(virtio_device_reset_done);
+
 static int virtio_init(void)
 {
 	if (bus_register(&virtio_bus) != 0)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index b36d2803674e..89da052f4f68 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -251,7 +251,7 @@ static unsigned int fill_balloon(struct virtio_balloon *vb, size_t num)
 
 	for (num_pfns = 0; num_pfns < num;
 	     num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
-		struct page *page = balloon_page_alloc();
+		page = balloon_page_alloc();
 
 		if (!page) {
 			dev_info_ratelimited(&vb->vdev->dev,
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index b0b871441578..8a294b9cbcf6 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -133,6 +133,8 @@ struct virtio_mem {
 	uint64_t addr;
 	/* Maximum region size in bytes. */
 	uint64_t region_size;
+	/* Usable region size in bytes. */
+	uint64_t usable_region_size;
 
 	/* The parent resource for all memory added via this device. */
 	struct resource *parent_resource;
@@ -2368,7 +2370,7 @@ static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm)
 static void virtio_mem_refresh_config(struct virtio_mem *vm)
 {
 	const struct range pluggable_range = mhp_get_pluggable_range(true);
-	uint64_t new_plugged_size, usable_region_size, end_addr;
+	uint64_t new_plugged_size, end_addr;
 
 	/* the plugged_size is just a reflection of what _we_ did previously */
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
@@ -2378,8 +2380,8 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm)
 
 	/* calculate the last usable memory block id */
 	virtio_cread_le(vm->vdev, struct virtio_mem_config,
-			usable_region_size, &usable_region_size);
-	end_addr = min(vm->addr + usable_region_size - 1,
+			usable_region_size, &vm->usable_region_size);
+	end_addr = min(vm->addr + vm->usable_region_size - 1,
 		       pluggable_range.end);
 
 	if (vm->in_sbm) {
@@ -2648,6 +2650,7 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm)
 	if (rc)
 		goto out_unreg_pm;
 
+	virtio_device_ready(vm->vdev);
 	return 0;
 out_unreg_pm:
 	unregister_pm_notifier(&vm->pm_notifier);
@@ -2725,13 +2728,103 @@ static bool virtio_mem_vmcore_pfn_is_ram(struct vmcore_cb *cb,
 	mutex_unlock(&vm->hotplug_mutex);
 	return is_ram;
 }
+
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+static int virtio_mem_vmcore_add_device_ram(struct virtio_mem *vm,
+		struct list_head *list, uint64_t start, uint64_t end)
+{
+	int rc;
+
+	rc = vmcore_alloc_add_range(list, start, end - start);
+	if (rc)
+		dev_err(&vm->vdev->dev,
+			 "Error adding device RAM range: %d\n", rc);
+	return rc;
+}
+
+static int virtio_mem_vmcore_get_device_ram(struct vmcore_cb *cb,
+		struct list_head *list)
+{
+	struct virtio_mem *vm = container_of(cb, struct virtio_mem,
+					     vmcore_cb);
+	const uint64_t device_start = vm->addr;
+	const uint64_t device_end = vm->addr + vm->usable_region_size;
+	uint64_t chunk_size, cur_start, cur_end, plugged_range_start = 0;
+	LIST_HEAD(tmp_list);
+	int rc;
+
+	if (!vm->plugged_size)
+		return 0;
+
+	/* Process memory sections, unless the device block size is bigger. */
+	chunk_size = max_t(uint64_t, PFN_PHYS(PAGES_PER_SECTION),
+			   vm->device_block_size);
+
+	mutex_lock(&vm->hotplug_mutex);
+
+	/*
+	 * We process larger chunks and indicate the complete chunk if any
+	 * block in there is plugged. This reduces the number of pfn_is_ram()
+	 * callbacks and mimic what is effectively being done when the old
+	 * kernel would add complete memory sections/blocks to the elfcore hdr.
+	 */
+	cur_start = device_start;
+	for (cur_start = device_start; cur_start < device_end; cur_start = cur_end) {
+		cur_end = ALIGN_DOWN(cur_start + chunk_size, chunk_size);
+		cur_end = min_t(uint64_t, cur_end, device_end);
+
+		rc = virtio_mem_send_state_request(vm, cur_start,
+						   cur_end - cur_start);
+
+		if (rc < 0) {
+			dev_err(&vm->vdev->dev,
+				"Error querying block states: %d\n", rc);
+			goto out;
+		} else if (rc != VIRTIO_MEM_STATE_UNPLUGGED) {
+			/* Merge ranges with plugged memory. */
+			if (!plugged_range_start)
+				plugged_range_start = cur_start;
+			continue;
+		}
+
+		/* Flush any plugged range. */
+		if (plugged_range_start) {
+			rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list,
+							      plugged_range_start,
+							      cur_start);
+			if (rc)
+				goto out;
+			plugged_range_start = 0;
+		}
+	}
+
+	/* Flush any plugged range. */
+	if (plugged_range_start)
+		rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list,
+						      plugged_range_start,
+						      cur_start);
+out:
+	mutex_unlock(&vm->hotplug_mutex);
+	if (rc < 0) {
+		vmcore_free_ranges(&tmp_list);
+		return rc;
+	}
+	list_splice_tail(&tmp_list, list);
+	return 0;
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
 #endif /* CONFIG_PROC_VMCORE */
 
 static int virtio_mem_init_kdump(struct virtio_mem *vm)
 {
+	/* We must be prepared to receive a callback immediately. */
+	virtio_device_ready(vm->vdev);
 #ifdef CONFIG_PROC_VMCORE
 	dev_info(&vm->vdev->dev, "memory hot(un)plug disabled in kdump kernel\n");
 	vm->vmcore_cb.pfn_is_ram = virtio_mem_vmcore_pfn_is_ram;
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+	vm->vmcore_cb.get_device_ram = virtio_mem_vmcore_get_device_ram;
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
 	register_vmcore_cb(&vm->vmcore_cb);
 	return 0;
 #else /* CONFIG_PROC_VMCORE */
@@ -2760,6 +2853,8 @@ static int virtio_mem_init(struct virtio_mem *vm)
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
 	virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
 			&vm->region_size);
+	virtio_cread_le(vm->vdev, struct virtio_mem_config, usable_region_size,
+			&vm->usable_region_size);
 
 	/* Determine the nid for the device based on the lowest address. */
 	if (vm->nid == NUMA_NO_NODE)
@@ -2870,8 +2965,6 @@ static int virtio_mem_probe(struct virtio_device *vdev)
 	if (rc)
 		goto out_del_vq;
 
-	virtio_device_ready(vdev);
-
 	/* trigger a config update to start processing the requested_size */
 	if (!vm->in_kdump) {
 		atomic_set(&vm->config_changed, 1);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 88074451dd61..d6d79af44569 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -794,6 +794,46 @@ static int virtio_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs)
 	return num_vfs;
 }
 
+static void virtio_pci_reset_prepare(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret = 0;
+
+	ret = virtio_device_reset_prepare(&vp_dev->vdev);
+	if (ret) {
+		if (ret != -EOPNOTSUPP)
+			dev_warn(&pci_dev->dev, "Reset prepare failure: %d",
+				 ret);
+		return;
+	}
+
+	if (pci_is_enabled(pci_dev))
+		pci_disable_device(pci_dev);
+}
+
+static void virtio_pci_reset_done(struct pci_dev *pci_dev)
+{
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+	int ret;
+
+	if (pci_is_enabled(pci_dev))
+		return;
+
+	ret = pci_enable_device(pci_dev);
+	if (!ret) {
+		pci_set_master(pci_dev);
+		ret = virtio_device_reset_done(&vp_dev->vdev);
+	}
+
+	if (ret && ret != -EOPNOTSUPP)
+		dev_warn(&pci_dev->dev, "Reset done failure: %d", ret);
+}
+
+static const struct pci_error_handlers virtio_pci_err_handler = {
+	.reset_prepare  = virtio_pci_reset_prepare,
+	.reset_done     = virtio_pci_reset_done,
+};
+
 static struct pci_driver virtio_pci_driver = {
 	.name		= "virtio-pci",
 	.id_table	= virtio_pci_id_table,
@@ -803,6 +843,7 @@ static struct pci_driver virtio_pci_driver = {
 	.driver.pm	= &virtio_pci_pm_ops,
 #endif
 	.sriov_configure = virtio_pci_sriov_configure,
+	.err_handler	= &virtio_pci_err_handler,
 };
 
 struct virtio_device *virtio_pci_vf_get_pf_dev(struct pci_dev *pdev)
diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c
index a2ecbb863c57..e2a568c9a43a 100644
--- a/drivers/w1/masters/ds2482.c
+++ b/drivers/w1/masters/ds2482.c
@@ -7,7 +7,7 @@
  * It is a I2C to 1-wire bridge.
  * There are two variations: -100 and -800, which have 1 or 8 1-wire ports.
  * The complete datasheet can be obtained from MAXIM's website at:
- *   http://www.maxim-ic.com/quick_view2.cfm/qv_pk/4382
+ *   https://www.analog.com/en/products/ds2482-100.html
  */
 
 #include <linux/module.h>
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/i2c.h>
 #include <linux/delay.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/w1.h>
 
@@ -445,17 +446,20 @@ static int ds2482_probe(struct i2c_client *client)
 	int err = -ENODEV;
 	int temp1;
 	int idx;
+	int ret;
 
 	if (!i2c_check_functionality(client->adapter,
 				     I2C_FUNC_SMBUS_WRITE_BYTE_DATA |
 				     I2C_FUNC_SMBUS_BYTE))
 		return -ENODEV;
 
-	data = kzalloc(sizeof(struct ds2482_data), GFP_KERNEL);
-	if (!data) {
-		err = -ENOMEM;
-		goto exit;
-	}
+	data = devm_kzalloc(&client->dev, sizeof(struct ds2482_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = devm_regulator_get_enable(&client->dev, "vcc");
+	if (ret)
+		return dev_err_probe(&client->dev, ret, "Failed to enable regulator\n");
 
 	data->client = client;
 	i2c_set_clientdata(client, data);
@@ -463,7 +467,7 @@ static int ds2482_probe(struct i2c_client *client)
 	/* Reset the device (sets the read_ptr to status) */
 	if (ds2482_send_cmd(data, DS2482_CMD_RESET) < 0) {
 		dev_warn(&client->dev, "DS2482 reset failed.\n");
-		goto exit_free;
+		return err;
 	}
 
 	/* Sleep at least 525ns to allow the reset to complete */
@@ -474,7 +478,7 @@ static int ds2482_probe(struct i2c_client *client)
 	if (temp1 != (DS2482_REG_STS_LL | DS2482_REG_STS_RST)) {
 		dev_warn(&client->dev, "DS2482 reset status "
 			 "0x%02X - not a DS2482\n", temp1);
-		goto exit_free;
+		return err;
 	}
 
 	/* Detect the 8-port version */
@@ -516,9 +520,6 @@ exit_w1_remove:
 		if (data->w1_ch[idx].pdev != NULL)
 			w1_remove_master_device(&data->w1_ch[idx].w1_bm);
 	}
-exit_free:
-	kfree(data);
-exit:
 	return err;
 }
 
@@ -532,9 +533,6 @@ static void ds2482_remove(struct i2c_client *client)
 		if (data->w1_ch[idx].pdev != NULL)
 			w1_remove_master_device(&data->w1_ch[idx].w1_bm);
 	}
-
-	/* Free the memory */
-	kfree(data);
 }
 
 /*
diff --git a/drivers/w1/slaves/w1_ds2406.c b/drivers/w1/slaves/w1_ds2406.c
index 2f5926859b8b..1cae9b243ff8 100644
--- a/drivers/w1/slaves/w1_ds2406.c
+++ b/drivers/w1/slaves/w1_ds2406.c
@@ -24,7 +24,7 @@
 
 static ssize_t w1_f12_read_state(
 	struct file *filp, struct kobject *kobj,
-	struct bin_attribute *bin_attr,
+	const struct bin_attribute *bin_attr,
 	char *buf, loff_t off, size_t count)
 {
 	u8 w1_buf[6] = {W1_F12_FUNC_READ_STATUS, 7, 0, 0, 0, 0};
@@ -61,7 +61,7 @@ static ssize_t w1_f12_read_state(
 
 static ssize_t w1_f12_write_output(
 	struct file *filp, struct kobject *kobj,
-	struct bin_attribute *bin_attr,
+	const struct bin_attribute *bin_attr,
 	char *buf, loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -95,14 +95,14 @@ static ssize_t w1_f12_write_output(
 }
 
 #define NB_SYSFS_BIN_FILES 2
-static struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = {
+static const struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = {
 	{
 		.attr = {
 			.name = "state",
 			.mode = 0444,
 		},
 		.size = 1,
-		.read = w1_f12_read_state,
+		.read_new = w1_f12_read_state,
 	},
 	{
 		.attr = {
@@ -110,7 +110,7 @@ static struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = {
 			.mode = 0664,
 		},
 		.size = 1,
-		.write = w1_f12_write_output,
+		.write_new = w1_f12_write_output,
 	}
 };
 
diff --git a/drivers/w1/slaves/w1_ds2408.c b/drivers/w1/slaves/w1_ds2408.c
index 56f822a1dfdb..beccd2912d2a 100644
--- a/drivers/w1/slaves/w1_ds2408.c
+++ b/drivers/w1/slaves/w1_ds2408.c
@@ -65,8 +65,8 @@ static int _read_reg(struct w1_slave *sl, u8 address, unsigned char *buf)
 }
 
 static ssize_t state_read(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr, char *buf, loff_t off,
-			  size_t count)
+			  const struct bin_attribute *bin_attr, char *buf,
+			  loff_t off, size_t count)
 {
 	dev_dbg(&kobj_to_w1_slave(kobj)->dev,
 		"Reading %s kobj: %p, off: %0#10x, count: %zu, buff addr: %p",
@@ -77,7 +77,7 @@ static ssize_t state_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t output_read(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr, char *buf,
+			   const struct bin_attribute *bin_attr, char *buf,
 			   loff_t off, size_t count)
 {
 	dev_dbg(&kobj_to_w1_slave(kobj)->dev,
@@ -90,7 +90,7 @@ static ssize_t output_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t activity_read(struct file *filp, struct kobject *kobj,
-			     struct bin_attribute *bin_attr, char *buf,
+			     const struct bin_attribute *bin_attr, char *buf,
 			     loff_t off, size_t count)
 {
 	dev_dbg(&kobj_to_w1_slave(kobj)->dev,
@@ -103,8 +103,8 @@ static ssize_t activity_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t cond_search_mask_read(struct file *filp, struct kobject *kobj,
-				     struct bin_attribute *bin_attr, char *buf,
-				     loff_t off, size_t count)
+				     const struct bin_attribute *bin_attr,
+				     char *buf, loff_t off, size_t count)
 {
 	dev_dbg(&kobj_to_w1_slave(kobj)->dev,
 		"Reading %s kobj: %p, off: %0#10x, count: %zu, buff addr: %p",
@@ -117,7 +117,7 @@ static ssize_t cond_search_mask_read(struct file *filp, struct kobject *kobj,
 
 static ssize_t cond_search_polarity_read(struct file *filp,
 					 struct kobject *kobj,
-					 struct bin_attribute *bin_attr,
+					 const struct bin_attribute *bin_attr,
 					 char *buf, loff_t off, size_t count)
 {
 	if (count != 1 || off != 0)
@@ -127,8 +127,8 @@ static ssize_t cond_search_polarity_read(struct file *filp,
 }
 
 static ssize_t status_control_read(struct file *filp, struct kobject *kobj,
-				   struct bin_attribute *bin_attr, char *buf,
-				   loff_t off, size_t count)
+				   const struct bin_attribute *bin_attr,
+				   char *buf, loff_t off, size_t count)
 {
 	if (count != 1 || off != 0)
 		return -EFAULT;
@@ -160,7 +160,7 @@ static bool optional_read_back_valid(struct w1_slave *sl, u8 expected)
 #endif
 
 static ssize_t output_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -210,7 +210,7 @@ out:
  * Writing to the activity file resets the activity latches.
  */
 static ssize_t activity_write(struct file *filp, struct kobject *kobj,
-			      struct bin_attribute *bin_attr, char *buf,
+			      const struct bin_attribute *bin_attr, char *buf,
 			      loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -240,8 +240,8 @@ error:
 }
 
 static ssize_t status_control_write(struct file *filp, struct kobject *kobj,
-				    struct bin_attribute *bin_attr, char *buf,
-				    loff_t off, size_t count)
+				    const struct bin_attribute *bin_attr,
+				    char *buf, loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
 	u8 w1_buf[4];
@@ -310,14 +310,14 @@ out:
 	return res;
 }
 
-static BIN_ATTR_RO(state, 1);
-static BIN_ATTR_RW(output, 1);
-static BIN_ATTR_RW(activity, 1);
-static BIN_ATTR_RO(cond_search_mask, 1);
-static BIN_ATTR_RO(cond_search_polarity, 1);
-static BIN_ATTR_RW(status_control, 1);
+static const BIN_ATTR_RO(state, 1);
+static const BIN_ATTR_RW(output, 1);
+static const BIN_ATTR_RW(activity, 1);
+static const BIN_ATTR_RO(cond_search_mask, 1);
+static const BIN_ATTR_RO(cond_search_polarity, 1);
+static const BIN_ATTR_RW(status_control, 1);
 
-static struct bin_attribute *w1_f29_bin_attrs[] = {
+static const struct bin_attribute *const w1_f29_bin_attrs[] = {
 	&bin_attr_state,
 	&bin_attr_output,
 	&bin_attr_activity,
@@ -328,7 +328,7 @@ static struct bin_attribute *w1_f29_bin_attrs[] = {
 };
 
 static const struct attribute_group w1_f29_group = {
-	.bin_attrs = w1_f29_bin_attrs,
+	.bin_attrs_new = w1_f29_bin_attrs,
 };
 
 static const struct attribute_group *w1_f29_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c
index 739009806467..5fa46017ca7c 100644
--- a/drivers/w1/slaves/w1_ds2413.c
+++ b/drivers/w1/slaves/w1_ds2413.c
@@ -25,8 +25,8 @@
 #define W1_F3A_INVALID_PIO_STATE           0xFF
 
 static ssize_t state_read(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr, char *buf, loff_t off,
-			  size_t count)
+			  const struct bin_attribute *bin_attr, char *buf,
+			  loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
 	unsigned int retries = W1_F3A_RETRIES;
@@ -78,10 +78,10 @@ out:
 	return bytes_read;
 }
 
-static BIN_ATTR_RO(state, 1);
+static const BIN_ATTR_RO(state, 1);
 
 static ssize_t output_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -128,16 +128,16 @@ out:
 	return bytes_written;
 }
 
-static BIN_ATTR(output, 0664, NULL, output_write, 1);
+static const BIN_ATTR(output, 0664, NULL, output_write, 1);
 
-static struct bin_attribute *w1_f3a_bin_attrs[] = {
+static const struct bin_attribute *const w1_f3a_bin_attrs[] = {
 	&bin_attr_state,
 	&bin_attr_output,
 	NULL,
 };
 
 static const struct attribute_group w1_f3a_group = {
-	.bin_attrs = w1_f3a_bin_attrs,
+	.bin_attrs_new = w1_f3a_bin_attrs,
 };
 
 static const struct attribute_group *w1_f3a_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2430.c b/drivers/w1/slaves/w1_ds2430.c
index 0ea7d779d17a..ff56e2e68e58 100644
--- a/drivers/w1/slaves/w1_ds2430.c
+++ b/drivers/w1/slaves/w1_ds2430.c
@@ -95,7 +95,7 @@ static int w1_f14_readblock(struct w1_slave *sl, int off, int count, char *buf)
 }
 
 static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr, char *buf,
+			   const struct bin_attribute *bin_attr, char *buf,
 			   loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -202,7 +202,7 @@ retry:
 }
 
 static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -263,15 +263,15 @@ out_up:
 	return count;
 }
 
-static BIN_ATTR_RW(eeprom, W1_F14_EEPROM_SIZE);
+static const BIN_ATTR_RW(eeprom, W1_F14_EEPROM_SIZE);
 
-static struct bin_attribute *w1_f14_bin_attrs[] = {
+static const struct bin_attribute *const w1_f14_bin_attrs[] = {
 	&bin_attr_eeprom,
 	NULL,
 };
 
 static const struct attribute_group w1_f14_group = {
-	.bin_attrs = w1_f14_bin_attrs,
+	.bin_attrs_new = w1_f14_bin_attrs,
 };
 
 static const struct attribute_group *w1_f14_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2431.c b/drivers/w1/slaves/w1_ds2431.c
index 6856b1c29e17..27b390fb59da 100644
--- a/drivers/w1/slaves/w1_ds2431.c
+++ b/drivers/w1/slaves/w1_ds2431.c
@@ -95,7 +95,7 @@ static int w1_f2d_readblock(struct w1_slave *sl, int off, int count, char *buf)
 }
 
 static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr, char *buf,
+			   const struct bin_attribute *bin_attr, char *buf,
 			   loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -201,7 +201,7 @@ retry:
 }
 
 static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -262,15 +262,15 @@ out_up:
 	return count;
 }
 
-static BIN_ATTR_RW(eeprom, W1_F2D_EEPROM_SIZE);
+static const BIN_ATTR_RW(eeprom, W1_F2D_EEPROM_SIZE);
 
-static struct bin_attribute *w1_f2d_bin_attrs[] = {
+static const struct bin_attribute *const w1_f2d_bin_attrs[] = {
 	&bin_attr_eeprom,
 	NULL,
 };
 
 static const struct attribute_group w1_f2d_group = {
-	.bin_attrs = w1_f2d_bin_attrs,
+	.bin_attrs_new = w1_f2d_bin_attrs,
 };
 
 static const struct attribute_group *w1_f2d_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c
index 250b7f7ec429..22331d840ec1 100644
--- a/drivers/w1/slaves/w1_ds2433.c
+++ b/drivers/w1/slaves/w1_ds2433.c
@@ -110,7 +110,7 @@ static int w1_f23_refresh_block(struct w1_slave *sl, struct w1_f23_data *data,
 #endif	/* CONFIG_W1_SLAVE_DS2433_CRC */
 
 static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr, char *buf,
+			   const struct bin_attribute *bin_attr, char *buf,
 			   loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -224,7 +224,7 @@ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 }
 
 static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -274,27 +274,27 @@ out_up:
 	return count;
 }
 
-static struct bin_attribute bin_attr_f23_eeprom = {
+static const struct bin_attribute bin_attr_f23_eeprom = {
 	.attr = { .name = "eeprom", .mode = 0644 },
-	.read = eeprom_read,
-	.write = eeprom_write,
+	.read_new = eeprom_read,
+	.write_new = eeprom_write,
 	.size = W1_EEPROM_DS2433_SIZE,
 };
 
-static struct bin_attribute bin_attr_f43_eeprom = {
+static const struct bin_attribute bin_attr_f43_eeprom = {
 	.attr = { .name = "eeprom", .mode = 0644 },
-	.read = eeprom_read,
-	.write = eeprom_write,
+	.read_new = eeprom_read,
+	.write_new = eeprom_write,
 	.size = W1_EEPROM_DS28EC20_SIZE,
 };
 
-static struct bin_attribute *w1_f23_bin_attributes[] = {
+static const struct bin_attribute *const w1_f23_bin_attributes[] = {
 	&bin_attr_f23_eeprom,
 	NULL,
 };
 
 static const struct attribute_group w1_f23_group = {
-	.bin_attrs = w1_f23_bin_attributes,
+	.bin_attrs_new = w1_f23_bin_attributes,
 };
 
 static const struct attribute_group *w1_f23_groups[] = {
@@ -302,13 +302,13 @@ static const struct attribute_group *w1_f23_groups[] = {
 	NULL,
 };
 
-static struct bin_attribute *w1_f43_bin_attributes[] = {
+static const struct bin_attribute *const w1_f43_bin_attributes[] = {
 	&bin_attr_f43_eeprom,
 	NULL,
 };
 
 static const struct attribute_group w1_f43_group = {
-	.bin_attrs = w1_f43_bin_attributes,
+	.bin_attrs_new = w1_f43_bin_attributes,
 };
 
 static const struct attribute_group *w1_f43_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2438.c b/drivers/w1/slaves/w1_ds2438.c
index e008c27b3db9..630a6db5045e 100644
--- a/drivers/w1/slaves/w1_ds2438.c
+++ b/drivers/w1/slaves/w1_ds2438.c
@@ -288,7 +288,7 @@ static int w1_ds2438_get_current(struct w1_slave *sl, int16_t *voltage)
 }
 
 static ssize_t iad_write(struct file *filp, struct kobject *kobj,
-			 struct bin_attribute *bin_attr, char *buf,
+			 const struct bin_attribute *bin_attr, char *buf,
 			 loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -310,7 +310,7 @@ static ssize_t iad_write(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t iad_read(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr, char *buf,
+			const struct bin_attribute *bin_attr, char *buf,
 			loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -331,7 +331,7 @@ static ssize_t iad_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t page0_read(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr, char *buf,
+			  const struct bin_attribute *bin_attr, char *buf,
 			  loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -361,7 +361,7 @@ static ssize_t page0_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t page1_read(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr, char *buf,
+			  const struct bin_attribute *bin_attr, char *buf,
 			  loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -391,7 +391,7 @@ static ssize_t page1_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t offset_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -410,7 +410,7 @@ static ssize_t offset_write(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t temperature_read(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
+				const struct bin_attribute *bin_attr, char *buf,
 				loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -431,7 +431,7 @@ static ssize_t temperature_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t vad_read(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr, char *buf,
+			const struct bin_attribute *bin_attr, char *buf,
 			loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -452,7 +452,7 @@ static ssize_t vad_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t vdd_read(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr, char *buf,
+			const struct bin_attribute *bin_attr, char *buf,
 			loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -472,15 +472,15 @@ static ssize_t vdd_read(struct file *filp, struct kobject *kobj,
 	return ret;
 }
 
-static BIN_ATTR_RW(iad, 0);
-static BIN_ATTR_RO(page0, DS2438_PAGE_SIZE);
-static BIN_ATTR_RO(page1, DS2438_PAGE_SIZE);
-static BIN_ATTR_WO(offset, 2);
-static BIN_ATTR_RO(temperature, 0/* real length varies */);
-static BIN_ATTR_RO(vad, 0/* real length varies */);
-static BIN_ATTR_RO(vdd, 0/* real length varies */);
+static const BIN_ATTR_RW(iad, 0);
+static const BIN_ATTR_RO(page0, DS2438_PAGE_SIZE);
+static const BIN_ATTR_RO(page1, DS2438_PAGE_SIZE);
+static const BIN_ATTR_WO(offset, 2);
+static const BIN_ATTR_RO(temperature, 0/* real length varies */);
+static const BIN_ATTR_RO(vad, 0/* real length varies */);
+static const BIN_ATTR_RO(vdd, 0/* real length varies */);
 
-static struct bin_attribute *w1_ds2438_bin_attrs[] = {
+static const struct bin_attribute *const w1_ds2438_bin_attrs[] = {
 	&bin_attr_iad,
 	&bin_attr_page0,
 	&bin_attr_page1,
@@ -492,7 +492,7 @@ static struct bin_attribute *w1_ds2438_bin_attrs[] = {
 };
 
 static const struct attribute_group w1_ds2438_group = {
-	.bin_attrs = w1_ds2438_bin_attrs,
+	.bin_attrs_new = w1_ds2438_bin_attrs,
 };
 
 static const struct attribute_group *w1_ds2438_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c
index 3cde1bb1886b..ba7beb7b01f9 100644
--- a/drivers/w1/slaves/w1_ds2780.c
+++ b/drivers/w1/slaves/w1_ds2780.c
@@ -87,7 +87,7 @@ int w1_ds2780_eeprom_cmd(struct device *dev, int addr, int cmd)
 EXPORT_SYMBOL(w1_ds2780_eeprom_cmd);
 
 static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj,
-			     struct bin_attribute *bin_attr, char *buf,
+			     const struct bin_attribute *bin_attr, char *buf,
 			     loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -95,15 +95,15 @@ static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj,
 	return w1_ds2780_io(dev, buf, off, count, 0);
 }
 
-static BIN_ATTR_RO(w1_slave, DS2780_DATA_SIZE);
+static const BIN_ATTR_RO(w1_slave, DS2780_DATA_SIZE);
 
-static struct bin_attribute *w1_ds2780_bin_attrs[] = {
+static const struct bin_attribute *const w1_ds2780_bin_attrs[] = {
 	&bin_attr_w1_slave,
 	NULL,
 };
 
 static const struct attribute_group w1_ds2780_group = {
-	.bin_attrs = w1_ds2780_bin_attrs,
+	.bin_attrs_new = w1_ds2780_bin_attrs,
 };
 
 static const struct attribute_group *w1_ds2780_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2781.c b/drivers/w1/slaves/w1_ds2781.c
index e418484b4a49..acd04ee96e81 100644
--- a/drivers/w1/slaves/w1_ds2781.c
+++ b/drivers/w1/slaves/w1_ds2781.c
@@ -84,7 +84,7 @@ int w1_ds2781_eeprom_cmd(struct device *dev, int addr, int cmd)
 EXPORT_SYMBOL(w1_ds2781_eeprom_cmd);
 
 static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj,
-			     struct bin_attribute *bin_attr, char *buf,
+			     const struct bin_attribute *bin_attr, char *buf,
 			     loff_t off, size_t count)
 {
 	struct device *dev = kobj_to_dev(kobj);
@@ -92,15 +92,15 @@ static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj,
 	return w1_ds2781_io(dev, buf, off, count, 0);
 }
 
-static BIN_ATTR_RO(w1_slave, DS2781_DATA_SIZE);
+static const BIN_ATTR_RO(w1_slave, DS2781_DATA_SIZE);
 
-static struct bin_attribute *w1_ds2781_bin_attrs[] = {
+static const struct bin_attribute *const w1_ds2781_bin_attrs[] = {
 	&bin_attr_w1_slave,
 	NULL,
 };
 
 static const struct attribute_group w1_ds2781_group = {
-	.bin_attrs = w1_ds2781_bin_attrs,
+	.bin_attrs_new = w1_ds2781_bin_attrs,
 };
 
 static const struct attribute_group *w1_ds2781_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds2805.c b/drivers/w1/slaves/w1_ds2805.c
index 4c1a2c515317..6ee895640d4a 100644
--- a/drivers/w1/slaves/w1_ds2805.c
+++ b/drivers/w1/slaves/w1_ds2805.c
@@ -92,7 +92,7 @@ static int w1_f0d_readblock(struct w1_slave *sl, int off, int count, char *buf)
 }
 
 static ssize_t w1_f0d_read_bin(struct file *filp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr,
+			       const struct bin_attribute *bin_attr,
 			       char *buf, loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -200,7 +200,7 @@ retry:
 }
 
 static ssize_t w1_f0d_write_bin(struct file *filp, struct kobject *kobj,
-				struct bin_attribute *bin_attr,
+				const struct bin_attribute *bin_attr,
 				char *buf, loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -261,14 +261,14 @@ out_up:
 	return count;
 }
 
-static struct bin_attribute w1_f0d_bin_attr = {
+static const struct bin_attribute w1_f0d_bin_attr = {
 	.attr = {
 		.name = "eeprom",
 		.mode = 0644,
 	},
 	.size = W1_F0D_EEPROM_SIZE,
-	.read = w1_f0d_read_bin,
-	.write = w1_f0d_write_bin,
+	.read_new = w1_f0d_read_bin,
+	.write_new = w1_f0d_write_bin,
 };
 
 static int w1_f0d_add_slave(struct w1_slave *sl)
diff --git a/drivers/w1/slaves/w1_ds28e04.c b/drivers/w1/slaves/w1_ds28e04.c
index 2854b8b9e93f..d99ffadbe29b 100644
--- a/drivers/w1/slaves/w1_ds28e04.c
+++ b/drivers/w1/slaves/w1_ds28e04.c
@@ -112,7 +112,7 @@ static int w1_f1C_read(struct w1_slave *sl, int addr, int len, char *data)
 }
 
 static ssize_t eeprom_read(struct file *filp, struct kobject *kobj,
-			   struct bin_attribute *bin_attr, char *buf,
+			   const struct bin_attribute *bin_attr, char *buf,
 			   loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -223,7 +223,7 @@ static int w1_f1C_write(struct w1_slave *sl, int addr, int len, const u8 *data)
 }
 
 static ssize_t eeprom_write(struct file *filp, struct kobject *kobj,
-			    struct bin_attribute *bin_attr, char *buf,
+			    const struct bin_attribute *bin_attr, char *buf,
 			    loff_t off, size_t count)
 
 {
@@ -276,10 +276,10 @@ out_up:
 	return count;
 }
 
-static BIN_ATTR_RW(eeprom, W1_EEPROM_SIZE);
+static const BIN_ATTR_RW(eeprom, W1_EEPROM_SIZE);
 
 static ssize_t pio_read(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr, char *buf, loff_t off,
+			const struct bin_attribute *bin_attr, char *buf, loff_t off,
 			size_t count)
 
 {
@@ -298,8 +298,8 @@ static ssize_t pio_read(struct file *filp, struct kobject *kobj,
 }
 
 static ssize_t pio_write(struct file *filp, struct kobject *kobj,
-			 struct bin_attribute *bin_attr, char *buf, loff_t off,
-			 size_t count)
+			 const struct bin_attribute *bin_attr, char *buf,
+			 loff_t off, size_t count)
 
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -337,7 +337,7 @@ static ssize_t pio_write(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static BIN_ATTR_RW(pio, 1);
+static const BIN_ATTR_RW(pio, 1);
 
 static ssize_t crccheck_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
@@ -363,7 +363,7 @@ static struct attribute *w1_f1C_attrs[] = {
 	NULL,
 };
 
-static struct bin_attribute *w1_f1C_bin_attrs[] = {
+static const struct bin_attribute *const w1_f1C_bin_attrs[] = {
 	&bin_attr_eeprom,
 	&bin_attr_pio,
 	NULL,
@@ -371,7 +371,7 @@ static struct bin_attribute *w1_f1C_bin_attrs[] = {
 
 static const struct attribute_group w1_f1C_group = {
 	.attrs		= w1_f1C_attrs,
-	.bin_attrs	= w1_f1C_bin_attrs,
+	.bin_attrs_new	= w1_f1C_bin_attrs,
 };
 
 static const struct attribute_group *w1_f1C_groups[] = {
diff --git a/drivers/w1/slaves/w1_ds28e17.c b/drivers/w1/slaves/w1_ds28e17.c
index 52261b54d842..5738cbce1a37 100644
--- a/drivers/w1/slaves/w1_ds28e17.c
+++ b/drivers/w1/slaves/w1_ds28e17.c
@@ -583,7 +583,7 @@ static ssize_t speed_show(struct device *dev, struct device_attribute *attr,
 		return result;
 
 	/* Return current speed value. */
-	return sprintf(buf, "%d\n", result);
+	return sysfs_emit(buf, "%d\n", result);
 }
 
 static ssize_t speed_store(struct device *dev, struct device_attribute *attr,
@@ -633,7 +633,7 @@ static ssize_t stretch_show(struct device *dev, struct device_attribute *attr,
 	struct w1_f19_data *data = sl->family_data;
 
 	/* Return current stretch value. */
-	return sprintf(buf, "%d\n", data->stretch);
+	return sysfs_emit(buf, "%d\n", data->stretch);
 }
 
 static ssize_t stretch_store(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index d82e86d3ddf6..29f200bbab41 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -111,7 +111,7 @@ ATTRIBUTE_GROUPS(w1_slave);
 /* Default family */
 
 static ssize_t rw_write(struct file *filp, struct kobject *kobj,
-			struct bin_attribute *bin_attr, char *buf, loff_t off,
+			const struct bin_attribute *bin_attr, char *buf, loff_t off,
 			size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
@@ -130,8 +130,8 @@ out_up:
 }
 
 static ssize_t rw_read(struct file *filp, struct kobject *kobj,
-		       struct bin_attribute *bin_attr, char *buf, loff_t off,
-		       size_t count)
+		       const struct bin_attribute *bin_attr, char *buf,
+		       loff_t off, size_t count)
 {
 	struct w1_slave *sl = kobj_to_w1_slave(kobj);
 
@@ -141,15 +141,15 @@ static ssize_t rw_read(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static BIN_ATTR_RW(rw, PAGE_SIZE);
+static const BIN_ATTR_RW(rw, PAGE_SIZE);
 
-static struct bin_attribute *w1_slave_bin_attrs[] = {
+static const struct bin_attribute *const w1_slave_bin_attrs[] = {
 	&bin_attr_rw,
 	NULL,
 };
 
 static const struct attribute_group w1_slave_default_group = {
-	.bin_attrs = w1_slave_bin_attrs,
+	.bin_attrs_new = w1_slave_bin_attrs,
 };
 
 static const struct attribute_group *w1_slave_default_groups[] = {
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 528395133b4f..163f7f1d70f1 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -84,7 +84,7 @@ module_param(balloon_boot_timeout, uint, 0444);
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
 static int xen_hotplug_unpopulated;
 
-static struct ctl_table balloon_table[] = {
+static const struct ctl_table balloon_table[] = {
 	{
 		.procname	= "hotplug_unpopulated",
 		.data		= &xen_hotplug_unpopulated,
diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c
index c63f317e3df3..093ad4a08672 100644
--- a/drivers/xen/pcpu.c
+++ b/drivers/xen/pcpu.c
@@ -105,7 +105,7 @@ static ssize_t online_show(struct device *dev,
 	return sprintf(buf, "%u\n", !!(cpu->flags & XEN_PCPU_FLAGS_ONLINE));
 }
 
-static ssize_t __ref online_store(struct device *dev,
+static ssize_t online_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index b72ee9379d77..4926d4badc57 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -341,6 +341,7 @@ int pvcalls_front_socket(struct socket *sock)
 	pvcalls_exit();
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_socket);
 
 static void free_active_ring(struct sock_mapping *map)
 {
@@ -486,6 +487,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr,
 	pvcalls_exit_sock(sock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_connect);
 
 static int __write_ring(struct pvcalls_data_intf *intf,
 			struct pvcalls_data *data,
@@ -581,6 +583,7 @@ again:
 	pvcalls_exit_sock(sock);
 	return tot_sent;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_sendmsg);
 
 static int __read_ring(struct pvcalls_data_intf *intf,
 		       struct pvcalls_data *data,
@@ -666,6 +669,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	pvcalls_exit_sock(sock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_recvmsg);
 
 int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 {
@@ -719,6 +723,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	pvcalls_exit_sock(sock);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_bind);
 
 int pvcalls_front_listen(struct socket *sock, int backlog)
 {
@@ -768,8 +773,10 @@ int pvcalls_front_listen(struct socket *sock, int backlog)
 	pvcalls_exit_sock(sock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_listen);
 
-int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
+int pvcalls_front_accept(struct socket *sock, struct socket *newsock,
+			 struct proto_accept_arg *arg)
 {
 	struct pvcalls_bedata *bedata;
 	struct sock_mapping *map;
@@ -788,7 +795,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags)
 		return -EINVAL;
 	}
 
-	nonblock = flags & SOCK_NONBLOCK;
+	nonblock = arg->flags & SOCK_NONBLOCK;
 	/*
 	 * Backend only supports 1 inflight accept request, will return
 	 * errors for the others
@@ -904,6 +911,7 @@ received:
 	pvcalls_exit_sock(sock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_accept);
 
 static __poll_t pvcalls_front_poll_passive(struct file *file,
 					       struct pvcalls_bedata *bedata,
@@ -1004,6 +1012,7 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock,
 	pvcalls_exit_sock(sock);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_poll);
 
 int pvcalls_front_release(struct socket *sock)
 {
@@ -1087,6 +1096,7 @@ int pvcalls_front_release(struct socket *sock)
 	pvcalls_exit();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pvcalls_front_release);
 
 static const struct xenbus_device_id pvcalls_front_ids[] = {
 	{ "pvcalls" },
diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
index f694ad77379f..881ef14660bc 100644
--- a/drivers/xen/pvcalls-front.h
+++ b/drivers/xen/pvcalls-front.h
@@ -12,7 +12,7 @@ int pvcalls_front_bind(struct socket *sock,
 int pvcalls_front_listen(struct socket *sock, int backlog);
 int pvcalls_front_accept(struct socket *sock,
 			 struct socket *newsock,
-			 int flags);
+			 struct proto_accept_arg *arg);
 int pvcalls_front_sendmsg(struct socket *sock,
 			  struct msghdr *msg,
 			  size_t len);
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 698c43dd5dc8..f28bc763847a 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -202,7 +202,7 @@ static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
 	return inode->i_sb->s_fs_info;
 }
 
-static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry)
+static inline struct v9fs_session_info *v9fs_dentry2v9ses(const struct dentry *dentry)
 {
 	return dentry->d_sb->s_fs_info;
 }
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 01338d4c2d9e..5061f192eafd 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -61,7 +61,7 @@ static void v9fs_dentry_release(struct dentry *dentry)
 		p9_fid_put(hlist_entry(p, struct p9_fid, dlist));
 }
 
-static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct p9_fid *fid;
 	struct inode *inode;
@@ -99,14 +99,36 @@ out_valid:
 	return 1;
 }
 
+static int v9fs_lookup_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *dentry, unsigned int flags)
+{
+	return __v9fs_lookup_revalidate(dentry, flags);
+}
+
+static bool v9fs_dentry_unalias_trylock(const struct dentry *dentry)
+{
+	struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry);
+	return down_write_trylock(&v9ses->rename_sem);
+}
+
+static void v9fs_dentry_unalias_unlock(const struct dentry *dentry)
+{
+	struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry);
+	up_write(&v9ses->rename_sem);
+}
+
 const struct dentry_operations v9fs_cached_dentry_operations = {
 	.d_revalidate = v9fs_lookup_revalidate,
-	.d_weak_revalidate = v9fs_lookup_revalidate,
+	.d_weak_revalidate = __v9fs_lookup_revalidate,
 	.d_delete = v9fs_cached_dentry_delete,
 	.d_release = v9fs_dentry_release,
+	.d_unalias_trylock = v9fs_dentry_unalias_trylock,
+	.d_unalias_unlock = v9fs_dentry_unalias_unlock,
 };
 
 const struct dentry_operations v9fs_dentry_operations = {
 	.d_delete = always_delete_dentry,
 	.d_release = v9fs_dentry_release,
+	.d_unalias_trylock = v9fs_dentry_unalias_trylock,
+	.d_unalias_unlock = v9fs_dentry_unalias_unlock,
 };
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index a843c36fc471..02cbf38e1a77 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -23,7 +23,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 				 unsigned int flags);
 static int afs_dir_open(struct inode *inode, struct file *file);
 static int afs_readdir(struct file *file, struct dir_context *ctx);
-static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
+static int afs_d_revalidate(struct inode *dir, const struct qstr *name,
+			    struct dentry *dentry, unsigned int flags);
 static int afs_d_delete(const struct dentry *dentry);
 static void afs_d_iput(struct dentry *dentry, struct inode *inode);
 static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int nlen,
@@ -597,19 +598,19 @@ static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name,
  * Do a lookup of a single name in a directory
  * - just returns the FID the dentry name maps to if found
  */
-static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry,
+static int afs_do_lookup_one(struct inode *dir, const struct qstr *name,
 			     struct afs_fid *fid,
 			     afs_dataversion_t *_dir_version)
 {
 	struct afs_super_info *as = dir->i_sb->s_fs_info;
 	struct afs_lookup_one_cookie cookie = {
 		.ctx.actor = afs_lookup_one_filldir,
-		.name = dentry->d_name,
+		.name = *name,
 		.fid.vid = as->volume->vid
 	};
 	int ret;
 
-	_enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);
+	_enter("{%lu},{%.*s},", dir->i_ino, name->len, name->name);
 
 	/* search the directory */
 	ret = afs_dir_iterate(dir, &cookie.ctx, NULL, _dir_version);
@@ -1023,21 +1024,12 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 /*
  * Check the validity of a dentry under RCU conditions.
  */
-static int afs_d_revalidate_rcu(struct dentry *dentry)
+static int afs_d_revalidate_rcu(struct afs_vnode *dvnode, struct dentry *dentry)
 {
-	struct afs_vnode *dvnode;
-	struct dentry *parent;
-	struct inode *dir;
 	long dir_version, de_version;
 
 	_enter("%p", dentry);
 
-	/* Check the parent directory is still valid first. */
-	parent = READ_ONCE(dentry->d_parent);
-	dir = d_inode_rcu(parent);
-	if (!dir)
-		return -ECHILD;
-	dvnode = AFS_FS_I(dir);
 	if (test_bit(AFS_VNODE_DELETED, &dvnode->flags))
 		return -ECHILD;
 
@@ -1065,11 +1057,11 @@ static int afs_d_revalidate_rcu(struct dentry *dentry)
  * - NOTE! the hit can be a negative hit too, so we can't assume we have an
  *   inode
  */
-static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int afs_d_revalidate(struct inode *parent_dir, const struct qstr *name,
+			    struct dentry *dentry, unsigned int flags)
 {
-	struct afs_vnode *vnode, *dir;
+	struct afs_vnode *vnode, *dir = AFS_FS_I(parent_dir);
 	struct afs_fid fid;
-	struct dentry *parent;
 	struct inode *inode;
 	struct key *key;
 	afs_dataversion_t dir_version, invalid_before;
@@ -1077,7 +1069,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	int ret;
 
 	if (flags & LOOKUP_RCU)
-		return afs_d_revalidate_rcu(dentry);
+		return afs_d_revalidate_rcu(dir, dentry);
 
 	if (d_really_is_positive(dentry)) {
 		vnode = AFS_FS_I(d_inode(dentry));
@@ -1092,14 +1084,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (IS_ERR(key))
 		key = NULL;
 
-	/* Hold the parent dentry so we can peer at it */
-	parent = dget_parent(dentry);
-	dir = AFS_FS_I(d_inode(parent));
-
 	/* validate the parent directory */
 	ret = afs_validate(dir, key);
 	if (ret == -ERESTARTSYS) {
-		dput(parent);
 		key_put(key);
 		return ret;
 	}
@@ -1127,7 +1114,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	afs_stat_v(dir, n_reval);
 
 	/* search the directory for this vnode */
-	ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, &dir_version);
+	ret = afs_do_lookup_one(&dir->netfs.inode, name, &fid, &dir_version);
 	switch (ret) {
 	case 0:
 		/* the filename maps to something */
@@ -1171,22 +1158,19 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_valid;
 
 	default:
-		_debug("failed to iterate dir %pd: %d",
-		       parent, ret);
+		_debug("failed to iterate parent %pd2: %d", dentry, ret);
 		goto not_found;
 	}
 
 out_valid:
 	dentry->d_fsdata = (void *)(unsigned long)dir_version;
 out_valid_noupdate:
-	dput(parent);
 	key_put(key);
 	_leave(" = 1 [valid]");
 	return 1;
 
 not_found:
 	_debug("dropping dentry %pd2", dentry);
-	dput(parent);
 	key_put(key);
 
 	_leave(" = 0 [bad]");
diff --git a/fs/aio.c b/fs/aio.c
index 50671640b588..7b976b564cfc 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -224,7 +224,7 @@ static unsigned long aio_nr;		/* current system wide number of aio requests */
 static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */
 /*----end sysctl variables---*/
 #ifdef CONFIG_SYSCTL
-static struct ctl_table aio_sysctls[] = {
+static const struct ctl_table aio_sysctls[] = {
 	{
 		.procname	= "aio-nr",
 		.data		= &aio_nr,
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 42bd1cb7c9cd..583ac81669c2 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -60,14 +60,14 @@ static struct inode *anon_inode_make_secure_inode(
 	const struct inode *context_inode)
 {
 	struct inode *inode;
-	const struct qstr qname = QSTR_INIT(name, strlen(name));
 	int error;
 
 	inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
 	if (IS_ERR(inode))
 		return inode;
 	inode->i_flags &= ~S_PRIVATE;
-	error =	security_inode_init_security_anon(inode, &qname, context_inode);
+	error =	security_inode_init_security_anon(inode, &QSTR(name),
+						  context_inode);
 	if (error) {
 		iput(inode);
 		return ERR_PTR(error);
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index fc2ef33b67b3..3ea809990ef1 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1803,7 +1803,6 @@ struct discard_buckets_state {
 	u64		open;
 	u64		need_journal_commit;
 	u64		discarded;
-	u64		need_journal_commit_this_dev;
 };
 
 static int bch2_discard_one_bucket(struct btree_trans *trans,
@@ -1827,11 +1826,11 @@ static int bch2_discard_one_bucket(struct btree_trans *trans,
 		goto out;
 	}
 
-	if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
-			c->journal.flushed_seq_ondisk,
-			pos.inode, pos.offset)) {
-		s->need_journal_commit++;
-		s->need_journal_commit_this_dev++;
+	u64 seq_ready = bch2_bucket_journal_seq_ready(&c->buckets_waiting_for_journal,
+						      pos.inode, pos.offset);
+	if (seq_ready > c->journal.flushed_seq_ondisk) {
+		if (seq_ready > c->journal.flushing_seq)
+			s->need_journal_commit++;
 		goto out;
 	}
 
@@ -1865,23 +1864,24 @@ static int bch2_discard_one_bucket(struct btree_trans *trans,
 		discard_locked = true;
 	}
 
-	if (!bkey_eq(*discard_pos_done, iter.pos) &&
-	    ca->mi.discard && !c->opts.nochanges) {
-		/*
-		 * This works without any other locks because this is the only
-		 * thread that removes items from the need_discard tree
-		 */
-		bch2_trans_unlock_long(trans);
-		blkdev_issue_discard(ca->disk_sb.bdev,
-				     k.k->p.offset * ca->mi.bucket_size,
-				     ca->mi.bucket_size,
-				     GFP_KERNEL);
-		*discard_pos_done = iter.pos;
+	if (!bkey_eq(*discard_pos_done, iter.pos)) {
 		s->discarded++;
+		*discard_pos_done = iter.pos;
 
-		ret = bch2_trans_relock_notrace(trans);
-		if (ret)
-			goto out;
+		if (ca->mi.discard && !c->opts.nochanges) {
+			/*
+			 * This works without any other locks because this is the only
+			 * thread that removes items from the need_discard tree
+			 */
+			bch2_trans_unlock_long(trans);
+			blkdev_issue_discard(ca->disk_sb.bdev,
+					     k.k->p.offset * ca->mi.bucket_size,
+					     ca->mi.bucket_size,
+					     GFP_KERNEL);
+			ret = bch2_trans_relock_notrace(trans);
+			if (ret)
+				goto out;
+		}
 	}
 
 	SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false);
@@ -1929,6 +1929,9 @@ static void bch2_do_discards_work(struct work_struct *work)
 				   POS(ca->dev_idx, U64_MAX), 0, k,
 			bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s, false)));
 
+	if (s.need_journal_commit > dev_buckets_available(ca, BCH_WATERMARK_normal))
+		bch2_journal_flush_async(&c->journal, NULL);
+
 	trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded,
 			      bch2_err_str(ret));
 
@@ -2024,7 +2027,7 @@ static void bch2_do_discards_fast_work(struct work_struct *work)
 			break;
 	}
 
-	trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret));
+	trace_discard_buckets_fast(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret));
 
 	bch2_trans_put(trans);
 	percpu_ref_put(&ca->io_ref);
diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 6df41c331a52..5a781fb4c794 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -205,8 +205,12 @@ static inline bool may_alloc_bucket(struct bch_fs *c,
 		return false;
 	}
 
-	if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal,
-			c->journal.flushed_seq_ondisk, bucket.inode, bucket.offset)) {
+	u64 journal_seq_ready =
+		bch2_bucket_journal_seq_ready(&c->buckets_waiting_for_journal,
+					      bucket.inode, bucket.offset);
+	if (journal_seq_ready > c->journal.flushed_seq_ondisk) {
+		if (journal_seq_ready > c->journal.flushing_seq)
+			s->need_journal_commit++;
 		s->skipped_need_journal_commit++;
 		return false;
 	}
@@ -570,7 +574,7 @@ alloc:
 		? bch2_bucket_alloc_freelist(trans, ca, watermark, &s, cl)
 		: bch2_bucket_alloc_early(trans, ca, watermark, &s, cl);
 
-	if (s.skipped_need_journal_commit * 2 > avail)
+	if (s.need_journal_commit * 2 > avail)
 		bch2_journal_flush_async(&c->journal, NULL);
 
 	if (!ob && s.btree_bitmap != BTREE_BITMAP_ANY) {
diff --git a/fs/bcachefs/alloc_types.h b/fs/bcachefs/alloc_types.h
index 9bbb28e90b93..4aa8ee026cb8 100644
--- a/fs/bcachefs/alloc_types.h
+++ b/fs/bcachefs/alloc_types.h
@@ -18,6 +18,7 @@ struct bucket_alloc_state {
 	u64	buckets_seen;
 	u64	skipped_open;
 	u64	skipped_need_journal_commit;
+	u64	need_journal_commit;
 	u64	skipped_nocow;
 	u64	skipped_nouse;
 	u64	skipped_mi_btree_bitmap;
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 672ca2c1d37d..ca755e8d1a37 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -24,7 +24,10 @@ do {						 \
 } while (0)
 
 const char * const bch2_btree_node_flags[] = {
-#define x(f)	#f,
+	"typebit",
+	"typebit",
+	"typebit",
+#define x(f)	[BTREE_NODE_##f] = #f,
 	BTREE_FLAGS()
 #undef x
 	NULL
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 367231ab1980..5988219c6908 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2239,8 +2239,6 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos
 	if (unlikely(ret))
 		return bkey_s_c_err(ret);
 
-	btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path);
-
 	k = bch2_btree_path_peek_slot(trans->paths + iter->key_cache_path, &u);
 	if (!k.k)
 		return k;
@@ -2251,6 +2249,7 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos
 
 	iter->k = u;
 	k.k = &iter->k;
+	btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path);
 	return k;
 }
 
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 3b62296c3100..1821f40c161a 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -291,8 +291,10 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans,
 					 struct btree_path *ck_path,
 					 unsigned flags)
 {
-	if (flags & BTREE_ITER_cached_nofill)
+	if (flags & BTREE_ITER_cached_nofill) {
+		ck_path->l[0].b = NULL;
 		return 0;
+	}
 
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
@@ -746,7 +748,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc)
 				rcu_read_unlock();
 				mutex_lock(&bc->table.mutex);
 				mutex_unlock(&bc->table.mutex);
-				rcu_read_lock();
 				continue;
 			}
 			for (i = 0; i < tbl->size; i++)
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 6b79b672e0b1..2760dd9569ed 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -348,7 +348,7 @@ static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans,
 						      unsigned flags)
 {
 	return bch2_journal_res_get(&trans->c->journal, &trans->journal_res,
-				    trans->journal_u64s, flags);
+				    trans->journal_u64s, flags, trans);
 }
 
 #define JSET_ENTRY_LOG_U64s		4
diff --git a/fs/bcachefs/buckets_waiting_for_journal.c b/fs/bcachefs/buckets_waiting_for_journal.c
index f9fb150eda70..c8a488e6b7b8 100644
--- a/fs/bcachefs/buckets_waiting_for_journal.c
+++ b/fs/bcachefs/buckets_waiting_for_journal.c
@@ -22,23 +22,21 @@ static void bucket_table_init(struct buckets_waiting_for_journal_table *t, size_
 	memset(t->d, 0, sizeof(t->d[0]) << t->bits);
 }
 
-bool bch2_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b,
-				      u64 flushed_seq,
-				      unsigned dev, u64 bucket)
+u64 bch2_bucket_journal_seq_ready(struct buckets_waiting_for_journal *b,
+				  unsigned dev, u64 bucket)
 {
 	struct buckets_waiting_for_journal_table *t;
 	u64 dev_bucket = (u64) dev << 56 | bucket;
-	bool ret = false;
-	unsigned i;
+	u64 ret = 0;
 
 	mutex_lock(&b->lock);
 	t = b->t;
 
-	for (i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) {
+	for (unsigned i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) {
 		struct bucket_hashed *h = bucket_hash(t, i, dev_bucket);
 
 		if (h->dev_bucket == dev_bucket) {
-			ret = h->journal_seq > flushed_seq;
+			ret = h->journal_seq;
 			break;
 		}
 	}
diff --git a/fs/bcachefs/buckets_waiting_for_journal.h b/fs/bcachefs/buckets_waiting_for_journal.h
index d2ae19cbe18c..365619ca44c8 100644
--- a/fs/bcachefs/buckets_waiting_for_journal.h
+++ b/fs/bcachefs/buckets_waiting_for_journal.h
@@ -4,8 +4,8 @@
 
 #include "buckets_waiting_for_journal_types.h"
 
-bool bch2_bucket_needs_journal_commit(struct buckets_waiting_for_journal *,
-				      u64, unsigned, u64);
+u64 bch2_bucket_journal_seq_ready(struct buckets_waiting_for_journal *,
+				  unsigned, u64);
 int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *,
 					 u64, unsigned, u64, u64);
 
diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c
index f99ff1819597..114bf2f3879f 100644
--- a/fs/bcachefs/compress.c
+++ b/fs/bcachefs/compress.c
@@ -4,6 +4,7 @@
 #include "compress.h"
 #include "error.h"
 #include "extents.h"
+#include "io_write.h"
 #include "opts.h"
 #include "super-io.h"
 
@@ -254,11 +255,14 @@ err:
 	goto out;
 }
 
-int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio,
-				struct bch_extent_crc_unpacked *crc)
+int bch2_bio_uncompress_inplace(struct bch_write_op *op,
+				struct bio *bio)
 {
+	struct bch_fs *c = op->c;
+	struct bch_extent_crc_unpacked *crc = &op->crc;
 	struct bbuf data = { NULL };
 	size_t dst_len = crc->uncompressed_size << 9;
+	int ret = 0;
 
 	/* bio must own its pages: */
 	BUG_ON(!bio->bi_vcnt);
@@ -266,17 +270,26 @@ int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio,
 
 	if (crc->uncompressed_size << 9	> c->opts.encoded_extent_max ||
 	    crc->compressed_size << 9	> c->opts.encoded_extent_max) {
-		bch_err(c, "error rewriting existing data: extent too big");
+		struct printbuf buf = PRINTBUF;
+		bch2_write_op_error(&buf, op);
+		prt_printf(&buf, "error rewriting existing data: extent too big");
+		bch_err_ratelimited(c, "%s", buf.buf);
+		printbuf_exit(&buf);
 		return -EIO;
 	}
 
 	data = __bounce_alloc(c, dst_len, WRITE);
 
 	if (__bio_uncompress(c, bio, data.b, *crc)) {
-		if (!c->opts.no_data_io)
-			bch_err(c, "error rewriting existing data: decompression error");
-		bio_unmap_or_unbounce(c, data);
-		return -EIO;
+		if (!c->opts.no_data_io) {
+			struct printbuf buf = PRINTBUF;
+			bch2_write_op_error(&buf, op);
+			prt_printf(&buf, "error rewriting existing data: decompression error");
+			bch_err_ratelimited(c, "%s", buf.buf);
+			printbuf_exit(&buf);
+		}
+		ret = -EIO;
+		goto err;
 	}
 
 	/*
@@ -293,9 +306,9 @@ int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio,
 	crc->uncompressed_size	= crc->live_size;
 	crc->offset		= 0;
 	crc->csum		= (struct bch_csum) { 0, 0 };
-
+err:
 	bio_unmap_or_unbounce(c, data);
-	return 0;
+	return ret;
 }
 
 int bch2_bio_uncompress(struct bch_fs *c, struct bio *src,
diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h
index 607fd5e232c9..bec2f05bfd52 100644
--- a/fs/bcachefs/compress.h
+++ b/fs/bcachefs/compress.h
@@ -47,8 +47,8 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v)
 	return __bch2_compression_opt_to_type[bch2_compression_decode(v).type];
 }
 
-int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *,
-				struct bch_extent_crc_unpacked *);
+struct bch_write_op;
+int bch2_bio_uncompress_inplace(struct bch_write_op *, struct bio *);
 int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *,
 		       struct bvec_iter, struct bch_extent_crc_unpacked);
 unsigned bch2_bio_compress(struct bch_fs *, struct bio *, size_t *,
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 585214931e05..337494facac6 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -91,15 +91,28 @@ static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struc
 	return true;
 }
 
-static void trace_move_extent_finish2(struct bch_fs *c, struct bkey_s_c k)
+static noinline void trace_move_extent_finish2(struct data_update *u,
+					       struct bkey_i *new,
+					       struct bkey_i *insert)
 {
-	if (trace_move_extent_finish_enabled()) {
-		struct printbuf buf = PRINTBUF;
+	struct bch_fs *c = u->op.c;
+	struct printbuf buf = PRINTBUF;
 
-		bch2_bkey_val_to_text(&buf, c, k);
-		trace_move_extent_finish(c, buf.buf);
-		printbuf_exit(&buf);
-	}
+	prt_newline(&buf);
+
+	bch2_data_update_to_text(&buf, u);
+	prt_newline(&buf);
+
+	prt_str_indented(&buf, "new replicas:\t");
+	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(new));
+	prt_newline(&buf);
+
+	prt_str_indented(&buf, "insert:\t");
+	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert));
+	prt_newline(&buf);
+
+	trace_move_extent_finish(c, buf.buf);
+	printbuf_exit(&buf);
 }
 
 static void trace_move_extent_fail2(struct data_update *m,
@@ -372,7 +385,8 @@ restart_drop_extra_replicas:
 			bch2_btree_iter_set_pos(&iter, next_pos);
 
 			this_cpu_add(c->counters[BCH_COUNTER_move_extent_finish], new->k.size);
-			trace_move_extent_finish2(c, bkey_i_to_s_c(&new->k_i));
+			if (trace_move_extent_finish_enabled())
+				trace_move_extent_finish2(m, &new->k_i, insert);
 		}
 err:
 		if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
@@ -525,34 +539,38 @@ void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c,
 				   struct data_update_opts *data_opts)
 {
 	printbuf_tabstop_push(out, 20);
-	prt_str(out, "rewrite ptrs:\t");
+
+	prt_str_indented(out, "rewrite ptrs:\t");
 	bch2_prt_u64_base2(out, data_opts->rewrite_ptrs);
 	prt_newline(out);
 
-	prt_str(out, "kill ptrs:\t");
+	prt_str_indented(out, "kill ptrs:\t");
 	bch2_prt_u64_base2(out, data_opts->kill_ptrs);
 	prt_newline(out);
 
-	prt_str(out, "target:\t");
+	prt_str_indented(out, "target:\t");
 	bch2_target_to_text(out, c, data_opts->target);
 	prt_newline(out);
 
-	prt_str(out, "compression:\t");
+	prt_str_indented(out, "compression:\t");
 	bch2_compression_opt_to_text(out, io_opts->background_compression);
 	prt_newline(out);
 
-	prt_str(out, "opts.replicas:\t");
+	prt_str_indented(out, "opts.replicas:\t");
 	prt_u64(out, io_opts->data_replicas);
+	prt_newline(out);
 
-	prt_str(out, "extra replicas:\t");
+	prt_str_indented(out, "extra replicas:\t");
 	prt_u64(out, data_opts->extra_replicas);
 }
 
 void bch2_data_update_to_text(struct printbuf *out, struct data_update *m)
 {
-	bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k));
-	prt_newline(out);
 	bch2_data_update_opts_to_text(out, m->op.c, &m->op.opts, &m->data_opts);
+	prt_newline(out);
+
+	prt_str_indented(out, "old key:\t");
+	bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k));
 }
 
 int bch2_extent_drop_ptrs(struct btree_trans *trans,
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index b5de52a50d10..55333e82d1fe 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -20,6 +20,7 @@
 #include "extents.h"
 #include "fsck.h"
 #include "inode.h"
+#include "journal_reclaim.h"
 #include "super.h"
 
 #include <linux/console.h>
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 8fcf7c8e5ede..53a421ff136d 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -450,7 +450,7 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 		return ret;
 
 	struct bch_hash_info dir_hash = bch2_hash_info_init(c, &lostfound);
-	struct qstr name = (struct qstr) QSTR(name_buf);
+	struct qstr name = QSTR(name_buf);
 
 	inode->bi_dir = lostfound.bi_inum;
 
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index d2e134528f0e..428b9be6af34 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -285,12 +285,14 @@ void bch2_inode_opts_get(struct bch_io_opts *, struct bch_fs *,
 			 struct bch_inode_unpacked *);
 int bch2_inum_opts_get(struct btree_trans*, subvol_inum, struct bch_io_opts *);
 
+#include "rebalance.h"
+
 static inline struct bch_extent_rebalance
 bch2_inode_rebalance_opts_get(struct bch_fs *c, struct bch_inode_unpacked *inode)
 {
 	struct bch_io_opts io_opts;
 	bch2_inode_opts_get(&io_opts, c, inode);
-	return io_opts_to_rebalance_opts(&io_opts);
+	return io_opts_to_rebalance_opts(c, &io_opts);
 }
 
 int bch2_inode_rm_snapshot(struct btree_trans *, u64, u32);
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index 3e71860f66b9..dd508d93e9fc 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -406,7 +406,7 @@ static void __bch2_write_op_error(struct printbuf *out, struct bch_write_op *op,
 		   op->flags & BCH_WRITE_MOVE ? "(internal move)" : "");
 }
 
-static void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op)
+void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op)
 {
 	__bch2_write_op_error(out, op, op->pos.offset);
 }
@@ -873,7 +873,7 @@ static enum prep_encoded_ret {
 		if (bch2_crc_cmp(op->crc.csum, csum) && !c->opts.no_data_io)
 			return PREP_ENCODED_CHECKSUM_ERR;
 
-		if (bch2_bio_uncompress_inplace(c, bio, &op->crc))
+		if (bch2_bio_uncompress_inplace(op, bio))
 			return PREP_ENCODED_ERR;
 	}
 
diff --git a/fs/bcachefs/io_write.h b/fs/bcachefs/io_write.h
index 5400ce94ee57..b4626013abc8 100644
--- a/fs/bcachefs/io_write.h
+++ b/fs/bcachefs/io_write.h
@@ -20,6 +20,8 @@ static inline void bch2_latency_acct(struct bch_dev *ca, u64 submit_time, int rw
 void bch2_submit_wbio_replicas(struct bch_write_bio *, struct bch_fs *,
 			       enum bch_data_type, const struct bkey_i *, bool);
 
+void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op);
+
 #define BCH_WRITE_FLAGS()		\
 	x(ALLOC_NOWAIT)			\
 	x(CACHED)			\
diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 2cd20114b74b..24c294d4634e 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -113,11 +113,10 @@ journal_seq_to_buf(struct journal *j, u64 seq)
 
 static void journal_pin_list_init(struct journal_entry_pin_list *p, int count)
 {
-	unsigned i;
-
-	for (i = 0; i < ARRAY_SIZE(p->list); i++)
-		INIT_LIST_HEAD(&p->list[i]);
-	INIT_LIST_HEAD(&p->flushed);
+	for (unsigned i = 0; i < ARRAY_SIZE(p->unflushed); i++)
+		INIT_LIST_HEAD(&p->unflushed[i]);
+	for (unsigned i = 0; i < ARRAY_SIZE(p->flushed); i++)
+		INIT_LIST_HEAD(&p->flushed[i]);
 	atomic_set(&p->count, count);
 	p->devs.nr = 0;
 }
@@ -320,6 +319,16 @@ void bch2_journal_halt(struct journal *j)
 	spin_unlock(&j->lock);
 }
 
+void bch2_journal_halt_locked(struct journal *j)
+{
+	lockdep_assert_held(&j->lock);
+
+	__journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL, true);
+	if (!j->err_seq)
+		j->err_seq = journal_cur_seq(j);
+	journal_wake(j);
+}
+
 static bool journal_entry_want_write(struct journal *j)
 {
 	bool ret = !journal_entry_is_open(j) ||
@@ -382,9 +391,12 @@ static int journal_entry_open(struct journal *j)
 	if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf))
 		return JOURNAL_ERR_max_in_flight;
 
-	if (bch2_fs_fatal_err_on(journal_cur_seq(j) >= JOURNAL_SEQ_MAX,
-				 c, "cannot start: journal seq overflow"))
+	if (journal_cur_seq(j) >= JOURNAL_SEQ_MAX) {
+		bch_err(c, "cannot start: journal seq overflow");
+		if (bch2_fs_emergency_read_only_locked(c))
+			bch_err(c, "fatal error - emergency read only");
 		return JOURNAL_ERR_insufficient_devices; /* -EROFS */
+	}
 
 	BUG_ON(!j->cur_entry_sectors);
 
@@ -601,6 +613,16 @@ out:
 		: -BCH_ERR_journal_res_get_blocked;
 }
 
+static unsigned max_dev_latency(struct bch_fs *c)
+{
+	u64 nsecs = 0;
+
+	for_each_rw_member(c, ca)
+		nsecs = max(nsecs, ca->io_latency[WRITE].stats.max_duration);
+
+	return nsecs_to_jiffies(nsecs);
+}
+
 /*
  * Essentially the entry function to the journaling code. When bcachefs is doing
  * a btree insert, it calls this function to get the current journal write.
@@ -612,17 +634,31 @@ out:
  * btree node write locks.
  */
 int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res,
-				  unsigned flags)
+				  unsigned flags,
+				  struct btree_trans *trans)
 {
 	int ret;
 
 	if (closure_wait_event_timeout(&j->async_wait,
 		   (ret = __journal_res_get(j, res, flags)) != -BCH_ERR_journal_res_get_blocked ||
 		   (flags & JOURNAL_RES_GET_NONBLOCK),
-		   HZ * 10))
+		   HZ))
 		return ret;
 
+	if (trans)
+		bch2_trans_unlock_long(trans);
+
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
+	int remaining_wait = max(max_dev_latency(c) * 2, HZ * 10);
+
+	remaining_wait = max(0, remaining_wait - HZ);
+
+	if (closure_wait_event_timeout(&j->async_wait,
+		   (ret = __journal_res_get(j, res, flags)) != -BCH_ERR_journal_res_get_blocked ||
+		   (flags & JOURNAL_RES_GET_NONBLOCK),
+		   remaining_wait))
+		return ret;
+
 	struct printbuf buf = PRINTBUF;
 	bch2_journal_debug_to_text(&buf, j);
 	bch_err(c, "Journal stuck? Waited for 10 seconds...\n%s",
@@ -727,7 +763,7 @@ recheck_need_open:
 		 * livelock:
 		 */
 		sched_annotate_sleep();
-		ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0);
+		ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL);
 		if (ret)
 			return ret;
 
@@ -760,6 +796,7 @@ recheck_need_open:
 	}
 
 	buf->must_flush = true;
+	j->flushing_seq = max(j->flushing_seq, seq);
 
 	if (parent && !closure_wait(&buf->wait, parent))
 		BUG();
@@ -848,7 +885,7 @@ out:
 static int __bch2_journal_meta(struct journal *j)
 {
 	struct journal_res res = {};
-	int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0);
+	int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL);
 	if (ret)
 		return ret;
 
@@ -1602,54 +1639,3 @@ void bch2_journal_debug_to_text(struct printbuf *out, struct journal *j)
 	__bch2_journal_debug_to_text(out, j);
 	spin_unlock(&j->lock);
 }
-
-bool bch2_journal_seq_pins_to_text(struct printbuf *out, struct journal *j, u64 *seq)
-{
-	struct journal_entry_pin_list *pin_list;
-	struct journal_entry_pin *pin;
-
-	spin_lock(&j->lock);
-	if (!test_bit(JOURNAL_running, &j->flags)) {
-		spin_unlock(&j->lock);
-		return true;
-	}
-
-	*seq = max(*seq, j->pin.front);
-
-	if (*seq >= j->pin.back) {
-		spin_unlock(&j->lock);
-		return true;
-	}
-
-	out->atomic++;
-
-	pin_list = journal_seq_pin(j, *seq);
-
-	prt_printf(out, "%llu: count %u\n", *seq, atomic_read(&pin_list->count));
-	printbuf_indent_add(out, 2);
-
-	for (unsigned i = 0; i < ARRAY_SIZE(pin_list->list); i++)
-		list_for_each_entry(pin, &pin_list->list[i], list)
-			prt_printf(out, "\t%px %ps\n", pin, pin->flush);
-
-	if (!list_empty(&pin_list->flushed))
-		prt_printf(out, "flushed:\n");
-
-	list_for_each_entry(pin, &pin_list->flushed, list)
-		prt_printf(out, "\t%px %ps\n", pin, pin->flush);
-
-	printbuf_indent_sub(out, 2);
-
-	--out->atomic;
-	spin_unlock(&j->lock);
-
-	return false;
-}
-
-void bch2_journal_pins_to_text(struct printbuf *out, struct journal *j)
-{
-	u64 seq = 0;
-
-	while (!bch2_journal_seq_pins_to_text(out, j, &seq))
-		seq++;
-}
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index cb0df0663946..107f7f901cd9 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -312,7 +312,7 @@ static inline void bch2_journal_res_put(struct journal *j,
 }
 
 int bch2_journal_res_get_slowpath(struct journal *, struct journal_res *,
-				  unsigned);
+				  unsigned, struct btree_trans *);
 
 /* First bits for BCH_WATERMARK: */
 enum journal_res_flags {
@@ -368,7 +368,8 @@ static inline int journal_res_get_fast(struct journal *j,
 }
 
 static inline int bch2_journal_res_get(struct journal *j, struct journal_res *res,
-				       unsigned u64s, unsigned flags)
+				       unsigned u64s, unsigned flags,
+				       struct btree_trans *trans)
 {
 	int ret;
 
@@ -380,7 +381,7 @@ static inline int bch2_journal_res_get(struct journal *j, struct journal_res *re
 	if (journal_res_get_fast(j, res, flags))
 		goto out;
 
-	ret = bch2_journal_res_get_slowpath(j, res, flags);
+	ret = bch2_journal_res_get_slowpath(j, res, flags, trans);
 	if (ret)
 		return ret;
 out:
@@ -408,6 +409,7 @@ bool bch2_journal_noflush_seq(struct journal *, u64, u64);
 int bch2_journal_meta(struct journal *);
 
 void bch2_journal_halt(struct journal *);
+void bch2_journal_halt_locked(struct journal *);
 
 static inline int bch2_journal_error(struct journal *j)
 {
@@ -429,8 +431,6 @@ struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u
 
 void __bch2_journal_debug_to_text(struct printbuf *, struct journal *);
 void bch2_journal_debug_to_text(struct printbuf *, struct journal *);
-void bch2_journal_pins_to_text(struct printbuf *, struct journal *);
-bool bch2_journal_seq_pins_to_text(struct printbuf *, struct journal *, u64 *);
 
 int bch2_set_nr_journal_buckets(struct bch_fs *, struct bch_dev *,
 				unsigned nr);
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 7f2efe85a805..11c39e0c34f4 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -17,6 +17,7 @@
 #include "sb-clean.h"
 #include "trace.h"
 
+#include <linux/ioprio.h>
 #include <linux/string_choices.h>
 
 void bch2_journal_pos_from_member_info_set(struct bch_fs *c)
@@ -1763,6 +1764,7 @@ static CLOSURE_CALLBACK(journal_write_submit)
 		bio->bi_iter.bi_sector	= ptr->offset;
 		bio->bi_end_io		= journal_write_endio;
 		bio->bi_private		= ca;
+		bio->bi_ioprio		= IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 0);
 
 		BUG_ON(bio->bi_iter.bi_sector == ca->prev_journal_sector);
 		ca->prev_journal_sector = bio->bi_iter.bi_sector;
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index 3c8242606da7..6a9cefb635d6 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -327,8 +327,10 @@ void bch2_journal_reclaim_fast(struct journal *j)
 		popped = true;
 	}
 
-	if (popped)
+	if (popped) {
 		bch2_journal_space_available(j);
+		__closure_wake_up(&j->reclaim_flush_wait);
+	}
 }
 
 bool __bch2_journal_pin_put(struct journal *j, u64 seq)
@@ -362,6 +364,9 @@ static inline bool __journal_pin_drop(struct journal *j,
 	pin->seq = 0;
 	list_del_init(&pin->list);
 
+	if (j->reclaim_flush_wait.list.first)
+		__closure_wake_up(&j->reclaim_flush_wait);
+
 	/*
 	 * Unpinning a journal entry may make journal_next_bucket() succeed, if
 	 * writing a new last_seq will now make another bucket available:
@@ -383,11 +388,11 @@ static enum journal_pin_type journal_pin_type(journal_pin_flush_fn fn)
 {
 	if (fn == bch2_btree_node_flush0 ||
 	    fn == bch2_btree_node_flush1)
-		return JOURNAL_PIN_btree;
+		return JOURNAL_PIN_TYPE_btree;
 	else if (fn == bch2_btree_key_cache_journal_flush)
-		return JOURNAL_PIN_key_cache;
+		return JOURNAL_PIN_TYPE_key_cache;
 	else
-		return JOURNAL_PIN_other;
+		return JOURNAL_PIN_TYPE_other;
 }
 
 static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq,
@@ -406,7 +411,12 @@ static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq,
 	atomic_inc(&pin_list->count);
 	pin->seq	= seq;
 	pin->flush	= flush_fn;
-	list_add(&pin->list, &pin_list->list[type]);
+
+	if (list_empty(&pin_list->unflushed[type]) &&
+	    j->reclaim_flush_wait.list.first)
+		__closure_wake_up(&j->reclaim_flush_wait);
+
+	list_add(&pin->list, &pin_list->unflushed[type]);
 }
 
 void bch2_journal_pin_copy(struct journal *j,
@@ -499,16 +509,15 @@ journal_get_next_pin(struct journal *j,
 {
 	struct journal_entry_pin_list *pin_list;
 	struct journal_entry_pin *ret = NULL;
-	unsigned i;
 
 	fifo_for_each_entry_ptr(pin_list, &j->pin, *seq) {
 		if (*seq > seq_to_flush && !allowed_above_seq)
 			break;
 
-		for (i = 0; i < JOURNAL_PIN_NR; i++)
-			if ((((1U << i) & allowed_below_seq) && *seq <= seq_to_flush) ||
-			    ((1U << i) & allowed_above_seq)) {
-				ret = list_first_entry_or_null(&pin_list->list[i],
+		for (unsigned i = 0; i < JOURNAL_PIN_TYPE_NR; i++)
+			if (((BIT(i) & allowed_below_seq) && *seq <= seq_to_flush) ||
+			    (BIT(i) & allowed_above_seq)) {
+				ret = list_first_entry_or_null(&pin_list->unflushed[i],
 					struct journal_entry_pin, list);
 				if (ret)
 					return ret;
@@ -544,8 +553,8 @@ static size_t journal_flush_pins(struct journal *j,
 		}
 
 		if (min_key_cache) {
-			allowed_above |= 1U << JOURNAL_PIN_key_cache;
-			allowed_below |= 1U << JOURNAL_PIN_key_cache;
+			allowed_above |= BIT(JOURNAL_PIN_TYPE_key_cache);
+			allowed_below |= BIT(JOURNAL_PIN_TYPE_key_cache);
 		}
 
 		cond_resched();
@@ -553,7 +562,9 @@ static size_t journal_flush_pins(struct journal *j,
 		j->last_flushed = jiffies;
 
 		spin_lock(&j->lock);
-		pin = journal_get_next_pin(j, seq_to_flush, allowed_below, allowed_above, &seq);
+		pin = journal_get_next_pin(j, seq_to_flush,
+					   allowed_below,
+					   allowed_above, &seq);
 		if (pin) {
 			BUG_ON(j->flush_in_progress);
 			j->flush_in_progress = pin;
@@ -576,7 +587,7 @@ static size_t journal_flush_pins(struct journal *j,
 		spin_lock(&j->lock);
 		/* Pin might have been dropped or rearmed: */
 		if (likely(!err && !j->flush_in_progress_dropped))
-			list_move(&pin->list, &journal_seq_pin(j, seq)->flushed);
+			list_move(&pin->list, &journal_seq_pin(j, seq)->flushed[journal_pin_type(flush_fn)]);
 		j->flush_in_progress = NULL;
 		j->flush_in_progress_dropped = false;
 		spin_unlock(&j->lock);
@@ -816,10 +827,41 @@ int bch2_journal_reclaim_start(struct journal *j)
 	return 0;
 }
 
+static bool journal_pins_still_flushing(struct journal *j, u64 seq_to_flush,
+					unsigned types)
+{
+	struct journal_entry_pin_list *pin_list;
+	u64 seq;
+
+	spin_lock(&j->lock);
+	fifo_for_each_entry_ptr(pin_list, &j->pin, seq) {
+		if (seq > seq_to_flush)
+			break;
+
+		for (unsigned i = 0; i < JOURNAL_PIN_TYPE_NR; i++)
+			if ((BIT(i) & types) &&
+			    (!list_empty(&pin_list->unflushed[i]) ||
+			     !list_empty(&pin_list->flushed[i]))) {
+				spin_unlock(&j->lock);
+				return true;
+			}
+	}
+	spin_unlock(&j->lock);
+
+	return false;
+}
+
+static bool journal_flush_pins_or_still_flushing(struct journal *j, u64 seq_to_flush,
+						 unsigned types)
+{
+	return  journal_flush_pins(j, seq_to_flush, types, 0, 0, 0) ||
+		journal_pins_still_flushing(j, seq_to_flush, types);
+}
+
 static int journal_flush_done(struct journal *j, u64 seq_to_flush,
 			      bool *did_work)
 {
-	int ret;
+	int ret = 0;
 
 	ret = bch2_journal_error(j);
 	if (ret)
@@ -827,12 +869,18 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush,
 
 	mutex_lock(&j->reclaim_lock);
 
-	if (journal_flush_pins(j, seq_to_flush,
-			       (1U << JOURNAL_PIN_key_cache)|
-			       (1U << JOURNAL_PIN_other), 0, 0, 0) ||
-	    journal_flush_pins(j, seq_to_flush,
-			       (1U << JOURNAL_PIN_btree), 0, 0, 0))
+	if (journal_flush_pins_or_still_flushing(j, seq_to_flush,
+			       BIT(JOURNAL_PIN_TYPE_key_cache)|
+			       BIT(JOURNAL_PIN_TYPE_other))) {
+		*did_work = true;
+		goto unlock;
+	}
+
+	if (journal_flush_pins_or_still_flushing(j, seq_to_flush,
+			       BIT(JOURNAL_PIN_TYPE_btree))) {
 		*did_work = true;
+		goto unlock;
+	}
 
 	if (seq_to_flush > journal_cur_seq(j))
 		bch2_journal_entry_close(j);
@@ -847,6 +895,7 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush,
 		!fifo_used(&j->pin);
 
 	spin_unlock(&j->lock);
+unlock:
 	mutex_unlock(&j->reclaim_lock);
 
 	return ret;
@@ -860,7 +909,7 @@ bool bch2_journal_flush_pins(struct journal *j, u64 seq_to_flush)
 	if (!test_bit(JOURNAL_running, &j->flags))
 		return false;
 
-	closure_wait_event(&j->async_wait,
+	closure_wait_event(&j->reclaim_flush_wait,
 		journal_flush_done(j, seq_to_flush, &did_work));
 
 	return did_work;
@@ -926,3 +975,54 @@ err:
 
 	return ret;
 }
+
+bool bch2_journal_seq_pins_to_text(struct printbuf *out, struct journal *j, u64 *seq)
+{
+	struct journal_entry_pin_list *pin_list;
+	struct journal_entry_pin *pin;
+
+	spin_lock(&j->lock);
+	if (!test_bit(JOURNAL_running, &j->flags)) {
+		spin_unlock(&j->lock);
+		return true;
+	}
+
+	*seq = max(*seq, j->pin.front);
+
+	if (*seq >= j->pin.back) {
+		spin_unlock(&j->lock);
+		return true;
+	}
+
+	out->atomic++;
+
+	pin_list = journal_seq_pin(j, *seq);
+
+	prt_printf(out, "%llu: count %u\n", *seq, atomic_read(&pin_list->count));
+	printbuf_indent_add(out, 2);
+
+	prt_printf(out, "unflushed:\n");
+	for (unsigned i = 0; i < ARRAY_SIZE(pin_list->unflushed); i++)
+		list_for_each_entry(pin, &pin_list->unflushed[i], list)
+			prt_printf(out, "\t%px %ps\n", pin, pin->flush);
+
+	prt_printf(out, "flushed:\n");
+	for (unsigned i = 0; i < ARRAY_SIZE(pin_list->flushed); i++)
+		list_for_each_entry(pin, &pin_list->flushed[i], list)
+			prt_printf(out, "\t%px %ps\n", pin, pin->flush);
+
+	printbuf_indent_sub(out, 2);
+
+	--out->atomic;
+	spin_unlock(&j->lock);
+
+	return false;
+}
+
+void bch2_journal_pins_to_text(struct printbuf *out, struct journal *j)
+{
+	u64 seq = 0;
+
+	while (!bch2_journal_seq_pins_to_text(out, j, &seq))
+		seq++;
+}
diff --git a/fs/bcachefs/journal_reclaim.h b/fs/bcachefs/journal_reclaim.h
index ec84c3345281..0a73d7134e1c 100644
--- a/fs/bcachefs/journal_reclaim.h
+++ b/fs/bcachefs/journal_reclaim.h
@@ -78,4 +78,7 @@ static inline bool bch2_journal_flush_all_pins(struct journal *j)
 
 int bch2_journal_flush_device_pins(struct journal *, int);
 
+void bch2_journal_pins_to_text(struct printbuf *, struct journal *);
+bool bch2_journal_seq_pins_to_text(struct printbuf *, struct journal *, u64 *);
+
 #endif /* _BCACHEFS_JOURNAL_RECLAIM_H */
diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h
index e9bd716fbb71..a198a81d7478 100644
--- a/fs/bcachefs/journal_types.h
+++ b/fs/bcachefs/journal_types.h
@@ -53,15 +53,15 @@ struct journal_buf {
  */
 
 enum journal_pin_type {
-	JOURNAL_PIN_btree,
-	JOURNAL_PIN_key_cache,
-	JOURNAL_PIN_other,
-	JOURNAL_PIN_NR,
+	JOURNAL_PIN_TYPE_btree,
+	JOURNAL_PIN_TYPE_key_cache,
+	JOURNAL_PIN_TYPE_other,
+	JOURNAL_PIN_TYPE_NR,
 };
 
 struct journal_entry_pin_list {
-	struct list_head		list[JOURNAL_PIN_NR];
-	struct list_head		flushed;
+	struct list_head		unflushed[JOURNAL_PIN_TYPE_NR];
+	struct list_head		flushed[JOURNAL_PIN_TYPE_NR];
 	atomic_t			count;
 	struct bch_devs_list		devs;
 };
@@ -226,6 +226,7 @@ struct journal {
 	/* Used when waiting because the journal was full */
 	wait_queue_head_t	wait;
 	struct closure_waitlist	async_wait;
+	struct closure_waitlist	reclaim_flush_wait;
 
 	struct delayed_work	write_work;
 	struct workqueue_struct *wq;
@@ -236,6 +237,7 @@ struct journal {
 	/* seq, last_seq from the most recent journal entry successfully written */
 	u64			seq_ondisk;
 	u64			flushed_seq_ondisk;
+	u64			flushing_seq;
 	u64			last_seq_ondisk;
 	u64			err_seq;
 	u64			last_empty_seq;
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 85c361e78ba5..21805509ab9e 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -215,7 +215,8 @@ static int bch2_copygc(struct moving_context *ctxt,
 	};
 	move_buckets buckets = { 0 };
 	struct move_bucket_in_flight *f;
-	u64 moved = atomic64_read(&ctxt->stats->sectors_moved);
+	u64 sectors_seen	= atomic64_read(&ctxt->stats->sectors_seen);
+	u64 sectors_moved	= atomic64_read(&ctxt->stats->sectors_moved);
 	int ret = 0;
 
 	ret = bch2_copygc_get_buckets(ctxt, buckets_in_flight, &buckets);
@@ -245,7 +246,6 @@ static int bch2_copygc(struct moving_context *ctxt,
 		*did_work = true;
 	}
 err:
-	darray_exit(&buckets);
 
 	/* no entries in LRU btree found, or got to end: */
 	if (bch2_err_matches(ret, ENOENT))
@@ -254,8 +254,11 @@ err:
 	if (ret < 0 && !bch2_err_matches(ret, EROFS))
 		bch_err_msg(c, ret, "from bch2_move_data()");
 
-	moved = atomic64_read(&ctxt->stats->sectors_moved) - moved;
-	trace_and_count(c, copygc, c, moved, 0, 0, 0);
+	sectors_seen	= atomic64_read(&ctxt->stats->sectors_seen) - sectors_seen;
+	sectors_moved	= atomic64_read(&ctxt->stats->sectors_moved) - sectors_moved;
+	trace_and_count(c, copygc, c, buckets.nr, sectors_seen, sectors_moved);
+
+	darray_exit(&buckets);
 	return ret;
 }
 
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index e763d52e0f38..9d397fc2a1f0 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -476,13 +476,13 @@ enum fsck_err_opts {
 	  NULL,		"Enable nocow mode: enables runtime locking in\n"\
 			"data move path needed if nocow will ever be in use\n")\
 	x(copygc_enabled,		u8,				\
-	  OPT_FS|OPT_MOUNT,						\
+	  OPT_FS|OPT_MOUNT|OPT_RUNTIME,					\
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,			true,			\
 	  NULL,		"Enable copygc: disable for debugging, or to\n"\
 			"quiet the system when doing performance testing\n")\
 	x(rebalance_enabled,		u8,				\
-	  OPT_FS|OPT_MOUNT,						\
+	  OPT_FS|OPT_MOUNT|OPT_RUNTIME,					\
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,			true,			\
 	  NULL,		"Enable rebalance: disable for debugging, or to\n"\
@@ -659,18 +659,4 @@ static inline void bch2_io_opts_fixups(struct bch_io_opts *opts)
 struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts);
 bool bch2_opt_is_inode_opt(enum bch_opt_id);
 
-/* rebalance opts: */
-
-static inline struct bch_extent_rebalance io_opts_to_rebalance_opts(struct bch_io_opts *opts)
-{
-	return (struct bch_extent_rebalance) {
-		.type = BIT(BCH_EXTENT_ENTRY_rebalance),
-#define x(_name)							\
-		._name = opts->_name,					\
-		._name##_from_inode = opts->_name##_from_inode,
-		BCH_REBALANCE_OPTS()
-#undef x
-	};
-};
-
 #endif /* _BCACHEFS_OPTS_H */
diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c
index 4adc74cd3f70..d0a1f5cd5c2b 100644
--- a/fs/bcachefs/rebalance.c
+++ b/fs/bcachefs/rebalance.c
@@ -121,12 +121,10 @@ u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k)
 		}
 	}
 incompressible:
-	if (opts->background_target &&
-	    bch2_target_accepts_data(c, BCH_DATA_user, opts->background_target)) {
+	if (opts->background_target)
 		bkey_for_each_ptr_decode(k.k, ptrs, p, entry)
 			if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, opts->background_target))
 				sectors += p.crc.compressed_size;
-	}
 
 	return sectors;
 }
@@ -140,7 +138,7 @@ static bool bch2_bkey_rebalance_needs_update(struct bch_fs *c, struct bch_io_opt
 	const struct bch_extent_rebalance *old = bch2_bkey_rebalance_opts(k);
 
 	if (k.k->type == KEY_TYPE_reflink_v || bch2_bkey_ptrs_need_rebalance(c, opts, k)) {
-		struct bch_extent_rebalance new = io_opts_to_rebalance_opts(opts);
+		struct bch_extent_rebalance new = io_opts_to_rebalance_opts(c, opts);
 		return old == NULL || memcmp(old, &new, sizeof(new));
 	} else {
 		return old != NULL;
@@ -163,7 +161,7 @@ int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bch_io_opts *opts,
 			k.k->u64s += sizeof(*old) / sizeof(u64);
 		}
 
-		*old = io_opts_to_rebalance_opts(opts);
+		*old = io_opts_to_rebalance_opts(c, opts);
 	} else {
 		if (old)
 			extent_entry_drop(k, (union bch_extent_entry *) old);
diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h
index 0a0821ab895d..62a3859d3823 100644
--- a/fs/bcachefs/rebalance.h
+++ b/fs/bcachefs/rebalance.h
@@ -4,8 +4,28 @@
 
 #include "compress.h"
 #include "disk_groups.h"
+#include "opts.h"
 #include "rebalance_types.h"
 
+static inline struct bch_extent_rebalance io_opts_to_rebalance_opts(struct bch_fs *c,
+								    struct bch_io_opts *opts)
+{
+	struct bch_extent_rebalance r = {
+		.type = BIT(BCH_EXTENT_ENTRY_rebalance),
+#define x(_name)							\
+		._name = opts->_name,					\
+		._name##_from_inode = opts->_name##_from_inode,
+		BCH_REBALANCE_OPTS()
+#undef x
+	};
+
+	if (r.background_target &&
+	    !bch2_target_accepts_data(c, BCH_DATA_user, r.background_target))
+		r.background_target = 0;
+
+	return r;
+};
+
 u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c);
 int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bch_io_opts *, struct bkey_i *);
 int bch2_get_update_rebalance_opts(struct btree_trans *,
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 98825437381c..71c786cdb192 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -32,7 +32,6 @@
 #include <linux/sort.h>
 #include <linux/stat.h>
 
-#define QSTR(n) { { { .len = strlen(n) } }, .name = n }
 
 int bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree)
 {
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 0b4fe899209b..ea0a18364751 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -57,7 +57,7 @@ enum bch_fsck_flags {
 	x(bset_wrong_sector_offset,				 44,	0)		\
 	x(bset_empty,						 45,	0)		\
 	x(bset_bad_seq,						 46,	0)		\
-	x(bset_blacklisted_journal_seq,				 47,	0)		\
+	x(bset_blacklisted_journal_seq,				 47,	FSCK_AUTOFIX)	\
 	x(first_bset_blacklisted_journal_seq,			 48,	FSCK_AUTOFIX)	\
 	x(btree_node_bad_btree,					 49,	0)		\
 	x(btree_node_bad_level,					 50,	0)		\
diff --git a/fs/bcachefs/str_hash.c b/fs/bcachefs/str_hash.c
index 8c2c5539de2e..d78451c2a0c6 100644
--- a/fs/bcachefs/str_hash.c
+++ b/fs/bcachefs/str_hash.c
@@ -31,11 +31,11 @@ static int bch2_dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dir
 	}
 }
 
-static int fsck_rename_dirent(struct btree_trans *trans,
-			      struct snapshots_seen *s,
-			      const struct bch_hash_desc desc,
-			      struct bch_hash_info *hash_info,
-			      struct bkey_s_c_dirent old)
+static noinline int fsck_rename_dirent(struct btree_trans *trans,
+				       struct snapshots_seen *s,
+				       const struct bch_hash_desc desc,
+				       struct bch_hash_info *hash_info,
+				       struct bkey_s_c_dirent old)
 {
 	struct qstr old_name = bch2_dirent_get_name(old);
 	struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32);
@@ -71,11 +71,11 @@ static int fsck_rename_dirent(struct btree_trans *trans,
 	return bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i);
 }
 
-static int hash_pick_winner(struct btree_trans *trans,
-			    const struct bch_hash_desc desc,
-			    struct bch_hash_info *hash_info,
-			    struct bkey_s_c k1,
-			    struct bkey_s_c k2)
+static noinline int hash_pick_winner(struct btree_trans *trans,
+				     const struct bch_hash_desc desc,
+				     struct bch_hash_info *hash_info,
+				     struct bkey_s_c k1,
+				     struct bkey_s_c k2)
 {
 	if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) &&
 	    !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k)))
@@ -142,8 +142,8 @@ fsck_err:
  * All versions of the same inode in different snapshots must have the same hash
  * seed/type: verify that the hash info we're using matches the root
  */
-static int check_inode_hash_info_matches_root(struct btree_trans *trans, u64 inum,
-					      struct bch_hash_info *hash_info)
+static noinline int check_inode_hash_info_matches_root(struct btree_trans *trans, u64 inum,
+						       struct bch_hash_info *hash_info)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c
index e3d0475232e5..b7b96283c316 100644
--- a/fs/bcachefs/subvolume.c
+++ b/fs/bcachefs/subvolume.c
@@ -428,7 +428,7 @@ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid)
 		bch2_bkey_get_iter_typed(trans, &snapshot_iter,
 				BTREE_ID_snapshots, POS(0, snapid),
 				0, snapshot);
-	ret = bkey_err(subvol);
+	ret = bkey_err(snapshot);
 	bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c,
 				"missing snapshot %u", snapid);
 	if (ret)
@@ -440,6 +440,11 @@ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid)
 		bch2_bkey_get_iter_typed(trans, &snapshot_tree_iter,
 				BTREE_ID_snapshot_trees, POS(0, treeid),
 				0, snapshot_tree);
+	ret = bkey_err(snapshot_tree);
+	bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c,
+				"missing snapshot tree %u", treeid);
+	if (ret)
+		goto err;
 
 	if (le32_to_cpu(snapshot_tree.v->master_subvol) == subvolid) {
 		struct bkey_i_snapshot_tree *snapshot_tree_mut =
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index d97ea7bd1171..6d97d412fed9 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -411,6 +411,17 @@ bool bch2_fs_emergency_read_only(struct bch_fs *c)
 	return ret;
 }
 
+bool bch2_fs_emergency_read_only_locked(struct bch_fs *c)
+{
+	bool ret = !test_and_set_bit(BCH_FS_emergency_ro, &c->flags);
+
+	bch2_journal_halt_locked(&c->journal);
+	bch2_fs_read_only_async(c);
+
+	wake_up(&bch2_read_only_wait);
+	return ret;
+}
+
 static int bch2_fs_read_write_late(struct bch_fs *c)
 {
 	int ret;
diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h
index fa6d52216510..04f8287eff5c 100644
--- a/fs/bcachefs/super.h
+++ b/fs/bcachefs/super.h
@@ -29,6 +29,7 @@ int bch2_dev_resize(struct bch_fs *, struct bch_dev *, u64);
 struct bch_dev *bch2_dev_lookup(struct bch_fs *, const char *);
 
 bool bch2_fs_emergency_read_only(struct bch_fs *);
+bool bch2_fs_emergency_read_only_locked(struct bch_fs *);
 void bch2_fs_read_only(struct bch_fs *);
 
 int bch2_fs_read_write(struct bch_fs *);
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 9d40b7d4ea29..c1b51009edf6 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -727,7 +727,7 @@ DEFINE_EVENT(fs_str, bucket_alloc_fail,
 	TP_ARGS(c, str)
 );
 
-TRACE_EVENT(discard_buckets,
+DECLARE_EVENT_CLASS(discard_buckets_class,
 	TP_PROTO(struct bch_fs *c, u64 seen, u64 open,
 		 u64 need_journal_commit, u64 discarded, const char *err),
 	TP_ARGS(c, seen, open, need_journal_commit, discarded, err),
@@ -759,6 +759,18 @@ TRACE_EVENT(discard_buckets,
 		  __entry->err)
 );
 
+DEFINE_EVENT(discard_buckets_class, discard_buckets,
+	TP_PROTO(struct bch_fs *c, u64 seen, u64 open,
+		 u64 need_journal_commit, u64 discarded, const char *err),
+	TP_ARGS(c, seen, open, need_journal_commit, discarded, err)
+);
+
+DEFINE_EVENT(discard_buckets_class, discard_buckets_fast,
+	TP_PROTO(struct bch_fs *c, u64 seen, u64 open,
+		 u64 need_journal_commit, u64 discarded, const char *err),
+	TP_ARGS(c, seen, open, need_journal_commit, discarded, err)
+);
+
 TRACE_EVENT(bucket_invalidate,
 	TP_PROTO(struct bch_fs *c, unsigned dev, u64 bucket, u32 sectors),
 	TP_ARGS(c, dev, bucket, sectors),
@@ -902,32 +914,30 @@ TRACE_EVENT(evacuate_bucket,
 
 TRACE_EVENT(copygc,
 	TP_PROTO(struct bch_fs *c,
-		 u64 sectors_moved, u64 sectors_not_moved,
-		 u64 buckets_moved, u64 buckets_not_moved),
-	TP_ARGS(c,
-		sectors_moved, sectors_not_moved,
-		buckets_moved, buckets_not_moved),
+		 u64 buckets,
+		 u64 sectors_seen,
+		 u64 sectors_moved),
+	TP_ARGS(c, buckets, sectors_seen, sectors_moved),
 
 	TP_STRUCT__entry(
 		__field(dev_t,		dev			)
+		__field(u64,		buckets			)
+		__field(u64,		sectors_seen		)
 		__field(u64,		sectors_moved		)
-		__field(u64,		sectors_not_moved	)
-		__field(u64,		buckets_moved		)
-		__field(u64,		buckets_not_moved	)
 	),
 
 	TP_fast_assign(
 		__entry->dev			= c->dev;
+		__entry->buckets		= buckets;
+		__entry->sectors_seen		= sectors_seen;
 		__entry->sectors_moved		= sectors_moved;
-		__entry->sectors_not_moved	= sectors_not_moved;
-		__entry->buckets_moved		= buckets_moved;
-		__entry->buckets_not_moved = buckets_moved;
 	),
 
-	TP_printk("%d,%d sectors moved %llu remain %llu buckets moved %llu remain %llu",
+	TP_printk("%d,%d buckets %llu sectors seen %llu moved %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->sectors_moved, __entry->sectors_not_moved,
-		  __entry->buckets_moved, __entry->buckets_not_moved)
+		  __entry->buckets,
+		  __entry->sectors_seen,
+		  __entry->sectors_moved)
 );
 
 TRACE_EVENT(copygc_wait,
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 1a1720116071..e7c3541b38f3 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -670,8 +670,6 @@ static inline int cmp_le32(__le32 l, __le32 r)
 
 #include <linux/uuid.h>
 
-#define QSTR(n) { { { .len = strlen(n) } }, .name = n }
-
 static inline bool qstr_eq(const struct qstr l, const struct qstr r)
 {
 	return l.len == r.len && !memcmp(l.name, r.name, l.len);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 92071ca0655f..3dc5a35dd19b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1496,6 +1496,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 
 		if (!p->skip_locking) {
 			btrfs_unlock_up_safe(p, parent_level + 1);
+			btrfs_maybe_reset_lockdep_class(root, tmp);
 			tmp_locked = true;
 			btrfs_tree_read_lock(tmp);
 			btrfs_release_path(p);
@@ -1539,6 +1540,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 
 	if (!p->skip_locking) {
 		ASSERT(ret == -EAGAIN);
+		btrfs_maybe_reset_lockdep_class(root, tmp);
 		tmp_locked = true;
 		btrfs_tree_read_lock(tmp);
 		btrfs_release_path(p);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d9f856358704..a2cac9d0a1a9 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -629,7 +629,7 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
 	for (allocated = 0; allocated < nr_pages;) {
 		unsigned int last = allocated;
 
-		allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array);
+		allocated = alloc_pages_bulk(gfp, nr_pages, page_array);
 		if (unlikely(allocated == last)) {
 			/* No progress, fail and do cleanup. */
 			for (int i = 0; i < allocated; i++) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fe2c810335ff..a9322601ab5c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10173,7 +10173,6 @@ out_unlock_mmap:
 	*span = bsi.highest_ppage - bsi.lowest_ppage + 1;
 	sis->max = bsi.nr_pages;
 	sis->pages = bsi.nr_pages - 1;
-	sis->highest_bit = bsi.nr_pages - 1;
 	return bsi.nr_extents;
 }
 #else
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 30eceaf829a7..4aca7475fd82 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -1229,6 +1229,18 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent(
 	 */
 	if (WARN_ON_ONCE(len >= ordered->num_bytes))
 		return ERR_PTR(-EINVAL);
+	/*
+	 * If our ordered extent had an error there's no point in continuing.
+	 * The error may have come from a transaction abort done either by this
+	 * task or some other concurrent task, and the transaction abort path
+	 * iterates over all existing ordered extents and sets the flag
+	 * BTRFS_ORDERED_IOERR on them.
+	 */
+	if (unlikely(flags & (1U << BTRFS_ORDERED_IOERR))) {
+		const int fs_error = BTRFS_FS_ERROR(fs_info);
+
+		return fs_error ? ERR_PTR(fs_error) : ERR_PTR(-EIO);
+	}
 	/* We cannot split partially completed ordered extents. */
 	if (ordered->bytes_left) {
 		ASSERT(!(flags & ~BTRFS_ORDERED_TYPE_FLAGS));
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index b90fabe302e6..f9d3766c809b 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1880,11 +1880,7 @@ int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 su
 	 * Commit current transaction to make sure all the rfer/excl numbers
 	 * get updated.
 	 */
-	trans = btrfs_start_transaction(fs_info->quota_root, 0);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-
-	ret = btrfs_commit_transaction(trans);
+	ret = btrfs_commit_current_transaction(fs_info->quota_root);
 	if (ret < 0)
 		return ret;
 
@@ -1897,8 +1893,11 @@ int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 su
 	/*
 	 * It's squota and the subvolume still has numbers needed for future
 	 * accounting, in this case we can not delete it.  Just skip it.
+	 *
+	 * Or the qgroup is already removed by a qgroup rescan. For both cases we're
+	 * safe to ignore them.
 	 */
-	if (ret == -EBUSY)
+	if (ret == -EBUSY || ret == -ENOENT)
 		ret = 0;
 	return ret;
 }
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 15312013f2a3..aca83a98b75a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -274,8 +274,10 @@ loop:
 	cur_trans = fs_info->running_transaction;
 	if (cur_trans) {
 		if (TRANS_ABORTED(cur_trans)) {
+			const int abort_error = cur_trans->aborted;
+
 			spin_unlock(&fs_info->trans_lock);
-			return cur_trans->aborted;
+			return abort_error;
 		}
 		if (btrfs_blocked_trans_types[cur_trans->state] & type) {
 			spin_unlock(&fs_info->trans_lock);
diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c
index 1715d5ca2b2d..e341ade47dd8 100644
--- a/fs/cachefiles/error_inject.c
+++ b/fs/cachefiles/error_inject.c
@@ -11,7 +11,7 @@
 unsigned int cachefiles_error_injection_state;
 
 static struct ctl_table_header *cachefiles_sysctl;
-static struct ctl_table cachefiles_sysctls[] = {
+static const struct ctl_table cachefiles_sysctls[] = {
 	{
 		.procname	= "error_injection",
 		.data		= &cachefiles_error_injection_state,
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index fdf9dc15eafa..fdd404fc8112 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -412,7 +412,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 
 void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
-	char name[100];
+	char name[NAME_MAX];
 
 	doutc(fsc->client, "begin\n");
 	fsc->debugfs_congestion_kb =
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 0bf388e07a02..62e99e65250d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1940,29 +1940,19 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry,
 /*
  * Check if cached dentry can be trusted.
  */
-static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int ceph_d_revalidate(struct inode *dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc;
 	struct ceph_client *cl = mdsc->fsc->client;
 	int valid = 0;
-	struct dentry *parent;
-	struct inode *dir, *inode;
+	struct inode *inode;
 
-	valid = fscrypt_d_revalidate(dentry, flags);
+	valid = fscrypt_d_revalidate(dir, name, dentry, flags);
 	if (valid <= 0)
 		return valid;
 
-	if (flags & LOOKUP_RCU) {
-		parent = READ_ONCE(dentry->d_parent);
-		dir = d_inode_rcu(parent);
-		if (!dir)
-			return -ECHILD;
-		inode = d_inode_rcu(dentry);
-	} else {
-		parent = dget_parent(dentry);
-		dir = d_inode(parent);
-		inode = d_inode(dentry);
-	}
+	inode = d_inode_rcu(dentry);
 
 	doutc(cl, "%p '%pd' inode %p offset 0x%llx nokey %d\n",
 	      dentry, dentry, inode, ceph_dentry(dentry)->offset,
@@ -2008,6 +1998,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			req->r_parent = dir;
 			ihold(dir);
 
+			req->r_dname = name;
+
 			mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
 			if (ceph_security_xattr_wanted(dir))
 				mask |= CEPH_CAP_XATTR_SHARED;
@@ -2038,9 +2030,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	doutc(cl, "%p '%pd' %s\n", dentry, dentry, valid ? "valid" : "invalid");
 	if (!valid)
 		ceph_dir_clear_complete(dir);
-
-	if (!(flags & LOOKUP_RCU))
-		dput(parent);
 	return valid;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 785fe489ef4b..54b3421501e9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2621,6 +2621,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
 {
 	struct inode *dir = req->r_parent;
 	struct dentry *dentry = req->r_dentry;
+	const struct qstr *name = req->r_dname;
 	u8 *cryptbuf = NULL;
 	u32 len = 0;
 	int ret = 0;
@@ -2641,8 +2642,10 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
 	if (!fscrypt_has_encryption_key(dir))
 		goto success;
 
-	if (!fscrypt_fname_encrypted_size(dir, dentry->d_name.len, NAME_MAX,
-					  &len)) {
+	if (!name)
+		name = &dentry->d_name;
+
+	if (!fscrypt_fname_encrypted_size(dir, name->len, NAME_MAX, &len)) {
 		WARN_ON_ONCE(1);
 		return ERR_PTR(-ENAMETOOLONG);
 	}
@@ -2657,7 +2660,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
 	if (!cryptbuf)
 		return ERR_PTR(-ENOMEM);
 
-	ret = fscrypt_fname_encrypt(dir, &dentry->d_name, cryptbuf, len);
+	ret = fscrypt_fname_encrypt(dir, name, cryptbuf, len);
 	if (ret) {
 		kfree(cryptbuf);
 		return ERR_PTR(ret);
@@ -2945,12 +2948,12 @@ static struct ceph_mds_request_head_legacy *
 find_legacy_request_head(void *p, u64 features)
 {
 	bool legacy = !(features & CEPH_FEATURE_FS_BTIME);
-	struct ceph_mds_request_head_old *ohead;
+	struct ceph_mds_request_head *head;
 
 	if (legacy)
 		return (struct ceph_mds_request_head_legacy *)p;
-	ohead = (struct ceph_mds_request_head_old *)p;
-	return (struct ceph_mds_request_head_legacy *)&ohead->oldest_client_tid;
+	head = (struct ceph_mds_request_head *)p;
+	return (struct ceph_mds_request_head_legacy *)&head->oldest_client_tid;
 }
 
 /*
@@ -3020,7 +3023,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	if (legacy)
 		len = sizeof(struct ceph_mds_request_head_legacy);
 	else if (request_head_version == 1)
-		len = sizeof(struct ceph_mds_request_head_old);
+		len = offsetofend(struct ceph_mds_request_head, args);
 	else if (request_head_version == 2)
 		len = offsetofend(struct ceph_mds_request_head, ext_num_fwd);
 	else
@@ -3104,11 +3107,11 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		msg->hdr.version = cpu_to_le16(3);
 		p = msg->front.iov_base + sizeof(*lhead);
 	} else if (request_head_version == 1) {
-		struct ceph_mds_request_head_old *ohead = msg->front.iov_base;
+		struct ceph_mds_request_head *nhead = msg->front.iov_base;
 
 		msg->hdr.version = cpu_to_le16(4);
-		ohead->version = cpu_to_le16(1);
-		p = msg->front.iov_base + sizeof(*ohead);
+		nhead->version = cpu_to_le16(1);
+		p = msg->front.iov_base + offsetofend(struct ceph_mds_request_head, args);
 	} else if (request_head_version == 2) {
 		struct ceph_mds_request_head *nhead = msg->front.iov_base;
 
@@ -3265,7 +3268,7 @@ static int __prepare_send_request(struct ceph_mds_session *session,
 	 * so we limit to retry at most 256 times.
 	 */
 	if (req->r_attempts) {
-	       old_max_retry = sizeof_field(struct ceph_mds_request_head_old,
+	       old_max_retry = sizeof_field(struct ceph_mds_request_head,
 					    num_retry);
 	       old_max_retry = 1 << (old_max_retry * BITS_PER_BYTE);
 	       if ((old_version && req->r_attempts >= old_max_retry) ||
@@ -5690,18 +5693,18 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc,
 			 *
 			 * All the other cases                       --> mismatch
 			 */
+			bool path_matched = true;
 			char *first = strstr(_tpath, auth->match.path);
-			if (first != _tpath) {
-				if (free_tpath)
-					kfree(_tpath);
-				return 0;
+			if (first != _tpath ||
+			    (tlen > len && _tpath[len] != '/')) {
+				path_matched = false;
 			}
 
-			if (tlen > len && _tpath[len] != '/') {
-				if (free_tpath)
-					kfree(_tpath);
+			if (free_tpath)
+				kfree(_tpath);
+
+			if (!path_matched)
 				return 0;
-			}
 		}
 	}
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 38bb7e0d2d79..7c9fee9e80d4 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -299,6 +299,8 @@ struct ceph_mds_request {
 	struct inode *r_target_inode;       /* resulting inode */
 	struct inode *r_new_inode;	    /* new inode (for creates) */
 
+	const struct qstr *r_dname;	    /* stable name (for ->d_revalidate) */
+
 #define CEPH_MDS_R_DIRECT_IS_HASH	(1) /* r_direct_hash is valid */
 #define CEPH_MDS_R_ABORTED		(2) /* call was aborted */
 #define CEPH_MDS_R_GOT_UNSAFE		(3) /* got an unsafe reply */
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index 06ee397e0c3a..d90eda19bcc4 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -166,7 +166,7 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
 	if (IS_ERR(in)) {
 		doutc(cl, "Can't lookup inode %llx (err: %ld)\n", realm->ino,
 		      PTR_ERR(in));
-		qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
+		qri->timeout = jiffies + secs_to_jiffies(60); /* XXX */
 	} else {
 		qri->timeout = 0;
 		qri->inode = in;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 4e552ba7bd43..a3e2dfeedfbf 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -445,7 +445,8 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
 }
 
 /* called when a cache lookup succeeds */
-static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
+static int coda_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *de, unsigned int flags)
 {
 	struct inode *inode;
 	struct coda_inode_info *cii;
diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c
index 9f2d5743e2c8..0df46f09b6cc 100644
--- a/fs/coda/sysctl.c
+++ b/fs/coda/sysctl.c
@@ -14,7 +14,7 @@
 
 static struct ctl_table_header *fs_table_header;
 
-static struct ctl_table coda_table[] = {
+static const struct ctl_table coda_table[] = {
 	{
 		.procname	= "timeout",
 		.data		= &coda_timeout,
diff --git a/fs/coredump.c b/fs/coredump.c
index d48edb37bc35..591700e1b2ce 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -995,7 +995,7 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
 static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT;
 static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX;
 
-static struct ctl_table coredump_sysctls[] = {
+static const struct ctl_table coredump_sysctls[] = {
 	{
 		.procname	= "core_uses_pid",
 		.data		= &core_uses_pid,
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 0ad52fbe51c9..010f9c0a4c2f 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -574,11 +574,10 @@ EXPORT_SYMBOL_GPL(fscrypt_fname_siphash);
  * Validate dentries in encrypted directories to make sure we aren't potentially
  * caching stale dentries after a key has been added.
  */
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
+			 struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *dir;
 	int err;
-	int valid;
 
 	/*
 	 * Plaintext names are always valid, since fscrypt doesn't support
@@ -591,30 +590,21 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 	/*
 	 * No-key name; valid if the directory's key is still unavailable.
 	 *
-	 * Although fscrypt forbids rename() on no-key names, we still must use
-	 * dget_parent() here rather than use ->d_parent directly.  That's
-	 * because a corrupted fs image may contain directory hard links, which
-	 * the VFS handles by moving the directory's dentry tree in the dcache
-	 * each time ->lookup() finds the directory and it already has a dentry
-	 * elsewhere.  Thus ->d_parent can be changing, and we must safely grab
-	 * a reference to some ->d_parent to prevent it from being freed.
+	 * Note in RCU mode we have to bail if we get here -
+	 * fscrypt_get_encryption_info() may block.
 	 */
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	dir = dget_parent(dentry);
 	/*
 	 * Pass allow_unsupported=true, so that files with an unsupported
 	 * encryption policy can be deleted.
 	 */
-	err = fscrypt_get_encryption_info(d_inode(dir), true);
-	valid = !fscrypt_has_encryption_key(d_inode(dir));
-	dput(dir);
-
+	err = fscrypt_get_encryption_info(dir, true);
 	if (err < 0)
 		return err;
 
-	return valid;
+	return !fscrypt_has_encryption_key(dir);
 }
 EXPORT_SYMBOL_GPL(fscrypt_d_revalidate);
diff --git a/fs/dcache.c b/fs/dcache.c
index 1a01d7a6a7a9..e3634916ffb9 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -192,7 +192,7 @@ static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_dcache_sysctls[] = {
+static const struct ctl_table fs_dcache_sysctls[] = {
 	{
 		.procname	= "dentry-state",
 		.data		= &dentry_stat,
@@ -295,12 +295,16 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	return dentry_string_cmp(cs, ct, tcount);
 }
 
+/*
+ * long names are allocated separately from dentry and never modified.
+ * Refcounted, freeing is RCU-delayed.  See take_dentry_name_snapshot()
+ * for the reason why ->count and ->head can't be combined into a union.
+ * dentry_string_cmp() relies upon ->name[] being word-aligned.
+ */
 struct external_name {
-	union {
-		atomic_t count;
-		struct rcu_head head;
-	} u;
-	unsigned char name[];
+	atomic_t count;
+	struct rcu_head head;
+	unsigned char name[] __aligned(sizeof(unsigned long));
 };
 
 static inline struct external_name *external_name(struct dentry *dentry)
@@ -324,31 +328,45 @@ static void __d_free_external(struct rcu_head *head)
 
 static inline int dname_external(const struct dentry *dentry)
 {
-	return dentry->d_name.name != dentry->d_iname;
+	return dentry->d_name.name != dentry->d_shortname.string;
 }
 
 void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
 {
-	spin_lock(&dentry->d_lock);
-	name->name = dentry->d_name;
-	if (unlikely(dname_external(dentry))) {
-		atomic_inc(&external_name(dentry)->u.count);
+	unsigned seq;
+	const unsigned char *s;
+
+	rcu_read_lock();
+retry:
+	seq = read_seqcount_begin(&dentry->d_seq);
+	s = READ_ONCE(dentry->d_name.name);
+	name->name.hash_len = dentry->d_name.hash_len;
+	name->name.name = name->inline_name.string;
+	if (likely(s == dentry->d_shortname.string)) {
+		name->inline_name = dentry->d_shortname;
 	} else {
-		memcpy(name->inline_name, dentry->d_iname,
-		       dentry->d_name.len + 1);
-		name->name.name = name->inline_name;
+		struct external_name *p;
+		p = container_of(s, struct external_name, name[0]);
+		// get a valid reference
+		if (unlikely(!atomic_inc_not_zero(&p->count)))
+			goto retry;
+		name->name.name = s;
 	}
-	spin_unlock(&dentry->d_lock);
+	if (read_seqcount_retry(&dentry->d_seq, seq)) {
+		release_dentry_name_snapshot(name);
+		goto retry;
+	}
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL(take_dentry_name_snapshot);
 
 void release_dentry_name_snapshot(struct name_snapshot *name)
 {
-	if (unlikely(name->name.name != name->inline_name)) {
+	if (unlikely(name->name.name != name->inline_name.string)) {
 		struct external_name *p;
 		p = container_of(name->name.name, struct external_name, name[0]);
-		if (unlikely(atomic_dec_and_test(&p->u.count)))
-			kfree_rcu(p, u.head);
+		if (unlikely(atomic_dec_and_test(&p->count)))
+			kfree_rcu(p, head);
 	}
 }
 EXPORT_SYMBOL(release_dentry_name_snapshot);
@@ -386,7 +404,7 @@ static void dentry_free(struct dentry *dentry)
 	WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
 	if (unlikely(dname_external(dentry))) {
 		struct external_name *p = external_name(dentry);
-		if (likely(atomic_dec_and_test(&p->u.count))) {
+		if (likely(atomic_dec_and_test(&p->count))) {
 			call_rcu(&dentry->d_u.d_rcu, __d_free_external);
 			return;
 		}
@@ -1654,10 +1672,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 * will still always have a NUL at the end, even if we might
 	 * be overwriting an internal NUL character
 	 */
-	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
+	dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0;
 	if (unlikely(!name)) {
 		name = &slash_name;
-		dname = dentry->d_iname;
+		dname = dentry->d_shortname.string;
 	} else if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
 		struct external_name *p = kmalloc(size + name->len,
@@ -1667,10 +1685,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
-		atomic_set(&p->u.count, 1);
+		atomic_set(&p->count, 1);
 		dname = p->name;
 	} else  {
-		dname = dentry->d_iname;
+		dname = dentry->d_shortname.string;
 	}	
 
 	dentry->d_name.len = name->len;
@@ -1682,7 +1700,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	smp_store_release(&dentry->d_name.name, dname); /* ^^^ */
 
 	dentry->d_flags = 0;
-	lockref_init(&dentry->d_lockref, 1);
+	lockref_init(&dentry->d_lockref);
 	seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock);
 	dentry->d_inode = NULL;
 	dentry->d_parent = dentry;
@@ -2728,10 +2746,9 @@ static void swap_names(struct dentry *dentry, struct dentry *target)
 			 * dentry:internal, target:external.  Steal target's
 			 * storage and make target internal.
 			 */
-			memcpy(target->d_iname, dentry->d_name.name,
-					dentry->d_name.len + 1);
 			dentry->d_name.name = target->d_name.name;
-			target->d_name.name = target->d_iname;
+			target->d_shortname = dentry->d_shortname;
+			target->d_name.name = target->d_shortname.string;
 		}
 	} else {
 		if (unlikely(dname_external(dentry))) {
@@ -2739,20 +2756,16 @@ static void swap_names(struct dentry *dentry, struct dentry *target)
 			 * dentry:external, target:internal.  Give dentry's
 			 * storage to target and make dentry internal
 			 */
-			memcpy(dentry->d_iname, target->d_name.name,
-					target->d_name.len + 1);
 			target->d_name.name = dentry->d_name.name;
-			dentry->d_name.name = dentry->d_iname;
+			dentry->d_shortname = target->d_shortname;
+			dentry->d_name.name = dentry->d_shortname.string;
 		} else {
 			/*
 			 * Both are internal.
 			 */
-			unsigned int i;
-			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
-			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
-				swap(((long *) &dentry->d_iname)[i],
-				     ((long *) &target->d_iname)[i]);
-			}
+			for (int i = 0; i < DNAME_INLINE_WORDS; i++)
+				swap(dentry->d_shortname.words[i],
+				     target->d_shortname.words[i]);
 		}
 	}
 	swap(dentry->d_name.hash_len, target->d_name.hash_len);
@@ -2764,16 +2777,15 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
 	if (unlikely(dname_external(dentry)))
 		old_name = external_name(dentry);
 	if (unlikely(dname_external(target))) {
-		atomic_inc(&external_name(target)->u.count);
+		atomic_inc(&external_name(target)->count);
 		dentry->d_name = target->d_name;
 	} else {
-		memcpy(dentry->d_iname, target->d_name.name,
-				target->d_name.len + 1);
-		dentry->d_name.name = dentry->d_iname;
+		dentry->d_shortname = target->d_shortname;
+		dentry->d_name.name = dentry->d_shortname.string;
 		dentry->d_name.hash_len = target->d_name.hash_len;
 	}
-	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
-		kfree_rcu(old_name, u.head);
+	if (old_name && likely(atomic_dec_and_test(&old_name->count)))
+		kfree_rcu(old_name, head);
 }
 
 /*
@@ -2954,7 +2966,12 @@ static int __d_unalias(struct dentry *dentry, struct dentry *alias)
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_rwsem;
 out_unalias:
+	if (alias->d_op && alias->d_op->d_unalias_trylock &&
+	    !alias->d_op->d_unalias_trylock(alias))
+		goto out_err;
 	__d_move(alias, dentry, false);
+	if (alias->d_op && alias->d_op->d_unalias_unlock)
+		alias->d_op->d_unalias_unlock(alias);
 	ret = 0;
 out_err:
 	if (m2)
@@ -3102,12 +3119,12 @@ void d_mark_tmpfile(struct file *file, struct inode *inode)
 {
 	struct dentry *dentry = file->f_path.dentry;
 
-	BUG_ON(dentry->d_name.name != dentry->d_iname ||
+	BUG_ON(dname_external(dentry) ||
 		!hlist_unhashed(&dentry->d_u.d_alias) ||
 		!d_unlinked(dentry));
 	spin_lock(&dentry->d_parent->d_lock);
 	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-	dentry->d_name.len = sprintf(dentry->d_iname, "#%llu",
+	dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu",
 				(unsigned long long)inode->i_ino);
 	spin_unlock(&dentry->d_lock);
 	spin_unlock(&dentry->d_parent->d_lock);
@@ -3195,7 +3212,7 @@ static void __init dcache_init(void)
 	 */
 	dentry_cache = KMEM_CACHE_USERCOPY(dentry,
 		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT,
-		d_iname);
+		d_shortname.string);
 
 	/* Hash may have been set up in dcache_init_early */
 	if (!hashdist)
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 16e198a26339..69e9ddcb113d 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -47,11 +47,17 @@ const struct file_operations debugfs_noop_file_operations = {
 
 #define F_DENTRY(filp) ((filp)->f_path.dentry)
 
+const void *debugfs_get_aux(const struct file *file)
+{
+	return DEBUGFS_I(file_inode(file))->aux;
+}
+EXPORT_SYMBOL_GPL(debugfs_get_aux);
+
 const struct file_operations *debugfs_real_fops(const struct file *filp)
 {
 	struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata;
 
-	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) {
+	if (!fsd) {
 		/*
 		 * Urgh, we've been called w/o a protecting
 		 * debugfs_file_get().
@@ -84,9 +90,12 @@ static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode)
 		return -EINVAL;
 
 	d_fsd = READ_ONCE(dentry->d_fsdata);
-	if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) {
+	if (d_fsd) {
 		fsd = d_fsd;
 	} else {
+		struct inode *inode = dentry->d_inode;
+		unsigned int methods = 0;
+
 		if (WARN_ON(mode == DBGFS_GET_ALREADY))
 			return -EINVAL;
 
@@ -95,23 +104,41 @@ static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode)
 			return -ENOMEM;
 
 		if (mode == DBGFS_GET_SHORT) {
+			const struct debugfs_short_fops *ops;
+			ops = fsd->short_fops = DEBUGFS_I(inode)->short_fops;
+			if (ops->llseek)
+				methods |= HAS_LSEEK;
+			if (ops->read)
+				methods |= HAS_READ;
+			if (ops->write)
+				methods |= HAS_WRITE;
 			fsd->real_fops = NULL;
-			fsd->short_fops = (void *)((unsigned long)d_fsd &
-						~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
 		} else {
-			fsd->real_fops = (void *)((unsigned long)d_fsd &
-						~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
+			const struct file_operations *ops;
+			ops = fsd->real_fops = DEBUGFS_I(inode)->real_fops;
+			if (ops->llseek)
+				methods |= HAS_LSEEK;
+			if (ops->read)
+				methods |= HAS_READ;
+			if (ops->write)
+				methods |= HAS_WRITE;
+			if (ops->unlocked_ioctl)
+				methods |= HAS_IOCTL;
+			if (ops->poll)
+				methods |= HAS_POLL;
 			fsd->short_fops = NULL;
 		}
+		fsd->methods = methods;
 		refcount_set(&fsd->active_users, 1);
 		init_completion(&fsd->active_users_drained);
 		INIT_LIST_HEAD(&fsd->cancellations);
 		mutex_init(&fsd->cancellations_mtx);
 
-		if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) {
+		d_fsd = cmpxchg(&dentry->d_fsdata, NULL, fsd);
+		if (d_fsd) {
 			mutex_destroy(&fsd->cancellations_mtx);
 			kfree(fsd);
-			fsd = READ_ONCE(dentry->d_fsdata);
+			fsd = d_fsd;
 		}
 	}
 
@@ -208,8 +235,7 @@ void debugfs_enter_cancellation(struct file *file,
 		return;
 
 	fsd = READ_ONCE(dentry->d_fsdata);
-	if (WARN_ON(!fsd ||
-		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+	if (WARN_ON(!fsd))
 		return;
 
 	mutex_lock(&fsd->cancellations_mtx);
@@ -240,8 +266,7 @@ void debugfs_leave_cancellation(struct file *file,
 		return;
 
 	fsd = READ_ONCE(dentry->d_fsdata);
-	if (WARN_ON(!fsd ||
-		    ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)))
+	if (WARN_ON(!fsd))
 		return;
 
 	mutex_lock(&fsd->cancellations_mtx);
@@ -322,13 +347,16 @@ const struct file_operations debugfs_open_proxy_file_operations = {
 #define PROTO(args...) args
 #define ARGS(args...) args
 
-#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args)		\
+#define FULL_PROXY_FUNC(name, ret_type, filp, proto, args, bit, ret)	\
 static ret_type full_proxy_ ## name(proto)				\
 {									\
-	struct dentry *dentry = F_DENTRY(filp);			\
+	struct dentry *dentry = F_DENTRY(filp);				\
+	struct debugfs_fsdata *fsd = dentry->d_fsdata;			\
 	const struct file_operations *real_fops;			\
 	ret_type r;							\
 									\
+	if (!(fsd->methods & bit))					\
+		return ret;						\
 	r = debugfs_file_get(dentry);					\
 	if (unlikely(r))						\
 		return r;						\
@@ -338,17 +366,18 @@ static ret_type full_proxy_ ## name(proto)				\
 	return r;							\
 }
 
-#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args)		\
+#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args, bit, ret)	\
 static ret_type full_proxy_ ## name(proto)				\
 {									\
 	struct dentry *dentry = F_DENTRY(filp);				\
-	struct debugfs_fsdata *fsd;					\
+	struct debugfs_fsdata *fsd = dentry->d_fsdata;			\
 	ret_type r;							\
 									\
+	if (!(fsd->methods & bit))					\
+		return ret;						\
 	r = debugfs_file_get(dentry);					\
 	if (unlikely(r))						\
 		return r;						\
-	fsd = dentry->d_fsdata;						\
 	if (fsd->real_fops)						\
 		r = fsd->real_fops->name(args);				\
 	else								\
@@ -359,29 +388,32 @@ static ret_type full_proxy_ ## name(proto)				\
 
 FULL_PROXY_FUNC_BOTH(llseek, loff_t, filp,
 		     PROTO(struct file *filp, loff_t offset, int whence),
-		     ARGS(filp, offset, whence));
+		     ARGS(filp, offset, whence), HAS_LSEEK, -ESPIPE);
 
 FULL_PROXY_FUNC_BOTH(read, ssize_t, filp,
 		     PROTO(struct file *filp, char __user *buf, size_t size,
 			   loff_t *ppos),
-		     ARGS(filp, buf, size, ppos));
+		     ARGS(filp, buf, size, ppos), HAS_READ, -EINVAL);
 
 FULL_PROXY_FUNC_BOTH(write, ssize_t, filp,
 		     PROTO(struct file *filp, const char __user *buf,
 			   size_t size, loff_t *ppos),
-		     ARGS(filp, buf, size, ppos));
+		     ARGS(filp, buf, size, ppos), HAS_WRITE, -EINVAL);
 
 FULL_PROXY_FUNC(unlocked_ioctl, long, filp,
 		PROTO(struct file *filp, unsigned int cmd, unsigned long arg),
-		ARGS(filp, cmd, arg));
+		ARGS(filp, cmd, arg), HAS_IOCTL, -ENOTTY);
 
 static __poll_t full_proxy_poll(struct file *filp,
 				struct poll_table_struct *wait)
 {
 	struct dentry *dentry = F_DENTRY(filp);
+	struct debugfs_fsdata *fsd = dentry->d_fsdata;
 	__poll_t r = 0;
 	const struct file_operations *real_fops;
 
+	if (!(fsd->methods & HAS_POLL))
+		return DEFAULT_POLLMASK;
 	if (debugfs_file_get(dentry))
 		return EPOLLHUP;
 
@@ -393,9 +425,7 @@ static __poll_t full_proxy_poll(struct file *filp,
 
 static int full_proxy_release(struct inode *inode, struct file *filp)
 {
-	const struct dentry *dentry = F_DENTRY(filp);
 	const struct file_operations *real_fops = debugfs_real_fops(filp);
-	const struct file_operations *proxy_fops = filp->f_op;
 	int r = 0;
 
 	/*
@@ -404,49 +434,21 @@ static int full_proxy_release(struct inode *inode, struct file *filp)
 	 * not to leak any resources. Releasers must not assume that
 	 * ->i_private is still being meaningful here.
 	 */
-	if (real_fops && real_fops->release)
+	if (real_fops->release)
 		r = real_fops->release(inode, filp);
 
-	replace_fops(filp, d_inode(dentry)->i_fop);
-	kfree(proxy_fops);
 	fops_put(real_fops);
 	return r;
 }
 
-static void __full_proxy_fops_init(struct file_operations *proxy_fops,
-				   struct debugfs_fsdata *fsd)
-{
-	proxy_fops->release = full_proxy_release;
-
-	if ((fsd->real_fops && fsd->real_fops->llseek) ||
-	    (fsd->short_fops && fsd->short_fops->llseek))
-		proxy_fops->llseek = full_proxy_llseek;
-
-	if ((fsd->real_fops && fsd->real_fops->read) ||
-	    (fsd->short_fops && fsd->short_fops->read))
-		proxy_fops->read = full_proxy_read;
-
-	if ((fsd->real_fops && fsd->real_fops->write) ||
-	    (fsd->short_fops && fsd->short_fops->write))
-		proxy_fops->write = full_proxy_write;
-
-	if (fsd->real_fops && fsd->real_fops->poll)
-		proxy_fops->poll = full_proxy_poll;
-
-	if (fsd->real_fops && fsd->real_fops->unlocked_ioctl)
-		proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl;
-}
-
-static int full_proxy_open(struct inode *inode, struct file *filp,
-			   enum dbgfs_get_mode mode)
+static int full_proxy_open_regular(struct inode *inode, struct file *filp)
 {
 	struct dentry *dentry = F_DENTRY(filp);
 	const struct file_operations *real_fops;
-	struct file_operations *proxy_fops = NULL;
 	struct debugfs_fsdata *fsd;
 	int r;
 
-	r = __debugfs_file_get(dentry, mode);
+	r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR);
 	if (r)
 		return r == -EIO ? -ENOENT : r;
 
@@ -456,7 +458,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp,
 	if (r)
 		goto out;
 
-	if (real_fops && !fops_get(real_fops)) {
+	if (!fops_get(real_fops)) {
 #ifdef CONFIG_MODULES
 		if (real_fops->owner &&
 		    real_fops->owner->state == MODULE_STATE_GOING) {
@@ -472,55 +474,52 @@ static int full_proxy_open(struct inode *inode, struct file *filp,
 		goto out;
 	}
 
-	proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL);
-	if (!proxy_fops) {
-		r = -ENOMEM;
-		goto free_proxy;
-	}
-	__full_proxy_fops_init(proxy_fops, fsd);
-	replace_fops(filp, proxy_fops);
-
-	if (!real_fops || real_fops->open) {
-		if (real_fops)
-			r = real_fops->open(inode, filp);
-		else
-			r = simple_open(inode, filp);
+	if (real_fops->open) {
+		r = real_fops->open(inode, filp);
 		if (r) {
-			replace_fops(filp, d_inode(dentry)->i_fop);
-			goto free_proxy;
-		} else if (filp->f_op != proxy_fops) {
+			fops_put(real_fops);
+		} else if (filp->f_op != &debugfs_full_proxy_file_operations) {
 			/* No protection against file removal anymore. */
 			WARN(1, "debugfs file owner replaced proxy fops: %pd",
 				dentry);
-			goto free_proxy;
+			fops_put(real_fops);
 		}
 	}
-
-	goto out;
-free_proxy:
-	kfree(proxy_fops);
-	fops_put(real_fops);
 out:
 	debugfs_file_put(dentry);
 	return r;
 }
 
-static int full_proxy_open_regular(struct inode *inode, struct file *filp)
-{
-	return full_proxy_open(inode, filp, DBGFS_GET_REGULAR);
-}
-
 const struct file_operations debugfs_full_proxy_file_operations = {
 	.open = full_proxy_open_regular,
+	.release = full_proxy_release,
+	.llseek = full_proxy_llseek,
+	.read = full_proxy_read,
+	.write = full_proxy_write,
+	.poll = full_proxy_poll,
+	.unlocked_ioctl = full_proxy_unlocked_ioctl
 };
 
 static int full_proxy_open_short(struct inode *inode, struct file *filp)
 {
-	return full_proxy_open(inode, filp, DBGFS_GET_SHORT);
+	struct dentry *dentry = F_DENTRY(filp);
+	int r;
+
+	r = __debugfs_file_get(dentry, DBGFS_GET_SHORT);
+	if (r)
+		return r == -EIO ? -ENOENT : r;
+	r = debugfs_locked_down(inode, filp, NULL);
+	if (!r)
+		r = simple_open(inode, filp);
+	debugfs_file_put(dentry);
+	return r;
 }
 
 const struct file_operations debugfs_full_short_proxy_file_operations = {
 	.open = full_proxy_open_short,
+	.llseek = full_proxy_llseek,
+	.read = full_proxy_read,
+	.write = full_proxy_write,
 };
 
 ssize_t debugfs_attr_read(struct file *file, char __user *buf,
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index e752009de929..75715d8877ee 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -208,16 +208,34 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static struct kmem_cache *debugfs_inode_cachep __ro_after_init;
+
+static void init_once(void *foo)
+{
+	struct debugfs_inode_info *info = foo;
+	inode_init_once(&info->vfs_inode);
+}
+
+static struct inode *debugfs_alloc_inode(struct super_block *sb)
+{
+	struct debugfs_inode_info *info;
+	info = alloc_inode_sb(sb, debugfs_inode_cachep, GFP_KERNEL);
+	if (!info)
+		return NULL;
+	return &info->vfs_inode;
+}
+
 static void debugfs_free_inode(struct inode *inode)
 {
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
-	free_inode_nonrcu(inode);
+	kmem_cache_free(debugfs_inode_cachep, DEBUGFS_I(inode));
 }
 
 static const struct super_operations debugfs_super_operations = {
 	.statfs		= simple_statfs,
 	.show_options	= debugfs_show_options,
+	.alloc_inode	= debugfs_alloc_inode,
 	.free_inode	= debugfs_free_inode,
 };
 
@@ -225,23 +243,18 @@ static void debugfs_release_dentry(struct dentry *dentry)
 {
 	struct debugfs_fsdata *fsd = dentry->d_fsdata;
 
-	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
-		return;
-
-	/* check it wasn't a dir (no fsdata) or automount (no real_fops) */
-	if (fsd && (fsd->real_fops || fsd->short_fops)) {
+	if (fsd) {
 		WARN_ON(!list_empty(&fsd->cancellations));
 		mutex_destroy(&fsd->cancellations_mtx);
 	}
-
 	kfree(fsd);
 }
 
 static struct vfsmount *debugfs_automount(struct path *path)
 {
-	struct debugfs_fsdata *fsd = path->dentry->d_fsdata;
+	struct inode *inode = path->dentry->d_inode;
 
-	return fsd->automount(path->dentry, d_inode(path->dentry)->i_private);
+	return DEBUGFS_I(inode)->automount(path->dentry, inode->i_private);
 }
 
 static const struct dentry_operations debugfs_dops = {
@@ -411,6 +424,7 @@ static struct dentry *end_creating(struct dentry *dentry)
 
 static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 				struct dentry *parent, void *data,
+				const void *aux,
 				const struct file_operations *proxy_fops,
 				const void *real_fops)
 {
@@ -441,9 +455,11 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 	inode->i_private = data;
 
 	inode->i_op = &debugfs_file_inode_operations;
+	if (!real_fops)
+		proxy_fops = &debugfs_noop_file_operations;
 	inode->i_fop = proxy_fops;
-	dentry->d_fsdata = (void *)((unsigned long)real_fops |
-				DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
+	DEBUGFS_I(inode)->raw = real_fops;
+	DEBUGFS_I(inode)->aux = aux;
 
 	d_instantiate(dentry, inode);
 	fsnotify_create(d_inode(dentry->d_parent), dentry);
@@ -452,30 +468,22 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 
 struct dentry *debugfs_create_file_full(const char *name, umode_t mode,
 					struct dentry *parent, void *data,
+					const void *aux,
 					const struct file_operations *fops)
 {
-	if (WARN_ON((unsigned long)fops &
-		    DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))
-		return ERR_PTR(-EINVAL);
-
-	return __debugfs_create_file(name, mode, parent, data,
-				fops ? &debugfs_full_proxy_file_operations :
-					&debugfs_noop_file_operations,
+	return __debugfs_create_file(name, mode, parent, data, aux,
+				&debugfs_full_proxy_file_operations,
 				fops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file_full);
 
 struct dentry *debugfs_create_file_short(const char *name, umode_t mode,
-					 struct dentry *parent, void *data,
-					 const struct debugfs_short_fops *fops)
+					struct dentry *parent, void *data,
+					const void *aux,
+					const struct debugfs_short_fops *fops)
 {
-	if (WARN_ON((unsigned long)fops &
-		    DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))
-		return ERR_PTR(-EINVAL);
-
-	return __debugfs_create_file(name, mode, parent, data,
-				fops ? &debugfs_full_short_proxy_file_operations :
-					&debugfs_noop_file_operations,
+	return __debugfs_create_file(name, mode, parent, data, aux,
+				&debugfs_full_short_proxy_file_operations,
 				fops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file_short);
@@ -512,9 +520,8 @@ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
 				   const struct file_operations *fops)
 {
 
-	return __debugfs_create_file(name, mode, parent, data,
-				fops ? &debugfs_open_proxy_file_operations :
-					&debugfs_noop_file_operations,
+	return __debugfs_create_file(name, mode, parent, data, NULL,
+				&debugfs_open_proxy_file_operations,
 				fops);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
@@ -624,23 +631,13 @@ struct dentry *debugfs_create_automount(const char *name,
 					void *data)
 {
 	struct dentry *dentry = start_creating(name, parent);
-	struct debugfs_fsdata *fsd;
 	struct inode *inode;
 
 	if (IS_ERR(dentry))
 		return dentry;
 
-	fsd = kzalloc(sizeof(*fsd), GFP_KERNEL);
-	if (!fsd) {
-		failed_creating(dentry);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	fsd->automount = f;
-
 	if (!(debugfs_allow & DEBUGFS_ALLOW_API)) {
 		failed_creating(dentry);
-		kfree(fsd);
 		return ERR_PTR(-EPERM);
 	}
 
@@ -648,14 +645,13 @@ struct dentry *debugfs_create_automount(const char *name,
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create automount '%s'\n",
 		       name);
-		kfree(fsd);
 		return failed_creating(dentry);
 	}
 
 	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
-	dentry->d_fsdata = fsd;
+	DEBUGFS_I(inode)->automount = f;
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
 	d_instantiate(dentry, inode);
@@ -730,7 +726,7 @@ static void __debugfs_file_removed(struct dentry *dentry)
 	 */
 	smp_mb();
 	fsd = READ_ONCE(dentry->d_fsdata);
-	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
+	if (!fsd)
 		return;
 
 	/* if this was the last reference, we're done */
@@ -834,76 +830,70 @@ void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
 EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
 
 /**
- * debugfs_rename - rename a file/directory in the debugfs filesystem
- * @old_dir: a pointer to the parent dentry for the renamed object. This
- *          should be a directory dentry.
- * @old_dentry: dentry of an object to be renamed.
- * @new_dir: a pointer to the parent dentry where the object should be
- *          moved. This should be a directory dentry.
- * @new_name: a pointer to a string containing the target name.
+ * debugfs_change_name - rename a file/directory in the debugfs filesystem
+ * @dentry: dentry of an object to be renamed.
+ * @fmt: format for new name
  *
  * This function renames a file/directory in debugfs.  The target must not
  * exist for rename to succeed.
  *
- * This function will return a pointer to old_dentry (which is updated to
- * reflect renaming) if it succeeds. If an error occurs, ERR_PTR(-ERROR)
- * will be returned.
+ * This function will return 0 on success and -E... on failure.
  *
  * If debugfs is not enabled in the kernel, the value -%ENODEV will be
  * returned.
  */
-struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
-		struct dentry *new_dir, const char *new_name)
+int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, ...)
 {
-	int error;
-	struct dentry *dentry = NULL, *trap;
+	int error = 0;
+	const char *new_name;
 	struct name_snapshot old_name;
+	struct dentry *parent, *target;
+	struct inode *dir;
+	va_list ap;
 
-	if (IS_ERR(old_dir))
-		return old_dir;
-	if (IS_ERR(new_dir))
-		return new_dir;
-	if (IS_ERR_OR_NULL(old_dentry))
-		return old_dentry;
-
-	trap = lock_rename(new_dir, old_dir);
-	/* Source or destination directories don't exist? */
-	if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir))
-		goto exit;
-	/* Source does not exist, cyclic rename, or mountpoint? */
-	if (d_really_is_negative(old_dentry) || old_dentry == trap ||
-	    d_mountpoint(old_dentry))
-		goto exit;
-	dentry = lookup_one_len(new_name, new_dir, strlen(new_name));
-	/* Lookup failed, cyclic rename or target exists? */
-	if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
-		goto exit;
-
-	take_dentry_name_snapshot(&old_name, old_dentry);
-
-	error = simple_rename(&nop_mnt_idmap, d_inode(old_dir), old_dentry,
-			      d_inode(new_dir), dentry, 0);
-	if (error) {
-		release_dentry_name_snapshot(&old_name);
-		goto exit;
+	if (IS_ERR_OR_NULL(dentry))
+		return 0;
+
+	va_start(ap, fmt);
+	new_name = kvasprintf_const(GFP_KERNEL, fmt, ap);
+	va_end(ap);
+	if (!new_name)
+		return -ENOMEM;
+
+	parent = dget_parent(dentry);
+	dir = d_inode(parent);
+	inode_lock(dir);
+
+	take_dentry_name_snapshot(&old_name, dentry);
+
+	if (WARN_ON_ONCE(dentry->d_parent != parent)) {
+		error = -EINVAL;
+		goto out;
 	}
-	d_move(old_dentry, dentry);
-	fsnotify_move(d_inode(old_dir), d_inode(new_dir), &old_name.name,
-		d_is_dir(old_dentry),
-		NULL, old_dentry);
+	if (strcmp(old_name.name.name, new_name) == 0)
+		goto out;
+	target = lookup_one_len(new_name, parent, strlen(new_name));
+	if (IS_ERR(target)) {
+		error = PTR_ERR(target);
+		goto out;
+	}
+	if (d_really_is_positive(target)) {
+		dput(target);
+		error = -EINVAL;
+		goto out;
+	}
+	simple_rename_timestamp(dir, dentry, dir, target);
+	d_move(dentry, target);
+	dput(target);
+	fsnotify_move(dir, dir, &old_name.name, d_is_dir(dentry), NULL, dentry);
+out:
 	release_dentry_name_snapshot(&old_name);
-	unlock_rename(new_dir, old_dir);
-	dput(dentry);
-	return old_dentry;
-exit:
-	if (dentry && !IS_ERR(dentry))
-		dput(dentry);
-	unlock_rename(new_dir, old_dir);
-	if (IS_ERR(dentry))
-		return dentry;
-	return ERR_PTR(-EINVAL);
+	inode_unlock(dir);
+	dput(parent);
+	kfree_const(new_name);
+	return error;
 }
-EXPORT_SYMBOL_GPL(debugfs_rename);
+EXPORT_SYMBOL_GPL(debugfs_change_name);
 
 /**
  * debugfs_initialized - Tells whether debugfs has been registered
@@ -939,12 +929,22 @@ static int __init debugfs_init(void)
 	if (retval)
 		return retval;
 
-	retval = register_filesystem(&debug_fs_type);
-	if (retval)
+	debugfs_inode_cachep = kmem_cache_create("debugfs_inode_cache",
+				sizeof(struct debugfs_inode_info), 0,
+				SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT,
+				init_once);
+	if (debugfs_inode_cachep == NULL) {
 		sysfs_remove_mount_point(kernel_kobj, "debug");
-	else
-		debugfs_registered = true;
+		return -ENOMEM;
+	}
 
-	return retval;
+	retval = register_filesystem(&debug_fs_type);
+	if (retval) { // Really not going to happen
+		sysfs_remove_mount_point(kernel_kobj, "debug");
+		kmem_cache_destroy(debugfs_inode_cachep);
+		return retval;
+	}
+	debugfs_registered = true;
+	return 0;
 }
 core_initcall(debugfs_init);
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
index bbae4a228ef4..93483fe84425 100644
--- a/fs/debugfs/internal.h
+++ b/fs/debugfs/internal.h
@@ -11,6 +11,22 @@
 
 struct file_operations;
 
+struct debugfs_inode_info {
+	struct inode vfs_inode;
+	union {
+		const void *raw;
+		const struct file_operations *real_fops;
+		const struct debugfs_short_fops *short_fops;
+		debugfs_automount_t automount;
+	};
+	const void *aux;
+};
+
+static inline struct debugfs_inode_info *DEBUGFS_I(struct inode *inode)
+{
+	return container_of(inode, struct debugfs_inode_info, vfs_inode);
+}
+
 /* declared over in file.c */
 extern const struct file_operations debugfs_noop_file_operations;
 extern const struct file_operations debugfs_open_proxy_file_operations;
@@ -20,29 +36,25 @@ extern const struct file_operations debugfs_full_short_proxy_file_operations;
 struct debugfs_fsdata {
 	const struct file_operations *real_fops;
 	const struct debugfs_short_fops *short_fops;
-	union {
-		/* automount_fn is used when real_fops is NULL */
-		debugfs_automount_t automount;
-		struct {
-			refcount_t active_users;
-			struct completion active_users_drained;
-
-			/* protect cancellations */
-			struct mutex cancellations_mtx;
-			struct list_head cancellations;
-		};
+	struct {
+		refcount_t active_users;
+		struct completion active_users_drained;
+
+		/* protect cancellations */
+		struct mutex cancellations_mtx;
+		struct list_head cancellations;
+		unsigned int methods;
 	};
 };
 
-/*
- * A dentry's ->d_fsdata either points to the real fops or to a
- * dynamically allocated debugfs_fsdata instance.
- * In order to distinguish between these two cases, a real fops
- * pointer gets its lowest bit set.
- */
-#define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0)
+enum {
+	HAS_READ = 1,
+	HAS_WRITE = 2,
+	HAS_LSEEK = 4,
+	HAS_POLL = 8,
+	HAS_IOCTL = 16
+};
 
-/* Access BITS */
 #define DEBUGFS_ALLOW_API	BIT(0)
 #define DEBUGFS_ALLOW_MOUNT	BIT(1)
 
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index b20e565b9c5e..1096ff8562fa 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -45,7 +45,7 @@ static int pty_limit_min;
 static int pty_limit_max = INT_MAX;
 static atomic_t pty_count = ATOMIC_INIT(0);
 
-static struct ctl_table pty_table[] = {
+static const struct ctl_table pty_table[] = {
 	{
 		.procname	= "max",
 		.maxlen		= sizeof(int),
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index acaa0825e9bb..1dfd5b81d831 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -17,7 +17,9 @@
 
 /**
  * ecryptfs_d_revalidate - revalidate an ecryptfs dentry
- * @dentry: The ecryptfs dentry
+ * @dir: inode of expected parent
+ * @name: expected name
+ * @dentry: dentry to revalidate
  * @flags: lookup flags
  *
  * Called when the VFS needs to revalidate a dentry. This
@@ -28,7 +30,8 @@
  * Returns 1 if valid, 0 otherwise.
  *
  */
-static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int ecryptfs_d_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	int rc = 1;
@@ -36,8 +39,15 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE)
-		rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
+	if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) {
+		struct inode *lower_dir = ecryptfs_inode_to_lower(dir);
+		struct name_snapshot n;
+
+		take_dentry_name_snapshot(&n, lower_dentry);
+		rc = lower_dentry->d_op->d_revalidate(lower_dir, &n.name,
+						      lower_dentry, flags);
+		release_dentry_name_snapshot(&n);
+	}
 
 	if (d_really_is_positive(dentry)) {
 		struct inode *inode = d_inode(dentry);
diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 7bfe251680ec..65ff39401020 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -29,29 +29,8 @@ struct z_erofs_decompressor {
 	char *name;
 };
 
-/* some special page->private (unsigned long, see below) */
 #define Z_EROFS_SHORTLIVED_PAGE		(-1UL << 2)
-#define Z_EROFS_PREALLOCATED_PAGE	(-2UL << 2)
-
-/*
- * For all pages in a pcluster, page->private should be one of
- * Type                         Last 2bits      page->private
- * short-lived page             00              Z_EROFS_SHORTLIVED_PAGE
- * preallocated page (tryalloc) 00              Z_EROFS_PREALLOCATED_PAGE
- * cached/managed page          00              pointer to z_erofs_pcluster
- * online page (file-backed,    01/10/11        sub-index << 2 | count
- *              some pages can be used for inplace I/O)
- *
- * page->mapping should be one of
- * Type                 page->mapping
- * short-lived page     NULL
- * preallocated page    NULL
- * cached/managed page  non-NULL or NULL (invalidated/truncated page)
- * online page          non-NULL
- *
- * For all managed pages, PG_private should be set with 1 extra refcount,
- * which is used for page reclaim / migration.
- */
+#define Z_EROFS_PREALLOCATED_FOLIO	((void *)(-2UL << 2))
 
 /*
  * Currently, short-lived pages are pages directly from buddy system
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index eb318c7ddd80..2b123b070a42 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -7,14 +7,7 @@
 #include "compress.h"
 #include <linux/lz4.h>
 
-#ifndef LZ4_DISTANCE_MAX	/* history window size */
-#define LZ4_DISTANCE_MAX 65535	/* set to maximum value by default */
-#endif
-
 #define LZ4_MAX_DISTANCE_PAGES	(DIV_ROUND_UP(LZ4_DISTANCE_MAX, PAGE_SIZE) + 1)
-#ifndef LZ4_DECOMPRESS_INPLACE_MARGIN
-#define LZ4_DECOMPRESS_INPLACE_MARGIN(srcsize)  (((srcsize) >> 8) + 32)
-#endif
 
 struct z_erofs_lz4_decompress_ctx {
 	struct z_erofs_decompress_req *rq;
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index c8f2ae845bd2..199395ed1c1f 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -9,6 +9,7 @@
 #ifndef __EROFS_FS_H
 #define __EROFS_FS_H
 
+/* to allow for x86 boot sectors and other oddities. */
 #define EROFS_SUPER_OFFSET      1024
 
 #define EROFS_FEATURE_COMPAT_SB_CHKSUM          0x00000001
@@ -54,7 +55,7 @@ struct erofs_deviceslot {
 /* erofs on-disk super block (currently 128 bytes) */
 struct erofs_super_block {
 	__le32 magic;           /* file system magic number */
-	__le32 checksum;        /* crc32c(super_block) */
+	__le32 checksum;        /* crc32c to avoid unexpected on-disk overlap */
 	__le32 feature_compat;
 	__u8 blkszbits;         /* filesystem block size in bit shift */
 	__u8 sb_extslots;	/* superblock size = 128 + sb_extslots * 16 */
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 33f8539dda4a..0ffd1c63beeb 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -6,7 +6,7 @@
 #include <trace/events/erofs.h>
 
 struct erofs_fileio_rq {
-	struct bio_vec bvecs[BIO_MAX_VECS];
+	struct bio_vec bvecs[16];
 	struct bio bio;
 	struct kiocb iocb;
 	struct super_block *sb;
@@ -68,7 +68,7 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev)
 	struct erofs_fileio_rq *rq = kzalloc(sizeof(*rq),
 					     GFP_KERNEL | __GFP_NOFAIL);
 
-	bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ);
+	bio_init(&rq->bio, NULL, rq->bvecs, ARRAY_SIZE(rq->bvecs), REQ_OP_READ);
 	rq->iocb.ki_filp = mdev->m_dif->file;
 	rq->sb = mdev->m_sb;
 	return rq;
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index f5956474bfde..827b62665649 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -39,29 +39,21 @@ void _erofs_printk(struct super_block *sb, const char *fmt, ...)
 
 static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata)
 {
-	size_t len = 1 << EROFS_SB(sb)->blkszbits;
-	struct erofs_super_block *dsb;
-	u32 expected_crc, crc;
+	struct erofs_super_block *dsb = sbdata + EROFS_SUPER_OFFSET;
+	u32 len = 1 << EROFS_SB(sb)->blkszbits, crc;
 
 	if (len > EROFS_SUPER_OFFSET)
 		len -= EROFS_SUPER_OFFSET;
+	len -= offsetof(struct erofs_super_block, checksum) +
+			sizeof(dsb->checksum);
 
-	dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET, len, GFP_KERNEL);
-	if (!dsb)
-		return -ENOMEM;
-
-	expected_crc = le32_to_cpu(dsb->checksum);
-	dsb->checksum = 0;
-	/* to allow for x86 boot sectors and other oddities. */
-	crc = crc32c(~0, dsb, len);
-	kfree(dsb);
-
-	if (crc != expected_crc) {
-		erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
-			  crc, expected_crc);
-		return -EBADMSG;
-	}
-	return 0;
+	/* skip .magic(pre-verified) and .checksum(0) fields */
+	crc = crc32c(0x5045B54A, (&dsb->checksum) + 1, len);
+	if (crc == le32_to_cpu(dsb->checksum))
+		return 0;
+	erofs_err(sb, "invalid checksum 0x%08x, 0x%08x expected",
+		  crc, le32_to_cpu(dsb->checksum));
+	return -EBADMSG;
 }
 
 static void erofs_inode_init_once(void *ptr)
@@ -516,8 +508,6 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 		errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
 #endif
 		break;
-	default:
-		return -ENOPARAM;
 	}
 	return 0;
 }
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index a90d7d649739..df2777e05661 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -407,7 +407,7 @@ int erofs_getxattr(struct inode *inode, int index, const char *name,
 	}
 
 	it.index = index;
-	it.name = (struct qstr)QSTR_INIT(name, strlen(name));
+	it.name = QSTR(name);
 	if (it.name.len > EROFS_NAME_LEN)
 		return -ERANGE;
 
@@ -478,7 +478,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb)
 	if (!sbi->xattr_prefix_count)
 		return 0;
 
-	pfs = kzalloc(sbi->xattr_prefix_count * sizeof(*pfs), GFP_KERNEL);
+	pfs = kcalloc(sbi->xattr_prefix_count, sizeof(*pfs), GFP_KERNEL);
 	if (!pfs)
 		return -ENOMEM;
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 33a128252687..d771e06db738 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -12,12 +12,6 @@
 #define Z_EROFS_PCLUSTER_MAX_PAGES	(Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE)
 #define Z_EROFS_INLINE_BVECS		2
 
-/*
- * let's leave a type here in case of introducing
- * another tagged pointer later.
- */
-typedef void *z_erofs_next_pcluster_t;
-
 struct z_erofs_bvec {
 	struct page *page;
 	int offset;
@@ -48,7 +42,7 @@ struct z_erofs_pcluster {
 	struct lockref lockref;
 
 	/* A: point to next chained pcluster or TAILs */
-	z_erofs_next_pcluster_t next;
+	struct z_erofs_pcluster *next;
 
 	/* I: start block address of this pcluster */
 	erofs_off_t index;
@@ -94,12 +88,11 @@ struct z_erofs_pcluster {
 
 /* the end of a chain of pclusters */
 #define Z_EROFS_PCLUSTER_TAIL           ((void *) 0x700 + POISON_POINTER_DELTA)
-#define Z_EROFS_PCLUSTER_NIL            (NULL)
 
 struct z_erofs_decompressqueue {
 	struct super_block *sb;
+	struct z_erofs_pcluster *head;
 	atomic_t pending_bios;
-	z_erofs_next_pcluster_t head;
 
 	union {
 		struct completion done;
@@ -462,39 +455,32 @@ err_decompressor:
 }
 
 enum z_erofs_pclustermode {
+	/* It has previously been linked into another processing chain */
 	Z_EROFS_PCLUSTER_INFLIGHT,
 	/*
-	 * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it
-	 * could be dispatched into bypass queue later due to uptodated managed
-	 * pages. All related online pages cannot be reused for inplace I/O (or
-	 * bvpage) since it can be directly decoded without I/O submission.
+	 * A weaker form of Z_EROFS_PCLUSTER_FOLLOWED; the difference is that it
+	 * may be dispatched to the bypass queue later due to uptodated managed
+	 * folios.  All file-backed folios related to this pcluster cannot be
+	 * reused for in-place I/O (or bvpage) since the pcluster may be decoded
+	 * in a separate queue (and thus out of order).
 	 */
 	Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE,
 	/*
-	 * The pcluster was just linked to a decompression chain by us.  It can
-	 * also be linked with the remaining pclusters, which means if the
-	 * processing page is the tail page of a pcluster, this pcluster can
-	 * safely use the whole page (since the previous pcluster is within the
-	 * same chain) for in-place I/O, as illustrated below:
-	 *  ___________________________________________________
-	 * |  tail (partial) page  |    head (partial) page    |
-	 * |  (of the current pcl) |   (of the previous pcl)   |
-	 * |___PCLUSTER_FOLLOWED___|_____PCLUSTER_FOLLOWED_____|
-	 *
-	 * [  (*) the page above can be used as inplace I/O.   ]
+	 * The pcluster has just been linked to our processing chain.
+	 * File-backed folios (except for the head page) related to it can be
+	 * used for in-place I/O (or bvpage).
 	 */
 	Z_EROFS_PCLUSTER_FOLLOWED,
 };
 
-struct z_erofs_decompress_frontend {
+struct z_erofs_frontend {
 	struct inode *const inode;
 	struct erofs_map_blocks map;
 	struct z_erofs_bvec_iter biter;
 
 	struct page *pagepool;
 	struct page *candidate_bvpage;
-	struct z_erofs_pcluster *pcl;
-	z_erofs_next_pcluster_t owned_head;
+	struct z_erofs_pcluster *pcl, *head;
 	enum z_erofs_pclustermode mode;
 
 	erofs_off_t headoffset;
@@ -503,11 +489,11 @@ struct z_erofs_decompress_frontend {
 	unsigned int icur;
 };
 
-#define DECOMPRESS_FRONTEND_INIT(__i) { \
-	.inode = __i, .owned_head = Z_EROFS_PCLUSTER_TAIL, \
-	.mode = Z_EROFS_PCLUSTER_FOLLOWED }
+#define Z_EROFS_DEFINE_FRONTEND(fe, i, ho) struct z_erofs_frontend fe = { \
+	.inode = i, .head = Z_EROFS_PCLUSTER_TAIL, \
+	.mode = Z_EROFS_PCLUSTER_FOLLOWED, .headoffset = ho }
 
-static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe)
+static bool z_erofs_should_alloc_cache(struct z_erofs_frontend *fe)
 {
 	unsigned int cachestrategy = EROFS_I_SB(fe->inode)->opt.cache_strategy;
 
@@ -524,19 +510,17 @@ static bool z_erofs_should_alloc_cache(struct z_erofs_decompress_frontend *fe)
 	return false;
 }
 
-static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
+static void z_erofs_bind_cache(struct z_erofs_frontend *fe)
 {
 	struct address_space *mc = MNGD_MAPPING(EROFS_I_SB(fe->inode));
 	struct z_erofs_pcluster *pcl = fe->pcl;
 	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
 	bool shouldalloc = z_erofs_should_alloc_cache(fe);
-	bool standalone = true;
-	/*
-	 * optimistic allocation without direct reclaim since inplace I/O
-	 * can be used if low memory otherwise.
-	 */
+	bool may_bypass = true;
+	/* Optimistic allocation, as in-place I/O can be used as a fallback */
 	gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) |
 			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
+	struct folio *folio, *newfolio;
 	unsigned int i;
 
 	if (i_blocksize(fe->inode) != PAGE_SIZE ||
@@ -544,47 +528,42 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
 		return;
 
 	for (i = 0; i < pclusterpages; ++i) {
-		struct page *page, *newpage;
-
 		/* Inaccurate check w/o locking to avoid unneeded lookups */
 		if (READ_ONCE(pcl->compressed_bvecs[i].page))
 			continue;
 
-		page = find_get_page(mc, pcl->index + i);
-		if (!page) {
-			/* I/O is needed, no possible to decompress directly */
-			standalone = false;
+		folio = filemap_get_folio(mc, pcl->index + i);
+		if (IS_ERR(folio)) {
+			may_bypass = false;
 			if (!shouldalloc)
 				continue;
 
 			/*
-			 * Try cached I/O if allocation succeeds or fallback to
-			 * in-place I/O instead to avoid any direct reclaim.
+			 * Allocate a managed folio for cached I/O, or it may be
+			 * then filled with a file-backed folio for in-place I/O
 			 */
-			newpage = erofs_allocpage(&fe->pagepool, gfp);
-			if (!newpage)
+			newfolio = filemap_alloc_folio(gfp, 0);
+			if (!newfolio)
 				continue;
-			set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
+			newfolio->private = Z_EROFS_PREALLOCATED_FOLIO;
+			folio = NULL;
 		}
 		spin_lock(&pcl->lockref.lock);
 		if (!pcl->compressed_bvecs[i].page) {
-			pcl->compressed_bvecs[i].page = page ? page : newpage;
+			pcl->compressed_bvecs[i].page =
+				folio_page(folio ?: newfolio, 0);
 			spin_unlock(&pcl->lockref.lock);
 			continue;
 		}
 		spin_unlock(&pcl->lockref.lock);
-
-		if (page)
-			put_page(page);
-		else if (newpage)
-			erofs_pagepool_add(&fe->pagepool, newpage);
+		folio_put(folio ?: newfolio);
 	}
 
 	/*
-	 * don't do inplace I/O if all compressed pages are available in
-	 * managed cache since it can be moved to the bypass queue instead.
+	 * Don't perform in-place I/O if all compressed pages are available in
+	 * the managed cache, as the pcluster can be moved to the bypass queue.
 	 */
-	if (standalone)
+	if (may_bypass)
 		fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
 }
 
@@ -681,7 +660,7 @@ int erofs_init_managed_cache(struct super_block *sb)
 }
 
 /* callers must be with pcluster lock held */
-static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
+static int z_erofs_attach_page(struct z_erofs_frontend *fe,
 			       struct z_erofs_bvec *bvec, bool exclusive)
 {
 	struct z_erofs_pcluster *pcl = fe->pcl;
@@ -727,7 +706,7 @@ static bool z_erofs_get_pcluster(struct z_erofs_pcluster *pcl)
 	return true;
 }
 
-static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
+static int z_erofs_register_pcluster(struct z_erofs_frontend *fe)
 {
 	struct erofs_map_blocks *map = &fe->map;
 	struct super_block *sb = fe->inode->i_sb;
@@ -747,13 +726,11 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 	if (IS_ERR(pcl))
 		return PTR_ERR(pcl);
 
-	lockref_init(&pcl->lockref, 1); /* one ref for this request */
+	lockref_init(&pcl->lockref); /* one ref for this request */
 	pcl->algorithmformat = map->m_algorithmformat;
 	pcl->length = 0;
 	pcl->partial = true;
-
-	/* new pclusters should be claimed as type 1, primary and followed */
-	pcl->next = fe->owned_head;
+	pcl->next = fe->head;
 	pcl->pageofs_out = map->m_la & ~PAGE_MASK;
 	fe->mode = Z_EROFS_PCLUSTER_FOLLOWED;
 
@@ -789,8 +766,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
 			goto err_out;
 		}
 	}
-	fe->owned_head = &pcl->next;
-	fe->pcl = pcl;
+	fe->head = fe->pcl = pcl;
 	return 0;
 
 err_out:
@@ -799,7 +775,7 @@ err_out:
 	return err;
 }
 
-static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
+static int z_erofs_pcluster_begin(struct z_erofs_frontend *fe)
 {
 	struct erofs_map_blocks *map = &fe->map;
 	struct super_block *sb = fe->inode->i_sb;
@@ -809,7 +785,7 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
 
 	DBG_BUGON(fe->pcl);
 	/* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */
-	DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL);
+	DBG_BUGON(!fe->head);
 
 	if (!(map->m_flags & EROFS_MAP_META)) {
 		while (1) {
@@ -837,10 +813,9 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
 	if (ret == -EEXIST) {
 		mutex_lock(&fe->pcl->lock);
 		/* check if this pcluster hasn't been linked into any chain. */
-		if (cmpxchg(&fe->pcl->next, Z_EROFS_PCLUSTER_NIL,
-			    fe->owned_head) == Z_EROFS_PCLUSTER_NIL) {
+		if (!cmpxchg(&fe->pcl->next, NULL, fe->head)) {
 			/* .. so it can be attached to our submission chain */
-			fe->owned_head = &fe->pcl->next;
+			fe->head = fe->pcl;
 			fe->mode = Z_EROFS_PCLUSTER_FOLLOWED;
 		} else {	/* otherwise, it belongs to an inflight chain */
 			fe->mode = Z_EROFS_PCLUSTER_INFLIGHT;
@@ -873,14 +848,9 @@ static int z_erofs_pcluster_begin(struct z_erofs_decompress_frontend *fe)
 	return 0;
 }
 
-/*
- * keep in mind that no referenced pclusters will be freed
- * only after a RCU grace period.
- */
 static void z_erofs_rcu_callback(struct rcu_head *head)
 {
-	z_erofs_free_pcluster(container_of(head,
-			struct z_erofs_pcluster, rcu));
+	z_erofs_free_pcluster(container_of(head, struct z_erofs_pcluster, rcu));
 }
 
 static bool __erofs_try_to_release_pcluster(struct erofs_sb_info *sbi,
@@ -922,12 +892,10 @@ static bool erofs_try_to_release_pcluster(struct erofs_sb_info *sbi,
 	return free;
 }
 
-unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi,
-				  unsigned long nr_shrink)
+unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi, unsigned long nr)
 {
 	struct z_erofs_pcluster *pcl;
-	unsigned int freed = 0;
-	unsigned long index;
+	unsigned long index, freed = 0;
 
 	xa_lock(&sbi->managed_pslots);
 	xa_for_each(&sbi->managed_pslots, index, pcl) {
@@ -937,7 +905,7 @@ unsigned long z_erofs_shrink_scan(struct erofs_sb_info *sbi,
 		xa_unlock(&sbi->managed_pslots);
 
 		++freed;
-		if (!--nr_shrink)
+		if (!--nr)
 			return freed;
 		xa_lock(&sbi->managed_pslots);
 	}
@@ -966,7 +934,7 @@ static void z_erofs_put_pcluster(struct erofs_sb_info *sbi,
 		call_rcu(&pcl->rcu, z_erofs_rcu_callback);
 }
 
-static void z_erofs_pcluster_end(struct z_erofs_decompress_frontend *fe)
+static void z_erofs_pcluster_end(struct z_erofs_frontend *fe)
 {
 	struct z_erofs_pcluster *pcl = fe->pcl;
 
@@ -979,13 +947,9 @@ static void z_erofs_pcluster_end(struct z_erofs_decompress_frontend *fe)
 	if (fe->candidate_bvpage)
 		fe->candidate_bvpage = NULL;
 
-	/*
-	 * if all pending pages are added, don't hold its reference
-	 * any longer if the pcluster isn't hosted by ourselves.
-	 */
+	/* Drop refcount if it doesn't belong to our processing chain */
 	if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE)
 		z_erofs_put_pcluster(EROFS_I_SB(fe->inode), pcl, false);
-
 	fe->pcl = NULL;
 }
 
@@ -1014,7 +978,7 @@ static int z_erofs_read_fragment(struct super_block *sb, struct folio *folio,
 	return 0;
 }
 
-static int z_erofs_scan_folio(struct z_erofs_decompress_frontend *f,
+static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 			      struct folio *folio, bool ra)
 {
 	struct inode *const inode = f->inode;
@@ -1129,7 +1093,7 @@ static bool z_erofs_page_is_invalidated(struct page *page)
 	return !page_folio(page)->mapping && !z_erofs_is_shortlived_page(page);
 }
 
-struct z_erofs_decompress_backend {
+struct z_erofs_backend {
 	struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES];
 	struct super_block *sb;
 	struct z_erofs_pcluster *pcl;
@@ -1149,7 +1113,7 @@ struct z_erofs_bvec_item {
 	struct list_head list;
 };
 
-static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be,
+static void z_erofs_do_decompressed_bvec(struct z_erofs_backend *be,
 					 struct z_erofs_bvec *bvec)
 {
 	struct z_erofs_bvec_item *item;
@@ -1172,8 +1136,7 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be,
 	list_add(&item->list, &be->decompressed_secondary_bvecs);
 }
 
-static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be,
-				      int err)
+static void z_erofs_fill_other_copies(struct z_erofs_backend *be, int err)
 {
 	unsigned int off0 = be->pcl->pageofs_out;
 	struct list_head *p, *n;
@@ -1214,7 +1177,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be,
 	}
 }
 
-static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be)
+static void z_erofs_parse_out_bvecs(struct z_erofs_backend *be)
 {
 	struct z_erofs_pcluster *pcl = be->pcl;
 	struct z_erofs_bvec_iter biter;
@@ -1239,8 +1202,7 @@ static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be)
 		z_erofs_put_shortlivedpage(be->pagepool, old_bvpage);
 }
 
-static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
-				  bool *overlapped)
+static int z_erofs_parse_in_bvecs(struct z_erofs_backend *be, bool *overlapped)
 {
 	struct z_erofs_pcluster *pcl = be->pcl;
 	unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
@@ -1275,8 +1237,7 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
 	return err;
 }
 
-static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
-				       int err)
+static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 {
 	struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
 	struct z_erofs_pcluster *pcl = be->pcl;
@@ -1393,7 +1354,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 	pcl->vcnt = 0;
 
 	/* pcluster lock MUST be taken before the following line */
-	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_NIL);
+	WRITE_ONCE(pcl->next, NULL);
 	mutex_unlock(&pcl->lock);
 
 	if (z_erofs_is_inline_pcluster(pcl))
@@ -1406,21 +1367,19 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
 static int z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
 				    struct page **pagepool)
 {
-	struct z_erofs_decompress_backend be = {
+	struct z_erofs_backend be = {
 		.sb = io->sb,
 		.pagepool = pagepool,
 		.decompressed_secondary_bvecs =
 			LIST_HEAD_INIT(be.decompressed_secondary_bvecs),
+		.pcl = io->head,
 	};
-	z_erofs_next_pcluster_t owned = io->head;
+	struct z_erofs_pcluster *next;
 	int err = io->eio ? -EIO : 0;
 
-	while (owned != Z_EROFS_PCLUSTER_TAIL) {
-		DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL);
-
-		be.pcl = container_of(owned, struct z_erofs_pcluster, next);
-		owned = READ_ONCE(be.pcl->next);
-
+	for (; be.pcl != Z_EROFS_PCLUSTER_TAIL; be.pcl = next) {
+		DBG_BUGON(!be.pcl);
+		next = READ_ONCE(be.pcl->next);
 		err = z_erofs_decompress_pcluster(&be, err) ?: err;
 	}
 	return err;
@@ -1486,7 +1445,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
 }
 
 static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
-				 struct z_erofs_decompress_frontend *f,
+				 struct z_erofs_frontend *f,
 				 struct z_erofs_pcluster *pcl,
 				 unsigned int nr,
 				 struct address_space *mc)
@@ -1513,12 +1472,8 @@ repeat:
 	DBG_BUGON(z_erofs_is_shortlived_page(bvec->bv_page));
 
 	folio = page_folio(zbv.page);
-	/*
-	 * Handle preallocated cached folios.  We tried to allocate such folios
-	 * without triggering direct reclaim.  If allocation failed, inplace
-	 * file-backed folios will be used instead.
-	 */
-	if (folio->private == (void *)Z_EROFS_PREALLOCATED_PAGE) {
+	/* For preallocated managed folios, add them to page cache here */
+	if (folio->private == Z_EROFS_PREALLOCATED_FOLIO) {
 		tocache = true;
 		goto out_tocache;
 	}
@@ -1630,18 +1585,13 @@ enum {
 	NR_JOBQUEUES,
 };
 
-static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
-				    z_erofs_next_pcluster_t qtail[],
-				    z_erofs_next_pcluster_t owned_head)
+static void z_erofs_move_to_bypass_queue(struct z_erofs_pcluster *pcl,
+					 struct z_erofs_pcluster *next,
+					 struct z_erofs_pcluster **qtail[])
 {
-	z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT];
-	z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS];
-
 	WRITE_ONCE(pcl->next, Z_EROFS_PCLUSTER_TAIL);
-
-	WRITE_ONCE(*submit_qtail, owned_head);
-	WRITE_ONCE(*bypass_qtail, &pcl->next);
-
+	WRITE_ONCE(*qtail[JQ_SUBMIT], next);
+	WRITE_ONCE(*qtail[JQ_BYPASS], pcl);
 	qtail[JQ_BYPASS] = &pcl->next;
 }
 
@@ -1670,15 +1620,15 @@ static void z_erofs_endio(struct bio *bio)
 		bio_put(bio);
 }
 
-static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
+static void z_erofs_submit_queue(struct z_erofs_frontend *f,
 				 struct z_erofs_decompressqueue *fgq,
 				 bool *force_fg, bool readahead)
 {
 	struct super_block *sb = f->inode->i_sb;
 	struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb));
-	z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
+	struct z_erofs_pcluster **qtail[NR_JOBQUEUES];
 	struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
-	z_erofs_next_pcluster_t owned_head = f->owned_head;
+	struct z_erofs_pcluster *pcl, *next;
 	/* bio is NULL initially, so no need to initialize last_{index,bdev} */
 	erofs_off_t last_pa;
 	unsigned int nr_bios = 0;
@@ -1694,22 +1644,19 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;
 
 	/* by default, all need io submission */
-	q[JQ_SUBMIT]->head = owned_head;
+	q[JQ_SUBMIT]->head = next = f->head;
 
 	do {
 		struct erofs_map_dev mdev;
-		struct z_erofs_pcluster *pcl;
 		erofs_off_t cur, end;
 		struct bio_vec bvec;
 		unsigned int i = 0;
 		bool bypass = true;
 
-		DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_NIL);
-		pcl = container_of(owned_head, struct z_erofs_pcluster, next);
-		owned_head = READ_ONCE(pcl->next);
-
+		pcl = next;
+		next = READ_ONCE(pcl->next);
 		if (z_erofs_is_inline_pcluster(pcl)) {
-			move_to_bypass_jobqueue(pcl, qtail, owned_head);
+			z_erofs_move_to_bypass_queue(pcl, next, qtail);
 			continue;
 		}
 
@@ -1781,8 +1728,8 @@ drain_io:
 		if (!bypass)
 			qtail[JQ_SUBMIT] = &pcl->next;
 		else
-			move_to_bypass_jobqueue(pcl, qtail, owned_head);
-	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
+			z_erofs_move_to_bypass_queue(pcl, next, qtail);
+	} while (next != Z_EROFS_PCLUSTER_TAIL);
 
 	if (bio) {
 		if (erofs_is_fileio_mode(EROFS_SB(sb)))
@@ -1806,17 +1753,16 @@ drain_io:
 	z_erofs_decompress_kickoff(q[JQ_SUBMIT], nr_bios);
 }
 
-static int z_erofs_runqueue(struct z_erofs_decompress_frontend *f,
-			    unsigned int ra_folios)
+static int z_erofs_runqueue(struct z_erofs_frontend *f, unsigned int rapages)
 {
 	struct z_erofs_decompressqueue io[NR_JOBQUEUES];
 	struct erofs_sb_info *sbi = EROFS_I_SB(f->inode);
-	bool force_fg = z_erofs_is_sync_decompress(sbi, ra_folios);
+	bool force_fg = z_erofs_is_sync_decompress(sbi, rapages);
 	int err;
 
-	if (f->owned_head == Z_EROFS_PCLUSTER_TAIL)
+	if (f->head == Z_EROFS_PCLUSTER_TAIL)
 		return 0;
-	z_erofs_submit_queue(f, io, &force_fg, !!ra_folios);
+	z_erofs_submit_queue(f, io, &force_fg, !!rapages);
 
 	/* handle bypass queue (no i/o pclusters) immediately */
 	err = z_erofs_decompress_queue(&io[JQ_BYPASS], &f->pagepool);
@@ -1834,7 +1780,7 @@ static int z_erofs_runqueue(struct z_erofs_decompress_frontend *f,
  * Since partial uptodate is still unimplemented for now, we have to use
  * approximate readmore strategies as a start.
  */
-static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
+static void z_erofs_pcluster_readmore(struct z_erofs_frontend *f,
 		struct readahead_control *rac, bool backmost)
 {
 	struct inode *inode = f->inode;
@@ -1889,12 +1835,10 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f,
 static int z_erofs_read_folio(struct file *file, struct folio *folio)
 {
 	struct inode *const inode = folio->mapping->host;
-	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
+	Z_EROFS_DEFINE_FRONTEND(f, inode, folio_pos(folio));
 	int err;
 
 	trace_erofs_read_folio(folio, false);
-	f.headoffset = (erofs_off_t)folio->index << PAGE_SHIFT;
-
 	z_erofs_pcluster_readmore(&f, NULL, true);
 	err = z_erofs_scan_folio(&f, folio, false);
 	z_erofs_pcluster_readmore(&f, NULL, false);
@@ -1914,17 +1858,14 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 static void z_erofs_readahead(struct readahead_control *rac)
 {
 	struct inode *const inode = rac->mapping->host;
-	struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
+	Z_EROFS_DEFINE_FRONTEND(f, inode, readahead_pos(rac));
 	struct folio *head = NULL, *folio;
-	unsigned int nr_folios;
+	unsigned int nrpages = readahead_count(rac);
 	int err;
 
-	f.headoffset = readahead_pos(rac);
-
 	z_erofs_pcluster_readmore(&f, rac, true);
-	nr_folios = readahead_count(rac);
-	trace_erofs_readpages(inode, readahead_index(rac), nr_folios, false);
-
+	nrpages = readahead_count(rac);
+	trace_erofs_readpages(inode, readahead_index(rac), nrpages, false);
 	while ((folio = readahead_folio(rac))) {
 		folio->private = head;
 		head = folio;
@@ -1943,7 +1884,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
 	z_erofs_pcluster_readmore(&f, rac, false);
 	z_erofs_pcluster_end(&f);
 
-	(void)z_erofs_runqueue(&f, nr_folios);
+	(void)z_erofs_runqueue(&f, nrpages);
 	erofs_put_metabuf(&f.map.buf);
 	erofs_release_pages(&f.pagepool);
 }
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 4535f2f0a014..689437e99a5a 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -97,17 +97,48 @@ static int get_compacted_la_distance(unsigned int lobits,
 	return d1;
 }
 
-static int unpack_compacted_index(struct z_erofs_maprecorder *m,
-				  unsigned int amortizedshift,
-				  erofs_off_t pos, bool lookahead)
+static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m,
+					 unsigned long lcn, bool lookahead)
 {
-	struct erofs_inode *const vi = EROFS_I(m->inode);
+	struct inode *const inode = m->inode;
+	struct erofs_inode *const vi = EROFS_I(inode);
+	const erofs_off_t ebase = sizeof(struct z_erofs_map_header) +
+		ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8);
 	const unsigned int lclusterbits = vi->z_logical_clusterbits;
+	const unsigned int totalidx = erofs_iblks(inode);
+	unsigned int compacted_4b_initial, compacted_2b, amortizedshift;
 	unsigned int vcnt, lo, lobits, encodebits, nblk, bytes;
-	bool big_pcluster;
+	bool big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
+	erofs_off_t pos;
 	u8 *in, type;
 	int i;
 
+	if (lcn >= totalidx || lclusterbits > 14)
+		return -EINVAL;
+
+	m->lcn = lcn;
+	/* used to align to 32-byte (compacted_2b) alignment */
+	compacted_4b_initial = ((32 - ebase % 32) / 4) & 7;
+	compacted_2b = 0;
+	if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) &&
+	    compacted_4b_initial < totalidx)
+		compacted_2b = rounddown(totalidx - compacted_4b_initial, 16);
+
+	pos = ebase;
+	amortizedshift = 2;	/* compact_4b */
+	if (lcn >= compacted_4b_initial) {
+		pos += compacted_4b_initial * 4;
+		lcn -= compacted_4b_initial;
+		if (lcn < compacted_2b) {
+			amortizedshift = 1;
+		} else {
+			pos += compacted_2b * 2;
+			lcn -= compacted_2b;
+		}
+	}
+	pos += lcn * (1 << amortizedshift);
+
+	/* figure out the lcluster count in this pack */
 	if (1 << amortizedshift == 4 && lclusterbits <= 14)
 		vcnt = 2;
 	else if (1 << amortizedshift == 2 && lclusterbits <= 12)
@@ -122,7 +153,6 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	/* it doesn't equal to round_up(..) */
 	m->nextpackoff = round_down(pos, vcnt << amortizedshift) +
 			 (vcnt << amortizedshift);
-	big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
 	lobits = max(lclusterbits, ilog2(Z_EROFS_LI_D0_CBLKCNT) + 1U);
 	encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
 	bytes = pos & ((vcnt << amortizedshift) - 1);
@@ -207,53 +237,6 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 	return 0;
 }
 
-static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m,
-					 unsigned long lcn, bool lookahead)
-{
-	struct inode *const inode = m->inode;
-	struct erofs_inode *const vi = EROFS_I(inode);
-	const erofs_off_t ebase = sizeof(struct z_erofs_map_header) +
-		ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8);
-	unsigned int totalidx = erofs_iblks(inode);
-	unsigned int compacted_4b_initial, compacted_2b;
-	unsigned int amortizedshift;
-	erofs_off_t pos;
-
-	if (lcn >= totalidx || vi->z_logical_clusterbits > 14)
-		return -EINVAL;
-
-	m->lcn = lcn;
-	/* used to align to 32-byte (compacted_2b) alignment */
-	compacted_4b_initial = (32 - ebase % 32) / 4;
-	if (compacted_4b_initial == 32 / 4)
-		compacted_4b_initial = 0;
-
-	if ((vi->z_advise & Z_EROFS_ADVISE_COMPACTED_2B) &&
-	    compacted_4b_initial < totalidx)
-		compacted_2b = rounddown(totalidx - compacted_4b_initial, 16);
-	else
-		compacted_2b = 0;
-
-	pos = ebase;
-	if (lcn < compacted_4b_initial) {
-		amortizedshift = 2;
-		goto out;
-	}
-	pos += compacted_4b_initial * 4;
-	lcn -= compacted_4b_initial;
-
-	if (lcn < compacted_2b) {
-		amortizedshift = 1;
-		goto out;
-	}
-	pos += compacted_2b * 2;
-	lcn -= compacted_2b;
-	amortizedshift = 2;
-out:
-	pos += lcn * (1 << amortizedshift);
-	return unpack_compacted_index(m, amortizedshift, pos, lookahead);
-}
-
 static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m,
 					   unsigned int lcn, bool lookahead)
 {
@@ -311,27 +294,23 @@ err_bogus:
 static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 					    unsigned int initial_lcn)
 {
-	struct super_block *sb = m->inode->i_sb;
-	struct erofs_inode *const vi = EROFS_I(m->inode);
-	struct erofs_map_blocks *const map = m->map;
-	const unsigned int lclusterbits = vi->z_logical_clusterbits;
-	unsigned long lcn;
+	struct inode *inode = m->inode;
+	struct super_block *sb = inode->i_sb;
+	struct erofs_inode *vi = EROFS_I(inode);
+	bool bigpcl1 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
+	bool bigpcl2 = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2;
+	unsigned long lcn = m->lcn + 1;
 	int err;
 
-	DBG_BUGON(m->type != Z_EROFS_LCLUSTER_TYPE_PLAIN &&
-		  m->type != Z_EROFS_LCLUSTER_TYPE_HEAD1 &&
-		  m->type != Z_EROFS_LCLUSTER_TYPE_HEAD2);
+	DBG_BUGON(m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD);
 	DBG_BUGON(m->type != m->headtype);
 
-	if (m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN ||
-	    ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1) &&
-	     !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) ||
-	    ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) &&
-	     !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) {
-		map->m_plen = 1ULL << lclusterbits;
-		return 0;
-	}
-	lcn = m->lcn + 1;
+	if ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1 && !bigpcl1) ||
+	    ((m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN ||
+	      m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) && !bigpcl2) ||
+	    (lcn << vi->z_logical_clusterbits) >= inode->i_size)
+		m->compressedblks = 1;
+
 	if (m->compressedblks)
 		goto out;
 
@@ -356,9 +335,9 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 	case Z_EROFS_LCLUSTER_TYPE_HEAD2:
 		/*
 		 * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
-		 * rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
+		 * rather than CBLKCNT, it's a 1 block-sized pcluster.
 		 */
-		m->compressedblks = 1 << (lclusterbits - sb->s_blocksize_bits);
+		m->compressedblks = 1;
 		break;
 	case Z_EROFS_LCLUSTER_TYPE_NONHEAD:
 		if (m->delta[0] != 1)
@@ -373,7 +352,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		return -EFSCORRUPTED;
 	}
 out:
-	map->m_plen = erofs_pos(sb, m->compressedblks);
+	m->map->m_plen = erofs_pos(sb, m->compressedblks);
 	return 0;
 err_bonus_cblkcnt:
 	erofs_err(sb, "bogus CBLKCNT @ lcn %lu of nid %llu", lcn, vi->nid);
diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
index 0dd65cefce33..55ff2ab5128e 100644
--- a/fs/erofs/zutil.c
+++ b/fs/erofs/zutil.c
@@ -87,8 +87,8 @@ int z_erofs_gbuf_growsize(unsigned int nrpages)
 			tmp_pages[j] = gbuf->pages[j];
 		do {
 			last = j;
-			j = alloc_pages_bulk_array(GFP_KERNEL, nrpages,
-						   tmp_pages);
+			j = alloc_pages_bulk(GFP_KERNEL, nrpages,
+					     tmp_pages);
 			if (last == j)
 				goto out;
 		} while (j != nrpages);
@@ -243,7 +243,7 @@ void erofs_shrinker_unregister(struct super_block *sb)
 static unsigned long erofs_shrink_count(struct shrinker *shrink,
 					struct shrink_control *sc)
 {
-	return atomic_long_read(&erofs_global_shrink_cnt);
+	return atomic_long_read(&erofs_global_shrink_cnt) ?: SHRINK_EMPTY;
 }
 
 static unsigned long erofs_shrink_scan(struct shrinker *shrink,
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index f9898e60dd8b..7c0980db77b3 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -318,7 +318,7 @@ static void unlist_file(struct epitems_head *head)
 static long long_zero;
 static long long_max = LONG_MAX;
 
-static struct ctl_table epoll_table[] = {
+static const struct ctl_table epoll_table[] = {
 	{
 		.procname	= "max_user_watches",
 		.data		= &max_user_watches,
diff --git a/fs/exec.c b/fs/exec.c
index 18f25c23b09f..506cd411f4ac 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -205,18 +205,10 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 	/*
 	 * Avoid relying on expanding the stack down in GUP (which
 	 * does not work for STACK_GROWSUP anyway), and just do it
-	 * by hand ahead of time.
+	 * ahead of time.
 	 */
-	if (write && pos < vma->vm_start) {
-		mmap_write_lock(mm);
-		ret = expand_downwards(vma, pos);
-		if (unlikely(ret < 0)) {
-			mmap_write_unlock(mm);
-			return NULL;
-		}
-		mmap_write_downgrade(mm);
-	} else
-		mmap_read_lock(mm);
+	if (!mmap_read_lock_maybe_expand(mm, vma, pos, write))
+		return NULL;
 
 	/*
 	 * We are doing an exec().  'current' is the process
@@ -2167,7 +2159,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ
 	return error;
 }
 
-static struct ctl_table fs_exec_sysctls[] = {
+static const struct ctl_table fs_exec_sysctls[] = {
 	{
 		.procname	= "suid_dumpable",
 		.data		= &suid_dumpable,
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 099f80645072..691dd77b6ab5 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -31,10 +31,9 @@ static inline void exfat_d_version_set(struct dentry *dentry,
  * If it happened, the negative dentry isn't actually negative anymore.  So,
  * drop it.
  */
-static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int exfat_d_revalidate(struct inode *dir, const struct qstr *name,
+			      struct dentry *dentry, unsigned int flags)
 {
-	int ret;
-
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
@@ -58,11 +57,7 @@ static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags)
 	if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
 		return 0;
 
-	spin_lock(&dentry->d_lock);
-	ret = inode_eq_iversion(d_inode(dentry->d_parent),
-			exfat_d_version(dentry));
-	spin_unlock(&dentry->d_lock);
-	return ret;
+	return inode_eq_iversion(dir, exfat_d_version(dentry));
 }
 
 /* returns the length of a struct qstr, ignoring trailing dots if necessary */
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 26c4fc37edcf..da4263a14a20 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -322,9 +322,7 @@ restart:
 	WARN_ON(!list_empty(&ei->i_fc_dilist));
 	spin_unlock(&sbi->s_fc_lock);
 
-	if (fc_dentry->fcd_name.name &&
-		fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
-		kfree(fc_dentry->fcd_name.name);
+	release_dentry_name_snapshot(&fc_dentry->fcd_name);
 	kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
 
 	return;
@@ -449,22 +447,7 @@ static int __track_dentry_update(handle_t *handle, struct inode *inode,
 	node->fcd_op = dentry_update->op;
 	node->fcd_parent = dir->i_ino;
 	node->fcd_ino = inode->i_ino;
-	if (dentry->d_name.len > DNAME_INLINE_LEN) {
-		node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS);
-		if (!node->fcd_name.name) {
-			kmem_cache_free(ext4_fc_dentry_cachep, node);
-			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle);
-			mutex_lock(&ei->i_fc_lock);
-			return -ENOMEM;
-		}
-		memcpy((u8 *)node->fcd_name.name, dentry->d_name.name,
-			dentry->d_name.len);
-	} else {
-		memcpy(node->fcd_iname, dentry->d_name.name,
-			dentry->d_name.len);
-		node->fcd_name.name = node->fcd_iname;
-	}
-	node->fcd_name.len = dentry->d_name.len;
+	take_dentry_name_snapshot(&node->fcd_name, dentry);
 	INIT_LIST_HEAD(&node->fcd_dilist);
 	spin_lock(&sbi->s_fc_lock);
 	if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
@@ -832,7 +815,7 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc,
 {
 	struct ext4_fc_dentry_info fcd;
 	struct ext4_fc_tl tl;
-	int dlen = fc_dentry->fcd_name.len;
+	int dlen = fc_dentry->fcd_name.name.len;
 	u8 *dst = ext4_fc_reserve_space(sb,
 			EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc);
 
@@ -847,7 +830,7 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc,
 	dst += EXT4_FC_TAG_BASE_LEN;
 	memcpy(dst, &fcd, sizeof(fcd));
 	dst += sizeof(fcd);
-	memcpy(dst, fc_dentry->fcd_name.name, dlen);
+	memcpy(dst, fc_dentry->fcd_name.name.name, dlen);
 
 	return true;
 }
@@ -1328,9 +1311,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 		list_del_init(&fc_dentry->fcd_dilist);
 		spin_unlock(&sbi->s_fc_lock);
 
-		if (fc_dentry->fcd_name.name &&
-			fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
-			kfree(fc_dentry->fcd_name.name);
+		release_dentry_name_snapshot(&fc_dentry->fcd_name);
 		kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
 		spin_lock(&sbi->s_fc_lock);
 	}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 2fadb2c4780c..3bd534e4dbbf 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -109,8 +109,7 @@ struct ext4_fc_dentry_update {
 	int fcd_op;		/* Type of update create / unlink / link */
 	int fcd_parent;		/* Parent inode number */
 	int fcd_ino;		/* Inode number */
-	struct qstr fcd_name;	/* Dirent name */
-	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
+	struct name_snapshot fcd_name;	/* Dirent name */
 	struct list_head fcd_list;
 	struct list_head fcd_dilist;
 };
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 7f26440e8595..985690d81a82 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -846,7 +846,7 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
 bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages,
 				int index, int nr_pages, bool uptodate)
 {
-	unsigned long pgidx = pages[index]->index;
+	unsigned long pgidx = page_folio(pages[index])->index;
 	int i = uptodate ? 0 : 1;
 
 	/*
@@ -860,9 +860,11 @@ bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages,
 		return false;
 
 	for (; i < cc->cluster_size; i++) {
-		if (pages[index + i]->index != pgidx + i)
+		struct folio *folio = page_folio(pages[index + i]);
+
+		if (folio->index != pgidx + i)
 			return false;
-		if (uptodate && !PageUptodate(pages[index + i]))
+		if (uptodate && !folio_test_uptodate(folio))
 			return false;
 	}
 
@@ -1195,7 +1197,8 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
 		.cluster_size = F2FS_I(inode)->i_cluster_size,
 		.rpages = fsdata,
 	};
-	bool first_index = (index == cc.rpages[0]->index);
+	struct folio *folio = page_folio(cc.rpages[0]);
+	bool first_index = (index == folio->index);
 
 	if (copied)
 		set_cluster_dirty(&cc);
@@ -1239,13 +1242,14 @@ int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock)
 		int i;
 
 		for (i = cluster_size - 1; i >= 0; i--) {
-			loff_t start = rpages[i]->index << PAGE_SHIFT;
+			struct folio *folio = page_folio(rpages[i]);
+			loff_t start = folio->index << PAGE_SHIFT;
 
 			if (from <= start) {
-				zero_user_segment(rpages[i], 0, PAGE_SIZE);
+				folio_zero_segment(folio, 0, folio_size(folio));
 			} else {
-				zero_user_segment(rpages[i], from - start,
-								PAGE_SIZE);
+				folio_zero_segment(folio, from - start,
+						folio_size(folio));
 				break;
 			}
 		}
@@ -1278,6 +1282,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 		.encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ?
 									1 : 0,
 	};
+	struct folio *folio;
 	struct dnode_of_data dn;
 	struct node_info ni;
 	struct compress_io_ctx *cic;
@@ -1289,7 +1294,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	/* we should bypass data pages to proceed the kworker jobs */
 	if (unlikely(f2fs_cp_error(sbi))) {
-		mapping_set_error(cc->rpages[0]->mapping, -EIO);
+		mapping_set_error(inode->i_mapping, -EIO);
 		goto out_free;
 	}
 
@@ -1316,7 +1321,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 			goto out_put_dnode;
 	}
 
-	psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT;
+	folio = page_folio(cc->rpages[last_index]);
+	psize = folio_pos(folio) + folio_size(folio);
 
 	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
 	if (err)
@@ -1339,7 +1345,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	for (i = 0; i < cc->valid_nr_cpages; i++) {
 		f2fs_set_compressed_page(cc->cpages[i], inode,
-					cc->rpages[i + 1]->index, cic);
+				page_folio(cc->rpages[i + 1])->index, cic);
 		fio.compressed_page = cc->cpages[i];
 
 		fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_page,
@@ -1374,7 +1380,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 			if (blkaddr == COMPRESS_ADDR)
 				fio.compr_blocks++;
 			if (__is_valid_data_blkaddr(blkaddr))
-				f2fs_invalidate_blocks(sbi, blkaddr);
+				f2fs_invalidate_blocks(sbi, blkaddr, 1);
 			f2fs_update_data_blkaddr(&dn, COMPRESS_ADDR);
 			goto unlock_continue;
 		}
@@ -1384,7 +1390,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 		if (i > cc->valid_nr_cpages) {
 			if (__is_valid_data_blkaddr(blkaddr)) {
-				f2fs_invalidate_blocks(sbi, blkaddr);
+				f2fs_invalidate_blocks(sbi, blkaddr, 1);
 				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
 			}
 			goto unlock_continue;
@@ -1545,6 +1551,7 @@ continue_unlock:
 		if (!clear_page_dirty_for_io(cc->rpages[i]))
 			goto continue_unlock;
 
+		submitted = 0;
 		ret = f2fs_write_single_data_page(page_folio(cc->rpages[i]),
 						&submitted,
 						NULL, NULL, wbc, io_type,
@@ -1903,11 +1910,12 @@ struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi)
 	return sbi->compress_inode->i_mapping;
 }
 
-void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr)
+void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi,
+				block_t blkaddr, unsigned int len)
 {
 	if (!sbi->compress_inode)
 		return;
-	invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr);
+	invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr + len - 1);
 }
 
 void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a2478c2afb3a..de4da6d9cd93 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -70,9 +70,9 @@ bool f2fs_is_cp_guaranteed(struct page *page)
 	return false;
 }
 
-static enum count_type __read_io_type(struct page *page)
+static enum count_type __read_io_type(struct folio *folio)
 {
-	struct address_space *mapping = page_file_mapping(page);
+	struct address_space *mapping = folio->mapping;
 
 	if (mapping) {
 		struct inode *inode = mapping->host;
@@ -136,27 +136,22 @@ struct bio_post_read_ctx {
  */
 static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
 {
-	struct bio_vec *bv;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 	struct bio_post_read_ctx *ctx = bio->bi_private;
 
-	bio_for_each_segment_all(bv, bio, iter_all) {
-		struct page *page = bv->bv_page;
+	bio_for_each_folio_all(fi, bio) {
+		struct folio *folio = fi.folio;
 
-		if (f2fs_is_compressed_page(page)) {
+		if (f2fs_is_compressed_page(&folio->page)) {
 			if (ctx && !ctx->decompression_attempted)
-				f2fs_end_read_compressed_page(page, true, 0,
+				f2fs_end_read_compressed_page(&folio->page, true, 0,
 							in_task);
-			f2fs_put_page_dic(page, in_task);
+			f2fs_put_page_dic(&folio->page, in_task);
 			continue;
 		}
 
-		if (bio->bi_status)
-			ClearPageUptodate(page);
-		else
-			SetPageUptodate(page);
-		dec_page_count(F2FS_P_SB(page), __read_io_type(page));
-		unlock_page(page);
+		dec_page_count(F2FS_F_SB(folio), __read_io_type(folio));
+		folio_end_read(folio, bio->bi_status == 0);
 	}
 
 	if (ctx)
@@ -516,10 +511,6 @@ static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio,
 				  enum page_type type)
 {
 	WARN_ON_ONCE(is_read_io(bio_op(bio)));
-
-	if (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type))
-		blk_finish_plug(current->plug);
-
 	trace_f2fs_submit_write_bio(sbi->sb, type, bio);
 	iostat_update_submit_ctx(bio, type);
 	submit_bio(bio);
@@ -689,33 +680,29 @@ void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
 int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 {
 	struct bio *bio;
-	struct page *page = fio->encrypted_page ?
-			fio->encrypted_page : fio->page;
+	struct folio *fio_folio = page_folio(fio->page);
+	struct folio *data_folio = fio->encrypted_page ?
+			page_folio(fio->encrypted_page) : fio_folio;
 
 	if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
 			fio->is_por ? META_POR : (__is_meta_io(fio) ?
 			META_GENERIC : DATA_GENERIC_ENHANCE)))
 		return -EFSCORRUPTED;
 
-	trace_f2fs_submit_page_bio(page, fio);
+	trace_f2fs_submit_folio_bio(data_folio, fio);
 
 	/* Allocate a new bio */
 	bio = __bio_alloc(fio, 1);
 
-	f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
-			page_folio(fio->page)->index, fio, GFP_NOIO);
-
-	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
-		bio_put(bio);
-		return -EFAULT;
-	}
+	f2fs_set_bio_crypt_ctx(bio, fio_folio->mapping->host,
+			fio_folio->index, fio, GFP_NOIO);
+	bio_add_folio_nofail(bio, data_folio, folio_size(data_folio), 0);
 
 	if (fio->io_wbc && !is_read_io(fio->op))
-		wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
-					 PAGE_SIZE);
+		wbc_account_cgroup_owner(fio->io_wbc, fio_folio, PAGE_SIZE);
 
 	inc_page_count(fio->sbi, is_read_io(fio->op) ?
-			__read_io_type(page) : WB_DATA_TYPE(fio->page, false));
+			__read_io_type(data_folio) : WB_DATA_TYPE(fio->page, false));
 
 	if (is_read_io(bio_op(bio)))
 		f2fs_submit_read_bio(fio->sbi, bio, fio->type);
@@ -894,7 +881,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
 			__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
 		return -EFSCORRUPTED;
 
-	trace_f2fs_submit_page_bio(page, fio);
+	trace_f2fs_submit_folio_bio(page_folio(page), fio);
 
 	if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
 						fio->new_blkaddr))
@@ -1018,7 +1005,7 @@ alloc_new:
 
 	io->last_block_in_bio = fio->new_blkaddr;
 
-	trace_f2fs_submit_page_write(fio->page, fio);
+	trace_f2fs_submit_folio_write(page_folio(fio->page), fio);
 #ifdef CONFIG_BLK_DEV_ZONED
 	if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
 			is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
@@ -1289,7 +1276,7 @@ struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 
-	page = find_get_page(mapping, index);
+	page = find_get_page_flags(mapping, index, FGP_ACCESSED);
 	if (page && PageUptodate(page))
 		return page;
 	f2fs_put_page(page, 0);
@@ -1423,7 +1410,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
 		return err;
 
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
-		f2fs_invalidate_internal_cache(sbi, old_blkaddr);
+		f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1);
 
 	f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
 	return 0;
@@ -2464,7 +2451,7 @@ next_page:
 
 static int f2fs_read_data_folio(struct file *file, struct folio *folio)
 {
-	struct inode *inode = folio_file_mapping(folio)->host;
+	struct inode *inode = folio->mapping->host;
 	int ret = -EAGAIN;
 
 	trace_f2fs_readpage(folio, DATA);
@@ -3163,6 +3150,7 @@ continue_unlock:
 				continue;
 			}
 #endif
+			submitted = 0;
 			ret = f2fs_write_single_data_page(folio,
 					&submitted, &bio, &last_block,
 					wbc, io_type, 0, true);
@@ -4043,7 +4031,6 @@ retry:
 		cur_lblock = 1;	/* force Empty message */
 	sis->max = cur_lblock;
 	sis->pages = cur_lblock - 1;
-	sis->highest_bit = cur_lblock - 1;
 out:
 	if (not_aligned)
 		f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%lu * N)",
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 47a5c806cf16..54dd52de7269 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -175,7 +175,8 @@ static unsigned long dir_block_index(unsigned int level,
 static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 				struct page *dentry_page,
 				const struct f2fs_filename *fname,
-				int *max_slots)
+				int *max_slots,
+				bool use_hash)
 {
 	struct f2fs_dentry_block *dentry_blk;
 	struct f2fs_dentry_ptr d;
@@ -183,7 +184,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 	dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
 
 	make_dentry_ptr_block(dir, &d, dentry_blk);
-	return f2fs_find_target_dentry(&d, fname, max_slots);
+	return f2fs_find_target_dentry(&d, fname, max_slots, use_hash);
 }
 
 static inline int f2fs_match_name(const struct inode *dir,
@@ -208,7 +209,8 @@ static inline int f2fs_match_name(const struct inode *dir,
 }
 
 struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
-			const struct f2fs_filename *fname, int *max_slots)
+			const struct f2fs_filename *fname, int *max_slots,
+			bool use_hash)
 {
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
@@ -231,7 +233,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
 			continue;
 		}
 
-		if (de->hash_code == fname->hash) {
+		if (!use_hash || de->hash_code == fname->hash) {
 			res = f2fs_match_name(d->inode, fname,
 					      d->filename[bit_pos],
 					      le16_to_cpu(de->name_len));
@@ -258,11 +260,12 @@ found:
 static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 					unsigned int level,
 					const struct f2fs_filename *fname,
-					struct page **res_page)
+					struct page **res_page,
+					bool use_hash)
 {
 	int s = GET_DENTRY_SLOTS(fname->disk_name.len);
 	unsigned int nbucket, nblock;
-	unsigned int bidx, end_block;
+	unsigned int bidx, end_block, bucket_no;
 	struct page *dentry_page;
 	struct f2fs_dir_entry *de = NULL;
 	pgoff_t next_pgofs;
@@ -272,8 +275,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
 
+	bucket_no = use_hash ? le32_to_cpu(fname->hash) % nbucket : 0;
+
+start_find_bucket:
 	bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
-			       le32_to_cpu(fname->hash) % nbucket);
+			       bucket_no);
 	end_block = bidx + nblock;
 
 	while (bidx < end_block) {
@@ -290,7 +296,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 			}
 		}
 
-		de = find_in_block(dir, dentry_page, fname, &max_slots);
+		de = find_in_block(dir, dentry_page, fname, &max_slots, use_hash);
 		if (IS_ERR(de)) {
 			*res_page = ERR_CAST(de);
 			de = NULL;
@@ -307,12 +313,18 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		bidx++;
 	}
 
-	if (!de && room && F2FS_I(dir)->chash != fname->hash) {
-		F2FS_I(dir)->chash = fname->hash;
-		F2FS_I(dir)->clevel = level;
-	}
+	if (de)
+		return de;
 
-	return de;
+	if (likely(use_hash)) {
+		if (room && F2FS_I(dir)->chash != fname->hash) {
+			F2FS_I(dir)->chash = fname->hash;
+			F2FS_I(dir)->clevel = level;
+		}
+	} else if (++bucket_no < nbucket) {
+		goto start_find_bucket;
+	}
+	return NULL;
 }
 
 struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
@@ -323,11 +335,15 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
 	struct f2fs_dir_entry *de = NULL;
 	unsigned int max_depth;
 	unsigned int level;
+	bool use_hash = true;
 
 	*res_page = NULL;
 
+#if IS_ENABLED(CONFIG_UNICODE)
+start_find_entry:
+#endif
 	if (f2fs_has_inline_dentry(dir)) {
-		de = f2fs_find_in_inline_dir(dir, fname, res_page);
+		de = f2fs_find_in_inline_dir(dir, fname, res_page, use_hash);
 		goto out;
 	}
 
@@ -343,11 +359,18 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
 	}
 
 	for (level = 0; level < max_depth; level++) {
-		de = find_in_level(dir, level, fname, res_page);
+		de = find_in_level(dir, level, fname, res_page, use_hash);
 		if (de || IS_ERR(*res_page))
 			break;
 	}
+
 out:
+#if IS_ENABLED(CONFIG_UNICODE)
+	if (IS_CASEFOLDED(dir) && !de && use_hash) {
+		use_hash = false;
+		goto start_find_entry;
+	}
+#endif
 	/* This is to increase the speed of f2fs_create */
 	if (!de)
 		F2FS_I(dir)->task = current;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index fd7e9cb6f893..1afa7be16e7d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1985,9 +1985,14 @@ static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
 	return F2FS_I_SB(mapping->host);
 }
 
+static inline struct f2fs_sb_info *F2FS_F_SB(struct folio *folio)
+{
+	return F2FS_M_SB(folio->mapping);
+}
+
 static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
 {
-	return F2FS_M_SB(page_file_mapping(page));
+	return F2FS_F_SB(page_folio(page));
 }
 
 static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
@@ -3565,7 +3570,8 @@ int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
 			struct f2fs_filename *fname);
 void f2fs_free_filename(struct f2fs_filename *fname);
 struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
-			const struct f2fs_filename *fname, int *max_slots);
+			const struct f2fs_filename *fname, int *max_slots,
+			bool use_hash);
 int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			unsigned int start_pos, struct fscrypt_str *fstr);
 void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
@@ -3700,7 +3706,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
 int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
 int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
 void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
-void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr,
+						unsigned int len);
 bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
 int f2fs_start_discard_thread(struct f2fs_sb_info *sbi);
 void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
@@ -4201,7 +4208,8 @@ int f2fs_write_inline_data(struct inode *inode, struct folio *folio);
 int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
 struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
 					const struct f2fs_filename *fname,
-					struct page **res_page);
+					struct page **res_page,
+					bool use_hash);
 int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
 			struct page *ipage);
 int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
@@ -4368,7 +4376,8 @@ void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
 int __init f2fs_init_compress_cache(void);
 void f2fs_destroy_compress_cache(void);
 struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi);
-void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr);
+void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi,
+					block_t blkaddr, unsigned int len);
 void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
 						nid_t ino, block_t blkaddr);
 bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
@@ -4423,8 +4432,8 @@ static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return
 static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
 static inline int __init f2fs_init_compress_cache(void) { return 0; }
 static inline void f2fs_destroy_compress_cache(void) { }
-static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi,
-				block_t blkaddr) { }
+static inline void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi,
+				block_t blkaddr, unsigned int len) { }
 static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi,
 				struct page *page, nid_t ino, block_t blkaddr) { }
 static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
@@ -4740,10 +4749,10 @@ static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi,
 }
 
 static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi,
-								block_t blkaddr)
+						block_t blkaddr, unsigned int len)
 {
-	f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1);
-	f2fs_invalidate_compress_page(sbi, blkaddr);
+	f2fs_truncate_meta_inode_pages(sbi, blkaddr, len);
+	f2fs_invalidate_compress_pages_range(sbi, blkaddr, len);
 }
 
 #define EFSBADCRC	EBADMSG		/* Bad CRC detected */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index aa9679b3d8e4..f92a9fba9991 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -621,8 +621,11 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 	int cluster_index = 0, valid_blocks = 0;
 	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
 	bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks);
+	block_t blkstart;
+	int blklen = 0;
 
 	addr = get_dnode_addr(dn->inode, dn->node_page) + ofs;
+	blkstart = le32_to_cpu(*addr);
 
 	/* Assumption: truncation starts with cluster */
 	for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) {
@@ -638,26 +641,44 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		}
 
 		if (blkaddr == NULL_ADDR)
-			continue;
+			goto next;
 
 		f2fs_set_data_blkaddr(dn, NULL_ADDR);
 
 		if (__is_valid_data_blkaddr(blkaddr)) {
 			if (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE))
-				continue;
+				goto next;
 			if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr,
 						DATA_GENERIC_ENHANCE))
-				continue;
+				goto next;
 			if (compressed_cluster)
 				valid_blocks++;
 		}
 
-		f2fs_invalidate_blocks(sbi, blkaddr);
+		if (blkstart + blklen == blkaddr) {
+			blklen++;
+		} else {
+			f2fs_invalidate_blocks(sbi, blkstart, blklen);
+			blkstart = blkaddr;
+			blklen = 1;
+		}
 
 		if (!released || blkaddr != COMPRESS_ADDR)
 			nr_free++;
+
+		continue;
+
+next:
+		if (blklen)
+			f2fs_invalidate_blocks(sbi, blkstart, blklen);
+
+		blkstart = le32_to_cpu(*(addr + 1));
+		blklen = 0;
 	}
 
+	if (blklen)
+		f2fs_invalidate_blocks(sbi, blkstart, blklen);
+
 	if (compressed_cluster)
 		f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false);
 
@@ -747,10 +768,8 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 	if (IS_DEVICE_ALIASING(inode)) {
 		struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
 		struct extent_info ei = et->largest;
-		unsigned int i;
 
-		for (i = 0; i < ei.len; i++)
-			f2fs_invalidate_blocks(sbi, ei.blk + i);
+		f2fs_invalidate_blocks(sbi, ei.blk, ei.len);
 
 		dec_valid_block_count(sbi, inode, ei.len);
 		f2fs_update_time(sbi, REQ_TIME);
@@ -1323,7 +1342,7 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
 		ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
 		if (ret) {
 			dec_valid_block_count(sbi, inode, 1);
-			f2fs_invalidate_blocks(sbi, *blkaddr);
+			f2fs_invalidate_blocks(sbi, *blkaddr, 1);
 		} else {
 			f2fs_update_data_blkaddr(&dn, *blkaddr);
 		}
@@ -1575,7 +1594,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
 			break;
 		}
 
-		f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
+		f2fs_invalidate_blocks(sbi, dn->data_blkaddr, 1);
 		f2fs_set_data_blkaddr(dn, NEW_ADDR);
 	}
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 3e1b6d2ff3a7..faf9fa1c804d 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -806,11 +806,14 @@ retry:
 			goto out;
 		}
 
-		if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+		if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) {
 			ret = -EBUSY;
-		else
-			p.min_segno = *result;
-		goto out;
+			goto out;
+		}
+		if (gc_type == FG_GC)
+			clear_bit(GET_SEC_FROM_SEG(sbi, *result), dirty_i->victim_secmap);
+		p.min_segno = *result;
+		goto got_result;
 	}
 
 	ret = -ENODATA;
@@ -1412,7 +1415,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 				page_address(mpage), PAGE_SIZE);
 	f2fs_put_page(mpage, 1);
 
-	f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr);
+	f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr, 1);
 
 	set_page_dirty(fio.encrypted_page);
 	if (clear_page_dirty_for_io(fio.encrypted_page))
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 005babf1bed1..3e3c35d4c98b 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -81,7 +81,7 @@ bool f2fs_may_inline_dentry(struct inode *inode)
 
 void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage)
 {
-	struct inode *inode = folio_file_mapping(folio)->host;
+	struct inode *inode = folio->mapping->host;
 
 	if (folio_test_uptodate(folio))
 		return;
@@ -352,7 +352,8 @@ process_inline:
 
 struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
 					const struct f2fs_filename *fname,
-					struct page **res_page)
+					struct page **res_page,
+					bool use_hash)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	struct f2fs_dir_entry *de;
@@ -369,7 +370,7 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
 	inline_dentry = inline_data_addr(dir, ipage);
 
 	make_dentry_ptr_inline(dir, &d, inline_dentry);
-	de = f2fs_find_target_dentry(&d, fname, NULL);
+	de = f2fs_find_target_dentry(&d, fname, NULL, use_hash);
 	unlock_page(ipage);
 	if (IS_ERR(de)) {
 		*res_page = ERR_CAST(de);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 282fd320bdb3..3dd25f64d6f1 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -302,15 +302,6 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 				  F2FS_TOTAL_EXTRA_ATTR_SIZE);
 			return false;
 		}
-		if (f2fs_sb_has_flexible_inline_xattr(sbi) &&
-			f2fs_has_inline_xattr(inode) &&
-			(!fi->i_inline_xattr_size ||
-			fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) {
-			f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %lu",
-				  __func__, inode->i_ino, fi->i_inline_xattr_size,
-				  MAX_INLINE_XATTR_SIZE);
-			return false;
-		}
 		if (f2fs_sb_has_compression(sbi) &&
 			fi->i_flags & F2FS_COMPR_FL &&
 			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
@@ -320,6 +311,16 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		}
 	}
 
+	if (f2fs_sb_has_flexible_inline_xattr(sbi) &&
+		f2fs_has_inline_xattr(inode) &&
+		(fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE ||
+		fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) {
+		f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, min: %zu, max: %lu",
+			  __func__, inode->i_ino, fi->i_inline_xattr_size,
+			  MIN_INLINE_XATTR_SIZE, MAX_INLINE_XATTR_SIZE);
+		return false;
+	}
+
 	if (!f2fs_sb_has_extra_attr(sbi)) {
 		if (f2fs_sb_has_project_quota(sbi)) {
 			f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.",
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 57d46e1439de..a278c7da8177 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -341,6 +341,7 @@ fail_drop:
 	trace_f2fs_new_inode(inode, err);
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
+	make_bad_inode(inode);
 	if (nid_free)
 		set_inode_flag(inode, FI_FREE_NID);
 	clear_nlink(inode);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 0b900a7a48e5..f88392fc4ba9 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -558,6 +558,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	block_t blkaddr;
 	int i;
 
+	ni->flag = 0;
 	ni->nid = nid;
 retry:
 	/* Check nat cache */
@@ -916,7 +917,7 @@ static int truncate_node(struct dnode_of_data *dn)
 	}
 
 	/* Deallocate node address */
-	f2fs_invalidate_blocks(sbi, ni.blk_addr);
+	f2fs_invalidate_blocks(sbi, ni.blk_addr, 1);
 	dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
@@ -1274,8 +1275,9 @@ int f2fs_remove_inode_page(struct inode *inode)
 	}
 
 	/* remove potential inline_data blocks */
-	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-				S_ISLNK(inode->i_mode))
+	if (!IS_DEVICE_ALIASING(inode) &&
+	    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	     S_ISLNK(inode->i_mode)))
 		f2fs_truncate_data_blocks_range(&dn, 1);
 
 	/* 0 is possible, after f2fs_new_inode() has failed */
@@ -2763,7 +2765,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
 	if (err)
 		return err;
 
-	f2fs_invalidate_blocks(sbi, ni.blk_addr);
+	f2fs_invalidate_blocks(sbi, ni.blk_addr, 1);
 	dec_valid_node_count(sbi, inode, false);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index f35be2c48e3c..69a2027e3ebc 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -899,10 +899,8 @@ skip:
 	 * and the f2fs is not read only, check and fix zoned block devices'
 	 * write pointer consistency.
 	 */
-	if (!err) {
+	if (!err)
 		err = f2fs_check_and_fix_write_pointer(sbi);
-		ret = err;
-	}
 
 	if (!err)
 		clear_sbi_flag(sbi, SBI_POR_DOING);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index eade36c5ef13..c282e8a0a2ec 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -201,6 +201,12 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
 	clear_inode_flag(inode, FI_ATOMIC_FILE);
 	if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
 		clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
+		/*
+		 * The vfs inode keeps clean during commit, but the f2fs inode
+		 * doesn't. So clear the dirty state after commit and let
+		 * f2fs_mark_inode_dirty_sync ensure a consistent dirty state.
+		 */
+		f2fs_inode_synced(inode);
 		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 	stat_dec_atomic_inode(inode);
@@ -245,7 +251,7 @@ retry:
 		if (!__is_valid_data_blkaddr(new_addr)) {
 			if (new_addr == NULL_ADDR)
 				dec_valid_block_count(sbi, inode, 1);
-			f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
+			f2fs_invalidate_blocks(sbi, dn.data_blkaddr, 1);
 			f2fs_update_data_blkaddr(&dn, new_addr);
 		} else {
 			f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
@@ -2426,78 +2432,38 @@ static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr,
 		SIT_I(sbi)->max_mtime = ctime;
 }
 
-static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+/*
+ * NOTE: when updating multiple blocks at the same time, please ensure
+ * that the consecutive input blocks belong to the same segment.
+ */
+static int update_sit_entry_for_release(struct f2fs_sb_info *sbi, struct seg_entry *se,
+				block_t blkaddr, unsigned int offset, int del)
 {
-	struct seg_entry *se;
-	unsigned int segno, offset;
-	long int new_vblocks;
 	bool exist;
 #ifdef CONFIG_F2FS_CHECK_FS
 	bool mir_exist;
 #endif
+	int i;
+	int del_count = -del;
 
-	segno = GET_SEGNO(sbi, blkaddr);
-	if (segno == NULL_SEGNO)
-		return;
-
-	se = get_seg_entry(sbi, segno);
-	new_vblocks = se->valid_blocks + del;
-	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
-
-	f2fs_bug_on(sbi, (new_vblocks < 0 ||
-			(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
-
-	se->valid_blocks = new_vblocks;
-
-	/* Update valid block bitmap */
-	if (del > 0) {
-		exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
-#ifdef CONFIG_F2FS_CHECK_FS
-		mir_exist = f2fs_test_and_set_bit(offset,
-						se->cur_valid_map_mir);
-		if (unlikely(exist != mir_exist)) {
-			f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
-				 blkaddr, exist);
-			f2fs_bug_on(sbi, 1);
-		}
-#endif
-		if (unlikely(exist)) {
-			f2fs_err(sbi, "Bitmap was wrongly set, blk:%u",
-				 blkaddr);
-			f2fs_bug_on(sbi, 1);
-			se->valid_blocks--;
-			del = 0;
-		}
-
-		if (f2fs_block_unit_discard(sbi) &&
-				!f2fs_test_and_set_bit(offset, se->discard_map))
-			sbi->discard_blks--;
+	f2fs_bug_on(sbi, GET_SEGNO(sbi, blkaddr) != GET_SEGNO(sbi, blkaddr + del_count - 1));
 
-		/*
-		 * SSR should never reuse block which is checkpointed
-		 * or newly invalidated.
-		 */
-		if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
-			if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
-				se->ckpt_valid_blocks++;
-		}
-	} else {
-		exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
+	for (i = 0; i < del_count; i++) {
+		exist = f2fs_test_and_clear_bit(offset + i, se->cur_valid_map);
 #ifdef CONFIG_F2FS_CHECK_FS
-		mir_exist = f2fs_test_and_clear_bit(offset,
+		mir_exist = f2fs_test_and_clear_bit(offset + i,
 						se->cur_valid_map_mir);
 		if (unlikely(exist != mir_exist)) {
 			f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d",
-				 blkaddr, exist);
+				blkaddr + i, exist);
 			f2fs_bug_on(sbi, 1);
 		}
 #endif
 		if (unlikely(!exist)) {
-			f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u",
-				 blkaddr);
+			f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", blkaddr + i);
 			f2fs_bug_on(sbi, 1);
 			se->valid_blocks++;
-			del = 0;
+			del += 1;
 		} else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
 			/*
 			 * If checkpoints are off, we must not reuse data that
@@ -2505,7 +2471,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 			 * before, we must track that to know how much space we
 			 * really have.
 			 */
-			if (f2fs_test_bit(offset, se->ckpt_valid_map)) {
+			if (f2fs_test_bit(offset + i, se->ckpt_valid_map)) {
 				spin_lock(&sbi->stat_lock);
 				sbi->unusable_block_count++;
 				spin_unlock(&sbi->stat_lock);
@@ -2513,12 +2479,91 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 		}
 
 		if (f2fs_block_unit_discard(sbi) &&
-			f2fs_test_and_clear_bit(offset, se->discard_map))
+				f2fs_test_and_clear_bit(offset + i, se->discard_map))
 			sbi->discard_blks++;
+
+		if (!f2fs_test_bit(offset + i, se->ckpt_valid_map))
+			se->ckpt_valid_blocks -= 1;
+	}
+
+	return del;
+}
+
+static int update_sit_entry_for_alloc(struct f2fs_sb_info *sbi, struct seg_entry *se,
+				block_t blkaddr, unsigned int offset, int del)
+{
+	bool exist;
+#ifdef CONFIG_F2FS_CHECK_FS
+	bool mir_exist;
+#endif
+
+	exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+	mir_exist = f2fs_test_and_set_bit(offset,
+					se->cur_valid_map_mir);
+	if (unlikely(exist != mir_exist)) {
+		f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
+			blkaddr, exist);
+		f2fs_bug_on(sbi, 1);
 	}
+#endif
+	if (unlikely(exist)) {
+		f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr);
+		f2fs_bug_on(sbi, 1);
+		se->valid_blocks--;
+		del = 0;
+	}
+
+	if (f2fs_block_unit_discard(sbi) &&
+			!f2fs_test_and_set_bit(offset, se->discard_map))
+		sbi->discard_blks--;
+
+	/*
+	 * SSR should never reuse block which is checkpointed
+	 * or newly invalidated.
+	 */
+	if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
+		if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+			se->ckpt_valid_blocks++;
+	}
+
 	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
 		se->ckpt_valid_blocks += del;
 
+	return del;
+}
+
+/*
+ * If releasing blocks, this function supports updating multiple consecutive blocks
+ * at one time, but please note that these consecutive blocks need to belong to the
+ * same segment.
+ */
+static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+{
+	struct seg_entry *se;
+	unsigned int segno, offset;
+	long int new_vblocks;
+
+	segno = GET_SEGNO(sbi, blkaddr);
+	if (segno == NULL_SEGNO)
+		return;
+
+	se = get_seg_entry(sbi, segno);
+	new_vblocks = se->valid_blocks + del;
+	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+	f2fs_bug_on(sbi, (new_vblocks < 0 ||
+			(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
+
+	se->valid_blocks = new_vblocks;
+
+	/* Update valid block bitmap */
+	if (del > 0) {
+		del = update_sit_entry_for_alloc(sbi, se, blkaddr, offset, del);
+	} else {
+		del = update_sit_entry_for_release(sbi, se, blkaddr, offset, del);
+	}
+
 	__mark_sit_entry_dirty(sbi, segno);
 
 	/* update total number of valid blocks to be written in ckpt area */
@@ -2528,25 +2573,43 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 		get_sec_entry(sbi, segno)->valid_blocks += del;
 }
 
-void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr,
+				unsigned int len)
 {
 	unsigned int segno = GET_SEGNO(sbi, addr);
 	struct sit_info *sit_i = SIT_I(sbi);
+	block_t addr_start = addr, addr_end = addr + len - 1;
+	unsigned int seg_num = GET_SEGNO(sbi, addr_end) - segno + 1;
+	unsigned int i = 1, max_blocks = sbi->blocks_per_seg, cnt;
 
 	f2fs_bug_on(sbi, addr == NULL_ADDR);
 	if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
 		return;
 
-	f2fs_invalidate_internal_cache(sbi, addr);
+	f2fs_invalidate_internal_cache(sbi, addr, len);
 
 	/* add it into sit main buffer */
 	down_write(&sit_i->sentry_lock);
 
-	update_segment_mtime(sbi, addr, 0);
-	update_sit_entry(sbi, addr, -1);
+	if (seg_num == 1)
+		cnt = len;
+	else
+		cnt = max_blocks - GET_BLKOFF_FROM_SEG0(sbi, addr);
+
+	do {
+		update_segment_mtime(sbi, addr_start, 0);
+		update_sit_entry(sbi, addr_start, -cnt);
 
-	/* add it into dirty seglist */
-	locate_dirty_segment(sbi, segno);
+		/* add it into dirty seglist */
+		locate_dirty_segment(sbi, segno);
+
+		/* update @addr_start and @cnt and @segno */
+		addr_start = START_BLOCK(sbi, ++segno);
+		if (++i == seg_num)
+			cnt = GET_BLKOFF_FROM_SEG0(sbi, addr_end) + 1;
+		else
+			cnt = max_blocks;
+	} while (i <= seg_num);
 
 	up_write(&sit_i->sentry_lock);
 }
@@ -3857,7 +3920,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 		goto out;
 	}
 	if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
-		f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr);
+		f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr, 1);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_write(fio);
@@ -4049,7 +4112,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		update_sit_entry(sbi, new_blkaddr, 1);
 	}
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
-		f2fs_invalidate_internal_cache(sbi, old_blkaddr);
+		f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1);
 		if (!from_gc)
 			update_segment_mtime(sbi, old_blkaddr, 0);
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -5405,7 +5468,8 @@ int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
 {
 	int ret;
 
-	if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb))
+	if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb) ||
+	    f2fs_hw_is_readonly(sbi))
 		return 0;
 
 	f2fs_notice(sbi, "Checking entire write pointers");
@@ -5492,8 +5556,10 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
 	secno = GET_SEC_FROM_SEG(sbi, segno);
 	start = GET_SEG_FROM_SEC(sbi, secno);
 
-	if (!__is_large_section(sbi))
-		return get_seg_entry(sbi, start + i)->mtime;
+	if (!__is_large_section(sbi)) {
+		mtime = get_seg_entry(sbi, start + i)->mtime;
+		goto out;
+	}
 
 	for (i = 0; i < usable_segs_per_sec; i++) {
 		/* for large section, only check the mtime of valid segments */
@@ -5506,7 +5572,11 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
 	if (total_valid_blocks == 0)
 		return INVALID_MTIME;
 
-	return div_u64(mtime, total_valid_blocks);
+	mtime = div_u64(mtime, total_valid_blocks);
+out:
+	if (unlikely(mtime == INVALID_MTIME))
+		mtime -= 1;
+	return mtime;
 }
 
 /*
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 6b99dc49f776..d15c68b28952 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -1472,7 +1472,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
 			le32_to_cpu(sbi->raw_super->segment_count_main);
 	int i, j;
 
-	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps|mtime\n"
 		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
 
 	for (i = 0; i < total_segs; i++) {
@@ -1482,6 +1482,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
 		seq_printf(seq, "%d|%-3u|", se->type, se->valid_blocks);
 		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
 			seq_printf(seq, " %.2x", se->cur_valid_map[j]);
+		seq_printf(seq, "| %llx", se->mtime);
 		seq_putc(seq, '\n');
 	}
 	return 0;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 15bf32c21ac0..926c26e90ef8 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -43,17 +43,13 @@ static inline void vfat_d_version_set(struct dentry *dentry,
  * If it happened, the negative dentry isn't actually negative
  * anymore.  So, drop it.
  */
-static int vfat_revalidate_shortname(struct dentry *dentry)
+static bool vfat_revalidate_shortname(struct dentry *dentry, struct inode *dir)
 {
-	int ret = 1;
-	spin_lock(&dentry->d_lock);
-	if (!inode_eq_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry)))
-		ret = 0;
-	spin_unlock(&dentry->d_lock);
-	return ret;
+	return inode_eq_iversion(dir, vfat_d_version(dentry));
 }
 
-static int vfat_revalidate(struct dentry *dentry, unsigned int flags)
+static int vfat_revalidate(struct inode *dir, const struct qstr *name,
+			   struct dentry *dentry, unsigned int flags)
 {
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -61,10 +57,11 @@ static int vfat_revalidate(struct dentry *dentry, unsigned int flags)
 	/* This is not negative dentry. Always valid. */
 	if (d_really_is_positive(dentry))
 		return 1;
-	return vfat_revalidate_shortname(dentry);
+	return vfat_revalidate_shortname(dentry, dir);
 }
 
-static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags)
+static int vfat_revalidate_ci(struct inode *dir, const struct qstr *name,
+			      struct dentry *dentry, unsigned int flags)
 {
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -97,7 +94,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags)
 	if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
 		return 0;
 
-	return vfat_revalidate_shortname(dentry);
+	return vfat_revalidate_shortname(dentry, dir);
 }
 
 /* returns the length of a struct qstr, ignoring trailing dots */
diff --git a/fs/file_table.c b/fs/file_table.c
index a32171d2b83f..5c00dc38558d 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -106,7 +106,7 @@ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer,
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_stat_sysctls[] = {
+static const struct ctl_table fs_stat_sysctls[] = {
 	{
 		.procname	= "file-nr",
 		.data		= &files_stat,
@@ -194,6 +194,11 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 	 * refcount bumps we should reinitialize the reused file first.
 	 */
 	file_ref_init(&f->f_ref, 1);
+	/*
+	 * Disable permission and pre-content events for all files by default.
+	 * They may be enabled later by file_set_fsnotify_mode_from_watchers().
+	 */
+	file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
 	return 0;
 }
 
@@ -351,9 +356,7 @@ static struct file *alloc_file(const struct path *path, int flags,
 static inline int alloc_path_pseudo(const char *name, struct inode *inode,
 				    struct vfsmount *mnt, struct path *path)
 {
-	struct qstr this = QSTR_INIT(name, strlen(name));
-
-	path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name));
 	if (!path->dentry)
 		return -ENOMEM;
 	path->mnt = mntget(mnt);
@@ -377,7 +380,13 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 	if (IS_ERR(file)) {
 		ihold(inode);
 		path_put(&path);
+		return file;
 	}
+	/*
+	 * Disable all fsnotify events for pseudo files by default.
+	 * They may be enabled by caller with file_set_fsnotify_mode().
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY);
 	return file;
 }
 EXPORT_SYMBOL(alloc_file_pseudo);
@@ -402,6 +411,11 @@ struct file *alloc_file_pseudo_noaccount(struct inode *inode,
 		return file;
 	}
 	file_init_path(file, &path, fops);
+	/*
+	 * Disable all fsnotify events for pseudo files by default.
+	 * They may be enabled by caller with file_set_fsnotify_mode().
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY);
 	return file;
 }
 EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 8674dbfbe59d..ca215a3cba3e 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -63,3 +63,15 @@ config FUSE_PASSTHROUGH
 	  to be performed directly on a backing file.
 
 	  If you want to allow passthrough operations, answer Y.
+
+config FUSE_IO_URING
+	bool "FUSE communication over io-uring"
+	default y
+	depends on FUSE_FS
+	depends on IO_URING
+	help
+	  This allows sending FUSE requests over the io-uring interface and
+          also adds request core affinity.
+
+	  If you want to allow fuse server/client communication through io-uring,
+	  answer Y
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 2c372180d631..3f0f312a31c1 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -15,5 +15,6 @@ fuse-y += iomode.o
 fuse-$(CONFIG_FUSE_DAX) += dax.o
 fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o
 fuse-$(CONFIG_SYSCTL) += sysctl.o
+fuse-$(CONFIG_FUSE_IO_URING) += dev_uring.o
 
 virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 9abbc2f2894f..0b6ee6dd1fd6 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -240,11 +240,12 @@ static int fuse_send_removemapping(struct inode *inode,
 
 	args.opcode = FUSE_REMOVEMAPPING;
 	args.nodeid = fi->nodeid;
-	args.in_numargs = 2;
-	args.in_args[0].size = sizeof(*inargp);
-	args.in_args[0].value = inargp;
-	args.in_args[1].size = inargp->count * sizeof(*remove_one);
-	args.in_args[1].value = remove_one;
+	args.in_numargs = 3;
+	fuse_set_zero_arg0(&args);
+	args.in_args[1].size = sizeof(*inargp);
+	args.in_args[1].value = inargp;
+	args.in_args[2].size = inargp->count * sizeof(*remove_one);
+	args.in_args[2].value = remove_one;
 	return fuse_simple_request(fm, &args);
 }
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 27ccae63495d..5b5f789b37eb 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -6,7 +6,9 @@
   See the file COPYING.
 */
 
+#include "dev_uring_i.h"
 #include "fuse_i.h"
+#include "fuse_dev_i.h"
 
 #include <linux/init.h>
 #include <linux/module.h>
@@ -28,23 +30,8 @@
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
 
-/* Ordinary requests have even IDs, while interrupts IDs are odd */
-#define FUSE_INT_REQ_BIT (1ULL << 0)
-#define FUSE_REQ_ID_STEP (1ULL << 1)
-
 static struct kmem_cache *fuse_req_cachep;
 
-static void end_requests(struct list_head *head);
-
-static struct fuse_dev *fuse_get_dev(struct file *file)
-{
-	/*
-	 * Lockless access is OK, because file->private data is set
-	 * once during mount and is valid until the file is released.
-	 */
-	return READ_ONCE(file->private_data);
-}
-
 static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req)
 {
 	INIT_LIST_HEAD(&req->list);
@@ -89,7 +76,8 @@ void fuse_set_initialized(struct fuse_conn *fc)
 
 static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
 {
-	return !fc->initialized || (for_background && fc->blocked);
+	return !fc->initialized || (for_background && fc->blocked) ||
+	       (fc->io_uring && !fuse_uring_ready(fc));
 }
 
 static void fuse_drop_waiting(struct fuse_conn *fc)
@@ -234,7 +222,7 @@ u64 fuse_get_unique(struct fuse_iqueue *fiq)
 }
 EXPORT_SYMBOL_GPL(fuse_get_unique);
 
-static unsigned int fuse_req_hash(u64 unique)
+unsigned int fuse_req_hash(u64 unique)
 {
 	return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS);
 }
@@ -250,7 +238,8 @@ __releases(fiq->lock)
 	spin_unlock(&fiq->lock);
 }
 
-static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *forget)
+void fuse_dev_queue_forget(struct fuse_iqueue *fiq,
+			   struct fuse_forget_link *forget)
 {
 	spin_lock(&fiq->lock);
 	if (fiq->connected) {
@@ -263,7 +252,7 @@ static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_li
 	}
 }
 
-static void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
+void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->lock);
 	if (list_empty(&req->intr_entry)) {
@@ -580,7 +569,25 @@ ssize_t __fuse_simple_request(struct mnt_idmap *idmap,
 	return ret;
 }
 
-static bool fuse_request_queue_background(struct fuse_req *req)
+#ifdef CONFIG_FUSE_IO_URING
+static bool fuse_request_queue_background_uring(struct fuse_conn *fc,
+					       struct fuse_req *req)
+{
+	struct fuse_iqueue *fiq = &fc->iq;
+
+	req->in.h.unique = fuse_get_unique(fiq);
+	req->in.h.len = sizeof(struct fuse_in_header) +
+		fuse_len_args(req->args->in_numargs,
+			      (struct fuse_arg *) req->args->in_args);
+
+	return fuse_uring_queue_bq_req(req);
+}
+#endif
+
+/*
+ * @return true if queued
+ */
+static int fuse_request_queue_background(struct fuse_req *req)
 {
 	struct fuse_mount *fm = req->fm;
 	struct fuse_conn *fc = fm->fc;
@@ -592,6 +599,12 @@ static bool fuse_request_queue_background(struct fuse_req *req)
 		atomic_inc(&fc->num_waiting);
 	}
 	__set_bit(FR_ISREPLY, &req->flags);
+
+#ifdef CONFIG_FUSE_IO_URING
+	if (fuse_uring_ready(fc))
+		return fuse_request_queue_background_uring(fc, req);
+#endif
+
 	spin_lock(&fc->bg_lock);
 	if (likely(fc->connected)) {
 		fc->num_background++;
@@ -692,22 +705,8 @@ static int unlock_request(struct fuse_req *req)
 	return err;
 }
 
-struct fuse_copy_state {
-	int write;
-	struct fuse_req *req;
-	struct iov_iter *iter;
-	struct pipe_buffer *pipebufs;
-	struct pipe_buffer *currbuf;
-	struct pipe_inode_info *pipe;
-	unsigned long nr_segs;
-	struct page *pg;
-	unsigned len;
-	unsigned offset;
-	unsigned move_pages:1;
-};
-
-static void fuse_copy_init(struct fuse_copy_state *cs, int write,
-			   struct iov_iter *iter)
+void fuse_copy_init(struct fuse_copy_state *cs, int write,
+		    struct iov_iter *iter)
 {
 	memset(cs, 0, sizeof(*cs));
 	cs->write = write;
@@ -814,6 +813,9 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
 	*size -= ncpy;
 	cs->len -= ncpy;
 	cs->offset += ncpy;
+	if (cs->is_uring)
+		cs->ring.copied_sz += ncpy;
+
 	return ncpy;
 }
 
@@ -1068,9 +1070,9 @@ static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size)
 }
 
 /* Copy request arguments to/from userspace buffer */
-static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
-			  unsigned argpages, struct fuse_arg *args,
-			  int zeroing)
+int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs,
+		   unsigned argpages, struct fuse_arg *args,
+		   int zeroing)
 {
 	int err = 0;
 	unsigned i;
@@ -1760,7 +1762,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	args = &ap->args;
 	args->nodeid = outarg->nodeid;
 	args->opcode = FUSE_NOTIFY_REPLY;
-	args->in_numargs = 2;
+	args->in_numargs = 3;
 	args->in_pages = true;
 	args->end = fuse_retrieve_end;
 
@@ -1788,9 +1790,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 	}
 	ra->inarg.offset = outarg->offset;
 	ra->inarg.size = total_len;
-	args->in_args[0].size = sizeof(ra->inarg);
-	args->in_args[0].value = &ra->inarg;
-	args->in_args[1].size = total_len;
+	fuse_set_zero_arg0(args);
+	args->in_args[1].size = sizeof(ra->inarg);
+	args->in_args[1].value = &ra->inarg;
+	args->in_args[2].size = total_len;
 
 	err = fuse_simple_notify_reply(fm, args, outarg->notify_unique);
 	if (err)
@@ -1885,7 +1888,7 @@ static void fuse_resend(struct fuse_conn *fc)
 		spin_unlock(&fiq->lock);
 		list_for_each_entry(req, &to_queue, list)
 			clear_bit(FR_PENDING, &req->flags);
-		end_requests(&to_queue);
+		fuse_dev_end_requests(&to_queue);
 		return;
 	}
 	/* iq and pq requests are both oldest to newest */
@@ -1934,7 +1937,7 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 }
 
 /* Look up request on processing list by unique ID */
-static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
+struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique)
 {
 	unsigned int hash = fuse_req_hash(unique);
 	struct fuse_req *req;
@@ -1946,10 +1949,17 @@ static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique)
 	return NULL;
 }
 
-static int copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
-			 unsigned nbytes)
+int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
+		       unsigned nbytes)
 {
-	unsigned reqsize = sizeof(struct fuse_out_header);
+
+	unsigned int reqsize = 0;
+
+	/*
+	 * Uring has all headers separated from args - args is payload only
+	 */
+	if (!cs->is_uring)
+		reqsize = sizeof(struct fuse_out_header);
 
 	reqsize += fuse_len_args(args->out_numargs, args->out_args);
 
@@ -2011,7 +2021,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	spin_lock(&fpq->lock);
 	req = NULL;
 	if (fpq->connected)
-		req = request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT);
+		req = fuse_request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT);
 
 	err = -ENOENT;
 	if (!req) {
@@ -2049,7 +2059,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	if (oh.error)
 		err = nbytes != sizeof(oh) ? -EINVAL : 0;
 	else
-		err = copy_out_args(cs, req->args, nbytes);
+		err = fuse_copy_out_args(cs, req->args, nbytes);
 	fuse_copy_finish(cs);
 
 	spin_lock(&fpq->lock);
@@ -2204,7 +2214,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait)
 }
 
 /* Abort all requests on the given list (pending or processing) */
-static void end_requests(struct list_head *head)
+void fuse_dev_end_requests(struct list_head *head)
 {
 	while (!list_empty(head)) {
 		struct fuse_req *req;
@@ -2307,7 +2317,13 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		wake_up_all(&fc->blocked_waitq);
 		spin_unlock(&fc->lock);
 
-		end_requests(&to_end);
+		fuse_dev_end_requests(&to_end);
+
+		/*
+		 * fc->lock must not be taken to avoid conflicts with io-uring
+		 * locks
+		 */
+		fuse_uring_abort(fc);
 	} else {
 		spin_unlock(&fc->lock);
 	}
@@ -2319,6 +2335,8 @@ void fuse_wait_aborted(struct fuse_conn *fc)
 	/* matches implicit memory barrier in fuse_drop_waiting() */
 	smp_mb();
 	wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0);
+
+	fuse_uring_wait_stopped_queues(fc);
 }
 
 int fuse_dev_release(struct inode *inode, struct file *file)
@@ -2337,7 +2355,7 @@ int fuse_dev_release(struct inode *inode, struct file *file)
 			list_splice_init(&fpq->processing[i], &to_end);
 		spin_unlock(&fpq->lock);
 
-		end_requests(&to_end);
+		fuse_dev_end_requests(&to_end);
 
 		/* Are we the last open device? */
 		if (atomic_dec_and_test(&fc->dev_count)) {
@@ -2475,6 +2493,9 @@ const struct file_operations fuse_dev_operations = {
 	.fasync		= fuse_dev_fasync,
 	.unlocked_ioctl = fuse_dev_ioctl,
 	.compat_ioctl   = compat_ptr_ioctl,
+#ifdef CONFIG_FUSE_IO_URING
+	.uring_cmd	= fuse_uring_cmd,
+#endif
 };
 EXPORT_SYMBOL_GPL(fuse_dev_operations);
 
diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c
new file mode 100644
index 000000000000..ebd2931b4f2a
--- /dev/null
+++ b/fs/fuse/dev_uring.c
@@ -0,0 +1,1319 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE: Filesystem in Userspace
+ * Copyright (c) 2023-2024 DataDirect Networks.
+ */
+
+#include "fuse_i.h"
+#include "dev_uring_i.h"
+#include "fuse_dev_i.h"
+
+#include <linux/fs.h>
+#include <linux/io_uring/cmd.h>
+
+static bool __read_mostly enable_uring;
+module_param(enable_uring, bool, 0644);
+MODULE_PARM_DESC(enable_uring,
+		 "Enable userspace communication through io-uring");
+
+#define FUSE_URING_IOV_SEGS 2 /* header and payload */
+
+
+bool fuse_uring_enabled(void)
+{
+	return enable_uring;
+}
+
+struct fuse_uring_pdu {
+	struct fuse_ring_ent *ent;
+};
+
+static const struct fuse_iqueue_ops fuse_io_uring_ops;
+
+static void uring_cmd_set_ring_ent(struct io_uring_cmd *cmd,
+				   struct fuse_ring_ent *ring_ent)
+{
+	struct fuse_uring_pdu *pdu =
+		io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu);
+
+	pdu->ent = ring_ent;
+}
+
+static struct fuse_ring_ent *uring_cmd_to_ring_ent(struct io_uring_cmd *cmd)
+{
+	struct fuse_uring_pdu *pdu =
+		io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu);
+
+	return pdu->ent;
+}
+
+static void fuse_uring_flush_bg(struct fuse_ring_queue *queue)
+{
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_conn *fc = ring->fc;
+
+	lockdep_assert_held(&queue->lock);
+	lockdep_assert_held(&fc->bg_lock);
+
+	/*
+	 * Allow one bg request per queue, ignoring global fc limits.
+	 * This prevents a single queue from consuming all resources and
+	 * eliminates the need for remote queue wake-ups when global
+	 * limits are met but this queue has no more waiting requests.
+	 */
+	while ((fc->active_background < fc->max_background ||
+		!queue->active_background) &&
+	       (!list_empty(&queue->fuse_req_bg_queue))) {
+		struct fuse_req *req;
+
+		req = list_first_entry(&queue->fuse_req_bg_queue,
+				       struct fuse_req, list);
+		fc->active_background++;
+		queue->active_background++;
+
+		list_move_tail(&req->list, &queue->fuse_req_queue);
+	}
+}
+
+static void fuse_uring_req_end(struct fuse_ring_ent *ent, struct fuse_req *req,
+			       int error)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_conn *fc = ring->fc;
+
+	lockdep_assert_not_held(&queue->lock);
+	spin_lock(&queue->lock);
+	ent->fuse_req = NULL;
+	if (test_bit(FR_BACKGROUND, &req->flags)) {
+		queue->active_background--;
+		spin_lock(&fc->bg_lock);
+		fuse_uring_flush_bg(queue);
+		spin_unlock(&fc->bg_lock);
+	}
+
+	spin_unlock(&queue->lock);
+
+	if (error)
+		req->out.h.error = error;
+
+	clear_bit(FR_SENT, &req->flags);
+	fuse_request_end(req);
+}
+
+/* Abort all list queued request on the given ring queue */
+static void fuse_uring_abort_end_queue_requests(struct fuse_ring_queue *queue)
+{
+	struct fuse_req *req;
+	LIST_HEAD(req_list);
+
+	spin_lock(&queue->lock);
+	list_for_each_entry(req, &queue->fuse_req_queue, list)
+		clear_bit(FR_PENDING, &req->flags);
+	list_splice_init(&queue->fuse_req_queue, &req_list);
+	spin_unlock(&queue->lock);
+
+	/* must not hold queue lock to avoid order issues with fi->lock */
+	fuse_dev_end_requests(&req_list);
+}
+
+void fuse_uring_abort_end_requests(struct fuse_ring *ring)
+{
+	int qid;
+	struct fuse_ring_queue *queue;
+	struct fuse_conn *fc = ring->fc;
+
+	for (qid = 0; qid < ring->nr_queues; qid++) {
+		queue = READ_ONCE(ring->queues[qid]);
+		if (!queue)
+			continue;
+
+		queue->stopped = true;
+
+		WARN_ON_ONCE(ring->fc->max_background != UINT_MAX);
+		spin_lock(&queue->lock);
+		spin_lock(&fc->bg_lock);
+		fuse_uring_flush_bg(queue);
+		spin_unlock(&fc->bg_lock);
+		spin_unlock(&queue->lock);
+		fuse_uring_abort_end_queue_requests(queue);
+	}
+}
+
+void fuse_uring_destruct(struct fuse_conn *fc)
+{
+	struct fuse_ring *ring = fc->ring;
+	int qid;
+
+	if (!ring)
+		return;
+
+	for (qid = 0; qid < ring->nr_queues; qid++) {
+		struct fuse_ring_queue *queue = ring->queues[qid];
+		struct fuse_ring_ent *ent, *next;
+
+		if (!queue)
+			continue;
+
+		WARN_ON(!list_empty(&queue->ent_avail_queue));
+		WARN_ON(!list_empty(&queue->ent_w_req_queue));
+		WARN_ON(!list_empty(&queue->ent_commit_queue));
+		WARN_ON(!list_empty(&queue->ent_in_userspace));
+
+		list_for_each_entry_safe(ent, next, &queue->ent_released,
+					 list) {
+			list_del_init(&ent->list);
+			kfree(ent);
+		}
+
+		kfree(queue->fpq.processing);
+		kfree(queue);
+		ring->queues[qid] = NULL;
+	}
+
+	kfree(ring->queues);
+	kfree(ring);
+	fc->ring = NULL;
+}
+
+/*
+ * Basic ring setup for this connection based on the provided configuration
+ */
+static struct fuse_ring *fuse_uring_create(struct fuse_conn *fc)
+{
+	struct fuse_ring *ring;
+	size_t nr_queues = num_possible_cpus();
+	struct fuse_ring *res = NULL;
+	size_t max_payload_size;
+
+	ring = kzalloc(sizeof(*fc->ring), GFP_KERNEL_ACCOUNT);
+	if (!ring)
+		return NULL;
+
+	ring->queues = kcalloc(nr_queues, sizeof(struct fuse_ring_queue *),
+			       GFP_KERNEL_ACCOUNT);
+	if (!ring->queues)
+		goto out_err;
+
+	max_payload_size = max(FUSE_MIN_READ_BUFFER, fc->max_write);
+	max_payload_size = max(max_payload_size, fc->max_pages * PAGE_SIZE);
+
+	spin_lock(&fc->lock);
+	if (fc->ring) {
+		/* race, another thread created the ring in the meantime */
+		spin_unlock(&fc->lock);
+		res = fc->ring;
+		goto out_err;
+	}
+
+	init_waitqueue_head(&ring->stop_waitq);
+
+	fc->ring = ring;
+	ring->nr_queues = nr_queues;
+	ring->fc = fc;
+	ring->max_payload_sz = max_payload_size;
+	atomic_set(&ring->queue_refs, 0);
+
+	spin_unlock(&fc->lock);
+	return ring;
+
+out_err:
+	kfree(ring->queues);
+	kfree(ring);
+	return res;
+}
+
+static struct fuse_ring_queue *fuse_uring_create_queue(struct fuse_ring *ring,
+						       int qid)
+{
+	struct fuse_conn *fc = ring->fc;
+	struct fuse_ring_queue *queue;
+	struct list_head *pq;
+
+	queue = kzalloc(sizeof(*queue), GFP_KERNEL_ACCOUNT);
+	if (!queue)
+		return NULL;
+	pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL);
+	if (!pq) {
+		kfree(queue);
+		return NULL;
+	}
+
+	queue->qid = qid;
+	queue->ring = ring;
+	spin_lock_init(&queue->lock);
+
+	INIT_LIST_HEAD(&queue->ent_avail_queue);
+	INIT_LIST_HEAD(&queue->ent_commit_queue);
+	INIT_LIST_HEAD(&queue->ent_w_req_queue);
+	INIT_LIST_HEAD(&queue->ent_in_userspace);
+	INIT_LIST_HEAD(&queue->fuse_req_queue);
+	INIT_LIST_HEAD(&queue->fuse_req_bg_queue);
+	INIT_LIST_HEAD(&queue->ent_released);
+
+	queue->fpq.processing = pq;
+	fuse_pqueue_init(&queue->fpq);
+
+	spin_lock(&fc->lock);
+	if (ring->queues[qid]) {
+		spin_unlock(&fc->lock);
+		kfree(queue->fpq.processing);
+		kfree(queue);
+		return ring->queues[qid];
+	}
+
+	/*
+	 * write_once and lock as the caller mostly doesn't take the lock at all
+	 */
+	WRITE_ONCE(ring->queues[qid], queue);
+	spin_unlock(&fc->lock);
+
+	return queue;
+}
+
+static void fuse_uring_stop_fuse_req_end(struct fuse_req *req)
+{
+	clear_bit(FR_SENT, &req->flags);
+	req->out.h.error = -ECONNABORTED;
+	fuse_request_end(req);
+}
+
+/*
+ * Release a request/entry on connection tear down
+ */
+static void fuse_uring_entry_teardown(struct fuse_ring_ent *ent)
+{
+	struct fuse_req *req;
+	struct io_uring_cmd *cmd;
+
+	struct fuse_ring_queue *queue = ent->queue;
+
+	spin_lock(&queue->lock);
+	cmd = ent->cmd;
+	ent->cmd = NULL;
+	req = ent->fuse_req;
+	ent->fuse_req = NULL;
+	if (req) {
+		/* remove entry from queue->fpq->processing */
+		list_del_init(&req->list);
+	}
+
+	/*
+	 * The entry must not be freed immediately, due to access of direct
+	 * pointer access of entries through IO_URING_F_CANCEL - there is a risk
+	 * of race between daemon termination (which triggers IO_URING_F_CANCEL
+	 * and accesses entries without checking the list state first
+	 */
+	list_move(&ent->list, &queue->ent_released);
+	ent->state = FRRS_RELEASED;
+	spin_unlock(&queue->lock);
+
+	if (cmd)
+		io_uring_cmd_done(cmd, -ENOTCONN, 0, IO_URING_F_UNLOCKED);
+
+	if (req)
+		fuse_uring_stop_fuse_req_end(req);
+}
+
+static void fuse_uring_stop_list_entries(struct list_head *head,
+					 struct fuse_ring_queue *queue,
+					 enum fuse_ring_req_state exp_state)
+{
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_ring_ent *ent, *next;
+	ssize_t queue_refs = SSIZE_MAX;
+	LIST_HEAD(to_teardown);
+
+	spin_lock(&queue->lock);
+	list_for_each_entry_safe(ent, next, head, list) {
+		if (ent->state != exp_state) {
+			pr_warn("entry teardown qid=%d state=%d expected=%d",
+				queue->qid, ent->state, exp_state);
+			continue;
+		}
+
+		ent->state = FRRS_TEARDOWN;
+		list_move(&ent->list, &to_teardown);
+	}
+	spin_unlock(&queue->lock);
+
+	/* no queue lock to avoid lock order issues */
+	list_for_each_entry_safe(ent, next, &to_teardown, list) {
+		fuse_uring_entry_teardown(ent);
+		queue_refs = atomic_dec_return(&ring->queue_refs);
+		WARN_ON_ONCE(queue_refs < 0);
+	}
+}
+
+static void fuse_uring_teardown_entries(struct fuse_ring_queue *queue)
+{
+	fuse_uring_stop_list_entries(&queue->ent_in_userspace, queue,
+				     FRRS_USERSPACE);
+	fuse_uring_stop_list_entries(&queue->ent_avail_queue, queue,
+				     FRRS_AVAILABLE);
+}
+
+/*
+ * Log state debug info
+ */
+static void fuse_uring_log_ent_state(struct fuse_ring *ring)
+{
+	int qid;
+	struct fuse_ring_ent *ent;
+
+	for (qid = 0; qid < ring->nr_queues; qid++) {
+		struct fuse_ring_queue *queue = ring->queues[qid];
+
+		if (!queue)
+			continue;
+
+		spin_lock(&queue->lock);
+		/*
+		 * Log entries from the intermediate queue, the other queues
+		 * should be empty
+		 */
+		list_for_each_entry(ent, &queue->ent_w_req_queue, list) {
+			pr_info(" ent-req-queue ring=%p qid=%d ent=%p state=%d\n",
+				ring, qid, ent, ent->state);
+		}
+		list_for_each_entry(ent, &queue->ent_commit_queue, list) {
+			pr_info(" ent-commit-queue ring=%p qid=%d ent=%p state=%d\n",
+				ring, qid, ent, ent->state);
+		}
+		spin_unlock(&queue->lock);
+	}
+	ring->stop_debug_log = 1;
+}
+
+static void fuse_uring_async_stop_queues(struct work_struct *work)
+{
+	int qid;
+	struct fuse_ring *ring =
+		container_of(work, struct fuse_ring, async_teardown_work.work);
+
+	/* XXX code dup */
+	for (qid = 0; qid < ring->nr_queues; qid++) {
+		struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]);
+
+		if (!queue)
+			continue;
+
+		fuse_uring_teardown_entries(queue);
+	}
+
+	/*
+	 * Some ring entries might be in the middle of IO operations,
+	 * i.e. in process to get handled by file_operations::uring_cmd
+	 * or on the way to userspace - we could handle that with conditions in
+	 * run time code, but easier/cleaner to have an async tear down handler
+	 * If there are still queue references left
+	 */
+	if (atomic_read(&ring->queue_refs) > 0) {
+		if (time_after(jiffies,
+			       ring->teardown_time + FUSE_URING_TEARDOWN_TIMEOUT))
+			fuse_uring_log_ent_state(ring);
+
+		schedule_delayed_work(&ring->async_teardown_work,
+				      FUSE_URING_TEARDOWN_INTERVAL);
+	} else {
+		wake_up_all(&ring->stop_waitq);
+	}
+}
+
+/*
+ * Stop the ring queues
+ */
+void fuse_uring_stop_queues(struct fuse_ring *ring)
+{
+	int qid;
+
+	for (qid = 0; qid < ring->nr_queues; qid++) {
+		struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]);
+
+		if (!queue)
+			continue;
+
+		fuse_uring_teardown_entries(queue);
+	}
+
+	if (atomic_read(&ring->queue_refs) > 0) {
+		ring->teardown_time = jiffies;
+		INIT_DELAYED_WORK(&ring->async_teardown_work,
+				  fuse_uring_async_stop_queues);
+		schedule_delayed_work(&ring->async_teardown_work,
+				      FUSE_URING_TEARDOWN_INTERVAL);
+	} else {
+		wake_up_all(&ring->stop_waitq);
+	}
+}
+
+/*
+ * Handle IO_URING_F_CANCEL, typically should come on daemon termination.
+ *
+ * Releasing the last entry should trigger fuse_dev_release() if
+ * the daemon was terminated
+ */
+static void fuse_uring_cancel(struct io_uring_cmd *cmd,
+			      unsigned int issue_flags)
+{
+	struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd);
+	struct fuse_ring_queue *queue;
+	bool need_cmd_done = false;
+
+	/*
+	 * direct access on ent - it must not be destructed as long as
+	 * IO_URING_F_CANCEL might come up
+	 */
+	queue = ent->queue;
+	spin_lock(&queue->lock);
+	if (ent->state == FRRS_AVAILABLE) {
+		ent->state = FRRS_USERSPACE;
+		list_move(&ent->list, &queue->ent_in_userspace);
+		need_cmd_done = true;
+		ent->cmd = NULL;
+	}
+	spin_unlock(&queue->lock);
+
+	if (need_cmd_done) {
+		/* no queue lock to avoid lock order issues */
+		io_uring_cmd_done(cmd, -ENOTCONN, 0, issue_flags);
+	}
+}
+
+static void fuse_uring_prepare_cancel(struct io_uring_cmd *cmd, int issue_flags,
+				      struct fuse_ring_ent *ring_ent)
+{
+	uring_cmd_set_ring_ent(cmd, ring_ent);
+	io_uring_cmd_mark_cancelable(cmd, issue_flags);
+}
+
+/*
+ * Checks for errors and stores it into the request
+ */
+static int fuse_uring_out_header_has_err(struct fuse_out_header *oh,
+					 struct fuse_req *req,
+					 struct fuse_conn *fc)
+{
+	int err;
+
+	err = -EINVAL;
+	if (oh->unique == 0) {
+		/* Not supported through io-uring yet */
+		pr_warn_once("notify through fuse-io-uring not supported\n");
+		goto err;
+	}
+
+	if (oh->error <= -ERESTARTSYS || oh->error > 0)
+		goto err;
+
+	if (oh->error) {
+		err = oh->error;
+		goto err;
+	}
+
+	err = -ENOENT;
+	if ((oh->unique & ~FUSE_INT_REQ_BIT) != req->in.h.unique) {
+		pr_warn_ratelimited("unique mismatch, expected: %llu got %llu\n",
+				    req->in.h.unique,
+				    oh->unique & ~FUSE_INT_REQ_BIT);
+		goto err;
+	}
+
+	/*
+	 * Is it an interrupt reply ID?
+	 * XXX: Not supported through fuse-io-uring yet, it should not even
+	 *      find the request - should not happen.
+	 */
+	WARN_ON_ONCE(oh->unique & FUSE_INT_REQ_BIT);
+
+	err = 0;
+err:
+	return err;
+}
+
+static int fuse_uring_copy_from_ring(struct fuse_ring *ring,
+				     struct fuse_req *req,
+				     struct fuse_ring_ent *ent)
+{
+	struct fuse_copy_state cs;
+	struct fuse_args *args = req->args;
+	struct iov_iter iter;
+	int err;
+	struct fuse_uring_ent_in_out ring_in_out;
+
+	err = copy_from_user(&ring_in_out, &ent->headers->ring_ent_in_out,
+			     sizeof(ring_in_out));
+	if (err)
+		return -EFAULT;
+
+	err = import_ubuf(ITER_SOURCE, ent->payload, ring->max_payload_sz,
+			  &iter);
+	if (err)
+		return err;
+
+	fuse_copy_init(&cs, 0, &iter);
+	cs.is_uring = 1;
+	cs.req = req;
+
+	return fuse_copy_out_args(&cs, args, ring_in_out.payload_sz);
+}
+
+ /*
+  * Copy data from the req to the ring buffer
+  */
+static int fuse_uring_args_to_ring(struct fuse_ring *ring, struct fuse_req *req,
+				   struct fuse_ring_ent *ent)
+{
+	struct fuse_copy_state cs;
+	struct fuse_args *args = req->args;
+	struct fuse_in_arg *in_args = args->in_args;
+	int num_args = args->in_numargs;
+	int err;
+	struct iov_iter iter;
+	struct fuse_uring_ent_in_out ent_in_out = {
+		.flags = 0,
+		.commit_id = req->in.h.unique,
+	};
+
+	err = import_ubuf(ITER_DEST, ent->payload, ring->max_payload_sz, &iter);
+	if (err) {
+		pr_info_ratelimited("fuse: Import of user buffer failed\n");
+		return err;
+	}
+
+	fuse_copy_init(&cs, 1, &iter);
+	cs.is_uring = 1;
+	cs.req = req;
+
+	if (num_args > 0) {
+		/*
+		 * Expectation is that the first argument is the per op header.
+		 * Some op code have that as zero size.
+		 */
+		if (args->in_args[0].size > 0) {
+			err = copy_to_user(&ent->headers->op_in, in_args->value,
+					   in_args->size);
+			if (err) {
+				pr_info_ratelimited(
+					"Copying the header failed.\n");
+				return -EFAULT;
+			}
+		}
+		in_args++;
+		num_args--;
+	}
+
+	/* copy the payload */
+	err = fuse_copy_args(&cs, num_args, args->in_pages,
+			     (struct fuse_arg *)in_args, 0);
+	if (err) {
+		pr_info_ratelimited("%s fuse_copy_args failed\n", __func__);
+		return err;
+	}
+
+	ent_in_out.payload_sz = cs.ring.copied_sz;
+	err = copy_to_user(&ent->headers->ring_ent_in_out, &ent_in_out,
+			   sizeof(ent_in_out));
+	return err ? -EFAULT : 0;
+}
+
+static int fuse_uring_copy_to_ring(struct fuse_ring_ent *ent,
+				   struct fuse_req *req)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+	struct fuse_ring *ring = queue->ring;
+	int err;
+
+	err = -EIO;
+	if (WARN_ON(ent->state != FRRS_FUSE_REQ)) {
+		pr_err("qid=%d ring-req=%p invalid state %d on send\n",
+		       queue->qid, ent, ent->state);
+		return err;
+	}
+
+	err = -EINVAL;
+	if (WARN_ON(req->in.h.unique == 0))
+		return err;
+
+	/* copy the request */
+	err = fuse_uring_args_to_ring(ring, req, ent);
+	if (unlikely(err)) {
+		pr_info_ratelimited("Copy to ring failed: %d\n", err);
+		return err;
+	}
+
+	/* copy fuse_in_header */
+	err = copy_to_user(&ent->headers->in_out, &req->in.h,
+			   sizeof(req->in.h));
+	if (err) {
+		err = -EFAULT;
+		return err;
+	}
+
+	return 0;
+}
+
+static int fuse_uring_prepare_send(struct fuse_ring_ent *ent,
+				   struct fuse_req *req)
+{
+	int err;
+
+	err = fuse_uring_copy_to_ring(ent, req);
+	if (!err)
+		set_bit(FR_SENT, &req->flags);
+	else
+		fuse_uring_req_end(ent, req, err);
+
+	return err;
+}
+
+/*
+ * Write data to the ring buffer and send the request to userspace,
+ * userspace will read it
+ * This is comparable with classical read(/dev/fuse)
+ */
+static int fuse_uring_send_next_to_ring(struct fuse_ring_ent *ent,
+					struct fuse_req *req,
+					unsigned int issue_flags)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+	int err;
+	struct io_uring_cmd *cmd;
+
+	err = fuse_uring_prepare_send(ent, req);
+	if (err)
+		return err;
+
+	spin_lock(&queue->lock);
+	cmd = ent->cmd;
+	ent->cmd = NULL;
+	ent->state = FRRS_USERSPACE;
+	list_move(&ent->list, &queue->ent_in_userspace);
+	spin_unlock(&queue->lock);
+
+	io_uring_cmd_done(cmd, 0, 0, issue_flags);
+	return 0;
+}
+
+/*
+ * Make a ring entry available for fuse_req assignment
+ */
+static void fuse_uring_ent_avail(struct fuse_ring_ent *ent,
+				 struct fuse_ring_queue *queue)
+{
+	WARN_ON_ONCE(!ent->cmd);
+	list_move(&ent->list, &queue->ent_avail_queue);
+	ent->state = FRRS_AVAILABLE;
+}
+
+/* Used to find the request on SQE commit */
+static void fuse_uring_add_to_pq(struct fuse_ring_ent *ent,
+				 struct fuse_req *req)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+	struct fuse_pqueue *fpq = &queue->fpq;
+	unsigned int hash;
+
+	req->ring_entry = ent;
+	hash = fuse_req_hash(req->in.h.unique);
+	list_move_tail(&req->list, &fpq->processing[hash]);
+}
+
+/*
+ * Assign a fuse queue entry to the given entry
+ */
+static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ent,
+					   struct fuse_req *req)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+	struct fuse_conn *fc = req->fm->fc;
+	struct fuse_iqueue *fiq = &fc->iq;
+
+	lockdep_assert_held(&queue->lock);
+
+	if (WARN_ON_ONCE(ent->state != FRRS_AVAILABLE &&
+			 ent->state != FRRS_COMMIT)) {
+		pr_warn("%s qid=%d state=%d\n", __func__, ent->queue->qid,
+			ent->state);
+	}
+
+	spin_lock(&fiq->lock);
+	clear_bit(FR_PENDING, &req->flags);
+	spin_unlock(&fiq->lock);
+	ent->fuse_req = req;
+	ent->state = FRRS_FUSE_REQ;
+	list_move(&ent->list, &queue->ent_w_req_queue);
+	fuse_uring_add_to_pq(ent, req);
+}
+
+/* Fetch the next fuse request if available */
+static struct fuse_req *fuse_uring_ent_assign_req(struct fuse_ring_ent *ent)
+	__must_hold(&queue->lock)
+{
+	struct fuse_req *req;
+	struct fuse_ring_queue *queue = ent->queue;
+	struct list_head *req_queue = &queue->fuse_req_queue;
+
+	lockdep_assert_held(&queue->lock);
+
+	/* get and assign the next entry while it is still holding the lock */
+	req = list_first_entry_or_null(req_queue, struct fuse_req, list);
+	if (req)
+		fuse_uring_add_req_to_ring_ent(ent, req);
+
+	return req;
+}
+
+/*
+ * Read data from the ring buffer, which user space has written to
+ * This is comparible with handling of classical write(/dev/fuse).
+ * Also make the ring request available again for new fuse requests.
+ */
+static void fuse_uring_commit(struct fuse_ring_ent *ent, struct fuse_req *req,
+			      unsigned int issue_flags)
+{
+	struct fuse_ring *ring = ent->queue->ring;
+	struct fuse_conn *fc = ring->fc;
+	ssize_t err = 0;
+
+	err = copy_from_user(&req->out.h, &ent->headers->in_out,
+			     sizeof(req->out.h));
+	if (err) {
+		req->out.h.error = -EFAULT;
+		goto out;
+	}
+
+	err = fuse_uring_out_header_has_err(&req->out.h, req, fc);
+	if (err) {
+		/* req->out.h.error already set */
+		goto out;
+	}
+
+	err = fuse_uring_copy_from_ring(ring, req, ent);
+out:
+	fuse_uring_req_end(ent, req, err);
+}
+
+/*
+ * Get the next fuse req and send it
+ */
+static void fuse_uring_next_fuse_req(struct fuse_ring_ent *ent,
+				     struct fuse_ring_queue *queue,
+				     unsigned int issue_flags)
+{
+	int err;
+	struct fuse_req *req;
+
+retry:
+	spin_lock(&queue->lock);
+	fuse_uring_ent_avail(ent, queue);
+	req = fuse_uring_ent_assign_req(ent);
+	spin_unlock(&queue->lock);
+
+	if (req) {
+		err = fuse_uring_send_next_to_ring(ent, req, issue_flags);
+		if (err)
+			goto retry;
+	}
+}
+
+static int fuse_ring_ent_set_commit(struct fuse_ring_ent *ent)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+
+	lockdep_assert_held(&queue->lock);
+
+	if (WARN_ON_ONCE(ent->state != FRRS_USERSPACE))
+		return -EIO;
+
+	ent->state = FRRS_COMMIT;
+	list_move(&ent->list, &queue->ent_commit_queue);
+
+	return 0;
+}
+
+/* FUSE_URING_CMD_COMMIT_AND_FETCH handler */
+static int fuse_uring_commit_fetch(struct io_uring_cmd *cmd, int issue_flags,
+				   struct fuse_conn *fc)
+{
+	const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe);
+	struct fuse_ring_ent *ent;
+	int err;
+	struct fuse_ring *ring = fc->ring;
+	struct fuse_ring_queue *queue;
+	uint64_t commit_id = READ_ONCE(cmd_req->commit_id);
+	unsigned int qid = READ_ONCE(cmd_req->qid);
+	struct fuse_pqueue *fpq;
+	struct fuse_req *req;
+
+	err = -ENOTCONN;
+	if (!ring)
+		return err;
+
+	if (qid >= ring->nr_queues)
+		return -EINVAL;
+
+	queue = ring->queues[qid];
+	if (!queue)
+		return err;
+	fpq = &queue->fpq;
+
+	if (!READ_ONCE(fc->connected) || READ_ONCE(queue->stopped))
+		return err;
+
+	spin_lock(&queue->lock);
+	/* Find a request based on the unique ID of the fuse request
+	 * This should get revised, as it needs a hash calculation and list
+	 * search. And full struct fuse_pqueue is needed (memory overhead).
+	 * As well as the link from req to ring_ent.
+	 */
+	req = fuse_request_find(fpq, commit_id);
+	err = -ENOENT;
+	if (!req) {
+		pr_info("qid=%d commit_id %llu not found\n", queue->qid,
+			commit_id);
+		spin_unlock(&queue->lock);
+		return err;
+	}
+	list_del_init(&req->list);
+	ent = req->ring_entry;
+	req->ring_entry = NULL;
+
+	err = fuse_ring_ent_set_commit(ent);
+	if (err != 0) {
+		pr_info_ratelimited("qid=%d commit_id %llu state %d",
+				    queue->qid, commit_id, ent->state);
+		spin_unlock(&queue->lock);
+		req->out.h.error = err;
+		clear_bit(FR_SENT, &req->flags);
+		fuse_request_end(req);
+		return err;
+	}
+
+	ent->cmd = cmd;
+	spin_unlock(&queue->lock);
+
+	/* without the queue lock, as other locks are taken */
+	fuse_uring_prepare_cancel(cmd, issue_flags, ent);
+	fuse_uring_commit(ent, req, issue_flags);
+
+	/*
+	 * Fetching the next request is absolutely required as queued
+	 * fuse requests would otherwise not get processed - committing
+	 * and fetching is done in one step vs legacy fuse, which has separated
+	 * read (fetch request) and write (commit result).
+	 */
+	fuse_uring_next_fuse_req(ent, queue, issue_flags);
+	return 0;
+}
+
+static bool is_ring_ready(struct fuse_ring *ring, int current_qid)
+{
+	int qid;
+	struct fuse_ring_queue *queue;
+	bool ready = true;
+
+	for (qid = 0; qid < ring->nr_queues && ready; qid++) {
+		if (current_qid == qid)
+			continue;
+
+		queue = ring->queues[qid];
+		if (!queue) {
+			ready = false;
+			break;
+		}
+
+		spin_lock(&queue->lock);
+		if (list_empty(&queue->ent_avail_queue))
+			ready = false;
+		spin_unlock(&queue->lock);
+	}
+
+	return ready;
+}
+
+/*
+ * fuse_uring_req_fetch command handling
+ */
+static void fuse_uring_do_register(struct fuse_ring_ent *ent,
+				   struct io_uring_cmd *cmd,
+				   unsigned int issue_flags)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_conn *fc = ring->fc;
+	struct fuse_iqueue *fiq = &fc->iq;
+
+	fuse_uring_prepare_cancel(cmd, issue_flags, ent);
+
+	spin_lock(&queue->lock);
+	ent->cmd = cmd;
+	fuse_uring_ent_avail(ent, queue);
+	spin_unlock(&queue->lock);
+
+	if (!ring->ready) {
+		bool ready = is_ring_ready(ring, queue->qid);
+
+		if (ready) {
+			WRITE_ONCE(fiq->ops, &fuse_io_uring_ops);
+			WRITE_ONCE(ring->ready, true);
+			wake_up_all(&fc->blocked_waitq);
+		}
+	}
+}
+
+/*
+ * sqe->addr is a ptr to an iovec array, iov[0] has the headers, iov[1]
+ * the payload
+ */
+static int fuse_uring_get_iovec_from_sqe(const struct io_uring_sqe *sqe,
+					 struct iovec iov[FUSE_URING_IOV_SEGS])
+{
+	struct iovec __user *uiov = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	struct iov_iter iter;
+	ssize_t ret;
+
+	if (sqe->len != FUSE_URING_IOV_SEGS)
+		return -EINVAL;
+
+	/*
+	 * Direction for buffer access will actually be READ and WRITE,
+	 * using write for the import should include READ access as well.
+	 */
+	ret = import_iovec(WRITE, uiov, FUSE_URING_IOV_SEGS,
+			   FUSE_URING_IOV_SEGS, &iov, &iter);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static struct fuse_ring_ent *
+fuse_uring_create_ring_ent(struct io_uring_cmd *cmd,
+			   struct fuse_ring_queue *queue)
+{
+	struct fuse_ring *ring = queue->ring;
+	struct fuse_ring_ent *ent;
+	size_t payload_size;
+	struct iovec iov[FUSE_URING_IOV_SEGS];
+	int err;
+
+	err = fuse_uring_get_iovec_from_sqe(cmd->sqe, iov);
+	if (err) {
+		pr_info_ratelimited("Failed to get iovec from sqe, err=%d\n",
+				    err);
+		return ERR_PTR(err);
+	}
+
+	err = -EINVAL;
+	if (iov[0].iov_len < sizeof(struct fuse_uring_req_header)) {
+		pr_info_ratelimited("Invalid header len %zu\n", iov[0].iov_len);
+		return ERR_PTR(err);
+	}
+
+	payload_size = iov[1].iov_len;
+	if (payload_size < ring->max_payload_sz) {
+		pr_info_ratelimited("Invalid req payload len %zu\n",
+				    payload_size);
+		return ERR_PTR(err);
+	}
+
+	err = -ENOMEM;
+	ent = kzalloc(sizeof(*ent), GFP_KERNEL_ACCOUNT);
+	if (!ent)
+		return ERR_PTR(err);
+
+	INIT_LIST_HEAD(&ent->list);
+
+	ent->queue = queue;
+	ent->headers = iov[0].iov_base;
+	ent->payload = iov[1].iov_base;
+
+	atomic_inc(&ring->queue_refs);
+	return ent;
+}
+
+/*
+ * Register header and payload buffer with the kernel and puts the
+ * entry as "ready to get fuse requests" on the queue
+ */
+static int fuse_uring_register(struct io_uring_cmd *cmd,
+			       unsigned int issue_flags, struct fuse_conn *fc)
+{
+	const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe);
+	struct fuse_ring *ring = fc->ring;
+	struct fuse_ring_queue *queue;
+	struct fuse_ring_ent *ent;
+	int err;
+	unsigned int qid = READ_ONCE(cmd_req->qid);
+
+	err = -ENOMEM;
+	if (!ring) {
+		ring = fuse_uring_create(fc);
+		if (!ring)
+			return err;
+	}
+
+	if (qid >= ring->nr_queues) {
+		pr_info_ratelimited("fuse: Invalid ring qid %u\n", qid);
+		return -EINVAL;
+	}
+
+	queue = ring->queues[qid];
+	if (!queue) {
+		queue = fuse_uring_create_queue(ring, qid);
+		if (!queue)
+			return err;
+	}
+
+	/*
+	 * The created queue above does not need to be destructed in
+	 * case of entry errors below, will be done at ring destruction time.
+	 */
+
+	ent = fuse_uring_create_ring_ent(cmd, queue);
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
+
+	fuse_uring_do_register(ent, cmd, issue_flags);
+
+	return 0;
+}
+
+/*
+ * Entry function from io_uring to handle the given passthrough command
+ * (op code IORING_OP_URING_CMD)
+ */
+int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
+{
+	struct fuse_dev *fud;
+	struct fuse_conn *fc;
+	u32 cmd_op = cmd->cmd_op;
+	int err;
+
+	if ((unlikely(issue_flags & IO_URING_F_CANCEL))) {
+		fuse_uring_cancel(cmd, issue_flags);
+		return 0;
+	}
+
+	/* This extra SQE size holds struct fuse_uring_cmd_req */
+	if (!(issue_flags & IO_URING_F_SQE128))
+		return -EINVAL;
+
+	fud = fuse_get_dev(cmd->file);
+	if (!fud) {
+		pr_info_ratelimited("No fuse device found\n");
+		return -ENOTCONN;
+	}
+	fc = fud->fc;
+
+	/* Once a connection has io-uring enabled on it, it can't be disabled */
+	if (!enable_uring && !fc->io_uring) {
+		pr_info_ratelimited("fuse-io-uring is disabled\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (fc->aborted)
+		return -ECONNABORTED;
+	if (!fc->connected)
+		return -ENOTCONN;
+
+	/*
+	 * fuse_uring_register() needs the ring to be initialized,
+	 * we need to know the max payload size
+	 */
+	if (!fc->initialized)
+		return -EAGAIN;
+
+	switch (cmd_op) {
+	case FUSE_IO_URING_CMD_REGISTER:
+		err = fuse_uring_register(cmd, issue_flags, fc);
+		if (err) {
+			pr_info_once("FUSE_IO_URING_CMD_REGISTER failed err=%d\n",
+				     err);
+			fc->io_uring = 0;
+			wake_up_all(&fc->blocked_waitq);
+			return err;
+		}
+		break;
+	case FUSE_IO_URING_CMD_COMMIT_AND_FETCH:
+		err = fuse_uring_commit_fetch(cmd, issue_flags, fc);
+		if (err) {
+			pr_info_once("FUSE_IO_URING_COMMIT_AND_FETCH failed err=%d\n",
+				     err);
+			return err;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return -EIOCBQUEUED;
+}
+
+static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd,
+			    ssize_t ret, unsigned int issue_flags)
+{
+	struct fuse_ring_queue *queue = ent->queue;
+
+	spin_lock(&queue->lock);
+	ent->state = FRRS_USERSPACE;
+	list_move(&ent->list, &queue->ent_in_userspace);
+	ent->cmd = NULL;
+	spin_unlock(&queue->lock);
+
+	io_uring_cmd_done(cmd, ret, 0, issue_flags);
+}
+
+/*
+ * This prepares and sends the ring request in fuse-uring task context.
+ * User buffers are not mapped yet - the application does not have permission
+ * to write to it - this has to be executed in ring task context.
+ */
+static void fuse_uring_send_in_task(struct io_uring_cmd *cmd,
+				    unsigned int issue_flags)
+{
+	struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd);
+	struct fuse_ring_queue *queue = ent->queue;
+	int err;
+
+	if (!(issue_flags & IO_URING_F_TASK_DEAD)) {
+		err = fuse_uring_prepare_send(ent, ent->fuse_req);
+		if (err) {
+			fuse_uring_next_fuse_req(ent, queue, issue_flags);
+			return;
+		}
+	} else {
+		err = -ECANCELED;
+	}
+
+	fuse_uring_send(ent, cmd, err, issue_flags);
+}
+
+static struct fuse_ring_queue *fuse_uring_task_to_queue(struct fuse_ring *ring)
+{
+	unsigned int qid;
+	struct fuse_ring_queue *queue;
+
+	qid = task_cpu(current);
+
+	if (WARN_ONCE(qid >= ring->nr_queues,
+		      "Core number (%u) exceeds nr queues (%zu)\n", qid,
+		      ring->nr_queues))
+		qid = 0;
+
+	queue = ring->queues[qid];
+	WARN_ONCE(!queue, "Missing queue for qid %d\n", qid);
+
+	return queue;
+}
+
+static void fuse_uring_dispatch_ent(struct fuse_ring_ent *ent)
+{
+	struct io_uring_cmd *cmd = ent->cmd;
+
+	uring_cmd_set_ring_ent(cmd, ent);
+	io_uring_cmd_complete_in_task(cmd, fuse_uring_send_in_task);
+}
+
+/* queue a fuse request and send it if a ring entry is available */
+void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req)
+{
+	struct fuse_conn *fc = req->fm->fc;
+	struct fuse_ring *ring = fc->ring;
+	struct fuse_ring_queue *queue;
+	struct fuse_ring_ent *ent = NULL;
+	int err;
+
+	err = -EINVAL;
+	queue = fuse_uring_task_to_queue(ring);
+	if (!queue)
+		goto err;
+
+	if (req->in.h.opcode != FUSE_NOTIFY_REPLY)
+		req->in.h.unique = fuse_get_unique(fiq);
+
+	spin_lock(&queue->lock);
+	err = -ENOTCONN;
+	if (unlikely(queue->stopped))
+		goto err_unlock;
+
+	ent = list_first_entry_or_null(&queue->ent_avail_queue,
+				       struct fuse_ring_ent, list);
+	if (ent)
+		fuse_uring_add_req_to_ring_ent(ent, req);
+	else
+		list_add_tail(&req->list, &queue->fuse_req_queue);
+	spin_unlock(&queue->lock);
+
+	if (ent)
+		fuse_uring_dispatch_ent(ent);
+
+	return;
+
+err_unlock:
+	spin_unlock(&queue->lock);
+err:
+	req->out.h.error = err;
+	clear_bit(FR_PENDING, &req->flags);
+	fuse_request_end(req);
+}
+
+bool fuse_uring_queue_bq_req(struct fuse_req *req)
+{
+	struct fuse_conn *fc = req->fm->fc;
+	struct fuse_ring *ring = fc->ring;
+	struct fuse_ring_queue *queue;
+	struct fuse_ring_ent *ent = NULL;
+
+	queue = fuse_uring_task_to_queue(ring);
+	if (!queue)
+		return false;
+
+	spin_lock(&queue->lock);
+	if (unlikely(queue->stopped)) {
+		spin_unlock(&queue->lock);
+		return false;
+	}
+
+	list_add_tail(&req->list, &queue->fuse_req_bg_queue);
+
+	ent = list_first_entry_or_null(&queue->ent_avail_queue,
+				       struct fuse_ring_ent, list);
+	spin_lock(&fc->bg_lock);
+	fc->num_background++;
+	if (fc->num_background == fc->max_background)
+		fc->blocked = 1;
+	fuse_uring_flush_bg(queue);
+	spin_unlock(&fc->bg_lock);
+
+	/*
+	 * Due to bg_queue flush limits there might be other bg requests
+	 * in the queue that need to be handled first. Or no further req
+	 * might be available.
+	 */
+	req = list_first_entry_or_null(&queue->fuse_req_queue, struct fuse_req,
+				       list);
+	if (ent && req) {
+		fuse_uring_add_req_to_ring_ent(ent, req);
+		spin_unlock(&queue->lock);
+
+		fuse_uring_dispatch_ent(ent);
+	} else {
+		spin_unlock(&queue->lock);
+	}
+
+	return true;
+}
+
+static const struct fuse_iqueue_ops fuse_io_uring_ops = {
+	/* should be send over io-uring as enhancement */
+	.send_forget = fuse_dev_queue_forget,
+
+	/*
+	 * could be send over io-uring, but interrupts should be rare,
+	 * no need to make the code complex
+	 */
+	.send_interrupt = fuse_dev_queue_interrupt,
+	.send_req = fuse_uring_queue_fuse_req,
+};
diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h
new file mode 100644
index 000000000000..2102b3d0c1ae
--- /dev/null
+++ b/fs/fuse/dev_uring_i.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * FUSE: Filesystem in Userspace
+ * Copyright (c) 2023-2024 DataDirect Networks.
+ */
+
+#ifndef _FS_FUSE_DEV_URING_I_H
+#define _FS_FUSE_DEV_URING_I_H
+
+#include "fuse_i.h"
+
+#ifdef CONFIG_FUSE_IO_URING
+
+#define FUSE_URING_TEARDOWN_TIMEOUT (5 * HZ)
+#define FUSE_URING_TEARDOWN_INTERVAL (HZ/20)
+
+enum fuse_ring_req_state {
+	FRRS_INVALID = 0,
+
+	/* The ring entry received from userspace and it is being processed */
+	FRRS_COMMIT,
+
+	/* The ring entry is waiting for new fuse requests */
+	FRRS_AVAILABLE,
+
+	/* The ring entry got assigned a fuse req */
+	FRRS_FUSE_REQ,
+
+	/* The ring entry is in or on the way to user space */
+	FRRS_USERSPACE,
+
+	/* The ring entry is in teardown */
+	FRRS_TEARDOWN,
+
+	/* The ring entry is released, but not freed yet */
+	FRRS_RELEASED,
+};
+
+/** A fuse ring entry, part of the ring queue */
+struct fuse_ring_ent {
+	/* userspace buffer */
+	struct fuse_uring_req_header __user *headers;
+	void __user *payload;
+
+	/* the ring queue that owns the request */
+	struct fuse_ring_queue *queue;
+
+	/* fields below are protected by queue->lock */
+
+	struct io_uring_cmd *cmd;
+
+	struct list_head list;
+
+	enum fuse_ring_req_state state;
+
+	struct fuse_req *fuse_req;
+};
+
+struct fuse_ring_queue {
+	/*
+	 * back pointer to the main fuse uring structure that holds this
+	 * queue
+	 */
+	struct fuse_ring *ring;
+
+	/* queue id, corresponds to the cpu core */
+	unsigned int qid;
+
+	/*
+	 * queue lock, taken when any value in the queue changes _and_ also
+	 * a ring entry state changes.
+	 */
+	spinlock_t lock;
+
+	/* available ring entries (struct fuse_ring_ent) */
+	struct list_head ent_avail_queue;
+
+	/*
+	 * entries in the process of being committed or in the process
+	 * to be sent to userspace
+	 */
+	struct list_head ent_w_req_queue;
+	struct list_head ent_commit_queue;
+
+	/* entries in userspace */
+	struct list_head ent_in_userspace;
+
+	/* entries that are released */
+	struct list_head ent_released;
+
+	/* fuse requests waiting for an entry slot */
+	struct list_head fuse_req_queue;
+
+	/* background fuse requests */
+	struct list_head fuse_req_bg_queue;
+
+	struct fuse_pqueue fpq;
+
+	unsigned int active_background;
+
+	bool stopped;
+};
+
+/**
+ * Describes if uring is for communication and holds alls the data needed
+ * for uring communication
+ */
+struct fuse_ring {
+	/* back pointer */
+	struct fuse_conn *fc;
+
+	/* number of ring queues */
+	size_t nr_queues;
+
+	/* maximum payload/arg size */
+	size_t max_payload_sz;
+
+	struct fuse_ring_queue **queues;
+
+	/*
+	 * Log ring entry states on stop when entries cannot be released
+	 */
+	unsigned int stop_debug_log : 1;
+
+	wait_queue_head_t stop_waitq;
+
+	/* async tear down */
+	struct delayed_work async_teardown_work;
+
+	/* log */
+	unsigned long teardown_time;
+
+	atomic_t queue_refs;
+
+	bool ready;
+};
+
+bool fuse_uring_enabled(void);
+void fuse_uring_destruct(struct fuse_conn *fc);
+void fuse_uring_stop_queues(struct fuse_ring *ring);
+void fuse_uring_abort_end_requests(struct fuse_ring *ring);
+int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags);
+void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req);
+bool fuse_uring_queue_bq_req(struct fuse_req *req);
+
+static inline void fuse_uring_abort(struct fuse_conn *fc)
+{
+	struct fuse_ring *ring = fc->ring;
+
+	if (ring == NULL)
+		return;
+
+	if (atomic_read(&ring->queue_refs) > 0) {
+		fuse_uring_abort_end_requests(ring);
+		fuse_uring_stop_queues(ring);
+	}
+}
+
+static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc)
+{
+	struct fuse_ring *ring = fc->ring;
+
+	if (ring)
+		wait_event(ring->stop_waitq,
+			   atomic_read(&ring->queue_refs) == 0);
+}
+
+static inline bool fuse_uring_ready(struct fuse_conn *fc)
+{
+	return fc->ring && fc->ring->ready;
+}
+
+#else /* CONFIG_FUSE_IO_URING */
+
+struct fuse_ring;
+
+static inline void fuse_uring_create(struct fuse_conn *fc)
+{
+}
+
+static inline void fuse_uring_destruct(struct fuse_conn *fc)
+{
+}
+
+static inline bool fuse_uring_enabled(void)
+{
+	return false;
+}
+
+static inline void fuse_uring_abort(struct fuse_conn *fc)
+{
+}
+
+static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc)
+{
+}
+
+static inline bool fuse_uring_ready(struct fuse_conn *fc)
+{
+	return false;
+}
+
+#endif /* CONFIG_FUSE_IO_URING */
+
+#endif /* _FS_FUSE_DEV_URING_I_H */
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index bf057cf7098d..198862b086ff 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -175,9 +175,12 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args,
 	memset(outarg, 0, sizeof(struct fuse_entry_out));
 	args->opcode = FUSE_LOOKUP;
 	args->nodeid = nodeid;
-	args->in_numargs = 1;
-	args->in_args[0].size = name->len + 1;
-	args->in_args[0].value = name->name;
+	args->in_numargs = 3;
+	fuse_set_zero_arg0(args);
+	args->in_args[1].size = name->len;
+	args->in_args[1].value = name->name;
+	args->in_args[2].size = 1;
+	args->in_args[2].value = "";
 	args->out_numargs = 1;
 	args->out_args[0].size = sizeof(struct fuse_entry_out);
 	args->out_args[0].value = outarg;
@@ -192,10 +195,10 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args,
  * the lookup once more.  If the lookup results in the same inode,
  * then refresh the attributes, timeouts and mark the dentry valid.
  */
-static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
+static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *entry, unsigned int flags)
 {
 	struct inode *inode;
-	struct dentry *parent;
 	struct fuse_mount *fm;
 	struct fuse_inode *fi;
 	int ret;
@@ -227,11 +230,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 
 		attr_version = fuse_get_attr_version(fm->fc);
 
-		parent = dget_parent(entry);
-		fuse_lookup_init(fm->fc, &args, get_node_id(d_inode(parent)),
-				 &entry->d_name, &outarg);
+		fuse_lookup_init(fm->fc, &args, get_node_id(dir),
+				 name, &outarg);
 		ret = fuse_simple_request(fm, &args);
-		dput(parent);
 		/* Zero nodeid is same as -ENOENT */
 		if (!ret && !outarg.nodeid)
 			ret = -ENOENT;
@@ -265,9 +266,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 			if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state))
 				return -ECHILD;
 		} else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) {
-			parent = dget_parent(entry);
-			fuse_advise_use_readdirplus(d_inode(parent));
-			dput(parent);
+			fuse_advise_use_readdirplus(dir);
 		}
 	}
 	ret = 1;
@@ -929,11 +928,12 @@ static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	FUSE_ARGS(args);
 
 	args.opcode = FUSE_SYMLINK;
-	args.in_numargs = 2;
-	args.in_args[0].size = entry->d_name.len + 1;
-	args.in_args[0].value = entry->d_name.name;
-	args.in_args[1].size = len;
-	args.in_args[1].value = link;
+	args.in_numargs = 3;
+	fuse_set_zero_arg0(&args);
+	args.in_args[1].size = entry->d_name.len + 1;
+	args.in_args[1].value = entry->d_name.name;
+	args.in_args[2].size = len;
+	args.in_args[2].value = link;
 	return create_new_entry(idmap, fm, &args, dir, entry, S_IFLNK);
 }
 
@@ -993,9 +993,10 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry)
 
 	args.opcode = FUSE_UNLINK;
 	args.nodeid = get_node_id(dir);
-	args.in_numargs = 1;
-	args.in_args[0].size = entry->d_name.len + 1;
-	args.in_args[0].value = entry->d_name.name;
+	args.in_numargs = 2;
+	fuse_set_zero_arg0(&args);
+	args.in_args[1].size = entry->d_name.len + 1;
+	args.in_args[1].value = entry->d_name.name;
 	err = fuse_simple_request(fm, &args);
 	if (!err) {
 		fuse_dir_changed(dir);
@@ -1016,9 +1017,10 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
 
 	args.opcode = FUSE_RMDIR;
 	args.nodeid = get_node_id(dir);
-	args.in_numargs = 1;
-	args.in_args[0].size = entry->d_name.len + 1;
-	args.in_args[0].value = entry->d_name.name;
+	args.in_numargs = 2;
+	fuse_set_zero_arg0(&args);
+	args.in_args[1].size = entry->d_name.len + 1;
+	args.in_args[1].value = entry->d_name.name;
 	err = fuse_simple_request(fm, &args);
 	if (!err) {
 		fuse_dir_changed(dir);
diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h
new file mode 100644
index 000000000000..3b2bfe1248d3
--- /dev/null
+++ b/fs/fuse/fuse_dev_i.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * FUSE: Filesystem in Userspace
+ * Copyright (C) 2001-2008  Miklos Szeredi <miklos@szeredi.hu>
+ */
+#ifndef _FS_FUSE_DEV_I_H
+#define _FS_FUSE_DEV_I_H
+
+#include <linux/types.h>
+
+/* Ordinary requests have even IDs, while interrupts IDs are odd */
+#define FUSE_INT_REQ_BIT (1ULL << 0)
+#define FUSE_REQ_ID_STEP (1ULL << 1)
+
+struct fuse_arg;
+struct fuse_args;
+struct fuse_pqueue;
+struct fuse_req;
+struct fuse_iqueue;
+struct fuse_forget_link;
+
+struct fuse_copy_state {
+	int write;
+	struct fuse_req *req;
+	struct iov_iter *iter;
+	struct pipe_buffer *pipebufs;
+	struct pipe_buffer *currbuf;
+	struct pipe_inode_info *pipe;
+	unsigned long nr_segs;
+	struct page *pg;
+	unsigned int len;
+	unsigned int offset;
+	unsigned int move_pages:1;
+	unsigned int is_uring:1;
+	struct {
+		unsigned int copied_sz; /* copied size into the user buffer */
+	} ring;
+};
+
+static inline struct fuse_dev *fuse_get_dev(struct file *file)
+{
+	/*
+	 * Lockless access is OK, because file->private data is set
+	 * once during mount and is valid until the file is released.
+	 */
+	return READ_ONCE(file->private_data);
+}
+
+unsigned int fuse_req_hash(u64 unique);
+struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique);
+
+void fuse_dev_end_requests(struct list_head *head);
+
+void fuse_copy_init(struct fuse_copy_state *cs, int write,
+			   struct iov_iter *iter);
+int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs,
+		   unsigned int argpages, struct fuse_arg *args,
+		   int zeroing);
+int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args,
+		       unsigned int nbytes);
+void fuse_dev_queue_forget(struct fuse_iqueue *fiq,
+			   struct fuse_forget_link *forget);
+void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req);
+
+#endif
+
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 74744c6f2860..fee96fe7887b 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -310,7 +310,7 @@ struct fuse_args {
 	bool is_ext:1;
 	bool is_pinned:1;
 	bool invalidate_vmap:1;
-	struct fuse_in_arg in_args[3];
+	struct fuse_in_arg in_args[4];
 	struct fuse_arg out_args[2];
 	void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error);
 	/* Used for kvec iter backed by vmalloc address */
@@ -438,6 +438,10 @@ struct fuse_req {
 
 	/** fuse_mount this request belongs to */
 	struct fuse_mount *fm;
+
+#ifdef CONFIG_FUSE_IO_URING
+	void *ring_entry;
+#endif
 };
 
 struct fuse_iqueue;
@@ -863,6 +867,9 @@ struct fuse_conn {
 	/* Use pages instead of pointer for kernel I/O */
 	unsigned int use_pages_for_kvec_io:1;
 
+	/* Use io_uring for communication */
+	unsigned int io_uring;
+
 	/** Maximum stack depth for passthrough backing files */
 	int max_stack_depth;
 
@@ -923,6 +930,11 @@ struct fuse_conn {
 	/** IDR for backing files ids */
 	struct idr backing_files_map;
 #endif
+
+#ifdef CONFIG_FUSE_IO_URING
+	/**  uring connection information*/
+	struct fuse_ring *ring;
+#endif
 };
 
 /*
@@ -947,6 +959,19 @@ struct fuse_mount {
 	struct rcu_head rcu;
 };
 
+/*
+ * Empty header for FUSE opcodes without specific header needs.
+ * Used as a placeholder in args->in_args[0] for consistency
+ * across all FUSE operations, simplifying request handling.
+ */
+struct fuse_zero_header {};
+
+static inline void fuse_set_zero_arg0(struct fuse_args *args)
+{
+	args->in_args[0].size = sizeof(struct fuse_zero_header);
+	args->in_args[0].value = NULL;
+}
+
 static inline struct fuse_mount *get_fuse_mount_super(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -1220,6 +1245,11 @@ void fuse_change_entry_timeout(struct dentry *entry, struct fuse_entry_out *o);
 struct fuse_conn *fuse_conn_get(struct fuse_conn *fc);
 
 /**
+ * Initialize the fuse processing queue
+ */
+void fuse_pqueue_init(struct fuse_pqueue *fpq);
+
+/**
  * Initialize fuse_conn
  */
 void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3ce4f4e81d09..e9db2cb8c150 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -7,6 +7,7 @@
 */
 
 #include "fuse_i.h"
+#include "dev_uring_i.h"
 
 #include <linux/pagemap.h>
 #include <linux/slab.h>
@@ -937,7 +938,7 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq,
 	fiq->priv = priv;
 }
 
-static void fuse_pqueue_init(struct fuse_pqueue *fpq)
+void fuse_pqueue_init(struct fuse_pqueue *fpq)
 {
 	unsigned int i;
 
@@ -992,6 +993,8 @@ static void delayed_release(struct rcu_head *p)
 {
 	struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu);
 
+	fuse_uring_destruct(fc);
+
 	put_user_ns(fc->user_ns);
 	fc->release(fc);
 }
@@ -1387,6 +1390,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				else
 					ok = false;
 			}
+			if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled())
+				fc->io_uring = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1446,6 +1451,13 @@ void fuse_send_init(struct fuse_mount *fm)
 	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
 		flags |= FUSE_PASSTHROUGH;
 
+	/*
+	 * This is just an information flag for fuse server. No need to check
+	 * the reply - server is either sending IORING_OP_URING_CMD or not.
+	 */
+	if (fuse_uring_enabled())
+		flags |= FUSE_OVER_IO_URING;
+
 	ia->in.flags = flags;
 	ia->in.flags2 = flags >> 32;
 
diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c
index b272bb333005..63fb1e5bee30 100644
--- a/fs/fuse/sysctl.c
+++ b/fs/fuse/sysctl.c
@@ -13,7 +13,7 @@ static struct ctl_table_header *fuse_table_header;
 /* Bound by fuse_init_out max_pages, which is a u16 */
 static unsigned int sysctl_fuse_max_pages_limit = 65535;
 
-static struct ctl_table fuse_sysctl_table[] = {
+static const struct ctl_table fuse_sysctl_table[] = {
 	{
 		.procname	= "max_pages_limit",
 		.data		= &fuse_max_pages_limit,
diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
index 9f568d345c51..93dfb06b6cea 100644
--- a/fs/fuse/xattr.c
+++ b/fs/fuse/xattr.c
@@ -164,9 +164,10 @@ int fuse_removexattr(struct inode *inode, const char *name)
 
 	args.opcode = FUSE_REMOVEXATTR;
 	args.nodeid = get_node_id(inode);
-	args.in_numargs = 1;
-	args.in_args[0].size = strlen(name) + 1;
-	args.in_args[0].value = name;
+	args.in_numargs = 2;
+	fuse_set_zero_arg0(&args);
+	args.in_args[1].size = strlen(name) + 1;
+	args.in_args[1].value = name;
 	err = fuse_simple_request(fm, &args);
 	if (err == -ENOSYS) {
 		fm->fc->no_removexattr = 1;
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 2e215e8c3c88..95050e719233 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -21,7 +21,9 @@
 
 /**
  * gfs2_drevalidate - Check directory lookup consistency
- * @dentry: the mapping to check
+ * @dir: expected parent directory inode
+ * @name: expexted name
+ * @dentry: dentry to check
  * @flags: lookup flags
  *
  * Check to make sure the lookup necessary to arrive at this inode from its
@@ -30,50 +32,43 @@
  * Returns: 1 if the dentry is ok, 0 if it isn't
  */
 
-static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
+static int gfs2_drevalidate(struct inode *dir, const struct qstr *name,
+			    struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *parent;
-	struct gfs2_sbd *sdp;
-	struct gfs2_inode *dip;
+	struct gfs2_sbd *sdp = GFS2_SB(dir);
+	struct gfs2_inode *dip = GFS2_I(dir);
 	struct inode *inode;
 	struct gfs2_holder d_gh;
 	struct gfs2_inode *ip = NULL;
-	int error, valid = 0;
+	int error, valid;
 	int had_lock = 0;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
-	parent = dget_parent(dentry);
-	sdp = GFS2_SB(d_inode(parent));
-	dip = GFS2_I(d_inode(parent));
 	inode = d_inode(dentry);
 
 	if (inode) {
 		if (is_bad_inode(inode))
-			goto out;
+			return 0;
 		ip = GFS2_I(inode);
 	}
 
-	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) {
-		valid = 1;
-		goto out;
-	}
+	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+		return 1;
 
 	had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
 	if (!had_lock) {
 		error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
 		if (error)
-			goto out;
+			return 0;
 	}
 
-	error = gfs2_dir_check(d_inode(parent), &dentry->d_name, ip);
+	error = gfs2_dir_check(dir, name, ip);
 	valid = inode ? !error : (error == -ENOENT);
 
 	if (!had_lock)
 		gfs2_glock_dq_uninit(&d_gh);
-out:
-	dput(parent);
 	return valid;
 }
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 8c4c1f871a88..65c07aa95718 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1201,8 +1201,8 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	if (glops->go_instantiate)
 		gl->gl_flags |= BIT(GLF_INSTANTIATE_NEEDED);
 	gl->gl_name = name;
+	lockref_init(&gl->gl_lockref);
 	lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass);
-	gl->gl_lockref.count = 1;
 	gl->gl_state = LM_ST_UNLOCKED;
 	gl->gl_target = LM_ST_UNLOCKED;
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 04cadc02e5a6..0727f60ad028 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -51,7 +51,6 @@ static void gfs2_init_glock_once(void *foo)
 {
 	struct gfs2_glock *gl = foo;
 
-	spin_lock_init(&gl->gl_lockref.lock);
 	INIT_LIST_HEAD(&gl->gl_holders);
 	INIT_LIST_HEAD(&gl->gl_lru);
 	INIT_LIST_HEAD(&gl->gl_ail_list);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 58bc5013ca49..2298e06797ac 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -236,7 +236,7 @@ static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, str
 		return NULL;
 
 	qd->qd_sbd = sdp;
-	lockref_init(&qd->qd_lockref, 0);
+	lockref_init(&qd->qd_lockref);
 	qd->qd_id = qid;
 	qd->qd_slot = -1;
 	INIT_LIST_HEAD(&qd->qd_lru);
@@ -297,7 +297,6 @@ static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
 	spin_lock_bucket(hash);
 	*qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid);
 	if (qd == NULL) {
-		new_qd->qd_lockref.count++;
 		*qdp = new_qd;
 		list_add(&new_qd->qd_list, &sdp->sd_quota_list);
 		hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]);
@@ -1450,6 +1449,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp)
 			if (qd == NULL)
 				goto fail_brelse;
 
+			qd->qd_lockref.count = 0;
 			set_bit(QDF_CHANGE, &qd->qd_flags);
 			qd->qd_change = qc_change;
 			qd->qd_slot = slot;
diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c
index 76fa02e3835b..ef54fc8093cf 100644
--- a/fs/hfs/sysdep.c
+++ b/fs/hfs/sysdep.c
@@ -13,7 +13,8 @@
 
 /* dentry case-handling: just lowercase everything */
 
-static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags)
+static int hfs_revalidate_dentry(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	int diff;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 7e51d2cec64b..e0741e468956 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -95,32 +95,17 @@ __uml_setup("hostfs=", hostfs_args,
 static char *__dentry_name(struct dentry *dentry, char *name)
 {
 	char *p = dentry_path_raw(dentry, name, PATH_MAX);
-	char *root;
-	size_t len;
-	struct hostfs_fs_info *fsi;
-
-	fsi = dentry->d_sb->s_fs_info;
-	root = fsi->host_root_path;
-	len = strlen(root);
-	if (IS_ERR(p)) {
-		__putname(name);
-		return NULL;
-	}
+	struct hostfs_fs_info *fsi = dentry->d_sb->s_fs_info;
+	char *root = fsi->host_root_path;
+	size_t len = strlen(root);
 
-	/*
-	 * This function relies on the fact that dentry_path_raw() will place
-	 * the path name at the end of the provided buffer.
-	 */
-	BUG_ON(p + strlen(p) + 1 != name + PATH_MAX);
-
-	strscpy(name, root, PATH_MAX);
-	if (len > p - name) {
+	if (IS_ERR(p) || len > p - name) {
 		__putname(name);
 		return NULL;
 	}
 
-	if (p > name + len)
-		strcpy(name + len, p);
+	memcpy(name, root, len);
+	memmove(name + len, p, name + PATH_MAX - p);
 
 	return name;
 }
@@ -410,38 +395,33 @@ static const struct file_operations hostfs_dir_fops = {
 	.fsync		= hostfs_fsync,
 };
 
-static int hostfs_writepage(struct page *page, struct writeback_control *wbc)
+static int hostfs_writepages(struct address_space *mapping,
+		struct writeback_control *wbc)
 {
-	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
-	char *buffer;
-	loff_t base = page_offset(page);
-	int count = PAGE_SIZE;
-	int end_index = inode->i_size >> PAGE_SHIFT;
-	int err;
-
-	if (page->index >= end_index)
-		count = inode->i_size & (PAGE_SIZE-1);
-
-	buffer = kmap_local_page(page);
-
-	err = write_file(HOSTFS_I(inode)->fd, &base, buffer, count);
-	if (err != count) {
-		if (err >= 0)
-			err = -EIO;
-		mapping_set_error(mapping, err);
-		goto out;
+	struct folio *folio = NULL;
+	loff_t i_size = i_size_read(inode);
+	int err = 0;
+
+	while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
+		loff_t pos = folio_pos(folio);
+		size_t count = folio_size(folio);
+		char *buffer;
+		int ret;
+
+		if (count > i_size - pos)
+			count = i_size - pos;
+
+		buffer = kmap_local_folio(folio, 0);
+		ret = write_file(HOSTFS_I(inode)->fd, &pos, buffer, count);
+		kunmap_local(buffer);
+		folio_unlock(folio);
+		if (ret != count) {
+			err = ret < 0 ? ret : -EIO;
+			mapping_set_error(mapping, err);
+		}
 	}
 
-	if (base > inode->i_size)
-		inode->i_size = base;
-
-	err = 0;
-
- out:
-	kunmap_local(buffer);
-	unlock_page(page);
-
 	return err;
 }
 
@@ -506,11 +486,12 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping,
 }
 
 static const struct address_space_operations hostfs_aops = {
-	.writepage 	= hostfs_writepage,
+	.writepages 	= hostfs_writepages,
 	.read_folio	= hostfs_read_folio,
 	.dirty_folio	= filemap_dirty_folio,
 	.write_begin	= hostfs_write_begin,
 	.write_end	= hostfs_write_end,
+	.migrate_folio	= filemap_migrate_folio,
 };
 
 static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index fc1ae5132127..0fc179a59830 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -99,7 +99,6 @@ static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
-	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 	loff_t len, vma_len;
 	int ret;
 	struct hstate *h = hstate_file(file);
@@ -116,10 +115,6 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND);
 	vma->vm_ops = &hugetlb_vm_ops;
 
-	ret = seal_check_write(info->seals, vma);
-	if (ret)
-		return ret;
-
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
 	 * overflow a loff_t when converted to byte offset.  This can
@@ -819,7 +814,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		 * folios in these areas, we need to consume the reserves
 		 * to keep reservation accounting consistent.
 		 */
-		folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0);
+		folio = alloc_hugetlb_folio(&pseudo_vma, addr, false);
 		if (IS_ERR(folio)) {
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			error = PTR_ERR(folio);
diff --git a/fs/inode.c b/fs/inode.c
index 6b4c77268fc0..5587aabdaa5e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -184,7 +184,7 @@ static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table inodes_sysctls[] = {
+static const struct ctl_table inodes_sysctls[] = {
 	{
 		.procname	= "inode-nr",
 		.data		= &inodes_stat,
diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
index 5fc0ac36dee3..b90d0eda9e51 100644
--- a/fs/iomap/swapfile.c
+++ b/fs/iomap/swapfile.c
@@ -189,7 +189,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
 	*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
 	sis->max = isi.nr_pages;
 	sis->pages = isi.nr_pages - 1;
-	sis->highest_bit = isi.nr_pages - 1;
 	return isi.nr_extents;
 }
 EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index d68a4e6ac345..fc8ede43afde 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -1576,7 +1576,8 @@ out:
 	return result;
 }
 
-static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags)
+static int jfs_ci_revalidate(struct inode *dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
 {
 	/*
 	 * This is not negative dentry. Always valid.
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 458519e416fe..5f0f8b95f44c 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1109,7 +1109,8 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 	return ERR_PTR(rc);
 }
 
-static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
+static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	struct kernfs_node *kn;
 	struct kernfs_root *root;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 8502ef68459b..0eb320617d7b 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -927,7 +927,7 @@ repeat:
 		if (!inode)
 			continue;
 
-		name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name));
+		name = QSTR(kn->name);
 		parent = kernfs_get_parent(kn);
 		if (parent) {
 			p_inode = ilookup(info->sb, kernfs_ino(parent));
diff --git a/fs/libfs.c b/fs/libfs.c
index 5b6120b19e99..8444f5cc4064 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1782,7 +1782,7 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 {
 	const struct dentry *parent;
 	const struct inode *dir;
-	char strbuf[DNAME_INLINE_LEN];
+	union shortname_store strbuf;
 	struct qstr qstr;
 
 	/*
@@ -1802,22 +1802,23 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 	if (!dir || !IS_CASEFOLDED(dir))
 		return 1;
 
+	qstr.len = len;
+	qstr.name = str;
 	/*
 	 * If the dentry name is stored in-line, then it may be concurrently
 	 * modified by a rename.  If this happens, the VFS will eventually retry
 	 * the lookup, so it doesn't matter what ->d_compare() returns.
 	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
 	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 * As above, len is guaranteed to match str, so the shortname case
+	 * is exactly when str points to ->d_shortname.
 	 */
-	if (len <= DNAME_INLINE_LEN - 1) {
-		memcpy(strbuf, str, len);
-		strbuf[len] = 0;
-		str = strbuf;
+	if (qstr.name == dentry->d_shortname.string) {
+		strbuf = dentry->d_shortname; // NUL is guaranteed to be in there
+		qstr.name = strbuf.string;
 		/* prevent compiler from optimizing out the temporary buffer */
 		barrier();
 	}
-	qstr.len = len;
-	qstr.name = str;
 
 	return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
 }
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 4ec22c2f2ea3..2c8eedc6c2cc 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -70,9 +70,6 @@ static unsigned long		nlm_grace_period;
 unsigned long			nlm_timeout = LOCKD_DFLT_TIMEO;
 static int			nlm_udpport, nlm_tcpport;
 
-/* RLIM_NOFILE defaults to 1024. That seems like a reasonable default here. */
-static unsigned int		nlm_max_connections = 1024;
-
 /*
  * Constants needed for the sysctl interface.
  */
@@ -136,9 +133,6 @@ lockd(void *vrqstp)
 	 * NFS mount or NFS daemon has gone away.
 	 */
 	while (!svc_thread_should_stop(rqstp)) {
-		/* update sv_maxconn if it has changed */
-		rqstp->rq_server->sv_maxconn = nlm_max_connections;
-
 		nlmsvc_retry_blocked(rqstp);
 		svc_recv(rqstp);
 	}
@@ -340,7 +334,6 @@ static int lockd_get(void)
 		return -ENOMEM;
 	}
 
-	serv->sv_maxconn = nlm_max_connections;
 	error = svc_set_num_threads(serv, NULL, 1);
 	if (error < 0) {
 		svc_destroy(&serv);
@@ -419,7 +412,7 @@ EXPORT_SYMBOL_GPL(lockd_down);
  * Sysctl parameters (same as module parameters, different interface).
  */
 
-static struct ctl_table nlm_sysctls[] = {
+static const struct ctl_table nlm_sysctls[] = {
 	{
 		.procname	= "nlm_grace_period",
 		.data		= &nlm_grace_period,
@@ -542,7 +535,6 @@ module_param_call(nlm_udpport, param_set_port, param_get_int,
 module_param_call(nlm_tcpport, param_set_port, param_get_int,
 		  &nlm_tcpport, 0644);
 module_param(nsm_use_hostnames, bool, 0644);
-module_param(nlm_max_connections, uint, 0644);
 
 static int lockd_init_net(struct net *net)
 {
diff --git a/fs/locks.c b/fs/locks.c
index 25afc8d9c9d1..1619cddfa7a4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -97,7 +97,7 @@ static int leases_enable = 1;
 static int lease_break_time = 45;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table locks_sysctls[] = {
+static const struct ctl_table locks_sysctls[] = {
 	{
 		.procname	= "leases-enable",
 		.data		= &leases_enable,
diff --git a/fs/namei.c b/fs/namei.c
index e56c29a22d26..3ab9440c5b93 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -921,10 +921,11 @@ out_dput:
 	return false;
 }
 
-static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
+static inline int d_revalidate(struct inode *dir, const struct qstr *name,
+			       struct dentry *dentry, unsigned int flags)
 {
 	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-		return dentry->d_op->d_revalidate(dentry, flags);
+		return dentry->d_op->d_revalidate(dir, name, dentry, flags);
 	else
 		return 1;
 }
@@ -1099,7 +1100,7 @@ static int sysctl_protected_fifos __read_mostly;
 static int sysctl_protected_regular __read_mostly;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table namei_sysctls[] = {
+static const struct ctl_table namei_sysctls[] = {
 	{
 		.procname	= "protected_symlinks",
 		.data		= &sysctl_protected_symlinks,
@@ -1652,7 +1653,7 @@ static struct dentry *lookup_dcache(const struct qstr *name,
 {
 	struct dentry *dentry = d_lookup(dir, name);
 	if (dentry) {
-		int error = d_revalidate(dentry, flags);
+		int error = d_revalidate(dir->d_inode, name, dentry, flags);
 		if (unlikely(error <= 0)) {
 			if (!error)
 				d_invalidate(dentry);
@@ -1737,19 +1738,20 @@ static struct dentry *lookup_fast(struct nameidata *nd)
 		if (read_seqcount_retry(&parent->d_seq, nd->seq))
 			return ERR_PTR(-ECHILD);
 
-		status = d_revalidate(dentry, nd->flags);
+		status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags);
 		if (likely(status > 0))
 			return dentry;
 		if (!try_to_unlazy_next(nd, dentry))
 			return ERR_PTR(-ECHILD);
 		if (status == -ECHILD)
 			/* we'd been told to redo it in non-rcu mode */
-			status = d_revalidate(dentry, nd->flags);
+			status = d_revalidate(nd->inode, &nd->last,
+					      dentry, nd->flags);
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
 		if (unlikely(!dentry))
 			return NULL;
-		status = d_revalidate(dentry, nd->flags);
+		status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags);
 	}
 	if (unlikely(status <= 0)) {
 		if (!status)
@@ -1777,7 +1779,7 @@ again:
 	if (IS_ERR(dentry))
 		return dentry;
 	if (unlikely(!d_in_lookup(dentry))) {
-		int error = d_revalidate(dentry, flags);
+		int error = d_revalidate(inode, name, dentry, flags);
 		if (unlikely(error <= 0)) {
 			if (!error) {
 				d_invalidate(dentry);
@@ -3575,7 +3577,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 		if (d_in_lookup(dentry))
 			break;
 
-		error = d_revalidate(dentry, nd->flags);
+		error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags);
 		if (likely(error > 0))
 			break;
 		if (error)
diff --git a/fs/namespace.c b/fs/namespace.c
index 4013fbac354a..8f1000f9f3df 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5087,30 +5087,29 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq)
 {
 	struct vfsmount *mnt = s->mnt;
 	struct super_block *sb = mnt->mnt_sb;
+	size_t start = seq->count;
 	int err;
 
-	if (sb->s_op->show_options) {
-		size_t start = seq->count;
-
-		err = security_sb_show_options(seq, sb);
-		if (err)
-			return err;
+	err = security_sb_show_options(seq, sb);
+	if (err)
+		return err;
 
+	if (sb->s_op->show_options) {
 		err = sb->s_op->show_options(seq, mnt->mnt_root);
 		if (err)
 			return err;
+	}
 
-		if (unlikely(seq_has_overflowed(seq)))
-			return -EAGAIN;
+	if (unlikely(seq_has_overflowed(seq)))
+		return -EAGAIN;
 
-		if (seq->count == start)
-			return 0;
+	if (seq->count == start)
+		return 0;
 
