diff options
1073 files changed, 11422 insertions, 6953 deletions
diff --git a/Documentation/ABI/testing/sysfs-ata b/Documentation/ABI/testing/sysfs-ata index aa4296498859..9ab0ef1dd1c7 100644 --- a/Documentation/ABI/testing/sysfs-ata +++ b/Documentation/ABI/testing/sysfs-ata @@ -1,110 +1,139 @@ What: /sys/class/ata_... -Date: August 2008 -Contact: Gwendal Grignou<gwendal@google.com> Description: - -Provide a place in sysfs for storing the ATA topology of the system. This allows -retrieving various information about ATA objects. + Provide a place in sysfs for storing the ATA topology of the + system. This allows retrieving various information about ATA + objects. Files under /sys/class/ata_port ------------------------------- - For each port, a directory ataX is created where X is the ata_port_id of - the port. The device parent is the ata host device. +For each port, a directory ataX is created where X is the ata_port_id of the +port. The device parent is the ata host device. -idle_irq (read) - Number of IRQ received by the port while idle [some ata HBA only]. +What: /sys/class/ata_port/ataX/nr_pmp_links +What: /sys/class/ata_port/ataX/idle_irq +Date: May, 2010 +KernelVersion: v2.6.37 +Contact: Gwendal Grignou <gwendal@chromium.org> +Description: + nr_pmp_links: (RO) If a SATA Port Multiplier (PM) is + connected, the number of links behind it. -nr_pmp_links (read) + idle_irq: (RO) Number of IRQ received by the port while + idle [some ata HBA only]. - If a SATA Port Multiplier (PM) is connected, number of link behind it. + +What: /sys/class/ata_port/ataX/port_no +Date: May, 2013 +KernelVersion: v3.11 +Contact: Gwendal Grignou <gwendal@chromium.org> +Description: + (RO) Host local port number. While registering host controller, + port numbers are tracked based upon number of ports available on + the controller. This attribute is needed by udev for composing + persistent links in /dev/disk/by-path. Files under /sys/class/ata_link ------------------------------- - Behind each port, there is a ata_link. If there is a SATA PM in the - topology, 15 ata_link objects are created. - - If a link is behind a port, the directory name is linkX, where X is - ata_port_id of the port. - If a link is behind a PM, its name is linkX.Y where X is ata_port_id - of the parent port and Y the PM port. +Behind each port, there is a ata_link. If there is a SATA PM in the topology, 15 +ata_link objects are created. -hw_sata_spd_limit +If a link is behind a port, the directory name is linkX, where X is ata_port_id +of the port. If a link is behind a PM, its name is linkX.Y where X is +ata_port_id of the parent port and Y the PM port. - Maximum speed supported by the connected SATA device. -sata_spd_limit +What: /sys/class/ata_link/linkX[.Y]/hw_sata_spd_limit +What: /sys/class/ata_link/linkX[.Y]/sata_spd_limit +What: /sys/class/ata_link/linkX[.Y]/sata_spd +Date: May, 2010 +KernelVersion: v2.6.37 +Contact: Gwendal Grignou <gwendal@chromium.org> +Description: + hw_sata_spd_limit: (RO) Maximum speed supported by the + connected SATA device. - Maximum speed imposed by libata. + sata_spd_limit: (RO) Maximum speed imposed by libata. -sata_spd + sata_spd: (RO) Current speed of the link + eg. 1.5, 3 Gbps etc. - Current speed of the link [1.5, 3Gps,...]. Files under /sys/class/ata_device --------------------------------- - Behind each link, up to two ata device are created. - The name of the directory is devX[.Y].Z where: - - X is ata_port_id of the port where the device is connected, - - Y the port of the PM if any, and - - Z the device id: for PATA, there is usually 2 devices [0,1], - only 1 for SATA. - -class - Device class. Can be "ata" for disk, "atapi" for packet device, - "pmp" for PM, or "none" if no device was found behind the link. - -dma_mode +Behind each link, up to two ata devices are created. +The name of the directory is devX[.Y].Z where: +- X is ata_port_id of the port where the device is connected, +- Y the port of the PM if any, and +- Z the device id: for PATA, there is usually 2 devices [0,1], only 1 for SATA. + + +What: /sys/class/ata_device/devX[.Y].Z/spdn_cnt +What: /sys/class/ata_device/devX[.Y].Z/gscr +What: /sys/class/ata_device/devX[.Y].Z/ering +What: /sys/class/ata_device/devX[.Y].Z/id +What: /sys/class/ata_device/devX[.Y].Z/pio_mode +What: /sys/class/ata_device/devX[.Y].Z/xfer_mode +What: /sys/class/ata_device/devX[.Y].Z/dma_mode +What: /sys/class/ata_device/devX[.Y].Z/class +Date: May, 2010 +KernelVersion: v2.6.37 +Contact: Gwendal Grignou <gwendal@chromium.org> +Description: + spdn_cnt: (RO) Number of times libata decided to lower the + speed of link due to errors. - Transfer modes supported by the device when in DMA mode. - Mostly used by PATA device. + gscr: (RO) Cached result of the dump of PM GSCR + register. Valid registers are: -pio_mode + 0: SATA_PMP_GSCR_PROD_ID, + 1: SATA_PMP_GSCR_REV, + 2: SATA_PMP_GSCR_PORT_INFO, + 32: SATA_PMP_GSCR_ERROR, + 33: SATA_PMP_GSCR_ERROR_EN, + 64: SATA_PMP_GSCR_FEAT, + 96: SATA_PMP_GSCR_FEAT_EN, + 130: SATA_PMP_GSCR_SII_GPIO - Transfer modes supported by the device when in PIO mode. - Mostly used by PATA device. + Only valid if the device is a PM. -xfer_mode + ering: (RO) Formatted output of the error ring of the + device. - Current transfer mode. + id: (RO) Cached result of IDENTIFY command, as + described in ATA8 7.16 and 7.17. Only valid if + the device is not a PM. -id + pio_mode: (RO) Transfer modes supported by the device when + in PIO mode. Mostly used by PATA device. - Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17. - Only valid if the device is not a PM. + xfer_mode: (RO) Current transfer mode -gscr + dma_mode: (RO) Transfer modes supported by the device when + in DMA mode. Mostly used by PATA device. - Cached result of the dump of PM GSCR register. - Valid registers are: - 0: SATA_PMP_GSCR_PROD_ID, - 1: SATA_PMP_GSCR_REV, - 2: SATA_PMP_GSCR_PORT_INFO, - 32: SATA_PMP_GSCR_ERROR, - 33: SATA_PMP_GSCR_ERROR_EN, - 64: SATA_PMP_GSCR_FEAT, - 96: SATA_PMP_GSCR_FEAT_EN, - 130: SATA_PMP_GSCR_SII_GPIO - Only valid if the device is a PM. + class: (RO) Device class. Can be "ata" for disk, + "atapi" for packet device, "pmp" for PM, or + "none" if no device was found behind the link. -trim - Shows the DSM TRIM mode currently used by the device. Valid - values are: - unsupported: Drive does not support DSM TRIM - unqueued: Drive supports unqueued DSM TRIM only - queued: Drive supports queued DSM TRIM - forced_unqueued: Drive's queued DSM support is known to be - buggy and only unqueued TRIM commands - are sent +What: /sys/class/ata_device/devX[.Y].Z/trim +Date: May, 2015 +KernelVersion: v4.10 +Contact: Gwendal Grignou <gwendal@chromium.org> +Description: + (RO) Shows the DSM TRIM mode currently used by the device. Valid + values are: -spdn_cnt + unsupported: Drive does not support DSM TRIM - Number of time libata decided to lower the speed of link due to errors. + unqueued: Drive supports unqueued DSM TRIM only -ering + queued: Drive supports queued DSM TRIM - Formatted output of the error ring of the device. + forced_unqueued: Drive's queued DSM support is known to + be buggy and only unqueued TRIM commands + are sent diff --git a/Documentation/ABI/testing/sysfs-block-device b/Documentation/ABI/testing/sysfs-block-device new file mode 100644 index 000000000000..82ef6eab042d --- /dev/null +++ b/Documentation/ABI/testing/sysfs-block-device @@ -0,0 +1,58 @@ +What: /sys/block/*/device/sw_activity +Date: Jun, 2008 +KernelVersion: v2.6.27 +Contact: linux-ide@vger.kernel.org +Description: + (RW) Used by drivers which support software controlled activity + LEDs. + + It has the following valid values: + + 0 OFF - the LED is not activated on activity + 1 BLINK_ON - the LED blinks on every 10ms when activity is + detected. + 2 BLINK_OFF - the LED is on when idle, and blinks off + every 10ms when activity is detected. + + Note that the user must turn sw_activity OFF it they wish to + control the activity LED via the em_message file. + + +What: /sys/block/*/device/unload_heads +Date: Sep, 2008 +KernelVersion: v2.6.28 +Contact: linux-ide@vger.kernel.org +Description: + (RW) Hard disk shock protection + + Writing an integer value to this file will take the heads of the + respective drive off the platter and block all I/O operations + for the specified number of milliseconds. + + - If the device does not support the unload heads feature, + access is denied with -EOPNOTSUPP. + - The maximal value accepted for a timeout is 30000 + milliseconds. + - A previously set timeout can be cancelled and disk can resume + normal operation immediately by specifying a timeout of 0. + - Some hard drives only comply with an earlier version of the + ATA standard, but support the unload feature nonetheless. + There is no safe way Linux can detect these devices, so this + is not enabled by default. If it is known that your device + does support the unload feature, then you can tell the kernel + to enable it by writing -1. It can be disabled again by + writing -2. + - Values below -2 are rejected with -EINVAL + + For more information, see + Documentation/laptops/disk-shock-protection.txt + + +What: /sys/block/*/device/ncq_prio_enable +Date: Oct, 2016 +KernelVersion: v4.10 +Contact: linux-ide@vger.kernel.org +Description: + (RW) Write to the file to turn on or off the SATA ncq (native + command queueing) support. By default this feature is turned + off. diff --git a/Documentation/ABI/testing/sysfs-class-scsi_host b/Documentation/ABI/testing/sysfs-class-scsi_host index 0eb255e7db12..bafc59fd7b69 100644 --- a/Documentation/ABI/testing/sysfs-class-scsi_host +++ b/Documentation/ABI/testing/sysfs-class-scsi_host @@ -27,3 +27,92 @@ Description: This file contains the current status of the "SSD Smart Path" the direct i/o path to physical devices. This setting is controller wide, affecting all configured logical drives on the controller. This file is readable and writable. + +What: /sys/class/scsi_host/hostX/link_power_management_policy +Date: Oct, 2007 +KernelVersion: v2.6.24 +Contact: linux-ide@vger.kernel.org +Description: + (RW) This parameter allows the user to read and set the link + (interface) power management. + + There are four possible options: + + min_power: Tell the controller to try to make the link use the + least possible power when possible. This may sacrifice some + performance due to increased latency when coming out of lower + power states. + + max_performance: Generally, this means no power management. + Tell the controller to have performance be a priority over power + management. + + medium_power: Tell the controller to enter a lower power state + when possible, but do not enter the lowest power state, thus + improving latency over min_power setting. + + med_power_with_dipm: Identical to the existing medium_power + setting except that it enables dipm (device initiated power + management) on top, which makes it match the Windows IRST (Intel + Rapid Storage Technology) driver settings. This setting is also + close to min_power, except that: + a) It does not use host-initiated slumber mode, but it does + allow device-initiated slumber + b) It does not enable low power device sleep mode (DevSlp). + +What: /sys/class/scsi_host/hostX/em_message +What: /sys/class/scsi_host/hostX/em_message_type +Date: Jun, 2008 +KernelVersion: v2.6.27 +Contact: linux-ide@vger.kernel.org +Description: + em_message: (RW) Enclosure management support. For the LED + protocol, writes and reads correspond to the LED message format + as defined in the AHCI spec. + + The user must turn sw_activity (under /sys/block/*/device/) OFF + it they wish to control the activity LED via the em_message + file. + + em_message_type: (RO) Displays the current enclosure management + protocol that is being used by the driver (for eg. LED, SAF-TE, + SES-2, SGPIO etc). + +What: /sys/class/scsi_host/hostX/ahci_port_cmd +What: /sys/class/scsi_host/hostX/ahci_host_caps +What: /sys/class/scsi_host/hostX/ahci_host_cap2 +Date: Mar, 2010 +KernelVersion: v2.6.35 +Contact: linux-ide@vger.kernel.org +Description: + [to be documented] + +What: /sys/class/scsi_host/hostX/ahci_host_version +Date: Mar, 2010 +KernelVersion: v2.6.35 +Contact: linux-ide@vger.kernel.org +Description: + (RO) Display the version of the AHCI spec implemented by the + host. + +What: /sys/class/scsi_host/hostX/em_buffer +Date: Apr, 2010 +KernelVersion: v2.6.35 +Contact: linux-ide@vger.kernel.org +Description: + (RW) Allows access to AHCI EM (enclosure management) buffer + directly if the host supports EM. + + For eg. the AHCI driver supports SGPIO EM messages but the + SATA/AHCI specs do not define the SGPIO message format of the EM + buffer. Different hardware(HW) vendors may have different + definitions. With the em_buffer attribute, this issue can be + solved by allowing HW vendors to provide userland drivers and + tools for their SGPIO initiators. + +What: /sys/class/scsi_host/hostX/em_message_supported +Date: Oct, 2009 +KernelVersion: v2.6.39 +Contact: linux-ide@vger.kernel.org +Description: + (RO) Displays supported enclosure management message types. diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt index 611a75e4366e..badb26ac33dc 100644 --- a/Documentation/PCI/pci.txt +++ b/Documentation/PCI/pci.txt @@ -570,7 +570,9 @@ your driver if they're helpful, or just use plain hex constants. The device IDs are arbitrary hex numbers (vendor controlled) and normally used only in a single location, the pci_device_id table. -Please DO submit new vendor/device IDs to http://pciids.sourceforge.net/. +Please DO submit new vendor/device IDs to http://pci-ids.ucw.cz/. +There are mirrors of the pci.ids file at http://pciids.sourceforge.net/ +and https://github.com/pciutils/pciids. diff --git a/Documentation/accelerators/ocxl.rst b/Documentation/accelerators/ocxl.rst index 4f7af841d935..ddcc58d01cfb 100644 --- a/Documentation/accelerators/ocxl.rst +++ b/Documentation/accelerators/ocxl.rst @@ -152,6 +152,11 @@ OCXL_IOCTL_IRQ_SET_FD: Associate an event fd to an AFU interrupt so that the user process can be notified when the AFU sends an interrupt. +OCXL_IOCTL_GET_METADATA: + + Obtains configuration information from the card, such at the size of + MMIO areas, the AFU version, and the PASID for the current context. + mmap ---- diff --git a/Documentation/devicetree/bindings/misc/arm-charlcd.txt b/Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt index e28e2aac47f1..e28e2aac47f1 100644 --- a/Documentation/devicetree/bindings/misc/arm-charlcd.txt +++ b/Documentation/devicetree/bindings/auxdisplay/arm-charlcd.txt diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt b/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt index 6394ea9e3b9e..58b12e25bbb1 100644 --- a/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt +++ b/Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt @@ -16,6 +16,7 @@ Required properties: - ddc: phandle to the hdmi ddc node - phy: phandle to the hdmi phy node - samsung,syscon-phandle: phandle for system controller node for PMU. +- #sound-dai-cells: should be 0. Required properties for Exynos 4210, 4212, 5420 and 5433: - clocks: list of clock IDs from SoC clock driver. diff --git a/Documentation/devicetree/bindings/dma/mv-xor-v2.txt b/Documentation/devicetree/bindings/dma/mv-xor-v2.txt index 217a90eaabe7..9c38bbe7e6d7 100644 --- a/Documentation/devicetree/bindings/dma/mv-xor-v2.txt +++ b/Documentation/devicetree/bindings/dma/mv-xor-v2.txt @@ -11,7 +11,11 @@ Required properties: interrupts. Optional properties: -- clocks: Optional reference to the clock used by the XOR engine. +- clocks: Optional reference to the clocks used by the XOR engine. +- clock-names: mandatory if there is a second clock, in this case the + name must be "core" for the first clock and "reg" for the second + one + Example: diff --git a/Documentation/devicetree/bindings/eeprom/at24.txt b/Documentation/devicetree/bindings/eeprom/at24.txt index 1812c848e369..abfae1beca2b 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.txt +++ b/Documentation/devicetree/bindings/eeprom/at24.txt @@ -38,9 +38,9 @@ Required properties: "catalyst", "microchip", + "nxp", "ramtron", "renesas", - "nxp", "st", Some vendors use different model names for chips which are just diff --git a/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt b/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt index e9ebb8a20e0d..ba24ca7ba95e 100644 --- a/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt +++ b/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt @@ -3,11 +3,11 @@ Device-Tree bindings for sigma delta modulator Required properties: - compatible: should be "ads1201", "sd-modulator". "sd-modulator" can be use as a generic SD modulator if modulator not specified in compatible list. -- #io-channel-cells = <1>: See the IIO bindings section "IIO consumers". +- #io-channel-cells = <0>: See the IIO bindings section "IIO consumers". Example node: ads1202: adc@0 { compatible = "sd-modulator"; - #io-channel-cells = <1>; + #io-channel-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt index 33c9a10fdc91..20f121daa910 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt @@ -14,6 +14,7 @@ Required properties: - "renesas,irqc-r8a7794" (R-Car E2) - "renesas,intc-ex-r8a7795" (R-Car H3) - "renesas,intc-ex-r8a7796" (R-Car M3-W) + - "renesas,intc-ex-r8a77965" (R-Car M3-N) - "renesas,intc-ex-r8a77970" (R-Car V3M) - "renesas,intc-ex-r8a77995" (R-Car D3) - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt index 1d4d0f49c9d0..8c033d48e2ba 100644 --- a/Documentation/devicetree/bindings/net/dsa/marvell.txt +++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt @@ -50,14 +50,15 @@ Example: compatible = "marvell,mv88e6085"; reg = <0>; reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>; - }; - mdio { - #address-cells = <1>; - #size-cells = <0>; - switch1phy0: switch1phy0@0 { - reg = <0>; - interrupt-parent = <&switch0>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + switch1phy0: switch1phy0@0 { + reg = <0>; + interrupt-parent = <&switch0>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + }; }; }; }; @@ -74,23 +75,24 @@ Example: compatible = "marvell,mv88e6390"; reg = <0>; reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>; - }; - mdio { - #address-cells = <1>; - #size-cells = <0>; - switch1phy0: switch1phy0@0 { - reg = <0>; - interrupt-parent = <&switch0>; - interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + switch1phy0: switch1phy0@0 { + reg = <0>; + interrupt-parent = <&switch0>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; + }; }; - }; - mdio1 { - compatible = "marvell,mv88e6xxx-mdio-external"; - #address-cells = <1>; - #size-cells = <0>; - switch1phy9: switch1phy0@9 { - reg = <9>; + mdio1 { + compatible = "marvell,mv88e6xxx-mdio-external"; + #address-cells = <1>; + #size-cells = <0>; + switch1phy9: switch1phy0@9 { + reg = <9>; + }; }; }; }; diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index c902261893b9..b4dc455eb155 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -18,6 +18,7 @@ Required properties: - "renesas,etheravb-r8a7795" for the R8A7795 SoC. - "renesas,etheravb-r8a7796" for the R8A7796 SoC. - "renesas,etheravb-r8a77970" for the R8A77970 SoC. + - "renesas,etheravb-r8a77980" for the R8A77980 SoC. - "renesas,etheravb-r8a77995" for the R8A77995 SoC. - "renesas,etheravb-rcar-gen3" as a fallback for the above R-Car Gen3 devices. @@ -26,7 +27,11 @@ Required properties: SoC-specific version corresponding to the platform first followed by the generic version. -- reg: offset and length of (1) the register block and (2) the stream buffer. +- reg: Offset and length of (1) the register block and (2) the stream buffer. + The region for the register block is mandatory. + The region for the stream buffer is optional, as it is only present on + R-Car Gen2 and RZ/G1 SoCs, and on R-Car H3 (R8A7795), M3-W (R8A7796), + and M3-N (R8A77965). - interrupts: A list of interrupt-specifiers, one for each entry in interrupt-names. If interrupt-names is not present, an interrupt specifier diff --git a/Documentation/devicetree/bindings/power/wakeup-source.txt b/Documentation/devicetree/bindings/power/wakeup-source.txt index 3c81f78b5c27..5d254ab13ebf 100644 --- a/Documentation/devicetree/bindings/power/wakeup-source.txt +++ b/Documentation/devicetree/bindings/power/wakeup-source.txt @@ -60,7 +60,7 @@ Examples #size-cells = <0>; button@1 { - debounce_interval = <50>; + debounce-interval = <50>; wakeup-source; linux,code = <116>; label = "POWER"; diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.txt b/Documentation/devicetree/bindings/thermal/imx-thermal.txt index 28be51afdb6a..379eb763073e 100644 --- a/Documentation/devicetree/bindings/thermal/imx-thermal.txt +++ b/Documentation/devicetree/bindings/thermal/imx-thermal.txt @@ -22,7 +22,32 @@ Optional properties: - clocks : thermal sensor's clock source. Example: +ocotp: ocotp@21bc000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "fsl,imx6sx-ocotp", "syscon"; + reg = <0x021bc000 0x4000>; + clocks = <&clks IMX6SX_CLK_OCOTP>; + tempmon_calib: calib@38 { + reg = <0x38 4>; + }; + + tempmon_temp_grade: temp-grade@20 { + reg = <0x20 4>; + }; +}; + +tempmon: tempmon { + compatible = "fsl,imx6sx-tempmon", "fsl,imx6q-tempmon"; + interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>; + fsl,tempmon = <&anatop>; + nvmem-cells = <&tempmon_calib>, <&tempmon_temp_grade>; + nvmem-cell-names = "calib", "temp_grade"; + clocks = <&clks IMX6SX_CLK_PLL3_USB_OTG>; +}; + +Legacy method (Deprecated): tempmon { compatible = "fsl,imx6q-tempmon"; fsl,tempmon = <&anatop>; diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt index e64d903bcbe8..46da5f184460 100644 --- a/Documentation/devicetree/bindings/usb/dwc2.txt +++ b/Documentation/devicetree/bindings/usb/dwc2.txt @@ -19,7 +19,7 @@ Required properties: configured in FS mode; - "st,stm32f4x9-hsotg": The DWC2 USB HS controller instance in STM32F4x9 SoCs configured in HS mode; - - "st,stm32f7xx-hsotg": The DWC2 USB HS controller instance in STM32F7xx SoCs + - "st,stm32f7-hsotg": The DWC2 USB HS controller instance in STM32F7 SoCs configured in HS mode; - reg : Should contain 1 register range (address and length) - interrupts : Should contain 1 interrupt diff --git a/Documentation/devicetree/bindings/usb/renesas_usb3.txt b/Documentation/devicetree/bindings/usb/renesas_usb3.txt index 87a45e2f9b7f..2c071bb5801e 100644 --- a/Documentation/devicetree/bindings/usb/renesas_usb3.txt +++ b/Documentation/devicetree/bindings/usb/renesas_usb3.txt @@ -4,6 +4,7 @@ Required properties: - compatible: Must contain one of the following: - "renesas,r8a7795-usb3-peri" - "renesas,r8a7796-usb3-peri" + - "renesas,r8a77965-usb3-peri" - "renesas,rcar-gen3-usb3-peri" for a generic R-Car Gen3 compatible device diff --git a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt index d060172f1529..43960faf5a88 100644 --- a/Documentation/devicetree/bindings/usb/renesas_usbhs.txt +++ b/Documentation/devicetree/bindings/usb/renesas_usbhs.txt @@ -12,6 +12,7 @@ Required properties: - "renesas,usbhs-r8a7794" for r8a7794 (R-Car E2) compatible device - "renesas,usbhs-r8a7795" for r8a7795 (R-Car H3) compatible device - "renesas,usbhs-r8a7796" for r8a7796 (R-Car M3-W) compatible device + - "renesas,usbhs-r8a77965" for r8a77965 (R-Car M3-N) compatible device - "renesas,usbhs-r8a77995" for r8a77995 (R-Car D3) compatible device - "renesas,usbhs-r7s72100" for r7s72100 (RZ/A1) compatible device - "renesas,rcar-gen2-usbhs" for R-Car Gen2 or RZ/G1 compatible devices diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt index e2ea59bbca93..1651483a7048 100644 --- a/Documentation/devicetree/bindings/usb/usb-xhci.txt +++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt @@ -13,6 +13,7 @@ Required properties: - "renesas,xhci-r8a7793" for r8a7793 SoC - "renesas,xhci-r8a7795" for r8a7795 SoC - "renesas,xhci-r8a7796" for r8a7796 SoC + - "renesas,xhci-r8a77965" for r8a77965 SoC - "renesas,rcar-gen2-xhci" for a generic R-Car Gen2 or RZ/G1 compatible device - "renesas,rcar-gen3-xhci" for a generic R-Car Gen3 compatible device diff --git a/Documentation/ia64/serial.txt b/Documentation/ia64/serial.txt index 6869c73de4e2..a63d2c54329b 100644 --- a/Documentation/ia64/serial.txt +++ b/Documentation/ia64/serial.txt @@ -111,7 +111,7 @@ TROUBLESHOOTING SERIAL CONSOLE PROBLEMS - If you don't have an HCDP, the kernel doesn't know where your console lives until the driver discovers serial - devices. Use "console=uart, io,0x3f8" (or appropriate + devices. Use "console=uart,io,0x3f8" (or appropriate address for your machine). Kernel and init script output works fine, but no "login:" prompt: diff --git a/Documentation/media/dmx.h.rst.exceptions b/Documentation/media/dmx.h.rst.exceptions index 63f55a9ae2b1..a8c4239ed95b 100644 --- a/Documentation/media/dmx.h.rst.exceptions +++ b/Documentation/media/dmx.h.rst.exceptions @@ -50,9 +50,15 @@ replace typedef dmx_filter_t :c:type:`dmx_filter` replace typedef dmx_pes_type_t :c:type:`dmx_pes_type` replace typedef dmx_input_t :c:type:`dmx_input` -ignore symbol DMX_OUT_DECODER -ignore symbol DMX_OUT_TAP -ignore symbol DMX_OUT_TS_TAP -ignore symbol DMX_OUT_TSDEMUX_TAP +replace symbol DMX_BUFFER_FLAG_HAD_CRC32_DISCARD :c:type:`dmx_buffer_flags` +replace symbol DMX_BUFFER_FLAG_TEI :c:type:`dmx_buffer_flags` +replace symbol DMX_BUFFER_PKT_COUNTER_MISMATCH :c:type:`dmx_buffer_flags` +replace symbol DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED :c:type:`dmx_buffer_flags` +replace symbol DMX_BUFFER_FLAG_DISCONTINUITY_INDICATOR :c:type:`dmx_buffer_flags` + +replace symbol DMX_OUT_DECODER :c:type:`dmx_output` +replace symbol DMX_OUT_TAP :c:type:`dmx_output` +replace symbol DMX_OUT_TS_TAP :c:type:`dmx_output` +replace symbol DMX_OUT_TSDEMUX_TAP :c:type:`dmx_output` replace ioctl DMX_DQBUF dmx_qbuf diff --git a/Documentation/media/uapi/dvb/dmx-qbuf.rst b/Documentation/media/uapi/dvb/dmx-qbuf.rst index b48c4931658e..be5a4c6f1904 100644 --- a/Documentation/media/uapi/dvb/dmx-qbuf.rst +++ b/Documentation/media/uapi/dvb/dmx-qbuf.rst @@ -51,9 +51,10 @@ out to disk. Buffers remain locked until dequeued, until the the device is closed. Applications call the ``DMX_DQBUF`` ioctl to dequeue a filled -(capturing) buffer from the driver's outgoing queue. They just set the ``reserved`` field array to zero. When ``DMX_DQBUF`` is called with a -pointer to this structure, the driver fills the remaining fields or -returns an error code. +(capturing) buffer from the driver's outgoing queue. +They just set the ``index`` field withe the buffer ID to be queued. +When ``DMX_DQBUF`` is called with a pointer to struct :c:type:`dmx_buffer`, +the driver fills the remaining fields or returns an error code. By default ``DMX_DQBUF`` blocks when no buffer is in the outgoing queue. When the ``O_NONBLOCK`` flag was given to the diff --git a/Documentation/networking/segmentation-offloads.txt b/Documentation/networking/segmentation-offloads.txt index d47480b61ac6..aca542ec125c 100644 --- a/Documentation/networking/segmentation-offloads.txt +++ b/Documentation/networking/segmentation-offloads.txt @@ -20,8 +20,8 @@ TCP Segmentation Offload TCP segmentation allows a device to segment a single frame into multiple frames with a data payload size specified in skb_shinfo()->gso_size. -When TCP segmentation requested the bit for either SKB_GSO_TCP or -SKB_GSO_TCP6 should be set in skb_shinfo()->gso_type and +When TCP segmentation requested the bit for either SKB_GSO_TCPV4 or +SKB_GSO_TCPV6 should be set in skb_shinfo()->gso_type and skb_shinfo()->gso_size should be set to a non-zero value. TCP segmentation is dependent on support for the use of partial checksum @@ -153,8 +153,18 @@ To signal this, gso_size is set to the special value GSO_BY_FRAGS. Therefore, any code in the core networking stack must be aware of the possibility that gso_size will be GSO_BY_FRAGS and handle that case -appropriately. (For size checks, the skb_gso_validate_*_len family of -helpers do this automatically.) +appropriately. + +There are some helpers to make this easier: + + - skb_is_gso(skb) && skb_is_gso_sctp(skb) is the best way to see if + an skb is an SCTP GSO skb. + + - For size checks, the skb_gso_validate_*_len family of helpers correctly + considers GSO_BY_FRAGS. + + - For manipulating packets, skb_increase_gso_size and skb_decrease_gso_size + will check for GSO_BY_FRAGS and WARN if asked to manipulate these skbs. This also affects drivers with the NETIF_F_FRAGLIST & NETIF_F_GSO_SCTP bits set. Note also that NETIF_F_GSO_SCTP is included in NETIF_F_GSO_SOFTWARE. diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py index 39aa9e8697cc..fbedcc39460b 100644 --- a/Documentation/sphinx/kerneldoc.py +++ b/Documentation/sphinx/kerneldoc.py @@ -36,8 +36,7 @@ import glob from docutils import nodes, statemachine from docutils.statemachine import ViewList -from docutils.parsers.rst import directives -from sphinx.util.compat import Directive +from docutils.parsers.rst import directives, Directive from sphinx.ext.autodoc import AutodocReporter __version__ = '1.0' diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 792fa8717d13..d6b3ff51a14f 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -123,14 +123,15 @@ memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the flag KVM_VM_MIPS_VZ. -4.3 KVM_GET_MSR_INDEX_LIST +4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST -Capability: basic +Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST Architectures: x86 -Type: system +Type: system ioctl Parameters: struct kvm_msr_list (in/out) Returns: 0 on success; -1 on error Errors: + EFAULT: the msr index list cannot be read from or written to E2BIG: the msr index list is to be to fit in the array specified by the user. @@ -139,16 +140,23 @@ struct kvm_msr_list { __u32 indices[0]; }; -This ioctl returns the guest msrs that are supported. The list varies -by kvm version and host processor, but does not change otherwise. The -user fills in the size of the indices array in nmsrs, and in return -kvm adjusts nmsrs to reflect the actual number of msrs and fills in -the indices array with their numbers. +The user fills in the size of the indices array in nmsrs, and in return +kvm adjusts nmsrs to reflect the actual number of msrs and fills in the +indices array with their numbers. + +KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported. The list +varies by kvm version and host processor, but does not change otherwise. Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are not returned in the MSR list, as different vcpus can have a different number of banks, as set via the KVM_X86_SETUP_MCE ioctl. +KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed +to the KVM_GET_MSRS system ioctl. This lets userspace probe host capabilities +and processor features that are exposed via MSRs (e.g., VMX capabilities). +This list also varies by kvm version and host processor, but does not change +otherwise. + 4.4 KVM_CHECK_EXTENSION @@ -475,14 +483,22 @@ Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead. 4.18 KVM_GET_MSRS -Capability: basic +Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system) Architectures: x86 -Type: vcpu ioctl +Type: system ioctl, vcpu ioctl Parameters: struct kvm_msrs (in/out) -Returns: 0 on success, -1 on error +Returns: number of msrs successfully returned; + -1 on error + +When used as a system ioctl: +Reads the values of MSR-based features that are available for the VM. This +is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values. +The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST +in a system ioctl. +When used as a vcpu ioctl: Reads model-specific registers from the vcpu. Supported msr indices can -be obtained using KVM_GET_MSR_INDEX_LIST. +be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl. struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt index dcab6dc11e3b..87a7506f31c2 100644 --- a/Documentation/virtual/kvm/cpuid.txt +++ b/Documentation/virtual/kvm/cpuid.txt @@ -58,6 +58,10 @@ KVM_FEATURE_PV_TLB_FLUSH || 9 || guest checks this feature bit || || before enabling paravirtualized || || tlb flush. ------------------------------------------------------------------------------ +KVM_FEATURE_ASYNC_PF_VMEXIT || 10 || paravirtualized async PF VM exit + || || can be enabled by setting bit 2 + || || when writing to msr 0x4b564d02 +------------------------------------------------------------------------------ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side || || per-cpu warps are expected in || || kvmclock. diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt index 1ebecc115dc6..f3f0d57ced8e 100644 --- a/Documentation/virtual/kvm/msr.txt +++ b/Documentation/virtual/kvm/msr.txt @@ -170,7 +170,8 @@ MSR_KVM_ASYNC_PF_EN: 0x4b564d02 when asynchronous page faults are enabled on the vcpu 0 when disabled. Bit 1 is 1 if asynchronous page faults can be injected when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults - are delivered to L1 as #PF vmexits. + are delivered to L1 as #PF vmexits. Bit 2 can be set only if + KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID. First 4 byte of 64 byte memory location will be written to by the hypervisor at the time of asynchronous page fault (APF) diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt index 756fd76b78a6..71c30984e94d 100644 --- a/Documentation/x86/intel_rdt_ui.txt +++ b/Documentation/x86/intel_rdt_ui.txt @@ -671,7 +671,7 @@ occupancy of the real time threads on these cores. # mkdir p1 Move the cpus 4-7 over to p1 -# echo f0 > p0/cpus +# echo f0 > p1/cpus View the llc occupancy snapshot diff --git a/MAINTAINERS b/MAINTAINERS index 93a12af4f180..73c0cdabf755 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1238,7 +1238,7 @@ F: drivers/clk/at91 ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Alexandre Belloni <alexandre.belloni@free-electrons.com> +M: Alexandre Belloni <alexandre.belloni@bootlin.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://www.linux4sam.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/nferre/linux-at91.git @@ -1590,7 +1590,7 @@ ARM/Marvell Dove/MV78xx0/Orion SOC support M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> -M: Gregory Clement <gregory.clement@free-electrons.com> +M: Gregory Clement <gregory.clement@bootlin.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/soc/dove/ @@ -1604,7 +1604,7 @@ F: arch/arm/boot/dts/orion5x* ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K SOC support M: Jason Cooper <jason@lakedaemon.net> M: Andrew Lunn <andrew@lunn.ch> -M: Gregory Clement <gregory.clement@free-electrons.com> +M: Gregory Clement <gregory.clement@bootlin.com> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -1999,8 +1999,10 @@ M: Maxime Coquelin <mcoquelin.stm32@gmail.com> M: Alexandre Torgue <alexandre.torgue@st.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/atorgue/stm32.git stm32-next N: stm32 +F: arch/arm/boot/dts/stm32* +F: arch/arm/mach-stm32/ F: drivers/clocksource/armv7m_systick.c ARM/TANGO ARCHITECTURE @@ -7600,8 +7602,10 @@ F: mm/kasan/ F: scripts/Makefile.kasan KCONFIG +M: Masahiro Yamada <yamada.masahiro@socionext.com> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git kconfig L: linux-kbuild@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/kbuild/kconfig-language.txt F: scripts/kconfig/ @@ -9921,6 +9925,13 @@ F: Documentation/ABI/stable/sysfs-bus-nvmem F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h +NXP SGTL5000 DRIVER +M: Fabio Estevam <fabio.estevam@nxp.com> +L: alsa-devel@alsa-project.org (moderated for non-subscribers) +S: Maintained +F: Documentation/devicetree/bindings/sound/sgtl5000.txt +F: sound/soc/codecs/sgtl5000* + NXP TDA998X DRM DRIVER M: Russell King <linux@armlinux.org.uk> S: Supported @@ -10323,7 +10334,7 @@ F: drivers/oprofile/ F: include/linux/oprofile.h ORACLE CLUSTER FILESYSTEM 2 (OCFS2) -M: Mark Fasheh <mfasheh@versity.com> +M: Mark Fasheh <mark@fasheh.com> M: Joel Becker <jlbec@evilplan.org> L: ocfs2-devel@oss.oracle.com (moderated for non-subscribers) W: http://ocfs2.wiki.kernel.org @@ -10833,6 +10844,7 @@ F: drivers/platform/x86/peaq-wmi.c PER-CPU MEMORY ALLOCATOR M: Tejun Heo <tj@kernel.org> M: Christoph Lameter <cl@linux.com> +M: Dennis Zhou <dennisszhou@gmail.com> T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git S: Maintained F: include/linux/percpu*.h @@ -10926,6 +10938,17 @@ L: linux-gpio@vger.kernel.org S: Supported F: drivers/pinctrl/pinctrl-at91-pio4.* +PIN CONTROLLER - FREESCALE +M: Dong Aisheng <aisheng.dong@nxp.com> +M: Fabio Estevam <festevam@gmail.com> +M: Shawn Guo <shawnguo@kernel.org> +M: Stefan Agner <stefan@agner.ch> +R: Pengutronix Kernel Team <kernel@pengutronix.de> +L: linux-gpio@vger.kernel.org +S: Maintained +F: drivers/pinctrl/freescale/ +F: Documentation/devicetree/bindings/pinctrl/fsl,* + PIN CONTROLLER - INTEL M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Heikki Krogerus <heikki.krogerus@linux.intel.com> @@ -12092,6 +12115,7 @@ M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/samsung/ +F: Documentation/devicetree/bindings/sound/samsung* SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER M: Krzysztof Kozlowski <krzk@kernel.org> @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc7 NAME = Fearless Coyote # *DOCUMENTATION* @@ -388,7 +388,7 @@ PYTHON = python CHECK = sparse CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ - -Wbitwise -Wno-return-void $(CF) + -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF) NOSTDINC_FLAGS = CFLAGS_MODULE = AFLAGS_MODULE = @@ -489,6 +489,11 @@ KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) endif +RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register +RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk +RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG))) +export RETPOLINE_CFLAGS + ifeq ($(config-targets),1) # =========================================================================== # *config targets only - make sure prerequisites are updated, and descend @@ -579,10 +584,9 @@ ifeq ($(KBUILD_EXTMOD),) # To avoid any implicit rule to kick in, define an empty command $(KCONFIG_CONFIG) include/config/auto.conf.cmd: ; -# If .config is newer than include/config/auto.conf, someone tinkered -# with it and forgot to run make oldconfig. -# if auto.conf.cmd is missing then we are probably in a cleaned tree so -# we execute the config step to be sure to catch updated Kconfig files +# The actual configuration files used during the build are stored in +# include/generated/ and include/config/. Update them if .config is newer than +# include/config/auto.conf (which mirrors .config). include/config/%.conf: $(KCONFIG_CONFIG) include/config/auto.conf.cmd $(Q)$(MAKE) -f $(srctree)/Makefile silentoldconfig else @@ -822,6 +826,15 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign) # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) +# clang sets -fmerge-all-constants by default as optimization, but this +# is non-conforming behavior for C and in fact breaks the kernel, so we +# need to disable it here generally. +KBUILD_CFLAGS += $(call cc-option,-fno-merge-all-constants) + +# for gcc -fno-merge-all-constants disables everything, but it is fine +# to have actual conforming behavior enabled. +KBUILD_CFLAGS += $(call cc-option,-fmerge-constants) + # Make sure -fstack-check isn't enabled (like gentoo apparently did) KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,) @@ -857,8 +870,7 @@ KBUILD_AFLAGS += $(ARCH_AFLAGS) $(KAFLAGS) KBUILD_CFLAGS += $(ARCH_CFLAGS) $(KCFLAGS) # Use --build-id when available. -LDFLAGS_BUILD_ID := $(patsubst -Wl$(comma)%,%,\ - $(call cc-ldoption, -Wl$(comma)--build-id,)) +LDFLAGS_BUILD_ID := $(call ld-option, --build-id) KBUILD_LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID) LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index f3a80cf164cc..d76bf4a83740 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -484,7 +484,6 @@ config ARC_CURR_IN_REG config ARC_EMUL_UNALIGNED bool "Emulate unaligned memory access (userspace only)" - default N select SYSCTL_ARCH_UNALIGN_NO_WARN select SYSCTL_ARCH_UNALIGN_ALLOW depends on ISA_ARCOMPACT diff --git a/arch/arc/boot/dts/axs101.dts b/arch/arc/boot/dts/axs101.dts index 70aec7d6ca60..626b694c7be7 100644 --- a/arch/arc/boot/dts/axs101.dts +++ b/arch/arc/boot/dts/axs101.dts @@ -17,6 +17,6 @@ compatible = "snps,axs101", "snps,arc-sdp"; chosen { - bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60"; + bootargs = "earlycon=uart8250,mmio32,0xe0022000,115200n8 console=tty0 console=ttyS3,115200n8 consoleblank=0 video=1280x720@60 print-fatal-signals=1"; }; }; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 74d070cd3c13..47b74fbc403c 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -214,13 +214,13 @@ }; eeprom@0x54{ - compatible = "24c01"; + compatible = "atmel,24c01"; reg = <0x54>; pagesize = <0x8>; }; eeprom@0x57{ - compatible = "24c04"; + compatible = "atmel,24c04"; reg = <0x57>; pagesize = <0x8>; }; diff --git a/arch/arc/boot/dts/haps_hs_idu.dts b/arch/arc/boot/dts/haps_hs_idu.dts index 215cddd0b63b..0c603308aeb3 100644 --- a/arch/arc/boot/dts/haps_hs_idu.dts +++ b/arch/arc/boot/dts/haps_hs_idu.dts @@ -22,7 +22,7 @@ }; chosen { - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 5ee96b067c08..ff2f2c70c545 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -17,7 +17,7 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_hs.dts b/arch/arc/boot/dts/nsim_hs.dts index 8d787b251f73..8e2489b16b0a 100644 --- a/arch/arc/boot/dts/nsim_hs.dts +++ b/arch/arc/boot/dts/nsim_hs.dts @@ -24,7 +24,7 @@ }; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsim_hs_idu.dts b/arch/arc/boot/dts/nsim_hs_idu.dts index 4f98ebf71fd8..ed12f494721d 100644 --- a/arch/arc/boot/dts/nsim_hs_idu.dts +++ b/arch/arc/boot/dts/nsim_hs_idu.dts @@ -15,7 +15,7 @@ interrupt-parent = <&core_intc>; chosen { - bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8"; + bootargs = "earlycon=arc_uart,mmio32,0xc0fc1000,115200n8 console=ttyARC0,115200n8 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index 3c391ba565ed..7842e5eb4ab5 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts index 14a727cbf4c9..b8838cf2b4ec 100644 --- a/arch/arc/boot/dts/nsimosci_hs.dts +++ b/arch/arc/boot/dts/nsimosci_hs.dts @@ -20,7 +20,7 @@ /* this is for console on PGU */ /* bootargs = "console=tty0 consoleblank=0"; */ /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts index 5052917d4a99..72a2c723f1f7 100644 --- a/arch/arc/boot/dts/nsimosci_hs_idu.dts +++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -18,7 +18,7 @@ chosen { /* this is for console on serial */ - bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24"; + bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblan=0 debug video=640x480-24 print-fatal-signals=1"; }; aliases { diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index 257a68f3c2fe..309f4e6721b3 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -184,7 +184,7 @@ .macro FAKE_RET_FROM_EXCPN lr r9, [status32] bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK) - or r9, r9, (STATUS_L_MASK|STATUS_IE_MASK) + or r9, r9, STATUS_IE_MASK kflag r9 .endm diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index f61a52b01625..5fe84e481654 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -22,10 +22,79 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static char smp_cpuinfo_buf[128]; +/* + * Set mask to halt GFRC if any online core in SMP cluster is halted. + * Only works for ARC HS v3.0+, on earlier versions has no effect. + */ +static void mcip_update_gfrc_halt_mask(int cpu) +{ + struct bcr_generic gfrc; + unsigned long flags; + u32 gfrc_halt_mask; + + READ_BCR(ARC_REG_GFRC_BUILD, gfrc); + + /* + * CMD_GFRC_SET_CORE and CMD_GFRC_READ_CORE commands were added in + * GFRC 0x3 version. + */ + if (gfrc.ver < 0x3) + return; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + __mcip_cmd(CMD_GFRC_READ_CORE, 0); + gfrc_halt_mask = read_aux_reg(ARC_REG_MCIP_READBACK); + gfrc_halt_mask |= BIT(cpu); + __mcip_cmd_data(CMD_GFRC_SET_CORE, 0, gfrc_halt_mask); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + +static void mcip_update_debug_halt_mask(int cpu) +{ + u32 mcip_mask = 0; + unsigned long flags; + + raw_spin_lock_irqsave(&mcip_lock, flags); + + /* + * mcip_mask is same for CMD_DEBUG_SET_SELECT and CMD_DEBUG_SET_MASK + * commands. So read it once instead of reading both CMD_DEBUG_READ_MASK + * and CMD_DEBUG_READ_SELECT. + */ + __mcip_cmd(CMD_DEBUG_READ_SELECT, 0); + mcip_mask = read_aux_reg(ARC_REG_MCIP_READBACK); + + mcip_mask |= BIT(cpu); + + __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, mcip_mask); + /* + * Parameter specified halt cause: + * STATUS32[H]/actionpoint/breakpoint/self-halt + * We choose all of them (0xF). + */ + __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xF, mcip_mask); + + raw_spin_unlock_irqrestore(&mcip_lock, flags); +} + static void mcip_setup_per_cpu(int cpu) { + struct mcip_bcr mp; + + READ_BCR(ARC_REG_MCIP_BCR, mp); + smp_ipi_irq_setup(cpu, IPI_IRQ); smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); + + /* Update GFRC halt mask as new CPU came online */ + if (mp.gfrc) + mcip_update_gfrc_halt_mask(cpu); + + /* Update MCIP debug mask as new CPU came online */ + if (mp.dbg) + mcip_update_debug_halt_mask(cpu); } static void mcip_ipi_send(int cpu) @@ -101,11 +170,6 @@ static void mcip_probe_n_setup(void) IS_AVAIL1(mp.gfrc, "GFRC")); cpuinfo_arc700[0].extn.gfrc = mp.gfrc; - - if (mp.dbg) { - __mcip_cmd_data(CMD_DEBUG_SET_SELECT, 0, 0xf); - __mcip_cmd_data(CMD_DEBUG_SET_MASK, 0xf, 0xf); - } } struct plat_smp_ops plat_smp_ops = { diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index ec12fe1c2f07..b2cae79a25d7 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -51,7 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = { { 0x51, "R2.0" }, { 0x52, "R2.1" }, { 0x53, "R3.0" }, - { 0x54, "R4.0" }, + { 0x54, "R3.10a" }, #endif { 0x00, NULL } }; diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index efe8b4200a67..21d86c36692b 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -24,6 +24,7 @@ #include <linux/reboot.h> #include <linux/irqdomain.h> #include <linux/export.h> +#include <linux/of_fdt.h> #include <asm/processor.h> #include <asm/setup.h> @@ -47,6 +48,42 @@ void __init smp_prepare_boot_cpu(void) { } +static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask) +{ + unsigned long dt_root = of_get_flat_dt_root(); + const char *buf; + + buf = of_get_flat_dt_prop(dt_root, name, NULL); + if (!buf) + return -EINVAL; + + if (cpulist_parse(buf, cpumask)) + return -EINVAL; + + return 0; +} + +/* + * Read from DeviceTree and setup cpu possible mask. If there is no + * "possible-cpus" property in DeviceTree pretend all [0..NR_CPUS-1] exist. + */ +static void __init arc_init_cpu_possible(void) +{ + struct cpumask cpumask; + + if (arc_get_cpu_map("possible-cpus", &cpumask)) { + pr_warn("Failed to get possible-cpus from dtb, pretending all %u cpus exist\n", + NR_CPUS); + + cpumask_setall(&cpumask); + } + + if (!cpumask_test_cpu(0, &cpumask)) + panic("Master cpu (cpu[0]) is missed in cpu possible mask!"); + + init_cpu_possible(&cpumask); +} + /* * Called from setup_arch() before calling setup_processor() * @@ -58,10 +95,7 @@ void __init smp_prepare_boot_cpu(void) */ void __init smp_init_cpus(void) { - unsigned int i; - - for (i = 0; i < NR_CPUS; i++) - set_cpu_possible(i, true); + arc_init_cpu_possible(); if (plat_smp_ops.init_early_smp) plat_smp_ops.init_early_smp(); @@ -70,16 +104,12 @@ void __init smp_init_cpus(void) /* called from init ( ) => process 1 */ void __init smp_prepare_cpus(unsigned int max_cpus) { - int i; - /* * if platform didn't set the present map already, do it now * boot cpu is set to present already by init/main.c */ - if (num_present_cpus() <= 1) { - for (i = 0; i < max_cpus; i++) - set_cpu_present(i, true); - } + if (num_present_cpus() <= 1) + init_cpu_present(cpu_possible_mask); } void __init smp_cpus_done(unsigned int max_cpus) diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index eee924dfffa6..2072f3451e9c 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -780,7 +780,10 @@ noinline static void slc_entire_op(const int op) write_aux_reg(r, ctrl); - write_aux_reg(ARC_REG_SLC_INVALIDATE, 1); + if (op & OP_INV) /* Inv or flush-n-inv use same cmd reg */ + write_aux_reg(ARC_REG_SLC_INVALIDATE, 0x1); + else + write_aux_reg(ARC_REG_SLC_FLUSH, 0x1); /* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */ read_aux_reg(r); diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi index 18045c38bcf1..db7cded1b7ad 100644 --- a/arch/arm/boot/dts/bcm11351.dtsi +++ b/arch/arm/boot/dts/bcm11351.dtsi @@ -55,7 +55,7 @@ <0x3ff00100 0x100>; }; - smc@0x3404c000 { + smc@3404c000 { compatible = "brcm,bcm11351-smc", "brcm,kona-smc"; reg = <0x3404c000 0x400>; /* 1 KiB in SRAM */ }; diff --git a/arch/arm/boot/dts/bcm21664.dtsi b/arch/arm/boot/dts/bcm21664.dtsi index 6dde95f21cef..266f2611dc22 100644 --- a/arch/arm/boot/dts/bcm21664.dtsi +++ b/arch/arm/boot/dts/bcm21664.dtsi @@ -55,7 +55,7 @@ <0x3ff00100 0x100>; }; - smc@0x3404e000 { + smc@3404e000 { compatible = "brcm,bcm21664-smc", "brcm,kona-smc"; reg = <0x3404e000 0x400>; /* 1 KiB in SRAM */ }; diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi index 0e3d2a5ff208..a5c3824c8056 100644 --- a/arch/arm/boot/dts/bcm2835.dtsi +++ b/arch/arm/boot/dts/bcm2835.dtsi @@ -18,10 +18,10 @@ soc { ranges = <0x7e000000 0x20000000 0x02000000>; dma-ranges = <0x40000000 0x00000000 0x20000000>; + }; - arm-pmu { - compatible = "arm,arm1176-pmu"; - }; + arm-pmu { + compatible = "arm,arm1176-pmu"; }; }; diff --git a/arch/arm/boot/dts/bcm2836.dtsi b/arch/arm/boot/dts/bcm2836.dtsi index 1dfd76442777..c933e8413884 100644 --- a/arch/arm/boot/dts/bcm2836.dtsi +++ b/arch/arm/boot/dts/bcm2836.dtsi @@ -9,19 +9,19 @@ <0x40000000 0x40000000 0x00001000>; dma-ranges = <0xc0000000 0x00000000 0x3f000000>; - local_intc: local_intc { + local_intc: local_intc@40000000 { compatible = "brcm,bcm2836-l1-intc"; reg = <0x40000000 0x100>; interrupt-controller; #interrupt-cells = <2>; interrupt-parent = <&local_intc>; }; + }; - arm-pmu { - compatible = "arm,cortex-a7-pmu"; - interrupt-parent = <&local_intc>; - interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; - }; + arm-pmu { + compatible = "arm,cortex-a7-pmu"; + interrupt-parent = <&local_intc>; + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; }; timer { diff --git a/arch/arm/boot/dts/bcm2837.dtsi b/arch/arm/boot/dts/bcm2837.dtsi index efa7d3387ab2..7704bb029605 100644 --- a/arch/arm/boot/dts/bcm2837.dtsi +++ b/arch/arm/boot/dts/bcm2837.dtsi @@ -8,7 +8,7 @@ <0x40000000 0x40000000 0x00001000>; dma-ranges = <0xc0000000 0x00000000 0x3f000000>; - local_intc: local_intc { + local_intc: local_intc@40000000 { compatible = "brcm,bcm2836-l1-intc"; reg = <0x40000000 0x100>; interrupt-controller; diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi index 18db25a5a66e..9d293decf8d3 100644 --- a/arch/arm/boot/dts/bcm283x.dtsi +++ b/arch/arm/boot/dts/bcm283x.dtsi @@ -465,7 +465,7 @@ status = "disabled"; }; - aux: aux@0x7e215000 { + aux: aux@7e215000 { compatible = "brcm,bcm2835-aux"; #clock-cells = <1>; reg = <0x7e215000 0x8>; diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 6a44b8021702..f0e2008f7490 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -49,7 +49,7 @@ memory { device_type = "memory"; - reg = <0x60000000 0x80000000>; + reg = <0x60000000 0x20000000>; }; gpio-restart { diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts index 08568ce24d06..da8bb9d60f99 100644 --- a/arch/arm/boot/dts/gemini-dlink-dns-313.dts +++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts @@ -269,7 +269,7 @@ sata: sata@46000000 { /* The ROM uses this muxmode */ - cortina,gemini-ata-muxmode = <3>; + cortina,gemini-ata-muxmode = <0>; cortina,gemini-enable-sata-bridge; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6dl-icore-rqs.dts b/arch/arm/boot/dts/imx6dl-icore-rqs.dts index cf42c2f5cdc7..1281bc39b7ab 100644 --- a/arch/arm/boot/dts/imx6dl-icore-rqs.dts +++ b/arch/arm/boot/dts/imx6dl-icore-rqs.dts @@ -42,7 +42,7 @@ /dts-v1/; -#include "imx6q.dtsi" +#include "imx6dl.dtsi" #include "imx6qdl-icore-rqs.dtsi" / { diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index c1aa7a4518fb..a30ee9fcb3ae 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -71,6 +71,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>; twl: twl@48 { @@ -189,7 +191,12 @@ >; }; - + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; }; &omap3_pmx_wkup { diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index b50b796e15c7..47915447a826 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -66,6 +66,8 @@ }; &i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; clock-frequency = <2600000>; twl: twl@48 { @@ -136,6 +138,12 @@ OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT | MUX_MODE0) /* hsusb0_data7.hsusb0_data7 */ >; }; + i2c1_pins: pinmux_i2c1_pins { + pinctrl-single,pins = < + OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */ + OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */ + >; + }; }; &uart2 { diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index ec2c8baef62a..592e17fd4eeb 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -47,7 +47,7 @@ gpios = <&gpio3 19 GPIO_ACTIVE_LOW>; /* gpio3_83 */ wakeup-source; autorepeat; - debounce_interval = <50>; + debounce-interval = <50>; }; }; diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 3b704cfed69a..a97458112ff6 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -280,7 +280,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; resets = <&cru SRST_SDIO>; @@ -298,7 +298,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; default-sample-phase = <158>; disable-wp; dmas = <&pdma 12>; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 780ec3a99b21..341deaf62ff6 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -621,7 +621,7 @@ interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_bus4>; @@ -634,7 +634,7 @@ interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; pinctrl-names = "default"; pinctrl-0 = <&sdio_clk &sdio_cmd &sdio_bus4>; @@ -649,7 +649,7 @@ max-frequency = <37500000>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; bus-width = <8>; default-sample-phase = <158>; fifo-depth = <0x100>; diff --git a/arch/arm/boot/dts/rk3288-phycore-som.dtsi b/arch/arm/boot/dts/rk3288-phycore-som.dtsi index 99cfae875e12..5eae4776ffde 100644 --- a/arch/arm/boot/dts/rk3288-phycore-som.dtsi +++ b/arch/arm/boot/dts/rk3288-phycore-som.dtsi @@ -110,26 +110,6 @@ }; }; -&cpu0 { - cpu0-supply = <&vdd_cpu>; - operating-points = < - /* KHz uV */ - 1800000 1400000 - 1608000 1350000 - 1512000 1300000 - 1416000 1200000 - 1200000 1100000 - 1008000 1050000 - 816000 1000000 - 696000 950000 - 600000 900000 - 408000 900000 - 312000 900000 - 216000 900000 - 126000 900000 - >; -}; - &emmc { status = "okay"; bus-width = <8>; diff --git a/arch/arm/boot/dts/zx296702.dtsi b/arch/arm/boot/dts/zx296702.dtsi index 8a74efdb6360..240e7a23d81f 100644 --- a/arch/arm/boot/dts/zx296702.dtsi +++ b/arch/arm/boot/dts/zx296702.dtsi @@ -56,7 +56,7 @@ clocks = <&topclk ZX296702_A9_PERIPHCLK>; }; - l2cc: l2-cache-controller@0x00c00000 { + l2cc: l2-cache-controller@c00000 { compatible = "arm,pl310-cache"; reg = <0x00c00000 0x1000>; cache-unified; @@ -67,30 +67,30 @@ arm,double-linefill-incr = <0>; }; - pcu: pcu@0xa0008000 { + pcu: pcu@a0008000 { compatible = "zte,zx296702-pcu"; reg = <0xa0008000 0x1000>; }; - topclk: topclk@0x09800000 { + topclk: topclk@9800000 { compatible = "zte,zx296702-topcrm-clk"; reg = <0x09800000 0x1000>; #clock-cells = <1>; }; - lsp1clk: lsp1clk@0x09400000 { + lsp1clk: lsp1clk@9400000 { compatible = "zte,zx296702-lsp1crpm-clk"; reg = <0x09400000 0x1000>; #clock-cells = <1>; }; - lsp0clk: lsp0clk@0x0b000000 { + lsp0clk: lsp0clk@b000000 { compatible = "zte,zx296702-lsp0crpm-clk"; reg = <0x0b000000 0x1000>; #clock-cells = <1>; }; - uart0: serial@0x09405000 { + uart0: serial@9405000 { compatible = "zte,zx296702-uart"; reg = <0x09405000 0x1000>; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; @@ -98,7 +98,7 @@ status = "disabled"; }; - uart1: serial@0x09406000 { + uart1: serial@9406000 { compatible = "zte,zx296702-uart"; reg = <0x09406000 0x1000>; interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>; @@ -106,7 +106,7 @@ status = "disabled"; }; - mmc0: mmc@0x09408000 { + mmc0: mmc@9408000 { compatible = "snps,dw-mshc"; #address-cells = <1>; #size-cells = <0>; @@ -119,7 +119,7 @@ status = "disabled"; }; - mmc1: mmc@0x0b003000 { + mmc1: mmc@b003000 { compatible = "snps,dw-mshc"; #address-cells = <1>; #size-cells = <0>; @@ -132,7 +132,7 @@ status = "disabled"; }; - sysctrl: sysctrl@0xa0007000 { + sysctrl: sysctrl@a0007000 { compatible = "zte,sysctrl", "syscon"; reg = <0xa0007000 0x1000>; }; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 2f145c4af93a..92674f247a12 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -319,7 +319,7 @@ CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_RC_CORE=m CONFIG_MEDIA_CONTROLLER=y CONFIG_VIDEO_V4L2_SUBDEV_API=y -CONFIG_LIRC=m +CONFIG_LIRC=y CONFIG_RC_DEVICES=y CONFIG_IR_RX51=m CONFIG_V4L_PLATFORM_DRIVERS=y diff --git a/arch/arm/kvm/hyp/Makefile b/arch/arm/kvm/hyp/Makefile index 5638ce0c9524..63d6b404d88e 100644 --- a/arch/arm/kvm/hyp/Makefile +++ b/arch/arm/kvm/hyp/Makefile @@ -7,6 +7,8 @@ ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING KVM=../../../../virt/kvm +CFLAGS_ARMV7VE :=$(call cc-option, -march=armv7ve) + obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v2-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/vgic-v3-sr.o obj-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/hyp/timer-sr.o @@ -15,7 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o obj-$(CONFIG_KVM_ARM_HOST) += cp15-sr.o obj-$(CONFIG_KVM_ARM_HOST) += vfp.o obj-$(CONFIG_KVM_ARM_HOST) += banked-sr.o +CFLAGS_banked-sr.o += $(CFLAGS_ARMV7VE) + obj-$(CONFIG_KVM_ARM_HOST) += entry.o obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o obj-$(CONFIG_KVM_ARM_HOST) += switch.o +CFLAGS_switch.o += $(CFLAGS_ARMV7VE) obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o diff --git a/arch/arm/kvm/hyp/banked-sr.c b/arch/arm/kvm/hyp/banked-sr.c index 111bda8cdebd..be4b8b0a40ad 100644 --- a/arch/arm/kvm/hyp/banked-sr.c +++ b/arch/arm/kvm/hyp/banked-sr.c @@ -20,6 +20,10 @@ #include <asm/kvm_hyp.h> +/* + * gcc before 4.9 doesn't understand -march=armv7ve, so we have to + * trick the assembler. + */ __asm__(".arch_extension virt"); void __hyp_text __banked_save_state(struct kvm_cpu_context *ctxt) diff --git a/arch/arm/mach-clps711x/board-dt.c b/arch/arm/mach-clps711x/board-dt.c index ee1f83b1a332..4c89a8e9a2e3 100644 --- a/arch/arm/mach-clps711x/board-dt.c +++ b/arch/arm/mach-clps711x/board-dt.c @@ -69,7 +69,7 @@ static void clps711x_restart(enum reboot_mode mode, const char *cmd) soft_restart(0); } -static const char *clps711x_compat[] __initconst = { +static const char *const clps711x_compat[] __initconst = { "cirrus,ep7209", NULL }; diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c index e457f299cd44..d6b11907380c 100644 --- a/arch/arm/mach-davinci/board-dm355-evm.c +++ b/arch/arm/mach-davinci/board-dm355-evm.c @@ -368,7 +368,7 @@ static struct spi_eeprom at25640a = { .flags = EE_ADDR2, }; -static struct spi_board_info dm355_evm_spi_info[] __initconst = { +static const struct spi_board_info dm355_evm_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640a, diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index be997243447b..fad9a5611a5d 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -217,7 +217,7 @@ static struct spi_eeprom at25640a = { .flags = EE_ADDR2, }; -static struct spi_board_info dm355_leopard_spi_info[] __initconst = { +static const struct spi_board_info dm355_leopard_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640a, diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index e75741fb2c1d..e3780986d2a3 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -726,7 +726,7 @@ static struct spi_eeprom at25640 = { .flags = EE_ADDR2, }; -static struct spi_board_info dm365_evm_spi_info[] __initconst = { +static const struct spi_board_info dm365_evm_spi_info[] __initconst = { { .modalias = "at25", .platform_data = &at25640, diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index 6b32dc527edc..2c20599cc350 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -41,7 +41,7 @@ config MACH_ARMADA_375 depends on ARCH_MULTI_V7 select ARMADA_370_XP_IRQ select ARM_ERRATA_720789 - select ARM_ERRATA_753970 + select PL310_ERRATA_753970 select ARM_GIC select ARMADA_375_CLK select HAVE_ARM_SCU @@ -57,7 +57,7 @@ config MACH_ARMADA_38X bool "Marvell Armada 380/385 boards" depends on ARCH_MULTI_V7 select ARM_ERRATA_720789 - select ARM_ERRATA_753970 + select PL310_ERRATA_753970 select ARM_GIC select ARM_GLOBAL_TIMER select CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK diff --git a/arch/arm/mach-omap1/clock.c b/arch/arm/mach-omap1/clock.c index 43e3e188f521..fa512413a471 100644 --- a/arch/arm/mach-omap1/clock.c +++ b/arch/arm/mach-omap1/clock.c @@ -1011,17 +1011,17 @@ static int clk_debugfs_register_one(struct clk *c) return -ENOMEM; c->dent = d; - d = debugfs_create_u8("usecount", S_IRUGO, c->dent, (u8 *)&c->usecount); + d = debugfs_create_u8("usecount", S_IRUGO, c->dent, &c->usecount); if (!d) { err = -ENOMEM; goto err_out; } - d = debugfs_create_u32("rate", S_IRUGO, c->dent, (u32 *)&c->rate); + d = debugfs_create_ulong("rate", S_IRUGO, c->dent, &c->rate); if (!d) { err = -ENOMEM; goto err_out; } - d = debugfs_create_x32("flags", S_IRUGO, c->dent, (u32 *)&c->flags); + d = debugfs_create_x8("flags", S_IRUGO, c->dent, &c->flags); if (!d) { err = -ENOMEM; goto err_out; diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index 4bb6751864a5..fc5fb776a710 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -299,8 +299,6 @@ static void irq_save_context(void) if (soc_is_dra7xx()) return; - if (!sar_base) - sar_base = omap4_get_sar_ram_base(); if (wakeupgen_ops && wakeupgen_ops->save_context) wakeupgen_ops->save_context(); } @@ -598,6 +596,8 @@ static int __init wakeupgen_init(struct device_node *node, irq_hotplug_init(); irq_pm_init(); + sar_base = omap4_get_sar_ram_base(); + return 0; } IRQCHIP_DECLARE(ti_wakeupgen, "ti,omap4-wugen-mpu", wakeupgen_init); diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 124f9af34a15..34156eca8e23 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -977,6 +977,9 @@ static int _enable_clocks(struct omap_hwmod *oh) pr_debug("omap_hwmod: %s: enabling clocks\n", oh->name); + if (oh->flags & HWMOD_OPT_CLKS_NEEDED) + _enable_optional_clocks(oh); + if (oh->_clk) clk_enable(oh->_clk); @@ -985,9 +988,6 @@ static int _enable_clocks(struct omap_hwmod *oh) clk_enable(os->_clk); } - if (oh->flags & HWMOD_OPT_CLKS_NEEDED) - _enable_optional_clocks(oh); - /* The opt clocks are controlled by the device driver. */ return 0; diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 366158a54fcd..6f68576e5695 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -186,7 +186,7 @@ static void omap_pm_end(void) cpu_idle_poll_ctrl(false); } -static void omap_pm_finish(void) +static void omap_pm_wake(void) { if (soc_is_omap34xx()) omap_prcm_irq_complete(); @@ -196,7 +196,7 @@ static const struct platform_suspend_ops omap_pm_ops = { .begin = omap_pm_begin, .end = omap_pm_end, .enter = omap_pm_enter, - .finish = omap_pm_finish, + .wake = omap_pm_wake, .valid = suspend_valid_only_mem, }; diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index ece09c9461f7..d61fbd7a2840 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -156,12 +156,6 @@ static struct clock_event_device clockevent_gpt = { .tick_resume = omap2_gp_timer_shutdown, }; -static struct property device_disabled = { - .name = "status", - .length = sizeof("disabled"), - .value = "disabled", -}; - static const struct of_device_id omap_timer_match[] __initconst = { { .compatible = "ti,omap2420-timer", }, { .compatible = "ti,omap3430-timer", }, @@ -203,8 +197,17 @@ static struct device_node * __init omap_get_timer_dt(const struct of_device_id * of_get_property(np, "ti,timer-secure", NULL))) continue; - if (!of_device_is_compatible(np, "ti,omap-counter32k")) - of_add_property(np, &device_disabled); + if (!of_device_is_compatible(np, "ti,omap-counter32k")) { + struct property *prop; + + prop = kzalloc(sizeof(*prop), GFP_KERNEL); + if (!prop) + return NULL; + prop->name = "status"; + prop->value = "disabled"; + prop->length = strlen(prop->value); + of_add_property(np, prop); + } return np; } diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig index 2a7bb6ccdcb7..a810f4dd34b1 100644 --- a/arch/arm/mach-orion5x/Kconfig +++ b/arch/arm/mach-orion5x/Kconfig @@ -58,7 +58,6 @@ config MACH_KUROBOX_PRO config MACH_DNS323 bool "D-Link DNS-323" - select GENERIC_NET_UTILS select I2C_BOARDINFO if I2C help Say 'Y' here if you want your kernel to support the @@ -66,7 +65,6 @@ config MACH_DNS323 config MACH_TS209 bool "QNAP TS-109/TS-209" - select GENERIC_NET_UTILS help Say 'Y' here if you want your kernel to support the QNAP TS-109/TS-209 platform. @@ -101,7 +99,6 @@ config MACH_LINKSTATION_LS_HGL config MACH_TS409 bool "QNAP TS-409" - select GENERIC_NET_UTILS help Say 'Y' here if you want your kernel to support the QNAP TS-409 platform. diff --git a/arch/arm/mach-orion5x/dns323-setup.c b/arch/arm/mach-orion5x/dns323-setup.c index cd483bfb5ca8..d13344b2ddcd 100644 --- a/arch/arm/mach-orion5x/dns323-setup.c +++ b/arch/arm/mach-orion5x/dns323-setup.c @@ -173,10 +173,42 @@ static struct mv643xx_eth_platform_data dns323_eth_data = { .phy_addr = MV643XX_ETH_PHY_ADDR(8), }; +/* dns323_parse_hex_*() taken from tsx09-common.c; should a common copy of these + * functions be kept somewhere? + */ +static int __init dns323_parse_hex_nibble(char n) +{ + if (n >= '0' && n <= '9') + return n - '0'; + + if (n >= 'A' && n <= 'F') + return n - 'A' + 10; + + if (n >= 'a' && n <= 'f') + return n - 'a' + 10; + + return -1; +} + +static int __init dns323_parse_hex_byte(const char *b) +{ + int hi; + int lo; + + hi = dns323_parse_hex_nibble(b[0]); + lo = dns323_parse_hex_nibble(b[1]); + + if (hi < 0 || lo < 0) + return -1; + + return (hi << 4) | lo; +} + static int __init dns323_read_mac_addr(void) { u_int8_t addr[6]; - void __iomem *mac_page; + int i; + char *mac_page; /* MAC address is stored as a regular ol' string in /dev/mtdblock4 * (0x007d0000-0x00800000) starting at offset 196480 (0x2ff80). @@ -185,8 +217,23 @@ static int __init dns323_read_mac_addr(void) if (!mac_page) return -ENOMEM; - if (!mac_pton((__force const char *) mac_page, addr)) - goto error_fail; + /* Sanity check the string we're looking at */ + for (i = 0; i < 5; i++) { + if (*(mac_page + (i * 3) + 2) != ':') { + goto error_fail; + } + } + + for (i = 0; i < 6; i++) { + int byte; + + byte = dns323_parse_hex_byte(mac_page + (i * 3)); + if (byte < 0) { + goto error_fail; + } + + addr[i] = byte; + } iounmap(mac_page); printk("DNS-323: Found ethernet MAC address: %pM\n", addr); diff --git a/arch/arm/mach-orion5x/tsx09-common.c b/arch/arm/mach-orion5x/tsx09-common.c index 89774985d380..905d4f2dd0b8 100644 --- a/arch/arm/mach-orion5x/tsx09-common.c +++ b/arch/arm/mach-orion5x/tsx09-common.c @@ -53,12 +53,53 @@ struct mv643xx_eth_platform_data qnap_tsx09_eth_data = { .phy_addr = MV643XX_ETH_PHY_ADDR(8), }; +static int __init qnap_tsx09_parse_hex_nibble(char n) +{ + if (n >= '0' && n <= '9') + return n - '0'; + + if (n >= 'A' && n <= 'F') + return n - 'A' + 10; + + if (n >= 'a' && n <= 'f') + return n - 'a' + 10; + + return -1; +} + +static int __init qnap_tsx09_parse_hex_byte(const char *b) +{ + int hi; + int lo; + + hi = qnap_tsx09_parse_hex_nibble(b[0]); + lo = qnap_tsx09_parse_hex_nibble(b[1]); + + if (hi < 0 || lo < 0) + return -1; + + return (hi << 4) | lo; +} + static int __init qnap_tsx09_check_mac_addr(const char *addr_str) { u_int8_t addr[6]; + int i; - if (!mac_pton(addr_str, addr)) - return -1; + for (i = 0; i < 6; i++) { + int byte; + + /* + * Enforce "xx:xx:xx:xx:xx:xx\n" format. + */ + if (addr_str[(i * 3) + 2] != ((i < 5) ? ':' : '\n')) + return -1; + + byte = qnap_tsx09_parse_hex_byte(addr_str + (i * 3)); + if (byte < 0) + return -1; + addr[i] = byte; + } printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr); @@ -77,12 +118,12 @@ void __init qnap_tsx09_find_mac_addr(u32 mem_base, u32 size) unsigned long addr; for (addr = mem_base; addr < (mem_base + size); addr += 1024) { - void __iomem *nor_page; + char *nor_page; int ret = 0; nor_page = ioremap(addr, 1024); if (nor_page != NULL) { - ret = qnap_tsx09_check_mac_addr((__force const char *)nor_page); + ret = qnap_tsx09_check_mac_addr(nor_page); iounmap(nor_page); } diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index aff6994950ba..a2399fd66e97 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -472,28 +472,27 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data, /***************************************************************************** * Ethernet switch ****************************************************************************/ -static __initconst const char *orion_ge00_mvmdio_bus_name = "orion-mii"; -static __initdata struct mdio_board_info - orion_ge00_switch_board_info; +static __initdata struct mdio_board_info orion_ge00_switch_board_info = { + .bus_id = "orion-mii", + .modalias = "mv88e6085", +}; void __init orion_ge00_switch_init(struct dsa_chip_data *d) { - struct mdio_board_info *bd; unsigned int i; if (!IS_BUILTIN(CONFIG_PHYLIB)) return; - for (i = 0; i < ARRAY_SIZE(d->port_names); i++) - if (!strcmp(d->port_names[i], "cpu")) + for (i = 0; i < ARRAY_SIZE(d->port_names); i++) { + if (!strcmp(d->port_names[i], "cpu")) { + d->netdev[i] = &orion_ge00.dev; break; + } + } - bd = &orion_ge00_switch_board_info; - bd->bus_id = orion_ge00_mvmdio_bus_name; - bd->mdio_addr = d->sw_addr; - d->netdev[i] = &orion_ge00.dev; - strcpy(bd->modalias, "mv88e6085"); - bd->platform_data = d; + orion_ge00_switch_board_info.mdio_addr = d->sw_addr; + orion_ge00_switch_board_info.platform_data = d; mdiobus_register_board_info(&orion_ge00_switch_board_info, 1); } diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index a80632641b39..70c776ef7aa7 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -165,14 +165,14 @@ uart_A: serial@24000 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart"; - reg = <0x0 0x24000 0x0 0x14>; + reg = <0x0 0x24000 0x0 0x18>; interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; uart_B: serial@23000 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-uart"; - reg = <0x0 0x23000 0x0 0x14>; + reg = <0x0 0x23000 0x0 0x18>; interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 6cb3c2a52baf..4ee2e7951482 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -235,14 +235,14 @@ uart_A: serial@84c0 { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x84c0 0x0 0x14>; + reg = <0x0 0x84c0 0x0 0x18>; interrupts = <GIC_SPI 26 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; uart_B: serial@84dc { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x84dc 0x0 0x14>; + reg = <0x0 0x84dc 0x0 0x18>; interrupts = <GIC_SPI 75 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; @@ -287,7 +287,7 @@ uart_C: serial@8700 { compatible = "amlogic,meson-gx-uart"; - reg = <0x0 0x8700 0x0 0x14>; + reg = <0x0 0x8700 0x0 0x18>; interrupts = <GIC_SPI 93 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; @@ -404,14 +404,14 @@ uart_AO: serial@4c0 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; - reg = <0x0 0x004c0 0x0 0x14>; + reg = <0x0 0x004c0 0x0 0x18>; interrupts = <GIC_SPI 193 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; uart_AO_B: serial@4e0 { compatible = "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; - reg = <0x0 0x004e0 0x0 0x14>; + reg = <0x0 0x004e0 0x0 0x18>; interrupts = <GIC_SPI 197 IRQ_TYPE_EDGE_RISING>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 4f355f17eed6..c8514110b9da 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -631,6 +631,7 @@ internal_phy: ethernet-phy@8 { compatible = "ethernet-phy-id0181.4400", "ethernet-phy-ieee802.3-c22"; + interrupts = <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>; reg = <8>; max-speed = <100>; }; diff --git a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi index 4220fbdcb24a..ff5c4c47b22b 100644 --- a/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi +++ b/arch/arm64/boot/dts/cavium/thunder2-99xx.dtsi @@ -98,7 +98,7 @@ clock-output-names = "clk125mhz"; }; - pci { + pcie@30000000 { compatible = "pci-host-ecam-generic"; device_type = "pci"; #interrupt-cells = <1>; @@ -118,6 +118,7 @@ ranges = <0x02000000 0 0x40000000 0 0x40000000 0 0x20000000 0x43000000 0x40 0x00000000 0x40 0x00000000 0x20 0x00000000>; + bus-range = <0 0xff>; interrupt-map-mask = <0 0 0 7>; interrupt-map = /* addr pin ic icaddr icintr */ diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index e94fa1a53192..047641fe294c 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -51,7 +51,7 @@ #size-cells = <2>; ranges; - ramoops@0x21f00000 { + ramoops@21f00000 { compatible = "ramoops"; reg = <0x0 0x21f00000 0x0 0x00100000>; record-size = <0x00020000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index 9fbe4705ee88..94597e33c806 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -341,7 +341,7 @@ reg = <0 0x10005000 0 0x1000>; }; - pio: pinctrl@0x10005000 { + pio: pinctrl@10005000 { compatible = "mediatek,mt8173-pinctrl"; reg = <0 0x1000b000 0 0x1000>; mediatek,pctl-regmap = <&syscfg_pctl_a>; diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi index 492a011f14f6..1c8f1b86472d 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi @@ -140,16 +140,16 @@ }; agnoc@0 { - qcom,pcie@00600000 { + qcom,pcie@600000 { perst-gpio = <&msmgpio 35 GPIO_ACTIVE_LOW>; }; - qcom,pcie@00608000 { + qcom,pcie@608000 { status = "okay"; perst-gpio = <&msmgpio 130 GPIO_ACTIVE_LOW>; }; - qcom,pcie@00610000 { + qcom,pcie@610000 { status = "okay"; perst-gpio = <&msmgpio 114 GPIO_ACTIVE_LOW>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 4b2afcc4fdf4..0a6f7952bbb1 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -840,7 +840,7 @@ #size-cells = <1>; ranges; - pcie0: qcom,pcie@00600000 { + pcie0: qcom,pcie@600000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; status = "disabled"; power-domains = <&gcc PCIE0_GDSC>; @@ -893,7 +893,7 @@ }; - pcie1: qcom,pcie@00608000 { + pcie1: qcom,pcie@608000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; power-domains = <&gcc PCIE1_GDSC>; bus-range = <0x00 0xff>; @@ -946,7 +946,7 @@ "bus_slave"; }; - pcie2: qcom,pcie@00610000 { + pcie2: qcom,pcie@610000 { compatible = "qcom,pcie-msm8996", "snps,dw-pcie"; power-domains = <&gcc PCIE2_GDSC>; bus-range = <0x00 0xff>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index 3890468678ce..28257724a56e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -132,17 +132,16 @@ assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>; assigned-clock-parents = <&gmac_clkin>, <&gmac_clkin>; clock_in_out = "input"; - /* shows instability at 1GBit right now */ - max-speed = <100>; phy-supply = <&vcc_io>; phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmiim1_pins>; + snps,force_thresh_dma_mode; snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - tx_delay = <0x26>; - rx_delay = <0x11>; + tx_delay = <0x24>; + rx_delay = <0x18>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index a037ee56fead..cae341554486 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -730,7 +730,7 @@ interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>, <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; @@ -741,7 +741,7 @@ interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_SDIO>, <&cru SCLK_SDIO>, <&cru SCLK_SDIO_DRV>, <&cru SCLK_SDIO_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; @@ -752,7 +752,7 @@ interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>, <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index aa4d07046a7b..03458ac44201 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -257,7 +257,7 @@ max-frequency = <150000000>; clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>, <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>; - clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + clock-names = "biu", "ciu", "ciu-drive", "ciu-sample"; fifo-depth = <0x100>; interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>; resets = <&cru SRST_SDIO0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi index 0f873c897d0d..ce592a4c0c4c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire.dtsi @@ -457,7 +457,7 @@ assigned-clocks = <&cru SCLK_PCIEPHY_REF>; assigned-clock-parents = <&cru SCLK_PCIEPHY_REF100M>; assigned-clock-rates = <100000000>; - ep-gpios = <&gpio3 RK_PB5 GPIO_ACTIVE_HIGH>; + ep-gpios = <&gpio2 RK_PA4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; pinctrl-0 = <&pcie_clkreqn_cpm>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 7aa2144e0d47..2605118d4b4c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1739,8 +1739,8 @@ compatible = "rockchip,rk3399-edp"; reg = <0x0 0xff970000 0x0 0x8000>; interrupts = <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH 0>; - clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>; - clock-names = "dp", "pclk"; + clocks = <&cru PCLK_EDP>, <&cru PCLK_EDP_CTRL>, <&cru PCLK_VIO_GRF>; + clock-names = "dp", "pclk", "grf"; pinctrl-names = "default"; pinctrl-0 = <&edp_hpd>; power-domains = <&power RK3399_PD_EDP>; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 52f15cd896e1..b5a28336c077 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -178,7 +178,7 @@ static int enable_smccc_arch_workaround_1(void *data) case PSCI_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if (res.a0) + if ((int)res.a0 < 0) return 0; cb = call_hvc_arch_workaround_1; smccc_start = __smccc_workaround_1_hvc_start; @@ -188,7 +188,7 @@ static int enable_smccc_arch_workaround_1(void *data) case PSCI_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if (res.a0) + if ((int)res.a0 < 0) return 0; cb = call_smc_arch_workaround_1; smccc_start = __smccc_workaround_1_smc_start; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d7e3299a7734..959e50d2588c 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -363,8 +363,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, { int ret = 0; - vcpu_load(vcpu); - trace_kvm_set_guest_debug(vcpu, dbg->control); if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) { @@ -386,7 +384,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, } out: - vcpu_put(vcpu); return ret; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 84a019f55022..2dbb2c9f1ec1 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -108,7 +108,7 @@ static bool pgattr_change_is_safe(u64 old, u64 new) * The following mapping attributes may be updated in live * kernel mappings without the need for break-before-make. */ - static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE; + static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG; /* creating or taking down mappings is always safe */ if (old == 0 || new == 0) @@ -118,9 +118,9 @@ static bool pgattr_change_is_safe(u64 old, u64 new) if ((old | new) & PTE_CONT) return false; - /* Transitioning from Global to Non-Global is safe */ - if (((old ^ new) == PTE_NG) && (new & PTE_NG)) - return true; + /* Transitioning from Non-Global to Global is unsafe */ + if (old & ~new & PTE_NG) + return false; return ((old ^ new) & ~mask) == 0; } @@ -972,3 +972,13 @@ int pmd_clear_huge(pmd_t *pmdp) pmd_clear(pmdp); return 1; } + +int pud_free_pmd_page(pud_t *pud) +{ + return pud_none(*pud); +} + +int pmd_free_pte_page(pmd_t *pmd) +{ + return pmd_none(*pmd); +} diff --git a/arch/h8300/include/asm/byteorder.h b/arch/h8300/include/asm/byteorder.h index ecff2d1ca5a3..6eaa7ad5fc2c 100644 --- a/arch/h8300/include/asm/byteorder.h +++ b/arch/h8300/include/asm/byteorder.h @@ -2,7 +2,6 @@ #ifndef __H8300_BYTEORDER_H__ #define __H8300_BYTEORDER_H__ -#define __BIG_ENDIAN __ORDER_BIG_ENDIAN__ #include <linux/byteorder/big_endian.h> #endif diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h index 762eeb0fcc1d..2524fb60fbc2 100644 --- a/arch/ia64/include/asm/atomic.h +++ b/arch/ia64/include/asm/atomic.h @@ -66,38 +66,35 @@ ATOMIC_OPS(add, +) ATOMIC_OPS(sub, -) #ifdef __OPTIMIZE__ -#define __ia64_atomic_const(i) __builtin_constant_p(i) ? \ +#define __ia64_atomic_const(i) \ + static const int __ia64_atomic_p = __builtin_constant_p(i) ? \ ((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 || \ - (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0 + (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0;\ + __ia64_atomic_p +#else +#define __ia64_atomic_const(i) 0 +#endif -#define atomic_add_return(i, v) \ +#define atomic_add_return(i,v) \ ({ \ - int __i = (i); \ - static const int __ia64_atomic_p = __ia64_atomic_const(i); \ - __ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) : \ - ia64_atomic_add(__i, v); \ + int __ia64_aar_i = (i); \ + __ia64_atomic_const(i) \ + ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ + : ia64_atomic_add(__ia64_aar_i, v); \ }) -#define atomic_sub_return(i, v) \ +#define atomic_sub_return(i,v) \ ({ \ - int __i = (i); \ - static const int __ia64_atomic_p = __ia64_atomic_const(i); \ - __ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) : \ - ia64_atomic_sub(__i, v); \ + int __ia64_asr_i = (i); \ + __ia64_atomic_const(i) \ + ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ + : ia64_atomic_sub(__ia64_asr_i, v); \ }) -#else -#define atomic_add_return(i, v) ia64_atomic_add(i, v) -#define atomic_sub_return(i, v) ia64_atomic_sub(i, v) -#endif #define atomic_fetch_add(i,v) \ ({ \ int __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq) \ : ia64_atomic_fetch_add(__ia64_aar_i, v); \ }) @@ -105,11 +102,7 @@ ATOMIC_OPS(sub, -) #define atomic_fetch_sub(i,v) \ ({ \ int __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq) \ : ia64_atomic_fetch_sub(__ia64_asr_i, v); \ }) @@ -170,11 +163,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_add_return(i,v) \ ({ \ long __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter) \ : ia64_atomic64_add(__ia64_aar_i, v); \ }) @@ -182,11 +171,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_sub_return(i,v) \ ({ \ long __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter) \ : ia64_atomic64_sub(__ia64_asr_i, v); \ }) @@ -194,11 +179,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_fetch_add(i,v) \ ({ \ long __ia64_aar_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_aar_i == 1) || (__ia64_aar_i == 4) \ - || (__ia64_aar_i == 8) || (__ia64_aar_i == 16) \ - || (__ia64_aar_i == -1) || (__ia64_aar_i == -4) \ - || (__ia64_aar_i == -8) || (__ia64_aar_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq) \ : ia64_atomic64_fetch_add(__ia64_aar_i, v); \ }) @@ -206,11 +187,7 @@ ATOMIC64_OPS(sub, -) #define atomic64_fetch_sub(i,v) \ ({ \ long __ia64_asr_i = (i); \ - (__builtin_constant_p(i) \ - && ( (__ia64_asr_i == 1) || (__ia64_asr_i == 4) \ - || (__ia64_asr_i == 8) || (__ia64_asr_i == 16) \ - || (__ia64_asr_i == -1) || (__ia64_asr_i == -4) \ - || (__ia64_asr_i == -8) || (__ia64_asr_i == -16))) \ + __ia64_atomic_const(i) \ ? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq) \ : ia64_atomic64_fetch_sub(__ia64_asr_i, v); \ }) diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 85bba43e7d5d..8b5b8e6bc9d9 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -117,7 +117,7 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]); - printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]); + printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]); printk(KERN_DEBUG "resources=%lx\n", resources[cpu]); #endif return size; @@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr, u64 virt_addr=simple_strtoull(buf, NULL, 16); int ret; - ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL); + ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL); if (ret<=0) { #ifdef ERR_INJ_DEBUG printk("Virtual address %lx is not existing.\n",virt_addr); diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py index 89f3a1480a63..c55276e31b6b 100644 --- a/arch/ia64/scripts/unwcheck.py +++ b/arch/ia64/scripts/unwcheck.py @@ -16,7 +16,7 @@ import re import sys if len(sys.argv) != 2: - print "Usage: %s FILE" % sys.argv[0] + print("Usage: %s FILE" % sys.argv[0]) sys.exit(2) readelf = os.getenv("READELF", "readelf") @@ -29,7 +29,7 @@ def check_func (func, slots, rlen_sum): global num_errors num_errors += 1 if not func: func = "[%#x-%#x]" % (start, end) - print "ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum) + print("ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum)) return num_funcs = 0 @@ -43,23 +43,23 @@ for line in os.popen("%s -u %s" % (readelf, sys.argv[1])): check_func(func, slots, rlen_sum) func = m.group(1) - start = long(m.group(2), 16) - end = long(m.group(3), 16) + start = int(m.group(2), 16) + end = int(m.group(3), 16) slots = 3 * (end - start) / 16 - rlen_sum = 0L + rlen_sum = 0 num_funcs += 1 else: m = rlen_pattern.match(line) if m: - rlen_sum += long(m.group(1)) + rlen_sum += int(m.group(1)) check_func(func, slots, rlen_sum) if num_errors == 0: - print "No errors detected in %u functions." % num_funcs + print("No errors detected in %u functions." % num_funcs) else: if num_errors > 1: err="errors" else: err="error" - print "%u %s detected in %u functions." % (num_errors, err, num_funcs) + print("%u %s detected in %u functions." % (num_errors, err, num_funcs)) sys.exit(1) diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 4f798aa671dd..3817a3e2146c 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -24,6 +24,7 @@ config MICROBLAZE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER + select NO_BOOTMEM select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE diff --git a/arch/microblaze/Kconfig.platform b/arch/microblaze/Kconfig.platform index 6996f397c16c..f7f1739c11b9 100644 --- a/arch/microblaze/Kconfig.platform +++ b/arch/microblaze/Kconfig.platform @@ -8,7 +8,6 @@ menu "Platform options" config OPT_LIB_FUNCTION bool "Optimalized lib function" - depends on CPU_LITTLE_ENDIAN default y help Allows turn on optimalized library function (memcpy and memmove). @@ -21,6 +20,7 @@ config OPT_LIB_FUNCTION config OPT_LIB_ASM bool "Optimalized lib function ASM" depends on OPT_LIB_FUNCTION && (XILINX_MICROBLAZE0_USE_BARREL = 1) + depends on CPU_BIG_ENDIAN default n help Allows turn on optimalized library function (memcpy and memmove). diff --git a/arch/microblaze/include/asm/setup.h b/arch/microblaze/include/asm/setup.h index be84a4d3917f..7c968c1d1729 100644 --- a/arch/microblaze/include/asm/setup.h +++ b/arch/microblaze/include/asm/setup.h @@ -44,7 +44,6 @@ void machine_shutdown(void); void machine_halt(void); void machine_power_off(void); -extern void *alloc_maybe_bootmem(size_t size, gfp_t mask); extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); # endif /* __ASSEMBLY__ */ diff --git a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S index 62021d7e249e..fdc48bb065d8 100644 --- a/arch/microblaze/lib/fastcopy.S +++ b/arch/microblaze/lib/fastcopy.S @@ -29,10 +29,6 @@ * between mem locations with size of xfer spec'd in bytes */ -#ifdef __MICROBLAZEEL__ -#error Microblaze LE not support ASM optimized lib func. Disable OPT_LIB_ASM. -#endif - #include <linux/linkage.h> .text .globl memcpy diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 434639f9a3a6..df6de7ccdc2e 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -32,9 +32,6 @@ int mem_init_done; #ifndef CONFIG_MMU unsigned int __page_offset; EXPORT_SYMBOL(__page_offset); - -#else -static int init_bootmem_done; #endif /* CONFIG_MMU */ char *klimit = _end; @@ -117,7 +114,6 @@ static void __init paging_init(void) void __init setup_memory(void) { - unsigned long map_size; struct memblock_region *reg; #ifndef CONFIG_MMU @@ -174,17 +170,6 @@ void __init setup_memory(void) pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn); pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn); - /* - * Find an area to use for the bootmem bitmap. - * We look for the first area which is at least - * 128kB in length (128kB is enough for a bitmap - * for 4GB of memory, using 4kB pages), plus 1 page - * (in case the address isn't page-aligned). - */ - map_size = init_bootmem_node(NODE_DATA(0), - PFN_UP(TOPHYS((u32)klimit)), min_low_pfn, max_low_pfn); - memblock_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size); - /* Add active regions with valid PFNs */ for_each_memblock(memory, reg) { unsigned long start_pfn, end_pfn; @@ -196,32 +181,9 @@ void __init setup_memory(void) &memblock.memory, 0); } - /* free bootmem is whole main memory */ - free_bootmem_with_active_regions(0, max_low_pfn); - - /* reserve allocate blocks */ - for_each_memblock(reserved, reg) { - unsigned long top = reg->base + reg->size - 1; - - pr_debug("reserved - 0x%08x-0x%08x, %lx, %lx\n", - (u32) reg->base, (u32) reg->size, top, - memory_start + lowmem_size - 1); - - if (top <= (memory_start + lowmem_size - 1)) { - reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); - } else if (reg->base < (memory_start + lowmem_size - 1)) { - unsigned long trunc_size = memory_start + lowmem_size - - reg->base; - reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT); - } - } - /* XXX need to clip this if using highmem? */ sparse_memory_present_with_active_regions(0); -#ifdef CONFIG_MMU - init_bootmem_done = 1; -#endif paging_init(); } @@ -398,30 +360,16 @@ asmlinkage void __init mmu_init(void) /* This is only called until mem_init is done. */ void __init *early_get_page(void) { - void *p; - if (init_bootmem_done) { - p = alloc_bootmem_pages(PAGE_SIZE); - } else { - /* - * Mem start + kernel_tlb -> here is limit - * because of mem mapping from head.S - */ - p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, - memory_start + kernel_tlb)); - } - return p; + /* + * Mem start + kernel_tlb -> here is limit + * because of mem mapping from head.S + */ + return __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, + memory_start + kernel_tlb)); } #endif /* CONFIG_MMU */ -void * __ref alloc_maybe_bootmem(size_t size, gfp_t mask) -{ - if (mem_init_done) - return kmalloc(size, mask); - else - return alloc_bootmem(size); -} - void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) { void *p; diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c index 9ab48ff80c1c..6d11ae581ea7 100644 --- a/arch/mips/ath25/board.c +++ b/arch/mips/ath25/board.c @@ -135,6 +135,8 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size) } board_data = kzalloc(BOARD_CONFIG_BUFSZ, GFP_KERNEL); + if (!board_data) + goto error; ath25_board.config = (struct ath25_boarddata *)board_data; memcpy_fromio(board_data, bcfg, 0x100); if (broken_boarddata) { diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 5b3a3f6a9ad3..d99f5242169e 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2277,6 +2277,8 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node, } host_data = kzalloc(sizeof(*host_data), GFP_KERNEL); + if (!host_data) + return -ENOMEM; raw_spin_lock_init(&host_data->lock); addr = of_get_address(ciu_node, 0, NULL, NULL); diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 9d41732a9146..159e83add4bb 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -168,11 +168,11 @@ static void bmips_prepare_cpus(unsigned int max_cpus) return; } - if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU, - "smp_ipi0", NULL)) + if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL)) panic("Can't request IPI0 interrupt"); - if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU, - "smp_ipi1", NULL)) + if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, + IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL)) panic("Can't request IPI1 interrupt"); } diff --git a/arch/mips/lantiq/Kconfig b/arch/mips/lantiq/Kconfig index 692ae85a3e3d..8e3a1fc2bc39 100644 --- a/arch/mips/lantiq/Kconfig +++ b/arch/mips/lantiq/Kconfig @@ -13,6 +13,8 @@ choice config SOC_AMAZON_SE bool "Amazon SE" select SOC_TYPE_XWAY + select MFD_SYSCON + select MFD_CORE config SOC_XWAY bool "XWAY" diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 52500d3b7004..e0af39b33e28 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -549,9 +549,9 @@ void __init ltq_soc_init(void) clkdev_add_static(ltq_ar9_cpu_hz(), ltq_ar9_fpi_hz(), ltq_ar9_fpi_hz(), CLOCK_250M); clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P); - clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0); + clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM); clkdev_add_pmu("1f203034.usb2-phy", "phy", 1, 0, PMU_USB1_P); - clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1); + clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1 | PMU_AHBM); clkdev_add_pmu("1e180000.etop", "switch", 1, 0, PMU_SWITCH); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); @@ -560,7 +560,7 @@ void __init ltq_soc_init(void) } else { clkdev_add_static(ltq_danube_cpu_hz(), ltq_danube_fpi_hz(), ltq_danube_fpi_hz(), ltq_danube_pp32_hz()); - clkdev_add_pmu("1f203018.usb2-phy", "ctrl", 1, 0, PMU_USB0); + clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM); clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index bc2fdbfa8223..72af0c183969 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -7,6 +7,8 @@ choice config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select CEVT_R4K select CSRC_R4K select SYS_HAS_CPU_LOONGSON2E @@ -33,6 +35,8 @@ config LEMOTE_FULOONG2E config LEMOTE_MACH2F bool "Lemote Loongson 2F family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select BOARD_SCACHE select BOOT_ELF32 select CEVT_R4K if ! MIPS_EXTERNAL_TIMER @@ -62,6 +66,8 @@ config LEMOTE_MACH2F config LOONGSON_MACH3X bool "Generic Loongson 3 family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select GENERIC_ISA_DMA_SUPPORT_BROKEN select BOOT_ELF32 select BOARD_SCACHE diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c index 1b274742077d..d2718de60b9b 100644 --- a/arch/mips/ralink/mt7621.c +++ b/arch/mips/ralink/mt7621.c @@ -170,6 +170,28 @@ void prom_soc_init(struct ralink_soc_info *soc_info) u32 n1; u32 rev; + /* Early detection of CMP support */ + mips_cm_probe(); + mips_cpc_probe(); + + if (mips_cps_numiocu(0)) { + /* + * mips_cm_probe() wipes out bootloader + * config for CM regions and we have to configure them + * again. This SoC cannot talk to pamlbus devices + * witout proper iocu region set up. + * + * FIXME: it would be better to do this with values + * from DT, but we need this very early because + * without this we cannot talk to pretty much anything + * including serial. + */ + write_gcr_reg0_base(MT7621_PALMBUS_BASE); + write_gcr_reg0_mask(~MT7621_PALMBUS_SIZE | + CM_GCR_REGn_MASK_CMTGT_IOCU0); + __sync(); + } + n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); @@ -194,26 +216,6 @@ void prom_soc_init(struct ralink_soc_info *soc_info) rt2880_pinmux_data = mt7621_pinmux_data; - /* Early detection of CMP support */ - mips_cm_probe(); - mips_cpc_probe(); - - if (mips_cps_numiocu(0)) { - /* - * mips_cm_probe() wipes out bootloader - * config for CM regions and we have to configure them - * again. This SoC cannot talk to pamlbus devices - * witout proper iocu region set up. - * - * FIXME: it would be better to do this with values - * from DT, but we need this very early because - * without this we cannot talk to pretty much anything - * including serial. - */ - write_gcr_reg0_base(MT7621_PALMBUS_BASE); - write_gcr_reg0_mask(~MT7621_PALMBUS_SIZE | - CM_GCR_REGn_MASK_CMTGT_IOCU0); - } if (!register_cps_smp_ops()) return; diff --git a/arch/mips/ralink/reset.c b/arch/mips/ralink/reset.c index 64543d66e76b..e9531fea23a2 100644 --- a/arch/mips/ralink/reset.c +++ b/arch/mips/ralink/reset.c @@ -96,16 +96,9 @@ static void ralink_restart(char *command) unreachable(); } -static void ralink_halt(void) -{ - local_irq_disable(); - unreachable(); -} - static int __init mips_reboot_setup(void) { _machine_restart = ralink_restart; - _machine_halt = ralink_halt; return 0; } diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 3742508cc534..bd5ce31936f5 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -26,6 +26,7 @@ void flush_user_icache_range_asm(unsigned long, unsigned long); void flush_kernel_icache_range_asm(unsigned long, unsigned long); void flush_user_dcache_range_asm(unsigned long, unsigned long); void flush_kernel_dcache_range_asm(unsigned long, unsigned long); +void purge_kernel_dcache_range_asm(unsigned long, unsigned long); void flush_kernel_dcache_page_asm(void *); void flush_kernel_icache_page(void *); diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 0e6ab6e4a4e9..2dbe5580a1a4 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -316,6 +316,8 @@ extern int _parisc_requires_coherency; #define parisc_requires_coherency() (0) #endif +extern int running_on_qemu; + #endif /* __ASSEMBLY__ */ #endif /* __ASM_PARISC_PROCESSOR_H */ diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 19c0c141bc3f..e3b45546d589 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -465,10 +465,10 @@ EXPORT_SYMBOL(copy_user_page); int __flush_tlb_range(unsigned long sid, unsigned long start, unsigned long end) { - unsigned long flags, size; + unsigned long flags; - size = (end - start); - if (size >= parisc_tlb_flush_threshold) { + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + end - start >= parisc_tlb_flush_threshold) { flush_tlb_all(); return 1; } @@ -539,13 +539,12 @@ void flush_cache_mm(struct mm_struct *mm) struct vm_area_struct *vma; pgd_t *pgd; - /* Flush the TLB to avoid speculation if coherency is required. */ - if (parisc_requires_coherency()) - flush_tlb_all(); - /* Flushing the whole cache on each cpu takes forever on rp3440, etc. So, avoid it if the mm isn't too big. */ - if (mm_total_size(mm) >= parisc_cache_flush_threshold) { + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + mm_total_size(mm) >= parisc_cache_flush_threshold) { + if (mm->context) + flush_tlb_all(); flush_cache_all(); return; } @@ -553,9 +552,9 @@ void flush_cache_mm(struct mm_struct *mm) if (mm->context == mfsp(3)) { for (vma = mm->mmap; vma; vma = vma->vm_next) { flush_user_dcache_range_asm(vma->vm_start, vma->vm_end); - if ((vma->vm_flags & VM_EXEC) == 0) - continue; - flush_user_icache_range_asm(vma->vm_start, vma->vm_end); + if (vma->vm_flags & VM_EXEC) + flush_user_icache_range_asm(vma->vm_start, vma->vm_end); + flush_tlb_range(vma, vma->vm_start, vma->vm_end); } return; } @@ -573,6 +572,8 @@ void flush_cache_mm(struct mm_struct *mm) pfn = pte_pfn(*ptep); if (!pfn_valid(pfn)) continue; + if (unlikely(mm->context)) + flush_tlb_page(vma, addr); __flush_cache_page(vma, addr, PFN_PHYS(pfn)); } } @@ -581,30 +582,45 @@ void flush_cache_mm(struct mm_struct *mm) void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - BUG_ON(!vma->vm_mm->context); - - /* Flush the TLB to avoid speculation if coherency is required. */ - if (parisc_requires_coherency()) - flush_tlb_range(vma, start, end); + pgd_t *pgd; + unsigned long addr; - if ((end - start) >= parisc_cache_flush_threshold - || vma->vm_mm->context != mfsp(3)) { + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + end - start >= parisc_cache_flush_threshold) { + if (vma->vm_mm->context) + flush_tlb_range(vma, start, end); flush_cache_all(); return; } - flush_user_dcache_range_asm(start, end); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(start, end); + if (vma->vm_mm->context == mfsp(3)) { + flush_user_dcache_range_asm(start, end); + if (vma->vm_flags & VM_EXEC) + flush_user_icache_range_asm(start, end); + flush_tlb_range(vma, start, end); + return; + } + + pgd = vma->vm_mm->pgd; + for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) { + unsigned long pfn; + pte_t *ptep = get_ptep(pgd, addr); + if (!ptep) + continue; + pfn = pte_pfn(*ptep); + if (pfn_valid(pfn)) { + if (unlikely(vma->vm_mm->context)) + flush_tlb_page(vma, addr); + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + } + } } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - BUG_ON(!vma->vm_mm->context); - if (pfn_valid(pfn)) { - if (parisc_requires_coherency()) + if (likely(vma->vm_mm->context)) flush_tlb_page(vma, vmaddr); __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } @@ -613,21 +629,33 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; + unsigned long end = start + size; - if ((unsigned long)size > parisc_cache_flush_threshold) + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + (unsigned long)size >= parisc_cache_flush_threshold) { + flush_tlb_kernel_range(start, end); flush_data_cache(); - else - flush_kernel_dcache_range_asm(start, start + size); + return; + } + + flush_kernel_dcache_range_asm(start, end); + flush_tlb_kernel_range(start, end); } EXPORT_SYMBOL(flush_kernel_vmap_range); void invalidate_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; + unsigned long end = start + size; - if ((unsigned long)size > parisc_cache_flush_threshold) + if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && + (unsigned long)size >= parisc_cache_flush_threshold) { + flush_tlb_kernel_range(start, end); flush_data_cache(); - else - flush_kernel_dcache_range_asm(start, start + size); + return; + } + + purge_kernel_dcache_range_asm(start, end); + flush_tlb_kernel_range(start, end); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index bbbe360b458f..fbb4e43fda05 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -138,6 +138,16 @@ $pgt_fill_loop: std %dp,0x18(%r10) #endif +#ifdef CONFIG_64BIT + /* Get PDCE_PROC for monarch CPU. */ +#define MEM_PDC_LO 0x388 +#define MEM_PDC_HI 0x35C + ldw MEM_PDC_LO(%r0),%r3 + ldw MEM_PDC_HI(%r0),%r10 + depd %r10, 31, 32, %r3 /* move to upper word */ +#endif + + #ifdef CONFIG_SMP /* Set the smp rendezvous address into page zero. ** It would be safer to do this in init_smp_config() but @@ -196,12 +206,6 @@ common_stext: ** Someday, palo might not do this for the Monarch either. */ 2: -#define MEM_PDC_LO 0x388 -#define MEM_PDC_HI 0x35C - ldw MEM_PDC_LO(%r0),%r3 - ldw MEM_PDC_HI(%r0),%r6 - depd %r6, 31, 32, %r3 /* move to upper word */ - mfctl %cr30,%r6 /* PCX-W2 firmware bug */ ldo PDC_PSW(%r0),%arg0 /* 21 */ @@ -268,6 +272,8 @@ $install_iva: aligned_rfi: pcxt_ssm_bug + copy %r3, %arg0 /* PDCE_PROC for smp_callin() */ + rsm PSW_SM_QUIET,%r0 /* off troublesome PSW bits */ /* Don't need NOPs, have 8 compliant insn before rfi */ diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 2d40c4ff3f69..67b0f7532e83 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -1110,6 +1110,28 @@ ENTRY_CFI(flush_kernel_dcache_range_asm) .procend ENDPROC_CFI(flush_kernel_dcache_range_asm) +ENTRY_CFI(purge_kernel_dcache_range_asm) + .proc + .callinfo NO_CALLS + .entry + + ldil L%dcache_stride, %r1 + ldw R%dcache_stride(%r1), %r23 + ldo -1(%r23), %r21 + ANDCM %r26, %r21, %r26 + +1: cmpb,COND(<<),n %r26, %r25,1b + pdc,m %r23(%r26) + + sync + syncdma + bv %r0(%r2) + nop + .exit + + .procend +ENDPROC_CFI(purge_kernel_dcache_range_asm) + ENTRY_CFI(flush_user_icache_range_asm) .proc .callinfo NO_CALLS diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 30c28ab14540..4065b5e48c9d 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -292,10 +292,15 @@ smp_cpu_init(int cpunum) * Slaves start using C here. Indirectly called from smp_slave_stext. * Do what start_kernel() and main() do for boot strap processor (aka monarch) */ -void __init smp_callin(void) +void __init smp_callin(unsigned long pdce_proc) { int slave_id = cpu_now_booting; +#ifdef CONFIG_64BIT + WARN_ON(((unsigned long)(PAGE0->mem_pdc_hi) << 32 + | PAGE0->mem_pdc) != pdce_proc); +#endif + smp_cpu_init(slave_id); preempt_disable(); diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 4b8fd6dc22da..f7e684560186 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -76,10 +76,10 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) next_tick = cpuinfo->it_value; /* Calculate how many ticks have elapsed. */ + now = mfctl(16); do { ++ticks_elapsed; next_tick += cpt; - now = mfctl(16); } while (next_tick - now > cpt); /* Store (in CR16 cycles) up to when we are accounting right now. */ @@ -103,16 +103,17 @@ irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id) * if one or the other wrapped. If "now" is "bigger" we'll end up * with a very large unsigned number. */ - while (next_tick - mfctl(16) > cpt) + now = mfctl(16); + while (next_tick - now > cpt) next_tick += cpt; /* Program the IT when to deliver the next interrupt. * Only bottom 32-bits of next_tick are writable in CR16! * Timer interrupt will be delivered at least a few hundred cycles - * after the IT fires, so if we are too close (<= 500 cycles) to the + * after the IT fires, so if we are too close (<= 8000 cycles) to the * next cycle, simply skip it. */ - if (next_tick - mfctl(16) <= 500) + if (next_tick - now <= 8000) next_tick += cpt; mtctl(next_tick, 16); @@ -248,7 +249,7 @@ static int __init init_cr16_clocksource(void) * different sockets, so mark them unstable and lower rating on * multi-socket SMP systems. */ - if (num_online_cpus() > 1) { + if (num_online_cpus() > 1 && !running_on_qemu) { int cpu; unsigned long cpu0_loc; cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 48f41399fc0b..cab32ee824d2 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -629,7 +629,12 @@ void __init mem_init(void) #endif mem_init_print_info(NULL); -#ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */ + +#if 0 + /* + * Do not expose the virtual kernel memory layout to userspace. + * But keep code for debugging purposes. + */ printk("virtual kernel memory layout:\n" " vmalloc : 0x%px - 0x%px (%4ld MB)\n" " memory : 0x%px - 0x%px (%4ld MB)\n" diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index ef6549e57157..26d5d2a5b8e9 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -101,7 +101,8 @@ $(addprefix $(obj)/,$(zlib-y)): \ libfdt := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c libfdtheader := fdt.h libfdt.h libfdt_internal.h -$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \ +$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o \ + treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \ $(addprefix $(obj)/,$(libfdtheader)) src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index d22c41c26bb3..acf4b2e0530c 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -874,7 +874,6 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = { .mmu = 0, .hash_ext = 0, .radix_ext = 0, - .byte22 = 0, }, /* option vector 6: IBM PAPR hints */ diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0c854816e653..5cb4e4687107 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -195,6 +195,12 @@ static void kvmppc_pte_free(pte_t *ptep) kmem_cache_free(kvm_pte_cache, ptep); } +/* Like pmd_huge() and pmd_large(), but works regardless of config options */ +static inline int pmd_is_leaf(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_PTE); +} + static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, unsigned int level, unsigned long mmu_seq) { @@ -219,7 +225,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, else new_pmd = pmd_alloc_one(kvm->mm, gpa); - if (level == 0 && !(pmd && pmd_present(*pmd))) + if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd))) new_ptep = kvmppc_pte_alloc(); /* Check if we might have been invalidated; let the guest retry if so */ @@ -244,12 +250,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa, new_pmd = NULL; } pmd = pmd_offset(pud, gpa); - if (pmd_large(*pmd)) { - /* Someone else has instantiated a large page here; retry */ - ret = -EAGAIN; - goto out_unlock; - } - if (level == 1 && !pmd_none(*pmd)) { + if (pmd_is_leaf(*pmd)) { + unsigned long lgpa = gpa & PMD_MASK; + + /* + * If we raced with another CPU which has just put + * a 2MB pte in after we saw a pte page, try again. + */ + if (level == 0 && !new_ptep) { + ret = -EAGAIN; + goto out_unlock; + } + /* Valid 2MB page here already, remove it */ + old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd), + ~0UL, 0, lgpa, PMD_SHIFT); + kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT); + if (old & _PAGE_DIRTY) { + unsigned long gfn = lgpa >> PAGE_SHIFT; + struct kvm_memory_slot *memslot; + memslot = gfn_to_memslot(kvm, gfn); + if (memslot && memslot->dirty_bitmap) + kvmppc_update_dirty_map(memslot, + gfn, PMD_SIZE); + } + } else if (level == 1 && !pmd_none(*pmd)) { /* * There's a page table page here, but we wanted * to install a large page. Tell the caller and let @@ -412,28 +436,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } else { page = pages[0]; pfn = page_to_pfn(page); - if (PageHuge(page)) { - page = compound_head(page); - pte_size <<= compound_order(page); + if (PageCompound(page)) { + pte_size <<= compound_order(compound_head(page)); /* See if we can insert a 2MB large-page PTE here */ if (pte_size >= PMD_SIZE && - (gpa & PMD_MASK & PAGE_MASK) == - (hva & PMD_MASK & PAGE_MASK)) { + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { level = 1; pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); } } /* See if we can provide write access */ if (writing) { - /* - * We assume gup_fast has set dirty on the host PTE. - */ pgflags |= _PAGE_WRITE; } else { local_irq_save(flags); ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL); - if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) + if (ptep && pte_write(*ptep)) pgflags |= _PAGE_WRITE; local_irq_restore(flags); } @@ -459,18 +479,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte = pfn_pte(pfn, __pgprot(pgflags)); ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); } - if (ret == 0 || ret == -EAGAIN) - ret = RESUME_GUEST; if (page) { - /* - * We drop pages[0] here, not page because page might - * have been set to the head page of a compound, but - * we have to drop the reference on the correct tail - * page to match the get inside gup() - */ - put_page(pages[0]); + if (!ret && (pgflags & _PAGE_WRITE)) + set_page_dirty_lock(page); + put_page(page); } + + if (ret == 0 || ret == -EAGAIN) + ret = RESUME_GUEST; return ret; } @@ -644,7 +661,7 @@ void kvmppc_free_radix(struct kvm *kvm) continue; pmd = pmd_offset(pud, 0); for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) { - if (pmd_huge(*pmd)) { + if (pmd_is_leaf(*pmd)) { pmd_clear(pmd); continue; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 89707354c2ef..9cb9448163c4 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2885,7 +2885,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ trace_hardirqs_on(); - guest_enter(); + guest_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); @@ -2893,8 +2893,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) srcu_read_unlock(&vc->kvm->srcu, srcu_idx); - guest_exit(); - trace_hardirqs_off(); set_irq_happened(trap); @@ -2937,6 +2935,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); local_irq_enable(); + guest_exit(); /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { @@ -3656,15 +3655,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto up_out; psize = vma_kernel_pagesize(vma); - porder = __ilog2(psize); up_read(¤t->mm->mmap_sem); /* We can handle 4k, 64k or 16M pages in the VRMA */ - err = -EINVAL; - if (!(psize == 0x1000 || psize == 0x10000 || - psize == 0x1000000)) - goto out_srcu; + if (psize >= 0x1000000) + psize = 0x1000000; + else if (psize >= 0x10000) + psize = 0x10000; + else + psize = 0x1000; + porder = __ilog2(psize); senc = slb_pgsize_encoding(psize); kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T | diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index f31f357b8c5a..d33264697a31 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -320,7 +320,6 @@ kvm_novcpu_exit: stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -1220,6 +1219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) secondary_too_late: li r12, 0 + stw r12, STACK_SLOT_TRAP(r1) cmpdi r4, 0 beq 11f stw r12, VCPU_TRAP(r4) @@ -1558,12 +1558,12 @@ mc_cont: 3: stw r5,VCPU_SLB_MAX(r9) guest_bypass: + stw r12, STACK_SLOT_TRAP(r1) mr r3, r12 /* Increment exit count, poke other threads to exit */ bl kvmhv_commence_exit nop ld r9, HSTATE_KVM_VCPU(r13) - lwz r12, VCPU_TRAP(r9) /* Stop others sending VCPU interrupts to this physical CPU */ li r0, -1 @@ -1898,6 +1898,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. + * Here STACK_SLOT_TRAP(r1) contains the trap number. */ kvmhv_switch_to_host: /* Secondary threads wait for primary to do partition switch */ @@ -1950,12 +1951,12 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* If HMI, call kvmppc_realmode_hmi_handler() */ + lwz r12, STACK_SLOT_TRAP(r1) cmpwi r12, BOOK3S_INTERRUPT_HMI bne 27f bl kvmppc_realmode_hmi_handler nop cmpdi r3, 0 - li r12, BOOK3S_INTERRUPT_HMI /* * At this point kvmppc_realmode_hmi_handler may have resync-ed * the TB, and if it has, we must not subtract the guest timebase @@ -2008,10 +2009,8 @@ BEGIN_FTR_SECTION lwz r8, KVM_SPLIT_DO_RESTORE(r3) cmpwi r8, 0 beq 47f - stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_p9_restore_lpcr nop - lwz r12, STACK_SLOT_TRAP(r1) b 48f 47: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) @@ -2049,6 +2048,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) + lwz r12, STACK_SLOT_TRAP(r1) /* return trap # in r12 */ ld r0, SFS+PPC_LR_STKOFF(r1) addi r1, r1, SFS mtlr r0 diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 403e642c78f5..52c205373986 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1345,7 +1345,7 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu, int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian) { - enum emulation_result emulated; + enum emulation_result emulated = EMULATE_DONE; while (vcpu->arch.mmio_vmx_copy_nums) { emulated = __kvmppc_handle_load(run, vcpu, rt, 8, @@ -1608,7 +1608,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_sigset_deactivate(vcpu); +#ifdef CONFIG_ALTIVEC out: +#endif vcpu_put(vcpu); return r; } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0a34b0cec7b7..0ef3d9580e98 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -240,6 +240,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * goto out; */ PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)); + PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31); PPC_CMPLW(b2p_index, b2p[TMP_REG_1]); PPC_BCC(COND_GE, out); diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index c0319cbf1eec..5510366d169a 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -34,9 +34,9 @@ #define wmb() RISCV_FENCE(ow,ow) /* These barriers do not need to enforce ordering on devices, just memory. */ -#define smp_mb() RISCV_FENCE(rw,rw) -#define smp_rmb() RISCV_FENCE(r,r) -#define smp_wmb() RISCV_FENCE(w,w) +#define __smp_mb() RISCV_FENCE(rw,rw) +#define __smp_rmb() RISCV_FENCE(r,r) +#define __smp_wmb() RISCV_FENCE(w,w) /* * This is a very specific barrier: it's currently only used in two places in diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 65154eaa3714..6c8ce15cde7b 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -63,6 +63,7 @@ static inline int init_new_context(struct task_struct *tsk, _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; /* pgd_alloc() did not account this pmd */ mm_inc_nr_pmds(mm); + mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 13a133a6015c..a5621ea6d123 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <asm/cache.h> #include <asm/ctl_reg.h> +#include <asm/dwarf.h> #include <asm/errno.h> #include <asm/ptrace.h> #include <asm/thread_info.h> @@ -230,7 +231,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) .hidden \name .type \name,@function \name: - .cfi_startproc + CFI_STARTPROC #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES exrl 0,0f #else @@ -239,7 +240,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) #endif j . 0: br \reg - .cfi_endproc + CFI_ENDPROC .endm GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1 @@ -426,13 +427,13 @@ ENTRY(system_call) UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP stmg %r0,%r7,__PT_R0(%r11) - # clear user controlled register to prevent speculative use - xgr %r0,%r0 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) .Lsysc_do_svc: + # clear user controlled register to prevent speculative use + xgr %r0,%r0 # load address of system call table lg %r10,__THREAD_sysc_table(%r13,%r12) llgh %r8,__PT_INT_CODE+2(%r11) @@ -1439,6 +1440,7 @@ cleanup_critical: stg %r15,__LC_SYSTEM_TIMER 0: # update accounting time stamp mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP # set up saved register r11 lg %r15,__LC_KERNEL_STACK la %r9,STACK_FRAME_OVERHEAD(%r15) diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index 69d7fcf48158..9aff72d3abda 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -2,8 +2,8 @@ #include <linux/module.h> #include <asm/nospec-branch.h> -int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF); -int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL); +int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF); +int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL); static int __init nospectre_v2_setup_early(char *str) { diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 9c7d70715862..07c6e81163bf 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -22,22 +22,6 @@ #include "trace.h" #include "trace-s390.h" - -static const intercept_handler_t instruction_handlers[256] = { - [0x01] = kvm_s390_handle_01, - [0x82] = kvm_s390_handle_lpsw, - [0x83] = kvm_s390_handle_diag, - [0xaa] = kvm_s390_handle_aa, - [0xae] = kvm_s390_handle_sigp, - [0xb2] = kvm_s390_handle_b2, - [0xb6] = kvm_s390_handle_stctl, - [0xb7] = kvm_s390_handle_lctl, - [0xb9] = kvm_s390_handle_b9, - [0xe3] = kvm_s390_handle_e3, - [0xe5] = kvm_s390_handle_e5, - [0xeb] = kvm_s390_handle_eb, -}; - u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; @@ -129,16 +113,39 @@ static int handle_validity(struct kvm_vcpu *vcpu) static int handle_instruction(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - vcpu->stat.exit_instruction++; trace_kvm_s390_intercept_instruction(vcpu, vcpu->arch.sie_block->ipa, vcpu->arch.sie_block->ipb); - handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + + switch (vcpu->arch.sie_block->ipa >> 8) { + case 0x01: + return kvm_s390_handle_01(vcpu); + case 0x82: + return kvm_s390_handle_lpsw(vcpu); + case 0x83: + return kvm_s390_handle_diag(vcpu); + case 0xaa: + return kvm_s390_handle_aa(vcpu); + case 0xae: + return kvm_s390_handle_sigp(vcpu); + case 0xb2: + return kvm_s390_handle_b2(vcpu); + case 0xb6: + return kvm_s390_handle_stctl(vcpu); + case 0xb7: + return kvm_s390_handle_lctl(vcpu); + case 0xb9: + return kvm_s390_handle_b9(vcpu); + case 0xe3: + return kvm_s390_handle_e3(vcpu); + case 0xe5: + return kvm_s390_handle_e5(vcpu); + case 0xeb: + return kvm_s390_handle_eb(vcpu); + default: + return -EOPNOTSUPP; + } } static int inject_prog_on_prog_intercept(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index aabf46f5f883..b04616b57a94 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -169,8 +169,15 @@ static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu) static int ckc_irq_pending(struct kvm_vcpu *vcpu) { - if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm)) + const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm); + const u64 ckc = vcpu->arch.sie_block->ckc; + + if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) { + if ((s64)ckc >= (s64)now) + return 0; + } else if (ckc >= now) { return 0; + } return ckc_interrupts_enabled(vcpu); } @@ -187,12 +194,6 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) return kvm_s390_get_cpu_timer(vcpu) >> 63; } -static inline int is_ioirq(unsigned long irq_type) -{ - return ((irq_type >= IRQ_PEND_IO_ISC_7) && - (irq_type <= IRQ_PEND_IO_ISC_0)); -} - static uint64_t isc_to_isc_bits(int isc) { return (0x80 >> isc) << 24; @@ -236,10 +237,15 @@ static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gis return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); } -static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) +static inline unsigned long pending_irqs_no_gisa(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs | + vcpu->arch.local_int.pending_irqs; +} + +static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) +{ + return pending_irqs_no_gisa(vcpu) | kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7; } @@ -337,7 +343,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) { - if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK)) + if (!(pending_irqs_no_gisa(vcpu) & IRQ_PEND_IO_MASK)) return; else if (psw_ioint_disabled(vcpu)) kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT); @@ -1011,24 +1017,6 @@ out: return rc; } -typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); - -static const deliver_irq_t deliver_irq_funcs[] = { - [IRQ_PEND_MCHK_EX] = __deliver_machine_check, - [IRQ_PEND_MCHK_REP] = __deliver_machine_check, - [IRQ_PEND_PROG] = __deliver_prog, - [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, - [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, - [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc, - [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer, - [IRQ_PEND_RESTART] = __deliver_restart, - [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, - [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, - [IRQ_PEND_EXT_SERVICE] = __deliver_service, - [IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done, - [IRQ_PEND_VIRTIO] = __deliver_virtio, -}; - /* Check whether an external call is pending (deliverable or not) */ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { @@ -1066,13 +1054,19 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) static u64 __calculate_sltime(struct kvm_vcpu *vcpu) { - u64 now, cputm, sltime = 0; + const u64 now = kvm_s390_get_tod_clock_fast(vcpu->kvm); + const u64 ckc = vcpu->arch.sie_block->ckc; + u64 cputm, sltime = 0; if (ckc_interrupts_enabled(vcpu)) { - now = kvm_s390_get_tod_clock_fast(vcpu->kvm); - sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now); - /* already expired or overflow? */ - if (!sltime || vcpu->arch.sie_block->ckc <= now) + if (vcpu->arch.sie_block->gcr[0] & 0x0020000000000000ul) { + if ((s64)now < (s64)ckc) + sltime = tod_to_ns((s64)ckc - (s64)now); + } else if (now < ckc) { + sltime = tod_to_ns(ckc - now); + } + /* already expired */ + if (!sltime) return 0; if (cpu_timer_interrupts_enabled(vcpu)) { cputm = kvm_s390_get_cpu_timer(vcpu); @@ -1192,7 +1186,6 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - deliver_irq_t func; int rc = 0; unsigned long irq_type; unsigned long irqs; @@ -1212,16 +1205,57 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) while ((irqs = deliverable_irqs(vcpu)) && !rc) { /* bits are in the reverse order of interrupt priority */ irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT); - if (is_ioirq(irq_type)) { + switch (irq_type) { + case IRQ_PEND_IO_ISC_0: + case IRQ_PEND_IO_ISC_1: + case IRQ_PEND_IO_ISC_2: + case IRQ_PEND_IO_ISC_3: + case IRQ_PEND_IO_ISC_4: + case IRQ_PEND_IO_ISC_5: + case IRQ_PEND_IO_ISC_6: + case IRQ_PEND_IO_ISC_7: rc = __deliver_io(vcpu, irq_type); - } else { - func = deliver_irq_funcs[irq_type]; - if (!func) { - WARN_ON_ONCE(func == NULL); - clear_bit(irq_type, &li->pending_irqs); - continue; - } - rc = func(vcpu); + break; + case IRQ_PEND_MCHK_EX: + case IRQ_PEND_MCHK_REP: + rc = __deliver_machine_check(vcpu); + break; + case IRQ_PEND_PROG: + rc = __deliver_prog(vcpu); + break; + case IRQ_PEND_EXT_EMERGENCY: + rc = __deliver_emergency_signal(vcpu); + break; + case IRQ_PEND_EXT_EXTERNAL: + rc = __deliver_external_call(vcpu); + break; + case IRQ_PEND_EXT_CLOCK_COMP: + rc = __deliver_ckc(vcpu); + break; + case IRQ_PEND_EXT_CPU_TIMER: + rc = __deliver_cpu_timer(vcpu); + break; + case IRQ_PEND_RESTART: + rc = __deliver_restart(vcpu); + break; + case IRQ_PEND_SET_PREFIX: + rc = __deliver_set_prefix(vcpu); + break; + case IRQ_PEND_PFAULT_INIT: + rc = __deliver_pfault_init(vcpu); + break; + case IRQ_PEND_EXT_SERVICE: + rc = __deliver_service(vcpu); + break; + case IRQ_PEND_PFAULT_DONE: + rc = __deliver_pfault_done(vcpu); + break; + case IRQ_PEND_VIRTIO: + rc = __deliver_virtio(vcpu); + break; + default: + WARN_ONCE(1, "Unknown pending irq type %ld", irq_type); + clear_bit(irq_type, &li->pending_irqs); } } @@ -1701,7 +1735,8 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT); break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); + if (!(type & KVM_S390_INT_IO_AI_MASK && kvm->arch.gisa)) + kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ba4c7092335a..339ac0964590 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -86,6 +86,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) }, { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, + { "deliver_io_interrupt", VCPU_STAT(deliver_io_int) }, { "exit_wait_state", VCPU_STAT(exit_wait_state) }, { "instruction_epsw", VCPU_STAT(instruction_epsw) }, { "instruction_gs", VCPU_STAT(instruction_gs) }, @@ -179,6 +180,28 @@ int kvm_arch_hardware_enable(void) static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); +static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta) +{ + u8 delta_idx = 0; + + /* + * The TOD jumps by delta, we have to compensate this by adding + * -delta to the epoch. + */ + delta = -delta; + + /* sign-extension - we're adding to signed values below */ + if ((s64)delta < 0) + delta_idx = -1; + + scb->epoch += delta; + if (scb->ecd & ECD_MEF) { + scb->epdx += delta_idx; + if (scb->epoch < delta) + scb->epdx += 1; + } +} + /* * This callback is executed during stop_machine(). All CPUs are therefore * temporarily stopped. In order not to change guest behavior, we have to @@ -194,13 +217,17 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { - kvm->arch.epoch -= *delta; kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu->arch.sie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.sie_block, *delta); + if (i == 0) { + kvm->arch.epoch = vcpu->arch.sie_block->epoch; + kvm->arch.epdx = vcpu->arch.sie_block->epdx; + } if (vcpu->arch.cputm_enabled) vcpu->arch.cputm_start += *delta; if (vcpu->arch.vsie_block) - vcpu->arch.vsie_block->epoch -= *delta; + kvm_clock_sync_scb(vcpu->arch.vsie_block, + *delta); } } return NOTIFY_OK; @@ -902,12 +929,9 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr) if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) return -EFAULT; - if (test_kvm_facility(kvm, 139)) - kvm_s390_set_tod_clock_ext(kvm, >od); - else if (gtod.epoch_idx == 0) - kvm_s390_set_tod_clock(kvm, gtod.tod); - else + if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx) return -EINVAL; + kvm_s390_set_tod_clock(kvm, >od); VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx", gtod.epoch_idx, gtod.tod); @@ -932,13 +956,14 @@ static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr) static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr) { - u64 gtod; + struct kvm_s390_vm_tod_clock gtod = { 0 }; - if (copy_from_user(>od, (void __user *)attr->addr, sizeof(gtod))) + if (copy_from_user(>od.tod, (void __user *)attr->addr, + sizeof(gtod.tod))) return -EFAULT; - kvm_s390_set_tod_clock(kvm, gtod); - VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod); + kvm_s390_set_tod_clock(kvm, >od); + VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod); return 0; } @@ -2122,6 +2147,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu) /* we still need the basic sca for the ipte control */ vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + return; } read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { @@ -2389,6 +2415,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) mutex_lock(&vcpu->kvm->lock); preempt_disable(); vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch; + vcpu->arch.sie_block->epdx = vcpu->kvm->arch.epdx; preempt_enable(); mutex_unlock(&vcpu->kvm->lock); if (!kvm_is_ucontrol(vcpu->kvm)) { @@ -3021,8 +3048,8 @@ retry: return 0; } -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod) +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod) { struct kvm_vcpu *vcpu; struct kvm_s390_tod_clock_ext htod; @@ -3034,10 +3061,12 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm, get_tod_clock_ext((char *)&htod); kvm->arch.epoch = gtod->tod - htod.tod; - kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; - - if (kvm->arch.epoch > gtod->tod) - kvm->arch.epdx -= 1; + kvm->arch.epdx = 0; + if (test_kvm_facility(kvm, 139)) { + kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx; + if (kvm->arch.epoch > gtod->tod) + kvm->arch.epdx -= 1; + } kvm_s390_vcpu_block_all(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -3050,22 +3079,6 @@ void kvm_s390_set_tod_clock_ext(struct kvm *kvm, mutex_unlock(&kvm->lock); } -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod) -{ - struct kvm_vcpu *vcpu; - int i; - - mutex_lock(&kvm->lock); - preempt_disable(); - kvm->arch.epoch = tod - get_tod_clock(); - kvm_s390_vcpu_block_all(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.sie_block->epoch = kvm->arch.epoch; - kvm_s390_vcpu_unblock_all(kvm); - preempt_enable(); - mutex_unlock(&kvm->lock); -} - /** * kvm_arch_fault_in_page - fault-in guest page if necessary * @vcpu: The corresponding virtual cpu diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index bd31b37b0e6f..f55ac0ef99ea 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -19,8 +19,6 @@ #include <asm/processor.h> #include <asm/sclp.h> -typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); - /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & ECB_TE)) #define TDB_FORMAT1 1 @@ -283,9 +281,8 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu); int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu); /* implemented in kvm-s390.c */ -void kvm_s390_set_tod_clock_ext(struct kvm *kvm, - const struct kvm_s390_vm_tod_clock *gtod); -void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod); +void kvm_s390_set_tod_clock(struct kvm *kvm, + const struct kvm_s390_vm_tod_clock *gtod); long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable); int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr); int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index c4c4e157c036..f0b4185158af 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -85,9 +85,10 @@ int kvm_s390_handle_e3(struct kvm_vcpu *vcpu) /* Handle SCK (SET CLOCK) interception */ static int handle_set_clock(struct kvm_vcpu *vcpu) { + struct kvm_s390_vm_tod_clock gtod = { 0 }; int rc; u8 ar; - u64 op2, val; + u64 op2; vcpu->stat.instruction_sck++; @@ -97,12 +98,12 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) op2 = kvm_s390_get_base_disp_s(vcpu, &ar); if (op2 & 7) /* Operand must be on a doubleword boundary */ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, op2, ar, &val, sizeof(val)); + rc = read_guest(vcpu, op2, ar, >od.tod, sizeof(gtod.tod)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", val); - kvm_s390_set_tod_clock(vcpu->kvm, val); + VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod); + kvm_s390_set_tod_clock(vcpu->kvm, >od); kvm_s390_set_psw_cc(vcpu, 0); return 0; @@ -795,55 +796,60 @@ out: return rc; } -static const intercept_handler_t b2_handlers[256] = { - [0x02] = handle_stidp, - [0x04] = handle_set_clock, - [0x10] = handle_set_prefix, - [0x11] = handle_store_prefix, - [0x12] = handle_store_cpu_address, - [0x14] = kvm_s390_handle_vsie, - [0x21] = handle_ipte_interlock, - [0x29] = handle_iske, - [0x2a] = handle_rrbe, - [0x2b] = handle_sske, - [0x2c] = handle_test_block, - [0x30] = handle_io_inst, - [0x31] = handle_io_inst, - [0x32] = handle_io_inst, - [0x33] = handle_io_inst, - [0x34] = handle_io_inst, - [0x35] = handle_io_inst, - [0x36] = handle_io_inst, - [0x37] = handle_io_inst, - [0x38] = handle_io_inst, - [0x39] = handle_io_inst, - [0x3a] = handle_io_inst, - [0x3b] = handle_io_inst, - [0x3c] = handle_io_inst, - [0x50] = handle_ipte_interlock, - [0x56] = handle_sthyi, - [0x5f] = handle_io_inst, - [0x74] = handle_io_inst, - [0x76] = handle_io_inst, - [0x7d] = handle_stsi, - [0xb1] = handle_stfl, - [0xb2] = handle_lpswe, -}; - int kvm_s390_handle_b2(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - /* - * A lot of B2 instructions are priviledged. Here we check for - * the privileged ones, that we can handle in the kernel. - * Anything else goes to userspace. - */ - handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x02: + return handle_stidp(vcpu); + case 0x04: + return handle_set_clock(vcpu); + case 0x10: + return handle_set_prefix(vcpu); + case 0x11: + return handle_store_prefix(vcpu); + case 0x12: + return handle_store_cpu_address(vcpu); + case 0x14: + return kvm_s390_handle_vsie(vcpu); + case 0x21: + case 0x50: + return handle_ipte_interlock(vcpu); + case 0x29: + return handle_iske(vcpu); + case 0x2a: + return handle_rrbe(vcpu); + case 0x2b: + return handle_sske(vcpu); + case 0x2c: + return handle_test_block(vcpu); + case 0x30: + case 0x31: + case 0x32: + case 0x33: + case 0x34: + case 0x35: + case 0x36: + case 0x37: + case 0x38: + case 0x39: + case 0x3a: + case 0x3b: + case 0x3c: + case 0x5f: + case 0x74: + case 0x76: + return handle_io_inst(vcpu); + case 0x56: + return handle_sthyi(vcpu); + case 0x7d: + return handle_stsi(vcpu); + case 0xb1: + return handle_stfl(vcpu); + case 0xb2: + return handle_lpswe(vcpu); + default: + return -EOPNOTSUPP; + } } static int handle_epsw(struct kvm_vcpu *vcpu) @@ -1105,25 +1111,22 @@ static int handle_essa(struct kvm_vcpu *vcpu) return 0; } -static const intercept_handler_t b9_handlers[256] = { - [0x8a] = handle_ipte_interlock, - [0x8d] = handle_epsw, - [0x8e] = handle_ipte_interlock, - [0x8f] = handle_ipte_interlock, - [0xab] = handle_essa, - [0xaf] = handle_pfmf, -}; - int kvm_s390_handle_b9(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - /* This is handled just as for the B2 instructions. */ - handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x8a: + case 0x8e: + case 0x8f: + return handle_ipte_interlock(vcpu); + case 0x8d: + return handle_epsw(vcpu); + case 0xab: + return handle_essa(vcpu); + case 0xaf: + return handle_pfmf(vcpu); + default: + return -EOPNOTSUPP; + } } int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) @@ -1271,22 +1274,20 @@ static int handle_stctg(struct kvm_vcpu *vcpu) return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } -static const intercept_handler_t eb_handlers[256] = { - [0x2f] = handle_lctlg, - [0x25] = handle_stctg, - [0x60] = handle_ri, - [0x61] = handle_ri, - [0x62] = handle_ri, -}; - int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipb & 0x000000ff) { + case 0x25: + return handle_stctg(vcpu); + case 0x2f: + return handle_lctlg(vcpu); + case 0x60: + case 0x61: + case 0x62: + return handle_ri(vcpu); + default: + return -EOPNOTSUPP; + } } static int handle_tprot(struct kvm_vcpu *vcpu) @@ -1346,10 +1347,12 @@ out_unlock: int kvm_s390_handle_e5(struct kvm_vcpu *vcpu) { - /* For e5xx... instructions we only handle TPROT */ - if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01) + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x01: return handle_tprot(vcpu); - return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } } static int handle_sckpf(struct kvm_vcpu *vcpu) @@ -1380,17 +1383,14 @@ static int handle_ptff(struct kvm_vcpu *vcpu) return 0; } -static const intercept_handler_t x01_handlers[256] = { - [0x04] = handle_ptff, - [0x07] = handle_sckpf, -}; - int kvm_s390_handle_01(struct kvm_vcpu *vcpu) { - intercept_handler_t handler; - - handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff]; - if (handler) - return handler(vcpu); - return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->ipa & 0x00ff) { + case 0x04: + return handle_ptff(vcpu); + case 0x07: + return handle_sckpf(vcpu); + default: + return -EOPNOTSUPP; + } } diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index ec772700ff96..8961e3970901 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -821,6 +821,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + int guest_bp_isolation; int rc; handle_last_fault(vcpu, vsie_page); @@ -831,6 +832,20 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) s390_handle_mcck(); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + + /* save current guest state of bp isolation override */ + guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); + + /* + * The guest is running with BPBC, so we have to force it on for our + * nested guest. This is done by enabling BPBC globally, so the BPBC + * control in the SCB (which the nested guest can modify) is simply + * ignored. + */ + if (test_kvm_facility(vcpu->kvm, 82) && + vcpu->arch.sie_block->fpf & FPF_BPBC) + set_thread_flag(TIF_ISOLATE_BP_GUEST); + local_irq_disable(); guest_enter_irqoff(); local_irq_enable(); @@ -840,6 +855,11 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) local_irq_disable(); guest_exit_irqoff(); local_irq_enable(); + + /* restore guest state for bp isolation override */ + if (!guest_bp_isolation) + clear_thread_flag(TIF_ISOLATE_BP_GUEST); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (rc == -EINTR) { diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile index 715def00a436..01d0f7fb14cc 100644 --- a/arch/sh/boot/dts/Makefile +++ b/arch/sh/boot/dts/Makefile @@ -1 +1,3 @@ -obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"") +obj-y += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +endif diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 847ddffbf38a..b5cfab711651 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -163,13 +163,10 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, pte_unmap(pte); } -void set_pmd_at(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, pmd_t pmd) -{ - pmd_t orig = *pmdp; - - *pmdp = pmd; +static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr, + pmd_t orig, pmd_t pmd) +{ if (mm == &init_mm) return; @@ -219,6 +216,15 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } } +void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + pmd_t orig = *pmdp; + + *pmdp = pmd; + __set_pmd_acct(mm, addr, orig, pmd); +} + static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { @@ -227,6 +233,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, do { old = *pmdp; } while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd); + __set_pmd_acct(vma->vm_mm, address, old, pmd); return old; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c1236b187824..0fa71a78ec99 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -430,6 +430,7 @@ config GOLDFISH config RETPOLINE bool "Avoid speculative indirect branches in kernel" default y + select STACK_VALIDATION if HAVE_STACK_VALIDATION help Compile kernel with the retpoline compiler options to guard against kernel-to-user data leaks by avoiding speculative indirect @@ -2306,7 +2307,7 @@ choice it can be used to assist security vulnerability exploitation. This setting can be changed at boot time via the kernel command - line parameter vsyscall=[native|emulate|none]. + line parameter vsyscall=[emulate|none]. On a system with recent enough glibc (2.14 or newer) and no static binaries, you can say None without a performance penalty @@ -2314,15 +2315,6 @@ choice If unsure, select "Emulate". - config LEGACY_VSYSCALL_NATIVE - bool "Native" - help - Actual executable code is located in the fixed vsyscall - address mapping, implementing time() efficiently. Since - this makes the mapping executable, it can be used during - security vulnerability exploitation (traditionally as - ROP gadgets). This configuration is not recommended. - config LEGACY_VSYSCALL_EMULATE bool "Emulate" help diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8b8d2297d486..638411f22267 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -315,19 +315,6 @@ config X86_L1_CACHE_SHIFT default "4" if MELAN || M486 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX -config X86_PPRO_FENCE - bool "PentiumPro memory ordering errata workaround" - depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1 - ---help--- - Old PentiumPro multiprocessor systems had errata that could cause - memory operations to violate the x86 ordering standard in rare cases. - Enabling this option will attempt to work around some (but not all) - occurrences of this problem, at the cost of much heavier spinlock and - memory barrier operations. - - If unsure, say n here. Even distro kernels should think twice before - enabling this: there are few systems, and an unlikely bug. - config X86_F00F_BUG def_bool y depends on M586MMX || M586TSC || M586 || M486 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index fad55160dcb9..1c4d012550ec 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -223,6 +223,15 @@ KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) LDFLAGS := -m elf_$(UTS_MACHINE) +# +# The 64-bit kernel must be aligned to 2MB. Pass -z max-page-size=0x200000 to +# the linker to force 2MB page size regardless of the default page size used +# by the linker. +# +ifdef CONFIG_X86_64 +LDFLAGS += $(call ld-option, -z max-page-size=0x200000) +endif + # Speed up the build KBUILD_CFLAGS += -pipe # Workaround for a gcc prelease that unfortunately was shipped in a suse release @@ -232,10 +241,9 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE - RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) - ifneq ($(RETPOLINE_CFLAGS),) - KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE - endif +ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE +endif endif archscripts: scripts_basic diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 98761a1576ce..252fee320816 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -309,6 +309,10 @@ static void parse_elf(void *output) switch (phdr->p_type) { case PT_LOAD: +#ifdef CONFIG_X86_64 + if ((phdr->p_align % 0x200000) != 0) + error("Alignment of LOAD segment isn't multiple of 2MB"); +#endif #ifdef CONFIG_RELOCATABLE dest = output; dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR); diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index dce7092ab24a..be63330c5511 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 /* * Push registers and sanitize registers of values that a * speculation attack might otherwise want to exploit. The @@ -105,32 +105,41 @@ For 32-bit we have the following conventions - kernel is built with * could be put to use in a speculative execution gadget. * Interleave XOR with PUSH for better uop scheduling: */ + .if \save_ret + pushq %rsi /* pt_regs->si */ + movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ + movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */ + .else pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ + .endif pushq \rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorq %r11, %r11 /* nospec r11*/ + xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12*/ + xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13*/ + xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14*/ + xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15*/ + xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret + pushq %rsi /* return address on top of stack */ + .endif .