-		/* skip leading comma */
-		memmove(seq->buf + start, seq->buf + start + 1,
-			seq->count - start - 1);
-		seq->count--;
-	}
+	/* skip leading comma */
+	memmove(seq->buf + start, seq->buf + start + 1,
+		seq->count - start - 1);
+	seq->count--;
 
 	return 0;
 }
@@ -5191,39 +5190,45 @@ static int statmount_string(struct kstatmount *s, u64 flag)
 	size_t kbufsize;
 	struct seq_file *seq = &s->seq;
 	struct statmount *sm = &s->sm;
-	u32 start = seq->count;
+	u32 start, *offp;
+
+	/* Reserve an empty string at the beginning for any unset offsets */
+	if (!seq->count)
+		seq_putc(seq, 0);
+
+	start = seq->count;
 
 	switch (flag) {
 	case STATMOUNT_FS_TYPE:
-		sm->fs_type = start;
+		offp = &sm->fs_type;
 		ret = statmount_fs_type(s, seq);
 		break;
 	case STATMOUNT_MNT_ROOT:
-		sm->mnt_root = start;
+		offp = &sm->mnt_root;
 		ret = statmount_mnt_root(s, seq);
 		break;
 	case STATMOUNT_MNT_POINT:
-		sm->mnt_point = start;
+		offp = &sm->mnt_point;
 		ret = statmount_mnt_point(s, seq);
 		break;
 	case STATMOUNT_MNT_OPTS:
-		sm->mnt_opts = start;
+		offp = &sm->mnt_opts;
 		ret = statmount_mnt_opts(s, seq);
 		break;
 	case STATMOUNT_OPT_ARRAY:
-		sm->opt_array = start;
+		offp = &sm->opt_array;
 		ret = statmount_opt_array(s, seq);
 		break;
 	case STATMOUNT_OPT_SEC_ARRAY:
-		sm->opt_sec_array = start;
+		offp = &sm->opt_sec_array;
 		ret = statmount_opt_sec_array(s, seq);
 		break;
 	case STATMOUNT_FS_SUBTYPE:
-		sm->fs_subtype = start;
+		offp = &sm->fs_subtype;
 		statmount_fs_subtype(s, seq);
 		break;
 	case STATMOUNT_SB_SOURCE:
-		sm->sb_source = start;
+		offp = &sm->sb_source;
 		ret = statmount_sb_source(s, seq);
 		break;
 	default:
@@ -5251,6 +5256,7 @@ static int statmount_string(struct kstatmount *s, u64 flag)
 
 	seq->buf[seq->count++] = '\0';
 	sm->mask |= flag;
+	*offp = start;
 	return 0;
 }
 
@@ -5985,7 +5991,7 @@ const struct proc_ns_operations mntns_operations = {
 };
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table fs_namespace_sysctls[] = {
+static const struct ctl_table fs_namespace_sysctls[] = {
 	{
 		.procname	= "mount-max",
 		.data		= &sysctl_mount_max,
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 0eb20012792f..d3f76101ad4b 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -170,7 +170,8 @@ config ROOT_NFS
 
 config NFS_FSCACHE
 	bool "Provide NFS client caching support"
-	depends on NFS_FS=m && NETFS_SUPPORT || NFS_FS=y && NETFS_SUPPORT=y
+	depends on NFS_FS
+	select NETFS_SUPPORT
 	select FSCACHE
 	help
 	  Say Y here if you want NFS data to be cached locally on disc through
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 6cf92498a5ac..86bdc7d23fb9 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -211,10 +211,6 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 		return ERR_PTR(-ENOMEM);
 	}
 	cb_info->serv = serv;
-	/* As there is only one thread we need to over-ride the
-	 * default maximum of 80 connections
-	 */
-	serv->sv_maxconn = 1024;
 	dprintk("nfs_callback_create_svc: service created\n");
 	return serv;
 }
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 7832fb0369a1..8397c43358bd 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -718,7 +718,7 @@ __be32 nfs4_callback_offload(void *data, void *dummy,
 
 	copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_KERNEL);
 	if (!copy)
-		return htonl(NFS4ERR_SERVERFAULT);
+		return cpu_to_be32(NFS4ERR_DELAY);
 
 	spin_lock(&cps->clp->cl_lock);
 	rcu_read_lock();
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index fdeb0b34a3d3..4254ba3ee7c5 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -984,6 +984,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 			nfs_put_client(cps.clp);
 			goto out_invalidcred;
 		}
+		svc_xprt_set_valid(rqstp->rq_xprt);
 	}
 
 	cps.minorversion = hdr_arg.minorversion;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 550ca934c9cf..3b0918ade53c 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -38,7 +38,7 @@
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/nsproxy.h>
 #include <linux/pid_namespace.h>
-
+#include <linux/nfslocalio.h>
 
 #include "nfs4_fs.h"
 #include "callback.h"
@@ -186,7 +186,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	seqlock_init(&clp->cl_boot_lock);
 	ktime_get_real_ts64(&clp->cl_nfssvc_boot);
 	nfs_uuid_init(&clp->cl_uuid);
-	spin_lock_init(&clp->cl_localio_lock);
+	INIT_WORK(&clp->cl_local_probe_work, nfs_local_probe_async_work);
 #endif /* CONFIG_NFS_LOCALIO */
 
 	clp->cl_principal = "*";
@@ -244,7 +244,7 @@ static void pnfs_init_server(struct nfs_server *server)
  */
 void nfs_free_client(struct nfs_client *clp)
 {
-	nfs_local_disable(clp);
+	nfs_localio_disable_client(clp);
 
 	/* -EIO all pending I/O */
 	if (!IS_ERR(clp->cl_rpcclient))
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 492cffd9d3d8..2b04038b0e40 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1672,7 +1672,7 @@ nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry,
 	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
 }
 
-static int nfs_lookup_revalidate_dentry(struct inode *dir,
+static int nfs_lookup_revalidate_dentry(struct inode *dir, const struct qstr *name,
 					struct dentry *dentry,
 					struct inode *inode, unsigned int flags)
 {
@@ -1690,7 +1690,7 @@ static int nfs_lookup_revalidate_dentry(struct inode *dir,
 		goto out;
 
 	dir_verifier = nfs_save_change_attribute(dir);
-	ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
+	ret = NFS_PROTO(dir)->lookup(dir, dentry, name, fhandle, fattr);
 	if (ret < 0)
 		goto out;
 
@@ -1732,8 +1732,8 @@ out:
  * cached dentry and do a new lookup.
  */
 static int
-nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
-			 unsigned int flags)
+nfs_do_lookup_revalidate(struct inode *dir, const struct qstr *name,
+			 struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	int error = 0;
@@ -1775,7 +1775,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 	if (NFS_STALE(inode))
 		goto out_bad;
 
-	return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags);
+	return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags);
 out_valid:
 	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
 out_bad:
@@ -1785,38 +1785,26 @@ out_bad:
 }
 
 static int
-__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags,
-			int (*reval)(struct inode *, struct dentry *, unsigned int))
+__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *parent;
-	struct inode *dir;
-	int ret;
-
 	if (flags & LOOKUP_RCU) {
 		if (dentry->d_fsdata == NFS_FSDATA_BLOCKED)
 			return -ECHILD;
-		parent = READ_ONCE(dentry->d_parent);
-		dir = d_inode_rcu(parent);
-		if (!dir)
-			return -ECHILD;
-		ret = reval(dir, dentry, flags);
-		if (parent != READ_ONCE(dentry->d_parent))
-			return -ECHILD;
 	} else {
 		/* Wait for unlink to complete - see unblock_revalidate() */
 		wait_var_event(&dentry->d_fsdata,
 			       smp_load_acquire(&dentry->d_fsdata)
 			       != NFS_FSDATA_BLOCKED);
-		parent = dget_parent(dentry);
-		ret = reval(d_inode(parent), dentry, flags);
-		dput(parent);
 	}
-	return ret;
+	return 0;
 }
 
-static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int nfs_lookup_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
-	return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate);
+	if (__nfs_lookup_revalidate(dentry, flags))
+		return -ECHILD;
+	return nfs_do_lookup_revalidate(dir, name, dentry, flags);
 }
 
 static void block_revalidate(struct dentry *dentry)
@@ -1982,7 +1970,8 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
 
 	dir_verifier = nfs_save_change_attribute(dir);
 	trace_nfs_lookup_enter(dir, dentry, flags);
-	error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
+	error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name,
+				       fhandle, fattr);
 	if (error == -ENOENT) {
 		if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
 			dir_verifier = inode_peek_iversion_raw(dir);
@@ -2025,7 +2014,8 @@ void nfs_d_prune_case_insensitive_aliases(struct inode *inode)
 EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases);
 
 #if IS_ENABLED(CONFIG_NFS_V4)
-static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
+static int nfs4_lookup_revalidate(struct inode *, const struct qstr *,
+				  struct dentry *, unsigned int);
 
 const struct dentry_operations nfs4_dentry_operations = {
 	.d_revalidate	= nfs4_lookup_revalidate,
@@ -2214,11 +2204,14 @@ no_open:
 EXPORT_SYMBOL_GPL(nfs_atomic_open);
 
 static int
-nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
-			  unsigned int flags)
+nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name,
+		       struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 
+	if (__nfs_lookup_revalidate(dentry, flags))
+		return -ECHILD;
+
 	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
 
 	if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
@@ -2254,16 +2247,10 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 reval_dentry:
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
-	return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags);
+	return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags);
 
 full_reval:
-	return nfs_do_lookup_revalidate(dir, dentry, flags);
-}
-
-static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	return __nfs_lookup_revalidate(dentry, flags,
-			nfs4_do_lookup_revalidate);
+	return nfs_do_lookup_revalidate(dir, name, dentry, flags);
 }
 
 #endif /* CONFIG_NFSV4 */
@@ -2319,7 +2306,8 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
 	d_drop(dentry);
 
 	if (fhandle->size == 0) {
-		error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
+		error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name,
+					       fhandle, fattr);
 		if (error)
 			goto out_error;
 	}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b08dbe96bc57..f45beea92d03 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -303,6 +303,7 @@ static void nfs_read_sync_pgio_error(struct list_head *head, int error)
 static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr)
 {
 	get_dreq(hdr->dreq);
+	set_bit(NFS_IOHDR_ODIRECT, &hdr->flags);
 }
 
 static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index f78115c6c2c1..98b45b636be3 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -164,18 +164,17 @@ decode_name(struct xdr_stream *xdr, u32 *id)
 }
 
 static struct nfsd_file *
-ff_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx,
+		 struct nfs_client *clp, const struct cred *cred,
 		 struct nfs_fh *fh, fmode_t mode)
 {
-	if (mode & FMODE_WRITE) {
-		/*
-		 * Always request read and write access since this corresponds
-		 * to a rw layout.
-		 */
-		mode |= FMODE_READ;
-	}
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
 
-	return nfs_local_open_fh(clp, cred, fh, mode);
+	return nfs_local_open_fh(clp, cred, fh, &mirror->nfl, mode);
+#else
+	return NULL;
+#endif
 }
 
 static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
@@ -247,6 +246,7 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
 		spin_lock_init(&mirror->lock);
 		refcount_set(&mirror->ref, 1);
 		INIT_LIST_HEAD(&mirror->mirrors);
+		nfs_localio_file_init(&mirror->nfl);
 	}
 	return mirror;
 }
@@ -257,6 +257,7 @@ static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
 
 	ff_layout_remove_mirror(mirror);
 	kfree(mirror->fh_versions);
+	nfs_close_local_fh(&mirror->nfl);
 	cred = rcu_access_pointer(mirror->ro_cred);
 	put_cred(cred);
 	cred = rcu_access_pointer(mirror->rw_cred);
@@ -847,6 +848,9 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs4_pnfs_ds *ds;
 	u32 ds_idx;
 
+	if (NFS_SERVER(pgio->pg_inode)->flags &
+			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+		pgio->pg_maxretrans = io_maxretrans;
 retry:
 	pnfs_generic_pg_check_layout(pgio, req);
 	/* Use full layout for now */
@@ -860,6 +864,8 @@ retry:
 		if (!pgio->pg_lseg)
 			goto out_nolseg;
 	}
+	/* Reset wb_nio, since getting layout segment was successful */
+	req->wb_nio = 0;
 
 	ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
 	if (!ds) {
@@ -876,14 +882,24 @@ retry:
 	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
 
 	pgio->pg_mirror_idx = ds_idx;
-
-	if (NFS_SERVER(pgio->pg_inode)->flags &
-			(NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
-		pgio->pg_maxretrans = io_maxretrans;
 	return;
 out_nolseg:
-	if (pgio->pg_error < 0)
-		return;
+	if (pgio->pg_error < 0) {
+		if (pgio->pg_error != -EAGAIN)
+			return;
+		/* Retry getting layout segment if lower layer returned -EAGAIN */
+		if (pgio->pg_maxretrans && req->wb_nio++ > pgio->pg_maxretrans) {
+			if (NFS_SERVER(pgio->pg_inode)->flags & NFS_MOUNT_SOFTERR)
+				pgio->pg_error = -ETIMEDOUT;
+			else
+				pgio->pg_error = -EIO;
+			return;
+		}
+		pgio->pg_error = 0;
+		/* Sleep for 1 second before retrying */
+		ssleep(1);
+		goto retry;
+	}
 out_mds:
 	trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,
 			0, NFS4_MAX_UINT64, IOMODE_READ,
@@ -1820,7 +1836,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->mds_offset = offset;
 
 	/* Start IO accounting for local read */
-	localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh, FMODE_READ);
+	localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh, FMODE_READ);
 	if (localio) {
 		hdr->task.tk_start = ktime_get();
 		ff_layout_read_record_layoutstats_start(&hdr->task, hdr);
@@ -1896,7 +1912,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	hdr->args.offset = offset;
 
 	/* Start IO accounting for local write */
-	localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh,
+	localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
 				   FMODE_READ|FMODE_WRITE);
 	if (localio) {
 		hdr->task.tk_start = ktime_get();
@@ -1981,7 +1997,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 		data->args.fh = fh;
 
 	/* Start IO accounting for local commit */
-	localio = ff_local_open_fh(ds->ds_clp, ds_cred, fh,
+	localio = ff_local_open_fh(lseg, idx, ds->ds_clp, ds_cred, fh,
 				   FMODE_READ|FMODE_WRITE);
 	if (localio) {
 		data->task.tk_start = ktime_get();
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f84b3fb0dddd..095df09017a5 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -83,6 +83,7 @@ struct nfs4_ff_layout_mirror {
 	nfs4_stateid			stateid;
 	const struct cred __rcu		*ro_cred;
 	const struct cred __rcu		*rw_cred;
+	struct nfs_file_localio		nfl;
 	refcount_t			ref;
 	spinlock_t			lock;
 	unsigned long			flags;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 596f35170137..1aa67fca69b2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1137,6 +1137,8 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry,
 	ctx->lock_context.open_context = ctx;
 	INIT_LIST_HEAD(&ctx->list);
 	ctx->mdsthreshold = NULL;
+	nfs_localio_file_init(&ctx->nfl);
+
 	return ctx;
 }
 EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
@@ -1168,6 +1170,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	nfs_sb_deactive(sb);
 	put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1));
 	kfree(ctx->mdsthreshold);
+	nfs_close_local_fh(&ctx->nfl);
 	kfree_rcu(ctx, rcu_head);
 }
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index e564bd11ba60..fae2c7ae4acc 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -455,11 +455,13 @@ extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
 
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 /* localio.c */
-extern void nfs_local_disable(struct nfs_client *);
 extern void nfs_local_probe(struct nfs_client *);
+extern void nfs_local_probe_async(struct nfs_client *);
+extern void nfs_local_probe_async_work(struct work_struct *);
 extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *,
 					   const struct cred *,
 					   struct nfs_fh *,
+					   struct nfs_file_localio *,
 					   const fmode_t);
 extern int nfs_local_doio(struct nfs_client *,
 			  struct nfsd_file *,
@@ -471,11 +473,12 @@ extern int nfs_local_commit(struct nfsd_file *,
 extern bool nfs_server_is_local(const struct nfs_client *clp);
 
 #else /* CONFIG_NFS_LOCALIO */
-static inline void nfs_local_disable(struct nfs_client *clp) {}
 static inline void nfs_local_probe(struct nfs_client *clp) {}
+static inline void nfs_local_probe_async(struct nfs_client *clp) {}
 static inline struct nfsd_file *
 nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
-		  struct nfs_fh *fh, const fmode_t mode)
+		  struct nfs_fh *fh, struct nfs_file_localio *nfl,
+		  const fmode_t mode)
 {
 	return NULL;
 }
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 4b8618cf114c..5c21caeae075 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -35,6 +35,7 @@ struct nfs_local_kiocb {
 	struct bio_vec		*bvec;
 	struct nfs_pgio_header	*hdr;
 	struct work_struct	work;
+	void (*aio_complete_work)(struct work_struct *);
 	struct nfsd_file	*localio;
 };
 
@@ -48,9 +49,14 @@ struct nfs_local_fsync_ctx {
 static bool localio_enabled __read_mostly = true;
 module_param(localio_enabled, bool, 0644);
 
+static bool localio_O_DIRECT_semantics __read_mostly = false;
+module_param(localio_O_DIRECT_semantics, bool, 0644);
+MODULE_PARM_DESC(localio_O_DIRECT_semantics,
+		 "LOCALIO will use O_DIRECT semantics to filesystem.");
+
 static inline bool nfs_client_is_local(const struct nfs_client *clp)
 {
-	return !!test_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
+	return !!rcu_access_pointer(clp->cl_uuid.net);
 }
 
 bool nfs_server_is_local(const struct nfs_client *clp)
@@ -116,30 +122,6 @@ const struct rpc_program nfslocalio_program = {
 };
 
 /*
- * nfs_local_enable - enable local i/o for an nfs_client
- */
-static void nfs_local_enable(struct nfs_client *clp)
-{
-	spin_lock(&clp->cl_localio_lock);
-	set_bit(NFS_CS_LOCAL_IO, &clp->cl_flags);
-	trace_nfs_local_enable(clp);
-	spin_unlock(&clp->cl_localio_lock);
-}
-
-/*
- * nfs_local_disable - disable local i/o for an nfs_client
- */
-void nfs_local_disable(struct nfs_client *clp)
-{
-	spin_lock(&clp->cl_localio_lock);
-	if (test_and_clear_bit(NFS_CS_LOCAL_IO, &clp->cl_flags)) {
-		trace_nfs_local_disable(clp);
-		nfs_uuid_invalidate_one_client(&clp->cl_uuid);
-	}
-	spin_unlock(&clp->cl_localio_lock);
-}
-
-/*
  * nfs_init_localioclient - Initialise an NFS localio client connection
  */
 static struct rpc_clnt *nfs_init_localioclient(struct nfs_client *clp)
@@ -178,7 +160,7 @@ static bool nfs_server_uuid_is_local(struct nfs_client *clp)
 	rpc_shutdown_client(rpcclient_localio);
 
 	/* Server is only local if it initialized required struct members */
-	if (status || !clp->cl_uuid.net || !clp->cl_uuid.dom)
+	if (status || !rcu_access_pointer(clp->cl_uuid.net) || !clp->cl_uuid.dom)
 		return false;
 
 	return true;
@@ -194,44 +176,64 @@ void nfs_local_probe(struct nfs_client *clp)
 	/* Disallow localio if disabled via sysfs or AUTH_SYS isn't used */
 	if (!localio_enabled ||
 	    clp->cl_rpcclient->cl_auth->au_flavor != RPC_AUTH_UNIX) {
-		nfs_local_disable(clp);
+		nfs_localio_disable_client(clp);
 		return;
 	}
 
 	if (nfs_client_is_local(clp)) {
 		/* If already enabled, disable and re-enable */
-		nfs_local_disable(clp);
+		nfs_localio_disable_client(clp);
 	}
 
 	if (!nfs_uuid_begin(&clp->cl_uuid))
 		return;
 	if (nfs_server_uuid_is_local(clp))
-		nfs_local_enable(clp);
+		nfs_localio_enable_client(clp);
 	nfs_uuid_end(&clp->cl_uuid);
 }
 EXPORT_SYMBOL_GPL(nfs_local_probe);
 
+void nfs_local_probe_async_work(struct work_struct *work)
+{
+	struct nfs_client *clp =
+		container_of(work, struct nfs_client, cl_local_probe_work);
+
+	nfs_local_probe(clp);
+}
+
+void nfs_local_probe_async(struct nfs_client *clp)
+{
+	queue_work(nfsiod_workqueue, &clp->cl_local_probe_work);
+}
+EXPORT_SYMBOL_GPL(nfs_local_probe_async);
+
+static inline struct nfsd_file *nfs_local_file_get(struct nfsd_file *nf)
+{
+	return nfs_to->nfsd_file_get(nf);
+}
+
+static inline void nfs_local_file_put(struct nfsd_file *nf)
+{
+	nfs_to->nfsd_file_put(nf);
+}
+
 /*
- * nfs_local_open_fh - open a local filehandle in terms of nfsd_file
+ * __nfs_local_open_fh - open a local filehandle in terms of nfsd_file.
  *
- * Returns a pointer to a struct nfsd_file or NULL
+ * Returns a pointer to a struct nfsd_file or ERR_PTR.
+ * Caller must release returned nfsd_file with nfs_to_nfsd_file_put_local().
  */
-struct nfsd_file *
-nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
-		  struct nfs_fh *fh, const fmode_t mode)
+static struct nfsd_file *
+__nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+		    struct nfs_fh *fh, struct nfs_file_localio *nfl,
+		    const fmode_t mode)
 {
 	struct nfsd_file *localio;
-	int status;
-
-	if (!nfs_server_is_local(clp))
-		return NULL;
-	if (mode & ~(FMODE_READ | FMODE_WRITE))
-		return NULL;
 
 	localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient,
-				    cred, fh, mode);
+				    cred, fh, nfl, mode);
 	if (IS_ERR(localio)) {
-		status = PTR_ERR(localio);
+		int status = PTR_ERR(localio);
 		trace_nfs_local_open_fh(fh, mode, status);
 		switch (status) {
 		case -ENOMEM:
@@ -240,10 +242,59 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 			/* Revalidate localio, will disable if unsupported */
 			nfs_local_probe(clp);
 		}
-		return NULL;
 	}
 	return localio;
 }
+
+/*
+ * nfs_local_open_fh - open a local filehandle in terms of nfsd_file.
+ * First checking if the open nfsd_file is already cached, otherwise
+ * must __nfs_local_open_fh and insert the nfsd_file in nfs_file_localio.
+ *
+ * Returns a pointer to a struct nfsd_file or NULL.
+ */
+struct nfsd_file *
+nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
+		  struct nfs_fh *fh, struct nfs_file_localio *nfl,
+		  const fmode_t mode)
+{
+	struct nfsd_file *nf, *new, __rcu **pnf;
+
+	if (!nfs_server_is_local(clp))
+		return NULL;
+	if (mode & ~(FMODE_READ | FMODE_WRITE))
+		return NULL;
+
+	if (mode & FMODE_WRITE)
+		pnf = &nfl->rw_file;
+	else
+		pnf = &nfl->ro_file;
+
+	new = NULL;
+	rcu_read_lock();
+	nf = rcu_dereference(*pnf);
+	if (!nf) {
+		rcu_read_unlock();
+		new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
+		if (IS_ERR(new))
+			return NULL;
+		/* try to swap in the pointer */
+		spin_lock(&clp->cl_uuid.lock);
+		nf = rcu_dereference_protected(*pnf, 1);
+		if (!nf) {
+			nf = new;
+			new = NULL;
+			rcu_assign_pointer(*pnf, nf);
+		}
+		spin_unlock(&clp->cl_uuid.lock);
+		rcu_read_lock();
+	}
+	nf = nfs_local_file_get(nf);
+	rcu_read_unlock();
+	if (new)
+		nfs_to_nfsd_file_put_local(new);
+	return nf;
+}
 EXPORT_SYMBOL_GPL(nfs_local_open_fh);
 
 static struct bio_vec *
@@ -285,10 +336,19 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 		kfree(iocb);
 		return NULL;
 	}
-	init_sync_kiocb(&iocb->kiocb, file);
+
+	if (localio_O_DIRECT_semantics &&
+	    test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) {
+		iocb->kiocb.ki_filp = file;
+		iocb->kiocb.ki_flags = IOCB_DIRECT;
+	} else
+		init_sync_kiocb(&iocb->kiocb, file);
+
 	iocb->kiocb.ki_pos = hdr->args.offset;
 	iocb->hdr = hdr;
 	iocb->kiocb.ki_flags &= ~IOCB_APPEND;
+	iocb->aio_complete_work = NULL;
+
 	return iocb;
 }
 
@@ -328,7 +388,7 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
 		hdr->res.op_status = NFS4_OK;
 		hdr->task.tk_status = 0;
 	} else {
-		hdr->res.op_status = nfs4_stat_to_errno(status);
+		hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status);
 		hdr->task.tk_status = status;
 	}
 }
@@ -338,11 +398,23 @@ nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
 
-	nfs_to_nfsd_file_put_local(iocb->localio);
+	nfs_local_file_put(iocb->localio);
 	nfs_local_iocb_free(iocb);
 	nfs_local_hdr_release(hdr, hdr->task.tk_ops);
 }
 
+/*
+ * Complete the I/O from iocb->kiocb.ki_complete()
+ *
+ * Note that this function can be called from a bottom half context,
+ * hence we need to queue the rpc_call_done() etc to a workqueue
+ */
+static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb)
+{
+	INIT_WORK(&iocb->work, iocb->aio_complete_work);
+	queue_work(nfsiod_workqueue, &iocb->work);
+}
+
 static void
 nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 {
@@ -365,6 +437,23 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 			status > 0 ? status : 0, hdr->res.eof);
 }
 
+static void nfs_local_read_aio_complete_work(struct work_struct *work)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(work, struct nfs_local_kiocb, work);
+
+	nfs_local_pgio_release(iocb);
+}
+
+static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(kiocb, struct nfs_local_kiocb, kiocb);
+
+	nfs_local_read_done(iocb, ret);
+	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */
+}
+
 static void nfs_local_call_read(struct work_struct *work)
 {
 	struct nfs_local_kiocb *iocb =
@@ -379,10 +468,10 @@ static void nfs_local_call_read(struct work_struct *work)
 	nfs_local_iter_init(&iter, iocb, READ);
 
 	status = filp->f_op->read_iter(&iocb->kiocb, &iter);
-	WARN_ON_ONCE(status == -EIOCBQUEUED);
-
-	nfs_local_read_done(iocb, status);
-	nfs_local_pgio_release(iocb);
+	if (status != -EIOCBQUEUED) {
+		nfs_local_read_done(iocb, status);
+		nfs_local_pgio_release(iocb);
+	}
 
 	revert_creds(save_cred);
 }
@@ -410,6 +499,11 @@ nfs_do_local_read(struct nfs_pgio_header *hdr,
 	nfs_local_pgio_init(hdr, call_ops);
 	hdr->res.eof = false;
 
+	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+		iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
+		iocb->aio_complete_work = nfs_local_read_aio_complete_work;
+	}
+
 	INIT_WORK(&iocb->work, nfs_local_call_read);
 	queue_work(nfslocaliod_workqueue, &iocb->work);
 
@@ -534,6 +628,24 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
 	nfs_local_pgio_done(hdr, status);
 }
 
+static void nfs_local_write_aio_complete_work(struct work_struct *work)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(work, struct nfs_local_kiocb, work);
+
+	nfs_local_vfs_getattr(iocb);
+	nfs_local_pgio_release(iocb);
+}
+
+static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
+{
+	struct nfs_local_kiocb *iocb =
+		container_of(kiocb, struct nfs_local_kiocb, kiocb);
+
+	nfs_local_write_done(iocb, ret);
+	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */
+}
+
 static void nfs_local_call_write(struct work_struct *work)
 {
 	struct nfs_local_kiocb *iocb =
@@ -552,11 +664,11 @@ static void nfs_local_call_write(struct work_struct *work)
 	file_start_write(filp);
 	status = filp->f_op->write_iter(&iocb->kiocb, &iter);
 	file_end_write(filp);
-	WARN_ON_ONCE(status == -EIOCBQUEUED);
-
-	nfs_local_write_done(iocb, status);
-	nfs_local_vfs_getattr(iocb);
-	nfs_local_pgio_release(iocb);
+	if (status != -EIOCBQUEUED) {
+		nfs_local_write_done(iocb, status);
+		nfs_local_vfs_getattr(iocb);
+		nfs_local_pgio_release(iocb);
+	}
 
 	revert_creds(save_cred);
 	current->flags = old_flags;
@@ -592,10 +704,16 @@ nfs_do_local_write(struct nfs_pgio_header *hdr,
 	case NFS_FILE_SYNC:
 		iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
 	}
+
 	nfs_local_pgio_init(hdr, call_ops);
 
 	nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
 
+	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
+		iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
+		iocb->aio_complete_work = nfs_local_write_aio_complete_work;
+	}
+
 	INIT_WORK(&iocb->work, nfs_local_call_write);
 	queue_work(nfslocaliod_workqueue, &iocb->work);
 
@@ -626,8 +744,8 @@ int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
 
 	if (status != 0) {
 		if (status == -EAGAIN)
-			nfs_local_disable(clp);
-		nfs_to_nfsd_file_put_local(localio);
+			nfs_localio_disable_client(clp);
+		nfs_local_file_put(localio);
 		hdr->task.tk_status = status;
 		nfs_local_hdr_release(hdr, call_ops);
 	}
@@ -668,7 +786,7 @@ nfs_local_commit_done(struct nfs_commit_data *data, int status)
 		data->task.tk_status = 0;
 	} else {
 		nfs_reset_boot_verifier(data->inode);
-		data->res.op_status = nfs4_stat_to_errno(status);
+		data->res.op_status = nfs_localio_errno_to_nfs4_stat(status);
 		data->task.tk_status = status;
 	}
 }
@@ -678,7 +796,7 @@ nfs_local_release_commit_data(struct nfsd_file *localio,
 		struct nfs_commit_data *data,
 		const struct rpc_call_ops *call_ops)
 {
-	nfs_to_nfsd_file_put_local(localio);
+	nfs_local_file_put(localio);
 	call_ops->rpc_call_done(&data->task, data);
 	call_ops->rpc_release(data);
 }
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 2d53574da605..973aed9cc5fe 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -308,7 +308,7 @@ int nfs_submount(struct fs_context *fc, struct nfs_server *server)
 	int err;
 
 	/* Look it up again to get its attributes */
-	err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry,
+	err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, &dentry->d_name,
 						  ctx->mntfh, ctx->clone_data.fattr);
 	dput(parent);
 	if (err != 0)
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 1566163c6d85..0c3bc98cd999 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -192,7 +192,7 @@ __nfs3_proc_lookup(struct inode *dir, const char *name, size_t len,
 }
 
 static int
-nfs3_proc_lookup(struct inode *dir, struct dentry *dentry,
+nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name,
 		 struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	unsigned short task_flags = 0;
@@ -202,8 +202,7 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry,
 		task_flags |= RPC_TASK_TIMEOUT;
 
 	dprintk("NFS call  lookup %pd2\n", dentry);
-	return __nfs3_proc_lookup(dir, dentry->d_name.name,
-				  dentry->d_name.len, fhandle, fattr,
+	return __nfs3_proc_lookup(dir, name->name, name->len, fhandle, fattr,
 				  task_flags);
 }
 
@@ -844,6 +843,41 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return status;
 }
 
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+static unsigned nfs3_localio_probe_throttle __read_mostly = 0;
+module_param(nfs3_localio_probe_throttle, uint, 0644);
+MODULE_PARM_DESC(nfs3_localio_probe_throttle,
+		 "Probe for NFSv3 LOCALIO every N IO requests. Must be power-of-2, defaults to 0 (probing disabled).");
+
+static void nfs3_localio_probe(struct nfs_server *server)
+{
+	struct nfs_client *clp = server->nfs_client;
+
+	/* Throttled to reduce nfs_local_probe_async() frequency */
+	if (!nfs3_localio_probe_throttle || nfs_server_is_local(clp))
+		return;
+
+	/*
+	 * Try (re)enabling LOCALIO if isn't enabled -- admin deems
+	 * it worthwhile to periodically check if LOCALIO possible by
+	 * setting the 'nfs3_localio_probe_throttle' module parameter.
+	 *
+	 * This is useful if LOCALIO was previously enabled, but was
+	 * disabled due to server restart, and IO has successfully
+	 * completed in terms of normal RPC.
+	 */
+	if ((clp->cl_uuid.nfs3_localio_probe_count++ &
+	     (nfs3_localio_probe_throttle - 1)) == 0) {
+		if (!nfs_server_is_local(clp))
+			nfs_local_probe_async(clp);
+	}
+}
+
+#else
+static void nfs3_localio_probe(struct nfs_server *server) {}
+#endif
+
 static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
@@ -855,8 +889,11 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
-	if (task->tk_status >= 0 && !server->read_hdrsize)
-		cmpxchg(&server->read_hdrsize, 0, hdr->res.replen);
+	if (task->tk_status >= 0) {
+		if (!server->read_hdrsize)
+			cmpxchg(&server->read_hdrsize, 0, hdr->res.replen);
+		nfs3_localio_probe(server);
+	}
 
 	nfs_invalidate_atime(inode);
 	nfs_refresh_inode(inode, &hdr->fattr);
@@ -886,8 +923,10 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
-	if (task->tk_status >= 0)
+	if (task->tk_status >= 0) {
 		nfs_writeback_update_inode(hdr);
+		nfs3_localio_probe(NFS_SERVER(inode));
+	}
 	return 0;
 }
 
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 531c9c20ef1d..1924c4a2077b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -498,15 +498,15 @@ out_put_src_lock:
 	return err;
 }
 
-struct nfs42_offloadcancel_data {
+struct nfs42_offload_data {
 	struct nfs_server *seq_server;
 	struct nfs42_offload_status_args args;
 	struct nfs42_offload_status_res res;
 };
 
-static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata)
+static void nfs42_offload_prepare(struct rpc_task *task, void *calldata)
 {
-	struct nfs42_offloadcancel_data *data = calldata;
+	struct nfs42_offload_data *data = calldata;
 
 	nfs4_setup_sequence(data->seq_server->nfs_client,
 				&data->args.osa_seq_args,
@@ -515,7 +515,7 @@ static void nfs42_offload_cancel_prepare(struct rpc_task *task, void *calldata)
 
 static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata)
 {
-	struct nfs42_offloadcancel_data *data = calldata;
+	struct nfs42_offload_data *data = calldata;
 
 	trace_nfs4_offload_cancel(&data->args, task->tk_status);
 	nfs41_sequence_done(task, &data->res.osr_seq_res);
@@ -525,22 +525,22 @@ static void nfs42_offload_cancel_done(struct rpc_task *task, void *calldata)
 		rpc_restart_call_prepare(task);
 }
 
-static void nfs42_free_offloadcancel_data(void *data)
+static void nfs42_offload_release(void *data)
 {
 	kfree(data);
 }
 
 static const struct rpc_call_ops nfs42_offload_cancel_ops = {
-	.rpc_call_prepare = nfs42_offload_cancel_prepare,
+	.rpc_call_prepare = nfs42_offload_prepare,
 	.rpc_call_done = nfs42_offload_cancel_done,
-	.rpc_release = nfs42_free_offloadcancel_data,
+	.rpc_release = nfs42_offload_release,
 };
 
 static int nfs42_do_offload_cancel_async(struct file *dst,
 					 nfs4_stateid *stateid)
 {
 	struct nfs_server *dst_server = NFS_SERVER(file_inode(dst));
-	struct nfs42_offloadcancel_data *data = NULL;
+	struct nfs42_offload_data *data = NULL;
 	struct nfs_open_context *ctx = nfs_file_open_context(dst);
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -552,14 +552,14 @@ static int nfs42_do_offload_cancel_async(struct file *dst,
 		.rpc_message = &msg,
 		.callback_ops = &nfs42_offload_cancel_ops,
 		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
+		.flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE,
 	};
 	int status;
 
 	if (!(dst_server->caps & NFS_CAP_OFFLOAD_CANCEL))
 		return -EOPNOTSUPP;
 
-	data = kzalloc(sizeof(struct nfs42_offloadcancel_data), GFP_KERNEL);
+	data = kzalloc(sizeof(struct nfs42_offload_data), GFP_KERNEL);
 	if (data == NULL)
 		return -ENOMEM;
 
@@ -861,7 +861,7 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server,
 		.rpc_message = &msg,
 		.callback_ops = &nfs42_layoutstat_ops,
 		.callback_data = data,
-		.flags = RPC_TASK_ASYNC,
+		.flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE,
 	};
 	struct rpc_task *task;
 
@@ -1016,7 +1016,7 @@ int nfs42_proc_layouterror(struct pnfs_layout_segment *lseg,
 	struct rpc_task_setup task_setup = {
 		.rpc_message = &msg,
 		.callback_ops = &nfs42_layouterror_ops,
-		.flags = RPC_TASK_ASYNC,
+		.flags = RPC_TASK_ASYNC | RPC_TASK_MOVEABLE,
 	};
 	unsigned int i;
 
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 9e3ae53e2205..5072d7ea72e9 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -144,9 +144,11 @@
 					 decode_putfh_maxsz + \
 					 decode_offload_cancel_maxsz)
 #define NFS4_enc_copy_notify_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_copy_notify_maxsz)
 #define NFS4_dec_copy_notify_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_copy_notify_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
@@ -549,7 +551,7 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
 }
 
 /*
- * Encode OFFLOAD_CANEL request
+ * Encode OFFLOAD_CANCEL request
  */
 static void nfs4_xdr_enc_offload_cancel(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d615d520f8cf..df9669d4ded7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4544,15 +4544,15 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 }
 
 static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
-		struct dentry *dentry, struct nfs_fh *fhandle,
-		struct nfs_fattr *fattr)
+		struct dentry *dentry, const struct qstr *name,
+		struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	struct nfs_server *server = NFS_SERVER(dir);
 	int		       status;
 	struct nfs4_lookup_arg args = {
 		.bitmask = server->attr_bitmask,
 		.dir_fh = NFS_FH(dir),
-		.name = &dentry->d_name,
+		.name = name,
 	};
 	struct nfs4_lookup_res res = {
 		.server = server,
@@ -4594,17 +4594,16 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr)
 }
 
 static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
-				   struct dentry *dentry, struct nfs_fh *fhandle,
-				   struct nfs_fattr *fattr)
+				   struct dentry *dentry, const struct qstr *name,
+				   struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	struct nfs4_exception exception = {
 		.interruptible = true,
 	};
 	struct rpc_clnt *client = *clnt;
-	const struct qstr *name = &dentry->d_name;
 	int err;
 	do {
-		err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr);
+		err = _nfs4_proc_lookup(client, dir, dentry, name, fhandle, fattr);
 		trace_nfs4_lookup(dir, name, err);
 		switch (err) {
 		case -NFS4ERR_BADNAME:
@@ -4639,13 +4638,13 @@ out:
 	return err;
 }
 
-static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry,
+static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name,
 			    struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	int status;
 	struct rpc_clnt *client = NFS_CLIENT(dir);
 
-	status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr);
+	status = nfs4_proc_lookup_common(&client, dir, dentry, name, fhandle, fattr);
 	if (client != NFS_CLIENT(dir)) {
 		rpc_shutdown_client(client);
 		nfs_fixup_secinfo_attributes(fattr);
@@ -4660,7 +4659,8 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry,
 	struct rpc_clnt *client = NFS_CLIENT(dir);
 	int status;
 
-	status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr);
+	status = nfs4_proc_lookup_common(&client, dir, dentry, &dentry->d_name,
+					 fhandle, fattr);
 	if (status < 0)
 		return ERR_PTR(status);
 	return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9a9f60a2291b..542cdf71229f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1955,6 +1955,7 @@ restart:
 	}
 	rcu_read_unlock();
 	nfs4_free_state_owners(&freeme);
+	nfs_local_probe_async(clp);
 	if (lost_locks)
 		pr_warn("NFS: %s: lost %d locks\n",
 			clp->cl_hostname, lost_locks);
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 886a7c4c60b3..d1a92d8f8ba4 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -17,7 +17,7 @@ static const int nfs_set_port_min;
 static const int nfs_set_port_max = 65535;
 static struct ctl_table_header *nfs4_callback_sysctl_table;
 
-static struct ctl_table nfs4_cb_sysctls[] = {
+static const struct ctl_table nfs4_cb_sysctls[] = {
 	{
 		.procname = "nfs_callback_tcpport",
 		.data = &nfs_callback_set_tcpport,
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 1eab98c277fa..7a058bd8c566 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -1714,38 +1714,6 @@ TRACE_EVENT(nfs_local_open_fh,
 		)
 );
 
-DECLARE_EVENT_CLASS(nfs_local_client_event,
-		TP_PROTO(
-			const struct nfs_client *clp
-		),
-
-		TP_ARGS(clp),
-
-		TP_STRUCT__entry(
-			__field(unsigned int, protocol)
-			__string(server, clp->cl_hostname)
-		),
-
-		TP_fast_assign(
-			__entry->protocol = clp->rpc_ops->version;
-			__assign_str(server);
-		),
-
-		TP_printk(
-			"server=%s NFSv%u", __get_str(server), __entry->protocol
-		)
-);
-
-#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \
-	DEFINE_EVENT(nfs_local_client_event, name, \
-			TP_PROTO( \
-				const struct nfs_client *clp \
-			), \
-			TP_ARGS(clp))
-
-DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_enable);
-DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_local_disable);
-
 DECLARE_EVENT_CLASS(nfs_xdr_event,
 		TP_PROTO(
 			const struct xdr_stream *xdr,
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index e27c07bd8929..11968dcb7243 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -961,8 +961,9 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 		struct nfs_client *clp = NFS_SERVER(hdr->inode)->nfs_client;
 
 		struct nfsd_file *localio =
-			nfs_local_open_fh(clp, hdr->cred,
-					  hdr->args.fh, hdr->args.context->mode);
+			nfs_local_open_fh(clp, hdr->cred, hdr->args.fh,
+					  &hdr->args.context->nfl,
+					  hdr->args.context->mode);
 
 		if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion)
 			task_flags = RPC_TASK_MOVEABLE;
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 6c09cd090c34..77920a2e3cef 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -153,13 +153,13 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 }
 
 static int
-nfs_proc_lookup(struct inode *dir, struct dentry *dentry,
+nfs_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name,
 		struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	struct nfs_diropargs	arg = {
 		.fh		= NFS_FH(dir),
-		.name		= dentry->d_name.name,
-		.len		= dentry->d_name.len
+		.name		= name->name,
+		.len		= name->len
 	};
 	struct nfs_diropok	res = {
 		.fh		= fhandle,
diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c
index e645be1a3381..f579df0e8d67 100644
--- a/fs/nfs/sysctl.c
+++ b/fs/nfs/sysctl.c
@@ -14,7 +14,7 @@
 
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
-static struct ctl_table nfs_cb_sysctls[] = {
+static const struct ctl_table nfs_cb_sysctls[] = {
 	{
 		.procname	= "nfs_mountpoint_timeout",
 		.data		= &nfs_mountpoint_expiry_timeout,
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index bf378ecd5d9f..7b59a40d40c0 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -280,9 +280,9 @@ void nfs_sysfs_link_rpc_client(struct nfs_server *server,
 	char name[RPC_CLIENT_NAME_SIZE];
 	int ret;
 
-	strcpy(name, clnt->cl_program->name);
-	strcat(name, uniq ? uniq : "");
-	strcat(name, "_client");
+	strscpy(name, clnt->cl_program->name, sizeof(name));
+	strncat(name, uniq ? uniq : "", sizeof(name) - strlen(name) - 1);
+	strncat(name, "_client", sizeof(name) - strlen(name) - 1);
 
 	ret = sysfs_create_link_nowarn(&server->kobj,
 						&clnt->cl_sysfs->kobject, name);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 50fa539611f5..aa3d8bea3ec0 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1826,7 +1826,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 		task_flags = RPC_TASK_MOVEABLE;
 
 	localio = nfs_local_open_fh(NFS_SERVER(inode)->nfs_client, data->cred,
-				    data->args.fh, data->context->mode);
+				    data->args.fh, &data->context->nfl,
+				    data->context->mode);
 	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
 				   data->mds_ops, how,
 				   RPC_TASK_CRED_NOREF | task_flags, localio);
diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile
index a5e54809701e..c10ead273ff2 100644
--- a/fs/nfs_common/Makefile
+++ b/fs/nfs_common/Makefile
@@ -6,8 +6,9 @@
 obj-$(CONFIG_NFS_ACL_SUPPORT) += nfs_acl.o
 nfs_acl-objs := nfsacl.o
 
+CFLAGS_localio_trace.o += -I$(src)
 obj-$(CONFIG_NFS_COMMON_LOCALIO_SUPPORT) += nfs_localio.o
-nfs_localio-objs := nfslocalio.o
+nfs_localio-objs := nfslocalio.o localio_trace.o
 
 obj-$(CONFIG_GRACE_PERIOD) += grace.o
 obj-$(CONFIG_NFS_V4_2_SSC_HELPER) += nfs_ssc.o
diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c
index 34a115176f97..af09aed09fd2 100644
--- a/fs/nfs_common/common.c
+++ b/fs/nfs_common/common.c
@@ -15,7 +15,7 @@ static const struct {
 	{ NFS_OK,		0		},
 	{ NFSERR_PERM,		-EPERM		},
 	{ NFSERR_NOENT,		-ENOENT		},
-	{ NFSERR_IO,		-errno_NFSERR_IO},
+	{ NFSERR_IO,		-EIO		},
 	{ NFSERR_NXIO,		-ENXIO		},
 /*	{ NFSERR_EAGAIN,	-EAGAIN		}, */
 	{ NFSERR_ACCES,		-EACCES		},
@@ -45,7 +45,6 @@ static const struct {
 	{ NFSERR_SERVERFAULT,	-EREMOTEIO	},
 	{ NFSERR_BADTYPE,	-EBADTYPE	},
 	{ NFSERR_JUKEBOX,	-EJUKEBOX	},
-	{ -1,			-EIO		}
 };
 
 /**
@@ -59,26 +58,29 @@ int nfs_stat_to_errno(enum nfs_stat status)
 {
 	int i;
 
-	for (i = 0; nfs_errtbl[i].stat != -1; i++) {
+	for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) {
 		if (nfs_errtbl[i].stat == (int)status)
 			return nfs_errtbl[i].errno;
 	}
-	return nfs_errtbl[i].errno;
+	return -EIO;
 }
 EXPORT_SYMBOL_GPL(nfs_stat_to_errno);
 
 /*
  * We need to translate between nfs v4 status return values and
  * the local errno values which may not be the same.
+ *
+ * nfs4_errtbl_common[] is used before more specialized mappings
+ * available in nfs4_errtbl[] or nfs4_errtbl_localio[].
  */
 static const struct {
 	int stat;
 	int errno;
-} nfs4_errtbl[] = {
+} nfs4_errtbl_common[] = {
 	{ NFS4_OK,		0		},
 	{ NFS4ERR_PERM,		-EPERM		},
 	{ NFS4ERR_NOENT,	-ENOENT		},
-	{ NFS4ERR_IO,		-errno_NFSERR_IO},
+	{ NFS4ERR_IO,		-EIO		},
 	{ NFS4ERR_NXIO,		-ENXIO		},
 	{ NFS4ERR_ACCESS,	-EACCES		},
 	{ NFS4ERR_EXIST,	-EEXIST		},
@@ -98,15 +100,20 @@ static const struct {
 	{ NFS4ERR_BAD_COOKIE,	-EBADCOOKIE	},
 	{ NFS4ERR_NOTSUPP,	-ENOTSUPP	},
 	{ NFS4ERR_TOOSMALL,	-ETOOSMALL	},
-	{ NFS4ERR_SERVERFAULT,	-EREMOTEIO	},
 	{ NFS4ERR_BADTYPE,	-EBADTYPE	},
-	{ NFS4ERR_LOCKED,	-EAGAIN		},
 	{ NFS4ERR_SYMLINK,	-ELOOP		},
-	{ NFS4ERR_OP_ILLEGAL,	-EOPNOTSUPP	},
 	{ NFS4ERR_DEADLOCK,	-EDEADLK	},
+};
+
+static const struct {
+	int stat;
+	int errno;
+} nfs4_errtbl[] = {
+	{ NFS4ERR_SERVERFAULT,	-EREMOTEIO	},
+	{ NFS4ERR_LOCKED,	-EAGAIN		},
+	{ NFS4ERR_OP_ILLEGAL,	-EOPNOTSUPP	},
 	{ NFS4ERR_NOXATTR,	-ENODATA	},
 	{ NFS4ERR_XATTR2BIG,	-E2BIG		},
-	{ -1,			-EIO		}
 };
 
 /*
@@ -116,7 +123,14 @@ static const struct {
 int nfs4_stat_to_errno(int stat)
 {
 	int i;
-	for (i = 0; nfs4_errtbl[i].stat != -1; i++) {
+
+	/* First check nfs4_errtbl_common */
+	for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_common); i++) {
+		if (nfs4_errtbl_common[i].stat == stat)
+			return nfs4_errtbl_common[i].errno;
+	}
+	/* Then check nfs4_errtbl */
+	for (i = 0; i < ARRAY_SIZE(nfs4_errtbl); i++) {
 		if (nfs4_errtbl[i].stat == stat)
 			return nfs4_errtbl[i].errno;
 	}
@@ -132,3 +146,56 @@ int nfs4_stat_to_errno(int stat)
 	return -stat;
 }
 EXPORT_SYMBOL_GPL(nfs4_stat_to_errno);
+
+/*
+ * This table is useful for conversion from local errno to NFS error.
+ * It provides more logically correct mappings for use with LOCALIO
+ * (which is focused on converting from errno to NFS status).
+ */
+static const struct {
+	int stat;
+	int errno;
+} nfs4_errtbl_localio[] = {
+	/* Map errors differently than nfs4_errtbl */
+	{ NFS4ERR_IO,		-EREMOTEIO	},
+	{ NFS4ERR_DELAY,	-EAGAIN		},
+	{ NFS4ERR_FBIG,		-E2BIG		},
+	/* Map errors not handled by nfs4_errtbl */
+	{ NFS4ERR_STALE,	-EBADF		},
+	{ NFS4ERR_STALE,	-EOPENSTALE	},
+	{ NFS4ERR_DELAY,	-ETIMEDOUT	},
+	{ NFS4ERR_DELAY,	-ERESTARTSYS	},
+	{ NFS4ERR_DELAY,	-ENOMEM		},
+	{ NFS4ERR_IO,		-ETXTBSY	},
+	{ NFS4ERR_IO,		-EBUSY		},
+	{ NFS4ERR_SERVERFAULT,	-ESERVERFAULT	},
+	{ NFS4ERR_SERVERFAULT,	-ENFILE		},
+	{ NFS4ERR_IO,		-EUCLEAN	},
+	{ NFS4ERR_PERM,		-ENOKEY		},
+};
+
+/*
+ * Convert an errno to an NFS error code for LOCALIO.
+ */
+__u32 nfs_localio_errno_to_nfs4_stat(int errno)
+{
+	int i;
+
+	/* First check nfs4_errtbl_common */
+	for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_common); i++) {
+		if (nfs4_errtbl_common[i].errno == errno)
+			return nfs4_errtbl_common[i].stat;
+	}
+	/* Then check nfs4_errtbl_localio */
+	for (i = 0; i < ARRAY_SIZE(nfs4_errtbl_localio); i++) {
+		if (nfs4_errtbl_localio[i].errno == errno)
+			return nfs4_errtbl_localio[i].stat;
+	}
+	/* If we cannot translate the error, the recovery routines should
+	 * handle it.
+	 * Note: remaining NFSv4 error codes have values > 10000, so should
+	 * not conflict with native Linux error codes.
+	 */
+	return NFS4ERR_SERVERFAULT;
+}
+EXPORT_SYMBOL_GPL(nfs_localio_errno_to_nfs4_stat);
diff --git a/fs/nfs_common/localio_trace.c b/fs/nfs_common/localio_trace.c
new file mode 100644
index 000000000000..7decfe57abeb
--- /dev/null
+++ b/fs/nfs_common/localio_trace.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+#include <linux/nfs_fs.h>
+#include <linux/namei.h>
+
+#define CREATE_TRACE_POINTS
+#include "localio_trace.h"
diff --git a/fs/nfs_common/localio_trace.h b/fs/nfs_common/localio_trace.h
new file mode 100644
index 000000000000..4055aec9ff8d
--- /dev/null
+++ b/fs/nfs_common/localio_trace.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024 Trond Myklebust <trond.myklebust@hammerspace.com>
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nfs_localio
+
+#if !defined(_TRACE_NFS_COMMON_LOCALIO_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NFS_COMMON_LOCALIO_H
+
+#include <linux/tracepoint.h>
+
+#include <trace/misc/fs.h>
+#include <trace/misc/nfs.h>
+#include <trace/misc/sunrpc.h>
+
+DECLARE_EVENT_CLASS(nfs_local_client_event,
+		TP_PROTO(
+			const struct nfs_client *clp
+		),
+
+		TP_ARGS(clp),
+
+		TP_STRUCT__entry(
+			__field(unsigned int, protocol)
+			__string(server, clp->cl_hostname)
+		),
+
+		TP_fast_assign(
+			__entry->protocol = clp->rpc_ops->version;
+			__assign_str(server);
+		),
+
+		TP_printk(
+			"server=%s NFSv%u", __get_str(server), __entry->protocol
+		)
+);
+
+#define DEFINE_NFS_LOCAL_CLIENT_EVENT(name) \
+	DEFINE_EVENT(nfs_local_client_event, name, \
+			TP_PROTO( \
+				const struct nfs_client *clp \
+			), \
+			TP_ARGS(clp))
+
+DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_localio_enable_client);
+DEFINE_NFS_LOCAL_CLIENT_EVENT(nfs_localio_disable_client);
+
+#endif /* _TRACE_NFS_COMMON_LOCALIO_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE localio_trace
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
index a74ec08f6c96..6a0bdea6d644 100644
--- a/fs/nfs_common/nfslocalio.c
+++ b/fs/nfs_common/nfslocalio.c
@@ -7,38 +7,67 @@
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/nfslocalio.h>
+#include <linux/nfs3.h>
+#include <linux/nfs4.h>
+#include <linux/nfs_fs.h>
 #include <net/netns/generic.h>
 
+#include "localio_trace.h"
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("NFS localio protocol bypass support");
 
-static DEFINE_SPINLOCK(nfs_uuid_lock);
+static DEFINE_SPINLOCK(nfs_uuids_lock);
 
 /*
  * Global list of nfs_uuid_t instances
- * that is protected by nfs_uuid_lock.
+ * that is protected by nfs_uuids_lock.
  */
 static LIST_HEAD(nfs_uuids);
 
+/*
+ * Lock ordering:
+ * 1: nfs_uuid->lock
+ * 2: nfs_uuids_lock
+ * 3: nfs_uuid->list_lock (aka nn->local_clients_lock)
+ *
+ * May skip locks in select cases, but never hold multiple
+ * locks out of order.
+ */
+
 void nfs_uuid_init(nfs_uuid_t *nfs_uuid)
 {
-	nfs_uuid->net = NULL;
+	RCU_INIT_POINTER(nfs_uuid->net, NULL);
 	nfs_uuid->dom = NULL;
+	nfs_uuid->list_lock = NULL;
 	INIT_LIST_HEAD(&nfs_uuid->list);
+	INIT_LIST_HEAD(&nfs_uuid->files);
+	spin_lock_init(&nfs_uuid->lock);
+	nfs_uuid->nfs3_localio_probe_count = 0;
 }
 EXPORT_SYMBOL_GPL(nfs_uuid_init);
 
 bool nfs_uuid_begin(nfs_uuid_t *nfs_uuid)
 {
-	spin_lock(&nfs_uuid_lock);
-	/* Is this nfs_uuid already in use? */
+	spin_lock(&nfs_uuid->lock);
+	if (rcu_access_pointer(nfs_uuid->net)) {
+		/* This nfs_uuid is already in use */
+		spin_unlock(&nfs_uuid->lock);
+		return false;
+	}
+
+	spin_lock(&nfs_uuids_lock);
 	if (!list_empty(&nfs_uuid->list)) {
-		spin_unlock(&nfs_uuid_lock);
+		/* This nfs_uuid is already in use */
+		spin_unlock(&nfs_uuids_lock);
+		spin_unlock(&nfs_uuid->lock);
 		return false;
 	}
-	uuid_gen(&nfs_uuid->uuid);
 	list_add_tail(&nfs_uuid->list, &nfs_uuids);
-	spin_unlock(&nfs_uuid_lock);
+	spin_unlock(&nfs_uuids_lock);
+
+	uuid_gen(&nfs_uuid->uuid);
+	spin_unlock(&nfs_uuid->lock);
 
 	return true;
 }
@@ -46,12 +75,16 @@ EXPORT_SYMBOL_GPL(nfs_uuid_begin);
 
 void nfs_uuid_end(nfs_uuid_t *nfs_uuid)
 {
-	if (nfs_uuid->net == NULL) {
-		spin_lock(&nfs_uuid_lock);
-		if (nfs_uuid->net == NULL)
+	if (!rcu_access_pointer(nfs_uuid->net)) {
+		spin_lock(&nfs_uuid->lock);
+		if (!rcu_access_pointer(nfs_uuid->net)) {
+			/* Not local, remove from nfs_uuids */
+			spin_lock(&nfs_uuids_lock);
 			list_del_init(&nfs_uuid->list);
-		spin_unlock(&nfs_uuid_lock);
-	}
+			spin_unlock(&nfs_uuids_lock);
+		}
+		spin_unlock(&nfs_uuid->lock);
+        }
 }
 EXPORT_SYMBOL_GPL(nfs_uuid_end);
 
@@ -69,68 +102,142 @@ static nfs_uuid_t * nfs_uuid_lookup_locked(const uuid_t *uuid)
 static struct module *nfsd_mod;
 
 void nfs_uuid_is_local(const uuid_t *uuid, struct list_head *list,
-		       struct net *net, struct auth_domain *dom,
-		       struct module *mod)
+		       spinlock_t *list_lock, struct net *net,
+		       struct auth_domain *dom, struct module *mod)
 {
 	nfs_uuid_t *nfs_uuid;
 
-	spin_lock(&nfs_uuid_lock);
+	spin_lock(&nfs_uuids_lock);
 	nfs_uuid = nfs_uuid_lookup_locked(uuid);
-	if (nfs_uuid) {
-		kref_get(&dom->ref);
-		nfs_uuid->dom = dom;
-		/*
-		 * We don't hold a ref on the net, but instead put
-		 * ourselves on a list so the net pointer can be
-		 * invalidated.
-		 */
-		list_move(&nfs_uuid->list, list);
-		rcu_assign_pointer(nfs_uuid->net, net);
-
-		__module_get(mod);
-		nfsd_mod = mod;
+	if (!nfs_uuid) {
+		spin_unlock(&nfs_uuids_lock);
+		return;
 	}
-	spin_unlock(&nfs_uuid_lock);
+
+	/*
+	 * We don't hold a ref on the net, but instead put
+	 * ourselves on @list (nn->local_clients) so the net
+	 * pointer can be invalidated.
+	 */
+	spin_lock(list_lock); /* list_lock is nn->local_clients_lock */
+	list_move(&nfs_uuid->list, list);
+	spin_unlock(list_lock);
+
+	spin_unlock(&nfs_uuids_lock);
+	/* Once nfs_uuid is parented to @list, avoid global nfs_uuids_lock */
+	spin_lock(&nfs_uuid->lock);
+
+	__module_get(mod);
+	nfsd_mod = mod;
+
+	nfs_uuid->list_lock = list_lock;
+	kref_get(&dom->ref);
+	nfs_uuid->dom = dom;
+	rcu_assign_pointer(nfs_uuid->net, net);
+	spin_unlock(&nfs_uuid->lock);
 }
 EXPORT_SYMBOL_GPL(nfs_uuid_is_local);
 
-static void nfs_uuid_put_locked(nfs_uuid_t *nfs_uuid)
+void nfs_localio_enable_client(struct nfs_client *clp)
+{
+	/* nfs_uuid_is_local() does the actual enablement */
+	trace_nfs_localio_enable_client(clp);
+}
+EXPORT_SYMBOL_GPL(nfs_localio_enable_client);
+
+/*
+ * Cleanup the nfs_uuid_t embedded in an nfs_client.
+ * This is the long-form of nfs_uuid_init().
+ */
+static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 {
-	if (nfs_uuid->net) {
-		module_put(nfsd_mod);
-		nfs_uuid->net = NULL;
+	LIST_HEAD(local_files);
+	struct nfs_file_localio *nfl, *tmp;
+
+	spin_lock(&nfs_uuid->lock);
+	if (unlikely(!rcu_access_pointer(nfs_uuid->net))) {
+		spin_unlock(&nfs_uuid->lock);
+		return false;
 	}
+	RCU_INIT_POINTER(nfs_uuid->net, NULL);
+
 	if (nfs_uuid->dom) {
 		auth_domain_put(nfs_uuid->dom);
 		nfs_uuid->dom = NULL;
 	}
-	list_del_init(&nfs_uuid->list);
+
+	list_splice_init(&nfs_uuid->files, &local_files);
+	spin_unlock(&nfs_uuid->lock);
+
+	/* Walk list of files and ensure their last references dropped */
+	list_for_each_entry_safe(nfl, tmp, &local_files, list) {
+		nfs_close_local_fh(nfl);
+		cond_resched();
+	}
+
+	spin_lock(&nfs_uuid->lock);
+	BUG_ON(!list_empty(&nfs_uuid->files));
+
+	/* Remove client from nn->local_clients */
+	if (nfs_uuid->list_lock) {
+		spin_lock(nfs_uuid->list_lock);
+		BUG_ON(list_empty(&nfs_uuid->list));
+		list_del_init(&nfs_uuid->list);
+		spin_unlock(nfs_uuid->list_lock);
+		nfs_uuid->list_lock = NULL;
+	}
+
+	module_put(nfsd_mod);
+	spin_unlock(&nfs_uuid->lock);
+
+	return true;
 }
 
-void nfs_uuid_invalidate_clients(struct list_head *list)
+void nfs_localio_disable_client(struct nfs_client *clp)
 {
+	if (nfs_uuid_put(&clp->cl_uuid))
+		trace_nfs_localio_disable_client(clp);
+}
+EXPORT_SYMBOL_GPL(nfs_localio_disable_client);
+
+void nfs_localio_invalidate_clients(struct list_head *nn_local_clients,
+				    spinlock_t *nn_local_clients_lock)
+{
+	LIST_HEAD(local_clients);
 	nfs_uuid_t *nfs_uuid, *tmp;
+	struct nfs_client *clp;
 
-	spin_lock(&nfs_uuid_lock);
-	list_for_each_entry_safe(nfs_uuid, tmp, list, list)
-		nfs_uuid_put_locked(nfs_uuid);
-	spin_unlock(&nfs_uuid_lock);
+	spin_lock(nn_local_clients_lock);
+	list_splice_init(nn_local_clients, &local_clients);
+	spin_unlock(nn_local_clients_lock);
+	list_for_each_entry_safe(nfs_uuid, tmp, &local_clients, list) {
+		if (WARN_ON(nfs_uuid->list_lock != nn_local_clients_lock))
+			break;
+		clp = container_of(nfs_uuid, struct nfs_client, cl_uuid);
+		nfs_localio_disable_client(clp);
+	}
 }
-EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_clients);
+EXPORT_SYMBOL_GPL(nfs_localio_invalidate_clients);
 
-void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid)
+static void nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl)
 {
-	if (nfs_uuid->net) {
-		spin_lock(&nfs_uuid_lock);
-		nfs_uuid_put_locked(nfs_uuid);
-		spin_unlock(&nfs_uuid_lock);
+	/* Add nfl to nfs_uuid->files if it isn't already */
+	spin_lock(&nfs_uuid->lock);
+	if (list_empty(&nfl->list)) {
+		rcu_assign_pointer(nfl->nfs_uuid, nfs_uuid);
+		list_add_tail(&nfl->list, &nfs_uuid->files);
 	}
+	spin_unlock(&nfs_uuid->lock);
 }
-EXPORT_SYMBOL_GPL(nfs_uuid_invalidate_one_client);
 
+/*
+ * Caller is responsible for calling nfsd_net_put and
+ * nfsd_file_put (via nfs_to_nfsd_file_put_local).
+ */
 struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 		   struct rpc_clnt *rpc_clnt, const struct cred *cred,
-		   const struct nfs_fh *nfs_fh, const fmode_t fmode)
+		   const struct nfs_fh *nfs_fh, struct nfs_file_localio *nfl,
+		   const fmode_t fmode)
 {
 	struct net *net;
 	struct nfsd_file *localio;
@@ -139,7 +246,7 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 	 * Not running in nfsd context, so must safely get reference on nfsd_serv.
 	 * But the server may already be shutting down, if so disallow new localio.
 	 * uuid->net is NOT a counted reference, but rcu_read_lock() ensures that
-	 * if uuid->net is not NULL, then calling nfsd_serv_try_get() is safe
+	 * if uuid->net is not NULL, then calling nfsd_net_try_get() is safe
 	 * and if it succeeds we will have an implied reference to the net.
 	 *
 	 * Otherwise NFS may not have ref on NFSD and therefore cannot safely
@@ -147,21 +254,62 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 	 */
 	rcu_read_lock();
 	net = rcu_dereference(uuid->net);
-	if (!net || !nfs_to->nfsd_serv_try_get(net)) {
+	if (!net || !nfs_to->nfsd_net_try_get(net)) {
 		rcu_read_unlock();
 		return ERR_PTR(-ENXIO);
 	}
 	rcu_read_unlock();
-	/* We have an implied reference to net thanks to nfsd_serv_try_get */
+	/* We have an implied reference to net thanks to nfsd_net_try_get */
 	localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt,
 					     cred, nfs_fh, fmode);
 	if (IS_ERR(localio))
 		nfs_to_nfsd_net_put(net);
+	else
+		nfs_uuid_add_file(uuid, nfl);
 
 	return localio;
 }
 EXPORT_SYMBOL_GPL(nfs_open_local_fh);
 
+void nfs_close_local_fh(struct nfs_file_localio *nfl)
+{
+	struct nfsd_file *ro_nf = NULL;
+	struct nfsd_file *rw_nf = NULL;
+	nfs_uuid_t *nfs_uuid;
+
+	rcu_read_lock();
+	nfs_uuid = rcu_dereference(nfl->nfs_uuid);
+	if (!nfs_uuid) {
+		/* regular (non-LOCALIO) NFS will hammer this */
+		rcu_read_unlock();
+		return;
+	}
+
+	ro_nf = rcu_access_pointer(nfl->ro_file);
+	rw_nf = rcu_access_pointer(nfl->rw_file);
+	if (ro_nf || rw_nf) {
+		spin_lock(&nfs_uuid->lock);
+		if (ro_nf)
+			ro_nf = rcu_dereference_protected(xchg(&nfl->ro_file, NULL), 1);
+		if (rw_nf)
+			rw_nf = rcu_dereference_protected(xchg(&nfl->rw_file, NULL), 1);
+
+		/* Remove nfl from nfs_uuid->files list */
+		RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
+		list_del_init(&nfl->list);
+		spin_unlock(&nfs_uuid->lock);
+		rcu_read_unlock();
+
+		if (ro_nf)
+			nfs_to_nfsd_file_put_local(ro_nf);
+		if (rw_nf)
+			nfs_to_nfsd_file_put_local(rw_nf);
+		return;
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nfs_close_local_fh);
+
 /*
  * The NFS LOCALIO code needs to call into NFSD using various symbols,
  * but cannot be statically linked, because that will make the NFS
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index 18cbd3fa7691..2f687619f65b 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -18,9 +18,23 @@ nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o
 nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
-			   nfs4acl.o nfs4callback.o nfs4recover.o
+			   nfs4acl.o nfs4callback.o nfs4recover.o nfs4xdr_gen.o
 nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
 nfsd-$(CONFIG_NFSD_BLOCKLAYOUT) += blocklayout.o blocklayoutxdr.o
 nfsd-$(CONFIG_NFSD_SCSILAYOUT) += blocklayout.o blocklayoutxdr.o
 nfsd-$(CONFIG_NFSD_FLEXFILELAYOUT) += flexfilelayout.o flexfilelayoutxdr.o
 nfsd-$(CONFIG_NFS_LOCALIO) += localio.o
+
+
+.PHONY: xdrgen
+
+xdrgen: ../../include/linux/sunrpc/xdrgen/nfs4_1.h nfs4xdr_gen.h nfs4xdr_gen.c
+
+../../include/linux/sunrpc/xdrgen/nfs4_1.h: ../../Documentation/sunrpc/xdr/nfs4_1.x
+	../../tools/net/sunrpc/xdrgen/xdrgen definitions $< > $@
+
+nfs4xdr_gen.h: ../../Documentation/sunrpc/xdr/nfs4_1.x
+	../../tools/net/sunrpc/xdrgen/xdrgen declarations $< > $@
+
+nfs4xdr_gen.c: ../../Documentation/sunrpc/xdr/nfs4_1.x
+	../../tools/net/sunrpc/xdrgen/xdrgen source $< > $@
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index aa4712362b3b..0363720280d4 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -355,16 +355,25 @@ static void export_stats_destroy(struct export_stats *stats)
 					    EXP_STATS_COUNTERS_NUM);
 }
 
-static void svc_export_put(struct kref *ref)
+static void svc_export_release(struct rcu_head *rcu_head)
 {
-	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
-	path_put(&exp->ex_path);
-	auth_domain_put(exp->ex_client);
+	struct svc_export *exp = container_of(rcu_head, struct svc_export,
+			ex_rcu);
+
 	nfsd4_fslocs_free(&exp->ex_fslocs);
 	export_stats_destroy(exp->ex_stats);
 	kfree(exp->ex_stats);
 	kfree(exp->ex_uuid);
-	kfree_rcu(exp, ex_rcu);
+	kfree(exp);
+}
+
+static void svc_export_put(struct kref *ref)
+{
+	struct svc_export *exp = container_of(ref, struct svc_export, h.ref);
+
+	path_put(&exp->ex_path);
+	auth_domain_put(exp->ex_client);
+	call_rcu(&exp->ex_rcu, svc_export_release);
 }
 
 static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
@@ -1425,13 +1434,9 @@ static int e_show(struct seq_file *m, void *p)
 		return 0;
 	}
 
-	if (!cache_get_rcu(&exp->h))
-		return 0;
-
-	if (cache_check(cd, &exp->h, NULL))
+	if (cache_check_rcu(cd, &exp->h, NULL))
 		return 0;
 
-	exp_put(exp);
 	return svc_export_show(m, cd, cp);
 }
 
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index dc5c9d8e8202..fb9b1656a287 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -39,6 +39,7 @@
 #include <linux/fsnotify.h>
 #include <linux/seq_file.h>
 #include <linux/rhashtable.h>
+#include <linux/nfslocalio.h>
 
 #include "vfs.h"
 #include "nfsd.h"
@@ -391,7 +392,7 @@ nfsd_file_put(struct nfsd_file *nf)
 }
 
 /**
- * nfsd_file_put_local - put nfsd_file reference and arm nfsd_serv_put in caller
+ * nfsd_file_put_local - put nfsd_file reference and arm nfsd_net_put in caller
  * @nf: nfsd_file of which to put the reference
  *
  * First save the associated net to return to caller, then put
@@ -445,11 +446,20 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose)
 						struct nfsd_file, nf_gc);
 		struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
 		struct nfsd_fcache_disposal *l = nn->fcache_disposal;
+		struct svc_serv *serv;
 
 		spin_lock(&l->lock);
 		list_move_tail(&nf->nf_gc, &l->freeme);
 		spin_unlock(&l->lock);
-		svc_wake_up(nn->nfsd_serv);
+
+		/*
+		 * The filecache laundrette is shut down after the
+		 * nn->nfsd_serv pointer is cleared, but before the
+		 * svc_serv is freed.
+		 */
+		serv = nn->nfsd_serv;
+		if (serv)
+			svc_wake_up(serv);
 	}
 }
 
@@ -833,6 +843,14 @@ __nfsd_file_cache_purge(struct net *net)
 	struct nfsd_file *nf;
 	LIST_HEAD(dispose);
 
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	if (net) {
+		struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+		nfs_localio_invalidate_clients(&nn->local_clients,
+					       &nn->local_clients_lock);
+	}
+#endif
+
 	rhltable_walk_enter(&nfsd_file_rhltable, &iter);
 	do {
 		rhashtable_walk_start(&iter);
@@ -1222,10 +1240,9 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * a file.  The security implications of this should be carefully
  * considered before use.
  *
- * The nfsd_file object returned by this API is reference-counted
- * and garbage-collected. The object is retained for a few
- * seconds after the final nfsd_file_put() in case the caller
- * wants to re-use it.
+ * The nfsd_file_object returned by this API is reference-counted
+ * but not garbage-collected. The object is unhashed after the
+ * final nfsd_file_put().
  *
  * Return values:
  *   %nfs_ok - @pnf points to an nfsd_file with its reference
@@ -1247,7 +1264,7 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred,
 	__be32 beres;
 
 	beres = nfsd_file_do_acquire(NULL, net, cred, client,
-				     fhp, may_flags, NULL, pnf, true);
+				     fhp, may_flags, NULL, pnf, false);
 	put_cred(revert_creds(save_cred));
 	return beres;
 }
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index f441cb9f74d5..238647fa379e 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -25,10 +25,12 @@
 #include "cache.h"
 
 static const struct nfsd_localio_operations nfsd_localio_ops = {
-	.nfsd_serv_try_get  = nfsd_serv_try_get,
-	.nfsd_serv_put  = nfsd_serv_put,
+	.nfsd_net_try_get  = nfsd_net_try_get,
+	.nfsd_net_put  = nfsd_net_put,
 	.nfsd_open_local_fh = nfsd_open_local_fh,
 	.nfsd_file_put_local = nfsd_file_put_local,
+	.nfsd_file_get = nfsd_file_get,
+	.nfsd_file_put = nfsd_file_put,
 	.nfsd_file_file = nfsd_file_file,
 };
 
@@ -52,7 +54,7 @@ void nfsd_localio_ops_init(void)
  * avoid all the NFS overhead with reads, writes and commits.
  *
  * On successful return, returned nfsd_file will have its nf_net member
- * set. Caller (NFS client) is responsible for calling nfsd_serv_put and
+ * set. Caller (NFS client) is responsible for calling nfsd_net_put and
  * nfsd_file_put (via nfs_to_nfsd_file_put_local).
  */
 struct nfsd_file *
@@ -114,6 +116,7 @@ static __be32 localio_proc_uuid_is_local(struct svc_rqst *rqstp)
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	nfs_uuid_is_local(&argp->uuid, &nn->local_clients,
+			  &nn->local_clients_lock,
 			  net, rqstp->rq_client, THIS_MODULE);
 
 	return rpc_success;
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 26f7b34d1a03..3e2d0fde80a7 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -128,21 +128,16 @@ struct nfsd_net {
 	seqlock_t writeverf_lock;
 	unsigned char writeverf[8];
 
-	/*
-	 * Max number of connections this nfsd container will allow. Defaults
-	 * to '0' which is means that it bases this on the number of threads.
-	 */
-	unsigned int max_connections;
-
 	u32 clientid_base;
 	u32 clientid_counter;
 	u32 clverifier_counter;
 
 	struct svc_info nfsd_info;
 #define nfsd_serv nfsd_info.serv
-	struct percpu_ref nfsd_serv_ref;
-	struct completion nfsd_serv_confirm_done;
-	struct completion nfsd_serv_free_done;
+
+	struct percpu_ref nfsd_net_ref;
+	struct completion nfsd_net_confirm_done;
+	struct completion nfsd_net_free_done;
 
 	/*
 	 * clientid and stateid data for construction of net unique COPY
@@ -219,6 +214,7 @@ struct nfsd_net {
 
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 	/* Local clients to be invalidated when net is shut down */
+	spinlock_t              local_clients_lock;
 	struct list_head	local_clients;
 #endif
 };
@@ -229,8 +225,8 @@ struct nfsd_net {
 extern bool nfsd_support_version(int vers);
 extern unsigned int nfsd_net_id;
 
-bool nfsd_serv_try_get(struct net *net);
-void nfsd_serv_put(struct net *net);
+bool nfsd_net_try_get(struct net *net);
+void nfsd_net_put(struct net *net);
 
 void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn);
 void nfsd_reset_write_verifier(struct nfsd_net *nn);
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 4e3be7201b1c..5fb202acb0fd 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -84,6 +84,8 @@ out:
 fail:
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
+	resp->acl_access = NULL;
+	resp->acl_default = NULL;
 	goto out;
 }
 
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 5e34e98db969..7b5433bd3019 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -76,6 +76,8 @@ out:
 fail:
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
+	resp->acl_access = NULL;
+	resp->acl_default = NULL;
 	goto out;
 }
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index c083e539e898..484077200c5d 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -42,6 +42,7 @@
 #include "trace.h"
 #include "xdr4cb.h"
 #include "xdr4.h"
+#include "nfs4xdr_gen.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -93,12 +94,35 @@ static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap,
 {
 	fattr->ncf_cb_change = 0;
 	fattr->ncf_cb_fsize = 0;
+	fattr->ncf_cb_atime.tv_sec = 0;
+	fattr->ncf_cb_atime.tv_nsec = 0;
+	fattr->ncf_cb_mtime.tv_sec = 0;
+	fattr->ncf_cb_mtime.tv_nsec = 0;
+
 	if (bitmap[0] & FATTR4_WORD0_CHANGE)
 		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_change) < 0)
 			return -NFSERR_BAD_XDR;
 	if (bitmap[0] & FATTR4_WORD0_SIZE)
 		if (xdr_stream_decode_u64(xdr, &fattr->ncf_cb_fsize) < 0)
 			return -NFSERR_BAD_XDR;
+	if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) {
+		fattr4_time_deleg_access access;
+
+		if (!xdrgen_decode_fattr4_time_deleg_access(xdr, &access))
+			return -NFSERR_BAD_XDR;
+		fattr->ncf_cb_atime.tv_sec = access.seconds;
+		fattr->ncf_cb_atime.tv_nsec = access.nseconds;
+
+	}
+	if (bitmap[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) {
+		fattr4_time_deleg_modify modify;
+
+		if (!xdrgen_decode_fattr4_time_deleg_modify(xdr, &modify))
+			return -NFSERR_BAD_XDR;
+		fattr->ncf_cb_mtime.tv_sec = modify.seconds;
+		fattr->ncf_cb_mtime.tv_nsec = modify.nseconds;
+
+	}
 	return 0;
 }
 
@@ -361,16 +385,24 @@ static void
 encode_cb_getattr4args(struct xdr_stream *xdr, struct nfs4_cb_compound_hdr *hdr,
 			struct nfs4_cb_fattr *fattr)
 {
-	struct nfs4_delegation *dp =
-		container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
+	struct nfs4_delegation *dp = container_of(fattr, struct nfs4_delegation, dl_cb_fattr);
 	struct knfsd_fh *fh = &dp->dl_stid.sc_file->fi_fhandle;
-	u32 bmap[1];
-
-	bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE;
-
+	struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr;
+	u32 bmap_size = 1;
+	u32 bmap[3];
+
+	bmap[0] = FATTR4_WORD0_SIZE;
+	if (!ncf->ncf_file_modified)
+		bmap[0] |= FATTR4_WORD0_CHANGE;
+
+	if (deleg_attrs_deleg(dp->dl_type)) {
+		bmap[1] = 0;
+		bmap[2] = FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY;
+		bmap_size = 3;
+	}
 	encode_nfs_cb_opnum4(xdr, OP_CB_GETATTR);
 	encode_nfs_fh4(xdr, fh);
-	encode_bitmap4(xdr, bmap, ARRAY_SIZE(bmap));
+	encode_bitmap4(xdr, bmap, bmap_size);
 	hdr->nops++;
 }
 
@@ -634,7 +666,7 @@ static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
 	struct nfs4_cb_compound_hdr hdr;
 	int status;
 	u32 bitmap[3] = {0};
-	u32 attrlen;
+	u32 attrlen, maxlen;
 	struct nfs4_cb_fattr *ncf =
 		container_of(cb, struct nfs4_cb_fattr, ncf_getattr);
 
@@ -647,13 +679,17 @@ static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp,
 		return status;
 
 	status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status);
-	if (status)
+	if (unlikely(status || cb->cb_status))
 		return status;
 	if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0)
 		return -NFSERR_BAD_XDR;
 	if (xdr_stream_decode_u32(xdr, &attrlen) < 0)
 		return -NFSERR_BAD_XDR;
-	if (attrlen > (sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize)))
+	maxlen = sizeof(ncf->ncf_cb_change) + sizeof(ncf->ncf_cb_fsize);
+	if (bitmap[2] != 0)
+		maxlen += (sizeof(ncf->ncf_cb_mtime.tv_sec) +
+			   sizeof(ncf->ncf_cb_mtime.tv_nsec)) * 2;
+	if (attrlen > maxlen)
 		return -NFSERR_BAD_XDR;
 	status = decode_cb_fattr4(xdr, bitmap, ncf);
 	return status;
@@ -1036,8 +1072,7 @@ static void nfsd41_cb_inflight_begin(struct nfs4_client *clp)
 static void nfsd41_cb_inflight_end(struct nfs4_client *clp)
 {
 
-	if (atomic_dec_and_test(&clp->cl_cb_inflight))
-		wake_up_var(&clp->cl_cb_inflight);
+	atomic_dec_and_wake_up(&clp->cl_cb_inflight);
 }
 
 static void nfsd41_cb_inflight_wait_complete(struct nfs4_client *clp)
@@ -1397,8 +1432,9 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		return;
 
 	if (cb->cb_status) {
-		WARN_ONCE(task->tk_status, "cb_status=%d tk_status=%d",
-			  cb->cb_status, task->tk_status);
+		WARN_ONCE(task->tk_status,
+			  "cb_status=%d tk_status=%d cb_opcode=%d",
+			  cb->cb_status, task->tk_status, cb->cb_ops->opcode);
 		task->tk_status = cb->cb_status;
 	}
 
@@ -1547,8 +1583,11 @@ nfsd4_run_cb_work(struct work_struct *work)
 		nfsd4_process_cb_update(cb);
 
 	clnt = clp->cl_cb_client;
-	if (!clnt) {
-		/* Callback channel broken, or client killed; give up: */
+	if (!clnt || clp->cl_state == NFSD4_COURTESY) {
+		/*
+		 * Callback channel broken, client killed or
+		 * nfs4_client in courtesy state; give up.
+		 */
 		nfsd41_destroy_cb(cb);
 		return;
 	}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ad44ad49274f..f6e06c779d09 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1135,18 +1135,43 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		.na_iattr	= &setattr->sa_iattr,
 		.na_seclabel	= &setattr->sa_label,
 	};
+	bool save_no_wcc, deleg_attrs;
+	struct nfs4_stid *st = NULL;
 	struct inode *inode;
 	__be32 status = nfs_ok;
-	bool save_no_wcc;
 	int err;
 
-	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
+	deleg_attrs = setattr->sa_bmval[2] & (FATTR4_WORD2_TIME_DELEG_ACCESS |
+					      FATTR4_WORD2_TIME_DELEG_MODIFY);
+
+	if (deleg_attrs || (setattr->sa_iattr.ia_valid & ATTR_SIZE)) {
+		int flags = WR_STATE;
+
+		if (setattr->sa_bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS)
+			flags |= RD_STATE;
+
 		status = nfs4_preprocess_stateid_op(rqstp, cstate,
 				&cstate->current_fh, &setattr->sa_stateid,
-				WR_STATE, NULL, NULL);
+				flags, NULL, &st);
 		if (status)
 			return status;
 	}
+
+	if (deleg_attrs) {
+		status = nfserr_bad_stateid;
+		if (st->sc_type & SC_TYPE_DELEG) {
+			struct nfs4_delegation *dp = delegstateid(st);
+
+			/* Only for *_ATTRS_DELEG flavors */
+			if (deleg_attrs_deleg(dp->dl_type))
+				status = nfs_ok;
+		}
+	}
+	if (st)
+		nfs4_put_stid(st);
+	if (status)
+		return status;
+
 	err = fh_want_write(&cstate->current_fh);
 	if (err)
 		return nfserrno(err);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 7f2ceeb118a4..28f4d5311c40 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -2051,7 +2051,6 @@ static inline int check_for_legacy_methods(int status, struct net *net)
 		path_put(&path);
 		if (status)
 			return -ENOTDIR;
-		status = nn->client_tracking_ops->init(net);
 	}
 	return status;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 741b9449f727..153eeea2c7c9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1909,17 +1909,86 @@ gen_sessionid(struct nfsd4_session *ses)
  */
 #define NFSD_MIN_HDR_SEQ_SZ  (24 + 12 + 44)
 
+static struct shrinker *nfsd_slot_shrinker;
+static DEFINE_SPINLOCK(nfsd_session_list_lock);
+static LIST_HEAD(nfsd_session_list);
+/* The sum of "target_slots-1" on every session.  The shrinker can push this
+ * down, though it can take a little while for the memory to actually
+ * be freed.  The "-1" is because we can never free slot 0 while the
+ * session is active.
+ */
+static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0);
+
 static void
-free_session_slots(struct nfsd4_session *ses)
+free_session_slots(struct nfsd4_session *ses, int from)
 {
 	int i;
 
-	for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
-		free_svc_cred(&ses->se_slots[i]->sl_cred);
-		kfree(ses->se_slots[i]);
+	if (from >= ses->se_fchannel.maxreqs)
+		return;
+
+	for (i = from; i < ses->se_fchannel.maxreqs; i++) {
+		struct nfsd4_slot *slot = xa_load(&ses->se_slots, i);
+
+		/*
+		 * Save the seqid in case we reactivate this slot.
+		 * This will never require a memory allocation so GFP
+		 * flag is irrelevant
+		 */
+		xa_store(&ses->se_slots, i, xa_mk_value(slot->sl_seqid), 0);
+		free_svc_cred(&slot->sl_cred);
+		kfree(slot);
+	}
+	ses->se_fchannel.maxreqs = from;
+	if (ses->se_target_maxslots > from) {
+		int new_target = from ?: 1;
+		atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots);
+		ses->se_target_maxslots = new_target;
 	}
 }
 
+/**
+ * reduce_session_slots - reduce the target max-slots of a session if possible
+ * @ses:  The session to affect
+ * @dec:  how much to decrease the target by
+ *
+ * This interface can be used by a shrinker to reduce the target max-slots
+ * for a session so that some slots can eventually be freed.
+ * It uses spin_trylock() as it may be called in a context where another
+ * spinlock is held that has a dependency on client_lock.  As shrinkers are
+ * best-effort, skiping a session is client_lock is already held has no
+ * great coast
+ *
+ * Return value:
+ *   The number of slots that the target was reduced by.
+ */
+static int
+reduce_session_slots(struct nfsd4_session *ses, int dec)
+{
+	struct nfsd_net *nn = net_generic(ses->se_client->net,
+					  nfsd_net_id);
+	int ret = 0;
+
+	if (ses->se_target_maxslots <= 1)
+		return ret;
+	if (!spin_trylock(&nn->client_lock))
+		return ret;
+	ret = min(dec, ses->se_target_maxslots-1);
+	ses->se_target_maxslots -= ret;
+	atomic_sub(ret, &nfsd_total_target_slots);
+	ses->se_slot_gen += 1;
+	if (ses->se_slot_gen == 0) {
+		int i;
+		ses->se_slot_gen = 1;
+		for (i = 0; i < ses->se_fchannel.maxreqs; i++) {
+			struct nfsd4_slot *slot = xa_load(&ses->se_slots, i);
+			slot->sl_generation = 0;
+		}
+	}
+	spin_unlock(&nn->client_lock);
+	return ret;
+}
+
 /*
  * We don't actually need to cache the rpc and session headers, so we
  * can allocate a little less for each slot:
@@ -1935,89 +2004,46 @@ static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca)
 	return size + sizeof(struct nfsd4_slot);
 }
 
-/*
- * XXX: If we run out of reserved DRC memory we could (up to a point)
- * re-negotiate active sessions and reduce their slot usage to make
- * room for new connections. For now we just fail the create session.
- */
-static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn)
-{
-	u32 slotsize = slot_bytes(ca);
-	u32 num = ca->maxreqs;
-	unsigned long avail, total_avail;
-	unsigned int scale_factor;
-
-	spin_lock(&nfsd_drc_lock);
-	if (nfsd_drc_max_mem > nfsd_drc_mem_used)
-		total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used;
-	else
-		/* We have handed out more space than we chose in
-		 * set_max_drc() to allow.  That isn't really a
-		 * problem as long as that doesn't make us think we
-		 * have lots more due to integer overflow.
-		 */
-		total_avail = 0;
-	avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail);
-	/*
-	 * Never use more than a fraction of the remaining memory,
-	 * unless it's the only way to give this client a slot.
-	 * The chosen fraction is either 1/8 or 1/number of threads,
-	 * whichever is smaller.  This ensures there are adequate
-	 * slots to support multiple clients per thread.
-	 * Give the client one slot even if that would require
-	 * over-allocation--it is better than failure.
-	 */
-	scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads);
-
-	avail = clamp_t(unsigned long, avail, slotsize,
-			total_avail/scale_factor);
-	num = min_t(int, num, avail / slotsize);
-	num = max_t(int, num, 1);
-	nfsd_drc_mem_used += num * slotsize;
-	spin_unlock(&nfsd_drc_lock);
-
-	return num;
-}
-
-static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca)
-{
-	int slotsize = slot_bytes(ca);
-
-	spin_lock(&nfsd_drc_lock);
-	nfsd_drc_mem_used -= slotsize * ca->maxreqs;
-	spin_unlock(&nfsd_drc_lock);
-}
-
 static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
 					   struct nfsd4_channel_attrs *battrs)
 {
 	int numslots = fattrs->maxreqs;
 	int slotsize = slot_bytes(fattrs);
 	struct nfsd4_session *new;
+	struct nfsd4_slot *slot;
 	int i;
 
-	BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION)
-		     > PAGE_SIZE);
-
-	new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL);
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
 	if (!new)
 		return NULL;
+	xa_init(&new->se_slots);
 	/* allocate each struct nfsd4_slot and data cache in one piece */
-	for (i = 0; i < numslots; i++) {
-		new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL);
-		if (!new->se_slots[i])
-			goto out_free;
-	}
+	slot = kzalloc(slotsize, GFP_KERNEL);
+	if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL)))
+		goto out_free;
 
+	for (i = 1; i < numslots; i++) {
+		const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
+		slot = kzalloc(slotsize, gfp);
+		if (!slot)
+			break;
+		if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) {
+			kfree(slot);
+			break;
+		}
+	}
+	fattrs->maxreqs = i;
 	memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
+	new->se_target_maxslots = i;
+	atomic_add(i - 1, &nfsd_total_target_slots);
 	new->se_cb_slot_avail = ~0U;
 	new->se_cb_highest_slot = min(battrs->maxreqs - 1,
 				      NFSD_BC_SLOT_TABLE_SIZE - 1);
 	spin_lock_init(&new->se_lock);
 	return new;
 out_free:
-	while (i--)
-		kfree(new->se_slots[i]);
+	kfree(slot);
+	xa_destroy(&new->se_slots);
 	kfree(new);
 	return NULL;
 }
@@ -2123,17 +2149,47 @@ static void nfsd4_del_conns(struct nfsd4_session *s)
 
 static void __free_session(struct nfsd4_session *ses)
 {
-	free_session_slots(ses);
+	free_session_slots(ses, 0);
+	xa_destroy(&ses->se_slots);
 	kfree(ses);
 }
 
 static void free_session(struct nfsd4_session *ses)
 {
 	nfsd4_del_conns(ses);
-	nfsd4_put_drc_mem(&ses->se_fchannel);
 	__free_session(ses);
 }
 
+static unsigned long
+nfsd_slot_count(struct shrinker *s, struct shrink_control *sc)
+{
+	unsigned long cnt = atomic_read(&nfsd_total_target_slots);
+
+	return cnt ? cnt : SHRINK_EMPTY;
+}
+
+static unsigned long
+nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc)
+{
+	struct nfsd4_session *ses;
+	unsigned long scanned = 0;
+	unsigned long freed = 0;
+
+	spin_lock(&nfsd_session_list_lock);
+	list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) {
+		freed += reduce_session_slots(ses, 1);
+		scanned += 1;
+		if (scanned >= sc->nr_to_scan) {
+			/* Move starting point for next scan */
+			list_move(&nfsd_session_list, &ses->se_all_sessions);
+			break;
+		}
+	}
+	spin_unlock(&nfsd_session_list_lock);
+	sc->nr_scanned = scanned;
+	return freed;
+}
+
 static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
 {
 	int idx;
@@ -2158,6 +2214,10 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
 	list_add(&new->se_perclnt, &clp->cl_sessions);
 	spin_unlock(&clp->cl_lock);
 
+	spin_lock(&nfsd_session_list_lock);
+	list_add_tail(&new->se_all_sessions, &nfsd_session_list);
+	spin_unlock(&nfsd_session_list_lock);
+
 	{
 		struct sockaddr *sa = svc_addr(rqstp);
 		/*
@@ -2227,6 +2287,9 @@ unhash_session(struct nfsd4_session *ses)
 	spin_lock(&ses->se_client->cl_lock);
 	list_del(&ses->se_perclnt);
 	spin_unlock(&ses->se_client->cl_lock);
+	spin_lock(&nfsd_session_list_lock);
+	list_del(&ses->se_all_sessions);
+	spin_unlock(&nfsd_session_list_lock);
 }
 
 /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
@@ -2362,8 +2425,12 @@ unhash_client_locked(struct nfs4_client *clp)
 	}
 	list_del_init(&clp->cl_lru);
 	spin_lock(&clp->cl_lock);
-	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
+	spin_lock(&nfsd_session_list_lock);
+	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) {
 		list_del_init(&ses->se_hash);
+		list_del_init(&ses->se_all_sessions);
+	}
+	spin_unlock(&nfsd_session_list_lock);
 	spin_unlock(&clp->cl_lock);
 }
 
@@ -2685,6 +2752,7 @@ static const char *cb_state2str(int state)
 static int client_info_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = file_inode(m->file);
+	struct nfsd4_session *ses;
 	struct nfs4_client *clp;
 	u64 clid;
 
@@ -2721,6 +2789,16 @@ static int client_info_show(struct seq_file *m, void *v)
 	seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr);
 	seq_printf(m, "admin-revoked states: %d\n",
 		   atomic_read(&clp->cl_admin_revoked));
+	spin_lock(&clp->cl_lock);
+	seq_printf(m, "session slots:");
+	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
+		seq_printf(m, " %u", ses->se_fchannel.maxreqs);
+	seq_printf(m, "\nsession target slots:");
+	list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
+		seq_printf(m, " %u", ses->se_target_maxslots);
+	spin_unlock(&clp->cl_lock);
+	seq_puts(m, "\n");
+
 	drop_client(clp);
 
 	return 0;
@@ -2873,6 +2951,21 @@ static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st)
 	return 0;
 }
 
+static char *nfs4_show_deleg_type(u32 dl_type)
+{
+	switch (dl_type) {
+	case OPEN_DELEGATE_READ:
+		return "r";
+	case OPEN_DELEGATE_WRITE:
+		return "w";
+	case OPEN_DELEGATE_READ_ATTRS_DELEG:
+		return "ra";
+	case OPEN_DELEGATE_WRITE_ATTRS_DELEG:
+		return "wa";
+	}
+	return "?";
+}
+
 static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 {
 	struct nfs4_delegation *ds;
@@ -2886,8 +2979,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 	nfs4_show_stateid(s, &st->sc_stateid);
 	seq_puts(s, ": { type: deleg, ");
 
-	seq_printf(s, "access: %s",
-		   ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w");
+	seq_printf(s, "access: %s", nfs4_show_deleg_type(ds->dl_type));
 
 	/* XXX: lease time, whether it's being recalled. */
 
@@ -3708,10 +3800,10 @@ nfsd4_exchange_id_release(union nfsd4_op_u *u)
 	kfree(exid->server_impl_name);
 }
 
-static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse)
+static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, u8 flags)
 {
 	/* The slot is in use, and no response has been sent. */
-	if (slot_inuse) {
+	if (flags & NFSD4_SLOT_INUSE) {
 		if (seqid == slot_seqid)
 			return nfserr_jukebox;
 		else
@@ -3720,6 +3812,8 @@ static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse)
 	/* Note unsigned 32-bit arithmetic handles wraparound: */
 	if (likely(seqid == slot_seqid + 1))
 		return nfs_ok;
+	if ((flags & NFSD4_SLOT_REUSED) && seqid == 1)
+		return nfs_ok;
 	if (seqid == slot_seqid)
 		return nfserr_replay_cache;
 	return nfserr_seq_misordered;
@@ -3778,17 +3872,6 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
 	ca->maxresp_cached = min_t(u32, ca->maxresp_cached,
 			NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ);
 	ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION);
-	/*
-	 * Note decreasing slot size below client's request may make it
-	 * difficult for client to function correctly, whereas
-	 * decreasing the number of slots will (just?) affect
-	 * performance.  When short on memory we therefore prefer to
-	 * decrease number of slots instead of their size.  Clients that
-	 * request larger slots than they need will get poor results:
-	 * Note that we always allow at least one slot, because our
-	 * accounting is soft and provides no guarantees either way.
-	 */
-	ca->maxreqs = nfsd4_get_drc_mem(ca, nn);
 
 	return nfs_ok;
 }
@@ -3866,11 +3949,11 @@ nfsd4_create_session(struct svc_rqst *rqstp,
 		return status;
 	status = check_backchannel_attrs(&cr_ses->back_channel);
 	if (status)
-		goto out_release_drc_mem;
+		goto out_err;
 	status = nfserr_jukebox;
 	new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel);
 	if (!new)
-		goto out_release_drc_mem;
+		goto out_err;
 	conn = alloc_conn_from_crses(rqstp, cr_ses);
 	if (!conn)
 		goto out_free_session;
@@ -3979,8 +4062,7 @@ out_free_conn:
 	free_conn(conn);
 out_free_session:
 	__free_session(new);
-out_release_drc_mem:
-	nfsd4_put_drc_mem(&cr_ses->fore_channel);
+out_err:
 	return status;
 }
 
@@ -4278,17 +4360,11 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (seq->slotid >= session->se_fchannel.maxreqs)
 		goto out_put_session;
 
-	slot = session->se_slots[seq->slotid];
+	slot = xa_load(&session->se_slots, seq->slotid);
 	dprintk("%s: slotid %d\n", __func__, seq->slotid);
 
-	/* We do not negotiate the number of slots yet, so set the
-	 * maxslots to the session maxreqs which is used to encode
-	 * sr_highest_slotid and the sr_target_slot id to maxslots */
-	seq->maxslots = session->se_fchannel.maxreqs;
-
 	trace_nfsd_slot_seqid_sequence(clp, seq, slot);
-	status = check_slot_seqid(seq->seqid, slot->sl_seqid,
-					slot->sl_flags & NFSD4_SLOT_INUSE);
+	status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags);
 	if (status == nfserr_replay_cache) {
 		status = nfserr_seq_misordered;
 		if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED))
@@ -4313,6 +4389,12 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (status)
 		goto out_put_session;
 
+	if (session->se_target_maxslots < session->se_fchannel.maxreqs &&
+	    slot->sl_generation == session->se_slot_gen &&
+	    seq->maxslots <= session->se_target_maxslots)
+		/* Client acknowledged our reduce maxreqs */
+		free_session_slots(session, session->se_target_maxslots);
+
 	buflen = (seq->cachethis) ?
 			session->se_fchannel.maxresp_cached :
 			session->se_fchannel.maxresp_sz;
@@ -4323,9 +4405,11 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	svc_reserve(rqstp, buflen);
 
 	status = nfs_ok;
-	/* Success! bump slot seqid */
+	/* Success! accept new slot seqid */
 	slot->sl_seqid = seq->seqid;
+	slot->sl_flags &= ~NFSD4_SLOT_REUSED;
 	slot->sl_flags |= NFSD4_SLOT_INUSE;
+	slot->sl_generation = session->se_slot_gen;
 	if (seq->cachethis)
 		slot->sl_flags |= NFSD4_SLOT_CACHETHIS;
 	else
@@ -4335,7 +4419,51 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	cstate->session = session;
 	cstate->clp = clp;
 
+	/*
+	 * If the client ever uses the highest available slot,
+	 * gently try to allocate another 20%.  This allows
+	 * fairly quick growth without grossly over-shooting what
+	 * the client might use.
+	 */
+	if (seq->slotid == session->se_fchannel.maxreqs - 1 &&
+	    session->se_target_maxslots >= session->se_fchannel.maxreqs &&
+	    session->se_fchannel.maxreqs < NFSD_MAX_SLOTS_PER_SESSION) {
+		int s = session->se_fchannel.maxreqs;
+		int cnt = DIV_ROUND_UP(s, 5);
+		void *prev_slot;
+
+		do {
+			/*
+			 * GFP_NOWAIT both allows allocation under a
+			 * spinlock, and only succeeds if there is
+			 * plenty of memory.
+			 */
+			slot = kzalloc(slot_bytes(&session->se_fchannel),
+				       GFP_NOWAIT);
+			prev_slot = xa_load(&session->se_slots, s);
+			if (xa_is_value(prev_slot) && slot) {
+				slot->sl_seqid = xa_to_value(prev_slot);
+				slot->sl_flags |= NFSD4_SLOT_REUSED;
+			}
+			if (slot &&
+			    !xa_is_err(xa_store(&session->se_slots, s, slot,
+						GFP_NOWAIT))) {
+				s += 1;
+				session->se_fchannel.maxreqs = s;
+				atomic_add(s - session->se_target_maxslots,
+					   &nfsd_total_target_slots);
+				session->se_target_maxslots = s;
+			} else {
+				kfree(slot);
+				slot = NULL;
+			}
+		} while (slot && --cnt > 0);
+	}
+
 out:
+	seq->maxslots = max(session->se_target_maxslots, seq->maxslots);
+	seq->target_maxslots = session->se_target_maxslots;
+
 	switch (clp->cl_cb_state) {
 	case NFSD4_CB_DOWN:
 		seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN;
@@ -4739,7 +4867,7 @@ static void init_nfs4_replay(struct nfs4_replay *rp)
 	rp->rp_status = nfserr_serverfault;
 	rp->rp_buflen = 0;
 	rp->rp_buf = rp->rp_ibuf;
-	atomic_set(&rp->rp_locked, RP_UNLOCKED);
+	rp->rp_locked = RP_UNLOCKED;
 }
 
 static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
@@ -4747,9 +4875,9 @@ static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
 {
 	if (!nfsd4_has_session(cstate)) {
 		wait_var_event(&so->so_replay.rp_locked,
-			       atomic_cmpxchg(&so->so_replay.rp_locked,
-					      RP_UNLOCKED, RP_LOCKED) != RP_LOCKED);
-		if (atomic_read(&so->so_replay.rp_locked) == RP_UNHASHED)
+			       cmpxchg(&so->so_replay.rp_locked,
+				       RP_UNLOCKED, RP_LOCKED) != RP_LOCKED);
+		if (so->so_replay.rp_locked == RP_UNHASHED)
 			return -EAGAIN;
 		cstate->replay_owner = nfs4_get_stateowner(so);
 	}
@@ -4762,9 +4890,7 @@ void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate)
 
 	if (so != NULL) {
 		cstate->replay_owner = NULL;
-		atomic_set(&so->so_replay.rp_locked, RP_UNLOCKED);
-		smp_mb__after_atomic();
-		wake_up_var(&so->so_replay.rp_locked);
+		store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED);
 		nfs4_put_stateowner(so);
 	}
 }
@@ -5069,9 +5195,7 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
 	 * Some threads with a reference might be waiting for rp_locked,
 	 * so tell them to stop waiting.
 	 */
-	atomic_set(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED);
-	smp_mb__after_atomic();
-	wake_up_var(&oo->oo_owner.so_replay.rp_locked);
+	store_release_wake_up(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED);
 	wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2);
 
 	release_all_access(s);
@@ -5472,7 +5596,7 @@ retry:
 static inline __be32
 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags)
 {
-	if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ))
+	if (!(flags & RD_STATE) && deleg_is_read(dp->dl_type))
 		return nfserr_openmode;
 	else
 		return nfs_ok;
@@ -5704,8 +5828,7 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
 	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
 }
 
-static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
-						int flag)
+static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp)
 {
 	struct file_lease *fl;
 
@@ -5714,7 +5837,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 		return NULL;
 	fl->fl_lmops = &nfsd_lease_mng_ops;
 	fl->c.flc_flags = FL_DELEG;
-	fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
+	fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK;
 	fl->c.flc_owner = (fl_owner_t)dp;
 	fl->c.flc_pid = current->tgid;
 	fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
@@ -5829,13 +5952,14 @@ static struct nfs4_delegation *
 nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 		    struct svc_fh *parent)
 {
-	int status = 0;
+	bool deleg_ts = open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS;
 	struct nfs4_client *clp = stp->st_stid.sc_client;
 	struct nfs4_file *fp = stp->st_stid.sc_file;
 	struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate;
 	struct nfs4_delegation *dp;
 	struct nfsd_file *nf = NULL;
 	struct file_lease *fl;
+	int status = 0;
 	u32 dl_type;
 
 	/*
@@ -5860,7 +5984,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	 */
 	if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == NFS4_SHARE_ACCESS_BOTH) {
 		nf = find_rw_file(fp);
-		dl_type = NFS4_OPEN_DELEGATE_WRITE;
+		dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE;
 	}
 
 	/*
@@ -5869,7 +5993,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	 */
 	if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) {
 		nf = find_readable_file(fp);
-		dl_type = NFS4_OPEN_DELEGATE_READ;
+		dl_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ;
 	}
 
 	if (!nf)
@@ -5901,7 +6025,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (!dp)
 		goto out_delegees;
 
-	fl = nfs4_alloc_init_lease(dp, dl_type);
+	fl = nfs4_alloc_init_lease(dp);
 	if (!fl)
 		goto out_clnt_odstate;
 
@@ -5958,20 +6082,20 @@ out_delegees:
 
 static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
 {
-	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+	open->op_delegate_type = OPEN_DELEGATE_NONE_EXT;
 	if (status == -EAGAIN)
 		open->op_why_no_deleg = WND4_CONTENTION;
 	else {
 		open->op_why_no_deleg = WND4_RESOURCE;
 		switch (open->op_deleg_want) {
-		case NFS4_SHARE_WANT_READ_DELEG:
-		case NFS4_SHARE_WANT_WRITE_DELEG:
-		case NFS4_SHARE_WANT_ANY_DELEG:
+		case OPEN4_SHARE_ACCESS_WANT_READ_DELEG:
+		case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG:
+		case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG:
 			break;
-		case NFS4_SHARE_WANT_CANCEL:
+		case OPEN4_SHARE_ACCESS_WANT_CANCEL:
 			open->op_why_no_deleg = WND4_CANCELLED;
 			break;
-		case NFS4_SHARE_WANT_NO_DELEG:
+		case OPEN4_SHARE_ACCESS_WANT_NO_DELEG:
 			WARN_ON_ONCE(1);
 		}
 	}
@@ -6027,13 +6151,14 @@ static void
 nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 		     struct svc_fh *currentfh)
 {
-	struct nfs4_delegation *dp;
+	bool deleg_ts = open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS;
 	struct nfs4_openowner *oo = openowner(stp->st_stateowner);
 	struct nfs4_client *clp = stp->st_stid.sc_client;
 	struct svc_fh *parent = NULL;
-	int cb_up;
-	int status = 0;
+	struct nfs4_delegation *dp;
 	struct kstat stat;
+	int status = 0;
+	int cb_up;
 
 	cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
 	open->op_recall = false;
@@ -6074,20 +6199,22 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 			destroy_delegation(dp);
 			goto out_no_deleg;
 		}
-		open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
+		open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG :
+						    OPEN_DELEGATE_WRITE;
 		dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
 		dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat);
 		trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
 	} else {
-		open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
+		open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG :
+						    OPEN_DELEGATE_READ;
 		trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
 	}
 	nfs4_put_stid(&dp->dl_stid);
 	return;
 out_no_deleg:
-	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE;
+	open->op_delegate_type = OPEN_DELEGATE_NONE;
 	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
-	    open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) {
+	    open->op_delegate_type != OPEN_DELEGATE_NONE) {
 		dprintk("NFSD: WARNING: refusing delegation reclaim\n");
 		open->op_recall = true;
 	}
@@ -6101,21 +6228,32 @@ out_no_deleg:
 static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
 					struct nfs4_delegation *dp)
 {
-	if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG &&
-	    dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
-		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
-		open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE;
-	} else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG &&
-		   dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
-		open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
-		open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE;
+	if (deleg_is_write(dp->dl_type)) {
+		if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_READ_DELEG) {
+			open->op_delegate_type = OPEN_DELEGATE_NONE_EXT;
+			open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE;
+		} else if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG) {
+			open->op_delegate_type = OPEN_DELEGATE_NONE_EXT;
+			open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE;
+		}
 	}
 	/* Otherwise the client must be confused wanting a delegation
 	 * it already has, therefore we don't return
-	 * NFS4_OPEN_DELEGATE_NONE_EXT and reason.
+	 * OPEN_DELEGATE_NONE_EXT and reason.
 	 */
 }
 
+/* Are we returning only a delegation stateid? */
+static bool open_xor_delegation(struct nfsd4_open *open)
+{
+	if (!(open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION))
+		return false;
+	/* Did we actually get a delegation? */
+	if (!deleg_is_read(open->op_delegate_type) && !deleg_is_write(open->op_delegate_type))
+		return false;
+	return true;
+}
+
 /**
  * nfsd4_process_open2 - finish open processing
  * @rqstp: the RPC transaction being executed
@@ -6201,8 +6339,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	mutex_unlock(&stp->st_mutex);
 
 	if (nfsd4_has_session(&resp->cstate)) {
-		if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
-			open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+		if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_NO_DELEG) {
+			open->op_delegate_type = OPEN_DELEGATE_NONE_EXT;
 			open->op_why_no_deleg = WND4_NOT_WANTED;
 			goto nodeleg;
 		}
@@ -6213,12 +6351,23 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	* OPEN succeeds even if we fail.
 	*/
 	nfs4_open_delegation(open, stp, &resp->cstate.current_fh);
+
+	/*
+	 * If there is an existing open stateid, it must be updated and
+	 * returned. Only respect WANT_OPEN_XOR_DELEGATION when a new
+	 * open stateid would have to be created.
+	 */
+	if (new_stp && open_xor_delegation(open)) {
+		memcpy(&open->op_stateid, &zero_stateid, sizeof(open->op_stateid));
+		open->op_rflags |= OPEN4_RESULT_NO_OPEN_STATEID;
+		release_open_stateid(stp);
+	}
 nodeleg:
 	status = nfs_ok;
 	trace_nfsd_open(&stp->st_stid.sc_stateid);
 out:
 	/* 4.1 client trying to upgrade/downgrade delegation? */
-	if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp &&
+	if (open->op_delegate_type == OPEN_DELEGATE_NONE && dp &&
 	    open->op_deleg_want)
 		nfsd4_deleg_xgrade_none_ext(open, dp);
 
@@ -6229,7 +6378,7 @@ out:
 	/*
 	* To finish the open response, we just need to set the rflags.
 	*/
-	open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX;
+	open->op_rflags |= NFS4_OPEN_RESULT_LOCKTYPE_POSIX;
 	if (nfsd4_has_session(&resp->cstate))
 		open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK;
 	else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED))
@@ -7966,7 +8115,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfsd4_blocked_lock *nbl = NULL;
 	struct file_lock *file_lock = NULL;
 	struct file_lock *conflock = NULL;
-	struct super_block *sb;
 	__be32 status = 0;
 	int lkflg;
 	int err;
@@ -7986,7 +8134,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0);
 	if (status != nfs_ok)
 		return status;
-	sb = cstate->current_fh.fh_dentry->d_sb;
 
 	if (lock->lk_is_new) {
 		if (nfsd4_has_session(cstate))
@@ -8721,7 +8868,6 @@ skip_grace:
 }
 
 /* initialization to perform when the nfsd service is started: */
-
 int
 nfs4_state_start(void)
 {
@@ -8731,6 +8877,15 @@ nfs4_state_start(void)
 	if (ret)
 		return ret;
 
+	nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot");
+	if (!nfsd_slot_shrinker) {
+		rhltable_destroy(&nfs4_file_rhltable);
+		return -ENOMEM;
+	}
+	nfsd_slot_shrinker->count_objects = nfsd_slot_count;
+	nfsd_slot_shrinker->scan_objects = nfsd_slot_scan;
+	shrinker_register(nfsd_slot_shrinker);
+
 	set_max_delegations();
 	return 0;
 }
@@ -8772,6 +8927,7 @@ void
 nfs4_state_shutdown(void)
 {
 	rhltable_destroy(&nfs4_file_rhltable);
+	shrinker_free(nfsd_slot_shrinker);
 }
 
 static void
@@ -8889,6 +9045,78 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
 }
 
 /**
+ * set_cb_time - vet and set the timespec for a cb_getattr update
+ * @cb: timestamp from the CB_GETATTR response
+ * @orig: original timestamp in the inode
+ * @now: current time
+ *
+ * Given a timestamp in a CB_GETATTR response, check it against the
+ * current timestamp in the inode and the current time. Returns true
+ * if the inode's timestamp needs to be updated, and false otherwise.
+ * @cb may also be changed if the timestamp needs to be clamped.
+ */
+static bool set_cb_time(struct timespec64 *cb, const struct timespec64 *orig,
+			const struct timespec64 *now)
+{
+
+	/*
+	 * "When the time presented is before the original time, then the
+	 *  update is ignored." Also no need to update if there is no change.
+	 */
+	if (timespec64_compare(cb, orig) <= 0)
+		return false;
+
+	/*
+	 * "When the time presented is in the future, the server can either
+	 *  clamp the new time to the current time, or it may
+	 *  return NFS4ERR_DELAY to the client, allowing it to retry."
+	 */
+	if (timespec64_compare(cb, now) > 0) {
+		/* clamp it */
+		*cb = *now;
+	}
+
+	return true;
+}
+
+static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp)
+{
+	struct inode *inode = d_inode(dentry);
+	struct timespec64 now = current_time(inode);
+	struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr;
+	struct iattr attrs = { };
+	int ret;
+
+	if (deleg_attrs_deleg(dp->dl_type)) {
+		struct timespec64 atime = inode_get_atime(inode);
+		struct timespec64 mtime = inode_get_mtime(inode);
+
+		attrs.ia_atime = ncf->ncf_cb_atime;
+		attrs.ia_mtime = ncf->ncf_cb_mtime;
+
+		if (set_cb_time(&attrs.ia_atime, &atime, &now))
+			attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET;
+
+		if (set_cb_time(&attrs.ia_mtime, &mtime, &now)) {
+			attrs.ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET;
+			attrs.ia_ctime = attrs.ia_mtime;
+		}
+	} else {
+		attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME;
+		attrs.ia_mtime = attrs.ia_ctime = now;
+	}
+
+	if (!attrs.ia_valid)
+		return 0;
+
+	attrs.ia_valid |= ATTR_DELEG;
+	inode_lock(inode);
+	ret = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL);
+	inode_unlock(inode);
+	return ret;
+}
+
+/**
  * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
  * @rqstp: RPC transaction context
  * @dentry: dentry of inode to be checked for a conflict
@@ -8914,7 +9142,6 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
 	struct file_lock_context *ctx;
 	struct nfs4_delegation *dp = NULL;
 	struct file_lease *fl;
-	struct iattr attrs;
 	struct nfs4_cb_fattr *ncf;
 	struct inode *inode = d_inode(dentry);
 
@@ -8976,11 +9203,7 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
 		 * not update the file's metadata with the client's
 		 * modified size
 		 */
-		attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
-		attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG;
-		inode_lock(inode);
-		err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL);
-		inode_unlock(inode);
+		err = cb_getattr_update_times(dentry, dp);
 		if (err) {
 			status = nfserrno(err);
 			goto out_status;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 8dd2e2ada474..e67420729ecd 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -55,6 +55,7 @@
 #include "netns.h"
 #include "pnfs.h"
 #include "filecache.h"
+#include "nfs4xdr_gen.h"
 
 #include "trace.h"
 
@@ -520,6 +521,26 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen,
 		*umask = mask & S_IRWXUGO;
 		iattr->ia_valid |= ATTR_MODE;
 	}
+	if (bmval[2] & FATTR4_WORD2_TIME_DELEG_ACCESS) {
+		fattr4_time_deleg_access access;
+
+		if (!xdrgen_decode_fattr4_time_deleg_access(argp->xdr, &access))
+			return nfserr_bad_xdr;
+		iattr->ia_atime.tv_sec = access.seconds;
+		iattr->ia_atime.tv_nsec = access.nseconds;
+		iattr->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET | ATTR_DELEG;
+	}
+	if (bmval[2] & FATTR4_WORD2_TIME_DELEG_MODIFY) {
+		fattr4_time_deleg_modify modify;
+
+		if (!xdrgen_decode_fattr4_time_deleg_modify(argp->xdr, &modify))
+			return nfserr_bad_xdr;
+		iattr->ia_mtime.tv_sec = modify.seconds;
+		iattr->ia_mtime.tv_nsec = modify.nseconds;
+		iattr->ia_ctime.tv_sec = modify.seconds;
+		iattr->ia_ctime.tv_nsec = modify.seconds;
+		iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME | ATTR_MTIME_SET | ATTR_DELEG;
+	}
 
 	/* request sanity: did attrlist4 contain the expected number of words? */
 	if (attrlist4_count != xdr_stream_pos(argp->xdr) - starting_pos)
@@ -1066,13 +1087,13 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh
 		return nfs_ok;
 	if (!argp->minorversion)
 		return nfserr_bad_xdr;
-	switch (w & NFS4_SHARE_WANT_MASK) {
-	case NFS4_SHARE_WANT_NO_PREFERENCE:
-	case NFS4_SHARE_WANT_READ_DELEG:
-	case NFS4_SHARE_WANT_WRITE_DELEG:
-	case NFS4_SHARE_WANT_ANY_DELEG:
-	case NFS4_SHARE_WANT_NO_DELEG:
-	case NFS4_SHARE_WANT_CANCEL:
+	switch (w & NFS4_SHARE_WANT_TYPE_MASK) {
+	case OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE:
+	case OPEN4_SHARE_ACCESS_WANT_READ_DELEG:
+	case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG:
+	case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG:
+	case OPEN4_SHARE_ACCESS_WANT_NO_DELEG:
+	case OPEN4_SHARE_ACCESS_WANT_CANCEL:
 		break;
 	default:
 		return nfserr_bad_xdr;
@@ -1884,7 +1905,8 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp,
 		return nfserr_bad_xdr;
 	seq->seqid = be32_to_cpup(p++);
 	seq->slotid = be32_to_cpup(p++);
-	seq->maxslots = be32_to_cpup(p++);
+	/* sa_highest_slotid counts from 0 but maxslots  counts from 1 ... */
+	seq->maxslots = be32_to_cpup(p++) + 1;
 	seq->cachethis = be32_to_cpup(p);
 
 	seq->status_flags = 0;
@@ -2919,6 +2941,7 @@ struct nfsd4_fattr_args {
 	struct kstat		stat;
 	struct kstatfs		statfs;
 	struct nfs4_acl		*acl;
+	u64			change_attr;
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 	struct lsm_context	context;
 #endif
@@ -3017,7 +3040,6 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr,
 					 const struct nfsd4_fattr_args *args)
 {
 	const struct svc_export *exp = args->exp;
-	u64 c;
 
 	if (unlikely(exp->ex_flags & NFSEXP_V4ROOT)) {
 		u32 flush_time = convert_to_wallclock(exp->cd->flush_time);
@@ -3028,9 +3050,7 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr,
 			return nfserr_resource;
 		return nfs_ok;
 	}
-
-	c = nfsd4_change_attribute(&args->stat);
-	return nfsd4_encode_changeid4(xdr, c);
+	return nfsd4_encode_changeid4(xdr, args->change_attr);
 }
 
 static __be32 nfsd4_encode_fattr4_size(struct xdr_stream *xdr,
@@ -3387,6 +3407,56 @@ static __be32 nfsd4_encode_fattr4_xattr_support(struct xdr_stream *xdr,
 	return nfsd4_encode_bool(xdr, err == 0);
 }
 
+#define NFSD_OA_SHARE_ACCESS	(BIT(OPEN_ARGS_SHARE_ACCESS_READ)	| \
+				 BIT(OPEN_ARGS_SHARE_ACCESS_WRITE)	| \
+				 BIT(OPEN_ARGS_SHARE_ACCESS_BOTH))
+
+#define NFSD_OA_SHARE_DENY	(BIT(OPEN_ARGS_SHARE_DENY_NONE)		| \
+				 BIT(OPEN_ARGS_SHARE_DENY_READ)		| \
+				 BIT(OPEN_ARGS_SHARE_DENY_WRITE)	| \
+				 BIT(OPEN_ARGS_SHARE_DENY_BOTH))
+
+#define NFSD_OA_SHARE_ACCESS_WANT	(BIT(OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG)		| \
+					 BIT(OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG)		| \
+					 BIT(OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL)		| \
+					 BIT(OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS)	| \
+					 BIT(OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION))
+
+#define NFSD_OA_OPEN_CLAIM	(BIT(OPEN_ARGS_OPEN_CLAIM_NULL)		| \
+				 BIT(OPEN_ARGS_OPEN_CLAIM_PREVIOUS)	| \
+				 BIT(OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR)	| \
+				 BIT(OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV)| \
+				 BIT(OPEN_ARGS_OPEN_CLAIM_FH)		| \
+				 BIT(OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH)	| \
+				 BIT(OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH))
+
+#define NFSD_OA_CREATE_MODE	(BIT(OPEN_ARGS_CREATEMODE_UNCHECKED4)	| \
+				 BIT(OPEN_ARGS_CREATE_MODE_GUARDED)	| \
+				 BIT(OPEN_ARGS_CREATEMODE_EXCLUSIVE4)	| \
+				 BIT(OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1))
+
+static uint32_t oa_share_access = NFSD_OA_SHARE_ACCESS;
+static uint32_t oa_share_deny = NFSD_OA_SHARE_DENY;
+static uint32_t oa_share_access_want = NFSD_OA_SHARE_ACCESS_WANT;
+static uint32_t oa_open_claim = NFSD_OA_OPEN_CLAIM;
+static uint32_t oa_create_mode = NFSD_OA_CREATE_MODE;
+
+static const struct open_arguments4 nfsd_open_arguments = {
+	.oa_share_access = { .count = 1, .element = &oa_share_access },
+	.oa_share_deny = { .count = 1, .element = &oa_share_deny },
+	.oa_share_access_want = { .count = 1, .element = &oa_share_access_want },
+	.oa_open_claim = { .count = 1, .element = &oa_open_claim },
+	.oa_create_mode = { .count = 1, .element = &oa_create_mode },
+};
+
+static __be32 nfsd4_encode_fattr4_open_arguments(struct xdr_stream *xdr,
+						 const struct nfsd4_fattr_args *args)
+{
+	if (!xdrgen_encode_fattr4_open_arguments(xdr, &nfsd_open_arguments))
+		return nfserr_resource;
+	return nfs_ok;
+}
+
 static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = {
 	[FATTR4_SUPPORTED_ATTRS]	= nfsd4_encode_fattr4_supported_attrs,
 	[FATTR4_TYPE]			= nfsd4_encode_fattr4_type,
@@ -3487,6 +3557,7 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = {
 
 	[FATTR4_MODE_UMASK]		= nfsd4_encode_fattr4__noop,
 	[FATTR4_XATTR_SUPPORT]		= nfsd4_encode_fattr4_xattr_support,
+	[FATTR4_OPEN_ARGUMENTS]		= nfsd4_encode_fattr4_open_arguments,
 };
 
 /*
@@ -3504,8 +3575,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	struct nfsd4_fattr_args args;
 	struct svc_fh *tempfh = NULL;
 	int starting_len = xdr->buf->len;
-	__be32 *attrlen_p, status;
-	int attrlen_offset;
+	unsigned int attrlen_offset;
+	__be32 attrlen, status;
 	u32 attrmask[3];
 	int err;
 	struct nfsd4_compoundres *resp = rqstp->rq_resp;
@@ -3542,7 +3613,11 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		if (status)
 			goto out;
 	}
-	if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
+	if ((attrmask[0] & (FATTR4_WORD0_CHANGE |
+			    FATTR4_WORD0_SIZE)) ||
+	    (attrmask[1] & (FATTR4_WORD1_TIME_ACCESS |
+			    FATTR4_WORD1_TIME_MODIFY |
+			    FATTR4_WORD1_TIME_METADATA))) {
 		status = nfsd4_deleg_getattr_conflict(rqstp, dentry, &dp);
 		if (status)
 			goto out;
@@ -3554,11 +3629,22 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	if (dp) {
 		struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr;
 
-		if (ncf->ncf_file_modified)
+		if (ncf->ncf_file_modified) {
+			++ncf->ncf_initial_cinfo;
 			args.stat.size = ncf->ncf_cur_fsize;
+			if (!timespec64_is_epoch(&ncf->ncf_cb_mtime))
+				args.stat.mtime = ncf->ncf_cb_mtime;
+		}
+		args.change_attr = ncf->ncf_initial_cinfo;
+
+		if (!timespec64_is_epoch(&ncf->ncf_cb_atime))
+			args.stat.atime = ncf->ncf_cb_atime;
 
 		nfs4_put_stid(&dp->dl_stid);
+	} else {
+		args.change_attr = nfsd4_change_attribute(&args.stat);
 	}
+
 	if (err)
 		goto out_nfserr;
 
@@ -3626,8 +3712,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 
 	/* attr_vals */
 	attrlen_offset = xdr->buf->len;
-	attrlen_p = xdr_reserve_space(xdr, XDR_UNIT);
-	if (!attrlen_p)
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT)))
 		goto out_resource;
 	bitmap_from_arr32(attr_bitmap, attrmask,
 			  ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
@@ -3637,7 +3722,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		if (status != nfs_ok)
 			goto out;
 	}
-	*attrlen_p = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
+	attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
+	write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT);
 	status = nfs_ok;
 
 out:
@@ -4227,18 +4313,20 @@ nfsd4_encode_open_delegation4(struct xdr_stream *xdr, struct nfsd4_open *open)
 	if (xdr_stream_encode_u32(xdr, open->op_delegate_type) != XDR_UNIT)
 		return nfserr_resource;
 	switch (open->op_delegate_type) {
-	case NFS4_OPEN_DELEGATE_NONE:
+	case OPEN_DELEGATE_NONE:
 		status = nfs_ok;
 		break;
-	case NFS4_OPEN_DELEGATE_READ:
+	case OPEN_DELEGATE_READ:
+	case OPEN_DELEGATE_READ_ATTRS_DELEG:
 		/* read */
 		status = nfsd4_encode_open_read_delegation4(xdr, open);
 		break;
-	case NFS4_OPEN_DELEGATE_WRITE:
+	case OPEN_DELEGATE_WRITE:
+	case OPEN_DELEGATE_WRITE_ATTRS_DELEG:
 		/* write */
 		status = nfsd4_encode_open_write_delegation4(xdr, open);
 		break;
-	case NFS4_OPEN_DELEGATE_NONE_EXT:
+	case OPEN_DELEGATE_NONE_EXT:
 		/* od_whynone */
 		status = nfsd4_encode_open_none_delegation4(xdr, open);
 		break;
@@ -4315,6 +4403,15 @@ static __be32 nfsd4_encode_splice_read(
 	__be32 nfserr;
 
 	/*
+	 * Splice read doesn't work if encoding has already wandered
+	 * into the XDR buf's page array.
+	 */
+	if (unlikely(xdr->buf->page_len)) {
+		WARN_ON_ONCE(1);
+		return nfserr_serverfault;
+	}
+
+	/*
 	 * Make sure there is room at the end of buf->head for
 	 * svcxdr_encode_opaque_pages() to create a tail buffer
 	 * to XDR-pad the payload.
@@ -4396,25 +4493,23 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	struct nfsd4_compoundargs *argp = resp->rqstp->rq_argp;
 	struct nfsd4_read *read = &u->read;
 	struct xdr_stream *xdr = resp->xdr;
-	int starting_len = xdr->buf->len;
 	bool splice_ok = argp->splice_ok;
+	unsigned int eof_offset;
 	unsigned long maxcount;
+	__be32 wire_data[2];
 	struct file *file;
-	__be32 *p;
 
 	if (nfserr)
 		return nfserr;
+
+	eof_offset = xdr->buf->len;
 	file = read->rd_nf->nf_file;
 
-	p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
-	if (!p) {
+	/* Reserve space for the eof flag and byte count */
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 2))) {
 		WARN_ON_ONCE(splice_ok);
 		return nfserr_resource;
 	}
-	if (resp->xdr->buf->page_len && splice_ok) {
-		WARN_ON_ONCE(1);
-		return nfserr_serverfault;
-	}
 	xdr_commit_encode(xdr);
 
 	maxcount = min_t(unsigned long, read->rd_length,
@@ -4425,12 +4520,13 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
 	else
 		nfserr = nfsd4_encode_readv(resp, read, file, maxcount);
 	if (nfserr) {
-		xdr_truncate_encode(xdr, starting_len);
+		xdr_truncate_encode(xdr, eof_offset);
 		return nfserr;
 	}
 
-	p = xdr_encode_bool(p, read->rd_eof);
-	*p = cpu_to_be32(read->rd_length);
+	wire_data[0] = read->rd_eof ? xdr_one : xdr_zero;
+	wire_data[1] = cpu_to_be32(read->rd_length);
+	write_bytes_to_xdr_buf(xdr->buf, eof_offset, &wire_data, XDR_UNIT * 2);
 	return nfs_ok;
 }
 
@@ -4439,25 +4535,21 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr,
 		      union nfsd4_op_u *u)
 {
 	struct nfsd4_readlink *readlink = &u->readlink;
-	__be32 *p, *maxcount_p, zero = xdr_zero;
+	__be32 *p, wire_count, zero = xdr_zero;
 	struct xdr_stream *xdr = resp->xdr;
-	int length_offset = xdr->buf->len;
+	unsigned int length_offset;
 	int maxcount, status;
 
-	maxcount_p = xdr_reserve_space(xdr, XDR_UNIT);
-	if (!maxcount_p)
+	/* linktext4.count */
+	length_offset = xdr->buf->len;
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT)))
 		return nfserr_resource;
-	maxcount = PAGE_SIZE;
 
+	/* linktext4.data */
+	maxcount = PAGE_SIZE;
 	p = xdr_reserve_space(xdr, maxcount);
 	if (!p)
 		return nfserr_resource;
-	/*
-	 * XXX: By default, vfs_readlink() will truncate symlinks if they
-	 * would overflow the buffer.  Is this kosher in NFSv4?  If not, one
-	 * easy fix is: if vfs_readlink() precisely fills the buffer, assume
-	 * that truncation occurred, and return NFS4ERR_RESOURCE.
-	 */
 	nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp,
 						(char *)p, &maxcount);
 	if (nfserr == nfserr_isdir)
@@ -4470,7 +4562,9 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr,
 		nfserr = nfserrno(status);
 		goto out_err;
 	}
-	*maxcount_p = cpu_to_be32(maxcount);
+
+	wire_count = cpu_to_be32(maxcount);
+	write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, XDR_UNIT);
 	xdr_truncate_encode(xdr, length_offset + 4 + xdr_align_size(maxcount));
 	write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero,
 			       xdr_pad_size(maxcount));
@@ -4605,14 +4699,42 @@ nfsd4_encode_rpcsec_gss_info(struct xdr_stream *xdr,
 }
 
 static __be32
-nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp)
+nfsd4_encode_secinfo4(struct xdr_stream *xdr, rpc_authflavor_t pf,
+		      u32 *supported)
+{
+	struct rpcsec_gss_info info;
+	__be32 status;
+
+	if (rpcauth_get_gssinfo(pf, &info) == 0) {
+		(*supported)++;
+
+		/* flavor */
+		status = nfsd4_encode_uint32_t(xdr, RPC_AUTH_GSS);
+		if (status != nfs_ok)
+			return status;
+		/* flavor_info */
+		status = nfsd4_encode_rpcsec_gss_info(xdr, &info);
+		if (status != nfs_ok)
+			return status;
+	} else if (pf < RPC_AUTH_MAXFLAVOR) {
+		(*supported)++;
+
+		/* flavor */
+		status = nfsd4_encode_uint32_t(xdr, pf);
+		if (status != nfs_ok)
+			return status;
+	}
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_encode_SECINFO4resok(struct xdr_stream *xdr, struct svc_export *exp)
 {
 	u32 i, nflavs, supported;
 	struct exp_flavor_info *flavs;
 	struct exp_flavor_info def_flavs[2];
-	static bool report = true;
-	__be32 *flavorsp;
-	__be32 status;
+	unsigned int count_offset;
+	__be32 status, wire_count;
 
 	if (exp->ex_nflavors) {
 		flavs = exp->ex_flavors;
@@ -4634,43 +4756,20 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp)
 		}
 	}
 
-	supported = 0;
-	flavorsp = xdr_reserve_space(xdr, XDR_UNIT);
-	if (!flavorsp)
+	count_offset = xdr->buf->len;
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT)))
 		return nfserr_resource;
 
-	for (i = 0; i < nflavs; i++) {
-		rpc_authflavor_t pf = flavs[i].pseudoflavor;
-		struct rpcsec_gss_info info;
-
-		if (rpcauth_get_gssinfo(pf, &info) == 0) {
-			supported++;
-
-			/* flavor */
-			status = nfsd4_encode_uint32_t(xdr, RPC_AUTH_GSS);
-			if (status != nfs_ok)
-				return status;
-			/* flavor_info */
-			status = nfsd4_encode_rpcsec_gss_info(xdr, &info);
-			if (status != nfs_ok)
-				return status;
-		} else if (pf < RPC_AUTH_MAXFLAVOR) {
-			supported++;
-
-			/* flavor */
-			status = nfsd4_encode_uint32_t(xdr, pf);
-			if (status != nfs_ok)
-				return status;
-		} else {
-			if (report)
-				pr_warn("NFS: SECINFO: security flavor %u "
-					"is not supported\n", pf);
-		}
+	for (i = 0, supported = 0; i < nflavs; i++) {
+		status = nfsd4_encode_secinfo4(xdr, flavs[i].pseudoflavor,
+					       &supported);
+		if (status != nfs_ok)
+			return status;
 	}
 
-	if (nflavs != supported)
-		report = false;
-	*flavorsp = cpu_to_be32(supported);
+	wire_count = cpu_to_be32(supported);
+	write_bytes_to_xdr_buf(xdr->buf, count_offset, &wire_count,
+			       XDR_UNIT);
 	return 0;
 }
 
@@ -4681,7 +4780,7 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 	struct nfsd4_secinfo *secinfo = &u->secinfo;
 	struct xdr_stream *xdr = resp->xdr;
 
-	return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp);
+	return nfsd4_encode_SECINFO4resok(xdr, secinfo->si_exp);
 }
 
 static __be32
@@ -4691,7 +4790,7 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
 	struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name;
 	struct xdr_stream *xdr = resp->xdr;
 
-	return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp);
+	return nfsd4_encode_SECINFO4resok(xdr, secinfo->sin_exp);
 }
 
 static __be32
@@ -4966,7 +5065,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
 	if (nfserr != nfs_ok)
 		return nfserr;
 	/* sr_target_highest_slotid */
-	nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1);
+	nfserr = nfsd4_encode_slotid4(xdr, seq->target_maxslots - 1);
 	if (nfserr != nfs_ok)
 		return nfserr;
 	/* sr_status_flags */
@@ -5294,17 +5393,20 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
 	struct file *file = read->rd_nf->nf_file;
 	struct xdr_stream *xdr = resp->xdr;
 	bool splice_ok = argp->splice_ok;
+	unsigned int offset_offset;
+	__be32 nfserr, wire_count;
 	unsigned long maxcount;
-	__be32 nfserr, *p;
+	__be64 wire_offset;
 
-	/* Content type, offset, byte count */
-	p = xdr_reserve_space(xdr, 4 + 8 + 4);
-	if (!p)
+	if (xdr_stream_encode_u32(xdr, NFS4_CONTENT_DATA) != XDR_UNIT)
 		return nfserr_io;
-	if (resp->xdr->buf->page_len && splice_ok) {
-		WARN_ON_ONCE(splice_ok);
-		return nfserr_serverfault;
-	}
+
+	offset_offset = xdr->buf->len;
+
+	/* Reserve space for the byte offset and count */
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 3)))
+		return nfserr_io;
+	xdr_commit_encode(xdr);
 
 	maxcount = min_t(unsigned long, read->rd_length,
 			 (xdr->buf->buflen - xdr->buf->len));
@@ -5316,10 +5418,12 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
 	if (nfserr)
 		return nfserr;
 
-	*p++ = cpu_to_be32(NFS4_CONTENT_DATA);
-	p = xdr_encode_hyper(p, read->rd_offset);
-	*p = cpu_to_be32(read->rd_length);
-
+	wire_offset = cpu_to_be64(read->rd_offset);
+	write_bytes_to_xdr_buf(xdr->buf, offset_offset, &wire_offset,
+			       XDR_UNIT * 2);
+	wire_count = cpu_to_be32(read->rd_length);
+	write_bytes_to_xdr_buf(xdr->buf, offset_offset + XDR_UNIT * 2,
+			       &wire_count, XDR_UNIT);
 	return nfs_ok;
 }
 
@@ -5330,16 +5434,17 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr,
 	struct nfsd4_read *read = &u->read;
 	struct file *file = read->rd_nf->nf_file;
 	struct xdr_stream *xdr = resp->xdr;
-	int starting_len = xdr->buf->len;
+	unsigned int eof_offset;
+	__be32 wire_data[2];
 	u32 segments = 0;
-	__be32 *p;
 
 	if (nfserr)
 		return nfserr;
 
-	/* eof flag, segment count */
-	p = xdr_reserve_space(xdr, 4 + 4);
-	if (!p)
+	eof_offset = xdr->buf->len;
+
+	/* Reserve space for the eof flag and segment count */
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT * 2)))
 		return nfserr_io;
 	xdr_commit_encode(xdr);
 
@@ -5349,15 +5454,16 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 	nfserr = nfsd4_encode_read_plus_data(resp, read);
 	if (nfserr) {
-		xdr_truncate_encode(xdr, starting_len);
+		xdr_truncate_encode(xdr, eof_offset);
 		return nfserr;
 	}
 
 	segments++;
 
 out:
-	p = xdr_encode_bool(p, read->rd_eof);
-	*p = cpu_to_be32(segments);
+	wire_data[0] = read->rd_eof ? xdr_one : xdr_zero;
+	wire_data[1] = cpu_to_be32(segments);
+	write_bytes_to_xdr_buf(xdr->buf, eof_offset, &wire_data, XDR_UNIT * 2);
 	return nfserr;
 }
 
@@ -5758,15 +5864,14 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 	struct nfs4_stateowner *so = resp->cstate.replay_owner;
 	struct svc_rqst *rqstp = resp->rqstp;
 	const struct nfsd4_operation *opdesc = op->opdesc;
-	int post_err_offset;
+	unsigned int op_status_offset;
 	nfsd4_enc encoder;
-	__be32 *p;
 
-	p = xdr_reserve_space(xdr, 8);
-	if (!p)
+	if (xdr_stream_encode_u32(xdr, op->opnum) != XDR_UNIT)
+		goto release;
+	op_status_offset = xdr->buf->len;
+	if (!xdr_reserve_space(xdr, XDR_UNIT))
 		goto release;
-	*p++ = cpu_to_be32(op->opnum);
-	post_err_offset = xdr->buf->len;
 
 	if (op->opnum == OP_ILLEGAL)
 		goto status;
@@ -5807,20 +5912,21 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 		 * bug if we had to do this on a non-idempotent op:
 		 */
 		warn_on_nonidempotent_op(op);
-		xdr_truncate_encode(xdr, post_err_offset);
+		xdr_truncate_encode(xdr, op_status_offset + XDR_UNIT);
 	}
 	if (so) {
-		int len = xdr->buf->len - post_err_offset;
+		int len = xdr->buf->len - (op_status_offset + XDR_UNIT);
 
 		so->so_replay.rp_status = op->status;
 		so->so_replay.rp_buflen = len;
-		read_bytes_from_xdr_buf(xdr->buf, post_err_offset,
+		read_bytes_from_xdr_buf(xdr->buf, op_status_offset + XDR_UNIT,
 						so->so_replay.rp_buf, len);
 	}
 status:
 	op->status = nfsd4_map_status(op->status,
 				      resp->cstate.minorversion);
-	*p = op->status;
+	write_bytes_to_xdr_buf(xdr->buf, op_status_offset,
+			       &op->status, XDR_UNIT);
 release:
 	if (opdesc && opdesc->op_release)
 		opdesc->op_release(&op->u);
diff --git a/fs/nfsd/nfs4xdr_gen.c b/fs/nfsd/nfs4xdr_gen.c
new file mode 100644
index 000000000000..a17b5d8e60b3
--- /dev/null
+++ b/fs/nfsd/nfs4xdr_gen.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+// Generated by xdrgen. Manual edits will be lost.
+// XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x
+// XDR specification modification time: Mon Oct 14 09:10:13 2024
+
+#include <linux/sunrpc/svc.h>
+
+#include "nfs4xdr_gen.h"
+
+static bool __maybe_unused
+xdrgen_decode_int64_t(struct xdr_stream *xdr, int64_t *ptr)
+{
+	return xdrgen_decode_hyper(xdr, ptr);
+};
+
+static bool __maybe_unused
+xdrgen_decode_uint32_t(struct xdr_stream *xdr, uint32_t *ptr)
+{
+	return xdrgen_decode_unsigned_int(xdr, ptr);
+};
+
+static bool __maybe_unused
+xdrgen_decode_bitmap4(struct xdr_stream *xdr, bitmap4 *ptr)
+{
+	if (xdr_stream_decode_u32(xdr, &ptr->count) < 0)
+		return false;
+	for (u32 i = 0; i < ptr->count; i++)
+		if (!xdrgen_decode_uint32_t(xdr, &ptr->element[i]))
+			return false;
+	return true;
+};
+
+static bool __maybe_unused
+xdrgen_decode_nfstime4(struct xdr_stream *xdr, struct nfstime4 *ptr)
+{
+	if (!xdrgen_decode_int64_t(xdr, &ptr->seconds))
+		return false;
+	if (!xdrgen_decode_uint32_t(xdr, &ptr->nseconds))
+		return false;
+	return true;
+};
+
+static bool __maybe_unused
+xdrgen_decode_fattr4_offline(struct xdr_stream *xdr, fattr4_offline *ptr)
+{
+	return xdrgen_decode_bool(xdr, ptr);
+};
+
+static bool __maybe_unused
+xdrgen_decode_open_arguments4(struct xdr_stream *xdr, struct open_arguments4 *ptr)
+{
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_deny))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_share_access_want))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_open_claim))
+		return false;
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->oa_create_mode))
+		return false;
+	return true;
+};
+
+static bool __maybe_unused
+xdrgen_decode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	*ptr = val;
+	return true;
+}
+
+bool
+xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr)
+{
+	return xdrgen_decode_open_arguments4(xdr, ptr);
+};
+
+bool
+xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr)
+{
+	return xdrgen_decode_nfstime4(xdr, ptr);
+};
+
+bool
+xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr)
+{
+	return xdrgen_decode_nfstime4(xdr, ptr);
+};
+
+static bool __maybe_unused
+xdrgen_decode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_int64_t(struct xdr_stream *xdr, const int64_t value)
+{
+	return xdrgen_encode_hyper(xdr, value);
+};
+
+static bool __maybe_unused
+xdrgen_encode_uint32_t(struct xdr_stream *xdr, const uint32_t value)
+{
+	return xdrgen_encode_unsigned_int(xdr, value);
+};
+
+static bool __maybe_unused
+xdrgen_encode_bitmap4(struct xdr_stream *xdr, const bitmap4 value)
+{
+	if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value.count; i++)
+		if (!xdrgen_encode_uint32_t(xdr, value.element[i]))
+			return false;
+	return true;
+};
+
+static bool __maybe_unused
+xdrgen_encode_nfstime4(struct xdr_stream *xdr, const struct nfstime4 *value)
+{
+	if (!xdrgen_encode_int64_t(xdr, value->seconds))
+		return false;
+	if (!xdrgen_encode_uint32_t(xdr, value->nseconds))
+		return false;
+	return true;
+};
+
+static bool __maybe_unused
+xdrgen_encode_fattr4_offline(struct xdr_stream *xdr, const fattr4_offline value)
+{
+	return xdrgen_encode_bool(xdr, value);
+};
+
+static bool __maybe_unused
+xdrgen_encode_open_arguments4(struct xdr_stream *xdr, const struct open_arguments4 *value)
+{
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_share_deny))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_share_access_want))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_open_claim))
+		return false;
+	if (!xdrgen_encode_bitmap4(xdr, value->oa_create_mode))
+		return false;
+	return true;
+};
+
+static bool __maybe_unused
+xdrgen_encode_open_args_share_access4(struct xdr_stream *xdr, open_args_share_access4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_share_deny4(struct xdr_stream *xdr, open_args_share_deny4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_share_access_want4(struct xdr_stream *xdr, open_args_share_access_want4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_open_claim4(struct xdr_stream *xdr, open_args_open_claim4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_open_args_createmode4(struct xdr_stream *xdr, open_args_createmode4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+bool
+xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value)
+{
+	return xdrgen_encode_open_arguments4(xdr, value);
+};
+
+bool
+xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value)
+{
+	return xdrgen_encode_nfstime4(xdr, value);
+};
+
+bool
+xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value)
+{
+	return xdrgen_encode_nfstime4(xdr, value);
+};
+
+static bool __maybe_unused
+xdrgen_encode_open_delegation_type4(struct xdr_stream *xdr, open_delegation_type4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
diff --git a/fs/nfsd/nfs4xdr_gen.h b/fs/nfsd/nfs4xdr_gen.h
new file mode 100644
index 000000000000..41a0033b7256
--- /dev/null
+++ b/fs/nfsd/nfs4xdr_gen.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Generated by xdrgen. Manual edits will be lost. */
+/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
+/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */
+
+#ifndef _LINUX_XDRGEN_NFS4_1_DECL_H
+#define _LINUX_XDRGEN_NFS4_1_DECL_H
+
+#include <linux/types.h>
+
+#include <linux/sunrpc/xdr.h>
+#include <linux/sunrpc/xdrgen/_defs.h>
+#include <linux/sunrpc/xdrgen/_builtins.h>
+#include <linux/sunrpc/xdrgen/nfs4_1.h>
+
+bool xdrgen_decode_fattr4_open_arguments(struct xdr_stream *xdr, fattr4_open_arguments *ptr);
+bool xdrgen_encode_fattr4_open_arguments(struct xdr_stream *xdr, const fattr4_open_arguments *value);
+
+bool xdrgen_decode_fattr4_time_deleg_access(struct xdr_stream *xdr, fattr4_time_deleg_access *ptr);
+bool xdrgen_encode_fattr4_time_deleg_access(struct xdr_stream *xdr, const fattr4_time_deleg_access *value);
+
+bool xdrgen_decode_fattr4_time_deleg_modify(struct xdr_stream *xdr, fattr4_time_deleg_modify *ptr);
+bool xdrgen_encode_fattr4_time_deleg_modify(struct xdr_stream *xdr, const fattr4_time_deleg_modify *value);
+
+#endif /* _LINUX_XDRGEN_NFS4_1_DECL_H */
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3adbc05ebaac..ce2a71e4904c 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -48,7 +48,6 @@ enum {
 	NFSD_Versions,
 	NFSD_Ports,
 	NFSD_MaxBlkSize,
-	NFSD_MaxConnections,
 	NFSD_Filecache,
 	NFSD_Leasetime,
 	NFSD_Gracetime,
@@ -68,7 +67,6 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size);
 static ssize_t write_versions(struct file *file, char *buf, size_t size);
 static ssize_t write_ports(struct file *file, char *buf, size_t size);
 static ssize_t write_maxblksize(struct file *file, char *buf, size_t size);
-static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
 #ifdef CONFIG_NFSD_V4
 static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
 static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
@@ -87,7 +85,6 @@ static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
 	[NFSD_Versions] = write_versions,
 	[NFSD_Ports] = write_ports,
 	[NFSD_MaxBlkSize] = write_maxblksize,
-	[NFSD_MaxConnections] = write_maxconn,
 #ifdef CONFIG_NFSD_V4
 	[NFSD_Leasetime] = write_leasetime,
 	[NFSD_Gracetime] = write_gracetime,
@@ -902,44 +899,6 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
 							nfsd_max_blksize);
 }
 
-/*
- * write_maxconn - Set or report the current max number of connections
- *
- * Input:
- *			buf:		ignored
- *			size:		zero
- * OR
- *
- * Input:
- *			buf:		C string containing an unsigned
- *					integer value representing the new
- *					number of max connections
- *			size:		non-zero length of C string in @buf
- * Output:
- *	On success:	passed-in buffer filled with '\n'-terminated C string
- *			containing numeric value of max_connections setting
- *			for this net namespace;
- *			return code is the size in bytes of the string
- *	On error:	return code is zero or a negative errno value
- */
-static ssize_t write_maxconn(struct file *file, char *buf, size_t size)
-{
-	char *mesg = buf;
-	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
-	unsigned int maxconn = nn->max_connections;
-
-	if (size > 0) {
-		int rv = get_uint(&mesg, &maxconn);
-
-		if (rv)
-			return rv;
-		trace_nfsd_ctl_maxconn(netns(file), maxconn);
-		nn->max_connections = maxconn;
-	}
-
-	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%u\n", maxconn);
-}
-
 #ifdef CONFIG_NFSD_V4
 static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
 				  time64_t *time, struct nfsd_net *nn)
@@ -1372,7 +1331,6 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
 		[NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
 		[NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},
-		[NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO},
 		[NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO},
 #ifdef CONFIG_NFSD_V4
 		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
@@ -2259,6 +2217,7 @@ static __net_init int nfsd_net_init(struct net *net)
 	seqlock_init(&nn->writeverf_lock);
 	nfsd_proc_stat_init(net);
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	spin_lock_init(&nn->local_clients_lock);
 	INIT_LIST_HEAD(&nn->local_clients);
 #endif
 	return 0;
@@ -2276,14 +2235,15 @@ out_export_error:
  * nfsd_net_pre_exit - Disconnect localio clients from net namespace
  * @net: a network namespace that is about to be destroyed
  *
- * This invalidated ->net pointers held by localio clients
+ * This invalidates ->net pointers held by localio clients
  * while they can still safely access nn->counter.
  */
 static __net_exit void nfsd_net_pre_exit(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	nfs_uuid_invalidate_clients(&nn->local_clients);
+	nfs_localio_invalidate_clients(&nn->local_clients,
+				       &nn->local_clients_lock);
 }
 #endif
 
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 4b56ba1e8e48..e2997f0ffbc5 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -88,9 +88,6 @@ struct nfsd_genl_rqstp {
 extern struct svc_program	nfsd_programs[];
 extern const struct svc_version	nfsd_version2, nfsd_version3, nfsd_version4;
 extern struct mutex		nfsd_mutex;
-extern spinlock_t		nfsd_drc_lock;
-extern unsigned long		nfsd_drc_max_mem;
-extern unsigned long		nfsd_drc_mem_used;
 extern atomic_t			nfsd_th_cnt;		/* number of available threads */
 
 extern const struct seq_operations nfs_exports_op;
@@ -458,7 +455,10 @@ enum {
 	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
 	FATTR4_WORD2_MODE_UMASK | \
 	NFSD4_2_SECURITY_ATTRS | \
-	FATTR4_WORD2_XATTR_SUPPORT)
+	FATTR4_WORD2_XATTR_SUPPORT | \
+	FATTR4_WORD2_TIME_DELEG_ACCESS | \
+	FATTR4_WORD2_TIME_DELEG_MODIFY | \
+	FATTR4_WORD2_OPEN_ARGUMENTS)
 
 extern const u32 nfsd_suppattrs[3][3];
 
@@ -528,7 +528,10 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval)
 #endif
 #define NFSD_WRITEABLE_ATTRS_WORD2 \
 	(FATTR4_WORD2_MODE_UMASK \
-	| MAYBE_FATTR4_WORD2_SECURITY_LABEL)
+	| MAYBE_FATTR4_WORD2_SECURITY_LABEL \
+	| FATTR4_WORD2_TIME_DELEG_ACCESS \
+	| FATTR4_WORD2_TIME_DELEG_MODIFY \
+	)
 
 #define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
 	NFSD_WRITEABLE_ATTRS_WORD0
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 98d6459724a7..aef474f1b84b 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -380,6 +380,9 @@ __fh_verify(struct svc_rqst *rqstp,
 	error = check_nfsd_access(exp, rqstp, may_bypass_gss);
 	if (error)
 		goto out;
+	/* During LOCALIO call to fh_verify will be called with a NULL rqstp */
+	if (rqstp)
+		svc_xprt_set_valid(rqstp->rq_xprt);
 
 	/* Finally, check access permissions. */
 	error = nfsd_permission(cred, exp, dentry, access);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 49e2f32102ab..9b3d6cff0e1e 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -70,16 +70,6 @@ static __be32			nfsd_init_request(struct svc_rqst *,
  */
 DEFINE_MUTEX(nfsd_mutex);
 
-/*
- * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
- * nfsd_drc_max_pages limits the total amount of memory available for
- * version 4.1 DRC caches.
- * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
- */
-DEFINE_SPINLOCK(nfsd_drc_lock);
-unsigned long	nfsd_drc_max_mem;
-unsigned long	nfsd_drc_mem_used;
-
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 static const struct svc_version *localio_versions[] = {
 	[1] = &localio_version1,
@@ -214,32 +204,32 @@ int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change
 	return 0;
 }
 
-bool nfsd_serv_try_get(struct net *net) __must_hold(rcu)
+bool nfsd_net_try_get(struct net *net) __must_hold(rcu)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	return (nn && percpu_ref_tryget_live(&nn->nfsd_serv_ref));
+	return (nn && percpu_ref_tryget_live(&nn->nfsd_net_ref));
 }
 
-void nfsd_serv_put(struct net *net) __must_hold(rcu)
+void nfsd_net_put(struct net *net) __must_hold(rcu)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	percpu_ref_put(&nn->nfsd_serv_ref);
+	percpu_ref_put(&nn->nfsd_net_ref);
 }
 
-static void nfsd_serv_done(struct percpu_ref *ref)
+static void nfsd_net_done(struct percpu_ref *ref)
 {
-	struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref);
+	struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref);
 
-	complete(&nn->nfsd_serv_confirm_done);
+	complete(&nn->nfsd_net_confirm_done);
 }
 
-static void nfsd_serv_free(struct percpu_ref *ref)
+static void nfsd_net_free(struct percpu_ref *ref)
 {
-	struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_serv_ref);
+	struct nfsd_net *nn = container_of(ref, struct nfsd_net, nfsd_net_ref);
 
-	complete(&nn->nfsd_serv_free_done);
+	complete(&nn->nfsd_net_free_done);
 }
 
 /*
@@ -436,6 +426,10 @@ static void nfsd_shutdown_net(struct net *net)
 
 	if (!nn->nfsd_net_up)
 		return;
+
+	percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done);
+	wait_for_completion(&nn->nfsd_net_confirm_done);
+
 	nfsd_export_flush(net);
 	nfs4_state_shutdown_net(net);
 	nfsd_reply_cache_shutdown(nn);
@@ -444,7 +438,10 @@ static void nfsd_shutdown_net(struct net *net)
 		lockd_down(net);
 		nn->lockd_up = false;
 	}
-	percpu_ref_exit(&nn->nfsd_serv_ref);
+
+	wait_for_completion(&nn->nfsd_net_free_done);
+	percpu_ref_exit(&nn->nfsd_net_ref);
+
 	nn->nfsd_net_up = false;
 	nfsd_shutdown_generic();
 }
@@ -526,11 +523,6 @@ void nfsd_destroy_serv(struct net *net)
 
 	lockdep_assert_held(&nfsd_mutex);
 
-	percpu_ref_kill_and_confirm(&nn->nfsd_serv_ref, nfsd_serv_done);
-	wait_for_completion(&nn->nfsd_serv_confirm_done);
-	wait_for_completion(&nn->nfsd_serv_free_done);
-	/* percpu_ref_exit is called in nfsd_shutdown_net */
-
 	spin_lock(&nfsd_notifier_lock);
 	nn->nfsd_serv = NULL;
 	spin_unlock(&nfsd_notifier_lock);
@@ -575,27 +567,6 @@ void nfsd_reset_versions(struct nfsd_net *nn)
 		}
 }
 
-/*
- * Each session guarantees a negotiated per slot memory cache for replies
- * which in turn consumes memory beyond the v2/v3/v4.0 server. A dedicated
- * NFSv4.1 server might want to use more memory for a DRC than a machine
- * with mutiple services.
- *
- * Impose a hard limit on the number of pages for the DRC which varies
- * according to the machines free pages. This is of course only a default.
- *
- * For now this is a #defined shift which could be under admin control
- * in the future.
- */
-static void set_max_drc(void)
-{
-	#define NFSD_DRC_SIZE_SHIFT	7
-	nfsd_drc_max_mem = (nr_free_buffer_pages()
-					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
-	nfsd_drc_mem_used = 0;
-	dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
-}
-
 static int nfsd_get_default_max_blksize(void)
 {
 	struct sysinfo i;
@@ -652,12 +623,12 @@ int nfsd_create_serv(struct net *net)
 	if (nn->nfsd_serv)
 		return 0;
 
-	error = percpu_ref_init(&nn->nfsd_serv_ref, nfsd_serv_free,
+	error = percpu_ref_init(&nn->nfsd_net_ref, nfsd_net_free,
 				0, GFP_KERNEL);
 	if (error)
 		return error;
-	init_completion(&nn->nfsd_serv_free_done);
-	init_completion(&nn->nfsd_serv_confirm_done);
+	init_completion(&nn->nfsd_net_free_done);
+	init_completion(&nn->nfsd_net_confirm_done);
 
 	if (nfsd_max_blksize == 0)
 		nfsd_max_blksize = nfsd_get_default_max_blksize();
@@ -668,7 +639,6 @@ int nfsd_create_serv(struct net *net)
 	if (serv == NULL)
 		return -ENOMEM;
 
-	serv->sv_maxconn = nn->max_connections;
 	error = svc_bind(serv, net);
 	if (error < 0) {
 		svc_destroy(&serv);
@@ -678,7 +648,6 @@ int nfsd_create_serv(struct net *net)
 	nn->nfsd_serv = serv;
 	spin_unlock(&nfsd_notifier_lock);
 
-	set_max_drc();
 	/* check if the notifier is already set */
 	if (atomic_inc_return(&nfsd_notifier_refcount) == 1) {
 		register_inetaddr_notifier(&nfsd_inetaddr_notifier);
@@ -954,11 +923,7 @@ nfsd(void *vrqstp)
 	 * The main request loop
 	 */
 	while (!svc_thread_should_stop(rqstp)) {
-		/* Update sv_maxconn if it has changed */
-		rqstp->rq_server->sv_maxconn = nn->max_connections;
-
 		svc_recv(rqstp);
-
 		nfsd_file_net_dispose(nn);
 	}
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index e16bb3717fb9..74d2d7b42676 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -159,6 +159,8 @@ struct nfs4_cb_fattr {
 	/* from CB_GETATTR reply */
 	u64 ncf_cb_change;
 	u64 ncf_cb_fsize;
+	struct timespec64 ncf_cb_mtime;
+	struct timespec64 ncf_cb_atime;
 
 	unsigned long ncf_cb_flags;
 	bool ncf_file_modified;
@@ -207,6 +209,22 @@ struct nfs4_delegation {
 	struct nfs4_cb_fattr    dl_cb_fattr;
 };
 
+static inline bool deleg_is_read(u32 dl_type)
+{
+	return (dl_type == OPEN_DELEGATE_READ || dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG);
+}
+
+static inline bool deleg_is_write(u32 dl_type)
+{
+	return (dl_type == OPEN_DELEGATE_WRITE || dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG);
+}
+
+static inline bool deleg_attrs_deleg(u32 dl_type)
+{
+	return dl_type == OPEN_DELEGATE_READ_ATTRS_DELEG ||
+	       dl_type == OPEN_DELEGATE_WRITE_ATTRS_DELEG;
+}
+
 #define cb_to_delegation(cb) \
 	container_of(cb, struct nfs4_delegation, dl_recall)
 
@@ -227,8 +245,11 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
 	return container_of(s, struct nfs4_delegation, dl_stid);
 }
 
-/* Maximum number of slots per session. 160 is useful for long haul TCP */
-#define NFSD_MAX_SLOTS_PER_SESSION     160
+/* Maximum number of slots per session.  This is for sanity-check only.
+ * It could be increased if we had a mechanism to shutdown misbehaving clients.
+ * A large number can be needed to get good throughput on high-latency servers.
+ */
+#define NFSD_MAX_SLOTS_PER_SESSION	2048
 /* Maximum  session per slot cache size */
 #define NFSD_SLOT_CACHE_SIZE		2048
 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
@@ -242,10 +263,12 @@ struct nfsd4_slot {
 	struct svc_cred sl_cred;
 	u32	sl_datalen;
 	u16	sl_opcnt;
+	u16	sl_generation;
 #define NFSD4_SLOT_INUSE	(1 << 0)
 #define NFSD4_SLOT_CACHETHIS	(1 << 1)
 #define NFSD4_SLOT_INITIALIZED	(1 << 2)
 #define NFSD4_SLOT_CACHED	(1 << 3)
+#define NFSD4_SLOT_REUSED	(1 << 4)
 	u8	sl_flags;
 	char	sl_data[];
 };
@@ -318,16 +341,19 @@ struct nfsd4_session {
 	u32			se_cb_slot_avail; /* bitmap of available slots */
 	u32			se_cb_highest_slot;	/* highest slot client wants */
 	u32			se_cb_prog;
-	bool			se_dead;
 	struct list_head	se_hash;	/* hash by sessionid */
 	struct list_head	se_perclnt;
+	struct list_head	se_all_sessions;/* global list of sessions */
 	struct nfs4_client	*se_client;
 	struct nfs4_sessionid	se_sessionid;
 	struct nfsd4_channel_attrs se_fchannel;
 	struct nfsd4_cb_sec	se_cb_sec;
 	struct list_head	se_conns;
 	u32			se_cb_seq_nr[NFSD_BC_SLOT_TABLE_SIZE];
-	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
+	struct xarray		se_slots;	/* forward channel slots */
+	u16			se_slot_gen;
+	bool			se_dead;
+	u32			se_target_maxslots;
 };
 
 /* formatted contents of nfs4_sessionid */
@@ -505,7 +531,7 @@ struct nfs4_replay {
 	unsigned int		rp_buflen;
 	char			*rp_buf;
 	struct knfsd_fh		rp_openfh;
-	atomic_t		rp_locked;
+	int			rp_locked;
 	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
 };
 
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 696c89f68a9e..ad2c0c432d08 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -626,7 +626,6 @@ DEFINE_STATEID_EVENT(open);
 DEFINE_STATEID_EVENT(deleg_read);
 DEFINE_STATEID_EVENT(deleg_write);
 DEFINE_STATEID_EVENT(deleg_return);
-DEFINE_STATEID_EVENT(deleg_recall);
 
 DECLARE_EVENT_CLASS(nfsd_stateseqid_class,
 	TP_PROTO(u32 seqid, const stateid_t *stp),
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 382cc1389396..c26ba86dbdfd 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -576,9 +576,7 @@ struct nfsd4_sequence {
 	u32			slotid;			/* request/response */
 	u32			maxslots;		/* request/response */
 	u32			cachethis;		/* request */
-#if 0
 	u32			target_maxslots;	/* response */
-#endif /* not yet */
 	u32			status_flags;		/* response */
 };
 
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index e8b00309c449..f1a315cd31b7 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -59,16 +59,20 @@
  * 1: CB_GETATTR opcode (32-bit)
  * N: file_handle
  * 1: number of entry in attribute array (32-bit)
- * 1: entry 0 in attribute array (32-bit)
+ * 3: entry 0-2 in attribute array (32-bit * 3)
  */
 #define NFS4_enc_cb_getattr_sz		(cb_compound_enc_hdr_sz +       \
 					cb_sequence_enc_sz +            \
-					1 + enc_nfs4_fh_sz + 1 + 1)
+					1 + enc_nfs4_fh_sz + 1 + 3)
 /*
  * 4: fattr_bitmap_maxsz
  * 1: attribute array len
  * 2: change attr (64-bit)
  * 2: size (64-bit)
+ * 2: atime.seconds (64-bit)
+ * 1: atime.nanoseconds (32-bit)
+ * 2: mtime.seconds (64-bit)
+ * 1: mtime.nanoseconds (32-bit)
  */
 #define NFS4_dec_cb_getattr_sz		(cb_compound_dec_hdr_sz  +      \
-			cb_sequence_dec_sz + 4 + 1 + 2 + 2 + op_dec_sz)
+			cb_sequence_dec_sz + 4 + 1 + 2 + 2 + 2 + 1 + 2 + 1 + op_dec_sz)
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index ba3e1f591f36..6b506995818d 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -21,6 +21,8 @@
  * nilfs_palloc_groups_per_desc_block - get the number of groups that a group
  *					descriptor block can maintain
  * @inode: inode of metadata file using this allocator
+ *
+ * Return: Number of groups that a group descriptor block can maintain.
  */
 static inline unsigned long
 nilfs_palloc_groups_per_desc_block(const struct inode *inode)
@@ -32,6 +34,8 @@ nilfs_palloc_groups_per_desc_block(const struct inode *inode)
 /**
  * nilfs_palloc_groups_count - get maximum number of groups
  * @inode: inode of metadata file using this allocator
+ *
+ * Return: Maximum number of groups.
  */
 static inline unsigned long
 nilfs_palloc_groups_count(const struct inode *inode)
@@ -43,6 +47,8 @@ nilfs_palloc_groups_count(const struct inode *inode)
  * nilfs_palloc_init_blockgroup - initialize private variables for allocator
  * @inode: inode of metadata file using this allocator
  * @entry_size: size of the persistent object
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned int entry_size)
 {
@@ -78,6 +84,9 @@ int nilfs_palloc_init_blockgroup(struct inode *inode, unsigned int entry_size)
  * @inode: inode of metadata file using this allocator
  * @nr: serial number of the entry (e.g. inode number)
  * @offset: pointer to store offset number in the group
+ *
+ * Return: Number of the group that contains the entry with the index
+ * specified by @nr.
  */
 static unsigned long nilfs_palloc_group(const struct inode *inode, __u64 nr,
 					unsigned long *offset)
@@ -93,8 +102,8 @@ static unsigned long nilfs_palloc_group(const struct inode *inode, __u64 nr,
  * @inode: inode of metadata file using this allocator
  * @group: group number
  *
- * nilfs_palloc_desc_blkoff() returns block offset of the descriptor
- * block which contains a descriptor of the specified group.
+ * Return: Index number in the metadata file of the descriptor block of
+ * the group specified by @group.
  */
 static unsigned long
 nilfs_palloc_desc_blkoff(const struct inode *inode, unsigned long group)
@@ -111,6 +120,9 @@ nilfs_palloc_desc_blkoff(const struct inode *inode, unsigned long group)
  *
  * nilfs_palloc_bitmap_blkoff() returns block offset of the bitmap
  * block used to allocate/deallocate entries in the specified group.
+ *
+ * Return: Index number in the metadata file of the bitmap block of
+ * the group specified by @group.
  */
 static unsigned long
 nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group)
@@ -125,6 +137,8 @@ nilfs_palloc_bitmap_blkoff(const struct inode *inode, unsigned long group)
  * nilfs_palloc_group_desc_nfrees - get the number of free entries in a group
  * @desc: pointer to descriptor structure for the group
  * @lock: spin lock protecting @desc
+ *
+ * Return: Number of free entries written in the group descriptor @desc.
  */
 static unsigned long
 nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc,
@@ -143,6 +157,9 @@ nilfs_palloc_group_desc_nfrees(const struct nilfs_palloc_group_desc *desc,
  * @desc: pointer to descriptor structure for the group
  * @lock: spin lock protecting @desc
  * @n: delta to be added
+ *
+ * Return: Number of free entries after adjusting the group descriptor
+ * @desc.
  */
 static u32
 nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc,
@@ -161,6 +178,9 @@ nilfs_palloc_group_desc_add_entries(struct nilfs_palloc_group_desc *desc,
  * nilfs_palloc_entry_blkoff - get block offset of an entry block
  * @inode: inode of metadata file using this allocator
  * @nr: serial number of the entry (e.g. inode number)
+ *
+ * Return: Index number in the metadata file of the block containing
+ * the entry specified by @nr.
  */
 static unsigned long
 nilfs_palloc_entry_blkoff(const struct inode *inode, __u64 nr)
@@ -238,6 +258,12 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff,
  * @blkoff: block offset
  * @prev: nilfs_bh_assoc struct of the last used buffer
  * @lock: spin lock protecting @prev
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- Non-existent block.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff,
 				     struct nilfs_bh_assoc *prev,
@@ -258,6 +284,8 @@ static int nilfs_palloc_delete_block(struct inode *inode, unsigned long blkoff,
  * @group: group number
  * @create: create flag
  * @bhp: pointer to store the resultant buffer head
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_palloc_get_desc_block(struct inode *inode,
 				       unsigned long group,
@@ -277,6 +305,8 @@ static int nilfs_palloc_get_desc_block(struct inode *inode,
  * @group: group number
  * @create: create flag
  * @bhp: pointer to store the resultant buffer head
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_palloc_get_bitmap_block(struct inode *inode,
 					 unsigned long group,
@@ -294,6 +324,8 @@ static int nilfs_palloc_get_bitmap_block(struct inode *inode,
  * nilfs_palloc_delete_bitmap_block - delete a bitmap block
  * @inode: inode of metadata file using this allocator
  * @group: group number
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_palloc_delete_bitmap_block(struct inode *inode,
 					    unsigned long group)
@@ -312,6 +344,8 @@ static int nilfs_palloc_delete_bitmap_block(struct inode *inode,
  * @nr: serial number of the entry (e.g. inode number)
  * @create: create flag
  * @bhp: pointer to store the resultant buffer head
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr,
 				 int create, struct buffer_head **bhp)
@@ -328,6 +362,8 @@ int nilfs_palloc_get_entry_block(struct inode *inode, __u64 nr,
  * nilfs_palloc_delete_entry_block - delete an entry block
  * @inode: inode of metadata file using this allocator
  * @nr: serial number of the entry
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_palloc_delete_entry_block(struct inode *inode, __u64 nr)
 {
@@ -397,6 +433,9 @@ size_t nilfs_palloc_entry_offset(const struct inode *inode, __u64 nr,
  * @bsize: size in bits
  * @lock: spin lock protecting @bitmap
  * @wrap: whether to wrap around
+ *
+ * Return: Offset number within the group of the found free entry, or
+ * %-ENOSPC if not found.
  */
 static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
 					    unsigned long target,
@@ -438,6 +477,9 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
  * @inode: inode of metadata file using this allocator
  * @curr: current group number
  * @max: maximum number of groups
+ *
+ * Return: Number of remaining descriptors (= groups) managed by the descriptor
+ * block.
  */
 static unsigned long
 nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode,
@@ -453,6 +495,8 @@ nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode,
  * nilfs_palloc_count_desc_blocks - count descriptor blocks number
  * @inode: inode of metadata file using this allocator
  * @desc_blocks: descriptor blocks number [out]
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_palloc_count_desc_blocks(struct inode *inode,
 					    unsigned long *desc_blocks)
@@ -473,6 +517,8 @@ static int nilfs_palloc_count_desc_blocks(struct inode *inode,
  *					MDT file growing
  * @inode: inode of metadata file using this allocator
  * @desc_blocks: known current descriptor blocks count
+ *
+ * Return: true if a group can be added in the metadata file, false if not.
  */
 static inline bool nilfs_palloc_mdt_file_can_grow(struct inode *inode,
 						    unsigned long desc_blocks)
@@ -487,6 +533,12 @@ static inline bool nilfs_palloc_mdt_file_can_grow(struct inode *inode,
  * @inode: inode of metadata file using this allocator
  * @nused: current number of used entries
  * @nmaxp: max number of entries [out]
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ERANGE	- Number of entries in use is out of range.
  */
 int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
 {
@@ -518,6 +570,13 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
  * @inode: inode of metadata file using this allocator
  * @req: nilfs_palloc_req structure exchanged for the allocation
  * @wrap: whether to wrap around
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ENOSPC	- Entries exhausted (No entries available for allocation).
+ * * %-EROFS	- Read only filesystem
  */
 int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
 				     struct nilfs_palloc_req *req, bool wrap)
@@ -710,6 +769,8 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
  * nilfs_palloc_prepare_free_entry - prepare to deallocate a persistent object
  * @inode: inode of metadata file using this allocator
  * @req: nilfs_palloc_req structure exchanged for the removal
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_palloc_prepare_free_entry(struct inode *inode,
 				    struct nilfs_palloc_req *req)
@@ -754,6 +815,8 @@ void nilfs_palloc_abort_free_entry(struct inode *inode,
  * @inode: inode of metadata file using this allocator
  * @entry_nrs: array of entry numbers to be deallocated
  * @nitems: number of entries stored in @entry_nrs
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
 {
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index 3f115ab7e9a7..046d876ea3e0 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -21,6 +21,8 @@
  *
  * The number of entries per group is defined by the number of bits
  * that a bitmap block can maintain.
+ *
+ * Return: Number of entries per group.
  */
 static inline unsigned long
 nilfs_palloc_entries_per_group(const struct inode *inode)
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index c9e8d9a7d820..ccc1a7aa52d2 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -47,17 +47,14 @@ static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap,
  * @ptrp: place to store the value associated to @key
  *
  * Description: nilfs_bmap_lookup_at_level() finds a record whose key
- * matches @key in the block at @level of the bmap.
- *
- * Return Value: On success, 0 is returned and the record associated with @key
- * is stored in the place pointed by @ptrp. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - A record associated with @key does not exist.
+ * matches @key in the block at @level of the bmap.  The record associated
+ * with @key is stored in the place pointed to by @ptrp.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- A record associated with @key does not exist.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level,
 			       __u64 *ptrp)
@@ -138,14 +135,11 @@ static int nilfs_bmap_do_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr)
  * Description: nilfs_bmap_insert() inserts the new key-record pair specified
  * by @key and @rec into @bmap.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EEXIST - A record associated with @key already exist.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EEXIST	- A record associated with @key already exists.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec)
 {
@@ -193,14 +187,11 @@ static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key)
  * Description: nilfs_bmap_seek_key() seeks a valid key on @bmap
  * starting from @start, and stores it to @keyp if found.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - No valid entry was found
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- No valid entry was found.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp)
 {
@@ -236,14 +227,11 @@ int nilfs_bmap_last_key(struct nilfs_bmap *bmap, __u64 *keyp)
  * Description: nilfs_bmap_delete() deletes the key-record pair specified by
  * @key from @bmap.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - A record associated with @key does not exist.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- A record associated with @key does not exist.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key)
 {
@@ -290,12 +278,10 @@ static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, __u64 key)
  * Description: nilfs_bmap_truncate() removes key-record pairs whose keys are
  * greater than or equal to @key from @bmap.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_truncate(struct nilfs_bmap *bmap, __u64 key)
 {
@@ -330,12 +316,10 @@ void nilfs_bmap_clear(struct nilfs_bmap *bmap)
  * Description: nilfs_bmap_propagate() marks the buffers that directly or
  * indirectly refer to the block specified by @bh dirty.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_propagate(struct nilfs_bmap *bmap, struct buffer_head *bh)
 {
@@ -362,22 +346,22 @@ void nilfs_bmap_lookup_dirty_buffers(struct nilfs_bmap *bmap,
 
 /**
  * nilfs_bmap_assign - assign a new block number to a block
- * @bmap: bmap
- * @bh: pointer to buffer head
+ * @bmap:    bmap
+ * @bh:      place to store a pointer to the buffer head to which a block
+ *           address is assigned (in/out)
  * @blocknr: block number
- * @binfo: block information
+ * @binfo:   block information
  *
  * Description: nilfs_bmap_assign() assigns the block number @blocknr to the
- * buffer specified by @bh.
- *
- * Return Value: On success, 0 is returned and the buffer head of a newly
- * create buffer and the block information associated with the buffer are
- * stored in the place pointed by @bh and @binfo, respectively. On error, one
- * of the following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * buffer specified by @bh.  The block information is stored in the memory
+ * pointed to by @binfo, and the buffer head may be replaced as a block
+ * address is assigned, in which case a pointer to the new buffer head is
+ * stored in the memory pointed to by @bh.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_assign(struct nilfs_bmap *bmap,
 		      struct buffer_head **bh,
@@ -402,12 +386,10 @@ int nilfs_bmap_assign(struct nilfs_bmap *bmap,
  * Description: nilfs_bmap_mark() marks the block specified by @key and @level
  * as dirty.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_mark(struct nilfs_bmap *bmap, __u64 key, int level)
 {
@@ -430,7 +412,7 @@ int nilfs_bmap_mark(struct nilfs_bmap *bmap, __u64 key, int level)
  * Description: nilfs_test_and_clear() is the atomic operation to test and
  * clear the dirty state of @bmap.
  *
- * Return Value: 1 is returned if @bmap is dirty, or 0 if clear.
+ * Return: 1 if @bmap is dirty, or 0 if clear.
  */
 int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *bmap)
 {
@@ -490,10 +472,10 @@ static struct lock_class_key nilfs_bmap_mdt_lock_key;
  *
  * Description: nilfs_bmap_read() initializes the bmap @bmap.
  *
- * Return Value: On success, 0 is returned. On error, the following negative
- * error code is returned.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (corrupted bmap).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode)
 {
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 54a3fa0cf67e..568367129092 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -201,7 +201,8 @@ void nilfs_btnode_delete(struct buffer_head *bh)
  * Note that the current implementation does not support folio sizes larger
  * than the page size.
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EIO	- I/O error (metadata corruption).
  * * %-ENOMEM	- Insufficient memory available.
  */
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index ef5061bb56da..0d8f7fb15c2e 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -334,7 +334,7 @@ static int nilfs_btree_node_lookup(const struct nilfs_btree_node *node,
  * @inode: host inode of btree
  * @blocknr: block number
  *
- * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ * Return: 0 if normal, 1 if the node is broken.
  */
 static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
 				   size_t size, struct inode *inode,
@@ -366,7 +366,7 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
  * @node: btree root node to be examined
  * @inode: host inode of btree
  *
- * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ * Return: 0 if normal, 1 if the root node is broken.
  */
 static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
 				   struct inode *inode)
@@ -652,8 +652,7 @@ static int nilfs_btree_do_lookup_last(const struct nilfs_bmap *btree,
  * @minlevel: start level
  * @nextkey: place to store the next valid key
  *
- * Return Value: If a next key was found, 0 is returned. Otherwise,
- * -ENOENT is returned.
+ * Return: 0 if the next key was found, %-ENOENT if not found.
  */
 static int nilfs_btree_get_next_key(const struct nilfs_bmap *btree,
 				    const struct nilfs_btree_path *path,
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index c20207d7a989..bcc7d76269ac 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -191,14 +191,11 @@ static inline int nilfs_cpfile_get_checkpoint_block(struct inode *cpfile,
  * @cnop: place to store the next checkpoint number
  * @bhp: place to store a pointer to buffer_head struct
  *
- * Return Value: On success, it returns 0. On error, the following negative
- * error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EIO - I/O error
- *
- * %-ENOENT - no block exists in the range.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- no block exists in the range.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_cpfile_find_checkpoint_block(struct inode *cpfile,
 					      __u64 start_cno, __u64 end_cno,
@@ -239,7 +236,8 @@ static inline int nilfs_cpfile_delete_checkpoint_block(struct inode *cpfile,
  * stores it to the inode file given by @ifile and the nilfs root object
  * given by @root.
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EINVAL	- Invalid checkpoint.
  * * %-ENOMEM	- Insufficient memory available.
  * * %-EIO	- I/O error (including metadata corruption).
@@ -307,7 +305,8 @@ out_sem:
  * In either case, the buffer of the block containing the checkpoint entry
  * and the cpfile inode are made dirty for inclusion in the write log.
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-ENOMEM	- Insufficient memory available.
  * * %-EIO	- I/O error (including metadata corruption).
  * * %-EROFS	- Read only filesystem
@@ -376,7 +375,8 @@ out_sem:
  * cpfile with the data given by the arguments @root, @blkinc, @ctime, and
  * @minor.
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-ENOMEM	- Insufficient memory available.
  * * %-EIO	- I/O error (including metadata corruption).
  */
@@ -447,14 +447,11 @@ error:
  * the period from @start to @end, excluding @end itself. The checkpoints
  * which have been already deleted are ignored.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - invalid checkpoints.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Invalid checkpoints.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
 				    __u64 start,
@@ -718,7 +715,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
  * number to continue searching.
  *
  * Return: Count of checkpoint info items stored in the output buffer on
- * success, or the following negative error code on failure.
+ * success, or one of the following negative error codes on failure:
  * * %-EINVAL	- Invalid checkpoint mode.
  * * %-ENOMEM	- Insufficient memory available.
  * * %-EIO	- I/O error (including metadata corruption).
@@ -743,7 +740,8 @@ ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode,
  * @cpfile: checkpoint file inode
  * @cno:    checkpoint number to delete
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EBUSY	- Checkpoint in use (snapshot specified).
  * * %-EIO	- I/O error (including metadata corruption).
  * * %-ENOENT	- No valid checkpoint found.
@@ -1011,7 +1009,7 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
  * @cno:    checkpoint number
  *
  * Return: 1 if the checkpoint specified by @cno is a snapshot, 0 if not, or
- * the following negative error code on failure.
+ * one of the following negative error codes on failure:
  * * %-EIO	- I/O error (including metadata corruption).
  * * %-ENOENT	- No such checkpoint.
  * * %-ENOMEM	- Insufficient memory available.
@@ -1058,14 +1056,11 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
  * Description: nilfs_change_cpmode() changes the mode of the checkpoint
  * specified by @cno. The mode @mode is NILFS_CHECKPOINT or NILFS_SNAPSHOT.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - No such checkpoint.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- No such checkpoint.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_cpfile_change_cpmode(struct inode *cpfile, __u64 cno, int mode)
 {
@@ -1097,14 +1092,12 @@ int nilfs_cpfile_change_cpmode(struct inode *cpfile, __u64 cno, int mode)
  * @cpstat: pointer to a structure of checkpoint statistics
  *
  * Description: nilfs_cpfile_get_stat() returns information about checkpoints.
+ * The checkpoint statistics are stored in the location pointed to by @cpstat.
  *
- * Return Value: On success, 0 is returned, and checkpoints information is
- * stored in the place pointed by @cpstat. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat)
 {
@@ -1135,6 +1128,8 @@ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat)
  * @cpsize: size of a checkpoint entry
  * @raw_inode: on-disk cpfile inode
  * @inodep: buffer to store the inode
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
 		      struct nilfs_inode *raw_inode, struct inode **inodep)
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index e220dcb08aa6..c664daba56ae 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -276,7 +276,8 @@ void nilfs_dat_abort_update(struct inode *dat,
  * @dat:      DAT file inode
  * @vblocknr: virtual block number
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EINVAL	- Invalid DAT entry (internal code).
  * * %-EIO	- I/O error (including metadata corruption).
  * * %-ENOMEM	- Insufficient memory available.
@@ -302,14 +303,11 @@ int nilfs_dat_mark_dirty(struct inode *dat, __u64 vblocknr)
  * Description: nilfs_dat_freev() frees the virtual block numbers specified by
  * @vblocknrs and @nitems.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - The virtual block number have not been allocated.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- The virtual block number have not been allocated.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_dat_freev(struct inode *dat, __u64 *vblocknrs, size_t nitems)
 {
@@ -325,12 +323,10 @@ int nilfs_dat_freev(struct inode *dat, __u64 *vblocknrs, size_t nitems)
  * Description: nilfs_dat_move() changes the block number associated with
  * @vblocknr to @blocknr.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
 {
@@ -390,17 +386,14 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
  * @blocknrp: pointer to a block number
  *
  * Description: nilfs_dat_translate() maps the virtual block number @vblocknr
- * to the corresponding block number.
- *
- * Return Value: On success, 0 is returned and the block number associated
- * with @vblocknr is stored in the place pointed by @blocknrp. On error, one
- * of the following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * to the corresponding block number.  The block number associated with
+ * @vblocknr is stored in the place pointed to by @blocknrp.
  *
- * %-ENOENT - A block number associated with @vblocknr does not exist.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- A block number associated with @vblocknr does not exist.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
 {
@@ -489,6 +482,8 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz,
  * @entry_size: size of a dat entry
  * @raw_inode: on-disk dat inode
  * @inodep: buffer to store the inode
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_dat_read(struct super_block *sb, size_t entry_size,
 		   struct nilfs_inode *raw_inode, struct inode **inodep)
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 0a3aea6c416b..9b7f8e9655a2 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -400,7 +400,7 @@ int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino)
 	return 0;
 }
 
-void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
+int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
 		    struct folio *folio, struct inode *inode)
 {
 	size_t from = offset_in_folio(folio, de);
@@ -410,11 +410,15 @@ void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
 
 	folio_lock(folio);
 	err = nilfs_prepare_chunk(folio, from, to);
-	BUG_ON(err);
+	if (unlikely(err)) {
+		folio_unlock(folio);
+		return err;
+	}
 	de->inode = cpu_to_le64(inode->i_ino);
 	de->file_type = fs_umode_to_ftype(inode->i_mode);
 	nilfs_commit_chunk(folio, mapping, from, to);
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
+	return 0;
 }
 
 /*
@@ -543,7 +547,10 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct folio *folio)
 		from = (char *)pde - kaddr;
 	folio_lock(folio);
 	err = nilfs_prepare_chunk(folio, from, to);
-	BUG_ON(err);
+	if (unlikely(err)) {
+		folio_unlock(folio);
+		goto out;
+	}
 	if (pde)
 		pde->rec_len = nilfs_rec_len_to_disk(to - from);
 	dir->inode = 0;
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 2dbb15767df1..561c220799c7 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -46,14 +46,11 @@
  * specified by @pbn to the GC pagecache with the key @blkoff.
  * This function sets @vbn (@pbn if @vbn is zero) in b_blocknr of the buffer.
  *
- * Return Value: On success, 0 is returned. On Error, one of the following
- * negative error code is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - The block specified with @pbn does not exist.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- The block specified with @pbn does not exist.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
 				   sector_t pbn, __u64 vbn,
@@ -114,12 +111,11 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
  * specified by @vbn to the GC pagecache.  @pbn can be supplied by the
  * caller to avoid translation of the disk block address.
  *
- * Return Value: On success, 0 is returned. On Error, one of the following
- * negative error code is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- Invalid virtual block address.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn,
 				   __u64 vbn, struct buffer_head **out_bh)
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index e7339eb3c08a..c4cd4a4dedd0 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -38,17 +38,16 @@ static inline struct nilfs_ifile_info *NILFS_IFILE_I(struct inode *ifile)
  * @out_ino: pointer to a variable to store inode number
  * @out_bh: buffer_head contains newly allocated disk inode
  *
- * Return Value: On success, 0 is returned and the newly allocated inode
- * number is stored in the place pointed by @ino, and buffer_head pointer
- * that contains newly allocated disk inode structure is stored in the
- * place pointed by @out_bh
- * On error, one of the following negative error codes is returned.
+ * nilfs_ifile_create_inode() allocates a new inode in the ifile metadata
+ * file and stores the inode number in the variable pointed to by @out_ino,
+ * as well as storing the ifile's buffer with the disk inode in the location
+ * pointed to by @out_bh.
  *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOSPC - No inode left.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ENOSPC	- No inode left.
  */
 int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
 			     struct buffer_head **out_bh)
@@ -83,14 +82,11 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
  * @ifile: ifile inode
  * @ino: inode number
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - The inode number @ino have not been allocated.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- Inode number unallocated.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_ifile_delete_inode(struct inode *ifile, ino_t ino)
 {
@@ -150,6 +146,8 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino,
  * @ifile: ifile inode
  * @nmaxinodes: current maximum of available inodes count [out]
  * @nfreeinodes: free inodes count [out]
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_ifile_count_free_inodes(struct inode *ifile,
 				    u64 *nmaxinodes, u64 *nfreeinodes)
@@ -174,7 +172,8 @@ int nilfs_ifile_count_free_inodes(struct inode *ifile,
  * @cno: number of checkpoint entry to read
  * @inode_size: size of an inode
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EINVAL	- Invalid checkpoint.
  * * %-ENOMEM	- Insufficient memory available.
  * * %-EIO	- I/O error (including metadata corruption).
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 23f3a75edd50..6613b8fcceb0 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -68,6 +68,8 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
  *
  * This function does not issue actual read request of the specified data
  * block. It is done by VFS.
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_get_block(struct inode *inode, sector_t blkoff,
 		    struct buffer_head *bh_result, int create)
@@ -141,6 +143,8 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff,
  * address_space_operations.
  * @file: file struct of the file to be read
  * @folio: the folio to be read
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_read_folio(struct file *file, struct folio *folio)
 {
@@ -598,10 +602,7 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
  * or does nothing if the inode already has it.  This function allocates
  * an additional inode to maintain page cache of B-tree nodes one-on-one.
  *
- * Return Value: On success, 0 is returned. On errors, one of the following
- * negative error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: 0 on success, or %-ENOMEM if memory is insufficient.
  */
 int nilfs_attach_btree_node_cache(struct inode *inode)
 {
@@ -660,11 +661,8 @@ void nilfs_detach_btree_node_cache(struct inode *inode)
  * in one inode and the one for b-tree node pages is set up in the
  * other inode, which is attached to the former inode.
  *
- * Return Value: On success, a pointer to the inode for data pages is
- * returned. On errors, one of the following negative error code is returned
- * in a pointer type.
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: a pointer to the inode for data pages on success, or %-ENOMEM
+ * if memory is insufficient.
  */
 struct inode *nilfs_iget_for_shadow(struct inode *inode)
 {
@@ -1188,7 +1186,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			if (size) {
 				if (phys && blkphy << blkbits == phys + size) {
 					/* The current extent goes on */
-					size += n << blkbits;
+					size += (u64)n << blkbits;
 				} else {
 					/* Terminate the current extent */
 					ret = fiemap_fill_next_extent(
@@ -1201,14 +1199,14 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 					flags = FIEMAP_EXTENT_MERGED;
 					logical = blkoff << blkbits;
 					phys = blkphy << blkbits;
-					size = n << blkbits;
+					size = (u64)n << blkbits;
 				}
 			} else {
 				/* Start a new extent */
 				flags = FIEMAP_EXTENT_MERGED;
 				logical = blkoff << blkbits;
 				phys = blkphy << blkbits;
-				size = n << blkbits;
+				size = (u64)n << blkbits;
 			}
 			blkoff += n;
 		}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index fa77f78df681..a66d62a51f77 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -33,17 +33,14 @@
  * @dofunc: concrete function of get/set metadata info
  *
  * Description: nilfs_ioctl_wrap_copy() gets/sets metadata info by means of
- * calling dofunc() function on the basis of @argv argument.
- *
- * Return Value: On success, 0 is returned and requested metadata info
- * is copied into userspace. On error, one of the following
- * negative error codes is returned.
- *
- * %-EINVAL - Invalid arguments from userspace.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EFAULT - Failure during execution of requested operation.
+ * calling dofunc() function on the basis of @argv argument.  If successful,
+ * the requested metadata information is copied to userspace memory.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EFAULT	- Failure during execution of requested operation.
+ * * %-EINVAL	- Invalid arguments from userspace.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
 				 struct nilfs_argv *argv, int dir,
@@ -190,13 +187,10 @@ static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp)
  * given checkpoint between checkpoint and snapshot state. This ioctl
  * is used in chcp and mkcp utilities.
  *
- * Return Value: On success, 0 is returned and mode of a checkpoint is
- * changed. On error, one of the following negative error codes
- * is returned.
- *
- * %-EPERM - Operation not permitted.
- *
- * %-EFAULT - Failure during checkpoint mode changing.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * %-EFAULT	- Failure during checkpoint mode changing.
+ * %-EPERM	- Operation not permitted.
  */
 static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
 				     unsigned int cmd, void __user *argp)
@@ -244,13 +238,10 @@ out:
  * checkpoint from NILFS2 file system. This ioctl is used in rmcp
  * utility.
  *
- * Return Value: On success, 0 is returned and a checkpoint is
- * removed. On error, one of the following negative error codes
- * is returned.
- *
- * %-EPERM - Operation not permitted.
- *
- * %-EFAULT - Failure during checkpoint removing.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * %-EFAULT	- Failure during checkpoint removing.
+ * %-EPERM	- Operation not permitted.
  */
 static int
 nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp,
@@ -296,7 +287,7 @@ out:
  * requested checkpoints. The NILFS_IOCTL_GET_CPINFO ioctl is used in
  * lscp utility and by nilfs_cleanerd daemon.
  *
- * Return value: count of nilfs_cpinfo structures in output buffer.
+ * Return: Count of nilfs_cpinfo structures in output buffer.
  */
 static ssize_t
 nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
@@ -320,17 +311,14 @@ nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
  *
  * Description: nilfs_ioctl_get_cpstat() returns information about checkpoints.
  * The NILFS_IOCTL_GET_CPSTAT ioctl is used by lscp, rmcp utilities
- * and by nilfs_cleanerd daemon.
+ * and by nilfs_cleanerd daemon.  The checkpoint statistics are copied to
+ * the userspace memory pointed to by @argp.
  *
- * Return Value: On success, 0 is returned, and checkpoints information is
- * copied into userspace pointer @argp. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EFAULT - Failure during getting checkpoints statistics.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EFAULT	- Failure during getting checkpoints statistics.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp,
 				  unsigned int cmd, void __user *argp)
@@ -363,7 +351,8 @@ static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp,
  * info about requested segments. The NILFS_IOCTL_GET_SUINFO ioctl is used
  * in lssu, nilfs_resize utilities and by nilfs_cleanerd daemon.
  *
- * Return value: count of nilfs_suinfo structures in output buffer.
+ * Return: Count of nilfs_suinfo structures in output buffer on success,
+ * or a negative error code on failure.
  */
 static ssize_t
 nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
@@ -387,17 +376,14 @@ nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
  *
  * Description: nilfs_ioctl_get_sustat() returns segment usage statistics.
  * The NILFS_IOCTL_GET_SUSTAT ioctl is used in lssu, nilfs_resize utilities
- * and by nilfs_cleanerd daemon.
- *
- * Return Value: On success, 0 is returned, and segment usage information is
- * copied into userspace pointer @argp. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * and by nilfs_cleanerd daemon.  The requested segment usage information is
+ * copied to the userspace memory pointed to by @argp.
  *
- * %-EFAULT - Failure during getting segment usage statistics.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EFAULT	- Failure during getting segment usage statistics.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp,
 				  unsigned int cmd, void __user *argp)
@@ -430,7 +416,8 @@ static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp,
  * on virtual block addresses. The NILFS_IOCTL_GET_VINFO ioctl is used
  * by nilfs_cleanerd daemon.
  *
- * Return value: count of nilfs_vinfo structures in output buffer.
+ * Return: Count of nilfs_vinfo structures in output buffer on success, or
+ * a negative error code on failure.
  */
 static ssize_t
 nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
@@ -457,7 +444,8 @@ nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
  * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl
  * is used by nilfs_cleanerd daemon.
  *
- * Return value: count of nilfs_bdescs structures in output buffer.
+ * Return: Count of nilfs_bdescs structures in output buffer on success, or
+ * a negative error code on failure.
  */
 static ssize_t
 nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
@@ -494,19 +482,15 @@ nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
  *
  * Description: nilfs_ioctl_do_get_bdescs() function returns information
  * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl
- * is used by nilfs_cleanerd daemon.
- *
- * Return Value: On success, 0 is returned, and disk block descriptors are
- * copied into userspace pointer @argp. On error, one of the following
- * negative error codes is returned.
- *
- * %-EINVAL - Invalid arguments from userspace.
+ * is used by nilfs_cleanerd daemon.  If successful, disk block descriptors
+ * are copied to userspace pointer @argp.
  *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EFAULT - Failure during getting disk block descriptors.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EFAULT	- Failure during getting disk block descriptors.
+ * * %-EINVAL	- Invalid arguments from userspace.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp,
 				  unsigned int cmd, void __user *argp)
@@ -540,16 +524,12 @@ static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp,
  * Description: nilfs_ioctl_move_inode_block() function registers data/node
  * buffer in the GC pagecache and submit read request.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - Requested block doesn't exist.
- *
- * %-EEXIST - Blocks conflict is detected.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EEXIST	- Block conflict detected.
+ * * %-EIO	- I/O error.
+ * * %-ENOENT	- Requested block doesn't exist.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_move_inode_block(struct inode *inode,
 					struct nilfs_vdesc *vdesc,
@@ -604,8 +584,8 @@ static int nilfs_ioctl_move_inode_block(struct inode *inode,
  * blocks that garbage collector specified with the array of nilfs_vdesc
  * structures and stores them into page caches of GC inodes.
  *
- * Return Value: Number of processed nilfs_vdesc structures or
- * error code, otherwise.
+ * Return: Number of processed nilfs_vdesc structures on success, or
+ * a negative error code on failure.
  */
 static int nilfs_ioctl_move_blocks(struct super_block *sb,
 				   struct nilfs_argv *argv, void *buf)
@@ -682,14 +662,11 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
  * in the period from p_start to p_end, excluding p_end itself. The checkpoints
  * which have been already deleted are ignored.
  *
- * Return Value: Number of processed nilfs_period structures or
- * error code, otherwise.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - invalid checkpoints.
+ * Return: Number of processed nilfs_period structures on success, or one of
+ * the following negative error codes on failure:
+ * * %-EINVAL	- invalid checkpoints.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs,
 					  struct nilfs_argv *argv, void *buf)
@@ -717,14 +694,11 @@ static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs,
  * Description: nilfs_ioctl_free_vblocknrs() function frees
  * the virtual block numbers specified by @buf and @argv->v_nmembs.
  *
- * Return Value: Number of processed virtual block numbers or
- * error code, otherwise.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - The virtual block number have not been allocated.
+ * Return: Number of processed virtual block numbers on success, or one of the
+ * following negative error codes on failure:
+ * * %-EIO	- I/O error.
+ * * %-ENOENT	- Unallocated virtual block number.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs,
 				      struct nilfs_argv *argv, void *buf)
@@ -746,14 +720,11 @@ static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs,
  * Description: nilfs_ioctl_mark_blocks_dirty() function marks
  * metadata file or data blocks as dirty.
  *
- * Return Value: Number of processed block descriptors or
- * error code, otherwise.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EIO - I/O error
- *
- * %-ENOENT - the specified block does not exist (hole block)
+ * Return: Number of processed block descriptors on success, or one of the
+ * following negative error codes on failure:
+ * * %-EIO	- I/O error.
+ * * %-ENOENT	- Non-existent block (hole block).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
 					 struct nilfs_argv *argv, void *buf)
@@ -852,7 +823,7 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs,
  * from userspace. The NILFS_IOCTL_CLEAN_SEGMENTS ioctl is used by
  * nilfs_cleanerd daemon.
  *
- * Return Value: On success, 0 is returned or error code, otherwise.
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
 				      unsigned int cmd, void __user *argp)
@@ -976,20 +947,14 @@ out:
  * and metadata are written out to the device when it successfully
  * returned.
  *
- * Return Value: On success, 0 is retured. On errors, one of the following
- * negative error code is returned.
- *
- * %-EROFS - Read only filesystem.
- *
- * %-EIO - I/O error
- *
- * %-ENOSPC - No space left on device (only in a panic state).
- *
- * %-ERESTARTSYS - Interrupted.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EFAULT - Failure during execution of requested operation.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EFAULT		- Failure during execution of requested operation.
+ * * %-EIO		- I/O error.
+ * * %-ENOMEM		- Insufficient memory available.
+ * * %-ENOSPC		- No space left on device (only in a panic state).
+ * * %-ERESTARTSYS	- Interrupted.
+ * * %-EROFS		- Read only filesystem.
  */
 static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
 			    unsigned int cmd, void __user *argp)
@@ -1023,7 +988,7 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
  * @filp: file object
  * @argp: pointer on argument from userspace
  *
- * Return Value: On success, 0 is returned or error code, otherwise.
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_ioctl_resize(struct inode *inode, struct file *filp,
 			      void __user *argp)
@@ -1059,7 +1024,7 @@ out:
  * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
  * performs the actual trim operation.
  *
- * Return Value: On success, 0 is returned or negative error code, otherwise.
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
 {
@@ -1101,7 +1066,7 @@ static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
  * of segments in bytes and upper limit of segments in bytes.
  * The NILFS_IOCTL_SET_ALLOC_RANGE is used by nilfs_resize utility.
  *
- * Return Value: On success, 0 is returned or error code, otherwise.
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
 {
@@ -1152,17 +1117,15 @@ out:
  * @dofunc: concrete function of getting metadata info
  *
  * Description: nilfs_ioctl_get_info() gets metadata info by means of
- * calling dofunc() function.
+ * calling dofunc() function.  The requested metadata information is copied
+ * to userspace memory @argp.
  *
- * Return Value: On success, 0 is returned and requested metadata info
- * is copied into userspace. On error, one of the following
- * negative error codes is returned.
- *
- * %-EINVAL - Invalid arguments from userspace.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EFAULT - Failure during execution of requested operation.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EFAULT	- Failure during execution of requested operation.
+ * * %-EINVAL	- Invalid arguments from userspace.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
 				unsigned int cmd, void __user *argp,
@@ -1202,18 +1165,14 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
  * encapsulated in nilfs_argv and updates the segment usage info
  * according to the flags in nilfs_suinfo_update.
  *
- * Return Value: On success, 0 is returned. On error, one of the
- * following negative error codes is returned.
- *
- * %-EPERM - Not enough permissions
- *
- * %-EFAULT - Error copying input data
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EEXIST	- Block conflict detected.
+ * * %-EFAULT	- Error copying input data.
+ * * %-EINVAL	- Invalid values in input (segment number, flags or nblocks).
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-EPERM	- Not enough permissions.
  */
 static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
 				unsigned int cmd, void __user *argp)
@@ -1309,7 +1268,8 @@ static int nilfs_ioctl_get_fslabel(struct super_block *sb, void __user *argp)
  * @filp: file object
  * @argp: pointer to userspace memory that contains the volume name
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EFAULT	- Error copying input data.
  * * %-EINVAL	- Label length exceeds record size in superblock.
  * * %-EIO	- I/O error.
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 965b5ad1c0df..2f850a18d6e7 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -226,20 +226,21 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
  * @out_bh: output of a pointer to the buffer_head
  *
  * nilfs_mdt_get_block() looks up the specified buffer and tries to create
- * a new buffer if @create is not zero.  On success, the returned buffer is
- * assured to be either existing or formatted using a buffer lock on success.
- * @out_bh is substituted only when zero is returned.
+ * a new buffer if @create is not zero.  If (and only if) this function
+ * succeeds, it stores a pointer to the retrieved buffer head in the location
+ * pointed to by @out_bh.
  *
- * Return Value: On success, it returns 0. On error, the following negative
- * error code is returned.
+ * The retrieved buffer may be either an existing one or a newly allocated one.
+ * For a newly created buffer, if the callback function argument @init_block
+ * is non-NULL, the callback will be called with the buffer locked to format
+ * the block.
  *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EIO - I/O error
- *
- * %-ENOENT - the specified block does not exist (hole block)
- *
- * %-EROFS - Read only filesystem (for create mode)
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- The specified block does not exist (hole block).
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-EROFS	- Read only filesystem (for create mode).
  */
 int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create,
 			void (*init_block)(struct inode *,
@@ -275,14 +276,11 @@ int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create,
  * @out_bh, and block offset to @blkoff, respectively.  @out_bh and
  * @blkoff are substituted only when zero is returned.
  *
- * Return Value: On success, it returns 0. On error, the following negative
- * error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EIO - I/O error
- *
- * %-ENOENT - no block was found in the range
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- No block was found in the range.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_mdt_find_block(struct inode *inode, unsigned long start,
 			 unsigned long end, unsigned long *blkoff,
@@ -321,12 +319,11 @@ out:
  * @inode: inode of the meta data file
  * @block: block offset
  *
- * Return Value: On success, zero is returned.
- * On error, one of the following negative error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-EIO - I/O error
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- Non-existent block.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_mdt_delete_block(struct inode *inode, unsigned long block)
 {
@@ -349,12 +346,10 @@ int nilfs_mdt_delete_block(struct inode *inode, unsigned long block)
  * nilfs_mdt_forget_block() clears a dirty flag of the specified buffer, and
  * tries to release the page including the buffer from a page cache.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error code is returned.
- *
- * %-EBUSY - page has an active buffer.
- *
- * %-ENOENT - page cache has no page addressed by the offset.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EBUSY	- Page has an active buffer.
+ * * %-ENOENT	- Page cache has no page addressed by the offset.
  */
 int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
 {
@@ -524,6 +519,8 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size,
  * nilfs_mdt_setup_shadow_map - setup shadow map and bind it to metadata file
  * @inode: inode of the metadata file
  * @shadow: shadow mapping
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_mdt_setup_shadow_map(struct inode *inode,
 			       struct nilfs_shadow_map *shadow)
@@ -545,6 +542,8 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 /**
  * nilfs_mdt_save_to_shadow_map - copy bmap and dirty pages to shadow map
  * @inode: inode of the metadata file
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_mdt_save_to_shadow_map(struct inode *inode)
 {
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1d836a5540f3..953fbd5f0851 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -370,6 +370,7 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 	struct folio *old_folio;
 	struct nilfs_dir_entry *old_de;
 	struct nilfs_transaction_info ti;
+	bool old_is_dir = S_ISDIR(old_inode->i_mode);
 	int err;
 
 	if (flags & ~RENAME_NOREPLACE)
@@ -385,7 +386,7 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 		goto out;
 	}
 
-	if (S_ISDIR(old_inode->i_mode)) {
+	if (old_is_dir && old_dir != new_dir) {
 		err = -EIO;
 		dir_de = nilfs_dotdot(old_inode, &dir_folio);
 		if (!dir_de)
@@ -397,7 +398,7 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 		struct nilfs_dir_entry *new_de;
 
 		err = -ENOTEMPTY;
-		if (dir_de && !nilfs_empty_dir(new_inode))
+		if (old_is_dir && !nilfs_empty_dir(new_inode))
 			goto out_dir;
 
 		new_de = nilfs_find_entry(new_dir, &new_dentry->d_name,
@@ -406,11 +407,13 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 			err = PTR_ERR(new_de);
 			goto out_dir;
 		}
-		nilfs_set_link(new_dir, new_de, new_folio, old_inode);
+		err = nilfs_set_link(new_dir, new_de, new_folio, old_inode);
 		folio_release_kmap(new_folio, new_de);
+		if (unlikely(err))
+			goto out_dir;
 		nilfs_mark_inode_dirty(new_dir);
 		inode_set_ctime_current(new_inode);
-		if (dir_de)
+		if (old_is_dir)
 			drop_nlink(new_inode);
 		drop_nlink(new_inode);
 		nilfs_mark_inode_dirty(new_inode);
@@ -418,7 +421,7 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 		err = nilfs_add_link(new_dentry, old_inode);
 		if (err)
 			goto out_dir;
-		if (dir_de) {
+		if (old_is_dir) {
 			inc_nlink(new_dir);
 			nilfs_mark_inode_dirty(new_dir);
 		}
@@ -430,28 +433,28 @@ static int nilfs_rename(struct mnt_idmap *idmap,
 	 */
 	inode_set_ctime_current(old_inode);
 
-	nilfs_delete_entry(old_de, old_folio);
-
-	if (dir_de) {
-		nilfs_set_link(old_inode, dir_de, dir_folio, new_dir);
-		folio_release_kmap(dir_folio, dir_de);
-		drop_nlink(old_dir);
+	err = nilfs_delete_entry(old_de, old_folio);
+	if (likely(!err)) {
+		if (old_is_dir) {
+			if (old_dir != new_dir)
+				err = nilfs_set_link(old_inode, dir_de,
+						     dir_folio, new_dir);
+			drop_nlink(old_dir);
+		}
+		nilfs_mark_inode_dirty(old_dir);
 	}
-	folio_release_kmap(old_folio, old_de);
-
-	nilfs_mark_inode_dirty(old_dir);
 	nilfs_mark_inode_dirty(old_inode);
 
-	err = nilfs_transaction_commit(old_dir->i_sb);
-	return err;
-
 out_dir:
 	if (dir_de)
 		folio_release_kmap(dir_folio, dir_de);
 out_old:
 	folio_release_kmap(old_folio, old_de);
 out:
-	nilfs_transaction_abort(old_dir->i_sb);
+	if (likely(!err))
+		err = nilfs_transaction_commit(old_dir->i_sb);
+	else
+		nilfs_transaction_abort(old_dir->i_sb);
 	return err;
 }
 
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index dff241c53fc5..cb6ed54accd7 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -261,8 +261,8 @@ struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *,
 int nilfs_delete_entry(struct nilfs_dir_entry *, struct folio *);
 int nilfs_empty_dir(struct inode *);
 struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct folio **);
-void nilfs_set_link(struct inode *, struct nilfs_dir_entry *,
-			   struct folio *, struct inode *);
+int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
+		   struct folio *folio, struct inode *inode);
 
 /* file.c */
 extern int nilfs_sync_file(struct file *, loff_t, loff_t, int);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 9de2a494a069..806b056d2260 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -135,8 +135,7 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
  * nilfs_folio_buffers_clean - Check if a folio has dirty buffers or not.
  * @folio: Folio to be checked.
  *
- * nilfs_folio_buffers_clean() returns false if the folio has dirty buffers.
- * Otherwise, it returns true.
+ * Return: false if the folio has dirty buffers, true otherwise.
  */
 bool nilfs_folio_buffers_clean(struct folio *folio)
 {
@@ -392,6 +391,11 @@ void nilfs_clear_dirty_pages(struct address_space *mapping)
 /**
  * nilfs_clear_folio_dirty - discard dirty folio
  * @folio: dirty folio that will be discarded
+ *
+ * nilfs_clear_folio_dirty() clears working states including dirty state for
+ * the folio and its buffers.  If the folio has buffers, clear only if it is
+ * confirmed that none of the buffer heads are busy (none have valid
+ * references and none are locked).
  */
 void nilfs_clear_folio_dirty(struct folio *folio)
 {
@@ -399,10 +403,6 @@ void nilfs_clear_folio_dirty(struct folio *folio)
 
 	BUG_ON(!folio_test_locked(folio));
 
-	folio_clear_uptodate(folio);
-	folio_clear_mappedtodisk(folio);
-	folio_clear_checked(folio);
-
 	head = folio_buffers(folio);
 	if (head) {
 		const unsigned long clear_bits =
@@ -410,6 +410,25 @@ void nilfs_clear_folio_dirty(struct folio *folio)
 			 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
 			 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) |
 			 BIT(BH_Delay));
+		bool busy, invalidated = false;
+
+recheck_buffers:
+		busy = false;
+		bh = head;
+		do {
+			if (atomic_read(&bh->b_count) | buffer_locked(bh)) {
+				busy = true;
+				break;
+			}
+		} while (bh = bh->b_this_page, bh != head);
+
+		if (busy) {
+			if (invalidated)
+				return;
+			invalidate_bh_lrus();
+			invalidated = true;
+			goto recheck_buffers;
+		}
 
 		bh = head;
 		do {
@@ -419,6 +438,9 @@ void nilfs_clear_folio_dirty(struct folio *folio)
 		} while (bh = bh->b_this_page, bh != head);
 	}
 
+	folio_clear_uptodate(folio);
+	folio_clear_mappedtodisk(folio);
+	folio_clear_checked(folio);
 	__nilfs_clear_folio_dirty(folio);
 }
 
@@ -477,8 +499,9 @@ void __nilfs_clear_folio_dirty(struct folio *folio)
  * This function searches an extent of buffers marked "delayed" which
  * starts from a block offset equal to or larger than @start_blk.  If
  * such an extent was found, this will store the start offset in
- * @blkoff and return its length in blocks.  Otherwise, zero is
- * returned.
+ * @blkoff and return its length in blocks.
+ *
+ * Return: Length in blocks of found extent, 0 otherwise.
  */
 unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index e43405bf521e..22aecf6e2344 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -88,6 +88,8 @@ static int nilfs_warn_segment_error(struct super_block *sb, int err)
  * @check_bytes: number of bytes to be checked
  * @start: DBN of start block
  * @nblock: number of blocks to be checked
+ *
+ * Return: 0 on success, or %-EIO if an I/O error occurs.
  */
 static int nilfs_compute_checksum(struct the_nilfs *nilfs,
 				  struct buffer_head *bhs, u32 *sum,
@@ -126,6 +128,11 @@ static int nilfs_compute_checksum(struct the_nilfs *nilfs,
  * @sr_block: disk block number of the super root block
  * @pbh: address of a buffer_head pointer to return super root buffer
  * @check: CRC check flag
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Super root block corrupted.
+ * * %-EIO	- I/O error.
  */
 int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block,
 				struct buffer_head **pbh, int check)
@@ -176,6 +183,8 @@ int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block,
  * @nilfs: nilfs object
  * @start_blocknr: start block number of the log
  * @sum: pointer to return segment summary structure
+ *
+ * Return: Buffer head pointer, or NULL if an I/O error occurs.
  */
 static struct buffer_head *
 nilfs_read_log_header(struct the_nilfs *nilfs, sector_t start_blocknr,
@@ -195,6 +204,13 @@ nilfs_read_log_header(struct the_nilfs *nilfs, sector_t start_blocknr,
  * @seg_seq: sequence number of segment
  * @bh_sum: buffer head of summary block
  * @sum: segment summary struct
+ *
+ * Return: 0 on success, or one of the following internal codes on failure:
+ * * %NILFS_SEG_FAIL_MAGIC	    - Magic number mismatch.
+ * * %NILFS_SEG_FAIL_SEQ	    - Sequence number mismatch.
+ * * %NIFLS_SEG_FAIL_CONSISTENCY    - Block count out of range.
+ * * %NILFS_SEG_FAIL_IO		    - I/O error.
+ * * %NILFS_SEG_FAIL_CHECKSUM_FULL  - Full log checksum verification failed.
  */
 static int nilfs_validate_log(struct the_nilfs *nilfs, u64 seg_seq,
 			      struct buffer_head *bh_sum,
@@ -238,6 +254,9 @@ out:
  * @pbh: the current buffer head on summary blocks [in, out]
  * @offset: the current byte offset on summary blocks [in, out]
  * @bytes: byte size of the item to be read
+ *
+ * Return: Kernel space address of current segment summary entry, or
+ * NULL if an I/O error occurs.
  */
 static void *nilfs_read_summary_info(struct the_nilfs *nilfs,
 				     struct buffer_head **pbh,
@@ -300,6 +319,11 @@ static void nilfs_skip_summary_info(struct the_nilfs *nilfs,
  * @start_blocknr: start block number of the log
  * @sum: log summary information
  * @head: list head to add nilfs_recovery_block struct
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_scan_dsync_log(struct the_nilfs *nilfs, sector_t start_blocknr,
 				struct nilfs_segment_summary *sum,
@@ -571,6 +595,12 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
  * @sb: super block instance
  * @root: NILFS root instance
  * @ri: pointer to a nilfs_recovery_info
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Log format error.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
 				 struct super_block *sb,
@@ -754,18 +784,13 @@ static void nilfs_abort_roll_forward(struct the_nilfs *nilfs)
  * @sb: super block instance
  * @ri: pointer to a nilfs_recovery_info struct to store search results.
  *
- * Return Value: On success, 0 is returned.  On error, one of the following
- * negative error code is returned.
- *
- * %-EINVAL - Inconsistent filesystem state.
- *
- * %-EIO - I/O error
- *
- * %-ENOSPC - No space left on device (only in a panic state).
- *
- * %-ERESTARTSYS - Interrupted.
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL		- Inconsistent filesystem state.
+ * * %-EIO		- I/O error.
+ * * %-ENOMEM		- Insufficient memory available.
+ * * %-ENOSPC		- No space left on device (only in a panic state).
+ * * %-ERESTARTSYS	- Interrupted.
  */
 int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
 			      struct super_block *sb,
@@ -830,14 +855,11 @@ failed:
  * segment pointed by the superblock.  It sets up struct the_nilfs through
  * this search. It fills nilfs_recovery_info (ri) required for recovery.
  *
- * Return Value: On success, 0 is returned.  On error, one of the following
- * negative error code is returned.
- *
- * %-EINVAL - No valid segment found
- *
- * %-EIO - I/O error
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- No valid segment found.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_search_super_root(struct the_nilfs *nilfs,
 			    struct nilfs_recovery_info *ri)
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index e08cab03366b..a8bdf3d318ea 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -406,12 +406,7 @@ static int nilfs_segbuf_submit_bh(struct nilfs_segment_buffer *segbuf,
  * @segbuf: buffer storing a log to be written
  * @nilfs: nilfs object
  *
- * Return Value: On Success, 0 is returned. On Error, one of the following
- * negative error code is returned.
- *
- * %-EIO - I/O error
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: Always 0.
  */
 static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf,
 			      struct the_nilfs *nilfs)
@@ -452,10 +447,7 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf,
  * nilfs_segbuf_wait - wait for completion of requested BIOs
  * @segbuf: segment buffer
  *
- * Return Value: On Success, 0 is returned. On Error, one of the following
- * negative error code is returned.
- *
- * %-EIO - I/O error
+ * Return: 0 on success, or %-EIO if I/O error is detected.
  */
 static int nilfs_segbuf_wait(struct nilfs_segment_buffer *segbuf)
 {
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 587251830897..3a202e51b360 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -191,12 +191,10 @@ static int nilfs_prepare_segment_lock(struct super_block *sb,
  * When @vacancy_check flag is set, this function will check the amount of
  * free space, and will wait for the GC to reclaim disk space if low capacity.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
- *
- * %-ENOSPC - No space left on device
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ENOSPC	- No space left on device (if checking free space).
  */
 int nilfs_transaction_begin(struct super_block *sb,
 			    struct nilfs_transaction_info *ti,
@@ -252,6 +250,8 @@ int nilfs_transaction_begin(struct super_block *sb,
  * nilfs_transaction_commit() sets a timer to start the segment
  * constructor.  If a sync flag is set, it starts construction
  * directly.
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_transaction_commit(struct super_block *sb)
 {
@@ -407,6 +407,8 @@ static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
 /**
  * nilfs_segctor_reset_segment_buffer - reset the current segment buffer
  * @sci: nilfs_sc_info
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci)
 {
@@ -734,7 +736,6 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
 		if (!head)
 			head = create_empty_buffers(folio,
 					i_blocksize(inode), 0);
-		folio_unlock(folio);
 
 		bh = head;
 		do {
@@ -744,11 +745,14 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
 			list_add_tail(&bh->b_assoc_buffers, listp);
 			ndirties++;
 			if (unlikely(ndirties >= nlimit)) {
+				folio_unlock(folio);
 				folio_batch_release(&fbatch);
 				cond_resched();
 				return ndirties;
 			}
 		} while (bh = bh->b_this_page, bh != head);
+
+		folio_unlock(folio);
 	}
 	folio_batch_release(&fbatch);
 	cond_resched();
@@ -1118,7 +1122,8 @@ static int nilfs_segctor_scan_file_dsync(struct nilfs_sc_info *sci,
  * a super root block containing this sufile change is complete, and it can
  * be canceled with nilfs_sufile_cancel_freev() until then.
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EINVAL	- Invalid segment number.
  * * %-EIO	- I/O error (including metadata corruption).
  * * %-ENOMEM	- Insufficient memory available.
@@ -1315,6 +1320,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
  * nilfs_segctor_begin_construction - setup segment buffer to make a new log
  * @sci: nilfs_sc_info
  * @nilfs: nilfs object
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_segctor_begin_construction(struct nilfs_sc_info *sci,
 					    struct the_nilfs *nilfs)
@@ -2312,18 +2319,13 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force)
  * nilfs_construct_segment - construct a logical segment
  * @sb: super block
  *
- * Return Value: On success, 0 is returned. On errors, one of the following
- * negative error code is returned.
- *
- * %-EROFS - Read only filesystem.
- *
- * %-EIO - I/O error
- *
- * %-ENOSPC - No space left on device (only in a panic state).
- *
- * %-ERESTARTSYS - Interrupted.
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO		- I/O error (including metadata corruption).
+ * * %-ENOMEM		- Insufficient memory available.
+ * * %-ENOSPC		- No space left on device (only in a panic state).
+ * * %-ERESTARTSYS	- Interrupted.
+ * * %-EROFS		- Read only filesystem.
  */
 int nilfs_construct_segment(struct super_block *sb)
 {
@@ -2347,18 +2349,13 @@ int nilfs_construct_segment(struct super_block *sb)
  * @start: start byte offset
  * @end: end byte offset (inclusive)
  *
- * Return Value: On success, 0 is returned. On errors, one of the following
- * negative error code is returned.
- *
- * %-EROFS - Read only filesystem.
- *
- * %-EIO - I/O error
- *
- * %-ENOSPC - No space left on device (only in a panic state).
- *
- * %-ERESTARTSYS - Interrupted.
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO		- I/O error (including metadata corruption).
+ * * %-ENOMEM		- Insufficient memory available.
+ * * %-ENOSPC		- No space left on device (only in a panic state).
+ * * %-ERESTARTSYS	- Interrupted.
+ * * %-EROFS		- Read only filesystem.
  */
 int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode,
 				  loff_t start, loff_t end)
@@ -2464,6 +2461,8 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err)
  * nilfs_segctor_construct - form logs and write them to disk
  * @sci: segment constructor object
  * @mode: mode of log forming
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_segctor_construct(struct nilfs_sc_info *sci, int mode)
 {
@@ -2836,7 +2835,8 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
  * This allocates a log writer object, initializes it, and starts the
  * log writer.
  *
- * Return: 0 on success, or the following negative error code on failure.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
  * * %-EINTR	- Log writer thread creation failed due to interruption.
  * * %-ENOMEM	- Insufficient memory available.
  */
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index d3ecc813d633..330f269abedf 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -133,6 +133,8 @@ static void nilfs_sufile_mod_counter(struct buffer_head *header_bh,
 /**
  * nilfs_sufile_get_ncleansegs - return the number of clean segments
  * @sufile: inode of segment usage file
+ *
+ * Return: Number of clean segments.
  */
 unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile)
 {
@@ -155,17 +157,13 @@ unsigned long nilfs_sufile_get_ncleansegs(struct inode *sufile)
  * of successfully modified segments from the head is stored in the
  * place @ndone points to.
  *
- * Return Value: On success, zero is returned.  On error, one of the
- * following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - Given segment usage is in hole block (may be returned if
- *            @create is zero)
- *
- * %-EINVAL - Invalid segment usage number
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Invalid segment usage number
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOENT	- Given segment usage is in hole block (may be returned if
+ *		  @create is zero)
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_sufile_updatev(struct inode *sufile, __u64 *segnumv, size_t nsegs,
 			 int create, size_t *ndone,
@@ -272,10 +270,7 @@ int nilfs_sufile_update(struct inode *sufile, __u64 segnum, int create,
  * @start: minimum segment number of allocatable region (inclusive)
  * @end: maximum segment number of allocatable region (inclusive)
  *
- * Return Value: On success, 0 is returned.  On error, one of the
- * following negative error codes is returned.
- *
- * %-ERANGE - invalid segment region
+ * Return: 0 on success, or %-ERANGE if segment range is invalid.
  */
 int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end)
 {
@@ -300,17 +295,14 @@ int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end)
  * @sufile: inode of segment usage file
  * @segnump: pointer to segment number
  *
- * Description: nilfs_sufile_alloc() allocates a clean segment.
- *
- * Return Value: On success, 0 is returned and the segment number of the
- * allocated segment is stored in the place pointed by @segnump. On error, one
- * of the following negative error codes is returned.
- *
- * %-EIO - I/O error.
+ * Description: nilfs_sufile_alloc() allocates a clean segment, and stores
+ * its segment number in the place pointed to by @segnump.
  *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOSPC - No clean segment left.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ENOSPC	- No clean segment left.
  */
 int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
 {
@@ -510,6 +502,8 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
  * nilfs_sufile_mark_dirty - mark the buffer having a segment usage dirty
  * @sufile: inode of segment usage file
  * @segnum: segment number
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
 {
@@ -569,6 +563,8 @@ out_sem:
  * @segnum: segment number
  * @nblocks: number of live blocks in the segment
  * @modtime: modification time (option)
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
 				   unsigned long nblocks, time64_t modtime)
@@ -610,16 +606,13 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
  * @sufile: inode of segment usage file
  * @sustat: pointer to a structure of segment usage statistics
  *
- * Description: nilfs_sufile_get_stat() returns information about segment
- * usage.
+ * Description: nilfs_sufile_get_stat() retrieves segment usage statistics
+ * and stores them in the location pointed to by @sustat.
  *
- * Return Value: On success, 0 is returned, and segment usage information is
- * stored in the place pointed by @sustat. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
 {
@@ -683,16 +676,12 @@ void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
  * @start: start segment number (inclusive)
  * @end: end segment number (inclusive)
  *
- * Return Value: On success, 0 is returned.  On error, one of the
- * following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - Invalid number of segments specified
- *
- * %-EBUSY - Dirty or active segments are present in the range
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EBUSY	- Dirty or active segments are present in the range.
+ * * %-EINVAL	- Invalid number of segments specified.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static int nilfs_sufile_truncate_range(struct inode *sufile,
 				       __u64 start, __u64 end)
@@ -787,16 +776,12 @@ out:
  * @sufile: inode of segment usage file
  * @newnsegs: new number of segments
  *
- * Return Value: On success, 0 is returned.  On error, one of the
- * following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOSPC - Enough free space is not left for shrinking
- *
- * %-EBUSY - Dirty or active segments exist in the region to be truncated
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EBUSY	- Dirty or active segments exist in the region to be truncated.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-ENOSPC	- Enough free space is not left for shrinking.
  */
 int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
 {
@@ -865,7 +850,7 @@ out:
  * @nsi:    size of suinfo array
  *
  * Return: Count of segment usage info items stored in the output buffer on
- * success, or the following negative error code on failure.
+ * success, or one of the following negative error codes on failure:
  * * %-EIO	- I/O error (including metadata corruption).
  * * %-ENOMEM	- Insufficient memory available.
  */
@@ -939,14 +924,11 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
  * segment usage accordingly. Only the fields indicated by the sup_flags
  * are updated.
  *
- * Return Value: On success, 0 is returned. On error, one of the
- * following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Invalid values in input (segment number, flags or nblocks).
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
 				unsigned int supsz, size_t nsup)
@@ -1073,7 +1055,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
  * and start+len is rounded down. For each clean segment blkdev_issue_discard
  * function is invoked.
  *
- * Return Value: On success, 0 is returned or negative error code, otherwise.
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
 {
@@ -1219,6 +1201,8 @@ out_sem:
  * @susize: size of a segment usage entry
  * @raw_inode: on-disk sufile inode
  * @inodep: buffer to store the inode
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_sufile_read(struct super_block *sb, size_t susize,
 		      struct nilfs_inode *raw_inode, struct inode **inodep)
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index 8e8a1a5a0402..cd6f28ab3521 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -58,6 +58,8 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);
  * nilfs_sufile_scrap - make a segment garbage
  * @sufile: inode of segment usage file
  * @segnum: segment number to be freed
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static inline int nilfs_sufile_scrap(struct inode *sufile, __u64 segnum)
 {
@@ -68,6 +70,8 @@ static inline int nilfs_sufile_scrap(struct inode *sufile, __u64 segnum)
  * nilfs_sufile_free - free segment
  * @sufile: inode of segment usage file
  * @segnum: segment number to be freed
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static inline int nilfs_sufile_free(struct inode *sufile, __u64 segnum)
 {
@@ -80,6 +84,8 @@ static inline int nilfs_sufile_free(struct inode *sufile, __u64 segnum)
  * @segnumv: array of segment numbers
  * @nsegs: size of @segnumv array
  * @ndone: place to store the number of freed segments
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static inline int nilfs_sufile_freev(struct inode *sufile, __u64 *segnumv,
 				     size_t nsegs, size_t *ndone)
@@ -95,8 +101,7 @@ static inline int nilfs_sufile_freev(struct inode *sufile, __u64 *segnumv,
  * @nsegs: size of @segnumv array
  * @ndone: place to store the number of cancelled segments
  *
- * Return Value: On success, 0 is returned. On error, a negative error codes
- * is returned.
+ * Return: 0 on success, or a negative error code on failure.
  */
 static inline int nilfs_sufile_cancel_freev(struct inode *sufile,
 					    __u64 *segnumv, size_t nsegs,
@@ -114,14 +119,11 @@ static inline int nilfs_sufile_cancel_freev(struct inode *sufile,
  * Description: nilfs_sufile_set_error() marks the segment specified by
  * @segnum as erroneous. The error segment will never be used again.
  *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-EINVAL - Invalid segment usage number.
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- Invalid segment usage number.
+ * * %-EIO	- I/O error (including metadata corruption).
+ * * %-ENOMEM	- Insufficient memory available.
  */
 static inline int nilfs_sufile_set_error(struct inode *sufile, __u64 segnum)
 {
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index eca79cca3803..badc2cbc895e 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -309,6 +309,8 @@ int nilfs_commit_super(struct super_block *sb, int flag)
  * This function restores state flags in the on-disk super block.
  * This will set "clean" flag (i.e. NILFS_VALID_FS) unless the
  * filesystem was not clean previously.
+ *
+ * Return: 0 on success, %-EIO if I/O error or superblock is corrupted.
  */
 int nilfs_cleanup_super(struct super_block *sb)
 {
@@ -339,6 +341,8 @@ int nilfs_cleanup_super(struct super_block *sb)
  * nilfs_move_2nd_super - relocate secondary super block
  * @sb: super block instance
  * @sb2off: new offset of the secondary super block (in bytes)
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 {
@@ -420,6 +424,8 @@ out:
  * nilfs_resize_fs - resize the filesystem
  * @sb: super block instance
  * @newsize: new size of the filesystem (in bytes)
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_resize_fs(struct super_block *sb, __u64 newsize)
 {
@@ -987,7 +993,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
  * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint
  * @root_dentry: root dentry of the tree to be shrunk
  *
- * This function returns true if the tree was in-use.
+ * Return: true if the tree was in-use, false otherwise.
  */
 static bool nilfs_tree_is_busy(struct dentry *root_dentry)
 {
@@ -1033,6 +1039,8 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
  *
  * This function is called exclusively by nilfs->ns_mount_mutex.
  * So, the recovery process is protected from other simultaneous mounts.
+ *
+ * Return: 0 on success, or a negative error code on failure.
  */
 static int
 nilfs_fill_super(struct super_block *sb, struct fs_context *fc)
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index ac03fd3c330c..cb01ea81724d 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -49,8 +49,8 @@ void nilfs_set_last_segment(struct the_nilfs *nilfs,
  * alloc_nilfs - allocate a nilfs object
  * @sb: super block instance
  *
- * Return Value: On success, pointer to the_nilfs is returned.
- * On error, NULL is returned.
+ * Return: a pointer to the allocated nilfs object on success, or NULL on
+ * failure.
  */
 struct the_nilfs *alloc_nilfs(struct super_block *sb)
 {
@@ -165,6 +165,9 @@ static void nilfs_clear_recovery_info(struct nilfs_recovery_info *ri)
  * containing a super root from a given super block, and initializes
  * relevant information on the nilfs object preparatory for log
  * scanning and recovery.
+ *
+ * Return: 0 on success, or %-EINVAL if current segment number is out
+ * of range.
  */
 static int nilfs_store_log_cursor(struct the_nilfs *nilfs,
 				  struct nilfs_super_block *sbp)
@@ -200,8 +203,7 @@ static int nilfs_store_log_cursor(struct the_nilfs *nilfs,
  * exponent information written in @sbp and stores it in @blocksize,
  * or aborts with an error message if it's too large.
  *
- * Return Value: On success, 0 is returned. If the block size is too
- * large, -EINVAL is returned.
+ * Return: 0 on success, or %-EINVAL if the block size is too large.
  */
 static int nilfs_get_blocksize(struct super_block *sb,
 			       struct nilfs_super_block *sbp, int *blocksize)
@@ -226,6 +228,13 @@ static int nilfs_get_blocksize(struct super_block *sb,
  * load_nilfs() searches and load the latest super root,
  * attaches the last segment, and does recovery if needed.
  * The caller must call this exclusively for simultaneous mounts.
+ *
+ * Return: 0 on success, or one of the following negative error codes on
+ * failure:
+ * * %-EINVAL	- No valid segment found.
+ * * %-EIO	- I/O error.
+ * * %-ENOMEM	- Insufficient memory available.
+ * * %-EROFS	- Read only device or RO compat mode (if recovery is required)
  */
 int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 {
@@ -395,6 +404,8 @@ static unsigned long long nilfs_max_size(unsigned int blkbits)
  * nilfs_nrsvsegs - calculate the number of reserved segments
  * @nilfs: nilfs object
  * @nsegs: total number of segments
+ *
+ * Return: Number of reserved segments.
  */
 unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs)
 {
@@ -406,6 +417,8 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs)
 /**
  * nilfs_max_segment_count - calculate the maximum number of segments
  * @nilfs: nilfs object
+ *
+ * Return: Maximum number of segments
  */
 static u64 nilfs_max_segment_count(struct the_nilfs *nilfs)
 {
@@ -538,7 +551,7 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp)
  * area, or if the parameters themselves are not normal, it is
  * determined to be invalid.
  *
- * Return Value: true if invalid, false if valid.
+ * Return: true if invalid, false if valid.
  */
 static bool nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset)
 {
@@ -684,8 +697,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
  * reading the super block, getting disk layout information, initializing
  * shared fields in the_nilfs).
  *
- * Return Value: On success, 0 is returned. On error, a negative error
- * code is returned.
+ * Return: 0 on success, or a negative error code on failure.
  */
 int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
 {
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 6004dfdfdf0f..c4cdaf5fa7ed 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -20,7 +20,7 @@
 
 static int dir_notify_enable __read_mostly = 1;
 #ifdef CONFIG_SYSCTL
-static struct ctl_table dnotify_sysctls[] = {
+static const struct ctl_table dnotify_sysctls[] = {
 	{
 		.procname	= "dir-notify-enable",
 		.data		= &dir_notify_enable,
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 6ff94e312232..ba3e2d09eb44 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -58,7 +58,7 @@ static int fanotify_max_queued_events __read_mostly;
 static long ft_zero = 0;
 static long ft_int_max = INT_MAX;
 
-static struct ctl_table fanotify_table[] = {
+static const struct ctl_table fanotify_table[] = {
 	{
 		.procname	= "max_user_groups",
 		.data	= &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 8ee495a58d0a..fae1b6d397ea 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -648,7 +648,7 @@ EXPORT_SYMBOL_GPL(fsnotify);
  * Later, fsnotify permission hooks do not check if there are permission event
  * watches, but that there were permission event watches at open time.
  */
-void file_set_fsnotify_mode(struct file *file)
+void file_set_fsnotify_mode_from_watchers(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry, *parent;
 	struct super_block *sb = dentry->d_sb;
@@ -665,7 +665,7 @@ void file_set_fsnotify_mode(struct file *file)
 	 */
 	if (likely(!fsnotify_sb_has_priority_watchers(sb,
 						FSNOTIFY_PRIO_CONTENT))) {
-		file->f_mode |= FMODE_NONOTIFY_PERM;
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
 		return;
 	}
 
@@ -676,7 +676,7 @@ void file_set_fsnotify_mode(struct file *file)
 	if ((!d_is_dir(dentry) && !d_is_reg(dentry)) ||
 	    likely(!fsnotify_sb_has_priority_watchers(sb,
 						FSNOTIFY_PRIO_PRE_CONTENT))) {
-		file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
 		return;
 	}
 
@@ -686,19 +686,25 @@ void file_set_fsnotify_mode(struct file *file)
 	 */
 	mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
 	if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask,
-				     FSNOTIFY_PRE_CONTENT_EVENTS)))
+				     FSNOTIFY_PRE_CONTENT_EVENTS))) {
+		/* Enable pre-content events */
+		file_set_fsnotify_mode(file, 0);
 		return;
+	}
 
 	/* Is parent watching for pre-content events on this file? */
 	if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
 		parent = dget_parent(dentry);
 		p_mask = fsnotify_inode_watches_children(d_inode(parent));
 		dput(parent);
-		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)
+		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) {
+			/* Enable pre-content events */
+			file_set_fsnotify_mode(file, 0);
 			return;
+		}
 	}
 	/* Nobody watching for pre-content events from this file */
-	file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
 }
 #endif
 
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e0c48956608a..b372fb2c56bd 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __ro_after_init;
 static long it_zero = 0;
 static long it_int_max = INT_MAX;
 
-static struct ctl_table inotify_table[] = {
+static const struct ctl_table inotify_table[] = {
 	{
 		.procname	= "max_user_instances",
 		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index 8d789b017fa9..af94e3737470 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -787,7 +787,8 @@ pack_runs:
 		if (err)
 			goto out;
 
-		attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id);
+		attr = mi_find_attr(ni, mi, NULL, type, name, name_len,
+				    &le->id);
 		if (!attr) {
 			err = -EINVAL;
 			goto bad_inode;
@@ -1181,7 +1182,7 @@ repack:
 			goto out;
 		}
 
-		attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id);
+		attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, &le->id);
 		if (!attr) {
 			err = -EINVAL;
 			goto out;
@@ -1406,7 +1407,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr,
 	 */
 	if (!attr->non_res) {
 		if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) {
-			ntfs_inode_err(&ni->vfs_inode, "is corrupted");
+			_ntfs_bad_inode(&ni->vfs_inode);
 			return -EINVAL;
 		}
 		addr = resident_data(attr);
@@ -1796,7 +1797,7 @@ repack:
 				goto out;
 			}
 
-			attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0,
+			attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0,
 					    &le->id);
 			if (!attr) {
 				err = -EINVAL;
@@ -2041,8 +2042,8 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes)
 				}
 
 				/* Look for required attribute. */
-				attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL,
-						    0, &le->id);
+				attr = mi_find_attr(ni, mi, NULL, ATTR_DATA,
+						    NULL, 0, &le->id);
 				if (!attr) {
 					err = -EINVAL;
 					goto out;
@@ -2587,7 +2588,7 @@ int attr_force_nonresident(struct ntfs_inode *ni)
 
 	attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, &mi);
 	if (!attr) {
-		ntfs_bad_inode(&ni->vfs_inode, "no data attribute");
+		_ntfs_bad_inode(&ni->vfs_inode);
 		return -ENOENT;
 	}
 
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index fc6a8aa29e3a..b6da80c69ca6 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -512,7 +512,7 @@ out:
 		ctx->pos = pos;
 	} else if (err < 0) {
 		if (err == -EINVAL)
-			ntfs_inode_err(dir, "directory corrupted");
+			_ntfs_bad_inode(dir);
 		ctx->pos = eod;
 	}
 
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 8b39d0ce5f28..5df6a0b5add9 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -75,7 +75,7 @@ struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni)
 {
 	const struct ATTRIB *attr;
 
-	attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL);
+	attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_STD, NULL, 0, NULL);
 	return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) :
 		      NULL;
 }
@@ -89,7 +89,7 @@ struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni)
 {
 	const struct ATTRIB *attr;
 
-	attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL);
+	attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_STD, NULL, 0, NULL);
 
 	return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) :
 		      NULL;
@@ -148,8 +148,10 @@ int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi)
 		goto out;
 
 	err = mi_get(ni->mi.sbi, rno, &r);
-	if (err)
+	if (err) {
+		_ntfs_bad_inode(&ni->vfs_inode);
 		return err;
+	}
 
 	ni_add_mi(ni, r);
 
@@ -201,7 +203,8 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr,
 			*mi = &ni->mi;
 
 		/* Look for required attribute in primary record. */
-		return mi_find_attr(&ni->mi, attr, type, name, name_len, NULL);
+		return mi_find_attr(ni, &ni->mi, attr, type, name, name_len,
+				    NULL);
 	}
 
 	/* First look for list entry of required type. */
@@ -217,7 +220,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr,
 		return NULL;
 
 	/* Look for required attribute. */
-	attr = mi_find_attr(m, NULL, type, name, name_len, &le->id);
+	attr = mi_find_attr(ni, m, NULL, type, name, name_len, &le->id);
 
 	if (!attr)
 		goto out;
@@ -238,8 +241,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr,
 	return attr;
 
 out:
-	ntfs_inode_err(&ni->vfs_inode, "failed to parse mft record");
-	ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR);
+	_ntfs_bad_inode(&ni->vfs_inode);
 	return NULL;
 }
 
@@ -259,7 +261,7 @@ struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr,
 		if (mi)
 			*mi = &ni->mi;
 		/* Enum attributes in primary record. */
-		return mi_enum_attr(&ni->mi, attr);
+		return mi_enum_attr(ni, &ni->mi, attr);
 	}
 
 	/* Get next list entry. */
@@ -275,7 +277,7 @@ struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr,
 		*mi = mi2;
 
 	/* Find attribute in loaded record. */
-	return rec_find_attr_le(mi2, le2);
+	return rec_find_attr_le(ni, mi2, le2);
 }
 
 /*
@@ -293,7 +295,8 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	if (!ni->attr_list.size) {
 		if (pmi)
 			*pmi = &ni->mi;
-		return mi_find_attr(&ni->mi, NULL, type, name, name_len, NULL);
+		return mi_find_attr(ni, &ni->mi, NULL, type, name, name_len,
+				    NULL);
 	}
 
 	le = al_find_ex(ni, NULL, type, name, name_len, NULL);
@@ -319,7 +322,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	if (pmi)
 		*pmi = mi;
 
-	attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id);
+	attr = mi_find_attr(ni, mi, NULL, type, name, name_len, &le->id);
 	if (!attr)
 		return NULL;
 
@@ -330,6 +333,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	    vcn <= le64_to_cpu(attr->nres.evcn))
 		return attr;
 
+	_ntfs_bad_inode(&ni->vfs_inode);
 	return NULL;
 }
 
@@ -398,7 +402,8 @@ int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	int diff;
 
 	if (base_only || type == ATTR_LIST || !ni->attr_list.size) {
-		attr = mi_find_attr(&ni->mi, NULL, type, name, name_len, id);
+		attr = mi_find_attr(ni, &ni->mi, NULL, type, name, name_len,
+				    id);
 		if (!attr)
 			return -ENOENT;
 
@@ -437,7 +442,7 @@ next_le2:
 
 		al_remove_le(ni, le);
 
-		attr = mi_find_attr(mi, NULL, type, name, name_len, id);
+		attr = mi_find_attr(ni, mi, NULL, type, name, name_len, id);
 		if (!attr)
 			return -ENOENT;
 
@@ -485,7 +490,7 @@ ni_ins_new_attr(struct ntfs_inode *ni, struct mft_inode *mi,
 		name = le->name;
 	}
 
-	attr = mi_insert_attr(mi, type, name, name_len, asize, name_off);
+	attr = mi_insert_attr(ni, mi, type, name, name_len, asize, name_off);
 	if (!attr) {
 		if (le_added)
 			al_remove_le(ni, le);
@@ -673,7 +678,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 	if (err)
 		return err;
 
-	attr_list = mi_find_attr(&ni->mi, NULL, ATTR_LIST, NULL, 0, NULL);
+	attr_list = mi_find_attr(ni, &ni->mi, NULL, ATTR_LIST, NULL, 0, NULL);
 	if (!attr_list)
 		return 0;
 
@@ -695,7 +700,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 		if (!mi)
 			return 0;
 
-		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
+		attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le),
 				    le->name_len, &le->id);
 		if (!attr)
 			return 0;
@@ -731,7 +736,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 			goto out;
 		}
 
-		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
+		attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le),
 				    le->name_len, &le->id);
 		if (!attr) {
 			/* Should never happened, 'cause already checked. */
@@ -740,7 +745,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 		asize = le32_to_cpu(attr->size);
 
 		/* Insert into primary record. */
-		attr_ins = mi_insert_attr(&ni->mi, le->type, le_name(le),
+		attr_ins = mi_insert_attr(ni, &ni->mi, le->type, le_name(le),
 					  le->name_len, asize,
 					  le16_to_cpu(attr->name_off));
 		if (!attr_ins) {
@@ -768,7 +773,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni)
 		if (!mi)
 			continue;
 
-		attr = mi_find_attr(mi, NULL, le->type, le_name(le),
+		attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le),
 				    le->name_len, &le->id);
 		if (!attr)
 			continue;
@@ -831,7 +836,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
 	free_b = 0;
 	attr = NULL;
 
-	for (; (attr = mi_enum_attr(&ni->mi, attr)); le = Add2Ptr(le, sz)) {
+	for (; (attr = mi_enum_attr(ni, &ni->mi, attr)); le = Add2Ptr(le, sz)) {
 		sz = le_size(attr->name_len);
 		le->type = attr->type;
 		le->size = cpu_to_le16(sz);
@@ -886,7 +891,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
 		u32 asize = le32_to_cpu(b->size);
 		u16 name_off = le16_to_cpu(b->name_off);
 
-		attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off),
+		attr = mi_insert_attr(ni, mi, b->type, Add2Ptr(b, name_off),
 				      b->name_len, asize, name_off);
 		if (!attr)
 			goto out;
@@ -909,7 +914,7 @@ int ni_create_attr_list(struct ntfs_inode *ni)
 			goto out;
 	}
 
-	attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0,
+	attr = mi_insert_attr(ni, &ni->mi, ATTR_LIST, NULL, 0,
 			      lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT);
 	if (!attr)
 		goto out;
@@ -993,13 +998,13 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le,
 		mi = rb_entry(node, struct mft_inode, node);
 
 		if (is_mft_data &&
-		    (mi_enum_attr(mi, NULL) ||
+		    (mi_enum_attr(ni, mi, NULL) ||
 		     vbo <= ((u64)mi->rno << sbi->record_bits))) {
 			/* We can't accept this record 'cause MFT's bootstrapping. */
 			continue;
 		}
 		if (is_mft &&
-		    mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, NULL)) {
+		    mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, NULL)) {
 			/*
 			 * This child record already has a ATTR_DATA.
 			 * So it can't accept any other records.
@@ -1008,7 +1013,7 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le,
 		}
 
 		if ((type != ATTR_NAME || name_len) &&
-		    mi_find_attr(mi, NULL, type, name, name_len, NULL)) {
+		    mi_find_attr(ni, mi, NULL, type, name, name_len, NULL)) {
 			/* Only indexed attributes can share same record. */
 			continue;
 		}
@@ -1157,7 +1162,7 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	/* Estimate the result of moving all possible attributes away. */
 	attr = NULL;
 
-	while ((attr = mi_enum_attr(&ni->mi, attr))) {
+	while ((attr = mi_enum_attr(ni, &ni->mi, attr))) {
 		if (attr->type == ATTR_STD)
 			continue;
 		if (attr->type == ATTR_LIST)
@@ -1175,7 +1180,7 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type,
 	attr = NULL;
 
 	for (;;) {
-		attr = mi_enum_attr(&ni->mi, attr);
+		attr = mi_enum_attr(ni, &ni->mi, attr);
 		if (!attr) {
 			/* We should never be here 'cause we have already check this case. */
 			err = -EINVAL;
@@ -1259,7 +1264,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni)
 	for (node = rb_first(&ni->mi_tree); node; node = rb_next(node)) {
 		mi = rb_entry(node, struct mft_inode, node);
 
-		attr = mi_enum_attr(mi, NULL);
+		attr = mi_enum_attr(ni, mi, NULL);
 
 		if (!attr) {
 			mft_min = mi->rno;
@@ -1280,7 +1285,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni)
 		ni_remove_mi(ni, mi_new);
 	}
 
-	attr = mi_find_attr(&ni->mi, NULL, ATTR_DATA, NULL, 0, NULL);
+	attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_DATA, NULL, 0, NULL);
 	if (!attr) {
 		err = -EINVAL;
 		goto out;
@@ -1397,7 +1402,7 @@ int ni_expand_list(struct ntfs_inode *ni)
 			continue;
 
 		/* Find attribute in primary record. */
-		attr = rec_find_attr_le(&ni->mi, le);
+		attr = rec_find_attr_le(ni, &ni->mi, le);
 		if (!attr) {
 			err = -EINVAL;
 			goto out;
@@ -1604,8 +1609,8 @@ int ni_delete_all(struct ntfs_inode *ni)
 		roff = le16_to_cpu(attr->nres.run_off);
 
 		if (roff > asize) {
-			_ntfs_bad_inode(&ni->vfs_inode);
-			return -EINVAL;
+			/* ni_enum_attr_ex checks this case. */
+			continue;
 		}
 
 		/* run==1 means unpack and deallocate. */
@@ -2726,9 +2731,10 @@ int ni_write_frame(struct ntfs_inode *ni, struct page **pages,
 {
 	int err;
 	struct ntfs_sb_info *sbi = ni->mi.sbi;
+	struct folio *folio = page_folio(pages[0]);
 	u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits;
 	u32 frame_size = sbi->cluster_size << NTFS_LZNT_CUNIT;
-	u64 frame_vbo = (u64)pages[0]->index << PAGE_SHIFT;
+	u64 frame_vbo = folio_pos(folio);
 	CLST frame = frame_vbo >> frame_bits;
 	char *frame_ondisk = NULL;
 	struct page **pages_disk = NULL;
@@ -3343,7 +3349,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint)
 		if (!mi->dirty)
 			continue;
 
-		is_empty = !mi_enum_attr(mi, NULL);
+		is_empty = !mi_enum_attr(ni, mi, NULL);
 
 		if (is_empty)
 			clear_rec_inuse(mi->mrec);
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 03471bc9371c..938d351ebac7 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -908,7 +908,11 @@ void ntfs_bad_inode(struct inode *inode, const char *hint)
 
 	ntfs_inode_err(inode, "%s", hint);
 	make_bad_inode(inode);
-	ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+	/* Avoid recursion if bad inode is $Volume. */
+	if (inode->i_ino != MFT_REC_VOL &&
+	    !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING)) {
+		ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+	}
 }
 
 /*
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index 9089c58a005c..7eb9fae22f8d 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -1094,8 +1094,7 @@ int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn,
 
 ok:
 	if (!index_buf_check(ib, bytes, &vbn)) {
-		ntfs_inode_err(&ni->vfs_inode, "directory corrupted");
-		ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR);
+		_ntfs_bad_inode(&ni->vfs_inode);
 		err = -EINVAL;
 		goto out;
 	}
@@ -1117,8 +1116,7 @@ ok:
 
 out:
 	if (err == -E_NTFS_CORRUPT) {
-		ntfs_inode_err(&ni->vfs_inode, "directory corrupted");
-		ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR);
+		_ntfs_bad_inode(&ni->vfs_inode);
 		err = -EINVAL;
 	}
 
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index be04d2845bb7..a1e11228dafd 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -410,6 +410,9 @@ end_enum:
 	if (!std5)
 		goto out;
 
+	if (is_bad_inode(inode))
+		goto out;
+
 	if (!is_match && name) {
 		err = -ENOENT;
 		goto out;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index cd8e8374bb5a..382820464dee 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -745,23 +745,24 @@ int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi);
 void mi_put(struct mft_inode *mi);
 int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno);
 int mi_read(struct mft_inode *mi, bool is_mft);
-struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr);
-// TODO: id?
-struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr,
-			    enum ATTR_TYPE type, const __le16 *name,
-			    u8 name_len, const __le16 *id);
-static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec,
+struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi,
+			    struct ATTRIB *attr);
+struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi,
+			    struct ATTRIB *attr, enum ATTR_TYPE type,
+			    const __le16 *name, u8 name_len, const __le16 *id);
+static inline struct ATTRIB *rec_find_attr_le(struct ntfs_inode *ni,
+					      struct mft_inode *rec,
 					      struct ATTR_LIST_ENTRY *le)
 {
-	return mi_find_attr(rec, NULL, le->type, le_name(le), le->name_len,
+	return mi_find_attr(ni, rec, NULL, le->type, le_name(le), le->name_len,
 			    &le->id);
 }
 int mi_write(struct mft_inode *mi, int wait);
 int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno,
 		  __le16 flags, bool is_mft);
-struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
-			      const __le16 *name, u8 name_len, u32 asize,
-			      u16 name_off);
+struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi,
+			      enum ATTR_TYPE type, const __le16 *name,
+			      u8 name_len, u32 asize, u16 name_off);
 
 bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi,
 		    struct ATTRIB *attr);
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index 61d53d39f3b9..714c7ecedca8 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -31,7 +31,7 @@ static inline int compare_attr(const struct ATTRIB *left, enum ATTR_TYPE type,
  *
  * Return: Unused attribute id that is less than mrec->next_attr_id.
  */
-static __le16 mi_new_attt_id(struct mft_inode *mi)
+static __le16 mi_new_attt_id(struct ntfs_inode *ni, struct mft_inode *mi)
 {
 	u16 free_id, max_id, t16;
 	struct MFT_REC *rec = mi->mrec;
@@ -52,7 +52,7 @@ static __le16 mi_new_attt_id(struct mft_inode *mi)
 	attr = NULL;
 
 	for (;;) {
-		attr = mi_enum_attr(mi, attr);
+		attr = mi_enum_attr(ni, mi, attr);
 		if (!attr) {
 			rec->next_attr_id = cpu_to_le16(max_id + 1);
 			mi->dirty = true;
@@ -195,7 +195,8 @@ out:
  * NOTE: mi->mrec - memory of size sbi->record_size
  * here we sure that mi->mrec->total == sbi->record_size (see mi_read)
  */
-struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
+struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi,
+			    struct ATTRIB *attr)
 {
 	const struct MFT_REC *rec = mi->mrec;
 	u32 used = le32_to_cpu(rec->used);
@@ -209,11 +210,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 		off = le16_to_cpu(rec->attr_off);
 
 		if (used > total)
-			return NULL;
+			goto out;
 
 		if (off >= used || off < MFTRECORD_FIXUP_OFFSET_1 ||
 		    !IS_ALIGNED(off, 8)) {
-			return NULL;
+			goto out;
 		}
 
 		/* Skip non-resident records. */
@@ -243,7 +244,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 	 */
 	if (off + 8 > used) {
 		static_assert(ALIGN(sizeof(enum ATTR_TYPE), 8) == 8);
-		return NULL;
+		goto out;
 	}
 
 	if (attr->type == ATTR_END) {
@@ -254,112 +255,116 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
 	/* 0x100 is last known attribute for now. */
 	t32 = le32_to_cpu(attr->type);
 	if (!t32 || (t32 & 0xf) || (t32 > 0x100))
-		return NULL;
+		goto out;
 
 	/* attributes in record must be ordered by type */
 	if (t32 < prev_type)
-		return NULL;
+		goto out;
 
 	asize = le32_to_cpu(attr->size);
 
 	if (!IS_ALIGNED(asize, 8))
-		return NULL;
+		goto out;
 
 	/* Check overflow and boundary. */
 	if (off + asize < off || off + asize > used)
-		return NULL;
+		goto out;
 
 	/* Can we use the field attr->non_res. */
 	if (off + 9 > used)
-		return NULL;
+		goto out;
 
 	/* Check size of attribute. */
 	if (!attr->non_res) {
 		/* Check resident fields. */
 		if (asize < SIZEOF_RESIDENT)
-			return NULL;
+			goto out;
 
 		t16 = le16_to_cpu(attr->res.data_off);
 		if (t16 > asize)
-			return NULL;
+			goto out;
 
 		if (le32_to_cpu(attr->res.data_size) > asize - t16)
-			return NULL;
+			goto out;
 
 		t32 = sizeof(short) * attr->name_len;
 		if (t32 && le16_to_cpu(attr->name_off) + t32 > t16)
-			return NULL;
+			goto out;
 
 		return attr;
 	}
 
 	/* Check nonresident fields. */
 	if (attr->non_res != 1)
-		return NULL;
+		goto out;
 
 	/* Can we use memory including attr->nres.valid_size? */
 	if (asize < SIZEOF_NONRESIDENT)
-		return NULL;
+		goto out;
 
 	t16 = le16_to_cpu(attr->nres.run_off);
 	if (t16 > asize)
-		return NULL;
+		goto out;
 
 	t32 = sizeof(short) * attr->name_len;
 	if (t32 && le16_to_cpu(attr->name_off) + t32 > t16)
-		return NULL;
+		goto out;
 
 	/* Check start/end vcn. */
 	if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1)
-		return NULL;
+		goto out;
 
 	data_size = le64_to_cpu(attr->nres.data_size);
 	if (le64_to_cpu(attr->nres.valid_size) > data_size)
-		return NULL;
+		goto out;
 
 	alloc_size = le64_to_cpu(attr->nres.alloc_size);
 	if (data_size > alloc_size)
-		return NULL;
+		goto out;
 
 	t32 = mi->sbi->cluster_mask;
 	if (alloc_size & t32)
-		return NULL;
+		goto out;
 
 	if (!attr->nres.svcn && is_attr_ext(attr)) {
 		/* First segment of sparse/compressed attribute */
 		/* Can we use memory including attr->nres.total_size? */
 		if (asize < SIZEOF_NONRESIDENT_EX)
-			return NULL;
+			goto out;
 
 		tot_size = le64_to_cpu(attr->nres.total_size);
 		if (tot_size & t32)
-			return NULL;
+			goto out;
 
 		if (tot_size > alloc_size)
-			return NULL;
+			goto out;
 	} else {
 		if (attr->nres.c_unit)
-			return NULL;
+			goto out;
 
 		if (alloc_size > mi->sbi->volume.size)
-			return NULL;
+			goto out;
 	}
 
 	return attr;
+
+out:
+	_ntfs_bad_inode(&ni->vfs_inode);
+	return NULL;
 }
 
 /*
  * mi_find_attr - Find the attribute by type and name and id.
  */
-struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr,
-			    enum ATTR_TYPE type, const __le16 *name,
-			    u8 name_len, const __le16 *id)
+struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi,
+			    struct ATTRIB *attr, enum ATTR_TYPE type,
+			    const __le16 *name, u8 name_len, const __le16 *id)
 {
 	u32 type_in = le32_to_cpu(type);
 	u32 atype;
 
 next_attr:
-	attr = mi_enum_attr(mi, attr);
+	attr = mi_enum_attr(ni, mi, attr);
 	if (!attr)
 		return NULL;
 
@@ -467,9 +472,9 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno,
  *
  * Return: Not full constructed attribute or NULL if not possible to create.
  */
-struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
-			      const __le16 *name, u8 name_len, u32 asize,
-			      u16 name_off)
+struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi,
+			      enum ATTR_TYPE type, const __le16 *name,
+			      u8 name_len, u32 asize, u16 name_off)
 {
 	size_t tail;
 	struct ATTRIB *attr;
@@ -488,7 +493,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
 	 * at which we should insert it.
 	 */
 	attr = NULL;
-	while ((attr = mi_enum_attr(mi, attr))) {
+	while ((attr = mi_enum_attr(ni, mi, attr))) {
 		int diff = compare_attr(attr, type, name, name_len, upcase);
 
 		if (diff < 0)
@@ -508,7 +513,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type,
 		tail = used - PtrOffset(rec, attr);
 	}
 
-	id = mi_new_attt_id(mi);
+	id = mi_new_attt_id(ni, mi);
 
 	memmove(Add2Ptr(attr, asize), attr, tail);
 	memset(attr, 0, asize);
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 395e23920632..4414743b638e 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -566,7 +566,7 @@ static void ocfs2_adjust_rightmost_records(handle_t *handle,
 					   struct ocfs2_path *path,
 					   struct ocfs2_extent_rec *insert_rec);
 /*
- * Reset the actual path elements so that we can re-use the structure
+ * Reset the actual path elements so that we can reuse the structure
  * to build another path. Generally, this involves freeing the buffer
  * heads.
  */
@@ -1182,7 +1182,7 @@ static int ocfs2_add_branch(handle_t *handle,
 
 	/*
 	 * If there is a gap before the root end and the real end
-	 * of the righmost leaf block, we need to remove the gap
+	 * of the rightmost leaf block, we need to remove the gap
 	 * between new_cpos and root_end first so that the tree
 	 * is consistent after we add a new branch(it will start
 	 * from new_cpos).
@@ -1238,7 +1238,7 @@ static int ocfs2_add_branch(handle_t *handle,
 
 	/* Note: new_eb_bhs[new_blocks - 1] is the guy which will be
 	 * linked with the rest of the tree.
-	 * conversly, new_eb_bhs[0] is the new bottommost leaf.
+	 * conversely, new_eb_bhs[0] is the new bottommost leaf.
 	 *
 	 * when we leave the loop, new_last_eb_blk will point to the
 	 * newest leaf, and next_blkno will point to the topmost extent
@@ -3712,7 +3712,7 @@ static int ocfs2_try_to_merge_extent(handle_t *handle,
 		 * update split_index here.
 		 *
 		 * When the split_index is zero, we need to merge it to the
-		 * prevoius extent block. It is more efficient and easier
+		 * previous extent block. It is more efficient and easier
 		 * if we do merge_right first and merge_left later.
 		 */
 		ret = ocfs2_merge_rec_right(path, handle, et, split_rec,
@@ -4517,7 +4517,7 @@ static void ocfs2_figure_contig_type(struct ocfs2_extent_tree *et,
 }
 
 /*
- * This should only be called against the righmost leaf extent list.
+ * This should only be called against the rightmost leaf extent list.
  *
  * ocfs2_figure_appending_type() will figure out whether we'll have to
  * insert at the tail of the rightmost leaf.
@@ -6154,6 +6154,9 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb,
 	int status;
 	struct inode *inode = NULL;
 	struct buffer_head *bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_truncate_log *tl;
+	unsigned int tl_count;
 
 	inode = ocfs2_get_system_file_inode(osb,
 					   TRUNCATE_LOG_SYSTEM_INODE,
@@ -6171,6 +6174,18 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb,
 		goto bail;
 	}
 
+	di = (struct ocfs2_dinode *)bh->b_data;
+	tl = &di->id2.i_dealloc;
+	tl_count = le16_to_cpu(tl->tl_count);
+	if (unlikely(tl_count > ocfs2_truncate_recs_per_inode(osb->sb) ||
+		     tl_count == 0)) {
+		status = -EFSCORRUPTED;
+		iput(inode);
+		brelse(bh);
+		mlog_errno(status);
+		goto bail;
+	}
+
 	*tl_inode = inode;
 	*tl_bh    = bh;
 bail:
@@ -6808,27 +6823,27 @@ static int ocfs2_zero_func(handle_t *handle, struct buffer_head *bh)
 	return 0;
 }
 
-void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
-			      unsigned int from, unsigned int to,
-			      struct page *page, int zero, u64 *phys)
+void ocfs2_map_and_dirty_folio(struct inode *inode, handle_t *handle,
+		size_t from, size_t to, struct folio *folio, int zero,
+		u64 *phys)
 {
 	int ret, partial = 0;
-	loff_t start_byte = ((loff_t)page->index << PAGE_SHIFT) + from;
+	loff_t start_byte = folio_pos(folio) + from;
 	loff_t length = to - from;
 
-	ret = ocfs2_map_page_blocks(page, phys, inode, from, to, 0);
+	ret = ocfs2_map_folio_blocks(folio, phys, inode, from, to, 0);
 	if (ret)
 		mlog_errno(ret);
 
 	if (zero)
-		zero_user_segment(page, from, to);
+		folio_zero_segment(folio, from, to);
 
 	/*
 	 * Need to set the buffers we zero'd into uptodate
 	 * here if they aren't - ocfs2_map_page_blocks()
 	 * might've skipped some
 	 */
-	ret = walk_page_buffers(handle, page_buffers(page),
+	ret = walk_page_buffers(handle, folio_buffers(folio),
 				from, to, &partial,
 				ocfs2_zero_func);
 	if (ret < 0)
@@ -6841,92 +6856,88 @@ void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
 	}
 
 	if (!partial)
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 
-	flush_dcache_page(page);
+	flush_dcache_folio(folio);
 }
 
-static void ocfs2_zero_cluster_pages(struct inode *inode, loff_t start,
-				     loff_t end, struct page **pages,
-				     int numpages, u64 phys, handle_t *handle)
+static void ocfs2_zero_cluster_folios(struct inode *inode, loff_t start,
+		loff_t end, struct folio **folios, int numfolios,
+		u64 phys, handle_t *handle)
 {
 	int i;
-	struct page *page;
-	unsigned int from, to = PAGE_SIZE;
 	struct super_block *sb = inode->i_sb;
 
 	BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(sb)));
 
-	if (numpages == 0)
+	if (numfolios == 0)
 		goto out;
 
-	to = PAGE_SIZE;
-	for(i = 0; i < numpages; i++) {
-		page = pages[i];
-
-		from = start & (PAGE_SIZE - 1);
-		if ((end >> PAGE_SHIFT) == page->index)
-			to = end & (PAGE_SIZE - 1);
+	for (i = 0; i < numfolios; i++) {
+		struct folio *folio = folios[i];
+		size_t to = folio_size(folio);
+		size_t from = offset_in_folio(folio, start);
 
-		BUG_ON(from > PAGE_SIZE);
-		BUG_ON(to > PAGE_SIZE);
+		if (to > end - folio_pos(folio))
+			to = end - folio_pos(folio);
 
-		ocfs2_map_and_dirty_page(inode, handle, from, to, page, 1,
-					 &phys);
+		ocfs2_map_and_dirty_folio(inode, handle, from, to, folio, 1,
+				&phys);
 
-		start = (page->index + 1) << PAGE_SHIFT;
+		start = folio_next_index(folio) << PAGE_SHIFT;
 	}
 out:
-	if (pages)
-		ocfs2_unlock_and_free_pages(pages, numpages);
+	if (folios)
+		ocfs2_unlock_and_free_folios(folios, numfolios);
 }
 
-int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end,
-		     struct page **pages, int *num)
+static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end,
+		struct folio **folios, int *num)
 {
-	int numpages, ret = 0;
+	int numfolios, ret = 0;
 	struct address_space *mapping = inode->i_mapping;
 	unsigned long index;
 	loff_t last_page_bytes;
 
 	BUG_ON(start > end);
 
-	numpages = 0;
+	numfolios = 0;
 	last_page_bytes = PAGE_ALIGN(end);
 	index = start >> PAGE_SHIFT;
 	do {
-		pages[numpages] = find_or_create_page(mapping, index, GFP_NOFS);
-		if (!pages[numpages]) {
-			ret = -ENOMEM;
+		folios[numfolios] = __filemap_get_folio(mapping, index,
+				FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS);
+		if (IS_ERR(folios[numfolios])) {
+			ret = PTR_ERR(folios[numfolios]);
 			mlog_errno(ret);
 			goto out;
 		}
 
-		numpages++;
-		index++;
+		index = folio_next_index(folios[numfolios]);
+		numfolios++;
 	} while (index < (last_page_bytes >> PAGE_SHIFT));
 
 out:
 	if (ret != 0) {
-		if (pages)
-			ocfs2_unlock_and_free_pages(pages, numpages);
-		numpages = 0;
+		if (folios)
+			ocfs2_unlock_and_free_folios(folios, numfolios);
+		numfolios = 0;
 	}
 
-	*num = numpages;
+	*num = numfolios;
 
 	return ret;
 }
 
-static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
-				struct page **pages, int *num)
+static int ocfs2_grab_eof_folios(struct inode *inode, loff_t start, loff_t end,
+				struct folio **folios, int *num)
 {
 	struct super_block *sb = inode->i_sb;
 
 	BUG_ON(start >> OCFS2_SB(sb)->s_clustersize_bits !=
 	       (end - 1) >> OCFS2_SB(sb)->s_clustersize_bits);
 
-	return ocfs2_grab_pages(inode, start, end, pages, num);
+	return ocfs2_grab_folios(inode, start, end, folios, num);
 }
 
 /*
@@ -6940,8 +6951,8 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 				  u64 range_start, u64 range_end)
 {
-	int ret = 0, numpages;
-	struct page **pages = NULL;
+	int ret = 0, numfolios;
+	struct folio **folios = NULL;
 	u64 phys;
 	unsigned int ext_flags;
 	struct super_block *sb = inode->i_sb;
@@ -6954,17 +6965,17 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 		return 0;
 
 	/*
-	 * Avoid zeroing pages fully beyond current i_size. It is pointless as
-	 * underlying blocks of those pages should be already zeroed out and
+	 * Avoid zeroing folios fully beyond current i_size. It is pointless as
+	 * underlying blocks of those folios should be already zeroed out and
 	 * page writeback will skip them anyway.
 	 */
 	range_end = min_t(u64, range_end, i_size_read(inode));
 	if (range_start >= range_end)
 		return 0;
 
-	pages = kcalloc(ocfs2_pages_per_cluster(sb),
-			sizeof(struct page *), GFP_NOFS);
-	if (pages == NULL) {
+	folios = kcalloc(ocfs2_pages_per_cluster(sb),
+			sizeof(struct folio *), GFP_NOFS);
+	if (folios == NULL) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
 		goto out;
@@ -6985,18 +6996,18 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 	if (phys == 0 || ext_flags & OCFS2_EXT_UNWRITTEN)
 		goto out;
 
-	ret = ocfs2_grab_eof_pages(inode, range_start, range_end, pages,
-				   &numpages);
+	ret = ocfs2_grab_eof_folios(inode, range_start, range_end, folios,
+				   &numfolios);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
 	}
 
-	ocfs2_zero_cluster_pages(inode, range_start, range_end, pages,
-				 numpages, phys, handle);
+	ocfs2_zero_cluster_folios(inode, range_start, range_end, folios,
+				 numfolios, phys, handle);
 
 	/*
-	 * Initiate writeout of the pages we zero'd here. We don't
+	 * Initiate writeout of the folios we zero'd here. We don't
 	 * wait on them - the truncate_inode_pages() call later will
 	 * do that for us.
 	 */
@@ -7006,7 +7017,7 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 		mlog_errno(ret);
 
 out:
-	kfree(pages);
+	kfree(folios);
 
 	return ret;
 }
@@ -7059,7 +7070,7 @@ void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di)
 int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 					 struct buffer_head *di_bh)
 {
-	int ret, has_data, num_pages = 0;
+	int ret, has_data, num_folios = 0;
 	int need_free = 0;
 	u32 bit_off, num;
 	handle_t *handle;
@@ -7068,7 +7079,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	struct ocfs2_alloc_context *data_ac = NULL;
-	struct page *page = NULL;
+	struct folio *folio = NULL;
 	struct ocfs2_extent_tree et;
 	int did_quota = 0;
 
@@ -7119,12 +7130,12 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 
 		/*
 		 * Save two copies, one for insert, and one that can
-		 * be changed by ocfs2_map_and_dirty_page() below.
+		 * be changed by ocfs2_map_and_dirty_folio() below.
 		 */
 		block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);
 
-		ret = ocfs2_grab_eof_pages(inode, 0, page_end, &page,
-					   &num_pages);
+		ret = ocfs2_grab_eof_folios(inode, 0, page_end, &folio,
+					   &num_folios);
 		if (ret) {
 			mlog_errno(ret);
 			need_free = 1;
@@ -7135,15 +7146,15 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		 * This should populate the 1st page for us and mark
 		 * it up to date.
 		 */
-		ret = ocfs2_read_inline_data(inode, page, di_bh);
+		ret = ocfs2_read_inline_data(inode, folio, di_bh);
 		if (ret) {
 			mlog_errno(ret);
 			need_free = 1;
 			goto out_unlock;
 		}
 
-		ocfs2_map_and_dirty_page(inode, handle, 0, page_end, page, 0,
-					 &phys);
+		ocfs2_map_and_dirty_folio(inode, handle, 0, page_end, folio, 0,
+				&phys);
 	}
 
 	spin_lock(&oi->ip_lock);
@@ -7174,8 +7185,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 	}
 
 out_unlock:
-	if (page)
-		ocfs2_unlock_and_free_pages(&page, num_pages);
+	if (folio)
+		ocfs2_unlock_and_free_folios(&folio, num_folios);
 
 out_commit:
 	if (ret < 0 && did_quota)
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index 4af7abaa6e40..1c0c83362904 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -254,11 +254,9 @@ static inline int ocfs2_is_empty_extent(struct ocfs2_extent_rec *rec)
 	return !rec->e_leaf_clusters;
 }
 
-int ocfs2_grab_pages(struct inode *inode, loff_t start, loff_t end,
-		     struct page **pages, int *num);
-void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
-			      unsigned int from, unsigned int to,
-			      struct page *page, int zero, u64 *phys);
+void ocfs2_map_and_dirty_folio(struct inode *inode, handle_t *handle,
+		size_t from, size_t to, struct folio *folio, int zero,
+		u64 *phys);
 /*
  * Structures which describe a path through a btree, and functions to
  * manipulate them.
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index db72b3e924b3..5bbeb6fbb1ac 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -215,10 +215,9 @@ bail:
 	return err;
 }
 
-int ocfs2_read_inline_data(struct inode *inode, struct page *page,
+int ocfs2_read_inline_data(struct inode *inode, struct folio *folio,
 			   struct buffer_head *di_bh)
 {
-	void *kaddr;
 	loff_t size;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 
@@ -230,7 +229,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 
 	size = i_size_read(inode);
 
-	if (size > PAGE_SIZE ||
+	if (size > folio_size(folio) ||
 	    size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
 		ocfs2_error(inode->i_sb,
 			    "Inode %llu has with inline data has bad size: %Lu\n",
@@ -239,25 +238,18 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 		return -EROFS;
 	}
 
-	kaddr = kmap_atomic(page);
-	if (size)
-		memcpy(kaddr, di->id2.i_data.id_data, size);
-	/* Clear the remaining part of the page */
-	memset(kaddr + size, 0, PAGE_SIZE - size);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr);
-
-	SetPageUptodate(page);
+	folio_fill_tail(folio, 0, di->id2.i_data.id_data, size);
+	folio_mark_uptodate(folio);
 
 	return 0;
 }
 
-static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
+static int ocfs2_readpage_inline(struct inode *inode, struct folio *folio)
 {
 	int ret;
 	struct buffer_head *di_bh = NULL;
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 	BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL));
 
 	ret = ocfs2_read_inode_block(inode, &di_bh);
@@ -266,9 +258,9 @@ static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
 		goto out;
 	}
 
-	ret = ocfs2_read_inline_data(inode, page, di_bh);
+	ret = ocfs2_read_inline_data(inode, folio, di_bh);
 out:
-	unlock_page(page);
+	folio_unlock(folio);
 
 	brelse(di_bh);
 	return ret;
@@ -283,7 +275,7 @@ static int ocfs2_read_folio(struct file *file, struct folio *folio)
 
 	trace_ocfs2_readpage((unsigned long long)oi->ip_blkno, folio->index);
 
-	ret = ocfs2_inode_lock_with_page(inode, NULL, 0, &folio->page);
+	ret = ocfs2_inode_lock_with_folio(inode, NULL, 0, folio);
 	if (ret != 0) {
 		if (ret == AOP_TRUNCATED_PAGE)
 			unlock = 0;
@@ -305,7 +297,7 @@ static int ocfs2_read_folio(struct file *file, struct folio *folio)
 	}
 
 	/*
-	 * i_size might have just been updated as we grabed the meta lock.  We
+	 * i_size might have just been updated as we grabbed the meta lock.  We
 	 * might now be discovering a truncate that hit on another node.
 	 * block_read_full_folio->get_block freaks out if it is asked to read
 	 * beyond the end of a file, so we check here.  Callers
@@ -322,7 +314,7 @@ static int ocfs2_read_folio(struct file *file, struct folio *folio)
 	}
 
 	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		ret = ocfs2_readpage_inline(inode, &folio->page);
+		ret = ocfs2_readpage_inline(inode, folio);
 	else
 		ret = block_read_full_folio(folio, ocfs2_get_block);
 	unlock = 0;
@@ -534,7 +526,7 @@ static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
  *
  * from == to == 0 is code for "zero the entire cluster region"
  */
-static void ocfs2_clear_page_regions(struct page *page,
+static void ocfs2_clear_folio_regions(struct folio *folio,
 				     struct ocfs2_super *osb, u32 cpos,
 				     unsigned from, unsigned to)
 {
@@ -543,7 +535,7 @@ static void ocfs2_clear_page_regions(struct page *page,
 
 	ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end);
 
-	kaddr = kmap_atomic(page);
+	kaddr = kmap_local_folio(folio, 0);
 
 	if (from || to) {
 		if (from > cluster_start)
@@ -554,13 +546,13 @@ static void ocfs2_clear_page_regions(struct page *page,
 		memset(kaddr + cluster_start, 0, cluster_end - cluster_start);
 	}
 
-	kunmap_atomic(kaddr);
+	kunmap_local(kaddr);
 }
 
 /*
  * Nonsparse file systems fully allocate before we get to the write
  * code. This prevents ocfs2_write() from tagging the write as an
- * allocating one, which means ocfs2_map_page_blocks() might try to
+ * allocating one, which means ocfs2_map_folio_blocks() might try to
  * read-in the blocks at the tail of our file. Avoid reading them by
  * testing i_size against each block offset.
  */
@@ -585,11 +577,10 @@ static int ocfs2_should_read_blk(struct inode *inode, struct folio *folio,
  *
  * This will also skip zeroing, which is handled externally.
  */
-int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
+int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno,
 			  struct inode *inode, unsigned int from,
 			  unsigned int to, int new)
 {
-	struct folio *folio = page_folio(page);
 	int ret = 0;
 	struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
 	unsigned int block_end, block_start;
@@ -729,24 +720,24 @@ struct ocfs2_write_ctxt {
 	unsigned int			w_large_pages;
 
 	/*
-	 * Pages involved in this write.
+	 * Folios involved in this write.
 	 *
-	 * w_target_page is the page being written to by the user.
+	 * w_target_folio is the folio being written to by the user.
 	 *
-	 * w_pages is an array of pages which always contains
-	 * w_target_page, and in the case of an allocating write with
+	 * w_folios is an array of folios which always contains
+	 * w_target_folio, and in the case of an allocating write with
 	 * page_size < cluster size, it will contain zero'd and mapped
-	 * pages adjacent to w_target_page which need to be written
+	 * pages adjacent to w_target_folio which need to be written
 	 * out in so that future reads from that region will get
 	 * zero's.
 	 */
-	unsigned int			w_num_pages;
-	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
-	struct page			*w_target_page;
+	unsigned int			w_num_folios;
+	struct folio			*w_folios[OCFS2_MAX_CTXT_PAGES];
+	struct folio			*w_target_folio;
 
 	/*
 	 * w_target_locked is used for page_mkwrite path indicating no unlocking
-	 * against w_target_page in ocfs2_write_end_nolock.
+	 * against w_target_folio in ocfs2_write_end_nolock.
 	 */
 	unsigned int			w_target_locked:1;
 
@@ -771,40 +762,40 @@ struct ocfs2_write_ctxt {
 	unsigned int			w_unwritten_count;
 };
 
-void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
+void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios)
 {
 	int i;
 
-	for(i = 0; i < num_pages; i++) {
-		if (pages[i]) {
-			unlock_page(pages[i]);
-			mark_page_accessed(pages[i]);
-			put_page(pages[i]);
-		}
+	for(i = 0; i < num_folios; i++) {
+		if (!folios[i])
+			continue;
+		folio_unlock(folios[i]);
+		folio_mark_accessed(folios[i]);
+		folio_put(folios[i]);
 	}
 }
 
-static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_folios(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
 	/*
 	 * w_target_locked is only set to true in the page_mkwrite() case.
 	 * The intent is to allow us to lock the target page from write_begin()
-	 * to write_end(). The caller must hold a ref on w_target_page.
+	 * to write_end(). The caller must hold a ref on w_target_folio.
 	 */
 	if (wc->w_target_locked) {
-		BUG_ON(!wc->w_target_page);
-		for (i = 0; i < wc->w_num_pages; i++) {
-			if (wc->w_target_page == wc->w_pages[i]) {
-				wc->w_pages[i] = NULL;
+		BUG_ON(!wc->w_target_folio);
+		for (i = 0; i < wc->w_num_folios; i++) {
+			if (wc->w_target_folio == wc->w_folios[i]) {
+				wc->w_folios[i] = NULL;
 				break;
 			}
 		}
-		mark_page_accessed(wc->w_target_page);
-		put_page(wc->w_target_page);
+		folio_mark_accessed(wc->w_target_folio);
+		folio_put(wc->w_target_folio);
 	}
-	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+	ocfs2_unlock_and_free_folios(wc->w_folios, wc->w_num_folios);
 }
 
 static void ocfs2_free_unwritten_list(struct inode *inode,
@@ -826,7 +817,7 @@ static void ocfs2_free_write_ctxt(struct inode *inode,
 				  struct ocfs2_write_ctxt *wc)
 {
 	ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
-	ocfs2_unlock_pages(wc);
+	ocfs2_unlock_folios(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -869,29 +860,30 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
  * and dirty so they'll be written out (in order to prevent uninitialised
  * block data from leaking). And clear the new bit.
  */
-static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ocfs2_zero_new_buffers(struct folio *folio, size_t from, size_t to)
 {
 	unsigned int block_start, block_end;
 	struct buffer_head *head, *bh;
 
-	BUG_ON(!PageLocked(page));
-	if (!page_has_buffers(page))
+	BUG_ON(!folio_test_locked(folio));
+	head = folio_buffers(folio);
+	if (!head)
 		return;
 
-	bh = head = page_buffers(page);
+	bh = head;
 	block_start = 0;
 	do {
 		block_end = block_start + bh->b_size;
 
 		if (buffer_new(bh)) {
 			if (block_end > from && block_start < to) {
-				if (!PageUptodate(page)) {
+				if (!folio_test_uptodate(folio)) {
 					unsigned start, end;
 
 					start = max(from, block_start);
 					end = min(to, block_end);
 
-					zero_user_segment(page, start, end);
+					folio_zero_segment(folio, start, end);
 					set_buffer_uptodate(bh);
 				}
 
@@ -916,29 +908,26 @@ static void ocfs2_write_failure(struct inode *inode,
 	int i;
 	unsigned from = user_pos & (PAGE_SIZE - 1),
 		to = user_pos + user_len;
-	struct page *tmppage;
 
-	if (wc->w_target_page)
-		ocfs2_zero_new_buffers(wc->w_target_page, from, to);
+	if (wc->w_target_folio)
+		ocfs2_zero_new_buffers(wc->w_target_folio, from, to);
 
-	for(i = 0; i < wc->w_num_pages; i++) {
-		tmppage = wc->w_pages[i];
+	for (i = 0; i < wc->w_num_folios; i++) {
+		struct folio *folio = wc->w_folios[i];
 
-		if (tmppage && page_has_buffers(tmppage)) {
+		if (folio && folio_buffers(folio)) {
 			if (ocfs2_should_order_data(inode))
 				ocfs2_jbd2_inode_add_write(wc->w_handle, inode,
 							   user_pos, user_len);
 
-			block_commit_write(tmppage, from, to);
+			block_commit_write(&folio->page, from, to);
 		}
 	}
 }
 
-static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
-					struct ocfs2_write_ctxt *wc,
-					struct page *page, u32 cpos,
-					loff_t user_pos, unsigned user_len,
-					int new)
+static int ocfs2_prepare_folio_for_write(struct inode *inode, u64 *p_blkno,
+		struct ocfs2_write_ctxt *wc, struct folio *folio, u32 cpos,
+		loff_t user_pos, unsigned user_len, int new)
 {
 	int ret;
 	unsigned int map_from = 0, map_to = 0;
@@ -951,20 +940,19 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
 	/* treat the write as new if the a hole/lseek spanned across
 	 * the page boundary.
 	 */
-	new = new | ((i_size_read(inode) <= page_offset(page)) &&
-			(page_offset(page) <= user_pos));
+	new = new | ((i_size_read(inode) <= folio_pos(folio)) &&
+			(folio_pos(folio) <= user_pos));
 
-	if (page == wc->w_target_page) {
+	if (folio == wc->w_target_folio) {
 		map_from = user_pos & (PAGE_SIZE - 1);
 		map_to = map_from + user_len;
 
 		if (new)
-			ret = ocfs2_map_page_blocks(page, p_blkno, inode,
-						    cluster_start, cluster_end,
-						    new);
+			ret = ocfs2_map_folio_blocks(folio, p_blkno, inode,
+					cluster_start, cluster_end, new);
 		else
-			ret = ocfs2_map_page_blocks(page, p_blkno, inode,
-						    map_from, map_to, new);
+			ret = ocfs2_map_folio_blocks(folio, p_blkno, inode,
+					map_from, map_to, new);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -978,7 +966,7 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
 		}
 	} else {
 		/*
-		 * If we haven't allocated the new page yet, we
+		 * If we haven't allocated the new folio yet, we
 		 * shouldn't be writing it out without copying user
 		 * data. This is likely a math error from the caller.
 		 */
@@ -987,8 +975,8 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
 		map_from = cluster_start;
 		map_to = cluster_end;
 
-		ret = ocfs2_map_page_blocks(page, p_blkno, inode,
-					    cluster_start, cluster_end, new);
+		ret = ocfs2_map_folio_blocks(folio, p_blkno, inode,
+				cluster_start, cluster_end, new);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -996,20 +984,20 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
 	}
 
 	/*
-	 * Parts of newly allocated pages need to be zero'd.
+	 * Parts of newly allocated folios need to be zero'd.
 	 *
 	 * Above, we have also rewritten 'to' and 'from' - as far as
 	 * the rest of the function is concerned, the entire cluster
-	 * range inside of a page needs to be written.
+	 * range inside of a folio needs to be written.
 	 *
-	 * We can skip this if the page is up to date - it's already
+	 * We can skip this if the folio is uptodate - it's already
 	 * been zero'd from being read in as a hole.
 	 */
-	if (new && !PageUptodate(page))
-		ocfs2_clear_page_regions(page, OCFS2_SB(inode->i_sb),
+	if (new && !folio_test_uptodate(folio))
+		ocfs2_clear_folio_regions(folio, OCFS2_SB(inode->i_sb),
 					 cpos, user_data_from, user_data_to);
 
-	flush_dcache_page(page);
+	flush_dcache_folio(folio);
 
 out:
 	return ret;
@@ -1018,11 +1006,9 @@ out:
 /*
  * This function will only grab one clusters worth of pages.
  */
-static int ocfs2_grab_pages_for_write(struct address_space *mapping,
-				      struct ocfs2_write_ctxt *wc,
-				      u32 cpos, loff_t user_pos,
-				      unsigned user_len, int new,
-				      struct page *mmap_page)
+static int ocfs2_grab_folios_for_write(struct address_space *mapping,
+		struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos,
+		unsigned user_len, int new, struct folio *mmap_folio)
 {
 	int ret = 0, i;
 	unsigned long start, target_index, end_index, index;
@@ -1039,7 +1025,7 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 	 * last page of the write.
 	 */
 	if (new) {
-		wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb);
+		wc->w_num_folios = ocfs2_pages_per_cluster(inode->i_sb);
 		start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos);
 		/*
 		 * We need the index *past* the last page we could possibly
@@ -1049,15 +1035,15 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 		last_byte = max(user_pos + user_len, i_size_read(inode));
 		BUG_ON(last_byte < 1);
 		end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1;
-		if ((start + wc->w_num_pages) > end_index)
-			wc->w_num_pages = end_index - start;
+		if ((start + wc->w_num_folios) > end_index)
+			wc->w_num_folios = end_index - start;
 	} else {
-		wc->w_num_pages = 1;
+		wc->w_num_folios = 1;
 		start = target_index;
 	}
 	end_index = (user_pos + user_len - 1) >> PAGE_SHIFT;
 
-	for(i = 0; i < wc->w_num_pages; i++) {
+	for(i = 0; i < wc->w_num_folios; i++) {
 		index = start + i;
 
 		if (index >= target_index && index <= end_index &&
@@ -1067,37 +1053,38 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			 * and wants us to directly use the page
 			 * passed in.
 			 */
-			lock_page(mmap_page);
+			folio_lock(mmap_folio);
 
 			/* Exit and let the caller retry */
-			if (mmap_page->mapping != mapping) {
-				WARN_ON(mmap_page->mapping);
-				unlock_page(mmap_page);
+			if (mmap_folio->mapping != mapping) {
+				WARN_ON(mmap_folio->mapping);
+				folio_unlock(mmap_folio);
 				ret = -EAGAIN;
 				goto out;
 			}
 
-			get_page(mmap_page);
-			wc->w_pages[i] = mmap_page;
+			folio_get(mmap_folio);
+			wc->w_folios[i] = mmap_folio;
 			wc->w_target_locked = true;
 		} else if (index >= target_index && index <= end_index &&
 			   wc->w_type == OCFS2_WRITE_DIRECT) {
 			/* Direct write has no mapping page. */
-			wc->w_pages[i] = NULL;
+			wc->w_folios[i] = NULL;
 			continue;
 		} else {
-			wc->w_pages[i] = find_or_create_page(mapping, index,
-							     GFP_NOFS);
-			if (!wc->w_pages[i]) {
-				ret = -ENOMEM;
+			wc->w_folios[i] = __filemap_get_folio(mapping, index,
+					FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+					GFP_NOFS);
+			if (IS_ERR(wc->w_folios[i])) {
+				ret = PTR_ERR(wc->w_folios[i]);
 				mlog_errno(ret);
 				goto out;
 			}
 		}
-		wait_for_stable_page(wc->w_pages[i]);
+		folio_wait_stable(wc->w_folios[i]);
 
 		if (index == target_index)
-			wc->w_target_page = wc->w_pages[i];
+			wc->w_target_folio = wc->w_folios[i];
 	}
 out:
 	if (ret)
@@ -1181,19 +1168,18 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 	if (!should_zero)
 		p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1);
 
-	for(i = 0; i < wc->w_num_pages; i++) {
+	for (i = 0; i < wc->w_num_folios; i++) {
 		int tmpret;
 
 		/* This is the direct io target page. */
-		if (wc->w_pages[i] == NULL) {
+		if (wc->w_folios[i] == NULL) {
 			p_blkno += (1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits));
 			continue;
 		}
 
-		tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
-						      wc->w_pages[i], cpos,
-						      user_pos, user_len,
-						      should_zero);
+		tmpret = ocfs2_prepare_folio_for_write(inode, &p_blkno, wc,
+				wc->w_folios[i], cpos, user_pos, user_len,
+				should_zero);
 		if (tmpret) {
 			mlog_errno(tmpret);
 			if (ret == 0)
@@ -1472,7 +1458,7 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 {
 	int ret;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct page *page;
+	struct folio *folio;
 	handle_t *handle;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
 
@@ -1483,19 +1469,21 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 		goto out;
 	}
 
-	page = find_or_create_page(mapping, 0, GFP_NOFS);
-	if (!page) {
+	folio = __filemap_get_folio(mapping, 0,
+			FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS);
+	if (IS_ERR(folio)) {
 		ocfs2_commit_trans(osb, handle);
-		ret = -ENOMEM;
+		ret = PTR_ERR(folio);
 		mlog_errno(ret);
 		goto out;
 	}
 	/*
-	 * If we don't set w_num_pages then this page won't get unlocked
+	 * If we don't set w_num_folios then this folio won't get unlocked
 	 * and freed on cleanup of the write context.
 	 */
-	wc->w_pages[0] = wc->w_target_page = page;
-	wc->w_num_pages = 1;
+	wc->w_target_folio = folio;
+	wc->w_folios[0] = folio;
+	wc->w_num_folios = 1;
 
 	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
 				      OCFS2_JOURNAL_ACCESS_WRITE);
@@ -1509,8 +1497,8 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
 		ocfs2_set_inode_data_inline(inode, di);
 
-	if (!PageUptodate(page)) {
-		ret = ocfs2_read_inline_data(inode, page, wc->w_di_bh);
+	if (!folio_test_uptodate(folio)) {
+		ret = ocfs2_read_inline_data(inode, folio, wc->w_di_bh);
 		if (ret) {
 			ocfs2_commit_trans(osb, handle);
 
@@ -1533,9 +1521,8 @@ int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size)
 }
 
 static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
-					  struct inode *inode, loff_t pos,
-					  unsigned len, struct page *mmap_page,
-					  struct ocfs2_write_ctxt *wc)
+		struct inode *inode, loff_t pos, size_t len,
+		struct folio *mmap_folio, struct ocfs2_write_ctxt *wc)
 {
 	int ret, written = 0;
 	loff_t end = pos + len;
@@ -1550,7 +1537,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
 	 * Handle inodes which already have inline data 1st.
 	 */
 	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
-		if (mmap_page == NULL &&
+		if (mmap_folio == NULL &&
 		    ocfs2_size_fits_inline_data(wc->w_di_bh, end))
 			goto do_inline_write;
 
@@ -1574,7 +1561,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
 	 * Check whether the write can fit.
 	 */
 	di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
-	if (mmap_page ||
+	if (mmap_folio ||
 	    end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di))
 		return 0;
 
@@ -1641,9 +1628,9 @@ static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
 }
 
 int ocfs2_write_begin_nolock(struct address_space *mapping,
-			     loff_t pos, unsigned len, ocfs2_write_type_t type,
-			     struct folio **foliop, void **fsdata,
-			     struct buffer_head *di_bh, struct page *mmap_page)
+		loff_t pos, unsigned len, ocfs2_write_type_t type,
+		struct folio **foliop, void **fsdata,
+		struct buffer_head *di_bh, struct folio *mmap_folio)
 {
 	int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS;
 	unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0;
@@ -1666,7 +1653,7 @@ try_again:
 
 	if (ocfs2_supports_inline_data(osb)) {
 		ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len,
-						     mmap_page, wc);
+						     mmap_folio, wc);
 		if (ret == 1) {
 			ret = 0;
 			goto success;
@@ -1718,7 +1705,7 @@ try_again:
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			(long long)i_size_read(inode),
 			le32_to_cpu(di->i_clusters),
-			pos, len, type, mmap_page,
+			pos, len, type, mmap_folio,
 			clusters_to_alloc, extents_to_split);
 
 	/*
@@ -1789,21 +1776,21 @@ try_again:
 	}
 
 	/*
-	 * Fill our page array first. That way we've grabbed enough so
+	 * Fill our folio array first. That way we've grabbed enough so
 	 * that we can zero and flush if we error after adding the
 	 * extent.
 	 */
-	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
-					 cluster_of_pages, mmap_page);
+	ret = ocfs2_grab_folios_for_write(mapping, wc, wc->w_cpos, pos, len,
+			cluster_of_pages, mmap_folio);
 	if (ret) {
 		/*
-		 * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock
-		 * the target page. In this case, we exit with no error and no target
-		 * page. This will trigger the caller, page_mkwrite(), to re-try
-		 * the operation.
+		 * ocfs2_grab_folios_for_write() returns -EAGAIN if it
+		 * could not lock the target folio. In this case, we exit
+		 * with no error and no target folio. This will trigger
+		 * the caller, page_mkwrite(), to re-try the operation.
 		 */
 		if (type == OCFS2_WRITE_MMAP && ret == -EAGAIN) {
-			BUG_ON(wc->w_target_page);
+			BUG_ON(wc->w_target_folio);
 			ret = 0;
 			goto out_quota;
 		}
@@ -1826,7 +1813,7 @@ try_again:
 
 success:
 	if (foliop)
-		*foliop = page_folio(wc->w_target_page);
+		*foliop = wc->w_target_folio;
 	*fsdata = wc;
 	return 0;
 out_quota:
@@ -1845,7 +1832,7 @@ out:
 	 * to VM code.
 	 */
 	if (wc->w_target_locked)
-		unlock_page(mmap_page);
+		folio_unlock(mmap_folio);
 
 	ocfs2_free_write_ctxt(inode, wc);
 
@@ -1924,18 +1911,15 @@ static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
 				   struct ocfs2_dinode *di,
 				   struct ocfs2_write_ctxt *wc)
 {
-	void *kaddr;
-
 	if (unlikely(*copied < len)) {
-		if (!PageUptodate(wc->w_target_page)) {
+		if (!folio_test_uptodate(wc->w_target_folio)) {
 			*copied = 0;
 			return;
 		}
 	}
 
-	kaddr = kmap_atomic(wc->w_target_page);
-	memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied);
-	kunmap_atomic(kaddr);
+	memcpy_from_folio(di->id2.i_data.id_data + pos, wc->w_target_folio,
+			pos, *copied);
 
 	trace_ocfs2_write_end_inline(
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1944,17 +1928,16 @@ static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
 	     le16_to_cpu(di->i_dyn_features));
 }
 
-int ocfs2_write_end_nolock(struct address_space *mapping,
-			   loff_t pos, unsigned len, unsigned copied, void *fsdata)
+int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos,
+		unsigned len, unsigned copied, void *fsdata)
 {
 	int i, ret;
-	unsigned from, to, start = pos & (PAGE_SIZE - 1);
+	size_t from, to, start = pos & (PAGE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_write_ctxt *wc = fsdata;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
 	handle_t *handle = wc->w_handle;
-	struct page *tmppage;
 
 	BUG_ON(!list_empty(&wc->w_unwritten_list));
 
@@ -1973,44 +1956,44 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		goto out_write_size;
 	}
 
-	if (unlikely(copied < len) && wc->w_target_page) {
+	if (unlikely(copied < len) && wc->w_target_folio) {
 		loff_t new_isize;
 
-		if (!PageUptodate(wc->w_target_page))
+		if (!folio_test_uptodate(wc->w_target_folio))
 			copied = 0;
 
 		new_isize = max_t(loff_t, i_size_read(inode), pos + copied);
-		if (new_isize > page_offset(wc->w_target_page))
-			ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
+		if (new_isize > folio_pos(wc->w_target_folio))
+			ocfs2_zero_new_buffers(wc->w_target_folio, start+copied,
 					       start+len);
 		else {
 			/*
-			 * When page is fully beyond new isize (data copy
-			 * failed), do not bother zeroing the page. Invalidate
+			 * When folio is fully beyond new isize (data copy
+			 * failed), do not bother zeroing the folio. Invalidate
 			 * it instead so that writeback does not get confused
 			 * put page & buffer dirty bits into inconsistent
 			 * state.
 			 */
-			block_invalidate_folio(page_folio(wc->w_target_page),
-						0, PAGE_SIZE);
+			block_invalidate_folio(wc->w_target_folio, 0,
+					folio_size(wc->w_target_folio));
 		}
 	}
-	if (wc->w_target_page)
-		flush_dcache_page(wc->w_target_page);
+	if (wc->w_target_folio)
+		flush_dcache_folio(wc->w_target_folio);
 
-	for(i = 0; i < wc->w_num_pages; i++) {
-		tmppage = wc->w_pages[i];
+	for (i = 0; i < wc->w_num_folios; i++) {
+		struct folio *folio = wc->w_folios[i];
 
-		/* This is the direct io target page. */
-		if (tmppage == NULL)
+		/* This is the direct io target folio */
+		if (folio == NULL)
 			continue;
 
-		if (tmppage == wc->w_target_page) {
+		if (folio == wc->w_target_folio) {
 			from = wc->w_target_from;
 			to = wc->w_target_to;
 
-			BUG_ON(from > PAGE_SIZE ||
-			       to > PAGE_SIZE ||
+			BUG_ON(from > folio_size(folio) ||
+			       to > folio_size(folio) ||
 			       to < from);
 		} else {
 			/*
@@ -2019,19 +2002,17 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			 * to flush their entire range.
 			 */
 			from = 0;
-			to = PAGE_SIZE;
+			to = folio_size(folio);
 		}
 
-		if (page_has_buffers(tmppage)) {
+		if (folio_buffers(folio)) {
 			if (handle && ocfs2_should_order_data(inode)) {
-				loff_t start_byte =
-					((loff_t)tmppage->index << PAGE_SHIFT) +
-					from;
+				loff_t start_byte = folio_pos(folio) + from;
 				loff_t length = to - from;
 				ocfs2_jbd2_inode_add_write(handle, inode,
 							   start_byte, length);
 			}
-			block_commit_write(tmppage, from, to);
+			block_commit_write(&folio->page, from, to);
 		}
 	}
 
@@ -2060,7 +2041,7 @@ out:
 	 * this lock and will ask for the page lock when flushing the data.
 	 * put it here to preserve the unlock order.
 	 */
-	ocfs2_unlock_pages(wc);
+	ocfs2_unlock_folios(wc);
 
 	if (handle)
 		ocfs2_commit_trans(osb, handle);
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 1d1b4b7edba0..114efc9111e4 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -8,16 +8,11 @@
 
 #include <linux/fs.h>
 
-handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
-							 struct page *page,
-							 unsigned from,
-							 unsigned to);
-
-int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
+int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno,
 			  struct inode *inode, unsigned int from,
 			  unsigned int to, int new);
 
-void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages);
+void ocfs2_unlock_and_free_folios(struct folio **folios, int num_folios);
 
 int walk_page_buffers(	handle_t *handle,
 			struct buffer_head *head,
@@ -37,11 +32,11 @@ typedef enum {
 } ocfs2_write_type_t;
 
 int ocfs2_write_begin_nolock(struct address_space *mapping,
-			     loff_t pos, unsigned len, ocfs2_write_type_t type,
-			     struct folio **foliop, void **fsdata,
-			     struct buffer_head *di_bh, struct page *mmap_page);
+		loff_t pos, unsigned len, ocfs2_write_type_t type,
+		struct folio **foliop, void **fsdata,
+		struct buffer_head *di_bh, struct folio *mmap_folio);
 
-int ocfs2_read_inline_data(struct inode *inode, struct page *page,
+int ocfs2_read_inline_data(struct inode *inode, struct folio *folio,
 			   struct buffer_head *di_bh);
 int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size);
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4200a0341343..724350925aff 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2004, 2005 Oracle.  All rights reserved.
  */
 
+#include "linux/kstrtox.h"
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/jiffies.h>
@@ -1020,7 +1021,7 @@ fire_callbacks:
 	if (list_empty(&slot->ds_live_item))
 		goto out;
 
-	/* live nodes only go dead after enough consequtive missed
+	/* live nodes only go dead after enough consecutive missed
 	 * samples..  reset the missed counter whenever we see
 	 * activity */
 	if (slot->ds_equal_samples >= o2hb_dead_threshold || gen_changed) {
@@ -1535,10 +1536,11 @@ static int o2hb_read_block_input(struct o2hb_region *reg,
 {
 	unsigned long bytes;
 	char *p = (char *)page;
+	int ret;
 
-	bytes = simple_strtoul(p, &p, 0);
-	if (!p || (*p && (*p != '\n')))
-		return -EINVAL;
+	ret = kstrtoul(p, 0, &bytes);
+	if (ret)
+		return ret;
 
 	/* Heartbeat and fs min / max block sizes are the same. */
 	if (bytes > 4096 || bytes < 512)
@@ -1622,13 +1624,14 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item,
 	struct o2hb_region *reg = to_o2hb_region(item);
 	unsigned long tmp;
 	char *p = (char *)page;
+	int ret;
 
 	if (reg->hr_bdev_file)
 		return -EINVAL;
 
-	tmp = simple_strtoul(p, &p, 0);
-	if (!p || (*p && (*p != '\n')))
-		return -EINVAL;
+	ret = kstrtoul(p, 0, &tmp);
+	if (ret)
+		return ret;
 
 	if (tmp > O2NM_MAX_NODES || tmp == 0)
 		return -ERANGE;
@@ -1776,8 +1779,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
 	if (o2nm_this_node() == O2NM_MAX_NODES)
 		return -EINVAL;
 
-	fd = simple_strtol(p, &p, 0);
-	if (!p || (*p && (*p != '\n')))
+	ret = kstrtol(p, 0, &fd);
+	if (ret < 0)
 		return -EINVAL;
 
 	if (fd < 0 || fd >= INT_MAX)
@@ -2136,10 +2139,11 @@ static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *ite
 {
 	unsigned long tmp;
 	char *p = (char *)page;
+	int ret;
 
-	tmp = simple_strtoul(p, &p, 10);
-	if (!p || (*p && (*p != '\n')))
-                return -EINVAL;
+	ret = kstrtoul(p, 10, &tmp);
+	if (ret)
+		return ret;
 
 	/* this will validate ranges for us. */
 	o2hb_dead_threshold_set((unsigned int) tmp);
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index b73fc42e46ff..630bd5a3dd0d 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -29,7 +29,7 @@
  * just calling printk() so that this can eventually make its way through
  * relayfs along with the debugging messages.  Everything else gets KERN_DEBUG.
  * The inline tests and macro dance give GCC the opportunity to quite cleverly
- * only emit the appropriage printk() when the caller passes in a constant
+ * only emit the appropriate printk() when the caller passes in a constant
  * mask, as is almost always the case.
  *
  * All this bitmask nonsense is managed from the files under
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 8bf17231d7b7..bfb8b456876c 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -23,7 +23,7 @@
  * race between when we see a node start heartbeating and when we connect
  * to it.
  *
- * So nodes that are in this transtion put a hold on the quorum decision
+ * So nodes that are in this transition put a hold on the quorum decision
  * with a counter.  As they fall out of this transition they drop the count
  * and if they're the last, they fire off the decision.
  */
@@ -189,7 +189,7 @@ static void o2quo_clear_hold(struct o2quo_state *qs, u8 node)
 }
 
 /* as a node comes up we delay the quorum decision until we know the fate of
- * the connection.  the hold will be droped in conn_up or hb_down.  it might be
+ * the connection.  the hold will be dropped in conn_up or hb_down.  it might be
  * perpetuated by con_err until hb_down.  if we already have a conn, we might
  * be dropping a hold that conn_up got. */
 void o2quo_hb_up(u8 node)
@@ -256,7 +256,7 @@ void o2quo_hb_still_up(u8 node)
 }
 
 /* This is analogous to hb_up.  as a node's connection comes up we delay the
- * quorum decision until we see it heartbeating.  the hold will be droped in
+ * quorum decision until we see it heartbeating.  the hold will be dropped in
  * hb_up or hb_down.  it might be perpetuated by con_err until hb_down.  if
  * it's already heartbeating we might be dropping a hold that conn_up got.
  * */
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 2b8fa3e782fb..0f46b22561d6 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -5,13 +5,13 @@
  *
  * ----
  *
- * Callers for this were originally written against a very simple synchronus
+ * Callers for this were originally written against a very simple synchronous
  * API.  This implementation reflects those simple callers.  Some day I'm sure
  * we'll need to move to a more robust posting/callback mechanism.
  *
  * Transmit calls pass in kernel virtual addresses and block copying this into
  * the socket's tx buffers via a usual blocking sendmsg.  They'll block waiting
- * for a failed socket to timeout.  TX callers can also pass in a poniter to an
+ * for a failed socket to timeout.  TX callers can also pass in a pointer to an
  * 'int' which gets filled with an errno off the wire in response to the
  * message they send.
  *
@@ -101,7 +101,7 @@ static struct socket *o2net_listen_sock;
  * o2net_wq.  teardown detaches the callbacks before destroying the workqueue.
  * quorum work is queued as sock containers are shutdown.. stop_listening
  * tears down all the node's sock containers, preventing future shutdowns
- * and queued quroum work, before canceling delayed quorum work and
+ * and queued quorum work, before canceling delayed quorum work and
  * destroying the work queue.
  */
 static struct workqueue_struct *o2net_wq;
@@ -1419,7 +1419,7 @@ out:
 	return ret;
 }
 
-/* this work func is triggerd by data ready.  it reads until it can read no
+/* this work func is triggered by data ready.  it reads until it can read no
  * more.  it interprets 0, eof, as fatal.  if data_ready hits while we're doing
  * our work the work struct will be marked and we'll be called again. */
 static void o2net_rx_until_empty(struct work_struct *work)
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index a9b8688aaf30..1873bbbb7e5b 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -32,7 +32,8 @@ void ocfs2_dentry_attach_gen(struct dentry *dentry)
 }
 
 
-static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+static int ocfs2_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				   struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	int ret = 0;    /* if all else fails, just return false */
@@ -44,8 +45,7 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 	inode = d_inode(dentry);
 	osb = OCFS2_SB(dentry->d_sb);
 
-	trace_ocfs2_dentry_revalidate(dentry, dentry->d_name.len,
-				      dentry->d_name.name);
+	trace_ocfs2_dentry_revalidate(dentry, name->len, name->name);
 
 	/* For a negative dentry -
 	 * check the generation number of the parent and compare with the
@@ -53,12 +53,8 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 	 */
 	if (inode == NULL) {
 		unsigned long gen = (unsigned long) dentry->d_fsdata;
-		unsigned long pgen;
-		spin_lock(&dentry->d_lock);
-		pgen = OCFS2_I(d_inode(dentry->d_parent))->ip_dir_lock_gen;
-		spin_unlock(&dentry->d_lock);
-		trace_ocfs2_dentry_revalidate_negative(dentry->d_name.len,
-						       dentry->d_name.name,
+		unsigned long pgen = OCFS2_I(dir)->ip_dir_lock_gen;
+		trace_ocfs2_dentry_revalidate_negative(name->len, name->name,
 						       pgen, gen);
 		if (gen != pgen)
 			goto bail;
diff --git a/fs/ocfs2/dlm/dlmapi.h b/fs/ocfs2/dlm/dlmapi.h
index 847a52dcbe7d..1969db8ffa9c 100644
--- a/fs/ocfs2/dlm/dlmapi.h
+++ b/fs/ocfs2/dlm/dlmapi.h
@@ -118,7 +118,7 @@ struct dlm_lockstatus {
 #define LKM_VALBLK       0x00000100  /* lock value block request */
 #define LKM_NOQUEUE      0x00000200  /* non blocking request */
 #define LKM_CONVERT      0x00000400  /* conversion request */
-#define LKM_NODLCKWT     0x00000800  /* this lock wont deadlock (U) */
+#define LKM_NODLCKWT     0x00000800  /* this lock won't deadlock (U) */
 #define LKM_UNLOCK       0x00001000  /* deallocate this lock */
 #define LKM_CANCEL       0x00002000  /* cancel conversion request */
 #define LKM_DEQALL       0x00004000  /* remove all locks held by proc (U) */
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index e9ef4e2b0e75..fe4fdd09bae3 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -14,6 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/export.h>
+#include <linux/string_choices.h>
 
 #include "../cluster/heartbeat.h"
 #include "../cluster/nodemanager.h"
@@ -90,12 +91,12 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res)
 	       buf, res->owner, res->state);
 	printk("  last used: %lu, refcnt: %u, on purge list: %s\n",
 	       res->last_used, kref_read(&res->refs),
-	       list_empty(&res->purge) ? "no" : "yes");
+	       str_no_yes(list_empty(&res->purge)));
 	printk("  on dirty list: %s, on reco list: %s, "
 	       "migrating pending: %s\n",
-	       list_empty(&res->dirty) ? "no" : "yes",
-	       list_empty(&res->recovering) ? "no" : "yes",
-	       res->migration_pending ? "yes" : "no");
+	       str_no_yes(list_empty(&res->dirty)),
+	       str_no_yes(list_empty(&res->recovering)),
+	       str_yes_no(res->migration_pending));
 	printk("  inflight locks: %d, asts reserved: %d\n",
 	       res->inflight_locks, atomic_read(&res->asts_reserved));
 	dlm_print_lockres_refmap(res);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index d610da8e2f24..86bb1a03bcc1 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -21,7 +21,7 @@
 #include <linux/inet.h>
 #include <linux/spinlock.h>
 #include <linux/delay.h>
-
+#include <linux/string_choices.h>
 
 #include "../cluster/heartbeat.h"
 #include "../cluster/nodemanager.h"
@@ -2859,7 +2859,7 @@ static int dlm_mark_lockres_migrating(struct dlm_ctxt *dlm,
 	dlm_lockres_release_ast(dlm, res);
 
 	mlog(0, "about to wait on migration_wq, dirty=%s\n",
-	       res->state & DLM_LOCK_RES_DIRTY ? "yes" : "no");
+	       str_yes_no(res->state & DLM_LOCK_RES_DIRTY));
 	/* if the extra ref we just put was the final one, this
 	 * will pass thru immediately.  otherwise, we need to wait
 	 * for the last ast to finish. */
@@ -2869,12 +2869,12 @@ again:
 		   msecs_to_jiffies(1000));
 	if (ret < 0) {
 		mlog(0, "woken again: migrating? %s, dead? %s\n",
-		       res->state & DLM_LOCK_RES_MIGRATING ? "yes":"no",
-		       test_bit(target, dlm->domain_map) ? "no":"yes");
+		       str_yes_no(res->state & DLM_LOCK_RES_MIGRATING),
+		       str_no_yes(test_bit(target, dlm->domain_map)));
 	} else {
 		mlog(0, "all is well: migrating? %s, dead? %s\n",
-		       res->state & DLM_LOCK_RES_MIGRATING ? "yes":"no",
-		       test_bit(target, dlm->domain_map) ? "no":"yes");
+		       str_yes_no(res->state & DLM_LOCK_RES_MIGRATING),
+		       str_no_yes(test_bit(target, dlm->domain_map)));
 	}
 	if (!dlm_migration_can_proceed(dlm, res, target)) {
 		mlog(0, "trying again...\n");
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 50da8af988c1..67fc62a49a76 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -22,7 +22,7 @@
 #include <linux/timer.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
-
+#include <linux/string_choices.h>
 
 #include "../cluster/heartbeat.h"
 #include "../cluster/nodemanager.h"
@@ -207,7 +207,7 @@ void dlm_complete_recovery_thread(struct dlm_ctxt *dlm)
  * 1) all recovery threads cluster wide will work on recovering
  *    ONE node at a time
  * 2) negotiate who will take over all the locks for the dead node.
- *    thats right... ALL the locks.
+ *    that's right... ALL the locks.
  * 3) once a new master is chosen, everyone scans all locks
  *    and moves aside those mastered by the dead guy
  * 4) each of these locks should be locked until recovery is done
@@ -581,8 +581,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 							   msecs_to_jiffies(1000));
 					mlog(0, "waited 1 sec for %u, "
 					     "dead? %s\n", ndata->node_num,
-					     dlm_is_node_dead(dlm, ndata->node_num) ?
-					     "yes" : "no");
+					     str_yes_no(dlm_is_node_dead(dlm, ndata->node_num)));
 				} else {
 					/* -ENOMEM on the other node */
 					mlog(0, "%s: node %u returned "
@@ -677,7 +676,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		spin_unlock(&dlm_reco_state_lock);
 
 		mlog(0, "pass #%d, all_nodes_done?: %s\n", ++pass,
-		     all_nodes_done?"yes":"no");
+		     str_yes_no(all_nodes_done));
 		if (all_nodes_done) {
 			int ret;
 
@@ -1469,7 +1468,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 		 * The first one is handled at the end of this function. The
 		 * other two are handled in the worker thread after locks have
 		 * been attached. Yes, we don't wait for purge time to match
-		 * kref_init. The lockres will still have atleast one ref
+		 * kref_init. The lockres will still have at least one ref
 		 * added because it is in the hash __dlm_insert_lockres() */
 		extra_refs++;
 
@@ -1735,7 +1734,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				spin_unlock(&res->spinlock);
 			}
 		} else {
-			/* put.. incase we are not the master */
+			/* put.. in case we are not the master */
 			spin_unlock(&res->spinlock);
 			dlm_lockres_put(res);
 		}
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 7fc0e920eda7..2a7f36643895 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -20,6 +20,7 @@
 
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/fs_context.h>
 #include <linux/pagemap.h>
 #include <linux/types.h>
 #include <linux/slab.h>
@@ -506,9 +507,7 @@ bail:
 	return status;
 }
 
-static int dlmfs_fill_super(struct super_block * sb,
-			    void * data,
-			    int silent)
+static int dlmfs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize = PAGE_SIZE;
@@ -556,17 +555,27 @@ static const struct inode_operations dlmfs_file_inode_operations = {
 	.setattr	= dlmfs_file_setattr,
 };
 
-static struct dentry *dlmfs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int dlmfs_get_tree(struct fs_context *fc)
 {
-	return mount_nodev(fs_type, flags, data, dlmfs_fill_super);
+	return get_tree_nodev(fc, dlmfs_fill_super);
+}
+
+static const struct fs_context_operations dlmfs_context_ops = {
+	.get_tree       = dlmfs_get_tree,
+};
+
+static int dlmfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &dlmfs_context_ops;
+
+	return 0;
 }
 
 static struct file_system_type dlmfs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "ocfs2_dlmfs",
-	.mount		= dlmfs_mount,
 	.kill_sb	= kill_litter_super,
+	.init_fs_context = dlmfs_init_fs_context,
 };
 MODULE_ALIAS_FS("ocfs2_dlmfs");
 
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 764ecbd5ad41..92a6149da9c1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -19,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/quotaops.h>
 #include <linux/sched/signal.h>
+#include <linux/string_choices.h>
 
 #define MLOG_MASK_PREFIX ML_DLM_GLUE
 #include <cluster/masklog.h>
@@ -794,7 +795,7 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res)
 
 /*
  * Keep a list of processes who have interest in a lockres.
- * Note: this is now only uesed for check recursive cluster locking.
+ * Note: this is now only used for check recursive cluster locking.
  */
 static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
 				   struct ocfs2_lock_holder *oh)
@@ -2529,30 +2530,28 @@ bail:
 
 /*
  * This is working around a lock inversion between tasks acquiring DLM
- * locks while holding a page lock and the downconvert thread which
- * blocks dlm lock acquiry while acquiring page locks.
+ * locks while holding a folio lock and the downconvert thread which
+ * blocks dlm lock acquiry while acquiring folio locks.
  *
- * ** These _with_page variantes are only intended to be called from aop
- * methods that hold page locks and return a very specific *positive* error
+ * ** These _with_folio variants are only intended to be called from aop
+ * methods that hold folio locks and return a very specific *positive* error
  * code that aop methods pass up to the VFS -- test for errors with != 0. **
  *
  * The DLM is called such that it returns -EAGAIN if it would have
  * blocked waiting for the downconvert thread.  In that case we unlock
- * our page so the downconvert thread can make progress.  Once we've
+ * our folio so the downconvert thread can make progress.  Once we've
  * done this we have to return AOP_TRUNCATED_PAGE so the aop method
  * that called us can bubble that back up into the VFS who will then
  * immediately retry the aop call.
  */
-int ocfs2_inode_lock_with_page(struct inode *inode,
-			      struct buffer_head **ret_bh,
-			      int ex,
-			      struct page *page)
+int ocfs2_inode_lock_with_folio(struct inode *inode,
+		struct buffer_head **ret_bh, int ex, struct folio *folio)
 {
 	int ret;
 
 	ret = ocfs2_inode_lock_full(inode, ret_bh, ex, OCFS2_LOCK_NONBLOCK);
 	if (ret == -EAGAIN) {
-		unlock_page(page);
+		folio_unlock(folio);
 		/*
 		 * If we can't get inode lock immediately, we should not return
 		 * directly here, since this will lead to a softlockup problem.
@@ -2630,7 +2629,7 @@ void ocfs2_inode_unlock(struct inode *inode,
 }
 
 /*
- * This _tracker variantes are introduced to deal with the recursive cluster
+ * This _tracker variants are introduced to deal with the recursive cluster
  * locking issue. The idea is to keep track of a lock holder on the stack of
  * the current process. If there's a lock holder on the stack, we know the
  * task context is already protected by cluster locking. Currently, they're
@@ -2735,7 +2734,7 @@ void ocfs2_inode_unlock_tracker(struct inode *inode,
 	struct ocfs2_lock_res *lockres;
 
 	lockres = &OCFS2_I(inode)->ip_inode_lockres;
-	/* had_lock means that the currect process already takes the cluster
+	/* had_lock means that the current process already takes the cluster
 	 * lock previously.
 	 * If had_lock is 1, we have nothing to do here.
 	 * If had_lock is 0, we will release the lock.
@@ -3802,9 +3801,9 @@ recheck:
 	 * set when the ast is received for an upconvert just before the
 	 * OCFS2_LOCK_BUSY flag is cleared. Now if the fs received a bast
 	 * on the heels of the ast, we want to delay the downconvert just
-	 * enough to allow the up requestor to do its task. Because this
+	 * enough to allow the up requester to do its task. Because this
 	 * lock is in the blocked queue, the lock will be downconverted
-	 * as soon as the requestor is done with the lock.
+	 * as soon as the requester is done with the lock.
 	 */
 	if (lockres->l_flags & OCFS2_LOCK_UPCONVERT_FINISHING)
 		goto leave_requeue;
@@ -4339,7 +4338,7 @@ unqueue:
 		ocfs2_schedule_blocked_lock(osb, lockres);
 
 	mlog(ML_BASTS, "lockres %s, requeue = %s.\n", lockres->l_name,
-	     ctl.requeue ? "yes" : "no");
+	     str_yes_no(ctl.requeue));
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
 
 	if (ctl.unblock_action != UNBLOCK_CONTINUE
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index e5da5809ed95..a3ebd7303ea2 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -137,10 +137,8 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 			 int ex,
 			 int arg_flags,
 			 int subclass);
-int ocfs2_inode_lock_with_page(struct inode *inode,
-			      struct buffer_head **ret_bh,
-			      int ex,
-			      struct page *page);
+int ocfs2_inode_lock_with_folio(struct inode *inode,
+		struct buffer_head **ret_bh, int ex, struct folio *folio);
 /* Variants without special locking class or flags */
 #define ocfs2_inode_lock_full(i, r, e, f)\
 		ocfs2_inode_lock_full_nested(i, r, e, f, OI_LS_NORMAL)
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index f7672472fa82..930150ed5db1 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -435,6 +435,16 @@ static int ocfs2_get_clusters_nocache(struct inode *inode,
 		}
 	}
 
+	if (le16_to_cpu(el->l_next_free_rec) > le16_to_cpu(el->l_count)) {
+		ocfs2_error(inode->i_sb,
+			    "Inode %lu has an invalid extent (next_free_rec %u, count %u)\n",
+			    inode->i_ino,
+			    le16_to_cpu(el->l_next_free_rec),
+			    le16_to_cpu(el->l_count));
+		ret = -EROFS;
+		goto out;
+	}
+
 	i = ocfs2_search_extent_list(el, v_cluster);
 	if (i == -1) {
 		/*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 957ced628eb1..e54f2c4b5a90 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -782,11 +782,11 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 		goto out_commit_trans;
 	}
 
-	/* Get the offsets within the page that we want to zero */
-	zero_from = abs_from & (PAGE_SIZE - 1);
-	zero_to = abs_to & (PAGE_SIZE - 1);
+	/* Get the offsets within the folio that we want to zero */
+	zero_from = offset_in_folio(folio, abs_from);
+	zero_to = offset_in_folio(folio, abs_to);
 	if (!zero_to)
-		zero_to = PAGE_SIZE;
+		zero_to = folio_size(folio);
 
 	trace_ocfs2_write_zero_page(
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 2cc5c99fe941..12e5d1f73325 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -200,6 +200,20 @@ bail:
 	return inode;
 }
 
+static int ocfs2_dinode_has_extents(struct ocfs2_dinode *di)
+{
+	/* inodes flagged with other stuff in id2 */
+	if (di->i_flags & (OCFS2_SUPER_BLOCK_FL | OCFS2_LOCAL_ALLOC_FL |
+			   OCFS2_CHAIN_FL | OCFS2_DEALLOC_FL))
+		return 0;
+	/* i_flags doesn't indicate when id2 is a fast symlink */
+	if (S_ISLNK(di->i_mode) && di->i_size && di->i_clusters == 0)
+		return 0;
+	if (di->i_dyn_features & OCFS2_INLINE_DATA_FL)
+		return 0;
+
+	return 1;
+}
 
 /*
  * here's how inodes get read from disk:
@@ -1122,7 +1136,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 
 	dquot_drop(inode);
 
-	/* To preven remote deletes we hold open lock before, now it
+	/* To prevent remote deletes we hold open lock before, now it
 	 * is time to unlock PR and EX open locks. */
 	ocfs2_open_unlock(inode);
 
@@ -1437,7 +1451,7 @@ static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
 	 * Call ocfs2_validate_meta_ecc() first since it has ecc repair
 	 * function, but we should not return error immediately when ecc
 	 * validation fails, because the reason is quite likely the invalid
-	 * inode number inputed.
+	 * inode number inputted.
 	 */
 	rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
 	if (rc) {
@@ -1547,6 +1561,16 @@ static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
 		     le32_to_cpu(di->i_fs_generation));
 	}
 
+	if (ocfs2_dinode_has_extents(di) &&
+	    le16_to_cpu(di->id2.i_list.l_next_free_rec) > le16_to_cpu(di->id2.i_list.l_count)) {
+		di->id2.i_list.l_next_free_rec = di->id2.i_list.l_count;
+		changed = 1;
+		mlog(ML_ERROR,
+		     "Filecheck: reset dinode #%llu: l_next_free_rec to %u\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le16_to_cpu(di->id2.i_list.l_next_free_rec));
+	}
+
 	if (changed || ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check)) {
 		ocfs2_compute_meta_ecc(sb, bh->b_data, &di->i_check);
 		mark_buffer_dirty(bh);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 71beef7f8a60..7ae96fb8807a 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -796,7 +796,7 @@ bail:
 /*
  * OCFS2_IOC_INFO handles an array of requests passed from userspace.
  *
- * ocfs2_info_handle() recevies a large info aggregation, grab and
+ * ocfs2_info_handle() receives a large info aggregation, grab and
  * validate the request count from header, then break it into small
  * pieces, later specific handlers can handle them one by one.
  *
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 1bf188b6866a..f1b4b3e611cb 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1956,7 +1956,7 @@ bail:
 
 /*
  * Scan timer should get fired every ORPHAN_SCAN_SCHEDULE_TIMEOUT. Add some
- * randomness to the timeout to minimize multple nodes firing the timer at the
+ * randomness to the timeout to minimize multiple nodes firing the timer at the
  * same time.
  */
 static inline unsigned long ocfs2_orphan_scan_timeout(void)
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 6ef4cb045ccd..6a314e9f2b49 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -44,13 +44,13 @@ static vm_fault_t ocfs2_fault(struct vm_fault *vmf)
 }
 
 static vm_fault_t __ocfs2_page_mkwrite(struct file *file,
-			struct buffer_head *di_bh, struct page *page)
+			struct buffer_head *di_bh, struct folio *folio)
 {
 	int err;
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
-	loff_t pos = page_offset(page);
+	loff_t pos = folio_pos(folio);
 	unsigned int len = PAGE_SIZE;
 	pgoff_t last_index;
 	struct folio *locked_folio = NULL;
@@ -72,9 +72,9 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file,
 	 *
 	 * Let VM retry with these cases.
 	 */
-	if ((page->mapping != inode->i_mapping) ||
-	    (!PageUptodate(page)) ||
-	    (page_offset(page) >= size))
+	if ((folio->mapping != inode->i_mapping) ||
+	    !folio_test_uptodate(folio) ||
+	    (pos >= size))
 		goto out;
 
 	/*
@@ -87,11 +87,11 @@ static vm_fault_t __ocfs2_page_mkwrite(struct file *file,
 	 * worry about ocfs2_write_begin() skipping some buffer reads
 	 * because the "write" would invalidate their data.
 	 */
-	if (page->index == last_index)
+	if (folio->index == last_index)
 		len = ((size - 1) & ~PAGE_MASK) + 1;
 
 	err = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP,
-				       &locked_folio, &fsdata, di_bh, page);
+				       &locked_folio, &fsdata, di_bh, folio);
 	if (err) {
 		if (err != -ENOSPC)
 			mlog_errno(err);
@@ -112,7 +112,7 @@ out:
 
 static vm_fault_t ocfs2_page_mkwrite(struct vm_fault *vmf)
 {
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct buffer_head *di_bh = NULL;
 	sigset_t oldset;
@@ -141,7 +141,7 @@ static vm_fault_t ocfs2_page_mkwrite(struct vm_fault *vmf)
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, page);
+	ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, folio);
 
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index f9d6a4f9ca92..369c7d27befd 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -492,7 +492,7 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
 	bg = (struct ocfs2_group_desc *)gd_bh->b_data;
 
 	/*
-	 * moving goal is not allowd to start with a group desc blok(#0 blk)
+	 * moving goal is not allowed to start with a group desc blok(#0 blk)
 	 * let's compromise to the latter cluster.
 	 */
 	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
@@ -658,7 +658,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 
 	/*
 	 * probe the victim cluster group to find a proper
-	 * region to fit wanted movement, it even will perfrom
+	 * region to fit wanted movement, it even will perform
 	 * a best-effort attempt by compromising to a threshold
 	 * around the goal.
 	 */
@@ -920,7 +920,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context)
 	}
 
 	/*
-	 * rememer ip_xattr_sem also needs to be held if necessary
+	 * remember ip_xattr_sem also needs to be held if necessary
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
@@ -1022,7 +1022,7 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
 	context->range = &range;
 
 	/*
-	 * ok, the default theshold for the defragmentation
+	 * ok, the default threshold for the defragmentation
 	 * is 1M, since our maximum clustersize was 1M also.
 	 * any thought?
 	 */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 5550f8afa438..0ec63a1a94b8 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -508,7 +508,6 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 				struct inode *inode,
 				dev_t dev,
 				struct buffer_head **new_fe_bh,
-				struct buffer_head *parent_fe_bh,
 				handle_t *handle,
 				struct ocfs2_alloc_context *inode_ac,
 				u64 fe_blkno, u64 suballoc_loc, u16 suballoc_bit)
@@ -641,8 +640,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 	}
 
 	return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
-				    parent_fe_bh, handle, inode_ac,
-				    fe_blkno, suballoc_loc, suballoc_bit);
+				    handle, inode_ac, fe_blkno,
+				    suballoc_loc, suballoc_bit);
 }
 
 static int ocfs2_mkdir(struct mnt_idmap *idmap,
@@ -2576,7 +2575,7 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
 	clear_nlink(inode);
 	/* do the real work now. */
 	status = __ocfs2_mknod_locked(dir, inode,
-				      0, &new_di_bh, parent_di_bh, handle,
+				      0, &new_di_bh, handle,
 				      inode_ac, di_blkno, suballoc_loc,
 				      suballoc_bit);
 	if (status < 0) {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index c93689b568fe..e8e94599e907 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -132,7 +132,7 @@
  * well as the name of the cluster being joined.
  * mount.ocfs2 must pass in a matching stack name.
  *
- * If not set, the classic stack will be used.  This is compatbile with
+ * If not set, the classic stack will be used.  This is compatible with
  * all older versions.
  */
 #define OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK	0x0080
@@ -143,7 +143,7 @@
 /* Support for extended attributes */
 #define OCFS2_FEATURE_INCOMPAT_XATTR		0x0200
 
-/* Support for indexed directores */
+/* Support for indexed directories */
 #define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS	0x0400
 
 /* Metadata checksum and error correction */
@@ -156,7 +156,7 @@
 #define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG	0x2000
 
 /*
- * Incompat bit to indicate useable clusterinfo with stackflags for all
+ * Incompat bit to indicate usable clusterinfo with stackflags for all
  * cluster stacks (userspace adnd o2cb). If this bit is set,
  * INCOMPAT_USERSPACE_STACK becomes superfluous and thus should not be set.
  */
@@ -1083,7 +1083,7 @@ struct ocfs2_xattr_block {
 		struct ocfs2_xattr_header xb_header; /* xattr header if this
 							block contains xattr */
 		struct ocfs2_xattr_tree_root xb_root;/* xattr tree root if this
-							block cotains xattr
+							block contains xattr
 							tree. */
 	} xb_attrs;
 };
diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h
index 9680797bc531..2de2f8733283 100644
--- a/fs/ocfs2/ocfs2_ioctl.h
+++ b/fs/ocfs2/ocfs2_ioctl.h
@@ -215,7 +215,7 @@ struct ocfs2_move_extents {
 							   movement less likely
 							   to fail, may make fs
 							   even more fragmented */
-#define OCFS2_MOVE_EXT_FL_COMPLETE	(0x00000004)	/* Move or defragmenation
+#define OCFS2_MOVE_EXT_FL_COMPLETE	(0x00000004)	/* Move or defragmentation
 							   completely gets done.
 							 */
 
diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h
index 8ac357ce6a30..9b234c03d693 100644
--- a/fs/ocfs2/ocfs2_lockid.h
+++ b/fs/ocfs2/ocfs2_lockid.h
@@ -93,7 +93,7 @@ static char *ocfs2_lock_type_strings[] = {
 	[OCFS2_LOCK_TYPE_DATA] = "Data",
 	[OCFS2_LOCK_TYPE_SUPER] = "Super",
 	[OCFS2_LOCK_TYPE_RENAME] = "Rename",
-	/* Need to differntiate from [R]ename.. serializing writes is the
+	/* Need to differentiate from [R]ename.. serializing writes is the
 	 * important job it does, anyway. */
 	[OCFS2_LOCK_TYPE_RW] = "Write/Read",
 	[OCFS2_LOCK_TYPE_DENTRY] = "Dentry",
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 0511c69c9fde..54ed1495de9a 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1658,34 +1658,34 @@ TRACE_EVENT(ocfs2_remount,
 );
 
 TRACE_EVENT(ocfs2_fill_super,
-	TP_PROTO(void *sb, void *data, int silent),
-	TP_ARGS(sb, data, silent),
+	TP_PROTO(void *sb, void *fc, int silent),
+	TP_ARGS(sb, fc, silent),
 	TP_STRUCT__entry(
 		__field(void *, sb)
-		__field(void *, data)
+		__field(void *, fc)
 		__field(int, silent)
 	),
 	TP_fast_assign(
 		__entry->sb = sb;
-		__entry->data = data;
+		__entry->fc = fc;
 		__entry->silent = silent;
 	),
 	TP_printk("%p %p %d", __entry->sb,
-		  __entry->data, __entry->silent)
+		  __entry->fc, __entry->silent)
 );
 
 TRACE_EVENT(ocfs2_parse_options,
-	TP_PROTO(int is_remount, char *options),
-	TP_ARGS(is_remount, options),
+	TP_PROTO(int is_remount, const char *option),
+	TP_ARGS(is_remount, option),
 	TP_STRUCT__entry(
 		__field(int, is_remount)
-		__string(options, options)
+		__string(option, option)
 	),
 	TP_fast_assign(
 		__entry->is_remount = is_remount;
-		__assign_str(options);
+		__assign_str(option);
 	),
-	TP_printk("%d %s", __entry->is_remount, __get_str(options))
+	TP_printk("%d %s", __entry->is_remount, __get_str(option))
 );
 
 DEFINE_OCFS2_POINTER_EVENT(ocfs2_put_super);
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 3404e7a30c33..15d9acd456ec 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -761,6 +761,11 @@ static int ocfs2_release_dquot(struct dquot *dquot)
 	handle = ocfs2_start_trans(osb,
 		ocfs2_calc_qdel_credits(dquot->dq_sb, dquot->dq_id.type));
 	if (IS_ERR(handle)) {
+		/*
+		 * Mark dquot as inactive to avoid endless cycle in
+		 * quota_release_workfn().
+		 */
+		clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
 		status = PTR_ERR(handle);
 		mlog_errno(status);
 		goto out_ilock;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 004393b13c0a..8f732742b26e 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2420,7 +2420,7 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb,
 		 *
 		 * If we will insert a new one, this is easy and only happens
 		 * during adding refcounted flag to the extent, so we don't
-		 * have a chance of spliting. We just need one record.
+		 * have a chance of splitting. We just need one record.
 		 *
 		 * If the refcount rec already exists, that would be a little
 		 * complicated. we may have to:
@@ -2610,11 +2610,11 @@ static inline unsigned int ocfs2_cow_align_length(struct super_block *sb,
 /*
  * Calculate out the start and number of virtual clusters we need to CoW.
  *
- * cpos is vitual start cluster position we want to do CoW in a
+ * cpos is virtual start cluster position we want to do CoW in a
  * file and write_len is the cluster length.
  * max_cpos is the place where we want to stop CoW intentionally.
  *
- * Normal we will start CoW from the beginning of extent record cotaining cpos.
+ * Normal we will start CoW from the beginning of extent record containing cpos.
  * We try to break up extents on boundaries of MAX_CONTIG_BYTES so that we
  * get good I/O from the resulting extent tree.
  */
@@ -2902,7 +2902,6 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 	int ret = 0, partial;
 	struct super_block *sb = inode->i_sb;
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
-	struct page *page;
 	pgoff_t page_index;
 	unsigned int from, to;
 	loff_t offset, end, map_end;
@@ -2921,6 +2920,7 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 		end = i_size_read(inode);
 
 	while (offset < end) {
+		struct folio *folio;
 		page_index = offset >> PAGE_SHIFT;
 		map_end = ((loff_t)page_index + 1) << PAGE_SHIFT;
 		if (map_end > end)
@@ -2933,9 +2933,10 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 			to = map_end & (PAGE_SIZE - 1);
 
 retry:
-		page = find_or_create_page(mapping, page_index, GFP_NOFS);
-		if (!page) {
-			ret = -ENOMEM;
+		folio = __filemap_get_folio(mapping, page_index,
+				FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS);
+		if (IS_ERR(folio)) {
+			ret = PTR_ERR(folio);
 			mlog_errno(ret);
 			break;
 		}
@@ -2945,9 +2946,9 @@ retry:
 		 * page, so write it back.
 		 */
 		if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) {
-			if (PageDirty(page)) {
-				unlock_page(page);
-				put_page(page);
+			if (folio_test_dirty(folio)) {
+				folio_unlock(folio);
+				folio_put(folio);
 
 				ret = filemap_write_and_wait_range(mapping,
 						offset, map_end - 1);
@@ -2955,9 +2956,7 @@ retry:
 			}
 		}
 
-		if (!PageUptodate(page)) {
-			struct folio *folio = page_folio(page);
-
+		if (!folio_test_uptodate(folio)) {
 			ret = block_read_full_folio(folio, ocfs2_get_block);
 			if (ret) {
 				mlog_errno(ret);
@@ -2966,8 +2965,8 @@ retry:
 			folio_lock(folio);
 		}
 
-		if (page_has_buffers(page)) {
-			ret = walk_page_buffers(handle, page_buffers(page),
+		if (folio_buffers(folio)) {
+			ret = walk_page_buffers(handle, folio_buffers(folio),
 						from, to, &partial,
 						ocfs2_clear_cow_buffer);
 			if (ret) {
@@ -2976,14 +2975,12 @@ retry:
 			}
 		}
 
-		ocfs2_map_and_dirty_page(inode,
-					 handle, from, to,
-					 page, 0, &new_block);
-		mark_page_accessed(page);
+		ocfs2_map_and_dirty_folio(inode, handle, from, to,
+				folio, 0, &new_block);
+		folio_mark_accessed(folio);
 unlock:
-		unlock_page(page);
-		put_page(page);
-		page = NULL;
+		folio_unlock(folio);
+		folio_put(folio);
 		offset = map_end;
 		if (ret)
 			break;
diff --git a/fs/ocfs2/reservations.h b/fs/ocfs2/reservations.h
index ec8101ef5717..4fce17180342 100644
--- a/fs/ocfs2/reservations.h
+++ b/fs/ocfs2/reservations.h
@@ -31,7 +31,7 @@ struct ocfs2_alloc_reservation {
 
 #define	OCFS2_RESV_FLAG_INUSE	0x01	/* Set when r_node is part of a btree */
 #define	OCFS2_RESV_FLAG_TMP	0x02	/* Temporary reservation, will be
-					 * destroyed immedately after use */
+					 * destroyed immediately after use */
 #define	OCFS2_RESV_FLAG_DIR	0x04	/* Reservation is for an unindexed
 					 * directory btree */
 
@@ -125,7 +125,7 @@ int ocfs2_resmap_resv_bits(struct ocfs2_reservation_map *resmap,
 /**
  * ocfs2_resmap_claimed_bits() - Tell the reservation code that bits were used.
  * @resmap: reservations bitmap
- * @resv: optional reservation to recalulate based on new bitmap
+ * @resv: optional reservation to recalculate based on new bitmap
  * @cstart: start of allocation in clusters
  * @clen: end of allocation in clusters.
  *
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 10157d9d7a9c..f58e891aa2da 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -227,7 +227,7 @@ static int o2cb_dlm_lock_status(struct ocfs2_dlm_lksb *lksb)
 }
 
 /*
- * o2dlm aways has a "valid" LVB. If the dlm loses track of the LVB
+ * o2dlm always has a "valid" LVB. If the dlm loses track of the LVB
  * contents, it will zero out the LVB.  Thus the caller can always trust
  * the contents.
  */
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 20aa37b67cfb..ddd761cf44c8 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -650,7 +650,7 @@ error:
  * and easier to preserve the name.
  */
 
-static struct ctl_table ocfs2_nm_table[] = {
+static const struct ctl_table ocfs2_nm_table[] = {
 	{
 		.procname	= "hb_ctl_path",
 		.data		= ocfs2_hb_ctl_path,
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index 02ab072c528a..5486a6dce70a 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -210,7 +210,7 @@ struct ocfs2_stack_operations {
 		     struct file_lock *fl);
 
 	/*
-	 * This is an optoinal debugging hook.  If provided, the
+	 * This is an optional debugging hook.  If provided, the
 	 * stack can dump debugging information about this lock.
 	 */
 	void (*dump_lksb)(struct ocfs2_dlm_lksb *lksb);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c79b4291777f..8bb5022f3082 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -19,10 +19,10 @@
 #include <linux/blkdev.h>
 #include <linux/socket.h>
 #include <linux/inet.h>
-#include <linux/parser.h>
+#include <linux/fs_parser.h>
+#include <linux/fs_context.h>
 #include <linux/crc32.h>
 #include <linux/debugfs.h>
-#include <linux/mount.h>
 #include <linux/seq_file.h>
 #include <linux/quotaops.h>
 #include <linux/signal.h>
@@ -80,17 +80,15 @@ struct mount_options
 	unsigned int	resv_level;
 	int		dir_resv_level;
 	char		cluster_stack[OCFS2_STACK_LABEL_LEN + 1];
+	bool		user_stack;
 };
 
-static int ocfs2_parse_options(struct super_block *sb, char *options,
-			       struct mount_options *mopt,
-			       int is_remount);
+static int ocfs2_parse_param(struct fs_context *fc, struct fs_parameter *param);
 static int ocfs2_check_set_options(struct super_block *sb,
 				   struct mount_options *options);
 static int ocfs2_show_options(struct seq_file *s, struct dentry *root);
 static void ocfs2_put_super(struct super_block *sb);
 static int ocfs2_mount_volume(struct super_block *sb);
-static int ocfs2_remount(struct super_block *sb, int *flags, char *data);
 static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err);
 static int ocfs2_initialize_mem_caches(void);
 static void ocfs2_free_mem_caches(void);
@@ -135,7 +133,6 @@ static const struct super_operations ocfs2_sops = {
 	.evict_inode	= ocfs2_evict_inode,
 	.sync_fs	= ocfs2_sync_fs,
 	.put_super	= ocfs2_put_super,
-	.remount_fs	= ocfs2_remount,
 	.show_options   = ocfs2_show_options,
 	.quota_read	= ocfs2_quota_read,
 	.quota_write	= ocfs2_quota_write,
@@ -144,15 +141,10 @@ static const struct super_operations ocfs2_sops = {
 
 enum {
 	Opt_barrier,
-	Opt_err_panic,
-	Opt_err_ro,
+	Opt_errors,
 	Opt_intr,
-	Opt_nointr,
-	Opt_hb_none,
-	Opt_hb_local,
-	Opt_hb_global,
-	Opt_data_ordered,
-	Opt_data_writeback,
+	Opt_heartbeat,
+	Opt_data,
 	Opt_atime_quantum,
 	Opt_slot,
 	Opt_commit,
@@ -160,52 +152,64 @@ enum {
 	Opt_localflocks,
 	Opt_stack,
 	Opt_user_xattr,
-	Opt_nouser_xattr,
 	Opt_inode64,
 	Opt_acl,
-	Opt_noacl,
 	Opt_usrquota,
 	Opt_grpquota,
-	Opt_coherency_buffered,
-	Opt_coherency_full,
+	Opt_coherency,
 	Opt_resv_level,
 	Opt_dir_resv_level,
 	Opt_journal_async_commit,
-	Opt_err_cont,
-	Opt_err,
 };
 
-static const match_table_t tokens = {
-	{Opt_barrier, "barrier=%u"},
-	{Opt_err_panic, "errors=panic"},
-	{Opt_err_ro, "errors=remount-ro"},
-	{Opt_intr, "intr"},
-	{Opt_nointr, "nointr"},
-	{Opt_hb_none, OCFS2_HB_NONE},
-	{Opt_hb_local, OCFS2_HB_LOCAL},
-	{Opt_hb_global, OCFS2_HB_GLOBAL},
-	{Opt_data_ordered, "data=ordered"},
-	{Opt_data_writeback, "data=writeback"},
-	{Opt_atime_quantum, "atime_quantum=%u"},
-	{Opt_slot, "preferred_slot=%u"},
-	{Opt_commit, "commit=%u"},
-	{Opt_localalloc, "localalloc=%d"},
-	{Opt_localflocks, "localflocks"},
-	{Opt_stack, "cluster_stack=%s"},
-	{Opt_user_xattr, "user_xattr"},
-	{Opt_nouser_xattr, "nouser_xattr"},
-	{Opt_inode64, "inode64"},
-	{Opt_acl, "acl"},
-	{Opt_noacl, "noacl"},
-	{Opt_usrquota, "usrquota"},
-	{Opt_grpquota, "grpquota"},
-	{Opt_coherency_buffered, "coherency=buffered"},
-	{Opt_coherency_full, "coherency=full"},
-	{Opt_resv_level, "resv_level=%u"},
-	{Opt_dir_resv_level, "dir_resv_level=%u"},
-	{Opt_journal_async_commit, "journal_async_commit"},
-	{Opt_err_cont, "errors=continue"},
-	{Opt_err, NULL}
+static const struct constant_table ocfs2_param_errors[] = {
+	{"panic",	OCFS2_MOUNT_ERRORS_PANIC},
+	{"remount-ro",	OCFS2_MOUNT_ERRORS_ROFS},
+	{"continue",	OCFS2_MOUNT_ERRORS_CONT},
+	{}
+};
+
+static const struct constant_table ocfs2_param_heartbeat[] = {
+	{"local",	OCFS2_MOUNT_HB_LOCAL},
+	{"none",	OCFS2_MOUNT_HB_NONE},
+	{"global",	OCFS2_MOUNT_HB_GLOBAL},
+	{}
+};
+
+static const struct constant_table ocfs2_param_data[] = {
+	{"writeback",	OCFS2_MOUNT_DATA_WRITEBACK},
+	{"ordered",	0},
+	{}
+};
+
+static const struct constant_table ocfs2_param_coherency[] = {
+	{"buffered",	OCFS2_MOUNT_COHERENCY_BUFFERED},
+	{"full",	0},
+	{}
+};
+
+static const struct fs_parameter_spec ocfs2_param_spec[] = {
+	fsparam_u32	("barrier",	Opt_barrier),
+	fsparam_enum	("errors",	Opt_errors,	ocfs2_param_errors),
+	fsparam_flag_no	("intr",	Opt_intr),
+	fsparam_enum	("heartbeat",	Opt_heartbeat,	ocfs2_param_heartbeat),
+	fsparam_enum	("data",	Opt_data,	ocfs2_param_data),
+	fsparam_u32	("atime_quantum", Opt_atime_quantum),
+	fsparam_u32	("preferred_slot", Opt_slot),
+	fsparam_u32	("commit",	Opt_commit),
+	fsparam_s32	("localalloc",	Opt_localalloc),
+	fsparam_flag	("localflocks",	Opt_localflocks),
+	fsparam_string	("cluster_stack", Opt_stack),
+	fsparam_flag_no	("user_xattr",	Opt_user_xattr),
+	fsparam_flag	("inode64",	Opt_inode64),
+	fsparam_flag_no	("acl",		Opt_acl),
+	fsparam_flag	("usrquota",	Opt_usrquota),
+	fsparam_flag	("grpquota",	Opt_grpquota),
+	fsparam_enum	("coherency",	Opt_coherency,	ocfs2_param_coherency),
+	fsparam_u32	("resv_level",	Opt_resv_level),
+	fsparam_u32	("dir_resv_level",	Opt_dir_resv_level),
+	fsparam_flag	("journal_async_commit", Opt_journal_async_commit),
+	{}
 };
 
 #ifdef CONFIG_DEBUG_FS
@@ -600,32 +604,32 @@ static unsigned long long ocfs2_max_file_offset(unsigned int bbits,
 	return (((unsigned long long)bytes) << bitshift) - trim;
 }
 
-static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
+static int ocfs2_reconfigure(struct fs_context *fc)
 {
 	int incompat_features;
 	int ret = 0;
-	struct mount_options parsed_options;
+	struct mount_options *parsed_options = fc->fs_private;
+	struct super_block *sb = fc->root->d_sb;
 	struct ocfs2_super *osb = OCFS2_SB(sb);
 	u32 tmp;
 
 	sync_filesystem(sb);
 
-	if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
-	    !ocfs2_check_set_options(sb, &parsed_options)) {
+	if (!ocfs2_check_set_options(sb, parsed_options)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
 		OCFS2_MOUNT_HB_NONE;
-	if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
+	if ((osb->s_mount_opt & tmp) != (parsed_options->mount_opt & tmp)) {
 		ret = -EINVAL;
 		mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n");
 		goto out;
 	}
 
 	if ((osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) !=
-	    (parsed_options.mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) {
+	    (parsed_options->mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) {
 		ret = -EINVAL;
 		mlog(ML_ERROR, "Cannot change data mode on remount\n");
 		goto out;
@@ -634,16 +638,16 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 	/* Probably don't want this on remount; it might
 	 * mess with other nodes */
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) &&
-	    (parsed_options.mount_opt & OCFS2_MOUNT_INODE64)) {
+	    (parsed_options->mount_opt & OCFS2_MOUNT_INODE64)) {
 		ret = -EINVAL;
 		mlog(ML_ERROR, "Cannot enable inode64 on remount\n");
 		goto out;
 	}
 
 	/* We're going to/from readonly mode. */
-	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
+	if ((bool)(fc->sb_flags & SB_RDONLY) != sb_rdonly(sb)) {
 		/* Disable quota accounting before remounting RO */
-		if (*flags & SB_RDONLY) {
+		if (fc->sb_flags & SB_RDONLY) {
 			ret = ocfs2_susp_quotas(osb, 0);
 			if (ret < 0)
 				goto out;
@@ -657,7 +661,7 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 			goto unlock_osb;
 		}
 
-		if (*flags & SB_RDONLY) {
+		if (fc->sb_flags & SB_RDONLY) {
 			sb->s_flags |= SB_RDONLY;
 			osb->osb_flags |= OCFS2_OSB_SOFT_RO;
 		} else {
@@ -678,11 +682,11 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
 			sb->s_flags &= ~SB_RDONLY;
 			osb->osb_flags &= ~OCFS2_OSB_SOFT_RO;
 		}
-		trace_ocfs2_remount(sb->s_flags, osb->osb_flags, *flags);
+		trace_ocfs2_remount(sb->s_flags, osb->osb_flags, fc->sb_flags);
 unlock_osb:
 		spin_unlock(&osb->osb_lock);
 		/* Enable quota accounting after remounting RW */
-		if (!ret && !(*flags & SB_RDONLY)) {
+		if (!ret && !(fc->sb_flags & SB_RDONLY)) {
 			if (sb_any_quota_suspended(sb))
 				ret = ocfs2_susp_quotas(osb, 1);
 			else
@@ -701,11 +705,11 @@ unlock_osb:
 	if (!ret) {
 		/* Only save off the new mount options in case of a successful
 		 * remount. */
-		osb->s_mount_opt = parsed_options.mount_opt;
-		osb->s_atime_quantum = parsed_options.atime_quantum;
-		osb->preferred_slot = parsed_options.slot;
-		if (parsed_options.commit_interval)
-			osb->osb_commit_interval = parsed_options.commit_interval;
+		osb->s_mount_opt = parsed_options->mount_opt;
+		osb->s_atime_quantum = parsed_options->atime_quantum;
+		osb->preferred_slot = parsed_options->slot;
+		if (parsed_options->commit_interval)
+			osb->osb_commit_interval = parsed_options->commit_interval;
 
 		if (!ocfs2_is_hard_readonly(osb))
 			ocfs2_set_journal_params(osb);
@@ -966,23 +970,18 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
 	}
 }
 
-static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
+static int ocfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct dentry *root;
 	int status, sector_size;
-	struct mount_options parsed_options;
+	struct mount_options *parsed_options = fc->fs_private;
 	struct inode *inode = NULL;
 	struct ocfs2_super *osb = NULL;
 	struct buffer_head *bh = NULL;
 	char nodestr[12];
 	struct ocfs2_blockcheck_stats stats;
 
-	trace_ocfs2_fill_super(sb, data, silent);
-
-	if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) {
-		status = -EINVAL;
-		goto out;
-	}
+	trace_ocfs2_fill_super(sb, fc, fc->sb_flags & SB_SILENT);
 
 	/* probe for superblock */
 	status = ocfs2_sb_probe(sb, &bh, &sector_size, &stats);
@@ -999,24 +998,24 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	osb = OCFS2_SB(sb);
 
-	if (!ocfs2_check_set_options(sb, &parsed_options)) {
+	if (!ocfs2_check_set_options(sb, parsed_options)) {
 		status = -EINVAL;
 		goto out_super;
 	}
-	osb->s_mount_opt = parsed_options.mount_opt;
-	osb->s_atime_quantum = parsed_options.atime_quantum;
-	osb->preferred_slot = parsed_options.slot;
-	osb->osb_commit_interval = parsed_options.commit_interval;
+	osb->s_mount_opt = parsed_options->mount_opt;
+	osb->s_atime_quantum = parsed_options->atime_quantum;
+	osb->preferred_slot = parsed_options->slot;
+	osb->osb_commit_interval = parsed_options->commit_interval;
 
-	ocfs2_la_set_sizes(osb, parsed_options.localalloc_opt);
-	osb->osb_resv_level = parsed_options.resv_level;
-	osb->osb_dir_resv_level = parsed_options.resv_level;
-	if (parsed_options.dir_resv_level == -1)
-		osb->osb_dir_resv_level = parsed_options.resv_level;
+	ocfs2_la_set_sizes(osb, parsed_options->localalloc_opt);
+	osb->osb_resv_level = parsed_options->resv_level;
+	osb->osb_dir_resv_level = parsed_options->resv_level;
+	if (parsed_options->dir_resv_level == -1)
+		osb->osb_dir_resv_level = parsed_options->resv_level;
 	else
-		osb->osb_dir_resv_level = parsed_options.dir_resv_level;
+		osb->osb_dir_resv_level = parsed_options->dir_resv_level;
 
-	status = ocfs2_verify_userspace_stack(osb, &parsed_options);
+	status = ocfs2_verify_userspace_stack(osb, parsed_options);
 	if (status)
 		goto out_super;
 
@@ -1180,27 +1179,72 @@ out:
 	return status;
 }
 
-static struct dentry *ocfs2_mount(struct file_system_type *fs_type,
-			int flags,
-			const char *dev_name,
-			void *data)
+static int ocfs2_get_tree(struct fs_context *fc)
+{
+	return get_tree_bdev(fc, ocfs2_fill_super);
+}
+
+static void ocfs2_free_fc(struct fs_context *fc)
 {
-	return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super);
+	kfree(fc->fs_private);
+}
+
+static const struct fs_context_operations ocfs2_context_ops = {
+	.parse_param	= ocfs2_parse_param,
+	.get_tree	= ocfs2_get_tree,
+	.reconfigure	= ocfs2_reconfigure,
+	.free		= ocfs2_free_fc,
+};
+
+static int ocfs2_init_fs_context(struct fs_context *fc)
+{
+	struct mount_options *mopt;
+
+	mopt = kzalloc(sizeof(struct mount_options), GFP_KERNEL);
+	if (!mopt)
+		return -EINVAL;
+
+	mopt->commit_interval = 0;
+	mopt->mount_opt = OCFS2_MOUNT_NOINTR;
+	mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
+	mopt->slot = OCFS2_INVALID_SLOT;
+	mopt->localalloc_opt = -1;
+	mopt->cluster_stack[0] = '\0';
+	mopt->resv_level = OCFS2_DEFAULT_RESV_LEVEL;
+	mopt->dir_resv_level = -1;
+
+	fc->fs_private = mopt;
+	fc->ops = &ocfs2_context_ops;
+
+	return 0;
 }
 
 static struct file_system_type ocfs2_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "ocfs2",
-	.mount          = ocfs2_mount,
 	.kill_sb        = kill_block_super,
 	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
-	.next           = NULL
+	.next           = NULL,
+	.init_fs_context = ocfs2_init_fs_context,
+	.parameters	= ocfs2_param_spec,
 };
 MODULE_ALIAS_FS("ocfs2");
 
 static int ocfs2_check_set_options(struct super_block *sb,
 				   struct mount_options *options)
 {
+	if (options->user_stack == 0) {
+		u32 tmp;
+
+		/* Ensure only one heartbeat mode */
+		tmp = options->mount_opt & (OCFS2_MOUNT_HB_LOCAL |
+					    OCFS2_MOUNT_HB_GLOBAL |
+					    OCFS2_MOUNT_HB_NONE);
+		if (hweight32(tmp) != 1) {
+			mlog(ML_ERROR, "Invalid heartbeat mount options\n");
+			return 0;
+		}
+	}
 	if (options->mount_opt & OCFS2_MOUNT_USRQUOTA &&
 	    !OCFS2_HAS_RO_COMPAT_FEATURE(sb,
 					 OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
@@ -1232,241 +1276,142 @@ static int ocfs2_check_set_options(struct super_block *sb,
 	return 1;
 }
 
-static int ocfs2_parse_options(struct super_block *sb,
-			       char *options,
-			       struct mount_options *mopt,
-			       int is_remount)
+static int ocfs2_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
-	int status, user_stack = 0;
-	char *p;
-	u32 tmp;
-	int token, option;
-	substring_t args[MAX_OPT_ARGS];
-
-	trace_ocfs2_parse_options(is_remount, options ? options : "(none)");
-
-	mopt->commit_interval = 0;
-	mopt->mount_opt = OCFS2_MOUNT_NOINTR;
-	mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
-	mopt->slot = OCFS2_INVALID_SLOT;
-	mopt->localalloc_opt = -1;
-	mopt->cluster_stack[0] = '\0';
-	mopt->resv_level = OCFS2_DEFAULT_RESV_LEVEL;
-	mopt->dir_resv_level = -1;
-
-	if (!options) {
-		status = 1;
-		goto bail;
-	}
-
-	while ((p = strsep(&options, ",")) != NULL) {
-		if (!*p)
-			continue;
-
-		token = match_token(p, tokens, args);
-		switch (token) {
-		case Opt_hb_local:
-			mopt->mount_opt |= OCFS2_MOUNT_HB_LOCAL;
-			break;
-		case Opt_hb_none:
-			mopt->mount_opt |= OCFS2_MOUNT_HB_NONE;
-			break;
-		case Opt_hb_global:
-			mopt->mount_opt |= OCFS2_MOUNT_HB_GLOBAL;
-			break;
-		case Opt_barrier:
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option)
-				mopt->mount_opt |= OCFS2_MOUNT_BARRIER;
-			else
-				mopt->mount_opt &= ~OCFS2_MOUNT_BARRIER;
-			break;
-		case Opt_intr:
-			mopt->mount_opt &= ~OCFS2_MOUNT_NOINTR;
-			break;
-		case Opt_nointr:
+	struct fs_parse_result result;
+	int opt;
+	struct mount_options *mopt = fc->fs_private;
+	bool is_remount = (fc->purpose & FS_CONTEXT_FOR_RECONFIGURE);
+
+	trace_ocfs2_parse_options(is_remount, param->key);
+
+	opt = fs_parse(fc, ocfs2_param_spec, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_heartbeat:
+		mopt->mount_opt |= result.uint_32;
+		break;
+	case Opt_barrier:
+		if (result.uint_32)
+			mopt->mount_opt |= OCFS2_MOUNT_BARRIER;
+		else
+			mopt->mount_opt &= ~OCFS2_MOUNT_BARRIER;
+		break;
+	case Opt_intr:
+		if (result.negated)
 			mopt->mount_opt |= OCFS2_MOUNT_NOINTR;
-			break;
-		case Opt_err_panic:
-			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT;
-			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS;
-			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_PANIC;
-			break;
-		case Opt_err_ro:
-			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT;
-			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
-			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_ROFS;
-			break;
-		case Opt_err_cont:
-			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS;
-			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
-			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_CONT;
-			break;
-		case Opt_data_ordered:
-			mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK;
-			break;
-		case Opt_data_writeback:
-			mopt->mount_opt |= OCFS2_MOUNT_DATA_WRITEBACK;
-			break;
-		case Opt_user_xattr:
-			mopt->mount_opt &= ~OCFS2_MOUNT_NOUSERXATTR;
-			break;
-		case Opt_nouser_xattr:
+		else
+			mopt->mount_opt &= ~OCFS2_MOUNT_NOINTR;
+		break;
+	case Opt_errors:
+		mopt->mount_opt &= ~(OCFS2_MOUNT_ERRORS_CONT |
+				     OCFS2_MOUNT_ERRORS_ROFS |
+				     OCFS2_MOUNT_ERRORS_PANIC);
+		mopt->mount_opt |= result.uint_32;
+		break;
+	case Opt_data:
+		mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK;
+		mopt->mount_opt |= result.uint_32;
+		break;
+	case Opt_user_xattr:
+		if (result.negated)
 			mopt->mount_opt |= OCFS2_MOUNT_NOUSERXATTR;
-			break;
-		case Opt_atime_quantum:
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option >= 0)
-				mopt->atime_quantum = option;
-			break;
-		case Opt_slot:
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option)
-				mopt->slot = (u16)option;
-			break;
-		case Opt_commit:
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option < 0)
-				return 0;
-			if (option == 0)
-				option = JBD2_DEFAULT_MAX_COMMIT_AGE;
-			mopt->commit_interval = HZ * option;
-			break;
-		case Opt_localalloc:
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option >= 0)
-				mopt->localalloc_opt = option;
-			break;
-		case Opt_localflocks:
-			/*
-			 * Changing this during remount could race
-			 * flock() requests, or "unbalance" existing
-			 * ones (e.g., a lock is taken in one mode but
-			 * dropped in the other). If users care enough
-			 * to flip locking modes during remount, we
-			 * could add a "local" flag to individual
-			 * flock structures for proper tracking of
-			 * state.
-			 */
-			if (!is_remount)
-				mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS;
-			break;
-		case Opt_stack:
-			/* Check both that the option we were passed
-			 * is of the right length and that it is a proper
-			 * string of the right length.
-			 */
-			if (((args[0].to - args[0].from) !=
-			     OCFS2_STACK_LABEL_LEN) ||
-			    (strnlen(args[0].from,
-				     OCFS2_STACK_LABEL_LEN) !=
-			     OCFS2_STACK_LABEL_LEN)) {
-				mlog(ML_ERROR,
-				     "Invalid cluster_stack option\n");
-				status = 0;
-				goto bail;
-			}
-			memcpy(mopt->cluster_stack, args[0].from,
-			       OCFS2_STACK_LABEL_LEN);
-			mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
-			/*
-			 * Open code the memcmp here as we don't have
-			 * an osb to pass to
-			 * ocfs2_userspace_stack().
-			 */
-			if (memcmp(mopt->cluster_stack,
-				   OCFS2_CLASSIC_CLUSTER_STACK,
-				   OCFS2_STACK_LABEL_LEN))
-				user_stack = 1;
-			break;
-		case Opt_inode64:
-			mopt->mount_opt |= OCFS2_MOUNT_INODE64;
-			break;
-		case Opt_usrquota:
-			mopt->mount_opt |= OCFS2_MOUNT_USRQUOTA;
-			break;
-		case Opt_grpquota:
-			mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA;
-			break;
-		case Opt_coherency_buffered:
-			mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED;
-			break;
-		case Opt_coherency_full:
-			mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED;
-			break;
-		case Opt_acl:
-			mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL;
-			mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL;
-			break;
-		case Opt_noacl:
+		else
+			mopt->mount_opt &= ~OCFS2_MOUNT_NOUSERXATTR;
+		break;
+	case Opt_atime_quantum:
+		mopt->atime_quantum = result.uint_32;
+		break;
+	case Opt_slot:
+		if (result.uint_32)
+			mopt->slot = (u16)result.uint_32;
+		break;
+	case Opt_commit:
+		if (result.uint_32 == 0)
+			mopt->commit_interval = HZ * JBD2_DEFAULT_MAX_COMMIT_AGE;
+		else
+			mopt->commit_interval = HZ * result.uint_32;
+		break;
+	case Opt_localalloc:
+		if (result.int_32 >= 0)
+			mopt->localalloc_opt = result.int_32;
+		break;
+	case Opt_localflocks:
+		/*
+		 * Changing this during remount could race flock() requests, or
+		 * "unbalance" existing ones (e.g., a lock is taken in one mode
+		 * but dropped in the other). If users care enough to flip
+		 * locking modes during remount, we could add a "local" flag to
+		 * individual flock structures for proper tracking of state.
+		 */
+		if (!is_remount)
+			mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS;
+		break;
+	case Opt_stack:
+		/* Check both that the option we were passed is of the right
+		 * length and that it is a proper string of the right length.
+		 */
+		if (strlen(param->string) != OCFS2_STACK_LABEL_LEN) {
+			mlog(ML_ERROR, "Invalid cluster_stack option\n");
+			return -EINVAL;
+		}
+		memcpy(mopt->cluster_stack, param->string, OCFS2_STACK_LABEL_LEN);
+		mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
+		/*
+		 * Open code the memcmp here as we don't have an osb to pass
+		 * to ocfs2_userspace_stack().
+		 */
+		if (memcmp(mopt->cluster_stack,
+			   OCFS2_CLASSIC_CLUSTER_STACK,
+			   OCFS2_STACK_LABEL_LEN))
+			mopt->user_stack = 1;
+		break;
+	case Opt_inode64:
+		mopt->mount_opt |= OCFS2_MOUNT_INODE64;
+		break;
+	case Opt_usrquota:
+		mopt->mount_opt |= OCFS2_MOUNT_USRQUOTA;
+		break;
+	case Opt_grpquota:
+		mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA;
+		break;
+	case Opt_coherency:
+		mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED;
+		mopt->mount_opt |= result.uint_32;
+		break;
+	case Opt_acl:
+		if (result.negated) {
 			mopt->mount_opt |= OCFS2_MOUNT_NO_POSIX_ACL;
 			mopt->mount_opt &= ~OCFS2_MOUNT_POSIX_ACL;
+		} else {
+			mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL;
+			mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL;
+		}
+		break;
+	case Opt_resv_level:
+		if (is_remount)
 			break;
-		case Opt_resv_level:
-			if (is_remount)
-				break;
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option >= OCFS2_MIN_RESV_LEVEL &&
-			    option < OCFS2_MAX_RESV_LEVEL)
-				mopt->resv_level = option;
-			break;
-		case Opt_dir_resv_level:
-			if (is_remount)
-				break;
-			if (match_int(&args[0], &option)) {
-				status = 0;
-				goto bail;
-			}
-			if (option >= OCFS2_MIN_RESV_LEVEL &&
-			    option < OCFS2_MAX_RESV_LEVEL)
-				mopt->dir_resv_level = option;
-			break;
-		case Opt_journal_async_commit:
-			mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
+		if (result.uint_32 >= OCFS2_MIN_RESV_LEVEL &&
+		    result.uint_32 < OCFS2_MAX_RESV_LEVEL)
+			mopt->resv_level = result.uint_32;
+		break;
+	case Opt_dir_resv_level:
+		if (is_remount)
 			break;
-		default:
-			mlog(ML_ERROR,
-			     "Unrecognized mount option \"%s\" "
-			     "or missing value\n", p);
-			status = 0;
-			goto bail;
-		}
-	}
-
-	if (user_stack == 0) {
-		/* Ensure only one heartbeat mode */
-		tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL |
-					 OCFS2_MOUNT_HB_GLOBAL |
-					 OCFS2_MOUNT_HB_NONE);
-		if (hweight32(tmp) != 1) {
-			mlog(ML_ERROR, "Invalid heartbeat mount options\n");
-			status = 0;
-			goto bail;
-		}
+		if (result.uint_32 >= OCFS2_MIN_RESV_LEVEL &&
+		    result.uint_32 < OCFS2_MAX_RESV_LEVEL)
+			mopt->dir_resv_level = result.uint_32;
+		break;
+	case Opt_journal_async_commit:
+		mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
+		break;
+	default:
+		return -EINVAL;
 	}
 
-	status = 1;
-
-bail:
-	return status;
+	return 0;
 }
 
 static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
@@ -1858,7 +1803,7 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	osb = OCFS2_SB(sb);
 	BUG_ON(!osb);
 
-	/* Remove file check sysfs related directores/files,
+	/* Remove file check sysfs related directories/files,
 	 * and wait for the pending file check operations */
 	ocfs2_filecheck_remove_sysfs(osb);
 
@@ -2340,7 +2285,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
 			mlog(ML_ERROR, "found superblock with incorrect block "
 			     "size bits: found %u, should be 9, 10, 11, or 12\n",
 			     blksz_bits);
-		} else if ((1 << le32_to_cpu(blksz_bits)) != blksz) {
+		} else if ((1 << blksz_bits) != blksz) {
 			mlog(ML_ERROR, "found superblock with incorrect block "
 			     "size: found %u, should be %u\n", 1 << blksz_bits, blksz);
 		} else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) !=
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index d4c5fdcfa1e4..ad8be3300b49 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -54,31 +54,27 @@
 
 static int ocfs2_fast_symlink_read_folio(struct file *f, struct folio *folio)
 {
-	struct page *page = &folio->page;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct buffer_head *bh = NULL;
 	int status = ocfs2_read_inode_block(inode, &bh);
 	struct ocfs2_dinode *fe;
 	const char *link;
-	void *kaddr;
 	size_t len;
 
 	if (status < 0) {
 		mlog_errno(status);
-		return status;
+		goto out;
 	}
 
 	fe = (struct ocfs2_dinode *) bh->b_data;
 	link = (char *) fe->id2.i_symlink;
 	/* will be less than a page size */
 	len = strnlen(link, ocfs2_fast_symlink_chars(inode->i_sb));
-	kaddr = kmap_atomic(page);
-	memcpy(kaddr, link, len + 1);
-	kunmap_atomic(kaddr);
-	SetPageUptodate(page);
-	unlock_page(page);
+	memcpy_to_folio(folio, 0, link, len + 1);
+out:
+	folio_end_read(folio, status == 0);
 	brelse(bh);
-	return 0;
+	return status;
 }
 
 const struct address_space_operations ocfs2_fast_symlink_aops = {
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 73a6f6fd8a8e..d70a20d29e3e 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -648,7 +648,7 @@ int ocfs2_calc_xattr_init(struct inode *dir,
 	 * 256(name) + 80(value) + 16(entry) = 352 bytes,
 	 * The max space of acl xattr taken inline is
 	 * 80(value) + 16(entry) * 2(if directory) = 192 bytes,
-	 * when blocksize = 512, may reserve one more cluser for
+	 * when blocksize = 512, may reserve one more cluster for
 	 * xattr bucket, otherwise reserve one metadata block
 	 * for them is ok.
 	 * If this is a new directory with inline data,
@@ -4371,7 +4371,7 @@ static int cmp_xe_offset(const void *a, const void *b)
 
 /*
  * defrag a xattr bucket if we find that the bucket has some
- * holes beteen name/value pairs.
+ * holes between name/value pairs.
  * We will move all the name/value pairs to the end of the bucket
  * so that we can spare some space for insertion.
  */
@@ -5011,7 +5011,7 @@ static int ocfs2_divide_xattr_cluster(struct inode *inode,
  * 2. If cluster_size == bucket_size:
  *    a) If the previous extent rec has more than one cluster and the insert
  *       place isn't in the last cluster, copy the entire last cluster to the
- *       new one. This time, we don't need to upate the first_bh and header_bh
+ *       new one. This time, we don't need to update the first_bh and header_bh
  *       since they will not be moved into the new cluster.
  *    b) Otherwise, move the bottom half of the xattrs in the last cluster into
  *       the new one. And we set the extend flag to zero if the insert place is
@@ -6189,7 +6189,7 @@ struct ocfs2_xattr_reflink {
 /*
  * Given a xattr header and xe offset,
  * return the proper xv and the corresponding bh.
- * xattr in inode, block and xattr tree have different implementaions.
+ * xattr in inode, block and xattr tree have different implementations.
  */
 typedef int (get_xattr_value_root)(struct super_block *sb,
 				   struct buffer_head *bh,
@@ -6269,7 +6269,7 @@ static int ocfs2_get_xattr_value_root(struct super_block *sb,
 }
 
 /*
- * Lock the meta_ac and caculate how much credits we need for reflink xattrs.
+ * Lock the meta_ac and calculate how much credits we need for reflink xattrs.
  * It is only used for inline xattr and xattr block.
  */
 static int ocfs2_reflink_lock_xattr_allocators(struct ocfs2_super *osb,
diff --git a/fs/open.c b/fs/open.c
index 0a5d2f6061c6..1be20de9f283 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -905,7 +905,8 @@ static int do_dentry_open(struct file *f,
 	f->f_sb_err = file_sample_sb_err(f);
 
 	if (unlikely(f->f_flags & O_PATH)) {
-		f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY;
+		f->f_mode = FMODE_PATH | FMODE_OPENED;
+		file_set_fsnotify_mode(f, FMODE_NONOTIFY);
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -935,10 +936,10 @@ static int do_dentry_open(struct file *f,
 
 	/*
 	 * Set FMODE_NONOTIFY_* bits according to existing permission watches.
-	 * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't
-	 * change anything.
+	 * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a
+	 * pseudo file, this call will not change the mode.
 	 */
-	file_set_fsnotify_mode(f);
+	file_set_fsnotify_mode_from_watchers(f);
 	error = fsnotify_open_perm(f);
 	if (error)
 		goto cleanup_all;
@@ -1122,7 +1123,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags,
 	if (!IS_ERR(f)) {
 		int error;
 
-		f->f_mode |= FMODE_NONOTIFY;
+		file_set_fsnotify_mode(f, FMODE_NONOTIFY);
 		error = vfs_open(path, f);
 		if (error) {
 			fput(f);
@@ -1529,7 +1530,7 @@ static int filp_flush(struct file *filp, fl_owner_t id)
 {
 	int retval = 0;
 
-	if (CHECK_DATA_CORRUPTION(file_count(filp) == 0,
+	if (CHECK_DATA_CORRUPTION(file_count(filp) == 0, filp,
 			"VFS: Close: file count is 0 (f_op=%ps)",
 			filp->f_op)) {
 		return 0;
diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c
index 395a00ed8ac7..a19d1ad705db 100644
--- a/fs/orangefs/dcache.c
+++ b/fs/orangefs/dcache.c
@@ -13,10 +13,9 @@
 #include "orangefs-kernel.h"
 
 /* Returns 1 if dentry can still be trusted, else 0. */
-static int orangefs_revalidate_lookup(struct dentry *dentry)
+static int orangefs_revalidate_lookup(struct inode *parent_inode, const struct qstr *name,
+				      struct dentry *dentry)
 {
-	struct dentry *parent_dentry = dget_parent(dentry);
-	struct inode *parent_inode = parent_dentry->d_inode;
 	struct orangefs_inode_s *parent = ORANGEFS_I(parent_inode);
 	struct inode *inode = dentry->d_inode;
 	struct orangefs_kernel_op_s *new_op;
@@ -26,14 +25,14 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
 	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__);
 
 	new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP);
-	if (!new_op) {
-		ret = -ENOMEM;
-		goto out_put_parent;
-	}
+	if (!new_op)
+		return -ENOMEM;
 
 	new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW;
 	new_op->upcall.req.lookup.parent_refn = parent->refn;
-	strscpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name);
+	/* op_alloc() leaves ->upcall zeroed */
+	memcpy(new_op->upcall.req.lookup.d_name, name->name,
+			min(name->len, ORANGEFS_NAME_MAX - 1));
 
 	gossip_debug(GOSSIP_DCACHE_DEBUG,
 		     "%s:%s:%d interrupt flag [%d]\n",
@@ -78,8 +77,6 @@ static int orangefs_revalidate_lookup(struct dentry *dentry)
 	ret = 1;
 out_release_op:
 	op_release(new_op);
-out_put_parent:
-	dput(parent_dentry);
 	return ret;
 out_drop:
 	gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d revalidate failed\n",
@@ -92,7 +89,8 @@ out_drop:
  *
  * Should return 1 if dentry can still be trusted, else 0.
  */
-static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int orangefs_d_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	int ret;
 	unsigned long time = (unsigned long) dentry->d_fsdata;
@@ -114,7 +112,7 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	 * If this passes, the positive dentry still exists or the negative
 	 * dentry still does not exist.
 	 */
-	if (!orangefs_revalidate_lookup(dentry))
+	if (!orangefs_revalidate_lookup(dir, name, dentry))
 		return 0;
 
 	/* We do not need to continue with negative dentries. */
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index 1b508f543384..f52073022fae 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -206,8 +206,8 @@ static void orangefs_kernel_debug_init(void)
 		pr_info("%s: overflow 1!\n", __func__);
 	}
 
-	debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer,
-			    &kernel_debug_fops);
+	debugfs_create_file_aux_num(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer,
+			    0, &kernel_debug_fops);
 }
 
 
@@ -306,11 +306,10 @@ static void orangefs_client_debug_init(void)
 		pr_info("%s: overflow! 2\n", __func__);
 	}
 
-	client_debug_dentry = debugfs_create_file(ORANGEFS_CLIENT_DEBUG_FILE,
-						  0444,
-						  debug_dir,
-						  c_buffer,
-						  &kernel_debug_fops);
+	client_debug_dentry = debugfs_create_file_aux_num(
+					  ORANGEFS_CLIENT_DEBUG_FILE,
+					  0444, debug_dir, c_buffer, 1,
+					  &kernel_debug_fops);
 }
 
 /* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/
@@ -393,9 +392,9 @@ static ssize_t orangefs_debug_write(struct file *file,
 	 * Thwart users who try to jamb a ridiculous number
 	 * of bytes into the debug file...
 	 */
-	if (count > ORANGEFS_MAX_DEBUG_STRING_LEN + 1) {
+	if (count > ORANGEFS_MAX_DEBUG_STRING_LEN) {
 		silly = count;
-		count = ORANGEFS_MAX_DEBUG_STRING_LEN + 1;
+		count = ORANGEFS_MAX_DEBUG_STRING_LEN;
 	}
 
 	buf = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
@@ -418,8 +417,7 @@ static ssize_t orangefs_debug_write(struct file *file,
 	 * A service operation is required to set a new client-side
 	 * debug mask.
 	 */
-	if (!strcmp(file->f_path.dentry->d_name.name,
-		    ORANGEFS_KMOD_DEBUG_FILE)) {
+	if (!debugfs_get_aux_num(file)) {	// kernel-debug
 		debug_string_to_mask(buf, &orangefs_gossip_debug_mask, 0);
 		debug_mask_to_string(&orangefs_gossip_debug_mask, 0);
 		debug_string = kernel_debug_string;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index cea820cb3b55..be5c65d6f848 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -14,8 +14,6 @@
 #include <linux/exportfs.h>
 #include "overlayfs.h"
 
-#include "../internal.h"	/* for vfs_path_lookup */
-
 struct ovl_lookup_data {
 	struct super_block *sb;
 	const struct ovl_layer *layer;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fe511192f83c..86ae6f6da36b 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -91,7 +91,24 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
 		if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE)
 			ret =  d->d_op->d_weak_revalidate(d, flags);
 	} else if (d->d_flags & DCACHE_OP_REVALIDATE) {
-		ret = d->d_op->d_revalidate(d, flags);
+		struct dentry *parent;
+		struct inode *dir;
+		struct name_snapshot n;
+
+		if (flags & LOOKUP_RCU) {
+			parent = READ_ONCE(d->d_parent);
+			dir = d_inode_rcu(parent);
+			if (!dir)
+				return -ECHILD;
+		} else {
+			parent = dget_parent(d);
+			dir = d_inode(parent);
+		}
+		take_dentry_name_snapshot(&n, d);
+		ret = d->d_op->d_revalidate(dir, &n.name, d, flags);
+		release_dentry_name_snapshot(&n);
+		if (!(flags & LOOKUP_RCU))
+			dput(parent);
 		if (!ret) {
 			if (!(flags & LOOKUP_RCU))
 				d_invalidate(d);
@@ -127,7 +144,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry,
 	return ret;
 }
 
-static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+static int ovl_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	return ovl_dentry_revalidate_common(dentry, flags, false);
 }
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 049352f973de..63f9699ebac3 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -287,7 +287,6 @@ static bool pidfs_ioctl_valid(unsigned int cmd)
 	switch (cmd) {
 	case FS_IOC_GETVERSION:
 	case PIDFD_GET_CGROUP_NAMESPACE:
-	case PIDFD_GET_INFO:
 	case PIDFD_GET_IPC_NAMESPACE:
 	case PIDFD_GET_MNT_NAMESPACE:
 	case PIDFD_GET_NET_NAMESPACE:
@@ -300,6 +299,17 @@ static bool pidfs_ioctl_valid(unsigned int cmd)
 		return true;
 	}
 
+	/* Extensible ioctls require some more careful checks. */
+	switch (_IOC_NR(cmd)) {
+	case _IOC_NR(PIDFD_GET_INFO):
+		/*
+		 * Try to prevent performing a pidfd ioctl when someone
+		 * erronously mistook the file descriptor for a pidfd.
+		 * This is not perfect but will catch most cases.
+		 */
+		return (_IOC_TYPE(cmd) == _IOC_TYPE(PIDFD_GET_INFO));
+	}
+
 	return false;
 }
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 82fede0f2111..ce1af7592780 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -960,6 +960,12 @@ int create_pipe_files(struct file **res, int flags)
 	res[1] = f;
 	stream_open(inode, res[0]);
 	stream_open(inode, res[1]);
+	/*
+	 * Disable permission and pre-content events, but enable legacy
+	 * inotify events for legacy users.
+	 */
+	file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM);
+	file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM);
 	return 0;
 }
 
@@ -1478,7 +1484,7 @@ static int proc_dopipe_max_size(const struct ctl_table *table, int write,
 				 do_proc_dopipe_max_size_conv, NULL);
 }
 
-static struct ctl_table fs_pipe_sysctls[] = {
+static const struct ctl_table fs_pipe_sysctls[] = {
 	{
 		.procname	= "pipe-max-size",
 		.data		= &pipe_max_size,
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index d80a1431ef7b..6ae966c561e7 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -61,6 +61,25 @@ config PROC_VMCORE_DEVICE_DUMP
 	  as ELF notes to /proc/vmcore. You can still disable device
 	  dump using the kernel command line option 'novmcoredd'.
 
+config NEED_PROC_VMCORE_DEVICE_RAM
+	bool
+
+config PROC_VMCORE_DEVICE_RAM
+	def_bool y
+	depends on PROC_VMCORE && NEED_PROC_VMCORE_DEVICE_RAM
+	depends on VIRTIO_MEM
+	help
+	  If the elfcore hdr is allocated and prepared by the dump kernel
+	  ("2nd kernel") instead of the crashed kernel, RAM provided by memory
+	  devices such as virtio-mem will not be included in the dump
+	  image, because only the device driver can properly detect them.
+
+	  With this config enabled, these RAM ranges will be queried from the
+	  device drivers once the device gets probed, so they can be included
+	  in the crash dump.
+
+	  Relevant architectures should select NEED_PROC_VMCORE_DEVICE_RAM.
+
 config PROC_SYSCTL
 	bool "Sysctl support (/proc/sys)" if EXPERT
 	depends on PROC_FS
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0edf14a9840e..cd89e956c322 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2058,7 +2058,8 @@ void pid_update_inode(struct task_struct *task, struct inode *inode)
  * performed a setuid(), etc.
  *
  */
-static int pid_revalidate(struct dentry *dentry, unsigned int flags)
+static int pid_revalidate(struct inode *dir, const struct qstr *name,
+			  struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct task_struct *task;
@@ -2191,7 +2192,8 @@ static int dname_to_vma_addr(struct dentry *dentry,
 	return 0;
 }
 
-static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int map_files_d_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *dentry, unsigned int flags)
 {
 	unsigned long vm_start, vm_end;
 	bool exact_vma_exists = false;
@@ -3269,6 +3271,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task)
 {
 	struct mm_struct *mm;
+	int ret = 0;
 
 	mm = get_task_mm(task);
 	if (mm) {
@@ -3276,6 +3279,16 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 		seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm));
 		seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
 		seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
+		seq_printf(m, "ksm_merge_any: %s\n",
+				test_bit(MMF_VM_MERGE_ANY, &mm->flags) ? "yes" : "no");
+		ret = mmap_read_lock_killable(mm);
+		if (ret) {
+			mmput(mm);
+			return ret;
+		}
+		seq_printf(m, "ksm_mergeable: %s\n",
+				ksm_process_mergeable(mm) ? "yes" : "no");
+		mmap_read_unlock(mm);
 		mmput(mm);
 	}
 
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 24baf23e864f..37aa778d1af7 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -140,7 +140,8 @@ static void tid_fd_update_inode(struct task_struct *task, struct inode *inode,
 	security_task_to_inode(task, inode);
 }
 
-static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
+static int tid_fd_revalidate(struct inode *dir, const struct qstr *name,
+			     struct dentry *dentry, unsigned int flags)
 {
 	struct task_struct *task;
 	struct inode *inode;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index dbe82cf23ee4..8ec90826a49e 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -216,7 +216,8 @@ void proc_free_inum(unsigned int inum)
 	ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
 }
 
-static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name,
+				  struct dentry *dentry, unsigned int flags)
 {
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -343,7 +344,8 @@ static const struct file_operations proc_dir_operations = {
 	.iterate_shared		= proc_readdir,
 };
 
-static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name,
+				 struct dentry *dentry, unsigned int flags)
 {
 	return 0;
 }
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 27a283d85a6e..cc9d74a06ff0 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -884,7 +884,8 @@ static const struct inode_operations proc_sys_dir_operations = {
 	.getattr	= proc_sys_getattr,
 };
 
-static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
+static int proc_sys_revalidate(struct inode *dir, const struct qstr *name,
+			       struct dentry *dentry, unsigned int flags)
 {
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 658bf199d424..a00120a3c099 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -8,6 +8,8 @@
  *
  */
 
+#define pr_fmt(fmt) "vmcore: " fmt
+
 #include <linux/mm.h>
 #include <linux/kcore.h>
 #include <linux/user.h>
@@ -51,9 +53,14 @@ static u64 vmcore_size;
 static struct proc_dir_entry *proc_vmcore;
 
 #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
+struct vmcoredd_node {
+	struct list_head list;	/* List of dumps */
+	void *buf;		/* Buffer containing device's dump */
+	unsigned int size;	/* Size of the buffer */
+};
+
 /* Device Dump list and mutex to synchronize access to list */
 static LIST_HEAD(vmcoredd_list);
-static DEFINE_MUTEX(vmcoredd_mutex);
 
 static bool vmcoredd_disabled;
 core_param(novmcoredd, vmcoredd_disabled, bool, 0);
@@ -62,17 +69,22 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
 /* Device Dump Size */
 static size_t vmcoredd_orig_sz;
 
-static DEFINE_SPINLOCK(vmcore_cb_lock);
+static DEFINE_MUTEX(vmcore_mutex);
+
 DEFINE_STATIC_SRCU(vmcore_cb_srcu);
 /* List of registered vmcore callbacks. */
 static LIST_HEAD(vmcore_cb_list);
 /* Whether the vmcore has been opened once. */
 static bool vmcore_opened;
+/* Whether the vmcore is currently open. */
+static unsigned int vmcore_open;
+
+static void vmcore_process_device_ram(struct vmcore_cb *cb);
 
 void register_vmcore_cb(struct vmcore_cb *cb)
 {
 	INIT_LIST_HEAD(&cb->next);
-	spin_lock(&vmcore_cb_lock);
+	mutex_lock(&vmcore_mutex);
 	list_add_tail(&cb->next, &vmcore_cb_list);
 	/*
 	 * Registering a vmcore callback after the vmcore was opened is
@@ -80,13 +92,15 @@ void register_vmcore_cb(struct vmcore_cb *cb)
 	 */
 	if (vmcore_opened)
 		pr_warn_once("Unexpected vmcore callback registration\n");
-	spin_unlock(&vmcore_cb_lock);
+	if (!vmcore_open && cb->get_device_ram)
+		vmcore_process_device_ram(cb);
+	mutex_unlock(&vmcore_mutex);
 }
 EXPORT_SYMBOL_GPL(register_vmcore_cb);
 
 void unregister_vmcore_cb(struct vmcore_cb *cb)
 {
-	spin_lock(&vmcore_cb_lock);
+	mutex_lock(&vmcore_mutex);
 	list_del_rcu(&cb->next);
 	/*
 	 * Unregistering a vmcore callback after the vmcore was opened is
@@ -95,7 +109,7 @@ void unregister_vmcore_cb(struct vmcore_cb *cb)
 	 */
 	if (vmcore_opened)
 		pr_warn_once("Unexpected vmcore callback unregistration\n");
-	spin_unlock(&vmcore_cb_lock);
+	mutex_unlock(&vmcore_mutex);
 
 	synchronize_srcu(&vmcore_cb_srcu);
 }
@@ -120,9 +134,23 @@ static bool pfn_is_ram(unsigned long pfn)
 
 static int open_vmcore(struct inode *inode, struct file *file)
 {
-	spin_lock(&vmcore_cb_lock);
+	mutex_lock(&vmcore_mutex);
 	vmcore_opened = true;
-	spin_unlock(&vmcore_cb_lock);
+	if (vmcore_open + 1 == 0) {
+		mutex_unlock(&vmcore_mutex);
+		return -EBUSY;
+	}
+	vmcore_open++;
+	mutex_unlock(&vmcore_mutex);
+
+	return 0;
+}
+
+static int release_vmcore(struct inode *inode, struct file *file)
+{
+	mutex_lock(&vmcore_mutex);
+	vmcore_open--;
+	mutex_unlock(&vmcore_mutex);
 
 	return 0;
 }
@@ -243,33 +271,27 @@ static int vmcoredd_copy_dumps(struct iov_iter *iter, u64 start, size_t size)
 {
 	struct vmcoredd_node *dump;
 	u64 offset = 0;
-	int ret = 0;
 	size_t tsz;
 	char *buf;
 
-	mutex_lock(&vmcoredd_mutex);
 	list_for_each_entry(dump, &vmcoredd_list, list) {
 		if (start < offset + dump->size) {
 			tsz = min(offset + (u64)dump->size - start, (u64)size);
 			buf = dump->buf + start - offset;
-			if (copy_to_iter(buf, tsz, iter) < tsz) {
-				ret = -EFAULT;
-				goto out_unlock;
-			}
+			if (copy_to_iter(buf, tsz, iter) < tsz)
+				return -EFAULT;
 
 			size -= tsz;
 			start += tsz;
 
 			/* Leave now if buffer filled already */
 			if (!size)
-				goto out_unlock;
+				return 0;
 		}
 		offset += dump->size;
 	}
 
-out_unlock:
-	mutex_unlock(&vmcoredd_mutex);
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_MMU
@@ -278,20 +300,16 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
 {
 	struct vmcoredd_node *dump;
 	u64 offset = 0;
-	int ret = 0;
 	size_t tsz;
 	char *buf;
 
-	mutex_lock(&vmcoredd_mutex);
 	list_for_each_entry(dump, &vmcoredd_list, list) {
 		if (start < offset + dump->size) {
 			tsz = min(offset + (u64)dump->size - start, (u64)size);
 			buf = dump->buf + start - offset;
 			if (remap_vmalloc_range_partial(vma, dst, buf, 0,
-							tsz)) {
-				ret = -EFAULT;
-				goto out_unlock;
-			}
+							tsz))
+				return -EFAULT;
 
 			size -= tsz;
 			start += tsz;
@@ -299,14 +317,12 @@ static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst,
 
 			/* Leave now if buffer filled already */
 			if (!size)
-				goto out_unlock;
+				return 0;
 		}
 		offset += dump->size;
 	}
 
-out_unlock:
-	mutex_unlock(&vmcoredd_mutex);
-	return ret;
+	return 0;
 }
 #endif /* CONFIG_MMU */
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
@@ -316,10 +332,10 @@ out_unlock:
  */
 static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
 {
+	struct vmcore_range *m = NULL;
 	ssize_t acc = 0, tmp;
 	size_t tsz;
 	u64 start;
-	struct vmcore *m = NULL;
 
 	if (!iov_iter_count(iter) || *fpos >= vmcore_size)
 		return 0;
@@ -576,7 +592,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 {
 	size_t size = vma->vm_end - vma->vm_start;
 	u64 start, end, len, tsz;
-	struct vmcore *m;
+	struct vmcore_range *m;
 
 	start = (u64)vma->vm_pgoff << PAGE_SHIFT;
 	end = start + size;
@@ -693,21 +709,17 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 static const struct proc_ops vmcore_proc_ops = {
 	.proc_open	= open_vmcore,
+	.proc_release	= release_vmcore,
 	.proc_read_iter	= read_vmcore,
 	.proc_lseek	= default_llseek,
 	.proc_mmap	= mmap_vmcore,
 };
 
-static struct vmcore* __init get_new_element(void)
-{
-	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
-}
-
 static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
 			   struct list_head *vc_list)
 {
+	struct vmcore_range *m;
 	u64 size;
-	struct vmcore *m;
 
 	size = elfsz + elfnotesegsz;
 	list_for_each_entry(m, vc_list, list) {
@@ -1109,7 +1121,6 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 	Elf64_Ehdr *ehdr_ptr;
 	Elf64_Phdr *phdr_ptr;
 	loff_t vmcore_off;
-	struct vmcore *new;
 
 	ehdr_ptr = (Elf64_Ehdr *)elfptr;
 	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
@@ -1128,13 +1139,8 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
 		size = end - start;
 
-		/* Add this contiguous chunk of memory to vmcore list.*/
-		new = get_new_element();
-		if (!new)
+		if (vmcore_alloc_add_range(vc_list, start, size))
 			return -ENOMEM;
-		new->paddr = start;
-		new->size = size;
-		list_add_tail(&new->list, vc_list);
 
 		/* Update the program header offset. */
 		phdr_ptr->p_offset = vmcore_off + (paddr - start);
@@ -1152,7 +1158,6 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
 	Elf32_Ehdr *ehdr_ptr;
 	Elf32_Phdr *phdr_ptr;
 	loff_t vmcore_off;
-	struct vmcore *new;
 
 	ehdr_ptr = (Elf32_Ehdr *)elfptr;
 	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */
@@ -1171,13 +1176,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
 		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
 		size = end - start;
 
-		/* Add this contiguous chunk of memory to vmcore list.*/
-		new = get_new_element();
-		if (!new)
+		if (vmcore_alloc_add_range(vc_list, start, size))
 			return -ENOMEM;
-		new->paddr = start;
-		new->size = size;
-		list_add_tail(&new->list, vc_list);
 
 		/* Update the program header offset */
 		phdr_ptr->p_offset = vmcore_off + (paddr - start);
@@ -1190,8 +1190,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
 static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
 				    struct list_head *vc_list)
 {
+	struct vmcore_range *m;
 	loff_t vmcore_off;
-	struct vmcore *m;
 
 	/* Skip ELF header, program headers and ELF note segment. */
 	vmcore_off = elfsz + elfnotes_sz;
@@ -1518,12 +1518,18 @@ int vmcore_add_device_dump(struct vmcoredd_data *data)
 	dump->buf = buf;
 	dump->size = data_size;
 
-	/* Add the dump to driver sysfs list */
-	mutex_lock(&vmcoredd_mutex);
-	list_add_tail(&dump->list, &vmcoredd_list);
-	mutex_unlock(&vmcoredd_mutex);
+	/* Add the dump to driver sysfs list and update the elfcore hdr */
+	mutex_lock(&vmcore_mutex);
+	if (vmcore_opened)
+		pr_warn_once("Unexpected adding of device dump\n");
+	if (vmcore_open) {
+		ret = -EBUSY;
+		goto out_err;
+	}
 
+	list_add_tail(&dump->list, &vmcoredd_list);
 	vmcoredd_update_size(data_size);
+	mutex_unlock(&vmcore_mutex);
 	return 0;
 
 out_err:
@@ -1535,11 +1541,163 @@ out_err:
 EXPORT_SYMBOL(vmcore_add_device_dump);
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+static int vmcore_realloc_elfcore_buffer_elf64(size_t new_size)
+{
+	char *elfcorebuf_new;
+
+	if (WARN_ON_ONCE(new_size < elfcorebuf_sz))
+		return -EINVAL;
+	if (get_order(elfcorebuf_sz_orig) == get_order(new_size)) {
+		elfcorebuf_sz_orig = new_size;
+		return 0;
+	}
+
+	elfcorebuf_new = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						  get_order(new_size));
+	if (!elfcorebuf_new)
+		return -ENOMEM;
+	memcpy(elfcorebuf_new, elfcorebuf, elfcorebuf_sz);
+	free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
+	elfcorebuf = elfcorebuf_new;
+	elfcorebuf_sz_orig = new_size;
+	return 0;
+}
+
+static void vmcore_reset_offsets_elf64(void)
+{
+	Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr));
+	loff_t vmcore_off = elfcorebuf_sz + elfnotes_sz;
+	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf;
+	Elf64_Phdr *phdr;
+	int i;
+
+	for (i = 0, phdr = phdr_start; i < ehdr->e_phnum; i++, phdr++) {
+		u64 start, end;
+
+		/*
+		 * After merge_note_headers_elf64() we should only have a single
+		 * PT_NOTE entry that starts immediately after elfcorebuf_sz.
+		 */
+		if (phdr->p_type == PT_NOTE) {
+			phdr->p_offset = elfcorebuf_sz;
+			continue;
+		}
+
+		start = rounddown(phdr->p_offset, PAGE_SIZE);
+		end = roundup(phdr->p_offset + phdr->p_memsz, PAGE_SIZE);
+		phdr->p_offset = vmcore_off + (phdr->p_offset - start);
+		vmcore_off = vmcore_off + end - start;
+	}
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
+}
+
+static int vmcore_add_device_ram_elf64(struct list_head *list, size_t count)
+{
+	Elf64_Phdr *phdr_start = (Elf64_Phdr *)(elfcorebuf + sizeof(Elf64_Ehdr));
+	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfcorebuf;
+	struct vmcore_range *cur;
+	Elf64_Phdr *phdr;
+	size_t new_size;
+	int rc;
+
+	if ((Elf32_Half)(ehdr->e_phnum + count) != ehdr->e_phnum + count) {
+		pr_err("too many device ram ranges\n");
+		return -ENOSPC;
+	}
+
+	/* elfcorebuf_sz must always cover full pages. */
+	new_size = sizeof(Elf64_Ehdr) +
+		   (ehdr->e_phnum + count) * sizeof(Elf64_Phdr);
+	new_size = roundup(new_size, PAGE_SIZE);
+
+	/*
+	 * Make sure we have sufficient space to include the new PT_LOAD
+	 * entries.
+	 */
+	rc = vmcore_realloc_elfcore_buffer_elf64(new_size);
+	if (rc) {
+		pr_err("resizing elfcore failed\n");
+		return rc;
+	}
+
+	/* Modify our used elfcore buffer size to cover the new entries. */
+	elfcorebuf_sz = new_size;
+
+	/* Fill the added PT_LOAD entries. */
+	phdr = phdr_start + ehdr->e_phnum;
+	list_for_each_entry(cur, list, list) {
+		WARN_ON_ONCE(!IS_ALIGNED(cur->paddr | cur->size, PAGE_SIZE));
+		elfcorehdr_fill_device_ram_ptload_elf64(phdr, cur->paddr, cur->size);
+
+		/* p_offset will be adjusted later. */
+		phdr++;
+		ehdr->e_phnum++;
+	}
+	list_splice_tail(list, &vmcore_list);
+
+	/* We changed elfcorebuf_sz and added new entries; reset all offsets. */
+	vmcore_reset_offsets_elf64();
+
+	/* Finally, recalculate the total vmcore size. */
+	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+				      &vmcore_list);
+	proc_vmcore->size = vmcore_size;
+	return 0;
+}
+
+static void vmcore_process_device_ram(struct vmcore_cb *cb)
+{
+	unsigned char *e_ident = (unsigned char *)elfcorebuf;
+	struct vmcore_range *first, *m;
+	LIST_HEAD(list);
+	int count;
+
+	/* We only support Elf64 dumps for now. */
+	if (WARN_ON_ONCE(e_ident[EI_CLASS] != ELFCLASS64)) {
+		pr_err("device ram ranges only support Elf64\n");
+		return;
+	}
+
+	if (cb->get_device_ram(cb, &list)) {
+		pr_err("obtaining device ram ranges failed\n");
+		return;
+	}
+	count = list_count_nodes(&list);
+	if (!count)
+		return;
+
+	/*
+	 * For some reason these ranges are already know? Might happen
+	 * with unusual register->unregister->register sequences; we'll simply
+	 * sanity check using the first range.
+	 */
+	first = list_first_entry(&list, struct vmcore_range, list);
+	list_for_each_entry(m, &vmcore_list, list) {
+		unsigned long long m_end = m->paddr + m->size;
+		unsigned long long first_end = first->paddr + first->size;
+
+		if (first->paddr < m_end && m->paddr < first_end)
+			goto out_free;
+	}
+
+	/* If adding the mem nodes succeeds, they must not be freed. */
+	if (!vmcore_add_device_ram_elf64(&list, count))
+		return;
+out_free:
+	vmcore_free_ranges(&list);
+}
+#else /* !CONFIG_PROC_VMCORE_DEVICE_RAM */
+static void vmcore_process_device_ram(struct vmcore_cb *cb)
+{
+}
+#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */
+
 /* Free all dumps in vmcore device dump list */
 static void vmcore_free_device_dumps(void)
 {
 #ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP
-	mutex_lock(&vmcoredd_mutex);
+	mutex_lock(&vmcore_mutex);
 	while (!list_empty(&vmcoredd_list)) {
 		struct vmcoredd_node *dump;
 
@@ -1549,7 +1707,7 @@ static void vmcore_free_device_dumps(void)
 		vfree(dump->buf);
 		vfree(dump);
 	}
-	mutex_unlock(&vmcoredd_mutex);
+	mutex_unlock(&vmcore_mutex);
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 }
 
@@ -1571,7 +1729,7 @@ static int __init vmcore_init(void)
 	rc = parse_crash_elf_headers();
 	if (rc) {
 		elfcorehdr_free(elfcorehdr_addr);
-		pr_warn("Kdump: vmcore not initialized\n");
+		pr_warn("not initialized\n");
 		return rc;
 	}
 	elfcorehdr_free(elfcorehdr_addr);
@@ -1592,14 +1750,7 @@ void vmcore_cleanup(void)
 		proc_vmcore = NULL;
 	}
 
-	/* clear the vmcore list. */
-	while (!list_empty(&vmcore_list)) {
-		struct vmcore *m;
-
-		m = list_first_entry(&vmcore_list, struct vmcore, list);
-		list_del(&m->list);
-		kfree(m);
-	}
+	vmcore_free_ranges(&vmcore_list);
 	free_elfcorebuf();
 
 	/* clear vmcore device dump list */
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index f9578918cfb2..825c5c2e0962 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2926,7 +2926,7 @@ static int do_proc_dqstats(const struct ctl_table *table, int write,
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table fs_dqstats_table[] = {
+static const struct ctl_table fs_dqstats_table[] = {
 	{
 		.procname	= "lookups",
 		.data		= &dqstats.stat[DQST_LOOKUPS],
diff --git a/fs/smb/client/asn1.c b/fs/smb/client/asn1.c
index b5724ef9f182..214a44509e7b 100644
--- a/fs/smb/client/asn1.c
+++ b/fs/smb/client/asn1.c
@@ -52,6 +52,8 @@ int cifs_neg_token_init_mech_type(void *context, size_t hdrlen,
 		server->sec_kerberos = true;
 	else if (oid == OID_ntlmssp)
 		server->sec_ntlmssp = true;
+	else if (oid == OID_IAKerb)
+		server->sec_iakerb = true;
 	else {
 		char buf[50];
 
diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c
index 28f568b5fc27..bc1c1e9b288a 100644
--- a/fs/smb/client/cifs_spnego.c
+++ b/fs/smb/client/cifs_spnego.c
@@ -138,11 +138,13 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo,
 
 	dp = description + strlen(description);
 
-	/* for now, only sec=krb5 and sec=mskrb5 are valid */
+	/* for now, only sec=krb5 and sec=mskrb5 and iakerb are valid */
 	if (server->sec_kerberos)
 		sprintf(dp, ";sec=krb5");
 	else if (server->sec_mskerberos)
 		sprintf(dp, ";sec=mskrb5");
+	else if (server->sec_iakerb)
+		sprintf(dp, ";sec=iakerb");
 	else {
 		cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n");
 		sprintf(dp, ";sec=krb5");
diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index ba79aa2107cc..699a3f76d083 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -1395,7 +1395,7 @@ chown_chgrp_exit:
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
 				      const struct cifs_fid *cifsfid, u32 *pacllen,
-				      u32 __maybe_unused unused)
+				      u32 info)
 {
 	struct smb_ntsd *pntsd = NULL;
 	unsigned int xid;
@@ -1407,7 +1407,7 @@ struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
 
 	xid = get_xid();
 	rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd,
-				pacllen);
+				pacllen, info);
 	free_xid(xid);
 
 	cifs_put_tlink(tlink);
@@ -1419,7 +1419,7 @@ struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
 }
 
 static struct smb_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
-		const char *path, u32 *pacllen)
+		const char *path, u32 *pacllen, u32 info)
 {
 	struct smb_ntsd *pntsd = NULL;
 	int oplock = 0;
@@ -1446,9 +1446,12 @@ static struct smb_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
 		.fid = &fid,
 	};
 
+	if (info & SACL_SECINFO)
+		oparms.desired_access |= SYSTEM_SECURITY;
+
 	rc = CIFS_open(xid, &oparms, &oplock, NULL);
 	if (!rc) {
-		rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen);
+		rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen, info);
 		CIFSSMBClose(xid, tcon, fid.netfid);
 	}
 
@@ -1472,7 +1475,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
 	if (inode)
 		open_file = find_readable_file(CIFS_I(inode), true);
 	if (!open_file)
-		return get_cifs_acl_by_path(cifs_sb, path, pacllen);
+		return get_cifs_acl_by_path(cifs_sb, path, pacllen, info);
 
 	pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info);
 	cifsFileInfo_put(open_file);
@@ -1485,7 +1488,7 @@ int set_cifs_acl(struct smb_ntsd *pnntsd, __u32 acllen,
 {
 	int oplock = 0;
 	unsigned int xid;
-	int rc, access_flags;
+	int rc, access_flags = 0;
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
@@ -1498,10 +1501,12 @@ int set_cifs_acl(struct smb_ntsd *pnntsd, __u32 acllen,
 	tcon = tlink_tcon(tlink);
 	xid = get_xid();
 
-	if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP)
-		access_flags = WRITE_OWNER;
-	else
-		access_flags = WRITE_DAC;
+	if (aclflag & CIFS_ACL_OWNER || aclflag & CIFS_ACL_GROUP)
+		access_flags |= WRITE_OWNER;
+	if (aclflag & CIFS_ACL_SACL)
+		access_flags |= SYSTEM_SECURITY;
+	if (aclflag & CIFS_ACL_DACL)
+		access_flags |= WRITE_DAC;
 
 	oparms = (struct cifs_open_parms) {
 		.tcon = tcon,
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index b800c9f585d8..6a3bd652d251 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -715,6 +715,12 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 					    cifs_sb->ctx->backupgid));
 	seq_show_option(s, "reparse",
 			cifs_reparse_type_str(cifs_sb->ctx->reparse_type));
+	if (cifs_sb->ctx->nonativesocket)
+		seq_puts(s, ",nonativesocket");
+	else
+		seq_puts(s, ",nativesocket");
+	seq_show_option(s, "symlink",
+			cifs_symlink_type_str(get_cifs_symlink_type(cifs_sb)));
 
 	seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize);
 	seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize);
diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h
index a762dbbbd959..831fee962c4d 100644
--- a/fs/smb/client/cifsfs.h
+++ b/fs/smb/client/cifsfs.h
@@ -146,6 +146,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 52
-#define CIFS_VERSION   "2.52"
+#define SMB3_PRODUCT_BUILD 53
+#define CIFS_VERSION   "2.53"
 #endif				/* _CIFSFS_H */
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 49ffc040f736..ac1f890a0d54 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -151,6 +151,7 @@ enum securityEnum {
 	NTLMv2,			/* Legacy NTLM auth with NTLMv2 hash */
 	RawNTLMSSP,		/* NTLMSSP without SPNEGO, NTLMv2 hash */
 	Kerberos,		/* Kerberos via SPNEGO */
+	IAKerb,			/* Kerberos proxy */
 };
 
 enum upcall_target_enum {
@@ -160,6 +161,7 @@ enum upcall_target_enum {
 };
 
 enum cifs_reparse_type {
+	CIFS_REPARSE_TYPE_NONE,
 	CIFS_REPARSE_TYPE_NFS,
 	CIFS_REPARSE_TYPE_WSL,
 	CIFS_REPARSE_TYPE_DEFAULT = CIFS_REPARSE_TYPE_NFS,
@@ -168,6 +170,8 @@ enum cifs_reparse_type {
 static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type)
 {
 	switch (type) {
+	case CIFS_REPARSE_TYPE_NONE:
+		return "none";
 	case CIFS_REPARSE_TYPE_NFS:
 		return "nfs";
 	case CIFS_REPARSE_TYPE_WSL:
@@ -177,6 +181,39 @@ static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type)
 	}
 }
 
+enum cifs_symlink_type {
+	CIFS_SYMLINK_TYPE_DEFAULT,
+	CIFS_SYMLINK_TYPE_NONE,
+	CIFS_SYMLINK_TYPE_NATIVE,
+	CIFS_SYMLINK_TYPE_UNIX,
+	CIFS_SYMLINK_TYPE_MFSYMLINKS,
+	CIFS_SYMLINK_TYPE_SFU,
+	CIFS_SYMLINK_TYPE_NFS,
+	CIFS_SYMLINK_TYPE_WSL,
+};
+
+static inline const char *cifs_symlink_type_str(enum cifs_symlink_type type)
+{
+	switch (type) {
+	case CIFS_SYMLINK_TYPE_NONE:
+		return "none";
+	case CIFS_SYMLINK_TYPE_NATIVE:
+		return "native";
+	case CIFS_SYMLINK_TYPE_UNIX:
+		return "unix";
+	case CIFS_SYMLINK_TYPE_MFSYMLINKS:
+		return "mfsymlinks";
+	case CIFS_SYMLINK_TYPE_SFU:
+		return "sfu";
+	case CIFS_SYMLINK_TYPE_NFS:
+		return "nfs";
+	case CIFS_SYMLINK_TYPE_WSL:
+		return "wsl";
+	default:
+		return "unknown";
+	}
+}
+
 struct session_key {
 	unsigned int len;
 	char *response;
@@ -215,10 +252,7 @@ struct cifs_cred {
 
 struct cifs_open_info_data {
 	bool adjust_tz;
-	union {
-		bool reparse_point;
-		bool symlink;
-	};
+	bool reparse_point;
 	struct {
 		/* ioctl response buffer */
 		struct {
@@ -226,10 +260,7 @@ struct cifs_open_info_data {
 			struct kvec iov;
 		} io;
 		__u32 tag;
-		union {
-			struct reparse_data_buffer *buf;
-			struct reparse_posix_data *posix;
-		};
+		struct reparse_data_buffer *buf;
 	} reparse;
 	struct {
 		__u8		eas[SMB2_WSL_MAX_QUERY_EA_RESP_SIZE];
@@ -326,7 +357,7 @@ struct smb_version_operations {
 	int (*handle_cancelled_mid)(struct mid_q_entry *, struct TCP_Server_Info *);
 	void (*downgrade_oplock)(struct TCP_Server_Info *server,
 				 struct cifsInodeInfo *cinode, __u32 oplock,
-				 unsigned int epoch, bool *purge_cache);
+				 __u16 epoch, bool *purge_cache);
 	/* process transaction2 response */
 	bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *,
 			     char *, int);
@@ -521,12 +552,12 @@ struct smb_version_operations {
 	/* if we can do cache read operations */
 	bool (*is_read_op)(__u32);
 	/* set oplock level for the inode */
-	void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int,
-				 bool *);
+	void (*set_oplock_level)(struct cifsInodeInfo *cinode, __u32 oplock, __u16 epoch,
+				 bool *purge_cache);
 	/* create lease context buffer for CREATE request */
 	char * (*create_lease_buf)(u8 *lease_key, u8 oplock);
 	/* parse lease context buffer and return oplock/epoch info */
-	__u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey);
+	__u8 (*parse_lease_buf)(void *buf, __u16 *epoch, char *lkey);
 	ssize_t (*copychunk_range)(const unsigned int,
 			struct cifsFileInfo *src_file,
 			struct cifsFileInfo *target_file,
@@ -751,6 +782,7 @@ struct TCP_Server_Info {
 	bool	sec_kerberosu2u;	/* supports U2U Kerberos */
 	bool	sec_kerberos;		/* supports plain Kerberos */
 	bool	sec_mskerberos;		/* supports legacy MS Kerberos */
+	bool	sec_iakerb;		/* supports pass-through auth for Kerberos (krb5 proxy) */
 	bool	large_buf;		/* is current buffer large? */
 	/* use SMBD connection instead of socket */
 	bool	rdma;
@@ -1415,7 +1447,7 @@ struct cifs_fid {
 	__u8 create_guid[16];
 	__u32 access;
 	struct cifs_pending_open *pending_open;
-	unsigned int epoch;
+	__u16 epoch;
 #ifdef CONFIG_CIFS_DEBUG2
 	__u64 mid;
 #endif /* CIFS_DEBUG2 */
@@ -1448,7 +1480,7 @@ struct cifsFileInfo {
 	bool oplock_break_cancelled:1;
 	bool status_file_deleted:1; /* file has been deleted */
 	bool offload:1; /* offload final part of _put to a wq */
-	unsigned int oplock_epoch; /* epoch from the lease break */
+	__u16 oplock_epoch; /* epoch from the lease break */
 	__u32 oplock_level; /* oplock/lease level from the lease break */
 	int count;
 	spinlock_t file_info_lock; /* protects four flag/count fields above */
@@ -1545,7 +1577,7 @@ struct cifsInodeInfo {
 	spinlock_t	open_file_lock;	/* protects openFileList */
 	__u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */
 	unsigned int oplock;		/* oplock/lease level we have */
-	unsigned int epoch;		/* used to track lease state changes */
+	__u16 epoch;		/* used to track lease state changes */
 #define CIFS_INODE_PENDING_OPLOCK_BREAK   (0) /* oplock break in progress */
 #define CIFS_INODE_PENDING_WRITERS	  (1) /* Writes in progress */
 #define CIFS_INODE_FLAG_UNUSED		  (2) /* Unused flag */
@@ -2118,6 +2150,8 @@ static inline char *get_security_type_str(enum securityEnum sectype)
 		return "Kerberos";
 	case NTLMv2:
 		return "NTLMv2";
+	case IAKerb:
+		return "IAKerb";
 	default:
 		return "Unknown";
 	}
@@ -2173,11 +2207,13 @@ static inline size_t ntlmssp_workstation_name_size(const struct cifs_ses *ses)
 
 static inline void move_cifs_info_to_smb2(struct smb2_file_all_info *dst, const FILE_ALL_INFO *src)
 {
-	memcpy(dst, src, (size_t)((u8 *)&src->AccessFlags - (u8 *)src));
-	dst->AccessFlags = src->AccessFlags;
-	dst->CurrentByteOffset = src->CurrentByteOffset;
-	dst->Mode = src->Mode;
-	dst->AlignmentRequirement = src->AlignmentRequirement;
+	memcpy(dst, src, (size_t)((u8 *)&src->EASize - (u8 *)src));
+	dst->IndexNumber = 0;
+	dst->EASize = src->EASize;
+	dst->AccessFlags = 0;
+	dst->CurrentByteOffset = 0;
+	dst->Mode = 0;
+	dst->AlignmentRequirement = 0;
 	dst->FileNameLength = src->FileNameLength;
 }
 
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index 5c047b00516f..48d0d6f439cf 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -190,42 +190,82 @@
  */
 
 #define FILE_READ_DATA        0x00000001  /* Data can be read from the file   */
+					  /* or directory child entries can   */
+					  /* be listed together with the      */
+					  /* associated child attributes      */
+					  /* (so the FILE_READ_ATTRIBUTES on  */
+					  /* the child entry is not needed)   */
 #define FILE_WRITE_DATA       0x00000002  /* Data can be written to the file  */
+					  /* or new file can be created in    */
+					  /* the directory                    */
 #define FILE_APPEND_DATA      0x00000004  /* Data can be appended to the file */
+					  /* (for non-local files over SMB it */
+					  /* is same as FILE_WRITE_DATA)      */
+					  /* or new subdirectory can be       */
+					  /* created in the directory         */
 #define FILE_READ_EA          0x00000008  /* Extended attributes associated   */
 					  /* with the file can be read        */
 #define FILE_WRITE_EA         0x00000010  /* Extended attributes associated   */
 					  /* with the file can be written     */
 #define FILE_EXECUTE          0x00000020  /*Data can be read into memory from */
 					  /* the file using system paging I/O */
-#define FILE_DELETE_CHILD     0x00000040
+					  /* for executing the file / script  */
+					  /* or right to traverse directory   */
+					  /* (but by default all users have   */
+					  /* directory bypass traverse        */
+					  /* privilege and do not need this   */
+					  /* permission on directories at all)*/
+#define FILE_DELETE_CHILD     0x00000040  /* Child entry can be deleted from  */
+					  /* the directory (so the DELETE on  */
+					  /* the child entry is not needed)   */
 #define FILE_READ_ATTRIBUTES  0x00000080  /* Attributes associated with the   */
-					  /* file can be read                 */
+					  /* file or directory can be read    */
 #define FILE_WRITE_ATTRIBUTES 0x00000100  /* Attributes associated with the   */
-					  /* file can be written              */
-#define DELETE                0x00010000  /* The file can be deleted          */
-#define READ_CONTROL          0x00020000  /* The access control list and      */
-					  /* ownership associated with the    */
-					  /* file can be read                 */
-#define WRITE_DAC             0x00040000  /* The access control list and      */
-					  /* ownership associated with the    */
-					  /* file can be written.             */
+					  /* file or directory can be written */
+#define DELETE                0x00010000  /* The file or dir can be deleted   */
+#define READ_CONTROL          0x00020000  /* The discretionary access control */
+					  /* list and ownership associated    */
+					  /* with the file or dir can be read */
+#define WRITE_DAC             0x00040000  /* The discretionary access control */
+					  /* list associated with the file or */
+					  /* directory can be written         */
 #define WRITE_OWNER           0x00080000  /* Ownership information associated */
-					  /* with the file can be written     */
+					  /* with the file/dir can be written */
 #define SYNCHRONIZE           0x00100000  /* The file handle can waited on to */
 					  /* synchronize with the completion  */
 					  /* of an input/output request       */
 #define SYSTEM_SECURITY       0x01000000  /* The system access control list   */
-					  /* can be read and changed          */
-#define GENERIC_ALL           0x10000000
-#define GENERIC_EXECUTE       0x20000000
-#define GENERIC_WRITE         0x40000000
-#define GENERIC_READ          0x80000000
-					 /* In summary - Relevant file       */
-					 /* access flags from CIFS are       */
-					 /* file_read_data, file_write_data  */
-					 /* file_execute, file_read_attributes*/
-					 /* write_dac, and delete.           */
+					  /* associated with the file or      */
+					  /* directory can be read or written */
+					  /* (cannot be in DACL, can in SACL) */
+#define MAXIMUM_ALLOWED       0x02000000  /* Maximal subset of GENERIC_ALL    */
+					  /* permissions which can be granted */
+					  /* (cannot be in DACL nor SACL)     */
+#define GENERIC_ALL           0x10000000  /* Same as: GENERIC_EXECUTE |       */
+					  /*          GENERIC_WRITE |         */
+					  /*          GENERIC_READ |          */
+					  /*          FILE_DELETE_CHILD |     */
+					  /*          DELETE |                */
+					  /*          WRITE_DAC |             */
+					  /*          WRITE_OWNER             */
+					  /* So GENERIC_ALL contains all bits */
+					  /* mentioned above except these two */
+					  /* SYSTEM_SECURITY  MAXIMUM_ALLOWED */
+#define GENERIC_EXECUTE       0x20000000  /* Same as: FILE_EXECUTE |          */
+					  /*          FILE_READ_ATTRIBUTES |  */
+					  /*          READ_CONTROL |          */
+					  /*          SYNCHRONIZE             */
+#define GENERIC_WRITE         0x40000000  /* Same as: FILE_WRITE_DATA |       */
+					  /*          FILE_APPEND_DATA |      */
+					  /*          FILE_WRITE_EA |         */
+					  /*          FILE_WRITE_ATTRIBUTES | */
+					  /*          READ_CONTROL |          */
+					  /*          SYNCHRONIZE             */
+#define GENERIC_READ          0x80000000  /* Same as: FILE_READ_DATA |        */
+					  /*          FILE_READ_EA |          */
+					  /*          FILE_READ_ATTRIBUTES |  */
+					  /*          READ_CONTROL |          */
+					  /*          SYNCHRONIZE             */
 
 #define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES)
 #define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \
@@ -1484,20 +1524,6 @@ struct file_notify_information {
 	__u8  FileName[];
 } __attribute__((packed));
 
-/* For IO_REPARSE_TAG_NFS */
-#define NFS_SPECFILE_LNK	0x00000000014B4E4C
-#define NFS_SPECFILE_CHR	0x0000000000524843
-#define NFS_SPECFILE_BLK	0x00000000004B4C42
-#define NFS_SPECFILE_FIFO	0x000000004F464946
-#define NFS_SPECFILE_SOCK	0x000000004B434F53
-struct reparse_posix_data {
-	__le32	ReparseTag;
-	__le16	ReparseDataLength;
-	__u16	Reserved;
-	__le64	InodeType; /* LNK, FIFO, CHR etc. */
-	__u8	DataBuffer[];
-} __attribute__((packed));
-
 struct cifs_quota_data {
 	__u32	rsrvd1;  /* 0 */
 	__u32	sid_size;
@@ -2264,13 +2290,7 @@ typedef struct { /* data block encoding of response to level 263 QPathInfo */
 	__u8 DeletePending;
 	__u8 Directory;
 	__u16 Pad2;
-	__le64 IndexNumber;
 	__le32 EASize;
-	__le32 AccessFlags;
-	__u64 IndexNumber1;
-	__le64 CurrentByteOffset;
-	__le32 Mode;
-	__le32 AlignmentRequirement;
 	__le32 FileNameLength;
 	union {
 		char __pad;
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 223e5e231f42..81680001944d 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -557,7 +557,7 @@ extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon,
 		const struct nls_table *nls_codepage,
 		struct cifs_sb_info *cifs_sb);
 extern int CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon,
-			__u16 fid, struct smb_ntsd **acl_inf, __u32 *buflen);
+			__u16 fid, struct smb_ntsd **acl_inf, __u32 *buflen, __u32 info);
 extern int CIFSSMBSetCIFSACL(const unsigned int, struct cifs_tcon *, __u16,
 			struct smb_ntsd *pntsd, __u32 len, int aclflag);
 extern int cifs_do_get_acl(const unsigned int xid, struct cifs_tcon *tcon,
@@ -656,7 +656,7 @@ char *extract_sharename(const char *unc);
 int parse_reparse_point(struct reparse_data_buffer *buf,
 			u32 plen, struct cifs_sb_info *cifs_sb,
 			const char *full_path,
-			bool unicode, struct cifs_open_info_data *data);
+			struct cifs_open_info_data *data);
 int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
 			 struct dentry *dentry, struct cifs_tcon *tcon,
 			 const char *full_path, umode_t mode, dev_t dev,
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 7f1cacc89dbb..3feaa0f68169 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -3369,7 +3369,7 @@ validate_ntransact(char *buf, char **ppparm, char **ppdata,
 /* Get Security Descriptor (by handle) from remote server for a file or dir */
 int
 CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
-		  struct smb_ntsd **acl_inf, __u32 *pbuflen)
+		  struct smb_ntsd **acl_inf, __u32 *pbuflen, __u32 info)
 {
 	int rc = 0;
 	int buf_type = 0;
@@ -3392,7 +3392,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 	pSMB->MaxSetupCount = 0;
 	pSMB->Fid = fid; /* file handle always le */
 	pSMB->AclFlags = cpu_to_le32(CIFS_ACL_OWNER | CIFS_ACL_GROUP |
-				     CIFS_ACL_DACL);
+				     CIFS_ACL_DACL | info);
 	pSMB->ByteCount = cpu_to_le16(11); /* 3 bytes pad + 8 bytes parm */
 	inc_rfc1001_len(pSMB, 11);
 	iov[0].iov_base = (char *)pSMB;
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 880d7cf8b730..f917de020dd5 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -2849,6 +2849,10 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 		return 0;
 	if (old->ctx->reparse_type != new->ctx->reparse_type)
 		return 0;
+	if (old->ctx->nonativesocket != new->ctx->nonativesocket)
+		return 0;
+	if (old->ctx->symlink_type != new->ctx->symlink_type)
+		return 0;
 
 	return 1;
 }
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index dad521336b5e..f65a8a90ba27 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -150,25 +150,27 @@ again:
 			if (rc)
 				continue;
 
-			if (tgt.flags & DFSREF_STORAGE_SERVER) {
-				rc = cifs_mount_get_tcon(mnt_ctx);
-				if (!rc)
-					rc = cifs_is_path_remote(mnt_ctx);
+			rc = cifs_mount_get_tcon(mnt_ctx);
+			if (rc) {
+				if (tgt.server_type == DFS_TYPE_LINK &&
+				    DFS_INTERLINK(tgt.flags))
+					rc = -EREMOTE;
+			} else {
+				rc = cifs_is_path_remote(mnt_ctx);
 				if (!rc) {
 					ref_walk_set_tgt_hint(rw);
 					break;
 				}
-				if (rc != -EREMOTE)
-					continue;
 			}
-
-			rc = ref_walk_advance(rw);
-			if (!rc) {
-				rc = setup_dfs_ref(&tgt, rw);
-				if (rc)
-					break;
-				ref_walk_mark_end(rw);
-				goto again;
+			if (rc == -EREMOTE) {
+				rc = ref_walk_advance(rw);
+				if (!rc) {
+					rc = setup_dfs_ref(&tgt, rw);
+					if (rc)
+						break;
+					ref_walk_mark_end(rw);
+					goto again;
+				}
 			}
 		}
 	} while (rc && ref_walk_descend(rw));
diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h
index ed4cd7cf1ec6..e60f0a24a8a1 100644
--- a/fs/smb/client/dfs.h
+++ b/fs/smb/client/dfs.h
@@ -188,4 +188,11 @@ static inline void dfs_put_root_smb_sessions(struct list_head *head)
 	}
 }
 
+static inline const char *dfs_ses_refpath(struct cifs_ses *ses)
+{
+	const char *path = ses->server->leaf_fullpath;
+
+	return path ? path + 1 : ERR_PTR(-ENOENT);
+}
+
 #endif /* _CIFS_DFS_H */
diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c
index 5022bb1f122a..4dada26d56b5 100644
--- a/fs/smb/client/dfs_cache.c
+++ b/fs/smb/client/dfs_cache.c
@@ -1136,33 +1136,19 @@ static bool is_ses_good(struct cifs_ses *ses)
 	return ret;
 }
 
-static char *get_ses_refpath(struct cifs_ses *ses)
-{
-	struct TCP_Server_Info *server = ses->server;
-	char *path = ERR_PTR(-ENOENT);
-
-	if (server->leaf_fullpath) {
-		path = kstrdup(server->leaf_fullpath + 1, GFP_KERNEL);
-		if (!path)
-			path = ERR_PTR(-ENOMEM);
-	}
-	return path;
-}
-
 /* Refresh dfs referral of @ses */
 static void refresh_ses_referral(struct cifs_ses *ses)
 {
 	struct cache_entry *ce;
 	unsigned int xid;
-	char *path;
+	const char *path;
 	int rc = 0;
 
 	xid = get_xid();
 
-	path = get_ses_refpath(ses);
+	path = dfs_ses_refpath(ses);
 	if (IS_ERR(path)) {
 		rc = PTR_ERR(path);
-		path = NULL;
 		goto out;
 	}
 
@@ -1181,7 +1167,6 @@ static void refresh_ses_referral(struct cifs_ses *ses)
 
 out:
 	free_xid(xid);
-	kfree(path);
 }
 
 static int __refresh_tcon_referral(struct cifs_tcon *tcon,
@@ -1231,19 +1216,18 @@ static void refresh_tcon_referral(struct cifs_tcon *tcon, bool force_refresh)
 	struct dfs_info3_param *refs = NULL;
 	struct cache_entry *ce;
 	struct cifs_ses *ses;
-	unsigned int xid;
 	bool needs_refresh;
-	char *path;
+	const char *path;
+	unsigned int xid;
 	int numrefs = 0;
 	int rc = 0;
 
 	xid = get_xid();
 	ses = tcon->ses;
 
-	path = get_ses_refpath(ses);
+	path = dfs_ses_refpath(ses);
 	if (IS_ERR(path)) {
 		rc = PTR_ERR(path);
-		path = NULL;
 		goto out;
 	}
 
@@ -1271,7 +1255,6 @@ static void refresh_tcon_referral(struct cifs_tcon *tcon, bool force_refresh)
 
 out:
 	free_xid(xid);
-	kfree(path);
 	free_dfs_info_array(refs, numrefs);
 }
 
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index 1822493dd084..d1e95632ac54 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -737,7 +737,8 @@ again:
 }
 
 static int
-cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
+cifs_d_revalidate(struct inode *dir, const struct qstr *name,
+		  struct dentry *direntry, unsigned int flags)
 {
 	struct inode *inode;
 	int rc;
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 5381f05420bc..e9b286d9a7ba 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -133,6 +133,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_flag("rootfs", Opt_rootfs),
 	fsparam_flag("compress", Opt_compress),
 	fsparam_flag("witness", Opt_witness),
+	fsparam_flag_no("nativesocket", Opt_nativesocket),
 
 	/* Mount options which take uid or gid */
 	fsparam_uid("backupuid", Opt_backupuid),
@@ -185,6 +186,8 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_string("cache", Opt_cache),
 	fsparam_string("reparse", Opt_reparse),
 	fsparam_string("upcall_target", Opt_upcalltarget),
+	fsparam_string("symlink", Opt_symlink),
+	fsparam_string("symlinkroot", Opt_symlinkroot),
 
 	/* Arguments that should be ignored */
 	fsparam_flag("guest", Opt_ignore),
@@ -332,6 +335,7 @@ cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_conte
 
 static const match_table_t reparse_flavor_tokens = {
 	{ Opt_reparse_default,	"default" },
+	{ Opt_reparse_none,	"none" },
 	{ Opt_reparse_nfs,	"nfs" },
 	{ Opt_reparse_wsl,	"wsl" },
 	{ Opt_reparse_err,	NULL },
@@ -346,6 +350,9 @@ static int parse_reparse_flavor(struct fs_context *fc, char *value,
 	case Opt_reparse_default:
 		ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT;
 		break;
+	case Opt_reparse_none:
+		ctx->reparse_type = CIFS_REPARSE_TYPE_NONE;
+		break;
 	case Opt_reparse_nfs:
 		ctx->reparse_type = CIFS_REPARSE_TYPE_NFS;
 		break;
@@ -359,6 +366,55 @@ static int parse_reparse_flavor(struct fs_context *fc, char *value,
 	return 0;
 }
 
+static const match_table_t symlink_flavor_tokens = {
+	{ Opt_symlink_default,		"default" },
+	{ Opt_symlink_none,		"none" },
+	{ Opt_symlink_native,		"native" },
+	{ Opt_symlink_unix,		"unix" },
+	{ Opt_symlink_mfsymlinks,	"mfsymlinks" },
+	{ Opt_symlink_sfu,		"sfu" },
+	{ Opt_symlink_nfs,		"nfs" },
+	{ Opt_symlink_wsl,		"wsl" },
+	{ Opt_symlink_err,		NULL },
+};
+
+static int parse_symlink_flavor(struct fs_context *fc, char *value,
+				struct smb3_fs_context *ctx)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	switch (match_token(value, symlink_flavor_tokens, args)) {
+	case Opt_symlink_default:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT;
+		break;
+	case Opt_symlink_none:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_NONE;
+		break;
+	case Opt_symlink_native:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_NATIVE;
+		break;
+	case Opt_symlink_unix:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_UNIX;
+		break;
+	case Opt_symlink_mfsymlinks:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_MFSYMLINKS;
+		break;
+	case Opt_symlink_sfu:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_SFU;
+		break;
+	case Opt_symlink_nfs:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_NFS;
+		break;
+	case Opt_symlink_wsl:
+		ctx->symlink_type = CIFS_SYMLINK_TYPE_WSL;
+		break;
+	default:
+		cifs_errorf(fc, "bad symlink= option: %s\n", value);
+		return 1;
+	}
+	return 0;
+}
+
 #define DUP_CTX_STR(field)						\
 do {									\
 	if (ctx->field) {						\
@@ -386,6 +442,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
 	new_ctx->iocharset = NULL;
 	new_ctx->leaf_fullpath = NULL;
 	new_ctx->dns_dom = NULL;
+	new_ctx->symlinkroot = NULL;
 	/*
 	 * Make sure to stay in sync with smb3_cleanup_fs_context_contents()
 	 */
@@ -401,6 +458,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
 	DUP_CTX_STR(iocharset);
 	DUP_CTX_STR(leaf_fullpath);
 	DUP_CTX_STR(dns_dom);
+	DUP_CTX_STR(symlinkroot);
 
 	return 0;
 }
@@ -1727,6 +1785,23 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		if (parse_reparse_flavor(fc, param->string, ctx))
 			goto cifs_parse_mount_err;
 		break;
+	case Opt_nativesocket:
+		ctx->nonativesocket = result.negated;
+		break;
+	case Opt_symlink:
+		if (parse_symlink_flavor(fc, param->string, ctx))
+			goto cifs_parse_mount_err;
+		break;
+	case Opt_symlinkroot:
+		if (param->string[0] != '/') {
+			cifs_errorf(fc, "symlinkroot mount options must be absolute path\n");
+			goto cifs_parse_mount_err;
+		}
+		kfree(ctx->symlinkroot);
+		ctx->symlinkroot = kstrdup(param->string, GFP_KERNEL);
+		if (!ctx->symlinkroot)
+			goto cifs_parse_mount_err;
+		break;
 	}
 	/* case Opt_ignore: - is ignored as expected ... */
 
@@ -1735,6 +1810,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		goto cifs_parse_mount_err;
 	}
 
+	/*
+	 * By default resolve all native absolute symlinks relative to "/mnt/".
+	 * Same default has drvfs driver running in WSL for resolving SMB shares.
+	 */
+	if (!ctx->symlinkroot)
+		ctx->symlinkroot = kstrdup("/mnt/", GFP_KERNEL);
+
 	return 0;
 
  cifs_parse_mount_err:
@@ -1745,6 +1827,24 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 	return -EINVAL;
 }
 
+enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb)
+{
+	if (cifs_sb->ctx->symlink_type == CIFS_SYMLINK_TYPE_DEFAULT) {
+		if (cifs_sb->ctx->mfsymlinks)
+			return CIFS_SYMLINK_TYPE_MFSYMLINKS;
+		else if (cifs_sb->ctx->sfu_emul)
+			return CIFS_SYMLINK_TYPE_SFU;
+		else if (cifs_sb->ctx->linux_ext && !cifs_sb->ctx->no_linux_ext)
+			return CIFS_SYMLINK_TYPE_UNIX;
+		else if (cifs_sb->ctx->reparse_type != CIFS_REPARSE_TYPE_NONE)
+			return CIFS_SYMLINK_TYPE_NATIVE;
+		else
+			return CIFS_SYMLINK_TYPE_NONE;
+	} else {
+		return cifs_sb->ctx->symlink_type;
+	}
+}
+
 int smb3_init_fs_context(struct fs_context *fc)
 {
 	struct smb3_fs_context *ctx;
@@ -1821,6 +1921,8 @@ int smb3_init_fs_context(struct fs_context *fc)
 
 	ctx->retrans = 1;
 	ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT;
+	ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT;
+	ctx->nonativesocket = 0;
 
 /*
  *	short int override_uid = -1;
@@ -1867,6 +1969,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx)
 	ctx->leaf_fullpath = NULL;
 	kfree(ctx->dns_dom);
 	ctx->dns_dom = NULL;
+	kfree(ctx->symlinkroot);
+	ctx->symlinkroot = NULL;
 }
 
 void
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 8813533345ee..881bfc08667e 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -43,11 +43,24 @@ enum {
 
 enum cifs_reparse_parm {
 	Opt_reparse_default,
+	Opt_reparse_none,
 	Opt_reparse_nfs,
 	Opt_reparse_wsl,
 	Opt_reparse_err
 };
 
+enum cifs_symlink_parm {
+	Opt_symlink_default,
+	Opt_symlink_none,
+	Opt_symlink_native,
+	Opt_symlink_unix,
+	Opt_symlink_mfsymlinks,
+	Opt_symlink_sfu,
+	Opt_symlink_nfs,
+	Opt_symlink_wsl,
+	Opt_symlink_err
+};
+
 enum cifs_sec_param {
 	Opt_sec_krb5,
 	Opt_sec_krb5i,
@@ -166,6 +179,9 @@ enum cifs_param {
 	Opt_cache,
 	Opt_reparse,
 	Opt_upcalltarget,
+	Opt_nativesocket,
+	Opt_symlink,
+	Opt_symlinkroot,
 
 	/* Mount options to be ignored */
 	Opt_ignore,
@@ -294,12 +310,17 @@ struct smb3_fs_context {
 	struct cifs_ses *dfs_root_ses;
 	bool dfs_automount:1; /* set for dfs automount only */
 	enum cifs_reparse_type reparse_type;
+	enum cifs_symlink_type symlink_type;
+	bool nonativesocket:1;
 	bool dfs_conn:1; /* set for dfs mounts */
 	char *dns_dom;
+	char *symlinkroot; /* top level directory for native SMB symlinks in absolute format */
 };
 
 extern const struct fs_parameter_spec smb3_fs_parameters[];
 
+extern enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb);
+
 extern int smb3_init_fs_context(struct fs_context *fc);
 extern void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx);
 extern void smb3_cleanup_fs_context(struct smb3_fs_context *ctx);
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 93e9188b2632..9cc31cf6ebd0 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -990,7 +990,7 @@ cifs_get_file_info(struct file *filp)
 		/* TODO: add support to query reparse tag */
 		data.adjust_tz = false;
 		if (data.symlink_target) {
-			data.symlink = true;
+			data.reparse_point = true;
 			data.reparse.tag = IO_REPARSE_TAG_SYMLINK;
 		}
 		path = build_path_from_dentry(dentry, page);
@@ -1216,6 +1216,11 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
 							      full_path,
 							      iov, data);
 		}
+
+		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) {
+			bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY;
+			rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb);
+		}
 		break;
 	}
 
diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c
index 47ddeb7fa111..6e6c09cc5ce7 100644
--- a/fs/smb/client/link.c
+++ b/fs/smb/client/link.c
@@ -18,6 +18,7 @@
 #include "cifs_unicode.h"
 #include "smb2proto.h"
 #include "cifs_ioctl.h"
+#include "fs_context.h"
 
 /*
  * M-F Symlink Functions - Begin
@@ -604,22 +605,53 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode,
 	cifs_dbg(FYI, "symname is %s\n", symname);
 
 	/* BB what if DFS and this volume is on different share? BB */
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
-		rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname);
-	} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
-		rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon,
-					  full_path, S_IFLNK, 0, symname);
+	rc = -EOPNOTSUPP;
+	switch (get_cifs_symlink_type(cifs_sb)) {
+	case CIFS_SYMLINK_TYPE_DEFAULT:
+		/* should not happen, get_cifs_symlink_type() resolves the default */
+		break;
+
+	case CIFS_SYMLINK_TYPE_NONE:
+		break;
+
+	case CIFS_SYMLINK_TYPE_UNIX:
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
-	} else if (pTcon->unix_ext) {
-		rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname,
-					   cifs_sb->local_nls,
-					   cifs_remap(cifs_sb));
+		if (pTcon->unix_ext) {
+			rc = CIFSUnixCreateSymLink(xid, pTcon, full_path,
+						   symname,
+						   cifs_sb->local_nls,
+						   cifs_remap(cifs_sb));
+		}
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
-	} else if (server->ops->create_reparse_symlink) {
-		rc =  server->ops->create_reparse_symlink(xid, inode, direntry,
-							  pTcon, full_path,
-							  symname);
-		goto symlink_exit;
+		break;
+
+	case CIFS_SYMLINK_TYPE_MFSYMLINKS:
+		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
+			rc = create_mf_symlink(xid, pTcon, cifs_sb,
+					       full_path, symname);
+		}
+		break;
+
+	case CIFS_SYMLINK_TYPE_SFU:
+		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
+			rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon,
+						  full_path, S_IFLNK,
+						  0, symname);
+		}
+		break;
+
+	case CIFS_SYMLINK_TYPE_NATIVE:
+	case CIFS_SYMLINK_TYPE_NFS:
+	case CIFS_SYMLINK_TYPE_WSL:
+		if (server->ops->create_reparse_symlink) {
+			rc = server->ops->create_reparse_symlink(xid, inode,
+								 direntry,
+								 pTcon,
+								 full_path,
+								 symname);
+			goto symlink_exit;
+		}
+		break;
 	}
 
 	if (rc == 0) {
diff --git a/fs/smb/client/netmisc.c b/fs/smb/client/netmisc.c
index 17b3e21ea868..9ec20601cee2 100644
--- a/fs/smb/client/netmisc.c
+++ b/fs/smb/client/netmisc.c
@@ -313,7 +313,6 @@ static const struct {
 	ERRDOS, 2215, NT_STATUS_NO_LOGON_SERVERS}, {
 	ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_LOGON_SESSION}, {
 	ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_PRIVILEGE}, {
-	ERRDOS, ERRnoaccess, NT_STATUS_PRIVILEGE_NOT_HELD}, {
 	ERRHRD, ERRgeneral, NT_STATUS_INVALID_ACCOUNT_NAME}, {
 	ERRHRD, ERRgeneral, NT_STATUS_USER_EXISTS},
 /*	{ This NT error code was 'sqashed'
@@ -871,6 +870,15 @@ map_smb_to_linux_error(char *buf, bool logErr)
 	}
 	/* else ERRHRD class errors or junk  - return EIO */
 
+	/* special cases for NT status codes which cannot be translated to DOS codes */
+	if (smb->Flags2 & SMBFLG2_ERR_STATUS) {
+		__u32 err = le32_to_cpu(smb->Status.CifsError);
+		if (err == (NT_STATUS_NOT_A_REPARSE_POINT))
+			rc = -ENODATA;
+		else if (err == (NT_STATUS_PRIVILEGE_NOT_HELD))
+			rc = -EPERM;
+	}
+
 	cifs_dbg(FYI, "Mapping smb error code 0x%x to POSIX err %d\n",
 		 le32_to_cpu(smb->Status.CifsError), rc);
 
diff --git a/fs/smb/client/nterr.c b/fs/smb/client/nterr.c
index d396a8e98a81..8f0bc441295e 100644
--- a/fs/smb/client/nterr.c
+++ b/fs/smb/client/nterr.c
@@ -674,6 +674,7 @@ const struct nt_err_code_struct nt_errs[] = {
 	{"NT_STATUS_QUOTA_LIST_INCONSISTENT",
 	 NT_STATUS_QUOTA_LIST_INCONSISTENT},
 	{"NT_STATUS_FILE_IS_OFFLINE", NT_STATUS_FILE_IS_OFFLINE},
+	{"NT_STATUS_NOT_A_REPARSE_POINT", NT_STATUS_NOT_A_REPARSE_POINT},
 	{"NT_STATUS_NO_MORE_ENTRIES", NT_STATUS_NO_MORE_ENTRIES},
 	{"NT_STATUS_MORE_ENTRIES", NT_STATUS_MORE_ENTRIES},
 	{"NT_STATUS_SOME_UNMAPPED", NT_STATUS_SOME_UNMAPPED},
diff --git a/fs/smb/client/nterr.h b/fs/smb/client/nterr.h
index edd4741cab0a..180602c22355 100644
--- a/fs/smb/client/nterr.h
+++ b/fs/smb/client/nterr.h
@@ -546,6 +546,7 @@ extern const struct nt_err_code_struct nt_errs[];
 #define NT_STATUS_TOO_MANY_LINKS 0xC0000000 | 0x0265
 #define NT_STATUS_QUOTA_LIST_INCONSISTENT 0xC0000000 | 0x0266
 #define NT_STATUS_FILE_IS_OFFLINE 0xC0000000 | 0x0267
+#define NT_STATUS_NOT_A_REPARSE_POINT 0xC0000000 | 0x0275
 #define NT_STATUS_NO_SUCH_JOB 0xC0000000 | 0xEDE	/* scheduler */
 
 #endif				/* _NTERR_H */
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index d88b41133e00..0a5a52a8a7dd 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -14,6 +14,20 @@
 #include "fs_context.h"
 #include "reparse.h"
 
+static int mknod_nfs(unsigned int xid, struct inode *inode,
+		     struct dentry *dentry, struct cifs_tcon *tcon,
+		     const char *full_path, umode_t mode, dev_t dev,
+		     const char *symname);
+
+static int mknod_wsl(unsigned int xid, struct inode *inode,
+		     struct dentry *dentry, struct cifs_tcon *tcon,
+		     const char *full_path, umode_t mode, dev_t dev,
+		     const char *symname);
+
+static int create_native_symlink(const unsigned int xid, struct inode *inode,
+				 struct dentry *dentry, struct cifs_tcon *tcon,
+				 const char *full_path, const char *symname);
+
 static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb,
 					   const unsigned int xid,
 					   const char *full_path,
@@ -24,37 +38,148 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode,
 				struct dentry *dentry, struct cifs_tcon *tcon,
 				const char *full_path, const char *symname)
 {
+	switch (get_cifs_symlink_type(CIFS_SB(inode->i_sb))) {
+	case CIFS_SYMLINK_TYPE_NATIVE:
+		return create_native_symlink(xid, inode, dentry, tcon, full_path, symname);
+	case CIFS_SYMLINK_TYPE_NFS:
+		return mknod_nfs(xid, inode, dentry, tcon, full_path, S_IFLNK, 0, symname);
+	case CIFS_SYMLINK_TYPE_WSL:
+		return mknod_wsl(xid, inode, dentry, tcon, full_path, S_IFLNK, 0, symname);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int create_native_symlink(const unsigned int xid, struct inode *inode,
+				 struct dentry *dentry, struct cifs_tcon *tcon,
+				 const char *full_path, const char *symname)
+{
 	struct reparse_symlink_data_buffer *buf = NULL;
-	struct cifs_open_info_data data;
+	struct cifs_open_info_data data = {};
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct inode *new;
 	struct kvec iov;
-	__le16 *path;
+	__le16 *path = NULL;
 	bool directory;
-	char *sym, sep = CIFS_DIR_SEP(cifs_sb);
-	u16 len, plen;
+	char *symlink_target = NULL;
+	char *sym = NULL;
+	char sep = CIFS_DIR_SEP(cifs_sb);
+	u16 len, plen, poff, slen;
 	int rc = 0;
 
 	if (strlen(symname) > REPARSE_SYM_PATH_MAX)
 		return -ENAMETOOLONG;
 
-	sym = kstrdup(symname, GFP_KERNEL);
-	if (!sym)
-		return -ENOMEM;
+	symlink_target = kstrdup(symname, GFP_KERNEL);
+	if (!symlink_target) {
+		rc = -ENOMEM;
+		goto out;
+	}
 
 	data = (struct cifs_open_info_data) {
 		.reparse_point = true,
 		.reparse = { .tag = IO_REPARSE_TAG_SYMLINK, },
-		.symlink_target = sym,
+		.symlink_target = symlink_target,
 	};
 
-	convert_delimiter(sym, sep);
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+		/*
+		 * This is a request to create an absolute symlink on the server
+		 * which does not support POSIX paths, and expects symlink in
+		 * NT-style path. So convert absolute Linux symlink target path
+		 * to the absolute NT-style path. Root of the NT-style path for
+		 * symlinks is specified in "symlinkroot" mount option. This will
+		 * ensure compatibility of this symlink stored in absolute form
+		 * on the SMB server.
+		 */
+		if (!strstarts(symname, cifs_sb->ctx->symlinkroot)) {
+			/*
+			 * If the absolute Linux symlink target path is not
+			 * inside "symlinkroot" location then there is no way
+			 * to convert such Linux symlink to NT-style path.
+			 */
+			cifs_dbg(VFS,
+				 "absolute symlink '%s' cannot be converted to NT format "
+				 "because it is outside of symlinkroot='%s'\n",
+				 symname, cifs_sb->ctx->symlinkroot);
+			rc = -EINVAL;
+			goto out;
+		}
+		len = strlen(cifs_sb->ctx->symlinkroot);
+		if (cifs_sb->ctx->symlinkroot[len-1] != '/')
+			len++;
+		if (symname[len] >= 'a' && symname[len] <= 'z' &&
+		    (symname[len+1] == '/' || symname[len+1] == '\0')) {
+			/*
+			 * Symlink points to Linux target /symlinkroot/x/path/...
+			 * where 'x' is the lowercase local Windows drive.
+			 * NT-style path for 'x' has common form \??\X:\path\...
+			 * with uppercase local Windows drive.
+			 */
+			int common_path_len = strlen(symname+len+1)+1;
+			sym = kzalloc(6+common_path_len, GFP_KERNEL);
+			if (!sym) {
+				rc = -ENOMEM;
+				goto out;
+			}
+			memcpy(sym, "\\??\\", 4);
+			sym[4] = symname[len] - ('a'-'A');
+			sym[5] = ':';
+			memcpy(sym+6, symname+len+1, common_path_len);
+		} else {
+			/* Unhandled absolute symlink. Report an error. */
+			cifs_dbg(
+				 VFS,
+				 "absolute symlink '%s' cannot be converted to NT format "
+				 "because it points to unknown target\n",
+				 symname);
+			rc = -EINVAL;
+			goto out;
+		}
+	} else {
+		/*
+		 * This is request to either create an absolute symlink on
+		 * server which expects POSIX paths or it is an request to
+		 * create a relative symlink from the current directory.
+		 * These paths have same format as relative SMB symlinks,
+		 * so no conversion is needed. So just take symname as-is.
+		 */
+		sym = kstrdup(symname, GFP_KERNEL);
+		if (!sym) {
+			rc = -ENOMEM;
+			goto out;
+		}
+	}
+
+	if (sep == '\\')
+		convert_delimiter(sym, sep);
+
+	/*
+	 * For absolute NT symlinks it is required to pass also leading
+	 * backslash and to not mangle NT object prefix "\\??\\" and not to
+	 * mangle colon in drive letter. But cifs_convert_path_to_utf16()
+	 * removes leading backslash and replaces '?' and ':'. So temporary
+	 * mask these characters in NT object prefix by '_' and then change
+	 * them back.
+	 */
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/')
+		sym[0] = sym[1] = sym[2] = sym[5] = '_';
+
 	path = cifs_convert_path_to_utf16(sym, cifs_sb);
 	if (!path) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+		sym[0] = '\\';
+		sym[1] = sym[2] = '?';
+		sym[5] = ':';
+		path[0] = cpu_to_le16('\\');
+		path[1] = path[2] = cpu_to_le16('?');
+		path[5] = cpu_to_le16(':');
+	}
+
 	/*
 	 * SMB distinguish between symlink to directory and symlink to file.
 	 * They cannot be exchanged (symlink of file type which points to
@@ -67,8 +192,18 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode,
 	if (rc < 0)
 		goto out;
 
-	plen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX);
-	len = sizeof(*buf) + plen * 2;
+	slen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX);
+	poff = 0;
+	plen = slen;
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+		/*
+		 * For absolute NT symlinks skip leading "\\??\\" in PrintName as
+		 * PrintName is user visible location in DOS/Win32 format (not in NT format).
+		 */
+		poff = 4;
+		plen -= 2 * poff;
+	}
+	len = sizeof(*buf) + plen + slen;
 	buf = kzalloc(len, GFP_KERNEL);
 	if (!buf) {
 		rc = -ENOMEM;
@@ -77,17 +212,17 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode,
 
 	buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_SYMLINK);
 	buf->ReparseDataLength = cpu_to_le16(len - sizeof(struct reparse_data_buffer));
+
 	buf->SubstituteNameOffset = cpu_to_le16(plen);
-	buf->SubstituteNameLength = cpu_to_le16(plen);
-	memcpy(&buf->PathBuffer[plen], path, plen);
+	buf->SubstituteNameLength = cpu_to_le16(slen);
+	memcpy(&buf->PathBuffer[plen], path, slen);
+
 	buf->PrintNameOffset = 0;
 	buf->PrintNameLength = cpu_to_le16(plen);
-	memcpy(buf->PathBuffer, path, plen);
+	memcpy(buf->PathBuffer, path+poff, plen);
+
 	buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0);
-	if (*sym != sep)
-		buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE);
 
-	convert_delimiter(sym, '/');
 	iov.iov_base = buf;
 	iov.iov_len = len;
 	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
@@ -98,6 +233,7 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode,
 	else
 		rc = PTR_ERR(new);
 out:
+	kfree(sym);
 	kfree(path);
 	cifs_free_open_info(&data);
 	kfree(buf);
@@ -242,8 +378,39 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb,
 	return 0;
 }
 
-static int nfs_set_reparse_buf(struct reparse_posix_data *buf,
+static int create_native_socket(const unsigned int xid, struct inode *inode,
+				struct dentry *dentry, struct cifs_tcon *tcon,
+				const char *full_path)
+{
+	struct reparse_data_buffer buf = {
+		.ReparseTag = cpu_to_le32(IO_REPARSE_TAG_AF_UNIX),
+		.ReparseDataLength = cpu_to_le16(0),
+	};
+	struct cifs_open_info_data data = {
+		.reparse_point = true,
+		.reparse = { .tag = IO_REPARSE_TAG_AF_UNIX, .buf = &buf, },
+	};
+	struct kvec iov = {
+		.iov_base = &buf,
+		.iov_len = sizeof(buf),
+	};
+	struct inode *new;
+	int rc = 0;
+
+	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
+				     tcon, full_path, false, &iov, NULL);
+	if (!IS_ERR(new))
+		d_instantiate(dentry, new);
+	else
+		rc = PTR_ERR(new);
+	cifs_free_open_info(&data);
+	return rc;
+}
+
+static int nfs_set_reparse_buf(struct reparse_nfs_data_buffer *buf,
 			       mode_t mode, dev_t dev,
+			       __le16 *symname_utf16,
+			       int symname_utf16_len,
 			       struct kvec *iov)
 {
 	u64 type;
@@ -254,7 +421,13 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf,
 	switch ((type = reparse_mode_nfs_type(mode))) {
 	case NFS_SPECFILE_BLK:
 	case NFS_SPECFILE_CHR:
-		dlen = sizeof(__le64);
+		dlen = 2 * sizeof(__le32);
+		((__le32 *)buf->DataBuffer)[0] = cpu_to_le32(MAJOR(dev));
+		((__le32 *)buf->DataBuffer)[1] = cpu_to_le32(MINOR(dev));
+		break;
+	case NFS_SPECFILE_LNK:
+		dlen = symname_utf16_len;
+		memcpy(buf->DataBuffer, symname_utf16, symname_utf16_len);
 		break;
 	case NFS_SPECFILE_FIFO:
 	case NFS_SPECFILE_SOCK:
@@ -269,8 +442,6 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf,
 	buf->InodeType = cpu_to_le64(type);
 	buf->ReparseDataLength = cpu_to_le16(len + dlen -
 					     sizeof(struct reparse_data_buffer));
-	*(__le64 *)buf->DataBuffer = cpu_to_le64(((u64)MINOR(dev) << 32) |
-						 MAJOR(dev));
 	iov->iov_base = buf;
 	iov->iov_len = len + dlen;
 	return 0;
@@ -278,23 +449,45 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf,
 
 static int mknod_nfs(unsigned int xid, struct inode *inode,
 		     struct dentry *dentry, struct cifs_tcon *tcon,
-		     const char *full_path, umode_t mode, dev_t dev)
+		     const char *full_path, umode_t mode, dev_t dev,
+		     const char *symname)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifs_open_info_data data;
-	struct reparse_posix_data *p;
+	struct reparse_nfs_data_buffer *p = NULL;
+	__le16 *symname_utf16 = NULL;
+	int symname_utf16_len = 0;
 	struct inode *new;
 	struct kvec iov;
 	__u8 buf[sizeof(*p) + sizeof(__le64)];
 	int rc;
 
-	p = (struct reparse_posix_data *)buf;
-	rc = nfs_set_reparse_buf(p, mode, dev, &iov);
+	if (S_ISLNK(mode)) {
+		symname_utf16 = cifs_strndup_to_utf16(symname, strlen(symname),
+						      &symname_utf16_len,
+						      cifs_sb->local_nls,
+						      NO_MAP_UNI_RSVD);
+		if (!symname_utf16) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		symname_utf16_len -= 2; /* symlink is without trailing wide-nul */
+		p = kzalloc(sizeof(*p) + symname_utf16_len, GFP_KERNEL);
+		if (!p) {
+			rc = -ENOMEM;
+			goto out;
+		}
+	} else {
+		p = (struct reparse_nfs_data_buffer *)buf;
+	}
+	rc = nfs_set_reparse_buf(p, mode, dev, symname_utf16, symname_utf16_len, &iov);
 	if (rc)
-		return rc;
+		goto out;
 
 	data = (struct cifs_open_info_data) {
 		.reparse_point = true,
-		.reparse = { .tag = IO_REPARSE_TAG_NFS, .posix = p, },
+		.reparse = { .tag = IO_REPARSE_TAG_NFS, .buf = (struct reparse_data_buffer *)p, },
+		.symlink_target = kstrdup(symname, GFP_KERNEL),
 	};
 
 	new = smb2_get_reparse_inode(&data, inode->i_sb, xid,
@@ -304,12 +497,25 @@ static int mknod_nfs(unsigned int xid, struct inode *inode,
 	else
 		rc = PTR_ERR(new);
 	cifs_free_open_info(&data);
+out:
+	if (S_ISLNK(mode)) {
+		kfree(symname_utf16);
+		kfree(p);
+	}
 	return rc;
 }
 
-static int wsl_set_reparse_buf(struct reparse_data_buffer *buf,
-			       mode_t mode, struct kvec *iov)
+static int wsl_set_reparse_buf(struct reparse_data_buffer **buf,
+			       mode_t mode, const char *symname,
+			       struct cifs_sb_info *cifs_sb,
+			       struct kvec *iov)
 {
+	struct reparse_wsl_symlink_data_buffer *symlink_buf;
+	__le16 *symname_utf16;
+	int symname_utf16_len;
+	int symname_utf8_maxlen;
+	int symname_utf8_len;
+	size_t buf_len;
 	u32 tag;
 
 	switch ((tag = reparse_mode_wsl_tag(mode))) {
@@ -317,16 +523,45 @@ static int wsl_set_reparse_buf(struct reparse_data_buffer *buf,
 	case IO_REPARSE_TAG_LX_CHR:
 	case IO_REPARSE_TAG_LX_FIFO:
 	case IO_REPARSE_TAG_AF_UNIX:
+		buf_len = sizeof(struct reparse_data_buffer);
+		*buf = kzalloc(buf_len, GFP_KERNEL);
+		if (!*buf)
+			return -ENOMEM;
+		break;
+	case IO_REPARSE_TAG_LX_SYMLINK:
+		symname_utf16 = cifs_strndup_to_utf16(symname, strlen(symname),
+						      &symname_utf16_len,
+						      cifs_sb->local_nls,
+						      NO_MAP_UNI_RSVD);
+		if (!symname_utf16)
+			return -ENOMEM;
+		symname_utf8_maxlen = symname_utf16_len/2*3;
+		symlink_buf = kzalloc(sizeof(struct reparse_wsl_symlink_data_buffer) +
+				      symname_utf8_maxlen, GFP_KERNEL);
+		if (!symlink_buf) {
+			kfree(symname_utf16);
+			return -ENOMEM;
+		}
+		/* Flag 0x02000000 is unknown, but all wsl symlinks have this value */
+		symlink_buf->Flags = cpu_to_le32(0x02000000);
+		/* PathBuffer is in UTF-8 but without trailing null-term byte */
+		symname_utf8_len = utf16s_to_utf8s((wchar_t *)symname_utf16, symname_utf16_len/2,
+						   UTF16_LITTLE_ENDIAN,
+						   symlink_buf->PathBuffer,
+						   symname_utf8_maxlen);
+		*buf = (struct reparse_data_buffer *)symlink_buf;
+		buf_len = sizeof(struct reparse_wsl_symlink_data_buffer) + symname_utf8_len;
+		kfree(symname_utf16);
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	buf->ReparseTag = cpu_to_le32(tag);
-	buf->Reserved = 0;
-	buf->ReparseDataLength = 0;
-	iov->iov_base = buf;
-	iov->iov_len = sizeof(*buf);
+	(*buf)->ReparseTag = cpu_to_le32(tag);
+	(*buf)->Reserved = 0;
+	(*buf)->ReparseDataLength = cpu_to_le16(buf_len - sizeof(struct reparse_data_buffer));
+	iov->iov_base = *buf;
+	iov->iov_len = buf_len;
 	return 0;
 }
 
@@ -415,27 +650,32 @@ static int wsl_set_xattrs(struct inode *inode, umode_t _mode,
 
 static int mknod_wsl(unsigned int xid, struct inode *inode,
 		     struct dentry *dentry, struct cifs_tcon *tcon,
-		     const char *full_path, umode_t mode, dev_t dev)
+		     const char *full_path, umode_t mode, dev_t dev,
+		     const char *symname)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifs_open_info_data data;
-	struct reparse_data_buffer buf;
+	struct reparse_data_buffer *buf;
 	struct smb2_create_ea_ctx *cc;
 	struct inode *new;
 	unsigned int len;
 	struct kvec reparse_iov, xattr_iov;
 	int rc;
 
-	rc = wsl_set_reparse_buf(&buf, mode, &reparse_iov);
+	rc = wsl_set_reparse_buf(&buf, mode, symname, cifs_sb, &reparse_iov);
 	if (rc)
 		return rc;
 
 	rc = wsl_set_xattrs(inode, mode, dev, &xattr_iov);
-	if (rc)
+	if (rc) {
+		kfree(buf);
 		return rc;
+	}
 
 	data = (struct cifs_open_info_data) {
 		.reparse_point = true,
-		.reparse = { .tag = le32_to_cpu(buf.ReparseTag), .buf = &buf, },
+		.reparse = { .tag = le32_to_cpu(buf->ReparseTag), .buf = buf, },
+		.symlink_target = kstrdup(symname, GFP_KERNEL),
 	};
 
 	cc = xattr_iov.iov_base;
@@ -452,6 +692,7 @@ static int mknod_wsl(unsigned int xid, struct inode *inode,
 		rc = PTR_ERR(new);
 	cifs_free_open_info(&data);
 	kfree(xattr_iov.iov_base);
+	kfree(buf);
 	return rc;
 }
 
@@ -460,21 +701,22 @@ int smb2_mknod_reparse(unsigned int xid, struct inode *inode,
 		       const char *full_path, umode_t mode, dev_t dev)
 {
 	struct smb3_fs_context *ctx = CIFS_SB(inode->i_sb)->ctx;
-	int rc = -EOPNOTSUPP;
+
+	if (S_ISSOCK(mode) && !ctx->nonativesocket && ctx->reparse_type != CIFS_REPARSE_TYPE_NONE)
+		return create_native_socket(xid, inode, dentry, tcon, full_path);
 
 	switch (ctx->reparse_type) {
 	case CIFS_REPARSE_TYPE_NFS:
-		rc = mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev);
-		break;
+		return mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev, NULL);
 	case CIFS_REPARSE_TYPE_WSL:
-		rc = mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev);
-		break;
+		return mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev, NULL);
+	default:
+		return -EOPNOTSUPP;
 	}
-	return rc;
 }
 
 /* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */
-static int parse_reparse_posix(struct reparse_posix_data *buf,
+static int parse_reparse_nfs(struct reparse_nfs_data_buffer *buf,
 			       struct cifs_sb_info *cifs_sb,
 			       struct cifs_open_info_data *data)
 {
@@ -536,43 +778,160 @@ static int parse_reparse_posix(struct reparse_posix_data *buf,
 }
 
 int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
-			      bool unicode, bool relative,
+			      bool relative,
 			      const char *full_path,
 			      struct cifs_sb_info *cifs_sb)
 {
 	char sep = CIFS_DIR_SEP(cifs_sb);
 	char *linux_target = NULL;
 	char *smb_target = NULL;
+	int symlinkroot_len;
+	int abs_path_len;
+	char *abs_path;
 	int levels;
 	int rc;
 	int i;
 
-	/* Check that length it valid for unicode/non-unicode mode */
-	if (!len || (unicode && (len % 2))) {
+	/* Check that length it valid */
+	if (!len || (len % 2)) {
 		cifs_dbg(VFS, "srv returned malformed symlink buffer\n");
 		rc = -EIO;
 		goto out;
 	}
 
 	/*
-	 * Check that buffer does not contain UTF-16 null codepoint in unicode
-	 * mode or null byte in non-unicode mode because Linux cannot process
-	 * symlink with null byte.
+	 * Check that buffer does not contain UTF-16 null codepoint
+	 * because Linux cannot process symlink with null byte.
 	 */
-	if ((unicode && UniStrnlen((wchar_t *)buf, len/2) != len/2) ||
-	    (!unicode && strnlen(buf, len) != len)) {
+	if (UniStrnlen((wchar_t *)buf, len/2) != len/2) {
 		cifs_dbg(VFS, "srv returned null byte in native symlink target location\n");
 		rc = -EIO;
 		goto out;
 	}
 
-	smb_target = cifs_strndup_from_utf16(buf, len, unicode, cifs_sb->local_nls);
+	smb_target = cifs_strndup_from_utf16(buf, len, true, cifs_sb->local_nls);
 	if (!smb_target) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	if (smb_target[0] == sep && relative) {
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && !relative) {
+		/*
+		 * This is an absolute symlink from the server which does not
+		 * support POSIX paths, so the symlink is in NT-style path.
+		 * So convert it to absolute Linux symlink target path. Root of
+		 * the NT-style path for symlinks is specified in "symlinkroot"
+		 * mount option.
+		 *
+		 * Root of the DOS and Win32 paths is at NT path \??\
+		 * It means that DOS/Win32 path C:\folder\file.txt is
+		 * NT path \??\C:\folder\file.txt
+		 *
+		 * NT systems have some well-known object symlinks in their NT
+		 * hierarchy, which is needed to take into account when resolving
+		 * other symlinks. Most commonly used symlink paths are:
+		 * \?? -> \GLOBAL??
+		 * \DosDevices -> \??
+		 * \GLOBAL??\GLOBALROOT -> \
+		 * \GLOBAL??\Global -> \GLOBAL??
+		 * \GLOBAL??\NUL -> \Device\Null
+		 * \GLOBAL??\UNC -> \Device\Mup
+		 * \GLOBAL??\PhysicalDrive0 -> \Device\Harddisk0\DR0 (for each harddisk)
+		 * \GLOBAL??\A: -> \Device\Floppy0 (if A: is the first floppy)
+		 * \GLOBAL??\C: -> \Device\HarddiskVolume1 (if C: is the first harddisk)
+		 * \GLOBAL??\D: -> \Device\CdRom0 (if D: is first cdrom)
+		 * \SystemRoot -> \Device\Harddisk0\Partition1\WINDOWS (or where is NT system installed)
+		 * \Volume{...} -> \Device\HarddiskVolume1 (where ... is system generated guid)
+		 *
+		 * In most common cases, absolute NT symlinks points to path on
+		 * DOS/Win32 drive letter, system-specific Volume or on UNC share.
+		 * Here are few examples of commonly used absolute NT symlinks
+		 * created by mklink.exe tool:
+		 * \??\C:\folder\file.txt
+		 * \??\\C:\folder\file.txt
+		 * \??\UNC\server\share\file.txt
+		 * \??\\UNC\server\share\file.txt
+		 * \??\Volume{b75e2c83-0000-0000-0000-602f00000000}\folder\file.txt
+		 *
+		 * It means that the most common path prefix \??\ is also NT path
+		 * symlink (to \GLOBAL??). It is less common that second path
+		 * separator is double backslash, but it is valid.
+		 *
+		 * Volume guid is randomly generated by the target system and so
+		 * only the target system knows the mapping between guid and the
+		 * hardisk number. Over SMB it is not possible to resolve this
+		 * mapping, therefore symlinks pointing to target location of
+		 * volume guids are totally unusable over SMB.
+		 *
+		 * For now parse only symlink paths available for DOS and Win32.
+		 * Those are paths with \??\ prefix or paths which points to \??\
+		 * via other NT symlink (\DosDevices\, \GLOBAL??\, ...).
+		 */
+		abs_path = smb_target;
+globalroot:
+		if (strstarts(abs_path, "\\??\\"))
+			abs_path += sizeof("\\??\\")-1;
+		else if (strstarts(abs_path, "\\DosDevices\\"))
+			abs_path += sizeof("\\DosDevices\\")-1;
+		else if (strstarts(abs_path, "\\GLOBAL??\\"))
+			abs_path += sizeof("\\GLOBAL??\\")-1;
+		else {
+			/* Unhandled absolute symlink, points outside of DOS/Win32 */
+			cifs_dbg(VFS,
+				 "absolute symlink '%s' cannot be converted from NT format "
+				 "because points to unknown target\n",
+				 smb_target);
+			rc = -EIO;
+			goto out;
+		}
+
+		/* Sometimes path separator after \?? is double backslash */
+		if (abs_path[0] == '\\')
+			abs_path++;
+
+		while (strstarts(abs_path, "Global\\"))
+			abs_path += sizeof("Global\\")-1;
+
+		if (strstarts(abs_path, "GLOBALROOT\\")) {
+			/* Label globalroot requires path with leading '\\', so do not trim '\\' */
+			abs_path += sizeof("GLOBALROOT")-1;
+			goto globalroot;
+		}
+
+		/* For now parse only paths to drive letters */
+		if (((abs_path[0] >= 'A' && abs_path[0] <= 'Z') ||
+		     (abs_path[0] >= 'a' && abs_path[0] <= 'z')) &&
+		    abs_path[1] == ':' &&
+		    (abs_path[2] == '\\' || abs_path[2] == '\0')) {
+			/* Convert drive letter to lowercase and drop colon */
+			char drive_letter = abs_path[0];
+			if (drive_letter >= 'A' && drive_letter <= 'Z')
+				drive_letter += 'a'-'A';
+			abs_path++;
+			abs_path[0] = drive_letter;
+		} else {
+			/* Unhandled absolute symlink. Report an error. */
+			cifs_dbg(VFS,
+				 "absolute symlink '%s' cannot be converted from NT format "
+				 "because points to unknown target\n",
+				 smb_target);
+			rc = -EIO;
+			goto out;
+		}
+
+		abs_path_len = strlen(abs_path)+1;
+		symlinkroot_len = strlen(cifs_sb->ctx->symlinkroot);
+		if (cifs_sb->ctx->symlinkroot[symlinkroot_len-1] == '/')
+			symlinkroot_len--;
+		linux_target = kmalloc(symlinkroot_len + 1 + abs_path_len, GFP_KERNEL);
+		if (!linux_target) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		memcpy(linux_target, cifs_sb->ctx->symlinkroot, symlinkroot_len);
+		linux_target[symlinkroot_len] = '/';
+		memcpy(linux_target + symlinkroot_len + 1, abs_path, abs_path_len);
+	} else if (smb_target[0] == sep && relative) {
 		/*
 		 * This is a relative SMB symlink from the top of the share,
 		 * which is the top level directory of the Linux mount point.
@@ -601,6 +960,12 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
 		}
 		memcpy(linux_target + levels*3, smb_target+1, smb_target_len); /* +1 to skip leading sep */
 	} else {
+		/*
+		 * This is either an absolute symlink in POSIX-style format
+		 * or relative SMB symlink from the current directory.
+		 * These paths have same format as Linux symlinks, so no
+		 * conversion is needed.
+		 */
 		linux_target = smb_target;
 		smb_target = NULL;
 	}
@@ -620,8 +985,8 @@ out:
 	return rc;
 }
 
-static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym,
-				 u32 plen, bool unicode,
+static int parse_reparse_native_symlink(struct reparse_symlink_data_buffer *sym,
+				 u32 plen,
 				 struct cifs_sb_info *cifs_sb,
 				 const char *full_path,
 				 struct cifs_open_info_data *data)
@@ -641,7 +1006,6 @@ static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym,
 	return smb2_parse_native_symlink(&data->symlink_target,
 					 sym->PathBuffer + offs,
 					 len,
-					 unicode,
 					 le32_to_cpu(sym->Flags) & SYMLINK_FLAG_RELATIVE,
 					 full_path,
 					 cifs_sb);
@@ -696,7 +1060,7 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf
 int parse_reparse_point(struct reparse_data_buffer *buf,
 			u32 plen, struct cifs_sb_info *cifs_sb,
 			const char *full_path,
-			bool unicode, struct cifs_open_info_data *data)
+			struct cifs_open_info_data *data)
 {
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
@@ -705,12 +1069,12 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
 	/* See MS-FSCC 2.1.2 */
 	switch (le32_to_cpu(buf->ReparseTag)) {
 	case IO_REPARSE_TAG_NFS:
-		return parse_reparse_posix((struct reparse_posix_data *)buf,
+		return parse_reparse_nfs((struct reparse_nfs_data_buffer *)buf,
 					   cifs_sb, data);
 	case IO_REPARSE_TAG_SYMLINK:
-		return parse_reparse_symlink(
+		return parse_reparse_native_symlink(
 			(struct reparse_symlink_data_buffer *)buf,
-			plen, unicode, cifs_sb, full_path, data);
+			plen, cifs_sb, full_path, data);
 	case IO_REPARSE_TAG_LX_SYMLINK:
 		return parse_reparse_wsl_symlink(
 			(struct reparse_wsl_symlink_data_buffer *)buf,
@@ -744,14 +1108,15 @@ int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
 
 	buf = (struct reparse_data_buffer *)((u8 *)io +
 					     le32_to_cpu(io->OutputOffset));
-	return parse_reparse_point(buf, plen, cifs_sb, full_path, true, data);
+	return parse_reparse_point(buf, plen, cifs_sb, full_path, data);
 }
 
-static void wsl_to_fattr(struct cifs_open_info_data *data,
+static bool wsl_to_fattr(struct cifs_open_info_data *data,
 			 struct cifs_sb_info *cifs_sb,
 			 u32 tag, struct cifs_fattr *fattr)
 {
 	struct smb2_file_full_ea_info *ea;
+	bool have_xattr_dev = false;
 	u32 next = 0;
 
 	switch (tag) {
@@ -794,21 +1159,31 @@ static void wsl_to_fattr(struct cifs_open_info_data *data,
 			fattr->cf_uid = wsl_make_kuid(cifs_sb, v);
 		else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen))
 			fattr->cf_gid = wsl_make_kgid(cifs_sb, v);
-		else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen))
+		else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) {
+			/* File type in reparse point tag and in xattr mode must match. */
+			if (S_DT(fattr->cf_mode) != S_DT(le32_to_cpu(*(__le32 *)v)))
+				return false;
 			fattr->cf_mode = (umode_t)le32_to_cpu(*(__le32 *)v);
-		else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen))
+		} else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) {
 			fattr->cf_rdev = reparse_mkdev(v);
+			have_xattr_dev = true;
+		}
 	} while (next);
 out:
+
+	/* Major and minor numbers for char and block devices are mandatory. */
+	if (!have_xattr_dev && (tag == IO_REPARSE_TAG_LX_CHR || tag == IO_REPARSE_TAG_LX_BLK))
+		return false;
+
 	fattr->cf_dtype = S_DT(fattr->cf_mode);
+	return true;
 }
 
 static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb,
 				   struct cifs_fattr *fattr,
 				   struct cifs_open_info_data *data)
 {
-	struct reparse_posix_data *buf = data->reparse.posix;
-
+	struct reparse_nfs_data_buffer *buf = (struct reparse_nfs_data_buffer *)data->reparse.buf;
 
 	if (buf == NULL)
 		return true;
@@ -874,7 +1249,9 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
 	case IO_REPARSE_TAG_AF_UNIX:
 	case IO_REPARSE_TAG_LX_CHR:
 	case IO_REPARSE_TAG_LX_BLK:
-		wsl_to_fattr(data, cifs_sb, tag, fattr);
+		ok = wsl_to_fattr(data, cifs_sb, tag, fattr);
+		if (!ok)
+			return false;
 		break;
 	case IO_REPARSE_TAG_NFS:
 		ok = posix_reparse_to_fattr(cifs_sb, fattr, data);
diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
index ff05b0e75c92..5a753fec7e2c 100644
--- a/fs/smb/client/reparse.h
+++ b/fs/smb/client/reparse.h
@@ -50,6 +50,7 @@ static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb,
 static inline u64 reparse_mode_nfs_type(mode_t mode)
 {
 	switch (mode & S_IFMT) {
+	case S_IFLNK: return NFS_SPECFILE_LNK;
 	case S_IFBLK: return NFS_SPECFILE_BLK;
 	case S_IFCHR: return NFS_SPECFILE_CHR;
 	case S_IFIFO: return NFS_SPECFILE_FIFO;
@@ -61,6 +62,7 @@ static inline u64 reparse_mode_nfs_type(mode_t mode)
 static inline u32 reparse_mode_wsl_tag(mode_t mode)
 {
 	switch (mode & S_IFMT) {
+	case S_IFLNK: return IO_REPARSE_TAG_LX_SYMLINK;
 	case S_IFBLK: return IO_REPARSE_TAG_LX_BLK;
 	case S_IFCHR: return IO_REPARSE_TAG_LX_CHR;
 	case S_IFIFO: return IO_REPARSE_TAG_LX_FIFO;
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index 91d4d409cb1d..faa80e7d54a6 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -1235,12 +1235,13 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		switch (requested) {
 		case Kerberos:
 		case RawNTLMSSP:
+		case IAKerb:
 			return requested;
 		case Unspecified:
 			if (server->sec_ntlmssp &&
 			    (global_secflags & CIFSSEC_MAY_NTLMSSP))
 				return RawNTLMSSP;
-			if ((server->sec_kerberos || server->sec_mskerberos) &&
+			if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) &&
 			    (global_secflags & CIFSSEC_MAY_KRB5))
 				return Kerberos;
 			fallthrough;
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 749a83cd0deb..d6e2fb669c40 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -377,7 +377,7 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)
 static void
 cifs_downgrade_oplock(struct TCP_Server_Info *server,
 		      struct cifsInodeInfo *cinode, __u32 oplock,
-		      unsigned int epoch, bool *purge_cache)
+		      __u16 epoch, bool *purge_cache)
 {
 	cifs_set_oplock_level(cinode, oplock);
 }
@@ -551,7 +551,7 @@ static int cifs_query_path_info(const unsigned int xid,
 	int rc;
 	FILE_ALL_INFO fi = {};
 
-	data->symlink = false;
+	data->reparse_point = false;
 	data->adjust_tz = false;
 
 	/* could do find first instead but this returns more info */
@@ -569,32 +569,8 @@ static int cifs_query_path_info(const unsigned int xid,
 	}
 
 	if (!rc) {
-		int tmprc;
-		int oplock = 0;
-		struct cifs_fid fid;
-		struct cifs_open_parms oparms;
-
 		move_cifs_info_to_smb2(&data->fi, &fi);
-
-		if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE))
-			return 0;
-
-		oparms = (struct cifs_open_parms) {
-			.tcon = tcon,
-			.cifs_sb = cifs_sb,
-			.desired_access = FILE_READ_ATTRIBUTES,
-			.create_options = cifs_create_options(cifs_sb, 0),
-			.disposition = FILE_OPEN,
-			.path = full_path,
-			.fid = &fid,
-		};
-
-		/* Need to check if this is a symbolic link or not */
-		tmprc = CIFS_open(xid, &oparms, &oplock, NULL);
-		if (tmprc == -EOPNOTSUPP)
-			data->symlink = true;
-		else if (tmprc == 0)
-			CIFSSMBClose(xid, tcon, fid.netfid);
+		data->reparse_point = le32_to_cpu(fi.Attributes) & ATTR_REPARSE;
 	}
 
 	return rc;
@@ -1010,7 +986,7 @@ static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb,
 
 	buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol +
 					     le32_to_cpu(io->DataOffset));
-	return parse_reparse_point(buf, plen, cifs_sb, full_path, true, data);
+	return parse_reparse_point(buf, plen, cifs_sb, full_path, data);
 }
 
 static bool
diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c
index 9ec44eab8dbc..d609a20fb98a 100644
--- a/fs/smb/client/smb2file.c
+++ b/fs/smb/client/smb2file.c
@@ -63,6 +63,52 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov)
 	return sym;
 }
 
+int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_info *cifs_sb)
+{
+	char *buf;
+	int len;
+
+	/*
+	 * POSIX server does not distinguish between symlinks to file and
+	 * symlink directory. So nothing is needed to fix on the client side.
+	 */
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
+		return 0;
+
+	if (!*target)
+		return -EIO;
+
+	len = strlen(*target);
+	if (!len)
+		return -EIO;
+
+	/*
+	 * If this is directory symlink and it does not have trailing slash then
+	 * append it. Trailing slash simulates Windows/SMB behavior which do not
+	 * allow resolving directory symlink to file.
+	 */
+	if (directory && (*target)[len-1] != '/') {
+		buf = krealloc(*target, len+2, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		buf[len] = '/';
+		buf[len+1] = '\0';
+		*target = buf;
+		len++;
+	}
+
+	/*
+	 * If this is a file (non-directory) symlink and it points to path name
+	 * with trailing slash then this is an invalid symlink because file name
+	 * cannot contain slash character. File name with slash is invalid on
+	 * both Windows and Linux systems. So return an error for such symlink.
+	 */
+	if (!directory && (*target)[len-1] == '/')
+		return -EIO;
+
+	return 0;
+}
+
 int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov,
 				const char *full_path, char **path)
 {
@@ -89,7 +135,6 @@ int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec
 	return smb2_parse_native_symlink(path,
 					 (char *)sym->PathBuffer + sub_offs,
 					 sub_len,
-					 true,
 					 le32_to_cpu(sym->Flags) & SYMLINK_FLAG_RELATIVE,
 					 full_path,
 					 cifs_sb);
@@ -133,6 +178,11 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32
 					       NULL, NULL, NULL);
 				oparms->create_options &= ~OPEN_REPARSE_POINT;
 			}
+			if (!rc) {
+				bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY;
+				rc = smb2_fix_symlink_target_type(&data->symlink_target,
+								  directory, oparms->cifs_sb);
+			}
 		}
 	}
 
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index c97f14757c27..5dfb30b0a852 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1010,6 +1010,11 @@ int smb2_query_path_info(const unsigned int xid,
 			else
 				rc = -EOPNOTSUPP;
 		}
+
+		if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) {
+			bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY;
+			rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb);
+		}
 		break;
 	case -EREMOTE:
 		break;
diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c
index b05313acf9b2..12c2b868789f 100644
--- a/fs/smb/client/smb2maperror.c
+++ b/fs/smb/client/smb2maperror.c
@@ -380,7 +380,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_NO_LOGON_SERVERS, -EIO, "STATUS_NO_LOGON_SERVERS"},
 	{STATUS_NO_SUCH_LOGON_SESSION, -EIO, "STATUS_NO_SUCH_LOGON_SESSION"},
 	{STATUS_NO_SUCH_PRIVILEGE, -EIO, "STATUS_NO_SUCH_PRIVILEGE"},
-	{STATUS_PRIVILEGE_NOT_HELD, -EIO, "STATUS_PRIVILEGE_NOT_HELD"},
+	{STATUS_PRIVILEGE_NOT_HELD, -EPERM, "STATUS_PRIVILEGE_NOT_HELD"},
 	{STATUS_INVALID_ACCOUNT_NAME, -EIO, "STATUS_INVALID_ACCOUNT_NAME"},
 	{STATUS_USER_EXISTS, -EIO, "STATUS_USER_EXISTS"},
 	{STATUS_NO_SUCH_USER, -EIO, "STATUS_NO_SUCH_USER"},
@@ -871,7 +871,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = {
 	{STATUS_VALIDATE_CONTINUE, -EIO, "STATUS_VALIDATE_CONTINUE"},
 	{STATUS_NO_MATCH, -EIO, "STATUS_NO_MATCH"},
 	{STATUS_NO_MORE_MATCHES, -EIO, "STATUS_NO_MORE_MATCHES"},
-	{STATUS_NOT_A_REPARSE_POINT, -EIO, "STATUS_NOT_A_REPARSE_POINT"},
+	{STATUS_NOT_A_REPARSE_POINT, -ENODATA, "STATUS_NOT_A_REPARSE_POINT"},
 	{STATUS_IO_REPARSE_TAG_INVALID, -EIO, "STATUS_IO_REPARSE_TAG_INVALID"},
 	{STATUS_IO_REPARSE_TAG_MISMATCH, -EIO,
 	"STATUS_IO_REPARSE_TAG_MISMATCH"},
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index d640dcabc305..ec36bed54b0b 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3904,22 +3904,22 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
 static void
 smb2_downgrade_oplock(struct TCP_Server_Info *server,
 		      struct cifsInodeInfo *cinode, __u32 oplock,
-		      unsigned int epoch, bool *purge_cache)
+		      __u16 epoch, bool *purge_cache)
 {
 	server->ops->set_oplock_level(cinode, oplock, 0, NULL);
 }
 
 static void
 smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
-		       unsigned int epoch, bool *purge_cache);
+		       __u16 epoch, bool *purge_cache);
 
 static void
 smb3_downgrade_oplock(struct TCP_Server_Info *server,
 		       struct cifsInodeInfo *cinode, __u32 oplock,
-		       unsigned int epoch, bool *purge_cache)
+		       __u16 epoch, bool *purge_cache)
 {
 	unsigned int old_state = cinode->oplock;
-	unsigned int old_epoch = cinode->epoch;
+	__u16 old_epoch = cinode->epoch;
 	unsigned int new_state;
 
 	if (epoch > old_epoch) {
@@ -3939,7 +3939,7 @@ smb3_downgrade_oplock(struct TCP_Server_Info *server,
 
 static void
 smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
-		      unsigned int epoch, bool *purge_cache)
+		      __u16 epoch, bool *purge_cache)
 {
 	oplock &= 0xFF;
 	cinode->lease_granted = false;
@@ -3963,7 +3963,7 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
 
 static void
 smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
-		       unsigned int epoch, bool *purge_cache)
+		       __u16 epoch, bool *purge_cache)
 {
 	char message[5] = {0};
 	unsigned int new_oplock = 0;
@@ -4000,7 +4000,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
 
 static void
 smb3_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
-		      unsigned int epoch, bool *purge_cache)
+		      __u16 epoch, bool *purge_cache)
 {
 	unsigned int old_oplock = cinode->oplock;
 
@@ -4114,7 +4114,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
 }
 
 static __u8
-smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
+smb2_parse_lease_buf(void *buf, __u16 *epoch, char *lease_key)
 {
 	struct create_lease *lc = (struct create_lease *)buf;
 
@@ -4125,7 +4125,7 @@ smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
 }
 
 static __u8
-smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
+smb3_parse_lease_buf(void *buf, __u16 *epoch, char *lease_key)
 {
 	struct create_lease_v2 *lc = (struct create_lease_v2 *)buf;
 
@@ -5077,6 +5077,7 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
 {
 	struct TCP_Server_Info *server = tcon->ses->server;
 	struct cifs_open_parms oparms;
+	struct cifs_open_info_data idata;
 	struct cifs_io_parms io_parms = {};
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifs_fid fid;
@@ -5146,10 +5147,20 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
 			     CREATE_OPTION_SPECIAL, ACL_NO_MODE);
 	oparms.fid = &fid;
 
-	rc = server->ops->open(xid, &oparms, &oplock, NULL);
+	rc = server->ops->open(xid, &oparms, &oplock, &idata);
 	if (rc)
 		goto out;
 
+	/*
+	 * Check if the server honored ATTR_SYSTEM flag by CREATE_OPTION_SPECIAL
+	 * option. If not then server does not support ATTR_SYSTEM and newly
+	 * created file is not SFU compatible, which means that the call failed.
+	 */
+	if (!(le32_to_cpu(idata.fi.Attributes) & ATTR_SYSTEM)) {
+		rc = -EOPNOTSUPP;
+		goto out_close;
+	}
+
 	if (type_len + data_len > 0) {
 		io_parms.pid = current->tgid;
 		io_parms.tcon = tcon;
@@ -5164,8 +5175,18 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
 					     iov, ARRAY_SIZE(iov)-1);
 	}
 
+out_close:
 	server->ops->close(xid, tcon, &fid);
 
+	/*
+	 * If CREATE was successful but either setting ATTR_SYSTEM failed or
+	 * writing type/data information failed then remove the intermediate
+	 * object created by CREATE. Otherwise intermediate empty object stay
+	 * on the server.
+	 */
+	if (rc)
+		server->ops->unlink(xid, tcon, full_path, cifs_sb, NULL);
+
 out:
 	kfree(symname_utf16);
 	return rc;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 9f54596a6866..ed7812247ebc 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -1429,7 +1429,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 		if (server->sec_ntlmssp &&
 			(global_secflags & CIFSSEC_MAY_NTLMSSP))
 			return RawNTLMSSP;
-		if ((server->sec_kerberos || server->sec_mskerberos) &&
+		if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) &&
 			(global_secflags & CIFSSEC_MAY_KRB5))
 			return Kerberos;
 		fallthrough;
@@ -2169,7 +2169,7 @@ tcon_exit:
 
 tcon_error_exit:
 	if (rsp && rsp->hdr.Status == STATUS_BAD_NETWORK_NAME)
-		cifs_tcon_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
+		cifs_dbg(VFS | ONCE, "BAD_NETWORK_NAME: %s\n", tree);
 	goto tcon_exit;
 }
 
@@ -2329,7 +2329,7 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info,
 
 int smb2_parse_contexts(struct TCP_Server_Info *server,
 			struct kvec *rsp_iov,
-			unsigned int *epoch,
+			__u16 *epoch,
 			char *lease_key, __u8 *oplock,
 			struct smb2_file_all_info *buf,
 			struct create_posix_rsp *posix)
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 09349fa8da03..4662c7e2d259 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -111,8 +111,9 @@ extern int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 			  struct cifs_sb_info *cifs_sb,
 			  const unsigned char *path, char *pbuf,
 			  unsigned int *pbytes_read);
+int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_info *cifs_sb);
 int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
-			      bool unicode, bool relative,
+			      bool relative,
 			      const char *full_path,
 			      struct cifs_sb_info *cifs_sb);
 int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb,
@@ -282,7 +283,7 @@ extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
 int smb2_parse_contexts(struct TCP_Server_Info *server,
 			struct kvec *rsp_iov,
-			unsigned int *epoch,
+			__u16 *epoch,
 			char *lease_key, __u8 *oplock,
 			struct smb2_file_all_info *buf,
 			struct create_posix_rsp *posix);
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 3c7c706c797d..3336df2ea5d4 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -1550,7 +1550,19 @@ struct reparse_symlink_data_buffer {
 	__u8	PathBuffer[]; /* Variable Length */
 } __packed;
 
-/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */
+/* For IO_REPARSE_TAG_NFS - see MS-FSCC 2.1.2.6 */
+#define NFS_SPECFILE_LNK	0x00000000014B4E4C
+#define NFS_SPECFILE_CHR	0x0000000000524843
+#define NFS_SPECFILE_BLK	0x00000000004B4C42
+#define NFS_SPECFILE_FIFO	0x000000004F464946
+#define NFS_SPECFILE_SOCK	0x000000004B434F53
+struct reparse_nfs_data_buffer {
+	__le32	ReparseTag;
+	__le16	ReparseDataLength;
+	__u16	Reserved;
+	__le64	InodeType; /* NFS_SPECFILE_* */
+	__u8	DataBuffer[];
+} __packed;
 
 /* For IO_REPARSE_TAG_LX_SYMLINK */
 struct reparse_wsl_symlink_data_buffer {
diff --git a/fs/splice.c b/fs/splice.c
index 2898fa1e9e63..28cfa63aa236 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -342,7 +342,7 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
 		return -ENOMEM;
 
 	pages = (struct page **)(bv + npages);
-	npages = alloc_pages_bulk_array(GFP_USER, npages, pages);
+	npages = alloc_pages_bulk(GFP_USER, npages, pages);
 	if (!npages) {
 		kfree(bv);
 		return -ENOMEM;
diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig
index 60fc98bdf421..b1091e70434a 100644
--- a/fs/squashfs/Kconfig
+++ b/fs/squashfs/Kconfig
@@ -5,8 +5,8 @@ config SQUASHFS
 	help
 	  Saying Y here includes support for SquashFS 4.0 (a Compressed
 	  Read-Only File System).  Squashfs is a highly compressed read-only
-	  filesystem for Linux.  It uses zlib, lzo or xz compression to
-	  compress both files, inodes and directories.  Inodes in the system
+	  filesystem for Linux.  It uses zlib, lz4, lzo, xz or zstd compression
+	  to compress both files, inodes and directories.  Inodes in the system
 	  are very small and all blocks are packed to minimise data overhead.
 	  Block sizes greater than 4K are supported up to a maximum of 1 Mbytes
 	  (default block size 128K).  SquashFS 4.0 supports 64 bit filesystems
@@ -16,7 +16,7 @@ config SQUASHFS
 	  Squashfs is intended for general read-only filesystem use, for
 	  archival use (i.e. in cases where a .tar.gz file may be used), and in
 	  embedded systems where low overhead is needed.  Further information
-	  and tools are available from http://squashfs.sourceforge.net.
+	  and tools are available from github.com/plougher/squashfs-tools.
 
 	  If you want to compile this as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want),
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 5062326d0efb..4db0d2b0aab8 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -224,11 +224,15 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 	int block_size)
 {
 	int i, j;
-	struct squashfs_cache *cache = kzalloc(sizeof(*cache), GFP_KERNEL);
+	struct squashfs_cache *cache;
 
+	if (entries == 0)
+		return NULL;
+
+	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
 	if (cache == NULL) {
 		ERROR("Failed to allocate %s cache\n", name);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	cache->entry = kcalloc(entries, sizeof(*(cache->entry)), GFP_KERNEL);
@@ -281,7 +285,7 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries,
 
 cleanup:
 	squashfs_cache_delete(cache);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
 
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 21aaa96856c1..5ca2baa16dc2 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -362,29 +362,33 @@ static int read_blocklist(struct inode *inode, int index, u64 *block)
 	return squashfs_block_size(size);
 }
 
-void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail)
+static bool squashfs_fill_page(struct folio *folio,
+		struct squashfs_cache_entry *buffer, size_t offset,
+		size_t avail)
 {
-	int copied;
+	size_t copied;
 	void *pageaddr;
 
-	pageaddr = kmap_atomic(page);
+	pageaddr = kmap_local_folio(folio, 0);
 	copied = squashfs_copy_data(pageaddr, buffer, offset, avail);
 	memset(pageaddr + copied, 0, PAGE_SIZE - copied);
-	kunmap_atomic(pageaddr);
+	kunmap_local(pageaddr);
 
-	flush_dcache_page(page);
-	if (copied == avail)
-		SetPageUptodate(page);
+	flush_dcache_folio(folio);
+
+	return copied == avail;
 }
 
 /* Copy data into page cache  */
-void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
-	int bytes, int offset)
+void squashfs_copy_cache(struct folio *folio,
+		struct squashfs_cache_entry *buffer, size_t bytes,
+		size_t offset)
 {
-	struct inode *inode = page->mapping->host;
+	struct address_space *mapping = folio->mapping;
+	struct inode *inode = mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
-	int start_index = page->index & ~mask, end_index = start_index | mask;
+	int start_index = folio->index & ~mask, end_index = start_index | mask;
 
 	/*
 	 * Loop copying datablock into pages.  As the datablock likely covers
@@ -394,32 +398,35 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer,
 	 */
 	for (i = start_index; i <= end_index && bytes > 0; i++,
 			bytes -= PAGE_SIZE, offset += PAGE_SIZE) {
-		struct page *push_page;
-		int avail = buffer ? min_t(int, bytes, PAGE_SIZE) : 0;
+		struct folio *push_folio;
+		size_t avail = buffer ? min(bytes, PAGE_SIZE) : 0;
+		bool updated = false;
 
-		TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail);
+		TRACE("bytes %zu, i %d, available_bytes %zu\n", bytes, i, avail);
 
-		push_page = (i == page->index) ? page :
-			grab_cache_page_nowait(page->mapping, i);
+		push_folio = (i == folio->index) ? folio :
+			__filemap_get_folio(mapping, i,
+					FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
+					mapping_gfp_mask(mapping));
 
-		if (!push_page)
+		if (IS_ERR(push_folio))
 			continue;
 
-		if (PageUptodate(push_page))
-			goto skip_page;
+		if (folio_test_uptodate(push_folio))
+			goto skip_folio;
 
-		squashfs_fill_page(push_page, buffer, offset, avail);
-skip_page:
-		unlock_page(push_page);
-		if (i != page->index)
-			put_page(push_page);
+		updated = squashfs_fill_page(push_folio, buffer, offset, avail);
+skip_folio:
+		folio_end_read(push_folio, updated);
+		if (i != folio->index)
+			folio_put(push_folio);
 	}
 }
 
 /* Read datablock stored packed inside a fragment (tail-end packed block) */
-static int squashfs_readpage_fragment(struct page *page, int expected)
+static int squashfs_readpage_fragment(struct folio *folio, int expected)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb,
 		squashfs_i(inode)->fragment_block,
 		squashfs_i(inode)->fragment_size);
@@ -430,36 +437,34 @@ static int squashfs_readpage_fragment(struct page *page, int expected)
 			squashfs_i(inode)->fragment_block,
 			squashfs_i(inode)->fragment_size);
 	else
-		squashfs_copy_cache(page, buffer, expected,
+		squashfs_copy_cache(folio, buffer, expected,
 			squashfs_i(inode)->fragment_offset);
 
 	squashfs_cache_put(buffer);
 	return res;
 }
 
-static int squashfs_readpage_sparse(struct page *page, int expected)
+static int squashfs_readpage_sparse(struct folio *folio, int expected)
 {
-	squashfs_copy_cache(page, NULL, expected, 0);
+	squashfs_copy_cache(folio, NULL, expected, 0);
 	return 0;
 }
 
 static int squashfs_read_folio(struct file *file, struct folio *folio)
 {
-	struct page *page = &folio->page;
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
-	int index = page->index >> (msblk->block_log - PAGE_SHIFT);
+	int index = folio->index >> (msblk->block_log - PAGE_SHIFT);
 	int file_end = i_size_read(inode) >> msblk->block_log;
 	int expected = index == file_end ?
 			(i_size_read(inode) & (msblk->block_size - 1)) :
 			 msblk->block_size;
 	int res = 0;
-	void *pageaddr;
 
 	TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n",
-				page->index, squashfs_i(inode)->start);
+				folio->index, squashfs_i(inode)->start);
 
-	if (page->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >>
+	if (folio->index >= ((i_size_read(inode) + PAGE_SIZE - 1) >>
 					PAGE_SHIFT))
 		goto out;
 
@@ -472,23 +477,18 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
 			goto out;
 
 		if (res == 0)
-			res = squashfs_readpage_sparse(page, expected);
+			res = squashfs_readpage_sparse(folio, expected);
 		else
-			res = squashfs_readpage_block(page, block, res, expected);
+			res = squashfs_readpage_block(folio, block, res, expected);
 	} else
-		res = squashfs_readpage_fragment(page, expected);
+		res = squashfs_readpage_fragment(folio, expected);
 
 	if (!res)
 		return 0;
 
 out:
-	pageaddr = kmap_atomic(page);
-	memset(pageaddr, 0, PAGE_SIZE);
-	kunmap_atomic(pageaddr);
-	flush_dcache_page(page);
-	if (res == 0)
-		SetPageUptodate(page);
-	unlock_page(page);
+	folio_zero_segment(folio, 0, folio_size(folio));
+	folio_end_read(folio, res == 0);
 
 	return res;
 }
diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c
index 54c17b7c85fd..40e59a43d098 100644
--- a/fs/squashfs/file_cache.c
+++ b/fs/squashfs/file_cache.c
@@ -18,9 +18,9 @@
 #include "squashfs.h"
 
 /* Read separately compressed datablock and memcopy into page cache */
-int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected)
+int squashfs_readpage_block(struct folio *folio, u64 block, int bsize, int expected)
 {
-	struct inode *i = page->mapping->host;
+	struct inode *i = folio->mapping->host;
 	struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb,
 		block, bsize);
 	int res = buffer->error;
@@ -29,7 +29,7 @@ int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expecte
 		ERROR("Unable to read page, block %llx, size %x\n", block,
 			bsize);
 	else
-		squashfs_copy_cache(page, buffer, expected, 0);
+		squashfs_copy_cache(folio, buffer, expected, 0);
 
 	squashfs_cache_put(buffer);
 	return res;
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index d19d4db74af8..2c3e809d6891 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -19,12 +19,11 @@
 #include "page_actor.h"
 
 /* Read separately compressed datablock directly into page cache */
-int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
-	int expected)
-
+int squashfs_readpage_block(struct folio *folio, u64 block, int bsize,
+		int expected)
 {
-	struct folio *folio = page_folio(target_page);
-	struct inode *inode = target_page->mapping->host;
+	struct page *target_page = &folio->page;
+	struct inode *inode = folio->mapping->host;
 	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
 	loff_t file_end = (i_size_read(inode) - 1) >> PAGE_SHIFT;
 	int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
@@ -48,7 +47,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize,
 	/* Try to grab all the pages covered by the Squashfs block */
 	for (i = 0, index = start_index; index <= end_index; index++) {
 		page[i] = (index == folio->index) ? target_page :
-			grab_cache_page_nowait(target_page->mapping, index);
+			grab_cache_page_nowait(folio->mapping, index);
 
 		if (page[i] == NULL)
 			continue;
diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h
index 5a756e6790b5..218868b20f16 100644
--- a/fs/squashfs/squashfs.h
+++ b/fs/squashfs/squashfs.h
@@ -14,6 +14,12 @@
 
 #define WARNING(s, args...)	pr_warn("SQUASHFS: "s, ## args)
 
+#ifdef CONFIG_SQUASHFS_FILE_CACHE
+#define SQUASHFS_READ_PAGES msblk->max_thread_num
+#else
+#define SQUASHFS_READ_PAGES 0
+#endif
+
 /* block.c */
 extern int squashfs_read_data(struct super_block *, u64, int, u64 *,
 				struct squashfs_page_actor *);
@@ -67,12 +73,11 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *,
 				u64, u64, unsigned int);
 
 /* file.c */
-void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int);
-void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int,
-				int);
+void squashfs_copy_cache(struct folio *, struct squashfs_cache_entry *,
+		size_t bytes, size_t offset);
 
 /* file_xxx.c */
-extern int squashfs_readpage_block(struct page *, u64, int, int);
+int squashfs_readpage_block(struct folio *, u64 block, int bsize, int expected);
 
 /* id.c */
 extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *);
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 22e812808e5c..67c55fe32ce8 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -314,26 +314,29 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_flags |= SB_RDONLY;
 	sb->s_op = &squashfs_super_ops;
 
-	err = -ENOMEM;
-
 	msblk->block_cache = squashfs_cache_init("metadata",
 			SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE);
-	if (msblk->block_cache == NULL)
+	if (IS_ERR(msblk->block_cache)) {
+		err = PTR_ERR(msblk->block_cache);
 		goto failed_mount;
+	}
 
 	/* Allocate read_page block */
 	msblk->read_page = squashfs_cache_init("data",
-		msblk->max_thread_num, msblk->block_size);
-	if (msblk->read_page == NULL) {
+		SQUASHFS_READ_PAGES, msblk->block_size);
+	if (IS_ERR(msblk->read_page)) {
 		errorf(fc, "Failed to allocate read_page block");
+		err = PTR_ERR(msblk->read_page);
 		goto failed_mount;
 	}
 
 	if (msblk->devblksize == PAGE_SIZE) {
 		struct inode *cache = new_inode(sb);
 
-		if (cache == NULL)
+		if (cache == NULL) {
+			err = -ENOMEM;
 			goto failed_mount;
+		}
 
 		set_nlink(cache, 1);
 		cache->i_size = OFFSET_MAX;
@@ -405,9 +408,9 @@ handle_fragments:
 		goto check_directory_table;
 
 	msblk->fragment_cache = squashfs_cache_init("fragment",
-		SQUASHFS_CACHED_FRAGMENTS, msblk->block_size);
-	if (msblk->fragment_cache == NULL) {
-		err = -ENOMEM;
+		min(SQUASHFS_CACHED_FRAGMENTS, fragments), msblk->block_size);
+	if (IS_ERR(msblk->fragment_cache)) {
+		err = PTR_ERR(msblk->fragment_cache);
 		goto failed_mount;
 	}
 
diff --git a/fs/stat.c b/fs/stat.c
index 2c0e111a098a..f13308bfdc98 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -281,6 +281,8 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat,
 			  u32 request_mask)
 {
 	int error = vfs_getattr(path, stat, request_mask, flags);
+	if (error)
+		return error;
 
 	if (request_mask & STATX_MNT_ID_UNIQUE) {
 		stat->mnt_id = real_mount(path->mnt)->mnt_id_unique;
@@ -302,7 +304,7 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat,
 	if (S_ISBLK(stat->mode))
 		bdev_statx(path, stat, request_mask);
 
-	return error;
+	return 0;
 }
 
 static int vfs_statx_fd(int fd, int flags, struct kstat *stat,
diff --git a/fs/super.c b/fs/super.c
index c9c7223bc2a2..5a7db4a556e3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -647,7 +647,7 @@ void generic_shutdown_super(struct super_block *sb)
 		 */
 		fscrypt_destroy_keyring(sb);
 
-		if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes),
+		if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), NULL,
 				"VFS: Busy inodes after unmount of %s (%s)",
 				sb->s_id, sb->s_type->name)) {
 			/*
diff --git a/fs/sysctls.c b/fs/sysctls.c
index 8dbde9a802fa..ad429dffeb4b 100644
--- a/fs/sysctls.c
+++ b/fs/sysctls.c
@@ -7,7 +7,7 @@
 #include <linux/init.h>
 #include <linux/sysctl.h>
 
-static struct ctl_table fs_shared_sysctls[] = {
+static const struct ctl_table fs_shared_sysctls[] = {
 	{
 		.procname	= "overflowuid",
 		.data		= &fs_overflowuid,
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 785408861c01..6931308876c4 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -817,7 +817,7 @@ EXPORT_SYMBOL_GPL(sysfs_emit_at);
  * Returns number of bytes written to @buf.
  */
 ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj,
-				   struct bin_attribute *attr, char *buf,
+				   const struct bin_attribute *attr, char *buf,
 				   loff_t off, size_t count)
 {
 	memcpy(buf, attr->private + off, count);
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index cfc614c638da..53214499e384 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -457,7 +457,8 @@ static void tracefs_d_release(struct dentry *dentry)
 		eventfs_d_release(dentry);
 }
 
-static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
+static int tracefs_d_revalidate(struct inode *inode, const struct qstr *name,
+				struct dentry *dentry, unsigned int flags)
 {
 	struct eventfs_inode *ei = dentry->d_fsdata;
 
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 5cc69beaa62e..b01f382ce8db 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -863,7 +863,6 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum)
 
 out:
 	vfree(buf);
-	return;
 }
 
 void ubifs_dump_znode(const struct ubifs_info *c,
@@ -946,16 +945,20 @@ void ubifs_dump_tnc(struct ubifs_info *c)
 
 	pr_err("\n");
 	pr_err("(pid %d) start dumping TNC tree\n", current->pid);
-	znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL);
-	level = znode->level;
-	pr_err("== Level %d ==\n", level);
-	while (znode) {
-		if (level != znode->level) {
-			level = znode->level;
-			pr_err("== Level %d ==\n", level);
+	if (c->zroot.znode) {
+		znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL);
+		level = znode->level;
+		pr_err("== Level %d ==\n", level);
+		while (znode) {
+			if (level != znode->level) {
+				level = znode->level;
+				pr_err("== Level %d ==\n", level);
+			}
+			ubifs_dump_znode(c, znode);
+			znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode);
 		}
-		ubifs_dump_znode(c, znode);
-		znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode);
+	} else {
+		pr_err("empty TNC tree in memory\n");
 	}
 	pr_err("(pid %d) finish dumping TNC tree\n", current->pid);
 }
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index aa8837e6247c..f2cb214581fd 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -1932,7 +1932,6 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum)
 	pr_err("(pid %d) finish dumping LEB %d\n", current->pid, lnum);
 out:
 	vfree(buf);
-	return;
 }
 
 /**
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 7c0bd0b55f88..97c4d71115d8 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -36,7 +36,7 @@
 static int sysctl_unprivileged_userfaultfd __read_mostly;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table vm_userfaultfd_table[] = {
+static const struct ctl_table vm_userfaultfd_table[] = {
 	{
 		.procname	= "unprivileged_userfaultfd",
 		.data		= &sysctl_unprivileged_userfaultfd,
diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c
index 5f1a14d5b927..a859ac9b74ba 100644
--- a/fs/vboxsf/dir.c
+++ b/fs/vboxsf/dir.c
@@ -192,7 +192,8 @@ const struct file_operations vboxsf_dir_fops = {
  * This is called during name resolution/lookup to check if the @dentry in
  * the cache is still valid. the job is handled by vboxsf_inode_revalidate.
  */
-static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+static int vboxsf_dentry_revalidate(struct inode *dir, const struct qstr *name,
+				    struct dentry *dentry, unsigned int flags)
 {
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index e95b8a48d8a0..1d94bb784108 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -21,7 +21,8 @@
 
 #define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */
 
-static const unsigned char VBSF_MOUNT_SIGNATURE[4] = "\000\377\376\375";
+static const unsigned char VBSF_MOUNT_SIGNATURE[4] = { '\000', '\377', '\376',
+						       '\375' };
 
 static int follow_symlinks;
 module_param(follow_symlinks, int, 0444);
diff --git a/fs/verity/init.c b/fs/verity/init.c
index f440f0e61e3e..6e8d33b50240 100644
--- a/fs/verity/init.c
+++ b/fs/verity/init.c
@@ -10,7 +10,7 @@
 #include <linux/ratelimit.h>
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table fsverity_sysctl_table[] = {
+static const struct ctl_table fsverity_sysctl_table[] = {
 #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES
 	{
 		.procname       = "require_signatures",
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 40ad22fb808b..0ef19f1469ec 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3563,12 +3563,12 @@ xfs_bmap_btalloc_at_eof(
 	int			error;
 
 	/*
-	 * If there are already extents in the file, try an exact EOF block
-	 * allocation to extend the file as a contiguous extent. If that fails,
-	 * or it's the first allocation in a file, just try for a stripe aligned
-	 * allocation.
+	 * If there are already extents in the file, and xfs_bmap_adjacent() has
+	 * given a better blkno, try an exact EOF block allocation to extend the
+	 * file as a contiguous extent. If that fails, or it's the first
+	 * allocation in a file, just try for a stripe aligned allocation.
 	 */
-	if (ap->offset) {
+	if (ap->eof) {
 		xfs_extlen_t	nextminlen = 0;
 
 		/*
@@ -3736,7 +3736,8 @@ xfs_bmap_btalloc_best_length(
 	int			error;
 
 	ap->blkno = XFS_INO_TO_FSB(args->mp, ap->ip->i_ino);
-	xfs_bmap_adjacent(ap);
+	if (!xfs_bmap_adjacent(ap))
+		ap->eof = false;
 
 	/*
 	 * Search for an allocation group with a single extent large enough for
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7fbdd4b30676..15bb790359f8 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -41,8 +41,7 @@ struct kmem_cache *xfs_buf_cache;
  *
  * xfs_buf_rele:
  *	b_lock
- *	  pag_buf_lock
- *	    lru_lock
+ *	  lru_lock
  *
  * xfs_buftarg_drain_rele
  *	lru_lock
@@ -220,23 +219,25 @@ _xfs_buf_alloc(
 	 */
 	flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
 
-	spin_lock_init(&bp->b_lock);
+	/*
+	 * A new buffer is held and locked by the owner.  This ensures that the
+	 * buffer is owned by the caller and racing RCU lookups right after
+	 * inserting into the hash table are safe (and will have to wait for
+	 * the unlock to do anything non-trivial).
+	 */
 	bp->b_hold = 1;
+	sema_init(&bp->b_sema, 0); /* held, no waiters */
+
+	spin_lock_init(&bp->b_lock);
 	atomic_set(&bp->b_lru_ref, 1);
 	init_completion(&bp->b_iowait);
 	INIT_LIST_HEAD(&bp->b_lru);
 	INIT_LIST_HEAD(&bp->b_list);
 	INIT_LIST_HEAD(&bp->b_li_list);
-	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	bp->b_target = target;
 	bp->b_mount = target->bt_mount;
 	bp->b_flags = flags;
 
-	/*
-	 * Set length and io_length to the same value initially.
-	 * I/O routines should use io_length, which will be the same in
-	 * most cases but may be reset (e.g. XFS recovery).
-	 */
 	error = xfs_buf_get_maps(bp, nmaps);
 	if (error)  {
 		kmem_cache_free(xfs_buf_cache, bp);
@@ -378,8 +379,8 @@ xfs_buf_alloc_pages(
 	for (;;) {
 		long	last = filled;
 
-		filled = alloc_pages_bulk_array(gfp_mask, bp->b_page_count,
-						bp->b_pages);
+		filled = alloc_pages_bulk(gfp_mask, bp->b_page_count,
+					  bp->b_pages);
 		if (filled == bp->b_page_count) {
 			XFS_STATS_INC(bp->b_mount, xb_page_found);
 			break;
@@ -502,7 +503,6 @@ int
 xfs_buf_cache_init(
 	struct xfs_buf_cache	*bch)
 {
-	spin_lock_init(&bch->bc_lock);
 	return rhashtable_init(&bch->bc_hash, &xfs_buf_hash_params);
 }
 
@@ -652,17 +652,20 @@ xfs_buf_find_insert(
 	if (error)
 		goto out_free_buf;
 
-	spin_lock(&bch->bc_lock);
+	/* The new buffer keeps the perag reference until it is freed. */
+	new_bp->b_pag = pag;
+
+	rcu_read_lock();
 	bp = rhashtable_lookup_get_insert_fast(&bch->bc_hash,
 			&new_bp->b_rhash_head, xfs_buf_hash_params);
 	if (IS_ERR(bp)) {
+		rcu_read_unlock();
 		error = PTR_ERR(bp);
-		spin_unlock(&bch->bc_lock);
 		goto out_free_buf;
 	}
 	if (bp && xfs_buf_try_hold(bp)) {
 		/* found an existing buffer */
-		spin_unlock(&bch->bc_lock);
+		rcu_read_unlock();
 		error = xfs_buf_find_lock(bp, flags);
 		if (error)
 			xfs_buf_rele(bp);
@@ -670,10 +673,8 @@ xfs_buf_find_insert(
 			*bpp = bp;
 		goto out_free_buf;
 	}
+	rcu_read_unlock();
 
-	/* The new buffer keeps the perag reference until it is freed. */
-	new_bp->b_pag = pag;
-	spin_unlock(&bch->bc_lock);
 	*bpp = new_bp;
 	return 0;
 
@@ -1090,7 +1091,6 @@ xfs_buf_rele_cached(
 	}
 
 	/* we are asked to drop the last reference */
-	spin_lock(&bch->bc_lock);
 	__xfs_buf_ioacct_dec(bp);
 	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
 		/*
@@ -1102,7 +1102,6 @@ xfs_buf_rele_cached(
 			bp->b_state &= ~XFS_BSTATE_DISPOSE;
 		else
 			bp->b_hold--;
-		spin_unlock(&bch->bc_lock);
 	} else {
 		bp->b_hold--;
 		/*
@@ -1120,7 +1119,6 @@ xfs_buf_rele_cached(
 		ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
 		rhashtable_remove_fast(&bch->bc_hash, &bp->b_rhash_head,
 				xfs_buf_hash_params);
-		spin_unlock(&bch->bc_lock);
 		if (pag)
 			xfs_perag_put(pag);
 		freebuf = true;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 7e73663c5d4a..3b4ed42e11c0 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -80,7 +80,6 @@ typedef unsigned int xfs_buf_flags_t;
 #define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */
 
 struct xfs_buf_cache {
-	spinlock_t		bc_lock;
 	struct rhashtable	bc_hash;
 };
 
diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c
index f340a2015c4c..0b41bdfecdfb 100644
--- a/fs/xfs/xfs_exchrange.c
+++ b/fs/xfs/xfs_exchrange.c
@@ -329,22 +329,6 @@ out_trans_cancel:
  * successfully but before locks are dropped.
  */
 
-/* Verify that we have security clearance to perform this operation. */
-static int
-xfs_exchange_range_verify_area(
-	struct xfs_exchrange	*fxr)
-{
-	int			ret;
-
-	ret = remap_verify_area(fxr->file1, fxr->file1_offset, fxr->length,
-			true);
-	if (ret)
-		return ret;
-
-	return remap_verify_area(fxr->file2, fxr->file2_offset, fxr->length,
-			true);
-}
-
 /*
  * Performs necessary checks before doing a range exchange, having stabilized
  * mutable inode attributes via i_rwsem.
@@ -355,11 +339,13 @@ xfs_exchange_range_checks(
 	unsigned int		alloc_unit)
 {
 	struct inode		*inode1 = file_inode(fxr->file1);
+	loff_t			size1 = i_size_read(inode1);
 	struct inode		*inode2 = file_inode(fxr->file2);
+	loff_t			size2 = i_size_read(inode2);
 	uint64_t		allocmask = alloc_unit - 1;
 	int64_t			test_len;
 	uint64_t		blen;
-	loff_t			size1, size2, tmp;
+	loff_t			tmp;
 	int			error;
 
 	/* Don't touch certain kinds of inodes */
@@ -368,24 +354,25 @@ xfs_exchange_range_checks(
 	if (IS_SWAPFILE(inode1) || IS_SWAPFILE(inode2))
 		return -ETXTBSY;
 
-	size1 = i_size_read(inode1);
-	size2 = i_size_read(inode2);
-
 	/* Ranges cannot start after EOF. */
 	if (fxr->file1_offset > size1 || fxr->file2_offset > size2)
 		return -EINVAL;
 
-	/*
-	 * If the caller said to exchange to EOF, we set the length of the
-	 * request large enough to cover everything to the end of both files.
-	 */
 	if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) {
+		/*
+		 * If the caller said to exchange to EOF, we set the length of
+		 * the request large enough to cover everything to the end of
+		 * both files.
+		 */
 		fxr->length = max_t(int64_t, size1 - fxr->file1_offset,
 					     size2 - fxr->file2_offset);
-
-		error = xfs_exchange_range_verify_area(fxr);
-		if (error)
-			return error;
+	} else {
+		/*
+		 * Otherwise we require both ranges to end within EOF.
+		 */
+		if (fxr->file1_offset + fxr->length > size1 ||
+		    fxr->file2_offset + fxr->length > size2)
+			return -EINVAL;
 	}
 
 	/*
@@ -402,15 +389,6 @@ xfs_exchange_range_checks(
 		return -EINVAL;
 
 	/*
-	 * We require both ranges to end within EOF, unless we're exchanging
-	 * to EOF.
-	 */
-	if (!(fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) &&
-	    (fxr->file1_offset + fxr->length > size1 ||
-	     fxr->file2_offset + fxr->length > size2))
-		return -EINVAL;
-
-	/*
 	 * Make sure we don't hit any file size limits.  If we hit any size
 	 * limits such that test_length was adjusted, we abort the whole
 	 * operation.
@@ -747,6 +725,7 @@ xfs_exchange_range(
 {
 	struct inode		*inode1 = file_inode(fxr->file1);
 	struct inode		*inode2 = file_inode(fxr->file2);
+	loff_t			check_len = fxr->length;
 	int			ret;
 
 	BUILD_BUG_ON(XFS_EXCHANGE_RANGE_ALL_FLAGS &
@@ -779,14 +758,18 @@ xfs_exchange_range(
 		return -EBADF;
 
 	/*
-	 * If we're not exchanging to EOF, we can check the areas before
-	 * stabilizing both files' i_size.
+	 * If we're exchanging to EOF we can't calculate the length until taking
+	 * the iolock.  Pass a 0 length to remap_verify_area similar to the
+	 * FICLONE and FICLONERANGE ioctls that support cloning to EOF as well.
 	 */
-	if (!(fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF)) {
-		ret = xfs_exchange_range_verify_area(fxr);
-		if (ret)
-			return ret;
-	}
+	if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF)
+		check_len = 0;
+	ret = remap_verify_area(fxr->file1, fxr->file1_offset, check_len, true);
+	if (ret)
+		return ret;
+	ret = remap_verify_area(fxr->file2, fxr->file2_offset, check_len, true);
+	if (ret)
+		return ret;
 
 	/* Update cmtime if the fd/inode don't forbid it. */
 	if (!(fxr->file1->f_mode & FMODE_NOCMTIME) && !IS_NOCMTIME(inode1))
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c95fe1b1de4e..b1f9f156ec88 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1404,8 +1404,11 @@ xfs_inactive(
 		goto out;
 
 	/* Try to clean out the cow blocks if there are any. */
-	if (xfs_inode_has_cow_data(ip))
-		xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
+	if (xfs_inode_has_cow_data(ip)) {
+		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
+		if (error)
+			goto out;
+	}
 
 	if (VFS_I(ip)->i_nlink != 0) {
 		/*
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 50fa3ef89f6c..d61460309a78 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -976,10 +976,8 @@ xfs_dax_write_iomap_end(
 	if (!xfs_is_cow_inode(ip))
 		return 0;
 
-	if (!written) {
-		xfs_reflink_cancel_cow_range(ip, pos, length, true);
-		return 0;
-	}
+	if (!written)
+		return xfs_reflink_cancel_cow_range(ip, pos, length, true);
 
 	return xfs_reflink_end_cow(ip, pos, written);
 }
diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c
index c84df23b494d..751dc74a3067 100644
--- a/fs/xfs/xfs_sysctl.c
+++ b/fs/xfs/xfs_sysctl.c
@@ -66,7 +66,7 @@ xfs_deprecated_dointvec_minmax(
 	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table xfs_table[] = {
+static const struct ctl_table xfs_table[] = {
 	{
 		.procname	= "irix_sgid_inherit",
 		.data		= &xfs_params.sgid_inherit.val,
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index b5f594754a9e..99b960bd473c 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -17,11 +17,16 @@ extern int node_to_pxm(int);
 extern int acpi_map_pxm_to_node(int);
 extern unsigned char acpi_srat_revision;
 extern void disable_srat(void);
+extern int fix_pxm_node_maps(int max_nid);
 
 extern void bad_srat(void);
 extern int srat_disabled(void);
 
 #else				/* CONFIG_ACPI_NUMA */
+static inline int fix_pxm_node_maps(int max_nid)
+{
+	return 0;
+}
 static inline void disable_srat(void)
 {
 }
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index d076ebd19a61..78b24b090488 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -763,6 +763,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 						     *event_status))
 ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_disable_all_gpes(void))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_hw_enable_all_wakeup_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_disable_all_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
index 9d0479f50f97..5db59a1efb65 100644
--- a/include/asm-generic/early_ioremap.h
+++ b/include/asm-generic/early_ioremap.h
@@ -35,7 +35,7 @@ extern void early_ioremap_reset(void);
 /*
  * Early copy from unmapped memory to kernel mapped memory.
  */
-extern void copy_from_early_mem(void *dest, phys_addr_t src,
+extern int copy_from_early_mem(void *dest, phys_addr_t src,
 				unsigned long size);
 
 #else
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 7c48f5fbf8aa..892ece4558a2 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -109,8 +109,7 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
 {
 	struct ptdesc *ptdesc = page_ptdesc(pte_page);
 
-	pagetable_pte_dtor(ptdesc);
-	pagetable_free(ptdesc);
+	pagetable_dtor_free(ptdesc);
 }
 
 
@@ -153,8 +152,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
 
 	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
-	pagetable_pmd_dtor(ptdesc);
-	pagetable_free(ptdesc);
+	pagetable_dtor_free(ptdesc);
 }
 #endif
 
@@ -202,8 +200,7 @@ static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
 	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
 
 	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	pagetable_pud_dtor(ptdesc);
-	pagetable_free(ptdesc);
+	pagetable_dtor_free(ptdesc);
 }
 
 #ifndef __HAVE_ARCH_PUD_FREE
@@ -215,10 +212,82 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 
 #endif /* CONFIG_PGTABLE_LEVELS > 3 */
 
+#if CONFIG_PGTABLE_LEVELS > 4
+
+static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+	struct ptdesc *ptdesc;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	gfp &= ~__GFP_HIGHMEM;
+
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+
+	pagetable_p4d_ctor(ptdesc);
+	return ptdesc_address(ptdesc);
+}
+#define __p4d_alloc_one(...)	alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_P4D_ALLOC_ONE
+static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	return __p4d_alloc_one_noprof(mm, addr);
+}
+#define p4d_alloc_one(...)	alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(p4d);
+
+	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+	pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_P4D_FREE
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		__p4d_free(mm, p4d);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 4 */
+
+static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+	struct ptdesc *ptdesc;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	gfp &= ~__GFP_HIGHMEM;
+
+	ptdesc = pagetable_alloc_noprof(gfp, order);
+	if (!ptdesc)
+		return NULL;
+
+	pagetable_pgd_ctor(ptdesc);
+	return ptdesc_address(ptdesc);
+}
+#define __pgd_alloc(...)	alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
+
+static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
+
+	BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+	pagetable_dtor_free(ptdesc);
+}
+
 #ifndef __HAVE_ARCH_PGD_FREE
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	pagetable_free(virt_to_ptdesc(pgd));
+	__pgd_free(mm, pgd);
 }
 #endif
 
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 5a80fe728dc8..182b039ce5fa 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -5,7 +5,7 @@
  * Copyright (C) 2008-2009 Red Hat, Inc.  All rights reserved.
  *
  * This file is a stub providing documentation for what functions
- * asm-ARCH/syscall.h files need to define.  Most arch definitions
+ * arch/ARCH/include/asm/syscall.h files need to define.  Most arch definitions
  * will be simple inlines.
  *
  * All of these functions expect to be called with no locks,
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 709830274b75..e402aef79c93 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -153,8 +153,9 @@
  *
  *  Useful if your architecture has non-page page directories.
  *
- *  When used, an architecture is expected to provide __tlb_remove_table()
- *  which does the actual freeing of these pages.
+ *  When used, an architecture is expected to provide __tlb_remove_table() or
+ *  use the generic __tlb_remove_table(), which does the actual freeing of these
+ *  pages.
  *
  *  MMU_GATHER_RCU_TABLE_FREE
  *
@@ -207,16 +208,31 @@ struct mmu_table_batch {
 #define MAX_TABLE_BATCH		\
 	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
 
+#ifndef __HAVE_ARCH_TLB_REMOVE_TABLE
+static inline void __tlb_remove_table(void *table)
+{
+	struct ptdesc *ptdesc = (struct ptdesc *)table;
+
+	pagetable_dtor_free(ptdesc);
+}
+#endif
+
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
-#else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */
+#else /* !CONFIG_MMU_GATHER_TABLE_FREE */
 
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page);
 /*
  * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based
  * page directories and we can use the normal page batching to free them.
  */
-#define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page))
+static inline void tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	struct page *page = (struct page *)table;
 
+	pagetable_dtor(page_ptdesc(page));
+	tlb_remove_page(tlb, page);
+}
 #endif /* CONFIG_MMU_GATHER_TABLE_FREE */
 
 #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 54504013c749..02a4adb4a999 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1038,6 +1038,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	*(.discard)							\
 	*(.discard.*)							\
 	*(.export_symbol)						\
+	*(.no_trim_symbol)						\
 	*(.modinfo)							\
 	/* ld.bfd warns about .gnu.version* even when not emitted */	\
 	*(.gnu.version*)						\
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index cbbc9a6dc571..ce6521ad04d1 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -22,6 +22,12 @@
 #define CNTHCTL_EVNTDIR			(1 << 3)
 #define CNTHCTL_EVNTI			(0xF << 4)
 #define CNTHCTL_ECV			(1 << 12)
+#define CNTHCTL_EL1TVT			(1 << 13)
+#define CNTHCTL_EL1TVCT			(1 << 14)
+#define CNTHCTL_EL1NVPCT		(1 << 15)
+#define CNTHCTL_EL1NVVCT		(1 << 16)
+#define CNTHCTL_CNTVMASK		(1 << 18)
+#define CNTHCTL_CNTPMASK		(1 << 19)
 
 enum arch_timer_reg {
 	ARCH_TIMER_REG_CTRL,
diff --git a/include/cxl/event.h b/include/cxl/event.h
index 0bea1afbd747..04edd44bd26f 100644
--- a/include/cxl/event.h
+++ b/include/cxl/event.h
@@ -18,7 +18,8 @@ struct cxl_event_record_hdr {
 	__le16 related_handle;
 	__le64 timestamp;
 	u8 maint_op_class;
-	u8 reserved[15];
+	u8 maint_op_sub_class;
+	u8 reserved[14];
 } __packed;
 
 struct cxl_event_media_hdr {
@@ -44,19 +45,22 @@ struct cxl_event_generic {
 
 /*
  * General Media Event Record
- * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45
  */
 #define CXL_EVENT_GEN_MED_COMP_ID_SIZE	0x10
 struct cxl_event_gen_media {
 	struct cxl_event_media_hdr media_hdr;
 	u8 device[3];
 	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
-	u8 reserved[46];
+	u8 cme_threshold_ev_flags;
+	u8 cme_count[3];
+	u8 sub_type;
+	u8 reserved[41];
 } __packed;
 
 /*
  * DRAM Event Record - DER
- * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44
+ * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46
  */
 #define CXL_EVENT_DER_CORRECTION_MASK_SIZE	0x20
 struct cxl_event_dram {
@@ -67,12 +71,17 @@ struct cxl_event_dram {
 	u8 row[3];
 	u8 column[2];
 	u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE];
-	u8 reserved[0x17];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 sub_channel;
+	u8 cme_threshold_ev_flags;
+	u8 cvme_count[3];
+	u8 sub_type;
+	u8 reserved;
 } __packed;
 
 /*
  * Get Health Info Record
- * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100
+ * CXL rev 3.1 section 8.2.9.9.3.1; Table 8-133
  */
 struct cxl_get_health_info {
 	u8 health_status;
@@ -87,13 +96,16 @@ struct cxl_get_health_info {
 
 /*
  * Memory Module Event Record
- * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ * CXL rev 3.1 section 8.2.9.2.1.3; Table 8-47
  */
 struct cxl_event_mem_module {
 	struct cxl_event_record_hdr hdr;
 	u8 event_type;
 	struct cxl_get_health_info info;
-	u8 reserved[0x3d];
+	u8 validity_flags[2];
+	u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE];
+	u8 event_sub_type;
+	u8 reserved[0x2a];
 } __packed;
 
 union cxl_event {
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index f77fe1531cf8..9732f514566d 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -32,6 +32,7 @@
 #include <linux/dynamic_debug.h>
 
 #include <drm/drm.h>
+#include <drm/drm_device.h>
 
 struct debugfs_regset32;
 struct drm_device;
diff --git a/include/dt-bindings/iio/adi,ad4695.h b/include/dt-bindings/iio/adc/adi,ad4695.h
index 9fbef542bf67..9fbef542bf67 100644
--- a/include/dt-bindings/iio/adi,ad4695.h
+++ b/include/dt-bindings/iio/adc/adi,ad4695.h
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index fd650a8789b9..681cf0c8b9df 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -98,6 +98,7 @@ int __init kvm_timer_hyp_init(bool has_gic);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_nested(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);
@@ -150,9 +151,31 @@ void kvm_timer_cpu_down(void);
 /* CNTKCTL_EL1 valid bits as of DDI0487J.a */
 #define CNTKCTL_VALID_BITS	(BIT(17) | GENMASK_ULL(9, 0))
 
+DECLARE_STATIC_KEY_FALSE(broken_cntvoff_key);
+
+static inline bool has_broken_cntvoff(void)
+{
+	return static_branch_unlikely(&broken_cntvoff_key);
+}
+
 static inline bool has_cntpoff(void)
 {
 	return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF));
 }
 
+static inline u64 timer_get_offset(struct arch_timer_context *ctxt)
+{
+	u64 offset = 0;
+
+	if (!ctxt)
+		return 0;
+
+	if (ctxt->offset.vm_offset)
+		offset += *ctxt->offset.vm_offset;
+	if (ctxt->offset.vcpu_offset)
+		offset += *ctxt->offset.vcpu_offset;
+
+	return offset;
+}
+
 #endif
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 0bbbe537c5f9..a946e0203e6d 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -224,9 +224,14 @@ static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {}
 
 #define alloc_hooks_tag(_tag, _do_alloc)				\
 ({									\
-	struct alloc_tag * __maybe_unused _old = alloc_tag_save(_tag);	\
-	typeof(_do_alloc) _res = _do_alloc;				\
-	alloc_tag_restore(_tag, _old);					\
+	typeof(_do_alloc) _res;						\
+	if (mem_alloc_profiling_enabled()) {				\
+		struct alloc_tag * __maybe_unused _old;			\
+		_old = alloc_tag_save(_tag);				\
+		_res = _do_alloc;					\
+		alloc_tag_restore(_tag, _old);				\
+	} else								\
+		_res = _do_alloc;					\
 	_res;								\
 })
 
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 262b6596eca5..2026953e2c4e 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -23,7 +23,7 @@ struct device;
  *
  * Function implementations generic to all architectures are in
  * lib/bitmap.c.  Functions implementations that are architecture
- * specific are in various include/asm-<arch>/bitops.h headers
+ * specific are in various arch/<arch>/include/asm/bitops.h headers
  * and other arch/<arch> specific files.
  *
  * See lib/bitmap.c for more details.
diff --git a/include/linux/bits.h b/include/linux/bits.h
index 60044b608817..61a75d3f294b 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -20,9 +20,8 @@
  */
 #if !defined(__ASSEMBLY__)
 #include <linux/build_bug.h>
-#define GENMASK_INPUT_CHECK(h, l) \
-	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__is_constexpr((l) > (h)), (l) > (h), 0)))
+#include <linux/compiler.h>
+#define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
 #else
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index a0a9007cc1e3..9ebb53f031cd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -900,8 +900,22 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
 void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
-void blk_mq_freeze_queue(struct request_queue *q);
-void blk_mq_unfreeze_queue(struct request_queue *q);
+void blk_mq_freeze_queue_nomemsave(struct request_queue *q);
+void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q);
+static inline unsigned int __must_check
+blk_mq_freeze_queue(struct request_queue *q)
+{
+	unsigned int memflags = memalloc_noio_save();
+
+	blk_mq_freeze_queue_nomemsave(q);
+	return memflags;
+}
+static inline void
+blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags)
+{
+	blk_mq_unfreeze_queue_nomemrestore(q);
+	memalloc_noio_restore(memflags);
+}
 void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 76f0a4e7c2e5..248416ecd01c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -561,7 +561,6 @@ struct request_queue {
 	struct list_head	flush_list;
 
 	struct mutex		sysfs_lock;
-	struct mutex		sysfs_dir_lock;
 	struct mutex		limits_lock;
 
 	/*
@@ -605,8 +604,6 @@ struct request_queue {
 	 * Serializes all debugfs metadata operations using the above dentries.
 	 */
 	struct mutex		debugfs_mutex;
-
-	bool			mq_sysfs_init_done;
 };
 
 /* Keep blk_queue_flag_name[] in sync with the definitions below */
diff --git a/include/linux/bug.h b/include/linux/bug.h
index 348acf2558f3..a9948a9f1093 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -73,15 +73,23 @@ static inline void generic_bug_clear_once(void) {}
 
 #endif	/* CONFIG_GENERIC_BUG */
 
+#ifdef CONFIG_PRINTK
+void mem_dump_obj(void *object);
+#else
+static inline void mem_dump_obj(void *object) {}
+#endif
+
 /*
  * Since detected data corruption should stop operation on the affected
  * structures. Return value must be checked and sanely acted on by caller.
  */
 static inline __must_check bool check_data_corruption(bool v) { return v; }
-#define CHECK_DATA_CORRUPTION(condition, fmt, ...)			 \
+#define CHECK_DATA_CORRUPTION(condition, addr, fmt, ...)		 \
 	check_data_corruption(({					 \
 		bool corruption = unlikely(condition);			 \
 		if (corruption) {					 \
+			if (addr)					 \
+				mem_dump_obj(addr);			 \
 			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
 				pr_err(fmt, ##__VA_ARGS__);		 \
 				BUG();					 \
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 7ad736538649..c8f4f0a0b874 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -147,7 +147,7 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level)
 	return ci ? ci->id : -1;
 }
 
-#ifdef CONFIG_ARM64
+#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
 #define use_arch_cache_info()	(true)
 #else
 #define use_arch_cache_info()	(false)
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 2d7d86f0290d..c7f2c63b3bc3 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -504,20 +504,6 @@ struct ceph_mds_request_head_legacy {
 
 #define CEPH_MDS_REQUEST_HEAD_VERSION  3
 
-struct ceph_mds_request_head_old {
-	__le16 version;                /* struct version */
-	__le64 oldest_client_tid;
-	__le32 mdsmap_epoch;           /* on client */
-	__le32 flags;                  /* CEPH_MDS_FLAG_* */
-	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
-	__le16 num_releases;           /* # include cap/lease release records */
-	__le32 op;                     /* mds op code */
-	__le32 caller_uid, caller_gid;
-	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
-					  etc. (if replaying) */
-	union ceph_mds_request_args_ext args;
-} __attribute__ ((packed));
-
 struct ceph_mds_request_head {
 	__le16 version;                /* struct version */
 	__le64 oldest_client_tid;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index efd43df3a99a..200fd3c5bc70 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -191,6 +191,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	__v;								\
 })
 
+#ifdef __CHECKER__
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
+#else /* __CHECKER__ */
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#endif /* __CHECKER__ */
+
+/* &a[0] degrades to a pointer: a different type from an array */
+#define __is_array(a)		(!__same_type((a), &(a)[0]))
+#define __must_be_array(a)	__BUILD_BUG_ON_ZERO_MSG(!__is_array(a), \
+							"must be array")
+
+#define __is_byte_array(a)	(__is_array(a) && sizeof((a)[0]) == 1)
+#define __must_be_byte_array(a)	__BUILD_BUG_ON_ZERO_MSG(!__is_byte_array(a), \
+							"must be byte array")
+
+/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */
+#define __must_be_cstr(p) \
+	__BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)")
+
 #endif /* __KERNEL__ */
 
 /**
@@ -231,19 +250,6 @@ static inline void *offset_to_ptr(const int *off)
 
 #define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym))
 
-#ifdef __CHECKER__
-#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
-#else /* __CHECKER__ */
-#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
-#endif /* __CHECKER__ */
-
-/* &a[0] degrades to a pointer: a different type from an array */
-#define __must_be_array(a)	__BUILD_BUG_ON_ZERO_MSG(__same_type((a), &(a)[0]), "must be array")
-
-/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */
-#define __must_be_cstr(p) \
-	__BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)")
-
 /*
  * This returns a constant expression while determining if an argument is
  * a constant expression, most importantly without evaluating the argument.
@@ -308,6 +314,28 @@ static inline void *offset_to_ptr(const int *off)
 #define statically_true(x) (__builtin_constant_p(x) && (x))
 
 /*
+ * Similar to statically_true() but produces a constant expression
+ *
+ * To be used in conjunction with macros, such as BUILD_BUG_ON_ZERO(),
+ * which require their input to be a constant expression and for which
+ * statically_true() would otherwise fail.
+ *
+ * This is a trade-off: const_true() requires all its operands to be
+ * compile time constants. Else, it would always returns false even on
+ * the most trivial cases like:
+ *
+ *   true || non_const_var
+ *
+ * On the opposite, statically_true() is able to fold more complex
+ * tautologies and will return true on expressions such as:
+ *
+ *   !(non_const_var * 8 % 4)
+ *
+ * For the general case, statically_true() is better.
+ */
+#define const_true(x) __builtin_choose_expr(__is_constexpr(x), x, false)
+
+/*
  * This is needed in functions which generate the stack canary, see
  * arch/x86/kernel/smpboot.c::start_secondary() for an example.
  */
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index c13342594278..17276965ff1d 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -172,6 +172,9 @@ struct coresight_desc {
  * @dest_dev:	a @coresight_device representation of the component
 		connected to @src_port. NULL until the device is created
  * @link: Representation of the connection as a sysfs link.
+ * @filter_src_fwnode: filter source component's fwnode handle.
+ * @filter_src_dev: a @coresight_device representation of the component that
+		needs to be filtered.
  *
  * The full connection structure looks like this, where in_conns store
  * references to same connection as the source device's out_conns.
@@ -200,8 +203,10 @@ struct coresight_connection {
 	struct coresight_device *dest_dev;
 	struct coresight_sysfs_link *link;
 	struct coresight_device *src_dev;
-	atomic_t src_refcnt;
-	atomic_t dest_refcnt;
+	struct fwnode_handle *filter_src_fwnode;
+	struct coresight_device *filter_src_dev;
+	int src_refcnt;
+	int dest_refcnt;
 };
 
 /**
@@ -588,9 +593,14 @@ static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 o
 }
 #endif	/* CONFIG_64BIT */
 
+static inline bool coresight_is_device_source(struct coresight_device *csdev)
+{
+	return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE);
+}
+
 static inline bool coresight_is_percpu_source(struct coresight_device *csdev)
 {
-	return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) &&
+	return csdev && coresight_is_device_source(csdev) &&
 	       (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_PROC);
 }
 
@@ -662,6 +672,7 @@ void coresight_relaxed_write64(struct coresight_device *csdev,
 void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset);
 
 extern int coresight_get_cpu(struct device *dev);
+extern int coresight_get_static_trace_id(struct device *dev, u32 *id);
 
 struct coresight_platform_data *coresight_get_platform_data(struct device *dev);
 struct coresight_connection *
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index bdcec1732445..6a0a8f1c7c90 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -77,6 +77,7 @@ extern ssize_t cpu_show_gds(struct device *dev,
 			    struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev,
 					       struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 9278a50d514f..36a890d0dd57 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -391,7 +391,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
 	for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 /**
- * cpumask_any_but - return a "random" in a cpumask, but not this one.
+ * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one.
  * @mask: the cpumask to search
  * @cpu: the cpu to ignore.
  *
@@ -411,7 +411,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 
 /**
- * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one.
+ * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one.
  * @mask1: the first input cpumask
  * @mask2: the second input cpumask
  * @cpu: the cpu to ignore
@@ -840,7 +840,7 @@ void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
 }
 
 /**
- * cpumask_any - pick a "random" cpu from *srcp
+ * cpumask_any - pick an arbitrary cpu from *srcp
  * @srcp: the input cpumask
  *
  * Return: >= nr_cpu_ids if no cpus set.
@@ -848,7 +848,7 @@ void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
 #define cpumask_any(srcp) cpumask_first(srcp)
 
 /**
- * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2
+ * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2
  * @mask1: the first input cpumask
  * @mask2: the second input cpumask
  *
@@ -1043,7 +1043,6 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
 /* Wrappers for arch boot code to manipulate normally-constant masks */
 void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
-void init_cpu_online(const struct cpumask *src);
 
 #define assign_cpu(cpu, mask, val)	\
 	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index acc55626afdc..2f2555e6407c 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -20,6 +20,8 @@ extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size);
 extern void elfcorehdr_free(unsigned long long addr);
 extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos);
 extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+		unsigned long long paddr, unsigned long long size);
 extern int remap_oldmem_pfn_range(struct vm_area_struct *vma,
 				  unsigned long from, unsigned long pfn,
 				  unsigned long size, pgprot_t prot);
@@ -99,6 +101,12 @@ static inline void vmcore_unusable(void)
  *              indicated in the vmcore instead. For example, a ballooned page
  *              contains no data and reading from such a page will cause high
  *              load in the hypervisor.
+ * @get_device_ram: query RAM ranges that can only be detected by device
+ *   drivers, such as the virtio-mem driver, so they can be included in
+ *   the crash dump on architectures that allocate the elfcore hdr in the dump
+ *   ("2nd") kernel. Indicated RAM ranges may contain holes to reduce the
+ *   total number of ranges; such holes can be detected using the pfn_is_ram
+ *   callback just like for other RAM.
  * @next: List head to manage registered callbacks internally; initialized by
  *        register_vmcore_cb().
  *
@@ -109,11 +117,44 @@ static inline void vmcore_unusable(void)
  */
 struct vmcore_cb {
 	bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn);
+	int (*get_device_ram)(struct vmcore_cb *cb, struct list_head *list);
 	struct list_head next;
 };
 extern void register_vmcore_cb(struct vmcore_cb *cb);
 extern void unregister_vmcore_cb(struct vmcore_cb *cb);
 
+struct vmcore_range {
+	struct list_head list;
+	unsigned long long paddr;
+	unsigned long long size;
+	loff_t offset;
+};
+
+/* Allocate a vmcore range and add it to the list. */
+static inline int vmcore_alloc_add_range(struct list_head *list,
+		unsigned long long paddr, unsigned long long size)
+{
+	struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL);
+
+	if (!m)
+		return -ENOMEM;
+	m->paddr = paddr;
+	m->size = size;
+	list_add_tail(&m->list, list);
+	return 0;
+}
+
+/* Free a list of vmcore ranges. */
+static inline void vmcore_free_ranges(struct list_head *list)
+{
+	struct vmcore_range *m, *tmp;
+
+	list_for_each_entry_safe(m, tmp, list, list) {
+		list_del(&m->list);
+		kfree(m);
+	}
+}
+
 #else /* !CONFIG_CRASH_DUMP */
 static inline bool is_kdump_kernel(void) { return false; }
 #endif /* CONFIG_CRASH_DUMP */
diff --git a/include/linux/damon.h b/include/linux/damon.h
index a67f2c4940e9..af525252b853 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -193,11 +193,16 @@ struct damos_quota_goal {
  * size quota is set, DAMON tries to apply the action only up to &sz bytes
  * within &reset_interval.
  *
- * Internally, the time quota is transformed to a size quota using estimated
- * throughput of the scheme's action.  DAMON then compares it against &sz and
- * uses smaller one as the effective quota.
+ * To convince the different types of quotas and goals, DAMON internally
+ * converts those into one single size quota called "effective quota".  DAMON
+ * internally uses it as the only one real quota.  The conversion is made as
+ * follows.
  *
- * If @goals is not empt, DAMON calculates yet another size quota based on the
+ * The time quota is transformed to a size quota using estimated throughput of
+ * the scheme's action.  DAMON then compares it against &sz and uses smaller
+ * one as the effective quota.
+ *
+ * If @goals is not empty, DAMON calculates yet another size quota based on the
  * goals using its internal feedback loop algorithm, for every @reset_interval.
  * Then, if the new size quota is smaller than the effective quota, it uses the
  * new size quota as the effective quota.
@@ -286,13 +291,33 @@ struct damos_watermarks {
  * @sz_tried:	Total size of regions that the scheme is tried to be applied.
  * @nr_applied:	Total number of regions that the scheme is applied.
  * @sz_applied:	Total size of regions that the scheme is applied.
+ * @sz_ops_filter_passed:
+ *		Total bytes that passed ops layer-handled DAMOS filters.
  * @qt_exceeds: Total number of times the quota of the scheme has exceeded.
+ *
+ * "Tried an action to a region" in this context means the DAMOS core logic
+ * determined the region as eligible to apply the action.  The access pattern
+ * (&struct damos_access_pattern), quotas (&struct damos_quota), watermarks
+ * (&struct damos_watermarks) and filters (&struct damos_filter) that handled
+ * on core logic can affect this.  The core logic asks the operation set
+ * (&struct damon_operations) to apply the action to the region.
+ *
+ * "Applied an action to a region" in this context means the operation set
+ * (&struct damon_operations) successfully applied the action to the region, at
+ * least to a part of the region.  The filters (&struct damos_filter) that
+ * handled on operation set layer and type of the action and pages of the
+ * region can affect this.  For example, if a filter is set to exclude
+ * anonymous pages and the region has only anonymous pages, the region will be
+ * failed at applying the action.  If the action is &DAMOS_PAGEOUT and all
+ * pages of the region are already paged out, the region will be failed at
+ * applying the action.
  */
 struct damos_stat {
 	unsigned long nr_tried;
 	unsigned long sz_tried;
 	unsigned long nr_applied;
 	unsigned long sz_applied;
+	unsigned long sz_ops_filter_passed;
 	unsigned long qt_exceeds;
 };
 
@@ -327,8 +352,9 @@ enum damos_filter_type {
 
 /**
  * struct damos_filter - DAMOS action target memory filter.
- * @type:	Type of the page.
- * @matching:	If the matching page should filtered out or in.
+ * @type:	Type of the target memory.
+ * @matching:	Whether this is for @type-matching memory.
+ * @allow:	Whether to include or exclude the @matching memory.
  * @memcg_id:	Memcg id of the question if @type is DAMOS_FILTER_MEMCG.
  * @addr_range:	Address range if @type is DAMOS_FILTER_TYPE_ADDR.
  * @target_idx:	Index of the &struct damon_target of
@@ -337,13 +363,15 @@ enum damos_filter_type {
  * @list:	List head for siblings.
  *
  * Before applying the &damos->action to a memory region, DAMOS checks if each
- * page of the region matches to this and avoid applying the action if so.
- * Support of each filter type depends on the running &struct damon_operations
- * and the type.  Refer to &enum damos_filter_type for more detai.
+ * byte of the region matches to this given condition and avoid applying the
+ * action if so.  Support of each filter type depends on the running &struct
+ * damon_operations and the type.  Refer to &enum damos_filter_type for more
+ * details.
  */
 struct damos_filter {
 	enum damos_filter_type type;
 	bool matching;
+	bool allow;
 	union {
 		unsigned short memcg_id;
 		struct damon_addr_range addr_range;
@@ -352,6 +380,31 @@ struct damos_filter {
 	struct list_head list;
 };
 
+struct damon_ctx;
+struct damos;
+
+/**
+ * struct damos_walk_control - Control damos_walk().
+ *
+ * @walk_fn:	Function to be called back for each region.
+ * @data:	Data that will be passed to walk functions.
+ *
+ * Control damos_walk(), which requests specific kdamond to invoke the given
+ * function to each region that eligible to apply actions of the kdamond's
+ * schemes.  Refer to damos_walk() for more details.
+ */
+struct damos_walk_control {
+	void (*walk_fn)(void *data, struct damon_ctx *ctx,
+			struct damon_target *t, struct damon_region *r,
+			struct damos *s, unsigned long sz_filter_passed);
+	void *data;
+/* private: internal use only */
+	/* informs if the kdamond finished handling of the walk request */
+	struct completion completion;
+	/* informs if the walk is canceled. */
+	bool canceled;
+};
+
 /**
  * struct damos_access_pattern - Target access pattern of the given scheme.
  * @min_sz_region:	Minimum size of target regions.
@@ -415,6 +468,8 @@ struct damos {
 	 * @action
 	 */
 	unsigned long next_apply_sis;
+	/* informs if ongoing DAMOS walk for this scheme is finished */
+	bool walk_completed;
 /* public: */
 	struct damos_quota quota;
 	struct damos_watermarks wmarks;
@@ -442,8 +497,6 @@ enum damon_ops_id {
 	NR_DAMON_OPS,
 };
 
-struct damon_ctx;
-
 /**
  * struct damon_operations - Monitoring operations for given use cases.
  *
@@ -487,7 +540,8 @@ struct damon_ctx;
  * @apply_scheme is called from @kdamond when a region for user provided
  * DAMON-based operation scheme is found.  It should apply the scheme's action
  * to the region and return bytes of the region that the action is successfully
- * applied.
+ * applied.  It should also report how many bytes of the region has passed
+ * filters (&struct damos_filter) that handled by itself.
  * @target_valid should check whether the target is still valid for the
  * monitoring.
  * @cleanup is called from @kdamond just before its termination.
@@ -504,7 +558,7 @@ struct damon_operations {
 			struct damos *scheme);
 	unsigned long (*apply_scheme)(struct damon_ctx *context,
 			struct damon_target *t, struct damon_region *r,
-			struct damos *scheme);
+			struct damos *scheme, unsigned long *sz_filter_passed);
 	bool (*target_valid)(struct damon_target *t);
 	void (*cleanup)(struct damon_ctx *context);
 };
@@ -552,6 +606,27 @@ struct damon_callback {
 	void (*before_terminate)(struct damon_ctx *context);
 };
 
+/*
+ * struct damon_call_control - Control damon_call().
+ *
+ * @fn:			Function to be called back.
+ * @data:		Data that will be passed to @fn.
+ * @return_code:	Return code from @fn invocation.
+ *
+ * Control damon_call(), which requests specific kdamond to invoke a given
+ * function.  Refer to damon_call() for more details.
+ */
+struct damon_call_control {
+	int (*fn)(void *data);
+	void *data;
+	int return_code;
+/* private: internal use only */
+	/* informs if the kdamond finished handling of the request */
+	struct completion completion;
+	/* informs if the kdamond canceled @fn infocation */
+	bool canceled;
+};
+
 /**
  * struct damon_attrs - Monitoring attributes for accuracy/overhead control.
  *
@@ -632,6 +707,12 @@ struct damon_ctx {
 	/* for scheme quotas prioritization */
 	unsigned long *regions_score_histogram;
 
+	struct damon_call_control *call_control;
+	struct mutex call_control_lock;
+
+	struct damos_walk_control *walk_control;
+	struct mutex walk_control_lock;
+
 /* public: */
 	struct task_struct *kdamond;
 	struct mutex kdamond_lock;
@@ -725,7 +806,7 @@ void damon_update_region_access_rate(struct damon_region *r, bool accessed,
 		struct damon_attrs *attrs);
 
 struct damos_filter *damos_new_filter(enum damos_filter_type type,
-		bool matching);
+		bool matching, bool allow);
 void damos_add_filter(struct damos *s, struct damos_filter *f);
 void damos_destroy_filter(struct damos_filter *f);
 
@@ -779,6 +860,9 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
 
+int damon_call(struct damon_ctx *ctx, struct damon_call_control *control);
+int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control);
+
 int damon_set_region_biggest_system_ram_default(struct damon_target *t,
 				unsigned long *start, unsigned long *end);
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index bff956f7b2b9..4afb60365675 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -57,6 +57,7 @@ struct qstr {
 };
 
 #define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
+#define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n))
 
 extern const struct qstr empty_name;
 extern const struct qstr slash_name;
@@ -68,16 +69,24 @@ extern const struct qstr dotdot_name;
  * large memory footprint increase).
  */
 #ifdef CONFIG_64BIT
-# define DNAME_INLINE_LEN 40 /* 192 bytes */
+# define DNAME_INLINE_WORDS 5 /* 192 bytes */
 #else
 # ifdef CONFIG_SMP
-#  define DNAME_INLINE_LEN 36 /* 128 bytes */
+#  define DNAME_INLINE_WORDS 9 /* 128 bytes */
 # else
-#  define DNAME_INLINE_LEN 44 /* 128 bytes */
+#  define DNAME_INLINE_WORDS 11 /* 128 bytes */
 # endif
 #endif
 
+#define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long))
+
+union shortname_store {
+	unsigned char string[DNAME_INLINE_LEN];
+	unsigned long words[DNAME_INLINE_WORDS];
+};
+
 #define d_lock	d_lockref.lock
+#define d_iname d_shortname.string
 
 struct dentry {
 	/* RCU lookup touched fields */
@@ -88,7 +97,7 @@ struct dentry {
 	struct qstr d_name;
 	struct inode *d_inode;		/* Where the name belongs to - NULL is
 					 * negative */
-	unsigned char d_iname[DNAME_INLINE_LEN];	/* small names */
+	union shortname_store d_shortname;
 	/* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */
 
 	/* Ref lookup also touches following */
@@ -136,7 +145,8 @@ enum d_real_type {
 };
 
 struct dentry_operations {
-	int (*d_revalidate)(struct dentry *, unsigned int);
+	int (*d_revalidate)(struct inode *, const struct qstr *,
+			    struct dentry *, unsigned int);
 	int (*d_weak_revalidate)(struct dentry *, unsigned int);
 	int (*d_hash)(const struct dentry *, struct qstr *);
 	int (*d_compare)(const struct dentry *,
@@ -150,6 +160,8 @@ struct dentry_operations {
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(const struct path *, bool);
 	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
+	bool (*d_unalias_trylock)(const struct dentry *);
+	void (*d_unalias_unlock)(const struct dentry *);
 } ____cacheline_aligned;
 
 /*
@@ -589,7 +601,7 @@ static inline struct inode *d_real_inode(const struct dentry *dentry)
 
 struct name_snapshot {
 	struct qstr name;
-	unsigned char inline_name[DNAME_INLINE_LEN];
+	union shortname_store inline_name;
 };
 void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
 void release_dentry_name_snapshot(struct name_snapshot *);
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 59444b495d49..fa2568b4380d 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -67,21 +67,23 @@ static const struct file_operations __fops = {				\
 
 typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
 
-#if defined(CONFIG_DEBUG_FS)
-
-struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
-
 struct debugfs_short_fops {
 	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
 	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
 	loff_t (*llseek) (struct file *, loff_t, int);
 };
 
+#if defined(CONFIG_DEBUG_FS)
+
+struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
+
 struct dentry *debugfs_create_file_full(const char *name, umode_t mode,
 					struct dentry *parent, void *data,
+					const void *aux,
 					const struct file_operations *fops);
 struct dentry *debugfs_create_file_short(const char *name, umode_t mode,
 					 struct dentry *parent, void *data,
+					 const void *aux,
 					 const struct debugfs_short_fops *fops);
 
 /**
@@ -126,7 +128,15 @@ struct dentry *debugfs_create_file_short(const char *name, umode_t mode,
 		 const struct debugfs_short_fops *: debugfs_create_file_short,	\
 		 struct file_operations *: debugfs_create_file_full,		\
 		 struct debugfs_short_fops *: debugfs_create_file_short)	\
-		(name, mode, parent, data, fops)
+		(name, mode, parent, data, NULL, fops)
+
+#define debugfs_create_file_aux(name, mode, parent, data, aux, fops)		\
+	_Generic(fops,								\
+		 const struct file_operations *: debugfs_create_file_full,	\
+		 const struct debugfs_short_fops *: debugfs_create_file_short,	\
+		 struct file_operations *: debugfs_create_file_full,		\
+		 struct debugfs_short_fops *: debugfs_create_file_short)	\
+		(name, mode, parent, data, aux, fops)
 
 struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
@@ -153,6 +163,7 @@ void debugfs_remove(struct dentry *dentry);
 void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
 
 const struct file_operations *debugfs_real_fops(const struct file *filp);
+const void *debugfs_get_aux(const struct file *file);
 
 int debugfs_file_get(struct dentry *dentry);
 void debugfs_file_put(struct dentry *dentry);
@@ -164,8 +175,7 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf,
 ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf,
 			size_t len, loff_t *ppos);
 
-struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
-                struct dentry *new_dir, const char *new_name);
+int debugfs_change_name(struct dentry *dentry, const char *fmt, ...) __printf(2, 3);
 
 void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent,
 		       u8 *value);
@@ -259,6 +269,14 @@ static inline struct dentry *debugfs_lookup(const char *name,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct dentry *debugfs_create_file_aux(const char *name,
+					umode_t mode, struct dentry *parent,
+					void *data, void *aux,
+					const void *fops)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct dentry *debugfs_create_file(const char *name, umode_t mode,
 					struct dentry *parent, void *data,
 					const void *fops)
@@ -312,6 +330,7 @@ static inline void debugfs_lookup_and_remove(const char *name,
 { }
 
 const struct file_operations *debugfs_real_fops(const struct file *filp);
+void *debugfs_get_aux(const struct file *file);
 
 static inline int debugfs_file_get(struct dentry *dentry)
 {
@@ -341,10 +360,10 @@ static inline ssize_t debugfs_attr_write_signed(struct file *file,
 	return -ENODEV;
 }
 
-static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
-                struct dentry *new_dir, char *new_name)
+static inline int __printf(2, 3) debugfs_change_name(struct dentry *dentry,
+					const char *fmt, ...)
 {
-	return ERR_PTR(-ENODEV);
+	return -ENODEV;
 }
 
 static inline void debugfs_create_u8(const char *name, umode_t mode,
@@ -452,6 +471,11 @@ static inline ssize_t debugfs_read_file_str(struct file *file,
 
 #endif
 
+#define debugfs_create_file_aux_num(name, mode, parent, data, n, fops) \
+	debugfs_create_file_aux(name, mode, parent, data, \
+				(void *)(unsigned long)n, fops)
+#define debugfs_get_aux_num(f) (unsigned long)debugfs_get_aux(f)
+
 /**
  * debugfs_create_xul - create a debugfs file that is used to read and write an
  * unsigned long value, formatted in hexadecimal
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6639f48dac36..800dcc360db2 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,25 +29,39 @@ struct task_delay_info {
 	 * XXX_delay contains the accumulated delay time in nanoseconds.
 	 */
 	u64 blkio_start;
+	u64 blkio_delay_max;
+	u64 blkio_delay_min;
 	u64 blkio_delay;	/* wait for sync block io completion */
 	u64 swapin_start;
+	u64 swapin_delay_max;
+	u64 swapin_delay_min;
 	u64 swapin_delay;	/* wait for swapin */
 	u32 blkio_count;	/* total count of the number of sync block */
 				/* io operations performed */
 	u32 swapin_count;	/* total count of swapin */
 
 	u64 freepages_start;
+	u64 freepages_delay_max;
+	u64 freepages_delay_min;
 	u64 freepages_delay;	/* wait for memory reclaim */
 
 	u64 thrashing_start;
+	u64 thrashing_delay_max;
+	u64 thrashing_delay_min;
 	u64 thrashing_delay;	/* wait for thrashing page */
 
 	u64 compact_start;
+	u64 compact_delay_max;
+	u64 compact_delay_min;
 	u64 compact_delay;	/* wait for memory compact */
 
 	u64 wpcopy_start;
+	u64 wpcopy_delay_max;
+	u64 wpcopy_delay_min;
 	u64 wpcopy_delay;	/* wait for write-protect copy */
 
+	u64 irq_delay_max;
+	u64 irq_delay_min;
 	u64 irq_delay;	/* wait for IRQ/SOFTIRQ */
 
 	u32 freepages_count;	/* total count of memory reclaim */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 8321f65897f3..bcc6d7b69470 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -299,6 +299,9 @@ struct target_type {
 #define dm_target_supports_mixed_zoned_model(type) (false)
 #endif
 
+#define DM_TARGET_ATOMIC_WRITES		0x00000400
+#define dm_target_supports_atomic_writes(type) ((type)->features & DM_TARGET_ATOMIC_WRITES)
+
 struct dm_target {
 	struct dm_table *table;
 	struct target_type *type;
diff --git a/include/linux/device.h b/include/linux/device.h
index 667cb6db9019..80a5b3268986 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -399,7 +399,23 @@ void __iomem *devm_of_iomap(struct device *dev,
 #endif
 
 /* allows to add/remove a custom action to devres stack */
-void devm_remove_action(struct device *dev, void (*action)(void *), void *data);
+int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data);
+
+/**
+ * devm_remove_action() - removes previously added custom action
+ * @dev: Device that owns the action
+ * @action: Function implementing the action
+ * @data: Pointer to data passed to @action implementation
+ *
+ * Removes instance of @action previously added by devm_add_action().
+ * Both action and data should match one of the existing entries.
+ */
+static inline
+void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
+{
+	WARN_ON(devm_remove_action_nowarn(dev, action, data));
+}
+
 void devm_release_action(struct device *dev, void (*action)(void *), void *data);
 
 int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name);
@@ -1074,18 +1090,44 @@ void device_del(struct device *dev);
 
 DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T))
 
-int device_for_each_child(struct device *dev, void *data,
-			  int (*fn)(struct device *dev, void *data));
-int device_for_each_child_reverse(struct device *dev, void *data,
-				  int (*fn)(struct device *dev, void *data));
+int device_for_each_child(struct device *parent, void *data,
+			  device_iter_t fn);
+int device_for_each_child_reverse(struct device *parent, void *data,
+				  device_iter_t fn);
 int device_for_each_child_reverse_from(struct device *parent,
-				       struct device *from, const void *data,
-				       int (*fn)(struct device *, const void *));
-struct device *device_find_child(struct device *dev, void *data,
-				 int (*match)(struct device *dev, void *data));
-struct device *device_find_child_by_name(struct device *parent,
-					 const char *name);
-struct device *device_find_any_child(struct device *parent);
+				       struct device *from, void *data,
+				       device_iter_t fn);
+struct device *device_find_child(struct device *parent, const void *data,
+				 device_match_t match);
+/**
+ * device_find_child_by_name - device iterator for locating a child device.
+ * @parent: parent struct device
+ * @name: name of the child device
+ *
+ * This is similar to the device_find_child() function above, but it
+ * returns a reference to a device that has the name @name.
+ *
+ * NOTE: you will need to drop the reference with put_device() after use.
+ */
+static inline struct device *device_find_child_by_name(struct device *parent,
+						       const char *name)
+{
+	return device_find_child(parent, name, device_match_name);
+}
+
+/**
+ * device_find_any_child - device iterator for locating a child device, if any.
+ * @parent: parent struct device
+ *
+ * This is similar to the device_find_child() function above, but it
+ * returns a reference to a child device, if any.
+ *
+ * NOTE: you will need to drop the reference with put_device() after use.
+ */
+static inline struct device *device_find_any_child(struct device *parent)
+{
+	return device_find_child(parent, NULL, device_match_any);
+}
 
 int device_rename(struct device *dev, const char *new_name);
 int device_move(struct device *dev, struct device *new_parent,
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index b18658bce2c3..f5a56efd2bd6 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -134,6 +134,7 @@ typedef int (*device_match_t)(struct device *dev, const void *data);
 
 /* Generic device matching functions that all busses can use to match with */
 int device_match_name(struct device *dev, const void *name);
+int device_match_type(struct device *dev, const void *type);
 int device_match_of_node(struct device *dev, const void *np);
 int device_match_fwnode(struct device *dev, const void *fwnode);
 int device_match_devt(struct device *dev, const void *pdevt);
@@ -141,9 +142,12 @@ int device_match_acpi_dev(struct device *dev, const void *adev);
 int device_match_acpi_handle(struct device *dev, const void *handle);
 int device_match_any(struct device *dev, const void *unused);
 
+/* Device iterating function type for various driver core for_each APIs */
+typedef int (*device_iter_t)(struct device *dev, void *data);
+
 /* iterator helpers for buses */
-int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data,
-		     int (*fn)(struct device *dev, void *data));
+int bus_for_each_dev(const struct bus_type *bus, struct device *start,
+		     void *data, device_iter_t fn);
 struct device *bus_find_device(const struct bus_type *bus, struct device *start,
 			       const void *data, device_match_t match);
 /**
diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index 518c9c83d64b..45ee3a634999 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -82,18 +82,16 @@ bool class_is_registered(const struct class *class);
 struct class_compat;
 struct class_compat *class_compat_register(const char *name);
 void class_compat_unregister(struct class_compat *cls);
-int class_compat_create_link(struct class_compat *cls, struct device *dev,
-			     struct device *device_link);
-void class_compat_remove_link(struct class_compat *cls, struct device *dev,
-			      struct device *device_link);
+int class_compat_create_link(struct class_compat *cls, struct device *dev);
+void class_compat_remove_link(struct class_compat *cls, struct device *dev);
 
 void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class,
 			 const struct device *start, const struct device_type *type);
 struct device *class_dev_iter_next(struct class_dev_iter *iter);
 void class_dev_iter_exit(struct class_dev_iter *iter);
 
-int class_for_each_device(const struct class *class, const struct device *start, void *data,
-			  int (*fn)(struct device *dev, void *data));
+int class_for_each_device(const struct class *class, const struct device *start,
+			  void *data, device_iter_t fn);
 struct device *class_find_device(const struct class *class, const struct device *start,
 				 const void *data, device_match_t match);
 
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index 5c04b8e3833b..cd8e0f0a634b 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -154,7 +154,7 @@ void driver_remove_file(const struct device_driver *driver,
 int driver_set_override(struct device *dev, const char **override,
 			const char *s, size_t len);
 int __must_check driver_for_each_device(struct device_driver *drv, struct device *start,
-					void *data, int (*fn)(struct device *dev, void *));
+					void *data, device_iter_t fn);
 struct device *driver_find_device(const struct device_driver *drv,
 				  struct device *start, const void *data,
 				  device_match_t match);
diff --git a/include/linux/export.h b/include/linux/export.h
index 2633df4d31e6..a8c23d945634 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -52,9 +52,24 @@
 
 #else
 
+#ifdef CONFIG_GENDWARFKSYMS
+/*
+ * With CONFIG_GENDWARFKSYMS, ensure the compiler emits debugging
+ * information for all exported symbols, including those defined in
+ * different TUs, by adding a __gendwarfksyms_ptr_<symbol> pointer
+ * that's discarded during the final link.
+ */
+#define __GENDWARFKSYMS_EXPORT(sym)				\
+	static typeof(sym) *__gendwarfksyms_ptr_##sym __used	\
+		__section(".discard.gendwarfksyms") = &sym;
+#else
+#define __GENDWARFKSYMS_EXPORT(sym)
+#endif
+
 #define __EXPORT_SYMBOL(sym, license, ns)			\
 	extern typeof(sym) sym;					\
 	__ADDRESSABLE(sym)					\
+	__GENDWARFKSYMS_EXPORT(sym)				\
 	asm(__stringify(___EXPORT_SYMBOL(sym, license, ns)))
 
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 534e652bd05f..2c3b2f8a621f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -222,7 +222,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_FSNOTIFY_HSM(mode)	0
 #endif
 
-
 /*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
@@ -791,6 +790,19 @@ struct inode {
 
 static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
 {
+	int testlen;
+
+	/*
+	 * TODO: patch it into a debug-only check if relevant macros show up.
+	 * In the meantime, since we are suffering strlen even on production kernels
+	 * to find the right length, do a fixup if the wrong value got passed.
+	 */
+	testlen = strlen(link);
+	if (testlen != linklen) {
+		WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)",
+			  link, linklen, testlen);
+		linklen = testlen;
+	}
 	inode->i_link = link;
 	inode->i_linklen = linklen;
 	inode->i_opflags |= IOP_CACHED_LINK;
@@ -2926,6 +2938,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
 extern int __must_check file_check_and_advance_wb_err(struct file *file);
 extern int __must_check file_write_and_wait_range(struct file *file,
 						loff_t start, loff_t end);
+int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
+		loff_t end);
 
 static inline int file_write_and_wait(struct file *file)
 {
@@ -2958,6 +2972,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 				(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
 		if (ret)
 			return ret;
+	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
+		struct address_space *mapping = iocb->ki_filp->f_mapping;
+
+		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos,
+					      iocb->ki_pos + count);
 	}
 
 	return count;
@@ -3133,6 +3152,12 @@ static inline void exe_file_allow_write_access(struct file *exe_file)
 	allow_write_access(exe_file);
 }
 
+static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode)
+{
+	file->f_mode &= ~FMODE_FSNOTIFY_MASK;
+	file->f_mode |= mode;
+}
+
 static inline bool inode_is_open_for_write(const struct inode *inode)
 {
 	return atomic_read(&inode->i_writecount) > 0;
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 772f822dc6b8..18855cb44b1c 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -192,7 +192,8 @@ struct fscrypt_operations {
 					     unsigned int *num_devs);
 };
 
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
+int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
+			 struct dentry *dentry, unsigned int flags);
 
 static inline struct fscrypt_inode_info *
 fscrypt_get_inode_info(const struct inode *inode)
@@ -711,8 +712,8 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir,
 	return 0;
 }
 
-static inline int fscrypt_d_revalidate(struct dentry *dentry,
-				       unsigned int flags)
+static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
+				       struct dentry *dentry, unsigned int flags)
 {
 	return 1;
 }
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index c90ec889bfc2..99f30c7d6208 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -438,21 +438,21 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 
 extern const struct bus_type fsl_mc_bus_type;
 
-extern struct device_type fsl_mc_bus_dprc_type;
-extern struct device_type fsl_mc_bus_dpni_type;
-extern struct device_type fsl_mc_bus_dpio_type;
-extern struct device_type fsl_mc_bus_dpsw_type;
-extern struct device_type fsl_mc_bus_dpbp_type;
-extern struct device_type fsl_mc_bus_dpcon_type;
-extern struct device_type fsl_mc_bus_dpmcp_type;
-extern struct device_type fsl_mc_bus_dpmac_type;
-extern struct device_type fsl_mc_bus_dprtc_type;
-extern struct device_type fsl_mc_bus_dpseci_type;
-extern struct device_type fsl_mc_bus_dpdmux_type;
-extern struct device_type fsl_mc_bus_dpdcei_type;
-extern struct device_type fsl_mc_bus_dpaiop_type;
-extern struct device_type fsl_mc_bus_dpci_type;
-extern struct device_type fsl_mc_bus_dpdmai_type;
+extern const struct device_type fsl_mc_bus_dprc_type;
+extern const struct device_type fsl_mc_bus_dpni_type;
+extern const struct device_type fsl_mc_bus_dpio_type;
+extern const struct device_type fsl_mc_bus_dpsw_type;
+extern const struct device_type fsl_mc_bus_dpbp_type;
+extern const struct device_type fsl_mc_bus_dpcon_type;
+extern const struct device_type fsl_mc_bus_dpmcp_type;
+extern const struct device_type fsl_mc_bus_dpmac_type;
+extern const struct device_type fsl_mc_bus_dprtc_type;
+extern const struct device_type fsl_mc_bus_dpseci_type;
+extern const struct device_type fsl_mc_bus_dpdmux_type;
+extern const struct device_type fsl_mc_bus_dpdcei_type;
+extern const struct device_type fsl_mc_bus_dpaiop_type;
+extern const struct device_type fsl_mc_bus_dpci_type;
+extern const struct device_type fsl_mc_bus_dpdmai_type;
 
 static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev)
 {
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 1a9ef8f6784d..6a33288bd6a1 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -129,7 +129,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 
-void file_set_fsnotify_mode(struct file *file);
+void file_set_fsnotify_mode_from_watchers(struct file *file);
 
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
@@ -213,7 +213,7 @@ static inline int fsnotify_open_perm(struct file *file)
 }
 
 #else
-static inline void file_set_fsnotify_mode(struct file *file)
+static inline void file_set_fsnotify_mode_from_watchers(struct file *file)
 {
 }
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index b0fe9f62d15b..6bb1a5a7a4ae 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -212,35 +212,31 @@ struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_
 
 unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 				nodemask_t *nodemask, int nr_pages,
-				struct list_head *page_list,
 				struct page **page_array);
 #define __alloc_pages_bulk(...)			alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__))
 
-unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp,
+unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp,
 				unsigned long nr_pages,
 				struct page **page_array);
-#define  alloc_pages_bulk_array_mempolicy(...)				\
-	alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__))
+#define  alloc_pages_bulk_mempolicy(...)				\
+	alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__))
 
 /* Bulk allocate order-0 pages */
-#define alloc_pages_bulk_list(_gfp, _nr_pages, _list)			\
-	__alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL)
-
-#define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array)		\
-	__alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array)
+#define alloc_pages_bulk(_gfp, _nr_pages, _page_array)		\
+	__alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array)
 
 static inline unsigned long
-alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages,
+alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages,
 				   struct page **page_array)
 {
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 
-	return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array);
+	return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array);
 }
 
-#define alloc_pages_bulk_array_node(...)				\
-	alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__))
+#define alloc_pages_bulk_node(...)				\
+	alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__))
 
 static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
 {
@@ -300,8 +296,6 @@ static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask,
 
 #ifdef CONFIG_NUMA
 struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order);
-struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
-		struct mempolicy *mpol, pgoff_t ilx, int nid);
 struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order);
 struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
 		struct mempolicy *mpol, pgoff_t ilx, int nid);
@@ -312,11 +306,6 @@ static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order
 {
 	return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order);
 }
-static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
-		struct mempolicy *mpol, pgoff_t ilx, int nid)
-{
-	return alloc_pages_noprof(gfp, order);
-}
 static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order)
 {
 	return __folio_alloc_node_noprof(gfp, order, numa_node_id());
@@ -331,7 +320,6 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde
 #endif
 
 #define alloc_pages(...)			alloc_hooks(alloc_pages_noprof(__VA_ARGS__))
-#define alloc_pages_mpol(...)			alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__))
 #define folio_alloc(...)			alloc_hooks(folio_alloc_noprof(__VA_ARGS__))
 #define folio_alloc_mpol(...)			alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__))
 #define vma_alloc_folio(...)			alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__))
diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h
index c3b4b7ed7c16..84a5045f80f3 100644
--- a/include/linux/hrtimer_defs.h
+++ b/include/linux/hrtimer_defs.h
@@ -125,6 +125,7 @@ struct hrtimer_cpu_base {
 	ktime_t				softirq_expires_next;
 	struct hrtimer			*softirq_next_timer;
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
+	call_single_data_t		csd;
 } ____cacheline_aligned;
 
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b94c2e8ee918..93e509b6c00e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -121,6 +121,8 @@ enum mthp_stat_item {
 	MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
 	MTHP_STAT_ZSWPOUT,
 	MTHP_STAT_SWPIN,
+	MTHP_STAT_SWPIN_FALLBACK,
+	MTHP_STAT_SWPIN_FALLBACK_CHARGE,
 	MTHP_STAT_SWPOUT,
 	MTHP_STAT_SWPOUT_FALLBACK,
 	MTHP_STAT_SHMEM_ALLOC,
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ae4fe8615bb6..ec8c0ccc8f95 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -153,11 +153,11 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
-bool isolate_hugetlb(struct folio *folio, struct list_head *list);
+bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list);
 int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison);
 int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 				bool *migratable_cleared);
-void folio_putback_active_hugetlb(struct folio *folio);
+void folio_putback_hugetlb(struct folio *folio);
 void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
@@ -414,7 +414,7 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	return NULL;
 }
 
-static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list)
+static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list)
 {
 	return false;
 }
@@ -430,7 +430,7 @@ static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 	return 0;
 }
 
-static inline void folio_putback_active_hugetlb(struct folio *folio)
+static inline void folio_putback_hugetlb(struct folio *folio)
 {
 }
 
@@ -681,8 +681,9 @@ struct huge_bootmem_page {
 };
 
 int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
+int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
-				unsigned long addr, int avoid_reserve);
+				unsigned long addr, bool cow_from_owner);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
 				nodemask_t *nmask, gfp_t gfp_mask,
 				bool allow_alloc_fallback);
@@ -1059,9 +1060,15 @@ static inline int isolate_or_dissolve_huge_page(struct page *page,
 	return -ENOMEM;
 }
 
+static inline int replace_free_hugepage_folios(unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	return 0;
+}
+
 static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 					   unsigned long addr,
-					   int avoid_reserve)
+					   bool cow_from_owner)
 {
 	return NULL;
 }
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index c31fd1dba3bd..2b2af24d2a43 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -244,6 +244,7 @@ enum i2c_driver_flags {
  * @id_table: List of I2C devices supported by this driver
  * @detect: Callback for device detection
  * @address_list: The I2C addresses to probe (for detect)
+ * @clients: List of detected clients we created (for i2c-core use only)
  * @flags: A bitmask of flags defined in &enum i2c_driver_flags
  *
  * The driver.owner field should be set to the module owner of this driver.
@@ -298,6 +299,7 @@ struct i2c_driver {
 	/* Device detection callback for automatic device creation */
 	int (*detect)(struct i2c_client *client, struct i2c_board_info *info);
 	const unsigned short *address_list;
+	struct list_head clients;
 
 	u32 flags;
 };
@@ -313,6 +315,8 @@ struct i2c_driver {
  * @dev: Driver model device node for the slave.
  * @init_irq: IRQ that was set at initialization
  * @irq: indicates the IRQ generated by this device (if any)
+ * @detected: member of an i2c_driver.clients list or i2c-core's
+ *	userspace_devices list
  * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter
  *	calls it to pass on slave events to the slave driver.
  * @devres_group_id: id of the devres group that will be created for resources
@@ -332,8 +336,6 @@ struct i2c_client {
 #define I2C_CLIENT_SLAVE	0x20	/* we are the slave */
 #define I2C_CLIENT_HOST_NOTIFY	0x40	/* We want to use I2C host notify */
 #define I2C_CLIENT_WAKE		0x80	/* for board_info; true iff can wake */
-#define I2C_CLIENT_AUTO		0x100	/* client was auto-detected */
-#define I2C_CLIENT_USER		0x200	/* client was userspace-created */
 #define I2C_CLIENT_SCCB		0x9000	/* Use Omnivision SCCB protocol */
 					/* Must match I2C_M_STOP|IGNORE_NAK */
 
@@ -345,6 +347,7 @@ struct i2c_client {
 	struct device dev;		/* the device structure		*/
 	int init_irq;			/* irq set at initialization	*/
 	int irq;			/* irq issued by device		*/
+	struct list_head detected;
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
 	i2c_slave_cb_t slave_cb;	/* callback for slave mode	*/
 #endif
@@ -751,6 +754,9 @@ struct i2c_adapter {
 	char name[48];
 	struct completion dev_released;
 
+	struct mutex userspace_clients_lock;
+	struct list_head userspace_clients;
+
 	struct i2c_bus_recovery_info *bus_recovery_info;
 	const struct i2c_adapter_quirks *quirks;
 
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index f8c1d2505940..417073c52380 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -29,6 +29,7 @@ struct ad_sd_calib_data {
 
 struct ad_sigma_delta;
 struct device;
+struct gpio_desc;
 struct iio_dev;
 
 /**
@@ -53,6 +54,7 @@ struct iio_dev;
  * @irq_flags: flags for the interrupt used by the triggered buffer
  * @num_slots: Number of sequencer slots
  * @irq_line: IRQ for reading conversions. If 0, spi->irq will be used
+ * @num_resetclks: Number of SPI clk cycles with MOSI=1 to reset the chip.
  */
 struct ad_sigma_delta_info {
 	int (*set_channel)(struct ad_sigma_delta *, unsigned int channel);
@@ -69,6 +71,7 @@ struct ad_sigma_delta_info {
 	unsigned long irq_flags;
 	unsigned int num_slots;
 	int irq_line;
+	unsigned int num_resetclks;
 };
 
 /**
@@ -85,6 +88,7 @@ struct ad_sigma_delta {
 
 /* private: */
 	struct completion	completion;
+	spinlock_t		irq_lock; /* protects .irq_dis and irq en/disable state */
 	bool			irq_dis;
 
 	bool			bus_locked;
@@ -96,7 +100,8 @@ struct ad_sigma_delta {
 	unsigned int		active_slots;
 	unsigned int		current_slot;
 	unsigned int		num_slots;
-	int		irq_line;
+	struct gpio_desc	*rdy_gpiod;
+	int			irq_line;
 	bool			status_appended;
 	/* map slots to channels in order to know what to expect from devices */
 	unsigned int		*slots;
@@ -178,8 +183,7 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int *val);
 
-int ad_sd_reset(struct ad_sigma_delta *sigma_delta,
-	unsigned int reset_length);
+int ad_sd_reset(struct ad_sigma_delta *sigma_delta);
 
 int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, int *val);
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index 418b1307d3f2..3b8d618bb3df 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -37,7 +37,7 @@ int iio_pop_from_buffer(struct iio_buffer *buffer, void *data);
 static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev,
 	void *data, int64_t timestamp)
 {
-	if (indio_dev->scan_timestamp) {
+	if (ACCESS_PRIVATE(indio_dev, scan_timestamp)) {
 		size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1;
 		((int64_t *)data)[ts_offset] = timestamp;
 	}
diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h
index 333d1d8ccb37..6a4479616479 100644
--- a/include/linux/iio/consumer.h
+++ b/include/linux/iio/consumer.h
@@ -418,7 +418,7 @@ unsigned int iio_get_channel_ext_info_count(struct iio_channel *chan);
  * @chan:		The channel being queried.
  * @attr:		The ext_info attribute to read.
  * @buf:		Where to store the attribute value. Assumed to hold
- *			at least PAGE_SIZE bytes.
+ *			at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE.
  *
  * Returns the number of bytes written to buf (perhaps w/o zero termination;
  * it need not even be a string), or an error code.
@@ -445,7 +445,7 @@ ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr,
  * iio_read_channel_label() - read label for a given channel
  * @chan:		The channel being queried.
  * @buf:		Where to store the attribute value. Assumed to hold
- *			at least PAGE_SIZE bytes.
+ *			at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE.
  *
  * Returns the number of bytes written to buf, or an error code.
  */
diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h
index 9cb6c80dea71..e5de7a124bad 100644
--- a/include/linux/iio/iio-gts-helper.h
+++ b/include/linux/iio/iio-gts-helper.h
@@ -188,6 +188,9 @@ int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain,
 int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel,
 					       int scale_int, int scale_nano,
 					       int *gain_sel);
+int iio_gts_find_gain_time_sel_for_scale(struct iio_gts *gts, int scale_int,
+					 int scale_nano, int *gain_sel,
+					 int *time_sel);
 int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int,
 		      int *scale_nano);
 int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts,
@@ -196,6 +199,9 @@ int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts,
 int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain,
 					   int old_time, int new_time,
 					   int *new_gain);
+int iio_gts_find_new_gain_by_gain_time_min(struct iio_gts *gts, int old_gain,
+					   int old_time, int new_time,
+					   int *new_gain, bool *in_range);
 int iio_gts_avail_times(struct iio_gts *gts,  const int **vals, int *type,
 			int *length);
 int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type,
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index a89e7e43e441..4247497f3f8b 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -28,7 +28,7 @@
  * @groupcounter:		index of next attribute group
  * @legacy_scan_el_group:	attribute group for legacy scan elements attribute group
  * @legacy_buffer_group:	attribute group for legacy buffer attributes group
- * @bounce_buffer:		for devices that call iio_push_to_buffers_with_timestamp_unaligned()
+ * @bounce_buffer:		for devices that call iio_push_to_buffers_with_ts_unaligned()
  * @bounce_buffer_size:		size of currently allocate bounce buffer
  * @scan_index_timestamp:	cache of the index to the timestamp
  * @clock_id:			timestamping clock posix identifier
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index ae65890d4567..56161e02f002 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -611,7 +611,7 @@ struct iio_dev {
 	const unsigned long		*available_scan_masks;
 	unsigned int			__private masklength;
 	const unsigned long		*active_scan_mask;
-	bool				scan_timestamp;
+	bool				__private scan_timestamp;
 	struct iio_trigger		*trig;
 	struct iio_poll_func		*pollfunc;
 	struct iio_poll_func		*pollfunc_event;
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index e6a75356567a..4bb98d9731de 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -99,7 +99,6 @@ struct adis_data {
  * @spi: Reference to SPI device which owns this ADIS IIO device
  * @trig: IIO trigger object data
  * @data: ADIS chip variant specific data
- * @burst: ADIS burst transfer information
  * @burst_extra_len: Burst extra length. Should only be used by devices that can
  *		     dynamically change their burst mode length.
  * @state_lock: Lock used by the device to protect state
diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h
index 37572e4dc73a..1ee237b56183 100644
--- a/include/linux/iio/timer/stm32-timer-trigger.h
+++ b/include/linux/iio/timer/stm32-timer-trigger.h
@@ -72,6 +72,12 @@
 
 #define TIM17_OC1	"tim17_oc1"
 
+#define TIM20_OC1	"tim20_oc1"
+#define TIM20_OC2	"tim20_oc2"
+#define TIM20_OC3	"tim20_oc3"
+#define TIM20_TRGO	"tim20_trgo"
+#define TIM20_TRGO2	"tim20_trgo2"
+
 #if IS_REACHABLE(CONFIG_IIO_STM32_TIMER_TRIGGER)
 bool is_stm32_timer_trigger(struct iio_trigger *trig);
 #else
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index a3ce553413de..abd0c8bd950b 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -19,8 +19,8 @@ struct io_uring_cmd {
 };
 
 struct io_uring_cmd_data {
-	struct io_uring_sqe	sqes[2];
 	void			*op_data;
+	struct io_uring_sqe	sqes[2];
 };
 
 static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 623d8e798a11..3def525a1da3 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -222,7 +222,8 @@ struct io_alloc_cache {
 	void			**entries;
 	unsigned int		nr_cached;
 	unsigned int		max_cached;
-	size_t			elem_size;
+	unsigned int		elem_size;
+	unsigned int		init_clear;
 };
 
 struct io_ring_ctx {
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index ed945f42e064..0ea8c9887429 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -537,7 +537,7 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m)
  *
  * Return: jiffies value
  */
-#define secs_to_jiffies(_secs) ((_secs) * HZ)
+#define secs_to_jiffies(_secs) (unsigned long)((_secs) * HZ)
 
 extern unsigned long __usecs_to_jiffies(const unsigned int u);
 #if !(USEC_PER_SEC % HZ)
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index c3f075e8f60c..1c6a6c1704d8 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -57,10 +57,10 @@ static inline void *dereference_symbol_descriptor(void *ptr)
 
 	preempt_disable();
 	mod = __module_address((unsigned long)ptr);
-	preempt_enable();
 
 	if (mod)
 		ptr = dereference_module_function_descriptor(mod, ptr);
+	preempt_enable();
 #endif
 	return ptr;
 }
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 6bbfc8aa42e8..890011071f2b 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -153,7 +153,7 @@ static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 
 void __kasan_poison_new_object(struct kmem_cache *cache, void *object);
 /**
- * kasan_unpoison_new_object - Repoison a new slab object.
+ * kasan_poison_new_object - Repoison a new slab object.
  * @cache: Cache the object belong to.
  * @object: Pointer to the object.
  *
@@ -491,7 +491,6 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
 void kasan_record_aux_stack(void *ptr);
-void kasan_record_aux_stack_noalloc(void *ptr);
 
 #else /* CONFIG_KASAN_GENERIC */
 
@@ -509,7 +508,6 @@ static inline void kasan_cache_create(struct kmem_cache *cache,
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
 static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
 static inline void kasan_record_aux_stack(void *ptr) {}
-static inline void kasan_record_aux_stack_noalloc(void *ptr) {}
 
 #endif /* CONFIG_KASAN_GENERIC */
 
diff --git a/include/linux/kcore.h b/include/linux/kcore.h
index 86c0f1d18998..9a2fa013c91d 100644
--- a/include/linux/kcore.h
+++ b/include/linux/kcore.h
@@ -20,19 +20,6 @@ struct kcore_list {
 	int type;
 };
 
-struct vmcore {
-	struct list_head list;
-	unsigned long long paddr;
-	unsigned long long size;
-	loff_t offset;
-};
-
-struct vmcoredd_node {
-	struct list_head list;	/* List of dumps */
-	void *buf;		/* Buffer containing device's dump */
-	unsigned int size;	/* Size of the buffer */
-};
-
 #ifdef CONFIG_PROC_KCORE
 void __init kclist_add(struct kcore_list *, void *, size_t, int type);
 
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 76e891ee9e37..51ef131e66b7 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -309,11 +309,9 @@ extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);
 #ifdef CONFIG_SERIAL_KGDB_NMI
 extern int kgdb_register_nmi_console(void);
 extern int kgdb_unregister_nmi_console(void);
-extern bool kgdb_nmi_poll_knock(void);
 #else
 static inline int kgdb_register_nmi_console(void) { return 0; }
 static inline int kgdb_unregister_nmi_console(void) { return 0; }
-static inline bool kgdb_nmi_poll_knock(void) { return true; }
 #endif
 
 extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops);
diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h
index be707748e7ce..150fe2ae1b6b 100644
--- a/include/linux/kobject_ns.h
+++ b/include/linux/kobject_ns.h
@@ -52,8 +52,6 @@ const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj);
 
 bool kobj_ns_current_may_mount(enum kobj_ns_type type);
 void *kobj_ns_grab_current(enum kobj_ns_type type);
-const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk);
-const void *kobj_ns_initial(enum kobj_ns_type type);
 void kobj_ns_drop(enum kobj_ns_type type, void *ns);
 
 #endif /* _LINUX_KOBJECT_NS_H */
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 6a53ac4885bb..d73095b5cd96 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -93,6 +93,7 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
 void collect_procs_ksm(const struct folio *folio, const struct page *page,
 		struct list_head *to_kill, int force_early);
 long ksm_process_profit(struct mm_struct *);
+bool ksm_process_mergeable(struct mm_struct *mm);
 
 #else  /* !CONFIG_KSM */
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3cb9a32a6330..f34f4cfaa513 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1615,7 +1615,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu);
-int kvm_arch_post_init_vm(struct kvm *kvm);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
 void kvm_arch_create_vm_debugfs(struct kvm *kvm);
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index be5183d75736..c1c57f814b98 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1199,10 +1199,9 @@ extern int ata_std_bios_param(struct scsi_device *sdev,
 			      struct block_device *bdev,
 			      sector_t capacity, int geom[]);
 extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev);
-extern int ata_scsi_slave_alloc(struct scsi_device *sdev);
-int ata_scsi_device_configure(struct scsi_device *sdev,
-		struct queue_limits *lim);
-extern void ata_scsi_slave_destroy(struct scsi_device *sdev);
+extern int ata_scsi_sdev_init(struct scsi_device *sdev);
+int ata_scsi_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim);
+extern void ata_scsi_sdev_destroy(struct scsi_device *sdev);
 extern int ata_scsi_change_queue_depth(struct scsi_device *sdev,
 				       int queue_depth);
 extern int ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
@@ -1301,8 +1300,8 @@ extern struct ata_port *ata_port_alloc(struct ata_host *host);
 extern void ata_port_free(struct ata_port *ap);
 extern int ata_tport_add(struct device *parent, struct ata_port *ap);
 extern void ata_tport_delete(struct ata_port *ap);
-int ata_sas_device_configure(struct scsi_device *sdev, struct queue_limits *lim,
-		struct ata_port *ap);
+int ata_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim,
+			   struct ata_port *ap);
 extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
 extern void ata_tf_to_fis(const struct ata_taskfile *tf,
 			  u8 pmp, int is_cmd, u8 *fis);
@@ -1458,8 +1457,8 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 	.this_id		= ATA_SHT_THIS_ID,		\
 	.emulated		= ATA_SHT_EMULATED,		\
 	.proc_name		= drv_name,			\
-	.slave_alloc		= ata_scsi_slave_alloc,		\
-	.slave_destroy		= ata_scsi_slave_destroy,	\
+	.sdev_init		= ata_scsi_sdev_init,		\
+	.sdev_destroy		= ata_scsi_sdev_destroy,	\
 	.bios_param		= ata_std_bios_param,		\
 	.unlock_native_capacity	= ata_scsi_unlock_native_capacity,\
 	.max_sectors		= ATA_MAX_SECTORS_LBA48
@@ -1468,13 +1467,13 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= ATA_DEF_QUEUE,		\
 	.tag_alloc_policy_rr	= true,				\
-	.device_configure	= ata_scsi_device_configure
+	.sdev_configure		= ata_scsi_sdev_configure
 
 #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd)			\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= drv_qd,			\
 	.tag_alloc_policy_rr	= true,				\
-	.device_configure	= ata_scsi_device_configure
+	.sdev_configure		= ata_scsi_sdev_configure
 
 #define ATA_BASE_SHT(drv_name)					\
 	ATA_SUBBASE_SHT(drv_name),				\
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 05c166811f6b..fe739d35a864 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -91,13 +91,24 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
  * @memcg: the cgroup of the sublist to add the item to.
  *
  * If the element is already part of a list, this function returns doing
- * nothing. Therefore the caller does not need to keep state about whether or
- * not the element already belongs in the list and is allowed to lazy update
- * it. Note however that this is valid for *a* list, not *this* list. If
- * the caller organize itself in a way that elements can be in more than
- * one type of list, it is up to the caller to fully remove the item from
- * the previous list (with list_lru_del() for instance) before moving it
- * to @lru.
+ * nothing. This means that it is not necessary to keep state about whether or
+ * not the element already belongs in the list. That said, this logic only
+ * works if the item is in *this* list. If the item might be in some other
+ * list, then you cannot rely on this check and you must remove it from the
+ * other list before trying to insert it.
+ *
+ * The lru list consists of many sublists internally; the @nid and @memcg
+ * parameters are used to determine which sublist to insert the item into.
+ * It's important to use the right value of @nid and @memcg when deleting the
+ * item, since it might otherwise get deleted from the wrong sublist.
+ *
+ * This also applies when attempting to insert the item multiple times - if
+ * the item is currently in one sublist and you call list_lru_add() again, you
+ * must pass the right @nid and @memcg parameters so that the same sublist is
+ * used.
+ *
+ * You must ensure that the memcg is not freed during this call (e.g., with
+ * rcu or by taking a css refcnt).
  *
  * Return: true if the list was updated, false otherwise
  */
@@ -113,7 +124,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
  * memcg of the sublist is determined by @item list_head. This assumption is
  * valid for slab objects LRU such as dentries, inodes, etc.
  *
- * Return value: true if the list was updated, false otherwise
+ * Return: true if the list was updated, false otherwise
  */
 bool list_lru_add_obj(struct list_lru *lru, struct list_head *item);
 
@@ -125,8 +136,19 @@ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item);
  * @memcg: the cgroup of the sublist to delete the item from.
  *
  * This function works analogously as list_lru_add() in terms of list
- * manipulation. The comments about an element already pertaining to
- * a list are also valid for list_lru_del().
+ * manipulation.
+ *
+ * The comments in list_lru_add() about an element already being in a list are
+ * also valid for list_lru_del(), that is, you can delete an item that has
+ * already been removed or never been added. However, if the item is in a
+ * list, it must be in *this* list, and you must pass the right value of @nid
+ * and @memcg so that the right sublist is used.
+ *
+ * You must ensure that the memcg is not freed during this call (e.g., with
+ * rcu or by taking a css refcnt). When a memcg is deleted, list_lru entries
+ * are automatically moved to the parent memcg. This is done in a race-free
+ * way, so during deletion of an memcg both the old and new memcg will resolve
+ * to the same sublist internally.
  *
  * Return: true if the list was updated, false otherwise
  */
@@ -142,7 +164,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
  * memcg of the sublist is determined by @item list_head. This assumption is
  * valid for slab objects LRU such as dentries, inodes, etc.
  *
- * Return value: true if the list was updated, false otherwise.
+ * Return: true if the list was updated, false otherwise.
  */
 bool list_lru_del_obj(struct list_lru *lru, struct list_head *item);
 
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index c39f119659ba..676721ee878d 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -37,12 +37,13 @@ struct lockref {
 /**
  * lockref_init - Initialize a lockref
  * @lockref: pointer to lockref structure
- * @count: initial count
+ *
+ * Initializes @lockref->count to 1.
  */
-static inline void lockref_init(struct lockref *lockref, unsigned int count)
+static inline void lockref_init(struct lockref *lockref)
 {
 	spin_lock_init(&lockref->lock);
-	lockref->count = count;
+	lockref->count = 1;
 }
 
 void lockref_get(struct lockref *lockref);
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index b16e15b9587a..ad6042a718b5 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -645,4 +645,10 @@ int LZ4_decompress_safe_usingDict(const char *source, char *dest,
 int LZ4_decompress_fast_usingDict(const char *source, char *dest,
 	int originalSize, const char *dictStart, int dictSize);
 
+#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize)          (((compressedSize) >> 8) + 32)
+
+#ifndef LZ4_DISTANCE_MAX	/* history window size; can be user-defined at compile time */
+#define LZ4_DISTANCE_MAX 65535	/* set to maximum value by default */
+#endif
+
 #endif
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 673d5cae7c81..e79eb6ac516f 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -378,6 +378,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r)
 /* Flags for memblock allocation APIs */
 #define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
 #define MEMBLOCK_ALLOC_ACCESSIBLE	0
+/*
+ *  MEMBLOCK_ALLOC_NOLEAKTRACE avoids kmemleak tracing. It implies
+ *  MEMBLOCK_ALLOC_ACCESSIBLE
+ */
 #define MEMBLOCK_ALLOC_NOLEAKTRACE	1
 
 /* We are using top down, so it is safe to use 0 here */
@@ -417,6 +421,12 @@ static __always_inline void *memblock_alloc(phys_addr_t size, phys_addr_t align)
 				      MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
 }
 
+void *__memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align,
+				const char *func);
+
+#define memblock_alloc_or_panic(size, align)    \
+	 __memblock_alloc_or_panic(size, align, __func__)
+
 static inline void *memblock_alloc_raw(phys_addr_t size,
 					       phys_addr_t align)
 {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 5502aa8e138e..6e74b8254d9b 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -620,8 +620,6 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
 		page_counter_read(&memcg->memory);
 }
 
-void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg);
-
 int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp);
 
 /**
@@ -646,8 +644,7 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
 	return __mem_cgroup_charge(folio, mm, gfp);
 }
 
-int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
-		long nr_pages);
+int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp);
 
 int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
 				  gfp_t gfp, swp_entry_t entry);
@@ -677,7 +674,6 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 	__mem_cgroup_uncharge_folios(folios);
 }
 
-void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages);
 void mem_cgroup_replace_folio(struct folio *old, struct folio *new);
 void mem_cgroup_migrate(struct folio *old, struct folio *new);
 
@@ -1046,6 +1042,23 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 
 void split_page_memcg(struct page *head, int old_order, int new_order);
 
+static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
+{
+	struct mem_cgroup *memcg;
+	u64 id;
+
+	if (mem_cgroup_disabled())
+		return 0;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (!memcg)
+		memcg = root_mem_cgroup;
+	id = cgroup_id(memcg->css.cgroup);
+	rcu_read_unlock();
+	return id;
+}
+
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
@@ -1135,21 +1148,15 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *target,
 	return false;
 }
 
-static inline void mem_cgroup_commit_charge(struct folio *folio,
-		struct mem_cgroup *memcg)
-{
-}
-
 static inline int mem_cgroup_charge(struct folio *folio,
 		struct mm_struct *mm, gfp_t gfp)
 {
 	return 0;
 }
 
-static inline int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg,
-		gfp_t gfp, long nr_pages)
+static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp)
 {
-	return 0;
+        return 0;
 }
 
 static inline int mem_cgroup_swapin_charge_folio(struct folio *folio,
@@ -1170,11 +1177,6 @@ static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 {
 }
 
-static inline void mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
-		unsigned int nr_pages)
-{
-}
-
 static inline void mem_cgroup_replace_folio(struct folio *old,
 		struct folio *new)
 {
@@ -1466,6 +1468,11 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 static inline void split_page_memcg(struct page *head, int old_order, int new_order)
 {
 }
+
+static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
+{
+	return 0;
+}
 #endif /* CONFIG_MEMCG */
 
 /*
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index d437e3070850..246daadbfde8 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -7,7 +7,14 @@
 #ifdef CONFIG_MEMFD_CREATE
 extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
 struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
-unsigned int *memfd_file_seals_ptr(struct file *file);
+/*
+ * Check for any existing seals on mmap, return an error if access is denied due
+ * to sealing, or 0 otherwise.
+ *
+ * We also update VMA flags if appropriate by manipulating the VMA flags pointed
+ * to by vm_flags_ptr.
+ */
+int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr);
 #else
 static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
 {
@@ -17,19 +24,11 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 {
 	return ERR_PTR(-EINVAL);
 }
-
-static inline unsigned int *memfd_file_seals_ptr(struct file *file)
+static inline int memfd_check_seals_mmap(struct file *file,
+					 unsigned long *vm_flags_ptr)
 {
-	return NULL;
+	return 0;
 }
 #endif
 
-/* Retrieve memfd seals associated with the file, if any. */
-static inline unsigned int memfd_file_seals(struct file *file)
-{
-	unsigned int *sealsp = memfd_file_seals_ptr(file);
-
-	return sealsp ? *sealsp : 0;
-}
-
 #endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index b27ddce5d324..eaac5ae8c05c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -144,8 +144,6 @@ extern u64 max_mem_size;
 
 extern int mhp_online_type_from_str(const char *str);
 
-/* Default online_type (MMOP_*) when new memory blocks are added. */
-extern int mhp_default_online_type;
 /* If movable_node boot option specified */
 extern bool movable_node_enabled;
 static inline bool movable_node_is_enabled(void)
@@ -303,6 +301,9 @@ static inline void __remove_memory(u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+/* Default online_type (MMOP_*) when new memory blocks are added. */
+extern int mhp_get_default_online_type(void);
+extern void mhp_set_default_online_type(int online_type);
 extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat);
 extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
 extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 002e49b2ebd9..29919faea2f1 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -144,16 +144,14 @@ const struct movable_operations *page_movable_ops(struct page *page)
 #ifdef CONFIG_NUMA_BALANCING
 int migrate_misplaced_folio_prepare(struct folio *folio,
 		struct vm_area_struct *vma, int node);
-int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
-			   int node);
+int migrate_misplaced_folio(struct folio *folio, int node);
 #else
 static inline int migrate_misplaced_folio_prepare(struct folio *folio,
 		struct vm_area_struct *vma, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
-static inline int migrate_misplaced_folio(struct folio *folio,
-					 struct vm_area_struct *vma, int node)
+static inline int migrate_misplaced_folio(struct folio *folio, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h
index 6325f6ffb895..1160bed6579e 100644
--- a/include/linux/min_heap.h
+++ b/include/linux/min_heap.h
@@ -6,6 +6,17 @@
 #include <linux/string.h>
 #include <linux/types.h>
 
+/*
+ * The Min Heap API provides utilities for managing min-heaps, a binary tree
+ * structure where each node's value is less than or equal to its children's
+ * values, ensuring the smallest element is at the root.
+ *
+ * Users should avoid directly calling functions prefixed with __min_heap_*().
+ * Instead, use the provided macro wrappers.
+ *
+ * For further details and examples, refer to Documentation/core-api/min_heap.rst.
+ */
+
 /**
  * Data structure to hold a min-heap.
  * @nr: Number of elements currently in the heap.
@@ -218,7 +229,7 @@ void __min_heap_init_inline(min_heap_char *heap, void *data, int size)
 }
 
 #define min_heap_init_inline(_heap, _data, _size)	\
-	__min_heap_init_inline((min_heap_char *)_heap, _data, _size)
+	__min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size)
 
 /* Get the minimum element from the heap. */
 static __always_inline
@@ -228,7 +239,8 @@ void *__min_heap_peek_inline(struct min_heap_char *heap)
 }
 
 #define min_heap_peek_inline(_heap)	\
-	(__minheap_cast(_heap) __min_heap_peek_inline((min_heap_char *)_heap))
+	(__minheap_cast(_heap)	\
+	 __min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr)))
 
 /* Check if the heap is full. */
 static __always_inline
@@ -238,7 +250,7 @@ bool __min_heap_full_inline(min_heap_char *heap)
 }
 
 #define min_heap_full_inline(_heap)	\
-	__min_heap_full_inline((min_heap_char *)_heap)
+	__min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr))
 
 /* Sift the element at pos down the heap. */
 static __always_inline
@@ -277,8 +289,8 @@ void __min_heap_sift_down_inline(min_heap_char *heap, int pos, size_t elem_size,
 }
 
 #define min_heap_sift_down_inline(_heap, _pos, _func, _args)	\
-	__min_heap_sift_down_inline((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap),	\
-				    _func, _args)
+	__min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos,	\
+				    __minheap_obj_size(_heap), _func, _args)
 
 /* Sift up ith element from the heap, O(log2(nr)). */
 static __always_inline
@@ -304,8 +316,8 @@ void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx
 }
 
 #define min_heap_sift_up_inline(_heap, _idx, _func, _args)	\
-	__min_heap_sift_up_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx,	\
-				  _func, _args)
+	__min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+				  __minheap_obj_size(_heap), _idx, _func, _args)
 
 /* Floyd's approach to heapification that is O(nr). */
 static __always_inline
@@ -319,7 +331,8 @@ void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size,
 }
 
 #define min_heapify_all_inline(_heap, _func, _args)	\
-	__min_heapify_all_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+	__min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+				 __minheap_obj_size(_heap), _func, _args)
 
 /* Remove minimum element from the heap, O(log2(nr)). */
 static __always_inline
@@ -340,7 +353,8 @@ bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size,
 }
 
 #define min_heap_pop_inline(_heap, _func, _args)	\
-	__min_heap_pop_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+	__min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			      __minheap_obj_size(_heap), _func, _args)
 
 /*
  * Remove the minimum element and then push the given element. The
@@ -356,8 +370,8 @@ void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t
 }
 
 #define min_heap_pop_push_inline(_heap, _element, _func, _args)	\
-	__min_heap_pop_push_inline((min_heap_char *)_heap, _element, __minheap_obj_size(_heap),	\
-				   _func, _args)
+	__min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+				   __minheap_obj_size(_heap), _func, _args)
 
 /* Push an element on to the heap, O(log2(nr)). */
 static __always_inline
@@ -382,8 +396,8 @@ bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t ele
 }
 
 #define min_heap_push_inline(_heap, _element, _func, _args)	\
-	__min_heap_push_inline((min_heap_char *)_heap, _element, __minheap_obj_size(_heap),	\
-			       _func, _args)
+	__min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+					    __minheap_obj_size(_heap), _func, _args)
 
 /* Remove ith element from the heap, O(log2(nr)). */
 static __always_inline
@@ -411,8 +425,8 @@ bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx,
 }
 
 #define min_heap_del_inline(_heap, _idx, _func, _args)	\
-	__min_heap_del_inline((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx,	\
-			      _func, _args)
+	__min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			      __minheap_obj_size(_heap), _idx, _func, _args)
 
 void __min_heap_init(min_heap_char *heap, void *data, int size);
 void *__min_heap_peek(struct min_heap_char *heap);
@@ -433,25 +447,31 @@ bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
 		    const struct min_heap_callbacks *func, void *args);
 
 #define min_heap_init(_heap, _data, _size)	\
-	__min_heap_init((min_heap_char *)_heap, _data, _size)
+	__min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size)
 #define min_heap_peek(_heap)	\
-	(__minheap_cast(_heap) __min_heap_peek((min_heap_char *)_heap))
+	(__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr)))
 #define min_heap_full(_heap)	\
-	__min_heap_full((min_heap_char *)_heap)
+	__min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr))
 #define min_heap_sift_down(_heap, _pos, _func, _args)	\
-	__min_heap_sift_down((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args)
+	__min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos,	\
+			     __minheap_obj_size(_heap), _func, _args)
 #define min_heap_sift_up(_heap, _idx, _func, _args)	\
-	__min_heap_sift_up((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
+	__min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			   __minheap_obj_size(_heap), _idx, _func, _args)
 #define min_heapify_all(_heap, _func, _args)	\
-	__min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+	__min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			  __minheap_obj_size(_heap), _func, _args)
 #define min_heap_pop(_heap, _func, _args)	\
-	__min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args)
+	__min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr),	\
+		       __minheap_obj_size(_heap), _func, _args)
 #define min_heap_pop_push(_heap, _element, _func, _args)	\
-	__min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap),	\
-			    _func, _args)
+	__min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+			    __minheap_obj_size(_heap), _func, _args)
 #define min_heap_push(_heap, _element, _func, _args)	\
-	__min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args)
+	__min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+			__minheap_obj_size(_heap), _func, _args)
 #define min_heap_del(_heap, _idx, _func, _args)	\
-	__min_heap_del((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args)
+	__min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr),	\
+		       __minheap_obj_size(_heap), _idx, _func, _args)
 
 #endif /* _LINUX_MIN_HEAP_H */
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 98008dd92153..eaaf5c008e4d 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -8,13 +8,10 @@
 #include <linux/types.h>
 
 /*
- * min()/max()/clamp() macros must accomplish three things:
+ * min()/max()/clamp() macros must accomplish several things:
  *
  * - Avoid multiple evaluations of the arguments (so side-effects like
  *   "x++" happen only once) when non-constant.
- * - Retain result as a constant expressions when called with only
- *   constant expressions (to avoid tripping VLA warnings in stack
- *   allocation usage).
  * - Perform signed v unsigned type-checking (to generate compile
  *   errors instead of nasty runtime surprises).
  * - Unsigned char/short are always promoted to signed int and can be
@@ -31,58 +28,54 @@
  *   bit #0 set if ok for unsigned comparisons
  *   bit #1 set if ok for signed comparisons
  *
- * In particular, statically non-negative signed integer
- * expressions are ok for both.
+ * In particular, statically non-negative signed integer expressions
+ * are ok for both.
  *
- * NOTE! Unsigned types smaller than 'int' are implicitly
- * converted to 'int' in expressions, and are accepted for
- * signed conversions for now. This is debatable.
+ * NOTE! Unsigned types smaller than 'int' are implicitly converted to 'int'
+ * in expressions, and are accepted for signed conversions for now.
+ * This is debatable.
  *
- * Note that 'x' is the original expression, and 'ux' is
- * the unique variable that contains the value.
+ * Note that 'x' is the original expression, and 'ux' is the unique variable
+ * that contains the value.
  *
- * We use 'ux' for pure type checking, and 'x' for when
- * we need to look at the value (but without evaluating
- * it for side effects! Careful to only ever evaluate it
- * with sizeof() or __builtin_constant_p() etc).
+ * We use 'ux' for pure type checking, and 'x' for when we need to look at the
+ * value (but without evaluating it for side effects!
+ * Careful to only ever evaluate it with sizeof() or __builtin_constant_p() etc).
  *
- * Pointers end up being checked by the normal C type
- * rules at the actual comparison, and these expressions
- * only need to be careful to not cause warnings for
- * pointer use.
+ * Pointers end up being checked by the normal C type rules at the actual
+ * comparison, and these expressions only need to be careful to not cause
+ * warnings for pointer use.
  */
-#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux))
-#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4))
-#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \
-	__signed_type_use(x,ux):__unsigned_type_use(x,ux))
+#define __sign_use(ux) (is_signed_type(typeof(ux)) ? \
+	(2 + __is_nonneg(ux)) : (1 + 2 * (sizeof(ux) < 4)))
 
 /*
- * To avoid warnings about casting pointers to integers
- * of different sizes, we need that special sign type.
+ * Check whether a signed value is always non-negative.
  *
- * On 64-bit we can just always use 'long', since any
- * integer or pointer type can just be cast to that.
+ * A cast is needed to avoid any warnings from values that aren't signed
+ * integer types (in which case the result doesn't matter).
  *
- * This does not work for 128-bit signed integers since
- * the cast would truncate them, but we do not use s128
- * types in the kernel (we do use 'u128', but they will
- * be handled by the !is_signed_type() case).
+ * On 64-bit any integer or pointer type can safely be cast to 'long long'.
+ * But on 32-bit we need to avoid warnings about casting pointers to integers
+ * of different sizes without truncating 64-bit values so 'long' or 'long long'
+ * must be used depending on the size of the value.
  *
- * NOTE! The cast is there only to avoid any warnings
- * from when values that aren't signed integer types.
+ * This does not work for 128-bit signed integers since the cast would truncate
+ * them, but we do not use s128 types in the kernel (we do use 'u128',
+ * but they are handled by the !is_signed_type() case).
  */
-#ifdef CONFIG_64BIT
-  #define __signed_type(ux) long
+#if __SIZEOF_POINTER__ == __SIZEOF_LONG_LONG__
+#define __is_nonneg(ux) statically_true((long long)(ux) >= 0)
 #else
-  #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L))
+#define __is_nonneg(ux) statically_true( \
+	(typeof(__builtin_choose_expr(sizeof(ux) > 4, 1LL, 1L)))(ux) >= 0)
 #endif
-#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0)
 
-#define __types_ok(x,y,ux,uy) \
-	(__sign_use(x,ux) & __sign_use(y,uy))
+#define __types_ok(ux, uy) \
+	(__sign_use(ux) & __sign_use(uy))
 
-#define __types_ok3(x,y,z,ux,uy,uz) \
-	(__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz))
+#define __types_ok3(ux, uy, uz) \
+	(__sign_use(ux) & __sign_use(uy) & __sign_use(uz))
 
 #define __cmp_op_min <
 #define __cmp_op_max >
@@ -97,30 +90,13 @@
 
 #define __careful_cmp_once(op, x, y, ux, uy) ({		\
 	__auto_type ux = (x); __auto_type uy = (y);	\
-	BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy),	\
+	BUILD_BUG_ON_MSG(!__types_ok(ux, uy),		\
 		#op"("#x", "#y") signedness error");	\
 	__cmp(op, ux, uy); })
 
 #define __careful_cmp(op, x, y) \
 	__careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
-#define __clamp(val, lo, hi)	\
-	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
-
-#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({				\
-	__auto_type uval = (val);						\
-	__auto_type ulo = (lo);							\
-	__auto_type uhi = (hi);							\
-	static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), 	\
-			(lo) <= (hi), true),					\
-		"clamp() low limit " #lo " greater than high limit " #hi);	\
-	BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi),			\
-		"clamp("#val", "#lo", "#hi") signedness error");		\
-	__clamp(uval, ulo, uhi); })
-
-#define __careful_clamp(val, lo, hi) \
-	__clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_))
-
 /**
  * min - return minimum of two values of the same or compatible types
  * @x: first value
@@ -154,7 +130,7 @@
 
 #define __careful_op3(op, x, y, z, ux, uy, uz) ({			\
 	__auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\
-	BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz),			\
+	BUILD_BUG_ON_MSG(!__types_ok3(ux, uy, uz),			\
 		#op"3("#x", "#y", "#z") signedness error");		\
 	__cmp(op, ux, __cmp(op, uy, uz)); })
 
@@ -177,6 +153,22 @@
 	__careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_))
 
 /**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define min_t(type, x, y) __cmp_once(min, type, x, y)
+
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define max_t(type, x, y) __cmp_once(max, type, x, y)
+
+/**
  * min_not_zero - return the minimum that is _not_ zero, unless both are zero
  * @x: value1
  * @y: value2
@@ -186,39 +178,57 @@
 	typeof(y) __y = (y);			\
 	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
 
+#define __clamp(val, lo, hi)	\
+	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
+
+#define __clamp_once(type, val, lo, hi, uval, ulo, uhi) ({			\
+	type uval = (val);							\
+	type ulo = (lo);							\
+	type uhi = (hi);							\
+	BUILD_BUG_ON_MSG(statically_true(ulo > uhi),				\
+		"clamp() low limit " #lo " greater than high limit " #hi);	\
+	BUILD_BUG_ON_MSG(!__types_ok3(uval, ulo, uhi),				\
+		"clamp("#val", "#lo", "#hi") signedness error");		\
+	__clamp(uval, ulo, uhi); })
+
+#define __careful_clamp(type, val, lo, hi) \
+	__clamp_once(type, val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_))
+
 /**
- * clamp - return a value clamped to a given range with strict typechecking
+ * clamp - return a value clamped to a given range with typechecking
  * @val: current value
  * @lo: lowest allowable value
  * @hi: highest allowable value
  *
- * This macro does strict typechecking of @lo/@hi to make sure they are of the
- * same type as @val.  See the unnecessary pointer comparisons.
- */
-#define clamp(val, lo, hi) __careful_clamp(val, lo, hi)
-
-/*
- * ..and if you can't take the strict
- * types, you can specify one yourself.
- *
- * Or not use min/max/clamp at all, of course.
+ * This macro checks @val/@lo/@hi to make sure they have compatible
+ * signedness.
  */
+#define clamp(val, lo, hi) __careful_clamp(__auto_type, val, lo, hi)
 
 /**
- * min_t - return minimum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
+ * clamp_t - return a value clamped to a given range using a given type
+ * @type: the type of variable to use
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of type
+ * @type to make all the comparisons.
  */
-#define min_t(type, x, y) __cmp_once(min, type, x, y)
+#define clamp_t(type, val, lo, hi) __careful_clamp(type, val, lo, hi)
 
 /**
- * max_t - return maximum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
+ * clamp_val - return a value clamped to a given range using val's type
+ * @val: current value
+ * @lo: minimum allowable value
+ * @hi: maximum allowable value
+ *
+ * This macro does no typechecking and uses temporary variables of whatever
+ * type the input argument @val is.  This is useful when @val is an unsigned
+ * type and @lo and @hi are literals that will otherwise be assigned a signed
+ * integer type.
  */
-#define max_t(type, x, y) __cmp_once(max, type, x, y)
+#define clamp_val(val, lo, hi) __careful_clamp(typeof(val), val, lo, hi)
 
 /*
  * Do not check the array parameter using __must_be_array().
@@ -263,31 +273,6 @@
  */
 #define max_array(array, len) __minmax_array(max, array, len)
 
-/**
- * clamp_t - return a value clamped to a given range using a given type
- * @type: the type of variable to use
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of type
- * @type to make all the comparisons.
- */
-#define clamp_t(type, val, lo, hi) __careful_clamp((type)(val), (type)(lo), (type)(hi))
-
-/**
- * clamp_val - return a value clamped to a given range using val's type
- * @val: current value
- * @lo: minimum allowable value
- * @hi: maximum allowable value
- *
- * This macro does no typechecking and uses temporary variables of whatever
- * type the input argument @val is.  This is useful when @val is an unsigned
- * type and @lo and @hi are literals that will otherwise be assigned a signed
- * integer type.
- */
-#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
-
 static inline bool in_range64(u64 val, u64 start, u64 len)
 {
 	return (val - start) < len;
@@ -326,9 +311,9 @@ static inline bool in_range32(u32 val, u32 start, u32 len)
  * Use these carefully: no type checking, and uses the arguments
  * multiple times. Use for obvious constants only.
  */
-#define MIN(a,b) __cmp(min,a,b)
-#define MAX(a,b) __cmp(max,a,b)
-#define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b))
-#define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b))
+#define MIN(a, b) __cmp(min, a, b)
+#define MAX(a, b) __cmp(max, a, b)
+#define MIN_T(type, a, b) __cmp(min, (type)(a), (type)(b))
+#define MAX_T(type, a, b) __cmp(max, (type)(a), (type)(b))
 
 #endif	/* _LINUX_MINMAX_H */
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index c0fea6ca5076..69e110c2b86a 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -76,7 +76,7 @@
 struct device;
 struct attribute_group;
 
-struct miscdevice  {
+struct miscdevice {
 	int minor;
 	const char *name;
 	const struct file_operations *fops;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 21428d897d76..7b1068ddcbb7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2320,6 +2320,7 @@ extern void pagefault_out_of_memory(void);
 struct zap_details {
 	struct folio *single_folio;	/* Locked folio to be unmapped */
 	bool even_cows;			/* Zap COWed private pages too? */
+	bool reclaim_pt;		/* Need reclaim page tables? */
 	zap_flags_t zap_flags;		/* Extra flags for zapping */
 };
 
@@ -2991,18 +2992,15 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
 static inline void ptlock_free(struct ptdesc *ptdesc) {}
 #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 
-static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc)
+static inline void __pagetable_ctor(struct ptdesc *ptdesc)
 {
 	struct folio *folio = ptdesc_folio(ptdesc);
 
-	if (!ptlock_init(ptdesc))
-		return false;
 	__folio_set_pgtable(folio);
 	lruvec_stat_add_folio(folio, NR_PAGETABLE);
-	return true;
 }
 
-static inline void pagetable_pte_dtor(struct ptdesc *ptdesc)
+static inline void pagetable_dtor(struct ptdesc *ptdesc)
 {
 	struct folio *folio = ptdesc_folio(ptdesc);
 
@@ -3011,6 +3009,20 @@ static inline void pagetable_pte_dtor(struct ptdesc *ptdesc)
 	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
 }
 
+static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
+{
+	pagetable_dtor(ptdesc);
+	pagetable_free(ptdesc);
+}
+
+static inline bool pagetable_pte_ctor(struct ptdesc *ptdesc)
+{
+	if (!ptlock_init(ptdesc))
+		return false;
+	__pagetable_ctor(ptdesc);
+	return true;
+}
+
 pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
 static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr,
 			pmd_t *pmdvalp)
@@ -3087,14 +3099,6 @@ static inline bool pmd_ptlock_init(struct ptdesc *ptdesc)
 	return ptlock_init(ptdesc);
 }
 
-static inline void pmd_ptlock_free(struct ptdesc *ptdesc)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON_PAGE(ptdesc->pmd_huge_pte, ptdesc_page(ptdesc));
-#endif
-	ptlock_free(ptdesc);
-}
-
 #define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte)
 
 #else
@@ -3105,7 +3109,6 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 }
 
 static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; }
-static inline void pmd_ptlock_free(struct ptdesc *ptdesc) {}
 
 #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
@@ -3120,25 +3123,13 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 
 static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc)
 {
-	struct folio *folio = ptdesc_folio(ptdesc);
-
 	if (!pmd_ptlock_init(ptdesc))
 		return false;
-	__folio_set_pgtable(folio);
 	ptdesc_pmd_pts_init(ptdesc);
-	lruvec_stat_add_folio(folio, NR_PAGETABLE);
+	__pagetable_ctor(ptdesc);
 	return true;
 }
 
-static inline void pagetable_pmd_dtor(struct ptdesc *ptdesc)
-{
-	struct folio *folio = ptdesc_folio(ptdesc);
-
-	pmd_ptlock_free(ptdesc);
-	__folio_clear_pgtable(folio);
-	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
-}
-
 /*
  * No scalability reason to split PUD locks yet, but follow the same pattern
  * as the PMD locks to make it easier if we decide to.  The VM should not be
@@ -3160,18 +3151,17 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
 
 static inline void pagetable_pud_ctor(struct ptdesc *ptdesc)
 {
-	struct folio *folio = ptdesc_folio(ptdesc);
-
-	__folio_set_pgtable(folio);
-	lruvec_stat_add_folio(folio, NR_PAGETABLE);
+	__pagetable_ctor(ptdesc);
 }
 
-static inline void pagetable_pud_dtor(struct ptdesc *ptdesc)
+static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc)
 {
-	struct folio *folio = ptdesc_folio(ptdesc);
+	__pagetable_ctor(ptdesc);
+}
 
-	__folio_clear_pgtable(folio);
-	lruvec_stat_sub_folio(folio, NR_PAGETABLE);
+static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc)
+{
+	__pagetable_ctor(ptdesc);
 }
 
 extern void __init pagecache_init(void);
@@ -3324,6 +3314,8 @@ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admi
 extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
 extern void exit_mmap(struct mm_struct *);
 int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift);
+bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma,
+				 unsigned long addr, bool write);
 
 static inline int check_data_rlimit(unsigned long rlim,
 				    unsigned long new,
@@ -3371,9 +3363,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
 }
 
-extern unsigned long mmap_region(struct file *file, unsigned long addr,
-	unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
-	struct list_head *uf);
 extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
 	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
@@ -3438,9 +3427,6 @@ extern unsigned long stack_guard_gap;
 int expand_stack_locked(struct vm_area_struct *vma, unsigned long address);
 struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr);
 
-/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */
-int expand_downwards(struct vm_area_struct *vma, unsigned long address);
-
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
 extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
@@ -4097,67 +4083,6 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 
 extern int sysctl_nr_trim_pages;
 
-#ifdef CONFIG_PRINTK
-void mem_dump_obj(void *object);
-#else
-static inline void mem_dump_obj(void *object) {}
-#endif
-
-static inline bool is_write_sealed(int seals)
-{
-	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
-}
-
-/**
- * is_readonly_sealed - Checks whether write-sealed but mapped read-only,
- *                      in which case writes should be disallowing moving
- *                      forwards.
- * @seals: the seals to check
- * @vm_flags: the VMA flags to check
- *
- * Returns whether readonly sealed, in which case writess should be disallowed
- * going forward.
- */
-static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags)
-{
-	/*
-	 * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as
-	 * MAP_SHARED and read-only, take care to not allow mprotect to
-	 * revert protections on such mappings. Do this only for shared
-	 * mappings. For private mappings, don't need to mask
-	 * VM_MAYWRITE as we still want them to be COW-writable.
-	 */
-	if (is_write_sealed(seals) &&
-	    ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED))
-		return true;
-
-	return false;
-}
-
-/**
- * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and
- *                    handle them.
- * @seals: the seals to check
- * @vma: the vma to operate on
- *
- * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper
- * check/handling on the vma flags.  Return 0 if check pass, or <0 for errors.
- */
-static inline int seal_check_write(int seals, struct vm_area_struct *vma)
-{
-	if (!is_write_sealed(seals))
-		return 0;
-
-	/*
-	 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
-	 * write seals are active.
-	 */
-	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
-		return -EPERM;
-
-	return 0;
-}
-
 #ifdef CONFIG_ANON_VMA_NAME
 int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 			  unsigned long len_in,
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 1b6a917fffa4..f9157a0c42a5 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -133,31 +133,25 @@ static inline int lru_hist_from_seq(unsigned long seq)
 	return seq % NR_HIST_GENS;
 }
 
-static inline int lru_tier_from_refs(int refs)
+static inline int lru_tier_from_refs(int refs, bool workingset)
 {
 	VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH));
 
-	/* see the comment in folio_lru_refs() */
-	return order_base_2(refs + 1);
+	/* see the comment on MAX_NR_TIERS */
+	return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs);
 }
 
 static inline int folio_lru_refs(struct folio *folio)
 {
 	unsigned long flags = READ_ONCE(folio->flags);
-	bool workingset = flags & BIT(PG_workingset);
 
+	if (!(flags & BIT(PG_referenced)))
+		return 0;
 	/*
-	 * Return the number of accesses beyond PG_referenced, i.e., N-1 if the
-	 * total number of accesses is N>1, since N=0,1 both map to the first
-	 * tier. lru_tier_from_refs() will account for this off-by-one. Also see
-	 * the comment on MAX_NR_TIERS.
+	 * Return the total number of accesses including PG_referenced. Also see
+	 * the comment on LRU_REFS_FLAGS.
 	 */
-	return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset;
-}
-
-static inline void folio_clear_lru_refs(struct folio *folio)
-{
-	set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0);
+	return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1;
 }
 
 static inline int folio_lru_gen(struct folio *folio)
@@ -223,11 +217,43 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli
 	VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
 }
 
+static inline unsigned long lru_gen_folio_seq(struct lruvec *lruvec, struct folio *folio,
+					      bool reclaiming)
+{
+	int gen;
+	int type = folio_is_file_lru(folio);
+	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+
+	/*
+	 * +-----------------------------------+-----------------------------------+
+	 * | Accessed through page tables and  | Accessed through file descriptors |
+	 * | promoted by folio_update_gen()    | and protected by folio_inc_gen()  |
+	 * +-----------------------------------+-----------------------------------+
+	 * | PG_active (set while isolated)    |                                   |
+	 * +-----------------+-----------------+-----------------+-----------------+
+	 * |  PG_workingset  |  PG_referenced  |  PG_workingset  |  LRU_REFS_FLAGS |
+	 * +-----------------------------------+-----------------------------------+
+	 * |<---------- MIN_NR_GENS ---------->|                                   |
+	 * |<---------------------------- MAX_NR_GENS ---------------------------->|
+	 */
+	if (folio_test_active(folio))
+		gen = MIN_NR_GENS - folio_test_workingset(folio);
+	else if (reclaiming)
+		gen = MAX_NR_GENS;
+	else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) ||
+		 (folio_test_reclaim(folio) &&
+		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
+		gen = MIN_NR_GENS;
+	else
+		gen = MAX_NR_GENS - folio_test_workingset(folio);
+
+	return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type]));
+}
+
 static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
 {
 	unsigned long seq;
 	unsigned long flags;
-	unsigned long mask;
 	int gen = folio_lru_gen(folio);
 	int type = folio_is_file_lru(folio);
 	int zone = folio_zonenum(folio);
@@ -237,40 +263,12 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
-	/*
-	 * There are four common cases for this page:
-	 * 1. If it's hot, i.e., freshly faulted in, add it to the youngest
-	 *    generation, and it's protected over the rest below.
-	 * 2. If it can't be evicted immediately, i.e., a dirty page pending
-	 *    writeback, add it to the second youngest generation.
-	 * 3. If it should be evicted first, e.g., cold and clean from
-	 *    folio_rotate_reclaimable(), add it to the oldest generation.
-	 * 4. Everything else falls between 2 & 3 above and is added to the
-	 *    second oldest generation if it's considered inactive, or the
-	 *    oldest generation otherwise. See lru_gen_is_active().
-	 */
-	if (folio_test_active(folio))
-		seq = lrugen->max_seq;
-	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
-		 (folio_test_reclaim(folio) &&
-		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
-		seq = lrugen->max_seq - 1;
-	else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq)
-		seq = lrugen->min_seq[type];
-	else
-		seq = lrugen->min_seq[type] + 1;
 
+	seq = lru_gen_folio_seq(lruvec, folio, reclaiming);
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
 	/* see the comment on MIN_NR_GENS about PG_active */
-	mask = LRU_GEN_MASK;
-	/*
-	 * Don't clear PG_workingset here because it can affect PSI accounting
-	 * if the activation is due to workingset refault.
-	 */
-	if (folio_test_active(folio))
-		mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active);
-	set_mask_bits(&folio->flags, mask, flags);
+	set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags);
 
 	lru_gen_update_size(lruvec, folio, -1, gen);
 	/* for folio_rotate_reclaimable() */
@@ -564,9 +562,9 @@ static inline pte_marker copy_pte_marker(
  * Must be called with pgtable lock held so that no thread will see the none
  * pte, and if they see it, they'll fault and serialize at the pgtable lock.
  *
- * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled.
+ * Returns true if an uffd-wp pte was installed, false otherwise.
  */
-static inline void
+static inline bool
 pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 			      pte_t *pte, pte_t pteval)
 {
@@ -583,7 +581,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 	 * with a swap pte.  There's no way of leaking the bit.
 	 */
 	if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
-		return;
+		return false;
 
 	/* A uffd-wp wr-protected normal pte */
 	if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
@@ -596,10 +594,13 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 	if (unlikely(pte_swp_uffd_wp_any(pteval)))
 		arm_uffd_pte = true;
 
-	if (unlikely(arm_uffd_pte))
+	if (unlikely(arm_uffd_pte)) {
 		set_pte_at(vma->vm_mm, addr, pte,
 			   make_pte_marker(PTE_MARKER_UFFD_WP));
+		return true;
+	}
 #endif
+	return false;
 }
 
 static inline bool vma_has_recency(struct vm_area_struct *vma)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 825c04b56403..6b27db7f9496 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -438,7 +438,9 @@ FOLIO_MATCH(compound_head, _head_2a);
  * struct ptdesc -    Memory descriptor for page tables.
  * @__page_flags:     Same as page flags. Powerpc only.
  * @pt_rcu_head:      For freeing page table pages.
- * @pt_list:          List of used page tables. Used for s390 and x86.
+ * @pt_list:          List of used page tables. Used for s390 gmap shadow pages
+ *                    (which are not linked into the user page tables) and x86
+ *                    pgds.
  * @_pt_pad_1:        Padding that aliases with page's compound head.
  * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
  * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
@@ -1404,6 +1406,7 @@ enum tlb_flush_reason {
 	TLB_LOCAL_SHOOTDOWN,
 	TLB_LOCAL_MM_SHOOTDOWN,
 	TLB_REMOTE_SEND_IPI,
+	TLB_REMOTE_WRONG_CPU,
 	NR_TLB_FLUSH_REASONS,
 };
 
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index d7cb1e5ecbda..a0a3894900ed 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -9,10 +9,12 @@ struct page;
 struct vm_area_struct;
 struct mm_struct;
 struct vma_iterator;
+struct vma_merge_struct;
 
 void dump_page(const struct page *page, const char *reason);
 void dump_vma(const struct vm_area_struct *vma);
 void dump_mm(const struct mm_struct *mm);
+void dump_vmg(const struct vma_merge_struct *vmg, const char *reason);
 void vma_iter_dump_tree(const struct vma_iterator *vmi);
 
 #ifdef CONFIG_DEBUG_VM
@@ -87,6 +89,15 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 	}								\
 	unlikely(__ret_warn_once);					\
 })
+#define VM_WARN_ON_VMG(cond, vmg)		({			\
+	int __ret_warn = !!(cond);					\
+									\
+	if (unlikely(__ret_warn)) {					\
+		dump_vmg(vmg, "VM_WARN_ON_VMG(" __stringify(cond)")");	\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn);						\
+})
 
 #define VM_WARN_ON(cond) (void)WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
@@ -104,9 +115,10 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 #define VM_WARN_ON_FOLIO(cond, folio)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE_FOLIO(cond, folio)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE_MM(cond, mm)  BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_VMG(cond, vmg)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
-#endif
+#endif /* CONFIG_DEBUG_VM */
 
 #ifdef CONFIG_DEBUG_VM_IRQSOFF
 #define VM_WARN_ON_IRQS_ENABLED() WARN_ON_ONCE(!irqs_disabled())
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b36124145a16..9540b41894da 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -332,66 +332,88 @@ enum lruvec_flags {
 #endif /* !__GENERATING_BOUNDS_H */
 
 /*
- * Evictable pages are divided into multiple generations. The youngest and the
+ * Evictable folios are divided into multiple generations. The youngest and the
  * oldest generation numbers, max_seq and min_seq, are monotonically increasing.
  * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An
  * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the
  * corresponding generation. The gen counter in folio->flags stores gen+1 while
- * a page is on one of lrugen->folios[]. Otherwise it stores 0.
+ * a folio is on one of lrugen->folios[]. Otherwise it stores 0.
  *
- * A page is added to the youngest generation on faulting. The aging needs to
- * check the accessed bit at least twice before handing this page over to the
- * eviction. The first check takes care of the accessed bit set on the initial
- * fault; the second check makes sure this page hasn't been used since then.
- * This process, AKA second chance, requires a minimum of two generations,
- * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive
- * LRU, e.g., /proc/vmstat, these two generations are considered active; the
- * rest of generations, if they exist, are considered inactive. See
- * lru_gen_is_active().
+ * After a folio is faulted in, the aging needs to check the accessed bit at
+ * least twice before handing this folio over to the eviction. The first check
+ * clears the accessed bit from the initial fault; the second check makes sure
+ * this folio hasn't been used since then. This process, AKA second chance,
+ * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI
+ * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two
+ * generations are considered active; the rest of generations, if they exist,
+ * are considered inactive. See lru_gen_is_active().
  *
- * PG_active is always cleared while a page is on one of lrugen->folios[] so
- * that the aging needs not to worry about it. And it's set again when a page
- * considered active is isolated for non-reclaiming purposes, e.g., migration.
- * See lru_gen_add_folio() and lru_gen_del_folio().
+ * PG_active is always cleared while a folio is on one of lrugen->folios[] so
+ * that the sliding window needs not to worry about it. And it's set again when
+ * a folio considered active is isolated for non-reclaiming purposes, e.g.,
+ * migration. See lru_gen_add_folio() and lru_gen_del_folio().
  *
  * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the
  * number of categories of the active/inactive LRU when keeping track of
  * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits
- * in folio->flags.
+ * in folio->flags, masked by LRU_GEN_MASK.
  */
 #define MIN_NR_GENS		2U
 #define MAX_NR_GENS		4U
 
 /*
- * Each generation is divided into multiple tiers. A page accessed N times
- * through file descriptors is in tier order_base_2(N). A page in the first tier
- * (N=0,1) is marked by PG_referenced unless it was faulted in through page
- * tables or read ahead. A page in any other tier (N>1) is marked by
- * PG_referenced and PG_workingset. This implies a minimum of two tiers is
- * supported without using additional bits in folio->flags.
+ * Each generation is divided into multiple tiers. A folio accessed N times
+ * through file descriptors is in tier order_base_2(N). A folio in the first
+ * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page
+ * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by
+ * PG_workingset. A folio in any other tier (1<N<5) between the first and last
+ * is marked by additional bits of LRU_REFS_WIDTH in folio->flags.
  *
  * In contrast to moving across generations which requires the LRU lock, moving
  * across tiers only involves atomic operations on folio->flags and therefore
  * has a negligible cost in the buffered access path. In the eviction path,
- * comparisons of refaulted/(evicted+protected) from the first tier and the
- * rest infer whether pages accessed multiple times through file descriptors
- * are statistically hot and thus worth protecting.
+ * comparisons of refaulted/(evicted+protected) from the first tier and the rest
+ * infer whether folios accessed multiple times through file descriptors are
+ * statistically hot and thus worth protecting.
  *
  * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the
  * number of categories of the active/inactive LRU when keeping track of
  * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in
- * folio->flags.
+ * folio->flags, masked by LRU_REFS_MASK.
  */
 #define MAX_NR_TIERS		4U
 
 #ifndef __GENERATING_BOUNDS_H
 
-struct lruvec;
-struct page_vma_mapped_walk;
-
 #define LRU_GEN_MASK		((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
 #define LRU_REFS_MASK		((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
 
+/*
+ * For folios accessed multiple times through file descriptors,
+ * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags
+ * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its
+ * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily
+ * promoted into the second oldest generation in the eviction path. And when
+ * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that
+ * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is
+ * only valid when PG_referenced is set.
+ *
+ * For folios accessed multiple times through page tables, folio_update_gen()
+ * from a page table walk or lru_gen_set_refs() from a rmap walk sets
+ * PG_referenced after the accessed bit is cleared for the first time.
+ * Thereafter, those two paths set PG_workingset and promote folios to the
+ * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears
+ * PG_referenced. Note that for this case, LRU_REFS_MASK is not used.
+ *
+ * For both cases above, after PG_workingset is set on a folio, it remains until
+ * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It
+ * can be set again if lru_gen_test_recent() returns true upon a refault.
+ */
+#define LRU_REFS_FLAGS		(LRU_REFS_MASK | BIT(PG_referenced))
+
+struct lruvec;
+struct page_vma_mapped_walk;
+
 #ifdef CONFIG_LRU_GEN
 
 enum {
@@ -406,8 +428,6 @@ enum {
 	NR_LRU_GEN_CAPS
 };
 
-#define LRU_REFS_FLAGS		(BIT(PG_referenced) | BIT(PG_workingset))
-
 #define MIN_LRU_BATCH		BITS_PER_LONG
 #define MAX_LRU_BATCH		(MIN_LRU_BATCH * 64)
 
@@ -421,12 +441,11 @@ enum {
 /*
  * The youngest generation number is stored in max_seq for both anon and file
  * types as they are aged on an equal footing. The oldest generation numbers are
- * stored in min_seq[] separately for anon and file types as clean file pages
- * can be evicted regardless of swap constraints.
- *
- * Normally anon and file min_seq are in sync. But if swapping is constrained,
- * e.g., out of swap space, file min_seq is allowed to advance and leave anon
- * min_seq behind.
+ * stored in min_seq[] separately for anon and file types so that they can be
+ * incremented independently. Ideally min_seq[] are kept in sync when both anon
+ * and file types are evictable. However, to adapt to situations like extreme
+ * swappiness, they are allowed to be out of sync by at most
+ * MAX_NR_GENS-MIN_NR_GENS-1.
  *
  * The number of pages in each generation is eventually consistent and therefore
  * can be transiently negative when reset_batch_size() is pending.
@@ -446,8 +465,8 @@ struct lru_gen_folio {
 	unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
 	/* the exponential moving average of evicted+protected */
 	unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
-	/* the first tier doesn't need protection, hence the minus one */
-	unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1];
+	/* can only be modified under the LRU lock */
+	unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	/* can be modified without holding the LRU lock */
 	atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
@@ -498,7 +517,7 @@ struct lru_gen_mm_walk {
 	int mm_stats[NR_MM_STATS];
 	/* total batched items */
 	int batched;
-	bool can_swap;
+	int swappiness;
 	bool force_scan;
 };
 
diff --git a/include/linux/module.h b/include/linux/module.h
index b3a643435357..30e5b19bafa9 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -52,9 +52,9 @@ struct module_kobject {
 
 struct module_attribute {
 	struct attribute attr;
-	ssize_t (*show)(struct module_attribute *, struct module_kobject *,
+	ssize_t (*show)(const struct module_attribute *, struct module_kobject *,
 			char *);
-	ssize_t (*store)(struct module_attribute *, struct module_kobject *,
+	ssize_t (*store)(const struct module_attribute *, struct module_kobject *,
 			 const char *, size_t count);
 	void (*setup)(struct module *, const char *);
 	int (*test)(struct module *);
@@ -67,10 +67,10 @@ struct module_version_attribute {
 	const char *version;
 };
 