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 @@ -172,12 +181,7 @@ For 32-bit we have the following conventions - kernel is built with */ .macro ENCODE_FRAME_POINTER ptregs_offset=0 #ifdef CONFIG_FRAME_POINTER - .if \ptregs_offset - leaq \ptregs_offset(%rsp), %rbp - .else - mov %rsp, %rbp - .endif - orq $0x1, %rbp + leaq 1+\ptregs_offset(%rsp), %rbp #endif .endm diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 16c2c022540d..6ad064c8cf35 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,8 +252,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %ebx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8971bd64d515..18ed349b4f83 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -55,7 +55,7 @@ END(native_usergs_sysret64) .macro TRACE_IRQS_FLAGS flags:req #ifdef CONFIG_TRACE_IRQFLAGS - bt $9, \flags /* interrupts off? */ + btl $9, \flags /* interrupts off? */ jnc 1f TRACE_IRQS_ON 1: @@ -364,8 +364,7 @@ ENTRY(__switch_to_asm) * exist, overwrite the RSB with entries which capture * speculative execution to prevent attack. */ - /* Clobbers %rbx */ - FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW + FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW #endif /* restore callee-saved registers */ @@ -449,9 +448,19 @@ END(irq_entries_start) * * The invariant is that, if irq_count != -1, then the IRQ stack is in use. */ -.macro ENTER_IRQ_STACK regs=1 old_rsp +.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0 DEBUG_ENTRY_ASSERT_IRQS_OFF + + .if \save_ret + /* + * If save_ret is set, the original stack contains one additional + * entry -- the return address. Therefore, move the address one + * entry below %rsp to \old_rsp. + */ + leaq 8(%rsp), \old_rsp + .else movq %rsp, \old_rsp + .endif .if \regs UNWIND_HINT_REGS base=\old_rsp @@ -497,6 +506,15 @@ END(irq_entries_start) .if \regs UNWIND_HINT_REGS indirect=1 .endif + + .if \save_ret + /* + * Push the return address to the stack. This return address can + * be found at the "real" original RSP, which was offset by 8 at + * the beginning of this macro. + */ + pushq -8(\old_rsp) + .endif .endm /* @@ -520,27 +538,65 @@ END(irq_entries_start) .endm /* - * Interrupt entry/exit. - * - * Interrupt entry points save only callee clobbered registers in fast path. + * Interrupt entry helper function. * - * Entry runs with interrupts off. + * Entry runs with interrupts off. Stack layout at entry: + * +----------------------------------------------------+ + * | regs->ss | + * | regs->rsp | + * | regs->eflags | + * | regs->cs | + * | regs->ip | + * +----------------------------------------------------+ + * | regs->orig_ax = ~(interrupt number) | + * +----------------------------------------------------+ + * | return address | + * +----------------------------------------------------+ */ - -/* 0(%rsp): ~(interrupt number) */ - .macro interrupt func +ENTRY(interrupt_entry) + UNWIND_HINT_FUNC + ASM_CLAC cld - testb $3, CS-ORIG_RAX(%rsp) + testb $3, CS-ORIG_RAX+8(%rsp) jz 1f SWAPGS - call switch_to_thread_stack + + /* + * Switch to the thread stack. The IRET frame and orig_ax are + * on the stack, as well as the return address. RDI..R12 are + * not (yet) on the stack and space has not (yet) been + * allocated for them. + */ + pushq %rdi + + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + /* + * We have RDI, return address, and orig_ax on the stack on + * top of the IRET frame. That means offset=24 + */ + UNWIND_HINT_IRET_REGS base=%rdi offset=24 + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi 1: - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 - testb $3, CS(%rsp) + testb $3, CS+8(%rsp) jz 1f /* @@ -548,7 +604,7 @@ END(irq_entries_start) * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode - * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * (which can take locks). Since TRACE_IRQS_OFF is idempotent, * the simplest way to handle it is to just call it twice if * we enter from user mode. There's no reason to optimize this since * TRACE_IRQS_OFF is a no-op if lockdep is off. @@ -558,12 +614,15 @@ END(irq_entries_start) CALL_enter_from_user_mode 1: - ENTER_IRQ_STACK old_rsp=%rdi + ENTER_IRQ_STACK old_rsp=%rdi save_ret=1 /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func /* rdi points to pt_regs */ - .endm + ret +END(interrupt_entry) + + +/* Interrupt entry/exit. */ /* * The interrupt stubs push (~vector+0x80) onto the stack and @@ -571,9 +630,10 @@ END(irq_entries_start) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - ASM_CLAC addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ - interrupt do_IRQ + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call do_IRQ /* rdi points to pt_regs */ /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_ANY) @@ -766,10 +826,11 @@ END(common_interrupt) .macro apicinterrupt3 num sym do_sym ENTRY(\sym) UNWIND_HINT_IRET_REGS - ASM_CLAC pushq $~(\num) .Lcommon_\sym: - interrupt \do_sym + call interrupt_entry + UNWIND_HINT_REGS indirect=1 + call \do_sym /* rdi points to pt_regs */ jmp ret_from_intr END(\sym) .endm @@ -832,34 +893,6 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) -/* - * Switch to the thread stack. This is called with the IRET frame and - * orig_ax on the stack. (That is, RDI..R12 are not on the stack and - * space has not been allocated for them.) - */ -ENTRY(switch_to_thread_stack) - UNWIND_HINT_FUNC - - pushq %rdi - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi - movq %rsp, %rdi - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI - - pushq 7*8(%rdi) /* regs->ss */ - pushq 6*8(%rdi) /* regs->rsp */ - pushq 5*8(%rdi) /* regs->eflags */ - pushq 4*8(%rdi) /* regs->cs */ - pushq 3*8(%rdi) /* regs->ip */ - pushq 2*8(%rdi) /* regs->orig_ax */ - pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC - - movq (%rdi), %rdi - ret -END(switch_to_thread_stack) - .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 @@ -875,12 +908,8 @@ ENTRY(\sym) pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif - /* Save all registers in pt_regs */ - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER - .if \paranoid < 2 - testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ + testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */ jnz .Lfrom_usermode_switch_stack_\@ .endif @@ -1109,7 +1138,7 @@ apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \ #endif /* CONFIG_HYPERV */ idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 idtentry stack_segment do_stack_segment has_error_code=1 #ifdef CONFIG_XEN @@ -1130,13 +1159,15 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif /* - * Switch gs if needed. + * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) UNWIND_HINT_FUNC cld + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 movl $1, %ebx movl $MSR_GS_BASE, %ecx rdmsr @@ -1181,12 +1212,14 @@ ENTRY(paranoid_exit) END(paranoid_exit) /* - * Switch gs if needed. + * Save all registers in pt_regs, and switch GS if needed. * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - UNWIND_HINT_REGS offset=8 + UNWIND_HINT_FUNC cld + PUSH_AND_CLEAR_REGS save_ret=1 + ENCODE_FRAME_POINTER 8 testb $3, CS+8(%rsp) jz .Lerror_kernelspace @@ -1577,8 +1610,6 @@ end_repeat_nmi: * frame to point back to repeat_nmi. */ pushq $-1 /* ORIG_RAX: no syscall to restart */ - PUSH_AND_CLEAR_REGS - ENCODE_FRAME_POINTER /* * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index fd65e016e413..08425c42f8b7 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -85,25 +85,25 @@ ENTRY(entry_SYSENTER_compat) pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* @@ -224,25 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp (will be overwritten) */ xorl %ebp, %ebp /* nospec rbp */ pushq $0 /* pt_regs->r12 = 0 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq $0 /* pt_regs->r13 = 0 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq $0 /* pt_regs->r14 = 0 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq $0 /* pt_regs->r15 = 0 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ /* * User mode is traced as though IRQs are on, and SYSENTER @@ -298,9 +298,9 @@ sysret32_from_system_call: */ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r10 + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d swapgs sysretl END(entry_SYSCALL_compat) @@ -347,36 +347,47 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax + /* switch to thread stack expects orig_ax and rdi to be pushed */ pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ - /* switch to thread stack expects orig_ax to be pushed */ - call switch_to_thread_stack + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - pushq %rdi /* pt_regs->di */ + pushq 6*8(%rdi) /* regs->ss */ + pushq 5*8(%rdi) /* regs->rsp */ + pushq 4*8(%rdi) /* regs->eflags */ + pushq 3*8(%rdi) /* regs->cs */ + pushq 2*8(%rdi) /* regs->ip */ + pushq 1*8(%rdi) /* regs->orig_ax */ + + pushq (%rdi) /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq $0 /* pt_regs->r8 = 0 */ - xorq %r8, %r8 /* nospec r8 */ + xorl %r8d, %r8d /* nospec r8 */ pushq $0 /* pt_regs->r9 = 0 */ - xorq %r9, %r9 /* nospec r9 */ + xorl %r9d, %r9d /* nospec r9 */ pushq $0 /* pt_regs->r10 = 0 */ - xorq %r10, %r10 /* nospec r10 */ + xorl %r10d, %r10d /* nospec r10 */ pushq $0 /* pt_regs->r11 = 0 */ - xorq %r11, %r11 /* nospec r11 */ + xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ - xorq %r12, %r12 /* nospec r12 */ + xorl %r12d, %r12d /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ - xorq %r13, %r13 /* nospec r13 */ + xorl %r13d, %r13d /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ - xorq %r14, %r14 /* nospec r14 */ + xorl %r14d, %r14d /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ - xorq %r15, %r15 /* nospec r15 */ + xorl %r15d, %r15d /* nospec r15 */ cld /* @@ -393,15 +404,3 @@ ENTRY(entry_INT80_compat) TRACE_IRQS_ON jmp swapgs_restore_regs_and_return_to_usermode END(entry_INT80_compat) - -ENTRY(stub32_clone) - /* - * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). - * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). - * - * The native 64-bit kernel's sys_clone() implements the latter, - * so we need to swap arguments here before calling it: - */ - xchg %r8, %rcx - jmp sys_clone -ENDPROC(stub32_clone) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 448ac2161112..2a5e99cff859 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,12 +8,12 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork sys_fork +2 i386 fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open 6 i386 close sys_close -7 i386 waitpid sys_waitpid sys32_waitpid +7 i386 waitpid sys_waitpid compat_sys_x86_waitpid 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink @@ -78,7 +78,7 @@ 69 i386 ssetmask sys_ssetmask 70 i386 setreuid sys_setreuid16 71 i386 setregid sys_setregid16 -72 i386 sigsuspend sys_sigsuspend sys_sigsuspend +72 i386 sigsuspend sys_sigsuspend 73 i386 sigpending sys_sigpending compat_sys_sigpending 74 i386 sethostname sys_sethostname 75 i386 setrlimit sys_setrlimit compat_sys_setrlimit @@ -96,7 +96,7 @@ 87 i386 swapon sys_swapon 88 i386 reboot sys_reboot 89 i386 readdir sys_old_readdir compat_sys_old_readdir -90 i386 mmap sys_old_mmap sys32_mmap +90 i386 mmap sys_old_mmap compat_sys_x86_mmap 91 i386 munmap sys_munmap 92 i386 truncate sys_truncate compat_sys_truncate 93 i386 ftruncate sys_ftruncate compat_sys_ftruncate @@ -126,7 +126,7 @@ 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync 119 i386 sigreturn sys_sigreturn sys32_sigreturn -120 i386 clone sys_clone stub32_clone +120 i386 clone sys_clone compat_sys_x86_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname 123 i386 modify_ldt sys_modify_ldt @@ -186,8 +186,8 @@ 177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 i386 rt_sigsuspend sys_rt_sigsuspend -180 i386 pread64 sys_pread64 sys32_pread -181 i386 pwrite64 sys_pwrite64 sys32_pwrite +180 i386 pread64 sys_pread64 compat_sys_x86_pread +181 i386 pwrite64 sys_pwrite64 compat_sys_x86_pwrite 182 i386 chown sys_chown16 183 i386 getcwd sys_getcwd 184 i386 capget sys_capget @@ -196,14 +196,14 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork sys_vfork +190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff -193 i386 truncate64 sys_truncate64 sys32_truncate64 -194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64 -195 i386 stat64 sys_stat64 sys32_stat64 -196 i386 lstat64 sys_lstat64 sys32_lstat64 -197 i386 fstat64 sys_fstat64 sys32_fstat64 +193 i386 truncate64 sys_truncate64 compat_sys_x86_truncate64 +194 i386 ftruncate64 sys_ftruncate64 compat_sys_x86_ftruncate64 +195 i386 stat64 sys_stat64 compat_sys_x86_stat64 +196 i386 lstat64 sys_lstat64 compat_sys_x86_lstat64 +197 i386 fstat64 sys_fstat64 compat_sys_x86_fstat64 198 i386 lchown32 sys_lchown 199 i386 getuid32 sys_getuid 200 i386 getgid32 sys_getgid @@ -231,7 +231,7 @@ # 222 is unused # 223 is unused 224 i386 gettid sys_gettid -225 i386 readahead sys_readahead sys32_readahead +225 i386 readahead sys_readahead compat_sys_x86_readahead 226 i386 setxattr sys_setxattr 227 i386 lsetxattr sys_lsetxattr 228 i386 fsetxattr sys_fsetxattr @@ -256,7 +256,7 @@ 247 i386 io_getevents sys_io_getevents compat_sys_io_getevents 248 i386 io_submit sys_io_submit compat_sys_io_submit 249 i386 io_cancel sys_io_cancel -250 i386 fadvise64 sys_fadvise64 sys32_fadvise64 +250 i386 fadvise64 sys_fadvise64 compat_sys_x86_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) 252 i386 exit_group sys_exit_group 253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie @@ -278,7 +278,7 @@ 269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 270 i386 tgkill sys_tgkill 271 i386 utimes sys_utimes compat_sys_utimes -272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64 +272 i386 fadvise64_64 sys_fadvise64_64 compat_sys_x86_fadvise64_64 273 i386 vserver 274 i386 mbind sys_mbind 275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy @@ -306,7 +306,7 @@ 297 i386 mknodat sys_mknodat 298 i386 fchownat sys_fchownat 299 i386 futimesat sys_futimesat compat_sys_futimesat -300 i386 fstatat64 sys_fstatat64 sys32_fstatat +300 i386 fstatat64 sys_fstatat64 compat_sys_x86_fstatat 301 i386 unlinkat sys_unlinkat 302 i386 renameat sys_renameat 303 i386 linkat sys_linkat @@ -320,7 +320,7 @@ 311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list 312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list 313 i386 splice sys_splice -314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range +314 i386 sync_file_range sys_sync_file_range compat_sys_x86_sync_file_range 315 i386 tee sys_tee 316 i386 vmsplice sys_vmsplice compat_sys_vmsplice 317 i386 move_pages sys_move_pages compat_sys_move_pages @@ -330,7 +330,7 @@ 321 i386 signalfd sys_signalfd compat_sys_signalfd 322 i386 timerfd_create sys_timerfd_create 323 i386 eventfd sys_eventfd -324 i386 fallocate sys_fallocate sys32_fallocate +324 i386 fallocate sys_fallocate compat_sys_x86_fallocate 325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime 326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime 327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4 diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 7780bbfb06ef..9242b28418d5 100644 --- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c +++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -5,8 +5,6 @@ #undef CONFIG_OPTIMIZE_INLINING #endif -#undef CONFIG_X86_PPRO_FENCE - #ifdef CONFIG_X86_64 /* diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 577fa8adb785..317be365bce3 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -42,10 +42,8 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = -#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) - NATIVE; -#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) +static enum { EMULATE, NONE } vsyscall_mode = +#ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #else EMULATE; @@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str) if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; - else if (!strcmp("native", str)) - vsyscall_mode = NATIVE; else if (!strcmp("none", str)) vsyscall_mode = NONE; else @@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) WARN_ON_ONCE(address != regs->ip); - /* This should be unreachable in NATIVE mode. */ - if (WARN_ON(vsyscall_mode == NATIVE)) - return false; - if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -355,7 +347,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root) set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); p4d = p4d_offset(pgd, VSYSCALL_ADDR); #if CONFIG_PGTABLE_LEVELS >= 5 - p4d->p4d |= _PAGE_USER; + set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER)); #endif pud = pud_offset(p4d, VSYSCALL_ADDR); set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); @@ -370,9 +362,7 @@ void __init map_vsyscall(void) if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 140d33288e78..88797c80b3e0 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2118,7 +2118,8 @@ static int x86_pmu_event_init(struct perf_event *event) event->destroy(event); } - if (READ_ONCE(x86_pmu.attr_rdpmc)) + if (READ_ONCE(x86_pmu.attr_rdpmc) && + !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; return err; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 56457cb73448..1e41d7508d99 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2952,9 +2952,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event) return intel_pebs_aliases_precdist(event); } -static unsigned long intel_pmu_free_running_flags(struct perf_event *event) +static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) { - unsigned long flags = x86_pmu.free_running_flags; + unsigned long flags = x86_pmu.large_pebs_flags; if (event->attr.use_clockid) flags &= ~PERF_SAMPLE_TIME; @@ -2976,8 +2976,8 @@ static int intel_pmu_hw_config(struct perf_event *event) if (!event->attr.freq) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & - ~intel_pmu_free_running_flags(event))) - event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + ~intel_pmu_large_pebs_flags(event))) + event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS; } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); @@ -3194,7 +3194,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left) X86_CONFIG(.event=0xc0, .umask=0x01)) { if (left < 128) left = 128; - left &= ~0x3fu; + left &= ~0x3fULL; } return left; } @@ -3460,7 +3460,7 @@ static __initconst const struct x86_pmu core_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, - .free_running_flags = PEBS_FREERUNNING_FLAGS, + .large_pebs_flags = LARGE_PEBS_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32-bit width, @@ -3502,7 +3502,7 @@ static __initconst const struct x86_pmu intel_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, - .free_running_flags = PEBS_FREERUNNING_FLAGS, + .large_pebs_flags = LARGE_PEBS_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32 bit width, * so we install an artificial 1<<31 period regardless of diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 18c25ab28557..d8015235ba76 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event) bool needed_cb = pebs_needs_sched_cb(cpuc); cpuc->n_pebs++; - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs++; pebs_update_state(needed_cb, cpuc, event->ctx->pmu); @@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event) bool needed_cb = pebs_needs_sched_cb(cpuc); cpuc->n_pebs--; - if (hwc->flags & PERF_X86_EVENT_FREERUNNING) + if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS) cpuc->n_large_pebs--; pebs_update_state(needed_cb, cpuc, event->ctx->pmu); @@ -1530,7 +1530,7 @@ void __init intel_ds_init(void) x86_pmu.pebs_record_size = sizeof(struct pebs_record_skl); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; - x86_pmu.free_running_flags |= PERF_SAMPLE_TIME; + x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; default: diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 6d8044ab1060..c98b943e58b4 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4), SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3), EVENT_EXTRA_END }; @@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = { NULL, }; +/* + * To determine the number of CHAs, it should read bits 27:0 in the CAPID6 + * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083. + */ +#define SKX_CAPID6 0x9c +#define SKX_CHA_BIT_MASK GENMASK(27, 0) + static int skx_count_chabox(void) { - struct pci_dev *chabox_dev = NULL; - int bus, count = 0; + struct pci_dev *dev = NULL; + u32 val = 0; - while (1) { - chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev); - if (!chabox_dev) - break; - if (count == 0) - bus = chabox_dev->bus->number; - if (bus != chabox_dev->bus->number) - break; - count++; - } + dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev); + if (!dev) + goto out; - pci_dev_put(chabox_dev); - return count; + pci_read_config_dword(dev, SKX_CAPID6, &val); + val &= SKX_CHA_BIT_MASK; +out: + pci_dev_put(dev); + return hweight32(val); } void skx_uncore_cpu_init(void) @@ -3606,7 +3610,7 @@ static struct intel_uncore_type skx_uncore_imc = { }; static struct attribute *skx_upi_uncore_formats_attr[] = { - &format_attr_event_ext.attr, + &format_attr_event.attr, &format_attr_umask_ext.attr, &format_attr_edge.attr, &format_attr_inv.attr, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 78f91ec1056e..39cd0615f04f 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -69,7 +69,7 @@ struct event_constraint { #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ struct amd_nb { @@ -88,7 +88,7 @@ struct amd_nb { * REGS_USER can be handled for events limited to ring 3. * */ -#define PEBS_FREERUNNING_FLAGS \ +#define LARGE_PEBS_FLAGS \ (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ @@ -608,7 +608,7 @@ struct x86_pmu { struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); int max_pebs_events; - unsigned long free_running_flags; + unsigned long large_pebs_flags; /* * Intel LBR diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 96cd33bbfc85..6512498bbef6 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -51,15 +51,14 @@ #define AA(__x) ((unsigned long)(__x)) -asmlinkage long sys32_truncate64(const char __user *filename, - unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, + unsigned long, offset_low, unsigned long, offset_high) { return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); } -asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low, - unsigned long offset_high) +COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, + unsigned long, offset_low, unsigned long, offset_high) { return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } @@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) return 0; } -asmlinkage long sys32_stat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_stat(filename, &stat); @@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename, return ret; } -asmlinkage long sys32_lstat64(const char __user *filename, - struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_lstat(filename, &stat); @@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename, return ret; } -asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) +COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd, + struct stat64 __user *, statbuf) { struct kstat stat; int ret = vfs_fstat(fd, &stat); @@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf) return ret; } -asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag) +COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd, + const char __user *, filename, + struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; @@ -153,7 +154,7 @@ struct mmap_arg_struct32 { unsigned int offset; }; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) +COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) { struct mmap_arg_struct32 a; @@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg) a.offset>>PAGE_SHIFT); } -asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr, - int options) +COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *, + stat_addr, int, options) { return compat_sys_wait4(pid, stat_addr, options, NULL); } /* warning: next two assume little endian */ -asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, - u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); } -asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, - u32 count, u32 poslo, u32 poshi) +COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, + u32, count, u32, poslo, u32, poshi) { return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo)); @@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf, * Some system calls that need sign extended arguments. This could be * done by a generic wrapper. */ -long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, - __u32 len_low, __u32 len_high, int advice) +COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, + __u32, offset_high, __u32, len_low, __u32, len_high, + int, advice) { return sys_fadvise64_64(fd, (((u64)offset_high)<<32) | offset_low, @@ -202,31 +204,43 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, advice); } -asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, - size_t count) +COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, + unsigned int, off_hi, size_t, count) { return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); } -asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi, - unsigned n_low, unsigned n_hi, int flags) +COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, + unsigned int, off_hi, unsigned int, n_low, + unsigned int, n_hi, int, flags) { return sys_sync_file_range(fd, ((u64)off_hi << 32) | off_low, ((u64)n_hi << 32) | n_low, flags); } -asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi, - size_t len, int advice) +COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, + unsigned int, offset_hi, size_t, len, int, advice) { return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, len, advice); } -asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo, - unsigned offset_hi, unsigned len_lo, - unsigned len_hi) +COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, + unsigned int, offset_lo, unsigned int, offset_hi, + unsigned int, len_lo, unsigned int, len_hi) { return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, ((u64)len_hi << 32) | len_lo); } + +/* + * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS + */ +COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags, + unsigned long, newsp, int __user *, parent_tidptr, + unsigned long, tls_val, int __user *, child_tidptr) +{ + return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr, + tls_val); +} diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 4d4015ddcf26..c356098b6fb9 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -7,6 +7,8 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H +#include <asm/nospec-branch.h> + #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -32,6 +34,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -44,6 +47,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); } static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -56,6 +60,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -68,6 +73,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 4d111616524b..1908214b9125 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -38,7 +38,4 @@ INDIRECT_THUNK(dx) INDIRECT_THUNK(si) INDIRECT_THUNK(di) INDIRECT_THUNK(bp) -asmlinkage void __fill_rsb(void); -asmlinkage void __clear_rsb(void); - #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index e1259f043ae9..042b5e892ed1 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -52,11 +52,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \ "lfence", X86_FEATURE_LFENCE_RDTSC) -#ifdef CONFIG_X86_PPRO_FENCE -#define dma_rmb() rmb() -#else #define dma_rmb() barrier() -#endif #define dma_wmb() barrier() #ifdef CONFIG_X86_32 @@ -68,30 +64,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #define __smp_wmb() barrier() #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -#if defined(CONFIG_X86_PPRO_FENCE) - -/* - * For this option x86 doesn't have a strong TSO memory - * model and we should fall back to full barriers. - */ - -#define __smp_store_release(p, v) \ -do { \ - compiletime_assert_atomic_type(*p); \ - __smp_mb(); \ - WRITE_ONCE(*p, v); \ -} while (0) - -#define __smp_load_acquire(p) \ -({ \ - typeof(*p) ___p1 = READ_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ - __smp_mb(); \ - ___p1; \ -}) - -#else /* regular x86 TSO memory ordering */ - #define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ @@ -107,8 +79,6 @@ do { \ ___p1; \ }) -#endif - /* Atomic operations are already serializing on x86 */ #define __smp_mb__before_atomic() barrier() #define __smp_mb__after_atomic() barrier() diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 3fa039855b8f..9f645ba57dbb 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -78,7 +78,7 @@ set_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)CONST_MASK(nr)) : "memory"); } else { - asm volatile(LOCK_PREFIX "bts %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr) : "memory"); } } @@ -94,7 +94,7 @@ set_bit(long nr, volatile unsigned long *addr) */ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { - asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); + asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory"); } /** @@ -115,7 +115,7 @@ clear_bit(long nr, volatile unsigned long *addr) : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)~CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btr %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -137,7 +137,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { - asm volatile("btr %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr)); } static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) @@ -182,7 +182,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long * */ static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { - asm volatile("btc %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr)); } /** @@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) : CONST_MASK_ADDR(nr, addr) : "iq" ((u8)CONST_MASK(nr))); } else { - asm volatile(LOCK_PREFIX "btc %1,%0" + asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : BITOP_ADDR(addr) : "Ir" (nr)); } @@ -217,7 +217,8 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), + *addr, "Ir", nr, "%0", c); } /** @@ -246,7 +247,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * { bool oldbit; - asm("bts %2,%1" + asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -263,7 +264,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), + *addr, "Ir", nr, "%0", c); } /** @@ -286,7 +288,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long { bool oldbit; - asm volatile("btr %2,%1" + asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr)); @@ -298,7 +300,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon { bool oldbit; - asm volatile("btc %2,%1" + asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit), ADDR : "Ir" (nr) : "memory"); @@ -316,7 +318,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c); + GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), + *addr, "Ir", nr, "%0", c); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) @@ -329,7 +332,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l { bool oldbit; - asm volatile("bt %2,%1" + asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..d554c11e01ff 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -315,6 +316,7 @@ #define X86_FEATURE_VPCLMULQDQ (16*32+10) /* Carry-Less Multiplication Double Quadword */ #define X86_FEATURE_AVX512_VNNI (16*32+11) /* Vector Neural Network Instructions */ #define X86_FEATURE_AVX512_BITALG (16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* Intel Total Memory Encryption */ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ @@ -327,6 +329,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 85f6ccb80b91..a399c1ebf6f0 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -6,6 +6,7 @@ #include <asm/pgtable.h> #include <asm/processor-flags.h> #include <asm/tlb.h> +#include <asm/nospec-branch.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -36,8 +37,18 @@ extern asmlinkage unsigned long efi_call_phys(void *, ...); -#define arch_efi_call_virt_setup() kernel_fpu_begin() -#define arch_efi_call_virt_teardown() kernel_fpu_end() +#define arch_efi_call_virt_setup() \ +({ \ + kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ +}) + +#define arch_efi_call_virt_teardown() \ +({ \ + firmware_restrict_branch_speculation_end(); \ + kernel_fpu_end(); \ +}) + /* * Wrap all the virtual calls in a way that forces the parameters on the stack. @@ -73,6 +84,7 @@ struct efi_scratch { efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ \ if (efi_scratch.use_pgd) { \ efi_scratch.prev_cr3 = __read_cr3(); \ @@ -91,6 +103,7 @@ struct efi_scratch { __flush_tlb_all(); \ } \ \ + firmware_restrict_branch_speculation_end(); \ __kernel_fpu_end(); \ preempt_enable(); \ }) diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 95e948627fd0..f6e5b9375d8c 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -232,21 +232,6 @@ extern void set_iounmap_nonlazy(void); */ #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) -/* - * Cache management - * - * This needed for two cases - * 1. Out of order aware processors - * 2. Accidentally out of order processors (PPro errata #51) - */ - -static inline void flush_write_buffers(void) -{ -#if defined(CONFIG_X86_PPRO_FENCE) - asm volatile("lock; addl $0,0(%%esp)": : :"memory"); -#endif -} - #endif /* __KERNEL__ */ extern void native_io_delay(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index dd6f57a54a26..b605a5b6a30c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -507,6 +507,7 @@ struct kvm_vcpu_arch { u64 smi_count; bool tpr_access_reporting; u64 ia32_xss; + u64 microcode_version; /* * Paging state of the vcpu @@ -1095,6 +1096,8 @@ struct kvm_x86_ops { int (*mem_enc_op)(struct kvm *kvm, void __user *argp); int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); + + int (*get_msr_feature)(struct kvm_msr_entry *entry); }; struct kvm_arch_async_pf { @@ -1464,7 +1467,4 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val -void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, - unsigned long start, unsigned long end); - #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 55520cec8b27..6cf0e4cb7b97 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -37,7 +37,13 @@ struct cpu_signature { struct device; -enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; +enum ucode_state { + UCODE_OK = 0, + UCODE_NEW, + UCODE_UPDATED, + UCODE_NFOUND, + UCODE_ERROR, +}; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, @@ -54,7 +60,7 @@ struct microcode_ops { * are being called. * See also the "Synchronization" section in microcode_core.c. */ - int (*apply_microcode) (int cpu); + enum ucode_state (*apply_microcode) (int cpu); int (*collect_cpu_info) (int cpu, struct cpu_signature *csig); }; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index c931b88982a0..1de72ce514cd 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -74,6 +74,7 @@ static inline void *ldt_slot_va(int slot) return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); #else BUG(); + return (void *)fix_to_virt(FIX_HOLE); #endif } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 81a1be326571..f928ad9b143f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -8,6 +8,50 @@ #include <asm/cpufeatures.h> #include <asm/msr-index.h> +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + lfence; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + #ifdef __ASSEMBLY__ /* @@ -24,6 +68,18 @@ .endm /* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +.macro ANNOTATE_RETPOLINE_SAFE + .Lannotate_\@: + .pushsection .discard.retpoline_safe + _ASM_PTR .Lannotate_\@ + .popsection +.endm + +/* * These are the bare retpoline primitives for indirect jmp and call. * Do not use these directly; they only exist to make the ALTERNATIVE * invocation below less ugly. @@ -59,9 +115,9 @@ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(jmp *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \ __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD #else jmp *\reg #endif @@ -70,18 +126,25 @@ .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE_2 __stringify(call *\reg), \ + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg), \ __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ - __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD #else call *\reg #endif .endm -/* This clobbers the BX register */ -.macro FILL_RETURN_BUFFER nr:req ftr:req + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req #ifdef CONFIG_RETPOLINE - ALTERNATIVE "", "call __clear_rsb", \ftr + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: #endif .endm @@ -93,6 +156,12 @@ ".long 999b - .\n\t" \ ".popsection\n\t" +#define ANNOTATE_RETPOLINE_SAFE \ + "999:\n\t" \ + ".pushsection .discard.retpoline_safe\n\t" \ + _ASM_PTR " 999b\n\t" \ + ".popsection\n\t" + #if defined(CONFIG_X86_64) && defined(RETPOLINE) /* @@ -102,6 +171,7 @@ # define CALL_NOSPEC \ ANNOTATE_NOSPEC_ALTERNATIVE \ ALTERNATIVE( \ + ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE) @@ -113,7 +183,10 @@ * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ -# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ +# define CALL_NOSPEC \ + ALTERNATIVE( \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ @@ -156,26 +229,54 @@ extern char __indirect_thunk_end[]; static inline void vmexit_fill_RSB(void) { #ifdef CONFIG_RETPOLINE - alternative_input("", - "call __fill_rsb", - X86_FEATURE_RETPOLINE, - ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory")); + unsigned long loops; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=r" (loops), ASM_CALL_CONSTRAINT + : : "memory" ); #endif } +#define alternative_msr_write(_msr, _val, _feature) \ + asm volatile(ALTERNATIVE("", \ + "movl %[msr], %%ecx\n\t" \ + "movl %[val], %%eax\n\t" \ + "movl $0, %%edx\n\t" \ + "wrmsr", \ + _feature) \ + : : [msr] "i" (_msr), [val] "i" (_val) \ + : "eax", "ecx", "edx", "memory") + static inline void indirect_branch_prediction_barrier(void) { - asm volatile(ALTERNATIVE("", - "movl %[msr], %%ecx\n\t" - "movl %[val], %%eax\n\t" - "movl $0, %%edx\n\t" - "wrmsr", - X86_FEATURE_USE_IBPB) - : : [msr] "i" (MSR_IA32_PRED_CMD), - [val] "i" (PRED_CMD_IBPB) - : "eax", "ecx", "edx", "memory"); + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, + X86_FEATURE_USE_IBPB); } +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) + */ +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ +} while (0) + +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 554841fab717..c83a2f418cea 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -7,6 +7,7 @@ #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> +#include <asm/nospec-branch.h> #include <asm/paravirt_types.h> @@ -879,23 +880,27 @@ extern void default_banner(void); #define INTERRUPT_RETURN \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx #else /* !CONFIG_X86_32 */ @@ -917,21 +922,25 @@ extern void default_banner(void); */ #define SWAPGS \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ ) #define GET_CR2_INTO_RAX \ - call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2) + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);) #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index f624f1f10316..180bc0bff0fb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -43,6 +43,7 @@ #include <asm/desc_defs.h> #include <asm/kmap_types.h> #include <asm/pgtable_types.h> +#include <asm/nospec-branch.h> struct page; struct thread_struct; @@ -392,7 +393,9 @@ int paravirt_disable_iospace(void); * offset into the paravirt_patch_template structure, and can therefore be * freely converted back into a structure offset. */ -#define PARAVIRT_CALL "call *%c[paravirt_opptr];" +#define PARAVIRT_CALL \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%c[paravirt_opptr];" /* * These macros are intended to wrap calls through one of the paravirt diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index ba3c523aaf16..a06b07399d17 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, { bool oldbit; - asm volatile("bt "__percpu_arg(2)",%1" + asm volatile("btl "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 63c2552b6b65..b444d83cfc95 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -350,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v | set); + return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); - return __pmd(v & ~clear); + return native_make_pmd(v & ~clear); } static inline pmd_t pmd_mkold(pmd_t pmd) @@ -409,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); - return __pud(v | set); + return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); - return __pud(v & ~clear); + return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index e55466760ff8..b3ec519e3982 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -32,6 +32,7 @@ extern pmd_t initial_pg_pmd[]; static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } void paging_init(void); +void sync_initial_page_table(void); /* * Define this if things work differently on an i386 and an i486: diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 81462e9a34f6..1149d2112b2e 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); +static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 3696398a9475..acfe755562a6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -174,7 +174,6 @@ enum page_cache_mode { #define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) #define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) #define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) -#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) #define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) #define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) @@ -206,7 +205,6 @@ enum page_cache_mode { #define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC) #define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC) -#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC) #define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC) #define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) @@ -323,6 +321,11 @@ static inline pudval_t native_pud_val(pud_t pud) #else #include <asm-generic/pgtable-nopud.h> +static inline pud_t native_make_pud(pudval_t val) +{ + return (pud_t) { .p4d.pgd = native_make_pgd(val) }; +} + static inline pudval_t native_pud_val(pud_t pud) { return native_pgd_val(pud.p4d.pgd); @@ -344,6 +347,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) #else #include <asm-generic/pgtable-nopmd.h> +static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; +} + static inline pmdval_t native_pmd_val(pmd_t pmd) { return native_pgd_val(pmd.pud.p4d.pgd); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 1bd9ed87606f..b0ccd4847a58 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -977,4 +977,5 @@ bool xen_set_default_idle(void); void stop_this_cpu(void *dummy); void df_debug(struct pt_regs *regs, long error_code); +void microcode_check(void); #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 4e44250e7d0d..4cf11d88d3b3 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -17,7 +17,7 @@ #define _REFCOUNT_EXCEPTION \ ".pushsection .text..refcount\n" \ "111:\tlea %[counter], %%" _ASM_CX "\n" \ - "112:\t" ASM_UD0 "\n" \ + "112:\t" ASM_UD2 "\n" \ ASM_UNREACHABLE \ ".popsection\n" \ "113:\n" \ @@ -67,13 +67,13 @@ static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "er", i, "%0", e); + r->refs.counter, "er", i, "%0", e, "cx"); } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "%0", e); + r->refs.counter, "%0", e, "cx"); } static __always_inline __must_check diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index f91c365e57c3..4914a3e7c803 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -2,8 +2,7 @@ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc -#define __CLOBBERS_MEM "memory" -#define __CLOBBERS_MEM_CC_CX "memory", "cc", "cx" +#define __CLOBBERS_MEM(clb...) "memory", ## clb #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) @@ -40,18 +39,19 @@ do { \ #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ #define GEN_UNARY_RMWcc(op, var, arg0, cc) \ - __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM) + __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) -#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc) \ +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\ __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX) + __CLOBBERS_MEM(clobbers)) #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \ - __CLOBBERS_MEM, vcon (val)) + __CLOBBERS_MEM(), vcon (val)) -#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc) \ +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \ + clobbers...) \ __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM_CC_CX, vcon (val)) + __CLOBBERS_MEM(clobbers), vcon (val)) #endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index d6baf23782bc..5c019d23d06b 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; +extern char __entry_trampoline_start[], __entry_trampoline_end[]; #endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 82c34ee25a65..906794aa034e 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -20,31 +20,43 @@ #include <asm/ia32.h> /* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); -asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); +asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long, + unsigned long); +asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long, + unsigned long); -asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); -asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, const char __user *, +asmlinkage long compat_sys_x86_stat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_lstat64(const char __user *, + struct stat64 __user *); +asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *); +asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *, struct stat64 __user *, int); struct mmap_arg_struct32; -asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); +asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *); -asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int); +asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *, + int); -asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); +asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32, + u32); +asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32, + u32, u32); -long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int); -long sys32_vm86_warning(void); +asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32, + int); -asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t); -asmlinkage long sys32_sync_file_range(int, unsigned, unsigned, - unsigned, unsigned, int); -asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int); -asmlinkage long sys32_fallocate(int, int, unsigned, - unsigned, unsigned, unsigned); +asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int, + size_t); +asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int, + unsigned int, unsigned int, + int); +asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int, + size_t, int); +asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int, + unsigned int, unsigned int); +asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *, + unsigned long, int __user *); /* ia32/ia32_signal.c */ asmlinkage long sys32_sigreturn(void); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 8b6780751132..5db8b0b10766 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -352,6 +352,7 @@ enum vmcs_field { #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ #define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ +#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ #define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 7a2ade4aa235..6cfa9c8cb7d6 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -26,6 +26,7 @@ #define KVM_FEATURE_PV_EOI 6 #define KVM_FEATURE_PV_UNHALT 7 #define KVM_FEATURE_PV_TLB_FLUSH 9 +#define KVM_FEATURE_ASYNC_PF_VMEXIT 10 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 91723461dc1f..435db58a7bad 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -30,6 +30,7 @@ struct mce { __u64 synd; /* MCA_SYND MSR: only valid on SMCA systems */ __u64 ipid; /* MCA_IPID MSR: only valid on SMCA systems */ __u64 ppin; /* Protected Processor Inventory Number */ + __u32 microcode;/* Microcode revision */ }; #define MCE_GET_RECORD_LEN _IOR('M', 1, int) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8ad2e410974f..7c5538769f7e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void) do { rep_nop(); now = rdtsc(); - } while ((now - start) < 40000000000UL / HZ && + } while ((now - start) < 40000000000ULL / HZ && time_before_eq(jiffies, end)); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d71c8b54b696..bfca937bdcc3 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -300,6 +300,15 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_USE_IBPB); pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } + + /* + * Retpoline means the kernel is safe because it has no indirect + * branches. But firmware isn't, so use IBRS to protect that. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); + pr_info("Enabling Restricted Speculation for firmware calls\n"); + } } #undef pr_fmt @@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", spectre_v2_module_string()); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 824aee0117bb..348cf4821240 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void) return 0; } core_initcall(init_cpu_syscore); + +/* + * The microcode loader calls this upon late microcode load to recheck features, + * only when microcode has been updated. Caller holds microcode_mutex and CPU + * hotplug lock. + */ +void microcode_check(void) +{ + struct cpuinfo_x86 info; + + perf_check_microcode(); + + /* Reload CPUID max function as it might've changed. */ + info.cpuid_level = cpuid_eax(0); + + /* + * Copy all capability leafs to pick up the synthetic ones so that + * memcmp() below doesn't fail on that. The ones coming from CPUID will + * get overwritten in get_cpu_cap(). + */ + memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)); + + get_cpu_cap(&info); + + if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability))) + return; + + pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n"); + pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); +} diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index d19e903214b4..c3af167d0a70 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -105,7 +105,7 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c) /* * Early microcode releases for the Spectre v2 mitigation were broken. * Information taken from; - * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf * - https://kb.vmware.com/s/article/52345 * - Microcode revisions observed in the wild * - Release note from 20180108 microcode release @@ -123,7 +123,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 }, @@ -144,6 +143,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) { int i; + /* + * We know that the hypervisor lie to us on the microcode version so + * we may as well hope that it is running the correct version. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8ff94d1e2dce..466f47301334 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -56,6 +56,9 @@ static DEFINE_MUTEX(mce_log_mutex); +/* sysfs synchronization */ +static DEFINE_MUTEX(mce_sysfs_mutex); + #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -130,6 +133,8 @@ void mce_setup(struct mce *m) if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) rdmsrl(MSR_PPIN, m->ppin); + + m->microcode = boot_cpu_data.microcode; } DEFINE_PER_CPU(struct mce, injectm); @@ -262,7 +267,7 @@ static void __print_mce(struct mce *m) */ pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, - cpu_data(m->extcpu).microcode); + m->microcode); } static void print_mce(struct mce *m) @@ -2086,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.ignore_ce ^ !!new) { if (new) { /* disable ce features */ @@ -2098,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s, on_each_cpu(mce_enable_ce, (void *)1, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2110,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s, if (kstrtou64(buf, 0, &new) < 0) return -EINVAL; + mutex_lock(&mce_sysfs_mutex); if (mca_cfg.cmci_disabled ^ !!new) { if (new) { /* disable cmci */ @@ -2121,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s, on_each_cpu(mce_enable_ce, NULL, 1); } } + mutex_unlock(&mce_sysfs_mutex); + return size; } @@ -2128,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s, struct device_attribute *attr, const char *buf, size_t size) { - ssize_t ret = device_store_int(s, attr, buf, size); + unsigned long old_check_interval = check_interval; + ssize_t ret = device_store_ulong(s, attr, buf, size); + + if (check_interval == old_check_interval) + return ret; + + if (check_interval < 1) + check_interval = 1; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); + return ret; } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 330b8462d426..48179928ff38 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -339,7 +339,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) return -EINVAL; ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size); - if (ret != UCODE_OK) + if (ret > UCODE_UPDATED) return -EINVAL; return 0; @@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } -static int apply_microcode_amd(int cpu) +static enum ucode_state apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; @@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu) p = find_patch(cpu); if (!p) - return 0; + return UCODE_NFOUND; mc_amd = p->data; uci->mc = p->data; @@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu) if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; uci->cpu_sig.rev = rev; - return 0; + return UCODE_OK; } if (__apply_microcode_amd(mc_amd)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); - return -1; + return UCODE_ERROR; } pr_info("CPU%d: new patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); @@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu) uci->cpu_sig.rev = mc_amd->hdr.patch_id; c->microcode = mc_amd->hdr.patch_id; - return 0; + return UCODE_UPDATED; } static int install_equiv_cpu_table(const u8 *buf) @@ -683,27 +683,35 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, static enum ucode_state load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) { + struct ucode_patch *p; enum ucode_state ret; /* free old equiv table */ free_equiv_cpu_table(); ret = __load_microcode_amd(family, data, size); - - if (ret != UCODE_OK) + if (ret != UCODE_OK) { cleanup(); + return ret; + } -#ifdef CONFIG_X86_32 - /* save BSP's matching patch for early load */ - if (save) { - struct ucode_patch *p = find_patch(0); - if (p) { - memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); - memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), - PATCH_MAX_SIZE)); - } + p = find_patch(0); + if (!p) { + return ret; + } else { + if (boot_cpu_data.microcode == p->patch_id) + return ret; + + ret = UCODE_NEW; } -#endif + + /* save BSP's matching patch for early load */ + if (!save) + return ret; + + memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); + memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE)); + return ret; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 319dd65f98a2..10c4fc2c91f8 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -22,13 +22,16 @@ #define pr_fmt(fmt) "microcode: " fmt #include <linux/platform_device.h> +#include <linux/stop_machine.h> #include <linux/syscore_ops.h> #include <linux/miscdevice.h> #include <linux/capability.h> #include <linux/firmware.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/mutex.h> #include <linux/cpu.h> +#include <linux/nmi.h> #include <linux/fs.h> #include <linux/mm.h> @@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); +/* + * Serialize late loading so that CPUs get updated one-by-one. + */ +static DEFINE_SPINLOCK(update_lock); + struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu) return ret; } -struct apply_microcode_ctx { - int err; -}; - static void apply_microcode_local(void *arg) { - struct apply_microcode_ctx *ctx = arg; + enum ucode_state *err = arg; - ctx->err = microcode_ops->apply_microcode(smp_processor_id()); + *err = microcode_ops->apply_microcode(smp_processor_id()); } static int apply_microcode_on_target(int cpu) { - struct apply_microcode_ctx ctx = { .err = 0 }; + enum ucode_state err; int ret; - ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1); - if (!ret) - ret = ctx.err; - + ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1); + if (!ret) { + if (err == UCODE_ERROR) + ret = 1; + } return ret; } @@ -489,31 +494,124 @@ static void __exit microcode_dev_exit(void) /* fake device for request_firmware */ static struct platform_device *microcode_pdev; -static int reload_for_cpu(int cpu) +/* + * Late loading dance. Why the heavy-handed stomp_machine effort? + * + * - HT siblings must be idle and not execute other code while the other sibling + * is loading microcode in order to avoid any negative interactions caused by + * the loading. + * + * - In addition, microcode update on the cores must be serialized until this + * requirement can be relaxed in the future. Right now, this is conservative + * and good. + */ +#define SPINUNIT 100 /* 100 nsec */ + +static int check_online_cpus(void) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - enum ucode_state ustate; - int err = 0; + if (num_online_cpus() == num_present_cpus()) + return 0; - if (!uci->valid) - return err; + pr_err("Not all CPUs online, aborting microcode update.\n"); - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true); - if (ustate == UCODE_OK) - apply_microcode_on_target(cpu); - else - if (ustate == UCODE_ERROR) - err = -EINVAL; - return err; + return -EINVAL; +} + +static atomic_t late_cpus_in; +static atomic_t late_cpus_out; + +static int __wait_for_cpus(atomic_t *t, long long timeout) +{ + int all_cpus = num_online_cpus(); + + atomic_inc(t); + + while (atomic_read(t) < all_cpus) { + if (timeout < SPINUNIT) { + pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", + all_cpus - atomic_read(t)); + return 1; + } + + ndelay(SPINUNIT); + timeout -= SPINUNIT; + + touch_nmi_watchdog(); + } + return 0; +} + +/* + * Returns: + * < 0 - on error + * 0 - no update done + * 1 - microcode was updated + */ +static int __reload_late(void *info) +{ + int cpu = smp_processor_id(); + enum ucode_state err; + int ret = 0; + + /* + * Wait for all CPUs to arrive. A load will not be attempted unless all + * CPUs show up. + * */ + if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) + return -1; + + spin_lock(&update_lock); + apply_microcode_local(&err); + spin_unlock(&update_lock); + + if (err > UCODE_NFOUND) { + pr_warn("Error reloading microcode on CPU %d\n", cpu); + return -1; + /* siblings return UCODE_OK because their engine got updated already */ + } else if (err == UCODE_UPDATED || err == UCODE_OK) { + ret = 1; + } else { + return ret; + } + + /* + * Increase the wait timeout to a safe value here since we're + * serializing the microcode update and that could take a while on a + * large number of CPUs. And that is fine as the *actual* timeout will + * be determined by the last CPU finished updating and thus cut short. + */ + if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus())) + panic("Timeout during microcode update!\n"); + + return ret; +} + +/* + * Reload microcode late on all CPUs. Wait for a sec until they + * all gather together. + */ +static int microcode_reload_late(void) +{ + int ret; + + atomic_set(&late_cpus_in, 0); + atomic_set(&late_cpus_out, 0); + + ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); + if (ret > 0) + microcode_check(); + + return ret; } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + enum ucode_state tmp_ret = UCODE_OK; + int bsp = boot_cpu_data.cpu_index; unsigned long val; - int cpu; - ssize_t ret = 0, tmp_ret; + ssize_t ret = 0; ret = kstrtoul(buf, 0, &val); if (ret) @@ -522,23 +620,24 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_NEW) + return size; + get_online_cpus(); - mutex_lock(µcode_mutex); - for_each_online_cpu(cpu) { - tmp_ret = reload_for_cpu(cpu); - if (tmp_ret != 0) - pr_warn("Error reloading microcode on CPU %d\n", cpu); - /* save retval of the first encountered reload error */ - if (!ret) - ret = tmp_ret; - } - if (!ret) - perf_check_microcode(); + ret = check_online_cpus(); + if (ret) + goto put; + + mutex_lock(µcode_mutex); + ret = microcode_reload_late(); mutex_unlock(µcode_mutex); + +put: put_online_cpus(); - if (!ret) + if (ret >= 0) ret = size; return ret; @@ -606,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) if (system_state != SYSTEM_RUNNING) return UCODE_NFOUND; - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, - refresh_fw); - - if (ustate == UCODE_OK) { + ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, refresh_fw); + if (ustate == UCODE_NEW) { pr_debug("CPU%d updated upon init\n", cpu); apply_microcode_on_target(cpu); } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a15db2b4e0d6..32b8e5724f96 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (!mc) return 0; + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) return 0; } -static int apply_microcode_intel(int cpu) +static enum ucode_state apply_microcode_intel(int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; - struct ucode_cpu_info *uci; - struct cpuinfo_x86 *c; static int prev_rev; u32 rev; /* We should bind the task to the CPU */ if (WARN_ON(raw_smp_processor_id() != cpu)) - return -1; + return UCODE_ERROR; - uci = ucode_cpu_info + cpu; - mc = uci->mc; + /* Look for a newer patch in our cache: */ + mc = find_patch(uci); if (!mc) { - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); + mc = uci->mc; if (!mc) - return 0; + return UCODE_NFOUND; } + /* + * Save us the MSR write below - which is a particular expensive + * operation - when the other hyperthread has updated the microcode + * already. + */ + rev = intel_get_microcode_revision(); + if (rev >= mc->hdr.rev) { + uci->cpu_sig.rev = rev; + c->microcode = rev; + return UCODE_OK; + } + + /* + * Writeback and invalidate caches before updating microcode to avoid + * internal issues depending on what the microcode is updating. + */ + native_wbinvd(); + /* write microcode via MSR 0x79 */ wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); @@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu) if (rev != mc->hdr.rev) { pr_err("CPU%d update to revision 0x%x failed\n", cpu, mc->hdr.rev); - return -1; + return UCODE_ERROR; } if (rev != prev_rev) { @@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu) prev_rev = rev; } - c = &cpu_data(cpu); - uci->cpu_sig.rev = rev; c->microcode = rev; - return 0; + return UCODE_UPDATED; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, @@ -830,6 +862,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, unsigned int leftover = size; unsigned int curr_mc_size = 0, new_mc_size = 0; unsigned int csig, cpf; + enum ucode_state ret = UCODE_OK; while (leftover) { struct microcode_header_intel mc_header; @@ -871,6 +904,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, new_mc = mc; new_mc_size = mc_size; mc = NULL; /* trigger new vmalloc */ + ret = UCODE_NEW; } ucode_ptr += mc_size; @@ -900,7 +934,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", cpu, new_rev, uci->cpu_sig.rev); - return UCODE_OK; + return ret; } static int get_ucode_fw(void *to, const void *from, size_t n) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 04a625f0fcda..0f545b3cf926 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -23,6 +23,7 @@ #include <asm/nops.h> #include "../entry/calling.h" #include <asm/export.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -134,6 +135,7 @@ ENTRY(secondary_startup_64) /* Ensure I am executing from virtual addresses */ movq $1f, %rax + ANNOTATE_RETPOLINE_SAFE jmp *%rax 1: UNWIND_HINT_EMPTY diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 56d99be3706a..50bee5fe1140 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -160,7 +160,6 @@ static const __initconst struct idt_data early_pf_idts[] = { */ static const __initconst struct idt_data dbg_idts[] = { INTG(X86_TRAP_DB, debug), - INTG(X86_TRAP_BP, int3), }; #endif @@ -183,7 +182,6 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; static const __initconst struct idt_data ist_idts[] = { ISTG(X86_TRAP_DB, debug, DEBUG_STACK), ISTG(X86_TRAP_NMI, nmi, NMI_STACK), - SISTG(X86_TRAP_BP, int3, DEBUG_STACK), ISTG(X86_TRAP_DF, double_fault, DOUBLEFAULT_STACK), #ifdef CONFIG_X86_MCE ISTG(X86_TRAP_MC, &machine_check, MCE_STACK), diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 2f723301eb58..38deafebb21b 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -23,7 +23,7 @@ /* * this changes the io permissions bitmap in the current task. */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on) { struct thread_struct *t = ¤t->thread; struct tss_struct *tss; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index bd36f3c33cd0..0715f827607c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler); bool arch_within_kprobe_blacklist(unsigned long addr) { + bool is_in_entry_trampoline_section = false; + +#ifdef CONFIG_X86_64 + is_in_entry_trampoline_section = + (addr >= (unsigned long)__entry_trampoline_start && + addr < (unsigned long)__entry_trampoline_end); +#endif return (addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end) || (addr >= (unsigned long)__entry_text_start && - addr < (unsigned long)__entry_text_end); + addr < (unsigned long)__entry_text_end) || + is_in_entry_trampoline_section; } int __init arch_init_kprobes(void) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 4e37d1a851a6..bc1a27280c4b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -49,7 +49,7 @@ static int kvmapf = 1; -static int parse_no_kvmapf(char *arg) +static int __init parse_no_kvmapf(char *arg) { kvmapf = 0; return 0; @@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg) early_param("no-kvmapf", parse_no_kvmapf); static int steal_acc = 1; -static int parse_no_stealacc(char *arg) +static int __init parse_no_stealacc(char *arg) { steal_acc = 0; return 0; @@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); static int kvmclock_vsyscall = 1; -static int parse_no_kvmclock_vsyscall(char *arg) +static int __init parse_no_kvmclock_vsyscall(char *arg) { kvmclock_vsyscall = 0; return 0; @@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void) #endif pa |= KVM_ASYNC_PF_ENABLED; - /* Async page fault support for L1 hypervisor is optional */ - if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN, - (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0) - wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) + pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT; + + wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); @@ -545,7 +545,8 @@ static void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) @@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void) { int cpu; - if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) { + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && + !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), GFP_KERNEL, cpu_to_node(cpu)); diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 618285e475c6..ac7ea3a8242f 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -37,7 +37,6 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) return NOMMU_MAPPING_ERROR; - flush_write_buffers(); return bus; } @@ -72,25 +71,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return 0; s->dma_length = s->length; } - flush_write_buffers(); return nents; } -static void nommu_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, - enum dma_data_direction dir) -{ - flush_write_buffers(); -} - - -static void nommu_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, - enum dma_data_direction dir) -{ - flush_write_buffers(); -} - static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) { return dma_addr == NOMMU_MAPPING_ERROR; @@ -101,8 +84,6 @@ const struct dma_map_ops nommu_dma_ops = { .free = dma_generic_free_coherent, .map_sg = nommu_map_sg, .map_page = nommu_map_page, - .sync_single_for_device = nommu_sync_single_for_device, - .sync_sg_for_device = nommu_sync_sg_for_device, .is_phys = 1, .mapping_error = nommu_mapping_error, .dma_supported = x86_dma_supported, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1ae67e982af7..4c616be28506 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1204,20 +1204,13 @@ void __init setup_arch(char **cmdline_p) kasan_init(); -#ifdef CONFIG_X86_32 - /* sync back kernel address range */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. + * Sync back kernel address range. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); tboot_probe(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 497aa766fab3..ea554f812ee1 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void) /* Setup cpu initialized, callin, callout masks */ setup_cpu_local_masks(); -#ifdef CONFIG_X86_32 /* * Sync back kernel address range again. We already did this in * setup_arch(), but percpu data also needs to be available in * the smpboot asm. We can't reliably pick up percpu mappings * using vmalloc_fault(), because exception dispatch needs * percpu data. + * + * FIXME: Can the later sync in setup_cpu_entry_areas() replace + * this call? */ - clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - KERNEL_PGD_PTRS); - - /* - * sync back low identity map too. It is used for example - * in the 32-bit EFI stub. - */ - clone_pgd_range(initial_page_table, - swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); -#endif + sync_initial_page_table(); } diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ac057f9b0763..0d930d8987cc 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int)); #define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name)) + BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8); + + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code) != 8); /* * Ensure that the size of each si_field never changes. * If it does, it is a sign that the @@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void) CHECK_CSI_SIZE (_kill, 2*sizeof(int)); CHECK_SI_SIZE (_kill, 2*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + CHECK_CSI_OFFSET(_timer); CHECK_CSI_SIZE (_timer, 3*sizeof(int)); CHECK_SI_SIZE (_timer, 6*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_rt); CHECK_CSI_SIZE (_rt, 3*sizeof(int)); CHECK_SI_SIZE (_rt, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14); + CHECK_CSI_OFFSET(_sigchld); CHECK_CSI_SIZE (_sigchld, 5*sizeof(int)); CHECK_SI_SIZE (_sigchld, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime) != 0x1C); + #ifdef CONFIG_X86_X32_ABI CHECK_CSI_OFFSET(_sigchld_x32); CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int)); /* no _sigchld_x32 in the generic siginfo_t */ + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) != 0x20); #endif CHECK_CSI_OFFSET(_sigfault); CHECK_CSI_SIZE (_sigfault, 4*sizeof(int)); CHECK_SI_SIZE (_sigfault, 8*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C); + + BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10); + + BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18); + + BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14); + CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); CHECK_SI_SIZE (_sigpoll, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x18); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd) != 0x10); + CHECK_CSI_OFFSET(_sigsys); CHECK_CSI_SIZE (_sigsys, 3*sizeof(int)); CHECK_SI_SIZE (_sigsys, 4*sizeof(int)); + BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10); + BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x18); + BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x1C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall) != 0x10); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch) != 0x14); + /* any new si_fields should be added here */ } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 3d9b2308e7fa..03f3d7695dac 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -577,7 +577,6 @@ do_general_protection(struct pt_regs *regs, long error_code) } NOKPROBE_SYMBOL(do_general_protection); -/* May run on IST stack. */ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { #ifdef CONFIG_DYNAMIC_FTRACE @@ -592,6 +591,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; + /* + * Use ist_enter despite the fact that we don't use an IST stack. + * We can be called from a kprobe in non-CONTEXT_KERNEL kernel + * mode or even during context tracking state changes. + * + * This means that we can't schedule. That's okay. + */ ist_enter(regs); RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -609,15 +615,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) SIGTRAP) == NOTIFY_STOP) goto exit; - /* - * Let others (NMI) know that the debug stack is in use - * as we may switch to the interrupt stack. - */ - debug_stack_usage_inc(); cond_local_irq_enable(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); cond_local_irq_disable(regs); - debug_stack_usage_dec(); + exit: ist_exit(regs); } diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 1f9188f5357c..feb28fee6cea 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -5,7 +5,6 @@ #include <asm/unwind.h> #include <asm/orc_types.h> #include <asm/orc_lookup.h> -#include <asm/sections.h> #define orc_warn(fmt, ...) \ printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) @@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext) + if (init_kernel_text(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 5edb27f1a2c4..9d0b5af7db91 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -727,7 +727,8 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) return; check_vip: - if (VEFLAGS & X86_EFLAGS_VIP) { + if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) == + (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) { save_v86_state(regs, VM86_STI); return; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 9b138a06c1a4..b854ebf5851b 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -118,9 +118,11 @@ SECTIONS #ifdef CONFIG_X86_64 . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_start) = .; _entry_trampoline = .; *(.entry_trampoline) . = ALIGN(PAGE_SIZE); + VMLINUX_SYMBOL(__entry_trampoline_end) = .; ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); #endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a0c5a69bc7c4..b671fc2d0422 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -607,7 +607,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | (1 << KVM_FEATURE_PV_UNHALT) | - (1 << KVM_FEATURE_PV_TLB_FLUSH); + (1 << KVM_FEATURE_PV_TLB_FLUSH) | + (1 << KVM_FEATURE_ASYNC_PF_VMEXIT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 924ac8ce9d50..391dda8d43b7 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2002,14 +2002,13 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { - struct kvm_lapic *apic; + struct kvm_lapic *apic = vcpu->arch.apic; int i; - apic_debug("%s\n", __func__); + if (!apic) + return; - ASSERT(vcpu); - apic = vcpu->arch.apic; - ASSERT(apic != NULL); + apic_debug("%s\n", __func__); /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2165,7 +2164,6 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -2569,7 +2567,6 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu, true); kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 46ff304140c7..763bb3bade63 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, else pte_access &= ~ACC_WRITE_MASK; + if (!kvm_is_mmio_pfn(pfn)) + spte |= shadow_me_mask; + spte |= (u64)pfn << PAGE_SHIFT; - spte |= shadow_me_mask; if (pte_access & ACC_WRITE_MASK) { @@ -3029,7 +3031,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) return RET_PF_RETRY; } - return -EFAULT; + return RET_PF_EMULATE; } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b3e488a74828..be9c839e2c89 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -49,6 +49,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/microcode.h> #include <asm/nospec-branch.h> #include <asm/virtext.h> @@ -178,6 +179,8 @@ struct vcpu_svm { uint64_t sysenter_eip; uint64_t tsc_aux; + u64 msr_decfg; + u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; @@ -300,6 +303,8 @@ module_param(vgif, int, 0444); static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); module_param(sev, int, 0444); +static u8 rsm_ins_bytes[] = "\x0f\xaa"; + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -1383,6 +1388,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_SKINIT); set_intercept(svm, INTERCEPT_WBINVD); set_intercept(svm, INTERCEPT_XSETBV); + set_intercept(svm, INTERCEPT_RSM); if (!kvm_mwait_in_guest()) { set_intercept(svm, INTERCEPT_MONITOR); @@ -1902,6 +1908,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 dummy; u32 eax = 1; + vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; if (!init_event) { @@ -3699,6 +3706,12 @@ static int emulate_on_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } +static int rsm_interception(struct vcpu_svm *svm) +{ + return x86_emulate_instruction(&svm->vcpu, 0, 0, + rsm_ins_bytes, 2) == EMULATE_DONE; +} + static int rdpmc_interception(struct vcpu_svm *svm) { int err; @@ -3860,6 +3873,22 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } +static int svm_get_msr_feature(struct kvm_msr_entry *msr) +{ + msr->data = 0; + + switch (msr->index) { + case MSR_F10H_DECFG: + if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE; + break; + default: + return 1; + } + + return 0; +} + static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3935,9 +3964,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = svm->spec_ctrl; break; - case MSR_IA32_UCODE_REV: - msr_info->data = 0x01000065; - break; case MSR_F15H_IC_CFG: { int family, model; @@ -3955,6 +3981,9 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0x1E; } break; + case MSR_F10H_DECFG: + msr_info->data = svm->msr_decfg; + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -4133,6 +4162,24 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_F10H_DECFG: { + struct kvm_msr_entry msr_entry; + + msr_entry.index = msr->index; + if (svm_get_msr_feature(&msr_entry)) + return 1; + + /* Check the supported bits */ + if (data & ~msr_entry.data) + return 1; + + /* Don't allow the guest to change a bit, #GP */ + if (!msr->host_initiated && (data ^ msr_entry.data)) + return 1; + + svm->msr_decfg = data; + break; + } case MSR_IA32_APICBASE: if (kvm_vcpu_apicv_active(vcpu)) avic_update_vapic_bar(to_svm(vcpu), data); @@ -4541,7 +4588,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = npf_interception, - [SVM_EXIT_RSM] = emulate_on_interception, + [SVM_EXIT_RSM] = rsm_interception, [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, }; @@ -5355,7 +5402,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5464,11 +5511,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (svm->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -6236,16 +6283,18 @@ e_free: static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) { + void __user *measure = (void __user *)(uintptr_t)argp->data; struct kvm_sev_info *sev = &kvm->arch.sev_info; struct sev_data_launch_measure *data; struct kvm_sev_launch_measure params; + void __user *p = NULL; void *blob = NULL; int ret; if (!sev_guest(kvm)) return -ENOTTY; - if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL); @@ -6256,17 +6305,13 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!params.len) goto cmd; - if (params.uaddr) { + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { if (params.len > SEV_FW_BLOB_MAX_SIZE) { ret = -EINVAL; goto e_free; } - if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) { - ret = -EFAULT; - goto e_free; - } - ret = -ENOMEM; blob = kmalloc(params.len, GFP_KERNEL); if (!blob) @@ -6290,13 +6335,13 @@ cmd: goto e_free_blob; if (blob) { - if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len)) + if (copy_to_user(p, blob, params.len)) ret = -EFAULT; } done: params.len = data->len; - if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + if (copy_to_user(measure, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); @@ -6597,7 +6642,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) struct page **pages; void *blob, *hdr; unsigned long n; - int ret; + int ret, offset; if (!sev_guest(kvm)) return -ENOTTY; @@ -6623,6 +6668,10 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) if (!data) goto e_unpin_memory; + offset = params.guest_uaddr & (PAGE_SIZE - 1); + data->guest_address = __sme_page_pa(pages[0]) + offset; + data->guest_len = params.guest_len; + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); if (IS_ERR(blob)) { ret = PTR_ERR(blob); @@ -6637,8 +6686,8 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) ret = PTR_ERR(hdr); goto e_free_blob; } - data->trans_address = __psp_pa(blob); - data->trans_len = params.trans_len; + data->hdr_address = __psp_pa(hdr); + data->hdr_len = params.hdr_len; data->handle = sev->handle; ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); @@ -6821,6 +6870,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_unblocking = svm_vcpu_unblocking, .update_bp_intercept = update_bp_intercept, + .get_msr_feature = svm_get_msr_feature, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 3dec126aa302..2d87603f9179 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -51,6 +51,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> #include <asm/mmu_context.h> +#include <asm/microcode.h> #include <asm/nospec-branch.h> #include "trace.h" @@ -1044,6 +1045,13 @@ static inline bool is_machine_check(u32 intr_info) (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); } +/* Undocumented: icebp/int1 */ +static inline bool is_icebp(u32 intr_info) +{ + return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) + == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK); +} + static inline bool cpu_has_vmx_msr_bitmap(void) { return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS; @@ -3226,6 +3234,11 @@ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, return !(val & ~valid_bits); } +static int vmx_get_msr_feature(struct kvm_msr_entry *msr) +{ + return 1; +} + /* * Reads an msr value (of 'msr_index') into 'pdata'. * Returns 0 on success, non-0 otherwise. @@ -4485,7 +4498,8 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); hw_cr4 &= ~X86_CR4_UMIP; - } else + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); @@ -5765,6 +5779,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->rmode.vm86_active = 0; vmx->spec_ctrl = 0; + vcpu->arch.microcode_version = 0x100000000ULL; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(vcpu, 0); @@ -6171,7 +6186,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { vcpu->arch.dr6 &= ~15; vcpu->arch.dr6 |= dr6 | DR6_RTM; - if (!(dr6 & ~DR6_RESERVED)) /* icebp */ + if (is_icebp(intr_info)) skip_emulated_instruction(vcpu); kvm_queue_exception(vcpu, DB_VECTOR); @@ -9452,7 +9467,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * being speculatively taken. */ if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); vmx->__launched = vmx->loaded_vmcs->launched; asm( @@ -9587,11 +9602,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)) - rdmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); if (vmx->spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, 0); + native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); /* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -11199,7 +11214,12 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (ret) return ret; - if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) + /* + * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken + * by event injection, halt vcpu. + */ + if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && + !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; @@ -12290,6 +12310,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .vcpu_put = vmx_vcpu_put, .update_bp_intercept = update_exception_bitmap, + .get_msr_feature = vmx_get_msr_feature, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c8a0b545ac20..18b5ca7a3197 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1049,6 +1049,45 @@ static u32 emulated_msrs[] = { static unsigned num_emulated_msrs; +/* + * List of msr numbers which are used to expose MSR-based features that + * can be used by a hypervisor to validate requested CPU features. + */ +static u32 msr_based_features[] = { + MSR_F10H_DECFG, + MSR_IA32_UCODE_REV, +}; + +static unsigned int num_msr_based_features; + +static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +{ + switch (msr->index) { + case MSR_IA32_UCODE_REV: + rdmsrl(msr->index, msr->data); + break; + default: + if (kvm_x86_ops->get_msr_feature(msr)) + return 1; + } + return 0; +} + +static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct kvm_msr_entry msr; + int r; + + msr.index = index; + r = kvm_get_msr_feature(&msr); + if (r) + return r; + + *data = msr.data; + + return 0; +} + bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) @@ -2222,7 +2261,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_AMD64_NB_CFG: - case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: case MSR_VM_HSAVE_PA: case MSR_AMD64_PATCH_LOADER: @@ -2230,6 +2268,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_DC_CFG: break; + case MSR_IA32_UCODE_REV: + if (msr_info->host_initiated) + vcpu->arch.microcode_version = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2525,7 +2567,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0; break; case MSR_IA32_UCODE_REV: - msr_info->data = 0x100000000ULL; + msr_info->data = vcpu->arch.microcode_version; break; case MSR_MTRRcap: case 0x200 ... 0x2ff: @@ -2680,13 +2722,11 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { - int i, idx; + int i; - idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; - srcu_read_unlock(&vcpu->kvm->srcu, idx); return i; } @@ -2785,6 +2825,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SET_BOOT_CPU_ID: case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_GET_MSR_FEATURES: r = 1; break; case KVM_CAP_ADJUST_CLOCK: @@ -2899,6 +2940,31 @@ long kvm_arch_dev_ioctl(struct file *filp, goto out; r = 0; break; + case KVM_GET_MSR_FEATURE_INDEX_LIST: { + struct kvm_msr_list __user *user_msr_list = argp; + struct kvm_msr_list msr_list; + unsigned int n; + + r = -EFAULT; + if (copy_from_user(&msr_list, user_msr_list, sizeof(msr_list))) + goto out; + n = msr_list.nmsrs; + msr_list.nmsrs = num_msr_based_features; + if (copy_to_user(user_msr_list, &msr_list, sizeof(msr_list))) + goto out; + r = -E2BIG; + if (n < msr_list.nmsrs) + goto out; + r = -EFAULT; + if (copy_to_user(user_msr_list->indices, &msr_based_features, + num_msr_based_features * sizeof(u32))) + goto out; + r = 0; + break; + } + case KVM_GET_MSRS: + r = msr_io(NULL, argp, do_get_msr_feature, 1); + break; } default: r = -EINVAL; @@ -3636,12 +3702,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_MSRS: + case KVM_GET_MSRS: { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_get_msr, 1); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; - case KVM_SET_MSRS: + } + case KVM_SET_MSRS: { + int idx = srcu_read_lock(&vcpu->kvm->srcu); r = msr_io(vcpu, argp, do_set_msr, 0); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; + } case KVM_TPR_ACCESS_REPORTING: { struct kvm_tpr_access_ctl tac; @@ -4464,6 +4536,19 @@ static void kvm_init_msr_list(void) j++; } num_emulated_msrs = j; + + for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + struct kvm_msr_entry msr; + + msr.index = msr_based_features[i]; + if (kvm_get_msr_feature(&msr)) + continue; + + if (j < i) + msr_based_features[j] = msr_based_features[i]; + j++; + } + num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -8017,6 +8102,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + kvm_lapic_reset(vcpu, init_event); + vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; @@ -8460,10 +8547,8 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) return r; } - if (!size) { - r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); - WARN_ON(r < 0); - } + if (!size) + vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); return 0; } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 91e9700cc6dc..25a972c61b0a 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -28,7 +28,6 @@ lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RETPOLINE) += retpoline.o -OBJECT_FILES_NON_STANDARD_retpoline.o :=y obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 480edc3a5e03..c909961e678a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -7,7 +7,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> #include <asm/nospec-branch.h> -#include <asm/bitsperlong.h> .macro THUNK reg .section .text.__x86.indirect_thunk @@ -47,58 +46,3 @@ GENERATE_THUNK(r13) GENERATE_THUNK(r14) GENERATE_THUNK(r15) #endif - -/* - * Fill the CPU return stack buffer. - * - * Each entry in the RSB, if used for a speculative 'ret', contains an - * infinite 'pause; lfence; jmp' loop to capture speculative execution. - * - * This is required in various cases for retpoline and IBRS-based - * mitigations for the Spectre variant 2 vulnerability. Sometimes to - * eliminate potentially bogus entries from the RSB, and sometimes - * purely to ensure that it doesn't get empty, which on some CPUs would - * allow predictions from other (unwanted!) sources to be used. - * - * Google experimented with loop-unrolling and this turned out to be - * the optimal version - two calls, each with their own speculation - * trap should their return address end up getting used, in a loop. - */ -.macro STUFF_RSB nr:req sp:req - mov $(\nr / 2), %_ASM_BX - .align 16 -771: - call 772f -773: /* speculation trap */ - pause - lfence - jmp 773b - .align 16 -772: - call 774f -775: /* speculation trap */ - pause - lfence - jmp 775b - .align 16 -774: - dec %_ASM_BX - jnz 771b - add $((BITS_PER_LONG/8) * \nr), \sp -.endm - -#define RSB_FILL_LOOPS 16 /* To avoid underflow */ - -ENTRY(__fill_rsb) - STUFF_RSB RSB_FILL_LOOPS, %_ASM_SP - ret -END(__fill_rsb) -EXPORT_SYMBOL_GPL(__fill_rsb) - -#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ - -ENTRY(__clear_rsb) - STUFF_RSB RSB_CLEAR_LOOPS, %_ASM_SP - ret -END(__clear_rsb) -EXPORT_SYMBOL_GPL(__clear_rsb) diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index b9283cc27622..476d810639a8 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -163,4 +163,10 @@ void __init setup_cpu_entry_areas(void) for_each_possible_cpu(cpu) setup_cpu_entry_area(cpu); + + /* + * This is the last essential update to swapper_pgdir which needs + * to be synchronized to initial_page_table on 32bit. + */ + sync_initial_page_table(); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 800de815519c..25a30b5d6582 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -330,7 +330,7 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; - if (pmd_huge(*pmd_k)) + if (pmd_large(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); @@ -475,7 +475,7 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); - if (pud_huge(*pud)) + if (pud_large(*pud)) return 0; pmd = pmd_offset(pud, address); @@ -486,7 +486,7 @@ static noinline int vmalloc_fault(unsigned long address) if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); - if (pmd_huge(*pmd)) + if (pmd_large(*pmd)) return 0; pte_ref = pte_offset_kernel(pmd_ref, address); @@ -1248,10 +1248,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, tsk = current; mm = tsk->mm; - /* - * Detect and handle instructions that would cause a page fault for - * both a tracked kernel page and a userspace page. - */ prefetchw(&mm->mmap_sem); if (unlikely(kmmio_fault(regs, address))) diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 79cb066f40c0..396e1f0151ac 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -453,6 +453,21 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base) } #endif /* CONFIG_HIGHMEM */ +void __init sync_initial_page_table(void) +{ + clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); +} + void __init native_pagetable_init(void) { unsigned long pfn, va; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 8b72923f1d35..af11a2890235 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -800,17 +800,11 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, #define PAGE_INUSE 0xFD -static void __meminit free_pagetable(struct page *page, int order, - struct vmem_altmap *altmap) +static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; - if (altmap) { - vmem_altmap_free(altmap, nr_pages); - return; - } - /* bootmem page has reserved flag */ if (PageReserved(page)) { __ClearPageReserved(page); @@ -826,9 +820,17 @@ static void __meminit free_pagetable(struct page *page, int order, free_pages((unsigned long)page_address(page), order); } -static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd, +static void __meminit free_hugepage_table(struct page *page, struct vmem_altmap *altmap) { + if (altmap) + vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE); + else + free_pagetable(page, get_order(PMD_SIZE)); +} + +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ pte_t *pte; int i; @@ -839,14 +841,13 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd, } /* free a pte talbe */ - free_pagetable(pmd_page(*pmd), 0, altmap); + free_pagetable(pmd_page(*pmd), 0); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); spin_unlock(&init_mm.page_table_lock); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, - struct vmem_altmap *altmap) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) { pmd_t *pmd; int i; @@ -858,14 +859,13 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, } /* free a pmd talbe */ - free_pagetable(pud_page(*pud), 0, altmap); + free_pagetable(pud_page(*pud), 0); spin_lock(&init_mm.page_table_lock); pud_clear(pud); spin_unlock(&init_mm.page_table_lock); } -static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, - struct vmem_altmap *altmap) +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) { pud_t *pud; int i; @@ -877,7 +877,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, } /* free a pud talbe */ - free_pagetable(p4d_page(*p4d), 0, altmap); + free_pagetable(p4d_page(*p4d), 0); spin_lock(&init_mm.page_table_lock); p4d_clear(p4d); spin_unlock(&init_mm.page_table_lock); @@ -885,7 +885,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d, static void __meminit remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, - struct vmem_altmap *altmap, bool direct) + bool direct) { unsigned long next, pages = 0; pte_t *pte; @@ -916,7 +916,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, * freed when offlining, or simplely not in use. */ if (!direct) - free_pagetable(pte_page(*pte), 0, altmap); + free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); @@ -939,7 +939,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, page_addr = page_address(pte_page(*pte)); if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) { - free_pagetable(pte_page(*pte), 0, altmap); + free_pagetable(pte_page(*pte), 0); spin_lock(&init_mm.page_table_lock); pte_clear(&init_mm, addr, pte); @@ -974,9 +974,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE)) { if (!direct) - free_pagetable(pmd_page(*pmd), - get_order(PMD_SIZE), - altmap); + free_hugepage_table(pmd_page(*pmd), + altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -989,9 +988,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, page_addr = page_address(pmd_page(*pmd)); if (!memchr_inv(page_addr, PAGE_INUSE, PMD_SIZE)) { - free_pagetable(pmd_page(*pmd), - get_order(PMD_SIZE), - altmap); + free_hugepage_table(pmd_page(*pmd), + altmap); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -1003,8 +1001,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, } pte_base = (pte_t *)pmd_page_vaddr(*pmd); - remove_pte_table(pte_base, addr, next, altmap, direct); - free_pte_table(pte_base, pmd, altmap); + remove_pte_table(pte_base, addr, next, direct); + free_pte_table(pte_base, pmd); } /* Call free_pmd_table() in remove_pud_table(). */ @@ -1033,8 +1031,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, IS_ALIGNED(next, PUD_SIZE)) { if (!direct) free_pagetable(pud_page(*pud), - get_order(PUD_SIZE), - altmap); + get_order(PUD_SIZE)); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1048,8 +1045,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!memchr_inv(page_addr, PAGE_INUSE, PUD_SIZE)) { free_pagetable(pud_page(*pud), - get_order(PUD_SIZE), - altmap); + get_order(PUD_SIZE)); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1062,7 +1058,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, pmd_base = pmd_offset(pud, 0); remove_pmd_table(pmd_base, addr, next, direct, altmap); - free_pmd_table(pmd_base, pud, altmap); + free_pmd_table(pmd_base, pud); } if (direct) @@ -1094,7 +1090,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, * to adapt for boot-time switching between 4 and 5 level page tables. */ if (CONFIG_PGTABLE_LEVELS == 5) - free_pud_table(pud_base, p4d, altmap); + free_pud_table(pud_base, p4d); } if (direct) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 01f682cf77a8..40a6085063d6 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -15,6 +15,7 @@ #include <asm/page.h> #include <asm/processor-flags.h> #include <asm/msr-index.h> +#include <asm/nospec-branch.h> .text .code64 @@ -59,6 +60,7 @@ ENTRY(sme_encrypt_execute) movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ + ANNOTATE_RETPOLINE_SAFE call *%rax /* Call the encryption routine */ pop %r12 diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 004abf9ebf12..34cda7e0551b 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -702,4 +702,52 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } + +/** + * pud_free_pmd_page - Clear pud entry and free pmd page. + * @pud: Pointer to a PUD. + * + * Context: The pud range has been unmaped and TLB purged. + * Return: 1 if clearing the entry succeeded. 0 otherwise. + */ +int pud_free_pmd_page(pud_t *pud) +{ + pmd_t *pmd; + int i; + + if (pud_none(*pud)) + return 1; + + pmd = (pmd_t *)pud_page_vaddr(*pud); + + for (i = 0; i < PTRS_PER_PMD; i++) + if (!pmd_free_pte_page(&pmd[i])) + return 0; + + pud_clear(pud); + free_page((unsigned long)pmd); + + return 1; +} + +/** + * pmd_free_pte_page - Clear pmd entry and free pte page. + * @pmd: Pointer to a PMD. + * + * Context: The pmd range has been unmaped and TLB purged. + * Return: 1 if clearing the entry succeeded. 0 otherwise. + */ +int pmd_free_pte_page(pmd_t *pmd) +{ + pte_t *pte; + + if (pmd_none(*pmd)) + return 1; + + pte = (pte_t *)pmd_page_vaddr(*pmd); + pmd_clear(pmd); + free_page((unsigned long)pte); + + return 1; +} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index ce38f165489b..631507f0c198 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void) } /* - * Clone the ESPFIX P4D into the user space visinble page table + * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 45e4eb5bcbb2..ce5b2ebd5701 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1188,7 +1188,7 @@ skip_init_addrs: * may converge on the last pass. In such case do one more * pass to emit the final image */ - for (pass = 0; pass < 10 || image; pass++) { + for (pass = 0; pass < 20 || image; pass++) { proglen = do_jit(prog, addrs, image, oldproglen, &ctx); if (proglen <= 0) { image = NULL; @@ -1215,6 +1215,7 @@ skip_init_addrs: } } oldproglen = proglen; + cond_resched(); } if (bpf_jit_enable > 1) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index c310a8284358..f9cfbc0d1f33 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -227,7 +227,7 @@ int __init efi_alloc_page_tables(void) if (!pud) { if (CONFIG_PGTABLE_LEVELS > 4) free_page((unsigned long) pgd_page_vaddr(*pgd)); - free_page((unsigned long)efi_pgd); + free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); return -ENOMEM; } diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 2c67bae6bb53..fb1df9488e98 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -79,7 +79,7 @@ static void intel_mid_power_off(void) static void intel_mid_reboot(void) { - intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0); + intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0); } static unsigned long __init intel_mid_calibrate_tsc(void) diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index de53bd15df5a..24bb7598774e 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -102,7 +102,7 @@ ENTRY(startup_32) * don't we'll eventually crash trying to execute encrypted * instructions. */ - bt $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags + btl $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags jnc .Ldone movl $MSR_K8_SYSCFG, %ecx rdmsr diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index b7d73400ea29..f31e5d903161 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -30,11 +30,7 @@ #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_PPRO_FENCE -#define dma_rmb() rmb() -#else /* CONFIG_X86_PPRO_FENCE */ #define dma_rmb() barrier() -#endif /* CONFIG_X86_PPRO_FENCE */ #define dma_wmb() barrier() #include <asm-generic/barrier.h> diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index c047f42552e1..3c2c2530737e 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1376,8 +1376,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (!xen_initial_domain()) { add_preferred_console("xenboot", 0, NULL); - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; } else { @@ -1410,6 +1408,10 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_boot_params_init_edd(); } + + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ pci_probe &= ~PCI_PROBE_BIOS; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index d9f96cc5d743..1d83152c761b 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,12 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/tick.h> +#include <linux/percpu-defs.h> #include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> +#include <asm/cpufeatures.h> +#include <asm/msr-index.h> #include <asm/xen/hypercall.h> #include <asm/xen/page.h> #include <asm/fixmap.h> @@ -15,6 +18,8 @@ #include "mmu.h" #include "pmu.h" +static DEFINE_PER_CPU(u64, spec_ctrl); + void xen_arch_pre_suspend(void) { xen_save_time_memory_area(); @@ -35,6 +40,9 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl)); + /* Boot processor notified via generic timekeeping_resume() */ if (smp_processor_id() == 0) return; @@ -44,7 +52,15 @@ static void xen_vcpu_notify_restore(void *data) static void xen_vcpu_notify_suspend(void *data) { + u64 tmp; + tick_suspend_local(); + + if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) { + rdmsrl(MSR_IA32_SPEC_CTRL, tmp); + this_cpu_write(spec_ctrl, tmp); + wrmsrl(MSR_IA32_SPEC_CTRL, 0); + } } void xen_arch_resume(void) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4117524ca45b..c2033a232a44 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -812,7 +812,6 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; - struct module *owner; unsigned int major, minor; int key_len, part, ret; char *body; @@ -904,9 +903,7 @@ fail_unlock: spin_unlock_irq(q->queue_lock); rcu_read_unlock(); fail: - owner = disk->fops->owner; - put_disk(disk); - module_put(owner); + put_disk_and_module(disk); /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue @@ -931,13 +928,9 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep); void blkg_conf_finish(struct blkg_conf_ctx *ctx) __releases(ctx->disk->queue->queue_lock) __releases(rcu) { - struct module *owner; - spin_unlock_irq(ctx->disk->queue->queue_lock); rcu_read_unlock(); - owner = ctx->disk->fops->owner; - put_disk(ctx->disk); - module_put(owner); + put_disk_and_module(ctx->disk); } EXPORT_SYMBOL_GPL(blkg_conf_finish); diff --git a/block/blk-core.c b/block/blk-core.c index 2d1a7bbe0634..6d82c4f7fadd 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2434,7 +2434,7 @@ blk_qc_t submit_bio(struct bio *bio) unsigned int count; if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) - count = queue_logical_block_size(bio->bi_disk->queue); + count = queue_logical_block_size(bio->bi_disk->queue) >> 9; else count = bio_sectors(bio); diff --git a/block/blk-mq.c b/block/blk-mq.c index 357492712b0e..16e83e6df404 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -712,7 +712,6 @@ static void __blk_mq_requeue_request(struct request *rq) trace_block_rq_requeue(q, rq); wbt_requeue(q->rq_wb, &rq->issue_stat); - blk_mq_sched_requeue_request(rq); if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) { blk_mq_rq_update_state(rq, MQ_RQ_IDLE); @@ -725,6 +724,9 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { __blk_mq_requeue_request(rq); + /* this request will be re-inserted to io scheduler queue */ + blk_mq_sched_requeue_request(rq); + BUG_ON(blk_queued_rq(rq)); blk_mq_add_to_requeue_list(rq, true, kick_requeue_list); } diff --git a/block/genhd.c b/block/genhd.c index 88a53c188cb7..9656f9e9f99e 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -547,7 +547,7 @@ static int exact_lock(dev_t devt, void *data) { struct gendisk *p = data; - if (!get_disk(p)) + if (!get_disk_and_module(p)) return -1; return 0; } @@ -717,6 +717,11 @@ void del_gendisk(struct gendisk *disk) blk_integrity_del(disk); disk_del_events(disk); + /* + * Block lookups of the disk until all bdevs are unhashed and the + * disk is marked as dead (GENHD_FL_UP cleared). + */ + down_write(&disk->lookup_sem); /* invalidate stuff */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE); @@ -731,6 +736,7 @@ void del_gendisk(struct gendisk *disk) bdev_unhash_inode(disk_devt(disk)); set_capacity(disk, 0); disk->flags &= ~GENHD_FL_UP; + up_write(&disk->lookup_sem); if (!(disk->flags & GENHD_FL_HIDDEN)) sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -809,16 +815,28 @@ struct gendisk *get_gendisk(dev_t devt, int *partno) spin_lock_bh(&ext_devt_lock); part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); - if (part && get_disk(part_to_disk(part))) { + if (part && get_disk_and_module(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } spin_unlock_bh(&ext_devt_lock); } - if (disk && unlikely(disk->flags & GENHD_FL_HIDDEN)) { - put_disk(disk); + if (!disk) + return NULL; + + /* + * Synchronize with del_gendisk() to not return disk that is being + * destroyed. + */ + down_read(&disk->lookup_sem); + if (unlikely((disk->flags & GENHD_FL_HIDDEN) || + !(disk->flags & GENHD_FL_UP))) { + up_read(&disk->lookup_sem); + put_disk_and_module(disk); disk = NULL; + } else { + up_read(&disk->lookup_sem); } return disk; } @@ -1418,6 +1436,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) kfree(disk); return NULL; } + init_rwsem(&disk->lookup_sem); disk->node_id = node_id; if (disk_expand_part_tbl(disk, 0)) { free_part_stats(&disk->part0); @@ -1453,7 +1472,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) } EXPORT_SYMBOL(__alloc_disk_node); -struct kobject *get_disk(struct gendisk *disk) +struct kobject *get_disk_and_module(struct gendisk *disk) { struct module *owner; struct kobject *kobj; @@ -1471,17 +1490,30 @@ struct kobject *get_disk(struct gendisk *disk) return kobj; } - -EXPORT_SYMBOL(get_disk); +EXPORT_SYMBOL(get_disk_and_module); void put_disk(struct gendisk *disk) { if (disk) kobject_put(&disk_to_dev(disk)->kobj); } - EXPORT_SYMBOL(put_disk); +/* + * This is a counterpart of get_disk_and_module() and thus also of + * get_gendisk(). + */ +void put_disk_and_module(struct gendisk *disk) +{ + if (disk) { + struct module *owner = disk->fops->owner; + + put_disk(disk); + module_put(owner); + } +} +EXPORT_SYMBOL(put_disk_and_module); + static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; diff --git a/block/ioctl.c b/block/ioctl.c index 1668506d8ed8..3884d810efd2 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -225,7 +225,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, if (start + len > i_size_read(bdev->bd_inode)) return -EINVAL; - truncate_inode_pages_range(mapping, start, start + len); + truncate_inode_pages_range(mapping, start, start + len - 1); return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, flags); } diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index f95c60774ce8..0d6d25e32e1f 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -833,6 +833,7 @@ static struct elevator_type kyber_sched = { .limit_depth = kyber_limit_depth, .prepare_request = kyber_prepare_request, .finish_request = kyber_finish_request, + .requeue_request = kyber_finish_request, .completed_request = kyber_completed_request, .dispatch_request = kyber_dispatch_request, .has_work = kyber_has_work, diff --git a/block/mq-deadline.c b/block/mq-deadline.c index c56f211c8440..8ec0ba9f5386 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -536,12 +536,21 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, } /* + * Nothing to do here. This is defined only to ensure that .finish_request + * method is called upon request completion. + */ +static void dd_prepare_request(struct request *rq, struct bio *bio) +{ +} + +/* * For zoned block devices, write unlock the target zone of * completed write requests. Do this while holding the zone lock * spinlock so that the zone is never unlocked while deadline_fifo_request() - * while deadline_next_request() are executing. + * or deadline_next_request() are executing. This function is called for + * all requests, whether or not these requests complete successfully. */ -static void dd_completed_request(struct request *rq) +static void dd_finish_request(struct request *rq) { struct request_queue *q = rq->q; @@ -756,7 +765,8 @@ static struct elevator_type mq_deadline = { .ops.mq = { .insert_requests = dd_insert_requests, .dispatch_request = dd_dispatch_request, - .completed_request = dd_completed_request, + .prepare_request = dd_prepare_request, + .finish_request = dd_finish_request, .next_request = elv_rb_latter_request, .former_request = elv_rb_former_request, .bio_merge = dd_bio_merge, diff --git a/block/partition-generic.c b/block/partition-generic.c index 91622db9aedf..08dabcd8b6ae 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -51,6 +51,12 @@ const char *bdevname(struct block_device *bdev, char *buf) EXPORT_SYMBOL(bdevname); +const char *bio_devname(struct bio *bio, char *buf) +{ + return disk_name(bio->bi_disk, bio->bi_partno, buf); +} +EXPORT_SYMBOL(bio_devname); + /* * There's very little reason to use this, you should really * have a struct block_device just about everywhere and use diff --git a/drivers/acpi/acpi_watchdog.c b/drivers/acpi/acpi_watchdog.c index 11b113f8e367..ebb626ffb5fa 100644 --- a/drivers/acpi/acpi_watchdog.c +++ b/drivers/acpi/acpi_watchdog.c @@ -74,10 +74,10 @@ void __init acpi_watchdog_init(void) res.start = gas->address; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { res.flags = IORESOURCE_MEM; - res.end = res.start + ALIGN(gas->access_width, 4); + res.end = res.start + ALIGN(gas->access_width, 4) - 1; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { res.flags = IORESOURCE_IO; - res.end = res.start + gas->access_width; + res.end = res.start + gas->access_width - 1; } else { pr_warn("Unsupported address space: %u\n", gas->space_id); diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 7128488a3a72..f2eb6c37ea0a 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -70,7 +70,6 @@ static async_cookie_t async_cookie; static bool battery_driver_registered; static int battery_bix_broken_package; static int battery_notification_delay_ms; -static int battery_full_discharging; static unsigned int cache_time = 1000; module_param(cache_time, uint, 0644); MODULE_PARM_DESC(cache_time, "cache time in milliseconds"); @@ -215,12 +214,9 @@ static int acpi_battery_get_property(struct power_supply *psy, return -ENODEV; switch (psp) { case POWER_SUPPLY_PROP_STATUS: - if (battery->state & ACPI_BATTERY_STATE_DISCHARGING) { - if (battery_full_discharging && battery->rate_now == 0) - val->intval = POWER_SUPPLY_STATUS_FULL; - else - val->intval = POWER_SUPPLY_STATUS_DISCHARGING; - } else if (battery->state & ACPI_BATTERY_STATE_CHARGING) + if (battery->state & ACPI_BATTERY_STATE_DISCHARGING) + val->intval = POWER_SUPPLY_STATUS_DISCHARGING; + else if (battery->state & ACPI_BATTERY_STATE_CHARGING) val->intval = POWER_SUPPLY_STATUS_CHARGING; else if (acpi_battery_is_charged(battery)) val->intval = POWER_SUPPLY_STATUS_FULL; @@ -1170,12 +1166,6 @@ battery_notification_delay_quirk(const struct dmi_system_id *d) return 0; } -static int __init battery_full_discharging_quirk(const struct dmi_system_id *d) -{ - battery_full_discharging = 1; - return 0; -} - static const struct dmi_system_id bat_dmi_table[] __initconst = { { .callback = battery_bix_broken_package_quirk, @@ -1193,38 +1183,6 @@ static const struct dmi_system_id bat_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-573G"), }, }, - { - .callback = battery_full_discharging_quirk, - .ident = "ASUS GL502VSK", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GL502VSK"), - }, - }, - { - .callback = battery_full_discharging_quirk, - .ident = "ASUS UX305LA", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "UX305LA"), - }, - }, - { - .callback = battery_full_discharging_quirk, - .ident = "ASUS UX360UA", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "UX360UA"), - }, - }, - { - .callback = battery_full_discharging_quirk, - .ident = "ASUS UX410UAK", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "UX410UAK"), - }, - }, {}, }; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index bbe48ad20886..eb09ef55c38a 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2675,10 +2675,14 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, else ndr_desc->numa_node = NUMA_NO_NODE; - if(acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_CACHE_FLUSH) + /* + * Persistence domain bits are hierarchical, if + * ACPI_NFIT_CAPABILITY_CACHE_FLUSH is set then + * ACPI_NFIT_CAPABILITY_MEM_FLUSH is implied. + */ + if (acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_CACHE_FLUSH) set_bit(ND_REGION_PERSIST_CACHE, &ndr_desc->flags); - - if (acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_MEM_FLUSH) + else if (acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_MEM_FLUSH) set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc->flags); list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 8ccaae3550d2..85167603b9c9 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -103,25 +103,27 @@ int acpi_map_pxm_to_node(int pxm) */ int acpi_map_pxm_to_online_node(int pxm) { - int node, n, dist, min_dist; + int node, min_node; node = acpi_map_pxm_to_node(pxm); if (node == NUMA_NO_NODE) node = 0; + min_node = node; if (!node_online(node)) { - min_dist = INT_MAX; + int min_dist = INT_MAX, dist, n; + for_each_online_node(n) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; - node = n; + min_node = n; } } } - return node; + return min_node; } EXPORT_SYMBOL(acpi_map_pxm_to_online_node); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 355a95a83a34..1ff17799769d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -550,7 +550,9 @@ static const struct pci_device_id ahci_pci_tbl[] = { .driver_data = board_ahci_yes_fbs }, { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230), .driver_data = board_ahci_yes_fbs }, - { PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642), + { PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642), /* highpoint rocketraid 642L */ + .driver_data = board_ahci_yes_fbs }, + { PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0645), /* highpoint rocketraid 644L */ .driver_data = board_ahci_yes_fbs }, /* Promise */ diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index a0de7a38430c..7adcf3caabd0 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -665,6 +665,16 @@ int ahci_stop_engine(struct ata_port *ap) if ((tmp & (PORT_CMD_START | PORT_CMD_LIST_ON)) == 0) return 0; + /* + * Don't try to issue commands but return with ENODEV if the + * AHCI controller not available anymore (e.g. due to PCIe hot + * unplugging). Otherwise a 500ms delay for each port is added. + */ + if (tmp == 0xffffffff) { + dev_err(ap->host->dev, "AHCI controller unavailable!\n"); + return -ENODEV; + } + /* setting HBA to idle */ tmp &= ~PORT_CMD_START; writel(tmp, port_mmio + PORT_CMD); diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 341d0ef82cbd..30cc8f1a31e1 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -340,7 +340,7 @@ static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port, * 2) regulator for controlling the targets power (optional) * 3) 0 - AHCI_MAX_CLKS clocks, as specified in the devs devicetree node, * or for non devicetree enabled platforms a single clock - * 4) phys (optional) + * 4) phys (optional) * * RETURNS: * The allocated ahci_host_priv on success, otherwise an ERR_PTR value diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 3c09122bf038..7431ccd03316 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4530,6 +4530,25 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, + /* Crucial BX100 SSD 500GB has broken LPM support */ + { "CT500BX100SSD1", NULL, ATA_HORKAGE_NOLPM }, + + /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ + { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NOLPM, }, + /* 512GB MX100 with newer firmware has only LPM issues */ + { "Crucial_CT512MX100*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NOLPM, }, + + /* 480GB+ M500 SSDs have both queued TRIM and LPM issues */ + { "Crucial_CT480M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NOLPM, }, + { "Crucial_CT960M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM | + ATA_HORKAGE_NOLPM, }, + /* devices that don't properly handle queued TRIM commands */ { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, @@ -4541,7 +4560,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, - { "Samsung SSD 8*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, @@ -5401,8 +5422,7 @@ void ata_qc_issue(struct ata_queued_cmd *qc) * We guarantee to LLDs that they will have at least one * non-zero sg if the command is a data command. */ - if (WARN_ON_ONCE(ata_is_data(prot) && - (!qc->sg || !qc->n_elem || !qc->nbytes))) + if (ata_is_data(prot) && (!qc->sg || !qc->n_elem || !qc->nbytes)) goto sys_err; if (ata_is_dma(prot) || (ata_is_pio(prot) && diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 11c3137d7b0a..c016829a38fd 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -815,7 +815,8 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) if (ap->pflags & ATA_PFLAG_LOADING) ap->pflags &= ~ATA_PFLAG_LOADING; - else if (ap->pflags & ATA_PFLAG_SCSI_HOTPLUG) + else if ((ap->pflags & ATA_PFLAG_SCSI_HOTPLUG) && + !(ap->flags & ATA_FLAG_SAS_HOST)) schedule_delayed_work(&ap->hotplug_task, 0); if (ap->pflags & ATA_PFLAG_RECOVERED) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 66be961c93a4..89a9d4a2efc8 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3316,6 +3316,12 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc) goto invalid_fld; } + /* We may not issue NCQ commands to devices not supporting NCQ */ + if (ata_is_ncq(tf->protocol) && !ata_ncq_enabled(dev)) { + fp = 1; + goto invalid_fld; + } + /* sanity check for pio multi commands */ if ((cdb[1] & 0xe0) && !is_multi_taskfile(tf)) { fp = 1; @@ -4282,7 +4288,7 @@ static inline void ata_scsi_dump_cdb(struct ata_port *ap, #ifdef ATA_DEBUG struct scsi_device *scsidev = cmd->device; - DPRINTK("CDB (%u:%d,%d,%d) %9ph\n", + DPRINTK("CDB (%u:%d,%d,%lld) %9ph\n", ap->print_id, scsidev->channel, scsidev->id, scsidev->lun, cmd->cmnd); @@ -4309,7 +4315,9 @@ static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, if (likely((scsi_op != ATA_16) || !atapi_passthru16)) { /* relay SCSI command to ATAPI device */ int len = COMMAND_SIZE(scsi_op); - if (unlikely(len > scmd->cmd_len || len > dev->cdb_len)) + if (unlikely(len > scmd->cmd_len || + len > dev->cdb_len || + scmd->cmd_len > ATAPI_CDB_LEN)) goto bad_cdb_len; xlat_func = atapi_xlat; diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 80ee2f2a50d0..6456e07db72a 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -146,6 +146,7 @@ enum sata_rcar_type { RCAR_GEN1_SATA, RCAR_GEN2_SATA, + RCAR_GEN3_SATA, RCAR_R8A7790_ES1_SATA, }; @@ -784,26 +785,11 @@ static void sata_rcar_setup_port(struct ata_host *host) ioaddr->command_addr = ioaddr->cmd_addr + (ATA_REG_CMD << 2); } -static void sata_rcar_init_controller(struct ata_host *host) +static void sata_rcar_init_module(struct sata_rcar_priv *priv) { - struct sata_rcar_priv *priv = host->private_data; void __iomem *base = priv->base; u32 val; - /* reset and setup phy */ - switch (priv->type) { - case RCAR_GEN1_SATA: - sata_rcar_gen1_phy_init(priv); - break; - case RCAR_GEN2_SATA: - case RCAR_R8A7790_ES1_SATA: - sata_rcar_gen2_phy_init(priv); - break; - default: - dev_warn(host->dev, "SATA phy is not initialized\n"); - break; - } - /* SATA-IP reset state */ val = ioread32(base + ATAPI_CONTROL1_REG); val |= ATAPI_CONTROL1_RESET; @@ -824,10 +810,33 @@ static void sata_rcar_init_controller(struct ata_host *host) /* ack and mask */ iowrite32(0, base + SATAINTSTAT_REG); iowrite32(0x7ff, base + SATAINTMASK_REG); + /* enable interrupts */ iowrite32(ATAPI_INT_ENABLE_SATAINT, base + ATAPI_INT_ENABLE_REG); } +static void sata_rcar_init_controller(struct ata_host *host) +{ + struct sata_rcar_priv *priv = host->private_data; + + /* reset and setup phy */ + switch (priv->type) { + case RCAR_GEN1_SATA: + sata_rcar_gen1_phy_init(priv); + break; + case RCAR_GEN2_SATA: + case RCAR_GEN3_SATA: + case RCAR_R8A7790_ES1_SATA: + sata_rcar_gen2_phy_init(priv); + break; + default: + dev_warn(host->dev, "SATA phy is not initialized\n"); + break; + } + + sata_rcar_init_module(priv); +} + static const struct of_device_id sata_rcar_match[] = { { /* Deprecated by "renesas,sata-r8a7779" */ @@ -856,7 +865,7 @@ static const struct of_device_id sata_rcar_match[] = { }, { .compatible = "renesas,sata-r8a7795", - .data = (void *)RCAR_GEN2_SATA + .data = (void *)RCAR_GEN3_SATA }, { .compatible = "renesas,rcar-gen2-sata", @@ -864,7 +873,7 @@ static const struct of_device_id sata_rcar_match[] = { }, { .compatible = "renesas,rcar-gen3-sata", - .data = (void *)RCAR_GEN2_SATA + .data = (void *)RCAR_GEN3_SATA }, { }, }; @@ -982,11 +991,18 @@ static int sata_rcar_resume(struct device *dev) if (ret) return ret; - /* ack and mask */ - iowrite32(0, base + SATAINTSTAT_REG); - iowrite32(0x7ff, base + SATAINTMASK_REG); - /* enable interrupts */ - iowrite32(ATAPI_INT_ENABLE_SATAINT, base + ATAPI_INT_ENABLE_REG); + if (priv->type == RCAR_GEN3_SATA) { + sata_rcar_gen2_phy_init(priv); + sata_rcar_init_module(priv); + } else { + /* ack and mask */ + iowrite32(0, base + SATAINTSTAT_REG); + iowrite32(0x7ff, base + SATAINTMASK_REG); + + /* enable interrupts */ + iowrite32(ATAPI_INT_ENABLE_SATAINT, + base + ATAPI_INT_ENABLE_REG); + } ata_host_resume(host); diff --git a/drivers/auxdisplay/img-ascii-lcd.c b/drivers/auxdisplay/img-ascii-lcd.c index 9180b9bd5821..834509506ef6 100644 --- a/drivers/auxdisplay/img-ascii-lcd.c +++ b/drivers/auxdisplay/img-ascii-lcd.c @@ -97,7 +97,7 @@ static struct img_ascii_lcd_config boston_config = { static void malta_update(struct img_ascii_lcd_ctx *ctx) { unsigned int i; - int err; + int err = 0; for (i = 0; i < ctx->cfg->num_chars; i++) { err = regmap_write(ctx->regmap, @@ -180,7 +180,7 @@ static int sead3_wait_lcd_idle(struct img_ascii_lcd_ctx *ctx) static void sead3_update(struct img_ascii_lcd_ctx *ctx) { unsigned int i; - int err; + int err = 0; for (i = 0; i < ctx->cfg->num_chars; i++) { err = sead3_wait_lcd_idle(ctx); @@ -224,7 +224,7 @@ MODULE_DEVICE_TABLE(of, img_ascii_lcd_matches); /** * img_ascii_lcd_scroll() - scroll the display by a character - * @arg: really a pointer to the private data structure + * @t: really a pointer to the private data structure * * Scroll the current message along the LCD by one character, rearming the * timer if required. diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index ea7869c0d7f9..ec5e8800f8ad 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -1372,7 +1372,7 @@ static void panel_process_inputs(void) break; input->rise_timer = 0; input->state = INPUT_ST_RISING; - /* no break here, fall through */ + /* fall through */ case INPUT_ST_RISING: if ((phys_curr & input->mask) != input->value) { input->state = INPUT_ST_LOW; @@ -1385,11 +1385,11 @@ static void panel_process_inputs(void) } input->high_timer = 0; input->state = INPUT_ST_HIGH; - /* no break here, fall through */ + /* fall through */ case INPUT_ST_HIGH: if (input_state_high(input)) break; - /* no break here, fall through */ + /* fall through */ case INPUT_ST_FALLING: input_state_falling(input); } diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index e5aa62fcf5a8..3aaf6af3ec23 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1758,7 +1758,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) if (unit[drive].type->code == FD_NODRIVE) return NULL; *part = 0; - return get_disk(unit[drive].gendisk); + return get_disk_and_module(unit[drive].gendisk); } static int __init amiga_floppy_probe(struct platform_device *pdev) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 8bc3b9fd8dd2..dfb2c2622e5a 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1917,7 +1917,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) if (drive >= FD_MAX_UNITS || type > NUM_DISK_MINORS) return NULL; *part = 0; - return get_disk(unit[drive].disk); + return get_disk_and_module(unit[drive].disk); } static int __init atari_floppy_init (void) diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 8028a3a7e7fd..deea78e485da 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -456,7 +456,7 @@ static struct kobject *brd_probe(dev_t dev, int *part, void *data) mutex_lock(&brd_devices_mutex); brd = brd_init_one(MINOR(dev) / max_part, &new); - kobj = brd ? get_disk(brd->brd_disk) : NULL; + kobj = brd ? get_disk_and_module(brd->brd_disk) : NULL; mutex_unlock(&brd_devices_mutex); if (new) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index eae484acfbbc..8ec7235fc93b 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4505,7 +4505,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) if (((*part >> 2) & 0x1f) >= ARRAY_SIZE(floppy_type)) return NULL; *part = 0; - return get_disk(disks[drive]); + return get_disk_and_module(disks[drive]); } static int __init do_floppy_init(void) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index d5fe720cf149..ee62d2d517bf 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -266,7 +266,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len); + iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); @@ -1922,7 +1922,7 @@ static struct kobject *loop_probe(dev_t dev, int *part, void *data) if (err < 0) kobj = NULL; else - kobj = get_disk(lo->lo_disk); + kobj = get_disk_and_module(lo->lo_disk); mutex_unlock(&loop_index_mutex); *part = 0; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5f2a4240a204..86258b00a1d4 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1591,7 +1591,7 @@ again: if (new_index < 0) { mutex_unlock(&nbd_index_mutex); printk(KERN_ERR "nbd: failed to add new device\n"); - return ret; + return new_index; } nbd = idr_find(&nbd_index_idr, new_index); } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 531a0915066b..c61d20c9f3f8 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1122,7 +1122,7 @@ static int pkt_start_recovery(struct packet_data *pkt) pkt->sector = new_sector; bio_reset(pkt->bio); - bio_set_set(pkt->bio, pd->bdev); + bio_set_dev(pkt->bio, pd->bdev); bio_set_op_attrs(pkt->bio, REQ_OP_WRITE, 0); pkt->bio->bi_iter.bi_sector = new_sector; pkt->bio->bi_iter.bi_size = pkt->frames * CD_FRAMESIZE; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 84434d3ea19b..64e066eba72e 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -799,7 +799,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) return NULL; *part = 0; - return get_disk(swd->unit[drive].disk); + return get_disk_and_module(swd->unit[drive].disk); } static int swim_add_floppy(struct swim_priv *swd, enum drive_location location) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index e126e4cac2ca..92ec1bbece51 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -262,6 +262,7 @@ static DEFINE_SPINLOCK(minor_lock); static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo); static void blkfront_gather_backend_features(struct blkfront_info *info); +static int negotiate_mq(struct blkfront_info *info); static int get_id_from_freelist(struct blkfront_ring_info *rinfo) { @@ -1774,11 +1775,18 @@ static int talk_to_blkback(struct xenbus_device *dev, unsigned int i, max_page_order; unsigned int ring_page_order; + if (!info) + return -ENODEV; + max_page_order = xenbus_read_unsigned(info->xbdev->otherend, "max-ring-page-order", 0); ring_page_order = min(xen_blkif_max_ring_order, max_page_order); info->nr_ring_pages = 1 << ring_page_order; + err = negotiate_mq(info); + if (err) + goto destroy_blkring; + for (i = 0; i < info->nr_rings; i++) { struct blkfront_ring_info *rinfo = &info->rinfo[i]; @@ -1978,11 +1986,6 @@ static int blkfront_probe(struct xenbus_device *dev, } info->xbdev = dev; - err = negotiate_mq(info); - if (err) { - kfree(info); - return err; - } mutex_init(&info->mutex); info->vdevice = vdevice; @@ -2099,10 +2102,6 @@ static int blkfront_resume(struct xenbus_device *dev) blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); - err = negotiate_mq(info); - if (err) - return err; - err = talk_to_blkback(dev, info); if (!err) blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings); diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 41c95c9b2ab4..8f9130ab5887 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -332,7 +332,7 @@ static const struct block_device_operations z2_fops = static struct kobject *z2_find(dev_t dev, int *part, void *data) { *part = 0; - return get_disk(z2ram_gendisk); + return get_disk_and_module(z2ram_gendisk); } static struct request_queue *z2_queue; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 2a55380ad730..366a49c7c08f 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -21,6 +21,7 @@ * */ +#include <linux/dmi.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/quirks.h> @@ -230,7 +231,6 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 }, - { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 }, @@ -263,6 +263,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 }, /* QCA ROME chipset */ + { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME }, @@ -379,6 +380,21 @@ static const struct usb_device_id blacklist_table[] = { { } /* Terminating entry */ }; +/* The Bluetooth USB module build into some devices needs to be reset on resume, + * this is a problem with the platform (likely shutting off all power) not with + * the module itself. So we use a DMI list to match known broken platforms. + */ +static const struct dmi_system_id btusb_needs_reset_resume_table[] = { + { + /* Dell OptiPlex 3060 (QCA ROME device 0cf3:e007) */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 3060"), + }, + }, + {} +}; + #define BTUSB_MAX_ISOC_FRAMES 10 #define BTUSB_INTR_RUNNING 0 @@ -2945,6 +2961,9 @@ static int btusb_probe(struct usb_interface *intf, hdev->send = btusb_send_frame; hdev->notify = btusb_notify; + if (dmi_check_system(btusb_needs_reset_resume_table)) + interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; + #ifdef CONFIG_PM err = btusb_config_oob_wake(hdev); if (err) @@ -3031,12 +3050,6 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_QCA_ROME) { data->setup_on_usb = btusb_setup_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; - - /* QCA Rome devices lose their updated firmware over suspend, - * but the USB hub doesn't notice any status change. - * explicitly request a device reset on resume. - */ - interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; } #ifdef CONFIG_BT_HCIBTUSB_RTL diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 0438a64b8185..40b9fb247010 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -244,7 +244,9 @@ static irqreturn_t bcm_host_wake(int irq, void *data) bt_dev_dbg(bdev, "Host wake IRQ"); - pm_request_resume(bdev->dev); + pm_runtime_get(bdev->dev); + pm_runtime_mark_last_busy(bdev->dev); + pm_runtime_put_autosuspend(bdev->dev); return IRQ_HANDLED; } @@ -301,7 +303,7 @@ static const struct bcm_set_sleep_mode default_sleep_params = { .usb_auto_sleep = 0, .usb_resume_timeout = 0, .break_to_host = 0, - .pulsed_host_wake = 0, + .pulsed_host_wake = 1, }; static int bcm_setup_sleep(struct hci_uart *hu) @@ -586,8 +588,11 @@ static int bcm_recv(struct hci_uart *hu, const void *data, int count) } else if (!bcm->rx_skb) { /* Delay auto-suspend when receiving completed packet */ mutex_lock(&bcm_device_lock); - if (bcm->dev && bcm_device_exists(bcm->dev)) - pm_request_resume(bcm->dev->dev); + if (bcm->dev && bcm_device_exists(bcm->dev)) { + pm_runtime_get(bcm->dev->dev); + pm_runtime_mark_last_busy(bcm->dev->dev); + pm_runtime_put_autosuspend(bcm->dev->dev); + } mutex_unlock(&bcm_device_lock); } @@ -922,12 +927,13 @@ static int bcm_get_resources(struct bcm_device *dev) dev->clk = devm_clk_get(dev->dev, NULL); - dev->device_wakeup = devm_gpiod_get(dev->dev, "device-wakeup", - GPIOD_OUT_LOW); + dev->device_wakeup = devm_gpiod_get_optional(dev->dev, "device-wakeup", + GPIOD_OUT_LOW); if (IS_ERR(dev->device_wakeup)) return PTR_ERR(dev->device_wakeup); - dev->shutdown = devm_gpiod_get(dev->dev, "shutdown", GPIOD_OUT_LOW); + dev->shutdown = devm_gpiod_get_optional(dev->dev, "shutdown", + GPIOD_OUT_LOW); if (IS_ERR(dev->shutdown)) return PTR_ERR(dev->shutdown); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 4d46003c46cf..cdaeeea7999c 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -630,7 +630,7 @@ static int sysc_init_dts_quirks(struct sysc *ddata) for (i = 0; i < ARRAY_SIZE(sysc_dts_quirks); i++) { prop = of_get_property(np, sysc_dts_quirks[i].name, &len); if (!prop) - break; + continue; ddata->cfg.quirks |= sysc_dts_quirks[i].mask; } diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c index 4d1dc8b46877..f95b9c75175b 100644 --- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -457,7 +457,7 @@ static int st33zp24_recv(struct tpm_chip *chip, unsigned char *buf, size_t count) { int size = 0; - int expected; + u32 expected; if (!chip) return -EBUSY; @@ -474,7 +474,7 @@ static int st33zp24_recv(struct tpm_chip *chip, unsigned char *buf, } expected = be32_to_cpu(*(__be32 *)(buf + 2)); - if (expected > count) { + if (expected > count || expected < TPM_HEADER_SIZE) { size = -EIO; goto out; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 76df4fbcf089..9e80a953d693 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -1190,6 +1190,10 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) break; recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len); + if (recd > num_bytes) { + total = -EFAULT; + break; + } rlength = be32_to_cpu(tpm_cmd.header.out.length); if (rlength < offsetof(struct tpm_getrandom_out, rng_data) + diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index c17e75348a99..a700f8f9ead7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -683,6 +683,10 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, if (!rc) { data_len = be16_to_cpup( (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { + rc = -EFAULT; + goto out; + } rlength = be32_to_cpu(((struct tpm2_cmd *)&buf) ->header.out.length); diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c index c1dd39eaaeeb..6116cd05e228 100644 --- a/drivers/char/tpm/tpm_i2c_infineon.c +++ b/drivers/char/tpm/tpm_i2c_infineon.c @@ -473,7 +473,8 @@ static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count) static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) { int size = 0; - int expected, status; + int status; + u32 expected; if (count < TPM_HEADER_SIZE) { size = -EIO; @@ -488,7 +489,7 @@ static int tpm_tis_i2c_recv(struct tpm_chip *chip, u8 *buf, size_t count) } expected = be32_to_cpu(*(__be32 *)(buf + 2)); - if ((size_t) expected > count) { + if (((size_t) expected > count) || (expected < TPM_HEADER_SIZE)) { size = -EIO; goto out; } diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index c6428771841f..caa86b19c76d 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -281,7 +281,11 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) struct device *dev = chip->dev.parent; struct i2c_client *client = to_i2c_client(dev); s32 rc; - int expected, status, burst_count, retries, size = 0; + int status; + int burst_count; + int retries; + int size = 0; + u32 expected; if (count < TPM_HEADER_SIZE) { i2c_nuvoton_ready(chip); /* return to idle */ @@ -323,7 +327,7 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count) * to machine native */ expected = be32_to_cpu(*(__be32 *) (buf + 2)); - if (expected > count) { + if (expected > count || expected < size) { dev_err(dev, "%s() expected > count\n", __func__); size = -EIO; continue; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 183a5f54d875..da074e3db19b 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -270,7 +270,8 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); int size = 0; - int expected, status; + int status; + u32 expected; if (count < TPM_HEADER_SIZE) { size = -EIO; @@ -285,7 +286,7 @@ static int tpm_tis_recv(struct tpm_chip *chip, u8 *buf, size_t count) } expected = be32_to_cpu(*(__be32 *) (buf + 2)); - if (expected > count) { + if (expected > count || expected < TPM_HEADER_SIZE) { size = -EIO; goto out; } diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 44301a3d9963..a07f6451694a 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -449,17 +449,17 @@ struct bcm2835_pll_ana_bits { static const struct bcm2835_pll_ana_bits bcm2835_ana_default = { .mask0 = 0, .set0 = 0, - .mask1 = (u32)~(A2W_PLL_KI_MASK | A2W_PLL_KP_MASK), + .mask1 = A2W_PLL_KI_MASK | A2W_PLL_KP_MASK, .set1 = (2 << A2W_PLL_KI_SHIFT) | (8 << A2W_PLL_KP_SHIFT), - .mask3 = (u32)~A2W_PLL_KA_MASK, + .mask3 = A2W_PLL_KA_MASK, .set3 = (2 << A2W_PLL_KA_SHIFT), .fb_prediv_mask = BIT(14), }; static const struct bcm2835_pll_ana_bits bcm2835_ana_pllh = { - .mask0 = (u32)~(A2W_PLLH_KA_MASK | A2W_PLLH_KI_LOW_MASK), + .mask0 = A2W_PLLH_KA_MASK | A2W_PLLH_KI_LOW_MASK, .set0 = (2 << A2W_PLLH_KA_SHIFT) | (2 << A2W_PLLH_KI_LOW_SHIFT), - .mask1 = (u32)~(A2W_PLLH_KI_HIGH_MASK | A2W_PLLH_KP_MASK), + .mask1 = A2W_PLLH_KI_HIGH_MASK | A2W_PLLH_KP_MASK, .set1 = (6 << A2W_PLLH_KP_SHIFT), .mask3 = 0, .set3 = 0, @@ -623,8 +623,10 @@ static int bcm2835_pll_on(struct clk_hw *hw) ~A2W_PLL_CTRL_PWRDN); /* Take the PLL out of reset. */ + spin_lock(&cprman->regs_lock); cprman_write(cprman, data->cm_ctrl_reg, cprman_read(cprman, data->cm_ctrl_reg) & ~CM_PLL_ANARST); + spin_unlock(&cprman->regs_lock); /* Wait for the PLL to lock. */ timeout = ktime_add_ns(ktime_get(), LOCK_TIMEOUT_NS); @@ -701,9 +703,11 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw, } /* Unmask the reference clock from the oscillator. */ + spin_lock(&cprman->regs_lock); cprman_write(cprman, A2W_XOSC_CTRL, cprman_read(cprman, A2W_XOSC_CTRL) | data->reference_enable_mask); + spin_unlock(&cprman->regs_lock); if (do_ana_setup_first) bcm2835_pll_write_ana(cprman, data->ana_reg_base, ana); diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c index 9f7f931d6b2f..5eb50c31e455 100644 --- a/drivers/clk/clk-aspeed.c +++ b/drivers/clk/clk-aspeed.c @@ -205,6 +205,18 @@ static const struct aspeed_clk_soc_data ast2400_data = { .calc_pll = aspeed_ast2400_calc_pll, }; +static int aspeed_clk_is_enabled(struct clk_hw *hw) +{ + struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); + u32 clk = BIT(gate->clock_idx); + u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk; + u32 reg; + + regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®); + + return ((reg & clk) == enval) ? 1 : 0; +} + static int aspeed_clk_enable(struct clk_hw *hw) { struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); @@ -215,6 +227,11 @@ static int aspeed_clk_enable(struct clk_hw *hw) spin_lock_irqsave(gate->lock, flags); + if (aspeed_clk_is_enabled(hw)) { + spin_unlock_irqrestore(gate->lock, flags); + return 0; + } + if (gate->reset_idx >= 0) { /* Put IP in reset */ regmap_update_bits(gate->map, ASPEED_RESET_CTRL, rst, rst); @@ -255,17 +272,6 @@ static void aspeed_clk_disable(struct clk_hw *hw) spin_unlock_irqrestore(gate->lock, flags); } -static int aspeed_clk_is_enabled(struct clk_hw *hw) -{ - struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); - u32 clk = BIT(gate->clock_idx); - u32 reg; - - regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®); - - return (reg & clk) ? 