-extern ssize_t __modver_version_show(struct module_attribute *,
+extern ssize_t __modver_version_show(const struct module_attribute *,
 				     struct module_kobject *, char *);
 
-extern struct module_attribute module_uevent;
+extern const struct module_attribute module_uevent;
 
 /* These are either module local, or the kernel's dummy ones. */
 extern int init_module(void);
@@ -275,7 +275,7 @@ extern typeof(name) __mod_device_table__##type##__##name		\
 #else
 #define MODULE_VERSION(_version)					\
 	MODULE_INFO(version, _version);					\
-	static struct module_version_attribute __modver_attr		\
+	static const struct module_version_attribute __modver_attr	\
 		__used __section("__modver")				\
 		__aligned(__alignof__(struct module_version_attribute)) \
 		= {							\
@@ -306,7 +306,10 @@ extern int modules_disabled; /* for sysctl */
 /* Get/put a kernel symbol (calls must be symmetric) */
 void *__symbol_get(const char *symbol);
 void *__symbol_get_gpl(const char *symbol);
-#define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x))))
+#define symbol_get(x)	({ \
+	static const char __notrim[] \
+		__used __section(".no_trim_symbol") = __stringify(x); \
+	(typeof(&x))(__symbol_get(__stringify(x))); })
 
 /* modules using other modules: kdb wants to see this. */
 struct module_use {
@@ -430,7 +433,7 @@ struct module {
 
 	/* Exported symbols */
 	const struct kernel_symbol *syms;
-	const s32 *crcs;
+	const u32 *crcs;
 	unsigned int num_syms;
 
 #ifdef CONFIG_ARCH_USES_CFI_TRAPS
@@ -448,7 +451,7 @@ struct module {
 	/* GPL-only exported symbols. */
 	unsigned int num_gpl_syms;
 	const struct kernel_symbol *gpl_syms;
-	const s32 *gpl_crcs;
+	const u32 *gpl_crcs;
 	bool using_gplonly_symbols;
 
 #ifdef CONFIG_MODULE_SIG
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8da4c61f97b9..03bb584c62cf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1085,8 +1085,8 @@ struct netdev_net_notifier {
  *
  * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
  *	Old-style ioctl entry point. This is used internally by the
- *	appletalk and ieee802154 subsystems but is no longer called by
- *	the device ioctl handler.
+ *	ieee802154 subsystem but is no longer called by the device
+ *	ioctl handler.
  *
  * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd);
  *	Used by the bonding driver for its device specific ioctls:
@@ -2904,9 +2904,9 @@ struct pcpu_sw_netstats {
 struct pcpu_dstats {
 	u64_stats_t		rx_packets;
 	u64_stats_t		rx_bytes;
-	u64_stats_t		rx_drops;
 	u64_stats_t		tx_packets;
 	u64_stats_t		tx_bytes;
+	u64_stats_t		rx_drops;
 	u64_stats_t		tx_drops;
 	struct u64_stats_sync	syncp;
 } __aligned(8 * sizeof(u64));
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 8d7430d9f218..71fbebfa43c7 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -17,6 +17,7 @@
 #include <linux/uidgid.h>
 #include <uapi/linux/nfs4.h>
 #include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/xdrgen/nfs4_1.h>
 
 enum nfs4_acl_whotype {
 	NFS4_ACL_WHO_NAMED = 0,
@@ -365,7 +366,7 @@ enum limit_by4 {
 	NFS4_LIMIT_BLOCKS = 2
 };
 
-enum open_delegation_type4 {
+enum nfs4_open_delegation_type4 {
 	NFS4_OPEN_DELEGATE_NONE = 0,
 	NFS4_OPEN_DELEGATE_READ = 1,
 	NFS4_OPEN_DELEGATE_WRITE = 2,
@@ -512,12 +513,6 @@ enum {
 	FATTR4_XATTR_SUPPORT		= 82,
 };
 
-enum {
-	FATTR4_TIME_DELEG_ACCESS	= 84,
-	FATTR4_TIME_DELEG_MODIFY	= 85,
-	FATTR4_OPEN_ARGUMENTS		= 86,
-};
-
 /*
  * The following internal definitions enable processing the above
  * attribute bits within 32-bit word boundaries.
diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h
index 5fc02df88252..a541c3a02887 100644
--- a/include/linux/nfs_common.h
+++ b/include/linux/nfs_common.h
@@ -9,9 +9,10 @@
 #include <uapi/linux/nfs.h>
 
 /* Mapping from NFS error code to "errno" error code. */
-#define errno_NFSERR_IO EIO
 
 int nfs_stat_to_errno(enum nfs_stat status);
 int nfs4_stat_to_errno(int stat);
 
+__u32 nfs_localio_errno_to_nfs4_stat(int errno);
+
 #endif /* _LINUX_NFS_COMMON_H */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 039898d70954..67ae2c3f41d2 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -77,6 +77,23 @@ struct nfs_lock_context {
 	struct rcu_head	rcu_head;
 };
 
+struct nfs_file_localio {
+	struct nfsd_file __rcu *ro_file;
+	struct nfsd_file __rcu *rw_file;
+	struct list_head list;
+	void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */
+};
+
+static inline void nfs_localio_file_init(struct nfs_file_localio *nfl)
+{
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	nfl->ro_file = NULL;
+	nfl->rw_file = NULL;
+	INIT_LIST_HEAD(&nfl->list);
+	nfl->nfs_uuid = NULL;
+#endif
+}
+
 struct nfs4_state;
 struct nfs_open_context {
 	struct nfs_lock_context lock_context;
@@ -87,15 +104,16 @@ struct nfs_open_context {
 	struct nfs4_state *state;
 	fmode_t mode;
 
+	int error;
 	unsigned long flags;
 #define NFS_CONTEXT_BAD			(2)
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
-	int error;
 
-	struct list_head list;
 	struct nfs4_threshold	*mdsthreshold;
+	struct list_head list;
 	struct rcu_head	rcu_head;
+	struct nfs_file_localio nfl;
 };
 
 struct nfs_open_dir_context {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b804346a9741..f00bfcee7120 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -50,7 +50,6 @@ struct nfs_client {
 #define NFS_CS_DS		7		/* - Server is a DS */
 #define NFS_CS_REUSEPORT	8		/* - reuse src port on reconnect */
 #define NFS_CS_PNFS		9		/* - Server used for pnfs */
-#define NFS_CS_LOCAL_IO		10		/* - client is local */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
@@ -132,7 +131,7 @@ struct nfs_client {
 	struct timespec64	cl_nfssvc_boot;
 	seqlock_t		cl_boot_lock;
 	nfs_uuid_t		cl_uuid;
-	spinlock_t		cl_localio_lock;
+	struct work_struct	cl_local_probe_work;
 #endif /* CONFIG_NFS_LOCALIO */
 };
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 559273a0f16d..9155a6ffc370 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1315,11 +1315,6 @@ struct nfs4_fsid_present_res {
 
 #endif /* CONFIG_NFS_V4 */
 
-struct nfstime4 {
-	u64	seconds;
-	u32	nseconds;
-};
-
 #ifdef CONFIG_NFS_V4_1
 
 struct pnfs_commit_bucket {
@@ -1637,6 +1632,7 @@ enum {
 	NFS_IOHDR_RESEND_PNFS,
 	NFS_IOHDR_RESEND_MDS,
 	NFS_IOHDR_UNSTABLE_WRITES,
+	NFS_IOHDR_ODIRECT,
 };
 
 struct nfs_io_completion;
@@ -1785,7 +1781,7 @@ struct nfs_rpc_ops {
 			    struct nfs_fattr *, struct inode *);
 	int	(*setattr) (struct dentry *, struct nfs_fattr *,
 			    struct iattr *);
-	int	(*lookup)  (struct inode *, struct dentry *,
+	int	(*lookup)  (struct inode *, struct dentry *, const struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *);
 	int	(*lookupp) (struct inode *, struct nfs_fh *,
 			    struct nfs_fattr *);
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index 9202f4b24343..9aa8a43843d7 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -6,9 +6,6 @@
 #ifndef __LINUX_NFSLOCALIO_H
 #define __LINUX_NFSLOCALIO_H
 
-/* nfsd_file structure is purposely kept opaque to NFS client */
-struct nfsd_file;
-
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 
 #include <linux/module.h>
@@ -19,6 +16,9 @@ struct nfsd_file;
 #include <linux/nfs.h>
 #include <net/net_namespace.h>
 
+struct nfs_client;
+struct nfs_file_localio;
+
 /*
  * Useful to allow a client to negotiate if localio
  * possible with its server.
@@ -27,28 +27,38 @@ struct nfsd_file;
  */
 typedef struct {
 	uuid_t uuid;
+	unsigned nfs3_localio_probe_count;
+	/* this struct is over a cacheline, avoid bouncing */
+	spinlock_t ____cacheline_aligned lock;
 	struct list_head list;
+	spinlock_t *list_lock; /* nn->local_clients_lock */
 	struct net __rcu *net; /* nfsd's network namespace */
 	struct auth_domain *dom; /* auth_domain for localio */
+	/* Local files to close when net is shut down or exports change */
+	struct list_head files;
 } nfs_uuid_t;
 
 void nfs_uuid_init(nfs_uuid_t *);
 bool nfs_uuid_begin(nfs_uuid_t *);
 void nfs_uuid_end(nfs_uuid_t *);
-void nfs_uuid_is_local(const uuid_t *, struct list_head *,
+void nfs_uuid_is_local(const uuid_t *, struct list_head *, spinlock_t *,
 		       struct net *, struct auth_domain *, struct module *);
-void nfs_uuid_invalidate_clients(struct list_head *list);
-void nfs_uuid_invalidate_one_client(nfs_uuid_t *nfs_uuid);
+
+void nfs_localio_enable_client(struct nfs_client *clp);
+void nfs_localio_disable_client(struct nfs_client *clp);
+void nfs_localio_invalidate_clients(struct list_head *nn_local_clients,
+				    spinlock_t *nn_local_clients_lock);
 
 /* localio needs to map filehandle -> struct nfsd_file */
 extern struct nfsd_file *
 nfsd_open_local_fh(struct net *, struct auth_domain *, struct rpc_clnt *,
 		   const struct cred *, const struct nfs_fh *,
 		   const fmode_t) __must_hold(rcu);
+void nfs_close_local_fh(struct nfs_file_localio *);
 
 struct nfsd_localio_operations {
-	bool (*nfsd_serv_try_get)(struct net *);
-	void (*nfsd_serv_put)(struct net *);
+	bool (*nfsd_net_try_get)(struct net *);
+	void (*nfsd_net_put)(struct net *);
 	struct nfsd_file *(*nfsd_open_local_fh)(struct net *,
 						struct auth_domain *,
 						struct rpc_clnt *,
@@ -56,6 +66,8 @@ struct nfsd_localio_operations {
 						const struct nfs_fh *,
 						const fmode_t);
 	struct net *(*nfsd_file_put_local)(struct nfsd_file *);
+	struct nfsd_file *(*nfsd_file_get)(struct nfsd_file *);
+	void (*nfsd_file_put)(struct nfsd_file *);
 	struct file *(*nfsd_file_file)(struct nfsd_file *);
 } ____cacheline_aligned;
 
@@ -64,17 +76,18 @@ extern const struct nfsd_localio_operations *nfs_to;
 
 struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
 		   struct rpc_clnt *, const struct cred *,
-		   const struct nfs_fh *, const fmode_t);
+		   const struct nfs_fh *, struct nfs_file_localio *,
+		   const fmode_t);
 
 static inline void nfs_to_nfsd_net_put(struct net *net)
 {
 	/*
-	 * Once reference to nfsd_serv is dropped, NFSD could be
-	 * unloaded, so ensure safe return from nfsd_file_put_local()
-	 * by always taking RCU.
+	 * Once reference to net (and associated nfsd_serv) is dropped, NFSD
+	 * could be unloaded, so ensure safe return from nfsd_net_put() by
+	 * always taking RCU.
 	 */
 	rcu_read_lock();
-	nfs_to->nfsd_serv_put(net);
+	nfs_to->nfsd_net_put(net);
 	rcu_read_unlock();
 }
 
@@ -91,12 +104,19 @@ static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
 }
 
 #else   /* CONFIG_NFS_LOCALIO */
+
+struct nfs_file_localio;
+static inline void nfs_close_local_fh(struct nfs_file_localio *nfl)
+{
+}
 static inline void nfsd_localio_ops_init(void)
 {
 }
-static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+struct nfs_client;
+static inline void nfs_localio_disable_client(struct nfs_client *clp)
 {
 }
+
 #endif  /* CONFIG_NFS_LOCALIO */
 
 #endif  /* __LINUX_NFSLOCALIO_H */
diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h
index cfad6ce7e1bd..dd85613cdd86 100644
--- a/include/linux/numa_memblks.h
+++ b/include/linux/numa_memblks.h
@@ -29,7 +29,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
 int __init numa_memblks_init(int (*init_func)(void),
 			     bool memblock_force_top_down);
 
+extern int numa_distance_cnt;
+
 #ifdef CONFIG_NUMA_EMU
+extern int emu_nid_to_phys[MAX_NUMNODES];
 int numa_emu_cmdline(char *str);
 void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
 					unsigned int nr_emu_nids);
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index 3ebeaa0ded00..515676ebe598 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -92,8 +92,8 @@ struct nvmem_cell_info {
  * @read_only:	Device is read-only.
  * @root_only:	Device is accessibly to root only.
  * @of_node:	If given, this will be used instead of the parent's of_node.
- * @reg_read:	Callback to read data.
- * @reg_write:	Callback to write data.
+ * @reg_read:	Callback to read data; return zero if successful.
+ * @reg_write:	Callback to write data; return zero if successful.
  * @size:	Device size.
  * @word_size:	Minimum read/write access granularity.
  * @stride:	Minimum read/write access stride.
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 691506bdf2c5..36d283552f80 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -110,6 +110,7 @@ enum pageflags {
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
+	PG_dropbehind,		/* drop pages on IO completion */
 #ifdef CONFIG_MMU
 	PG_mlocked,		/* Page is vma mlocked */
 #endif
@@ -562,6 +563,10 @@ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
 FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE)
 	FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE)
 
+FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+	__FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+
 #ifdef CONFIG_HIGHMEM
 /*
  * Must use a macro here due to header dependency issues. page_zone() is not
@@ -894,21 +899,9 @@ static inline int PageTransCompound(const struct page *page)
 {
 	return PageCompound(page);
 }
-
-/*
- * PageTransTail returns true for both transparent huge pages
- * and hugetlbfs pages, so it should only be called when it's known
- * that hugetlbfs pages aren't involved.
- */
-static inline int PageTransTail(const struct page *page)
-{
-	return PageTail(page);
-}
 #else
 TESTPAGEFLAG_FALSE(TransHuge, transhuge)
 TESTPAGEFLAG_FALSE(TransCompound, transcompound)
-TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap)
-TESTPAGEFLAG_FALSE(TransTail, transtail)
 #endif
 
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -918,11 +911,9 @@ TESTPAGEFLAG_FALSE(TransTail, transtail)
  *
  * This flag is set by hwpoison handler.  Cleared by THP split or free page.
  */
-PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
-	TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE)
 #else
-PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned)
-	TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned)
+FOLIO_FLAG_FALSE(has_hwpoisoned)
 #endif
 
 /*
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 73dc2c1841ec..898bb788243b 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -31,7 +31,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page,
 				  int migratetype);
 
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype, int flags, gfp_t gfp_flags);
+			     int migratetype, int flags);
 
 void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			     int migratetype);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcf0865a38ae..47bfc6b1b632 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -710,6 +710,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
  * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
  * * %FGP_NOWAIT - Don't block on the folio lock.
  * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
+ * * %FGP_DONTCACHE - Uncached buffered IO
  * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin()
  *   implementation.
  */
@@ -723,10 +724,21 @@ typedef unsigned int __bitwise fgf_t;
 #define FGP_NOWAIT		((__force fgf_t)0x00000020)
 #define FGP_FOR_MMAP		((__force fgf_t)0x00000040)
 #define FGP_STABLE		((__force fgf_t)0x00000080)
+#define FGP_DONTCACHE		((__force fgf_t)0x00000100)
 #define FGF_GET_ORDER(fgf)	(((__force unsigned)fgf) >> 26)	/* top 6 bits */
 
 #define FGP_WRITEBEGIN		(FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
 
+static inline unsigned int filemap_get_order(size_t size)
+{
+	unsigned int shift = ilog2(size);
+
+	if (shift <= PAGE_SHIFT)
+		return 0;
+
+	return shift - PAGE_SHIFT;
+}
+
 /**
  * fgf_set_order - Encode a length in the fgf_t flags.
  * @size: The suggested size of the folio to create.
@@ -740,11 +752,11 @@ typedef unsigned int __bitwise fgf_t;
  */
 static inline fgf_t fgf_set_order(size_t size)
 {
-	unsigned int shift = ilog2(size);
+	unsigned int order = filemap_get_order(size);
 
-	if (shift <= PAGE_SHIFT)
+	if (!order)
 		return 0;
-	return (__force fgf_t)((shift - PAGE_SHIFT) << 26);
+	return (__force fgf_t)(order << 26);
 }
 
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
@@ -1271,11 +1283,6 @@ void folio_wait_private_2(struct folio *folio);
 int folio_wait_private_2_killable(struct folio *folio);
 
 /*
- * Add an arbitrary waiter to a page's wait queue
- */
-void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
-
-/*
  * Fault in userspace address range.
  */
 size_t fault_in_writeable(char __user *uaddr, size_t size);
@@ -1353,6 +1360,7 @@ struct readahead_control {
 	pgoff_t _index;
 	unsigned int _nr_pages;
 	unsigned int _batch_count;
+	bool dropbehind;
 	bool _workingset;
 	unsigned long _pflags;
 };
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index d2402bf4aea2..de5deb1a0118 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2593,6 +2593,11 @@
 
 #define PCI_VENDOR_ID_REDHAT		0x1b36
 
+#define PCI_VENDOR_ID_WCHIC		0x1c00
+#define PCI_DEVICE_ID_WCHIC_CH382_0S1P	0x3050
+#define PCI_DEVICE_ID_WCHIC_CH382_2S1P	0x3250
+#define PCI_DEVICE_ID_WCHIC_CH382_2S	0x3253
+
 #define PCI_VENDOR_ID_SILICOM_DENMARK	0x1c2c
 
 #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS	0x1c36
@@ -2647,6 +2652,12 @@
 #define PCI_VENDOR_ID_AKS		0x416c
 #define PCI_DEVICE_ID_AKS_ALADDINCARD	0x0100
 
+#define PCI_VENDOR_ID_WCHCN		0x4348
+#define PCI_DEVICE_ID_WCHCN_CH353_4S	0x3453
+#define PCI_DEVICE_ID_WCHCN_CH353_2S1PF	0x5046
+#define PCI_DEVICE_ID_WCHCN_CH353_1S1P	0x5053
+#define PCI_DEVICE_ID_WCHCN_CH353_2S1P	0x7053
+
 #define PCI_VENDOR_ID_ACCESSIO		0x494f
 #define PCI_DEVICE_ID_ACCESSIO_WDG_CSM	0x22c0
 
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index adef9d6e9b1b..94d267d02372 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -533,7 +533,14 @@ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
 static inline void ptep_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
-	ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = ptep_get(ptep);
+
+	pte_clear(mm, addr, ptep);
+	/*
+	 * No need for ptep_get_and_clear(): page table check doesn't care about
+	 * any bits that could have been set by HW concurrently.
+	 */
+	page_table_check_pte_clear(mm, pte);
 }
 
 #ifdef CONFIG_GUP_GET_PXX_LOW_HIGH
diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index b3c4993e656e..ecf290a0c98f 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -5044,8 +5044,11 @@ struct ec_response_pd_status {
 #define PD_EVENT_POWER_CHANGE      BIT(1)
 #define PD_EVENT_IDENTITY_RECEIVED BIT(2)
 #define PD_EVENT_DATA_SWAP         BIT(3)
+#define PD_EVENT_TYPEC             BIT(4)
+#define PD_EVENT_PPM               BIT(5)
+
 struct ec_response_host_event_status {
-	uint32_t status;      /* PD MCU host event status */
+	uint32_t status; /* PD MCU host event status */
 } __ec_align4;
 
 /* Set USB type-C port role and muxes */
@@ -6105,6 +6108,29 @@ struct ec_response_typec_vdm_response {
 
 #undef VDO_MAX_SIZE
 
+/*
+ * UCSI OPM-PPM commands
+ *
+ * These commands are used for communication between OPM and PPM.
+ * Only UCSI3.0 is tested.
+ */
+
+#define EC_CMD_UCSI_PPM_SET 0x0140
+
+/* The data size is stored in the host command protocol header. */
+struct ec_params_ucsi_ppm_set {
+	uint16_t offset;
+	uint8_t data[];
+} __ec_align2;
+
+#define EC_CMD_UCSI_PPM_GET 0x0141
+
+/* For 'GET' sub-commands, data will be returned as a raw payload. */
+struct ec_params_ucsi_ppm_get {
+	uint16_t offset;
+	uint8_t size;
+} __ec_align2;
+
 /*****************************************************************************/
 /* The command range 0x200-0x2FF is reserved for Rotor. */
 
diff --git a/include/linux/pm.h b/include/linux/pm.h
index e7f0260f15ad..78855d794342 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -384,12 +384,8 @@ const struct dev_pm_ops name = { \
 
 #ifdef CONFIG_PM
 #define _EXPORT_DEV_PM_OPS(name, license, ns)		_EXPORT_PM_OPS(name, license, ns)
-#define EXPORT_PM_FN_GPL(name)				EXPORT_SYMBOL_GPL(name)
-#define EXPORT_PM_FN_NS_GPL(name, ns)			EXPORT_SYMBOL_NS_GPL(name, "ns")
 #else
 #define _EXPORT_DEV_PM_OPS(name, license, ns)		_DISCARD_PM_OPS(name, license, ns)
-#define EXPORT_PM_FN_GPL(name)
-#define EXPORT_PM_FN_NS_GPL(name, ns)
 #endif
 
 #ifdef CONFIG_PM_SLEEP
@@ -570,7 +566,8 @@ const struct dev_pm_ops name = { \
 					{ .event = PM_EVENT_AUTO_RESUME, })
 
 #define PMSG_IS_AUTO(msg)	(((msg).event & PM_EVENT_AUTO) != 0)
-
+#define PMSG_NO_WAKEUP(msg)	(((msg).event & \
+				(PM_EVENT_FREEZE | PM_EVENT_QUIESCE)) != 0)
 /*
  * Device run-time power management status.
  *
@@ -683,6 +680,7 @@ struct dev_pm_info {
 	bool			no_pm_callbacks:1;	/* Owned by the PM core */
 	bool			async_in_progress:1;	/* Owned by the PM core */
 	bool			must_resume:1;		/* Owned by the PM core */
+	bool			set_active:1;		/* Owned by the PM core */
 	bool			may_skip_resume:1;	/* Set by subsystems */
 #else
 	bool			should_wakeup:1;
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index 5180dc9f1706..6b190639b08e 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -61,6 +61,7 @@ struct bq27xxx_device_info {
 	struct bq27xxx_access_methods bus;
 	struct bq27xxx_reg_cache cache;
 	int charge_design_full;
+	int voltage_min_design;
 	bool removed;
 	unsigned long last_update;
 	union power_supply_propval last_status;
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index b98106e1a90f..6ed53b292162 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -15,6 +15,8 @@
 #include <linux/device.h>
 #include <linux/workqueue.h>
 #include <linux/leds.h>
+#include <linux/rwsem.h>
+#include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/notifier.h>
 
@@ -40,7 +42,7 @@ enum {
 };
 
 /* What algorithm is the charger using? */
-enum {
+enum power_supply_charge_type {
 	POWER_SUPPLY_CHARGE_TYPE_UNKNOWN = 0,
 	POWER_SUPPLY_CHARGE_TYPE_NONE,
 	POWER_SUPPLY_CHARGE_TYPE_TRICKLE,	/* slow speed */
@@ -58,6 +60,7 @@ enum {
 	POWER_SUPPLY_HEALTH_OVERHEAT,
 	POWER_SUPPLY_HEALTH_DEAD,
 	POWER_SUPPLY_HEALTH_OVERVOLTAGE,
+	POWER_SUPPLY_HEALTH_UNDERVOLTAGE,
 	POWER_SUPPLY_HEALTH_UNSPEC_FAILURE,
 	POWER_SUPPLY_HEALTH_COLD,
 	POWER_SUPPLY_HEALTH_WATCHDOG_TIMER_EXPIRE,
@@ -99,6 +102,7 @@ enum power_supply_property {
 	/* Properties of type `int' */
 	POWER_SUPPLY_PROP_STATUS = 0,
 	POWER_SUPPLY_PROP_CHARGE_TYPE,
+	POWER_SUPPLY_PROP_CHARGE_TYPES,
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_ONLINE,
@@ -245,6 +249,7 @@ struct power_supply_desc {
 	const char *name;
 	enum power_supply_type type;
 	u8 charge_behaviours;
+	u32 charge_types;
 	u32 usb_types;
 	const enum power_supply_property *properties;
 	size_t num_properties;
@@ -281,6 +286,28 @@ struct power_supply_desc {
 	int use_for_apm;
 };
 
+struct power_supply_ext {
+	const char *const name;
+	u8 charge_behaviours;
+	const enum power_supply_property *properties;
+	size_t num_properties;
+
+	int (*get_property)(struct power_supply *psy,
+			    const struct power_supply_ext *ext,
+			    void *data,
+			    enum power_supply_property psp,
+			    union power_supply_propval *val);
+	int (*set_property)(struct power_supply *psy,
+			    const struct power_supply_ext *ext,
+			    void *data,
+			    enum power_supply_property psp,
+			    const union power_supply_propval *val);
+	int (*property_is_writeable)(struct power_supply *psy,
+				     const struct power_supply_ext *ext,
+				     void *data,
+				     enum power_supply_property psp);
+};
+
 struct power_supply {
 	const struct power_supply_desc *desc;
 
@@ -300,10 +327,13 @@ struct power_supply {
 	struct delayed_work deferred_register_work;
 	spinlock_t changed_lock;
 	bool changed;
+	bool update_groups;
 	bool initialized;
 	bool removing;
 	atomic_t use_cnt;
 	struct power_supply_battery_info *battery_info;
+	struct rw_semaphore extensions_sem; /* protects "extensions" */
+	struct list_head extensions;
 #ifdef CONFIG_THERMAL
 	struct thermal_zone_device *tzd;
 	struct thermal_cooling_device *tcd;
@@ -318,6 +348,8 @@ struct power_supply {
 #endif
 };
 
+#define dev_to_psy(__dev)	container_of_const(__dev, struct power_supply, dev)
+
 /*
  * This is recommended structure to specify static power supply parameters.
  * Generic one, parametrizable for different power supplies. Power supply
@@ -878,10 +910,18 @@ devm_power_supply_register(struct device *parent,
 extern void power_supply_unregister(struct power_supply *psy);
 extern int power_supply_powers(struct power_supply *psy, struct device *dev);
 
+extern int __must_check
+power_supply_register_extension(struct power_supply *psy,
+				const struct power_supply_ext *ext,
+				struct device *dev,
+				void *data);
+extern void power_supply_unregister_extension(struct power_supply *psy,
+					      const struct power_supply_ext *ext);
+
 #define to_power_supply(device) container_of(device, struct power_supply, dev)
 
 extern void *power_supply_get_drvdata(struct power_supply *psy);
-extern int power_supply_for_each_device(void *data, int (*fn)(struct device *dev, void *data));
+extern int power_supply_for_each_psy(void *data, int (*fn)(struct power_supply *psy, void *data));
 
 static inline bool power_supply_is_amp_property(enum power_supply_property psp)
 {
@@ -944,6 +984,11 @@ ssize_t power_supply_charge_behaviour_show(struct device *dev,
 					   char *buf);
 
 int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf);
+ssize_t power_supply_charge_types_show(struct device *dev,
+				       unsigned int available_types,
+				       enum power_supply_charge_type current_type,
+				       char *buf);
+int power_supply_charge_types_parse(unsigned int available_types, const char *buf);
 #else
 static inline
 ssize_t power_supply_charge_behaviour_show(struct device *dev,
@@ -959,6 +1004,20 @@ static inline int power_supply_charge_behaviour_parse(unsigned int available_beh
 {
 	return -EOPNOTSUPP;
 }
+
+static inline
+ssize_t power_supply_charge_types_show(struct device *dev,
+				       unsigned int available_types,
+				       enum power_supply_charge_type current_type,
+				       char *buf)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int power_supply_charge_types_parse(unsigned int available_types, const char *buf)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #endif /* __LINUX_POWER_SUPPLY_H__ */
diff --git a/include/linux/pps_gen_kernel.h b/include/linux/pps_gen_kernel.h
new file mode 100644
index 000000000000..022ea0ac4440
--- /dev/null
+++ b/include/linux/pps_gen_kernel.h
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PPS generator API kernel header
+ *
+ * Copyright (C) 2024 Rodolfo Giometti <giometti@enneenne.com>
+ */
+
+#ifndef LINUX_PPS_GEN_KERNEL_H
+#define LINUX_PPS_GEN_KERNEL_H
+
+#include <linux/pps_gen.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+
+/*
+ * Global defines
+ */
+
+#define PPS_GEN_MAX_SOURCES	16		/* should be enough... */
+
+struct pps_gen_device;
+
+/**
+ * struct pps_gen_source_info - the specific PPS generator info
+ * @use_system_clock: true, if the system clock is used to generate pulses
+ * @get_time: query the time stored into the generator clock
+ * @enable: enable/disable the PPS pulses generation
+ *
+ * This is the main generator struct where all needed information must be
+ * placed before calling the pps_gen_register_source().
+ */
+struct pps_gen_source_info {
+	bool use_system_clock;
+
+	int (*get_time)(struct pps_gen_device *pps_gen,
+					struct timespec64 *time);
+	int (*enable)(struct pps_gen_device *pps_gen, bool enable);
+
+/* private: internal use only */
+	struct module *owner;
+	struct device *parent;			/* for device_create */
+};
+
+/* The main struct */
+struct pps_gen_device {
+	struct pps_gen_source_info info;	/* PSS generator info */
+	bool enabled;				/* PSS generator status */
+
+	unsigned int event;
+	unsigned int sequence;
+
+	unsigned int last_ev;			/* last PPS event id */
+	wait_queue_head_t queue;		/* PPS event queue */
+
+	unsigned int id;			/* PPS generator unique ID */
+	struct cdev cdev;
+	struct device *dev;
+	struct fasync_struct *async_queue;	/* fasync method */
+	spinlock_t lock;
+};
+
+/*
+ * Global variables
+ */
+
+extern const struct attribute_group *pps_gen_groups[];
+
+/*
+ * Exported functions
+ */
+
+extern struct pps_gen_device *pps_gen_register_source(
+				struct pps_gen_source_info *info);
+extern void pps_gen_unregister_source(struct pps_gen_device *pps_gen);
+extern void pps_gen_event(struct pps_gen_device *pps_gen,
+				unsigned int event, void *data);
+
+#endif /* LINUX_PPS_GEN_KERNEL_H */
diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h
index 78c8ac4951b5..c7abce28ed29 100644
--- a/include/linux/pps_kernel.h
+++ b/include/linux/pps_kernel.h
@@ -56,8 +56,7 @@ struct pps_device {
 
 	unsigned int id;			/* PPS source unique ID */
 	void const *lookup_cookie;		/* For pps_lookup_dev() only */
-	struct cdev cdev;
-	struct device *dev;
+	struct device dev;
 	struct fasync_struct *async_queue;	/* fasync method */
 	spinlock_t lock;
 };
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 6853e29d9674..a2df509056ac 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -347,6 +347,23 @@ struct pwm_chip {
 	struct pwm_device pwms[] __counted_by(npwm);
 };
 
+/**
+ * pwmchip_supports_waveform() - checks if the given chip supports waveform callbacks
+ * @chip: The pwm_chip to test
+ *
+ * Returns true iff the pwm chip support the waveform functions like
+ * pwm_set_waveform_might_sleep() and pwm_round_waveform_might_sleep()
+ */
+static inline bool pwmchip_supports_waveform(struct pwm_chip *chip)
+{
+	/*
+	 * only check for .write_waveform(). If that is available,
+	 * .round_waveform_tohw() and .round_waveform_fromhw() asserted to be
+	 * available, too, in pwmchip_add().
+	 */
+	return chip->ops->write_waveform != NULL;
+}
+
 static inline struct device *pwmchip_parent(const struct pwm_chip *chip)
 {
 	return chip->dev.parent;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ac08431e238f..9632e3318e0d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -398,6 +398,12 @@ struct sched_info {
 	/* Time spent waiting on a runqueue: */
 	unsigned long long		run_delay;
 
+	/* Max time spent waiting on a runqueue: */
+	unsigned long long		max_run_delay;
+
+	/* Min time spent waiting on a runqueue: */
+	unsigned long long		min_run_delay;
+
 	/* Timestamps: */
 
 	/* When did we last run on a CPU? */
diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h
index 412cdaba33eb..17e04859b9a4 100644
--- a/include/linux/sched/hotplug.h
+++ b/include/linux/sched/hotplug.h
@@ -18,10 +18,6 @@ extern int sched_cpu_dying(unsigned int cpu);
 # define sched_cpu_dying	NULL
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern void idle_task_exit(void);
-#else
 static inline void idle_task_exit(void) {}
-#endif
 
 #endif /* _LINUX_SCHED_HOTPLUG_H */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index d1a2346cf0f8..5ce48eab7a2a 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -322,6 +322,7 @@ SEQCOUNT_LOCKNAME(mutex,        struct mutex,    true,     mutex)
  * raw_seqcount_try_begin() - begin a seqcount_t read critical section
  *                            w/o lockdep and w/o counter stabilization
  * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants
+ * @start: count to be passed to read_seqcount_retry()
  *
  * Similar to raw_seqcount_begin(), except it enables eliding the critical
  * section entirely if odd, instead of doing the speculation knowing it will
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index e0717c8393d7..144de7a7948d 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -161,8 +161,8 @@ struct uart_8250_port {
 	void			(*dl_write)(struct uart_8250_port *up, u32 value);
 
 	struct uart_8250_em485 *em485;
-	void			(*rs485_start_tx)(struct uart_8250_port *);
-	void			(*rs485_stop_tx)(struct uart_8250_port *);
+	void			(*rs485_start_tx)(struct uart_8250_port *up, bool toggle_ier);
+	void			(*rs485_stop_tx)(struct uart_8250_port *up, bool toggle_ier);
 
 	/* Serial port overrun backoff */
 	struct delayed_work overrun_backoff;
diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h
index bd9836690da6..2d6c30317792 100644
--- a/include/linux/soundwire/sdw.h
+++ b/include/linux/soundwire/sdw.h
@@ -54,6 +54,8 @@ struct sdw_slave;
 #define SDW_MAX_PORTS			15
 #define SDW_VALID_PORT_RANGE(n)		((n) < SDW_MAX_PORTS && (n) >= 1)
 
+#define SDW_MAX_LANES		8
+
 enum {
 	SDW_PORT_DIRN_SINK = 0,
 	SDW_PORT_DIRN_SOURCE,
@@ -356,6 +358,7 @@ struct sdw_dpn_prop {
  * and masks are supported
  * @commit_register_supported: is PCP_Commit register supported
  * @scp_int1_mask: SCP_INT1_MASK desired settings
+ * @lane_maps: Lane mapping for the slave, only valid if lane_control_support is set
  * @clock_reg_supported: the Peripheral implements the clock base and scale
  * registers introduced with the SoundWire 1.2 specification. SDCA devices
  * do not need to set this boolean property as the registers are required.
@@ -385,6 +388,7 @@ struct sdw_slave_prop {
 	u32 sdca_interrupt_register_list;
 	u8 commit_register_supported;
 	u8 scp_int1_mask;
+	u8 lane_maps[SDW_MAX_LANES];
 	bool clock_reg_supported;
 	bool use_domain_irq;
 };
@@ -450,6 +454,7 @@ struct sdw_master_prop {
 
 int sdw_master_read_prop(struct sdw_bus *bus);
 int sdw_slave_read_prop(struct sdw_slave *slave);
+int sdw_slave_read_lane_mapping(struct sdw_slave *slave);
 
 /*
  * SDW Slave Structures and APIs
@@ -850,77 +855,6 @@ struct sdw_master_ops {
 					int dev_num);
 };
 
-/**
- * struct sdw_bus - SoundWire bus
- * @dev: Shortcut to &bus->md->dev to avoid changing the entire code.
- * @md: Master device
- * @bus_lock_key: bus lock key associated to @bus_lock
- * @bus_lock: bus lock
- * @slaves: list of Slaves on this bus
- * @msg_lock_key: message lock key associated to @msg_lock
- * @msg_lock: message lock
- * @m_rt_list: List of Master instance of all stream(s) running on Bus. This
- * is used to compute and program bus bandwidth, clock, frame shape,
- * transport and port parameters
- * @defer_msg: Defer message
- * @params: Current bus parameters
- * @stream_refcount: number of streams currently using this bus
- * @ops: Master callback ops
- * @port_ops: Master port callback ops
- * @prop: Master properties
- * @vendor_specific_prop: pointer to non-standard properties
- * @hw_sync_min_links: Number of links used by a stream above which
- * hardware-based synchronization is required. This value is only
- * meaningful if multi_link is set. If set to 1, hardware-based
- * synchronization will be used even if a stream only uses a single
- * SoundWire segment.
- * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
- * @link_id: Link id number, can be 0 to N, unique for each Controller
- * @id: bus system-wide unique id
- * @compute_params: points to Bus resource management implementation
- * @assigned: Bitmap for Slave device numbers.
- * Bit set implies used number, bit clear implies unused number.
- * @clk_stop_timeout: Clock stop timeout computed
- * @bank_switch_timeout: Bank switch timeout computed
- * @domain: IRQ domain
- * @irq_chip: IRQ chip
- * @debugfs: Bus debugfs (optional)
- * @multi_link: Store bus property that indicates if multi links
- * are supported. This flag is populated by drivers after reading
- * appropriate firmware (ACPI/DT).
- */
-struct sdw_bus {
-	struct device *dev;
-	struct sdw_master_device *md;
-	struct lock_class_key bus_lock_key;
-	struct mutex bus_lock;
-	struct list_head slaves;
-	struct lock_class_key msg_lock_key;
-	struct mutex msg_lock;
-	struct list_head m_rt_list;
-	struct sdw_defer defer_msg;
-	struct sdw_bus_params params;
-	int stream_refcount;
-	const struct sdw_master_ops *ops;
-	const struct sdw_master_port_ops *port_ops;
-	struct sdw_master_prop prop;
-	void *vendor_specific_prop;
-	int hw_sync_min_links;
-	int controller_id;
-	unsigned int link_id;
-	int id;
-	int (*compute_params)(struct sdw_bus *bus);
-	DECLARE_BITMAP(assigned, SDW_MAX_DEVICES);
-	unsigned int clk_stop_timeout;
-	u32 bank_switch_timeout;
-	struct irq_chip irq_chip;
-	struct irq_domain *domain;
-#ifdef CONFIG_DEBUG_FS
-	struct dentry *debugfs;
-#endif
-	bool multi_link;
-};
-
 int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent,
 		       struct fwnode_handle *fwnode);
 void sdw_bus_master_delete(struct sdw_bus *bus);
@@ -1010,10 +944,83 @@ struct sdw_stream_runtime {
 	struct list_head master_list;
 };
 
+/**
+ * struct sdw_bus - SoundWire bus
+ * @dev: Shortcut to &bus->md->dev to avoid changing the entire code.
+ * @md: Master device
+ * @bus_lock_key: bus lock key associated to @bus_lock
+ * @bus_lock: bus lock
+ * @slaves: list of Slaves on this bus
+ * @msg_lock_key: message lock key associated to @msg_lock
+ * @msg_lock: message lock
+ * @m_rt_list: List of Master instance of all stream(s) running on Bus. This
+ * is used to compute and program bus bandwidth, clock, frame shape,
+ * transport and port parameters
+ * @defer_msg: Defer message
+ * @params: Current bus parameters
+ * @stream_refcount: number of streams currently using this bus
+ * @ops: Master callback ops
+ * @port_ops: Master port callback ops
+ * @prop: Master properties
+ * @vendor_specific_prop: pointer to non-standard properties
+ * @hw_sync_min_links: Number of links used by a stream above which
+ * hardware-based synchronization is required. This value is only
+ * meaningful if multi_link is set. If set to 1, hardware-based
+ * synchronization will be used even if a stream only uses a single
+ * SoundWire segment.
+ * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used.
+ * @link_id: Link id number, can be 0 to N, unique for each Controller
+ * @id: bus system-wide unique id
+ * @compute_params: points to Bus resource management implementation
+ * @assigned: Bitmap for Slave device numbers.
+ * Bit set implies used number, bit clear implies unused number.
+ * @clk_stop_timeout: Clock stop timeout computed
+ * @bank_switch_timeout: Bank switch timeout computed
+ * @domain: IRQ domain
+ * @irq_chip: IRQ chip
+ * @debugfs: Bus debugfs (optional)
+ * @multi_link: Store bus property that indicates if multi links
+ * are supported. This flag is populated by drivers after reading
+ * appropriate firmware (ACPI/DT).
+ * @lane_used_bandwidth: how much bandwidth in bits per second is used by each lane
+ */
+struct sdw_bus {
+	struct device *dev;
+	struct sdw_master_device *md;
+	struct lock_class_key bus_lock_key;
+	struct mutex bus_lock;
+	struct list_head slaves;
+	struct lock_class_key msg_lock_key;
+	struct mutex msg_lock;
+	struct list_head m_rt_list;
+	struct sdw_defer defer_msg;
+	struct sdw_bus_params params;
+	int stream_refcount;
+	const struct sdw_master_ops *ops;
+	const struct sdw_master_port_ops *port_ops;
+	struct sdw_master_prop prop;
+	void *vendor_specific_prop;
+	int hw_sync_min_links;
+	int controller_id;
+	unsigned int link_id;
+	int id;
+	int (*compute_params)(struct sdw_bus *bus, struct sdw_stream_runtime *stream);
+	DECLARE_BITMAP(assigned, SDW_MAX_DEVICES);
+	unsigned int clk_stop_timeout;
+	u32 bank_switch_timeout;
+	struct irq_chip irq_chip;
+	struct irq_domain *domain;
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debugfs;
+#endif
+	bool multi_link;
+	unsigned int lane_used_bandwidth[SDW_MAX_LANES];
+};
+
 struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name);
 void sdw_release_stream(struct sdw_stream_runtime *stream);
 
-int sdw_compute_params(struct sdw_bus *bus);
+int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream);
 
 int sdw_stream_add_master(struct sdw_bus *bus,
 			  struct sdw_stream_config *stream_config,
@@ -1034,6 +1041,7 @@ int sdw_bus_exit_clk_stop(struct sdw_bus *bus);
 
 int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id);
 void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id);
+bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave);
 
 #if IS_ENABLED(CONFIG_SOUNDWIRE)
 
@@ -1045,6 +1053,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave,
 int sdw_stream_remove_slave(struct sdw_slave *slave,
 			    struct sdw_stream_runtime *stream);
 
+int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base);
+
 /* messaging and data APIs */
 int sdw_read(struct sdw_slave *slave, u32 addr);
 int sdw_write(struct sdw_slave *slave, u32 addr, u8 value);
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 9d8382e23a9c..be7496a6a0dd 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -50,11 +50,11 @@ struct kstat {
 	struct timespec64 btime;			/* File creation time */
 	u64		blocks;
 	u64		mnt_id;
+	u64		change_cookie;
+	u64		subvol;
 	u32		dio_mem_align;
 	u32		dio_offset_align;
 	u32		dio_read_offset_align;
-	u64		change_cookie;
-	u64		subvol;
 	u32		atomic_write_unit_min;
 	u32		atomic_write_unit_max;
 	u32		atomic_write_segments_max;
diff --git a/include/linux/string.h b/include/linux/string.h
index 86d5d352068b..f8e21e80942f 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -414,7 +414,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
  * must be discoverable by the compiler.
  */
 #define strtomem_pad(dest, src, pad)	do {				\
-	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+	const size_t _dest_len = __must_be_byte_array(dest) +		\
+				 ARRAY_SIZE(dest);			\
 	const size_t _src_len = __builtin_object_size(src, 1);		\
 									\
 	BUILD_BUG_ON(!__builtin_constant_p(_dest_len) ||		\
@@ -437,7 +438,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
  * must be discoverable by the compiler.
  */
 #define strtomem(dest, src)	do {					\
-	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+	const size_t _dest_len = __must_be_byte_array(dest) +		\
+				 ARRAY_SIZE(dest);			\
 	const size_t _src_len = __builtin_object_size(src, 1);		\
 									\
 	BUILD_BUG_ON(!__builtin_constant_p(_dest_len) ||		\
@@ -456,7 +458,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
  * Note that sizes of @dest and @src must be known at compile-time.
  */
 #define memtostr(dest, src)	do {					\
-	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+	const size_t _dest_len = __must_be_byte_array(dest) +		\
+				 ARRAY_SIZE(dest);			\
 	const size_t _src_len = __builtin_object_size(src, 1);		\
 	const size_t _src_chars = strnlen(src, _src_len);		\
 	const size_t _copy_len = min(_dest_len - 1, _src_chars);	\
@@ -481,7 +484,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count,
  * Note that sizes of @dest and @src must be known at compile-time.
  */
 #define memtostr_pad(dest, src)		do {				\
-	const size_t _dest_len = __builtin_object_size(dest, 1);	\
+	const size_t _dest_len = __must_be_byte_array(dest) +		\
+				 ARRAY_SIZE(dest);			\
 	const size_t _src_len = __builtin_object_size(src, 1);		\
 	const size_t _src_chars = strnlen(src, _src_len);		\
 	const size_t _copy_len = min(_dest_len - 1, _src_chars);	\
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 35766963dd14..e783132e481f 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -222,6 +222,8 @@ static inline bool cache_is_expired(struct cache_detail *detail, struct cache_he
 	return detail->flush_time >= h->last_refresh;
 }
 
+extern int cache_check_rcu(struct cache_detail *detail,
+		       struct cache_head *h, struct cache_req *rqstp);
 extern int cache_check(struct cache_detail *detail,
 		       struct cache_head *h, struct cache_req *rqstp);
 extern void cache_flush(void);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 5321585c778f..fec976e58174 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -93,6 +93,7 @@ struct rpc_clnt {
 	const struct cred	*cl_cred;
 	unsigned int		cl_max_connect; /* max number of transports not to the same IP */
 	struct super_block *pipefs_sb;
+	atomic_t		cl_task_count;
 };
 
 /*
diff --git a/include/linux/sunrpc/gss_asn1.h b/include/linux/sunrpc/gss_asn1.h
deleted file mode 100644
index 3ccecd0ad229..000000000000
--- a/include/linux/sunrpc/gss_asn1.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- *  linux/include/linux/sunrpc/gss_asn1.h
- *
- *  minimal asn1 for generic encoding/decoding of gss tokens
- *
- *  Adapted from MIT Kerberos 5-1.2.1 lib/include/krb5.h,
- *  lib/gssapi/krb5/gssapiP_krb5.h, and others
- *
- *  Copyright (c) 2000 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson   <andros@umich.edu>
- */
-
-/*
- * Copyright 1995 by the Massachusetts Institute of Technology.
- * All Rights Reserved.
- *
- * Export of this software from the United States of America may
- *   require a specific license from the United States Government.
- *   It is the responsibility of any person or organization contemplating
- *   export to obtain such a license before exporting.
- *
- * WITHIN THAT CONSTRAINT, permission to use, copy, modify, and
- * distribute this software and its documentation for any purpose and
- * without fee is hereby granted, provided that the above copyright
- * notice appear in all copies and that both that copyright notice and
- * this permission notice appear in supporting documentation, and that
- * the name of M.I.T. not be used in advertising or publicity pertaining
- * to distribution of the software without specific, written prior
- * permission.  Furthermore if you modify this software you must label
- * your software as modified software and not distribute it in such a
- * fashion that it might be confused with the original M.I.T. software.
- * M.I.T. makes no representations about the suitability of
- * this software for any purpose.  It is provided "as is" without express
- * or implied warranty.
- *
- */
-
-
-#include <linux/sunrpc/gss_api.h>
-
-#define SIZEOF_INT 4
-
-/* from gssapi_err_generic.h */
-#define G_BAD_SERVICE_NAME                       (-2045022976L)
-#define G_BAD_STRING_UID                         (-2045022975L)
-#define G_NOUSER                                 (-2045022974L)
-#define G_VALIDATE_FAILED                        (-2045022973L)
-#define G_BUFFER_ALLOC                           (-2045022972L)
-#define G_BAD_MSG_CTX                            (-2045022971L)
-#define G_WRONG_SIZE                             (-2045022970L)
-#define G_BAD_USAGE                              (-2045022969L)
-#define G_UNKNOWN_QOP                            (-2045022968L)
-#define G_NO_HOSTNAME                            (-2045022967L)
-#define G_BAD_HOSTNAME                           (-2045022966L)
-#define G_WRONG_MECH                             (-2045022965L)
-#define G_BAD_TOK_HEADER                         (-2045022964L)
-#define G_BAD_DIRECTION                          (-2045022963L)
-#define G_TOK_TRUNC                              (-2045022962L)
-#define G_REFLECT                                (-2045022961L)
-#define G_WRONG_TOKID                            (-2045022960L)
-
-#define g_OID_equal(o1,o2) \
-   (((o1)->len == (o2)->len) && \
-    (memcmp((o1)->data,(o2)->data,(int) (o1)->len) == 0))
-
-u32 g_verify_token_header(
-     struct xdr_netobj *mech,
-     int *body_size,
-     unsigned char **buf_in,
-     int toksize);
-
-int g_token_size(
-     struct xdr_netobj *mech,
-     unsigned int body_size);
-
-void g_make_token_header(
-     struct xdr_netobj *mech,
-     int body_size,
-     unsigned char **buf);
diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h
index 78a80bf3fdcb..43950b5237c8 100644
--- a/include/linux/sunrpc/gss_krb5.h
+++ b/include/linux/sunrpc/gss_krb5.h
@@ -40,7 +40,6 @@
 #include <crypto/skcipher.h>
 #include <linux/sunrpc/auth_gss.h>
 #include <linux/sunrpc/gss_err.h>
-#include <linux/sunrpc/gss_asn1.h>
 
 /* Length of constant used in key derivation */
 #define GSS_KRB5_K5CLENGTH (5)
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index e68fecf6eab5..74658cca0f38 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -72,16 +72,12 @@ struct svc_serv {
 	spinlock_t		sv_lock;
 	unsigned int		sv_nprogs;	/* Number of sv_programs */
 	unsigned int		sv_nrthreads;	/* # of server threads */
-	unsigned int		sv_maxconn;	/* max connections allowed or
-						 * '0' causing max to be based
-						 * on number of threads. */
-
 	unsigned int		sv_max_payload;	/* datagram payload size */
 	unsigned int		sv_max_mesg;	/* max_payload + 1 page for overheads */
 	unsigned int		sv_xdrsize;	/* XDR buffer size */
 	struct list_head	sv_permsocks;	/* all permanent sockets */
 	struct list_head	sv_tempsocks;	/* all temporary sockets */
-	int			sv_tmpcnt;	/* count of temporary sockets */
+	int			sv_tmpcnt;	/* count of temporary "valid" sockets */
 	struct timer_list	sv_temptimer;	/* timer for aging temporary sockets */
 
 	char *			sv_name;	/* service name */
@@ -327,12 +323,7 @@ static inline bool svc_thread_should_stop(struct svc_rqst *rqstp)
  */
 static inline void svc_thread_init_status(struct svc_rqst *rqstp, int err)
 {
-	rqstp->rq_err = err;
-	/* memory barrier ensures assignment to error above is visible before
-	 * waitqueue_active() test below completes.
-	 */
-	smp_mb();
-	wake_up_var(&rqstp->rq_err);
+	store_release_wake_up(&rqstp->rq_err, err);
 	if (err)
 		kthread_exit(1);
 }
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 0981e35a9fed..72be60952579 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -99,8 +99,30 @@ enum {
 	XPT_HANDSHAKE,		/* xprt requests a handshake */
 	XPT_TLS_SESSION,	/* transport-layer security established */
 	XPT_PEER_AUTH,		/* peer has been authenticated */
+	XPT_PEER_VALID,		/* peer has presented a filehandle that
+				 * it has access to.  It is NOT counted
+				 * in ->sv_tmpcnt.
+				 */
 };
 
+/*
+ * Maximum number of "tmp" connections - those without XPT_PEER_VALID -
+ * permitted on any service.
+ */
+#define XPT_MAX_TMP_CONN	64
+
+static inline void svc_xprt_set_valid(struct svc_xprt *xpt)
+{
+	if (test_bit(XPT_TEMP, &xpt->xpt_flags) &&
+	    !test_and_set_bit(XPT_PEER_VALID, &xpt->xpt_flags)) {
+		struct svc_serv *serv = xpt->xpt_server;
+
+		spin_lock(&serv->sv_lock);
+		serv->sv_tmpcnt -= 1;
+		spin_unlock(&serv->sv_lock);
+	}
+}
+
 static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
 {
 	spin_lock(&xpt->xpt_lock);
diff --git a/include/linux/sunrpc/xdrgen/nfs4_1.h b/include/linux/sunrpc/xdrgen/nfs4_1.h
new file mode 100644
index 000000000000..cf21a14aa885
--- /dev/null
+++ b/include/linux/sunrpc/xdrgen/nfs4_1.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Generated by xdrgen. Manual edits will be lost. */
+/* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
+/* XDR specification modification time: Mon Oct 14 09:10:13 2024 */
+
+#ifndef _LINUX_XDRGEN_NFS4_1_DEF_H
+#define _LINUX_XDRGEN_NFS4_1_DEF_H
+
+#include <linux/types.h>
+#include <linux/sunrpc/xdrgen/_defs.h>
+
+typedef s64 int64_t;
+
+typedef u32 uint32_t;
+
+typedef struct {
+	u32 count;
+	uint32_t *element;
+} bitmap4;
+
+struct nfstime4 {
+	int64_t seconds;
+	uint32_t nseconds;
+};
+
+typedef bool fattr4_offline;
+
+enum { FATTR4_OFFLINE = 83 };
+
+struct open_arguments4 {
+	bitmap4 oa_share_access;
+	bitmap4 oa_share_deny;
+	bitmap4 oa_share_access_want;
+	bitmap4 oa_open_claim;
+	bitmap4 oa_create_mode;
+};
+
+enum open_args_share_access4 {
+	OPEN_ARGS_SHARE_ACCESS_READ = 1,
+	OPEN_ARGS_SHARE_ACCESS_WRITE = 2,
+	OPEN_ARGS_SHARE_ACCESS_BOTH = 3,
+};
+typedef enum open_args_share_access4 open_args_share_access4;
+
+enum open_args_share_deny4 {
+	OPEN_ARGS_SHARE_DENY_NONE = 0,
+	OPEN_ARGS_SHARE_DENY_READ = 1,
+	OPEN_ARGS_SHARE_DENY_WRITE = 2,
+	OPEN_ARGS_SHARE_DENY_BOTH = 3,
+};
+typedef enum open_args_share_deny4 open_args_share_deny4;
+
+enum open_args_share_access_want4 {
+	OPEN_ARGS_SHARE_ACCESS_WANT_ANY_DELEG = 3,
+	OPEN_ARGS_SHARE_ACCESS_WANT_NO_DELEG = 4,
+	OPEN_ARGS_SHARE_ACCESS_WANT_CANCEL = 5,
+	OPEN_ARGS_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 17,
+	OPEN_ARGS_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 18,
+	OPEN_ARGS_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 20,
+	OPEN_ARGS_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 21,
+};
+typedef enum open_args_share_access_want4 open_args_share_access_want4;
+
+enum open_args_open_claim4 {
+	OPEN_ARGS_OPEN_CLAIM_NULL = 0,
+	OPEN_ARGS_OPEN_CLAIM_PREVIOUS = 1,
+	OPEN_ARGS_OPEN_CLAIM_DELEGATE_CUR = 2,
+	OPEN_ARGS_OPEN_CLAIM_DELEGATE_PREV = 3,
+	OPEN_ARGS_OPEN_CLAIM_FH = 4,
+	OPEN_ARGS_OPEN_CLAIM_DELEG_CUR_FH = 5,
+	OPEN_ARGS_OPEN_CLAIM_DELEG_PREV_FH = 6,
+};
+typedef enum open_args_open_claim4 open_args_open_claim4;
+
+enum open_args_createmode4 {
+	OPEN_ARGS_CREATEMODE_UNCHECKED4 = 0,
+	OPEN_ARGS_CREATE_MODE_GUARDED = 1,
+	OPEN_ARGS_CREATEMODE_EXCLUSIVE4 = 2,
+	OPEN_ARGS_CREATE_MODE_EXCLUSIVE4_1 = 3,
+};
+typedef enum open_args_createmode4 open_args_createmode4;
+
+typedef struct open_arguments4 fattr4_open_arguments;
+
+enum { FATTR4_OPEN_ARGUMENTS = 86 };
+
+enum { OPEN4_RESULT_NO_OPEN_STATEID = 0x00000010 };
+
+typedef struct nfstime4 fattr4_time_deleg_access;
+
+typedef struct nfstime4 fattr4_time_deleg_modify;
+
+enum { FATTR4_TIME_DELEG_ACCESS = 84 };
+
+enum { FATTR4_TIME_DELEG_MODIFY = 85 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_DELEG_MASK = 0xFF00 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_NO_PREFERENCE = 0x0000 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_READ_DELEG = 0x0100 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG = 0x0200 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_ANY_DELEG = 0x0300 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_NO_DELEG = 0x0400 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_CANCEL = 0x0500 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_SIGNAL_DELEG_WHEN_RESRC_AVAIL = 0x10000 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_PUSH_DELEG_WHEN_UNCONTENDED = 0x20000 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS = 0x100000 };
+
+enum { OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION = 0x200000 };
+
+enum open_delegation_type4 {
+	OPEN_DELEGATE_NONE = 0,
+	OPEN_DELEGATE_READ = 1,
+	OPEN_DELEGATE_WRITE = 2,
+	OPEN_DELEGATE_NONE_EXT = 3,
+	OPEN_DELEGATE_READ_ATTRS_DELEG = 4,
+	OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5,
+};
+typedef enum open_delegation_type4 open_delegation_type4;
+
+#define NFS4_int64_t_sz                 \
+	(XDR_hyper)
+#define NFS4_uint32_t_sz                \
+	(XDR_unsigned_int)
+#define NFS4_bitmap4_sz                 (XDR_unsigned_int)
+#define NFS4_nfstime4_sz                \
+	(NFS4_int64_t_sz + NFS4_uint32_t_sz)
+#define NFS4_fattr4_offline_sz          \
+	(XDR_bool)
+#define NFS4_open_arguments4_sz         \
+	(NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz + NFS4_bitmap4_sz)
+#define NFS4_open_args_share_access4_sz (XDR_int)
+#define NFS4_open_args_share_deny4_sz   (XDR_int)
+#define NFS4_open_args_share_access_want4_sz (XDR_int)
+#define NFS4_open_args_open_claim4_sz   (XDR_int)
+#define NFS4_open_args_createmode4_sz   (XDR_int)
+#define NFS4_fattr4_open_arguments_sz   \
+	(NFS4_open_arguments4_sz)
+#define NFS4_fattr4_time_deleg_access_sz \
+	(NFS4_nfstime4_sz)
+#define NFS4_fattr4_time_deleg_modify_sz \
+	(NFS4_nfstime4_sz)
+#define NFS4_open_delegation_type4_sz   (XDR_int)
+
+#endif /* _LINUX_XDRGEN_NFS4_1_DEF_H */
diff --git a/include/linux/sunrpc/xprtmultipath.h b/include/linux/sunrpc/xprtmultipath.h
index c0514c684b2c..e411368cdacf 100644
--- a/include/linux/sunrpc/xprtmultipath.h
+++ b/include/linux/sunrpc/xprtmultipath.h
@@ -75,7 +75,6 @@ extern struct rpc_xprt_switch *xprt_iter_xchg_switch(
 		struct rpc_xprt_switch *newswitch);
 
 extern struct rpc_xprt *xprt_iter_xprt(struct rpc_xprt_iter *xpi);
-extern struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi);
 extern struct rpc_xprt *xprt_iter_get_next(struct rpc_xprt_iter *xpi);
 
 extern bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index f3e0ac20c2e8..b13b72645db3 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -219,10 +219,10 @@ enum {
 	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
 	SWP_SYNCHRONOUS_IO = (1 << 12),	/* synchronous IO is efficient */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 14),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
+#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10)
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
 /* Bit flag in swap_map */
@@ -257,18 +257,27 @@ struct swap_cluster_info {
 	u8 order;
 	struct list_head list;
 };
-#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */
-#define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */
-#define CLUSTER_FLAG_FULL 8 /* This cluster is on full list */
+
+/* All on-list cluster must have a non-zero flag. */
+enum swap_cluster_flags {
+	CLUSTER_FLAG_NONE = 0, /* For temporary off-list cluster */
+	CLUSTER_FLAG_FREE,
+	CLUSTER_FLAG_NONFULL,
+	CLUSTER_FLAG_FRAG,
+	/* Clusters with flags above are allocatable */
+	CLUSTER_FLAG_USABLE = CLUSTER_FLAG_FRAG,
+	CLUSTER_FLAG_FULL,
+	CLUSTER_FLAG_DISCARD,
+	CLUSTER_FLAG_MAX,
+};
 
 /*
  * The first page in the swap file is the swap header, which is always marked
  * bad to prevent it from being allocated as an entry. This also prevents the
  * cluster to which it belongs being marked free. Therefore 0 is safe to use as
- * a sentinel to indicate next is not valid in percpu_cluster.
+ * a sentinel to indicate an entry is not valid.
  */
-#define SWAP_NEXT_INVALID	0
+#define SWAP_ENTRY_INVALID	0
 
 #ifdef CONFIG_THP_SWAP
 #define SWAP_NR_ORDERS		(PMD_ORDER + 1)
@@ -282,6 +291,7 @@ struct swap_cluster_info {
  * throughput.
  */
 struct percpu_cluster {
+	local_lock_t lock; /* Protect the percpu_cluster above */
 	unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
@@ -304,15 +314,12 @@ struct swap_info_struct {
 					/* list of cluster that contains at least one free slot */
 	struct list_head frag_clusters[SWAP_NR_ORDERS];
 					/* list of cluster that are fragmented or contented */
-	unsigned int frag_cluster_nr[SWAP_NR_ORDERS];
-	unsigned int lowest_bit;	/* index of first free in swap_map */
-	unsigned int highest_bit;	/* index of last free in swap_map */
+	atomic_long_t frag_cluster_nr[SWAP_NR_ORDERS];
 	unsigned int pages;		/* total of usable pages of swap */
-	unsigned int inuse_pages;	/* number of those currently in use */
-	unsigned int cluster_next;	/* likely index for next allocation */
-	unsigned int cluster_nr;	/* countdown to next cluster search */
-	unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
+	atomic_long_t inuse_pages;	/* number of those currently in use */
 	struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
+	struct percpu_cluster *global_cluster; /* Use one global cluster for rotating device */
+	spinlock_t global_cluster_lock;	/* Serialize usage of global cluster */
 	struct rb_root swap_extent_root;/* root of the swap extent rbtree */
 	struct block_device *bdev;	/* swap device or bdev of swap file */
 	struct file *swap_file;		/* seldom referenced */
diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
index ae73a87775b3..b5ec038069da 100644
--- a/include/linux/swap_cgroup.h
+++ b/include/linux/swap_cgroup.h
@@ -6,10 +6,8 @@
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP)
 
-extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new);
-extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
-					 unsigned int nr_ents);
+extern void swap_cgroup_record(struct folio *folio, swp_entry_t ent);
+extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents);
 extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
 extern int swap_cgroup_swapon(int type, unsigned long max_pages);
 extern void swap_cgroup_swapoff(int type);
@@ -17,8 +15,12 @@ extern void swap_cgroup_swapoff(int type);
 #else
 
 static inline
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
-				  unsigned int nr_ents)
+void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
+{
+}
+
+static inline
+unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents)
 {
 	return 0;
 }
diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h
index 15adfb8c813a..840aec3523b2 100644
--- a/include/linux/swap_slots.h
+++ b/include/linux/swap_slots.h
@@ -16,15 +16,12 @@ struct swap_slots_cache {
 	swp_entry_t	*slots;
 	int		nr;
 	int		cur;
-	spinlock_t	free_lock;  /* protects slots_ret, n_ret */
-	swp_entry_t	*slots_ret;
 	int		n_ret;
 };
 
 void disable_swap_slots_cache_lock(void);
 void reenable_swap_slots_cache_unlock(void);
 void enable_swap_slots_cache(void);
-void free_swap_slot(swp_entry_t entry);
 
 extern bool swap_slot_cache_enabled;
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 0f2fcd244523..18f7e1fd093c 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -293,7 +293,7 @@ __ATTRIBUTE_GROUPS(_name)
 
 #define BIN_ATTRIBUTE_GROUPS(_name)				\
 static const struct attribute_group _name##_group = {		\
-	.bin_attrs = _name##_attrs,				\
+	.bin_attrs_new = _name##_attrs,				\
 };								\
 __ATTRIBUTE_GROUPS(_name)
 
@@ -511,7 +511,7 @@ __printf(3, 4)
 int sysfs_emit_at(char *buf, int at, const char *fmt, ...);
 
 ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj,
-				   struct bin_attribute *attr, char *buf,
+				   const struct bin_attribute *attr, char *buf,
 				   loff_t off, size_t count);
 
 #else /* CONFIG_SYSFS */
@@ -774,7 +774,7 @@ static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...)
 
 static inline ssize_t sysfs_bin_attr_simple_read(struct file *file,
 						 struct kobject *kobj,
-						 struct bin_attribute *attr,
+						 const struct bin_attribute *attr,
 						 char *buf, loff_t off,
 						 size_t count)
 {
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 2964171856e0..0646804860ff 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -19,9 +19,6 @@ enum task_work_notify_mode {
 	TWA_SIGNAL,
 	TWA_SIGNAL_NO_IPI,
 	TWA_NMI_CURRENT,
-
-	TWA_FLAGS = 0xff00,
-	TWAF_NO_ALLOC = 0x0100,
 };
 
 static inline bool task_work_pending(struct task_struct *task)
diff --git a/include/linux/time64.h b/include/linux/time64.h
index f1bcea8c124a..9934331c7b86 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -49,6 +49,11 @@ static inline int timespec64_equal(const struct timespec64 *a,
 	return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec);
 }
 
+static inline bool timespec64_is_epoch(const struct timespec64 *ts)
+{
+	return ts->tv_sec == 0 && ts->tv_nsec == 0;
+}
+
 /*
  * lhs < rhs:  return <0
  * lhs == rhs: return 0
diff --git a/include/linux/types.h b/include/linux/types.h
index 2d7b9ae8714c..1c509ce8f7f6 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -43,7 +43,7 @@ typedef unsigned long		uintptr_t;
 typedef long			intptr_t;
 
 #ifdef CONFIG_HAVE_UID16
-/* This is defined by include/asm-{arch}/posix_types.h */
+/* This is defined by arch/{arch}/include/asm/posix_types.h */
 typedef __kernel_old_uid_t	old_uid_t;
 typedef __kernel_old_gid_t	old_gid_t;
 #endif /* CONFIG_UID16 */
diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h
index d50098fb16b5..3068c3084eb6 100644
--- a/include/linux/usb/pd.h
+++ b/include/linux/usb/pd.h
@@ -33,7 +33,9 @@ enum pd_ctrl_msg_type {
 	PD_CTRL_FR_SWAP = 19,
 	PD_CTRL_GET_PPS_STATUS = 20,
 	PD_CTRL_GET_COUNTRY_CODES = 21,
-	/* 22-31 Reserved */
+	/* 22-23 Reserved */
+	PD_CTRL_GET_REVISION = 24,
+	/* 25-31 Reserved */
 };
 
 enum pd_data_msg_type {
@@ -46,7 +48,9 @@ enum pd_data_msg_type {
 	PD_DATA_ALERT = 6,
 	PD_DATA_GET_COUNTRY_INFO = 7,
 	PD_DATA_ENTER_USB = 8,
-	/* 9-14 Reserved */
+	/* 9-11 Reserved */
+	PD_DATA_REVISION = 12,
+	/* 13-14 Reserved */
 	PD_DATA_VENDOR_DEF = 15,
 	/* 16-31 Reserved */
 };
@@ -453,6 +457,20 @@ static inline unsigned int rdo_max_power(u32 rdo)
 #define EUDO_TBT_SUPPORT		BIT(14)
 #define EUDO_HOST_PRESENT		BIT(13)
 
+/*
+ * Request Message Data Object (PD Revision 3.1+ only)
+ * --------
+ * <31:28> :: Revision Major
+ * <27:24> :: Revision Minor
+ * <23:20> :: Version Major
+ * <19:16> :: Version Minor
+ * <15:0>  :: Reserved, Shall be set to zero
+ */
+
+#define RMDO(rev_maj, rev_min, ver_maj, ver_min)			\
+	(((rev_maj) & 0xf) << 28 | ((rev_min) & 0xf) << 24 |		\
+	 ((ver_maj) & 0xf) << 20 | ((ver_min) & 0xf) << 16)
+
 /* USB PD timers and counters */
 #define PD_T_NO_RESPONSE	5000	/* 4.5 - 5.5 seconds */
 #define PD_T_DB_DETECT		10000	/* 10 - 15 seconds */
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index e4de6bc1f69b..0fa9885a1038 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -223,7 +223,6 @@ extern struct usb_phy *devm_usb_get_phy_by_phandle(struct device *dev,
 extern struct usb_phy *devm_usb_get_phy_by_node(struct device *dev,
 	struct device_node *node, struct notifier_block *nb);
 extern void usb_put_phy(struct usb_phy *);
-extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x);
 extern void usb_phy_set_event(struct usb_phy *x, unsigned long event);
 extern void usb_phy_set_charger_current(struct usb_phy *usb_phy,
 					unsigned int mA);
@@ -259,10 +258,6 @@ static inline void usb_put_phy(struct usb_phy *x)
 {
 }
 
-static inline void devm_usb_put_phy(struct device *dev, struct usb_phy *x)
-{
-}
-
 static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event)
 {
 }
diff --git a/include/linux/usb/storage.h b/include/linux/usb/storage.h
index 8539956bc2be..51be3bb8fccb 100644
--- a/include/linux/usb/storage.h
+++ b/include/linux/usb/storage.h
@@ -82,4 +82,12 @@ struct bulk_cs_wrap {
 #define US_BULK_RESET_REQUEST   0xff
 #define US_BULK_GET_MAX_LUN     0xfe
 
+/*
+ * If 4 LUNs are supported then the LUNs would be
+ * numbered from 0 to 3, and the return value for
+ * US_BULK_GET_MAX_LUN request would be 3. The valid
+ * LUN field is 4 bits wide, the upper limit is 0x0f.
+ */
+#define US_BULK_MAX_LUN_LIMIT   0x0f
+
 #endif
diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h
index 061da9546a81..b22e659f81ba 100644
--- a/include/linux/usb/tcpm.h
+++ b/include/linux/usb/tcpm.h
@@ -163,7 +163,8 @@ struct tcpc_dev {
 	void (*frs_sourcing_vbus)(struct tcpc_dev *dev);
 	int (*enable_auto_vbus_discharge)(struct tcpc_dev *dev, bool enable);
 	int (*set_auto_vbus_discharge_threshold)(struct tcpc_dev *dev, enum typec_pwr_opmode mode,
-						 bool pps_active, u32 requested_vbus_voltage);
+						 bool pps_active, u32 requested_vbus_voltage,
+						 u32 pps_apdo_min_voltage);
 	bool (*is_vbus_vsafe0v)(struct tcpc_dev *dev);
 	void (*set_partner_usb_comm_capable)(struct tcpc_dev *dev, bool enable);
 	void (*check_contaminant)(struct tcpc_dev *dev);
diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h
index d616b8807000..252af3f77039 100644
--- a/include/linux/usb/typec.h
+++ b/include/linux/usb/typec.h
@@ -140,6 +140,7 @@ int typec_cable_set_identity(struct typec_cable *cable);
  * @mode: Index of the Mode
  * @vdo: VDO returned by Discover Modes USB PD command
  * @roles: Only for ports. DRP if the mode is available in both roles
+ * @inactive: Only for ports. Make this port inactive (default is active).
  *
  * Description of an Alternate Mode which a connector, cable plug or partner
  * supports.
@@ -150,6 +151,7 @@ struct typec_altmode_desc {
 	u32			vdo;
 	/* Only used with ports */
 	enum typec_port_data	roles;
+	bool			inactive;
 };
 
 void typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision);
diff --git a/include/linux/usb/typec_tbt.h b/include/linux/usb/typec_tbt.h
index fa97d7e00f5c..55dcea12082c 100644
--- a/include/linux/usb/typec_tbt.h
+++ b/include/linux/usb/typec_tbt.h
@@ -44,6 +44,7 @@ struct typec_thunderbolt_data {
 
 #define   TBT_GEN3_NON_ROUNDED                 0
 #define   TBT_GEN3_GEN4_ROUNDED_NON_ROUNDED    1
+#define TBT_CABLE_ROUNDED		BIT(19)
 #define TBT_CABLE_OPTICAL		BIT(21)
 #define TBT_CABLE_RETIMER		BIT(22)
 #define TBT_CABLE_LINK_TRAINING		BIT(23)
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index dd88682e27e3..4d16c13d0df5 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -190,6 +190,8 @@ int virtio_device_freeze(struct virtio_device *dev);
 int virtio_device_restore(struct virtio_device *dev);
 #endif
 void virtio_reset_device(struct virtio_device *dev);
+int virtio_device_reset_prepare(struct virtio_device *dev);
+int virtio_device_reset_done(struct virtio_device *dev);
 
 size_t virtio_max_dma_size(const struct virtio_device *vdev);
 
@@ -214,6 +216,10 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
  *    changes; may be called in interrupt context.
  * @freeze: optional function to call during suspend/hibernation.
  * @restore: optional function to call on resume.
+ * @reset_prepare: optional function to call when a transport specific reset
+ *    occurs.
+ * @reset_done: optional function to call after transport specific reset
+ *    operation has finished.
  */
 struct virtio_driver {
 	struct device_driver driver;
@@ -229,6 +235,8 @@ struct virtio_driver {
 	void (*config_changed)(struct virtio_device *dev);
 	int (*freeze)(struct virtio_device *dev);
 	int (*restore)(struct virtio_device *dev);
+	int (*reset_prepare)(struct virtio_device *dev);
+	int (*reset_done)(struct virtio_device *dev);
 };
 
 #define drv_to_virtio(__drv)	container_of_const(__drv, struct virtio_driver, driver)
diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h
index 6fb663b36f72..60c9eacd2cf3 100644
--- a/include/linux/vmw_vmci_defs.h
+++ b/include/linux/vmw_vmci_defs.h
@@ -431,11 +431,11 @@ enum {
 	((((_p)[0] & 0xFF) << 24) | (((_p)[1] & 0xFF) << 16) | ((_p)[2]))
 
 /*
- * The VMCI IOCTLs.  We use identity code 7, as noted in ioctl-number.h, and
- * we start at sequence 9f.  This gives us the same values that our shipping
- * products use, starting at 1951, provided we leave out the direction and
- * structure size.  Note that VMMon occupies the block following us, starting
- * at 2001.
+ * The VMCI IOCTLs.  We use identity code 7, as noted in ioctl-number.rst,
+ * and we start at sequence 9f.  This gives us the same values that our
+ * shipping products use, starting at 1951, provided we leave out the
+ * direction and structure size.  Note that VMMon occupies the block
+ * following us, starting at 2001.
  */
 #define IOCTL_VMCI_VERSION			_IO(7, 0x9f)	/* 1951 */
 #define IOCTL_VMCI_INIT_CONTEXT			_IO(7, 0xa0)
@@ -453,9 +453,7 @@ enum {
 #define IOCTL_VMCI_CTX_GET_CPT_STATE		_IO(7, 0xb1)
 #define IOCTL_VMCI_CTX_SET_CPT_STATE		_IO(7, 0xb2)
 #define IOCTL_VMCI_GET_CONTEXT_ID		_IO(7, 0xb3)
-#define IOCTL_VMCI_SOCKETS_VERSION		_IO(7, 0xb4)
-#define IOCTL_VMCI_SOCKETS_GET_AF_VALUE		_IO(7, 0xb8)
-#define IOCTL_VMCI_SOCKETS_GET_LOCAL_CID	_IO(7, 0xb9)
+/*IOCTL_VM_SOCKETS_GET_LOCAL_CID		_IO(7, 0xb9)*/
 #define IOCTL_VMCI_SET_NOTIFY			_IO(7, 0xcb)	/* 1995 */
 /*IOCTL_VMMON_START				_IO(7, 0xd1)*/	/* 2001 */
 
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index ed4cd114180a..7f405672b089 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -237,7 +237,6 @@ struct page_pool {
 	struct {
 		struct hlist_node list;
 		u64 detach_time;
-		u32 napi_id;
 		u32 id;
 	} user;
 };
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d635c5b47eba..d48c657191cd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -851,7 +851,7 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 }
 
 static inline void _bstats_update(struct gnet_stats_basic_sync *bstats,
-				  __u64 bytes, __u32 packets)
+				  __u64 bytes, __u64 packets)
 {
 	u64_stats_update_begin(&bstats->syncp);
 	u64_stats_add(&bstats->bytes, bytes);
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4b0677e48190..ed4b83696c77 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1268,9 +1268,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir,
 
 	if (xo) {
 		x = xfrm_input_state(skb);
-		if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
-			return (xo->flags & CRYPTO_DONE) &&
-			       (xo->status & CRYPTO_SUCCESS);
+		if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
+			bool check = (xo->flags & CRYPTO_DONE) &&
+				     (xo->status & CRYPTO_SUCCESS);
+
+			/* The packets here are plain ones and secpath was
+			 * needed to indicate that hardware already handled
+			 * them and there is no need to do nothing in addition.
+			 *
+			 * Consume secpath which was set by drivers.
+			 */
+			secpath_reset(skb);
+			return check;
+		}
 	}
 
 	return __xfrm_check_nopolicy(net, skb, dir) ||
diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h
index 9705b2a98e49..510c88bfabd4 100644
--- a/include/rv/da_monitor.h
+++ b/include/rv/da_monitor.h
@@ -14,6 +14,7 @@
 #include <rv/automata.h>
 #include <linux/rv.h>
 #include <linux/bug.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_RV_REACTORS
 
@@ -324,10 +325,13 @@ static inline struct da_monitor *da_get_monitor_##name(struct task_struct *tsk)
 static void da_monitor_reset_all_##name(void)							\
 {												\
 	struct task_struct *g, *p;								\
+	int cpu;										\
 												\
 	read_lock(&tasklist_lock);								\
 	for_each_process_thread(g, p)								\
 		da_monitor_reset_##name(da_get_monitor_##name(p));				\
+	for_each_present_cpu(cpu)								\
+		da_monitor_reset_##name(da_get_monitor_##name(idle_task(cpu)));			\
 	read_unlock(&tasklist_lock);								\
 }												\
 												\
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index 4a9b4169e081..183d9fd50d2d 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -963,7 +963,7 @@ int fc_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 int fc_eh_abort(struct scsi_cmnd *);
 int fc_eh_device_reset(struct scsi_cmnd *);
 int fc_eh_host_reset(struct scsi_cmnd *);
-int fc_slave_alloc(struct scsi_device *);
+int fc_sdev_init(struct scsi_device *);
 
 /*
  * ELS/CT interface
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 1324068dd950..ba460b6c0374 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -683,8 +683,7 @@ int sas_phy_reset(struct sas_phy *phy, int hard_reset);
 int sas_phy_enable(struct sas_phy *phy, int enable);
 extern int sas_queuecommand(struct Scsi_Host *, struct scsi_cmnd *);
 extern int sas_target_alloc(struct scsi_target *);
-int sas_device_configure(struct scsi_device *dev,
-		struct queue_limits *lim);
+int sas_sdev_configure(struct scsi_device *dev, struct queue_limits *lim);
 extern int sas_change_queue_depth(struct scsi_device *, int new_depth);
 extern int sas_bios_param(struct scsi_device *, struct block_device *,
 			  sector_t capacity, int *hsc);
@@ -703,7 +702,7 @@ int sas_eh_device_reset_handler(struct scsi_cmnd *cmd);
 int sas_eh_target_reset_handler(struct scsi_cmnd *cmd);
 
 extern void sas_target_destroy(struct scsi_target *);
-extern int sas_slave_alloc(struct scsi_device *);
+extern int sas_sdev_init(struct scsi_device *);
 extern int sas_ioctl(struct scsi_device *sdev, unsigned int cmd,
 		     void __user *arg);
 extern int sas_drain_work(struct sas_ha_struct *ha);
@@ -750,8 +749,8 @@ void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event,
 #endif
 
 #define LIBSAS_SHT_BASE			_LIBSAS_SHT_BASE		\
-	.device_configure		= sas_device_configure,		\
-	.slave_alloc			= sas_slave_alloc,		\
+	.sdev_configure			= sas_sdev_configure,		\
+	.sdev_init			= sas_sdev_init,		\
 
 #define LIBSAS_SHT_BASE_NO_SLAVE_INIT	_LIBSAS_SHT_BASE
 
diff --git a/include/scsi/scsi_bsg_iscsi.h b/include/scsi/scsi_bsg_iscsi.h
index 9b1f0f424a79..a569c35b258d 100644
--- a/include/scsi/scsi_bsg_iscsi.h
+++ b/include/scsi/scsi_bsg_iscsi.h
@@ -59,7 +59,7 @@ struct iscsi_bsg_host_vendor {
  */
 struct iscsi_bsg_host_vendor_reply {
 	/* start of vendor response area */
-	uint32_t vendor_rsp[0];
+	DECLARE_FLEX_ARRAY(uint32_t, vendor_rsp);
 };
 
 
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 9c540f5468eb..7acd0ec82bb0 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -155,7 +155,7 @@ struct scsi_device {
 
 	blist_flags_t		sdev_bflags; /* black/white flags as also found in
 				 * scsi_devinfo.[hc]. For now used only to
-				 * pass settings from slave_alloc to scsi
+				 * pass settings from sdev_init to scsi
 				 * core. */
 	unsigned int eh_timeout; /* Error handling timeout */
 
@@ -357,7 +357,7 @@ struct scsi_target {
 	atomic_t		target_blocked;
 
 	/*
-	 * LLDs should set this in the slave_alloc host template callout.
+	 * LLDs should set this in the sdev_init host template callout.
 	 * If set to zero then there is not limit.
 	 */
 	unsigned int		can_queue;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 02823d6af37d..26bc23419cfd 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -168,20 +168,20 @@ struct scsi_host_template {
 	 * Return values: 0 on success, non-0 on failure
 	 *
 	 * Deallocation:  If we didn't find any devices at this ID, you will
-	 * get an immediate call to slave_destroy().  If we find something
-	 * here then you will get a call to slave_configure(), then the
+	 * get an immediate call to sdev_destroy().  If we find something
+	 * here then you will get a call to sdev_configure(), then the
 	 * device will be used for however long it is kept around, then when
 	 * the device is removed from the system (or * possibly at reboot
-	 * time), you will then get a call to slave_destroy().  This is
-	 * assuming you implement slave_configure and slave_destroy.
+	 * time), you will then get a call to sdev_destroy().  This is
+	 * assuming you implement sdev_configure and sdev_destroy.
 	 * However, if you allocate memory and hang it off the device struct,
-	 * then you must implement the slave_destroy() routine at a minimum
+	 * then you must implement the sdev_destroy() routine at a minimum
 	 * in order to avoid leaking memory
 	 * each time a device is tore down.
 	 *
 	 * Status: OPTIONAL
 	 */
-	int (* slave_alloc)(struct scsi_device *);
+	int (* sdev_init)(struct scsi_device *);
 
 	/*
 	 * Once the device has responded to an INQUIRY and we know the
@@ -206,28 +206,24 @@ struct scsi_host_template {
 	 *     specific setup basis...
 	 * 6.  Return 0 on success, non-0 on error.  The device will be marked
 	 *     as offline on error so that no access will occur.  If you return
-	 *     non-0, your slave_destroy routine will never get called for this
+	 *     non-0, your sdev_destroy routine will never get called for this
 	 *     device, so don't leave any loose memory hanging around, clean
 	 *     up after yourself before returning non-0
 	 *
 	 * Status: OPTIONAL
-	 *
-	 * Note: slave_configure is the legacy version, use device_configure for
-	 * all new code.  A driver must never define both.
 	 */
-	int (* device_configure)(struct scsi_device *, struct queue_limits *lim);
-	int (* slave_configure)(struct scsi_device *);
+	int (* sdev_configure)(struct scsi_device *, struct queue_limits *lim);
 
 	/*
 	 * Immediately prior to deallocating the device and after all activity
 	 * has ceased the mid layer calls this point so that the low level
 	 * driver may completely detach itself from the scsi device and vice
 	 * versa.  The low level driver is responsible for freeing any memory
-	 * it allocated in the slave_alloc or slave_configure calls. 
+	 * it allocated in the sdev_init or sdev_configure calls.
 	 *
 	 * Status: OPTIONAL
 	 */
-	void (* slave_destroy)(struct scsi_device *);
+	void (* sdev_destroy)(struct scsi_device *);
 
 	/*
 	 * Before the mid layer attempts to scan for a new device attached
@@ -601,7 +597,7 @@ struct Scsi_Host {
 	 * have some way of identifying each detected host adapter properly
 	 * and uniquely.  For hosts that do not support more than one card
 	 * in the system at one time, this does not need to be set.  It is
-	 * initialized to 0 in scsi_register.
+	 * initialized to 0 in scsi_host_alloc.
 	 */
 	unsigned int unique_id;
 
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index bd1243657c01..76de2b662f4f 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -447,10 +447,6 @@ extern int iscsi_add_session(struct iscsi_cls_session *session,
 			     unsigned int target_id);
 extern int iscsi_session_event(struct iscsi_cls_session *session,
 			       enum iscsi_uevent_e event);
-extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost,
-						struct iscsi_transport *t,
-						int dd_size,
-						unsigned int target_id);
 extern void iscsi_force_destroy_session(struct iscsi_cls_session *session);
 extern void iscsi_remove_session(struct iscsi_cls_session *session);
 extern void iscsi_free_session(struct iscsi_cls_session *session);
@@ -497,8 +493,8 @@ extern void iscsi_destroy_all_flashnode(struct Scsi_Host *shost);
 extern int iscsi_flashnode_bus_match(struct device *dev,
 				     const struct device_driver *drv);
 extern struct device *
-iscsi_find_flashnode_sess(struct Scsi_Host *shost, void *data,
-			  int (*fn)(struct device *dev, void *data));
+iscsi_find_flashnode_sess(struct Scsi_Host *shost, const void *data,
+			  device_match_t fn);
 extern struct device *
 iscsi_find_flashnode_conn(struct iscsi_bus_flash_session *fnode_sess);
 
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 2851c823095b..eb3b2f1326b1 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -1119,11 +1119,11 @@ TRACE_EVENT(f2fs_reserve_new_blocks,
 		(unsigned long long)__entry->count)
 );
 
-DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
+DECLARE_EVENT_CLASS(f2fs__submit_folio_bio,
 
-	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+	TP_PROTO(struct folio *folio, struct f2fs_io_info *fio),
 
-	TP_ARGS(page, fio),
+	TP_ARGS(folio, fio),
 
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -1138,9 +1138,9 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= page_file_mapping(page)->host->i_sb->s_dev;
-		__entry->ino		= page_file_mapping(page)->host->i_ino;
-		__entry->index		= page->index;
+		__entry->dev		= folio->mapping->host->i_sb->s_dev;
+		__entry->ino		= folio->mapping->host->i_ino;
+		__entry->index		= folio->index;
 		__entry->old_blkaddr	= fio->old_blkaddr;
 		__entry->new_blkaddr	= fio->new_blkaddr;
 		__entry->op		= fio->op;
@@ -1149,7 +1149,7 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__entry->type		= fio->type;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
+	TP_printk("dev = (%d,%d), ino = %lu, folio_index = 0x%lx, "
 		"oldaddr = 0x%llx, newaddr = 0x%llx, rw = %s(%s), type = %s_%s",
 		show_dev_ino(__entry),
 		(unsigned long)__entry->index,
@@ -1160,22 +1160,22 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		show_block_type(__entry->type))
 );
 
-DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
+DEFINE_EVENT_CONDITION(f2fs__submit_folio_bio, f2fs_submit_folio_bio,
 
-	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+	TP_PROTO(struct folio *folio, struct f2fs_io_info *fio),
 
-	TP_ARGS(page, fio),
+	TP_ARGS(folio, fio),
 
-	TP_CONDITION(page->mapping)
+	TP_CONDITION(folio->mapping)
 );
 
-DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_write,
+DEFINE_EVENT_CONDITION(f2fs__submit_folio_bio, f2fs_submit_folio_write,
 
-	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+	TP_PROTO(struct folio *folio, struct f2fs_io_info *fio),
 
-	TP_ARGS(page, fio),
+	TP_ARGS(folio, fio),
 
-	TP_CONDITION(page->mapping)
+	TP_CONDITION(folio->mapping)
 );
 
 DECLARE_EVENT_CLASS(f2fs__bio,
@@ -1322,12 +1322,11 @@ DECLARE_EVENT_CLASS(f2fs__folio,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= folio_file_mapping(folio)->host->i_sb->s_dev;
-		__entry->ino	= folio_file_mapping(folio)->host->i_ino;
+		__entry->dev	= folio->mapping->host->i_sb->s_dev;
+		__entry->ino	= folio->mapping->host->i_ino;
 		__entry->type	= type;
-		__entry->dir	=
-			S_ISDIR(folio_file_mapping(folio)->host->i_mode);
-		__entry->index	= folio_index(folio);
+		__entry->dir	= S_ISDIR(folio->mapping->host->i_mode);
+		__entry->index	= folio->index;
 		__entry->dirty	= folio_test_dirty(folio);
 		__entry->uptodate = folio_test_uptodate(folio);
 	),
diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h
index bc2e3ad787b3..cf9f9faf8914 100644
--- a/include/trace/events/mmap_lock.h
+++ b/include/trace/events/mmap_lock.h
@@ -5,6 +5,7 @@
 #if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_MMAP_LOCK_H
 
+#include <linux/memcontrol.h>
 #include <linux/tracepoint.h>
 #include <linux/types.h>
 
@@ -12,64 +13,61 @@ struct mm_struct;
 
 DECLARE_EVENT_CLASS(mmap_lock,
 
-	TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write),
+	TP_PROTO(struct mm_struct *mm, bool write),
 
-	TP_ARGS(mm, memcg_path, write),
+	TP_ARGS(mm, write),
 
 	TP_STRUCT__entry(
 		__field(struct mm_struct *, mm)
-		__string(memcg_path, memcg_path)
+		__field(u64, memcg_id)
 		__field(bool, write)
 	),
 
 	TP_fast_assign(
 		__entry->mm = mm;
-		__assign_str(memcg_path);
+		__entry->memcg_id = cgroup_id_from_mm(mm);
 		__entry->write = write;
 	),
 
 	TP_printk(
-		"mm=%p memcg_path=%s write=%s",
-		__entry->mm,
-		__get_str(memcg_path),
+		"mm=%p memcg_id=%llu write=%s",
+		__entry->mm, __entry->memcg_id,
 		__entry->write ? "true" : "false"
 	)
 );
 
 #define DEFINE_MMAP_LOCK_EVENT(name)                                    \
 	DEFINE_EVENT(mmap_lock, name,                                   \
-		TP_PROTO(struct mm_struct *mm, const char *memcg_path,  \
-			bool write),                                    \
-		TP_ARGS(mm, memcg_path, write))
+		TP_PROTO(struct mm_struct *mm, bool write),		\
+		TP_ARGS(mm, write))
 
 DEFINE_MMAP_LOCK_EVENT(mmap_lock_start_locking);
 DEFINE_MMAP_LOCK_EVENT(mmap_lock_released);
 
 TRACE_EVENT(mmap_lock_acquire_returned,
 
-	TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write,
-		bool success),
+	TP_PROTO(struct mm_struct *mm, bool write, bool success),
 
-	TP_ARGS(mm, memcg_path, write, success),
+	TP_ARGS(mm, write, success),
 
 	TP_STRUCT__entry(
 		__field(struct mm_struct *, mm)
-		__string(memcg_path, memcg_path)
+		__field(u64, memcg_id)
 		__field(bool, write)
 		__field(bool, success)
 	),
 
 	TP_fast_assign(
 		__entry->mm = mm;
-		__assign_str(memcg_path);
+		__entry->memcg_id = cgroup_id_from_mm(mm);
 		__entry->write = write;
 		__entry->success = success;
 	),
 
 	TP_printk(
-		"mm=%p memcg_path=%s write=%s success=%s",
+		"mm=%p memcg_id=%llu write=%s success=%s",
 		__entry->mm,
-		__get_str(memcg_path),
+		__entry->memcg_id,
 		__entry->write ? "true" : "false",
 		__entry->success ? "true" : "false"
 	)
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index d36c857dd249..72fbfe3caeaf 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -179,7 +179,8 @@ TRACE_DEFINE_ENUM(___GFP_LAST_BIT);
 	DEF_PAGEFLAG_NAME(head),					\
 	DEF_PAGEFLAG_NAME(reclaim),					\
 	DEF_PAGEFLAG_NAME(swapbacked),					\
-	DEF_PAGEFLAG_NAME(unevictable)					\
+	DEF_PAGEFLAG_NAME(unevictable),					\
+	DEF_PAGEFLAG_NAME(dropbehind)					\
 IF_HAVE_PG_MLOCK(mlocked)						\
 IF_HAVE_PG_HWPOISON(hwpoison)						\
 IF_HAVE_PG_IDLE(idle)							\
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 2f119d18a061..cad50d91077e 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -219,6 +219,7 @@
 	EM(rxrpc_conn_get_conn_input,		"GET inp-conn") \
 	EM(rxrpc_conn_get_idle,			"GET idle    ") \
 	EM(rxrpc_conn_get_poke_abort,		"GET pk-abort") \
+	EM(rxrpc_conn_get_poke_secured,		"GET secured ") \
 	EM(rxrpc_conn_get_poke_timer,		"GET poke    ") \
 	EM(rxrpc_conn_get_service_conn,		"GET svc-conn") \
 	EM(rxrpc_conn_new_client,		"NEW client  ") \
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index efe5de6ce208..aaa4f3bc688b 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -411,13 +411,20 @@ struct drm_amdgpu_gem_userptr {
 /* GFX12 and later: */
 #define AMDGPU_TILING_GFX12_SWIZZLE_MODE_SHIFT			0
 #define AMDGPU_TILING_GFX12_SWIZZLE_MODE_MASK			0x7
-/* These are DCC recompression setting for memory management: */
+/* These are DCC recompression settings for memory management: */
 #define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_SHIFT	3
 #define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_MASK	0x3 /* 0:64B, 1:128B, 2:256B */
 #define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_SHIFT		5
 #define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_MASK		0x7 /* CB_COLOR0_INFO.NUMBER_TYPE */
 #define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_SHIFT		8
 #define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_MASK		0x3f /* [0:4]:CB_COLOR0_INFO.FORMAT, [5]:MM */
+/* When clearing the buffer or moving it from VRAM to GTT, don't compress and set DCC metadata
+ * to uncompressed. Set when parts of an allocation bypass DCC and read raw data. */
+#define AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE_SHIFT	14
+#define AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE_MASK	0x1
+/* bit gap */
+#define AMDGPU_TILING_GFX12_SCANOUT_SHIFT			63
+#define AMDGPU_TILING_GFX12_SCANOUT_MASK			0x1
 
 /* Set/Get helpers for tiling flags. */
 #define AMDGPU_TILING_SET(field, value) \
diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h
index 1990b5700f69..b08c7378164d 100644
--- a/include/uapi/linux/dm-ioctl.h
+++ b/include/uapi/linux/dm-ioctl.h
@@ -286,9 +286,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	48
+#define DM_VERSION_MINOR	49
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2023-03-01)"
+#define DM_VERSION_EXTRA	"-ioctl (2025-01-17)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index f1e99458e29e..5e0eb41d967e 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -220,6 +220,15 @@
  *
  *  7.41
  *  - add FUSE_ALLOW_IDMAP
+ *  7.42
+ *  - Add FUSE_OVER_IO_URING and all other io-uring related flags and data
+ *    structures:
+ *    - struct fuse_uring_ent_in_out
+ *    - struct fuse_uring_req_header
+ *    - struct fuse_uring_cmd_req
+ *    - FUSE_URING_IN_OUT_HEADER_SZ
+ *    - FUSE_URING_OP_IN_OUT_SZ
+ *    - enum fuse_uring_cmd
  */
 
 #ifndef _LINUX_FUSE_H
@@ -255,7 +264,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 41
+#define FUSE_KERNEL_MINOR_VERSION 42
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -425,6 +434,7 @@ struct fuse_file_lock {
  * FUSE_HAS_RESEND: kernel supports resending pending requests, and the high bit
  *		    of the request ID indicates resend requests
  * FUSE_ALLOW_IDMAP: allow creation of idmapped mounts
+ * FUSE_OVER_IO_URING: Indicate that client supports io-uring
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -471,6 +481,7 @@ struct fuse_file_lock {
 /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
 #define FUSE_DIRECT_IO_RELAX	FUSE_DIRECT_IO_ALLOW_MMAP
 #define FUSE_ALLOW_IDMAP	(1ULL << 40)
+#define FUSE_OVER_IO_URING	(1ULL << 41)
 
 /**
  * CUSE INIT request/reply flags
@@ -1206,4 +1217,67 @@ struct fuse_supp_groups {
 	uint32_t	groups[];
 };
 
+/**
+ * Size of the ring buffer header
+ */
+#define FUSE_URING_IN_OUT_HEADER_SZ 128
+#define FUSE_URING_OP_IN_OUT_SZ 128
+
+/* Used as part of the fuse_uring_req_header */
+struct fuse_uring_ent_in_out {
+	uint64_t flags;
+
+	/*
+	 * commit ID to be used in a reply to a ring request (see also
+	 * struct fuse_uring_cmd_req)
+	 */
+	uint64_t commit_id;
+
+	/* size of user payload buffer */
+	uint32_t payload_sz;
+	uint32_t padding;
+
+	uint64_t reserved;
+};
+
+/**
+ * Header for all fuse-io-uring requests
+ */
+struct fuse_uring_req_header {
+	/* struct fuse_in_header / struct fuse_out_header */
+	char in_out[FUSE_URING_IN_OUT_HEADER_SZ];
+
+	/* per op code header */
+	char op_in[FUSE_URING_OP_IN_OUT_SZ];
+
+	struct fuse_uring_ent_in_out ring_ent_in_out;
+};
+
+/**
+ * sqe commands to the kernel
+ */
+enum fuse_uring_cmd {
+	FUSE_IO_URING_CMD_INVALID = 0,
+
+	/* register the request buffer and fetch a fuse request */
+	FUSE_IO_URING_CMD_REGISTER = 1,
+
+	/* commit fuse request result and fetch next request */
+	FUSE_IO_URING_CMD_COMMIT_AND_FETCH = 2,
+};
+
+/**
+ * In the 80B command area of the SQE.
+ */
+struct fuse_uring_cmd_req {
+	uint64_t flags;
+
+	/* entry identifier for commits */
+	uint64_t commit_id;
+
+	/* queue the command is for (queue index) */
+	uint16_t qid;
+	uint8_t padding[6];
+};
+
 #endif /* _LINUX_FUSE_H */
diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h
index caf4db2fcbb9..4273e0249fcb 100644
--- a/include/uapi/linux/nfs4.h
+++ b/include/uapi/linux/nfs4.h
@@ -58,7 +58,7 @@
 #define NFS4_SHARE_DENY_BOTH	0x0003
 
 /* nfs41 */
-#define NFS4_SHARE_WANT_MASK		0xFF00
+#define NFS4_SHARE_WANT_TYPE_MASK	0xFF00
 #define NFS4_SHARE_WANT_NO_PREFERENCE	0x0000
 #define NFS4_SHARE_WANT_READ_DELEG	0x0100
 #define NFS4_SHARE_WANT_WRITE_DELEG	0x0200
@@ -66,13 +66,16 @@
 #define NFS4_SHARE_WANT_NO_DELEG	0x0400
 #define NFS4_SHARE_WANT_CANCEL		0x0500
 
-#define NFS4_SHARE_WHEN_MASK		0xF0000
+#define NFS4_SHARE_WHEN_MASK				0xF0000
 #define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL	0x10000
 #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED		0x20000
 
+#define NFS4_SHARE_WANT_MOD_MASK			0xF00000
 #define NFS4_SHARE_WANT_DELEG_TIMESTAMPS		0x100000
 #define NFS4_SHARE_WANT_OPEN_XOR_DELEGATION		0x200000
 
+#define NFS4_SHARE_WANT_MASK	(NFS4_SHARE_WANT_TYPE_MASK | NFS4_SHARE_WANT_MOD_MASK)
+
 #define NFS4_CDFC4_FORE	0x1
 #define NFS4_CDFC4_BACK 0x2
 #define NFS4_CDFC4_BOTH 0x3
diff --git a/include/uapi/linux/ntsync.h b/include/uapi/linux/ntsync.h
index dcfa38fdc93c..6d06793512b1 100644
--- a/include/uapi/linux/ntsync.h
+++ b/include/uapi/linux/ntsync.h
@@ -11,13 +11,49 @@
 #include <linux/types.h>
 
 struct ntsync_sem_args {
-	__u32 sem;
 	__u32 count;
 	__u32 max;
 };
 
-#define NTSYNC_IOC_CREATE_SEM		_IOWR('N', 0x80, struct ntsync_sem_args)
+struct ntsync_mutex_args {
+	__u32 owner;
+	__u32 count;
+};
+
+struct ntsync_event_args {
+	__u32 manual;
+	__u32 signaled;
+};
+
+#define NTSYNC_WAIT_REALTIME	0x1
+
+struct ntsync_wait_args {
+	__u64 timeout;
+	__u64 objs;
+	__u32 count;
+	__u32 index;
+	__u32 flags;
+	__u32 owner;
+	__u32 alert;
+	__u32 pad;
+};
+
+#define NTSYNC_MAX_WAIT_COUNT 64
+
+#define NTSYNC_IOC_CREATE_SEM		_IOW ('N', 0x80, struct ntsync_sem_args)
+#define NTSYNC_IOC_WAIT_ANY		_IOWR('N', 0x82, struct ntsync_wait_args)
+#define NTSYNC_IOC_WAIT_ALL		_IOWR('N', 0x83, struct ntsync_wait_args)
+#define NTSYNC_IOC_CREATE_MUTEX		_IOW ('N', 0x84, struct ntsync_mutex_args)
+#define NTSYNC_IOC_CREATE_EVENT		_IOW ('N', 0x87, struct ntsync_event_args)
 
-#define NTSYNC_IOC_SEM_POST		_IOWR('N', 0x81, __u32)
+#define NTSYNC_IOC_SEM_RELEASE		_IOWR('N', 0x81, __u32)
+#define NTSYNC_IOC_MUTEX_UNLOCK		_IOWR('N', 0x85, struct ntsync_mutex_args)
+#define NTSYNC_IOC_MUTEX_KILL		_IOW ('N', 0x86, __u32)
+#define NTSYNC_IOC_EVENT_SET		_IOR ('N', 0x88, __u32)
+#define NTSYNC_IOC_EVENT_RESET		_IOR ('N', 0x89, __u32)
+#define NTSYNC_IOC_EVENT_PULSE		_IOR ('N', 0x8a, __u32)
+#define NTSYNC_IOC_SEM_READ		_IOR ('N', 0x8b, struct ntsync_sem_args)
+#define NTSYNC_IOC_MUTEX_READ		_IOR ('N', 0x8c, struct ntsync_mutex_args)
+#define NTSYNC_IOC_EVENT_READ		_IOR ('N', 0x8d, struct ntsync_event_args)
 
 #endif
diff --git a/include/uapi/linux/pps_gen.h b/include/uapi/linux/pps_gen.h
new file mode 100644
index 000000000000..60a5d0fcfa68
--- /dev/null
+++ b/include/uapi/linux/pps_gen.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * PPS generator API header
+ *
+ * Copyright (C) 2024 Rodolfo Giometti <giometti@enneenne.com>
+ */
+
+#ifndef _PPS_GEN_H_
+#define _PPS_GEN_H_
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/**
+ * struct pps_gen_event - the PPS generator events
+ * @event: the event type
+ * @sequence: the event sequence number
+ *
+ * Userspace can get the last PPS generator event by using the
+ * ioctl(pps_gen, PPS_GEN_FETCHEVENT, ...) syscall.
+ * The sequence field can be used to save the last event ID, while in the
+ * event field is stored the last event type. Currently known event is:
+ *
+ *     PPS_GEN_EVENT_MISSEDPULSE	: last pulse was not generated
+ */
+struct pps_gen_event {
+	unsigned int event;
+	unsigned int sequence;
+};
+
+#define PPS_GEN_EVENT_MISSEDPULSE	1
+
+#define PPS_GEN_SETENABLE		_IOW('p', 0xb1, unsigned int *)
+#define PPS_GEN_USESYSTEMCLOCK		_IOR('p', 0xb2, unsigned int *)
+#define PPS_GEN_FETCHEVENT		_IOR('p', 0xb3, struct pps_gen_event *)
+
+#endif /* _PPS_GEN_H_ */
diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h
index b50b2eb257a0..934e20ef7f79 100644
--- a/include/uapi/linux/taskstats.h
+++ b/include/uapi/linux/taskstats.h
@@ -72,6 +72,8 @@ struct taskstats {
 	 */
 	__u64	cpu_count __attribute__((aligned(8)));
 	__u64	cpu_delay_total;
+	__u64	cpu_delay_max;
+	__u64	cpu_delay_min;
 
 	/* Following four fields atomically updated using task->delays->lock */
 
@@ -80,10 +82,14 @@ struct taskstats {
 	 */
 	__u64	blkio_count;
 	__u64	blkio_delay_total;
+	__u64	blkio_delay_max;
+	__u64	blkio_delay_min;
 
 	/* Delay waiting for page fault I/O (swap in only) */
 	__u64	swapin_count;
 	__u64	swapin_delay_total;
+	__u64	swapin_delay_max;
+	__u64	swapin_delay_min;
 
 	/* cpu "wall-clock" running time
 	 * On some architectures, value will adjust for cpu time stolen
@@ -166,10 +172,14 @@ struct taskstats {
 	/* Delay waiting for memory reclaim */
 	__u64	freepages_count;
 	__u64	freepages_delay_total;
+	__u64	freepages_delay_max;
+	__u64	freepages_delay_min;
 
 	/* Delay waiting for thrashing page */
 	__u64	thrashing_count;
 	__u64	thrashing_delay_total;
+	__u64	thrashing_delay_max;
+	__u64	thrashing_delay_min;
 
 	/* v10: 64-bit btime to avoid overflow */
 	__u64	ac_btime64;		/* 64-bit begin time */
@@ -177,6 +187,8 @@ struct taskstats {
 	/* v11: Delay waiting for memory compact */
 	__u64	compact_count;
 	__u64	compact_delay_total;
+	__u64	compact_delay_max;
+	__u64	compact_delay_min;
 
 	/* v12 begin */
 	__u32   ac_tgid;	/* thread group ID */
@@ -198,10 +210,15 @@ struct taskstats {
 	/* v13: Delay waiting for write-protect copy */
 	__u64    wpcopy_count;
 	__u64    wpcopy_delay_total;
+	__u64    wpcopy_delay_max;
+	__u64    wpcopy_delay_min;
 
 	/* v14: Delay waiting for IRQ/SOFTIRQ */
 	__u64    irq_count;
 	__u64    irq_delay_total;
+	__u64    irq_delay_max;
+	__u64    irq_delay_min;
+	/* v15: add Delay max */
 };
 
 
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index 2ebdba111a8f..beef1752e36e 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -206,7 +206,7 @@ struct usb_ffs_dmabuf_transfer_req {
  * +-----+-----------------+------+--------------------------+
  * | off | name            | type | description              |
  * +-----+-----------------+------+--------------------------+
- * |   0 | inteface        | U8   | related interface number |
+ * |   0 | interface       | U8   | related interface number |
  * +-----+-----------------+------+--------------------------+
  * |   1 | dwLength        | U32  | length of the descriptor |
  * +-----+-----------------+------+--------------------------+
@@ -224,7 +224,7 @@ struct usb_ffs_dmabuf_transfer_req {
  * +-----+-----------------+------+--------------------------+
  * | off | name            | type | description              |
  * +-----+-----------------+------+--------------------------+
- * |   0 | inteface        | U8   | related interface number |
+ * |   0 | interface       | U8   | related interface number |
  * +-----+-----------------+------+--------------------------+
  * |   1 | dwLength        | U32  | length of the descriptor |
  * +-----+-----------------+------+--------------------------+
@@ -237,7 +237,7 @@ struct usb_ffs_dmabuf_transfer_req {
  * |  11 | ExtProp[]       |      | list of ext. prop. d.    |
  * +-----+-----------------+------+--------------------------+
  *
- * ExtCompat[] is an array of valid Extended Compatiblity descriptors
+ * ExtCompat[] is an array of valid Extended Compatibility descriptors
  * which have the following format:
  *
  * +-----+-----------------------+------+-------------------------------------+
@@ -295,7 +295,7 @@ struct usb_functionfs_strings_head {
  * |  16 | stringtab  | StringTab[lang_count] | table of strings per lang  |
  *
  * For each language there is one stringtab entry (ie. there are lang_count
- * stringtab entires).  Each StringTab has following format:
+ * stringtab entries).  Each StringTab has following format:
  *
  * | off | name    | type              | description                        |
  * |-----+---------+-------------------+------------------------------------|
diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h
index 11bd48c72c6c..68a627d04afa 100644
--- a/include/uapi/linux/vduse.h
+++ b/include/uapi/linux/vduse.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
 #ifndef _UAPI_VDUSE_H_
 #define _UAPI_VDUSE_H_
 
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 1beb317df1b9..8549d4571257 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -116,6 +116,8 @@
 #define VIRTIO_PCI_CAP_PCI_CFG		5
 /* Additional shared memory capability */
 #define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8
+/* PCI vendor data configuration */
+#define VIRTIO_PCI_CAP_VENDOR_CFG	9
 
 /* This is the PCI capability header: */
 struct virtio_pci_cap {
@@ -130,6 +132,18 @@ struct virtio_pci_cap {
 	__le32 length;		/* Length of the structure, in bytes. */
 };
 
+/* This is the PCI vendor data capability header: */
+struct virtio_pci_vndr_data {
+	__u8 cap_vndr;		/* Generic PCI field: PCI_CAP_ID_VNDR */
+	__u8 cap_next;		/* Generic PCI field: next ptr. */
+	__u8 cap_len;		/* Generic PCI field: capability length */
+	__u8 cfg_type;		/* Identifies the structure. */
+	__u16 vendor_id;	/* Identifies the vendor-specific format. */
+	/* For Vendor Definition */
+	/* Pads structure to a multiple of 4 bytes */
+	/* Reads must not have side effects */
+};
+
 struct virtio_pci_cap64 {
 	struct virtio_pci_cap cap;
 	__le32 offset_hi;             /* Most sig 32 bits of offset */
diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h
index e1571603175e..aa872a41ffb9 100644
--- a/include/uapi/mtd/ubi-user.h
+++ b/include/uapi/mtd/ubi-user.h
@@ -175,6 +175,8 @@
 #define UBI_IOCRPEB _IOW(UBI_IOC_MAGIC, 4, __s32)
 /* Force scrubbing on the specified PEB */
 #define UBI_IOCSPEB _IOW(UBI_IOC_MAGIC, 5, __s32)
+/* Read detailed device erase counter information */
+#define UBI_IOCECNFO _IOWR(UBI_IOC_MAGIC, 6, struct ubi_ecinfo_req)
 
 /* ioctl commands of the UBI control character device */
 
@@ -413,6 +415,37 @@ struct ubi_rnvol_req {
 } __packed;
 
 /**
+ * struct ubi_ecinfo_req - a data structure used for requesting and receiving
+ * erase block counter information from a UBI device.
+ *
+ * @start: index of first physical erase block to read (in)
+ * @length: number of erase counters to read (in)
+ * @read_length: number of erase counters that was actually read (out)
+ * @padding: reserved for future, not used, has to be zeroed
+ * @erase_counters: array of erase counter values (out)
+ *
+ * This structure is used to retrieve erase counter information for a specified
+ * range of PEBs on a UBI device.
+ * Erase counters are read from @start and attempts to read @length number of
+ * erase counters.
+ * The retrieved values are stored in the @erase_counters array. It is the
+ * responsibility of the caller to allocate enough memory for storing @length
+ * elements in the @erase_counters array.
+ * If a block is bad or if the erase counter is unknown the corresponding value
+ * in the array will be set to -1.
+ * The @read_length field will indicate the number of erase counters actually
+ * read. Typically @read_length will be limited due to memory or the number of
+ * PEBs on the UBI device.
+ */
+struct ubi_ecinfo_req {
+	__s32 start;
+	__s32 length;
+	__s32 read_length;
+	__s8  padding[16];
+	__s32 erase_counters[];
+}  __packed;
+
+/**
  * struct ubi_leb_change_req - a data structure used in atomic LEB change
  *                             requests.
  * @lnum: logical eraseblock number to change
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index e594abe5d05f..f151feb0ca8c 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -180,7 +180,6 @@ enum attr_idn {
 	QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE       = 0x1D,
 	QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST    = 0x1E,
 	QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE        = 0x1F,
-	QUERY_ATTR_IDN_EXT_IID_EN		= 0x2A,
 	QUERY_ATTR_IDN_TIMESTAMP		= 0x30
 };
 
@@ -386,12 +385,11 @@ enum {
 
 /* Possible values for dExtendedUFSFeaturesSupport */
 enum {
-	UFS_DEV_LOW_TEMP_NOTIF		= BIT(4),
-	UFS_DEV_HIGH_TEMP_NOTIF		= BIT(5),
+	UFS_DEV_HIGH_TEMP_NOTIF		= BIT(4),
+	UFS_DEV_LOW_TEMP_NOTIF		= BIT(5),
 	UFS_DEV_EXT_TEMP_NOTIF		= BIT(6),
 	UFS_DEV_HPB_SUPPORT		= BIT(7),
 	UFS_DEV_WRITE_BOOSTER_SUP	= BIT(8),
-	UFS_DEV_EXT_IID_SUP		= BIT(16),
 };
 #define UFS_DEV_HPB_SUPPORT_VERSION		0x310
 
@@ -585,9 +583,6 @@ struct ufs_dev_info {
 
 	bool    b_advanced_rpmb_en;
 
-	/* UFS EXT_IID Enable */
-	bool	b_ext_iid_en;
-
 	/* UFS RTC */
 	enum ufs_rtc_time rtc_type;
 	time64_t rtc_time_baseline;
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 74e5b9960c54..8bf31e6ca4e5 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -326,7 +326,6 @@ struct ufs_pwr_mode_info {
  * @phy_initialization: used to initialize phys
  * @device_reset: called to issue a reset pulse on the UFS device
  * @config_scaling_param: called to configure clock scaling parameters
- * @program_key: program or evict an inline encryption key
  * @fill_crypto_prdt: initialize crypto-related fields in the PRDT
  * @event_notify: called to notify important events
  * @mcq_config_resource: called to configure MCQ platform resources
@@ -373,8 +372,6 @@ struct ufs_hba_variant_ops {
 	void	(*config_scaling_param)(struct ufs_hba *hba,
 				struct devfreq_dev_profile *profile,
 				struct devfreq_simple_ondemand_data *data);
-	int	(*program_key)(struct ufs_hba *hba,
-			       const union ufs_crypto_cfg_entry *cfg, int slot);
 	int	(*fill_crypto_prdt)(struct ufs_hba *hba,
 				    const struct bio_crypt_ctx *crypt_ctx,
 				    void *prdt, unsigned int num_segments);
@@ -403,6 +400,9 @@ enum clk_gating_state {
  * delay_ms
  * @ungate_work: worker to turn on clocks that will be used in case of
  * interrupt context
+ * @clk_gating_workq: workqueue for clock gating work.
+ * @lock: serialize access to some struct ufs_clk_gating members. An outer lock
+ * relative to the host lock
  * @state: the current clocks state
  * @delay_ms: gating delay in ms
  * @is_suspended: clk gating is suspended when set to 1 which can be used
@@ -413,11 +413,14 @@ enum clk_gating_state {
  * @is_initialized: Indicates whether clock gating is initialized or not
  * @active_reqs: number of requests that are pending and should be waited for
  * completion before gating clocks.
- * @clk_gating_workq: workqueue for clock gating work.
  */
 struct ufs_clk_gating {
 	struct delayed_work gate_work;
 	struct work_struct ungate_work;
+	struct workqueue_struct *clk_gating_workq;
+
+	spinlock_t lock;
+
 	enum clk_gating_state state;
 	unsigned long delay_ms;
 	bool is_suspended;
@@ -426,11 +429,14 @@ struct ufs_clk_gating {
 	bool is_enabled;
 	bool is_initialized;
 	int active_reqs;
-	struct workqueue_struct *clk_gating_workq;
 };
 
 /**
  * struct ufs_clk_scaling - UFS clock scaling related data
+ * @workq: workqueue to schedule devfreq suspend/resume work
+ * @suspend_work: worker to suspend devfreq
+ * @resume_work: worker to resume devfreq
+ * @lock: serialize access to some struct ufs_clk_scaling members
  * @active_reqs: number of requests that are pending. If this is zero when
  * devfreq ->target() function is called then schedule "suspend_work" to
  * suspend devfreq.
@@ -440,9 +446,6 @@ struct ufs_clk_gating {
  * @enable_attr: sysfs attribute to enable/disable clock scaling
  * @saved_pwr_info: UFS power mode may also be changed during scaling and this
  * one keeps track of previous power mode.
- * @workq: workqueue to schedule devfreq suspend/resume work
- * @suspend_work: worker to suspend devfreq
- * @resume_work: worker to resume devfreq
  * @target_freq: frequency requested by devfreq framework
  * @min_gear: lowest HS gear to scale down to
  * @is_enabled: tracks if scaling is currently enabled or not, controlled by
@@ -454,15 +457,18 @@ struct ufs_clk_gating {
  * @is_suspended: tracks if devfreq is suspended or not
  */
 struct ufs_clk_scaling {
+	struct workqueue_struct *workq;
+	struct work_struct suspend_work;
+	struct work_struct resume_work;
+
+	spinlock_t lock;
+
 	int active_reqs;
 	unsigned long tot_busy_t;
 	ktime_t window_start_t;
 	ktime_t busy_start_t;
 	struct device_attribute enable_attr;
 	struct ufs_pa_layer_attr saved_pwr_info;
-	struct workqueue_struct *workq;
-	struct work_struct suspend_work;
-	struct work_struct resume_work;
 	unsigned long target_freq;
 	u32 min_gear;
 	bool is_enabled;
@@ -946,7 +952,6 @@ enum ufshcd_mcq_opr {
  * @nr_queues: number of Queues of different queue types
  * @complete_put: whether or not to call ufshcd_rpm_put() from inside
  *	ufshcd_resume_complete()
- * @ext_iid_sup: is EXT_IID is supported by UFSHC
  * @mcq_sup: is mcq supported by UFSHC
  * @mcq_enabled: is mcq ready to accept requests
  * @res: array of resource info of MCQ registers
@@ -1112,7 +1117,6 @@ struct ufs_hba {
 	unsigned int nr_hw_queues;
 	unsigned int nr_queues[HCTX_MAX_TYPES];
 	bool complete_put;
-	bool ext_iid_sup;
 	bool scsi_host_added;
 	bool mcq_sup;
 	bool lsdb_sup;
@@ -1202,6 +1206,14 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba)
 	({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); })
 #endif
 
+#ifdef CONFIG_SCSI_UFS_CRYPTO
+static inline struct ufs_hba *
+ufs_hba_from_crypto_profile(struct blk_crypto_profile *profile)
+{
+	return container_of(profile, struct ufs_hba, crypto_profile);
+}
+#endif
+
 static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba)
 {
 	return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba);
@@ -1297,7 +1309,6 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg)
 void ufshcd_enable_irq(struct ufs_hba *hba);
 void ufshcd_disable_irq(struct ufs_hba *hba);
 int ufshcd_alloc_host(struct device *, struct ufs_hba **);
-void ufshcd_dealloc_host(struct ufs_hba *);
 int ufshcd_hba_enable(struct ufs_hba *hba);
 int ufshcd_init(struct ufs_hba *, void __iomem *, unsigned int);
 int ufshcd_link_recovery(struct ufs_hba *hba);
diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h
index 27364c4a6ef9..612500a7088f 100644
--- a/include/ufs/ufshci.h
+++ b/include/ufs/ufshci.h
@@ -82,11 +82,6 @@ enum {
 	MASK_MCQ_SUPPORT			= 0x40000000,
 };
 
-/* MCQ capability mask */
-enum {
-	MASK_EXT_IID_SUPPORT = 0x00000400,
-};
-
 enum {
 	REG_SQATTR		= 0x0,
 	REG_SQLBA		= 0x4,
diff --git a/init/Kconfig b/init/Kconfig
index 7fe82a46e88c..d0d021b3fa3b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1131,7 +1131,6 @@ config CGROUP_PIDS
 
 config CGROUP_RDMA
 	bool "RDMA controller"
-	select PAGE_COUNTER
 	help
 	  Provides enforcement of RDMA resources defined by IB stack.
 	  It is fairly easy for consumers to exhaust RDMA resources, which
@@ -1970,7 +1969,8 @@ config RUST
 	bool "Rust support"
 	depends on HAVE_RUST
 	depends on RUST_IS_AVAILABLE
-	depends on !MODVERSIONS
+	select EXTENDED_MODVERSIONS if MODVERSIONS
+	depends on !MODVERSIONS || GENDWARFKSYMS
 	depends on !GCC_PLUGIN_RANDSTRUCT
 	depends on !RANDSTRUCT
 	depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE
diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 22c7f41ff642..f6867bad0d78 100644
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -21,7 +21,7 @@ phys_addr_t phys_initrd_start __initdata;
 unsigned long phys_initrd_size __initdata;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_do_mounts_initrd_table[] = {
+static const struct ctl_table kern_do_mounts_initrd_table[] = {
 	{
 		.procname       = "real-root-dev",
 		.data           = &real_root_dev,
@@ -89,7 +89,7 @@ static void __init handle_initrd(char *root_device_name)
 	extern char *envp_init[];
 	int error;
 
-	pr_warn("using deprecated initrd support, will be removed in 2021.\n");
+	pr_warn("using deprecated initrd support, will be removed soon.\n");
 
 	real_root_dev = new_encode_dev(ROOT_DEV);
 	create_dev("/dev/root.old", Root_RAM0);
diff --git a/init/main.c b/init/main.c
index 893cb77aef22..2a1757826397 100644
--- a/init/main.c
+++ b/init/main.c
@@ -640,15 +640,11 @@ static void __init setup_command_line(char *command_line)
 
 	len = xlen + strlen(boot_command_line) + ilen + 1;
 
-	saved_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
-	if (!saved_command_line)
-		panic("%s: Failed to allocate %zu bytes\n", __func__, len);
+	saved_command_line = memblock_alloc_or_panic(len, SMP_CACHE_BYTES);
 
 	len = xlen + strlen(command_line) + 1;
 
-	static_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
-	if (!static_command_line)
-		panic("%s: Failed to allocate %zu bytes\n", __func__, len);
+	static_command_line = memblock_alloc_or_panic(len, SMP_CACHE_BYTES);
 
 	if (xlen) {
 		/*
@@ -1146,16 +1142,10 @@ static int __init initcall_blacklist(char *str)
 		str_entry = strsep(&str, ",");
 		if (str_entry) {
 			pr_debug("blacklisting initcall %s\n", str_entry);
-			entry = memblock_alloc(sizeof(*entry),
+			entry = memblock_alloc_or_panic(sizeof(*entry),
 					       SMP_CACHE_BYTES);
-			if (!entry)
-				panic("%s: Failed to allocate %zu bytes\n",
-				      __func__, sizeof(*entry));
-			entry->buf = memblock_alloc(strlen(str_entry) + 1,
+			entry->buf = memblock_alloc_or_panic(strlen(str_entry) + 1,
 						    SMP_CACHE_BYTES);
-			if (!entry->buf)
-				panic("%s: Failed to allocate %zu bytes\n",
-				      __func__, strlen(str_entry) + 1);
 			strcpy(entry->buf, str_entry);
 			list_add(&entry->next, &blacklisted_initcalls);
 		}
diff --git a/io_uring/Makefile b/io_uring/Makefile
index 53167bef37d7..d695b60dba4f 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					sync.o msg_ring.o advise.o openclose.o \
 					epoll.o statx.o timeout.o fdinfo.o \
 					cancel.o waitid.o register.o \
-					truncate.o memmap.o
+					truncate.o memmap.o alloc_cache.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
 obj-$(CONFIG_FUTEX)		+= futex.o
 obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/alloc_cache.c b/io_uring/alloc_cache.c
new file mode 100644
index 000000000000..58423888b736
--- /dev/null
+++ b/io_uring/alloc_cache.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "alloc_cache.h"
+
+void io_alloc_cache_free(struct io_alloc_cache *cache,
+			 void (*free)(const void *))
+{
+	void *entry;
+
+	if (!cache->entries)
+		return;
+
+	while ((entry = io_alloc_cache_get(cache)) != NULL)
+		free(entry);
+
+	kvfree(cache->entries);
+	cache->entries = NULL;
+}
+
+/* returns false if the cache was initialized properly */
+bool io_alloc_cache_init(struct io_alloc_cache *cache,
+			 unsigned max_nr, unsigned int size,
+			 unsigned int init_bytes)
+{
+	cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL);
+	if (!cache->entries)
+		return true;
+
+	cache->nr_cached = 0;
+	cache->max_cached = max_nr;
+	cache->elem_size = size;
+	cache->init_clear = init_bytes;
+	return false;
+}
+
+void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp)
+{
+	void *obj;
+
+	obj = kmalloc(cache->elem_size, gfp);
+	if (obj && cache->init_clear)
+		memset(obj, 0, cache->init_clear);
+	return obj;
+}
diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
index a3a8cfec32ce..0dd17d8ba93a 100644
--- a/io_uring/alloc_cache.h
+++ b/io_uring/alloc_cache.h
@@ -1,11 +1,30 @@
 #ifndef IOU_ALLOC_CACHE_H
 #define IOU_ALLOC_CACHE_H
 
+#include <linux/io_uring_types.h>
+
 /*
  * Don't allow the cache to grow beyond this size.
  */
 #define IO_ALLOC_CACHE_MAX	128
 
+void io_alloc_cache_free(struct io_alloc_cache *cache,
+			 void (*free)(const void *));
+bool io_alloc_cache_init(struct io_alloc_cache *cache,
+			 unsigned max_nr, unsigned int size,
+			 unsigned int init_bytes);
+
+void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp);
+
+static inline void io_alloc_cache_kasan(struct iovec **iov, int *nr)
+{
+	if (IS_ENABLED(CONFIG_KASAN)) {
+		kfree(*iov);
+		*iov = NULL;
+		*nr = 0;
+	}
+}
+
 static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
 				      void *entry)
 {
@@ -23,52 +42,30 @@ static inline void *io_alloc_cache_get(struct io_alloc_cache *cache)
 	if (cache->nr_cached) {
 		void *entry = cache->entries[--cache->nr_cached];
 
+		/*
+		 * If KASAN is enabled, always clear the initial bytes that
+		 * must be zeroed post alloc, in case any of them overlap
+		 * with KASAN storage.
+		 */
+#if defined(CONFIG_KASAN)
 		kasan_mempool_unpoison_object(entry, cache->elem_size);
+		if (cache->init_clear)
+			memset(entry, 0, cache->init_clear);
+#endif
 		return entry;
 	}
 
 	return NULL;
 }
 
-static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp,
-				   void (*init_once)(void *obj))
+static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp)
 {
-	if (unlikely(!cache->nr_cached)) {
-		void *obj = kmalloc(cache->elem_size, gfp);
+	void *obj;
 
-		if (obj && init_once)
-			init_once(obj);
+	obj = io_alloc_cache_get(cache);
+	if (obj)
 		return obj;
-	}
-	return io_alloc_cache_get(cache);
+	return io_cache_alloc_new(cache, gfp);
 }
 
-/* returns false if the cache was initialized properly */
-static inline bool io_alloc_cache_init(struct io_alloc_cache *cache,
-				       unsigned max_nr, size_t size)
-{
-	cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL);
-	if (cache->entries) {
-		cache->nr_cached = 0;
-		cache->max_cached = max_nr;
-		cache->elem_size = size;
-		return false;
-	}
-	return true;
-}
-
-static inline void io_alloc_cache_free(struct io_alloc_cache *cache,
-				       void (*free)(const void *))
-{
-	void *entry;
-
-	if (!cache->entries)
-		return;
-
-	while ((entry = io_alloc_cache_get(cache)) != NULL)
-		free(entry);
-
-	kvfree(cache->entries);
-	cache->entries = NULL;
-}
 #endif
diff --git a/io_uring/filetable.c b/io_uring/filetable.c
index a21660e3145a..dd8eeec97acf 100644
--- a/io_uring/filetable.c
+++ b/io_uring/filetable.c
@@ -68,7 +68,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
 	if (slot_index >= ctx->file_table.data.nr)
 		return -EINVAL;
 
-	node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
+	node = io_rsrc_node_alloc(IORING_RSRC_FILE);
 	if (!node)
 		return -ENOMEM;
 
diff --git a/io_uring/futex.c b/io_uring/futex.c
index 30139cc150f2..43e2143255f5 100644
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -36,7 +36,7 @@ struct io_futex_data {
 bool io_futex_cache_init(struct io_ring_ctx *ctx)
 {
 	return io_alloc_cache_init(&ctx->futex_cache, IO_FUTEX_ALLOC_CACHE_MAX,
-				sizeof(struct io_futex_data));
+				sizeof(struct io_futex_data), 0);
 }
 
 void io_futex_cache_free(struct io_ring_ctx *ctx)
@@ -320,7 +320,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
 	}
 
 	io_ring_submit_lock(ctx, issue_flags);
-	ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT, NULL);
+	ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT);
 	if (!ifd) {
 		ret = -ENOMEM;
 		goto done_unlock;
@@ -338,7 +338,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
 		hlist_add_head(&req->hash_node, &ctx->futex_list);
 		io_ring_submit_unlock(ctx, issue_flags);
 
-		futex_queue(&ifd->q, hb);
+		futex_queue(&ifd->q, hb, NULL);
 		return IOU_ISSUE_SKIP_COMPLETE;
 	}
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 7bfbc7c22367..ceacf6230e34 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -157,7 +157,7 @@ static int __read_mostly sysctl_io_uring_disabled;
 static int __read_mostly sysctl_io_uring_group = -1;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kernel_io_uring_disabled_table[] = {
+static const struct ctl_table kernel_io_uring_disabled_table[] = {
 	{
 		.procname	= "io_uring_disabled",
 		.data		= &sysctl_io_uring_disabled,
@@ -315,16 +315,18 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	INIT_LIST_HEAD(&ctx->io_buffers_cache);
 	ret = io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX,
-			    sizeof(struct async_poll));
+			    sizeof(struct async_poll), 0);
 	ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX,
-			    sizeof(struct io_async_msghdr));
+			    sizeof(struct io_async_msghdr),
+			    offsetof(struct io_async_msghdr, clear));
 	ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX,
-			    sizeof(struct io_async_rw));
+			    sizeof(struct io_async_rw),
+			    offsetof(struct io_async_rw, clear));
 	ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX,
-			    sizeof(struct io_uring_cmd_data));
+			    sizeof(struct io_uring_cmd_data), 0);
 	spin_lock_init(&ctx->msg_lock);
 	ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX,
-			    sizeof(struct io_kiocb));
+			    sizeof(struct io_kiocb), 0);
 	ret |= io_futex_cache_init(ctx);
 	if (ret)
 		goto free_ref;
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index f65e3f3ede51..ab619e63ef39 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -226,21 +226,16 @@ static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
 }
 
 static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache,
-					      struct io_kiocb *req,
-					      void (*init_once)(void *obj))
+					      struct io_kiocb *req)
 {
-	req->async_data = io_cache_alloc(cache, GFP_KERNEL, init_once);
-	if (req->async_data)
-		req->flags |= REQ_F_ASYNC_DATA;
-	return req->async_data;
-}
+	if (cache) {
+		req->async_data = io_cache_alloc(cache, GFP_KERNEL);
+	} else {
+		const struct io_issue_def *def = &io_issue_defs[req->opcode];
 
-static inline void *io_uring_alloc_async_data_nocache(struct io_kiocb *req)
-{
-	const struct io_issue_def *def = &io_issue_defs[req->opcode];
-
-	WARN_ON_ONCE(!def->async_size);
-	req->async_data = kmalloc(def->async_size, GFP_KERNEL);
+		WARN_ON_ONCE(!def->async_size);
+		req->async_data = kmalloc(def->async_size, GFP_KERNEL);
+	}
 	if (req->async_data)
 		req->flags |= REQ_F_ASYNC_DATA;
 	return req->async_data;
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index dda846190fbd..361134544427 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -170,8 +170,8 @@ static int io_region_allocate_pages(struct io_ring_ctx *ctx,
 		goto done;
 	}
 
-	nr_allocated = alloc_pages_bulk_array_node(gfp, NUMA_NO_NODE,
-						   mr->nr_pages, pages);
+	nr_allocated = alloc_pages_bulk_node(gfp, NUMA_NO_NODE,
+					     mr->nr_pages, pages);
 	if (nr_allocated != mr->nr_pages) {
 		if (nr_allocated)
 			release_pages(pages, nr_allocated);
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index bd3cd78d2dba..7e6f68e911f1 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -89,8 +89,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, struct io_tw_state *ts)
 static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			      int res, u32 cflags, u64 user_data)
 {
-	req->tctx = READ_ONCE(ctx->submitter_task->io_uring);
-	if (!req->tctx) {
+	if (!READ_ONCE(ctx->submitter_task)) {
 		kmem_cache_free(req_cachep, req);
 		return -EOWNERDEAD;
 	}
@@ -98,6 +97,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	io_req_set_res(req, res, cflags);
 	percpu_ref_get(&ctx->refs);
 	req->ctx = ctx;
+	req->tctx = NULL;
 	req->io_task_work.func = io_msg_tw_complete;
 	io_req_task_work_add_remote(req, ctx, IOU_F_TWQ_LAZY_WAKE);
 	return 0;
diff --git a/io_uring/net.c b/io_uring/net.c
index 85f55fbc25c9..17852a6616ff 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -137,7 +137,6 @@ static void io_netmsg_iovec_free(struct io_async_msghdr *kmsg)
 static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_async_msghdr *hdr = req->async_data;
-	struct iovec *iov;
 
 	/* can't recycle, ensure we free the iovec if we have one */
 	if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) {
@@ -146,44 +145,30 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags)
 	}
 
 	/* Let normal cleanup path reap it if we fail adding to the cache */
-	iov = hdr->free_iov;
+	io_alloc_cache_kasan(&hdr->free_iov, &hdr->free_iov_nr);
 	if (io_alloc_cache_put(&req->ctx->netmsg_cache, hdr)) {
-		if (iov)
-			kasan_mempool_poison_object(iov);
 		req->async_data = NULL;
 		req->flags &= ~REQ_F_ASYNC_DATA;
 	}
 }
 
-static void io_msg_async_data_init(void *obj)
-{
-	struct io_async_msghdr *hdr = (struct io_async_msghdr *)obj;
-
-	hdr->free_iov = NULL;
-	hdr->free_iov_nr = 0;
-}
-
 static struct io_async_msghdr *io_msg_alloc_async(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_async_msghdr *hdr;
 
-	hdr = io_uring_alloc_async_data(&ctx->netmsg_cache, req,
-					io_msg_async_data_init);
+	hdr = io_uring_alloc_async_data(&ctx->netmsg_cache, req);
 	if (!hdr)
 		return NULL;
 
 	/* If the async data was cached, we might have an iov cached inside. */
-	if (hdr->free_iov) {
-		kasan_mempool_unpoison_object(hdr->free_iov,
-					      hdr->free_iov_nr * sizeof(struct iovec));
+	if (hdr->free_iov)
 		req->flags |= REQ_F_NEED_CLEANUP;
-	}
 	return hdr;
 }
 
 /* assign new iovec to kmsg, if we need to */
-static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg,
+static void io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg,
 			     struct iovec *iov)
 {
 	if (iov) {
@@ -193,7 +178,6 @@ static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg,
 			kfree(kmsg->free_iov);
 		kmsg->free_iov = iov;
 	}
-	return 0;
 }
 
 static inline void io_mshot_prep_retry(struct io_kiocb *req,
@@ -255,7 +239,8 @@ static int io_compat_msg_copy_hdr(struct io_kiocb *req,
 	if (unlikely(ret < 0))
 		return ret;
 
-	return io_net_vec_assign(req, iomsg, iov);
+	io_net_vec_assign(req, iomsg, iov);
+	return 0;
 }
 #endif
 
@@ -295,11 +280,12 @@ static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg,
 			ret = -EINVAL;
 			goto ua_end;
 		} else {
+			struct iovec __user *uiov = msg->msg_iov;
+
 			/* we only need the length for provided buffers */
-			if (!access_ok(&msg->msg_iov[0].iov_len, sizeof(__kernel_size_t)))
+			if (!access_ok(&uiov->iov_len, sizeof(uiov->iov_len)))
 				goto ua_end;
-			unsafe_get_user(iov->iov_len, &msg->msg_iov[0].iov_len,
-					ua_end);
+			unsafe_get_user(iov->iov_len, &uiov->iov_len, ua_end);
 			sr->len = iov->iov_len;
 		}
 		ret = 0;
@@ -314,7 +300,8 @@ ua_end:
 	if (unlikely(ret < 0))
 		return ret;
 
-	return io_net_vec_assign(req, iomsg, iov);
+	io_net_vec_assign(req, iomsg, iov);
+	return 0;
 }
 
 static int io_sendmsg_copy_hdr(struct io_kiocb *req,
@@ -579,6 +566,54 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 	return IOU_OK;
 }
 
+static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags,
+				 struct io_async_msghdr *kmsg)
+{
+	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
+
+	int ret;
+	struct buf_sel_arg arg = {
+		.iovs = &kmsg->fast_iov,
+		.max_len = min_not_zero(sr->len, INT_MAX),
+		.nr_iovs = 1,
+	};
+
+	if (kmsg->free_iov) {
+		arg.nr_iovs = kmsg->free_iov_nr;
+		arg.iovs = kmsg->free_iov;
+		arg.mode = KBUF_MODE_FREE;
+	}
+
+	if (!(sr->flags & IORING_RECVSEND_BUNDLE))
+		arg.nr_iovs = 1;
+	else
+		arg.mode |= KBUF_MODE_EXPAND;
+
+	ret = io_buffers_select(req, &arg, issue_flags);
+	if (unlikely(ret < 0))
+		return ret;
+
+	if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
+		kmsg->free_iov_nr = ret;
+		kmsg->free_iov = arg.iovs;
+		req->flags |= REQ_F_NEED_CLEANUP;
+	}
+	sr->len = arg.out_len;
+
+	if (ret == 1) {
+		sr->buf = arg.iovs[0].iov_base;
+		ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len,
+					&kmsg->msg.msg_iter);
+		if (unlikely(ret))
+			return ret;
+	} else {
+		iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE,
+				arg.iovs, ret, arg.out_len);
+	}
+
+	return 0;
+}
+
 int io_send(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
@@ -602,44 +637,9 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
 
 retry_bundle:
 	if (io_do_buffer_select(req)) {
-		struct buf_sel_arg arg = {
-			.iovs = &kmsg->fast_iov,
-			.max_len = min_not_zero(sr->len, INT_MAX),
-			.nr_iovs = 1,
-		};
-
-		if (kmsg->free_iov) {
-			arg.nr_iovs = kmsg->free_iov_nr;
-			arg.iovs = kmsg->free_iov;
-			arg.mode = KBUF_MODE_FREE;
-		}
-
-		if (!(sr->flags & IORING_RECVSEND_BUNDLE))
-			arg.nr_iovs = 1;
-		else
-			arg.mode |= KBUF_MODE_EXPAND;
-
-		ret = io_buffers_select(req, &arg, issue_flags);
-		if (unlikely(ret < 0))
+		ret = io_send_select_buffer(req, issue_flags, kmsg);
+		if (ret)
 			return ret;
-
-		if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
-			kmsg->free_iov_nr = ret;
-			kmsg->free_iov = arg.iovs;
-			req->flags |= REQ_F_NEED_CLEANUP;
-		}
-		sr->len = arg.out_len;
-
-		if (ret == 1) {
-			sr->buf = arg.iovs[0].iov_base;
-			ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len,
-						&kmsg->msg.msg_iter);
-			if (unlikely(ret))
-				return ret;
-		} else {
-			iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE,
-					arg.iovs, ret, arg.out_len);
-		}
 	}
 
 	/*
@@ -1710,6 +1710,11 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 	int ret;
 	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
 
+	if (unlikely(req->flags & REQ_F_FAIL)) {
+		ret = -ECONNRESET;
+		goto out;
+	}
+
 	file_flags = force_nonblock ? O_NONBLOCK : 0;
 
 	ret = __sys_connect_file(req->file, &io->addr, connect->addr_len,
@@ -1813,11 +1818,8 @@ void io_netmsg_cache_free(const void *entry)
 {
 	struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry;
 
-	if (kmsg->free_iov) {
-		kasan_mempool_unpoison_object(kmsg->free_iov,
-				kmsg->free_iov_nr * sizeof(struct iovec));
+	if (kmsg->free_iov)
 		io_netmsg_iovec_free(kmsg);
-	}
 	kfree(kmsg);
 }
 #endif
diff --git a/io_uring/net.h b/io_uring/net.h
index 52bfee05f06a..b804c2b36e60 100644
--- a/io_uring/net.h
+++ b/io_uring/net.h
@@ -5,16 +5,20 @@
 
 struct io_async_msghdr {
 #if defined(CONFIG_NET)
-	struct iovec			fast_iov;
-	/* points to an allocated iov, if NULL we use fast_iov instead */
 	struct iovec			*free_iov;
+	/* points to an allocated iov, if NULL we use fast_iov instead */
 	int				free_iov_nr;
-	int				namelen;
-	__kernel_size_t			controllen;
-	__kernel_size_t			payloadlen;
-	struct sockaddr __user		*uaddr;
-	struct msghdr			msg;
-	struct sockaddr_storage		addr;
+	struct_group(clear,
+		int				namelen;
+		struct iovec			fast_iov;
+		__kernel_size_t			controllen;
+		__kernel_size_t			payloadlen;
+		struct sockaddr __user		*uaddr;
+		struct msghdr			msg;
+		struct sockaddr_storage		addr;
+	);
+#else
+	struct_group(clear);
 #endif
 };
 
diff --git a/io_uring/poll.c b/io_uring/poll.c
index cc01c40b43d3..bb1c0cd4f809 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -273,6 +273,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
 				return IOU_POLL_REISSUE;
 			}
 		}
+		if (unlikely(req->cqe.res & EPOLLERR))
+			req_set_fail(req);
 		if (req->apoll_events & EPOLLONESHOT)
 			return IOU_POLL_DONE;
 
@@ -315,8 +317,10 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
 
 	ret = io_poll_check_events(req, ts);
 	if (ret == IOU_POLL_NO_ACTION) {
+		io_kbuf_recycle(req, 0);
 		return;
 	} else if (ret == IOU_POLL_REQUEUE) {
+		io_kbuf_recycle(req, 0);
 		__io_poll_execute(req, 0);
 		return;
 	}
@@ -650,7 +654,7 @@ static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
 		kfree(apoll->double_poll);
 	} else {
 		if (!(issue_flags & IO_URING_F_UNLOCKED))
-			apoll = io_cache_alloc(&ctx->apoll_cache, GFP_ATOMIC, NULL);
+			apoll = io_cache_alloc(&ctx->apoll_cache, GFP_ATOMIC);
 		else
 			apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
 		if (!apoll)
diff --git a/io_uring/register.c b/io_uring/register.c
index 05025047d1da..9a4d2fbce4ae 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -552,7 +552,7 @@ overflow:
 	ctx->cqe_cached = ctx->cqe_sentinel = NULL;
 
 	WRITE_ONCE(n.rings->sq_dropped, READ_ONCE(o.rings->sq_dropped));
-	WRITE_ONCE(n.rings->sq_flags, READ_ONCE(o.rings->sq_flags));
+	atomic_set(&n.rings->sq_flags, atomic_read(&o.rings->sq_flags));
 	WRITE_ONCE(n.rings->cq_flags, READ_ONCE(o.rings->cq_flags));
 	WRITE_ONCE(n.rings->cq_overflow, READ_ONCE(o.rings->cq_overflow));
 
@@ -853,6 +853,8 @@ struct file *io_uring_register_get_file(unsigned int fd, bool registered)
 			return ERR_PTR(-EINVAL);
 		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
 		file = tctx->registered_rings[fd];
+		if (file)
+			get_file(file);
 	} else {
 		file = fget(fd);
 	}
@@ -919,7 +921,7 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
 	trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr,
 				ctx->buf_table.nr, ret);
 	mutex_unlock(&ctx->uring_lock);
-	if (!use_registered_ring)
-		fput(file);
+
+	fput(file);
 	return ret;
 }
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index e32ac5853391..af39b69eb4fd 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -118,7 +118,7 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
 	}
 }
 
-struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type)
+struct io_rsrc_node *io_rsrc_node_alloc(int type)
 {
 	struct io_rsrc_node *node;
 
@@ -203,7 +203,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx,
 				err = -EBADF;
 				break;
 			}
-			node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
+			node = io_rsrc_node_alloc(IORING_RSRC_FILE);
 			if (!node) {
 				err = -ENOMEM;
 				fput(file);
@@ -444,8 +444,6 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
 
 void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
 {
-	lockdep_assert_held(&ctx->uring_lock);
-
 	if (node->tag)
 		io_post_aux_cqe(ctx, node->tag, 0, 0);
 
@@ -525,7 +523,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			goto fail;
 		}
 		ret = -ENOMEM;
-		node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
+		node = io_rsrc_node_alloc(IORING_RSRC_FILE);
 		if (!node) {
 			fput(file);
 			goto fail;
@@ -730,7 +728,7 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
 	if (!iov->iov_base)
 		return NULL;
 
-	node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
+	node = io_rsrc_node_alloc(IORING_RSRC_BUFFER);
 	if (!node)
 		return ERR_PTR(-ENOMEM);
 	node->buf = NULL;
@@ -921,6 +919,16 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 	return 0;
 }
 
+/* Lock two rings at once. The rings must be different! */
+static void lock_two_rings(struct io_ring_ctx *ctx1, struct io_ring_ctx *ctx2)
+{
+	if (ctx1 > ctx2)
+		swap(ctx1, ctx2);
+	mutex_lock(&ctx1->uring_lock);
+	mutex_lock_nested(&ctx2->uring_lock, SINGLE_DEPTH_NESTING);
+}
+
+/* Both rings are locked by the caller. */
 static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx,
 			    struct io_uring_clone_buffers *arg)
 {
@@ -928,6 +936,9 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	int i, ret, off, nr;
 	unsigned int nbufs;
 
+	lockdep_assert_held(&ctx->uring_lock);
+	lockdep_assert_held(&src_ctx->uring_lock);
+
 	/*
 	 * Accounting state is shared between the two rings; that only works if
 	 * both rings are accounted towards the same counters.
@@ -942,7 +953,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	if (ctx->buf_table.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
 		return -EBUSY;
 
-	nbufs = READ_ONCE(src_ctx->buf_table.nr);
+	nbufs = src_ctx->buf_table.nr;
 	if (!arg->nr)
 		arg->nr = nbufs;
 	else if (arg->nr > nbufs)
@@ -966,27 +977,20 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		}
 	}
 
-	/*
-	 * Drop our own lock here. We'll setup the data we need and reference
-	 * the source buffers, then re-grab, check, and assign at the end.
-	 */
-	mutex_unlock(&ctx->uring_lock);
-
-	mutex_lock(&src_ctx->uring_lock);
 	ret = -ENXIO;
 	nbufs = src_ctx->buf_table.nr;
 	if (!nbufs)
-		goto out_unlock;
+		goto out_free;
 	ret = -EINVAL;
 	if (!arg->nr)
 		arg->nr = nbufs;
 	else if (arg->nr > nbufs)
-		goto out_unlock;
+		goto out_free;
 	ret = -EOVERFLOW;
 	if (check_add_overflow(arg->nr, arg->src_off, &off))
-		goto out_unlock;
+		goto out_free;
 	if (off > nbufs)
-		goto out_unlock;
+		goto out_free;
 
 	off = arg->dst_off;
 	i = arg->src_off;
@@ -998,10 +1002,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		if (!src_node) {
 			dst_node = NULL;
 		} else {
-			dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
+			dst_node = io_rsrc_node_alloc(IORING_RSRC_BUFFER);
 			if (!dst_node) {
 				ret = -ENOMEM;
-				goto out_unlock;
+				goto out_free;
 			}
 
 			refcount_inc(&src_node->buf->refs);
@@ -1011,10 +1015,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		i++;
 	}
 
-	/* Have a ref on the bufs now, drop src lock and re-grab our own lock */
-	mutex_unlock(&src_ctx->uring_lock);
-	mutex_lock(&ctx->uring_lock);
-
 	/*
 	 * If asked for replace, put the old table. data->nodes[] holds both
 	 * old and new nodes at this point.
@@ -1023,24 +1023,17 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		io_rsrc_data_free(ctx, &ctx->buf_table);
 
 	/*
-	 * ctx->buf_table should be empty now - either the contents are being
-	 * replaced and we just freed the table, or someone raced setting up
-	 * a buffer table while the clone was happening. If not empty, fall
-	 * through to failure handling.
+	 * ctx->buf_table must be empty now - either the contents are being
+	 * replaced and we just freed the table, or the contents are being
+	 * copied to a ring that does not have buffers yet (checked at function
+	 * entry).
 	 */
-	if (!ctx->buf_table.nr) {
-		ctx->buf_table = data;
-		return 0;
-	}
+	WARN_ON_ONCE(ctx->buf_table.nr);
+	ctx->buf_table = data;
+	return 0;
 
-	mutex_unlock(&ctx->uring_lock);
-	mutex_lock(&src_ctx->uring_lock);
-	/* someone raced setting up buffers, dump ours */
-	ret = -EBUSY;
-out_unlock:
+out_free:
 	io_rsrc_data_free(ctx, &data);
-	mutex_unlock(&src_ctx->uring_lock);
-	mutex_lock(&ctx->uring_lock);
 	return ret;
 }
 
@@ -1054,6 +1047,7 @@ out_unlock:
 int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 {
 	struct io_uring_clone_buffers buf;
+	struct io_ring_ctx *src_ctx;
 	bool registered_src;
 	struct file *file;
 	int ret;
@@ -1071,8 +1065,18 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 	file = io_uring_register_get_file(buf.src_fd, registered_src);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
-	ret = io_clone_buffers(ctx, file->private_data, &buf);
-	if (!registered_src)
-		fput(file);
+
+	src_ctx = file->private_data;
+	if (src_ctx != ctx) {
+		mutex_unlock(&ctx->uring_lock);
+		lock_two_rings(ctx, src_ctx);
+	}
+
+	ret = io_clone_buffers(ctx, src_ctx, &buf);
+
+	if (src_ctx != ctx)
+		mutex_unlock(&src_ctx->uring_lock);
+
+	fput(file);
 	return ret;
 }
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index c8b093584461..190f7ee45de9 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -2,6 +2,8 @@
 #ifndef IOU_RSRC_H
 #define IOU_RSRC_H
 
+#include <linux/lockdep.h>
+
 #define IO_NODE_ALLOC_CACHE_MAX 32
 
 #define IO_RSRC_TAG_TABLE_SHIFT	(PAGE_SHIFT - 3)
@@ -43,7 +45,7 @@ struct io_imu_folio_data {
 	unsigned int	nr_folios;
 };
 
-struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type);
+struct io_rsrc_node *io_rsrc_node_alloc(int type);
 void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node);
 void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data);
 int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr);
@@ -80,6 +82,7 @@ static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data
 
 static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
 {
+	lockdep_assert_held(&ctx->uring_lock);
 	if (node && !--node->refs)
 		io_free_rsrc_node(ctx, node);
 }
diff --git a/io_uring/rw.c b/io_uring/rw.c
index a9a2733be842..7aa1e4c9f64a 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -146,28 +146,15 @@ static inline int io_import_iovec(int rw, struct io_kiocb *req,
 	return 0;
 }
 
-static void io_rw_iovec_free(struct io_async_rw *rw)
-{
-	if (rw->free_iovec) {
-		kfree(rw->free_iovec);
-		rw->free_iov_nr = 0;
-		rw->free_iovec = NULL;
-	}
-}
-
 static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_async_rw *rw = req->async_data;
-	struct iovec *iov;
 
-	if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) {
-		io_rw_iovec_free(rw);
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
 		return;
-	}
-	iov = rw->free_iovec;
+
+	io_alloc_cache_kasan(&rw->free_iovec, &rw->free_iov_nr);
 	if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) {
-		if (iov)
-			kasan_mempool_poison_object(iov);
 		req->async_data = NULL;
 		req->flags &= ~REQ_F_ASYNC_DATA;
 	}
@@ -208,27 +195,16 @@ static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags)
 	}
 }
 
-static void io_rw_async_data_init(void *obj)
-{
-	struct io_async_rw *rw = (struct io_async_rw *)obj;
-
-	rw->free_iovec = NULL;
-	rw->bytes_done = 0;
-}
-
 static int io_rw_alloc_async(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	struct io_async_rw *rw;
 
-	rw = io_uring_alloc_async_data(&ctx->rw_cache, req, io_rw_async_data_init);
+	rw = io_uring_alloc_async_data(&ctx->rw_cache, req);
 	if (!rw)
 		return -ENOMEM;
-	if (rw->free_iovec) {
-		kasan_mempool_unpoison_object(rw->free_iovec,
-					      rw->free_iov_nr * sizeof(struct iovec));
+	if (rw->free_iovec)
 		req->flags |= REQ_F_NEED_CLEANUP;
-	}
 	rw->bytes_done = 0;
 	return 0;
 }
@@ -1323,10 +1299,7 @@ void io_rw_cache_free(const void *entry)
 {
 	struct io_async_rw *rw = (struct io_async_rw *) entry;
 
-	if (rw->free_iovec) {
-		kasan_mempool_unpoison_object(rw->free_iovec,
-				rw->free_iov_nr * sizeof(struct iovec));
-		io_rw_iovec_free(rw);
-	}
+	if (rw->free_iovec)
+		kfree(rw->free_iovec);
 	kfree(rw);
 }
diff --git a/io_uring/rw.h b/io_uring/rw.h
index 2d7656bd268d..eaa59bd64870 100644
--- a/io_uring/rw.h
+++ b/io_uring/rw.h
@@ -9,19 +9,24 @@ struct io_meta_state {
 
 struct io_async_rw {
 	size_t				bytes_done;
-	struct iov_iter			iter;
-	struct iov_iter_state		iter_state;
-	struct iovec			fast_iov;
 	struct iovec			*free_iovec;
-	int				free_iov_nr;
-	/* wpq is for buffered io, while meta fields are used with direct io */
-	union {
-		struct wait_page_queue		wpq;
-		struct {
-			struct uio_meta			meta;
-			struct io_meta_state		meta_state;
+	struct_group(clear,
+		struct iov_iter			iter;
+		struct iov_iter_state		iter_state;
+		struct iovec			fast_iov;
+		int				free_iov_nr;
+		/*
+		 * wpq is for buffered io, while meta fields are used with
+		 * direct io
+		 */
+		union {
+			struct wait_page_queue		wpq;
+			struct {
+				struct uio_meta			meta;
+				struct io_meta_state		meta_state;
+			};
 		};
-	};
+	);
 };
 
 int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
diff --git a/io_uring/timeout.c b/io_uring/timeout.c
index 2bd7e0a317bb..48fc8cf70784 100644
--- a/io_uring/timeout.c
+++ b/io_uring/timeout.c
@@ -544,7 +544,7 @@ static int __io_timeout_prep(struct io_kiocb *req,
 
 	if (WARN_ON_ONCE(req_has_async_data(req)))
 		return -EFAULT;
-	data = io_uring_alloc_async_data_nocache(req);
+	data = io_uring_alloc_async_data(NULL, req);
 	if (!data)
 		return -ENOMEM;
 	data->req = req;
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index fc94c465a985..1f6a82128b47 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -168,23 +168,16 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, u64 res2,
 }
 EXPORT_SYMBOL_GPL(io_uring_cmd_done);
 
-static void io_uring_cmd_init_once(void *obj)
-{
-	struct io_uring_cmd_data *data = obj;
-
-	data->op_data = NULL;
-}	
-
 static int io_uring_cmd_prep_setup(struct io_kiocb *req,
 				   const struct io_uring_sqe *sqe)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
 	struct io_uring_cmd_data *cache;
 
-	cache = io_uring_alloc_async_data(&req->ctx->uring_cache, req,
-			io_uring_cmd_init_once);
+	cache = io_uring_alloc_async_data(&req->ctx->uring_cache, req);
 	if (!cache)
 		return -ENOMEM;
+	cache->op_data = NULL;
 
 	if (!(req->flags & REQ_F_FORCE_ASYNC)) {
 		/* defer memcpy until we need it */
@@ -192,8 +185,8 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req,
 		return 0;
 	}
 
-	memcpy(req->async_data, sqe, uring_sqe_size(req->ctx));
-	ioucmd->sqe = req->async_data;
+	memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx));
+	ioucmd->sqe = cache->sqes;
 	return 0;
 }
 
@@ -260,7 +253,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 		struct io_uring_cmd_data *cache = req->async_data;
 
 		if (ioucmd->sqe != (void *) cache)
-			memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx));
+			memcpy(cache->sqes, ioucmd->sqe, uring_sqe_size(req->ctx));
 		return -EAGAIN;
 	} else if (ret == -EIOCBQUEUED) {
 		return -EIOCBQUEUED;
@@ -350,7 +343,7 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
 	if (!prot || !prot->ioctl)
 		return -EOPNOTSUPP;
 
-	switch (cmd->sqe->cmd_op) {
+	switch (cmd->cmd_op) {
 	case SOCKET_URING_OP_SIOCINQ:
 		ret = prot->ioctl(sk, SIOCINQ, &arg);
 		if (ret)
diff --git a/io_uring/waitid.c b/io_uring/waitid.c
index 6778c0ee76c4..853e97a7b0ec 100644
--- a/io_uring/waitid.c
+++ b/io_uring/waitid.c
@@ -303,7 +303,7 @@ int io_waitid(struct io_kiocb *req, unsigned int issue_flags)
 	struct io_waitid_async *iwa;
 	int ret;
 
-	iwa = io_uring_alloc_async_data_nocache(req);
+	iwa = io_uring_alloc_async_data(NULL, req);
 	if (!iwa)
 		return -ENOMEM;
 
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 54318e0b4557..15b17e86e198 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -73,7 +73,7 @@ int ipc_mni = IPCMNI;
 int ipc_mni_shift = IPCMNI_SHIFT;
 int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
 
-static struct ctl_table ipc_sysctls[] = {
+static const struct ctl_table ipc_sysctls[] = {
 	{
 		.procname	= "shmmax",
 		.data		= &init_ipc_ns.shm_ctlmax,
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index b70dc2ff22d8..0dd12e1c9f53 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -20,7 +20,7 @@ static int msg_max_limit_max = HARD_MSGMAX;
 static int msg_maxsize_limit_min = MIN_MSGSIZEMAX;
 static int msg_maxsize_limit_max = HARD_MSGSIZEMAX;
 
-static struct ctl_table mq_sysctls[] = {
+static const struct ctl_table mq_sysctls[] = {
 	{
 		.procname	= "queues_max",
 		.data		= &init_ipc_ns.mq_queues_max,
diff --git a/ipc/util.c b/ipc/util.c
index 05cb9de66735..cae60f11d9c2 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -615,12 +615,11 @@ void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out)
 }
 
 /**
- * ipc_obtain_object_idr
+ * ipc_obtain_object_idr - Look for an id in the ipc ids idr and
+ *   return associated ipc object.
  * @ids: ipc identifier set
  * @id: ipc id to look for
  *
- * Look for an id in the ipc ids idr and return associated ipc object.
- *
  * Call inside the RCU critical section.
  * The ipc object is *not* locked on exit.
  */
@@ -637,13 +636,11 @@ struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id)
 }
 
 /**
- * ipc_obtain_object_check
+ * ipc_obtain_object_check - Similar to ipc_obtain_object_idr() but
+ *   also checks the ipc object sequence number.
  * @ids: ipc identifier set
  * @id: ipc id to look for
  *
- * Similar to ipc_obtain_object_idr() but also checks the ipc object
- * sequence number.
- *
  * Call inside the RCU critical section.
  * The ipc object is *not* locked on exit.
  */
diff --git a/kernel/acct.c b/kernel/acct.c
index 179848ad33e9..31222e8cd534 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -76,7 +76,7 @@ static int acct_parm[3] = {4, 2, 30};
 #define ACCT_TIMEOUT	(acct_parm[2])	/* foo second timeout between checks */
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_acct_table[] = {
+static const struct ctl_table kern_acct_table[] = {
 	{
 		.procname       = "acct",
 		.data           = &acct_parm,
diff --git a/kernel/audit.c b/kernel/audit.c
index 13d0144efaa3..5f5bf85bcc90 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1221,7 +1221,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct audit_buffer	*ab;
 	u16			msg_type = nlh->nlmsg_type;
 	struct audit_sig_info   *sig_data;
-	struct lsm_context	lsmctx;
+	struct lsm_context	lsmctx = { NULL, 0, 0 };
 
 	err = audit_netlink_ok(skb, msg_type);
 	if (err)
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 4b22a651b5d5..870aeb51d70a 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -445,7 +445,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 			return 0;
 	}
 
-	/* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */
+	/* zeroing is needed, since alloc_pages_bulk() only fills in non-zero entries */
 	pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return 0;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 8396ce1d0fba..9de6acddd479 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -8001,17 +8001,6 @@ struct btf_module {
 static LIST_HEAD(btf_modules);
 static DEFINE_MUTEX(btf_module_mutex);
 
-static ssize_t
-btf_module_read(struct file *file, struct kobject *kobj,
-		struct bin_attribute *bin_attr,
-		char *buf, loff_t off, size_t len)
-{
-	const struct btf *btf = bin_attr->private;
-
-	memcpy(buf, btf->data + off, len);
-	return len;
-}
-
 static void purge_cand_cache(struct btf *btf);
 
 static int btf_module_notify(struct notifier_block *nb, unsigned long op,
@@ -8072,8 +8061,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op,
 			attr->attr.name = btf->name;
 			attr->attr.mode = 0444;
 			attr->size = btf->data_size;
-			attr->private = btf;
-			attr->read = btf_module_read;
+			attr->private = btf->data;
+			attr->read_new = sysfs_bin_attr_simple_read;
 
 			err = sysfs_create_bin_file(btf_kobj, attr);
 			if (err) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0daf098e3207..c420edbfb7c8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -6128,7 +6128,7 @@ static int bpf_unpriv_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table bpf_syscall_table[] = {
+static const struct ctl_table bpf_syscall_table[] = {
 	{
 		.procname	= "unprivileged_bpf_disabled",
 		.data		= &sysctl_unprivileged_bpf_disabled,
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
index fedb54c94cdb..81d6cf90584a 100644
--- a/kernel/bpf/sysfs_btf.c
+++ b/kernel/bpf/sysfs_btf.c
@@ -12,24 +12,16 @@
 extern char __start_BTF[];
 extern char __stop_BTF[];
 
-static ssize_t
-btf_vmlinux_read(struct file *file, struct kobject *kobj,
-		 struct bin_attribute *bin_attr,
-		 char *buf, loff_t off, size_t len)
-{
-	memcpy(buf, __start_BTF + off, len);
-	return len;
-}
-
 static struct bin_attribute bin_attr_btf_vmlinux __ro_after_init = {
 	.attr = { .name = "vmlinux", .mode = 0444, },
-	.read = btf_vmlinux_read,
+	.read_new = sysfs_bin_attr_simple_read,
 };
 
 struct kobject *btf_kobj;
 
 static int __init btf_vmlinux_init(void)
 {
+	bin_attr_btf_vmlinux.private = __start_BTF;
 	bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF;
 
 	if (bin_attr_btf_vmlinux.size == 0)
diff --git a/kernel/capability.c b/kernel/capability.c
index dac4df77e376..e089d2628c29 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -38,10 +38,8 @@ __setup("no_file_caps", file_caps_disable);
 
 static void warn_legacy_capability_use(void)
 {
-	char name[sizeof(current->comm)];
-
 	pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n",
-		     get_task_comm(name, current));
+		     current->comm);
 }
 
 /*
@@ -62,10 +60,8 @@ static void warn_legacy_capability_use(void)
 
 static void warn_deprecated_v2(void)
 {
-	char name[sizeof(current->comm)];
-
 	pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n",
-		     get_task_comm(name, current));
+		     current->comm);
 }
 
 /*
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0509a9733745..07455d25329c 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -905,12 +905,13 @@ static int finish_cpu(unsigned int cpu)
 	struct mm_struct *mm = idle->active_mm;
 
 	/*
-	 * idle_task_exit() will have switched to &init_mm, now
-	 * clean up any remaining active_mm state.
+	 * sched_force_init_mm() ensured the use of &init_mm,
+	 * drop that refcount now that the CPU has stopped.
 	 */
-	if (mm != &init_mm)
-		idle->active_mm = &init_mm;
+	WARN_ON(mm != &init_mm);
+	idle->active_mm = NULL;
 	mmdrop_lazy_tlb(mm);
+
 	return 0;
 }
 
@@ -3128,11 +3129,6 @@ void init_cpu_possible(const struct cpumask *src)
 	cpumask_copy(&__cpu_possible_mask, src);
 }
 
-void init_cpu_online(const struct cpumask *src)
-{
-	cpumask_copy(&__cpu_online_mask, src);
-}
-
 void set_cpu_online(unsigned int cpu, bool online)
 {
 	/*
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index dead51de8eb5..eb63a021ac04 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -64,7 +64,7 @@ static int sysctl_delayacct(const struct ctl_table *table, int write, void *buff
 	return err;
 }
 
-static struct ctl_table kern_delayacct_table[] = {
+static const struct ctl_table kern_delayacct_table[] = {
 	{
 		.procname       = "task_delayacct",
 		.data           = NULL,
@@ -93,9 +93,9 @@ void __delayacct_tsk_init(struct task_struct *tsk)
 
 /*
  * Finish delay accounting for a statistic using its timestamps (@start),
- * accumalator (@total) and @count
+ * accumulator (@total) and @count
  */
-static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count)
+static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count, u64 *max, u64 *min)
 {
 	s64 ns = local_clock() - *start;
 	unsigned long flags;
@@ -104,6 +104,10 @@ static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *cou
 		raw_spin_lock_irqsave(lock, flags);
 		*total += ns;
 		(*count)++;
+		if (ns > *max)
+			*max = ns;
+		if (*min == 0 || ns < *min)
+			*min = ns;
 		raw_spin_unlock_irqrestore(lock, flags);
 	}
 }
@@ -122,7 +126,9 @@ void __delayacct_blkio_end(struct task_struct *p)
 	delayacct_end(&p->delays->lock,
 		      &p->delays->blkio_start,
 		      &p->delays->blkio_delay,
-		      &p->delays->blkio_count);
+		      &p->delays->blkio_count,
+		      &p->delays->blkio_delay_max,
+		      &p->delays->blkio_delay_min);
 }
 
 int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
@@ -153,10 +159,12 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 
 	d->cpu_count += t1;
 
+	d->cpu_delay_max = tsk->sched_info.max_run_delay;
+	d->cpu_delay_min = tsk->sched_info.min_run_delay;
 	tmp = (s64)d->cpu_delay_total + t2;
 	d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp;
-
 	tmp = (s64)d->cpu_run_virtual_total + t3;
+
 	d->cpu_run_virtual_total =
 		(tmp < (s64)d->cpu_run_virtual_total) ?	0 : tmp;
 
@@ -164,20 +172,33 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 		return 0;
 
 	/* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */
-
 	raw_spin_lock_irqsave(&tsk->delays->lock, flags);
+	d->blkio_delay_max = tsk->delays->blkio_delay_max;
+	d->blkio_delay_min = tsk->delays->blkio_delay_min;
 	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
 	d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp;
+	d->swapin_delay_max = tsk->delays->swapin_delay_max;
+	d->swapin_delay_min = tsk->delays->swapin_delay_min;
 	tmp = d->swapin_delay_total + tsk->delays->swapin_delay;
 	d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp;
+	d->freepages_delay_max = tsk->delays->freepages_delay_max;
+	d->freepages_delay_min = tsk->delays->freepages_delay_min;
 	tmp = d->freepages_delay_total + tsk->delays->freepages_delay;
 	d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp;
+	d->thrashing_delay_max = tsk->delays->thrashing_delay_max;
+	d->thrashing_delay_min = tsk->delays->thrashing_delay_min;
 	tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay;
 	d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp;
+	d->compact_delay_max = tsk->delays->compact_delay_max;
+	d->compact_delay_min = tsk->delays->compact_delay_min;
 	tmp = d->compact_delay_total + tsk->delays->compact_delay;
 	d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
+	d->wpcopy_delay_max = tsk->delays->wpcopy_delay_max;
+	d->wpcopy_delay_min = tsk->delays->wpcopy_delay_min;
 	tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay;
 	d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp;
+	d->irq_delay_max = tsk->delays->irq_delay_max;
+	d->irq_delay_min = tsk->delays->irq_delay_min;
 	tmp = d->irq_delay_total + tsk->delays->irq_delay;
 	d->irq_delay_total = (tmp < d->irq_delay_total) ? 0 : tmp;
 	d->blkio_count += tsk->delays->blkio_count;
@@ -213,7 +234,9 @@ void __delayacct_freepages_end(void)
 	delayacct_end(&current->delays->lock,
 		      &current->delays->freepages_start,
 		      &current->delays->freepages_delay,
-		      &current->delays->freepages_count);
+		      &current->delays->freepages_count,
+		      &current->delays->freepages_delay_max,
+		      &current->delays->freepages_delay_min);
 }
 
 void __delayacct_thrashing_start(bool *in_thrashing)
@@ -235,7 +258,9 @@ void __delayacct_thrashing_end(bool *in_thrashing)
 	delayacct_end(&current->delays->lock,
 		      &current->delays->thrashing_start,
 		      &current->delays->thrashing_delay,
-		      &current->delays->thrashing_count);
+		      &current->delays->thrashing_count,
+		      &current->delays->thrashing_delay_max,
+		      &current->delays->thrashing_delay_min);
 }
 
 void __delayacct_swapin_start(void)
@@ -248,7 +273,9 @@ void __delayacct_swapin_end(void)
 	delayacct_end(&current->delays->lock,
 		      &current->delays->swapin_start,
 		      &current->delays->swapin_delay,
-		      &current->delays->swapin_count);
+		      &current->delays->swapin_count,
+		      &current->delays->swapin_delay_max,
+		      &current->delays->swapin_delay_min);
 }
 
 void __delayacct_compact_start(void)
@@ -261,7 +288,9 @@ void __delayacct_compact_end(void)
 	delayacct_end(&current->delays->lock,
 		      &current->delays->compact_start,
 		      &current->delays->compact_delay,
-		      &current->delays->compact_count);
+		      &current->delays->compact_count,
+		      &current->delays->compact_delay_max,
+		      &current->delays->compact_delay_min);
 }
 
 void __delayacct_wpcopy_start(void)
@@ -274,7 +303,9 @@ void __delayacct_wpcopy_end(void)
 	delayacct_end(&current->delays->lock,
 		      &current->delays->wpcopy_start,
 		      &current->delays->wpcopy_delay,
-		      &current->delays->wpcopy_count);
+		      &current->delays->wpcopy_count,
+		      &current->delays->wpcopy_delay_max,
+		      &current->delays->wpcopy_delay_min);
 }
 
 void __delayacct_irq(struct task_struct *task, u32 delta)
@@ -284,6 +315,10 @@ void __delayacct_irq(struct task_struct *task, u32 delta)
 	raw_spin_lock_irqsave(&task->delays->lock, flags);
 	task->delays->irq_delay += delta;
 	task->delays->irq_count++;
+	if (delta > task->delays->irq_delay_max)
+		task->delays->irq_delay_max = delta;
+	if (delta && (!task->delays->irq_delay_min || delta < task->delays->irq_delay_min))
+		task->delays->irq_delay_min = delta;
 	raw_spin_unlock_irqrestore(&task->delays->lock, flags);
 }
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index e421a5f2ec7d..2ca797cbe465 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -28,6 +28,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/workqueue.h>
 #include <linux/srcu.h>
+#include <linux/oom.h>          /* check_stable_address_space */
 
 #include <linux/uprobes.h>
 
@@ -1260,6 +1261,9 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new)
 		 * returns NULL in find_active_uprobe_rcu().
 		 */
 		mmap_write_lock(mm);
+		if (check_stable_address_space(mm))
+			goto unlock;
+
 		vma = find_vma(mm, info->vaddr);
 		if (!vma || !valid_vma(vma, is_register) ||
 		    file_inode(vma->vm_file) != uprobe->inode)
diff --git a/kernel/exit.c b/kernel/exit.c
index 1dcddfe537ee..3485e5fc499e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -85,7 +85,7 @@
 static unsigned int oops_limit = 10000;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_exit_table[] = {
+static const struct ctl_table kern_exit_table[] = {
 	{
 		.procname       = "oops_limit",
 		.data           = &oops_limit,
diff --git a/kernel/fork.c b/kernel/fork.c
index 2fa2a3582925..735405a9c5f3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -760,7 +760,8 @@ loop_out:
 		mt_set_in_rcu(vmi.mas.tree);
 		ksm_fork(mm, oldmm);
 		khugepaged_fork(mm, oldmm);
-	} else if (mpnt) {
+	} else {
+
 		/*
 		 * The entire maple tree has already been duplicated. If the
 		 * mmap duplication fails, mark the failure point with
@@ -768,8 +769,18 @@ loop_out:
 		 * stop releasing VMAs that have not been duplicated after this
 		 * point.
 		 */
-		mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
-		mas_store(&vmi.mas, XA_ZERO_ENTRY);
+		if (mpnt) {
+			mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1);
+			mas_store(&vmi.mas, XA_ZERO_ENTRY);
+			/* Avoid OOM iterating a broken tree */
+			set_bit(MMF_OOM_SKIP, &mm->flags);
+		}
+		/*
+		 * The mm_struct is going to exit, but the locks will be dropped
+		 * first.  Set the mm_struct as unstable is advisable as it is
+		 * not fully initialised.
+		 */
+		set_bit(MMF_UNSTABLE, &mm->flags);
 	}
 out:
 	mmap_write_unlock(mm);
@@ -1511,12 +1522,13 @@ struct file *get_task_exe_file(struct task_struct *task)
 	struct file *exe_file = NULL;
 	struct mm_struct *mm;
 
+	if (task->flags & PF_KTHREAD)
+		return NULL;
+
 	task_lock(task);
 	mm = task->mm;
-	if (mm) {
-		if (!(task->flags & PF_KTHREAD))
-			exe_file = get_mm_exe_file(mm);
-	}
+	if (mm)
+		exe_file = get_mm_exe_file(mm);
 	task_unlock(task);
 	return exe_file;
 }
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index ebdd76b4ecbb..3db8567f5a44 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -532,7 +532,8 @@ void futex_q_unlock(struct futex_hash_bucket *hb)
 	futex_hb_waiters_dec(hb);
 }
 
-void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
+void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+		   struct task_struct *task)
 {
 	int prio;
 
@@ -548,7 +549,7 @@ void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
 
 	plist_node_init(&q->list, prio);
 	plist_add(&q->list, &hb->chain);
-	q->task = current;
+	q->task = task;
 }
 
 /**
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 99b32e728c4a..6b2f4c7eb720 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -285,13 +285,15 @@ static inline int futex_get_value_locked(u32 *dest, u32 __user *from)
 }
 
 extern void __futex_unqueue(struct futex_q *q);
-extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb);
+extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+				struct task_struct *task);
 extern int futex_unqueue(struct futex_q *q);
 
 /**
  * futex_queue() - Enqueue the futex_q on the futex_hash_bucket
  * @q:	The futex_q to enqueue
  * @hb:	The destination hash bucket
+ * @task: Task queueing this futex
  *
  * The hb->lock must be held by the caller, and is released here. A call to
  * futex_queue() is typically paired with exactly one call to futex_unqueue().  The
@@ -299,11 +301,14 @@ extern int futex_unqueue(struct futex_q *q);
  * or nothing if the unqueue is done as part of the wake process and the unqueue
  * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
  * an example).
+ *
+ * Note that @task may be NULL, for async usage of futexes.
  */
-static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb)
+static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb,
+			       struct task_struct *task)
 	__releases(&hb->lock)
 {
-	__futex_queue(q, hb);
+	__futex_queue(q, hb, task);
 	spin_unlock(&hb->lock);
 }
 
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index daea650b16f5..7a941845f7ee 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -982,7 +982,7 @@ retry_private:
 	/*
 	 * Only actually queue now that the atomic ops are done:
 	 */
-	__futex_queue(&q, hb);
+	__futex_queue(&q, hb, current);
 
 	if (trylock) {
 		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c
index 3a10375d9521..25877d4f2f8f 100644
--- a/kernel/futex/waitwake.c
+++ b/kernel/futex/waitwake.c
@@ -210,13 +210,12 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
 		if (oparg < 0 || oparg > 31) {
-			char comm[sizeof(current->comm)];
 			/*
 			 * kill this print and return -EINVAL when userspace
 			 * is sane again
 			 */
 			pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
-					get_task_comm(comm, current), oparg);
+					    current->comm, oparg);
 			oparg &= 31;
 		}
 		oparg = 1 << oparg;
@@ -350,7 +349,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q,
 	 * access to the hash list and forcing another memory barrier.
 	 */
 	set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
-	futex_queue(q, hb);
+	futex_queue(q, hb, current);
 
 	/* Arm the timer */
 	if (timeout)
@@ -461,7 +460,7 @@ retry:
 			 * next futex. Queue each futex at this moment so hb can
 			 * be unlocked.
 			 */
-			futex_queue(q, hb);
+			futex_queue(q, hb, current);
 			continue;
 		}
 
diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c
index 7670a811a565..8b888a6193cc 100644
--- a/kernel/gcov/clang.c
+++ b/kernel/gcov/clang.c
@@ -264,10 +264,10 @@ int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
 
 /**
  * gcov_info_add - add up profiling data
- * @dest: profiling data set to which data is added
- * @source: profiling data set which is added
+ * @dst: profiling data set to which data is added
+ * @src: profiling data set which is added
  *
- * Adds profiling counts of @source to @dest.
+ * Adds profiling counts of @src to @dst.
  */
 void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
 {
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 7e1340da5aca..00529c81cc40 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -7,20 +7,13 @@ set -e
 sfile="$(readlink -f "$0")"
 outdir="$(pwd)"
 tarfile=$1
-cpio_dir=$outdir/${tarfile%/*}/.tmp_cpio_dir
+tmpdir=$outdir/${tarfile%/*}/.tmp_dir
 
 dir_list="
 include/
 arch/$SRCARCH/include/
 "
 
-if ! command -v cpio >/dev/null; then
-	echo >&2 "***"
-	echo >&2 "*** 'cpio' could not be found."
-	echo >&2 "***"
-	exit 1
-fi
-
 # Support incremental builds by skipping archive generation
 # if timestamps of files being archived are not changed.
 
@@ -48,9 +41,9 @@ all_dirs="$all_dirs $dir_list"
 # check include/generated/autoconf.h explicitly.
 #
 # Ignore them for md5 calculation to avoid pointless regeneration.
-headers_md5="$(find $all_dirs -name "*.h"			|
-		grep -v "include/generated/utsversion.h"	|
-		grep -v "include/generated/autoconf.h"	|
+headers_md5="$(find $all_dirs -name "*.h" -a			\
+		! -path include/generated/utsversion.h -a	\
+		! -path include/generated/autoconf.h		|
 		xargs ls -l | md5sum | cut -d ' ' -f1)"
 
 # Any changes to this script will also cause a rebuild of the archive.
@@ -65,36 +58,43 @@ fi
 
 echo "  GEN     $tarfile"
 
-rm -rf $cpio_dir
-mkdir $cpio_dir
+rm -rf "${tmpdir}"
+mkdir "${tmpdir}"
 
 if [ "$building_out_of_srctree" ]; then
 	(
 		cd $srctree
 		for f in $dir_list
 			do find "$f" -name "*.h";
-		done | cpio --quiet -pd $cpio_dir
+		done | tar -c -f - -T - | tar -xf - -C "${tmpdir}"
 	)
 fi
 
-# The second CPIO can complain if files already exist which can happen with out
-# of tree builds having stale headers in srctree. Just silence CPIO for now.
 for f in $dir_list;
 	do find "$f" -name "*.h";
-done | cpio --quiet -pdu $cpio_dir >/dev/null 2>&1
+done | tar -c -f - -T - | tar -xf - -C "${tmpdir}"
+
+# Always exclude include/generated/utsversion.h
+# Otherwise, the contents of the tarball may vary depending on the build steps.
+rm -f "${tmpdir}/include/generated/utsversion.h"
 
 # Remove comments except SDPX lines
-find $cpio_dir -type f -print0 |
-	xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;'
+# Use a temporary file to store directory contents to prevent find/xargs from
+# seeing temporary files created by perl.
+find "${tmpdir}" -type f -print0 > "${tmpdir}.contents.txt"
+xargs -0 -P8 -n1 \
+	perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' \
+	< "${tmpdir}.contents.txt"
+rm -f "${tmpdir}.contents.txt"
 
 # Create archive and try to normalize metadata for reproducibility.
 tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
     --exclude=".__afs*" --exclude=".nfs*" \
     --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \
-    -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null
+    -I $XZ -cf $tarfile -C "${tmpdir}/" . > /dev/null
 
 echo $headers_md5 > kernel/kheaders.md5
 echo "$this_file_md5" >> kernel/kheaders.md5
 echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5
 
-rm -rf $cpio_dir
+rm -rf "${tmpdir}"
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index c18717189f32..04efa7a6e69b 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -147,6 +147,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 			print_tainted(), init_utsname()->release,
 			(int)strcspn(init_utsname()->version, " "),
 			init_utsname()->version);
+		if (t->flags & PF_POSTCOREDUMP)
+			pr_err("      Blocked by coredump.\n");
 		pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
 			" disables this message.\n");
 		sched_show_task(t);
@@ -272,7 +274,7 @@ static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int writ
  * and hung_task_check_interval_secs
  */
 static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ);
-static struct ctl_table hung_task_sysctls[] = {
+static const struct ctl_table hung_task_sysctls[] = {
 #ifdef CONFIG_SMP
 	{
 		.procname	= "hung_task_all_cpu_backtrace",
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 2f4fb336dda1..73f7e1fd4ab4 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -147,7 +147,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (!irq_work_claim(work))
 		return false;
 
-	kasan_record_aux_stack_noalloc(work);
+	kasan_record_aux_stack(work);
 
 	preempt_disable();
 	if (cpu != smp_processor_id()) {
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index b424a5c6ae87..c0bdc1686154 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -925,7 +925,7 @@ static int kexec_limit_handler(const struct ctl_table *table, int write,
 	return proc_dointvec(&tmp, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table kexec_core_sysctls[] = {
+static const struct ctl_table kexec_core_sysctls[] = {
 	{
 		.procname	= "kexec_load_disabled",
 		.data		= &kexec_load_disabled,
diff --git a/kernel/kheaders.c b/kernel/kheaders.c
index 42163c9e94e5..378088b07f46 100644
--- a/kernel/kheaders.c
+++ b/kernel/kheaders.c
@@ -29,25 +29,12 @@ asm (
 extern char kernel_headers_data[];
 extern char kernel_headers_data_end[];
 
-static ssize_t
-ikheaders_read(struct file *file,  struct kobject *kobj,
-	       struct bin_attribute *bin_attr,
-	       char *buf, loff_t off, size_t len)
-{
-	memcpy(buf, &kernel_headers_data[off], len);
-	return len;
-}
-
-static struct bin_attribute kheaders_attr __ro_after_init = {
-	.attr = {
-		.name = "kheaders.tar.xz",
-		.mode = 0444,
-	},
-	.read = &ikheaders_read,
-};
+static struct bin_attribute kheaders_attr __ro_after_init =
+	__BIN_ATTR_SIMPLE_RO(kheaders.tar.xz, 0444);
 
 static int __init ikheaders_init(void)
 {
+	kheaders_attr.private = kernel_headers_data;
 	kheaders_attr.size = (kernel_headers_data_end -
 			      kernel_headers_data);
 	return sysfs_create_bin_file(kernel_kobj, &kheaders_attr);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 030569210670..88aeac84e4c0 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -946,7 +946,7 @@ static int proc_kprobes_optimization_handler(const struct ctl_table *table,
 	return ret;
 }
 
-static struct ctl_table kprobe_sysctls[] = {
+static const struct ctl_table kprobe_sysctls[] = {
 	{
 		.procname	= "kprobes-optimization",
 		.data		= &sysctl_kprobes_optimization,
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 1bab21b4718f..eefb67d9883c 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -239,21 +239,7 @@ extern const void __start_notes;
 extern const void __stop_notes;
 #define	notes_size (&__stop_notes - &__start_notes)
 
-static ssize_t notes_read(struct file *filp, struct kobject *kobj,
-			  struct bin_attribute *bin_attr,
-			  char *buf, loff_t off, size_t count)
-{
-	memcpy(buf, &__start_notes + off, count);
-	return count;
-}
-
-static struct bin_attribute notes_attr __ro_after_init  = {
-	.attr = {
-		.name = "notes",
-		.mode = S_IRUGO,
-	},
-	.read = &notes_read,
-};
+static __ro_after_init BIN_ATTR_SIMPLE_RO(notes);
 
 struct kobject *kernel_kobj;
 EXPORT_SYMBOL_GPL(kernel_kobj);
@@ -307,8 +293,9 @@ static int __init ksysfs_init(void)
 		goto kset_exit;
 
 	if (notes_size > 0) {
-		notes_attr.size = notes_size;
-		error = sysfs_create_bin_file(kernel_kobj, &notes_attr);
+		bin_attr_notes.private = (void *)&__start_notes;
+		bin_attr_notes.size = notes_size;
+		error = sysfs_create_bin_file(kernel_kobj, &bin_attr_notes);
 		if (error)
 			goto group_exit;
 	}
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 6a034c76b6e9..5dc5b0d7238e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -859,7 +859,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
 	struct kthread *kthread = to_kthread(p);
 	cpumask_var_t affinity;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) {
 		WARN_ON(1);
@@ -892,7 +892,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask)
 out:
 	free_cpumask_var(affinity);
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -1175,7 +1175,7 @@ static void kthread_insert_work(struct kthread_worker *worker,
  * @work: kthread_work to queue
  *
  * Queue @work to work processor @task for async execution.  @task
- * must have been created with kthread_worker_create().  Returns %true
+ * must have been created with kthread_create_worker().  Returns %true
  * if @work was successfully queued, %false if it was already pending.
  *
  * Reinitialize the work if it needs to be used by another worker.
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 7a75eab9c179..d4281d1e13a6 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -77,7 +77,7 @@ static int sysctl_latencytop(const struct ctl_table *table, int write, void *buf
 	return err;
 }
 
-static struct ctl_table latencytop_sysctl[] = {
+static const struct ctl_table latencytop_sysctl[] = {
 	{
 		.procname   = "latencytop",
 		.data       = &latencytop_enabled,
@@ -158,9 +158,9 @@ account_global_scheduler_latency(struct task_struct *tsk,
 
 /**
  * __account_scheduler_latency - record an occurred latency
- * @tsk - the task struct of the task hitting the latency
- * @usecs - the duration of the latency in microseconds
- * @inter - 1 if the sleep was interruptible, 0 if uninterruptible
+ * @tsk: the task struct of the task hitting the latency
+ * @usecs: the duration of the latency in microseconds
+ * @inter: 1 if the sleep was interruptible, 0 if uninterruptible
  *
  * This function is the main entry point for recording latency entries
  * as called by the scheduler.
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 29acd238dad7..4470680f0226 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644);
 #endif
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_lockdep_table[] = {
+static const struct ctl_table kern_lockdep_table[] = {
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname       = "prove_locking",
diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig
index 7b329057997a..d7762ef5949a 100644
--- a/kernel/module/Kconfig
+++ b/kernel/module/Kconfig
@@ -169,6 +169,36 @@ config MODVERSIONS
 	  make them incompatible with the kernel you are running.  If
 	  unsure, say N.
 
+choice
+	prompt "Module versioning implementation"
+	depends on MODVERSIONS
+	help
+	  Select the tool used to calculate symbol versions for modules.
+
+	  If unsure, select GENKSYMS.
+
+config GENKSYMS
+	bool "genksyms (from source code)"
+	help
+	  Calculate symbol versions from pre-processed source code using
+	  genksyms.
+
+	  If unsure, say Y.
+
+config GENDWARFKSYMS
+	bool "gendwarfksyms (from debugging information)"
+	depends on DEBUG_INFO
+	# Requires full debugging information, split DWARF not supported.
+	depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT
+	# Requires ELF object files.
+	depends on !LTO
+	help
+	  Calculate symbol versions from DWARF debugging information using
+	  gendwarfksyms. Requires DEBUG_INFO to be enabled.
+
+	  If unsure, say N.
+endchoice
+
 config ASM_MODVERSIONS
 	bool
 	default HAVE_ASM_MODVERSIONS && MODVERSIONS
@@ -177,6 +207,31 @@ config ASM_MODVERSIONS
 	  assembly. This can be enabled only when the target architecture
 	  supports it.
 
+config EXTENDED_MODVERSIONS
+	bool "Extended Module Versioning Support"
+	depends on MODVERSIONS
+	help
+	  This enables extended MODVERSIONs support, allowing long symbol
+	  names to be versioned.
+
+	  The most likely reason you would enable this is to enable Rust
+	  support. If unsure, say N.
+
+config BASIC_MODVERSIONS
+	bool "Basic Module Versioning Support"
+	depends on MODVERSIONS
+	default y
+	help
+	  This enables basic MODVERSIONS support, allowing older tools or
+	  kernels to potentially load modules.
+
+	  Disabling this may cause older `modprobe` or `kmod` to be unable
+	  to read MODVERSIONS information from built modules. With this
+	  disabled, older kernels may treat this module as unversioned.
+
+	  This is enabled by default when MODVERSIONS are enabled.
+	  If unsure, say Y.
+
 config MODULE_SRCVERSION_ALL
 	bool "Source checksum for all modules"
 	help
@@ -231,6 +286,7 @@ comment "Do not forget to sign required modules with scripts/sign-file"
 choice
 	prompt "Hash algorithm to sign modules"
 	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
+	default MODULE_SIG_SHA512
 	help
 	  This determines which sort of hashing algorithm will be used during
 	  signature generation.  This algorithm _must_ be built into the kernel
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index daef2be83902..d09b46ef032f 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -47,16 +47,16 @@ struct kernel_symbol {
 extern struct mutex module_mutex;
 extern struct list_head modules;
 
-extern struct module_attribute *modinfo_attrs[];
-extern size_t modinfo_attrs_count;
+extern const struct module_attribute *const modinfo_attrs[];
+extern const size_t modinfo_attrs_count;
 
 /* Provided by the linker */
 extern const struct kernel_symbol __start___ksymtab[];
 extern const struct kernel_symbol __stop___ksymtab[];
 extern const struct kernel_symbol __start___ksymtab_gpl[];
 extern const struct kernel_symbol __stop___ksymtab_gpl[];
-extern const s32 __start___kcrctab[];
-extern const s32 __start___kcrctab_gpl[];
+extern const u32 __start___kcrctab[];
+extern const u32 __start___kcrctab_gpl[];
 
 struct load_info {
 	const char *name;
@@ -86,6 +86,8 @@ struct load_info {
 		unsigned int vers;
 		unsigned int info;
 		unsigned int pcpu;
+		unsigned int vers_ext_crc;
+		unsigned int vers_ext_name;
 	} index;
 };
 
@@ -102,7 +104,7 @@ struct find_symbol_arg {
 
 	/* Output */
 	struct module *owner;
-	const s32 *crc;
+	const u32 *crc;
 	const struct kernel_symbol *sym;
 	enum mod_license license;
 };
@@ -327,7 +329,8 @@ static inline struct module *mod_find(unsigned long addr, struct mod_tree_root *
 }
 #endif /* CONFIG_MODULES_TREE_LOOKUP */
 
-int module_enable_rodata_ro(const struct module *mod, bool after_init);
+int module_enable_rodata_ro(const struct module *mod);
+int module_enable_rodata_ro_after_init(const struct module *mod);
 int module_enable_data_nx(const struct module *mod);
 int module_enable_text_rox(const struct module *mod);
 int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
@@ -384,16 +387,25 @@ static inline void init_param_lock(struct module *mod) { }
 
 #ifdef CONFIG_MODVERSIONS
 int check_version(const struct load_info *info,
-		  const char *symname, struct module *mod, const s32 *crc);
+		  const char *symname, struct module *mod, const u32 *crc);
 void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp,
 		   struct kernel_symbol *ks, struct tracepoint * const *tp);
 int check_modstruct_version(const struct load_info *info, struct module *mod);
 int same_magic(const char *amagic, const char *bmagic, bool has_crcs);
+struct modversion_info_ext {
+	size_t remaining;
+	const u32 *crc;
+	const char *name;
+};
+void modversion_ext_start(const struct load_info *info, struct modversion_info_ext *ver);
+void modversion_ext_advance(struct modversion_info_ext *ver);
+#define for_each_modversion_info_ext(ver, info) \
+	for (modversion_ext_start(info, &ver); ver.remaining > 0; modversion_ext_advance(&ver))
 #else /* !CONFIG_MODVERSIONS */
 static inline int check_version(const struct load_info *info,
 				const char *symname,
 				struct module *mod,
-				const s32 *crc)
+				const u32 *crc)
 {
 	return 1;
 }
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 5399c182b3cb..1fb9ad289a6f 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -86,7 +86,7 @@ struct mod_tree_root mod_tree __cacheline_aligned = {
 
 struct symsearch {
 	const struct kernel_symbol *start, *stop;
-	const s32 *crcs;
+	const u32 *crcs;
 	enum mod_license license;
 };
 
@@ -538,7 +538,7 @@ static void setup_modinfo_##field(struct module *mod, const char *s)  \
 {                                                                     \
 	mod->field = kstrdup(s, GFP_KERNEL);                          \
 }                                                                     \
-static ssize_t show_modinfo_##field(struct module_attribute *mattr,   \
+static ssize_t show_modinfo_##field(const struct module_attribute *mattr, \
 			struct module_kobject *mk, char *buffer)      \
 {                                                                     \
 	return scnprintf(buffer, PAGE_SIZE, "%s\n", mk->mod->field);  \
@@ -552,7 +552,7 @@ static void free_modinfo_##field(struct module *mod)                  \
 	kfree(mod->field);                                            \
 	mod->field = NULL;                                            \
 }                                                                     \
-static struct module_attribute modinfo_##field = {                    \
+static const struct module_attribute modinfo_##field = {              \
 	.attr = { .name = __stringify(field), .mode = 0444 },         \
 	.show = show_modinfo_##field,                                 \
 	.setup = setup_modinfo_##field,                               \
@@ -842,13 +842,13 @@ void symbol_put_addr(void *addr)
 }
 EXPORT_SYMBOL_GPL(symbol_put_addr);
 
-static ssize_t show_refcnt(struct module_attribute *mattr,
+static ssize_t show_refcnt(const struct module_attribute *mattr,
 			   struct module_kobject *mk, char *buffer)
 {
 	return sprintf(buffer, "%i\n", module_refcount(mk->mod));
 }
 
-static struct module_attribute modinfo_refcnt =
+static const struct module_attribute modinfo_refcnt =
 	__ATTR(refcnt, 0444, show_refcnt, NULL);
 
 void __module_get(struct module *module)
@@ -917,7 +917,7 @@ size_t module_flags_taint(unsigned long taints, char *buf)
 	return l;
 }
 
-static ssize_t show_initstate(struct module_attribute *mattr,
+static ssize_t show_initstate(const struct module_attribute *mattr,
 			      struct module_kobject *mk, char *buffer)
 {
 	const char *state = "unknown";
@@ -938,10 +938,10 @@ static ssize_t show_initstate(struct module_attribute *mattr,
 	return sprintf(buffer, "%s\n", state);
 }
 
-static struct module_attribute modinfo_initstate =
+static const struct module_attribute modinfo_initstate =
 	__ATTR(initstate, 0444, show_initstate, NULL);
 
-static ssize_t store_uevent(struct module_attribute *mattr,
+static ssize_t store_uevent(const struct module_attribute *mattr,
 			    struct module_kobject *mk,
 			    const char *buffer, size_t count)
 {
@@ -951,10 +951,10 @@ static ssize_t store_uevent(struct module_attribute *mattr,
 	return rc ? rc : count;
 }
 
-struct module_attribute module_uevent =
+const struct module_attribute module_uevent =
 	__ATTR(uevent, 0200, NULL, store_uevent);
 
-static ssize_t show_coresize(struct module_attribute *mattr,
+static ssize_t show_coresize(const struct module_attribute *mattr,
 			     struct module_kobject *mk, char *buffer)
 {
 	unsigned int size = mk->mod->mem[MOD_TEXT].size;
@@ -966,11 +966,11 @@ static ssize_t show_coresize(struct module_attribute *mattr,
 	return sprintf(buffer, "%u\n", size);
 }
 
-static struct module_attribute modinfo_coresize =
+static const struct module_attribute modinfo_coresize =
 	__ATTR(coresize, 0444, show_coresize, NULL);
 
 #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
-static ssize_t show_datasize(struct module_attribute *mattr,
+static ssize_t show_datasize(const struct module_attribute *mattr,
 			     struct module_kobject *mk, char *buffer)
 {
 	unsigned int size = 0;
@@ -980,11 +980,11 @@ static ssize_t show_datasize(struct module_attribute *mattr,
 	return sprintf(buffer, "%u\n", size);
 }
 
-static struct module_attribute modinfo_datasize =
+static const struct module_attribute modinfo_datasize =
 	__ATTR(datasize, 0444, show_datasize, NULL);
 #endif
 
-static ssize_t show_initsize(struct module_attribute *mattr,
+static ssize_t show_initsize(const struct module_attribute *mattr,
 			     struct module_kobject *mk, char *buffer)
 {
 	unsigned int size = 0;
@@ -994,10 +994,10 @@ static ssize_t show_initsize(struct module_attribute *mattr,
 	return sprintf(buffer, "%u\n", size);
 }
 
-static struct module_attribute modinfo_initsize =
+static const struct module_attribute modinfo_initsize =
 	__ATTR(initsize, 0444, show_initsize, NULL);
 
-static ssize_t show_taint(struct module_attribute *mattr,
+static ssize_t show_taint(const struct module_attribute *mattr,
 			  struct module_kobject *mk, char *buffer)
 {
 	size_t l;
@@ -1007,10 +1007,10 @@ static ssize_t show_taint(struct module_attribute *mattr,
 	return l;
 }
 
-static struct module_attribute modinfo_taint =
+static const struct module_attribute modinfo_taint =
 	__ATTR(taint, 0444, show_taint, NULL);
 
-struct module_attribute *modinfo_attrs[] = {
+const struct module_attribute *const modinfo_attrs[] = {
 	&module_uevent,
 	&modinfo_version,
 	&modinfo_srcversion,
@@ -1027,7 +1027,7 @@ struct module_attribute *modinfo_attrs[] = {
 	NULL,
 };
 
-size_t modinfo_attrs_count = ARRAY_SIZE(modinfo_attrs);
+const size_t modinfo_attrs_count = ARRAY_SIZE(modinfo_attrs);
 
 static const char vermagic[] = VERMAGIC_STRING;
 
@@ -1681,7 +1681,7 @@ static void module_license_taint_check(struct module *mod, const char *license)
 
 static void setup_modinfo(struct module *mod, struct load_info *info)
 {
-	struct module_attribute *attr;
+	const struct module_attribute *attr;
 	int i;
 
 	for (i = 0; (attr = modinfo_attrs[i]); i++) {
@@ -1692,7 +1692,7 @@ static void setup_modinfo(struct module *mod, struct load_info *info)
 
 static void free_modinfo(struct module *mod)
 {
-	struct module_attribute *attr;
+	const struct module_attribute *attr;
 	int i;
 
 	for (i = 0; (attr = modinfo_attrs[i]); i++) {
@@ -2074,6 +2074,82 @@ static int elf_validity_cache_index_str(struct load_info *info)
 }
 
 /**
+ * elf_validity_cache_index_versions() - Validate and cache version indices
+ * @info:  Load info to cache version indices in.
+ *         Must have &load_info->sechdrs and &load_info->secstrings populated.
+ * @flags: Load flags, relevant to suppress version loading, see
+ *         uapi/linux/module.h
+ *
+ * If we're ignoring modversions based on @flags, zero all version indices
+ * and return validity. Othewrise check:
+ *
+ * * If "__version_ext_crcs" is present, "__version_ext_names" is present
+ * * There is a name present for every crc
+ *
+ * Then populate:
+ *
+ * * &load_info->index.vers
+ * * &load_info->index.vers_ext_crc
+ * * &load_info->index.vers_ext_names
+ *
+ * if present.
+ *
+ * Return: %0 if valid, %-ENOEXEC on failure.
+ */
+static int elf_validity_cache_index_versions(struct load_info *info, int flags)
+{
+	unsigned int vers_ext_crc;
+	unsigned int vers_ext_name;
+	size_t crc_count;
+	size_t remaining_len;
+	size_t name_size;
+	char *name;
+
+	/* If modversions were suppressed, pretend we didn't find any */
+	if (flags & MODULE_INIT_IGNORE_MODVERSIONS) {
+		info->index.vers = 0;
+		info->index.vers_ext_crc = 0;
+		info->index.vers_ext_name = 0;
+		return 0;
+	}
+
+	vers_ext_crc = find_sec(info, "__version_ext_crcs");
+	vers_ext_name = find_sec(info, "__version_ext_names");
+
+	/* If we have one field, we must have the other */
+	if (!!vers_ext_crc != !!vers_ext_name) {
+		pr_err("extended version crc+name presence does not match");
+		return -ENOEXEC;
+	}
+
+	/*
+	 * If we have extended version information, we should have the same
+	 * number of entries in every section.
+	 */
+	if (vers_ext_crc) {
+		crc_count = info->sechdrs[vers_ext_crc].sh_size / sizeof(u32);
+		name = (void *)info->hdr +
+			info->sechdrs[vers_ext_name].sh_offset;
+		remaining_len = info->sechdrs[vers_ext_name].sh_size;
+
+		while (crc_count--) {
+			name_size = strnlen(name, remaining_len) + 1;
+			if (name_size > remaining_len) {
+				pr_err("more extended version crcs than names");
+				return -ENOEXEC;
+			}
+			remaining_len -= name_size;
+			name += name_size;
+		}
+	}
+
+	info->index.vers = find_sec(info, "__versions");
+	info->index.vers_ext_crc = vers_ext_crc;
+	info->index.vers_ext_name = vers_ext_name;
+	return 0;
+}
+
+/**
  * elf_validity_cache_index() - Resolve, validate, cache section indices
  * @info:  Load info to read from and update.
  *         &load_info->sechdrs and &load_info->secstrings must be populated.
@@ -2087,9 +2163,7 @@ static int elf_validity_cache_index_str(struct load_info *info)
  * * elf_validity_cache_index_mod()
  * * elf_validity_cache_index_sym()
  * * elf_validity_cache_index_str()
- *
- * If versioning is not suppressed via flags, load the version index from
- * a section called "__versions" with no validation.
+ * * elf_validity_cache_index_versions()
  *
  * If CONFIG_SMP is enabled, load the percpu section by name with no
  * validation.
@@ -2112,11 +2186,9 @@ static int elf_validity_cache_index(struct load_info *info, int flags)
 	err = elf_validity_cache_index_str(info);
 	if (err < 0)
 		return err;
-
-	if (flags & MODULE_INIT_IGNORE_MODVERSIONS)
-		info->index.vers = 0; /* Pretend no __versions section! */
-	else
-		info->index.vers = find_sec(info, "__versions");
+	err = elf_validity_cache_index_versions(info, flags);
+	if (err < 0)
+		return err;
 
 	info->index.pcpu = find_pcpusec(info);
 
@@ -2327,16 +2399,29 @@ static int rewrite_section_headers(struct load_info *info, int flags)
 
 	/* Track but don't keep modinfo and version sections. */
 	info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC;
+	info->sechdrs[info->index.vers_ext_crc].sh_flags &=
+		~(unsigned long)SHF_ALLOC;
+	info->sechdrs[info->index.vers_ext_name].sh_flags &=
+		~(unsigned long)SHF_ALLOC;
 	info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC;
 
 	return 0;
 }
 
+static const char *const module_license_offenders[] = {
+	/* driverloader was caught wrongly pretending to be under GPL */
+	"driverloader",
+
+	/* lve claims to be GPL but upstream won't provide source */
+	"lve",
+};
+
 /*
  * These calls taint the kernel depending certain module circumstances */
 static void module_augment_kernel_taints(struct module *mod, struct load_info *info)
 {
 	int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE);
+	size_t i;
 
 	if (!get_modinfo(info, "intree")) {
 		if (!test_taint(TAINT_OOT_MODULE))
@@ -2385,15 +2470,11 @@ static void module_augment_kernel_taints(struct module *mod, struct load_info *i
 	if (strcmp(mod->name, "ndiswrapper") == 0)
 		add_taint(TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE);
 
-	/* driverloader was caught wrongly pretending to be under GPL */
-	if (strcmp(mod->name, "driverloader") == 0)
-		add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
-				 LOCKDEP_NOW_UNRELIABLE);
-
-	/* lve claims to be GPL but upstream won't provide source */
-	if (strcmp(mod->name, "lve") == 0)
-		add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
-				 LOCKDEP_NOW_UNRELIABLE);
+	for (i = 0; i < ARRAY_SIZE(module_license_offenders); ++i) {
+		if (strcmp(mod->name, module_license_offenders[i]) == 0)
+			add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
+					 LOCKDEP_NOW_UNRELIABLE);
+	}
 
 	if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE))
 		pr_warn("%s: module license taints kernel.\n", mod->name);
@@ -2948,9 +3029,12 @@ static noinline int do_init_module(struct module *mod)
 	/* Switch to core kallsyms now init is done: kallsyms may be walking! */
 	rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms);
 #endif
-	ret = module_enable_rodata_ro(mod, true);
+	ret = module_enable_rodata_ro_after_init(mod);
 	if (ret)
-		goto fail_mutex_unlock;
+		pr_warn("%s: module_enable_rodata_ro_after_init() returned %d, "
+			"ro_after_init data might still be writable\n",
+			mod->name, ret);
+
 	mod_tree_remove_init(mod);
 	module_arch_freeing_init(mod);
 	for_class_mod_mem_type(type, init) {
@@ -2989,8 +3073,6 @@ static noinline int do_init_module(struct module *mod)
 
 	return 0;
 
-fail_mutex_unlock:
-	mutex_unlock(&module_mutex);
 fail_free_freeinit:
 	kfree(freeinit);
 fail:
@@ -3118,7 +3200,7 @@ static int complete_formation(struct module *mod, struct load_info *info)
 	module_bug_finalize(info->hdr, info->sechdrs, mod);
 	module_cfi_finalize(info->hdr, info->sechdrs, mod);
 
-	err = module_enable_rodata_ro(mod, false);
+	err = module_enable_rodata_ro(mod);
 	if (err)
 		goto out_strict_rwx;
 	err = module_enable_data_nx(mod);
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index 239e5013359d..74834ba15615 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -47,7 +47,7 @@ int module_enable_text_rox(const struct module *mod)
 	return 0;
 }
 
-int module_enable_rodata_ro(const struct module *mod, bool after_init)
+int module_enable_rodata_ro(const struct module *mod)
 {
 	int ret;
 
@@ -61,12 +61,17 @@ int module_enable_rodata_ro(const struct module *mod, bool after_init)
 	if (ret)
 		return ret;
 
-	if (after_init)
-		return module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro);
-
 	return 0;
 }
 
+int module_enable_rodata_ro_after_init(const struct module *mod)
+{
+	if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX) || !rodata_enabled)
+		return 0;
+
+	return module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro);
+}
+
 int module_enable_data_nx(const struct module *mod)
 {
 	if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c
index 456358e1fdc4..b401ff4b02d2 100644
--- a/kernel/module/sysfs.c
+++ b/kernel/module/sysfs.c
@@ -19,24 +19,16 @@
  * J. Corbet <corbet@lwn.net>
  */
 #ifdef CONFIG_KALLSYMS
-struct module_sect_attr {
-	struct bin_attribute battr;
-	unsigned long address;
-};
-
 struct module_sect_attrs {
 	struct attribute_group grp;
-	unsigned int nsections;
-	struct module_sect_attr attrs[];
+	struct bin_attribute attrs[];
 };
 
 #define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4))
 static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
-				struct bin_attribute *battr,
+				const struct bin_attribute *battr,
 				char *buf, loff_t pos, size_t count)
 {
-	struct module_sect_attr *sattr =
-		container_of(battr, struct module_sect_attr, battr);
 	char bounce[MODULE_SECT_READ_SIZE + 1];
 	size_t wrote;
 
@@ -53,7 +45,7 @@ static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
 	 */
 	wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n",
 			  kallsyms_show_value(file->f_cred)
-				? (void *)sattr->address : NULL);
+				? battr->private : NULL);
 	count = min(count, wrote);
 	memcpy(buf, bounce, count);
 
@@ -62,59 +54,59 @@ static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
 {
-	unsigned int section;
+	const struct bin_attribute *const *bin_attr;
 
-	for (section = 0; section < sect_attrs->nsections; section++)
-		kfree(sect_attrs->attrs[section].battr.attr.name);
+	for (bin_attr = sect_attrs->grp.bin_attrs_new; *bin_attr; bin_attr++)
+		kfree((*bin_attr)->attr.name);
+	kfree(sect_attrs->grp.bin_attrs_new);
 	kfree(sect_attrs);
 }
 
 static int add_sect_attrs(struct module *mod, const struct load_info *info)
 {
-	unsigned int nloaded = 0, i, size[2];
 	struct module_sect_attrs *sect_attrs;
-	struct module_sect_attr *sattr;
-	struct bin_attribute **gattr;
+	const struct bin_attribute **gattr;
+	struct bin_attribute *sattr;
+	unsigned int nloaded = 0, i;
 	int ret;
 
 	/* Count loaded sections and allocate structures */
 	for (i = 0; i < info->hdr->e_shnum; i++)
 		if (!sect_empty(&info->sechdrs[i]))
 			nloaded++;
-	size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded),
-			sizeof(sect_attrs->grp.bin_attrs[0]));
-	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]);
-	sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL);
+	sect_attrs = kzalloc(struct_size(sect_attrs, attrs, nloaded), GFP_KERNEL);
 	if (!sect_attrs)
 		return -ENOMEM;
 
+	gattr = kcalloc(nloaded + 1, sizeof(*gattr), GFP_KERNEL);
+	if (!gattr) {
+		kfree(sect_attrs);
+		return -ENOMEM;
+	}
+
 	/* Setup section attributes. */
 	sect_attrs->grp.name = "sections";
-	sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0];
+	sect_attrs->grp.bin_attrs_new = gattr;
 
-	sect_attrs->nsections = 0;
 	sattr = &sect_attrs->attrs[0];
-	gattr = &sect_attrs->grp.bin_attrs[0];
 	for (i = 0; i < info->hdr->e_shnum; i++) {
 		Elf_Shdr *sec = &info->sechdrs[i];
 
 		if (sect_empty(sec))
 			continue;
-		sysfs_bin_attr_init(&sattr->battr);
-		sattr->address = sec->sh_addr;
-		sattr->battr.attr.name =
+		sysfs_bin_attr_init(sattr);
+		sattr->attr.name =
 			kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL);
-		if (!sattr->battr.attr.name) {
+		if (!sattr->attr.name) {
 			ret = -ENOMEM;
 			goto out;
 		}
-		sect_attrs->nsections++;
-		sattr->battr.read = module_sect_read;
-		sattr->battr.size = MODULE_SECT_READ_SIZE;
-		sattr->battr.attr.mode = 0400;
-		*(gattr++) = &(sattr++)->battr;
+		sattr->read_new = module_sect_read;
+		sattr->private = (void *)sec->sh_addr;
+		sattr->size = MODULE_SECT_READ_SIZE;
+		sattr->attr.mode = 0400;
+		*(gattr++) = sattr++;
 	}
-	*gattr = NULL;
 
 	ret = sysfs_create_group(&mod->mkobj.kobj, &sect_attrs->grp);
 	if (ret)
@@ -146,20 +138,13 @@ static void remove_sect_attrs(struct module *mod)
  */
 
 struct module_notes_attrs {
-	struct kobject *dir;
-	unsigned int notes;
-	struct bin_attribute attrs[] __counted_by(notes);
+	struct attribute_group grp;
+	struct bin_attribute attrs[];
 };
 
-static void free_notes_attrs(struct module_notes_attrs *notes_attrs,
-			     unsigned int i)
+static void free_notes_attrs(struct module_notes_attrs *notes_attrs)
 {
-	if (notes_attrs->dir) {
-		while (i-- > 0)
-			sysfs_remove_bin_file(notes_attrs->dir,
-					      &notes_attrs->attrs[i]);
-		kobject_put(notes_attrs->dir);
-	}
+	kfree(notes_attrs->grp.bin_attrs_new);
 	kfree(notes_attrs);
 }
 
@@ -167,6 +152,7 @@ static int add_notes_attrs(struct module *mod, const struct load_info *info)
 {
 	unsigned int notes, loaded, i;
 	struct module_notes_attrs *notes_attrs;
+	const struct bin_attribute **gattr;
 	struct bin_attribute *nattr;
 	int ret;
 
@@ -185,47 +171,55 @@ static int add_notes_attrs(struct module *mod, const struct load_info *info)
 	if (!notes_attrs)
 		return -ENOMEM;
 
-	notes_attrs->notes = notes;
+	gattr = kcalloc(notes + 1, sizeof(*gattr), GFP_KERNEL);
+	if (!gattr) {
+		kfree(notes_attrs);
+		return -ENOMEM;
+	}
+
+	notes_attrs->grp.name = "notes";
+	notes_attrs->grp.bin_attrs_new = gattr;
+
 	nattr = &notes_attrs->attrs[0];
 	for (loaded = i = 0; i < info->hdr->e_shnum; ++i) {
 		if (sect_empty(&info->sechdrs[i]))
 			continue;
 		if (info->sechdrs[i].sh_type == SHT_NOTE) {
 			sysfs_bin_attr_init(nattr);
-			nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name;
+			nattr->attr.name = mod->sect_attrs->attrs[loaded].attr.name;
 			nattr->attr.mode = 0444;
 			nattr->size = info->sechdrs[i].sh_size;
 			nattr->private = (void *)info->sechdrs[i].sh_addr;
-			nattr->read = sysfs_bin_attr_simple_read;
-			++nattr;
+			nattr->read_new = sysfs_bin_attr_simple_read;
+			*(gattr++) = nattr++;
 		}
 		++loaded;
 	}
 
-	notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj);
-	if (!notes_attrs->dir) {
-		ret = -ENOMEM;
+	ret = sysfs_create_group(&mod->mkobj.kobj, &notes_attrs->grp);
+	if (ret)
 		goto out;
-	}
-
-	for (i = 0; i < notes; ++i) {
-		ret = sysfs_create_bin_file(notes_attrs->dir, &notes_attrs->attrs[i]);
-		if (ret)
-			goto out;
-	}
 
 	mod->notes_attrs = notes_attrs;
 	return 0;
 
 out:
-	free_notes_attrs(notes_attrs, i);
+	free_notes_attrs(notes_attrs);
 	return ret;
 }
 
 static void remove_notes_attrs(struct module *mod)
 {
-	if (mod->notes_attrs)
-		free_notes_attrs(mod->notes_attrs, mod->notes_attrs->notes);
+	if (mod->notes_attrs) {
+		sysfs_remove_group(&mod->mkobj.kobj,
+				   &mod->notes_attrs->grp);
+		/*
+		 * We are positive that no one is using any notes attrs
+		 * at this point.  Deallocate immediately.
+		 */
+		free_notes_attrs(mod->notes_attrs);
+		mod->notes_attrs = NULL;
+	}
 }
 
 #else /* !CONFIG_KALLSYMS */
@@ -275,7 +269,7 @@ static int add_usage_links(struct module *mod)
 
 static void module_remove_modinfo_attrs(struct module *mod, int end)
 {
-	struct module_attribute *attr;
+	const struct module_attribute *attr;
 	int i;
 
 	for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) {
@@ -293,7 +287,7 @@ static void module_remove_modinfo_attrs(struct module *mod, int end)
 
 static int module_add_modinfo_attrs(struct module *mod)
 {
-	struct module_attribute *attr;
+	const struct module_attribute *attr;
 	struct module_attribute *temp_attr;
 	int error = 0;
 	int i;
diff --git a/kernel/module/version.c b/kernel/module/version.c
index 53f43ac5a73e..3718a8868321 100644
--- a/kernel/module/version.c
+++ b/kernel/module/version.c
@@ -13,17 +13,34 @@
 int check_version(const struct load_info *info,
 		  const char *symname,
 			 struct module *mod,
-			 const s32 *crc)
+			 const u32 *crc)
 {
 	Elf_Shdr *sechdrs = info->sechdrs;
 	unsigned int versindex = info->index.vers;
 	unsigned int i, num_versions;
 	struct modversion_info *versions;
+	struct modversion_info_ext version_ext;
 
 	/* Exporting module didn't supply crcs?  OK, we're already tainted. */
 	if (!crc)
 		return 1;
 
+	/* If we have extended version info, rely on it */
+	if (info->index.vers_ext_crc) {
+		for_each_modversion_info_ext(version_ext, info) {
+			if (strcmp(version_ext.name, symname) != 0)
+				continue;
+			if (*version_ext.crc == *crc)
+				return 1;
+			pr_debug("Found checksum %X vs module %X\n",
+				 *crc, *version_ext.crc);
+			goto bad_version;
+		}
+		pr_warn_once("%s: no extended symbol version for %s\n",
+			     info->name, symname);
+		return 1;
+	}
+
 	/* No versions at all?  modprobe --force does this. */
 	if (versindex == 0)
 		return try_to_force_load(mod, symname) == 0;
@@ -87,6 +104,34 @@ int same_magic(const char *amagic, const char *bmagic,
 	return strcmp(amagic, bmagic) == 0;
 }
 
+void modversion_ext_start(const struct load_info *info,
+			  struct modversion_info_ext *start)
+{
+	unsigned int crc_idx = info->index.vers_ext_crc;
+	unsigned int name_idx = info->index.vers_ext_name;
+	Elf_Shdr *sechdrs = info->sechdrs;
+
+	/*
+	 * Both of these fields are needed for this to be useful
+	 * Any future fields should be initialized to NULL if absent.
+	 */
+	if (crc_idx == 0 || name_idx == 0) {
+		start->remaining = 0;
+		return;
+	}
+
+	start->crc = (const u32 *)sechdrs[crc_idx].sh_addr;
+	start->name = (const char *)sechdrs[name_idx].sh_addr;
+	start->remaining = sechdrs[crc_idx].sh_size / sizeof(*start->crc);
+}
+
+void modversion_ext_advance(struct modversion_info_ext *vers)
+{
+	vers->remaining--;
+	vers->crc++;
+	vers->name += strlen(vers->name) + 1;
+}
+
 /*
  * Generate the signature for all relevant module structures here.
  * If these change, we don't want to try to parse the module.
diff --git a/kernel/panic.c b/kernel/panic.c
index fbc59b3b64d0..d8635d5cecb2 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -84,7 +84,7 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
 EXPORT_SYMBOL(panic_notifier_list);
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_panic_table[] = {
+static const struct ctl_table kern_panic_table[] = {
 #ifdef CONFIG_SMP
 	{
 		.procname       = "oops_all_cpu_backtrace",
diff --git a/kernel/params.c b/kernel/params.c
index 2e447f8ae183..0074d29c9b80 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -538,7 +538,7 @@ const struct kernel_param_ops param_ops_string = {
 EXPORT_SYMBOL(param_ops_string);
 
 /* sysfs output in /sys/modules/XYZ/parameters/ */
-#define to_module_attr(n) container_of(n, struct module_attribute, attr)
+#define to_module_attr(n) container_of_const(n, struct module_attribute, attr)
 #define to_module_kobject(n) container_of(n, struct module_kobject, kobj)
 
 struct param_attribute
@@ -555,13 +555,13 @@ struct module_param_attrs
 };
 
 #ifdef CONFIG_SYSFS
-#define to_param_attr(n) container_of(n, struct param_attribute, mattr)
+#define to_param_attr(n) container_of_const(n, struct param_attribute, mattr)
 
-static ssize_t param_attr_show(struct module_attribute *mattr,
+static ssize_t param_attr_show(const struct module_attribute *mattr,
 			       struct module_kobject *mk, char *buf)
 {
 	int count;
-	struct param_attribute *attribute = to_param_attr(mattr);
+	const struct param_attribute *attribute = to_param_attr(mattr);
 
 	if (!attribute->param->ops->get)
 		return -EPERM;
@@ -573,12 +573,12 @@ static ssize_t param_attr_show(struct module_attribute *mattr,
 }
 
 /* sysfs always hands a nul-terminated string in buf.  We rely on that. */
-static ssize_t param_attr_store(struct module_attribute *mattr,
+static ssize_t param_attr_store(const struct module_attribute *mattr,
 				struct module_kobject *mk,
 				const char *buf, size_t len)
 {
  	int err;
-	struct param_attribute *attribute = to_param_attr(mattr);
+	const struct param_attribute *attribute = to_param_attr(mattr);
 
 	if (!attribute->param->ops->set)
 		return -EPERM;
@@ -857,11 +857,11 @@ static void __init param_sysfs_builtin(void)
 	}
 }
 
-ssize_t __modver_version_show(struct module_attribute *mattr,
+ssize_t __modver_version_show(const struct module_attribute *mattr,
 			      struct module_kobject *mk, char *buf)
 {
-	struct module_version_attribute *vattr =
-		container_of(mattr, struct module_version_attribute, mattr);
+	const struct module_version_attribute *vattr =
+		container_of_const(mattr, struct module_version_attribute, mattr);
 
 	return scnprintf(buf, PAGE_SIZE, "%s\n", vattr->version);
 }
@@ -892,7 +892,7 @@ static ssize_t module_attr_show(struct kobject *kobj,
 				struct attribute *attr,
 				char *buf)
 {
-	struct module_attribute *attribute;
+	const struct module_attribute *attribute;
 	struct module_kobject *mk;
 	int ret;
 
@@ -911,7 +911,7 @@ static ssize_t module_attr_store(struct kobject *kobj,
 				struct attribute *attr,
 				const char *buf, size_t len)
 {
-	struct module_attribute *attribute;
+	const struct module_attribute *attribute;
 	struct module_kobject *mk;
 	int ret;
 
diff --git a/kernel/pid.c b/kernel/pid.c
index 3a10a7b6fcf8..924084713be8 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -695,7 +695,7 @@ static struct ctl_table_root pid_table_root = {
 	.set_ownership	= pid_table_root_set_ownership,
 };
 
-static struct ctl_table pid_table[] = {
+static const struct ctl_table pid_table[] = {
 	{
 		.procname	= "pid_max",
 		.data		= &init_pid_ns.pid_max,
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index f1ffa032fc32..8f6cfec87555 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -303,7 +303,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table pid_ns_ctl_table[] = {
+static const struct ctl_table pid_ns_ctl_table[] = {
 	{
 		.procname = "ns_last_pid",
 		.maxlen = sizeof(int),
diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h
index 18ecaef6be41..5d8f981de7c5 100644
--- a/kernel/pid_sysctl.h
+++ b/kernel/pid_sysctl.h
@@ -31,7 +31,7 @@ static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table,
 	return err;
 }
 
-static struct ctl_table pid_ns_ctl_table_vm[] = {
+static const struct ctl_table pid_ns_ctl_table_vm[] = {
 	{
 		.procname	= "memfd_noexec",
 		.data		= &init_pid_ns.memfd_noexec_scope,
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 1f87aa01ba44..10a01af63a80 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -608,7 +608,11 @@ int hibernation_platform_enter(void)
 
 	local_irq_disable();
 	system_state = SYSTEM_SUSPEND;
-	syscore_suspend();
+
+	error = syscore_suspend();
+	if (error)
+		goto Enable_irqs;
+
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
 		goto Power_up;
@@ -620,6 +624,7 @@ int hibernation_platform_enter(void)
 
  Power_up:
 	syscore_resume();
+ Enable_irqs:
 	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 30894d8f0a78..c9fb559a6399 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1011,11 +1011,8 @@ void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pf
 		}
 	}
 	/* This allocation cannot fail */
-	region = memblock_alloc(sizeof(struct nosave_region),
+	region = memblock_alloc_or_panic(sizeof(struct nosave_region),
 				SMP_CACHE_BYTES);
-	if (!region)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      sizeof(struct nosave_region));
 	region->start_pfn = start_pfn;
 	region->end_pfn = end_pfn;
 	list_add_tail(&region->list, &nosave_regions);
diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c
index f5072dc85f7a..da77f3f5c1fe 100644
--- a/kernel/printk/sysctl.c
+++ b/kernel/printk/sysctl.c
@@ -20,7 +20,7 @@ static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int writ
 	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table printk_sysctls[] = {
+static const struct ctl_table printk_sysctls[] = {
 	{
 		.procname	= "printk",
 		.data		= &console_loglevel,
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index b3b3ce34df63..4b3f31911465 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -250,7 +250,7 @@ EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
 void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 {
 	if (head)
-		kasan_record_aux_stack_noalloc(ptr);
+		kasan_record_aux_stack(ptr);
 
 	__kvfree_call_rcu(head, ptr);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2795d6b5109c..475f31deed14 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3062,7 +3062,7 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
 	}
 	head->func = func;
 	head->next = NULL;
-	kasan_record_aux_stack_noalloc(head);
+	kasan_record_aux_stack(head);
 
 	local_irq_save(flags);
 	rdp = this_cpu_ptr(&rcu_data);
diff --git a/kernel/reboot.c b/kernel/reboot.c
index a701000bab34..b5a8569e5d81 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -1287,7 +1287,7 @@ static struct attribute *reboot_attrs[] = {
 };
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table kern_reboot_table[] = {
+static const struct ctl_table kern_reboot_table[] = {
 	{
 		.procname       = "poweroff_cmd",
 		.data           = &poweroff_cmd,
diff --git a/kernel/resource.c b/kernel/resource.c
index b7c0e24d9398..12004452d999 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1683,8 +1683,7 @@ void __devm_release_region(struct device *dev, struct resource *parent,
 {
 	struct region_devres match_data = { parent, start, n };
 
-	__release_region(parent, start, n);
-	WARN_ON(devres_destroy(dev, devm_region_release, devm_region_match,
+	WARN_ON(devres_release(dev, devm_region_release, devm_region_match,
 			       &match_data));
 }
 EXPORT_SYMBOL(__devm_release_region);
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index db68a964e34e..83d46b9b8ec8 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -9,7 +9,7 @@ static struct autogroup autogroup_default;
 static atomic_t autogroup_seq_nr;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_autogroup_sysctls[] = {
+static const struct ctl_table sched_autogroup_sysctls[] = {
 	{
 		.procname       = "sched_autogroup_enabled",
 		.data           = &sysctl_sched_autogroup_enabled,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 901170708e2a..165c90ba64ea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4654,7 +4654,7 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf
 #endif /* CONFIG_SCHEDSTATS */
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_core_sysctls[] = {
+static const struct ctl_table sched_core_sysctls[] = {
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname       = "sched_schedstats",
@@ -7709,9 +7709,9 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
+	pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d task_flags:0x%04x flags:0x%08lx\n",
 		free, task_pid_nr(p), task_tgid_nr(p),
-		ppid, read_task_thread_flags(p));
+		ppid, p->flags, read_task_thread_flags(p));
 
 	print_worker_info(KERN_INFO, p);
 	print_stop_info(KERN_INFO, p);
@@ -7938,19 +7938,26 @@ void sched_setnuma(struct task_struct *p, int nid)
 
 #ifdef CONFIG_HOTPLUG_CPU
 /*
- * Ensure that the idle task is using init_mm right before its CPU goes
- * offline.
+ * Invoked on the outgoing CPU in context of the CPU hotplug thread
+ * after ensuring that there are no user space tasks left on the CPU.
+ *
+ * If there is a lazy mm in use on the hotplug thread, drop it and
+ * switch to init_mm.
+ *
+ * The reference count on init_mm is dropped in finish_cpu().
  */
-void idle_task_exit(void)
+static void sched_force_init_mm(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	BUG_ON(cpu_online(smp_processor_id()));
-	BUG_ON(current != this_rq()->idle);
-
 	if (mm != &init_mm) {
-		switch_mm(mm, &init_mm, current);
+		mmgrab_lazy_tlb(&init_mm);
+		local_irq_disable();
+		current->active_mm = &init_mm;
+		switch_mm_irqs_off(mm, &init_mm, current);
+		local_irq_enable();
 		finish_arch_post_lock_switch();
+		mmdrop_lazy_tlb(mm);
 	}
 
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
@@ -8344,6 +8351,7 @@ int sched_cpu_starting(unsigned int cpu)
 int sched_cpu_wait_empty(unsigned int cpu)
 {
 	balance_hotplug_wait();
+	sched_force_init_mm();
 	return 0;
 }
 
@@ -10590,7 +10598,7 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
 		return;
 
 	/* No page allocation under rq lock */
-	task_work_add(curr, work, TWA_RESUME | TWAF_NO_ALLOC);
+	task_work_add(curr, work, TWA_RESUME);
 }
 
 void sched_mm_cid_exit_signals(struct task_struct *t)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index a2a29e3fffca..1a19d69b91ed 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -666,7 +666,11 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
 	}
 
 	sg_policy->thread = thread;
-	kthread_bind_mask(thread, policy->related_cpus);
+	if (policy->dvfs_possible_from_any_cpu)
+		set_cpus_allowed_ptr(thread, policy->related_cpus);
+	else
+		kthread_bind_mask(thread, policy->related_cpus);
+
 	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
 	mutex_init(&sg_policy->work_lock);
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 62192ac79c30..38e4537790af 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -26,7 +26,7 @@
 static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
 static unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_dl_sysctls[] = {
+static const struct ctl_table sched_dl_sysctls[] = {
 	{
 		.procname       = "sched_deadline_period_max_us",
 		.data           = &sysctl_sched_dl_period_max,
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fd7e85220715..ef047add7f9e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1262,6 +1262,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 	if (task_has_dl_policy(p)) {
 		P(dl.runtime);
 		P(dl.deadline);
+	} else if (fair_policy(p->policy)) {
+		P(se.slice);
 	}
 #ifdef CONFIG_SCHED_CLASS_EXT
 	__PS("ext.enabled", task_on_scx(p));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1e78caa21436..1c0ef435a7aa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -133,7 +133,7 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
 #endif
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table sched_fair_sysctls[] = {
+static const struct ctl_table sched_fair_sysctls[] = {
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.procname       = "sched_cfs_bandwidth_slice_us",
@@ -5385,6 +5385,15 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 static void set_delayed(struct sched_entity *se)
 {
 	se->sched_delayed = 1;
+
+	/*
+	 * Delayed se of cfs_rq have no tasks queued on them.
+	 * Do not adjust h_nr_runnable since dequeue_entities()
+	 * will account it for blocked tasks.
+	 */
+	if (!entity_is_task(se))
+		return;
+
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
@@ -5397,6 +5406,16 @@ static void set_delayed(struct sched_entity *se)
 static void clear_delayed(struct sched_entity *se)
 {
 	se->sched_delayed = 0;
+
+	/*
+	 * Delayed se of cfs_rq have no tasks queued on them.
+	 * Do not adjust h_nr_runnable since a dequeue has
+	 * already accounted for it or an enqueue of a task
+	 * below it will account for it in enqueue_task_fair().
+	 */
+	if (!entity_is_task(se))
+		return;
+
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bd66a46b06ac..4b8e33c615b1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -26,7 +26,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
 		size_t *lenp, loff_t *ppos);
 static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos);
-static struct ctl_table sched_rt_sysctls[] = {
+static const struct ctl_table sched_rt_sysctls[] = {
 	{
 		.procname       = "sched_rt_period_us",
 		.data           = &sysctl_sched_rt_period,
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 6ade91bce63e..19cdbe96f93d 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -248,7 +248,10 @@ static inline void sched_info_dequeue(struct rq *rq, struct task_struct *t)
 	delta = rq_clock(rq) - t->sched_info.last_queued;
 	t->sched_info.last_queued = 0;
 	t->sched_info.run_delay += delta;
-
+	if (delta > t->sched_info.max_run_delay)
+		t->sched_info.max_run_delay = delta;
+	if (delta && (!t->sched_info.min_run_delay || delta < t->sched_info.min_run_delay))
+		t->sched_info.min_run_delay = delta;
 	rq_sched_info_dequeue(rq, delta);
 }
 
@@ -270,6 +273,10 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t)
 	t->sched_info.run_delay += delta;
 	t->sched_info.last_arrival = now;
 	t->sched_info.pcount++;
+	if (delta > t->sched_info.max_run_delay)
+		t->sched_info.max_run_delay = delta;
+	if (delta && (!t->sched_info.min_run_delay || delta < t->sched_info.min_run_delay))
+		t->sched_info.min_run_delay = delta;
 
 	rq_sched_info_arrive(rq, delta);
 }
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 149e2c8036d3..456d339be98f 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -1130,6 +1130,13 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 		return 0;
 
 	/*
+	 * The special/sugov task isn't part of regular bandwidth/admission
+	 * control so let userspace change affinities.
+	 */
+	if (dl_entity_is_special(&p->dl))
+		return 0;
+
+	/*
 	 * Since bandwidth control happens on root_domain basis,
 	 * if admission test is enabled, we only admit -deadline
 	 * tasks allowed to run on all the CPUs in the task's
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index da33ec9e94ab..c49aea8c1025 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -312,7 +312,7 @@ static int sched_energy_aware_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table sched_energy_aware_sysctls[] = {
+static const struct ctl_table sched_energy_aware_sysctls[] = {
 	{
 		.procname       = "sched_energy_aware",
 		.data           = &sysctl_sched_energy_aware,
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 385d48293a5f..7bbb408431eb 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -749,6 +749,15 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog,
 	if (WARN_ON_ONCE(!fprog))
 		return false;
 
+	/* Our single exception to filtering. */
+#ifdef __NR_uretprobe
+#ifdef SECCOMP_ARCH_COMPAT
+	if (sd->arch == SECCOMP_ARCH_NATIVE)
+#endif
+		if (sd->nr == __NR_uretprobe)
+			return true;
+#endif
+
 	for (pc = 0; pc < fprog->len; pc++) {
 		struct sock_filter *insn = &fprog->filter[pc];
 		u16 code = insn->code;
@@ -1023,6 +1032,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
  */
 static const int mode1_syscalls[] = {
 	__NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn,
+#ifdef __NR_uretprobe
+	__NR_uretprobe,
+#endif
 	-1, /* negative terminated */
 };
 
@@ -2450,7 +2462,7 @@ static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int
 	return ret;
 }
 
-static struct ctl_table seccomp_sysctl_table[] = {
+static const struct ctl_table seccomp_sysctl_table[] = {
 	{
 		.procname	= "actions_avail",
 		.data		= (void *) &seccomp_actions_avail,
diff --git a/kernel/signal.c b/kernel/signal.c
index a2afd54303f0..875e97f6205a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4950,7 +4950,7 @@ static inline void siginfo_buildtime_checks(void)
 }
 
 #if defined(CONFIG_SYSCTL)
-static struct ctl_table signal_debug_table[] = {
+static const struct ctl_table signal_debug_table[] = {
 #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE
 	{
 		.procname	= "exception-trace",
diff --git a/kernel/smp.c b/kernel/smp.c
index f104c8e83fc4..974f3a3962e8 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -170,9 +170,9 @@ static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func);
 static DEFINE_PER_CPU(void *, cur_csd_info);
 
 static ulong csd_lock_timeout = 5000;  /* CSD lock timeout in milliseconds. */
-module_param(csd_lock_timeout, ulong, 0444);
+module_param(csd_lock_timeout, ulong, 0644);
 static int panic_on_ipistall;  /* CSD panic timeout in milliseconds, 300000 for five minutes. */
-module_param(panic_on_ipistall, int, 0444);
+module_param(panic_on_ipistall, int, 0644);
 
 static atomic_t csd_bug_count = ATOMIC_INIT(0);
 
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
index 0f4804f28c61..bb65321761b4 100644
--- a/kernel/stackleak.c
+++ b/kernel/stackleak.c
@@ -45,7 +45,7 @@ static int stack_erasing_sysctl(const struct ctl_table *table, int write,
 					str_enabled_disabled(state));
 	return ret;
 }
-static struct ctl_table stackleak_sysctls[] = {
+static const struct ctl_table stackleak_sysctls[] = {
 	{
 		.procname	= "stack_erasing",
 		.data		= NULL,
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index da821ce258ea..8896d844d738 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -250,8 +250,8 @@ static int multi_cpu_stop(void *data)
 			 * be detected and reported on their side.
 			 */
 			touch_nmi_watchdog();
+			rcu_momentary_eqs();
 		}
-		rcu_momentary_eqs();
 	} while (curstate != MULTI_STOP_EXIT);
 
 	local_irq_restore(flags);
diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c
index 3ac98bb7fb82..eb2842bd0557 100644
--- a/kernel/sysctl-test.c
+++ b/kernel/sysctl-test.c
@@ -374,7 +374,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value(
 		struct kunit *test)
 {
 	unsigned char data = 0;
-	struct ctl_table table_foo[] = {
+	const struct ctl_table table_foo[] = {
 		{
 			.procname	= "foo",
 			.data		= &data,
@@ -386,7 +386,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value(
 		},
 	};
 
-	struct ctl_table table_bar[] = {
+	const struct ctl_table table_bar[] = {
 		{
 			.procname	= "bar",
 			.data		= &data,
@@ -398,7 +398,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value(
 		},
 	};
 
-	struct ctl_table table_qux[] = {
+	const struct ctl_table table_qux[] = {
 		{
 			.procname	= "qux",
 			.data		= &data,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7ae7a4136855..cb57da499ebb 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1609,7 +1609,7 @@ int proc_do_static_key(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table kern_table[] = {
+static const struct ctl_table kern_table[] = {
 	{
 		.procname	= "panic",
 		.data		= &panic_timeout,
@@ -2021,7 +2021,7 @@ static struct ctl_table kern_table[] = {
 #endif
 };
 
-static struct ctl_table vm_table[] = {
+static const struct ctl_table vm_table[] = {
 	{
 		.procname	= "overcommit_memory",
 		.data		= &sysctl_overcommit_memory,
diff --git a/kernel/task_work.c b/kernel/task_work.c
index c969f1f26be5..d1efec571a4a 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -55,26 +55,14 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 		  enum task_work_notify_mode notify)
 {
 	struct callback_head *head;
-	int flags = notify & TWA_FLAGS;
 
-	notify &= ~TWA_FLAGS;
 	if (notify == TWA_NMI_CURRENT) {
 		if (WARN_ON_ONCE(task != current))
 			return -EINVAL;
 		if (!IS_ENABLED(CONFIG_IRQ_WORK))
 			return -EINVAL;
 	} else {
-		/*
-		 * Record the work call stack in order to print it in KASAN
-		 * reports.
-		 *
-		 * Note that stack allocation can fail if TWAF_NO_ALLOC flag
-		 * is set and new page is needed to expand the stack buffer.
-		 */
-		if (flags & TWAF_NO_ALLOC)
-			kasan_record_aux_stack_noalloc(work);
-		else
-			kasan_record_aux_stack(work);
+		kasan_record_aux_stack(work);
 	}
 
 	head = READ_ONCE(task->task_works);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 7304d7cf47f2..2a7802ec480c 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -373,16 +373,18 @@ void clocksource_verify_percpu(struct clocksource *cs)
 	cpumask_clear(&cpus_ahead);
 	cpumask_clear(&cpus_behind);
 	cpus_read_lock();
-	preempt_disable();
+	migrate_disable();
 	clocksource_verify_choose_cpus();
 	if (cpumask_empty(&cpus_chosen)) {
-		preempt_enable();
+		migrate_enable();
 		cpus_read_unlock();
 		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
 		return;
 	}
 	testcpu = smp_processor_id();
-	pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+	pr_info("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n",
+		cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+	preempt_disable();
 	for_each_cpu(cpu, &cpus_chosen) {
 		if (cpu == testcpu)
 			continue;
@@ -402,6 +404,7 @@ void clocksource_verify_percpu(struct clocksource *cs)
 			cs_nsec_min = cs_nsec;
 	}
 	preempt_enable();
+	migrate_enable();
 	cpus_read_unlock();
 	if (!cpumask_empty(&cpus_ahead))
 		pr_warn("        CPUs %*pbl ahead of CPU %d for clocksource %s.\n",
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index f6d8df94045c..deb1aa32814e 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -58,6 +58,8 @@
 #define HRTIMER_ACTIVE_SOFT	(HRTIMER_ACTIVE_HARD << MASK_SHIFT)
 #define HRTIMER_ACTIVE_ALL	(HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD)
 
+static void retrigger_next_event(void *arg);
+
 /*
  * The timer bases:
  *
@@ -111,7 +113,8 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 			.clockid = CLOCK_TAI,
 			.get_time = &ktime_get_clocktai,
 		},
-	}
+	},
+	.csd = CSD_INIT(retrigger_next_event, NULL)
 };
 
 static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
@@ -124,6 +127,14 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
 	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
+static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base)
+{
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return true;
+	else
+		return likely(base->online);
+}
+
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
@@ -145,11 +156,6 @@ static struct hrtimer_cpu_base migration_cpu_base = {
 
 #define migration_base	migration_cpu_base.clock_base[0]
 
-static inline bool is_migration_base(struct hrtimer_clock_base *base)
-{
-	return base == &migration_base;
-}
-
 /*
  * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock
  * means that all timers which are tied to this base via timer->base are
@@ -183,27 +189,54 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 }
 
 /*
- * We do not migrate the timer when it is expiring before the next
- * event on the target cpu. When high resolution is enabled, we cannot
- * reprogram the target cpu hardware and we would cause it to fire
- * late. To keep it simple, we handle the high resolution enabled and
- * disabled case similar.
+ * Check if the elected target is suitable considering its next
+ * event and the hotplug state of the current CPU.
+ *
+ * If the elected target is remote and its next event is after the timer
+ * to queue, then a remote reprogram is necessary. However there is no
+ * guarantee the IPI handling the operation would arrive in time to meet
+ * the high resolution deadline. In this case the local CPU becomes a
+ * preferred target, unless it is offline.
+ *
+ * High and low resolution modes are handled the same way for simplicity.
  *
  * Called with cpu_base->lock of target cpu held.
  */
-static int
-hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base)
+static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base,
+				    struct hrtimer_cpu_base *new_cpu_base,
+				    struct hrtimer_cpu_base *this_cpu_base)
 {
 	ktime_t expires;
 
+	/*
+	 * The local CPU clockevent can be reprogrammed. Also get_target_base()
+	 * guarantees it is online.
+	 */
+	if (new_cpu_base == this_cpu_base)
+		return true;
+
+	/*
+	 * The offline local CPU can't be the default target if the
+	 * next remote target event is after this timer. Keep the
+	 * elected new base. An IPI will we issued to reprogram
+	 * it as a last resort.
+	 */
+	if (!hrtimer_base_is_online(this_cpu_base))
+		return true;
+
 	expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset);
-	return expires < new_base->cpu_base->expires_next;
+
+	return expires >= new_base->cpu_base->expires_next;
 }
 
-static inline
-struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base,
-					 int pinned)
+static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned)
 {
+	if (!hrtimer_base_is_online(base)) {
+		int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER));
+
+		return &per_cpu(hrtimer_bases, cpu);
+	}
+
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 	if (static_branch_likely(&timers_migration_enabled) && !pinned)
 		return &per_cpu(hrtimer_bases, get_nohz_timer_target());
@@ -254,8 +287,8 @@ again:
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
-		if (new_cpu_base != this_cpu_base &&
-		    hrtimer_check_target(timer, new_base)) {
+		if (!hrtimer_suitable_target(timer, new_base, new_cpu_base,
+					     this_cpu_base)) {
 			raw_spin_unlock(&new_base->cpu_base->lock);
 			raw_spin_lock(&base->cpu_base->lock);
 			new_cpu_base = this_cpu_base;
@@ -264,8 +297,7 @@ again:
 		}
 		WRITE_ONCE(timer->base, new_base);
 	} else {
-		if (new_cpu_base != this_cpu_base &&
-		    hrtimer_check_target(timer, new_base)) {
+		if (!hrtimer_suitable_target(timer, new_base,  new_cpu_base, this_cpu_base)) {
 			new_cpu_base = this_cpu_base;
 			goto again;
 		}
@@ -275,11 +307,6 @@ again:
 
 #else /* CONFIG_SMP */
 
-static inline bool is_migration_base(struct hrtimer_clock_base *base)
-{
-	return false;
-}
-
 static inline struct hrtimer_clock_base *
 lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 	__acquires(&timer->base->cpu_base->lock)
@@ -716,8 +743,6 @@ static inline int hrtimer_is_hres_enabled(void)
 	return hrtimer_hres_enabled;
 }
 
-static void retrigger_next_event(void *arg);
-
 /*
  * Switch to high resolution mode
  */
@@ -1205,6 +1230,7 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 				    u64 delta_ns, const enum hrtimer_mode mode,
 				    struct hrtimer_clock_base *base)
 {
+	struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases);
 	struct hrtimer_clock_base *new_base;
 	bool force_local, first;
 
@@ -1216,10 +1242,16 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	 * and enforce reprogramming after it is queued no matter whether
 	 * it is the new first expiring timer again or not.
 	 */
-	force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
+	force_local = base->cpu_base == this_cpu_base;
 	force_local &= base->cpu_base->next_timer == timer;
 
 	/*
+	 * Don't force local queuing if this enqueue happens on a unplugged
+	 * CPU after hrtimer_cpu_dying() has been invoked.
+	 */
+	force_local &= this_cpu_base->online;
+
+	/*
 	 * Remove an active timer from the queue. In case it is not queued
 	 * on the current CPU, make sure that remove_hrtimer() updates the
 	 * remote data correctly.
@@ -1248,8 +1280,27 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	}
 
 	first = enqueue_hrtimer(timer, new_base, mode);
-	if (!force_local)
-		return first;
+	if (!force_local) {
+		/*
+		 * If the current CPU base is online, then the timer is
+		 * never queued on a remote CPU if it would be the first
+		 * expiring timer there.
+		 */
+		if (hrtimer_base_is_online(this_cpu_base))
+			return first;
+
+		/*
+		 * Timer was enqueued remote because the current base is
+		 * already offline. If the timer is the first to expire,
+		 * kick the remote CPU to reprogram the clock event.
+		 */
+		if (first) {
+			struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base;
+
+			smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd);
+		}
+		return 0;
+	}
 
 	/*
 	 * Timer was forced to stay on the current CPU to avoid
@@ -1370,6 +1421,18 @@ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base,
 	}
 }
 
+#ifdef CONFIG_SMP
+static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
+{
+	return base == &migration_base;
+}
+#else
+static __always_inline bool is_migration_base(struct hrtimer_clock_base *base)
+{
+	return false;
+}
+#endif
+
 /*
  * This function is called on PREEMPT_RT kernels when the fast path
  * deletion of a timer failed because the timer callback function was
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 40706cb36920..c8f776dc6ee0 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -301,7 +301,7 @@ static int timer_migration_handler(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table timer_sysctl[] = {
+static const struct ctl_table timer_sysctl[] = {
 	{
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index 9cb9b6584ea1..2f6330831f08 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -1675,6 +1675,9 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
 
 	} while (i < tmigr_hierarchy_levels);
 
+	/* Assert single root */
+	WARN_ON_ONCE(!err && !group->parent && !list_is_singular(&tmigr_level_list[top]));
+
 	while (i > 0) {
 		group = stack[--i];
 
@@ -1716,7 +1719,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node)
 		WARN_ON_ONCE(top == 0);
 
 		lvllist = &tmigr_level_list[top];
-		if (group->num_children == 1 && list_is_singular(lvllist)) {
+
+		/*
+		 * Newly created root level should have accounted the upcoming
+		 * CPU's child group and pre-accounted the old root.
+		 */
+		if (group->num_children == 2 && list_is_singular(lvllist)) {
 			/*
 			 * The target CPU must never do the prepare work, except
 			 * on early boot when the boot CPU is the target. Otherwise
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f79eb9386c7f..728ecda6e8d4 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -8780,7 +8780,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write,
 	return 0;
 }
 
-static struct ctl_table ftrace_sysctls[] = {
+static const struct ctl_table ftrace_sysctls[] = {
 	{
 		.procname       = "ftrace_enabled",
 		.data           = &ftrace_enabled,
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 831779607e84..8226352a0062 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -25,30 +25,9 @@ menuconfig RV
 	  For further information, see:
 	    Documentation/trace/rv/runtime-verification.rst
 
-config RV_MON_WIP
-	depends on RV
-	depends on PREEMPT_TRACER
-	select DA_MON_EVENTS_IMPLICIT
-	bool "wip monitor"
-	help
-	  Enable wip (wakeup in preemptive) sample monitor that illustrates
-	  the usage of per-cpu monitors, and one limitation of the
-	  preempt_disable/enable events.
-
-	  For further information, see:
-	    Documentation/trace/rv/monitor_wip.rst
-
-config RV_MON_WWNR
-	depends on RV
-	select DA_MON_EVENTS_ID
-	bool "wwnr monitor"
-	help
-	  Enable wwnr (wakeup while not running) sample monitor, this is a
-	  sample monitor that illustrates the usage of per-task monitor.
-	  The model is borken on purpose: it serves to test reactors.
-
-	  For further information, see:
-	    Documentation/trace/rv/monitor_wwnr.rst
+source "kernel/trace/rv/monitors/wip/Kconfig"
+source "kernel/trace/rv/monitors/wwnr/Kconfig"
+# Add new monitors here
 
 config RV_REACTORS
 	bool "Runtime verification reactors"
diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile
index 963d14875b45..188b64668e1f 100644
--- a/kernel/trace/rv/Makefile
+++ b/kernel/trace/rv/Makefile
@@ -1,8 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
+ccflags-y += -I $(src)		# needed for trace events
+
 obj-$(CONFIG_RV) += rv.o
 obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o
 obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o
+# Add new monitors here
 obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
 obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
 obj-$(CONFIG_RV_REACT_PANIC) += reactor_panic.o
diff --git a/kernel/trace/rv/monitors/wip/Kconfig b/kernel/trace/rv/monitors/wip/Kconfig
new file mode 100644
index 000000000000..3ef664b5cd90
--- /dev/null
+++ b/kernel/trace/rv/monitors/wip/Kconfig
@@ -0,0 +1,12 @@
+config RV_MON_WIP
+	depends on RV
+	depends on PREEMPT_TRACER
+	select DA_MON_EVENTS_IMPLICIT
+	bool "wip monitor"
+	help
+	  Enable wip (wakeup in preemptive) sample monitor that illustrates
+	  the usage of per-cpu monitors, and one limitation of the
+	  preempt_disable/enable events.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_wip.rst
diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c
index b2b49a27e886..db7389157c87 100644
--- a/kernel/trace/rv/monitors/wip/wip.c
+++ b/kernel/trace/rv/monitors/wip/wip.c
@@ -10,7 +10,7 @@
 
 #define MODULE_NAME "wip"
 
-#include <trace/events/rv.h>
+#include <rv_trace.h>
 #include <trace/events/sched.h>
 #include <trace/events/preemptirq.h>
 
diff --git a/kernel/trace/rv/monitors/wip/wip_trace.h b/kernel/trace/rv/monitors/wip/wip_trace.h
new file mode 100644
index 000000000000..aa2162f47a4c
--- /dev/null
+++ b/kernel/trace/rv/monitors/wip/wip_trace.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_WIP
+DEFINE_EVENT(event_da_monitor, event_wip,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_wip,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_WIP */
diff --git a/kernel/trace/rv/monitors/wwnr/Kconfig b/kernel/trace/rv/monitors/wwnr/Kconfig
new file mode 100644
index 000000000000..ee741aa6d6b8
--- /dev/null
+++ b/kernel/trace/rv/monitors/wwnr/Kconfig
@@ -0,0 +1,11 @@
+config RV_MON_WWNR
+	depends on RV
+	select DA_MON_EVENTS_ID
+	bool "wwnr monitor"
+	help
+	  Enable wwnr (wakeup while not running) sample monitor, this is a
+	  sample monitor that illustrates the usage of per-task monitor.
+	  The model is borken on purpose: it serves to test reactors.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_wwnr.rst
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c
index 0e43dd2db685..3b16994a9984 100644
--- a/kernel/trace/rv/monitors/wwnr/wwnr.c
+++ b/kernel/trace/rv/monitors/wwnr/wwnr.c
@@ -10,7 +10,7 @@
 
 #define MODULE_NAME "wwnr"
 
-#include <trace/events/rv.h>
+#include <rv_trace.h>
 #include <trace/events/sched.h>
 
 #include "wwnr.h"
diff --git a/kernel/trace/rv/monitors/wwnr/wwnr_trace.h b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h
new file mode 100644
index 000000000000..fc97ec7476ad
--- /dev/null
+++ b/kernel/trace/rv/monitors/wwnr/wwnr_trace.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_WWNR
+/* id is the pid of the task */
+DEFINE_EVENT(event_da_monitor_id, event_wwnr,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_wwnr,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_WWNR */
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 279c70e1bd74..8657fc8806e7 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -145,7 +145,7 @@
 
 #ifdef CONFIG_DA_MON_EVENTS
 #define CREATE_TRACE_POINTS
-#include <trace/events/rv.h>
+#include <rv_trace.h>
 #endif
 
 #include "rv.h"
diff --git a/include/trace/events/rv.h b/kernel/trace/rv/rv_trace.h
index 56592da9301c..5e65097423ba 100644
--- a/include/trace/events/rv.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -57,15 +57,9 @@ DECLARE_EVENT_CLASS(error_da_monitor,
 		__entry->state)
 );
 
-#ifdef CONFIG_RV_MON_WIP
-DEFINE_EVENT(event_da_monitor, event_wip,
-	    TP_PROTO(char *state, char *event, char *next_state, bool final_state),
-	    TP_ARGS(state, event, next_state, final_state));
-
-DEFINE_EVENT(error_da_monitor, error_wip,
-	     TP_PROTO(char *state, char *event),
-	     TP_ARGS(state, event));
-#endif /* CONFIG_RV_MON_WIP */
+#include <monitors/wip/wip_trace.h>
+// Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here
+
 #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */
 
 #ifdef CONFIG_DA_MON_EVENTS_ID
@@ -123,20 +117,14 @@ DECLARE_EVENT_CLASS(error_da_monitor_id,
 		__entry->state)
 );
 
-#ifdef CONFIG_RV_MON_WWNR
-/* id is the pid of the task */
-DEFINE_EVENT(event_da_monitor_id, event_wwnr,
-	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
-	     TP_ARGS(id, state, event, next_state, final_state));
-
-DEFINE_EVENT(error_da_monitor_id, error_wwnr,
-	     TP_PROTO(int id, char *state, char *event),
-	     TP_ARGS(id, state, event));
-#endif /* CONFIG_RV_MON_WWNR */
+#include <monitors/wwnr/wwnr_trace.h>
+// Add new monitors based on CONFIG_DA_MON_EVENTS_ID here
 
 #endif /* CONFIG_DA_MON_EVENTS_ID */
 #endif /* _TRACE_RV_H */
 
 /* This part ust be outside protection */
 #undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE rv_trace
 #include <trace/define_trace.h>
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 17bcad8f79de..97325fbd6283 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -2899,7 +2899,7 @@ static int set_max_user_events_sysctl(const struct ctl_table *table, int write,
 	return ret;
 }
 
-static struct ctl_table user_event_sysctls[] = {
+static const struct ctl_table user_event_sysctls[] = {
 	{
 		.procname	= "user_events_max",
 		.data		= &max_user_events,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 54d850997c0a..136c750b0b4d 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -198,7 +198,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	 * returning from the function.
 	 */
 	if (ftrace_graph_notrace_addr(trace->func)) {
-		*task_var |= TRACE_GRAPH_NOTRACE_BIT;
+		*task_var |= TRACE_GRAPH_NOTRACE;
 		/*
 		 * Need to return 1 to have the return called
 		 * that will clear the NOTRACE bit.
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index b25c30b05dd0..f3a2722ee4c0 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1229,6 +1229,8 @@ static void trace_sched_migrate_callback(void *data, struct task_struct *p, int
 	}
 }
 
+static bool monitor_enabled;
+
 static int register_migration_monitor(void)
 {
 	int ret = 0;
@@ -1237,16 +1239,25 @@ static int register_migration_monitor(void)
 	 * Timerlat thread migration check is only required when running timerlat in user-space.
 	 * Thus, enable callback only if timerlat is set with no workload.
 	 */
-	if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options))
+	if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options)) {
+		if (WARN_ON_ONCE(monitor_enabled))
+			return 0;
+
 		ret = register_trace_sched_migrate_task(trace_sched_migrate_callback, NULL);
+		if (!ret)
+			monitor_enabled = true;
+	}
 
 	return ret;
 }
 
 static void unregister_migration_monitor(void)
 {
-	if (timerlat_enabled() && !test_bit(OSN_WORKLOAD, &osnoise_options))
-		unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL);
+	if (!monitor_enabled)
+		return;
+
+	unregister_trace_sched_migrate_task(trace_sched_migrate_callback, NULL);
+	monitor_enabled = false;
 }
 #else
 static int register_migration_monitor(void)
diff --git a/kernel/ucount.c b/kernel/ucount.c
index f950b5e59d63..86c5f1c0bad9 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -164,8 +164,8 @@ struct ucounts *get_ucounts(struct ucounts *ucounts)
 struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
 {
 	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
-	struct ucounts *ucounts, *new;
 	bool wrapped;
+	struct ucounts *ucounts, *new = NULL;
 
 	spin_lock_irq(&ucounts_lock);
 	ucounts = find_ucounts(ns, uid, hashent);
@@ -182,17 +182,17 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
 
 		spin_lock_irq(&ucounts_lock);
 		ucounts = find_ucounts(ns, uid, hashent);
-		if (ucounts) {
-			kfree(new);
-		} else {
+		if (!ucounts) {
 			hlist_add_head(&new->node, hashent);
 			get_user_ns(new->ns);
 			spin_unlock_irq(&ucounts_lock);
 			return new;
 		}
 	}
+
 	wrapped = !get_ucounts_or_wrap(ucounts);
 	spin_unlock_irq(&ucounts_lock);
+	kfree(new);
 	if (wrapped) {
 		put_ucounts(ucounts);
 		return NULL;
diff --git a/kernel/umh.c b/kernel/umh.c
index be9234270777..b4da45a3a7cf 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -544,7 +544,7 @@ static int proc_cap_handler(const struct ctl_table *table, int write,
 	return 0;
 }
 
-static struct ctl_table usermodehelper_table[] = {
+static const struct ctl_table usermodehelper_table[] = {
 	{
 		.procname	= "bset",
 		.data		= &usermodehelper_bset,
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 7282f61a8650..bfbaaecb1dd4 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -75,7 +75,7 @@ static DEFINE_CTL_TABLE_POLL(hostname_poll);
 static DEFINE_CTL_TABLE_POLL(domainname_poll);
 
 // Note: update 'enum uts_proc' to match any changes to this table
-static struct ctl_table uts_kern_table[] = {
+static const struct ctl_table uts_kern_table[] = {
 	{
 		.procname	= "arch",
 		.data		= init_uts_ns.name.machine,
@@ -129,7 +129,7 @@ static struct ctl_table uts_kern_table[] = {
  */
 void uts_proc_notify(enum uts_proc proc)
 {
-	struct ctl_table *table = &uts_kern_table[proc];
+	const struct ctl_table *table = &uts_kern_table[proc];
 
 	proc_sys_poll_notify(table->poll);
 }
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 41e0f7e9fa35..b2da7de39d06 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -190,7 +190,7 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 		 * with printk_cpu_sync_get_irqsave() that we can still at least
 		 * get the message about the lockup out.
 		 */
-		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu);
+		pr_emerg("CPU%u: Watchdog detected hard LOCKUP on cpu %u\n", this_cpu, cpu);
 		printk_cpu_sync_get_irqsave(flags);
 
 		print_modules();
@@ -1094,7 +1094,7 @@ static int proc_watchdog_cpumask(const struct ctl_table *table, int write,
 
 static const int sixty = 60;
 
-static struct ctl_table watchdog_sysctls[] = {
+static const struct ctl_table watchdog_sysctls[] = {
 	{
 		.procname       = "watchdog",
 		.data		= &watchdog_user_enabled,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 33a23c7b2274..3c2c45313c88 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2180,7 +2180,7 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 	debug_work_activate(work);
 
 	/* record the work call stack in order to print it in KASAN reports */
-	kasan_record_aux_stack_noalloc(work);
+	kasan_record_aux_stack(work);
 
 	/* we own @work, set data and link */
 	set_work_pwq(work, pwq, extra_flags);
diff --git a/lib/Kconfig b/lib/Kconfig
index a78d22c6507f..dccb61b7d698 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -164,34 +164,9 @@ config CRC_T10DIF
 config ARCH_HAS_CRC_T10DIF
 	bool
 
-choice
-	prompt "CRC-T10DIF implementation"
-	depends on CRC_T10DIF
-	default CRC_T10DIF_IMPL_ARCH if ARCH_HAS_CRC_T10DIF
-	default CRC_T10DIF_IMPL_GENERIC if !ARCH_HAS_CRC_T10DIF
-	help
-	  This option allows you to override the default choice of CRC-T10DIF
-	  implementation.
-
-config CRC_T10DIF_IMPL_ARCH
-	bool "Architecture-optimized" if ARCH_HAS_CRC_T10DIF
-	help
-	  Use the optimized implementation of CRC-T10DIF for the selected
-	  architecture.  It is recommended to keep this enabled, as it can
-	  greatly improve CRC-T10DIF performance.
-
-config CRC_T10DIF_IMPL_GENERIC
-	bool "Generic implementation"
-	help
-	  Use the generic table-based implementation of CRC-T10DIF.  Selecting
-	  this will reduce code size slightly but can greatly reduce CRC-T10DIF
-	  performance.
-
-endchoice
-
 config CRC_T10DIF_ARCH
 	tristate
-	default CRC_T10DIF if CRC_T10DIF_IMPL_ARCH
+	default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS
 
 config CRC64_ROCKSOFT
 	tristate "CRC calculation for the Rocksoft model CRC64"
@@ -223,87 +198,9 @@ config CRC32
 config ARCH_HAS_CRC32
 	bool
 
-choice
-	prompt "CRC32 implementation"
-	depends on CRC32
-	default CRC32_IMPL_ARCH_PLUS_SLICEBY8 if ARCH_HAS_CRC32
-	default CRC32_IMPL_SLICEBY8 if !ARCH_HAS_CRC32
-	help
-	  This option allows you to override the default choice of CRC32
-	  implementation.  Choose the default unless you know that you need one
-	  of the others.
-
-config CRC32_IMPL_ARCH_PLUS_SLICEBY8
-	bool "Arch-optimized, with fallback to slice-by-8" if ARCH_HAS_CRC32
-	help
-	  Use architecture-optimized implementation of CRC32.  Fall back to
-	  slice-by-8 in cases where the arch-optimized implementation cannot be
-	  used, e.g. if the CPU lacks support for the needed instructions.
-
-	  This is the default when an arch-optimized implementation exists.
-
-config CRC32_IMPL_ARCH_PLUS_SLICEBY1
-	bool "Arch-optimized, with fallback to slice-by-1" if ARCH_HAS_CRC32
-	help
-	  Use architecture-optimized implementation of CRC32, but fall back to
-	  slice-by-1 instead of slice-by-8 in order to reduce the binary size.
-
-config CRC32_IMPL_SLICEBY8
-	bool "Slice by 8 bytes"
-	help
-	  Calculate checksum 8 bytes at a time with a clever slicing algorithm.
-	  This is much slower than the architecture-optimized implementation of
-	  CRC32 (if the selected arch has one), but it is portable and is the
-	  fastest implementation when no arch-optimized implementation is
-	  available.  It uses an 8KiB lookup table.  Most modern processors have
-	  enough cache to hold this table without thrashing the cache.
-
-config CRC32_IMPL_SLICEBY4
-	bool "Slice by 4 bytes"
-	help
-	  Calculate checksum 4 bytes at a time with a clever slicing algorithm.
-	  This is a bit slower than slice by 8, but has a smaller 4KiB lookup
-	  table.
-
-	  Only choose this option if you know what you are doing.
-
-config CRC32_IMPL_SLICEBY1
-	bool "Slice by 1 byte (Sarwate's algorithm)"
-	help
-	  Calculate checksum a byte at a time using Sarwate's algorithm.  This
-	  is not particularly fast, but has a small 1KiB lookup table.
-
-	  Only choose this option if you know what you are doing.
-
-config CRC32_IMPL_BIT
-	bool "Classic Algorithm (one bit at a time)"
-	help
-	  Calculate checksum one bit at a time.  This is VERY slow, but has
-	  no lookup table.  This is provided as a debugging option.
-
-	  Only choose this option if you are debugging crc32.
-
-endchoice
-
 config CRC32_ARCH
 	tristate
-	default CRC32 if CRC32_IMPL_ARCH_PLUS_SLICEBY8 || CRC32_IMPL_ARCH_PLUS_SLICEBY1
-
-config CRC32_SLICEBY8
-	bool
-	default y if CRC32_IMPL_SLICEBY8 || CRC32_IMPL_ARCH_PLUS_SLICEBY8
-
-config CRC32_SLICEBY4
-	bool
-	default y if CRC32_IMPL_SLICEBY4
-
-config CRC32_SARWATE
-	bool
-	default y if CRC32_IMPL_SLICEBY1 || CRC32_IMPL_ARCH_PLUS_SLICEBY1
-
-config CRC32_BIT
-	bool
-	default y if CRC32_IMPL_BIT
+	default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS
 
 config CRC64
 	tristate "CRC64 functions"
@@ -343,6 +240,17 @@ config CRC8
 	  when they need to do cyclic redundancy check according CRC8
 	  algorithm. Module will be called crc8.
 
+config CRC_OPTIMIZATIONS
+	bool "Enable optimized CRC implementations" if EXPERT
+	default y
+	help
+	  Disabling this option reduces code size slightly by disabling the
+	  architecture-optimized implementations of any CRC variants that are
+	  enabled.  CRC checksumming performance may get much slower.
+
+	  Keep this enabled unless you're really trying to minimize the size of
+	  the kernel.
+
 config XXHASH
 	tristate
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 5f1874622175..1af972a92d06 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2269,7 +2269,6 @@ config TEST_LIST_SORT
 config TEST_MIN_HEAP
 	tristate "Min heap test"
 	depends on DEBUG_KERNEL || m
-	select MIN_HEAP
 	help
 	  Enable this to turn on min heap function tests. This test is
 	  executed only once during system boot (so affects only boot time),
@@ -2479,6 +2478,17 @@ config TEST_RHASHTABLE
 config TEST_IDA
 	tristate "Perform selftest on IDA functions"
 
+config TEST_MISC_MINOR
+	tristate "Basic misc minor Kunit test" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Kunit test for the misc minor.
+	  It tests misc minor functions for dynamic and misc dynamic minor.
+	  This include misc_xxx functions
+
+	  If unsure, say N.
+
 config TEST_PARMAN
 	tristate "Perform selftest on priority array manager"
 	depends on PARMAN
@@ -3172,6 +3182,21 @@ config INT_POW_TEST
 
 	  If unsure, say N
 
+config INT_SQRT_KUNIT_TEST
+	tristate "Integer square root test" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  This option enables the KUnit test suite for the int_sqrt() function,
+	  which performs square root calculation. The test suite checks
+	  various scenarios, including edge cases, to ensure correctness.
+
+	  Enabling this option will include tests that check various scenarios
+	  and edge cases to ensure the accuracy and reliability of the square root
+	  function.
+
+	  If unsure, say N
+
 endif # RUNTIME_TESTING_MENU
 
 config ARCH_USE_MEMTEST
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 65e706e1bc19..19b45617bdcf 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -29,6 +29,8 @@ EXPORT_SYMBOL(_shared_alloc_tag);
 
 DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
 			mem_alloc_profiling_key);
+EXPORT_SYMBOL(mem_alloc_profiling_key);
+
 DEFINE_STATIC_KEY_FALSE(mem_profiling_compressed);
 
 struct alloc_tag_kernel_section kernel_tags = { NULL, 0 };
@@ -423,8 +425,8 @@ static int vm_module_tags_populate(void)
 		unsigned long nr;
 
 		more_pages = ALIGN(new_end - phys_end, PAGE_SIZE) >> PAGE_SHIFT;
-		nr = alloc_pages_bulk_array_node(GFP_KERNEL | __GFP_NOWARN,
-						 NUMA_NO_NODE, more_pages, next_page);
+		nr = alloc_pages_bulk_node(GFP_KERNEL | __GFP_NOWARN,
+					   NUMA_NO_NODE, more_pages, next_page);
 		if (nr < more_pages ||
 		    vmap_pages_range(phys_end, phys_end + (nr << PAGE_SHIFT), PAGE_KERNEL,
 				     next_page, PAGE_SHIFT) < 0) {
diff --git a/lib/cpumask.c b/lib/cpumask.c
index e77ee9d46f71..57274ba8b6d9 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -83,10 +83,7 @@ EXPORT_SYMBOL(alloc_cpumask_var_node);
  */
 void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
-	*mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES);
-	if (!*mask)
-		panic("%s: Failed to allocate %u bytes\n", __func__,
-		      cpumask_size());
+	*mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES);
 }
 
 /**
diff --git a/lib/crc32.c b/lib/crc32.c
index 47151624332e..ede6131f66fc 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -30,20 +30,6 @@
 #include <linux/crc32poly.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/sched.h>
-#include "crc32defs.h"
-
-#if CRC_LE_BITS > 8
-# define tole(x) ((__force u32) cpu_to_le32(x))
-#else
-# define tole(x) (x)
-#endif
-
-#if CRC_BE_BITS > 8
-# define tobe(x) ((__force u32) cpu_to_be32(x))
-#else
-# define tobe(x) (x)
-#endif
 
 #include "crc32table.h"
 
@@ -51,157 +37,20 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
 MODULE_DESCRIPTION("Various CRC32 calculations");
 MODULE_LICENSE("GPL");
 
-#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8
-
-/* implements slicing-by-4 or slicing-by-8 algorithm */
-static inline u32 __pure
-crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
-{
-# ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8)
-#  define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \
-		   t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255])
-#  define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \
-		   t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255])
-# else
-#  define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
-#  define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \
-		   t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255])
-#  define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \
-		   t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255])
-# endif
-	const u32 *b;
-	size_t    rem_len;
-# ifdef CONFIG_X86
-	size_t i;
-# endif
-	const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3];
-# if CRC_LE_BITS != 32
-	const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7];
-# endif
-	u32 q;
-
-	/* Align it */
-	if (unlikely((long)buf & 3 && len)) {
-		do {
-			DO_CRC(*buf++);
-		} while ((--len) && ((long)buf)&3);
-	}
-
-# if CRC_LE_BITS == 32
-	rem_len = len & 3;
-	len = len >> 2;
-# else
-	rem_len = len & 7;
-	len = len >> 3;
-# endif
-
-	b = (const u32 *)buf;
-# ifdef CONFIG_X86
-	--b;
-	for (i = 0; i < len; i++) {
-# else
-	for (--b; len; --len) {
-# endif
-		q = crc ^ *++b; /* use pre increment for speed */
-# if CRC_LE_BITS == 32
-		crc = DO_CRC4;
-# else
-		crc = DO_CRC8;
-		q = *++b;
-		crc ^= DO_CRC4;
-# endif
-	}
-	len = rem_len;
-	/* And the last few bytes */
-	if (len) {
-		u8 *p = (u8 *)(b + 1) - 1;
-# ifdef CONFIG_X86
-		for (i = 0; i < len; i++)
-			DO_CRC(*++p); /* use pre increment for speed */
-# else
-		do {
-			DO_CRC(*++p); /* use pre increment for speed */
-		} while (--len);
-# endif
-	}
-	return crc;
-#undef DO_CRC
-#undef DO_CRC4
-#undef DO_CRC8
-}
-#endif
-
-
-/**
- * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II
- *			CRC32/CRC32C
- * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for other
- *	 uses, or the previous crc32/crc32c value if computing incrementally.
- * @p: pointer to buffer over which CRC32/CRC32C is run
- * @len: length of buffer @p
- * @tab: little-endian Ethernet table
- * @polynomial: CRC32/CRC32c LE polynomial
- */
-static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
-					  size_t len, const u32 (*tab)[256],
-					  u32 polynomial)
+u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len)
 {
-#if CRC_LE_BITS == 1
-	int i;
-	while (len--) {
-		crc ^= *p++;
-		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
-	}
-# elif CRC_LE_BITS == 2
-	while (len--) {
-		crc ^= *p++;
-		crc = (crc >> 2) ^ tab[0][crc & 3];
-		crc = (crc >> 2) ^ tab[0][crc & 3];
-		crc = (crc >> 2) ^ tab[0][crc & 3];
-		crc = (crc >> 2) ^ tab[0][crc & 3];
-	}
-# elif CRC_LE_BITS == 4
-	while (len--) {
-		crc ^= *p++;
-		crc = (crc >> 4) ^ tab[0][crc & 15];
-		crc = (crc >> 4) ^ tab[0][crc & 15];
-	}
-# elif CRC_LE_BITS == 8
-	/* aka Sarwate algorithm */
-	while (len--) {
-		crc ^= *p++;
-		crc = (crc >> 8) ^ tab[0][crc & 255];
-	}
-# else
-	crc = (__force u32) __cpu_to_le32(crc);
-	crc = crc32_body(crc, p, len, tab);
-	crc = __le32_to_cpu((__force __le32)crc);
-#endif
+	while (len--)
+		crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++];
 	return crc;
 }
+EXPORT_SYMBOL(crc32_le_base);
 
-#if CRC_LE_BITS == 1
-u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE);
-}
-u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE);
-}
-#else
-u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE);
-}
 u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE);
+	while (len--)
+		crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++];
+	return crc;
 }
-#endif
-EXPORT_SYMBOL(crc32_le_base);
 EXPORT_SYMBOL(crc32c_le_base);
 
 /*
@@ -277,64 +126,10 @@ u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len)
 EXPORT_SYMBOL(crc32_le_shift);
 EXPORT_SYMBOL(__crc32c_le_shift);
 
-/**
- * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
- * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
- *	other uses, or the previous crc32 value if computing incrementally.
- * @p: pointer to buffer over which CRC32 is run
- * @len: length of buffer @p
- * @tab: big-endian Ethernet table
- * @polynomial: CRC32 BE polynomial
- */
-static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
-					  size_t len, const u32 (*tab)[256],
-					  u32 polynomial)
-{
-#if CRC_BE_BITS == 1
-	int i;
-	while (len--) {
-		crc ^= *p++ << 24;
-		for (i = 0; i < 8; i++)
-			crc =
-			    (crc << 1) ^ ((crc & 0x80000000) ? polynomial :
-					  0);
-	}
-# elif CRC_BE_BITS == 2
-	while (len--) {
-		crc ^= *p++ << 24;
-		crc = (crc << 2) ^ tab[0][crc >> 30];
-		crc = (crc << 2) ^ tab[0][crc >> 30];
-		crc = (crc << 2) ^ tab[0][crc >> 30];
-		crc = (crc << 2) ^ tab[0][crc >> 30];
-	}
-# elif CRC_BE_BITS == 4
-	while (len--) {
-		crc ^= *p++ << 24;
-		crc = (crc << 4) ^ tab[0][crc >> 28];
-		crc = (crc << 4) ^ tab[0][crc >> 28];
-	}
-# elif CRC_BE_BITS == 8
-	while (len--) {
-		crc ^= *p++ << 24;
-		crc = (crc << 8) ^ tab[0][crc >> 24];
-	}
-# else
-	crc = (__force u32) __cpu_to_be32(crc);
-	crc = crc32_body(crc, p, len, tab);
-	crc = __be32_to_cpu((__force __be32)crc);
-# endif
-	return crc;
-}
-
-#if CRC_BE_BITS == 1
-u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len)
-{
-	return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE);
-}
-#else
 u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len)
 {
-	return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE);
+	while (len--)
+		crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++];
+	return crc;
 }
-#endif
 EXPORT_SYMBOL(crc32_be_base);
diff --git a/lib/crc32defs.h b/lib/crc32defs.h
deleted file mode 100644
index 0c8fb5923e7e..000000000000
--- a/lib/crc32defs.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/* Try to choose an implementation variant via Kconfig */
-#ifdef CONFIG_CRC32_SLICEBY8
-# define CRC_LE_BITS 64
-# define CRC_BE_BITS 64
-#endif
-#ifdef CONFIG_CRC32_SLICEBY4
-# define CRC_LE_BITS 32
-# define CRC_BE_BITS 32
-#endif
-#ifdef CONFIG_CRC32_SARWATE
-# define CRC_LE_BITS 8
-# define CRC_BE_BITS 8
-#endif
-#ifdef CONFIG_CRC32_BIT
-# define CRC_LE_BITS 1
-# define CRC_BE_BITS 1
-#endif
-
-/*
- * How many bits at a time to use.  Valid values are 1, 2, 4, 8, 32 and 64.
- * For less performance-sensitive, use 4 or 8 to save table size.
- * For larger systems choose same as CPU architecture as default.
- * This works well on X86_64, SPARC64 systems. This may require some
- * elaboration after experiments with other architectures.
- */
-#ifndef CRC_LE_BITS
-#  ifdef CONFIG_64BIT
-#  define CRC_LE_BITS 64
-#  else
-#  define CRC_LE_BITS 32
-#  endif
-#endif
-#ifndef CRC_BE_BITS
-#  ifdef CONFIG_64BIT
-#  define CRC_BE_BITS 64
-#  else
-#  define CRC_BE_BITS 32
-#  endif
-#endif
-
-/*
- * Little-endian CRC computation.  Used with serial bit streams sent
- * lsbit-first.  Be sure to use cpu_to_le32() to append the computed CRC.
- */
-#if CRC_LE_BITS > 64 || CRC_LE_BITS < 1 || CRC_LE_BITS == 16 || \
-	CRC_LE_BITS & CRC_LE_BITS-1
-# error "CRC_LE_BITS must be one of {1, 2, 4, 8, 32, 64}"
-#endif
-
-/*
- * Big-endian CRC computation.  Used with serial bit streams sent
- * msbit-first.  Be sure to use cpu_to_be32() to append the computed CRC.
- */
-#if CRC_BE_BITS > 64 || CRC_BE_BITS < 1 || CRC_BE_BITS == 16 || \
-	CRC_BE_BITS & CRC_BE_BITS-1
-# error "CRC_BE_BITS must be one of {1, 2, 4, 8, 32, 64}"
-#endif
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 52eb6ba29698..999053fa133e 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/random.h>
+#include <linux/prandom.h>
 #include <linux/debugfs.h>
 #include <linux/sched.h>
 #include <linux/stat.h>
@@ -13,6 +13,24 @@
 #include <linux/fault-inject.h>
 
 /*
+ * The should_fail() functions use prandom instead of the normal Linux RNG
+ * since they don't need cryptographically secure random numbers.
+ */
+static DEFINE_PER_CPU(struct rnd_state, fault_rnd_state);
+
+static u32 fault_prandom_u32_below_100(void)
+{
+	struct rnd_state *state;
+	u32 res;
+
+	state = &get_cpu_var(fault_rnd_state);
+	res = prandom_u32_state(state);
+	put_cpu_var(fault_rnd_state);
+
+	return res % 100;
+}
+
+/*
  * setup_fault_attr() is a helper function for various __setup handlers, so it
  * returns 0 on error, because that is what __setup handlers do.
  */
@@ -31,6 +49,8 @@ int setup_fault_attr(struct fault_attr *attr, char *str)
 		return 0;
 	}
 
+	prandom_init_once(&fault_rnd_state);
+
 	attr->probability = probability;
 	attr->interval = interval;
 	atomic_set(&attr->times, times);
@@ -146,7 +166,7 @@ bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags)
 			return false;
 	}
 
-	if (attr->probability <= get_random_u32_below(100))
+	if (attr->probability <= fault_prandom_u32_below_100())
 		return false;
 
 fail:
@@ -219,6 +239,8 @@ struct dentry *fault_create_debugfs_attr(const char *name,
 	if (IS_ERR(dir))
 		return dir;
 
+	prandom_init_once(&fault_rnd_state);
+
 	debugfs_create_ul("probability", mode, dir, &attr->probability);
 	debugfs_create_ul("interval", mode, dir, &attr->interval);
 	debugfs_create_atomic_t("times", mode, dir, &attr->times);
@@ -431,6 +453,8 @@ static const struct config_item_type fault_config_type = {
 
 void fault_config_init(struct fault_config *config, const char *name)
 {
+	prandom_init_once(&fault_rnd_state);
+
 	config_group_init_type_name(&config->group, name, &fault_config_type);
 }
 EXPORT_SYMBOL_GPL(fault_config_init);
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index f755b997b967..6d03425b849e 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -2,30 +2,11 @@
 #include <stdio.h>
 #include "../include/linux/crc32poly.h"
 #include "../include/generated/autoconf.h"
-#include "crc32defs.h"
 #include <inttypes.h>
 
-#define ENTRIES_PER_LINE 4
-
-#if CRC_LE_BITS > 8
-# define LE_TABLE_ROWS (CRC_LE_BITS/8)
-# define LE_TABLE_SIZE 256
-#else
-# define LE_TABLE_ROWS 1
-# define LE_TABLE_SIZE (1 << CRC_LE_BITS)
-#endif
-
-#if CRC_BE_BITS > 8
-# define BE_TABLE_ROWS (CRC_BE_BITS/8)
-# define BE_TABLE_SIZE 256
-#else
-# define BE_TABLE_ROWS 1
-# define BE_TABLE_SIZE (1 << CRC_BE_BITS)
-#endif
-
-static uint32_t crc32table_le[LE_TABLE_ROWS][256];
-static uint32_t crc32table_be[BE_TABLE_ROWS][256];
-static uint32_t crc32ctable_le[LE_TABLE_ROWS][256];
+static uint32_t crc32table_le[256];
+static uint32_t crc32table_be[256];
+static uint32_t crc32ctable_le[256];
 
 /**
  * crc32init_le() - allocate and initialize LE table data
@@ -34,25 +15,17 @@ static uint32_t crc32ctable_le[LE_TABLE_ROWS][256];
  * fact that crctable[i^j] = crctable[i] ^ crctable[j].
  *
  */
-static void crc32init_le_generic(const uint32_t polynomial,
-				 uint32_t (*tab)[256])
+static void crc32init_le_generic(const uint32_t polynomial, uint32_t tab[256])
 {
 	unsigned i, j;
 	uint32_t crc = 1;
 
-	tab[0][0] = 0;
+	tab[0] = 0;
 
-	for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) {
+	for (i = 128; i; i >>= 1) {
 		crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
-		for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
-			tab[0][i + j] = crc ^ tab[0][j];
-	}
-	for (i = 0; i < LE_TABLE_SIZE; i++) {
-		crc = tab[0][i];
-		for (j = 1; j < LE_TABLE_ROWS; j++) {
-			crc = tab[0][crc & 0xff] ^ (crc >> 8);
-			tab[j][i] = crc;
-		}
+		for (j = 0; j < 256; j += 2 * i)
+			tab[i + j] = crc ^ tab[j];
 	}
 }
 
@@ -74,34 +47,22 @@ static void crc32init_be(void)
 	unsigned i, j;
 	uint32_t crc = 0x80000000;
 
-	crc32table_be[0][0] = 0;
+	crc32table_be[0] = 0;
 
-	for (i = 1; i < BE_TABLE_SIZE; i <<= 1) {
+	for (i = 1; i < 256; i <<= 1) {
 		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0);
 		for (j = 0; j < i; j++)
-			crc32table_be[0][i + j] = crc ^ crc32table_be[0][j];
-	}
-	for (i = 0; i < BE_TABLE_SIZE; i++) {
-		crc = crc32table_be[0][i];
-		for (j = 1; j < BE_TABLE_ROWS; j++) {
-			crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8);
-			crc32table_be[j][i] = crc;
-		}
+			crc32table_be[i + j] = crc ^ crc32table_be[j];
 	}
 }
 
-static void output_table(uint32_t (*table)[256], int rows, int len, char *trans)
+static void output_table(const uint32_t table[256])
 {
-	int i, j;
-
-	for (j = 0 ; j < rows; j++) {
-		printf("{");
-		for (i = 0; i < len - 1; i++) {
-			if (i % ENTRIES_PER_LINE == 0)
-				printf("\n");
-			printf("%s(0x%8.8xL), ", trans, table[j][i]);
-		}
-		printf("%s(0x%8.8xL)},\n", trans, table[j][len - 1]);
+	int i;
+
+	for (i = 0; i < 256; i += 4) {
+		printf("\t0x%08x, 0x%08x, 0x%08x, 0x%08x,\n",
+		       table[i], table[i + 1], table[i + 2], table[i + 3]);
 	}
 }
 
@@ -109,34 +70,20 @@ int main(int argc, char** argv)
 {
 	printf("/* this file is generated - do not edit */\n\n");
 
-	if (CRC_LE_BITS > 1) {
-		crc32init_le();
-		printf("static const u32 ____cacheline_aligned "
-		       "crc32table_le[%d][%d] = {",
-		       LE_TABLE_ROWS, LE_TABLE_SIZE);
-		output_table(crc32table_le, LE_TABLE_ROWS,
-			     LE_TABLE_SIZE, "tole");
-		printf("};\n");
-	}
+	crc32init_le();
+	printf("static const u32 ____cacheline_aligned crc32table_le[256] = {\n");
+	output_table(crc32table_le);
+	printf("};\n");
 
-	if (CRC_BE_BITS > 1) {
-		crc32init_be();
-		printf("static const u32 ____cacheline_aligned "
-		       "crc32table_be[%d][%d] = {",
-		       BE_TABLE_ROWS, BE_TABLE_SIZE);
-		output_table(crc32table_be, LE_TABLE_ROWS,
-			     BE_TABLE_SIZE, "tobe");
-		printf("};\n");
-	}
-	if (CRC_LE_BITS > 1) {
-		crc32cinit_le();
-		printf("static const u32 ____cacheline_aligned "
-		       "crc32ctable_le[%d][%d] = {",
-		       LE_TABLE_ROWS, LE_TABLE_SIZE);
-		output_table(crc32ctable_le, LE_TABLE_ROWS,
-			     LE_TABLE_SIZE, "tole");
-		printf("};\n");
-	}
+	crc32init_be();
+	printf("static const u32 ____cacheline_aligned crc32table_be[256] = {\n");
+	output_table(crc32table_be);
+	printf("};\n");
+
+	crc32cinit_le();
+	printf("static const u32 ____cacheline_aligned crc32ctable_le[256] = {\n");
+	output_table(crc32ctable_le);
+	printf("};\n");
 
 	return 0;
 }
diff --git a/lib/inflate.c b/lib/inflate.c
index fbaf03c1748d..eab886baa1b4 100644
--- a/lib/inflate.c
+++ b/lib/inflate.c
@@ -1257,8 +1257,6 @@ static int INIT gunzip(void)
     /* Decompress */
     if ((res = inflate())) {
 	    switch (res) {
-	    case 0:
-		    break;
 	    case 1:
 		    error("invalid compressed format (err=1)");
 		    break;
diff --git a/lib/kobject.c b/lib/kobject.c
index 72fa20f405f1..abe5f5b856ce 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -1096,30 +1096,6 @@ void *kobj_ns_grab_current(enum kobj_ns_type type)
 }
 EXPORT_SYMBOL_GPL(kobj_ns_grab_current);
 
-const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk)
-{
-	const void *ns = NULL;
-
-	spin_lock(&kobj_ns_type_lock);
-	if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type])
-		ns = kobj_ns_ops_tbl[type]->netlink_ns(sk);
-	spin_unlock(&kobj_ns_type_lock);
-
-	return ns;
-}
-
-const void *kobj_ns_initial(enum kobj_ns_type type)
-{
-	const void *ns = NULL;
-
-	spin_lock(&kobj_ns_type_lock);
-	if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type])
-		ns = kobj_ns_ops_tbl[type]->initial_ns();
-	spin_unlock(&kobj_ns_type_lock);
-
-	return ns;
-}
-
 void kobj_ns_drop(enum kobj_ns_type type, void *ns)
 {
 	spin_lock(&kobj_ns_type_lock);
diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c
index 10a560feb66e..48342736d016 100644
--- a/lib/kunit_iov_iter.c
+++ b/lib/kunit_iov_iter.c
@@ -57,15 +57,12 @@ static void *__init iov_kunit_create_buffer(struct kunit *test,
         KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pages);
 	*ppages = pages;
 
-	got = alloc_pages_bulk_array(GFP_KERNEL, npages, pages);
+	got = alloc_pages_bulk(GFP_KERNEL, npages, pages);
 	if (got != npages) {
 		release_pages(pages, got);
 		KUNIT_ASSERT_EQ(test, got, npages);
 	}
 
-	for (int i = 0; i < npages; i++)
-		pages[i]->index = i;
-
 	buffer = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL);
         KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buffer);
 
diff --git a/lib/list_debug.c b/lib/list_debug.c
index db602417febf..ee7eeeb8f92c 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -22,17 +22,17 @@ __list_valid_slowpath
 bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev,
 				struct list_head *next)
 {
-	if (CHECK_DATA_CORRUPTION(prev == NULL,
+	if (CHECK_DATA_CORRUPTION(prev == NULL, NULL,
 			"list_add corruption. prev is NULL.\n") ||
-	    CHECK_DATA_CORRUPTION(next == NULL,
+	    CHECK_DATA_CORRUPTION(next == NULL, NULL,
 			"list_add corruption. next is NULL.\n") ||
-	    CHECK_DATA_CORRUPTION(next->prev != prev,
+	    CHECK_DATA_CORRUPTION(next->prev != prev, next,
 			"list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n",
 			prev, next->prev, next) ||
-	    CHECK_DATA_CORRUPTION(prev->next != next,
+	    CHECK_DATA_CORRUPTION(prev->next != next, prev,
 			"list_add corruption. prev->next should be next (%px), but was %px. (prev=%px).\n",
 			next, prev->next, prev) ||
-	    CHECK_DATA_CORRUPTION(new == prev || new == next,
+	    CHECK_DATA_CORRUPTION(new == prev || new == next, NULL,
 			"list_add double add: new=%px, prev=%px, next=%px.\n",
 			new, prev, next))
 		return false;
@@ -49,20 +49,20 @@ bool __list_del_entry_valid_or_report(struct list_head *entry)
 	prev = entry->prev;
 	next = entry->next;
 
-	if (CHECK_DATA_CORRUPTION(next == NULL,
+	if (CHECK_DATA_CORRUPTION(next == NULL, NULL,
 			"list_del corruption, %px->next is NULL\n", entry) ||
-	    CHECK_DATA_CORRUPTION(prev == NULL,
+	    CHECK_DATA_CORRUPTION(prev == NULL, NULL,
 			"list_del corruption, %px->prev is NULL\n", entry) ||
-	    CHECK_DATA_CORRUPTION(next == LIST_POISON1,
+	    CHECK_DATA_CORRUPTION(next == LIST_POISON1, next,
 			"list_del corruption, %px->next is LIST_POISON1 (%px)\n",
 			entry, LIST_POISON1) ||
-	    CHECK_DATA_CORRUPTION(prev == LIST_POISON2,
+	    CHECK_DATA_CORRUPTION(prev == LIST_POISON2, prev,
 			"list_del corruption, %px->prev is LIST_POISON2 (%px)\n",
 			entry, LIST_POISON2) ||
-	    CHECK_DATA_CORRUPTION(prev->next != entry,
+	    CHECK_DATA_CORRUPTION(prev->next != entry, prev,
 			"list_del corruption. prev->next should be %px, but was %px. (prev=%px)\n",
 			entry, prev->next, prev) ||
-	    CHECK_DATA_CORRUPTION(next->prev != entry,
+	    CHECK_DATA_CORRUPTION(next->prev != entry, next,
 			"list_del corruption. next->prev should be %px, but was %px. (next=%px)\n",
 			entry, next->prev, next))
 		return false;
diff --git a/lib/list_sort.c b/lib/list_sort.c
index 8d3f623536fe..a310ecb7ccc0 100644
--- a/lib/list_sort.c
+++ b/lib/list_sort.c
@@ -108,6 +108,13 @@ static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head,
  * and list_sort is a stable sort, so it is not necessary to distinguish
  * the @a < @b and @a == @b cases.
  *
+ * The comparison function must adhere to specific mathematical properties
+ * to ensure correct and stable sorting:
+ * - Antisymmetry: cmp(@a, @b) must return the opposite sign of
+ * cmp(@b, @a).
+ * - Transitivity: if cmp(@a, @b) <= 0 and cmp(@b, @c) <= 0, then
+ * cmp(@a, @c) <= 0.
+ *
  * This is compatible with two styles of @cmp function:
  * - The traditional style which returns <0 / =0 / >0, or
  * - Returning a boolean 0/1.
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
index b0bbeeb74b9e..2a397bb2c661 100644
--- a/lib/lz4/lz4_compress.c
+++ b/lib/lz4/lz4_compress.c
@@ -33,7 +33,6 @@
 /*-************************************
  *	Dependencies
  **************************************/
-#include <linux/lz4.h>
 #include "lz4defs.h"
 #include <linux/module.h>
 #include <linux/kernel.h>
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 0e31e6da5ce7..3a2cd9acada4 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -33,7 +33,6 @@
 /*-************************************
  *	Dependencies
  **************************************/
-#include <linux/lz4.h>
 #include "lz4defs.h"
 #include <linux/init.h>
 #include <linux/module.h>
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index cb358d6bde5a..17277ec16919 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -39,6 +39,7 @@
 
 #include <linux/bitops.h>
 #include <linux/string.h>	 /* memset, memcpy */
+#include <linux/lz4.h>
 
 #define FORCE_INLINE __always_inline
 
@@ -92,8 +93,7 @@ typedef uintptr_t uptrval;
 #define MB (1 << 20)
 #define GB (1U << 30)
 
-#define MAXD_LOG 16
-#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
+#define MAX_DISTANCE LZ4_DISTANCE_MAX
 #define STEPSIZE sizeof(size_t)
 
 #define ML_BITS	4
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
index bc45594ad2a8..91936dc3d14b 100644
--- a/lib/lz4/lz4hc_compress.c
+++ b/lib/lz4/lz4hc_compress.c
@@ -34,7 +34,6 @@
 /*-************************************
  *	Dependencies
  **************************************/
-#include <linux/lz4.h>
 #include "lz4defs.h"
 #include <linux/module.h>
 #include <linux/kernel.h>
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 047397136f15..f7153ade1be5 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -1863,11 +1863,11 @@ static inline int mab_no_null_split(struct maple_big_node *b_node,
  * Return: The first split location.  The middle split is set in @mid_split.
  */
 static inline int mab_calc_split(struct ma_state *mas,
-	 struct maple_big_node *bn, unsigned char *mid_split, unsigned long min)
+	 struct maple_big_node *bn, unsigned char *mid_split)
 {
 	unsigned char b_end = bn->b_end;
 	int split = b_end / 2; /* Assume equal split. */
-	unsigned char slot_min, slot_count = mt_slots[bn->type];
+	unsigned char slot_count = mt_slots[bn->type];
 
 	/*
 	 * To support gap tracking, all NULL entries are kept together and a node cannot
@@ -1900,18 +1900,7 @@ static inline int mab_calc_split(struct ma_state *mas,
 		split = b_end / 3;
 		*mid_split = split * 2;
 	} else {
-		slot_min = mt_min_slots[bn->type];
-
 		*mid_split = 0;
-		/*
-		 * Avoid having a range less than the slot count unless it
-		 * causes one node to be deficient.
-		 * NOTE: mt_min_slots is 1 based, b_end and split are zero.
-		 */
-		while ((split < slot_count - 1) &&
-		       ((bn->pivot[split] - min) < slot_count - 1) &&
-		       (b_end - split > slot_min))
-			split++;
 	}
 
 	/* Avoid ending a node on a NULL entry */
@@ -2377,7 +2366,7 @@ static inline struct maple_enode
 static inline unsigned char mas_mab_to_node(struct ma_state *mas,
 	struct maple_big_node *b_node, struct maple_enode **left,
 	struct maple_enode **right, struct maple_enode **middle,
-	unsigned char *mid_split, unsigned long min)
+	unsigned char *mid_split)
 {
 	unsigned char split = 0;
 	unsigned char slot_count = mt_slots[b_node->type];
@@ -2390,7 +2379,7 @@ static inline unsigned char mas_mab_to_node(struct ma_state *mas,
 	if (b_node->b_end < slot_count) {
 		split = b_node->b_end;
 	} else {
-		split = mab_calc_split(mas, b_node, mid_split, min);
+		split = mab_calc_split(mas, b_node, mid_split);
 		*right = mas_new_ma_node(mas, b_node);
 	}
 
@@ -2877,7 +2866,7 @@ static void mas_spanning_rebalance(struct ma_state *mas,
 		mast->bn->b_end--;
 		mast->bn->type = mte_node_type(mast->orig_l->node);
 		split = mas_mab_to_node(mas, mast->bn, &left, &right, &middle,
-					&mid_split, mast->orig_l->min);
+					&mid_split);
 		mast_set_split_parents(mast, left, middle, right, split,
 				       mid_split);
 		mast_cp_to_nodes(mast, left, middle, right, split, mid_split);
@@ -3365,7 +3354,7 @@ static void mas_split(struct ma_state *mas, struct maple_big_node *b_node)
 		if (mas_push_data(mas, height, &mast, false))
 			break;
 
-		split = mab_calc_split(mas, b_node, &mid_split, prev_l_mas.min);
+		split = mab_calc_split(mas, b_node, &mid_split);
 		mast_split_data(&mast, mas, split);
 		/*
 		 * Usually correct, mab_mas_cp in the above call overwrites
@@ -4746,29 +4735,6 @@ again:
 }
 
 /*
- * mas_next_entry() - Internal function to get the next entry.
- * @mas: The maple state
- * @limit: The maximum range start.
- *
- * Set the @mas->node to the next entry and the range_start to
- * the beginning value for the entry.  Does not check beyond @limit.
- * Sets @mas->index and @mas->last to the range, Does not update @mas->index and
- * @mas->last on overflow.
- * Restarts on dead nodes.
- *
- * Return: the next entry or %NULL.
- */
-static inline void *mas_next_entry(struct ma_state *mas, unsigned long limit)
-{
-	if (mas->last >= limit) {
-		mas->status = ma_overflow;
-		return NULL;
-	}
-
-	return mas_next_slot(mas, limit, false);
-}
-
-/*
  * mas_rev_awalk() - Internal function.  Reverse allocation walk.  Find the
  * highest gap address of a given size in a given node and descend.
  * @mas: The maple state
@@ -4903,15 +4869,14 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
 		if (gap >= size) {
 			if (ma_is_leaf(type)) {
 				found = true;
-				goto done;
-			}
-			if (mas->index <= pivot) {
-				mas->node = mas_slot(mas, slots, offset);
-				mas->min = min;
-				mas->max = pivot;
-				offset = 0;
 				break;
 			}
+
+			mas->node = mas_slot(mas, slots, offset);
+			mas->min = min;
+			mas->max = pivot;
+			offset = 0;
+			break;
 		}
 next_slot:
 		min = pivot + 1;
@@ -4921,9 +4886,6 @@ next_slot:
 		}
 	}
 
-	if (mte_is_root(mas->node))
-		found = true;
-done:
 	mas->offset = offset;
 	return found;
 }
@@ -5027,8 +4989,8 @@ static inline void mas_awalk(struct ma_state *mas, unsigned long size)
 	 * There are 4 options:
 	 * go to child (descend)
 	 * go back to parent (ascend)
-	 * no gap found. (return, slot == MAPLE_NODE_SLOTS)
-	 * found the gap. (return, slot != MAPLE_NODE_SLOTS)
+	 * no gap found. (return, error == -EBUSY)
+	 * found the gap. (return)
 	 */
 	while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) {
 		if (last == mas->node)
@@ -5113,9 +5075,6 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 		return xa_err(mas->node);
 
 	offset = mas->offset;
-	if (unlikely(offset == MAPLE_NODE_SLOTS))
-		return -EBUSY;
-
 	node = mas_mn(mas);
 	mt = mte_node_type(mas->node);
 	pivots = ma_pivots(node, mt);
@@ -6938,7 +6897,7 @@ retry:
 		goto unlock;
 
 	while (mas_is_active(&mas) && (mas.last < max)) {
-		entry = mas_next_entry(&mas, max);
+		entry = mas_next_slot(&mas, max, false);
 		if (likely(entry && !xa_is_zero(entry)))
 			break;
 	}
@@ -7597,7 +7556,7 @@ void mt_validate(struct maple_tree *mt)
 		MAS_WARN_ON(&mas, mte_dead_node(mas.node));
 		end = mas_data_end(&mas);
 		if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) &&
-				(mas.max != ULONG_MAX))) {
+				(!mte_is_root(mas.node)))) {
 			pr_err("Invalid size %u of " PTR_FMT "\n",
 			       end, mas_mn(&mas));
 		}
diff --git a/lib/math/Makefile b/lib/math/Makefile
index 3ef11305f8d2..853f023ae537 100644
--- a/lib/math/Makefile
+++ b/lib/math/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_INT_POW_TEST)  += tests/int_pow_kunit.o
 obj-$(CONFIG_TEST_DIV64)	+= test_div64.o
 obj-$(CONFIG_TEST_MULDIV64)	+= test_mul_u64_u64_div_u64.o
 obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o
+obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += tests/int_sqrt_kunit.o
\ No newline at end of file
diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile
index 6a169123320a..e1a79f093b2d 100644
--- a/lib/math/tests/Makefile
+++ b/lib/math/tests/Makefile
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o
+obj-$(CONFIG_INT_SQRT_KUNIT_TEST) += int_sqrt_kunit.o
diff --git a/lib/math/tests/int_sqrt_kunit.c b/lib/math/tests/int_sqrt_kunit.c
new file mode 100644
index 000000000000..1798e1312eb7
--- /dev/null
+++ b/lib/math/tests/int_sqrt_kunit.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <kunit/test.h>
+#include <linux/limits.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+struct test_case_params {
+	unsigned long x;
+	unsigned long expected_result;
+	const char *name;
+};
+
+static const struct test_case_params params[] = {
+	{ 0, 0, "edge case: square root of 0" },
+	{ 1, 1, "perfect square: square root of 1" },
+	{ 2, 1, "non-perfect square: square root of 2" },
+	{ 3, 1, "non-perfect square: square root of 3" },
+	{ 4, 2, "perfect square: square root of 4" },
+	{ 5, 2, "non-perfect square: square root of 5" },
+	{ 6, 2, "non-perfect square: square root of 6" },
+	{ 7, 2, "non-perfect square: square root of 7" },
+	{ 8, 2, "non-perfect square: square root of 8" },
+	{ 9, 3, "perfect square: square root of 9" },
+	{ 15, 3, "non-perfect square: square root of 15 (N-1 from 16)" },
+	{ 16, 4, "perfect square: square root of 16" },
+	{ 17, 4, "non-perfect square: square root of 17 (N+1 from 16)" },
+	{ 80, 8, "non-perfect square: square root of 80 (N-1 from 81)" },
+	{ 81, 9, "perfect square: square root of 81" },
+	{ 82, 9, "non-perfect square: square root of 82 (N+1 from 81)" },
+	{ 255, 15, "non-perfect square: square root of 255 (N-1 from 256)" },
+	{ 256, 16, "perfect square: square root of 256" },
+	{ 257, 16, "non-perfect square: square root of 257 (N+1 from 256)" },
+	{ 2147483648, 46340, "large input: square root of 2147483648" },
+	{ 4294967295, 65535, "edge case: ULONG_MAX for 32-bit" },
+};
+
+static void get_desc(const struct test_case_params *tc, char *desc)
+{
+	strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE);
+}
+
+KUNIT_ARRAY_PARAM(int_sqrt, params, get_desc);
+
+static void int_sqrt_test(struct kunit *test)
+{
+	const struct test_case_params *tc = (const struct test_case_params *)test->param_value;
+
+	KUNIT_EXPECT_EQ(test, tc->expected_result, int_sqrt(tc->x));
+}
+
+static struct kunit_case math_int_sqrt_test_cases[] = {
+	KUNIT_CASE_PARAM(int_sqrt_test, int_sqrt_gen_params),
+	{}
+};
+
+static struct kunit_suite int_sqrt_test_suite = {
+	.name = "math-int_sqrt",
+	.test_cases = math_int_sqrt_test_cases,
+};
+
+kunit_test_suites(&int_sqrt_test_suite);
+
+MODULE_DESCRIPTION("math.int_sqrt KUnit test suite");
+MODULE_LICENSE("GPL");
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 0e9a1d4cf89b..3e555d012ed6 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -669,7 +669,7 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow);
  * structure outside the hash table.
  *
  * This function may be called from any process context, including
- * non-preemptable context, but cannot be called from softirq or
+ * non-preemptible context, but cannot be called from softirq or
  * hardirq context.
  *
  * You must call rhashtable_walk_exit after this function returns.
diff --git a/lib/sort.c b/lib/sort.c
index 048b7a6ef967..8e73dc55476b 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -200,6 +200,13 @@ static size_t parent(size_t i, unsigned int lsbit, size_t size)
  * copy (e.g. fix up pointers or auxiliary data), but the built-in swap
  * avoids a slow retpoline and so is significantly faster.
  *
+ * The comparison function must adhere to specific mathematical
+ * properties to ensure correct and stable sorting:
+ * - Antisymmetry: cmp_func(a, b) must return the opposite sign of
+ * cmp_func(b, a).
+ * - Transitivity: if cmp_func(a, b) <= 0 and cmp_func(b, c) <= 0, then
+ * cmp_func(a, c) <= 0.
+ *
  * Sorting time is O(n log n) both on average and worst-case. While
  * quicksort is slightly faster on average, it suffers from exploitable
  * O(n*n) worst-case behavior and extra memory requirements that make
diff --git a/lib/stackinit_kunit.c b/lib/stackinit_kunit.c
index c40818ec9c18..135322592faf 100644
--- a/lib/stackinit_kunit.c
+++ b/lib/stackinit_kunit.c
@@ -47,10 +47,12 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
 #define DO_NOTHING_TYPE_SCALAR(var_type)	var_type
 #define DO_NOTHING_TYPE_STRING(var_type)	void
 #define DO_NOTHING_TYPE_STRUCT(var_type)	void
+#define DO_NOTHING_TYPE_UNION(var_type)		void
 
 #define DO_NOTHING_RETURN_SCALAR(ptr)		*(ptr)
 #define DO_NOTHING_RETURN_STRING(ptr)		/**/
 #define DO_NOTHING_RETURN_STRUCT(ptr)		/**/
+#define DO_NOTHING_RETURN_UNION(ptr)		/**/
 
 #define DO_NOTHING_CALL_SCALAR(var, name)			\
 		(var) = do_nothing_ ## name(&(var))
@@ -58,10 +60,13 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
 		do_nothing_ ## name(var)
 #define DO_NOTHING_CALL_STRUCT(var, name)			\
 		do_nothing_ ## name(&(var))
+#define DO_NOTHING_CALL_UNION(var, name)			\
+		do_nothing_ ## name(&(var))
 
 #define FETCH_ARG_SCALAR(var)		&var
 #define FETCH_ARG_STRING(var)		var
 #define FETCH_ARG_STRUCT(var)		&var
+#define FETCH_ARG_UNION(var)		&var
 
 /*
  * On m68k, if the leaf function test variable is longer than 8 bytes,
@@ -70,13 +75,16 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
  */
 #ifdef CONFIG_M68K
 #define FILL_SIZE_STRING		8
+#define FILL_SIZE_ARRAY			2
 #else
 #define FILL_SIZE_STRING		16
+#define FILL_SIZE_ARRAY			8
 #endif
 
 #define INIT_CLONE_SCALAR		/**/
 #define INIT_CLONE_STRING		[FILL_SIZE_STRING]
 #define INIT_CLONE_STRUCT		/**/
+#define INIT_CLONE_UNION		/**/
 
 #define ZERO_CLONE_SCALAR(zero)		memset(&(zero), 0x00, sizeof(zero))
 #define ZERO_CLONE_STRING(zero)		memset(&(zero), 0x00, sizeof(zero))
@@ -92,6 +100,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
 		zero.three = 0;				\
 		zero.four = 0;				\
 	} while (0)
+#define ZERO_CLONE_UNION(zero)		ZERO_CLONE_STRUCT(zero)
 
 #define INIT_SCALAR_none(var_type)	/**/
 #define INIT_SCALAR_zero(var_type)	= 0
@@ -101,6 +110,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
 
 #define INIT_STRUCT_none(var_type)	/**/
 #define INIT_STRUCT_zero(var_type)	= { }
+#define INIT_STRUCT_old_zero(var_type)	= { 0 }
 
 
 #define __static_partial		{ .two = 0, }
@@ -146,6 +156,34 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size,
 #define INIT_STRUCT_assigned_copy(var_type)				\
 					; var = *(arg)
 
+/* Union initialization is the same as structs. */
+#define INIT_UNION_none(var_type)	INIT_STRUCT_none(var_type)
+#define INIT_UNION_zero(var_type)	INIT_STRUCT_zero(var_type)
+#define INIT_UNION_old_zero(var_type)	INIT_STRUCT_old_zero(var_type)
+
+#define INIT_UNION_static_partial(var_type)		\
+	INIT_STRUCT_static_partial(var_type)
+#define INIT_UNION_static_all(var_type)			\
+	INIT_STRUCT_static_all(var_type)
+#define INIT_UNION_dynamic_partial(var_type)		\
+	INIT_STRUCT_dynamic_partial(var_type)
+#define INIT_UNION_dynamic_all(var_type)		\
+	INIT_STRUCT_dynamic_all(var_type)
+#define INIT_UNION_runtime_partial(var_type)		\
+	INIT_STRUCT_runtime_partial(var_type)
+#define INIT_UNION_runtime_all(var_type)		\
+	INIT_STRUCT_runtime_all(var_type)
+#define INIT_UNION_assigned_static_partial(var_type)	\
+	INIT_STRUCT_assigned_static_partial(var_type)
+#define INIT_UNION_assigned_static_all(var_type)	\
+	INIT_STRUCT_assigned_static_all(var_type)
+#define INIT_UNION_assigned_dynamic_partial(var_type)	\
+	INIT_STRUCT_assigned_dynamic_partial(var_type)
+#define INIT_UNION_assigned_dynamic_all(var_type)	\
+	INIT_STRUCT_assigned_dynamic_all(var_type)
+#define INIT_UNION_assigned_copy(var_type)		\
+	INIT_STRUCT_assigned_copy(var_type)
+
 /*
  * @name: unique string name for the test
  * @var_type: type to be tested for zeroing initialization
@@ -294,6 +332,33 @@ struct test_user {
 	unsigned long four;
 };
 
+/* No padding: all members are the same size. */
+union test_same_sizes {
+	unsigned long one;
+	unsigned long two;
+	unsigned long three;
+	unsigned long four;
+};
+
+/* Mismatched sizes, with one and two being small */
+union test_small_start {
+	char one:1;
+	char two;
+	short three;
+	unsigned long four;
+	struct big_struct {
+		unsigned long array[FILL_SIZE_ARRAY];
+	} big;
+};
+
+/* Mismatched sizes, with three and four being small */
+union test_small_end {
+	short one;
+	unsigned long two;
+	char three:1;
+	char four;
+};
+
 #define ALWAYS_PASS	WANT_SUCCESS
 #define ALWAYS_FAIL	XFAIL
 
@@ -332,6 +397,11 @@ struct test_user {
 			    struct test_ ## name, STRUCT, init, \
 			    xfail)
 
+#define DEFINE_UNION_TEST(name, init, xfail)			\
+		DEFINE_TEST(name ## _ ## init,			\
+			    union test_ ## name, STRUCT, init,	\
+			    xfail)
+
 #define DEFINE_STRUCT_TESTS(init, xfail)			\
 		DEFINE_STRUCT_TEST(small_hole, init, xfail);	\
 		DEFINE_STRUCT_TEST(big_hole, init, xfail);	\
@@ -343,9 +413,22 @@ struct test_user {
 				    xfail);			\
 		DEFINE_STRUCT_TESTS(base ## _ ## all, xfail)
 
+#define DEFINE_UNION_INITIALIZER_TESTS(base, xfail)		\
+		DEFINE_UNION_TESTS(base ## _ ## partial,	\
+				    xfail);			\
+		DEFINE_UNION_TESTS(base ## _ ## all, xfail)
+
+#define DEFINE_UNION_TESTS(init, xfail)				\
+		DEFINE_UNION_TEST(same_sizes, init, xfail);	\
+		DEFINE_UNION_TEST(small_start, init, xfail);	\
+		DEFINE_UNION_TEST(small_end, init, xfail);
+
 /* These should be fully initialized all the time! */
 DEFINE_SCALAR_TESTS(zero, ALWAYS_PASS);
 DEFINE_STRUCT_TESTS(zero, ALWAYS_PASS);
+DEFINE_STRUCT_TESTS(old_zero, ALWAYS_PASS);
+DEFINE_UNION_TESTS(zero, ALWAYS_PASS);
+DEFINE_UNION_TESTS(old_zero, ALWAYS_PASS);
 /* Struct initializers: padding may be left uninitialized. */
 DEFINE_STRUCT_INITIALIZER_TESTS(static, STRONG_PASS);
 DEFINE_STRUCT_INITIALIZER_TESTS(dynamic, STRONG_PASS);
@@ -353,6 +436,12 @@ DEFINE_STRUCT_INITIALIZER_TESTS(runtime, STRONG_PASS);
 DEFINE_STRUCT_INITIALIZER_TESTS(assigned_static, STRONG_PASS);
 DEFINE_STRUCT_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS);
 DEFINE_STRUCT_TESTS(assigned_copy, ALWAYS_FAIL);
+DEFINE_UNION_INITIALIZER_TESTS(static, STRONG_PASS);
+DEFINE_UNION_INITIALIZER_TESTS(dynamic, STRONG_PASS);
+DEFINE_UNION_INITIALIZER_TESTS(runtime, STRONG_PASS);
+DEFINE_UNION_INITIALIZER_TESTS(assigned_static, STRONG_PASS);
+DEFINE_UNION_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS);
+DEFINE_UNION_TESTS(assigned_copy, ALWAYS_FAIL);
 /* No initialization without compiler instrumentation. */
 DEFINE_SCALAR_TESTS(none, STRONG_PASS);
 DEFINE_STRUCT_TESTS(none, BYREF_PASS);
@@ -436,13 +525,23 @@ DEFINE_TEST_DRIVER(switch_2_none, uint64_t, SCALAR, ALWAYS_FAIL);
 		KUNIT_CASE(test_trailing_hole_ ## init),\
 		KUNIT_CASE(test_packed_ ## init)	\
 
+#define KUNIT_test_unions(init)				\
+		KUNIT_CASE(test_same_sizes_ ## init),	\
+		KUNIT_CASE(test_small_start_ ## init),	\
+		KUNIT_CASE(test_small_end_ ## init)	\
+
 static struct kunit_case stackinit_test_cases[] = {
 	/* These are explicitly initialized and should always pass. */
 	KUNIT_test_scalars(zero),
 	KUNIT_test_structs(zero),
+	KUNIT_test_structs(old_zero),
+	KUNIT_test_unions(zero),
+	KUNIT_test_unions(old_zero),
 	/* Padding here appears to be accidentally always initialized? */
 	KUNIT_test_structs(dynamic_partial),
 	KUNIT_test_structs(assigned_dynamic_partial),
+	KUNIT_test_unions(dynamic_partial),
+	KUNIT_test_unions(assigned_dynamic_partial),
 	/* Padding initialization depends on compiler behaviors. */
 	KUNIT_test_structs(static_partial),
 	KUNIT_test_structs(static_all),
@@ -452,8 +551,17 @@ static struct kunit_case stackinit_test_cases[] = {
 	KUNIT_test_structs(assigned_static_partial),
 	KUNIT_test_structs(assigned_static_all),
 	KUNIT_test_structs(assigned_dynamic_all),
+	KUNIT_test_unions(static_partial),
+	KUNIT_test_unions(static_all),
+	KUNIT_test_unions(dynamic_all),
+	KUNIT_test_unions(runtime_partial),
+	KUNIT_test_unions(runtime_all),
+	KUNIT_test_unions(assigned_static_partial),
+	KUNIT_test_unions(assigned_static_all),
+	KUNIT_test_unions(assigned_dynamic_all),
 	/* Everything fails this since it effectively performs a memcpy(). */
 	KUNIT_test_structs(assigned_copy),
+	KUNIT_test_unions(assigned_copy),
 	/* STRUCTLEAK_BYREF_ALL should cover everything from here down. */
 	KUNIT_test_scalars(none),
 	KUNIT_CASE(test_switch_1_none),
diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c
index 704cb1093ae8..13e2a10d7554 100644
--- a/lib/test_maple_tree.c
+++ b/lib/test_maple_tree.c
@@ -1563,6 +1563,30 @@ static noinline void __init check_root_expand(struct maple_tree *mt)
 	mas_unlock(&mas);
 }
 
+static noinline void __init check_deficient_node(struct maple_tree *mt)
+{
+	MA_STATE(mas, mt, 0, 0);
+	int count;
+
+	mas_lock(&mas);
+	for (count = 0; count < 10; count++) {
+		mas_set(&mas, count);
+		mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL);
+	}
+
+	for (count = 20; count < 39; count++) {
+		mas_set(&mas, count);
+		mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL);
+	}
+
+	for (count = 10; count < 12; count++) {
+		mas_set(&mas, count);
+		mas_store_gfp(&mas, xa_mk_value(count), GFP_KERNEL);
+	}
+	mas_unlock(&mas);
+	mt_validate(mt);
+}
+
 static noinline void __init check_gap_combining(struct maple_tree *mt)
 {
 	struct maple_enode *mn1, *mn2;
@@ -3714,6 +3738,34 @@ static noinline void __init alloc_cyclic_testing(struct maple_tree *mt)
 	}
 
 	mtree_destroy(mt);
+
+	/*
+	 * Issue with reverse search was discovered
+	 * https://lore.kernel.org/all/20241216060600.287B4C4CED0@smtp.kernel.org/
+	 * Exhausting the allocation area and forcing the search to wrap needs a
+	 * mas_reset() in mas_alloc_cyclic().
+	 */
+	next = 0;
+	mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE);
+	for (int i = 0; i < 1023; i++) {
+		mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL);
+		MT_BUG_ON(mt, i != location - 2);
+		MT_BUG_ON(mt, i != next - 3);
+		MT_BUG_ON(mt, mtree_load(mt, location) != mt);
+	}
+	mtree_erase(mt, 123);
+	MT_BUG_ON(mt, mtree_load(mt, 123) != NULL);
+	mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, 123 != location);
+	MT_BUG_ON(mt, 124 != next);
+	MT_BUG_ON(mt, mtree_load(mt, location) != mt);
+	mtree_erase(mt, 100);
+	mtree_alloc_cyclic(mt, &location, mt, 2, 1024, &next, GFP_KERNEL);
+	MT_BUG_ON(mt, 100 != location);
+	MT_BUG_ON(mt, 101 != next);
+	MT_BUG_ON(mt, mtree_load(mt, location) != mt);
+	mtree_destroy(mt);
+
 	/* Overflow test */
 	next = ULONG_MAX - 1;
 	ret = mtree_alloc_cyclic(mt, &location, mt, 2, ULONG_MAX, &next, GFP_KERNEL);
@@ -3797,6 +3849,10 @@ static int __init maple_tree_seed(void)
 #endif
 
 	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
+	check_deficient_node(&tree);
+	mtree_destroy(&tree);
+
+	mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE);
 	check_store_null(&tree);
 	mtree_destroy(&tree);
 
diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c
index e6fbb798558b..a9c4a74d3898 100644
--- a/lib/test_min_heap.c
+++ b/lib/test_min_heap.c
@@ -32,7 +32,7 @@ static __init int pop_verify_heap(bool min_heap,
 	int last;
 
 	last = values[0];
-	min_heap_pop(heap, funcs, NULL);
+	min_heap_pop_inline(heap, funcs, NULL);
 	while (heap->nr > 0) {
 		if (min_heap) {
 			if (last > values[0]) {
@@ -48,7 +48,7 @@ static __init int pop_verify_heap(bool min_heap,
 			}
 		}
 		last = values[0];
-		min_heap_pop(heap, funcs, NULL);
+		min_heap_pop_inline(heap, funcs, NULL);
 	}
 	return err;
 }
@@ -69,7 +69,7 @@ static __init int test_heapify_all(bool min_heap)
 	int i, err;
 
 	/* Test with known set of values. */
-	min_heapify_all(&heap, &funcs, NULL);
+	min_heapify_all_inline(&heap, &funcs, NULL);
 	err = pop_verify_heap(min_heap, &heap, &funcs);
 
 
@@ -78,7 +78,7 @@ static __init int test_heapify_all(bool min_heap)
 	for (i = 0; i < heap.nr; i++)
 		values[i] = get_random_u32();
 
-	min_heapify_all(&heap, &funcs, NULL);
+	min_heapify_all_inline(&heap, &funcs, NULL);
 	err += pop_verify_heap(min_heap, &heap, &funcs);
 
 	return err;
@@ -102,14 +102,14 @@ static __init int test_heap_push(bool min_heap)
 
 	/* Test with known set of values copied from data. */
 	for (i = 0; i < ARRAY_SIZE(data); i++)
-		min_heap_push(&heap, &data[i], &funcs, NULL);
+		min_heap_push_inline(&heap, &data[i], &funcs, NULL);
 
 	err = pop_verify_heap(min_heap, &heap, &funcs);
 
 	/* Test with randomly generated values. */
 	while (heap.nr < heap.size) {
 		temp = get_random_u32();
-		min_heap_push(&heap, &temp, &funcs, NULL);
+		min_heap_push_inline(&heap, &temp, &funcs, NULL);
 	}
 	err += pop_verify_heap(min_heap, &heap, &funcs);
 
@@ -135,22 +135,22 @@ static __init int test_heap_pop_push(bool min_heap)
 	/* Fill values with data to pop and replace. */
 	temp = min_heap ? 0x80000000 : 0x7FFFFFFF;
 	for (i = 0; i < ARRAY_SIZE(data); i++)
-		min_heap_push(&heap, &temp, &funcs, NULL);
+		min_heap_push_inline(&heap, &temp, &funcs, NULL);
 
 	/* Test with known set of values copied from data. */
 	for (i = 0; i < ARRAY_SIZE(data); i++)
-		min_heap_pop_push(&heap, &data[i], &funcs, NULL);
+		min_heap_pop_push_inline(&heap, &data[i], &funcs, NULL);
 
 	err = pop_verify_heap(min_heap, &heap, &funcs);
 
 	heap.nr = 0;
 	for (i = 0; i < ARRAY_SIZE(data); i++)
-		min_heap_push(&heap, &temp, &funcs, NULL);
+		min_heap_push_inline(&heap, &temp, &funcs, NULL);
 
 	/* Test with randomly generated values. */
 	for (i = 0; i < ARRAY_SIZE(data); i++) {
 		temp = get_random_u32();
-		min_heap_pop_push(&heap, &temp, &funcs, NULL);
+		min_heap_pop_push_inline(&heap, &temp, &funcs, NULL);
 	}
 	err += pop_verify_heap(min_heap, &heap, &funcs);
 
@@ -163,7 +163,7 @@ static __init int test_heap_del(bool min_heap)
 			 -3, -1, -2, -4, 0x8000000, 0x7FFFFFF };
 	struct min_heap_test heap;
 
-	min_heap_init(&heap, values, ARRAY_SIZE(values));
+	min_heap_init_inline(&heap, values, ARRAY_SIZE(values));
 	heap.nr = ARRAY_SIZE(values);
 	struct min_heap_callbacks funcs = {
 		.less = min_heap ? less_than : greater_than,
@@ -172,9 +172,9 @@ static __init int test_heap_del(bool min_heap)
 	int i, err;
 
 	/* Test with known set of values. */
-	min_heapify_all(&heap, &funcs, NULL);
+	min_heapify_all_inline(&heap, &funcs, NULL);
 	for (i = 0; i < ARRAY_SIZE(values) / 2; i++)
-		min_heap_del(&heap, get_random_u32() % heap.nr, &funcs, NULL);
+		min_heap_del_inline(&heap, get_random_u32() % heap.nr, &funcs, NULL);
 	err = pop_verify_heap(min_heap, &heap, &funcs);
 
 
@@ -182,10 +182,10 @@ static __init int test_heap_del(bool min_heap)
 	heap.nr = ARRAY_SIZE(values);
 	for (i = 0; i < heap.nr; i++)
 		values[i] = get_random_u32();
-	min_heapify_all(&heap, &funcs, NULL);
+	min_heapify_all_inline(&heap, &funcs, NULL);
 
 	for (i = 0; i < ARRAY_SIZE(values) / 2; i++)
-		min_heap_del(&heap, get_random_u32() % heap.nr, &funcs, NULL);
+		min_heap_del_inline(&heap, get_random_u32() % heap.nr, &funcs, NULL);
 	err += pop_verify_heap(min_heap, &heap, &funcs);
 
 	return err;
diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index b6696fa1d426..4249e0cc8aaf 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -71,7 +71,7 @@ static struct test_sysctl_data test_data = {
 };
 
 /* These are all under /proc/sys/debug/test_sysctl/ */
-static struct ctl_table test_table[] = {
+static const struct ctl_table test_table[] = {
 	{
 		.procname	= "int_0001",
 		.data		= &test_data.int_0001,
@@ -177,7 +177,7 @@ static int test_sysctl_setup_node_tests(void)
 }
 
 /* Used to test that unregister actually removes the directory */
-static struct ctl_table test_table_unregister[] = {
+static const struct ctl_table test_table_unregister[] = {
 	{
 		.procname	= "unregister_error",
 		.data		= &test_data.int_0001,
@@ -220,7 +220,7 @@ static int test_sysctl_run_register_mount_point(void)
 	return 0;
 }
 
-static struct ctl_table test_table_empty[] = { };
+static const struct ctl_table test_table_empty[] = { };
 
 static int test_sysctl_run_register_empty(void)
 {
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 4ddf769861ff..f585949ff696 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -373,7 +373,7 @@ vm_map_ram_test(void)
 	if (!pages)
 		return -1;
 
-	nr_allocated = alloc_pages_bulk_array(GFP_KERNEL, map_nr_pages, pages);
+	nr_allocated = alloc_pages_bulk(GFP_KERNEL, map_nr_pages, pages);
 	if (nr_allocated != map_nr_pages)
 		goto cleanup;
 
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index d5c5cbba33ed..6932a26f4927 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1448,6 +1448,41 @@ static noinline void check_pause(struct xarray *xa)
 	XA_BUG_ON(xa, count != order_limit);
 
 	xa_destroy(xa);
+
+	index = 0;
+	for (order = XA_CHUNK_SHIFT; order > 0; order--) {
+		XA_BUG_ON(xa, xa_store_order(xa, index, order,
+					xa_mk_index(index), GFP_KERNEL));
+		index += 1UL << order;
+	}
+
+	index = 0;
+	count = 0;
+	xas_set(&xas, 0);
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		XA_BUG_ON(xa, entry != xa_mk_index(index));
+		index += 1UL << (XA_CHUNK_SHIFT - count);
+		count++;
+	}
+	rcu_read_unlock();
+	XA_BUG_ON(xa, count != XA_CHUNK_SHIFT);
+
+	index = 0;
+	count = 0;
+	xas_set(&xas, XA_CHUNK_SIZE / 2 + 1);
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		XA_BUG_ON(xa, entry != xa_mk_index(index));
+		index += 1UL << (XA_CHUNK_SHIFT - count);
+		count++;
+		xas_pause(&xas);
+	}
+	rcu_read_unlock();
+	XA_BUG_ON(xa, count != XA_CHUNK_SHIFT);
+
+	xa_destroy(xa);
+
 }
 
 static noinline void check_move_tiny(struct xarray *xa)
diff --git a/lib/xarray.c b/lib/xarray.c
index 32d4bac8c94c..116e9286c64e 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -125,19 +125,20 @@ static inline void node_mark_all(struct xa_node *node, xa_mark_t mark)
  */
 static void xas_squash_marks(const struct xa_state *xas)
 {
-	unsigned int mark = 0;
+	xa_mark_t mark = 0;
 	unsigned int limit = xas->xa_offset + xas->xa_sibs + 1;
 
-	if (!xas->xa_sibs)
-		return;
+	for (;;) {
+		unsigned long *marks = node_marks(xas->xa_node, mark);
 
-	do {
-		unsigned long *marks = xas->xa_node->marks[mark];
-		if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit)
-			continue;
-		__set_bit(xas->xa_offset, marks);
-		bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
-	} while (mark++ != (__force unsigned)XA_MARK_MAX);
+		if (find_next_bit(marks, limit, xas->xa_offset + 1) != limit) {
+			__set_bit(xas->xa_offset, marks);
+			bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs);
+		}
+		if (mark == XA_MARK_MAX)
+			break;
+		mark_inc(mark);
+	}
 }
 
 /* extracts the offset within this node from the index */
@@ -435,6 +436,11 @@ static unsigned long max_index(void *entry)
 	return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1;
 }
 
+static inline void *xa_zero_to_null(void *entry)
+{
+	return xa_is_zero(entry) ? NULL : entry;
+}
+
 static void xas_shrink(struct xa_state *xas)
 {
 	struct xarray *xa = xas->xa;
@@ -451,8 +457,8 @@ static void xas_shrink(struct xa_state *xas)
 			break;
 		if (!xa_is_node(entry) && node->shift)
 			break;
-		if (xa_is_zero(entry) && xa_zero_busy(xa))
-			entry = NULL;
+		if (xa_zero_busy(xa))
+			entry = xa_zero_to_null(entry);
 		xas->xa_node = XAS_BOUNDS;
 
 		RCU_INIT_POINTER(xa->xa_head, entry);
@@ -1022,7 +1028,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order,
 	unsigned int mask = xas->xa_sibs;
 
 	/* XXX: no support for splitting really large entries yet */
-	if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order))
+	if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT <= order))
 		goto nomem;
 	if (xas->xa_shift + XA_CHUNK_SHIFT > order)
 		return;
@@ -1147,6 +1153,7 @@ void xas_pause(struct xa_state *xas)
 			if (!xa_is_sibling(xa_entry(xas->xa, node, offset)))
 				break;
 		}
+		xas->xa_index &= ~0UL << node->shift;
 		xas->xa_index += (offset - xas->xa_offset) << node->shift;
 		if (xas->xa_index == 0)
 			xas->xa_node = XAS_BOUNDS;
@@ -1382,6 +1389,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark)
 		entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset);
 		if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK))
 			continue;
+		if (xa_is_sibling(entry))
+			continue;
 		if (!xa_is_node(entry))
 			return entry;
 		xas->xa_node = xa_to_node(entry);
@@ -1474,9 +1483,7 @@ void *xa_load(struct xarray *xa, unsigned long index)
 
 	rcu_read_lock();
 	do {
-		entry = xas_load(&xas);
-		if (xa_is_zero(entry))
-			entry = NULL;
+		entry = xa_zero_to_null(xas_load(&xas));
 	} while (xas_retry(&xas, entry));
 	rcu_read_unlock();
 
@@ -1486,8 +1493,6 @@ EXPORT_SYMBOL(xa_load);
 
 static void *xas_result(struct xa_state *xas, void *curr)
 {
-	if (xa_is_zero(curr))
-		return NULL;
 	if (xas_error(xas))
 		curr = xas->xa_node;
 	return curr;
@@ -1508,7 +1513,7 @@ static void *xas_result(struct xa_state *xas, void *curr)
 void *__xa_erase(struct xarray *xa, unsigned long index)
 {
 	XA_STATE(xas, xa, index);
-	return xas_result(&xas, xas_store(&xas, NULL));
+	return xas_result(&xas, xa_zero_to_null(xas_store(&xas, NULL)));
 }
 EXPORT_SYMBOL(__xa_erase);
 
@@ -1567,7 +1572,7 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
 			xas_clear_mark(&xas, XA_FREE_MARK);
 	} while (__xas_nomem(&xas, gfp));
 
-	return xas_result(&xas, curr);
+	return xas_result(&xas, xa_zero_to_null(curr));
 }
 EXPORT_SYMBOL(__xa_store);
 
@@ -1600,6 +1605,9 @@ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
 }
 EXPORT_SYMBOL(xa_store);
 
+static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index,
+			void *old, void *entry, gfp_t gfp);
+
 /**
  * __xa_cmpxchg() - Store this entry in the XArray.
  * @xa: XArray.
@@ -1619,6 +1627,13 @@ EXPORT_SYMBOL(xa_store);
 void *__xa_cmpxchg(struct xarray *xa, unsigned long index,
 			void *old, void *entry, gfp_t gfp)
 {
+	return xa_zero_to_null(__xa_cmpxchg_raw(xa, index, old, entry, gfp));
+}
+EXPORT_SYMBOL(__xa_cmpxchg);
+
+static inline void *__xa_cmpxchg_raw(struct xarray *xa, unsigned long index,
+			void *old, void *entry, gfp_t gfp)
+{
 	XA_STATE(xas, xa, index);
 	void *curr;
 
@@ -1636,7 +1651,6 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index,
 
 	return xas_result(&xas, curr);
 }
-EXPORT_SYMBOL(__xa_cmpxchg);
 
 /**
  * __xa_insert() - Store this entry in the XArray if no entry is present.
@@ -1656,26 +1670,16 @@ EXPORT_SYMBOL(__xa_cmpxchg);
  */
 int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp)
 {
-	XA_STATE(xas, xa, index);
 	void *curr;
+	int errno;
 
-	if (WARN_ON_ONCE(xa_is_advanced(entry)))
-		return -EINVAL;
 	if (!entry)
 		entry = XA_ZERO_ENTRY;
-
-	do {
-		curr = xas_load(&xas);
-		if (!curr) {
-			xas_store(&xas, entry);
-			if (xa_track_free(xa))
-				xas_clear_mark(&xas, XA_FREE_MARK);
-		} else {
-			xas_set_err(&xas, -EBUSY);
-		}
-	} while (__xas_nomem(&xas, gfp));
-
-	return xas_error(&xas);
+	curr = __xa_cmpxchg_raw(xa, index, NULL, entry, gfp);
+	errno = xa_err(curr);
+	if (errno)
+		return errno;
+	return (curr != NULL) ? -EBUSY : 0;
 }
 EXPORT_SYMBOL(__xa_insert);
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 84000b016808..1b501db06417 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -550,20 +550,63 @@ menuconfig MEMORY_HOTPLUG
 
 if MEMORY_HOTPLUG
 
-config MEMORY_HOTPLUG_DEFAULT_ONLINE
-	bool "Online the newly added memory blocks by default"
-	depends on MEMORY_HOTPLUG
+choice
+	prompt "Memory Hotplug Default Online Type"
+	default MHP_DEFAULT_ONLINE_TYPE_OFFLINE
 	help
+	  Default memory type for hotplugged memory.
+
 	  This option sets the default policy setting for memory hotplug
 	  onlining policy (/sys/devices/system/memory/auto_online_blocks) which
 	  determines what happens to newly added memory regions. Policy setting
 	  can always be changed at runtime.
+
+	  The default is 'offline'.
+
+	  Select offline to defer onlining to drivers and user policy.
+	  Select auto to let the kernel choose what zones to utilize.
+	  Select online_kernel to generally allow kernel usage of this memory.
+	  Select online_movable to generally disallow kernel usage of this memory.
+
+	  Example kernel usage would be page structs and page tables.
+
 	  See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
 
-	  Say Y here if you want all hot-plugged memory blocks to appear in
-	  'online' state by default.
-	  Say N here if you want the default policy to keep all hot-plugged
-	  memory blocks in 'offline' state.
+config MHP_DEFAULT_ONLINE_TYPE_OFFLINE
+	bool "offline"
+	help
+	  Hotplugged memory will not be onlined by default.
+	  Choose this for systems with drivers and user policy that
+	  handle onlining of hotplug memory policy.
+
+config MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO
+	bool "auto"
+	help
+	  Select this if you want the kernel to automatically online
+	  hotplugged memory into the zone it thinks is reasonable.
+	  This memory may be utilized for kernel data.
+
+config MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL
+	bool "kernel"
+	help
+	  Select this if you want the kernel to automatically online
+	  hotplugged memory into a zone capable of being used for kernel
+	  data. This typically means ZONE_NORMAL.
+
+config MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE
+	bool "movable"
+	help
+	  Select this if you want the kernel to automatically online
+	  hotplug memory into ZONE_MOVABLE. This memory will generally
+	  not be utilized for kernel data.
+
+	  This should only be used when the admin knows sufficient
+	  ZONE_NORMAL memory is available to describe hotplug memory,
+	  otherwise hotplug memory may fail to online. For example,
+	  sufficient kernel-capable memory (ZONE_NORMAL) must be
+	  available to allocate page structs to describe ZONE_MOVABLE.
+
+endchoice
 
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
@@ -1301,6 +1344,21 @@ config ARCH_HAS_USER_SHADOW_STACK
 	  The architecture has hardware support for userspace shadow call
           stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss).
 
+config ARCH_SUPPORTS_PT_RECLAIM
+	def_bool n
+
+config PT_RECLAIM
+	bool "reclaim empty user page table pages"
+	default y
+	depends on ARCH_SUPPORTS_PT_RECLAIM && MMU && SMP
+	select MMU_GATHER_RCU_TABLE_FREE
+	help
+	  Try to reclaim empty user page table pages in paths other than munmap
+	  and exit_mmap path.
+
+	  Note: now only empty user PTE page table pages will be reclaimed.
+
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/Makefile b/mm/Makefile
index dba52bb0da8a..850386a67b3e 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -146,3 +146,4 @@ obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
 obj-$(CONFIG_EXECMEM) += execmem.o
 obj-$(CONFIG_TMPFS_QUOTA) += shmem_quota.o
+obj-$(CONFIG_PT_RECLAIM) += pt_reclaim.o
diff --git a/mm/cma.h b/mm/cma.h
index ad61cc6dd439..8485ef893e99 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -36,7 +36,7 @@ struct cma {
 };
 
 extern struct cma cma_areas[MAX_CMA_AREAS];
-extern unsigned cma_area_count;
+extern unsigned int cma_area_count;
 
 static inline unsigned long cma_bitmap_maxno(struct cma *cma)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index a31c0f5758cf..12ed8425fa17 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -83,6 +83,7 @@ static inline bool is_via_compact_memory(int order) { return false; }
 static struct page *mark_allocated_noprof(struct page *page, unsigned int order, gfp_t gfp_flags)
 {
 	post_alloc_hook(page, order, __GFP_MOVABLE);
+	set_page_refcounted(page);
 	return page;
 }
 #define mark_allocated(...)	alloc_hooks(mark_allocated_noprof(__VA_ARGS__))
@@ -630,7 +631,8 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (PageCompound(page)) {
 			const unsigned int order = compound_order(page);
 
-			if (blockpfn + (1UL << order) <= end_pfn) {
+			if ((order <= MAX_PAGE_ORDER) &&
+			    (blockpfn + (1UL << order) <= end_pfn)) {
 				blockpfn += (1UL << order) - 1;
 				page += (1UL << order) - 1;
 				nr_scanned += (1UL << order) - 1;
@@ -1868,6 +1870,7 @@ again:
 	dst = (struct folio *)freepage;
 
 	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
+	set_page_refcounted(&dst->page);
 	if (order)
 		prep_compound_page(&dst->page, order);
 	cc->nr_freepages -= 1 << order;
@@ -2488,7 +2491,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
  */
 static enum compact_result
 compaction_suit_allocation_order(struct zone *zone, unsigned int order,
-				 int highest_zoneidx, unsigned int alloc_flags)
+				 int highest_zoneidx, unsigned int alloc_flags,
+				 bool async)
 {
 	unsigned long watermark;
 
@@ -2497,6 +2501,23 @@ compaction_suit_allocation_order(struct zone *zone, unsigned int order,
 			      alloc_flags))
 		return COMPACT_SUCCESS;
 
+	/*
+	 * For unmovable allocations (without ALLOC_CMA), check if there is enough
+	 * free memory in the non-CMA pageblocks. Otherwise compaction could form
+	 * the high-order page in CMA pageblocks, which would not help the
+	 * allocation to succeed. However, limit the check to costly order async
+	 * compaction (such as opportunistic THP attempts) because there is the
+	 * possibility that compaction would migrate pages from non-CMA to CMA
+	 * pageblock.
+	 */
+	if (order > PAGE_ALLOC_COSTLY_ORDER && async &&
+	    !(alloc_flags & ALLOC_CMA)) {
+		watermark = low_wmark_pages(zone) + compact_gap(order);
+		if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx,
+					   0, zone_page_state(zone, NR_FREE_PAGES)))
+			return COMPACT_SKIPPED;
+	}
+
 	if (!compaction_suitable(zone, order, highest_zoneidx))
 		return COMPACT_SKIPPED;
 
@@ -2532,7 +2553,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 	if (!is_via_compact_memory(cc->order)) {
 		ret = compaction_suit_allocation_order(cc->zone, cc->order,
 						       cc->highest_zoneidx,
-						       cc->alloc_flags);
+						       cc->alloc_flags,
+						       cc->mode == MIGRATE_ASYNC);
 		if (ret != COMPACT_CONTINUE)
 			return ret;
 	}
@@ -3035,7 +3057,8 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat)
 
 		ret = compaction_suit_allocation_order(zone,
 				pgdat->kcompactd_max_order,
-				highest_zoneidx, ALLOC_WMARK_MIN);
+				highest_zoneidx, ALLOC_WMARK_MIN,
+				false);
 		if (ret == COMPACT_CONTINUE)
 			return true;
 	}
@@ -3076,7 +3099,8 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 			continue;
 
 		ret = compaction_suit_allocation_order(zone,
-				cc.order, zoneid, ALLOC_WMARK_MIN);
+				cc.order, zoneid, ALLOC_WMARK_MIN,
+				false);
 		if (ret != COMPACT_CONTINUE)
 			continue;
 
@@ -3269,7 +3293,7 @@ static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table,
 	return ret;
 }
 
-static struct ctl_table vm_compaction[] = {
+static const struct ctl_table vm_compaction[] = {
 	{
 		.procname	= "compact_memory",
 		.data		= &sysctl_compact_memory,
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index d0357f3e9372..c213cf8b5638 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -71,36 +71,6 @@ config DAMON_SYSFS_KUNIT_TEST
 
 	  If unsure, say N.
 
-config DAMON_DBGFS_DEPRECATED
-	bool "DAMON debugfs interface (DEPRECATED!)"
-	depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS
-	help
-	  This builds the debugfs interface for DAMON.  The user space admins
-	  can use the interface for arbitrary data access monitoring.
-
-	  If unsure, say N.
-
-	  This is deprecated, so users should move to the sysfs interface
-	  (DAMON_SYSFS).  If you depend on this and cannot move, please report
-	  your usecase to damon@lists.linux.dev and linux-mm@kvack.org.
-
-config DAMON_DBGFS
-	bool
-	default y
-	depends on DAMON_DBGFS_DEPRECATED
-
-config DAMON_DBGFS_KUNIT_TEST
-	bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS
-	depends on DAMON_DBGFS && KUNIT=y
-	default KUNIT_ALL_TESTS
-	help
-	  This builds the DAMON debugfs interface Kunit test suite.
-
-	  For more information on KUnit and unit tests in general, please refer
-	  to the KUnit documentation.
-
-	  If unsure, say N.
-
 config DAMON_RECLAIM
 	bool "Build DAMON-based reclaim (DAMON_RECLAIM)"
 	depends on DAMON_PADDR
diff --git a/mm/damon/Makefile b/mm/damon/Makefile
index f7add3f4aa79..8b49012ba8c3 100644
--- a/mm/damon/Makefile
+++ b/mm/damon/Makefile
@@ -4,6 +4,5 @@ obj-y				:= core.o
 obj-$(CONFIG_DAMON_VADDR)	+= ops-common.o vaddr.o
 obj-$(CONFIG_DAMON_PADDR)	+= ops-common.o paddr.o
 obj-$(CONFIG_DAMON_SYSFS)	+= sysfs-common.o sysfs-schemes.o sysfs.o
-obj-$(CONFIG_DAMON_DBGFS)	+= dbgfs.o
 obj-$(CONFIG_DAMON_RECLAIM)	+= modules-common.o reclaim.o
 obj-$(CONFIG_DAMON_LRU_SORT)	+= modules-common.o lru_sort.o
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 0776452a1abb..c7b981308862 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -14,6 +14,7 @@
 #include <linux/psi.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/damon.h>
@@ -266,7 +267,7 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
 }
 
 struct damos_filter *damos_new_filter(enum damos_filter_type type,
-		bool matching)
+		bool matching, bool allow)
 {
 	struct damos_filter *filter;
 
@@ -275,6 +276,7 @@ struct damos_filter *damos_new_filter(enum damos_filter_type type,
 		return NULL;
 	filter->type = type;
 	filter->matching = matching;
+	filter->allow = allow;
 	INIT_LIST_HEAD(&filter->list);
 	return filter;
 }
@@ -504,6 +506,8 @@ struct damon_ctx *damon_new_ctx(void)
 	ctx->next_ops_update_sis = 0;
 
 	mutex_init(&ctx->kdamond_lock);
+	mutex_init(&ctx->call_control_lock);
+	mutex_init(&ctx->walk_control_lock);
 
 	ctx->attrs.min_nr_regions = 10;
 	ctx->attrs.max_nr_regions = 1000;
@@ -803,7 +807,8 @@ static int damos_commit_filters(struct damos *dst, struct damos *src)
 			continue;
 
 		new_filter = damos_new_filter(
-				src_filter->type, src_filter->matching);
+				src_filter->type, src_filter->matching,
+				src_filter->allow);
 		if (!new_filter)
 			return -ENOMEM;
 		damos_commit_filter_arg(new_filter, src_filter);
@@ -1162,6 +1167,94 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs)
 	return err;
 }
 
+static bool damon_is_running(struct damon_ctx *ctx)
+{
+	bool running;
+
+	mutex_lock(&ctx->kdamond_lock);
+	running = ctx->kdamond != NULL;
+	mutex_unlock(&ctx->kdamond_lock);
+	return running;
+}
+
+/**
+ * damon_call() - Invoke a given function on DAMON worker thread (kdamond).
+ * @ctx:	DAMON context to call the function for.
+ * @control:	Control variable of the call request.
+ *
+ * Ask DAMON worker thread (kdamond) of @ctx to call a function with an
+ * argument data that respectively passed via &damon_call_control->fn and
+ * &damon_call_control->data of @control, and wait until the kdamond finishes
+ * handling of the request.
+ *
+ * The kdamond executes the function with the argument in the main loop, just
+ * after a sampling of the iteration is finished.  The function can hence
+ * safely access the internal data of the &struct damon_ctx without additional
+ * synchronization.  The return value of the function will be saved in
+ * &damon_call_control->return_code.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_call(struct damon_ctx *ctx, struct damon_call_control *control)
+{
+	init_completion(&control->completion);
+	control->canceled = false;
+
+	mutex_lock(&ctx->call_control_lock);
+	if (ctx->call_control) {
+		mutex_unlock(&ctx->call_control_lock);
+		return -EBUSY;
+	}
+	ctx->call_control = control;
+	mutex_unlock(&ctx->call_control_lock);
+	if (!damon_is_running(ctx))
+		return -EINVAL;
+	wait_for_completion(&control->completion);
+	if (control->canceled)
+		return -ECANCELED;
+	return 0;
+}
+
+/**
+ * damos_walk() - Invoke a given functions while DAMOS walk regions.
+ * @ctx:	DAMON context to call the functions for.
+ * @control:	Control variable of the walk request.
+ *
+ * Ask DAMON worker thread (kdamond) of @ctx to call a function for each region
+ * that the kdamond will apply DAMOS action to, and wait until the kdamond
+ * finishes handling of the request.
+ *
+ * The kdamond executes the given function in the main loop, for each region
+ * just after it applied any DAMOS actions of @ctx to it.  The invocation is
+ * made only within one &damos->apply_interval_us since damos_walk()
+ * invocation, for each scheme.  The given callback function can hence safely
+ * access the internal data of &struct damon_ctx and &struct damon_region that
+ * each of the scheme will apply the action for next interval, without
+ * additional synchronizations against the kdamond.  If every scheme of @ctx
+ * passed at least one &damos->apply_interval_us, kdamond marks the request as
+ * completed so that damos_walk() can wakeup and return.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control)
+{
+	init_completion(&control->completion);
+	control->canceled = false;
+	mutex_lock(&ctx->walk_control_lock);
+	if (ctx->walk_control) {
+		mutex_unlock(&ctx->walk_control_lock);
+		return -EBUSY;
+	}
+	ctx->walk_control = control;
+	mutex_unlock(&ctx->walk_control_lock);
+	if (!damon_is_running(ctx))
+		return -EINVAL;
+	wait_for_completion(&control->completion);
+	if (control->canceled)
+		return -ECANCELED;
+	return 0;
+}
+
 /*
  * Reset the aggregated monitoring results ('nr_accesses' of each region).
  */
@@ -1272,16 +1365,18 @@ static bool damos_skip_charged_region(struct damon_target *t,
 }
 
 static void damos_update_stat(struct damos *s,
-		unsigned long sz_tried, unsigned long sz_applied)
+		unsigned long sz_tried, unsigned long sz_applied,
+		unsigned long sz_ops_filter_passed)
 {
 	s->stat.nr_tried++;
 	s->stat.sz_tried += sz_tried;
 	if (sz_applied)
 		s->stat.nr_applied++;
 	s->stat.sz_applied += sz_applied;
+	s->stat.sz_ops_filter_passed += sz_ops_filter_passed;
 }
 
-static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
+static bool damos_filter_match(struct damon_ctx *ctx, struct damon_target *t,
 		struct damon_region *r, struct damos_filter *filter)
 {
 	bool matched = false;
@@ -1335,12 +1430,98 @@ static bool damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
 	struct damos_filter *filter;
 
 	damos_for_each_filter(filter, s) {
-		if (__damos_filter_out(ctx, t, r, filter))
-			return true;
+		if (damos_filter_match(ctx, t, r, filter))
+			return !filter->allow;
 	}
 	return false;
 }
 
+/*
+ * damos_walk_call_walk() - Call &damos_walk_control->walk_fn.
+ * @ctx:	The context of &damon_ctx->walk_control.
+ * @t:		The monitoring target of @r that @s will be applied.
+ * @r:		The region of @t that @s will be applied.
+ * @s:		The scheme of @ctx that will be applied to @r.
+ *
+ * This function is called from kdamond whenever it asked the operation set to
+ * apply a DAMOS scheme action to a region.  If a DAMOS walk request is
+ * installed by damos_walk() and not yet uninstalled, invoke it.
+ */
+static void damos_walk_call_walk(struct damon_ctx *ctx, struct damon_target *t,
+		struct damon_region *r, struct damos *s,
+		unsigned long sz_filter_passed)
+{
+	struct damos_walk_control *control;
+
+	mutex_lock(&ctx->walk_control_lock);
+	control = ctx->walk_control;
+	mutex_unlock(&ctx->walk_control_lock);
+	if (!control)
+		return;
+	control->walk_fn(control->data, ctx, t, r, s, sz_filter_passed);
+}
+
+/*
+ * damos_walk_complete() - Complete DAMOS walk request if all walks are done.
+ * @ctx:	The context of &damon_ctx->walk_control.
+ * @s:		A scheme of @ctx that all walks are now done.
+ *
+ * This function is called when kdamond finished applying the action of a DAMOS
+ * scheme to all regions that eligible for the given &damos->apply_interval_us.
+ * If every scheme of @ctx including @s now finished walking for at least one
+ * &damos->apply_interval_us, this function makrs the handling of the given
+ * DAMOS walk request is done, so that damos_walk() can wake up and return.
+ */
+static void damos_walk_complete(struct damon_ctx *ctx, struct damos *s)
+{
+	struct damos *siter;
+	struct damos_walk_control *control;
+
+	mutex_lock(&ctx->walk_control_lock);
+	control = ctx->walk_control;
+	mutex_unlock(&ctx->walk_control_lock);
+	if (!control)
+		return;
+
+	s->walk_completed = true;
+	/* if all schemes completed, signal completion to walker */
+	damon_for_each_scheme(siter, ctx) {
+		if (!siter->walk_completed)
+			return;
+	}
+	complete(&control->completion);
+	mutex_lock(&ctx->walk_control_lock);
+	ctx->walk_control = NULL;
+	mutex_unlock(&ctx->walk_control_lock);
+}
+
+/*
+ * damos_walk_cancel() - Cancel the current DAMOS walk request.
+ * @ctx:	The context of &damon_ctx->walk_control.
+ *
+ * This function is called when @ctx is deactivated by DAMOS watermarks, DAMOS
+ * walk is requested but there is no DAMOS scheme to walk for, or the kdamond
+ * is already out of the main loop and therefore gonna be terminated, and hence
+ * cannot continue the walks.  This function therefore marks the walk request
+ * as canceled, so that damos_walk() can wake up and return.
+ */
+static void damos_walk_cancel(struct damon_ctx *ctx)
+{
+	struct damos_walk_control *control;
+
+	mutex_lock(&ctx->walk_control_lock);
+	control = ctx->walk_control;
+	mutex_unlock(&ctx->walk_control_lock);
+
+	if (!control)
+		return;
+	control->canceled = true;
+	complete(&control->completion);
+	mutex_lock(&ctx->walk_control_lock);
+	ctx->walk_control = NULL;
+	mutex_unlock(&ctx->walk_control_lock);
+}
+
 static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
 		struct damon_region *r, struct damos *s)
 {
@@ -1348,6 +1529,7 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
 	unsigned long sz = damon_sz_region(r);
 	struct timespec64 begin, end;
 	unsigned long sz_applied = 0;
+	unsigned long sz_ops_filter_passed = 0;
 	int err = 0;
 	/*
 	 * We plan to support multiple context per kdamond, as DAMON sysfs
@@ -1393,8 +1575,10 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
 		if (!err) {
 			trace_damos_before_apply(cidx, sidx, tidx, r,
 					damon_nr_regions(t), do_trace);
-			sz_applied = c->ops.apply_scheme(c, t, r, s);
+			sz_applied = c->ops.apply_scheme(c, t, r, s,
+					&sz_ops_filter_passed);
 		}
+		damos_walk_call_walk(c, t, r, s, sz_ops_filter_passed);
 		ktime_get_coarse_ts64(&end);
 		quota->total_charged_ns += timespec64_to_ns(&end) -
 			timespec64_to_ns(&begin);
@@ -1408,7 +1592,7 @@ static void damos_apply_scheme(struct damon_ctx *c, struct damon_target *t,
 		r->age = 0;
 
 update_stat:
-	damos_update_stat(s, sz, sz_applied);
+	damos_update_stat(s, sz, sz_applied, sz_ops_filter_passed);
 }
 
 static void damon_do_apply_schemes(struct damon_ctx *c,
@@ -1550,7 +1734,7 @@ static unsigned long damos_quota_score(struct damos_quota *quota)
 static void damos_set_effective_quota(struct damos_quota *quota)
 {
 	unsigned long throughput;
-	unsigned long esz;
+	unsigned long esz = ULONG_MAX;
 
 	if (!quota->ms && list_empty(&quota->goals)) {
 		quota->esz = quota->sz;
@@ -1572,10 +1756,7 @@ static void damos_set_effective_quota(struct damos_quota *quota)
 				quota->total_charged_ns;
 		else
 			throughput = PAGE_SIZE * 1024;
-		if (!list_empty(&quota->goals))
-			esz = min(throughput * quota->ms, esz);
-		else
-			esz = throughput * quota->ms;
+		esz = min(throughput * quota->ms, esz);
 	}
 
 	if (quota->sz && quota->sz < esz)
@@ -1666,6 +1847,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 	damon_for_each_scheme(s, c) {
 		if (c->passed_sample_intervals < s->next_apply_sis)
 			continue;
+		damos_walk_complete(c, s);
 		s->next_apply_sis = c->passed_sample_intervals +
 			(s->apply_interval_us ? s->apply_interval_us :
 			 c->attrs.aggr_interval) / sample_interval;
@@ -1894,9 +2076,8 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme)
 	if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) {
 		if (scheme->wmarks.activated)
 			pr_debug("deactivate a scheme (%d) for %s wmark\n",
-					scheme->action,
-					metric > scheme->wmarks.high ?
-					"high" : "low");
+				 scheme->action,
+				 str_high_low(metric > scheme->wmarks.high));
 		scheme->wmarks.activated = false;
 		return scheme->wmarks.interval;
 	}
@@ -1920,6 +2101,39 @@ static void kdamond_usleep(unsigned long usecs)
 		usleep_range_idle(usecs, usecs + 1);
 }
 
+/*
+ * kdamond_call() - handle damon_call_control.
+ * @ctx:	The &struct damon_ctx of the kdamond.
+ * @cancel:	Whether to cancel the invocation of the function.
+ *
+ * If there is a &struct damon_call_control request that registered via
+ * &damon_call() on @ctx, do or cancel the invocation of the function depending
+ * on @cancel.  @cancel is set when the kdamond is deactivated by DAMOS
+ * watermarks, or the kdamond is already out of the main loop and therefore
+ * will be terminated.
+ */
+static void kdamond_call(struct damon_ctx *ctx, bool cancel)
+{
+	struct damon_call_control *control;
+	int ret = 0;
+
+	mutex_lock(&ctx->call_control_lock);
+	control = ctx->call_control;
+	mutex_unlock(&ctx->call_control_lock);
+	if (!control)
+		return;
+	if (cancel) {
+		control->canceled = true;
+	} else {
+		ret = control->fn(control->data);
+		control->return_code = ret;
+	}
+	complete(&control->completion);
+	mutex_lock(&ctx->call_control_lock);
+	ctx->call_control = NULL;
+	mutex_unlock(&ctx->call_control_lock);
+}
+
 /* Returns negative error code if it's not activated but should return */
 static int kdamond_wait_activation(struct damon_ctx *ctx)
 {
@@ -1944,6 +2158,8 @@ static int kdamond_wait_activation(struct damon_ctx *ctx)
 		if (ctx->callback.after_wmarks_check &&
 				ctx->callback.after_wmarks_check(ctx))
 			break;
+		kdamond_call(ctx, true);
+		damos_walk_cancel(ctx);
 	}
 	return -EBUSY;
 }
@@ -2014,6 +2230,7 @@ static int kdamond_fn(void *data)
 		if (ctx->callback.after_sampling &&
 				ctx->callback.after_sampling(ctx))
 			break;
+		kdamond_call(ctx, false);
 
 		kdamond_usleep(sample_interval);
 		ctx->passed_sample_intervals++;
@@ -2036,6 +2253,8 @@ static int kdamond_fn(void *data)
 		 */
 		if (!list_empty(&ctx->schemes))
 			kdamond_apply_schemes(ctx);
+		else
+			damos_walk_cancel(ctx);
 
 		sample_interval = ctx->attrs.sample_interval ?
 			ctx->attrs.sample_interval : 1;
@@ -2075,6 +2294,9 @@ done:
 	ctx->kdamond = NULL;
 	mutex_unlock(&ctx->kdamond_lock);
 
+	kdamond_call(ctx, true);
+	damos_walk_cancel(ctx);
+
 	mutex_lock(&damon_lock);
 	nr_running_ctxs--;
 	if (!nr_running_ctxs && running_exclusive_ctxs)
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
deleted file mode 100644
index b4213bc47e44..000000000000
--- a/mm/damon/dbgfs.c
+++ /dev/null
@@ -1,1148 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * DAMON Debugfs Interface
- *
- * Author: SeongJae Park <sj@kernel.org>
- */
-
-#define pr_fmt(fmt) "damon-dbgfs: " fmt
-
-#include <linux/damon.h>
-#include <linux/debugfs.h>
-#include <linux/file.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/page_idle.h>
-#include <linux/slab.h>
-
-#define DAMON_DBGFS_DEPRECATION_NOTICE					\
-	"DAMON debugfs interface is deprecated, so users should move "	\
-	"to DAMON_SYSFS. If you cannot, please report your usecase to "	\
-	"damon@lists.linux.dev and linux-mm@kvack.org.\n"
-
-static struct damon_ctx **dbgfs_ctxs;
-static int dbgfs_nr_ctxs;
-static struct dentry **dbgfs_dirs;
-static DEFINE_MUTEX(damon_dbgfs_lock);
-
-static void damon_dbgfs_warn_deprecation(void)
-{
-	pr_warn_once(DAMON_DBGFS_DEPRECATION_NOTICE);
-}
-
-/*
- * Returns non-empty string on success, negative error code otherwise.
- */
-static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos)
-{
-	char *kbuf;
-	ssize_t ret;
-
-	/* We do not accept continuous write */
-	if (*ppos)
-		return ERR_PTR(-EINVAL);
-
-	kbuf = kmalloc(count + 1, GFP_KERNEL | __GFP_NOWARN);
-	if (!kbuf)
-		return ERR_PTR(-ENOMEM);
-
-	ret = simple_write_to_buffer(kbuf, count + 1, ppos, buf, count);
-	if (ret != count) {
-		kfree(kbuf);
-		return ERR_PTR(-EIO);
-	}
-	kbuf[ret] = '\0';
-
-	return kbuf;
-}
-
-static ssize_t dbgfs_attrs_read(struct file *file,
-		char __user *buf, size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	char kbuf[128];
-	int ret;
-
-	mutex_lock(&ctx->kdamond_lock);
-	ret = scnprintf(kbuf, ARRAY_SIZE(kbuf), "%lu %lu %lu %lu %lu\n",
-			ctx->attrs.sample_interval, ctx->attrs.aggr_interval,
-			ctx->attrs.ops_update_interval,
-			ctx->attrs.min_nr_regions, ctx->attrs.max_nr_regions);
-	mutex_unlock(&ctx->kdamond_lock);
-
-	return simple_read_from_buffer(buf, count, ppos, kbuf, ret);
-}
-
-static ssize_t dbgfs_attrs_write(struct file *file,
-		const char __user *buf, size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	struct damon_attrs attrs;
-	char *kbuf;
-	ssize_t ret;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-
-	if (sscanf(kbuf, "%lu %lu %lu %lu %lu",
-				&attrs.sample_interval, &attrs.aggr_interval,
-				&attrs.ops_update_interval,
-				&attrs.min_nr_regions,
-				&attrs.max_nr_regions) != 5) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	mutex_lock(&ctx->kdamond_lock);
-	if (ctx->kdamond) {
-		ret = -EBUSY;
-		goto unlock_out;
-	}
-
-	ret = damon_set_attrs(ctx, &attrs);
-	if (!ret)
-		ret = count;
-unlock_out:
-	mutex_unlock(&ctx->kdamond_lock);
-out:
-	kfree(kbuf);
-	return ret;
-}
-
-/*
- * Return corresponding dbgfs' scheme action value (int) for the given
- * damos_action if the given damos_action value is valid and supported by
- * dbgfs, negative error code otherwise.
- */
-static int damos_action_to_dbgfs_scheme_action(enum damos_action action)
-{
-	switch (action) {
-	case DAMOS_WILLNEED:
-		return 0;
-	case DAMOS_COLD:
-		return 1;
-	case DAMOS_PAGEOUT:
-		return 2;
-	case DAMOS_HUGEPAGE:
-		return 3;
-	case DAMOS_NOHUGEPAGE:
-		return 4;
-	case DAMOS_STAT:
-		return 5;
-	default:
-		return -EINVAL;
-	}
-}
-
-static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len)
-{
-	struct damos *s;
-	int written = 0;
-	int rc;
-
-	damon_for_each_scheme(s, c) {
-		rc = scnprintf(&buf[written], len - written,
-				"%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %d %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
-				s->pattern.min_sz_region,
-				s->pattern.max_sz_region,
-				s->pattern.min_nr_accesses,
-				s->pattern.max_nr_accesses,
-				s->pattern.min_age_region,
-				s->pattern.max_age_region,
-				damos_action_to_dbgfs_scheme_action(s->action),
-				s->quota.ms, s->quota.sz,
-				s->quota.reset_interval,
-				s->quota.weight_sz,
-				s->quota.weight_nr_accesses,
-				s->quota.weight_age,
-				s->wmarks.metric, s->wmarks.interval,
-				s->wmarks.high, s->wmarks.mid, s->wmarks.low,
-				s->stat.nr_tried, s->stat.sz_tried,
-				s->stat.nr_applied, s->stat.sz_applied,
-				s->stat.qt_exceeds);
-		if (!rc)
-			return -ENOMEM;
-
-		written += rc;
-	}
-	return written;
-}
-
-static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf,
-		size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	char *kbuf;
-	ssize_t len;
-
-	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
-	if (!kbuf)
-		return -ENOMEM;
-
-	mutex_lock(&ctx->kdamond_lock);
-	len = sprint_schemes(ctx, kbuf, count);
-	mutex_unlock(&ctx->kdamond_lock);
-	if (len < 0)
-		goto out;
-	len = simple_read_from_buffer(buf, count, ppos, kbuf, len);
-
-out:
-	kfree(kbuf);
-	return len;
-}
-
-static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes)
-{
-	ssize_t i;
-
-	for (i = 0; i < nr_schemes; i++)
-		kfree(schemes[i]);
-	kfree(schemes);
-}
-
-/*
- * Return corresponding damos_action for the given dbgfs input for a scheme
- * action if the input is valid, negative error code otherwise.
- */
-static enum damos_action dbgfs_scheme_action_to_damos_action(int dbgfs_action)
-{
-	switch (dbgfs_action) {
-	case 0:
-		return DAMOS_WILLNEED;
-	case 1:
-		return DAMOS_COLD;
-	case 2:
-		return DAMOS_PAGEOUT;
-	case 3:
-		return DAMOS_HUGEPAGE;
-	case 4:
-		return DAMOS_NOHUGEPAGE;
-	case 5:
-		return DAMOS_STAT;
-	default:
-		return -EINVAL;
-	}
-}
-
-/*
- * Converts a string into an array of struct damos pointers
- *
- * Returns an array of struct damos pointers that converted if the conversion
- * success, or NULL otherwise.
- */
-static struct damos **str_to_schemes(const char *str, ssize_t len,
-				ssize_t *nr_schemes)
-{
-	struct damos *scheme, **schemes;
-	const int max_nr_schemes = 256;
-	int pos = 0, parsed, ret;
-	unsigned int action_input;
-	enum damos_action action;
-
-	schemes = kmalloc_array(max_nr_schemes, sizeof(scheme),
-			GFP_KERNEL);
-	if (!schemes)
-		return NULL;
-
-	*nr_schemes = 0;
-	while (pos < len && *nr_schemes < max_nr_schemes) {
-		struct damos_access_pattern pattern = {};
-		struct damos_quota quota = {};
-		struct damos_watermarks wmarks;
-
-		ret = sscanf(&str[pos],
-				"%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n",
-				&pattern.min_sz_region, &pattern.max_sz_region,
-				&pattern.min_nr_accesses,
-				&pattern.max_nr_accesses,
-				&pattern.min_age_region,
-				&pattern.max_age_region,
-				&action_input, &quota.ms,
-				&quota.sz, &quota.reset_interval,
-				&quota.weight_sz, &quota.weight_nr_accesses,
-				&quota.weight_age, &wmarks.metric,
-				&wmarks.interval, &wmarks.high, &wmarks.mid,
-				&wmarks.low, &parsed);
-		if (ret != 18)
-			break;
-		action = dbgfs_scheme_action_to_damos_action(action_input);
-		if ((int)action < 0)
-			goto fail;
-
-		if (pattern.min_sz_region > pattern.max_sz_region ||
-		    pattern.min_nr_accesses > pattern.max_nr_accesses ||
-		    pattern.min_age_region > pattern.max_age_region)
-			goto fail;
-
-		if (wmarks.high < wmarks.mid || wmarks.high < wmarks.low ||
-		    wmarks.mid <  wmarks.low)
-			goto fail;
-
-		pos += parsed;
-		scheme = damon_new_scheme(&pattern, action, 0, &quota,
-				&wmarks, NUMA_NO_NODE);
-		if (!scheme)
-			goto fail;
-
-		schemes[*nr_schemes] = scheme;
-		*nr_schemes += 1;
-	}
-	return schemes;
-fail:
-	free_schemes_arr(schemes, *nr_schemes);
-	return NULL;
-}
-
-static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf,
-		size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	char *kbuf;
-	struct damos **schemes;
-	ssize_t nr_schemes = 0, ret;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-
-	schemes = str_to_schemes(kbuf, count, &nr_schemes);
-	if (!schemes) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	mutex_lock(&ctx->kdamond_lock);
-	if (ctx->kdamond) {
-		ret = -EBUSY;
-		goto unlock_out;
-	}
-
-	damon_set_schemes(ctx, schemes, nr_schemes);
-	ret = count;
-	nr_schemes = 0;
-
-unlock_out:
-	mutex_unlock(&ctx->kdamond_lock);
-	free_schemes_arr(schemes, nr_schemes);
-out:
-	kfree(kbuf);
-	return ret;
-}
-
-static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len)
-{
-	struct damon_target *t;
-	int id;
-	int written = 0;
-	int rc;
-
-	damon_for_each_target(t, ctx) {
-		if (damon_target_has_pid(ctx))
-			/* Show pid numbers to debugfs users */
-			id = pid_vnr(t->pid);
-		else
-			/* Show 42 for physical address space, just for fun */
-			id = 42;
-
-		rc = scnprintf(&buf[written], len - written, "%d ", id);
-		if (!rc)
-			return -ENOMEM;
-		written += rc;
-	}
-	if (written)
-		written -= 1;
-	written += scnprintf(&buf[written], len - written, "\n");
-	return written;
-}
-
-static ssize_t dbgfs_target_ids_read(struct file *file,
-		char __user *buf, size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	ssize_t len;
-	char ids_buf[320];
-
-	mutex_lock(&ctx->kdamond_lock);
-	len = sprint_target_ids(ctx, ids_buf, 320);
-	mutex_unlock(&ctx->kdamond_lock);
-	if (len < 0)
-		return len;
-
-	return simple_read_from_buffer(buf, count, ppos, ids_buf, len);
-}
-
-/*
- * Converts a string into an integers array
- *
- * Returns an array of integers array if the conversion success, or NULL
- * otherwise.
- */
-static int *str_to_ints(const char *str, ssize_t len, ssize_t *nr_ints)
-{
-	int *array;
-	const int max_nr_ints = 32;
-	int nr;
-	int pos = 0, parsed, ret;
-
-	*nr_ints = 0;
-	array = kmalloc_array(max_nr_ints, sizeof(*array), GFP_KERNEL);
-	if (!array)
-		return NULL;
-	while (*nr_ints < max_nr_ints && pos < len) {
-		ret = sscanf(&str[pos], "%d%n", &nr, &parsed);
-		pos += parsed;
-		if (ret != 1)
-			break;
-		array[*nr_ints] = nr;
-		*nr_ints += 1;
-	}
-
-	return array;
-}
-
-static void dbgfs_put_pids(struct pid **pids, int nr_pids)
-{
-	int i;
-
-	for (i = 0; i < nr_pids; i++)
-		put_pid(pids[i]);
-}
-
-/*
- * Converts a string into an struct pid pointers array
- *
- * Returns an array of struct pid pointers if the conversion success, or NULL
- * otherwise.
- */
-static struct pid **str_to_pids(const char *str, ssize_t len, ssize_t *nr_pids)
-{
-	int *ints;
-	ssize_t nr_ints;
-	struct pid **pids;
-
-	*nr_pids = 0;
-
-	ints = str_to_ints(str, len, &nr_ints);
-	if (!ints)
-		return NULL;
-
-	pids = kmalloc_array(nr_ints, sizeof(*pids), GFP_KERNEL);
-	if (!pids)
-		goto out;
-
-	for (; *nr_pids < nr_ints; (*nr_pids)++) {
-		pids[*nr_pids] = find_get_pid(ints[*nr_pids]);
-		if (!pids[*nr_pids]) {
-			dbgfs_put_pids(pids, *nr_pids);
-			kfree(ints);
-			kfree(pids);
-			return NULL;
-		}
-	}
-
-out:
-	kfree(ints);
-	return pids;
-}
-
-/*
- * dbgfs_set_targets() - Set monitoring targets.
- * @ctx:	monitoring context
- * @nr_targets:	number of targets
- * @pids:	array of target pids (size is same to @nr_targets)
- *
- * This function should not be called while the kdamond is running.  @pids is
- * ignored if the context is not configured to have pid in each target.  On
- * failure, reference counts of all pids in @pids are decremented.
- *
- * Return: 0 on success, negative error code otherwise.
- */
-static int dbgfs_set_targets(struct damon_ctx *ctx, ssize_t nr_targets,
-		struct pid **pids)
-{
-	ssize_t i;
-	struct damon_target *t, *next;
-
-	damon_for_each_target_safe(t, next, ctx) {
-		if (damon_target_has_pid(ctx))
-			put_pid(t->pid);
-		damon_destroy_target(t);
-	}
-
-	for (i = 0; i < nr_targets; i++) {
-		t = damon_new_target();
-		if (!t) {
-			damon_for_each_target_safe(t, next, ctx)
-				damon_destroy_target(t);
-			if (damon_target_has_pid(ctx))
-				dbgfs_put_pids(pids, nr_targets);
-			return -ENOMEM;
-		}
-		if (damon_target_has_pid(ctx))
-			t->pid = pids[i];
-		damon_add_target(ctx, t);
-	}
-
-	return 0;
-}
-
-static ssize_t dbgfs_target_ids_write(struct file *file,
-		const char __user *buf, size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	bool id_is_pid = true;
-	char *kbuf;
-	struct pid **target_pids = NULL;
-	ssize_t nr_targets;
-	ssize_t ret;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-
-	if (!strncmp(kbuf, "paddr\n", count)) {
-		id_is_pid = false;
-		nr_targets = 1;
-	}
-
-	if (id_is_pid) {
-		target_pids = str_to_pids(kbuf, count, &nr_targets);
-		if (!target_pids) {
-			ret = -ENOMEM;
-			goto out;
-		}
-	}
-
-	mutex_lock(&ctx->kdamond_lock);
-	if (ctx->kdamond) {
-		if (id_is_pid)
-			dbgfs_put_pids(target_pids, nr_targets);
-		ret = -EBUSY;
-		goto unlock_out;
-	}
-
-	/* remove previously set targets */
-	dbgfs_set_targets(ctx, 0, NULL);
-	if (!nr_targets) {
-		ret = count;
-		goto unlock_out;
-	}
-
-	/* Configure the context for the address space type */
-	if (id_is_pid)
-		ret = damon_select_ops(ctx, DAMON_OPS_VADDR);
-	else
-		ret = damon_select_ops(ctx, DAMON_OPS_PADDR);
-	if (ret)
-		goto unlock_out;
-
-	ret = dbgfs_set_targets(ctx, nr_targets, target_pids);
-	if (!ret)
-		ret = count;
-
-unlock_out:
-	mutex_unlock(&ctx->kdamond_lock);
-	kfree(target_pids);
-out:
-	kfree(kbuf);
-	return ret;
-}
-
-static ssize_t sprint_init_regions(struct damon_ctx *c, char *buf, ssize_t len)
-{
-	struct damon_target *t;
-	struct damon_region *r;
-	int target_idx = 0;
-	int written = 0;
-	int rc;
-
-	damon_for_each_target(t, c) {
-		damon_for_each_region(r, t) {
-			rc = scnprintf(&buf[written], len - written,
-					"%d %lu %lu\n",
-					target_idx, r->ar.start, r->ar.end);
-			if (!rc)
-				return -ENOMEM;
-			written += rc;
-		}
-		target_idx++;
-	}
-	return written;
-}
-
-static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf,
-		size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	char *kbuf;
-	ssize_t len;
-
-	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
-	if (!kbuf)
-		return -ENOMEM;
-
-	mutex_lock(&ctx->kdamond_lock);
-	if (ctx->kdamond) {
-		mutex_unlock(&ctx->kdamond_lock);
-		len = -EBUSY;
-		goto out;
-	}
-
-	len = sprint_init_regions(ctx, kbuf, count);
-	mutex_unlock(&ctx->kdamond_lock);
-	if (len < 0)
-		goto out;
-	len = simple_read_from_buffer(buf, count, ppos, kbuf, len);
-
-out:
-	kfree(kbuf);
-	return len;
-}
-
-static int add_init_region(struct damon_ctx *c, int target_idx,
-		struct damon_addr_range *ar)
-{
-	struct damon_target *t;
-	struct damon_region *r, *prev;
-	unsigned long idx = 0;
-	int rc = -EINVAL;
-
-	if (ar->start >= ar->end)
-		return -EINVAL;
-
-	damon_for_each_target(t, c) {
-		if (idx++ == target_idx) {
-			r = damon_new_region(ar->start, ar->end);
-			if (!r)
-				return -ENOMEM;
-			damon_add_region(r, t);
-			if (damon_nr_regions(t) > 1) {
-				prev = damon_prev_region(r);
-				if (prev->ar.end > r->ar.start) {
-					damon_destroy_region(r, t);
-					return -EINVAL;
-				}
-			}
-			rc = 0;
-		}
-	}
-	return rc;
-}
-
-static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len)
-{
-	struct damon_target *t;
-	struct damon_region *r, *next;
-	int pos = 0, parsed, ret;
-	int target_idx;
-	struct damon_addr_range ar;
-	int err;
-
-	damon_for_each_target(t, c) {
-		damon_for_each_region_safe(r, next, t)
-			damon_destroy_region(r, t);
-	}
-
-	while (pos < len) {
-		ret = sscanf(&str[pos], "%d %lu %lu%n",
-				&target_idx, &ar.start, &ar.end, &parsed);
-		if (ret != 3)
-			break;
-		err = add_init_region(c, target_idx, &ar);
-		if (err)
-			goto fail;
-		pos += parsed;
-	}
-
-	return 0;
-
-fail:
-	damon_for_each_target(t, c) {
-		damon_for_each_region_safe(r, next, t)
-			damon_destroy_region(r, t);
-	}
-	return err;
-}
-
-static ssize_t dbgfs_init_regions_write(struct file *file,
-					  const char __user *buf, size_t count,
-					  loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	char *kbuf;
-	ssize_t ret = count;
-	int err;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-
-	mutex_lock(&ctx->kdamond_lock);
-	if (ctx->kdamond) {
-		ret = -EBUSY;
-		goto unlock_out;
-	}
-
-	err = set_init_regions(ctx, kbuf, ret);
-	if (err)
-		ret = err;
-
-unlock_out:
-	mutex_unlock(&ctx->kdamond_lock);
-	kfree(kbuf);
-	return ret;
-}
-
-static ssize_t dbgfs_kdamond_pid_read(struct file *file,
-		char __user *buf, size_t count, loff_t *ppos)
-{
-	struct damon_ctx *ctx = file->private_data;
-	char *kbuf;
-	ssize_t len;
-
-	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
-	if (!kbuf)
-		return -ENOMEM;
-
-	mutex_lock(&ctx->kdamond_lock);
-	if (ctx->kdamond)
-		len = scnprintf(kbuf, count, "%d\n", ctx->kdamond->pid);
-	else
-		len = scnprintf(kbuf, count, "none\n");
-	mutex_unlock(&ctx->kdamond_lock);
-	if (!len)
-		goto out;
-	len = simple_read_from_buffer(buf, count, ppos, kbuf, len);
-
-out:
-	kfree(kbuf);
-	return len;
-}
-
-static int damon_dbgfs_open(struct inode *inode, struct file *file)
-{
-	damon_dbgfs_warn_deprecation();
-
-	file->private_data = inode->i_private;
-
-	return nonseekable_open(inode, file);
-}
-
-static const struct file_operations attrs_fops = {
-	.open = damon_dbgfs_open,
-	.read = dbgfs_attrs_read,
-	.write = dbgfs_attrs_write,
-};
-
-static const struct file_operations schemes_fops = {
-	.open = damon_dbgfs_open,
-	.read = dbgfs_schemes_read,
-	.write = dbgfs_schemes_write,
-};
-
-static const struct file_operations target_ids_fops = {
-	.open = damon_dbgfs_open,
-	.read = dbgfs_target_ids_read,
-	.write = dbgfs_target_ids_write,
-};
-
-static const struct file_operations init_regions_fops = {
-	.open = damon_dbgfs_open,
-	.read = dbgfs_init_regions_read,
-	.write = dbgfs_init_regions_write,
-};
-
-static const struct file_operations kdamond_pid_fops = {
-	.open = damon_dbgfs_open,
-	.read = dbgfs_kdamond_pid_read,
-};
-
-static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx)
-{
-	const char * const file_names[] = {"attrs", "schemes", "target_ids",
-		"init_regions", "kdamond_pid"};
-	const struct file_operations *fops[] = {&attrs_fops, &schemes_fops,
-		&target_ids_fops, &init_regions_fops, &kdamond_pid_fops};
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(file_names); i++)
-		debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]);
-}
-
-static void dbgfs_before_terminate(struct damon_ctx *ctx)
-{
-	struct damon_target *t, *next;
-
-	if (!damon_target_has_pid(ctx))
-		return;
-
-	mutex_lock(&ctx->kdamond_lock);
-	damon_for_each_target_safe(t, next, ctx) {
-		put_pid(t->pid);
-		damon_destroy_target(t);
-	}
-	mutex_unlock(&ctx->kdamond_lock);
-}
-
-static struct damon_ctx *dbgfs_new_ctx(void)
-{
-	struct damon_ctx *ctx;
-
-	ctx = damon_new_ctx();
-	if (!ctx)
-		return NULL;
-
-	if (damon_select_ops(ctx, DAMON_OPS_VADDR) &&
-			damon_select_ops(ctx, DAMON_OPS_PADDR)) {
-		damon_destroy_ctx(ctx);
-		return NULL;
-	}
-	ctx->callback.before_terminate = dbgfs_before_terminate;
-	return ctx;
-}
-
-static void dbgfs_destroy_ctx(struct damon_ctx *ctx)
-{
-	damon_destroy_ctx(ctx);
-}
-
-static ssize_t damon_dbgfs_deprecated_read(struct file *file,
-		char __user *buf, size_t count, loff_t *ppos)
-{
-	static const char kbuf[512] = DAMON_DBGFS_DEPRECATION_NOTICE;
-
-	return simple_read_from_buffer(buf, count, ppos, kbuf, strlen(kbuf));
-}
-
-/*
- * Make a context of @name and create a debugfs directory for it.
- *
- * This function should be called while holding damon_dbgfs_lock.
- *
- * Returns 0 on success, negative error code otherwise.
- */
-static int dbgfs_mk_context(char *name)
-{
-	struct dentry *root, **new_dirs, *new_dir;
-	struct damon_ctx **new_ctxs, *new_ctx;
-
-	if (damon_nr_running_ctxs())
-		return -EBUSY;
-
-	new_ctxs = krealloc(dbgfs_ctxs, sizeof(*dbgfs_ctxs) *
-			(dbgfs_nr_ctxs + 1), GFP_KERNEL);
-	if (!new_ctxs)
-		return -ENOMEM;
-	dbgfs_ctxs = new_ctxs;
-
-	new_dirs = krealloc(dbgfs_dirs, sizeof(*dbgfs_dirs) *
-			(dbgfs_nr_ctxs + 1), GFP_KERNEL);
-	if (!new_dirs)
-		return -ENOMEM;
-	dbgfs_dirs = new_dirs;
-
-	root = dbgfs_dirs[0];
-	if (!root)
-		return -ENOENT;
-
-	new_dir = debugfs_create_dir(name, root);
-	/* Below check is required for a potential duplicated name case */
-	if (IS_ERR(new_dir))
-		return PTR_ERR(new_dir);
-	dbgfs_dirs[dbgfs_nr_ctxs] = new_dir;
-
-	new_ctx = dbgfs_new_ctx();
-	if (!new_ctx) {
-		debugfs_remove(new_dir);
-		dbgfs_dirs[dbgfs_nr_ctxs] = NULL;
-		return -ENOMEM;
-	}
-
-	dbgfs_ctxs[dbgfs_nr_ctxs] = new_ctx;
-	dbgfs_fill_ctx_dir(dbgfs_dirs[dbgfs_nr_ctxs],
-			dbgfs_ctxs[dbgfs_nr_ctxs]);
-	dbgfs_nr_ctxs++;
-
-	return 0;
-}
-
-static ssize_t dbgfs_mk_context_write(struct file *file,
-		const char __user *buf, size_t count, loff_t *ppos)
-{
-	char *kbuf;
-	char *ctx_name;
-	ssize_t ret;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-	ctx_name = kmalloc(count + 1, GFP_KERNEL);
-	if (!ctx_name) {
-		kfree(kbuf);
-		return -ENOMEM;
-	}
-
-	/* Trim white space */
-	if (sscanf(kbuf, "%s", ctx_name) != 1) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	mutex_lock(&damon_dbgfs_lock);
-	ret = dbgfs_mk_context(ctx_name);
-	if (!ret)
-		ret = count;
-	mutex_unlock(&damon_dbgfs_lock);
-
-out:
-	kfree(kbuf);
-	kfree(ctx_name);
-	return ret;
-}
-
-/*
- * Remove a context of @name and its debugfs directory.
- *
- * This function should be called while holding damon_dbgfs_lock.
- *
- * Return 0 on success, negative error code otherwise.
- */
-static int dbgfs_rm_context(char *name)
-{
-	struct dentry *root, *dir, **new_dirs;
-	struct inode *inode;
-	struct damon_ctx **new_ctxs;
-	int i, j;
-	int ret = 0;
-
-	if (damon_nr_running_ctxs())
-		return -EBUSY;
-
-	root = dbgfs_dirs[0];
-	if (!root)
-		return -ENOENT;
-
-	dir = debugfs_lookup(name, root);
-	if (!dir)
-		return -ENOENT;
-
-	inode = d_inode(dir);
-	if (!S_ISDIR(inode->i_mode)) {
-		ret = -EINVAL;
-		goto out_dput;
-	}
-
-	new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs),
-			GFP_KERNEL);
-	if (!new_dirs) {
-		ret = -ENOMEM;
-		goto out_dput;
-	}
-
-	new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs),
-			GFP_KERNEL);
-	if (!new_ctxs) {
-		ret = -ENOMEM;
-		goto out_new_dirs;
-	}
-
-	for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) {
-		if (dbgfs_dirs[i] == dir) {
-			debugfs_remove(dbgfs_dirs[i]);
-			dbgfs_destroy_ctx(dbgfs_ctxs[i]);
-			continue;
-		}
-		new_dirs[j] = dbgfs_dirs[i];
-		new_ctxs[j++] = dbgfs_ctxs[i];
-	}
-
-	kfree(dbgfs_dirs);
-	kfree(dbgfs_ctxs);
-
-	dbgfs_dirs = new_dirs;
-	dbgfs_ctxs = new_ctxs;
-	dbgfs_nr_ctxs--;
-
-	goto out_dput;
-
-out_new_dirs:
-	kfree(new_dirs);
-out_dput:
-	dput(dir);
-	return ret;
-}
-
-static ssize_t dbgfs_rm_context_write(struct file *file,
-		const char __user *buf, size_t count, loff_t *ppos)
-{
-	char *kbuf;
-	ssize_t ret;
-	char *ctx_name;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-	ctx_name = kmalloc(count + 1, GFP_KERNEL);
-	if (!ctx_name) {
-		kfree(kbuf);
-		return -ENOMEM;
-	}
-
-	/* Trim white space */
-	if (sscanf(kbuf, "%s", ctx_name) != 1) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	mutex_lock(&damon_dbgfs_lock);
-	ret = dbgfs_rm_context(ctx_name);
-	if (!ret)
-		ret = count;
-	mutex_unlock(&damon_dbgfs_lock);
-
-out:
-	kfree(kbuf);
-	kfree(ctx_name);
-	return ret;
-}
-
-static ssize_t dbgfs_monitor_on_read(struct file *file,
-		char __user *buf, size_t count, loff_t *ppos)
-{
-	char monitor_on_buf[5];
-	bool monitor_on = damon_nr_running_ctxs() != 0;
-	int len;
-
-	len = scnprintf(monitor_on_buf, 5, monitor_on ? "on\n" : "off\n");
-
-	return simple_read_from_buffer(buf, count, ppos, monitor_on_buf, len);
-}
-
-static ssize_t dbgfs_monitor_on_write(struct file *file,
-		const char __user *buf, size_t count, loff_t *ppos)
-{
-	ssize_t ret;
-	char *kbuf;
-
-	kbuf = user_input_str(buf, count, ppos);
-	if (IS_ERR(kbuf))
-		return PTR_ERR(kbuf);
-
-	/* Remove white space */
-	if (sscanf(kbuf, "%s", kbuf) != 1) {
-		kfree(kbuf);
-		return -EINVAL;
-	}
-
-	mutex_lock(&damon_dbgfs_lock);
-	if (!strncmp(kbuf, "on", count)) {
-		int i;
-
-		for (i = 0; i < dbgfs_nr_ctxs; i++) {
-			if (damon_targets_empty(dbgfs_ctxs[i])) {
-				kfree(kbuf);
-				mutex_unlock(&damon_dbgfs_lock);
-				return -EINVAL;
-			}
-		}
-		ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs, true);
-	} else if (!strncmp(kbuf, "off", count)) {
-		ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs);
-	} else {
-		ret = -EINVAL;
-	}
-	mutex_unlock(&damon_dbgfs_lock);
-
-	if (!ret)
-		ret = count;
-	kfree(kbuf);
-	return ret;
-}
-
-static int damon_dbgfs_static_file_open(struct inode *inode, struct file *file)
-{
-	damon_dbgfs_warn_deprecation();
-	return nonseekable_open(inode, file);
-}
-
-static const struct file_operations deprecated_fops = {
-	.read = damon_dbgfs_deprecated_read,
-};
-
-static const struct file_operations mk_contexts_fops = {
-	.open = damon_dbgfs_static_file_open,
-	.write = dbgfs_mk_context_write,
-};
-
-static const struct file_operations rm_contexts_fops = {
-	.open = damon_dbgfs_static_file_open,
-	.write = dbgfs_rm_context_write,
-};
-
-static const struct file_operations monitor_on_fops = {
-	.open = damon_dbgfs_static_file_open,
-	.read = dbgfs_monitor_on_read,
-	.write = dbgfs_monitor_on_write,
-};
-
-static int __init __damon_dbgfs_init(void)
-{
-	struct dentry *dbgfs_root;
-	const char * const file_names[] = {"mk_contexts", "rm_contexts",
-		"monitor_on_DEPRECATED", "DEPRECATED"};
-	const struct file_operations *fops[] = {&mk_contexts_fops,
-		&rm_contexts_fops, &monitor_on_fops, &deprecated_fops};
-	int i;
-
-	dbgfs_root = debugfs_create_dir("damon", NULL);
-
-	for (i = 0; i < ARRAY_SIZE(file_names); i++)
-		debugfs_create_file(file_names[i], 0600, dbgfs_root, NULL,
-				fops[i]);
-	dbgfs_fill_ctx_dir(dbgfs_root, dbgfs_ctxs[0]);
-
-	dbgfs_dirs = kmalloc(sizeof(dbgfs_root), GFP_KERNEL);
-	if (!dbgfs_dirs) {
-		debugfs_remove(dbgfs_root);
-		return -ENOMEM;
-	}
-	dbgfs_dirs[0] = dbgfs_root;
-
-	return 0;
-}
-
-/*
- * Functions for the initialization
- */
-
-static int __init damon_dbgfs_init(void)
-{
-	int rc = -ENOMEM;
-
-	mutex_lock(&damon_dbgfs_lock);
-	dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL);
-	if (!dbgfs_ctxs)
-		goto out;
-	dbgfs_ctxs[0] = dbgfs_new_ctx();
-	if (!dbgfs_ctxs[0]) {
-		kfree(dbgfs_ctxs);
-		goto out;
-	}
-	dbgfs_nr_ctxs = 1;
-
-	rc = __damon_dbgfs_init();
-	if (rc) {
-		kfree(dbgfs_ctxs[0]);
-		kfree(dbgfs_ctxs);
-		pr_err("%s: dbgfs init failed\n", __func__);
-	}
-
-out:
-	mutex_unlock(&damon_dbgfs_lock);
-	return rc;
-}
-
-module_init(damon_dbgfs_init);
-
-#include "tests/dbgfs-kunit.h"
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index a9ff35341d65..0f9ae14f884d 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -198,7 +198,7 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
 	return max_nr_accesses;
 }
 
-static bool __damos_pa_filter_out(struct damos_filter *filter,
+static bool damos_pa_filter_match(struct damos_filter *filter,
 		struct folio *folio)
 {
 	bool matched = false;
@@ -237,13 +237,14 @@ static bool damos_pa_filter_out(struct damos *scheme, struct folio *folio)
 	struct damos_filter *filter;
 
 	damos_for_each_filter(filter, scheme) {
-		if (__damos_pa_filter_out(filter, folio))
-			return true;
+		if (damos_pa_filter_match(filter, folio))
+			return !filter->allow;
 	}
 	return false;
 }
 
-static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
+static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
+		unsigned long *sz_filter_passed)
 {
 	unsigned long addr, applied;
 	LIST_HEAD(folio_list);
@@ -258,7 +259,8 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
 		}
 	}
 	if (install_young_filter) {
-		filter = damos_new_filter(DAMOS_FILTER_TYPE_YOUNG, true);
+		filter = damos_new_filter(
+				DAMOS_FILTER_TYPE_YOUNG, true, false);
 		if (!filter)
 			return 0;
 		damos_add_filter(s, filter);
@@ -272,6 +274,8 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
+		else
+			*sz_filter_passed += folio_size(folio);
 
 		folio_clear_referenced(folio);
 		folio_test_clear_young(folio);
@@ -292,7 +296,8 @@ put_folio:
 }
 
 static inline unsigned long damon_pa_mark_accessed_or_deactivate(
-		struct damon_region *r, struct damos *s, bool mark_accessed)
+		struct damon_region *r, struct damos *s, bool mark_accessed,
+		unsigned long *sz_filter_passed)
 {
 	unsigned long addr, applied = 0;
 
@@ -304,6 +309,8 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
+		else
+			*sz_filter_passed += folio_size(folio);
 
 		if (mark_accessed)
 			folio_mark_accessed(folio);
@@ -317,15 +324,17 @@ put_folio:
 }
 
 static unsigned long damon_pa_mark_accessed(struct damon_region *r,
-	struct damos *s)
+	struct damos *s, unsigned long *sz_filter_passed)
 {
-	return damon_pa_mark_accessed_or_deactivate(r, s, true);
+	return damon_pa_mark_accessed_or_deactivate(r, s, true,
+			sz_filter_passed);
 }
 
 static unsigned long damon_pa_deactivate_pages(struct damon_region *r,
-	struct damos *s)
+	struct damos *s, unsigned long *sz_filter_passed)
 {
-	return damon_pa_mark_accessed_or_deactivate(r, s, false);
+	return damon_pa_mark_accessed_or_deactivate(r, s, false,
+			sz_filter_passed);
 }
 
 static unsigned int __damon_pa_migrate_folio_list(
@@ -449,7 +458,8 @@ static unsigned long damon_pa_migrate_pages(struct list_head *folio_list,
 	return nr_migrated;
 }
 
-static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s)
+static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s,
+		unsigned long *sz_filter_passed)
 {
 	unsigned long addr, applied;
 	LIST_HEAD(folio_list);
@@ -462,6 +472,8 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s)
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
+		else
+			*sz_filter_passed += folio_size(folio);
 
 		if (!folio_isolate_lru(folio))
 			goto put_folio;
@@ -474,23 +486,57 @@ put_folio:
 	return applied * PAGE_SIZE;
 }
 
+static bool damon_pa_scheme_has_filter(struct damos *s)
+{
+	struct damos_filter *f;
+
+	damos_for_each_filter(f, s)
+		return true;
+	return false;
+}
+
+static unsigned long damon_pa_stat(struct damon_region *r, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	unsigned long addr;
+	LIST_HEAD(folio_list);
+
+	if (!damon_pa_scheme_has_filter(s))
+		return 0;
+
+	addr = r->ar.start;
+	while (addr < r->ar.end) {
+		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
+
+		if (!folio) {
+			addr += PAGE_SIZE;
+			continue;
+		}
+
+		if (!damos_pa_filter_out(s, folio))
+			*sz_filter_passed += folio_size(folio);
+		addr += folio_size(folio);
+		folio_put(folio);
+	}
+	return 0;
+}
 
 static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
 		struct damon_target *t, struct damon_region *r,
-		struct damos *scheme)
+		struct damos *scheme, unsigned long *sz_filter_passed)
 {
 	switch (scheme->action) {
 	case DAMOS_PAGEOUT:
-		return damon_pa_pageout(r, scheme);
+		return damon_pa_pageout(r, scheme, sz_filter_passed);
 	case DAMOS_LRU_PRIO:
-		return damon_pa_mark_accessed(r, scheme);
+		return damon_pa_mark_accessed(r, scheme, sz_filter_passed);
 	case DAMOS_LRU_DEPRIO:
-		return damon_pa_deactivate_pages(r, scheme);
+		return damon_pa_deactivate_pages(r, scheme, sz_filter_passed);
 	case DAMOS_MIGRATE_HOT:
 	case DAMOS_MIGRATE_COLD:
-		return damon_pa_migrate(r, scheme);
+		return damon_pa_migrate(r, scheme, sz_filter_passed);
 	case DAMOS_STAT:
-		break;
+		return damon_pa_stat(r, scheme, sz_filter_passed);
 	default:
 		/* DAMOS actions that not yet supported by 'paddr'. */
 		break;
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index 9e0077a9404e..a675150965e0 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -221,7 +221,7 @@ static int damon_reclaim_apply_parameters(void)
 	}
 
 	if (skip_anon) {
-		filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true);
+		filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, false);
 		if (!filter)
 			goto out;
 		damos_add_filter(scheme, filter);
diff --git a/mm/damon/sysfs-common.h b/mm/damon/sysfs-common.h
index 9a18f3c535d3..70d84bdc9f5f 100644
--- a/mm/damon/sysfs-common.h
+++ b/mm/damon/sysfs-common.h
@@ -45,19 +45,13 @@ void damon_sysfs_schemes_update_stats(
 		struct damon_sysfs_schemes *sysfs_schemes,
 		struct damon_ctx *ctx);
 
-int damon_sysfs_schemes_update_regions_start(
-		struct damon_sysfs_schemes *sysfs_schemes,
-		struct damon_ctx *ctx, bool total_bytes_only);
-
-void damos_sysfs_mark_finished_regions_updates(struct damon_ctx *ctx);
-
-bool damos_sysfs_regions_upd_done(void);
-
-int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx);
+void damos_sysfs_populate_region_dir(struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx, struct damon_target *t,
+		struct damon_region *r, struct damos *s,
+		bool total_bytes_only, unsigned long sz_filter_passed);
 
 int damon_sysfs_schemes_clear_regions(
-		struct damon_sysfs_schemes *sysfs_schemes,
-		struct damon_ctx *ctx);
+		struct damon_sysfs_schemes *sysfs_schemes);
 
 int damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes,
 		struct damon_ctx *ctx);
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index b095457380b5..98f93ae9f59e 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -19,6 +19,7 @@ struct damon_sysfs_scheme_region {
 	struct damon_addr_range ar;
 	unsigned int nr_accesses;
 	unsigned int age;
+	unsigned long sz_filter_passed;
 	struct list_head list;
 };
 
@@ -74,6 +75,15 @@ static ssize_t age_show(struct kobject *kobj, struct kobj_attribute *attr,
 	return sysfs_emit(buf, "%u\n", region->age);
 }
 
+static ssize_t sz_filter_passed_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damon_sysfs_scheme_region *region = container_of(kobj,
+			struct damon_sysfs_scheme_region, kobj);
+
+	return sysfs_emit(buf, "%lu\n", region->sz_filter_passed);
+}
+
 static void damon_sysfs_scheme_region_release(struct kobject *kobj)
 {
 	struct damon_sysfs_scheme_region *region = container_of(kobj,
@@ -95,11 +105,15 @@ static struct kobj_attribute damon_sysfs_scheme_region_nr_accesses_attr =
 static struct kobj_attribute damon_sysfs_scheme_region_age_attr =
 		__ATTR_RO_MODE(age, 0400);
 
+static struct kobj_attribute damon_sysfs_scheme_region_sz_filter_passed_attr =
+		__ATTR_RO_MODE(sz_filter_passed, 0400);
+
 static struct attribute *damon_sysfs_scheme_region_attrs[] = {
 	&damon_sysfs_scheme_region_start_attr.attr,
 	&damon_sysfs_scheme_region_end_attr.attr,
 	&damon_sysfs_scheme_region_nr_accesses_attr.attr,
 	&damon_sysfs_scheme_region_age_attr.attr,
+	&damon_sysfs_scheme_region_sz_filter_passed_attr.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(damon_sysfs_scheme_region);
@@ -114,55 +128,11 @@ static const struct kobj_type damon_sysfs_scheme_region_ktype = {
  * scheme regions directory
  */
 
-/*
- * enum damos_sysfs_regions_upd_status - Represent DAMOS tried regions update
- *					 status
- * @DAMOS_TRIED_REGIONS_UPD_IDLE:		Waiting for next request.
- * @DAMOS_TRIED_REGIONS_UPD_STARTED:		Update started.
- * @DAMOS_TRIED_REGIONS_UPD_FINISHED:	Update finished.
- *
- * Each DAMON-based operation scheme (&struct damos) has its own apply
- * interval, and we need to expose the scheme tried regions based on only
- * single snapshot.  For this, we keep the tried regions update status for each
- * scheme.  The status becomes 'idle' at the beginning.
- *
- * Once the tried regions update request is received, the request handling
- * start function (damon_sysfs_scheme_update_regions_start()) sets the status
- * of all schemes as 'idle' again, and register ->before_damos_apply()
- * callback.
- *
- * Then, the first followup ->before_damos_apply() callback
- * (damon_sysfs_before_damos_apply()) sets the status 'started'.  The first
- * ->after_sampling() or ->after_aggregation() callback
- *  (damon_sysfs_cmd_request_callback()) after the call is called only after
- *  the scheme is completely applied to the given snapshot.  Hence the callback
- *  knows the situation by showing 'started' status, and sets the status as
- *  'finished'.  Then, damon_sysfs_before_damos_apply() understands the
- *  situation by showing the 'finished' status and do nothing.
- *
- * If DAMOS is not applied to any region due to any reasons including the
- * access pattern, the watermarks, the quotas, and the filters,
- * ->before_damos_apply() will not be called back.  Until the situation is
- * changed, the update will not be finished.  To avoid this,
- * damon_sysfs_after_sampling() set the status as 'finished' if more than two
- * apply intervals of the scheme is passed while the state is 'idle'.
- *
- *  Finally, the tried regions request handling finisher function
- *  (damon_sysfs_schemes_update_regions_stop()) unregisters the callbacks.
- */
-enum damos_sysfs_regions_upd_status {
-	DAMOS_TRIED_REGIONS_UPD_IDLE,
-	DAMOS_TRIED_REGIONS_UPD_STARTED,
-	DAMOS_TRIED_REGIONS_UPD_FINISHED,
-};
-
 struct damon_sysfs_scheme_regions {
 	struct kobject kobj;
 	struct list_head regions_list;
 	int nr_regions;
 	unsigned long total_bytes;
-	enum damos_sysfs_regions_upd_status upd_status;
-	unsigned long upd_timeout_jiffies;
 };
 
 static struct damon_sysfs_scheme_regions *
@@ -178,7 +148,6 @@ damon_sysfs_scheme_regions_alloc(void)
 	INIT_LIST_HEAD(&regions->regions_list);
 	regions->nr_regions = 0;
 	regions->total_bytes = 0;
-	regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE;
 	return regions;
 }
 
@@ -233,6 +202,7 @@ struct damon_sysfs_stats {
 	unsigned long sz_tried;
 	unsigned long nr_applied;
 	unsigned long sz_applied;
+	unsigned long sz_ops_filter_passed;
 	unsigned long qt_exceeds;
 };
 
@@ -277,6 +247,15 @@ static ssize_t sz_applied_show(struct kobject *kobj,
 	return sysfs_emit(buf, "%lu\n", stats->sz_applied);
 }
 
+static ssize_t sz_ops_filter_passed_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damon_sysfs_stats *stats = container_of(kobj,
+			struct damon_sysfs_stats, kobj);
+
+	return sysfs_emit(buf, "%lu\n", stats->sz_ops_filter_passed);
+}
+
 static ssize_t qt_exceeds_show(struct kobject *kobj,
 		struct kobj_attribute *attr, char *buf)
 {
@@ -303,6 +282,9 @@ static struct kobj_attribute damon_sysfs_stats_nr_applied_attr =
 static struct kobj_attribute damon_sysfs_stats_sz_applied_attr =
 		__ATTR_RO_MODE(sz_applied, 0400);
 
+static struct kobj_attribute damon_sysfs_stats_sz_ops_filter_passed_attr =
+		__ATTR_RO_MODE(sz_ops_filter_passed, 0400);
+
 static struct kobj_attribute damon_sysfs_stats_qt_exceeds_attr =
 		__ATTR_RO_MODE(qt_exceeds, 0400);
 
@@ -311,6 +293,7 @@ static struct attribute *damon_sysfs_stats_attrs[] = {
 	&damon_sysfs_stats_sz_tried_attr.attr,
 	&damon_sysfs_stats_nr_applied_attr.attr,
 	&damon_sysfs_stats_sz_applied_attr.attr,
+	&damon_sysfs_stats_sz_ops_filter_passed_attr.attr,
 	&damon_sysfs_stats_qt_exceeds_attr.attr,
 	NULL,
 };
@@ -330,6 +313,7 @@ struct damon_sysfs_scheme_filter {
 	struct kobject kobj;
 	enum damos_filter_type type;
 	bool matching;
+	bool allow;
 	char *memcg_path;
 	struct damon_addr_range addr_range;
 	int target_idx;
@@ -402,6 +386,30 @@ static ssize_t matching_store(struct kobject *kobj,
 	return count;
 }
 
+static ssize_t allow_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damon_sysfs_scheme_filter *filter = container_of(kobj,
+			struct damon_sysfs_scheme_filter, kobj);
+
+	return sysfs_emit(buf, "%c\n", filter->allow ? 'Y' : 'N');
+}
+
+static ssize_t allow_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	struct damon_sysfs_scheme_filter *filter = container_of(kobj,
+			struct damon_sysfs_scheme_filter, kobj);
+	bool allow;
+	int err = kstrtobool(buf, &allow);
+
+	if (err)
+		return err;
+
+	filter->allow = allow;
+	return count;
+}
+
 static ssize_t memcg_path_show(struct kobject *kobj,
 		struct kobj_attribute *attr, char *buf)
 {
@@ -499,6 +507,9 @@ static struct kobj_attribute damon_sysfs_scheme_filter_type_attr =
 static struct kobj_attribute damon_sysfs_scheme_filter_matching_attr =
 		__ATTR_RW_MODE(matching, 0600);
 
+static struct kobj_attribute damon_sysfs_scheme_filter_allow_attr =
+		__ATTR_RW_MODE(allow, 0600);
+
 static struct kobj_attribute damon_sysfs_scheme_filter_memcg_path_attr =
 		__ATTR_RW_MODE(memcg_path, 0600);
 
@@ -514,6 +525,7 @@ static struct kobj_attribute damon_sysfs_scheme_filter_damon_target_idx_attr =
 static struct attribute *damon_sysfs_scheme_filter_attrs[] = {
 	&damon_sysfs_scheme_filter_type_attr.attr,
 	&damon_sysfs_scheme_filter_matching_attr.attr,
+	&damon_sysfs_scheme_filter_allow_attr.attr,
 	&damon_sysfs_scheme_filter_memcg_path_attr.attr,
 	&damon_sysfs_scheme_filter_addr_start_attr.attr,
 	&damon_sysfs_scheme_filter_addr_end_attr.attr,
@@ -1918,7 +1930,8 @@ static int damon_sysfs_add_scheme_filters(struct damos *scheme,
 			sysfs_filters->filters_arr[i];
 		struct damos_filter *filter =
 			damos_new_filter(sysfs_filter->type,
-					sysfs_filter->matching);
+					sysfs_filter->matching,
+					sysfs_filter->allow);
 		int err;
 
 		if (!filter)
@@ -2122,32 +2135,32 @@ void damon_sysfs_schemes_update_stats(
 		sysfs_stats->sz_tried = scheme->stat.sz_tried;
 		sysfs_stats->nr_applied = scheme->stat.nr_applied;
 		sysfs_stats->sz_applied = scheme->stat.sz_applied;
+		sysfs_stats->sz_ops_filter_passed =
+			scheme->stat.sz_ops_filter_passed;
 		sysfs_stats->qt_exceeds = scheme->stat.qt_exceeds;
 	}
 }
 
-/*
- * damon_sysfs_schemes that need to update its schemes regions dir.  Protected
- * by damon_sysfs_lock
- */
-static struct damon_sysfs_schemes *damon_sysfs_schemes_for_damos_callback;
-static int damon_sysfs_schemes_region_idx;
-static bool damos_regions_upd_total_bytes_only;
-
-/*
- * DAMON callback that called before damos apply.  While this callback is
- * registered, damon_sysfs_lock should be held to ensure the regions
- * directories exist.
+/**
+ * damos_sysfs_populate_region_dir() - Populate a schemes tried region dir.
+ * @sysfs_schemes:	Schemes directory to populate regions directory.
+ * @ctx:		Corresponding DAMON context.
+ * @t:			DAMON target of @r.
+ * @r:			DAMON region to populate the directory for.
+ * @s:			Corresponding scheme.
+ * @total_bytes_only:	Whether the request is for bytes update only.
+ * @sz_filter_passed:	Bytes of @r that passed filters of @s.
+ *
+ * Called from DAMOS walk callback while holding damon_sysfs_lock.
  */
-static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx,
-		struct damon_target *t, struct damon_region *r,
-		struct damos *s)
+void damos_sysfs_populate_region_dir(struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx, struct damon_target *t,
+		struct damon_region *r, struct damos *s, bool total_bytes_only,
+		unsigned long sz_filter_passed)
 {
 	struct damos *scheme;
 	struct damon_sysfs_scheme_regions *sysfs_regions;
 	struct damon_sysfs_scheme_region *region;
-	struct damon_sysfs_schemes *sysfs_schemes =
-		damon_sysfs_schemes_for_damos_callback;
 	int schemes_idx = 0;
 
 	damon_for_each_scheme(scheme, ctx) {
@@ -2158,152 +2171,40 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx,
 
 	/* user could have removed the scheme sysfs dir */
 	if (schemes_idx >= sysfs_schemes->nr)
-		return 0;
+		return;
 
 	sysfs_regions = sysfs_schemes->schemes_arr[schemes_idx]->tried_regions;
-	if (sysfs_regions->upd_status == DAMOS_TRIED_REGIONS_UPD_FINISHED)
-		return 0;
-	if (sysfs_regions->upd_status == DAMOS_TRIED_REGIONS_UPD_IDLE)
-		sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_STARTED;
 	sysfs_regions->total_bytes += r->ar.end - r->ar.start;
-	if (damos_regions_upd_total_bytes_only)
-		return 0;
+	if (total_bytes_only)
+		return;
 
 	region = damon_sysfs_scheme_region_alloc(r);
 	if (!region)
-		return 0;
+		return;
+	region->sz_filter_passed = sz_filter_passed;
 	list_add_tail(&region->list, &sysfs_regions->regions_list);
 	sysfs_regions->nr_regions++;
 	if (kobject_init_and_add(&region->kobj,
 				&damon_sysfs_scheme_region_ktype,
 				&sysfs_regions->kobj, "%d",
-				damon_sysfs_schemes_region_idx++)) {
+				sysfs_regions->nr_regions++)) {
 		kobject_put(&region->kobj);
 	}
-	return 0;
-}
-
-/*
- * DAMON callback that called after each accesses sampling.  While this
- * callback is registered, damon_sysfs_lock should be held to ensure the
- * regions directories exist.
- */
-void damos_sysfs_mark_finished_regions_updates(struct damon_ctx *ctx)
-{
-	struct damon_sysfs_schemes *sysfs_schemes =
-		damon_sysfs_schemes_for_damos_callback;
-	struct damon_sysfs_scheme_regions *sysfs_regions;
-	int i;
-
-	for (i = 0; i < sysfs_schemes->nr; i++) {
-		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
-		if (sysfs_regions->upd_status ==
-				DAMOS_TRIED_REGIONS_UPD_STARTED ||
-				time_after(jiffies,
-					sysfs_regions->upd_timeout_jiffies))
-			sysfs_regions->upd_status =
-				DAMOS_TRIED_REGIONS_UPD_FINISHED;
-	}
 }
 
 /* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */
 int damon_sysfs_schemes_clear_regions(
-		struct damon_sysfs_schemes *sysfs_schemes,
-		struct damon_ctx *ctx)
+		struct damon_sysfs_schemes *sysfs_schemes)
 {
-	struct damos *scheme;
-	int schemes_idx = 0;
+	int i;
 
-	damon_for_each_scheme(scheme, ctx) {
+	for (i = 0; i < sysfs_schemes->nr; i++) {
 		struct damon_sysfs_scheme *sysfs_scheme;
 
-		/* user could have removed the scheme sysfs dir */
-		if (schemes_idx >= sysfs_schemes->nr)
-			break;
-
-		sysfs_scheme = sysfs_schemes->schemes_arr[schemes_idx++];
+		sysfs_scheme = sysfs_schemes->schemes_arr[i];
 		damon_sysfs_scheme_regions_rm_dirs(
 				sysfs_scheme->tried_regions);
 		sysfs_scheme->tried_regions->total_bytes = 0;
 	}
 	return 0;
 }
-
-static struct damos *damos_sysfs_nth_scheme(int n, struct damon_ctx *ctx)
-{
-	struct damos *scheme;
-	int i = 0;
-
-	damon_for_each_scheme(scheme, ctx) {
-		if (i == n)
-			return scheme;
-		i++;
-	}
-	return NULL;
-}
-
-static void damos_tried_regions_init_upd_status(
-		struct damon_sysfs_schemes *sysfs_schemes,
-		struct damon_ctx *ctx)
-{
-	int i;
-	struct damos *scheme;
-	struct damon_sysfs_scheme_regions *sysfs_regions;
-
-	for (i = 0; i < sysfs_schemes->nr; i++) {
-		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
-		scheme = damos_sysfs_nth_scheme(i, ctx);
-		if (!scheme) {
-			sysfs_regions->upd_status =
-				DAMOS_TRIED_REGIONS_UPD_FINISHED;
-			continue;
-		}
-		sysfs_regions->upd_status = DAMOS_TRIED_REGIONS_UPD_IDLE;
-		sysfs_regions->upd_timeout_jiffies = jiffies +
-			2 * usecs_to_jiffies(scheme->apply_interval_us ?
-					scheme->apply_interval_us :
-					ctx->attrs.aggr_interval);
-	}
-}
-
-/* Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock */
-int damon_sysfs_schemes_update_regions_start(
-		struct damon_sysfs_schemes *sysfs_schemes,
-		struct damon_ctx *ctx, bool total_bytes_only)
-{
-	damon_sysfs_schemes_clear_regions(sysfs_schemes, ctx);
-	damon_sysfs_schemes_for_damos_callback = sysfs_schemes;
-	damos_tried_regions_init_upd_status(sysfs_schemes, ctx);
-	damos_regions_upd_total_bytes_only = total_bytes_only;
-	ctx->callback.before_damos_apply = damon_sysfs_before_damos_apply;
-	return 0;
-}
-
-bool damos_sysfs_regions_upd_done(void)
-{
-	struct damon_sysfs_schemes *sysfs_schemes =
-		damon_sysfs_schemes_for_damos_callback;
-	struct damon_sysfs_scheme_regions *sysfs_regions;
-	int i;
-
-	for (i = 0; i < sysfs_schemes->nr; i++) {
-		sysfs_regions = sysfs_schemes->schemes_arr[i]->tried_regions;
-		if (sysfs_regions->upd_status !=
-				DAMOS_TRIED_REGIONS_UPD_FINISHED)
-			return false;
-	}
-	return true;
-}
-
-/*
- * Called from damon_sysfs_cmd_request_callback under damon_sysfs_lock.  Caller
- * should unlock damon_sysfs_lock which held before
- * damon_sysfs_schemes_update_regions_start()
- */
-int damon_sysfs_schemes_update_regions_stop(struct damon_ctx *ctx)
-{
-	damon_sysfs_schemes_for_damos_callback = NULL;
-	ctx->callback.before_damos_apply = NULL;
-	damon_sysfs_schemes_region_idx = 0;
-	return 0;
-}
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 58145d59881d..deeab04d3b46 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1181,25 +1181,9 @@ static int damon_sysfs_add_targets(struct damon_ctx *ctx,
 	return 0;
 }
 
-static bool damon_sysfs_schemes_regions_updating;
-
 static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
 {
 	struct damon_target *t, *next;
-	struct damon_sysfs_kdamond *kdamond;
-	enum damon_sysfs_cmd cmd;
-
-	/* damon_sysfs_schemes_update_regions_stop() might not yet called */
-	kdamond = damon_sysfs_cmd_request.kdamond;
-	cmd = damon_sysfs_cmd_request.cmd;
-	if (kdamond && ctx == kdamond->damon_ctx &&
-			(cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS ||
-			 cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES) &&
-			damon_sysfs_schemes_regions_updating) {
-		damon_sysfs_schemes_update_regions_stop(ctx);
-		damon_sysfs_schemes_regions_updating = false;
-		mutex_unlock(&damon_sysfs_lock);
-	}
 
 	if (!damon_target_has_pid(ctx))
 		return;
@@ -1214,57 +1198,24 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
 
 /*
  * damon_sysfs_upd_schemes_stats() - Update schemes stats sysfs files.
- * @kdamond:	The kobject wrapper that associated to the kdamond thread.
+ * @data:	The kobject wrapper that associated to the kdamond thread.
  *
  * This function reads the schemes stats of specific kdamond and update the
  * related values for sysfs files.  This function should be called from DAMON
- * callbacks while holding ``damon_syfs_lock``, to safely access the DAMON
- * contexts-internal data and DAMON sysfs variables.
+ * worker thread,to safely access the DAMON contexts-internal data.  Caller
+ * should also ensure holding ``damon_syfs_lock``, and ->damon_ctx of @data is
+ * not NULL but a valid pointer, to safely access DAMON sysfs variables.
  */
-static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond)
+static int damon_sysfs_upd_schemes_stats(void *data)
 {
+	struct damon_sysfs_kdamond *kdamond = data;
 	struct damon_ctx *ctx = kdamond->damon_ctx;
 
-	if (!ctx)
-		return -EINVAL;
 	damon_sysfs_schemes_update_stats(
 			kdamond->contexts->contexts_arr[0]->schemes, ctx);
 	return 0;
 }
 
-static int damon_sysfs_upd_schemes_regions_start(
-		struct damon_sysfs_kdamond *kdamond, bool total_bytes_only)
-{
-	struct damon_ctx *ctx = kdamond->damon_ctx;
-
-	if (!ctx)
-		return -EINVAL;
-	return damon_sysfs_schemes_update_regions_start(
-			kdamond->contexts->contexts_arr[0]->schemes, ctx,
-			total_bytes_only);
-}
-
-static int damon_sysfs_upd_schemes_regions_stop(
-		struct damon_sysfs_kdamond *kdamond)
-{
-	struct damon_ctx *ctx = kdamond->damon_ctx;
-
-	if (!ctx)
-		return -EINVAL;
-	return damon_sysfs_schemes_update_regions_stop(ctx);
-}
-
-static int damon_sysfs_clear_schemes_regions(
-		struct damon_sysfs_kdamond *kdamond)
-{
-	struct damon_ctx *ctx = kdamond->damon_ctx;
-
-	if (!ctx)
-		return -EINVAL;
-	return damon_sysfs_schemes_clear_regions(
-			kdamond->contexts->contexts_arr[0]->schemes, ctx);
-}
-
 static inline bool damon_sysfs_kdamond_running(
 		struct damon_sysfs_kdamond *kdamond)
 {
@@ -1318,9 +1269,9 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond)
 	return err;
 }
 
-static int damon_sysfs_commit_schemes_quota_goals(
-		struct damon_sysfs_kdamond *sysfs_kdamond)
+static int damon_sysfs_commit_schemes_quota_goals(void *data)
 {
+	struct damon_sysfs_kdamond *sysfs_kdamond = data;
 	struct damon_ctx *ctx;
 	struct damon_sysfs_context *sysfs_ctx;
 
@@ -1338,20 +1289,18 @@ static int damon_sysfs_commit_schemes_quota_goals(
 /*
  * damon_sysfs_upd_schemes_effective_quotas() - Update schemes effective quotas
  * sysfs files.
- * @kdamond:	The kobject wrapper that associated to the kdamond thread.
+ * @data:	The kobject wrapper that associated to the kdamond thread.
  *
  * This function reads the schemes' effective quotas of specific kdamond and
  * update the related values for sysfs files.  This function should be called
  * from DAMON callbacks while holding ``damon_syfs_lock``, to safely access the
  * DAMON contexts-internal data and DAMON sysfs variables.
  */
-static int damon_sysfs_upd_schemes_effective_quotas(
-		struct damon_sysfs_kdamond *kdamond)
+static int damon_sysfs_upd_schemes_effective_quotas(void *data)
 {
+	struct damon_sysfs_kdamond *kdamond = data;
 	struct damon_ctx *ctx = kdamond->damon_ctx;
 
-	if (!ctx)
-		return -EINVAL;
 	damos_sysfs_update_effective_quotas(
 			kdamond->contexts->contexts_arr[0]->schemes, ctx);
 	return 0;
@@ -1371,67 +1320,27 @@ static int damon_sysfs_cmd_request_callback(struct damon_ctx *c, bool active,
 		bool after_aggregation)
 {
 	struct damon_sysfs_kdamond *kdamond;
-	bool total_bytes_only = false;
 	int err = 0;
 
 	/* avoid deadlock due to concurrent state_store('off') */
-	if (!damon_sysfs_schemes_regions_updating &&
-			!mutex_trylock(&damon_sysfs_lock))
+	if (!mutex_trylock(&damon_sysfs_lock))
 		return 0;
 	kdamond = damon_sysfs_cmd_request.kdamond;
 	if (!kdamond || kdamond->damon_ctx != c)
 		goto out;
 	switch (damon_sysfs_cmd_request.cmd) {
-	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS:
-		err = damon_sysfs_upd_schemes_stats(kdamond);
-		break;
 	case DAMON_SYSFS_CMD_COMMIT:
 		if (!after_aggregation)
 			goto out;
 		err = damon_sysfs_commit_input(kdamond);
 		break;
-	case DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS:
-		err = damon_sysfs_commit_schemes_quota_goals(kdamond);
-		break;
-	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES:
-		total_bytes_only = true;
-		fallthrough;
-	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS:
-		if (!damon_sysfs_schemes_regions_updating) {
-			err = damon_sysfs_upd_schemes_regions_start(kdamond,
-					total_bytes_only);
-			if (!err) {
-				damon_sysfs_schemes_regions_updating = true;
-				goto keep_lock_out;
-			}
-		} else {
-			damos_sysfs_mark_finished_regions_updates(c);
-			/*
-			 * Continue regions updating if DAMON is till
-			 * active and the update for all schemes is not
-			 * finished.
-			 */
-			if (active && !damos_sysfs_regions_upd_done())
-				goto keep_lock_out;
-			err = damon_sysfs_upd_schemes_regions_stop(kdamond);
-			damon_sysfs_schemes_regions_updating = false;
-		}
-		break;
-	case DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS:
-		err = damon_sysfs_clear_schemes_regions(kdamond);
-		break;
-	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_EFFECTIVE_QUOTAS:
-		err = damon_sysfs_upd_schemes_effective_quotas(kdamond);
-		break;
 	default:
 		break;
 	}
 	/* Mark the request as invalid now. */
 	damon_sysfs_cmd_request.kdamond = NULL;
 out:
-	if (!damon_sysfs_schemes_regions_updating)
-		mutex_unlock(&damon_sysfs_lock);
-keep_lock_out:
+	mutex_unlock(&damon_sysfs_lock);
 	return err;
 }
 
@@ -1525,6 +1434,58 @@ static int damon_sysfs_turn_damon_off(struct damon_sysfs_kdamond *kdamond)
 	 */
 }
 
+static int damon_sysfs_damon_call(int (*fn)(void *data),
+		struct damon_sysfs_kdamond *kdamond)
+{
+	struct damon_call_control call_control = {};
+
+	if (!kdamond->damon_ctx)
+		return -EINVAL;
+	call_control.fn = fn;
+	call_control.data = kdamond;
+	return damon_call(kdamond->damon_ctx, &call_control);
+}
+
+struct damon_sysfs_schemes_walk_data {
+	struct damon_sysfs_kdamond *sysfs_kdamond;
+	bool total_bytes_only;
+};
+
+/* populate the region directory */
+static void damon_sysfs_schemes_tried_regions_upd_one(void *data, struct damon_ctx *ctx,
+		struct damon_target *t, struct damon_region *r,
+		struct damos *s, unsigned long sz_filter_passed)
+{
+	struct damon_sysfs_schemes_walk_data *walk_data = data;
+	struct damon_sysfs_kdamond *sysfs_kdamond = walk_data->sysfs_kdamond;
+
+	damos_sysfs_populate_region_dir(
+			sysfs_kdamond->contexts->contexts_arr[0]->schemes,
+			ctx, t, r, s, walk_data->total_bytes_only,
+			sz_filter_passed);
+}
+
+static int damon_sysfs_update_schemes_tried_regions(
+		struct damon_sysfs_kdamond *sysfs_kdamond, bool total_bytes_only)
+{
+	struct damon_sysfs_schemes_walk_data walk_data = {
+		.sysfs_kdamond = sysfs_kdamond,
+		.total_bytes_only = total_bytes_only,
+	};
+	struct damos_walk_control control = {
+		.walk_fn = damon_sysfs_schemes_tried_regions_upd_one,
+		.data = &walk_data,
+	};
+	struct damon_ctx *ctx = sysfs_kdamond->damon_ctx;
+
+	if (!ctx)
+		return -EINVAL;
+
+	damon_sysfs_schemes_clear_regions(
+			sysfs_kdamond->contexts->contexts_arr[0]->schemes);
+	return damos_walk(ctx, &control);
+}
+
 /*
  * damon_sysfs_handle_cmd() - Handle a command for a specific kdamond.
  * @cmd:	The command to handle.
@@ -1543,12 +1504,29 @@ static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd,
 {
 	bool need_wait = true;
 
-	/* Handle commands that doesn't access DAMON context-internal data */
 	switch (cmd) {
 	case DAMON_SYSFS_CMD_ON:
 		return damon_sysfs_turn_damon_on(kdamond);
 	case DAMON_SYSFS_CMD_OFF:
 		return damon_sysfs_turn_damon_off(kdamond);
+	case DAMON_SYSFS_CMD_COMMIT_SCHEMES_QUOTA_GOALS:
+		return damon_sysfs_damon_call(
+				damon_sysfs_commit_schemes_quota_goals,
+				kdamond);
+	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS:
+		return damon_sysfs_damon_call(
+				damon_sysfs_upd_schemes_stats, kdamond);
+	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES:
+		return damon_sysfs_update_schemes_tried_regions(kdamond, true);
+	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS:
+		return damon_sysfs_update_schemes_tried_regions(kdamond, false);
+	case DAMON_SYSFS_CMD_CLEAR_SCHEMES_TRIED_REGIONS:
+		return damon_sysfs_schemes_clear_regions(
+			kdamond->contexts->contexts_arr[0]->schemes);
+	case DAMON_SYSFS_CMD_UPDATE_SCHEMES_EFFECTIVE_QUOTAS:
+		return damon_sysfs_damon_call(
+				damon_sysfs_upd_schemes_effective_quotas,
+				kdamond);
 	default:
 		break;
 	}
diff --git a/mm/damon/tests/.kunitconfig b/mm/damon/tests/.kunitconfig
index a73be044fc9b..36a450f57b58 100644
--- a/mm/damon/tests/.kunitconfig
+++ b/mm/damon/tests/.kunitconfig
@@ -13,10 +13,3 @@ CONFIG_DAMON_VADDR_KUNIT_TEST=y
 CONFIG_SYSFS=y
 CONFIG_DAMON_SYSFS=y
 CONFIG_DAMON_SYSFS_KUNIT_TEST=y
-
-# for DAMON debugfs interface
-CONFIG_DEBUG_FS=y
-CONFIG_DAMON_PADDR=y
-CONFIG_DAMON_DBGFS_DEPRECATED=y
-CONFIG_DAMON_DBGFS=y
-CONFIG_DAMON_DBGFS_KUNIT_TEST=y
diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h
index cf22e09a3507..532c6a6f21f9 100644
--- a/mm/damon/tests/core-kunit.h
+++ b/mm/damon/tests/core-kunit.h
@@ -411,7 +411,7 @@ static void damos_test_new_filter(struct kunit *test)
 {
 	struct damos_filter *filter;
 
-	filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true);
+	filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, false);
 	KUNIT_EXPECT_EQ(test, filter->type, DAMOS_FILTER_TYPE_ANON);
 	KUNIT_EXPECT_EQ(test, filter->matching, true);
 	KUNIT_EXPECT_PTR_EQ(test, filter->list.prev, &filter->list);
@@ -425,7 +425,7 @@ static void damos_test_filter_out(struct kunit *test)
 	struct damon_region *r, *r2;
 	struct damos_filter *f;
 
-	f = damos_new_filter(DAMOS_FILTER_TYPE_ADDR, true);
+	f = damos_new_filter(DAMOS_FILTER_TYPE_ADDR, true, false);
 	f->addr_range = (struct damon_addr_range){
 		.start = DAMON_MIN_REGION * 2, .end = DAMON_MIN_REGION * 6};
 
@@ -434,25 +434,25 @@ static void damos_test_filter_out(struct kunit *test)
 	damon_add_region(r, t);
 
 	/* region in the range */
-	KUNIT_EXPECT_TRUE(test, __damos_filter_out(NULL, t, r, f));
+	KUNIT_EXPECT_TRUE(test, damos_filter_match(NULL, t, r, f));
 	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1);
 
 	/* region before the range */
 	r->ar.start = DAMON_MIN_REGION * 1;
 	r->ar.end = DAMON_MIN_REGION * 2;
-	KUNIT_EXPECT_FALSE(test, __damos_filter_out(NULL, t, r, f));
+	KUNIT_EXPECT_FALSE(test, damos_filter_match(NULL, t, r, f));
 	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1);
 
 	/* region after the range */
 	r->ar.start = DAMON_MIN_REGION * 6;
 	r->ar.end = DAMON_MIN_REGION * 8;
-	KUNIT_EXPECT_FALSE(test, __damos_filter_out(NULL, t, r, f));
+	KUNIT_EXPECT_FALSE(test, damos_filter_match(NULL, t, r, f));
 	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1);
 
 	/* region started before the range */
 	r->ar.start = DAMON_MIN_REGION * 1;
 	r->ar.end = DAMON_MIN_REGION * 4;
-	KUNIT_EXPECT_FALSE(test, __damos_filter_out(NULL, t, r, f));
+	KUNIT_EXPECT_FALSE(test, damos_filter_match(NULL, t, r, f));
 	/* filter should have split the region */
 	KUNIT_EXPECT_EQ(test, r->ar.start, DAMON_MIN_REGION * 1);
 	KUNIT_EXPECT_EQ(test, r->ar.end, DAMON_MIN_REGION * 2);
@@ -465,7 +465,7 @@ static void damos_test_filter_out(struct kunit *test)
 	/* region started in the range */
 	r->ar.start = DAMON_MIN_REGION * 2;
 	r->ar.end = DAMON_MIN_REGION * 8;
-	KUNIT_EXPECT_TRUE(test, __damos_filter_out(NULL, t, r, f));
+	KUNIT_EXPECT_TRUE(test, damos_filter_match(NULL, t, r, f));
 	/* filter should have split the region */
 	KUNIT_EXPECT_EQ(test, r->ar.start, DAMON_MIN_REGION * 2);
 	KUNIT_EXPECT_EQ(test, r->ar.end, DAMON_MIN_REGION * 6);
diff --git a/mm/damon/tests/dbgfs-kunit.h b/mm/damon/tests/dbgfs-kunit.h
deleted file mode 100644
index 087e53f641a8..000000000000
--- a/mm/damon/tests/dbgfs-kunit.h
+++ /dev/null
@@ -1,173 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * DAMON Debugfs Interface Unit Tests
- *
- * Author: SeongJae Park <sj@kernel.org>
- */
-
-#ifdef CONFIG_DAMON_DBGFS_KUNIT_TEST
-
-#ifndef _DAMON_DBGFS_TEST_H
-#define _DAMON_DBGFS_TEST_H
-
-#include <kunit/test.h>
-
-static void damon_dbgfs_test_str_to_ints(struct kunit *test)
-{
-	char *question;
-	int *answers;
-	int expected[] = {12, 35, 46};
-	ssize_t nr_integers = 0, i;
-
-	question = "123";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers);
-	KUNIT_EXPECT_EQ(test, 123, answers[0]);
-	kfree(answers);
-
-	question = "123abc";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers);
-	KUNIT_EXPECT_EQ(test, 123, answers[0]);
-	kfree(answers);
-
-	question = "a123";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
-	kfree(answers);
-
-	question = "12 35";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers);
-	for (i = 0; i < nr_integers; i++)
-		KUNIT_EXPECT_EQ(test, expected[i], answers[i]);
-	kfree(answers);
-
-	question = "12 35 46";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers);
-	for (i = 0; i < nr_integers; i++)
-		KUNIT_EXPECT_EQ(test, expected[i], answers[i]);
-	kfree(answers);
-
-	question = "12 35 abc 46";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers);
-	for (i = 0; i < 2; i++)
-		KUNIT_EXPECT_EQ(test, expected[i], answers[i]);
-	kfree(answers);
-
-	question = "";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
-	kfree(answers);
-
-	question = "\n";
-	answers = str_to_ints(question, strlen(question), &nr_integers);
-	KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers);
-	kfree(answers);
-}
-
-static void damon_dbgfs_test_set_targets(struct kunit *test)
-{
-	struct damon_ctx *ctx = dbgfs_new_ctx();
-	char buf[64];
-
-	if (!damon_is_registered_ops(DAMON_OPS_PADDR)) {
-		dbgfs_destroy_ctx(ctx);
-		kunit_skip(test, "PADDR not registered");
-	}
-
-	/* Make DAMON consider target has no pid */
-	damon_select_ops(ctx, DAMON_OPS_PADDR);
-
-	dbgfs_set_targets(ctx, 0, NULL);
-	sprint_target_ids(ctx, buf, 64);
-	KUNIT_EXPECT_STREQ(test, (char *)buf, "\n");
-
-	dbgfs_set_targets(ctx, 1, NULL);
-	sprint_target_ids(ctx, buf, 64);
-	KUNIT_EXPECT_STREQ(test, (char *)buf, "42\n");
-
-	dbgfs_set_targets(ctx, 0, NULL);
-	sprint_target_ids(ctx, buf, 64);
-	KUNIT_EXPECT_STREQ(test, (char *)buf, "\n");
-
-	dbgfs_destroy_ctx(ctx);
-}
-
-static void damon_dbgfs_test_set_init_regions(struct kunit *test)
-{
-	struct damon_ctx *ctx = damon_new_ctx();
-	/* Each line represents one region in ``<target idx> <start> <end>`` */
-	char * const valid_inputs[] = {"1 10 20\n 1   20 30\n1 35 45",
-		"1 10 20\n",
-		"1 10 20\n0 39 59\n0 70 134\n  1  20 25\n",
-		""};
-	/* Reading the file again will show sorted, clean output */
-	char * const valid_expects[] = {"1 10 20\n1 20 30\n1 35 45\n",
-		"1 10 20\n",
-		"0 39 59\n0 70 134\n1 10 20\n1 20 25\n",
-		""};
-	char * const invalid_inputs[] = {"3 10 20\n",	/* target not exists */
-		"1 10 20\n 1 14 26\n",		/* regions overlap */
-		"0 10 20\n1 30 40\n 0 5 8"};	/* not sorted by address */
-	char *input, *expect;
-	int i, rc;
-	char buf[256];
-
-	if (!damon_is_registered_ops(DAMON_OPS_PADDR)) {
-		damon_destroy_ctx(ctx);
-		kunit_skip(test, "PADDR not registered");
-	}
-
-	damon_select_ops(ctx, DAMON_OPS_PADDR);
-
-	dbgfs_set_targets(ctx, 3, NULL);
-
-	/* Put valid inputs and check the results */
-	for (i = 0; i < ARRAY_SIZE(valid_inputs); i++) {
-		input = valid_inputs[i];
-		expect = valid_expects[i];
-
-		rc = set_init_regions(ctx, input, strnlen(input, 256));
-		KUNIT_EXPECT_EQ(test, rc, 0);
-
-		memset(buf, 0, 256);
-		sprint_init_regions(ctx, buf, 256);
-
-		KUNIT_EXPECT_STREQ(test, (char *)buf, expect);
-	}
-	/* Put invalid inputs and check the return error code */
-	for (i = 0; i < ARRAY_SIZE(invalid_inputs); i++) {
-		input = invalid_inputs[i];
-		pr_info("input: %s\n", input);
-		rc = set_init_regions(ctx, input, strnlen(input, 256));
-		KUNIT_EXPECT_EQ(test, rc, -EINVAL);
-
-		memset(buf, 0, 256);
-		sprint_init_regions(ctx, buf, 256);
-
-		KUNIT_EXPECT_STREQ(test, (char *)buf, "");
-	}
-
-	dbgfs_set_targets(ctx, 0, NULL);
-	damon_destroy_ctx(ctx);
-}
-
-static struct kunit_case damon_test_cases[] = {
-	KUNIT_CASE(damon_dbgfs_test_str_to_ints),
-	KUNIT_CASE(damon_dbgfs_test_set_targets),
-	KUNIT_CASE(damon_dbgfs_test_set_init_regions),
-	{},
-};
-
-static struct kunit_suite damon_test_suite = {
-	.name = "damon-dbgfs",
-	.test_cases = damon_test_cases,
-};
-kunit_test_suite(damon_test_suite);
-
-#endif /* _DAMON_DBGFS_TEST_H */
-
-#endif	/* CONFIG_DAMON_KUNIT_TEST */
diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h
index b9fe3bc8472b..7cd944266a92 100644
--- a/mm/damon/tests/vaddr-kunit.h
+++ b/mm/damon/tests/vaddr-kunit.h
@@ -68,7 +68,7 @@ static void damon_test_three_regions_in_vmas(struct kunit *test)
 	static struct mm_struct mm;
 	struct damon_addr_range regions[3] = {0};
 	/* 10-20-25, 200-210-220, 300-305, 307-330 */
-	struct vm_area_struct vmas[] = {
+	static struct vm_area_struct vmas[] = {
 		(struct vm_area_struct) {.vm_start = 10, .vm_end = 20},
 		(struct vm_area_struct) {.vm_start = 20, .vm_end = 25},
 		(struct vm_area_struct) {.vm_start = 200, .vm_end = 210},
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index b9eaa20b73b9..a6174f725bd7 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -655,7 +655,7 @@ static unsigned long damos_madvise(struct damon_target *target,
 
 static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx,
 		struct damon_target *t, struct damon_region *r,
-		struct damos *scheme)
+		struct damos *scheme, unsigned long *sz_filter_passed)
 {
 	int madv_action;
 
diff --git a/mm/debug.c b/mm/debug.c
index 95b6ab809c0e..8d2acf432385 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -249,6 +249,77 @@ void dump_mm(const struct mm_struct *mm)
 }
 EXPORT_SYMBOL(dump_mm);
 
+void dump_vmg(const struct vma_merge_struct *vmg, const char *reason)
+{
+	if (reason)
+		pr_warn("vmg %px dumped because: %s\n", vmg, reason);
+
+	if (!vmg) {
+		pr_warn("vmg %px state: (NULL)\n", vmg);
+		return;
+	}
+
+	pr_warn("vmg %px state: mm %px pgoff %lx\n"
+		"vmi %px [%lx,%lx)\n"
+		"prev %px next %px vma %px\n"
+		"start %lx end %lx flags %lx\n"
+		"file %px anon_vma %px policy %px\n"
+		"uffd_ctx %px\n"
+		"anon_name %px\n"
+		"merge_flags %x state %x\n",
+		vmg, vmg->mm, vmg->pgoff,
+		vmg->vmi, vmg->vmi ? vma_iter_addr(vmg->vmi) : 0,
+		vmg->vmi ? vma_iter_end(vmg->vmi) : 0,
+		vmg->prev, vmg->next, vmg->vma,
+		vmg->start, vmg->end, vmg->flags,
+		vmg->file, vmg->anon_vma, vmg->policy,
+#ifdef CONFIG_USERFAULTFD
+		vmg->uffd_ctx.ctx,
+#else
+		(void *)0,
+#endif
+		vmg->anon_name,
+		(int)vmg->merge_flags, (int)vmg->state);
+
+	if (vmg->mm) {
+		pr_warn("vmg %px mm:\n", vmg);
+		dump_mm(vmg->mm);
+	} else {
+		pr_warn("vmg %px mm: (NULL)\n", vmg);
+	}
+
+	if (vmg->vma) {
+		pr_warn("vmg %px vma:\n", vmg);
+		dump_vma(vmg->vma);
+	} else {
+		pr_warn("vmg %px vma: (NULL)\n", vmg);
+	}
+
+	if (vmg->prev) {
+		pr_warn("vmg %px prev:\n", vmg);
+		dump_vma(vmg->prev);
+	} else {
+		pr_warn("vmg %px prev: (NULL)\n", vmg);
+	}
+
+	if (vmg->next) {
+		pr_warn("vmg %px next:\n", vmg);
+		dump_vma(vmg->next);
+	} else {
+		pr_warn("vmg %px next: (NULL)\n", vmg);
+	}
+
+#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
+	if (vmg->vmi) {
+		pr_warn("vmg %px vmi:\n", vmg);
+		vma_iter_dump_tree(vmg->vmi);
+	} else {
+		pr_warn("vmg %px vmi: (NULL)\n", vmg);
+	}
+#endif
+}
+EXPORT_SYMBOL(dump_vmg);
+
 static bool page_init_poisoning __read_mostly = true;
 
 static int __init setup_vm_debug(char *str)
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index ce06b2884789..ff35b84a7b50 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -245,7 +245,10 @@ early_memremap_prot(resource_size_t phys_addr, unsigned long size,
 
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 
-void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size)
+/*
+ * If no empty slot, handle that and return -ENOMEM.
+ */
+int __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size)
 {
 	unsigned long slop, clen;
 	char *p;
@@ -256,12 +259,15 @@ void __init copy_from_early_mem(void *dest, phys_addr_t src, unsigned long size)
 		if (clen > MAX_MAP_CHUNK - slop)
 			clen = MAX_MAP_CHUNK - slop;
 		p = early_memremap(src & PAGE_MASK, clen + slop);
+		if (!p)
+			return -ENOMEM;
 		memcpy(dest, p + slop, clen);
 		early_memunmap(p, clen + slop);
 		dest += clen;
 		src += clen;
 		size -= clen;
 	}
+	return 0;
 }
 
 #else /* CONFIG_MMU */
diff --git a/mm/filemap.c b/mm/filemap.c
index b8ed647416e9..804d7365680c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -442,6 +442,24 @@ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 EXPORT_SYMBOL(filemap_fdatawrite_range);
 
 /**
+ * filemap_fdatawrite_range_kick - start writeback on a range
+ * @mapping:	target address_space
+ * @start:	index to start writeback on
+ * @end:	last (non-inclusive) index for writeback
+ *
+ * This is a non-integrity writeback helper, to start writing back folios
+ * for the indicated range.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
+				  loff_t end)
+{
+	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
+}
+EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
+
+/**
  * filemap_flush - mostly a non-blocking flush
  * @mapping:	target address_space
  *
@@ -1465,25 +1483,6 @@ static int folio_put_wait_locked(struct folio *folio, int state)
 }
 
 /**
- * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue
- * @folio: Folio defining the wait queue of interest
- * @waiter: Waiter to add to the queue
- *
- * Add an arbitrary @waiter to the wait queue for the nominated @folio.
- */
-void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter)
-{
-	wait_queue_head_t *q = folio_waitqueue(folio);
-	unsigned long flags;
-
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue_entry_tail(q, waiter);
-	folio_set_waiters(folio);
-	spin_unlock_irqrestore(&q->lock, flags);
-}
-EXPORT_SYMBOL_GPL(folio_add_wait_queue);
-
-/**
  * folio_unlock - Unlock a locked folio.
  * @folio: The folio.
  *
@@ -1591,6 +1590,27 @@ int folio_wait_private_2_killable(struct folio *folio)
 }
 EXPORT_SYMBOL(folio_wait_private_2_killable);
 
+/*
+ * If folio was marked as dropbehind, then pages should be dropped when writeback
+ * completes. Do that now. If we fail, it's likely because of a big folio -
+ * just reset dropbehind for that case and latter completions should invalidate.
+ */
+static void folio_end_dropbehind_write(struct folio *folio)
+{
+	/*
+	 * Hitting !in_task() should not happen off RWF_DONTCACHE writeback,
+	 * but can happen if normal writeback just happens to find dirty folios
+	 * that were created as part of uncached writeback, and that writeback
+	 * would otherwise not need non-IRQ handling. Just skip the
+	 * invalidation in that case.
+	 */
+	if (in_task() && folio_trylock(folio)) {
+		if (folio->mapping)
+			folio_unmap_invalidate(folio->mapping, folio, 0);
+		folio_unlock(folio);
+	}
+}
+
 /**
  * folio_end_writeback - End writeback against a folio.
  * @folio: The folio.
@@ -1601,6 +1621,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable);
  */
 void folio_end_writeback(struct folio *folio)
 {
+	bool folio_dropbehind = false;
+
 	VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
 
 	/*
@@ -1622,9 +1644,14 @@ void folio_end_writeback(struct folio *folio)
 	 * reused before the folio_wake_bit().
 	 */
 	folio_get(folio);
+	if (!folio_test_dirty(folio))
+		folio_dropbehind = folio_test_clear_dropbehind(folio);
 	if (__folio_end_writeback(folio))
 		folio_wake_bit(folio, PG_writeback);
 	acct_reclaim_writeback(folio);
+
+	if (folio_dropbehind)
+		folio_end_dropbehind_write(folio);
 	folio_put(folio);
 }
 EXPORT_SYMBOL(folio_end_writeback);
@@ -1947,6 +1974,8 @@ no_page:
 			/* Init accessed so avoid atomic mark_page_accessed later */
 			if (fgp_flags & FGP_ACCESSED)
 				__folio_set_referenced(folio);
+			if (fgp_flags & FGP_DONTCACHE)
+				__folio_set_dropbehind(folio);
 
 			err = filemap_add_folio(mapping, folio, index, gfp);
 			if (!err)
@@ -1969,6 +1998,9 @@ no_page:
 
 	if (!folio)
 		return ERR_PTR(-ENOENT);
+	/* not an uncached lookup, clear uncached if set */
+	if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE))
+		folio_clear_dropbehind(folio);
 	return folio;
 }
 EXPORT_SYMBOL(__filemap_get_folio);
@@ -2451,18 +2483,22 @@ unlock_mapping:
 	return error;
 }
 
-static int filemap_create_folio(struct file *file,
-		struct address_space *mapping, loff_t pos,
-		struct folio_batch *fbatch)
+static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch)
 {
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct folio *folio;
 	int error;
 	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t index;
 
+	if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
+		return -EAGAIN;
+
 	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
 	if (!folio)
 		return -ENOMEM;
+	if (iocb->ki_flags & IOCB_DONTCACHE)
+		__folio_set_dropbehind(folio);
 
 	/*
 	 * Protect against truncate / hole punch. Grabbing invalidate_lock
@@ -2478,7 +2514,7 @@ static int filemap_create_folio(struct file *file,
 	 * well to keep locking rules simple.
 	 */
 	filemap_invalidate_lock_shared(mapping);
-	index = (pos >> (PAGE_SHIFT + min_order)) << min_order;
+	index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order;
 	error = filemap_add_folio(mapping, folio, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2486,7 +2522,8 @@ static int filemap_create_folio(struct file *file,
 	if (error)
 		goto error;
 
-	error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
+	error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
+					folio);
 	if (error)
 		goto error;
 
@@ -2507,6 +2544,8 @@ static int filemap_readahead(struct kiocb *iocb, struct file *file,
 
 	if (iocb->ki_flags & IOCB_NOIO)
 		return -EAGAIN;
+	if (iocb->ki_flags & IOCB_DONTCACHE)
+		ractl.dropbehind = 1;
 	page_cache_async_ra(&ractl, folio, last_index - folio->index);
 	return 0;
 }
@@ -2516,7 +2555,6 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 {
 	struct file *filp = iocb->ki_filp;
 	struct address_space *mapping = filp->f_mapping;
-	struct file_ra_state *ra = &filp->f_ra;
 	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
 	pgoff_t last_index;
 	struct folio *folio;
@@ -2531,20 +2569,21 @@ retry:
 
 	filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
 	if (!folio_batch_count(fbatch)) {
+		DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index);
+
 		if (iocb->ki_flags & IOCB_NOIO)
 			return -EAGAIN;
 		if (iocb->ki_flags & IOCB_NOWAIT)
 			flags = memalloc_noio_save();
-		page_cache_sync_readahead(mapping, ra, filp, index,
-				last_index - index);
+		if (iocb->ki_flags & IOCB_DONTCACHE)
+			ractl.dropbehind = 1;
+		page_cache_sync_ra(&ractl, last_index - index);
 		if (iocb->ki_flags & IOCB_NOWAIT)
 			memalloc_noio_restore(flags);
 		filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
 	}
 	if (!folio_batch_count(fbatch)) {
-		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
-			return -EAGAIN;
-		err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch);
+		err = filemap_create_folio(iocb, fbatch);
 		if (err == AOP_TRUNCATED_PAGE)
 			goto retry;
 		return err;
@@ -2585,6 +2624,20 @@ static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio)
 	return (pos1 >> shift == pos2 >> shift);
 }
 
+static void filemap_end_dropbehind_read(struct address_space *mapping,
+					struct folio *folio)
+{
+	if (!folio_test_dropbehind(folio))
+		return;
+	if (folio_test_writeback(folio) || folio_test_dirty(folio))
+		return;
+	if (folio_trylock(folio)) {
+		if (folio_test_clear_dropbehind(folio))
+			folio_unmap_invalidate(mapping, folio, 0);
+		folio_unlock(folio);
+	}
+}
+
 /**
  * filemap_read - Read data from the page cache.
  * @iocb: The iocb to read.
@@ -2698,8 +2751,12 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 			}
 		}
 put_folios:
-		for (i = 0; i < folio_batch_count(&fbatch); i++)
-			folio_put(fbatch.folios[i]);
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			struct folio *folio = fbatch.folios[i];
+
+			filemap_end_dropbehind_read(mapping, folio);
+			folio_put(folio);
+		}
 		folio_batch_init(&fbatch);
 	} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
 
diff --git a/mm/gup.c b/mm/gup.c
index 87a9c2026e4d..3883b307780e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -596,6 +596,33 @@ static struct folio *try_grab_folio_fast(struct page *page, int refs,
 }
 #endif	/* CONFIG_HAVE_GUP_FAST */
 
+/* Common code for can_follow_write_* */
+static inline bool can_follow_write_common(struct page *page,
+		struct vm_area_struct *vma, unsigned int flags)
+{
+	/* Maybe FOLL_FORCE is set to override it? */
+	if (!(flags & FOLL_FORCE))
+		return false;
+
+	/* But FOLL_FORCE has no effect on shared mappings */
+	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
+		return false;
+
+	/* ... or read-only private ones */
+	if (!(vma->vm_flags & VM_MAYWRITE))
+		return false;
+
+	/* ... or already writable ones that just need to take a write fault */
+	if (vma->vm_flags & VM_WRITE)
+		return false;
+
+	/*
+	 * See can_change_pte_writable(): we broke COW and could map the page
+	 * writable if we have an exclusive anonymous page ...
+	 */
+	return page && PageAnon(page) && PageAnonExclusive(page);
+}
+
 static struct page *no_page_table(struct vm_area_struct *vma,
 				  unsigned int flags, unsigned long address)
 {
@@ -622,6 +649,18 @@ static struct page *no_page_table(struct vm_area_struct *vma,
 }
 
 #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
+/* FOLL_FORCE can write to even unwritable PUDs in COW mappings. */
+static inline bool can_follow_write_pud(pud_t pud, struct page *page,
+					struct vm_area_struct *vma,
+					unsigned int flags)
+{
+	/* If the pud is writable, we can write to the page. */
+	if (pud_write(pud))
+		return true;
+
+	return can_follow_write_common(page, vma, flags);
+}
+
 static struct page *follow_huge_pud(struct vm_area_struct *vma,
 				    unsigned long addr, pud_t *pudp,
 				    int flags, struct follow_page_context *ctx)
@@ -634,10 +673,11 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 
 	assert_spin_locked(pud_lockptr(mm, pudp));
 
-	if ((flags & FOLL_WRITE) && !pud_write(pud))
+	if (!pud_present(pud))
 		return NULL;
 
-	if (!pud_present(pud))
+	if ((flags & FOLL_WRITE) &&
+	    !can_follow_write_pud(pud, pfn_to_page(pfn), vma, flags))
 		return NULL;
 
 	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
@@ -686,27 +726,7 @@ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
 	if (pmd_write(pmd))
 		return true;
 
-	/* Maybe FOLL_FORCE is set to override it? */
-	if (!(flags & FOLL_FORCE))
-		return false;
-
-	/* But FOLL_FORCE has no effect on shared mappings */
-	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
-		return false;
-
-	/* ... or read-only private ones */
-	if (!(vma->vm_flags & VM_MAYWRITE))
-		return false;
-
-	/* ... or already writable ones that just need to take a write fault */
-	if (vma->vm_flags & VM_WRITE)
-		return false;
-
-	/*
-	 * See can_change_pte_writable(): we broke COW and could map the page
-	 * writable if we have an exclusive anonymous page ...
-	 */
-	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+	if (!can_follow_write_common(page, vma, flags))
 		return false;
 
 	/* ... and a write-fault isn't required for other reasons. */
@@ -807,27 +827,7 @@ static inline bool can_follow_write_pte(pte_t pte, struct page *page,
 	if (pte_write(pte))
 		return true;
 
-	/* Maybe FOLL_FORCE is set to override it? */
-	if (!(flags & FOLL_FORCE))
-		return false;
-
-	/* But FOLL_FORCE has no effect on shared mappings */
-	if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED))
-		return false;
-
-	/* ... or read-only private ones */
-	if (!(vma->vm_flags & VM_MAYWRITE))
-		return false;
-
-	/* ... or already writable ones that just need to take a write fault */
-	if (vma->vm_flags & VM_WRITE)
-		return false;
-
-	/*
-	 * See can_change_pte_writable(): we broke COW and could map the page
-	 * writable if we have an exclusive anonymous page ...
-	 */
-	if (!page || !PageAnon(page) || !PageAnonExclusive(page))
+	if (!can_follow_write_common(page, vma, flags))
 		return false;
 
 	/* ... and a write-fault isn't required for other reasons. */
@@ -1294,9 +1294,6 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
 		if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) {
 			if (!(gup_flags & FOLL_FORCE))
 				return -EFAULT;
-			/* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */
-			if (is_vm_hugetlb_page(vma))
-				return -EFAULT;
 			/*
 			 * We used to let the write,force case do COW in a
 			 * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could
@@ -2323,13 +2320,13 @@ static void pofs_unpin(struct pages_or_folios *pofs)
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
-static unsigned long collect_longterm_unpinnable_folios(
+static void collect_longterm_unpinnable_folios(
 		struct list_head *movable_folio_list,
 		struct pages_or_folios *pofs)
 {
-	unsigned long i, collected = 0;
 	struct folio *prev_folio = NULL;
 	bool drain_allow = true;
+	unsigned long i;
 
 	for (i = 0; i < pofs->nr_entries; i++) {
 		struct folio *folio = pofs_get_folio(pofs, i);
@@ -2341,13 +2338,11 @@ static unsigned long collect_longterm_unpinnable_folios(
 		if (folio_is_longterm_pinnable(folio))
 			continue;
 
-		collected++;
-
 		if (folio_is_device_coherent(folio))
 			continue;
 
 		if (folio_test_hugetlb(folio)) {
-			isolate_hugetlb(folio, movable_folio_list);
+			folio_isolate_hugetlb(folio, movable_folio_list);
 			continue;
 		}
 
@@ -2364,8 +2359,6 @@ static unsigned long collect_longterm_unpinnable_folios(
 				    NR_ISOLATED_ANON + folio_is_file_lru(folio),
 				    folio_nr_pages(folio));
 	}
-
-	return collected;
 }
 
 /*
@@ -2442,11 +2435,9 @@ static long
 check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
 {
 	LIST_HEAD(movable_folio_list);
-	unsigned long collected;
 
-	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
-						       pofs);
-	if (!collected)
+	collect_longterm_unpinnable_folios(&movable_folio_list, pofs);
+	if (list_empty(&movable_folio_list))
 		return 0;
 
 	return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index db64116a4f84..3d3ebdc002d5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -617,6 +617,8 @@ DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
 DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
 DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT);
 DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN);
+DEFINE_MTHP_STAT_ATTR(swpin_fallback, MTHP_STAT_SWPIN_FALLBACK);
+DEFINE_MTHP_STAT_ATTR(swpin_fallback_charge, MTHP_STAT_SWPIN_FALLBACK_CHARGE);
 DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
 DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
 #ifdef CONFIG_SHMEM
@@ -637,6 +639,8 @@ static struct attribute *anon_stats_attrs[] = {
 #ifndef CONFIG_SHMEM
 	&zswpout_attr.attr,
 	&swpin_attr.attr,
+	&swpin_fallback_attr.attr,
+	&swpin_fallback_charge_attr.attr,
 	&swpout_attr.attr,
 	&swpout_fallback_attr.attr,
 #endif
@@ -669,6 +673,8 @@ static struct attribute *any_stats_attrs[] = {
 #ifdef CONFIG_SHMEM
 	&zswpout_attr.attr,
 	&swpin_attr.attr,
+	&swpin_fallback_attr.attr,
+	&swpin_fallback_charge_attr.attr,
 	&swpout_attr.attr,
 	&swpout_fallback_attr.attr,
 #endif
@@ -2003,7 +2009,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	spin_unlock(vmf->ptl);
 	writable = false;
 
-	if (!migrate_misplaced_folio(folio, vma, target_nid)) {
+	if (!migrate_misplaced_folio(folio, target_nid)) {
 		flags |= TNF_MIGRATED;
 		nid = target_nid;
 		task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
@@ -3284,7 +3290,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	/* lock lru list/PageCompound, ref frozen by page_ref_freeze */
 	lruvec = folio_lruvec_lock(folio);
 
-	ClearPageHasHWPoisoned(head);
+	folio_clear_has_hwpoisoned(folio);
 
 	for (i = nr - new_nr; i >= new_nr; i -= new_nr) {
 		struct folio *tail;
@@ -4175,20 +4181,21 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 
 	if (input_buf[0] == '/') {
 		char *tok;
-		char *buf = input_buf;
+		char *tok_buf = input_buf;
 		char file_path[MAX_INPUT_BUF_SZ];
 		pgoff_t off_start = 0, off_end = 0;
 		size_t input_len = strlen(input_buf);
 
-		tok = strsep(&buf, ",");
-		if (tok && buf) {
+		tok = strsep(&tok_buf, ",");
+		if (tok && tok_buf) {
 			strscpy(file_path, tok);
 		} else {
 			ret = -EINVAL;
 			goto out;
 		}
 
-		ret = sscanf(buf, "0x%lx,0x%lx,%d", &off_start, &off_end, &new_order);
+		ret = sscanf(tok_buf, "0x%lx,0x%lx,%d", &off_start,
+			    &off_end, &new_order);
 		if (ret != 2 && ret != 3) {
 			ret = -EINVAL;
 			goto out;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eaaec19caa7c..65068671e460 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -48,6 +48,7 @@
 #include <linux/page_owner.h>
 #include "internal.h"
 #include "hugetlb_vmemmap.h"
+#include <linux/page-isolation.h>
 
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
@@ -1246,69 +1247,6 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
 	hugetlb_dup_vma_private(vma);
 }
 
-/* Returns true if the VMA has associated reserve pages */
-static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
-{
-	if (vma->vm_flags & VM_NORESERVE) {
-		/*
-		 * This address is already reserved by other process(chg == 0),
-		 * so, we should decrement reserved count. Without decrementing,
-		 * reserve count remains after releasing inode, because this
-		 * allocated page will go into page cache and is regarded as
-		 * coming from reserved pool in releasing step.  Currently, we
-		 * don't have any other solution to deal with this situation
-		 * properly, so add work-around here.
-		 */
-		if (vma->vm_flags & VM_MAYSHARE && chg == 0)
-			return true;
-		else
-			return false;
-	}
-
-	/* Shared mappings always use reserves */
-	if (vma->vm_flags & VM_MAYSHARE) {
-		/*
-		 * We know VM_NORESERVE is not set.  Therefore, there SHOULD
-		 * be a region map for all pages.  The only situation where
-		 * there is no region map is if a hole was punched via
-		 * fallocate.  In this case, there really are no reserves to
-		 * use.  This situation is indicated if chg != 0.
-		 */
-		if (chg)
-			return false;
-		else
-			return true;
-	}
-
-	/*
-	 * Only the process that called mmap() has reserves for
-	 * private mappings.
-	 */
-	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
-		/*
-		 * Like the shared case above, a hole punch or truncate
-		 * could have been performed on the private mapping.
-		 * Examine the value of chg to determine if reserves
-		 * actually exist or were previously consumed.
-		 * Very Subtle - The value of chg comes from a previous
-		 * call to vma_needs_reserves().  The reserve map for
-		 * private mappings has different (opposite) semantics
-		 * than that of shared mappings.  vma_needs_reserves()
-		 * has already taken this difference in semantics into
-		 * account.  Therefore, the meaning of chg is the same
-		 * as in the shared case above.  Code could easily be
-		 * combined, but keeping it separate draws attention to
-		 * subtle differences.
-		 */
-		if (chg)
-			return false;
-		else
-			return true;
-	}
-
-	return false;
-}
-
 static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio)
 {
 	int nid = folio_nid(folio);
@@ -1336,6 +1274,9 @@ static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h,
 		if (folio_test_hwpoison(folio))
 			continue;
 
+		if (is_migrate_isolate_page(&folio->page))
+			continue;
+
 		list_move(&folio->lru, &h->hugepage_activelist);
 		folio_ref_unfreeze(folio, 1);
 		folio_clear_hugetlb_freed(folio);
@@ -1394,8 +1335,7 @@ static unsigned long available_huge_pages(struct hstate *h)
 
 static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h,
 				struct vm_area_struct *vma,
-				unsigned long address, int avoid_reserve,
-				long chg)
+				unsigned long address, long gbl_chg)
 {
 	struct folio *folio = NULL;
 	struct mempolicy *mpol;
@@ -1404,15 +1344,10 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h,
 	int nid;
 
 	/*
-	 * A child process with MAP_PRIVATE mappings created by their parent
-	 * have no page reserves. This check ensures that reservations are
-	 * not "stolen". The child may still get SIGKILLed
+	 * gbl_chg==1 means the allocation requires a new page that was not
+	 * reserved before.  Making sure there's at least one free page.
 	 */
-	if (!vma_has_reserves(vma, chg) && !available_huge_pages(h))
-		goto err;
-
-	/* If reserves cannot be used, ensure enough pages are in the pool */
-	if (avoid_reserve && !available_huge_pages(h))
+	if (gbl_chg && !available_huge_pages(h))
 		goto err;
 
 	gfp_mask = htlb_alloc_mask(h);
@@ -1430,11 +1365,6 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h,
 		folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask,
 							nid, nodemask);
 
-	if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) {
-		folio_set_hugetlb_restore_reserve(folio);
-		h->resv_huge_pages--;
-	}
-
 	mpol_cond_put(mpol);
 	return folio;
 
@@ -2463,7 +2393,13 @@ static int gather_surplus_pages(struct hstate *h, long delta)
 	long needed, allocated;
 	bool alloc_ok = true;
 	int node;
-	nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
+	nodemask_t *mbind_nodemask, alloc_nodemask;
+
+	mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
+	if (mbind_nodemask)
+		nodes_and(alloc_nodemask, *mbind_nodemask, cpuset_current_mems_allowed);
+	else
+		alloc_nodemask = cpuset_current_mems_allowed;
 
 	lockdep_assert_held(&hugetlb_lock);
 	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
@@ -2479,8 +2415,16 @@ retry:
 	spin_unlock_irq(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
 		folio = NULL;
-		for_each_node_mask(node, cpuset_current_mems_allowed) {
-			if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) {
+
+		/* Prioritize current node */
+		if (node_isset(numa_mem_id(), alloc_nodemask))
+			folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
+					numa_mem_id(), NULL);
+
+		if (!folio) {
+			for_each_node_mask(node, alloc_nodemask) {
+				if (node == numa_mem_id())
+					continue;
 				folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
 						node, NULL);
 				if (folio)
@@ -2868,7 +2812,7 @@ retry:
 		 * Fail with -EBUSY if not possible.
 		 */
 		spin_unlock_irq(&hugetlb_lock);
-		isolated = isolate_hugetlb(old_folio, list);
+		isolated = folio_isolate_hugetlb(old_folio, list);
 		ret = isolated ? 0 : -EBUSY;
 		spin_lock_irq(&hugetlb_lock);
 		goto free_new;
@@ -2953,7 +2897,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
 	if (hstate_is_gigantic(h))
 		return -ENOMEM;
 
-	if (folio_ref_count(folio) && isolate_hugetlb(folio, list))
+	if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list))
 		ret = 0;
 	else if (!folio_ref_count(folio))
 		ret = alloc_and_dissolve_hugetlb_folio(h, folio, list);
@@ -2961,69 +2905,129 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list)
 	return ret;
 }
 
+/*
+ *  replace_free_hugepage_folios - Replace free hugepage folios in a given pfn
+ *  range with new folios.
+ *  @start_pfn: start pfn of the given pfn range
+ *  @end_pfn: end pfn of the given pfn range
+ *  Returns 0 on success, otherwise negated error.
+ */
+int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
+{
+	struct hstate *h;
+	struct folio *folio;
+	int ret = 0;
+
+	LIST_HEAD(isolate_list);
+
+	while (start_pfn < end_pfn) {
+		folio = pfn_folio(start_pfn);
+		if (folio_test_hugetlb(folio)) {
+			h = folio_hstate(folio);
+		} else {
+			start_pfn++;
+			continue;
+		}
+
+		if (!folio_ref_count(folio)) {
+			ret = alloc_and_dissolve_hugetlb_folio(h, folio,
+							       &isolate_list);
+			if (ret)
+				break;
+
+			putback_movable_pages(&isolate_list);
+		}
+		start_pfn++;
+	}
+
+	return ret;
+}
+
+typedef enum {
+	/*
+	 * For either 0/1: we checked the per-vma resv map, and one resv
+	 * count either can be reused (0), or an extra needed (1).
+	 */
+	MAP_CHG_REUSE = 0,
+	MAP_CHG_NEEDED = 1,
+	/*
+	 * Cannot use per-vma resv count can be used, hence a new resv
+	 * count is enforced.
+	 *
+	 * NOTE: This is mostly identical to MAP_CHG_NEEDED, except
+	 * that currently vma_needs_reservation() has an unwanted side
+	 * effect to either use end() or commit() to complete the
+	 * transaction.	 Hence it needs to differenciate from NEEDED.
+	 */
+	MAP_CHG_ENFORCED = 2,
+} map_chg_state;
+
+/*
+ * NOTE! "cow_from_owner" represents a very hacky usage only used in CoW
+ * faults of hugetlb private mappings on top of a non-page-cache folio (in
+ * which case even if there's a private vma resv map it won't cover such
+ * allocation).  New call sites should (probably) never set it to true!!
+ * When it's set, the allocation will bypass all vma level reservations.
+ */
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
-				    unsigned long addr, int avoid_reserve)
+				    unsigned long addr, bool cow_from_owner)
 {
 	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct folio *folio;
-	long map_chg, map_commit, nr_pages = pages_per_huge_page(h);
-	long gbl_chg;
-	int memcg_charge_ret, ret, idx;
+	long retval, gbl_chg;
+	map_chg_state map_chg;
+	int ret, idx;
 	struct hugetlb_cgroup *h_cg = NULL;
-	struct mem_cgroup *memcg;
-	bool deferred_reserve;
 	gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL;
 
-	memcg = get_mem_cgroup_from_current();
-	memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages);
-	if (memcg_charge_ret == -ENOMEM) {
-		mem_cgroup_put(memcg);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	idx = hstate_index(h);
-	/*
-	 * Examine the region/reserve map to determine if the process
-	 * has a reservation for the page to be allocated.  A return
-	 * code of zero indicates a reservation exists (no change).
-	 */
-	map_chg = gbl_chg = vma_needs_reservation(h, vma, addr);
-	if (map_chg < 0) {
-		if (!memcg_charge_ret)
-			mem_cgroup_cancel_charge(memcg, nr_pages);
-		mem_cgroup_put(memcg);
-		return ERR_PTR(-ENOMEM);
+
+	/* Whether we need a separate per-vma reservation? */
+	if (cow_from_owner) {
+		/*
+		 * Special case!  Since it's a CoW on top of a reserved
+		 * page, the private resv map doesn't count.  So it cannot
+		 * consume the per-vma resv map even if it's reserved.
+		 */
+		map_chg = MAP_CHG_ENFORCED;
+	} else {
+		/*
+		 * Examine the region/reserve map to determine if the process
+		 * has a reservation for the page to be allocated.  A return
+		 * code of zero indicates a reservation exists (no change).
+		 */
+		retval = vma_needs_reservation(h, vma, addr);
+		if (retval < 0)
+			return ERR_PTR(-ENOMEM);
+		map_chg = retval ? MAP_CHG_NEEDED : MAP_CHG_REUSE;
 	}
 
 	/*
+	 * Whether we need a separate global reservation?
+	 *
 	 * Processes that did not create the mapping will have no
 	 * reserves as indicated by the region/reserve map. Check
 	 * that the allocation will not exceed the subpool limit.
-	 * Allocations for MAP_NORESERVE mappings also need to be
-	 * checked against any subpool limit.
+	 * Or if it can get one from the pool reservation directly.
 	 */
-	if (map_chg || avoid_reserve) {
+	if (map_chg) {
 		gbl_chg = hugepage_subpool_get_pages(spool, 1);
 		if (gbl_chg < 0)
 			goto out_end_reservation;
-
+	} else {
 		/*
-		 * Even though there was no reservation in the region/reserve
-		 * map, there could be reservations associated with the
-		 * subpool that can be used.  This would be indicated if the
-		 * return value of hugepage_subpool_get_pages() is zero.
-		 * However, if avoid_reserve is specified we still avoid even
-		 * the subpool reservations.
+		 * If we have the vma reservation ready, no need for extra
+		 * global reservation.
 		 */
-		if (avoid_reserve)
-			gbl_chg = 1;
+		gbl_chg = 0;
 	}
 
-	/* If this allocation is not consuming a reservation, charge it now.
+	/*
+	 * If this allocation is not consuming a per-vma reservation,
+	 * charge the hugetlb cgroup now.
 	 */
-	deferred_reserve = map_chg || avoid_reserve;
-	if (deferred_reserve) {
+	if (map_chg) {
 		ret = hugetlb_cgroup_charge_cgroup_rsvd(
 			idx, pages_per_huge_page(h), &h_cg);
 		if (ret)
@@ -3040,27 +3044,32 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	 * from the global free pool (global change).  gbl_chg == 0 indicates
 	 * a reservation exists for the allocation.
 	 */
-	folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg);
+	folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg);
 	if (!folio) {
 		spin_unlock_irq(&hugetlb_lock);
 		folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr);
 		if (!folio)
 			goto out_uncharge_cgroup;
 		spin_lock_irq(&hugetlb_lock);
-		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
-			folio_set_hugetlb_restore_reserve(folio);
-			h->resv_huge_pages--;
-		}
 		list_add(&folio->lru, &h->hugepage_activelist);
 		folio_ref_unfreeze(folio, 1);
 		/* Fall through */
 	}
 
+	/*
+	 * Either dequeued or buddy-allocated folio needs to add special
+	 * mark to the folio when it consumes a global reservation.
+	 */
+	if (!gbl_chg) {
+		folio_set_hugetlb_restore_reserve(folio);
+		h->resv_huge_pages--;
+	}
+
 	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio);
 	/* If allocation is not consuming a reservation, also store the
 	 * hugetlb_cgroup pointer on the page.
 	 */
-	if (deferred_reserve) {
+	if (map_chg) {
 		hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h),
 						  h_cg, folio);
 	}
@@ -3069,50 +3078,61 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 
 	hugetlb_set_folio_subpool(folio, spool);
 
-	map_commit = vma_commit_reservation(h, vma, addr);
-	if (unlikely(map_chg > map_commit)) {
+	if (map_chg != MAP_CHG_ENFORCED) {
+		/* commit() is only needed if the map_chg is not enforced */
+		retval = vma_commit_reservation(h, vma, addr);
 		/*
+		 * Check for possible race conditions. When it happens..
 		 * The page was added to the reservation map between
 		 * vma_needs_reservation and vma_commit_reservation.
 		 * This indicates a race with hugetlb_reserve_pages.
 		 * Adjust for the subpool count incremented above AND
-		 * in hugetlb_reserve_pages for the same page.  Also,
+		 * in hugetlb_reserve_pages for the same page.	Also,
 		 * the reservation count added in hugetlb_reserve_pages
 		 * no longer applies.
 		 */
-		long rsv_adjust;
+		if (unlikely(map_chg == MAP_CHG_NEEDED && retval == 0)) {
+			long rsv_adjust;
 
-		rsv_adjust = hugepage_subpool_put_pages(spool, 1);
-		hugetlb_acct_memory(h, -rsv_adjust);
-		if (deferred_reserve) {
-			spin_lock_irq(&hugetlb_lock);
-			hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h),
-					pages_per_huge_page(h), folio);
-			spin_unlock_irq(&hugetlb_lock);
+			rsv_adjust = hugepage_subpool_put_pages(spool, 1);
+			hugetlb_acct_memory(h, -rsv_adjust);
+			if (map_chg) {
+				spin_lock_irq(&hugetlb_lock);
+				hugetlb_cgroup_uncharge_folio_rsvd(
+				    hstate_index(h), pages_per_huge_page(h),
+				    folio);
+				spin_unlock_irq(&hugetlb_lock);
+			}
 		}
 	}
 
-	if (!memcg_charge_ret)
-		mem_cgroup_commit_charge(folio, memcg);
+	ret = mem_cgroup_charge_hugetlb(folio, gfp);
+	/*
+	 * Unconditionally increment NR_HUGETLB here. If it turns out that
+	 * mem_cgroup_charge_hugetlb failed, then immediately free the page and
+	 * decrement NR_HUGETLB.
+	 */
 	lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h));
-	mem_cgroup_put(memcg);
+
+	if (ret == -ENOMEM) {
+		free_huge_folio(folio);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	return folio;
 
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
 out_uncharge_cgroup_reservation:
-	if (deferred_reserve)
+	if (map_chg)
 		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
 						    h_cg);
 out_subpool_put:
-	if (map_chg || avoid_reserve)
+	if (map_chg)
 		hugepage_subpool_put_pages(spool, 1);
 out_end_reservation:
-	vma_end_reservation(h, vma, addr);
-	if (!memcg_charge_ret)
-		mem_cgroup_cancel_charge(memcg, nr_pages);
-	mem_cgroup_put(memcg);
+	if (map_chg != MAP_CHG_ENFORCED)
+		vma_end_reservation(h, vma, addr);
 	return ERR_PTR(-ENOSPC);
 }
 
@@ -3289,7 +3309,7 @@ static void __init gather_bootmem_prealloc(void)
 		.thread_fn	= gather_bootmem_prealloc_parallel,
 		.fn_arg		= NULL,
 		.start		= 0,
-		.size		= num_node_state(N_MEMORY),
+		.size		= nr_node_ids,
 		.align		= 1,
 		.min_chunk	= 1,
 		.max_threads	= num_node_state(N_MEMORY),
@@ -3806,13 +3826,15 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
 
 		for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) {
 			struct page *page = folio_page(folio, i);
+			/* Careful: see __split_huge_page_tail() */
+			struct folio *new_folio = (struct folio *)page;
 
-			page->mapping = NULL;
 			clear_compound_head(page);
 			prep_compound_page(page, dst->order);
 
-			init_new_hugetlb_folio(dst, page_folio(page));
-			list_add(&page->lru, &dst_list);
+			new_folio->mapping = NULL;
+			init_new_hugetlb_folio(dst, new_folio);
+			list_add(&new_folio->lru, &dst_list);
 		}
 	}
 
@@ -4845,7 +4867,7 @@ out:
 	return ret;
 }
 
-static struct ctl_table hugetlb_table[] = {
+static const struct ctl_table hugetlb_table[] = {
 	{
 		.procname	= "nr_hugepages",
 		.data		= NULL,
@@ -5141,12 +5163,12 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
-				int writable)
+		bool try_mkwrite)
 {
 	pte_t entry;
 	unsigned int shift = huge_page_shift(hstate_vma(vma));
 
-	if (writable) {
+	if (try_mkwrite && (vma->vm_flags & VM_WRITE)) {
 		entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page,
 					 vma->vm_page_prot)));
 	} else {
@@ -5169,6 +5191,13 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 		update_mmu_cache(vma, address, ptep);
 }
 
+static void set_huge_ptep_maybe_writable(struct vm_area_struct *vma,
+					 unsigned long address, pte_t *ptep)
+{
+	if (vma->vm_flags & VM_WRITE)
+		set_huge_ptep_writable(vma, address, ptep);
+}
+
 bool is_hugetlb_entry_migration(pte_t pte)
 {
 	swp_entry_t swp;
@@ -5199,7 +5228,7 @@ static void
 hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
 		      struct folio *new_folio, pte_t old, unsigned long sz)
 {
-	pte_t newpte = make_huge_pte(vma, &new_folio->page, 1);
+	pte_t newpte = make_huge_pte(vma, &new_folio->page, true);
 
 	__folio_mark_uptodate(new_folio);
 	hugetlb_add_new_anon_rmap(new_folio, vma, addr);
@@ -5333,7 +5362,7 @@ again:
 				spin_unlock(src_ptl);
 				spin_unlock(dst_ptl);
 				/* Do not use reserve as it's private owned */
-				new_folio = alloc_hugetlb_folio(dst_vma, addr, 1);
+				new_folio = alloc_hugetlb_folio(dst_vma, addr, false);
 				if (IS_ERR(new_folio)) {
 					folio_put(pte_folio);
 					ret = PTR_ERR(new_folio);
@@ -5799,7 +5828,7 @@ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio,
 	struct hstate *h = hstate_vma(vma);
 	struct folio *old_folio;
 	struct folio *new_folio;
-	int outside_reserve = 0;
+	bool cow_from_owner = 0;
 	vm_fault_t ret = 0;
 	struct mmu_notifier_range range;
 
@@ -5814,13 +5843,6 @@ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio,
 	if (!unshare && huge_pte_uffd_wp(pte))
 		return 0;
 
-	/*
-	 * hugetlb does not support FOLL_FORCE-style write faults that keep the
-	 * PTE mapped R/O such as maybe_mkwrite() would do.
-	 */
-	if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE)))
-		return VM_FAULT_SIGSEGV;
-
 	/* Let's take out MAP_SHARED mappings first. */
 	if (vma->vm_flags & VM_MAYSHARE) {
 		set_huge_ptep_writable(vma, vmf->address, vmf->pte);
@@ -5849,7 +5871,8 @@ retry_avoidcopy:
 			SetPageAnonExclusive(&old_folio->page);
 		}
 		if (likely(!unshare))
-			set_huge_ptep_writable(vma, vmf->address, vmf->pte);
+			set_huge_ptep_maybe_writable(vma, vmf->address,
+						     vmf->pte);
 
 		delayacct_wpcopy_end();
 		return 0;
@@ -5868,7 +5891,7 @@ retry_avoidcopy:
 	 */
 	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
 			old_folio != pagecache_folio)
-		outside_reserve = 1;
+		cow_from_owner = true;
 
 	folio_get(old_folio);
 
@@ -5877,7 +5900,7 @@ retry_avoidcopy:
 	 * be acquired again before returning to the caller, as expected.
 	 */
 	spin_unlock(vmf->ptl);
-	new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve);
+	new_folio = alloc_hugetlb_folio(vma, vmf->address, cow_from_owner);
 
 	if (IS_ERR(new_folio)) {
 		/*
@@ -5887,7 +5910,7 @@ retry_avoidcopy:
 		 * reliability, unmap the page from child processes. The child
 		 * may get SIGKILLed if it later faults.
 		 */
-		if (outside_reserve) {
+		if (cow_from_owner) {
 			struct address_space *mapping = vma->vm_file->f_mapping;
 			pgoff_t idx;
 			u32 hash;
@@ -6138,7 +6161,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
 				goto out;
 		}
 
-		folio = alloc_hugetlb_folio(vma, vmf->address, 0);
+		folio = alloc_hugetlb_folio(vma, vmf->address, false);
 		if (IS_ERR(folio)) {
 			/*
 			 * Returning error will result in faulting task being
@@ -6235,8 +6258,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
 		hugetlb_add_new_anon_rmap(folio, vma, vmf->address);
 	else
 		hugetlb_add_file_rmap(folio);
-	new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE)
-				&& (vma->vm_flags & VM_SHARED)));
+	new_pte = make_huge_pte(vma, &folio->page, vma->vm_flags & VM_SHARED);
 	/*
 	 * If this pte was previously wr-protected, keep it wr-protected even
 	 * if populated.
@@ -6568,7 +6590,6 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 	spinlock_t *ptl;
 	int ret = -ENOMEM;
 	struct folio *folio;
-	int writable;
 	bool folio_in_pagecache = false;
 
 	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) {
@@ -6606,7 +6627,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 			goto out;
 		}
 
-		folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0);
+		folio = alloc_hugetlb_folio(dst_vma, dst_addr, false);
 		if (IS_ERR(folio)) {
 			ret = -ENOMEM;
 			goto out;
@@ -6648,7 +6669,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 			goto out;
 		}
 
-		folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0);
+		folio = alloc_hugetlb_folio(dst_vma, dst_addr, false);
 		if (IS_ERR(folio)) {
 			folio_put(*foliop);
 			ret = -ENOMEM;
@@ -6722,12 +6743,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 	 * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY
 	 * with wp flag set, don't set pte write bit.
 	 */
-	if (wp_enabled || (is_continue && !vm_shared))
-		writable = 0;
-	else
-		writable = dst_vma->vm_flags & VM_WRITE;
-
-	_dst_pte = make_huge_pte(dst_vma, &folio->page, writable);
+	_dst_pte = make_huge_pte(dst_vma, &folio->page,
+				 !wp_enabled && !(is_continue && !vm_shared));
 	/*
 	 * Always mark UFFDIO_COPY page dirty; note that this may not be
 	 * extremely important for hugetlbfs for now since swapping is not
@@ -7406,7 +7423,24 @@ __weak unsigned long hugetlb_mask_last_page(struct hstate *h)
 
 #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
 
-bool isolate_hugetlb(struct folio *folio, struct list_head *list)
+/**
+ * folio_isolate_hugetlb - try to isolate an allocated hugetlb folio
+ * @folio: the folio to isolate
+ * @list: the list to add the folio to on success
+ *
+ * Isolate an allocated (refcount > 0) hugetlb folio, marking it as
+ * isolated/non-migratable, and moving it from the active list to the
+ * given list.
+ *
+ * Isolation will fail if @folio is not an allocated hugetlb folio, or if
+ * it is already isolated/non-migratable.
+ *
+ * On success, an additional folio reference is taken that must be dropped
+ * using folio_putback_hugetlb() to undo the isolation.
+ *
+ * Return: True if isolation worked, otherwise False.
+ */
+bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list)
 {
 	bool ret = true;
 
@@ -7454,7 +7488,18 @@ int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 	return ret;
 }
 
-void folio_putback_active_hugetlb(struct folio *folio)
+/**
+ * folio_putback_hugetlb - unisolate a hugetlb folio
+ * @folio: the isolated hugetlb folio
+ *
+ * Putback/un-isolate the hugetlb folio that was previous isolated using
+ * folio_isolate_hugetlb(): marking it non-isolated/migratable and putting it
+ * back onto the active list.
+ *
+ * Will drop the additional folio reference obtained through
+ * folio_isolate_hugetlb().
+ */
+void folio_putback_hugetlb(struct folio *folio)
 {
 	spin_lock_irq(&hugetlb_lock);
 	folio_set_hugetlb_migratable(folio);
@@ -7501,6 +7546,16 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
 		}
 		spin_unlock_irq(&hugetlb_lock);
 	}
+
+	/*
+	 * Our old folio is isolated and has "migratable" cleared until it
+	 * is putback. As migration succeeded, set the new folio "migratable"
+	 * and add it to the active list.
+	 */
+	spin_lock_irq(&hugetlb_lock);
+	folio_set_hugetlb_migratable(new_folio);
+	list_move_tail(&new_folio->lru, &(folio_hstate(new_folio))->hugepage_activelist);
+	spin_unlock_irq(&hugetlb_lock);
 }
 
 static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index e716c4671a15..bb9578bd99f9 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -195,24 +195,23 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
  * cannot fail.
  */
 static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
-				       struct page *page)
+				       struct folio *folio)
 {
 	unsigned int nr_pages;
 	struct page_counter *counter;
-	struct hugetlb_cgroup *page_hcg;
+	struct hugetlb_cgroup *hcg;
 	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
-	struct folio *folio = page_folio(page);
 
-	page_hcg = hugetlb_cgroup_from_folio(folio);
+	hcg = hugetlb_cgroup_from_folio(folio);
 	/*
 	 * We can have pages in active list without any cgroup
 	 * ie, hugepage with less than 3 pages. We can safely
 	 * ignore those pages.
 	 */
-	if (!page_hcg || page_hcg != h_cg)
+	if (!hcg || hcg != h_cg)
 		goto out;
 
-	nr_pages = compound_nr(page);
+	nr_pages = folio_nr_pages(folio);
 	if (!parent) {
 		parent = root_h_cgroup;
 		/* root has no limit */
@@ -235,13 +234,13 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css)
 {
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
 	struct hstate *h;
-	struct page *page;
+	struct folio *folio;
 
 	do {
 		for_each_hstate(h) {
 			spin_lock_irq(&hugetlb_lock);
-			list_for_each_entry(page, &h->hugepage_activelist, lru)
-				hugetlb_cgroup_move_parent(hstate_index(h), h_cg, page);
+			list_for_each_entry(folio, &h->hugepage_activelist, lru)
+				hugetlb_cgroup_move_parent(hstate_index(h), h_cg, folio);
 
 			spin_unlock_irq(&hugetlb_lock);
 		}
@@ -917,7 +916,6 @@ void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio)
 	set_hugetlb_cgroup_rsvd(new_folio, h_cg_rsvd);
 	list_move(&new_folio->lru, &h->hugepage_activelist);
 	spin_unlock_irq(&hugetlb_lock);
-	return;
 }
 
 static struct cftype hugetlb_files[] = {
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 57b7f591eee8..7735972add01 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -693,7 +693,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
-static struct ctl_table hugetlb_vmemmap_sysctls[] = {
+static const struct ctl_table hugetlb_vmemmap_sysctls[] = {
 	{
 		.procname	= "hugetlb_optimize_vmemmap",
 		.data		= &vmemmap_optimize_enabled,
diff --git a/mm/internal.h b/mm/internal.h
index 9826f7dce607..109ef30fee11 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -392,6 +392,8 @@ void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
 			     struct zap_details *details);
+int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
+			   gfp_t gfp);
 
 void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
 		unsigned int order);
@@ -735,15 +737,30 @@ static inline void prep_compound_tail(struct page *head, int tail_idx)
 
 extern void prep_compound_page(struct page *page, unsigned int order);
 
-extern void post_alloc_hook(struct page *page, unsigned int order,
-					gfp_t gfp_flags);
+void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags);
 extern bool free_pages_prepare(struct page *page, unsigned int order);
 
 extern int user_min_free_kbytes;
 
-void free_unref_page(struct page *page, unsigned int order);
+struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid,
+		nodemask_t *);
+#define __alloc_frozen_pages(...) \
+	alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__))
+void free_frozen_pages(struct page *page, unsigned int order);
 void free_unref_folios(struct folio_batch *fbatch);
 
+#ifdef CONFIG_NUMA
+struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order);
+#else
+static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order)
+{
+	return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL);
+}
+#endif
+
+#define alloc_frozen_pages(...) \
+	alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__))
+
 extern void zone_pcp_reset(struct zone *zone);
 extern void zone_pcp_disable(struct zone *zone);
 extern void zone_pcp_enable(struct zone *zone);
@@ -824,10 +841,6 @@ int
 isolate_migratepages_range(struct compact_control *cc,
 			   unsigned long low_pfn, unsigned long end_pfn);
 
-int __alloc_contig_migrate_range(struct compact_control *cc,
-					unsigned long start, unsigned long end,
-					int migratetype);
-
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void init_cma_reserved_pageblock(struct page *page);
 
@@ -1440,22 +1453,6 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn,
 unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg,
 			  int priority);
 
-#ifdef CONFIG_64BIT
-static inline int can_do_mseal(unsigned long flags)
-{
-	if (flags)
-		return -EINVAL;
-
-	return 0;
-}
-
-#else
-static inline int can_do_mseal(unsigned long flags)
-{
-	return -EPERM;
-}
-#endif
-
 #ifdef CONFIG_SHRINKER_DEBUG
 static inline __printf(2, 0) int shrinker_debugfs_name_alloc(
 			struct shrinker *shrinker, const char *fmt, va_list ap)
@@ -1530,4 +1527,23 @@ int walk_page_range_mm(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
 
+/* pt_reclaim.c */
+bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval);
+void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb,
+	      pmd_t pmdval);
+void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr,
+		     struct mmu_gather *tlb);
+
+#ifdef CONFIG_PT_RECLAIM
+bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
+			   struct zap_details *details);
+#else
+static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
+					 struct zap_details *details)
+{
+	return false;
+}
+#endif /* CONFIG_PT_RECLAIM */
+
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c
index 8b9e348113b1..d54e89f8c3e7 100644
--- a/mm/kasan/generic.c
+++ b/mm/kasan/generic.c
@@ -524,7 +524,11 @@ size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object)
 			sizeof(struct kasan_free_meta) : 0);
 }
 
-static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
+/*
+ * This function avoids dynamic memory allocations and thus can be called from
+ * contexts that do not allow allocating memory.
+ */
+void kasan_record_aux_stack(void *addr)
 {
 	struct slab *slab = kasan_addr_to_slab(addr);
 	struct kmem_cache *cache;
@@ -541,17 +545,7 @@ static void __kasan_record_aux_stack(void *addr, depot_flags_t depot_flags)
 		return;
 
 	alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0];
-	alloc_meta->aux_stack[0] = kasan_save_stack(0, depot_flags);
-}
-
-void kasan_record_aux_stack(void *addr)
-{
-	return __kasan_record_aux_stack(addr, STACK_DEPOT_FLAG_CAN_ALLOC);
-}
-
-void kasan_record_aux_stack_noalloc(void *addr)
-{
-	return __kasan_record_aux_stack(addr, 0);
+	alloc_meta->aux_stack[0] = kasan_save_stack(0, 0);
 }
 
 void kasan_save_alloc_info(struct kmem_cache *cache, void *object, gfp_t flags)
diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
index ccd66c7a4081..9a6927394b54 100644
--- a/mm/kasan/hw_tags.c
+++ b/mm/kasan/hw_tags.c
@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/static_key.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -263,8 +264,8 @@ void __init kasan_init_hw_tags(void)
 
 	pr_info("KernelAddressSanitizer initialized (hw-tags, mode=%s, vmalloc=%s, stacktrace=%s)\n",
 		kasan_mode_info(),
-		kasan_vmalloc_enabled() ? "on" : "off",
-		kasan_stack_collection_enabled() ? "on" : "off");
+		str_on_off(kasan_vmalloc_enabled()),
+		str_on_off(kasan_stack_collection_enabled()));
 }
 
 #ifdef CONFIG_KASAN_VMALLOC
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index b7e4b81421b3..129178be5e64 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -501,18 +501,18 @@ static inline bool kasan_byte_accessible(const void *addr)
 
 /**
  * kasan_poison - mark the memory range as inaccessible
- * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE
- * @size - range size, must be aligned to KASAN_GRANULE_SIZE
- * @value - value that's written to metadata for the range
- * @init - whether to initialize the memory range (only for hardware tag-based)
+ * @addr: range start address, must be aligned to KASAN_GRANULE_SIZE
+ * @size: range size, must be aligned to KASAN_GRANULE_SIZE
+ * @value: value that's written to metadata for the range
+ * @init: whether to initialize the memory range (only for hardware tag-based)
  */
 void kasan_poison(const void *addr, size_t size, u8 value, bool init);
 
 /**
  * kasan_unpoison - mark the memory range as accessible
- * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE
- * @size - range size, can be unaligned
- * @init - whether to initialize the memory range (only for hardware tag-based)
+ * @addr: range start address, must be aligned to KASAN_GRANULE_SIZE
+ * @size: range size, can be unaligned
+ * @init: whether to initialize the memory range (only for hardware tag-based)
  *
  * For the tag-based modes, the @size gets aligned to KASAN_GRANULE_SIZE before
  * marking the range.
@@ -530,8 +530,8 @@ bool kasan_byte_accessible(const void *addr);
 /**
  * kasan_poison_last_granule - mark the last granule of the memory range as
  * inaccessible
- * @addr - range start address, must be aligned to KASAN_GRANULE_SIZE
- * @size - range size
+ * @address: range start address, must be aligned to KASAN_GRANULE_SIZE
+ * @size: range size
  *
  * This function is only available for the generic mode, as it's the only mode
  * that has partially poisoned memory granules.
diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c
index 99d4ff0ed57a..59d673400085 100644
--- a/mm/kasan/kasan_test_c.c
+++ b/mm/kasan/kasan_test_c.c
@@ -47,8 +47,8 @@ static struct {
  * Some tests use these global variables to store return values from function
  * calls that could otherwise be eliminated by the compiler as dead code.
  */
-void *kasan_ptr_result;
-int kasan_int_result;
+static volatile void *kasan_ptr_result;
+static volatile int kasan_int_result;
 
 /* Probe for console output: obtains test_status lines of interest. */
 static void probe_console(void *ignore, const char *buf, size_t len)
diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c
index 220b5d4c6876..b9382b5b6a37 100644
--- a/mm/kasan/sw_tags.c
+++ b/mm/kasan/sw_tags.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 #include <linux/bug.h>
@@ -45,7 +46,7 @@ void __init kasan_init_sw_tags(void)
 	kasan_init_tags();
 
 	pr_info("KernelAddressSanitizer initialized (sw-tags, stacktrace=%s)\n",
-		kasan_stack_collection_enabled() ? "on" : "off");
+		str_on_off(kasan_stack_collection_enabled()));
 }
 
 /*
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 67fc321db79b..102048821c22 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -21,6 +21,7 @@
 #include <linux/log2.h>
 #include <linux/memblock.h>
 #include <linux/moduleparam.h>
+#include <linux/nodemask.h>
 #include <linux/notifier.h>
 #include <linux/panic_notifier.h>
 #include <linux/random.h>
@@ -1084,6 +1085,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
 	 * properties (e.g. reside in DMAable memory).
 	 */
 	if ((flags & GFP_ZONEMASK) ||
+	    ((flags & __GFP_THISNODE) && num_online_nodes() > 1) ||
 	    (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) {
 		atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]);
 		return NULL;
diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c
index f65fb182466d..00034e37bc9f 100644
--- a/mm/kfence/kfence_test.c
+++ b/mm/kfence/kfence_test.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/tracepoint.h>
 #include <trace/events/printk.h>
 
@@ -88,7 +89,7 @@ struct expect_report {
 
 static const char *get_access_type(const struct expect_report *r)
 {
-	return r->is_write ? "write" : "read";
+	return str_write_read(r->is_write);
 }
 
 /* Check observed report matches information in @r. */
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index 6370c5207d1a..10e6802a2edf 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -16,6 +16,7 @@
 #include <linux/sprintf.h>
 #include <linux/stacktrace.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/sched/clock.h>
 #include <trace/events/error_report.h>
 
@@ -184,7 +185,7 @@ static void print_diff_canary(unsigned long address, size_t bytes_to_show,
 
 static const char *get_access_type(bool is_write)
 {
-	return is_write ? "write" : "read";
+	return str_write_read(is_write);
 }
 
 void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs,
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index bad1e130eda8..5f0be134141e 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -948,17 +948,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 	return SCAN_SUCCEED;
 }
 
-static int find_pmd_or_thp_or_none(struct mm_struct *mm,
-				   unsigned long address,
-				   pmd_t **pmd)
+static inline int check_pmd_state(pmd_t *pmd)
 {
-	pmd_t pmde;
+	pmd_t pmde = pmdp_get_lockless(pmd);
 
-	*pmd = mm_find_pmd(mm, address);
-	if (!*pmd)
-		return SCAN_PMD_NULL;
-
-	pmde = pmdp_get_lockless(*pmd);
 	if (pmd_none(pmde))
 		return SCAN_PMD_NONE;
 	if (!pmd_present(pmde))
@@ -972,6 +965,17 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm,
 	return SCAN_SUCCEED;
 }
 
+static int find_pmd_or_thp_or_none(struct mm_struct *mm,
+				   unsigned long address,
+				   pmd_t **pmd)
+{
+	*pmd = mm_find_pmd(mm, address);
+	if (!*pmd)
+		return SCAN_PMD_NULL;
+
+	return check_pmd_state(*pmd);
+}
+
 static int check_pmd_still_valid(struct mm_struct *mm,
 				 unsigned long address,
 				 pmd_t *pmd)
@@ -1721,7 +1725,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		pmd_t *pmd, pgt_pmd;
 		spinlock_t *pml;
 		spinlock_t *ptl;
-		bool skipped_uffd = false;
+		bool success = false;
 
 		/*
 		 * Check vma->anon_vma to exclude MAP_PRIVATE mappings that
@@ -1758,6 +1762,19 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		mmu_notifier_invalidate_range_start(&range);
 
 		pml = pmd_lock(mm, pmd);
+		/*
+		 * The lock of new_folio is still held, we will be blocked in
+		 * the page fault path, which prevents the pte entries from
+		 * being set again. So even though the old empty PTE page may be
+		 * concurrently freed and a new PTE page is filled into the pmd
+		 * entry, it is still empty and can be removed.
+		 *
+		 * So here we only need to recheck if the state of pmd entry
+		 * still meets our requirements, rather than checking pmd_same()
+		 * like elsewhere.
+		 */
+		if (check_pmd_state(pmd) != SCAN_SUCCEED)
+			goto drop_pml;
 		ptl = pte_lockptr(mm, pmd);
 		if (ptl != pml)
 			spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
@@ -1771,20 +1788,20 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * repeating the anon_vma check protects from one category,
 		 * and repeating the userfaultfd_wp() check from another.
 		 */
-		if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) {
-			skipped_uffd = true;
-		} else {
+		if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) {
 			pgt_pmd = pmdp_collapse_flush(vma, addr, pmd);
 			pmdp_get_lockless_sync();
+			success = true;
 		}
 
 		if (ptl != pml)
 			spin_unlock(ptl);
+drop_pml:
 		spin_unlock(pml);
 
 		mmu_notifier_invalidate_range_end(&range);
 
-		if (!skipped_uffd) {
+		if (success) {
 			mm_dec_nr_ptes(mm);
 			page_table_check_pte_clear_range(mm, addr, pgt_pmd);
 			pte_free_defer(mm, pmd_pgtable(pgt_pmd));
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 820ba3b5cbfc..c6ed68604136 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1689,7 +1689,7 @@ static void kmemleak_scan(void)
 			unsigned long phys = object->pointer;
 
 			if (PHYS_PFN(phys) < min_low_pfn ||
-			    PHYS_PFN(phys + object->size) >= max_low_pfn)
+			    PHYS_PFN(phys + object->size) > max_low_pfn)
 				__paint_it(object, KMEMLEAK_BLACK);
 		}
 
@@ -1855,7 +1855,7 @@ static int kmemleak_scan_thread(void *arg)
 	 * Wait before the first scan to allow the system to fully initialize.
 	 */
 	if (first_run) {
-		signed long timeout = msecs_to_jiffies(SECS_FIRST_SCAN * 1000);
+		signed long timeout = secs_to_jiffies(SECS_FIRST_SCAN);
 		first_run = 0;
 		while (timeout && !kthread_should_stop())
 			timeout = schedule_timeout_interruptible(timeout);
@@ -2241,7 +2241,7 @@ void __init kmemleak_init(void)
 		return;
 
 	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
-	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
+	jiffies_scan_wait = secs_to_jiffies(SECS_SCAN_WAIT);
 
 	object_cache = KMEM_CACHE(kmemleak_object, SLAB_NOLEAKTRACE);
 	scan_area_cache = KMEM_CACHE(kmemleak_scan_area, SLAB_NOLEAKTRACE);
diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c
index 9c58f081d84f..1bb505a08415 100644
--- a/mm/kmsan/shadow.c
+++ b/mm/kmsan/shadow.c
@@ -280,12 +280,8 @@ void __init kmsan_init_alloc_meta_for_range(void *start, void *end)
 
 	start = (void *)PAGE_ALIGN_DOWN((u64)start);
 	size = PAGE_ALIGN((u64)end - (u64)start);
-	shadow = memblock_alloc(size, PAGE_SIZE);
-	origin = memblock_alloc(size, PAGE_SIZE);
-
-	if (!shadow || !origin)
-		panic("%s: Failed to allocate metadata memory for early boot range of size %llu",
-		      __func__, size);
+	shadow = memblock_alloc_or_panic(size, PAGE_SIZE);
+	origin = memblock_alloc_or_panic(size, PAGE_SIZE);
 
 	for (u64 addr = 0; addr < size; addr += PAGE_SIZE) {
 		page = virt_to_page_or_null((char *)start + addr);
diff --git a/mm/ksm.c b/mm/ksm.c
index 31a9bc365437..8be2b144fefd 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -3262,6 +3262,25 @@ static void wait_while_offlining(void)
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 #ifdef CONFIG_PROC_FS
+/*
+ * The process is mergeable only if any VMA is currently
+ * applicable to KSM.
+ *
+ * The mmap lock must be held in read mode.
+ */
+bool ksm_process_mergeable(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma;
+
+	mmap_assert_locked(mm);
+	VMA_ITERATOR(vmi, mm, 0);
+	for_each_vma(vmi, vma)
+		if (vma->vm_flags & VM_MERGEABLE)
+			return true;
+
+	return false;
+}
+
 long ksm_process_profit(struct mm_struct *mm)
 {
 	return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE -
diff --git a/mm/madvise.c b/mm/madvise.c
index 0ceae57da7da..49f3a75046f6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -851,7 +851,12 @@ static int madvise_free_single_vma(struct vm_area_struct *vma,
 static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
 					unsigned long start, unsigned long end)
 {
-	zap_page_range_single(vma, start, end - start, NULL);
+	struct zap_details details = {
+		.reclaim_pt = true,
+		.even_cows = true,
+	};
+
+	zap_page_range_single(vma, start, end - start, &details);
 	return 0;
 }
 
diff --git a/mm/memblock.c b/mm/memblock.c
index 095c18b5c430..95af35fd1389 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1692,6 +1692,26 @@ void * __init memblock_alloc_try_nid(
 }
 
 /**
+ * __memblock_alloc_or_panic - Try to allocate memory and panic on failure
+ * @size: size of memory block to be allocated in bytes
+ * @align: alignment of the region and block's size
+ * @func: caller func name
+ *
+ * This function attempts to allocate memory using memblock_alloc,
+ * and in case of failure, it calls panic with the formatted message.
+ * This function should not be used directly, please use the macro memblock_alloc_or_panic.
+ */
+void *__init __memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align,
+				       const char *func)
+{
+	void *addr = memblock_alloc(size, align);
+
+	if (unlikely(!addr))
+		panic("%s: Failed to allocate %pap bytes\n", func, &size);
+	return addr;
+}
+
+/**
  * memblock_free_late - free pages directly to buddy allocator
  * @base: phys starting address of the  boot memory block
  * @size: size of the boot memory block in bytes
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index a071fa43d479..2be6b9112808 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -899,7 +899,7 @@ static void memcg_event_remove(struct work_struct *work)
  *
  * Called with wqh->lock held and interrupts disabled.
  */
-static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode,
+static int memcg_event_wake(wait_queue_entry_t *wait, unsigned int mode,
 			    int sync, void *key)
 {
 	struct mem_cgroup_event *event =
@@ -1040,13 +1040,13 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	} else if (!strcmp(name, "memory.oom_control")) {
 		pr_warn_once("oom_control is deprecated and will be removed. "
 			     "Please report your usecase to linux-mm-@kvack.org"
-			     " if you depend on this functionality. \n");
+			     " if you depend on this functionality.\n");
 		event->register_event = mem_cgroup_oom_register_event;
 		event->unregister_event = mem_cgroup_oom_unregister_event;
 	} else if (!strcmp(name, "memory.pressure_level")) {
 		pr_warn_once("pressure_level is deprecated and will be removed. "
 			     "Please report your usecase to linux-mm-@kvack.org "
-			     "if you depend on this functionality. \n");
+			     "if you depend on this functionality.\n");
 		event->register_event = vmpressure_register_event;
 		event->unregister_event = vmpressure_unregister_event;
 	} else if (!strcmp(name, "memory.memsw.usage_in_bytes")) {
@@ -1134,8 +1134,8 @@ static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
 			failed = iter;
 			mem_cgroup_iter_break(memcg, iter);
 			break;
-		} else
-			iter->oom_lock = true;
+		}
+		iter->oom_lock = true;
 	}
 
 	if (failed) {
@@ -1202,7 +1202,7 @@ struct oom_wait_info {
 };
 
 static int memcg_oom_wake_function(wait_queue_entry_t *wait,
-	unsigned mode, int sync, void *arg)
+	unsigned int mode, int sync, void *arg)
 {
 	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
 	struct mem_cgroup *oom_wait_memcg;
@@ -1644,7 +1644,7 @@ static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 	unsigned long nr = 0;
 	enum lru_list lru;
 
-	VM_BUG_ON((unsigned)nid >= nr_node_ids);
+	VM_BUG_ON((unsigned int)nid >= nr_node_ids);
 
 	for_each_lru(lru) {
 		if (!(BIT(lru) & lru_mask))
@@ -1881,7 +1881,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
 
 	pr_warn_once("oom_control is deprecated and will be removed. "
 		     "Please report your usecase to linux-mm-@kvack.org if you "
-		     "depend on this functionality. \n");
+		     "depend on this functionality.\n");
 
 	/* cannot set to root cgroup and only 0 and 1 are allowed */
 	if (mem_cgroup_is_root(memcg) || !((val == 0) || (val == 1)))
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7b3503d12aaf..46f8b372d212 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1161,6 +1161,7 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup *iter;
 	int ret = 0;
+	int i = 0;
 
 	BUG_ON(mem_cgroup_is_root(memcg));
 
@@ -1169,8 +1170,12 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 		struct task_struct *task;
 
 		css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it);
-		while (!ret && (task = css_task_iter_next(&it)))
+		while (!ret && (task = css_task_iter_next(&it))) {
+			/* Avoid potential softlockup warning */
+			if ((++i & 1023) == 0)
+				cond_resched();
 			ret = fn(task, arg);
+		}
 		css_task_iter_end(&it);
 		if (ret) {
 			mem_cgroup_iter_break(memcg, iter);
@@ -1448,6 +1453,18 @@ unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item)
 		memcg_page_state_output_unit(item);
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static bool memcg_accounts_hugetlb(void)
+{
+	return cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING;
+}
+#else /* CONFIG_HUGETLB_PAGE */
+static bool memcg_accounts_hugetlb(void)
+{
+	return false;
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
 static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 {
 	int i;
@@ -1469,7 +1486,7 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 
 #ifdef CONFIG_HUGETLB_PAGE
 		if (unlikely(memory_stats[i].idx == NR_HUGETLB) &&
-		    !(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING))
+			!memcg_accounts_hugetlb())
 			continue;
 #endif
 		size = memcg_page_state_output(memcg, memory_stats[i].idx);
@@ -2371,21 +2388,6 @@ done_restock:
 	return 0;
 }
 
-/**
- * mem_cgroup_cancel_charge() - cancel an uncommitted try_charge() call.
- * @memcg: memcg previously charged.
- * @nr_pages: number of pages previously charged.
- */
-void mem_cgroup_cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
-{
-	if (mem_cgroup_is_root(memcg))
-		return;
-
-	page_counter_uncharge(&memcg->memory, nr_pages);
-	if (do_memsw_account())
-		page_counter_uncharge(&memcg->memsw, nr_pages);
-}
-
 static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 {
 	VM_BUG_ON_FOLIO(folio_memcg_charged(folio), folio);
@@ -2399,18 +2401,6 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
 	folio->memcg_data = (unsigned long)memcg;
 }
 
-/**
- * mem_cgroup_commit_charge - commit a previously successful try_charge().
- * @folio: folio to commit the charge to.
- * @memcg: memcg previously charged.
- */
-void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg)
-{
-	css_get(&memcg->css);
-	commit_charge(folio, memcg);
-	memcg1_commit_charge(folio, memcg);
-}
-
 static inline void __mod_objcg_mlstate(struct obj_cgroup *objcg,
 				       struct pglist_data *pgdat,
 				       enum node_stat_item idx, int nr)
@@ -4498,7 +4488,9 @@ static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
 	if (ret)
 		goto out;
 
-	mem_cgroup_commit_charge(folio, memcg);
+	css_get(&memcg->css);
+	commit_charge(folio, memcg);
+	memcg1_commit_charge(folio, memcg);
 out:
 	return ret;
 }
@@ -4516,38 +4508,37 @@ int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
 }
 
 /**
- * mem_cgroup_hugetlb_try_charge - try to charge the memcg for a hugetlb folio
- * @memcg: memcg to charge.
- * @gfp: reclaim mode.
- * @nr_pages: number of pages to charge.
- *
- * This function is called when allocating a huge page folio to determine if
- * the memcg has the capacity for it. It does not commit the charge yet,
- * as the hugetlb folio itself has not been obtained from the hugetlb pool.
+ * mem_cgroup_charge_hugetlb - charge the memcg for a hugetlb folio
+ * @folio: folio being charged
+ * @gfp: reclaim mode
  *
- * Once we have obtained the hugetlb folio, we can call
- * mem_cgroup_commit_charge() to commit the charge. If we fail to obtain the
- * folio, we should instead call mem_cgroup_cancel_charge() to undo the effect
- * of try_charge().
+ * This function is called when allocating a huge page folio, after the page has
+ * already been obtained and charged to the appropriate hugetlb cgroup
+ * controller (if it is enabled).
  *
- * Returns 0 on success. Otherwise, an error code is returned.
+ * Returns ENOMEM if the memcg is already full.
+ * Returns 0 if either the charge was successful, or if we skip the charging.
  */
-int mem_cgroup_hugetlb_try_charge(struct mem_cgroup *memcg, gfp_t gfp,
-			long nr_pages)
+int mem_cgroup_charge_hugetlb(struct folio *folio, gfp_t gfp)
 {
+	struct mem_cgroup *memcg = get_mem_cgroup_from_current();
+	int ret = 0;
+
 	/*
-	 * If hugetlb memcg charging is not enabled, do not fail hugetlb allocation,
-	 * but do not attempt to commit charge later (or cancel on error) either.
+	 * Even memcg does not account for hugetlb, we still want to update
+	 * system-level stats via lruvec_stat_mod_folio. Return 0, and skip
+	 * charging the memcg.
 	 */
-	if (mem_cgroup_disabled() || !memcg ||
-		!cgroup_subsys_on_dfl(memory_cgrp_subsys) ||
-		!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING))
-		return -EOPNOTSUPP;
+	if (mem_cgroup_disabled() || !memcg_accounts_hugetlb() ||
+		!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		goto out;
 
-	if (try_charge(memcg, gfp, nr_pages))
-		return -ENOMEM;
+	if (charge_memcg(folio, memcg, gfp))
+		ret = -ENOMEM;
 
-	return 0;
+out:
+	mem_cgroup_put(memcg);
+	return ret;
 }
 
 /**
@@ -4609,7 +4600,7 @@ void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
 	 * correspond 1:1 to page and swap slot lifetimes: we charge the
 	 * page to memory here, and uncharge swap when the slot is freed.
 	 */
-	if (!mem_cgroup_disabled() && do_memsw_account()) {
+	if (do_memsw_account()) {
 		/*
 		 * The swap entry might not get freed for a long time,
 		 * let's not wait for it.  The page already received a
@@ -4973,7 +4964,6 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 {
 	struct mem_cgroup *memcg, *swap_memcg;
 	unsigned int nr_entries;
-	unsigned short oldid;
 
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 	VM_BUG_ON_FOLIO(folio_ref_count(folio), folio);
@@ -5000,11 +4990,10 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 	/* Get references for the tail pages, too */
 	if (nr_entries > 1)
 		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
-	oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg),
-				   nr_entries);
-	VM_BUG_ON_FOLIO(oldid, folio);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
+	swap_cgroup_record(folio, entry);
+
 	folio_unqueue_deferred_split(folio);
 	folio->memcg_data = 0;
 
@@ -5035,7 +5024,6 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 	unsigned int nr_pages = folio_nr_pages(folio);
 	struct page_counter *counter;
 	struct mem_cgroup *memcg;
-	unsigned short oldid;
 
 	if (do_memsw_account())
 		return 0;
@@ -5064,10 +5052,10 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 	/* Get references for the tail pages, too */
 	if (nr_pages > 1)
 		mem_cgroup_id_get_many(memcg, nr_pages - 1);
-	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
-	VM_BUG_ON_FOLIO(oldid, folio);
 	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
+	swap_cgroup_record(folio, entry);
+
 	return 0;
 }
 
@@ -5081,7 +5069,7 @@ void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
 	struct mem_cgroup *memcg;
 	unsigned short id;
 
-	id = swap_cgroup_record(entry, 0, nr_pages);
+	id = swap_cgroup_clear(entry, nr_pages);
 	rcu_read_lock();
 	memcg = mem_cgroup_from_id(id);
 	if (memcg) {
diff --git a/mm/memfd.c b/mm/memfd.c
index 35a370d75c9a..37f7be57c2f5 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping)
 	return error;
 }
 
-unsigned int *memfd_file_seals_ptr(struct file *file)
+static unsigned int *memfd_file_seals_ptr(struct file *file)
 {
 	if (shmem_file(file))
 		return &SHMEM_I(file_inode(file))->seals;
@@ -327,15 +327,51 @@ static int check_sysctl_memfd_noexec(unsigned int *flags)
 	return 0;
 }
 
-SYSCALL_DEFINE2(memfd_create,
-		const char __user *, uname,
-		unsigned int, flags)
+static inline bool is_write_sealed(unsigned int seals)
 {
-	unsigned int *file_seals;
-	struct file *file;
-	int fd, error;
-	char *name;
-	long len;
+	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
+}
+
+static int check_write_seal(unsigned long *vm_flags_ptr)
+{
+	unsigned long vm_flags = *vm_flags_ptr;
+	unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE);
+
+	/* If a private matting then writability is irrelevant. */
+	if (!(mask & VM_SHARED))
+		return 0;
+
+	/*
+	 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
+	 * write seals are active.
+	 */
+	if (mask & VM_WRITE)
+		return -EPERM;
+
+	/*
+	 * This is a read-only mapping, disallow mprotect() from making a
+	 * write-sealed mapping writable in future.
+	 */
+	*vm_flags_ptr &= ~VM_MAYWRITE;
+
+	return 0;
+}
+
+int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr)
+{
+	int err = 0;
+	unsigned int *seals_ptr = memfd_file_seals_ptr(file);
+	unsigned int seals = seals_ptr ? *seals_ptr : 0;
+
+	if (is_write_sealed(seals))
+		err = check_write_seal(vm_flags_ptr);
+
+	return err;
+}
+
+static int sanitize_flags(unsigned int *flags_ptr)
+{
+	unsigned int flags = *flags_ptr;
 
 	if (!(flags & MFD_HUGETLB)) {
 		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
@@ -351,50 +387,52 @@ SYSCALL_DEFINE2(memfd_create,
 	if ((flags & MFD_EXEC) && (flags & MFD_NOEXEC_SEAL))
 		return -EINVAL;
 
-	error = check_sysctl_memfd_noexec(&flags);
-	if (error < 0)
-		return error;
+	return check_sysctl_memfd_noexec(flags_ptr);
+}
 
-	/* length includes terminating zero */
-	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
-	if (len <= 0)
-		return -EFAULT;
-	if (len > MFD_NAME_MAX_LEN + 1)
-		return -EINVAL;
+static char *alloc_name(const char __user *uname)
+{
+	int error;
+	char *name;
+	long len;
 
-	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL);
+	name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
 	if (!name)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	strcpy(name, MFD_NAME_PREFIX);
-	if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) {
+	/* returned length does not include terminating zero */
+	len = strncpy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, MFD_NAME_MAX_LEN + 1);
+	if (len < 0) {
 		error = -EFAULT;
 		goto err_name;
-	}
-
-	/* terminating-zero may have changed after strnlen_user() returned */
-	if (name[len + MFD_NAME_PREFIX_LEN - 1]) {
-		error = -EFAULT;
+	} else if (len > MFD_NAME_MAX_LEN) {
+		error = -EINVAL;
 		goto err_name;
 	}
 
-	fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
-	if (fd < 0) {
-		error = fd;
-		goto err_name;
-	}
+	return name;
+
+err_name:
+	kfree(name);
+	return ERR_PTR(error);
+}
+
+static struct file *alloc_file(const char *name, unsigned int flags)
+{
+	unsigned int *file_seals;
+	struct file *file;
 
 	if (flags & MFD_HUGETLB) {
 		file = hugetlb_file_setup(name, 0, VM_NORESERVE,
 					HUGETLB_ANONHUGE_INODE,
 					(flags >> MFD_HUGE_SHIFT) &
 					MFD_HUGE_MASK);
-	} else
+	} else {
 		file = shmem_file_setup(name, 0, VM_NORESERVE);
-	if (IS_ERR(file)) {
-		error = PTR_ERR(file);
-		goto err_fd;
 	}
+	if (IS_ERR(file))
+		return file;
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	file->f_flags |= O_LARGEFILE;
 
@@ -414,6 +452,37 @@ SYSCALL_DEFINE2(memfd_create,
 			*file_seals &= ~F_SEAL_SEAL;
 	}
 
+	return file;
+}
+
+SYSCALL_DEFINE2(memfd_create,
+		const char __user *, uname,
+		unsigned int, flags)
+{
+	struct file *file;
+	int fd, error;
+	char *name;
+
+	error = sanitize_flags(&flags);
+	if (error < 0)
+		return error;
+
+	name = alloc_name(uname);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
+	if (fd < 0) {
+		error = fd;
+		goto err_name;
+	}
+
+	file = alloc_file(name, flags);
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto err_fd;
+	}
+
 	fd_install(fd, file);
 	kfree(name);
 	return fd;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a7b8ccd29b6f..995a15eb67e2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -124,7 +124,7 @@ const struct attribute_group memory_failure_attr_group = {
 	.attrs = memory_failure_attr,
 };
 
-static struct ctl_table memory_failure_table[] = {
+static const struct ctl_table memory_failure_table[] = {
 	{
 		.procname	= "memory_failure_early_kill",
 		.data		= &sysctl_memory_failure_early_kill,
diff --git a/mm/memory.c b/mm/memory.c
index f8bebec145f5..539c0f7c6d54 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1437,7 +1437,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 static inline bool should_zap_cows(struct zap_details *details)
 {
 	/* By default, zap all pages */
-	if (!details)
+	if (!details || details->reclaim_pt)
 		return true;
 
 	/* Or, we zap COWed pages only if the caller wants to */
@@ -1467,34 +1467,42 @@ static inline bool zap_drop_markers(struct zap_details *details)
 /*
  * This function makes sure that we'll replace the none pte with an uffd-wp
  * swap special pte marker when necessary. Must be with the pgtable lock held.
+ *
+ * Returns true if uffd-wp ptes was installed, false otherwise.
  */
-static inline void
+static inline bool
 zap_install_uffd_wp_if_needed(struct vm_area_struct *vma,
 			      unsigned long addr, pte_t *pte, int nr,
 			      struct zap_details *details, pte_t pteval)
 {
+	bool was_installed = false;
+
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
 	/* Zap on anonymous always means dropping everything */
 	if (vma_is_anonymous(vma))
-		return;
+		return false;
 
 	if (zap_drop_markers(details))
-		return;
+		return false;
 
 	for (;;) {
 		/* the PFN in the PTE is irrelevant. */
-		pte_install_uffd_wp_if_needed(vma, addr, pte, pteval);
+		if (pte_install_uffd_wp_if_needed(vma, addr, pte, pteval))
+			was_installed = true;
 		if (--nr == 0)
 			break;
 		pte++;
 		addr += PAGE_SIZE;
 	}
+#endif
+	return was_installed;
 }
 
 static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, struct folio *folio,
 		struct page *page, pte_t *pte, pte_t ptent, unsigned int nr,
 		unsigned long addr, struct zap_details *details, int *rss,
-		bool *force_flush, bool *force_break)
+		bool *force_flush, bool *force_break, bool *any_skipped)
 {
 	struct mm_struct *mm = tlb->mm;
 	bool delay_rmap = false;
@@ -1520,8 +1528,8 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb,
 	arch_check_zapped_pte(vma, ptent);
 	tlb_remove_tlb_entries(tlb, pte, nr, addr);
 	if (unlikely(userfaultfd_pte_wp(vma, ptent)))
-		zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details,
-					      ptent);
+		*any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte,
+							     nr, details, ptent);
 
 	if (!delay_rmap) {
 		folio_remove_rmap_ptes(folio, page, nr, vma);
@@ -1545,7 +1553,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
 		unsigned int max_nr, unsigned long addr,
 		struct zap_details *details, int *rss, bool *force_flush,
-		bool *force_break)
+		bool *force_break, bool *any_skipped)
 {
 	const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
 	struct mm_struct *mm = tlb->mm;
@@ -1560,15 +1568,17 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
 		arch_check_zapped_pte(vma, ptent);
 		tlb_remove_tlb_entry(tlb, pte, addr);
 		if (userfaultfd_pte_wp(vma, ptent))
-			zap_install_uffd_wp_if_needed(vma, addr, pte, 1,
-						      details, ptent);
+			*any_skipped = zap_install_uffd_wp_if_needed(vma, addr,
+						pte, 1, details, ptent);
 		ksm_might_unmap_zero_page(mm, ptent);
 		return 1;
 	}
 
 	folio = page_folio(page);
-	if (unlikely(!should_zap_folio(details, folio)))
+	if (unlikely(!should_zap_folio(details, folio))) {
+		*any_skipped = true;
 		return 1;
+	}
 
 	/*
 	 * Make sure that the common "small folio" case is as fast as possible
@@ -1580,14 +1590,121 @@ static inline int zap_present_ptes(struct mmu_gather *tlb,
 
 		zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr,
 				       addr, details, rss, force_flush,
-				       force_break);
+				       force_break, any_skipped);
 		return nr;
 	}
 	zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, 1, addr,
-			       details, rss, force_flush, force_break);
+			       details, rss, force_flush, force_break, any_skipped);
 	return 1;
 }
 
+static inline int zap_nonpresent_ptes(struct mmu_gather *tlb,
+		struct vm_area_struct *vma, pte_t *pte, pte_t ptent,
+		unsigned int max_nr, unsigned long addr,
+		struct zap_details *details, int *rss, bool *any_skipped)
+{
+	swp_entry_t entry;
+	int nr = 1;
+
+	*any_skipped = true;
+	entry = pte_to_swp_entry(ptent);
+	if (is_device_private_entry(entry) ||
+		is_device_exclusive_entry(entry)) {
+		struct page *page = pfn_swap_entry_to_page(entry);
+		struct folio *folio = page_folio(page);
+
+		if (unlikely(!should_zap_folio(details, folio)))
+			return 1;
+		/*
+		 * Both device private/exclusive mappings should only
+		 * work with anonymous page so far, so we don't need to
+		 * consider uffd-wp bit when zap. For more information,
+		 * see zap_install_uffd_wp_if_needed().
+		 */
+		WARN_ON_ONCE(!vma_is_anonymous(vma));
+		rss[mm_counter(folio)]--;
+		if (is_device_private_entry(entry))
+			folio_remove_rmap_pte(folio, page, vma);
+		folio_put(folio);
+	} else if (!non_swap_entry(entry)) {
+		/* Genuine swap entries, hence a private anon pages */
+		if (!should_zap_cows(details))
+			return 1;
+
+		nr = swap_pte_batch(pte, max_nr, ptent);
+		rss[MM_SWAPENTS] -= nr;
+		free_swap_and_cache_nr(entry, nr);
+	} else if (is_migration_entry(entry)) {
+		struct folio *folio = pfn_swap_entry_folio(entry);
+
+		if (!should_zap_folio(details, folio))
+			return 1;
+		rss[mm_counter(folio)]--;
+	} else if (pte_marker_entry_uffd_wp(entry)) {
+		/*
+		 * For anon: always drop the marker; for file: only
+		 * drop the marker if explicitly requested.
+		 */
+		if (!vma_is_anonymous(vma) && !zap_drop_markers(details))
+			return 1;
+	} else if (is_guard_swp_entry(entry)) {
+		/*
+		 * Ordinary zapping should not remove guard PTE
+		 * markers. Only do so if we should remove PTE markers
+		 * in general.
+		 */
+		if (!zap_drop_markers(details))
+			return 1;
+	} else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) {
+		if (!should_zap_cows(details))
+			return 1;
+	} else {
+		/* We should have covered all the swap entry types */
+		pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
+		WARN_ON_ONCE(1);
+	}
+	clear_not_present_full_ptes(vma->vm_mm, addr, pte, nr, tlb->fullmm);
+	*any_skipped = zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
+
+	return nr;
+}
+
+static inline int do_zap_pte_range(struct mmu_gather *tlb,
+				   struct vm_area_struct *vma, pte_t *pte,
+				   unsigned long addr, unsigned long end,
+				   struct zap_details *details, int *rss,
+				   bool *force_flush, bool *force_break,
+				   bool *any_skipped)
+{
+	pte_t ptent = ptep_get(pte);
+	int max_nr = (end - addr) / PAGE_SIZE;
+	int nr = 0;
+
+	/* Skip all consecutive none ptes */
+	if (pte_none(ptent)) {
+		for (nr = 1; nr < max_nr; nr++) {
+			ptent = ptep_get(pte + nr);
+			if (!pte_none(ptent))
+				break;
+		}
+		max_nr -= nr;
+		if (!max_nr)
+			return nr;
+		pte += nr;
+		addr += nr * PAGE_SIZE;
+	}
+
+	if (pte_present(ptent))
+		nr += zap_present_ptes(tlb, vma, pte, ptent, max_nr, addr,
+				       details, rss, force_flush, force_break,
+				       any_skipped);
+	else
+		nr += zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr,
+					  details, rss, any_skipped);
+
+	return nr;
+}
+
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
@@ -1599,9 +1716,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
-	swp_entry_t entry;
+	pmd_t pmdval;
+	unsigned long start = addr;
+	bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details);
+	bool direct_reclaim = false;
 	int nr;
 
+retry:
 	tlb_change_page_size(tlb, PAGE_SIZE);
 	init_rss_vec(rss);
 	start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
@@ -1611,90 +1732,24 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
 	do {
-		pte_t ptent = ptep_get(pte);
-		struct folio *folio;
-		struct page *page;
-		int max_nr;
-
-		nr = 1;
-		if (pte_none(ptent))
-			continue;
+		bool any_skipped = false;
 
 		if (need_resched())
 			break;
 
-		if (pte_present(ptent)) {
-			max_nr = (end - addr) / PAGE_SIZE;
-			nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr,
-					      addr, details, rss, &force_flush,
-					      &force_break);
-			if (unlikely(force_break)) {
-				addr += nr * PAGE_SIZE;
-				break;
-			}
-			continue;
-		}
-
-		entry = pte_to_swp_entry(ptent);
-		if (is_device_private_entry(entry) ||
-		    is_device_exclusive_entry(entry)) {
-			page = pfn_swap_entry_to_page(entry);
-			folio = page_folio(page);
-			if (unlikely(!should_zap_folio(details, folio)))
-				continue;
-			/*
-			 * Both device private/exclusive mappings should only
-			 * work with anonymous page so far, so we don't need to
-			 * consider uffd-wp bit when zap. For more information,
-			 * see zap_install_uffd_wp_if_needed().
-			 */
-			WARN_ON_ONCE(!vma_is_anonymous(vma));
-			rss[mm_counter(folio)]--;
-			if (is_device_private_entry(entry))
-				folio_remove_rmap_pte(folio, page, vma);
-			folio_put(folio);
-		} else if (!non_swap_entry(entry)) {
-			max_nr = (end - addr) / PAGE_SIZE;
-			nr = swap_pte_batch(pte, max_nr, ptent);
-			/* Genuine swap entries, hence a private anon pages */
-			if (!should_zap_cows(details))
-				continue;
-			rss[MM_SWAPENTS] -= nr;
-			free_swap_and_cache_nr(entry, nr);
-		} else if (is_migration_entry(entry)) {
-			folio = pfn_swap_entry_folio(entry);
-			if (!should_zap_folio(details, folio))
-				continue;
-			rss[mm_counter(folio)]--;
-		} else if (pte_marker_entry_uffd_wp(entry)) {
-			/*
-			 * For anon: always drop the marker; for file: only
-			 * drop the marker if explicitly requested.
-			 */
-			if (!vma_is_anonymous(vma) &&
-			    !zap_drop_markers(details))
-				continue;
-		} else if (is_guard_swp_entry(entry)) {
-			/*
-			 * Ordinary zapping should not remove guard PTE
-			 * markers. Only do so if we should remove PTE markers
-			 * in general.
-			 */
-			if (!zap_drop_markers(details))
-				continue;
-		} else if (is_hwpoison_entry(entry) ||
-			   is_poisoned_swp_entry(entry)) {
-			if (!should_zap_cows(details))
-				continue;
-		} else {
-			/* We should have covered all the swap entry types */
-			pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
-			WARN_ON_ONCE(1);
+		nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss,
+				      &force_flush, &force_break, &any_skipped);
+		if (any_skipped)
+			can_reclaim_pt = false;
+		if (unlikely(force_break)) {
+			addr += nr * PAGE_SIZE;
+			break;
 		}
-		clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);
-		zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
 	} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
 
+	if (can_reclaim_pt && addr == end)
+		direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval);
+
 	add_mm_rss_vec(mm, rss);
 	arch_leave_lazy_mmu_mode();
 
@@ -1714,6 +1769,20 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	if (force_flush)
 		tlb_flush_mmu(tlb);
 
+	if (addr != end) {
+		cond_resched();
+		force_flush = false;
+		force_break = false;
+		goto retry;
+	}
+
+	if (can_reclaim_pt) {
+		if (direct_reclaim)
+			free_pte(mm, start, tlb, pmdval);
+		else
+			try_to_free_pte(mm, pmd, start, tlb);
+	}
+
 	return addr;
 }
 
@@ -1936,7 +2005,6 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
 	struct mmu_notifier_range range;
 	struct mmu_gather tlb;
 
-	lru_add_drain();
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm,
 				address, end);
 	hugetlb_zap_begin(vma, &range.start, &range.end);
@@ -3014,7 +3082,6 @@ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr,
 {
 	return __apply_to_page_range(mm, addr, size, fn, data, false);
 }
-EXPORT_SYMBOL_GPL(apply_to_existing_page_range);
 
 /*
  * handle_pte_fault chooses page fault handler according to an entry which was
@@ -4190,8 +4257,10 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
 			if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm,
 							    gfp, entry))
 				return folio;
+			count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK_CHARGE);
 			folio_put(folio);
 		}
+		count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK);
 		order = next_order(&orders, order);
 	}
 
@@ -5626,7 +5695,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	ignore_writable = true;
 
 	/* Migrate to the requested node */
-	if (!migrate_misplaced_folio(folio, vma, target_nid)) {
+	if (!migrate_misplaced_folio(folio, target_nid)) {
 		nid = target_nid;
 		flags |= TNF_MIGRATED;
 		task_numa_fault(last_cpupid, nid, nr_pages, flags);
@@ -6088,7 +6157,8 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma,
 }
 
 /*
- * By the time we get here, we already hold the mm semaphore
+ * By the time we get here, we already hold either the VMA lock or the
+ * mmap_lock (FAULT_FLAG_VMA_LOCK tells you which).
  *
  * The mmap_lock may have been released depending on flags and our
  * return value.  See filemap_fault() and __folio_lock_or_retry().
@@ -6204,7 +6274,7 @@ static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, struct pt_r
 /*
  * Helper for page fault handling.
  *
- * This is kind of equivalend to "mmap_read_lock()" followed
+ * This is kind of equivalent to "mmap_read_lock()" followed
  * by "find_extend_vma()", except it's a lot more careful about
  * the locking (and will drop the lock on failure).
  *
@@ -6980,7 +7050,8 @@ bool ptlock_alloc(struct ptdesc *ptdesc)
 
 void ptlock_free(struct ptdesc *ptdesc)
 {
-	kmem_cache_free(page_ptl_cachep, ptdesc->ptl);
+	if (ptdesc->ptl)
+		kmem_cache_free(page_ptl_cachep, ptdesc->ptl);
 }
 #endif
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c43b4e7fb298..e3655f07dd6e 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -219,11 +219,30 @@ void put_online_mems(void)
 
 bool movable_node_enabled = false;
 
-#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE
-int mhp_default_online_type = MMOP_OFFLINE;
-#else
-int mhp_default_online_type = MMOP_ONLINE;
-#endif
+static int mhp_default_online_type = -1;
+int mhp_get_default_online_type(void)
+{
+	if (mhp_default_online_type >= 0)
+		return mhp_default_online_type;
+
+	if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE))
+		mhp_default_online_type = MMOP_OFFLINE;
+	else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO))
+		mhp_default_online_type = MMOP_ONLINE;
+	else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL))
+		mhp_default_online_type = MMOP_ONLINE_KERNEL;
+	else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE))
+		mhp_default_online_type = MMOP_ONLINE_MOVABLE;
+	else
+		mhp_default_online_type = MMOP_OFFLINE;
+
+	return mhp_default_online_type;
+}
+
+void mhp_set_default_online_type(int online_type)
+{
+	mhp_default_online_type = online_type;
+}
 
 static int __init setup_memhp_default_state(char *str)
 {
@@ -650,6 +669,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 	 * this and the first chunk to online will be pageblock_nr_pages.
 	 */
 	for (pfn = start_pfn; pfn < end_pfn;) {
+		struct page *page = pfn_to_page(pfn);
 		int order;
 
 		/*
@@ -664,7 +684,14 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 		else
 			order = MAX_PAGE_ORDER;
 
-		(*online_page_callback)(pfn_to_page(pfn), order);
+		/*
+		 * Exposing the page to the buddy by freeing can cause
+		 * issues with debug_pagealloc enabled: some archs don't
+		 * like double-unmappings. So treat them like any pages that
+		 * were allocated from the buddy.
+		 */
+		debug_pagealloc_map_pages(page, 1 << order);
+		(*online_page_callback)(page, order);
 		pfn += (1UL << order);
 	}
 
@@ -1320,7 +1347,7 @@ static int check_hotplug_memory_range(u64 start, u64 size)
 
 static int online_memory_block(struct memory_block *mem, void *arg)
 {
-	mem->online_type = mhp_default_online_type;
+	mem->online_type = mhp_get_default_online_type();
 	return device_online(&mem->dev);
 }
 
@@ -1567,7 +1594,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		merge_system_ram_resource(res);
 
 	/* online pages if requested */
-	if (mhp_default_online_type != MMOP_OFFLINE)
+	if (mhp_get_default_online_type() != MMOP_OFFLINE)
 		walk_memory_blocks(start, size, NULL, online_memory_block);
 
 	return ret;
@@ -1830,7 +1857,7 @@ put_folio:
 		nodemask_t nmask = node_states[N_MEMORY];
 		struct migration_target_control mtc = {
 			.nmask = &nmask,
-			.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+			.gfp_mask = GFP_KERNEL | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
 			.reason = MR_MEMORY_HOTPLUG,
 		};
 		int ret;
@@ -1992,8 +2019,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn,
 				       MIGRATE_MOVABLE,
-				       MEMORY_OFFLINE | REPORT_FAILURE,
-				       GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL);
+				       MEMORY_OFFLINE | REPORT_FAILURE);
 	if (ret) {
 		reason = "failure to isolate range";
 		goto failed_removal_pcplists_disabled;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 162407fbf2bc..bbaadbeeb291 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -647,7 +647,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask,
 	 */
 	if ((flags & MPOL_MF_MOVE_ALL) ||
 	    (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte)))
-		if (!isolate_hugetlb(folio, qp->pagelist))
+		if (!folio_isolate_hugetlb(folio, qp->pagelist))
 			qp->nr_failed++;
 unlock:
 	spin_unlock(ptl);
@@ -2205,9 +2205,9 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
 	 */
 	preferred_gfp = gfp | __GFP_NOWARN;
 	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
-	page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask);
+	page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask);
 	if (!page)
-		page = __alloc_pages_noprof(gfp, order, nid, NULL);
+		page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL);
 
 	return page;
 }
@@ -2222,7 +2222,7 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
  *
  * Return: The page on success or NULL if allocation fails.
  */
-struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
+static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order,
 		struct mempolicy *pol, pgoff_t ilx, int nid)
 {
 	nodemask_t *nodemask;
@@ -2253,8 +2253,9 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
 			 * First, try to allocate THP only on local node, but
 			 * don't reclaim unnecessarily, just compact.
 			 */
-			page = __alloc_pages_node_noprof(nid,
-				gfp | __GFP_THISNODE | __GFP_NORETRY, order);
+			page = __alloc_frozen_pages_noprof(
+				gfp | __GFP_THISNODE | __GFP_NORETRY, order,
+				nid, NULL);
 			if (page || !(gfp & __GFP_DIRECT_RECLAIM))
 				return page;
 			/*
@@ -2266,7 +2267,7 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
 		}
 	}
 
-	page = __alloc_pages_noprof(gfp, order, nid, nodemask);
+	page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask);
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE ||
 		     pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) {
@@ -2285,8 +2286,13 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order,
 struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
 		struct mempolicy *pol, pgoff_t ilx, int nid)
 {
-	return page_rmappable_folio(alloc_pages_mpol_noprof(gfp | __GFP_COMP,
-							order, pol, ilx, nid));
+	struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol,
+			ilx, nid);
+	if (!page)
+		return NULL;
+
+	set_page_refcounted(page);
+	return page_rmappable_folio(page);
 }
 
 /**
@@ -2300,7 +2306,7 @@ struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
  * NUMA policy.  The caller must hold the mmap_lock of the mm_struct of the
  * VMA to prevent it from going away.  Should be used for all allocations
  * for folios that will be mapped into user space, excepting hugetlbfs, and
- * excepting where direct use of alloc_pages_mpol() is more appropriate.
+ * excepting where direct use of folio_alloc_mpol() is more appropriate.
  *
  * Return: The folio on success or NULL if allocation fails.
  */
@@ -2321,6 +2327,21 @@ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct
 }
 EXPORT_SYMBOL(vma_alloc_folio_noprof);
 
+struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order)
+{
+	struct mempolicy *pol = &default_policy;
+
+	/*
+	 * No reference counting needed for current->mempolicy
+	 * nor system default_policy
+	 */
+	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
+		pol = get_task_policy(current);
+
+	return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX,
+				       numa_node_id());
+}
+
 /**
  * alloc_pages - Allocate pages.
  * @gfp: GFP flags.
@@ -2337,17 +2358,11 @@ EXPORT_SYMBOL(vma_alloc_folio_noprof);
  */
 struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order)
 {
-	struct mempolicy *pol = &default_policy;
+	struct page *page = alloc_frozen_pages_noprof(gfp, order);
 
-	/*
-	 * No reference counting needed for current->mempolicy
-	 * nor system default_policy
-	 */
-	if (!in_interrupt() && !(gfp & __GFP_THISNODE))
-		pol = get_task_policy(current);
-
-	return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX,
-				       numa_node_id());
+	if (page)
+		set_page_refcounted(page);
+	return page;
 }
 EXPORT_SYMBOL(alloc_pages_noprof);
 
@@ -2357,7 +2372,7 @@ struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order)
 }
 EXPORT_SYMBOL(folio_alloc_noprof);
 
-static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
+static unsigned long alloc_pages_bulk_interleave(gfp_t gfp,
 		struct mempolicy *pol, unsigned long nr_pages,
 		struct page **page_array)
 {
@@ -2376,13 +2391,13 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
 		if (delta) {
 			nr_allocated = alloc_pages_bulk_noprof(gfp,
 					interleave_nodes(pol), NULL,
-					nr_pages_per_node + 1, NULL,
+					nr_pages_per_node + 1,
 					page_array);
 			delta--;
 		} else {
 			nr_allocated = alloc_pages_bulk_noprof(gfp,
 					interleave_nodes(pol), NULL,
-					nr_pages_per_node, NULL, page_array);
+					nr_pages_per_node, page_array);
 		}
 
 		page_array += nr_allocated;
@@ -2392,7 +2407,7 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp,
 	return total_allocated;
 }
 
-static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
+static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp,
 		struct mempolicy *pol, unsigned long nr_pages,
 		struct page **page_array)
 {
@@ -2431,7 +2446,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
 	if (weight && node_isset(node, nodes)) {
 		node_pages = min(rem_pages, weight);
 		nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages,
-						  NULL, page_array);
+						  page_array);
 		page_array += nr_allocated;
 		total_allocated += nr_allocated;
 		/* if that's all the pages, no need to interleave */
@@ -2494,7 +2509,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
 		if (!node_pages)
 			break;
 		nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages,
-						  NULL, page_array);
+						  page_array);
 		page_array += nr_allocated;
 		total_allocated += nr_allocated;
 		if (total_allocated == nr_pages)
@@ -2507,7 +2522,7 @@ static unsigned long alloc_pages_bulk_array_weighted_interleave(gfp_t gfp,
 	return total_allocated;
 }
 
-static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
+static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid,
 		struct mempolicy *pol, unsigned long nr_pages,
 		struct page **page_array)
 {
@@ -2518,11 +2533,11 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
 	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
 
 	nr_allocated  = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes,
-					   nr_pages, NULL, page_array);
+					   nr_pages, page_array);
 
 	if (nr_allocated < nr_pages)
 		nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL,
-				nr_pages - nr_allocated, NULL,
+				nr_pages - nr_allocated,
 				page_array + nr_allocated);
 	return nr_allocated;
 }
@@ -2533,7 +2548,7 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid,
  * It can accelerate memory allocation especially interleaving
  * allocate memory.
  */
-unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp,
+unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp,
 		unsigned long nr_pages, struct page **page_array)
 {
 	struct mempolicy *pol = &default_policy;
@@ -2544,21 +2559,21 @@ unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp,
 		pol = get_task_policy(current);
 
 	if (pol->mode == MPOL_INTERLEAVE)
-		return alloc_pages_bulk_array_interleave(gfp, pol,
+		return alloc_pages_bulk_interleave(gfp, pol,
 							 nr_pages, page_array);
 
 	if (pol->mode == MPOL_WEIGHTED_INTERLEAVE)
-		return alloc_pages_bulk_array_weighted_interleave(
+		return alloc_pages_bulk_weighted_interleave(
 				  gfp, pol, nr_pages, page_array);
 
 	if (pol->mode == MPOL_PREFERRED_MANY)
-		return alloc_pages_bulk_array_preferred_many(gfp,
+		return alloc_pages_bulk_preferred_many(gfp,
 				numa_node_id(), pol, nr_pages, page_array);
 
 	nid = numa_node_id();
 	nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid);
 	return alloc_pages_bulk_noprof(gfp, nid, nodemask,
-				       nr_pages, NULL, page_array);
+				       nr_pages, page_array);
 }
 
 int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
diff --git a/mm/migrate.c b/mm/migrate.c
index cc68583c86f9..fb19a18892c8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -68,10 +68,6 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode)
 	if (!folio)
 		goto out;
 
-	if (unlikely(folio_test_slab(folio)))
-		goto out_putfolio;
-	/* Pairs with smp_wmb() in slab freeing, e.g. SLUB's __free_slab() */
-	smp_rmb();
 	/*
 	 * Check movable flag before taking the page lock because
 	 * we use non-atomic bitops on newly allocated page flags so
@@ -79,10 +75,6 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode)
 	 */
 	if (unlikely(!__folio_test_movable(folio)))
 		goto out_putfolio;
-	/* Pairs with smp_wmb() in slab allocation, e.g. SLUB's alloc_slab_page() */
-	smp_rmb();
-	if (unlikely(folio_test_slab(folio)))
-		goto out_putfolio;
 
 	/*
 	 * As movable pages are not isolated from LRU lists, concurrent
@@ -136,7 +128,7 @@ static void putback_movable_folio(struct folio *folio)
  *
  * This function shall be used whenever the isolated pageset has been
  * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range()
- * and isolate_hugetlb().
+ * and folio_isolate_hugetlb().
  */
 void putback_movable_pages(struct list_head *l)
 {
@@ -145,7 +137,7 @@ void putback_movable_pages(struct list_head *l)
 
 	list_for_each_entry_safe(folio, folio2, l, lru) {
 		if (unlikely(folio_test_hugetlb(folio))) {
-			folio_putback_active_hugetlb(folio);
+			folio_putback_hugetlb(folio);
 			continue;
 		}
 		list_del(&folio->lru);
@@ -177,7 +169,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
 	bool isolated, lru;
 
 	if (folio_test_hugetlb(folio))
-		return isolate_hugetlb(folio, list);
+		return folio_isolate_hugetlb(folio, list);
 
 	lru = !__folio_test_movable(folio);
 	if (lru)
@@ -1459,7 +1451,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio,
 
 	if (folio_ref_count(src) == 1) {
 		/* page was freed from under us. So we are done. */
-		folio_putback_active_hugetlb(src);
+		folio_putback_hugetlb(src);
 		return MIGRATEPAGE_SUCCESS;
 	}
 
@@ -1542,19 +1534,19 @@ out_unlock:
 	folio_unlock(src);
 out:
 	if (rc == MIGRATEPAGE_SUCCESS)
-		folio_putback_active_hugetlb(src);
+		folio_putback_hugetlb(src);
 	else if (rc != -EAGAIN)
 		list_move_tail(&src->lru, ret);
 
 	/*
-	 * If migration was not successful and there's a freeing callback, use
-	 * it.  Otherwise, put_page() will drop the reference grabbed during
-	 * isolation.
+	 * If migration was not successful and there's a freeing callback,
+	 * return the folio to that special allocator. Otherwise, simply drop
+	 * our additional reference.
 	 */
 	if (put_new_folio)
 		put_new_folio(dst, private);
 	else
-		folio_putback_active_hugetlb(dst);
+		folio_put(dst);
 
 	return rc;
 }
@@ -1695,6 +1687,81 @@ static int migrate_hugetlbs(struct list_head *from, new_folio_t get_new_folio,
 	return nr_failed;
 }
 
+static void migrate_folios_move(struct list_head *src_folios,
+		struct list_head *dst_folios,
+		free_folio_t put_new_folio, unsigned long private,
+		enum migrate_mode mode, int reason,
+		struct list_head *ret_folios,
+		struct migrate_pages_stats *stats,
+		int *retry, int *thp_retry, int *nr_failed,
+		int *nr_retry_pages)
+{
+	struct folio *folio, *folio2, *dst, *dst2;
+	bool is_thp;
+	int nr_pages;
+	int rc;
+
+	dst = list_first_entry(dst_folios, struct folio, lru);
+	dst2 = list_next_entry(dst, lru);
+	list_for_each_entry_safe(folio, folio2, src_folios, lru) {
+		is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio);
+		nr_pages = folio_nr_pages(folio);
+
+		cond_resched();
+
+		rc = migrate_folio_move(put_new_folio, private,
+				folio, dst, mode,
+				reason, ret_folios);
+		/*
+		 * The rules are:
+		 *	Success: folio will be freed
+		 *	-EAGAIN: stay on the unmap_folios list
+		 *	Other errno: put on ret_folios list
+		 */
+		switch (rc) {
+		case -EAGAIN:
+			*retry += 1;
+			*thp_retry += is_thp;
+			*nr_retry_pages += nr_pages;
+			break;
+		case MIGRATEPAGE_SUCCESS:
+			stats->nr_succeeded += nr_pages;
+			stats->nr_thp_succeeded += is_thp;
+			break;
+		default:
+			*nr_failed += 1;
+			stats->nr_thp_failed += is_thp;
+			stats->nr_failed_pages += nr_pages;
+			break;
+		}
+		dst = dst2;
+		dst2 = list_next_entry(dst, lru);
+	}
+}
+
+static void migrate_folios_undo(struct list_head *src_folios,
+		struct list_head *dst_folios,
+		free_folio_t put_new_folio, unsigned long private,
+		struct list_head *ret_folios)
+{
+	struct folio *folio, *folio2, *dst, *dst2;
+
+	dst = list_first_entry(dst_folios, struct folio, lru);
+	dst2 = list_next_entry(dst, lru);
+	list_for_each_entry_safe(folio, folio2, src_folios, lru) {
+		int old_page_state = 0;
+		struct anon_vma *anon_vma = NULL;
+
+		__migrate_folio_extract(dst, &old_page_state, &anon_vma);
+		migrate_folio_undo_src(folio, old_page_state & PAGE_WAS_MAPPED,
+				anon_vma, true, ret_folios);
+		list_del(&dst->lru);
+		migrate_folio_undo_dst(dst, true, put_new_folio, private);
+		dst = dst2;
+		dst2 = list_next_entry(dst, lru);
+	}
+}
+
 /*
  * migrate_pages_batch() first unmaps folios in the from list as many as
  * possible, then move the unmapped folios.
@@ -1717,7 +1784,7 @@ static int migrate_pages_batch(struct list_head *from,
 	int pass = 0;
 	bool is_thp = false;
 	bool is_large = false;
-	struct folio *folio, *folio2, *dst = NULL, *dst2;
+	struct folio *folio, *folio2, *dst = NULL;
 	int rc, rc_saved = 0, nr_pages;
 	LIST_HEAD(unmap_folios);
 	LIST_HEAD(dst_folios);
@@ -1888,42 +1955,11 @@ move:
 		thp_retry = 0;
 		nr_retry_pages = 0;
 
-		dst = list_first_entry(&dst_folios, struct folio, lru);
-		dst2 = list_next_entry(dst, lru);
-		list_for_each_entry_safe(folio, folio2, &unmap_folios, lru) {
-			is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio);
-			nr_pages = folio_nr_pages(folio);
-
-			cond_resched();
-
-			rc = migrate_folio_move(put_new_folio, private,
-						folio, dst, mode,
-						reason, ret_folios);
-			/*
-			 * The rules are:
-			 *	Success: folio will be freed
-			 *	-EAGAIN: stay on the unmap_folios list
-			 *	Other errno: put on ret_folios list
-			 */
-			switch(rc) {
-			case -EAGAIN:
-				retry++;
-				thp_retry += is_thp;
-				nr_retry_pages += nr_pages;
-				break;
-			case MIGRATEPAGE_SUCCESS:
-				stats->nr_succeeded += nr_pages;
-				stats->nr_thp_succeeded += is_thp;
-				break;
-			default:
-				nr_failed++;
-				stats->nr_thp_failed += is_thp;
-				stats->nr_failed_pages += nr_pages;
-				break;
-			}
-			dst = dst2;
-			dst2 = list_next_entry(dst, lru);
-		}
+		/* Move the unmapped folios */
+		migrate_folios_move(&unmap_folios, &dst_folios,
+				put_new_folio, private, mode, reason,
+				ret_folios, stats, &retry, &thp_retry,
+				&nr_failed, &nr_retry_pages);
 	}
 	nr_failed += retry;
 	stats->nr_thp_failed += thp_retry;
@@ -1932,20 +1968,8 @@ move:
 	rc = rc_saved ? : nr_failed;
 out:
 	/* Cleanup remaining folios */
-	dst = list_first_entry(&dst_folios, struct folio, lru);
-	dst2 = list_next_entry(dst, lru);
-	list_for_each_entry_safe(folio, folio2, &unmap_folios, lru) {
-		int old_page_state = 0;
-		struct anon_vma *anon_vma = NULL;
-
-		__migrate_folio_extract(dst, &old_page_state, &anon_vma);
-		migrate_folio_undo_src(folio, old_page_state & PAGE_WAS_MAPPED,
-				       anon_vma, true, ret_folios);
-		list_del(&dst->lru);
-		migrate_folio_undo_dst(dst, true, put_new_folio, private);
-		dst = dst2;
-		dst2 = list_next_entry(dst, lru);
-	}
+	migrate_folios_undo(&unmap_folios, &dst_folios,
+			put_new_folio, private, ret_folios);
 
 	return rc;
 }
@@ -2208,7 +2232,7 @@ static int __add_folio_for_migration(struct folio *folio, int node,
 		return -EACCES;
 
 	if (folio_test_hugetlb(folio)) {
-		if (isolate_hugetlb(folio, pagelist))
+		if (folio_isolate_hugetlb(folio, pagelist))
 			return 1;
 	} else if (folio_isolate_lru(folio)) {
 		list_add_tail(&folio->lru, pagelist);
@@ -2683,8 +2707,7 @@ int migrate_misplaced_folio_prepare(struct folio *folio,
  * elevated reference count on the folio. This function will un-isolate the
  * folio, dereferencing the folio before returning.
  */
-int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
-			    int node)
+int migrate_misplaced_folio(struct folio *folio, int node)
 {
 	pg_data_t *pgdat = NODE_DATA(node);
 	int nr_remaining;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 24b68b425afb..2630cc30147e 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1585,13 +1585,17 @@ void __init *memmap_alloc(phys_addr_t size, phys_addr_t align,
 {
 	void *ptr;
 
+	/*
+	 * Kmemleak will explicitly scan mem_map by traversing all valid
+	 * `struct *page`,so memblock does not need to be added to the scan list.
+	 */
 	if (exact_nid)
 		ptr = memblock_alloc_exact_nid_raw(size, align, min_addr,
-						   MEMBLOCK_ALLOC_ACCESSIBLE,
+						   MEMBLOCK_ALLOC_NOLEAKTRACE,
 						   nid);
 	else
 		ptr = memblock_alloc_try_nid_raw(size, align, min_addr,
-						 MEMBLOCK_ALLOC_ACCESSIBLE,
+						 MEMBLOCK_ALLOC_NOLEAKTRACE,
 						 nid);
 
 	if (ptr && size > 0)
diff --git a/mm/mmap.c b/mm/mmap.c
index aec208f90337..cda01071c7b1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -111,8 +111,7 @@ static int check_brk_limits(unsigned long addr, unsigned long len)
 	return mlock_future_ok(current->mm, current->mm->def_flags, len)
 		? 0 : -EAGAIN;
 }
-static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
-		unsigned long addr, unsigned long request, unsigned long flags);
+
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long newbrk, oldbrk, origbrk;
@@ -278,8 +277,62 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode,
 	return true;
 }
 
-/*
+/**
+ * do_mmap() - Perform a userland memory mapping into the current process
+ * address space of length @len with protection bits @prot, mmap flags @flags
+ * (from which VMA flags will be inferred), and any additional VMA flags to
+ * apply @vm_flags. If this is a file-backed mapping then the file is specified
+ * in @file and page offset into the file via @pgoff.
+ *
+ * This function does not perform security checks on the file and assumes, if
+ * @uf is non-NULL, the caller has provided a list head to track unmap events
+ * for userfaultfd @uf.
+ *
+ * It also simply indicates whether memory population is required by setting
+ * @populate, which must be non-NULL, expecting the caller to actually perform
+ * this task itself if appropriate.
+ *
+ * This function will invoke architecture-specific (and if provided and
+ * relevant, file system-specific) logic to determine the most appropriate
+ * unmapped area in which to place the mapping if not MAP_FIXED.
+ *
+ * Callers which require userland mmap() behaviour should invoke vm_mmap(),
+ * which is also exported for module use.
+ *
+ * Those which require this behaviour less security checks, userfaultfd and
+ * populate behaviour, and who handle the mmap write lock themselves, should
+ * call this function.
+ *
+ * Note that the returned address may reside within a merged VMA if an
+ * appropriate merge were to take place, so it doesn't necessarily specify the
+ * start of a VMA, rather only the start of a valid mapped range of length
+ * @len bytes, rounded down to the nearest page size.
+ *
  * The caller must write-lock current->mm->mmap_lock.
+ *
+ * @file: An optional struct file pointer describing the file which is to be
+ * mapped, if a file-backed mapping.
+ * @addr: If non-zero, hints at (or if @flags has MAP_FIXED set, specifies) the
+ * address at which to perform this mapping. See mmap (2) for details. Must be
+ * page-aligned.
+ * @len: The length of the mapping. Will be page-aligned and must be at least 1
+ * page in size.
+ * @prot: Protection bits describing access required to the mapping. See mmap
+ * (2) for details.
+ * @flags: Flags specifying how the mapping should be performed, see mmap (2)
+ * for details.
+ * @vm_flags: VMA flags which should be set by default, or 0 otherwise.
+ * @pgoff: Page offset into the @file if file-backed, should be 0 otherwise.
+ * @populate: A pointer to a value which will be set to 0 if no population of
+ * the range is required, or the number of bytes to populate if it is. Must be
+ * non-NULL. See mmap (2) for details as to under what circumstances population
+ * of the range occurs.
+ * @uf: An optional pointer to a list head to track userfaultfd unmap events
+ * should unmapping events arise. If provided, it is up to the caller to manage
+ * this.
+ *
+ * Returns: Either an error, or the address at which the requested mapping has
+ * been performed.
  */
 unsigned long do_mmap(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
@@ -292,6 +345,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 
 	*populate = 0;
 
+	mmap_assert_write_locked(mm);
+
 	if (!len)
 		return -EINVAL;
 
@@ -369,8 +424,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 
 	if (file) {
 		struct inode *inode = file_inode(file);
-		unsigned int seals = memfd_file_seals(file);
 		unsigned long flags_mask;
+		int err;
 
 		if (!file_mmap_ok(file, inode, pgoff, len))
 			return -EOVERFLOW;
@@ -410,8 +465,6 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
 			if (!(file->f_mode & FMODE_WRITE))
 				vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
-			else if (is_readonly_sealed(seals, vm_flags))
-				vm_flags &= ~VM_MAYWRITE;
 			fallthrough;
 		case MAP_PRIVATE:
 			if (!(file->f_mode & FMODE_READ))
@@ -431,6 +484,14 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		default:
 			return -EINVAL;
 		}
+
+		/*
+		 * Check to see if we are violating any seals and update VMA
+		 * flags if necessary to avoid future seal violations.
+		 */
+		err = memfd_check_seals_mmap(file, &vm_flags);
+		if (err)
+			return (unsigned long)err;
 	} else {
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
@@ -581,115 +642,6 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
 }
 #endif /* __ARCH_WANT_SYS_OLD_MMAP */
 
-/**
- * unmapped_area() - Find an area between the low_limit and the high_limit with
- * the correct alignment and offset, all from @info. Note: current->mm is used
- * for the search.
- *
- * @info: The unmapped area information including the range [low_limit -
- * high_limit), the alignment offset and mask.
- *
- * Return: A memory address or -ENOMEM.
- */
-static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
-{
-	unsigned long length, gap;
-	unsigned long low_limit, high_limit;
-	struct vm_area_struct *tmp;
-	VMA_ITERATOR(vmi, current->mm, 0);
-
-	/* Adjust search length to account for worst case alignment overhead */
-	length = info->length + info->align_mask + info->start_gap;
-	if (length < info->length)
-		return -ENOMEM;
-
-	low_limit = info->low_limit;
-	if (low_limit < mmap_min_addr)
-		low_limit = mmap_min_addr;
-	high_limit = info->high_limit;
-retry:
-	if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length))
-		return -ENOMEM;
-
-	/*
-	 * Adjust for the gap first so it doesn't interfere with the
-	 * later alignment. The first step is the minimum needed to
-	 * fulill the start gap, the next steps is the minimum to align
-	 * that. It is the minimum needed to fulill both.
-	 */
-	gap = vma_iter_addr(&vmi) + info->start_gap;
-	gap += (info->align_offset - gap) & info->align_mask;
-	tmp = vma_next(&vmi);
-	if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
-		if (vm_start_gap(tmp) < gap + length - 1) {
-			low_limit = tmp->vm_end;
-			vma_iter_reset(&vmi);
-			goto retry;
-		}
-	} else {
-		tmp = vma_prev(&vmi);
-		if (tmp && vm_end_gap(tmp) > gap) {
-			low_limit = vm_end_gap(tmp);
-			vma_iter_reset(&vmi);
-			goto retry;
-		}
-	}
-
-	return gap;
-}
-
-/**
- * unmapped_area_topdown() - Find an area between the low_limit and the
- * high_limit with the correct alignment and offset at the highest available
- * address, all from @info. Note: current->mm is used for the search.
- *
- * @info: The unmapped area information including the range [low_limit -
- * high_limit), the alignment offset and mask.
- *
- * Return: A memory address or -ENOMEM.
- */
-static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
-{
-	unsigned long length, gap, gap_end;
-	unsigned long low_limit, high_limit;
-	struct vm_area_struct *tmp;
-	VMA_ITERATOR(vmi, current->mm, 0);
-
-	/* Adjust search length to account for worst case alignment overhead */
-	length = info->length + info->align_mask + info->start_gap;
-	if (length < info->length)
-		return -ENOMEM;
-
-	low_limit = info->low_limit;
-	if (low_limit < mmap_min_addr)
-		low_limit = mmap_min_addr;
-	high_limit = info->high_limit;
-retry:
-	if (vma_iter_area_highest(&vmi, low_limit, high_limit, length))
-		return -ENOMEM;
-
-	gap = vma_iter_end(&vmi) - info->length;
-	gap -= (gap - info->align_offset) & info->align_mask;
-	gap_end = vma_iter_end(&vmi);
-	tmp = vma_next(&vmi);
-	if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
-		if (vm_start_gap(tmp) < gap_end) {
-			high_limit = vm_start_gap(tmp);
-			vma_iter_reset(&vmi);
-			goto retry;
-		}
-	} else {
-		tmp = vma_prev(&vmi);
-		if (tmp && vm_end_gap(tmp) > gap) {
-			high_limit = tmp->vm_start;
-			vma_iter_reset(&vmi);
-			goto retry;
-		}
-	}
-
-	return gap;
-}
-
 /*
  * Determine if the allocation needs to ensure that there is no
  * existing mapping within it's guard gaps, for use as start_gap.
@@ -989,211 +941,6 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr,
 	return vma;
 }
 
-/*
- * Verify that the stack growth is acceptable and
- * update accounting. This is shared with both the
- * grow-up and grow-down cases.
- */
-static int acct_stack_growth(struct vm_area_struct *vma,
-			     unsigned long size, unsigned long grow)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned long new_start;
-
-	/* address space limit tests */
-	if (!may_expand_vm(mm, vma->vm_flags, grow))
-		return -ENOMEM;
-
-	/* Stack limit test */
-	if (size > rlimit(RLIMIT_STACK))
-		return -ENOMEM;
-
-	/* mlock limit tests */
-	if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT))
-		return -ENOMEM;
-
-	/* Check to ensure the stack will not grow into a hugetlb-only region */
-	new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
-			vma->vm_end - size;
-	if (is_hugepage_only_range(vma->vm_mm, new_start, size))
-		return -EFAULT;
-
-	/*
-	 * Overcommit..  This must be the final test, as it will
-	 * update security statistics.
-	 */
-	if (security_vm_enough_memory_mm(mm, grow))
-		return -ENOMEM;
-
-	return 0;
-}
-
-#if defined(CONFIG_STACK_GROWSUP)
-/*
- * PA-RISC uses this for its stack.
- * vma is the last one with address > vma->vm_end.  Have to extend vma.
- */
-static int expand_upwards(struct vm_area_struct *vma, unsigned long address)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	struct vm_area_struct *next;
-	unsigned long gap_addr;
-	int error = 0;
-	VMA_ITERATOR(vmi, mm, vma->vm_start);
-
-	if (!(vma->vm_flags & VM_GROWSUP))
-		return -EFAULT;
-
-	mmap_assert_write_locked(mm);
-
-	/* Guard against exceeding limits of the address space. */
-	address &= PAGE_MASK;
-	if (address >= (TASK_SIZE & PAGE_MASK))
-		return -ENOMEM;
-	address += PAGE_SIZE;
-
-	/* Enforce stack_guard_gap */
-	gap_addr = address + stack_guard_gap;
-
-	/* Guard against overflow */
-	if (gap_addr < address || gap_addr > TASK_SIZE)
-		gap_addr = TASK_SIZE;
-
-	next = find_vma_intersection(mm, vma->vm_end, gap_addr);
-	if (next && vma_is_accessible(next)) {
-		if (!(next->vm_flags & VM_GROWSUP))
-			return -ENOMEM;
-		/* Check that both stack segments have the same anon_vma? */
-	}
-
-	if (next)
-		vma_iter_prev_range_limit(&vmi, address);
-
-	vma_iter_config(&vmi, vma->vm_start, address);
-	if (vma_iter_prealloc(&vmi, vma))
-		return -ENOMEM;
-
-	/* We must make sure the anon_vma is allocated. */
-	if (unlikely(anon_vma_prepare(vma))) {
-		vma_iter_free(&vmi);
-		return -ENOMEM;
-	}
-
-	/* Lock the VMA before expanding to prevent concurrent page faults */
-	vma_start_write(vma);
-	/* We update the anon VMA tree. */
-	anon_vma_lock_write(vma->anon_vma);
-
-	/* Somebody else might have raced and expanded it already */
-	if (address > vma->vm_end) {
-		unsigned long size, grow;
-
-		size = address - vma->vm_start;
-		grow = (address - vma->vm_end) >> PAGE_SHIFT;
-
-		error = -ENOMEM;
-		if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) {
-			error = acct_stack_growth(vma, size, grow);
-			if (!error) {
-				if (vma->vm_flags & VM_LOCKED)
-					mm->locked_vm += grow;
-				vm_stat_account(mm, vma->vm_flags, grow);
-				anon_vma_interval_tree_pre_update_vma(vma);
-				vma->vm_end = address;
-				/* Overwrite old entry in mtree. */
-				vma_iter_store(&vmi, vma);
-				anon_vma_interval_tree_post_update_vma(vma);
-
-				perf_event_mmap(vma);
-			}
-		}
-	}
-	anon_vma_unlock_write(vma->anon_vma);
-	vma_iter_free(&vmi);
-	validate_mm(mm);
-	return error;
-}
-#endif /* CONFIG_STACK_GROWSUP */
-
-/*
- * vma is the first one with address < vma->vm_start.  Have to extend vma.
- * mmap_lock held for writing.
- */
-int expand_downwards(struct vm_area_struct *vma, unsigned long address)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	struct vm_area_struct *prev;
-	int error = 0;
-	VMA_ITERATOR(vmi, mm, vma->vm_start);
-
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		return -EFAULT;
-
-	mmap_assert_write_locked(mm);
-
-	address &= PAGE_MASK;
-	if (address < mmap_min_addr || address < FIRST_USER_ADDRESS)
-		return -EPERM;
-
-	/* Enforce stack_guard_gap */
-	prev = vma_prev(&vmi);
-	/* Check that both stack segments have the same anon_vma? */
-	if (prev) {
-		if (!(prev->vm_flags & VM_GROWSDOWN) &&
-		    vma_is_accessible(prev) &&
-		    (address - prev->vm_end < stack_guard_gap))
-			return -ENOMEM;
-	}
-
-	if (prev)
-		vma_iter_next_range_limit(&vmi, vma->vm_start);
-
-	vma_iter_config(&vmi, address, vma->vm_end);
-	if (vma_iter_prealloc(&vmi, vma))
-		return -ENOMEM;
-
-	/* We must make sure the anon_vma is allocated. */
-	if (unlikely(anon_vma_prepare(vma))) {
-		vma_iter_free(&vmi);
-		return -ENOMEM;
-	}
-
-	/* Lock the VMA before expanding to prevent concurrent page faults */
-	vma_start_write(vma);
-	/* We update the anon VMA tree. */
-	anon_vma_lock_write(vma->anon_vma);
-
-	/* Somebody else might have raced and expanded it already */
-	if (address < vma->vm_start) {
-		unsigned long size, grow;
-
-		size = vma->vm_end - address;
-		grow = (vma->vm_start - address) >> PAGE_SHIFT;
-
-		error = -ENOMEM;
-		if (grow <= vma->vm_pgoff) {
-			error = acct_stack_growth(vma, size, grow);
-			if (!error) {
-				if (vma->vm_flags & VM_LOCKED)
-					mm->locked_vm += grow;
-				vm_stat_account(mm, vma->vm_flags, grow);
-				anon_vma_interval_tree_pre_update_vma(vma);
-				vma->vm_start = address;
-				vma->vm_pgoff -= grow;
-				/* Overwrite old entry in mtree. */
-				vma_iter_store(&vmi, vma);
-				anon_vma_interval_tree_post_update_vma(vma);
-
-				perf_event_mmap(vma);
-			}
-		}
-	}
-	anon_vma_unlock_write(vma->anon_vma);
-	vma_iter_free(&vmi);
-	validate_mm(mm);
-	return error;
-}
-
 /* enforced gap between the expanding stack and other mappings. */
 unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
 
@@ -1325,58 +1072,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
 	return do_vmi_munmap(&vmi, mm, start, len, uf, false);
 }
 
-unsigned long mmap_region(struct file *file, unsigned long addr,
-			  unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
-			  struct list_head *uf)
-{
-	unsigned long ret;
-	bool writable_file_mapping = false;
-
-	/* Check to see if MDWE is applicable. */
-	if (map_deny_write_exec(vm_flags, vm_flags))
-		return -EACCES;
-
-	/* Allow architectures to sanity-check the vm_flags. */
-	if (!arch_validate_flags(vm_flags))
-		return -EINVAL;
-
-	/* Map writable and ensure this isn't a sealed memfd. */
-	if (file && is_shared_maywrite(vm_flags)) {
-		int error = mapping_map_writable(file->f_mapping);
-
-		if (error)
-			return error;
-		writable_file_mapping = true;
-	}
-
-	ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf);
-
-	/* Clear our write mapping regardless of error. */
-	if (writable_file_mapping)
-		mapping_unmap_writable(file->f_mapping);
-
-	validate_mm(current->mm);
-	return ret;
-}
-
-static int __vm_munmap(unsigned long start, size_t len, bool unlock)
-{
-	int ret;
-	struct mm_struct *mm = current->mm;
-	LIST_HEAD(uf);
-	VMA_ITERATOR(vmi, mm, start);
-
-	if (mmap_write_lock_killable(mm))
-		return -EINTR;
-
-	ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock);
-	if (ret || !unlock)
-		mmap_write_unlock(mm);
-
-	userfaultfd_unmap_complete(mm, &uf);
-	return ret;
-}
-
 int vm_munmap(unsigned long start, size_t len)
 {
 	return __vm_munmap(start, len, false);
@@ -1512,88 +1207,6 @@ out:
 	return ret;
 }
 
-/*
- * do_brk_flags() - Increase the brk vma if the flags match.
- * @vmi: The vma iterator
- * @addr: The start address
- * @len: The length of the increase
- * @vma: The vma,
- * @flags: The VMA Flags
- *
- * Extend the brk VMA from addr to addr + len.  If the VMA is NULL or the flags
- * do not match then create a new anonymous VMA.  Eventually we may be able to
- * do some brk-specific accounting here.
- */
-static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long len, unsigned long flags)
-{
-	struct mm_struct *mm = current->mm;
-
-	/*
-	 * Check against address space limits by the changed size
-	 * Note: This happens *after* clearing old mappings in some code paths.
-	 */
-	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
-	if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
-		return -ENOMEM;
-
-	if (mm->map_count > sysctl_max_map_count)
-		return -ENOMEM;
-
-	if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT))
-		return -ENOMEM;
-
-	/*
-	 * Expand the existing vma if possible; Note that singular lists do not
-	 * occur after forking, so the expand will only happen on new VMAs.
-	 */
-	if (vma && vma->vm_end == addr) {
-		VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr));
-
-		vmg.prev = vma;
-		/* vmi is positioned at prev, which this mode expects. */
-		vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
-
-		if (vma_merge_new_range(&vmg))
-			goto out;
-		else if (vmg_nomem(&vmg))
-			goto unacct_fail;
-	}
-
-	if (vma)
-		vma_iter_next_range(vmi);
-	/* create a vma struct for an anonymous mapping */
-	vma = vm_area_alloc(mm);
-	if (!vma)
-		goto unacct_fail;
-
-	vma_set_anonymous(vma);
-	vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT);
-	vm_flags_init(vma, flags);
-	vma->vm_page_prot = vm_get_page_prot(flags);
-	vma_start_write(vma);
-	if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL))
-		goto mas_store_fail;
-
-	mm->map_count++;
-	validate_mm(mm);
-	ksm_add_vma(vma);
-out:
-	perf_event_mmap(vma);
-	mm->total_vm += len >> PAGE_SHIFT;
-	mm->data_vm += len >> PAGE_SHIFT;
-	if (flags & VM_LOCKED)
-		mm->locked_vm += (len >> PAGE_SHIFT);
-	vm_flags_set(vma, VM_SOFTDIRTY);
-	return 0;
-
-mas_store_fail:
-	vm_area_free(vma);
-unacct_fail:
-	vm_unacct_memory(len >> PAGE_SHIFT);
-	return -ENOMEM;
-}
-
 int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
@@ -1664,7 +1277,6 @@ void exit_mmap(struct mm_struct *mm)
 		goto destroy;
 	}
 
-	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb_gather_mmu_fullmm(&tlb, mm);
 	/* update_hiwater_rss(mm) here? but nobody should be looking */
@@ -2107,7 +1719,6 @@ int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
 				       vma, new_start, length, false, true))
 		return -ENOMEM;
 
-	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm);
 	next = vma_next(&vmi);
 	if (new_end > old_start) {
@@ -2132,3 +1743,55 @@ int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
 	/* Shrink the vma to just the new range */
 	return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff);
 }
+
+#ifdef CONFIG_MMU
+/*
+ * Obtain a read lock on mm->mmap_lock, if the specified address is below the
+ * start of the VMA, the intent is to perform a write, and it is a
+ * downward-growing stack, then attempt to expand the stack to contain it.
+ *
+ * This function is intended only for obtaining an argument page from an ELF
+ * image, and is almost certainly NOT what you want to use for any other
+ * purpose.
+ *
+ * IMPORTANT - VMA fields are accessed without an mmap lock being held, so the
+ * VMA referenced must not be linked in any user-visible tree, i.e. it must be a
+ * new VMA being mapped.
+ *
+ * The function assumes that addr is either contained within the VMA or below
+ * it, and makes no attempt to validate this value beyond that.
+ *
+ * Returns true if the read lock was obtained and a stack was perhaps expanded,
+ * false if the stack expansion failed.
+ *
+ * On stack expansion the function temporarily acquires an mmap write lock
+ * before downgrading it.
+ */
+bool mmap_read_lock_maybe_expand(struct mm_struct *mm,
+				 struct vm_area_struct *new_vma,
+				 unsigned long addr, bool write)
+{
+	if (!write || addr >= new_vma->vm_start) {
+		mmap_read_lock(mm);
+		return true;
+	}
+
+	if (!(new_vma->vm_flags & VM_GROWSDOWN))
+		return false;
+
+	mmap_write_lock(mm);
+	if (expand_downwards(new_vma, addr)) {
+		mmap_write_unlock(mm);
+		return false;
+	}
+
+	mmap_write_downgrade(mm);
+	return true;
+}
+#else
+bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma,
+				 unsigned long addr, bool write)
+{
+	return false;
+}
+#endif
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
index f186d57df2c6..e7dbaf96aa17 100644
--- a/mm/mmap_lock.c
+++ b/mm/mmap_lock.c
@@ -17,51 +17,7 @@ EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking);
 EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned);
 EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released);
 
-#ifdef CONFIG_MEMCG
-
-/*
- * Size of the buffer for memcg path names. Ignoring stack trace support,
- * trace_events_hist.c uses MAX_FILTER_STR_VAL for this, so we also use it.
- */
-#define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL
-
-#define TRACE_MMAP_LOCK_EVENT(type, mm, ...)				\
-	do {								\
-		if (trace_mmap_lock_##type##_enabled()) {		\
-			char buf[MEMCG_PATH_BUF_SIZE];                  \
-			get_mm_memcg_path(mm, buf, sizeof(buf));        \
-			trace_mmap_lock_##type(mm, buf, ##__VA_ARGS__); \
-		}							\
-	} while (0)
-
-#else /* !CONFIG_MEMCG */
-
-#define TRACE_MMAP_LOCK_EVENT(type, mm, ...)                                   \
-	trace_mmap_lock_##type(mm, "", ##__VA_ARGS__)
-
-#endif /* CONFIG_MEMCG */
-
 #ifdef CONFIG_TRACING
-#ifdef CONFIG_MEMCG
-/*
- * Write the given mm_struct's memcg path to a buffer. If the path cannot be
- * determined, empty string is written.
- */
-static void get_mm_memcg_path(struct mm_struct *mm, char *buf, size_t buflen)
-{
-	struct mem_cgroup *memcg;
-
-	buf[0] = '\0';
-	memcg = get_mem_cgroup_from_mm(mm);
-	if (memcg == NULL)
-		return;
-	if (memcg->css.cgroup)
-		cgroup_path(memcg->css.cgroup, buf, buflen);
-	css_put(&memcg->css);
-}
-
-#endif /* CONFIG_MEMCG */
-
 /*
  * Trace calls must be in a separate file, as otherwise there's a circular
  * dependency between linux/mmap_lock.h and trace/events/mmap_lock.h.
@@ -69,20 +25,20 @@ static void get_mm_memcg_path(struct mm_struct *mm, char *buf, size_t buflen)
 
 void __mmap_lock_do_trace_start_locking(struct mm_struct *mm, bool write)
 {
-	TRACE_MMAP_LOCK_EVENT(start_locking, mm, write);
+	trace_mmap_lock_start_locking(mm, write);
 }
 EXPORT_SYMBOL(__mmap_lock_do_trace_start_locking);
 
 void __mmap_lock_do_trace_acquire_returned(struct mm_struct *mm, bool write,
 					   bool success)
 {
-	TRACE_MMAP_LOCK_EVENT(acquire_returned, mm, write, success);
+	trace_mmap_lock_acquire_returned(mm, write, success);
 }
 EXPORT_SYMBOL(__mmap_lock_do_trace_acquire_returned);
 
 void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write)
 {
-	TRACE_MMAP_LOCK_EVENT(released, mm, write);
+	trace_mmap_lock_released(mm, write);
 }
 EXPORT_SYMBOL(__mmap_lock_do_trace_released);
 #endif /* CONFIG_TRACING */
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 99b3e9408aa0..7aa6f18c500b 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -311,11 +311,34 @@ static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 	}
 }
 
-static void tlb_remove_table_one(void *table)
+#ifdef CONFIG_PT_RECLAIM
+static inline void __tlb_remove_table_one_rcu(struct rcu_head *head)
+{
+	struct ptdesc *ptdesc;
+
+	ptdesc = container_of(head, struct ptdesc, pt_rcu_head);
+	__tlb_remove_table(ptdesc);
+}
+
+static inline void __tlb_remove_table_one(void *table)
+{
+	struct ptdesc *ptdesc;
+
+	ptdesc = table;
+	call_rcu(&ptdesc->pt_rcu_head, __tlb_remove_table_one_rcu);
+}
+#else
+static inline void __tlb_remove_table_one(void *table)
 {
 	tlb_remove_table_sync_one();
 	__tlb_remove_table(table);
 }
+#endif /* CONFIG_PT_RECLAIM */
+
+static void tlb_remove_table_one(void *table)
+{
+	__tlb_remove_table_one(table);
+}
 
 static void tlb_table_flush(struct mmu_gather *tlb)
 {
diff --git a/mm/mseal.c b/mm/mseal.c
index 81d6e980e8a9..c27197ac04e8 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -217,9 +217,9 @@ int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 	unsigned long end;
 	struct mm_struct *mm = current->mm;
 
-	ret = can_do_mseal(flags);
-	if (ret)
-		return ret;
+	/* Verify flags not set. */
+	if (flags)
+		return -EINVAL;
 
 	start = untagged_addr(start);
 	if (!PAGE_ALIGNED(start))
diff --git a/mm/numa.c b/mm/numa.c
index e2eec07707d1..f1787d7713a6 100644
--- a/mm/numa.c
+++ b/mm/numa.c
@@ -37,13 +37,7 @@ void __init alloc_node_data(int nid)
 void __init alloc_offline_node_data(int nid)
 {
 	pg_data_t *pgdat;
-
-	pgdat = memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES);
-	if (!pgdat)
-		panic("Cannot allocate %zuB for node %d.\n",
-		      sizeof(*pgdat), nid);
-
-	node_data[nid] = pgdat;
+	node_data[nid] = memblock_alloc_or_panic(sizeof(*pgdat), SMP_CACHE_BYTES);
 }
 
 /* Stub functions: */
diff --git a/mm/numa_emulation.c b/mm/numa_emulation.c
index 031fb9961bf7..9d55679d99ce 100644
--- a/mm/numa_emulation.c
+++ b/mm/numa_emulation.c
@@ -8,11 +8,12 @@
 #include <linux/memblock.h>
 #include <linux/numa_memblks.h>
 #include <asm/numa.h>
+#include <acpi/acpi_numa.h>
 
 #define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
 #define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
 
-static int emu_nid_to_phys[MAX_NUMNODES];
+int emu_nid_to_phys[MAX_NUMNODES];
 static char *emu_cmdline __initdata;
 
 int __init numa_emu_cmdline(char *str)
@@ -379,6 +380,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
 	int max_emu_nid, dfl_phys_nid;
 	int i, j, ret;
+	nodemask_t physnode_mask = numa_nodes_parsed;
 
 	if (!emu_cmdline)
 		goto no_emu;
@@ -395,7 +397,6 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	 * split the system RAM into N fake nodes.
 	 */
 	if (strchr(emu_cmdline, 'U')) {
-		nodemask_t physnode_mask = numa_nodes_parsed;
 		unsigned long n;
 		int nid = 0;
 
@@ -465,9 +466,6 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	 */
 	max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid);
 
-	/* commit */
-	*numa_meminfo = ei;
-
 	/* Make sure numa_nodes_parsed only contains emulated nodes */
 	nodes_clear(numa_nodes_parsed);
 	for (i = 0; i < ARRAY_SIZE(ei.blk); i++)
@@ -475,10 +473,21 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 		    ei.blk[i].nid != NUMA_NO_NODE)
 			node_set(ei.blk[i].nid, numa_nodes_parsed);
 
-	numa_emu_update_cpu_to_node(emu_nid_to_phys, ARRAY_SIZE(emu_nid_to_phys));
+	/* fix pxm_to_node_map[] and node_to_pxm_map[] to avoid collision
+	 * with faked numa nodes, particularly during later memory hotplug
+	 * handling, and also update numa_nodes_parsed accordingly.
+	 */
+	ret = fix_pxm_node_maps(max_emu_nid);
+	if (ret < 0)
+		goto no_emu;
+
+	/* commit */
+	*numa_meminfo = ei;
+
+	numa_emu_update_cpu_to_node(emu_nid_to_phys, max_emu_nid + 1);
 
 	/* make sure all emulated nodes are mapped to a physical node */
-	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
+	for (i = 0; i < max_emu_nid + 1; i++)
 		if (emu_nid_to_phys[i] == NUMA_NO_NODE)
 			emu_nid_to_phys[i] = dfl_phys_nid;
 
@@ -501,12 +510,34 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 			numa_set_distance(i, j, dist);
 		}
 	}
+	for (i = 0; i < numa_distance_cnt; i++) {
+		for (j = 0; j < numa_distance_cnt; j++) {
+			int physi, physj;
+			u8 dist;
+
+			/* distance between fake nodes is already ok */
+			if (emu_nid_to_phys[i] != NUMA_NO_NODE &&
+			    emu_nid_to_phys[j] != NUMA_NO_NODE)
+				continue;
+			if (emu_nid_to_phys[i] != NUMA_NO_NODE)
+				physi = emu_nid_to_phys[i];
+			else
+				physi = i - max_emu_nid;
+			if (emu_nid_to_phys[j] != NUMA_NO_NODE)
+				physj = emu_nid_to_phys[j];
+			else
+				physj = j - max_emu_nid;
+			dist = phys_dist[physi * numa_dist_cnt + physj];
+			numa_set_distance(i, j, dist);
+		}
+	}
 
 	/* free the copied physical distance table */
 	memblock_free(phys_dist, phys_size);
 	return;
 
 no_emu:
+	numa_nodes_parsed = physnode_mask;
 	/* No emulation.  Build identity emu_nid_to_phys[] for numa_add_cpu() */
 	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
 		emu_nid_to_phys[i] = i;
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index a3877e9bc878..ff4054f4334d 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -7,7 +7,7 @@
 #include <linux/numa.h>
 #include <linux/numa_memblks.h>
 
-static int numa_distance_cnt;
+int numa_distance_cnt;
 static u8 *numa_distance;
 
 nodemask_t numa_nodes_parsed __initdata;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 1c485beb0b93..1cf121ad7085 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -44,6 +44,7 @@
 #include <linux/init.h>
 #include <linux/mmu_notifier.h>
 #include <linux/cred.h>
+#include <linux/nmi.h>
 
 #include <asm/tlb.h>
 #include "internal.h"
@@ -430,10 +431,15 @@ static void dump_tasks(struct oom_control *oc)
 		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
 	else {
 		struct task_struct *p;
+		int i = 0;
 
 		rcu_read_lock();
-		for_each_process(p)
+		for_each_process(p) {
+			/* Avoid potential softlockup warning */
+			if ((++i & 1023) == 0)
+				touch_softlockup_watchdog();
 			dump_task(p, oc);
+		}
 		rcu_read_unlock();
 	}
 }
@@ -699,7 +705,7 @@ static void queue_oom_reaper(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table vm_oom_kill_table[] = {
+static const struct ctl_table vm_oom_kill_table[] = {
 	{
 		.procname	= "panic_on_oom",
 		.data		= &sysctl_panic_on_oom,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d9861e42b2bd..eb55ece39c56 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -942,26 +942,25 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc,
 	wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio);
 
 	wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE);
-	wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
-	if (wb_thresh > wb_max_thresh)
-		wb_thresh = wb_max_thresh;
 
 	/*
-	 * With strictlimit flag, the wb_thresh is treated as
-	 * a hard limit in balance_dirty_pages() and wb_position_ratio().
-	 * It's possible that wb_thresh is close to zero, not because
-	 * the device is slow, but because it has been inactive.
-	 * To prevent occasional writes from being blocked, we raise wb_thresh.
+	 * It's very possible that wb_thresh is close to 0 not because the
+	 * device is slow, but that it has remained inactive for long time.
+	 * Honour such devices a reasonable good (hopefully IO efficient)
+	 * threshold, so that the occasional writes won't be blocked and active
+	 * writes can rampup the threshold quickly.
 	 */
-	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
-		unsigned long limit = hard_dirty_limit(dom, dtc->thresh);
-		u64 wb_scale_thresh = 0;
-
-		if (limit > dtc->dirty)
-			wb_scale_thresh = (limit - dtc->dirty) / 100;
-		wb_thresh = max(wb_thresh, min(wb_scale_thresh, wb_max_thresh / 4));
+	if (thresh > dtc->dirty) {
+		if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT))
+			wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100);
+		else
+			wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8);
 	}
 
+	wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE);
+	if (wb_thresh > wb_max_thresh)
+		wb_thresh = wb_max_thresh;
+
 	return wb_thresh;
 }
 
@@ -969,6 +968,7 @@ unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh)
 {
 	struct dirty_throttle_control gdtc = { GDTC_INIT(wb) };
 
+	domain_dirty_avail(&gdtc, true);
 	return __wb_calc_thresh(&gdtc, thresh);
 }
 
@@ -1145,12 +1145,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		long long wb_pos_ratio;
 
-		if (dtc->wb_dirty < 8) {
-			dtc->pos_ratio = min_t(long long, pos_ratio * 2,
-					   2 << RATELIMIT_CALC_SHIFT);
-			return;
-		}
-
 		if (dtc->wb_dirty >= wb_thresh)
 			return;
 
@@ -1222,14 +1216,6 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	if (unlikely(wb_thresh > dtc->thresh))
 		wb_thresh = dtc->thresh;
 	/*
-	 * It's very possible that wb_thresh is close to 0 not because the
-	 * device is slow, but that it has remained inactive for long time.
-	 * Honour such devices a reasonable good (hopefully IO efficient)
-	 * threshold, so that the occasional writes won't be blocked and active
-	 * writes can rampup the threshold quickly.
-	 */
-	wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8);
-	/*
 	 * scale global setpoint to wb's:
 	 *	wb_setpoint = setpoint * wb_thresh / thresh
 	 */
@@ -1484,17 +1470,10 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc,
 	 * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate).
 	 * Hence, to calculate "step" properly, we have to use wb_dirty as
 	 * "dirty" and wb_setpoint as "setpoint".
-	 *
-	 * We rampup dirty_ratelimit forcibly if wb_dirty is low because
-	 * it's possible that wb_thresh is close to zero due to inactivity
-	 * of backing device.
 	 */
 	if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) {
 		dirty = dtc->wb_dirty;
-		if (dtc->wb_dirty < 8)
-			setpoint = dtc->wb_dirty + 1;
-		else
-			setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
+		setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2;
 	}
 
 	if (dirty < setpoint) {
@@ -2319,7 +2298,7 @@ static int page_writeback_cpu_online(unsigned int cpu)
 /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
 static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 
-static struct ctl_table vm_page_writeback_sysctls[] = {
+static const struct ctl_table vm_page_writeback_sysctls[] = {
 	{
 		.procname   = "dirty_background_ratio",
 		.data       = &dirty_background_ratio,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 01eab25edf89..579789600a3c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1295,12 +1295,6 @@ void __meminit __free_pages_core(struct page *page, unsigned int order,
 			set_page_count(p, 0);
 		}
 
-		/*
-		 * Freeing the page with debug_pagealloc enabled will try to
-		 * unmap it; some archs don't like double-unmappings, so
-		 * map it first.
-		 */
-		debug_pagealloc_map_pages(page, nr_pages);
 		adjust_managed_page_count(page, nr_pages);
 	} else {
 		for (loop = 0; loop < nr_pages; loop++, p++) {
@@ -1508,7 +1502,6 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	int i;
 
 	set_page_private(page, 0);
-	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
 	debug_pagealloc_map_pages(page, 1 << order);
@@ -1856,6 +1849,14 @@ static bool can_steal_fallback(unsigned int order, int start_mt)
 	if (order >= pageblock_order)
 		return true;
 
+	/*
+	 * Movable pages won't cause permanent fragmentation, so when you alloc
+	 * small pages, you just need to temporarily steal unmovable or
+	 * reclaimable pages that are closest to the request size.  After a
+	 * while, memory compaction may occur to form large contiguous pages,
+	 * and the next movable allocation may not need to steal.  Unmovable and
+	 * reclaimable allocations need to actually steal pages.
+	 */
 	if (order >= pageblock_order / 2 ||
 		start_mt == MIGRATE_RECLAIMABLE ||
 		start_mt == MIGRATE_UNMOVABLE ||
@@ -2592,9 +2593,9 @@ static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone,
 	return high;
 }
 
-static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
-				   struct page *page, int migratetype,
-				   unsigned int order)
+static void free_frozen_page_commit(struct zone *zone,
+		struct per_cpu_pages *pcp, struct page *page, int migratetype,
+		unsigned int order)
 {
 	int high, batch;
 	int pindex;
@@ -2643,7 +2644,7 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
 /*
  * Free a pcp page
  */
-void free_unref_page(struct page *page, unsigned int order)
+void free_frozen_pages(struct page *page, unsigned int order)
 {
 	unsigned long __maybe_unused UP_flags;
 	struct per_cpu_pages *pcp;
@@ -2666,20 +2667,20 @@ void free_unref_page(struct page *page, unsigned int order)
 	 * get those areas back if necessary. Otherwise, we may have to free
 	 * excessively into the page allocator
 	 */
+	zone = page_zone(page);
 	migratetype = get_pfnblock_migratetype(page, pfn);
 	if (unlikely(migratetype >= MIGRATE_PCPTYPES)) {
 		if (unlikely(is_migrate_isolate(migratetype))) {
-			free_one_page(page_zone(page), page, pfn, order, FPI_NONE);
+			free_one_page(zone, page, pfn, order, FPI_NONE);
 			return;
 		}
 		migratetype = MIGRATE_MOVABLE;
 	}
 
-	zone = page_zone(page);
 	pcp_trylock_prepare(UP_flags);
 	pcp = pcp_spin_trylock(zone->per_cpu_pageset);
 	if (pcp) {
-		free_unref_page_commit(zone, pcp, page, migratetype, order);
+		free_frozen_page_commit(zone, pcp, page, migratetype, order);
 		pcp_spin_unlock(pcp);
 	} else {
 		free_one_page(zone, page, pfn, order, FPI_NONE);
@@ -2743,7 +2744,7 @@ void free_unref_folios(struct folio_batch *folios)
 
 			/*
 			 * Free isolated pages directly to the
-			 * allocator, see comment in free_unref_page.
+			 * allocator, see comment in free_frozen_pages.
 			 */
 			if (is_migrate_isolate(migratetype)) {
 				free_one_page(zone, &folio->page, pfn,
@@ -2774,7 +2775,7 @@ void free_unref_folios(struct folio_batch *folios)
 			migratetype = MIGRATE_MOVABLE;
 
 		trace_mm_page_free_batched(&folio->page);
-		free_unref_page_commit(zone, pcp, &folio->page, migratetype,
+		free_frozen_page_commit(zone, pcp, &folio->page, migratetype,
 				order);
 	}
 
@@ -3567,7 +3568,6 @@ __alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
 	if (!page)
 		page = get_page_from_freelist(gfp_mask, order,
 				alloc_flags, ac);
-
 	return page;
 }
 
@@ -4531,28 +4531,23 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 }
 
 /*
- * __alloc_pages_bulk - Allocate a number of order-0 pages to a list or array
+ * __alloc_pages_bulk - Allocate a number of order-0 pages to an array
  * @gfp: GFP flags for the allocation
  * @preferred_nid: The preferred NUMA node ID to allocate from
  * @nodemask: Set of nodes to allocate from, may be NULL
- * @nr_pages: The number of pages desired on the list or array
- * @page_list: Optional list to store the allocated pages
- * @page_array: Optional array to store the pages
+ * @nr_pages: The number of pages desired in the array
+ * @page_array: Array to store the pages
  *
  * This is a batched version of the page allocator that attempts to
- * allocate nr_pages quickly. Pages are added to page_list if page_list
- * is not NULL, otherwise it is assumed that the page_array is valid.
+ * allocate nr_pages quickly. Pages are added to the page_array.
  *
- * For lists, nr_pages is the number of pages that should be allocated.
- *
- * For arrays, only NULL elements are populated with pages and nr_pages
+ * Note that only NULL elements are populated with pages and nr_pages
  * is the maximum number of pages that will be stored in the array.
  *
- * Returns the number of pages on the list or array.
+ * Returns the number of pages in the array.
  */
 unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 			nodemask_t *nodemask, int nr_pages,
-			struct list_head *page_list,
 			struct page **page_array)
 {
 	struct page *page;
@@ -4570,7 +4565,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 	 * Skip populated array elements to determine if any pages need
 	 * to be allocated before disabling IRQs.
 	 */
-	while (page_array && nr_populated < nr_pages && page_array[nr_populated])
+	while (nr_populated < nr_pages && page_array[nr_populated])
 		nr_populated++;
 
 	/* No pages requested? */
@@ -4578,7 +4573,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 		goto out;
 
 	/* Already populated array? */
-	if (unlikely(page_array && nr_pages - nr_populated == 0))
+	if (unlikely(nr_pages - nr_populated == 0))
 		goto out;
 
 	/* Bulk allocator does not support memcg accounting. */
@@ -4660,7 +4655,7 @@ retry_this_zone:
 	while (nr_populated < nr_pages) {
 
 		/* Skip existing pages */
-		if (page_array && page_array[nr_populated]) {
+		if (page_array[nr_populated]) {
 			nr_populated++;
 			continue;
 		}
@@ -4678,11 +4673,8 @@ retry_this_zone:
 		nr_account++;
 
 		prep_new_page(page, 0, gfp, 0);
-		if (page_list)
-			list_add(&page->lru, page_list);
-		else
-			page_array[nr_populated] = page;
-		nr_populated++;
+		set_page_refcounted(page);
+		page_array[nr_populated++] = page;
 	}
 
 	pcp_spin_unlock(pcp);
@@ -4699,14 +4691,8 @@ failed_irq:
 
 failed:
 	page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask);
-	if (page) {
-		if (page_list)
-			list_add(&page->lru, page_list);
-		else
-			page_array[nr_populated] = page;
-		nr_populated++;
-	}
-
+	if (page)
+		page_array[nr_populated++] = page;
 	goto out;
 }
 EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof);
@@ -4714,8 +4700,8 @@ EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof);
 /*
  * This is the 'heart' of the zoned buddy allocator.
  */
-struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order,
-				      int preferred_nid, nodemask_t *nodemask)
+struct page *__alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order,
+		int preferred_nid, nodemask_t *nodemask)
 {
 	struct page *page;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
@@ -4768,7 +4754,7 @@ struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order,
 out:
 	if (memcg_kmem_online() && (gfp & __GFP_ACCOUNT) && page &&
 	    unlikely(__memcg_kmem_charge_page(page, gfp, order) != 0)) {
-		__free_pages(page, order);
+		free_frozen_pages(page, order);
 		page = NULL;
 	}
 
@@ -4777,6 +4763,18 @@ out:
 
 	return page;
 }
+EXPORT_SYMBOL(__alloc_frozen_pages_noprof);
+
+struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order,
+		int preferred_nid, nodemask_t *nodemask)
+{
+	struct page *page;
+
+	page = __alloc_frozen_pages_noprof(gfp, order, preferred_nid, nodemask);
+	if (page)
+		set_page_refcounted(page);
+	return page;
+}
 EXPORT_SYMBOL(__alloc_pages_noprof);
 
 struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
@@ -4837,11 +4835,11 @@ void __free_pages(struct page *page, unsigned int order)
 	struct alloc_tag *tag = pgalloc_tag_get(page);
 
 	if (put_page_testzero(page))
-		free_unref_page(page, order);
+		free_frozen_pages(page, order);
 	else if (!head) {
 		pgalloc_tag_sub_pages(tag, (1 << order) - 1);
 		while (order-- > 0)
-			free_unref_page(page + (1 << order), order);
+			free_frozen_pages(page + (1 << order), order);
 	}
 }
 EXPORT_SYMBOL(__free_pages);
@@ -5161,13 +5159,6 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
 	zonerefs->zone_idx = 0;
 }
 
-/*
- * Build zonelists ordered by zone and nodes within zones.
- * This results in conserving DMA zone[s] until all Normal memory is
- * exhausted, but results in overflowing to remote node while memory
- * may still exist in local DMA zone.
- */
-
 static void build_zonelists(pg_data_t *pgdat)
 {
 	static int node_order[MAX_NUMNODES];
@@ -6175,7 +6166,7 @@ out:
 	return ret;
 }
 
-static struct ctl_table page_alloc_sysctl_table[] = {
+static const struct ctl_table page_alloc_sysctl_table[] = {
 	{
 		.procname	= "min_free_kbytes",
 		.data		= &min_free_kbytes,
@@ -6270,9 +6261,8 @@ static void alloc_contig_dump_pages(struct list_head *page_list)
  * @migratetype: using migratetype to filter the type of migration in
  *		trace_mm_alloc_contig_migrate_range_info.
  */
-int __alloc_contig_migrate_range(struct compact_control *cc,
-					unsigned long start, unsigned long end,
-					int migratetype)
+static int __alloc_contig_migrate_range(struct compact_control *cc,
+		unsigned long start, unsigned long end, int migratetype)
 {
 	/* This function is based on compact_zone() from compaction.c. */
 	unsigned int nr_reclaimed;
@@ -6281,7 +6271,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 	int ret = 0;
 	struct migration_target_control mtc = {
 		.nid = zone_to_nid(cc->zone),
-		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+		.gfp_mask = cc->gfp_mask,
 		.reason = MR_CONTIG_RANGE,
 	};
 	struct page *page;
@@ -6351,7 +6341,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 	return (ret < 0) ? ret : 0;
 }
 
-static void split_free_pages(struct list_head *list)
+static void split_free_pages(struct list_head *list, gfp_t gfp_mask)
 {
 	int order;
 
@@ -6362,7 +6352,8 @@ static void split_free_pages(struct list_head *list)
 		list_for_each_entry_safe(page, next, &list[order], lru) {
 			int i;
 
-			post_alloc_hook(page, order, __GFP_MOVABLE);
+			post_alloc_hook(page, order, gfp_mask);
+			set_page_refcounted(page);
 			if (!order)
 				continue;
 
@@ -6376,6 +6367,40 @@ static void split_free_pages(struct list_head *list)
 	}
 }
 
+static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask)
+{
+	const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM;
+	const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN |
+				  __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO;
+	const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN;
+
+	/*
+	 * We are given the range to allocate; node, mobility and placement
+	 * hints are irrelevant at this point. We'll simply ignore them.
+	 */
+	gfp_mask &= ~(GFP_ZONEMASK | __GFP_RECLAIMABLE | __GFP_WRITE |
+		      __GFP_HARDWALL | __GFP_THISNODE | __GFP_MOVABLE);
+
+	/*
+	 * We only support most reclaim flags (but not NOFAIL/NORETRY), and
+	 * selected action flags.
+	 */
+	if (gfp_mask & ~(reclaim_mask | action_mask))
+		return -EINVAL;
+
+	/*
+	 * Flags to control page compaction/migration/reclaim, to free up our
+	 * page range. Migratable pages are movable, __GFP_MOVABLE is implied
+	 * for them.
+	 *
+	 * Traditionally we always had __GFP_RETRY_MAYFAIL set, keep doing that
+	 * to not degrade callers.
+	 */
+	*gfp_cc_mask = (gfp_mask & (reclaim_mask | cc_action_mask)) |
+			__GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
+	return 0;
+}
+
 /**
  * alloc_contig_range() -- tries to allocate given range of pages
  * @start:	start PFN to allocate
@@ -6384,7 +6409,9 @@ static void split_free_pages(struct list_head *list)
  *			#MIGRATE_MOVABLE or #MIGRATE_CMA).  All pageblocks
  *			in range must have the same migratetype and it must
  *			be either of the two.
- * @gfp_mask:	GFP mask to use during compaction
+ * @gfp_mask:	GFP mask. Node/zone/placement hints are ignored; only some
+ *		action and reclaim modifiers are supported. Reclaim modifiers
+ *		control allocation behavior during compaction/migration/reclaim.
  *
  * The PFN range does not have to be pageblock aligned. The PFN range must
  * belong to a single zone.
@@ -6410,11 +6437,14 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 		.no_set_skip_hint = true,
-		.gfp_mask = current_gfp_context(gfp_mask),
 		.alloc_contig = true,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 
+	gfp_mask = current_gfp_context(gfp_mask);
+	if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask))
+		return -EINVAL;
+
 	/*
 	 * What we do here is we mark all pageblocks in range as
 	 * MIGRATE_ISOLATE.  Because pageblock and max order pages may
@@ -6436,7 +6466,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 	 * put back to page allocator so that buddy can use them.
 	 */
 
-	ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask);
+	ret = start_isolate_page_range(start, end, migratetype, 0);
 	if (ret)
 		goto done;
 
@@ -6455,7 +6485,17 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 	ret = __alloc_contig_migrate_range(&cc, start, end, migratetype);
 	if (ret && ret != -EBUSY)
 		goto done;
-	ret = 0;
+
+	/*
+	 * When in-use hugetlb pages are migrated, they may simply be released
+	 * back into the free hugepage pool instead of being returned to the
+	 * buddy system.  After the migration of in-use huge pages is completed,
+	 * we will invoke replace_free_hugepage_folios() to ensure that these
+	 * hugepages are properly released to the buddy system.
+	 */
+	ret = replace_free_hugepage_folios(start, end);
+	if (ret)
+		goto done;
 
 	/*
 	 * Pages from [start, end) are within a pageblock_nr_pages
@@ -6489,7 +6529,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 	}
 
 	if (!(gfp_mask & __GFP_COMP)) {
-		split_free_pages(cc.freepages);
+		split_free_pages(cc.freepages, gfp_mask);
 
 		/* Free head and tail (if any) */
 		if (start != outer_start)
@@ -6502,6 +6542,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 
 		check_new_pages(head, order);
 		prep_new_page(head, order, gfp_mask, 0);
+		set_page_refcounted(head);
 	} else {
 		ret = -EINVAL;
 		WARN(true, "PFN range: requested [%lu, %lu), allocated [%lu, %lu)\n",
@@ -6556,7 +6597,9 @@ static bool zone_spans_last_pfn(const struct zone *zone,
 /**
  * alloc_contig_pages() -- tries to find and allocate contiguous range of pages
  * @nr_pages:	Number of contiguous pages to allocate
- * @gfp_mask:	GFP mask to limit search and used during compaction
+ * @gfp_mask:	GFP mask. Node/zone/placement hints limit the search; only some
+ *		action and reclaim modifiers are supported. Reclaim modifiers
+ *		control allocation behavior during compaction/migration/reclaim.
  * @nid:	Target node
  * @nodemask:	Mask for other possible nodes
  *
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 3f7a203d35c6..d2423f30577e 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -86,7 +86,7 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
 
 	if (page_ref_sub_and_test(page, count))
-		free_unref_page(page, compound_order(page));
+		free_frozen_pages(page, compound_order(page));
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
@@ -138,7 +138,7 @@ refill:
 			goto refill;
 
 		if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) {
-			free_unref_page(page,
+			free_frozen_pages(page,
 					encoded_page_decode_order(encoded_page));
 			goto refill;
 		}
@@ -166,6 +166,6 @@ void page_frag_free(void *addr)
 	struct page *page = virt_to_head_page(addr);
 
 	if (unlikely(put_page_testzero(page)))
-		free_unref_page(page, compound_order(page));
+		free_frozen_pages(page, compound_order(page));
 }
 EXPORT_SYMBOL(page_frag_free);
diff --git a/mm/page_idle.c b/mm/page_idle.c
index 41ea77f22011..947c7c7a3728 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -112,7 +112,7 @@ static void page_idle_clear_pte_refs(struct folio *folio)
 }
 
 static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
-				     struct bin_attribute *attr, char *buf,
+				     const struct bin_attribute *attr, char *buf,
 				     loff_t pos, size_t count)
 {
 	u64 *out = (u64 *)buf;
@@ -157,7 +157,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
 }
 
 static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
-				      struct bin_attribute *attr, char *buf,
+				      const struct bin_attribute *attr, char *buf,
 				      loff_t pos, size_t count)
 {
 	const u64 *in = (u64 *)buf;
@@ -193,17 +193,17 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
 	return (char *)in - buf;
 }
 
-static struct bin_attribute page_idle_bitmap_attr =
+static const struct bin_attribute page_idle_bitmap_attr =
 		__BIN_ATTR(bitmap, 0600,
 			   page_idle_bitmap_read, page_idle_bitmap_write, 0);
 
-static struct bin_attribute *page_idle_bin_attrs[] = {
+static const struct bin_attribute *const page_idle_bin_attrs[] = {
 	&page_idle_bitmap_attr,
 	NULL,
 };
 
 static const struct attribute_group page_idle_attr_group = {
-	.bin_attrs = page_idle_bin_attrs,
+	.bin_attrs_new = page_idle_bin_attrs,
 	.name = "page_idle",
 };
 
diff --git a/mm/page_io.c b/mm/page_io.c
index 4b4ea8e49cf6..9b983de351f9 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -163,7 +163,6 @@ reprobe:
 		page_no = 1;	/* force Empty message */
 	sis->max = page_no;
 	sis->pages = page_no - 1;
-	sis->highest_bit = page_no - 1;
 out:
 	return ret;
 bad_bmap:
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 7e04047977cf..c608e9d72865 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -286,7 +286,6 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * within a free or in-use page.
  * @boundary_pfn:		pageblock-aligned pfn that a page might cross
  * @flags:			isolation flags
- * @gfp_flags:			GFP flags used for migrating pages
  * @isolate_before:	isolate the pageblock before the boundary_pfn
  * @skip_isolation:	the flag to skip the pageblock isolation in second
  *			isolate_single_pageblock()
@@ -306,8 +305,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * the in-use page then splitting the free page.
  */
 static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
-			gfp_t gfp_flags, bool isolate_before, bool skip_isolation,
-			int migratetype)
+		bool isolate_before, bool skip_isolation, int migratetype)
 {
 	unsigned long start_pfn;
 	unsigned long isolate_pageblock;
@@ -444,8 +442,6 @@ failed:
  *					 and PageOffline() pages.
  *			REPORT_FAILURE - report details about the failure to
  *			isolate the range
- * @gfp_flags:		GFP flags used for migrating pages that sit across the
- *			range boundaries.
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
@@ -478,7 +474,7 @@ failed:
  * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype, int flags, gfp_t gfp_flags)
+			     int migratetype, int flags)
 {
 	unsigned long pfn;
 	struct page *page;
@@ -489,7 +485,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	bool skip_isolation = false;
 
 	/* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */
-	ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false,
+	ret = isolate_single_pageblock(isolate_start, flags, false,
 			skip_isolation, migratetype);
 	if (ret)
 		return ret;
@@ -498,7 +494,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		skip_isolation = true;
 
 	/* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */
-	ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true,
+	ret = isolate_single_pageblock(isolate_end, flags, true,
 			skip_isolation, migratetype);
 	if (ret) {
 		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
diff --git a/mm/percpu.c b/mm/percpu.c
index d8dd31a2e407..ac61e3fc5f15 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1359,10 +1359,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	/* allocate chunk */
 	alloc_size = struct_size(chunk, populated,
 				 BITS_TO_LONGS(region_size >> PAGE_SHIFT));
-	chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!chunk)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	chunk = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	INIT_LIST_HEAD(&chunk->list);
 
@@ -1374,24 +1371,14 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
 	region_bits = pcpu_chunk_map_bits(chunk);
 
 	alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]);
-	chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!chunk->alloc_map)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	chunk->alloc_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	alloc_size =
 		BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]);
-	chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!chunk->bound_map)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	chunk->bound_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]);
-	chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!chunk->md_blocks)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
-
+	chunk->md_blocks = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 #ifdef NEED_PCPUOBJ_EXT
 	/* first chunk is free to use */
 	chunk->obj_exts = NULL;
@@ -2595,28 +2582,16 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* process group information and build config tables accordingly */
 	alloc_size = ai->nr_groups * sizeof(group_offsets[0]);
-	group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!group_offsets)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	group_offsets = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	alloc_size = ai->nr_groups * sizeof(group_sizes[0]);
-	group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!group_sizes)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	group_sizes = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	alloc_size = nr_cpu_ids * sizeof(unit_map[0]);
-	unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!unit_map)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	unit_map = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	alloc_size = nr_cpu_ids * sizeof(unit_off[0]);
-	unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES);
-	if (!unit_off)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      alloc_size);
+	unit_off = memblock_alloc_or_panic(alloc_size, SMP_CACHE_BYTES);
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
@@ -2685,12 +2660,9 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	pcpu_free_slot = pcpu_sidelined_slot + 1;
 	pcpu_to_depopulate_slot = pcpu_free_slot + 1;
 	pcpu_nr_slots = pcpu_to_depopulate_slot + 1;
-	pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots *
+	pcpu_chunk_lists = memblock_alloc_or_panic(pcpu_nr_slots *
 					  sizeof(pcpu_chunk_lists[0]),
 					  SMP_CACHE_BYTES);
-	if (!pcpu_chunk_lists)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]));
 
 	for (i = 0; i < pcpu_nr_slots; i++)
 		INIT_LIST_HEAD(&pcpu_chunk_lists[i]);
@@ -3155,25 +3127,19 @@ void __init __weak pcpu_populate_pte(unsigned long addr)
 	pmd_t *pmd;
 
 	if (pgd_none(*pgd)) {
-		p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
-		if (!p4d)
-			goto err_alloc;
+		p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
 		pgd_populate(&init_mm, pgd, p4d);
 	}
 
 	p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d)) {
-		pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
-		if (!pud)
-			goto err_alloc;
+		pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
 		p4d_populate(&init_mm, p4d, pud);
 	}
 
 	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
-		pmd = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
-		if (!pmd)
-			goto err_alloc;
+		pmd = memblock_alloc_or_panic(PMD_TABLE_SIZE, PMD_TABLE_SIZE);
 		pud_populate(&init_mm, pud, pmd);
 	}
 
@@ -3181,16 +3147,11 @@ void __init __weak pcpu_populate_pte(unsigned long addr)
 	if (!pmd_present(*pmd)) {
 		pte_t *new;
 
-		new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
-		if (!new)
-			goto err_alloc;
+		new = memblock_alloc_or_panic(PTE_TABLE_SIZE, PTE_TABLE_SIZE);
 		pmd_populate_kernel(&init_mm, pmd, new);
 	}
 
 	return;
-
-err_alloc:
-	panic("%s: Failed to allocate memory\n", __func__);
 }
 
 /**
@@ -3237,10 +3198,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 	/* unaligned allocations can't be freed, round up to page size */
 	pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() *
 			       sizeof(pages[0]));
-	pages = memblock_alloc(pages_size, SMP_CACHE_BYTES);
-	if (!pages)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      pages_size);
+	pages = memblock_alloc_or_panic(pages_size, SMP_CACHE_BYTES);
 
 	/* allocate pages */
 	j = 0;
diff --git a/mm/pt_reclaim.c b/mm/pt_reclaim.c
new file mode 100644
index 000000000000..7e9455a18aae
--- /dev/null
+++ b/mm/pt_reclaim.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/hugetlb.h>
+#include <asm-generic/tlb.h>
+#include <asm/pgalloc.h>
+
+#include "internal.h"
+
+bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
+			   struct zap_details *details)
+{
+	return details && details->reclaim_pt && (end - start >= PMD_SIZE);
+}
+
+bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval)
+{
+	spinlock_t *pml = pmd_lockptr(mm, pmd);
+
+	if (!spin_trylock(pml))
+		return false;
+
+	*pmdval = pmdp_get_lockless(pmd);
+	pmd_clear(pmd);
+	spin_unlock(pml);
+
+	return true;
+}
+
+void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb,
+	      pmd_t pmdval)
+{
+	pte_free_tlb(tlb, pmd_pgtable(pmdval), addr);
+	mm_dec_nr_ptes(mm);
+}
+
+void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr,
+		     struct mmu_gather *tlb)
+{
+	pmd_t pmdval;
+	spinlock_t *pml, *ptl = NULL;
+	pte_t *start_pte, *pte;
+	int i;
+
+	pml = pmd_lock(mm, pmd);
+	start_pte = pte_offset_map_rw_nolock(mm, pmd, addr, &pmdval, &ptl);
+	if (!start_pte)
+		goto out_ptl;
+	if (ptl != pml)
+		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
+
+	/* Check if it is empty PTE page */
+	for (i = 0, pte = start_pte; i < PTRS_PER_PTE; i++, pte++) {
+		if (!pte_none(ptep_get(pte)))
+			goto out_ptl;
+	}
+	pte_unmap(start_pte);
+
+	pmd_clear(pmd);
+
+	if (ptl != pml)
+		spin_unlock(ptl);
+	spin_unlock(pml);
+
+	free_pte(mm, addr, tlb, pmdval);
+
+	return;
+out_ptl:
+	if (start_pte)
+		pte_unmap_unlock(start_pte, ptl);
+	if (ptl != pml)
+		spin_unlock(pml);
+}
diff --git a/mm/readahead.c b/mm/readahead.c
index 95e3e71abb6b..220155a5c964 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -159,20 +159,10 @@ static void read_pages(struct readahead_control *rac)
 
 	if (aops->readahead) {
 		aops->readahead(rac);
-		/*
-		 * Clean up the remaining folios.  The sizes in ->ra
-		 * may be used to size the next readahead, so make sure
-		 * they accurately reflect what happened.
-		 */
+		/* Clean up the remaining folios. */
 		while ((folio = readahead_folio(rac)) != NULL) {
-			unsigned long nr = folio_nr_pages(folio);
-
 			folio_get(folio);
-			rac->ra->size -= nr;
-			if (rac->ra->async_size >= nr) {
-				rac->ra->async_size -= nr;
-				filemap_remove_folio(folio);
-			}
+			filemap_remove_folio(folio);
 			folio_unlock(folio);
 			folio_put(folio);
 		}
@@ -189,6 +179,18 @@ static void read_pages(struct readahead_control *rac)
 	BUG_ON(readahead_count(rac));
 }
 
+static struct folio *ractl_alloc_folio(struct readahead_control *ractl,
+				       gfp_t gfp_mask, unsigned int order)
+{
+	struct folio *folio;
+
+	folio = filemap_alloc_folio(gfp_mask, order);
+	if (folio && ractl->dropbehind)
+		__folio_set_dropbehind(folio);
+
+	return folio;
+}
+
 /**
  * page_cache_ra_unbounded - Start unchecked readahead.
  * @ractl: Readahead control.
@@ -266,8 +268,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			continue;
 		}
 
-		folio = filemap_alloc_folio(gfp_mask,
-					    mapping_min_folio_order(mapping));
+		folio = ractl_alloc_folio(ractl, gfp_mask,
+					mapping_min_folio_order(mapping));
 		if (!folio)
 			break;
 
@@ -437,7 +439,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 		pgoff_t mark, unsigned int order, gfp_t gfp)
 {
 	int err;
-	struct folio *folio = filemap_alloc_folio(gfp, order);
+	struct folio *folio = ractl_alloc_folio(ractl, gfp, order);
 
 	if (!folio)
 		return -ENOMEM;
@@ -459,7 +461,8 @@ void page_cache_ra_order(struct readahead_control *ractl,
 		struct file_ra_state *ra, unsigned int new_order)
 {
 	struct address_space *mapping = ractl->mapping;
-	pgoff_t index = readahead_index(ractl);
+	pgoff_t start = readahead_index(ractl);
+	pgoff_t index = start;
 	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
 	pgoff_t mark = index + ra->size - ra->async_size;
@@ -517,12 +520,18 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	/*
 	 * If there were already pages in the page cache, then we may have
 	 * left some gaps.  Let the regular readahead code take care of this
-	 * situation.
+	 * situation below.
 	 */
 	if (!err)
 		return;
 fallback:
-	do_page_cache_ra(ractl, ra->size, ra->async_size);
+	/*
+	 * ->readahead() may have updated readahead window size so we have to
+	 * check there's still something to read.
+	 */
+	if (ra->size > index - start)
+		do_page_cache_ra(ractl, ra->size - (index - start),
+				 ra->async_size);
 }
 
 static unsigned long ractl_max_pages(struct readahead_control *ractl,
@@ -768,7 +777,7 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, min_order);
+		folio = ractl_alloc_folio(ractl, gfp_mask, min_order);
 		if (!folio)
 			return;
 
@@ -797,7 +806,7 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, min_order);
+		folio = ractl_alloc_folio(ractl, gfp_mask, min_order);
 		if (!folio)
 			return;
 
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
index 6d783436951f..e7173fcd210c 100644
--- a/mm/rodata_test.c
+++ b/mm/rodata_test.c
@@ -12,7 +12,8 @@
 #include <linux/mm.h>
 #include <asm/sections.h>
 
-static const int rodata_test_data = 0xC3;
+#define TEST_VALUE 0xC3
+static const int rodata_test_data = TEST_VALUE;
 
 void rodata_test(void)
 {
@@ -20,7 +21,7 @@ void rodata_test(void)
 
 	/* test 1: read the value */
 	/* If this test fails, some previous testrun has clobbered the state */
-	if (!rodata_test_data) {
+	if (unlikely(READ_ONCE(rodata_test_data) != TEST_VALUE)) {
 		pr_err("test 1 fails (start data)\n");
 		return;
 	}
@@ -33,7 +34,7 @@ void rodata_test(void)
 	}
 
 	/* test 3: check the value hasn't changed */
-	if (rodata_test_data == zero) {
+	if (unlikely(READ_ONCE(rodata_test_data) != TEST_VALUE)) {
 		pr_err("test data was changed\n");
 		return;
 	}
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 399552814fd0..1b0a214ee558 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -195,14 +195,13 @@ static struct file *secretmem_file_create(unsigned long flags)
 	struct file *file;
 	struct inode *inode;
 	const char *anon_name = "[secretmem]";
-	const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name));
 	int err;
 
 	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	err = security_inode_init_security_anon(inode, &qname, NULL);
+	err = security_inode_init_security_anon(inode, &QSTR(anon_name), NULL);
 	if (err) {
 		file = ERR_PTR(err);
 		goto err_free_inode;
diff --git a/mm/shmem.c b/mm/shmem.c
index 532afd8e049c..4ea6109a8043 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -553,38 +553,105 @@ static bool shmem_confirm_swap(struct address_space *mapping,
 /* ifdef here to avoid bloating shmem.o when not necessary */
 
 static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
+static int tmpfs_huge __read_mostly = SHMEM_HUGE_NEVER;
 
-static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
-				      loff_t write_end, bool shmem_huge_force,
-				      unsigned long vm_flags)
+/**
+ * shmem_mapping_size_orders - Get allowable folio orders for the given file size.
+ * @mapping: Target address_space.
+ * @index: The page index.
+ * @write_end: end of a write, could extend inode size.
+ *
+ * This returns huge orders for folios (when supported) based on the file size
+ * which the mapping currently allows at the given index. The index is relevant
+ * due to alignment considerations the mapping might have. The returned order
+ * may be less than the size passed.
+ *
+ * Return: The orders.
+ */
+static inline unsigned int
+shmem_mapping_size_orders(struct address_space *mapping, pgoff_t index, loff_t write_end)
 {
+	unsigned int order;
+	size_t size;
+
+	if (!mapping_large_folio_support(mapping) || !write_end)
+		return 0;
+
+	/* Calculate the write size based on the write_end */
+	size = write_end - (index << PAGE_SHIFT);
+	order = filemap_get_order(size);
+	if (!order)
+		return 0;
+
+	/* If we're not aligned, allocate a smaller folio */
+	if (index & ((1UL << order) - 1))
+		order = __ffs(index);
+
+	order = min_t(size_t, order, MAX_PAGECACHE_ORDER);
+	return order > 0 ? BIT(order + 1) - 1 : 0;
+}
+
+static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
+					      loff_t write_end, bool shmem_huge_force,
+					      struct vm_area_struct *vma,
+					      unsigned long vm_flags)
+{
+	unsigned int maybe_pmd_order = HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER ?
+		0 : BIT(HPAGE_PMD_ORDER);
+	unsigned long within_size_orders;
+	unsigned int order;
+	pgoff_t aligned_index;
 	loff_t i_size;
 
-	if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER)
-		return false;
 	if (!S_ISREG(inode->i_mode))
-		return false;
+		return 0;
 	if (shmem_huge == SHMEM_HUGE_DENY)
-		return false;
+		return 0;
 	if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
-		return true;
+		return maybe_pmd_order;
 
+	/*
+	 * The huge order allocation for anon shmem is controlled through
+	 * the mTHP interface, so we still use PMD-sized huge order to
+	 * check whether global control is enabled.
+	 *
+	 * For tmpfs mmap()'s huge order, we still use PMD-sized order to
+	 * allocate huge pages due to lack of a write size hint.
+	 *
+	 * Otherwise, tmpfs will allow getting a highest order hint based on
+	 * the size of write and fallocate paths, then will try each allowable
+	 * huge orders.
+	 */
 	switch (SHMEM_SB(inode->i_sb)->huge) {
 	case SHMEM_HUGE_ALWAYS:
-		return true;
+		if (vma)
+			return maybe_pmd_order;
+
+		return shmem_mapping_size_orders(inode->i_mapping, index, write_end);
 	case SHMEM_HUGE_WITHIN_SIZE:
-		index = round_up(index + 1, HPAGE_PMD_NR);
-		i_size = max(write_end, i_size_read(inode));
-		i_size = round_up(i_size, PAGE_SIZE);
-		if (i_size >> PAGE_SHIFT >= index)
-			return true;
+		if (vma)
+			within_size_orders = maybe_pmd_order;
+		else
+			within_size_orders = shmem_mapping_size_orders(inode->i_mapping,
+								       index, write_end);
+
+		order = highest_order(within_size_orders);
+		while (within_size_orders) {
+			aligned_index = round_up(index + 1, 1 << order);
+			i_size = max(write_end, i_size_read(inode));
+			i_size = round_up(i_size, PAGE_SIZE);
+			if (i_size >> PAGE_SHIFT >= aligned_index)
+				return within_size_orders;
+
+			order = next_order(&within_size_orders, order);
+		}
 		fallthrough;
 	case SHMEM_HUGE_ADVISE:
 		if (vm_flags & VM_HUGEPAGE)
-			return true;
+			return maybe_pmd_order;
 		fallthrough;
 	default:
-		return false;
+		return 0;
 	}
 }
 
@@ -779,11 +846,12 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 	return 0;
 }
 
-static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
-				      loff_t write_end, bool shmem_huge_force,
-				      unsigned long vm_flags)
+static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
+					      loff_t write_end, bool shmem_huge_force,
+					      struct vm_area_struct *vma,
+					      unsigned long vm_flags)
 {
-	return false;
+	return 0;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -1180,7 +1248,7 @@ static int shmem_getattr(struct mnt_idmap *idmap,
 			STATX_ATTR_NODUMP);
 	generic_fillattr(idmap, request_mask, inode, stat);
 
-	if (shmem_huge_global_enabled(inode, 0, 0, false, 0))
+	if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0))
 		stat->blksize = HPAGE_PMD_SIZE;
 
 	if (request_mask & STATX_BTIME) {
@@ -1690,22 +1758,18 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode,
 	unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size);
 	unsigned long vm_flags = vma ? vma->vm_flags : 0;
 	pgoff_t aligned_index;
-	bool global_huge;
+	unsigned int global_orders;
 	loff_t i_size;
 	int order;
 
 	if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags)))
 		return 0;
 
-	global_huge = shmem_huge_global_enabled(inode, index, write_end,
-						shmem_huge_force, vm_flags);
-	if (!vma || !vma_is_anon_shmem(vma)) {
-		/*
-		 * For tmpfs, we now only support PMD sized THP if huge page
-		 * is enabled, otherwise fallback to order 0.
-		 */
-		return global_huge ? BIT(HPAGE_PMD_ORDER) : 0;
-	}
+	global_orders = shmem_huge_global_enabled(inode, index, write_end,
+						  shmem_huge_force, vma, vm_flags);
+	/* Tmpfs huge pages allocation */
+	if (!vma || !vma_is_anon_shmem(vma))
+		return global_orders;
 
 	/*
 	 * Following the 'deny' semantics of the top level, force the huge
@@ -1737,7 +1801,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode,
 	if (vm_flags & VM_HUGEPAGE)
 		mask |= READ_ONCE(huge_shmem_orders_madvise);
 
-	if (global_huge)
+	if (global_orders > 0)
 		mask |= READ_ONCE(huge_shmem_orders_inherit);
 
 	return THP_ORDERS_ALL_FILE_DEFAULT & mask;
@@ -1903,6 +1967,65 @@ unlock:
 	return ERR_PTR(error);
 }
 
+static struct folio *shmem_swap_alloc_folio(struct inode *inode,
+		struct vm_area_struct *vma, pgoff_t index,
+		swp_entry_t entry, int order, gfp_t gfp)
+{
+	struct shmem_inode_info *info = SHMEM_I(inode);
+	struct folio *new;
+	void *shadow;
+	int nr_pages;
+
+	/*
+	 * We have arrived here because our zones are constrained, so don't
+	 * limit chance of success with further cpuset and node constraints.
+	 */
+	gfp &= ~GFP_CONSTRAINT_MASK;
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && order > 0) {
+		gfp_t huge_gfp = vma_thp_gfp_mask(vma);
+
+		gfp = limit_gfp_mask(huge_gfp, gfp);
+	}
+
+	new = shmem_alloc_folio(gfp, order, info, index);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+
+	nr_pages = folio_nr_pages(new);
+	if (mem_cgroup_swapin_charge_folio(new, vma ? vma->vm_mm : NULL,
+					   gfp, entry)) {
+		folio_put(new);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/*
+	 * Prevent parallel swapin from proceeding with the swap cache flag.
+	 *
+	 * Of course there is another possible concurrent scenario as well,
+	 * that is to say, the swap cache flag of a large folio has already
+	 * been set by swapcache_prepare(), while another thread may have
+	 * already split the large swap entry stored in the shmem mapping.
+	 * In this case, shmem_add_to_page_cache() will help identify the
+	 * concurrent swapin and return -EEXIST.
+	 */
+	if (swapcache_prepare(entry, nr_pages)) {
+		folio_put(new);
+		return ERR_PTR(-EEXIST);
+	}
+
+	__folio_set_locked(new);
+	__folio_set_swapbacked(new);
+	new->swap = entry;
+
+	mem_cgroup_swapin_uncharge_swap(entry, nr_pages);
+	shadow = get_shadow_from_swap_cache(entry);
+	if (shadow)
+		workingset_refault(new, shadow);
+	folio_add_lru(new);
+	swap_read_folio(new, NULL);
+	return new;
+}
+
 /*
  * When a page is moved from swapcache to shmem filecache (either by the
  * usual swapin of shmem_get_folio_gfp(), or by the less common swapoff of
@@ -2006,7 +2129,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
 }
 
 static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
-					 struct folio *folio, swp_entry_t swap)
+					 struct folio *folio, swp_entry_t swap,
+					 bool skip_swapcache)
 {
 	struct address_space *mapping = inode->i_mapping;
 	swp_entry_t swapin_error;
@@ -2022,7 +2146,8 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
 
 	nr_pages = folio_nr_pages(folio);
 	folio_wait_writeback(folio);
-	delete_from_swap_cache(folio);
+	if (!skip_swapcache)
+		delete_from_swap_cache(folio);
 	/*
 	 * Don't treat swapin error folio as alloced. Otherwise inode->i_blocks
 	 * won't be 0 when inode is released and thus trigger WARN_ON(i_blocks)
@@ -2126,6 +2251,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct swap_info_struct *si;
 	struct folio *folio = NULL;
+	bool skip_swapcache = false;
 	swp_entry_t swap;
 	int error, nr_pages;
 
@@ -2147,6 +2273,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	/* Look it up and read it in.. */
 	folio = swap_cache_get_folio(swap, NULL, 0);
 	if (!folio) {
+		int order = xa_get_order(&mapping->i_pages, index);
+		bool fallback_order0 = false;
 		int split_order;
 
 		/* Or update major stats only when swapin succeeds?? */
@@ -2157,6 +2285,33 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 		}
 
 		/*
+		 * If uffd is active for the vma, we need per-page fault
+		 * fidelity to maintain the uffd semantics, then fallback
+		 * to swapin order-0 folio, as well as for zswap case.
+		 */
+		if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) ||
+				  !zswap_never_enabled()))
+			fallback_order0 = true;
+
+		/* Skip swapcache for synchronous device. */
+		if (!fallback_order0 && data_race(si->flags & SWP_SYNCHRONOUS_IO)) {
+			folio = shmem_swap_alloc_folio(inode, vma, index, swap, order, gfp);
+			if (!IS_ERR(folio)) {
+				skip_swapcache = true;
+				goto alloced;
+			}
+
+			/*
+			 * Fallback to swapin order-0 folio unless the swap entry
+			 * already exists.
+			 */
+			error = PTR_ERR(folio);
+			folio = NULL;
+			if (error == -EEXIST)
+				goto failed;
+		}
+
+		/*
 		 * Now swap device can only swap in order 0 folio, then we
 		 * should split the large swap entry stored in the pagecache
 		 * if necessary.
@@ -2186,9 +2341,10 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 		}
 	}
 
+alloced:
 	/* We have to do this with folio locked to prevent races */
 	folio_lock(folio);
-	if (!folio_test_swapcache(folio) ||
+	if ((!skip_swapcache && !folio_test_swapcache(folio)) ||
 	    folio->swap.val != swap.val ||
 	    !shmem_confirm_swap(mapping, index, swap)) {
 		error = -EEXIST;
@@ -2224,7 +2380,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	if (sgp == SGP_WRITE)
 		folio_mark_accessed(folio);
 
-	delete_from_swap_cache(folio);
+	if (skip_swapcache) {
+		folio->swap.val = 0;
+		swapcache_clear(si, swap, nr_pages);
+	} else {
+		delete_from_swap_cache(folio);
+	}
 	folio_mark_dirty(folio);
 	swap_free_nr(swap, nr_pages);
 	put_swap_device(si);
@@ -2235,8 +2396,11 @@ failed:
 	if (!shmem_confirm_swap(mapping, index, swap))
 		error = -EEXIST;
 	if (error == -EIO)
-		shmem_set_folio_swapin_error(inode, index, folio, swap);
+		shmem_set_folio_swapin_error(inode, index, folio, swap,
+					     skip_swapcache);
 unlock:
+	if (skip_swapcache)
+		swapcache_clear(si, swap, folio_nr_pages(folio));
 	if (folio) {
 		folio_unlock(folio);
 		folio_put(folio);
@@ -2752,12 +2916,6 @@ out_nomem:
 static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
-	struct shmem_inode_info *info = SHMEM_I(inode);
-	int ret;
-
-	ret = seal_check_write(info->seals, vma);
-	if (ret)
-		return ret;
 
 	file_accessed(file);
 	/* This is anonymous shared memory if it is unlinked at the time of mmap */
@@ -4585,48 +4743,37 @@ bad_value:
 	return invalfc(fc, "Bad value for '%s'", param->key);
 }
 
-static int shmem_parse_options(struct fs_context *fc, void *data)
+static char *shmem_next_opt(char **s)
 {
-	char *options = data;
+	char *sbegin = *s;
+	char *p;
 
-	if (options) {
-		int err = security_sb_eat_lsm_opts(options, &fc->security);
-		if (err)
-			return err;
-	}
+	if (sbegin == NULL)
+		return NULL;
 
-	while (options != NULL) {
-		char *this_char = options;
-		for (;;) {
-			/*
-			 * NUL-terminate this option: unfortunately,
-			 * mount options form a comma-separated list,
-			 * but mpol's nodelist may also contain commas.
-			 */
-			options = strchr(options, ',');
-			if (options == NULL)
-				break;
-			options++;
-			if (!isdigit(*options)) {
-				options[-1] = '\0';
-				break;
-			}
-		}
-		if (*this_char) {
-			char *value = strchr(this_char, '=');
-			size_t len = 0;
-			int err;
-
-			if (value) {
-				*value++ = '\0';
-				len = strlen(value);
-			}
-			err = vfs_parse_fs_string(fc, this_char, value, len);
-			if (err < 0)
-				return err;
+	/*
+	 * NUL-terminate this option: unfortunately,
+	 * mount options form a comma-separated list,
+	 * but mpol's nodelist may also contain commas.
+	 */
+	for (;;) {
+		p = strchr(*s, ',');
+		if (p == NULL)
+			break;
+		*s = p + 1;
+		if (!isdigit(*(p+1))) {
+			*p = '\0';
+			return sbegin;
 		}
 	}
-	return 0;
+
+	*s = NULL;
+	return sbegin;
+}
+
+static int shmem_parse_monolithic(struct fs_context *fc, void *data)
+{
+	return vfs_parse_monolithic_sep(fc, data, shmem_next_opt);
 }
 
 /*
@@ -4893,7 +5040,12 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 	sbinfo->gid = ctx->gid;
 	sbinfo->full_inums = ctx->full_inums;
 	sbinfo->mode = ctx->mode;
-	sbinfo->huge = ctx->huge;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (ctx->seen & SHMEM_SEEN_HUGE)
+		sbinfo->huge = ctx->huge;
+	else
+		sbinfo->huge = tmpfs_huge;
+#endif
 	sbinfo->mpol = ctx->mpol;
 	ctx->mpol = NULL;
 
@@ -4971,7 +5123,7 @@ static const struct fs_context_operations shmem_fs_context_ops = {
 	.free			= shmem_free_fc,
 	.get_tree		= shmem_get_tree,
 #ifdef CONFIG_TMPFS
-	.parse_monolithic	= shmem_parse_options,
+	.parse_monolithic	= shmem_parse_monolithic,
 	.parse_param		= shmem_parse_one,
 	.reconfigure		= shmem_reconfigure,
 #endif
@@ -5444,6 +5596,21 @@ static int __init setup_transparent_hugepage_shmem(char *str)
 }
 __setup("transparent_hugepage_shmem=", setup_transparent_hugepage_shmem);
 
+static int __init setup_transparent_hugepage_tmpfs(char *str)
+{
+	int huge;
+
+	huge = shmem_parse_huge(str);
+	if (huge < 0) {
+		pr_warn("transparent_hugepage_tmpfs= cannot parse, ignored\n");
+		return huge;
+	}
+
+	tmpfs_huge = huge;
+	return 1;
+}
+__setup("transparent_hugepage_tmpfs=", setup_transparent_hugepage_tmpfs);
+
 static char str_dup[PAGE_SIZE] __initdata;
 static int __init setup_thp_shmem(char *str)
 {
diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c
index 4a85b94d12ce..794bd433cce0 100644
--- a/mm/shrinker_debug.c
+++ b/mm/shrinker_debug.c
@@ -195,8 +195,6 @@ int shrinker_debugfs_add(struct shrinker *shrinker)
 
 int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 {
-	struct dentry *entry;
-	char buf[128];
 	const char *new, *old;
 	va_list ap;
 	int ret = 0;
@@ -213,18 +211,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 	old = shrinker->name;
 	shrinker->name = new;
 
-	if (shrinker->debugfs_entry) {
-		snprintf(buf, sizeof(buf), "%s-%d", shrinker->name,
-			 shrinker->debugfs_id);
-
-		entry = debugfs_rename(shrinker_debugfs_root,
-				       shrinker->debugfs_entry,
-				       shrinker_debugfs_root, buf);
-		if (IS_ERR(entry))
-			ret = PTR_ERR(entry);
-		else
-			shrinker->debugfs_entry = entry;
-	}
+	ret = debugfs_change_name(shrinker->debugfs_entry, "%s-%d",
+			shrinker->name, shrinker->debugfs_id);
 
 	mutex_unlock(&shrinker_mutex);
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 69f2d19010de..4030907b6b7d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1944,7 +1944,7 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr)
 		return;
 	}
 
-	kasan_record_aux_stack_noalloc(ptr);
+	kasan_record_aux_stack(ptr);
 	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
diff --git a/mm/slub.c b/mm/slub.c
index c2151c9fee22..1f50129dcfb3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2311,7 +2311,7 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init,
 			 * We have to do this manually because the rcu_head is
 			 * not located inside the object.
 			 */
-			kasan_record_aux_stack_noalloc(x);
+			kasan_record_aux_stack(x);
 
 			delayed_free->object = x;
 			call_rcu(&delayed_free->head, slab_free_after_rcu_debug);
@@ -2420,17 +2420,15 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node,
 	unsigned int order = oo_order(oo);
 
 	if (node == NUMA_NO_NODE)
-		folio = (struct folio *)alloc_pages(flags, order);
+		folio = (struct folio *)alloc_frozen_pages(flags, order);
 	else
-		folio = (struct folio *)__alloc_pages_node(node, flags, order);
+		folio = (struct folio *)__alloc_frozen_pages(flags, order, node, NULL);
 
 	if (!folio)
 		return NULL;
 
 	slab = folio_slab(folio);
 	__folio_set_slab(folio);
-	/* Make the flag visible before any changes to folio->mapping */
-	smp_wmb();
 	if (folio_is_pfmemalloc(folio))
 		slab_set_pfmemalloc(slab);
 
@@ -2651,12 +2649,10 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab)
 
 	__slab_clear_pfmemalloc(slab);
 	folio->mapping = NULL;
-	/* Make the mapping reset visible before clearing the flag */
-	smp_wmb();
 	__folio_clear_slab(folio);
 	mm_account_reclaimed_pages(pages);
 	unaccount_slab(slab, order, s);
-	__free_pages(&folio->page, order);
+	free_frozen_pages(&folio->page, order);
 }
 
 static void rcu_free_slab(struct rcu_head *h)
@@ -7513,10 +7509,7 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep)
 		return -ENOMEM;
 	}
 
-	if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0)
-		alloc = TRACK_ALLOC;
-	else
-		alloc = TRACK_FREE;
+	alloc = debugfs_get_aux_num(filep);
 
 	if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) {
 		bitmap_free(obj_map);
@@ -7572,11 +7565,11 @@ static void debugfs_slab_add(struct kmem_cache *s)
 
 	slab_cache_dir = debugfs_create_dir(s->name, slab_debugfs_root);
 