0 : 1; -} - static const struct clk_ops aspeed_clk_gate_ops = { .enable = aspeed_clk_enable, .disable = aspeed_clk_disable, diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 0f686a9dac3e..076d4244d672 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1125,8 +1125,10 @@ static int clk_core_round_rate_nolock(struct clk_core *core, { lockdep_assert_held(&prepare_lock); - if (!core) + if (!core) { + req->rate = 0; return 0; + } clk_core_init_rate_req(core, req); @@ -2309,8 +2311,11 @@ static int clk_core_set_phase_nolock(struct clk_core *core, int degrees) trace_clk_set_phase(core, degrees); - if (core->ops->set_phase) + if (core->ops->set_phase) { ret = core->ops->set_phase(core->hw, degrees); + if (!ret) + core->phase = degrees; + } trace_clk_set_phase_complete(core, degrees); @@ -2968,22 +2973,37 @@ static int __clk_core_init(struct clk_core *core) core->rate = core->req_rate = rate; /* + * Enable CLK_IS_CRITICAL clocks so newly added critical clocks + * don't get accidentally disabled when walking the orphan tree and + * reparenting clocks + */ + if (core->flags & CLK_IS_CRITICAL) { + unsigned long flags; + + clk_core_prepare(core); + + flags = clk_enable_lock(); + clk_core_enable(core); + clk_enable_unlock(flags); + } + + /* * walk the list of orphan clocks and reparent any that newly finds a * parent. */ hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) { struct clk_core *parent = __clk_init_parent(orphan); - unsigned long flags; /* - * we could call __clk_set_parent, but that would result in a - * redundant call to the .set_rate op, if it exists + * We need to use __clk_set_parent_before() and _after() to + * to properly migrate any prepare/enable count of the orphan + * clock. This is important for CLK_IS_CRITICAL clocks, which + * are enabled during init but might not have a parent yet. */ if (parent) { /* update the clk tree topology */ - flags = clk_enable_lock(); - clk_reparent(orphan, parent); - clk_enable_unlock(flags); + __clk_set_parent_before(orphan, parent); + __clk_set_parent_after(orphan, parent, NULL); __clk_recalc_accuracies(orphan); __clk_recalc_rates(orphan, 0); } @@ -3000,16 +3020,6 @@ static int __clk_core_init(struct clk_core *core) if (core->ops->init) core->ops->init(core->hw); - if (core->flags & CLK_IS_CRITICAL) { - unsigned long flags; - - clk_core_prepare(core); - - flags = clk_enable_lock(); - clk_core_enable(core); - clk_enable_unlock(flags); - } - kref_init(&core->ref); out: clk_pm_runtime_put(core); diff --git a/drivers/clk/hisilicon/clk-hi3660-stub.c b/drivers/clk/hisilicon/clk-hi3660-stub.c index 9b6c72bbddf9..e8b2c43b1bb8 100644 --- a/drivers/clk/hisilicon/clk-hi3660-stub.c +++ b/drivers/clk/hisilicon/clk-hi3660-stub.c @@ -149,6 +149,8 @@ static int hi3660_stub_clk_probe(struct platform_device *pdev) return PTR_ERR(stub_clk_chan.mbox); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -EINVAL; freq_reg = devm_ioremap(dev, res->start, resource_size(res)); if (!freq_reg) return -ENOMEM; diff --git a/drivers/clk/imx/clk-imx51-imx53.c b/drivers/clk/imx/clk-imx51-imx53.c index c864992e6983..caa8bd40692c 100644 --- a/drivers/clk/imx/clk-imx51-imx53.c +++ b/drivers/clk/imx/clk-imx51-imx53.c @@ -131,7 +131,17 @@ static const char *ieee1588_sels[] = { "pll3_sw", "pll4_sw", "dummy" /* usbphy2_ static struct clk *clk[IMX5_CLK_END]; static struct clk_onecell_data clk_data; -static struct clk ** const uart_clks[] __initconst = { +static struct clk ** const uart_clks_mx51[] __initconst = { + &clk[IMX5_CLK_UART1_IPG_GATE], + &clk[IMX5_CLK_UART1_PER_GATE], + &clk[IMX5_CLK_UART2_IPG_GATE], + &clk[IMX5_CLK_UART2_PER_GATE], + &clk[IMX5_CLK_UART3_IPG_GATE], + &clk[IMX5_CLK_UART3_PER_GATE], + NULL +}; + +static struct clk ** const uart_clks_mx50_mx53[] __initconst = { &clk[IMX5_CLK_UART1_IPG_GATE], &clk[IMX5_CLK_UART1_PER_GATE], &clk[IMX5_CLK_UART2_IPG_GATE], @@ -321,8 +331,6 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base) clk_prepare_enable(clk[IMX5_CLK_TMAX1]); clk_prepare_enable(clk[IMX5_CLK_TMAX2]); /* esdhc2, fec */ clk_prepare_enable(clk[IMX5_CLK_TMAX3]); /* esdhc1, esdhc4 */ - - imx_register_uart_clocks(uart_clks); } static void __init mx50_clocks_init(struct device_node *np) @@ -388,6 +396,8 @@ static void __init mx50_clocks_init(struct device_node *np) r = clk_round_rate(clk[IMX5_CLK_USBOH3_PER_GATE], 54000000); clk_set_rate(clk[IMX5_CLK_USBOH3_PER_GATE], r); + + imx_register_uart_clocks(uart_clks_mx50_mx53); } CLK_OF_DECLARE(imx50_ccm, "fsl,imx50-ccm", mx50_clocks_init); @@ -477,6 +487,8 @@ static void __init mx51_clocks_init(struct device_node *np) val = readl(MXC_CCM_CLPCR); val |= 1 << 23; writel(val, MXC_CCM_CLPCR); + + imx_register_uart_clocks(uart_clks_mx51); } CLK_OF_DECLARE(imx51_ccm, "fsl,imx51-ccm", mx51_clocks_init); @@ -606,5 +618,7 @@ static void __init mx53_clocks_init(struct device_node *np) r = clk_round_rate(clk[IMX5_CLK_USBOH3_PER_GATE], 54000000); clk_set_rate(clk[IMX5_CLK_USBOH3_PER_GATE], r); + + imx_register_uart_clocks(uart_clks_mx50_mx53); } CLK_OF_DECLARE(imx53_ccm, "fsl,imx53-ccm", mx53_clocks_init); diff --git a/drivers/clk/qcom/apcs-msm8916.c b/drivers/clk/qcom/apcs-msm8916.c index 246957f1a413..b1cc8dbcd327 100644 --- a/drivers/clk/qcom/apcs-msm8916.c +++ b/drivers/clk/qcom/apcs-msm8916.c @@ -49,11 +49,10 @@ static int qcom_apcs_msm8916_clk_probe(struct platform_device *pdev) struct clk_regmap_mux_div *a53cc; struct regmap *regmap; struct clk_init_data init = { }; - int ret; + int ret = -ENODEV; regmap = dev_get_regmap(parent, NULL); - if (IS_ERR(regmap)) { - ret = PTR_ERR(regmap); + if (!regmap) { dev_err(dev, "failed to get regmap: %d\n", ret); return ret; } diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c index 72b16ed1012b..3b97f60540ad 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c @@ -762,7 +762,7 @@ static struct ccu_mp out_a_clk = { .features = CCU_FEATURE_FIXED_PREDIV, .hw.init = CLK_HW_INIT_PARENTS("out-a", clk_out_parents, - &ccu_div_ops, + &ccu_mp_ops, 0), }, }; @@ -783,7 +783,7 @@ static struct ccu_mp out_b_clk = { .features = CCU_FEATURE_FIXED_PREDIV, .hw.init = CLK_HW_INIT_PARENTS("out-b", clk_out_parents, - &ccu_div_ops, + &ccu_mp_ops, 0), }, }; @@ -804,7 +804,7 @@ static struct ccu_mp out_c_clk = { .features = CCU_FEATURE_FIXED_PREDIV, .hw.init = CLK_HW_INIT_PARENTS("out-c", clk_out_parents, - &ccu_div_ops, + &ccu_mp_ops, 0), }, }; diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c index 612491a26070..12e0a2d19911 100644 --- a/drivers/clk/ti/clk-33xx.c +++ b/drivers/clk/ti/clk-33xx.c @@ -45,7 +45,7 @@ static const struct omap_clkctrl_bit_data am3_gpio4_bit_data[] __initconst = { static const struct omap_clkctrl_reg_data am3_l4_per_clkctrl_regs[] __initconst = { { AM3_CPGMAC0_CLKCTRL, NULL, CLKF_SW_SUP, "cpsw_125mhz_gclk", "cpsw_125mhz_clkdm" }, - { AM3_LCDC_CLKCTRL, NULL, CLKF_SW_SUP, "lcd_gclk", "lcdc_clkdm" }, + { AM3_LCDC_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_SET_RATE_PARENT, "lcd_gclk", "lcdc_clkdm" }, { AM3_USB_OTG_HS_CLKCTRL, NULL, CLKF_SW_SUP, "usbotg_fck", "l3s_clkdm" }, { AM3_TPTC0_CLKCTRL, NULL, CLKF_SW_SUP, "l3_gclk", "l3_clkdm" }, { AM3_EMIF_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_ddr_m2_div2_ck", "l3_clkdm" }, diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c index 2b7c2e017665..63c5ddb50187 100644 --- a/drivers/clk/ti/clk-43xx.c +++ b/drivers/clk/ti/clk-43xx.c @@ -187,7 +187,7 @@ static const struct omap_clkctrl_reg_data am4_l4_per_clkctrl_regs[] __initconst { AM4_OCP2SCP0_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" }, { AM4_OCP2SCP1_CLKCTRL, NULL, CLKF_SW_SUP, "l4ls_gclk" }, { AM4_EMIF_CLKCTRL, NULL, CLKF_SW_SUP, "dpll_ddr_m2_ck", "emif_clkdm" }, - { AM4_DSS_CORE_CLKCTRL, NULL, CLKF_SW_SUP, "disp_clk", "dss_clkdm" }, + { AM4_DSS_CORE_CLKCTRL, NULL, CLKF_SW_SUP | CLKF_SET_RATE_PARENT, "disp_clk", "dss_clkdm" }, { AM4_CPGMAC0_CLKCTRL, NULL, CLKF_SW_SUP, "cpsw_125mhz_gclk", "cpsw_125mhz_clkdm" }, { 0 }, }; diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index afa0d6bfc5c1..421b05392220 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -537,6 +537,8 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) init.parent_names = ®_data->parent; init.num_parents = 1; init.flags = 0; + if (reg_data->flags & CLKF_SET_RATE_PARENT) + init.flags |= CLK_SET_RATE_PARENT; init.name = kasprintf(GFP_KERNEL, "%s:%s:%04x:%d", node->parent->name, node->name, reg_data->offset, 0); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index b3b4ed9b6874..d2e5382821a4 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -386,6 +386,7 @@ config ATMEL_PIT config ATMEL_ST bool "Atmel ST timer support" if COMPILE_TEST + depends on HAS_IOMEM select TIMER_OF select MFD_SYSCON help diff --git a/drivers/clocksource/arc_timer.c b/drivers/clocksource/arc_timer.c index 4927355f9cbe..471b428d8034 100644 --- a/drivers/clocksource/arc_timer.c +++ b/drivers/clocksource/arc_timer.c @@ -251,9 +251,14 @@ static irqreturn_t timer_irq_handler(int irq, void *dev_id) int irq_reenable = clockevent_state_periodic(evt); /* - * Any write to CTRL reg ACks the interrupt, we rewrite the - * Count when [N]ot [H]alted bit. - * And re-arm it if perioid by [I]nterrupt [E]nable bit + * 1. ACK the interrupt + * - For ARC700, any write to CTRL reg ACKs it, so just rewrite + * Count when [N]ot [H]alted bit. + * - For HS3x, it is a bit subtle. On taken count-down interrupt, + * IP bit [3] is set, which needs to be cleared for ACK'ing. + * The write below can only update the other two bits, hence + * explicitly clears IP bit + * 2. Re-arm interrupt if periodic by writing to IE bit [0] */ write_aux_reg(ARC_REG_TIMER0_CTRL, irq_reenable | TIMER_CTRL_NH); diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c index 3ee7e6fea621..846d18daf893 100644 --- a/drivers/clocksource/fsl_ftm_timer.c +++ b/drivers/clocksource/fsl_ftm_timer.c @@ -281,7 +281,7 @@ static int __init __ftm_clk_init(struct device_node *np, char *cnt_name, static unsigned long __init ftm_clk_init(struct device_node *np) { - unsigned long freq; + long freq; freq = __ftm_clk_init(np, "ftm-evt-counter-en", "ftm-evt"); if (freq <= 0) diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index 65e18c86d9b9..986b6796b631 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -166,7 +166,7 @@ static int __init __gic_clocksource_init(void) /* Set clocksource mask. */ count_width = read_gic_config() & GIC_CONFIG_COUNTBITS; - count_width >>= __fls(GIC_CONFIG_COUNTBITS); + count_width >>= __ffs(GIC_CONFIG_COUNTBITS); count_width *= 4; count_width += 32; gic_clocksource.mask = CLOCKSOURCE_MASK(count_width); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 3a88e33b0cfe..fb586e09682d 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -44,10 +44,10 @@ config ARM_DT_BL_CPUFREQ config ARM_SCPI_CPUFREQ tristate "SCPI based CPUfreq driver" - depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI + depends on ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI help - This adds the CPUfreq driver support for ARM big.LITTLE platforms - using SCPI protocol for CPU power management. + This adds the CPUfreq driver support for ARM platforms using SCPI + protocol for CPU power management. This driver uses SCPI Message Protocol driver to interact with the firmware providing the CPU DVFS functionality. diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c index 7b596fa38ad2..6bebc1f9f55a 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq.c +++ b/drivers/cpufreq/s3c24xx-cpufreq.c @@ -351,7 +351,13 @@ struct clk *s3c_cpufreq_clk_get(struct device *dev, const char *name) static int s3c_cpufreq_init(struct cpufreq_policy *policy) { policy->clk = clk_arm; - return cpufreq_generic_init(policy, ftab, cpu_cur.info->latency); + + policy->cpuinfo.transition_latency = cpu_cur.info->latency; + + if (ftab) + return cpufreq_table_validate_and_show(policy, ftab); + + return 0; } static int __init s3c_cpufreq_initclks(void) diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index c32a833e1b00..d300a163945f 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -51,15 +51,23 @@ static unsigned int scpi_cpufreq_get_rate(unsigned int cpu) static int scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index) { + unsigned long freq = policy->freq_table[index].frequency; struct scpi_data *priv = policy->driver_data; - u64 rate = policy->freq_table[index].frequency * 1000; + u64 rate = freq * 1000; int ret; ret = clk_set_rate(priv->clk, rate); - if (!ret && (clk_get_rate(priv->clk) != rate)) - ret = -EIO; - return ret; + if (ret) + return ret; + + if (clk_get_rate(priv->clk) != rate) + return -EIO; + + arch_set_freq_scale(policy->related_cpus, freq, + policy->cpuinfo.max_freq); + + return 0; } static int diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index fcfa5b1eae61..b3afb6cc9d72 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -211,7 +211,7 @@ static int __sev_platform_shutdown_locked(int *error) { int ret; - ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, 0, error); + ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); if (ret) return ret; @@ -271,7 +271,7 @@ static int sev_ioctl_do_reset(struct sev_issue_cmd *argp) return rc; } - return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, 0, &argp->error); + return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, NULL, &argp->error); } static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) @@ -299,7 +299,7 @@ static int sev_ioctl_do_pek_pdh_gen(int cmd, struct sev_issue_cmd *argp) return rc; } - return __sev_do_cmd_locked(cmd, 0, &argp->error); + return __sev_do_cmd_locked(cmd, NULL, &argp->error); } static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp) @@ -624,7 +624,7 @@ EXPORT_SYMBOL_GPL(sev_guest_decommission); int sev_guest_df_flush(int *error) { - return sev_do_cmd(SEV_CMD_DF_FLUSH, 0, error); + return sev_do_cmd(SEV_CMD_DF_FLUSH, NULL, error); } EXPORT_SYMBOL_GPL(sev_guest_df_flush); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 473af694ad1c..ecdc292aa4e4 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -246,12 +246,6 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, { long avail; - /* - * The device driver is allowed to sleep, in order to make the - * memory directly accessible. - */ - might_sleep(); - if (!dax_dev) return -EOPNOTSUPP; diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index f652a0e0f5a2..3548caa9e933 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -163,6 +163,7 @@ struct mv_xor_v2_device { void __iomem *dma_base; void __iomem *glob_base; struct clk *clk; + struct clk *reg_clk; struct tasklet_struct irq_tasklet; struct list_head free_sw_desc; struct dma_device dmadev; @@ -749,13 +750,26 @@ static int mv_xor_v2_probe(struct platform_device *pdev) if (ret) return ret; + xor_dev->reg_clk = devm_clk_get(&pdev->dev, "reg"); + if (PTR_ERR(xor_dev->reg_clk) != -ENOENT) { + if (!IS_ERR(xor_dev->reg_clk)) { + ret = clk_prepare_enable(xor_dev->reg_clk); + if (ret) + return ret; + } else { + return PTR_ERR(xor_dev->reg_clk); + } + } + xor_dev->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { + ret = EPROBE_DEFER; + goto disable_reg_clk; + } if (!IS_ERR(xor_dev->clk)) { ret = clk_prepare_enable(xor_dev->clk); if (ret) - return ret; + goto disable_reg_clk; } ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1, @@ -866,8 +880,9 @@ free_hw_desq: free_msi_irqs: platform_msi_domain_free_irqs(&pdev->dev); disable_clk: - if (!IS_ERR(xor_dev->clk)) - clk_disable_unprepare(xor_dev->clk); + clk_disable_unprepare(xor_dev->clk); +disable_reg_clk: + clk_disable_unprepare(xor_dev->reg_clk); return ret; } diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index e3ff162c03fc..d0cacdb0713e 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -917,7 +917,7 @@ rcar_dmac_chan_prep_sg(struct rcar_dmac_chan *chan, struct scatterlist *sgl, rcar_dmac_chan_configure_desc(chan, desc); - max_chunk_size = (RCAR_DMATCR_MASK + 1) << desc->xfer_shift; + max_chunk_size = RCAR_DMATCR_MASK << desc->xfer_shift; /* * Allocate and fill the transfer chunk descriptors. We own the only diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c index 4dbb30cf94ac..b922db90939a 100644 --- a/drivers/dma/stm32-dmamux.c +++ b/drivers/dma/stm32-dmamux.c @@ -118,14 +118,15 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, spin_lock_irqsave(&dmamux->lock, flags); mux->chan_id = find_first_zero_bit(dmamux->dma_inuse, dmamux->dma_requests); - set_bit(mux->chan_id, dmamux->dma_inuse); - spin_unlock_irqrestore(&dmamux->lock, flags); if (mux->chan_id == dmamux->dma_requests) { + spin_unlock_irqrestore(&dmamux->lock, flags); dev_err(&pdev->dev, "Run out of free DMA requests\n"); ret = -ENOMEM; - goto error; + goto error_chan_id; } + set_bit(mux->chan_id, dmamux->dma_inuse); + spin_unlock_irqrestore(&dmamux->lock, flags); /* Look for DMA Master */ for (i = 1, min = 0, max = dmamux->dma_reqs[i]; @@ -173,6 +174,8 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec, error: clear_bit(mux->chan_id, dmamux->dma_inuse); + +error_chan_id: kfree(mux); return ERR_PTR(ret); } diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index f34430f99fd8..872100215ca0 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -279,7 +279,7 @@ static const u32 correrrthrsld[] = { * sbridge structs */ -#define NUM_CHANNELS 4 /* Max channels per MC */ +#define NUM_CHANNELS 6 /* Max channels per MC */ #define MAX_DIMMS 3 /* Max DIMMS per channel */ #define KNL_MAX_CHAS 38 /* KNL max num. of Cache Home Agents */ #define KNL_MAX_CHANNELS 6 /* KNL max num. of PCI channels */ diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c index c16600f30611..0bdea60c65dd 100644 --- a/drivers/firmware/dcdbas.c +++ b/drivers/firmware/dcdbas.c @@ -639,7 +639,7 @@ static void __exit dcdbas_exit(void) platform_driver_unregister(&dcdbas_driver); } -module_init(dcdbas_init); +subsys_initcall_sync(dcdbas_init); module_exit(dcdbas_exit); MODULE_DESCRIPTION(DRIVER_DESCRIPTION " (version " DRIVER_VERSION ")"); diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index da661bf8cb96..13c1edd37e96 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -68,11 +68,11 @@ void efi_retrieve_tpm2_eventlog_1_2(efi_system_table_t *sys_table_arg) efi_guid_t linux_eventlog_guid = LINUX_EFI_TPM_EVENT_LOG_GUID; efi_status_t status; efi_physical_addr_t log_location, log_last_entry; - struct linux_efi_tpm_eventlog *log_tbl; + struct linux_efi_tpm_eventlog *log_tbl = NULL; unsigned long first_entry_addr, last_entry_addr; size_t log_size, last_entry_size; efi_bool_t truncated; - void *tcg2_protocol; + void *tcg2_protocol = NULL; status = efi_call_early(locate_protocol, &tcg2_guid, NULL, &tcg2_protocol); diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index e76de57dd617..ebaea8b1594b 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -14,7 +14,6 @@ * GNU General Public License for more details. */ -#include <linux/clk.h> #include <linux/err.h> #include <linux/gpio.h> #include <linux/init.h> @@ -37,10 +36,9 @@ struct gpio_rcar_priv { struct platform_device *pdev; struct gpio_chip gpio_chip; struct irq_chip irq_chip; - struct clk *clk; unsigned int irq_parent; + atomic_t wakeup_path; bool has_both_edge_trigger; - bool needs_clk; }; #define IOINTSEL 0x00 /* General IO/Interrupt Switching Register */ @@ -186,13 +184,10 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) } } - if (!p->clk) - return 0; - if (on) - clk_enable(p->clk); + atomic_inc(&p->wakeup_path); else - clk_disable(p->clk); + atomic_dec(&p->wakeup_path); return 0; } @@ -330,17 +325,14 @@ static int gpio_rcar_direction_output(struct gpio_chip *chip, unsigned offset, struct gpio_rcar_info { bool has_both_edge_trigger; - bool needs_clk; }; static const struct gpio_rcar_info gpio_rcar_info_gen1 = { .has_both_edge_trigger = false, - .needs_clk = false, }; static const struct gpio_rcar_info gpio_rcar_info_gen2 = { .has_both_edge_trigger = true, - .needs_clk = true, }; static const struct of_device_id gpio_rcar_of_table[] = { @@ -403,7 +395,6 @@ static int gpio_rcar_parse_dt(struct gpio_rcar_priv *p, unsigned int *npins) ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args); *npins = ret == 0 ? args.args[2] : RCAR_MAX_GPIO_PER_BANK; p->has_both_edge_trigger = info->has_both_edge_trigger; - p->needs_clk = info->needs_clk; if (*npins == 0 || *npins > RCAR_MAX_GPIO_PER_BANK) { dev_warn(&p->pdev->dev, @@ -440,16 +431,6 @@ static int gpio_rcar_probe(struct platform_device *pdev) platform_set_drvdata(pdev, p); - p->clk = devm_clk_get(dev, NULL); - if (IS_ERR(p->clk)) { - if (p->needs_clk) { - dev_err(dev, "unable to get clock\n"); - ret = PTR_ERR(p->clk); - goto err0; - } - p->clk = NULL; - } - pm_runtime_enable(dev); irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); @@ -531,11 +512,24 @@ static int gpio_rcar_remove(struct platform_device *pdev) return 0; } +static int __maybe_unused gpio_rcar_suspend(struct device *dev) +{ + struct gpio_rcar_priv *p = dev_get_drvdata(dev); + + if (atomic_read(&p->wakeup_path)) + device_set_wakeup_path(dev); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(gpio_rcar_pm_ops, gpio_rcar_suspend, NULL); + static struct platform_driver gpio_rcar_device_driver = { .probe = gpio_rcar_probe, .remove = gpio_rcar_remove, .driver = { .name = "gpio_rcar", + .pm = &gpio_rcar_pm_ops, .of_match_table = of_match_ptr(gpio_rcar_of_table), } }; diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 564bb7a31da4..84e5a9df2344 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -241,6 +241,19 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx, &of_flags); + /* + * -EPROBE_DEFER in our case means that we found a + * valid GPIO property, but no controller has been + * registered so far. + * + * This means we don't need to look any further for + * alternate name conventions, and we should really + * preserve the return code for our user to be able to + * retry probing later. + */ + if (IS_ERR(desc) && PTR_ERR(desc) == -EPROBE_DEFER) + return desc; + if (!IS_ERR(desc) || (PTR_ERR(desc) != -ENOENT)) break; } @@ -250,7 +263,7 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id, desc = of_find_spi_gpio(dev, con_id, &of_flags); /* Special handling for regulator GPIOs if used */ - if (IS_ERR(desc)) + if (IS_ERR(desc) && PTR_ERR(desc) != -EPROBE_DEFER) desc = of_find_regulator_gpio(dev, con_id, &of_flags); if (IS_ERR(desc)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d5a2eefd6c3e..74edba18b159 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1156,7 +1156,7 @@ static inline void amdgpu_set_ib_value(struct amdgpu_cs_parser *p, /* * Writeback */ -#define AMDGPU_MAX_WB 512 /* Reserve at most 512 WB slots for amdgpu-owned rings. */ +#define AMDGPU_MAX_WB 128 /* Reserve at most 128 WB slots for amdgpu-owned rings. */ struct amdgpu_wb { struct amdgpu_bo *wb_obj; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 57afad79f55d..8fa850a070e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -540,6 +540,9 @@ int amdgpu_acpi_pcie_performance_request(struct amdgpu_device *adev, size_t size; u32 retry = 3; + if (amdgpu_acpi_pcie_notify_device_ready(adev)) + return -EINVAL; + /* Get the device handle */ handle = ACPI_HANDLE(&adev->pdev->dev); if (!handle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 74d2efaec52f..7a073ac5f9c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -69,25 +69,18 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) /* don't do anything if sink is not display port, i.e., * passive dp->(dvi|hdmi) adaptor */ - if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) { - int saved_dpms = connector->dpms; - /* Only turn off the display if it's physically disconnected */ - if (!amdgpu_display_hpd_sense(adev, amdgpu_connector->hpd.hpd)) { - drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); - } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { - /* Don't try to start link training before we - * have the dpcd */ - if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) - return; - - /* set it to OFF so that drm_helper_connector_dpms() - * won't return immediately since the current state - * is ON at this point. - */ - connector->dpms = DRM_MODE_DPMS_OFF; - drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); - } - connector->dpms = saved_dpms; + if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT && + amdgpu_display_hpd_sense(adev, amdgpu_connector->hpd.hpd) && + amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { + /* Don't start link training before we have the DPCD */ + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + return; + + /* Turn the connector off and back on immediately, which + * will trigger link training + */ + drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); + drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 00a50cc5ec9a..66cb10cdc7c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -492,7 +492,7 @@ static int amdgpu_device_wb_init(struct amdgpu_device *adev) memset(&adev->wb.used, 0, sizeof(adev->wb.used)); /* clear wb memory */ - memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t)); + memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t) * 8); } return 0; @@ -530,8 +530,9 @@ int amdgpu_device_wb_get(struct amdgpu_device *adev, u32 *wb) */ void amdgpu_device_wb_free(struct amdgpu_device *adev, u32 wb) { + wb >>= 3; if (wb < adev->wb.num_wb) - __clear_bit(wb >> 3, adev->wb.used); + __clear_bit(wb, adev->wb.used); } /** @@ -1455,11 +1456,6 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.hw) continue; - if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { - amdgpu_free_static_csa(adev); - amdgpu_device_wb_fini(adev); - amdgpu_device_vram_scratch_fini(adev); - } if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE) { @@ -1486,6 +1482,13 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev) for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.sw) continue; + + if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) { + amdgpu_free_static_csa(adev); + amdgpu_device_wb_fini(adev); + amdgpu_device_vram_scratch_fini(adev); + } + r = adev->ip_blocks[i].version->funcs->sw_fini((void *)adev); /* XXX handle errors */ if (r) { @@ -2060,9 +2063,12 @@ void amdgpu_device_fini(struct amdgpu_device *adev) DRM_INFO("amdgpu: finishing device.\n"); adev->shutdown = true; - if (adev->mode_info.mode_config_initialized) - drm_crtc_force_disable_all(adev->ddev); - + if (adev->mode_info.mode_config_initialized){ + if (!amdgpu_device_has_dc_support(adev)) + drm_crtc_force_disable_all(adev->ddev); + else + drm_atomic_helper_shutdown(adev->ddev); + } amdgpu_ib_pool_fini(adev); amdgpu_fence_driver_fini(adev); amdgpu_fbdev_fini(adev); @@ -2284,14 +2290,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon) drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); } drm_modeset_unlock_all(dev); - } else { - /* - * There is no equivalent atomic helper to turn on - * display, so we defined our own function for this, - * once suspend resume is supported by the atomic - * framework this will be reworked - */ - amdgpu_dm_display_resume(adev); } } @@ -2726,7 +2724,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, if (amdgpu_device_has_dc_support(adev)) { if (drm_atomic_helper_resume(adev->ddev, state)) dev_info(adev->dev, "drm resume failed:%d\n", r); - amdgpu_dm_display_resume(adev); } else { drm_helper_resume_force_mode(adev->ddev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index e48b4ec88c8c..ca6c931dabfa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -36,8 +36,6 @@ void amdgpu_gem_object_free(struct drm_gem_object *gobj) struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj); if (robj) { - if (robj->gem_base.import_attach) - drm_prime_gem_destroy(&robj->gem_base, robj->tbo.sg); amdgpu_mn_unregister(robj); amdgpu_bo_unref(&robj); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index e14ab34d8262..7c2be32c5aea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -75,7 +75,7 @@ static int amdgpu_gtt_mgr_init(struct ttm_mem_type_manager *man, static int amdgpu_gtt_mgr_fini(struct ttm_mem_type_manager *man) { struct amdgpu_gtt_mgr *mgr = man->priv; - + spin_lock(&mgr->lock); drm_mm_takedown(&mgr->mm); spin_unlock(&mgr->lock); kfree(mgr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 56bcd59c3399..36483e0d3c97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -257,7 +257,8 @@ int amdgpu_irq_init(struct amdgpu_device *adev) r = drm_irq_install(adev->ddev, adev->ddev->pdev->irq); if (r) { adev->irq.installed = false; - flush_work(&adev->hotplug_work); + if (!amdgpu_device_has_dc_support(adev)) + flush_work(&adev->hotplug_work); cancel_work_sync(&adev->reset_work); return r; } @@ -282,7 +283,8 @@ void amdgpu_irq_fini(struct amdgpu_device *adev) adev->irq.installed = false; if (adev->irq.msi_enabled) pci_disable_msi(adev->pdev); - flush_work(&adev->hotplug_work); + if (!amdgpu_device_has_dc_support(adev)) + flush_work(&adev->hotplug_work); cancel_work_sync(&adev->reset_work); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 54f06c959340..2264c5c97009 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -352,6 +352,7 @@ struct amdgpu_mode_info { u16 firmware_flags; /* pointer to backlight encoder */ struct amdgpu_encoder *bl_encoder; + u8 bl_level; /* saved backlight level */ struct amdgpu_audio audio; /* audio stuff */ int num_crtc; /* number of crtcs */ int num_hpd; /* number of hpd pins */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 5c4c3e0d527b..1220322c1680 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -56,6 +56,8 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo) amdgpu_bo_kunmap(bo); + if (bo->gem_base.import_attach) + drm_prime_gem_destroy(&bo->gem_base, bo->tbo.sg); drm_gem_object_release(&bo->gem_base); amdgpu_bo_unref(&bo->parent); if (!list_empty(&bo->shadow_list)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 13044e66dcaf..561d3312af32 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -481,7 +481,7 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf, result = 0; if (*pos < 12) { - early[0] = amdgpu_ring_get_rptr(ring); + early[0] = amdgpu_ring_get_rptr(ring) & ring->buf_mask; early[1] = amdgpu_ring_get_wptr(ring) & ring->buf_mask; early[2] = ring->wptr & ring->buf_mask; for (i = *pos / 4; i < 3 && size; i++) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index b2eae86bf906..5c26a8e806b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -299,12 +299,15 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev) cancel_delayed_work_sync(&adev->uvd.idle_work); - for (i = 0; i < adev->uvd.max_handles; ++i) - if (atomic_read(&adev->uvd.handles[i])) - break; + /* only valid for physical mode */ + if (adev->asic_type < CHIP_POLARIS10) { + for (i = 0; i < adev->uvd.max_handles; ++i) + if (atomic_read(&adev->uvd.handles[i])) + break; - if (i == AMDGPU_MAX_UVD_HANDLES) - return 0; + if (i == adev->uvd.max_handles) + return 0; + } size = amdgpu_bo_size(adev->uvd.vcpu_bo); ptr = adev->uvd.cpu_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 2af26d2da127..d702fb8e3427 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -34,7 +34,7 @@ #include <linux/backlight.h> #include "bif/bif_4_1_d.h" -static u8 +u8 amdgpu_atombios_encoder_get_backlight_level_from_reg(struct amdgpu_device *adev) { u8 backlight_level; @@ -48,7 +48,7 @@ amdgpu_atombios_encoder_get_backlight_level_from_reg(struct amdgpu_device *adev) return backlight_level; } -static void +void amdgpu_atombios_encoder_set_backlight_level_to_reg(struct amdgpu_device *adev, u8 backlight_level) { diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h index 2bdec40515ce..f77cbdef679e 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.h @@ -25,6 +25,11 @@ #define __ATOMBIOS_ENCODER_H__ u8 +amdgpu_atombios_encoder_get_backlight_level_from_reg(struct amdgpu_device *adev); +void +amdgpu_atombios_encoder_set_backlight_level_to_reg(struct amdgpu_device *adev, + u8 backlight_level); +u8 amdgpu_atombios_encoder_get_backlight_level(struct amdgpu_encoder *amdgpu_encoder); void amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encoder, diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index f34bc68aadfb..022f303463fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2921,6 +2921,11 @@ static int dce_v10_0_hw_fini(void *handle) static int dce_v10_0_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + adev->mode_info.bl_level = + amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); + return dce_v10_0_hw_fini(handle); } @@ -2929,6 +2934,9 @@ static int dce_v10_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret; + amdgpu_atombios_encoder_set_backlight_level_to_reg(adev, + adev->mode_info.bl_level); + ret = dce_v10_0_hw_init(handle); /* turn on the BL */ diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 26378bd6aba4..800a9f36ab4f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3047,6 +3047,11 @@ static int dce_v11_0_hw_fini(void *handle) static int dce_v11_0_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + adev->mode_info.bl_level = + amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); + return dce_v11_0_hw_fini(handle); } @@ -3055,6 +3060,9 @@ static int dce_v11_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret; + amdgpu_atombios_encoder_set_backlight_level_to_reg(adev, + adev->mode_info.bl_level); + ret = dce_v11_0_hw_init(handle); /* turn on the BL */ diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index bd2c4f727df6..b8368f69ce1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -2787,6 +2787,11 @@ static int dce_v6_0_hw_fini(void *handle) static int dce_v6_0_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + adev->mode_info.bl_level = + amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); + return dce_v6_0_hw_fini(handle); } @@ -2795,6 +2800,9 @@ static int dce_v6_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret; + amdgpu_atombios_encoder_set_backlight_level_to_reg(adev, + adev->mode_info.bl_level); + ret = dce_v6_0_hw_init(handle); /* turn on the BL */ @@ -3093,7 +3101,7 @@ static int dce_v6_0_hpd_irq(struct amdgpu_device *adev, tmp |= DC_HPD1_INT_CONTROL__DC_HPD1_INT_ACK_MASK; WREG32(mmDC_HPD1_INT_CONTROL + hpd_offsets[hpd], tmp); schedule_work(&adev->hotplug_work); - DRM_INFO("IH: HPD%d\n", hpd + 1); + DRM_DEBUG("IH: HPD%d\n", hpd + 1); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index c008dc030687..012e0a9ae0ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2819,6 +2819,11 @@ static int dce_v8_0_hw_fini(void *handle) static int dce_v8_0_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + adev->mode_info.bl_level = + amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); + return dce_v8_0_hw_fini(handle); } @@ -2827,6 +2832,9 @@ static int dce_v8_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret; + amdgpu_atombios_encoder_set_backlight_level_to_reg(adev, + adev->mode_info.bl_level); + ret = dce_v8_0_hw_init(handle); /* turn on the BL */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index a066c5eda135..a4309698e76c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -4384,34 +4384,8 @@ static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev) case CHIP_KAVERI: adev->gfx.config.max_shader_engines = 1; adev->gfx.config.max_tile_pipes = 4; - if ((adev->pdev->device == 0x1304) || - (adev->pdev->device == 0x1305) || - (adev->pdev->device == 0x130C) || - (adev->pdev->device == 0x130F) || - (adev->pdev->device == 0x1310) || - (adev->pdev->device == 0x1311) || - (adev->pdev->device == 0x131C)) { - adev->gfx.config.max_cu_per_sh = 8; - adev->gfx.config.max_backends_per_se = 2; - } else if ((adev->pdev->device == 0x1309) || - (adev->pdev->device == 0x130A) || - (adev->pdev->device == 0x130D) || - (adev->pdev->device == 0x1313) || - (adev->pdev->device == 0x131D)) { - adev->gfx.config.max_cu_per_sh = 6; - adev->gfx.config.max_backends_per_se = 2; - } else if ((adev->pdev->device == 0x1306) || - (adev->pdev->device == 0x1307) || - (adev->pdev->device == 0x130B) || - (adev->pdev->device == 0x130E) || - (adev->pdev->device == 0x1315) || - (adev->pdev->device == 0x131B)) { - adev->gfx.config.max_cu_per_sh = 4; - adev->gfx.config.max_backends_per_se = 1; - } else { - adev->gfx.config.max_cu_per_sh = 3; - adev->gfx.config.max_backends_per_se = 1; - } + adev->gfx.config.max_cu_per_sh = 8; + adev->gfx.config.max_backends_per_se = 2; adev->gfx.config.max_sh_per_se = 1; adev->gfx.config.max_texture_channel_caches = 4; adev->gfx.config.max_gprs = 256; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 2719937e09d6..3b7e7af09ead 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -634,7 +634,7 @@ static int gmc_v9_0_late_init(void *handle) for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i) BUG_ON(vm_inv_eng[i] > 16); - if (adev->asic_type == CHIP_VEGA10) { + if (adev->asic_type == CHIP_VEGA10 && !amdgpu_sriov_vf(adev)) { r = gmc_v9_0_ecc_available(adev); if (r == 1) { DRM_INFO("ECC is active.\n"); @@ -682,7 +682,10 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) adev->mc.vram_width = amdgpu_atomfirmware_get_vram_width(adev); if (!adev->mc.vram_width) { /* hbm memory channel size */ - chansize = 128; + if (adev->flags & AMD_IS_APU) + chansize = 64; + else + chansize = 128; tmp = RREG32_SOC15(DF, 0, mmDF_CS_AON0_DramBaseAddress0); tmp &= DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index e92fb372bc99..91cf95a8c39c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -238,31 +238,27 @@ static uint64_t sdma_v4_0_ring_get_rptr(struct amdgpu_ring *ring) static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; - u64 *wptr = NULL; - uint64_t local_wptr = 0; + u64 wptr; if (ring->use_doorbell) { /* XXX check if swapping is necessary on BE */ - wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]); - DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr); - *wptr = (*wptr) >> 2; - DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr); + wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs])); + DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr); } else { u32 lowbit, highbit; int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1; - wptr = &local_wptr; lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2; highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2; DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n", me, highbit, lowbit); - *wptr = highbit; - *wptr = (*wptr) << 32; - *wptr |= lowbit; + wptr = highbit; + wptr = wptr << 32; + wptr |= lowbit; } - return *wptr; + return wptr >> 2; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index 543101d5a5ed..2095173aaabf 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -31,6 +31,7 @@ #include "amdgpu_uvd.h" #include "amdgpu_vce.h" #include "atom.h" +#include "amd_pcie.h" #include "amdgpu_powerplay.h" #include "sid.h" #include "si_ih.h" @@ -1461,8 +1462,8 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) { struct pci_dev *root = adev->pdev->bus->self; int bridge_pos, gpu_pos; - u32 speed_cntl, mask, current_data_rate; - int ret, i; + u32 speed_cntl, current_data_rate; + int i; u16 tmp16; if (pci_is_root_bus(adev->pdev->bus)) @@ -1474,23 +1475,20 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) if (adev->flags & AMD_IS_APU) return; - ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask); - if (ret != 0) - return; - - if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80))) + if (!(adev->pm.pcie_gen_mask & (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 | + CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3))) return; speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL); current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >> LC_CURRENT_DATA_RATE_SHIFT; - if (mask & DRM_PCIE_SPEED_80) { + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) { if (current_data_rate == 2) { DRM_INFO("PCIE gen 3 link speeds already enabled\n"); return; } DRM_INFO("enabling PCIE gen 3 link speeds, disable with amdgpu.pcie_gen2=0\n"); - } else if (mask & DRM_PCIE_SPEED_50) { + } else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) { if (current_data_rate == 1) { DRM_INFO("PCIE gen 2 link speeds already enabled\n"); return; @@ -1506,7 +1504,7 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) if (!gpu_pos) return; - if (mask & DRM_PCIE_SPEED_80) { + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) { if (current_data_rate != 2) { u16 bridge_cfg, gpu_cfg; u16 bridge_cfg2, gpu_cfg2; @@ -1589,9 +1587,9 @@ static void si_pcie_gen3_enable(struct amdgpu_device *adev) pci_read_config_word(adev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16); tmp16 &= ~0xf; - if (mask & DRM_PCIE_SPEED_80) + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) tmp16 |= 3; - else if (mask & DRM_PCIE_SPEED_50) + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) tmp16 |= 2; else tmp16 |= 1; diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index ce675a7f179a..22f0b7ff3ac9 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -26,6 +26,7 @@ #include "amdgpu_pm.h" #include "amdgpu_dpm.h" #include "amdgpu_atombios.h" +#include "amd_pcie.h" #include "sid.h" #include "r600_dpm.h" #include "si_dpm.h" @@ -3331,29 +3332,6 @@ static void btc_apply_voltage_delta_rules(struct amdgpu_device *adev, } } -static enum amdgpu_pcie_gen r600_get_pcie_gen_support(struct amdgpu_device *adev, - u32 sys_mask, - enum amdgpu_pcie_gen asic_gen, - enum amdgpu_pcie_gen default_gen) -{ - switch (asic_gen) { - case AMDGPU_PCIE_GEN1: - return AMDGPU_PCIE_GEN1; - case AMDGPU_PCIE_GEN2: - return AMDGPU_PCIE_GEN2; - case AMDGPU_PCIE_GEN3: - return AMDGPU_PCIE_GEN3; - default: - if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == AMDGPU_PCIE_GEN3)) - return AMDGPU_PCIE_GEN3; - else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == AMDGPU_PCIE_GEN2)) - return AMDGPU_PCIE_GEN2; - else - return AMDGPU_PCIE_GEN1; - } - return AMDGPU_PCIE_GEN1; -} - static void r600_calculate_u_and_p(u32 i, u32 r_c, u32 p_b, u32 *p, u32 *u) { @@ -5028,10 +5006,11 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, table->ACPIState.levels[0].vddc.index, &table->ACPIState.levels[0].std_vddc); } - table->ACPIState.levels[0].gen2PCIE = (u8)r600_get_pcie_gen_support(adev, - si_pi->sys_pcie_mask, - si_pi->boot_pcie_gen, - AMDGPU_PCIE_GEN1); + table->ACPIState.levels[0].gen2PCIE = + (u8)amdgpu_get_pcie_gen_support(adev, + si_pi->sys_pcie_mask, + si_pi->boot_pcie_gen, + AMDGPU_PCIE_GEN1); if (si_pi->vddc_phase_shed_control) si_populate_phase_shedding_value(adev, @@ -7168,10 +7147,10 @@ static void si_parse_pplib_clock_info(struct amdgpu_device *adev, pl->vddc = le16_to_cpu(clock_info->si.usVDDC); pl->vddci = le16_to_cpu(clock_info->si.usVDDCI); pl->flags = le32_to_cpu(clock_info->si.ulFlags); - pl->pcie_gen = r600_get_pcie_gen_support(adev, - si_pi->sys_pcie_mask, - si_pi->boot_pcie_gen, - clock_info->si.ucPCIEGen); + pl->pcie_gen = amdgpu_get_pcie_gen_support(adev, + si_pi->sys_pcie_mask, + si_pi->boot_pcie_gen, + clock_info->si.ucPCIEGen); /* patch up vddc if necessary */ ret = si_get_leakage_voltage_from_leakage_index(adev, pl->vddc, @@ -7326,7 +7305,6 @@ static int si_dpm_init(struct amdgpu_device *adev) struct si_power_info *si_pi; struct atom_clock_dividers dividers; int ret; - u32 mask; si_pi = kzalloc(sizeof(struct si_power_info), GFP_KERNEL); if (si_pi == NULL) @@ -7336,11 +7314,9 @@ static int si_dpm_init(struct amdgpu_device *adev) eg_pi = &ni_pi->eg; pi = &eg_pi->rv7xx; - ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask); - if (ret) - si_pi->sys_pcie_mask = 0; - else - si_pi->sys_pcie_mask = mask; + si_pi->sys_pcie_mask = + (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >> + CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT; si_pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID; si_pi->boot_pcie_gen = si_get_current_pcie_speed(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index b2bfedaf57f1..9bab4842cd44 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -1618,7 +1618,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_enc_ring_vm_funcs = { .set_wptr = uvd_v6_0_enc_ring_set_wptr, .emit_frame_size = 4 + /* uvd_v6_0_enc_ring_emit_pipeline_sync */ - 6 + /* uvd_v6_0_enc_ring_emit_vm_flush */ + 5 + /* uvd_v6_0_enc_ring_emit_vm_flush */ 5 + 5 + /* uvd_v6_0_enc_ring_emit_fence x2 vm fence */ 1, /* uvd_v6_0_enc_ring_insert_end */ .emit_ib_size = 5, /* uvd_v6_0_enc_ring_emit_ib */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 1ce4c98385e3..63c67346d316 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -629,11 +629,13 @@ static int dm_resume(void *handle) { struct amdgpu_device *adev = handle; struct amdgpu_display_manager *dm = &adev->dm; + int ret = 0; /* power on hardware */ dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0); - return 0; + ret = amdgpu_dm_display_resume(adev); + return ret; } int amdgpu_dm_display_resume(struct amdgpu_device *adev) @@ -1035,6 +1037,10 @@ static void handle_hpd_rx_irq(void *param) !is_mst_root_connector) { /* Downstream Port status changed. */ if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) { + + if (aconnector->fake_enable) + aconnector->fake_enable = false; + amdgpu_dm_update_connector_after_detect(aconnector); @@ -2010,30 +2016,32 @@ static void update_stream_scaling_settings(const struct drm_display_mode *mode, dst.width = stream->timing.h_addressable; dst.height = stream->timing.v_addressable; - rmx_type = dm_state->scaling; - if (rmx_type == RMX_ASPECT || rmx_type == RMX_OFF) { - if (src.width * dst.height < - src.height * dst.width) { - /* height needs less upscaling/more downscaling */ - dst.width = src.width * - dst.height / src.height; - } else { - /* width needs less upscaling/more downscaling */ - dst.height = src.height * - dst.width / src.width; + if (dm_state) { + rmx_type = dm_state->scaling; + if (rmx_type == RMX_ASPECT || rmx_type == RMX_OFF) { + if (src.width * dst.height < + src.height * dst.width) { + /* height needs less upscaling/more downscaling */ + dst.width = src.width * + dst.height / src.height; + } else { + /* width needs less upscaling/more downscaling */ + dst.height = src.height * + dst.width / src.width; + } + } else if (rmx_type == RMX_CENTER) { + dst = src; } - } else if (rmx_type == RMX_CENTER) { - dst = src; - } - dst.x = (stream->timing.h_addressable - dst.width) / 2; - dst.y = (stream->timing.v_addressable - dst.height) / 2; + dst.x = (stream->timing.h_addressable - dst.width) / 2; + dst.y = (stream->timing.v_addressable - dst.height) / 2; - if (dm_state->underscan_enable) { - dst.x += dm_state->underscan_hborder / 2; - dst.y += dm_state->underscan_vborder / 2; - dst.width -= dm_state->underscan_hborder; - dst.height -= dm_state->underscan_vborder; + if (dm_state->underscan_enable) { + dst.x += dm_state->underscan_hborder / 2; + dst.y += dm_state->underscan_vborder / 2; + dst.width -= dm_state->underscan_hborder; + dst.height -= dm_state->underscan_vborder; + } } stream->src = src; @@ -2358,12 +2366,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (aconnector == NULL) { DRM_ERROR("aconnector is NULL!\n"); - goto drm_connector_null; - } - - if (dm_state == NULL) { - DRM_ERROR("dm_state is NULL!\n"); - goto dm_state_null; + return stream; } drm_connector = &aconnector->base; @@ -2375,18 +2378,18 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, */ if (aconnector->mst_port) { dm_dp_mst_dc_sink_create(drm_connector); - goto mst_dc_sink_create_done; + return stream; } if (create_fake_sink(aconnector)) - goto stream_create_fail; + return stream; } stream = dc_create_stream_for_sink(aconnector->dc_sink); if (stream == NULL) { DRM_ERROR("Failed to create stream for sink!\n"); - goto stream_create_fail; + return stream; } list_for_each_entry(preferred_mode, &aconnector->base.modes, head) { @@ -2412,9 +2415,12 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, } else { decide_crtc_timing_for_drm_display_mode( &mode, preferred_mode, - dm_state->scaling != RMX_OFF); + dm_state ? (dm_state->scaling != RMX_OFF) : false); } + if (!dm_state) + drm_mode_set_crtcinfo(&mode, 0); + fill_stream_properties_from_drm_display_mode(stream, &mode, &aconnector->base); update_stream_scaling_settings(&mode, dm_state, stream); @@ -2424,10 +2430,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, drm_connector, aconnector->dc_sink); -stream_create_fail: -dm_state_null: -drm_connector_null: -mst_dc_sink_create_done: + update_stream_signal(stream); + return stream; } @@ -2495,6 +2499,27 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc) return &state->base; } + +static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) +{ + enum dc_irq_source irq_source; + struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); + struct amdgpu_device *adev = crtc->dev->dev_private; + + irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; + return dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; +} + +static int dm_enable_vblank(struct drm_crtc *crtc) +{ + return dm_set_vblank(crtc, true); +} + +static void dm_disable_vblank(struct drm_crtc *crtc) +{ + dm_set_vblank(crtc, false); +} + /* Implemented only the options currently availible for the driver */ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = { .reset = dm_crtc_reset_state, @@ -2504,6 +2529,8 @@ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = { .page_flip = drm_atomic_helper_page_flip, .atomic_duplicate_state = dm_crtc_duplicate_state, .atomic_destroy_state = dm_crtc_destroy_state, + .enable_vblank = dm_enable_vblank, + .disable_vblank = dm_disable_vblank, }; static enum drm_connector_status @@ -2798,7 +2825,7 @@ int amdgpu_dm_connector_mode_valid(struct drm_connector *connector, goto fail; } - stream = dc_create_stream_for_sink(dc_sink); + stream = create_stream_for_sink(aconnector, mode, NULL); if (stream == NULL) { DRM_ERROR("Failed to create stream for sink!\n"); goto fail; @@ -3058,6 +3085,9 @@ static int dm_plane_atomic_check(struct drm_plane *plane, if (!dm_plane_state->dc_state) return 0; + if (!fill_rects_from_plane_state(state, dm_plane_state->dc_state)) + return -EINVAL; + if (dc_validate_plane(dc, dm_plane_state->dc_state) == DC_OK) return 0; @@ -3104,8 +3134,6 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm, switch (aplane->base.type) { case DRM_PLANE_TYPE_PRIMARY: - aplane->base.format_default = true; - res = drm_universal_plane_init( dm->adev->ddev, &aplane->base, @@ -4630,8 +4658,6 @@ static int dm_update_planes_state(struct dc *dc, bool pflip_needed = !state->allow_modeset; int ret = 0; - if (pflip_needed) - return ret; /* Add new planes */ for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { @@ -4646,6 +4672,8 @@ static int dm_update_planes_state(struct dc *dc, /* Remove any changed/removed planes */ if (!enable) { + if (pflip_needed) + continue; if (!old_plane_crtc) continue; @@ -4677,6 +4705,7 @@ static int dm_update_planes_state(struct dc *dc, *lock_and_validation_needed = true; } else { /* Add new planes */ + struct dc_plane_state *dc_new_plane_state; if (drm_atomic_plane_disabling(plane->state, new_plane_state)) continue; @@ -4690,38 +4719,50 @@ static int dm_update_planes_state(struct dc *dc, if (!dm_new_crtc_state->stream) continue; + if (pflip_needed) + continue; WARN_ON(dm_new_plane_state->dc_state); - dm_new_plane_state->dc_state = dc_create_plane_state(dc); - - DRM_DEBUG_DRIVER("Enabling DRM plane: %d on DRM crtc %d\n", - plane->base.id, new_plane_crtc->base.id); - - if (!dm_new_plane_state->dc_state) { + dc_new_plane_state = dc_create_plane_state(dc); + if (!dc_new_plane_state) { ret = -EINVAL; return ret; } + DRM_DEBUG_DRIVER("Enabling DRM plane: %d on DRM crtc %d\n", + plane->base.id, new_plane_crtc->base.id); + ret = fill_plane_attributes( new_plane_crtc->dev->dev_private, - dm_new_plane_state->dc_state, + dc_new_plane_state, new_plane_state, new_crtc_state); - if (ret) + if (ret) { + dc_plane_state_release(dc_new_plane_state); return ret; + } - + /* + * Any atomic check errors that occur after this will + * not need a release. The plane state will be attached + * to the stream, and therefore part of the atomic + * state. It'll be released when the atomic state is + * cleaned. + */ if (!dc_add_plane_to_context( dc, dm_new_crtc_state->stream, - dm_new_plane_state->dc_state, + dc_new_plane_state, dm_state->context)) { + dc_plane_state_release(dc_new_plane_state); ret = -EINVAL; return ret; } + dm_new_plane_state->dc_state = dc_new_plane_state; + /* Tell DC to do a full surface update every time there * is a plane change. Inefficient, but works for now. */ @@ -4735,6 +4776,33 @@ static int dm_update_planes_state(struct dc *dc, return ret; } +static int dm_atomic_check_plane_state_fb(struct drm_atomic_state *state, + struct drm_crtc *crtc) +{ + struct drm_plane *plane; + struct drm_crtc_state *crtc_state; + + WARN_ON(!drm_atomic_get_new_crtc_state(state, crtc)); + + drm_for_each_plane_mask(plane, state->dev, crtc->state->plane_mask) { + struct drm_plane_state *plane_state = + drm_atomic_get_plane_state(state, plane); + + if (IS_ERR(plane_state)) + return -EDEADLK; + + crtc_state = drm_atomic_get_crtc_state(plane_state->state, crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); + + if (crtc->primary == plane && crtc_state->active) { + if (!plane_state->fb) + return -EINVAL; + } + } + return 0; +} + static int amdgpu_dm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { @@ -4758,6 +4826,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { + ret = dm_atomic_check_plane_state_fb(state, crtc); + if (ret) + goto fail; + if (!drm_atomic_crtc_needs_modeset(new_crtc_state) && !new_crtc_state->color_mgmt_changed) continue; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 9bd142f65f9b..e1acc10e35a2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -109,7 +109,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( struct cea_sad *sad = &sads[i]; edid_caps->audio_modes[i].format_code = sad->format; - edid_caps->audio_modes[i].channel_count = sad->channels; + edid_caps->audio_modes[i].channel_count = sad->channels + 1; edid_caps->audio_modes[i].sample_rate = sad->freq; edid_caps->audio_modes[i].sample_size = sad->byte2; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c index 1874b6cee6af..422055080df4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c @@ -683,10 +683,8 @@ static const struct amdgpu_irq_src_funcs dm_hpd_irq_funcs = { void amdgpu_dm_set_irq_funcs(struct amdgpu_device *adev) { - if (adev->mode_info.num_crtc > 0) - adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VLINE1 + adev->mode_info.num_crtc; - else - adev->crtc_irq.num_types = 0; + + adev->crtc_irq.num_types = adev->mode_info.num_crtc; adev->crtc_irq.funcs = &dm_crtc_irq_funcs; adev->pageflip_irq.num_types = adev->mode_info.num_crtc; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index f3d87f418d2e..93421dad21bd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -189,6 +189,12 @@ void dm_dp_mst_dc_sink_create(struct drm_connector *connector) .link = aconnector->dc_link, .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; + /* + * TODO: Need to further figure out why ddc.algo is NULL while MST port exists + */ + if (!aconnector->port || !aconnector->port->aux.ddc.algo) + return; + edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port); if (!edid) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 35e84ed031de..12868c769606 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1358,13 +1358,13 @@ enum dc_irq_source dc_interrupt_to_irq_source( return dal_irq_service_to_irq_source(dc->res_pool->irqs, src_id, ext_id); } -void dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable) +bool dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable) { if (dc == NULL) - return; + return false; - dal_irq_service_set(dc->res_pool->irqs, src, enable); + return dal_irq_service_set(dc->res_pool->irqs, src, enable); } void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index a37428271573..be5546181fa8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1749,8 +1749,7 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) link->link_enc, pipe_ctx->clock_source->id, display_color_depth, - pipe_ctx->stream->signal == SIGNAL_TYPE_HDMI_TYPE_A, - pipe_ctx->stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK, + pipe_ctx->stream->signal, stream->phy_pix_clk); if (pipe_ctx->stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 33d91e4474ea..639421a00ab6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1465,7 +1465,7 @@ void decide_link_settings(struct dc_stream_state *stream, /* MST doesn't perform link training for now * TODO: add MST specific link training routine */ - if (is_mst_supported(link)) { + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { *link_setting = link->verified_link_cap; return; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 95b8dd0e53c6..4d07ffebfd31 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1360,9 +1360,6 @@ bool dc_is_stream_scaling_unchanged( return true; } -/* Maximum TMDS single link pixel clock 165MHz */ -#define TMDS_MAX_PIXEL_CLOCK_IN_KHZ 165000 - static void update_stream_engine_usage( struct resource_context *res_ctx, const struct resource_pool *pool, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 261811e0c094..cd5819789d76 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -33,8 +33,7 @@ /******************************************************************************* * Private functions ******************************************************************************/ -#define TMDS_MAX_PIXEL_CLOCK_IN_KHZ_UPMOST 297000 -static void update_stream_signal(struct dc_stream_state *stream) +void update_stream_signal(struct dc_stream_state *stream) { struct dc_sink *dc_sink = stream->sink; @@ -45,8 +44,9 @@ static void update_stream_signal(struct dc_stream_state *stream) stream->signal = dc_sink->sink_signal; if (dc_is_dvi_signal(stream->signal)) { - if (stream->timing.pix_clk_khz > TMDS_MAX_PIXEL_CLOCK_IN_KHZ_UPMOST && - stream->sink->sink_signal != SIGNAL_TYPE_DVI_SINGLE_LINK) + if (stream->ctx->dc->caps.dual_link_dvi && + stream->timing.pix_clk_khz > TMDS_MAX_PIXEL_CLOCK && + stream->sink->sink_signal != SIGNAL_TYPE_DVI_SINGLE_LINK) stream->signal = SIGNAL_TYPE_DVI_DUAL_LINK; else stream->signal = SIGNAL_TYPE_DVI_SINGLE_LINK; @@ -193,44 +193,20 @@ bool dc_stream_set_cursor_attributes( core_dc = stream->ctx->dc; res_ctx = &core_dc->current_state->res_ctx; + stream->cursor_attributes = *attributes; for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; - if (pipe_ctx->stream != stream || (!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp)) + if (pipe_ctx->stream != stream || (!pipe_ctx->plane_res.xfm && + !pipe_ctx->plane_res.dpp) || !pipe_ctx->plane_res.ipp) continue; if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) continue; - if (pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes != NULL) - pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes( - pipe_ctx->plane_res.ipp, attributes); - - if (pipe_ctx->plane_res.hubp != NULL && - pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes( - pipe_ctx->plane_res.hubp, attributes); - - if (pipe_ctx->plane_res.mi != NULL && - pipe_ctx->plane_res.mi->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.mi->funcs->set_cursor_attributes( - pipe_ctx->plane_res.mi, attributes); - - - if (pipe_ctx->plane_res.xfm != NULL && - pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes( - pipe_ctx->plane_res.xfm, attributes); - - if (pipe_ctx->plane_res.dpp != NULL && - pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes != NULL) - pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes( - pipe_ctx->plane_res.dpp, attributes->color_format); + core_dc->hwss.set_cursor_attribute(pipe_ctx); } - - stream->cursor_attributes = *attributes; - return true; } @@ -254,55 +230,21 @@ bool dc_stream_set_cursor_position( core_dc = stream->ctx->dc; res_ctx = &core_dc->current_state->res_ctx; + stream->cursor_position = *position; for (i = 0; i < MAX_PIPES; i++) { struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i]; - struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp; - struct mem_input *mi = pipe_ctx->plane_res.mi; - struct hubp *hubp = pipe_ctx->plane_res.hubp; - struct dpp *dpp = pipe_ctx->plane_res.dpp; - struct dc_cursor_position pos_cpy = *position; - struct dc_cursor_mi_param param = { - .pixel_clk_khz = stream->timing.pix_clk_khz, - .ref_clk_khz = core_dc->res_pool->ref_clock_inKhz, - .viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x, - .viewport_width = pipe_ctx->plane_res.scl_data.viewport.width, - .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz - }; if (pipe_ctx->stream != stream || (!pipe_ctx->plane_res.mi && !pipe_ctx->plane_res.hubp) || !pipe_ctx->plane_state || - (!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp)) - continue; - - if (pipe_ctx->plane_state->address.type - == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) - pos_cpy.enable = false; - - if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) - pos_cpy.enable = false; - - - if (ipp != NULL && ipp->funcs->ipp_cursor_set_position != NULL) - ipp->funcs->ipp_cursor_set_position(ipp, &pos_cpy, ¶m); - - if (mi != NULL && mi->funcs->set_cursor_position != NULL) - mi->funcs->set_cursor_position(mi, &pos_cpy, ¶m); - - if (!hubp) + (!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp) || + !pipe_ctx->plane_res.ipp) continue; - if (hubp->funcs->set_cursor_position != NULL) - hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m); - - if (dpp != NULL && dpp->funcs->set_cursor_position != NULL) - dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width); - + core_dc->hwss.set_cursor_position(pipe_ctx); } - stream->cursor_position = *position; - return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index e2e3c9df79ea..d6d56611604e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -62,6 +62,7 @@ struct dc_caps { bool dcc_const_color; bool dynamic_audio; bool is_apu; + bool dual_link_dvi; }; struct dc_dcc_surface_param { @@ -672,7 +673,7 @@ enum dc_irq_source dc_interrupt_to_irq_source( struct dc *dc, uint32_t src_id, uint32_t ext_id); -void dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable); +bool dc_interrupt_set(struct dc *dc, enum dc_irq_source src, bool enable); void dc_interrupt_ack(struct dc *dc, enum dc_irq_source src); enum dc_irq_source dc_get_hpd_irq_source_at_index( struct dc *dc, uint32_t link_index); diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 01c60f11b2bd..456e4d29eadd 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -237,6 +237,8 @@ enum surface_update_type dc_check_update_surfaces_for_stream( */ struct dc_stream_state *dc_create_stream_for_sink(struct dc_sink *dc_sink); +void update_stream_signal(struct dc_stream_state *stream); + void dc_stream_retain(struct dc_stream_state *dc_stream); void dc_stream_release(struct dc_stream_state *dc_stream); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h index b73db9e78437..f11f17fe08f9 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h @@ -236,6 +236,7 @@ SR(D2VGA_CONTROL), \ SR(D3VGA_CONTROL), \ SR(D4VGA_CONTROL), \ + SR(VGA_TEST_CONTROL), \ SR(DC_IP_REQUEST_CNTL), \ BL_REG_LIST() @@ -337,6 +338,7 @@ struct dce_hwseq_registers { uint32_t D2VGA_CONTROL; uint32_t D3VGA_CONTROL; uint32_t D4VGA_CONTROL; + uint32_t VGA_TEST_CONTROL; /* MMHUB registers. read only. temporary hack */ uint32_t VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32; uint32_t VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32; @@ -493,6 +495,12 @@ struct dce_hwseq_registers { HWS_SF(, DOMAIN6_PG_STATUS, DOMAIN6_PGFSM_PWR_STATUS, mask_sh), \ HWS_SF(, DOMAIN7_PG_STATUS, DOMAIN7_PGFSM_PWR_STATUS, mask_sh), \ HWS_SF(, DC_IP_REQUEST_CNTL, IP_REQUEST_EN, mask_sh), \ + HWS_SF(, D1VGA_CONTROL, D1VGA_MODE_ENABLE, mask_sh),\ + HWS_SF(, D2VGA_CONTROL, D2VGA_MODE_ENABLE, mask_sh),\ + HWS_SF(, D3VGA_CONTROL, D3VGA_MODE_ENABLE, mask_sh),\ + HWS_SF(, D4VGA_CONTROL, D4VGA_MODE_ENABLE, mask_sh),\ + HWS_SF(, VGA_TEST_CONTROL, VGA_TEST_ENABLE, mask_sh),\ + HWS_SF(, VGA_TEST_CONTROL, VGA_TEST_RENDER_START, mask_sh),\ HWS_SF(, LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh), \ HWS_SF(, LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh) @@ -583,7 +591,13 @@ struct dce_hwseq_registers { type DCFCLK_GATE_DIS; \ type DCHUBBUB_GLOBAL_TIMER_REFDIV; \ type DENTIST_DPPCLK_WDIVIDER; \ - type DENTIST_DISPCLK_WDIVIDER; + type DENTIST_DISPCLK_WDIVIDER; \ + type VGA_TEST_ENABLE; \ + type VGA_TEST_RENDER_START; \ + type D1VGA_MODE_ENABLE; \ + type D2VGA_MODE_ENABLE; \ + type D3VGA_MODE_ENABLE; \ + type D4VGA_MODE_ENABLE; struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index a266e3f5e75f..e4741f1a2b01 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -82,13 +82,6 @@ #define DCE110_DIG_FE_SOURCE_SELECT_DIGF 0x20 #define DCE110_DIG_FE_SOURCE_SELECT_DIGG 0x40 -/* Minimum pixel clock, in KHz. For TMDS signal is 25.00 MHz */ -#define TMDS_MIN_PIXEL_CLOCK 25000 -/* Maximum pixel clock, in KHz. For TMDS signal is 165.00 MHz */ -#define TMDS_MAX_PIXEL_CLOCK 165000 -/* For current ASICs pixel clock - 600MHz */ -#define MAX_ENCODER_CLOCK 600000 - enum { DP_MST_UPDATE_MAX_RETRY = 50 }; @@ -683,6 +676,7 @@ void dce110_link_encoder_construct( { struct bp_encoder_cap_info bp_cap_info = {0}; const struct dc_vbios_funcs *bp_funcs = init_data->ctx->dc_bios->funcs; + enum bp_result result = BP_RESULT_OK; enc110->base.funcs = &dce110_lnk_enc_funcs; enc110->base.ctx = init_data->ctx; @@ -757,15 +751,24 @@ void dce110_link_encoder_construct( enc110->base.preferred_engine = ENGINE_ID_UNKNOWN; } + /* default to one to mirror Windows behavior */ + enc110->base.features.flags.bits.HDMI_6GB_EN = 1; + + result = bp_funcs->get_encoder_cap_info(enc110->base.ctx->dc_bios, + enc110->base.id, &bp_cap_info); + /* Override features with DCE-specific values */ - if (BP_RESULT_OK == bp_funcs->get_encoder_cap_info( - enc110->base.ctx->dc_bios, enc110->base.id, - &bp_cap_info)) { + if (BP_RESULT_OK == result) { enc110->base.features.flags.bits.IS_HBR2_CAPABLE = bp_cap_info.DP_HBR2_EN; enc110->base.features.flags.bits.IS_HBR3_CAPABLE = bp_cap_info.DP_HBR3_EN; enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN; + } else { + dm_logger_write(enc110->base.ctx->logger, LOG_WARNING, + "%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n", + __func__, + result); } } @@ -904,8 +907,7 @@ void dce110_link_encoder_enable_tmds_output( struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock) { struct dce110_link_encoder *enc110 = TO_DCE110_LINK_ENC(enc); @@ -919,16 +921,12 @@ void dce110_link_encoder_enable_tmds_output( cntl.engine_id = enc->preferred_engine; cntl.transmitter = enc110->base.transmitter; cntl.pll_id = clock_source; - if (hdmi) { - cntl.signal = SIGNAL_TYPE_HDMI_TYPE_A; - cntl.lanes_number = 4; - } else if (dual_link) { - cntl.signal = SIGNAL_TYPE_DVI_DUAL_LINK; + cntl.signal = signal; + if (cntl.signal == SIGNAL_TYPE_DVI_DUAL_LINK) cntl.lanes_number = 8; - } else { - cntl.signal = SIGNAL_TYPE_DVI_SINGLE_LINK; + else cntl.lanes_number = 4; - } + cntl.hpd_sel = enc110->base.hpd_source; cntl.pixel_clock = pixel_clock; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h index 8ca9afe47a2b..0ec3433d34b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.h @@ -210,8 +210,7 @@ void dce110_link_encoder_enable_tmds_output( struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock); /* enables DP PHY output */ diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c b/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c index 3931412ab6d3..87093894ea9e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_opp.c @@ -128,23 +128,22 @@ static void set_truncation( return; } /* on other format-to do */ - if (params->flags.TRUNCATE_ENABLED == 0 || - params->flags.TRUNCATE_DEPTH == 2) + if (params->flags.TRUNCATE_ENABLED == 0) return; /*Set truncation depth and Enable truncation*/ REG_UPDATE_3(FMT_BIT_DEPTH_CONTROL, FMT_TRUNCATE_EN, 1, FMT_TRUNCATE_DEPTH, - params->flags.TRUNCATE_MODE, + params->flags.TRUNCATE_DEPTH, FMT_TRUNCATE_MODE, - params->flags.TRUNCATE_DEPTH); + params->flags.TRUNCATE_MODE); } /** * set_spatial_dither * 1) set spatial dithering mode: pattern of seed - * 2) set spatical dithering depth: 0 for 18bpp or 1 for 24bpp + * 2) set spatial dithering depth: 0 for 18bpp or 1 for 24bpp * 3) set random seed * 4) set random mode * lfsr is reset every frame or not reset diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c index 3ea43e2a9450..442dd2d93618 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c @@ -852,6 +852,7 @@ static bool construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 40; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; for (i = 0; i < pool->base.pipe_count; i++) { pool->base.timing_generators[i] = diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 86cdd7b4811f..6f382a3ac90f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -688,15 +688,22 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; struct dc_link *link = pipe_ctx->stream->sink->link; - /* 1. update AVI info frame (HDMI, DP) - * we always need to update info frame - */ + uint32_t active_total_with_borders; uint32_t early_control = 0; struct timing_generator *tg = pipe_ctx->stream_res.tg; - /* TODOFPGA may change to hwss.update_info_frame */ + /* For MST, there are multiply stream go to only one link. + * connect DIG back_end to front_end while enable_stream and + * disconnect them during disable_stream + * BY this, it is logic clean to separate stream and link */ + link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc, + pipe_ctx->stream_res.stream_enc->id, true); + + /* update AVI info frame (HDMI, DP)*/ + /* TODO: FPGA may change to hwss.update_info_frame */ dce110_update_info_frame(pipe_ctx); + /* enable early control to avoid corruption on DP monitor*/ active_total_with_borders = timing->h_addressable @@ -717,12 +724,8 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx) pipe_ctx->stream_res.stream_enc->funcs->dp_audio_enable(pipe_ctx->stream_res.stream_enc); } - /* For MST, there are multiply stream go to only one link. - * connect DIG back_end to front_end while enable_stream and - * disconnect them during disable_stream - * BY this, it is logic clean to separate stream and link */ - link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc, - pipe_ctx->stream_res.stream_enc->id, true); + + } @@ -1690,9 +1693,13 @@ static void apply_min_clocks( * Check if FBC can be enabled */ static bool should_enable_fbc(struct dc *dc, - struct dc_state *context) + struct dc_state *context, + uint32_t *pipe_idx) { - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[0]; + uint32_t i; + struct pipe_ctx *pipe_ctx = NULL; + struct resource_context *res_ctx = &context->res_ctx; + ASSERT(dc->fbc_compressor); @@ -1704,6 +1711,14 @@ static bool should_enable_fbc(struct dc *dc, if (context->stream_count != 1) return false; + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (res_ctx->pipe_ctx[i].stream) { + pipe_ctx = &res_ctx->pipe_ctx[i]; + *pipe_idx = i; + break; + } + } + /* Only supports eDP */ if (pipe_ctx->stream->sink->link->connector_signal != SIGNAL_TYPE_EDP) return false; @@ -1729,11 +1744,14 @@ static bool should_enable_fbc(struct dc *dc, static void enable_fbc(struct dc *dc, struct dc_state *context) { - if (should_enable_fbc(dc, context)) { + uint32_t pipe_idx = 0; + + if (should_enable_fbc(dc, context, &pipe_idx)) { /* Program GRPH COMPRESSED ADDRESS and PITCH */ struct compr_addr_and_pitch_params params = {0, 0, 0}; struct compressor *compr = dc->fbc_compressor; - struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[0]; + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx]; + params.source_view_width = pipe_ctx->stream->timing.h_addressable; params.source_view_height = pipe_ctx->stream->timing.v_addressable; @@ -2915,6 +2933,49 @@ static void program_csc_matrix(struct pipe_ctx *pipe_ctx, } } +void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; + struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp; + struct mem_input *mi = pipe_ctx->plane_res.mi; + struct dc_cursor_mi_param param = { + .pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz, + .ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz, + .viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x, + .viewport_width = pipe_ctx->plane_res.scl_data.viewport.width, + .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz + }; + + if (pipe_ctx->plane_state->address.type + == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + pos_cpy.enable = false; + + if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) + pos_cpy.enable = false; + + if (ipp->funcs->ipp_cursor_set_position) + ipp->funcs->ipp_cursor_set_position(ipp, &pos_cpy, ¶m); + if (mi->funcs->set_cursor_position) + mi->funcs->set_cursor_position(mi, &pos_cpy, ¶m); +} + +void dce110_set_cursor_attribute(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; + + if (pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes) + pipe_ctx->plane_res.ipp->funcs->ipp_cursor_set_attributes( + pipe_ctx->plane_res.ipp, attributes); + + if (pipe_ctx->plane_res.mi->funcs->set_cursor_attributes) + pipe_ctx->plane_res.mi->funcs->set_cursor_attributes( + pipe_ctx->plane_res.mi, attributes); + + if (pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes) + pipe_ctx->plane_res.xfm->funcs->set_cursor_attributes( + pipe_ctx->plane_res.xfm, attributes); +} + static void ready_shared_resources(struct dc *dc, struct dc_state *context) {} static void optimize_shared_resources(struct dc *dc) {} @@ -2957,6 +3018,8 @@ static const struct hw_sequencer_funcs dce110_funcs = { .edp_backlight_control = hwss_edp_backlight_control, .edp_power_control = hwss_edp_power_control, .edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready, + .set_cursor_position = dce110_set_cursor_position, + .set_cursor_attribute = dce110_set_cursor_attribute }; void dce110_hw_sequencer_construct(struct dc *dc) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index 7c4779578fb7..00f18c485e1e 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -846,6 +846,16 @@ static bool dce110_validate_bandwidth( return result; } +enum dc_status dce110_validate_plane(const struct dc_plane_state *plane_state, + struct dc_caps *caps) +{ + if (((plane_state->dst_rect.width * 2) < plane_state->src_rect.width) || + ((plane_state->dst_rect.height * 2) < plane_state->src_rect.height)) + return DC_FAIL_SURFACE_VALIDATE; + + return DC_OK; +} + static bool dce110_validate_surface_sets( struct dc_state *context) { @@ -869,6 +879,13 @@ static bool dce110_validate_surface_sets( plane->src_rect.height > 1080)) return false; + /* we don't have the logic to support underlay + * only yet so block the use case where we get + * NV12 plane as top layer + */ + if (j == 0) + return false; + /* irrespective of plane format, * stream should be RGB encoded */ @@ -1021,6 +1038,7 @@ static const struct resource_funcs dce110_res_pool_funcs = { .link_enc_create = dce110_link_encoder_create, .validate_guaranteed = dce110_validate_guaranteed, .validate_bandwidth = dce110_validate_bandwidth, + .validate_plane = dce110_validate_plane, .acquire_idle_pipe_for_layer = dce110_acquire_underlay, .add_stream_to_ctx = dce110_add_stream_to_ctx, .validate_global = dce110_validate_global diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c index 663e0a047a4b..98d9cd0109e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c @@ -1103,6 +1103,8 @@ static bool construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 100; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; + /************************************************* * Create resources * diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c index 57cd67359567..5aab01db28ee 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c @@ -835,6 +835,8 @@ static bool construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 100; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; + dc->debug = debug_defaults; /************************************************* diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index 8f2bd56f3461..25d7eb1567ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -793,6 +793,7 @@ static bool dce80_construct( dc->caps.max_downscale_ratio = 200; dc->caps.i2c_speed_in_khz = 40; dc->caps.max_cursor_size = 128; + dc->caps.dual_link_dvi = true; /************************************************* * Create resources * diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 82572863acab..dc1e010725c1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -238,10 +238,34 @@ static void enable_power_gating_plane( static void disable_vga( struct dce_hwseq *hws) { + unsigned int in_vga1_mode = 0; + unsigned int in_vga2_mode = 0; + unsigned int in_vga3_mode = 0; + unsigned int in_vga4_mode = 0; + + REG_GET(D1VGA_CONTROL, D1VGA_MODE_ENABLE, &in_vga1_mode); + REG_GET(D2VGA_CONTROL, D2VGA_MODE_ENABLE, &in_vga2_mode); + REG_GET(D3VGA_CONTROL, D3VGA_MODE_ENABLE, &in_vga3_mode); + REG_GET(D4VGA_CONTROL, D4VGA_MODE_ENABLE, &in_vga4_mode); + + if (in_vga1_mode == 0 && in_vga2_mode == 0 && + in_vga3_mode == 0 && in_vga4_mode == 0) + return; + REG_WRITE(D1VGA_CONTROL, 0); REG_WRITE(D2VGA_CONTROL, 0); REG_WRITE(D3VGA_CONTROL, 0); REG_WRITE(D4VGA_CONTROL, 0); + + /* HW Engineer's Notes: + * During switch from vga->extended, if we set the VGA_TEST_ENABLE and + * then hit the VGA_TEST_RENDER_START, then the DCHUBP timing gets updated correctly. + * + * Then vBIOS will have it poll for the VGA_TEST_RENDER_DONE and unset + * VGA_TEST_ENABLE, to leave it in the same state as before. + */ + REG_UPDATE(VGA_TEST_CONTROL, VGA_TEST_ENABLE, 1); + REG_UPDATE(VGA_TEST_CONTROL, VGA_TEST_RENDER_START, 1); } static void dpp_pg_control( @@ -1761,6 +1785,11 @@ static void update_dchubp_dpp( &pipe_ctx->plane_res.scl_data.viewport_c); } + if (pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { + dc->hwss.set_cursor_position(pipe_ctx); + dc->hwss.set_cursor_attribute(pipe_ctx); + } + if (plane_state->update_flags.bits.full_update) { /*gamut remap*/ program_gamut_remap(pipe_ctx); @@ -2296,7 +2325,7 @@ static bool dcn10_dummy_display_power_gating( return true; } -void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx) +static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx) { struct dc_plane_state *plane_state = pipe_ctx->plane_state; struct timing_generator *tg = pipe_ctx->stream_res.tg; @@ -2316,12 +2345,46 @@ void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx) } } -void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data) +static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data) { if (hws->ctx->dc->res_pool->hubbub != NULL) hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data); } +static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; + struct hubp *hubp = pipe_ctx->plane_res.hubp; + struct dpp *dpp = pipe_ctx->plane_res.dpp; + struct dc_cursor_mi_param param = { + .pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz, + .ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz, + .viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x, + .viewport_width = pipe_ctx->plane_res.scl_data.viewport.width, + .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz + }; + + if (pipe_ctx->plane_state->address.type + == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + pos_cpy.enable = false; + + if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state) + pos_cpy.enable = false; + + hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m); + dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width); +} + +static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx) +{ + struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; + + pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes( + pipe_ctx->plane_res.hubp, attributes); + pipe_ctx->plane_res.dpp->funcs->set_cursor_attributes( + pipe_ctx->plane_res.dpp, attributes->color_format); +} + static const struct hw_sequencer_funcs dcn10_funcs = { .program_gamut_remap = program_gamut_remap, .program_csc_matrix = program_csc_matrix, @@ -2362,6 +2425,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .edp_backlight_control = hwss_edp_backlight_control, .edp_power_control = hwss_edp_power_control, .edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready, + .set_cursor_position = dcn10_set_cursor_position, + .set_cursor_attribute = dcn10_set_cursor_attribute }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h index 0fd329deacd8..54d8a1386142 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h @@ -123,8 +123,7 @@ struct link_encoder_funcs { void (*enable_tmds_output)(struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock); void (*enable_dp_output)(struct link_encoder *enc, const struct dc_link_settings *link_settings, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 4c0aa56f7bae..379c6ecd271a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -198,6 +198,9 @@ struct hw_sequencer_funcs { bool enable); void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up); + void (*set_cursor_position)(struct pipe_ctx *pipe); + void (*set_cursor_attribute)(struct pipe_ctx *pipe); + }; void color_space_to_black_color( diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c index f7e40b292dfb..d3e1923b01a8 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c @@ -217,7 +217,7 @@ bool dce110_vblank_set( core_dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg; if (enable) { - if (!tg->funcs->arm_vert_intr(tg, 2)) { + if (!tg || !tg->funcs->arm_vert_intr(tg, 2)) { DC_ERROR("Failed to get VBLANK!\n"); return false; } diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c index 57a54a7b89e5..1c079ba37c30 100644 --- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_encoder.c @@ -42,8 +42,7 @@ static void virtual_link_encoder_enable_tmds_output( struct link_encoder *enc, enum clock_source_id clock_source, enum dc_color_depth color_depth, - bool hdmi, - bool dual_link, + enum signal_type signal, uint32_t pixel_clock) {} static void virtual_link_encoder_enable_dp_output( diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h index 7a9b43f84a31..36bbad594267 100644 --- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h +++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h @@ -419,11 +419,6 @@ struct bios_event_info { bool backlight_changed; }; -enum { - HDMI_PIXEL_CLOCK_IN_KHZ_297 = 297000, - TMDS_PIXEL_CLOCK_IN_KHZ_165 = 165000 -}; - /* * DFS-bypass flag */ diff --git a/drivers/gpu/drm/amd/display/include/signal_types.h b/drivers/gpu/drm/amd/display/include/signal_types.h index b5ebde642207..199c5db67cbc 100644 --- a/drivers/gpu/drm/amd/display/include/signal_types.h +++ b/drivers/gpu/drm/amd/display/include/signal_types.h @@ -26,6 +26,11 @@ #ifndef __DC_SIGNAL_TYPES_H__ #define __DC_SIGNAL_TYPES_H__ +/* Minimum pixel clock, in KHz. For TMDS signal is 25.00 MHz */ +#define TMDS_MIN_PIXEL_CLOCK 25000 +/* Maximum pixel clock, in KHz. For TMDS signal is 165.00 MHz */ +#define TMDS_MAX_PIXEL_CLOCK 165000 + enum signal_type { SIGNAL_TYPE_NONE = 0L, /* no signal */ SIGNAL_TYPE_DVI_SINGLE_LINK = (1 << 0), diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 41e42beff213..08e8a793714f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -2756,10 +2756,13 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, PHM_PlatformCaps_DisableMclkSwitchingForFrameLock); - disable_mclk_switching = ((1 < info.display_count) || - disable_mclk_switching_for_frame_lock || - smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us) || - (mode_info.refresh_rate > 120)); + if (info.display_count == 0) + disable_mclk_switching = false; + else + disable_mclk_switching = ((1 < info.display_count) || + disable_mclk_switching_for_frame_lock || + smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us) || + (mode_info.refresh_rate > 120)); sclk = smu7_ps->performance_levels[0].engine_clock; mclk = smu7_ps->performance_levels[0].memory_clock; @@ -4534,13 +4537,6 @@ static int smu7_set_power_profile_state(struct pp_hwmgr *hwmgr, int tmp_result, result = 0; uint32_t sclk_mask = 0, mclk_mask = 0; - if (hwmgr->chip_id == CHIP_FIJI) { - if (request->type == AMD_PP_GFX_PROFILE) - smu7_enable_power_containment(hwmgr); - else if (request->type == AMD_PP_COMPUTE_PROFILE) - smu7_disable_power_containment(hwmgr); - } - if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_AUTO) return -EINVAL; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index 2d55dabc77d4..5f9c3efb532f 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -3168,10 +3168,13 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, disable_mclk_switching_for_vr = PP_CAP(PHM_PlatformCaps_DisableMclkSwitchForVR); force_mclk_high = PP_CAP(PHM_PlatformCaps_ForceMclkHigh); - disable_mclk_switching = (info.display_count > 1) || - disable_mclk_switching_for_frame_lock || - disable_mclk_switching_for_vr || - force_mclk_high; + if (info.display_count == 0) + disable_mclk_switching = false; + else + disable_mclk_switching = (info.display_count > 1) || + disable_mclk_switching_for_frame_lock || + disable_mclk_switching_for_vr || + force_mclk_high; sclk = vega10_ps->performance_levels[0].gfx_clock; mclk = vega10_ps->performance_levels[0].mem_clock; diff --git a/drivers/gpu/drm/ast/ast_tables.h b/drivers/gpu/drm/ast/ast_tables.h index 5f4c2e833a65..d665dd5af5dd 100644 --- a/drivers/gpu/drm/ast/ast_tables.h +++ b/drivers/gpu/drm/ast/ast_tables.h @@ -97,7 +97,7 @@ static const struct ast_vbios_dclk_info dclk_table[] = { {0x67, 0x22, 0x00}, /* 0E: VCLK157_5 */ {0x6A, 0x22, 0x00}, /* 0F: VCLK162 */ {0x4d, 0x4c, 0x80}, /* 10: VCLK154 */ - {0xa7, 0x78, 0x80}, /* 11: VCLK83.5 */ + {0x68, 0x6f, 0x80}, /* 11: VCLK83.5 */ {0x28, 0x49, 0x80}, /* 12: VCLK106.5 */ {0x37, 0x49, 0x80}, /* 13: VCLK146.25 */ {0x1f, 0x45, 0x80}, /* 14: VCLK148.5 */ @@ -127,7 +127,7 @@ static const struct ast_vbios_dclk_info dclk_table_ast2500[] = { {0x67, 0x22, 0x00}, /* 0E: VCLK157_5 */ {0x6A, 0x22, 0x00}, /* 0F: VCLK162 */ {0x4d, 0x4c, 0x80}, /* 10: VCLK154 */ - {0xa7, 0x78, 0x80}, /* 11: VCLK83.5 */ + {0x68, 0x6f, 0x80}, /* 11: VCLK83.5 */ {0x28, 0x49, 0x80}, /* 12: VCLK106.5 */ {0x37, 0x49, 0x80}, /* 13: VCLK146.25 */ {0x1f, 0x45, 0x80}, /* 14: VCLK148.5 */ diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index 5a13ff29f4f0..2dc5e8bed172 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -121,6 +121,10 @@ int drm_mode_addfb(struct drm_device *dev, r.pixel_format = drm_mode_legacy_fb_format(or->bpp, or->depth); r.handles[0] = or->handle; + if (r.pixel_format == DRM_FORMAT_XRGB2101010 && + dev->driver->driver_features & DRIVER_PREFER_XBGR_30BPP) + r.pixel_format = DRM_FORMAT_XBGR2101010; + ret = drm_mode_addfb2(dev, &r, file_priv); if (ret) return ret; @@ -457,6 +461,12 @@ int drm_mode_getfb(struct drm_device *dev, if (!fb) return -ENOENT; + /* Multi-planar framebuffers need getfb2. */ + if (fb->format->num_planes > 1) { + ret = -EINVAL; + goto out; + } + r->height = fb->height; r->width = fb->width; r->depth = fb->format->depth; @@ -480,6 +490,7 @@ int drm_mode_getfb(struct drm_device *dev, ret = -ENODEV; } +out: drm_framebuffer_put(fb); return ret; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index c8454ac43fae..db6b94dda5df 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -471,6 +471,7 @@ struct parser_exec_state { * used when ret from 2nd level batch buffer */ int saved_buf_addr_type; + bool is_ctx_wa; struct cmd_info *info; @@ -1715,6 +1716,11 @@ static int perform_bb_shadow(struct parser_exec_state *s) bb->accessing = true; bb->bb_start_cmd_va = s->ip_va; + if ((s->buf_type == BATCH_BUFFER_INSTRUCTION) && (!s->is_ctx_wa)) + bb->bb_offset = s->ip_va - s->rb_va; + else + bb->bb_offset = 0; + /* * ip_va saves the virtual address of the shadow batch buffer, while * ip_gma saves the graphics address of the original batch buffer. @@ -2571,6 +2577,7 @@ static int scan_workload(struct intel_vgpu_workload *workload) s.ring_tail = gma_tail; s.rb_va = workload->shadow_ring_buffer_va; s.workload = workload; + s.is_ctx_wa = false; if ((bypass_scan_mask & (1 << workload->ring_id)) || gma_head == gma_tail) @@ -2624,6 +2631,7 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) s.ring_tail = gma_tail; s.rb_va = wa_ctx->indirect_ctx.shadow_va; s.workload = workload; + s.is_ctx_wa = true; if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) { ret = -EINVAL; diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 256f1bb522b7..152df3d0291e 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -394,9 +394,11 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre, * performace for batch mmio read/write, so we need * handle forcewake mannually. */ + intel_runtime_pm_get(dev_priv); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); switch_mmio(pre, next, ring_id); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + intel_runtime_pm_put(dev_priv); } /** diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index b55b3580ca1d..d74d6f05c62c 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -52,6 +52,54 @@ static void set_context_pdp_root_pointer( pdp_pair[i].val = pdp[7 - i]; } +/* + * when populating shadow ctx from guest, we should not overrride oa related + * registers, so that they will not be overlapped by guest oa configs. Thus + * made it possible to capture oa data from host for both host and guests. + */ +static void sr_oa_regs(struct intel_vgpu_workload *workload, + u32 *reg_state, bool save) +{ + struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv; + u32 ctx_oactxctrl = dev_priv->perf.oa.ctx_oactxctrl_offset; + u32 ctx_flexeu0 = dev_priv->perf.oa.ctx_flexeu0_offset; + int i = 0; + u32 flex_mmio[] = { + i915_mmio_reg_offset(EU_PERF_CNTL0), + i915_mmio_reg_offset(EU_PERF_CNTL1), + i915_mmio_reg_offset(EU_PERF_CNTL2), + i915_mmio_reg_offset(EU_PERF_CNTL3), + i915_mmio_reg_offset(EU_PERF_CNTL4), + i915_mmio_reg_offset(EU_PERF_CNTL5), + i915_mmio_reg_offset(EU_PERF_CNTL6), + }; + + if (!workload || !reg_state || workload->ring_id != RCS) + return; + + if (save) { + workload->oactxctrl = reg_state[ctx_oactxctrl + 1]; + + for (i = 0; i < ARRAY_SIZE(workload->flex_mmio); i++) { + u32 state_offset = ctx_flexeu0 + i * 2; + + workload->flex_mmio[i] = reg_state[state_offset + 1]; + } + } else { + reg_state[ctx_oactxctrl] = + i915_mmio_reg_offset(GEN8_OACTXCONTROL); + reg_state[ctx_oactxctrl + 1] = workload->oactxctrl; + + for (i = 0; i < ARRAY_SIZE(workload->flex_mmio); i++) { + u32 state_offset = ctx_flexeu0 + i * 2; + u32 mmio = flex_mmio[i]; + + reg_state[state_offset] = mmio; + reg_state[state_offset + 1] = workload->flex_mmio[i]; + } + } +} + static int populate_shadow_context(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; @@ -98,6 +146,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload) page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN); shadow_ring_context = kmap(page); + sr_oa_regs(workload, (u32 *)shadow_ring_context, true); #define COPY_REG(name) \ intel_gvt_hypervisor_read_gpa(vgpu, workload->ring_context_gpa \ + RING_CTX_OFF(name.val), &shadow_ring_context->name.val, 4) @@ -122,6 +171,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload) sizeof(*shadow_ring_context), I915_GTT_PAGE_SIZE - sizeof(*shadow_ring_context)); + sr_oa_regs(workload, (u32 *)shadow_ring_context, false); kunmap(page); return 0; } @@ -376,6 +426,17 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) goto err; } + /* For privilge batch buffer and not wa_ctx, the bb_start_cmd_va + * is only updated into ring_scan_buffer, not real ring address + * allocated in later copy_workload_to_ring_buffer. pls be noted + * shadow_ring_buffer_va is now pointed to real ring buffer va + * in copy_workload_to_ring_buffer. + */ + + if (bb->bb_offset) + bb->bb_start_cmd_va = workload->shadow_ring_buffer_va + + bb->bb_offset; + /* relocate shadow batch buffer */ bb->bb_start_cmd_va[1] = i915_ggtt_offset(bb->vma); if (gmadr_bytes == 8) @@ -1044,10 +1105,12 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES); - s->workloads = kmem_cache_create("gvt-g_vgpu_workload", - sizeof(struct intel_vgpu_workload), 0, - SLAB_HWCACHE_ALIGN, - NULL); + s->workloads = kmem_cache_create_usercopy("gvt-g_vgpu_workload", + sizeof(struct intel_vgpu_workload), 0, + SLAB_HWCACHE_ALIGN, + offsetof(struct intel_vgpu_workload, rb_tail), + sizeof_field(struct intel_vgpu_workload, rb_tail), + NULL); if (!s->workloads) { ret = -ENOMEM; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index ff175a98b19e..a79a4f60637e 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -110,6 +110,10 @@ struct intel_vgpu_workload { /* shadow batch buffer */ struct list_head shadow_bb; struct intel_shadow_wa_ctx wa_ctx; + + /* oa registers */ + u32 oactxctrl; + u32 flex_mmio[7]; }; struct intel_vgpu_shadow_bb { @@ -120,6 +124,7 @@ struct intel_vgpu_shadow_bb { u32 *bb_start_cmd_va; unsigned int clflush; bool accessing; + unsigned long bb_offset; }; #define workload_q_head(vgpu, ring_id) \ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index dd89abd2263d..6ff5d655c202 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -434,20 +434,28 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, dma_fence_put(shared[i]); kfree(shared); + /* + * If both shared fences and an exclusive fence exist, + * then by construction the shared fences must be later + * than the exclusive fence. If we successfully wait for + * all the shared fences, we know that the exclusive fence + * must all be signaled. If all the shared fences are + * signaled, we can prune the array and recover the + * floating references on the fences/requests. + */ prune_fences = count && timeout >= 0; } else { excl = reservation_object_get_excl_rcu(resv); } - if (excl && timeout >= 0) { + if (excl && timeout >= 0) timeout = i915_gem_object_wait_fence(excl, flags, timeout, rps_client); - prune_fences = timeout >= 0; - } dma_fence_put(excl); - /* Oportunistically prune the fences iff we know they have *all* been + /* + * Opportunistically prune the fences iff we know they have *all* been * signaled and that the reservation object has not been changed (i.e. * no new fences have been added). */ @@ -3205,8 +3213,10 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) * rolling the global seqno forward (since this would complete requests * for which we haven't set the fence error to EIO yet). */ - for_each_engine(engine, i915, id) + for_each_engine(engine, i915, id) { + i915_gem_reset_prepare_engine(engine); engine->submit_request = nop_submit_request; + } /* * Make sure no one is running the old callback before we proceed with @@ -3244,6 +3254,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) intel_engine_init_global_seqno(engine, intel_engine_last_submit(engine)); spin_unlock_irqrestore(&engine->timeline->lock, flags); + + i915_gem_reset_finish_engine(engine); } set_bit(I915_WEDGED, &i915->gpu_error.flags); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 4401068ff468..3ab1ace2a6bd 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -505,6 +505,8 @@ eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma) list_add_tail(&vma->exec_link, &eb->unbound); if (drm_mm_node_allocated(&vma->node)) err = i915_vma_unbind(vma); + if (unlikely(err)) + vma->exec_flags = NULL; } return err; } @@ -2410,7 +2412,7 @@ err_request: if (out_fence) { if (err == 0) { fd_install(out_fence_fd, out_fence->file); - args->rsvd2 &= GENMASK_ULL(0, 31); /* keep in-fence */ + args->rsvd2 &= GENMASK_ULL(31, 0); /* keep in-fence */ args->rsvd2 |= (u64)out_fence_fd << 32; out_fence_fd = -1; } else { diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index e09d18df8b7f..a3e93d46316a 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -476,8 +476,6 @@ void __i915_gem_request_submit(struct drm_i915_gem_request *request) GEM_BUG_ON(!irqs_disabled()); lockdep_assert_held(&engine->timeline->lock); - trace_i915_gem_request_execute(request); - /* Transfer from per-context onto the global per-engine timeline */ timeline = engine->timeline; GEM_BUG_ON(timeline == request->timeline); @@ -501,6 +499,8 @@ void __i915_gem_request_submit(struct drm_i915_gem_request *request) list_move_tail(&request->link, &timeline->requests); spin_unlock(&request->timeline->lock); + trace_i915_gem_request_execute(request); + wake_up_all(&request->execute); } diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0be50e43507d..f8fe5ffcdcff 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1303,9 +1303,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) */ mutex_lock(&dev_priv->drm.struct_mutex); dev_priv->perf.oa.exclusive_stream = NULL; - mutex_unlock(&dev_priv->drm.struct_mutex); - dev_priv->perf.oa.ops.disable_metric_set(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); free_oa_buffer(dev_priv); @@ -1756,22 +1755,13 @@ static int gen8_switch_to_updated_kernel_context(struct drm_i915_private *dev_pr * Note: it's only the RCS/Render context that has any OA state. */ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, - const struct i915_oa_config *oa_config, - bool interruptible) + const struct i915_oa_config *oa_config) { struct i915_gem_context *ctx; int ret; unsigned int wait_flags = I915_WAIT_LOCKED; - if (interruptible) { - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - return ret; - - wait_flags |= I915_WAIT_INTERRUPTIBLE; - } else { - mutex_lock(&dev_priv->drm.struct_mutex); - } + lockdep_assert_held(&dev_priv->drm.struct_mutex); /* Switch away from any user context. */ ret = gen8_switch_to_updated_kernel_context(dev_priv, oa_config); @@ -1819,8 +1809,6 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, } out: - mutex_unlock(&dev_priv->drm.struct_mutex); - return ret; } @@ -1863,7 +1851,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv, * to make sure all slices/subslices are ON before writing to NOA * registers. */ - ret = gen8_configure_all_contexts(dev_priv, oa_config, true); + ret = gen8_configure_all_contexts(dev_priv, oa_config); if (ret) return ret; @@ -1878,7 +1866,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv, static void gen8_disable_metric_set(struct drm_i915_private *dev_priv) { /* Reset all contexts' slices/subslices configurations. */ - gen8_configure_all_contexts(dev_priv, NULL, false); + gen8_configure_all_contexts(dev_priv, NULL); I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) & ~GT_NOA_ENABLE)); @@ -1888,7 +1876,7 @@ static void gen8_disable_metric_set(struct drm_i915_private *dev_priv) static void gen10_disable_metric_set(struct drm_i915_private *dev_priv) { /* Reset all contexts' slices/subslices configurations. */ - gen8_configure_all_contexts(dev_priv, NULL, false); + gen8_configure_all_contexts(dev_priv, NULL); /* Make sure we disable noa to save power. */ I915_WRITE(RPM_CONFIG1, @@ -2138,6 +2126,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, if (ret) goto err_oa_buf_alloc; + ret = i915_mutex_lock_interruptible(&dev_priv->drm); + if (ret) + goto err_lock; + ret = dev_priv->perf.oa.ops.enable_metric_set(dev_priv, stream->oa_config); if (ret) @@ -2145,23 +2137,17 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; - /* Lock device for exclusive_stream access late because - * enable_metric_set() might lock as well on gen8+. - */ - ret = i915_mutex_lock_interruptible(&dev_priv->drm); - if (ret) - goto err_lock; - dev_priv->perf.oa.exclusive_stream = stream; mutex_unlock(&dev_priv->drm.struct_mutex); return 0; -err_lock: +err_enable: dev_priv->perf.oa.ops.disable_metric_set(dev_priv); + mutex_unlock(&dev_priv->drm.struct_mutex); -err_enable: +err_lock: free_oa_buffer(dev_priv); err_oa_buf_alloc: diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index a2108e35c599..33eb0c5b1d32 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2027,7 +2027,7 @@ enum i915_power_well_id { #define _CNL_PORT_TX_DW5_LN0_AE 0x162454 #define _CNL_PORT_TX_DW5_LN0_B 0x162654 #define _CNL_PORT_TX_DW5_LN0_C 0x162C54 -#define _CNL_PORT_TX_DW5_LN0_D 0x162ED4 +#define _CNL_PORT_TX_DW5_LN0_D 0x162E54 #define _CNL_PORT_TX_DW5_LN0_F 0x162854 #define CNL_PORT_TX_DW5_GRP(port) _MMIO_PORT6(port, \ _CNL_PORT_TX_DW5_GRP_AE, \ @@ -2058,7 +2058,7 @@ enum i915_power_well_id { #define _CNL_PORT_TX_DW7_LN0_AE 0x16245C #define _CNL_PORT_TX_DW7_LN0_B 0x16265C #define _CNL_PORT_TX_DW7_LN0_C 0x162C5C -#define _CNL_PORT_TX_DW7_LN0_D 0x162EDC +#define _CNL_PORT_TX_DW7_LN0_D 0x162E5C #define _CNL_PORT_TX_DW7_LN0_F 0x16285C #define CNL_PORT_TX_DW7_GRP(port) _MMIO_PORT6(port, \ _CNL_PORT_TX_DW7_GRP_AE, \ diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index b33d2158c234..e5e6f6bb2b05 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -304,8 +304,9 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev, { struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); struct intel_rps *rps = &dev_priv->gt_pm.rps; - u32 val; + bool boost = false; ssize_t ret; + u32 val; ret = kstrtou32(buf, 0, &val); if (ret) @@ -317,8 +318,13 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev, return -EINVAL; mutex_lock(&dev_priv->pcu_lock); - rps->boost_freq = val; + if (val != rps->boost_freq) { + rps->boost_freq = val; + boost = atomic_read(&rps->num_waiters); + } mutex_unlock(&dev_priv->pcu_lock); + if (boost) + schedule_work(&rps->work); return count; } diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 522d54fecb53..4a01f62a392d 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -779,11 +779,11 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, { struct intel_encoder *encoder; - if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map))) - return NULL; - /* MST */ if (pipe >= 0) { + if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map))) + return NULL; + encoder = dev_priv->av_enc_map[pipe]; /* * when bootup, audio driver may not know it is diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f51645a08dca..6aff9d096e13 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -2175,8 +2175,7 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, intel_prepare_dp_ddi_buffers(encoder, crtc_state); intel_ddi_init_dp_buf_reg(encoder); - if (!is_mst) - intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); + intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); intel_dp_start_link_train(intel_dp); if (port != PORT_A || INTEL_GEN(dev_priv) >= 9) intel_dp_stop_link_train(intel_dp); @@ -2274,14 +2273,12 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base); struct intel_dp *intel_dp = &dig_port->dp; - bool is_mst = intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST); /* * Power down sink before disabling the port, otherwise we end * up getting interrupts from the sink on detecting link loss. */ - if (!is_mst) - intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); + intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); intel_disable_ddi_buf(encoder); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 35c5299feab6..a29868cd30c7 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -620,19 +620,15 @@ static int bxt_power_sequencer_idx(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp)); + int backlight_controller = dev_priv->vbt.backlight.controller; lockdep_assert_held(&dev_priv->pps_mutex); /* We should never land here with regular DP ports */ WARN_ON(!intel_dp_is_edp(intel_dp)); - /* - * TODO: BXT has 2 PPS instances. The correct port->PPS instance - * mapping needs to be retrieved from VBT, for now just hard-code to - * use instance #0 always. - */ if (!intel_dp->pps_reset) - return 0; + return backlight_controller; intel_dp->pps_reset = false; @@ -642,7 +638,7 @@ bxt_power_sequencer_idx(struct intel_dp *intel_dp) */ intel_dp_init_panel_power_sequencer_registers(intel_dp, false); - return 0; + return backlight_controller; } typedef bool (*vlv_pipe_check)(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c index 348a4f7ffb67..53747318f4a7 100644 --- a/drivers/gpu/drm/i915/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/intel_hangcheck.c @@ -246,7 +246,7 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd) */ tmp = I915_READ_CTL(engine); if (tmp & RING_WAIT) { - i915_handle_error(dev_priv, 0, + i915_handle_error(dev_priv, BIT(engine->id), "Kicking stuck wait on %s", engine->name); I915_WRITE_CTL(engine, tmp); @@ -258,7 +258,7 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd) default: return ENGINE_DEAD; case 1: - i915_handle_error(dev_priv, 0, + i915_handle_error(dev_priv, ALL_ENGINES, "Kicking stuck semaphore on %s", engine->name); I915_WRITE_CTL(engine, tmp); diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 7ece2f061b9e..e0fca035ff78 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -719,6 +719,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) struct rb_node *rb; unsigned long flags; + GEM_TRACE("%s\n", engine->name); + spin_lock_irqsave(&engine->timeline->lock, flags); /* Cancel the requests on the HW and clear the ELSP tracker. */ @@ -765,6 +767,9 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) */ clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); + /* Mark all CS interrupts as complete */ + execlists->active = 0; + spin_unlock_irqrestore(&engine->timeline->lock, flags); } diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index 9a9961802f5c..e83af0f2be86 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -225,7 +225,11 @@ static void ipu_crtc_atomic_begin(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) { drm_crtc_vblank_on(crtc); +} +static void ipu_crtc_atomic_flush(struct drm_crtc *crtc, + struct drm_crtc_state *old_crtc_state) +{ spin_lock_irq(&crtc->dev->event_lock); if (crtc->state->event) { WARN_ON(drm_crtc_vblank_get(crtc)); @@ -293,6 +297,7 @@ static const struct drm_crtc_helper_funcs ipu_helper_funcs = { .mode_set_nofb = ipu_crtc_mode_set_nofb, .atomic_check = ipu_crtc_atomic_check, .atomic_begin = ipu_crtc_atomic_begin, + .atomic_flush = ipu_crtc_atomic_flush, .atomic_disable = ipu_crtc_atomic_disable, .atomic_enable = ipu_crtc_atomic_enable, }; diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 57ed56d8623f..d9113faaa62f 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -22,6 +22,7 @@ #include <drm/drm_plane_helper.h> #include "video/imx-ipu-v3.h" +#include "imx-drm.h" #include "ipuv3-plane.h" struct ipu_plane_state { @@ -272,7 +273,7 @@ static void ipu_plane_destroy(struct drm_plane *plane) kfree(ipu_plane); } -void ipu_plane_state_reset(struct drm_plane *plane) +static void ipu_plane_state_reset(struct drm_plane *plane) { struct ipu_plane_state *ipu_state; @@ -292,7 +293,8 @@ void ipu_plane_state_reset(struct drm_plane *plane) plane->state = &ipu_state->base; } -struct drm_plane_state *ipu_plane_duplicate_state(struct drm_plane *plane) +static struct drm_plane_state * +ipu_plane_duplicate_state(struct drm_plane *plane) { struct ipu_plane_state *state; @@ -306,8 +308,8 @@ struct drm_plane_state *ipu_plane_duplicate_state(struct drm_plane *plane) return &state->base; } -void ipu_plane_destroy_state(struct drm_plane *plane, - struct drm_plane_state *state) +static void ipu_plane_destroy_state(struct drm_plane *plane, + struct drm_plane_state *state) { struct ipu_plane_state *ipu_state = to_ipu_plane_state(state); diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index 380f340204e8..debbbf0fd4bd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -134,7 +134,7 @@ nv50_get_intensity(struct backlight_device *bd) struct nouveau_encoder *nv_encoder = bl_get_data(bd); struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev); struct nvif_object *device = &drm->client.device.object; - int or = nv_encoder->or; + int or = ffs(nv_encoder->dcb->or) - 1; u32 div = 1025; u32 val; @@ -149,7 +149,7 @@ nv50_set_intensity(struct backlight_device *bd) struct nouveau_encoder *nv_encoder = bl_get_data(bd); struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev); struct nvif_object *device = &drm->client.device.object; - int or = nv_encoder->or; + int or = ffs(nv_encoder->dcb->or) - 1; u32 div = 1025; u32 val = (bd->props.brightness * div) / 100; @@ -170,7 +170,7 @@ nva3_get_intensity(struct backlight_device *bd) struct nouveau_encoder *nv_encoder = bl_get_data(bd); struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev); struct nvif_object *device = &drm->client.device.object; - int or = nv_encoder->or; + int or = ffs(nv_encoder->dcb->or) - 1; u32 div, val; div = nvif_rd32(device, NV50_PDISP_SOR_PWM_DIV(or)); @@ -188,7 +188,7 @@ nva3_set_intensity(struct backlight_device *bd) struct nouveau_encoder *nv_encoder = bl_get_data(bd); struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev); struct nvif_object *device = &drm->client.device.object; - int or = nv_encoder->or; + int or = ffs(nv_encoder->dcb->or) - 1; u32 div, val; div = nvif_rd32(device, NV50_PDISP_SOR_PWM_DIV(or)); @@ -228,7 +228,7 @@ nv50_backlight_init(struct drm_connector *connector) return -ENODEV; } - if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(nv_encoder->or))) + if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1))) return 0; if (drm->client.device.info.chipset <= 0xa0 || @@ -268,13 +268,13 @@ nouveau_backlight_init(struct drm_device *dev) struct nvif_device *device = &drm->client.device; struct drm_connector *connector; + INIT_LIST_HEAD(&drm->bl_connectors); + if (apple_gmux_present()) { NV_INFO(drm, "Apple GMUX detected: not registering Nouveau backlight interface\n"); return 0; } - INIT_LIST_HEAD(&drm->bl_connectors); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) { if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS && connector->connector_type != DRM_MODE_CONNECTOR_eDP) diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index dd8d4352ed99..caddce88d2d8 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -4477,6 +4477,7 @@ nv50_display_create(struct drm_device *dev) nouveau_display(dev)->fini = nv50_display_fini; disp->disp = &nouveau_display(dev)->disp; dev->mode_config.funcs = &nv50_disp_func; + dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP; if (nouveau_atomic) dev->driver->driver_features |= DRIVER_ATOMIC; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index 93946dcee319..1c12e58f44c2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -1354,7 +1354,7 @@ nvkm_vmm_get_locked(struct nvkm_vmm *vmm, bool getref, bool mapref, bool sparse, tail = this->addr + this->size; if (vmm->func->page_block && next && next->page != p) - tail = ALIGN_DOWN(addr, vmm->func->page_block); + tail = ALIGN_DOWN(tail, vmm->func->page_block); if (addr <= tail && tail - addr >= size) { rb_erase(&this->tree, &vmm->free); diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index d3045a371a55..7c73bc7e2f85 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3221,35 +3221,8 @@ static void cik_gpu_init(struct radeon_device *rdev) case CHIP_KAVERI: rdev->config.cik.max_shader_engines = 1; rdev->config.cik.max_tile_pipes = 4; - if ((rdev->pdev->device == 0x1304) || - (rdev->pdev->device == 0x1305) || - (rdev->pdev->device == 0x130C) || - (rdev->pdev->device == 0x130F) || - (rdev->pdev->device == 0x1310) || - (rdev->pdev->device == 0x1311) || - (rdev->pdev->device == 0x131C)) { - rdev->config.cik.max_cu_per_sh = 8; - rdev->config.cik.max_backends_per_se = 2; - } else if ((rdev->pdev->device == 0x1309) || - (rdev->pdev->device == 0x130A) || - (rdev->pdev->device == 0x130D) || - (rdev->pdev->device == 0x1313) || - (rdev->pdev->device == 0x131D)) { - rdev->config.cik.max_cu_per_sh = 6; - rdev->config.cik.max_backends_per_se = 2; - } else if ((rdev->pdev->device == 0x1306) || - (rdev->pdev->device == 0x1307) || - (rdev->pdev->device == 0x130B) || - (rdev->pdev->device == 0x130E) || - (rdev->pdev->device == 0x1315) || - (rdev->pdev->device == 0x1318) || - (rdev->pdev->device == 0x131B)) { - rdev->config.cik.max_cu_per_sh = 4; - rdev->config.cik.max_backends_per_se = 1; - } else { - rdev->config.cik.max_cu_per_sh = 3; - rdev->config.cik.max_backends_per_se = 1; - } + rdev->config.cik.max_cu_per_sh = 8; + rdev->config.cik.max_backends_per_se = 2; rdev->config.cik.max_sh_per_se = 1; rdev->config.cik.max_texture_channel_caches = 4; rdev->config.cik.max_gprs = 256; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 2e2ca3c6b47d..df9469a8fdb1 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -90,25 +90,18 @@ void radeon_connector_hotplug(struct drm_connector *connector) /* don't do anything if sink is not display port, i.e., * passive dp->(dvi|hdmi) adaptor */ - if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) { - int saved_dpms = connector->dpms; - /* Only turn off the display if it's physically disconnected */ - if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd)) { - drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); - } else if (radeon_dp_needs_link_train(radeon_connector)) { - /* Don't try to start link training before we - * have the dpcd */ - if (!radeon_dp_getdpcd(radeon_connector)) - return; - - /* set it to OFF so that drm_helper_connector_dpms() - * won't return immediately since the current state - * is ON at this point. - */ - connector->dpms = DRM_MODE_DPMS_OFF; - drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); - } - connector->dpms = saved_dpms; + if (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT && + radeon_hpd_sense(rdev, radeon_connector->hpd.hpd) && + radeon_dp_needs_link_train(radeon_connector)) { + /* Don't start link training before we have the DPCD */ + if (!radeon_dp_getdpcd(radeon_connector)) + return; + + /* Turn the connector off and back on immediately, which + * will trigger link training + */ + drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF); + drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON); } } } diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 8d3e3d2e0090..7828a5e10629 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1365,6 +1365,10 @@ int radeon_device_init(struct radeon_device *rdev, if ((rdev->flags & RADEON_IS_PCI) && (rdev->family <= CHIP_RS740)) rdev->need_dma32 = true; +#ifdef CONFIG_PPC64 + if (rdev->family == CHIP_CEDAR) + rdev->need_dma32 = true; +#endif dma_bits = rdev->need_dma32 ? 32 : 40; r = pci_set_dma_mask(rdev->pdev, DMA_BIT_MASK(dma_bits)); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index a9962ffba720..27d8e7dd2d06 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -34,8 +34,6 @@ void radeon_gem_object_free(struct drm_gem_object *gobj) struct radeon_bo *robj = gem_to_radeon_bo(gobj); if (robj) { - if (robj->gem_base.import_attach) - drm_prime_gem_destroy(&robj->gem_base, robj->tbo.sg); radeon_mn_unregister(robj); radeon_bo_unref(&robj); } diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 15404af9d740..31f5ad605e59 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -82,6 +82,8 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo) mutex_unlock(&bo->rdev->gem.mutex); radeon_bo_clear_surface_reg(bo); WARN_ON_ONCE(!list_empty(&bo->va)); + if (bo->gem_base.import_attach) + drm_prime_gem_destroy(&bo->gem_base, bo->tbo.sg); drm_gem_object_release(&bo->gem_base); kfree(bo); } diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 326ad068c15a..4b6542538ff9 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -47,7 +47,6 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev); static bool radeon_pm_debug_check_in_vbl(struct radeon_device *rdev, bool finish); static void radeon_pm_update_profile(struct radeon_device *rdev); static void radeon_pm_set_clocks(struct radeon_device *rdev); -static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev); int radeon_pm_get_type_index(struct radeon_device *rdev, enum radeon_pm_state_type ps_type, @@ -80,8 +79,6 @@ void radeon_pm_acpi_event_handler(struct radeon_device *rdev) radeon_dpm_enable_bapm(rdev, rdev->pm.dpm.ac_power); } mutex_unlock(&rdev->pm.mutex); - /* allow new DPM state to be picked */ - radeon_pm_compute_clocks_dpm(rdev); } else if (rdev->pm.pm_method == PM_METHOD_PROFILE) { if (rdev->pm.profile == PM_PROFILE_AUTO) { mutex_lock(&rdev->pm.mutex); @@ -885,8 +882,7 @@ static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev, dpm_state = POWER_STATE_TYPE_INTERNAL_3DPERF; /* balanced states don't exist at the moment */ if (dpm_state == POWER_STATE_TYPE_BALANCED) - dpm_state = rdev->pm.dpm.ac_power ? - POWER_STATE_TYPE_PERFORMANCE : POWER_STATE_TYPE_BATTERY; + dpm_state = POWER_STATE_TYPE_PERFORMANCE; restart_search: /* Pick the best power state based on current conditions */ diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c index 5decae0069d0..78cbc3145e44 100644 --- a/drivers/gpu/drm/sun4i/sun4i_crtc.c +++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c @@ -93,6 +93,8 @@ static void sun4i_crtc_atomic_disable(struct drm_crtc *crtc, DRM_DEBUG_DRIVER("Disabling the CRTC\n"); + drm_crtc_vblank_off(crtc); + sun4i_tcon_set_status(scrtc->tcon, encoder, false); if (crtc->state->event && !crtc->state->active) { @@ -113,6 +115,8 @@ static void sun4i_crtc_atomic_enable(struct drm_crtc *crtc, DRM_DEBUG_DRIVER("Enabling the CRTC\n"); sun4i_tcon_set_status(scrtc->tcon, encoder, true); + + drm_crtc_vblank_on(crtc); } static void sun4i_crtc_mode_set_nofb(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/sun4i/sun4i_dotclock.c b/drivers/gpu/drm/sun4i/sun4i_dotclock.c index 023f39bda633..e36004fbe453 100644 --- a/drivers/gpu/drm/sun4i/sun4i_dotclock.c +++ b/drivers/gpu/drm/sun4i/sun4i_dotclock.c @@ -132,10 +132,13 @@ static int sun4i_dclk_get_phase(struct clk_hw *hw) static int sun4i_dclk_set_phase(struct clk_hw *hw, int degrees) { struct sun4i_dclk *dclk = hw_to_dclk(hw); + u32 val = degrees / 120; + + val <<= 28; regmap_update_bits(dclk->regmap, SUN4I_TCON0_IO_POL_REG, GENMASK(29, 28), - degrees / 120); + val); return 0; } diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 4570da0227b4..d9a71f361b14 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -111,7 +111,7 @@ static int sun4i_drv_bind(struct device *dev) /* drm_vblank_init calls kcalloc, which can fail */ ret = drm_vblank_init(drm, drm->mode_config.num_crtc); if (ret) - goto free_mem_region; + goto cleanup_mode_config; drm->irq_enabled = true; @@ -139,7 +139,6 @@ finish_poll: sun4i_framebuffer_free(drm); cleanup_mode_config: drm_mode_config_cleanup(drm); -free_mem_region: of_reserved_mem_device_release(dev); free_drm: drm_dev_unref(drm); diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index 500b6fb3e028..fa4bcd092eaf 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -538,7 +538,8 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, &sun4i_hdmi_regmap_config); if (IS_ERR(hdmi->regmap)) { dev_err(dev, "Couldn't create HDMI encoder regmap\n"); - return PTR_ERR(hdmi->regmap); + ret = PTR_ERR(hdmi->regmap); + goto err_disable_mod_clk; } ret = sun4i_tmds_create(hdmi); @@ -551,7 +552,8 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, hdmi->ddc_parent_clk = devm_clk_get(dev, "ddc"); if (IS_ERR(hdmi->ddc_parent_clk)) { dev_err(dev, "Couldn't get the HDMI DDC clock\n"); - return PTR_ERR(hdmi->ddc_parent_clk); + ret = PTR_ERR(hdmi->ddc_parent_clk); + goto err_disable_mod_clk; } } else { hdmi->ddc_parent_clk = hdmi->tmds_clk; diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index 832f8f9bc47f..b8da5a50a61d 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -92,6 +92,8 @@ static int sun4i_rgb_mode_valid(struct drm_connector *connector, DRM_DEBUG_DRIVER("Vertical parameters OK\n"); + tcon->dclk_min_div = 6; + tcon->dclk_max_div = 127; rounded_rate = clk_round_rate(tcon->dclk, rate); if (rounded_rate < rate) return MODE_CLOCK_LOW; diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 3c15cf24b503..a818ca491605 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -101,10 +101,13 @@ static void sun4i_tcon_channel_set_status(struct sun4i_tcon *tcon, int channel, return; } - if (enabled) + if (enabled) { clk_prepare_enable(clk); - else + clk_rate_exclusive_get(clk); + } else { + clk_rate_exclusive_put(clk); clk_disable_unprepare(clk); + } } static void sun4i_tcon_lvds_set_status(struct sun4i_tcon *tcon, @@ -335,6 +338,9 @@ static void sun4i_tcon0_mode_set_lvds(struct sun4i_tcon *tcon, regmap_update_bits(tcon->regs, SUN4I_TCON_GCTL_REG, SUN4I_TCON_GCTL_IOMAP_MASK, SUN4I_TCON_GCTL_IOMAP_TCON0); + + /* Enable the output on the pins */ + regmap_write(tcon->regs, SUN4I_TCON0_IO_TRI_REG, 0xe0000000); } static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, @@ -870,52 +876,56 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master, return ret; } - /* - * This can only be made optional since we've had DT nodes - * without the LVDS reset properties. - * - * If the property is missing, just disable LVDS, and print a - * warning. - */ - tcon->lvds_rst = devm_reset_control_get_optional(dev, "lvds"); - if (IS_ERR(tcon->lvds_rst)) { - dev_err(dev, "Couldn't get our reset line\n"); - return PTR_ERR(tcon->lvds_rst); - } else if (tcon->lvds_rst) { - has_lvds_rst = true; - reset_control_reset(tcon->lvds_rst); - } else { - has_lvds_rst = false; - } + if (tcon->quirks->supports_lvds) { + /* + * This can only be made optional since we've had DT + * nodes without the LVDS reset properties. + * + * If the property is missing, just disable LVDS, and + * print a warning. + */ + tcon->lvds_rst = devm_reset_control_get_optional(dev, "lvds"); + if (IS_ERR(tcon->lvds_rst)) { + dev_err(dev, "Couldn't get our reset line\n"); + return PTR_ERR(tcon->lvds_rst); + } else if (tcon->lvds_rst) { + has_lvds_rst = true; + reset_control_reset(tcon->lvds_rst); + } else { + has_lvds_rst = false; + } - /* - * This can only be made optional since we've had DT nodes - * without the LVDS reset properties. - * - * If the property is missing, just disable LVDS, and print a - * warning. - */ - if (tcon->quirks->has_lvds_alt) { - tcon->lvds_pll = devm_clk_get(dev, "lvds-alt"); - if (IS_ERR(tcon->lvds_pll)) { - if (PTR_ERR(tcon->lvds_pll) == -ENOENT) { - has_lvds_alt = false; + /* + * This can only be made optional since we've had DT + * nodes without the LVDS reset properties. + * + * If the property is missing, just disable LVDS, and + * print a warning. + */ + if (tcon->quirks->has_lvds_alt) { + tcon->lvds_pll = devm_clk_get(dev, "lvds-alt"); + if (IS_ERR(tcon->lvds_pll)) { + if (PTR_ERR(tcon->lvds_pll) == -ENOENT) { + has_lvds_alt = false; + } else { + dev_err(dev, "Couldn't get the LVDS PLL\n"); + return PTR_ERR(tcon->lvds_pll); + } } else { - dev_err(dev, "Couldn't get the LVDS PLL\n"); - return PTR_ERR(tcon->lvds_pll); + has_lvds_alt = true; } - } else { - has_lvds_alt = true; } - } - if (!has_lvds_rst || (tcon->quirks->has_lvds_alt && !has_lvds_alt)) { - dev_warn(dev, - "Missing LVDS properties, Please upgrade your DT\n"); - dev_warn(dev, "LVDS output disabled\n"); - can_lvds = false; + if (!has_lvds_rst || + (tcon->quirks->has_lvds_alt && !has_lvds_alt)) { + dev_warn(dev, "Missing LVDS properties, Please upgrade your DT\n"); + dev_warn(dev, "LVDS output disabled\n"); + can_lvds = false; + } else { + can_lvds = true; + } } else { - can_lvds = true; + can_lvds = false; } ret = sun4i_tcon_init_clocks(dev, tcon); @@ -1134,7 +1144,7 @@ static const struct sun4i_tcon_quirks sun8i_a33_quirks = { }; static const struct sun4i_tcon_quirks sun8i_a83t_lcd_quirks = { - /* nothing is supported */ + .supports_lvds = true, }; static const struct sun4i_tcon_quirks sun8i_v3s_quirks = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h index b761c7b823c5..278700c7bf9f 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.h +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h @@ -175,6 +175,7 @@ struct sun4i_tcon_quirks { bool has_channel_1; /* a33 does not have channel 1 */ bool has_lvds_alt; /* Does the LVDS clock have a parent other than the TCON clock? */ bool needs_de_be_mux; /* sun6i needs mux to select backend */ + bool supports_lvds; /* Does the TCON support an LVDS output? */ /* callback to handle tcon muxing options */ int (*set_mux)(struct sun4i_tcon *, const struct drm_encoder *); diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index b8403ed48285..fbffe1948b3b 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -1903,8 +1903,12 @@ cleanup: if (!IS_ERR(primary)) drm_plane_cleanup(primary); - if (group && tegra->domain) { - iommu_detach_group(tegra->domain, group); + if (group && dc->domain) { + if (group == tegra->group) { + iommu_detach_group(dc->domain, group); + tegra->group = NULL; + } + dc->domain = NULL; } @@ -1913,8 +1917,10 @@ cleanup: static int tegra_dc_exit(struct host1x_client *client) { + struct drm_device *drm = dev_get_drvdata(client->parent); struct iommu_group *group = iommu_group_get(client->dev); struct tegra_dc *dc = host1x_client_to_dc(client); + struct tegra_drm *tegra = drm->dev_private; int err; devm_free_irq(dc->dev, dc->irq, dc); @@ -1926,7 +1932,11 @@ static int tegra_dc_exit(struct host1x_client *client) } if (group && dc->domain) { - iommu_detach_group(dc->domain, group); + if (group == tegra->group) { + iommu_detach_group(dc->domain, group); + tegra->group = NULL; + } + dc->domain = NULL; } diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index d50bddb2e447..7fcf4a242840 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -250,6 +250,7 @@ static void tegra_drm_unload(struct drm_device *drm) drm_kms_helper_poll_fini(drm); tegra_drm_fb_exit(drm); + drm_atomic_helper_shutdown(drm); drm_mode_config_cleanup(drm); err = host1x_device_exit(device); diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 4d2ed966f9e3..87c5d89bc9ba 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -1072,7 +1072,6 @@ static int tegra_dsi_exit(struct host1x_client *client) struct tegra_dsi *dsi = host1x_client_to_dsi(client); tegra_output_exit(&dsi->output); - regulator_disable(dsi->vdd); return 0; } diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 36a06a993698..94dac79ac3c9 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -297,6 +297,10 @@ int tegra_plane_format_get_alpha(unsigned int opaque, unsigned int *alpha) case WIN_COLOR_DEPTH_B8G8R8X8: *alpha = WIN_COLOR_DEPTH_B8G8R8A8; return 0; + + case WIN_COLOR_DEPTH_B5G6R5: + *alpha = opaque; + return 0; } return -EINVAL; @@ -330,9 +334,6 @@ void tegra_plane_check_dependent(struct tegra_plane *tegra, unsigned int zpos[2]; unsigned int i; - for (i = 0; i < 3; i++) - state->dependent[i] = false; - for (i = 0; i < 2; i++) zpos[i] = 0; @@ -346,6 +347,8 @@ void tegra_plane_check_dependent(struct tegra_plane *tegra, index = tegra_plane_get_overlap_index(tegra, p); + state->dependent[index] = false; + /* * If any of the other planes is on top of this plane and uses * a format with an alpha component, mark this plane as being diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index b5b335c9b2bb..2ebdc6d5a76e 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -159,10 +159,15 @@ static int udl_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) { unsigned long start = vma->vm_start; unsigned long size = vma->vm_end - vma->vm_start; - unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + unsigned long offset; unsigned long page, pos; - if (offset + size > info->fix.smem_len) + if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) + return -EINVAL; + + offset = vma->vm_pgoff << PAGE_SHIFT; + + if (offset > info->fix.smem_len || size > info->fix.smem_len - offset) return -EINVAL; pos = (unsigned long)info->fix.smem_start + offset; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 5720a0d4ac0a..677ac16c8a6d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -197,6 +197,9 @@ static int virtio_gpu_getparam_ioctl(struct drm_device *dev, void *data, case VIRTGPU_PARAM_3D_FEATURES: value = vgdev->has_virgl_3d == true ? 1 : 0; break; + case VIRTGPU_PARAM_CAPSET_QUERY_FIX: + value = 1; + break; default: return -EINVAL; } @@ -472,7 +475,7 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, { struct virtio_gpu_device *vgdev = dev->dev_private; struct drm_virtgpu_get_caps *args = data; - int size; + unsigned size, host_caps_size; int i; int found_valid = -1; int ret; @@ -481,6 +484,10 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, if (vgdev->num_capsets == 0) return -ENOSYS; + /* don't allow userspace to pass 0 */ + if (args->size == 0) + return -EINVAL; + spin_lock(&vgdev->display_info_lock); for (i = 0; i < vgdev->num_capsets; i++) { if (vgdev->capsets[i].id == args->cap_set_id) { @@ -496,11 +503,9 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, return -EINVAL; } - size = vgdev->capsets[found_valid].max_size; - if (args->size > size) { - spin_unlock(&vgdev->display_info_lock); - return -EINVAL; - } + host_caps_size = vgdev->capsets[found_valid].max_size; + /* only copy to user the minimum of the host caps size or the guest caps size */ + size = min(args->size, host_caps_size); list_for_each_entry(cache_ent, &vgdev->cap_cache, head) { if (cache_ent->id == args->cap_set_id && diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 184340d486c3..86d25f18aa99 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1337,6 +1337,19 @@ static void __vmw_svga_disable(struct vmw_private *dev_priv) */ void vmw_svga_disable(struct vmw_private *dev_priv) { + /* + * Disabling SVGA will turn off device modesetting capabilities, so + * notify KMS about that so that it doesn't cache atomic state that + * isn't valid anymore, for example crtcs turned on. + * Strictly we'd want to do this under the SVGA lock (or an SVGA mutex), + * but vmw_kms_lost_device() takes the reservation sem and thus we'll + * end up with lock order reversal. Thus, a master may actually perform + * a new modeset just after we call vmw_kms_lost_device() and race with + * vmw_svga_disable(), but that should at worst cause atomic KMS state + * to be inconsistent with the device, causing modesetting problems. + * + */ + vmw_kms_lost_device(dev_priv->dev); ttm_write_lock(&dev_priv->reservation_sem, false); spin_lock(&dev_priv->svga_lock); if (dev_priv->bdev.man[TTM_PL_VRAM].use_type) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index d08753e8fd94..9116fe8baebc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -938,6 +938,7 @@ int vmw_kms_present(struct vmw_private *dev_priv, int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); void vmw_kms_legacy_hotspot_clear(struct vmw_private *dev_priv); +void vmw_kms_lost_device(struct drm_device *dev); int vmw_dumb_create(struct drm_file *file_priv, struct drm_device *dev, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index ead61015cd79..3c824fd7cbf3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -31,7 +31,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_rect.h> - /* Might need a hrtimer here? */ #define VMWGFX_PRESENT_RATE ((HZ / 60 > 0) ? HZ / 60 : 1) @@ -2517,9 +2516,12 @@ void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv, * Helper to be used if an error forces the caller to undo the actions of * vmw_kms_helper_resource_prepare. */ -void vmw_kms_helper_resource_revert(struct vmw_resource *res) +void vmw_kms_helper_resource_revert(struct vmw_validation_ctx *ctx) { - vmw_kms_helper_buffer_revert(res->backup); + struct vmw_resource *res = ctx->res; + + vmw_kms_helper_buffer_revert(ctx->buf); + vmw_dmabuf_unreference(&ctx->buf); vmw_resource_unreserve(res, false, NULL, 0); mutex_unlock(&res->dev_priv->cmdbuf_mutex); } @@ -2536,10 +2538,14 @@ void vmw_kms_helper_resource_revert(struct vmw_resource *res) * interrupted by a signal. */ int vmw_kms_helper_resource_prepare(struct vmw_resource *res, - bool interruptible) + bool interruptible, + struct vmw_validation_ctx *ctx) { int ret = 0; + ctx->buf = NULL; + ctx->res = res; + if (interruptible) ret = mutex_lock_interruptible(&res->dev_priv->cmdbuf_mutex); else @@ -2558,6 +2564,8 @@ int vmw_kms_helper_resource_prepare(struct vmw_resource *res, res->dev_priv->has_mob); if (ret) goto out_unreserve; + + ctx->buf = vmw_dmabuf_reference(res->backup); } ret = vmw_resource_validate(res); if (ret) @@ -2565,7 +2573,7 @@ int vmw_kms_helper_resource_prepare(struct vmw_resource *res, return 0; out_revert: - vmw_kms_helper_buffer_revert(res->backup); + vmw_kms_helper_buffer_revert(ctx->buf); out_unreserve: vmw_resource_unreserve(res, false, NULL, 0); out_unlock: @@ -2581,11 +2589,13 @@ out_unlock: * @out_fence: Optional pointer to a fence pointer. If non-NULL, a * ref-counted fence pointer is returned here. */ -void vmw_kms_helper_resource_finish(struct vmw_resource *res, - struct vmw_fence_obj **out_fence) +void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx, + struct vmw_fence_obj **out_fence) { - if (res->backup || out_fence) - vmw_kms_helper_buffer_finish(res->dev_priv, NULL, res->backup, + struct vmw_resource *res = ctx->res; + + if (ctx->buf || out_fence) + vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf, out_fence, NULL); vmw_resource_unreserve(res, false, NULL, 0); @@ -2851,3 +2861,14 @@ int vmw_kms_set_config(struct drm_mode_set *set, return drm_atomic_helper_set_config(set, ctx); } + + +/** + * vmw_kms_lost_device - Notify kms that modesetting capabilities will be lost + * + * @dev: Pointer to the drm device + */ +void vmw_kms_lost_device(struct drm_device *dev) +{ + drm_atomic_helper_shutdown(dev); +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index cd9da2dd79af..3d2ca280eaa7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -240,6 +240,11 @@ struct vmw_display_unit { int set_gui_y; }; +struct vmw_validation_ctx { + struct vmw_resource *res; + struct vmw_dma_buffer *buf; +}; + #define vmw_crtc_to_du(x) \ container_of(x, struct vmw_display_unit, crtc) #define vmw_connector_to_du(x) \ @@ -296,9 +301,10 @@ void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv, struct drm_vmw_fence_rep __user * user_fence_rep); int vmw_kms_helper_resource_prepare(struct vmw_resource *res, - bool interruptible); -void vmw_kms_helper_resource_revert(struct vmw_resource *res); -void vmw_kms_helper_resource_finish(struct vmw_resource *res, + bool interruptible, + struct vmw_validation_ctx *ctx); +void vmw_kms_helper_resource_revert(struct vmw_validation_ctx *ctx); +void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx, struct vmw_fence_obj **out_fence); int vmw_kms_readback(struct vmw_private *dev_priv, struct drm_file *file_priv, @@ -439,5 +445,4 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv, int vmw_kms_set_config(struct drm_mode_set *set, struct drm_modeset_acquire_ctx *ctx); - #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 63a4cd794b73..3ec9eae831b8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -909,12 +909,13 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv, struct vmw_framebuffer_surface *vfbs = container_of(framebuffer, typeof(*vfbs), base); struct vmw_kms_sou_surface_dirty sdirty; + struct vmw_validation_ctx ctx; int ret; if (!srf) srf = &vfbs->surface->res; - ret = vmw_kms_helper_resource_prepare(srf, true); + ret = vmw_kms_helper_resource_prepare(srf, true, &ctx); if (ret) return ret; @@ -933,7 +934,7 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv, ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips, dest_x, dest_y, num_clips, inc, &sdirty.base); - vmw_kms_helper_resource_finish(srf, out_fence); + vmw_kms_helper_resource_finish(&ctx, out_fence); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index b68d74888ab1..6b969e5dea2a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -980,12 +980,13 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv, struct vmw_framebuffer_surface *vfbs = container_of(framebuffer, typeof(*vfbs), base); struct vmw_stdu_dirty sdirty; + struct vmw_validation_ctx ctx; int ret; if (!srf) srf = &vfbs->surface->res; - ret = vmw_kms_helper_resource_prepare(srf, true); + ret = vmw_kms_helper_resource_prepare(srf, true, &ctx); if (ret) return ret; @@ -1008,7 +1009,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv, dest_x, dest_y, num_clips, inc, &sdirty.base); out_finish: - vmw_kms_helper_resource_finish(srf, out_fence); + vmw_kms_helper_resource_finish(&ctx, out_fence); return ret; } diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c index 97b99500153d..83f9dd934a5d 100644 --- a/drivers/gpu/ipu-v3/ipu-prg.c +++ b/drivers/gpu/ipu-v3/ipu-prg.c @@ -250,10 +250,14 @@ void ipu_prg_channel_disable(struct ipuv3_channel *ipu_chan) { int prg_chan = ipu_prg_ipu_to_prg_chan(ipu_chan->num); struct ipu_prg *prg = ipu_chan->ipu->prg_priv; - struct ipu_prg_channel *chan = &prg->chan[prg_chan]; + struct ipu_prg_channel *chan; u32 val; - if (!chan->enabled || prg_chan < 0) + if (prg_chan < 0) + return; + + chan = &prg->chan[prg_chan]; + if (!chan->enabled) return; pm_runtime_get_sync(prg->dev); @@ -280,13 +284,15 @@ int ipu_prg_channel_configure(struct ipuv3_channel *ipu_chan, { int prg_chan = ipu_prg_ipu_to_prg_chan(ipu_chan->num); struct ipu_prg *prg = ipu_chan->ipu->prg_priv; - struct ipu_prg_channel *chan = &prg->chan[prg_chan]; + struct ipu_prg_channel *chan; u32 val; int ret; if (prg_chan < 0) return prg_chan; + chan = &prg->chan[prg_chan]; + if (chan->enabled) { ipu_pre_update(prg->pres[chan->used_pre], *eba); return 0; diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 50e071444a5c..8699bb969e7e 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -417,13 +417,24 @@ __hv_pkt_iter_next(struct vmbus_channel *channel, } EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); +/* How many bytes were read in this iterator cycle */ +static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi, + u32 start_read_index) +{ + if (rbi->priv_read_index >= start_read_index) + return rbi->priv_read_index - start_read_index; + else + return rbi->ring_datasize - start_read_index + + rbi->priv_read_index; +} + /* * Update host ring buffer after iterating over packets. */ void hv_pkt_iter_close(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->inbound; - u32 orig_write_sz = hv_get_bytes_to_write(rbi); + u32 curr_write_sz, pending_sz, bytes_read, start_read_index; /* * Make sure all reads are done before we update the read index since @@ -431,8 +442,12 @@ void hv_pkt_iter_close(struct vmbus_channel *channel) * is updated. */ virt_rmb(); + start_read_index = rbi->ring_buffer->read_index; rbi->ring_buffer->read_index = rbi->priv_read_index; + if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz) + return; + /* * Issue a full memory barrier before making the signaling decision. * Here is the reason for having this barrier: @@ -446,26 +461,29 @@ void hv_pkt_iter_close(struct vmbus_channel *channel) */ virt_mb(); - /* If host has disabled notifications then skip */ - if (rbi->ring_buffer->interrupt_mask) + pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); + if (!pending_sz) return; - if (rbi->ring_buffer->feature_bits.feat_pending_send_sz) { - u32 pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); + /* + * Ensure the read of write_index in hv_get_bytes_to_write() + * happens after the read of pending_send_sz. + */ + virt_rmb(); + curr_write_sz = hv_get_bytes_to_write(rbi); + bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index); - /* - * If there was space before we began iteration, - * then host was not blocked. Also handles case where - * pending_sz is zero then host has nothing pending - * and does not need to be signaled. - */ - if (orig_write_sz > pending_sz) - return; + /* + * If there was space before we began iteration, + * then host was not blocked. + */ - /* If pending write will not fit, don't give false hope. */ - if (hv_get_bytes_to_write(rbi) < pending_sz) - return; - } + if (curr_write_sz - bytes_read > pending_sz) + return; + + /* If pending write will not fit, don't give false hope. */ + if (curr_write_sz <= pending_sz) + return; vmbus_setevent(channel); } diff --git a/drivers/i2c/busses/i2c-octeon-core.c b/drivers/i2c/busses/i2c-octeon-core.c index 1d8775799056..d9607905dc2f 100644 --- a/drivers/i2c/busses/i2c-octeon-core.c +++ b/drivers/i2c/busses/i2c-octeon-core.c @@ -233,6 +233,7 @@ static int octeon_i2c_check_status(struct octeon_i2c *i2c, int final_read) return -EOPNOTSUPP; case STAT_TXDATA_NAK: + case STAT_BUS_ERROR: return -EIO; case STAT_TXADDR_NAK: case STAT_RXADDR_NAK: diff --git a/drivers/i2c/busses/i2c-octeon-core.h b/drivers/i2c/busses/i2c-octeon-core.h index a7ef19855bb8..9bb9f64fdda0 100644 --- a/drivers/i2c/busses/i2c-octeon-core.h +++ b/drivers/i2c/busses/i2c-octeon-core.h @@ -43,7 +43,7 @@ #define TWSI_CTL_AAK 0x04 /* Assert ACK */ /* Status values */ -#define STAT_ERROR 0x00 +#define STAT_BUS_ERROR 0x00 #define STAT_START 0x08 #define STAT_REP_START 0x10 #define STAT_TXADDR_ACK 0x18 diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 17fd55af4d92..caa20eb5f26b 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -928,7 +928,7 @@ static int exact_lock(dev_t dev, void *data) { struct gendisk *p = data; - if (!get_disk(p)) + if (!get_disk_and_module(p)) return -1; return 0; } diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 6fe995cf16a6..3e6fd5a8ac5b 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -920,6 +920,8 @@ static const struct iio_trigger_ops st_accel_trigger_ops = { int st_accel_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *adata = iio_priv(indio_dev); + struct st_sensors_platform_data *pdata = + (struct st_sensors_platform_data *)adata->dev->platform_data; int irq = adata->get_irq_data_ready(indio_dev); int err; @@ -946,7 +948,10 @@ int st_accel_common_probe(struct iio_dev *indio_dev) &adata->sensor_settings->fs.fs_avl[0]; adata->odr = adata->sensor_settings->odr.odr_avl[0].hz; - err = st_sensors_init_sensor(indio_dev, adata->dev->platform_data); + if (!pdata) + pdata = (struct st_sensors_platform_data *)&default_accel_pdata; + + err = st_sensors_init_sensor(indio_dev, pdata); if (err < 0) goto st_accel_power_off; diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index 29fa7736d80c..ede955d9b2a4 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -462,8 +462,10 @@ static int meson_sar_adc_lock(struct iio_dev *indio_dev) regmap_read(priv->regmap, MESON_SAR_ADC_DELAY, &val); } while (val & MESON_SAR_ADC_DELAY_BL30_BUSY && timeout--); - if (timeout < 0) + if (timeout < 0) { + mutex_unlock(&indio_dev->mlock); return -ETIMEDOUT; + } } return 0; diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index daa026d6a94f..01422d11753c 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -54,7 +54,6 @@ struct stm32_dfsdm_adc { struct stm32_dfsdm *dfsdm; const struct stm32_dfsdm_dev_data *dev_data; unsigned int fl_id; - unsigned int ch_id; /* ADC specific */ unsigned int oversamp; @@ -384,7 +383,7 @@ static ssize_t dfsdm_adc_audio_set_spiclk(struct iio_dev *indio_dev, { struct stm32_dfsdm_adc *adc = iio_priv(indio_dev); struct stm32_dfsdm_filter *fl = &adc->dfsdm->fl_list[adc->fl_id]; - struct stm32_dfsdm_channel *ch = &adc->dfsdm->ch_list[adc->ch_id]; + struct stm32_dfsdm_channel *ch = &adc->dfsdm->ch_list[chan->channel]; unsigned int sample_freq = adc->sample_freq; unsigned int spi_freq; int ret; @@ -419,18 +418,20 @@ static ssize_t dfsdm_adc_audio_set_spiclk(struct iio_dev *indio_dev, return len; } -static int stm32_dfsdm_start_conv(struct stm32_dfsdm_adc *adc, bool dma) +static int stm32_dfsdm_start_conv(struct stm32_dfsdm_adc *adc, + const struct iio_chan_spec *chan, + bool dma) { struct regmap *regmap = adc->dfsdm->regmap; int ret; unsigned int dma_en = 0, cont_en = 0; - ret = stm32_dfsdm_start_channel(adc->dfsdm, adc->ch_id); + ret = stm32_dfsdm_start_channel(adc->dfsdm, chan->channel); if (ret < 0) return ret; ret = stm32_dfsdm_filter_configure(adc->dfsdm, adc->fl_id, - adc->ch_id); + chan->channel); if (ret < 0) goto stop_channels; @@ -464,12 +465,13 @@ stop_channels: regmap_update_bits(regmap, DFSDM_CR1(adc->fl_id), DFSDM_CR1_RCONT_MASK, 0); - stm32_dfsdm_stop_channel(adc->dfsdm, adc->fl_id); + stm32_dfsdm_stop_channel(adc->dfsdm, chan->channel); return ret; } -static void stm32_dfsdm_stop_conv(struct stm32_dfsdm_adc *adc) +static void stm32_dfsdm_stop_conv(struct stm32_dfsdm_adc *adc, + const struct iio_chan_spec *chan) { struct regmap *regmap = adc->dfsdm->regmap; @@ -482,7 +484,7 @@ static void stm32_dfsdm_stop_conv(struct stm32_dfsdm_adc *adc) regmap_update_bits(regmap, DFSDM_CR1(adc->fl_id), DFSDM_CR1_RCONT_MASK, 0); - stm32_dfsdm_stop_channel(adc->dfsdm, adc->ch_id); + stm32_dfsdm_stop_channel(adc->dfsdm, chan->channel); } static int stm32_dfsdm_set_watermark(struct iio_dev *indio_dev, @@ -609,6 +611,7 @@ static int stm32_dfsdm_adc_dma_start(struct iio_dev *indio_dev) static int stm32_dfsdm_postenable(struct iio_dev *indio_dev) { struct stm32_dfsdm_adc *adc = iio_priv(indio_dev); + const struct iio_chan_spec *chan = &indio_dev->channels[0]; int ret; /* Reset adc buffer index */ @@ -618,7 +621,7 @@ static int stm32_dfsdm_postenable(struct iio_dev *indio_dev) if (ret < 0) return ret; - ret = stm32_dfsdm_start_conv(adc, true); + ret = stm32_dfsdm_start_conv(adc, chan, true); if (ret) { dev_err(&indio_dev->dev, "Can't start conversion\n"); goto stop_dfsdm; @@ -635,7 +638,7 @@ static int stm32_dfsdm_postenable(struct iio_dev *indio_dev) return 0; err_stop_conv: - stm32_dfsdm_stop_conv(adc); + stm32_dfsdm_stop_conv(adc, chan); stop_dfsdm: stm32_dfsdm_stop_dfsdm(adc->dfsdm); @@ -645,11 +648,12 @@ stop_dfsdm: static int stm32_dfsdm_predisable(struct iio_dev *indio_dev) { struct stm32_dfsdm_adc *adc = iio_priv(indio_dev); + const struct iio_chan_spec *chan = &indio_dev->channels[0]; if (adc->dma_chan) dmaengine_terminate_all(adc->dma_chan); - stm32_dfsdm_stop_conv(adc); + stm32_dfsdm_stop_conv(adc, chan); stm32_dfsdm_stop_dfsdm(adc->dfsdm); @@ -730,7 +734,7 @@ static int stm32_dfsdm_single_conv(struct iio_dev *indio_dev, if (ret < 0) goto stop_dfsdm; - ret = stm32_dfsdm_start_conv(adc, false); + ret = stm32_dfsdm_start_conv(adc, chan, false); if (ret < 0) { regmap_update_bits(adc->dfsdm->regmap, DFSDM_CR2(adc->fl_id), DFSDM_CR2_REOCIE_MASK, DFSDM_CR2_REOCIE(0)); @@ -751,7 +755,7 @@ static int stm32_dfsdm_single_conv(struct iio_dev *indio_dev, else ret = IIO_VAL_INT; - stm32_dfsdm_stop_conv(adc); + stm32_dfsdm_stop_conv(adc, chan); stop_dfsdm: stm32_dfsdm_stop_dfsdm(adc->dfsdm); @@ -765,7 +769,7 @@ static int stm32_dfsdm_write_raw(struct iio_dev *indio_dev, { struct stm32_dfsdm_adc *adc = iio_priv(indio_dev); struct stm32_dfsdm_filter *fl = &adc->dfsdm->fl_list[adc->fl_id]; - struct stm32_dfsdm_channel *ch = &adc->dfsdm->ch_list[adc->ch_id]; + struct stm32_dfsdm_channel *ch = &adc->dfsdm->ch_list[chan->channel]; unsigned int spi_freq = adc->spi_freq; int ret = -EINVAL; @@ -972,7 +976,6 @@ static int stm32_dfsdm_adc_chan_init_one(struct iio_dev *indio_dev, } ch->scan_type.realbits = 24; ch->scan_type.storagebits = 32; - adc->ch_id = ch->channel; return stm32_dfsdm_chan_configure(adc->dfsdm, &adc->dfsdm->ch_list[ch->channel]); @@ -1001,7 +1004,7 @@ static int stm32_dfsdm_audio_init(struct iio_dev *indio_dev) } ch->info_mask_separate = BIT(IIO_CHAN_INFO_SAMP_FREQ); - d_ch = &adc->dfsdm->ch_list[adc->ch_id]; + d_ch = &adc->dfsdm->ch_list[ch->channel]; if (d_ch->src != DFSDM_CHANNEL_SPI_CLOCK_EXTERNAL) adc->spi_freq = adc->dfsdm->spi_master_freq; @@ -1042,8 +1045,8 @@ static int stm32_dfsdm_adc_init(struct iio_dev *indio_dev) return -ENOMEM; for (chan_idx = 0; chan_idx < num_ch; chan_idx++) { - ch->scan_index = chan_idx; - ret = stm32_dfsdm_adc_chan_init_one(indio_dev, ch); + ch[chan_idx].scan_index = chan_idx; + ret = stm32_dfsdm_adc_chan_init_one(indio_dev, &ch[chan_idx]); if (ret < 0) { dev_err(&indio_dev->dev, "Channels init failed\n"); return ret; diff --git a/drivers/iio/adc/stm32-dfsdm-core.c b/drivers/iio/adc/stm32-dfsdm-core.c index 6290332cfd3f..e50efdcc41ff 100644 --- a/drivers/iio/adc/stm32-dfsdm-core.c +++ b/drivers/iio/adc/stm32-dfsdm-core.c @@ -83,7 +83,7 @@ int stm32_dfsdm_start_dfsdm(struct stm32_dfsdm *dfsdm) { struct dfsdm_priv *priv = container_of(dfsdm, struct dfsdm_priv, dfsdm); struct device *dev = &priv->pdev->dev; - unsigned int clk_div = priv->spi_clk_out_div; + unsigned int clk_div = priv->spi_clk_out_div, clk_src; int ret; if (atomic_inc_return(&priv->n_active_ch) == 1) { @@ -100,6 +100,14 @@ int stm32_dfsdm_start_dfsdm(struct stm32_dfsdm *dfsdm) } } + /* select clock source, e.g. 0 for "dfsdm" or 1 for "audio" */ + clk_src = priv->aclk ? 