-	debugfs_create_file("alloc_traces", 0400,
-		slab_cache_dir, s, &slab_debugfs_fops);
+	debugfs_create_file_aux_num("alloc_traces", 0400, slab_cache_dir, s,
+					TRACK_ALLOC, &slab_debugfs_fops);
 
-	debugfs_create_file("free_traces", 0400,
-		slab_cache_dir, s, &slab_debugfs_fops);
+	debugfs_create_file_aux_num("free_traces", 0400, slab_cache_dir, s,
+					TRACK_FREE, &slab_debugfs_fops);
 }
 
 void debugfs_slab_release(struct kmem_cache *s)
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index cec67c5f37d8..3287ebadd167 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -31,6 +31,8 @@
 #include <asm/dma.h>
 #include <asm/pgalloc.h>
 
+#include "internal.h"
+
 /*
  * Allocate a block of memory to be used to back the virtual memory map
  * or to back the page tables that are used to create the mapping.
@@ -42,8 +44,7 @@ static void * __ref __earlyonly_bootmem_alloc(int node,
 				unsigned long align,
 				unsigned long goal)
 {
-	return memblock_alloc_try_nid_raw(size, align, goal,
-					       MEMBLOCK_ALLOC_ACCESSIBLE, node);
+	return memmap_alloc(size, align, goal, node, false);
 }
 
 void * __meminit vmemmap_alloc_block(unsigned long size, int node)
diff --git a/mm/sparse.c b/mm/sparse.c
index 13b6624d3562..133b033d0cba 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -257,10 +257,7 @@ static void __init memblocks_present(void)
 
 		size = sizeof(struct mem_section *) * NR_SECTION_ROOTS;
 		align = 1 << (INTERNODE_CACHE_SHIFT);
-		mem_section = memblock_alloc(size, align);
-		if (!mem_section)
-			panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
-			      __func__, size, align);
+		mem_section = memblock_alloc_or_panic(size, align);
 	}
 #endif
 
diff --git a/mm/swap.c b/mm/swap.c
index 10decd9dffa1..fc8281ef4241 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -109,7 +109,7 @@ void __folio_put(struct folio *folio)
 	page_cache_release(folio);
 	folio_unqueue_deferred_split(folio);
 	mem_cgroup_uncharge(folio);
-	free_unref_page(&folio->page, folio_order(folio));
+	free_frozen_pages(&folio->page, folio_order(folio));
 }
 EXPORT_SYMBOL(__folio_put);
 
@@ -379,37 +379,58 @@ static void __lru_cache_activate_folio(struct folio *folio)
 }
 
 #ifdef CONFIG_LRU_GEN
-static void folio_inc_refs(struct folio *folio)
+
+static void lru_gen_inc_refs(struct folio *folio)
 {
 	unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
 
 	if (folio_test_unevictable(folio))
 		return;
 
+	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio)) {
-		folio_set_referenced(folio);
-		return;
-	}
-
-	if (!folio_test_workingset(folio)) {
-		folio_set_workingset(folio);
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
 		return;
 	}
 
-	/* see the comment on MAX_NR_TIERS */
 	do {
-		new_flags = old_flags & LRU_REFS_MASK;
-		if (new_flags == LRU_REFS_MASK)
-			break;
+		if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) {
+			if (!folio_test_workingset(folio))
+				folio_set_workingset(folio);
+			return;
+		}
 
-		new_flags += BIT(LRU_REFS_PGOFF);
-		new_flags |= old_flags & ~LRU_REFS_MASK;
+		new_flags = old_flags + BIT(LRU_REFS_PGOFF);
 	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
 }
-#else
-static void folio_inc_refs(struct folio *folio)
+
+static bool lru_gen_clear_refs(struct folio *folio)
+{
+	struct lru_gen_folio *lrugen;
+	int gen = folio_lru_gen(folio);
+	int type = folio_is_file_lru(folio);
+
+	if (gen < 0)
+		return true;
+
+	set_mask_bits(&folio->flags, LRU_REFS_FLAGS | BIT(PG_workingset), 0);
+
+	lrugen = &folio_lruvec(folio)->lrugen;
+	/* whether can do without shuffling under the LRU lock */
+	return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type]));
+}
+
+#else /* !CONFIG_LRU_GEN */
+
+static void lru_gen_inc_refs(struct folio *folio)
+{
+}
+
+static bool lru_gen_clear_refs(struct folio *folio)
 {
+	return false;
 }
+
 #endif /* CONFIG_LRU_GEN */
 
 /**
@@ -427,8 +448,10 @@ static void folio_inc_refs(struct folio *folio)
  */
 void folio_mark_accessed(struct folio *folio)
 {
+	if (folio_test_dropbehind(folio))
+		return;
 	if (lru_gen_enabled()) {
-		folio_inc_refs(folio);
+		lru_gen_inc_refs(folio);
 		return;
 	}
 
@@ -474,7 +497,7 @@ void folio_add_lru(struct folio *folio)
 			folio_test_unevictable(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
-	/* see the comment in lru_gen_add_folio() */
+	/* see the comment in lru_gen_folio_seq() */
 	if (lru_gen_enabled() && !folio_test_unevictable(folio) &&
 	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC))
 		folio_set_active(folio);
@@ -524,7 +547,7 @@ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma)
  */
 static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio)
 {
-	bool active = folio_test_active(folio);
+	bool active = folio_test_active(folio) || lru_gen_enabled();
 	long nr_pages = folio_nr_pages(folio);
 
 	if (folio_test_unevictable(folio))
@@ -589,7 +612,10 @@ static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
 
 	lruvec_del_folio(lruvec, folio);
 	folio_clear_active(folio);
-	folio_clear_referenced(folio);
+	if (lru_gen_enabled())
+		lru_gen_clear_refs(folio);
+	else
+		folio_clear_referenced(folio);
 	/*
 	 * Lazyfree folios are clean anonymous folios.  They have
 	 * the swapbacked flag cleared, to distinguish them from normal
@@ -657,6 +683,9 @@ void deactivate_file_folio(struct folio *folio)
 	if (folio_test_unevictable(folio))
 		return;
 
+	if (lru_gen_enabled() && lru_gen_clear_refs(folio))
+		return;
+
 	folio_batch_add_and_move(folio, lru_deactivate_file, true);
 }
 
@@ -670,7 +699,10 @@ void deactivate_file_folio(struct folio *folio)
  */
 void folio_deactivate(struct folio *folio)
 {
-	if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled()))
+	if (folio_test_unevictable(folio))
+		return;
+
+	if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio))
 		return;
 
 	folio_batch_add_and_move(folio, lru_deactivate, true);
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index da1278f0563b..be39078f255b 100644
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -6,149 +6,106 @@
 #include <linux/swapops.h> /* depends on mm.h include */
 
 static DEFINE_MUTEX(swap_cgroup_mutex);
-struct swap_cgroup_ctrl {
-	struct page **map;
-	unsigned long length;
-	spinlock_t	lock;
-};
-
-static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
 
+/* Pack two cgroup id (short) of two entries in one swap_cgroup (atomic_t) */
+#define ID_PER_SC (sizeof(struct swap_cgroup) / sizeof(unsigned short))
+#define ID_SHIFT (BITS_PER_TYPE(unsigned short))
+#define ID_MASK (BIT(ID_SHIFT) - 1)
 struct swap_cgroup {
-	unsigned short		id;
+	atomic_t ids;
 };
-#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
-
-/*
- * SwapCgroup implements "lookup" and "exchange" operations.
- * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
- * against SwapCache. At swap_free(), this is accessed directly from swap.
- *
- * This means,
- *  - we have no race in "exchange" when we're accessed via SwapCache because
- *    SwapCache(and its swp_entry) is under lock.
- *  - When called via swap_free(), there is no user of this entry and no race.
- * Then, we don't need lock around "exchange".
- *
- * TODO: we can push these buffers out to HIGHMEM.
- */
-
-/*
- * allocate buffer for swap_cgroup.
- */
-static int swap_cgroup_prepare(int type)
-{
-	struct page *page;
-	struct swap_cgroup_ctrl *ctrl;
-	unsigned long idx, max;
-
-	ctrl = &swap_cgroup_ctrl[type];
-
-	for (idx = 0; idx < ctrl->length; idx++) {
-		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!page)
-			goto not_enough_page;
-		ctrl->map[idx] = page;
 
-		if (!(idx % SWAP_CLUSTER_MAX))
-			cond_resched();
-	}
-	return 0;
-not_enough_page:
-	max = idx;
-	for (idx = 0; idx < max; idx++)
-		__free_page(ctrl->map[idx]);
+struct swap_cgroup_ctrl {
+	struct swap_cgroup *map;
+};
 
-	return -ENOMEM;
-}
+static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
 
-static struct swap_cgroup *__lookup_swap_cgroup(struct swap_cgroup_ctrl *ctrl,
-						pgoff_t offset)
+static unsigned short __swap_cgroup_id_lookup(struct swap_cgroup *map,
+					      pgoff_t offset)
 {
-	struct page *mappage;
-	struct swap_cgroup *sc;
+	unsigned int shift = (offset % ID_PER_SC) * ID_SHIFT;
+	unsigned int old_ids = atomic_read(&map[offset / ID_PER_SC].ids);
+
+	BUILD_BUG_ON(!is_power_of_2(ID_PER_SC));
+	BUILD_BUG_ON(sizeof(struct swap_cgroup) != sizeof(atomic_t));
 
-	mappage = ctrl->map[offset / SC_PER_PAGE];
-	sc = page_address(mappage);
-	return sc + offset % SC_PER_PAGE;
+	return (old_ids >> shift) & ID_MASK;
 }
 
-static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
-					struct swap_cgroup_ctrl **ctrlp)
+static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map,
+					    pgoff_t offset,
+					    unsigned short new_id)
 {
-	pgoff_t offset = swp_offset(ent);
-	struct swap_cgroup_ctrl *ctrl;
-
-	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
-	if (ctrlp)
-		*ctrlp = ctrl;
-	return __lookup_swap_cgroup(ctrl, offset);
+	unsigned short old_id;
+	struct swap_cgroup *sc = &map[offset / ID_PER_SC];
+	unsigned int shift = (offset % ID_PER_SC) * ID_SHIFT;
+	unsigned int new_ids, old_ids = atomic_read(&sc->ids);
+
+	do {
+		old_id = (old_ids >> shift) & ID_MASK;
+		new_ids = (old_ids & ~(ID_MASK << shift));
+		new_ids |= ((unsigned int)new_id) << shift;
+	} while (!atomic_try_cmpxchg(&sc->ids, &old_ids, new_ids));
+
+	return old_id;
 }
 
 /**
- * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
- * @ent: swap entry to be cmpxchged
- * @old: old id
- * @new: new id
+ * swap_cgroup_record - record mem_cgroup for a set of swap entries.
+ * These entries must belong to one single folio, and that folio
+ * must be being charged for swap space (swap out), and these
+ * entries must not have been charged
  *
- * Returns old id at success, 0 at failure.
- * (There is no mem_cgroup using 0 as its id)
+ * @folio: the folio that the swap entry belongs to
+ * @ent: the first swap entry to be recorded
  */
-unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new)
+void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
 {
-	struct swap_cgroup_ctrl *ctrl;
-	struct swap_cgroup *sc;
-	unsigned long flags;
-	unsigned short retval;
-
-	sc = lookup_swap_cgroup(ent, &ctrl);
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	retval = sc->id;
-	if (retval == old)
-		sc->id = new;
-	else
-		retval = 0;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-	return retval;
+	unsigned int nr_ents = folio_nr_pages(folio);
+	struct swap_cgroup *map;
+	pgoff_t offset, end;
+	unsigned short old;
+
+	offset = swp_offset(ent);
+	end = offset + nr_ents;
+	map = swap_cgroup_ctrl[swp_type(ent)].map;
+
+	do {
+		old = __swap_cgroup_id_xchg(map, offset,
+					    mem_cgroup_id(folio_memcg(folio)));
+		VM_BUG_ON(old);
+	} while (++offset != end);
 }
 
 /**
- * swap_cgroup_record - record mem_cgroup for a set of swap entries
+ * swap_cgroup_clear - clear mem_cgroup for a set of swap entries.
+ * These entries must be being uncharged from swap. They either
+ * belongs to one single folio in the swap cache (swap in for
+ * cgroup v1), or no longer have any users (slot freeing).
+ *
  * @ent: the first swap entry to be recorded into
- * @id: mem_cgroup to be recorded
  * @nr_ents: number of swap entries to be recorded
  *
- * Returns old value at success, 0 at failure.
- * (Of course, old value can be 0.)
+ * Returns the existing old value.
  */
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
-				  unsigned int nr_ents)
+unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents)
 {
-	struct swap_cgroup_ctrl *ctrl;
-	struct swap_cgroup *sc;
-	unsigned short old;
-	unsigned long flags;
 	pgoff_t offset = swp_offset(ent);
 	pgoff_t end = offset + nr_ents;
+	struct swap_cgroup *map;
+	unsigned short old, iter = 0;
 
-	sc = lookup_swap_cgroup(ent, &ctrl);
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	old = sc->id;
-	for (;;) {
-		VM_BUG_ON(sc->id != old);
-		sc->id = id;
-		offset++;
-		if (offset == end)
-			break;
-		if (offset % SC_PER_PAGE)
-			sc++;
-		else
-			sc = __lookup_swap_cgroup(ctrl, offset);
-	}
-	spin_unlock_irqrestore(&ctrl->lock, flags);
+	offset = swp_offset(ent);
+	end = offset + nr_ents;
+	map = swap_cgroup_ctrl[swp_type(ent)].map;
+
+	do {
+		old = __swap_cgroup_id_xchg(map, offset, 0);
+		if (!iter)
+			iter = old;
+		VM_BUG_ON(iter != old);
+	} while (++offset != end);
 
 	return old;
 }
@@ -161,39 +118,33 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
  */
 unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
 {
+	struct swap_cgroup_ctrl *ctrl;
+
 	if (mem_cgroup_disabled())
 		return 0;
-	return lookup_swap_cgroup(ent, NULL)->id;
+
+	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+	return __swap_cgroup_id_lookup(ctrl->map, swp_offset(ent));
 }
 
 int swap_cgroup_swapon(int type, unsigned long max_pages)
 {
-	void *array;
-	unsigned long length;
+	struct swap_cgroup *map;
 	struct swap_cgroup_ctrl *ctrl;
 
 	if (mem_cgroup_disabled())
 		return 0;
 
-	length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
-
-	array = vcalloc(length, sizeof(void *));
-	if (!array)
+	BUILD_BUG_ON(sizeof(unsigned short) * ID_PER_SC !=
+		     sizeof(struct swap_cgroup));
+	map = vzalloc(DIV_ROUND_UP(max_pages, ID_PER_SC) *
+		      sizeof(struct swap_cgroup));
+	if (!map)
 		goto nomem;
 
 	ctrl = &swap_cgroup_ctrl[type];
 	mutex_lock(&swap_cgroup_mutex);
-	ctrl->length = length;
-	ctrl->map = array;
-	spin_lock_init(&ctrl->lock);
-	if (swap_cgroup_prepare(type)) {
-		/* memory shortage */
-		ctrl->map = NULL;
-		ctrl->length = 0;
-		mutex_unlock(&swap_cgroup_mutex);
-		vfree(array);
-		goto nomem;
-	}
+	ctrl->map = map;
 	mutex_unlock(&swap_cgroup_mutex);
 
 	return 0;
@@ -205,8 +156,7 @@ nomem:
 
 void swap_cgroup_swapoff(int type)
 {
-	struct page **map;
-	unsigned long i, length;
+	struct swap_cgroup *map;
 	struct swap_cgroup_ctrl *ctrl;
 
 	if (mem_cgroup_disabled())
@@ -215,19 +165,8 @@ void swap_cgroup_swapoff(int type)
 	mutex_lock(&swap_cgroup_mutex);
 	ctrl = &swap_cgroup_ctrl[type];
 	map = ctrl->map;
-	length = ctrl->length;
 	ctrl->map = NULL;
-	ctrl->length = 0;
 	mutex_unlock(&swap_cgroup_mutex);
 
-	if (map) {
-		for (i = 0; i < length; i++) {
-			struct page *page = map[i];
-			if (page)
-				__free_page(page);
-			if (!(i % SWAP_CLUSTER_MAX))
-				cond_resched();
-		}
-		vfree(map);
-	}
+	vfree(map);
 }
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 13ab3b771409..9c7c171df7ba 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -43,17 +43,15 @@ static DEFINE_MUTEX(swap_slots_cache_mutex);
 /* Serialize swap slots cache enable/disable operations */
 static DEFINE_MUTEX(swap_slots_cache_enable_mutex);
 
-static void __drain_swap_slots_cache(unsigned int type);
+static void __drain_swap_slots_cache(void);
 
 #define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled)
-#define SLOTS_CACHE 0x1
-#define SLOTS_CACHE_RET 0x2
 
 static void deactivate_swap_slots_cache(void)
 {
 	mutex_lock(&swap_slots_cache_mutex);
 	swap_slot_cache_active = false;
-	__drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET);
+	__drain_swap_slots_cache();
 	mutex_unlock(&swap_slots_cache_mutex);
 }
 
@@ -72,7 +70,7 @@ void disable_swap_slots_cache_lock(void)
 	if (swap_slot_cache_initialized) {
 		/* serialize with cpu hotplug operations */
 		cpus_read_lock();
-		__drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET);
+		__drain_swap_slots_cache();
 		cpus_read_unlock();
 	}
 }
@@ -113,7 +111,7 @@ out:
 static int alloc_swap_slot_cache(unsigned int cpu)
 {
 	struct swap_slots_cache *cache;
-	swp_entry_t *slots, *slots_ret;
+	swp_entry_t *slots;
 
 	/*
 	 * Do allocation outside swap_slots_cache_mutex
@@ -125,28 +123,19 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 	if (!slots)
 		return -ENOMEM;
 
-	slots_ret = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t),
-			     GFP_KERNEL);
-	if (!slots_ret) {
-		kvfree(slots);
-		return -ENOMEM;
-	}
-
 	mutex_lock(&swap_slots_cache_mutex);
 	cache = &per_cpu(swp_slots, cpu);
-	if (cache->slots || cache->slots_ret) {
+	if (cache->slots) {
 		/* cache already allocated */
 		mutex_unlock(&swap_slots_cache_mutex);
 
 		kvfree(slots);
-		kvfree(slots_ret);
 
 		return 0;
 	}
 
 	if (!cache->lock_initialized) {
 		mutex_init(&cache->alloc_lock);
-		spin_lock_init(&cache->free_lock);
 		cache->lock_initialized = true;
 	}
 	cache->nr = 0;
@@ -160,19 +149,16 @@ static int alloc_swap_slot_cache(unsigned int cpu)
 	 */
 	mb();
 	cache->slots = slots;
-	cache->slots_ret = slots_ret;
 	mutex_unlock(&swap_slots_cache_mutex);
 	return 0;
 }
 
-static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
-				  bool free_slots)
+static void drain_slots_cache_cpu(unsigned int cpu, bool free_slots)
 {
 	struct swap_slots_cache *cache;
-	swp_entry_t *slots = NULL;
 
 	cache = &per_cpu(swp_slots, cpu);
-	if ((type & SLOTS_CACHE) && cache->slots) {
+	if (cache->slots) {
 		mutex_lock(&cache->alloc_lock);
 		swapcache_free_entries(cache->slots + cache->cur, cache->nr);
 		cache->cur = 0;
@@ -183,20 +169,9 @@ static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type,
 		}
 		mutex_unlock(&cache->alloc_lock);
 	}
-	if ((type & SLOTS_CACHE_RET) && cache->slots_ret) {
-		spin_lock_irq(&cache->free_lock);
-		swapcache_free_entries(cache->slots_ret, cache->n_ret);
-		cache->n_ret = 0;
-		if (free_slots && cache->slots_ret) {
-			slots = cache->slots_ret;
-			cache->slots_ret = NULL;
-		}
-		spin_unlock_irq(&cache->free_lock);
-		kvfree(slots);
-	}
 }
 
-static void __drain_swap_slots_cache(unsigned int type)
+static void __drain_swap_slots_cache(void)
 {
 	unsigned int cpu;
 
@@ -224,13 +199,13 @@ static void __drain_swap_slots_cache(unsigned int type)
 	 * There are no slots on such cpu that need to be drained.
 	 */
 	for_each_online_cpu(cpu)
-		drain_slots_cache_cpu(cpu, type, false);
+		drain_slots_cache_cpu(cpu, false);
 }
 
 static int free_slot_cache(unsigned int cpu)
 {
 	mutex_lock(&swap_slots_cache_mutex);
-	drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true);
+	drain_slots_cache_cpu(cpu, true);
 	mutex_unlock(&swap_slots_cache_mutex);
 	return 0;
 }
@@ -269,39 +244,6 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache)
 	return cache->nr;
 }
 
-void free_swap_slot(swp_entry_t entry)
-{
-	struct swap_slots_cache *cache;
-
-	/* Large folio swap slot is not covered. */
-	zswap_invalidate(entry);
-
-	cache = raw_cpu_ptr(&swp_slots);
-	if (likely(use_swap_slot_cache && cache->slots_ret)) {
-		spin_lock_irq(&cache->free_lock);
-		/* Swap slots cache may be deactivated before acquiring lock */
-		if (!use_swap_slot_cache || !cache->slots_ret) {
-			spin_unlock_irq(&cache->free_lock);
-			goto direct_free;
-		}
-		if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) {
-			/*
-			 * Return slots to global pool.
-			 * The current swap_map value is SWAP_HAS_CACHE.
-			 * Set it to 0 to indicate it is available for
-			 * allocation in global pool
-			 */
-			swapcache_free_entries(cache->slots_ret, cache->n_ret);
-			cache->n_ret = 0;
-		}
-		cache->slots_ret[cache->n_ret++] = entry;
-		spin_unlock_irq(&cache->free_lock);
-	} else {
-direct_free:
-		swapcache_free_entries(&entry, 1);
-	}
-}
-
 swp_entry_t folio_alloc_swap(struct folio *folio)
 {
 	swp_entry_t entry;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e0c0321b8ff7..ca42b2be64d9 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -317,7 +317,6 @@ void free_pages_and_swap_cache(struct encoded_page **pages, int nr)
 	struct folio_batch folios;
 	unsigned int refs[PAGEVEC_SIZE];
 
-	lru_add_drain();
 	folio_batch_init(&folios);
 	for (int i = 0; i < nr; i++) {
 		struct folio *folio = page_folio(encoded_page_ptr(pages[i]));
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b0a9071cfe1d..ba19430dd4ea 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -53,15 +53,15 @@
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
 static void free_swap_count_continuations(struct swap_info_struct *);
-static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry,
-				  unsigned int nr_pages);
-static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
+static void swap_entry_range_free(struct swap_info_struct *si,
+				  struct swap_cluster_info *ci,
+				  swp_entry_t entry, unsigned int nr_pages);
+static void swap_range_alloc(struct swap_info_struct *si,
 			     unsigned int nr_entries);
 static bool folio_swapcache_freeable(struct folio *folio);
-static struct swap_cluster_info *lock_cluster_or_swap_info(
-		struct swap_info_struct *si, unsigned long offset);
-static void unlock_cluster_or_swap_info(struct swap_info_struct *si,
-					struct swap_cluster_info *ci);
+static struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
+					      unsigned long offset);
+static inline void unlock_cluster(struct swap_cluster_info *ci);
 
 static DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
@@ -129,6 +129,26 @@ static inline unsigned char swap_count(unsigned char ent)
 	return ent & ~SWAP_HAS_CACHE;	/* may include COUNT_CONTINUED flag */
 }
 
+/*
+ * Use the second highest bit of inuse_pages counter as the indicator
+ * if one swap device is on the available plist, so the atomic can
+ * still be updated arithmetically while having special data embedded.
+ *
+ * inuse_pages counter is the only thing indicating if a device should
+ * be on avail_lists or not (except swapon / swapoff). By embedding the
+ * off-list bit in the atomic counter, updates no longer need any lock
+ * to check the list status.
+ *
+ * This bit will be set if the device is not on the plist and not
+ * usable, will be cleared if the device is on the plist.
+ */
+#define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2))
+#define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT)
+static long swap_usage_in_pages(struct swap_info_struct *si)
+{
+	return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK;
+}
+
 /* Reclaim the swap entry anyway if possible */
 #define TTRS_ANYWAY		0x1
 /*
@@ -222,9 +242,9 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
 	 * swap_map is HAS_CACHE only, which means the slots have no page table
 	 * reference or pending writeback, and can't be allocated to others.
 	 */
-	ci = lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
 	need_reclaim = swap_is_has_cache(si, offset, nr_pages);
-	unlock_cluster_or_swap_info(si, ci);
+	unlock_cluster(ci);
 	if (!need_reclaim)
 		goto out_unlock;
 
@@ -242,12 +262,9 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
 	folio_ref_sub(folio, nr_pages);
 	folio_set_dirty(folio);
 
-	spin_lock(&si->lock);
-	/* Only sinple page folio can be backed by zswap */
-	if (nr_pages == 1)
-		zswap_invalidate(entry);
-	swap_entry_range_free(si, entry, nr_pages);
-	spin_unlock(&si->lock);
+	ci = lock_cluster(si, offset);
+	swap_entry_range_free(si, ci, entry, nr_pages);
+	unlock_cluster(ci);
 	ret = nr_pages;
 out_unlock:
 	folio_unlock(folio);
@@ -382,9 +399,23 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #endif
 #define LATENCY_LIMIT		256
 
-static inline bool cluster_is_free(struct swap_cluster_info *info)
+static inline bool cluster_is_empty(struct swap_cluster_info *info)
 {
-	return info->flags & CLUSTER_FLAG_FREE;
+	return info->count == 0;
+}
+
+static inline bool cluster_is_discard(struct swap_cluster_info *info)
+{
+	return info->flags == CLUSTER_FLAG_DISCARD;
+}
+
+static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order)
+{
+	if (unlikely(ci->flags > CLUSTER_FLAG_USABLE))
+		return false;
+	if (!order)
+		return true;
+	return cluster_is_empty(ci) || order == ci->order;
 }
 
 static inline unsigned int cluster_index(struct swap_info_struct *si,
@@ -393,6 +424,12 @@ static inline unsigned int cluster_index(struct swap_info_struct *si,
 	return ci - si->cluster_info;
 }
 
+static inline struct swap_cluster_info *offset_to_cluster(struct swap_info_struct *si,
+							  unsigned long offset)
+{
+	return &si->cluster_info[offset / SWAPFILE_CLUSTER];
+}
+
 static inline unsigned int cluster_offset(struct swap_info_struct *si,
 					  struct swap_cluster_info *ci)
 {
@@ -404,45 +441,38 @@ static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si
 {
 	struct swap_cluster_info *ci;
 
-	ci = si->cluster_info;
-	if (ci) {
-		ci += offset / SWAPFILE_CLUSTER;
-		spin_lock(&ci->lock);
-	}
+	ci = offset_to_cluster(si, offset);
+	spin_lock(&ci->lock);
+
 	return ci;
 }
 
 static inline void unlock_cluster(struct swap_cluster_info *ci)
 {
-	if (ci)
-		spin_unlock(&ci->lock);
+	spin_unlock(&ci->lock);
 }
 
-/*
- * Determine the locking method in use for this device.  Return
- * swap_cluster_info if SSD-style cluster-based locking is in place.
- */
-static inline struct swap_cluster_info *lock_cluster_or_swap_info(
-		struct swap_info_struct *si, unsigned long offset)
+static void move_cluster(struct swap_info_struct *si,
+			 struct swap_cluster_info *ci, struct list_head *list,
+			 enum swap_cluster_flags new_flags)
 {
-	struct swap_cluster_info *ci;
+	VM_WARN_ON(ci->flags == new_flags);
 
-	/* Try to use fine-grained SSD-style locking if available: */
-	ci = lock_cluster(si, offset);
-	/* Otherwise, fall back to traditional, coarse locking: */
-	if (!ci)
-		spin_lock(&si->lock);
-
-	return ci;
-}
+	BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX);
+	lockdep_assert_held(&ci->lock);
 
-static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
-					       struct swap_cluster_info *ci)
-{
-	if (ci)
-		unlock_cluster(ci);
+	spin_lock(&si->lock);
+	if (ci->flags == CLUSTER_FLAG_NONE)
+		list_add_tail(&ci->list, list);
 	else
-		spin_unlock(&si->lock);
+		list_move_tail(&ci->list, list);
+	spin_unlock(&si->lock);
+
+	if (ci->flags == CLUSTER_FLAG_FRAG)
+		atomic_long_dec(&si->frag_cluster_nr[ci->order]);
+	else if (new_flags == CLUSTER_FLAG_FRAG)
+		atomic_long_inc(&si->frag_cluster_nr[ci->order]);
+	ci->flags = new_flags;
 }
 
 /* Add a cluster to discard list and schedule it to do discard */
@@ -458,51 +488,98 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
 	 */
 	memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 			SWAP_MAP_BAD, SWAPFILE_CLUSTER);
-
-	VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE);
-	list_move_tail(&ci->list, &si->discard_clusters);
-	ci->flags = 0;
+	VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);
+	move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD);
 	schedule_work(&si->discard_work);
 }
 
 static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-	lockdep_assert_held(&si->lock);
 	lockdep_assert_held(&ci->lock);
-
-	if (ci->flags)
-		list_move_tail(&ci->list, &si->free_clusters);
-	else
-		list_add_tail(&ci->list, &si->free_clusters);
-	ci->flags = CLUSTER_FLAG_FREE;
+	move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE);
 	ci->order = 0;
 }
 
 /*
+ * Isolate and lock the first cluster that is not contented on a list,
+ * clean its flag before taken off-list. Cluster flag must be in sync
+ * with list status, so cluster updaters can always know the cluster
+ * list status without touching si lock.
+ *
+ * Note it's possible that all clusters on a list are contented so
+ * this returns NULL for an non-empty list.
+ */
+static struct swap_cluster_info *isolate_lock_cluster(
+		struct swap_info_struct *si, struct list_head *list)
+{
+	struct swap_cluster_info *ci, *ret = NULL;
+
+	spin_lock(&si->lock);
+
+	if (unlikely(!(si->flags & SWP_WRITEOK)))
+		goto out;
+
+	list_for_each_entry(ci, list, list) {
+		if (!spin_trylock(&ci->lock))
+			continue;
+
+		/* We may only isolate and clear flags of following lists */
+		VM_BUG_ON(!ci->flags);
+		VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE &&
+			  ci->flags != CLUSTER_FLAG_FULL);
+
+		list_del(&ci->list);
+		ci->flags = CLUSTER_FLAG_NONE;
+		ret = ci;
+		break;
+	}
+out:
+	spin_unlock(&si->lock);
+
+	return ret;
+}
+
+/*
  * Doing discard actually. After a cluster discard is finished, the cluster
- * will be added to free cluster list. caller should hold si->lock.
-*/
-static void swap_do_scheduled_discard(struct swap_info_struct *si)
+ * will be added to free cluster list. Discard cluster is a bit special as
+ * they don't participate in allocation or reclaim, so clusters marked as
+ * CLUSTER_FLAG_DISCARD must remain off-list or on discard list.
+ */
+static bool swap_do_scheduled_discard(struct swap_info_struct *si)
 {
 	struct swap_cluster_info *ci;
+	bool ret = false;
 	unsigned int idx;
 
+	spin_lock(&si->lock);
 	while (!list_empty(&si->discard_clusters)) {
 		ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+		/*
+		 * Delete the cluster from list to prepare for discard, but keep
+		 * the CLUSTER_FLAG_DISCARD flag, there could be percpu_cluster
+		 * pointing to it, or ran into by relocate_cluster.
+		 */
 		list_del(&ci->list);
 		idx = cluster_index(si, ci);
 		spin_unlock(&si->lock);
-
 		discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
 				SWAPFILE_CLUSTER);
 
-		spin_lock(&si->lock);
 		spin_lock(&ci->lock);
-		__free_cluster(si, ci);
+		/*
+		 * Discard is done, clear its flags as it's off-list, then
+		 * return the cluster to allocation list.
+		 */
+		ci->flags = CLUSTER_FLAG_NONE;
 		memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 				0, SWAPFILE_CLUSTER);
+		__free_cluster(si, ci);
 		spin_unlock(&ci->lock);
+		ret = true;
+		spin_lock(&si->lock);
 	}
+	spin_unlock(&si->lock);
+	return ret;
 }
 
 static void swap_discard_work(struct work_struct *work)
@@ -511,9 +588,7 @@ static void swap_discard_work(struct work_struct *work)
 
 	si = container_of(work, struct swap_info_struct, discard_work);
 
-	spin_lock(&si->lock);
 	swap_do_scheduled_discard(si);
-	spin_unlock(&si->lock);
 }
 
 static void swap_users_ref_free(struct percpu_ref *ref)
@@ -524,15 +599,16 @@ static void swap_users_ref_free(struct percpu_ref *ref)
 	complete(&si->comp);
 }
 
+/*
+ * Must be called after freeing if ci->count == 0, moves the cluster to free
+ * or discard list.
+ */
 static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
 	VM_BUG_ON(ci->count != 0);
-	lockdep_assert_held(&si->lock);
+	VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);
 	lockdep_assert_held(&ci->lock);
 
-	if (ci->flags & CLUSTER_FLAG_FRAG)
-		si->frag_cluster_nr[ci->order]--;
-
 	/*
 	 * If the swap is discardable, prepare discard the cluster
 	 * instead of free it immediately. The cluster will be freed
@@ -548,6 +624,48 @@ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *
 }
 
 /*
+ * Must be called after freeing if ci->count != 0, moves the cluster to
+ * nonfull list.
+ */
+static void partial_free_cluster(struct swap_info_struct *si,
+				 struct swap_cluster_info *ci)
+{
+	VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER);
+	lockdep_assert_held(&ci->lock);
+
+	if (ci->flags != CLUSTER_FLAG_NONFULL)
+		move_cluster(si, ci, &si->nonfull_clusters[ci->order],
+			     CLUSTER_FLAG_NONFULL);
+}
+
+/*
+ * Must be called after allocation, moves the cluster to full or frag list.
+ * Note: allocation doesn't acquire si lock, and may drop the ci lock for
+ * reclaim, so the cluster could be any where when called.
+ */
+static void relocate_cluster(struct swap_info_struct *si,
+			     struct swap_cluster_info *ci)
+{
+	lockdep_assert_held(&ci->lock);
+
+	/* Discard cluster must remain off-list or on discard list */
+	if (cluster_is_discard(ci))
+		return;
+
+	if (!ci->count) {
+		free_cluster(si, ci);
+	} else if (ci->count != SWAPFILE_CLUSTER) {
+		if (ci->flags != CLUSTER_FLAG_FRAG)
+			move_cluster(si, ci, &si->frag_clusters[ci->order],
+				     CLUSTER_FLAG_FRAG);
+	} else {
+		if (ci->flags != CLUSTER_FLAG_FULL)
+			move_cluster(si, ci, &si->full_clusters,
+				     CLUSTER_FLAG_FULL);
+	}
+}
+
+/*
  * The cluster corresponding to page_nr will be used. The cluster will not be
  * added to free cluster list and its usage counter will be increased by 1.
  * Only used for initialization.
@@ -558,9 +676,6 @@ static void inc_cluster_info_page(struct swap_info_struct *si,
 	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
 	struct swap_cluster_info *ci;
 
-	if (!cluster_info)
-		return;
-
 	ci = cluster_info + idx;
 	ci->count++;
 
@@ -568,63 +683,33 @@ static void inc_cluster_info_page(struct swap_info_struct *si,
 	VM_BUG_ON(ci->flags);
 }
 
-/*
- * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0,
- * which means no page in the cluster is in use, we can optionally discard
- * the cluster and add it to free cluster list.
- */
-static void dec_cluster_info_page(struct swap_info_struct *si,
-				  struct swap_cluster_info *ci, int nr_pages)
-{
-	if (!si->cluster_info)
-		return;
-
-	VM_BUG_ON(ci->count < nr_pages);
-	VM_BUG_ON(cluster_is_free(ci));
-	lockdep_assert_held(&si->lock);
-	lockdep_assert_held(&ci->lock);
-	ci->count -= nr_pages;
-
-	if (!ci->count) {
-		free_cluster(si, ci);
-		return;
-	}
-
-	if (!(ci->flags & CLUSTER_FLAG_NONFULL)) {
-		VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE);
-		if (ci->flags & CLUSTER_FLAG_FRAG)
-			si->frag_cluster_nr[ci->order]--;
-		list_move_tail(&ci->list, &si->nonfull_clusters[ci->order]);
-		ci->flags = CLUSTER_FLAG_NONFULL;
-	}
-}
-
 static bool cluster_reclaim_range(struct swap_info_struct *si,
 				  struct swap_cluster_info *ci,
 				  unsigned long start, unsigned long end)
 {
 	unsigned char *map = si->swap_map;
-	unsigned long offset;
+	unsigned long offset = start;
+	int nr_reclaim;
 
 	spin_unlock(&ci->lock);
-	spin_unlock(&si->lock);
-
-	for (offset = start; offset < end; offset++) {
+	do {
 		switch (READ_ONCE(map[offset])) {
 		case 0:
-			continue;
+			offset++;
+			break;
 		case SWAP_HAS_CACHE:
-			if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0)
-				continue;
-			goto out;
+			nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT);
+			if (nr_reclaim > 0)
+				offset += nr_reclaim;
+			else
+				goto out;
+			break;
 		default:
 			goto out;
 		}
-	}
+	} while (offset < end);
 out:
-	spin_lock(&si->lock);
 	spin_lock(&ci->lock);
-
 	/*
 	 * Recheck the range no matter reclaim succeeded or not, the slot
 	 * could have been be freed while we are not holding the lock.
@@ -638,11 +723,11 @@ out:
 
 static bool cluster_scan_range(struct swap_info_struct *si,
 			       struct swap_cluster_info *ci,
-			       unsigned long start, unsigned int nr_pages)
+			       unsigned long start, unsigned int nr_pages,
+			       bool *need_reclaim)
 {
 	unsigned long offset, end = start + nr_pages;
 	unsigned char *map = si->swap_map;
-	bool need_reclaim = false;
 
 	for (offset = start; offset < end; offset++) {
 		switch (READ_ONCE(map[offset])) {
@@ -651,16 +736,13 @@ static bool cluster_scan_range(struct swap_info_struct *si,
 		case SWAP_HAS_CACHE:
 			if (!vm_swap_full())
 				return false;
-			need_reclaim = true;
+			*need_reclaim = true;
 			continue;
 		default:
 			return false;
 		}
 	}
 
-	if (need_reclaim)
-		return cluster_reclaim_range(si, ci, start, end);
-
 	return true;
 }
 
@@ -670,73 +752,79 @@ static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster
 {
 	unsigned int nr_pages = 1 << order;
 
+	lockdep_assert_held(&ci->lock);
+
 	if (!(si->flags & SWP_WRITEOK))
 		return false;
 
-	if (cluster_is_free(ci)) {
-		if (nr_pages < SWAPFILE_CLUSTER) {
-			list_move_tail(&ci->list, &si->nonfull_clusters[order]);
-			ci->flags = CLUSTER_FLAG_NONFULL;
-		}
+	/*
+	 * The first allocation in a cluster makes the
+	 * cluster exclusive to this order
+	 */
+	if (cluster_is_empty(ci))
 		ci->order = order;
-	}
 
 	memset(si->swap_map + start, usage, nr_pages);
-	swap_range_alloc(si, start, nr_pages);
+	swap_range_alloc(si, nr_pages);
 	ci->count += nr_pages;
 
-	if (ci->count == SWAPFILE_CLUSTER) {
-		VM_BUG_ON(!(ci->flags &
-			  (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG)));
-		if (ci->flags & CLUSTER_FLAG_FRAG)
-			si->frag_cluster_nr[ci->order]--;
-		list_move_tail(&ci->list, &si->full_clusters);
-		ci->flags = CLUSTER_FLAG_FULL;
-	}
-
 	return true;
 }
 
-static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset,
-					    unsigned int *foundp, unsigned int order,
+/* Try use a new cluster for current CPU and allocate from it. */
+static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si,
+					    struct swap_cluster_info *ci,
+					    unsigned long offset,
+					    unsigned int order,
 					    unsigned char usage)
 {
-	unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1);
+	unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID;
+	unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER);
 	unsigned long end = min(start + SWAPFILE_CLUSTER, si->max);
 	unsigned int nr_pages = 1 << order;
-	struct swap_cluster_info *ci;
+	bool need_reclaim, ret;
 
-	if (end < nr_pages)
-		return SWAP_NEXT_INVALID;
-	end -= nr_pages;
+	lockdep_assert_held(&ci->lock);
 
-	ci = lock_cluster(si, offset);
-	if (ci->count + nr_pages > SWAPFILE_CLUSTER) {
-		offset = SWAP_NEXT_INVALID;
-		goto done;
-	}
+	if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER)
+		goto out;
 
-	while (offset <= end) {
-		if (cluster_scan_range(si, ci, offset, nr_pages)) {
-			if (!cluster_alloc_range(si, ci, offset, usage, order)) {
-				offset = SWAP_NEXT_INVALID;
-				goto done;
-			}
-			*foundp = offset;
-			if (ci->count == SWAPFILE_CLUSTER) {
-				offset = SWAP_NEXT_INVALID;
-				goto done;
-			}
-			offset += nr_pages;
-			break;
+	for (end -= nr_pages; offset <= end; offset += nr_pages) {
+		need_reclaim = false;
+		if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim))
+			continue;
+		if (need_reclaim) {
+			ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages);
+			/*
+			 * Reclaim drops ci->lock and cluster could be used
+			 * by another order. Not checking flag as off-list
+			 * cluster has no flag set, and change of list
+			 * won't cause fragmentation.
+			 */
+			if (!cluster_is_usable(ci, order))
+				goto out;
+			if (cluster_is_empty(ci))
+				offset = start;
+			/* Reclaim failed but cluster is usable, try next */
+			if (!ret)
+				continue;
 		}
+		if (!cluster_alloc_range(si, ci, offset, usage, order))
+			break;
+		found = offset;
 		offset += nr_pages;
+		if (ci->count < SWAPFILE_CLUSTER && offset <= end)
+			next = offset;
+		break;
 	}
-	if (offset > end)
-		offset = SWAP_NEXT_INVALID;
-done:
+out:
+	relocate_cluster(si, ci);
 	unlock_cluster(ci);
-	return offset;
+	if (si->flags & SWP_SOLIDSTATE)
+		__this_cpu_write(si->percpu_cluster->next[order], next);
+	else
+		si->global_cluster->next[order] = next;
+	return found;
 }
 
 /* Return true if reclaimed a whole cluster */
@@ -749,20 +837,19 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
 	int nr_reclaim;
 
 	if (force)
-		to_scan = si->inuse_pages / SWAPFILE_CLUSTER;
+		to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER;
 
-	while (!list_empty(&si->full_clusters)) {
-		ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list);
-		list_move_tail(&ci->list, &si->full_clusters);
+	while ((ci = isolate_lock_cluster(si, &si->full_clusters))) {
 		offset = cluster_offset(si, ci);
 		end = min(si->max, offset + SWAPFILE_CLUSTER);
 		to_scan--;
 
-		spin_unlock(&si->lock);
 		while (offset < end) {
 			if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) {
+				spin_unlock(&ci->lock);
 				nr_reclaim = __try_to_reclaim_swap(si, offset,
 								   TTRS_ANYWAY | TTRS_DIRECT);
+				spin_lock(&ci->lock);
 				if (nr_reclaim) {
 					offset += abs(nr_reclaim);
 					continue;
@@ -770,8 +857,8 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
 			}
 			offset++;
 		}
-		spin_lock(&si->lock);
 
+		unlock_cluster(ci);
 		if (to_scan <= 0)
 			break;
 	}
@@ -783,9 +870,7 @@ static void swap_reclaim_work(struct work_struct *work)
 
 	si = container_of(work, struct swap_info_struct, reclaim_work);
 
-	spin_lock(&si->lock);
 	swap_reclaim_full_clusters(si, true);
-	spin_unlock(&si->lock);
 }
 
 /*
@@ -796,29 +881,41 @@ static void swap_reclaim_work(struct work_struct *work)
 static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order,
 					      unsigned char usage)
 {
-	struct percpu_cluster *cluster;
 	struct swap_cluster_info *ci;
 	unsigned int offset, found = 0;
 
-new_cluster:
-	lockdep_assert_held(&si->lock);
-	cluster = this_cpu_ptr(si->percpu_cluster);
-	offset = cluster->next[order];
+	if (si->flags & SWP_SOLIDSTATE) {
+		/* Fast path using per CPU cluster */
+		local_lock(&si->percpu_cluster->lock);
+		offset = __this_cpu_read(si->percpu_cluster->next[order]);
+	} else {
+		/* Serialize HDD SWAP allocation for each device. */
+		spin_lock(&si->global_cluster_lock);
+		offset = si->global_cluster->next[order];
+	}
+
 	if (offset) {
-		offset = alloc_swap_scan_cluster(si, offset, &found, order, usage);
+		ci = lock_cluster(si, offset);
+		/* Cluster could have been used by another order */
+		if (cluster_is_usable(ci, order)) {
+			if (cluster_is_empty(ci))
+				offset = cluster_offset(si, ci);
+			found = alloc_swap_scan_cluster(si, ci, offset,
+							order, usage);
+		} else {
+			unlock_cluster(ci);
+		}
 		if (found)
 			goto done;
 	}
 
-	if (!list_empty(&si->free_clusters)) {
-		ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
-		offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage);
-		/*
-		 * Either we didn't touch the cluster due to swapoff,
-		 * or the allocation must success.
-		 */
-		VM_BUG_ON((si->flags & SWP_WRITEOK) && !found);
-		goto done;
+new_cluster:
+	ci = isolate_lock_cluster(si, &si->free_clusters);
+	if (ci) {
+		found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+						order, usage);
+		if (found)
+			goto done;
 	}
 
 	/* Try reclaim from full clusters if free clusters list is drained */
@@ -826,56 +923,42 @@ new_cluster:
 		swap_reclaim_full_clusters(si, false);
 
 	if (order < PMD_ORDER) {
-		unsigned int frags = 0;
-
-		while (!list_empty(&si->nonfull_clusters[order])) {
-			ci = list_first_entry(&si->nonfull_clusters[order],
-					      struct swap_cluster_info, list);
-			list_move_tail(&ci->list, &si->frag_clusters[order]);
-			ci->flags = CLUSTER_FLAG_FRAG;
-			si->frag_cluster_nr[order]++;
-			offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
-							 &found, order, usage);
-			frags++;
+		unsigned int frags = 0, frags_existing;
+
+		while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[order]))) {
+			found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+							order, usage);
 			if (found)
-				break;
+				goto done;
+			/* Clusters failed to allocate are moved to frag_clusters */
+			frags++;
 		}
 
-		if (!found) {
+		frags_existing = atomic_long_read(&si->frag_cluster_nr[order]);
+		while (frags < frags_existing &&
+		       (ci = isolate_lock_cluster(si, &si->frag_clusters[order]))) {
+			atomic_long_dec(&si->frag_cluster_nr[order]);
 			/*
-			 * Nonfull clusters are moved to frag tail if we reached
-			 * here, count them too, don't over scan the frag list.
+			 * Rotate the frag list to iterate, they were all
+			 * failing high order allocation or moved here due to
+			 * per-CPU usage, but they could contain newly released
+			 * reclaimable (eg. lazy-freed swap cache) slots.
 			 */
-			while (frags < si->frag_cluster_nr[order]) {
-				ci = list_first_entry(&si->frag_clusters[order],
-						      struct swap_cluster_info, list);
-				/*
-				 * Rotate the frag list to iterate, they were all failing
-				 * high order allocation or moved here due to per-CPU usage,
-				 * this help keeping usable cluster ahead.
-				 */
-				list_move_tail(&ci->list, &si->frag_clusters[order]);
-				offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
-								 &found, order, usage);
-				frags++;
-				if (found)
-					break;
-			}
+			found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+							order, usage);
+			if (found)
+				goto done;
+			frags++;
 		}
 	}
 
-	if (found)
-		goto done;
-
-	if (!list_empty(&si->discard_clusters)) {
-		/*
-		 * we don't have free cluster but have some clusters in
-		 * discarding, do discard now and reclaim them, then
-		 * reread cluster_next_cpu since we dropped si->lock
-		 */
-		swap_do_scheduled_discard(si);
+	/*
+	 * We don't have free cluster but have some clusters in
+	 * discarding, do discard now and reclaim them, then
+	 * reread cluster_next_cpu since we dropped si->lock
+	 */
+	if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si))
 		goto new_cluster;
-	}
 
 	if (order)
 		goto done;
@@ -886,74 +969,151 @@ new_cluster:
 		 * Clusters here have at least one usable slots and can't fail order 0
 		 * allocation, but reclaim may drop si->lock and race with another user.
 		 */
-		while (!list_empty(&si->frag_clusters[o])) {
-			ci = list_first_entry(&si->frag_clusters[o],
-					      struct swap_cluster_info, list);
-			offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
-							 &found, 0, usage);
+		while ((ci = isolate_lock_cluster(si, &si->frag_clusters[o]))) {
+			atomic_long_dec(&si->frag_cluster_nr[o]);
+			found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+							0, usage);
 			if (found)
 				goto done;
 		}
 
-		while (!list_empty(&si->nonfull_clusters[o])) {
-			ci = list_first_entry(&si->nonfull_clusters[o],
-					      struct swap_cluster_info, list);
-			offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
-							 &found, 0, usage);
+		while ((ci = isolate_lock_cluster(si, &si->nonfull_clusters[o]))) {
+			found = alloc_swap_scan_cluster(si, ci, cluster_offset(si, ci),
+							0, usage);
 			if (found)
 				goto done;
 		}
 	}
-
 done:
-	cluster->next[order] = offset;
+	if (si->flags & SWP_SOLIDSTATE)
+		local_unlock(&si->percpu_cluster->lock);
+	else
+		spin_unlock(&si->global_cluster_lock);
 	return found;
 }
 
-static void __del_from_avail_list(struct swap_info_struct *si)
+/* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */
+static void del_from_avail_list(struct swap_info_struct *si, bool swapoff)
 {
 	int nid;
+	unsigned long pages;
+
+	spin_lock(&swap_avail_lock);
+
+	if (swapoff) {
+		/*
+		 * Forcefully remove it. Clear the SWP_WRITEOK flags for
+		 * swapoff here so it's synchronized by both si->lock and
+		 * swap_avail_lock, to ensure the result can be seen by
+		 * add_to_avail_list.
+		 */
+		lockdep_assert_held(&si->lock);
+		si->flags &= ~SWP_WRITEOK;
+		atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
+	} else {
+		/*
+		 * If not called by swapoff, take it off-list only if it's
+		 * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly
+		 * si->inuse_pages == pages), any concurrent slot freeing,
+		 * or device already removed from plist by someone else
+		 * will make this return false.
+		 */
+		pages = si->pages;
+		if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages,
+					     pages | SWAP_USAGE_OFFLIST_BIT))
+			goto skip;
+	}
 
-	assert_spin_locked(&si->lock);
 	for_each_node(nid)
 		plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]);
+
+skip:
+	spin_unlock(&swap_avail_lock);
 }
 
-static void del_from_avail_list(struct swap_info_struct *si)
+/* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */
+static void add_to_avail_list(struct swap_info_struct *si, bool swapon)
 {
+	int nid;
+	long val;
+	unsigned long pages;
+
 	spin_lock(&swap_avail_lock);
-	__del_from_avail_list(si);
+
+	/* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */
+	if (swapon) {
+		lockdep_assert_held(&si->lock);
+		si->flags |= SWP_WRITEOK;
+	} else {
+		if (!(READ_ONCE(si->flags) & SWP_WRITEOK))
+			goto skip;
+	}
+
+	if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT))
+		goto skip;
+
+	val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages);
+
+	/*
+	 * When device is full and device is on the plist, only one updater will
+	 * see (inuse_pages == si->pages) and will call del_from_avail_list. If
+	 * that updater happen to be here, just skip adding.
+	 */
+	pages = si->pages;
+	if (val == pages) {
+		/* Just like the cmpxchg in del_from_avail_list */
+		if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages,
+					    pages | SWAP_USAGE_OFFLIST_BIT))
+			goto skip;
+	}
+
+	for_each_node(nid)
+		plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]);
+
+skip:
 	spin_unlock(&swap_avail_lock);
 }
 
-static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
-			     unsigned int nr_entries)
+/*
+ * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock
+ * within each cluster, so the total contribution to the global counter should
+ * always be positive and cannot exceed the total number of usable slots.
+ */
+static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries)
 {
-	unsigned int end = offset + nr_entries - 1;
-
-	if (offset == si->lowest_bit)
-		si->lowest_bit += nr_entries;
-	if (end == si->highest_bit)
-		WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries);
-	WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries);
-	if (si->inuse_pages == si->pages) {
-		si->lowest_bit = si->max;
-		si->highest_bit = 0;
-		del_from_avail_list(si);
+	long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages);
 
-		if (si->cluster_info && vm_swap_full())
-			schedule_work(&si->reclaim_work);
+	/*
+	 * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set,
+	 * remove it from the plist.
+	 */
+	if (unlikely(val == si->pages)) {
+		del_from_avail_list(si, false);
+		return true;
 	}
+
+	return false;
 }
 
-static void add_to_avail_list(struct swap_info_struct *si)
+static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries)
 {
-	int nid;
+	long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages);
 
-	spin_lock(&swap_avail_lock);
-	for_each_node(nid)
-		plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]);
-	spin_unlock(&swap_avail_lock);
+	/*
+	 * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set,
+	 * remove it from the plist.
+	 */
+	if (unlikely(val & SWAP_USAGE_OFFLIST_BIT))
+		add_to_avail_list(si, false);
+}
+
+static void swap_range_alloc(struct swap_info_struct *si,
+			     unsigned int nr_entries)
+{
+	if (swap_usage_add(si, nr_entries)) {
+		if (vm_swap_full())
+			schedule_work(&si->reclaim_work);
+	}
 }
 
 static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
@@ -968,18 +1128,11 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 	 * Use atomic clear_bit operations only on zeromap instead of non-atomic
 	 * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
 		clear_bit(offset + i, si->zeromap);
-
-	if (offset < si->lowest_bit)
-		si->lowest_bit = offset;
-	if (end > si->highest_bit) {
-		bool was_full = !si->highest_bit;
-
-		WRITE_ONCE(si->highest_bit, end);
-		if (was_full && (si->flags & SWP_WRITEOK))
-			add_to_avail_list(si);
+		zswap_invalidate(swp_entry(si->type, offset + i));
 	}
+
 	if (si->flags & SWP_BLKDEV)
 		swap_slot_free_notify =
 			si->bdev->bd_disk->fops->swap_slot_free_notify;
@@ -999,50 +1152,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 	 */
 	smp_wmb();
 	atomic_long_add(nr_entries, &nr_swap_pages);
-	WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries);
-}
-
-static void set_cluster_next(struct swap_info_struct *si, unsigned long next)
-{
-	unsigned long prev;
-
-	if (!(si->flags & SWP_SOLIDSTATE)) {
-		si->cluster_next = next;
-		return;
-	}
-
-	prev = this_cpu_read(*si->cluster_next_cpu);
-	/*
-	 * Cross the swap address space size aligned trunk, choose
-	 * another trunk randomly to avoid lock contention on swap
-	 * address space if possible.
-	 */
-	if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) !=
-	    (next >> SWAP_ADDRESS_SPACE_SHIFT)) {
-		/* No free swap slots available */
-		if (si->highest_bit <= si->lowest_bit)
-			return;
-		next = get_random_u32_inclusive(si->lowest_bit, si->highest_bit);
-		next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES);
-		next = max_t(unsigned int, next, si->lowest_bit);
-	}
-	this_cpu_write(*si->cluster_next_cpu, next);
-}
-
-static bool swap_offset_available_and_locked(struct swap_info_struct *si,
-					     unsigned long offset)
-{
-	if (data_race(!si->swap_map[offset])) {
-		spin_lock(&si->lock);
-		return true;
-	}
-
-	if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
-		spin_lock(&si->lock);
-		return true;
-	}
-
-	return false;
+	swap_usage_sub(si, nr_entries);
 }
 
 static int cluster_alloc_swap(struct swap_info_struct *si,
@@ -1051,10 +1161,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si,
 {
 	int n_ret = 0;
 
-	VM_BUG_ON(!si->cluster_info);
-
-	si->flags += SWP_SCANNING;
-
 	while (n_ret < nr) {
 		unsigned long offset = cluster_alloc_swap_entry(si, order, usage);
 
@@ -1063,8 +1169,6 @@ static int cluster_alloc_swap(struct swap_info_struct *si,
 		slots[n_ret++] = swp_entry(si->type, offset);
 	}
 
-	si->flags -= SWP_SCANNING;
-
 	return n_ret;
 }
 
@@ -1072,13 +1176,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 			       unsigned char usage, int nr,
 			       swp_entry_t slots[], int order)
 {
-	unsigned long offset;
-	unsigned long scan_base;
-	unsigned long last_in_cluster = 0;
-	int latency_ration = LATENCY_LIMIT;
 	unsigned int nr_pages = 1 << order;
-	int n_ret = 0;
-	bool scanned_many = false;
 
 	/*
 	 * We try to cluster swap pages by allocating them sequentially
@@ -1090,7 +1188,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 	 * But we do now try to find an empty cluster.  -Andrea
 	 * And we let swap pages go all over an SSD partition.  Hugh
 	 */
-
 	if (order > 0) {
 		/*
 		 * Should not even be attempting large allocations when huge
@@ -1103,165 +1200,30 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 		}
 
 		/*
-		 * Swapfile is not block device or not using clusters so unable
+		 * Swapfile is not block device so unable
 		 * to allocate large entries.
 		 */
-		if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
+		if (!(si->flags & SWP_BLKDEV))
 			return 0;
 	}
 
-	if (si->cluster_info)
-		return cluster_alloc_swap(si, usage, nr, slots, order);
-
-	si->flags += SWP_SCANNING;
-
-	/* For HDD, sequential access is more important. */
-	scan_base = si->cluster_next;
-	offset = scan_base;
-
-	if (unlikely(!si->cluster_nr--)) {
-		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
-			si->cluster_nr = SWAPFILE_CLUSTER - 1;
-			goto checks;
-		}
-
-		spin_unlock(&si->lock);
-
-		/*
-		 * If seek is expensive, start searching for new cluster from
-		 * start of partition, to minimize the span of allocated swap.
-		 */
-		scan_base = offset = si->lowest_bit;
-		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
-
-		/* Locate the first empty (unaligned) cluster */
-		for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) {
-			if (si->swap_map[offset])
-				last_in_cluster = offset + SWAPFILE_CLUSTER;
-			else if (offset == last_in_cluster) {
-				spin_lock(&si->lock);
-				offset -= SWAPFILE_CLUSTER - 1;
-				si->cluster_next = offset;
-				si->cluster_nr = SWAPFILE_CLUSTER - 1;
-				goto checks;
-			}
-			if (unlikely(--latency_ration < 0)) {
-				cond_resched();
-				latency_ration = LATENCY_LIMIT;
-			}
-		}
-
-		offset = scan_base;
-		spin_lock(&si->lock);
-		si->cluster_nr = SWAPFILE_CLUSTER - 1;
-	}
-
-checks:
-	if (!(si->flags & SWP_WRITEOK))
-		goto no_page;
-	if (!si->highest_bit)
-		goto no_page;
-	if (offset > si->highest_bit)
-		scan_base = offset = si->lowest_bit;
-
-	/* reuse swap entry of cache-only swap if not busy. */
-	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
-		int swap_was_freed;
-		spin_unlock(&si->lock);
-		swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT);
-		spin_lock(&si->lock);
-		/* entry was freed successfully, try to use this again */
-		if (swap_was_freed > 0)
-			goto checks;
-		goto scan; /* check next one */
-	}
-
-	if (si->swap_map[offset]) {
-		if (!n_ret)
-			goto scan;
-		else
-			goto done;
-	}
-	memset(si->swap_map + offset, usage, nr_pages);
-
-	swap_range_alloc(si, offset, nr_pages);
-	slots[n_ret++] = swp_entry(si->type, offset);
-
-	/* got enough slots or reach max slots? */
-	if ((n_ret == nr) || (offset >= si->highest_bit))
-		goto done;
-
-	/* search for next available slot */
-
-	/* time to take a break? */
-	if (unlikely(--latency_ration < 0)) {
-		if (n_ret)
-			goto done;
-		spin_unlock(&si->lock);
-		cond_resched();
-		spin_lock(&si->lock);
-		latency_ration = LATENCY_LIMIT;
-	}
-
-	if (si->cluster_nr && !si->swap_map[++offset]) {
-		/* non-ssd case, still more slots in cluster? */
-		--si->cluster_nr;
-		goto checks;
-	}
+	return cluster_alloc_swap(si, usage, nr, slots, order);
+}
 
+static bool get_swap_device_info(struct swap_info_struct *si)
+{
+	if (!percpu_ref_tryget_live(&si->users))
+		return false;
 	/*
-	 * Even if there's no free clusters available (fragmented),
-	 * try to scan a little more quickly with lock held unless we
-	 * have scanned too many slots already.
+	 * Guarantee the si->users are checked before accessing other
+	 * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is
+	 * up to dated.
+	 *
+	 * Paired with the spin_unlock() after setup_swap_info() in
+	 * enable_swap_info(), and smp_wmb() in swapoff.
 	 */
-	if (!scanned_many) {
-		unsigned long scan_limit;
-
-		if (offset < scan_base)
-			scan_limit = scan_base;
-		else
-			scan_limit = si->highest_bit;
-		for (; offset <= scan_limit && --latency_ration > 0;
-		     offset++) {
-			if (!si->swap_map[offset])
-				goto checks;
-		}
-	}
-
-done:
-	if (order == 0)
-		set_cluster_next(si, offset + 1);
-	si->flags -= SWP_SCANNING;
-	return n_ret;
-
-scan:
-	VM_WARN_ON(order > 0);
-	spin_unlock(&si->lock);
-	while (++offset <= READ_ONCE(si->highest_bit)) {
-		if (unlikely(--latency_ration < 0)) {
-			cond_resched();
-			latency_ration = LATENCY_LIMIT;
-			scanned_many = true;
-		}
-		if (swap_offset_available_and_locked(si, offset))
-			goto checks;
-	}
-	offset = si->lowest_bit;
-	while (offset < scan_base) {
-		if (unlikely(--latency_ration < 0)) {
-			cond_resched();
-			latency_ration = LATENCY_LIMIT;
-			scanned_many = true;
-		}
-		if (swap_offset_available_and_locked(si, offset))
-			goto checks;
-		offset++;
-	}
-	spin_lock(&si->lock);
-
-no_page:
-	si->flags -= SWP_SCANNING;
-	return n_ret;
+	smp_rmb();
+	return true;
 }
 
 int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
@@ -1291,32 +1253,15 @@ start_over:
 		/* requeue si to after same-priority siblings */
 		plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]);
 		spin_unlock(&swap_avail_lock);
-		spin_lock(&si->lock);
-		if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
-			spin_lock(&swap_avail_lock);
-			if (plist_node_empty(&si->avail_lists[node])) {
-				spin_unlock(&si->lock);
-				goto nextsi;
-			}
-			WARN(!si->highest_bit,
-			     "swap_info %d in list but !highest_bit\n",
-			     si->type);
-			WARN(!(si->flags & SWP_WRITEOK),
-			     "swap_info %d in list but !SWP_WRITEOK\n",
-			     si->type);
-			__del_from_avail_list(si);
-			spin_unlock(&si->lock);
-			goto nextsi;
+		if (get_swap_device_info(si)) {
+			n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
+					n_goal, swp_entries, order);
+			put_swap_device(si);
+			if (n_ret || size > 1)
+				goto check_out;
 		}
-		n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
-					    n_goal, swp_entries, order);
-		spin_unlock(&si->lock);
-		if (n_ret || size > 1)
-			goto check_out;
-		cond_resched();
 
 		spin_lock(&swap_avail_lock);
-nextsi:
 		/*
 		 * if we got here, it's likely that si was almost full before,
 		 * and since scan_swap_map_slots() can drop the si->lock,
@@ -1376,22 +1321,6 @@ out:
 	return NULL;
 }
 
-static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
-					struct swap_info_struct *q)
-{
-	struct swap_info_struct *p;
-
-	p = _swap_info_get(entry);
-
-	if (p != q) {
-		if (q != NULL)
-			spin_unlock(&q->lock);
-		if (p != NULL)
-			spin_lock(&p->lock);
-	}
-	return p;
-}
-
 static unsigned char __swap_entry_free_locked(struct swap_info_struct *si,
 					      unsigned long offset,
 					      unsigned char usage)
@@ -1481,16 +1410,8 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry)
 	si = swp_swap_info(entry);
 	if (!si)
 		goto bad_nofile;
-	if (!percpu_ref_tryget_live(&si->users))
+	if (!get_swap_device_info(si))
 		goto out;
-	/*
-	 * Guarantee the si->users are checked before accessing other
-	 * fields of swap_info_struct.
-	 *
-	 * Paired with the spin_unlock() after setup_swap_info() in
-	 * enable_swap_info().
-	 */
-	smp_rmb();
 	offset = swp_offset(entry);
 	if (offset >= si->max)
 		goto put_out;
@@ -1513,11 +1434,11 @@ static unsigned char __swap_entry_free(struct swap_info_struct *si,
 	unsigned long offset = swp_offset(entry);
 	unsigned char usage;
 
-	ci = lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
 	usage = __swap_entry_free_locked(si, offset, 1);
-	unlock_cluster_or_swap_info(si, ci);
 	if (!usage)
-		free_swap_slot(entry);
+		swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
+	unlock_cluster(ci);
 
 	return usage;
 }
@@ -1538,22 +1459,17 @@ static bool __swap_entries_free(struct swap_info_struct *si,
 	if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER)
 		goto fallback;
 
-	ci = lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
 	if (!swap_is_last_map(si, offset, nr, &has_cache)) {
-		unlock_cluster_or_swap_info(si, ci);
+		unlock_cluster(ci);
 		goto fallback;
 	}
 	for (i = 0; i < nr; i++)
 		WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
-	unlock_cluster_or_swap_info(si, ci);
+	if (!has_cache)
+		swap_entry_range_free(si, ci, entry, nr);
+	unlock_cluster(ci);
 
-	if (!has_cache) {
-		for (i = 0; i < nr; i++)
-			zswap_invalidate(swp_entry(si->type, offset + i));
-		spin_lock(&si->lock);
-		swap_entry_range_free(si, entry, nr);
-		spin_unlock(&si->lock);
-	}
 	return has_cache;
 
 fallback:
@@ -1573,24 +1489,32 @@ fallback:
  * Drop the last HAS_CACHE flag of swap entries, caller have to
  * ensure all entries belong to the same cgroup.
  */
-static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry,
-				  unsigned int nr_pages)
+static void swap_entry_range_free(struct swap_info_struct *si,
+				  struct swap_cluster_info *ci,
+				  swp_entry_t entry, unsigned int nr_pages)
 {
 	unsigned long offset = swp_offset(entry);
 	unsigned char *map = si->swap_map + offset;
 	unsigned char *map_end = map + nr_pages;
-	struct swap_cluster_info *ci;
 
-	ci = lock_cluster(si, offset);
+	/* It should never free entries across different clusters */
+	VM_BUG_ON(ci != offset_to_cluster(si, offset + nr_pages - 1));
+	VM_BUG_ON(cluster_is_empty(ci));
+	VM_BUG_ON(ci->count < nr_pages);
+
+	ci->count -= nr_pages;
 	do {
 		VM_BUG_ON(*map != SWAP_HAS_CACHE);
 		*map = 0;
 	} while (++map < map_end);
-	dec_cluster_info_page(si, ci, nr_pages);
-	unlock_cluster(ci);
 
 	mem_cgroup_uncharge_swap(entry, nr_pages);
 	swap_range_free(si, offset, nr_pages);
+
+	if (!ci->count)
+		free_cluster(si, ci);
+	else
+		partial_free_cluster(si, ci);
 }
 
 static void cluster_swap_free_nr(struct swap_info_struct *si,
@@ -1598,29 +1522,14 @@ static void cluster_swap_free_nr(struct swap_info_struct *si,
 		unsigned char usage)
 {
 	struct swap_cluster_info *ci;
-	DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 };
-	int i, nr;
+	unsigned long end = offset + nr_pages;
 
-	ci = lock_cluster_or_swap_info(si, offset);
-	while (nr_pages) {
-		nr = min(BITS_PER_LONG, nr_pages);
-		for (i = 0; i < nr; i++) {
-			if (!__swap_entry_free_locked(si, offset + i, usage))
-				bitmap_set(to_free, i, 1);
-		}
-		if (!bitmap_empty(to_free, BITS_PER_LONG)) {
-			unlock_cluster_or_swap_info(si, ci);
-			for_each_set_bit(i, to_free, BITS_PER_LONG)
-				free_swap_slot(swp_entry(si->type, offset + i));
-			if (nr == nr_pages)
-				return;
-			bitmap_clear(to_free, 0, BITS_PER_LONG);
-			ci = lock_cluster_or_swap_info(si, offset);
-		}
-		offset += nr;
-		nr_pages -= nr;
-	}
-	unlock_cluster_or_swap_info(si, ci);
+	ci = lock_cluster(si, offset);
+	do {
+		if (!__swap_entry_free_locked(si, offset, usage))
+			swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
+	} while (++offset < end);
+	unlock_cluster(ci);
 }
 
 /*
@@ -1659,59 +1568,35 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 	if (!si)
 		return;
 
-	ci = lock_cluster_or_swap_info(si, offset);
-	if (size > 1 && swap_is_has_cache(si, offset, size)) {
-		unlock_cluster_or_swap_info(si, ci);
-		spin_lock(&si->lock);
-		swap_entry_range_free(si, entry, size);
-		spin_unlock(&si->lock);
-		return;
-	}
-	for (int i = 0; i < size; i++, entry.val++) {
-		if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
-			unlock_cluster_or_swap_info(si, ci);
-			free_swap_slot(entry);
-			if (i == size - 1)
-				return;
-			lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
+	if (swap_is_has_cache(si, offset, size))
+		swap_entry_range_free(si, ci, entry, size);
+	else {
+		for (int i = 0; i < size; i++, entry.val++) {
+			if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE))
+				swap_entry_range_free(si, ci, entry, 1);
 		}
 	}
-	unlock_cluster_or_swap_info(si, ci);
-}
-
-static int swp_entry_cmp(const void *ent1, const void *ent2)
-{
-	const swp_entry_t *e1 = ent1, *e2 = ent2;
-
-	return (int)swp_type(*e1) - (int)swp_type(*e2);
+	unlock_cluster(ci);
 }
 
 void swapcache_free_entries(swp_entry_t *entries, int n)
 {
-	struct swap_info_struct *p, *prev;
 	int i;
+	struct swap_cluster_info *ci;
+	struct swap_info_struct *si = NULL;
 
 	if (n <= 0)
 		return;
 
-	prev = NULL;
-	p = NULL;
-
-	/*
-	 * Sort swap entries by swap device, so each lock is only taken once.
-	 * nr_swapfiles isn't absolutely correct, but the overhead of sort() is
-	 * so low that it isn't necessary to optimize further.
-	 */
-	if (nr_swapfiles > 1)
-		sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL);
 	for (i = 0; i < n; ++i) {
-		p = swap_info_get_cont(entries[i], prev);
-		if (p)
-			swap_entry_range_free(p, entries[i], 1);
-		prev = p;
+		si = _swap_info_get(entries[i]);
+		if (si) {
+			ci = lock_cluster(si, swp_offset(entries[i]));
+			swap_entry_range_free(si, ci, entries[i], 1);
+			unlock_cluster(ci);
+		}
 	}
-	if (p)
-		spin_unlock(&p->lock);
 }
 
 int __swap_count(swp_entry_t entry)
@@ -1733,9 +1618,9 @@ int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
 	struct swap_cluster_info *ci;
 	int count;
 
-	ci = lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
 	count = swap_count(si->swap_map[offset]);
-	unlock_cluster_or_swap_info(si, ci);
+	unlock_cluster(ci);
 	return count;
 }
 
@@ -1758,7 +1643,7 @@ int swp_swapcount(swp_entry_t entry)
 
 	offset = swp_offset(entry);
 
-	ci = lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
 
 	count = swap_count(si->swap_map[offset]);
 	if (!(count & COUNT_CONTINUED))
@@ -1781,7 +1666,7 @@ int swp_swapcount(swp_entry_t entry)
 		n *= (SWAP_CONT_MAX + 1);
 	} while (tmp_count & COUNT_CONTINUED);
 out:
-	unlock_cluster_or_swap_info(si, ci);
+	unlock_cluster(ci);
 	return count;
 }
 
@@ -1796,8 +1681,8 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
 	int i;
 	bool ret = false;
 
-	ci = lock_cluster_or_swap_info(si, offset);
-	if (!ci || nr_pages == 1) {
+	ci = lock_cluster(si, offset);
+	if (nr_pages == 1) {
 		if (swap_count(map[roffset]))
 			ret = true;
 		goto unlock_out;
@@ -1809,7 +1694,7 @@ static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
 		}
 	}
 unlock_out:
-	unlock_cluster_or_swap_info(si, ci);
+	unlock_cluster(ci);
 	return ret;
 }
 
@@ -1963,10 +1848,11 @@ swp_entry_t get_swap_page_of_type(int type)
 		goto fail;
 
 	/* This is called for allocating swap entry, not cache */
-	spin_lock(&si->lock);
-	if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
-		atomic_long_dec(&nr_swap_pages);
-	spin_unlock(&si->lock);
+	if (get_swap_device_info(si)) {
+		if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
+			atomic_long_dec(&nr_swap_pages);
+		put_swap_device(si);
+	}
 fail:
 	return entry;
 }
@@ -2057,7 +1943,7 @@ unsigned int count_swap_pages(int type, int free)
 		if (sis->flags & SWP_WRITEOK) {
 			n = sis->pages;
 			if (free)
-				n -= sis->inuse_pages;
+				n -= swap_usage_in_pages(sis);
 		}
 		spin_unlock(&sis->lock);
 	}
@@ -2392,7 +2278,7 @@ static int try_to_unuse(unsigned int type)
 	swp_entry_t entry;
 	unsigned int i;
 
-	if (!READ_ONCE(si->inuse_pages))
+	if (!swap_usage_in_pages(si))
 		goto success;
 
 retry:
@@ -2405,7 +2291,7 @@ retry:
 
 	spin_lock(&mmlist_lock);
 	p = &init_mm.mmlist;
-	while (READ_ONCE(si->inuse_pages) &&
+	while (swap_usage_in_pages(si) &&
 	       !signal_pending(current) &&
 	       (p = p->next) != &init_mm.mmlist) {
 
@@ -2433,7 +2319,7 @@ retry:
 	mmput(prev_mm);
 
 	i = 0;
-	while (READ_ONCE(si->inuse_pages) &&
+	while (swap_usage_in_pages(si) &&
 	       !signal_pending(current) &&
 	       (i = find_next_to_unuse(si, i)) != 0) {
 
@@ -2468,7 +2354,7 @@ retry:
 	 * folio_alloc_swap(), temporarily hiding that swap.  It's easy
 	 * and robust (though cpu-intensive) just to keep retrying.
 	 */
-	if (READ_ONCE(si->inuse_pages)) {
+	if (swap_usage_in_pages(si)) {
 		if (!signal_pending(current))
 			goto retry;
 		return -EINTR;
@@ -2495,7 +2381,7 @@ static void drain_mmlist(void)
 	unsigned int type;
 
 	for (type = 0; type < nr_swapfiles; type++)
-		if (swap_info[type]->inuse_pages)
+		if (swap_usage_in_pages(swap_info[type]))
 			return;
 	spin_lock(&mmlist_lock);
 	list_for_each_safe(p, next, &init_mm.mmlist)
@@ -2674,7 +2560,6 @@ static void setup_swap_info(struct swap_info_struct *si, int prio,
 
 static void _enable_swap_info(struct swap_info_struct *si)
 {
-	si->flags |= SWP_WRITEOK;
 	atomic_long_add(si->pages, &nr_swap_pages);
 	total_swap_pages += si->pages;
 
@@ -2691,9 +2576,8 @@ static void _enable_swap_info(struct swap_info_struct *si)
 	 */
 	plist_add(&si->list, &swap_active_head);
 
-	/* add to available list iff swap device is not full */
-	if (si->highest_bit)
-		add_to_avail_list(si);
+	/* Add back to available list */
+	add_to_avail_list(si, true);
 }
 
 static void enable_swap_info(struct swap_info_struct *si, int prio,
@@ -2742,6 +2626,25 @@ bool has_usable_swap(void)
 	return ret;
 }
 
+/*
+ * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range
+ * see the updated flags, so there will be no more allocations.
+ */
+static void wait_for_allocation(struct swap_info_struct *si)
+{
+	unsigned long offset;
+	unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER);
+	struct swap_cluster_info *ci;
+
+	BUG_ON(si->flags & SWP_WRITEOK);
+
+	for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
+		ci = lock_cluster(si, offset);
+		unlock_cluster(ci);
+		offset += SWAPFILE_CLUSTER;
+	}
+}
+
 SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct *p = NULL;
@@ -2791,7 +2694,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		goto out_dput;
 	}
 	spin_lock(&p->lock);
-	del_from_avail_list(p);
+	del_from_avail_list(p, true);
 	if (p->prio < 0) {
 		struct swap_info_struct *si = p;
 		int nid;
@@ -2809,10 +2712,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	plist_del(&p->list, &swap_active_head);
 	atomic_long_sub(p->pages, &nr_swap_pages);
 	total_swap_pages -= p->pages;
-	p->flags &= ~SWP_WRITEOK;
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 
+	wait_for_allocation(p);
+
 	disable_swap_slots_cache_lock();
 
 	set_current_oom_origin();
@@ -2855,16 +2759,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	spin_lock(&p->lock);
 	drain_mmlist();
 
-	/* wait for anyone still in scan_swap_map_slots */
-	p->highest_bit = 0;		/* cuts scans short */
-	while (p->flags >= SWP_SCANNING) {
-		spin_unlock(&p->lock);
-		spin_unlock(&swap_lock);
-		schedule_timeout_uninterruptible(1);
-		spin_lock(&swap_lock);
-		spin_lock(&p->lock);
-	}
-
 	swap_file = p->swap_file;
 	p->swap_file = NULL;
 	p->max = 0;
@@ -2881,8 +2775,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	mutex_unlock(&swapon_mutex);
 	free_percpu(p->percpu_cluster);
 	p->percpu_cluster = NULL;
-	free_percpu(p->cluster_next_cpu);
-	p->cluster_next_cpu = NULL;
+	kfree(p->global_cluster);
+	p->global_cluster = NULL;
 	vfree(swap_map);
 	kvfree(zeromap);
 	kvfree(cluster_info);
@@ -2992,7 +2886,7 @@ static int swap_show(struct seq_file *swap, void *v)
 	}
 
 	bytes = K(si->pages);
-	inuse = K(READ_ONCE(si->inuse_pages));
+	inuse = K(swap_usage_in_pages(si));
 
 	file = si->swap_file;
 	len = seq_file_path(swap, file, " \t\n\\");
@@ -3109,6 +3003,7 @@ static struct swap_info_struct *alloc_swap_info(void)
 	}
 	spin_lock_init(&p->lock);
 	spin_lock_init(&p->cont_lock);
+	atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT);
 	init_completion(&p->comp);
 
 	return p;
@@ -3193,10 +3088,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
 		return 0;
 	}
 
-	si->lowest_bit  = 1;
-	si->cluster_next = 1;
-	si->cluster_nr = 0;
-
 	maxpages = swapfile_maximum_size;
 	last_page = swap_header->info.last_page;
 	if (!last_page) {
@@ -3213,7 +3104,6 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
 		if ((unsigned int)maxpages == 0)
 			maxpages = UINT_MAX;
 	}
-	si->highest_bit = maxpages - 1;
 
 	if (!maxpages)
 		return 0;
@@ -3281,7 +3171,6 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 						unsigned long maxpages)
 {
 	unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
-	unsigned long col = si->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS;
 	struct swap_cluster_info *cluster_info;
 	unsigned long i, j, k, idx;
 	int cpu, err = -ENOMEM;
@@ -3293,25 +3182,27 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 	for (i = 0; i < nr_clusters; i++)
 		spin_lock_init(&cluster_info[i].lock);
 
-	si->cluster_next_cpu = alloc_percpu(unsigned int);
-	if (!si->cluster_next_cpu)
-		goto err_free;
-
-	/* Random start position to help with wear leveling */
-	for_each_possible_cpu(cpu)
-		per_cpu(*si->cluster_next_cpu, cpu) =
-		get_random_u32_inclusive(1, si->highest_bit);
+	if (si->flags & SWP_SOLIDSTATE) {
+		si->percpu_cluster = alloc_percpu(struct percpu_cluster);
+		if (!si->percpu_cluster)
+			goto err_free;
 
-	si->percpu_cluster = alloc_percpu(struct percpu_cluster);
-	if (!si->percpu_cluster)
-		goto err_free;
+		for_each_possible_cpu(cpu) {
+			struct percpu_cluster *cluster;
 
-	for_each_possible_cpu(cpu) {
-		struct percpu_cluster *cluster;
-
-		cluster = per_cpu_ptr(si->percpu_cluster, cpu);
+			cluster = per_cpu_ptr(si->percpu_cluster, cpu);
+			for (i = 0; i < SWAP_NR_ORDERS; i++)
+				cluster->next[i] = SWAP_ENTRY_INVALID;
+			local_lock_init(&cluster->lock);
+		}
+	} else {
+		si->global_cluster = kmalloc(sizeof(*si->global_cluster),
+				     GFP_KERNEL);
+		if (!si->global_cluster)
+			goto err_free;
 		for (i = 0; i < SWAP_NR_ORDERS; i++)
-			cluster->next[i] = SWAP_NEXT_INVALID;
+			si->global_cluster->next[i] = SWAP_ENTRY_INVALID;
+		spin_lock_init(&si->global_cluster_lock);
 	}
 
 	/*
@@ -3335,7 +3226,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 	for (i = 0; i < SWAP_NR_ORDERS; i++) {
 		INIT_LIST_HEAD(&si->nonfull_clusters[i]);
 		INIT_LIST_HEAD(&si->frag_clusters[i]);
-		si->frag_cluster_nr[i] = 0;
+		atomic_long_set(&si->frag_cluster_nr[i], 0);
 	}
 
 	/*
@@ -3343,7 +3234,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 	 * sharing same address space.
 	 */
 	for (k = 0; k < SWAP_CLUSTER_COLS; k++) {
-		j = (k + col) % SWAP_CLUSTER_COLS;
+		j = k % SWAP_CLUSTER_COLS;
 		for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) {
 			struct swap_cluster_info *ci;
 			idx = i * SWAP_CLUSTER_COLS + j;
@@ -3493,18 +3384,18 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	if (si->bdev && bdev_nonrot(si->bdev)) {
 		si->flags |= SWP_SOLIDSTATE;
-
-		cluster_info = setup_clusters(si, swap_header, maxpages);
-		if (IS_ERR(cluster_info)) {
-			error = PTR_ERR(cluster_info);
-			cluster_info = NULL;
-			goto bad_swap_unlock_inode;
-		}
 	} else {
 		atomic_inc(&nr_rotate_swap);
 		inced_nr_rotate_swap = true;
 	}
 
+	cluster_info = setup_clusters(si, swap_header, maxpages);
+	if (IS_ERR(cluster_info)) {
+		error = PTR_ERR(cluster_info);
+		cluster_info = NULL;
+		goto bad_swap_unlock_inode;
+	}
+
 	if ((swap_flags & SWAP_FLAG_DISCARD) &&
 	    si->bdev && bdev_max_discard_sectors(si->bdev)) {
 		/*
@@ -3585,8 +3476,8 @@ bad_swap_unlock_inode:
 bad_swap:
 	free_percpu(si->percpu_cluster);
 	si->percpu_cluster = NULL;
-	free_percpu(si->cluster_next_cpu);
-	si->cluster_next_cpu = NULL;
+	kfree(si->global_cluster);
+	si->global_cluster = NULL;
 	inode = NULL;
 	destroy_swap_extents(si);
 	swap_cgroup_swapoff(si->type);
@@ -3623,7 +3514,7 @@ void si_swapinfo(struct sysinfo *val)
 		struct swap_info_struct *si = swap_info[type];
 
 		if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK))
-			nr_to_be_unused += READ_ONCE(si->inuse_pages);
+			nr_to_be_unused += swap_usage_in_pages(si);
 	}
 	val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused;
 	val->totalswap = total_swap_pages + nr_to_be_unused;
@@ -3655,7 +3546,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
 	offset = swp_offset(entry);
 	VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
 	VM_WARN_ON(usage == 1 && nr > 1);
-	ci = lock_cluster_or_swap_info(si, offset);
+	ci = lock_cluster(si, offset);
 
 	err = 0;
 	for (i = 0; i < nr; i++) {
@@ -3710,7 +3601,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
 	}
 
 unlock_out:
-	unlock_cluster_or_swap_info(si, ci);
+	unlock_cluster(ci);
 	return err;
 }
 
@@ -3819,7 +3710,6 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 		 */
 		goto outer;
 	}
-	spin_lock(&si->lock);
 
 	offset = swp_offset(entry);
 
@@ -3884,7 +3774,6 @@ out_unlock_cont:
 	spin_unlock(&si->cont_lock);
 out:
 	unlock_cluster(ci);
-	spin_unlock(&si->lock);
 	put_swap_device(si);
 outer:
 	if (page)
diff --git a/mm/truncate.c b/mm/truncate.c
index 7c304d2f0052..e2e115adfbc5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -525,6 +525,15 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 }
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
+static int folio_launder(struct address_space *mapping, struct folio *folio)
+{
+	if (!folio_test_dirty(folio))
+		return 0;
+	if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
+		return 0;
+	return mapping->a_ops->launder_folio(folio);
+}
+
 /*
  * This is like mapping_evict_folio(), except it ignores the folio's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
@@ -532,14 +541,26 @@ EXPORT_SYMBOL(invalidate_mapping_pages);
  * shrink_folio_list() has a temp ref on them, or because they're transiently
  * sitting in the folio_add_lru() caches.
  */
-static int invalidate_complete_folio2(struct address_space *mapping,
-					struct folio *folio)
+int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
+			   gfp_t gfp)
 {
-	if (folio->mapping != mapping)
-		return 0;
+	int ret;
+
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
-	if (!filemap_release_folio(folio, GFP_KERNEL))
+	if (folio_test_dirty(folio))
 		return 0;
+	if (folio_mapped(folio))
+		unmap_mapping_folio(folio);
+	BUG_ON(folio_mapped(folio));
+
+	ret = folio_launder(mapping, folio);
+	if (ret)
+		return ret;
+	if (folio->mapping != mapping)
+		return -EBUSY;
+	if (!filemap_release_folio(folio, gfp))
+		return -EBUSY;
 
 	spin_lock(&mapping->host->i_lock);
 	xa_lock_irq(&mapping->i_pages);
@@ -558,16 +579,7 @@ static int invalidate_complete_folio2(struct address_space *mapping,
 failed:
 	xa_unlock_irq(&mapping->i_pages);
 	spin_unlock(&mapping->host->i_lock);
-	return 0;
-}
-
-static int folio_launder(struct address_space *mapping, struct folio *folio)
-{
-	if (!folio_test_dirty(folio))
-		return 0;
-	if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
-		return 0;
-	return mapping->a_ops->launder_folio(folio);
+	return -EBUSY;
 }
 
 /**
@@ -631,16 +643,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			}
 			VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio);
 			folio_wait_writeback(folio);
-
-			if (folio_mapped(folio))
-				unmap_mapping_folio(folio);
-			BUG_ON(folio_mapped(folio));
-
-			ret2 = folio_launder(mapping, folio);
-			if (ret2 == 0) {
-				if (!invalidate_complete_folio2(mapping, folio))
-					ret2 = -EBUSY;
-			}
+			ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL);
 			if (ret2 < 0)
 				ret = ret2;
 			folio_unlock(folio);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 60a0be33766f..af3dfc3633db 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1020,6 +1020,14 @@ void double_pt_unlock(spinlock_t *ptl1,
 		__release(ptl2);
 }
 
+static inline bool is_pte_pages_stable(pte_t *dst_pte, pte_t *src_pte,
+				       pte_t orig_dst_pte, pte_t orig_src_pte,
+				       pmd_t *dst_pmd, pmd_t dst_pmdval)
+{
+	return pte_same(ptep_get(src_pte), orig_src_pte) &&
+	       pte_same(ptep_get(dst_pte), orig_dst_pte) &&
+	       pmd_same(dst_pmdval, pmdp_get_lockless(dst_pmd));
+}
 
 static int move_present_pte(struct mm_struct *mm,
 			    struct vm_area_struct *dst_vma,
@@ -1027,6 +1035,7 @@ static int move_present_pte(struct mm_struct *mm,
 			    unsigned long dst_addr, unsigned long src_addr,
 			    pte_t *dst_pte, pte_t *src_pte,
 			    pte_t orig_dst_pte, pte_t orig_src_pte,
+			    pmd_t *dst_pmd, pmd_t dst_pmdval,
 			    spinlock_t *dst_ptl, spinlock_t *src_ptl,
 			    struct folio *src_folio)
 {
@@ -1034,8 +1043,8 @@ static int move_present_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
-	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
+	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
+				 dst_pmd, dst_pmdval)) {
 		err = -EAGAIN;
 		goto out;
 	}
@@ -1071,6 +1080,7 @@ static int move_swap_pte(struct mm_struct *mm,
 			 unsigned long dst_addr, unsigned long src_addr,
 			 pte_t *dst_pte, pte_t *src_pte,
 			 pte_t orig_dst_pte, pte_t orig_src_pte,
+			 pmd_t *dst_pmd, pmd_t dst_pmdval,
 			 spinlock_t *dst_ptl, spinlock_t *src_ptl)
 {
 	if (!pte_swp_exclusive(orig_src_pte))
@@ -1078,8 +1088,8 @@ static int move_swap_pte(struct mm_struct *mm,
 
 	double_pt_lock(dst_ptl, src_ptl);
 
-	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
-	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
+	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
+				 dst_pmd, dst_pmdval)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
 	}
@@ -1097,13 +1107,14 @@ static int move_zeropage_pte(struct mm_struct *mm,
 			     unsigned long dst_addr, unsigned long src_addr,
 			     pte_t *dst_pte, pte_t *src_pte,
 			     pte_t orig_dst_pte, pte_t orig_src_pte,
+			     pmd_t *dst_pmd, pmd_t dst_pmdval,
 			     spinlock_t *dst_ptl, spinlock_t *src_ptl)
 {
 	pte_t zero_pte;
 
 	double_pt_lock(dst_ptl, src_ptl);
-	if (!pte_same(ptep_get(src_pte), orig_src_pte) ||
-	    !pte_same(ptep_get(dst_pte), orig_dst_pte)) {
+	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
+				 dst_pmd, dst_pmdval)) {
 		double_pt_unlock(dst_ptl, src_ptl);
 		return -EAGAIN;
 	}
@@ -1136,6 +1147,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 	pte_t *src_pte = NULL;
 	pte_t *dst_pte = NULL;
 	pmd_t dummy_pmdval;
+	pmd_t dst_pmdval;
 	struct folio *src_folio = NULL;
 	struct anon_vma *src_anon_vma = NULL;
 	struct mmu_notifier_range range;
@@ -1148,11 +1160,11 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 retry:
 	/*
 	 * Use the maywrite version to indicate that dst_pte will be modified,
-	 * but since we will use pte_same() to detect the change of the pte
-	 * entry, there is no need to get pmdval, so just pass a dummy variable
-	 * to it.
+	 * since dst_pte needs to be none, the subsequent pte_same() check
+	 * cannot prevent the dst_pte page from being freed concurrently, so we
+	 * also need to abtain dst_pmdval and recheck pmd_same() later.
 	 */
-	dst_pte = pte_offset_map_rw_nolock(mm, dst_pmd, dst_addr, &dummy_pmdval,
+	dst_pte = pte_offset_map_rw_nolock(mm, dst_pmd, dst_addr, &dst_pmdval,
 					   &dst_ptl);
 
 	/* Retry if a huge pmd materialized from under us */
@@ -1161,7 +1173,11 @@ retry:
 		goto out;
 	}
 
-	/* same as dst_pte */
+	/*
+	 * Unlike dst_pte, the subsequent pte_same() check can ensure the
+	 * stability of the src_pte page, so there is no need to get pmdval,
+	 * just pass a dummy variable to it.
+	 */
 	src_pte = pte_offset_map_rw_nolock(mm, src_pmd, src_addr, &dummy_pmdval,
 					   &src_ptl);
 
@@ -1177,8 +1193,8 @@ retry:
 	}
 
 	/* Sanity checks before the operation */
-	if (WARN_ON_ONCE(pmd_none(*dst_pmd)) ||	WARN_ON_ONCE(pmd_none(*src_pmd)) ||
-	    WARN_ON_ONCE(pmd_trans_huge(*dst_pmd)) || WARN_ON_ONCE(pmd_trans_huge(*src_pmd))) {
+	if (pmd_none(*dst_pmd) || pmd_none(*src_pmd) ||
+	    pmd_trans_huge(*dst_pmd) || pmd_trans_huge(*src_pmd)) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -1213,7 +1229,7 @@ retry:
 			err = move_zeropage_pte(mm, dst_vma, src_vma,
 					       dst_addr, src_addr, dst_pte, src_pte,
 					       orig_dst_pte, orig_src_pte,
-					       dst_ptl, src_ptl);
+					       dst_pmd, dst_pmdval, dst_ptl, src_ptl);
 			goto out;
 		}
 
@@ -1303,8 +1319,8 @@ retry:
 
 		err = move_present_pte(mm,  dst_vma, src_vma,
 				       dst_addr, src_addr, dst_pte, src_pte,
-				       orig_dst_pte, orig_src_pte,
-				       dst_ptl, src_ptl, src_folio);
+				       orig_dst_pte, orig_src_pte, dst_pmd,
+				       dst_pmdval, dst_ptl, src_ptl, src_folio);
 	} else {
 		entry = pte_to_swp_entry(orig_src_pte);
 		if (non_swap_entry(entry)) {
@@ -1319,10 +1335,9 @@ retry:
 			goto out;
 		}
 
-		err = move_swap_pte(mm, dst_addr, src_addr,
-				    dst_pte, src_pte,
-				    orig_dst_pte, orig_src_pte,
-				    dst_ptl, src_ptl);
+		err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte,
+				    orig_dst_pte, orig_src_pte, dst_pmd,
+				    dst_pmdval, dst_ptl, src_ptl);
 	}
 
 out:
diff --git a/mm/util.c b/mm/util.c
index 60aa40f612b8..b6b9684a1438 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -582,6 +582,23 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	return ret;
 }
 
+/*
+ * Perform a userland memory mapping into the current process address space. See
+ * the comment for do_mmap() for more details on this operation in general.
+ *
+ * This differs from do_mmap() in that:
+ *
+ * a. An offset parameter is provided rather than pgoff, which is both checked
+ *    for overflow and page alignment.
+ * b. mmap locking is performed on the caller's behalf.
+ * c. Userfaultfd unmap events and memory population are handled.
+ *
+ * This means that this function performs essentially the same work as if
+ * userland were invoking mmap (2).
+ *
+ * Returns either an error, or the address at which the requested mapping has
+ * been performed.
+ */
 unsigned long vm_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot,
 	unsigned long flag, unsigned long offset)
diff --git a/mm/vma.c b/mm/vma.c
index bb2119e5a0d0..af1d549b179c 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -203,6 +203,38 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 }
 
 /*
+ * vma has some anon_vma assigned, and is already inserted on that
+ * anon_vma's interval trees.
+ *
+ * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
+ * vma must be removed from the anon_vma's interval trees using
+ * anon_vma_interval_tree_pre_update_vma().
+ *
+ * After the update, the vma will be reinserted using
+ * anon_vma_interval_tree_post_update_vma().
+ *
+ * The entire update must be protected by exclusive mmap_lock and by
+ * the root anon_vma's mutex.
+ */
+static void
+anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
+{
+	struct anon_vma_chain *avc;
+
+	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
+}
+
+static void
+anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
+{
+	struct anon_vma_chain *avc;
+
+	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
+}
+
+/*
  * vma_prepare() - Helper function for handling locking VMAs prior to altering
  * @vp: The initialized vma_prepare struct
  */
@@ -398,7 +430,6 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_gather tlb;
 
-	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm);
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, mas, vma, vma->vm_start, vma->vm_end, vma->vm_end,
@@ -415,8 +446,9 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
  * has already been checked or doesn't make sense to fail.
  * VMA Iterator will point to the original VMA.
  */
-static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		       unsigned long addr, int new_below)
+static __must_check int
+__split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
+	    unsigned long addr, int new_below)
 {
 	struct vma_prepare vp;
 	struct vm_area_struct *new;
@@ -511,38 +543,6 @@ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 }
 
 /*
- * vma has some anon_vma assigned, and is already inserted on that
- * anon_vma's interval trees.
- *
- * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the
- * vma must be removed from the anon_vma's interval trees using
- * anon_vma_interval_tree_pre_update_vma().
- *
- * After the update, the vma will be reinserted using
- * anon_vma_interval_tree_post_update_vma().
- *
- * The entire update must be protected by exclusive mmap_lock and by
- * the root anon_vma's mutex.
- */
-void
-anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma)
-{
-	struct anon_vma_chain *avc;
-
-	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-		anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root);
-}
-
-void
-anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma)
-{
-	struct anon_vma_chain *avc;
-
-	list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-		anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root);
-}
-
-/*
  * dup_anon_vma() - Helper function to duplicate anon_vma
  * @dst: The destination VMA
  * @src: The source VMA
@@ -710,7 +710,8 @@ static bool can_merge_remove_vma(struct vm_area_struct *vma)
  * - The caller must hold a WRITE lock on the mm_struct->mmap_lock.
  * - vmi must be positioned within [@vmg->vma->vm_start, @vmg->vma->vm_end).
  */
-static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *vmg)
+static __must_check struct vm_area_struct *vma_merge_existing_range(
+		struct vma_merge_struct *vmg)
 {
 	struct vm_area_struct *vma = vmg->vma;
 	struct vm_area_struct *prev = vmg->prev;
@@ -728,19 +729,20 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *
 	bool expanded;
 
 	mmap_assert_write_locked(vmg->mm);
-	VM_WARN_ON(!vma); /* We are modifying a VMA, so caller must specify. */
-	VM_WARN_ON(vmg->next); /* We set this. */
-	VM_WARN_ON(prev && start <= prev->vm_start);
-	VM_WARN_ON(start >= end);
+	VM_WARN_ON_VMG(!vma, vmg); /* We are modifying a VMA, so caller must specify. */
+	VM_WARN_ON_VMG(vmg->next, vmg); /* We set this. */
+	VM_WARN_ON_VMG(prev && start <= prev->vm_start, vmg);
+	VM_WARN_ON_VMG(start >= end, vmg);
+
 	/*
 	 * If vma == prev, then we are offset into a VMA. Otherwise, if we are
 	 * not, we must span a portion of the VMA.
 	 */
-	VM_WARN_ON(vma && ((vma != prev && vmg->start != vma->vm_start) ||
-			   vmg->end > vma->vm_end));
+	VM_WARN_ON_VMG(vma && ((vma != prev && vmg->start != vma->vm_start) ||
+			       vmg->end > vma->vm_end), vmg);
 	/* The vmi must be positioned within vmg->vma. */
-	VM_WARN_ON(vma && !(vma_iter_addr(vmg->vmi) >= vma->vm_start &&
-			    vma_iter_addr(vmg->vmi) < vma->vm_end));
+	VM_WARN_ON_VMG(vma && !(vma_iter_addr(vmg->vmi) >= vma->vm_start &&
+				vma_iter_addr(vmg->vmi) < vma->vm_end), vmg);
 
 	vmg->state = VMA_MERGE_NOMERGE;
 
@@ -857,9 +859,9 @@ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *
 
 		pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start);
 
-		VM_WARN_ON(!merge_right);
+		VM_WARN_ON_VMG(!merge_right, vmg);
 		/* If we are offset into a VMA, then prev must be vma. */
-		VM_WARN_ON(vmg->start > vma->vm_start && prev && vma != prev);
+		VM_WARN_ON_VMG(vmg->start > vma->vm_start && prev && vma != prev, vmg);
 
 		if (merge_will_delete_vma) {
 			vmg->vma = next;
@@ -971,9 +973,9 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 	bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND;
 
 	mmap_assert_write_locked(vmg->mm);
-	VM_WARN_ON(vmg->vma);
+	VM_WARN_ON_VMG(vmg->vma, vmg);
 	/* vmi must point at or before the gap. */
-	VM_WARN_ON(vma_iter_addr(vmg->vmi) > end);
+	VM_WARN_ON_VMG(vma_iter_addr(vmg->vmi) > end, vmg);
 
 	vmg->state = VMA_MERGE_NOMERGE;
 
@@ -1055,7 +1057,7 @@ int vma_expand(struct vma_merge_struct *vmg)
 
 		remove_next = true;
 		/* This should already have been checked by this point. */
-		VM_WARN_ON(!can_merge_remove_vma(next));
+		VM_WARN_ON_VMG(!can_merge_remove_vma(next), vmg);
 		vma_start_write(next);
 		ret = dup_anon_vma(vma, next, &anon_dup);
 		if (ret)
@@ -1063,10 +1065,10 @@ int vma_expand(struct vma_merge_struct *vmg)
 	}
 
 	/* Not merging but overwriting any part of next is not handled. */
-	VM_WARN_ON(next && !remove_next &&
-		  next != vma && vmg->end > next->vm_start);
+	VM_WARN_ON_VMG(next && !remove_next &&
+		       next != vma && vmg->end > next->vm_start, vmg);
 	/* Only handles expanding */
-	VM_WARN_ON(vma->vm_start < vmg->start || vma->vm_end > vmg->end);
+	VM_WARN_ON_VMG(vma->vm_start < vmg->start || vma->vm_end > vmg->end, vmg);
 
 	if (commit_merge(vmg, NULL, remove_next ? next : NULL, NULL, 0, true))
 		goto nomem;
@@ -1130,7 +1132,6 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms,
 	 * were isolated before we downgraded mmap_lock.
 	 */
 	mas_set(mas_detach, 1);
-	lru_add_drain();
 	tlb_gather_mmu(&tlb, vms->vma->vm_mm);
 	update_hiwater_rss(vms->vma->vm_mm);
 	unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end,
@@ -2430,7 +2431,7 @@ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma)
 	vma_set_page_prot(vma);
 }
 
-unsigned long __mmap_region(struct file *file, unsigned long addr,
+static unsigned long __mmap_region(struct file *file, unsigned long addr,
 		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
 		struct list_head *uf)
 {
@@ -2481,3 +2482,476 @@ abort_munmap:
 	vms_abort_munmap_vmas(&map.vms, &map.mas_detach);
 	return error;
 }
+
+/**
+ * mmap_region() - Actually perform the userland mapping of a VMA into
+ * current->mm with known, aligned and overflow-checked @addr and @len, and
+ * correctly determined VMA flags @vm_flags and page offset @pgoff.
+ *
+ * This is an internal memory management function, and should not be used
+ * directly.
+ *
+ * The caller must write-lock current->mm->mmap_lock.
+ *
+ * @file: If a file-backed mapping, a pointer to the struct file describing the
+ * file to be mapped, otherwise NULL.
+ * @addr: The page-aligned address at which to perform the mapping.
+ * @len: The page-aligned, non-zero, length of the mapping.
+ * @vm_flags: The VMA flags which should be applied to the mapping.
+ * @pgoff: If @file is specified, the page offset into the file, if not then
+ * the virtual page offset in memory of the anonymous mapping.
+ * @uf: Optionally, a pointer to a list head used for tracking userfaultfd unmap
+ * events.
+ *
+ * Returns: Either an error, or the address at which the requested mapping has
+ * been performed.
+ */
+unsigned long mmap_region(struct file *file, unsigned long addr,
+			  unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
+			  struct list_head *uf)
+{
+	unsigned long ret;
+	bool writable_file_mapping = false;
+
+	mmap_assert_write_locked(current->mm);
+
+	/* Check to see if MDWE is applicable. */
+	if (map_deny_write_exec(vm_flags, vm_flags))
+		return -EACCES;
+
+	/* Allow architectures to sanity-check the vm_flags. */
+	if (!arch_validate_flags(vm_flags))
+		return -EINVAL;
+
+	/* Map writable and ensure this isn't a sealed memfd. */
+	if (file && is_shared_maywrite(vm_flags)) {
+		int error = mapping_map_writable(file->f_mapping);
+
+		if (error)
+			return error;
+		writable_file_mapping = true;
+	}
+
+	ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf);
+
+	/* Clear our write mapping regardless of error. */
+	if (writable_file_mapping)
+		mapping_unmap_writable(file->f_mapping);
+
+	validate_mm(current->mm);
+	return ret;
+}
+
+/*
+ * do_brk_flags() - Increase the brk vma if the flags match.
+ * @vmi: The vma iterator
+ * @addr: The start address
+ * @len: The length of the increase
+ * @vma: The vma,
+ * @flags: The VMA Flags
+ *
+ * Extend the brk VMA from addr to addr + len.  If the VMA is NULL or the flags
+ * do not match then create a new anonymous VMA.  Eventually we may be able to
+ * do some brk-specific accounting here.
+ */
+int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
+		 unsigned long addr, unsigned long len, unsigned long flags)
+{
+	struct mm_struct *mm = current->mm;
+
+	/*
+	 * Check against address space limits by the changed size
+	 * Note: This happens *after* clearing old mappings in some code paths.
+	 */
+	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+	if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
+		return -ENOMEM;
+
+	if (mm->map_count > sysctl_max_map_count)
+		return -ENOMEM;
+
+	if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT))
+		return -ENOMEM;
+
+	/*
+	 * Expand the existing vma if possible; Note that singular lists do not
+	 * occur after forking, so the expand will only happen on new VMAs.
+	 */
+	if (vma && vma->vm_end == addr) {
+		VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr));
+
+		vmg.prev = vma;
+		/* vmi is positioned at prev, which this mode expects. */
+		vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
+
+		if (vma_merge_new_range(&vmg))
+			goto out;
+		else if (vmg_nomem(&vmg))
+			goto unacct_fail;
+	}
+
+	if (vma)
+		vma_iter_next_range(vmi);
+	/* create a vma struct for an anonymous mapping */
+	vma = vm_area_alloc(mm);
+	if (!vma)
+		goto unacct_fail;
+
+	vma_set_anonymous(vma);
+	vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT);
+	vm_flags_init(vma, flags);
+	vma->vm_page_prot = vm_get_page_prot(flags);
+	vma_start_write(vma);
+	if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL))
+		goto mas_store_fail;
+
+	mm->map_count++;
+	validate_mm(mm);
+	ksm_add_vma(vma);
+out:
+	perf_event_mmap(vma);
+	mm->total_vm += len >> PAGE_SHIFT;
+	mm->data_vm += len >> PAGE_SHIFT;
+	if (flags & VM_LOCKED)
+		mm->locked_vm += (len >> PAGE_SHIFT);
+	vm_flags_set(vma, VM_SOFTDIRTY);
+	return 0;
+
+mas_store_fail:
+	vm_area_free(vma);
+unacct_fail:
+	vm_unacct_memory(len >> PAGE_SHIFT);
+	return -ENOMEM;
+}
+
+/**
+ * unmapped_area() - Find an area between the low_limit and the high_limit with
+ * the correct alignment and offset, all from @info. Note: current->mm is used
+ * for the search.
+ *
+ * @info: The unmapped area information including the range [low_limit -
+ * high_limit), the alignment offset and mask.
+ *
+ * Return: A memory address or -ENOMEM.
+ */
+unsigned long unmapped_area(struct vm_unmapped_area_info *info)
+{
+	unsigned long length, gap;
+	unsigned long low_limit, high_limit;
+	struct vm_area_struct *tmp;
+	VMA_ITERATOR(vmi, current->mm, 0);
+
+	/* Adjust search length to account for worst case alignment overhead */
+	length = info->length + info->align_mask + info->start_gap;
+	if (length < info->length)
+		return -ENOMEM;
+
+	low_limit = info->low_limit;
+	if (low_limit < mmap_min_addr)
+		low_limit = mmap_min_addr;
+	high_limit = info->high_limit;
+retry:
+	if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length))
+		return -ENOMEM;
+
+	/*
+	 * Adjust for the gap first so it doesn't interfere with the
+	 * later alignment. The first step is the minimum needed to
+	 * fulill the start gap, the next steps is the minimum to align
+	 * that. It is the minimum needed to fulill both.
+	 */
+	gap = vma_iter_addr(&vmi) + info->start_gap;
+	gap += (info->align_offset - gap) & info->align_mask;
+	tmp = vma_next(&vmi);
+	if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
+		if (vm_start_gap(tmp) < gap + length - 1) {
+			low_limit = tmp->vm_end;
+			vma_iter_reset(&vmi);
+			goto retry;
+		}
+	} else {
+		tmp = vma_prev(&vmi);
+		if (tmp && vm_end_gap(tmp) > gap) {
+			low_limit = vm_end_gap(tmp);
+			vma_iter_reset(&vmi);
+			goto retry;
+		}
+	}
+
+	return gap;
+}
+
+/**
+ * unmapped_area_topdown() - Find an area between the low_limit and the
+ * high_limit with the correct alignment and offset at the highest available
+ * address, all from @info. Note: current->mm is used for the search.
+ *
+ * @info: The unmapped area information including the range [low_limit -
+ * high_limit), the alignment offset and mask.
+ *
+ * Return: A memory address or -ENOMEM.
+ */
+unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
+{
+	unsigned long length, gap, gap_end;
+	unsigned long low_limit, high_limit;
+	struct vm_area_struct *tmp;
+	VMA_ITERATOR(vmi, current->mm, 0);
+
+	/* Adjust search length to account for worst case alignment overhead */
+	length = info->length + info->align_mask + info->start_gap;
+	if (length < info->length)
+		return -ENOMEM;
+
+	low_limit = info->low_limit;
+	if (low_limit < mmap_min_addr)
+		low_limit = mmap_min_addr;
+	high_limit = info->high_limit;
+retry:
+	if (vma_iter_area_highest(&vmi, low_limit, high_limit, length))
+		return -ENOMEM;
+
+	gap = vma_iter_end(&vmi) - info->length;
+	gap -= (gap - info->align_offset) & info->align_mask;
+	gap_end = vma_iter_end(&vmi);
+	tmp = vma_next(&vmi);
+	if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */
+		if (vm_start_gap(tmp) < gap_end) {
+			high_limit = vm_start_gap(tmp);
+			vma_iter_reset(&vmi);
+			goto retry;
+		}
+	} else {
+		tmp = vma_prev(&vmi);
+		if (tmp && vm_end_gap(tmp) > gap) {
+			high_limit = tmp->vm_start;
+			vma_iter_reset(&vmi);
+			goto retry;
+		}
+	}
+
+	return gap;
+}
+
+/*
+ * Verify that the stack growth is acceptable and
+ * update accounting. This is shared with both the
+ * grow-up and grow-down cases.
+ */
+static int acct_stack_growth(struct vm_area_struct *vma,
+			     unsigned long size, unsigned long grow)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long new_start;
+
+	/* address space limit tests */
+	if (!may_expand_vm(mm, vma->vm_flags, grow))
+		return -ENOMEM;
+
+	/* Stack limit test */
+	if (size > rlimit(RLIMIT_STACK))
+		return -ENOMEM;
+
+	/* mlock limit tests */
+	if (!mlock_future_ok(mm, vma->vm_flags, grow << PAGE_SHIFT))
+		return -ENOMEM;
+
+	/* Check to ensure the stack will not grow into a hugetlb-only region */
+	new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
+			vma->vm_end - size;
+	if (is_hugepage_only_range(vma->vm_mm, new_start, size))
+		return -EFAULT;
+
+	/*
+	 * Overcommit..  This must be the final test, as it will
+	 * update security statistics.
+	 */
+	if (security_vm_enough_memory_mm(mm, grow))
+		return -ENOMEM;
+
+	return 0;
+}
+
+#if defined(CONFIG_STACK_GROWSUP)
+/*
+ * PA-RISC uses this for its stack.
+ * vma is the last one with address > vma->vm_end.  Have to extend vma.
+ */
+int expand_upwards(struct vm_area_struct *vma, unsigned long address)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *next;
+	unsigned long gap_addr;
+	int error = 0;
+	VMA_ITERATOR(vmi, mm, vma->vm_start);
+
+	if (!(vma->vm_flags & VM_GROWSUP))
+		return -EFAULT;
+
+	mmap_assert_write_locked(mm);
+
+	/* Guard against exceeding limits of the address space. */
+	address &= PAGE_MASK;
+	if (address >= (TASK_SIZE & PAGE_MASK))
+		return -ENOMEM;
+	address += PAGE_SIZE;
+
+	/* Enforce stack_guard_gap */
+	gap_addr = address + stack_guard_gap;
+
+	/* Guard against overflow */
+	if (gap_addr < address || gap_addr > TASK_SIZE)
+		gap_addr = TASK_SIZE;
+
+	next = find_vma_intersection(mm, vma->vm_end, gap_addr);
+	if (next && vma_is_accessible(next)) {
+		if (!(next->vm_flags & VM_GROWSUP))
+			return -ENOMEM;
+		/* Check that both stack segments have the same anon_vma? */
+	}
+
+	if (next)
+		vma_iter_prev_range_limit(&vmi, address);
+
+	vma_iter_config(&vmi, vma->vm_start, address);
+	if (vma_iter_prealloc(&vmi, vma))
+		return -ENOMEM;
+
+	/* We must make sure the anon_vma is allocated. */
+	if (unlikely(anon_vma_prepare(vma))) {
+		vma_iter_free(&vmi);
+		return -ENOMEM;
+	}
+
+	/* Lock the VMA before expanding to prevent concurrent page faults */
+	vma_start_write(vma);
+	/* We update the anon VMA tree. */
+	anon_vma_lock_write(vma->anon_vma);
+
+	/* Somebody else might have raced and expanded it already */
+	if (address > vma->vm_end) {
+		unsigned long size, grow;
+
+		size = address - vma->vm_start;
+		grow = (address - vma->vm_end) >> PAGE_SHIFT;
+
+		error = -ENOMEM;
+		if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) {
+			error = acct_stack_growth(vma, size, grow);
+			if (!error) {
+				if (vma->vm_flags & VM_LOCKED)
+					mm->locked_vm += grow;
+				vm_stat_account(mm, vma->vm_flags, grow);
+				anon_vma_interval_tree_pre_update_vma(vma);
+				vma->vm_end = address;
+				/* Overwrite old entry in mtree. */
+				vma_iter_store(&vmi, vma);
+				anon_vma_interval_tree_post_update_vma(vma);
+
+				perf_event_mmap(vma);
+			}
+		}
+	}
+	anon_vma_unlock_write(vma->anon_vma);
+	vma_iter_free(&vmi);
+	validate_mm(mm);
+	return error;
+}
+#endif /* CONFIG_STACK_GROWSUP */
+
+/*
+ * vma is the first one with address < vma->vm_start.  Have to extend vma.
+ * mmap_lock held for writing.
+ */
+int expand_downwards(struct vm_area_struct *vma, unsigned long address)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct vm_area_struct *prev;
+	int error = 0;
+	VMA_ITERATOR(vmi, mm, vma->vm_start);
+
+	if (!(vma->vm_flags & VM_GROWSDOWN))
+		return -EFAULT;
+
+	mmap_assert_write_locked(mm);
+
+	address &= PAGE_MASK;
+	if (address < mmap_min_addr || address < FIRST_USER_ADDRESS)
+		return -EPERM;
+
+	/* Enforce stack_guard_gap */
+	prev = vma_prev(&vmi);
+	/* Check that both stack segments have the same anon_vma? */
+	if (prev) {
+		if (!(prev->vm_flags & VM_GROWSDOWN) &&
+		    vma_is_accessible(prev) &&
+		    (address - prev->vm_end < stack_guard_gap))
+			return -ENOMEM;
+	}
+
+	if (prev)
+		vma_iter_next_range_limit(&vmi, vma->vm_start);
+
+	vma_iter_config(&vmi, address, vma->vm_end);
+	if (vma_iter_prealloc(&vmi, vma))
+		return -ENOMEM;
+
+	/* We must make sure the anon_vma is allocated. */
+	if (unlikely(anon_vma_prepare(vma))) {
+		vma_iter_free(&vmi);
+		return -ENOMEM;
+	}
+
+	/* Lock the VMA before expanding to prevent concurrent page faults */
+	vma_start_write(vma);
+	/* We update the anon VMA tree. */
+	anon_vma_lock_write(vma->anon_vma);
+
+	/* Somebody else might have raced and expanded it already */
+	if (address < vma->vm_start) {
+		unsigned long size, grow;
+
+		size = vma->vm_end - address;
+		grow = (vma->vm_start - address) >> PAGE_SHIFT;
+
+		error = -ENOMEM;
+		if (grow <= vma->vm_pgoff) {
+			error = acct_stack_growth(vma, size, grow);
+			if (!error) {
+				if (vma->vm_flags & VM_LOCKED)
+					mm->locked_vm += grow;
+				vm_stat_account(mm, vma->vm_flags, grow);
+				anon_vma_interval_tree_pre_update_vma(vma);
+				vma->vm_start = address;
+				vma->vm_pgoff -= grow;
+				/* Overwrite old entry in mtree. */
+				vma_iter_store(&vmi, vma);
+				anon_vma_interval_tree_post_update_vma(vma);
+
+				perf_event_mmap(vma);
+			}
+		}
+	}
+	anon_vma_unlock_write(vma->anon_vma);
+	vma_iter_free(&vmi);
+	validate_mm(mm);
+	return error;
+}
+
+int __vm_munmap(unsigned long start, size_t len, bool unlock)
+{
+	int ret;
+	struct mm_struct *mm = current->mm;
+	LIST_HEAD(uf);
+	VMA_ITERATOR(vmi, mm, start);
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	ret = do_vmi_munmap(&vmi, mm, start, len, &uf, unlock);
+	if (ret || !unlock)
+		mmap_write_unlock(mm);
+
+	userfaultfd_unmap_complete(mm, &uf);
+	return ret;
+}
diff --git a/mm/vma.h b/mm/vma.h
index 388d34748674..a2e8710b8c47 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -139,15 +139,10 @@ void validate_mm(struct mm_struct *mm);
 #define validate_mm(mm) do { } while (0)
 #endif
 
-/* Required for expand_downwards(). */
-void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma);
-
-/* Required for expand_downwards(). */
-void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma);
-
-int vma_expand(struct vma_merge_struct *vmg);
-int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
-	       unsigned long start, unsigned long end, pgoff_t pgoff);
+__must_check int vma_expand(struct vma_merge_struct *vmg);
+__must_check int vma_shrink(struct vma_iterator *vmi,
+		struct vm_area_struct *vma,
+		unsigned long start, unsigned long end, pgoff_t pgoff);
 
 static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 			struct vm_area_struct *vma, gfp_t gfp)
@@ -180,13 +175,14 @@ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct vm_area_struct *next);
 
 /* We are about to modify the VMA's flags. */
-struct vm_area_struct *vma_modify_flags(struct vma_iterator *vmi,
+__must_check struct vm_area_struct
+*vma_modify_flags(struct vma_iterator *vmi,
 		struct vm_area_struct *prev, struct vm_area_struct *vma,
 		unsigned long start, unsigned long end,
 		unsigned long new_flags);
 
 /* We are about to modify the VMA's flags and/or anon_name. */
-struct vm_area_struct
+__must_check struct vm_area_struct
 *vma_modify_flags_name(struct vma_iterator *vmi,
 		       struct vm_area_struct *prev,
 		       struct vm_area_struct *vma,
@@ -196,7 +192,7 @@ struct vm_area_struct
 		       struct anon_vma_name *new_name);
 
 /* We are about to modify the VMA's memory policy. */
-struct vm_area_struct
+__must_check struct vm_area_struct
 *vma_modify_policy(struct vma_iterator *vmi,
 		   struct vm_area_struct *prev,
 		   struct vm_area_struct *vma,
@@ -204,7 +200,7 @@ struct vm_area_struct
 		   struct mempolicy *new_pol);
 
 /* We are about to modify the VMA's flags and/or uffd context. */
-struct vm_area_struct
+__must_check struct vm_area_struct
 *vma_modify_flags_uffd(struct vma_iterator *vmi,
 		       struct vm_area_struct *prev,
 		       struct vm_area_struct *vma,
@@ -212,11 +208,13 @@ struct vm_area_struct
 		       unsigned long new_flags,
 		       struct vm_userfaultfd_ctx new_ctx);
 
-struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg);
+__must_check struct vm_area_struct
+*vma_merge_new_range(struct vma_merge_struct *vmg);
 
-struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi,
-					struct vm_area_struct *vma,
-					unsigned long delta);
+__must_check struct vm_area_struct
+*vma_merge_extend(struct vma_iterator *vmi,
+		  struct vm_area_struct *vma,
+		  unsigned long delta);
 
 void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb);
 
@@ -243,10 +241,16 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
 int mm_take_all_locks(struct mm_struct *mm);
 void mm_drop_all_locks(struct mm_struct *mm);
 
-unsigned long __mmap_region(struct file *file, unsigned long addr,
+unsigned long mmap_region(struct file *file, unsigned long addr,
 		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
 		struct list_head *uf);
 
+int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
+		 unsigned long addr, unsigned long request, unsigned long flags);
+
+unsigned long unmapped_area(struct vm_unmapped_area_info *info);
+unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info);
+
 static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma)
 {
 	/*
@@ -472,4 +476,12 @@ static inline bool can_modify_vma_madv(struct vm_area_struct *vma, int behavior)
 
 #endif
 
+#if defined(CONFIG_STACK_GROWSUP)
+int expand_upwards(struct vm_area_struct *vma, unsigned long address);
+#endif
+
+int expand_downwards(struct vm_area_struct *vma, unsigned long address);
+
+int __vm_munmap(unsigned long start, size_t len, bool unlock);
+
 #endif	/* __MM_VMA_H */
diff --git a/mm/vma_internal.h b/mm/vma_internal.h
index fc5f172a36bd..2f05735ff190 100644
--- a/mm/vma_internal.h
+++ b/mm/vma_internal.h
@@ -35,6 +35,7 @@
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
+#include <linux/personality.h>
 #include <linux/pfn.h>
 #include <linux/rcupdate.h>
 #include <linux/rmap.h>
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5c88d0e90c20..a6e7acebe9ad 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3562,11 +3562,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 * but mempolicy wants to alloc memory by interleaving.
 			 */
 			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
-				nr = alloc_pages_bulk_array_mempolicy_noprof(gfp,
+				nr = alloc_pages_bulk_mempolicy_noprof(gfp,
 							nr_pages_request,
 							pages + nr_allocated);
 			else
-				nr = alloc_pages_bulk_array_node_noprof(gfp, nid,
+				nr = alloc_pages_bulk_node_noprof(gfp, nid,
 							nr_pages_request,
 							pages + nr_allocated);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 867a2554434a..c767d71c43d7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -862,6 +862,31 @@ enum folio_references {
 	FOLIOREF_ACTIVATE,
 };
 
+#ifdef CONFIG_LRU_GEN
+/*
+ * Only used on a mapped folio in the eviction (rmap walk) path, where promotion
+ * needs to be done by taking the folio off the LRU list and then adding it back
+ * with PG_active set. In contrast, the aging (page table walk) path uses
+ * folio_update_gen().
+ */
+static bool lru_gen_set_refs(struct folio *folio)
+{
+	/* see the comment on LRU_REFS_FLAGS */
+	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
+		return false;
+	}
+
+	set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_workingset));
+	return true;
+}
+#else
+static bool lru_gen_set_refs(struct folio *folio)
+{
+	return false;
+}
+#endif /* CONFIG_LRU_GEN */
+
 static enum folio_references folio_check_references(struct folio *folio,
 						  struct scan_control *sc)
 {
@@ -870,7 +895,6 @@ static enum folio_references folio_check_references(struct folio *folio,
 
 	referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
 					   &vm_flags);
-	referenced_folio = folio_test_clear_referenced(folio);
 
 	/*
 	 * The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
@@ -888,6 +912,15 @@ static enum folio_references folio_check_references(struct folio *folio,
 	if (referenced_ptes == -1)
 		return FOLIOREF_KEEP;
 
+	if (lru_gen_enabled()) {
+		if (!referenced_ptes)
+			return FOLIOREF_RECLAIM;
+
+		return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP;
+	}
+
+	referenced_folio = folio_test_clear_referenced(folio);
+
 	if (referenced_ptes) {
 		/*
 		 * All mapped folios start out with page table
@@ -1053,7 +1086,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 	struct folio_batch free_folios;
 	LIST_HEAD(ret_folios);
 	LIST_HEAD(demote_folios);
-	unsigned int nr_reclaimed = 0;
+	unsigned int nr_reclaimed = 0, nr_demoted = 0;
 	unsigned int pgactivate = 0;
 	bool do_demote_pass;
 	struct swap_iocb *plug = NULL;
@@ -1092,11 +1125,6 @@ retry:
 		if (!sc->may_unmap && folio_mapped(folio))
 			goto keep_locked;
 
-		/* folio_update_gen() tried to promote this page? */
-		if (lru_gen_enabled() && !ignore_references &&
-		    folio_mapped(folio) && folio_test_referenced(folio))
-			goto keep_locked;
-
 		/*
 		 * The number of dirty pages determines if a node is marked
 		 * reclaim_congested. kswapd will stall and start writing
@@ -1522,8 +1550,9 @@ keep:
 	/* 'folio_list' is always empty here */
 
 	/* Migrate folios selected for demotion */
-	stat->nr_demoted = demote_folio_list(&demote_folios, pgdat);
-	nr_reclaimed += stat->nr_demoted;
+	nr_demoted = demote_folio_list(&demote_folios, pgdat);
+	nr_reclaimed += nr_demoted;
+	stat->nr_demoted += nr_demoted;
 	/* Folios that could not be demoted are still in @demote_folios */
 	if (!list_empty(&demote_folios)) {
 		/* Folios which weren't demoted go back on @folio_list */
@@ -1664,6 +1693,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long skipped = 0;
 	unsigned long scan, total_scan, nr_pages;
+	unsigned long max_nr_skipped = 0;
 	LIST_HEAD(folios_skipped);
 
 	total_scan = 0;
@@ -1678,9 +1708,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 		nr_pages = folio_nr_pages(folio);
 		total_scan += nr_pages;
 
-		if (folio_zonenum(folio) > sc->reclaim_idx) {
+		/* Using max_nr_skipped to prevent hard LOCKUP*/
+		if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED &&
+		    (folio_zonenum(folio) > sc->reclaim_idx)) {
 			nr_skipped[folio_zonenum(folio)] += nr_pages;
 			move_to = &folios_skipped;
+			max_nr_skipped++;
 			goto move;
 		}
 
@@ -2619,11 +2652,17 @@ static bool should_clear_pmd_young(void)
 		READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]),	\
 	}
 
+#define evictable_min_seq(min_seq, swappiness)				\
+	min((min_seq)[!(swappiness)], (min_seq)[(swappiness) <= MAX_SWAPPINESS])
+
 #define for_each_gen_type_zone(gen, type, zone)				\
 	for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++)			\
 		for ((type) = 0; (type) < ANON_AND_FILE; (type)++)	\
 			for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
 
+#define for_each_evictable_type(type, swappiness)			\
+	for ((type) = !(swappiness); (type) <= ((swappiness) <= MAX_SWAPPINESS); (type)++)
+
 #define get_memcg_gen(seq)	((seq) % MEMCG_NR_GENS)
 #define get_memcg_bin(bin)	((bin) % MEMCG_NR_BINS)
 
@@ -2669,10 +2708,16 @@ static int get_nr_gens(struct lruvec *lruvec, int type)
 
 static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
 {
-	/* see the comment on lru_gen_folio */
-	return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS &&
-	       get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) &&
-	       get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
+	int type;
+
+	for (type = 0; type < ANON_AND_FILE; type++) {
+		int n = get_nr_gens(lruvec, type);
+
+		if (n < MIN_NR_GENS || n > MAX_NR_GENS)
+			return false;
+	}
+
+	return true;
 }
 
 /******************************************************************************
@@ -3073,16 +3118,20 @@ struct ctrl_pos {
 static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
 			  struct ctrl_pos *pos)
 {
+	int i;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
-	pos->refaulted = lrugen->avg_refaulted[type][tier] +
-			 atomic_long_read(&lrugen->refaulted[hist][type][tier]);
-	pos->total = lrugen->avg_total[type][tier] +
-		     atomic_long_read(&lrugen->evicted[hist][type][tier]);
-	if (tier)
-		pos->total += lrugen->protected[hist][type][tier - 1];
 	pos->gain = gain;
+	pos->refaulted = pos->total = 0;
+
+	for (i = tier % MAX_NR_TIERS; i <= min(tier, MAX_NR_TIERS - 1); i++) {
+		pos->refaulted += lrugen->avg_refaulted[type][i] +
+				  atomic_long_read(&lrugen->refaulted[hist][type][i]);
+		pos->total += lrugen->avg_total[type][i] +
+			      lrugen->protected[hist][type][i] +
+			      atomic_long_read(&lrugen->evicted[hist][type][i]);
+	}
 }
 
 static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
@@ -3108,17 +3157,15 @@ static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
 			WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2);
 
 			sum = lrugen->avg_total[type][tier] +
+			      lrugen->protected[hist][type][tier] +
 			      atomic_long_read(&lrugen->evicted[hist][type][tier]);
-			if (tier)
-				sum += lrugen->protected[hist][type][tier - 1];
 			WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2);
 		}
 
 		if (clear) {
 			atomic_long_set(&lrugen->refaulted[hist][type][tier], 0);
 			atomic_long_set(&lrugen->evicted[hist][type][tier], 0);
-			if (tier)
-				WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0);
+			WRITE_ONCE(lrugen->protected[hist][type][tier], 0);
 		}
 	}
 }
@@ -3145,16 +3192,19 @@ static int folio_update_gen(struct folio *folio, int gen)
 
 	VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
 
+	/* see the comment on LRU_REFS_FLAGS */
+	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
+		return -1;
+	}
+
 	do {
 		/* lru_gen_del_folio() has isolated this page? */
-		if (!(old_flags & LRU_GEN_MASK)) {
-			/* for shrink_folio_list() */
-			new_flags = old_flags | BIT(PG_referenced);
-			continue;
-		}
+		if (!(old_flags & LRU_GEN_MASK))
+			return -1;
 
-		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
-		new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
+		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS);
+		new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset);
 	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
 
 	return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
@@ -3178,7 +3228,7 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai
 
 		new_gen = (old_gen + 1) % MAX_NR_GENS;
 
-		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
+		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS);
 		new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
 		/* for folio_end_writeback() */
 		if (reclaiming)
@@ -3253,7 +3303,7 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal
 		return true;
 
 	if (vma_is_anonymous(vma))
-		return !walk->can_swap;
+		return !walk->swappiness;
 
 	if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping))
 		return true;
@@ -3263,7 +3313,10 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal
 		return true;
 
 	if (shmem_mapping(mapping))
-		return !walk->can_swap;
+		return !walk->swappiness;
+
+	if (walk->swappiness > MAX_SWAPPINESS)
+		return true;
 
 	/* to exclude special mappings like dax, etc. */
 	return !mapping->a_ops->read_folio;
@@ -3351,19 +3404,17 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 }
 
 static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
-				   struct pglist_data *pgdat, bool can_swap)
+				   struct pglist_data *pgdat)
 {
-	struct folio *folio;
+	struct folio *folio = pfn_folio(pfn);
 
-	folio = pfn_folio(pfn);
-	if (folio_nid(folio) != pgdat->node_id)
+	if (folio_lru_gen(folio) < 0)
 		return NULL;
 
-	if (folio_memcg(folio) != memcg)
+	if (folio_nid(folio) != pgdat->node_id)
 		return NULL;
 
-	/* file VMAs can contain anon pages from COW */
-	if (!folio_is_file_lru(folio) && !can_swap)
+	if (folio_memcg(folio) != memcg)
 		return NULL;
 
 	return folio;
@@ -3377,29 +3428,55 @@ static bool suitable_to_scan(int total, int young)
 	return young * n >= total;
 }
 
+static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio,
+			      int new_gen, bool dirty)
+{
+	int old_gen;
+
+	if (!folio)
+		return;
+
+	if (dirty && !folio_test_dirty(folio) &&
+	    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
+	      !folio_test_swapcache(folio)))
+		folio_mark_dirty(folio);
+
+	if (walk) {
+		old_gen = folio_update_gen(folio, new_gen);
+		if (old_gen >= 0 && old_gen != new_gen)
+			update_batch_size(walk, folio, old_gen, new_gen);
+	} else if (lru_gen_set_refs(folio)) {
+		old_gen = folio_lru_gen(folio);
+		if (old_gen >= 0 && old_gen != new_gen)
+			folio_activate(folio);
+	}
+}
+
 static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
 			   struct mm_walk *args)
 {
 	int i;
+	bool dirty;
 	pte_t *pte;
 	spinlock_t *ptl;
 	unsigned long addr;
 	int total = 0;
 	int young = 0;
+	struct folio *last = NULL;
 	struct lru_gen_mm_walk *walk = args->private;
 	struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
 	DEFINE_MAX_SEQ(walk->lruvec);
-	int old_gen, new_gen = lru_gen_from_seq(max_seq);
+	int gen = lru_gen_from_seq(max_seq);
 	pmd_t pmdval;
 
-	pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval,
-				       &ptl);
+	pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl);
 	if (!pte)
 		return false;
+
 	if (!spin_trylock(ptl)) {
 		pte_unmap(pte);
-		return false;
+		return true;
 	}
 
 	if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
@@ -3421,26 +3498,30 @@ restart:
 		if (pfn == -1)
 			continue;
 
-		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
+		folio = get_pfn_folio(pfn, memcg, pgdat);
 		if (!folio)
 			continue;
 
 		if (!ptep_clear_young_notify(args->vma, addr, pte + i))
 			continue;
 
-		young++;
-		walk->mm_stats[MM_LEAF_YOUNG]++;
+		if (last != folio) {
+			walk_update_folio(walk, last, gen, dirty);
 
-		if (pte_dirty(ptent) && !folio_test_dirty(folio) &&
-		    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-		      !folio_test_swapcache(folio)))
-			folio_mark_dirty(folio);
+			last = folio;
+			dirty = false;
+		}
 
-		old_gen = folio_update_gen(folio, new_gen);
-		if (old_gen >= 0 && old_gen != new_gen)
-			update_batch_size(walk, folio, old_gen, new_gen);
+		if (pte_dirty(ptent))
+			dirty = true;
+
+		young++;
+		walk->mm_stats[MM_LEAF_YOUNG]++;
 	}
 
+	walk_update_folio(walk, last, gen, dirty);
+	last = NULL;
+
 	if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end))
 		goto restart;
 
@@ -3454,13 +3535,15 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 				  struct mm_walk *args, unsigned long *bitmap, unsigned long *first)
 {
 	int i;
+	bool dirty;
 	pmd_t *pmd;
 	spinlock_t *ptl;
+	struct folio *last = NULL;
 	struct lru_gen_mm_walk *walk = args->private;
 	struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
 	DEFINE_MAX_SEQ(walk->lruvec);
-	int old_gen, new_gen = lru_gen_from_seq(max_seq);
+	int gen = lru_gen_from_seq(max_seq);
 
 	VM_WARN_ON_ONCE(pud_leaf(*pud));
 
@@ -3506,27 +3589,30 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		if (pfn == -1)
 			goto next;
 
-		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
+		folio = get_pfn_folio(pfn, memcg, pgdat);
 		if (!folio)
 			goto next;
 
 		if (!pmdp_clear_young_notify(vma, addr, pmd + i))
 			goto next;
 
-		walk->mm_stats[MM_LEAF_YOUNG]++;
+		if (last != folio) {
+			walk_update_folio(walk, last, gen, dirty);
+
+			last = folio;
+			dirty = false;
+		}
 
-		if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) &&
-		    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-		      !folio_test_swapcache(folio)))
-			folio_mark_dirty(folio);
+		if (pmd_dirty(pmd[i]))
+			dirty = true;
 
-		old_gen = folio_update_gen(folio, new_gen);
-		if (old_gen >= 0 && old_gen != new_gen)
-			update_batch_size(walk, folio, old_gen, new_gen);
+		walk->mm_stats[MM_LEAF_YOUNG]++;
 next:
 		i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1;
 	} while (i <= MIN_LRU_BATCH);
 
+	walk_update_folio(walk, last, gen, dirty);
+
 	arch_leave_lazy_mmu_mode();
 	spin_unlock(ptl);
 done:
@@ -3718,22 +3804,25 @@ static void clear_mm_walk(void)
 		kfree(walk);
 }
 
-static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
+static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness)
 {
 	int zone;
 	int remaining = MAX_LRU_BATCH;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 	int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
 
-	if (type == LRU_GEN_ANON && !can_swap)
+	if (type ? swappiness > MAX_SWAPPINESS : !swappiness)
 		goto done;
 
-	/* prevent cold/hot inversion if force_scan is true */
+	/* prevent cold/hot inversion if the type is evictable */
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		struct list_head *head = &lrugen->folios[old_gen][type][zone];
 
 		while (!list_empty(head)) {
 			struct folio *folio = lru_to_folio(head);
+			int refs = folio_lru_refs(folio);
+			bool workingset = folio_test_workingset(folio);
 
 			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
 			VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
@@ -3743,6 +3832,15 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
 			new_gen = folio_inc_gen(lruvec, folio, false);
 			list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]);
 
+			/* don't count the workingset being lazily promoted */
+			if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) {
+				int tier = lru_tier_from_refs(refs, workingset);
+				int delta = folio_nr_pages(folio);
+
+				WRITE_ONCE(lrugen->protected[hist][type][tier],
+					   lrugen->protected[hist][type][tier] + delta);
+			}
+
 			if (!--remaining)
 				return false;
 		}
@@ -3754,7 +3852,7 @@ done:
 	return true;
 }
 
-static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness)
 {
 	int gen, type, zone;
 	bool success = false;
@@ -3764,7 +3862,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
 	VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
 
 	/* find the oldest populated generation */
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+	for_each_evictable_type(type, swappiness) {
 		while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) {
 			gen = lru_gen_from_seq(min_seq[type]);
 
@@ -3780,13 +3878,17 @@ next:
 	}
 
 	/* see the comment on lru_gen_folio */
-	if (can_swap) {
-		min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]);
-		min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]);
+	if (swappiness && swappiness <= MAX_SWAPPINESS) {
+		unsigned long seq = lrugen->max_seq - MIN_NR_GENS;
+
+		if (min_seq[LRU_GEN_ANON] > seq && min_seq[LRU_GEN_FILE] < seq)
+			min_seq[LRU_GEN_ANON] = seq;
+		else if (min_seq[LRU_GEN_FILE] > seq && min_seq[LRU_GEN_ANON] < seq)
+			min_seq[LRU_GEN_FILE] = seq;
 	}
 
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
-		if (min_seq[type] == lrugen->min_seq[type])
+	for_each_evictable_type(type, swappiness) {
+		if (min_seq[type] <= lrugen->min_seq[type])
 			continue;
 
 		reset_ctrl_pos(lruvec, type, true);
@@ -3797,8 +3899,7 @@ next:
 	return success;
 }
 
-static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq,
-			bool can_swap, bool force_scan)
+static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness)
 {
 	bool success;
 	int prev, next;
@@ -3816,13 +3917,11 @@ restart:
 	if (!success)
 		goto unlock;
 
-	for (type = ANON_AND_FILE - 1; type >= 0; type--) {
+	for (type = 0; type < ANON_AND_FILE; type++) {
 		if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
 			continue;
 
-		VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap));
-
-		if (inc_min_seq(lruvec, type, can_swap))
+		if (inc_min_seq(lruvec, type, swappiness))
 			continue;
 
 		spin_unlock_irq(&lruvec->lru_lock);
@@ -3866,7 +3965,7 @@ unlock:
 }
 
 static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
-			       bool can_swap, bool force_scan)
+			       int swappiness, bool force_scan)
 {
 	bool success;
 	struct lru_gen_mm_walk *walk;
@@ -3877,7 +3976,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 	VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq));
 
 	if (!mm_state)
-		return inc_max_seq(lruvec, seq, can_swap, force_scan);
+		return inc_max_seq(lruvec, seq, swappiness);
 
 	/* see the comment in iterate_mm_list() */
 	if (seq <= READ_ONCE(mm_state->seq))
@@ -3902,7 +4001,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 
 	walk->lruvec = lruvec;
 	walk->seq = seq;
-	walk->can_swap = can_swap;
+	walk->swappiness = swappiness;
 	walk->force_scan = force_scan;
 
 	do {
@@ -3912,7 +4011,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 	} while (mm);
 done:
 	if (success) {
-		success = inc_max_seq(lruvec, seq, can_swap, force_scan);
+		success = inc_max_seq(lruvec, seq, swappiness);
 		WARN_ON_ONCE(!success);
 	}
 
@@ -3953,13 +4052,13 @@ static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc)
 {
 	int gen, type, zone;
 	unsigned long total = 0;
-	bool can_swap = get_swappiness(lruvec, sc);
+	int swappiness = get_swappiness(lruvec, sc);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+	for_each_evictable_type(type, swappiness) {
 		unsigned long seq;
 
 		for (seq = min_seq[type]; seq <= max_seq; seq++) {
@@ -3979,6 +4078,7 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc
 {
 	int gen;
 	unsigned long birth;
+	int swappiness = get_swappiness(lruvec, sc);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
@@ -3988,8 +4088,7 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc
 	if (!lruvec_is_sizable(lruvec, sc))
 		return false;
 
-	/* see the comment on lru_gen_folio */
-	gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
+	gen = lru_gen_from_seq(evictable_min_seq(min_seq, swappiness));
 	birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
 
 	return time_is_before_jiffies(birth + min_ttl);
@@ -4048,21 +4147,22 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 	int i;
+	bool dirty;
 	unsigned long start;
 	unsigned long end;
 	struct lru_gen_mm_walk *walk;
+	struct folio *last = NULL;
 	int young = 1;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
 	struct vm_area_struct *vma = pvmw->vma;
 	struct folio *folio = pfn_folio(pvmw->pfn);
-	bool can_swap = !folio_is_file_lru(folio);
 	struct mem_cgroup *memcg = folio_memcg(folio);
 	struct pglist_data *pgdat = folio_pgdat(folio);
 	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
-	int old_gen, new_gen = lru_gen_from_seq(max_seq);
+	int gen = lru_gen_from_seq(max_seq);
 
 	lockdep_assert_held(pvmw->ptl);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
@@ -4109,37 +4209,28 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		if (pfn == -1)
 			continue;
 
-		folio = get_pfn_folio(pfn, memcg, pgdat, can_swap);
+		folio = get_pfn_folio(pfn, memcg, pgdat);
 		if (!folio)
 			continue;
 
 		if (!ptep_clear_young_notify(vma, addr, pte + i))
 			continue;
 
-		young++;
-
-		if (pte_dirty(ptent) && !folio_test_dirty(folio) &&
-		    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-		      !folio_test_swapcache(folio)))
-			folio_mark_dirty(folio);
+		if (last != folio) {
+			walk_update_folio(walk, last, gen, dirty);
 
-		if (walk) {
-			old_gen = folio_update_gen(folio, new_gen);
-			if (old_gen >= 0 && old_gen != new_gen)
-				update_batch_size(walk, folio, old_gen, new_gen);
-
-			continue;
+			last = folio;
+			dirty = false;
 		}
 
-		old_gen = folio_lru_gen(folio);
-		if (old_gen < 0)
-			folio_set_referenced(folio);
-		else if (old_gen != new_gen) {
-			folio_clear_lru_refs(folio);
-			folio_activate(folio);
-		}
+		if (pte_dirty(ptent))
+			dirty = true;
+
+		young++;
 	}
 
+	walk_update_folio(walk, last, gen, dirty);
+
 	arch_leave_lazy_mmu_mode();
 
 	/* feedback from rmap walkers to page table walkers */
@@ -4297,7 +4388,8 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	int zone = folio_zonenum(folio);
 	int delta = folio_nr_pages(folio);
 	int refs = folio_lru_refs(folio);
-	int tier = lru_tier_from_refs(refs);
+	bool workingset = folio_test_workingset(folio);
+	int tier = lru_tier_from_refs(refs, workingset);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 
 	VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio);
@@ -4319,14 +4411,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* protected */
-	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
-		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
-
+	if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) {
 		gen = folio_inc_gen(lruvec, folio, false);
-		list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
+		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
+
+		/* don't count the workingset being lazily promoted */
+		if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) {
+			int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
-		WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
-			   lrugen->protected[hist][type][tier - 1] + delta);
+			WRITE_ONCE(lrugen->protected[hist][type][tier],
+				   lrugen->protected[hist][type][tier] + delta);
+		}
 		return true;
 	}
 
@@ -4346,8 +4441,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* waiting for writeback */
-	if (folio_test_locked(folio) || writeback ||
-	    (type == LRU_GEN_FILE && dirty)) {
+	if (writeback || (type == LRU_GEN_FILE && dirty)) {
 		gen = folio_inc_gen(lruvec, folio, true);
 		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
 		return true;
@@ -4376,13 +4470,12 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca
 		return false;
 	}
 
-	/* see the comment on MAX_NR_TIERS */
+	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio))
-		folio_clear_lru_refs(folio);
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, 0);
 
 	/* for shrink_folio_list() */
 	folio_clear_reclaim(folio);
-	folio_clear_referenced(folio);
 
 	success = lru_gen_del_folio(lruvec, folio, true);
 	VM_WARN_ON_ONCE_FOLIO(!success, folio);
@@ -4478,13 +4571,13 @@ static int get_tier_idx(struct lruvec *lruvec, int type)
 	struct ctrl_pos sp, pv;
 
 	/*
-	 * To leave a margin for fluctuations, use a larger gain factor (1:2).
+	 * To leave a margin for fluctuations, use a larger gain factor (2:3).
 	 * This value is chosen because any other tier would have at least twice
 	 * as many refaults as the first tier.
 	 */
-	read_ctrl_pos(lruvec, type, 0, 1, &sp);
+	read_ctrl_pos(lruvec, type, 0, 2, &sp);
 	for (tier = 1; tier < MAX_NR_TIERS; tier++) {
-		read_ctrl_pos(lruvec, type, tier, 2, &pv);
+		read_ctrl_pos(lruvec, type, tier, 3, &pv);
 		if (!positive_ctrl_err(&sp, &pv))
 			break;
 	}
@@ -4492,79 +4585,45 @@ static int get_tier_idx(struct lruvec *lruvec, int type)
 	return tier - 1;
 }
 
-static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx)
+static int get_type_to_scan(struct lruvec *lruvec, int swappiness)
 {
-	int type, tier;
 	struct ctrl_pos sp, pv;
-	int gain[ANON_AND_FILE] = { swappiness, MAX_SWAPPINESS - swappiness };
 
+	if (swappiness <= MIN_SWAPPINESS + 1)
+		return LRU_GEN_FILE;
+
+	if (swappiness >= MAX_SWAPPINESS)
+		return LRU_GEN_ANON;
 	/*
-	 * Compare the first tier of anon with that of file to determine which
-	 * type to scan. Also need to compare other tiers of the selected type
-	 * with the first tier of the other type to determine the last tier (of
-	 * the selected type) to evict.
+	 * Compare the sum of all tiers of anon with that of file to determine
+	 * which type to scan.
 	 */
-	read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp);
-	read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv);
-	type = positive_ctrl_err(&sp, &pv);
-
-	read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp);
-	for (tier = 1; tier < MAX_NR_TIERS; tier++) {
-		read_ctrl_pos(lruvec, type, tier, gain[type], &pv);
-		if (!positive_ctrl_err(&sp, &pv))
-			break;
-	}
+	read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp);
+	read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv);
 
-	*tier_idx = tier - 1;
-
-	return type;
+	return positive_ctrl_err(&sp, &pv);
 }
 
 static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
 			  int *type_scanned, struct list_head *list)
 {
 	int i;
-	int type;
-	int scanned;
-	int tier = -1;
-	DEFINE_MIN_SEQ(lruvec);
+	int type = get_type_to_scan(lruvec, swappiness);
 
-	/*
-	 * Try to make the obvious choice first, and if anon and file are both
-	 * available from the same generation,
-	 * 1. Interpret swappiness 1 as file first and MAX_SWAPPINESS as anon
-	 *    first.
-	 * 2. If !__GFP_IO, file first since clean pagecache is more likely to
-	 *    exist than clean swapcache.
-	 */
-	if (!swappiness)
-		type = LRU_GEN_FILE;
-	else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE])
-		type = LRU_GEN_ANON;
-	else if (swappiness == 1)
-		type = LRU_GEN_FILE;
-	else if (swappiness == MAX_SWAPPINESS)
-		type = LRU_GEN_ANON;
-	else if (!(sc->gfp_mask & __GFP_IO))
-		type = LRU_GEN_FILE;
-	else
-		type = get_type_to_scan(lruvec, swappiness, &tier);
+	for_each_evictable_type(i, swappiness) {
+		int scanned;
+		int tier = get_tier_idx(lruvec, type);
 
-	for (i = !swappiness; i < ANON_AND_FILE; i++) {
-		if (tier < 0)
-			tier = get_tier_idx(lruvec, type);
+		*type_scanned = type;
 
 		scanned = scan_folios(lruvec, sc, type, tier, list);
 		if (scanned)
-			break;
+			return scanned;
 
 		type = !type;
-		tier = -1;
 	}
 
-	*type_scanned = type;
-
-	return scanned;
+	return 0;
 }
 
 static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
@@ -4580,6 +4639,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	struct reclaim_stat stat;
 	struct lru_gen_mm_walk *walk;
 	bool skip_retry = false;
+	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
@@ -4589,7 +4649,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 
 	scanned += try_to_inc_min_seq(lruvec, swappiness);
 
-	if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS)
+	if (evictable_min_seq(lrugen->min_seq, swappiness) + MIN_NR_GENS > lrugen->max_seq)
 		scanned = 0;
 
 	spin_unlock_irq(&lruvec->lru_lock);
@@ -4605,31 +4665,24 @@ retry:
 			type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
 
 	list_for_each_entry_safe_reverse(folio, next, &list, lru) {
+		DEFINE_MIN_SEQ(lruvec);
+
 		if (!folio_evictable(folio)) {
 			list_del(&folio->lru);
 			folio_putback_lru(folio);
 			continue;
 		}
 
-		if (folio_test_reclaim(folio) &&
-		    (folio_test_dirty(folio) || folio_test_writeback(folio))) {
-			/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
-			if (folio_test_workingset(folio))
-				folio_set_referenced(folio);
-			continue;
-		}
-
-		if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) ||
-		    folio_mapped(folio) || folio_test_locked(folio) ||
-		    folio_test_dirty(folio) || folio_test_writeback(folio)) {
-			/* don't add rejected folios to the oldest generation */
-			set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS,
-				      BIT(PG_active));
+		/* retry folios that may have missed folio_rotate_reclaimable() */
+		if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) &&
+		    !folio_test_dirty(folio) && !folio_test_writeback(folio)) {
+			list_move(&folio->lru, &clean);
 			continue;
 		}
 
-		/* retry folios that may have missed folio_rotate_reclaimable() */
-		list_move(&folio->lru, &clean);
+		/* don't add rejected folios to the oldest generation */
+		if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type])
+			set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active));
 	}
 
 	spin_lock_irq(&lruvec->lru_lock);
@@ -4664,63 +4717,32 @@ retry:
 }
 
 static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
-			     bool can_swap, unsigned long *nr_to_scan)
+			     int swappiness, unsigned long *nr_to_scan)
 {
 	int gen, type, zone;
-	unsigned long old = 0;
-	unsigned long young = 0;
-	unsigned long total = 0;
+	unsigned long size = 0;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	DEFINE_MIN_SEQ(lruvec);
 
-	/* whether this lruvec is completely out of cold folios */
-	if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) {
-		*nr_to_scan = 0;
+	*nr_to_scan = 0;
+	/* have to run aging, since eviction is not possible anymore */
+	if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq)
 		return true;
-	}
 
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+	for_each_evictable_type(type, swappiness) {
 		unsigned long seq;
 
 		for (seq = min_seq[type]; seq <= max_seq; seq++) {
-			unsigned long size = 0;
-
 			gen = lru_gen_from_seq(seq);
 
 			for (zone = 0; zone < MAX_NR_ZONES; zone++)
 				size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
-
-			total += size;
-			if (seq == max_seq)
-				young += size;
-			else if (seq + MIN_NR_GENS == max_seq)
-				old += size;
 		}
 	}
 
-	*nr_to_scan = total;
-
-	/*
-	 * The aging tries to be lazy to reduce the overhead, while the eviction
-	 * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
-	 * ideal number of generations is MIN_NR_GENS+1.
-	 */
-	if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
-		return false;
-
-	/*
-	 * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
-	 * of the total number of pages for each generation. A reasonable range
-	 * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
-	 * aging cares about the upper bound of hot pages, while the eviction
-	 * cares about the lower bound of cold pages.
-	 */
-	if (young * MIN_NR_GENS > total)
-		return true;
-	if (old * (MIN_NR_GENS + 2) < total)
-		return true;
-
-	return false;
+	*nr_to_scan = size;
+	/* better to run aging even though eviction is still possible */
+	return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq;
 }
 
 /*
@@ -4728,7 +4750,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
  * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
  *    reclaim.
  */
-static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap)
+static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
 {
 	bool success;
 	unsigned long nr_to_scan;
@@ -4738,7 +4760,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
 		return -1;
 
-	success = should_run_aging(lruvec, max_seq, can_swap, &nr_to_scan);
+	success = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan);
 
 	/* try to scrape all its memory if this memcg was deleted */
 	if (nr_to_scan && !mem_cgroup_online(memcg))
@@ -4749,7 +4771,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 		return nr_to_scan >> sc->priority;
 
 	/* stop scanning this lruvec as it's low on cold folios */
-	return try_to_inc_max_seq(lruvec, max_seq, can_swap, false) ? -1 : 0;
+	return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0;
 }
 
 static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
@@ -5293,8 +5315,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 				s = "rep";
 				n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]);
 				n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]);
-				if (tier)
-					n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]);
+				n[2] = READ_ONCE(lrugen->protected[hist][type][tier]);
 			}
 
 			for (i = 0; i < 3; i++)
@@ -5349,7 +5370,7 @@ static int lru_gen_seq_show(struct seq_file *m, void *v)
 	seq_printf(m, " node %5d\n", nid);
 
 	if (!full)
-		seq = min_seq[LRU_GEN_ANON];
+		seq = evictable_min_seq(min_seq, MAX_SWAPPINESS / 2);
 	else if (max_seq >= MAX_NR_GENS)
 		seq = max_seq - MAX_NR_GENS + 1;
 	else
@@ -5389,23 +5410,14 @@ static const struct seq_operations lru_gen_seq_ops = {
 };
 
 static int run_aging(struct lruvec *lruvec, unsigned long seq,
-		     bool can_swap, bool force_scan)
+		     int swappiness, bool force_scan)
 {
 	DEFINE_MAX_SEQ(lruvec);
-	DEFINE_MIN_SEQ(lruvec);
-
-	if (seq < max_seq)
-		return 0;
 
 	if (seq > max_seq)
 		return -EINVAL;
 
-	if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq)
-		return -ERANGE;
-
-	try_to_inc_max_seq(lruvec, max_seq, can_swap, force_scan);
-
-	return 0;
+	return try_to_inc_max_seq(lruvec, max_seq, swappiness, force_scan) ? 0 : -EEXIST;
 }
 
 static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
@@ -5421,7 +5433,7 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co
 	while (!signal_pending(current)) {
 		DEFINE_MIN_SEQ(lruvec);
 
-		if (seq < min_seq[!swappiness])
+		if (seq < evictable_min_seq(min_seq, swappiness))
 			return 0;
 
 		if (sc->nr_reclaimed >= nr_to_reclaim)
@@ -5466,7 +5478,7 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq,
 
 	if (swappiness < MIN_SWAPPINESS)
 		swappiness = get_swappiness(lruvec, sc);
-	else if (swappiness > MAX_SWAPPINESS)
+	else if (swappiness > MAX_SWAPPINESS + 1)
 		goto done;
 
 	switch (cmd) {
diff --git a/mm/workingset.c b/mm/workingset.c
index a4705e196545..4841ae8af411 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -239,7 +239,8 @@ static void *lru_gen_eviction(struct folio *folio)
 	int type = folio_is_file_lru(folio);
 	int delta = folio_nr_pages(folio);
 	int refs = folio_lru_refs(folio);
-	int tier = lru_tier_from_refs(refs);
+	bool workingset = folio_test_workingset(folio);
+	int tier = lru_tier_from_refs(refs, workingset);
 	struct mem_cgroup *memcg = folio_memcg(folio);
 	struct pglist_data *pgdat = folio_pgdat(folio);
 
@@ -253,18 +254,18 @@ static void *lru_gen_eviction(struct folio *folio)
 	hist = lru_hist_from_seq(min_seq);
 	atomic_long_add(delta, &lrugen->evicted[hist][type][tier]);
 
-	return pack_shadow(mem_cgroup_id(memcg), pgdat, token, refs);
+	return pack_shadow(mem_cgroup_id(memcg), pgdat, token, workingset);
 }
 
 /*
  * Tests if the shadow entry is for a folio that was recently evicted.
  * Fills in @lruvec, @token, @workingset with the values unpacked from shadow.
  */
-static bool lru_gen_test_recent(void *shadow, bool file, struct lruvec **lruvec,
+static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec,
 				unsigned long *token, bool *workingset)
 {
 	int memcg_id;
-	unsigned long min_seq;
+	unsigned long max_seq;
 	struct mem_cgroup *memcg;
 	struct pglist_data *pgdat;
 
@@ -273,8 +274,10 @@ static bool lru_gen_test_recent(void *shadow, bool file, struct lruvec **lruvec,
 	memcg = mem_cgroup_from_id(memcg_id);
 	*lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
-	min_seq = READ_ONCE((*lruvec)->lrugen.min_seq[file]);
-	return (*token >> LRU_REFS_WIDTH) == (min_seq & (EVICTION_MASK >> LRU_REFS_WIDTH));
+	max_seq = READ_ONCE((*lruvec)->lrugen.max_seq);
+	max_seq &= EVICTION_MASK >> LRU_REFS_WIDTH;
+
+	return abs_diff(max_seq, *token >> LRU_REFS_WIDTH) < MAX_NR_GENS;
 }
 
 static void lru_gen_refault(struct folio *folio, void *shadow)
@@ -290,7 +293,7 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 
 	rcu_read_lock();
 
-	recent = lru_gen_test_recent(shadow, type, &lruvec, &token, &workingset);
+	recent = lru_gen_test_recent(shadow, &lruvec, &token, &workingset);
 	if (lruvec != folio_lruvec(folio))
 		goto unlock;
 
@@ -302,24 +305,20 @@ static void lru_gen_refault(struct folio *folio, void *shadow)
 	lrugen = &lruvec->lrugen;
 
 	hist = lru_hist_from_seq(READ_ONCE(lrugen->min_seq[type]));
-	/* see the comment in folio_lru_refs() */
-	refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + workingset;
-	tier = lru_tier_from_refs(refs);
+	refs = (token & (BIT(LRU_REFS_WIDTH) - 1)) + 1;
+	tier = lru_tier_from_refs(refs, workingset);
 
 	atomic_long_add(delta, &lrugen->refaulted[hist][type][tier]);
-	mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
 
-	/*
-	 * Count the following two cases as stalls:
-	 * 1. For pages accessed through page tables, hotter pages pushed out
-	 *    hot pages which refaulted immediately.
-	 * 2. For pages accessed multiple times through file descriptors,
-	 *    they would have been protected by sort_folio().
-	 */
-	if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) {
-		set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset));
+	/* see folio_add_lru() where folio_set_active() will be called */
+	if (lru_gen_in_fault())
+		mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + type, delta);
+
+	if (workingset) {
+		folio_set_workingset(folio);
 		mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta);
-	}
+	} else
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, (refs - 1UL) << LRU_REFS_PGOFF);
 unlock:
 	rcu_read_unlock();
 }
@@ -331,7 +330,7 @@ static void *lru_gen_eviction(struct folio *folio)
 	return NULL;
 }
 
-static bool lru_gen_test_recent(void *shadow, bool file, struct lruvec **lruvec,
+static bool lru_gen_test_recent(void *shadow, struct lruvec **lruvec,
 				unsigned long *token, bool *workingset)
 {
 	return false;
@@ -428,17 +427,16 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset,
 	struct pglist_data *pgdat;
 	unsigned long eviction;
 
-	rcu_read_lock();
-
 	if (lru_gen_enabled()) {
-		bool recent = lru_gen_test_recent(shadow, file,
-				&eviction_lruvec, &eviction, workingset);
+		bool recent;
 
+		rcu_read_lock();
+		recent = lru_gen_test_recent(shadow, &eviction_lruvec, &eviction, workingset);
 		rcu_read_unlock();
 		return recent;
 	}
 
-
+	rcu_read_lock();
 	unpack_shadow(shadow, &memcgid, &pgdat, &eviction, workingset);
 	eviction <<= bucket_order;
 
@@ -459,14 +457,12 @@ bool workingset_test_recent(void *shadow, bool file, bool *workingset,
 	 * configurations instead.
 	 */
 	eviction_memcg = mem_cgroup_from_id(memcgid);
-	if (!mem_cgroup_disabled() &&
-	    (!eviction_memcg || !mem_cgroup_tryget(eviction_memcg))) {
-		rcu_read_unlock();
-		return false;
-	}
-
+	if (!mem_cgroup_tryget(eviction_memcg))
+		eviction_memcg = NULL;
 	rcu_read_unlock();
 
+	if (!mem_cgroup_disabled() && !eviction_memcg)
+		return false;
 	/*
 	 * Flush stats (and potentially sleep) outside the RCU read section.
 	 *
@@ -544,6 +540,8 @@ void workingset_refault(struct folio *folio, void *shadow)
 	bool workingset;
 	long nr;
 
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+
 	if (lru_gen_enabled()) {
 		lru_gen_refault(folio, shadow);
 		return;
@@ -558,7 +556,6 @@ void workingset_refault(struct folio *folio, void *shadow)
 	 * is actually experiencing the refault event. Make sure the folio is
 	 * locked to guarantee folio_memcg() stability throughout.
 	 */
-	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	nr = folio_nr_pages(folio);
 	memcg = folio_memcg(folio);
 	pgdat = folio_pgdat(folio);
diff --git a/mm/zpdesc.h b/mm/zpdesc.h
new file mode 100644
index 000000000000..fa47fece2237
--- /dev/null
+++ b/mm/zpdesc.h
@@ -0,0 +1,182 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* zpdesc.h: zswap.zpool memory descriptor
+ *
+ * Written by Alex Shi <alexs@kernel.org>
+ *	      Hyeonggon Yoo <42.hyeyoo@gmail.com>
+ */
+#ifndef __MM_ZPDESC_H__
+#define __MM_ZPDESC_H__
+
+/*
+ * struct zpdesc -	Memory descriptor for zpool memory.
+ * @flags:		Page flags, mostly unused by zsmalloc.
+ * @lru:		Indirectly used by page migration.
+ * @movable_ops:	Used by page migration.
+ * @next:		Next zpdesc in a zspage in zsmalloc zpool.
+ * @handle:		For huge zspage in zsmalloc zpool.
+ * @zspage:		Points to the zspage this zpdesc is a part of.
+ * @first_obj_offset:	First object offset in zsmalloc zpool.
+ * @_refcount:		The number of references to this zpdesc.
+ *
+ * This struct overlays struct page for now. Do not modify without a good
+ * understanding of the issues. In particular, do not expand into the overlap
+ * with memcg_data.
+ *
+ * Page flags used:
+ * * PG_private identifies the first component page.
+ * * PG_locked is used by page migration code.
+ */
+struct zpdesc {
+	unsigned long flags;
+	struct list_head lru;
+	unsigned long movable_ops;
+	union {
+		struct zpdesc *next;
+		unsigned long handle;
+	};
+	struct zspage *zspage;
+	/*
+	 * Only the lower 24 bits are available for offset, limiting a page
+	 * to 16 MiB. The upper 8 bits are reserved for PGTY_zsmalloc.
+	 *
+	 * Do not access this field directly.
+	 * Instead, use {get,set}_first_obj_offset() helpers.
+	 */
+	unsigned int first_obj_offset;
+	atomic_t _refcount;
+};
+#define ZPDESC_MATCH(pg, zp) \
+	static_assert(offsetof(struct page, pg) == offsetof(struct zpdesc, zp))
+
+ZPDESC_MATCH(flags, flags);
+ZPDESC_MATCH(lru, lru);
+ZPDESC_MATCH(mapping, movable_ops);
+ZPDESC_MATCH(index, next);
+ZPDESC_MATCH(index, handle);
+ZPDESC_MATCH(private, zspage);
+ZPDESC_MATCH(page_type, first_obj_offset);
+ZPDESC_MATCH(_refcount, _refcount);
+#undef ZPDESC_MATCH
+static_assert(sizeof(struct zpdesc) <= sizeof(struct page));
+
+/*
+ * zpdesc_page - The first struct page allocated for a zpdesc
+ * @zp: The zpdesc.
+ *
+ * A convenience wrapper for converting zpdesc to the first struct page of the
+ * underlying folio, to communicate with code not yet converted to folio or
+ * struct zpdesc.
+ *
+ */
+#define zpdesc_page(zp)			(_Generic((zp),			\
+	const struct zpdesc *:		(const struct page *)(zp),	\
+	struct zpdesc *:		(struct page *)(zp)))
+
+/**
+ * zpdesc_folio - The folio allocated for a zpdesc
+ * @zp: The zpdesc.
+ *
+ * Zpdescs are descriptors for zpool memory. The zpool memory itself is
+ * allocated as folios that contain the zpool objects, and zpdesc uses specific
+ * fields in the first struct page of the folio - those fields are now accessed
+ * by struct zpdesc.
+ *
+ * It is occasionally necessary convert to back to a folio in order to
+ * communicate with the rest of the mm. Please use this helper function
+ * instead of casting yourself, as the implementation may change in the future.
+ */
+#define zpdesc_folio(zp)		(_Generic((zp),			\
+	const struct zpdesc *:		(const struct folio *)(zp),	\
+	struct zpdesc *:		(struct folio *)(zp)))
+/**
+ * page_zpdesc - Converts from first struct page to zpdesc.
+ * @p: The first (either head of compound or single) page of zpdesc.
+ *
+ * A temporary wrapper to convert struct page to struct zpdesc in situations
+ * where we know the page is the compound head, or single order-0 page.
+ *
+ * Long-term ideally everything would work with struct zpdesc directly or go
+ * through folio to struct zpdesc.
+ *
+ * Return: The zpdesc which contains this page
+ */
+#define page_zpdesc(p)			(_Generic((p),			\
+	const struct page *:		(const struct zpdesc *)(p),	\
+	struct page *:			(struct zpdesc *)(p)))
+
+static inline void zpdesc_lock(struct zpdesc *zpdesc)
+{
+	folio_lock(zpdesc_folio(zpdesc));
+}
+
+static inline bool zpdesc_trylock(struct zpdesc *zpdesc)
+{
+	return folio_trylock(zpdesc_folio(zpdesc));
+}
+
+static inline void zpdesc_unlock(struct zpdesc *zpdesc)
+{
+	folio_unlock(zpdesc_folio(zpdesc));
+}
+
+static inline void zpdesc_wait_locked(struct zpdesc *zpdesc)
+{
+	folio_wait_locked(zpdesc_folio(zpdesc));
+}
+
+static inline void zpdesc_get(struct zpdesc *zpdesc)
+{
+	folio_get(zpdesc_folio(zpdesc));
+}
+
+static inline void zpdesc_put(struct zpdesc *zpdesc)
+{
+	folio_put(zpdesc_folio(zpdesc));
+}
+
+static inline void *kmap_local_zpdesc(struct zpdesc *zpdesc)
+{
+	return kmap_local_page(zpdesc_page(zpdesc));
+}
+
+static inline unsigned long zpdesc_pfn(struct zpdesc *zpdesc)
+{
+	return page_to_pfn(zpdesc_page(zpdesc));
+}
+
+static inline struct zpdesc *pfn_zpdesc(unsigned long pfn)
+{
+	return page_zpdesc(pfn_to_page(pfn));
+}
+
+static inline void __zpdesc_set_movable(struct zpdesc *zpdesc,
+					const struct movable_operations *mops)
+{
+	__SetPageMovable(zpdesc_page(zpdesc), mops);
+}
+
+static inline void __zpdesc_set_zsmalloc(struct zpdesc *zpdesc)
+{
+	__SetPageZsmalloc(zpdesc_page(zpdesc));
+}
+
+static inline void __zpdesc_clear_zsmalloc(struct zpdesc *zpdesc)
+{
+	__ClearPageZsmalloc(zpdesc_page(zpdesc));
+}
+
+static inline bool zpdesc_is_isolated(struct zpdesc *zpdesc)
+{
+	return PageIsolated(zpdesc_page(zpdesc));
+}
+
+static inline struct zone *zpdesc_zone(struct zpdesc *zpdesc)
+{
+	return page_zone(zpdesc_page(zpdesc));
+}
+
+static inline bool zpdesc_is_locked(struct zpdesc *zpdesc)
+{
+	return folio_test_locked(zpdesc_folio(zpdesc));
+}
+#endif
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 64b66a4d3e6e..6d0e47f7ae33 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -13,24 +13,6 @@
  * Released under the terms of GNU General Public License Version 2.0
  */
 
-/*
- * Following is how we use various fields and flags of underlying
- * struct page(s) to form a zspage.
- *
- * Usage of struct page fields:
- *	page->private: points to zspage
- *	page->index: links together all component pages of a zspage
- *		For the huge page, this is always 0, so we use this field
- *		to store handle.
- *	page->page_type: PGTY_zsmalloc, lower 24 bits locate the first object
- *		offset in a subpage of a zspage
- *
- * Usage of struct page flags:
- *	PG_private: identifies the first component page
- *	PG_owner_priv_1: identifies the huge component page
- *
- */
-
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 /*
@@ -67,6 +49,7 @@
 #include <linux/pagemap.h>
 #include <linux/fs.h>
 #include <linux/local_lock.h>
+#include "zpdesc.h"
 
 #define ZSPAGE_MAGIC	0x58
 
@@ -245,6 +228,35 @@ struct zs_pool {
 	atomic_t compaction_in_progress;
 };
 
+static inline void zpdesc_set_first(struct zpdesc *zpdesc)
+{
+	SetPagePrivate(zpdesc_page(zpdesc));
+}
+
+static inline void zpdesc_inc_zone_page_state(struct zpdesc *zpdesc)
+{
+	inc_zone_page_state(zpdesc_page(zpdesc), NR_ZSPAGES);
+}
+
+static inline void zpdesc_dec_zone_page_state(struct zpdesc *zpdesc)
+{
+	dec_zone_page_state(zpdesc_page(zpdesc), NR_ZSPAGES);
+}
+
+static inline struct zpdesc *alloc_zpdesc(gfp_t gfp)
+{
+	struct page *page = alloc_page(gfp);
+
+	return page_zpdesc(page);
+}
+
+static inline void free_zpdesc(struct zpdesc *zpdesc)
+{
+	struct page *page = zpdesc_page(zpdesc);
+
+	__free_page(page);
+}
+
 struct zspage {
 	struct {
 		unsigned int huge:HUGE_BITS;
@@ -254,7 +266,7 @@ struct zspage {
 	};
 	unsigned int inuse;
 	unsigned int freeobj;
-	struct page *first_page;
+	struct zpdesc *first_zpdesc;
 	struct list_head list; /* fullness list */
 	struct zs_pool *pool;
 	rwlock_t lock;
@@ -440,9 +452,9 @@ static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = {
 	.lock	= INIT_LOCAL_LOCK(lock),
 };
 
-static __maybe_unused int is_first_page(struct page *page)
+static inline bool __maybe_unused is_first_zpdesc(struct zpdesc *zpdesc)
 {
-	return PagePrivate(page);
+	return PagePrivate(zpdesc_page(zpdesc));
 }
 
 /* Protected by class->lock */
@@ -451,36 +463,35 @@ static inline int get_zspage_inuse(struct zspage *zspage)
 	return zspage->inuse;
 }
 
-
 static inline void mod_zspage_inuse(struct zspage *zspage, int val)
 {
 	zspage->inuse += val;
 }
 
-static inline struct page *get_first_page(struct zspage *zspage)
+static struct zpdesc *get_first_zpdesc(struct zspage *zspage)
 {
-	struct page *first_page = zspage->first_page;
+	struct zpdesc *first_zpdesc = zspage->first_zpdesc;
 
-	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
-	return first_page;
+	VM_BUG_ON_PAGE(!is_first_zpdesc(first_zpdesc), zpdesc_page(first_zpdesc));
+	return first_zpdesc;
 }
 
 #define FIRST_OBJ_PAGE_TYPE_MASK	0xffffff
 
-static inline unsigned int get_first_obj_offset(struct page *page)
+static inline unsigned int get_first_obj_offset(struct zpdesc *zpdesc)
 {
-	VM_WARN_ON_ONCE(!PageZsmalloc(page));
-	return page->page_type & FIRST_OBJ_PAGE_TYPE_MASK;
+	VM_WARN_ON_ONCE(!PageZsmalloc(zpdesc_page(zpdesc)));
+	return zpdesc->first_obj_offset & FIRST_OBJ_PAGE_TYPE_MASK;
 }
 
-static inline void set_first_obj_offset(struct page *page, unsigned int offset)
+static inline void set_first_obj_offset(struct zpdesc *zpdesc, unsigned int offset)
 {
 	/* With 24 bits available, we can support offsets into 16 MiB pages. */
 	BUILD_BUG_ON(PAGE_SIZE > SZ_16M);
-	VM_WARN_ON_ONCE(!PageZsmalloc(page));
+	VM_WARN_ON_ONCE(!PageZsmalloc(zpdesc_page(zpdesc)));
 	VM_WARN_ON_ONCE(offset & ~FIRST_OBJ_PAGE_TYPE_MASK);
-	page->page_type &= ~FIRST_OBJ_PAGE_TYPE_MASK;
-	page->page_type |= offset & FIRST_OBJ_PAGE_TYPE_MASK;
+	zpdesc->first_obj_offset &= ~FIRST_OBJ_PAGE_TYPE_MASK;
+	zpdesc->first_obj_offset |= offset & FIRST_OBJ_PAGE_TYPE_MASK;
 }
 
 static inline unsigned int get_freeobj(struct zspage *zspage)
@@ -733,52 +744,52 @@ out:
 	return newfg;
 }
 
-static struct zspage *get_zspage(struct page *page)
+static struct zspage *get_zspage(struct zpdesc *zpdesc)
 {
-	struct zspage *zspage = (struct zspage *)page_private(page);
+	struct zspage *zspage = zpdesc->zspage;
 
 	BUG_ON(zspage->magic != ZSPAGE_MAGIC);
 	return zspage;
 }
 
-static struct page *get_next_page(struct page *page)
+static struct zpdesc *get_next_zpdesc(struct zpdesc *zpdesc)
 {
-	struct zspage *zspage = get_zspage(page);
+	struct zspage *zspage = get_zspage(zpdesc);
 
 	if (unlikely(ZsHugePage(zspage)))
 		return NULL;
 
-	return (struct page *)page->index;
+	return zpdesc->next;
 }
 
 /**
- * obj_to_location - get (<page>, <obj_idx>) from encoded object value
+ * obj_to_location - get (<zpdesc>, <obj_idx>) from encoded object value
  * @obj: the encoded object value
- * @page: page object resides in zspage
+ * @zpdesc: zpdesc object resides in zspage
  * @obj_idx: object index
  */
-static void obj_to_location(unsigned long obj, struct page **page,
+static void obj_to_location(unsigned long obj, struct zpdesc **zpdesc,
 				unsigned int *obj_idx)
 {
-	*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
+	*zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS);
 	*obj_idx = (obj & OBJ_INDEX_MASK);
 }
 
-static void obj_to_page(unsigned long obj, struct page **page)
+static void obj_to_zpdesc(unsigned long obj, struct zpdesc **zpdesc)
 {
-	*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
+	*zpdesc = pfn_zpdesc(obj >> OBJ_INDEX_BITS);
 }
 
 /**
- * location_to_obj - get obj value encoded from (<page>, <obj_idx>)
- * @page: page object resides in zspage
+ * location_to_obj - get obj value encoded from (<zpdesc>, <obj_idx>)
+ * @zpdesc: zpdesc object resides in zspage
  * @obj_idx: object index
  */
-static unsigned long location_to_obj(struct page *page, unsigned int obj_idx)
+static unsigned long location_to_obj(struct zpdesc *zpdesc, unsigned int obj_idx)
 {
 	unsigned long obj;
 
-	obj = page_to_pfn(page) << OBJ_INDEX_BITS;
+	obj = zpdesc_pfn(zpdesc) << OBJ_INDEX_BITS;
 	obj |= obj_idx & OBJ_INDEX_MASK;
 
 	return obj;
@@ -789,15 +800,15 @@ static unsigned long handle_to_obj(unsigned long handle)
 	return *(unsigned long *)handle;
 }
 
-static inline bool obj_allocated(struct page *page, void *obj,
+static inline bool obj_allocated(struct zpdesc *zpdesc, void *obj,
 				 unsigned long *phandle)
 {
 	unsigned long handle;
-	struct zspage *zspage = get_zspage(page);
+	struct zspage *zspage = get_zspage(zpdesc);
 
 	if (unlikely(ZsHugePage(zspage))) {
-		VM_BUG_ON_PAGE(!is_first_page(page), page);
-		handle = page->index;
+		VM_BUG_ON_PAGE(!is_first_zpdesc(zpdesc), zpdesc_page(zpdesc));
+		handle = zpdesc->handle;
 	} else
 		handle = *(unsigned long *)obj;
 
@@ -809,22 +820,24 @@ static inline bool obj_allocated(struct page *page, void *obj,
 	return true;
 }
 
-static void reset_page(struct page *page)
+static void reset_zpdesc(struct zpdesc *zpdesc)
 {
+	struct page *page = zpdesc_page(zpdesc);
+
 	__ClearPageMovable(page);
 	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	page->index = 0;
+	zpdesc->zspage = NULL;
+	zpdesc->next = NULL;
 	__ClearPageZsmalloc(page);
 }
 
 static int trylock_zspage(struct zspage *zspage)
 {
-	struct page *cursor, *fail;
+	struct zpdesc *cursor, *fail;
 
-	for (cursor = get_first_page(zspage); cursor != NULL; cursor =
-					get_next_page(cursor)) {
-		if (!trylock_page(cursor)) {
+	for (cursor = get_first_zpdesc(zspage); cursor != NULL; cursor =
+					get_next_zpdesc(cursor)) {
+		if (!zpdesc_trylock(cursor)) {
 			fail = cursor;
 			goto unlock;
 		}
@@ -832,9 +845,9 @@ static int trylock_zspage(struct zspage *zspage)
 
 	return 1;
 unlock:
-	for (cursor = get_first_page(zspage); cursor != fail; cursor =
-					get_next_page(cursor))
-		unlock_page(cursor);
+	for (cursor = get_first_zpdesc(zspage); cursor != fail; cursor =
+					get_next_zpdesc(cursor))
+		zpdesc_unlock(cursor);
 
 	return 0;
 }
@@ -842,23 +855,23 @@ unlock:
 static void __free_zspage(struct zs_pool *pool, struct size_class *class,
 				struct zspage *zspage)
 {
-	struct page *page, *next;
+	struct zpdesc *zpdesc, *next;
 
 	assert_spin_locked(&class->lock);
 
 	VM_BUG_ON(get_zspage_inuse(zspage));
 	VM_BUG_ON(zspage->fullness != ZS_INUSE_RATIO_0);
 
-	next = page = get_first_page(zspage);
+	next = zpdesc = get_first_zpdesc(zspage);
 	do {
-		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		next = get_next_page(page);
-		reset_page(page);
-		unlock_page(page);
-		dec_zone_page_state(page, NR_ZSPAGES);
-		put_page(page);
-		page = next;
-	} while (page != NULL);
+		VM_BUG_ON_PAGE(!zpdesc_is_locked(zpdesc), zpdesc_page(zpdesc));
+		next = get_next_zpdesc(zpdesc);
+		reset_zpdesc(zpdesc);
+		zpdesc_unlock(zpdesc);
+		zpdesc_dec_zone_page_state(zpdesc);
+		zpdesc_put(zpdesc);
+		zpdesc = next;
+	} while (zpdesc != NULL);
 
 	cache_free_zspage(pool, zspage);
 
@@ -891,16 +904,16 @@ static void init_zspage(struct size_class *class, struct zspage *zspage)
 {
 	unsigned int freeobj = 1;
 	unsigned long off = 0;
-	struct page *page = get_first_page(zspage);
+	struct zpdesc *zpdesc = get_first_zpdesc(zspage);
 
-	while (page) {
-		struct page *next_page;
+	while (zpdesc) {
+		struct zpdesc *next_zpdesc;
 		struct link_free *link;
 		void *vaddr;
 
-		set_first_obj_offset(page, off);
+		set_first_obj_offset(zpdesc, off);
 
-		vaddr = kmap_local_page(page);
+		vaddr = kmap_local_zpdesc(zpdesc);
 		link = (struct link_free *)vaddr + off / sizeof(*link);
 
 		while ((off += class->size) < PAGE_SIZE) {
@@ -913,8 +926,8 @@ static void init_zspage(struct size_class *class, struct zspage *zspage)
 		 * page, which must point to the first object on the next
 		 * page (if present)
 		 */
-		next_page = get_next_page(page);
-		if (next_page) {
+		next_zpdesc = get_next_zpdesc(zpdesc);
+		if (next_zpdesc) {
 			link->next = freeobj++ << OBJ_TAG_BITS;
 		} else {
 			/*
@@ -924,7 +937,7 @@ static void init_zspage(struct size_class *class, struct zspage *zspage)
 			link->next = -1UL << OBJ_TAG_BITS;
 		}
 		kunmap_local(vaddr);
-		page = next_page;
+		zpdesc = next_zpdesc;
 		off %= PAGE_SIZE;
 	}
 
@@ -932,35 +945,35 @@ static void init_zspage(struct size_class *class, struct zspage *zspage)
 }
 
 static void create_page_chain(struct size_class *class, struct zspage *zspage,
-				struct page *pages[])
+				struct zpdesc *zpdescs[])
 {
 	int i;
-	struct page *page;
-	struct page *prev_page = NULL;
-	int nr_pages = class->pages_per_zspage;
+	struct zpdesc *zpdesc;
+	struct zpdesc *prev_zpdesc = NULL;
+	int nr_zpdescs = class->pages_per_zspage;
 
 	/*
 	 * Allocate individual pages and link them together as:
-	 * 1. all pages are linked together using page->index
-	 * 2. each sub-page point to zspage using page->private
+	 * 1. all pages are linked together using zpdesc->next
+	 * 2. each sub-page point to zspage using zpdesc->zspage
 	 *
-	 * we set PG_private to identify the first page (i.e. no other sub-page
+	 * we set PG_private to identify the first zpdesc (i.e. no other zpdesc
 	 * has this flag set).
 	 */
-	for (i = 0; i < nr_pages; i++) {
-		page = pages[i];
-		set_page_private(page, (unsigned long)zspage);
-		page->index = 0;
+	for (i = 0; i < nr_zpdescs; i++) {
+		zpdesc = zpdescs[i];
+		zpdesc->zspage = zspage;
+		zpdesc->next = NULL;
 		if (i == 0) {
-			zspage->first_page = page;
-			SetPagePrivate(page);
+			zspage->first_zpdesc = zpdesc;
+			zpdesc_set_first(zpdesc);
 			if (unlikely(class->objs_per_zspage == 1 &&
 					class->pages_per_zspage == 1))
 				SetZsHugePage(zspage);
 		} else {
-			prev_page->index = (unsigned long)page;
+			prev_zpdesc->next = zpdesc;
 		}
-		prev_page = page;
+		prev_zpdesc = zpdesc;
 	}
 }
 
@@ -972,7 +985,7 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
 					gfp_t gfp)
 {
 	int i;
-	struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE];
+	struct zpdesc *zpdescs[ZS_MAX_PAGES_PER_ZSPAGE];
 	struct zspage *zspage = cache_alloc_zspage(pool, gfp);
 
 	if (!zspage)
@@ -982,25 +995,25 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
 	migrate_lock_init(zspage);
 
 	for (i = 0; i < class->pages_per_zspage; i++) {
-		struct page *page;
+		struct zpdesc *zpdesc;
 
-		page = alloc_page(gfp);
-		if (!page) {
+		zpdesc = alloc_zpdesc(gfp);
+		if (!zpdesc) {
 			while (--i >= 0) {
-				dec_zone_page_state(pages[i], NR_ZSPAGES);
-				__ClearPageZsmalloc(pages[i]);
-				__free_page(pages[i]);
+				zpdesc_dec_zone_page_state(zpdescs[i]);
+				__zpdesc_clear_zsmalloc(zpdescs[i]);
+				free_zpdesc(zpdescs[i]);
 			}
 			cache_free_zspage(pool, zspage);
 			return NULL;
 		}
-		__SetPageZsmalloc(page);
+		__zpdesc_set_zsmalloc(zpdesc);
 
-		inc_zone_page_state(page, NR_ZSPAGES);
-		pages[i] = page;
+		zpdesc_inc_zone_page_state(zpdesc);
+		zpdescs[i] = zpdesc;
 	}
 
-	create_page_chain(class, zspage, pages);
+	create_page_chain(class, zspage, zpdescs);
 	init_zspage(class, zspage);
 	zspage->pool = pool;
 	zspage->class = class->index;
@@ -1044,7 +1057,7 @@ static inline void __zs_cpu_down(struct mapping_area *area)
 }
 
 static void *__zs_map_object(struct mapping_area *area,
-			struct page *pages[2], int off, int size)
+			struct zpdesc *zpdescs[2], int off, int size)
 {
 	size_t sizes[2];
 	char *buf = area->vm_buf;
@@ -1060,14 +1073,14 @@ static void *__zs_map_object(struct mapping_area *area,
 	sizes[1] = size - sizes[0];
 
 	/* copy object to per-cpu buffer */
-	memcpy_from_page(buf, pages[0], off, sizes[0]);
-	memcpy_from_page(buf + sizes[0], pages[1], 0, sizes[1]);
+	memcpy_from_page(buf, zpdesc_page(zpdescs[0]), off, sizes[0]);
+	memcpy_from_page(buf + sizes[0], zpdesc_page(zpdescs[1]), 0, sizes[1]);
 out:
 	return area->vm_buf;
 }
 
 static void __zs_unmap_object(struct mapping_area *area,
-			struct page *pages[2], int off, int size)
+			struct zpdesc *zpdescs[2], int off, int size)
 {
 	size_t sizes[2];
 	char *buf;
@@ -1085,8 +1098,8 @@ static void __zs_unmap_object(struct mapping_area *area,
 	sizes[1] = size - sizes[0];
 
 	/* copy per-cpu buffer to object */
-	memcpy_to_page(pages[0], off, buf, sizes[0]);
-	memcpy_to_page(pages[1], 0, buf + sizes[0], sizes[1]);
+	memcpy_to_page(zpdesc_page(zpdescs[0]), off, buf, sizes[0]);
+	memcpy_to_page(zpdesc_page(zpdescs[1]), 0, buf + sizes[0], sizes[1]);
 
 out:
 	/* enable page faults to match kunmap_local() return conditions */
@@ -1176,13 +1189,13 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 			enum zs_mapmode mm)
 {
 	struct zspage *zspage;
-	struct page *page;
+	struct zpdesc *zpdesc;
 	unsigned long obj, off;
 	unsigned int obj_idx;
 
 	struct size_class *class;
 	struct mapping_area *area;
-	struct page *pages[2];
+	struct zpdesc *zpdescs[2];
 	void *ret;
 
 	/*
@@ -1195,8 +1208,8 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 	/* It guarantees it can get zspage from handle safely */
 	read_lock(&pool->migrate_lock);
 	obj = handle_to_obj(handle);
-	obj_to_location(obj, &page, &obj_idx);
-	zspage = get_zspage(page);
+	obj_to_location(obj, &zpdesc, &obj_idx);
+	zspage = get_zspage(zpdesc);
 
 	/*
 	 * migration cannot move any zpages in this zspage. Here, class->lock
@@ -1215,17 +1228,17 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 	area->vm_mm = mm;
 	if (off + class->size <= PAGE_SIZE) {
 		/* this object is contained entirely within a page */
-		area->vm_addr = kmap_local_page(page);
+		area->vm_addr = kmap_local_zpdesc(zpdesc);
 		ret = area->vm_addr + off;
 		goto out;
 	}
 
 	/* this object spans two pages */
-	pages[0] = page;
-	pages[1] = get_next_page(page);
-	BUG_ON(!pages[1]);
+	zpdescs[0] = zpdesc;
+	zpdescs[1] = get_next_zpdesc(zpdesc);
+	BUG_ON(!zpdescs[1]);
 
-	ret = __zs_map_object(area, pages, off, class->size);
+	ret = __zs_map_object(area, zpdescs, off, class->size);
 out:
 	if (likely(!ZsHugePage(zspage)))
 		ret += ZS_HANDLE_SIZE;
@@ -1237,7 +1250,7 @@ EXPORT_SYMBOL_GPL(zs_map_object);
 void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 {
 	struct zspage *zspage;
-	struct page *page;
+	struct zpdesc *zpdesc;
 	unsigned long obj, off;
 	unsigned int obj_idx;
 
@@ -1245,8 +1258,8 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 	struct mapping_area *area;
 
 	obj = handle_to_obj(handle);
-	obj_to_location(obj, &page, &obj_idx);
-	zspage = get_zspage(page);
+	obj_to_location(obj, &zpdesc, &obj_idx);
+	zspage = get_zspage(zpdesc);
 	class = zspage_class(pool, zspage);
 	off = offset_in_page(class->size * obj_idx);
 
@@ -1254,13 +1267,13 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 	if (off + class->size <= PAGE_SIZE)
 		kunmap_local(area->vm_addr);
 	else {
-		struct page *pages[2];
+		struct zpdesc *zpdescs[2];
 
-		pages[0] = page;
-		pages[1] = get_next_page(page);
-		BUG_ON(!pages[1]);
+		zpdescs[0] = zpdesc;
+		zpdescs[1] = get_next_zpdesc(zpdesc);
+		BUG_ON(!zpdescs[1]);
 
-		__zs_unmap_object(area, pages, off, class->size);
+		__zs_unmap_object(area, zpdescs, off, class->size);
 	}
 	local_unlock(&zs_map_area.lock);
 
@@ -1290,12 +1303,12 @@ EXPORT_SYMBOL_GPL(zs_huge_class_size);
 static unsigned long obj_malloc(struct zs_pool *pool,
 				struct zspage *zspage, unsigned long handle)
 {
-	int i, nr_page, offset;
+	int i, nr_zpdesc, offset;
 	unsigned long obj;
 	struct link_free *link;
 	struct size_class *class;
 
-	struct page *m_page;
+	struct zpdesc *m_zpdesc;
 	unsigned long m_offset;
 	void *vaddr;
 
@@ -1303,27 +1316,26 @@ static unsigned long obj_malloc(struct zs_pool *pool,
 	obj = get_freeobj(zspage);
 
 	offset = obj * class->size;
-	nr_page = offset >> PAGE_SHIFT;
+	nr_zpdesc = offset >> PAGE_SHIFT;
 	m_offset = offset_in_page(offset);
-	m_page = get_first_page(zspage);
+	m_zpdesc = get_first_zpdesc(zspage);
 
-	for (i = 0; i < nr_page; i++)
-		m_page = get_next_page(m_page);
+	for (i = 0; i < nr_zpdesc; i++)
+		m_zpdesc = get_next_zpdesc(m_zpdesc);
 
-	vaddr = kmap_local_page(m_page);
+	vaddr = kmap_local_zpdesc(m_zpdesc);
 	link = (struct link_free *)vaddr + m_offset / sizeof(*link);
 	set_freeobj(zspage, link->next >> OBJ_TAG_BITS);
 	if (likely(!ZsHugePage(zspage)))
 		/* record handle in the header of allocated chunk */
 		link->handle = handle | OBJ_ALLOCATED_TAG;
 	else
-		/* record handle to page->index */
-		zspage->first_page->index = handle | OBJ_ALLOCATED_TAG;
+		zspage->first_zpdesc->handle = handle | OBJ_ALLOCATED_TAG;
 
 	kunmap_local(vaddr);
 	mod_zspage_inuse(zspage, 1);
 
-	obj = location_to_obj(m_page, obj);
+	obj = location_to_obj(m_zpdesc, obj);
 	record_obj(handle, obj);
 
 	return obj;
@@ -1402,23 +1414,24 @@ static void obj_free(int class_size, unsigned long obj)
 {
 	struct link_free *link;
 	struct zspage *zspage;
-	struct page *f_page;
+	struct zpdesc *f_zpdesc;
 	unsigned long f_offset;
 	unsigned int f_objidx;
 	void *vaddr;
 
-	obj_to_location(obj, &f_page, &f_objidx);
+
+	obj_to_location(obj, &f_zpdesc, &f_objidx);
 	f_offset = offset_in_page(class_size * f_objidx);
-	zspage = get_zspage(f_page);
+	zspage = get_zspage(f_zpdesc);
 
-	vaddr = kmap_local_page(f_page);
+	vaddr = kmap_local_zpdesc(f_zpdesc);
 	link = (struct link_free *)(vaddr + f_offset);
 
 	/* Insert this object in containing zspage's freelist */
 	if (likely(!ZsHugePage(zspage)))
 		link->next = get_freeobj(zspage) << OBJ_TAG_BITS;
 	else
-		f_page->index = 0;
+		f_zpdesc->handle = 0;
 	set_freeobj(zspage, f_objidx);
 
 	kunmap_local(vaddr);
@@ -1428,7 +1441,7 @@ static void obj_free(int class_size, unsigned long obj)
 void zs_free(struct zs_pool *pool, unsigned long handle)
 {
 	struct zspage *zspage;
-	struct page *f_page;
+	struct zpdesc *f_zpdesc;
 	unsigned long obj;
 	struct size_class *class;
 	int fullness;
@@ -1442,8 +1455,8 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 	 */
 	read_lock(&pool->migrate_lock);
 	obj = handle_to_obj(handle);
-	obj_to_page(obj, &f_page);
-	zspage = get_zspage(f_page);
+	obj_to_zpdesc(obj, &f_zpdesc);
+	zspage = get_zspage(f_zpdesc);
 	class = zspage_class(pool, zspage);
 	spin_lock(&class->lock);
 	read_unlock(&pool->migrate_lock);
@@ -1463,7 +1476,7 @@ EXPORT_SYMBOL_GPL(zs_free);
 static void zs_object_copy(struct size_class *class, unsigned long dst,
 				unsigned long src)
 {
-	struct page *s_page, *d_page;
+	struct zpdesc *s_zpdesc, *d_zpdesc;
 	unsigned int s_objidx, d_objidx;
 	unsigned long s_off, d_off;
 	void *s_addr, *d_addr;
@@ -1472,8 +1485,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst,
 
 	s_size = d_size = class->size;
 
-	obj_to_location(src, &s_page, &s_objidx);
-	obj_to_location(dst, &d_page, &d_objidx);
+	obj_to_location(src, &s_zpdesc, &s_objidx);
+	obj_to_location(dst, &d_zpdesc, &d_objidx);
 
 	s_off = offset_in_page(class->size * s_objidx);
 	d_off = offset_in_page(class->size * d_objidx);
@@ -1484,8 +1497,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst,
 	if (d_off + class->size > PAGE_SIZE)
 		d_size = PAGE_SIZE - d_off;
 
-	s_addr = kmap_local_page(s_page);
-	d_addr = kmap_local_page(d_page);
+	s_addr = kmap_local_zpdesc(s_zpdesc);
+	d_addr = kmap_local_zpdesc(d_zpdesc);
 
 	while (1) {
 		size = min(s_size, d_size);
@@ -1510,17 +1523,17 @@ static void zs_object_copy(struct size_class *class, unsigned long dst,
 		if (s_off >= PAGE_SIZE) {
 			kunmap_local(d_addr);
 			kunmap_local(s_addr);
-			s_page = get_next_page(s_page);
-			s_addr = kmap_local_page(s_page);
-			d_addr = kmap_local_page(d_page);
+			s_zpdesc = get_next_zpdesc(s_zpdesc);
+			s_addr = kmap_local_zpdesc(s_zpdesc);
+			d_addr = kmap_local_zpdesc(d_zpdesc);
 			s_size = class->size - written;
 			s_off = 0;
 		}
 
 		if (d_off >= PAGE_SIZE) {
 			kunmap_local(d_addr);
-			d_page = get_next_page(d_page);
-			d_addr = kmap_local_page(d_page);
+			d_zpdesc = get_next_zpdesc(d_zpdesc);
+			d_addr = kmap_local_zpdesc(d_zpdesc);
 			d_size = class->size - written;
 			d_off = 0;
 		}
@@ -1535,18 +1548,18 @@ static void zs_object_copy(struct size_class *class, unsigned long dst,
  * return handle.
  */
 static unsigned long find_alloced_obj(struct size_class *class,
-				      struct page *page, int *obj_idx)
+				      struct zpdesc *zpdesc, int *obj_idx)
 {
 	unsigned int offset;
 	int index = *obj_idx;
 	unsigned long handle = 0;
-	void *addr = kmap_local_page(page);
+	void *addr = kmap_local_zpdesc(zpdesc);
 
-	offset = get_first_obj_offset(page);
+	offset = get_first_obj_offset(zpdesc);
 	offset += class->size * index;
 
 	while (offset < PAGE_SIZE) {
-		if (obj_allocated(page, addr + offset, &handle))
+		if (obj_allocated(zpdesc, addr + offset, &handle))
 			break;
 
 		offset += class->size;
@@ -1566,14 +1579,14 @@ static void migrate_zspage(struct zs_pool *pool, struct zspage *src_zspage,
 	unsigned long used_obj, free_obj;
 	unsigned long handle;
 	int obj_idx = 0;
-	struct page *s_page = get_first_page(src_zspage);
+	struct zpdesc *s_zpdesc = get_first_zpdesc(src_zspage);
 	struct size_class *class = pool->size_class[src_zspage->class];
 
 	while (1) {
-		handle = find_alloced_obj(class, s_page, &obj_idx);
+		handle = find_alloced_obj(class, s_zpdesc, &obj_idx);
 		if (!handle) {
-			s_page = get_next_page(s_page);
-			if (!s_page)
+			s_zpdesc = get_next_zpdesc(s_zpdesc);
+			if (!s_zpdesc)
 				break;
 			obj_idx = 0;
 			continue;
@@ -1653,7 +1666,7 @@ static int putback_zspage(struct size_class *class, struct zspage *zspage)
  */
 static void lock_zspage(struct zspage *zspage)
 {
-	struct page *curr_page, *page;
+	struct zpdesc *curr_zpdesc, *zpdesc;
 
 	/*
 	 * Pages we haven't locked yet can be migrated off the list while we're
@@ -1665,24 +1678,24 @@ static void lock_zspage(struct zspage *zspage)
 	 */
 	while (1) {
 		migrate_read_lock(zspage);
-		page = get_first_page(zspage);
-		if (trylock_page(page))
+		zpdesc = get_first_zpdesc(zspage);
+		if (zpdesc_trylock(zpdesc))
 			break;
-		get_page(page);
+		zpdesc_get(zpdesc);
 		migrate_read_unlock(zspage);
-		wait_on_page_locked(page);
-		put_page(page);
+		zpdesc_wait_locked(zpdesc);
+		zpdesc_put(zpdesc);
 	}
 
-	curr_page = page;
-	while ((page = get_next_page(curr_page))) {
-		if (trylock_page(page)) {
-			curr_page = page;
+	curr_zpdesc = zpdesc;
+	while ((zpdesc = get_next_zpdesc(curr_zpdesc))) {
+		if (zpdesc_trylock(zpdesc)) {
+			curr_zpdesc = zpdesc;
 		} else {
-			get_page(page);
+			zpdesc_get(zpdesc);
 			migrate_read_unlock(zspage);
-			wait_on_page_locked(page);
-			put_page(page);
+			zpdesc_wait_locked(zpdesc);
+			zpdesc_put(zpdesc);
 			migrate_read_lock(zspage);
 		}
 	}
@@ -1720,26 +1733,28 @@ static void migrate_write_unlock(struct zspage *zspage)
 static const struct movable_operations zsmalloc_mops;
 
 static void replace_sub_page(struct size_class *class, struct zspage *zspage,
-				struct page *newpage, struct page *oldpage)
+				struct zpdesc *newzpdesc, struct zpdesc *oldzpdesc)
 {
-	struct page *page;
-	struct page *pages[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, };
+	struct zpdesc *zpdesc;
+	struct zpdesc *zpdescs[ZS_MAX_PAGES_PER_ZSPAGE] = {NULL, };
+	unsigned int first_obj_offset;
 	int idx = 0;
 
-	page = get_first_page(zspage);
+	zpdesc = get_first_zpdesc(zspage);
 	do {
-		if (page == oldpage)
-			pages[idx] = newpage;
+		if (zpdesc == oldzpdesc)
+			zpdescs[idx] = newzpdesc;
 		else
-			pages[idx] = page;
+			zpdescs[idx] = zpdesc;
 		idx++;
-	} while ((page = get_next_page(page)) != NULL);
+	} while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL);
 
-	create_page_chain(class, zspage, pages);
-	set_first_obj_offset(newpage, get_first_obj_offset(oldpage));
+	create_page_chain(class, zspage, zpdescs);
+	first_obj_offset = get_first_obj_offset(oldzpdesc);
+	set_first_obj_offset(newzpdesc, first_obj_offset);
 	if (unlikely(ZsHugePage(zspage)))
-		newpage->index = oldpage->index;
-	__SetPageMovable(newpage, &zsmalloc_mops);
+		newzpdesc->handle = oldzpdesc->handle;
+	__zpdesc_set_movable(newzpdesc, &zsmalloc_mops);
 }
 
 static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
@@ -1759,20 +1774,22 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 	struct zs_pool *pool;
 	struct size_class *class;
 	struct zspage *zspage;
-	struct page *dummy;
+	struct zpdesc *dummy;
+	struct zpdesc *newzpdesc = page_zpdesc(newpage);
+	struct zpdesc *zpdesc = page_zpdesc(page);
 	void *s_addr, *d_addr, *addr;
 	unsigned int offset;
 	unsigned long handle;
 	unsigned long old_obj, new_obj;
 	unsigned int obj_idx;
 
-	VM_BUG_ON_PAGE(!PageIsolated(page), page);
+	VM_BUG_ON_PAGE(!zpdesc_is_isolated(zpdesc), zpdesc_page(zpdesc));
 
 	/* We're committed, tell the world that this is a Zsmalloc page. */
-	__SetPageZsmalloc(newpage);
+	__zpdesc_set_zsmalloc(newzpdesc);
 
 	/* The page is locked, so this pointer must remain valid */
-	zspage = get_zspage(page);
+	zspage = get_zspage(zpdesc);
 	pool = zspage->pool;
 
 	/*
@@ -1789,30 +1806,29 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 	/* the migrate_write_lock protects zpage access via zs_map_object */
 	migrate_write_lock(zspage);
 
-	offset = get_first_obj_offset(page);
-	s_addr = kmap_local_page(page);
+	offset = get_first_obj_offset(zpdesc);
+	s_addr = kmap_local_zpdesc(zpdesc);
 
 	/*
 	 * Here, any user cannot access all objects in the zspage so let's move.
 	 */
-	d_addr = kmap_local_page(newpage);
+	d_addr = kmap_local_zpdesc(newzpdesc);
 	copy_page(d_addr, s_addr);
 	kunmap_local(d_addr);
 
 	for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE;
 					addr += class->size) {
-		if (obj_allocated(page, addr, &handle)) {
+		if (obj_allocated(zpdesc, addr, &handle)) {
 
 			old_obj = handle_to_obj(handle);
 			obj_to_location(old_obj, &dummy, &obj_idx);
-			new_obj = (unsigned long)location_to_obj(newpage,
-								obj_idx);
+			new_obj = (unsigned long)location_to_obj(newzpdesc, obj_idx);
 			record_obj(handle, new_obj);
 		}
 	}
 	kunmap_local(s_addr);
 
-	replace_sub_page(class, zspage, newpage, page);
+	replace_sub_page(class, zspage, newzpdesc, zpdesc);
 	/*
 	 * Since we complete the data copy and set up new zspage structure,
 	 * it's okay to release migration_lock.
@@ -1821,14 +1837,14 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 	spin_unlock(&class->lock);
 	migrate_write_unlock(zspage);
 
-	get_page(newpage);
-	if (page_zone(newpage) != page_zone(page)) {
-		dec_zone_page_state(page, NR_ZSPAGES);
-		inc_zone_page_state(newpage, NR_ZSPAGES);
+	zpdesc_get(newzpdesc);
+	if (zpdesc_zone(newzpdesc) != zpdesc_zone(zpdesc)) {
+		zpdesc_dec_zone_page_state(zpdesc);
+		zpdesc_inc_zone_page_state(newzpdesc);
 	}
 
-	reset_page(page);
-	put_page(page);
+	reset_zpdesc(zpdesc);
+	zpdesc_put(zpdesc);
 
 	return MIGRATEPAGE_SUCCESS;
 }
@@ -1897,13 +1913,13 @@ static void init_deferred_free(struct zs_pool *pool)
 
 static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage)
 {
-	struct page *page = get_first_page(zspage);
+	struct zpdesc *zpdesc = get_first_zpdesc(zspage);
 
 	do {
-		WARN_ON(!trylock_page(page));
-		__SetPageMovable(page, &zsmalloc_mops);
-		unlock_page(page);
-	} while ((page = get_next_page(page)) != NULL);
+		WARN_ON(!zpdesc_trylock(zpdesc));
+		__zpdesc_set_movable(zpdesc, &zsmalloc_mops);
+		zpdesc_unlock(zpdesc);
+	} while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL);
 }
 #else
 static inline void zs_flush_migration(struct zs_pool *pool) { }
diff --git a/mm/zswap.c b/mm/zswap.c
index b84c20d889b1..6504174fbc6a 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1192,7 +1192,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 
 	/*
 	 * It's safe to drop the lock here because we return either
-	 * LRU_REMOVED_RETRY or LRU_RETRY.
+	 * LRU_REMOVED_RETRY, LRU_RETRY or LRU_STOP.
 	 */
 	spin_unlock(&l->lock);
 
diff --git a/net/bluetooth/hidp/Kconfig b/net/bluetooth/hidp/Kconfig
index 6746be07e222..e08aae35351a 100644
--- a/net/bluetooth/hidp/Kconfig
+++ b/net/bluetooth/hidp/Kconfig
@@ -1,8 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config BT_HIDP
 	tristate "HIDP protocol support"
-	depends on BT_BREDR && INPUT && HID_SUPPORT
-	select HID
+	depends on BT_BREDR && HID
 	help
 	  HIDP (Human Interface Device Protocol) is a transport layer
 	  for HID reports.  HIDP is required for the Bluetooth Human
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 49f97d4138ea..46ea0bee2259 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -710,12 +710,12 @@ static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu)
 {
 	switch (chan->scid) {
 	case L2CAP_CID_ATT:
-		if (mtu < L2CAP_LE_MIN_MTU)
+		if (mtu && mtu < L2CAP_LE_MIN_MTU)
 			return false;
 		break;
 
 	default:
-		if (mtu < L2CAP_DEFAULT_MIN_MTU)
+		if (mtu && mtu < L2CAP_DEFAULT_MIN_MTU)
 			return false;
 	}
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 09bac3c9c2d5..f53304cb09db 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -210,7 +210,7 @@ static const u16 mgmt_untrusted_events[] = {
 	MGMT_EV_EXP_FEATURE_CHANGED,
 };
 
-#define CACHE_TIMEOUT	msecs_to_jiffies(2 * 1000)
+#define CACHE_TIMEOUT	secs_to_jiffies(2)
 
 #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \
 		 "\x00\x00\x00\x00\x00\x00\x00\x00"
diff --git a/net/core/dev.c b/net/core/dev.c
index afa2282f2604..b91658e8aedb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6708,7 +6708,7 @@ void napi_resume_irqs(unsigned int napi_id)
 static void __napi_hash_add_with_id(struct napi_struct *napi,
 				    unsigned int napi_id)
 {
-	napi->napi_id = napi_id;
+	WRITE_ONCE(napi->napi_id, napi_id);
 	hlist_add_head_rcu(&napi->napi_hash_node,
 			   &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
 }
@@ -9924,6 +9924,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 			NL_SET_ERR_MSG(extack, "Program bound to different device");
 			return -EINVAL;
 		}
+		if (bpf_prog_is_dev_bound(new_prog->aux) && mode == XDP_MODE_SKB) {
+			NL_SET_ERR_MSG(extack, "Can't attach device-bound programs in generic mode");
+			return -EINVAL;
+		}
 		if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) {
 			NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device");
 			return -EINVAL;
@@ -10260,37 +10264,14 @@ static bool from_cleanup_net(void)
 #endif
 }
 
-static void rtnl_drop_if_cleanup_net(void)
-{
-	if (from_cleanup_net())
-		__rtnl_unlock();
-}
-
-static void rtnl_acquire_if_cleanup_net(void)
-{
-	if (from_cleanup_net())
-		rtnl_lock();
-}
-
 /* Delayed registration/unregisteration */
 LIST_HEAD(net_todo_list);
-static LIST_HEAD(net_todo_list_for_cleanup_net);
-
-/* TODO: net_todo_list/net_todo_list_for_cleanup_net should probably
- * be provided by callers, instead of being static, rtnl protected.
- */
-static struct list_head *todo_list(void)
-{
-	return from_cleanup_net() ? &net_todo_list_for_cleanup_net :
-				    &net_todo_list;
-}
-
 DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 atomic_t dev_unreg_count = ATOMIC_INIT(0);
 
 static void net_set_todo(struct net_device *dev)
 {
-	list_add_tail(&dev->todo_list, todo_list());
+	list_add_tail(&dev->todo_list, &net_todo_list);
 }
 
 static netdev_features_t netdev_sync_upper_features(struct net_device *lower,
@@ -11140,7 +11121,7 @@ void netdev_run_todo(void)
 #endif
 
 	/* Snapshot list, allow later requests */
-	list_replace_init(todo_list(), &list);
+	list_replace_init(&net_todo_list, &list);
 
 	__rtnl_unlock();
 
@@ -11305,6 +11286,20 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 	const struct net_device_ops *ops = dev->netdev_ops;
 	const struct net_device_core_stats __percpu *p;
 
+	/*
+	 * IPv{4,6} and udp tunnels share common stat helpers and use
+	 * different stat type (NETDEV_PCPU_STAT_TSTATS vs
+	 * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent.
+	 */
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) !=
+		     offsetof(struct pcpu_dstats, rx_bytes));
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) !=
+		     offsetof(struct pcpu_dstats, rx_packets));
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) !=
+		     offsetof(struct pcpu_dstats, tx_bytes));
+	BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) !=
+		     offsetof(struct pcpu_dstats, tx_packets));
+
 	if (ops->ndo_get_stats64) {
 		memset(storage, 0, sizeof(*storage));
 		ops->ndo_get_stats64(dev, storage);
@@ -11785,11 +11780,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING);
 		netdev_unlock(dev);
 	}
-
-	rtnl_drop_if_cleanup_net();
 	flush_all_backlogs();
+
 	synchronize_net();
-	rtnl_acquire_if_cleanup_net();
 
 	list_for_each_entry(dev, head, unreg_list) {
 		struct sk_buff *skb = NULL;
@@ -11849,9 +11842,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 #endif
 	}
 
-	rtnl_drop_if_cleanup_net();
 	synchronize_net();
-	rtnl_acquire_if_cleanup_net();
 
 	list_for_each_entry(dev, head, unreg_list) {
 		netdev_put(dev, &dev->dev_registered_tracker);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index a3de752c5178..f5e908c9e7ad 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -536,12 +536,11 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool,
 	if (unlikely(pool->alloc.count > 0))
 		return pool->alloc.cache[--pool->alloc.count];
 
-	/* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */
+	/* Mark empty alloc.cache slots "empty" for alloc_pages_bulk */
 	memset(&pool->alloc.cache, 0, sizeof(void *) * bulk);
 
-	nr_pages = alloc_pages_bulk_array_node(gfp,
-					       pool->p.nid, bulk,
-					       (struct page **)pool->alloc.cache);
+	nr_pages = alloc_pages_bulk_node(gfp, pool->p.nid, bulk,
+					 (struct page **)pool->alloc.cache);
 	if (unlikely(!nr_pages))
 		return 0;
 
@@ -1147,7 +1146,9 @@ void page_pool_disable_direct_recycling(struct page_pool *pool)
 	WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state));
 	WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1);
 
+	mutex_lock(&page_pools_lock);
 	WRITE_ONCE(pool->p.napi, NULL);
+	mutex_unlock(&page_pools_lock);
 }
 EXPORT_SYMBOL(page_pool_disable_direct_recycling);
 
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
index 57439787b9c2..2fb06d5f6d55 100644
--- a/net/core/page_pool_priv.h
+++ b/net/core/page_pool_priv.h
@@ -7,6 +7,8 @@
 
 #include "netmem_priv.h"
 
+extern struct mutex page_pools_lock;
+
 s32 page_pool_inflight(const struct page_pool *pool, bool strict);
 
 int page_pool_list(struct page_pool *pool);
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 48335766c1bf..6677e0c2e256 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -3,6 +3,7 @@
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/xarray.h>
+#include <net/busy_poll.h>
 #include <net/net_debug.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
@@ -14,10 +15,11 @@
 #include "netdev-genl-gen.h"
 
 static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1);
-/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user.
+/* Protects: page_pools, netdevice->page_pools, pool->p.napi, pool->slow.netdev,
+ *	pool->user.
  * Ordering: inside rtnl_lock
  */
-static DEFINE_MUTEX(page_pools_lock);
+DEFINE_MUTEX(page_pools_lock);
 
 /* Page pools are only reachable from user space (via netlink) if they are
  * linked to a netdev at creation time. Following page pool "visibility"
@@ -216,6 +218,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 {
 	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
 	size_t inflight, refsz;
+	unsigned int napi_id;
 	void *hdr;
 
 	hdr = genlmsg_iput(rsp, info);
@@ -229,8 +232,10 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 	    nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX,
 			pool->slow.netdev->ifindex))
 		goto err_cancel;
-	if (pool->user.napi_id &&
-	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
+
+	napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0;
+	if (napi_id >= MIN_NAPI_ID &&
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id))
 		goto err_cancel;
 
 	inflight = page_pool_inflight(pool, false);
@@ -319,8 +324,6 @@ int page_pool_list(struct page_pool *pool)
 	if (pool->slow.netdev) {
 		hlist_add_head(&pool->user.list,
 			       &pool->slow.netdev->page_pools);
-		pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0;
-
 		netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF);
 	}
 
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 5a7c0e565a89..e827775baf2e 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -1367,7 +1367,7 @@ static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn)
 	return dsa_switch_parse_ports_of(ds, dn);
 }
 
-static int dev_is_class(struct device *dev, void *class)
+static int dev_is_class(struct device *dev, const void *class)
 {
 	if (dev->class != NULL && !strcmp(dev->class->name, class))
 		return 1;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 7bb94875a7ec..7609ce2b2c5e 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -993,12 +993,12 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		return rc;
 
 	/* Nonzero ring with RSS only makes sense if NIC adds them together */
-	if (cmd == ETHTOOL_SRXCLSRLINS && info.flow_type & FLOW_RSS &&
+	if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS &&
 	    !ops->cap_rss_rxnfc_adds &&
 	    ethtool_get_flow_spec_ring(info.fs.ring_cookie))
 		return -EINVAL;
 
-	if (ops->get_rxfh) {
+	if (cmd == ETHTOOL_SRXFH && ops->get_rxfh) {
 		struct ethtool_rxfh_param rxfh = {};
 
 		rc = ops->get_rxfh(dev, &rxfh);
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 7cb106b590ab..58df9ad02ce8 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -107,6 +107,8 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev,
 	u32 total_size, indir_bytes;
 	u8 *rss_config;
 
+	data->no_key_fields = !dev->ethtool_ops->rxfh_per_ctx_key;
+
 	ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context);
 	if (!ctx)
 		return -ENOENT;
@@ -153,7 +155,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context)
 			return -EOPNOTSUPP;
 
-		data->no_key_fields = !ops->rxfh_per_ctx_key;
 		return rss_prepare_ctx(request, dev, data, info);
 	}
 
diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c
index 1a195efc79cd..5b2cfac3b2ba 100644
--- a/net/hsr/hsr_debugfs.c
+++ b/net/hsr/hsr_debugfs.c
@@ -57,14 +57,11 @@ DEFINE_SHOW_ATTRIBUTE(hsr_node_table);
 void hsr_debugfs_rename(struct net_device *dev)
 {
 	struct hsr_priv *priv = netdev_priv(dev);
-	struct dentry *d;
+	int err;
 
-	d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root,
-			   hsr_debugfs_root_dir, dev->name);
-	if (IS_ERR(d))
+	err = debugfs_change_name(priv->node_tbl_root, "%s", dev->name);
+	if (err)
 		netdev_warn(dev, "failed to rename\n");
-	else
-		priv->node_tbl_root = d;
 }
 
 /* hsr_debugfs_init - create hsr node_table file for dumping
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 87bb3a91598e..a4bacf198555 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -700,9 +700,12 @@ static int fill_frame_info(struct hsr_frame_info *frame,
 		frame->is_vlan = true;
 
 	if (frame->is_vlan) {
-		if (skb->mac_len < offsetofend(struct hsr_vlan_ethhdr, vlanhdr))
+		/* Note: skb->mac_len might be wrong here. */
+		if (!pskb_may_pull(skb,
+				   skb_mac_offset(skb) +
+				   offsetofend(struct hsr_vlan_ethhdr, vlanhdr)))
 			return -EINVAL;
-		vlan_hdr = (struct hsr_vlan_ethhdr *)ethhdr;
+		vlan_hdr = (struct hsr_vlan_ethhdr *)skb_mac_header(skb);
 		proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto;
 	}
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b0fbf804bbba..0e4076866c0a 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -279,7 +279,7 @@ static void esp_output_done(void *data, int err)
 		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 			esp_output_tail_tcp(x, skb);
 		else
-			xfrm_output_resume(skb->sk, skb, err);
+			xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 	}
 }
 
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 03b6eee407a2..28d77d454d44 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -330,9 +330,6 @@ next_entry:
 	list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
 		if (e < s_e)
 			goto next_entry2;
-		if (filter->dev &&
-		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
-			goto next_entry2;
 
 		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
 			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0e5b9a654254..bc95d2a5924f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -265,11 +265,14 @@ static u16 tcp_select_window(struct sock *sk)
 	u32 cur_win, new_win;
 
 	/* Make the window 0 if we failed to queue the data because we
-	 * are out of memory. The window is temporary, so we don't store
-	 * it on the socket.
+	 * are out of memory.
 	 */
-	if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM))
+	if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) {
+		tp->pred_flags = 0;
+		tp->rcv_wnd = 0;
+		tp->rcv_wup = tp->rcv_nxt;
 		return 0;
+	}
 
 	cur_win = tcp_receive_window(tp);
 	new_win = __tcp_select_window(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c472c9a57cf6..a9bb9ce5438e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1141,9 +1141,9 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 		const int hlen = skb_network_header_len(skb) +
 				 sizeof(struct udphdr);
 
-		if (hlen + cork->gso_size > cork->fragsize) {
+		if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
 			kfree_skb(skb);
-			return -EINVAL;
+			return -EMSGSIZE;
 		}
 		if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
 			kfree_skb(skb);
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 5f3d0cc1555a..9e73944e3b53 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -315,7 +315,7 @@ static void esp_output_done(void *data, int err)
 		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 			esp_output_tail_tcp(x, skb);
 		else
-			xfrm_output_resume(skb->sk, skb, err);
+			xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 	}
 }
 
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 28e5a89dc255..2c383c12a431 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -336,7 +336,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 
 static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb), *cache_dst;
+	struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
 	struct in6_addr orig_daddr;
 	struct ioam6_lwt *ilwt;
 	int err = -EINVAL;
@@ -407,13 +407,15 @@ do_encap:
 		cache_dst = ip6_route_output(net, NULL, &fl6);
 		if (cache_dst->error) {
 			err = cache_dst->error;
-			dst_release(cache_dst);
 			goto drop;
 		}
 
-		local_bh_disable();
-		dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
-		local_bh_enable();
+		/* cache only if we don't create a dst reference loop */
+		if (dst->lwtstate != cache_dst->lwtstate) {
+			local_bh_disable();
+			dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr);
+			local_bh_enable();
+		}
 
 		err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev));
 		if (unlikely(err))
@@ -426,8 +428,10 @@ do_encap:
 		return dst_output(net, sk, skb);
 	}
 out:
+	dst_release(cache_dst);
 	return dst->lwtstate->orig_output(net, sk, skb);
 drop:
+	dst_release(cache_dst);
 	kfree_skb(skb);
 	return err;
 }
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 7ba22d2f2bfe..0ac4283acdf2 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -232,13 +232,15 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		dst = ip6_route_output(net, NULL, &fl6);
 		if (dst->error) {
 			err = dst->error;
-			dst_release(dst);
 			goto drop;
 		}
 
-		local_bh_disable();
-		dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
-		local_bh_enable();
+		/* cache only if we don't create a dst reference loop */
+		if (orig_dst->lwtstate != dst->lwtstate) {
+			local_bh_disable();
+			dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr);
+			local_bh_enable();
+		}
 
 		err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 		if (unlikely(err))
@@ -251,6 +253,7 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	return dst_output(net, sk, skb);
 
 drop:
+	dst_release(dst);
 	kfree_skb(skb);
 	return err;
 }
@@ -269,8 +272,10 @@ static int rpl_input(struct sk_buff *skb)
 	local_bh_enable();
 
 	err = rpl_do_srh(skb, rlwt, dst);
-	if (unlikely(err))
+	if (unlikely(err)) {
+		dst_release(dst);
 		goto drop;
+	}
 
 	if (!dst) {
 		ip6_route_input(skb);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 4bf937bfc263..33833b2064c0 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -482,8 +482,10 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 	local_bh_enable();
 
 	err = seg6_do_srh(skb, dst);
-	if (unlikely(err))
+	if (unlikely(err)) {
+		dst_release(dst);
 		goto drop;
+	}
 
 	if (!dst) {
 		ip6_route_input(skb);
@@ -571,13 +573,15 @@ static int seg6_output_core(struct net *net, struct sock *sk,
 		dst = ip6_route_output(net, NULL, &fl6);
 		if (dst->error) {
 			err = dst->error;
-			dst_release(dst);
 			goto drop;
 		}
 
-		local_bh_disable();
-		dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
-		local_bh_enable();
+		/* cache only if we don't create a dst reference loop */
+		if (orig_dst->lwtstate != dst->lwtstate) {
+			local_bh_disable();
+			dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+			local_bh_enable();
+		}
 
 		err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 		if (unlikely(err))
@@ -593,6 +597,7 @@ static int seg6_output_core(struct net *net, struct sock *sk,
 
 	return dst_output(net, sk, skb);
 drop:
+	dst_release(dst);
 	kfree_skb(skb);
 	return err;
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6671daa67f4f..c6ea438b5c75 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1389,9 +1389,9 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 		const int hlen = skb_network_header_len(skb) +
 				 sizeof(struct udphdr);
 
-		if (hlen + cork->gso_size > cork->fragsize) {
+		if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
 			kfree_skb(skb);
-			return -EINVAL;
+			return -EMSGSIZE;
 		}
 		if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
 			kfree_skb(skb);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 5f7b1fdbffe6..b3d5d1f266ee 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -82,14 +82,14 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	toobig = skb->len > mtu && !skb_is_gso(skb);
 
-	if (toobig && xfrm6_local_dontfrag(skb->sk)) {
+	if (toobig && xfrm6_local_dontfrag(sk)) {
 		xfrm6_local_rxpmtu(skb, mtu);
 		kfree_skb(skb);
 		return -EMSGSIZE;
 	} else if (toobig && xfrm6_noneed_fragment(skb)) {
 		skb->ignore_df = 1;
 		goto skip_frag;
-	} else if (!skb->ignore_df && toobig && skb->sk) {
+	} else if (!skb->ignore_df && toobig && sk) {
 		xfrm_local_error(skb, mtu);
 		kfree_skb(skb);
 		return -EMSGSIZE;
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index e7687a7b1683..54c479910d05 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -1025,16 +1025,7 @@ void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata)
 
 void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata)
 {
-	struct dentry *dir;
-	char buf[10 + IFNAMSIZ];
-
-	dir = sdata->vif.debugfs_dir;
-
-	if (IS_ERR_OR_NULL(dir))
-		return;
-
-	sprintf(buf, "netdev:%s", sdata->name);
-	debugfs_rename(dir->d_parent, dir, dir->d_parent, buf);
+	debugfs_change_name(sdata->vif.debugfs_dir, "netdev:%s", sdata->name);
 }
 
 void ieee80211_debugfs_recreate_netdev(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 3999e0ba2c35..2dd81e6c26bd 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -418,9 +418,9 @@ void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
 			MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
 			subflow->mpc_drop = 1;
 			mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
-		} else {
-			subflow->mpc_drop = 0;
 		}
+	} else if (ssk->sk_state == TCP_SYN_SENT) {
+		subflow->mpc_drop = 0;
 	}
 }
 
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 123f3f297284..fd2de185bc93 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -108,7 +108,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->suboptions |= OPTION_MPTCP_DSS;
 			mp_opt->use_map = 1;
 			mp_opt->mpc_map = 1;
-			mp_opt->use_ack = 0;
 			mp_opt->data_len = get_unaligned_be16(ptr);
 			ptr += 2;
 		}
@@ -157,11 +156,6 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		pr_debug("DSS\n");
 		ptr++;
 
-		/* we must clear 'mpc_map' be able to detect MP_CAPABLE
-		 * map vs DSS map in mptcp_incoming_options(), and reconstruct
-		 * map info accordingly
-		 */
-		mp_opt->mpc_map = 0;
 		flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
 		mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
 		mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
@@ -369,8 +363,11 @@ void mptcp_get_options(const struct sk_buff *skb,
 	const unsigned char *ptr;
 	int length;
 
-	/* initialize option status */
-	mp_opt->suboptions = 0;
+	/* Ensure that casting the whole status to u32 is efficient and safe */
+	BUILD_BUG_ON(sizeof_field(struct mptcp_options_received, status) != sizeof(u32));
+	BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_options_received, status),
+				 sizeof(u32)));
+	*(u32 *)&mp_opt->status = 0;
 
 	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 98ac73938bd8..572d160edca3 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -2020,7 +2020,8 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 	if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
-	    (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+	    (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL |
+			     MPTCP_PM_ADDR_FLAG_IMPLICIT))) {
 		spin_unlock_bh(&pernet->lock);
 		GENL_SET_ERR_MSG(info, "invalid addr flags");
 		return -EINVAL;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c44c89ecaca6..6bd819047470 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1767,8 +1767,10 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 		 * see mptcp_disconnect().
 		 * Attempt it again outside the problematic scope.
 		 */
-		if (!mptcp_disconnect(sk, 0))
+		if (!mptcp_disconnect(sk, 0)) {
+			sk->sk_disconnects++;
 			sk->sk_socket->state = SS_UNCONNECTED;
+		}
 	}
 	inet_clear_bit(DEFER_CONNECT, sk);
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0174a5aad279..f6a207958459 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -149,22 +149,24 @@ struct mptcp_options_received {
 	u32	subflow_seq;
 	u16	data_len;
 	__sum16	csum;
-	u16	suboptions;
+	struct_group(status,
+		u16 suboptions;
+		u16 use_map:1,
+		    dsn64:1,
+		    data_fin:1,
+		    use_ack:1,
+		    ack64:1,
+		    mpc_map:1,
+		    reset_reason:4,
+		    reset_transient:1,
+		    echo:1,
+		    backup:1,
+		    deny_join_id0:1,
+		    __unused:2;
+	);
+	u8	join_id;
 	u32	token;
 	u32	nonce;
-	u16	use_map:1,
-		dsn64:1,
-		data_fin:1,
-		use_ack:1,
-		ack64:1,
-		mpc_map:1,
-		reset_reason:4,
-		reset_transient:1,
-		echo:1,
-		backup:1,
-		deny_join_id0:1,
-		__unused:2;
-	u8	join_id;
 	u64	thmac;
 	u8	hmac[MPTCPOPT_HMAC_LEN];
 	struct mptcp_addr_info addr;
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index bf276eaf9330..7891a537bddd 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1385,6 +1385,12 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 		nd->state = ncsi_dev_state_probe_package;
 		break;
 	case ncsi_dev_state_probe_package:
+		if (ndp->package_probe_id >= 8) {
+			/* Last package probed, finishing */
+			ndp->flags |= NCSI_DEV_PROBED;
+			break;
+		}
+
 		ndp->pending_req_num = 1;
 
 		nca.type = NCSI_PKT_CMD_SP;
@@ -1501,13 +1507,8 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
 		if (ret)
 			goto error;
 
-		/* Probe next package */
+		/* Probe next package after receiving response */
 		ndp->package_probe_id++;
-		if (ndp->package_probe_id >= 8) {
-			/* Probe finished */
-			ndp->flags |= NCSI_DEV_PROBED;
-			break;
-		}
 		nd->state = ncsi_dev_state_probe_package;
 		ndp->active_package = NULL;
 		break;
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 14bd66909ca4..4a8ce2949fae 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -1089,14 +1089,12 @@ static int ncsi_rsp_handler_netlink(struct ncsi_request *nr)
 static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr)
 {
 	struct ncsi_dev_priv *ndp = nr->ndp;
+	struct sockaddr *saddr = &ndp->pending_mac;
 	struct net_device *ndev = ndp->ndev.dev;
 	struct ncsi_rsp_gmcma_pkt *rsp;
-	struct sockaddr saddr;
-	int ret = -1;
 	int i;
 
 	rsp = (struct ncsi_rsp_gmcma_pkt *)skb_network_header(nr->rsp);
-	saddr.sa_family = ndev->type;
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	netdev_info(ndev, "NCSI: Received %d provisioned MAC addresses\n",
@@ -1108,20 +1106,20 @@ static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr)
 			    rsp->addresses[i][4], rsp->addresses[i][5]);
 	}
 
+	saddr->sa_family = ndev->type;
 	for (i = 0; i < rsp->address_count; i++) {
-		memcpy(saddr.sa_data, &rsp->addresses[i], ETH_ALEN);
-		ret = ndev->netdev_ops->ndo_set_mac_address(ndev, &saddr);
-		if (ret < 0) {
+		if (!is_valid_ether_addr(rsp->addresses[i])) {
 			netdev_warn(ndev, "NCSI: Unable to assign %pM to device\n",
-				    saddr.sa_data);
+				    rsp->addresses[i]);
 			continue;
 		}
-		netdev_warn(ndev, "NCSI: Set MAC address to %pM\n", saddr.sa_data);
+		memcpy(saddr->sa_data, rsp->addresses[i], ETH_ALEN);
+		netdev_warn(ndev, "NCSI: Will set MAC address to %pM\n", saddr->sa_data);
 		break;
 	}
 
-	ndp->gma_flag = ret == 0;
-	return ret;
+	ndp->gma_flag = 1;
+	return 0;
 }
 
 static struct ncsi_rsp_handler {
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 4cc97f971264..7c6f7c9f7332 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -39,20 +39,15 @@ static const char *const sctp_conntrack_names[] = {
 	[SCTP_CONNTRACK_HEARTBEAT_SENT]		= "HEARTBEAT_SENT",
 };
 
-#define SECS  * HZ
-#define MINS  * 60 SECS
-#define HOURS * 60 MINS
-#define DAYS  * 24 HOURS
-
 static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
-	[SCTP_CONNTRACK_CLOSED]			= 10 SECS,
-	[SCTP_CONNTRACK_COOKIE_WAIT]		= 3 SECS,
-	[SCTP_CONNTRACK_COOKIE_ECHOED]		= 3 SECS,
-	[SCTP_CONNTRACK_ESTABLISHED]		= 210 SECS,
-	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= 3 SECS,
-	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= 3 SECS,
-	[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]	= 3 SECS,
-	[SCTP_CONNTRACK_HEARTBEAT_SENT]		= 30 SECS,
+	[SCTP_CONNTRACK_CLOSED]			= secs_to_jiffies(10),
+	[SCTP_CONNTRACK_COOKIE_WAIT]		= secs_to_jiffies(3),
+	[SCTP_CONNTRACK_COOKIE_ECHOED]		= secs_to_jiffies(3),
+	[SCTP_CONNTRACK_ESTABLISHED]		= secs_to_jiffies(210),
+	[SCTP_CONNTRACK_SHUTDOWN_SENT]		= secs_to_jiffies(3),
+	[SCTP_CONNTRACK_SHUTDOWN_RECD]		= secs_to_jiffies(3),
+	[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]	= secs_to_jiffies(3),
+	[SCTP_CONNTRACK_HEARTBEAT_SENT]		= secs_to_jiffies(30),
 };
 
 #define	SCTP_FLAG_HEARTBEAT_VTAG_FAILED	1
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 667459256e4c..a34de9c17cf1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5078,7 +5078,7 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr,
 static int nft_set_desc_concat(struct nft_set_desc *desc,
 			       const struct nlattr *nla)
 {
-	u32 num_regs = 0, key_num_regs = 0;
+	u32 len = 0, num_regs;
 	struct nlattr *attr;
 	int rem, err, i;
 
@@ -5092,12 +5092,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc,
 	}
 
 	for (i = 0; i < desc->field_count; i++)
-		num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32));
+		len += round_up(desc->field_len[i], sizeof(u32));
 
-	key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32));
-	if (key_num_regs != num_regs)
+	if (len != desc->klen)
 		return -EINVAL;
 
+	num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32));
 	if (num_regs > NFT_REG32_COUNT)
 		return -E2BIG;
 
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index de175318a3a0..082ab66f120b 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -542,6 +542,8 @@ static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host,
 
 	pr_debug("pipe created=%d\n", pipe);
 
+	if (pipe >= NCI_HCI_MAX_PIPES)
+		pipe = NCI_HCI_INVALID_PIPE;
 	return pipe;
 }
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 72c65d938a15..a4a668b88a8f 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -701,11 +701,9 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct net_device *dev;
 	ax25_address *source;
 	ax25_uid_assoc *user;
+	int err = -EINVAL;
 	int n;
 
-	if (!sock_flag(sk, SOCK_ZAPPED))
-		return -EINVAL;
-
 	if (addr_len != sizeof(struct sockaddr_rose) && addr_len != sizeof(struct full_sockaddr_rose))
 		return -EINVAL;
 
@@ -718,8 +716,15 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS)
 		return -EINVAL;
 
-	if ((dev = rose_dev_get(&addr->srose_addr)) == NULL)
-		return -EADDRNOTAVAIL;
+	lock_sock(sk);
+
+	if (!sock_flag(sk, SOCK_ZAPPED))
+		goto out_release;
+
+	err = -EADDRNOTAVAIL;
+	dev = rose_dev_get(&addr->srose_addr);
+	if (!dev)
+		goto out_release;
 
 	source = &addr->srose_call;
 
@@ -730,7 +735,8 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	} else {
 		if (ax25_uid_policy && !capable(CAP_NET_BIND_SERVICE)) {
 			dev_put(dev);
-			return -EACCES;
+			err = -EACCES;
+			goto out_release;
 		}
 		rose->source_call   = *source;
 	}
@@ -753,8 +759,10 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	rose_insert_socket(sk);
 
 	sock_reset_flag(sk, SOCK_ZAPPED);
-
-	return 0;
+	err = 0;
+out_release:
+	release_sock(sk);
+	return err;
 }
 
 static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags)
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index f06ddbed3fed..1525773e94aa 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -122,6 +122,10 @@ static void rose_heartbeat_expiry(struct timer_list *t)
 	struct rose_sock *rose = rose_sk(sk);
 
 	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
+		sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ/20);
+		goto out;
+	}
 	switch (rose->state) {
 	case ROSE_STATE_0:
 		/* Magic here: If we listen() and a new link dies before it
@@ -152,6 +156,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
 	}
 
 	rose_start_heartbeat(sk);
+out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
 }
@@ -162,6 +167,10 @@ static void rose_timer_expiry(struct timer_list *t)
 	struct sock *sk = &rose->sock;
 
 	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
+		sk_reset_timer(sk, &rose->timer, jiffies + HZ/20);
+		goto out;
+	}
 	switch (rose->state) {
 	case ROSE_STATE_1:	/* T1 */
 	case ROSE_STATE_4:	/* T2 */
@@ -182,6 +191,7 @@ static void rose_timer_expiry(struct timer_list *t)
 		}
 		break;
 	}
+out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
 }
@@ -192,6 +202,10 @@ static void rose_idletimer_expiry(struct timer_list *t)
 	struct sock *sk = &rose->sock;
 
 	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
+		sk_reset_timer(sk, &rose->idletimer, jiffies + HZ/20);
+		goto out;
+	}
 	rose_clear_queues(sk);
 
 	rose_write_internal(sk, ROSE_CLEAR_REQUEST);
@@ -207,6 +221,7 @@ static void rose_idletimer_expiry(struct timer_list *t)
 		sk->sk_state_change(sk);
 		sock_set_flag(sk, SOCK_DEAD);
 	}
+out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
 }
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 718193df9d2e..f251845fe532 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -582,6 +582,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_EXCLUSIVE,		/* The call uses a once-only connection */
 	RXRPC_CALL_RX_IS_IDLE,		/* recvmsg() is idle - send an ACK */
 	RXRPC_CALL_RECVMSG_READ_ALL,	/* recvmsg() read all of the received data */
+	RXRPC_CALL_CONN_CHALLENGING,	/* The connection is being challenged */
 };
 
 /*
@@ -602,7 +603,6 @@ enum rxrpc_call_state {
 	RXRPC_CALL_CLIENT_AWAIT_REPLY,	/* - client awaiting reply */
 	RXRPC_CALL_CLIENT_RECV_REPLY,	/* - client receiving reply phase */
 	RXRPC_CALL_SERVER_PREALLOC,	/* - service preallocation */
-	RXRPC_CALL_SERVER_SECURING,	/* - server securing request connection */
 	RXRPC_CALL_SERVER_RECV_REQUEST,	/* - server receiving request */
 	RXRPC_CALL_SERVER_ACK_REQUEST,	/* - server pending ACK of request */
 	RXRPC_CALL_SERVER_SEND_REPLY,	/* - server sending reply */
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 5a543c3f6fb0..c4c8b46a68c6 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -22,7 +22,6 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = {
 	[RXRPC_CALL_CLIENT_AWAIT_REPLY]		= "ClAwtRpl",
 	[RXRPC_CALL_CLIENT_RECV_REPLY]		= "ClRcvRpl",
 	[RXRPC_CALL_SERVER_PREALLOC]		= "SvPrealc",
-	[RXRPC_CALL_SERVER_SECURING]		= "SvSecure",
 	[RXRPC_CALL_SERVER_RECV_REQUEST]	= "SvRcvReq",
 	[RXRPC_CALL_SERVER_ACK_REQUEST]		= "SvAckReq",
 	[RXRPC_CALL_SERVER_SEND_REPLY]		= "SvSndRpl",
@@ -453,17 +452,16 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
 	call->cong_tstamp	= skb->tstamp;
 
 	__set_bit(RXRPC_CALL_EXPOSED, &call->flags);
-	rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
+	rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
 
 	spin_lock(&conn->state_lock);
 
 	switch (conn->state) {
 	case RXRPC_CONN_SERVICE_UNSECURED:
 	case RXRPC_CONN_SERVICE_CHALLENGING:
-		rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
+		__set_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags);
 		break;
 	case RXRPC_CONN_SERVICE:
-		rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
 		break;
 
 	case RXRPC_CONN_ABORTED:
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 713e04394ceb..4d9c5e21ba78 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -228,10 +228,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn)
  */
 static void rxrpc_call_is_secure(struct rxrpc_call *call)
 {
-	if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) {
-		rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
+	if (call && __test_and_clear_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags))
 		rxrpc_notify_socket(call);
-	}
 }
 
 /*
@@ -272,6 +270,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 			 * we've already received the packet, put it on the
 			 * front of the queue.
 			 */
+			sp->conn = rxrpc_get_connection(conn, rxrpc_conn_get_poke_secured);
 			skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED;
 			rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured);
 			skb_queue_head(&conn->local->rx_queue, skb);
@@ -437,14 +436,16 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
 	if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
 		rxrpc_abort_calls(conn);
 
-	switch (skb->mark) {
-	case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
-		if (conn->state != RXRPC_CONN_SERVICE)
-			break;
+	if (skb) {
+		switch (skb->mark) {
+		case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+			if (conn->state != RXRPC_CONN_SERVICE)
+				break;
 
-		for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
-			rxrpc_call_is_secure(conn->channels[loop].call);
-		break;
+			for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
+				rxrpc_call_is_secure(conn->channels[loop].call);
+			break;
+		}
 	}
 
 	/* Process delayed ACKs whose time has come. */
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 7eba4d7d9a38..2f1fd1e2e7e4 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -67,6 +67,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet,
 		INIT_WORK(&conn->destructor, rxrpc_clean_up_connection);
 		INIT_LIST_HEAD(&conn->proc_link);
 		INIT_LIST_HEAD(&conn->link);
+		INIT_LIST_HEAD(&conn->attend_link);
 		mutex_init(&conn->security_lock);
 		mutex_init(&conn->tx_data_alloc_lock);
 		skb_queue_head_init(&conn->rx_queue);
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 4974b5accafa..9047ba13bd31 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -448,11 +448,19 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb,
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	bool last = sp->hdr.flags & RXRPC_LAST_PACKET;
 
-	skb_queue_tail(&call->recvmsg_queue, skb);
+	spin_lock_irq(&call->recvmsg_queue.lock);
+
+	__skb_queue_tail(&call->recvmsg_queue, skb);
 	rxrpc_input_update_ack_window(call, window, wtop);
 	trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq);
 	if (last)
+		/* Change the state inside the lock so that recvmsg syncs
+		 * correctly with it and using sendmsg() to send a reply
+		 * doesn't race.
+		 */
 		rxrpc_end_rx_phase(call, sp->hdr.serial);
+
+	spin_unlock_irq(&call->recvmsg_queue.lock);
 }
 
 /*
@@ -657,7 +665,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb
 		rxrpc_propose_delay_ACK(call, sp->hdr.serial,
 					rxrpc_propose_ack_input_data);
 	}
-	if (notify) {
+	if (notify && !test_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags)) {
 		trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial);
 		rxrpc_notify_socket(call);
 	}
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index d82e44a3901b..e874c31fa901 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -246,7 +246,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 	bool use;
 	int slot;
 
-	spin_lock(&rxnet->peer_hash_lock);
+	spin_lock_bh(&rxnet->peer_hash_lock);
 
 	while (!list_empty(collector)) {
 		peer = list_entry(collector->next,
@@ -257,7 +257,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 			continue;
 
 		use = __rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive);
-		spin_unlock(&rxnet->peer_hash_lock);
+		spin_unlock_bh(&rxnet->peer_hash_lock);
 
 		if (use) {
 			keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
@@ -277,17 +277,17 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 			 */
 			slot += cursor;
 			slot &= mask;
-			spin_lock(&rxnet->peer_hash_lock);
+			spin_lock_bh(&rxnet->peer_hash_lock);
 			list_add_tail(&peer->keepalive_link,
 				      &rxnet->peer_keepalive[slot & mask]);
-			spin_unlock(&rxnet->peer_hash_lock);
+			spin_unlock_bh(&rxnet->peer_hash_lock);
 			rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive);
 		}
 		rxrpc_put_peer(peer, rxrpc_peer_put_keepalive);
-		spin_lock(&rxnet->peer_hash_lock);
+		spin_lock_bh(&rxnet->peer_hash_lock);
 	}
 
-	spin_unlock(&rxnet->peer_hash_lock);
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 }
 
 /*
@@ -317,7 +317,7 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work)
 	 * second; the bucket at cursor + 1 goes at now + 1s and so
 	 * on...
 	 */
-	spin_lock(&rxnet->peer_hash_lock);
+	spin_lock_bh(&rxnet->peer_hash_lock);
 	list_splice_init(&rxnet->peer_keepalive_new, &collector);
 
 	stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
@@ -329,7 +329,7 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work)
 	}
 
 	base = now;
-	spin_unlock(&rxnet->peer_hash_lock);
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 
 	rxnet->peer_keepalive_base = base;
 	rxnet->peer_keepalive_cursor = cursor;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index e1c63129586b..0fcc87f0409f 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -325,10 +325,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
 	hash_key = rxrpc_peer_hash_key(local, &peer->srx);
 	rxrpc_init_peer(local, peer, hash_key);
 
-	spin_lock(&rxnet->peer_hash_lock);
+	spin_lock_bh(&rxnet->peer_hash_lock);
 	hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
 	list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
-	spin_unlock(&rxnet->peer_hash_lock);
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 }
 
 /*
@@ -360,7 +360,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
 			return NULL;
 		}
 
-		spin_lock(&rxnet->peer_hash_lock);
+		spin_lock_bh(&rxnet->peer_hash_lock);
 
 		/* Need to check that we aren't racing with someone else */
 		peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
@@ -373,7 +373,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
 				      &rxnet->peer_keepalive_new);
 		}
 
-		spin_unlock(&rxnet->peer_hash_lock);
+		spin_unlock_bh(&rxnet->peer_hash_lock);
 
 		if (peer)
 			rxrpc_free_peer(candidate);
@@ -423,10 +423,10 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 
 	ASSERT(hlist_empty(&peer->error_targets));
 
-	spin_lock(&rxnet->peer_hash_lock);
+	spin_lock_bh(&rxnet->peer_hash_lock);
 	hash_del_rcu(&peer->hash_link);
 	list_del_init(&peer->keepalive_link);
-	spin_unlock(&rxnet->peer_hash_lock);
+	spin_unlock_bh(&rxnet->peer_hash_lock);
 
 	rxrpc_free_peer(peer);
 }
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0e8da909d4f2..584397aba4a0 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -707,7 +707,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	} else {
 		switch (rxrpc_call_state(call)) {
 		case RXRPC_CALL_CLIENT_AWAIT_CONN:
-		case RXRPC_CALL_SERVER_SECURING:
+		case RXRPC_CALL_SERVER_RECV_REQUEST:
 			if (p.command == RXRPC_CMD_SEND_ABORT)
 				break;
 			fallthrough;
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index f80bc05d4c5a..516038a44163 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -91,6 +91,8 @@ ets_class_from_arg(struct Qdisc *sch, unsigned long arg)
 {
 	struct ets_sched *q = qdisc_priv(sch);
 
+	if (arg == 0 || arg > q->nbands)
+		return NULL;
 	return &q->classes[arg - 1];
 }
 
diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c
index b50b2c2cc09b..e6bfd39ff339 100644
--- a/net/sched/sch_fifo.c
+++ b/net/sched/sch_fifo.c
@@ -40,6 +40,9 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 {
 	unsigned int prev_backlog;
 
+	if (unlikely(READ_ONCE(sch->limit) == 0))
+		return qdisc_drop(skb, sch, to_free);
+
 	if (likely(sch->q.qlen < READ_ONCE(sch->limit)))
 		return qdisc_enqueue_tail(skb, sch);
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 71ec9986ed37..fdd79d3ccd8c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -749,9 +749,9 @@ deliver:
 				if (err != NET_XMIT_SUCCESS) {
 					if (net_xmit_drop_count(err))
 						qdisc_qstats_drop(sch);
-					qdisc_tree_reduce_backlog(sch, 1, pkt_len);
 					sch->qstats.backlog -= pkt_len;
 					sch->q.qlen--;
+					qdisc_tree_reduce_backlog(sch, 1, pkt_len);
 				}
 				goto tfifo_dequeue;
 			}
diff --git a/net/socket.c b/net/socket.c
index 262a28b59c7f..28bae5a94234 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -479,6 +479,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 	sock->file = file;
 	file->private_data = sock;
 	stream_open(SOCK_INODE(sock), file);
+	/*
+	 * Disable permission and pre-content events, but enable legacy
+	 * inotify events for legacy users.
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
 	return file;
 }
 EXPORT_SYMBOL(sock_alloc_file);
diff --git a/net/sunrpc/auth_gss/Makefile b/net/sunrpc/auth_gss/Makefile
index ad1736d93b76..452f67deebc6 100644
--- a/net/sunrpc/auth_gss/Makefile
+++ b/net/sunrpc/auth_gss/Makefile
@@ -5,7 +5,7 @@
 
 obj-$(CONFIG_SUNRPC_GSS) += auth_rpcgss.o
 
-auth_rpcgss-y := auth_gss.o gss_generic_token.o \
+auth_rpcgss-y := auth_gss.o \
 	gss_mech_switch.o svcauth_gss.o \
 	gss_rpc_upcall.o gss_rpc_xdr.o trace.o
 
diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c
deleted file mode 100644
index 4a4082bb22ad..000000000000
--- a/net/sunrpc/auth_gss/gss_generic_token.c
+++ /dev/null
@@ -1,231 +0,0 @@
-/*
- *  linux/net/sunrpc/gss_generic_token.c
- *
- *  Adapted from MIT Kerberos 5-1.2.1 lib/gssapi/generic/util_token.c
- *
- *  Copyright (c) 2000 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson   <andros@umich.edu>
- */
-
-/*
- * Copyright 1993 by OpenVision Technologies, Inc.
- *
- * Permission to use, copy, modify, distribute, and sell this software
- * and its documentation for any purpose is hereby granted without fee,
- * provided that the above copyright notice appears in all copies and
- * that both that copyright notice and this permission notice appear in
- * supporting documentation, and that the name of OpenVision not be used
- * in advertising or publicity pertaining to distribution of the software
- * without specific, written prior permission. OpenVision makes no
- * representations about the suitability of this software for any
- * purpose.  It is provided "as is" without express or implied warranty.
- *
- * OPENVISION DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
- * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
- * EVENT SHALL OPENVISION BE LIABLE FOR ANY SPECIAL, INDIRECT OR
- * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF
- * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
- * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
- * PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/sunrpc/gss_asn1.h>
-
-
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-# define RPCDBG_FACILITY        RPCDBG_AUTH
-#endif
-
-
-/* TWRITE_STR from gssapiP_generic.h */
-#define TWRITE_STR(ptr, str, len) \
-	memcpy((ptr), (char *) (str), (len)); \
-	(ptr) += (len);
-
-/* XXXX this code currently makes the assumption that a mech oid will
-   never be longer than 127 bytes.  This assumption is not inherent in
-   the interfaces, so the code can be fixed if the OSI namespace
-   balloons unexpectedly. */
-
-/* Each token looks like this:
-
-0x60				tag for APPLICATION 0, SEQUENCE
-					(constructed, definite-length)
-	<length>		possible multiple bytes, need to parse/generate
-	0x06			tag for OBJECT IDENTIFIER
-		<moid_length>	compile-time constant string (assume 1 byte)
-		<moid_bytes>	compile-time constant string
-	<inner_bytes>		the ANY containing the application token
-					bytes 0,1 are the token type
-					bytes 2,n are the token data
-
-For the purposes of this abstraction, the token "header" consists of
-the sequence tag and length octets, the mech OID DER encoding, and the
-first two inner bytes, which indicate the token type.  The token
-"body" consists of everything else.
-
-*/
-
-static int
-der_length_size( int length)
-{
-	if (length < (1<<7))
-		return 1;
-	else if (length < (1<<8))
-		return 2;
-#if (SIZEOF_INT == 2)
-	else
-		return 3;
-#else
-	else if (length < (1<<16))
-		return 3;
-	else if (length < (1<<24))
-		return 4;
-	else
-		return 5;
-#endif
-}
-
-static void
-der_write_length(unsigned char **buf, int length)
-{
-	if (length < (1<<7)) {
-		*(*buf)++ = (unsigned char) length;
-	} else {
-		*(*buf)++ = (unsigned char) (der_length_size(length)+127);
-#if (SIZEOF_INT > 2)
-		if (length >= (1<<24))
-			*(*buf)++ = (unsigned char) (length>>24);
-		if (length >= (1<<16))
-			*(*buf)++ = (unsigned char) ((length>>16)&0xff);
-#endif
-		if (length >= (1<<8))
-			*(*buf)++ = (unsigned char) ((length>>8)&0xff);
-		*(*buf)++ = (unsigned char) (length&0xff);
-	}
-}
-
-/* returns decoded length, or < 0 on failure.  Advances buf and
-   decrements bufsize */
-
-static int
-der_read_length(unsigned char **buf, int *bufsize)
-{
-	unsigned char sf;
-	int ret;
-
-	if (*bufsize < 1)
-		return -1;
-	sf = *(*buf)++;
-	(*bufsize)--;
-	if (sf & 0x80) {
-		if ((sf &= 0x7f) > ((*bufsize)-1))
-			return -1;
-		if (sf > SIZEOF_INT)
-			return -1;
-		ret = 0;
-		for (; sf; sf--) {
-			ret = (ret<<8) + (*(*buf)++);
-			(*bufsize)--;
-		}
-	} else {
-		ret = sf;
-	}
-
-	return ret;
-}
-
-/* returns the length of a token, given the mech oid and the body size */
-
-int
-g_token_size(struct xdr_netobj *mech, unsigned int body_size)
-{
-	/* set body_size to sequence contents size */
-	body_size += 2 + (int) mech->len;         /* NEED overflow check */
-	return 1 + der_length_size(body_size) + body_size;
-}
-
-EXPORT_SYMBOL_GPL(g_token_size);
-
-/* fills in a buffer with the token header.  The buffer is assumed to
-   be the right size.  buf is advanced past the token header */
-
-void
-g_make_token_header(struct xdr_netobj *mech, int body_size, unsigned char **buf)
-{
-	*(*buf)++ = 0x60;
-	der_write_length(buf, 2 + mech->len + body_size);
-	*(*buf)++ = 0x06;
-	*(*buf)++ = (unsigned char) mech->len;
-	TWRITE_STR(*buf, mech->data, ((int) mech->len));
-}
-
-EXPORT_SYMBOL_GPL(g_make_token_header);
-
-/*
- * Given a buffer containing a token, reads and verifies the token,
- * leaving buf advanced past the token header, and setting body_size
- * to the number of remaining bytes.  Returns 0 on success,
- * G_BAD_TOK_HEADER for a variety of errors, and G_WRONG_MECH if the
- * mechanism in the token does not match the mech argument.  buf and
- * *body_size are left unmodified on error.
- */
-u32
-g_verify_token_header(struct xdr_netobj *mech, int *body_size,
-		      unsigned char **buf_in, int toksize)
-{
-	unsigned char *buf = *buf_in;
-	int seqsize;
-	struct xdr_netobj toid;
-	int ret = 0;
-
-	if ((toksize-=1) < 0)
-		return G_BAD_TOK_HEADER;
-	if (*buf++ != 0x60)
-		return G_BAD_TOK_HEADER;
-
-	if ((seqsize = der_read_length(&buf, &toksize)) < 0)
-		return G_BAD_TOK_HEADER;
-
-	if (seqsize != toksize)
-		return G_BAD_TOK_HEADER;
-
-	if ((toksize-=1) < 0)
-		return G_BAD_TOK_HEADER;
-	if (*buf++ != 0x06)
-		return G_BAD_TOK_HEADER;
-
-	if ((toksize-=1) < 0)
-		return G_BAD_TOK_HEADER;
-	toid.len = *buf++;
-
-	if ((toksize-=toid.len) < 0)
-		return G_BAD_TOK_HEADER;
-	toid.data = buf;
-	buf+=toid.len;
-
-	if (! g_OID_equal(&toid, mech))
-		ret = G_WRONG_MECH;
-
-   /* G_WRONG_MECH is not returned immediately because it's more important
-      to return G_BAD_TOK_HEADER if the token header is in fact bad */
-
-	if ((toksize-=2) < 0)
-		return G_BAD_TOK_HEADER;
-
-	if (ret)
-		return ret;
-
-	*buf_in = buf;
-	*body_size = toksize;
-
-	return ret;
-}
-
-EXPORT_SYMBOL_GPL(g_verify_token_header);
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index d2b02710ab07..9a27201638e2 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -442,35 +442,6 @@ encryptor(struct scatterlist *sg, void *data)
 	return 0;
 }
 
-int
-gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *buf,
-		    int offset, struct page **pages)
-{
-	int ret;
-	struct encryptor_desc desc;
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
-
-	BUG_ON((buf->len - offset) % crypto_sync_skcipher_blocksize(tfm) != 0);
-
-	skcipher_request_set_sync_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-
-	memset(desc.iv, 0, sizeof(desc.iv));
-	desc.req = req;
-	desc.pos = offset;
-	desc.outbuf = buf;
-	desc.pages = pages;
-	desc.fragno = 0;
-	desc.fraglen = 0;
-
-	sg_init_table(desc.infrags, 4);
-	sg_init_table(desc.outfrags, 4);
-
-	ret = xdr_process_buf(buf, offset, buf->len - offset, encryptor, &desc);
-	skcipher_request_zero(req);
-	return ret;
-}
-
 struct decryptor_desc {
 	u8 iv[GSS_KRB5_MAX_BLOCKSIZE];
 	struct skcipher_request *req;
@@ -525,32 +496,6 @@ decryptor(struct scatterlist *sg, void *data)
 	return 0;
 }
 
-int
-gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *buf,
-		    int offset)
-{
-	int ret;
-	struct decryptor_desc desc;
-	SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
-
-	/* XXXJBF: */
-	BUG_ON((buf->len - offset) % crypto_sync_skcipher_blocksize(tfm) != 0);
-
-	skcipher_request_set_sync_tfm(req, tfm);
-	skcipher_request_set_callback(req, 0, NULL, NULL);
-
-	memset(desc.iv, 0, sizeof(desc.iv));
-	desc.req = req;
-	desc.fragno = 0;
-	desc.fraglen = 0;
-
-	sg_init_table(desc.frags, 4);
-
-	ret = xdr_process_buf(buf, offset, buf->len - offset, decryptor, &desc);
-	skcipher_request_zero(req);
-	return ret;
-}
-
 /*
  * This function makes the assumption that it was ultimately called
  * from gss_wrap().
diff --git a/net/sunrpc/auth_gss/gss_krb5_internal.h b/net/sunrpc/auth_gss/gss_krb5_internal.h
index 3afd4065bf3d..a47e9ec228a5 100644
--- a/net/sunrpc/auth_gss/gss_krb5_internal.h
+++ b/net/sunrpc/auth_gss/gss_krb5_internal.h
@@ -172,13 +172,6 @@ u32 krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in,
 int xdr_extend_head(struct xdr_buf *buf, unsigned int base,
 		    unsigned int shiftlen);
 
-int gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm,
-			struct xdr_buf *outbuf, int offset,
-			struct page **pages);
-
-int gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm,
-			struct xdr_buf *inbuf, int offset);
-
 u32 gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset,
 			 struct xdr_buf *buf, struct page **pages);
 
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index fae632da1058..c84d0cf61980 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/oid_registry.h>
 #include <linux/sunrpc/msg_prot.h>
-#include <linux/sunrpc/gss_asn1.h>
 #include <linux/sunrpc/auth_gss.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/gss_err.h>
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 059f6ef1ad18..cb279eb9ac4b 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -281,21 +281,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
 	return rv;
 }
 
-/*
- * This is the generic cache management routine for all
- * the authentication caches.
- * It checks the currency of a cache item and will (later)
- * initiate an upcall to fill it if needed.
- *
- *
- * Returns 0 if the cache_head can be used, or cache_puts it and returns
- * -EAGAIN if upcall is pending and request has been queued
- * -ETIMEDOUT if upcall failed or request could not be queue or
- *           upcall completed but item is still invalid (implying that
- *           the cache item has been replaced with a newer one).
- * -ENOENT if cache entry was negative
- */
-int cache_check(struct cache_detail *detail,
+int cache_check_rcu(struct cache_detail *detail,
 		    struct cache_head *h, struct cache_req *rqstp)
 {
 	int rv;
@@ -336,6 +322,31 @@ int cache_check(struct cache_detail *detail,
 				rv = -ETIMEDOUT;
 		}
 	}
+
+	return rv;
+}
+EXPORT_SYMBOL_GPL(cache_check_rcu);
+
+/*
+ * This is the generic cache management routine for all
+ * the authentication caches.
+ * It checks the currency of a cache item and will (later)
+ * initiate an upcall to fill it if needed.
+ *
+ *
+ * Returns 0 if the cache_head can be used, or cache_puts it and returns
+ * -EAGAIN if upcall is pending and request has been queued
+ * -ETIMEDOUT if upcall failed or request could not be queue or
+ *           upcall completed but item is still invalid (implying that
+ *           the cache item has been replaced with a newer one).
+ * -ENOENT if cache entry was negative
+ */
+int cache_check(struct cache_detail *detail,
+		struct cache_head *h, struct cache_req *rqstp)
+{
+	int rv;
+
+	rv = cache_check_rcu(detail, h, rqstp);
 	if (rv)
 		cache_put(h, detail);
 	return rv;
@@ -1427,17 +1438,11 @@ static int c_show(struct seq_file *m, void *p)
 		seq_printf(m, "# expiry=%lld refcnt=%d flags=%lx\n",
 			   convert_to_wallclock(cp->expiry_time),
 			   kref_read(&cp->ref), cp->flags);
-	if (!cache_get_rcu(cp))
-		return 0;
 
-	if (cache_check(cd, cp, NULL))
-		/* cache_check does a cache_put on failure */
+	if (cache_check_rcu(cd, cp, NULL))
+		seq_puts(m, "# ");
+	else if (cache_is_expired(cd, cp))
 		seq_puts(m, "# ");
-	else {
-		if (cache_is_expired(cd, cp))
-			seq_puts(m, "# ");
-		cache_put(cp, cd);
-	}
 
 	return cd->cache_show(m, cd, cp);
 }
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 0090162ee8c3..2fe88ea79a70 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -958,12 +958,17 @@ void rpc_shutdown_client(struct rpc_clnt *clnt)
 
 	trace_rpc_clnt_shutdown(clnt);
 
+	clnt->cl_shutdown = 1;
 	while (!list_empty(&clnt->cl_tasks)) {
 		rpc_killall_tasks(clnt);
 		wait_event_timeout(destroy_wait,
 			list_empty(&clnt->cl_tasks), 1*HZ);
 	}
 
+	/* wait for tasks still in workqueue or waitqueue */
+	wait_event_timeout(destroy_wait,
+			   atomic_read(&clnt->cl_task_count) == 0, 1 * HZ);
+
 	rpc_release_client(clnt);
 }
 EXPORT_SYMBOL_GPL(rpc_shutdown_client);
@@ -1139,6 +1144,7 @@ void rpc_task_release_client(struct rpc_task *task)
 		list_del(&task->tk_task);
 		spin_unlock(&clnt->cl_lock);
 		task->tk_client = NULL;
+		atomic_dec(&clnt->cl_task_count);
 
 		rpc_release_client(clnt);
 	}
@@ -1189,10 +1195,7 @@ void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
 		task->tk_flags |= RPC_TASK_TIMEOUT;
 	if (clnt->cl_noretranstimeo)
 		task->tk_flags |= RPC_TASK_NO_RETRANS_TIMEOUT;
-	/* Add to the client's list of all tasks */
-	spin_lock(&clnt->cl_lock);
-	list_add_tail(&task->tk_task, &clnt->cl_tasks);
-	spin_unlock(&clnt->cl_lock);
+	atomic_inc(&clnt->cl_task_count);
 }
 
 static void
@@ -1787,9 +1790,14 @@ call_reserveresult(struct rpc_task *task)
 	if (status >= 0) {
 		if (task->tk_rqstp) {
 			task->tk_action = call_refresh;
+
+			/* Add to the client's list of all tasks */
+			spin_lock(&task->tk_client->cl_lock);
+			if (list_empty(&task->tk_task))
+				list_add_tail(&task->tk_task, &task->tk_client->cl_tasks);
+			spin_unlock(&task->tk_client->cl_lock);
 			return;
 		}
-
 		rpc_call_rpcerror(task, -EIO);
 		return;
 	}
@@ -1854,13 +1862,13 @@ call_refreshresult(struct rpc_task *task)
 		fallthrough;
 	case -EAGAIN:
 		status = -EACCES;
-		fallthrough;
-	case -EKEYEXPIRED:
 		if (!task->tk_cred_retry)
 			break;
 		task->tk_cred_retry--;
 		trace_rpc_retry_refresh_status(task);
 		return;
+	case -EKEYEXPIRED:
+		break;
 	case -ENOMEM:
 		rpc_delay(task, HZ >> 4);
 		return;
@@ -3319,8 +3327,11 @@ bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
 EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_has_addr);
 
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-static void rpc_show_header(void)
+static void rpc_show_header(struct rpc_clnt *clnt)
 {
+	printk(KERN_INFO "clnt[%pISpc] RPC tasks[%d]\n",
+	       (struct sockaddr *)&clnt->cl_xprt->addr,
+	       atomic_read(&clnt->cl_task_count));
 	printk(KERN_INFO "-pid- flgs status -client- --rqstp- "
 		"-timeout ---ops--\n");
 }
@@ -3352,7 +3363,7 @@ void rpc_show_tasks(struct net *net)
 		spin_lock(&clnt->cl_lock);
 		list_for_each_entry(task, &clnt->cl_tasks, tk_task) {
 			if (!header) {
-				rpc_show_header();
+				rpc_show_header(clnt);
 				header++;
 			}
 			rpc_show_task(clnt, task);
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index a176d5a0b0ee..32417db340de 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -74,6 +74,9 @@ tasks_stop(struct seq_file *f, void *v)
 {
 	struct rpc_clnt *clnt = f->private;
 	spin_unlock(&clnt->cl_lock);
+	seq_printf(f, "clnt[%pISpc] RPC tasks[%d]\n",
+		   (struct sockaddr *)&clnt->cl_xprt->addr,
+		   atomic_read(&clnt->cl_task_count));
 }
 
 static const struct seq_operations tasks_seq_operations = {
@@ -179,6 +182,18 @@ xprt_info_show(struct seq_file *f, void *v)
 	seq_printf(f, "addr:  %s\n", xprt->address_strings[RPC_DISPLAY_ADDR]);
 	seq_printf(f, "port:  %s\n", xprt->address_strings[RPC_DISPLAY_PORT]);
 	seq_printf(f, "state: 0x%lx\n", xprt->state);
+	seq_printf(f, "netns: %u\n", xprt->xprt_net->ns.inum);
+
+	if (xprt->ops->get_srcaddr) {
+		int ret, buflen;
+		char buf[INET6_ADDRSTRLEN];
+
+		buflen = ARRAY_SIZE(buf);
+		ret = xprt->ops->get_srcaddr(xprt, buf, buflen);
+		if (ret < 0)
+			ret = sprintf(buf, "<closed>");
+		seq_printf(f, "saddr: %.*s\n", ret, buf);
+	}
 	return 0;
 }
 
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 7ce3721c06ca..eadc00410ebc 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -630,7 +630,7 @@ static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry)
 static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent,
 					  const char *name)
 {
-	struct qstr q = QSTR_INIT(name, strlen(name));
+	struct qstr q = QSTR(name);
 	struct dentry *dentry = d_hash_and_lookup(parent, &q);
 	if (!dentry) {
 		dentry = d_alloc(parent, &q);
@@ -1190,8 +1190,7 @@ static const struct rpc_filelist files[] = {
 struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
 			       const unsigned char *dir_name)
 {
-	struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name));
-	return d_hash_and_lookup(sb->s_root, &dir);
+	return d_hash_and_lookup(sb->s_root, &QSTR(dir_name));
 }
 EXPORT_SYMBOL_GPL(rpc_d_lookup_sb);
 
@@ -1300,11 +1299,9 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
 	struct dentry *gssd_dentry;
 	struct dentry *clnt_dentry = NULL;
 	struct dentry *pipe_dentry = NULL;
-	struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name,
-				  strlen(files[RPCAUTH_gssd].name));
 
 	/* We should never get this far if "gssd" doesn't exist */
-	gssd_dentry = d_hash_and_lookup(root, &q);
+	gssd_dentry = d_hash_and_lookup(root, &QSTR(files[RPCAUTH_gssd].name));
 	if (!gssd_dentry)
 		return ERR_PTR(-ENOENT);
 
@@ -1314,9 +1311,8 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
 		goto out;
 	}
 
-	q.name = gssd_dummy_clnt_dir[0].name;
-	q.len = strlen(gssd_dummy_clnt_dir[0].name);
-	clnt_dentry = d_hash_and_lookup(gssd_dentry, &q);
+	clnt_dentry = d_hash_and_lookup(gssd_dentry,
+					&QSTR(gssd_dummy_clnt_dir[0].name));
 	if (!clnt_dentry) {
 		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
 		pipe_dentry = ERR_PTR(-ENOENT);
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 79879b7d39cb..e7f9c295d13c 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -651,8 +651,8 @@ svc_init_buffer(struct svc_rqst *rqstp, unsigned int size, int node)
 	if (pages > RPCSVC_MAXPAGES)
 		pages = RPCSVC_MAXPAGES;
 
-	ret = alloc_pages_bulk_array_node(GFP_KERNEL, node, pages,
-					  rqstp->rq_pages);
+	ret = alloc_pages_bulk_node(GFP_KERNEL, node, pages,
+				    rqstp->rq_pages);
 	return ret == pages;
 }
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 43c57124de52..ae25405d8bd2 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -606,7 +606,8 @@ int svc_port_is_privileged(struct sockaddr *sin)
 }
 
 /*
- * Make sure that we don't have too many active connections. If we have,
+ * Make sure that we don't have too many connections that have not yet
+ * demonstrated that they have access to the NFS server. If we have,
  * something must be dropped. It's not clear what will happen if we allow
  * "too many" connections, but when dealing with network-facing software,
  * we have to code defensively. Here we do that by imposing hard limits.
@@ -618,34 +619,26 @@ int svc_port_is_privileged(struct sockaddr *sin)
  * The only somewhat efficient mechanism would be if drop old
  * connections from the same IP first. But right now we don't even
  * record the client IP in svc_sock.
- *
- * single-threaded services that expect a lot of clients will probably
- * need to set sv_maxconn to override the default value which is based
- * on the number of threads
  */
 static void svc_check_conn_limits(struct svc_serv *serv)
 {
-	unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn :
-				(serv->sv_nrthreads+3) * 20;
-
-	if (serv->sv_tmpcnt > limit) {
-		struct svc_xprt *xprt = NULL;
+	if (serv->sv_tmpcnt > XPT_MAX_TMP_CONN) {
+		struct svc_xprt *xprt = NULL, *xprti;
 		spin_lock_bh(&serv->sv_lock);
 		if (!list_empty(&serv->sv_tempsocks)) {
-			/* Try to help the admin */
-			net_notice_ratelimited("%s: too many open connections, consider increasing the %s\n",
-					       serv->sv_name, serv->sv_maxconn ?
-					       "max number of connections" :
-					       "number of threads");
 			/*
 			 * Always select the oldest connection. It's not fair,
-			 * but so is life
+			 * but nor is life.
 			 */
-			xprt = list_entry(serv->sv_tempsocks.prev,
-					  struct svc_xprt,
-					  xpt_list);
-			set_bit(XPT_CLOSE, &xprt->xpt_flags);
-			svc_xprt_get(xprt);
+			list_for_each_entry_reverse(xprti, &serv->sv_tempsocks,
+						    xpt_list) {
+				if (!test_bit(XPT_PEER_VALID, &xprti->xpt_flags)) {
+					xprt = xprti;
+					set_bit(XPT_CLOSE, &xprt->xpt_flags);
+					svc_xprt_get(xprt);
+					break;
+				}
+			}
 		}
 		spin_unlock_bh(&serv->sv_lock);
 
@@ -671,8 +664,7 @@ static bool svc_alloc_arg(struct svc_rqst *rqstp)
 	}
 
 	for (filled = 0; filled < pages; filled = ret) {
-		ret = alloc_pages_bulk_array(GFP_KERNEL, pages,
-					     rqstp->rq_pages);
+		ret = alloc_pages_bulk(GFP_KERNEL, pages, rqstp->rq_pages);
 		if (ret > filled)
 			/* Made progress, don't sleep yet */
 			continue;
@@ -1039,7 +1031,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt)
 
 	spin_lock_bh(&serv->sv_lock);
 	list_del_init(&xprt->xpt_list);
-	if (test_bit(XPT_TEMP, &xprt->xpt_flags))
+	if (test_bit(XPT_TEMP, &xprt->xpt_flags) &&
+	    !test_bit(XPT_PEER_VALID, &xprt->xpt_flags))
 		serv->sv_tmpcnt--;
 	spin_unlock_bh(&serv->sv_lock);
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 95397677673b..cb3bd12f5818 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1083,9 +1083,6 @@ static void svc_tcp_fragment_received(struct svc_sock *svsk)
 	/* If we have more data, signal svc_xprt_enqueue() to try again */
 	svsk->sk_tcplen = 0;
 	svsk->sk_marker = xdr_zero;
-
-	smp_wmb();
-	tcp_set_rcvlowat(svsk->sk_sk, 1);
 }
 
 /**
@@ -1175,17 +1172,10 @@ err_incomplete:
 		goto err_delete;
 	if (len == want)
 		svc_tcp_fragment_received(svsk);
-	else {
-		/* Avoid more ->sk_data_ready() calls until the rest
-		 * of the message has arrived. This reduces service
-		 * thread wake-ups on large incoming messages. */
-		tcp_set_rcvlowat(svsk->sk_sk,
-				 svc_sock_reclen(svsk) - svsk->sk_tcplen);
-
+	else
 		trace_svcsock_tcp_recv_short(&svsk->sk_xprt,
 				svc_sock_reclen(svsk),
 				svsk->sk_tcplen - sizeof(rpc_fraghdr));
-	}
 	goto err_noclose;
 error:
 	if (len != -EAGAIN)
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 62e07c330a66..4e003cb516fe 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -1097,6 +1097,12 @@ out_overflow:
  * Checks that we have enough buffer space to encode 'nbytes' more
  * bytes of data. If so, update the total xdr_buf length, and
  * adjust the length of the current kvec.
+ *
+ * The returned pointer is valid only until the next call to
+ * xdr_reserve_space() or xdr_commit_encode() on @xdr. The current
+ * implementation of this API guarantees that space reserved for a
+ * four-byte data item remains valid until @xdr is destroyed, but
+ * that might not always be true in the future.
  */
 __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 {
diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c
index 720d3ba742ec..7e98d4dd9f10 100644
--- a/net/sunrpc/xprtmultipath.c
+++ b/net/sunrpc/xprtmultipath.c
@@ -603,23 +603,6 @@ struct rpc_xprt *xprt_iter_get_helper(struct rpc_xprt_iter *xpi,
 }
 
 /**
- * xprt_iter_get_xprt - Returns the rpc_xprt pointed to by the cursor
- * @xpi: pointer to rpc_xprt_iter
- *
- * Returns a reference to the struct rpc_xprt that is currently
- * pointed to by the cursor.
- */
-struct rpc_xprt *xprt_iter_get_xprt(struct rpc_xprt_iter *xpi)
-{
-	struct rpc_xprt *xprt;
-
-	rcu_read_lock();
-	xprt = xprt_iter_get_helper(xpi, xprt_iter_ops(xpi)->xpi_xprt);
-	rcu_read_unlock();
-	return xprt;
-}
-
-/**
  * xprt_iter_get_next - Returns the next rpc_xprt following the cursor
  * @xpi: pointer to rpc_xprt_iter
  *
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index fa9d1b49599b..075695173648 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -337,7 +337,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
 
 void vsock_remove_sock(struct vsock_sock *vsk)
 {
-	vsock_remove_bound(vsk);
+	/* Transport reassignment must not remove the binding. */
+	if (sock_flag(sk_vsock(vsk), SOCK_DEAD))
+		vsock_remove_bound(vsk);
+
 	vsock_remove_connected(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_remove_sock);
@@ -821,12 +824,13 @@ static void __vsock_release(struct sock *sk, int level)
 	 */
 	lock_sock_nested(sk, level);
 
+	sock_orphan(sk);
+
 	if (vsk->transport)
 		vsk->transport->release(vsk);
 	else if (sock_type_connectible(sk->sk_type))
 		vsock_remove_sock(vsk);
 
-	sock_orphan(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	skb_queue_purge(&sk->sk_receive_queue);
@@ -1519,6 +1523,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 		if (err < 0)
 			goto out;
 
+		/* sk_err might have been set as a result of an earlier
+		 * (failed) connect attempt.
+		 */
+		sk->sk_err = 0;
+
 		/* Mark sock as connecting and set the error code to in
 		 * progress in case this is a non-blocking connect.
 		 */
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 70857018f020..12b780de8779 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -143,10 +143,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 	if (result)
 		return result;
 
-	if (!IS_ERR_OR_NULL(rdev->wiphy.debugfsdir))
-		debugfs_rename(rdev->wiphy.debugfsdir->d_parent,
-			       rdev->wiphy.debugfsdir,
-			       rdev->wiphy.debugfsdir->d_parent, newname);
+	debugfs_change_name(rdev->wiphy.debugfsdir, "%s", newname);
 
 	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
 
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 3bb04b05c5ce..bea70eb6f034 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -640,10 +640,8 @@ EXPORT_SYMBOL(wireless_send_event);
 #ifdef CONFIG_CFG80211_WEXT
 static void wireless_warn_cfg80211_wext(void)
 {
-	char name[sizeof(current->comm)];
-
 	pr_warn_once("warning: `%s' uses wireless extensions which will stop working for Wi-Fi 7 hardware; use nl80211\n",
-		     get_task_comm(name, current));
+		     current->comm);
 }
 #endif
 
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 98f1e2b67c76..c397eb99d867 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -506,7 +506,7 @@ xmit:
 	skb_dst_set(skb, dst);
 	skb->dev = tdev;
 
-	err = dst_output(xi->net, skb->sk, skb);
+	err = dst_output(xi->net, skb_to_full_sk(skb), skb);
 	if (net_xmit_eval(err) == 0) {
 		dev_sw_netstats_tx_add(dev, 1, length);
 	} else {
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index b5025cf6136e..f7abd42c077d 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -802,7 +802,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 	     !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
 		skb->protocol = htons(ETH_P_IP);
 
-		if (skb->sk)
+		if (skb->sk && sk_fullsock(skb->sk))
 			xfrm_local_error(skb, mtu);
 		else
 			icmp_send(skb, ICMP_DEST_UNREACH,
@@ -838,6 +838,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 {
 	int mtu, ret = 0;
 	struct dst_entry *dst = skb_dst(skb);
+	struct sock *sk = skb_to_full_sk(skb);
 
 	if (skb->ignore_df)
 		goto out;
@@ -852,9 +853,9 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 		skb->dev = dst->dev;
 		skb->protocol = htons(ETH_P_IPV6);
 
-		if (xfrm6_local_dontfrag(skb->sk))
+		if (xfrm6_local_dontfrag(sk))
 			ipv6_stub->xfrm6_local_rxpmtu(skb, mtu);
-		else if (skb->sk)
+		else if (sk)
 			xfrm_local_error(skb, mtu);
 		else
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 9e510021ee91..6551e588fe52 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2964,7 +2964,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 
-		dst_output(net, skb->sk, skb);
+		dst_output(net, skb_to_full_sk(skb), skb);
 	}
 
 out:
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index e500aebbad22..dbdf8a39dffe 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -714,10 +714,12 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
 			oseq += skb_shinfo(skb)->gso_segs;
 		}
 
-		if (unlikely(xo->seq.low < replay_esn->oseq)) {
-			XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
-			xo->seq.hi = oseq_hi;
-			replay_esn->oseq_hi = oseq_hi;
+		if (unlikely(oseq < replay_esn->oseq)) {
+			replay_esn->oseq_hi = ++oseq_hi;
+			if (xo->seq.low < replay_esn->oseq) {
+				XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+				xo->seq.hi = oseq_hi;
+			}
 			if (replay_esn->oseq_hi == 0) {
 				replay_esn->oseq--;
 				replay_esn->oseq_hi--;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 34067cb8a479..ad2202fa82f3 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -34,6 +34,8 @@
 
 #define xfrm_state_deref_prot(table, net) \
 	rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+#define xfrm_state_deref_check(table, net) \
+	rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
 
 static void xfrm_state_gc_task(struct work_struct *work);
 
@@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net,
 					 u32 reqid,
 					 unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
 }
 
@@ -70,6 +74,8 @@ static inline unsigned int xfrm_src_hash(struct net *net,
 					 const xfrm_address_t *saddr,
 					 unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
 }
 
@@ -77,11 +83,15 @@ static inline unsigned int
 xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
 	      __be32 spi, u8 proto, unsigned short family)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
 }
 
 static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
 {
+	lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
 	return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
 }
 
@@ -1108,16 +1118,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 	x->props.family = tmpl->encap_family;
 }
 
-static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
+struct xfrm_hash_state_ptrs {
+	const struct hlist_head *bydst;
+	const struct hlist_head *bysrc;
+	const struct hlist_head *byspi;
+	unsigned int hmask;
+};
+
+static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs)
+{
+	unsigned int sequence;
+
+	do {
+		sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+		ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net);
+		ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net);
+		ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net);
+		ptrs->hmask = net->xfrm.state_hmask;
+	} while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence));
+}
+
+static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs,
+						  u32 mark,
 						  const xfrm_address_t *daddr,
 						  __be32 spi, u8 proto,
 						  unsigned short family,
 						  struct xfrm_dev_offload *xdo)
 {
-	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+	hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1151,15 +1183,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
 	return NULL;
 }
 
-static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs,
+					      u32 mark,
 					      const xfrm_address_t *daddr,
 					      __be32 spi, u8 proto,
 					      unsigned short family)
 {
-	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+	unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+	hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
 		    x->id.proto     != proto ||
@@ -1181,11 +1214,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 					   __be32 spi, u8 proto,
 					   unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct hlist_head *state_cache_input;
 	struct xfrm_state *x = NULL;
-	int cpu = get_cpu();
 
-	state_cache_input =  per_cpu_ptr(net->xfrm.state_cache_input, cpu);
+	state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
@@ -1202,7 +1235,9 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 		goto out;
 	}
 
-	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
 
 	if (x && x->km.state == XFRM_STATE_VALID) {
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -1217,20 +1252,20 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
 
 out:
 	rcu_read_unlock();
-	put_cpu();
 	return x;
 }
 EXPORT_SYMBOL(xfrm_input_state_lookup);
 
-static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs,
+						     u32 mark,
 						     const xfrm_address_t *daddr,
 						     const xfrm_address_t *saddr,
 						     u8 proto, unsigned short family)
 {
-	unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
+	unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
+	hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) {
 		if (x->props.family != family ||
 		    x->id.proto     != proto ||
 		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
@@ -1250,14 +1285,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 static inline struct xfrm_state *
 __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct net *net = xs_net(x);
 	u32 mark = x->mark.v & x->mark.m;
 
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
 	if (use_spi)
-		return __xfrm_state_lookup(net, mark, &x->id.daddr,
+		return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr,
 					   x->id.spi, x->id.proto, family);
 	else
-		return __xfrm_state_lookup_byaddr(net, mark,
+		return __xfrm_state_lookup_byaddr(&state_ptrs, mark,
 						  &x->id.daddr,
 						  &x->props.saddr,
 						  x->id.proto, family);
@@ -1331,6 +1369,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		unsigned short family, u32 if_id)
 {
 	static xfrm_address_t saddr_wildcard = { };
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct net *net = xp_net(pol);
 	unsigned int h, h_wildcard;
 	struct xfrm_state *x, *x0, *to_put;
@@ -1395,8 +1434,10 @@ cached:
 	else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */
 		WARN_ON(1);
 
-	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask);
+	hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1429,8 +1470,9 @@ cached:
 	if (best || acquire_in_progress)
 		goto found;
 
-	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
-	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
+	h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid,
+				     encap_family, state_ptrs.hmask);
+	hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) {
 #ifdef CONFIG_XFRM_OFFLOAD
 		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1468,7 +1510,7 @@ found:
 
 	if (!x && !error && !acquire_in_progress) {
 		if (tmpl->id.spi &&
-		    (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+		    (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr,
 						  tmpl->id.spi, tmpl->id.proto,
 						  encap_family,
 						  &pol->xdo)) != NULL) {
@@ -2253,10 +2295,13 @@ struct xfrm_state *
 xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
 		  u8 proto, unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct xfrm_state *x;
 
 	rcu_read_lock();
-	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
 	rcu_read_unlock();
 	return x;
 }
@@ -2267,10 +2312,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 			 const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 			 u8 proto, unsigned short family)
 {
+	struct xfrm_hash_state_ptrs state_ptrs;
 	struct xfrm_state *x;
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
+
+	xfrm_hash_ptrs_get(net, &state_ptrs);
+
+	x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	return x;
 }
diff --git a/rust/Makefile b/rust/Makefile
index 71a05a3c895a..ea3849eb78f6 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -144,7 +144,7 @@ rusttestlib-kernel: private rustc_target_flags = --extern ffi \
     --extern bindings --extern uapi
 rusttestlib-kernel: $(src)/kernel/lib.rs \
     rusttestlib-bindings rusttestlib-uapi rusttestlib-build_error \
-    $(obj)/libmacros.so $(obj)/bindings.o FORCE
+    $(obj)/$(libmacros_name) $(obj)/bindings.o FORCE
 	+$(call if_changed,rustc_test_library)
 
 rusttestlib-bindings: private rustc_target_flags = --extern ffi
@@ -240,6 +240,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \
 	-fzero-call-used-regs=% -fno-stack-clash-protection \
 	-fno-inline-functions-called-once -fsanitize=bounds-strict \
 	-fstrict-flex-arrays=% -fmin-function-alignment=% \
+	-fzero-init-padding-bits=% \
 	--param=% --param asan-%
 
 # Derived from `scripts/Makefile.clang`.
@@ -331,10 +332,11 @@ $(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ;
 $(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers/helpers.c FORCE
 	$(call if_changed_dep,bindgen)
 
+rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ && $$3!~/__odr_asan/ { printf $(2),$$3 }'
+
 quiet_cmd_exports = EXPORTS $@
       cmd_exports = \
-	$(NM) -p --defined-only $< \
-		| awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ {printf "EXPORT_SYMBOL_RUST_GPL(%s);\n",$$3}' > $@
+	$(call rust_exports,$<,"EXPORT_SYMBOL_RUST_GPL(%s);\n") > $@
 
 $(obj)/exports_core_generated.h: $(obj)/core.o FORCE
 	$(call if_changed,exports)
@@ -403,11 +405,36 @@ ifneq ($(or $(CONFIG_ARM64),$(and $(CONFIG_RISCV),$(CONFIG_64BIT))),)
 		__ashlti3 __lshrti3
 endif
 
+ifdef CONFIG_MODVERSIONS
+cmd_gendwarfksyms = $(if $(skip_gendwarfksyms),, \
+	$(call rust_exports,$@,"%s\n") | \
+	scripts/gendwarfksyms/gendwarfksyms \
+		$(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable) \
+		$(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes),) \
+		$@ >> $(dot-target).cmd)
+endif
+
 define rule_rustc_library
 	$(call cmd_and_fixdep,rustc_library)
 	$(call cmd,gen_objtooldep)
+	$(call cmd,gendwarfksyms)
 endef
 
+define rule_rust_cc_library
+	$(call if_changed_rule,cc_o_c)
+	$(call cmd,force_checksrc)
+	$(call cmd,gendwarfksyms)
+endef
+
+# helpers.o uses the same export mechanism as Rust libraries, so ensure symbol
+# versions are calculated for the helpers too.
+$(obj)/helpers/helpers.o: $(src)/helpers/helpers.c $(recordmcount_source) FORCE
+	+$(call if_changed_rule,rust_cc_library)
+
+# Disable symbol versioning for exports.o to avoid conflicts with the actual
+# symbol versions generated from Rust objects.
+$(obj)/exports.o: private skip_gendwarfksyms = 1
+
 $(obj)/core.o: private skip_clippy = 1
 $(obj)/core.o: private skip_flags = -Wunreachable_pub
 $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym))
@@ -419,13 +446,16 @@ ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),)
 $(obj)/core.o: scripts/target.json
 endif
 
+$(obj)/compiler_builtins.o: private skip_gendwarfksyms = 1
 $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*'
 $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
+$(obj)/build_error.o: private skip_gendwarfksyms = 1
 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
+$(obj)/ffi.o: private skip_gendwarfksyms = 1
 $(obj)/ffi.o: $(src)/ffi.rs $(obj)/compiler_builtins.o FORCE
 	+$(call if_changed_rule,rustc_library)
 
@@ -437,6 +467,7 @@ $(obj)/bindings.o: $(src)/bindings/lib.rs \
 	+$(call if_changed_rule,rustc_library)
 
 $(obj)/uapi.o: private rustc_target_flags = --extern ffi
+$(obj)/uapi.o: private skip_gendwarfksyms = 1
 $(obj)/uapi.o: $(src)/uapi/lib.rs \
     $(obj)/ffi.o \
     $(obj)/uapi/uapi_generated.rs FORCE
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 5c4dfe22f41a..55354e4dec14 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -20,9 +20,13 @@
 #include <linux/jump_label.h>
 #include <linux/mdio.h>
 #include <linux/miscdevice.h>
+#include <linux/of_device.h>
+#include <linux/pci.h>
 #include <linux/phy.h>
 #include <linux/pid_namespace.h>
+#include <linux/platform_device.h>
 #include <linux/poll.h>
+#include <linux/property.h>
 #include <linux/refcount.h>
 #include <linux/sched.h>
 #include <linux/security.h>
diff --git a/rust/helpers/device.c b/rust/helpers/device.c
new file mode 100644
index 000000000000..b2135c6686b0
--- /dev/null
+++ b/rust/helpers/device.c
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/device.h>
+
+int rust_helper_devm_add_action(struct device *dev,
+				void (*action)(void *),
+				void *data)
+{
+	return devm_add_action(dev, action, data);
+}
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index dcf827a61b52..0640b7e115be 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -12,14 +12,19 @@
 #include "build_assert.c"
 #include "build_bug.c"
 #include "cred.c"
+#include "device.c"
 #include "err.c"
 #include "fs.c"
+#include "io.c"
 #include "jump_label.c"
 #include "kunit.c"
 #include "mutex.c"
 #include "page.c"
+#include "platform.c"
+#include "pci.c"
 #include "pid_namespace.c"
 #include "rbtree.c"
+#include "rcu.c"
 #include "refcount.c"
 #include "security.c"
 #include "signal.c"
diff --git a/rust/helpers/io.c b/rust/helpers/io.c
new file mode 100644
index 000000000000..4c2401ccd720
--- /dev/null
+++ b/rust/helpers/io.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/io.h>
+
+void __iomem *rust_helper_ioremap(phys_addr_t offset, size_t size)
+{
+	return ioremap(offset, size);
+}
+
+void rust_helper_iounmap(volatile void __iomem *addr)
+{
+	iounmap(addr);
+}
+
+u8 rust_helper_readb(const volatile void __iomem *addr)
+{
+	return readb(addr);
+}
+
+u16 rust_helper_readw(const volatile void __iomem *addr)
+{
+	return readw(addr);
+}
+
+u32 rust_helper_readl(const volatile void __iomem *addr)
+{
+	return readl(addr);
+}
+
+#ifdef CONFIG_64BIT
+u64 rust_helper_readq(const volatile void __iomem *addr)
+{
+	return readq(addr);
+}
+#endif
+
+void rust_helper_writeb(u8 value, volatile void __iomem *addr)
+{
+	writeb(value, addr);
+}
+
+void rust_helper_writew(u16 value, volatile void __iomem *addr)
+{
+	writew(value, addr);
+}
+
+void rust_helper_writel(u32 value, volatile void __iomem *addr)
+{
+	writel(value, addr);
+}
+
+#ifdef CONFIG_64BIT
+void rust_helper_writeq(u64 value, volatile void __iomem *addr)
+{
+	writeq(value, addr);
+}
+#endif
+
+u8 rust_helper_readb_relaxed(const volatile void __iomem *addr)
+{
+	return readb_relaxed(addr);
+}
+
+u16 rust_helper_readw_relaxed(const volatile void __iomem *addr)
+{
+	return readw_relaxed(addr);
+}
+
+u32 rust_helper_readl_relaxed(const volatile void __iomem *addr)
+{
+	return readl_relaxed(addr);
+}
+
+#ifdef CONFIG_64BIT
+u64 rust_helper_readq_relaxed(const volatile void __iomem *addr)
+{
+	return readq_relaxed(addr);
+}
+#endif
+
+void rust_helper_writeb_relaxed(u8 value, volatile void __iomem *addr)
+{
+	writeb_relaxed(value, addr);
+}
+
+void rust_helper_writew_relaxed(u16 value, volatile void __iomem *addr)
+{
+	writew_relaxed(value, addr);
+}
+
+void rust_helper_writel_relaxed(u32 value, volatile void __iomem *addr)
+{
+	writel_relaxed(value, addr);
+}
+
+#ifdef CONFIG_64BIT
+void rust_helper_writeq_relaxed(u64 value, volatile void __iomem *addr)
+{
+	writeq_relaxed(value, addr);
+}
+#endif
diff --git a/rust/helpers/pci.c b/rust/helpers/pci.c
new file mode 100644
index 000000000000..8ba22f911459
--- /dev/null
+++ b/rust/helpers/pci.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pci.h>
+
+void rust_helper_pci_set_drvdata(struct pci_dev *pdev, void *data)
+{
+	pci_set_drvdata(pdev, data);
+}
+
+void *rust_helper_pci_get_drvdata(struct pci_dev *pdev)
+{
+	return pci_get_drvdata(pdev);
+}
+
+resource_size_t rust_helper_pci_resource_len(struct pci_dev *pdev, int bar)
+{
+	return pci_resource_len(pdev, bar);
+}
diff --git a/rust/helpers/platform.c b/rust/helpers/platform.c
new file mode 100644
index 000000000000..ab9b9f317301
--- /dev/null
+++ b/rust/helpers/platform.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/platform_device.h>
+
+void *rust_helper_platform_get_drvdata(const struct platform_device *pdev)
+{
+	return platform_get_drvdata(pdev);
+}
+
+void rust_helper_platform_set_drvdata(struct platform_device *pdev, void *data)
+{
+	platform_set_drvdata(pdev, data);
+}
diff --git a/rust/helpers/rcu.c b/rust/helpers/rcu.c
new file mode 100644
index 000000000000..f1cec6583513
--- /dev/null
+++ b/rust/helpers/rcu.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/rcupdate.h>
+
+void rust_helper_rcu_read_lock(void)
+{
+	rcu_read_lock();
+}
+
+void rust_helper_rcu_read_unlock(void)
+{
+	rcu_read_unlock();
+}
diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs
index d5e6a19ff6b7..db2d9658ba47 100644
--- a/rust/kernel/device.rs
+++ b/rust/kernel/device.rs
@@ -6,6 +6,7 @@
 
 use crate::{
     bindings,
+    str::CStr,
     types::{ARef, Opaque},
 };
 use core::{fmt, ptr};
@@ -180,6 +181,12 @@ impl Device {
             )
         };
     }
+
+    /// Checks if property is present or not.
+    pub fn property_present(&self, name: &CStr) -> bool {
+        // SAFETY: By the invariant of `CStr`, `name` is null-terminated.
+        unsafe { bindings::device_property_present(self.as_raw().cast_const(), name.as_char_ptr()) }
+    }
 }
 
 // SAFETY: Instances of `Device` are always reference-counted.
diff --git a/rust/kernel/device_id.rs b/rust/kernel/device_id.rs
new file mode 100644
index 000000000000..e5859217a579
--- /dev/null
+++ b/rust/kernel/device_id.rs
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Generic implementation of device IDs.
+//!
+//! Each bus / subsystem that matches device and driver through a bus / subsystem specific ID is
+//! expected to implement [`RawDeviceId`].
+
+use core::mem::MaybeUninit;
+
+/// Marker trait to indicate a Rust device ID type represents a corresponding C device ID type.
+///
+/// This is meant to be implemented by buses/subsystems so that they can use [`IdTable`] to
+/// guarantee (at compile-time) zero-termination of device id tables provided by drivers.
+///
+/// # Safety
+///
+/// Implementers must ensure that:
+///   - `Self` is layout-compatible with [`RawDeviceId::RawType`]; i.e. it's safe to transmute to
+///     `RawDeviceId`.
+///
+///     This requirement is needed so `IdArray::new` can convert `Self` to `RawType` when building
+///     the ID table.
+///
+///     Ideally, this should be achieved using a const function that does conversion instead of
+///     transmute; however, const trait functions relies on `const_trait_impl` unstable feature,
+///     which is broken/gone in Rust 1.73.
+///
+///   - `DRIVER_DATA_OFFSET` is the offset of context/data field of the device ID (usually named
+///     `driver_data`) of the device ID, the field is suitable sized to write a `usize` value.
+///
+///     Similar to the previous requirement, the data should ideally be added during `Self` to
+///     `RawType` conversion, but there's currently no way to do it when using traits in const.
+pub unsafe trait RawDeviceId {
+    /// The raw type that holds the device id.
+    ///
+    /// Id tables created from [`Self`] are going to hold this type in its zero-terminated array.
+    type RawType: Copy;
+
+    /// The offset to the context/data field.
+    const DRIVER_DATA_OFFSET: usize;
+
+    /// The index stored at `DRIVER_DATA_OFFSET` of the implementor of the [`RawDeviceId`] trait.
+    fn index(&self) -> usize;
+}
+
+/// A zero-terminated device id array.
+#[repr(C)]
+pub struct RawIdArray<T: RawDeviceId, const N: usize> {
+    ids: [T::RawType; N],
+    sentinel: MaybeUninit<T::RawType>,
+}
+
+impl<T: RawDeviceId, const N: usize> RawIdArray<T, N> {
+    #[doc(hidden)]
+    pub const fn size(&self) -> usize {
+        core::mem::size_of::<Self>()
+    }
+}
+
+/// A zero-terminated device id array, followed by context data.
+#[repr(C)]
+pub struct IdArray<T: RawDeviceId, U, const N: usize> {
+    raw_ids: RawIdArray<T, N>,
+    id_infos: [U; N],
+}
+
+impl<T: RawDeviceId, U, const N: usize> IdArray<T, U, N> {
+    /// Creates a new instance of the array.
+    ///
+    /// The contents are derived from the given identifiers and context information.
+    pub const fn new(ids: [(T, U); N]) -> Self {
+        let mut raw_ids = [const { MaybeUninit::<T::RawType>::uninit() }; N];
+        let mut infos = [const { MaybeUninit::uninit() }; N];
+
+        let mut i = 0usize;
+        while i < N {
+            // SAFETY: by the safety requirement of `RawDeviceId`, we're guaranteed that `T` is
+            // layout-wise compatible with `RawType`.
+            raw_ids[i] = unsafe { core::mem::transmute_copy(&ids[i].0) };
+            // SAFETY: by the safety requirement of `RawDeviceId`, this would be effectively
+            // `raw_ids[i].driver_data = i;`.
+            unsafe {
+                raw_ids[i]
+                    .as_mut_ptr()
+                    .byte_offset(T::DRIVER_DATA_OFFSET as _)
+                    .cast::<usize>()
+                    .write(i);
+            }
+
+            // SAFETY: this is effectively a move: `infos[i] = ids[i].1`. We make a copy here but
+            // later forget `ids`.
+            infos[i] = MaybeUninit::new(unsafe { core::ptr::read(&ids[i].1) });
+            i += 1;
+        }
+
+        core::mem::forget(ids);
+
+        Self {
+            raw_ids: RawIdArray {
+                // SAFETY: this is effectively `array_assume_init`, which is unstable, so we use
+                // `transmute_copy` instead. We have initialized all elements of `raw_ids` so this
+                // `array_assume_init` is safe.
+                ids: unsafe { core::mem::transmute_copy(&raw_ids) },
+                sentinel: MaybeUninit::zeroed(),
+            },
+            // SAFETY: We have initialized all elements of `infos` so this `array_assume_init` is
+            // safe.
+            id_infos: unsafe { core::mem::transmute_copy(&infos) },
+        }
+    }
+
+    /// Reference to the contained [`RawIdArray`].
+    pub const fn raw_ids(&self) -> &RawIdArray<T, N> {
+        &self.raw_ids
+    }
+}
+
+/// A device id table.
+///
+/// This trait is only implemented by `IdArray`.
+///
+/// The purpose of this trait is to allow `&'static dyn IdArray<T, U>` to be in context when `N` in
+/// `IdArray` doesn't matter.
+pub trait IdTable<T: RawDeviceId, U> {
+    /// Obtain the pointer to the ID table.
+    fn as_ptr(&self) -> *const T::RawType;
+
+    /// Obtain the pointer to the bus specific device ID from an index.
+    fn id(&self, index: usize) -> &T::RawType;
+
+    /// Obtain the pointer to the driver-specific information from an index.
+    fn info(&self, index: usize) -> &U;
+}
+
+impl<T: RawDeviceId, U, const N: usize> IdTable<T, U> for IdArray<T, U, N> {
+    fn as_ptr(&self) -> *const T::RawType {
+        // This cannot be `self.ids.as_ptr()`, as the return pointer must have correct provenance
+        // to access the sentinel.
+        (self as *const Self).cast()
+    }
+
+    fn id(&self, index: usize) -> &T::RawType {
+        &self.raw_ids.ids[index]
+    }
+
+    fn info(&self, index: usize) -> &U {
+        &self.id_infos[index]
+    }
+}
+
+/// Create device table alias for modpost.
+#[macro_export]
+macro_rules! module_device_table {
+    ($table_type: literal, $module_table_name:ident, $table_name:ident) => {
+        #[rustfmt::skip]
+        #[export_name =
+            concat!("__mod_device_table__", $table_type,
+                    "__", module_path!(),
+                    "_", line!(),
+                    "_", stringify!($table_name))
+        ]
+        static $module_table_name: [core::mem::MaybeUninit<u8>; $table_name.raw_ids().size()] =
+            unsafe { core::mem::transmute_copy($table_name.raw_ids()) };
+    };
+}
diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs
new file mode 100644
index 000000000000..942376f6f3af
--- /dev/null
+++ b/rust/kernel/devres.rs
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Devres abstraction
+//!
+//! [`Devres`] represents an abstraction for the kernel devres (device resource management)
+//! implementation.
+
+use crate::{
+    alloc::Flags,
+    bindings,
+    device::Device,
+    error::{Error, Result},
+    ffi::c_void,
+    prelude::*,
+    revocable::Revocable,
+    sync::Arc,
+    types::ARef,
+};
+
+use core::ops::Deref;
+
+#[pin_data]
+struct DevresInner<T> {
+    dev: ARef<Device>,
+    callback: unsafe extern "C" fn(*mut c_void),
+    #[pin]
+    data: Revocable<T>,
+}
+
+/// This abstraction is meant to be used by subsystems to containerize [`Device`] bound resources to
+/// manage their lifetime.
+///
+/// [`Device`] bound resources should be freed when either the resource goes out of scope or the
+/// [`Device`] is unbound respectively, depending on what happens first.
+///
+/// To achieve that [`Devres`] registers a devres callback on creation, which is called once the
+/// [`Device`] is unbound, revoking access to the encapsulated resource (see also [`Revocable`]).
+///
+/// After the [`Devres`] has been unbound it is not possible to access the encapsulated resource
+/// anymore.
+///
+/// [`Devres`] users should make sure to simply free the corresponding backing resource in `T`'s
+/// [`Drop`] implementation.
+///
+/// # Example
+///
+/// ```no_run
+/// # use kernel::{bindings, c_str, device::Device, devres::Devres, io::{Io, IoRaw}};
+/// # use core::ops::Deref;
+///
+/// // See also [`pci::Bar`] for a real example.
+/// struct IoMem<const SIZE: usize>(IoRaw<SIZE>);
+///
+/// impl<const SIZE: usize> IoMem<SIZE> {
+///     /// # Safety
+///     ///
+///     /// [`paddr`, `paddr` + `SIZE`) must be a valid MMIO region that is mappable into the CPUs
+///     /// virtual address space.
+///     unsafe fn new(paddr: usize) -> Result<Self>{
+///         // SAFETY: By the safety requirements of this function [`paddr`, `paddr` + `SIZE`) is
+///         // valid for `ioremap`.
+///         let addr = unsafe { bindings::ioremap(paddr as _, SIZE as _) };
+///         if addr.is_null() {
+///             return Err(ENOMEM);
+///         }
+///
+///         Ok(IoMem(IoRaw::new(addr as _, SIZE)?))
+///     }
+/// }
+///
+/// impl<const SIZE: usize> Drop for IoMem<SIZE> {
+///     fn drop(&mut self) {
+///         // SAFETY: `self.0.addr()` is guaranteed to be properly mapped by `Self::new`.
+///         unsafe { bindings::iounmap(self.0.addr() as _); };
+///     }
+/// }
+///
+/// impl<const SIZE: usize> Deref for IoMem<SIZE> {
+///    type Target = Io<SIZE>;
+///
+///    fn deref(&self) -> &Self::Target {
+///         // SAFETY: The memory range stored in `self` has been properly mapped in `Self::new`.
+///         unsafe { Io::from_raw(&self.0) }
+///    }
+/// }
+/// # fn no_run() -> Result<(), Error> {
+/// # // SAFETY: Invalid usage; just for the example to get an `ARef<Device>` instance.
+/// # let dev = unsafe { Device::get_device(core::ptr::null_mut()) };
+///
+/// // SAFETY: Invalid usage for example purposes.
+/// let iomem = unsafe { IoMem::<{ core::mem::size_of::<u32>() }>::new(0xBAAAAAAD)? };
+/// let devres = Devres::new(&dev, iomem, GFP_KERNEL)?;
+///
+/// let res = devres.try_access().ok_or(ENXIO)?;
+/// res.writel(0x42, 0x0);
+/// # Ok(())
+/// # }
+/// ```
+pub struct Devres<T>(Arc<DevresInner<T>>);
+
+impl<T> DevresInner<T> {
+    fn new(dev: &Device, data: T, flags: Flags) -> Result<Arc<DevresInner<T>>> {
+        let inner = Arc::pin_init(
+            pin_init!( DevresInner {
+                dev: dev.into(),
+                callback: Self::devres_callback,
+                data <- Revocable::new(data),
+            }),
+            flags,
+        )?;
+
+        // Convert `Arc<DevresInner>` into a raw pointer and make devres own this reference until
+        // `Self::devres_callback` is called.
+        let data = inner.clone().into_raw();
+
+        // SAFETY: `devm_add_action` guarantees to call `Self::devres_callback` once `dev` is
+        // detached.
+        let ret =
+            unsafe { bindings::devm_add_action(dev.as_raw(), Some(inner.callback), data as _) };
+
+        if ret != 0 {
+            // SAFETY: We just created another reference to `inner` in order to pass it to
+            // `bindings::devm_add_action`. If `bindings::devm_add_action` fails, we have to drop
+            // this reference accordingly.
+            let _ = unsafe { Arc::from_raw(data) };
+            return Err(Error::from_errno(ret));
+        }
+
+        Ok(inner)
+    }
+
+    fn as_ptr(&self) -> *const Self {
+        self as _
+    }
+
+    fn remove_action(this: &Arc<Self>) {
+        // SAFETY:
+        // - `self.inner.dev` is a valid `Device`,
+        // - the `action` and `data` pointers are the exact same ones as given to devm_add_action()
+        //   previously,
+        // - `self` is always valid, even if the action has been released already.
+        let ret = unsafe {
+            bindings::devm_remove_action_nowarn(
+                this.dev.as_raw(),
+                Some(this.callback),
+                this.as_ptr() as _,
+            )
+        };
+
+        if ret == 0 {
+            // SAFETY: We leaked an `Arc` reference to devm_add_action() in `DevresInner::new`; if
+            // devm_remove_action_nowarn() was successful we can (and have to) claim back ownership
+            // of this reference.
+            let _ = unsafe { Arc::from_raw(this.as_ptr()) };
+        }
+    }
+
+    #[allow(clippy::missing_safety_doc)]
+    unsafe extern "C" fn devres_callback(ptr: *mut kernel::ffi::c_void) {
+        let ptr = ptr as *mut DevresInner<T>;
+        // Devres owned this memory; now that we received the callback, drop the `Arc` and hence the
+        // reference.
+        // SAFETY: Safe, since we leaked an `Arc` reference to devm_add_action() in
+        //         `DevresInner::new`.
+        let inner = unsafe { Arc::from_raw(ptr) };
+
+        inner.data.revoke();
+    }
+}
+
+impl<T> Devres<T> {
+    /// Creates a new [`Devres`] instance of the given `data`. The `data` encapsulated within the
+    /// returned `Devres` instance' `data` will be revoked once the device is detached.
+    pub fn new(dev: &Device, data: T, flags: Flags) -> Result<Self> {
+        let inner = DevresInner::new(dev, data, flags)?;
+
+        Ok(Devres(inner))
+    }
+
+    /// Same as [`Devres::new`], but does not return a `Devres` instance. Instead the given `data`
+    /// is owned by devres and will be revoked / dropped, once the device is detached.
+    pub fn new_foreign_owned(dev: &Device, data: T, flags: Flags) -> Result {
+        let _ = DevresInner::new(dev, data, flags)?;
+
+        Ok(())
+    }
+}
+
+impl<T> Deref for Devres<T> {
+    type Target = Revocable<T>;
+
+    fn deref(&self) -> &Self::Target {
+        &self.0.data
+    }
+}
+
+impl<T> Drop for Devres<T> {
+    fn drop(&mut self) {
+        DevresInner::remove_action(&self.0);
+    }
+}
diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs
new file mode 100644
index 000000000000..2a16d5e64e6c
--- /dev/null
+++ b/rust/kernel/driver.rs
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Generic support for drivers of different buses (e.g., PCI, Platform, Amba, etc.).
+//!
+//! Each bus / subsystem is expected to implement [`RegistrationOps`], which allows drivers to
+//! register using the [`Registration`] class.
+
+use crate::error::{Error, Result};
+use crate::{device, init::PinInit, of, str::CStr, try_pin_init, types::Opaque, ThisModule};
+use core::pin::Pin;
+use macros::{pin_data, pinned_drop};
+
+/// The [`RegistrationOps`] trait serves as generic interface for subsystems (e.g., PCI, Platform,
+/// Amba, etc.) to provide the corresponding subsystem specific implementation to register /
+/// unregister a driver of the particular type (`RegType`).
+///
+/// For instance, the PCI subsystem would set `RegType` to `bindings::pci_driver` and call
+/// `bindings::__pci_register_driver` from `RegistrationOps::register` and
+/// `bindings::pci_unregister_driver` from `RegistrationOps::unregister`.
+///
+/// # Safety
+///
+/// A call to [`RegistrationOps::unregister`] for a given instance of `RegType` is only valid if a
+/// preceding call to [`RegistrationOps::register`] has been successful.
+pub unsafe trait RegistrationOps {
+    /// The type that holds information about the registration. This is typically a struct defined
+    /// by the C portion of the kernel.
+    type RegType: Default;
+
+    /// Registers a driver.
+    ///
+    /// # Safety
+    ///
+    /// On success, `reg` must remain pinned and valid until the matching call to
+    /// [`RegistrationOps::unregister`].
+    unsafe fn register(
+        reg: &Opaque<Self::RegType>,
+        name: &'static CStr,
+        module: &'static ThisModule,
+    ) -> Result;
+
+    /// Unregisters a driver previously registered with [`RegistrationOps::register`].
+    ///
+    /// # Safety
+    ///
+    /// Must only be called after a preceding successful call to [`RegistrationOps::register`] for
+    /// the same `reg`.
+    unsafe fn unregister(reg: &Opaque<Self::RegType>);
+}
+
+/// A [`Registration`] is a generic type that represents the registration of some driver type (e.g.
+/// `bindings::pci_driver`). Therefore a [`Registration`] must be initialized with a type that
+/// implements the [`RegistrationOps`] trait, such that the generic `T::register` and
+/// `T::unregister` calls result in the subsystem specific registration calls.
+///
+///Once the `Registration` structure is dropped, the driver is unregistered.
+#[pin_data(PinnedDrop)]
+pub struct Registration<T: RegistrationOps> {
+    #[pin]
+    reg: Opaque<T::RegType>,
+}
+
+// SAFETY: `Registration` has no fields or methods accessible via `&Registration`, so it is safe to
+// share references to it with multiple threads as nothing can be done.
+unsafe impl<T: RegistrationOps> Sync for Registration<T> {}
+
+// SAFETY: Both registration and unregistration are implemented in C and safe to be performed from
+// any thread, so `Registration` is `Send`.
+unsafe impl<T: RegistrationOps> Send for Registration<T> {}
+
+impl<T: RegistrationOps> Registration<T> {
+    /// Creates a new instance of the registration object.
+    pub fn new(name: &'static CStr, module: &'static ThisModule) -> impl PinInit<Self, Error> {
+        try_pin_init!(Self {
+            reg <- Opaque::try_ffi_init(|ptr: *mut T::RegType| {
+                // SAFETY: `try_ffi_init` guarantees that `ptr` is valid for write.
+                unsafe { ptr.write(T::RegType::default()) };
+
+                // SAFETY: `try_ffi_init` guarantees that `ptr` is valid for write, and it has
+                // just been initialised above, so it's also valid for read.
+                let drv = unsafe { &*(ptr as *const Opaque<T::RegType>) };
+
+                // SAFETY: `drv` is guaranteed to be pinned until `T::unregister`.
+                unsafe { T::register(drv, name, module) }
+            }),
+        })
+    }
+}
+
+#[pinned_drop]
+impl<T: RegistrationOps> PinnedDrop for Registration<T> {
+    fn drop(self: Pin<&mut Self>) {
+        // SAFETY: The existence of `self` guarantees that `self.reg` has previously been
+        // successfully registered with `T::register`
+        unsafe { T::unregister(&self.reg) };
+    }
+}
+
+/// Declares a kernel module that exposes a single driver.
+///
+/// It is meant to be used as a helper by other subsystems so they can more easily expose their own
+/// macros.
+#[macro_export]
+macro_rules! module_driver {
+    (<$gen_type:ident>, $driver_ops:ty, { type: $type:ty, $($f:tt)* }) => {
+        type Ops<$gen_type> = $driver_ops;
+
+        #[$crate::prelude::pin_data]
+        struct DriverModule {
+            #[pin]
+            _driver: $crate::driver::Registration<Ops<$type>>,
+        }
+
+        impl $crate::InPlaceModule for DriverModule {
+            fn init(
+                module: &'static $crate::ThisModule
+            ) -> impl $crate::init::PinInit<Self, $crate::error::Error> {
+                $crate::try_pin_init!(Self {
+                    _driver <- $crate::driver::Registration::new(
+                        <Self as $crate::ModuleMetadata>::NAME,
+                        module,
+                    ),
+                })
+            }
+        }
+
+        $crate::prelude::module! {
+            type: DriverModule,
+            $($f)*
+        }
+    }
+}
+
+/// The bus independent adapter to match a drivers and a devices.
+///
+/// This trait should be implemented by the bus specific adapter, which represents the connection
+/// of a device and a driver.
+///
+/// It provides bus independent functions for device / driver interactions.
+pub trait Adapter {
+    /// The type holding driver private data about each device id supported by the driver.
+    type IdInfo: 'static;
+
+    /// The [`of::IdTable`] of the corresponding driver.
+    fn of_id_table() -> Option<of::IdTable<Self::IdInfo>>;
+
+    /// Returns the driver's private data from the matching entry in the [`of::IdTable`], if any.
+    ///
+    /// If this returns `None`, it means there is no match with an entry in the [`of::IdTable`].
+    #[cfg(CONFIG_OF)]
+    fn of_id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
+        let table = Self::of_id_table()?;
+
+        // SAFETY:
+        // - `table` has static lifetime, hence it's valid for read,
+        // - `dev` is guaranteed to be valid while it's alive, and so is `pdev.as_ref().as_raw()`.
+        let raw_id = unsafe { bindings::of_match_device(table.as_ptr(), dev.as_raw()) };
+
+        if raw_id.is_null() {
+            None
+        } else {
+            // SAFETY: `DeviceId` is a `#[repr(transparent)` wrapper of `struct of_device_id` and
+            // does not add additional invariants, so it's safe to transmute.
+            let id = unsafe { &*raw_id.cast::<of::DeviceId>() };
+
+            Some(table.info(<of::DeviceId as crate::device_id::RawDeviceId>::index(id)))
+        }
+    }
+
+    #[cfg(not(CONFIG_OF))]
+    #[allow(missing_docs)]
+    fn of_id_info(_dev: &device::Device) -> Option<&'static Self::IdInfo> {
+        None
+    }
+
+    /// Returns the driver's private data from the matching entry of any of the ID tables, if any.
+    ///
+    /// If this returns `None`, it means that there is no match in any of the ID tables directly
+    /// associated with a [`device::Device`].
+    fn id_info(dev: &device::Device) -> Option<&'static Self::IdInfo> {
+        let id = Self::of_id_info(dev);
+        if id.is_some() {
+            return id;
+        }
+
+        None
+    }
+}
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 3f9236c1c9d5..7fd1ea8265a5 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -870,7 +870,7 @@ pub unsafe trait PinInit<T: ?Sized, E = Infallible>: Sized {
     /// use kernel::{types::Opaque, init::pin_init_from_closure};
     /// #[repr(C)]
     /// struct RawFoo([u8; 16]);
-    /// extern {
+    /// extern "C" {
     ///     fn init_foo(_: *mut RawFoo);
     /// }
     ///
diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs
new file mode 100644
index 000000000000..d4a73e52e3ee
--- /dev/null
+++ b/rust/kernel/io.rs
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Memory-mapped IO.
+//!
+//! C header: [`include/asm-generic/io.h`](srctree/include/asm-generic/io.h)
+
+use crate::error::{code::EINVAL, Result};
+use crate::{bindings, build_assert};
+
+/// Raw representation of an MMIO region.
+///
+/// By itself, the existence of an instance of this structure does not provide any guarantees that
+/// the represented MMIO region does exist or is properly mapped.
+///
+/// Instead, the bus specific MMIO implementation must convert this raw representation into an `Io`
+/// instance providing the actual memory accessors. Only by the conversion into an `Io` structure
+/// any guarantees are given.
+pub struct IoRaw<const SIZE: usize = 0> {
+    addr: usize,
+    maxsize: usize,
+}
+
+impl<const SIZE: usize> IoRaw<SIZE> {
+    /// Returns a new `IoRaw` instance on success, an error otherwise.
+    pub fn new(addr: usize, maxsize: usize) -> Result<Self> {
+        if maxsize < SIZE {
+            return Err(EINVAL);
+        }
+
+        Ok(Self { addr, maxsize })
+    }
+
+    /// Returns the base address of the MMIO region.
+    #[inline]
+    pub fn addr(&self) -> usize {
+        self.addr
+    }
+
+    /// Returns the maximum size of the MMIO region.
+    #[inline]
+    pub fn maxsize(&self) -> usize {
+        self.maxsize
+    }
+}
+
+/// IO-mapped memory, starting at the base address @addr and spanning @maxlen bytes.
+///
+/// The creator (usually a subsystem / bus such as PCI) is responsible for creating the
+/// mapping, performing an additional region request etc.
+///
+/// # Invariant
+///
+/// `addr` is the start and `maxsize` the length of valid I/O mapped memory region of size
+/// `maxsize`.
+///
+/// # Examples
+///
+/// ```no_run
+/// # use kernel::{bindings, io::{Io, IoRaw}};
+/// # use core::ops::Deref;
+///
+/// // See also [`pci::Bar`] for a real example.
+/// struct IoMem<const SIZE: usize>(IoRaw<SIZE>);
+///
+/// impl<const SIZE: usize> IoMem<SIZE> {
+///     /// # Safety
+///     ///
+///     /// [`paddr`, `paddr` + `SIZE`) must be a valid MMIO region that is mappable into the CPUs
+///     /// virtual address space.
+///     unsafe fn new(paddr: usize) -> Result<Self>{
+///         // SAFETY: By the safety requirements of this function [`paddr`, `paddr` + `SIZE`) is
+///         // valid for `ioremap`.
+///         let addr = unsafe { bindings::ioremap(paddr as _, SIZE as _) };
+///         if addr.is_null() {
+///             return Err(ENOMEM);
+///         }
+///
+///         Ok(IoMem(IoRaw::new(addr as _, SIZE)?))
+///     }
+/// }
+///
+/// impl<const SIZE: usize> Drop for IoMem<SIZE> {
+///     fn drop(&mut self) {
+///         // SAFETY: `self.0.addr()` is guaranteed to be properly mapped by `Self::new`.
+///         unsafe { bindings::iounmap(self.0.addr() as _); };
+///     }
+/// }
+///
+/// impl<const SIZE: usize> Deref for IoMem<SIZE> {
+///    type Target = Io<SIZE>;
+///
+///    fn deref(&self) -> &Self::Target {
+///         // SAFETY: The memory range stored in `self` has been properly mapped in `Self::new`.
+///         unsafe { Io::from_raw(&self.0) }
+///    }
+/// }
+///
+///# fn no_run() -> Result<(), Error> {
+/// // SAFETY: Invalid usage for example purposes.
+/// let iomem = unsafe { IoMem::<{ core::mem::size_of::<u32>() }>::new(0xBAAAAAAD)? };
+/// iomem.writel(0x42, 0x0);
+/// assert!(iomem.try_writel(0x42, 0x0).is_ok());
+/// assert!(iomem.try_writel(0x42, 0x4).is_err());
+/// # Ok(())
+/// # }
+/// ```
+#[repr(transparent)]
+pub struct Io<const SIZE: usize = 0>(IoRaw<SIZE>);
+
+macro_rules! define_read {
+    ($(#[$attr:meta])* $name:ident, $try_name:ident, $type_name:ty) => {
+        /// Read IO data from a given offset known at compile time.
+        ///
+        /// Bound checks are performed on compile time, hence if the offset is not known at compile
+        /// time, the build will fail.
+        $(#[$attr])*
+        #[inline]
+        pub fn $name(&self, offset: usize) -> $type_name {
+            let addr = self.io_addr_assert::<$type_name>(offset);
+
+            // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
+            unsafe { bindings::$name(addr as _) }
+        }
+
+        /// Read IO data from a given offset.
+        ///
+        /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is
+        /// out of bounds.
+        $(#[$attr])*
+        pub fn $try_name(&self, offset: usize) -> Result<$type_name> {
+            let addr = self.io_addr::<$type_name>(offset)?;
+
+            // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
+            Ok(unsafe { bindings::$name(addr as _) })
+        }
+    };
+}
+
+macro_rules! define_write {
+    ($(#[$attr:meta])* $name:ident, $try_name:ident, $type_name:ty) => {
+        /// Write IO data from a given offset known at compile time.
+        ///
+        /// Bound checks are performed on compile time, hence if the offset is not known at compile
+        /// time, the build will fail.
+        $(#[$attr])*
+        #[inline]
+        pub fn $name(&self, value: $type_name, offset: usize) {
+            let addr = self.io_addr_assert::<$type_name>(offset);
+
+            // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
+            unsafe { bindings::$name(value, addr as _, ) }
+        }
+
+        /// Write IO data from a given offset.
+        ///
+        /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is
+        /// out of bounds.
+        $(#[$attr])*
+        pub fn $try_name(&self, value: $type_name, offset: usize) -> Result {
+            let addr = self.io_addr::<$type_name>(offset)?;
+
+            // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
+            unsafe { bindings::$name(value, addr as _) }
+            Ok(())
+        }
+    };
+}
+
+impl<const SIZE: usize> Io<SIZE> {
+    /// Converts an `IoRaw` into an `Io` instance, providing the accessors to the MMIO mapping.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that `addr` is the start of a valid I/O mapped memory region of size
+    /// `maxsize`.
+    pub unsafe fn from_raw(raw: &IoRaw<SIZE>) -> &Self {
+        // SAFETY: `Io` is a transparent wrapper around `IoRaw`.
+        unsafe { &*core::ptr::from_ref(raw).cast() }
+    }
+
+    /// Returns the base address of this mapping.
+    #[inline]
+    pub fn addr(&self) -> usize {
+        self.0.addr()
+    }
+
+    /// Returns the maximum size of this mapping.
+    #[inline]
+    pub fn maxsize(&self) -> usize {
+        self.0.maxsize()
+    }
+
+    #[inline]
+    const fn offset_valid<U>(offset: usize, size: usize) -> bool {
+        let type_size = core::mem::size_of::<U>();
+        if let Some(end) = offset.checked_add(type_size) {
+            end <= size && offset % type_size == 0
+        } else {
+            false
+        }
+    }
+
+    #[inline]
+    fn io_addr<U>(&self, offset: usize) -> Result<usize> {
+        if !Self::offset_valid::<U>(offset, self.maxsize()) {
+            return Err(EINVAL);
+        }
+
+        // Probably no need to check, since the safety requirements of `Self::new` guarantee that
+        // this can't overflow.
+        self.addr().checked_add(offset).ok_or(EINVAL)
+    }
+
+    #[inline]
+    fn io_addr_assert<U>(&self, offset: usize) -> usize {
+        build_assert!(Self::offset_valid::<U>(offset, SIZE));
+
+        self.addr() + offset
+    }
+
+    define_read!(readb, try_readb, u8);
+    define_read!(readw, try_readw, u16);
+    define_read!(readl, try_readl, u32);
+    define_read!(
+        #[cfg(CONFIG_64BIT)]
+        readq,
+        try_readq,
+        u64
+    );
+
+    define_read!(readb_relaxed, try_readb_relaxed, u8);
+    define_read!(readw_relaxed, try_readw_relaxed, u16);
+    define_read!(readl_relaxed, try_readl_relaxed, u32);
+    define_read!(
+        #[cfg(CONFIG_64BIT)]
+        readq_relaxed,
+        try_readq_relaxed,
+        u64
+    );
+
+    define_write!(writeb, try_writeb, u8);
+    define_write!(writew, try_writew, u16);
+    define_write!(writel, try_writel, u32);
+    define_write!(
+        #[cfg(CONFIG_64BIT)]
+        writeq,
+        try_writeq,
+        u64
+    );
+
+    define_write!(writeb_relaxed, try_writeb_relaxed, u8);
+    define_write!(writew_relaxed, try_writew_relaxed, u16);
+    define_write!(writel_relaxed, try_writel_relaxed, u32);
+    define_write!(
+        #[cfg(CONFIG_64BIT)]
+        writeq_relaxed,
+        try_writeq_relaxed,
+        u64
+    );
+}
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 545d1170ee63..496ed32b0911 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -19,6 +19,11 @@
 #![cfg_attr(not(CONFIG_RUSTC_HAS_COERCE_POINTEE), feature(unsize))]
 #![feature(inline_const)]
 #![feature(lint_reasons)]
+// Stable in Rust 1.83
+#![feature(const_maybe_uninit_as_mut_ptr)]
+#![feature(const_mut_refs)]
+#![feature(const_ptr_write)]
+#![feature(const_refs_to_cell)]
 
 // Ensure conditional compilation based on the kernel configuration works;
 // otherwise we may silently break things like initcall handling.
@@ -37,11 +42,15 @@ pub mod block;
 pub mod build_assert;
 pub mod cred;
 pub mod device;
+pub mod device_id;
+pub mod devres;
+pub mod driver;
 pub mod error;
 #[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)]
 pub mod firmware;
 pub mod fs;
 pub mod init;
+pub mod io;
 pub mod ioctl;
 pub mod jump_label;
 #[cfg(CONFIG_KUNIT)]
@@ -50,11 +59,16 @@ pub mod list;
 pub mod miscdevice;
 #[cfg(CONFIG_NET)]
 pub mod net;
+pub mod of;
 pub mod page;
+#[cfg(CONFIG_PCI)]
+pub mod pci;
 pub mod pid_namespace;
+pub mod platform;
 pub mod prelude;
 pub mod print;
 pub mod rbtree;
+pub mod revocable;
 pub mod security;
 pub mod seq_file;
 pub mod sizes;
@@ -115,6 +129,12 @@ impl<T: Module> InPlaceModule for T {
     }
 }
 
+/// Metadata attached to a [`Module`] or [`InPlaceModule`].
+pub trait ModuleMetadata {
+    /// The name of the module as specified in the `module!` macro.
+    const NAME: &'static crate::str::CStr;
+}
+
 /// Equivalent to `THIS_MODULE` in the C API.
 ///
 /// C header: [`include/linux/init.h`](srctree/include/linux/init.h)
diff --git a/rust/kernel/miscdevice.rs b/rust/kernel/miscdevice.rs
index b3a6cc50b240..e14433b2ab9d 100644
--- a/rust/kernel/miscdevice.rs
+++ b/rust/kernel/miscdevice.rs
@@ -10,9 +10,12 @@
 
 use crate::{
     bindings,
+    device::Device,
     error::{to_result, Error, Result, VTABLE_DEFAULT_ERROR},
     ffi::{c_int, c_long, c_uint, c_ulong},
+    fs::File,
     prelude::*,
+    seq_file::SeqFile,
     str::CStr,
     types::{ForeignOwnable, Opaque},
 };
@@ -80,6 +83,16 @@ impl<T: MiscDevice> MiscDeviceRegistration<T> {
     pub fn as_raw(&self) -> *mut bindings::miscdevice {
         self.inner.get()
     }
+
+    /// Access the `this_device` field.
+    pub fn device(&self) -> &Device {
+        // SAFETY: This can only be called after a successful register(), which always
+        // initialises `this_device` with a valid device. Furthermore, the signature of this
+        // function tells the borrow-checker that the `&Device` reference must not outlive the
+        // `&MiscDeviceRegistration<T>` used to obtain it, so the last use of the reference must be
+        // before the underlying `struct miscdevice` is destroyed.
+        unsafe { Device::as_ref((*self.as_raw()).this_device) }
+    }
 }
 
 #[pinned_drop]
@@ -92,17 +105,17 @@ impl<T> PinnedDrop for MiscDeviceRegistration<T> {
 
 /// Trait implemented by the private data of an open misc device.
 #[vtable]
-pub trait MiscDevice {
+pub trait MiscDevice: Sized {
     /// What kind of pointer should `Self` be wrapped in.
     type Ptr: ForeignOwnable + Send + Sync;
 
     /// Called when the misc device is opened.
     ///
     /// The returned pointer will be stored as the private data for the file.
-    fn open() -> Result<Self::Ptr>;
+    fn open(_file: &File, _misc: &MiscDeviceRegistration<Self>) -> Result<Self::Ptr>;
 
     /// Called when the misc device is released.
-    fn release(device: Self::Ptr) {
+    fn release(device: Self::Ptr, _file: &File) {
         drop(device);
     }
 
@@ -113,6 +126,7 @@ pub trait MiscDevice {
     /// [`kernel::ioctl`]: mod@crate::ioctl
     fn ioctl(
         _device: <Self::Ptr as ForeignOwnable>::Borrowed<'_>,
+        _file: &File,
         _cmd: u32,
         _arg: usize,
     ) -> Result<isize> {
@@ -129,11 +143,21 @@ pub trait MiscDevice {
     #[cfg(CONFIG_COMPAT)]
     fn compat_ioctl(
         _device: <Self::Ptr as ForeignOwnable>::Borrowed<'_>,
+        _file: &File,
         _cmd: u32,
         _arg: usize,
     ) -> Result<isize> {
         build_error!(VTABLE_DEFAULT_ERROR)
     }
+
+    /// Show info for this fd.
+    fn show_fdinfo(
+        _device: <Self::Ptr as ForeignOwnable>::Borrowed<'_>,
+        _m: &SeqFile,
+        _file: &File,
+    ) {
+        build_error!(VTABLE_DEFAULT_ERROR)
+    }
 }
 
 const fn create_vtable<T: MiscDevice>() -> &'static bindings::file_operations {
@@ -161,6 +185,7 @@ const fn create_vtable<T: MiscDevice>() -> &'static bindings::file_operations {
             } else {
                 None
             },
+            show_fdinfo: maybe_fn(T::HAS_SHOW_FDINFO, fops_show_fdinfo::<T>),
             // SAFETY: All zeros is a valid value for `bindings::file_operations`.
             ..unsafe { MaybeUninit::zeroed().assume_init() }
         };
@@ -175,21 +200,38 @@ const fn create_vtable<T: MiscDevice>() -> &'static bindings::file_operations {
 /// The file must be associated with a `MiscDeviceRegistration<T>`.
 unsafe extern "C" fn fops_open<T: MiscDevice>(
     inode: *mut bindings::inode,
-    file: *mut bindings::file,
+    raw_file: *mut bindings::file,
 ) -> c_int {
     // SAFETY: The pointers are valid and for a file being opened.
-    let ret = unsafe { bindings::generic_file_open(inode, file) };
+    let ret = unsafe { bindings::generic_file_open(inode, raw_file) };
     if ret != 0 {
         return ret;
     }
 
-    let ptr = match T::open() {
+    // SAFETY: The open call of a file can access the private data.
+    let misc_ptr = unsafe { (*raw_file).private_data };
+
+    // SAFETY: This is a miscdevice, so `misc_open()` set the private data to a pointer to the
+    // associated `struct miscdevice` before calling into this method. Furthermore, `misc_open()`
+    // ensures that the miscdevice can't be unregistered and freed during this call to `fops_open`.
+    let misc = unsafe { &*misc_ptr.cast::<MiscDeviceRegistration<T>>() };
+
+    // SAFETY:
+    // * This underlying file is valid for (much longer than) the duration of `T::open`.
+    // * There is no active fdget_pos region on the file on this thread.
+    let file = unsafe { File::from_raw_file(raw_file) };
+
+    let ptr = match T::open(file, misc) {
         Ok(ptr) => ptr,
         Err(err) => return err.to_errno(),
     };
 
-    // SAFETY: The open call of a file owns the private data.
-    unsafe { (*file).private_data = ptr.into_foreign() };
+    // This overwrites the private data with the value specified by the user, changing the type of
+    // this file's private data. All future accesses to the private data is performed by other
+    // fops_* methods in this file, which all correctly cast the private data to the new type.
+    //
+    // SAFETY: The open call of a file can access the private data.
+    unsafe { (*raw_file).private_data = ptr.into_foreign() };
 
     0
 }
@@ -207,7 +249,10 @@ unsafe extern "C" fn fops_release<T: MiscDevice>(
     // SAFETY: The release call of a file owns the private data.
     let ptr = unsafe { <T::Ptr as ForeignOwnable>::from_foreign(private) };
 
-    T::release(ptr);
+    // SAFETY:
+    // * The file is valid for the duration of this call.
+    // * There is no active fdget_pos region on the file on this thread.
+    T::release(ptr, unsafe { File::from_raw_file(file) });
 
     0
 }
@@ -225,7 +270,12 @@ unsafe extern "C" fn fops_ioctl<T: MiscDevice>(
     // SAFETY: Ioctl calls can borrow the private data of the file.
     let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
 
-    match T::ioctl(device, cmd, arg) {
+    // SAFETY:
+    // * The file is valid for the duration of this call.
+    // * There is no active fdget_pos region on the file on this thread.
+    let file = unsafe { File::from_raw_file(file) };
+
+    match T::ioctl(device, file, cmd, arg) {
         Ok(ret) => ret as c_long,
         Err(err) => err.to_errno() as c_long,
     }
@@ -245,8 +295,36 @@ unsafe extern "C" fn fops_compat_ioctl<T: MiscDevice>(
     // SAFETY: Ioctl calls can borrow the private data of the file.
     let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
 
-    match T::compat_ioctl(device, cmd, arg) {
+    // SAFETY:
+    // * The file is valid for the duration of this call.
+    // * There is no active fdget_pos region on the file on this thread.
+    let file = unsafe { File::from_raw_file(file) };
+
+    match T::compat_ioctl(device, file, cmd, arg) {
         Ok(ret) => ret as c_long,
         Err(err) => err.to_errno() as c_long,
     }
 }
+
+/// # Safety
+///
+/// - `file` must be a valid file that is associated with a `MiscDeviceRegistration<T>`.
+/// - `seq_file` must be a valid `struct seq_file` that we can write to.
+unsafe extern "C" fn fops_show_fdinfo<T: MiscDevice>(
+    seq_file: *mut bindings::seq_file,
+    file: *mut bindings::file,
+) {
+    // SAFETY: The release call of a file owns the private data.
+    let private = unsafe { (*file).private_data };
+    // SAFETY: Ioctl calls can borrow the private data of the file.
+    let device = unsafe { <T::Ptr as ForeignOwnable>::borrow(private) };
+    // SAFETY:
+    // * The file is valid for the duration of this call.
+    // * There is no active fdget_pos region on the file on this thread.
+    let file = unsafe { File::from_raw_file(file) };
+    // SAFETY: The caller ensures that the pointer is valid and exclusive for the duration in which
+    // this method is called.
+    let m = unsafe { SeqFile::from_raw(seq_file) };
+
+    T::show_fdinfo(device, m, file);
+}
diff --git a/rust/kernel/of.rs b/rust/kernel/of.rs
new file mode 100644
index 000000000000..04f2d8ef29cb
--- /dev/null
+++ b/rust/kernel/of.rs
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Device Tree / Open Firmware abstractions.
+
+use crate::{bindings, device_id::RawDeviceId, prelude::*};
+
+/// IdTable type for OF drivers.
+pub type IdTable<T> = &'static dyn kernel::device_id::IdTable<DeviceId, T>;
+
+/// An open firmware device id.
+#[repr(transparent)]
+#[derive(Clone, Copy)]
+pub struct DeviceId(bindings::of_device_id);
+
+// SAFETY:
+// * `DeviceId` is a `#[repr(transparent)` wrapper of `struct of_device_id` and does not add
+//   additional invariants, so it's safe to transmute to `RawType`.
+// * `DRIVER_DATA_OFFSET` is the offset to the `data` field.
+unsafe impl RawDeviceId for DeviceId {
+    type RawType = bindings::of_device_id;
+
+    const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::of_device_id, data);
+
+    fn index(&self) -> usize {
+        self.0.data as _
+    }
+}
+
+impl DeviceId {
+    /// Create a new device id from an OF 'compatible' string.
+    pub const fn new(compatible: &'static CStr) -> Self {
+        let src = compatible.as_bytes_with_nul();
+        // Replace with `bindings::of_device_id::default()` once stabilized for `const`.
+        // SAFETY: FFI type is valid to be zero-initialized.
+        let mut of: bindings::of_device_id = unsafe { core::mem::zeroed() };
+
+        // TODO: Use `clone_from_slice` once the corresponding types do match.
+        let mut i = 0;
+        while i < src.len() {
+            of.compatible[i] = src[i] as _;
+            i += 1;
+        }
+
+        Self(of)
+    }
+}
+
+/// Create an OF `IdTable` with an "alias" for modpost.
+#[macro_export]
+macro_rules! of_device_table {
+    ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
+        const $table_name: $crate::device_id::IdArray<
+            $crate::of::DeviceId,
+            $id_info_type,
+            { $table_data.len() },
+        > = $crate::device_id::IdArray::new($table_data);
+
+        $crate::module_device_table!("of", $module_table_name, $table_name);
+    };
+}
diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
new file mode 100644
index 000000000000..4c98b5b9aa1e
--- /dev/null
+++ b/rust/kernel/pci.rs
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Abstractions for the PCI bus.
+//!
+//! C header: [`include/linux/pci.h`](srctree/include/linux/pci.h)
+
+use crate::{
+    alloc::flags::*,
+    bindings, container_of, device,
+    device_id::RawDeviceId,
+    devres::Devres,
+    driver,
+    error::{to_result, Result},
+    io::Io,
+    io::IoRaw,
+    str::CStr,
+    types::{ARef, ForeignOwnable, Opaque},
+    ThisModule,
+};
+use core::{ops::Deref, ptr::addr_of_mut};
+use kernel::prelude::*;
+
+/// An adapter for the registration of PCI drivers.
+pub struct Adapter<T: Driver>(T);
+
+// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if
+// a preceding call to `register` has been successful.
+unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> {
+    type RegType = bindings::pci_driver;
+
+    unsafe fn register(
+        pdrv: &Opaque<Self::RegType>,
+        name: &'static CStr,
+        module: &'static ThisModule,
+    ) -> Result {
+        // SAFETY: It's safe to set the fields of `struct pci_driver` on initialization.
+        unsafe {
+            (*pdrv.get()).name = name.as_char_ptr();
+            (*pdrv.get()).probe = Some(Self::probe_callback);
+            (*pdrv.get()).remove = Some(Self::remove_callback);
+            (*pdrv.get()).id_table = T::ID_TABLE.as_ptr();
+        }
+
+        // SAFETY: `pdrv` is guaranteed to be a valid `RegType`.
+        to_result(unsafe {
+            bindings::__pci_register_driver(pdrv.get(), module.0, name.as_char_ptr())
+        })
+    }
+
+    unsafe fn unregister(pdrv: &Opaque<Self::RegType>) {
+        // SAFETY: `pdrv` is guaranteed to be a valid `RegType`.
+        unsafe { bindings::pci_unregister_driver(pdrv.get()) }
+    }
+}
+
+impl<T: Driver + 'static> Adapter<T> {
+    extern "C" fn probe_callback(
+        pdev: *mut bindings::pci_dev,
+        id: *const bindings::pci_device_id,
+    ) -> kernel::ffi::c_int {
+        // SAFETY: The PCI bus only ever calls the probe callback with a valid pointer to a
+        // `struct pci_dev`.
+        let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) };
+        // SAFETY: `dev` is guaranteed to be embedded in a valid `struct pci_dev` by the call
+        // above.
+        let mut pdev = unsafe { Device::from_dev(dev) };
+
+        // SAFETY: `DeviceId` is a `#[repr(transparent)` wrapper of `struct pci_device_id` and
+        // does not add additional invariants, so it's safe to transmute.
+        let id = unsafe { &*id.cast::<DeviceId>() };
+        let info = T::ID_TABLE.info(id.index());
+
+        match T::probe(&mut pdev, info) {
+            Ok(data) => {
+                // Let the `struct pci_dev` own a reference of the driver's private data.
+                // SAFETY: By the type invariant `pdev.as_raw` returns a valid pointer to a
+                // `struct pci_dev`.
+                unsafe { bindings::pci_set_drvdata(pdev.as_raw(), data.into_foreign() as _) };
+            }
+            Err(err) => return Error::to_errno(err),
+        }
+
+        0
+    }
+
+    extern "C" fn remove_callback(pdev: *mut bindings::pci_dev) {
+        // SAFETY: The PCI bus only ever calls the remove callback with a valid pointer to a
+        // `struct pci_dev`.
+        let ptr = unsafe { bindings::pci_get_drvdata(pdev) };
+
+        // SAFETY: `remove_callback` is only ever called after a successful call to
+        // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized
+        // `KBox<T>` pointer created through `KBox::into_foreign`.
+        let _ = unsafe { KBox::<T>::from_foreign(ptr) };
+    }
+}
+
+/// Declares a kernel module that exposes a single PCI driver.
+///
+/// # Example
+///
+///```ignore
+/// kernel::module_pci_driver! {
+///     type: MyDriver,
+///     name: "Module name",
+///     author: "Author name",
+///     description: "Description",
+///     license: "GPL v2",
+/// }
+///```
+#[macro_export]
+macro_rules! module_pci_driver {
+($($f:tt)*) => {
+    $crate::module_driver!(<T>, $crate::pci::Adapter<T>, { $($f)* });
+};
+}
+
+/// Abstraction for bindings::pci_device_id.
+#[repr(transparent)]
+#[derive(Clone, Copy)]
+pub struct DeviceId(bindings::pci_device_id);
+
+impl DeviceId {
+    const PCI_ANY_ID: u32 = !0;
+
+    /// Equivalent to C's `PCI_DEVICE` macro.
+    ///
+    /// Create a new `pci::DeviceId` from a vendor and device ID number.
+    pub const fn from_id(vendor: u32, device: u32) -> Self {
+        Self(bindings::pci_device_id {
+            vendor,
+            device,
+            subvendor: DeviceId::PCI_ANY_ID,
+            subdevice: DeviceId::PCI_ANY_ID,
+            class: 0,
+            class_mask: 0,
+            driver_data: 0,
+            override_only: 0,
+        })
+    }
+
+    /// Equivalent to C's `PCI_DEVICE_CLASS` macro.
+    ///
+    /// Create a new `pci::DeviceId` from a class number and mask.
+    pub const fn from_class(class: u32, class_mask: u32) -> Self {
+        Self(bindings::pci_device_id {
+            vendor: DeviceId::PCI_ANY_ID,
+            device: DeviceId::PCI_ANY_ID,
+            subvendor: DeviceId::PCI_ANY_ID,
+            subdevice: DeviceId::PCI_ANY_ID,
+            class,
+            class_mask,
+            driver_data: 0,
+            override_only: 0,
+        })
+    }
+}
+
+// SAFETY:
+// * `DeviceId` is a `#[repr(transparent)` wrapper of `pci_device_id` and does not add
+//   additional invariants, so it's safe to transmute to `RawType`.
+// * `DRIVER_DATA_OFFSET` is the offset to the `driver_data` field.
+unsafe impl RawDeviceId for DeviceId {
+    type RawType = bindings::pci_device_id;
+
+    const DRIVER_DATA_OFFSET: usize = core::mem::offset_of!(bindings::pci_device_id, driver_data);
+
+    fn index(&self) -> usize {
+        self.0.driver_data as _
+    }
+}
+
+/// IdTable type for PCI
+pub type IdTable<T> = &'static dyn kernel::device_id::IdTable<DeviceId, T>;
+
+/// Create a PCI `IdTable` with its alias for modpost.
+#[macro_export]
+macro_rules! pci_device_table {
+    ($table_name:ident, $module_table_name:ident, $id_info_type: ty, $table_data: expr) => {
+        const $table_name: $crate::device_id::IdArray<
+            $crate::pci::DeviceId,
+            $id_info_type,
+            { $table_data.len() },
+        > = $crate::device_id::IdArray::new($table_data);
+
+        $crate::module_device_table!("pci", $module_table_name, $table_name);
+    };
+}
+
+/// The PCI driver trait.
+///
+/// # Example
+///
+///```
+/// # use kernel::{bindings, pci};
+///
+/// struct MyDriver;
+///
+/// kernel::pci_device_table!(
+///     PCI_TABLE,
+///     MODULE_PCI_TABLE,
+///     <MyDriver as pci::Driver>::IdInfo,
+///     [
+///         (pci::DeviceId::from_id(bindings::PCI_VENDOR_ID_REDHAT, bindings::PCI_ANY_ID as _), ())
+///     ]
+/// );
+///
+/// impl pci::Driver for MyDriver {
+///     type IdInfo = ();
+///     const ID_TABLE: pci::IdTable<Self::IdInfo> = &PCI_TABLE;
+///
+///     fn probe(
+///         _pdev: &mut pci::Device,
+///         _id_info: &Self::IdInfo,
+///     ) -> Result<Pin<KBox<Self>>> {
+///         Err(ENODEV)
+///     }
+/// }
+///```
+/// Drivers must implement this trait in order to get a PCI driver registered. Please refer to the
+/// `Adapter` documentation for an example.
+pub trait Driver {
+    /// The type holding information about each device id supported by the driver.
+    ///
+    /// TODO: Use associated_type_defaults once stabilized:
+    ///
+    /// type IdInfo: 'static = ();
+    type IdInfo: 'static;
+
+    /// The table of device ids supported by the driver.
+    const ID_TABLE: IdTable<Self::IdInfo>;
+
+    /// PCI driver probe.
+    ///
+    /// Called when a new platform device is added or discovered.
+    /// Implementers should attempt to initialize the device here.
+    fn probe(dev: &mut Device, id_info: &Self::IdInfo) -> Result<Pin<KBox<Self>>>;
+}
+
+/// The PCI device representation.
+///
+/// A PCI device is based on an always reference counted `device:Device` instance. Cloning a PCI
+/// device, hence, also increments the base device' reference count.
+///
+/// # Invariants
+///
+/// `Device` hold a valid reference of `ARef<device::Device>` whose underlying `struct device` is a
+/// member of a `struct pci_dev`.
+#[derive(Clone)]
+pub struct Device(ARef<device::Device>);
+
+/// A PCI BAR to perform I/O-Operations on.
+///
+/// # Invariants
+///
+/// `Bar` always holds an `IoRaw` inststance that holds a valid pointer to the start of the I/O
+/// memory mapped PCI bar and its size.
+pub struct Bar<const SIZE: usize = 0> {
+    pdev: Device,
+    io: IoRaw<SIZE>,
+    num: i32,
+}
+
+impl<const SIZE: usize> Bar<SIZE> {
+    fn new(pdev: Device, num: u32, name: &CStr) -> Result<Self> {
+        let len = pdev.resource_len(num)?;
+        if len == 0 {
+            return Err(ENOMEM);
+        }
+
+        // Convert to `i32`, since that's what all the C bindings use.
+        let num = i32::try_from(num)?;
+
+        // SAFETY:
+        // `pdev` is valid by the invariants of `Device`.
+        // `num` is checked for validity by a previous call to `Device::resource_len`.
+        // `name` is always valid.
+        let ret = unsafe { bindings::pci_request_region(pdev.as_raw(), num, name.as_char_ptr()) };
+        if ret != 0 {
+            return Err(EBUSY);
+        }
+
+        // SAFETY:
+        // `pdev` is valid by the invariants of `Device`.
+        // `num` is checked for validity by a previous call to `Device::resource_len`.
+        // `name` is always valid.
+        let ioptr: usize = unsafe { bindings::pci_iomap(pdev.as_raw(), num, 0) } as usize;
+        if ioptr == 0 {
+            // SAFETY:
+            // `pdev` valid by the invariants of `Device`.
+            // `num` is checked for validity by a previous call to `Device::resource_len`.
+            unsafe { bindings::pci_release_region(pdev.as_raw(), num) };
+            return Err(ENOMEM);
+        }
+
+        let io = match IoRaw::new(ioptr, len as usize) {
+            Ok(io) => io,
+            Err(err) => {
+                // SAFETY:
+                // `pdev` is valid by the invariants of `Device`.
+                // `ioptr` is guaranteed to be the start of a valid I/O mapped memory region.
+                // `num` is checked for validity by a previous call to `Device::resource_len`.
+                unsafe { Self::do_release(&pdev, ioptr, num) };
+                return Err(err);
+            }
+        };
+
+        Ok(Bar { pdev, io, num })
+    }
+
+    /// # Safety
+    ///
+    /// `ioptr` must be a valid pointer to the memory mapped PCI bar number `num`.
+    unsafe fn do_release(pdev: &Device, ioptr: usize, num: i32) {
+        // SAFETY:
+        // `pdev` is valid by the invariants of `Device`.
+        // `ioptr` is valid by the safety requirements.
+        // `num` is valid by the safety requirements.
+        unsafe {
+            bindings::pci_iounmap(pdev.as_raw(), ioptr as _);
+            bindings::pci_release_region(pdev.as_raw(), num);
+        }
+    }
+
+    fn release(&self) {
+        // SAFETY: The safety requirements are guaranteed by the type invariant of `self.pdev`.
+        unsafe { Self::do_release(&self.pdev, self.io.addr(), self.num) };
+    }
+}
+
+impl Bar {
+    fn index_is_valid(index: u32) -> bool {
+        // A `struct pci_dev` owns an array of resources with at most `PCI_NUM_RESOURCES` entries.
+        index < bindings::PCI_NUM_RESOURCES
+    }
+}
+
+impl<const SIZE: usize> Drop for Bar<SIZE> {
+    fn drop(&mut self) {
+        self.release();
+    }
+}
+
+impl<const SIZE: usize> Deref for Bar<SIZE> {
+    type Target = Io<SIZE>;
+
+    fn deref(&self) -> &Self::Target {
+        // SAFETY: By the type invariant of `Self`, the MMIO range in `self.io` is properly mapped.
+        unsafe { Io::from_raw(&self.io) }
+    }
+}
+
+impl Device {
+    /// Create a PCI Device instance from an existing `device::Device`.
+    ///
+    /// # Safety
+    ///
+    /// `dev` must be an `ARef<device::Device>` whose underlying `bindings::device` is a member of
+    /// a `bindings::pci_dev`.
+    pub unsafe fn from_dev(dev: ARef<device::Device>) -> Self {
+        Self(dev)
+    }
+
+    fn as_raw(&self) -> *mut bindings::pci_dev {
+        // SAFETY: By the type invariant `self.0.as_raw` is a pointer to the `struct device`
+        // embedded in `struct pci_dev`.
+        unsafe { container_of!(self.0.as_raw(), bindings::pci_dev, dev) as _ }
+    }
+
+    /// Returns the PCI vendor ID.
+    pub fn vendor_id(&self) -> u16 {
+        // SAFETY: `self.as_raw` is a valid pointer to a `struct pci_dev`.
+        unsafe { (*self.as_raw()).vendor }
+    }
+
+    /// Returns the PCI device ID.
+    pub fn device_id(&self) -> u16 {
+        // SAFETY: `self.as_raw` is a valid pointer to a `struct pci_dev`.
+        unsafe { (*self.as_raw()).device }
+    }
+
+    /// Enable memory resources for this device.
+    pub fn enable_device_mem(&self) -> Result {
+        // SAFETY: `self.as_raw` is guaranteed to be a pointer to a valid `struct pci_dev`.
+        let ret = unsafe { bindings::pci_enable_device_mem(self.as_raw()) };
+        if ret != 0 {
+            Err(Error::from_errno(ret))
+        } else {
+            Ok(())
+        }
+    }
+
+    /// Enable bus-mastering for this device.
+    pub fn set_master(&self) {
+        // SAFETY: `self.as_raw` is guaranteed to be a pointer to a valid `struct pci_dev`.
+        unsafe { bindings::pci_set_master(self.as_raw()) };
+    }
+
+    /// Returns the size of the given PCI bar resource.
+    pub fn resource_len(&self, bar: u32) -> Result<bindings::resource_size_t> {
+        if !Bar::index_is_valid(bar) {
+            return Err(EINVAL);
+        }
+
+        // SAFETY:
+        // - `bar` is a valid bar number, as guaranteed by the above call to `Bar::index_is_valid`,
+        // - by its type invariant `self.as_raw` is always a valid pointer to a `struct pci_dev`.
+        Ok(unsafe { bindings::pci_resource_len(self.as_raw(), bar.try_into()?) })
+    }
+
+    /// Mapps an entire PCI-BAR after performing a region-request on it. I/O operation bound checks
+    /// can be performed on compile time for offsets (plus the requested type size) < SIZE.
+    pub fn iomap_region_sized<const SIZE: usize>(
+        &self,
+        bar: u32,
+        name: &CStr,
+    ) -> Result<Devres<Bar<SIZE>>> {
+        let bar = Bar::<SIZE>::new(self.clone(), bar, name)?;
+        let devres = Devres::new(self.as_ref(), bar, GFP_KERNEL)?;
+
+        Ok(devres)
+    }
+
+    /// Mapps an entire PCI-BAR after performing a region-request on it.
+    pub fn iomap_region(&self, bar: u32, name: &CStr) -> Result<Devres<Bar>> {
+        self.iomap_region_sized::<0>(bar, name)
+    }
+}
+
+impl AsRef<device::Device> for Device {
+    fn as_ref(&self) -> &device::Device {
+        &self.0
+    }
+}
diff --git a/rust/kernel/platform.rs b/rust/kernel/platform.rs
new file mode 100644
index 000000000000..50e6b0421813
--- /dev/null
+++ b/rust/kernel/platform.rs
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Abstractions for the platform bus.
+//!
+//! C header: [`include/linux/platform_device.h`](srctree/include/linux/platform_device.h)
+
+use crate::{
+    bindings, container_of, device, driver,
+    error::{to_result, Result},
+    of,
+    prelude::*,
+    str::CStr,
+    types::{ARef, ForeignOwnable, Opaque},
+    ThisModule,
+};
+
+use core::ptr::addr_of_mut;
+
+/// An adapter for the registration of platform drivers.
+pub struct Adapter<T: Driver>(T);
+
+// SAFETY: A call to `unregister` for a given instance of `RegType` is guaranteed to be valid if
+// a preceding call to `register` has been successful.
+unsafe impl<T: Driver + 'static> driver::RegistrationOps for Adapter<T> {
+    type RegType = bindings::platform_driver;
+
+    unsafe fn register(
+        pdrv: &Opaque<Self::RegType>,
+        name: &'static CStr,
+        module: &'static ThisModule,
+    ) -> Result {
+        let of_table = match T::OF_ID_TABLE {
+            Some(table) => table.as_ptr(),
+            None => core::ptr::null(),
+        };
+
+        // SAFETY: It's safe to set the fields of `struct platform_driver` on initialization.
+        unsafe {
+            (*pdrv.get()).driver.name = name.as_char_ptr();
+            (*pdrv.get()).probe = Some(Self::probe_callback);
+            (*pdrv.get()).remove = Some(Self::remove_callback);
+            (*pdrv.get()).driver.of_match_table = of_table;
+        }
+
+        // SAFETY: `pdrv` is guaranteed to be a valid `RegType`.
+        to_result(unsafe { bindings::__platform_driver_register(pdrv.get(), module.0) })
+    }
+
+    unsafe fn unregister(pdrv: &Opaque<Self::RegType>) {
+        // SAFETY: `pdrv` is guaranteed to be a valid `RegType`.
+        unsafe { bindings::platform_driver_unregister(pdrv.get()) };
+    }
+}
+
+impl<T: Driver + 'static> Adapter<T> {
+    extern "C" fn probe_callback(pdev: *mut bindings::platform_device) -> kernel::ffi::c_int {
+        // SAFETY: The platform bus only ever calls the probe callback with a valid `pdev`.
+        let dev = unsafe { device::Device::get_device(addr_of_mut!((*pdev).dev)) };
+        // SAFETY: `dev` is guaranteed to be embedded in a valid `struct platform_device` by the
+        // call above.
+        let mut pdev = unsafe { Device::from_dev(dev) };
+
+        let info = <Self as driver::Adapter>::id_info(pdev.as_ref());
+        match T::probe(&mut pdev, info) {
+            Ok(data) => {
+                // Let the `struct platform_device` own a reference of the driver's private data.
+                // SAFETY: By the type invariant `pdev.as_raw` returns a valid pointer to a
+                // `struct platform_device`.
+                unsafe { bindings::platform_set_drvdata(pdev.as_raw(), data.into_foreign() as _) };
+            }
+            Err(err) => return Error::to_errno(err),
+        }
+
+        0
+    }
+
+    extern "C" fn remove_callback(pdev: *mut bindings::platform_device) {
+        // SAFETY: `pdev` is a valid pointer to a `struct platform_device`.
+        let ptr = unsafe { bindings::platform_get_drvdata(pdev) };
+
+        // SAFETY: `remove_callback` is only ever called after a successful call to
+        // `probe_callback`, hence it's guaranteed that `ptr` points to a valid and initialized
+        // `KBox<T>` pointer created through `KBox::into_foreign`.
+        let _ = unsafe { KBox::<T>::from_foreign(ptr) };
+    }
+}
+
+impl<T: Driver + 'static> driver::Adapter for Adapter<T> {
+    type IdInfo = T::IdInfo;
+
+    fn of_id_table() -> Option<of::IdTable<Self::IdInfo>> {
+        T::OF_ID_TABLE
+    }
+}
+
+/// Declares a kernel module that exposes a single platform driver.
+///
+/// # Examples
+///
+/// ```ignore
+/// kernel::module_platform_driver! {
+///     type: MyDriver,
+///     name: "Module name",
+///     author: "Author name",
+///     description: "Description",
+///     license: "GPL v2",
+/// }
+/// ```
+#[macro_export]
+macro_rules! module_platform_driver {
+    ($($f:tt)*) => {
+        $crate::module_driver!(<T>, $crate::platform::Adapter<T>, { $($f)* });
+    };
+}
+
+/// The platform driver trait.
+///
+/// Drivers must implement this trait in order to get a platform driver registered.
+///
+/// # Example
+///
+///```
+/// # use kernel::{bindings, c_str, of, platform};
+///
+/// struct MyDriver;
+///
+/// kernel::of_device_table!(
+///     OF_TABLE,
+///     MODULE_OF_TABLE,
+///     <MyDriver as platform::Driver>::IdInfo,
+///     [
+///         (of::DeviceId::new(c_str!("test,device")), ())
+///     ]
+/// );
+///
+/// impl platform::Driver for MyDriver {
+///     type IdInfo = ();
+///     const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = Some(&OF_TABLE);
+///
+///     fn probe(
+///         _pdev: &mut platform::Device,
+///         _id_info: Option<&Self::IdInfo>,
+///     ) -> Result<Pin<KBox<Self>>> {
+///         Err(ENODEV)
+///     }
+/// }
+///```
+pub trait Driver {
+    /// The type holding driver private data about each device id supported by the driver.
+    ///
+    /// TODO: Use associated_type_defaults once stabilized:
+    ///
+    /// type IdInfo: 'static = ();
+    type IdInfo: 'static;
+
+    /// The table of OF device ids supported by the driver.
+    const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>>;
+
+    /// Platform driver probe.
+    ///
+    /// Called when a new platform device is added or discovered.
+    /// Implementers should attempt to initialize the device here.
+    fn probe(dev: &mut Device, id_info: Option<&Self::IdInfo>) -> Result<Pin<KBox<Self>>>;
+}
+
+/// The platform device representation.
+///
+/// A platform device is based on an always reference counted `device:Device` instance. Cloning a
+/// platform device, hence, also increments the base device' reference count.
+///
+/// # Invariants
+///
+/// `Device` holds a valid reference of `ARef<device::Device>` whose underlying `struct device` is a
+/// member of a `struct platform_device`.
+#[derive(Clone)]
+pub struct Device(ARef<device::Device>);
+
+impl Device {
+    /// Convert a raw kernel device into a `Device`
+    ///
+    /// # Safety
+    ///
+    /// `dev` must be an `Aref<device::Device>` whose underlying `bindings::device` is a member of a
+    /// `bindings::platform_device`.
+    unsafe fn from_dev(dev: ARef<device::Device>) -> Self {
+        Self(dev)
+    }
+
+    fn as_raw(&self) -> *mut bindings::platform_device {
+        // SAFETY: By the type invariant `self.0.as_raw` is a pointer to the `struct device`
+        // embedded in `struct platform_device`.
+        unsafe { container_of!(self.0.as_raw(), bindings::platform_device, dev) }.cast_mut()
+    }
+}
+
+impl AsRef<device::Device> for Device {
+    fn as_ref(&self) -> &device::Device {
+        &self.0
+    }
+}
diff --git a/rust/kernel/revocable.rs b/rust/kernel/revocable.rs
new file mode 100644
index 000000000000..1e5a9d25c21b
--- /dev/null
+++ b/rust/kernel/revocable.rs
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Revocable objects.
+//!
+//! The [`Revocable`] type wraps other types and allows access to them to be revoked. The existence
+//! of a [`RevocableGuard`] ensures that objects remain valid.
+
+use crate::{bindings, prelude::*, sync::rcu, types::Opaque};
+use core::{
+    marker::PhantomData,
+    ops::Deref,
+    ptr::drop_in_place,
+    sync::atomic::{AtomicBool, Ordering},
+};
+
+/// An object that can become inaccessible at runtime.
+///
+/// Once access is revoked and all concurrent users complete (i.e., all existing instances of
+/// [`RevocableGuard`] are dropped), the wrapped object is also dropped.
+///
+/// # Examples
+///
+/// ```
+/// # use kernel::revocable::Revocable;
+///
+/// struct Example {
+///     a: u32,
+///     b: u32,
+/// }
+///
+/// fn add_two(v: &Revocable<Example>) -> Option<u32> {
+///     let guard = v.try_access()?;
+///     Some(guard.a + guard.b)
+/// }
+///
+/// let v = KBox::pin_init(Revocable::new(Example { a: 10, b: 20 }), GFP_KERNEL).unwrap();
+/// assert_eq!(add_two(&v), Some(30));
+/// v.revoke();
+/// assert_eq!(add_two(&v), None);
+/// ```
+///
+/// Sample example as above, but explicitly using the rcu read side lock.
+///
+/// ```
+/// # use kernel::revocable::Revocable;
+/// use kernel::sync::rcu;
+///
+/// struct Example {
+///     a: u32,
+///     b: u32,
+/// }
+///
+/// fn add_two(v: &Revocable<Example>) -> Option<u32> {
+///     let guard = rcu::read_lock();
+///     let e = v.try_access_with_guard(&guard)?;
+///     Some(e.a + e.b)
+/// }
+///
+/// let v = KBox::pin_init(Revocable::new(Example { a: 10, b: 20 }), GFP_KERNEL).unwrap();
+/// assert_eq!(add_two(&v), Some(30));
+/// v.revoke();
+/// assert_eq!(add_two(&v), None);
+/// ```
+#[pin_data(PinnedDrop)]
+pub struct Revocable<T> {
+    is_available: AtomicBool,
+    #[pin]
+    data: Opaque<T>,
+}
+
+// SAFETY: `Revocable` is `Send` if the wrapped object is also `Send`. This is because while the
+// functionality exposed by `Revocable` can be accessed from any thread/CPU, it is possible that
+// this isn't supported by the wrapped object.
+unsafe impl<T: Send> Send for Revocable<T> {}
+
+// SAFETY: `Revocable` is `Sync` if the wrapped object is both `Send` and `Sync`. We require `Send`
+// from the wrapped object as well because  of `Revocable::revoke`, which can trigger the `Drop`
+// implementation of the wrapped object from an arbitrary thread.
+unsafe impl<T: Sync + Send> Sync for Revocable<T> {}
+
+impl<T> Revocable<T> {
+    /// Creates a new revocable instance of the given data.
+    pub fn new(data: impl PinInit<T>) -> impl PinInit<Self> {
+        pin_init!(Self {
+            is_available: AtomicBool::new(true),
+            data <- Opaque::pin_init(data),
+        })
+    }
+
+    /// Tries to access the revocable wrapped object.
+    ///
+    /// Returns `None` if the object has been revoked and is therefore no longer accessible.
+    ///
+    /// Returns a guard that gives access to the object otherwise; the object is guaranteed to
+    /// remain accessible while the guard is alive. In such cases, callers are not allowed to sleep
+    /// because another CPU may be waiting to complete the revocation of this object.
+    pub fn try_access(&self) -> Option<RevocableGuard<'_, T>> {
+        let guard = rcu::read_lock();
+        if self.is_available.load(Ordering::Relaxed) {
+            // Since `self.is_available` is true, data is initialised and has to remain valid
+            // because the RCU read side lock prevents it from being dropped.
+            Some(RevocableGuard::new(self.data.get(), guard))
+        } else {
+            None
+        }
+    }
+
+    /// Tries to access the revocable wrapped object.
+    ///
+    /// Returns `None` if the object has been revoked and is therefore no longer accessible.
+    ///
+    /// Returns a shared reference to the object otherwise; the object is guaranteed to
+    /// remain accessible while the rcu read side guard is alive. In such cases, callers are not
+    /// allowed to sleep because another CPU may be waiting to complete the revocation of this
+    /// object.
+    pub fn try_access_with_guard<'a>(&'a self, _guard: &'a rcu::Guard) -> Option<&'a T> {
+        if self.is_available.load(Ordering::Relaxed) {
+            // SAFETY: Since `self.is_available` is true, data is initialised and has to remain
+            // valid because the RCU read side lock prevents it from being dropped.
+            Some(unsafe { &*self.data.get() })
+        } else {
+            None
+        }
+    }
+
+    /// # Safety
+    ///
+    /// Callers must ensure that there are no more concurrent users of the revocable object.
+    unsafe fn revoke_internal<const SYNC: bool>(&self) {
+        if self.is_available.swap(false, Ordering::Relaxed) {
+            if SYNC {
+                // SAFETY: Just an FFI call, there are no further requirements.
+                unsafe { bindings::synchronize_rcu() };
+            }
+
+            // SAFETY: We know `self.data` is valid because only one CPU can succeed the
+            // `compare_exchange` above that takes `is_available` from `true` to `false`.
+            unsafe { drop_in_place(self.data.get()) };
+        }
+    }
+
+    /// Revokes access to and drops the wrapped object.
+    ///
+    /// Access to the object is revoked immediately to new callers of [`Revocable::try_access`],
+    /// expecting that there are no concurrent users of the object.
+    ///
+    /// # Safety
+    ///
+    /// Callers must ensure that there are no more concurrent users of the revocable object.
+    pub unsafe fn revoke_nosync(&self) {
+        // SAFETY: By the safety requirement of this function, the caller ensures that nobody is
+        // accessing the data anymore and hence we don't have to wait for the grace period to
+        // finish.
+        unsafe { self.revoke_internal::<false>() }
+    }
+
+    /// Revokes access to and drops the wrapped object.
+    ///
+    /// Access to the object is revoked immediately to new callers of [`Revocable::try_access`].
+    ///
+    /// If there are concurrent users of the object (i.e., ones that called
+    /// [`Revocable::try_access`] beforehand and still haven't dropped the returned guard), this
+    /// function waits for the concurrent access to complete before dropping the wrapped object.
+    pub fn revoke(&self) {
+        // SAFETY: By passing `true` we ask `revoke_internal` to wait for the grace period to
+        // finish.
+        unsafe { self.revoke_internal::<true>() }
+    }
+}
+
+#[pinned_drop]
+impl<T> PinnedDrop for Revocable<T> {
+    fn drop(self: Pin<&mut Self>) {
+        // Drop only if the data hasn't been revoked yet (in which case it has already been
+        // dropped).
+        // SAFETY: We are not moving out of `p`, only dropping in place
+        let p = unsafe { self.get_unchecked_mut() };
+        if *p.is_available.get_mut() {
+            // SAFETY: We know `self.data` is valid because no other CPU has changed
+            // `is_available` to `false` yet, and no other CPU can do it anymore because this CPU
+            // holds the only reference (mutable) to `self` now.
+            unsafe { drop_in_place(p.data.get()) };
+        }
+    }
+}
+
+/// A guard that allows access to a revocable object and keeps it alive.
+///
+/// CPUs may not sleep while holding on to [`RevocableGuard`] because it's in atomic context
+/// holding the RCU read-side lock.
+///
+/// # Invariants
+///
+/// The RCU read-side lock is held while the guard is alive.
+pub struct RevocableGuard<'a, T> {
+    data_ref: *const T,
+    _rcu_guard: rcu::Guard,
+    _p: PhantomData<&'a ()>,
+}
+
+impl<T> RevocableGuard<'_, T> {
+    fn new(data_ref: *const T, rcu_guard: rcu::Guard) -> Self {
+        Self {
+            data_ref,
+            _rcu_guard: rcu_guard,
+            _p: PhantomData,
+        }
+    }
+}
+
+impl<T> Deref for RevocableGuard<'_, T> {
+    type Target = T;
+
+    fn deref(&self) -> &Self::Target {
+        // SAFETY: By the type invariants, we hold the rcu read-side lock, so the object is
+        // guaranteed to remain valid.
+        unsafe { &*self.data_ref }
+    }
+}
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index dffdaad972ce..3498fb344dc9 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -12,6 +12,7 @@ mod condvar;
 pub mod lock;
 mod locked_by;
 pub mod poll;
+pub mod rcu;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
 pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
diff --git a/rust/kernel/sync/rcu.rs b/rust/kernel/sync/rcu.rs
new file mode 100644
index 000000000000..b51d9150ffe2
--- /dev/null
+++ b/rust/kernel/sync/rcu.rs
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! RCU support.
+//!
+//! C header: [`include/linux/rcupdate.h`](srctree/include/linux/rcupdate.h)
+
+use crate::{bindings, types::NotThreadSafe};
+
+/// Evidence that the RCU read side lock is held on the current thread/CPU.
+///
+/// The type is explicitly not `Send` because this property is per-thread/CPU.
+///
+/// # Invariants
+///
+/// The RCU read side lock is actually held while instances of this guard exist.
+pub struct Guard(NotThreadSafe);
+
+impl Guard {
+    /// Acquires the RCU read side lock and returns a guard.
+    pub fn new() -> Self {
+        // SAFETY: An FFI call with no additional requirements.
+        unsafe { bindings::rcu_read_lock() };
+        // INVARIANT: The RCU read side lock was just acquired above.
+        Self(NotThreadSafe)
+    }
+
+    /// Explicitly releases the RCU read side lock.
+    pub fn unlock(self) {}
+}
+
+impl Default for Guard {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl Drop for Guard {
+    fn drop(&mut self) {
+        // SAFETY: By the type invariants, the RCU read side is locked, so it is ok to unlock it.
+        unsafe { bindings::rcu_read_unlock() };
+    }
+}
+
+/// Acquires the RCU read side lock.
+pub fn read_lock() -> Guard {
+    Guard::new()
+}
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index 0dfaf45a755c..2bbaab83b9d6 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -326,6 +326,17 @@ impl<T> Opaque<T> {
         }
     }
 
+    /// Create an opaque pin-initializer from the given pin-initializer.
+    pub fn pin_init(slot: impl PinInit<T>) -> impl PinInit<Self> {
+        Self::ffi_init(|ptr: *mut T| {
+            // SAFETY:
+            //   - `ptr` is a valid pointer to uninitialized memory,
+            //   - `slot` is not accessed on error; the call is infallible,
+            //   - `slot` is pinned in memory.
+            let _ = unsafe { init::PinInit::<T>::__pinned_init(slot, ptr) };
+        })
+    }
+
     /// Creates a pin-initializer from the given initializer closure.
     ///
     /// The returned initializer calls the given closure with the pointer to the inner `T` of this
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index 2587f41b0d39..cdf94f4982df 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -228,6 +228,10 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
                 kernel::ThisModule::from_ptr(core::ptr::null_mut())
             }};
 
+            impl kernel::ModuleMetadata for {type_} {{
+                const NAME: &'static kernel::str::CStr = kernel::c_str!(\"{name}\");
+            }}
+
             // Double nested modules, since then nobody can access the public items inside.
             mod __module_init {{
                 mod __module_init {{
diff --git a/samples/Kconfig b/samples/Kconfig
index 84a9d4e8d947..820e00b2ed68 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -302,6 +302,8 @@ config SAMPLE_CHECK_EXEC
 
 source "samples/rust/Kconfig"
 
+source "samples/damon/Kconfig"
+
 endif # SAMPLES
 
 config HAVE_SAMPLE_FTRACE_DIRECT
diff --git a/samples/Makefile b/samples/Makefile
index f988202f3a30..f24cd0d72dd0 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -40,3 +40,5 @@ obj-$(CONFIG_SAMPLE_KMEMLEAK)		+= kmemleak/
 obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG)	+= coresight/
 obj-$(CONFIG_SAMPLE_FPROBE)		+= fprobe/
 obj-$(CONFIG_SAMPLES_RUST)		+= rust/
+obj-$(CONFIG_SAMPLE_DAMON_WSSE)		+= damon/
+obj-$(CONFIG_SAMPLE_DAMON_PRCL)		+= damon/
diff --git a/samples/check-exec/inc.c b/samples/check-exec/inc.c
index 94b87569d2a2..7f6ef06a2f06 100644
--- a/samples/check-exec/inc.c
+++ b/samples/check-exec/inc.c
@@ -21,8 +21,15 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/prctl.h>
+#include <sys/syscall.h>
 #include <unistd.h>
 
+static int sys_execveat(int dirfd, const char *pathname, char *const argv[],
+			char *const envp[], int flags)
+{
+	return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags);
+}
+
 /* Returns 1 on error, 0 otherwise. */
 static int interpret_buffer(char *buffer, size_t buffer_size)
 {
@@ -78,8 +85,8 @@ static int interpret_stream(FILE *script, char *const script_name,
 	 * script execution.  We must use the script file descriptor instead of
 	 * the script path name to avoid race conditions.
 	 */
-	err = execveat(fileno(script), "", script_argv, envp,
-		       AT_EMPTY_PATH | AT_EXECVE_CHECK);
+	err = sys_execveat(fileno(script), "", script_argv, envp,
+			   AT_EMPTY_PATH | AT_EXECVE_CHECK);
 	if (err && restrict_stream) {
 		perror("ERROR: Script execution check");
 		return 1;
diff --git a/samples/damon/Kconfig b/samples/damon/Kconfig
new file mode 100644
index 000000000000..63f6dcd71daa
--- /dev/null
+++ b/samples/damon/Kconfig
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+
+menu "DAMON Samples"
+
+config SAMPLE_DAMON_WSSE
+	bool "DAMON sameple module for working set size estimation"
+	depends on DAMON && DAMON_VADDR
+	help
+	  This builds DAMON sample module for working set size estimation.
+
+	  The module receives a pid, monitor access to the virtual address
+	  space of the process, estimate working set size of the process, and
+	  repeatedly prints the size on the kernel log.
+
+	  If unsure, say N.
+
+config SAMPLE_DAMON_PRCL
+	bool "DAMON sameple module for access-aware proactive reclamation"
+	depends on DAMON && DAMON_VADDR
+	help
+	  This builds DAMON sample module for access-aware proactive
+	  reclamation.
+
+	  The module receives a pid, monitor access to the virtual address
+	  space of the process, find memory regions that not accessed, and
+	  proactively reclaim the regions.
+
+	  If unsure, say N.
+
+endmenu
diff --git a/samples/damon/Makefile b/samples/damon/Makefile
new file mode 100644
index 000000000000..7f155143f237
--- /dev/null
+++ b/samples/damon/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_SAMPLE_DAMON_WSSE) += wsse.o
+obj-$(CONFIG_SAMPLE_DAMON_PRCL) += prcl.o
diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c
new file mode 100644
index 000000000000..c3acbdab7a62
--- /dev/null
+++ b/samples/damon/prcl.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * proactive reclamation: monitor access pattern of a given process, find
+ * regiosn that seems not accessed, and proactively page out the regions.
+ */
+
+#define pr_fmt(fmt) "damon_sample_prcl: " fmt
+
+#include <linux/damon.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static int target_pid __read_mostly;
+module_param(target_pid, int, 0600);
+
+static int damon_sample_prcl_enable_store(
+		const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops enable_param_ops = {
+	.set = damon_sample_prcl_enable_store,
+	.get = param_get_bool,
+};
+
+static bool enable __read_mostly;
+module_param_cb(enable, &enable_param_ops, &enable, 0600);
+MODULE_PARM_DESC(enable, "Enable of disable DAMON_SAMPLE_WSSE");
+
+static struct damon_ctx *ctx;
+static struct pid *target_pidp;
+
+static int damon_sample_prcl_after_aggregate(struct damon_ctx *c)
+{
+	struct damon_target *t;
+
+	damon_for_each_target(t, c) {
+		struct damon_region *r;
+		unsigned long wss = 0;
+
+		damon_for_each_region(r, t) {
+			if (r->nr_accesses > 0)
+				wss += r->ar.end - r->ar.start;
+		}
+		pr_info("wss: %lu\n", wss);
+	}
+	return 0;
+}
+
+static int damon_sample_prcl_start(void)
+{
+	struct damon_target *target;
+	struct damos *scheme;
+
+	pr_info("start\n");
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return -ENOMEM;
+	if (damon_select_ops(ctx, DAMON_OPS_VADDR)) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+
+	target = damon_new_target();
+	if (!target) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_add_target(ctx, target);
+	target_pidp = find_get_pid(target_pid);
+	if (!target_pidp) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+	target->pid = target_pidp;
+
+	ctx->callback.after_aggregation = damon_sample_prcl_after_aggregate;
+
+	scheme = damon_new_scheme(
+			&(struct damos_access_pattern) {
+			.min_sz_region = PAGE_SIZE,
+			.max_sz_region = ULONG_MAX,
+			.min_nr_accesses = 0,
+			.max_nr_accesses = 0,
+			.min_age_region = 50,
+			.max_age_region = UINT_MAX},
+			DAMOS_PAGEOUT,
+			0,
+			&(struct damos_quota){},
+			&(struct damos_watermarks){},
+			NUMA_NO_NODE);
+	if (!scheme) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_set_schemes(ctx, &scheme, 1);
+
+	return damon_start(&ctx, 1, true);
+}
+
+static void damon_sample_prcl_stop(void)
+{
+	pr_info("stop\n");
+	if (ctx) {
+		damon_stop(&ctx, 1);
+		damon_destroy_ctx(ctx);
+	}
+	if (target_pidp)
+		put_pid(target_pidp);
+}
+
+static int damon_sample_prcl_enable_store(
+		const char *val, const struct kernel_param *kp)
+{
+	bool enabled = enable;
+	int err;
+
+	err = kstrtobool(val, &enable);
+	if (err)
+		return err;
+
+	if (enable == enabled)
+		return 0;
+
+	if (enable)
+		return damon_sample_prcl_start();
+	damon_sample_prcl_stop();
+	return 0;
+}
+
+static int __init damon_sample_prcl_init(void)
+{
+	return 0;
+}
+
+module_init(damon_sample_prcl_init);
diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c
new file mode 100644
index 000000000000..11be25803274
--- /dev/null
+++ b/samples/damon/wsse.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * working set size estimation: monitor access pattern of given process and
+ * print estimated working set size (total size of regions that showing some
+ * access).
+ */
+
+#define pr_fmt(fmt) "damon_sample_wsse: " fmt
+
+#include <linux/damon.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static int target_pid __read_mostly;
+module_param(target_pid, int, 0600);
+
+static int damon_sample_wsse_enable_store(
+		const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops enable_param_ops = {
+	.set = damon_sample_wsse_enable_store,
+	.get = param_get_bool,
+};
+
+static bool enable __read_mostly;
+module_param_cb(enable, &enable_param_ops, &enable, 0600);
+MODULE_PARM_DESC(enable, "Enable or disable DAMON_SAMPLE_WSSE");
+
+static struct damon_ctx *ctx;
+static struct pid *target_pidp;
+
+static int damon_sample_wsse_after_aggregate(struct damon_ctx *c)
+{
+	struct damon_target *t;
+
+	damon_for_each_target(t, c) {
+		struct damon_region *r;
+		unsigned long wss = 0;
+
+		damon_for_each_region(r, t) {
+			if (r->nr_accesses > 0)
+				wss += r->ar.end - r->ar.start;
+		}
+		pr_info("wss: %lu\n", wss);
+	}
+	return 0;
+}
+
+static int damon_sample_wsse_start(void)
+{
+	struct damon_target *target;
+
+	pr_info("start\n");
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return -ENOMEM;
+	if (damon_select_ops(ctx, DAMON_OPS_VADDR)) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+
+	target = damon_new_target();
+	if (!target) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_add_target(ctx, target);
+	target_pidp = find_get_pid(target_pid);
+	if (!target_pidp) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+	target->pid = target_pidp;
+
+	ctx->callback.after_aggregation = damon_sample_wsse_after_aggregate;
+	return damon_start(&ctx, 1, true);
+}
+
+static void damon_sample_wsse_stop(void)
+{
+	pr_info("stop\n");
+	if (ctx) {
+		damon_stop(&ctx, 1);
+		damon_destroy_ctx(ctx);
+	}
+	if (target_pidp)
+		put_pid(target_pidp);
+}
+
+static int damon_sample_wsse_enable_store(
+		const char *val, const struct kernel_param *kp)
+{
+	bool enabled = enable;
+	int err;
+
+	err = kstrtobool(val, &enable);
+	if (err)
+		return err;
+
+	if (enable == enabled)
+		return 0;
+
+	if (enable)
+		return damon_sample_wsse_start();
+	damon_sample_wsse_stop();
+	return 0;
+}
+
+static int __init damon_sample_wsse_init(void)
+{
+	return 0;
+}
+
+module_init(damon_sample_wsse_init);
diff --git a/samples/hid/Makefile b/samples/hid/Makefile
index 8ea59e9631a3..db5a077c77fc 100644
--- a/samples/hid/Makefile
+++ b/samples/hid/Makefile
@@ -40,16 +40,17 @@ BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-generic
 endif
 endif
 
-TPROGS_CFLAGS += -Wall -O2
-TPROGS_CFLAGS += -Wmissing-prototypes
-TPROGS_CFLAGS += -Wstrict-prototypes
+COMMON_CFLAGS += -Wall -O2
+COMMON_CFLAGS += -Wmissing-prototypes
+COMMON_CFLAGS += -Wstrict-prototypes
 
+TPROGS_CFLAGS += $(COMMON_CFLAGS)
 TPROGS_CFLAGS += -I$(objtree)/usr/include
 TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE)
 TPROGS_CFLAGS += -I$(srctree)/tools/include
 
 ifdef SYSROOT
-TPROGS_CFLAGS += --sysroot=$(SYSROOT)
+COMMON_CFLAGS += --sysroot=$(SYSROOT)
 TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib
 endif
 
@@ -112,7 +113,7 @@ clean:
 
 $(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT)
 # Fix up variables inherited from Kbuild that tools/ build system won't like
-	$(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \
+	$(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(COMMON_CFLAGS)" \
 		LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(HID_SAMPLES_PATH)/../../ \
 		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
 		$@ install_headers
@@ -163,7 +164,7 @@ $(obj)/hid_surface_dial.o: $(obj)/hid_surface_dial.skel.h
 
 VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux))				\
 		     $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux))	\
-		     $(abspath ./vmlinux)
+		     $(abspath $(objtree)/vmlinux)
 VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
 
 $(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
diff --git a/samples/livepatch/livepatch-callbacks-busymod.c b/samples/livepatch/livepatch-callbacks-busymod.c
index 378e2d40271a..69105596e72e 100644
--- a/samples/livepatch/livepatch-callbacks-busymod.c
+++ b/samples/livepatch/livepatch-callbacks-busymod.c
@@ -44,8 +44,7 @@ static void busymod_work_func(struct work_struct *work)
 static int livepatch_callbacks_mod_init(void)
 {
 	pr_info("%s\n", __func__);
-	schedule_delayed_work(&work,
-		msecs_to_jiffies(1000 * 0));
+	schedule_delayed_work(&work, 0);
 	return 0;
 }
 
diff --git a/samples/livepatch/livepatch-shadow-fix1.c b/samples/livepatch/livepatch-shadow-fix1.c
index 6701641bf12d..f3f153895d6c 100644
--- a/samples/livepatch/livepatch-shadow-fix1.c
+++ b/samples/livepatch/livepatch-shadow-fix1.c
@@ -72,8 +72,7 @@ static struct dummy *livepatch_fix1_dummy_alloc(void)
 	if (!d)
 		return NULL;
 
-	d->jiffies_expire = jiffies +
-		msecs_to_jiffies(1000 * EXPIRE_PERIOD);
+	d->jiffies_expire = jiffies + secs_to_jiffies(EXPIRE_PERIOD);
 
 	/*
 	 * Patch: save the extra memory location into a SV_LEAK shadow
diff --git a/samples/livepatch/livepatch-shadow-mod.c b/samples/livepatch/livepatch-shadow-mod.c
index 7e753b0d2fa6..5d83ad5a8118 100644
--- a/samples/livepatch/livepatch-shadow-mod.c
+++ b/samples/livepatch/livepatch-shadow-mod.c
@@ -101,8 +101,7 @@ static __used noinline struct dummy *dummy_alloc(void)
 	if (!d)
 		return NULL;
 
-	d->jiffies_expire = jiffies +
-		msecs_to_jiffies(1000 * EXPIRE_PERIOD);
+	d->jiffies_expire = jiffies + secs_to_jiffies(EXPIRE_PERIOD);
 
 	/* Oops, forgot to save leak! */
 	leak = kzalloc(sizeof(*leak), GFP_KERNEL);
@@ -152,8 +151,7 @@ static void alloc_work_func(struct work_struct *work)
 	list_add(&d->list, &dummy_list);
 	mutex_unlock(&dummy_list_mutex);
 
-	schedule_delayed_work(&alloc_dwork,
-		msecs_to_jiffies(1000 * ALLOC_PERIOD));
+	schedule_delayed_work(&alloc_dwork, secs_to_jiffies(ALLOC_PERIOD));
 }
 
 /*
@@ -184,16 +182,13 @@ static void cleanup_work_func(struct work_struct *work)
 	}
 	mutex_unlock(&dummy_list_mutex);
 
-	schedule_delayed_work(&cleanup_dwork,
-		msecs_to_jiffies(1000 * CLEANUP_PERIOD));
+	schedule_delayed_work(&cleanup_dwork, secs_to_jiffies(CLEANUP_PERIOD));
 }
 
 static int livepatch_shadow_mod_init(void)
 {
-	schedule_delayed_work(&alloc_dwork,
-		msecs_to_jiffies(1000 * ALLOC_PERIOD));
-	schedule_delayed_work(&cleanup_dwork,
-		msecs_to_jiffies(1000 * CLEANUP_PERIOD));
+	schedule_delayed_work(&alloc_dwork, secs_to_jiffies(ALLOC_PERIOD));
+	schedule_delayed_work(&cleanup_dwork, secs_to_jiffies(CLEANUP_PERIOD));
 
 	return 0;
 }
diff --git a/samples/rust/Kconfig b/samples/rust/Kconfig
index b0f74a81c8f9..918dbead2c0b 100644
--- a/samples/rust/Kconfig
+++ b/samples/rust/Kconfig
@@ -20,6 +20,16 @@ config SAMPLE_RUST_MINIMAL
 
 	  If unsure, say N.
 
+config SAMPLE_RUST_MISC_DEVICE
+	tristate "Misc device"
+	help
+	  This option builds the Rust misc device.
+
+	  To compile this as a module, choose M here:
+	  the module will be called rust_misc_device.
+
+	  If unsure, say N.
+
 config SAMPLE_RUST_PRINT
 	tristate "Printing macros"
 	help
@@ -30,6 +40,27 @@ config SAMPLE_RUST_PRINT
 
 	  If unsure, say N.
 
+config SAMPLE_RUST_DRIVER_PCI
+	tristate "PCI Driver"
+	depends on PCI
+	help
+	  This option builds the Rust PCI driver sample.
+
+	  To compile this as a module, choose M here:
+	  the module will be called driver_pci.
+
+	  If unsure, say N.
+
+config SAMPLE_RUST_DRIVER_PLATFORM
+	tristate "Platform Driver"
+	help
+	  This option builds the Rust Platform driver sample.
+
+	  To compile this as a module, choose M here:
+	  the module will be called rust_driver_platform.
+
+	  If unsure, say N.
+
 config SAMPLE_RUST_HOSTPROGS
 	bool "Host programs"
 	help
diff --git a/samples/rust/Makefile b/samples/rust/Makefile
index c1a5c1655395..5a8ab0df0567 100644
--- a/samples/rust/Makefile
+++ b/samples/rust/Makefile
@@ -2,7 +2,10 @@
 ccflags-y += -I$(src)				# needed for trace events
 
 obj-$(CONFIG_SAMPLE_RUST_MINIMAL)		+= rust_minimal.o
+obj-$(CONFIG_SAMPLE_RUST_MISC_DEVICE)		+= rust_misc_device.o
 obj-$(CONFIG_SAMPLE_RUST_PRINT)			+= rust_print.o
+obj-$(CONFIG_SAMPLE_RUST_DRIVER_PCI)		+= rust_driver_pci.o
+obj-$(CONFIG_SAMPLE_RUST_DRIVER_PLATFORM)	+= rust_driver_platform.o
 
 rust_print-y := rust_print_main.o rust_print_events.o
 
diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs
new file mode 100644
index 000000000000..1fb6e44f3395
--- /dev/null
+++ b/samples/rust/rust_driver_pci.rs
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Rust PCI driver sample (based on QEMU's `pci-testdev`).
+//!
+//! To make this driver probe, QEMU must be run with `-device pci-testdev`.
+
+use kernel::{bindings, c_str, devres::Devres, pci, prelude::*};
+
+struct Regs;
+
+impl Regs {
+    const TEST: usize = 0x0;
+    const OFFSET: usize = 0x4;
+    const DATA: usize = 0x8;
+    const COUNT: usize = 0xC;
+    const END: usize = 0x10;
+}
+
+type Bar0 = pci::Bar<{ Regs::END }>;
+
+#[derive(Debug)]
+struct TestIndex(u8);
+
+impl TestIndex {
+    const NO_EVENTFD: Self = Self(0);
+}
+
+struct SampleDriver {
+    pdev: pci::Device,
+    bar: Devres<Bar0>,
+}
+
+kernel::pci_device_table!(
+    PCI_TABLE,
+    MODULE_PCI_TABLE,
+    <SampleDriver as pci::Driver>::IdInfo,
+    [(
+        pci::DeviceId::from_id(bindings::PCI_VENDOR_ID_REDHAT, 0x5),
+        TestIndex::NO_EVENTFD
+    )]
+);
+
+impl SampleDriver {
+    fn testdev(index: &TestIndex, bar: &Bar0) -> Result<u32> {
+        // Select the test.
+        bar.writeb(index.0, Regs::TEST);
+
+        let offset = u32::from_le(bar.readl(Regs::OFFSET)) as usize;
+        let data = bar.readb(Regs::DATA);
+
+        // Write `data` to `offset` to increase `count` by one.
+        //
+        // Note that we need `try_writeb`, since `offset` can't be checked at compile-time.
+        bar.try_writeb(data, offset)?;
+
+        Ok(bar.readl(Regs::COUNT))
+    }
+}
+
+impl pci::Driver for SampleDriver {
+    type IdInfo = TestIndex;
+
+    const ID_TABLE: pci::IdTable<Self::IdInfo> = &PCI_TABLE;
+
+    fn probe(pdev: &mut pci::Device, info: &Self::IdInfo) -> Result<Pin<KBox<Self>>> {
+        dev_dbg!(
+            pdev.as_ref(),
+            "Probe Rust PCI driver sample (PCI ID: 0x{:x}, 0x{:x}).\n",
+            pdev.vendor_id(),
+            pdev.device_id()
+        );
+
+        pdev.enable_device_mem()?;
+        pdev.set_master();
+
+        let bar = pdev.iomap_region_sized::<{ Regs::END }>(0, c_str!("rust_driver_pci"))?;
+
+        let drvdata = KBox::new(
+            Self {
+                pdev: pdev.clone(),
+                bar,
+            },
+            GFP_KERNEL,
+        )?;
+
+        let bar = drvdata.bar.try_access().ok_or(ENXIO)?;
+
+        dev_info!(
+            pdev.as_ref(),
+            "pci-testdev data-match count: {}\n",
+            Self::testdev(info, &bar)?
+        );
+
+        Ok(drvdata.into())
+    }
+}
+
+impl Drop for SampleDriver {
+    fn drop(&mut self) {
+        dev_dbg!(self.pdev.as_ref(), "Remove Rust PCI driver sample.\n");
+    }
+}
+
+kernel::module_pci_driver! {
+    type: SampleDriver,
+    name: "rust_driver_pci",
+    author: "Danilo Krummrich",
+    description: "Rust PCI driver",
+    license: "GPL v2",
+}
diff --git a/samples/rust/rust_driver_platform.rs b/samples/rust/rust_driver_platform.rs
new file mode 100644
index 000000000000..8120609e2940
--- /dev/null
+++ b/samples/rust/rust_driver_platform.rs
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Rust Platform driver sample.
+
+use kernel::{c_str, of, platform, prelude::*};
+
+struct SampleDriver {
+    pdev: platform::Device,
+}
+
+struct Info(u32);
+
+kernel::of_device_table!(
+    OF_TABLE,
+    MODULE_OF_TABLE,
+    <SampleDriver as platform::Driver>::IdInfo,
+    [(of::DeviceId::new(c_str!("test,rust-device")), Info(42))]
+);
+
+impl platform::Driver for SampleDriver {
+    type IdInfo = Info;
+    const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = Some(&OF_TABLE);
+
+    fn probe(pdev: &mut platform::Device, info: Option<&Self::IdInfo>) -> Result<Pin<KBox<Self>>> {
+        dev_dbg!(pdev.as_ref(), "Probe Rust Platform driver sample.\n");
+
+        if let Some(info) = info {
+            dev_info!(pdev.as_ref(), "Probed with info: '{}'.\n", info.0);
+        }
+
+        let drvdata = KBox::new(Self { pdev: pdev.clone() }, GFP_KERNEL)?;
+
+        Ok(drvdata.into())
+    }
+}
+
+impl Drop for SampleDriver {
+    fn drop(&mut self) {
+        dev_dbg!(self.pdev.as_ref(), "Remove Rust Platform driver sample.\n");
+    }
+}
+
+kernel::module_platform_driver! {
+    type: SampleDriver,
+    name: "rust_driver_platform",
+    author: "Danilo Krummrich",
+    description: "Rust Platform driver",
+    license: "GPL v2",
+}
diff --git a/samples/rust/rust_misc_device.rs b/samples/rust/rust_misc_device.rs
new file mode 100644
index 000000000000..40ad7266c225
--- /dev/null
+++ b/samples/rust/rust_misc_device.rs
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 Google LLC.
+
+//! Rust misc device sample.
+
+/// Below is an example userspace C program that exercises this sample's functionality.
+///
+/// ```c
+/// #include <stdio.h>
+/// #include <stdlib.h>
+/// #include <errno.h>
+/// #include <fcntl.h>
+/// #include <unistd.h>
+/// #include <sys/ioctl.h>
+///
+/// #define RUST_MISC_DEV_FAIL _IO('|', 0)
+/// #define RUST_MISC_DEV_HELLO _IO('|', 0x80)
+/// #define RUST_MISC_DEV_GET_VALUE _IOR('|', 0x81, int)
+/// #define RUST_MISC_DEV_SET_VALUE _IOW('|', 0x82, int)
+///
+/// int main() {
+///   int value, new_value;
+///   int fd, ret;
+///
+///   // Open the device file
+///   printf("Opening /dev/rust-misc-device for reading and writing\n");
+///   fd = open("/dev/rust-misc-device", O_RDWR);
+///   if (fd < 0) {
+///     perror("open");
+///     return errno;
+///   }
+///
+///   // Make call into driver to say "hello"
+///   printf("Calling Hello\n");
+///   ret = ioctl(fd, RUST_MISC_DEV_HELLO, NULL);
+///   if (ret < 0) {
+///     perror("ioctl: Failed to call into Hello");
+///     close(fd);
+///     return errno;
+///   }
+///
+///   // Get initial value
+///   printf("Fetching initial value\n");
+///   ret = ioctl(fd, RUST_MISC_DEV_GET_VALUE, &value);
+///   if (ret < 0) {
+///     perror("ioctl: Failed to fetch the initial value");
+///     close(fd);
+///     return errno;
+///   }
+///
+///   value++;
+///
+///   // Set value to something different
+///   printf("Submitting new value (%d)\n", value);
+///   ret = ioctl(fd, RUST_MISC_DEV_SET_VALUE, &value);
+///   if (ret < 0) {
+///     perror("ioctl: Failed to submit new value");
+///     close(fd);
+///     return errno;
+///   }
+///
+///   // Ensure new value was applied
+///   printf("Fetching new value\n");
+///   ret = ioctl(fd, RUST_MISC_DEV_GET_VALUE, &new_value);
+///   if (ret < 0) {
+///     perror("ioctl: Failed to fetch the new value");
+///     close(fd);
+///     return errno;
+///   }
+///
+///   if (value != new_value) {
+///     printf("Failed: Committed and retrieved values are different (%d - %d)\n", value, new_value);
+///     close(fd);
+///     return -1;
+///   }
+///
+///   // Call the unsuccessful ioctl
+///   printf("Attempting to call in to an non-existent IOCTL\n");
+///   ret = ioctl(fd, RUST_MISC_DEV_FAIL, NULL);
+///   if (ret < 0) {
+///     perror("ioctl: Succeeded to fail - this was expected");
+///   } else {
+///     printf("ioctl: Failed to fail\n");
+///     close(fd);
+///     return -1;
+///   }
+///
+///   // Close the device file
+///   printf("Closing /dev/rust-misc-device\n");
+///   close(fd);
+///
+///   printf("Success\n");
+///   return 0;
+/// }
+/// ```
+use core::pin::Pin;
+
+use kernel::{
+    c_str,
+    device::Device,
+    fs::File,
+    ioctl::{_IO, _IOC_SIZE, _IOR, _IOW},
+    miscdevice::{MiscDevice, MiscDeviceOptions, MiscDeviceRegistration},
+    new_mutex,
+    prelude::*,
+    sync::Mutex,
+    types::ARef,
+    uaccess::{UserSlice, UserSliceReader, UserSliceWriter},
+};
+
+const RUST_MISC_DEV_HELLO: u32 = _IO('|' as u32, 0x80);
+const RUST_MISC_DEV_GET_VALUE: u32 = _IOR::<i32>('|' as u32, 0x81);
+const RUST_MISC_DEV_SET_VALUE: u32 = _IOW::<i32>('|' as u32, 0x82);
+
+module! {
+    type: RustMiscDeviceModule,
+    name: "rust_misc_device",
+    author: "Lee Jones",
+    description: "Rust misc device sample",
+    license: "GPL",
+}
+
+#[pin_data]
+struct RustMiscDeviceModule {
+    #[pin]
+    _miscdev: MiscDeviceRegistration<RustMiscDevice>,
+}
+
+impl kernel::InPlaceModule for RustMiscDeviceModule {
+    fn init(_module: &'static ThisModule) -> impl PinInit<Self, Error> {
+        pr_info!("Initialising Rust Misc Device Sample\n");
+
+        let options = MiscDeviceOptions {
+            name: c_str!("rust-misc-device"),
+        };
+
+        try_pin_init!(Self {
+            _miscdev <- MiscDeviceRegistration::register(options),
+        })
+    }
+}
+
+struct Inner {
+    value: i32,
+}
+
+#[pin_data(PinnedDrop)]
+struct RustMiscDevice {
+    #[pin]
+    inner: Mutex<Inner>,
+    dev: ARef<Device>,
+}
+
+#[vtable]
+impl MiscDevice for RustMiscDevice {
+    type Ptr = Pin<KBox<Self>>;
+
+    fn open(_file: &File, misc: &MiscDeviceRegistration<Self>) -> Result<Pin<KBox<Self>>> {
+        let dev = ARef::from(misc.device());
+
+        dev_info!(dev, "Opening Rust Misc Device Sample\n");
+
+        KBox::try_pin_init(
+            try_pin_init! {
+                RustMiscDevice {
+                    inner <- new_mutex!( Inner{ value: 0_i32 } ),
+                    dev: dev,
+                }
+            },
+            GFP_KERNEL,
+        )
+    }
+
+    fn ioctl(me: Pin<&RustMiscDevice>, _file: &File, cmd: u32, arg: usize) -> Result<isize> {
+        dev_info!(me.dev, "IOCTLing Rust Misc Device Sample\n");
+
+        let size = _IOC_SIZE(cmd);
+
+        match cmd {
+            RUST_MISC_DEV_GET_VALUE => me.get_value(UserSlice::new(arg, size).writer())?,
+            RUST_MISC_DEV_SET_VALUE => me.set_value(UserSlice::new(arg, size).reader())?,
+            RUST_MISC_DEV_HELLO => me.hello()?,
+            _ => {
+                dev_err!(me.dev, "-> IOCTL not recognised: {}\n", cmd);
+                return Err(ENOTTY);
+            }
+        };
+
+        Ok(0)
+    }
+}
+
+#[pinned_drop]
+impl PinnedDrop for RustMiscDevice {
+    fn drop(self: Pin<&mut Self>) {
+        dev_info!(self.dev, "Exiting the Rust Misc Device Sample\n");
+    }
+}
+
+impl RustMiscDevice {
+    fn set_value(&self, mut reader: UserSliceReader) -> Result<isize> {
+        let new_value = reader.read::<i32>()?;
+        let mut guard = self.inner.lock();
+
+        dev_info!(
+            self.dev,
+            "-> Copying data from userspace (value: {})\n",
+            new_value
+        );
+
+        guard.value = new_value;
+        Ok(0)
+    }
+
+    fn get_value(&self, mut writer: UserSliceWriter) -> Result<isize> {
+        let guard = self.inner.lock();
+        let value = guard.value;
+
+        // Free-up the lock and use our locally cached instance from here
+        drop(guard);
+
+        dev_info!(
+            self.dev,
+            "-> Copying data to userspace (value: {})\n",
+            &value
+        );
+
+        writer.write::<i32>(&value)?;
+        Ok(0)
+    }
+
+    fn hello(&self) -> Result<isize> {
+        dev_info!(self.dev, "-> Hello from the Rust Misc Device\n");
+
+        Ok(0)
+    }
+}
diff --git a/scripts/Makefile b/scripts/Makefile
index 546e8175e1c4..46f860529df5 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -53,7 +53,8 @@ hostprogs += unifdef gen_packed_field_checks
 targets += module.lds
 
 subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
-subdir-$(CONFIG_MODVERSIONS) += genksyms
+subdir-$(CONFIG_GENKSYMS) += genksyms
+subdir-$(CONFIG_GENDWARFKSYMS) += gendwarfksyms
 subdir-$(CONFIG_SECURITY_SELINUX) += selinux
 subdir-$(CONFIG_SECURITY_IPE) += ipe
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index c16e4cf54d77..993708d11874 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -107,13 +107,24 @@ cmd_cpp_i_c       = $(CPP) $(c_flags) -o $@ $<
 $(obj)/%.i: $(obj)/%.c FORCE
 	$(call if_changed_dep,cpp_i_c)
 
+getexportsymbols = $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/$(1)/p'
+
+gendwarfksyms = $(objtree)/scripts/gendwarfksyms/gendwarfksyms	\
+	$(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes))	\
+	$(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable)
+
 genksyms = $(objtree)/scripts/genksyms/genksyms		\
 	$(if $(KBUILD_SYMTYPES), -T $(@:.o=.symtypes))	\
 	$(if $(KBUILD_PRESERVE), -p)			\
 	$(addprefix -r , $(wildcard $(@:.o=.symref)))
 
 # These mirror gensymtypes_S and co below, keep them in synch.
+ifdef CONFIG_GENDWARFKSYMS
+cmd_gensymtypes_c = $(if $(skip_gendwarfksyms),,	\
+	$(call getexportsymbols,\1) | $(gendwarfksyms) $@)
+else
 cmd_gensymtypes_c = $(CPP) -D__GENKSYMS__ $(c_flags) $< | $(genksyms)
+endif # CONFIG_GENDWARFKSYMS
 
 # LLVM assembly
 # Generate .ll files from .c
@@ -183,7 +194,9 @@ endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT
 
 is-standard-object = $(if $(filter-out y%, $(OBJECT_FILES_NON_STANDARD_$(target-stem).o)$(OBJECT_FILES_NON_STANDARD)n),$(is-kernel-object))
 
+ifdef CONFIG_OBJTOOL
 $(obj)/%.o: private objtool-enabled = $(if $(is-standard-object),$(if $(delay-objtool),$(is-single-obj-m),y))
+endif
 
 ifneq ($(findstring 1, $(KBUILD_EXTRA_WARN)),)
 cmd_warn_shared_object = $(if $(word 2, $(modname-multi)),$(warning $(kbuild-file): $*.o is added to multiple modules: $(modname-multi)))
@@ -286,14 +299,26 @@ $(obj)/%.rs: $(obj)/%.rs.S FORCE
 # This is convoluted. The .S file must first be preprocessed to run guards and
 # expand names, then the resulting exports must be constructed into plain
 # EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed
-# to make the genksyms input.
+# to make the genksyms input or compiled into an object for gendwarfksyms.
 #
 # These mirror gensymtypes_c and co above, keep them in synch.
-cmd_gensymtypes_S =                                                         \
-   { echo "\#include <linux/kernel.h>" ;                                    \
-     echo "\#include <asm/asm-prototypes.h>" ;                              \
-     $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/EXPORT_SYMBOL(\1);/p' ; } | \
-    $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms)
+getasmexports =								\
+   { echo "\#include <linux/kernel.h>" ;				\
+     echo "\#include <linux/string.h>" ;				\
+     echo "\#include <asm/asm-prototypes.h>" ;				\
+     $(call getexportsymbols,EXPORT_SYMBOL(\1);) ; }
+
+ifdef CONFIG_GENDWARFKSYMS
+cmd_gensymtypes_S =							\
+	$(getasmexports) |						\
+	$(CC) $(c_flags) -c -o $(@:.o=.gendwarfksyms.o) -xc -;		\
+	$(call getexportsymbols,\1) |					\
+	$(gendwarfksyms) $(@:.o=.gendwarfksyms.o)
+else
+cmd_gensymtypes_S =							\
+	$(getasmexports) |						\
+	$(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms)
+endif # CONFIG_GENDWARFKSYMS
 
 quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@
 cmd_cpp_s_S       = $(CPP) $(a_flags) -o $@ $<
diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf
index 226ea3df3b4b..a44307f08e9d 100644
--- a/scripts/Makefile.defconf
+++ b/scripts/Makefile.defconf
@@ -1,6 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 # Configuration heplers
 
+cmd_merge_fragments = \
+	$(srctree)/scripts/kconfig/merge_config.sh \
+	$4 -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$2 \
+	$(foreach config,$3,$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
+
 # Creates 'merged defconfigs'
 # ---------------------------------------------------------------------------
 # Usage:
@@ -8,9 +13,7 @@
 #
 # Input config fragments without '.config' suffix
 define merge_into_defconfig
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
+	$(call cmd,merge_fragments,$1,$2)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
 
@@ -22,8 +25,6 @@ endef
 #
 # Input config fragments without '.config' suffix
 define merge_into_defconfig_override
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-		-Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \
-		$(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config)
+	$(call cmd,merge_fragments,$1,$2,-Q)
 	+$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 endef
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
index 1d13cecc7cc7..dc081cf46d21 100644
--- a/scripts/Makefile.extrawarn
+++ b/scripts/Makefile.extrawarn
@@ -31,6 +31,11 @@ KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds
 ifdef CONFIG_CC_IS_CLANG
 # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable.
 KBUILD_CFLAGS += -Wno-gnu
+
+# Clang checks for overflow/truncation with '%p', while GCC does not:
+# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219
+KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf)
+KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf)
 else
 
 # gcc inanely warns about local variables called 'main'
@@ -77,6 +82,9 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init)
 # Warn if there is an enum types mismatch
 KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion)
 
+# Explicitly clear padding bits during variable initialization
+KBUILD_CFLAGS += $(call cc-option,-fzero-init-padding-bits=all)
+
 KBUILD_CFLAGS += -Wextra
 KBUILD_CFLAGS += -Wunused
 
@@ -102,11 +110,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
 ifdef CONFIG_CC_IS_GCC
 KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
-else
-# Clang checks for overflow/truncation with '%p', while GCC does not:
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219
-KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf)
-KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf)
 endif
 KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation)
 
@@ -130,7 +133,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast)
 KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare
 KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access)
 KBUILD_CFLAGS += -Wno-enum-compare-conditional
-KBUILD_CFLAGS += -Wno-enum-enum-conversion
 endif
 
 endif
@@ -154,6 +156,10 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers
 KBUILD_CFLAGS += -Wno-type-limits
 KBUILD_CFLAGS += -Wno-shift-negative-value
 
+ifdef CONFIG_CC_IS_CLANG
+KBUILD_CFLAGS += -Wno-enum-enum-conversion
+endif
+
 ifdef CONFIG_CC_IS_GCC
 KBUILD_CFLAGS += -Wno-maybe-uninitialized
 endif
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 7395200538da..cad20f0e66ee 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -287,6 +287,8 @@ delay-objtool := $(or $(CONFIG_LTO_CLANG),$(CONFIG_X86_KERNEL_IBT))
 cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool-args) $@)
 cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd)
 
+objtool-enabled := y
+
 endif # CONFIG_OBJTOOL
 
 # Useful for describing the dependency of composite objects
@@ -302,11 +304,11 @@ endef
 # ===========================================================================
 # These are shared by some Makefile.* files.
 
-objtool-enabled := y
-
 ifdef CONFIG_LTO_CLANG
-# objtool cannot process LLVM IR. Make $(LD) covert LLVM IR to ELF here.
-cmd_ld_single = $(if $(objtool-enabled), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@)
+# Run $(LD) here to convert LLVM IR to ELF in the following cases:
+#  - when this object needs objtool processing, as objtool cannot process LLVM IR
+#  - when this is a single-object module, as modpost cannot process LLVM IR
+cmd_ld_single = $(if $(objtool-enabled)$(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@)
 endif
 
 quiet_cmd_cc_o_c = CC $(quiet_modtag)  $@
@@ -374,6 +376,9 @@ quiet_cmd_ar = AR      $@
 quiet_cmd_objcopy = OBJCOPY $@
 cmd_objcopy = $(OBJCOPY) $(OBJCOPYFLAGS) $(OBJCOPYFLAGS_$(@F)) $< $@
 
+quiet_cmd_strip_relocs = RSTRIP  $@
+cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $@
+
 # Gzip
 # ---------------------------------------------------------------------------
 
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index f97c9926ed31..1628198f3e83 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -105,7 +105,7 @@ else
 sig-key := $(CONFIG_MODULE_SIG_KEY)
 endif
 quiet_cmd_sign = SIGN    $@
-      cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \
+      cmd_sign = $(objtree)/scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" $(objtree)/certs/signing_key.x509 $@ \
                  $(if $(KBUILD_EXTMOD),|| true)
 
 ifeq ($(sign-only),)
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index ab0e94ea6249..d7d45067d08b 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -43,6 +43,8 @@ MODPOST = $(objtree)/scripts/mod/modpost
 modpost-args =										\
 	$(if $(CONFIG_MODULES),-M)							\
 	$(if $(CONFIG_MODVERSIONS),-m)							\
+	$(if $(CONFIG_BASIC_MODVERSIONS),-b)						\
+	$(if $(CONFIG_EXTENDED_MODVERSIONS),-x)						\
 	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
 	$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E)					\
 	$(if $(KBUILD_MODPOST_WARN),-w)							\
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index fe71e6a65eb9..7b28ad331742 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -834,16 +834,6 @@ foreach my $entry (@mode_permission_funcs) {
 $mode_perms_search = "(?:${mode_perms_search})";
 
 our %deprecated_apis = (
-	"synchronize_rcu_bh"			=> "synchronize_rcu",
-	"synchronize_rcu_bh_expedited"		=> "synchronize_rcu_expedited",
-	"call_rcu_bh"				=> "call_rcu",
-	"rcu_barrier_bh"			=> "rcu_barrier",
-	"synchronize_sched"			=> "synchronize_rcu",
-	"synchronize_sched_expedited"		=> "synchronize_rcu_expedited",
-	"call_rcu_sched"			=> "call_rcu",
-	"rcu_barrier_sched"			=> "rcu_barrier",
-	"get_state_synchronize_sched"		=> "get_state_synchronize_rcu",
-	"cond_synchronize_sched"		=> "cond_synchronize_rcu",
 	"kmap"					=> "kmap_local_page",
 	"kunmap"				=> "kunmap_local",
 	"kmap_atomic"				=> "kmap_local_page",
@@ -2875,7 +2865,7 @@ sub process {
 
 			if ($realfile =~ m@^include/asm/@) {
 				ERROR("MODIFIED_INCLUDE_ASM",
-				      "do not modify files in include/asm, change architecture specific files in include/asm-<architecture>\n" . "$here$rawline\n");
+				      "do not modify files in include/asm, change architecture specific files in arch/<architecture>/include/asm\n" . "$here$rawline\n");
 			}
 			$found_file = 1;
 		}
@@ -3237,12 +3227,12 @@ sub process {
 			my ($cid, $ctitle) = git_commit_info($orig_commit, $id,
 							     $title);
 
-			if ($ctitle ne $title || $tag_case || $tag_space ||
-			    $id_length || $id_case || !$title_has_quotes) {
+			if (defined($cid) && ($ctitle ne $title || $tag_case || $tag_space || $id_length || $id_case || !$title_has_quotes)) {
+				my $fixed = "Fixes: $cid (\"$ctitle\")";
 				if (WARN("BAD_FIXES_TAG",
-				     "Please use correct Fixes: style 'Fixes: <12+ chars of sha1> (\"<title line>\")' - ie: 'Fixes: $cid (\"$ctitle\")'\n" . $herecurr) &&
+				     "Please use correct Fixes: style 'Fixes: <12+ chars of sha1> (\"<title line>\")' - ie: '$fixed'\n" . $herecurr) &&
 				    $fix) {
-					$fixed[$fixlinenr] = "Fixes: $cid (\"$ctitle\")";
+					$fixed[$fixlinenr] = $fixed;
 				}
 			}
 		}
@@ -5513,9 +5503,9 @@ sub process {
 			}
 		}
 
-# check for unnecessary parentheses around comparisons in if uses
-# when !drivers/staging or command-line uses --strict
-		if (($realfile !~ m@^(?:drivers/staging/)@ || $check_orig) &&
+# check for unnecessary parentheses around comparisons
+# except in drivers/staging
+		if (($realfile !~ m@^(?:drivers/staging/)@) &&
 		    $perl_version_ok && defined($stat) &&
 		    $stat =~ /(^.\s*if\s*($balanced_parens))/) {
 			my $if_stat = $1;
diff --git a/scripts/coccinelle/misc/secs_to_jiffies.cocci b/scripts/coccinelle/misc/secs_to_jiffies.cocci
new file mode 100644
index 000000000000..8bbb2884ea5d
--- /dev/null
+++ b/scripts/coccinelle/misc/secs_to_jiffies.cocci
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+///
+/// Find usages of:
+/// - msecs_to_jiffies(value*1000)
+/// - msecs_to_jiffies(value*MSEC_PER_SEC)
+///
+// Confidence: High
+// Copyright: (C) 2024 Easwar Hariharan, Microsoft
+// Keywords: secs, seconds, jiffies
+//
+
+virtual patch
+
+@depends on patch@ constant C; @@
+
+- msecs_to_jiffies(C * 1000)
++ secs_to_jiffies(C)
+
+@depends on patch@ constant C; @@
+
+- msecs_to_jiffies(C * MSEC_PER_SEC)
++ secs_to_jiffies(C)
diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py
index 2f11c4f9c345..13eb8b3901b8 100644
--- a/scripts/gdb/linux/cpus.py
+++ b/scripts/gdb/linux/cpus.py
@@ -167,7 +167,7 @@ def get_current_task(cpu):
             var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task")
             return per_cpu(var_ptr, cpu).dereference()
     elif utils.is_target_arch("aarch64"):
-        current_task_addr = gdb.parse_and_eval("$SP_EL0")
+        current_task_addr = gdb.parse_and_eval("(unsigned long)$SP_EL0")
         if (current_task_addr >> 63) != 0:
             current_task = current_task_addr.cast(task_ptr_type)
             return current_task.dereference()
diff --git a/scripts/gendwarfksyms/.gitignore b/scripts/gendwarfksyms/.gitignore
new file mode 100644
index 000000000000..0927f8d3cd96
--- /dev/null
+++ b/scripts/gendwarfksyms/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+/gendwarfksyms
diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile
new file mode 100644
index 000000000000..6334c7d3c4d5
--- /dev/null
+++ b/scripts/gendwarfksyms/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+hostprogs-always-y += gendwarfksyms
+
+gendwarfksyms-objs += gendwarfksyms.o
+gendwarfksyms-objs += cache.o
+gendwarfksyms-objs += die.o
+gendwarfksyms-objs += dwarf.o
+gendwarfksyms-objs += kabi.o
+gendwarfksyms-objs += symbols.o
+gendwarfksyms-objs += types.o
+
+HOSTLDLIBS_gendwarfksyms := -ldw -lelf -lz
diff --git a/scripts/gendwarfksyms/cache.c b/scripts/gendwarfksyms/cache.c
new file mode 100644
index 000000000000..c9c19b86a686
--- /dev/null
+++ b/scripts/gendwarfksyms/cache.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include "gendwarfksyms.h"
+
+struct cache_item {
+	unsigned long key;
+	int value;
+	struct hlist_node hash;
+};
+
+void cache_set(struct cache *cache, unsigned long key, int value)
+{
+	struct cache_item *ci;
+
+	ci = xmalloc(sizeof(struct cache_item));
+	ci->key = key;
+	ci->value = value;
+	hash_add(cache->cache, &ci->hash, hash_32(key));
+}
+
+int cache_get(struct cache *cache, unsigned long key)
+{
+	struct cache_item *ci;
+
+	hash_for_each_possible(cache->cache, ci, hash, hash_32(key)) {
+		if (ci->key == key)
+			return ci->value;
+	}
+
+	return -1;
+}
+
+void cache_init(struct cache *cache)
+{
+	hash_init(cache->cache);
+}
+
+void cache_free(struct cache *cache)
+{
+	struct hlist_node *tmp;
+	struct cache_item *ci;
+
+	hash_for_each_safe(cache->cache, ci, tmp, hash) {
+		free(ci);
+	}
+
+	hash_init(cache->cache);
+}
diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c
new file mode 100644
index 000000000000..66bd4c9bc952
--- /dev/null
+++ b/scripts/gendwarfksyms/die.c
@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <string.h>
+#include "gendwarfksyms.h"
+
+#define DIE_HASH_BITS 15
+
+/* {die->addr, state} -> struct die * */
+static HASHTABLE_DEFINE(die_map, 1 << DIE_HASH_BITS);
+
+static unsigned int map_hits;
+static unsigned int map_misses;
+
+static inline unsigned int die_hash(uintptr_t addr, enum die_state state)
+{
+	return hash_32(addr_hash(addr) ^ (unsigned int)state);
+}
+
+static void init_die(struct die *cd)
+{
+	cd->state = DIE_INCOMPLETE;
+	cd->mapped = false;
+	cd->fqn = NULL;
+	cd->tag = -1;
+	cd->addr = 0;
+	INIT_LIST_HEAD(&cd->fragments);
+}
+
+static struct die *create_die(Dwarf_Die *die, enum die_state state)
+{
+	struct die *cd;
+
+	cd = xmalloc(sizeof(struct die));
+	init_die(cd);
+	cd->addr = (uintptr_t)die->addr;
+
+	hash_add(die_map, &cd->hash, die_hash(cd->addr, state));
+	return cd;
+}
+
+int __die_map_get(uintptr_t addr, enum die_state state, struct die **res)
+{
+	struct die *cd;
+
+	hash_for_each_possible(die_map, cd, hash, die_hash(addr, state)) {
+		if (cd->addr == addr && cd->state == state) {
+			*res = cd;
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+struct die *die_map_get(Dwarf_Die *die, enum die_state state)
+{
+	struct die *cd;
+
+	if (__die_map_get((uintptr_t)die->addr, state, &cd) == 0) {
+		map_hits++;
+		return cd;
+	}
+
+	map_misses++;
+	return create_die(die, state);
+}
+
+static void reset_die(struct die *cd)
+{
+	struct die_fragment *tmp;
+	struct die_fragment *df;
+
+	list_for_each_entry_safe(df, tmp, &cd->fragments, list) {
+		if (df->type == FRAGMENT_STRING)
+			free(df->data.str);
+		free(df);
+	}
+
+	if (cd->fqn && *cd->fqn)
+		free(cd->fqn);
+	init_die(cd);
+}
+
+void die_map_for_each(die_map_callback_t func, void *arg)
+{
+	struct hlist_node *tmp;
+	struct die *cd;
+
+	hash_for_each_safe(die_map, cd, tmp, hash) {
+		func(cd, arg);
+	}
+}
+
+void die_map_free(void)
+{
+	struct hlist_node *tmp;
+	unsigned int stats[DIE_LAST + 1];
+	struct die *cd;
+	int i;
+
+	memset(stats, 0, sizeof(stats));
+
+	hash_for_each_safe(die_map, cd, tmp, hash) {
+		stats[cd->state]++;
+		reset_die(cd);
+		free(cd);
+	}
+	hash_init(die_map);
+
+	if (map_hits + map_misses > 0)
+		debug("hits %u, misses %u (hit rate %.02f%%)", map_hits,
+		      map_misses,
+		      (100.0f * map_hits) / (map_hits + map_misses));
+
+	for (i = 0; i <= DIE_LAST; i++)
+		debug("%s: %u entries", die_state_name(i), stats[i]);
+}
+
+static struct die_fragment *append_item(struct die *cd)
+{
+	struct die_fragment *df;
+
+	df = xmalloc(sizeof(struct die_fragment));
+	df->type = FRAGMENT_EMPTY;
+	list_add_tail(&df->list, &cd->fragments);
+	return df;
+}
+
+void die_map_add_string(struct die *cd, const char *str)
+{
+	struct die_fragment *df;
+
+	if (!cd)
+		return;
+
+	df = append_item(cd);
+	df->data.str = xstrdup(str);
+	df->type = FRAGMENT_STRING;
+}
+
+void die_map_add_linebreak(struct die *cd, int linebreak)
+{
+	struct die_fragment *df;
+
+	if (!cd)
+		return;
+
+	df = append_item(cd);
+	df->data.linebreak = linebreak;
+	df->type = FRAGMENT_LINEBREAK;
+}
+
+void die_map_add_die(struct die *cd, struct die *child)
+{
+	struct die_fragment *df;
+
+	if (!cd)
+		return;
+
+	df = append_item(cd);
+	df->data.addr = child->addr;
+	df->type = FRAGMENT_DIE;
+}
diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c
new file mode 100644
index 000000000000..534d9aa7c114
--- /dev/null
+++ b/scripts/gendwarfksyms/dwarf.c
@@ -0,0 +1,1159 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <assert.h>
+#include <inttypes.h>
+#include <stdarg.h>
+#include "gendwarfksyms.h"
+
+/* See get_union_kabi_status */
+#define KABI_PREFIX "__kabi_"
+#define KABI_PREFIX_LEN (sizeof(KABI_PREFIX) - 1)
+#define KABI_RESERVED_PREFIX "reserved"
+#define KABI_RESERVED_PREFIX_LEN (sizeof(KABI_RESERVED_PREFIX) - 1)
+#define KABI_RENAMED_PREFIX "renamed"
+#define KABI_RENAMED_PREFIX_LEN (sizeof(KABI_RENAMED_PREFIX) - 1)
+#define KABI_IGNORED_PREFIX "ignored"
+#define KABI_IGNORED_PREFIX_LEN (sizeof(KABI_IGNORED_PREFIX) - 1)
+
+static inline bool is_kabi_prefix(const char *name)
+{
+	return name && !strncmp(name, KABI_PREFIX, KABI_PREFIX_LEN);
+}
+
+enum kabi_status {
+	/* >0 to stop DIE processing */
+	KABI_NORMAL = 1,
+	KABI_RESERVED,
+	KABI_IGNORED,
+};
+
+static bool do_linebreak;
+static int indentation_level;
+
+/* Line breaks and indentation for pretty-printing */
+static void process_linebreak(struct die *cache, int n)
+{
+	indentation_level += n;
+	do_linebreak = true;
+	die_map_add_linebreak(cache, n);
+}
+
+#define DEFINE_GET_ATTR(attr, type)                                    \
+	static bool get_##attr##_attr(Dwarf_Die *die, unsigned int id, \
+				      type *value)                     \
+	{                                                              \
+		Dwarf_Attribute da;                                    \
+		return dwarf_attr(die, id, &da) &&                     \
+		       !dwarf_form##attr(&da, value);                  \
+	}
+
+DEFINE_GET_ATTR(flag, bool)
+DEFINE_GET_ATTR(udata, Dwarf_Word)
+
+static bool get_ref_die_attr(Dwarf_Die *die, unsigned int id, Dwarf_Die *value)
+{
+	Dwarf_Attribute da;
+
+	/* dwarf_formref_die returns a pointer instead of an error value. */
+	return dwarf_attr(die, id, &da) && dwarf_formref_die(&da, value);
+}
+
+#define DEFINE_GET_STRING_ATTR(attr)                         \
+	static const char *get_##attr##_attr(Dwarf_Die *die) \
+	{                                                    \
+		Dwarf_Attribute da;                          \
+		if (dwarf_attr(die, DW_AT_##attr, &da))      \
+			return dwarf_formstring(&da);        \
+		return NULL;                                 \
+	}
+
+DEFINE_GET_STRING_ATTR(name)
+DEFINE_GET_STRING_ATTR(linkage_name)
+
+static const char *get_symbol_name(Dwarf_Die *die)
+{
+	const char *name;
+
+	/* rustc uses DW_AT_linkage_name for exported symbols */
+	name = get_linkage_name_attr(die);
+	if (!name)
+		name = get_name_attr(die);
+
+	return name;
+}
+
+static bool match_export_symbol(struct state *state, Dwarf_Die *die)
+{
+	Dwarf_Die *source = die;
+	Dwarf_Die origin;
+
+	/* If the DIE has an abstract origin, use it for type information. */
+	if (get_ref_die_attr(die, DW_AT_abstract_origin, &origin))
+		source = &origin;
+
+	state->sym = symbol_get(get_symbol_name(die));
+
+	/* Look up using the origin name if there are no matches. */
+	if (!state->sym && source != die)
+		state->sym = symbol_get(get_symbol_name(source));
+
+	state->die = *source;
+	return !!state->sym;
+}
+
+/* DW_AT_decl_file -> struct srcfile */
+static struct cache srcfile_cache;
+
+static bool is_definition_private(Dwarf_Die *die)
+{
+	Dwarf_Word filenum;
+	Dwarf_Files *files;
+	Dwarf_Die cudie;
+	const char *s;
+	int res;
+
+	/*
+	 * Definitions in .c files cannot change the public ABI,
+	 * so consider them private.
+	 */
+	if (!get_udata_attr(die, DW_AT_decl_file, &filenum))
+		return false;
+
+	res = cache_get(&srcfile_cache, filenum);
+	if (res >= 0)
+		return !!res;
+
+	if (!dwarf_cu_die(die->cu, &cudie, NULL, NULL, NULL, NULL, NULL, NULL))
+		error("dwarf_cu_die failed: '%s'", dwarf_errmsg(-1));
+
+	if (dwarf_getsrcfiles(&cudie, &files, NULL))
+		error("dwarf_getsrcfiles failed: '%s'", dwarf_errmsg(-1));
+
+	s = dwarf_filesrc(files, filenum, NULL, NULL);
+	if (!s)
+		error("dwarf_filesrc failed: '%s'", dwarf_errmsg(-1));
+
+	s = strrchr(s, '.');
+	res = s && !strcmp(s, ".c");
+	cache_set(&srcfile_cache, filenum, res);
+
+	return !!res;
+}
+
+static bool is_kabi_definition(struct die *cache, Dwarf_Die *die)
+{
+	bool value;
+
+	if (get_flag_attr(die, DW_AT_declaration, &value) && value)
+		return false;
+
+	if (kabi_is_declonly(cache->fqn))
+		return false;
+
+	return !is_definition_private(die);
+}
+
+/*
+ * Type string processing
+ */
+static void process(struct die *cache, const char *s)
+{
+	s = s ?: "<null>";
+
+	if (dump_dies && do_linebreak) {
+		fputs("\n", stderr);
+		for (int i = 0; i < indentation_level; i++)
+			fputs("  ", stderr);
+		do_linebreak = false;
+	}
+	if (dump_dies)
+		fputs(s, stderr);
+
+	if (cache)
+		die_debug_r("cache %p string '%s'", cache, s);
+	die_map_add_string(cache, s);
+}
+
+#define MAX_FMT_BUFFER_SIZE 128
+
+static void process_fmt(struct die *cache, const char *fmt, ...)
+{
+	char buf[MAX_FMT_BUFFER_SIZE];
+	va_list args;
+
+	va_start(args, fmt);
+
+	if (checkp(vsnprintf(buf, sizeof(buf), fmt, args)) >= sizeof(buf))
+		error("vsnprintf overflow: increase MAX_FMT_BUFFER_SIZE");
+
+	process(cache, buf);
+	va_end(args);
+}
+
+#define MAX_FQN_SIZE 64
+
+/* Get a fully qualified name from DWARF scopes */
+static char *get_fqn(Dwarf_Die *die)
+{
+	const char *list[MAX_FQN_SIZE];
+	Dwarf_Die *scopes = NULL;
+	bool has_name = false;
+	char *fqn = NULL;
+	char *p;
+	int count = 0;
+	int len = 0;
+	int res;
+	int i;
+
+	res = checkp(dwarf_getscopes_die(die, &scopes));
+	if (!res) {
+		list[count] = get_name_attr(die);
+
+		if (!list[count])
+			return NULL;
+
+		len += strlen(list[count]);
+		count++;
+
+		goto done;
+	}
+
+	for (i = res - 1; i >= 0 && count < MAX_FQN_SIZE; i--) {
+		if (dwarf_tag(&scopes[i]) == DW_TAG_compile_unit)
+			continue;
+
+		list[count] = get_name_attr(&scopes[i]);
+
+		if (list[count]) {
+			has_name = true;
+		} else {
+			list[count] = "<anonymous>";
+			has_name = false;
+		}
+
+		len += strlen(list[count]);
+		count++;
+
+		if (i > 0) {
+			list[count++] = "::";
+			len += 2;
+		}
+	}
+
+	free(scopes);
+
+	if (count == MAX_FQN_SIZE)
+		warn("increase MAX_FQN_SIZE: reached the maximum");
+
+	/* Consider the DIE unnamed if the last scope doesn't have a name */
+	if (!has_name)
+		return NULL;
+done:
+	fqn = xmalloc(len + 1);
+	*fqn = '\0';
+
+	p = fqn;
+	for (i = 0; i < count; i++)
+		p = stpcpy(p, list[i]);
+
+	return fqn;
+}
+
+static void update_fqn(struct die *cache, Dwarf_Die *die)
+{
+	if (!cache->fqn)
+		cache->fqn = get_fqn(die) ?: "";
+}
+
+static void process_fqn(struct die *cache, Dwarf_Die *die)
+{
+	update_fqn(cache, die);
+	if (*cache->fqn)
+		process(cache, " ");
+	process(cache, cache->fqn);
+}
+
+#define DEFINE_PROCESS_UDATA_ATTRIBUTE(attribute)                          \
+	static void process_##attribute##_attr(struct die *cache,          \
+					       Dwarf_Die *die)             \
+	{                                                                  \
+		Dwarf_Word value;                                          \
+		if (get_udata_attr(die, DW_AT_##attribute, &value))        \
+			process_fmt(cache, " " #attribute "(%" PRIu64 ")", \
+				    value);                                \
+	}
+
+DEFINE_PROCESS_UDATA_ATTRIBUTE(accessibility)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(alignment)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(bit_size)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(byte_size)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(data_bit_offset)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(data_member_location)
+DEFINE_PROCESS_UDATA_ATTRIBUTE(discr_value)
+
+/* Match functions -- die_match_callback_t */
+#define DEFINE_MATCH(type)                                     \
+	static bool match_##type##_type(Dwarf_Die *die)        \
+	{                                                      \
+		return dwarf_tag(die) == DW_TAG_##type##_type; \
+	}
+
+DEFINE_MATCH(enumerator)
+DEFINE_MATCH(formal_parameter)
+DEFINE_MATCH(member)
+DEFINE_MATCH(subrange)
+
+bool match_all(Dwarf_Die *die)
+{
+	return true;
+}
+
+int process_die_container(struct state *state, struct die *cache,
+			  Dwarf_Die *die, die_callback_t func,
+			  die_match_callback_t match)
+{
+	Dwarf_Die current;
+	int res;
+
+	/* Track the first item in lists. */
+	if (state)
+		state->first_list_item = true;
+
+	res = checkp(dwarf_child(die, &current));
+	while (!res) {
+		if (match(&current)) {
+			/* <0 = error, 0 = continue, >0 = stop */
+			res = checkp(func(state, cache, &current));
+			if (res)
+				goto out;
+		}
+
+		res = checkp(dwarf_siblingof(&current, &current));
+	}
+
+	res = 0;
+out:
+	if (state)
+		state->first_list_item = false;
+
+	return res;
+}
+
+static int process_type(struct state *state, struct die *parent,
+			Dwarf_Die *die);
+
+static void process_type_attr(struct state *state, struct die *cache,
+			      Dwarf_Die *die)
+{
+	Dwarf_Die type;
+
+	if (get_ref_die_attr(die, DW_AT_type, &type)) {
+		check(process_type(state, cache, &type));
+		return;
+	}
+
+	/* Compilers can omit DW_AT_type -- print out 'void' to clarify */
+	process(cache, "base_type void");
+}
+
+static void process_list_comma(struct state *state, struct die *cache)
+{
+	if (state->first_list_item) {
+		state->first_list_item = false;
+	} else {
+		process(cache, " ,");
+		process_linebreak(cache, 0);
+	}
+}
+
+/* Comma-separated with DW_AT_type */
+static void __process_list_type(struct state *state, struct die *cache,
+				Dwarf_Die *die, const char *type)
+{
+	const char *name = get_name_attr(die);
+
+	if (stable) {
+		if (is_kabi_prefix(name))
+			name = NULL;
+		state->kabi.orig_name = NULL;
+	}
+
+	process_list_comma(state, cache);
+	process(cache, type);
+	process_type_attr(state, cache, die);
+
+	if (stable && state->kabi.orig_name)
+		name = state->kabi.orig_name;
+	if (name) {
+		process(cache, " ");
+		process(cache, name);
+	}
+
+	process_accessibility_attr(cache, die);
+	process_bit_size_attr(cache, die);
+	process_data_bit_offset_attr(cache, die);
+	process_data_member_location_attr(cache, die);
+}
+
+#define DEFINE_PROCESS_LIST_TYPE(type)                                       \
+	static void process_##type##_type(struct state *state,               \
+					  struct die *cache, Dwarf_Die *die) \
+	{                                                                    \
+		__process_list_type(state, cache, die, #type " ");           \
+	}
+
+DEFINE_PROCESS_LIST_TYPE(formal_parameter)
+DEFINE_PROCESS_LIST_TYPE(member)
+
+/* Container types with DW_AT_type */
+static void __process_type(struct state *state, struct die *cache,
+			   Dwarf_Die *die, const char *type)
+{
+	process(cache, type);
+	process_fqn(cache, die);
+	process(cache, " {");
+	process_linebreak(cache, 1);
+	process_type_attr(state, cache, die);
+	process_linebreak(cache, -1);
+	process(cache, "}");
+	process_byte_size_attr(cache, die);
+	process_alignment_attr(cache, die);
+}
+
+#define DEFINE_PROCESS_TYPE(type)                                            \
+	static void process_##type##_type(struct state *state,               \
+					  struct die *cache, Dwarf_Die *die) \
+	{                                                                    \
+		__process_type(state, cache, die, #type "_type");            \
+	}
+
+DEFINE_PROCESS_TYPE(atomic)
+DEFINE_PROCESS_TYPE(const)
+DEFINE_PROCESS_TYPE(immutable)
+DEFINE_PROCESS_TYPE(packed)
+DEFINE_PROCESS_TYPE(pointer)
+DEFINE_PROCESS_TYPE(reference)
+DEFINE_PROCESS_TYPE(restrict)
+DEFINE_PROCESS_TYPE(rvalue_reference)
+DEFINE_PROCESS_TYPE(shared)
+DEFINE_PROCESS_TYPE(template_type_parameter)
+DEFINE_PROCESS_TYPE(volatile)
+DEFINE_PROCESS_TYPE(typedef)
+
+static void process_subrange_type(struct state *state, struct die *cache,
+				  Dwarf_Die *die)
+{
+	Dwarf_Word count = 0;
+
+	if (get_udata_attr(die, DW_AT_count, &count))
+		process_fmt(cache, "[%" PRIu64 "]", count);
+	else if (get_udata_attr(die, DW_AT_upper_bound, &count))
+		process_fmt(cache, "[%" PRIu64 "]", count + 1);
+	else
+		process(cache, "[]");
+}
+
+static void process_array_type(struct state *state, struct die *cache,
+			       Dwarf_Die *die)
+{
+	process(cache, "array_type");
+	/* Array size */
+	check(process_die_container(state, cache, die, process_type,
+				    match_subrange_type));
+	process(cache, " {");
+	process_linebreak(cache, 1);
+	process_type_attr(state, cache, die);
+	process_linebreak(cache, -1);
+	process(cache, "}");
+}
+
+static void __process_subroutine_type(struct state *state, struct die *cache,
+				      Dwarf_Die *die, const char *type)
+{
+	process(cache, type);
+	process(cache, " (");
+	process_linebreak(cache, 1);
+	/* Parameters */
+	check(process_die_container(state, cache, die, process_type,
+				    match_formal_parameter_type));
+	process_linebreak(cache, -1);
+	process(cache, ")");
+	process_linebreak(cache, 0);
+	/* Return type */
+	process(cache, "-> ");
+	process_type_attr(state, cache, die);
+}
+
+static void process_subroutine_type(struct state *state, struct die *cache,
+				    Dwarf_Die *die)
+{
+	__process_subroutine_type(state, cache, die, "subroutine_type");
+}
+
+static void process_variant_type(struct state *state, struct die *cache,
+				 Dwarf_Die *die)
+{
+	process_list_comma(state, cache);
+	process(cache, "variant {");
+	process_linebreak(cache, 1);
+	check(process_die_container(state, cache, die, process_type,
+				    match_member_type));
+	process_linebreak(cache, -1);
+	process(cache, "}");
+	process_discr_value_attr(cache, die);
+}
+
+static void process_variant_part_type(struct state *state, struct die *cache,
+				      Dwarf_Die *die)
+{
+	process_list_comma(state, cache);
+	process(cache, "variant_part {");
+	process_linebreak(cache, 1);
+	check(process_die_container(state, cache, die, process_type,
+				    match_all));
+	process_linebreak(cache, -1);
+	process(cache, "}");
+}
+
+static int get_kabi_status(Dwarf_Die *die, const char **suffix)
+{
+	const char *name = get_name_attr(die);
+
+	if (suffix)
+		*suffix = NULL;
+
+	if (is_kabi_prefix(name)) {
+		name += KABI_PREFIX_LEN;
+
+		if (!strncmp(name, KABI_RESERVED_PREFIX,
+			     KABI_RESERVED_PREFIX_LEN))
+			return KABI_RESERVED;
+		if (!strncmp(name, KABI_IGNORED_PREFIX,
+			     KABI_IGNORED_PREFIX_LEN))
+			return KABI_IGNORED;
+
+		if (!strncmp(name, KABI_RENAMED_PREFIX,
+			     KABI_RENAMED_PREFIX_LEN)) {
+			if (suffix) {
+				name += KABI_RENAMED_PREFIX_LEN;
+				*suffix = name;
+			}
+			return KABI_RESERVED;
+		}
+	}
+
+	return KABI_NORMAL;
+}
+
+static int check_struct_member_kabi_status(struct state *state,
+					   struct die *__unused, Dwarf_Die *die)
+{
+	int res;
+
+	assert(dwarf_tag(die) == DW_TAG_member_type);
+
+	/*
+	 * If the union member is a struct, expect the __kabi field to
+	 * be the first member of the structure, i.e..:
+	 *
+	 * union {
+	 * 	type new_member;
+	 * 	struct {
+	 * 		type __kabi_field;
+	 * 	}
+	 * };
+	 */
+	res = get_kabi_status(die, &state->kabi.orig_name);
+
+	if (res == KABI_RESERVED &&
+	    !get_ref_die_attr(die, DW_AT_type, &state->kabi.placeholder))
+		error("structure member missing a type?");
+
+	return res;
+}
+
+static int check_union_member_kabi_status(struct state *state,
+					  struct die *__unused, Dwarf_Die *die)
+{
+	Dwarf_Die type;
+	int res;
+
+	assert(dwarf_tag(die) == DW_TAG_member_type);
+
+	if (!get_ref_die_attr(die, DW_AT_type, &type))
+		error("union member missing a type?");
+
+	/*
+	 * We expect a union with two members. Check if either of them
+	 * has a __kabi name prefix, i.e.:
+	 *
+	 * union {
+	 * 	...
+	 * 	type memberN; // <- type, N = {0,1}
+	 *	...
+	 * };
+	 *
+	 * The member can also be a structure type, in which case we'll
+	 * check the first structure member.
+	 *
+	 * In any case, stop processing after we've seen two members.
+	 */
+	res = get_kabi_status(die, &state->kabi.orig_name);
+
+	if (res == KABI_RESERVED)
+		state->kabi.placeholder = type;
+	if (res != KABI_NORMAL)
+		return res;
+
+	if (dwarf_tag(&type) == DW_TAG_structure_type)
+		res = checkp(process_die_container(
+			state, NULL, &type, check_struct_member_kabi_status,
+			match_member_type));
+
+	if (res <= KABI_NORMAL && ++state->kabi.members < 2)
+		return 0; /* Continue */
+
+	return res;
+}
+
+static int get_union_kabi_status(Dwarf_Die *die, Dwarf_Die *placeholder,
+				 const char **orig_name)
+{
+	struct state state;
+	int res;
+
+	if (!stable)
+		return KABI_NORMAL;
+
+	/*
+	 * To maintain a stable kABI, distributions may choose to reserve
+	 * space in structs for later use by adding placeholder members,
+	 * for example:
+	 *
+	 * struct s {
+	 * 	u32 a;
+	 *	// an 8-byte placeholder for future use
+	 * 	u64 __kabi_reserved_0;
+	 * };
+	 *
+	 * When the reserved member is taken into use, the type change
+	 * would normally cause the symbol version to change as well, but
+	 * if the replacement uses the following convention, gendwarfksyms
+	 * continues to use the placeholder type for versioning instead,
+	 * thus maintaining the same symbol version:
+	 *
+	 * struct s {
+	 * 	u32 a;
+	 *	union {
+	 * 		// placeholder replaced with a new member `b`
+	 * 		struct t b;
+	 * 		struct {
+	 * 			// the placeholder type that is still
+	 *			// used for versioning
+	 * 			u64 __kabi_reserved_0;
+	 * 		};
+	 * 	};
+	 * };
+	 *
+	 * I.e., as long as the replaced member is in a union, and the
+	 * placeholder has a __kabi_reserved name prefix, we'll continue
+	 * to use the placeholder type (here u64) for version calculation
+	 * instead of the union type.
+	 *
+	 * It's also possible to ignore new members from versioning if
+	 * they've been added to alignment holes, for example, by
+	 * including them in a union with another member that uses the
+	 * __kabi_ignored name prefix:
+	 *
+	 * struct s {
+	 * 	u32 a;
+	 *	// an alignment hole is used to add `n`
+	 * 	union {
+	 * 		u32 n;
+	 *		// hide the entire union member from versioning
+	 * 		u8 __kabi_ignored_0;
+	 * 	};
+	 * 	u64 b;
+	 * };
+	 *
+	 * Note that the user of this feature is responsible for ensuring
+	 * that the structure actually remains ABI compatible.
+	 */
+	memset(&state.kabi, 0, sizeof(struct kabi_state));
+
+	res = checkp(process_die_container(&state, NULL, die,
+					   check_union_member_kabi_status,
+					   match_member_type));
+
+	if (res == KABI_RESERVED) {
+		if (placeholder)
+			*placeholder = state.kabi.placeholder;
+		if (orig_name)
+			*orig_name = state.kabi.orig_name;
+	}
+
+	return res;
+}
+
+static bool is_kabi_ignored(Dwarf_Die *die)
+{
+	Dwarf_Die type;
+
+	if (!stable)
+		return false;
+
+	if (!get_ref_die_attr(die, DW_AT_type, &type))
+		error("member missing a type?");
+
+	return dwarf_tag(&type) == DW_TAG_union_type &&
+	       checkp(get_union_kabi_status(&type, NULL, NULL)) == KABI_IGNORED;
+}
+
+static int ___process_structure_type(struct state *state, struct die *cache,
+				     Dwarf_Die *die)
+{
+	switch (dwarf_tag(die)) {
+	case DW_TAG_member:
+		if (is_kabi_ignored(die))
+			return 0;
+		return check(process_type(state, cache, die));
+	case DW_TAG_variant_part:
+		return check(process_type(state, cache, die));
+	case DW_TAG_class_type:
+	case DW_TAG_enumeration_type:
+	case DW_TAG_structure_type:
+	case DW_TAG_template_type_parameter:
+	case DW_TAG_union_type:
+	case DW_TAG_subprogram:
+		/* Skip non-member types, including member functions */
+		return 0;
+	default:
+		error("unexpected structure_type child: %x", dwarf_tag(die));
+	}
+}
+
+static void __process_structure_type(struct state *state, struct die *cache,
+				     Dwarf_Die *die, const char *type,
+				     die_callback_t process_func,
+				     die_match_callback_t match_func)
+{
+	bool expand;
+
+	process(cache, type);
+	process_fqn(cache, die);
+	process(cache, " {");
+	process_linebreak(cache, 1);
+
+	expand = state->expand.expand && is_kabi_definition(cache, die);
+
+	if (expand) {
+		state->expand.current_fqn = cache->fqn;
+		check(process_die_container(state, cache, die, process_func,
+					    match_func));
+	}
+
+	process_linebreak(cache, -1);
+	process(cache, "}");
+
+	if (expand) {
+		process_byte_size_attr(cache, die);
+		process_alignment_attr(cache, die);
+	}
+}
+
+#define DEFINE_PROCESS_STRUCTURE_TYPE(structure)                        \
+	static void process_##structure##_type(                         \
+		struct state *state, struct die *cache, Dwarf_Die *die) \
+	{                                                               \
+		__process_structure_type(state, cache, die,             \
+					 #structure "_type",            \
+					 ___process_structure_type,     \
+					 match_all);                    \
+	}
+
+DEFINE_PROCESS_STRUCTURE_TYPE(class)
+DEFINE_PROCESS_STRUCTURE_TYPE(structure)
+
+static void process_union_type(struct state *state, struct die *cache,
+			       Dwarf_Die *die)
+{
+	Dwarf_Die placeholder;
+
+	int res = checkp(get_union_kabi_status(die, &placeholder,
+					       &state->kabi.orig_name));
+
+	if (res == KABI_RESERVED)
+		check(process_type(state, cache, &placeholder));
+	if (res > KABI_NORMAL)
+		return;
+
+	__process_structure_type(state, cache, die, "union_type",
+				 ___process_structure_type, match_all);
+}
+
+static void process_enumerator_type(struct state *state, struct die *cache,
+				    Dwarf_Die *die)
+{
+	bool overridden = false;
+	Dwarf_Word value;
+
+	if (stable) {
+		/* Get the fqn before we process anything */
+		update_fqn(cache, die);
+
+		if (kabi_is_enumerator_ignored(state->expand.current_fqn,
+					       cache->fqn))
+			return;
+
+		overridden = kabi_get_enumerator_value(
+			state->expand.current_fqn, cache->fqn, &value);
+	}
+
+	process_list_comma(state, cache);
+	process(cache, "enumerator");
+	process_fqn(cache, die);
+
+	if (overridden || get_udata_attr(die, DW_AT_const_value, &value)) {
+		process(cache, " = ");
+		process_fmt(cache, "%" PRIu64, value);
+	}
+}
+
+static void process_enumeration_type(struct state *state, struct die *cache,
+				     Dwarf_Die *die)
+{
+	__process_structure_type(state, cache, die, "enumeration_type",
+				 process_type, match_enumerator_type);
+}
+
+static void process_base_type(struct state *state, struct die *cache,
+			      Dwarf_Die *die)
+{
+	process(cache, "base_type");
+	process_fqn(cache, die);
+	process_byte_size_attr(cache, die);
+	process_encoding_attr(cache, die);
+	process_alignment_attr(cache, die);
+}
+
+static void process_unspecified_type(struct state *state, struct die *cache,
+				     Dwarf_Die *die)
+{
+	/*
+	 * These can be emitted for stand-alone assembly code, which means we
+	 * might run into them in vmlinux.o.
+	 */
+	process(cache, "unspecified_type");
+}
+
+static void process_cached(struct state *state, struct die *cache,
+			   Dwarf_Die *die)
+{
+	struct die_fragment *df;
+	Dwarf_Die child;
+
+	list_for_each_entry(df, &cache->fragments, list) {
+		switch (df->type) {
+		case FRAGMENT_STRING:
+			die_debug_b("cache %p STRING '%s'", cache,
+				    df->data.str);
+			process(NULL, df->data.str);
+			break;
+		case FRAGMENT_LINEBREAK:
+			process_linebreak(NULL, df->data.linebreak);
+			break;
+		case FRAGMENT_DIE:
+			if (!dwarf_die_addr_die(dwarf_cu_getdwarf(die->cu),
+						(void *)df->data.addr, &child))
+				error("dwarf_die_addr_die failed");
+			die_debug_b("cache %p DIE addr %" PRIxPTR " tag %x",
+				    cache, df->data.addr, dwarf_tag(&child));
+			check(process_type(state, NULL, &child));
+			break;
+		default:
+			error("empty die_fragment");
+		}
+	}
+}
+
+static void state_init(struct state *state)
+{
+	state->expand.expand = true;
+	state->expand.current_fqn = NULL;
+	cache_init(&state->expansion_cache);
+}
+
+static void expansion_state_restore(struct expansion_state *state,
+				    struct expansion_state *saved)
+{
+	state->expand = saved->expand;
+	state->current_fqn = saved->current_fqn;
+}
+
+static void expansion_state_save(struct expansion_state *state,
+				 struct expansion_state *saved)
+{
+	expansion_state_restore(saved, state);
+}
+
+static bool is_expanded_type(int tag)
+{
+	return tag == DW_TAG_class_type || tag == DW_TAG_structure_type ||
+	       tag == DW_TAG_union_type || tag == DW_TAG_enumeration_type;
+}
+
+#define PROCESS_TYPE(type)                                \
+	case DW_TAG_##type##_type:                        \
+		process_##type##_type(state, cache, die); \
+		break;
+
+static int process_type(struct state *state, struct die *parent, Dwarf_Die *die)
+{
+	enum die_state want_state = DIE_COMPLETE;
+	struct die *cache;
+	struct expansion_state saved;
+	int tag = dwarf_tag(die);
+
+	expansion_state_save(&state->expand, &saved);
+
+	/*
+	 * Structures and enumeration types are expanded only once per
+	 * exported symbol. This is sufficient for detecting ABI changes
+	 * within the structure.
+	 */
+	if (is_expanded_type(tag)) {
+		if (cache_was_expanded(&state->expansion_cache, die->addr))
+			state->expand.expand = false;
+
+		if (state->expand.expand)
+			cache_mark_expanded(&state->expansion_cache, die->addr);
+		else
+			want_state = DIE_UNEXPANDED;
+	}
+
+	/*
+	 * If we have want_state already cached, use it instead of walking
+	 * through DWARF.
+	 */
+	cache = die_map_get(die, want_state);
+
+	if (cache->state == want_state) {
+		die_debug_g("cached addr %p tag %x -- %s", die->addr, tag,
+			    die_state_name(cache->state));
+
+		process_cached(state, cache, die);
+		die_map_add_die(parent, cache);
+
+		expansion_state_restore(&state->expand, &saved);
+		return 0;
+	}
+
+	die_debug_g("addr %p tag %x -- %s -> %s", die->addr, tag,
+		    die_state_name(cache->state), die_state_name(want_state));
+
+	switch (tag) {
+	/* Type modifiers */
+	PROCESS_TYPE(atomic)
+	PROCESS_TYPE(const)
+	PROCESS_TYPE(immutable)
+	PROCESS_TYPE(packed)
+	PROCESS_TYPE(pointer)
+	PROCESS_TYPE(reference)
+	PROCESS_TYPE(restrict)
+	PROCESS_TYPE(rvalue_reference)
+	PROCESS_TYPE(shared)
+	PROCESS_TYPE(volatile)
+	/* Container types */
+	PROCESS_TYPE(class)
+	PROCESS_TYPE(structure)
+	PROCESS_TYPE(union)
+	PROCESS_TYPE(enumeration)
+	/* Subtypes */
+	PROCESS_TYPE(enumerator)
+	PROCESS_TYPE(formal_parameter)
+	PROCESS_TYPE(member)
+	PROCESS_TYPE(subrange)
+	PROCESS_TYPE(template_type_parameter)
+	PROCESS_TYPE(variant)
+	PROCESS_TYPE(variant_part)
+	/* Other types */
+	PROCESS_TYPE(array)
+	PROCESS_TYPE(base)
+	PROCESS_TYPE(subroutine)
+	PROCESS_TYPE(typedef)
+	PROCESS_TYPE(unspecified)
+	default:
+		error("unexpected type: %x", tag);
+	}
+
+	die_debug_r("parent %p cache %p die addr %p tag %x", parent, cache,
+		    die->addr, tag);
+
+	/* Update cache state and append to the parent (if any) */
+	cache->tag = tag;
+	cache->state = want_state;
+	die_map_add_die(parent, cache);
+
+	expansion_state_restore(&state->expand, &saved);
+	return 0;
+}
+
+/*
+ * Exported symbol processing
+ */
+static struct die *get_symbol_cache(struct state *state, Dwarf_Die *die)
+{
+	struct die *cache;
+
+	cache = die_map_get(die, DIE_SYMBOL);
+
+	if (cache->state != DIE_INCOMPLETE)
+		return NULL; /* We already processed a symbol for this DIE */
+
+	cache->tag = dwarf_tag(die);
+	return cache;
+}
+
+static void process_symbol(struct state *state, Dwarf_Die *die,
+			   die_callback_t process_func)
+{
+	struct die *cache;
+
+	symbol_set_die(state->sym, die);
+
+	cache = get_symbol_cache(state, die);
+	if (!cache)
+		return;
+
+	debug("%s", state->sym->name);
+	check(process_func(state, cache, die));
+	cache->state = DIE_SYMBOL;
+	if (dump_dies)
+		fputs("\n", stderr);
+}
+
+static int __process_subprogram(struct state *state, struct die *cache,
+				Dwarf_Die *die)
+{
+	__process_subroutine_type(state, cache, die, "subprogram");
+	return 0;
+}
+
+static void process_subprogram(struct state *state, Dwarf_Die *die)
+{
+	process_symbol(state, die, __process_subprogram);
+}
+
+static int __process_variable(struct state *state, struct die *cache,
+			      Dwarf_Die *die)
+{
+	process(cache, "variable ");
+	process_type_attr(state, cache, die);
+	return 0;
+}
+
+static void process_variable(struct state *state, Dwarf_Die *die)
+{
+	process_symbol(state, die, __process_variable);
+}
+
+static void save_symbol_ptr(struct state *state)
+{
+	Dwarf_Die ptr_type;
+	Dwarf_Die type;
+
+	if (!get_ref_die_attr(&state->die, DW_AT_type, &ptr_type) ||
+	    dwarf_tag(&ptr_type) != DW_TAG_pointer_type)
+		error("%s must be a pointer type!",
+		      get_symbol_name(&state->die));
+
+	if (!get_ref_die_attr(&ptr_type, DW_AT_type, &type))
+		error("%s pointer missing a type attribute?",
+		      get_symbol_name(&state->die));
+
+	/*
+	 * Save the symbol pointer DIE in case the actual symbol is
+	 * missing from the DWARF. Clang, for example, intentionally
+	 * omits external symbols from the debugging information.
+	 */
+	if (dwarf_tag(&type) == DW_TAG_subroutine_type)
+		symbol_set_ptr(state->sym, &type);
+	else
+		symbol_set_ptr(state->sym, &ptr_type);
+}
+
+static int process_exported_symbols(struct state *unused, struct die *cache,
+				    Dwarf_Die *die)
+{
+	int tag = dwarf_tag(die);
+
+	switch (tag) {
+	/* Possible containers of exported symbols */
+	case DW_TAG_namespace:
+	case DW_TAG_class_type:
+	case DW_TAG_structure_type:
+		return check(process_die_container(
+			NULL, cache, die, process_exported_symbols, match_all));
+
+	/* Possible exported symbols */
+	case DW_TAG_subprogram:
+	case DW_TAG_variable: {
+		struct state state;
+
+		if (!match_export_symbol(&state, die))
+			return 0;
+
+		state_init(&state);
+
+		if (is_symbol_ptr(get_symbol_name(&state.die)))
+			save_symbol_ptr(&state);
+		else if (tag == DW_TAG_subprogram)
+			process_subprogram(&state, &state.die);
+		else
+			process_variable(&state, &state.die);
+
+		cache_free(&state.expansion_cache);
+		return 0;
+	}
+	default:
+		return 0;
+	}
+}
+
+static void process_symbol_ptr(struct symbol *sym, void *arg)
+{
+	struct state state;
+	Dwarf *dwarf = arg;
+
+	if (sym->state != SYMBOL_UNPROCESSED || !sym->ptr_die_addr)
+		return;
+
+	debug("%s", sym->name);
+	state_init(&state);
+	state.sym = sym;
+
+	if (!dwarf_die_addr_die(dwarf, (void *)sym->ptr_die_addr, &state.die))
+		error("dwarf_die_addr_die failed for symbol ptr: '%s'",
+		      sym->name);
+
+	if (dwarf_tag(&state.die) == DW_TAG_subroutine_type)
+		process_subprogram(&state, &state.die);
+	else
+		process_variable(&state, &state.die);
+
+	cache_free(&state.expansion_cache);
+}
+
+void process_cu(Dwarf_Die *cudie)
+{
+	check(process_die_container(NULL, NULL, cudie, process_exported_symbols,
+				    match_all));
+
+	symbol_for_each(process_symbol_ptr, dwarf_cu_getdwarf(cudie->cu));
+
+	cache_free(&srcfile_cache);
+}
diff --git a/scripts/gendwarfksyms/examples/kabi.h b/scripts/gendwarfksyms/examples/kabi.h
new file mode 100644
index 000000000000..97a5669b083d
--- /dev/null
+++ b/scripts/gendwarfksyms/examples/kabi.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Google LLC
+ *
+ * Example macros for maintaining kABI stability.
+ *
+ * This file is based on android_kabi.h, which has the following notice:
+ *
+ * Heavily influenced by rh_kabi.h which came from the RHEL/CENTOS kernel
+ * and was:
+ *	Copyright (c) 2014 Don Zickus
+ *	Copyright (c) 2015-2018 Jiri Benc
+ *	Copyright (c) 2015 Sabrina Dubroca, Hannes Frederic Sowa
+ *	Copyright (c) 2016-2018 Prarit Bhargava
+ *	Copyright (c) 2017 Paolo Abeni, Larry Woodman
+ */
+
+#ifndef __KABI_H__
+#define __KABI_H__
+
+/* Kernel macros for userspace testing. */
+#ifndef __aligned
+#define __aligned(x) __attribute__((__aligned__(x)))
+#endif
+#ifndef __used
+#define __used __attribute__((__used__))
+#endif
+#ifndef __section
+#define __section(section) __attribute__((__section__(section)))
+#endif
+#ifndef __PASTE
+#define ___PASTE(a, b) a##b
+#define __PASTE(a, b) ___PASTE(a, b)
+#endif
+#ifndef __stringify
+#define __stringify_1(x...) #x
+#define __stringify(x...) __stringify_1(x)
+#endif
+
+#define __KABI_RULE(hint, target, value)                             \
+	static const char __PASTE(__gendwarfksyms_rule_,             \
+				  __COUNTER__)[] __used __aligned(1) \
+		__section(".discard.gendwarfksyms.kabi_rules") =     \
+			"1\0" #hint "\0" #target "\0" #value
+
+#define __KABI_NORMAL_SIZE_ALIGN(_orig, _new)                                             \
+	union {                                                                           \
+		_Static_assert(                                                           \
+			sizeof(struct { _new; }) <= sizeof(struct { _orig; }),            \
+			__FILE__ ":" __stringify(__LINE__) ": " __stringify(              \
+				_new) " is larger than " __stringify(_orig));             \
+		_Static_assert(                                                           \
+			__alignof__(struct { _new; }) <=                                  \
+				__alignof__(struct { _orig; }),                           \
+			__FILE__ ":" __stringify(__LINE__) ": " __stringify(              \
+				_orig) " is not aligned the same as " __stringify(_new)); \
+	}
+
+#define __KABI_REPLACE(_orig, _new)                    \
+	union {                                        \
+		_new;                                  \
+		struct {                               \
+			_orig;                         \
+		};                                     \
+		__KABI_NORMAL_SIZE_ALIGN(_orig, _new); \
+	}
+
+/*
+ * KABI_DECLONLY(fqn)
+ *   Treat the struct/union/enum fqn as a declaration, i.e. even if
+ *   a definition is available, don't expand the contents.
+ */
+#define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, )
+
+/*
+ * KABI_ENUMERATOR_IGNORE(fqn, field)
+ *   When expanding enum fqn, skip the provided field. This makes it
+ *   possible to hide added enum fields from versioning.
+ */
+#define KABI_ENUMERATOR_IGNORE(fqn, field) \
+	__KABI_RULE(enumerator_ignore, fqn field, )
+
+/*
+ * KABI_ENUMERATOR_VALUE(fqn, field, value)
+ *   When expanding enum fqn, use the provided value for the
+ *   specified field. This makes it possible to override enumerator
+ *   values when calculating versions.
+ */
+#define KABI_ENUMERATOR_VALUE(fqn, field, value) \
+	__KABI_RULE(enumerator_value, fqn field, value)
+
+/*
+ * KABI_RESERVE
+ *   Reserve some "padding" in a structure for use by LTS backports.
+ *   This is normally placed at the end of a structure.
+ *   number: the "number" of the padding variable in the structure.  Start with
+ *   1 and go up.
+ */
+#define KABI_RESERVE(n) unsigned long __kabi_reserved##n
+
+/*
+ * KABI_RESERVE_ARRAY
+ *   Same as _BACKPORT_RESERVE but allocates an array with the specified
+ *   size in bytes.
+ */
+#define KABI_RESERVE_ARRAY(n, s) \
+	unsigned char __aligned(8) __kabi_reserved##n[s]
+
+/*
+ * KABI_IGNORE
+ *   Add a new field that's ignored in versioning.
+ */
+#define KABI_IGNORE(n, _new)                     \
+	union {                                  \
+		_new;                            \
+		unsigned char __kabi_ignored##n; \
+	}
+
+/*
+ * KABI_REPLACE
+ *   Replace a field with a compatible new field.
+ */
+#define KABI_REPLACE(_oldtype, _oldname, _new) \
+	__KABI_REPLACE(_oldtype __kabi_renamed##_oldname, struct { _new; })
+
+/*
+ * KABI_USE(number, _new)
+ *   Use a previous padding entry that was defined with KABI_RESERVE
+ *   number: the previous "number" of the padding variable
+ *   _new: the variable to use now instead of the padding variable
+ */
+#define KABI_USE(number, _new) __KABI_REPLACE(KABI_RESERVE(number), _new)
+
+/*
+ * KABI_USE2(number, _new1, _new2)
+ *   Use a previous padding entry that was defined with KABI_RESERVE for
+ *   two new variables that fit into 64 bits.  This is good for when you do not
+ *   want to "burn" a 64bit padding variable for a smaller variable size if not
+ *   needed.
+ */
+#define KABI_USE2(number, _new1, _new2)        \
+	__KABI_REPLACE(                        \
+		KABI_RESERVE(number), struct { \
+			_new1;                 \
+			_new2;                 \
+		})
+/*
+ * KABI_USE_ARRAY(number, bytes, _new)
+ *   Use a previous padding entry that was defined with KABI_RESERVE_ARRAY
+ *   number: the previous "number" of the padding variable
+ *   bytes: the size in bytes reserved for the array
+ *   _new: the variable to use now instead of the padding variable
+ */
+#define KABI_USE_ARRAY(number, bytes, _new) \
+	__KABI_REPLACE(KABI_RESERVE_ARRAY(number, bytes), _new)
+
+#endif /* __KABI_H__ */
diff --git a/scripts/gendwarfksyms/examples/kabi_ex.c b/scripts/gendwarfksyms/examples/kabi_ex.c
new file mode 100644
index 000000000000..0b7ffd830541
--- /dev/null
+++ b/scripts/gendwarfksyms/examples/kabi_ex.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kabi_ex.c
+ *
+ * Copyright (C) 2024 Google LLC
+ *
+ * Examples for kABI stability features with --stable. See kabi_ex.h
+ * for details.
+ */
+
+#include "kabi_ex.h"
+
+struct s e0;
+enum e e1;
+
+struct ex0a ex0a;
+struct ex0b ex0b;
+struct ex0c ex0c;
+
+struct ex1a ex1a;
+struct ex1b ex1b;
+struct ex1c ex1c;
+
+struct ex2a ex2a;
+struct ex2b ex2b;
+struct ex2c ex2c;
+
+struct ex3a ex3a;
+struct ex3b ex3b;
+struct ex3c ex3c;
diff --git a/scripts/gendwarfksyms/examples/kabi_ex.h b/scripts/gendwarfksyms/examples/kabi_ex.h
new file mode 100644
index 000000000000..1736e0f65208
--- /dev/null
+++ b/scripts/gendwarfksyms/examples/kabi_ex.h
@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * kabi_ex.h
+ *
+ * Copyright (C) 2024 Google LLC
+ *
+ * Examples for kABI stability features with --stable.
+ */
+
+/*
+ * The comments below each example contain the expected gendwarfksyms
+ * output, which can be verified using LLVM's FileCheck tool:
+ *
+ * https://llvm.org/docs/CommandGuide/FileCheck.html
+ *
+ * Usage:
+ *
+ * $ gcc -g -c examples/kabi_ex.c -o examples/kabi_ex.o
+ *
+ * $ nm examples/kabi_ex.o | awk '{ print $NF }' | \
+ * 	./gendwarfksyms --stable --dump-dies \
+ * 		examples/kabi_ex.o 2>&1 >/dev/null | \
+ * 	FileCheck examples/kabi_ex.h --check-prefix=STABLE
+ */
+
+#ifndef __KABI_EX_H__
+#define __KABI_EX_H__
+
+#include "kabi.h"
+
+/*
+ * Example: kABI rules
+ */
+
+struct s {
+	int a;
+};
+
+KABI_DECLONLY(s);
+
+/*
+ * STABLE:      variable structure_type s {
+ * STABLE-NEXT: }
+ */
+
+enum e {
+	A,
+	B,
+	C,
+	D,
+};
+
+KABI_ENUMERATOR_IGNORE(e, B);
+KABI_ENUMERATOR_IGNORE(e, C);
+KABI_ENUMERATOR_VALUE(e, D, 123456789);
+
+/*
+ * STABLE:      variable enumeration_type e {
+ * STABLE-NEXT:   enumerator A = 0 ,
+ * STABLE-NEXT:   enumerator D = 123456789
+ * STABLE-NEXT: } byte_size(4)
+*/
+
+/*
+ * Example: Reserved fields
+ */
+struct ex0a {
+	int a;
+	KABI_RESERVE(0);
+	KABI_RESERVE(1);
+};
+
+/*
+ * STABLE:      variable structure_type ex0a {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) data_member_location(8) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16)
+ * STABLE-NEXT: } byte_size(24)
+ */
+
+struct ex0b {
+	int a;
+	KABI_RESERVE(0);
+	KABI_USE2(1, int b, int c);
+};
+
+/*
+ * STABLE:      variable structure_type ex0b {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16)
+ * STABLE-NEXT: } byte_size(24)
+ */
+
+struct ex0c {
+	int a;
+	KABI_USE(0, void *p);
+	KABI_USE2(1, int b, int c);
+};
+
+/*
+ * STABLE:      variable structure_type ex0c {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16)
+ * STABLE-NEXT: } byte_size(24)
+ */
+
+/*
+ * Example: A reserved array
+ */
+
+struct ex1a {
+	unsigned int a;
+	KABI_RESERVE_ARRAY(0, 64);
+};
+
+/*
+ * STABLE:      variable structure_type ex1a {
+ * STABLE-NEXT:   member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) ,
+ * STABLE-NEXT:   member array_type[64] {
+ * STABLE-NEXT:     base_type unsigned char byte_size(1) encoding(8)
+ * STABLE-NEXT:   } data_member_location(8)
+ * STABLE-NEXT: } byte_size(72)
+ */
+
+struct ex1b {
+	unsigned int a;
+	KABI_USE_ARRAY(
+		0, 64, struct {
+			void *p;
+			KABI_RESERVE_ARRAY(1, 56);
+		});
+};
+
+/*
+ * STABLE:      variable structure_type ex1b {
+ * STABLE-NEXT:   member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) ,
+ * STABLE-NEXT:   member array_type[64] {
+ * STABLE-NEXT:     base_type unsigned char byte_size(1) encoding(8)
+ * STABLE-NEXT:   } data_member_location(8)
+ * STABLE-NEXT: } byte_size(72)
+ */
+
+struct ex1c {
+	unsigned int a;
+	KABI_USE_ARRAY(0, 64, void *p[8]);
+};
+
+/*
+ * STABLE:      variable structure_type ex1c {
+ * STABLE-NEXT:   member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) ,
+ * STABLE-NEXT:   member array_type[64] {
+ * STABLE-NEXT:     base_type unsigned char byte_size(1) encoding(8)
+ * STABLE-NEXT:   } data_member_location(8)
+ * STABLE-NEXT: } byte_size(72)
+ */
+
+/*
+ * Example: An ignored field added to an alignment hole
+ */
+
+struct ex2a {
+	int a;
+	unsigned long b;
+	int c;
+	unsigned long d;
+};
+
+/*
+ * STABLE:      variable structure_type ex2a {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) b data_member_location(8)
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) c data_member_location(16) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24)
+ * STABLE-NEXT: } byte_size(32)
+ */
+
+struct ex2b {
+	int a;
+	KABI_IGNORE(0, unsigned int n);
+	unsigned long b;
+	int c;
+	unsigned long d;
+};
+
+_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2b), "ex2a size doesn't match ex2b");
+
+/*
+ * STABLE:      variable structure_type ex2b {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8)
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) c data_member_location(16) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24)
+ * STABLE-NEXT: } byte_size(32)
+ */
+
+struct ex2c {
+	int a;
+	KABI_IGNORE(0, unsigned int n);
+	unsigned long b;
+	int c;
+	KABI_IGNORE(1, unsigned int m);
+	unsigned long d;
+};
+
+_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2c), "ex2a size doesn't match ex2c");
+
+/*
+ * STABLE:      variable structure_type ex2c {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8)
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) c data_member_location(16) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24)
+ * STABLE-NEXT: } byte_size(32)
+ */
+
+
+/*
+ * Example: A replaced field
+ */
+
+struct ex3a {
+	unsigned long a;
+	unsigned long unused;
+};
+
+/*
+ * STABLE:      variable structure_type ex3a {
+ * STABLE-NEXT:   member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8)
+ * STABLE-NEXT: } byte_size(16)
+ */
+
+struct ex3b {
+	unsigned long a;
+	KABI_REPLACE(unsigned long, unused, unsigned long renamed);
+};
+
+_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3b), "ex3a size doesn't match ex3b");
+
+/*
+ * STABLE:      variable structure_type ex3b {
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8)
+ * STABLE-NEXT: } byte_size(16)
+ */
+
+struct ex3c {
+	unsigned long a;
+	KABI_REPLACE(unsigned long, unused, long replaced);
+};
+
+_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3c), "ex3a size doesn't match ex3c");
+
+/*
+ * STABLE:      variable structure_type ex3c {
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8)
+ * STABLE-NEXT: } byte_size(16)
+ */
+
+#endif /* __KABI_EX_H__ */
diff --git a/scripts/gendwarfksyms/examples/symbolptr.c b/scripts/gendwarfksyms/examples/symbolptr.c
new file mode 100644
index 000000000000..88bc1bd60da8
--- /dev/null
+++ b/scripts/gendwarfksyms/examples/symbolptr.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ *
+ * Example for symbol pointers. When compiled with Clang, gendwarfkyms
+ * uses a symbol pointer for `f`.
+ *
+ * $ clang -g -c examples/symbolptr.c -o examples/symbolptr.o
+ * $ echo -e "f\ng\np" | ./gendwarfksyms -d examples/symbolptr.o
+ */
+
+/* Kernel macros for userspace testing. */
+#ifndef __used
+#define __used __attribute__((__used__))
+#endif
+#ifndef __section
+#define __section(section) __attribute__((__section__(section)))
+#endif
+
+#define __GENDWARFKSYMS_EXPORT(sym)				\
+	static typeof(sym) *__gendwarfksyms_ptr_##sym __used	\
+		__section(".discard.gendwarfksyms") = &sym;
+
+extern void f(unsigned int arg);
+void g(int *arg);
+void g(int *arg) {}
+
+struct s;
+extern struct s *p;
+
+__GENDWARFKSYMS_EXPORT(f);
+__GENDWARFKSYMS_EXPORT(g);
+__GENDWARFKSYMS_EXPORT(p);
diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c
new file mode 100644
index 000000000000..08ae61eb327e
--- /dev/null
+++ b/scripts/gendwarfksyms/gendwarfksyms.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <fcntl.h>
+#include <getopt.h>
+#include <errno.h>
+#include <stdarg.h>
+#include <string.h>
+#include <unistd.h>
+#include "gendwarfksyms.h"
+
+/*
+ * Options
+ */
+
+/* Print debugging information to stderr */
+int debug;
+/* Dump DIE contents */
+int dump_dies;
+/* Print debugging information about die_map changes */
+int dump_die_map;
+/* Print out type strings (i.e. type_map) */
+int dump_types;
+/* Print out expanded type strings used for symbol versions */
+int dump_versions;
+/* Support kABI stability features */
+int stable;
+/* Write a symtypes file */
+int symtypes;
+static const char *symtypes_file;
+
+static void usage(void)
+{
+	fputs("Usage: gendwarfksyms [options] elf-object-file ... < symbol-list\n\n"
+	      "Options:\n"
+	      "  -d, --debug          Print debugging information\n"
+	      "      --dump-dies      Dump DWARF DIE contents\n"
+	      "      --dump-die-map   Print debugging information about die_map changes\n"
+	      "      --dump-types     Dump type strings\n"
+	      "      --dump-versions  Dump expanded type strings used for symbol versions\n"
+	      "  -s, --stable         Support kABI stability features\n"
+	      "  -T, --symtypes file  Write a symtypes file\n"
+	      "  -h, --help           Print this message\n"
+	      "\n",
+	      stderr);
+}
+
+static int process_module(Dwfl_Module *mod, void **userdata, const char *name,
+			  Dwarf_Addr base, void *arg)
+{
+	Dwarf_Addr dwbias;
+	Dwarf_Die cudie;
+	Dwarf_CU *cu = NULL;
+	Dwarf *dbg;
+	FILE *symfile = arg;
+	int res;
+
+	debug("%s", name);
+	dbg = dwfl_module_getdwarf(mod, &dwbias);
+
+	/*
+	 * Look for exported symbols in each CU, follow the DIE tree, and add
+	 * the entries to die_map.
+	 */
+	do {
+		res = dwarf_get_units(dbg, cu, &cu, NULL, NULL, &cudie, NULL);
+		if (res < 0)
+			error("dwarf_get_units failed: no debugging information?");
+		if (res == 1)
+			break; /* No more units */
+
+		process_cu(&cudie);
+	} while (cu);
+
+	/*
+	 * Use die_map to expand type strings, write them to `symfile`, and
+	 * calculate symbol versions.
+	 */
+	generate_symtypes_and_versions(symfile);
+	die_map_free();
+
+	return DWARF_CB_OK;
+}
+
+static const Dwfl_Callbacks callbacks = {
+	.section_address = dwfl_offline_section_address,
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+};
+
+int main(int argc, char **argv)
+{
+	FILE *symfile = NULL;
+	unsigned int n;
+	int opt;
+
+	static const struct option opts[] = {
+		{ "debug", 0, NULL, 'd' },
+		{ "dump-dies", 0, &dump_dies, 1 },
+		{ "dump-die-map", 0, &dump_die_map, 1 },
+		{ "dump-types", 0, &dump_types, 1 },
+		{ "dump-versions", 0, &dump_versions, 1 },
+		{ "stable", 0, NULL, 's' },
+		{ "symtypes", 1, NULL, 'T' },
+		{ "help", 0, NULL, 'h' },
+		{ 0, 0, NULL, 0 }
+	};
+
+	while ((opt = getopt_long(argc, argv, "dsT:h", opts, NULL)) != EOF) {
+		switch (opt) {
+		case 0:
+			break;
+		case 'd':
+			debug = 1;
+			break;
+		case 's':
+			stable = 1;
+			break;
+		case 'T':
+			symtypes = 1;
+			symtypes_file = optarg;
+			break;
+		case 'h':
+			usage();
+			return 0;
+		default:
+			usage();
+			return 1;
+		}
+	}
+
+	if (dump_die_map)
+		dump_dies = 1;
+
+	if (optind >= argc) {
+		usage();
+		error("no input files?");
+	}
+
+	symbol_read_exports(stdin);
+
+	if (symtypes_file) {
+		symfile = fopen(symtypes_file, "w");
+		if (!symfile)
+			error("fopen failed for '%s': %s", symtypes_file,
+			      strerror(errno));
+	}
+
+	for (n = optind; n < argc; n++) {
+		Dwfl *dwfl;
+		int fd;
+
+		fd = open(argv[n], O_RDONLY);
+		if (fd == -1)
+			error("open failed for '%s': %s", argv[n],
+			      strerror(errno));
+
+		symbol_read_symtab(fd);
+		kabi_read_rules(fd);
+
+		dwfl = dwfl_begin(&callbacks);
+		if (!dwfl)
+			error("dwfl_begin failed for '%s': %s", argv[n],
+			      dwarf_errmsg(-1));
+
+		if (!dwfl_report_offline(dwfl, argv[n], argv[n], fd))
+			error("dwfl_report_offline failed for '%s': %s",
+			      argv[n], dwarf_errmsg(-1));
+
+		dwfl_report_end(dwfl, NULL, NULL);
+
+		if (dwfl_getmodules(dwfl, &process_module, symfile, 0))
+			error("dwfl_getmodules failed for '%s'", argv[n]);
+
+		dwfl_end(dwfl);
+		kabi_free();
+	}
+
+	if (symfile)
+		check(fclose(symfile));
+
+	symbol_print_versions();
+	symbol_free();
+
+	return 0;
+}
diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h
new file mode 100644
index 000000000000..197a1a8123c6
--- /dev/null
+++ b/scripts/gendwarfksyms/gendwarfksyms.h
@@ -0,0 +1,296 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#include <hash.h>
+#include <hashtable.h>
+#include <xalloc.h>
+
+#ifndef __GENDWARFKSYMS_H
+#define __GENDWARFKSYMS_H
+
+/*
+ * Options -- in gendwarfksyms.c
+ */
+extern int debug;
+extern int dump_dies;
+extern int dump_die_map;
+extern int dump_types;
+extern int dump_versions;
+extern int stable;
+extern int symtypes;
+
+/*
+ * Output helpers
+ */
+#define __PREFIX "gendwarfksyms: "
+#define __println(prefix, format, ...)                                \
+	fprintf(stderr, prefix __PREFIX "%s: " format "\n", __func__, \
+		##__VA_ARGS__)
+
+#define debug(format, ...)                                    \
+	do {                                                  \
+		if (debug)                                    \
+			__println("", format, ##__VA_ARGS__); \
+	} while (0)
+
+#define warn(format, ...) __println("warning: ", format, ##__VA_ARGS__)
+#define error(format, ...)                                   \
+	do {                                                 \
+		__println("error: ", format, ##__VA_ARGS__); \
+		exit(1);                                     \
+	} while (0)
+
+#define __die_debug(color, format, ...)                                 \
+	do {                                                            \
+		if (dump_dies && dump_die_map)                          \
+			fprintf(stderr,                                 \
+				"\033[" #color "m<" format ">\033[39m", \
+				__VA_ARGS__);                           \
+	} while (0)
+
+#define die_debug_r(format, ...) __die_debug(91, format, __VA_ARGS__)
+#define die_debug_g(format, ...) __die_debug(92, format, __VA_ARGS__)
+#define die_debug_b(format, ...) __die_debug(94, format, __VA_ARGS__)
+
+/*
+ * Error handling helpers
+ */
+#define __check(expr, test)                                     \
+	({                                                      \
+		int __res = expr;                               \
+		if (test)                                       \
+			error("`%s` failed: %d", #expr, __res); \
+		__res;                                          \
+	})
+
+/* Error == non-zero values */
+#define check(expr) __check(expr, __res)
+/* Error == negative values */
+#define checkp(expr) __check(expr, __res < 0)
+
+/* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */
+#define DW_TAG_enumerator_type DW_TAG_enumerator
+#define DW_TAG_formal_parameter_type DW_TAG_formal_parameter
+#define DW_TAG_member_type DW_TAG_member
+#define DW_TAG_template_type_parameter_type DW_TAG_template_type_parameter
+#define DW_TAG_typedef_type DW_TAG_typedef
+#define DW_TAG_variant_part_type DW_TAG_variant_part
+#define DW_TAG_variant_type DW_TAG_variant
+
+/*
+ * symbols.c
+ */
+
+/* See symbols.c:is_symbol_ptr */
+#define SYMBOL_PTR_PREFIX "__gendwarfksyms_ptr_"
+#define SYMBOL_PTR_PREFIX_LEN (sizeof(SYMBOL_PTR_PREFIX) - 1)
+
+static inline unsigned int addr_hash(uintptr_t addr)
+{
+	return hash_ptr((const void *)addr);
+}
+
+enum symbol_state {
+	SYMBOL_UNPROCESSED,
+	SYMBOL_MAPPED,
+	SYMBOL_PROCESSED
+};
+
+struct symbol_addr {
+	uint32_t section;
+	Elf64_Addr address;
+};
+
+struct symbol {
+	const char *name;
+	struct symbol_addr addr;
+	struct hlist_node addr_hash;
+	struct hlist_node name_hash;
+	enum symbol_state state;
+	uintptr_t die_addr;
+	uintptr_t ptr_die_addr;
+	unsigned long crc;
+};
+
+typedef void (*symbol_callback_t)(struct symbol *, void *arg);
+
+bool is_symbol_ptr(const char *name);
+void symbol_read_exports(FILE *file);
+void symbol_read_symtab(int fd);
+struct symbol *symbol_get(const char *name);
+void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr);
+void symbol_set_die(struct symbol *sym, Dwarf_Die *die);
+void symbol_set_crc(struct symbol *sym, unsigned long crc);
+void symbol_for_each(symbol_callback_t func, void *arg);
+void symbol_print_versions(void);
+void symbol_free(void);
+
+/*
+ * die.c
+ */
+
+enum die_state {
+	DIE_INCOMPLETE,
+	DIE_UNEXPANDED,
+	DIE_COMPLETE,
+	DIE_SYMBOL,
+	DIE_LAST = DIE_SYMBOL
+};
+
+enum die_fragment_type {
+	FRAGMENT_EMPTY,
+	FRAGMENT_STRING,
+	FRAGMENT_LINEBREAK,
+	FRAGMENT_DIE
+};
+
+struct die_fragment {
+	enum die_fragment_type type;
+	union {
+		char *str;
+		int linebreak;
+		uintptr_t addr;
+	} data;
+	struct list_head list;
+};
+
+#define CASE_CONST_TO_STR(name) \
+	case name:              \
+		return #name;
+
+static inline const char *die_state_name(enum die_state state)
+{
+	switch (state) {
+	CASE_CONST_TO_STR(DIE_INCOMPLETE)
+	CASE_CONST_TO_STR(DIE_UNEXPANDED)
+	CASE_CONST_TO_STR(DIE_COMPLETE)
+	CASE_CONST_TO_STR(DIE_SYMBOL)
+	}
+
+	error("unexpected die_state: %d", state);
+}
+
+struct die {
+	enum die_state state;
+	bool mapped;
+	char *fqn;
+	int tag;
+	uintptr_t addr;
+	struct list_head fragments;
+	struct hlist_node hash;
+};
+
+typedef void (*die_map_callback_t)(struct die *, void *arg);
+
+int __die_map_get(uintptr_t addr, enum die_state state, struct die **res);
+struct die *die_map_get(Dwarf_Die *die, enum die_state state);
+void die_map_add_string(struct die *pd, const char *str);
+void die_map_add_linebreak(struct die *pd, int linebreak);
+void die_map_for_each(die_map_callback_t func, void *arg);
+void die_map_add_die(struct die *pd, struct die *child);
+void die_map_free(void);
+
+/*
+ * cache.c
+ */
+
+#define CACHE_HASH_BITS 10
+
+/* A cache for addresses we've already seen. */
+struct cache {
+	HASHTABLE_DECLARE(cache, 1 << CACHE_HASH_BITS);
+};
+
+void cache_set(struct cache *cache, unsigned long key, int value);
+int cache_get(struct cache *cache, unsigned long key);
+void cache_init(struct cache *cache);
+void cache_free(struct cache *cache);
+
+static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr)
+{
+	cache_set(cache, addr, 1);
+}
+
+static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr)
+{
+	return cache_get(cache, addr) == 1;
+}
+
+static inline void cache_mark_expanded(struct cache *cache, void *addr)
+{
+	__cache_mark_expanded(cache, (uintptr_t)addr);
+}
+
+static inline bool cache_was_expanded(struct cache *cache, void *addr)
+{
+	return __cache_was_expanded(cache, (uintptr_t)addr);
+}
+
+/*
+ * dwarf.c
+ */
+
+struct expansion_state {
+	bool expand;
+	const char *current_fqn;
+};
+
+struct kabi_state {
+	int members;
+	Dwarf_Die placeholder;
+	const char *orig_name;
+};
+
+struct state {
+	struct symbol *sym;
+	Dwarf_Die die;
+
+	/* List expansion */
+	bool first_list_item;
+
+	/* Structure expansion */
+	struct expansion_state expand;
+	struct cache expansion_cache;
+
+	/* Reserved or ignored members */
+	struct kabi_state kabi;
+};
+
+typedef int (*die_callback_t)(struct state *state, struct die *cache,
+			      Dwarf_Die *die);
+typedef bool (*die_match_callback_t)(Dwarf_Die *die);
+bool match_all(Dwarf_Die *die);
+
+int process_die_container(struct state *state, struct die *cache,
+			  Dwarf_Die *die, die_callback_t func,
+			  die_match_callback_t match);
+
+void process_cu(Dwarf_Die *cudie);
+
+/*
+ * types.c
+ */
+
+void generate_symtypes_and_versions(FILE *file);
+
+/*
+ * kabi.c
+ */
+
+bool kabi_is_enumerator_ignored(const char *fqn, const char *field);
+bool kabi_get_enumerator_value(const char *fqn, const char *field,
+			       unsigned long *value);
+bool kabi_is_declonly(const char *fqn);
+
+void kabi_read_rules(int fd);
+void kabi_free(void);
+
+#endif /* __GENDWARFKSYMS_H */
diff --git a/scripts/gendwarfksyms/kabi.c b/scripts/gendwarfksyms/kabi.c
new file mode 100644
index 000000000000..66f01fcd1607
--- /dev/null
+++ b/scripts/gendwarfksyms/kabi.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdio.h>
+
+#include "gendwarfksyms.h"
+
+#define KABI_RULE_SECTION ".discard.gendwarfksyms.kabi_rules"
+#define KABI_RULE_VERSION "1"
+
+/*
+ * The rule section consists of four null-terminated strings per
+ * entry:
+ *
+ *   1. version
+ *      Entry format version. Must match KABI_RULE_VERSION.
+ *
+ *   2. type
+ *      Type of the kABI rule. Must be one of the tags defined below.
+ *
+ *   3. target
+ *      Rule-dependent target, typically the fully qualified name of
+ *      the target DIE.
+ *
+ *   4. value
+ *      Rule-dependent value.
+ */
+#define KABI_RULE_MIN_ENTRY_SIZE                                  \
+	(/* version\0 */ 2 + /* type\0 */ 2 + /* target\0" */ 1 + \
+	 /* value\0 */ 1)
+#define KABI_RULE_EMPTY_VALUE ""
+
+/*
+ * Rule: declonly
+ * - For the struct/enum/union in the target field, treat it as a
+ *   declaration only even if a definition is available.
+ */
+#define KABI_RULE_TAG_DECLONLY "declonly"
+
+/*
+ * Rule: enumerator_ignore
+ * - For the enum_field in the target field, ignore the enumerator.
+ */
+#define KABI_RULE_TAG_ENUMERATOR_IGNORE "enumerator_ignore"
+
+/*
+ * Rule: enumerator_value
+ * - For the fqn_field in the target field, set the value to the
+ *   unsigned integer in the value field.
+ */
+#define KABI_RULE_TAG_ENUMERATOR_VALUE "enumerator_value"
+
+enum kabi_rule_type {
+	KABI_RULE_TYPE_UNKNOWN,
+	KABI_RULE_TYPE_DECLONLY,
+	KABI_RULE_TYPE_ENUMERATOR_IGNORE,
+	KABI_RULE_TYPE_ENUMERATOR_VALUE,
+};
+
+#define RULE_HASH_BITS 7
+
+struct rule {
+	enum kabi_rule_type type;
+	const char *target;
+	const char *value;
+	struct hlist_node hash;
+};
+
+/* { type, target } -> struct rule */
+static HASHTABLE_DEFINE(rules, 1 << RULE_HASH_BITS);
+
+static inline unsigned int rule_values_hash(enum kabi_rule_type type,
+					    const char *target)
+{
+	return hash_32(type) ^ hash_str(target);
+}
+
+static inline unsigned int rule_hash(const struct rule *rule)
+{
+	return rule_values_hash(rule->type, rule->target);
+}
+
+static inline const char *get_rule_field(const char **pos, ssize_t *left)
+{
+	const char *start = *pos;
+	size_t len;
+
+	if (*left <= 0)
+		error("unexpected end of kABI rules");
+
+	len = strnlen(start, *left) + 1;
+	*pos += len;
+	*left -= len;
+
+	return start;
+}
+
+void kabi_read_rules(int fd)
+{
+	GElf_Shdr shdr_mem;
+	GElf_Shdr *shdr;
+	Elf_Data *rule_data = NULL;
+	Elf_Scn *scn;
+	Elf *elf;
+	size_t shstrndx;
+	const char *rule_str;
+	ssize_t left;
+	int i;
+
+	const struct {
+		enum kabi_rule_type type;
+		const char *tag;
+	} rule_types[] = {
+		{
+			.type = KABI_RULE_TYPE_DECLONLY,
+			.tag = KABI_RULE_TAG_DECLONLY,
+		},
+		{
+			.type = KABI_RULE_TYPE_ENUMERATOR_IGNORE,
+			.tag = KABI_RULE_TAG_ENUMERATOR_IGNORE,
+		},
+		{
+			.type = KABI_RULE_TYPE_ENUMERATOR_VALUE,
+			.tag = KABI_RULE_TAG_ENUMERATOR_VALUE,
+		},
+	};
+
+	if (!stable)
+		return;
+
+	if (elf_version(EV_CURRENT) != EV_CURRENT)
+		error("elf_version failed: %s", elf_errmsg(-1));
+
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf)
+		error("elf_begin failed: %s", elf_errmsg(-1));
+
+	if (elf_getshdrstrndx(elf, &shstrndx) < 0)
+		error("elf_getshdrstrndx failed: %s", elf_errmsg(-1));
+
+	scn = elf_nextscn(elf, NULL);
+
+	while (scn) {
+		const char *sname;
+
+		shdr = gelf_getshdr(scn, &shdr_mem);
+		if (!shdr)
+			error("gelf_getshdr failed: %s", elf_errmsg(-1));
+
+		sname = elf_strptr(elf, shstrndx, shdr->sh_name);
+		if (!sname)
+			error("elf_strptr failed: %s", elf_errmsg(-1));
+
+		if (!strcmp(sname, KABI_RULE_SECTION)) {
+			rule_data = elf_getdata(scn, NULL);
+			if (!rule_data)
+				error("elf_getdata failed: %s", elf_errmsg(-1));
+			break;
+		}
+
+		scn = elf_nextscn(elf, scn);
+	}
+
+	if (!rule_data) {
+		debug("kABI rules not found");
+		check(elf_end(elf));
+		return;
+	}
+
+	rule_str = rule_data->d_buf;
+	left = shdr->sh_size;
+
+	if (left < KABI_RULE_MIN_ENTRY_SIZE)
+		error("kABI rule section too small: %zd bytes", left);
+
+	if (rule_str[left - 1] != '\0')
+		error("kABI rules are not null-terminated");
+
+	while (left > KABI_RULE_MIN_ENTRY_SIZE) {
+		enum kabi_rule_type type = KABI_RULE_TYPE_UNKNOWN;
+		const char *field;
+		struct rule *rule;
+
+		/* version */
+		field = get_rule_field(&rule_str, &left);
+
+		if (strcmp(field, KABI_RULE_VERSION))
+			error("unsupported kABI rule version: '%s'", field);
+
+		/* type */
+		field = get_rule_field(&rule_str, &left);
+
+		for (i = 0; i < ARRAY_SIZE(rule_types); i++) {
+			if (!strcmp(field, rule_types[i].tag)) {
+				type = rule_types[i].type;
+				break;
+			}
+		}
+
+		if (type == KABI_RULE_TYPE_UNKNOWN)
+			error("unsupported kABI rule type: '%s'", field);
+
+		rule = xmalloc(sizeof(struct rule));
+
+		rule->type = type;
+		rule->target = xstrdup(get_rule_field(&rule_str, &left));
+		rule->value = xstrdup(get_rule_field(&rule_str, &left));
+
+		hash_add(rules, &rule->hash, rule_hash(rule));
+
+		debug("kABI rule: type: '%s', target: '%s', value: '%s'", field,
+		      rule->target, rule->value);
+	}
+
+	if (left > 0)
+		warn("unexpected data at the end of the kABI rules section");
+
+	check(elf_end(elf));
+}
+
+bool kabi_is_declonly(const char *fqn)
+{
+	struct rule *rule;
+
+	if (!stable)
+		return false;
+	if (!fqn || !*fqn)
+		return false;
+
+	hash_for_each_possible(rules, rule, hash,
+			       rule_values_hash(KABI_RULE_TYPE_DECLONLY, fqn)) {
+		if (rule->type == KABI_RULE_TYPE_DECLONLY &&
+		    !strcmp(fqn, rule->target))
+			return true;
+	}
+
+	return false;
+}
+
+static char *get_enumerator_target(const char *fqn, const char *field)
+{
+	char *target = NULL;
+
+	if (asprintf(&target, "%s %s", fqn, field) < 0)
+		error("asprintf failed for '%s %s'", fqn, field);
+
+	return target;
+}
+
+static unsigned long get_ulong_value(const char *value)
+{
+	unsigned long result = 0;
+	char *endptr = NULL;
+
+	errno = 0;
+	result = strtoul(value, &endptr, 10);
+
+	if (errno || *endptr)
+		error("invalid unsigned value '%s'", value);
+
+	return result;
+}
+
+bool kabi_is_enumerator_ignored(const char *fqn, const char *field)
+{
+	bool match = false;
+	struct rule *rule;
+	char *target;
+
+	if (!stable)
+		return false;
+	if (!fqn || !*fqn || !field || !*field)
+		return false;
+
+	target = get_enumerator_target(fqn, field);
+
+	hash_for_each_possible(
+		rules, rule, hash,
+		rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_IGNORE, target)) {
+		if (rule->type == KABI_RULE_TYPE_ENUMERATOR_IGNORE &&
+		    !strcmp(target, rule->target)) {
+			match = true;
+			break;
+		}
+	}
+
+	free(target);
+	return match;
+}
+
+bool kabi_get_enumerator_value(const char *fqn, const char *field,
+			       unsigned long *value)
+{
+	bool match = false;
+	struct rule *rule;
+	char *target;
+
+	if (!stable)
+		return false;
+	if (!fqn || !*fqn || !field || !*field)
+		return false;
+
+	target = get_enumerator_target(fqn, field);
+
+	hash_for_each_possible(rules, rule, hash,
+			       rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_VALUE,
+						target)) {
+		if (rule->type == KABI_RULE_TYPE_ENUMERATOR_VALUE &&
+		    !strcmp(target, rule->target)) {
+			*value = get_ulong_value(rule->value);
+			match = true;
+			break;
+		}
+	}
+
+	free(target);
+	return match;
+}
+
+void kabi_free(void)
+{
+	struct hlist_node *tmp;
+	struct rule *rule;
+
+	hash_for_each_safe(rules, rule, tmp, hash) {
+		free((void *)rule->target);
+		free((void *)rule->value);
+		free(rule);
+	}
+
+	hash_init(rules);
+}
diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c
new file mode 100644
index 000000000000..327f87389c34
--- /dev/null
+++ b/scripts/gendwarfksyms/symbols.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include "gendwarfksyms.h"
+
+#define SYMBOL_HASH_BITS 12
+
+/* struct symbol_addr -> struct symbol */
+static HASHTABLE_DEFINE(symbol_addrs, 1 << SYMBOL_HASH_BITS);
+/* name -> struct symbol */
+static HASHTABLE_DEFINE(symbol_names, 1 << SYMBOL_HASH_BITS);
+
+static inline unsigned int symbol_addr_hash(const struct symbol_addr *addr)
+{
+	return hash_32(addr->section ^ addr_hash(addr->address));
+}
+
+static unsigned int __for_each_addr(struct symbol *sym, symbol_callback_t func,
+				    void *data)
+{
+	struct hlist_node *tmp;
+	struct symbol *match = NULL;
+	unsigned int processed = 0;
+
+	hash_for_each_possible_safe(symbol_addrs, match, tmp, addr_hash,
+				    symbol_addr_hash(&sym->addr)) {
+		if (match == sym)
+			continue; /* Already processed */
+
+		if (match->addr.section == sym->addr.section &&
+		    match->addr.address == sym->addr.address) {
+			func(match, data);
+			++processed;
+		}
+	}
+
+	return processed;
+}
+
+/*
+ * For symbols without debugging information (e.g. symbols defined in other
+ * TUs), we also match __gendwarfksyms_ptr_<symbol_name> symbols, which the
+ * kernel uses to ensure type information is present in the TU that exports
+ * the symbol. A __gendwarfksyms_ptr pointer must have the same type as the
+ * exported symbol, e.g.:
+ *
+ *   typeof(symname) *__gendwarf_ptr_symname = &symname;
+ */
+bool is_symbol_ptr(const char *name)
+{
+	return name && !strncmp(name, SYMBOL_PTR_PREFIX, SYMBOL_PTR_PREFIX_LEN);
+}
+
+static unsigned int for_each(const char *name, symbol_callback_t func,
+			     void *data)
+{
+	struct hlist_node *tmp;
+	struct symbol *match;
+
+	if (!name || !*name)
+		return 0;
+	if (is_symbol_ptr(name))
+		name += SYMBOL_PTR_PREFIX_LEN;
+
+	hash_for_each_possible_safe(symbol_names, match, tmp, name_hash,
+				    hash_str(name)) {
+		if (strcmp(match->name, name))
+			continue;
+
+		/* Call func for the match, and all address matches */
+		if (func)
+			func(match, data);
+
+		if (match->addr.section != SHN_UNDEF)
+			return __for_each_addr(match, func, data) + 1;
+
+		return 1;
+	}
+
+	return 0;
+}
+
+static void set_crc(struct symbol *sym, void *data)
+{
+	unsigned long *crc = data;
+
+	if (sym->state == SYMBOL_PROCESSED && sym->crc != *crc)
+		warn("overriding version for symbol %s (crc %lx vs. %lx)",
+		     sym->name, sym->crc, *crc);
+
+	sym->state = SYMBOL_PROCESSED;
+	sym->crc = *crc;
+}
+
+void symbol_set_crc(struct symbol *sym, unsigned long crc)
+{
+	if (for_each(sym->name, set_crc, &crc) == 0)
+		error("no matching symbols: '%s'", sym->name);
+}
+
+static void set_ptr(struct symbol *sym, void *data)
+{
+	sym->ptr_die_addr = (uintptr_t)((Dwarf_Die *)data)->addr;
+}
+
+void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr)
+{
+	if (for_each(sym->name, set_ptr, ptr) == 0)
+		error("no matching symbols: '%s'", sym->name);
+}
+
+static void set_die(struct symbol *sym, void *data)
+{
+	sym->die_addr = (uintptr_t)((Dwarf_Die *)data)->addr;
+	sym->state = SYMBOL_MAPPED;
+}
+
+void symbol_set_die(struct symbol *sym, Dwarf_Die *die)
+{
+	if (for_each(sym->name, set_die, die) == 0)
+		error("no matching symbols: '%s'", sym->name);
+}
+
+static bool is_exported(const char *name)
+{
+	return for_each(name, NULL, NULL) > 0;
+}
+
+void symbol_read_exports(FILE *file)
+{
+	struct symbol *sym;
+	char *line = NULL;
+	char *name = NULL;
+	size_t size = 0;
+	int nsym = 0;
+
+	while (getline(&line, &size, file) > 0) {
+		if (sscanf(line, "%ms\n", &name) != 1)
+			error("malformed input line: %s", line);
+
+		if (is_exported(name)) {
+			/* Ignore duplicates */
+			free(name);
+			continue;
+		}
+
+		sym = xcalloc(1, sizeof(struct symbol));
+		sym->name = name;
+		sym->addr.section = SHN_UNDEF;
+		sym->state = SYMBOL_UNPROCESSED;
+
+		hash_add(symbol_names, &sym->name_hash, hash_str(sym->name));
+		++nsym;
+
+		debug("%s", sym->name);
+	}
+
+	free(line);
+	debug("%d exported symbols", nsym);
+}
+
+static void get_symbol(struct symbol *sym, void *arg)
+{
+	struct symbol **res = arg;
+
+	if (sym->state == SYMBOL_UNPROCESSED)
+		*res = sym;
+}
+
+struct symbol *symbol_get(const char *name)
+{
+	struct symbol *sym = NULL;
+
+	for_each(name, get_symbol, &sym);
+	return sym;
+}
+
+void symbol_for_each(symbol_callback_t func, void *arg)
+{
+	struct hlist_node *tmp;
+	struct symbol *sym;
+
+	hash_for_each_safe(symbol_names, sym, tmp, name_hash) {
+		func(sym, arg);
+	}
+}
+
+typedef void (*elf_symbol_callback_t)(const char *name, GElf_Sym *sym,
+				      Elf32_Word xndx, void *arg);
+
+static void elf_for_each_global(int fd, elf_symbol_callback_t func, void *arg)
+{
+	size_t sym_size;
+	GElf_Shdr shdr_mem;
+	GElf_Shdr *shdr;
+	Elf_Data *xndx_data = NULL;
+	Elf_Scn *scn;
+	Elf *elf;
+
+	if (elf_version(EV_CURRENT) != EV_CURRENT)
+		error("elf_version failed: %s", elf_errmsg(-1));
+
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf)
+		error("elf_begin failed: %s", elf_errmsg(-1));
+
+	scn = elf_nextscn(elf, NULL);
+
+	while (scn) {
+		shdr = gelf_getshdr(scn, &shdr_mem);
+		if (!shdr)
+			error("gelf_getshdr failed: %s", elf_errmsg(-1));
+
+		if (shdr->sh_type == SHT_SYMTAB_SHNDX) {
+			xndx_data = elf_getdata(scn, NULL);
+			if (!xndx_data)
+				error("elf_getdata failed: %s", elf_errmsg(-1));
+			break;
+		}
+
+		scn = elf_nextscn(elf, scn);
+	}
+
+	sym_size = gelf_fsize(elf, ELF_T_SYM, 1, EV_CURRENT);
+	scn = elf_nextscn(elf, NULL);
+
+	while (scn) {
+		shdr = gelf_getshdr(scn, &shdr_mem);
+		if (!shdr)
+			error("gelf_getshdr failed: %s", elf_errmsg(-1));
+
+		if (shdr->sh_type == SHT_SYMTAB) {
+			unsigned int nsyms;
+			unsigned int n;
+			Elf_Data *data = elf_getdata(scn, NULL);
+
+			if (!data)
+				error("elf_getdata failed: %s", elf_errmsg(-1));
+
+			if (shdr->sh_entsize != sym_size)
+				error("expected sh_entsize (%lu) to be %zu",
+				      shdr->sh_entsize, sym_size);
+
+			nsyms = shdr->sh_size / shdr->sh_entsize;
+
+			for (n = 1; n < nsyms; ++n) {
+				const char *name = NULL;
+				Elf32_Word xndx = 0;
+				GElf_Sym sym_mem;
+				GElf_Sym *sym;
+
+				sym = gelf_getsymshndx(data, xndx_data, n,
+						       &sym_mem, &xndx);
+				if (!sym)
+					error("gelf_getsymshndx failed: %s",
+					      elf_errmsg(-1));
+
+				if (GELF_ST_BIND(sym->st_info) == STB_LOCAL)
+					continue;
+
+				if (sym->st_shndx != SHN_XINDEX)
+					xndx = sym->st_shndx;
+
+				name = elf_strptr(elf, shdr->sh_link,
+						  sym->st_name);
+				if (!name)
+					error("elf_strptr failed: %s",
+					      elf_errmsg(-1));
+
+				/* Skip empty symbol names */
+				if (*name)
+					func(name, sym, xndx, arg);
+			}
+		}
+
+		scn = elf_nextscn(elf, scn);
+	}
+
+	check(elf_end(elf));
+}
+
+static void set_symbol_addr(struct symbol *sym, void *arg)
+{
+	struct symbol_addr *addr = arg;
+
+	if (sym->addr.section == SHN_UNDEF) {
+		sym->addr = *addr;
+		hash_add(symbol_addrs, &sym->addr_hash,
+			 symbol_addr_hash(&sym->addr));
+
+		debug("%s -> { %u, %lx }", sym->name, sym->addr.section,
+		      sym->addr.address);
+	} else if (sym->addr.section != addr->section ||
+		   sym->addr.address != addr->address) {
+		warn("multiple addresses for symbol %s?", sym->name);
+	}
+}
+
+static void elf_set_symbol_addr(const char *name, GElf_Sym *sym,
+				Elf32_Word xndx, void *arg)
+{
+	struct symbol_addr addr = { .section = xndx, .address = sym->st_value };
+
+	/* Set addresses for exported symbols */
+	if (addr.section != SHN_UNDEF)
+		for_each(name, set_symbol_addr, &addr);
+}
+
+void symbol_read_symtab(int fd)
+{
+	elf_for_each_global(fd, elf_set_symbol_addr, NULL);
+}
+
+void symbol_print_versions(void)
+{
+	struct hlist_node *tmp;
+	struct symbol *sym;
+
+	hash_for_each_safe(symbol_names, sym, tmp, name_hash) {
+		if (sym->state != SYMBOL_PROCESSED)
+			warn("no information for symbol %s", sym->name);
+
+		printf("#SYMVER %s 0x%08lx\n", sym->name, sym->crc);
+	}
+}
+
+void symbol_free(void)
+{
+	struct hlist_node *tmp;
+	struct symbol *sym;
+
+	hash_for_each_safe(symbol_names, sym, tmp, name_hash) {
+		free((void *)sym->name);
+		free(sym);
+	}
+
+	hash_init(symbol_addrs);
+	hash_init(symbol_names);
+}
diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c
new file mode 100644
index 000000000000..6c03265f4d10
--- /dev/null
+++ b/scripts/gendwarfksyms/types.c
@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#define _GNU_SOURCE
+#include <inttypes.h>
+#include <stdio.h>
+#include <zlib.h>
+
+#include "gendwarfksyms.h"
+
+static struct cache expansion_cache;
+
+/*
+ * A simple linked list of shared or owned strings to avoid copying strings
+ * around when not necessary.
+ */
+struct type_list_entry {
+	const char *str;
+	void *owned;
+	struct list_head list;
+};
+
+static void type_list_free(struct list_head *list)
+{
+	struct type_list_entry *entry;
+	struct type_list_entry *tmp;
+
+	list_for_each_entry_safe(entry, tmp, list, list) {
+		if (entry->owned)
+			free(entry->owned);
+		free(entry);
+	}
+
+	INIT_LIST_HEAD(list);
+}
+
+static int type_list_append(struct list_head *list, const char *s, void *owned)
+{
+	struct type_list_entry *entry;
+
+	if (!s)
+		return 0;
+
+	entry = xmalloc(sizeof(struct type_list_entry));
+	entry->str = s;
+	entry->owned = owned;
+	list_add_tail(&entry->list, list);
+
+	return strlen(entry->str);
+}
+
+static void type_list_write(struct list_head *list, FILE *file)
+{
+	struct type_list_entry *entry;
+
+	list_for_each_entry(entry, list, list) {
+		if (entry->str)
+			checkp(fputs(entry->str, file));
+	}
+}
+
+/*
+ * An expanded type string in symtypes format.
+ */
+struct type_expansion {
+	char *name;
+	size_t len;
+	struct list_head expanded;
+	struct hlist_node hash;
+};
+
+static void type_expansion_init(struct type_expansion *type)
+{
+	type->name = NULL;
+	type->len = 0;
+	INIT_LIST_HEAD(&type->expanded);
+}
+
+static inline void type_expansion_free(struct type_expansion *type)
+{
+	free(type->name);
+	type->name = NULL;
+	type->len = 0;
+	type_list_free(&type->expanded);
+}
+
+static void type_expansion_append(struct type_expansion *type, const char *s,
+				  void *owned)
+{
+	type->len += type_list_append(&type->expanded, s, owned);
+}
+
+/*
+ * type_map -- the longest expansions for each type.
+ *
+ * const char *name -> struct type_expansion *
+ */
+#define TYPE_HASH_BITS 12
+static HASHTABLE_DEFINE(type_map, 1 << TYPE_HASH_BITS);
+
+static int type_map_get(const char *name, struct type_expansion **res)
+{
+	struct type_expansion *e;
+
+	hash_for_each_possible(type_map, e, hash, hash_str(name)) {
+		if (!strcmp(name, e->name)) {
+			*res = e;
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+static void type_map_add(const char *name, struct type_expansion *type)
+{
+	struct type_expansion *e;
+
+	if (type_map_get(name, &e)) {
+		e = xmalloc(sizeof(struct type_expansion));
+		type_expansion_init(e);
+		e->name = xstrdup(name);
+
+		hash_add(type_map, &e->hash, hash_str(e->name));
+
+		if (dump_types)
+			debug("adding %s", e->name);
+	} else {
+		/* Use the longest available expansion */
+		if (type->len <= e->len)
+			return;
+
+		type_list_free(&e->expanded);
+
+		if (dump_types)
+			debug("replacing %s", e->name);
+	}
+
+	/* Take ownership of type->expanded */
+	list_replace_init(&type->expanded, &e->expanded);
+	e->len = type->len;
+
+	if (dump_types) {
+		checkp(fputs(e->name, stderr));
+		checkp(fputs(" ", stderr));
+		type_list_write(&e->expanded, stderr);
+		checkp(fputs("\n", stderr));
+	}
+}
+
+static void type_map_write(FILE *file)
+{
+	struct type_expansion *e;
+	struct hlist_node *tmp;
+
+	if (!file)
+		return;
+
+	hash_for_each_safe(type_map, e, tmp, hash) {
+		checkp(fputs(e->name, file));
+		checkp(fputs(" ", file));
+		type_list_write(&e->expanded, file);
+		checkp(fputs("\n", file));
+	}
+}
+
+static void type_map_free(void)
+{
+	struct type_expansion *e;
+	struct hlist_node *tmp;
+
+	hash_for_each_safe(type_map, e, tmp, hash) {
+		type_expansion_free(e);
+		free(e);
+	}
+
+	hash_init(type_map);
+}
+
+/*
+ * CRC for a type, with an optional fully expanded type string for
+ * debugging.
+ */
+struct version {
+	struct type_expansion type;
+	unsigned long crc;
+};
+
+static void version_init(struct version *version)
+{
+	version->crc = crc32(0, NULL, 0);
+	type_expansion_init(&version->type);
+}
+
+static void version_free(struct version *version)
+{
+	type_expansion_free(&version->type);
+}
+
+static void version_add(struct version *version, const char *s)
+{
+	version->crc = crc32(version->crc, (void *)s, strlen(s));
+	if (dump_versions)
+		type_expansion_append(&version->type, s, NULL);
+}
+
+/*
+ * Type reference format: <prefix>#<name>, where prefix:
+ * 	s -> structure
+ * 	u -> union
+ * 	e -> enum
+ * 	t -> typedef
+ *
+ * Names with spaces are additionally wrapped in single quotes.
+ */
+static inline bool is_type_prefix(const char *s)
+{
+	return (s[0] == 's' || s[0] == 'u' || s[0] == 'e' || s[0] == 't') &&
+	       s[1] == '#';
+}
+
+static char get_type_prefix(int tag)
+{
+	switch (tag) {
+	case DW_TAG_class_type:
+	case DW_TAG_structure_type:
+		return 's';
+	case DW_TAG_union_type:
+		return 'u';
+	case DW_TAG_enumeration_type:
+		return 'e';
+	case DW_TAG_typedef_type:
+		return 't';
+	default:
+		return 0;
+	}
+}
+
+static char *get_type_name(struct die *cache)
+{
+	const char *quote;
+	char prefix;
+	char *name;
+
+	if (cache->state == DIE_INCOMPLETE) {
+		warn("found incomplete cache entry: %p", cache);
+		return NULL;
+	}
+	if (cache->state == DIE_SYMBOL)
+		return NULL;
+	if (!cache->fqn || !*cache->fqn)
+		return NULL;
+
+	prefix = get_type_prefix(cache->tag);
+	if (!prefix)
+		return NULL;
+
+	/* Wrap names with spaces in single quotes */
+	quote = strstr(cache->fqn, " ") ? "'" : "";
+
+	/* <prefix>#<type_name>\0 */
+	if (asprintf(&name, "%c#%s%s%s", prefix, quote, cache->fqn, quote) < 0)
+		error("asprintf failed for '%s'", cache->fqn);
+
+	return name;
+}
+
+static void __calculate_version(struct version *version, struct list_head *list)
+{
+	struct type_list_entry *entry;
+	struct type_expansion *e;
+
+	/* Calculate a CRC over an expanded type string */
+	list_for_each_entry(entry, list, list) {
+		if (is_type_prefix(entry->str)) {
+			check(type_map_get(entry->str, &e));
+
+			/*
+			 * It's sufficient to expand each type reference just
+			 * once to detect changes.
+			 */
+			if (cache_was_expanded(&expansion_cache, e)) {
+				version_add(version, entry->str);
+			} else {
+				cache_mark_expanded(&expansion_cache, e);
+				__calculate_version(version, &e->expanded);
+			}
+		} else {
+			version_add(version, entry->str);
+		}
+	}
+}
+
+static void calculate_version(struct version *version, struct list_head *list)
+{
+	version_init(version);
+	__calculate_version(version, list);
+	cache_free(&expansion_cache);
+}
+
+static void __type_expand(struct die *cache, struct type_expansion *type,
+			  bool recursive);
+
+static void type_expand_child(struct die *cache, struct type_expansion *type,
+			      bool recursive)
+{
+	struct type_expansion child;
+	char *name;
+
+	name = get_type_name(cache);
+	if (!name) {
+		__type_expand(cache, type, recursive);
+		return;
+	}
+
+	if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) {
+		__cache_mark_expanded(&expansion_cache, cache->addr);
+		type_expansion_init(&child);
+		__type_expand(cache, &child, true);
+		type_map_add(name, &child);
+		type_expansion_free(&child);
+	}
+
+	type_expansion_append(type, name, name);
+}
+
+static void __type_expand(struct die *cache, struct type_expansion *type,
+			  bool recursive)
+{
+	struct die_fragment *df;
+	struct die *child;
+
+	list_for_each_entry(df, &cache->fragments, list) {
+		switch (df->type) {
+		case FRAGMENT_STRING:
+			type_expansion_append(type, df->data.str, NULL);
+			break;
+		case FRAGMENT_DIE:
+			/* Use a complete die_map expansion if available */
+			if (__die_map_get(df->data.addr, DIE_COMPLETE,
+					  &child) &&
+			    __die_map_get(df->data.addr, DIE_UNEXPANDED,
+					  &child))
+				error("unknown child: %" PRIxPTR,
+				      df->data.addr);
+
+			type_expand_child(child, type, recursive);
+			break;
+		case FRAGMENT_LINEBREAK:
+			/*
+			 * Keep whitespace in the symtypes format, but avoid
+			 * repeated spaces.
+			 */
+			if (list_is_last(&df->list, &cache->fragments) ||
+			    list_next_entry(df, list)->type !=
+				    FRAGMENT_LINEBREAK)
+				type_expansion_append(type, " ", NULL);
+			break;
+		default:
+			error("empty die_fragment in %p", cache);
+		}
+	}
+}
+
+static void type_expand(struct die *cache, struct type_expansion *type,
+			bool recursive)
+{
+	type_expansion_init(type);
+	__type_expand(cache, type, recursive);
+	cache_free(&expansion_cache);
+}
+
+static void expand_type(struct die *cache, void *arg)
+{
+	struct type_expansion type;
+	char *name;
+
+	if (cache->mapped)
+		return;
+
+	cache->mapped = true;
+
+	/*
+	 * Skip unexpanded die_map entries if there's a complete
+	 * expansion available for this DIE.
+	 */
+	if (cache->state == DIE_UNEXPANDED &&
+	    !__die_map_get(cache->addr, DIE_COMPLETE, &cache)) {
+		if (cache->mapped)
+			return;
+
+		cache->mapped = true;
+	}
+
+	name = get_type_name(cache);
+	if (!name)
+		return;
+
+	debug("%s", name);
+	type_expand(cache, &type, true);
+	type_map_add(name, &type);
+
+	type_expansion_free(&type);
+	free(name);
+}
+
+static void expand_symbol(struct symbol *sym, void *arg)
+{
+	struct type_expansion type;
+	struct version version;
+	struct die *cache;
+
+	/*
+	 * No need to expand again unless we want a symtypes file entry
+	 * for the symbol. Note that this means `sym` has the same address
+	 * as another symbol that was already processed.
+	 */
+	if (!symtypes && sym->state == SYMBOL_PROCESSED)
+		return;
+
+	if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache))
+		return; /* We'll warn about missing CRCs later. */
+
+	type_expand(cache, &type, false);
+
+	/* If the symbol already has a version, don't calculate it again. */
+	if (sym->state != SYMBOL_PROCESSED) {
+		calculate_version(&version, &type.expanded);
+		symbol_set_crc(sym, version.crc);
+		debug("%s = %lx", sym->name, version.crc);
+
+		if (dump_versions) {
+			checkp(fputs(sym->name, stderr));
+			checkp(fputs(" ", stderr));
+			type_list_write(&version.type.expanded, stderr);
+			checkp(fputs("\n", stderr));
+		}
+
+		version_free(&version);
+	}
+
+	/* These aren't needed in type_map unless we want a symtypes file. */
+	if (symtypes)
+		type_map_add(sym->name, &type);
+
+	type_expansion_free(&type);
+}
+
+void generate_symtypes_and_versions(FILE *file)
+{
+	cache_init(&expansion_cache);
+
+	/*
+	 * die_map processing:
+	 *
+	 *   1. die_map contains all types referenced in exported symbol
+	 *      signatures, but can contain duplicates just like the original
+	 *      DWARF, and some references may not be fully expanded depending
+	 *      on how far we processed the DIE tree for that specific symbol.
+	 *
+	 *      For each die_map entry, find the longest available expansion,
+	 *      and add it to type_map.
+	 */
+	die_map_for_each(expand_type, NULL);
+
+	/*
+	 *   2. For each exported symbol, expand the die_map type, and use
+	 *      type_map expansions to calculate a symbol version from the
+	 *      fully expanded type string.
+	 */
+	symbol_for_each(expand_symbol, NULL);
+
+	/*
+	 *   3. If a symtypes file is requested, write type_map contents to
+	 *      the file.
+	 */
+	type_map_write(file);
+	type_map_free();
+}
diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 0d00ac3723b5..4fd6b6ab3e32 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -165,6 +165,18 @@ impl KernelConfig {
         let option = "CONFIG_".to_owned() + option;
         self.0.contains_key(&option)
     }
+
+    /// Is the rustc version at least `major.minor.patch`?
+    fn rustc_version_atleast(&self, major: u32, minor: u32, patch: u32) -> bool {
+        let check_version = 100000 * major + 100 * minor + patch;
+        let actual_version = self
+            .0
+            .get("CONFIG_RUSTC_VERSION")
+            .unwrap()
+            .parse::<u32>()
+            .unwrap();
+        check_version <= actual_version
+    }
 }
 
 fn main() {
@@ -182,6 +194,9 @@ fn main() {
         }
     } else if cfg.has("X86_64") {
         ts.push("arch", "x86_64");
+        if cfg.rustc_version_atleast(1, 86, 0) {
+            ts.push("rustc-abi", "x86-softfloat");
+        }
         ts.push(
             "data-layout",
             "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128",
@@ -215,6 +230,9 @@ fn main() {
             panic!("32-bit x86 only works under UML");
         }
         ts.push("arch", "x86");
+        if cfg.rustc_version_atleast(1, 86, 0) {
+            ts.push("rustc-abi", "x86-softfloat");
+        }
         ts.push(
             "data-layout",
             "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128",
diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile
index 312edccda736..4350311fb7b3 100644
--- a/scripts/genksyms/Makefile
+++ b/scripts/genksyms/Makefile
@@ -4,24 +4,6 @@ hostprogs-always-y	+= genksyms
 
 genksyms-objs	:= genksyms.o parse.tab.o lex.lex.o
 
-# FIXME: fix the ambiguous grammar in parse.y and delete this hack
-#
-# Suppress shift/reduce, reduce/reduce conflicts warnings
-# unless W=1 is specified.
-#
-# Just in case, run "$(YACC) --version" without suppressing stderr
-# so that 'bison: not found' will be displayed if it is missing.
-ifeq ($(findstring 1,$(KBUILD_EXTRA_WARN)),)
-
-quiet_cmd_bison_no_warn = $(quiet_cmd_bison)
-      cmd_bison_no_warn = $(YACC) --version >/dev/null; \
-			  $(cmd_bison) 2>/dev/null
-
-$(obj)/pars%.tab.c $(obj)/pars%.tab.h: $(src)/pars%.y FORCE
-	$(call if_changed,bison_no_warn)
-
-endif
-
 # -I needed for generated C source to include headers in source tree
 HOSTCFLAGS_parse.tab.o := -I $(src)
 HOSTCFLAGS_lex.lex.o := -I $(src)
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index 07f9b8cfb233..8b0d7ac73dbb 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -12,18 +12,19 @@
 
 #include <stdio.h>
 #include <string.h>
+#include <stdint.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <assert.h>
 #include <stdarg.h>
 #include <getopt.h>
 
+#include <hashtable.h>
+
 #include "genksyms.h"
 /*----------------------------------------------------------------------*/
 
-#define HASH_BUCKETS  4096
-
-static struct symbol *symtab[HASH_BUCKETS];
+static HASHTABLE_DEFINE(symbol_hashtable, 1U << 12);
 static FILE *debugfile;
 
 int cur_line = 1;
@@ -60,7 +61,7 @@ static void print_type_name(enum symbol_type type, const char *name);
 
 /*----------------------------------------------------------------------*/
 
-static const unsigned int crctab32[] = {
+static const uint32_t crctab32[] = {
 	0x00000000U, 0x77073096U, 0xee0e612cU, 0x990951baU, 0x076dc419U,
 	0x706af48fU, 0xe963a535U, 0x9e6495a3U, 0x0edb8832U, 0x79dcb8a4U,
 	0xe0d5e91eU, 0x97d2d988U, 0x09b64c2bU, 0x7eb17cbdU, 0xe7b82d07U,
@@ -115,19 +116,19 @@ static const unsigned int crctab32[] = {
 	0x2d02ef8dU
 };
 
-static unsigned long partial_crc32_one(unsigned char c, unsigned long crc)
+static uint32_t partial_crc32_one(uint8_t c, uint32_t crc)
 {
 	return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8);
 }
 
-static unsigned long partial_crc32(const char *s, unsigned long crc)
+static uint32_t partial_crc32(const char *s, uint32_t crc)
 {
 	while (*s)
 		crc = partial_crc32_one(*s++, crc);
 	return crc;
 }
 
-static unsigned long crc32(const char *s)
+static uint32_t crc32(const char *s)
 {
 	return partial_crc32(s, 0xffffffff) ^ 0xffffffff;
 }
@@ -151,14 +152,14 @@ static enum symbol_type map_to_ns(enum symbol_type t)
 
 struct symbol *find_symbol(const char *name, enum symbol_type ns, int exact)
 {
-	unsigned long h = crc32(name) % HASH_BUCKETS;
 	struct symbol *sym;
 
-	for (sym = symtab[h]; sym; sym = sym->hash_next)
+	hash_for_each_possible(symbol_hashtable, sym, hnode, crc32(name)) {
 		if (map_to_ns(sym->type) == map_to_ns(ns) &&
 		    strcmp(name, sym->name) == 0 &&
 		    sym->is_declared)
 			break;
+	}
 
 	if (exact && sym && sym->type != ns)
 		return NULL;
@@ -224,64 +225,56 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type,
 			return NULL;
 	}
 
-	h = crc32(name) % HASH_BUCKETS;
-	for (sym = symtab[h]; sym; sym = sym->hash_next) {
-		if (map_to_ns(sym->type) == map_to_ns(type) &&
-		    strcmp(name, sym->name) == 0) {
-			if (is_reference)
-				/* fall through */ ;
-			else if (sym->type == type &&
-				 equal_list(sym->defn, defn)) {
-				if (!sym->is_declared && sym->is_override) {
-					print_location();
-					print_type_name(type, name);
-					fprintf(stderr, " modversion is "
-						"unchanged\n");
-				}
-				sym->is_declared = 1;
-				return sym;
-			} else if (!sym->is_declared) {
-				if (sym->is_override && flag_preserve) {
-					print_location();
-					fprintf(stderr, "ignoring ");
-					print_type_name(type, name);
-					fprintf(stderr, " modversion change\n");
-					sym->is_declared = 1;
-					return sym;
-				} else {
-					status = is_unknown_symbol(sym) ?
-						STATUS_DEFINED : STATUS_MODIFIED;
-				}
-			} else {
-				error_with_pos("redefinition of %s", name);
-				return sym;
+	h = crc32(name);
+	hash_for_each_possible(symbol_hashtable, sym, hnode, h) {
+		if (map_to_ns(sym->type) != map_to_ns(type) ||
+		    strcmp(name, sym->name))
+			continue;
+
+		if (is_reference) {
+			break;
+		} else if (sym->type == type && equal_list(sym->defn, defn)) {
+			if (!sym->is_declared && sym->is_override) {
+				print_location();
+				print_type_name(type, name);
+				fprintf(stderr, " modversion is unchanged\n");
 			}
+			sym->is_declared = 1;
+		} else if (sym->is_declared) {
+			error_with_pos("redefinition of %s", name);
+		} else if (sym->is_override && flag_preserve) {
+			print_location();
+			fprintf(stderr, "ignoring ");
+			print_type_name(type, name);
+			fprintf(stderr, " modversion change\n");
+			sym->is_declared = 1;
+		} else {
+			status = is_unknown_symbol(sym) ?
+					STATUS_DEFINED : STATUS_MODIFIED;
 			break;
 		}
+		free_list(defn, NULL);
+		return sym;
 	}
 
 	if (sym) {
-		struct symbol **psym;
+		hash_del(&sym->hnode);
 
-		for (psym = &symtab[h]; *psym; psym = &(*psym)->hash_next) {
-			if (*psym == sym) {
-				*psym = sym->hash_next;
-				break;
-			}
-		}
+		free_list(sym->defn, NULL);
+		free(sym->name);
+		free(sym);
 		--nsyms;
 	}
 
 	sym = xmalloc(sizeof(*sym));
-	sym->name = name;
+	sym->name = xstrdup(name);
 	sym->type = type;
 	sym->defn = defn;
 	sym->expansion_trail = NULL;
 	sym->visited = NULL;
 	sym->is_extern = is_extern;
 
-	sym->hash_next = symtab[h];
-	symtab[h] = sym;
+	hash_add(symbol_hashtable, &sym->hnode, h);
 
 	sym->is_declared = !is_reference;
 	sym->status = status;
@@ -480,7 +473,7 @@ static void read_reference(FILE *f)
 			defn = def;
 			def = read_node(f);
 		}
-		subsym = add_reference_symbol(xstrdup(sym->string), sym->tag,
+		subsym = add_reference_symbol(sym->string, sym->tag,
 					      defn, is_extern);
 		subsym->is_override = is_override;
 		free_node(sym);
@@ -525,7 +518,7 @@ static void print_list(FILE * f, struct string_list *list)
 	}
 }
 
-static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc)
+static uint32_t expand_and_crc_sym(struct symbol *sym, uint32_t crc)
 {
 	struct string_list *list = sym->defn;
 	struct string_list **e, **b;
@@ -632,7 +625,7 @@ static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc)
 void export_symbol(const char *name)
 {
 	struct symbol *sym;
-	unsigned long crc;
+	uint32_t crc;
 	int has_changed = 0;
 
 	sym = find_symbol(name, SYM_NORMAL, 0);
@@ -680,7 +673,7 @@ void export_symbol(const char *name)
 	if (flag_dump_defs)
 		fputs(">\n", debugfile);
 
-	printf("#SYMVER %s 0x%08lx\n", name, crc);
+	printf("#SYMVER %s 0x%08lx\n", name, (unsigned long)crc);
 }
 
 /*----------------------------------------------------------------------*/
@@ -832,9 +825,9 @@ int main(int argc, char **argv)
 	}
 
 	if (flag_debug) {
-		fprintf(debugfile, "Hash table occupancy %d/%d = %g\n",
-			nsyms, HASH_BUCKETS,
-			(double)nsyms / (double)HASH_BUCKETS);
+		fprintf(debugfile, "Hash table occupancy %d/%zd = %g\n",
+			nsyms, HASH_SIZE(symbol_hashtable),
+			(double)nsyms / HASH_SIZE(symbol_hashtable));
 	}
 
 	if (dumpfile)
diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h
index 21ed2ec2d98c..0c355075f0e6 100644
--- a/scripts/genksyms/genksyms.h
+++ b/scripts/genksyms/genksyms.h
@@ -12,8 +12,11 @@
 #ifndef MODUTILS_GENKSYMS_H
 #define MODUTILS_GENKSYMS_H 1
 
+#include <stdbool.h>
 #include <stdio.h>
 
+#include <list_types.h>
+
 enum symbol_type {
 	SYM_NORMAL, SYM_TYPEDEF, SYM_ENUM, SYM_STRUCT, SYM_UNION,
 	SYM_ENUM_CONST
@@ -31,8 +34,8 @@ struct string_list {
 };
 
 struct symbol {
-	struct symbol *hash_next;
-	const char *name;
+	struct hlist_node hnode;
+	char *name;
 	enum symbol_type type;
 	struct string_list *defn;
 	struct symbol *expansion_trail;
@@ -64,6 +67,8 @@ struct string_list *copy_list_range(struct string_list *start,
 int yylex(void);
 int yyparse(void);
 
+extern bool dont_want_type_specifier;
+
 void error_with_pos(const char *, ...) __attribute__ ((format(printf, 1, 2)));
 
 /*----------------------------------------------------------------------*/
diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l
index a4d7495eaf75..22aeb57649d9 100644
--- a/scripts/genksyms/lex.l
+++ b/scripts/genksyms/lex.l
@@ -12,6 +12,7 @@
 %{
 
 #include <limits.h>
+#include <stdbool.h>
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
@@ -50,6 +51,7 @@ MC_TOKEN		([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>)
 
 %%
 
+u?int(8|16|32|64)x(1|2|4|8|16)_t	return BUILTIN_INT_KEYW;
 
  /* Keep track of our location in the original source files.  */
 ^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n	return FILENAME;
@@ -113,6 +115,12 @@ MC_TOKEN		([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>)
 /* The second stage lexer.  Here we incorporate knowledge of the state
    of the parser to tailor the tokens that are returned.  */
 
+/*
+ * The lexer cannot distinguish whether a typedef'ed string is a TYPE or an
+ * IDENT. We need a hint from the parser to handle this accurately.
+ */
+bool dont_want_type_specifier;
+
 int
 yylex(void)
 {
@@ -207,7 +215,7 @@ repeat:
 		    goto repeat;
 		  }
 	      }
-	    if (!suppress_type_lookup)
+	    if (!suppress_type_lookup && !dont_want_type_specifier)
 	      {
 		if (find_symbol(yytext, SYM_TYPEDEF, 1))
 		  token = TYPE;
@@ -431,7 +439,12 @@ fini:
 
   if (suppress_type_lookup > 0)
     --suppress_type_lookup;
-  if (dont_want_brace_phrase > 0)
+
+  /*
+   *  __attribute__() can be placed immediately after the 'struct' keyword.
+   *  e.g.) struct __attribute__((__packed__)) foo { ... };
+   */
+  if (token != ATTRIBUTE_PHRASE && dont_want_brace_phrase > 0)
     --dont_want_brace_phrase;
 
   yylval = &next_node->next;
diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y
index 8e9b5e69e8f0..ee600a804fa1 100644
--- a/scripts/genksyms/parse.y
+++ b/scripts/genksyms/parse.y
@@ -12,6 +12,7 @@
 %{
 
 #include <assert.h>
+#include <stdbool.h>
 #include <stdlib.h>
 #include <string.h>
 #include "genksyms.h"
@@ -148,32 +149,45 @@ simple_declaration:
 		    current_name = NULL;
 		  }
 		  $$ = $3;
+		  dont_want_type_specifier = false;
 		}
 	;
 
 init_declarator_list_opt:
-	/* empty */				{ $$ = NULL; }
-	| init_declarator_list
+	/* empty */			{ $$ = NULL; }
+	| init_declarator_list		{ free_list(decl_spec, NULL); $$ = $1; }
 	;
 
 init_declarator_list:
 	init_declarator
 		{ struct string_list *decl = *$1;
 		  *$1 = NULL;
+
+		  /* avoid sharing among multiple init_declarators */
+		  if (decl_spec)
+		    decl_spec = copy_list_range(decl_spec, NULL);
+
 		  add_symbol(current_name,
 			     is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern);
 		  current_name = NULL;
 		  $$ = $1;
+		  dont_want_type_specifier = true;
 		}
-	| init_declarator_list ',' init_declarator
-		{ struct string_list *decl = *$3;
-		  *$3 = NULL;
+	| init_declarator_list ',' attribute_opt init_declarator
+		{ struct string_list *decl = *$4;
+		  *$4 = NULL;
 		  free_list(*$2, NULL);
 		  *$2 = decl_spec;
+
+		  /* avoid sharing among multiple init_declarators */
+		  if (decl_spec)
+		    decl_spec = copy_list_range(decl_spec, NULL);
+
 		  add_symbol(current_name,
 			     is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern);
 		  current_name = NULL;
-		  $$ = $3;
+		  $$ = $4;
+		  dont_want_type_specifier = true;
 		}
 	;
 
@@ -189,8 +203,9 @@ decl_specifier_seq_opt:
 	;
 
 decl_specifier_seq:
-	decl_specifier				{ decl_spec = *$1; }
+	attribute_opt decl_specifier		{ decl_spec = *$2; }
 	| decl_specifier_seq decl_specifier	{ decl_spec = *$2; }
+	| decl_specifier_seq ATTRIBUTE_PHRASE	{ decl_spec = *$2; }
 	;
 
 decl_specifier:
@@ -200,7 +215,8 @@ decl_specifier:
 		  remove_node($1);
 		  $$ = $1;
 		}
-	| type_specifier
+	| type_specifier	{ dont_want_type_specifier = true; $$ = $1; }
+	| type_qualifier
 	;
 
 storage_class_specifier:
@@ -213,24 +229,23 @@ storage_class_specifier:
 
 type_specifier:
 	simple_type_specifier
-	| cvar_qualifier
 	| TYPEOF_KEYW '(' parameter_declaration ')'
 	| TYPEOF_PHRASE
 
 	/* References to s/u/e's defined elsewhere.  Rearrange things
 	   so that it is easier to expand the definition fully later.  */
-	| STRUCT_KEYW IDENT
-		{ remove_node($1); (*$2)->tag = SYM_STRUCT; $$ = $2; }
-	| UNION_KEYW IDENT
-		{ remove_node($1); (*$2)->tag = SYM_UNION; $$ = $2; }
+	| STRUCT_KEYW attribute_opt IDENT
+		{ remove_node($1); (*$3)->tag = SYM_STRUCT; $$ = $3; }
+	| UNION_KEYW attribute_opt IDENT
+		{ remove_node($1); (*$3)->tag = SYM_UNION; $$ = $3; }
 	| ENUM_KEYW IDENT
 		{ remove_node($1); (*$2)->tag = SYM_ENUM; $$ = $2; }
 
 	/* Full definitions of an s/u/e.  Record it.  */
-	| STRUCT_KEYW IDENT class_body
-		{ record_compound($1, $2, $3, SYM_STRUCT); $$ = $3; }
-	| UNION_KEYW IDENT class_body
-		{ record_compound($1, $2, $3, SYM_UNION); $$ = $3; }
+	| STRUCT_KEYW attribute_opt IDENT class_body
+		{ record_compound($1, $3, $4, SYM_STRUCT); $$ = $4; }
+	| UNION_KEYW attribute_opt IDENT class_body
+		{ record_compound($1, $3, $4, SYM_UNION); $$ = $4; }
 	| ENUM_KEYW IDENT enum_body
 		{ record_compound($1, $2, $3, SYM_ENUM); $$ = $3; }
 	/*
@@ -239,8 +254,8 @@ type_specifier:
 	| ENUM_KEYW enum_body
 		{ add_symbol(NULL, SYM_ENUM, NULL, 0); $$ = $2; }
 	/* Anonymous s/u definitions.  Nothing needs doing.  */
-	| STRUCT_KEYW class_body			{ $$ = $2; }
-	| UNION_KEYW class_body				{ $$ = $2; }
+	| STRUCT_KEYW attribute_opt class_body		{ $$ = $3; }
+	| UNION_KEYW attribute_opt class_body		{ $$ = $3; }
 	;
 
 simple_type_specifier:
@@ -260,22 +275,24 @@ simple_type_specifier:
 	;
 
 ptr_operator:
-	'*' cvar_qualifier_seq_opt
+	'*' type_qualifier_seq_opt
 		{ $$ = $2 ? $2 : $1; }
 	;
 
-cvar_qualifier_seq_opt:
+type_qualifier_seq_opt:
 	/* empty */					{ $$ = NULL; }
-	| cvar_qualifier_seq
+	| type_qualifier_seq
 	;
 
-cvar_qualifier_seq:
-	cvar_qualifier
-	| cvar_qualifier_seq cvar_qualifier		{ $$ = $2; }
+type_qualifier_seq:
+	type_qualifier
+	| ATTRIBUTE_PHRASE
+	| type_qualifier_seq type_qualifier		{ $$ = $2; }
+	| type_qualifier_seq ATTRIBUTE_PHRASE		{ $$ = $2; }
 	;
 
-cvar_qualifier:
-	CONST_KEYW | VOLATILE_KEYW | ATTRIBUTE_PHRASE
+type_qualifier:
+	CONST_KEYW | VOLATILE_KEYW
 	| RESTRICT_KEYW
 		{ /* restrict has no effect in prototypes so ignore it */
 		  remove_node($1);
@@ -297,15 +314,7 @@ direct_declarator:
 		    current_name = (*$1)->string;
 		    $$ = $1;
 		  }
-		}
-	| TYPE
-		{ if (current_name != NULL) {
-		    error_with_pos("unexpected second declaration name");
-		    YYERROR;
-		  } else {
-		    current_name = (*$1)->string;
-		    $$ = $1;
-		  }
+		  dont_want_type_specifier = false;
 		}
 	| direct_declarator '(' parameter_declaration_clause ')'
 		{ $$ = $4; }
@@ -325,16 +334,19 @@ nested_declarator:
 	;
 
 direct_nested_declarator:
-	IDENT
-	| TYPE
-	| direct_nested_declarator '(' parameter_declaration_clause ')'
+	direct_nested_declarator1
+	| direct_nested_declarator1 '(' parameter_declaration_clause ')'
 		{ $$ = $4; }
-	| direct_nested_declarator '(' error ')'
+	;
+
+direct_nested_declarator1:
+	IDENT	{ $$ = $1; dont_want_type_specifier = false; }
+	| direct_nested_declarator1 '(' error ')'
 		{ $$ = $4; }
-	| direct_nested_declarator BRACKET_PHRASE
+	| direct_nested_declarator1 BRACKET_PHRASE
 		{ $$ = $2; }
-	| '(' nested_declarator ')'
-		{ $$ = $3; }
+	| '(' attribute_opt nested_declarator ')'
+		{ $$ = $4; }
 	| '(' error ')'
 		{ $$ = $3; }
 	;
@@ -352,45 +364,57 @@ parameter_declaration_list_opt:
 
 parameter_declaration_list:
 	parameter_declaration
+		{ $$ = $1; dont_want_type_specifier = false; }
 	| parameter_declaration_list ',' parameter_declaration
-		{ $$ = $3; }
+		{ $$ = $3; dont_want_type_specifier = false; }
 	;
 
 parameter_declaration:
-	decl_specifier_seq m_abstract_declarator
+	decl_specifier_seq abstract_declarator_opt
 		{ $$ = $2 ? $2 : $1; }
 	;
 
-m_abstract_declarator:
-	ptr_operator m_abstract_declarator
+abstract_declarator_opt:
+	/* empty */				{ $$ = NULL; }
+	| abstract_declarator
+	;
+
+abstract_declarator:
+	ptr_operator
+	| ptr_operator abstract_declarator
 		{ $$ = $2 ? $2 : $1; }
-	| direct_m_abstract_declarator
+	| direct_abstract_declarator attribute_opt
+		{ $$ = $2; dont_want_type_specifier = false; }
 	;
 
-direct_m_abstract_declarator:
-	/* empty */					{ $$ = NULL; }
-	| IDENT
+direct_abstract_declarator:
+	direct_abstract_declarator1
+	| direct_abstract_declarator1 open_paren parameter_declaration_clause ')'
+		{ $$ = $4; }
+	| open_paren parameter_declaration_clause ')'
+		{ $$ = $3; }
+	;
+
+direct_abstract_declarator1:
+	  IDENT
 		{ /* For version 2 checksums, we don't want to remember
 		     private parameter names.  */
 		  remove_node($1);
 		  $$ = $1;
 		}
-	/* This wasn't really a typedef name but an identifier that
-	   shadows one.  */
-	| TYPE
-		{ remove_node($1);
-		  $$ = $1;
-		}
-	| direct_m_abstract_declarator '(' parameter_declaration_clause ')'
-		{ $$ = $4; }
-	| direct_m_abstract_declarator '(' error ')'
+	| direct_abstract_declarator1 open_paren error ')'
 		{ $$ = $4; }
-	| direct_m_abstract_declarator BRACKET_PHRASE
+	| direct_abstract_declarator1 BRACKET_PHRASE
 		{ $$ = $2; }
-	| '(' m_abstract_declarator ')'
-		{ $$ = $3; }
-	| '(' error ')'
+	| open_paren attribute_opt abstract_declarator ')'
+		{ $$ = $4; }
+	| open_paren error ')'
 		{ $$ = $3; }
+	| BRACKET_PHRASE
+	;
+
+open_paren:
+	'('	{ $$ = $1; dont_want_type_specifier = false; }
 	;
 
 function_definition:
@@ -430,9 +454,9 @@ member_specification:
 
 member_declaration:
 	decl_specifier_seq_opt member_declarator_list_opt ';'
-		{ $$ = $3; }
+		{ $$ = $3; dont_want_type_specifier = false; }
 	| error ';'
-		{ $$ = $2; }
+		{ $$ = $2; dont_want_type_specifier = false; }
 	;
 
 member_declarator_list_opt:
@@ -442,7 +466,9 @@ member_declarator_list_opt:
 
 member_declarator_list:
 	member_declarator
-	| member_declarator_list ',' member_declarator	{ $$ = $3; }
+		{ $$ = $1; dont_want_type_specifier = true; }
+	| member_declarator_list ',' member_declarator
+		{ $$ = $3; dont_want_type_specifier = true; }
 	;
 
 member_declarator:
@@ -457,7 +483,7 @@ member_bitfield_declarator:
 
 attribute_opt:
 	/* empty */					{ $$ = NULL; }
-	| attribute_opt ATTRIBUTE_PHRASE
+	| attribute_opt ATTRIBUTE_PHRASE		{ $$ = $2; }
 	;
 
 enum_body:
@@ -472,12 +498,12 @@ enumerator_list:
 enumerator:
 	IDENT
 		{
-			const char *name = strdup((*$1)->string);
+			const char *name = (*$1)->string;
 			add_symbol(name, SYM_ENUM_CONST, NULL, 0);
 		}
 	| IDENT '=' EXPRESSION_PHRASE
 		{
-			const char *name = strdup((*$1)->string);
+			const char *name = (*$1)->string;
 			struct string_list *expr = copy_list_range(*$3, *$2);
 			add_symbol(name, SYM_ENUM_CONST, expr, 0);
 		}
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index a0a0be38cbdc..fb50bd4f4103 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -105,9 +105,11 @@ configfiles = $(wildcard $(srctree)/kernel/configs/$(1) $(srctree)/arch/$(SRCARC
 all-config-fragments = $(call configfiles,*.config)
 config-fragments = $(call configfiles,$@)
 
+cmd_merge_fragments = $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments)
+
 %.config: $(obj)/conf
 	$(if $(config-fragments),, $(error $@ fragment does not exists on this architecture))
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments)
+	$(call cmd,merge_fragments)
 	$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
 
 PHONY += tinyconfig
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 4286d5e7f95d..3b55e7a4131d 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -360,10 +360,12 @@ int conf_read_simple(const char *name, int def)
 
 			*p = '\0';
 
-			in = zconf_fopen(env);
+			name = env;
+
+			in = zconf_fopen(name);
 			if (in) {
 				conf_message("using defaults found in %s",
-					     env);
+					     name);
 				goto load;
 			}
 
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index 6c92ef1e16ef..eaa465b0ccf9 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -1464,8 +1464,8 @@ void ConfigMainWindow::loadConfig(void)
 {
 	QString str;
 
-	str = QFileDialog::getOpenFileName(this, "", configname);
-	if (str.isNull())
+	str = QFileDialog::getOpenFileName(this, QString(), configname);
+	if (str.isEmpty())
 		return;
 
 	if (conf_read(str.toLocal8Bit().constData()))
@@ -1491,8 +1491,8 @@ void ConfigMainWindow::saveConfigAs(void)
 {
 	QString str;
 
-	str = QFileDialog::getSaveFileName(this, "", configname);
-	if (str.isNull())
+	str = QFileDialog::getSaveFileName(this, QString(), configname);
+	if (str.isEmpty())
 		return;
 
 	if (conf_write(str.toLocal8Bit().constData())) {
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 89b84bf8e21f..7beb59dec5a0 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -388,6 +388,7 @@ static void sym_warn_unmet_dep(const struct symbol *sym)
 			       "  Selected by [m]:\n");
 
 	fputs(str_get(&gs), stderr);
+	str_free(&gs);
 	sym_warnings++;
 }
 
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index 9c7b404defbd..d3d00e85edf7 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -237,7 +237,6 @@ int main(void)
 
 	DEVID(typec_device_id);
 	DEVID_FIELD(typec_device_id, svid);
-	DEVID_FIELD(typec_device_id, mode);
 
 	DEVID(tee_client_device_id);
 	DEVID_FIELD(tee_client_device_id, uuid);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 19ec72a69e90..00586119a25b 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1219,17 +1219,12 @@ static void do_tbsvc_entry(struct module *mod, void *symval)
 	module_alias_printf(mod, true, "tbsvc:%s", alias);
 }
 
-/* Looks like: typec:idNmN */
+/* Looks like: typec:idN */
 static void do_typec_entry(struct module *mod, void *symval)
 {
-	char alias[256] = {};
-
 	DEF_FIELD(symval, typec_device_id, svid);
-	DEF_FIELD(symval, typec_device_id, mode);
-
-	ADD(alias, "m", mode != TYPEC_ANY_MODE, mode);
 
-	module_alias_printf(mod, false, "typec:id%04X%s", svid, alias);
+	module_alias_printf(mod, false, "typec:id%04X", svid);
 }
 
 /* Looks like: tee:uuid */
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 7ea59dc4926b..36b28987a2f0 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -33,6 +33,10 @@ static bool module_enabled;
 static bool modversions;
 /* Is CONFIG_MODULE_SRCVERSION_ALL set? */
 static bool all_versions;
+/* Is CONFIG_BASIC_MODVERSIONS set? */
+static bool basic_modversions;
+/* Is CONFIG_EXTENDED_MODVERSIONS set? */
+static bool extended_modversions;
 /* If we are modposting external module set to 1 */
 static bool external_module;
 /* Only warn about unresolved symbols */
@@ -503,6 +507,9 @@ static int parse_elf(struct elf_info *info, const char *filename)
 			info->modinfo_len = sechdrs[i].sh_size;
 		} else if (!strcmp(secname, ".export_symbol")) {
 			info->export_symbol_secndx = i;
+		} else if (!strcmp(secname, ".no_trim_symbol")) {
+			info->no_trim_symbol = (void *)hdr + sechdrs[i].sh_offset;
+			info->no_trim_symbol_len = sechdrs[i].sh_size;
 		}
 
 		if (sechdrs[i].sh_type == SHT_SYMTAB) {
@@ -1562,6 +1569,14 @@ static void read_symbols(const char *modname)
 	/* strip trailing .o */
 	mod = new_module(modname, strlen(modname) - strlen(".o"));
 
+	/* save .no_trim_symbol section for later use */
+	if (info.no_trim_symbol_len) {
+		mod->no_trim_symbol = xmalloc(info.no_trim_symbol_len);
+		memcpy(mod->no_trim_symbol, info.no_trim_symbol,
+		       info.no_trim_symbol_len);
+		mod->no_trim_symbol_len = info.no_trim_symbol_len;
+	}
+
 	if (!mod->is_vmlinux) {
 		license = get_modinfo(&info, "license");
 		if (!license)
@@ -1724,6 +1739,28 @@ static void handle_white_list_exports(const char *white_list)
 	free(buf);
 }
 
+/*
+ * Keep symbols recorded in the .no_trim_symbol section. This is necessary to
+ * prevent CONFIG_TRIM_UNUSED_KSYMS from dropping EXPORT_SYMBOL because
+ * symbol_get() relies on the symbol being present in the ksymtab for lookups.
+ */
+static void keep_no_trim_symbols(struct module *mod)
+{
+	unsigned long size = mod->no_trim_symbol_len;
+
+	for (char *s = mod->no_trim_symbol; s; s = next_string(s , &size)) {
+		struct symbol *sym;
+
+		/*
+		 * If find_symbol() returns NULL, this symbol is not provided
+		 * by any module, and symbol_get() will fail.
+		 */
+		sym = find_symbol(s);
+		if (sym)
+			sym->used = true;
+	}
+}
+
 static void check_modname_len(struct module *mod)
 {
 	const char *mod_name;
@@ -1806,13 +1843,56 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod)
 }
 
 /**
+ * Record CRCs for unresolved symbols, supporting long names
+ */
+static void add_extended_versions(struct buffer *b, struct module *mod)
+{
+	struct symbol *s;
+
+	if (!extended_modversions)
+		return;
+
+	buf_printf(b, "\n");
+	buf_printf(b, "static const u32 ____version_ext_crcs[]\n");
+	buf_printf(b, "__used __section(\"__version_ext_crcs\") = {\n");
+	list_for_each_entry(s, &mod->unresolved_symbols, list) {
+		if (!s->module)
+			continue;
+		if (!s->crc_valid) {
+			warn("\"%s\" [%s.ko] has no CRC!\n",
+				s->name, mod->name);
+			continue;
+		}
+		buf_printf(b, "\t0x%08x,\n", s->crc);
+	}
+	buf_printf(b, "};\n");
+
+	buf_printf(b, "static const char ____version_ext_names[]\n");
+	buf_printf(b, "__used __section(\"__version_ext_names\") =\n");
+	list_for_each_entry(s, &mod->unresolved_symbols, list) {
+		if (!s->module)
+			continue;
+		if (!s->crc_valid)
+			/*
+			 * We already warned on this when producing the crc
+			 * table.
+			 * We need to skip its name too, as the indexes in
+			 * both tables need to align.
+			 */
+			continue;
+		buf_printf(b, "\t\"%s\\0\"\n", s->name);
+	}
+	buf_printf(b, ";\n");
+}
+
+/**
  * Record CRCs for unresolved symbols
  **/
 static void add_versions(struct buffer *b, struct module *mod)
 {
 	struct symbol *s;
 
-	if (!modversions)
+	if (!basic_modversions)
 		return;
 
 	buf_printf(b, "\n");
@@ -1828,11 +1908,16 @@ static void add_versions(struct buffer *b, struct module *mod)
 			continue;
 		}
 		if (strlen(s->name) >= MODULE_NAME_LEN) {
-			error("too long symbol \"%s\" [%s.ko]\n",
-			      s->name, mod->name);
-			break;
+			if (extended_modversions) {
+				/* this symbol will only be in the extended info */
+				continue;
+			} else {
+				error("too long symbol \"%s\" [%s.ko]\n",
+				      s->name, mod->name);
+				break;
+			}
 		}
-		buf_printf(b, "\t{ %#8x, \"%s\" },\n",
+		buf_printf(b, "\t{ 0x%08x, \"%s\" },\n",
 			   s->crc, s->name);
 	}
 
@@ -1961,6 +2046,7 @@ static void write_mod_c_file(struct module *mod)
 	add_header(&buf, mod);
 	add_exported_symbols(&buf, mod);
 	add_versions(&buf, mod);
+	add_extended_versions(&buf, mod);
 	add_depends(&buf, mod);
 
 	buf_printf(&buf, "\n");
@@ -2126,7 +2212,7 @@ int main(int argc, char **argv)
 	LIST_HEAD(dump_lists);
 	struct dump_list *dl, *dl2;
 
-	while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:")) != -1) {
+	while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:xb")) != -1) {
 		switch (opt) {
 		case 'e':
 			external_module = true;
@@ -2175,6 +2261,12 @@ int main(int argc, char **argv)
 		case 'd':
 			missing_namespace_deps = optarg;
 			break;
+		case 'b':
+			basic_modversions = true;
+			break;
+		case 'x':
+			extended_modversions = true;
+			break;
 		default:
 			exit(1);
 		}
@@ -2195,6 +2287,8 @@ int main(int argc, char **argv)
 		read_symbols_from_files(files_source);
 
 	list_for_each_entry(mod, &modules, list) {
+		keep_no_trim_symbols(mod);
+
 		if (mod->dump_file || mod->is_vmlinux)
 			continue;
 
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index ffd0a52a606e..59366f456b76 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -111,6 +111,8 @@ struct module_alias {
  *
  * @dump_file: path to the .symvers file if loaded from a file
  * @aliases: list head for module_aliases
+ * @no_trim_symbol: .no_trim_symbol section data
+ * @no_trim_symbol_len: length of the .no_trim_symbol section
  */
 struct module {
 	struct list_head list;
@@ -128,6 +130,8 @@ struct module {
 	// Actual imported namespaces
 	struct list_head imported_namespaces;
 	struct list_head aliases;
+	char *no_trim_symbol;
+	unsigned int no_trim_symbol_len;
 	char name[];
 };
 
@@ -141,6 +145,8 @@ struct elf_info {
 	char         *strtab;
 	char	     *modinfo;
 	unsigned int modinfo_len;
+	char         *no_trim_symbol;
+	unsigned int no_trim_symbol_len;
 
 	/* support for 32bit section numbers */
 
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index c2f80f9141d4..450f1088d5fd 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -16,6 +16,7 @@ SECTIONS {
 		*(.discard)
 		*(.discard.*)
 		*(.export_symbol)
+		*(.no_trim_symbol)
 	}
 
 	__ksymtab		0 : ALIGN(8) { *(SORT(___ksymtab+*)) }
diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD
index dca706617adc..0cf3a55b05e1 100644
--- a/scripts/package/PKGBUILD
+++ b/scripts/package/PKGBUILD
@@ -22,7 +22,6 @@ license=(GPL-2.0-only)
 makedepends=(
 	bc
 	bison
-	cpio
 	flex
 	gettext
 	kmod
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index ad7aba0f268e..3627ca227e5a 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -5,10 +5,12 @@
 #
 # Simple script to generate a deb package for a Linux kernel. All the
 # complexity of what to do with a kernel after it is installed or removed
-# is left to other scripts and packages: they can install scripts in the
-# /etc/kernel/{pre,post}{inst,rm}.d/ directories (or an alternative location
-# specified in KDEB_HOOKDIR) that will be called on package install and
-# removal.
+# is left to other scripts and packages. Scripts can be placed into the
+# preinst, postinst, prerm and postrm directories in /etc/kernel or
+# /usr/share/kernel. A different list of search directories can be given
+# via KDEB_HOOKDIR. Scripts in directories earlier in the list will
+# override scripts of the same name in later directories.  The script will
+# be called on package installation and removal.
 
 set -eu
 
@@ -74,10 +76,8 @@ install_maint_scripts () {
 	# kernel packages, as well as kernel packages built using make-kpkg.
 	# make-kpkg sets $INITRD to indicate whether an initramfs is wanted, and
 	# so do we; recent versions of dracut and initramfs-tools will obey this.
-	debhookdir=${KDEB_HOOKDIR:-/etc/kernel}
+	debhookdir=${KDEB_HOOKDIR:-/etc/kernel /usr/share/kernel}
 	for script in postinst postrm preinst prerm; do
-		mkdir -p "${pdir}${debhookdir}/${script}.d"
-
 		mkdir -p "${pdir}/DEBIAN"
 		cat <<-EOF > "${pdir}/DEBIAN/${script}"
 		#!/bin/sh
@@ -90,7 +90,15 @@ install_maint_scripts () {
 		# Tell initramfs builder whether it's wanted
 		export INITRD=$(if_enabled_echo CONFIG_BLK_DEV_INITRD Yes No)
 
-		test -d ${debhookdir}/${script}.d && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" ${debhookdir}/${script}.d
+		# run-parts will error out if one of its directory arguments does not
+		# exist, so filter the list of hook directories accordingly.
+		hookdirs=
+		for dir in ${debhookdir}; do
+			test -d "\$dir/${script}.d" || continue
+			hookdirs="\$hookdirs \$dir/${script}.d"
+		done
+		hookdirs="\${hookdirs# }"
+		test -n "\$hookdirs" && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" \$hookdirs
 		exit 0
 		EOF
 		chmod 755 "${pdir}/DEBIAN/${script}"
diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index d3c5b104c063..b724626ea0ca 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -49,17 +49,10 @@ mkdir -p "${destdir}"
 # This caters to host programs that participate in Kbuild. objtool and
 # resolve_btfids are out of scope.
 if [ "${CC}" != "${HOSTCC}" ]; then
-	echo "Rebuilding host programs with ${CC}..."
-
-	# This leverages external module building.
-	# - Clear sub_make_done to allow the top-level Makefile to redo sub-make.
-	# - Filter out --no-print-directory to print "Entering directory" logs
-	#   when Make changes the working directory.
-	unset sub_make_done
-	MAKEFLAGS=$(echo "${MAKEFLAGS}" | sed s/--no-print-directory//)
-
-	cat <<-'EOF' >  "${destdir}/Kbuild"
-	subdir-y := scripts
+	cat "${destdir}/scripts/Makefile" - <<-'EOF' > "${destdir}/scripts/Kbuild"
+	subdir-y += basic
+	hostprogs-always-y += mod/modpost
+	mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o)
 	EOF
 
 	# HOSTCXX is not overridden. The C++ compiler is used to build:
@@ -67,20 +60,12 @@ if [ "${CC}" != "${HOSTCC}" ]; then
 	# - GCC plugins, which will not work on the installed system even after
 	#   being rebuilt.
 	#
-	# Use the single-target build to avoid the modpost invocation, which
-	# would overwrite Module.symvers.
-	"${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/
-
-	cat <<-'EOF' >  "${destdir}/scripts/Kbuild"
-	subdir-y := basic
-	hostprogs-always-y := mod/modpost
-	mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o)
-	EOF
-
-	# Run once again to rebuild scripts/basic/ and scripts/mod/modpost.
-	"${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/
+	# Clear VPATH and srcroot because the source files reside in the output
+	# directory.
+	# shellcheck disable=SC2016 # $(MAKE), $(CC), and $(build) will be expanded by Make
+	"${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC="$(CC)" VPATH= srcroot=. $(build)='"${destdir}"/scripts
 
-	rm -f "${destdir}/Kbuild" "${destdir}/scripts/Kbuild"
+	rm -f "${destdir}/scripts/Kbuild"
 fi
 
 find "${destdir}" \( -name '.*.cmd' -o -name '*.o' \) -delete
diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index b038a1380b8a..b6dd98ca860b 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -205,7 +205,7 @@ Priority: optional
 Maintainer: $maintainer
 Rules-Requires-Root: no
 Build-Depends: debhelper-compat (= 12)
-Build-Depends-Arch: bc, bison, cpio, flex,
+Build-Depends-Arch: bc, bison, flex,
  gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>,
  kmod, libelf-dev:native,
  libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>,
diff --git a/scripts/spdxcheck.py b/scripts/spdxcheck.py
index 8b8fb115fc81..8d608f61bf37 100755
--- a/scripts/spdxcheck.py
+++ b/scripts/spdxcheck.py
@@ -214,9 +214,15 @@ class id_parser(object):
                 # Remove trailing xml comment closure
                 if line.strip().endswith('-->'):
                     expr = expr.rstrip('-->').strip()
+                # Remove trailing Jinja2 comment closure
+                if line.strip().endswith('#}'):
+                    expr = expr.rstrip('#}').strip()
                 # Special case for SH magic boot code files
                 if line.startswith('LIST \"'):
                     expr = expr.rstrip('\"').strip()
+                # Remove j2 comment closure
+                if line.startswith('{#'):
+                    expr = expr.rstrip('#}').strip()
                 self.parse(expr)
                 self.spdx_valid += 1
                 #
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 05bd9ca1fbfa..a290db720b0f 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -222,6 +222,7 @@ autonymous||autonomous
 auxillary||auxiliary
 auxilliary||auxiliary
 avaiable||available
+avaialable||available
 avaible||available
 availabe||available
 availabled||available
@@ -267,6 +268,7 @@ broadcase||broadcast
 broadcat||broadcast
 bufer||buffer
 bufferred||buffered
+bufferur||buffer
 bufufer||buffer
 cacluated||calculated
 caculate||calculate
@@ -405,6 +407,7 @@ configutation||configuration
 congiuration||configuration
 conider||consider
 conjuction||conjunction
+connction||connection
 connecetd||connected
 connectinos||connections
 connetor||connector
@@ -413,6 +416,7 @@ connnections||connections
 consistancy||consistency
 consistant||consistent
 consits||consists
+constructred||constructed
 containes||contains
 containts||contains
 contaisn||contains
@@ -450,6 +454,7 @@ creationg||creating
 cryptocraphic||cryptographic
 cummulative||cumulative
 cunter||counter
+curent||current
 curently||currently
 cylic||cyclic
 dafault||default
@@ -461,6 +466,7 @@ decendant||descendant
 decendants||descendants
 decompres||decompress
 decsribed||described
+decrese||decrease
 decription||description
 detault||default
 dectected||detected
@@ -485,6 +491,7 @@ delare||declare
 delares||declares
 delaring||declaring
 delemiter||delimiter
+deley||delay
 delibrately||deliberately
 delievered||delivered
 demodualtor||demodulator
@@ -551,6 +558,7 @@ disgest||digest
 disired||desired
 dispalying||displaying
 dissable||disable
+dissapeared||disappeared
 diplay||display
 directon||direction
 direcly||directly
@@ -606,6 +614,7 @@ eigth||eight
 elementry||elementary
 eletronic||electronic
 embeded||embedded
+emtpy||empty
 enabledi||enabled
 enbale||enable
 enble||enable
@@ -669,6 +678,7 @@ exmaple||example
 expecially||especially
 experies||expires
 explicite||explicit
+explicity||explicitly
 explicitely||explicitly
 explict||explicit
 explictely||explicitly
@@ -723,10 +733,12 @@ followign||following
 followings||following
 follwing||following
 fonud||found
+forcebly||forcibly
 forseeable||foreseeable
 forse||force
 fortan||fortran
 forwardig||forwarding
+forwared||forwarded
 frambuffer||framebuffer
 framming||framing
 framwork||framework
@@ -767,6 +779,7 @@ grahpical||graphical
 granularty||granularity
 grapic||graphic
 grranted||granted
+grups||groups
 guage||gauge
 guarenteed||guaranteed
 guarentee||guarantee
@@ -780,6 +793,7 @@ hardare||hardware
 harware||hardware
 hardward||hardware
 havind||having
+heigth||height
 heirarchically||hierarchically
 heirarchy||hierarchy
 heirachy||hierarchy
@@ -788,9 +802,11 @@ hearbeat||heartbeat
 heterogenous||heterogeneous
 hexdecimal||hexadecimal
 hybernate||hibernate
+hiearchy||hierarchy
 hierachy||hierarchy
 hierarchie||hierarchy
 homogenous||homogeneous
+horizental||horizontal
 howver||however
 hsould||should
 hypervior||hypervisor
@@ -842,6 +858,7 @@ independed||independent
 indiate||indicate
 indicat||indicate
 inexpect||inexpected
+infalte||inflate
 inferface||interface
 infinit||infinite
 infomation||information
@@ -861,6 +878,7 @@ initators||initiators
 initialiazation||initialization
 initializationg||initialization
 initializiation||initialization
+initializtion||initialization
 initialze||initialize
 initialzed||initialized
 initialzing||initializing
@@ -877,6 +895,7 @@ instanciate||instantiate
 instanciated||instantiated
 instuments||instruments
 insufficent||insufficient
+intead||instead
 inteface||interface
 integreated||integrated
 integrety||integrity
@@ -1081,6 +1100,7 @@ notications||notifications
 notifcations||notifications
 notifed||notified
 notity||notify
+notfify||notify
 nubmer||number
 numebr||number
 numer||number
@@ -1122,6 +1142,7 @@ orientatied||orientated
 orientied||oriented
 orignal||original
 originial||original
+orphanded||orphaned
 otherise||otherwise
 ouput||output
 oustanding||outstanding
@@ -1184,9 +1205,11 @@ peroid||period
 persistance||persistence
 persistant||persistent
 phoneticly||phonetically
+pipline||pipeline
 plaform||platform
 plalform||platform
 platfoem||platform
+platfomr||platform
 platfrom||platform
 plattform||platform
 pleaes||please
@@ -1211,6 +1234,7 @@ preceeding||preceding
 preceed||precede
 precendence||precedence
 precission||precision
+predicition||prediction
 preemptable||preemptible
 prefered||preferred
 prefferably||preferably
@@ -1289,6 +1313,7 @@ querrying||querying
 queus||queues
 randomally||randomly
 raoming||roaming
+readyness||readiness
 reasearcher||researcher
 reasearchers||researchers
 reasearch||research
@@ -1305,8 +1330,10 @@ recieves||receives
 recieving||receiving
 recogniced||recognised
 recognizeable||recognizable
+recompte||recompute
 recommanded||recommended
 recyle||recycle
+redect||reject
 redircet||redirect
 redirectrion||redirection
 redundacy||redundancy
@@ -1314,6 +1341,7 @@ reename||rename
 refcounf||refcount
 refence||reference
 refered||referred
+referencce||reference
 referenace||reference
 refererence||reference
 refering||referring
@@ -1348,11 +1376,13 @@ replys||replies
 reponse||response
 representaion||representation
 repsonse||response
+reqested||requested
 reqeust||request
 reqister||register
 requed||requeued
 requestied||requested
 requiere||require
+requieres||requires
 requirment||requirement
 requred||required
 requried||required
@@ -1440,6 +1470,7 @@ sequencial||sequential
 serivce||service
 serveral||several
 servive||service
+sesion||session
 setts||sets
 settting||setting
 shapshot||snapshot
@@ -1602,11 +1633,13 @@ trys||tries
 thses||these
 tiggers||triggers
 tiggered||triggered
+tiggerring||triggering
 tipically||typically
 timeing||timing
 timming||timing
 timout||timeout
 tmis||this
+tolarance||tolerance
 toogle||toggle
 torerable||tolerable
 torlence||tolerance
@@ -1633,6 +1666,7 @@ trasfer||transfer
 trasmission||transmission
 trasmitter||transmitter
 treshold||threshold
+trigged||triggered
 triggerd||triggered
 trigerred||triggered
 trigerring||triggering
@@ -1648,6 +1682,7 @@ uknown||unknown
 usccess||success
 uncommited||uncommitted
 uncompatible||incompatible
+uncomressed||uncompressed
 unconditionaly||unconditionally
 undeflow||underflow
 undelying||underlying
@@ -1715,6 +1750,7 @@ utitity||utility
 utitlty||utility
 vaid||valid
 vaild||valid
+validationg||validating
 valide||valid
 variantions||variations
 varible||variable
@@ -1724,6 +1760,7 @@ verbse||verbose
 veify||verify
 verfication||verification
 veriosn||version
+versoin||version
 verisons||versions
 verison||version
 veritical||vertical
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 7939aea731f1..45eaf35f5bff 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -188,6 +188,7 @@ regex_c=(
 	'/^PCI_OP_WRITE([[:space:]]*\(\w*\).*[1-4])/pci_bus_write_config_\1/'
 	'/\<DEFINE_\(RT_MUTEX\|MUTEX\|SEMAPHORE\|SPINLOCK\)([[:space:]]*\([[:alnum:]_]*\)/\2/v/'
 	'/\<DEFINE_\(RAW_SPINLOCK\|RWLOCK\|SEQLOCK\)([[:space:]]*\([[:alnum:]_]*\)/\2/v/'
+	'/\<DEFINE_TIMER(\([^,)]*\),/\1/'
 	'/\<DECLARE_\(RWSEM\|COMPLETION\)([[:space:]]*\([[:alnum:]_]\+\)/\2/v/'
 	'/\<DECLARE_BITMAP([[:space:]]*\([[:alnum:]_]\+\)/\1/v/'
 	'/\(^\|\s\)\(\|L\|H\)LIST_HEAD([[:space:]]*\([[:alnum:]_]*\)/\3/v/'
@@ -267,7 +268,8 @@ exuberant()
 	# identifiers to ignore by ctags
 	local ign=(
 		ACPI_EXPORT_SYMBOL
-		DEFINE_{TRACE,MUTEX}
+		DECLARE_BITMAP
+		DEFINE_{TRACE,MUTEX,TIMER}
 		EXPORT_SYMBOL EXPORT_SYMBOL_GPL
 		EXPORT_TRACEPOINT_SYMBOL EXPORT_TRACEPOINT_SYMBOL_GPL
 		____cacheline_aligned ____cacheline_aligned_in_smp
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 1edc12862a7d..9b6c2f157f83 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -2038,7 +2038,7 @@ static int apparmor_dointvec(const struct ctl_table *table, int write,
 	return proc_dointvec(table, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table apparmor_sysctl_table[] = {
+static const struct ctl_table apparmor_sysctl_table[] = {
 #ifdef CONFIG_USER_NS
 	{
 		.procname       = "unprivileged_userns_apparmor_policy",
diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
index 91f000eef3ad..cde08c478f32 100644
--- a/security/keys/sysctl.c
+++ b/security/keys/sysctl.c
@@ -9,7 +9,7 @@
 #include <linux/sysctl.h>
 #include "internal.h"
 
-static struct ctl_table key_sysctls[] = {
+static const struct ctl_table key_sysctls[] = {
 	{
 		.procname = "maxkeys",
 		.data = &key_quota_maxkeys,
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index e1a5e13ea269..1971710620c1 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -76,7 +76,6 @@ static void report_access(const char *access, struct task_struct *target,
 				struct task_struct *agent)
 {
 	struct access_report_info *info;
-	char agent_comm[sizeof(agent->comm)];
 
 	assert_spin_locked(&target->alloc_lock); /* for target->comm */
 
@@ -86,8 +85,7 @@ static void report_access(const char *access, struct task_struct *target,
 		 */
 		pr_notice_ratelimited(
 		    "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n",
-		    access, target->comm, target->pid,
-		    get_task_comm(agent_comm, agent), agent->pid);
+		    access, target->comm, target->pid, agent->comm, agent->pid);
 		return;
 	}
 
@@ -454,7 +452,7 @@ static int yama_dointvec_minmax(const struct ctl_table *table, int write,
 
 static int max_scope = YAMA_SCOPE_NO_ATTACH;
 
-static struct ctl_table yama_sysctl_table[] = {
+static const struct ctl_table yama_sysctl_table[] = {
 	{
 		.procname       = "ptrace_scope",
 		.data           = &ptrace_scope,
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 8a3384342e8d..6c2b6a62d9d2 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -3245,7 +3245,7 @@ static int snd_pcm_xfern_frames_ioctl(struct snd_pcm_substream *substream,
 	if (copy_from_user(&xfern, _xfern, sizeof(xfern)))
 		return -EFAULT;
 
-	bufs = memdup_user(xfern.bufs, sizeof(void *) * runtime->channels);
+	bufs = memdup_array_user(xfern.bufs, runtime->channels, sizeof(void *));
 	if (IS_ERR(bufs))
 		return PTR_ERR(bufs);
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 84393f4f429d..8923813ce424 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -80,7 +80,11 @@ static int compare_input_type(const void *ap, const void *bp)
 
 	/* In case one has boost and the other one has not,
 	   pick the one with boost first. */
-	return (int)(b->has_boost_on_pin - a->has_boost_on_pin);
+	if (a->has_boost_on_pin != b->has_boost_on_pin)
+		return (int)(b->has_boost_on_pin - a->has_boost_on_pin);
+
+	/* Keep the original order */
+	return a->order - b->order;
 }
 
 /* Reorder the surround channels
@@ -400,6 +404,8 @@ int snd_hda_parse_pin_defcfg(struct hda_codec *codec,
 	reorder_outputs(cfg->speaker_outs, cfg->speaker_pins);
 
 	/* sort inputs in the order of AUTO_PIN_* type */
+	for (i = 0; i < cfg->num_inputs; i++)
+		cfg->inputs[i].order = i;
 	sort(cfg->inputs, cfg->num_inputs, sizeof(cfg->inputs[0]),
 	     compare_input_type, NULL);
 
diff --git a/sound/pci/hda/hda_auto_parser.h b/sound/pci/hda/hda_auto_parser.h
index 579b11beac71..87af3d8c02f7 100644
--- a/sound/pci/hda/hda_auto_parser.h
+++ b/sound/pci/hda/hda_auto_parser.h
@@ -37,6 +37,7 @@ struct auto_pin_cfg_item {
 	unsigned int is_headset_mic:1;
 	unsigned int is_headphone_mic:1; /* Mic-only in headphone jack */
 	unsigned int has_boost_on_pin:1;
+	int order;
 };
 
 struct auto_pin_cfg;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d3c9ed963588..8192be394d0d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7497,6 +7497,16 @@ static void alc287_fixup_lenovo_thinkpad_with_alc1318(struct hda_codec *codec,
 	spec->gen.pcm_playback_hook = alc287_alc1318_playback_pcm_hook;
 }
 
+/*
+ * Clear COEF 0x0d (PCBEEP passthrough) bit 0x40 where BIOS sets it wrongly
+ * at PM resume
+ */
+static void alc283_fixup_dell_hp_resume(struct hda_codec *codec,
+					const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_INIT)
+		alc_write_coef_idx(codec, 0xd, 0x2800);
+}
 
 enum {
 	ALC269_FIXUP_GPIO2,
@@ -7799,6 +7809,7 @@ enum {
 	ALC269_FIXUP_VAIO_VJFH52_MIC_NO_PRESENCE,
 	ALC233_FIXUP_MEDION_MTL_SPK,
 	ALC294_FIXUP_BASS_SPEAKER_15,
+	ALC283_FIXUP_DELL_HP_RESUME,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -10143,6 +10154,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc294_fixup_bass_speaker_15,
 	},
+	[ALC283_FIXUP_DELL_HP_RESUME] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc283_fixup_dell_hp_resume,
+	},
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -10203,6 +10218,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x05f4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0604, "Dell Venue 11 Pro 7130", ALC283_FIXUP_DELL_HP_RESUME),
 	SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x062c, "Dell Latitude E5550", ALC292_FIXUP_DELL_E7X),
@@ -10918,7 +10934,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	HDA_CODEC_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x386e, "Yoga Pro 7 14ARP8", ALC285_FIXUP_SPEAKER2_TO_DAC1),
-	HDA_CODEC_QUIRK(0x17aa, 0x386f, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C),
+	HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */
 	SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c
index 1f59ee248771..89e99ed4275a 100644
--- a/sound/soc/amd/acp/acp-i2s.c
+++ b/sound/soc/amd/acp/acp-i2s.c
@@ -181,6 +181,7 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas
 			break;
 		default:
 			dev_err(dev, "Unknown chip revision %d\n", chip->acp_rev);
+			spin_unlock_irq(&adata->acp_lock);
 			return -EINVAL;
 		}
 	}
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index ecf57a6cb7c3..b16587d8f97a 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -307,6 +307,34 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 	{
 		.driver_data = &acp6x_card,
 		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83L3"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83N6"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"),
+		}
+	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"),
 		}
diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c
index ca4cc954efa8..eb97ac73ec06 100644
--- a/sound/soc/codecs/da7213.c
+++ b/sound/soc/codecs/da7213.c
@@ -2203,6 +2203,8 @@ static int da7213_i2c_probe(struct i2c_client *i2c)
 		return ret;
 	}
 
+	mutex_init(&da7213->ctrl_lock);
+
 	pm_runtime_set_autosuspend_delay(&i2c->dev, 100);
 	pm_runtime_use_autosuspend(&i2c->dev);
 	pm_runtime_set_active(&i2c->dev);
diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c
index f508df01145b..e7bd561a8f40 100644
--- a/sound/soc/codecs/es8316.c
+++ b/sound/soc/codecs/es8316.c
@@ -101,7 +101,7 @@ static const struct snd_kcontrol_new es8316_snd_controls[] = {
 	SOC_DOUBLE_R_TLV("DAC Playback Volume", ES8316_DAC_VOLL,
 			 ES8316_DAC_VOLR, 0, 0xc0, 1, dac_vol_tlv),
 	SOC_SINGLE("DAC Soft Ramp Switch", ES8316_DAC_SET1, 4, 1, 1),
-	SOC_SINGLE("DAC Soft Ramp Rate", ES8316_DAC_SET1, 2, 4, 0),
+	SOC_SINGLE("DAC Soft Ramp Rate", ES8316_DAC_SET1, 2, 3, 0),
 	SOC_SINGLE("DAC Notch Filter Switch", ES8316_DAC_SET2, 6, 1, 0),
 	SOC_SINGLE("DAC Double Fs Switch", ES8316_DAC_SET2, 7, 1, 0),
 	SOC_SINGLE("DAC Stereo Enhancement", ES8316_DAC_SET3, 0, 7, 0),
diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index b06eead7e0f6..066d92b54312 100644
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -911,7 +911,7 @@ static void es8326_jack_detect_handler(struct work_struct *work)
 			regmap_write(es8326->regmap, ES8326_INT_SOURCE,
 					(ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON));
 			regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f);
-			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08);
+			regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x0d);
 			queue_delayed_work(system_wq, &es8326->jack_detect_work,
 					msecs_to_jiffies(400));
 			es8326->hp = 1;
@@ -1023,7 +1023,7 @@ static void es8326_init(struct snd_soc_component *component)
 	struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component);
 
 	regmap_write(es8326->regmap, ES8326_RESET, 0x1f);
-	regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
+	regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x3E);
 	regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0);
 	usleep_range(10000, 15000);
 	regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xd9);
diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index 2b3c0f9e178c..9cb74962161a 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -1091,8 +1091,7 @@ static int rt5514_set_bias_level(struct snd_soc_component *component,
 static int rt5514_probe(struct snd_soc_component *component)
 {
 	struct rt5514_priv *rt5514 = snd_soc_component_get_drvdata(component);
-	struct platform_device *pdev = container_of(component->dev,
-						   struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(component->dev);
 
 	rt5514->mclk = devm_clk_get_optional(component->dev, "mclk");
 	if (IS_ERR(rt5514->mclk))
diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig
index e5fbf5305ea2..c4cf3cff58de 100644
--- a/sound/soc/fsl/Kconfig
+++ b/sound/soc/fsl/Kconfig
@@ -6,6 +6,7 @@ comment "Common SoC Audio options for Freescale CPUs:"
 config SND_SOC_FSL_ASRC
 	tristate "Asynchronous Sample Rate Converter (ASRC) module support"
 	depends on HAS_DMA
+	select DMA_SHARED_BUFFER
 	select REGMAP_MMIO
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 	select SND_COMPRESS_ACCEL
diff --git a/sound/soc/fsl/fsl_asrc_m2m.c b/sound/soc/fsl/fsl_asrc_m2m.c
index 4906843e2a8f..f46881f71e43 100644
--- a/sound/soc/fsl/fsl_asrc_m2m.c
+++ b/sound/soc/fsl/fsl_asrc_m2m.c
@@ -183,7 +183,7 @@ static int asrc_dmaconfig(struct fsl_asrc_pair *pair,
 }
 
 /* main function of converter */
-static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_task_runtime *task)
+static int asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_task_runtime *task)
 {
 	struct fsl_asrc *asrc = pair->asrc;
 	struct device *dev = &asrc->pdev->dev;
@@ -193,7 +193,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas
 	unsigned int out_dma_len;
 	unsigned int width;
 	u32 fifo_addr;
-	int ret;
+	int ret = 0;
 
 	/* set ratio mod */
 	if (asrc->m2m_set_ratio_mod) {
@@ -215,6 +215,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas
 	    in_buf_len > ASRC_M2M_BUFFER_SIZE ||
 	    in_buf_len % (width * pair->channels / 8)) {
 		dev_err(dev, "out buffer size is error: [%d]\n", in_buf_len);
+		ret = -EINVAL;
 		goto end;
 	}
 
@@ -245,6 +246,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas
 		}
 	} else if (out_dma_len > ASRC_M2M_BUFFER_SIZE) {
 		dev_err(dev, "cap buffer size error\n");
+		ret = -EINVAL;
 		goto end;
 	}
 
@@ -263,12 +265,14 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas
 
 	if (!wait_for_completion_interruptible_timeout(&pair->complete[IN], 10 * HZ)) {
 		dev_err(dev, "out DMA task timeout\n");
+		ret = -ETIMEDOUT;
 		goto end;
 	}
 
 	if (out_dma_len > 0) {
 		if (!wait_for_completion_interruptible_timeout(&pair->complete[OUT], 10 * HZ)) {
 			dev_err(dev, "cap DMA task timeout\n");
+			ret = -ETIMEDOUT;
 			goto end;
 		}
 	}
@@ -278,7 +282,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas
 	/* update payload length for capture */
 	task->output_size = out_dma_len;
 end:
-	return;
+	return ret;
 }
 
 static int fsl_asrc_m2m_comp_open(struct snd_compr_stream *stream)
@@ -525,9 +529,7 @@ static int fsl_asrc_m2m_comp_task_start(struct snd_compr_stream *stream,
 	struct snd_compr_runtime *runtime = stream->runtime;
 	struct fsl_asrc_pair *pair = runtime->private_data;
 
-	asrc_m2m_device_run(pair, task);
-
-	return 0;
+	return asrc_m2m_device_run(pair, task);
 }
 
 static int fsl_asrc_m2m_comp_task_stop(struct snd_compr_stream *stream,
@@ -633,7 +635,7 @@ int fsl_asrc_m2m_suspend(struct fsl_asrc *asrc)
 
 	for (i = 0; i < PAIR_CTX_NUM; i++) {
 		pair = asrc->pair[i];
-		if (!pair)
+		if (!pair || !pair->dma_buffer[IN].area || !pair->dma_buffer[OUT].area)
 			continue;
 		if (!completion_done(&pair->complete[IN])) {
 			if (pair->dma_chan[IN])
diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c
index c36b1a2ac949..ee94b256b770 100644
--- a/sound/soc/generic/audio-graph-card2.c
+++ b/sound/soc/generic/audio-graph-card2.c
@@ -648,23 +648,23 @@ multi_err:
 
 static int graph_parse_node_single(struct simple_util_priv *priv,
 				   enum graph_type gtype,
-				   struct device_node *port,
+				   struct device_node *ep,
 				   struct link_info *li, int is_cpu)
 {
-	struct device_node *ep __free(device_node) = of_graph_get_next_port_endpoint(port, NULL);
-
 	return __graph_parse_node(priv, gtype, ep, li, is_cpu, 0);
 }
 
 static int graph_parse_node(struct simple_util_priv *priv,
 			    enum graph_type gtype,
-			    struct device_node *port,
+			    struct device_node *ep,
 			    struct link_info *li, int is_cpu)
 {
+	struct device_node *port __free(device_node) = ep_to_port(ep);
+
 	if (graph_lnk_is_multi(port))
 		return graph_parse_node_multi(priv, gtype, port, li, is_cpu);
 	else
-		return graph_parse_node_single(priv, gtype, port, li, is_cpu);
+		return graph_parse_node_single(priv, gtype, ep, li, is_cpu);
 }
 
 static void graph_parse_daifmt(struct device_node *node, unsigned int *daifmt)
@@ -722,14 +722,15 @@ static unsigned int graph_parse_bitframe(struct device_node *ep)
 
 static void graph_link_init(struct simple_util_priv *priv,
 			    struct device_node *lnk,
-			    struct device_node *port_cpu,
-			    struct device_node *port_codec,
+			    struct device_node *ep_cpu,
+			    struct device_node *ep_codec,
 			    struct link_info *li,
 			    int is_cpu_node)
 {
 	struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link);
 	struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link);
-	struct device_node *ep_cpu, *ep_codec;
+	struct device_node *port_cpu = ep_to_port(ep_cpu);
+	struct device_node *port_codec = ep_to_port(ep_codec);
 	struct device_node *multi_cpu_port = NULL, *multi_codec_port = NULL;
 	struct snd_soc_dai_link_component *dlc;
 	unsigned int daifmt = 0;
@@ -739,25 +740,23 @@ static void graph_link_init(struct simple_util_priv *priv,
 	int multi_cpu_port_idx = 1, multi_codec_port_idx = 1;
 	int i;
 
-	of_node_get(port_cpu);
 	if (graph_lnk_is_multi(port_cpu)) {
 		multi_cpu_port = port_cpu;
 		ep_cpu = graph_get_next_multi_ep(&multi_cpu_port, multi_cpu_port_idx++);
 		of_node_put(port_cpu);
 		port_cpu = ep_to_port(ep_cpu);
 	} else {
-		ep_cpu = of_graph_get_next_port_endpoint(port_cpu, NULL);
+		of_node_get(ep_cpu);
 	}
 	struct device_node *ports_cpu __free(device_node) = port_to_ports(port_cpu);
 
-	of_node_get(port_codec);
 	if (graph_lnk_is_multi(port_codec)) {
 		multi_codec_port = port_codec;
 		ep_codec = graph_get_next_multi_ep(&multi_codec_port, multi_codec_port_idx++);
 		of_node_put(port_codec);
 		port_codec = ep_to_port(ep_codec);
 	} else {
-		ep_codec = of_graph_get_next_port_endpoint(port_codec, NULL);
+		of_node_get(ep_codec);
 	}
 	struct device_node *ports_codec __free(device_node) = port_to_ports(port_codec);
 
@@ -833,7 +832,7 @@ int audio_graph2_link_normal(struct simple_util_priv *priv,
 {
 	struct device_node *cpu_port = lnk;
 	struct device_node *cpu_ep	__free(device_node) = of_graph_get_next_port_endpoint(cpu_port, NULL);
-	struct device_node *codec_port	__free(device_node) = of_graph_get_remote_port(cpu_ep);
+	struct device_node *codec_ep	__free(device_node) = of_graph_get_remote_endpoint(cpu_ep);
 	int ret;
 
 	/*
@@ -841,18 +840,18 @@ int audio_graph2_link_normal(struct simple_util_priv *priv,
 	 * see
 	 *	__graph_parse_node() :: DAI Naming
 	 */
-	ret = graph_parse_node(priv, GRAPH_NORMAL, codec_port, li, 0);
+	ret = graph_parse_node(priv, GRAPH_NORMAL, codec_ep, li, 0);
 	if (ret < 0)
 		return ret;
 
 	/*
 	 * call CPU, and set DAI Name
 	 */
-	ret = graph_parse_node(priv, GRAPH_NORMAL, cpu_port, li, 1);
+	ret = graph_parse_node(priv, GRAPH_NORMAL, cpu_ep, li, 1);
 	if (ret < 0)
 		return ret;
 
-	graph_link_init(priv, lnk, cpu_port, codec_port, li, 1);
+	graph_link_init(priv, lnk, cpu_ep, codec_ep, li, 1);
 
 	return ret;
 }
@@ -864,15 +863,15 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv,
 {
 	struct device_node *ep	__free(device_node) = of_graph_get_next_port_endpoint(lnk, NULL);
 	struct device_node *rep	__free(device_node) = of_graph_get_remote_endpoint(ep);
-	struct device_node *cpu_port = NULL;
-	struct device_node *codec_port = NULL;
+	struct device_node *cpu_ep = NULL;
+	struct device_node *codec_ep = NULL;
 	struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link);
 	struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link);
 	int is_cpu = graph_util_is_ports0(lnk);
 	int ret;
 
 	if (is_cpu) {
-		cpu_port = of_graph_get_remote_port(ep); /* rport */
+		cpu_ep = rep;
 
 		/*
 		 * dpcm {
@@ -901,12 +900,12 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv,
 		dai_link->dynamic		= 1;
 		dai_link->dpcm_merged_format	= 1;
 
-		ret = graph_parse_node(priv, GRAPH_DPCM, cpu_port, li, 1);
+		ret = graph_parse_node(priv, GRAPH_DPCM, cpu_ep, li, 1);
 		if (ret)
-			goto err;
+			return ret;
 
 	} else {
-		codec_port = of_graph_get_remote_port(ep); /* rport */
+		codec_ep = rep;
 
 		/*
 		 * dpcm {
@@ -937,18 +936,15 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv,
 		dai_link->no_pcm		= 1;
 		dai_link->be_hw_params_fixup	= simple_util_be_hw_params_fixup;
 
-		ret = graph_parse_node(priv, GRAPH_DPCM, codec_port, li, 0);
+		ret = graph_parse_node(priv, GRAPH_DPCM, codec_ep, li, 0);
 		if (ret < 0)
-			goto err;
+			return ret;
 	}
 
 	graph_parse_convert(ep,  dai_props); /* at node of <dpcm> */
 	graph_parse_convert(rep, dai_props); /* at node of <CPU/Codec> */
 
-	graph_link_init(priv, lnk, cpu_port, codec_port, li, is_cpu);
-err:
-	of_node_put(cpu_port);
-	of_node_put(codec_port);
+	graph_link_init(priv, lnk, cpu_ep, codec_ep, li, is_cpu);
 
 	return ret;
 }
@@ -1013,26 +1009,26 @@ int audio_graph2_link_c2c(struct simple_util_priv *priv,
 	struct device_node *ep0 __free(device_node) = of_graph_get_next_port_endpoint(port0, NULL);
 	struct device_node *ep1 __free(device_node) = of_graph_get_next_port_endpoint(port1, NULL);
 
-	struct device_node *codec0_port __free(device_node) = of_graph_get_remote_port(ep0);
-	struct device_node *codec1_port __free(device_node) = of_graph_get_remote_port(ep1);
+	struct device_node *codec0_ep __free(device_node) = of_graph_get_remote_endpoint(ep0);
+	struct device_node *codec1_ep __free(device_node) = of_graph_get_remote_endpoint(ep1);
 
 	/*
 	 * call Codec first.
 	 * see
 	 *	__graph_parse_node() :: DAI Naming
 	 */
-	ret = graph_parse_node(priv, GRAPH_C2C, codec1_port, li, 0);
+	ret = graph_parse_node(priv, GRAPH_C2C, codec1_ep, li, 0);
 	if (ret < 0)
 		return ret;
 
 	/*
 	 * call CPU, and set DAI Name
 	 */
-	ret = graph_parse_node(priv, GRAPH_C2C, codec0_port, li, 1);
+	ret = graph_parse_node(priv, GRAPH_C2C, codec0_ep, li, 1);
 	if (ret < 0)
 		return ret;
 
-	graph_link_init(priv, lnk, codec0_port, codec1_port, li, 1);
+	graph_link_init(priv, lnk, codec0_ep, codec1_ep, li, 1);
 
 	return ret;
 }
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 9caa4407c1ca..6446cda0f857 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -1132,7 +1132,22 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF2 |
 					BYT_RT5640_MCLK_EN),
 	},
-	{	/* Vexia Edu Atla 10 tablet */
+	{
+		/* Vexia Edu Atla 10 tablet 5V version */
+		.matches = {
+			/* Having all 3 of these not set is somewhat unique */
+			DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."),
+			DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."),
+			/* Above strings are too generic, also match on BIOS date */
+			DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_JD_NOT_INV |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
+	{	/* Vexia Edu Atla 10 tablet 9V version */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 			DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"),
diff --git a/sound/soc/renesas/Kconfig b/sound/soc/renesas/Kconfig
index 426632996a0a..cb01fb36355f 100644
--- a/sound/soc/renesas/Kconfig
+++ b/sound/soc/renesas/Kconfig
@@ -67,7 +67,7 @@ config SND_SH7760_AC97
 
 config SND_SIU_MIGOR
 	tristate "SIU sound support on Migo-R"
-	depends on SH_MIGOR && I2C
+	depends on SH_MIGOR && I2C && DMADEVICES
 	select SND_SOC_SH4_SIU
 	select SND_SOC_WM8978
 	help
diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c
index bd0dc586e24a..7f5fcaecee4b 100644
--- a/sound/soc/rockchip/rockchip_i2s_tdm.c
+++ b/sound/soc/rockchip/rockchip_i2s_tdm.c
@@ -22,7 +22,6 @@
 
 #define DRV_NAME "rockchip-i2s-tdm"
 
-#define DEFAULT_MCLK_FS				256
 #define CH_GRP_MAX				4  /* The max channel 8 / 2 */
 #define MULTIPLEX_CH_MAX			10
 
@@ -70,6 +69,8 @@ struct rk_i2s_tdm_dev {
 	bool has_playback;
 	bool has_capture;
 	struct snd_soc_dai_driver *dai;
+	unsigned int mclk_rx_freq;
+	unsigned int mclk_tx_freq;
 };
 
 static int to_ch_num(unsigned int val)
@@ -617,6 +618,27 @@ static int rockchip_i2s_trcm_mode(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+static int rockchip_i2s_tdm_set_sysclk(struct snd_soc_dai *cpu_dai, int stream,
+				       unsigned int freq, int dir)
+{
+	struct rk_i2s_tdm_dev *i2s_tdm = to_info(cpu_dai);
+
+	if (i2s_tdm->clk_trcm) {
+		i2s_tdm->mclk_tx_freq = freq;
+		i2s_tdm->mclk_rx_freq = freq;
+	} else {
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+			i2s_tdm->mclk_tx_freq = freq;
+		else
+			i2s_tdm->mclk_rx_freq = freq;
+	}
+
+	dev_dbg(i2s_tdm->dev, "The target mclk_%s freq is: %d\n",
+		stream ? "rx" : "tx", freq);
+
+	return 0;
+}
+
 static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream,
 				      struct snd_pcm_hw_params *params,
 				      struct snd_soc_dai *dai)
@@ -631,15 +653,19 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream,
 
 		if (i2s_tdm->clk_trcm == TRCM_TX) {
 			mclk = i2s_tdm->mclk_tx;
+			mclk_rate = i2s_tdm->mclk_tx_freq;
 		} else if (i2s_tdm->clk_trcm == TRCM_RX) {
 			mclk = i2s_tdm->mclk_rx;
+			mclk_rate = i2s_tdm->mclk_rx_freq;
 		} else if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 			mclk = i2s_tdm->mclk_tx;
+			mclk_rate = i2s_tdm->mclk_tx_freq;
 		} else {
 			mclk = i2s_tdm->mclk_rx;
+			mclk_rate = i2s_tdm->mclk_rx_freq;
 		}
 
-		err = clk_set_rate(mclk, DEFAULT_MCLK_FS * params_rate(params));
+		err = clk_set_rate(mclk, mclk_rate);
 		if (err)
 			return err;
 
@@ -799,6 +825,7 @@ static const struct snd_soc_dai_ops rockchip_i2s_tdm_dai_ops = {
 	.hw_params = rockchip_i2s_tdm_hw_params,
 	.set_bclk_ratio	= rockchip_i2s_tdm_set_bclk_ratio,
 	.set_fmt = rockchip_i2s_tdm_set_fmt,
+	.set_sysclk = rockchip_i2s_tdm_set_sysclk,
 	.set_tdm_slot = rockchip_dai_tdm_slot,
 	.trigger = rockchip_i2s_tdm_trigger,
 };
diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c
index 0b85b29d1067..1e7bf00d7c46 100644
--- a/sound/soc/sof/imx/imx8.c
+++ b/sound/soc/sof/imx/imx8.c
@@ -175,8 +175,7 @@ static int imx8_run(struct snd_sof_dev *sdev)
 
 static int imx8_probe(struct snd_sof_dev *sdev)
 {
-	struct platform_device *pdev =
-		container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	struct device_node *res_node;
 	struct resource *mmio;
@@ -607,10 +606,31 @@ static struct snd_sof_of_mach sof_imx8_machs[] = {
 		.drv_name = "asoc-audio-graph-card2",
 	},
 	{
+		.compatible = "fsl,imx8qxp-mek-wcpu",
+		.sof_tplg_filename = "sof-imx8-wm8962.tplg",
+		.drv_name = "asoc-audio-graph-card2",
+	},
+	{
 		.compatible = "fsl,imx8qm-mek",
 		.sof_tplg_filename = "sof-imx8-wm8960.tplg",
 		.drv_name = "asoc-audio-graph-card2",
 	},
+	{
+		.compatible = "fsl,imx8qm-mek-revd",
+		.sof_tplg_filename = "sof-imx8-wm8962.tplg",
+		.drv_name = "asoc-audio-graph-card2",
+	},
+	{
+		.compatible = "fsl,imx8qxp-mek-bb",
+		.sof_tplg_filename = "sof-imx8-cs42888.tplg",
+		.drv_name = "asoc-audio-graph-card2",
+	},
+	{
+		.compatible = "fsl,imx8qm-mek-bb",
+		.sof_tplg_filename = "sof-imx8-cs42888.tplg",
+		.drv_name = "asoc-audio-graph-card2",
+	},
+
 	{}
 };
 
diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c
index ff42743efa79..3cabdebac558 100644
--- a/sound/soc/sof/imx/imx8m.c
+++ b/sound/soc/sof/imx/imx8m.c
@@ -144,8 +144,7 @@ static int imx8m_reset(struct snd_sof_dev *sdev)
 
 static int imx8m_probe(struct snd_sof_dev *sdev)
 {
-	struct platform_device *pdev =
-		container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	struct device_node *res_node;
 	struct resource *mmio;
@@ -295,6 +294,17 @@ static struct snd_soc_dai_driver imx8m_dai[] = {
 	},
 },
 {
+	.name = "sai2",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+},
+{
 	.name = "sai3",
 	.playback = {
 		.channels_min = 1,
@@ -306,6 +316,39 @@ static struct snd_soc_dai_driver imx8m_dai[] = {
 	},
 },
 {
+	.name = "sai5",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+},
+{
+	.name = "sai6",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+},
+{
+	.name = "sai7",
+	.playback = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+	.capture = {
+		.channels_min = 1,
+		.channels_max = 32,
+	},
+},
+{
 	.name = "micfil",
 	.capture = {
 		.channels_min = 1,
@@ -472,6 +515,11 @@ static const struct snd_sof_dsp_ops sof_imx8m_ops = {
 
 static struct snd_sof_of_mach sof_imx8mp_machs[] = {
 	{
+		.compatible = "fsl,imx8mp-evk-revb4",
+		.sof_tplg_filename = "sof-imx8mp-wm8962.tplg",
+		.drv_name = "asoc-audio-graph-card2",
+	},
+	{
 		.compatible = "fsl,imx8mp-evk",
 		.sof_tplg_filename = "sof-imx8mp-wm8960.tplg",
 		.drv_name = "asoc-audio-graph-card2",
diff --git a/sound/soc/sof/imx/imx8ulp.c b/sound/soc/sof/imx/imx8ulp.c
index 6965791ab6ef..0704da27e69d 100644
--- a/sound/soc/sof/imx/imx8ulp.c
+++ b/sound/soc/sof/imx/imx8ulp.c
@@ -155,8 +155,7 @@ static int imx8ulp_reset(struct snd_sof_dev *sdev)
 
 static int imx8ulp_probe(struct snd_sof_dev *sdev)
 {
-	struct platform_device *pdev =
-		container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	struct device_node *np = pdev->dev.of_node;
 	struct device_node *res_node;
 	struct resource *mmio;
diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c
index 5282c0071534..e1f0e38c2407 100644
--- a/sound/soc/sof/intel/bdw.c
+++ b/sound/soc/sof/intel/bdw.c
@@ -410,8 +410,7 @@ static int bdw_probe(struct snd_sof_dev *sdev)
 {
 	struct snd_sof_pdata *pdata = sdev->pdata;
 	const struct sof_dev_desc *desc = pdata->desc;
-	struct platform_device *pdev =
-		container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	const struct sof_intel_dsp_desc *chip;
 	struct resource *mmio;
 	u32 base, size;
diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c
index 536d4c89d2f0..cae7dc0036c6 100644
--- a/sound/soc/sof/intel/byt.c
+++ b/sound/soc/sof/intel/byt.c
@@ -109,8 +109,7 @@ static int byt_acpi_probe(struct snd_sof_dev *sdev)
 {
 	struct snd_sof_pdata *pdata = sdev->pdata;
 	const struct sof_dev_desc *desc = pdata->desc;
-	struct platform_device *pdev =
-		container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	const struct sof_intel_dsp_desc *chip;
 	struct resource *mmio;
 	u32 base, size;
diff --git a/sound/soc/sof/mediatek/mt8186/mt8186.c b/sound/soc/sof/mediatek/mt8186/mt8186.c
index 9955dfa520ae..31437fdd4e92 100644
--- a/sound/soc/sof/mediatek/mt8186/mt8186.c
+++ b/sound/soc/sof/mediatek/mt8186/mt8186.c
@@ -238,7 +238,7 @@ static int mt8186_run(struct snd_sof_dev *sdev)
 
 static int mt8186_dsp_probe(struct snd_sof_dev *sdev)
 {
-	struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	struct adsp_priv *priv;
 	int ret;
 
diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c
index 6032b566c679..371563d7ce79 100644
--- a/sound/soc/sof/mediatek/mt8195/mt8195.c
+++ b/sound/soc/sof/mediatek/mt8195/mt8195.c
@@ -228,7 +228,7 @@ static int mt8195_run(struct snd_sof_dev *sdev)
 
 static int mt8195_dsp_probe(struct snd_sof_dev *sdev)
 {
-	struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	struct adsp_priv *priv;
 	int ret;
 
@@ -341,7 +341,7 @@ static int mt8195_dsp_shutdown(struct snd_sof_dev *sdev)
 
 static void mt8195_dsp_remove(struct snd_sof_dev *sdev)
 {
-	struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	struct adsp_priv *priv = sdev->pdata->hw_pdata;
 
 	platform_device_unregister(priv->ipc_dev);
@@ -351,7 +351,7 @@ static void mt8195_dsp_remove(struct snd_sof_dev *sdev)
 
 static int mt8195_dsp_suspend(struct snd_sof_dev *sdev, u32 target_state)
 {
-	struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev);
+	struct platform_device *pdev = to_platform_device(sdev->dev);
 	int ret;
 	u32 reset_sw, dbg_pc;
 
diff --git a/sound/soc/sof/sof-client-ipc-flood-test.c b/sound/soc/sof/sof-client-ipc-flood-test.c
index b35c98896968..11b6f7da2882 100644
--- a/sound/soc/sof/sof-client-ipc-flood-test.c
+++ b/sound/soc/sof/sof-client-ipc-flood-test.c
@@ -158,7 +158,6 @@ static ssize_t sof_ipc_flood_dfs_write(struct file *file, const char __user *buf
 	unsigned long ipc_duration_ms = 0;
 	bool flood_duration_test = false;
 	unsigned long ipc_count = 0;
-	struct dentry *dentry;
 	int err;
 	char *string;
 	int ret;
@@ -182,14 +181,7 @@ static ssize_t sof_ipc_flood_dfs_write(struct file *file, const char __user *buf
 	 * ipc_duration_ms test floods the DSP for the time specified
 	 * in the debugfs entry.
 	 */
-	dentry = file->f_path.dentry;
-	if (strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_COUNT) &&
-	    strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_DURATION)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (!strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_DURATION))
+	if (debugfs_get_aux_num(file))
 		flood_duration_test = true;
 
 	/* test completion criterion */
@@ -252,22 +244,15 @@ static ssize_t sof_ipc_flood_dfs_read(struct file *file, char __user *buffer,
 	struct sof_ipc_flood_priv *priv = cdev->data;
 	size_t size_ret;
 
-	struct dentry *dentry;
+	if (*ppos)
+		return 0;
 
-	dentry = file->f_path.dentry;
-	if (!strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_COUNT) ||
-	    !strcmp(dentry->d_name.name, DEBUGFS_IPC_FLOOD_DURATION)) {
-		if (*ppos)
-			return 0;
+	count = min_t(size_t, count, strlen(priv->buf));
+	size_ret = copy_to_user(buffer, priv->buf, count);
+	if (size_ret)
+		return -EFAULT;
 
-		count = min_t(size_t, count, strlen(priv->buf));
-		size_ret = copy_to_user(buffer, priv->buf, count);
-		if (size_ret)
-			return -EFAULT;
-
-		*ppos += count;
-		return count;
-	}
+	*ppos += count;
 	return count;
 }
 
@@ -320,12 +305,12 @@ static int sof_ipc_flood_probe(struct auxiliary_device *auxdev,
 	priv->dfs_root = debugfs_create_dir(dev_name(dev), debugfs_root);
 	if (!IS_ERR_OR_NULL(priv->dfs_root)) {
 		/* create read-write ipc_flood_count debugfs entry */
-		debugfs_create_file(DEBUGFS_IPC_FLOOD_COUNT, 0644, priv->dfs_root,
-				    cdev, &sof_ipc_flood_fops);
+		debugfs_create_file_aux_num(DEBUGFS_IPC_FLOOD_COUNT, 0644,
+				    priv->dfs_root, cdev, 0, &sof_ipc_flood_fops);
 
 		/* create read-write ipc_flood_duration_ms debugfs entry */
-		debugfs_create_file(DEBUGFS_IPC_FLOOD_DURATION, 0644,
-				    priv->dfs_root, cdev, &sof_ipc_flood_fops);
+		debugfs_create_file_aux_num(DEBUGFS_IPC_FLOOD_DURATION, 0644,
+				    priv->dfs_root, cdev, 1, &sof_ipc_flood_fops);
 
 		if (auxdev->id == 0) {
 			/*
diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c
index ca2c6f5de407..c073b38cd673 100644
--- a/sound/usb/line6/toneport.c
+++ b/sound/usb/line6/toneport.c
@@ -386,7 +386,7 @@ static int toneport_setup(struct usb_line6_toneport *toneport)
 		toneport_update_led(toneport);
 
 	schedule_delayed_work(&toneport->line6.startup_work,
-			      msecs_to_jiffies(TONEPORT_PCM_DELAY * 1000));
+			      secs_to_jiffies(TONEPORT_PCM_DELAY));
 	return 0;
 }
 
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 7968d6a2f592..a97efb7b131e 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2343,6 +2343,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */
+		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c
index 1334214546d7..100ad3dc091a 100644
--- a/tools/accounting/getdelays.c
+++ b/tools/accounting/getdelays.c
@@ -192,60 +192,77 @@ static int get_family_id(int sd)
 }
 
 #define average_ms(t, c) (t / 1000000ULL / (c ? c : 1))
+#define delay_ms(t) (t / 1000000ULL)
 
 static void print_delayacct(struct taskstats *t)
 {
-	printf("\n\nCPU   %15s%15s%15s%15s%15s\n"
-	       "      %15llu%15llu%15llu%15llu%15.3fms\n"
-	       "IO    %15s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n"
-	       "SWAP  %15s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n"
-	       "RECLAIM  %12s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n"
-	       "THRASHING%12s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n"
-	       "COMPACT  %12s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n"
-	       "WPCOPY   %12s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n"
-	       "IRQ   %15s%15s%15s\n"
-	       "      %15llu%15llu%15.3fms\n",
+	printf("\n\nCPU   %15s%15s%15s%15s%15s%15s\n"
+	       "      %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n"
+	       "IO    %15s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n"
+	       "SWAP  %15s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n"
+	       "RECLAIM  %12s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n"
+	       "THRASHING%12s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n"
+	       "COMPACT  %12s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n"
+	       "WPCOPY   %12s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n"
+	       "IRQ   %15s%15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms%13.6fms\n",
 	       "count", "real total", "virtual total",
-	       "delay total", "delay average",
+	       "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->cpu_count,
 	       (unsigned long long)t->cpu_run_real_total,
 	       (unsigned long long)t->cpu_run_virtual_total,
 	       (unsigned long long)t->cpu_delay_total,
 	       average_ms((double)t->cpu_delay_total, t->cpu_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->cpu_delay_max),
+	       delay_ms((double)t->cpu_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->blkio_count,
 	       (unsigned long long)t->blkio_delay_total,
 	       average_ms((double)t->blkio_delay_total, t->blkio_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->blkio_delay_max),
+	       delay_ms((double)t->blkio_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->swapin_count,
 	       (unsigned long long)t->swapin_delay_total,
 	       average_ms((double)t->swapin_delay_total, t->swapin_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->swapin_delay_max),
+	       delay_ms((double)t->swapin_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->freepages_count,
 	       (unsigned long long)t->freepages_delay_total,
 	       average_ms((double)t->freepages_delay_total, t->freepages_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->freepages_delay_max),
+	       delay_ms((double)t->freepages_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->thrashing_count,
 	       (unsigned long long)t->thrashing_delay_total,
 	       average_ms((double)t->thrashing_delay_total, t->thrashing_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->thrashing_delay_max),
+	       delay_ms((double)t->thrashing_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->compact_count,
 	       (unsigned long long)t->compact_delay_total,
 	       average_ms((double)t->compact_delay_total, t->compact_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->compact_delay_max),
+	       delay_ms((double)t->compact_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->wpcopy_count,
 	       (unsigned long long)t->wpcopy_delay_total,
 	       average_ms((double)t->wpcopy_delay_total, t->wpcopy_count),
-	       "count", "delay total", "delay average",
+	       delay_ms((double)t->wpcopy_delay_max),
+	       delay_ms((double)t->wpcopy_delay_min),
+	       "count", "delay total", "delay average", "delay max", "delay min",
 	       (unsigned long long)t->irq_count,
 	       (unsigned long long)t->irq_delay_total,
-	       average_ms((double)t->irq_delay_total, t->irq_count));
+	       average_ms((double)t->irq_delay_total, t->irq_count),
+	       delay_ms((double)t->irq_delay_max),
+	       delay_ms((double)t->irq_delay_min));
 }
 
 static void task_context_switch_counts(struct taskstats *t)
diff --git a/tools/accounting/procacct.c b/tools/accounting/procacct.c
index 90c4a37f53d9..e8dee05a6264 100644
--- a/tools/accounting/procacct.c
+++ b/tools/accounting/procacct.c
@@ -274,12 +274,11 @@ int main(int argc, char *argv[])
 	int maskset = 0;
 	char *logfile = NULL;
 	int cfd = 0;
-	int forking = 0;
 
 	struct msgtemplate msg;
 
-	while (!forking) {
-		c = getopt(argc, argv, "m:vr:");
+	while (1) {
+		c = getopt(argc, argv, "m:vr:w:");
 		if (c < 0)
 			break;
 
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index cd8420e8c3ad..150416682e2c 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -11,6 +11,7 @@
 
 #include <linux/bits.h>
 #include <linux/stringify.h>
+#include <linux/kasan-tags.h>
 
 #include <asm/gpr-num.h>
 
@@ -108,6 +109,9 @@
 #define set_pstate_ssbs(x)		asm volatile(SET_PSTATE_SSBS(x))
 #define set_pstate_dit(x)		asm volatile(SET_PSTATE_DIT(x))
 
+/* Register-based PAN access, for save/restore purposes */
+#define SYS_PSTATE_PAN			sys_reg(3, 0, 4, 2, 3)
+
 #define __SYS_BARRIER_INSN(CRm, op2, Rt) \
 	__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
 
@@ -123,6 +127,37 @@
 #define SYS_DC_CIGSW			sys_insn(1, 0, 7, 14, 4)
 #define SYS_DC_CIGDSW			sys_insn(1, 0, 7, 14, 6)
 
+#define SYS_IC_IALLUIS			sys_insn(1, 0, 7, 1, 0)
+#define SYS_IC_IALLU			sys_insn(1, 0, 7, 5, 0)
+#define SYS_IC_IVAU			sys_insn(1, 3, 7, 5, 1)
+
+#define SYS_DC_IVAC			sys_insn(1, 0, 7, 6, 1)
+#define SYS_DC_IGVAC			sys_insn(1, 0, 7, 6, 3)
+#define SYS_DC_IGDVAC			sys_insn(1, 0, 7, 6, 5)
+
+#define SYS_DC_CVAC			sys_insn(1, 3, 7, 10, 1)
+#define SYS_DC_CGVAC			sys_insn(1, 3, 7, 10, 3)
+#define SYS_DC_CGDVAC			sys_insn(1, 3, 7, 10, 5)
+
+#define SYS_DC_CVAU			sys_insn(1, 3, 7, 11, 1)
+
+#define SYS_DC_CVAP			sys_insn(1, 3, 7, 12, 1)
+#define SYS_DC_CGVAP			sys_insn(1, 3, 7, 12, 3)
+#define SYS_DC_CGDVAP			sys_insn(1, 3, 7, 12, 5)
+
+#define SYS_DC_CVADP			sys_insn(1, 3, 7, 13, 1)
+#define SYS_DC_CGVADP			sys_insn(1, 3, 7, 13, 3)
+#define SYS_DC_CGDVADP			sys_insn(1, 3, 7, 13, 5)
+
+#define SYS_DC_CIVAC			sys_insn(1, 3, 7, 14, 1)
+#define SYS_DC_CIGVAC			sys_insn(1, 3, 7, 14, 3)
+#define SYS_DC_CIGDVAC			sys_insn(1, 3, 7, 14, 5)
+
+/* Data cache zero operations */
+#define SYS_DC_ZVA			sys_insn(1, 3, 7, 4, 1)
+#define SYS_DC_GVA			sys_insn(1, 3, 7, 4, 3)
+#define SYS_DC_GZVA			sys_insn(1, 3, 7, 4, 4)
+
 /*
  * Automatically generated definitions for system registers, the
  * manual encodings below are in the process of being converted to
@@ -162,6 +197,84 @@
 #define SYS_DBGDTRTX_EL0		sys_reg(2, 3, 0, 5, 0)
 #define SYS_DBGVCR32_EL2		sys_reg(2, 4, 0, 7, 0)
 
+#define SYS_BRBINF_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 0))
+#define SYS_BRBINFINJ_EL1		sys_reg(2, 1, 9, 1, 0)
+#define SYS_BRBSRC_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 1))
+#define SYS_BRBSRCINJ_EL1		sys_reg(2, 1, 9, 1, 1)
+#define SYS_BRBTGT_EL1(n)		sys_reg(2, 1, 8, (n & 15), (((n & 16) >> 2) | 2))
+#define SYS_BRBTGTINJ_EL1		sys_reg(2, 1, 9, 1, 2)
+#define SYS_BRBTS_EL1			sys_reg(2, 1, 9, 0, 2)
+
+#define SYS_BRBCR_EL1			sys_reg(2, 1, 9, 0, 0)
+#define SYS_BRBFCR_EL1			sys_reg(2, 1, 9, 0, 1)
+#define SYS_BRBIDR0_EL1			sys_reg(2, 1, 9, 2, 0)
+
+#define SYS_TRCITECR_EL1		sys_reg(3, 0, 1, 2, 3)
+#define SYS_TRCACATR(m)			sys_reg(2, 1, 2, ((m & 7) << 1), (2 | (m >> 3)))
+#define SYS_TRCACVR(m)			sys_reg(2, 1, 2, ((m & 7) << 1), (0 | (m >> 3)))
+#define SYS_TRCAUTHSTATUS		sys_reg(2, 1, 7, 14, 6)
+#define SYS_TRCAUXCTLR			sys_reg(2, 1, 0, 6, 0)
+#define SYS_TRCBBCTLR			sys_reg(2, 1, 0, 15, 0)
+#define SYS_TRCCCCTLR			sys_reg(2, 1, 0, 14, 0)
+#define SYS_TRCCIDCCTLR0		sys_reg(2, 1, 3, 0, 2)
+#define SYS_TRCCIDCCTLR1		sys_reg(2, 1, 3, 1, 2)
+#define SYS_TRCCIDCVR(m)		sys_reg(2, 1, 3, ((m & 7) << 1), 0)
+#define SYS_TRCCLAIMCLR			sys_reg(2, 1, 7, 9, 6)
+#define SYS_TRCCLAIMSET			sys_reg(2, 1, 7, 8, 6)
+#define SYS_TRCCNTCTLR(m)		sys_reg(2, 1, 0, (4 | (m & 3)), 5)
+#define SYS_TRCCNTRLDVR(m)		sys_reg(2, 1, 0, (0 | (m & 3)), 5)
+#define SYS_TRCCNTVR(m)			sys_reg(2, 1, 0, (8 | (m & 3)), 5)
+#define SYS_TRCCONFIGR			sys_reg(2, 1, 0, 4, 0)
+#define SYS_TRCDEVARCH			sys_reg(2, 1, 7, 15, 6)
+#define SYS_TRCDEVID			sys_reg(2, 1, 7, 2, 7)
+#define SYS_TRCEVENTCTL0R		sys_reg(2, 1, 0, 8, 0)
+#define SYS_TRCEVENTCTL1R		sys_reg(2, 1, 0, 9, 0)
+#define SYS_TRCEXTINSELR(m)		sys_reg(2, 1, 0, (8 | (m & 3)), 4)
+#define SYS_TRCIDR0			sys_reg(2, 1, 0, 8, 7)
+#define SYS_TRCIDR10			sys_reg(2, 1, 0, 2, 6)
+#define SYS_TRCIDR11			sys_reg(2, 1, 0, 3, 6)
+#define SYS_TRCIDR12			sys_reg(2, 1, 0, 4, 6)
+#define SYS_TRCIDR13			sys_reg(2, 1, 0, 5, 6)
+#define SYS_TRCIDR1			sys_reg(2, 1, 0, 9, 7)
+#define SYS_TRCIDR2			sys_reg(2, 1, 0, 10, 7)
+#define SYS_TRCIDR3			sys_reg(2, 1, 0, 11, 7)
+#define SYS_TRCIDR4			sys_reg(2, 1, 0, 12, 7)
+#define SYS_TRCIDR5			sys_reg(2, 1, 0, 13, 7)
+#define SYS_TRCIDR6			sys_reg(2, 1, 0, 14, 7)
+#define SYS_TRCIDR7			sys_reg(2, 1, 0, 15, 7)
+#define SYS_TRCIDR8			sys_reg(2, 1, 0, 0, 6)
+#define SYS_TRCIDR9			sys_reg(2, 1, 0, 1, 6)
+#define SYS_TRCIMSPEC(m)		sys_reg(2, 1, 0, (m & 7), 7)
+#define SYS_TRCITEEDCR			sys_reg(2, 1, 0, 2, 1)
+#define SYS_TRCOSLSR			sys_reg(2, 1, 1, 1, 4)
+#define SYS_TRCPRGCTLR			sys_reg(2, 1, 0, 1, 0)
+#define SYS_TRCQCTLR			sys_reg(2, 1, 0, 1, 1)
+#define SYS_TRCRSCTLR(m)		sys_reg(2, 1, 1, (m & 15), (0 | (m >> 4)))
+#define SYS_TRCRSR			sys_reg(2, 1, 0, 10, 0)
+#define SYS_TRCSEQEVR(m)		sys_reg(2, 1, 0, (m & 3), 4)
+#define SYS_TRCSEQRSTEVR		sys_reg(2, 1, 0, 6, 4)
+#define SYS_TRCSEQSTR			sys_reg(2, 1, 0, 7, 4)
+#define SYS_TRCSSCCR(m)			sys_reg(2, 1, 1, (m & 7), 2)
+#define SYS_TRCSSCSR(m)			sys_reg(2, 1, 1, (8 | (m & 7)), 2)
+#define SYS_TRCSSPCICR(m)		sys_reg(2, 1, 1, (m & 7), 3)
+#define SYS_TRCSTALLCTLR		sys_reg(2, 1, 0, 11, 0)
+#define SYS_TRCSTATR			sys_reg(2, 1, 0, 3, 0)
+#define SYS_TRCSYNCPR			sys_reg(2, 1, 0, 13, 0)
+#define SYS_TRCTRACEIDR			sys_reg(2, 1, 0, 0, 1)
+#define SYS_TRCTSCTLR			sys_reg(2, 1, 0, 12, 0)
+#define SYS_TRCVICTLR			sys_reg(2, 1, 0, 0, 2)
+#define SYS_TRCVIIECTLR			sys_reg(2, 1, 0, 1, 2)
+#define SYS_TRCVIPCSSCTLR		sys_reg(2, 1, 0, 3, 2)
+#define SYS_TRCVISSCTLR			sys_reg(2, 1, 0, 2, 2)
+#define SYS_TRCVMIDCCTLR0		sys_reg(2, 1, 3, 2, 2)
+#define SYS_TRCVMIDCCTLR1		sys_reg(2, 1, 3, 3, 2)
+#define SYS_TRCVMIDCVR(m)		sys_reg(2, 1, 3, ((m & 7) << 1), 1)
+
+/* ETM */
+#define SYS_TRCOSLAR			sys_reg(2, 1, 1, 0, 4)
+
+#define SYS_BRBCR_EL2			sys_reg(2, 4, 9, 0, 0)
+
 #define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
 #define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
 #define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
@@ -170,8 +283,6 @@
 #define SYS_RGSR_EL1			sys_reg(3, 0, 1, 0, 5)
 #define SYS_GCR_EL1			sys_reg(3, 0, 1, 0, 6)
 
-#define SYS_TRFCR_EL1			sys_reg(3, 0, 1, 2, 1)
-
 #define SYS_TCR_EL1			sys_reg(3, 0, 2, 0, 2)
 
 #define SYS_APIAKEYLO_EL1		sys_reg(3, 0, 2, 1, 0)
@@ -202,15 +313,38 @@
 #define SYS_ERXCTLR_EL1			sys_reg(3, 0, 5, 4, 1)
 #define SYS_ERXSTATUS_EL1		sys_reg(3, 0, 5, 4, 2)
 #define SYS_ERXADDR_EL1			sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXPFGF_EL1			sys_reg(3, 0, 5, 4, 4)
+#define SYS_ERXPFGCTL_EL1		sys_reg(3, 0, 5, 4, 5)
+#define SYS_ERXPFGCDN_EL1		sys_reg(3, 0, 5, 4, 6)
 #define SYS_ERXMISC0_EL1		sys_reg(3, 0, 5, 5, 0)
 #define SYS_ERXMISC1_EL1		sys_reg(3, 0, 5, 5, 1)
+#define SYS_ERXMISC2_EL1		sys_reg(3, 0, 5, 5, 2)
+#define SYS_ERXMISC3_EL1		sys_reg(3, 0, 5, 5, 3)
 #define SYS_TFSR_EL1			sys_reg(3, 0, 5, 6, 0)
 #define SYS_TFSRE0_EL1			sys_reg(3, 0, 5, 6, 1)
 
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
 #define SYS_PAR_EL1_F			BIT(0)
+/* When PAR_EL1.F == 1 */
 #define SYS_PAR_EL1_FST			GENMASK(6, 1)
+#define SYS_PAR_EL1_PTW			BIT(8)
+#define SYS_PAR_EL1_S			BIT(9)
+#define SYS_PAR_EL1_AssuredOnly		BIT(12)
+#define SYS_PAR_EL1_TopLevel		BIT(13)
+#define SYS_PAR_EL1_Overlay		BIT(14)
+#define SYS_PAR_EL1_DirtyBit		BIT(15)
+#define SYS_PAR_EL1_F1_IMPDEF		GENMASK_ULL(63, 48)
+#define SYS_PAR_EL1_F1_RES0		(BIT(7) | BIT(10) | GENMASK_ULL(47, 16))
+#define SYS_PAR_EL1_RES1		BIT(11)
+/* When PAR_EL1.F == 0 */
+#define SYS_PAR_EL1_SH			GENMASK_ULL(8, 7)
+#define SYS_PAR_EL1_NS			BIT(9)
+#define SYS_PAR_EL1_F0_IMPDEF		BIT(10)
+#define SYS_PAR_EL1_NSE			BIT(11)
+#define SYS_PAR_EL1_PA			GENMASK_ULL(51, 12)
+#define SYS_PAR_EL1_ATTR		GENMASK_ULL(63, 56)
+#define SYS_PAR_EL1_F0_RES0		(GENMASK_ULL(6, 1) | GENMASK_ULL(55, 52))
 
 /*** Statistical Profiling Extension ***/
 #define PMSEVFR_EL1_RES0_IMP	\
@@ -274,6 +408,8 @@
 #define SYS_ICC_IGRPEN0_EL1		sys_reg(3, 0, 12, 12, 6)
 #define SYS_ICC_IGRPEN1_EL1		sys_reg(3, 0, 12, 12, 7)
 
+#define SYS_ACCDATA_EL1			sys_reg(3, 0, 13, 0, 5)
+
 #define SYS_CNTKCTL_EL1			sys_reg(3, 0, 14, 1, 0)
 
 #define SYS_AIDR_EL1			sys_reg(3, 1, 0, 0, 7)
@@ -286,7 +422,6 @@
 #define SYS_PMCNTENCLR_EL0		sys_reg(3, 3, 9, 12, 2)
 #define SYS_PMOVSCLR_EL0		sys_reg(3, 3, 9, 12, 3)
 #define SYS_PMSWINC_EL0			sys_reg(3, 3, 9, 12, 4)
-#define SYS_PMSELR_EL0			sys_reg(3, 3, 9, 12, 5)
 #define SYS_PMCEID0_EL0			sys_reg(3, 3, 9, 12, 6)
 #define SYS_PMCEID1_EL0			sys_reg(3, 3, 9, 12, 7)
 #define SYS_PMCCNTR_EL0			sys_reg(3, 3, 9, 13, 0)
@@ -369,6 +504,7 @@
 
 #define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
 #define SYS_ACTLR_EL2			sys_reg(3, 4, 1, 0, 1)
+#define SYS_SCTLR2_EL2			sys_reg(3, 4, 1, 0, 3)
 #define SYS_HCR_EL2			sys_reg(3, 4, 1, 1, 0)
 #define SYS_MDCR_EL2			sys_reg(3, 4, 1, 1, 1)
 #define SYS_CPTR_EL2			sys_reg(3, 4, 1, 1, 2)
@@ -381,13 +517,15 @@
 #define SYS_VTTBR_EL2			sys_reg(3, 4, 2, 1, 0)
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
-#define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
-#define SYS_HDFGRTR_EL2			sys_reg(3, 4, 3, 1, 4)
-#define SYS_HDFGWTR_EL2			sys_reg(3, 4, 3, 1, 5)
+#define SYS_VNCR_EL2			sys_reg(3, 4, 2, 2, 0)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
 #define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
+#define SYS_SPSR_irq			sys_reg(3, 4, 4, 3, 0)
+#define SYS_SPSR_abt			sys_reg(3, 4, 4, 3, 1)
+#define SYS_SPSR_und			sys_reg(3, 4, 4, 3, 2)
+#define SYS_SPSR_fiq			sys_reg(3, 4, 4, 3, 3)
 #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
 #define SYS_AFSR0_EL2			sys_reg(3, 4, 5, 1, 0)
 #define SYS_AFSR1_EL2			sys_reg(3, 4, 5, 1, 1)
@@ -449,24 +587,49 @@
 
 #define SYS_CONTEXTIDR_EL2		sys_reg(3, 4, 13, 0, 1)
 #define SYS_TPIDR_EL2			sys_reg(3, 4, 13, 0, 2)
+#define SYS_SCXTNUM_EL2			sys_reg(3, 4, 13, 0, 7)
+
+#define __AMEV_op2(m)			(m & 0x7)
+#define __AMEV_CRm(n, m)		(n | ((m & 0x8) >> 3))
+#define __SYS__AMEVCNTVOFF0n_EL2(m)	sys_reg(3, 4, 13, __AMEV_CRm(0x8, m), __AMEV_op2(m))
+#define SYS_AMEVCNTVOFF0n_EL2(m)	__SYS__AMEVCNTVOFF0n_EL2(m)
+#define __SYS__AMEVCNTVOFF1n_EL2(m)	sys_reg(3, 4, 13, __AMEV_CRm(0xA, m), __AMEV_op2(m))
+#define SYS_AMEVCNTVOFF1n_EL2(m)	__SYS__AMEVCNTVOFF1n_EL2(m)
 
 #define SYS_CNTVOFF_EL2			sys_reg(3, 4, 14, 0, 3)
 #define SYS_CNTHCTL_EL2			sys_reg(3, 4, 14, 1, 0)
+#define SYS_CNTHP_TVAL_EL2		sys_reg(3, 4, 14, 2, 0)
+#define SYS_CNTHP_CTL_EL2		sys_reg(3, 4, 14, 2, 1)
+#define SYS_CNTHP_CVAL_EL2		sys_reg(3, 4, 14, 2, 2)
+#define SYS_CNTHV_TVAL_EL2		sys_reg(3, 4, 14, 3, 0)
+#define SYS_CNTHV_CTL_EL2		sys_reg(3, 4, 14, 3, 1)
+#define SYS_CNTHV_CVAL_EL2		sys_reg(3, 4, 14, 3, 2)
 
 /* VHE encodings for architectural EL0/1 system registers */
+#define SYS_BRBCR_EL12			sys_reg(2, 5, 9, 0, 0)
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
+#define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
+#define SYS_SCTLR2_EL12			sys_reg(3, 5, 1, 0, 3)
+#define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
+#define SYS_TRFCR_EL12			sys_reg(3, 5, 1, 2, 1)
+#define SYS_SMCR_EL12			sys_reg(3, 5, 1, 2, 6)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
 #define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
+#define SYS_TCR2_EL12			sys_reg(3, 5, 2, 0, 3)
 #define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
 #define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
 #define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
+#define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
+#define SYS_PMSCR_EL12			sys_reg(3, 5, 9, 9, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
 #define SYS_VBAR_EL12			sys_reg(3, 5, 12, 0, 0)
+#define SYS_CONTEXTIDR_EL12		sys_reg(3, 5, 13, 0, 1)
+#define SYS_SCXTNUM_EL12		sys_reg(3, 5, 13, 0, 7)
 #define SYS_CNTKCTL_EL12		sys_reg(3, 5, 14, 1, 0)
 #define SYS_CNTP_TVAL_EL02		sys_reg(3, 5, 14, 2, 0)
 #define SYS_CNTP_CTL_EL02		sys_reg(3, 5, 14, 2, 1)
@@ -477,6 +640,183 @@
 
 #define SYS_SP_EL2			sys_reg(3, 6,  4, 1, 0)
 
+/* AT instructions */
+#define AT_Op0 1
+#define AT_CRn 7
+
+#define OP_AT_S1E1R	sys_insn(AT_Op0, 0, AT_CRn, 8, 0)
+#define OP_AT_S1E1W	sys_insn(AT_Op0, 0, AT_CRn, 8, 1)
+#define OP_AT_S1E0R	sys_insn(AT_Op0, 0, AT_CRn, 8, 2)
+#define OP_AT_S1E0W	sys_insn(AT_Op0, 0, AT_CRn, 8, 3)
+#define OP_AT_S1E1RP	sys_insn(AT_Op0, 0, AT_CRn, 9, 0)
+#define OP_AT_S1E1WP	sys_insn(AT_Op0, 0, AT_CRn, 9, 1)
+#define OP_AT_S1E1A	sys_insn(AT_Op0, 0, AT_CRn, 9, 2)
+#define OP_AT_S1E2R	sys_insn(AT_Op0, 4, AT_CRn, 8, 0)
+#define OP_AT_S1E2W	sys_insn(AT_Op0, 4, AT_CRn, 8, 1)
+#define OP_AT_S12E1R	sys_insn(AT_Op0, 4, AT_CRn, 8, 4)
+#define OP_AT_S12E1W	sys_insn(AT_Op0, 4, AT_CRn, 8, 5)
+#define OP_AT_S12E0R	sys_insn(AT_Op0, 4, AT_CRn, 8, 6)
+#define OP_AT_S12E0W	sys_insn(AT_Op0, 4, AT_CRn, 8, 7)
+#define OP_AT_S1E2A	sys_insn(AT_Op0, 4, AT_CRn, 9, 2)
+
+/* TLBI instructions */
+#define TLBI_Op0	1
+
+#define TLBI_Op1_EL1	0	/* Accessible from EL1 or higher */
+#define TLBI_Op1_EL2	4	/* Accessible from EL2 or higher */
+
+#define TLBI_CRn_XS	8	/* Extra Slow (the common one) */
+#define TLBI_CRn_nXS	9	/* not Extra Slow (which nobody uses)*/
+
+#define TLBI_CRm_IPAIS	0	/* S2 Inner-Shareable */
+#define TLBI_CRm_nROS	1	/* non-Range, Outer-Sharable */
+#define TLBI_CRm_RIS	2	/* Range, Inner-Sharable */
+#define TLBI_CRm_nRIS	3	/* non-Range, Inner-Sharable */
+#define TLBI_CRm_IPAONS	4	/* S2 Outer and Non-Shareable */
+#define TLBI_CRm_ROS	5	/* Range, Outer-Sharable */
+#define TLBI_CRm_RNS	6	/* Range, Non-Sharable */
+#define TLBI_CRm_nRNS	7	/* non-Range, Non-Sharable */
+
+#define OP_TLBI_VMALLE1OS		sys_insn(1, 0, 8, 1, 0)
+#define OP_TLBI_VAE1OS			sys_insn(1, 0, 8, 1, 1)
+#define OP_TLBI_ASIDE1OS		sys_insn(1, 0, 8, 1, 2)
+#define OP_TLBI_VAAE1OS			sys_insn(1, 0, 8, 1, 3)
+#define OP_TLBI_VALE1OS			sys_insn(1, 0, 8, 1, 5)
+#define OP_TLBI_VAALE1OS		sys_insn(1, 0, 8, 1, 7)
+#define OP_TLBI_RVAE1IS			sys_insn(1, 0, 8, 2, 1)
+#define OP_TLBI_RVAAE1IS		sys_insn(1, 0, 8, 2, 3)
+#define OP_TLBI_RVALE1IS		sys_insn(1, 0, 8, 2, 5)
+#define OP_TLBI_RVAALE1IS		sys_insn(1, 0, 8, 2, 7)
+#define OP_TLBI_VMALLE1IS		sys_insn(1, 0, 8, 3, 0)
+#define OP_TLBI_VAE1IS			sys_insn(1, 0, 8, 3, 1)
+#define OP_TLBI_ASIDE1IS		sys_insn(1, 0, 8, 3, 2)
+#define OP_TLBI_VAAE1IS			sys_insn(1, 0, 8, 3, 3)
+#define OP_TLBI_VALE1IS			sys_insn(1, 0, 8, 3, 5)
+#define OP_TLBI_VAALE1IS		sys_insn(1, 0, 8, 3, 7)
+#define OP_TLBI_RVAE1OS			sys_insn(1, 0, 8, 5, 1)
+#define OP_TLBI_RVAAE1OS		sys_insn(1, 0, 8, 5, 3)
+#define OP_TLBI_RVALE1OS		sys_insn(1, 0, 8, 5, 5)
+#define OP_TLBI_RVAALE1OS		sys_insn(1, 0, 8, 5, 7)
+#define OP_TLBI_RVAE1			sys_insn(1, 0, 8, 6, 1)
+#define OP_TLBI_RVAAE1			sys_insn(1, 0, 8, 6, 3)
+#define OP_TLBI_RVALE1			sys_insn(1, 0, 8, 6, 5)
+#define OP_TLBI_RVAALE1			sys_insn(1, 0, 8, 6, 7)
+#define OP_TLBI_VMALLE1			sys_insn(1, 0, 8, 7, 0)
+#define OP_TLBI_VAE1			sys_insn(1, 0, 8, 7, 1)
+#define OP_TLBI_ASIDE1			sys_insn(1, 0, 8, 7, 2)
+#define OP_TLBI_VAAE1			sys_insn(1, 0, 8, 7, 3)
+#define OP_TLBI_VALE1			sys_insn(1, 0, 8, 7, 5)
+#define OP_TLBI_VAALE1			sys_insn(1, 0, 8, 7, 7)
+#define OP_TLBI_VMALLE1OSNXS		sys_insn(1, 0, 9, 1, 0)
+#define OP_TLBI_VAE1OSNXS		sys_insn(1, 0, 9, 1, 1)
+#define OP_TLBI_ASIDE1OSNXS		sys_insn(1, 0, 9, 1, 2)
+#define OP_TLBI_VAAE1OSNXS		sys_insn(1, 0, 9, 1, 3)
+#define OP_TLBI_VALE1OSNXS		sys_insn(1, 0, 9, 1, 5)
+#define OP_TLBI_VAALE1OSNXS		sys_insn(1, 0, 9, 1, 7)
+#define OP_TLBI_RVAE1ISNXS		sys_insn(1, 0, 9, 2, 1)
+#define OP_TLBI_RVAAE1ISNXS		sys_insn(1, 0, 9, 2, 3)
+#define OP_TLBI_RVALE1ISNXS		sys_insn(1, 0, 9, 2, 5)
+#define OP_TLBI_RVAALE1ISNXS		sys_insn(1, 0, 9, 2, 7)
+#define OP_TLBI_VMALLE1ISNXS		sys_insn(1, 0, 9, 3, 0)
+#define OP_TLBI_VAE1ISNXS		sys_insn(1, 0, 9, 3, 1)
+#define OP_TLBI_ASIDE1ISNXS		sys_insn(1, 0, 9, 3, 2)
+#define OP_TLBI_VAAE1ISNXS		sys_insn(1, 0, 9, 3, 3)
+#define OP_TLBI_VALE1ISNXS		sys_insn(1, 0, 9, 3, 5)
+#define OP_TLBI_VAALE1ISNXS		sys_insn(1, 0, 9, 3, 7)
+#define OP_TLBI_RVAE1OSNXS		sys_insn(1, 0, 9, 5, 1)
+#define OP_TLBI_RVAAE1OSNXS		sys_insn(1, 0, 9, 5, 3)
+#define OP_TLBI_RVALE1OSNXS		sys_insn(1, 0, 9, 5, 5)
+#define OP_TLBI_RVAALE1OSNXS		sys_insn(1, 0, 9, 5, 7)
+#define OP_TLBI_RVAE1NXS		sys_insn(1, 0, 9, 6, 1)
+#define OP_TLBI_RVAAE1NXS		sys_insn(1, 0, 9, 6, 3)
+#define OP_TLBI_RVALE1NXS		sys_insn(1, 0, 9, 6, 5)
+#define OP_TLBI_RVAALE1NXS		sys_insn(1, 0, 9, 6, 7)
+#define OP_TLBI_VMALLE1NXS		sys_insn(1, 0, 9, 7, 0)
+#define OP_TLBI_VAE1NXS			sys_insn(1, 0, 9, 7, 1)
+#define OP_TLBI_ASIDE1NXS		sys_insn(1, 0, 9, 7, 2)
+#define OP_TLBI_VAAE1NXS		sys_insn(1, 0, 9, 7, 3)
+#define OP_TLBI_VALE1NXS		sys_insn(1, 0, 9, 7, 5)
+#define OP_TLBI_VAALE1NXS		sys_insn(1, 0, 9, 7, 7)
+#define OP_TLBI_IPAS2E1IS		sys_insn(1, 4, 8, 0, 1)
+#define OP_TLBI_RIPAS2E1IS		sys_insn(1, 4, 8, 0, 2)
+#define OP_TLBI_IPAS2LE1IS		sys_insn(1, 4, 8, 0, 5)
+#define OP_TLBI_RIPAS2LE1IS		sys_insn(1, 4, 8, 0, 6)
+#define OP_TLBI_ALLE2OS			sys_insn(1, 4, 8, 1, 0)
+#define OP_TLBI_VAE2OS			sys_insn(1, 4, 8, 1, 1)
+#define OP_TLBI_ALLE1OS			sys_insn(1, 4, 8, 1, 4)
+#define OP_TLBI_VALE2OS			sys_insn(1, 4, 8, 1, 5)
+#define OP_TLBI_VMALLS12E1OS		sys_insn(1, 4, 8, 1, 6)
+#define OP_TLBI_RVAE2IS			sys_insn(1, 4, 8, 2, 1)
+#define OP_TLBI_RVALE2IS		sys_insn(1, 4, 8, 2, 5)
+#define OP_TLBI_ALLE2IS			sys_insn(1, 4, 8, 3, 0)
+#define OP_TLBI_VAE2IS			sys_insn(1, 4, 8, 3, 1)
+#define OP_TLBI_ALLE1IS			sys_insn(1, 4, 8, 3, 4)
+#define OP_TLBI_VALE2IS			sys_insn(1, 4, 8, 3, 5)
+#define OP_TLBI_VMALLS12E1IS		sys_insn(1, 4, 8, 3, 6)
+#define OP_TLBI_IPAS2E1OS		sys_insn(1, 4, 8, 4, 0)
+#define OP_TLBI_IPAS2E1			sys_insn(1, 4, 8, 4, 1)
+#define OP_TLBI_RIPAS2E1		sys_insn(1, 4, 8, 4, 2)
+#define OP_TLBI_RIPAS2E1OS		sys_insn(1, 4, 8, 4, 3)
+#define OP_TLBI_IPAS2LE1OS		sys_insn(1, 4, 8, 4, 4)
+#define OP_TLBI_IPAS2LE1		sys_insn(1, 4, 8, 4, 5)
+#define OP_TLBI_RIPAS2LE1		sys_insn(1, 4, 8, 4, 6)
+#define OP_TLBI_RIPAS2LE1OS		sys_insn(1, 4, 8, 4, 7)
+#define OP_TLBI_RVAE2OS			sys_insn(1, 4, 8, 5, 1)
+#define OP_TLBI_RVALE2OS		sys_insn(1, 4, 8, 5, 5)
+#define OP_TLBI_RVAE2			sys_insn(1, 4, 8, 6, 1)
+#define OP_TLBI_RVALE2			sys_insn(1, 4, 8, 6, 5)
+#define OP_TLBI_ALLE2			sys_insn(1, 4, 8, 7, 0)
+#define OP_TLBI_VAE2			sys_insn(1, 4, 8, 7, 1)
+#define OP_TLBI_ALLE1			sys_insn(1, 4, 8, 7, 4)
+#define OP_TLBI_VALE2			sys_insn(1, 4, 8, 7, 5)
+#define OP_TLBI_VMALLS12E1		sys_insn(1, 4, 8, 7, 6)
+#define OP_TLBI_IPAS2E1ISNXS		sys_insn(1, 4, 9, 0, 1)
+#define OP_TLBI_RIPAS2E1ISNXS		sys_insn(1, 4, 9, 0, 2)
+#define OP_TLBI_IPAS2LE1ISNXS		sys_insn(1, 4, 9, 0, 5)
+#define OP_TLBI_RIPAS2LE1ISNXS		sys_insn(1, 4, 9, 0, 6)
+#define OP_TLBI_ALLE2OSNXS		sys_insn(1, 4, 9, 1, 0)
+#define OP_TLBI_VAE2OSNXS		sys_insn(1, 4, 9, 1, 1)
+#define OP_TLBI_ALLE1OSNXS		sys_insn(1, 4, 9, 1, 4)
+#define OP_TLBI_VALE2OSNXS		sys_insn(1, 4, 9, 1, 5)
+#define OP_TLBI_VMALLS12E1OSNXS		sys_insn(1, 4, 9, 1, 6)
+#define OP_TLBI_RVAE2ISNXS		sys_insn(1, 4, 9, 2, 1)
+#define OP_TLBI_RVALE2ISNXS		sys_insn(1, 4, 9, 2, 5)
+#define OP_TLBI_ALLE2ISNXS		sys_insn(1, 4, 9, 3, 0)
+#define OP_TLBI_VAE2ISNXS		sys_insn(1, 4, 9, 3, 1)
+#define OP_TLBI_ALLE1ISNXS		sys_insn(1, 4, 9, 3, 4)
+#define OP_TLBI_VALE2ISNXS		sys_insn(1, 4, 9, 3, 5)
+#define OP_TLBI_VMALLS12E1ISNXS		sys_insn(1, 4, 9, 3, 6)
+#define OP_TLBI_IPAS2E1OSNXS		sys_insn(1, 4, 9, 4, 0)
+#define OP_TLBI_IPAS2E1NXS		sys_insn(1, 4, 9, 4, 1)
+#define OP_TLBI_RIPAS2E1NXS		sys_insn(1, 4, 9, 4, 2)
+#define OP_TLBI_RIPAS2E1OSNXS		sys_insn(1, 4, 9, 4, 3)
+#define OP_TLBI_IPAS2LE1OSNXS		sys_insn(1, 4, 9, 4, 4)
+#define OP_TLBI_IPAS2LE1NXS		sys_insn(1, 4, 9, 4, 5)
+#define OP_TLBI_RIPAS2LE1NXS		sys_insn(1, 4, 9, 4, 6)
+#define OP_TLBI_RIPAS2LE1OSNXS		sys_insn(1, 4, 9, 4, 7)
+#define OP_TLBI_RVAE2OSNXS		sys_insn(1, 4, 9, 5, 1)
+#define OP_TLBI_RVALE2OSNXS		sys_insn(1, 4, 9, 5, 5)
+#define OP_TLBI_RVAE2NXS		sys_insn(1, 4, 9, 6, 1)
+#define OP_TLBI_RVALE2NXS		sys_insn(1, 4, 9, 6, 5)
+#define OP_TLBI_ALLE2NXS		sys_insn(1, 4, 9, 7, 0)
+#define OP_TLBI_VAE2NXS			sys_insn(1, 4, 9, 7, 1)
+#define OP_TLBI_ALLE1NXS		sys_insn(1, 4, 9, 7, 4)
+#define OP_TLBI_VALE2NXS		sys_insn(1, 4, 9, 7, 5)
+#define OP_TLBI_VMALLS12E1NXS		sys_insn(1, 4, 9, 7, 6)
+
+/* Misc instructions */
+#define OP_GCSPUSHX			sys_insn(1, 0, 7, 7, 4)
+#define OP_GCSPOPCX			sys_insn(1, 0, 7, 7, 5)
+#define OP_GCSPOPX			sys_insn(1, 0, 7, 7, 6)
+#define OP_GCSPUSHM			sys_insn(1, 3, 7, 7, 0)
+
+#define OP_BRB_IALL			sys_insn(1, 1, 7, 2, 4)
+#define OP_BRB_INJ			sys_insn(1, 1, 7, 2, 5)
+#define OP_CFP_RCTX			sys_insn(1, 3, 7, 3, 4)
+#define OP_DVP_RCTX			sys_insn(1, 3, 7, 3, 5)
+#define OP_COSP_RCTX			sys_insn(1, 3, 7, 3, 6)
+#define OP_CPP_RCTX			sys_insn(1, 3, 7, 3, 7)
+
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_ENTP2	(BIT(60))
 #define SCTLR_ELx_DSSBS	(BIT(44))
@@ -555,16 +895,14 @@
 /* Position the attr at the correct index */
 #define MAIR_ATTRIDX(attr, idx)		((attr) << ((idx) * 8))
 