1 : 0; + ret = regmap_update_bits(dfsdm->regmap, DFSDM_CHCFGR1(0), + DFSDM_CHCFGR1_CKOUTSRC_MASK, + DFSDM_CHCFGR1_CKOUTSRC(clk_src)); + if (ret < 0) + goto disable_aclk; + /* Output the SPI CLKOUT (if clk_div == 0 clock if OFF) */ ret = regmap_update_bits(dfsdm->regmap, DFSDM_CHCFGR1(0), DFSDM_CHCFGR1_CKOUTDIV_MASK, @@ -274,7 +282,7 @@ static int stm32_dfsdm_probe(struct platform_device *pdev) dfsdm->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "dfsdm", dfsdm->base, - &stm32h7_dfsdm_regmap_cfg); + dev_data->regmap_cfg); if (IS_ERR(dfsdm->regmap)) { ret = PTR_ERR(dfsdm->regmap); dev_err(&pdev->dev, "%s: Failed to allocate regmap: %d\n", diff --git a/drivers/iio/chemical/ccs811.c b/drivers/iio/chemical/ccs811.c index fbe2431f5b81..1ea9f5513b02 100644 --- a/drivers/iio/chemical/ccs811.c +++ b/drivers/iio/chemical/ccs811.c @@ -133,6 +133,9 @@ static int ccs811_start_sensor_application(struct i2c_client *client) if (ret < 0) return ret; + if ((ret & CCS811_STATUS_FW_MODE_APPLICATION)) + return 0; + if ((ret & CCS811_STATUS_APP_VALID_MASK) != CCS811_STATUS_APP_VALID_LOADED) return -EIO; diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 349e5c713c03..4ddb6cf7d401 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -640,7 +640,7 @@ int st_press_common_probe(struct iio_dev *indio_dev) press_data->sensor_settings->drdy_irq.int2.addr)) pdata = (struct st_sensors_platform_data *)&default_press_pdata; - err = st_sensors_init_sensor(indio_dev, press_data->dev->platform_data); + err = st_sensors_init_sensor(indio_dev, pdata); if (err < 0) goto st_press_power_off; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a5b4cf030c11..9183d148d644 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -550,18 +550,13 @@ static int addr_resolve(struct sockaddr *src_in, dst_release(dst); } - if (ndev->flags & IFF_LOOPBACK) { - ret = rdma_translate_ip(dst_in, addr); - /* - * Put the loopback device and get the translated - * device instead. - */ + if (ndev) { + if (ndev->flags & IFF_LOOPBACK) + ret = rdma_translate_ip(dst_in, addr); + else + addr->bound_dev_if = ndev->ifindex; dev_put(ndev); - ndev = dev_get_by_index(addr->net, addr->bound_dev_if); - } else { - addr->bound_dev_if = ndev->ifindex; } - dev_put(ndev); return ret; } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e66963ca58bd..a5367c5efbe7 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3069,7 +3069,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list, continue; /* different dest port -> unique */ - if (!cma_any_port(cur_daddr) && + if (!cma_any_port(daddr) && + !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; @@ -3080,7 +3081,8 @@ static int cma_port_is_unique(struct rdma_bind_list *bind_list, continue; /* different dst address -> unique */ - if (!cma_any_addr(cur_daddr) && + if (!cma_any_addr(daddr) && + !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; @@ -3378,13 +3380,13 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) } #endif } + daddr = cma_dst_addr(id_priv); + daddr->sa_family = addr->sa_family; + ret = cma_get_port(id_priv); if (ret) goto err2; - daddr = cma_dst_addr(id_priv); - daddr->sa_family = addr->sa_family; - return 0; err2: if (id_priv->cma_dev) @@ -4173,6 +4175,9 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, struct cma_multicast *mc; int ret; + if (!id->device) + return -EINVAL; + id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp(id_priv, RDMA_CM_ADDR_BOUND) && !cma_comp(id_priv, RDMA_CM_ADDR_RESOLVED)) diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c index bc79ca8215d7..af5ad6a56ae4 100644 --- a/drivers/infiniband/core/cq.c +++ b/drivers/infiniband/core/cq.c @@ -17,6 +17,7 @@ /* # of WCs to poll for with a single call to ib_poll_cq */ #define IB_POLL_BATCH 16 +#define IB_POLL_BATCH_DIRECT 8 /* # of WCs to iterate over before yielding */ #define IB_POLL_BUDGET_IRQ 256 @@ -25,18 +26,18 @@ #define IB_POLL_FLAGS \ (IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS) -static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) +static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs, + int batch) { int i, n, completed = 0; - struct ib_wc *wcs = poll_wc ? : cq->wc; /* * budget might be (-1) if the caller does not * want to bound this call, thus we need unsigned * minimum here. */ - while ((n = ib_poll_cq(cq, min_t(u32, IB_POLL_BATCH, - budget - completed), wcs)) > 0) { + while ((n = ib_poll_cq(cq, min_t(u32, batch, + budget - completed), wcs)) > 0) { for (i = 0; i < n; i++) { struct ib_wc *wc = &wcs[i]; @@ -48,8 +49,7 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) completed += n; - if (n != IB_POLL_BATCH || - (budget != -1 && completed >= budget)) + if (n != batch || (budget != -1 && completed >= budget)) break; } @@ -72,9 +72,9 @@ static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *poll_wc) */ int ib_process_cq_direct(struct ib_cq *cq, int budget) { - struct ib_wc wcs[IB_POLL_BATCH]; + struct ib_wc wcs[IB_POLL_BATCH_DIRECT]; - return __ib_process_cq(cq, budget, wcs); + return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT); } EXPORT_SYMBOL(ib_process_cq_direct); @@ -88,7 +88,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget) struct ib_cq *cq = container_of(iop, struct ib_cq, iop); int completed; - completed = __ib_process_cq(cq, budget, NULL); + completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH); if (completed < budget) { irq_poll_complete(&cq->iop); if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) @@ -108,7 +108,8 @@ static void ib_cq_poll_work(struct work_struct *work) struct ib_cq *cq = container_of(work, struct ib_cq, work); int completed; - completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, NULL); + completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc, + IB_POLL_BATCH); if (completed >= IB_POLL_BUDGET_WORKQUEUE || ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) queue_work(ib_comp_wq, &cq->work); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index e8010e73a1cf..bb065c9449be 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -536,14 +536,14 @@ int ib_register_device(struct ib_device *device, ret = device->query_device(device, &device->attrs, &uhw); if (ret) { pr_warn("Couldn't query the device attributes\n"); - goto cache_cleanup; + goto cg_cleanup; } ret = ib_device_register_sysfs(device, port_callback); if (ret) { pr_warn("Couldn't register device %s with driver model\n", device->name); - goto cache_cleanup; + goto cg_cleanup; } device->reg_state = IB_DEV_REGISTERED; @@ -559,6 +559,8 @@ int ib_register_device(struct ib_device *device, mutex_unlock(&device_mutex); return 0; +cg_cleanup: + ib_device_unregister_rdmacg(device); cache_cleanup: ib_cache_cleanup_one(device); ib_cache_release_one(device); diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c index 8cf15d4a8ac4..9f029a1ca5ea 100644 --- a/drivers/infiniband/core/sa_query.c +++ b/drivers/infiniband/core/sa_query.c @@ -1291,10 +1291,9 @@ int ib_init_ah_attr_from_path(struct ib_device *device, u8 port_num, resolved_dev = dev_get_by_index(dev_addr.net, dev_addr.bound_dev_if); - if (resolved_dev->flags & IFF_LOOPBACK) { - dev_put(resolved_dev); - resolved_dev = idev; - dev_hold(resolved_dev); + if (!resolved_dev) { + dev_put(idev); + return -ENODEV; } ndev = ib_get_ndev_from_path(rec); rcu_read_lock(); diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index f015f1bf88c9..e5a1e7d81326 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -132,7 +132,7 @@ static inline struct ucma_context *_ucma_find_context(int id, ctx = idr_find(&ctx_idr, id); if (!ctx) ctx = ERR_PTR(-ENOENT); - else if (ctx->file != file) + else if (ctx->file != file || !ctx->cm_id) ctx = ERR_PTR(-EINVAL); return ctx; } @@ -456,6 +456,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, struct rdma_ucm_create_id cmd; struct rdma_ucm_create_id_resp resp; struct ucma_context *ctx; + struct rdma_cm_id *cm_id; enum ib_qp_type qp_type; int ret; @@ -476,10 +477,10 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, return -ENOMEM; ctx->uid = cmd.uid; - ctx->cm_id = rdma_create_id(current->nsproxy->net_ns, - ucma_event_handler, ctx, cmd.ps, qp_type); - if (IS_ERR(ctx->cm_id)) { - ret = PTR_ERR(ctx->cm_id); + cm_id = rdma_create_id(current->nsproxy->net_ns, + ucma_event_handler, ctx, cmd.ps, qp_type); + if (IS_ERR(cm_id)) { + ret = PTR_ERR(cm_id); goto err1; } @@ -489,14 +490,19 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, ret = -EFAULT; goto err2; } + + ctx->cm_id = cm_id; return 0; err2: - rdma_destroy_id(ctx->cm_id); + rdma_destroy_id(cm_id); err1: mutex_lock(&mut); idr_remove(&ctx_idr, ctx->id); mutex_unlock(&mut); + mutex_lock(&file->mut); + list_del(&ctx->list); + mutex_unlock(&file->mut); kfree(ctx); return ret; } @@ -664,19 +670,23 @@ static ssize_t ucma_resolve_ip(struct ucma_file *file, int in_len, int out_len) { struct rdma_ucm_resolve_ip cmd; + struct sockaddr *src, *dst; struct ucma_context *ctx; int ret; if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; + src = (struct sockaddr *) &cmd.src_addr; + dst = (struct sockaddr *) &cmd.dst_addr; + if (!rdma_addr_size(src) || !rdma_addr_size(dst)) + return -EINVAL; + ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); - ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, - (struct sockaddr *) &cmd.dst_addr, - cmd.timeout_ms); + ret = rdma_resolve_addr(ctx->cm_id, src, dst, cmd.timeout_ms); ucma_put_ctx(ctx); return ret; } @@ -1149,6 +1159,9 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file, if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; + if (cmd.qp_state > IB_QPS_ERR) + return -EINVAL; + ctx = ucma_get_ctx(file, cmd.id); if (IS_ERR(ctx)) return PTR_ERR(ctx); @@ -1294,6 +1307,9 @@ static ssize_t ucma_set_option(struct ucma_file *file, const char __user *inbuf, if (IS_ERR(ctx)) return PTR_ERR(ctx); + if (unlikely(cmd.optval > KMALLOC_MAX_SIZE)) + return -EINVAL; + optval = memdup_user((void __user *) (unsigned long) cmd.optval, cmd.optlen); if (IS_ERR(optval)) { @@ -1343,7 +1359,7 @@ static ssize_t ucma_process_join(struct ucma_file *file, return -ENOSPC; addr = (struct sockaddr *) &cmd->addr; - if (!cmd->addr_size || (cmd->addr_size != rdma_addr_size(addr))) + if (cmd->addr_size != rdma_addr_size(addr)) return -EINVAL; if (cmd->join_flags == RDMA_MC_JOIN_FLAG_FULLMEMBER) @@ -1411,6 +1427,9 @@ static ssize_t ucma_join_ip_multicast(struct ucma_file *file, join_cmd.uid = cmd.uid; join_cmd.id = cmd.id; join_cmd.addr_size = rdma_addr_size((struct sockaddr *) &cmd.addr); + if (!join_cmd.addr_size) + return -EINVAL; + join_cmd.join_flags = RDMA_MC_JOIN_FLAG_FULLMEMBER; memcpy(&join_cmd.addr, &cmd.addr, join_cmd.addr_size); @@ -1426,6 +1445,9 @@ static ssize_t ucma_join_multicast(struct ucma_file *file, if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; + if (!rdma_addr_size((struct sockaddr *)&cmd.addr)) + return -EINVAL; + return ucma_process_join(file, &cmd, out_len); } diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 3eb7a8387116..96f76896488d 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -57,8 +57,8 @@ #define BNXT_RE_PAGE_SIZE_8M BIT(BNXT_RE_PAGE_SHIFT_8M) #define BNXT_RE_PAGE_SIZE_1G BIT(BNXT_RE_PAGE_SHIFT_1G) -#define BNXT_RE_MAX_MR_SIZE_LOW BIT(BNXT_RE_PAGE_SHIFT_1G) -#define BNXT_RE_MAX_MR_SIZE_HIGH BIT(39) +#define BNXT_RE_MAX_MR_SIZE_LOW BIT_ULL(BNXT_RE_PAGE_SHIFT_1G) +#define BNXT_RE_MAX_MR_SIZE_HIGH BIT_ULL(39) #define BNXT_RE_MAX_MR_SIZE BNXT_RE_MAX_MR_SIZE_HIGH #define BNXT_RE_MAX_QPC_COUNT (64 * 1024) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 643174d949a8..8301d7e5fa8c 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -785,7 +785,7 @@ int bnxt_re_query_ah(struct ib_ah *ib_ah, struct rdma_ah_attr *ah_attr) return 0; } -static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) +unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) __acquires(&qp->scq->cq_lock) __acquires(&qp->rcq->cq_lock) { unsigned long flags; @@ -799,8 +799,8 @@ static unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp) return flags; } -static void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, - unsigned long flags) +void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, + unsigned long flags) __releases(&qp->scq->cq_lock) __releases(&qp->rcq->cq_lock) { if (qp->rcq != qp->scq) @@ -1606,6 +1606,7 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, int status; union ib_gid sgid; struct ib_gid_attr sgid_attr; + unsigned int flags; u8 nw_type; qp->qplib_qp.modify_flags = 0; @@ -1634,14 +1635,18 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, dev_dbg(rdev_to_dev(rdev), "Move QP = %p to flush list\n", qp); + flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); } if (!qp->sumem && qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_RESET) { dev_dbg(rdev_to_dev(rdev), "Move QP = %p out of flush list\n", qp); + flags = bnxt_re_lock_cqs(qp); bnxt_qplib_clean_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); } } if (qp_attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY) { @@ -2227,10 +2232,13 @@ static int bnxt_re_build_inv_wqe(struct ib_send_wr *wr, wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV; wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey; + /* Need unconditional fence for local invalidate + * opcode to work as expected. + */ + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + if (wr->send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; - if (wr->send_flags & IB_SEND_FENCE) - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; if (wr->send_flags & IB_SEND_SOLICITED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT; @@ -2251,8 +2259,12 @@ static int bnxt_re_build_reg_wqe(struct ib_reg_wr *wr, wqe->frmr.levels = qplib_frpl->hwq.level + 1; wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR; - if (wr->wr.send_flags & IB_SEND_FENCE) - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + /* Need unconditional fence for reg_mr + * opcode to function as expected. + */ + + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; + if (wr->wr.send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; @@ -3586,7 +3598,7 @@ struct ib_mr *bnxt_re_reg_user_mr(struct ib_pd *ib_pd, u64 start, u64 length, int umem_pgs, page_shift, rc; if (length > BNXT_RE_MAX_MR_SIZE) { - dev_err(rdev_to_dev(rdev), "MR Size: %lld > Max supported:%ld\n", + dev_err(rdev_to_dev(rdev), "MR Size: %lld > Max supported:%lld\n", length, BNXT_RE_MAX_MR_SIZE); return ERR_PTR(-ENOMEM); } diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index b88a48d43a9d..e62b7c2c7da6 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -222,4 +222,7 @@ struct ib_ucontext *bnxt_re_alloc_ucontext(struct ib_device *ibdev, struct ib_udata *udata); int bnxt_re_dealloc_ucontext(struct ib_ucontext *context); int bnxt_re_mmap(struct ib_ucontext *context, struct vm_area_struct *vma); + +unsigned long bnxt_re_lock_cqs(struct bnxt_re_qp *qp); +void bnxt_re_unlock_cqs(struct bnxt_re_qp *qp, unsigned long flags); #endif /* __BNXT_RE_IB_VERBS_H__ */ diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 33a448036c2e..f6e361750466 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -730,6 +730,13 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct bnxt_re_qp *qp) { struct ib_event event; + unsigned int flags; + + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + flags = bnxt_re_lock_cqs(qp); + bnxt_qplib_add_flush_qp(&qp->qplib_qp); + bnxt_re_unlock_cqs(qp, flags); + } memset(&event, 0, sizeof(event)); if (qp->qplib_qp.srq) { @@ -1416,9 +1423,12 @@ static void bnxt_re_task(struct work_struct *work) switch (re_work->event) { case NETDEV_REGISTER: rc = bnxt_re_ib_reg(rdev); - if (rc) + if (rc) { dev_err(rdev_to_dev(rdev), "Failed to register with IB: %#x", rc); + bnxt_re_remove_one(rdev); + bnxt_re_dev_unreg(rdev); + } break; case NETDEV_UP: bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 3ea5b9624f6b..3a78faba8d91 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -88,75 +88,35 @@ static void __bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) } } -void bnxt_qplib_acquire_cq_locks(struct bnxt_qplib_qp *qp, - unsigned long *flags) - __acquires(&qp->scq->hwq.lock) __acquires(&qp->rcq->hwq.lock) +static void bnxt_qplib_acquire_cq_flush_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __acquires(&qp->scq->flush_lock) __acquires(&qp->rcq->flush_lock) { - spin_lock_irqsave(&qp->scq->hwq.lock, *flags); + spin_lock_irqsave(&qp->scq->flush_lock, *flags); if (qp->scq == qp->rcq) - __acquire(&qp->rcq->hwq.lock); + __acquire(&qp->rcq->flush_lock); else - spin_lock(&qp->rcq->hwq.lock); + spin_lock(&qp->rcq->flush_lock); } -void bnxt_qplib_release_cq_locks(struct bnxt_qplib_qp *qp, - unsigned long *flags) - __releases(&qp->scq->hwq.lock) __releases(&qp->rcq->hwq.lock) +static void bnxt_qplib_release_cq_flush_locks(struct bnxt_qplib_qp *qp, + unsigned long *flags) + __releases(&qp->scq->flush_lock) __releases(&qp->rcq->flush_lock) { if (qp->scq == qp->rcq) - __release(&qp->rcq->hwq.lock); + __release(&qp->rcq->flush_lock); else - spin_unlock(&qp->rcq->hwq.lock); - spin_unlock_irqrestore(&qp->scq->hwq.lock, *flags); -} - -static struct bnxt_qplib_cq *bnxt_qplib_find_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - if (qp->scq == qp->rcq) - buddy_cq = NULL; - else if (qp->scq == cq) - buddy_cq = qp->rcq; - else - buddy_cq = qp->scq; - return buddy_cq; -} - -static void bnxt_qplib_lock_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) - __acquires(&buddy_cq->hwq.lock) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); - if (!buddy_cq) - __acquire(&cq->hwq.lock); - else - spin_lock(&buddy_cq->hwq.lock); -} - -static void bnxt_qplib_unlock_buddy_cq(struct bnxt_qplib_qp *qp, - struct bnxt_qplib_cq *cq) - __releases(&buddy_cq->hwq.lock) -{ - struct bnxt_qplib_cq *buddy_cq = NULL; - - buddy_cq = bnxt_qplib_find_buddy_cq(qp, cq); - if (!buddy_cq) - __release(&cq->hwq.lock); - else - spin_unlock(&buddy_cq->hwq.lock); + spin_unlock(&qp->rcq->flush_lock); + spin_unlock_irqrestore(&qp->scq->flush_lock, *flags); } void bnxt_qplib_add_flush_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; - bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_acquire_cq_flush_locks(qp, &flags); __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + bnxt_qplib_release_cq_flush_locks(qp, &flags); } static void __bnxt_qplib_del_flush_qp(struct bnxt_qplib_qp *qp) @@ -177,7 +137,7 @@ void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) { unsigned long flags; - bnxt_qplib_acquire_cq_locks(qp, &flags); + bnxt_qplib_acquire_cq_flush_locks(qp, &flags); __clean_cq(qp->scq, (u64)(unsigned long)qp); qp->sq.hwq.prod = 0; qp->sq.hwq.cons = 0; @@ -186,7 +146,7 @@ void bnxt_qplib_clean_qp(struct bnxt_qplib_qp *qp) qp->rq.hwq.cons = 0; __bnxt_qplib_del_flush_qp(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + bnxt_qplib_release_cq_flush_locks(qp, &flags); } static void bnxt_qpn_cqn_sched_task(struct work_struct *work) @@ -283,7 +243,7 @@ static void bnxt_qplib_service_nq(unsigned long data) u32 sw_cons, raw_cons; u16 type; int budget = nq->budget; - u64 q_handle; + uintptr_t q_handle; /* Service the NQ until empty */ raw_cons = hwq->cons; @@ -566,7 +526,7 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, /* Configure the request */ req.dpi = cpu_to_le32(srq->dpi->dpi); - req.srq_handle = cpu_to_le64(srq); + req.srq_handle = cpu_to_le64((uintptr_t)srq); req.srq_size = cpu_to_le16((u16)srq->hwq.max_elements); pbl = &srq->hwq.pbl[PBL_LVL_0]; @@ -2107,9 +2067,6 @@ void bnxt_qplib_mark_qp_error(void *qp_handle) /* Must block new posting of SQ and RQ */ qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; bnxt_qplib_cancel_phantom_processing(qp); - - /* Add qp to flush list of the CQ */ - __bnxt_qplib_add_flush_qp(qp); } /* Note: SQE is valid from sw_sq_cons up to cqe_sq_cons (exclusive) @@ -2285,9 +2242,9 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, sw_sq_cons, cqe->wr_id, cqe->status); cqe++; (*budget)--; - bnxt_qplib_lock_buddy_cq(qp, cq); bnxt_qplib_mark_qp_error(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + /* Add qp to flush list of the CQ */ + bnxt_qplib_add_flush_qp(qp); } else { if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { /* Before we complete, do WA 9060 */ @@ -2403,9 +2360,7 @@ static int bnxt_qplib_cq_process_res_rc(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } @@ -2489,9 +2444,7 @@ static int bnxt_qplib_cq_process_res_ud(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } done: @@ -2501,11 +2454,9 @@ done: bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq) { struct cq_base *hw_cqe, **hw_cqe_ptr; - unsigned long flags; u32 sw_cons, raw_cons; bool rc = true; - spin_lock_irqsave(&cq->hwq.lock, flags); raw_cons = cq->hwq.cons; sw_cons = HWQ_CMP(raw_cons, &cq->hwq); hw_cqe_ptr = (struct cq_base **)cq->hwq.pbl_ptr; @@ -2513,7 +2464,6 @@ bool bnxt_qplib_is_cq_empty(struct bnxt_qplib_cq *cq) /* Check for Valid bit. If the CQE is valid, return false */ rc = !CQE_CMP_VALID(hw_cqe, raw_cons, cq->hwq.max_elements); - spin_unlock_irqrestore(&cq->hwq.lock, flags); return rc; } @@ -2602,9 +2552,7 @@ static int bnxt_qplib_cq_process_res_raweth_qp1(struct bnxt_qplib_cq *cq, if (hwcqe->status != CQ_RES_RC_STATUS_OK) { qp->state = CMDQ_MODIFY_QP_NEW_STATE_ERR; /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); } } @@ -2719,9 +2667,7 @@ do_rq: */ /* Add qp to flush list of the CQ */ - bnxt_qplib_lock_buddy_cq(qp, cq); - __bnxt_qplib_add_flush_qp(qp); - bnxt_qplib_unlock_buddy_cq(qp, cq); + bnxt_qplib_add_flush_qp(qp); done: return rc; } @@ -2750,7 +2696,7 @@ int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, u32 budget = num_cqes; unsigned long flags; - spin_lock_irqsave(&cq->hwq.lock, flags); + spin_lock_irqsave(&cq->flush_lock, flags); list_for_each_entry(qp, &cq->sqf_head, sq_flush) { dev_dbg(&cq->hwq.pdev->dev, "QPLIB: FP: Flushing SQ QP= %p", @@ -2764,7 +2710,7 @@ int bnxt_qplib_process_flush_list(struct bnxt_qplib_cq *cq, qp); __flush_rq(&qp->rq, qp, &cqe, &budget); } - spin_unlock_irqrestore(&cq->hwq.lock, flags); + spin_unlock_irqrestore(&cq->flush_lock, flags); return num_cqes - budget; } @@ -2773,11 +2719,9 @@ int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, int num_cqes, struct bnxt_qplib_qp **lib_qp) { struct cq_base *hw_cqe, **hw_cqe_ptr; - unsigned long flags; u32 sw_cons, raw_cons; int budget, rc = 0; - spin_lock_irqsave(&cq->hwq.lock, flags); raw_cons = cq->hwq.cons; budget = num_cqes; @@ -2853,20 +2797,15 @@ int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, bnxt_qplib_arm_cq(cq, DBR_DBR_TYPE_CQ); } exit: - spin_unlock_irqrestore(&cq->hwq.lock, flags); return num_cqes - budget; } void bnxt_qplib_req_notify_cq(struct bnxt_qplib_cq *cq, u32 arm_type) { - unsigned long flags; - - spin_lock_irqsave(&cq->hwq.lock, flags); if (arm_type) bnxt_qplib_arm_cq(cq, arm_type); /* Using cq->arm_state variable to track whether to issue cq handler */ atomic_set(&cq->arm_state, 1); - spin_unlock_irqrestore(&cq->hwq.lock, flags); } void bnxt_qplib_flush_cqn_wq(struct bnxt_qplib_qp *qp) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index ca0a2ffa3509..ade9f13c0fd1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -389,6 +389,18 @@ struct bnxt_qplib_cq { struct list_head sqf_head, rqf_head; atomic_t arm_state; spinlock_t compl_lock; /* synch CQ handlers */ +/* Locking Notes: + * QP can move to error state from modify_qp, async error event or error + * CQE as part of poll_cq. When QP is moved to error state, it gets added + * to two flush lists, one each for SQ and RQ. + * Each flush list is protected by qplib_cq->flush_lock. Both scq and rcq + * flush_locks should be acquired when QP is moved to error. The control path + * operations(modify_qp and async error events) are synchronized with poll_cq + * using upper level CQ locks (bnxt_re_cq->cq_lock) of both SCQ and RCQ. + * The qplib_cq->flush_lock is required to synchronize two instances of poll_cq + * of the same QP while manipulating the flush list. + */ + spinlock_t flush_lock; /* QP flush management */ }; #define BNXT_QPLIB_MAX_IRRQE_ENTRY_SIZE sizeof(struct xrrq_irrq) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 8329ec6a7946..80027a494730 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -305,9 +305,8 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, err_event->res_err_state_reason); if (!qp) break; - bnxt_qplib_acquire_cq_locks(qp, &flags); bnxt_qplib_mark_qp_error(qp); - bnxt_qplib_release_cq_locks(qp, &flags); + rcfw->aeq_handler(rcfw, qp_event, qp); break; default: /* Command Response */ @@ -460,7 +459,11 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, int rc; RCFW_CMD_PREP(req, INITIALIZE_FW, cmd_flags); - + /* Supply (log-base-2-of-host-page-size - base-page-shift) + * to bono to adjust the doorbell page sizes. + */ + req.log2_dbr_pg_size = cpu_to_le16(PAGE_SHIFT - + RCFW_DBR_BASE_PAGE_SHIFT); /* * VFs need not setup the HW context area, PF * shall setup this area for VF. Skipping the diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 6bee6e3636ea..c7cce2e4185e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -49,6 +49,7 @@ #define RCFW_COMM_SIZE 0x104 #define RCFW_DBR_PCI_BAR_REGION 2 +#define RCFW_DBR_BASE_PAGE_SHIFT 12 #define RCFW_CMD_PREP(req, CMD, cmd_flags) \ do { \ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 03057983341f..ee98e5efef84 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -139,7 +139,8 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_pkey = le32_to_cpu(sb->max_pkeys); attr->max_inline_data = le32_to_cpu(sb->max_inline_data); - attr->l2_db_size = (sb->l2_db_space_size + 1) * PAGE_SIZE; + attr->l2_db_size = (sb->l2_db_space_size + 1) * + (0x01 << RCFW_DBR_BASE_PAGE_SHIFT); attr->max_sgid = le32_to_cpu(sb->max_gid); bnxt_qplib_query_version(rcfw, attr->fw_ver); diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index 2d7ea096a247..3e5a4f760d0e 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -1761,7 +1761,30 @@ struct cmdq_initialize_fw { #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_2M (0x3UL << 4) #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8M (0x4UL << 4) #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G (0x5UL << 4) - __le16 reserved16; + /* This value is (log-base-2-of-DBR-page-size - 12). + * 0 for 4KB. HW supported values are enumerated below. + */ + __le16 log2_dbr_pg_size; + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_SFT 0 + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4K 0x0UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8K 0x1UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16K 0x2UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32K 0x3UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64K 0x4UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128K 0x5UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_256K 0x6UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_512K 0x7UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_1M 0x8UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_2M 0x9UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4M 0xaUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8M 0xbUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16M 0xcUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32M 0xdUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64M 0xeUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_LAST \ + CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M __le64 qpc_page_dir; __le64 mrw_page_dir; __le64 srq_page_dir; diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 9a566ee3ceff..82adc0d1d30e 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -601,6 +601,7 @@ static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->dlid_path_bits = 0; if (is_eth) { + wc->slid = 0; wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid); memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4); memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2); @@ -851,7 +852,6 @@ repoll: } } - wc->slid = be16_to_cpu(cqe->rlid); g_mlpath_rqpn = be32_to_cpu(cqe->g_mlpath_rqpn); wc->src_qp = g_mlpath_rqpn & 0xffffff; wc->dlid_path_bits = (g_mlpath_rqpn >> 24) & 0x7f; @@ -860,6 +860,7 @@ repoll: wc->wc_flags |= mlx4_ib_ipoib_csum_ok(cqe->status, cqe->checksum) ? IB_WC_IP_CSUM_OK : 0; if (is_eth) { + wc->slid = 0; wc->sl = be16_to_cpu(cqe->sl_vid) >> 13; if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_CVLAN_PRESENT_MASK) { @@ -871,6 +872,7 @@ repoll: memcpy(wc->smac, cqe->smac, ETH_ALEN); wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC); } else { + wc->slid = be16_to_cpu(cqe->rlid); wc->sl = be16_to_cpu(cqe->sl_vid) >> 12; wc->vlan_id = 0xffff; } diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8d2ee9322f2e..5a0e4fc4785a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -219,8 +219,6 @@ static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids, gid_tbl[i].version = 2; if (!ipv6_addr_v4mapped((struct in6_addr *)&gids[i].gid)) gid_tbl[i].type = 1; - else - memset(&gid_tbl[i].gid, 0, 12); } } @@ -366,8 +364,13 @@ static int mlx4_ib_del_gid(struct ib_device *device, if (!gids) { ret = -ENOMEM; } else { - for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) - memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid)); + for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) { + memcpy(&gids[i].gid, + &port_gid_table->gids[i].gid, + sizeof(union ib_gid)); + gids[i].gid_type = + port_gid_table->gids[i].gid_type; + } } } spin_unlock_bh(&iboe->lock); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 5b974fb97611..15457c9569a7 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -226,7 +226,6 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, wc->ex.invalidate_rkey = be32_to_cpu(cqe->imm_inval_pkey); break; } - wc->slid = be16_to_cpu(cqe->slid); wc->src_qp = be32_to_cpu(cqe->flags_rqpn) & 0xffffff; wc->dlid_path_bits = cqe->ml_path; g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; @@ -241,10 +240,12 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe, } if (ll != IB_LINK_LAYER_ETHERNET) { + wc->slid = be16_to_cpu(cqe->slid); wc->sl = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf; return; } + wc->slid = 0; vlan_present = cqe->l4_l3_hdr_type & 0x1; roce_packet_type = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0x3; if (vlan_present) { @@ -1177,7 +1178,12 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, if (ucmd.reserved0 || ucmd.reserved1) return -EINVAL; - umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size, + /* check multiplication overflow */ + if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1) + return -EINVAL; + + umem = ib_umem_get(context, ucmd.buf_addr, + (size_t)ucmd.cqe_size * entries, IB_ACCESS_LOCAL_WRITE, 1); if (IS_ERR(umem)) { err = PTR_ERR(umem); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 4236c8086820..da091de4e69d 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -245,12 +245,16 @@ struct mlx5_core_dev *mlx5_ib_get_native_port_mdev(struct mlx5_ib_dev *ibdev, struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_port *port; + if (!mlx5_core_mp_enabled(ibdev->mdev) || + ll != IB_LINK_LAYER_ETHERNET) { + if (native_port_num) + *native_port_num = ib_port_num; + return ibdev->mdev; + } + if (native_port_num) *native_port_num = 1; - if (!mlx5_core_mp_enabled(ibdev->mdev) || ll != IB_LINK_LAYER_ETHERNET) - return ibdev->mdev; - port = &ibdev->port[ib_port_num - 1]; if (!port) return NULL; @@ -3263,7 +3267,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) struct mlx5_ib_dev *ibdev; struct ib_event ibev; bool fatal = false; - u8 port = 0; + u8 port = (u8)work->param; if (mlx5_core_is_mp_slave(work->dev)) { ibdev = mlx5_ib_get_ibdev_from_mpi(work->context); @@ -3283,8 +3287,6 @@ static void mlx5_ib_handle_event(struct work_struct *_work) case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: case MLX5_DEV_EVENT_PORT_INITIALIZED: - port = (u8)work->param; - /* In RoCE, port up/down events are handled in * mlx5_netdev_event(). */ @@ -3298,24 +3300,19 @@ static void mlx5_ib_handle_event(struct work_struct *_work) case MLX5_DEV_EVENT_LID_CHANGE: ibev.event = IB_EVENT_LID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_PKEY_CHANGE: ibev.event = IB_EVENT_PKEY_CHANGE; - port = (u8)work->param; - schedule_work(&ibdev->devr.ports[port - 1].pkey_change_work); break; case MLX5_DEV_EVENT_GUID_CHANGE: ibev.event = IB_EVENT_GID_CHANGE; - port = (u8)work->param; break; case MLX5_DEV_EVENT_CLIENT_REREG: ibev.event = IB_EVENT_CLIENT_REREGISTER; - port = (u8)work->param; break; case MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT: schedule_work(&ibdev->delay_drop.delay_drop_work); @@ -3327,7 +3324,7 @@ static void mlx5_ib_handle_event(struct work_struct *_work) ibev.device = &ibdev->ib_dev; ibev.element.port_num = port; - if (port < 1 || port > ibdev->num_ports) { + if (!rdma_is_port_valid(&ibdev->ib_dev, port)) { mlx5_ib_warn(ibdev, "warning: event on port %d\n", port); goto out; } @@ -4863,19 +4860,19 @@ static int mlx5_ib_stage_ib_reg_init(struct mlx5_ib_dev *dev) return ib_register_device(&dev->ib_dev, NULL); } -static void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev) +static void mlx5_ib_stage_pre_ib_reg_umr_cleanup(struct mlx5_ib_dev *dev) { - ib_unregister_device(&dev->ib_dev); + destroy_umrc_res(dev); } -static int mlx5_ib_stage_umr_res_init(struct mlx5_ib_dev *dev) +static void mlx5_ib_stage_ib_reg_cleanup(struct mlx5_ib_dev *dev) { - return create_umr_res(dev); + ib_unregister_device(&dev->ib_dev); } -static void mlx5_ib_stage_umr_res_cleanup(struct mlx5_ib_dev *dev) +static int mlx5_ib_stage_post_ib_reg_umr_init(struct mlx5_ib_dev *dev) { - destroy_umrc_res(dev); + return create_umr_res(dev); } static int mlx5_ib_stage_delay_drop_init(struct mlx5_ib_dev *dev) @@ -4985,12 +4982,15 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_BFREG, mlx5_ib_stage_bfrag_init, mlx5_ib_stage_bfrag_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_PRE_IB_REG_UMR, + NULL, + mlx5_ib_stage_pre_ib_reg_umr_cleanup), STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_UMR_RESOURCES, - mlx5_ib_stage_umr_res_init, - mlx5_ib_stage_umr_res_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, + mlx5_ib_stage_post_ib_reg_umr_init, + NULL), STAGE_CREATE(MLX5_IB_STAGE_DELAY_DROP, mlx5_ib_stage_delay_drop_init, mlx5_ib_stage_delay_drop_cleanup), diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 139385129973..a5272499b600 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -739,8 +739,9 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_CONG_DEBUGFS, MLX5_IB_STAGE_UAR, MLX5_IB_STAGE_BFREG, + MLX5_IB_STAGE_PRE_IB_REG_UMR, MLX5_IB_STAGE_IB_REG, - MLX5_IB_STAGE_UMR_RESOURCES, + MLX5_IB_STAGE_POST_IB_REG_UMR, MLX5_IB_STAGE_DELAY_DROP, MLX5_IB_STAGE_CLASS_ATTR, MLX5_IB_STAGE_MAX, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 556e015678de..c51c602f06d6 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -838,7 +838,8 @@ static int mr_umem_get(struct ib_pd *pd, u64 start, u64 length, *umem = ib_umem_get(pd->uobject->context, start, length, access_flags, 0); err = PTR_ERR_OR_ZERO(*umem); - if (err < 0) { + if (err) { + *umem = NULL; mlx5_ib_err(dev, "umem get failed (%d)\n", err); return err; } @@ -1415,6 +1416,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, if (err) { mlx5_ib_warn(dev, "Failed to rereg UMR\n"); ib_umem_release(mr->umem); + mr->umem = NULL; clean_mr(dev, mr); return err; } @@ -1498,14 +1500,11 @@ static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) u32 key = mr->mmkey.key; err = destroy_mkey(dev, mr); - kfree(mr); if (err) { mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n", key, err); return err; } - } else { - mlx5_mr_cache_free(dev, mr); } return 0; @@ -1548,6 +1547,11 @@ static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) atomic_sub(npages, &dev->mdev->priv.reg_pages); } + if (!mr->allocated_from_cache) + kfree(mr); + else + mlx5_mr_cache_free(dev, mr); + return 0; } @@ -1816,7 +1820,6 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, mr->ibmr.iova = sg_dma_address(sg) + sg_offset; mr->ibmr.length = 0; - mr->ndescs = sg_nents; for_each_sg(sgl, sg, sg_nents, i) { if (unlikely(i >= mr->max_descs)) @@ -1828,6 +1831,7 @@ mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, sg_offset = 0; } + mr->ndescs = i; if (sg_offset_p) *sg_offset_p = sg_offset; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 39d24bf694a8..a2e1aa86e133 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1161,7 +1161,7 @@ static void destroy_raw_packet_qp_sq(struct mlx5_ib_dev *dev, ib_umem_release(sq->ubuffer.umem); } -static int get_rq_pas_size(void *qpc) +static size_t get_rq_pas_size(void *qpc) { u32 log_page_size = MLX5_GET(qpc, qpc, log_page_size) + 12; u32 log_rq_stride = MLX5_GET(qpc, qpc, log_rq_stride); @@ -1177,7 +1177,8 @@ static int get_rq_pas_size(void *qpc) } static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev, - struct mlx5_ib_rq *rq, void *qpin) + struct mlx5_ib_rq *rq, void *qpin, + size_t qpinlen) { struct mlx5_ib_qp *mqp = rq->base.container_mibqp; __be64 *pas; @@ -1186,9 +1187,12 @@ static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev, void *rqc; void *wq; void *qpc = MLX5_ADDR_OF(create_qp_in, qpin, qpc); - int inlen; + size_t rq_pas_size = get_rq_pas_size(qpc); + size_t inlen; int err; - u32 rq_pas_size = get_rq_pas_size(qpc); + + if (qpinlen < rq_pas_size + MLX5_BYTE_OFF(create_qp_in, pas)) + return -EINVAL; inlen = MLX5_ST_SZ_BYTES(create_rq_in) + rq_pas_size; in = kvzalloc(inlen, GFP_KERNEL); @@ -1277,7 +1281,7 @@ static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev, } static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, - u32 *in, + u32 *in, size_t inlen, struct ib_pd *pd) { struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp; @@ -1309,7 +1313,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, rq->flags |= MLX5_IB_RQ_CVLAN_STRIPPING; if (qp->flags & MLX5_IB_QP_PCI_WRITE_END_PADDING) rq->flags |= MLX5_IB_RQ_PCI_WRITE_END_PADDING; - err = create_raw_packet_qp_rq(dev, rq, in); + err = create_raw_packet_qp_rq(dev, rq, in, inlen); if (err) goto err_destroy_sq; @@ -1584,6 +1588,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, u32 uidx = MLX5_IB_DEFAULT_UIDX; struct mlx5_ib_create_qp ucmd; struct mlx5_ib_qp_base *base; + int mlx5_st; void *qpc; u32 *in; int err; @@ -1592,6 +1597,10 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); + mlx5_st = to_mlx5_st(init_attr->qp_type); + if (mlx5_st < 0) + return -EINVAL; + if (init_attr->rwq_ind_tbl) { if (!udata) return -ENOSYS; @@ -1753,7 +1762,7 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); - MLX5_SET(qpc, qpc, st, to_mlx5_st(init_attr->qp_type)); + MLX5_SET(qpc, qpc, st, mlx5_st); MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); if (init_attr->qp_type != MLX5_IB_QPT_REG_UMR) @@ -1867,11 +1876,16 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, } } + if (inlen < 0) { + err = -EINVAL; + goto err; + } + if (init_attr->qp_type == IB_QPT_RAW_PACKET || qp->flags & MLX5_IB_QP_UNDERLAY) { qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr; raw_packet_qp_copy_info(qp, &qp->raw_packet_qp); - err = create_raw_packet_qp(dev, qp, in, pd); + err = create_raw_packet_qp(dev, qp, in, inlen, pd); } else { err = mlx5_core_create_qp(dev->mdev, &base->mqp, in, inlen); } @@ -3095,8 +3109,10 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, goto out; if (mlx5_cur >= MLX5_QP_NUM_STATE || mlx5_new >= MLX5_QP_NUM_STATE || - !optab[mlx5_cur][mlx5_new]) + !optab[mlx5_cur][mlx5_new]) { + err = -EINVAL; goto out; + } op = optab[mlx5_cur][mlx5_new]; optpar = ib_mask_to_mlx5_opt(attr_mask); diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 6d5fadad9090..3c7522d025f2 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -241,8 +241,8 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, { struct mlx5_ib_dev *dev = to_mdev(pd->device); struct mlx5_ib_srq *srq; - int desc_size; - int buf_size; + size_t desc_size; + size_t buf_size; int err; struct mlx5_srq_attr in = {0}; __u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz); @@ -266,15 +266,18 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, desc_size = sizeof(struct mlx5_wqe_srq_next_seg) + srq->msrq.max_gs * sizeof(struct mlx5_wqe_data_seg); + if (desc_size == 0 || srq->msrq.max_gs > desc_size) + return ERR_PTR(-EINVAL); desc_size = roundup_pow_of_two(desc_size); - desc_size = max_t(int, 32, desc_size); + desc_size = max_t(size_t, 32, desc_size); + if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg)) + return ERR_PTR(-EINVAL); srq->msrq.max_avail_gather = (desc_size - sizeof(struct mlx5_wqe_srq_next_seg)) / sizeof(struct mlx5_wqe_data_seg); srq->msrq.wqe_shift = ilog2(desc_size); buf_size = srq->msrq.max * desc_size; - mlx5_ib_dbg(dev, "desc_size 0x%x, req wr 0x%x, srq size 0x%x, max_gs 0x%x, max_avail_gather 0x%x\n", - desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs, - srq->msrq.max_avail_gather); + if (buf_size < desc_size) + return ERR_PTR(-EINVAL); in.type = init_attr->srq_type; if (pd->uobject) diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 478b7317b80a..26dc374787f7 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -458,8 +458,7 @@ qedr_addr6_resolve(struct qedr_dev *dev, } return -EINVAL; } - neigh = dst_neigh_lookup(dst, &dst_in); - + neigh = dst_neigh_lookup(dst, &fl6.daddr); if (neigh) { rcu_read_lock(); if (neigh->nud_state & NUD_VALID) { @@ -494,10 +493,14 @@ int qedr_iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) qp = idr_find(&dev->qpidr, conn_param->qpn); - laddr = (struct sockaddr_in *)&cm_id->local_addr; - raddr = (struct sockaddr_in *)&cm_id->remote_addr; - laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; - raddr6 = (struct sockaddr_in6 *)&cm_id->remote_addr; + laddr = (struct sockaddr_in *)&cm_id->m_local_addr; + raddr = (struct sockaddr_in *)&cm_id->m_remote_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr; + raddr6 = (struct sockaddr_in6 *)&cm_id->m_remote_addr; + + DP_DEBUG(dev, QEDR_MSG_IWARP, "MAPPED %d %d\n", + ntohs(((struct sockaddr_in *)&cm_id->remote_addr)->sin_port), + ntohs(raddr->sin_port)); DP_DEBUG(dev, QEDR_MSG_IWARP, "Connect source address: %pISpc, remote address: %pISpc\n", @@ -599,8 +602,8 @@ int qedr_iw_create_listen(struct iw_cm_id *cm_id, int backlog) int rc; int i; - laddr = (struct sockaddr_in *)&cm_id->local_addr; - laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr; + laddr = (struct sockaddr_in *)&cm_id->m_local_addr; + laddr6 = (struct sockaddr_in6 *)&cm_id->m_local_addr; DP_DEBUG(dev, QEDR_MSG_IWARP, "Create Listener address: %pISpc\n", &cm_id->local_addr); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 53f00dbf313f..875b17272d65 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -3034,6 +3034,11 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, switch (wr->opcode) { case IB_WR_SEND_WITH_IMM: + if (unlikely(rdma_protocol_iwarp(&dev->ibdev, 1))) { + rc = -EINVAL; + *bad_wr = wr; + break; + } wqe->req_type = RDMA_SQ_REQ_TYPE_SEND_WITH_IMM; swqe = (struct rdma_sq_send_wqe_1st *)wqe; swqe->wqe_size = 2; @@ -3075,6 +3080,11 @@ static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, break; case IB_WR_RDMA_WRITE_WITH_IMM: + if (unlikely(rdma_protocol_iwarp(&dev->ibdev, 1))) { + rc = -EINVAL; + *bad_wr = wr; + break; + } wqe->req_type = RDMA_SQ_REQ_TYPE_RDMA_WR_WITH_IMM; rwqe = (struct rdma_sq_rdma_wqe_1st *)wqe; @@ -3724,7 +3734,7 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) { struct qedr_dev *dev = get_qedr_dev(ibcq->device); struct qedr_cq *cq = get_qedr_cq(ibcq); - union rdma_cqe *cqe = cq->latest_cqe; + union rdma_cqe *cqe; u32 old_cons, new_cons; unsigned long flags; int update = 0; @@ -3741,6 +3751,7 @@ int qedr_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) return qedr_gsi_poll_cq(ibcq, num_entries, wc); spin_lock_irqsave(&cq->cq_lock, flags); + cqe = cq->latest_cqe; old_cons = qed_chain_get_cons_idx_u32(&cq->pbl); while (num_entries && is_valid_cqe(cq, cqe)) { struct qedr_qp *qp; diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 1b2e5362a3ff..cc429b567d0a 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -489,11 +489,13 @@ static int rvt_check_refs(struct rvt_mregion *mr, const char *t) unsigned long timeout; struct rvt_dev_info *rdi = ib_to_rvt(mr->pd->device); - if (percpu_ref_is_zero(&mr->refcount)) - return 0; - /* avoid dma mr */ - if (mr->lkey) + if (mr->lkey) { + /* avoid dma mr */ rvt_dereg_clean_qps(mr); + /* @mr was indexed on rcu protected @lkey_table */ + synchronize_rcu(); + } + timeout = wait_for_completion_timeout(&mr->comp, 5 * HZ); if (!timeout) { rvt_pr_err(rdi, diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 1f316d66e6f7..41614c185918 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -218,8 +218,10 @@ static void matrix_keypad_stop(struct input_dev *dev) { struct matrix_keypad *keypad = input_get_drvdata(dev); + spin_lock_irq(&keypad->lock); keypad->stopped = true; - mb(); + spin_unlock_irq(&keypad->lock); + flush_work(&keypad->work.work); /* * matrix_keypad_scan() will leave IRQs enabled; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 3d2e23a0ae39..a246fc686bb7 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -173,7 +173,6 @@ static const char * const smbus_pnp_ids[] = { "LEN0046", /* X250 */ "LEN004a", /* W541 */ "LEN200f", /* T450s */ - "LEN2018", /* T460p */ NULL }; diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c index db4f6bb502e3..a5ab774da4cc 100644 --- a/drivers/input/touchscreen/mms114.c +++ b/drivers/input/touchscreen/mms114.c @@ -1,11 +1,8 @@ -/* - * Copyright (C) 2012 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim <jy0922.shim@samsung.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ +// SPDX-License-Identifier: GPL-2.0 +// Melfas MMS114/MMS152 touchscreen device driver +// +// Copyright (c) 2012 Samsung Electronics Co., Ltd. +// Author: Joonyoung Shim <jy0922.shim@samsung.com> #include <linux/module.h> #include <linux/delay.h> @@ -624,4 +621,4 @@ module_i2c_driver(mms114_driver); /* Module information */ MODULE_AUTHOR("Joonyoung Shim <jy0922.shim@samsung.com>"); MODULE_DESCRIPTION("MELFAS mms114 Touchscreen driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 1d3056f53747..2cbb19cddbf8 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1412,7 +1412,7 @@ static struct irq_chip its_irq_chip = { * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations. */ #define IRQS_PER_CHUNK_SHIFT 5 -#define IRQS_PER_CHUNK (1 << IRQS_PER_CHUNK_SHIFT) +#define IRQS_PER_CHUNK (1UL << IRQS_PER_CHUNK_SHIFT) #define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */ static unsigned long *lpi_bitmap; @@ -2119,11 +2119,10 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, dev = kzalloc(sizeof(*dev), GFP_KERNEL); /* - * At least one bit of EventID is being used, hence a minimum - * of two entries. No, the architecture doesn't let you - * express an ITT with a single entry. + * We allocate at least one chunk worth of LPIs bet device, + * and thus that many ITEs. The device may require less though. */ - nr_ites = max(2UL, roundup_pow_of_two(nvecs)); + nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs)); sz = nr_ites * its->ite_size; sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1; itt = kzalloc(sz, GFP_KERNEL); @@ -2495,7 +2494,7 @@ static int its_vpe_set_affinity(struct irq_data *d, static void its_vpe_schedule(struct its_vpe *vpe) { - void * __iomem vlpi_base = gic_data_rdist_vlpi_base(); + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); u64 val; /* Schedule the VPE */ @@ -2527,7 +2526,7 @@ static void its_vpe_schedule(struct its_vpe *vpe) static void its_vpe_deschedule(struct its_vpe *vpe) { - void * __iomem vlpi_base = gic_data_rdist_vlpi_base(); + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); u32 count = 1000000; /* 1s! */ bool clean; u64 val; diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index 675eda5ff2b8..4760307ab43f 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -28,20 +28,6 @@ struct gpcv2_irqchip_data { static struct gpcv2_irqchip_data *imx_gpcv2_instance; -/* - * Interface for the low level wakeup code. - */ -u32 imx_gpcv2_get_wakeup_source(u32 **sources) -{ - if (!imx_gpcv2_instance) - return 0; - - if (sources) - *sources = imx_gpcv2_instance->wakeup_sources; - - return IMR_NUM; -} - static int gpcv2_wakeup_source_save(void) { struct gpcv2_irqchip_data *cd; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 1a46b41dac70..6422846b546e 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -659,11 +659,11 @@ static void do_bio_hook(struct search *s, struct bio *orig_bio) static void search_free(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); - bio_complete(s); if (s->iop.bio) bio_put(s->iop.bio); + bio_complete(s); closure_debug_destroy(cl); mempool_free(s, s->d->c->search); } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 312895788036..f2273143b3cb 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -963,6 +963,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, uint32_t rtime = cpu_to_le32(get_seconds()); struct uuid_entry *u; char buf[BDEVNAME_SIZE]; + struct cached_dev *exist_dc, *t; bdevname(dc->bdev, buf); @@ -987,6 +988,16 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, return -EINVAL; } + /* Check whether already attached */ + list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) { + if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) { + pr_err("Tried to attach %s but duplicate UUID already attached", + buf); + + return -EINVAL; + } + } + u = uuid_find(c, dc->sb.uuid); if (u && @@ -1204,7 +1215,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page, return; err: - pr_notice("error opening %s: %s", bdevname(bdev, name), err); + pr_notice("error %s: %s", bdevname(bdev, name), err); bcache_device_stop(&dc->disk); } @@ -1274,7 +1285,7 @@ static int flash_devs_run(struct cache_set *c) struct uuid_entry *u; for (u = c->uuids; - u < c->uuids + c->devices_max_used && !ret; + u < c->uuids + c->nr_uuids && !ret; u++) if (UUID_FLASH_ONLY(u)) ret = flash_dev_run(c, u); @@ -1883,6 +1894,8 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, const char *err = NULL; /* must be set for any error case */ int ret = 0; + bdevname(bdev, name); + memcpy(&ca->sb, sb, sizeof(struct cache_sb)); ca->bdev = bdev; ca->bdev->bd_holder = ca; @@ -1891,11 +1904,12 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, bio_first_bvec_all(&ca->sb_bio)->bv_page = sb_page; get_page(sb_page); - if (blk_queue_discard(bdev_get_queue(ca->bdev))) + if (blk_queue_discard(bdev_get_queue(bdev))) ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); if (ret != 0) { + blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; else @@ -1918,14 +1932,14 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, goto out; } - pr_info("registered cache device %s", bdevname(bdev, name)); + pr_info("registered cache device %s", name); out: kobject_put(&ca->kobj); err: if (err) - pr_notice("error opening %s: %s", bdevname(bdev, name), err); + pr_notice("error %s: %s", name, err); return ret; } @@ -2014,6 +2028,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (err) goto err_close; + err = "failed to register device"; if (SB_IS_BDEV(sb)) { struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL); if (!dc) @@ -2028,7 +2043,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, goto err_close; if (register_cache(sb, sb_page, bdev, ca) != 0) - goto err_close; + goto err; } out: if (sb_page) @@ -2041,7 +2056,7 @@ out: err_close: blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); err: - pr_info("error opening %s: %s", path, err); + pr_info("error %s: %s", path, err); ret = -EINVAL; goto out; } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 414c9af54ded..aa2032fa80d4 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -386,9 +386,6 @@ static void __cache_size_refresh(void) static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, enum data_mode *data_mode) { - unsigned noio_flag; - void *ptr; - if (c->block_size <= DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT) { *data_mode = DATA_MODE_SLAB; return kmem_cache_alloc(DM_BUFIO_CACHE(c), gfp_mask); @@ -412,16 +409,15 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, * all allocations done by this process (including pagetables) are done * as if GFP_NOIO was specified. */ + if (gfp_mask & __GFP_NORETRY) { + unsigned noio_flag = memalloc_noio_save(); + void *ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); - if (gfp_mask & __GFP_NORETRY) - noio_flag = memalloc_noio_save(); - - ptr = __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); - - if (gfp_mask & __GFP_NORETRY) memalloc_noio_restore(noio_flag); + return ptr; + } - return ptr; + return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); } /* diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 7d3e572072f5..a05a560d3cba 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -211,29 +211,27 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m) else m->queue_mode = DM_TYPE_REQUEST_BASED; - } else if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) { + } else if (m->queue_mode == DM_TYPE_BIO_BASED) { INIT_WORK(&m->process_queued_bios, process_queued_bios); - - if (m->queue_mode == DM_TYPE_BIO_BASED) { - /* - * bio-based doesn't support any direct scsi_dh management; - * it just discovers if a scsi_dh is attached. - */ - set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); - } - } - - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) { - set_bit(MPATHF_QUEUE_IO, &m->flags); - atomic_set(&m->pg_init_in_progress, 0); - atomic_set(&m->pg_init_count, 0); - m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT; - init_waitqueue_head(&m->pg_init_wait); + /* + * bio-based doesn't support any direct scsi_dh management; + * it just discovers if a scsi_dh is attached. + */ + set_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags); } dm_table_set_type(ti->table, m->queue_mode); + /* + * Init fields that are only used when a scsi_dh is attached + * - must do this unconditionally (really doesn't hurt non-SCSI uses) + */ + set_bit(MPATHF_QUEUE_IO, &m->flags); + atomic_set(&m->pg_init_in_progress, 0); + atomic_set(&m->pg_init_count, 0); + m->pg_init_delay_msecs = DM_PG_INIT_DELAY_DEFAULT; + init_waitqueue_head(&m->pg_init_wait); + return 0; } @@ -337,9 +335,6 @@ static void __switch_pg(struct multipath *m, struct priority_group *pg) { m->current_pg = pg; - if (m->queue_mode == DM_TYPE_NVME_BIO_BASED) - return; - /* Must we initialise the PG first, and queue I/O till it's ready? */ if (m->hw_handler_name) { set_bit(MPATHF_PG_INIT_REQUIRED, &m->flags); @@ -385,8 +380,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes) unsigned bypassed = 1; if (!atomic_read(&m->nr_valid_paths)) { - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) - clear_bit(MPATHF_QUEUE_IO, &m->flags); + clear_bit(MPATHF_QUEUE_IO, &m->flags); goto failed; } @@ -599,7 +593,7 @@ static struct pgpath *__map_bio(struct multipath *m, struct bio *bio) return pgpath; } -static struct pgpath *__map_bio_nvme(struct multipath *m, struct bio *bio) +static struct pgpath *__map_bio_fast(struct multipath *m, struct bio *bio) { struct pgpath *pgpath; unsigned long flags; @@ -634,8 +628,8 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, { struct pgpath *pgpath; - if (m->queue_mode == DM_TYPE_NVME_BIO_BASED) - pgpath = __map_bio_nvme(m, bio); + if (!m->hw_handler_name) + pgpath = __map_bio_fast(m, bio); else pgpath = __map_bio(m, bio); @@ -675,8 +669,7 @@ static void process_queued_io_list(struct multipath *m) { if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED) dm_mq_kick_requeue_list(dm_table_get_md(m->ti->table)); - else if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) + else if (m->queue_mode == DM_TYPE_BIO_BASED) queue_work(kmultipathd, &m->process_queued_bios); } @@ -811,15 +804,14 @@ static int parse_path_selector(struct dm_arg_set *as, struct priority_group *pg, return 0; } -static int setup_scsi_dh(struct block_device *bdev, struct multipath *m, char **error) +static int setup_scsi_dh(struct block_device *bdev, struct multipath *m, + const char *attached_handler_name, char **error) { struct request_queue *q = bdev_get_queue(bdev); - const char *attached_handler_name; int r; if (test_bit(MPATHF_RETAIN_ATTACHED_HW_HANDLER, &m->flags)) { retain: - attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL); if (attached_handler_name) { /* * Clear any hw_handler_params associated with a @@ -873,6 +865,8 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps int r; struct pgpath *p; struct multipath *m = ti->private; + struct request_queue *q; + const char *attached_handler_name; /* we need at least a path arg */ if (as->argc < 1) { @@ -891,9 +885,11 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps goto bad; } - if (m->queue_mode != DM_TYPE_NVME_BIO_BASED) { + q = bdev_get_queue(p->path.dev->bdev); + attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL); + if (attached_handler_name) { INIT_DELAYED_WORK(&p->activate_path, activate_path_work); - r = setup_scsi_dh(p->path.dev->bdev, m, &ti->error); + r = setup_scsi_dh(p->path.dev->bdev, m, attached_handler_name, &ti->error); if (r) { dm_put_device(ti, p->path.dev); goto bad; @@ -1001,8 +997,7 @@ static int parse_hw_handler(struct dm_arg_set *as, struct multipath *m) if (!hw_argc) return 0; - if (m->queue_mode == DM_TYPE_BIO_BASED || - m->queue_mode == DM_TYPE_NVME_BIO_BASED) { + if (m->queue_mode == DM_TYPE_BIO_BASED) { dm_consume_args(as, hw_argc); DMERR("bio-based multipath doesn't allow hardware handler args"); return 0; @@ -1091,8 +1086,6 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) if (!strcasecmp(queue_mode_name, "bio")) m->queue_mode = DM_TYPE_BIO_BASED; - else if (!strcasecmp(queue_mode_name, "nvme")) - m->queue_mode = DM_TYPE_NVME_BIO_BASED; else if (!strcasecmp(queue_mode_name, "rq")) m->queue_mode = DM_TYPE_REQUEST_BASED; else if (!strcasecmp(queue_mode_name, "mq")) @@ -1193,7 +1186,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->num_discard_bios = 1; ti->num_write_same_bios = 1; ti->num_write_zeroes_bios = 1; - if (m->queue_mode == DM_TYPE_BIO_BASED || m->queue_mode == DM_TYPE_NVME_BIO_BASED) + if (m->queue_mode == DM_TYPE_BIO_BASED) ti->per_io_data_size = multipath_per_bio_data_size(); else ti->per_io_data_size = sizeof(struct dm_mpath_io); @@ -1730,9 +1723,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, case DM_TYPE_BIO_BASED: DMEMIT("queue_mode bio "); break; - case DM_TYPE_NVME_BIO_BASED: - DMEMIT("queue_mode nvme "); - break; case DM_TYPE_MQ_REQUEST_BASED: DMEMIT("queue_mode mq "); break; @@ -2030,8 +2020,9 @@ static int multipath_busy(struct dm_target *ti) *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 12, 0}, - .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE, + .version = {1, 13, 0}, + .features = DM_TARGET_SINGLETON | DM_TARGET_IMMUTABLE | + DM_TARGET_PASSES_INTEGRITY, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 7ef469e902c6..c1d1034ff7b7 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3408,9 +3408,10 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - if (test_bit(MD_RECOVERY_NEEDED, &recovery) || - test_bit(MD_RECOVERY_RESHAPE, &recovery) || - test_bit(MD_RECOVERY_RUNNING, &recovery)) + if (!test_bit(MD_RECOVERY_INTR, &recovery) && + (test_bit(MD_RECOVERY_NEEDED, &recovery) || + test_bit(MD_RECOVERY_RESHAPE, &recovery) || + test_bit(MD_RECOVERY_RUNNING, &recovery))) r = mddev->curr_resync_completed; else r = mddev->recovery_cp; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 5fe7ec356c33..7eb3e2a3c07d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -942,17 +942,12 @@ static int dm_table_determine_type(struct dm_table *t) if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ - if (t->type == DM_TYPE_BIO_BASED) - return 0; - else if (t->type == DM_TYPE_NVME_BIO_BASED) { - if (!dm_table_does_not_support_partial_completion(t)) { - DMERR("nvme bio-based is only possible with devices" - " that don't support partial completion"); - return -EINVAL; - } - /* Fallthru, also verify all devices are blk-mq */ + if (t->type == DM_TYPE_BIO_BASED) { + /* possibly upgrade to a variant of bio-based */ + goto verify_bio_based; } BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED); + BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED); goto verify_rq_based; } @@ -985,6 +980,7 @@ static int dm_table_determine_type(struct dm_table *t) } if (bio_based) { +verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; if (dm_table_supports_dax(t) || @@ -1755,7 +1751,7 @@ static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev char b[BDEVNAME_SIZE]; /* For now, NVMe devices are the only devices of this class */ - return (strncmp(bdevname(dev->bdev, b), "nvme", 3) == 0); + return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0); } static bool dm_table_does_not_support_partial_completion(struct dm_table *t) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 68136806d365..45328d8b2859 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -458,9 +458,11 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } -static int dm_grab_bdev_for_ioctl(struct mapped_device *md, - struct block_device **bdev, - fmode_t *mode) +static char *_dm_claim_ptr = "I belong to device-mapper"; + +static int dm_get_bdev_for_ioctl(struct mapped_device *md, + struct block_device **bdev, + fmode_t *mode) { struct dm_target *tgt; struct dm_table *map; @@ -490,6 +492,10 @@ retry: goto out; bdgrab(*bdev); + r = blkdev_get(*bdev, *mode, _dm_claim_ptr); + if (r < 0) + goto out; + dm_put_live_table(md, srcu_idx); return r; @@ -508,7 +514,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, struct mapped_device *md = bdev->bd_disk->private_data; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -528,7 +534,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, r = __blkdev_driver_ioctl(bdev, mode, cmd, arg); out: - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -708,14 +714,13 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU) static int open_table_device(struct table_device *td, dev_t dev, struct mapped_device *md) { - static char *_claim_ptr = "I belong to device-mapper"; struct block_device *bdev; int r; BUG_ON(td->dm_dev.bdev); - bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _claim_ptr); + bdev = blkdev_get_by_dev(dev, td->dm_dev.mode | FMODE_EXCL, _dm_claim_ptr); if (IS_ERR(bdev)) return PTR_ERR(bdev); @@ -3011,7 +3016,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3021,7 +3026,7 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3032,7 +3037,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3042,7 +3047,7 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3054,7 +3059,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3064,7 +3069,7 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } @@ -3075,7 +3080,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key) fmode_t mode; int r; - r = dm_grab_bdev_for_ioctl(md, &bdev, &mode); + r = dm_get_bdev_for_ioctl(md, &bdev, &mode); if (r < 0) return r; @@ -3085,7 +3090,7 @@ static int dm_pr_clear(struct block_device *bdev, u64 key) else r = -EOPNOTSUPP; - bdput(bdev); + blkdev_put(bdev, mode); return r; } diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index e40065bdbfc8..0a7e99d62c69 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -157,7 +157,7 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev) seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); } rcu_read_unlock(); - seq_printf (seq, "]"); + seq_putc(seq, ']'); } static int multipath_congested(struct mddev *mddev, int bits) diff --git a/drivers/md/md.c b/drivers/md/md.c index bc67ab6844f0..254e44e44668 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -801,6 +801,9 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio; int ff = 0; + if (!page) + return; + if (test_bit(Faulty, &rdev->flags)) return; @@ -5452,6 +5455,7 @@ int md_run(struct mddev *mddev) * the only valid external interface is through the md * device. */ + mddev->has_superblocks = false; rdev_for_each(rdev, mddev) { if (test_bit(Faulty, &rdev->flags)) continue; @@ -5465,6 +5469,9 @@ int md_run(struct mddev *mddev) set_disk_ro(mddev->gendisk, 1); } + if (rdev->sb_page) + mddev->has_superblocks = true; + /* perform some consistency tests on the device. * We don't want the data to overlap the metadata, * Internal Bitmap issues have been handled elsewhere. @@ -5497,8 +5504,10 @@ int md_run(struct mddev *mddev) } if (mddev->sync_set == NULL) { mddev->sync_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (!mddev->sync_set) - return -ENOMEM; + if (!mddev->sync_set) { + err = -ENOMEM; + goto abort; + } } spin_lock(&pers_lock); @@ -5511,7 +5520,8 @@ int md_run(struct mddev *mddev) else pr_warn("md: personality for level %s is not loaded!