-/* id_aa64pfr0 */
-#define ID_AA64PFR0_EL1_ELx_64BIT_ONLY		0x1
-#define ID_AA64PFR0_EL1_ELx_32BIT_64BIT		0x2
-
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN	0x0
+#define ID_AA64MMFR0_EL1_TGRAN4_LPA2		ID_AA64MMFR0_EL1_TGRAN4_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX	0x7
 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN	0x0
 #define ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX	0x7
 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN	0x1
+#define ID_AA64MMFR0_EL1_TGRAN16_LPA2		ID_AA64MMFR0_EL1_TGRAN16_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX	0xf
 
 #define ARM64_MIN_PARANGE_BITS		32
@@ -572,6 +910,7 @@
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT	0x0
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE		0x1
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN		0x2
+#define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2		0x3
 #define ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX		0x7
 
 #ifdef CONFIG_ARM64_PA_BITS_52
@@ -582,11 +921,13 @@
 
 #if defined(CONFIG_ARM64_4K_PAGES)
 #define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_LPA2		ID_AA64MMFR0_EL1_TGRAN4_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX
 #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT
 #elif defined(CONFIG_ARM64_16K_PAGES)
 #define ID_AA64MMFR0_EL1_TGRAN_SHIFT		ID_AA64MMFR0_EL1_TGRAN16_SHIFT
+#define ID_AA64MMFR0_EL1_TGRAN_LPA2		ID_AA64MMFR0_EL1_TGRAN16_52_BIT
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN	ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN
 #define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX	ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX
 #define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT		ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT
@@ -610,6 +951,19 @@
 #define SYS_GCR_EL1_RRND	(BIT(16))
 #define SYS_GCR_EL1_EXCL_MASK	0xffffUL
 
+#ifdef CONFIG_KASAN_HW_TAGS
+/*
+ * KASAN always uses a whole byte for its tags. With CONFIG_KASAN_HW_TAGS it
+ * only uses tags in the range 0xF0-0xFF, which we map to MTE tags 0x0-0xF.
+ */
+#define __MTE_TAG_MIN		(KASAN_TAG_MIN & 0xf)
+#define __MTE_TAG_MAX		(KASAN_TAG_MAX & 0xf)
+#define __MTE_TAG_INCL		GENMASK(__MTE_TAG_MAX, __MTE_TAG_MIN)
+#define KERNEL_GCR_EL1_EXCL	(SYS_GCR_EL1_EXCL_MASK & ~__MTE_TAG_INCL)
+#else
+#define KERNEL_GCR_EL1_EXCL	SYS_GCR_EL1_EXCL_MASK
+#endif
+
 #define KERNEL_GCR_EL1		(SYS_GCR_EL1_RRND | KERNEL_GCR_EL1_EXCL)
 
 /* RGSR_EL1 Definitions */
@@ -626,15 +980,6 @@
 /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
 #define SYS_MPIDR_SAFE_VAL	(BIT(31))
 
-#define TRFCR_ELx_TS_SHIFT		5
-#define TRFCR_ELx_TS_MASK		((0x3UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_ELx_TS_VIRTUAL		((0x1UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_ELx_TS_GUEST_PHYSICAL	((0x2UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_ELx_TS_PHYSICAL		((0x3UL) << TRFCR_ELx_TS_SHIFT)
-#define TRFCR_EL2_CX			BIT(3)
-#define TRFCR_ELx_ExTRE			BIT(1)
-#define TRFCR_ELx_E0TRE			BIT(0)
-
 /* GIC Hypervisor interface registers */
 /* ICH_MISR_EL2 bit definitions */
 #define ICH_MISR_EOI		(1 << 0)
@@ -716,6 +1061,22 @@
 
 #define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
 
+/*
+ * Permission Overlay Extension (POE) permission encodings.
+ */
+#define POE_NONE	UL(0x0)
+#define POE_R		UL(0x1)
+#define POE_X		UL(0x2)
+#define POE_RX		UL(0x3)
+#define POE_W		UL(0x4)
+#define POE_RW		UL(0x5)
+#define POE_XW		UL(0x6)
+#define POE_RXW		UL(0x7)
+#define POE_MASK	UL(0xf)
+
+/* Initial value for Permission Overlay Extension for EL0 */
+#define POR_EL0_INIT	POE_RXW
+
 #define ARM64_FEATURE_FIELD_BITS	4
 
 /* Defined for compatibility only, do not add new users. */
@@ -789,15 +1150,21 @@
 /*
  * For registers without architectural names, or simply unsupported by
  * GAS.
+ *
+ * __check_r forces warnings to be generated by the compiler when
+ * evaluating r which wouldn't normally happen due to being passed to
+ * the assembler via __stringify(r).
  */
 #define read_sysreg_s(r) ({						\
 	u64 __val;							\
+	u32 __maybe_unused __check_r = (u32)(r);			\
 	asm volatile(__mrs_s("%0", r) : "=r" (__val));			\
 	__val;								\
 })
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)(v);						\
+	u32 __maybe_unused __check_r = (u32)(r);			\
 	asm volatile(__msr_s(r, "%x0") : : "rZ" (__val));		\
 } while (0)
 
@@ -827,6 +1194,8 @@
 	par;								\
 })
 
+#define SYS_FIELD_VALUE(reg, field, val)	reg##_##field##_##val
+
 #define SYS_FIELD_GET(reg, field, val)		\
 		 FIELD_GET(reg##_##field##_MASK, val)
 
@@ -834,7 +1203,8 @@
 		 FIELD_PREP(reg##_##field##_MASK, val)
 
 #define SYS_FIELD_PREP_ENUM(reg, field, val)		\
-		 FIELD_PREP(reg##_##field##_MASK, reg##_##field##_##val)
+		 FIELD_PREP(reg##_##field##_MASK,	\
+			    SYS_FIELD_VALUE(reg, field, val))
 
 #endif
 
diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 156b62a163c5..8a48cc2536f5 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -226,7 +226,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	/* Wrong Checksum */
 	rcsum = xbc_calc_checksum(*buf, size);
 	if (csum != rcsum) {
-		pr_err("checksum error: %d != %d\n", csum, rcsum);
+		pr_err("checksum error: %u != %u\n", csum, rcsum);
 		return -EINVAL;
 	}
 
@@ -395,7 +395,7 @@ static int apply_xbc(const char *path, const char *xbc_path)
 	xbc_get_info(&ret, NULL);
 	printf("\tNumber of nodes: %d\n", ret);
 	printf("\tSize: %u bytes\n", (unsigned int)size);
-	printf("\tChecksum: %d\n", (unsigned int)csum);
+	printf("\tChecksum: %u\n", (unsigned int)csum);
 
 	/* TODO: Check the options by schema */
 	xbc_exit();
diff --git a/tools/include/linux/kasan-tags.h b/tools/include/linux/kasan-tags.h
new file mode 100644
index 000000000000..4f85f562512c
--- /dev/null
+++ b/tools/include/linux/kasan-tags.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KASAN_TAGS_H
+#define _LINUX_KASAN_TAGS_H
+
+#define KASAN_TAG_KERNEL	0xFF /* native kernel pointers tag */
+#define KASAN_TAG_INVALID	0xFE /* inaccessible memory tag */
+#define KASAN_TAG_MAX		0xFD /* maximum value for random tags */
+
+#ifdef CONFIG_KASAN_HW_TAGS
+#define KASAN_TAG_MIN		0xF0 /* minimum value for random tags */
+#else
+#define KASAN_TAG_MIN		0x00 /* minimum value for random tags */
+#endif
+
+#endif /* LINUX_KASAN_TAGS_H */
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index e16cef160bc2..ce32cb35007d 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -95,7 +95,7 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off,
 
 	ynl_attr_for_each_payload(start, data_len, attr) {
 		astart_off = (char *)attr - (char *)start;
-		aend_off = astart_off + ynl_attr_data_len(attr);
+		aend_off = (char *)ynl_attr_data_end(attr) - (char *)start;
 		if (aend_off <= off)
 			continue;
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d7c7d29291fb..d466447ae928 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2107,8 +2107,12 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 		return PTR_ERR(sc->tp_format);
 	}
 
+	/*
+	 * The tracepoint format contains __syscall_nr field, so it's one more
+	 * than the actual number of syscall arguments.
+	 */
 	if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ?
-					RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields))
+					RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields - 1))
 		return -ENOMEM;
 
 	sc->args = sc->tp_format->format.fields;
diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh
index 5a3b8a5a9b5c..8d1e6bbeac90 100755
--- a/tools/perf/tests/shell/trace_btf_enum.sh
+++ b/tools/perf/tests/shell/trace_btf_enum.sh
@@ -26,8 +26,12 @@ check_vmlinux() {
 trace_landlock() {
   echo "Tracing syscall ${syscall}"
 
-  # test flight just to see if landlock_add_rule and libbpf are available
-  $TESTPROG
+  # test flight just to see if landlock_add_rule is available
+  if ! perf trace $TESTPROG 2>&1 | grep -q landlock
+  then
+    echo "No landlock system call found, skipping to non-syscall tracing."
+    return
+  fi
 
   if perf trace -e $syscall $TESTPROG 2>&1 | \
      grep -q -E ".*landlock_add_rule\(ruleset_fd: 11, rule_type: (LANDLOCK_RULE_PATH_BENEATH|LANDLOCK_RULE_NET_PORT), rule_attr: 0x[a-f0-9]+, flags: 45\) = -1.*"
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0d2ea22bd9e4..31bb326b07a6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2100,6 +2100,57 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	return 0;
 }
 
+const char * const perf_disassembler__strs[] = {
+	[PERF_DISASM_UNKNOWN]  = "unknown",
+	[PERF_DISASM_LLVM]     = "llvm",
+	[PERF_DISASM_CAPSTONE] = "capstone",
+	[PERF_DISASM_OBJDUMP]  = "objdump",
+};
+
+
+static void annotation_options__add_disassembler(struct annotation_options *options,
+						 enum perf_disassembler dis)
+{
+	for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers); i++) {
+		if (options->disassemblers[i] == dis) {
+			/* Disassembler is already present then don't add again. */
+			return;
+		}
+		if (options->disassemblers[i] == PERF_DISASM_UNKNOWN) {
+			/* Found a free slot. */
+			options->disassemblers[i] = dis;
+			return;
+		}
+	}
+	pr_err("Failed to add disassembler %d\n", dis);
+}
+
+static int annotation_options__add_disassemblers_str(struct annotation_options *options,
+						const char *str)
+{
+	while (str && *str != '\0') {
+		const char *comma = strchr(str, ',');
+		int len = comma ? comma - str : (int)strlen(str);
+		bool match = false;
+
+		for (u8 i = 0; i < ARRAY_SIZE(perf_disassembler__strs); i++) {
+			const char *dis_str = perf_disassembler__strs[i];
+
+			if (len == (int)strlen(dis_str) && !strncmp(str, dis_str, len)) {
+				annotation_options__add_disassembler(options, i);
+				match = true;
+				break;
+			}
+		}
+		if (!match) {
+			pr_err("Invalid disassembler '%.*s'\n", len, str);
+			return -1;
+		}
+		str = comma ? comma + 1 : NULL;
+	}
+	return 0;
+}
+
 static int annotation__config(const char *var, const char *value, void *data)
 {
 	struct annotation_options *opt = data;
@@ -2115,11 +2166,10 @@ static int annotation__config(const char *var, const char *value, void *data)
 		else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL)
 			opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
 	} else if (!strcmp(var, "annotate.disassemblers")) {
-		opt->disassemblers_str = strdup(value);
-		if (!opt->disassemblers_str) {
-			pr_err("Not enough memory for annotate.disassemblers\n");
-			return -1;
-		}
+		int err = annotation_options__add_disassemblers_str(opt, value);
+
+		if (err)
+			return err;
 	} else if (!strcmp(var, "annotate.hide_src_code")) {
 		opt->hide_src_code = perf_config_bool("hide_src_code", value);
 	} else if (!strcmp(var, "annotate.jump_arrows")) {
@@ -2185,9 +2235,25 @@ void annotation_options__exit(void)
 	zfree(&annotate_opts.objdump_path);
 }
 
+static void annotation_options__default_init_disassemblers(struct annotation_options *options)
+{
+	if (options->disassemblers[0] != PERF_DISASM_UNKNOWN) {
+		/* Already initialized. */
+		return;
+	}
+#ifdef HAVE_LIBLLVM_SUPPORT
+	annotation_options__add_disassembler(options, PERF_DISASM_LLVM);
+#endif
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	annotation_options__add_disassembler(options, PERF_DISASM_CAPSTONE);
+#endif
+	annotation_options__add_disassembler(options, PERF_DISASM_OBJDUMP);
+}
+
 void annotation_config__init(void)
 {
 	perf_config(annotation__config, &annotate_opts);
+	annotation_options__default_init_disassemblers(&annotate_opts);
 }
 
 static unsigned int parse_percent_type(char *str1, char *str2)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 0ba5846dad4d..98db1b88daf4 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -34,8 +34,13 @@ struct annotated_data_type;
 #define ANNOTATION__BR_CNTR_WIDTH 30
 #define ANNOTATION_DUMMY_LEN	256
 
-// llvm, capstone, objdump
-#define MAX_DISASSEMBLERS 3
+enum perf_disassembler {
+	PERF_DISASM_UNKNOWN = 0,
+	PERF_DISASM_LLVM,
+	PERF_DISASM_CAPSTONE,
+	PERF_DISASM_OBJDUMP,
+};
+#define MAX_DISASSEMBLERS (PERF_DISASM_OBJDUMP + 1)
 
 struct annotation_options {
 	bool hide_src_code,
@@ -52,14 +57,12 @@ struct annotation_options {
 	     annotate_src,
 	     full_addr;
 	u8   offset_level;
-	u8   nr_disassemblers;
+	u8   disassemblers[MAX_DISASSEMBLERS];
 	int  min_pcnt;
 	int  max_lines;
 	int  context;
 	char *objdump_path;
 	char *disassembler_style;
-	const char *disassemblers_str;
-	const char *disassemblers[MAX_DISASSEMBLERS];
 	const char *prefix;
 	const char *prefix_strip;
 	unsigned int percent_type;
@@ -134,6 +137,8 @@ struct disasm_line {
 	struct annotation_line	 al;
 };
 
+extern const char * const perf_disassembler__strs[];
+
 void annotation_line__add(struct annotation_line *al, struct list_head *head);
 
 static inline double annotation_data__percent(struct annotation_data *data,
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 4a62ed593e84..e4352881e3fa 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid)
 static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
 {
 	bool augmented, do_output = false;
-	int zero = 0, size, aug_size, index,
-	    value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
+	int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value);
 	u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */
+	s64 aug_size, size;
 	unsigned int nr, *beauty_map;
 	struct beauty_payload_enter *payload;
 	void *arg, *payload_offset;
@@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args)
 		} else if (size > 0 && size <= value_size) { /* struct */
 			if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg))
 				augmented = true;
-		} else if (size < 0 && size >= -6) { /* buffer */
+		} else if ((int)size < 0 && size >= -6) { /* buffer */
 			index = -(size + 1);
 			barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick.
 			index &= 7;	    // Satisfy the bounds checking with the verifier in some kernels.
-			aug_size = args->args[index];
-
-			if (aug_size > TRACE_AUG_MAX_BUF)
-				aug_size = TRACE_AUG_MAX_BUF;
+			aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index];
 
 			if (aug_size > 0) {
 				if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg))
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 27094211edd8..5c329ad614e9 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -293,7 +293,7 @@ struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data)
 
 	die = cpu__get_die_id(cpu);
 	/* There is no die_id on legacy system. */
-	if (die == -1)
+	if (die < 0)
 		die = 0;
 
 	/*
@@ -322,7 +322,7 @@ struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data)
 	struct aggr_cpu_id id;
 
 	/* There is no cluster_id on legacy system. */
-	if (cluster == -1)
+	if (cluster < 0)
 		cluster = 0;
 
 	id = aggr_cpu_id__die(cpu, data);
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index b7de4d9fd004..50c5c206b70e 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -2216,56 +2216,6 @@ out_free_command:
 	return err;
 }
 
-static int annotation_options__init_disassemblers(struct annotation_options *options)
-{
-	char *disassembler;
-
-	if (options->disassemblers_str == NULL) {
-		const char *default_disassemblers_str =
-#ifdef HAVE_LIBLLVM_SUPPORT
-				"llvm,"
-#endif
-#ifdef HAVE_LIBCAPSTONE_SUPPORT
-				"capstone,"
-#endif
-				"objdump";
-
-		options->disassemblers_str = strdup(default_disassemblers_str);
-		if (!options->disassemblers_str)
-			goto out_enomem;
-	}
-
-	disassembler = strdup(options->disassemblers_str);
-	if (disassembler == NULL)
-		goto out_enomem;
-
-	while (1) {
-		char *comma = strchr(disassembler, ',');
-
-		if (comma != NULL)
-			*comma = '\0';
-
-		options->disassemblers[options->nr_disassemblers++] = strim(disassembler);
-
-		if (comma == NULL)
-			break;
-
-		disassembler = comma + 1;
-
-		if (options->nr_disassemblers >= MAX_DISASSEMBLERS) {
-			pr_debug("annotate.disassemblers can have at most %d entries, ignoring \"%s\"\n",
-				 MAX_DISASSEMBLERS, disassembler);
-			break;
-		}
-	}
-
-	return 0;
-
-out_enomem:
-	pr_err("Not enough memory for annotate.disassemblers\n");
-	return -1;
-}
-
 int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
 	struct annotation_options *options = args->options;
@@ -2274,7 +2224,6 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	char symfs_filename[PATH_MAX];
 	bool delete_extract = false;
 	struct kcore_extract kce;
-	const char *disassembler;
 	bool decomp = false;
 	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
 
@@ -2334,28 +2283,26 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		}
 	}
 
-	err = annotation_options__init_disassemblers(options);
-	if (err)
-		goto out_remove_tmp;
-
 	err = -1;
+	for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers) && err != 0; i++) {
+		enum perf_disassembler dis = options->disassemblers[i];
 
-	for (int i = 0; i < options->nr_disassemblers && err != 0; ++i) {
-		disassembler = options->disassemblers[i];
-
-		if (!strcmp(disassembler, "llvm"))
+		switch (dis) {
+		case PERF_DISASM_LLVM:
 			err = symbol__disassemble_llvm(symfs_filename, sym, args);
-		else if (!strcmp(disassembler, "capstone"))
+			break;
+		case PERF_DISASM_CAPSTONE:
 			err = symbol__disassemble_capstone(symfs_filename, sym, args);
-		else if (!strcmp(disassembler, "objdump"))
+			break;
+		case PERF_DISASM_OBJDUMP:
 			err = symbol__disassemble_objdump(symfs_filename, sym, args);
-		else
-			pr_debug("Unknown disassembler %s, skipping...\n", disassembler);
-	}
-
-	if (err == 0) {
-		pr_debug("Disassembled with %s\nannotate.disassemblers=%s\n",
-			 disassembler, options->disassemblers_str);
+			break;
+		case PERF_DISASM_UNKNOWN: /* End of disassemblers. */
+		default:
+			goto out_remove_tmp;
+		}
+		if (err == 0)
+			pr_debug("Disassembled with %s\n", perf_disassembler__strs[dis]);
 	}
 out_remove_tmp:
 	if (decomp)
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index a7f7ed01421c..99bf905ade81 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -136,7 +136,7 @@ displays the statistics gathered since it was forked.
 The system configuration dump (if --quiet is not used) is followed by statistics.  The first row of the statistics labels the content of each column (below).  The second row of statistics is the system summary line.  The system summary line has a '-' in the columns for the Package, Core, and CPU.  The contents of the system summary line depends on the type of column.  Columns that count items (eg. IRQ) show the sum across all CPUs in the system.  Columns that show a percentage show the average across all CPUs in the system.  Columns that dump raw MSR values simply show 0 in the summary.  After the system summary row, each row describes a specific Package/Core/CPU.  Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
 .SH COLUMN DESCRIPTIONS
 .PP
-\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any.  This counter is disabled by default, and is enabled with "--enable usec", or --debug.  On the summary row, usec refers to the total elapsed time to collect the counters on all cpus.
+\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any.  This counter is disabled by default, and is enabled with "--enable usec", or --debug.  On the summary row, usec refers to the total elapsed time to snapshot the procfs/sysfs and collect the counters on all cpus.
 .PP
 \fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected.  This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug".  On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU.
 .PP
@@ -190,7 +190,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 .PP
 \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
 .PP
-\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default.  Enable with --enable SysWatt.
+\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS).
 .PP
 \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.  Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system.  Note that the meaning of this field is model specific.  For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits.  Comparing PkgWatt and PkgTmp to system limits is necessary.
 .PP
@@ -516,14 +516,40 @@ that they count at TSC rate, which is true on all processors tested to date.
 Volume 3B: System Programming Guide"
 https://www.intel.com/products/processor/manuals/
 
+.SH RUN THE LATEST VERSION
+If turbostat complains that it doesn't recognize your processor,
+please try the latest version.
+
+The latest version of turbostat does not require the latest version of the Linux kernel.
+However, some features, such as perf(1) counters, do require kernel support.
+
+The latest turbostat release is available in the upstream Linux Kernel source tree.
+eg. "git pull https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git"
+and run make in tools/power/x86/turbostat/.
+
+n.b. "make install" will update your system manually, but a distro update may subsequently downgrade your turbostat to an older version.
+For this reason, manually installing to /usr/local/bin may be what you want.
+
+Note that turbostat/Makefile has a "make snapshot" target, which will create a tar file
+that can build without a local kernel source tree.
+
+If the upstream version isn't new enough, the development tree can be found here:
+"git pull https://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat"
+
+If the development tree doesn't work, please contact the author via chat,
+or via email with the word "turbostat" on the Subject line.
+
 .SH FILES
 .ta
 .nf
+/sys/bus/event_source/devices/
 /dev/cpu/*/msr
+/sys/class/intel_pmt/
+/sys/devices/system/cpu/
 .fi
 
 .SH "SEE ALSO"
-msr(4), vmstat(8)
+perf(1), msr(4), vmstat(8)
 .PP
 .SH AUTHOR
 .nf
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 58a487c225a7..8d5011a0bf60 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3,7 +3,7 @@
  * turbostat -- show CPU frequency and C-state residency
  * on modern Intel and AMD processors.
  *
- * Copyright (c) 2024 Intel Corporation.
+ * Copyright (c) 2025 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  */
 
@@ -95,6 +95,8 @@
 #define INTEL_ECORE_TYPE	0x20
 #define INTEL_PCORE_TYPE	0x40
 
+#define ROUND_UP_TO_PAGE_SIZE(n) (((n) + 0x1000UL-1UL) & ~(0x1000UL-1UL))
+
 enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
 enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M };
 enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE };
@@ -202,6 +204,8 @@ struct msr_counter bic[] = {
 	{ 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 },
 	{ 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 },
 	{ 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 },
+	{ 0x0, "NMI", NULL, 0, 0, 0, NULL, 0 },
+	{ 0x0, "CPU%c1e", NULL, 0, 0, 0, NULL, 0 },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -266,14 +270,16 @@ struct msr_counter bic[] = {
 #define	BIC_Diec6		(1ULL << 58)
 #define	BIC_SysWatt		(1ULL << 59)
 #define	BIC_Sys_J		(1ULL << 60)
+#define	BIC_NMI			(1ULL << 61)
+#define	BIC_CPU_c1e		(1ULL << 62)
 
-#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
-#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
+#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die)
+#define BIC_THERMAL_PWR (BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__ | BIC_SysWatt)
 #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ)
-#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6)
-#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
+#define BIC_IDLE (BIC_Busy | BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6)
+#define BIC_OTHER (BIC_IRQ | BIC_NMI | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
 
-#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J)
+#define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
 unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
 unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
@@ -326,6 +332,7 @@ unsigned int rapl_joules;
 unsigned int summary_only;
 unsigned int list_header_only;
 unsigned int dump_only;
+unsigned int force_load;
 unsigned int has_aperf;
 unsigned int has_aperf_access;
 unsigned int has_epb;
@@ -353,7 +360,7 @@ unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int tj_max;
 unsigned int tj_max_override;
 double rapl_power_units, rapl_time_units;
-double rapl_dram_energy_units, rapl_energy_units;
+double rapl_dram_energy_units, rapl_energy_units, rapl_psys_energy_units;
 double rapl_joule_counter_range;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
@@ -365,6 +372,9 @@ unsigned int has_hwp_activity_window;	/* IA32_HWP_REQUEST[bits 41:32] */
 unsigned int has_hwp_epp;	/* IA32_HWP_REQUEST[bits 31:24] */
 unsigned int has_hwp_pkg;	/* IA32_HWP_REQUEST_PKG */
 unsigned int first_counter_read = 1;
+
+static struct timeval procsysfs_tv_begin;
+
 int ignore_stdin;
 bool no_msr;
 bool no_perf;
@@ -419,6 +429,7 @@ struct platform_features {
 	bool has_per_core_rapl;	/* Indicates cores energy collection is per-core, not per-package. AMD specific for now */
 	bool has_rapl_divisor;	/* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */
 	bool has_fixed_rapl_unit;	/* Fixed Energy Unit used for DRAM RAPL Domain */
+	bool has_fixed_rapl_psys_unit;	/* Fixed Energy Unit used for PSYS RAPL Domain */
 	int rapl_quirk_tdp;	/* Hardcoded TDP value when cannot be retrieved from hardware */
 	int tcc_offset_bits;	/* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */
 	bool enable_tsc_tweak;	/* Use CPU Base freq instead of TSC freq for aperf/mperf counter */
@@ -819,6 +830,7 @@ static const struct platform_features spr_features = {
 	.has_msr_core_c1_res = 1,
 	.has_irtl_msrs = 1,
 	.has_cst_prewake_bit = 1,
+	.has_fixed_rapl_psys_unit = 1,
 	.trl_msrs = TRL_BASE | TRL_CORECOUNT,
 	.rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS,
 };
@@ -1024,6 +1036,7 @@ static const struct platform_data turbostat_pdata[] = {
 	{ INTEL_ARROWLAKE_U, &adl_features },
 	{ INTEL_ARROWLAKE, &adl_features },
 	{ INTEL_LUNARLAKE_M, &lnl_features },
+	{ INTEL_PANTHERLAKE_L, &lnl_features },
 	{ INTEL_ATOM_SILVERMONT, &slv_features },
 	{ INTEL_ATOM_SILVERMONT_D, &slvd_features },
 	{ INTEL_ATOM_AIRMONT, &amt_features },
@@ -1036,6 +1049,7 @@ static const struct platform_data turbostat_pdata[] = {
 	{ INTEL_ATOM_GRACEMONT, &adl_features },
 	{ INTEL_ATOM_CRESTMONT_X, &srf_features },
 	{ INTEL_ATOM_CRESTMONT, &grr_features },
+	{ INTEL_ATOM_DARKMONT_X, &srf_features },
 	{ INTEL_XEON_PHI_KNL, &knl_features },
 	{ INTEL_XEON_PHI_KNM, &knl_features },
 	/*
@@ -1054,9 +1068,10 @@ void probe_platform_features(unsigned int family, unsigned int model)
 {
 	int i;
 
-	platform = &default_features;
 
 	if (authentic_amd || hygon_genuine) {
+		/* fallback to default features on unsupported models */
+		force_load++;
 		if (max_extended_level >= 0x80000007) {
 			unsigned int eax, ebx, ecx, edx;
 
@@ -1065,11 +1080,11 @@ void probe_platform_features(unsigned int family, unsigned int model)
 			if ((edx & (1 << 14)) && family >= 0x17)
 				platform = &amd_features_with_rapl;
 		}
-		return;
+		goto end;
 	}
 
 	if (!genuine_intel)
-		return;
+		goto end;
 
 	for (i = 0; turbostat_pdata[i].features; i++) {
 		if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) {
@@ -1077,6 +1092,19 @@ void probe_platform_features(unsigned int family, unsigned int model)
 			return;
 		}
 	}
+
+end:
+	if (force_load && !platform) {
+		fprintf(outf, "Forced to run on unsupported platform!\n");
+		platform = &default_features;
+	}
+
+	if (platform)
+		return;
+
+	fprintf(stderr, "Unsupported platform detected.\n"
+		"\tSee RUN THE LATEST VERSION on turbostat(8)\n");
+	exit(1);
 }
 
 /* Model specific support End */
@@ -1094,8 +1122,8 @@ int backwards_count;
 char *progname;
 
 #define CPU_SUBSET_MAXCPUS	1024	/* need to use before probe... */
-cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset;
-size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size;
+cpu_set_t *cpu_present_set, *cpu_possible_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset;
+size_t cpu_present_setsize, cpu_possible_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size;
 #define MAX_ADDED_THREAD_COUNTERS 24
 #define MAX_ADDED_CORE_COUNTERS 8
 #define MAX_ADDED_PACKAGE_COUNTERS 16
@@ -1271,7 +1299,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = {
 	 .msr = MSR_PLATFORM_ENERGY_STATUS,
 	 .msr_mask = 0x00000000FFFFFFFF,
 	 .msr_shift = 0,
-	 .platform_rapl_msr_scale = &rapl_energy_units,
+	 .platform_rapl_msr_scale = &rapl_psys_energy_units,
 	 .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM,
 	 .bic = BIC_SysWatt | BIC_Sys_J,
 	 .compat_scale = 1.0,
@@ -1510,6 +1538,17 @@ static struct msr_counter_arch_info msr_counter_arch_infos[] = {
 #define PMT_COUNTER_MTL_DC6_LSB    0
 #define PMT_COUNTER_MTL_DC6_MSB    63
 #define PMT_MTL_DC6_GUID           0x1a067102
+#define PMT_MTL_DC6_SEQ            0
+
+#define PMT_COUNTER_CWF_MC1E_OFFSET_BASE          20936
+#define PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT     24
+#define PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE 12
+#define PMT_COUNTER_CWF_CPUS_PER_MODULE           4
+#define PMT_COUNTER_CWF_MC1E_LSB                  0
+#define PMT_COUNTER_CWF_MC1E_MSB                  63
+#define PMT_CWF_MC1E_GUID                         0x14421519
+
+unsigned long long tcore_clock_freq_hz = 800000000;
 
 #define PMT_COUNTER_NAME_SIZE_BYTES      16
 #define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32
@@ -1533,6 +1572,7 @@ struct pmt_mmio {
 enum pmt_datatype {
 	PMT_TYPE_RAW,
 	PMT_TYPE_XTAL_TIME,
+	PMT_TYPE_TCORE_CLOCK,
 };
 
 struct pmt_domain_info {
@@ -1562,6 +1602,93 @@ struct pmt_counter {
 	struct pmt_domain_info *domains;
 };
 
+/*
+ * PMT telemetry directory iterator.
+ * Used to iterate telemetry files in sysfs in correct order.
+ */
+struct pmt_diriter_t {
+	DIR *dir;
+	struct dirent **namelist;
+	unsigned int num_names;
+	unsigned int current_name_idx;
+};
+
+int pmt_telemdir_filter(const struct dirent *e)
+{
+	unsigned int dummy;
+
+	return sscanf(e->d_name, "telem%u", &dummy);
+}
+
+int pmt_telemdir_sort(const struct dirent **a, const struct dirent **b)
+{
+	unsigned int aidx = 0, bidx = 0;
+
+	sscanf((*a)->d_name, "telem%u", &aidx);
+	sscanf((*b)->d_name, "telem%u", &bidx);
+
+	return aidx >= bidx;
+}
+
+const struct dirent *pmt_diriter_next(struct pmt_diriter_t *iter)
+{
+	const struct dirent *ret = NULL;
+
+	if (!iter->dir)
+		return NULL;
+
+	if (iter->current_name_idx >= iter->num_names)
+		return NULL;
+
+	ret = iter->namelist[iter->current_name_idx];
+	++iter->current_name_idx;
+
+	return ret;
+}
+
+const struct dirent *pmt_diriter_begin(struct pmt_diriter_t *iter, const char *pmt_root_path)
+{
+	int num_names = iter->num_names;
+
+	if (!iter->dir) {
+		iter->dir = opendir(pmt_root_path);
+		if (iter->dir == NULL)
+			return NULL;
+
+		num_names = scandir(pmt_root_path, &iter->namelist, pmt_telemdir_filter, pmt_telemdir_sort);
+		if (num_names == -1)
+			return NULL;
+	}
+
+	iter->current_name_idx = 0;
+	iter->num_names = num_names;
+
+	return pmt_diriter_next(iter);
+}
+
+void pmt_diriter_init(struct pmt_diriter_t *iter)
+{
+	memset(iter, 0, sizeof(*iter));
+}
+
+void pmt_diriter_remove(struct pmt_diriter_t *iter)
+{
+	if (iter->namelist) {
+		for (unsigned int i = 0; i < iter->num_names; i++) {
+			free(iter->namelist[i]);
+			iter->namelist[i] = NULL;
+		}
+	}
+
+	free(iter->namelist);
+	iter->namelist = NULL;
+	iter->num_names = 0;
+	iter->current_name_idx = 0;
+
+	closedir(iter->dir);
+	iter->dir = NULL;
+}
+
 unsigned int pmt_counter_get_width(const struct pmt_counter *p)
 {
 	return (p->msb - p->lsb) + 1;
@@ -1611,6 +1738,7 @@ struct thread_data {
 	unsigned long long c1;
 	unsigned long long instr_count;
 	unsigned long long irq_count;
+	unsigned long long nmi_count;
 	unsigned int smi_count;
 	unsigned int cpu_id;
 	unsigned int apic_id;
@@ -1917,6 +2045,7 @@ struct timeval tv_even, tv_odd, tv_delta;
 
 int *irq_column_2_cpu;		/* /proc/interrupts column numbers */
 int *irqs_per_cpu;		/* indexed by cpu_num */
+int *nmi_per_cpu;		/* indexed by cpu_num */
 
 void setup_all_buffers(bool startup);
 
@@ -1944,6 +2073,8 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 {
 	int retval, pkg_no, core_no, thread_no, node_no;
 
+	retval = 0;
+
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
 		for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
 			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
@@ -1959,14 +2090,12 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk
 					c = GET_CORE(core_base, core_no, node_no, pkg_no);
 					p = GET_PKG(pkg_base, pkg_no);
 
-					retval = func(t, c, p);
-					if (retval)
-						return retval;
+					retval |= func(t, c, p);
 				}
 			}
 		}
 	}
-	return 0;
+	return retval;
 }
 
 int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p)
@@ -2085,13 +2214,17 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 int probe_msr(int cpu, off_t offset)
 {
 	ssize_t retval;
-	unsigned long long dummy;
+	unsigned long long value;
 
 	assert(!no_msr);
 
-	retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset);
+	retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset);
 
-	if (retval != sizeof(dummy))
+	/*
+	 * Expect MSRs to accumulate some non-zero value since the system was powered on.
+	 * Treat zero as a read failure.
+	 */
+	if (retval != sizeof(value) || value == 0)
 		return 1;
 
 	return 0;
@@ -2135,41 +2268,54 @@ void help(void)
 		"when COMMAND completes.\n"
 		"If no COMMAND is specified, turbostat wakes every 5-seconds\n"
 		"to print statistics, until interrupted.\n"
-		"  -a, --add	add a counter\n"
+		"  -a, --add counter\n"
+		"		add a counter\n"
 		"		  eg. --add msr0x10,u64,cpu,delta,MY_TSC\n"
 		"		  eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n"
 		"		  eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n"
-		"  -c, --cpu	cpu-set	limit output to summary plus cpu-set:\n"
+		"  -c, --cpu cpu-set\n"
+		"		limit output to summary plus cpu-set:\n"
 		"		  {core | package | j,k,l..m,n-p }\n"
-		"  -d, --debug	displays usec, Time_Of_Day_Seconds and more debugging\n"
+		"  -d, --debug\n"
+		"		displays usec, Time_Of_Day_Seconds and more debugging\n"
 		"		debug messages are printed to stderr\n"
-		"  -D, --Dump	displays the raw counter values\n"
-		"  -e, --enable	[all | column]\n"
+		"  -D, --Dump\n"
+		"		displays the raw counter values\n"
+		"  -e, --enable [all | column]\n"
 		"		shows all or the specified disabled column\n"
-		"  -H, --hide [column|column,column,...]\n"
+		"  -f, --force\n"
+		"		force load turbostat with minimum default features on unsupported platforms.\n"
+		"  -H, --hide [column | column,column,...]\n"
 		"		hide the specified column(s)\n"
 		"  -i, --interval sec.subsec\n"
-		"		Override default 5-second measurement interval\n"
-		"  -J, --Joules	displays energy in Joules instead of Watts\n"
-		"  -l, --list	list column headers only\n"
-		"  -M, --no-msr Disable all uses of the MSR driver\n"
-		"  -P, --no-perf Disable all uses of the perf API\n"
+		"		override default 5-second measurement interval\n"
+		"  -J, --Joules\n"
+		"		displays energy in Joules instead of Watts\n"
+		"  -l, --list\n"
+		"		list column headers only\n"
+		"  -M, --no-msr\n"
+		"		disable all uses of the MSR driver\n"
+		"  -P, --no-perf\n"
+		"		disable all uses of the perf API\n"
 		"  -n, --num_iterations num\n"
 		"		number of the measurement iterations\n"
 		"  -N, --header_iterations num\n"
 		"		print header every num iterations\n"
 		"  -o, --out file\n"
 		"		create or truncate \"file\" for all output\n"
-		"  -q, --quiet	skip decoding system configuration header\n"
-		"  -s, --show [column|column,column,...]\n"
+		"  -q, --quiet\n"
+		"		skip decoding system configuration header\n"
+		"  -s, --show [column | column,column,...]\n"
 		"		show only the specified column(s)\n"
 		"  -S, --Summary\n"
 		"		limits output to 1-line system summary per interval\n"
 		"  -T, --TCC temperature\n"
 		"		sets the Thermal Control Circuit temperature in\n"
 		"		  degrees Celsius\n"
-		"  -h, --help	print this help message\n"
-		"  -v, --version	print version information\n" "\n" "For more help, run \"man turbostat\"\n");
+		"  -h, --help\n"
+		"		print this help message\n"
+		"  -v, --version\n"
+		"		print version information\n\nFor more help, run \"man turbostat\"\n");
 }
 
 /*
@@ -2289,6 +2435,12 @@ void print_header(char *delim)
 		else
 			outp += sprintf(outp, "%sIRQ", (printed++ ? delim : ""));
 	}
+	if (DO_BIC(BIC_NMI)) {
+		if (sums_need_wide_columns)
+			outp += sprintf(outp, "%s     NMI", (printed++ ? delim : ""));
+		else
+			outp += sprintf(outp, "%sNMI", (printed++ ? delim : ""));
+	}
 
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "%sSMI", (printed++ ? delim : ""));
@@ -2335,6 +2487,7 @@ void print_header(char *delim)
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+		case PMT_TYPE_TCORE_CLOCK:
 			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name);
 			break;
 		}
@@ -2409,6 +2562,7 @@ void print_header(char *delim)
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+		case PMT_TYPE_TCORE_CLOCK:
 			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name);
 			break;
 		}
@@ -2540,6 +2694,7 @@ void print_header(char *delim)
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+		case PMT_TYPE_TCORE_CLOCK:
 			outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name);
 			break;
 		}
@@ -2575,6 +2730,8 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
 
 		if (DO_BIC(BIC_IRQ))
 			outp += sprintf(outp, "IRQ: %lld\n", t->irq_count);
+		if (DO_BIC(BIC_NMI))
+			outp += sprintf(outp, "IRQ: %lld\n", t->nmi_count);
 		if (DO_BIC(BIC_SMI))
 			outp += sprintf(outp, "SMI: %d\n", t->smi_count);
 
@@ -2794,6 +2951,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count);
 	}
 
+	/* NMI */
+	if (DO_BIC(BIC_NMI)) {
+		if (sums_need_wide_columns)
+			outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->nmi_count);
+		else
+			outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->nmi_count);
+	}
+
 	/* SMI */
 	if (DO_BIC(BIC_SMI))
 		outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count);
@@ -2848,7 +3013,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) {
 		const unsigned long value_raw = t->pmt_counter[i];
-		const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+		double value_converted;
 		switch (ppmt->type) {
 		case PMT_TYPE_RAW:
 			if (pmt_counter_get_width(ppmt) <= 32)
@@ -2860,8 +3025,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+			value_converted = 100.0 * value_raw / crystal_hz / interval_float;
 			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 			break;
+
+		case PMT_TYPE_TCORE_CLOCK:
+			value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float;
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 		}
 	}
 
@@ -2928,7 +3098,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) {
 		const unsigned long value_raw = c->pmt_counter[i];
-		const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+		double value_converted;
 		switch (ppmt->type) {
 		case PMT_TYPE_RAW:
 			if (pmt_counter_get_width(ppmt) <= 32)
@@ -2940,8 +3110,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+			value_converted = 100.0 * value_raw / crystal_hz / interval_float;
 			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 			break;
+
+		case PMT_TYPE_TCORE_CLOCK:
+			value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float;
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 		}
 	}
 
@@ -3126,7 +3301,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) {
 		const unsigned long value_raw = p->pmt_counter[i];
-		const double value_converted = 100.0 * value_raw / crystal_hz / interval_float;
+		double value_converted;
 		switch (ppmt->type) {
 		case PMT_TYPE_RAW:
 			if (pmt_counter_get_width(ppmt) <= 32)
@@ -3138,8 +3313,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 			break;
 
 		case PMT_TYPE_XTAL_TIME:
+			value_converted = 100.0 * value_raw / crystal_hz / interval_float;
 			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 			break;
+
+		case PMT_TYPE_TCORE_CLOCK:
+			value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float;
+			outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted);
 		}
 	}
 
@@ -3409,6 +3589,9 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d
 	if (DO_BIC(BIC_IRQ))
 		old->irq_count = new->irq_count - old->irq_count;
 
+	if (DO_BIC(BIC_NMI))
+		old->nmi_count = new->nmi_count - old->nmi_count;
+
 	if (DO_BIC(BIC_SMI))
 		old->smi_count = new->smi_count - old->smi_count;
 
@@ -3447,12 +3630,10 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
 
 	/* always calculate thread delta */
 	retval = delta_thread(t, t2, c2);	/* c2 is core delta */
-	if (retval)
-		return retval;
 
 	/* calculate package delta only for 1st core in package */
 	if (is_cpu_first_core_in_package(t, c, p))
-		retval = delta_package(p, p2);
+		retval |= delta_package(p, p2);
 
 	return retval;
 }
@@ -3489,6 +3670,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	t->instr_count = 0;
 
 	t->irq_count = 0;
+	t->nmi_count = 0;
 	t->smi_count = 0;
 
 	c->c3 = 0;
@@ -3580,7 +3762,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	/* remember first tv_begin */
 	if (average.threads.tv_begin.tv_sec == 0)
-		average.threads.tv_begin = t->tv_begin;
+		average.threads.tv_begin = procsysfs_tv_begin;
 
 	/* remember last tv_end */
 	average.threads.tv_end = t->tv_end;
@@ -3593,6 +3775,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 	average.threads.instr_count += t->instr_count;
 
 	average.threads.irq_count += t->irq_count;
+	average.threads.nmi_count += t->nmi_count;
 	average.threads.smi_count += t->smi_count;
 
 	for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
@@ -3734,6 +3917,9 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data
 
 	if (average.threads.irq_count > 9999999)
 		sums_need_wide_columns = 1;
+	if (average.threads.nmi_count > 9999999)
+		sums_need_wide_columns = 1;
+
 
 	average.cores.c3 /= topo.allowed_cores;
 	average.cores.c6 /= topo.allowed_cores;
@@ -4546,7 +4732,8 @@ unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb)
 
 unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id)
 {
-	assert(domain_id < ppmt->num_domains);
+	if (domain_id >= ppmt->num_domains)
+		return 0;
 
 	const unsigned long *pmmio = ppmt->domains[domain_id].pcounter;
 	const unsigned long value = pmmio ? *pmmio : 0;
@@ -4590,6 +4777,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 
 	if (DO_BIC(BIC_IRQ))
 		t->irq_count = irqs_per_cpu[cpu];
+	if (DO_BIC(BIC_NMI))
+		t->nmi_count = nmi_per_cpu[cpu];
 
 	get_cstate_counters(cpu, t, c, p);
 
@@ -5335,6 +5524,7 @@ void free_all_buffers(void)
 
 	free(irq_column_2_cpu);
 	free(irqs_per_cpu);
+	free(nmi_per_cpu);
 
 	for (i = 0; i <= topo.max_cpu_num; ++i) {
 		if (cpus[i].put_ids)
@@ -5566,6 +5756,8 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *,
 {
 	int retval, pkg_no, node_no, core_no, thread_no;
 
+	retval = 0;
+
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
 		for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) {
 			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
@@ -5587,14 +5779,12 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *,
 					p = GET_PKG(pkg_base, pkg_no);
 					p2 = GET_PKG(pkg_base2, pkg_no);
 
-					retval = func(t, c, p, t2, c2, p2);
-					if (retval)
-						return retval;
+					retval |= func(t, c, p, t2, c2, p2);
 				}
 			}
 		}
 	}
-	return 0;
+	return retval;
 }
 
 /*
@@ -5791,31 +5981,37 @@ int snapshot_proc_interrupts(void)
 
 		irq_column_2_cpu[column] = cpu_number;
 		irqs_per_cpu[cpu_number] = 0;
+		nmi_per_cpu[cpu_number] = 0;
 	}
 
 	/* read /proc/interrupt count lines and sum up irqs per cpu */
 	while (1) {
 		int column;
 		char buf[64];
+		int this_row_is_nmi = 0;
 
-		retval = fscanf(fp, " %s:", buf);	/* flush irq# "N:" */
+		retval = fscanf(fp, " %s:", buf);	/* irq# "N:" */
 		if (retval != 1)
 			break;
 
+		if (strncmp(buf, "NMI", strlen("NMI")) == 0)
+			this_row_is_nmi = 1;
+
 		/* read the count per cpu */
 		for (column = 0; column < topo.num_cpus; ++column) {
 
 			int cpu_number, irq_count;
 
 			retval = fscanf(fp, " %d", &irq_count);
+
 			if (retval != 1)
 				break;
 
 			cpu_number = irq_column_2_cpu[column];
 			irqs_per_cpu[cpu_number] += irq_count;
-
+			if (this_row_is_nmi)
+				nmi_per_cpu[cpu_number] += irq_count;
 		}
-
 		while (getc(fp) != '\n') ;	/* flush interrupt description */
 
 	}
@@ -5912,7 +6108,9 @@ int snapshot_sys_lpi_us(void)
  */
 int snapshot_proc_sysfs_files(void)
 {
-	if (DO_BIC(BIC_IRQ))
+	gettimeofday(&procsysfs_tv_begin, (struct timezone *)NULL);
+
+	if (DO_BIC(BIC_IRQ) || DO_BIC(BIC_NMI))
 		if (snapshot_proc_interrupts())
 			return 1;
 
@@ -7043,6 +7241,11 @@ void rapl_probe_intel(void)
 	else
 		rapl_dram_energy_units = rapl_energy_units;
 
+	if (platform->has_fixed_rapl_psys_unit)
+		rapl_psys_energy_units = 1.0;
+	else
+		rapl_psys_energy_units = rapl_energy_units;
+
 	time_unit = msr >> 16 & 0xF;
 	if (time_unit == 0)
 		time_unit = 0xA;
@@ -8233,6 +8436,7 @@ void process_cpuid()
 		aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1;
 
 	BIC_PRESENT(BIC_IRQ);
+	BIC_PRESENT(BIC_NMI);
 	BIC_PRESENT(BIC_TSC_MHz);
 }
 
@@ -8292,6 +8496,33 @@ int dir_filter(const struct dirent *dirp)
 		return 0;
 }
 
+char *possible_file = "/sys/devices/system/cpu/possible";
+char possible_buf[1024];
+
+int initialize_cpu_possible_set(void)
+{
+	FILE *fp;
+
+	fp = fopen(possible_file, "r");
+	if (!fp) {
+		warn("open %s", possible_file);
+		return -1;
+	}
+	if (fread(possible_buf, sizeof(char), 1024, fp) == 0) {
+		warn("read %s", possible_file);
+		goto err;
+	}
+	if (parse_cpu_str(possible_buf, cpu_possible_set, cpu_possible_setsize)) {
+		warnx("%s: cpu str malformat %s\n", possible_file, cpu_effective_str);
+		goto err;
+	}
+	return 0;
+
+err:
+	fclose(fp);
+	return -1;
+}
+
 void topology_probe(bool startup)
 {
 	int i;
@@ -8324,6 +8555,16 @@ void topology_probe(bool startup)
 	for_all_proc_cpus(mark_cpu_present);
 
 	/*
+	 * Allocate and initialize cpu_possible_set
+	 */
+	cpu_possible_set = CPU_ALLOC((topo.max_cpu_num + 1));
+	if (cpu_possible_set == NULL)
+		err(3, "CPU_ALLOC");
+	cpu_possible_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+	CPU_ZERO_S(cpu_possible_setsize, cpu_possible_set);
+	initialize_cpu_possible_set();
+
+	/*
 	 * Allocate and initialize cpu_effective_set
 	 */
 	cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1));
@@ -8583,7 +8824,11 @@ void allocate_irq_buffers(void)
 
 	irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int));
 	if (irqs_per_cpu == NULL)
-		err(-1, "calloc %d", topo.max_cpu_num + 1);
+		err(-1, "calloc %d IRQ", topo.max_cpu_num + 1);
+
+	nmi_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int));
+	if (nmi_per_cpu == NULL)
+		err(-1, "calloc %d NMI", topo.max_cpu_num + 1);
 }
 
 int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p)
@@ -8854,49 +9099,36 @@ int parse_telem_info_file(int fd_dir, const char *info_filename, const char *for
 
 struct pmt_mmio *pmt_mmio_open(unsigned int target_guid)
 {
-	DIR *dirp;
-	struct dirent *entry;
+	struct pmt_diriter_t pmt_iter;
+	const struct dirent *entry;
 	struct stat st;
-	unsigned int telem_idx;
 	int fd_telem_dir, fd_pmt;
 	unsigned long guid, size, offset;
 	size_t mmap_size;
 	void *mmio;
-	struct pmt_mmio *ret = NULL;
+	struct pmt_mmio *head = NULL, *last = NULL;
+	struct pmt_mmio *new_pmt = NULL;
 
 	if (stat(SYSFS_TELEM_PATH, &st) == -1)
 		return NULL;
 
-	dirp = opendir(SYSFS_TELEM_PATH);
-	if (dirp == NULL)
+	pmt_diriter_init(&pmt_iter);
+	entry = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH);
+	if (!entry) {
+		pmt_diriter_remove(&pmt_iter);
 		return NULL;
+	}
 
-	for (;;) {
-		entry = readdir(dirp);
-
-		if (entry == NULL)
-			break;
-
-		if (strcmp(entry->d_name, ".") == 0)
-			continue;
-
-		if (strcmp(entry->d_name, "..") == 0)
-			continue;
-
-		if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1)
-			continue;
-
-		if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) {
+	for ( ; entry != NULL; entry = pmt_diriter_next(&pmt_iter)) {
+		if (fstatat(dirfd(pmt_iter.dir), entry->d_name, &st, 0) == -1)
 			break;
-		}
 
 		if (!S_ISDIR(st.st_mode))
 			continue;
 
-		fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY);
-		if (fd_telem_dir == -1) {
+		fd_telem_dir = openat(dirfd(pmt_iter.dir), entry->d_name, O_RDONLY);
+		if (fd_telem_dir == -1)
 			break;
-		}
 
 		if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) {
 			close(fd_telem_dir);
@@ -8924,38 +9156,54 @@ struct pmt_mmio *pmt_mmio_open(unsigned int target_guid)
 		if (fd_pmt == -1)
 			goto loop_cleanup_and_break;
 
-		mmap_size = (size + 0x1000UL) & (~0x1000UL);
+		mmap_size = ROUND_UP_TO_PAGE_SIZE(size);
 		mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0);
 		if (mmio != MAP_FAILED) {
-
 			if (debug)
 				fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio);
 
-			ret = calloc(1, sizeof(*ret));
+			new_pmt = calloc(1, sizeof(*new_pmt));
 
-			if (!ret) {
+			if (!new_pmt) {
 				fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__);
 				exit(1);
 			}
 
-			ret->guid = guid;
-			ret->mmio_base = mmio;
-			ret->pmt_offset = offset;
-			ret->size = size;
+			/*
+			 * Create linked list of mmaped regions,
+			 * but preserve the ordering from sysfs.
+			 * Ordering is important for the user to
+			 * use the seq=%u parameter when adding a counter.
+			 */
+			new_pmt->guid = guid;
+			new_pmt->mmio_base = mmio;
+			new_pmt->pmt_offset = offset;
+			new_pmt->size = size;
+			new_pmt->next = pmt_mmios;
+
+			if (last)
+				last->next = new_pmt;
+			else
+				head = new_pmt;
 
-			ret->next = pmt_mmios;
-			pmt_mmios = ret;
+			last = new_pmt;
 		}
 
 loop_cleanup_and_break:
 		close(fd_pmt);
 		close(fd_telem_dir);
-		break;
 	}
 
-	closedir(dirp);
+	pmt_diriter_remove(&pmt_iter);
 
-	return ret;
+	/*
+	 * If we found something, stick just
+	 * created linked list to the front.
+	 */
+	if (head)
+		pmt_mmios = head;
+
+	return head;
 }
 
 struct pmt_mmio *pmt_mmio_find(unsigned int guid)
@@ -8992,7 +9240,7 @@ void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offs
 	return ret;
 }
 
-struct pmt_mmio *pmt_add_guid(unsigned int guid)
+struct pmt_mmio *pmt_add_guid(unsigned int guid, unsigned int seq)
 {
 	struct pmt_mmio *ret;
 
@@ -9000,6 +9248,11 @@ struct pmt_mmio *pmt_add_guid(unsigned int guid)
 	if (!ret)
 		ret = pmt_mmio_open(guid);
 
+	while (ret && seq) {
+		ret = ret->next;
+		--seq;
+	}
+
 	return ret;
 }
 
@@ -9046,7 +9299,7 @@ void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio,
 	pcounter->domains[domain_id].pcounter = pmmio;
 }
 
-int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
+int pmt_add_counter(unsigned int guid, unsigned int seq, const char *name, enum pmt_datatype type,
 		    unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope,
 		    enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode)
 {
@@ -9066,10 +9319,10 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
 		exit(1);
 	}
 
-	mmio = pmt_add_guid(guid);
+	mmio = pmt_add_guid(guid, seq);
 	if (!mmio) {
 		if (mode != PMT_OPEN_TRY) {
-			fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid);
+			fprintf(stderr, "%s: failed to map PMT MMIO for guid %x, seq %u\n", __func__, guid, seq);
 			exit(1);
 		}
 
@@ -9124,10 +9377,68 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type,
 
 void pmt_init(void)
 {
+	int cpu_num;
+	unsigned long seq, offset, mod_num;
+
 	if (BIC_IS_ENABLED(BIC_Diec6)) {
-		pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB,
-				PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA,
-				0, PMT_OPEN_TRY);
+		pmt_add_counter(PMT_MTL_DC6_GUID, PMT_MTL_DC6_SEQ, "Die%c6", PMT_TYPE_XTAL_TIME,
+				PMT_COUNTER_MTL_DC6_LSB, PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET,
+				SCOPE_PACKAGE, FORMAT_DELTA, 0, PMT_OPEN_TRY);
+	}
+
+	if (BIC_IS_ENABLED(BIC_CPU_c1e)) {
+		seq = 0;
+		offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE;
+		mod_num = 0;	/* Relative module number for current PMT file. */
+
+		/* Open the counter for each CPU. */
+		for (cpu_num = 0; cpu_num < topo.max_cpu_num;) {
+
+			if (cpu_is_not_allowed(cpu_num))
+				goto next_loop_iter;
+
+			/*
+			 * Set the scope to CPU, even though CWF report the counter per module.
+			 * CPUs inside the same module will read from the same location, instead of reporting zeros.
+			 *
+			 * CWF with newer firmware might require a PMT_TYPE_XTAL_TIME intead of PMT_TYPE_TCORE_CLOCK.
+			 */
+			pmt_add_counter(PMT_CWF_MC1E_GUID, seq, "CPU%c1e", PMT_TYPE_TCORE_CLOCK,
+					PMT_COUNTER_CWF_MC1E_LSB, PMT_COUNTER_CWF_MC1E_MSB, offset, SCOPE_CPU,
+					FORMAT_DELTA, cpu_num, PMT_OPEN_TRY);
+
+			/*
+			 * Rather complex logic for each time we go to the next loop iteration,
+			 * so keep it as a label.
+			 */
+next_loop_iter:
+			/*
+			 * Advance the cpu number and check if we should also advance offset to
+			 * the next counter inside the PMT file.
+			 *
+			 * On Clearwater Forest platform, the counter is reported per module,
+			 * so open the same counter for all of the CPUs inside the module.
+			 * That way, reported table show the correct value for all of the CPUs inside the module,
+			 * instead of zeros.
+			 */
+			++cpu_num;
+			if (cpu_num % PMT_COUNTER_CWF_CPUS_PER_MODULE == 0) {
+				offset += PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT;
+				++mod_num;
+			}
+
+			/*
+			 * There are PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE in each PMT file.
+			 *
+			 * If that number is reached, seq must be incremented to advance to the next file in a sequence.
+			 * Offset inside that file and a module counter has to be reset.
+			 */
+			if (mod_num == PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE) {
+				++seq;
+				offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE;
+				mod_num = 0;
+			}
+		}
 	}
 }
 
@@ -9163,6 +9474,18 @@ void turbostat_init()
 	}
 }
 
+void affinitize_child(void)
+{
+	/* Prefer cpu_possible_set, if available */
+	if (sched_setaffinity(0, cpu_possible_setsize, cpu_possible_set)) {
+		warn("sched_setaffinity cpu_possible_set");
+
+		/* Otherwise, allow child to run on same cpu set as turbostat */
+		if (sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set))
+			warn("sched_setaffinity cpu_allowed_set");
+	}
+}
+
 int fork_it(char **argv)
 {
 	pid_t child_pid;
@@ -9178,6 +9501,7 @@ int fork_it(char **argv)
 	child_pid = fork();
 	if (!child_pid) {
 		/* child */
+		affinitize_child();
 		execvp(argv[0], argv);
 		err(errno, "exec %s", argv[0]);
 	} else {
@@ -9204,10 +9528,9 @@ int fork_it(char **argv)
 	timersub(&tv_odd, &tv_even, &tv_delta);
 	if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS))
 		fprintf(outf, "%s: Counter reset detected\n", progname);
-	else {
-		compute_average(EVEN_COUNTERS);
-		format_all_counters(EVEN_COUNTERS);
-	}
+
+	compute_average(EVEN_COUNTERS);
+	format_all_counters(EVEN_COUNTERS);
 
 	fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec / 1000000.0);
 
@@ -9236,7 +9559,7 @@ int get_and_dump_counters(void)
 
 void print_version()
 {
-	fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n");
+	fprintf(outf, "turbostat version 2025.02.02 - Len Brown <lenb@kernel.org>\n");
 }
 
 #define COMMAND_LINE_SIZE 2048
@@ -9561,7 +9884,7 @@ next:
 
 	}
 	if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) {
-		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n");
+		fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event) required\n");
 		fail++;
 	}
 
@@ -9599,15 +9922,100 @@ bool starts_with(const char *str, const char *prefix)
 	return strncmp(prefix, str, strlen(prefix)) == 0;
 }
 
+int pmt_parse_from_path(const char *target_path, unsigned int *out_guid, unsigned int *out_seq)
+{
+	struct pmt_diriter_t pmt_iter;
+	const struct dirent *dirname;
+	struct stat stat, target_stat;
+	int fd_telem_dir = -1;
+	int fd_target_dir;
+	unsigned int seq = 0;
+	unsigned long guid, target_guid;
+	int ret = -1;
+
+	fd_target_dir = open(target_path, O_RDONLY | O_DIRECTORY);
+	if (fd_target_dir == -1) {
+		return -1;
+	}
+
+	if (fstat(fd_target_dir, &target_stat) == -1) {
+		fprintf(stderr, "%s: Failed to stat the target: %s", __func__, strerror(errno));
+		exit(1);
+	}
+
+	if (parse_telem_info_file(fd_target_dir, "guid", "%lx", &target_guid)) {
+		fprintf(stderr, "%s: Failed to parse the target guid file: %s", __func__, strerror(errno));
+		exit(1);
+	}
+
+	close(fd_target_dir);
+
+	pmt_diriter_init(&pmt_iter);
+
+	for (dirname = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); dirname != NULL;
+	     dirname = pmt_diriter_next(&pmt_iter)) {
+
+		fd_telem_dir = openat(dirfd(pmt_iter.dir), dirname->d_name, O_RDONLY | O_DIRECTORY);
+		if (fd_telem_dir == -1)
+			continue;
+
+		if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) {
+			fprintf(stderr, "%s: Failed to parse the guid file: %s", __func__, strerror(errno));
+			continue;
+		}
+
+		if (fstat(fd_telem_dir, &stat) == -1) {
+			fprintf(stderr, "%s: Failed to stat %s directory: %s", __func__,
+				dirname->d_name, strerror(errno));
+			continue;
+		}
+
+		/*
+		 * If reached the same directory as target, exit the loop.
+		 * Seq has the correct value now.
+		 */
+		if (stat.st_dev == target_stat.st_dev && stat.st_ino == target_stat.st_ino) {
+			ret = 0;
+			break;
+		}
+
+		/*
+		 * If reached directory with the same guid,
+		 * but it's not the target directory yet,
+		 * increment seq and continue the search.
+		 */
+		if (guid == target_guid)
+			++seq;
+
+		close(fd_telem_dir);
+		fd_telem_dir = -1;
+	}
+
+	pmt_diriter_remove(&pmt_iter);
+
+	if (fd_telem_dir != -1)
+		close(fd_telem_dir);
+
+	if (!ret) {
+		*out_guid = target_guid;
+		*out_seq = seq;
+	}
+
+	return ret;
+}
+
 void parse_add_command_pmt(char *add_command)
 {
 	char *name = NULL;
 	char *type_name = NULL;
 	char *format_name = NULL;
+	char *direct_path = NULL;
+	static const char direct_path_prefix[] = "path=";
 	unsigned int offset;
 	unsigned int lsb;
 	unsigned int msb;
 	unsigned int guid;
+	unsigned int seq = 0; /* By default, pick first file in a sequence with a given GUID. */
 	unsigned int domain_id;
 	enum counter_scope scope = 0;
 	enum pmt_datatype type = PMT_TYPE_RAW;
@@ -9687,6 +10095,13 @@ void parse_add_command_pmt(char *add_command)
 			goto next;
 		}
 
+		if (sscanf(add_command, "seq=%x", &seq) == 1)
+			goto next;
+
+		if (strncmp(add_command, direct_path_prefix, strlen(direct_path_prefix)) == 0) {
+			direct_path = add_command + strlen(direct_path_prefix);
+			goto next;
+		}
 next:
 		add_command = strchr(add_command, ',');
 		if (add_command) {
@@ -9737,6 +10152,11 @@ next:
 			has_type = true;
 		}
 
+		if (strcmp("tcore_clock", type_name) == 0) {
+			type = PMT_TYPE_TCORE_CLOCK;
+			has_type = true;
+		}
+
 		if (!has_type) {
 			printf("%s: invalid %s: %s\n", __func__, "type", type_name);
 			exit(1);
@@ -9758,8 +10178,24 @@ next:
 		exit(1);
 	}
 
+	if (direct_path && has_guid) {
+		printf("%s: path and guid+seq parameters are mutually exclusive\n"
+		       "notice: passed guid=0x%x and path=%s\n", __func__, guid, direct_path);
+		exit(1);
+	}
+
+	if (direct_path) {
+		if (pmt_parse_from_path(direct_path, &guid, &seq)) {
+			printf("%s: failed to parse PMT file from %s\n", __func__, direct_path);
+			exit(1);
+		}
+
+		/* GUID was just infered from the direct path. */
+		has_guid = true;
+	}
+
 	if (!has_guid) {
-		printf("%s: missing %s\n", __func__, "guid");
+		printf("%s: missing %s\n", __func__, "guid or path");
 		exit(1);
 	}
 
@@ -9773,7 +10209,7 @@ next:
 		exit(1);
 	}
 
-	pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED);
+	pmt_add_counter(guid, seq, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED);
 }
 
 void parse_add_command(char *add_command)
@@ -9921,6 +10357,7 @@ void cmdline(int argc, char **argv)
 		{ "Dump", no_argument, 0, 'D' },
 		{ "debug", no_argument, 0, 'd' },	/* internal, not documented */
 		{ "enable", required_argument, 0, 'e' },
+		{ "force", no_argument, 0, 'f' },
 		{ "interval", required_argument, 0, 'i' },
 		{ "IPC", no_argument, 0, 'I' },
 		{ "num_iterations", required_argument, 0, 'n' },
@@ -9981,6 +10418,9 @@ void cmdline(int argc, char **argv)
 			/* --enable specified counter */
 			bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST);
 			break;
+		case 'f':
+			force_load++;
+			break;
 		case 'd':
 			debug++;
 			ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index d0337c11f9ee..cc8948f49117 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -725,7 +725,7 @@ static void default_mock_decoder(struct cxl_decoder *cxld)
 	cxld->reset = mock_decoder_reset;
 }
 
-static int first_decoder(struct device *dev, void *data)
+static int first_decoder(struct device *dev, const void *data)
 {
 	struct cxl_decoder *cxld;
 
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 347c1e7b37bd..8d731bd63988 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -401,6 +401,10 @@ struct cxl_test_gen_media gen_media = {
 			.channel = 1,
 			.rank = 30,
 		},
+		.component_id = { 0x3, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d },
+		.cme_threshold_ev_flags = 3,
+		.cme_count = { 33, 0, 0 },
+		.sub_type = 0x2,
 	},
 };
 
@@ -429,6 +433,11 @@ struct cxl_test_dram dram = {
 		.bank_group = 5,
 		.bank = 2,
 		.column = {0xDE, 0xAD},
+		.component_id = { 0x1, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d },
+		.sub_channel = 8,
+		.cme_threshold_ev_flags = 2,
+		.cvme_count = { 14, 0, 0 },
+		.sub_type = 0x5,
 	},
 };
 
@@ -456,7 +465,10 @@ struct cxl_test_mem_module mem_module = {
 			.dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef },
 			.cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
 			.cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef },
-		}
+		},
+		/* .validity_flags = <set below> */
+		.component_id = { 0x2, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d },
+		.event_sub_type = 0x3,
 	},
 };
 
@@ -478,13 +490,18 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds,
 
 static void cxl_mock_add_event_logs(struct mock_event_store *mes)
 {
-	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK,
+	put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK |
+			   CXL_GMER_VALID_COMPONENT | CXL_GMER_VALID_COMPONENT_ID_FORMAT,
 			   &gen_media.rec.media_hdr.validity_flags);
 
 	put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP |
-			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN,
+			   CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN | CXL_DER_VALID_SUB_CHANNEL |
+			   CXL_DER_VALID_COMPONENT | CXL_DER_VALID_COMPONENT_ID_FORMAT,
 			   &dram.rec.media_hdr.validity_flags);
 
+	put_unaligned_le16(CXL_MMER_VALID_COMPONENT | CXL_MMER_VALID_COMPONENT_ID_FORMAT,
+			   &mem_module.rec.validity_flags);
+
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed);
 	mes_add_event(mes, CXL_EVENT_TYPE_INFO,
 		      (struct cxl_event_record_raw *)&gen_media);
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index 450c7566c33f..af2594e4f35d 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -228,16 +228,16 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds,
 }
 EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL");
 
-int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
+int __wrap_cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds,
 			       struct cxl_endpoint_dvsec_info *info)
 {
 	int rc = 0, index;
 	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
 
-	if (ops && ops->is_mock_dev(dev))
+	if (ops && ops->is_mock_dev(cxlds->dev))
 		rc = 0;
 	else
-		rc = cxl_dvsec_rr_decode(dev, port, info);
+		rc = cxl_dvsec_rr_decode(cxlds, info);
 	put_cxl_mock_ops(index);
 
 	return rc;
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index b3b00269a52a..b0049be00c70 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -38,9 +38,6 @@ CONFIG_IWLWIFI=y
 CONFIG_DAMON=y
 CONFIG_DAMON_VADDR=y
 CONFIG_DAMON_PADDR=y
-CONFIG_DEBUG_FS=y
-CONFIG_DAMON_DBGFS=y
-CONFIG_DAMON_DBGFS_DEPRECATED=y
 
 CONFIG_REGMAP_BUILD=y
 
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index cffaf2245d4f..eaff1b036989 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -227,6 +227,7 @@ static void *load_creator(void *ptr)
 			unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) -
 						(1 << order);
 			item_insert_order(tree, index, order);
+			xa_set_mark(tree, index, XA_MARK_1);
 			item_delete_rcu(tree, index);
 		}
 	}
@@ -242,8 +243,11 @@ static void *load_worker(void *ptr)
 
 	rcu_register_thread();
 	while (!stop_iteration) {
+		unsigned long find_index = (2 << RADIX_TREE_MAP_SHIFT) + 1;
 		struct item *item = xa_load(ptr, index);
 		assert(!xa_is_internal(item));
+		item = xa_find(ptr, &find_index, index, XA_MARK_1);
+		assert(!xa_is_internal(item));
 	}
 	rcu_unregister_thread();
 
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 50931cd6aff2..8daac70c2f9d 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -18,6 +18,7 @@ TARGETS += devices/error_logs
 TARGETS += devices/probe
 TARGETS += dmabuf-heaps
 TARGETS += drivers/dma-buf
+TARGETS += drivers/ntsync
 TARGETS += drivers/s390x/uvdevice
 TARGETS += drivers/net
 TARGETS += drivers/net/bonding
diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c
index 38034fb82530..02b82774469c 100644
--- a/tools/testing/selftests/bpf/progs/find_vma.c
+++ b/tools/testing/selftests/bpf/progs/find_vma.c
@@ -25,7 +25,7 @@ static long check_vma(struct task_struct *task, struct vm_area_struct *vma,
 {
 	if (vma->vm_file)
 		bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1,
-					  vma->vm_file->f_path.dentry->d_iname);
+					  vma->vm_file->f_path.dentry->d_shortname.string);
 
 	/* check for VM_EXEC */
 	if (vma->vm_flags & VM_EXEC)
diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore
index 2ab675fecb6b..2f0297657c81 100644
--- a/tools/testing/selftests/damon/.gitignore
+++ b/tools/testing/selftests/damon/.gitignore
@@ -1,6 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-huge_count_read_write
-debugfs_target_ids_read_before_terminate_race
-debugfs_target_ids_pid_leak
 access_memory
 access_memory_even
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 812f656260fb..ecbf07afc6dd 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -1,15 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for damon selftests
 
-TEST_GEN_FILES += huge_count_read_write
-TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race
-TEST_GEN_FILES += debugfs_target_ids_pid_leak
 TEST_GEN_FILES += access_memory access_memory_even
 
-TEST_FILES = _chk_dependency.sh _debugfs_common.sh _damon_sysfs.py
+TEST_FILES = _chk_dependency.sh _damon_sysfs.py
 
 # functionality tests
-TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
 TEST_PROGS += sysfs.sh
 TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py
 TEST_PROGS += damos_quota.py damos_quota_goal.py damos_apply_interval.py
@@ -17,11 +13,6 @@ TEST_PROGS += damos_tried_regions.py damon_nr_regions.py
 TEST_PROGS += reclaim.sh lru_sort.sh
 
 # regression tests (reproducers of previously found bugs)
-TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
-TEST_PROGS += debugfs_duplicate_context_creation.sh
-TEST_PROGS += debugfs_rm_non_contexts.sh
-TEST_PROGS += debugfs_target_ids_read_before_terminate_race.sh
-TEST_PROGS += debugfs_target_ids_pid_leak.sh
 TEST_PROGS += sysfs_update_removed_scheme_dir.sh
 TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py
 
diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config
index 0daf38974eb0..a68a9fead5dc 100644
--- a/tools/testing/selftests/damon/config
+++ b/tools/testing/selftests/damon/config
@@ -1,6 +1,5 @@
 CONFIG_DAMON=y
 CONFIG_DAMON_SYSFS=y
-CONFIG_DAMON_DBGFS=y
 CONFIG_DAMON_PADDR=y
 CONFIG_DAMON_VADDR=y
 CONFIG_DAMON_RECLAIM=y
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
deleted file mode 100755
index 902e312bca89..000000000000
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ /dev/null
@@ -1,17 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test attrs file
-# ===============
-
-file="$DBGFS/attrs"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5" "$orig_content" "valid input"
-test_write_fail "$file" "1 2 3 4" "$orig_content" "no enough fields"
-test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
-	"min_nr_regions > max_nr_regions"
-test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
-echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
deleted file mode 100755
index bd6c22d96ead..000000000000
--- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
+++ /dev/null
@@ -1,27 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test duplicated context creation
-# ================================
-
-if ! echo foo > "$DBGFS/mk_contexts"
-then
-	echo "context creation failed"
-	exit 1
-fi
-
-if echo foo > "$DBGFS/mk_contexts" 2> /dev/null
-then
-	echo "duplicate context creation success"
-	exit 1
-fi
-
-if ! echo foo > "$DBGFS/rm_contexts"
-then
-	echo "context deletion failed"
-	exit 1
-fi
-
-exit 0
diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh
deleted file mode 100755
index effbea33dc16..000000000000
--- a/tools/testing/selftests/damon/debugfs_empty_targets.sh
+++ /dev/null
@@ -1,21 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test empty targets case
-# =======================
-
-orig_target_ids=$(cat "$DBGFS/target_ids")
-echo "" > "$DBGFS/target_ids"
-
-if [ -f "$DBGFS/monitor_on_DEPRECATED" ]
-then
-	monitor_on_file="$DBGFS/monitor_on_DEPRECATED"
-else
-	monitor_on_file="$DBGFS/monitor_on"
-fi
-
-orig_monitor_on=$(cat "$monitor_on_file")
-test_write_fail "$monitor_on_file" "on" "orig_monitor_on" "empty target ids"
-echo "$orig_target_ids" > "$DBGFS/target_ids"
diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
deleted file mode 100755
index 922cadac2950..000000000000
--- a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
+++ /dev/null
@@ -1,22 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test huge count read write
-# ==========================
-
-dmesg -C
-
-for file in "$DBGFS/"*
-do
-	./huge_count_read_write "$file"
-done
-
-if dmesg | grep -q WARNING
-then
-	dmesg
-	exit 1
-else
-	exit 0
-fi
diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh
deleted file mode 100755
index f3ffeb1343cf..000000000000
--- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test putting non-ctx files/dirs to rm_contexts file
-# ===================================================
-
-dmesg -C
-
-for file in "$DBGFS/"*
-do
-	(echo "$(basename "$f")" > "$DBGFS/rm_contexts") &> /dev/null
-	if dmesg | grep -q BUG
-	then
-		dmesg
-		exit 1
-	fi
-done
diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh
deleted file mode 100755
index 5b39ab44731c..000000000000
--- a/tools/testing/selftests/damon/debugfs_schemes.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test schemes file
-# =================
-
-file="$DBGFS/schemes"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
-	"$orig_content" "valid input"
-test_write_fail "$file" "1 2
-3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
-test_write_succ "$file" "" "$orig_content" "disabling"
-test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
-	"$orig_content" "wrong condition ranges"
-echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh
deleted file mode 100755
index 49aeabdb0aae..000000000000
--- a/tools/testing/selftests/damon/debugfs_target_ids.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test target_ids file
-# ====================
-
-file="$DBGFS/target_ids"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
-test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
-test_content "$file" "$orig_content" "1 2" "non-integer was there"
-test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
-test_content "$file" "$orig_content" "" "wrong input written"
-test_write_succ "$file" "" "$orig_content" "empty input"
-test_content "$file" "$orig_content" "" "empty input written"
-echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c
deleted file mode 100644
index 0cc2eef7d142..000000000000
--- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c
+++ /dev/null
@@ -1,68 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Author: SeongJae Park <sj@kernel.org>
- */
-
-#define _GNU_SOURCE
-
-#include <fcntl.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <sys/time.h>
-#include <unistd.h>
-
-#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids"
-
-static void write_targetid_exit(void)
-{
-	int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR);
-	char pid_str[128];
-
-	snprintf(pid_str, sizeof(pid_str), "%d", getpid());
-	write(target_ids_fd, pid_str, sizeof(pid_str));
-	close(target_ids_fd);
-	exit(0);
-}
-
-unsigned long msec_timestamp(void)
-{
-	struct timeval tv;
-
-	gettimeofday(&tv, NULL);
-	return tv.tv_sec * 1000UL + tv.tv_usec / 1000;
-}
-
-int main(int argc, char *argv[])
-{
-	unsigned long start_ms;
-	int time_to_run, nr_forks = 0;
-
-	if (argc != 2) {
-		fprintf(stderr, "Usage: %s <msecs to run>\n", argv[0]);
-		exit(1);
-	}
-	time_to_run = atoi(argv[1]);
-
-	start_ms = msec_timestamp();
-	while (true) {
-		int pid = fork();
-
-		if (pid < 0) {
-			fprintf(stderr, "fork() failed\n");
-			exit(1);
-		}
-		if (pid == 0)
-			write_targetid_exit();
-		wait(NULL);
-		nr_forks++;
-
-		if (msec_timestamp() - start_ms > time_to_run)
-			break;
-	}
-	printf("%d\n", nr_forks);
-	return 0;
-}
diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh
deleted file mode 100755
index 31fe33c2b032..000000000000
--- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh
+++ /dev/null
@@ -1,22 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-before=$(grep "^pid " /proc/slabinfo | awk '{print $2}')
-
-nr_leaks=$(./debugfs_target_ids_pid_leak 1000)
-expected_after_max=$((before + nr_leaks / 2))
-
-after=$(grep "^pid " /proc/slabinfo | awk '{print $2}')
-
-echo > /sys/kernel/debug/damon/target_ids
-
-echo "tried $nr_leaks pid leak"
-echo "number of active pid slabs: $before -> $after"
-echo "(up to $expected_after_max expected)"
-if [ $after -gt $expected_after_max ]
-then
-	echo "maybe pids are leaking"
-	exit 1
-else
-	exit 0
-fi
diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c
deleted file mode 100644
index b06f52a8ce2d..000000000000
--- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Author: SeongJae Park <sj@kernel.org>
- */
-#define _GNU_SOURCE
-
-#include <fcntl.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <time.h>
-#include <unistd.h>
-
-#define DBGFS_MONITOR_ON "/sys/kernel/debug/damon/monitor_on_DEPRECATED"
-#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids"
-
-static void turn_damon_on_exit(void)
-{
-	int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR);
-	int monitor_on_fd = open(DBGFS_MONITOR_ON, O_RDWR);
-	char pid_str[128];
-
-	snprintf(pid_str, sizeof(pid_str), "%d", getpid());
-	write(target_ids_fd, pid_str, sizeof(pid_str));
-	write(monitor_on_fd, "on\n", 3);
-	close(target_ids_fd);
-	close(monitor_on_fd);
-	usleep(1000);
-	exit(0);
-}
-
-static void try_race(void)
-{
-	int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR);
-	int pid = fork();
-	int buf[256];
-
-	if (pid < 0) {
-		fprintf(stderr, "fork() failed\n");
-		exit(1);
-	}
-	if (pid == 0)
-		turn_damon_on_exit();
-	while (true) {
-		int status;
-
-		read(target_ids_fd, buf, sizeof(buf));
-		if (waitpid(-1, &status, WNOHANG) == pid)
-			break;
-	}
-	close(target_ids_fd);
-}
-
-static inline uint64_t ts_to_ms(struct timespec *ts)
-{
-	return (uint64_t)ts->tv_sec * 1000 + (uint64_t)ts->tv_nsec / 1000000;
-}
-
-int main(int argc, char *argv[])
-{
-	struct timespec start_time, now;
-	int runtime_ms;
-
-	if (argc != 2) {
-		fprintf(stderr, "Usage: %s <runtime in ms>\n", argv[0]);
-		exit(1);
-	}
-	runtime_ms = atoi(argv[1]);
-	clock_gettime(CLOCK_MONOTONIC, &start_time);
-	while (true) {
-		try_race();
-		clock_gettime(CLOCK_MONOTONIC, &now);
-		if (ts_to_ms(&now) - ts_to_ms(&start_time) > runtime_ms)
-			break;
-	}
-	return 0;
-}
diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh
deleted file mode 100755
index fc793c4c9aea..000000000000
--- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-dmesg -C
-
-./debugfs_target_ids_read_before_terminate_race 5000
-
-if dmesg | grep -q dbgfs_target_ids_read
-then
-	dmesg
-	exit 1
-else
-	exit 0
-fi
diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c
deleted file mode 100644
index 53e69a669668..000000000000
--- a/tools/testing/selftests/damon/huge_count_read_write.c
+++ /dev/null
@@ -1,46 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Author: SeongJae Park <sj@kernel.org>
- */
-
-#include <fcntl.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <stdio.h>
-
-#pragma GCC diagnostic push
-#if __GNUC__ >= 11 && __GNUC_MINOR__ >= 1
-/* Ignore read(2) overflow and write(2) overread compile warnings */
-#pragma GCC diagnostic ignored "-Wstringop-overread"
-#pragma GCC diagnostic ignored "-Wstringop-overflow"
-#endif
-
-void write_read_with_huge_count(char *file)
-{
-	int filedesc = open(file, O_RDWR);
-	char buf[256];
-	int ret;
-
-	printf("%s %s\n", __func__, file);
-	if (filedesc < 0) {
-		fprintf(stderr, "failed opening %s\n", file);
-		exit(1);
-	}
-
-	write(filedesc, "", 0xfffffffful);
-	ret = read(filedesc, buf, 0xfffffffful);
-	close(filedesc);
-}
-
-#pragma GCC diagnostic pop
-
-int main(int argc, char *argv[])
-{
-	if (argc != 2) {
-		fprintf(stderr, "Usage: %s <file>\n", argv[0]);
-		exit(1);
-	}
-	write_read_with_huge_count(argv[1]);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index ca8a7edff3dd..319aaa004c40 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -252,6 +252,7 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True):
         try:
             # this targets queue 4, which doesn't exist
             ntuple2 = ethtool_create(cfg, "-N", flow)
+            defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}")
         except CmdExitFailure:
             pass
         else:
@@ -259,7 +260,13 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True):
         # change the table to target queues 0 and 2
         ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0")
         # ntuple rule therefore targets queues 1 and 3
-        ntuple2 = ethtool_create(cfg, "-N", flow)
+        try:
+            ntuple2 = ethtool_create(cfg, "-N", flow)
+        except CmdExitFailure:
+            ksft_pr("Driver does not support rss + queue offset")
+            return
+
+        defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}")
         # should replace existing filter
         ksft_eq(ntuple, ntuple2)
         _send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3),
diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
index 384cfa3d38a6..92c2f0376c08 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -142,7 +142,7 @@ function pre_ethtool {
 }
 
 function check_table {
-    local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1
+    local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1
     local -n expected=$2
     local last=$3
 
@@ -212,7 +212,7 @@ function check_tables {
 }
 
 function print_table {
-    local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1
+    local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1
     read -a have < $path
 
     tree $NSIM_DEV_DFS/
@@ -641,7 +641,7 @@ for port in 0 1; do
     NSIM_NETDEV=`get_netdev_name old_netdevs`
     ip link set dev $NSIM_NETDEV up
 
-    echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
+    echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error
 
     msg="1 - create VxLANs v6"
     exp0=( 0 0 0 0 )
@@ -663,7 +663,7 @@ for port in 0 1; do
     new_geneve gnv0 20000
 
     msg="2 - destroy GENEVE"
-    echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
+    echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error
     exp1=( `mke 20000 2` 0 0 0 )
     del_dev gnv0
 
@@ -764,7 +764,7 @@ for port in 0 1; do
     msg="create VxLANs v4"
     new_vxlan vxlan0 10000 $NSIM_NETDEV
 
-    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
     check_tables
 
     msg="NIC device goes down"
@@ -775,7 +775,7 @@ for port in 0 1; do
     fi
     check_tables
 
-    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
     check_tables
 
     msg="NIC device goes up again"
@@ -789,7 +789,7 @@ for port in 0 1; do
     del_dev vxlan0
     check_tables
 
-    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
     check_tables
 
     msg="destroy NIC"
@@ -896,7 +896,7 @@ msg="vacate VxLAN in overflow table"
 exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` )
 del_dev vxlan2
 
-echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
 check_tables
 
 msg="tunnels destroyed 2"
diff --git a/tools/testing/selftests/drivers/ntsync/.gitignore b/tools/testing/selftests/drivers/ntsync/.gitignore
new file mode 100644
index 000000000000..848573a3d3ea
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/.gitignore
@@ -0,0 +1 @@
+ntsync
diff --git a/tools/testing/selftests/drivers/ntsync/Makefile b/tools/testing/selftests/drivers/ntsync/Makefile
new file mode 100644
index 000000000000..dbf2b055c0b2
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/Makefile
@@ -0,0 +1,7 @@
+# SPDX-LICENSE-IDENTIFIER: GPL-2.0-only
+TEST_GEN_PROGS := ntsync
+
+CFLAGS += $(KHDR_INCLUDES)
+LDLIBS += -lpthread
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/drivers/ntsync/config b/tools/testing/selftests/drivers/ntsync/config
new file mode 100644
index 000000000000..60539c826d06
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/config
@@ -0,0 +1 @@
+CONFIG_WINESYNC=y
diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c
new file mode 100644
index 000000000000..3aad311574c4
--- /dev/null
+++ b/tools/testing/selftests/drivers/ntsync/ntsync.c
@@ -0,0 +1,1343 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Various unit tests for the "ntsync" synchronization primitive driver.
+ *
+ * Copyright (C) 2021-2022 Elizabeth Figura <zfigura@codeweavers.com>
+ */
+
+#define _GNU_SOURCE
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/ntsync.h>
+#include "../../kselftest_harness.h"
+
+static int read_sem_state(int sem, __u32 *count, __u32 *max)
+{
+	struct ntsync_sem_args args;
+	int ret;
+
+	memset(&args, 0xcc, sizeof(args));
+	ret = ioctl(sem, NTSYNC_IOC_SEM_READ, &args);
+	*count = args.count;
+	*max = args.max;
+	return ret;
+}
+
+#define check_sem_state(sem, count, max) \
+	({ \
+		__u32 __count, __max; \
+		int ret = read_sem_state((sem), &__count, &__max); \
+		EXPECT_EQ(0, ret); \
+		EXPECT_EQ((count), __count); \
+		EXPECT_EQ((max), __max); \
+	})
+
+static int release_sem(int sem, __u32 *count)
+{
+	return ioctl(sem, NTSYNC_IOC_SEM_RELEASE, count);
+}
+
+static int read_mutex_state(int mutex, __u32 *count, __u32 *owner)
+{
+	struct ntsync_mutex_args args;
+	int ret;
+
+	memset(&args, 0xcc, sizeof(args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &args);
+	*count = args.count;
+	*owner = args.owner;
+	return ret;
+}
+
+#define check_mutex_state(mutex, count, owner) \
+	({ \
+		__u32 __count, __owner; \
+		int ret = read_mutex_state((mutex), &__count, &__owner); \
+		EXPECT_EQ(0, ret); \
+		EXPECT_EQ((count), __count); \
+		EXPECT_EQ((owner), __owner); \
+	})
+
+static int unlock_mutex(int mutex, __u32 owner, __u32 *count)
+{
+	struct ntsync_mutex_args args;
+	int ret;
+
+	args.owner = owner;
+	args.count = 0xdeadbeef;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_UNLOCK, &args);
+	*count = args.count;
+	return ret;
+}
+
+static int read_event_state(int event, __u32 *signaled, __u32 *manual)
+{
+	struct ntsync_event_args args;
+	int ret;
+
+	memset(&args, 0xcc, sizeof(args));
+	ret = ioctl(event, NTSYNC_IOC_EVENT_READ, &args);
+	*signaled = args.signaled;
+	*manual = args.manual;
+	return ret;
+}
+
+#define check_event_state(event, signaled, manual) \
+	({ \
+		__u32 __signaled, __manual; \
+		int ret = read_event_state((event), &__signaled, &__manual); \
+		EXPECT_EQ(0, ret); \
+		EXPECT_EQ((signaled), __signaled); \
+		EXPECT_EQ((manual), __manual); \
+	})
+
+static int wait_objs(int fd, unsigned long request, __u32 count,
+		     const int *objs, __u32 owner, int alert, __u32 *index)
+{
+	struct ntsync_wait_args args = {0};
+	struct timespec timeout;
+	int ret;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	args.timeout = timeout.tv_sec * 1000000000 + timeout.tv_nsec;
+	args.count = count;
+	args.objs = (uintptr_t)objs;
+	args.owner = owner;
+	args.index = 0xdeadbeef;
+	args.alert = alert;
+	ret = ioctl(fd, request, &args);
+	*index = args.index;
+	return ret;
+}
+
+static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ANY, count, objs, owner, 0, index);
+}
+
+static int wait_all(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ALL, count, objs, owner, 0, index);
+}
+
+static int wait_any_alert(int fd, __u32 count, const int *objs,
+			  __u32 owner, int alert, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ANY,
+			 count, objs, owner, alert, index);
+}
+
+static int wait_all_alert(int fd, __u32 count, const int *objs,
+			  __u32 owner, int alert, __u32 *index)
+{
+	return wait_objs(fd, NTSYNC_IOC_WAIT_ALL,
+			 count, objs, owner, alert, index);
+}
+
+TEST(semaphore_state)
+{
+	struct ntsync_sem_args sem_args;
+	struct timespec timeout;
+	__u32 count, index;
+	int fd, ret, sem;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 3;
+	sem_args.max = 2;
+	sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_EQ(-1, sem);
+	EXPECT_EQ(EINVAL, errno);
+
+	sem_args.count = 2;
+	sem_args.max = 2;
+	sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, sem);
+	check_sem_state(sem, 2, 2);
+
+	count = 0;
+	ret = release_sem(sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+	check_sem_state(sem, 2, 2);
+
+	count = 1;
+	ret = release_sem(sem, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOVERFLOW, errno);
+	check_sem_state(sem, 2, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem, 1, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(sem, 0, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	count = 3;
+	ret = release_sem(sem, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOVERFLOW, errno);
+	check_sem_state(sem, 0, 2);
+
+	count = 2;
+	ret = release_sem(sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(sem, 2, 2);
+
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+	ret = wait_any(fd, 1, &sem, 123, &index);
+	EXPECT_EQ(0, ret);
+
+	count = 1;
+	ret = release_sem(sem, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(sem, 1, 2);
+
+	count = ~0u;
+	ret = release_sem(sem, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOVERFLOW, errno);
+	check_sem_state(sem, 1, 2);
+
+	close(sem);
+
+	close(fd);
+}
+
+TEST(mutex_state)
+{
+	struct ntsync_mutex_args mutex_args;
+	__u32 owner, count, index;
+	struct timespec timeout;
+	int fd, ret, mutex;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 0;
+	mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(-1, mutex);
+	EXPECT_EQ(EINVAL, errno);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 2;
+	mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_EQ(-1, mutex);
+	EXPECT_EQ(EINVAL, errno);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 2;
+	mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, mutex);
+	check_mutex_state(mutex, 2, 123);
+
+	ret = unlock_mutex(mutex, 0, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	ret = unlock_mutex(mutex, 456, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EPERM, errno);
+	check_mutex_state(mutex, 2, 123);
+
+	ret = unlock_mutex(mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+	check_mutex_state(mutex, 1, 123);
+
+	ret = unlock_mutex(mutex, 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, count);
+	check_mutex_state(mutex, 0, 0);
+
+	ret = unlock_mutex(mutex, 123, &count);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EPERM, errno);
+
+	ret = wait_any(fd, 1, &mutex, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 456);
+
+	ret = wait_any(fd, 1, &mutex, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 2, 456);
+
+	ret = unlock_mutex(mutex, 456, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+	check_mutex_state(mutex, 1, 456);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	owner = 0;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	owner = 123;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EPERM, errno);
+	check_mutex_state(mutex, 1, 456);
+
+	owner = 456;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	memset(&mutex_args, 0xcc, sizeof(mutex_args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, mutex_args.count);
+	EXPECT_EQ(0, mutex_args.owner);
+
+	memset(&mutex_args, 0xcc, sizeof(mutex_args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, mutex_args.count);
+	EXPECT_EQ(0, mutex_args.owner);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 123);
+
+	owner = 123;
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	memset(&mutex_args, 0xcc, sizeof(mutex_args));
+	ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, mutex_args.count);
+	EXPECT_EQ(0, mutex_args.owner);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 123);
+
+	close(mutex);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, mutex);
+	check_mutex_state(mutex, 0, 0);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_mutex_state(mutex, 1, 123);
+
+	close(mutex);
+
+	mutex_args.owner = 123;
+	mutex_args.count = ~0u;
+	mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, mutex);
+	check_mutex_state(mutex, ~0u, 123);
+
+	ret = wait_any(fd, 1, &mutex, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	close(mutex);
+
+	close(fd);
+}
+
+TEST(manual_event_state)
+{
+	struct ntsync_event_args event_args;
+	__u32 index, signaled;
+	int fd, event, ret;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	event_args.manual = 1;
+	event_args.signaled = 0;
+	event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, event);
+	check_event_state(event, 0, 1);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 1, 1);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 1, 1);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_event_state(event, 1, 1);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 0, 1);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 1);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 0, 1);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 1);
+
+	close(event);
+
+	close(fd);
+}
+
+TEST(auto_event_state)
+{
+	struct ntsync_event_args event_args;
+	__u32 index, signaled;
+	int fd, event, ret;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	event_args.manual = 0;
+	event_args.signaled = 1;
+	event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, event);
+
+	check_event_state(event, 1, 0);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 1, 0);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_event_state(event, 0, 0);
+
+	signaled = 0xdeadbeef;
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 0);
+
+	ret = wait_any(fd, 1, &event, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+	check_event_state(event, 0, 0);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(event, 0, 0);
+
+	close(event);
+
+	close(fd);
+}
+
+TEST(test_wait_any)
+{
+	int objs[NTSYNC_MAX_WAIT_COUNT + 1], fd, ret;
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	__u32 owner, index, count, i;
+	struct timespec timeout;
+
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 2;
+	sem_args.max = 3;
+	objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[0]);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, objs[1]);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 1, 3);
+	check_mutex_state(objs[1], 0, 0);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 0, 3);
+	check_mutex_state(objs[1], 0, 0);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+	check_sem_state(objs[0], 0, 3);
+	check_mutex_state(objs[1], 1, 123);
+
+	count = 1;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 0, 3);
+	check_mutex_state(objs[1], 1, 123);
+
+	ret = wait_any(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+	check_sem_state(objs[0], 0, 3);
+	check_mutex_state(objs[1], 2, 123);
+
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	owner = 123;
+	ret = ioctl(objs[1], NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	EXPECT_EQ(1, index);
+
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+
+	close(objs[1]);
+
+	/* test waiting on the same object twice */
+
+	count = 2;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	objs[1] = objs[0];
+	ret = wait_any(fd, 2, objs, 456, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 1, 3);
+
+	ret = wait_any(fd, 0, NULL, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	for (i = 1; i < NTSYNC_MAX_WAIT_COUNT + 1; ++i)
+		objs[i] = objs[0];
+
+	ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT + 1, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	ret = wait_any(fd, -1, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	close(objs[0]);
+
+	close(fd);
+}
+
+TEST(test_wait_all)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	__u32 owner, index, count;
+	int objs[2], fd, ret;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 2;
+	sem_args.max = 3;
+	objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[0]);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, objs[1]);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 1, 3);
+	check_mutex_state(objs[1], 1, 123);
+
+	ret = wait_all(fd, 2, objs, 456, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+	check_sem_state(objs[0], 1, 3);
+	check_mutex_state(objs[1], 1, 123);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 0, 3);
+	check_mutex_state(objs[1], 2, 123);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+	check_sem_state(objs[0], 0, 3);
+	check_mutex_state(objs[1], 2, 123);
+
+	count = 3;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 2, 3);
+	check_mutex_state(objs[1], 3, 123);
+
+	owner = 123;
+	ret = ioctl(objs[1], NTSYNC_IOC_MUTEX_KILL, &owner);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EOWNERDEAD, errno);
+	check_sem_state(objs[0], 1, 3);
+	check_mutex_state(objs[1], 1, 123);
+
+	close(objs[1]);
+
+	event_args.manual = true;
+	event_args.signaled = true;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, objs[1]);
+
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+	check_sem_state(objs[0], 0, 3);
+	check_event_state(objs[1], 1, 1);
+
+	close(objs[1]);
+
+	/* test waiting on the same object twice */
+	objs[1] = objs[0];
+	ret = wait_all(fd, 2, objs, 123, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(EINVAL, errno);
+
+	close(objs[0]);
+
+	close(fd);
+}
+
+struct wake_args {
+	int fd;
+	int obj;
+};
+
+struct wait_args {
+	int fd;
+	unsigned long request;
+	struct ntsync_wait_args *args;
+	int ret;
+	int err;
+};
+
+static void *wait_thread(void *arg)
+{
+	struct wait_args *args = arg;
+
+	args->ret = ioctl(args->fd, args->request, args->args);
+	args->err = errno;
+	return NULL;
+}
+
+static __u64 get_abs_timeout(unsigned int ms)
+{
+	struct timespec timeout;
+	clock_gettime(CLOCK_MONOTONIC, &timeout);
+	return (timeout.tv_sec * 1000000000) + timeout.tv_nsec + (ms * 1000000);
+}
+
+static int wait_for_thread(pthread_t thread, unsigned int ms)
+{
+	struct timespec timeout;
+
+	clock_gettime(CLOCK_REALTIME, &timeout);
+	timeout.tv_nsec += ms * 1000000;
+	timeout.tv_sec += (timeout.tv_nsec / 1000000000);
+	timeout.tv_nsec %= 1000000000;
+	return pthread_timedjoin_np(thread, NULL, &timeout);
+}
+
+TEST(wake_any)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	struct wait_args thread_args;
+	__u32 count, index, signaled;
+	int objs[2], fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 0;
+	sem_args.max = 3;
+	objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[0]);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 1;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, objs[1]);
+
+	/* test waking the semaphore */
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 2;
+	wait_args.owner = 456;
+	wait_args.index = 0xdeadbeef;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ANY;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	count = 1;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(objs[0], 0, 3);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(0, wait_args.index);
+
+	/* test waking the mutex */
+
+	/* first grab it again for owner 123 */
+	ret = wait_any(fd, 1, &objs[1], 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.owner = 456;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = unlock_mutex(objs[1], 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, count);
+
+	ret = pthread_tryjoin_np(thread, NULL);
+	EXPECT_EQ(EBUSY, ret);
+
+	ret = unlock_mutex(objs[1], 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, mutex_args.count);
+	check_mutex_state(objs[1], 1, 456);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	close(objs[1]);
+
+	/* test waking events */
+
+	event_args.manual = false;
+	event_args.signaled = false;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, objs[1]);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(objs[1], NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(objs[1], 0, 0);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(objs[1], 0, 0);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	close(objs[1]);
+
+	event_args.manual = true;
+	event_args.signaled = false;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, objs[1]);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(objs[1], NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(objs[1], 1, 1);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	ret = ioctl(objs[1], NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+	check_event_state(objs[1], 0, 1);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(1, wait_args.index);
+
+	/* delete an object while it's being waited on */
+
+	wait_args.timeout = get_abs_timeout(200);
+	wait_args.owner = 123;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	close(objs[0]);
+	close(objs[1]);
+
+	ret = wait_for_thread(thread, 200);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(-1, thread_args.ret);
+	EXPECT_EQ(ETIMEDOUT, thread_args.err);
+
+	close(fd);
+}
+
+TEST(wake_all)
+{
+	struct ntsync_event_args manual_event_args = {0};
+	struct ntsync_event_args auto_event_args = {0};
+	struct ntsync_mutex_args mutex_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	struct wait_args thread_args;
+	__u32 count, index, signaled;
+	int objs[4], fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 0;
+	sem_args.max = 3;
+	objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[0]);
+
+	mutex_args.owner = 123;
+	mutex_args.count = 1;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, objs[1]);
+
+	manual_event_args.manual = true;
+	manual_event_args.signaled = true;
+	objs[2] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &manual_event_args);
+	EXPECT_LE(0, objs[2]);
+
+	auto_event_args.manual = false;
+	auto_event_args.signaled = true;
+	objs[3] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &auto_event_args);
+	EXPECT_EQ(0, objs[3]);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 4;
+	wait_args.owner = 456;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ALL;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	count = 1;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+
+	ret = pthread_tryjoin_np(thread, NULL);
+	EXPECT_EQ(EBUSY, ret);
+
+	check_sem_state(objs[0], 1, 3);
+
+	ret = wait_any(fd, 1, &objs[0], 123, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = unlock_mutex(objs[1], 123, &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, count);
+
+	ret = pthread_tryjoin_np(thread, NULL);
+	EXPECT_EQ(EBUSY, ret);
+
+	check_mutex_state(objs[1], 0, 0);
+
+	ret = ioctl(objs[2], NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+
+	count = 2;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, count);
+	check_sem_state(objs[0], 2, 3);
+
+	ret = ioctl(objs[3], NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, signaled);
+
+	ret = ioctl(objs[2], NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	ret = ioctl(objs[3], NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, signaled);
+
+	check_sem_state(objs[0], 1, 3);
+	check_mutex_state(objs[1], 1, 456);
+	check_event_state(objs[2], 1, 1);
+	check_event_state(objs[3], 0, 0);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+
+	/* delete an object while it's being waited on */
+
+	wait_args.timeout = get_abs_timeout(200);
+	wait_args.owner = 123;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	close(objs[0]);
+	close(objs[1]);
+	close(objs[2]);
+	close(objs[3]);
+
+	ret = wait_for_thread(thread, 200);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(-1, thread_args.ret);
+	EXPECT_EQ(ETIMEDOUT, thread_args.err);
+
+	close(fd);
+}
+
+TEST(alert_any)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	__u32 index, count, signaled;
+	struct wait_args thread_args;
+	int objs[2], event, fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 0;
+	sem_args.max = 2;
+	objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[0]);
+
+	sem_args.count = 1;
+	sem_args.max = 2;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[1]);
+
+	event_args.manual = true;
+	event_args.signaled = true;
+	event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, event);
+
+	ret = wait_any_alert(fd, 0, NULL, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 0, NULL, 123, event, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(1, index);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	/* test wakeup via alert */
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 2;
+	wait_args.owner = 123;
+	wait_args.index = 0xdeadbeef;
+	wait_args.alert = event;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ANY;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(2, wait_args.index);
+
+	close(event);
+
+	/* test with an auto-reset event */
+
+	event_args.manual = false;
+	event_args.signaled = true;
+	event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, event);
+
+	count = 1;
+	ret = release_sem(objs[0], &count);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	ret = wait_any_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	close(event);
+
+	close(objs[0]);
+	close(objs[1]);
+
+	close(fd);
+}
+
+TEST(alert_all)
+{
+	struct ntsync_event_args event_args = {0};
+	struct ntsync_wait_args wait_args = {0};
+	struct ntsync_sem_args sem_args = {0};
+	struct wait_args thread_args;
+	__u32 index, count, signaled;
+	int objs[2], event, fd, ret;
+	pthread_t thread;
+
+	fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, fd);
+
+	sem_args.count = 2;
+	sem_args.max = 2;
+	objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[0]);
+
+	sem_args.count = 1;
+	sem_args.max = 2;
+	objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args);
+	EXPECT_LE(0, objs[1]);
+
+	event_args.manual = true;
+	event_args.signaled = true;
+	event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, event);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	/* test wakeup via alert */
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	wait_args.timeout = get_abs_timeout(1000);
+	wait_args.objs = (uintptr_t)objs;
+	wait_args.count = 2;
+	wait_args.owner = 123;
+	wait_args.index = 0xdeadbeef;
+	wait_args.alert = event;
+	thread_args.fd = fd;
+	thread_args.args = &wait_args;
+	thread_args.request = NTSYNC_IOC_WAIT_ALL;
+	ret = pthread_create(&thread, NULL, wait_thread, &thread_args);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(ETIMEDOUT, ret);
+
+	ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_for_thread(thread, 100);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, thread_args.ret);
+	EXPECT_EQ(2, wait_args.index);
+
+	close(event);
+
+	/* test with an auto-reset event */
+
+	event_args.manual = false;
+	event_args.signaled = true;
+	event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, event);
+
+	count = 2;
+	ret = release_sem(objs[1], &count);
+	EXPECT_EQ(0, ret);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(0, index);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(0, ret);
+	EXPECT_EQ(2, index);
+
+	ret = wait_all_alert(fd, 2, objs, 123, event, &index);
+	EXPECT_EQ(-1, ret);
+	EXPECT_EQ(ETIMEDOUT, errno);
+
+	close(event);
+
+	close(objs[0]);
+	close(objs[1]);
+
+	close(fd);
+}
+
+#define STRESS_LOOPS 10000
+#define STRESS_THREADS 4
+
+static unsigned int stress_counter;
+static int stress_device, stress_start_event, stress_mutex;
+
+static void *stress_thread(void *arg)
+{
+	struct ntsync_wait_args wait_args = {0};
+	__u32 index, count, i;
+	int ret;
+
+	wait_args.timeout = UINT64_MAX;
+	wait_args.count = 1;
+	wait_args.objs = (uintptr_t)&stress_start_event;
+	wait_args.owner = gettid();
+	wait_args.index = 0xdeadbeef;
+
+	ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args);
+
+	wait_args.objs = (uintptr_t)&stress_mutex;
+
+	for (i = 0; i < STRESS_LOOPS; ++i) {
+		ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args);
+
+		++stress_counter;
+
+		unlock_mutex(stress_mutex, wait_args.owner, &count);
+	}
+
+	return NULL;
+}
+
+TEST(stress_wait)
+{
+	struct ntsync_event_args event_args;
+	struct ntsync_mutex_args mutex_args;
+	pthread_t threads[STRESS_THREADS];
+	__u32 signaled, i;
+	int ret;
+
+	stress_device = open("/dev/ntsync", O_CLOEXEC | O_RDONLY);
+	ASSERT_LE(0, stress_device);
+
+	mutex_args.owner = 0;
+	mutex_args.count = 0;
+	stress_mutex = ioctl(stress_device, NTSYNC_IOC_CREATE_MUTEX, &mutex_args);
+	EXPECT_LE(0, stress_mutex);
+
+	event_args.manual = 1;
+	event_args.signaled = 0;
+	stress_start_event = ioctl(stress_device, NTSYNC_IOC_CREATE_EVENT, &event_args);
+	EXPECT_LE(0, stress_start_event);
+
+	for (i = 0; i < STRESS_THREADS; ++i)
+		pthread_create(&threads[i], NULL, stress_thread, NULL);
+
+	ret = ioctl(stress_start_event, NTSYNC_IOC_EVENT_SET, &signaled);
+	EXPECT_EQ(0, ret);
+
+	for (i = 0; i < STRESS_THREADS; ++i) {
+		ret = pthread_join(threads[i], NULL);
+		EXPECT_EQ(0, ret);
+	}
+
+	EXPECT_EQ(STRESS_LOOPS * STRESS_THREADS, stress_counter);
+
+	close(stress_start_event);
+	close(stress_mutex);
+	close(stress_device);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/exec/check-exec.c b/tools/testing/selftests/exec/check-exec.c
index 4d3f4525e1e1..55bce47e56b7 100644
--- a/tools/testing/selftests/exec/check-exec.c
+++ b/tools/testing/selftests/exec/check-exec.c
@@ -22,6 +22,7 @@
 #include <sys/prctl.h>
 #include <sys/socket.h>
 #include <sys/stat.h>
+#include <sys/syscall.h>
 #include <sys/sysmacros.h>
 #include <unistd.h>
 
@@ -31,6 +32,12 @@
 
 #include "../kselftest_harness.h"
 
+static int sys_execveat(int dirfd, const char *pathname, char *const argv[],
+			char *const envp[], int flags)
+{
+	return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags);
+}
+
 static void drop_privileges(struct __test_metadata *const _metadata)
 {
 	const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED;
@@ -219,8 +226,8 @@ static void test_exec_fd(struct __test_metadata *_metadata, const int fd,
 	 * test framework as an error.  With AT_EXECVE_CHECK, we only check a
 	 * potential successful execution.
 	 */
-	access_ret =
-		execveat(fd, "", argv, NULL, AT_EMPTY_PATH | AT_EXECVE_CHECK);
+	access_ret = sys_execveat(fd, "", argv, NULL,
+				  AT_EMPTY_PATH | AT_EXECVE_CHECK);
 	access_errno = errno;
 	if (err_code) {
 		EXPECT_EQ(-1, access_ret);
diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c
index 8eb6aa606a0d..46d289611ce8 100644
--- a/tools/testing/selftests/filesystems/statmount/statmount_test.c
+++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c
@@ -383,6 +383,10 @@ static void test_statmount_mnt_point(void)
 		return;
 	}
 
+	if (!(sm->mask & STATMOUNT_MNT_POINT)) {
+		ksft_test_result_fail("missing STATMOUNT_MNT_POINT in mask\n");
+		return;
+	}
 	if (strcmp(sm->str + sm->mnt_point, "/") != 0) {
 		ksft_test_result_fail("unexpected mount point: '%s' != '/'\n",
 				      sm->str + sm->mnt_point);
@@ -408,6 +412,10 @@ static void test_statmount_mnt_root(void)
 				      strerror(errno));
 		return;
 	}
+	if (!(sm->mask & STATMOUNT_MNT_ROOT)) {
+		ksft_test_result_fail("missing STATMOUNT_MNT_ROOT in mask\n");
+		return;
+	}
 	mnt_root = sm->str + sm->mnt_root;
 	last_root = strrchr(mnt_root, '/');
 	if (last_root)
@@ -437,6 +445,10 @@ static void test_statmount_fs_type(void)
 				      strerror(errno));
 		return;
 	}
+	if (!(sm->mask & STATMOUNT_FS_TYPE)) {
+		ksft_test_result_fail("missing STATMOUNT_FS_TYPE in mask\n");
+		return;
+	}
 	fs_type = sm->str + sm->fs_type;
 	for (s = known_fs; s != NULL; s++) {
 		if (strcmp(fs_type, *s) == 0)
@@ -464,6 +476,11 @@ static void test_statmount_mnt_opts(void)
 		return;
 	}
 
+	if (!(sm->mask & STATMOUNT_MNT_BASIC)) {
+		ksft_test_result_fail("missing STATMOUNT_MNT_BASIC in mask\n");
+		return;
+	}
+
 	while (getline(&line, &len, f_mountinfo) != -1) {
 		int i;
 		char *p, *p2;
@@ -514,7 +531,10 @@ static void test_statmount_mnt_opts(void)
 		if (p2)
 			*p2 = '\0';
 
-		statmount_opts = sm->str + sm->mnt_opts;
+		if (sm->mask & STATMOUNT_MNT_OPTS)
+			statmount_opts = sm->str + sm->mnt_opts;
+		else
+			statmount_opts = "";
 		if (strcmp(statmount_opts, p) != 0)
 			ksft_test_result_fail(
 				"unexpected mount options: '%s' != '%s'\n",
diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh
index 6fb66a687f17..bbc29ed9c60a 100755
--- a/tools/testing/selftests/gpio/gpio-sim.sh
+++ b/tools/testing/selftests/gpio/gpio-sim.sh
@@ -46,12 +46,6 @@ remove_chip() {
 	rmdir $CONFIGFS_DIR/$CHIP || fail "Unable to remove the chip"
 }
 
-configfs_cleanup() {
-	for CHIP in `ls $CONFIGFS_DIR/`; do
-		remove_chip $CHIP
-	done
-}
-
 create_chip() {
 	local CHIP=$1
 
@@ -105,6 +99,13 @@ disable_chip() {
 	echo 0 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to disable the chip"
 }
 
+configfs_cleanup() {
+	for CHIP in `ls $CONFIGFS_DIR/`; do
+		disable_chip $CHIP
+		remove_chip $CHIP
+	done
+}
+
 configfs_chip_name() {
 	local CHIP=$1
 	local BANK=$2
@@ -181,6 +182,7 @@ create_chip chip
 create_bank chip bank
 enable_chip chip
 test -n `cat $CONFIGFS_DIR/chip/bank/chip_name` || fail "chip_name doesn't work"
+disable_chip chip
 remove_chip chip
 
 echo "1.2. chip_name returns 'none' if the chip is still pending"
@@ -195,6 +197,7 @@ create_chip chip
 create_bank chip bank
 enable_chip chip
 test -n `cat $CONFIGFS_DIR/chip/dev_name` || fail "dev_name doesn't work"
+disable_chip chip
 remove_chip chip
 
 echo "2. Creating and configuring simulated chips"
@@ -204,6 +207,7 @@ create_chip chip
 create_bank chip bank
 enable_chip chip
 test "`get_chip_num_lines chip bank`" = "1" || fail "default number of lines is not 1"
+disable_chip chip
 remove_chip chip
 
 echo "2.2. Number of lines can be specified"
@@ -212,6 +216,7 @@ create_bank chip bank
 set_num_lines chip bank 16
 enable_chip chip
 test "`get_chip_num_lines chip bank`" = "16" || fail "number of lines is not 16"
+disable_chip chip
 remove_chip chip
 
 echo "2.3. Label can be set"
@@ -220,6 +225,7 @@ create_bank chip bank
 set_label chip bank foobar
 enable_chip chip
 test "`get_chip_label chip bank`" = "foobar" || fail "label is incorrect"
+disable_chip chip
 remove_chip chip
 
 echo "2.4. Label can be left empty"
@@ -227,6 +233,7 @@ create_chip chip
 create_bank chip bank
 enable_chip chip
 test -z "`cat $CONFIGFS_DIR/chip/bank/label`" || fail "label is not empty"
+disable_chip chip
 remove_chip chip
 
 echo "2.5. Line names can be configured"
@@ -238,6 +245,7 @@ set_line_name chip bank 2 bar
 enable_chip chip
 test "`get_line_name chip bank 0`" = "foo" || fail "line name is incorrect"
 test "`get_line_name chip bank 2`" = "bar" || fail "line name is incorrect"
+disable_chip chip
 remove_chip chip
 
 echo "2.6. Line config can remain unused if offset is greater than number of lines"
@@ -248,6 +256,7 @@ set_line_name chip bank 5 foobar
 enable_chip chip
 test "`get_line_name chip bank 0`" = "" || fail "line name is incorrect"
 test "`get_line_name chip bank 1`" = "" || fail "line name is incorrect"
+disable_chip chip
 remove_chip chip
 
 echo "2.7. Line configfs directory names are sanitized"
@@ -267,6 +276,7 @@ for CHIP in $CHIPS; do
 	enable_chip $CHIP
 done
 for CHIP in $CHIPS; do
+  disable_chip $CHIP
 	remove_chip $CHIP
 done
 
@@ -278,6 +288,7 @@ echo foobar > $CONFIGFS_DIR/chip/bank/label 2> /dev/null && \
 	fail "Setting label of a live chip should fail"
 echo 8 > $CONFIGFS_DIR/chip/bank/num_lines 2> /dev/null && \
 	fail "Setting number of lines of a live chip should fail"
+disable_chip chip
 remove_chip chip
 
 echo "2.10. Can't create line items when chip is live"
@@ -285,6 +296,7 @@ create_chip chip
 create_bank chip bank
 enable_chip chip
 mkdir $CONFIGFS_DIR/chip/bank/line0 2> /dev/null && fail "Creating line item should fail"
+disable_chip chip
 remove_chip chip
 
 echo "2.11. Probe errors are propagated to user-space"
@@ -316,6 +328,7 @@ mkdir -p $CONFIGFS_DIR/chip/bank/line4/hog
 enable_chip chip
 $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 4 2> /dev/null && \
 	fail "Setting the value of a hogged line shouldn't succeed"
+disable_chip chip
 remove_chip chip
 
 echo "3. Controlling simulated chips"
@@ -331,6 +344,7 @@ test "$?" = "1" || fail "pull set incorrectly"
 sysfs_set_pull chip bank 0 pull-down
 $BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 1
 test "$?" = "0" || fail "pull set incorrectly"
+disable_chip chip
 remove_chip chip
 
 echo "3.2. Pull can be read from sysfs"
@@ -344,6 +358,7 @@ SYSFS_PATH=/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull
 test `cat $SYSFS_PATH` = "pull-down" || fail "reading the pull failed"
 sysfs_set_pull chip bank 0 pull-up
 test `cat $SYSFS_PATH` = "pull-up" || fail "reading the pull failed"
+disable_chip chip
 remove_chip chip
 
 echo "3.3. Incorrect input in sysfs is rejected"
@@ -355,6 +370,7 @@ DEVNAME=`configfs_dev_name chip`
 CHIPNAME=`configfs_chip_name chip bank`
 SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull"
 echo foobar > $SYSFS_PATH 2> /dev/null && fail "invalid input not detected"
+disable_chip chip
 remove_chip chip
 
 echo "3.4. Can't write to value"
@@ -365,6 +381,7 @@ DEVNAME=`configfs_dev_name chip`
 CHIPNAME=`configfs_chip_name chip bank`
 SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value"
 echo 1 > $SYSFS_PATH 2> /dev/null && fail "writing to 'value' succeeded unexpectedly"
+disable_chip chip
 remove_chip chip
 
 echo "4. Simulated GPIO chips are functional"
@@ -382,6 +399,7 @@ $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 0 &
 sleep 0.1 # FIXME Any better way?
 test `cat $SYSFS_PATH` = "1" || fail "incorrect value read from sysfs"
 kill $!
+disable_chip chip
 remove_chip chip
 
 echo "4.2. Bias settings work correctly"
@@ -394,6 +412,7 @@ CHIPNAME=`configfs_chip_name chip bank`
 SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value"
 $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0
 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work"
+disable_chip chip
 remove_chip chip
 
 echo "GPIO $MODULE test PASS"
diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
index 447d61cae4db..cef8f7323ceb 100644
--- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
@@ -147,7 +147,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 
 	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
-	return el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY;
+	return el0 == ID_AA64PFR0_EL1_EL0_IMP;
 }
 
 int main(void)
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 3dd85ce8551c..217541fe6536 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -666,7 +666,7 @@ int main(void)
 	/* Check for AARCH64 only system */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
-	aarch64_only = (el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY);
+	aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP);
 
 	ksft_print_header();
 
diff --git a/tools/testing/selftests/kvm/s390/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c
index e32dd59703a0..85cc8c18d6e7 100644
--- a/tools/testing/selftests/kvm/s390/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390/cmma_test.c
@@ -444,7 +444,7 @@ static void assert_no_pages_cmma_dirty(struct kvm_vm *vm)
 			 );
 }
 
-static void test_get_inital_dirty(void)
+static void test_get_initial_dirty(void)
 {
 	struct kvm_vm *vm = create_vm_two_memslots();
 	struct kvm_vcpu *vcpu;
@@ -651,7 +651,7 @@ struct testdef {
 } testlist[] = {
 	{ "migration mode and dirty tracking", test_migration_mode },
 	{ "GET_CMMA_BITS: basic calls", test_get_cmma_basic },
-	{ "GET_CMMA_BITS: all pages are dirty initally", test_get_inital_dirty },
+	{ "GET_CMMA_BITS: all pages are dirty initially", test_get_initial_dirty },
 	{ "GET_CMMA_BITS: holes are skipped", test_get_skip_holes },
 };
 
diff --git a/tools/testing/selftests/kvm/s390/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c
index 135ee22856cf..d265b34c54be 100644
--- a/tools/testing/selftests/kvm/s390/ucontrol_test.c
+++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c
@@ -88,10 +88,6 @@ asm("test_skey_asm:\n"
 	"	ahi	%r0,1\n"
 	"	st	%r1,0(%r5,%r6)\n"
 
-	"	iske	%r1,%r6\n"
-	"	ahi	%r0,1\n"
-	"	diag	0,0,0x44\n"
-
 	"	sske	%r1,%r6\n"
 	"	xgr	%r1,%r1\n"
 	"	iske	%r1,%r6\n"
@@ -459,10 +455,14 @@ TEST_F(uc_kvm, uc_no_user_region)
 	};
 
 	ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, &region));
-	ASSERT_EQ(EINVAL, errno);
+	ASSERT_TRUE(errno == EEXIST || errno == EINVAL)
+		TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION",
+		       strerror(errno), errno);
 
 	ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION2, &region2));
-	ASSERT_EQ(EINVAL, errno);
+	ASSERT_TRUE(errno == EEXIST || errno == EINVAL)
+		TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION2",
+		       strerror(errno), errno);
 }
 
 TEST_F(uc_kvm, uc_map_unmap)
@@ -596,7 +596,9 @@ TEST_F(uc_kvm, uc_skey)
 	ASSERT_EQ(true, uc_handle_exit(self));
 	ASSERT_EQ(1, sync_regs->gprs[0]);
 
-	/* ISKE */
+	/* SSKE + ISKE */
+	sync_regs->gprs[1] = skeyvalue;
+	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
 	ASSERT_EQ(0, uc_run_once(self));
 
 	/*
@@ -608,21 +610,11 @@ TEST_F(uc_kvm, uc_skey)
 	TEST_ASSERT_EQ(0, sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE));
 	TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason);
 	TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode);
-	TEST_REQUIRE(sie_block->ipa != 0xb229);
+	TEST_REQUIRE(sie_block->ipa != 0xb22b);
 
-	/* ISKE contd. */
+	/* SSKE + ISKE contd. */
 	ASSERT_EQ(false, uc_handle_exit(self));
 	ASSERT_EQ(2, sync_regs->gprs[0]);
-	/* assert initial skey (ACC = 0, R & C = 1) */
-	ASSERT_EQ(0x06, sync_regs->gprs[1]);
-	uc_assert_diag44(self);
-
-	/* SSKE + ISKE */
-	sync_regs->gprs[1] = skeyvalue;
-	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
-	ASSERT_EQ(0, uc_run_once(self));
-	ASSERT_EQ(false, uc_handle_exit(self));
-	ASSERT_EQ(3, sync_regs->gprs[0]);
 	ASSERT_EQ(skeyvalue, sync_regs->gprs[1]);
 	uc_assert_diag44(self);
 
@@ -631,7 +623,7 @@ TEST_F(uc_kvm, uc_skey)
 	run->kvm_dirty_regs |= KVM_SYNC_GPRS;
 	ASSERT_EQ(0, uc_run_once(self));
 	ASSERT_EQ(false, uc_handle_exit(self));
-	ASSERT_EQ(4, sync_regs->gprs[0]);
+	ASSERT_EQ(3, sync_regs->gprs[0]);
 	/* assert R reset but rest of skey unchanged */
 	ASSERT_EQ(skeyvalue & 0xfa, sync_regs->gprs[1]);
 	ASSERT_EQ(0, sync_regs->gprs[1] & 0x04);
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 2af86bd796ba..aa6f2c1cbec7 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -59,6 +59,12 @@ int open_tree(int dfd, const char *filename, unsigned int flags)
 }
 #endif
 
+static int sys_execveat(int dirfd, const char *pathname, char *const argv[],
+			char *const envp[], int flags)
+{
+	return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags);
+}
+
 #ifndef RENAME_EXCHANGE
 #define RENAME_EXCHANGE (1 << 1)
 #endif
@@ -2024,8 +2030,8 @@ static void test_check_exec(struct __test_metadata *const _metadata,
 	int ret;
 	char *const argv[] = { (char *)path, NULL };
 
-	ret = execveat(AT_FDCWD, path, argv, NULL,
-		       AT_EMPTY_PATH | AT_EXECVE_CHECK);
+	ret = sys_execveat(AT_FDCWD, path, argv, NULL,
+			   AT_EMPTY_PATH | AT_EXECVE_CHECK);
 	if (err) {
 		EXPECT_EQ(-1, ret);
 		EXPECT_EQ(errno, err);
diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index e5d06fb40233..15601402dee6 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -306,7 +306,8 @@ function check_result {
 	result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \
 		 grep -e 'livepatch:' -e 'test_klp' | \
 		 grep -v '\(tainting\|taints\) kernel' | \
-		 sed 's/^\[[ 0-9.]*\] //')
+		 sed 's/^\[[ 0-9.]*\] //' | \
+		 sed 's/^\[[ ]*[CT][0-9]*\] //')
 
 	if [[ "$expect" == "$result" ]] ; then
 		echo "ok"
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index c0c53451a16d..5b993924cc3f 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -171,7 +171,7 @@ static void mfd_fail_new(const char *name, unsigned int flags)
 	r = sys_memfd_create(name, flags);
 	if (r >= 0) {
 		printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n",
-		       name, flags);
+		       name ? name : "NULL", flags);
 		close(r);
 		abort();
 	}
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 8f01f4da1c0d..121000c28c10 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -27,6 +27,7 @@ protection_keys_64
 madv_populate
 uffd-stress
 uffd-unit-tests
+uffd-wp-mremap
 mlock-intersect-test
 mlock-random-test
 virtual_address_range
@@ -36,6 +37,9 @@ map_fixed_noreplace
 write_to_hugetlbfs
 hmm-tests
 memfd_secret
+hugetlb_dio
+pkey_sighandler_tests_32
+pkey_sighandler_tests_64
 soft-dirty
 split_huge_page_test
 ksm_tests
@@ -49,7 +53,6 @@ va_high_addr_switch
 hugetlb_fault_after_madv
 hugetlb_madv_vs_map
 mseal_test
-seal_elf
 droppable
 hugetlb_dio
 pkey_sighandler_tests_32
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 3de23ea4663f..63ce39d024bb 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -33,9 +33,16 @@ endif
 # LDLIBS.
 MAKEFLAGS += --no-builtin-rules
 
-CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS = -lrt -lpthread -lm
 
+# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is
+# automatically enabled at -O1 or above. This triggers various unused-result
+# warnings where functions such as read() or write() are called and their
+# return value is not checked. Disable _FORTIFY_SOURCE to silence those
+# warnings.
+CFLAGS += -U_FORTIFY_SOURCE
+
 KDIR ?= /lib/modules/$(shell uname -r)/build
 ifneq (,$(wildcard $(KDIR)/Module.symvers))
 ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h))
@@ -75,13 +82,13 @@ TEST_GEN_FILES += mrelease_test
 TEST_GEN_FILES += mremap_dontunmap
 TEST_GEN_FILES += mremap_test
 TEST_GEN_FILES += mseal_test
-TEST_GEN_FILES += seal_elf
 TEST_GEN_FILES += on-fault-limit
 TEST_GEN_FILES += pagemap_ioctl
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += uffd-stress
 TEST_GEN_FILES += uffd-unit-tests
+TEST_GEN_FILES += uffd-wp-mremap
 TEST_GEN_FILES += split_huge_page_test
 TEST_GEN_FILES += ksm_tests
 TEST_GEN_FILES += ksm_functional_tests
@@ -152,11 +159,16 @@ $(TEST_GEN_FILES): vm_util.c thp_settings.c
 
 $(OUTPUT)/uffd-stress: uffd-common.c
 $(OUTPUT)/uffd-unit-tests: uffd-common.c
+$(OUTPUT)/uffd-wp-mremap: uffd-common.c
+$(OUTPUT)/protection_keys: pkey_util.c
+$(OUTPUT)/pkey_sighandler_tests: pkey_util.c
 
 ifeq ($(ARCH),x86_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
+$(BINARIES_32) $(BINARIES_64): pkey_util.c
+
 define gen-target-rule-32
 $(1) $(1)_32: $(OUTPUT)/$(1)_32
 .PHONY: $(1) $(1)_32
diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config
index 4309916f629e..a28baa536332 100644
--- a/tools/testing/selftests/mm/config
+++ b/tools/testing/selftests/mm/config
@@ -7,3 +7,4 @@ CONFIG_TEST_HMM=m
 CONFIG_GUP_TEST=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_MEM_SOFT_DIRTY=y
+CONFIG_ANON_VMA_NAME=y
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index 1238e1c5aae1..9446673645eb 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -1482,7 +1482,7 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc)
 	}
 
 	smem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0);
-	if (mem == MAP_FAILED) {
+	if (smem == MAP_FAILED) {
 		ksft_test_result_fail("mmap() failed\n");
 		goto munmap;
 	}
@@ -1583,7 +1583,7 @@ static void run_with_memfd(non_anon_test_fn fn, const char *desc)
 		goto close;
 	}
 	smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0);
-	if (mem == MAP_FAILED) {
+	if (smem == MAP_FAILED) {
 		ksft_test_result_fail("mmap() failed\n");
 		goto munmap;
 	}
@@ -1634,7 +1634,7 @@ static void run_with_tmpfile(non_anon_test_fn fn, const char *desc)
 		goto close;
 	}
 	smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0);
-	if (mem == MAP_FAILED) {
+	if (smem == MAP_FAILED) {
 		ksft_test_result_fail("mmap() failed\n");
 		goto munmap;
 	}
@@ -1684,7 +1684,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc,
 		goto close;
 	}
 	smem = mmap(NULL, hugetlbsize, PROT_READ, MAP_SHARED, fd, 0);
-	if (mem == MAP_FAILED) {
+	if (smem == MAP_FAILED) {
 		ksft_test_result_fail("mmap() failed\n");
 		goto munmap;
 	}
@@ -1696,7 +1696,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc,
 	fn(mem, smem, hugetlbsize);
 munmap:
 	munmap(mem, hugetlbsize);
-	if (mem != MAP_FAILED)
+	if (smem != MAP_FAILED)
 		munmap(smem, hugetlbsize);
 close:
 	close(fd);
diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c
index 7cdf815d0d63..ece37212a8a2 100644
--- a/tools/testing/selftests/mm/guard-pages.c
+++ b/tools/testing/selftests/mm/guard-pages.c
@@ -55,6 +55,12 @@ static int pidfd_open(pid_t pid, unsigned int flags)
 	return syscall(SYS_pidfd_open, pid, flags);
 }
 
+static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec,
+				   size_t n, int advice, unsigned int flags)
+{
+	return syscall(__NR_process_madvise, pidfd, iovec, n, advice, flags);
+}
+
 /*
  * Enable our signal catcher and try to read/write the specified buffer. The
  * return value indicates whether the read/write succeeds without a fatal
@@ -419,7 +425,7 @@ TEST_F(guard_pages, process_madvise)
 	ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0);
 
 	/* Now guard in one step. */
-	count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0);
+	count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0);
 
 	/* OK we don't have permission to do this, skip. */
 	if (count == -1 && errno == EPERM)
@@ -440,7 +446,7 @@ TEST_F(guard_pages, process_madvise)
 	ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size]));
 
 	/* Now do the same with unguard... */
-	count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0);
+	count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0);
 
 	/* ...and everything should now succeed. */
 
@@ -990,7 +996,7 @@ TEST_F(guard_pages, fork)
 		   MAP_ANON | MAP_PRIVATE, -1, 0);
 	ASSERT_NE(ptr, MAP_FAILED);
 
-	/* Establish guard apges in the first 5 pages. */
+	/* Establish guard pages in the first 5 pages. */
 	ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0);
 
 	pid = fork();
@@ -1030,6 +1036,77 @@ TEST_F(guard_pages, fork)
 }
 
 /*
+ * Assert expected behaviour after we fork populated ranges of anonymous memory
+ * and then guard and unguard the range.
+ */
+TEST_F(guard_pages, fork_cow)
+{
+	const unsigned long page_size = self->page_size;
+	char *ptr;
+	pid_t pid;
+	int i;
+
+	/* Map 10 pages. */
+	ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+		   MAP_ANON | MAP_PRIVATE, -1, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	/* Populate range. */
+	for (i = 0; i < 10 * page_size; i++) {
+		char chr = 'a' + (i % 26);
+
+		ptr[i] = chr;
+	}
+
+	pid = fork();
+	ASSERT_NE(pid, -1);
+	if (!pid) {
+		/* This is the child process now. */
+
+		/* Ensure the range is as expected. */
+		for (i = 0; i < 10 * page_size; i++) {
+			char expected = 'a' + (i % 26);
+			char actual = ptr[i];
+
+			ASSERT_EQ(actual, expected);
+		}
+
+		/* Establish guard pages across the whole range. */
+		ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+		/* Remove it. */
+		ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+		/*
+		 * By removing the guard pages, the page tables will be
+		 * cleared. Assert that we are looking at the zero page now.
+		 */
+		for (i = 0; i < 10 * page_size; i++) {
+			char actual = ptr[i];
+
+			ASSERT_EQ(actual, '\0');
+		}
+
+		exit(0);
+	}
+
+	/* Parent process. */
+
+	/* Parent simply waits on child. */
+	waitpid(pid, NULL, 0);
+
+	/* Ensure the range is unchanged in parent anon range. */
+	for (i = 0; i < 10 * page_size; i++) {
+		char expected = 'a' + (i % 26);
+		char actual = ptr[i];
+
+		ASSERT_EQ(actual, expected);
+	}
+
+	/* Cleanup. */
+	ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/*
  * Assert that forking a process with VMAs that do have VM_WIPEONFORK set
  * behave as expected.
  */
diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c
index b748c48908d9..dcdd5bb20f3d 100644
--- a/tools/testing/selftests/mm/ksm_tests.c
+++ b/tools/testing/selftests/mm/ksm_tests.c
@@ -776,7 +776,7 @@ err_out:
 
 int main(int argc, char *argv[])
 {
-	int ret, opt;
+	int ret = 0, opt;
 	int prot = 0;
 	int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT;
 	int merge_type = KSM_MERGE_TYPE_DEFAULT;
diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c
index 64bcbb7151cf..1e3a595fbf01 100644
--- a/tools/testing/selftests/mm/migration.c
+++ b/tools/testing/selftests/mm/migration.c
@@ -204,4 +204,103 @@ TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME)
 		ASSERT_EQ(pthread_cancel(self->threads[i]), 0);
 }
 
+/*
+ * migration test with shared anon THP page
+ */
+
+TEST_F_TIMEOUT(migration, shared_anon_thp, 2*RUNTIME)
+{
+	pid_t pid;
+	uint64_t *ptr;
+	int i;
+
+	if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0)
+		SKIP(return, "Not enough threads or NUMA nodes available");
+
+	ptr = mmap(NULL, 2 * TWOMEG, PROT_READ | PROT_WRITE,
+		MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	ptr = (uint64_t *) ALIGN((uintptr_t) ptr, TWOMEG);
+	ASSERT_EQ(madvise(ptr, TWOMEG, MADV_HUGEPAGE), 0);
+
+	memset(ptr, 0xde, TWOMEG);
+	for (i = 0; i < self->nthreads - 1; i++) {
+		pid = fork();
+		if (!pid) {
+			prctl(PR_SET_PDEATHSIG, SIGHUP);
+			/* Parent may have died before prctl so check now. */
+			if (getppid() == 1)
+				kill(getpid(), SIGHUP);
+			access_mem(ptr);
+		} else {
+			self->pids[i] = pid;
+		}
+	}
+
+	ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0);
+	for (i = 0; i < self->nthreads - 1; i++)
+		ASSERT_EQ(kill(self->pids[i], SIGTERM), 0);
+}
+
+/*
+ * migration test with private anon hugetlb page
+ */
+TEST_F_TIMEOUT(migration, private_anon_htlb, 2*RUNTIME)
+{
+	uint64_t *ptr;
+	int i;
+
+	if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0)
+		SKIP(return, "Not enough threads or NUMA nodes available");
+
+	ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE,
+		MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	memset(ptr, 0xde, TWOMEG);
+	for (i = 0; i < self->nthreads - 1; i++)
+		if (pthread_create(&self->threads[i], NULL, access_mem, ptr))
+			perror("Couldn't create thread");
+
+	ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0);
+	for (i = 0; i < self->nthreads - 1; i++)
+		ASSERT_EQ(pthread_cancel(self->threads[i]), 0);
+}
+
+/*
+ * migration test with shared anon hugetlb page
+ */
+TEST_F_TIMEOUT(migration, shared_anon_htlb, 2*RUNTIME)
+{
+	pid_t pid;
+	uint64_t *ptr;
+	int i;
+
+	if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0)
+		SKIP(return, "Not enough threads or NUMA nodes available");
+
+	ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE,
+		MAP_SHARED | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
+	ASSERT_NE(ptr, MAP_FAILED);
+
+	memset(ptr, 0xde, TWOMEG);
+	for (i = 0; i < self->nthreads - 1; i++) {
+		pid = fork();
+		if (!pid) {
+			prctl(PR_SET_PDEATHSIG, SIGHUP);
+			/* Parent may have died before prctl so check now. */
+			if (getppid() == 1)
+				kill(getpid(), SIGHUP);
+			access_mem(ptr);
+		} else {
+			self->pids[i] = pid;
+		}
+	}
+
+	ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0);
+	for (i = 0; i < self->nthreads - 1; i++)
+		ASSERT_EQ(kill(self->pids[i], SIGTERM), 0);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c
index 1db134063c38..af2fce496912 100644
--- a/tools/testing/selftests/mm/mkdirty.c
+++ b/tools/testing/selftests/mm/mkdirty.c
@@ -280,6 +280,7 @@ static void test_uffdio_copy(void)
 	dst = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0);
 	if (dst == MAP_FAILED) {
 		ksft_test_result_fail("mmap() failed\n");
+		free(src);
 		return;
 	}
 
diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index 5a3a9bcba640..bb84476a177f 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -34,7 +34,7 @@ struct config {
 	unsigned long long dest_alignment;
 	unsigned long long region_size;
 	int overlapping;
-	int dest_preamble_size;
+	unsigned int dest_preamble_size;
 };
 
 struct test {
@@ -328,7 +328,7 @@ static void mremap_move_within_range(unsigned int pattern_seed, char *rand_addr)
 {
 	char *test_name = "mremap mremap move within range";
 	void *src, *dest;
-	int i, success = 1;
+	unsigned int i, success = 1;
 
 	size_t size = SIZE_MB(20);
 	void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
@@ -384,7 +384,7 @@ out:
 static long long remap_region(struct config c, unsigned int threshold_mb,
 			      char *rand_addr)
 {
-	void *addr, *src_addr, *dest_addr, *dest_preamble_addr;
+	void *addr, *src_addr, *dest_addr, *dest_preamble_addr = NULL;
 	unsigned long long t, d;
 	struct timespec t_start = {0, 0}, t_end = {0, 0};
 	long long  start_ns, end_ns, align_mask, ret, offset;
@@ -569,7 +569,7 @@ static void mremap_move_1mb_from_start(unsigned int pattern_seed,
 {
 	char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src";
 	void *src = NULL, *dest = NULL;
-	int i, success = 1;
+	unsigned int i, success = 1;
 
 	/* Config to reuse get_source_mapping() to do an aligned mmap. */
 	struct config c = {
@@ -636,7 +636,7 @@ out:
 
 static void run_mremap_test_case(struct test test_case, int *failures,
 				 unsigned int threshold_mb,
-				 unsigned int pattern_seed, char *rand_addr)
+				 char *rand_addr)
 {
 	long long remap_time = remap_region(test_case.config, threshold_mb,
 					    rand_addr);
@@ -708,7 +708,8 @@ static int parse_args(int argc, char **argv, unsigned int *threshold_mb,
 int main(int argc, char **argv)
 {
 	int failures = 0;
-	int i, run_perf_tests;
+	unsigned int i;
+	int run_perf_tests;
 	unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD;
 
 	/* hard-coded test configs */
@@ -831,7 +832,7 @@ int main(int argc, char **argv)
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++)
 		run_mremap_test_case(test_cases[i], &failures, threshold_mb,
-				     pattern_seed, rand_addr);
+				     rand_addr);
 
 	maps_fp = fopen("/proc/self/maps", "r");
 
@@ -853,7 +854,7 @@ int main(int argc, char **argv)
 		 "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:");
 		for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++)
 			run_mremap_test_case(perf_test_cases[i], &failures,
-					     threshold_mb, pattern_seed,
+					     threshold_mb,
 					     rand_addr);
 	}
 
diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c
index 01675c412b2a..ad17005521a8 100644
--- a/tools/testing/selftests/mm/mseal_test.c
+++ b/tools/testing/selftests/mm/mseal_test.c
@@ -802,7 +802,7 @@ static void test_seal_mprotect_partial_mprotect_tail(bool seal)
 }
 
 
-static void test_seal_mprotect_two_vma_with_gap(bool seal)
+static void test_seal_mprotect_two_vma_with_gap(void)
 {
 	void *ptr;
 	unsigned long page_size = getpagesize();
@@ -1864,7 +1864,7 @@ static void test_seal_madvise_nodiscard(bool seal)
 	REPORT_TEST_PASS();
 }
 
-int main(int argc, char **argv)
+int main(void)
 {
 	bool test_seal = seal_support();
 
@@ -1913,8 +1913,8 @@ int main(int argc, char **argv)
 	test_seal_mprotect_partial_mprotect(false);
 	test_seal_mprotect_partial_mprotect(true);
 
-	test_seal_mprotect_two_vma_with_gap(false);
-	test_seal_mprotect_two_vma_with_gap(true);
+	test_seal_mprotect_two_vma_with_gap();
+	test_seal_mprotect_two_vma_with_gap();
 
 	test_seal_mprotect_merge(false);
 	test_seal_mprotect_merge(true);
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index bcc73b4e805c..57b4bba2b45f 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -34,8 +34,8 @@
 #define PAGEMAP "/proc/self/pagemap"
 int pagemap_fd;
 int uffd;
-int page_size;
-int hpage_size;
+unsigned int page_size;
+unsigned int hpage_size;
 const char *progname;
 
 #define LEN(region)	((region.end - region.start)/page_size)
@@ -235,7 +235,9 @@ int get_reads(struct page_region *vec, int vec_size)
 
 int sanity_tests_sd(void)
 {
-	int mem_size, vec_size, ret, ret2, ret3, i, num_pages = 1000, total_pages = 0;
+	unsigned long long mem_size, vec_size, i, total_pages = 0;
+	long ret, ret2, ret3;
+	int num_pages = 1000;
 	int total_writes, total_reads, reads, count;
 	struct page_region *vec, *vec2;
 	char *mem, *m[2];
@@ -321,9 +323,9 @@ int sanity_tests_sd(void)
 	ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0,
 			    0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
-	ksft_test_result(ret == mem_size/(page_size * 2),
+	ksft_test_result((unsigned long long)ret == mem_size/(page_size * 2),
 			 "%s Repeated pattern of written and non-written pages\n", __func__);
 
 	/* 4. Repeated pattern of written and non-written pages in parts */
@@ -331,21 +333,21 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			    num_pages/2 - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	ret2 = pagemap_ioctl(mem, mem_size, vec, 2, 0, 0, PAGE_IS_WRITTEN, 0, 0,
 			     PAGE_IS_WRITTEN);
 	if (ret2 < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno));
 
 	ret3 = pagemap_ioctl(mem, mem_size, vec, vec_size,
 			     PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			     0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret3 < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret3, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret3, errno, strerror(errno));
 
 	ksft_test_result((ret + ret3) == num_pages/2 && ret2 == 2,
-			 "%s Repeated pattern of written and non-written pages in parts %d %d %d\n",
+			 "%s Repeated pattern of written and non-written pages in parts %ld %ld %ld\n",
 			 __func__, ret, ret3, ret2);
 
 	/* 5. Repeated pattern of written and non-written pages max_pages */
@@ -357,13 +359,13 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			    num_pages/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	ret2 = pagemap_ioctl(mem, mem_size, vec, vec_size,
 			     PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			     0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret2 < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno));
 
 	ksft_test_result(ret == num_pages/2 && ret2 == 1,
 			 "%s Repeated pattern of written and non-written pages max_pages\n",
@@ -378,12 +380,12 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			    2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	ret2 = pagemap_ioctl(mem, mem_size, vec2, vec_size, 0, 0,
 			      PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret2 < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno));
 
 	ksft_test_result(ret == 1 && LEN(vec[0]) == 2 &&
 			 vec[0].start == (uintptr_t)(mem + page_size) &&
@@ -416,7 +418,7 @@ int sanity_tests_sd(void)
 	ret = pagemap_ioctl(m[1], mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0,
 			    PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	ksft_test_result(ret == 1 && LEN(vec[0]) == mem_size/page_size,
 			 "%s Two regions\n", __func__);
@@ -448,7 +450,7 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0,
 			    PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	for (i = 0; i < mem_size/page_size; i += 2)
 		mem[i * page_size]++;
@@ -457,7 +459,7 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			    mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	total_pages += ret;
 
@@ -465,7 +467,7 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			    mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	total_pages += ret;
 
@@ -473,7 +475,7 @@ int sanity_tests_sd(void)
 			    PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			    mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
 	total_pages += ret;
 
@@ -515,9 +517,9 @@ int sanity_tests_sd(void)
 					  vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 					  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 			if (ret < 0)
-				ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+				ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 
-			if (ret > vec_size)
+			if ((unsigned long)ret > vec_size)
 				break;
 
 			reads = get_reads(vec, ret);
@@ -554,63 +556,63 @@ int sanity_tests_sd(void)
 	ret = pagemap_ioc(mem, 0, vec, vec_size, 0,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 0 && walk_end == (long)mem,
 			 "Walk_end: Same start and end address\n");
 
 	ret = pagemap_ioc(mem, 0, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 0 && walk_end == (long)mem,
 			 "Walk_end: Same start and end with WP\n");
 
 	ret = pagemap_ioc(mem, 0, vec, 0, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 0 && walk_end == (long)mem,
 			 "Walk_end: Same start and end with 0 output buffer\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size),
 			 "Walk_end: Big vec\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, 1, 0,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size),
 			 "Walk_end: vec of minimum length\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, 1, 0,
 			  vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size),
 			 "Walk_end: Max pages specified\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size/2),
 			 "Walk_end: Half max pages\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size),
 			 "Walk_end: 1 max page\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  -1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size),
 			 "Walk_end: max pages\n");
 
@@ -621,49 +623,49 @@ int sanity_tests_sd(void)
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
-	ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size),
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
+	ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size),
 			 "Walk_end sparse: Big vec\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, 1, 0,
 			  0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2),
 			 "Walk_end sparse: vec of minimum length\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, 1, 0,
 			  vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2),
 			 "Walk_end sparse: Max pages specified\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size/2, 0,
 			  vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
-	ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size),
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
+	ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size),
 			 "Walk_end sparse: Max pages specified\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
-	ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size),
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
+	ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size),
 			 "Walk_end sparse: Max pages specified\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
-	ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size),
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
+	ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size),
 			 "Walk_endsparse : Half max pages\n");
 
 	ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0,
 			  1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end);
 	if (ret < 0)
-		ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno));
+		ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno));
 	ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2),
 			 "Walk_end: 1 max page\n");
 
@@ -674,9 +676,10 @@ int sanity_tests_sd(void)
 	return 0;
 }
 
-int base_tests(char *prefix, char *mem, int mem_size, int skip)
+int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip)
 {
-	int vec_size, written;
+	unsigned long long vec_size;
+	int written;
 	struct page_region *vec, *vec2;
 
 	if (skip) {
@@ -799,8 +802,8 @@ int hpage_unit_tests(void)
 	char *map;
 	int ret, ret2;
 	size_t num_pages = 10;
-	int map_size = hpage_size * num_pages;
-	int vec_size = map_size/page_size;
+	unsigned long long map_size = hpage_size * num_pages;
+	unsigned long long vec_size = map_size/page_size;
 	struct page_region *vec, *vec2;
 
 	vec = malloc(sizeof(struct page_region) * vec_size);
@@ -1047,7 +1050,8 @@ static void test_simple(void)
 
 int sanity_tests(void)
 {
-	int mem_size, vec_size, ret, fd, i, buf_size;
+	unsigned long long mem_size, vec_size;
+	int ret, fd, i, buf_size;
 	struct page_region *vec;
 	char *mem, *fmem;
 	struct stat sbuf;
@@ -1312,7 +1316,9 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count,
 {
 	struct pm_scan_arg arg = {0};
 	struct page_region rgns[256];
-	int i, j, cnt, ret;
+	unsigned long long i, j;
+	long ret;
+	int cnt;
 
 	arg.size = sizeof(struct pm_scan_arg);
 	arg.start = (uintptr_t)mem;
@@ -1330,7 +1336,7 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count,
 		ksft_exit_fail_msg("ioctl failed\n");
 
 	cnt = 0;
-	for (i = 0; i < ret; ++i) {
+	for (i = 0; i < (unsigned long)ret; ++i) {
 		if (rgns[i].categories != PAGE_IS_WRITTEN)
 			ksft_exit_fail_msg("wrong flags\n");
 
@@ -1384,9 +1390,10 @@ void *thread_proc(void *mem)
 static void transact_test(int page_size)
 {
 	unsigned int i, count, extra_pages;
+	unsigned int c;
 	pthread_t th;
 	char *mem;
-	int ret, c;
+	int ret;
 
 	if (pthread_barrier_init(&start_barrier, NULL, nthreads + 1))
 		ksft_exit_fail_msg("pthread_barrier_init\n");
@@ -1405,9 +1412,9 @@ static void transact_test(int page_size)
 	memset(mem, 0, 0x1000 * nthreads * pages_per_thread);
 
 	count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size);
-	ksft_test_result(count > 0, "%s count %d\n", __func__, count);
+	ksft_test_result(count > 0, "%s count %u\n", __func__, count);
 	count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size);
-	ksft_test_result(count == 0, "%s count %d\n", __func__, count);
+	ksft_test_result(count == 0, "%s count %u\n", __func__, count);
 
 	finish = 0;
 	for (i = 0; i < nthreads; ++i)
@@ -1429,7 +1436,7 @@ static void transact_test(int page_size)
 			ksft_exit_fail_msg("pthread_barrier_wait\n");
 
 		if (count > nthreads * access_per_thread)
-			ksft_exit_fail_msg("Too big count %d expected %d, iter %d\n",
+			ksft_exit_fail_msg("Too big count %u expected %u, iter %u\n",
 					   count, nthreads * access_per_thread, i);
 
 		c = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size);
@@ -1454,7 +1461,7 @@ static void transact_test(int page_size)
 			 * access and application gets page fault again for the same write.
 			 */
 			if (count < nthreads * access_per_thread) {
-				ksft_test_result_fail("Lost update, iter %d, %d vs %d.\n", i, count,
+				ksft_test_result_fail("Lost update, iter %u, %u vs %u.\n", i, count,
 						      nthreads * access_per_thread);
 				return;
 			}
@@ -1467,15 +1474,16 @@ static void transact_test(int page_size)
 	finish = 1;
 	pthread_barrier_wait(&end_barrier);
 
-	ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %d.\n", __func__,
+	ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %u.\n", __func__,
 			      extra_pages,
 			      100.0 * extra_pages / (iter_count * nthreads * access_per_thread),
 			      extra_thread_faults);
 }
 
-int main(int argc, char *argv[])
+int main(int __attribute__((unused)) argc, char *argv[])
 {
-	int mem_size, shmid, buf_size, fd, i, ret;
+	int shmid, buf_size, fd, i, ret;
+	unsigned long long mem_size;
 	char *mem, *map, *fmem;
 	struct stat sbuf;
 
diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h
index d9d2100eafc0..8e9685e03c44 100644
--- a/tools/testing/selftests/mm/pkey-arm64.h
+++ b/tools/testing/selftests/mm/pkey-arm64.h
@@ -30,7 +30,7 @@
 #define NR_PKEYS		8
 #define NR_RESERVED_PKEYS	1 /* pkey-0 */
 
-#define PKEY_ALLOW_ALL		0x77777777
+#define PKEY_REG_ALLOW_ALL	0x77777777
 #define PKEY_REG_ALLOW_NONE	0x0
 
 #define PKEY_BITS_PER_PKEY	4
@@ -81,11 +81,11 @@ static inline int get_arch_reserved_keys(void)
 	return NR_RESERVED_PKEYS;
 }
 
-void expect_fault_on_read_execonly_key(void *p1, int pkey)
+static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
 {
 }
 
-void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
 {
 	return PTR_ERR_ENOTSUP;
 }
diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h
index f7cfe163b0ff..f080e97b39be 100644
--- a/tools/testing/selftests/mm/pkey-helpers.h
+++ b/tools/testing/selftests/mm/pkey-helpers.h
@@ -13,22 +13,22 @@
 #include <ucontext.h>
 #include <sys/mman.h>
 
+#include <linux/types.h>
+
 #include "../kselftest.h"
 
 /* Define some kernel-like types */
-#define  u8 __u8
-#define u16 __u16
-#define u32 __u32
-#define u64 __u64
+typedef __u8	u8;
+typedef __u16	u16;
+typedef __u32	u32;
+typedef __u64	u64;
 
 #define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)
 
 #ifndef DEBUG_LEVEL
 #define DEBUG_LEVEL 0
 #endif
-#define DPRINT_IN_SIGNAL_BUF_SIZE 4096
 extern int dprint_in_signal;
-extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
 
 extern int test_nr;
 extern int iteration_nr;
@@ -83,17 +83,18 @@ extern void abort_hooks(void);
 #ifndef noinline
 # define noinline __attribute__((noinline))
 #endif
+#ifndef __maybe_unused
+# define __maybe_unused __attribute__((__unused__))
+#endif
 
-noinline int read_ptr(int *ptr)
-{
-	/* Keep GCC from optimizing this away somehow */
-	barrier();
-	return *ptr;
-}
-
-void expected_pkey_fault(int pkey);
 int sys_pkey_alloc(unsigned long flags, unsigned long init_val);
 int sys_pkey_free(unsigned long pkey);
+int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+		unsigned long pkey);
+
+/* For functions called from protection_keys.c only */
+noinline int read_ptr(int *ptr);
+void expected_pkey_fault(int pkey);
 int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
 		unsigned long pkey);
 void record_pkey_malloc(void *ptr, long size, int prot);
@@ -171,38 +172,6 @@ static inline void write_pkey_reg(u64 pkey_reg)
 			pkey_reg, __read_pkey_reg());
 }
 
-/*
- * These are technically racy. since something could
- * change PKEY register between the read and the write.
- */
-static inline void __pkey_access_allow(int pkey, int do_allow)
-{
-	u64 pkey_reg = read_pkey_reg();
-	int bit = pkey * 2;
-
-	if (do_allow)
-		pkey_reg &= (1<<bit);
-	else
-		pkey_reg |= (1<<bit);
-
-	dprintf4("pkey_reg now: %016llx\n", read_pkey_reg());
-	write_pkey_reg(pkey_reg);
-}
-
-static inline void __pkey_write_allow(int pkey, int do_allow_write)
-{
-	u64 pkey_reg = read_pkey_reg();
-	int bit = pkey * 2 + 1;
-
-	if (do_allow_write)
-		pkey_reg &= (1<<bit);
-	else
-		pkey_reg |= (1<<bit);
-
-	write_pkey_reg(pkey_reg);
-	dprintf4("pkey_reg now: %016llx\n", read_pkey_reg());
-}
-
 #define ALIGN_UP(x, align_to)	(((x) + ((align_to)-1)) & ~((align_to)-1))
 #define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1))
 #define ALIGN_PTR_UP(p, ptr_align_to)	\
diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h
index 3d0c0bdae5bc..1bad310d282a 100644
--- a/tools/testing/selftests/mm/pkey-powerpc.h
+++ b/tools/testing/selftests/mm/pkey-powerpc.h
@@ -91,7 +91,7 @@ static inline int get_arch_reserved_keys(void)
 			return NR_RESERVED_PKEYS_64K_3KEYS;
 }
 
-void expect_fault_on_read_execonly_key(void *p1, int pkey)
+static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
 {
 	/*
 	 * powerpc does not allow userspace to change permissions of exec-only
@@ -105,7 +105,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey)
 /* 4-byte instructions * 16384 = 64K page */
 #define __page_o_noops() asm(".rept 16384 ; nop; .endr")
 
-void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
 {
 	void *ptr;
 	int ret;
diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h
index ac91777c8917..f7ecd335df1e 100644
--- a/tools/testing/selftests/mm/pkey-x86.h
+++ b/tools/testing/selftests/mm/pkey-x86.h
@@ -113,7 +113,7 @@ static inline u32 pkey_bit_position(int pkey)
 #define XSTATE_PKEY	0x200
 #define XSTATE_BV_OFFSET	512
 
-int pkey_reg_xstate_offset(void)
+static inline int pkey_reg_xstate_offset(void)
 {
 	unsigned int eax;
 	unsigned int ebx;
@@ -148,7 +148,7 @@ static inline int get_arch_reserved_keys(void)
 	return NR_RESERVED_PKEYS;
 }
 
-void expect_fault_on_read_execonly_key(void *p1, int pkey)
+static inline void expect_fault_on_read_execonly_key(void *p1, int pkey)
 {
 	int ptr_contents;
 
@@ -157,7 +157,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey)
 	expected_pkey_fault(pkey);
 }
 
-void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
 {
 	return PTR_ERR_ENOTSUP;
 }
diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c
index c593a426341c..1ac8c8809880 100644
--- a/tools/testing/selftests/mm/pkey_sighandler_tests.c
+++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c
@@ -32,11 +32,9 @@
 
 #define STACK_SIZE PTHREAD_STACK_MIN
 
-void expected_pkey_fault(int pkey) {}
-
-pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
-pthread_cond_t cond = PTHREAD_COND_INITIALIZER;
-siginfo_t siginfo = {0};
+static pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t cond = PTHREAD_COND_INITIALIZER;
+static siginfo_t siginfo = {0};
 
 /*
  * We need to use inline assembly instead of glibc's syscall because glibc's
@@ -163,7 +161,7 @@ static void *thread_segv_with_pkey0_disabled(void *ptr)
 	__write_pkey_reg(pkey_reg_restrictive_default());
 
 	/* Segfault (with SEGV_MAPERR) */
-	*(int *) (0x1) = 1;
+	*(volatile int *)NULL = 1;
 	return NULL;
 }
 
@@ -179,7 +177,6 @@ static void *thread_segv_pkuerr_stack(void *ptr)
 static void *thread_segv_maperr_ptr(void *ptr)
 {
 	stack_t *stack = ptr;
-	int *bad = (int *)1;
 	u64 pkey_reg;
 
 	/*
@@ -195,7 +192,7 @@ static void *thread_segv_maperr_ptr(void *ptr)
 	__write_pkey_reg(pkey_reg);
 
 	/* Segfault */
-	*bad = 1;
+	*(volatile int *)NULL = 1;
 	syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0);
 	return NULL;
 }
@@ -234,7 +231,7 @@ static void test_sigsegv_handler_with_pkey0_disabled(void)
 
 	ksft_test_result(siginfo.si_signo == SIGSEGV &&
 			 siginfo.si_code == SEGV_MAPERR &&
-			 siginfo.si_addr == (void *)1,
+			 siginfo.si_addr == NULL,
 			 "%s\n", __func__);
 }
 
@@ -314,11 +311,11 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void)
 	__write_pkey_reg(pkey_reg);
 
 	/* Protect the new stack with MPK 1 */
-	pkey = pkey_alloc(0, 0);
-	pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey);
+	pkey = sys_pkey_alloc(0, 0);
+	sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey);
 
 	/* Set up alternate signal stack that will use the default MPK */
-	sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC,
+	sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE,
 			      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	sigstack.ss_flags = 0;
 	sigstack.ss_size = STACK_SIZE;
@@ -349,7 +346,7 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void)
 
 	ksft_test_result(siginfo.si_signo == SIGSEGV &&
 			 siginfo.si_code == SEGV_MAPERR &&
-			 siginfo.si_addr == (void *)1,
+			 siginfo.si_addr == NULL,
 			 "%s\n", __func__);
 }
 
@@ -487,11 +484,11 @@ static void test_pkru_sigreturn(void)
 	__write_pkey_reg(pkey_reg);
 
 	/* Protect the stack with MPK 2 */
-	pkey = pkey_alloc(0, 0);
-	pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey);
+	pkey = sys_pkey_alloc(0, 0);
+	sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey);
 
 	/* Set up alternate signal stack that will use the default MPK */
-	sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC,
+	sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE,
 			      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	sigstack.ss_flags = 0;
 	sigstack.ss_size = STACK_SIZE;
@@ -538,6 +535,9 @@ int main(int argc, char *argv[])
 	ksft_print_header();
 	ksft_set_plan(ARRAY_SIZE(pkey_tests));
 
+	if (!is_pkeys_supported())
+		ksft_exit_skip("pkeys not supported\n");
+
 	for (i = 0; i < ARRAY_SIZE(pkey_tests); i++)
 		(*pkey_tests[i])();
 
diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c
new file mode 100644
index 000000000000..ca4ad0d44ab2
--- /dev/null
+++ b/tools/testing/selftests/mm/pkey_util.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "pkey-helpers.h"
+
+int sys_pkey_alloc(unsigned long flags, unsigned long init_val)
+{
+	int ret = syscall(SYS_pkey_alloc, flags, init_val);
+	dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n",
+			__func__, flags, init_val, ret, errno);
+	return ret;
+}
+
+int sys_pkey_free(unsigned long pkey)
+{
+	int ret = syscall(SYS_pkey_free, pkey);
+	dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret);
+	return ret;
+}
+
+int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+		unsigned long pkey)
+{
+	int sret;
+
+	dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__,
+			ptr, size, orig_prot, pkey);
+
+	errno = 0;
+	sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey);
+	if (errno) {
+		dprintf2("SYS_mprotect_key sret: %d\n", sret);
+		dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot);
+		dprintf2("SYS_mprotect_key failed, errno: %d\n", errno);
+		if (DEBUG_LEVEL >= 2)
+			perror("SYS_mprotect_pkey");
+	}
+	return sret;
+}
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index 4990f7ab4cb7..a4683f2476f2 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -53,9 +53,15 @@ int test_nr;
 
 u64 shadow_pkey_reg;
 int dprint_in_signal;
-char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
 
-void cat_into_file(char *str, char *file)
+noinline int read_ptr(int *ptr)
+{
+	/* Keep GCC from optimizing this away somehow */
+	barrier();
+	return *ptr;
+}
+
+static void cat_into_file(char *str, char *file)
 {
 	int fd = open(file, O_RDWR);
 	int ret;
@@ -82,7 +88,7 @@ void cat_into_file(char *str, char *file)
 
 #if CONTROL_TRACING > 0
 static int warned_tracing;
-int tracing_root_ok(void)
+static int tracing_root_ok(void)
 {
 	if (geteuid() != 0) {
 		if (!warned_tracing)
@@ -95,7 +101,7 @@ int tracing_root_ok(void)
 }
 #endif
 
-void tracing_on(void)
+static void tracing_on(void)
 {
 #if CONTROL_TRACING > 0
 #define TRACEDIR "/sys/kernel/tracing"
@@ -119,7 +125,7 @@ void tracing_on(void)
 #endif
 }
 
-void tracing_off(void)
+static void tracing_off(void)
 {
 #if CONTROL_TRACING > 0
 	if (!tracing_root_ok())
@@ -153,7 +159,7 @@ __attribute__((__aligned__(65536)))
 #else
 __attribute__((__aligned__(PAGE_SIZE)))
 #endif
-void lots_o_noops_around_write(int *write_to_me)
+static void lots_o_noops_around_write(int *write_to_me)
 {
 	dprintf3("running %s()\n", __func__);
 	__page_o_noops();
@@ -164,7 +170,7 @@ void lots_o_noops_around_write(int *write_to_me)
 	dprintf3("%s() done\n", __func__);
 }
 
-void dump_mem(void *dumpme, int len_bytes)
+static void dump_mem(void *dumpme, int len_bytes)
 {
 	char *c = (void *)dumpme;
 	int i;
@@ -207,7 +213,7 @@ static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
 	return 0;
 }
 
-void pkey_disable_set(int pkey, int flags)
+static void pkey_disable_set(int pkey, int flags)
 {
 	unsigned long syscall_flags = 0;
 	int ret;
@@ -245,7 +251,7 @@ void pkey_disable_set(int pkey, int flags)
 		pkey, flags);
 }
 
-void pkey_disable_clear(int pkey, int flags)
+static void pkey_disable_clear(int pkey, int flags)
 {
 	unsigned long syscall_flags = 0;
 	int ret;
@@ -271,19 +277,19 @@ void pkey_disable_clear(int pkey, int flags)
 			pkey, read_pkey_reg());
 }
 
-void pkey_write_allow(int pkey)
+__maybe_unused static void pkey_write_allow(int pkey)
 {
 	pkey_disable_clear(pkey, PKEY_DISABLE_WRITE);
 }
-void pkey_write_deny(int pkey)
+__maybe_unused static void pkey_write_deny(int pkey)
 {
 	pkey_disable_set(pkey, PKEY_DISABLE_WRITE);
 }
-void pkey_access_allow(int pkey)
+__maybe_unused static void pkey_access_allow(int pkey)
 {
 	pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS);
 }
-void pkey_access_deny(int pkey)
+__maybe_unused static void pkey_access_deny(int pkey)
 {
 	pkey_disable_set(pkey, PKEY_DISABLE_ACCESS);
 }
@@ -301,9 +307,9 @@ static char *si_code_str(int si_code)
 	return "UNKNOWN";
 }
 
-int pkey_faults;
-int last_si_pkey = -1;
-void signal_handler(int signum, siginfo_t *si, void *vucontext)
+static int pkey_faults;
+static int last_si_pkey = -1;
+static void signal_handler(int signum, siginfo_t *si, void *vucontext)
 {
 	ucontext_t *uctxt = vucontext;
 	int trapno;
@@ -390,27 +396,21 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	/* restore access and let the faulting instruction continue */
 	pkey_access_allow(siginfo_pkey);
 #elif defined(__aarch64__)
-	aarch64_write_signal_pkey(uctxt, PKEY_ALLOW_ALL);
+	aarch64_write_signal_pkey(uctxt, PKEY_REG_ALLOW_ALL);
 #endif /* arch */
 	pkey_faults++;
 	dprintf1("<<<<==================================================\n");
 	dprint_in_signal = 0;
 }
 
-int wait_all_children(void)
-{
-	int status;
-	return waitpid(-1, &status, 0);
-}
-
-void sig_chld(int x)
+static void sig_chld(int x)
 {
 	dprint_in_signal = 1;
 	dprintf2("[%d] SIGCHLD: %d\n", getpid(), x);
 	dprint_in_signal = 0;
 }
 
-void setup_sigsegv_handler(void)
+static void setup_sigsegv_handler(void)
 {
 	int r, rs;
 	struct sigaction newact;
@@ -436,13 +436,13 @@ void setup_sigsegv_handler(void)
 	pkey_assert(r == 0);
 }
 
-void setup_handlers(void)
+static void setup_handlers(void)
 {
 	signal(SIGCHLD, &sig_chld);
 	setup_sigsegv_handler();
 }
 
-pid_t fork_lazy_child(void)
+static pid_t fork_lazy_child(void)
 {
 	pid_t forkret;
 
@@ -460,35 +460,7 @@ pid_t fork_lazy_child(void)
 	return forkret;
 }
 
-int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
-		unsigned long pkey)
-{
-	int sret;
-
-	dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__,
-			ptr, size, orig_prot, pkey);
-
-	errno = 0;
-	sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey);
-	if (errno) {
-		dprintf2("SYS_mprotect_key sret: %d\n", sret);
-		dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot);
-		dprintf2("SYS_mprotect_key failed, errno: %d\n", errno);
-		if (DEBUG_LEVEL >= 2)
-			perror("SYS_mprotect_pkey");
-	}
-	return sret;
-}
-
-int sys_pkey_alloc(unsigned long flags, unsigned long init_val)
-{
-	int ret = syscall(SYS_pkey_alloc, flags, init_val);
-	dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n",
-			__func__, flags, init_val, ret, errno);
-	return ret;
-}
-
-int alloc_pkey(void)
+static int alloc_pkey(void)
 {
 	int ret;
 	unsigned long init_val = 0x0;
@@ -534,19 +506,12 @@ int alloc_pkey(void)
 	return ret;
 }
 
-int sys_pkey_free(unsigned long pkey)
-{
-	int ret = syscall(SYS_pkey_free, pkey);
-	dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret);
-	return ret;
-}
-
 /*
  * I had a bug where pkey bits could be set by mprotect() but
  * not cleared.  This ensures we get lots of random bit sets
  * and clears on the vma and pte pkey bits.
  */
-int alloc_random_pkey(void)
+static int alloc_random_pkey(void)
 {
 	int max_nr_pkey_allocs;
 	int ret;
@@ -629,7 +594,7 @@ struct pkey_malloc_record {
 };
 struct pkey_malloc_record *pkey_malloc_records;
 struct pkey_malloc_record *pkey_last_malloc_record;
-long nr_pkey_malloc_records;
+static long nr_pkey_malloc_records;
 void record_pkey_malloc(void *ptr, long size, int prot)
 {
 	long i;
@@ -667,7 +632,7 @@ void record_pkey_malloc(void *ptr, long size, int prot)
 	nr_pkey_malloc_records++;
 }
 
-void free_pkey_malloc(void *ptr)
+static void free_pkey_malloc(void *ptr)
 {
 	long i;
 	int ret;
@@ -694,8 +659,7 @@ void free_pkey_malloc(void *ptr)
 	pkey_assert(false);
 }
 
-
-void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
+static void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
 {
 	void *ptr;
 	int ret;
@@ -715,7 +679,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
 	return ptr;
 }
 
-void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
+static void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
 {
 	int ret;
 	void *ptr;
@@ -745,10 +709,10 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
 	return ptr;
 }
 
-int hugetlb_setup_ok;
+static int hugetlb_setup_ok;
 #define SYSFS_FMT_NR_HUGE_PAGES "/sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages"
 #define GET_NR_HUGE_PAGES 10
-void setup_hugetlbfs(void)
+static void setup_hugetlbfs(void)
 {
 	int err;
 	int fd;
@@ -796,7 +760,7 @@ void setup_hugetlbfs(void)
 	hugetlb_setup_ok = 1;
 }
 
-void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
+static void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
 {
 	void *ptr;
 	int flags = MAP_ANONYMOUS|MAP_PRIVATE|MAP_HUGETLB;
@@ -817,42 +781,15 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
 	return ptr;
 }
 
-void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey)
-{
-	void *ptr;
-	int fd;
-
-	dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
-			size, prot, pkey);
-	pkey_assert(pkey < NR_PKEYS);
-	fd = open("/dax/foo", O_RDWR);
-	pkey_assert(fd >= 0);
-
-	ptr = mmap(0, size, prot, MAP_SHARED, fd, 0);
-	pkey_assert(ptr != (void *)-1);
-
-	mprotect_pkey(ptr, size, prot, pkey);
-
-	record_pkey_malloc(ptr, size, prot);
-
-	dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr);
-	close(fd);
-	return ptr;
-}
-
-void *(*pkey_malloc[])(long size, int prot, u16 pkey) = {
+static void *(*pkey_malloc[])(long size, int prot, u16 pkey) = {
 
 	malloc_pkey_with_mprotect,
 	malloc_pkey_with_mprotect_subpage,
 	malloc_pkey_anon_huge,
 	malloc_pkey_hugetlb
-/* can not do direct with the pkey_mprotect() API:
-	malloc_pkey_mmap_direct,
-	malloc_pkey_mmap_dax,
-*/
 };
 
-void *malloc_pkey(long size, int prot, u16 pkey)
+static void *malloc_pkey(long size, int prot, u16 pkey)
 {
 	void *ret;
 	static int malloc_type;
@@ -882,7 +819,7 @@ void *malloc_pkey(long size, int prot, u16 pkey)
 	return ret;
 }
 
-int last_pkey_faults;
+static int last_pkey_faults;
 #define UNKNOWN_PKEY -2
 void expected_pkey_fault(int pkey)
 {
@@ -905,7 +842,7 @@ void expected_pkey_fault(int pkey)
 	 */
 	if (__read_pkey_reg() != 0)
 #elif defined(__aarch64__)
-	if (__read_pkey_reg() != PKEY_ALLOW_ALL)
+	if (__read_pkey_reg() != PKEY_REG_ALLOW_ALL)
 #else
 	if (__read_pkey_reg() != shadow_pkey_reg)
 #endif /* arch */
@@ -924,9 +861,9 @@ void expected_pkey_fault(int pkey)
 	pkey_assert(last_pkey_faults == pkey_faults);		\
 } while (0)
 
-int test_fds[10] = { -1 };
-int nr_test_fds;
-void __save_test_fd(int fd)
+static int test_fds[10] = { -1 };
+static int nr_test_fds;
+static void __save_test_fd(int fd)
 {
 	pkey_assert(fd >= 0);
 	pkey_assert(nr_test_fds < ARRAY_SIZE(test_fds));
@@ -934,14 +871,14 @@ void __save_test_fd(int fd)
 	nr_test_fds++;
 }
 
-int get_test_read_fd(void)
+static int get_test_read_fd(void)
 {
 	int test_fd = open("/etc/passwd", O_RDONLY);
 	__save_test_fd(test_fd);
 	return test_fd;
 }
 
-void close_test_fds(void)
+static void close_test_fds(void)
 {
 	int i;
 
@@ -954,7 +891,7 @@ void close_test_fds(void)
 	nr_test_fds = 0;
 }
 
-void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey)
+static void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey)
 {
 	int i, err;
 	int max_nr_pkey_allocs;
@@ -1006,7 +943,7 @@ void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey)
 	pkey_assert(!err);
 }
 
-void test_read_of_write_disabled_region(int *ptr, u16 pkey)
+static void test_read_of_write_disabled_region(int *ptr, u16 pkey)
 {
 	int ptr_contents;
 
@@ -1016,7 +953,7 @@ void test_read_of_write_disabled_region(int *ptr, u16 pkey)
 	dprintf1("*ptr: %d\n", ptr_contents);
 	dprintf1("\n");
 }
-void test_read_of_access_disabled_region(int *ptr, u16 pkey)
+static void test_read_of_access_disabled_region(int *ptr, u16 pkey)
 {
 	int ptr_contents;
 
@@ -1028,7 +965,7 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey)
 	expected_pkey_fault(pkey);
 }
 
-void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr,
+static void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr,
 		u16 pkey)
 {
 	int ptr_contents;
@@ -1045,7 +982,7 @@ void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr,
 	expected_pkey_fault(pkey);
 }
 
-void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr,
+static void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr,
 		u16 pkey)
 {
 	*ptr = __LINE__;
@@ -1056,14 +993,14 @@ void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr,
 	expected_pkey_fault(pkey);
 }
 
-void test_write_of_write_disabled_region(int *ptr, u16 pkey)
+static void test_write_of_write_disabled_region(int *ptr, u16 pkey)
 {
 	dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey);
 	pkey_write_deny(pkey);
 	*ptr = __LINE__;
 	expected_pkey_fault(pkey);
 }
-void test_write_of_access_disabled_region(int *ptr, u16 pkey)
+static void test_write_of_access_disabled_region(int *ptr, u16 pkey)
 {
 	dprintf1("disabling access to PKEY[%02d], doing write\n", pkey);
 	pkey_access_deny(pkey);
@@ -1071,7 +1008,7 @@ void test_write_of_access_disabled_region(int *ptr, u16 pkey)
 	expected_pkey_fault(pkey);
 }
 
-void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr,
+static void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr,
 			u16 pkey)
 {
 	*ptr = __LINE__;
@@ -1082,7 +1019,7 @@ void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr,
 	expected_pkey_fault(pkey);
 }
 
-void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
+static void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
 {
 	int ret;
 	int test_fd = get_test_read_fd();
@@ -1094,7 +1031,8 @@ void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
 	dprintf1("read ret: %d\n", ret);
 	pkey_assert(ret);
 }
-void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey)
+
+static void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey)
 {
 	int ret;
 	int test_fd = get_test_read_fd();
@@ -1107,7 +1045,7 @@ void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey)
 	pkey_assert(ret);
 }
 
-void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey)
+static void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey)
 {
 	int pipe_ret, vmsplice_ret;
 	struct iovec iov;
@@ -1129,7 +1067,7 @@ void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey)
 	close(pipe_fds[1]);
 }
 
-void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey)
+static void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey)
 {
 	int ignored = 0xdada;
 	int futex_ret;
@@ -1147,7 +1085,7 @@ void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey)
 }
 
 /* Assumes that all pkeys other than 'pkey' are unallocated */
-void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
+static void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
 {
 	int err;
 	int i;
@@ -1170,7 +1108,7 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
 }
 
 /* Assumes that all pkeys other than 'pkey' are unallocated */
-void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
+static void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 {
 	int err;
 	int bad_pkey = NR_PKEYS+99;
@@ -1180,7 +1118,7 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 	pkey_assert(err);
 }
 
-void become_child(void)
+static void become_child(void)
 {
 	pid_t forkret;
 
@@ -1196,7 +1134,7 @@ void become_child(void)
 }
 
 /* Assumes that all pkeys other than 'pkey' are unallocated */
-void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
+static void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 {
 	int err;
 	int allocated_pkeys[NR_PKEYS] = {0};
@@ -1263,7 +1201,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	}
 }
 
-void arch_force_pkey_reg_init(void)
+static void arch_force_pkey_reg_init(void)
 {
 #if defined(__i386__) || defined(__x86_64__) /* arch */
 	u64 *buf;
@@ -1302,7 +1240,7 @@ void arch_force_pkey_reg_init(void)
  * a long-running test that continually checks the pkey
  * register.
  */
-void test_pkey_init_state(int *ptr, u16 pkey)
+static void test_pkey_init_state(int *ptr, u16 pkey)
 {
 	int err;
 	int allocated_pkeys[NR_PKEYS] = {0};
@@ -1340,7 +1278,7 @@ void test_pkey_init_state(int *ptr, u16 pkey)
  * have to call pkey_alloc() to use it first.  Make sure that it
  * is usable.
  */
-void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
+static void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
 {
 	long size;
 	int prot;
@@ -1364,7 +1302,7 @@ void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
 	mprotect_pkey(ptr, size, prot, pkey);
 }
 
-void test_ptrace_of_child(int *ptr, u16 pkey)
+static void test_ptrace_of_child(int *ptr, u16 pkey)
 {
 	__attribute__((__unused__)) int peek_result;
 	pid_t child_pid;
@@ -1440,7 +1378,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
 	free(plain_ptr_unaligned);
 }
 
-void *get_pointer_to_instructions(void)
+static void *get_pointer_to_instructions(void)
 {
 	void *p1;
 
@@ -1461,7 +1399,7 @@ void *get_pointer_to_instructions(void)
 	return p1;
 }
 
-void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+static void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
 {
 	void *p1;
 	int scratch;
@@ -1493,7 +1431,7 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
 	pkey_assert(!ret);
 }
 
-void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
+static void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
 {
 	void *p1;
 	int scratch;
@@ -1542,7 +1480,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
 }
 
 #if defined(__i386__) || defined(__x86_64__)
-void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
+static void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
 {
 	u32 new_pkru;
 	pid_t child;
@@ -1665,7 +1603,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
 #endif
 
 #if defined(__aarch64__)
-void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
+static void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
 {
 	pid_t child;
 	int status, ret;
@@ -1742,7 +1680,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey)
 }
 #endif
 
-void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
+static void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 {
 	int size = PAGE_SIZE;
 	int sret;
@@ -1756,7 +1694,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 	pkey_assert(sret < 0);
 }
 
-void (*pkey_tests[])(int *ptr, u16 pkey) = {
+static void (*pkey_tests[])(int *ptr, u16 pkey) = {
 	test_read_of_write_disabled_region,
 	test_read_of_access_disabled_region,
 	test_read_of_access_disabled_region_with_page_already_mapped,
@@ -1782,7 +1720,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
 #endif
 };
 
-void run_tests_once(void)
+static void run_tests_once(void)
 {
 	int *ptr;
 	int prot = PROT_READ|PROT_WRITE;
@@ -1816,7 +1754,7 @@ void run_tests_once(void)
 	iteration_nr++;
 }
 
-void pkey_setup_shadow(void)
+static void pkey_setup_shadow(void)
 {
 	shadow_pkey_reg = __read_pkey_reg();
 }
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 2fc290d9430c..333c468c2699 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -45,6 +45,8 @@ separated by spaces:
 	vmalloc smoke tests
 - hmm
 	hmm smoke tests
+- madv_guard
+	test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options
 - madv_populate
 	test memadvise(2) MADV_POPULATE_{READ,WRITE} options
 - memfd_secret
@@ -307,6 +309,7 @@ CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 3
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16
+CATEGORY="userfaultfd" run_test ./uffd-wp-mremap
 
 #cleanup
 echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
@@ -375,6 +378,9 @@ CATEGORY="mremap" run_test ./mremap_dontunmap
 
 CATEGORY="hmm" run_test bash ./test_hmm.sh smoke
 
+# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests
+CATEGORY="madv_guard" run_test ./guard-pages
+
 # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
 CATEGORY="madv_populate" run_test ./madv_populate
 
diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c
deleted file mode 100644
index d9f8ba8d5050..000000000000
--- a/tools/testing/selftests/mm/seal_elf.c
+++ /dev/null
@@ -1,137 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-#include <sys/mman.h>
-#include <stdint.h>
-#include <asm-generic/unistd.h>
-#include <string.h>
-#include <sys/time.h>
-#include <sys/resource.h>
-#include <stdbool.h>
-#include "../kselftest.h"
-#include <syscall.h>
-#include <errno.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <fcntl.h>
-#include <sys/ioctl.h>
-#include <sys/vfs.h>
-#include <sys/stat.h>
-#include "mseal_helpers.h"
-
-/*
- * define sys_xyx to call syscall directly.
- */
-static int sys_mseal(void *start, size_t len)
-{
-	int sret;
-
-	errno = 0;
-	sret = syscall(__NR_mseal, start, len, 0);
-	return sret;
-}
-
-static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot)
-{
-	int sret;
-
-	errno = 0;
-	sret = syscall(__NR_mprotect, ptr, size, prot);
-	return sret;
-}
-
-static bool seal_support(void)
-{
-	int ret;
-	void *ptr;
-	unsigned long page_size = getpagesize();
-
-	ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
-	if (ptr == (void *) -1)
-		return false;
-
-	ret = sys_mseal(ptr, page_size);
-	if (ret < 0)
-		return false;
-
-	return true;
-}
-
-const char somestr[4096] = {"READONLY"};
-
-static void test_seal_elf(void)
-{
-	int ret;
-	FILE *maps;
-	char line[512];
-	uintptr_t  addr_start, addr_end;
-	char prot[5];
-	char filename[256];
-	unsigned long page_size = getpagesize();
-	unsigned long long ptr = (unsigned long long) somestr;
-	char *somestr2 = (char *)somestr;
-
-	/*
-	 * Modify the protection of readonly somestr
-	 */
-	if (((unsigned long long)ptr % page_size) != 0)
-		ptr = (unsigned long long)ptr & ~(page_size - 1);
-
-	ksft_print_msg("somestr = %s\n", somestr);
-	ksft_print_msg("change protection to rw\n");
-	ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE);
-	FAIL_TEST_IF_FALSE(!ret);
-	*somestr2 = 'A';
-	ksft_print_msg("somestr is modified to: %s\n", somestr);
-	ret = sys_mprotect((void *)ptr, page_size, PROT_READ);
-	FAIL_TEST_IF_FALSE(!ret);
-
-	maps = fopen("/proc/self/maps", "r");
-	FAIL_TEST_IF_FALSE(maps);
-
-	/*
-	 * apply sealing to elf binary
-	 */
-	while (fgets(line, sizeof(line), maps)) {
-		if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]",
-			&addr_start, &addr_end, prot, filename) == 4) {
-			if (strlen(filename)) {
-				/*
-				 * seal the mapping if read only.
-				 */
-				if (strstr(prot, "r-")) {
-					ret = sys_mseal((void *)addr_start, addr_end - addr_start);
-					FAIL_TEST_IF_FALSE(!ret);
-					ksft_print_msg("sealed: %lx-%lx %s %s\n",
-						addr_start, addr_end, prot, filename);
-					if ((uintptr_t) somestr >= addr_start &&
-						(uintptr_t) somestr <= addr_end)
-						ksft_print_msg("mapping for somestr found\n");
-				}
-			}
-		}
-	}
-	fclose(maps);
-
-	ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE);
-	FAIL_TEST_IF_FALSE(ret < 0);
-	ksft_print_msg("somestr is sealed, mprotect is rejected\n");
-
-	REPORT_TEST_PASS();
-}
-
-int main(int argc, char **argv)
-{
-	bool test_seal = seal_support();
-
-	ksft_print_header();
-	ksft_print_msg("pid=%d\n", getpid());
-
-	if (!test_seal)
-		ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n");
-
-	ksft_set_plan(1);
-
-	test_seal_elf();
-
-	ksft_finished();
-}
diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c
index bdfa5d085f00..8e1462ce0532 100644
--- a/tools/testing/selftests/mm/soft-dirty.c
+++ b/tools/testing/selftests/mm/soft-dirty.c
@@ -128,7 +128,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon)
 {
 	const char *type[] = {"file", "anon"};
 	const char *fname = "./soft-dirty-test-file";
-	int test_fd;
+	int test_fd = 0;
 	char *map;
 
 	if (anon) {
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index eb6d1b9fc362..3f353f3d070f 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -108,38 +108,28 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp
 	unsigned long rss_anon_before, rss_anon_after;
 	size_t i;
 
-	if (!check_huge_anon(one_page, 4, pmd_pagesize)) {
-		printf("No THP is allocated\n");
-		exit(EXIT_FAILURE);
-	}
+	if (!check_huge_anon(one_page, 4, pmd_pagesize))
+		ksft_exit_fail_msg("No THP is allocated\n");
 
 	rss_anon_before = rss_anon();
-	if (!rss_anon_before) {
-		printf("No RssAnon is allocated before split\n");
-		exit(EXIT_FAILURE);
-	}
+	if (!rss_anon_before)
+		ksft_exit_fail_msg("No RssAnon is allocated before split\n");
 
 	/* split all THPs */
 	write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
 		      (uint64_t)one_page + len, 0);
 
 	for (i = 0; i < len; i++)
-		if (one_page[i] != (char)0) {
-			printf("%ld byte corrupted\n", i);
-			exit(EXIT_FAILURE);
-		}
+		if (one_page[i] != (char)0)
+			ksft_exit_fail_msg("%ld byte corrupted\n", i);
 
-	if (!check_huge_anon(one_page, 0, pmd_pagesize)) {
-		printf("Still AnonHugePages not split\n");
-		exit(EXIT_FAILURE);
-	}
+	if (!check_huge_anon(one_page, 0, pmd_pagesize))
+		ksft_exit_fail_msg("Still AnonHugePages not split\n");
 
 	rss_anon_after = rss_anon();
-	if (rss_anon_after >= rss_anon_before) {
-		printf("Incorrect RssAnon value. Before: %ld After: %ld\n",
+	if (rss_anon_after >= rss_anon_before)
+		ksft_exit_fail_msg("Incorrect RssAnon value. Before: %ld After: %ld\n",
 		       rss_anon_before, rss_anon_after);
-		exit(EXIT_FAILURE);
-	}
 }
 
 void split_pmd_zero_pages(void)
@@ -150,11 +140,11 @@ void split_pmd_zero_pages(void)
 
 	one_page = allocate_zero_filled_hugepage(len);
 	verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len);
-	printf("Split zero filled huge pages successful\n");
+	ksft_test_result_pass("Split zero filled huge pages successful\n");
 	free(one_page);
 }
 
-void split_pmd_thp(void)
+void split_pmd_thp_to_order(int order)
 {
 	char *one_page;
 	size_t len = 4 * pmd_pagesize;
@@ -174,7 +164,7 @@ void split_pmd_thp(void)
 
 	/* split all THPs */
 	write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
-		(uint64_t)one_page + len, 0);
+		(uint64_t)one_page + len, order);
 
 	for (i = 0; i < len; i++)
 		if (one_page[i] != (char)i)
@@ -184,7 +174,7 @@ void split_pmd_thp(void)
 	if (!check_huge_anon(one_page, 0, pmd_pagesize))
 		ksft_exit_fail_msg("Still AnonHugePages not split\n");
 
-	ksft_test_result_pass("Split huge pages successful\n");
+	ksft_test_result_pass("Split huge pages to order %d successful\n", order);
 	free(one_page);
 }
 
@@ -491,7 +481,7 @@ int main(int argc, char **argv)
 	if (argc > 1)
 		optional_xfs_path = argv[1];
 
-	ksft_set_plan(3+9);
+	ksft_set_plan(1+8+2+9);
 
 	pagesize = getpagesize();
 	pageshift = ffs(pagesize) - 1;
@@ -502,7 +492,11 @@ int main(int argc, char **argv)
 	fd_size = 2 * pmd_pagesize;
 
 	split_pmd_zero_pages();
-	split_pmd_thp();
+
+	for (i = 0; i < 9; i++)
+		if (i != 1)
+			split_pmd_thp_to_order(i);
+
 	split_pte_mapped_thp();
 	split_file_backed_thp();
 
diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c
index 577eaab6266f..ad872af1c81a 100644
--- a/tools/testing/selftests/mm/thp_settings.c
+++ b/tools/testing/selftests/mm/thp_settings.c
@@ -87,7 +87,7 @@ int write_file(const char *path, const char *buf, size_t buflen)
 	return (unsigned int) numwritten;
 }
 
-const unsigned long read_num(const char *path)
+unsigned long read_num(const char *path)
 {
 	char buf[21];
 
@@ -172,7 +172,7 @@ void thp_write_string(const char *name, const char *val)
 	}
 }
 
-const unsigned long thp_read_num(const char *name)
+unsigned long thp_read_num(const char *name)
 {
 	char path[PATH_MAX];
 	int ret;
diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h
index 876235a23460..fc131d23d593 100644
--- a/tools/testing/selftests/mm/thp_settings.h
+++ b/tools/testing/selftests/mm/thp_settings.h
@@ -64,12 +64,12 @@ struct thp_settings {
 
 int read_file(const char *path, char *buf, size_t buflen);
 int write_file(const char *path, const char *buf, size_t buflen);
-const unsigned long read_num(const char *path);
+unsigned long read_num(const char *path);
 void write_num(const char *path, unsigned long num);
 
 int thp_read_string(const char *name, const char * const strings[]);
 void thp_write_string(const char *name, const char *val);
-const unsigned long thp_read_num(const char *name);
+unsigned long thp_read_num(const char *name);
 void thp_write_num(const char *name, unsigned long num);
 
 void thp_write_settings(struct thp_settings *settings);
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index a2e71b1636e7..9ff71fa1f9bf 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -1122,7 +1122,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
 	char c;
 	unsigned long long count;
 	struct uffd_args args = { 0 };
-	char *orig_area_src, *orig_area_dst;
+	char *orig_area_src = NULL, *orig_area_dst = NULL;
 	unsigned long step_size, step_count;
 	unsigned long src_offs = 0;
 	unsigned long dst_offs = 0;
@@ -1190,7 +1190,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size,
 				    nr, count, count_verify[src_offs + nr + i]);
 		}
 	}
-	if (step_size > page_size) {
+	if (chunk_size > page_size) {
 		area_src = orig_area_src;
 		area_dst = orig_area_dst;
 	}
diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c
new file mode 100644
index 000000000000..2c4f984bd73c
--- /dev/null
+++ b/tools/testing/selftests/mm/uffd-wp-mremap.c
@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <stdint.h>
+#include <fcntl.h>
+#include <assert.h>
+#include <linux/mman.h>
+#include <sys/mman.h>
+#include "../kselftest.h"
+#include "thp_settings.h"
+#include "uffd-common.h"
+
+static int pagemap_fd;
+static size_t pagesize;
+static int nr_pagesizes = 1;
+static int nr_thpsizes;
+static size_t thpsizes[20];
+static int nr_hugetlbsizes;
+static size_t hugetlbsizes[10];
+
+static int sz2ord(size_t size)
+{
+	return __builtin_ctzll(size / pagesize);
+}
+
+static int detect_thp_sizes(size_t sizes[], int max)
+{
+	int count = 0;
+	unsigned long orders;
+	size_t kb;
+	int i;
+
+	/* thp not supported at all. */
+	if (!read_pmd_pagesize())
+		return 0;
+
+	orders = thp_supported_orders();
+
+	for (i = 0; orders && count < max; i++) {
+		if (!(orders & (1UL << i)))
+			continue;
+		orders &= ~(1UL << i);
+		kb = (pagesize >> 10) << i;
+		sizes[count++] = kb * 1024;
+		ksft_print_msg("[INFO] detected THP size: %zu KiB\n", kb);
+	}
+
+	return count;
+}
+
+static void *mmap_aligned(size_t size, int prot, int flags)
+{
+	size_t mmap_size = size * 2;
+	char *mmap_mem, *mem;
+
+	mmap_mem = mmap(NULL, mmap_size, prot, flags, -1, 0);
+	if (mmap_mem == MAP_FAILED)
+		return mmap_mem;
+
+	mem = (char *)(((uintptr_t)mmap_mem + size - 1) & ~(size - 1));
+	munmap(mmap_mem, mem - mmap_mem);
+	munmap(mem + size, mmap_mem + mmap_size - mem - size);
+
+	return mem;
+}
+
+static void *alloc_one_folio(size_t size, bool private, bool hugetlb)
+{
+	bool thp = !hugetlb && size > pagesize;
+	int flags = MAP_ANONYMOUS;
+	int prot = PROT_READ | PROT_WRITE;
+	char *mem, *addr;
+
+	assert((size & (size - 1)) == 0);
+
+	if (private)
+		flags |= MAP_PRIVATE;
+	else
+		flags |= MAP_SHARED;
+
+	/*
+	 * For THP, we must explicitly enable the THP size, allocate twice the
+	 * required space then manually align.
+	 */
+	if (thp) {
+		struct thp_settings settings = *thp_current_settings();
+
+		if (private)
+			settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS;
+		else
+			settings.shmem_hugepages[sz2ord(size)].enabled = SHMEM_ALWAYS;
+
+		thp_push_settings(&settings);
+
+		mem = mmap_aligned(size, prot, flags);
+	} else {
+		if (hugetlb) {
+			flags |= MAP_HUGETLB;
+			flags |= __builtin_ctzll(size) << MAP_HUGE_SHIFT;
+		}
+
+		mem = mmap(NULL, size, prot, flags, -1, 0);
+	}
+
+	if (mem == MAP_FAILED) {
+		mem = NULL;
+		goto out;
+	}
+
+	assert(((uintptr_t)mem & (size - 1)) == 0);
+
+	/*
+	 * Populate the folio by writing the first byte and check that all pages
+	 * are populated. Finally set the whole thing to non-zero data to avoid
+	 * kernel from mapping it back to the zero page.
+	 */
+	mem[0] = 1;
+	for (addr = mem; addr < mem + size; addr += pagesize) {
+		if (!pagemap_is_populated(pagemap_fd, addr)) {
+			munmap(mem, size);
+			mem = NULL;
+			goto out;
+		}
+	}
+	memset(mem, 1, size);
+out:
+	if (thp)
+		thp_pop_settings();
+
+	return mem;
+}
+
+static bool check_uffd_wp_state(void *mem, size_t size, bool expect)
+{
+	uint64_t pte;
+	void *addr;
+
+	for (addr = mem; addr < mem + size; addr += pagesize) {
+		pte = pagemap_get_entry(pagemap_fd, addr);
+		if (!!(pte & PM_UFFD_WP) != expect) {
+			ksft_test_result_fail("uffd-wp not %s for pte %lu!\n",
+					      expect ? "set" : "clear",
+					      (addr - mem) / pagesize);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static bool range_is_swapped(void *addr, size_t size)
+{
+	for (; size; addr += pagesize, size -= pagesize)
+		if (!pagemap_is_swapped(pagemap_fd, addr))
+			return false;
+	return true;
+}
+
+static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb)
+{
+	struct uffdio_writeprotect wp_prms;
+	uint64_t features = 0;
+	void *addr = NULL;
+	void *mem = NULL;
+
+	assert(!(hugetlb && swapout));
+
+	ksft_print_msg("[RUN] %s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n",
+				__func__,
+				size,
+				private ? "true" : "false",
+				swapout ? "true" : "false",
+				hugetlb ? "true" : "false");
+
+	/* Allocate a folio of required size and type. */
+	mem = alloc_one_folio(size, private, hugetlb);
+	if (!mem) {
+		ksft_test_result_fail("alloc_one_folio() failed\n");
+		goto out;
+	}
+
+	/* Register range for uffd-wp. */
+	if (userfaultfd_open(&features)) {
+		ksft_test_result_fail("userfaultfd_open() failed\n");
+		goto out;
+	}
+	if (uffd_register(uffd, mem, size, false, true, false)) {
+		ksft_test_result_fail("uffd_register() failed\n");
+		goto out;
+	}
+	wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP;
+	wp_prms.range.start = (uintptr_t)mem;
+	wp_prms.range.len = size;
+	if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) {
+		ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n");
+		goto out;
+	}
+
+	if (swapout) {
+		madvise(mem, size, MADV_PAGEOUT);
+		if (!range_is_swapped(mem, size)) {
+			ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n");
+			goto out;
+		}
+	}
+
+	/* Check that uffd-wp is set for all PTEs in range. */
+	if (!check_uffd_wp_state(mem, size, true))
+		goto out;
+
+	/*
+	 * Move the mapping to a new, aligned location. Since
+	 * UFFD_FEATURE_EVENT_REMAP is not set, we expect the uffd-wp bit for
+	 * each PTE to be cleared in the new mapping.
+	 */
+	addr = mmap_aligned(size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS);
+	if (addr == MAP_FAILED) {
+		ksft_test_result_fail("mmap_aligned() failed\n");
+		goto out;
+	}
+	if (mremap(mem, size, size, MREMAP_FIXED | MREMAP_MAYMOVE, addr) == MAP_FAILED) {
+		ksft_test_result_fail("mremap() failed\n");
+		munmap(addr, size);
+		goto out;
+	}
+	mem = addr;
+
+	/* Check that uffd-wp is cleared for all PTEs in range. */
+	if (!check_uffd_wp_state(mem, size, false))
+		goto out;
+
+	ksft_test_result_pass("%s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n",
+				__func__,
+				size,
+				private ? "true" : "false",
+				swapout ? "true" : "false",
+				hugetlb ? "true" : "false");
+out:
+	if (mem)
+		munmap(mem, size);
+	if (uffd >= 0) {
+		close(uffd);
+		uffd = -1;
+	}
+}
+
+struct testcase {
+	size_t *sizes;
+	int *nr_sizes;
+	bool private;
+	bool swapout;
+	bool hugetlb;
+};
+
+static const struct testcase testcases[] = {
+	/* base pages. */
+	{
+		.sizes = &pagesize,
+		.nr_sizes = &nr_pagesizes,
+		.private = false,
+		.swapout = false,
+		.hugetlb = false,
+	},
+	{
+		.sizes = &pagesize,
+		.nr_sizes = &nr_pagesizes,
+		.private = true,
+		.swapout = false,
+		.hugetlb = false,
+	},
+	{
+		.sizes = &pagesize,
+		.nr_sizes = &nr_pagesizes,
+		.private = false,
+		.swapout = true,
+		.hugetlb = false,
+	},
+	{
+		.sizes = &pagesize,
+		.nr_sizes = &nr_pagesizes,
+		.private = true,
+		.swapout = true,
+		.hugetlb = false,
+	},
+
+	/* thp. */
+	{
+		.sizes = thpsizes,
+		.nr_sizes = &nr_thpsizes,
+		.private = false,
+		.swapout = false,
+		.hugetlb = false,
+	},
+	{
+		.sizes = thpsizes,
+		.nr_sizes = &nr_thpsizes,
+		.private = true,
+		.swapout = false,
+		.hugetlb = false,
+	},
+	{
+		.sizes = thpsizes,
+		.nr_sizes = &nr_thpsizes,
+		.private = false,
+		.swapout = true,
+		.hugetlb = false,
+	},
+	{
+		.sizes = thpsizes,
+		.nr_sizes = &nr_thpsizes,
+		.private = true,
+		.swapout = true,
+		.hugetlb = false,
+	},
+
+	/* hugetlb. */
+	{
+		.sizes = hugetlbsizes,
+		.nr_sizes = &nr_hugetlbsizes,
+		.private = false,
+		.swapout = false,
+		.hugetlb = true,
+	},
+	{
+		.sizes = hugetlbsizes,
+		.nr_sizes = &nr_hugetlbsizes,
+		.private = true,
+		.swapout = false,
+		.hugetlb = true,
+	},
+};
+
+int main(int argc, char **argv)
+{
+	struct thp_settings settings;
+	int i, j, plan = 0;
+
+	pagesize = getpagesize();
+	nr_thpsizes = detect_thp_sizes(thpsizes, ARRAY_SIZE(thpsizes));
+	nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes,
+						    ARRAY_SIZE(hugetlbsizes));
+
+	/* If THP is supported, save THP settings and initially disable THP. */
+	if (nr_thpsizes) {
+		thp_save_settings();
+		thp_read_settings(&settings);
+		for (i = 0; i < NR_ORDERS; i++) {
+			settings.hugepages[i].enabled = THP_NEVER;
+			settings.shmem_hugepages[i].enabled = SHMEM_NEVER;
+		}
+		thp_push_settings(&settings);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++)
+		plan += *testcases[i].nr_sizes;
+	ksft_set_plan(plan);
+
+	pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+	if (pagemap_fd < 0)
+		ksft_exit_fail_msg("opening pagemap failed\n");
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		const struct testcase *tc = &testcases[i];
+
+		for (j = 0; j < *tc->nr_sizes; j++)
+			test_one_folio(tc->sizes[j], tc->private, tc->swapout,
+				       tc->hugetlb);
+	}
+
+	/* If THP is supported, restore original THP settings. */
+	if (nr_thpsizes)
+		thp_restore_settings();
+
+	i = ksft_get_fail_cnt();
+	if (i)
+		ksft_exit_fail_msg("%d out of %d tests failed\n",
+				   i, ksft_test_num());
+	ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c
index 2a2b69e91950..b380e102b22f 100644
--- a/tools/testing/selftests/mm/virtual_address_range.c
+++ b/tools/testing/selftests/mm/virtual_address_range.c
@@ -10,10 +10,12 @@
 #include <string.h>
 #include <unistd.h>
 #include <errno.h>
+#include <sys/prctl.h>
 #include <sys/mman.h>
 #include <sys/time.h>
 #include <fcntl.h>
 
+#include "vm_util.h"
 #include "../kselftest.h"
 
 /*
@@ -82,6 +84,24 @@ static void validate_addr(char *ptr, int high_addr)
 		ksft_exit_fail_msg("Bad address %lx\n", addr);
 }
 
+static void mark_range(char *ptr, size_t size)
+{
+	if (prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, ptr, size, "virtual_address_range") == -1) {
+		if (errno == EINVAL) {
+			/* Depends on CONFIG_ANON_VMA_NAME */
+			ksft_test_result_skip("prctl(PR_SET_VMA_ANON_NAME) not supported\n");
+			ksft_finished();
+		} else {
+			ksft_exit_fail_perror("prctl(PR_SET_VMA_ANON_NAME) failed\n");
+		}
+	}
+}
+
+static int is_marked_vma(const char *vma_name)
+{
+	return vma_name && !strcmp(vma_name, "[anon:virtual_address_range]\n");
+}
+
 static int validate_lower_address_hint(void)
 {
 	char *ptr;
@@ -116,12 +136,17 @@ static int validate_complete_va_space(void)
 
 	prev_end_addr = 0;
 	while (fgets(line, sizeof(line), file)) {
+		const char *vma_name = NULL;
+		int vma_name_start = 0;
 		unsigned long hop;
 
-		if (sscanf(line, "%lx-%lx %s[rwxp-]",
-			   &start_addr, &end_addr, prot) != 3)
+		if (sscanf(line, "%lx-%lx %4s %*s %*s %*s %n",
+			   &start_addr, &end_addr, prot, &vma_name_start) != 3)
 			ksft_exit_fail_msg("cannot parse /proc/self/maps\n");
 
+		if (vma_name_start)
+			vma_name = line + vma_name_start;
+
 		/* end of userspace mappings; ignore vsyscall mapping */
 		if (start_addr & (1UL << 63))
 			return 0;
@@ -135,6 +160,9 @@ static int validate_complete_va_space(void)
 		if (prot[0] != 'r')
 			continue;
 
+		if (check_vmflag_io((void *)start_addr))
+			continue;
+
 		/*
 		 * Confirm whether MAP_CHUNK_SIZE chunk can be found or not.
 		 * If write succeeds, no need to check MAP_CHUNK_SIZE - 1
@@ -149,6 +177,9 @@ static int validate_complete_va_space(void)
 				return 1;
 			lseek(fd, 0, SEEK_SET);
 
+			if (is_marked_vma(vma_name))
+				munmap((char *)(start_addr + hop), MAP_CHUNK_SIZE);
+
 			hop += MAP_CHUNK_SIZE;
 		}
 	}
@@ -166,7 +197,7 @@ int main(int argc, char *argv[])
 	ksft_set_plan(1);
 
 	for (i = 0; i < NR_CHUNKS_LOW; i++) {
-		ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE,
+		ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ,
 			      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 
 		if (ptr[i] == MAP_FAILED) {
@@ -175,6 +206,7 @@ int main(int argc, char *argv[])
 			break;
 		}
 
+		mark_range(ptr[i], MAP_CHUNK_SIZE);
 		validate_addr(ptr[i], 0);
 	}
 	lchunks = i;
@@ -186,12 +218,13 @@ int main(int argc, char *argv[])
 
 	for (i = 0; i < NR_CHUNKS_HIGH; i++) {
 		hint = hint_addr();
-		hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE,
+		hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ,
 			       MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 
 		if (hptr[i] == MAP_FAILED)
 			break;
 
+		mark_range(ptr[i], MAP_CHUNK_SIZE);
 		validate_addr(hptr[i], 1);
 	}
 	hchunks = i;
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index d8d0cf04bb57..a36734fb62f3 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -2,6 +2,7 @@
 #include <string.h>
 #include <fcntl.h>
 #include <dirent.h>
+#include <inttypes.h>
 #include <sys/ioctl.h>
 #include <linux/userfaultfd.h>
 #include <linux/fs.h>
@@ -138,7 +139,7 @@ void clear_softdirty(void)
 		ksft_exit_fail_msg("opening clear_refs failed\n");
 	ret = write(fd, ctrl, strlen(ctrl));
 	close(fd);
-	if (ret != strlen(ctrl))
+	if (ret != (signed int)strlen(ctrl))
 		ksft_exit_fail_msg("writing clear_refs failed\n");
 }
 
@@ -193,13 +194,11 @@ err_out:
 	return rss_anon;
 }
 
-bool __check_huge(void *addr, char *pattern, int nr_hpages,
-		  uint64_t hpage_size)
+char *__get_smap_entry(void *addr, const char *pattern, char *buf, size_t len)
 {
-	uint64_t thp = -1;
 	int ret;
 	FILE *fp;
-	char buffer[MAX_LINE_LENGTH];
+	char *entry = NULL;
 	char addr_pattern[MAX_LINE_LENGTH];
 
 	ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
@@ -211,23 +210,40 @@ bool __check_huge(void *addr, char *pattern, int nr_hpages,
 	if (!fp)
 		ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, SMAP_FILE_PATH);
 
-	if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer)))
+	if (!check_for_pattern(fp, addr_pattern, buf, len))
 		goto err_out;
 
-	/*
-	 * Fetch the pattern in the same block and check the number of
-	 * hugepages.
-	 */
-	if (!check_for_pattern(fp, pattern, buffer, sizeof(buffer)))
+	/* Fetch the pattern in the same block */
+	if (!check_for_pattern(fp, pattern, buf, len))
 		goto err_out;
 
-	snprintf(addr_pattern, MAX_LINE_LENGTH, "%s%%9ld kB", pattern);
+	/* Trim trailing newline */
+	entry = strchr(buf, '\n');
+	if (entry)
+		*entry = '\0';
 
-	if (sscanf(buffer, addr_pattern, &thp) != 1)
-		ksft_exit_fail_msg("Reading smap error\n");
+	entry = buf + strlen(pattern);
 
 err_out:
 	fclose(fp);
+	return entry;
+}
+
+bool __check_huge(void *addr, char *pattern, int nr_hpages,
+		  uint64_t hpage_size)
+{
+	char buffer[MAX_LINE_LENGTH];
+	uint64_t thp = -1;
+	char *entry;
+
+	entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer));
+	if (!entry)
+		goto err_out;
+
+	if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1)
+		ksft_exit_fail_msg("Reading smap error\n");
+
+err_out:
 	return thp == (nr_hpages * (hpage_size >> 10));
 }
 
@@ -384,3 +400,27 @@ unsigned long get_free_hugepages(void)
 	fclose(f);
 	return fhp;
 }
+
+bool check_vmflag_io(void *addr)
+{
+	char buffer[MAX_LINE_LENGTH];
+	const char *flags;
+	size_t flaglen;
+
+	flags = __get_smap_entry(addr, "VmFlags:", buffer, sizeof(buffer));
+	if (!flags)
+		ksft_exit_fail_msg("%s: No VmFlags for %p\n", __func__, addr);
+
+	while (true) {
+		flags += strspn(flags, " ");
+
+		flaglen = strcspn(flags, " ");
+		if (!flaglen)
+			return false;
+
+		if (flaglen == strlen("io") && !memcmp(flags, "io", flaglen))
+			return true;
+
+		flags += flaglen;
+	}
+}
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 2eaed8209925..b60ac68a9dc8 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -53,6 +53,7 @@ int uffd_unregister(int uffd, void *addr, uint64_t len);
 int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
 			      bool miss, bool wp, bool minor, uint64_t *ioctls);
 unsigned long get_free_hugepages(void);
+bool check_vmflag_io(void *addr);
 
 /*
  * On ppc64 this will only work with radix 2M hugepage size
diff --git a/tools/testing/selftests/mm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c
index 1289d311efd7..34c91f7e6128 100644
--- a/tools/testing/selftests/mm/write_to_hugetlbfs.c
+++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c
@@ -89,7 +89,7 @@ int main(int argc, char **argv)
 			size = atoi(optarg);
 			break;
 		case 'p':
-			strncpy(path, optarg, sizeof(path));
+			strncpy(path, optarg, sizeof(path) - 1);
 			break;
 		case 'm':
 			if (atoi(optarg) >= MAX_METHOD) {
diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py
index d10f420e4ef6..fd0d959914e4 100755
--- a/tools/testing/selftests/net/bpf_offload.py
+++ b/tools/testing/selftests/net/bpf_offload.py
@@ -215,12 +215,14 @@ def bpftool_map_list_wait(expected=0, n_retry=20, ns=""):
     raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
 
 def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None,
-                      fail=True, include_stderr=False):
+                      fail=True, include_stderr=False, dev_bind=None):
     args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name)
     if prog_type is not None:
         args += " type " + prog_type
     if dev is not None:
         args += " dev " + dev
+    elif dev_bind is not None:
+        args += " xdpmeta_dev " + dev_bind
     if len(maps):
         args += " map " + " map ".join(maps)
 
@@ -980,6 +982,16 @@ try:
     rm("/sys/fs/bpf/offload")
     sim.wait_for_flush()
 
+    bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/devbound",
+                      dev_bind=sim['ifname'])
+    devbound = bpf_pinned("/sys/fs/bpf/devbound")
+    start_test("Test dev-bound program in generic mode...")
+    ret, _, err = sim.set_xdp(devbound, "generic", fail=False, include_stderr=True)
+    fail(ret == 0, "devbound program in generic mode allowed")
+    check_extack(err, "Can't attach device-bound programs in generic mode.", args)
+    rm("/sys/fs/bpf/devbound")
+    sim.wait_for_flush()
+
     start_test("Test XDP load failure...")
     sim.dfs["dev/bpf_bind_verifier_accept"] = 0
     ret, _, err = bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/offload",
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index 18b9443454a9..bc6b6762baf3 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g
 CFLAGS += -I../../../../../usr/include/ $(KHDR_INCLUDES)
 # Additional include paths needed by kselftest.h
 CFLAGS += -I../../
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index 8e3fc05a5397..c76525fe2b84 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -2,7 +2,7 @@
 
 top_srcdir = ../../../../..
 
-CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
 
 TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
 	      simult_flows.sh mptcp_sockopt.sh userspace_pm.sh
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 414addef9a45..d240d02fa443 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -1302,7 +1302,7 @@ again:
 		return ret;
 
 	if (cfg_truncate > 0) {
-		xdisconnect(fd);
+		shutdown(fd, SHUT_WR);
 	} else if (--cfg_repeat > 0) {
 		xdisconnect(fd);
 
diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile
index 2f1508abc826..3fd1da2ec07d 100644
--- a/tools/testing/selftests/net/openvswitch/Makefile
+++ b/tools/testing/selftests/net/openvswitch/Makefile
@@ -2,7 +2,7 @@
 
 top_srcdir = ../../../../..
 
-CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
 
 TEST_PROGS := openvswitch.sh
 
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
index e15c43b7359b..ef8b25a606d8 100755
--- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -39,11 +39,13 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then
 	# xfail tests that are known flaky with dbg config, not fixable.
 	# still run them for coverage (and expect 100% pass without dbg).
 	declare -ar xfail_list=(
+		"tcp_eor_no-coalesce-retrans.pkt"
 		"tcp_fast_recovery_prr-ss.*.pkt"
+		"tcp_slow_start_slow-start-after-win-update.pkt"
 		"tcp_timestamping.*.pkt"
 		"tcp_user_timeout_user-timeout-probe.pkt"
 		"tcp_zerocopy_epoll_.*.pkt"
-		"tcp_tcp_info_tcp-info-*-limited.pkt"
+		"tcp_tcp_info_tcp-info-.*-limited.pkt"
 	)
 	readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$"
 	[[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 3f2fca02fec5..36ff28af4b19 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -103,6 +103,19 @@ struct testcase testcases_v4[] = {
 		.r_num_mss = 1,
 	},
 	{
+		/* datalen <= MSS < gso_len: will fall back to no GSO */
+		.tlen = CONST_MSS_V4,
+		.gso_len = CONST_MSS_V4 + 1,
+		.r_num_mss = 0,
+		.r_len_last = CONST_MSS_V4,
+	},
+	{
+		/* MSS < datalen < gso_len: fail */
+		.tlen = CONST_MSS_V4 + 1,
+		.gso_len = CONST_MSS_V4 + 2,
+		.tfail = true,
+	},
+	{
 		/* send a single MSS + 1B */
 		.tlen = CONST_MSS_V4 + 1,
 		.gso_len = CONST_MSS_V4,
@@ -206,6 +219,19 @@ struct testcase testcases_v6[] = {
 		.r_num_mss = 1,
 	},
 	{
+		/* datalen <= MSS < gso_len: will fall back to no GSO */
+		.tlen = CONST_MSS_V6,
+		.gso_len = CONST_MSS_V6 + 1,
+		.r_num_mss = 0,
+		.r_len_last = CONST_MSS_V6,
+	},
+	{
+		/* MSS < datalen < gso_len: fail */
+		.tlen = CONST_MSS_V6 + 1,
+		.gso_len = CONST_MSS_V6 + 2,
+		.tfail = true
+	},
+	{
 		/* send a single MSS + 1B */
 		.tlen = CONST_MSS_V6 + 1,
 		.gso_len = CONST_MSS_V6,
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 9faa686f90e4..e9728e86b4f2 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -497,7 +497,7 @@ static int child_poll_leader_exit_test(void *args)
 	pthread_create(&t2, NULL, test_pidfd_poll_leader_exit_thread, NULL);
 
 	/*
-	 * glibc exit calls exit_group syscall, so explicity call exit only
+	 * glibc exit calls exit_group syscall, so explicitly call exit only
 	 * so that only the group leader exits, leaving the threads alone.
 	 */
 	*child_exit_secs = time(NULL);
diff --git a/tools/testing/selftests/riscv/vector/.gitignore b/tools/testing/selftests/riscv/vector/.gitignore
index 9ae7964491d5..7d9c87cd0649 100644
--- a/tools/testing/selftests/riscv/vector/.gitignore
+++ b/tools/testing/selftests/riscv/vector/.gitignore
@@ -1,3 +1,4 @@
 vstate_exec_nolibc
 vstate_prctl
-v_initval_nolibc
+v_initval
+v_exec_initval_nolibc
diff --git a/tools/testing/selftests/riscv/vector/Makefile b/tools/testing/selftests/riscv/vector/Makefile
index bfff0ff4f3be..6f7497f4e7b3 100644
--- a/tools/testing/selftests/riscv/vector/Makefile
+++ b/tools/testing/selftests/riscv/vector/Makefile
@@ -2,18 +2,27 @@
 # Copyright (C) 2021 ARM Limited
 # Originally tools/testing/arm64/abi/Makefile
 
-TEST_GEN_PROGS := vstate_prctl v_initval_nolibc
-TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc
+TEST_GEN_PROGS := v_initval vstate_prctl
+TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc v_exec_initval_nolibc
 
 include ../../lib.mk
 
-$(OUTPUT)/vstate_prctl: vstate_prctl.c ../hwprobe/sys_hwprobe.S
+$(OUTPUT)/sys_hwprobe.o: ../hwprobe/sys_hwprobe.S
+	$(CC) -static -c -o$@ $(CFLAGS) $^
+
+$(OUTPUT)/v_helpers.o: v_helpers.c
+	$(CC) -static -c -o$@ $(CFLAGS) $^
+
+$(OUTPUT)/vstate_prctl: vstate_prctl.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o
 	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
 
 $(OUTPUT)/vstate_exec_nolibc: vstate_exec_nolibc.c
 	$(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \
 		-Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc
 
-$(OUTPUT)/v_initval_nolibc: v_initval_nolibc.c
+$(OUTPUT)/v_initval: v_initval.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o
+	$(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^
+
+$(OUTPUT)/v_exec_initval_nolibc: v_exec_initval_nolibc.c
 	$(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \
 		-Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc
diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c
new file mode 100644
index 000000000000..35c0812e32de
--- /dev/null
+++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Get values of vector registers as soon as the program starts to test if
+ * is properly cleaning the values before starting a new program. Vector
+ * registers are caller saved, so no function calls may happen before reading
+ * the values. To further ensure consistency, this file is compiled without
+ * libc and without auto-vectorization.
+ *
+ * To be "clean" all values must be either all ones or all zeroes.
+ */
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+int main(int argc, char **argv)
+{
+	char prev_value = 0, value;
+	unsigned long vl;
+	int first = 1;
+
+	if (argc > 2 && strcmp(argv[2], "x"))
+		asm volatile (
+			// 0 | zimm[10:0] | rs1 | 1 1 1 | rd |1010111| vsetvli
+			// vsetvli	t4, x0, e8, m1, d1
+			".4byte		0b00000000000000000111111011010111\n\t"
+			"mv		%[vl], t4\n\t"
+			: [vl] "=r" (vl) : : "t4"
+		);
+	else
+		asm volatile (
+			".option push\n\t"
+			".option arch, +v\n\t"
+			"vsetvli	%[vl], x0, e8, m1, ta, ma\n\t"
+			".option pop\n\t"
+			: [vl] "=r" (vl)
+		);
+
+#define CHECK_VECTOR_REGISTER(register) ({					\
+	for (int i = 0; i < vl; i++) {						\
+		asm volatile (							\
+			".option push\n\t"					\
+			".option arch, +v\n\t"					\
+			"vmv.x.s %0, " __stringify(register) "\n\t"		\
+			"vsrl.vi " __stringify(register) ", " __stringify(register) ", 8\n\t" \
+			".option pop\n\t"					\
+			: "=r" (value));					\
+		if (first) {							\
+			first = 0;						\
+		} else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \
+			printf("Register " __stringify(register)		\
+				" values not clean! value: %u\n", value);	\
+			exit(-1);						\
+		}								\
+		prev_value = value;						\
+	}									\
+})
+
+	CHECK_VECTOR_REGISTER(v0);
+	CHECK_VECTOR_REGISTER(v1);
+	CHECK_VECTOR_REGISTER(v2);
+	CHECK_VECTOR_REGISTER(v3);
+	CHECK_VECTOR_REGISTER(v4);
+	CHECK_VECTOR_REGISTER(v5);
+	CHECK_VECTOR_REGISTER(v6);
+	CHECK_VECTOR_REGISTER(v7);
+	CHECK_VECTOR_REGISTER(v8);
+	CHECK_VECTOR_REGISTER(v9);
+	CHECK_VECTOR_REGISTER(v10);
+	CHECK_VECTOR_REGISTER(v11);
+	CHECK_VECTOR_REGISTER(v12);
+	CHECK_VECTOR_REGISTER(v13);
+	CHECK_VECTOR_REGISTER(v14);
+	CHECK_VECTOR_REGISTER(v15);
+	CHECK_VECTOR_REGISTER(v16);
+	CHECK_VECTOR_REGISTER(v17);
+	CHECK_VECTOR_REGISTER(v18);
+	CHECK_VECTOR_REGISTER(v19);
+	CHECK_VECTOR_REGISTER(v20);
+	CHECK_VECTOR_REGISTER(v21);
+	CHECK_VECTOR_REGISTER(v22);
+	CHECK_VECTOR_REGISTER(v23);
+	CHECK_VECTOR_REGISTER(v24);
+	CHECK_VECTOR_REGISTER(v25);
+	CHECK_VECTOR_REGISTER(v26);
+	CHECK_VECTOR_REGISTER(v27);
+	CHECK_VECTOR_REGISTER(v28);
+	CHECK_VECTOR_REGISTER(v29);
+	CHECK_VECTOR_REGISTER(v30);
+	CHECK_VECTOR_REGISTER(v31);
+
+#undef CHECK_VECTOR_REGISTER
+
+	return 0;
+}
diff --git a/tools/testing/selftests/riscv/vector/v_helpers.c b/tools/testing/selftests/riscv/vector/v_helpers.c
new file mode 100644
index 000000000000..01a8799dcb78
--- /dev/null
+++ b/tools/testing/selftests/riscv/vector/v_helpers.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "../hwprobe/hwprobe.h"
+#include <asm/vendor/thead.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+bool is_xtheadvector_supported(void)
+{
+	struct riscv_hwprobe pair;
+
+	pair.key = RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0;
+	riscv_hwprobe(&pair, 1, 0, NULL, 0);
+	return pair.value & RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR;
+}
+
+bool is_vector_supported(void)
+{
+	struct riscv_hwprobe pair;
+
+	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
+	riscv_hwprobe(&pair, 1, 0, NULL, 0);
+	return pair.value & RISCV_HWPROBE_EXT_ZVE32X;
+}
+
+int launch_test(char *next_program, int test_inherit, int xtheadvector)
+{
+	char *exec_argv[4], *exec_envp[1];
+	int rc, pid, status;
+
+	pid = fork();
+	if (pid < 0) {
+		printf("fork failed %d", pid);
+		return -1;
+	}
+
+	if (!pid) {
+		exec_argv[0] = next_program;
+		exec_argv[1] = test_inherit != 0 ? "x" : NULL;
+		exec_argv[2] = xtheadvector != 0 ? "x" : NULL;
+		exec_argv[3] = NULL;
+		exec_envp[0] = NULL;
+		/* launch the program again to check inherit */
+		rc = execve(next_program, exec_argv, exec_envp);
+		if (rc) {
+			perror("execve");
+			printf("child execve failed %d\n", rc);
+			exit(-1);
+		}
+	}
+
+	rc = waitpid(-1, &status, 0);
+	if (rc < 0) {
+		printf("waitpid failed\n");
+		return -3;
+	}
+
+	if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) ||
+	    WIFSIGNALED(status)) {
+		printf("child exited abnormally\n");
+		return -4;
+	}
+
+	return WEXITSTATUS(status);
+}
diff --git a/tools/testing/selftests/riscv/vector/v_helpers.h b/tools/testing/selftests/riscv/vector/v_helpers.h
new file mode 100644
index 000000000000..763cddfe26da
--- /dev/null
+++ b/tools/testing/selftests/riscv/vector/v_helpers.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <stdbool.h>
+
+bool is_xtheadvector_supported(void);
+
+bool is_vector_supported(void);
+
+int launch_test(char *next_program, int test_inherit, int xtheadvector);
diff --git a/tools/testing/selftests/riscv/vector/v_initval.c b/tools/testing/selftests/riscv/vector/v_initval.c
new file mode 100644
index 000000000000..be9e1d18ad29
--- /dev/null
+++ b/tools/testing/selftests/riscv/vector/v_initval.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "../../kselftest_harness.h"
+#include "v_helpers.h"
+
+#define NEXT_PROGRAM "./v_exec_initval_nolibc"
+
+TEST(v_initval)
+{
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
+	}
+
+	ASSERT_EQ(0, launch_test(NEXT_PROGRAM, 0, xtheadvector));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
deleted file mode 100644
index 6174ffe016dc..000000000000
--- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
+++ /dev/null
@@ -1,72 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-
-#include "../../kselftest.h"
-#define MAX_VSIZE	(8192 * 32)
-
-void dump(char *ptr, int size)
-{
-	int i = 0;
-
-	for (i = 0; i < size; i++) {
-		if (i != 0) {
-			if (i % 16 == 0)
-				printf("\n");
-			else if (i % 8 == 0)
-				printf("  ");
-		}
-		printf("%02x ", ptr[i]);
-	}
-	printf("\n");
-}
-
-int main(void)
-{
-	int i;
-	unsigned long vl;
-	char *datap, *tmp;
-
-	ksft_set_plan(1);
-
-	datap = malloc(MAX_VSIZE);
-	if (!datap) {
-		ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE);
-		exit(-1);
-	}
-
-	tmp = datap;
-	asm volatile (
-		".option push\n\t"
-		".option arch, +v\n\t"
-		"vsetvli	%0, x0, e8, m8, ta, ma\n\t"
-		"vse8.v		v0, (%2)\n\t"
-		"add		%1, %2, %0\n\t"
-		"vse8.v		v8, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vse8.v		v16, (%1)\n\t"
-		"add		%1, %1, %0\n\t"
-		"vse8.v		v24, (%1)\n\t"
-		".option pop\n\t"
-		: "=&r" (vl), "=r" (tmp) : "r" (datap) : "memory");
-
-	ksft_print_msg("vl = %lu\n", vl);
-
-	if (datap[0] != 0x00 && datap[0] != 0xff) {
-		ksft_test_result_fail("v-regesters are not properly initialized\n");
-		dump(datap, vl * 4);
-		exit(-1);
-	}
-
-	for (i = 1; i < vl * 4; i++) {
-		if (datap[i] != datap[0]) {
-			ksft_test_result_fail("detect stale values on v-regesters\n");
-			dump(datap, vl * 4);
-			exit(-2);
-		}
-	}
-
-	free(datap);
-
-	ksft_test_result_pass("tests for v_initval_nolibc pass\n");
-	ksft_exit_pass();
-	return 0;
-}
diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
index 1f9969bed235..7b7d6f21acb4 100644
--- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c
@@ -6,13 +6,16 @@
 
 int main(int argc, char **argv)
 {
-	int rc, pid, status, test_inherit = 0;
+	int rc, pid, status, test_inherit = 0, xtheadvector = 0;
 	long ctrl, ctrl_c;
 	char *exec_argv[2], *exec_envp[2];
 
-	if (argc > 1)
+	if (argc > 1 && strcmp(argv[1], "x"))
 		test_inherit = 1;
 
+	if (argc > 2 && strcmp(argv[2], "x"))
+		xtheadvector = 1;
+
 	ctrl = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL);
 	if (ctrl < 0) {
 		puts("PR_RISCV_V_GET_CONTROL is not supported\n");
@@ -53,11 +56,14 @@ int main(int argc, char **argv)
 				puts("child's vstate_ctrl not equal to parent's\n");
 				exit(-1);
 			}
-			asm volatile (".option push\n\t"
-				      ".option arch, +v\n\t"
-				      "vsetvli x0, x0, e32, m8, ta, ma\n\t"
-				      ".option pop\n\t"
-				      );
+			if (xtheadvector)
+				asm volatile (".4byte	0x00007ed7");
+			else
+				asm volatile (".option push\n\t"
+					".option arch, +v\n\t"
+					"vsetvli x0, x0, e32, m8, ta, ma\n\t"
+					".option pop\n\t"
+					);
 			exit(ctrl);
 		}
 	}
diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c
index 40b3bffcbb40..62fbb17a0556 100644
--- a/tools/testing/selftests/riscv/vector/vstate_prctl.c
+++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c
@@ -3,181 +3,244 @@
 #include <unistd.h>
 #include <errno.h>
 #include <sys/wait.h>
+#include <sys/types.h>
+#include <stdlib.h>
 
-#include "../hwprobe/hwprobe.h"
-#include "../../kselftest.h"
+#include "../../kselftest_harness.h"
+#include "v_helpers.h"
 
 #define NEXT_PROGRAM "./vstate_exec_nolibc"
-static int launch_test(int test_inherit)
-{
-	char *exec_argv[3], *exec_envp[1];
-	int rc, pid, status;
-
-	pid = fork();
-	if (pid < 0) {
-		ksft_test_result_fail("fork failed %d", pid);
-		return -1;
-	}
 
-	if (!pid) {
-		exec_argv[0] = NEXT_PROGRAM;
-		exec_argv[1] = test_inherit != 0 ? "x" : NULL;
-		exec_argv[2] = NULL;
-		exec_envp[0] = NULL;
-		/* launch the program again to check inherit */
-		rc = execve(NEXT_PROGRAM, exec_argv, exec_envp);
-		if (rc) {
-			perror("execve");
-			ksft_test_result_fail("child execve failed %d\n", rc);
-			exit(-1);
-		}
-	}
-
-	rc = waitpid(-1, &status, 0);
-	if (rc < 0) {
-		ksft_test_result_fail("waitpid failed\n");
-		return -3;
-	}
-
-	if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) ||
-	    WIFSIGNALED(status)) {
-		ksft_test_result_fail("child exited abnormally\n");
-		return -4;
-	}
-
-	return WEXITSTATUS(status);
-}
-
-int test_and_compare_child(long provided, long expected, int inherit)
+int test_and_compare_child(long provided, long expected, int inherit, int xtheadvector)
 {
 	int rc;
 
 	rc = prctl(PR_RISCV_V_SET_CONTROL, provided);
 	if (rc != 0) {
-		ksft_test_result_fail("prctl with provided arg %lx failed with code %d\n",
-				      provided, rc);
+		printf("prctl with provided arg %lx failed with code %d\n",
+		       provided, rc);
 		return -1;
 	}
-	rc = launch_test(inherit);
+	rc = launch_test(NEXT_PROGRAM, inherit, xtheadvector);
 	if (rc != expected) {
-		ksft_test_result_fail("Test failed, check %d != %ld\n", rc,
-				      expected);
+		printf("Test failed, check %d != %ld\n", rc, expected);
 		return -2;
 	}
 	return 0;
 }
 
-#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT	0
-#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT	2
+#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0
+#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2
 
-int main(void)
+TEST(get_control_no_v)
 {
-	struct riscv_hwprobe pair;
-	long flag, expected;
 	long rc;
 
-	ksft_set_plan(1);
+	if (is_vector_supported() || is_xtheadvector_supported())
+		SKIP(return, "Test expects vector to be not supported");
 
-	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
-	rc = riscv_hwprobe(&pair, 1, 0, NULL, 0);
-	if (rc < 0) {
-		ksft_test_result_fail("hwprobe() failed with %ld\n", rc);
-		return -1;
-	}
+	rc = prctl(PR_RISCV_V_GET_CONTROL);
+	EXPECT_EQ(-1, rc)
+	TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X");
+	EXPECT_EQ(EINVAL, errno)
+	TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X");
+}
 
-	if (pair.key != RISCV_HWPROBE_KEY_IMA_EXT_0) {
-		ksft_test_result_fail("hwprobe cannot probe RISCV_HWPROBE_KEY_IMA_EXT_0\n");
-		return -2;
-	}
+TEST(set_control_no_v)
+{
+	long rc;
 
-	if (!(pair.value & RISCV_HWPROBE_EXT_ZVE32X)) {
-		rc = prctl(PR_RISCV_V_GET_CONTROL);
-		if (rc != -1 || errno != EINVAL) {
-			ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without ZVE32X\n");
-			return -3;
-		}
-
-		rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON);
-		if (rc != -1 || errno != EINVAL) {
-			ksft_test_result_fail("SET_CONTROL should fail on kernel/hw without ZVE32X\n");
-			return -4;
-		}
-
-		ksft_test_result_skip("Vector not supported\n");
-		return 0;
-	}
+	if (is_vector_supported() || is_xtheadvector_supported())
+		SKIP(return, "Test expects vector to be not supported");
+
+	rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON);
+	EXPECT_EQ(-1, rc)
+	TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X");
+	EXPECT_EQ(EINVAL, errno)
+	TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X");
+}
+
+TEST(vstate_on_current)
+{
+	long flag;
+	long rc;
+
+	if (!is_vector_supported() && !is_xtheadvector_supported())
+		SKIP(return, "Vector not supported");
 
 	flag = PR_RISCV_V_VSTATE_CTRL_ON;
 	rc = prctl(PR_RISCV_V_SET_CONTROL, flag);
-	if (rc != 0) {
-		ksft_test_result_fail("Enabling V for current should always success\n");
-		return -5;
-	}
+	EXPECT_EQ(0, rc) TH_LOG("Enabling V for current should always succeed");
+}
+
+TEST(vstate_off_eperm)
+{
+	long flag;
+	long rc;
+
+	if (!is_vector_supported() && !is_xtheadvector_supported())
+		SKIP(return, "Vector not supported");
 
 	flag = PR_RISCV_V_VSTATE_CTRL_OFF;
 	rc = prctl(PR_RISCV_V_SET_CONTROL, flag);
-	if (rc != -1 || errno != EPERM) {
-		ksft_test_result_fail("Disabling current's V alive must fail with EPERM(%d)\n",
-				      errno);
-		return -5;
+	EXPECT_EQ(EPERM, errno)
+	TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno);
+	EXPECT_EQ(-1, rc)
+	TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno);
+}
+
+TEST(vstate_on_no_nesting)
+{
+	long flag;
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
 	}
 
 	/* Turn on next's vector explicitly and test */
 	flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT;
-	if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0))
-		return -6;
+
+	EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0, xtheadvector));
+}
+
+TEST(vstate_off_nesting)
+{
+	long flag;
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
+	}
 
 	/* Turn off next's vector explicitly and test */
 	flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT;
-	if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 0))
-		return -7;
+
+	EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 1, xtheadvector));
+}
+
+TEST(vstate_on_inherit_no_nesting)
+{
+	long flag, expected;
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
+	}
+
+	/* Turn on next's vector explicitly and test no inherit */
+	flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT;
+	flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
+	expected = flag | PR_RISCV_V_VSTATE_CTRL_ON;
+
+	EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector));
+}
+
+TEST(vstate_on_inherit)
+{
+	long flag, expected;
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
+	}
 
 	/* Turn on next's vector explicitly and test inherit */
 	flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT;
 	flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
 	expected = flag | PR_RISCV_V_VSTATE_CTRL_ON;
-	if (test_and_compare_child(flag, expected, 0))
-		return -8;
 
-	if (test_and_compare_child(flag, expected, 1))
-		return -9;
+	EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector));
+}
+
+TEST(vstate_off_inherit_no_nesting)
+{
+	long flag, expected;
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
+	}
+	/* Turn off next's vector explicitly and test no inherit */
+	flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT;
+	flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
+	expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF;
+
+	EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector));
+}
+
+TEST(vstate_off_inherit)
+{
+	long flag, expected;
+	int xtheadvector = 0;
+
+	if (!is_vector_supported()) {
+		if (is_xtheadvector_supported())
+			xtheadvector = 1;
+		else
+			SKIP(return, "Vector not supported");
+	}
 
 	/* Turn off next's vector explicitly and test inherit */
 	flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT;
 	flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
 	expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF;
-	if (test_and_compare_child(flag, expected, 0))
-		return -10;
 
-	if (test_and_compare_child(flag, expected, 1))
-		return -11;
+	EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector));
+}
+
+/* arguments should fail with EINVAL */
+TEST(inval_set_control_1)
+{
+	int rc;
+
+	if (!is_vector_supported() && !is_xtheadvector_supported())
+		SKIP(return, "Vector not supported");
 
-	/* arguments should fail with EINVAL */
 	rc = prctl(PR_RISCV_V_SET_CONTROL, 0xff0);
-	if (rc != -1 || errno != EINVAL) {
-		ksft_test_result_fail("Undefined control argument should return EINVAL\n");
-		return -12;
-	}
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+}
+
+/* arguments should fail with EINVAL */
+TEST(inval_set_control_2)
+{
+	int rc;
+
+	if (!is_vector_supported() && !is_xtheadvector_supported())
+		SKIP(return, "Vector not supported");
 
 	rc = prctl(PR_RISCV_V_SET_CONTROL, 0x3);
-	if (rc != -1 || errno != EINVAL) {
-		ksft_test_result_fail("Undefined control argument should return EINVAL\n");
-		return -12;
-	}
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
+}
 
-	rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc);
-	if (rc != -1 || errno != EINVAL) {
-		ksft_test_result_fail("Undefined control argument should return EINVAL\n");
-		return -12;
-	}
+/* arguments should fail with EINVAL */
+TEST(inval_set_control_3)
+{
+	int rc;
 
-	rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc);
-	if (rc != -1 || errno != EINVAL) {
-		ksft_test_result_fail("Undefined control argument should return EINVAL\n");
-		return -12;
-	}
+	if (!is_vector_supported() && !is_xtheadvector_supported())
+		SKIP(return, "Vector not supported");
 
-	ksft_test_result_pass("tests for riscv_v_vstate_ctrl pass\n");
-	ksft_exit_pass();
-	return 0;
+	rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc);
+	EXPECT_EQ(-1, rc);
+	EXPECT_EQ(EINVAL, errno);
 }
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 8c3a73461475..14ba51b52095 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -47,6 +47,7 @@
 #include <linux/kcmp.h>
 #include <sys/resource.h>
 #include <sys/capability.h>
+#include <linux/perf_event.h>
 
 #include <unistd.h>
 #include <sys/syscall.h>
@@ -68,6 +69,10 @@
 # define PR_SET_PTRACER 0x59616d61
 #endif
 
+#ifndef noinline
+#define noinline __attribute__((noinline))
+#endif
+
 #ifndef PR_SET_NO_NEW_PRIVS
 #define PR_SET_NO_NEW_PRIVS 38
 #define PR_GET_NO_NEW_PRIVS 39
@@ -4888,6 +4893,200 @@ TEST(tsync_vs_dead_thread_leader)
 	EXPECT_EQ(0, status);
 }
 
+noinline int probed(void)
+{
+	return 1;
+}
+
+static int parse_uint_from_file(const char *file, const char *fmt)
+{
+	int err = -1, ret;
+	FILE *f;
+
+	f = fopen(file, "re");
+	if (f) {
+		err = fscanf(f, fmt, &ret);
+		fclose(f);
+	}
+	return err == 1 ? ret : err;
+}
+
+static int determine_uprobe_perf_type(void)
+{
+	const char *file = "/sys/bus/event_source/devices/uprobe/type";
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
+static int determine_uprobe_retprobe_bit(void)
+{
+	const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe";
+
+	return parse_uint_from_file(file, "config:%d\n");
+}
+
+static ssize_t get_uprobe_offset(const void *addr)
+{
+	size_t start, base, end;
+	bool found = false;
+	char buf[256];
+	FILE *f;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f)
+		return -1;
+
+	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
+		if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
+			found = true;
+			break;
+		}
+	}
+	fclose(f);
+	return found ? (uintptr_t)addr - start + base : -1;
+}
+
+FIXTURE(URETPROBE) {
+	int fd;
+};
+
+FIXTURE_VARIANT(URETPROBE) {
+	/*
+	 * All of the URETPROBE behaviors can be tested with either
+	 * uretprobe attached or not
+	 */
+	bool attach;
+};
+
+FIXTURE_VARIANT_ADD(URETPROBE, attached) {
+	.attach = true,
+};
+
+FIXTURE_VARIANT_ADD(URETPROBE, not_attached) {
+	.attach = false,
+};
+
+FIXTURE_SETUP(URETPROBE)
+{
+	const size_t attr_sz = sizeof(struct perf_event_attr);
+	struct perf_event_attr attr;
+	ssize_t offset;
+	int type, bit;
+
+#ifndef __NR_uretprobe
+	SKIP(return, "__NR_uretprobe syscall not defined");
+#endif
+
+	if (!variant->attach)
+		return;
+
+	memset(&attr, 0, attr_sz);
+
+	type = determine_uprobe_perf_type();
+	ASSERT_GE(type, 0);
+	bit = determine_uprobe_retprobe_bit();
+	ASSERT_GE(bit, 0);
+	offset = get_uprobe_offset(probed);
+	ASSERT_GE(offset, 0);
+
+	attr.config |= 1 << bit;
+	attr.size = attr_sz;
+	attr.type = type;
+	attr.config1 = ptr_to_u64("/proc/self/exe");
+	attr.config2 = offset;
+
+	self->fd = syscall(__NR_perf_event_open, &attr,
+			   getpid() /* pid */, -1 /* cpu */, -1 /* group_fd */,
+			   PERF_FLAG_FD_CLOEXEC);
+}
+
+FIXTURE_TEARDOWN(URETPROBE)
+{
+	/* we could call close(self->fd), but we'd need extra filter for
+	 * that and since we are calling _exit right away..
+	 */
+}
+
+static int run_probed_with_filter(struct sock_fprog *prog)
+{
+	if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) ||
+	    seccomp(SECCOMP_SET_MODE_FILTER, 0, prog)) {
+		return -1;
+	}
+
+	probed();
+	return 0;
+}
+
+TEST_F(URETPROBE, uretprobe_default_allow)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+
+	ASSERT_EQ(0, run_probed_with_filter(&prog));
+}
+
+TEST_F(URETPROBE, uretprobe_default_block)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+
+	ASSERT_EQ(0, run_probed_with_filter(&prog));
+}
+
+TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+#ifdef __NR_uretprobe
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 0, 1),
+#endif
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+
+	ASSERT_EQ(0, run_probed_with_filter(&prog));
+}
+
+TEST_F(URETPROBE, uretprobe_default_block_with_uretprobe_syscall)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+			offsetof(struct seccomp_data, nr)),
+#ifdef __NR_uretprobe
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 2, 0),
+#endif
+		BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+		BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+
+	ASSERT_EQ(0, run_probed_with_filter(&prog));
+}
+
 /*
  * TODO:
  * - expand NNP testing
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index d3dd65b05b5f..9044ac054167 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -94,5 +94,37 @@
             "$TC qdisc del dev $DUMMY ingress",
             "$IP addr del 10.10.10.10/24 dev $DUMMY"
         ]
-    }
+    },
+    {
+	"id": "a4b9",
+	"name": "Test class qlen notification",
+	"category": [
+	    "qdisc"
+	],
+	"plugins": {
+	    "requires": "nsPlugin"
+	},
+	"setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: drr",
+            "$TC filter add dev $DUMMY parent 1: basic classid 1:1",
+            "$TC class add dev $DUMMY parent 1: classid 1:1 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem",
+            "$TC qdisc add dev $DUMMY parent 2: handle 3: drr",
+            "$TC filter add dev $DUMMY parent 3: basic action drop",
+            "$TC class add dev $DUMMY parent 3: classid 3:1 drr",
+            "$TC class del dev $DUMMY classid 1:1",
+            "$TC class add dev $DUMMY parent 1: classid 1:1 drr"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC qdisc ls dev $DUMMY",
+        "matchPattern": "drr 1: root",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle 1: drr",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY"
+        ]
+   }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
index ae3d286a32b2..6f20d033670d 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json
@@ -313,6 +313,29 @@
         "matchPattern": "qdisc bfifo 1: root",
         "matchCount": "0",
         "teardown": [
+	]
+    },
+    {
+        "id": "d774",
+        "name": "Check pfifo_head_drop qdisc enqueue behaviour when limit == 0",
+        "category": [
+            "qdisc",
+            "pfifo_head_drop"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: pfifo_head_drop limit 0",
+            "$IP link set dev $DUMMY up || true"
+        ],
+        "cmdUnderTest": "ping -c2 -W0.01 -I $DUMMY 10.10.10.1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "dropped 2",
+        "matchCount": "1",
+        "teardown": [
         ]
     }
 ]
diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 0ea4f6813930..4d4a76532dc9 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -237,7 +237,7 @@ static uint64_t set_metadata(uint64_t src, unsigned long lam)
  * both pointers should point to the same address.
  *
  * @return:
- * 0: value on the pointer with metadate and value on original are same
+ * 0: value on the pointer with metadata and value on original are same
  * 1: not same.
  */
 static int handle_lam_test(void *src, unsigned int lam)
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index 9bcf1736bf18..04ab45e27fb8 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -18,6 +18,12 @@ static bool fail_prealloc;
 #define vma_iter_prealloc(vmi, vma)					\
 	(fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL))
 
+#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536
+
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
 /*
  * Directly import the VMA implementation here. Our vma_internal.h wrapper
  * provides userland-equivalent functionality for everything vma.c uses.
@@ -47,6 +53,11 @@ struct task_struct *get_current(void)
 	return &__current;
 }
 
+unsigned long rlimit(unsigned int limit)
+{
+	return (unsigned long)-1;
+}
+
 /* Helper function to simply allocate a VMA. */
 static struct vm_area_struct *alloc_vma(struct mm_struct *mm,
 					unsigned long start,
@@ -1563,6 +1574,57 @@ static bool test_expand_only_mode(void)
 	return true;
 }
 
+static bool test_mmap_region_basic(void)
+{
+	struct mm_struct mm = {};
+	unsigned long addr;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, &mm, 0);
+
+	current->mm = &mm;
+
+	/* Map at 0x300000, length 0x3000. */
+	addr = __mmap_region(NULL, 0x300000, 0x3000,
+			     VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+			     0x300, NULL);
+	ASSERT_EQ(addr, 0x300000);
+
+	/* Map at 0x250000, length 0x3000. */
+	addr = __mmap_region(NULL, 0x250000, 0x3000,
+			     VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+			     0x250, NULL);
+	ASSERT_EQ(addr, 0x250000);
+
+	/* Map at 0x303000, merging to 0x300000 of length 0x6000. */
+	addr = __mmap_region(NULL, 0x303000, 0x3000,
+			     VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+			     0x303, NULL);
+	ASSERT_EQ(addr, 0x303000);
+
+	/* Map at 0x24d000, merging to 0x250000 of length 0x6000. */
+	addr = __mmap_region(NULL, 0x24d000, 0x3000,
+			     VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+			     0x24d, NULL);
+	ASSERT_EQ(addr, 0x24d000);
+
+	ASSERT_EQ(mm.map_count, 2);
+
+	for_each_vma(vmi, vma) {
+		if (vma->vm_start == 0x300000) {
+			ASSERT_EQ(vma->vm_end, 0x306000);
+			ASSERT_EQ(vma->vm_pgoff, 0x300);
+		} else if (vma->vm_start == 0x24d000) {
+			ASSERT_EQ(vma->vm_end, 0x253000);
+			ASSERT_EQ(vma->vm_pgoff, 0x24d);
+		} else {
+			ASSERT_FALSE(true);
+		}
+	}
+
+	cleanup_mm(&mm, &vmi);
+	return true;
+}
+
 int main(void)
 {
 	int num_tests = 0, num_fail = 0;
@@ -1596,6 +1658,8 @@ int main(void)
 	TEST(copy_vma);
 	TEST(expand_only_mode);
 
+	TEST(mmap_region_basic);
+
 #undef TEST
 
 	printf("%d tests run, %d passed, %d failed.\n",
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 1d9fc97b8e80..1eae23039854 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -27,11 +27,23 @@
 #include <linux/rbtree.h>
 #include <linux/rwsem.h>
 
+extern unsigned long stack_guard_gap;
+#ifdef CONFIG_MMU
+extern unsigned long mmap_min_addr;
+extern unsigned long dac_mmap_min_addr;
+#else
+#define mmap_min_addr		0UL
+#define dac_mmap_min_addr	0UL
+#endif
+
 #define VM_WARN_ON(_expr) (WARN_ON(_expr))
 #define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr))
+#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr))
 #define VM_BUG_ON(_expr) (BUG_ON(_expr))
 #define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr))
 
+#define MMF_HAS_MDWE	28
+
 #define VM_NONE		0x00000000
 #define VM_READ		0x00000001
 #define VM_WRITE	0x00000002
@@ -39,6 +51,7 @@
 #define VM_SHARED	0x00000008
 #define VM_MAYREAD	0x00000010
 #define VM_MAYWRITE	0x00000020
+#define VM_MAYEXEC	0x00000040
 #define VM_GROWSDOWN	0x00000100
 #define VM_PFNMAP	0x00000400
 #define VM_LOCKED	0x00002000
@@ -51,6 +64,8 @@
 #define VM_STACK	VM_GROWSDOWN
 #define VM_SHADOW_STACK	VM_NONE
 #define VM_SOFTDIRTY	0
+#define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
+#define VM_GROWSUP	VM_NONE
 
 #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
@@ -58,6 +73,20 @@
 /* This mask represents all the VMA flag bits used by mlock */
 #define VM_LOCKED_MASK	(VM_LOCKED | VM_LOCKONFAULT)
 
+#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
+
+#define VM_DATA_FLAGS_TSK_EXEC	(VM_READ | VM_WRITE | TASK_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#define VM_DATA_DEFAULT_FLAGS	VM_DATA_FLAGS_TSK_EXEC
+
+#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
+
+#define RLIMIT_STACK		3	/* max stack size */
+#define RLIMIT_MEMLOCK		8	/* max locked-in-memory address space */
+
+#define CAP_IPC_LOCK         14
+
 #ifdef CONFIG_64BIT
 /* VM is sealed, in vm_flags */
 #define VM_SEALED	_BITUL(63)
@@ -122,10 +151,22 @@ enum {
 	TASK_COMM_LEN = 16,
 };
 
+/*
+ * Flags for bug emulation.
+ *
+ * These occupy the top three bytes.
+ */
+enum {
+	READ_IMPLIES_EXEC =	0x0400000,
+};
+
 struct task_struct {
 	char comm[TASK_COMM_LEN];
 	pid_t pid;
 	struct mm_struct *mm;
+
+	/* Used for emulating ABI behavior of previous Linux versions: */
+	unsigned int			personality;
 };
 
 struct task_struct *get_current(void);
@@ -186,6 +227,10 @@ struct mm_struct {
 	unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
 	unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
 	unsigned long stack_vm;	   /* VM_STACK */
+
+	unsigned long def_flags;
+
+	unsigned long flags; /* Must use atomic bitops to access */
 };
 
 struct vma_lock {
@@ -373,6 +418,17 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+struct vm_unmapped_area_info {
+#define VM_UNMAPPED_AREA_TOPDOWN 1
+	unsigned long flags;
+	unsigned long length;
+	unsigned long low_limit;
+	unsigned long high_limit;
+	unsigned long align_mask;
+	unsigned long align_offset;
+	unsigned long start_gap;
+};
+
 static inline void vma_iter_invalidate(struct vma_iterator *vmi)
 {
 	mas_pause(&vmi->mas);
@@ -432,6 +488,8 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached)
 
 extern const struct vm_operations_struct vma_dummy_vm_ops;
 
+extern unsigned long rlimit(unsigned int limit);
+
 static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 {
 	memset(vma, 0, sizeof(*vma));
@@ -853,6 +911,11 @@ static inline void mmap_write_unlock(struct mm_struct *)
 {
 }
 
+static inline int mmap_write_lock_killable(struct mm_struct *)
+{
+	return 0;
+}
+
 static inline bool can_modify_mm(struct mm_struct *mm,
 				 unsigned long start,
 				 unsigned long end)
@@ -938,7 +1001,7 @@ static inline bool is_file_hugepages(struct file *)
 
 static inline int security_vm_enough_memory_mm(struct mm_struct *, long)
 {
-	return true;
+	return 0;
 }
 
 static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long)
@@ -1033,4 +1096,159 @@ static inline int mmap_file(struct file *, struct vm_area_struct *)
 	return 0;
 }
 
+static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_GROWSDOWN)
+		return stack_guard_gap;
+
+	/* See reasoning around the VM_SHADOW_STACK definition */
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return PAGE_SIZE;
+
+	return 0;
+}
+
+static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+{
+	unsigned long gap = stack_guard_start_gap(vma);
+	unsigned long vm_start = vma->vm_start;
+
+	vm_start -= gap;
+	if (vm_start > vma->vm_start)
+		vm_start = 0;
+	return vm_start;
+}
+
+static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+{
+	unsigned long vm_end = vma->vm_end;
+
+	if (vma->vm_flags & VM_GROWSUP) {
+		vm_end += stack_guard_gap;
+		if (vm_end < vma->vm_end)
+			vm_end = -PAGE_SIZE;
+	}
+	return vm_end;
+}
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					unsigned long addr, unsigned long len)
+{
+	return 0;
+}
+
+static inline bool vma_is_accessible(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & VM_ACCESS_FLAGS;
+}
+
+static inline bool capable(int cap)
+{
+	return true;
+}
+
+static inline bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+			unsigned long bytes)
+{
+	unsigned long locked_pages, limit_pages;
+
+	if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
+		return true;
+
+	locked_pages = bytes >> PAGE_SHIFT;
+	locked_pages += mm->locked_vm;
+
+	limit_pages = rlimit(RLIMIT_MEMLOCK);
+	limit_pages >>= PAGE_SHIFT;
+
+	return locked_pages <= limit_pages;
+}
+
+static inline int __anon_vma_prepare(struct vm_area_struct *vma)
+{
+	struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma));
+
+	if (!anon_vma)
+		return -ENOMEM;
+
+	anon_vma->root = anon_vma;
+	vma->anon_vma = anon_vma;
+
+	return 0;
+}
+
+static inline int anon_vma_prepare(struct vm_area_struct *vma)
+{
+	if (likely(vma->anon_vma))
+		return 0;
+
+	return __anon_vma_prepare(vma);
+}
+
+static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
+					      struct list_head *uf)
+{
+}
+
+/*
+ * Denies creating a writable executable mapping or gaining executable permissions.
+ *
+ * This denies the following:
+ *
+ *     a)      mmap(PROT_WRITE | PROT_EXEC)
+ *
+ *     b)      mmap(PROT_WRITE)
+ *             mprotect(PROT_EXEC)
+ *
+ *     c)      mmap(PROT_WRITE)
+ *             mprotect(PROT_READ)
+ *             mprotect(PROT_EXEC)
+ *
+ * But allows the following:
+ *
+ *     d)      mmap(PROT_READ | PROT_EXEC)
+ *             mmap(PROT_READ | PROT_EXEC | PROT_BTI)
+ *
+ * This is only applicable if the user has set the Memory-Deny-Write-Execute
+ * (MDWE) protection mask for the current process.
+ *
+ * @old specifies the VMA flags the VMA originally possessed, and @new the ones
+ * we propose to set.
+ *
+ * Return: false if proposed change is OK, true if not ok and should be denied.
+ */
+static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
+{
+	/* If MDWE is disabled, we have nothing to deny. */
+	if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
+		return false;
+
+	/* If the new VMA is not executable, we have nothing to deny. */
+	if (!(new & VM_EXEC))
+		return false;
+
+	/* Under MDWE we do not accept newly writably executable VMAs... */
+	if (new & VM_WRITE)
+		return true;
+
+	/* ...nor previously non-executable VMAs becoming executable. */
+	if (!(old & VM_EXEC))
+		return true;
+
+	return false;
+}
+
+static inline int mapping_map_writable(struct address_space *mapping)
+{
+	int c = atomic_read(&mapping->i_mmap_writable);
+
+	/* Derived from the raw_atomic_inc_unless_negative() implementation. */
+	do {
+		if (c < 0)
+			return -EPERM;
+	} while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1));
+
+	return 0;
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 7058dc614c25..de25892f865f 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -96,41 +96,57 @@ void vsock_wait_remote_close(int fd)
 	close(epollfd);
 }
 
-/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */
-int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type)
+/* Create socket <type>, bind to <cid, port> and return the file descriptor. */
+int vsock_bind(unsigned int cid, unsigned int port, int type)
 {
-	struct sockaddr_vm sa_client = {
-		.svm_family = AF_VSOCK,
-		.svm_cid = VMADDR_CID_ANY,
-		.svm_port = bind_port,
-	};
-	struct sockaddr_vm sa_server = {
+	struct sockaddr_vm sa = {
 		.svm_family = AF_VSOCK,
 		.svm_cid = cid,
 		.svm_port = port,
 	};
+	int fd;
 
-	int client_fd, ret;
-
-	client_fd = socket(AF_VSOCK, type, 0);
-	if (client_fd < 0) {
+	fd = socket(AF_VSOCK, type, 0);
+	if (fd < 0) {
 		perror("socket");
 		exit(EXIT_FAILURE);
 	}
 
-	if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) {
+	if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) {
 		perror("bind");
 		exit(EXIT_FAILURE);
 	}
 
+	return fd;
+}
+
+int vsock_connect_fd(int fd, unsigned int cid, unsigned int port)
+{
+	struct sockaddr_vm sa = {
+		.svm_family = AF_VSOCK,
+		.svm_cid = cid,
+		.svm_port = port,
+	};
+	int ret;
+
 	timeout_begin(TIMEOUT);
 	do {
-		ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server));
+		ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa));
 		timeout_check("connect");
 	} while (ret < 0 && errno == EINTR);
 	timeout_end();
 
-	if (ret < 0) {
+	return ret;
+}
+
+/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */
+int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type)
+{
+	int client_fd;
+
+	client_fd = vsock_bind(VMADDR_CID_ANY, bind_port, type);
+
+	if (vsock_connect_fd(client_fd, cid, port)) {
 		perror("connect");
 		exit(EXIT_FAILURE);
 	}
@@ -141,17 +157,6 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po
 /* Connect to <cid, port> and return the file descriptor. */
 int vsock_connect(unsigned int cid, unsigned int port, int type)
 {
-	union {
-		struct sockaddr sa;
-		struct sockaddr_vm svm;
-	} addr = {
-		.svm = {
-			.svm_family = AF_VSOCK,
-			.svm_port = port,
-			.svm_cid = cid,
-		},
-	};
-	int ret;
 	int fd;
 
 	control_expectln("LISTENING");
@@ -162,20 +167,14 @@ int vsock_connect(unsigned int cid, unsigned int port, int type)
 		exit(EXIT_FAILURE);
 	}
 
-	timeout_begin(TIMEOUT);
-	do {
-		ret = connect(fd, &addr.sa, sizeof(addr.svm));
-		timeout_check("connect");
-	} while (ret < 0 && errno == EINTR);
-	timeout_end();
-
-	if (ret < 0) {
+	if (vsock_connect_fd(fd, cid, port)) {
 		int old_errno = errno;
 
 		close(fd);
 		fd = -1;
 		errno = old_errno;
 	}
+
 	return fd;
 }
 
@@ -192,28 +191,9 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port)
 /* Listen on <cid, port> and return the file descriptor. */
 static int vsock_listen(unsigned int cid, unsigned int port, int type)
 {
-	union {
-		struct sockaddr sa;
-		struct sockaddr_vm svm;
-	} addr = {
-		.svm = {
-			.svm_family = AF_VSOCK,
-			.svm_port = port,
-			.svm_cid = cid,
-		},
-	};
 	int fd;
 
-	fd = socket(AF_VSOCK, type, 0);
-	if (fd < 0) {
-		perror("socket");
-		exit(EXIT_FAILURE);
-	}
-
-	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
-		perror("bind");
-		exit(EXIT_FAILURE);
-	}
+	fd = vsock_bind(cid, port, type);
 
 	if (listen(fd, 1) < 0) {
 		perror("listen");
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index e62f46b2b92a..d1f765ce3eee 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -39,10 +39,12 @@ struct test_case {
 void init_signals(void);
 unsigned int parse_cid(const char *str);
 unsigned int parse_port(const char *str);
+int vsock_connect_fd(int fd, unsigned int cid, unsigned int port);
 int vsock_connect(unsigned int cid, unsigned int port, int type);
 int vsock_accept(unsigned int cid, unsigned int port,
 		 struct sockaddr_vm *clientaddrp, int type);
 int vsock_stream_connect(unsigned int cid, unsigned int port);
+int vsock_bind(unsigned int cid, unsigned int port, int type);
 int vsock_bind_connect(unsigned int cid, unsigned int port,
 		       unsigned int bind_port, int type);
 int vsock_seqpacket_connect(unsigned int cid, unsigned int port);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 1eebbc0d5f61..dfff8b288265 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -113,24 +113,9 @@ static void test_stream_bind_only_client(const struct test_opts *opts)
 
 static void test_stream_bind_only_server(const struct test_opts *opts)
 {
-	union {
-		struct sockaddr sa;
-		struct sockaddr_vm svm;
-	} addr = {
-		.svm = {
-			.svm_family = AF_VSOCK,
-			.svm_port = opts->peer_port,
-			.svm_cid = VMADDR_CID_ANY,
-		},
-	};
 	int fd;
 
-	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
-
-	if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
-		perror("bind");
-		exit(EXIT_FAILURE);
-	}
+	fd = vsock_bind(VMADDR_CID_ANY, opts->peer_port, SOCK_STREAM);
 
 	/* Notify the client that the server is ready */
 	control_writeln("BIND");
@@ -1708,6 +1693,101 @@ static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts)
 	close(fd);
 }
 
+#define MAX_PORT_RETRIES	24	/* net/vmw_vsock/af_vsock.c */
+
+/* Test attempts to trigger a transport release for an unbound socket. This can
+ * lead to a reference count mishandling.
+ */
+static void test_stream_transport_uaf_client(const struct test_opts *opts)
+{
+	int sockets[MAX_PORT_RETRIES];
+	struct sockaddr_vm addr;
+	int fd, i, alen;
+
+	fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM);
+
+	alen = sizeof(addr);
+	if (getsockname(fd, (struct sockaddr *)&addr, &alen)) {
+		perror("getsockname");
+		exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < MAX_PORT_RETRIES; ++i)
+		sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port,
+					SOCK_STREAM);
+
+	close(fd);
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) {
+		perror("Unexpected connect() #1 success");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Vulnerable system may crash now. */
+	if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) {
+		perror("Unexpected connect() #2 success");
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+	while (i--)
+		close(sockets[i]);
+
+	control_writeln("DONE");
+}
+
+static void test_stream_transport_uaf_server(const struct test_opts *opts)
+{
+	control_expectln("DONE");
+}
+
+static void test_stream_connect_retry_client(const struct test_opts *opts)
+{
+	int fd;
+
+	fd = socket(AF_VSOCK, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		exit(EXIT_FAILURE);
+	}
+
+	if (!vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) {
+		fprintf(stderr, "Unexpected connect() #1 success\n");
+		exit(EXIT_FAILURE);
+	}
+
+	control_writeln("LISTEN");
+	control_expectln("LISTENING");
+
+	if (vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) {
+		perror("connect() #2");
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}
+
+static void test_stream_connect_retry_server(const struct test_opts *opts)
+{
+	int fd;
+
+	control_expectln("LISTEN");
+
+	fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL);
+	if (fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	vsock_wait_remote_close(fd);
+	close(fd);
+}
+
 static struct test_case test_cases[] = {
 	{
 		.name = "SOCK_STREAM connection reset",
@@ -1853,6 +1933,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_msgzcopy_leak_zcskb_client,
 		.run_server = test_stream_msgzcopy_leak_zcskb_server,
 	},
+	{
+		.name = "SOCK_STREAM transport release use-after-free",
+		.run_client = test_stream_transport_uaf_client,
+		.run_server = test_stream_transport_uaf_server,
+	},
+	{
+		.name = "SOCK_STREAM retry failed connect()",
+		.run_client = test_stream_connect_retry_client,
+		.run_server = test_stream_connect_retry_server,
+	},
 	{},
 };
 
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index a6a7dee16622..8b5101457c70 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -85,4 +85,6 @@ clean: doc_clean fixdep-clean
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)rm -f rtla rtla-static fixdep FEATURE-DUMP rtla-*
 	$(Q)rm -rf feature
-.PHONY: FORCE clean
+check: $(RTLA)
+	RTLA=$(RTLA) prove -o -f tests/
+.PHONY: FORCE clean check
diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c
index 245e9344932b..85f398b89597 100644
--- a/tools/tracing/rtla/src/osnoise.c
+++ b/tools/tracing/rtla/src/osnoise.c
@@ -867,7 +867,7 @@ int osnoise_set_workload(struct osnoise_context *context, bool onoff)
 
 	retval = osnoise_options_set_option("OSNOISE_WORKLOAD", onoff);
 	if (retval < 0)
-		return -1;
+		return -2;
 
 	context->opt_workload = onoff;
 
@@ -1079,6 +1079,42 @@ out_err:
 	return NULL;
 }
 
+bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record)
+{
+	/*
+	 * The tool instance is always present, it is the one used to collect
+	 * data.
+	 */
+	if (!tracefs_trace_is_on(tool->trace.inst))
+		return true;
+
+	/*
+	 * The trace record instance is only enabled when -t is set. IOW, when the system
+	 * is tracing.
+	 */
+	return record && !tracefs_trace_is_on(record->trace.inst);
+}
+
+/*
+ * osnoise_report_missed_events - report number of events dropped by trace
+ * buffer
+ */
+void
+osnoise_report_missed_events(struct osnoise_tool *tool)
+{
+	unsigned long long total_events;
+
+	if (tool->trace.missed_events == UINT64_MAX)
+		printf("unknown number of events missed, results might not be accurate\n");
+	else if (tool->trace.missed_events > 0) {
+		total_events = tool->trace.processed_events + tool->trace.missed_events;
+
+		printf("%lld (%.2f%%) events missed, results might not be accurate\n",
+		       tool->trace.missed_events,
+		       (double) tool->trace.missed_events / total_events * 100.0);
+	}
+}
+
 static void osnoise_usage(int err)
 {
 	int i;
diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h
index 555f4f4903cc..91835a7d8c2b 100644
--- a/tools/tracing/rtla/src/osnoise.h
+++ b/tools/tracing/rtla/src/osnoise.h
@@ -104,6 +104,8 @@ struct osnoise_tool {
 void osnoise_destroy_tool(struct osnoise_tool *top);
 struct osnoise_tool *osnoise_init_tool(char *tool_name);
 struct osnoise_tool *osnoise_init_trace_tool(char *tracer);
+void osnoise_report_missed_events(struct osnoise_tool *tool);
+bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record);
 
 int osnoise_hist_main(int argc, char *argv[]);
 int osnoise_top_main(int argc, char **argv);
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
index 214e2c93fde0..b4930b835b0a 100644
--- a/tools/tracing/rtla/src/osnoise_hist.c
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -440,6 +440,7 @@ osnoise_print_stats(struct osnoise_hist_params *params, struct osnoise_tool *too
 	trace_seq_reset(trace->seq);
 
 	osnoise_print_summary(params, trace, data);
+	osnoise_report_missed_events(tool);
 }
 
 /*
@@ -970,7 +971,7 @@ int osnoise_hist_main(int argc, char *argv[])
 			goto out_hist;
 		}
 
-		if (trace_is_off(&tool->trace, &record->trace))
+		if (osnoise_trace_is_off(tool, record))
 			break;
 	}
 
@@ -980,7 +981,7 @@ int osnoise_hist_main(int argc, char *argv[])
 
 	return_value = 0;
 
-	if (trace_is_off(&tool->trace, &record->trace)) {
+	if (osnoise_trace_is_off(tool, record)) {
 		printf("rtla osnoise hit stop tracing\n");
 		if (params->trace_output) {
 			printf("  Saving trace to %s\n", params->trace_output);
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
index 45647495ce3b..4772677ac762 100644
--- a/tools/tracing/rtla/src/osnoise_top.c
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -280,6 +280,7 @@ osnoise_print_stats(struct osnoise_top_params *params, struct osnoise_tool *top)
 
 	trace_seq_do_printf(trace->seq);
 	trace_seq_reset(trace->seq);
+	osnoise_report_missed_events(top);
 }
 
 /*
@@ -801,7 +802,7 @@ int osnoise_top_main(int argc, char **argv)
 		if (!params->quiet)
 			osnoise_print_stats(params, tool);
 
-		if (trace_is_off(&tool->trace, &record->trace))
+		if (osnoise_trace_is_off(tool, record))
 			break;
 
 	}
@@ -810,7 +811,7 @@ int osnoise_top_main(int argc, char **argv)
 
 	return_value = 0;
 
-	if (trace_is_off(&tool->trace, &record->trace)) {
+	if (osnoise_trace_is_off(tool, record)) {
 		printf("osnoise hit stop tracing\n");
 		if (params->trace_output) {
 			printf("  Saving trace to %s\n", params->trace_output);
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 4403cc4eba30..6d7d0a2d45b4 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -656,6 +656,7 @@ timerlat_print_stats(struct timerlat_hist_params *params, struct osnoise_tool *t
 
 	timerlat_print_summary(params, trace, data);
 	timerlat_print_stats_all(params, trace, data);
+	osnoise_report_missed_events(tool);
 }
 
 /*
@@ -1100,12 +1101,15 @@ timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_hist_param
 		}
 	}
 
-	if (params->user_hist) {
-		retval = osnoise_set_workload(tool->context, 0);
-		if (retval) {
-			err_msg("Failed to set OSNOISE_WORKLOAD option\n");
-			goto out_err;
-		}
+	/*
+	* Set workload according to type of thread if the kernel supports it.
+	* On kernels without support, user threads will have already failed
+	* on missing timerlat_fd, and kernel threads do not need it.
+	*/
+	retval = osnoise_set_workload(tool->context, params->kernel_workload);
+	if (retval < -1) {
+		err_msg("Failed to set OSNOISE_WORKLOAD option\n");
+		goto out_err;
 	}
 
 	return 0;
@@ -1146,9 +1150,20 @@ out_err:
 }
 
 static int stop_tracing;
+static struct trace_instance *hist_inst = NULL;
 static void stop_hist(int sig)
 {
+	if (stop_tracing) {
+		/*
+		 * Stop requested twice in a row; abort event processing and
+		 * exit immediately
+		 */
+		tracefs_iterate_stop(hist_inst->inst);
+		return;
+	}
 	stop_tracing = 1;
+	if (hist_inst)
+		trace_instance_stop(hist_inst);
 }
 
 /*
@@ -1195,6 +1210,12 @@ int timerlat_hist_main(int argc, char *argv[])
 	}
 
 	trace = &tool->trace;
+	/*
+	 * Save trace instance into global variable so that SIGINT can stop
+	 * the timerlat tracer.
+	 * Otherwise, rtla could loop indefinitely when overloaded.
+	 */
+	hist_inst = trace;
 
 	retval = enable_timerlat(trace);
 	if (retval) {
@@ -1342,7 +1363,7 @@ int timerlat_hist_main(int argc, char *argv[])
 			goto out_hist;
 		}
 
-		if (trace_is_off(&tool->trace, &record->trace))
+		if (osnoise_trace_is_off(tool, record))
 			break;
 
 		/* is there still any user-threads ? */
@@ -1363,7 +1384,7 @@ int timerlat_hist_main(int argc, char *argv[])
 
 	return_value = 0;
 
-	if (trace_is_off(&tool->trace, &record->trace)) {
+	if (osnoise_trace_is_off(tool, record) && !stop_tracing) {
 		printf("rtla timerlat hit stop tracing\n");
 
 		if (!params->no_aa)
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 059b468981e4..05a9403b01d2 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -435,6 +435,7 @@ timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *to
 
 	trace_seq_do_printf(trace->seq);
 	trace_seq_reset(trace->seq);
+	osnoise_report_missed_events(top);
 }
 
 /*
@@ -851,12 +852,15 @@ timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_top_params *
 		}
 	}
 
-	if (params->user_top) {
-		retval = osnoise_set_workload(top->context, 0);
-		if (retval) {
-			err_msg("Failed to set OSNOISE_WORKLOAD option\n");
-			goto out_err;
-		}
+	/*
+	* Set workload according to type of thread if the kernel supports it.
+	* On kernels without support, user threads will have already failed
+	* on missing timerlat_fd, and kernel threads do not need it.
+	*/
+	retval = osnoise_set_workload(top->context, params->kernel_workload);
+	if (retval < -1) {
+		err_msg("Failed to set OSNOISE_WORKLOAD option\n");
+		goto out_err;
 	}
 
 	if (isatty(STDOUT_FILENO) && !params->quiet)
@@ -900,9 +904,20 @@ out_err:
 }
 
 static int stop_tracing;
+static struct trace_instance *top_inst = NULL;
 static void stop_top(int sig)
 {
+	if (stop_tracing) {
+		/*
+		 * Stop requested twice in a row; abort event processing and
+		 * exit immediately
+		 */
+		tracefs_iterate_stop(top_inst->inst);
+		return;
+	}
 	stop_tracing = 1;
+	if (top_inst)
+		trace_instance_stop(top_inst);
 }
 
 /*
@@ -950,6 +965,13 @@ int timerlat_top_main(int argc, char *argv[])
 	}
 
 	trace = &top->trace;
+	/*
+	* Save trace instance into global variable so that SIGINT can stop
+	* the timerlat tracer.
+	* Otherwise, rtla could loop indefinitely when overloaded.
+	*/
+	top_inst = trace;
+
 
 	retval = enable_timerlat(trace);
 	if (retval) {
@@ -1093,7 +1115,7 @@ int timerlat_top_main(int argc, char *argv[])
 	while (!stop_tracing) {
 		sleep(params->sleep_time);
 
-		if (params->aa_only && !trace_is_off(&top->trace, &record->trace))
+		if (params->aa_only && !osnoise_trace_is_off(top, record))
 			continue;
 
 		retval = tracefs_iterate_raw_events(trace->tep,
@@ -1110,7 +1132,7 @@ int timerlat_top_main(int argc, char *argv[])
 		if (!params->quiet)
 			timerlat_print_stats(params, top);
 
-		if (trace_is_off(&top->trace, &record->trace))
+		if (osnoise_trace_is_off(top, record))
 			break;
 
 		/* is there still any user-threads ? */
@@ -1131,7 +1153,7 @@ int timerlat_top_main(int argc, char *argv[])
 
 	return_value = 0;
 
-	if (trace_is_off(&top->trace, &record->trace)) {
+	if (osnoise_trace_is_off(top, record) && !stop_tracing) {
 		printf("rtla timerlat hit stop tracing\n");
 
 		if (!params->no_aa)
diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c
index 170a706248ab..728f5029d533 100644
--- a/tools/tracing/rtla/src/trace.c
+++ b/tools/tracing/rtla/src/trace.c
@@ -118,6 +118,8 @@ collect_registered_events(struct tep_event *event, struct tep_record *record,
 	struct trace_instance *trace = context;
 	struct trace_seq *s = trace->seq;
 
+	trace->processed_events++;
+
 	if (!event->handler)
 		return 0;
 
@@ -127,6 +129,31 @@ collect_registered_events(struct tep_event *event, struct tep_record *record,
 }
 
 /*
+ * collect_missed_events - record number of missed events
+ *
+ * If rtla cannot keep up with events generated by tracer, events are going
+ * to fall out of the ring buffer.
+ * Collect how many events were missed so it can be reported to the user.
+ */
+static int
+collect_missed_events(struct tep_event *event, struct tep_record *record,
+		      int cpu, void *context)
+{
+	struct trace_instance *trace = context;
+
+	if (trace->missed_events == UINT64_MAX)
+		return 0;
+
+	if (record->missed_events > 0)
+		trace->missed_events += record->missed_events;
+	else
+		/* Events missed but no data on how many */
+		trace->missed_events = UINT64_MAX;
+
+	return 0;
+}
+
+/*
  * trace_instance_destroy - destroy and free a rtla trace instance
  */
 void trace_instance_destroy(struct trace_instance *trace)
@@ -181,6 +208,17 @@ int trace_instance_init(struct trace_instance *trace, char *tool_name)
 	 */
 	tracefs_trace_off(trace->inst);
 
+	/*
+	 * Collect the number of events missed due to tracefs buffer
+	 * overflow.
+	 */
+	trace->missed_events = 0;
+	tracefs_follow_missed_events(trace->inst,
+				     collect_missed_events,
+				     trace);
+
+	trace->processed_events = 0;
+
 	return 0;
 
 out_err:
@@ -197,6 +235,14 @@ int trace_instance_start(struct trace_instance *trace)
 }
 
 /*
+ * trace_instance_stop - stop tracing a given rtla instance
+ */
+int trace_instance_stop(struct trace_instance *trace)
+{
+	return tracefs_trace_off(trace->inst);
+}
+
+/*
  * trace_events_free - free a list of trace events
  */
 static void trace_events_free(struct trace_events *events)
@@ -522,25 +568,6 @@ void trace_events_destroy(struct trace_instance *instance,
 	trace_events_free(events);
 }
 
-int trace_is_off(struct trace_instance *tool, struct trace_instance *trace)
-{
-	/*
-	 * The tool instance is always present, it is the one used to collect
-	 * data.
-	 */
-	if (!tracefs_trace_is_on(tool->inst))
-		return 1;
-
-	/*
-	 * The trace instance is only enabled when -t is set. IOW, when the system
-	 * is tracing.
-	 */
-	if (trace && !tracefs_trace_is_on(trace->inst))
-		return 1;
-
-	return 0;
-}
-
 /*
  * trace_set_buffer_size - set the per-cpu tracing buffer size.
  */
diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h
index c7c92dc9a18a..3cd40dd3f06c 100644
--- a/tools/tracing/rtla/src/trace.h
+++ b/tools/tracing/rtla/src/trace.h
@@ -17,10 +17,13 @@ struct trace_instance {
 	struct tracefs_instance		*inst;
 	struct tep_handle		*tep;
 	struct trace_seq		*seq;
+	unsigned long long		missed_events;
+	unsigned long long		processed_events;
 };
 
 int trace_instance_init(struct trace_instance *trace, char *tool_name);
 int trace_instance_start(struct trace_instance *trace);
+int trace_instance_stop(struct trace_instance *trace);
 void trace_instance_destroy(struct trace_instance *trace);
 
 struct trace_seq *get_trace_seq(void);
@@ -47,5 +50,4 @@ int trace_events_enable(struct trace_instance *instance,
 
 int trace_event_add_filter(struct trace_events *event, char *filter);
 int trace_event_add_trigger(struct trace_events *event, char *trigger);
-int trace_is_off(struct trace_instance *tool, struct trace_instance *trace);
 int trace_set_buffer_size(struct trace_instance *trace, int size);
diff --git a/tools/tracing/rtla/tests/engine.sh b/tools/tracing/rtla/tests/engine.sh
new file mode 100644
index 000000000000..64d0446dc28e
--- /dev/null
+++ b/tools/tracing/rtla/tests/engine.sh
@@ -0,0 +1,48 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+test_begin() {
+	# Count tests to allow the test harness to double-check if all were
+	# included correctly.
+	ctr=0
+	[ -z "$RTLA" ] && RTLA="./rtla"
+	[ -n "$TEST_COUNT" ] && echo "1..$TEST_COUNT"
+}
+
+check() {
+	# Simple check: run rtla with given arguments and test exit code.
+	# If TEST_COUNT is set, run the test. Otherwise, just count.
+	ctr=$(($ctr + 1))
+	if [ -n "$TEST_COUNT" ]
+	then
+		# Run rtla; in case of failure, include its output as comment
+		# in the test results.
+		result=$(stdbuf -oL $TIMEOUT "$RTLA" $2 2>&1); exitcode=$?
+		if [ $exitcode -eq 0 ]
+		then
+			echo "ok $ctr - $1"
+		else
+			echo "not ok $ctr - $1"
+			# Add rtla output and exit code as comments in case of failure
+			echo "$result" | col -b | while read line; do echo "# $line"; done
+			printf "#\n# exit code %s\n" $exitcode
+		fi
+	fi
+}
+
+set_timeout() {
+	TIMEOUT="timeout -v -k 15s $1"
+}
+
+unset_timeout() {
+	unset TIMEOUT
+}
+
+test_end() {
+	# If running without TEST_COUNT, tests are not actually run, just
+	# counted. In that case, re-run the test with the correct count.
+	[ -z "$TEST_COUNT" ] && TEST_COUNT=$ctr exec bash $0 || true
+}
+
+# Avoid any environmental discrepancies
+export LC_ALL=C
+unset_timeout
diff --git a/tools/tracing/rtla/tests/hwnoise.t b/tools/tracing/rtla/tests/hwnoise.t
new file mode 100644
index 000000000000..bbed17580537
--- /dev/null
+++ b/tools/tracing/rtla/tests/hwnoise.t
@@ -0,0 +1,21 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source tests/engine.sh
+test_begin
+
+set_timeout 2m
+
+check "verify help page" \
+	"hwnoise --help"
+check "detect noise higher than one microsecond" \
+	"hwnoise -c 0 -T 1 -d 5s -q"
+check "set the automatic trace mode" \
+	"hwnoise -a 5 -d 30s"
+check "set scheduling param to the osnoise tracer threads" \
+	"hwnoise -P F:1 -c 0 -r 900000 -d 1M -q"
+check "stop the trace if a single sample is higher than 1 us" \
+	"hwnoise -s 1 -T 1 -t -d 30s"
+check "enable a trace event trigger" \
+	"hwnoise -t -e osnoise:irq_noise trigger=\"hist:key=desc,duration:sort=desc,duration:vals=hitcount\" -d 1m"
+
+test_end
diff --git a/tools/tracing/rtla/tests/osnoise.t b/tools/tracing/rtla/tests/osnoise.t
new file mode 100644
index 000000000000..86596e547893
--- /dev/null
+++ b/tools/tracing/rtla/tests/osnoise.t
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source tests/engine.sh
+test_begin
+
+set_timeout 2m
+
+check "verify help page" \
+	"osnoise --help"
+check "verify the --priority/-P param" \
+	"osnoise top -P F:1 -c 0 -r 900000 -d 1M -q"
+check "verify the --stop/-s param" \
+	"osnoise top -s 30 -T 1 -t"
+check "verify the  --trace param" \
+	"osnoise hist -s 30 -T 1 -t"
+check "verify the --entries/-E param" \
+	"osnoise hist -P F:1 -c 0 -r 900000 -d 1M -b 10 -E 25"
+
+test_end
diff --git a/tools/tracing/rtla/tests/timerlat.t b/tools/tracing/rtla/tests/timerlat.t
new file mode 100644
index 000000000000..e86f40e5749e
--- /dev/null
+++ b/tools/tracing/rtla/tests/timerlat.t
@@ -0,0 +1,27 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source tests/engine.sh
+test_begin
+
+set_timeout 2m
+
+check "verify help page" \
+	"timerlat --help"
+check "verify -s/--stack" \
+	"timerlat top -s 3 -T 10 -t"
+check "verify -P/--priority" \
+	"timerlat top -P F:1 -c 0 -d 1M -q"
+check "test in nanoseconds" \
+	"timerlat top -i 2 -c 0 -n -d 30s"
+check "set the automatic trace mode" \
+	"timerlat top -a 5 --dump-tasks"
+check "print the auto-analysis if hits the stop tracing condition" \
+	"timerlat top --aa-only 5"
+check "disable auto-analysis" \
+	"timerlat top -s 3 -T 10 -t --no-aa"
+check "verify -c/--cpus" \
+	"timerlat hist -c 0 -d 30s"
+check "hist test in nanoseconds" \
+	"timerlat hist -i 2 -c 0 -n -d 30s"
+
+test_end
diff --git a/tools/verification/dot2/automata.py b/tools/verification/dot2/automata.py
index bdeb98baa8b0..d9a3fe2b74bf 100644
--- a/tools/verification/dot2/automata.py
+++ b/tools/verification/dot2/automata.py
@@ -19,13 +19,14 @@ class Automata:
 
     invalid_state_str = "INVALID_STATE"
 
-    def __init__(self, file_path):
+    def __init__(self, file_path, model_name=None):
         self.__dot_path = file_path
-        self.name = self.__get_model_name()
+        self.name = model_name or self.__get_model_name()
         self.__dot_lines = self.__open_dot()
         self.states, self.initial_state, self.final_states = self.__get_state_variables()
         self.events = self.__get_event_variables()
         self.function = self.__create_matrix()
+        self.events_start, self.events_start_run = self.__store_init_events()
 
     def __get_model_name(self):
         basename = ntpath.basename(self.__dot_path)
@@ -172,3 +173,34 @@ class Automata:
             cursor += 1
 
         return matrix
+
+    def __store_init_events(self):
+        events_start = [False] * len(self.events)
+        events_start_run = [False] * len(self.events)
+        for i, _ in enumerate(self.events):
+            curr_event_will_init = 0
+            curr_event_from_init = False
+            curr_event_used = 0
+            for j, _ in enumerate(self.states):
+                if self.function[j][i] != self.invalid_state_str:
+                    curr_event_used += 1
+                if self.function[j][i] == self.initial_state:
+                    curr_event_will_init += 1
+            if self.function[0][i] != self.invalid_state_str:
+                curr_event_from_init = True
+            # this event always leads to init
+            if curr_event_will_init and curr_event_used == curr_event_will_init:
+                events_start[i] = True
+            # this event is only called from init
+            if curr_event_from_init and curr_event_used == 1:
+                events_start_run[i] = True
+        return events_start, events_start_run
+
+    def is_start_event(self, event):
+        return self.events_start[self.events.index(event)]
+
+    def is_start_run_event(self, event):
+        # prefer handle_start_event if there
+        if any(self.events_start):
+            return False
+        return self.events_start_run[self.events.index(event)]
diff --git a/tools/verification/dot2/dot2c.py b/tools/verification/dot2/dot2c.py
index 87d8a1e1470c..fa2816ac7b61 100644
--- a/tools/verification/dot2/dot2c.py
+++ b/tools/verification/dot2/dot2c.py
@@ -22,8 +22,8 @@ class Dot2c(Automata):
     struct_automaton_def = "automaton"
     var_automaton_def = "aut"
 
-    def __init__(self, file_path):
-        super().__init__(file_path)
+    def __init__(self, file_path, model_name=None):
+        super().__init__(file_path, model_name)
         self.line_length = 100
 
     def __buff_to_string(self, buff):
diff --git a/tools/verification/dot2/dot2k b/tools/verification/dot2/dot2k
index d4d7e52d549e..559ba191a1f6 100644
--- a/tools/verification/dot2/dot2k
+++ b/tools/verification/dot2/dot2k
@@ -21,25 +21,24 @@ if __name__ == '__main__':
     parser.add_argument('-t', "--monitor_type", dest="monitor_type", required=True)
     parser.add_argument('-n', "--model_name", dest="model_name", required=False)
     parser.add_argument("-D", "--description", dest="description", required=False)
+    parser.add_argument("-a", "--auto_patch", dest="auto_patch",
+                        action="store_true", required=False,
+                        help="Patch the kernel in place")
     params = parser.parse_args()
 
     print("Opening and parsing the dot file %s" % params.dot_file)
     try:
-        monitor=dot2k(params.dot_file, params.monitor_type)
+        monitor=dot2k(params.dot_file, params.monitor_type, vars(params))
     except Exception as e:
         print('Error: '+ str(e))
         print("Sorry : :-(")
         sys.exit(1)
 
-    # easier than using argparse action.
-    if params.model_name != None:
-        print(params.model_name)
-
     print("Writing the monitor into the directory %s" % monitor.name)
     monitor.print_files()
     print("Almost done, checklist")
     print("  - Edit the %s/%s.c to add the instrumentation" % (monitor.name, monitor.name))
-    print("  - Edit include/trace/events/rv.h to add the tracepoint entry")
-    print("  - Move it to the kernel's monitor directory")
-    print("  - Edit kernel/trace/rv/Makefile")
-    print("  - Edit kernel/trace/rv/Kconfig")
+    print(monitor.fill_tracepoint_tooltip())
+    print(monitor.fill_makefile_tooltip())
+    print(monitor.fill_kconfig_tooltip())
+    print(monitor.fill_monitor_tooltip())
diff --git a/tools/verification/dot2/dot2k.py b/tools/verification/dot2/dot2k.py
index 016550fccf1f..7547eb290b7d 100644
--- a/tools/verification/dot2/dot2k.py
+++ b/tools/verification/dot2/dot2k.py
@@ -14,50 +14,83 @@ import os
 
 class dot2k(Dot2c):
     monitor_types = { "global" : 1, "per_cpu" : 2, "per_task" : 3 }
-    monitor_templates_dir = "dot2k/rv_templates/"
+    monitor_templates_dir = "dot2/dot2k_templates/"
+    rv_dir = "kernel/trace/rv"
     monitor_type = "per_cpu"
 
-    def __init__(self, file_path, MonitorType):
-        super().__init__(file_path)
+    def __init__(self, file_path, MonitorType, extra_params={}):
+        super().__init__(file_path, extra_params.get("model_name"))
 
         self.monitor_type = self.monitor_types.get(MonitorType)
-        if self.monitor_type == None:
-            raise Exception("Unknown monitor type: %s" % MonitorType)
+        if self.monitor_type is None:
+            raise ValueError("Unknown monitor type: %s" % MonitorType)
 
         self.monitor_type = MonitorType
         self.__fill_rv_templates_dir()
-        self.main_c = self.__open_file(self.monitor_templates_dir + "main_" + MonitorType + ".c")
+        self.main_c = self.__read_file(self.monitor_templates_dir + "main.c")
+        self.trace_h = self.__read_file(self.monitor_templates_dir + "trace.h")
+        self.kconfig = self.__read_file(self.monitor_templates_dir + "Kconfig")
         self.enum_suffix = "_%s" % self.name
+        self.description = extra_params.get("description", self.name) or "auto-generated"
+        self.auto_patch = extra_params.get("auto_patch")
+        if self.auto_patch:
+            self.__fill_rv_kernel_dir()
 
     def __fill_rv_templates_dir(self):
 
-        if os.path.exists(self.monitor_templates_dir) == True:
+        if os.path.exists(self.monitor_templates_dir):
             return
 
         if platform.system() != "Linux":
-            raise Exception("I can only run on Linux.")
+            raise OSError("I can only run on Linux.")
 
         kernel_path = "/lib/modules/%s/build/tools/verification/dot2/dot2k_templates/" % (platform.release())
 
-        if os.path.exists(kernel_path) == True:
+        if os.path.exists(kernel_path):
             self.monitor_templates_dir = kernel_path
             return
 
-        if os.path.exists("/usr/share/dot2/dot2k_templates/") == True:
+        if os.path.exists("/usr/share/dot2/dot2k_templates/"):
             self.monitor_templates_dir = "/usr/share/dot2/dot2k_templates/"
             return
 
-        raise Exception("Could not find the template directory, do you have the kernel source installed?")
+        raise FileNotFoundError("Could not find the template directory, do you have the kernel source installed?")
 
+    def __fill_rv_kernel_dir(self):
 
-    def __open_file(self, path):
+        # first try if we are running in the kernel tree root
+        if os.path.exists(self.rv_dir):
+            return
+
+        # offset if we are running inside the kernel tree from verification/dot2
+        kernel_path = os.path.join("../..", self.rv_dir)
+
+        if os.path.exists(kernel_path):
+            self.rv_dir = kernel_path
+            return
+
+        if platform.system() != "Linux":
+            raise OSError("I can only run on Linux.")
+
+        kernel_path = os.path.join("/lib/modules/%s/build" % platform.release(), self.rv_dir)
+
+        # if the current kernel is from a distro this may not be a full kernel tree
+        # verify that one of the files we are going to modify is available
+        if os.path.exists(os.path.join(kernel_path, "rv_trace.h")):
+            self.rv_dir = kernel_path
+            return
+
+        raise FileNotFoundError("Could not find the rv directory, do you have the kernel source installed?")
+
+    def __read_file(self, path):
         try:
-            fd = open(path)
+            fd = open(path, 'r')
         except OSError:
             raise Exception("Cannot open the file: %s" % path)
 
         content = fd.read()
 
+        fd.close()
         return content
 
     def __buff_to_string(self, buff):
@@ -69,16 +102,26 @@ class dot2k(Dot2c):
         # cut off the last \n
         return string[:-1]
 
+    def fill_monitor_type(self):
+        return self.monitor_type.upper()
+
     def fill_tracepoint_handlers_skel(self):
         buff = []
         for event in self.events:
             buff.append("static void handle_%s(void *data, /* XXX: fill header */)" % event)
             buff.append("{")
+            handle = "handle_event"
+            if self.is_start_event(event):
+                buff.append("\t/* XXX: validate that this event always leads to the initial state */")
+                handle = "handle_start_event"
+            elif self.is_start_run_event(event):
+                buff.append("\t/* XXX: validate that this event is only valid in the initial state */")
+                handle = "handle_start_run_event"
             if self.monitor_type == "per_task":
                 buff.append("\tstruct task_struct *p = /* XXX: how do I get p? */;");
-                buff.append("\tda_handle_event_%s(p, %s%s);" % (self.name, event, self.enum_suffix));
+                buff.append("\tda_%s_%s(p, %s%s);" % (handle, self.name, event, self.enum_suffix));
             else:
-                buff.append("\tda_handle_event_%s(%s%s);" % (self.name, event, self.enum_suffix));
+                buff.append("\tda_%s_%s(%s%s);" % (handle, self.name, event, self.enum_suffix));
             buff.append("}")
             buff.append("")
         return self.__buff_to_string(buff)
@@ -97,18 +140,21 @@ class dot2k(Dot2c):
 
     def fill_main_c(self):
         main_c = self.main_c
+        monitor_type = self.fill_monitor_type()
         min_type = self.get_minimun_type()
-        nr_events = self.events.__len__()
+        nr_events = len(self.events)
         tracepoint_handlers = self.fill_tracepoint_handlers_skel()
         tracepoint_attach = self.fill_tracepoint_attach_probe()
         tracepoint_detach = self.fill_tracepoint_detach_helper()
 
-        main_c = main_c.replace("MIN_TYPE", min_type)
-        main_c = main_c.replace("MODEL_NAME", self.name)
-        main_c = main_c.replace("NR_EVENTS", str(nr_events))
-        main_c = main_c.replace("TRACEPOINT_HANDLERS_SKEL", tracepoint_handlers)
-        main_c = main_c.replace("TRACEPOINT_ATTACH", tracepoint_attach)
-        main_c = main_c.replace("TRACEPOINT_DETACH", tracepoint_detach)
+        main_c = main_c.replace("%%MONITOR_TYPE%%", monitor_type)
+        main_c = main_c.replace("%%MIN_TYPE%%", min_type)
+        main_c = main_c.replace("%%MODEL_NAME%%", self.name)
+        main_c = main_c.replace("%%NR_EVENTS%%", str(nr_events))
+        main_c = main_c.replace("%%TRACEPOINT_HANDLERS_SKEL%%", tracepoint_handlers)
+        main_c = main_c.replace("%%TRACEPOINT_ATTACH%%", tracepoint_attach)
+        main_c = main_c.replace("%%TRACEPOINT_DETACH%%", tracepoint_detach)
+        main_c = main_c.replace("%%DESCRIPTION%%", self.description)
 
         return main_c
 
@@ -137,31 +183,142 @@ class dot2k(Dot2c):
 
         return self.__buff_to_string(buff)
 
+    def fill_monitor_class_type(self):
+        if self.monitor_type == "per_task":
+            return "DA_MON_EVENTS_ID"
+        return "DA_MON_EVENTS_IMPLICIT"
+
+    def fill_monitor_class(self):
+        if self.monitor_type == "per_task":
+            return "da_monitor_id"
+        return "da_monitor"
+
+    def fill_tracepoint_args_skel(self, tp_type):
+        buff = []
+        tp_args_event = [
+                ("char *", "state"),
+                ("char *", "event"),
+                ("char *", "next_state"),
+                ("bool ",  "final_state"),
+                ]
+        tp_args_error = [
+                ("char *", "state"),
+                ("char *", "event"),
+                ]
+        tp_args_id = ("int ", "id")
+        tp_args = tp_args_event if tp_type == "event" else tp_args_error
+        if self.monitor_type == "per_task":
+            tp_args.insert(0, tp_args_id)
+        tp_proto_c = ", ".join([a+b for a,b in tp_args])
+        tp_args_c = ", ".join([b for a,b in tp_args])
+        buff.append("	     TP_PROTO(%s)," % tp_proto_c)
+        buff.append("	     TP_ARGS(%s)" % tp_args_c)
+        return self.__buff_to_string(buff)
+
+    def fill_trace_h(self):
+        trace_h = self.trace_h
+        monitor_class = self.fill_monitor_class()
+        monitor_class_type = self.fill_monitor_class_type()
+        tracepoint_args_skel_event = self.fill_tracepoint_args_skel("event")
+        tracepoint_args_skel_error = self.fill_tracepoint_args_skel("error")
+        trace_h = trace_h.replace("%%MODEL_NAME%%", self.name)
+        trace_h = trace_h.replace("%%MODEL_NAME_UP%%", self.name.upper())
+        trace_h = trace_h.replace("%%MONITOR_CLASS%%", monitor_class)
+        trace_h = trace_h.replace("%%MONITOR_CLASS_TYPE%%", monitor_class_type)
+        trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_EVENT%%", tracepoint_args_skel_event)
+        trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_ERROR%%", tracepoint_args_skel_error)
+        return trace_h
+
+    def fill_kconfig(self):
+        kconfig = self.kconfig
+        monitor_class_type = self.fill_monitor_class_type()
+        kconfig = kconfig.replace("%%MODEL_NAME%%", self.name)
+        kconfig = kconfig.replace("%%MODEL_NAME_UP%%", self.name.upper())
+        kconfig = kconfig.replace("%%MONITOR_CLASS_TYPE%%", monitor_class_type)
+        kconfig = kconfig.replace("%%DESCRIPTION%%", self.description)
+        return kconfig
+
+    def __patch_file(self, file, marker, line):
+        file_to_patch = os.path.join(self.rv_dir, file)
+        content = self.__read_file(file_to_patch)
+        content = content.replace(marker, line + "\n" + marker)
+        self.__write_file(file_to_patch, content)
+
+    def fill_tracepoint_tooltip(self):
+        monitor_class_type = self.fill_monitor_class_type()
+        if self.auto_patch:
+            self.__patch_file("rv_trace.h",
+                            "// Add new monitors based on CONFIG_%s here" % monitor_class_type,
+                            "#include <monitors/%s/%s_trace.h>" % (self.name, self.name))
+            return "  - Patching %s/rv_trace.h, double check the result" % self.rv_dir
+
+        return """  - Edit %s/rv_trace.h:
+Add this line where other tracepoints are included and %s is defined:
+#include <monitors/%s/%s_trace.h>
+""" % (self.rv_dir, monitor_class_type, self.name, self.name)
+
+    def fill_kconfig_tooltip(self):
+        if self.auto_patch:
+            self.__patch_file("Kconfig",
+                            "# Add new monitors here",
+                            "source \"kernel/trace/rv/monitors/%s/Kconfig\"" % (self.name))
+            return "  - Patching %s/Kconfig, double check the result" % self.rv_dir
+
+        return """  - Edit %s/Kconfig:
+Add this line where other monitors are included:
+source \"kernel/trace/rv/monitors/%s/Kconfig\"
+""" % (self.rv_dir, self.name)
+
+    def fill_makefile_tooltip(self):
+        name = self.name
+        name_up = name.upper()
+        if self.auto_patch:
+            self.__patch_file("Makefile",
+                            "# Add new monitors here",
+                            "obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o" % (name_up, name, name))
+            return "  - Patching %s/Makefile, double check the result" % self.rv_dir
+
+        return """  - Edit %s/Makefile:
+Add this line where other monitors are included:
+obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o
+""" % (self.rv_dir, name_up, name, name)
+
+    def fill_monitor_tooltip(self):
+        if self.auto_patch:
+            return "  - Monitor created in %s/monitors/%s" % (self.rv_dir, self. name)
+        return "  - Move %s/ to the kernel's monitor directory (%s/monitors)" % (self.name, self.rv_dir)
+
     def __create_directory(self):
+        path = self.name
+        if self.auto_patch:
+            path = os.path.join(self.rv_dir, "monitors", path)
         try:
-            os.mkdir(self.name)
+            os.mkdir(path)
         except FileExistsError:
             return
         except:
             print("Fail creating the output dir: %s" % self.name)
 
-    def __create_file(self, file_name, content):
-        path = "%s/%s" % (self.name, file_name)
+    def __write_file(self, file_name, content):
         try:
-            file = open(path, 'w')
-        except FileExistsError:
-            return
+            file = open(file_name, 'w')
         except:
-            print("Fail creating file: %s" % path)
+            print("Fail writing to file: %s" % file_name)
 
         file.write(content)
 
         file.close()
 
+    def __create_file(self, file_name, content):
+        path = "%s/%s" % (self.name, file_name)
+        if self.auto_patch:
+            path = os.path.join(self.rv_dir, "monitors", path)
+        self.__write_file(path, content)
+
     def __get_main_name(self):
         path = "%s/%s" % (self.name, "main.c")
-        if os.path.exists(path) == False:
-           return "main.c"
+        if not os.path.exists(path):
+            return "main.c"
         return "__main.c"
 
     def print_files(self):
@@ -175,3 +332,10 @@ class dot2k(Dot2c):
 
         path = "%s.h" % self.name
         self.__create_file(path, model_h)
+
+        trace_h = self.fill_trace_h()
+        path = "%s_trace.h" % self.name
+        self.__create_file(path, trace_h)
+
+        kconfig = self.fill_kconfig()
+        self.__create_file("Kconfig", kconfig)
diff --git a/tools/verification/dot2/dot2k_templates/Kconfig b/tools/verification/dot2/dot2k_templates/Kconfig
new file mode 100644
index 000000000000..90cdc1e9379e
--- /dev/null
+++ b/tools/verification/dot2/dot2k_templates/Kconfig
@@ -0,0 +1,6 @@
+config RV_MON_%%MODEL_NAME_UP%%
+	depends on RV
+	select %%MONITOR_CLASS_TYPE%%
+	bool "%%MODEL_NAME%% monitor"
+	help
+	  %%DESCRIPTION%%
diff --git a/tools/verification/dot2/dot2k_templates/main.c b/tools/verification/dot2/dot2k_templates/main.c
new file mode 100644
index 000000000000..9605ca994416
--- /dev/null
+++ b/tools/verification/dot2/dot2k_templates/main.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+#include <rv/da_monitor.h>
+
+#define MODULE_NAME "%%MODEL_NAME%%"
+
+/*
+ * XXX: include required tracepoint headers, e.g.,
+ * #include <trace/events/sched.h>
+ */
+#include <rv_trace.h>
+
+/*
+ * This is the self-generated part of the monitor. Generally, there is no need
+ * to touch this section.
+ */
+#include "%%MODEL_NAME%%.h"
+
+/*
+ * Declare the deterministic automata monitor.
+ *
+ * The rv monitor reference is needed for the monitor declaration.
+ */
+static struct rv_monitor rv_%%MODEL_NAME%%;
+DECLARE_DA_MON_%%MONITOR_TYPE%%(%%MODEL_NAME%%, %%MIN_TYPE%%);
+
+/*
+ * This is the instrumentation part of the monitor.
+ *
+ * This is the section where manual work is required. Here the kernel events
+ * are translated into model's event.
+ *
+ */
+%%TRACEPOINT_HANDLERS_SKEL%%
+static int enable_%%MODEL_NAME%%(void)
+{
+	int retval;
+
+	retval = da_monitor_init_%%MODEL_NAME%%();
+	if (retval)
+		return retval;
+
+%%TRACEPOINT_ATTACH%%
+
+	return 0;
+}
+
+static void disable_%%MODEL_NAME%%(void)
+{
+	rv_%%MODEL_NAME%%.enabled = 0;
+
+%%TRACEPOINT_DETACH%%
+
+	da_monitor_destroy_%%MODEL_NAME%%();
+}
+
+/*
+ * This is the monitor register section.
+ */
+static struct rv_monitor rv_%%MODEL_NAME%% = {
+	.name = "%%MODEL_NAME%%",
+	.description = "%%DESCRIPTION%%",
+	.enable = enable_%%MODEL_NAME%%,
+	.disable = disable_%%MODEL_NAME%%,
+	.reset = da_monitor_reset_all_%%MODEL_NAME%%,
+	.enabled = 0,
+};
+
+static int __init register_%%MODEL_NAME%%(void)
+{
+	rv_register_monitor(&rv_%%MODEL_NAME%%);
+	return 0;
+}
+
+static void __exit unregister_%%MODEL_NAME%%(void)
+{
+	rv_unregister_monitor(&rv_%%MODEL_NAME%%);
+}
+
+module_init(register_%%MODEL_NAME%%);
+module_exit(unregister_%%MODEL_NAME%%);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("dot2k: auto-generated");
+MODULE_DESCRIPTION("%%MODEL_NAME%%: %%DESCRIPTION%%");
diff --git a/tools/verification/dot2/dot2k_templates/main_global.c b/tools/verification/dot2/dot2k_templates/main_global.c
deleted file mode 100644
index a5658bfb9044..000000000000
--- a/tools/verification/dot2/dot2k_templates/main_global.c
+++ /dev/null
@@ -1,91 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/ftrace.h>
-#include <linux/tracepoint.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/rv.h>
-#include <rv/instrumentation.h>
-#include <rv/da_monitor.h>
-
-#define MODULE_NAME "MODEL_NAME"
-
-/*
- * XXX: include required tracepoint headers, e.g.,
- * #include <trace/events/sched.h>
- */
-#include <trace/events/rv.h>
-
-/*
- * This is the self-generated part of the monitor. Generally, there is no need
- * to touch this section.
- */
-#include "MODEL_NAME.h"
-
-/*
- * Declare the deterministic automata monitor.
- *
- * The rv monitor reference is needed for the monitor declaration.
- */
-static struct rv_monitor rv_MODEL_NAME;
-DECLARE_DA_MON_GLOBAL(MODEL_NAME, MIN_TYPE);
-
-/*
- * This is the instrumentation part of the monitor.
- *
- * This is the section where manual work is required. Here the kernel events
- * are translated into model's event.
- *
- */
-TRACEPOINT_HANDLERS_SKEL
-static int enable_MODEL_NAME(void)
-{
-	int retval;
-
-	retval = da_monitor_init_MODEL_NAME();
-	if (retval)
-		return retval;
-
-TRACEPOINT_ATTACH
-
-	return 0;
-}
-
-static void disable_MODEL_NAME(void)
-{
-	rv_MODEL_NAME.enabled = 0;
-
-TRACEPOINT_DETACH
-
-	da_monitor_destroy_MODEL_NAME();
-}
-
-/*
- * This is the monitor register section.
- */
-static struct rv_monitor rv_MODEL_NAME = {
-	.name = "MODEL_NAME",
-	.description = "auto-generated MODEL_NAME",
-	.enable = enable_MODEL_NAME,
-	.disable = disable_MODEL_NAME,
-	.reset = da_monitor_reset_all_MODEL_NAME,
-	.enabled = 0,
-};
-
-static int __init register_MODEL_NAME(void)
-{
-	rv_register_monitor(&rv_MODEL_NAME);
-	return 0;
-}
-
-static void __exit unregister_MODEL_NAME(void)
-{
-	rv_unregister_monitor(&rv_MODEL_NAME);
-}
-
-module_init(register_MODEL_NAME);
-module_exit(unregister_MODEL_NAME);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("dot2k: auto-generated");
-MODULE_DESCRIPTION("MODEL_NAME");
diff --git a/tools/verification/dot2/dot2k_templates/main_per_cpu.c b/tools/verification/dot2/dot2k_templates/main_per_cpu.c
deleted file mode 100644
index 03539a97633f..000000000000
--- a/tools/verification/dot2/dot2k_templates/main_per_cpu.c
+++ /dev/null
@@ -1,91 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/ftrace.h>
-#include <linux/tracepoint.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/rv.h>
-#include <rv/instrumentation.h>
-#include <rv/da_monitor.h>
-
-#define MODULE_NAME "MODEL_NAME"
-
-/*
- * XXX: include required tracepoint headers, e.g.,
- * #include <linux/trace/events/sched.h>
- */
-#include <trace/events/rv.h>
-
-/*
- * This is the self-generated part of the monitor. Generally, there is no need
- * to touch this section.
- */
-#include "MODEL_NAME.h"
-
-/*
- * Declare the deterministic automata monitor.
- *
- * The rv monitor reference is needed for the monitor declaration.
- */
-static struct rv_monitor rv_MODEL_NAME;
-DECLARE_DA_MON_PER_CPU(MODEL_NAME, MIN_TYPE);
-
-/*
- * This is the instrumentation part of the monitor.
- *
- * This is the section where manual work is required. Here the kernel events
- * are translated into model's event.
- *
- */
-TRACEPOINT_HANDLERS_SKEL
-static int enable_MODEL_NAME(void)
-{
-	int retval;
-
-	retval = da_monitor_init_MODEL_NAME();
-	if (retval)
-		return retval;
-
-TRACEPOINT_ATTACH
-
-	return 0;
-}
-
-static void disable_MODEL_NAME(void)
-{
-	rv_MODEL_NAME.enabled = 0;
-
-TRACEPOINT_DETACH
-
-	da_monitor_destroy_MODEL_NAME();
-}
-
-/*
- * This is the monitor register section.
- */
-static struct rv_monitor rv_MODEL_NAME = {
-	.name = "MODEL_NAME",
-	.description = "auto-generated MODEL_NAME",
-	.enable = enable_MODEL_NAME,
-	.disable = disable_MODEL_NAME,
-	.reset = da_monitor_reset_all_MODEL_NAME,
-	.enabled = 0,
-};
-
-static int __init register_MODEL_NAME(void)
-{
-	rv_register_monitor(&rv_MODEL_NAME);
-	return 0;
-}
-
-static void __exit unregister_MODEL_NAME(void)
-{
-	rv_unregister_monitor(&rv_MODEL_NAME);
-}
-
-module_init(register_MODEL_NAME);
-module_exit(unregister_MODEL_NAME);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("dot2k: auto-generated");
-MODULE_DESCRIPTION("MODEL_NAME");
diff --git a/tools/verification/dot2/dot2k_templates/main_per_task.c b/tools/verification/dot2/dot2k_templates/main_per_task.c
deleted file mode 100644
index ffd92af87a86..000000000000
--- a/tools/verification/dot2/dot2k_templates/main_per_task.c
+++ /dev/null
@@ -1,91 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/ftrace.h>
-#include <linux/tracepoint.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/rv.h>
-#include <rv/instrumentation.h>
-#include <rv/da_monitor.h>
-
-#define MODULE_NAME "MODEL_NAME"
-
-/*
- * XXX: include required tracepoint headers, e.g.,
- * #include <linux/trace/events/sched.h>
- */
-#include <trace/events/rv.h>
-
-/*
- * This is the self-generated part of the monitor. Generally, there is no need
- * to touch this section.
- */
-#include "MODEL_NAME.h"
-
-/*
- * Declare the deterministic automata monitor.
- *
- * The rv monitor reference is needed for the monitor declaration.
- */
-static struct rv_monitor rv_MODEL_NAME;
-DECLARE_DA_MON_PER_TASK(MODEL_NAME, MIN_TYPE);
-
-/*
- * This is the instrumentation part of the monitor.
- *
- * This is the section where manual work is required. Here the kernel events
- * are translated into model's event.
- *
- */
-TRACEPOINT_HANDLERS_SKEL
-static int enable_MODEL_NAME(void)
-{
-	int retval;
-
-	retval = da_monitor_init_MODEL_NAME();
-	if (retval)
-		return retval;
-
-TRACEPOINT_ATTACH
-
-	return 0;
-}
-
-static void disable_MODEL_NAME(void)
-{
-	rv_MODEL_NAME.enabled = 0;
-
-TRACEPOINT_DETACH
-
-	da_monitor_destroy_MODEL_NAME();
-}
-
-/*
- * This is the monitor register section.
- */
-static struct rv_monitor rv_MODEL_NAME = {
-	.name = "MODEL_NAME",
-	.description = "auto-generated MODEL_NAME",
-	.enable = enable_MODEL_NAME,
-	.disable = disable_MODEL_NAME,
-	.reset = da_monitor_reset_all_MODEL_NAME,
-	.enabled = 0,
-};
-
-static int __init register_MODEL_NAME(void)
-{
-	rv_register_monitor(&rv_MODEL_NAME);
-	return 0;
-}
-
-static void __exit unregister_MODEL_NAME(void)
-{
-	rv_unregister_monitor(&rv_MODEL_NAME);
-}
-
-module_init(register_MODEL_NAME);
-module_exit(unregister_MODEL_NAME);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("dot2k: auto-generated");
-MODULE_DESCRIPTION("MODEL_NAME");
diff --git a/tools/verification/dot2/dot2k_templates/trace.h b/tools/verification/dot2/dot2k_templates/trace.h
new file mode 100644
index 000000000000..87d3a1308926
--- /dev/null
+++ b/tools/verification/dot2/dot2k_templates/trace.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_%%MODEL_NAME_UP%%
+DEFINE_EVENT(event_%%MONITOR_CLASS%%, event_%%MODEL_NAME%%,
+%%TRACEPOINT_ARGS_SKEL_EVENT%%);
+
+DEFINE_EVENT(error_%%MONITOR_CLASS%%, error_%%MODEL_NAME%%,
+%%TRACEPOINT_ARGS_SKEL_ERROR%%);
+#endif /* CONFIG_RV_MON_%%MODEL_NAME_UP%% */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index faf10671eed2..ba0327e2d0d3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1071,15 +1071,6 @@ out_err:
 }
 
 /*
- * Called after the VM is otherwise initialized, but just before adding it to
- * the vm_list.
- */
-int __weak kvm_arch_post_init_vm(struct kvm *kvm)
-{
-	return 0;
-}
-
-/*
  * Called just after removing the VM from the vm_list, but before doing any
  * other destruction.
  */
@@ -1199,10 +1190,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_debugfs;
 
-	r = kvm_arch_post_init_vm(kvm);
-	if (r)
-		goto out_err;
-
 	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	mutex_unlock(&kvm_lock);
@@ -1212,8 +1199,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 
 	return kvm;
 
-out_err:
-	kvm_destroy_vm_debugfs(kvm);
 out_err_no_debugfs:
 	kvm_coalesced_mmio_free(kvm);
 out_no_coalesced_mmio:
@@ -1971,7 +1956,15 @@ static int kvm_set_memory_region(struct kvm *kvm,
 		return -EINVAL;
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		return -EINVAL;
-	if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
+
+	/*
+	 * The size of userspace-defined memory regions is restricted in order
+	 * to play nice with dirty bitmap operations, which are indexed with an
+	 * "unsigned int".  KVM's internal memory regions don't support dirty
+	 * logging, and so are exempt.
+	 */
+	if (id < KVM_USER_MEM_SLOTS &&
+	    (mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);