\n", mddev->clevel); - return -EINVAL; + err = -EINVAL; + goto abort; } spin_unlock(&pers_lock); if (mddev->level != pers->level) { @@ -5524,7 +5534,8 @@ int md_run(struct mddev *mddev) pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ module_put(pers->owner); - return -EINVAL; + err = -EINVAL; + goto abort; } if (pers->sync_request) { @@ -5593,7 +5604,7 @@ int md_run(struct mddev *mddev) mddev->private = NULL; module_put(pers->owner); bitmap_destroy(mddev); - return err; + goto abort; } if (mddev->queue) { bool nonrot = true; @@ -5655,6 +5666,18 @@ int md_run(struct mddev *mddev) sysfs_notify_dirent_safe(mddev->sysfs_action); sysfs_notify(&mddev->kobj, NULL, "degraded"); return 0; + +abort: + if (mddev->bio_set) { + bioset_free(mddev->bio_set); + mddev->bio_set = NULL; + } + if (mddev->sync_set) { + bioset_free(mddev->sync_set); + mddev->sync_set = NULL; + } + + return err; } EXPORT_SYMBOL_GPL(md_run); @@ -8049,6 +8072,7 @@ EXPORT_SYMBOL(md_done_sync); bool md_write_start(struct mddev *mddev, struct bio *bi) { int did_change = 0; + if (bio_data_dir(bi) != WRITE) return true; @@ -8081,6 +8105,8 @@ bool md_write_start(struct mddev *mddev, struct bio *bi) rcu_read_unlock(); if (did_change) sysfs_notify_dirent_safe(mddev->sysfs_state); + if (!mddev->has_superblocks) + return true; wait_event(mddev->sb_wait, !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) || mddev->suspended); @@ -8543,6 +8569,19 @@ void md_do_sync(struct md_thread *thread) set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_PENDING) | BIT(MD_SB_CHANGE_DEVS)); + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + !test_bit(MD_RECOVERY_INTR, &mddev->recovery) && + mddev->delta_disks > 0 && + mddev->pers->finish_reshape && + mddev->pers->size && + mddev->queue) { + mddev_lock_nointr(mddev); + md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); + mddev_unlock(mddev); + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + } + spin_lock(&mddev->lock); if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { /* We completed so min/max setting can be forgotten if used. */ @@ -8569,6 +8608,10 @@ static int remove_and_add_spares(struct mddev *mddev, int removed = 0; bool remove_some = false; + if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + /* Mustn't remove devices when resync thread is running */ + return 0; + rdev_for_each(rdev, mddev) { if ((this == NULL || rdev == this) && rdev->raid_disk >= 0 && diff --git a/drivers/md/md.h b/drivers/md/md.h index 58cd20a5e85e..fbc925cce810 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -468,6 +468,8 @@ struct mddev { void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; unsigned int good_device_nr; /* good device num within cluster raid */ + + bool has_superblocks:1; }; enum recovery_flags { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index f978eddc7a21..fe872dc6712e 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1809,6 +1809,17 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct md_rdev *repl = conf->mirrors[conf->raid_disks + number].rdev; freeze_array(conf, 0); + if (atomic_read(&repl->nr_pending)) { + /* It means that some queued IO of retry_list + * hold repl. Thus, we cannot set replacement + * as NULL, avoiding rdev NULL pointer + * dereference in sync_request_write and + * handle_write_finished. + */ + err = -EBUSY; + unfreeze_array(conf); + goto abort; + } clear_bit(Replacement, &repl->flags); p->rdev = repl; conf->mirrors[conf->raid_disks + number].rdev = NULL; diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index c7294e7557e0..eb84bc68e2fd 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -26,6 +26,18 @@ #define BARRIER_BUCKETS_NR_BITS (PAGE_SHIFT - ilog2(sizeof(atomic_t))) #define BARRIER_BUCKETS_NR (1<<BARRIER_BUCKETS_NR_BITS) +/* Note: raid1_info.rdev can be set to NULL asynchronously by raid1_remove_disk. + * There are three safe ways to access raid1_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery is known to be happening - i.e. in code that is + * called as part of performing resync/recovery. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the + * RCU lock. + * When .rdev is set to NULL, the nr_pending count checked again and if it has + * been incremented, the pointer is put back in .rdev. + */ + struct raid1_info { struct md_rdev *rdev; sector_t head_position; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 99c9207899a7..c5e6c60fc0d4 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -141,7 +141,7 @@ static void r10bio_pool_free(void *r10_bio, void *data) #define RESYNC_WINDOW (1024*1024) /* maximum number of concurrent requests, memory permitting */ #define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE) -#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW) +#define CLUSTER_RESYNC_WINDOW (32 * RESYNC_WINDOW) #define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9) /* @@ -2655,7 +2655,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) for (m = 0; m < conf->copies; m++) { int dev = r10_bio->devs[m].devnum; rdev = conf->mirrors[dev].rdev; - if (r10_bio->devs[m].bio == NULL) + if (r10_bio->devs[m].bio == NULL || + r10_bio->devs[m].bio->bi_end_io == NULL) continue; if (!r10_bio->devs[m].bio->bi_status) { rdev_clear_badblocks( @@ -2670,7 +2671,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) md_error(conf->mddev, rdev); } rdev = conf->mirrors[dev].replacement; - if (r10_bio->devs[m].repl_bio == NULL) + if (r10_bio->devs[m].repl_bio == NULL || + r10_bio->devs[m].repl_bio->bi_end_io == NULL) continue; if (!r10_bio->devs[m].repl_bio->bi_status) { @@ -3782,7 +3784,7 @@ static int raid10_run(struct mddev *mddev) if (fc > 1 || fo > 0) { pr_err("only near layout is supported by clustered" " raid10\n"); - goto out; + goto out_free_conf; } } @@ -4830,17 +4832,11 @@ static void raid10_finish_reshape(struct mddev *mddev) return; if (mddev->delta_disks > 0) { - sector_t size = raid10_size(mddev, 0, 0); - md_set_array_sectors(mddev, size); if (mddev->recovery_cp > mddev->resync_max_sectors) { mddev->recovery_cp = mddev->resync_max_sectors; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } - mddev->resync_max_sectors = size; - if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); - } + mddev->resync_max_sectors = mddev->array_sectors; } else { int d; rcu_read_lock(); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index db2ac22ac1b4..e2e8840de9bf 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -2,6 +2,19 @@ #ifndef _RAID10_H #define _RAID10_H +/* Note: raid10_info.rdev can be set to NULL asynchronously by + * raid10_remove_disk. + * There are three safe ways to access raid10_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery/reshape is known to be happening - i.e. in code + * that is called as part of performing resync/recovery/reshape. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the + * RCU lock. + * When .rdev is set to NULL, the nr_pending count checked again and if it has + * been incremented, the pointer is put back in .rdev. + */ + struct raid10_info { struct md_rdev *rdev, *replacement; sector_t head_position; diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index 0c76bcedfc1c..a001808a2b77 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -44,6 +44,7 @@ extern void ppl_write_stripe_run(struct r5conf *conf); extern void ppl_stripe_write_finished(struct stripe_head *sh); extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); extern void ppl_quiesce(struct r5conf *conf, int quiesce); +extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio); static inline bool raid5_has_ppl(struct r5conf *conf) { @@ -104,7 +105,7 @@ static inline int log_handle_flush_request(struct r5conf *conf, struct bio *bio) if (conf->log) ret = r5l_handle_flush_request(conf->log, bio); else if (raid5_has_ppl(conf)) - ret = 0; + ret = ppl_handle_flush_request(conf->log, bio); return ret; } diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index 2764c2290062..42890a08375b 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -693,6 +693,16 @@ void ppl_quiesce(struct r5conf *conf, int quiesce) } } +int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio) +{ + if (bio->bi_iter.bi_size == 0) { + bio_endio(bio); + return 0; + } + bio->bi_opf &= ~REQ_PREFLUSH; + return -EAGAIN; +} + void ppl_stripe_write_finished(struct stripe_head *sh) { struct ppl_io_unit *io; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 50d01144b805..b5d2601483e3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2196,15 +2196,16 @@ static int grow_one_stripe(struct r5conf *conf, gfp_t gfp) static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; + size_t namelen = sizeof(conf->cache_name[0]); int devs = max(conf->raid_disks, conf->previous_raid_disks); if (conf->mddev->gendisk) - sprintf(conf->cache_name[0], + snprintf(conf->cache_name[0], namelen, "raid%d-%s", conf->level, mdname(conf->mddev)); else - sprintf(conf->cache_name[0], + snprintf(conf->cache_name[0], namelen, "raid%d-%p", conf->level, conf->mddev); - sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]); + snprintf(conf->cache_name[1], namelen, "%.27s-alt", conf->cache_name[0]); conf->active_name = 0; sc = kmem_cache_create(conf->cache_name[conf->active_name], @@ -6764,9 +6765,7 @@ static void free_conf(struct r5conf *conf) log_exit(conf); - if (conf->shrinker.nr_deferred) - unregister_shrinker(&conf->shrinker); - + unregister_shrinker(&conf->shrinker); free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); @@ -8001,13 +8000,7 @@ static void raid5_finish_reshape(struct mddev *mddev) if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { - if (mddev->delta_disks > 0) { - md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); - if (mddev->queue) { - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); - } - } else { + if (mddev->delta_disks <= 0) { int d; spin_lock_irq(&conf->device_lock); mddev->degraded = raid5_calc_degraded(conf); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 2e6123825095..3f8da26032ac 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -450,6 +450,18 @@ enum { * HANDLE gets cleared if stripe_handle leaves nothing locked. */ +/* Note: disk_info.rdev can be set to NULL asynchronously by raid5_remove_disk. + * There are three safe ways to access disk_info.rdev. + * 1/ when holding mddev->reconfig_mutex + * 2/ when resync/recovery/reshape is known to be happening - i.e. in code that + * is called as part of performing resync/recovery/reshape. + * 3/ while holding rcu_read_lock(), use rcu_dereference to get the pointer + * and if it is non-NULL, increment rdev->nr_pending before dropping the RCU + * lock. + * When .rdev is set to NULL, the nr_pending count checked again and if + * it has been incremented, the pointer is put back in .rdev. + */ + struct disk_info { struct md_rdev *rdev, *replacement; struct page *extra_page; /* extra page to use in prexor */ diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig index 145e12bfb819..86c1a190d946 100644 --- a/drivers/media/Kconfig +++ b/drivers/media/Kconfig @@ -147,9 +147,11 @@ config DVB_CORE config DVB_MMAP bool "Enable DVB memory-mapped API (EXPERIMENTAL)" depends on DVB_CORE + depends on VIDEO_V4L2=y || VIDEO_V4L2=DVB_CORE + select VIDEOBUF2_VMALLOC default n help - This option enables DVB experimental memory-mapped API, with + This option enables DVB experimental memory-mapped API, which reduces the number of context switches to read DVB buffers, as the buffers can use mmap() syscalls. diff --git a/drivers/media/common/videobuf2/Kconfig b/drivers/media/common/videobuf2/Kconfig index 5df05250de94..17c32ea58395 100644 --- a/drivers/media/common/videobuf2/Kconfig +++ b/drivers/media/common/videobuf2/Kconfig @@ -3,6 +3,9 @@ config VIDEOBUF2_CORE select DMA_SHARED_BUFFER tristate +config VIDEOBUF2_V4L2 + tristate + config VIDEOBUF2_MEMOPS tristate select FRAME_VECTOR diff --git a/drivers/media/common/videobuf2/Makefile b/drivers/media/common/videobuf2/Makefile index 19de5ccda20b..77bebe8b202f 100644 --- a/drivers/media/common/videobuf2/Makefile +++ b/drivers/media/common/videobuf2/Makefile @@ -1,5 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +videobuf2-common-objs := videobuf2-core.o -obj-$(CONFIG_VIDEOBUF2_CORE) += videobuf2-core.o videobuf2-v4l2.o +ifeq ($(CONFIG_TRACEPOINTS),y) + videobuf2-common-objs += vb2-trace.o +endif + +obj-$(CONFIG_VIDEOBUF2_CORE) += videobuf2-common.o +obj-$(CONFIG_VIDEOBUF2_V4L2) += videobuf2-v4l2.o obj-$(CONFIG_VIDEOBUF2_MEMOPS) += videobuf2-memops.o obj-$(CONFIG_VIDEOBUF2_VMALLOC) += videobuf2-vmalloc.o obj-$(CONFIG_VIDEOBUF2_DMA_CONTIG) += videobuf2-dma-contig.o diff --git a/drivers/media/v4l2-core/vb2-trace.c b/drivers/media/common/videobuf2/vb2-trace.c index 4c0f39d271f0..4c0f39d271f0 100644 --- a/drivers/media/v4l2-core/vb2-trace.c +++ b/drivers/media/common/videobuf2/vb2-trace.c diff --git a/drivers/media/dvb-core/Makefile b/drivers/media/dvb-core/Makefile index 3a105d82019a..62b028ded9f7 100644 --- a/drivers/media/dvb-core/Makefile +++ b/drivers/media/dvb-core/Makefile @@ -4,7 +4,7 @@ # dvb-net-$(CONFIG_DVB_NET) := dvb_net.o -dvb-vb2-$(CONFIG_DVB_MMSP) := dvb_vb2.o +dvb-vb2-$(CONFIG_DVB_MMAP) := dvb_vb2.o dvb-core-objs := dvbdev.o dmxdev.o dvb_demux.o \ dvb_ca_en50221.o dvb_frontend.o \ diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c index 6d53af00190e..61a750fae465 100644 --- a/drivers/media/dvb-core/dmxdev.c +++ b/drivers/media/dvb-core/dmxdev.c @@ -128,11 +128,7 @@ static int dvb_dvr_open(struct inode *inode, struct file *file) struct dvb_device *dvbdev = file->private_data; struct dmxdev *dmxdev = dvbdev->priv; struct dmx_frontend *front; -#ifndef DVB_MMAP bool need_ringbuffer = false; -#else - const bool need_ringbuffer = true; -#endif dprintk("%s\n", __func__); @@ -144,17 +140,31 @@ static int dvb_dvr_open(struct inode *inode, struct file *file) return -ENODEV; } -#ifndef DVB_MMAP + dmxdev->may_do_mmap = 0; + + /* + * The logic here is a little tricky due to the ifdef. + * + * The ringbuffer is used for both read and mmap. + * + * It is not needed, however, on two situations: + * - Write devices (access with O_WRONLY); + * - For duplex device nodes, opened with O_RDWR. + */ + if ((file->f_flags & O_ACCMODE) == O_RDONLY) need_ringbuffer = true; -#else - if ((file->f_flags & O_ACCMODE) == O_RDWR) { + else if ((file->f_flags & O_ACCMODE) == O_RDWR) { if (!(dmxdev->capabilities & DMXDEV_CAP_DUPLEX)) { +#ifdef CONFIG_DVB_MMAP + dmxdev->may_do_mmap = 1; + need_ringbuffer = true; +#else mutex_unlock(&dmxdev->mutex); return -EOPNOTSUPP; +#endif } } -#endif if (need_ringbuffer) { void *mem; @@ -169,8 +179,9 @@ static int dvb_dvr_open(struct inode *inode, struct file *file) return -ENOMEM; } dvb_ringbuffer_init(&dmxdev->dvr_buffer, mem, DVR_BUFFER_SIZE); - dvb_vb2_init(&dmxdev->dvr_vb2_ctx, "dvr", - file->f_flags & O_NONBLOCK); + if (dmxdev->may_do_mmap) + dvb_vb2_init(&dmxdev->dvr_vb2_ctx, "dvr", + file->f_flags & O_NONBLOCK); dvbdev->readers--; } @@ -200,11 +211,6 @@ static int dvb_dvr_release(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dmxdev *dmxdev = dvbdev->priv; -#ifndef DVB_MMAP - bool need_ringbuffer = false; -#else - const bool need_ringbuffer = true; -#endif mutex_lock(&dmxdev->mutex); @@ -213,15 +219,14 @@ static int dvb_dvr_release(struct inode *inode, struct file *file) dmxdev->demux->connect_frontend(dmxdev->demux, dmxdev->dvr_orig_fe); } -#ifndef DVB_MMAP - if ((file->f_flags & O_ACCMODE) == O_RDONLY) - need_ringbuffer = true; -#endif - if (need_ringbuffer) { - if (dvb_vb2_is_streaming(&dmxdev->dvr_vb2_ctx)) - dvb_vb2_stream_off(&dmxdev->dvr_vb2_ctx); - dvb_vb2_release(&dmxdev->dvr_vb2_ctx); + if (((file->f_flags & O_ACCMODE) == O_RDONLY) || + dmxdev->may_do_mmap) { + if (dmxdev->may_do_mmap) { + if (dvb_vb2_is_streaming(&dmxdev->dvr_vb2_ctx)) + dvb_vb2_stream_off(&dmxdev->dvr_vb2_ctx); + dvb_vb2_release(&dmxdev->dvr_vb2_ctx); + } dvbdev->readers++; if (dmxdev->dvr_buffer.data) { void *mem = dmxdev->dvr_buffer.data; @@ -380,7 +385,8 @@ static void dvb_dmxdev_filter_timer(struct dmxdev_filter *dmxdevfilter) static int dvb_dmxdev_section_callback(const u8 *buffer1, size_t buffer1_len, const u8 *buffer2, size_t buffer2_len, - struct dmx_section_filter *filter) + struct dmx_section_filter *filter, + u32 *buffer_flags) { struct dmxdev_filter *dmxdevfilter = filter->priv; int ret; @@ -399,10 +405,12 @@ static int dvb_dmxdev_section_callback(const u8 *buffer1, size_t buffer1_len, dprintk("section callback %*ph\n", 6, buffer1); if (dvb_vb2_is_streaming(&dmxdevfilter->vb2_ctx)) { ret = dvb_vb2_fill_buffer(&dmxdevfilter->vb2_ctx, - buffer1, buffer1_len); + buffer1, buffer1_len, + buffer_flags); if (ret == buffer1_len) ret = dvb_vb2_fill_buffer(&dmxdevfilter->vb2_ctx, - buffer2, buffer2_len); + buffer2, buffer2_len, + buffer_flags); } else { ret = dvb_dmxdev_buffer_write(&dmxdevfilter->buffer, buffer1, buffer1_len); @@ -422,11 +430,12 @@ static int dvb_dmxdev_section_callback(const u8 *buffer1, size_t buffer1_len, static int dvb_dmxdev_ts_callback(const u8 *buffer1, size_t buffer1_len, const u8 *buffer2, size_t buffer2_len, - struct dmx_ts_feed *feed) + struct dmx_ts_feed *feed, + u32 *buffer_flags) { struct dmxdev_filter *dmxdevfilter = feed->priv; struct dvb_ringbuffer *buffer; -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP struct dvb_vb2_ctx *ctx; #endif int ret; @@ -440,20 +449,22 @@ static int dvb_dmxdev_ts_callback(const u8 *buffer1, size_t buffer1_len, if (dmxdevfilter->params.pes.output == DMX_OUT_TAP || dmxdevfilter->params.pes.output == DMX_OUT_TSDEMUX_TAP) { buffer = &dmxdevfilter->buffer; -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP ctx = &dmxdevfilter->vb2_ctx; #endif } else { buffer = &dmxdevfilter->dev->dvr_buffer; -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP ctx = &dmxdevfilter->dev->dvr_vb2_ctx; #endif } if (dvb_vb2_is_streaming(ctx)) { - ret = dvb_vb2_fill_buffer(ctx, buffer1, buffer1_len); + ret = dvb_vb2_fill_buffer(ctx, buffer1, buffer1_len, + buffer_flags); if (ret == buffer1_len) - ret = dvb_vb2_fill_buffer(ctx, buffer2, buffer2_len); + ret = dvb_vb2_fill_buffer(ctx, buffer2, buffer2_len, + buffer_flags); } else { if (buffer->error) { spin_unlock(&dmxdevfilter->dev->lock); @@ -802,6 +813,12 @@ static int dvb_demux_open(struct inode *inode, struct file *file) mutex_init(&dmxdevfilter->mutex); file->private_data = dmxdevfilter; +#ifdef CONFIG_DVB_MMAP + dmxdev->may_do_mmap = 1; +#else + dmxdev->may_do_mmap = 0; +#endif + dvb_ringbuffer_init(&dmxdevfilter->buffer, NULL, 8192); dvb_vb2_init(&dmxdevfilter->vb2_ctx, "demux_filter", file->f_flags & O_NONBLOCK); @@ -1111,7 +1128,7 @@ static int dvb_demux_do_ioctl(struct file *file, mutex_unlock(&dmxdevfilter->mutex); break; -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP case DMX_REQBUFS: if (mutex_lock_interruptible(&dmxdevfilter->mutex)) { mutex_unlock(&dmxdev->mutex); @@ -1160,7 +1177,7 @@ static int dvb_demux_do_ioctl(struct file *file, break; #endif default: - ret = -EINVAL; + ret = -ENOTTY; break; } mutex_unlock(&dmxdev->mutex); @@ -1199,13 +1216,16 @@ static __poll_t dvb_demux_poll(struct file *file, poll_table *wait) return mask; } -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP static int dvb_demux_mmap(struct file *file, struct vm_area_struct *vma) { struct dmxdev_filter *dmxdevfilter = file->private_data; struct dmxdev *dmxdev = dmxdevfilter->dev; int ret; + if (!dmxdev->may_do_mmap) + return -ENOTTY; + if (mutex_lock_interruptible(&dmxdev->mutex)) return -ERESTARTSYS; @@ -1249,7 +1269,7 @@ static const struct file_operations dvb_demux_fops = { .release = dvb_demux_release, .poll = dvb_demux_poll, .llseek = default_llseek, -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP .mmap = dvb_demux_mmap, #endif }; @@ -1280,7 +1300,7 @@ static int dvb_dvr_do_ioctl(struct file *file, ret = dvb_dvr_set_buffer_size(dmxdev, arg); break; -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP case DMX_REQBUFS: ret = dvb_vb2_reqbufs(&dmxdev->dvr_vb2_ctx, parg); break; @@ -1304,7 +1324,7 @@ static int dvb_dvr_do_ioctl(struct file *file, break; #endif default: - ret = -EINVAL; + ret = -ENOTTY; break; } mutex_unlock(&dmxdev->mutex); @@ -1322,11 +1342,6 @@ static __poll_t dvb_dvr_poll(struct file *file, poll_table *wait) struct dvb_device *dvbdev = file->private_data; struct dmxdev *dmxdev = dvbdev->priv; __poll_t mask = 0; -#ifndef DVB_MMAP - bool need_ringbuffer = false; -#else - const bool need_ringbuffer = true; -#endif dprintk("%s\n", __func__); @@ -1337,11 +1352,8 @@ static __poll_t dvb_dvr_poll(struct file *file, poll_table *wait) poll_wait(file, &dmxdev->dvr_buffer.queue, wait); -#ifndef DVB_MMAP - if ((file->f_flags & O_ACCMODE) == O_RDONLY) - need_ringbuffer = true; -#endif - if (need_ringbuffer) { + if (((file->f_flags & O_ACCMODE) == O_RDONLY) || + dmxdev->may_do_mmap) { if (dmxdev->dvr_buffer.error) mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI | EPOLLERR); @@ -1353,13 +1365,16 @@ static __poll_t dvb_dvr_poll(struct file *file, poll_table *wait) return mask; } -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP static int dvb_dvr_mmap(struct file *file, struct vm_area_struct *vma) { struct dvb_device *dvbdev = file->private_data; struct dmxdev *dmxdev = dvbdev->priv; int ret; + if (!dmxdev->may_do_mmap) + return -ENOTTY; + if (dmxdev->exit) return -ENODEV; @@ -1381,7 +1396,7 @@ static const struct file_operations dvb_dvr_fops = { .release = dvb_dvr_release, .poll = dvb_dvr_poll, .llseek = default_llseek, -#ifdef DVB_MMAP +#ifdef CONFIG_DVB_MMAP .mmap = dvb_dvr_mmap, #endif }; diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c index 210eed0269b0..f45091246bdc 100644 --- a/drivers/media/dvb-core/dvb_demux.c +++ b/drivers/media/dvb-core/dvb_demux.c @@ -55,6 +55,17 @@ MODULE_PARM_DESC(dvb_demux_feed_err_pkts, dprintk(x); \ } while (0) +#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG +# define dprintk_sect_loss(x...) dprintk(x) +#else +# define dprintk_sect_loss(x...) +#endif + +#define set_buf_flags(__feed, __flag) \ + do { \ + (__feed)->buffer_flags |= (__flag); \ + } while (0) + /****************************************************************************** * static inlined helper functions ******************************************************************************/ @@ -104,31 +115,30 @@ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, { int count = payload(buf); int p; -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG int ccok; u8 cc; -#endif if (count == 0) return -1; p = 188 - count; -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; feed->cc = cc; - if (!ccok) - dprintk("missed packet: %d instead of %d!\n", - cc, (feed->cc + 1) & 0x0f); -#endif + if (!ccok) { + set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); + dprintk_sect_loss("missed packet: %d instead of %d!\n", + cc, (feed->cc + 1) & 0x0f); + } if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; feed->peslen += count; - return feed->cb.ts(&buf[p], count, NULL, 0, &feed->feed.ts); + return feed->cb.ts(&buf[p], count, NULL, 0, &feed->feed.ts, + &feed->buffer_flags); } static int dvb_dmx_swfilter_sectionfilter(struct dvb_demux_feed *feed, @@ -150,7 +160,7 @@ static int dvb_dmx_swfilter_sectionfilter(struct dvb_demux_feed *feed, return 0; return feed->cb.sec(feed->feed.sec.secbuf, feed->feed.sec.seclen, - NULL, 0, &f->filter); + NULL, 0, &f->filter, &feed->buffer_flags); } static inline int dvb_dmx_swfilter_section_feed(struct dvb_demux_feed *feed) @@ -169,8 +179,10 @@ static inline int dvb_dmx_swfilter_section_feed(struct dvb_demux_feed *feed) if (sec->check_crc) { section_syntax_indicator = ((sec->secbuf[1] & 0x80) != 0); if (section_syntax_indicator && - demux->check_crc32(feed, sec->secbuf, sec->seclen)) + demux->check_crc32(feed, sec->secbuf, sec->seclen)) { + set_buf_flags(feed, DMX_BUFFER_FLAG_HAD_CRC32_DISCARD); return -1; + } } do { @@ -187,7 +199,6 @@ static void dvb_dmx_swfilter_section_new(struct dvb_demux_feed *feed) { struct dmx_section_feed *sec = &feed->feed.sec; -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG if (sec->secbufp < sec->tsfeedp) { int n = sec->tsfeedp - sec->secbufp; @@ -197,12 +208,13 @@ static void dvb_dmx_swfilter_section_new(struct dvb_demux_feed *feed) * but just first and last. */ if (sec->secbuf[0] != 0xff || sec->secbuf[n - 1] != 0xff) { - dprintk("section ts padding loss: %d/%d\n", - n, sec->tsfeedp); - dprintk("pad data: %*ph\n", n, sec->secbuf); + set_buf_flags(feed, + DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); + dprintk_sect_loss("section ts padding loss: %d/%d\n", + n, sec->tsfeedp); + dprintk_sect_loss("pad data: %*ph\n", n, sec->secbuf); } } -#endif sec->tsfeedp = sec->secbufp = sec->seclen = 0; sec->secbuf = sec->secbuf_base; @@ -237,11 +249,10 @@ static int dvb_dmx_swfilter_section_copy_dump(struct dvb_demux_feed *feed, return 0; if (sec->tsfeedp + len > DMX_MAX_SECFEED_SIZE) { -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG - dprintk("section buffer full loss: %d/%d\n", - sec->tsfeedp + len - DMX_MAX_SECFEED_SIZE, - DMX_MAX_SECFEED_SIZE); -#endif + set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); + dprintk_sect_loss("section buffer full loss: %d/%d\n", + sec->tsfeedp + len - DMX_MAX_SECFEED_SIZE, + DMX_MAX_SECFEED_SIZE); len = DMX_MAX_SECFEED_SIZE - sec->tsfeedp; } @@ -269,12 +280,13 @@ static int dvb_dmx_swfilter_section_copy_dump(struct dvb_demux_feed *feed, sec->seclen = seclen; sec->crc_val = ~0; /* dump [secbuf .. secbuf+seclen) */ - if (feed->pusi_seen) + if (feed->pusi_seen) { dvb_dmx_swfilter_section_feed(feed); -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG - else - dprintk("pusi not seen, discarding section data\n"); -#endif + } else { + set_buf_flags(feed, + DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); + dprintk_sect_loss("pusi not seen, discarding section data\n"); + } sec->secbufp += seclen; /* secbufp and secbuf moving together is */ sec->secbuf += seclen; /* redundant but saves pointer arithmetic */ } @@ -307,18 +319,22 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, } if (!ccok || dc_i) { -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG - if (dc_i) - dprintk("%d frame with disconnect indicator\n", + if (dc_i) { + set_buf_flags(feed, + DMX_BUFFER_FLAG_DISCONTINUITY_INDICATOR); + dprintk_sect_loss("%d frame with disconnect indicator\n", cc); - else - dprintk("discontinuity: %d instead of %d. %d bytes lost\n", + } else { + set_buf_flags(feed, + DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); + dprintk_sect_loss("discontinuity: %d instead of %d. %d bytes lost\n", cc, (feed->cc + 1) & 0x0f, count + 4); + } /* - * those bytes under sume circumstances will again be reported + * those bytes under some circumstances will again be reported * in the following dvb_dmx_swfilter_section_new */ -#endif + /* * Discontinuity detected. Reset pusi_seen to * stop feeding of suspicious data until next PUSI=1 arrives @@ -326,6 +342,7 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, * FIXME: does it make sense if the MPEG-TS is the one * reporting discontinuity? */ + feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } @@ -345,11 +362,11 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, dvb_dmx_swfilter_section_new(feed); dvb_dmx_swfilter_section_copy_dump(feed, after, after_len); + } else if (count > 0) { + set_buf_flags(feed, + DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); + dprintk_sect_loss("PUSI=1 but %d bytes lost\n", count); } -#ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG - else if (count > 0) - dprintk("PUSI=1 but %d bytes lost\n", count); -#endif } else { /* PUSI=0 (is not set), no section boundary */ dvb_dmx_swfilter_section_copy_dump(feed, &buf[p], count); @@ -369,7 +386,8 @@ static inline void dvb_dmx_swfilter_packet_type(struct dvb_demux_feed *feed, if (feed->ts_type & TS_PAYLOAD_ONLY) dvb_dmx_swfilter_payload(feed, buf); else - feed->cb.ts(buf, 188, NULL, 0, &feed->feed.ts); + feed->cb.ts(buf, 188, NULL, 0, &feed->feed.ts, + &feed->buffer_flags); } /* Used only on full-featured devices */ if (feed->ts_type & TS_DECODER) @@ -430,6 +448,11 @@ static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf) } if (buf[1] & 0x80) { + list_for_each_entry(feed, &demux->feed_list, list_head) { + if ((feed->pid != pid) && (feed->pid != 0x2000)) + continue; + set_buf_flags(feed, DMX_BUFFER_FLAG_TEI); + } dprintk_tscheck("TEI detected. PID=0x%x data1=0x%x\n", pid, buf[1]); /* data in this packet can't be trusted - drop it unless @@ -445,6 +468,13 @@ static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf) (demux->cnt_storage[pid] + 1) & 0xf; if ((buf[3] & 0xf) != demux->cnt_storage[pid]) { + list_for_each_entry(feed, &demux->feed_list, list_head) { + if ((feed->pid != pid) && (feed->pid != 0x2000)) + continue; + set_buf_flags(feed, + DMX_BUFFER_PKT_COUNTER_MISMATCH); + } + dprintk_tscheck("TS packet counter mismatch. PID=0x%x expected 0x%x got 0x%x\n", pid, demux->cnt_storage[pid], buf[3] & 0xf); @@ -466,7 +496,8 @@ static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf) if (feed->pid == pid) dvb_dmx_swfilter_packet_type(feed, buf); else if (feed->pid == 0x2000) - feed->cb.ts(buf, 188, NULL, 0, &feed->feed.ts); + feed->cb.ts(buf, 188, NULL, 0, &feed->feed.ts, + &feed->buffer_flags); } } @@ -585,7 +616,8 @@ void dvb_dmx_swfilter_raw(struct dvb_demux *demux, const u8 *buf, size_t count) spin_lock_irqsave(&demux->lock, flags); - demux->feed->cb.ts(buf, count, NULL, 0, &demux->feed->feed.ts); + demux->feed->cb.ts(buf, count, NULL, 0, &demux->feed->feed.ts, + &demux->feed->buffer_flags); spin_unlock_irqrestore(&demux->lock, flags); } @@ -785,6 +817,7 @@ static int dvbdmx_allocate_ts_feed(struct dmx_demux *dmx, feed->demux = demux; feed->pid = 0xffff; feed->peslen = 0xfffa; + feed->buffer_flags = 0; (*ts_feed) = &feed->feed.ts; (*ts_feed)->parent = dmx; @@ -1042,6 +1075,7 @@ static int dvbdmx_allocate_section_feed(struct dmx_demux *demux, dvbdmxfeed->cb.sec = callback; dvbdmxfeed->demux = dvbdmx; dvbdmxfeed->pid = 0xffff; + dvbdmxfeed->buffer_flags = 0; dvbdmxfeed->feed.sec.secbuf = dvbdmxfeed->feed.sec.secbuf_base; dvbdmxfeed->feed.sec.secbufp = dvbdmxfeed->feed.sec.seclen = 0; dvbdmxfeed->feed.sec.tsfeedp = 0; diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index b6c7eec863b9..ba39f9942e1d 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -883,7 +883,8 @@ static void dvb_net_ule(struct net_device *dev, const u8 *buf, size_t buf_len) static int dvb_net_ts_callback(const u8 *buffer1, size_t buffer1_len, const u8 *buffer2, size_t buffer2_len, - struct dmx_ts_feed *feed) + struct dmx_ts_feed *feed, + u32 *buffer_flags) { struct net_device *dev = feed->priv; @@ -992,7 +993,7 @@ static void dvb_net_sec(struct net_device *dev, static int dvb_net_sec_callback(const u8 *buffer1, size_t buffer1_len, const u8 *buffer2, size_t buffer2_len, - struct dmx_section_filter *filter) + struct dmx_section_filter *filter, u32 *buffer_flags) { struct net_device *dev = filter->priv; diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c index 763145d74e83..b811adf88afa 100644 --- a/drivers/media/dvb-core/dvb_vb2.c +++ b/drivers/media/dvb-core/dvb_vb2.c @@ -256,7 +256,8 @@ int dvb_vb2_is_streaming(struct dvb_vb2_ctx *ctx) } int dvb_vb2_fill_buffer(struct dvb_vb2_ctx *ctx, - const unsigned char *src, int len) + const unsigned char *src, int len, + enum dmx_buffer_flags *buffer_flags) { unsigned long flags = 0; void *vbuf = NULL; @@ -264,15 +265,17 @@ int dvb_vb2_fill_buffer(struct dvb_vb2_ctx *ctx, unsigned char *psrc = (unsigned char *)src; int ll = 0; - dprintk(3, "[%s] %d bytes are rcvd\n", ctx->name, len); - if (!src) { - dprintk(3, "[%s]:NULL pointer src\n", ctx->name); - /**normal case: This func is called twice from demux driver - * once with valid src pointer, second time with NULL pointer - */ + /* + * normal case: This func is called twice from demux driver + * one with valid src pointer, second time with NULL pointer + */ + if (!src || !len) return 0; - } spin_lock_irqsave(&ctx->slock, flags); + if (buffer_flags && *buffer_flags) { + ctx->flags |= *buffer_flags; + *buffer_flags = 0; + } while (todo) { if (!ctx->buf) { if (list_empty(&ctx->dvb_q)) { @@ -395,6 +398,7 @@ int dvb_vb2_qbuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b) int dvb_vb2_dqbuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b) { + unsigned long flags; int ret; ret = vb2_core_dqbuf(&ctx->vb_q, &b->index, b, ctx->nonblocking); @@ -402,7 +406,16 @@ int dvb_vb2_dqbuf(struct dvb_vb2_ctx *ctx, struct dmx_buffer *b) dprintk(1, "[%s] errno=%d\n", ctx->name, ret); return ret; } - dprintk(5, "[%s] index=%d\n", ctx->name, b->index); + + spin_lock_irqsave(&ctx->slock, flags); + b->count = ctx->count++; + b->flags = ctx->flags; + ctx->flags = 0; + spin_unlock_irqrestore(&ctx->slock, flags); + + dprintk(5, "[%s] index=%d, count=%d, flags=%d\n", + ctx->name, b->index, ctx->count, b->flags); + return 0; } diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c index 50bce68ffd66..65d157fe76d1 100644 --- a/drivers/media/dvb-frontends/m88ds3103.c +++ b/drivers/media/dvb-frontends/m88ds3103.c @@ -1262,11 +1262,12 @@ static int m88ds3103_select(struct i2c_mux_core *muxc, u32 chan) * New users must use I2C client binding directly! */ struct dvb_frontend *m88ds3103_attach(const struct m88ds3103_config *cfg, - struct i2c_adapter *i2c, struct i2c_adapter **tuner_i2c_adapter) + struct i2c_adapter *i2c, + struct i2c_adapter **tuner_i2c_adapter) { struct i2c_client *client; struct i2c_board_info board_info; - struct m88ds3103_platform_data pdata; + struct m88ds3103_platform_data pdata = {}; pdata.clk = cfg->clock; pdata.i2c_wr_max = cfg->i2c_wr_max; @@ -1409,6 +1410,8 @@ static int m88ds3103_probe(struct i2c_client *client, case M88DS3103_CHIP_ID: break; default: + ret = -ENODEV; + dev_err(&client->dev, "Unknown device. Chip_id=%02x\n", dev->chip_id); goto err_kfree; } diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c index 3c1851984b90..2476d812f669 100644 --- a/drivers/media/i2c/tvp5150.c +++ b/drivers/media/i2c/tvp5150.c @@ -505,80 +505,77 @@ static struct i2c_vbi_ram_value vbi_ram_default[] = /* FIXME: Current api doesn't handle all VBI types, those not yet supported are placed under #if 0 */ #if 0 - {0x010, /* Teletext, SECAM, WST System A */ + [0] = {0x010, /* Teletext, SECAM, WST System A */ {V4L2_SLICED_TELETEXT_SECAM,6,23,1}, { 0xaa, 0xaa, 0xff, 0xff, 0xe7, 0x2e, 0x20, 0x26, 0xe6, 0xb4, 0x0e, 0x00, 0x00, 0x00, 0x10, 0x00 } }, #endif - {0x030, /* Teletext, PAL, WST System B */ + [1] = {0x030, /* Teletext, PAL, WST System B */ {V4L2_SLICED_TELETEXT_B,6,22,1}, { 0xaa, 0xaa, 0xff, 0xff, 0x27, 0x2e, 0x20, 0x2b, 0xa6, 0x72, 0x10, 0x00, 0x00, 0x00, 0x10, 0x00 } }, #if 0 - {0x050, /* Teletext, PAL, WST System C */ + [2] = {0x050, /* Teletext, PAL, WST System C */ {V4L2_SLICED_TELETEXT_PAL_C,6,22,1}, { 0xaa, 0xaa, 0xff, 0xff, 0xe7, 0x2e, 0x20, 0x22, 0xa6, 0x98, 0x0d, 0x00, 0x00, 0x00, 0x10, 0x00 } }, - {0x070, /* Teletext, NTSC, WST System B */ + [3] = {0x070, /* Teletext, NTSC, WST System B */ {V4L2_SLICED_TELETEXT_NTSC_B,10,21,1}, { 0xaa, 0xaa, 0xff, 0xff, 0x27, 0x2e, 0x20, 0x23, 0x69, 0x93, 0x0d, 0x00, 0x00, 0x00, 0x10, 0x00 } }, - {0x090, /* Tetetext, NTSC NABTS System C */ + [4] = {0x090, /* Tetetext, NTSC NABTS System C */ {V4L2_SLICED_TELETEXT_NTSC_C,10,21,1}, { 0xaa, 0xaa, 0xff, 0xff, 0xe7, 0x2e, 0x20, 0x22, 0x69, 0x93, 0x0d, 0x00, 0x00, 0x00, 0x15, 0x00 } }, - {0x0b0, /* Teletext, NTSC-J, NABTS System D */ + [5] = {0x0b0, /* Teletext, NTSC-J, NABTS System D */ {V4L2_SLICED_TELETEXT_NTSC_D,10,21,1}, { 0xaa, 0xaa, 0xff, 0xff, 0xa7, 0x2e, 0x20, 0x23, 0x69, 0x93, 0x0d, 0x00, 0x00, 0x00, 0x10, 0x00 } }, - {0x0d0, /* Closed Caption, PAL/SECAM */ + [6] = {0x0d0, /* Closed Caption, PAL/SECAM */ {V4L2_SLICED_CAPTION_625,22,22,1}, { 0xaa, 0x2a, 0xff, 0x3f, 0x04, 0x51, 0x6e, 0x02, 0xa6, 0x7b, 0x09, 0x00, 0x00, 0x00, 0x27, 0x00 } }, #endif - {0x0f0, /* Closed Caption, NTSC */ + [7] = {0x0f0, /* Closed Caption, NTSC */ {V4L2_SLICED_CAPTION_525,21,21,1}, { 0xaa, 0x2a, 0xff, 0x3f, 0x04, 0x51, 0x6e, 0x02, 0x69, 0x8c, 0x09, 0x00, 0x00, 0x00, 0x27, 0x00 } }, - {0x110, /* Wide Screen Signal, PAL/SECAM */ + [8] = {0x110, /* Wide Screen Signal, PAL/SECAM */ {V4L2_SLICED_WSS_625,23,23,1}, { 0x5b, 0x55, 0xc5, 0xff, 0x00, 0x71, 0x6e, 0x42, 0xa6, 0xcd, 0x0f, 0x00, 0x00, 0x00, 0x3a, 0x00 } }, #if 0 - {0x130, /* Wide Screen Signal, NTSC C */ + [9] = {0x130, /* Wide Screen Signal, NTSC C */ {V4L2_SLICED_WSS_525,20,20,1}, { 0x38, 0x00, 0x3f, 0x00, 0x00, 0x71, 0x6e, 0x43, 0x69, 0x7c, 0x08, 0x00, 0x00, 0x00, 0x39, 0x00 } }, - {0x150, /* Vertical Interval Timecode (VITC), PAL/SECAM */ + [10] = {0x150, /* Vertical Interval Timecode (VITC), PAL/SECAM */ {V4l2_SLICED_VITC_625,6,22,0}, { 0x00, 0x00, 0x00, 0x00, 0x00, 0x8f, 0x6d, 0x49, 0xa6, 0x85, 0x08, 0x00, 0x00, 0x00, 0x4c, 0x00 } }, - {0x170, /* Vertical Interval Timecode (VITC), NTSC */ + [11] = {0x170, /* Vertical Interval Timecode (VITC), NTSC */ {V4l2_SLICED_VITC_525,10,20,0}, { 0x00, 0x00, 0x00, 0x00, 0x00, 0x8f, 0x6d, 0x49, 0x69, 0x94, 0x08, 0x00, 0x00, 0x00, 0x4c, 0x00 } }, #endif - {0x190, /* Video Program System (VPS), PAL */ + [12] = {0x190, /* Video Program System (VPS), PAL */ {V4L2_SLICED_VPS,16,16,0}, { 0xaa, 0xaa, 0xff, 0xff, 0xba, 0xce, 0x2b, 0x0d, 0xa6, 0xda, 0x0b, 0x00, 0x00, 0x00, 0x60, 0x00 } }, /* 0x1d0 User programmable */ - - /* End of struct */ - { (u16)-1 } }; static int tvp5150_write_inittab(struct v4l2_subdev *sd, @@ -591,10 +588,10 @@ static int tvp5150_write_inittab(struct v4l2_subdev *sd, return 0; } -static int tvp5150_vdp_init(struct v4l2_subdev *sd, - const struct i2c_vbi_ram_value *regs) +static int tvp5150_vdp_init(struct v4l2_subdev *sd) { unsigned int i; + int j; /* Disable Full Field */ tvp5150_write(sd, TVP5150_FULL_FIELD_ENA, 0); @@ -604,14 +601,17 @@ static int tvp5150_vdp_init(struct v4l2_subdev *sd, tvp5150_write(sd, i, 0xff); /* Load Ram Table */ - while (regs->reg != (u16)-1) { + for (j = 0; j < ARRAY_SIZE(vbi_ram_default); j++) { + const struct i2c_vbi_ram_value *regs = &vbi_ram_default[j]; + + if (!regs->type.vbi_type) + continue; + tvp5150_write(sd, TVP5150_CONF_RAM_ADDR_HIGH, regs->reg >> 8); tvp5150_write(sd, TVP5150_CONF_RAM_ADDR_LOW, regs->reg); for (i = 0; i < 16; i++) tvp5150_write(sd, TVP5150_VDP_CONF_RAM_DATA, regs->values[i]); - - regs++; } return 0; } @@ -620,19 +620,23 @@ static int tvp5150_vdp_init(struct v4l2_subdev *sd, static int tvp5150_g_sliced_vbi_cap(struct v4l2_subdev *sd, struct v4l2_sliced_vbi_cap *cap) { - const struct i2c_vbi_ram_value *regs = vbi_ram_default; - int line; + int line, i; dev_dbg_lvl(sd->dev, 1, debug, "g_sliced_vbi_cap\n"); memset(cap, 0, sizeof *cap); - while (regs->reg != (u16)-1 ) { - for (line=regs->type.ini_line;line<=regs->type.end_line;line++) { + for (i = 0; i < ARRAY_SIZE(vbi_ram_default); i++) { + const struct i2c_vbi_ram_value *regs = &vbi_ram_default[i]; + + if (!regs->type.vbi_type) + continue; + + for (line = regs->type.ini_line; + line <= regs->type.end_line; + line++) { cap->service_lines[0][line] |= regs->type.vbi_type; } cap->service_set |= regs->type.vbi_type; - - regs++; } return 0; } @@ -651,14 +655,13 @@ static int tvp5150_g_sliced_vbi_cap(struct v4l2_subdev *sd, * MSB = field2 */ static int tvp5150_set_vbi(struct v4l2_subdev *sd, - const struct i2c_vbi_ram_value *regs, unsigned int type,u8 flags, int line, const int fields) { struct tvp5150 *decoder = to_tvp5150(sd); v4l2_std_id std = decoder->norm; u8 reg; - int pos = 0; + int i, pos = 0; if (std == V4L2_STD_ALL) { dev_err(sd->dev, "VBI can't be configured without knowing number of lines\n"); @@ -671,19 +674,19 @@ static int tvp5150_set_vbi(struct v4l2_subdev *sd, if (line < 6 || line > 27) return 0; - while (regs->reg != (u16)-1) { + for (i = 0; i < ARRAY_SIZE(vbi_ram_default); i++) { + const struct i2c_vbi_ram_value *regs = &vbi_ram_default[i]; + + if (!regs->type.vbi_type) + continue; + if ((type & regs->type.vbi_type) && (line >= regs->type.ini_line) && (line <= regs->type.end_line)) break; - - regs++; pos++; } - if (regs->reg == (u16)-1) - return 0; - type = pos | (flags & 0xf0); reg = ((line - 6) << 1) + TVP5150_LINE_MODE_INI; @@ -696,8 +699,7 @@ static int tvp5150_set_vbi(struct v4l2_subdev *sd, return type; } -static int tvp5150_get_vbi(struct v4l2_subdev *sd, - const struct i2c_vbi_ram_value *regs, int line) +static int tvp5150_get_vbi(struct v4l2_subdev *sd, int line) { struct tvp5150 *decoder = to_tvp5150(sd); v4l2_std_id std = decoder->norm; @@ -726,8 +728,8 @@ static int tvp5150_get_vbi(struct v4l2_subdev *sd, return 0; } pos = ret & 0x0f; - if (pos < 0x0f) - type |= regs[pos].type.vbi_type; + if (pos < ARRAY_SIZE(vbi_ram_default)) + type |= vbi_ram_default[pos].type.vbi_type; } return type; @@ -788,7 +790,7 @@ static int tvp5150_reset(struct v4l2_subdev *sd, u32 val) tvp5150_write_inittab(sd, tvp5150_init_default); /* Initializes VDP registers */ - tvp5150_vdp_init(sd, vbi_ram_default); + tvp5150_vdp_init(sd); /* Selects decoder input */ tvp5150_selmux(sd); @@ -1121,8 +1123,8 @@ static int tvp5150_s_sliced_fmt(struct v4l2_subdev *sd, struct v4l2_sliced_vbi_f for (i = 0; i <= 23; i++) { svbi->service_lines[1][i] = 0; svbi->service_lines[0][i] = - tvp5150_set_vbi(sd, vbi_ram_default, - svbi->service_lines[0][i], 0xf0, i, 3); + tvp5150_set_vbi(sd, svbi->service_lines[0][i], + 0xf0, i, 3); } /* Enables FIFO */ tvp5150_write(sd, TVP5150_FIFO_OUT_CTRL, 1); @@ -1148,7 +1150,7 @@ static int tvp5150_g_sliced_fmt(struct v4l2_subdev *sd, struct v4l2_sliced_vbi_f for (i = 0; i <= 23; i++) { svbi->service_lines[0][i] = - tvp5150_get_vbi(sd, vbi_ram_default, i); + tvp5150_get_vbi(sd, i); mask |= svbi->service_lines[0][i]; } svbi->service_set = mask; diff --git a/drivers/media/pci/ttpci/av7110.c b/drivers/media/pci/ttpci/av7110.c index dc8e577b2f74..d6816effb878 100644 --- a/drivers/media/pci/ttpci/av7110.c +++ b/drivers/media/pci/ttpci/av7110.c @@ -324,14 +324,15 @@ static int DvbDmxFilterCallback(u8 *buffer1, size_t buffer1_len, } return dvbdmxfilter->feed->cb.sec(buffer1, buffer1_len, buffer2, buffer2_len, - &dvbdmxfilter->filter); + &dvbdmxfilter->filter, NULL); case DMX_TYPE_TS: if (!(dvbdmxfilter->feed->ts_type & TS_PACKET)) return 0; if (dvbdmxfilter->feed->ts_type & TS_PAYLOAD_ONLY) return dvbdmxfilter->feed->cb.ts(buffer1, buffer1_len, buffer2, buffer2_len, - &dvbdmxfilter->feed->feed.ts); + &dvbdmxfilter->feed->feed.ts, + NULL); else av7110_p2t_write(buffer1, buffer1_len, dvbdmxfilter->feed->pid, diff --git a/drivers/media/pci/ttpci/av7110_av.c b/drivers/media/pci/ttpci/av7110_av.c index 4daba76ec240..ef1bc17cdc4d 100644 --- a/drivers/media/pci/ttpci/av7110_av.c +++ b/drivers/media/pci/ttpci/av7110_av.c @@ -99,7 +99,7 @@ int av7110_record_cb(struct dvb_filter_pes2ts *p2t, u8 *buf, size_t len) buf[4] = buf[5] = 0; if (dvbdmxfeed->ts_type & TS_PAYLOAD_ONLY) return dvbdmxfeed->cb.ts(buf, len, NULL, 0, - &dvbdmxfeed->feed.ts); + &dvbdmxfeed->feed.ts, NULL); else return dvb_filter_pes2ts(p2t, buf, len, 1); } @@ -109,7 +109,7 @@ static int dvb_filter_pes2ts_cb(void *priv, unsigned char *data) struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *) priv; dvbdmxfeed->cb.ts(data, 188, NULL, 0, - &dvbdmxfeed->feed.ts); + &dvbdmxfeed->feed.ts, NULL); return 0; } @@ -814,7 +814,7 @@ static void p_to_t(u8 const *buf, long int length, u16 pid, u8 *counter, memcpy(obuf + l, buf + c, TS_SIZE - l); c = length; } - feed->cb.ts(obuf, 188, NULL, 0, &feed->feed.ts); + feed->cb.ts(obuf, 188, NULL, 0, &feed->feed.ts, NULL); pes_start = 0; } } diff --git a/drivers/media/platform/tegra-cec/tegra_cec.c b/drivers/media/platform/tegra-cec/tegra_cec.c index 92f93a880015..aba488cd0e64 100644 --- a/drivers/media/platform/tegra-cec/tegra_cec.c +++ b/drivers/media/platform/tegra-cec/tegra_cec.c @@ -172,16 +172,13 @@ static irqreturn_t tegra_cec_irq_handler(int irq, void *data) } } - if (status & (TEGRA_CEC_INT_STAT_RX_REGISTER_OVERRUN | - TEGRA_CEC_INT_STAT_RX_BUS_ANOMALY_DETECTED | - TEGRA_CEC_INT_STAT_RX_START_BIT_DETECTED | - TEGRA_CEC_INT_STAT_RX_BUS_ERROR_DETECTED)) { + if (status & TEGRA_CEC_INT_STAT_RX_START_BIT_DETECTED) { cec_write(cec, TEGRA_CEC_INT_STAT, - (TEGRA_CEC_INT_STAT_RX_REGISTER_OVERRUN | - TEGRA_CEC_INT_STAT_RX_BUS_ANOMALY_DETECTED | - TEGRA_CEC_INT_STAT_RX_START_BIT_DETECTED | - TEGRA_CEC_INT_STAT_RX_BUS_ERROR_DETECTED)); - } else if (status & TEGRA_CEC_INT_STAT_RX_REGISTER_FULL) { + TEGRA_CEC_INT_STAT_RX_START_BIT_DETECTED); + cec->rx_done = false; + cec->rx_buf_cnt = 0; + } + if (status & TEGRA_CEC_INT_STAT_RX_REGISTER_FULL) { u32 v; cec_write(cec, TEGRA_CEC_INT_STAT, @@ -255,7 +252,7 @@ static int tegra_cec_adap_enable(struct cec_adapter *adap, bool enable) TEGRA_CEC_INT_MASK_TX_BUS_ANOMALY_DETECTED | TEGRA_CEC_INT_MASK_TX_FRAME_TRANSMITTED | TEGRA_CEC_INT_MASK_RX_REGISTER_FULL | - TEGRA_CEC_INT_MASK_RX_REGISTER_OVERRUN); + TEGRA_CEC_INT_MASK_RX_START_BIT_DETECTED); cec_write(cec, TEGRA_CEC_HW_CONTROL, TEGRA_CEC_HWCTRL_TX_RX_MODE); return 0; diff --git a/drivers/media/usb/au0828/Kconfig b/drivers/media/usb/au0828/Kconfig index 70521e0b4c53..bfaa806633df 100644 --- a/drivers/media/usb/au0828/Kconfig +++ b/drivers/media/usb/au0828/Kconfig @@ -1,7 +1,7 @@ config VIDEO_AU0828 tristate "Auvitek AU0828 support" - depends on I2C && INPUT && DVB_CORE && USB + depends on I2C && INPUT && DVB_CORE && USB && VIDEO_V4L2 select I2C_ALGOBIT select VIDEO_TVEEPROM select VIDEOBUF2_VMALLOC diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index a8900f5571f7..44ca66cb9b8f 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -428,7 +428,7 @@ static int ttusb_dec_audio_pes2ts_cb(void *priv, unsigned char *data) struct ttusb_dec *dec = priv; dec->audio_filter->feed->cb.ts(data, 188, NULL, 0, - &dec->audio_filter->feed->feed.ts); + &dec->audio_filter->feed->feed.ts, NULL); return 0; } @@ -438,7 +438,7 @@ static int ttusb_dec_video_pes2ts_cb(void *priv, unsigned char *data) struct ttusb_dec *dec = priv; dec->video_filter->feed->cb.ts(data, 188, NULL, 0, - &dec->video_filter->feed->feed.ts); + &dec->video_filter->feed->feed.ts, NULL); return 0; } @@ -490,7 +490,7 @@ static void ttusb_dec_process_pva(struct ttusb_dec *dec, u8 *pva, int length) if (output_pva) { dec->video_filter->feed->cb.ts(pva, length, NULL, 0, - &dec->video_filter->feed->feed.ts); + &dec->video_filter->feed->feed.ts, NULL); return; } @@ -551,7 +551,7 @@ static void ttusb_dec_process_pva(struct ttusb_dec *dec, u8 *pva, int length) case 0x02: /* MainAudioStream */ if (output_pva) { dec->audio_filter->feed->cb.ts(pva, length, NULL, 0, - &dec->audio_filter->feed->feed.ts); + &dec->audio_filter->feed->feed.ts, NULL); return; } @@ -589,7 +589,7 @@ static void ttusb_dec_process_filter(struct ttusb_dec *dec, u8 *packet, if (filter) filter->feed->cb.sec(&packet[2], length - 2, NULL, 0, - &filter->filter); + &filter->filter, NULL); } static void ttusb_dec_process_packet(struct ttusb_dec *dec) diff --git a/drivers/media/v4l2-core/Kconfig b/drivers/media/v4l2-core/Kconfig index bf52fbd07aed..8e37e7c5e0f7 100644 --- a/drivers/media/v4l2-core/Kconfig +++ b/drivers/media/v4l2-core/Kconfig @@ -7,6 +7,7 @@ config VIDEO_V4L2 tristate depends on (I2C || I2C=n) && VIDEO_DEV select RATIONAL + select VIDEOBUF2_V4L2 if VIDEOBUF2_CORE default (I2C || I2C=n) && VIDEO_DEV config VIDEO_ADV_DEBUG diff --git a/drivers/media/v4l2-core/Makefile b/drivers/media/v4l2-core/Makefile index 80de2cb9c476..7df54582e956 100644 --- a/drivers/media/v4l2-core/Makefile +++ b/drivers/media/v4l2-core/Makefile @@ -13,7 +13,7 @@ ifeq ($(CONFIG_COMPAT),y) endif obj-$(CONFIG_V4L2_FWNODE) += v4l2-fwnode.o ifeq ($(CONFIG_TRACEPOINTS),y) - videodev-objs += vb2-trace.o v4l2-trace.o + videodev-objs += v4l2-trace.o endif videodev-$(CONFIG_MEDIA_CONTROLLER) += v4l2-mc.o @@ -35,4 +35,3 @@ obj-$(CONFIG_VIDEOBUF_DVB) += videobuf-dvb.o ccflags-y += -I$(srctree)/drivers/media/dvb-frontends ccflags-y += -I$(srctree)/drivers/media/tuners - diff --git a/drivers/memory/brcmstb_dpfe.c b/drivers/memory/brcmstb_dpfe.c index 0a7bdbed3a6f..e9c1485c32b9 100644 --- a/drivers/memory/brcmstb_dpfe.c +++ b/drivers/memory/brcmstb_dpfe.c @@ -45,8 +45,16 @@ #define REG_TO_DCPU_MBOX 0x10 #define REG_TO_HOST_MBOX 0x14 +/* Macros to process offsets returned by the DCPU */ +#define DRAM_MSG_ADDR_OFFSET 0x0 +#define DRAM_MSG_TYPE_OFFSET 0x1c +#define DRAM_MSG_ADDR_MASK ((1UL << DRAM_MSG_TYPE_OFFSET) - 1) +#define DRAM_MSG_TYPE_MASK ((1UL << \ + (BITS_PER_LONG - DRAM_MSG_TYPE_OFFSET)) - 1) + /* Message RAM */ -#define DCPU_MSG_RAM(x) (0x100 + (x) * sizeof(u32)) +#define DCPU_MSG_RAM_START 0x100 +#define DCPU_MSG_RAM(x) (DCPU_MSG_RAM_START + (x) * sizeof(u32)) /* DRAM Info Offsets & Masks */ #define DRAM_INFO_INTERVAL 0x0 @@ -255,6 +263,40 @@ static unsigned int get_msg_chksum(const u32 msg[]) return sum; } +static void __iomem *get_msg_ptr(struct private_data *priv, u32 response, + char *buf, ssize_t *size) +{ + unsigned int msg_type; + unsigned int offset; + void __iomem *ptr = NULL; + + msg_type = (response >> DRAM_MSG_TYPE_OFFSET) & DRAM_MSG_TYPE_MASK; + offset = (response >> DRAM_MSG_ADDR_OFFSET) & DRAM_MSG_ADDR_MASK; + + /* + * msg_type == 1: the offset is relative to the message RAM + * msg_type == 0: the offset is relative to the data RAM (this is the + * previous way of passing data) + * msg_type is anything else: there's critical hardware problem + */ + switch (msg_type) { + case 1: + ptr = priv->regs + DCPU_MSG_RAM_START + offset; + break; + case 0: + ptr = priv->dmem + offset; + break; + default: + dev_emerg(priv->dev, "invalid message reply from DCPU: %#x\n", + response); + if (buf && size) + *size = sprintf(buf, + "FATAL: communication error with DCPU\n"); + } + + return ptr; +} + static int __send_command(struct private_data *priv, unsigned int cmd, u32 result[]) { @@ -507,7 +549,7 @@ static ssize_t show_info(struct device *dev, struct device_attribute *devattr, { u32 response[MSG_FIELD_MAX]; unsigned int info; - int ret; + ssize_t ret; ret = generic_show(DPFE_CMD_GET_INFO, response, dev, buf); if (ret) @@ -528,18 +570,19 @@ static ssize_t show_refresh(struct device *dev, u32 response[MSG_FIELD_MAX]; void __iomem *info; struct private_data *priv; - unsigned int offset; u8 refresh, sr_abort, ppre, thermal_offs, tuf; u32 mr4; - int ret; + ssize_t ret; ret = generic_show(DPFE_CMD_GET_REFRESH, response, dev, buf); if (ret) return ret; priv = dev_get_drvdata(dev); - offset = response[MSG_ARG0]; - info = priv->dmem + offset; + + info = get_msg_ptr(priv, response[MSG_ARG0], buf, &ret); + if (!info) + return ret; mr4 = readl_relaxed(info + DRAM_INFO_MR4) & DRAM_INFO_MR4_MASK; @@ -561,7 +604,6 @@ static ssize_t store_refresh(struct device *dev, struct device_attribute *attr, u32 response[MSG_FIELD_MAX]; struct private_data *priv; void __iomem *info; - unsigned int offset; unsigned long val; int ret; @@ -574,8 +616,10 @@ static ssize_t store_refresh(struct device *dev, struct device_attribute *attr, if (ret) return ret; - offset = response[MSG_ARG0]; - info = priv->dmem + offset; + info = get_msg_ptr(priv, response[MSG_ARG0], NULL, NULL); + if (!info) + return -EIO; + writel_relaxed(val, info + DRAM_INFO_INTERVAL); return count; @@ -587,23 +631,25 @@ static ssize_t show_vendor(struct device *dev, struct device_attribute *devattr, u32 response[MSG_FIELD_MAX]; struct private_data *priv; void __iomem *info; - unsigned int offset; - int ret; + ssize_t ret; ret = generic_show(DPFE_CMD_GET_VENDOR, response, dev, buf); if (ret) return ret; - offset = response[MSG_ARG0]; priv = dev_get_drvdata(dev); - info = priv->dmem + offset; + + info = get_msg_ptr(priv, response[MSG_ARG0], buf, &ret); + if (!info) + return ret; return sprintf(buf, "%#x %#x %#x %#x %#x\n", readl_relaxed(info + DRAM_VENDOR_MR5) & DRAM_VENDOR_MASK, readl_relaxed(info + DRAM_VENDOR_MR6) & DRAM_VENDOR_MASK, readl_relaxed(info + DRAM_VENDOR_MR7) & DRAM_VENDOR_MASK, readl_relaxed(info + DRAM_VENDOR_MR8) & DRAM_VENDOR_MASK, - readl_relaxed(info + DRAM_VENDOR_ERROR)); + readl_relaxed(info + DRAM_VENDOR_ERROR) & + DRAM_VENDOR_MASK); } static int brcmstb_dpfe_resume(struct platform_device *pdev) diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index 337462e1569f..038509e5d031 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -102,10 +102,32 @@ static long afu_ioctl_attach(struct ocxl_context *ctx, return rc; } +static long afu_ioctl_get_metadata(struct ocxl_context *ctx, + struct ocxl_ioctl_metadata __user *uarg) +{ + struct ocxl_ioctl_metadata arg; + + memset(&arg, 0, sizeof(arg)); + + arg.version = 0; + + arg.afu_version_major = ctx->afu->config.version_major; + arg.afu_version_minor = ctx->afu->config.version_minor; + arg.pasid = ctx->pasid; + arg.pp_mmio_size = ctx->afu->config.pp_mmio_stride; + arg.global_mmio_size = ctx->afu->config.global_mmio_size; + + if (copy_to_user(uarg, &arg, sizeof(arg))) + return -EFAULT; + + return 0; +} + #define CMD_STR(x) (x == OCXL_IOCTL_ATTACH ? "ATTACH" : \ x == OCXL_IOCTL_IRQ_ALLOC ? "IRQ_ALLOC" : \ x == OCXL_IOCTL_IRQ_FREE ? "IRQ_FREE" : \ x == OCXL_IOCTL_IRQ_SET_FD ? "IRQ_SET_FD" : \ + x == OCXL_IOCTL_GET_METADATA ? "GET_METADATA" : \ "UNKNOWN") static long afu_ioctl(struct file *file, unsigned int cmd, @@ -159,6 +181,11 @@ static long afu_ioctl(struct file *file, unsigned int cmd, irq_fd.eventfd); break; + case OCXL_IOCTL_GET_METADATA: + rc = afu_ioctl_get_metadata(ctx, + (struct ocxl_ioctl_metadata __user *) args); + break; + default: rc = -EINVAL; } diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 20135a5de748..2cfb963d9f37 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -72,6 +72,7 @@ MODULE_ALIAS("mmc:block"); #define MMC_BLK_TIMEOUT_MS (10 * 1000) #define MMC_SANITIZE_REQ_TIMEOUT 240000 #define MMC_EXTRACT_INDEX_FROM_ARG(x) ((x & 0x00FF0000) >> 16) +#define MMC_EXTRACT_VALUE_FROM_ARG(x) ((x & 0x0000FF00) >> 8) #define mmc_req_rel_wr(req) ((req->cmd_flags & REQ_FUA) && \ (rq_data_dir(req) == WRITE)) @@ -587,6 +588,24 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, } /* + * Make sure the cache of the PARTITION_CONFIG register and + * PARTITION_ACCESS bits is updated in case the ioctl ext_csd write + * changed it successfully. + */ + if ((MMC_EXTRACT_INDEX_FROM_ARG(cmd.arg) == EXT_CSD_PART_CONFIG) && + (cmd.opcode == MMC_SWITCH)) { + struct mmc_blk_data *main_md = dev_get_drvdata(&card->dev); + u8 value = MMC_EXTRACT_VALUE_FROM_ARG(cmd.arg); + + /* + * Update cache so the next mmc_blk_part_switch call operates + * on up-to-date data. + */ + card->ext_csd.part_config = value; + main_md->part_curr = value & EXT_CSD_PART_CONFIG_ACC_MASK; + } + + /* * According to the SD specs, some commands require a delay after * issuing the command. */ diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h index 79a5b985ccf5..9c821eedd156 100644 --- a/drivers/mmc/core/card.h +++ b/drivers/mmc/core/card.h @@ -82,6 +82,7 @@ struct mmc_fixup { #define CID_MANFID_APACER 0x27 #define CID_MANFID_KINGSTON 0x70 #define CID_MANFID_HYNIX 0x90 +#define CID_MANFID_NUMONYX 0xFE #define END_FIXUP { NULL } diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index 908e4db03535..42d6aa89a48a 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -848,7 +848,6 @@ int mmc_interrupt_hpi(struct mmc_card *card) return 1; } - mmc_claim_host(card->host); err = mmc_send_status(card, &status); if (err) { pr_err("%s: Get card status fail\n", mmc_hostname(card->host)); @@ -890,7 +889,6 @@ int mmc_interrupt_hpi(struct mmc_card *card) } while (!err); out: - mmc_release_host(card->host); return err; } @@ -932,9 +930,7 @@ static int mmc_read_bkops_status(struct mmc_card *card) int err; u8 *ext_csd; - mmc_claim_host(card->host); err = mmc_get_ext_csd(card, &ext_csd); - mmc_release_host(card->host); if (err) return err; diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index 75d317623852..5153577754f0 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -109,6 +109,12 @@ static const struct mmc_fixup mmc_ext_csd_fixups[] = { */ MMC_FIXUP_EXT_CSD_REV(CID_NAME_ANY, CID_MANFID_HYNIX, 0x014a, add_quirk, MMC_QUIRK_BROKEN_HPI, 5), + /* + * Certain Micron (Numonyx) eMMC 4.5 cards might get broken when HPI + * feature is used so disable the HPI feature for such buggy cards. + */ + MMC_FIXUP_EXT_CSD_REV(CID_NAME_ANY, CID_MANFID_NUMONYX, + 0x014e, add_quirk, MMC_QUIRK_BROKEN_HPI, 6), END_FIXUP }; diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c index 35026795be28..a84aa3f1ae85 100644 --- a/drivers/mmc/host/dw_mmc-exynos.c +++ b/drivers/mmc/host/dw_mmc-exynos.c @@ -165,9 +165,15 @@ static void dw_mci_exynos_set_clksel_timing(struct dw_mci *host, u32 timing) static int dw_mci_exynos_runtime_resume(struct device *dev) { struct dw_mci *host = dev_get_drvdata(dev); + int ret; + + ret = dw_mci_runtime_resume(dev); + if (ret) + return ret; dw_mci_exynos_config_smu(host); - return dw_mci_runtime_resume(dev); + + return ret; } /** @@ -487,6 +493,7 @@ static unsigned long exynos_dwmmc_caps[4] = { static const struct dw_mci_drv_data exynos_drv_data = { .caps = exynos_dwmmc_caps, + .num_caps = ARRAY_SIZE(exynos_dwmmc_caps), .init = dw_mci_exynos_priv_init, .set_ios = dw_mci_exynos_set_ios, .parse_dt = dw_mci_exynos_parse_dt, diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c index 73fd75c3c824..89cdb3d533bb 100644 --- a/drivers/mmc/host/dw_mmc-k3.c +++ b/drivers/mmc/host/dw_mmc-k3.c @@ -135,6 +135,9 @@ static int dw_mci_hi6220_parse_dt(struct dw_mci *host) if (priv->ctrl_id < 0) priv->ctrl_id = 0; + if (priv->ctrl_id >= TIMING_MODE) + return -EINVAL; + host->priv = priv; return 0; } @@ -207,6 +210,7 @@ static int dw_mci_hi6220_execute_tuning(struct dw_mci_slot *slot, u32 opcode) static const struct dw_mci_drv_data hi6220_data = { .caps = dw_mci_hi6220_caps, + .num_caps = ARRAY_SIZE(dw_mci_hi6220_caps), .switch_voltage = dw_mci_hi6220_switch_voltage, .set_ios = dw_mci_hi6220_set_ios, .parse_dt = dw_mci_hi6220_parse_dt, diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c index a3f1c2b30145..339295212935 100644 --- a/drivers/mmc/host/dw_mmc-rockchip.c +++ b/drivers/mmc/host/dw_mmc-rockchip.c @@ -319,6 +319,7 @@ static const struct dw_mci_drv_data rk2928_drv_data = { static const struct dw_mci_drv_data rk3288_drv_data = { .caps = dw_mci_rk3288_dwmmc_caps, + .num_caps = ARRAY_SIZE(dw_mci_rk3288_dwmmc_caps), .set_ios = dw_mci_rk3288_set_ios, .execute_tuning = dw_mci_rk3288_execute_tuning, .parse_dt = dw_mci_rk3288_parse_dt, diff --git a/drivers/mmc/host/dw_mmc-zx.c b/drivers/mmc/host/dw_mmc-zx.c index d38e94ae2b85..c06b5393312f 100644 --- a/drivers/mmc/host/dw_mmc-zx.c +++ b/drivers/mmc/host/dw_mmc-zx.c @@ -195,6 +195,7 @@ static unsigned long zx_dwmmc_caps[3] = { static const struct dw_mci_drv_data zx_drv_data = { .caps = zx_dwmmc_caps, + .num_caps = ARRAY_SIZE(zx_dwmmc_caps), .execute_tuning = dw_mci_zx_execute_tuning, .prepare_hs400_tuning = dw_mci_zx_prepare_hs400_tuning, .parse_dt = dw_mci_zx_parse_dt, diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 0aa39975f33b..06d47414d0c1 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -165,6 +165,8 @@ static int dw_mci_regs_show(struct seq_file *s, void *v) { struct dw_mci *host = s->private; + pm_runtime_get_sync(host->dev); + seq_printf(s, "STATUS:\t0x%08x\n", mci_readl(host, STATUS)); seq_printf(s, "RINTSTS:\t0x%08x\n", mci_readl(host, RINTSTS)); seq_printf(s, "CMD:\t0x%08x\n", mci_readl(host, CMD)); @@ -172,6 +174,8 @@ static int dw_mci_regs_show(struct seq_file *s, void *v) seq_printf(s, "INTMASK:\t0x%08x\n", mci_readl(host, INTMASK)); seq_printf(s, "CLKENA:\t0x%08x\n", mci_readl(host, CLKENA)); + pm_runtime_put_autosuspend(host->dev); + return 0; } @@ -409,7 +413,9 @@ static inline void dw_mci_set_cto(struct dw_mci *host) cto_div = (mci_readl(host, CLKDIV) & 0xff) * 2; if (cto_div == 0) cto_div = 1; - cto_ms = DIV_ROUND_UP(MSEC_PER_SEC * cto_clks * cto_div, host->bus_hz); + + cto_ms = DIV_ROUND_UP_ULL((u64)MSEC_PER_SEC * cto_clks * cto_div, + host->bus_hz); /* add a bit spare time */ cto_ms += 10; @@ -558,6 +564,7 @@ static int dw_mci_idmac_init(struct dw_mci *host) (sizeof(struct idmac_desc_64addr) * (i + 1))) >> 32; /* Initialize reserved and buffer size fields to "0" */ + p->des0 = 0; p->des1 = 0; p->des2 = 0; p->des3 = 0; @@ -580,6 +587,7 @@ static int dw_mci_idmac_init(struct dw_mci *host) i++, p++) { p->des3 = cpu_to_le32(host->sg_dma + (sizeof(struct idmac_desc) * (i + 1))); + p->des0 = 0; p->des1 = 0; } @@ -1795,8 +1803,8 @@ static bool dw_mci_reset(struct dw_mci *host) } if (host->use_dma == TRANS_MODE_IDMAC) - /* It is also recommended that we reset and reprogram idmac */ - dw_mci_idmac_reset(host); + /* It is also required that we reinit idmac */ + dw_mci_idmac_init(host); ret = true; @@ -1944,8 +1952,9 @@ static void dw_mci_set_drto(struct dw_mci *host) drto_div = (mci_readl(host, CLKDIV) & 0xff) * 2; if (drto_div == 0) drto_div = 1; - drto_ms = DIV_ROUND_UP(MSEC_PER_SEC * drto_clks * drto_div, - host->bus_hz); + + drto_ms = DIV_ROUND_UP_ULL((u64)MSEC_PER_SEC * drto_clks * drto_div, + host->bus_hz); /* add a bit spare time */ drto_ms += 10; @@ -2778,12 +2787,57 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static int dw_mci_init_slot_caps(struct dw_mci_slot *slot) +{ + struct dw_mci *host = slot->host; + const struct dw_mci_drv_data *drv_data = host->drv_data; + struct mmc_host *mmc = slot->mmc; + int ctrl_id; + + if (host->pdata->caps) + mmc->caps = host->pdata->caps; + + /* + * Support MMC_CAP_ERASE by default. + * It needs to use trim/discard/erase commands. + */ + mmc->caps |= MMC_CAP_ERASE; + + if (host->pdata->pm_caps) + mmc->pm_caps = host->pdata->pm_caps; + + if (host->dev->of_node) { + ctrl_id = of_alias_get_id(host->dev->of_node, "mshc"); + if (ctrl_id < 0) + ctrl_id = 0; + } else { + ctrl_id = to_platform_device(host->dev)->id; + } + + if (drv_data && drv_data->caps) { + if (ctrl_id >= drv_data->num_caps) { + dev_err(host->dev, "invalid controller id %d\n", + ctrl_id); + return -EINVAL; + } + mmc->caps |= drv_data->caps[ctrl_id]; + } + + if (host->pdata->caps2) + mmc->caps2 = host->pdata->caps2; + + /* Process SDIO IRQs through the sdio_irq_work. */ + if (mmc->caps & MMC_CAP_SDIO_IRQ) + mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD; + + return 0; +} + static int dw_mci_init_slot(struct dw_mci *host) { struct mmc_host *mmc; struct dw_mci_slot *slot; - const struct dw_mci_drv_data *drv_data = host->drv_data; - int ctrl_id, ret; + int ret; u32 freq[2]; mmc = mmc_alloc_host(sizeof(struct dw_mci_slot), host->dev); @@ -2817,38 +2871,13 @@ static int dw_mci_init_slot(struct dw_mci *host) if (!mmc->ocr_avail) mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34; - if (host->pdata->caps) - mmc->caps = host->pdata->caps; - - /* - * Support MMC_CAP_ERASE by default. - * It needs to use trim/discard/erase commands. - */ - mmc->caps |= MMC_CAP_ERASE; - - if (host->pdata->pm_caps) - mmc->pm_caps = host->pdata->pm_caps; - - if (host->dev->of_node) { - ctrl_id = of_alias_get_id(host->dev->of_node, "mshc"); - if (ctrl_id < 0) - ctrl_id = 0; - } else { - ctrl_id = to_platform_device(host->dev)->id; - } - if (drv_data && drv_data->caps) - mmc->caps |= drv_data->caps[ctrl_id]; - - if (host->pdata->caps2) - mmc->caps2 = host->pdata->caps2; - ret = mmc_of_parse(mmc); if (ret) goto err_host_allocated; - /* Process SDIO IRQs through the sdio_irq_work. */ - if (mmc->caps & MMC_CAP_SDIO_IRQ) - mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD; + ret = dw_mci_init_slot_caps(slot); + if (ret) + goto err_host_allocated; /* Useful defaults if platform data is unset. */ if (host->use_dma == TRANS_MODE_IDMAC) { diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h index e3124f06a47e..1424bd490dd1 100644 --- a/drivers/mmc/host/dw_mmc.h +++ b/drivers/mmc/host/dw_mmc.h @@ -543,6 +543,7 @@ struct dw_mci_slot { /** * dw_mci driver data - dw-mshc implementation specific driver data. * @caps: mmc subsystem specified capabilities of the controller(s). + * @num_caps: number of capabilities specified by @caps. * @init: early implementation specific initialization. * @set_ios: handle bus specific extensions. * @parse_dt: parse implementation specific device tree properties. @@ -554,6 +555,7 @@ struct dw_mci_slot { */ struct dw_mci_drv_data { unsigned long *caps; + u32 num_caps; int (*init)(struct dw_mci *host); void (*set_ios)(struct dw_mci *host, struct mmc_ios *ios); int (*parse_dt)(struct dw_mci *host); diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 4065da58789d..32321bd596d8 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -680,7 +680,7 @@ static int sdhci_acpi_probe(struct platform_device *pdev) host->hw_name = "ACPI"; host->ops = &sdhci_acpi_ops_dflt; host->irq = platform_get_irq(pdev, 0); - if (host->irq <= 0) { + if (host->irq < 0) { err = -EINVAL; goto err_free; } diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 6d1a983e6227..82c4f05f91d8 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -654,9 +654,36 @@ static void byt_read_dsm(struct sdhci_pci_slot *slot) slot->chip->rpm_retune = intel_host->d3_retune; } -static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) +static int intel_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + int err = sdhci_execute_tuning(mmc, opcode); + struct sdhci_host *host = mmc_priv(mmc); + + if (err) + return err; + + /* + * Tuning can leave the IP in an active state (Buffer Read Enable bit + * set) which prevents the entry to low power states (i.e. S0i3). Data + * reset will clear it. + */ + sdhci_reset(host, SDHCI_RESET_DATA); + + return 0; +} + +static void byt_probe_slot(struct sdhci_pci_slot *slot) { + struct mmc_host_ops *ops = &slot->host->mmc_host_ops; + byt_read_dsm(slot); + + ops->execute_tuning = intel_execute_tuning; +} + +static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) +{ + byt_probe_slot(slot); slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE | MMC_CAP_HW_RESET | MMC_CAP_1_8V_DDR | MMC_CAP_CMD_DURING_TFR | @@ -779,7 +806,7 @@ static int ni_byt_sdio_probe_slot(struct sdhci_pci_slot *slot) { int err; - byt_read_dsm(slot); + byt_probe_slot(slot); err = ni_set_max_freq(slot); if (err) @@ -792,7 +819,7 @@ static int ni_byt_sdio_probe_slot(struct sdhci_pci_slot *slot) static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot) { - byt_read_dsm(slot); + byt_probe_slot(slot); slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE | MMC_CAP_WAIT_WHILE_BUSY; return 0; @@ -800,7 +827,7 @@ static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot) static int byt_sd_probe_slot(struct sdhci_pci_slot *slot) { - byt_read_dsm(slot); + byt_probe_slot(slot); slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY | MMC_CAP_AGGRESSIVE_PM | MMC_CAP_CD_WAKE; slot->cd_idx = 0; diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index de8c902059b8..7d80a8bb96fe 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -479,7 +479,7 @@ static int shrink_ecclayout(struct mtd_info *mtd, for (i = 0; i < MTD_MAX_ECCPOS_ENTRIES;) { u32 eccpos; - ret = mtd_ooblayout_ecc(mtd, section, &oobregion); + ret = mtd_ooblayout_ecc(mtd, section++, &oobregion); if (ret < 0) { if (ret != -ERANGE) return ret; @@ -526,7 +526,7 @@ static int get_oobinfo(struct mtd_info *mtd, struct nand_oobinfo *to) for (i = 0; i < ARRAY_SIZE(to->eccpos);) { u32 eccpos; - ret = mtd_ooblayout_ecc(mtd, section, &oobregion); + ret = mtd_ooblayout_ecc(mtd, section++, &oobregion); if (ret < 0) { if (ret != -ERANGE) return ret; diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c index 4872a7ba6503..5a9c2f0020c2 100644 --- a/drivers/mtd/nand/fsl_ifc_nand.c +++ b/drivers/mtd/nand/fsl_ifc_nand.c @@ -173,14 +173,9 @@ static void set_addr(struct mtd_info *mtd, int column, int page_addr, int oob) /* returns nonzero if entire page is blank */ static int check_read_ecc(struct mtd_info *mtd, struct fsl_ifc_ctrl *ctrl, - u32 *eccstat, unsigned int bufnum) + u32 eccstat, unsigned int bufnum) { - u32 reg = eccstat[bufnum / 4]; - int errors; - - errors = (reg >> ((3 - bufnum % 4) * 8)) & 15; - - return errors; + return (eccstat >> ((3 - bufnum % 4) * 8)) & 15; } /* @@ -193,7 +188,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd) struct fsl_ifc_ctrl *ctrl = priv->ctrl; struct fsl_ifc_nand_ctrl *nctrl = ifc_nand_ctrl; struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs; - u32 eccstat[4]; + u32 eccstat; int i; /* set the chip select for NAND Transaction */ @@ -228,19 +223,17 @@ static void fsl_ifc_run_command(struct mtd_info *mtd) if (nctrl->eccread) { int errors; int bufnum = nctrl->page & priv->bufnum_mask; - int sector = bufnum * chip->ecc.steps; - int sector_end = sector + chip->ecc.steps - 1; + int sector_start = bufnum * chip->ecc.steps; + int sector_end = sector_start + chip->ecc.steps - 1; __be32 *eccstat_regs; - if (ctrl->version >= FSL_IFC_VERSION_2_0_0) - eccstat_regs = ifc->ifc_nand.v2_nand_eccstat; - else - eccstat_regs = ifc->ifc_nand.v1_nand_eccstat; + eccstat_regs = ifc->ifc_nand.nand_eccstat; + eccstat = ifc_in32(&eccstat_regs[sector_start / 4]); - for (i = sector / 4; i <= sector_end / 4; i++) - eccstat[i] = ifc_in32(&eccstat_regs[i]); + for (i = sector_start; i <= sector_end; i++) { + if (i != sector_start && !(i % 4)) + eccstat = ifc_in32(&eccstat_regs[i / 4]); - for (i = sector; i <= sector_end; i++) { errors = check_read_ecc(mtd, ctrl, eccstat, i); if (errors == 15) { @@ -626,6 +619,7 @@ static int fsl_ifc_wait(struct mtd_info *mtd, struct nand_chip *chip) struct fsl_ifc_ctrl *ctrl = priv->ctrl; struct fsl_ifc_runtime __iomem *ifc = ctrl->rregs; u32 nand_fsr; + int status; /* Use READ_STATUS command, but wait for the device to be ready */ ifc_out32((IFC_FIR_OP_CW0 << IFC_NAND_FIR0_OP0_SHIFT) | @@ -640,12 +634,12 @@ static int fsl_ifc_wait(struct mtd_info *mtd, struct nand_chip *chip) fsl_ifc_run_command(mtd); nand_fsr = ifc_in32(&ifc->ifc_nand.nand_fsr); - + status = nand_fsr >> 24; /* * The chip always seems to report that it is * write-protected, even when it is not. */ - return nand_fsr | NAND_STATUS_WP; + return status | NAND_STATUS_WP; } /* diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index 1e37313054f3..6da69af103e6 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -390,37 +390,23 @@ static int cc770_get_berr_counter(const struct net_device *dev, return 0; } -static netdev_tx_t cc770_start_xmit(struct sk_buff *skb, struct net_device *dev) +static void cc770_tx(struct net_device *dev, int mo) { struct cc770_priv *priv = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct can_frame *cf = (struct can_frame *)skb->data; - unsigned int mo = obj2msgobj(CC770_OBJ_TX); + struct can_frame *cf = (struct can_frame *)priv->tx_skb->data; u8 dlc, rtr; u32 id; int i; - if (can_dropped_invalid_skb(dev, skb)) - return NETDEV_TX_OK; - - if ((cc770_read_reg(priv, - msgobj[mo].ctrl1) & TXRQST_UNC) == TXRQST_SET) { - netdev_err(dev, "TX register is still occupied!\n"); - return NETDEV_TX_BUSY; - } - - netif_stop_queue(dev); - dlc = cf->can_dlc; id = cf->can_id; - if (cf->can_id & CAN_RTR_FLAG) - rtr = 0; - else - rtr = MSGCFG_DIR; + rtr = cf->can_id & CAN_RTR_FLAG ? 0 : MSGCFG_DIR; + + cc770_write_reg(priv, msgobj[mo].ctrl0, + MSGVAL_RES | TXIE_RES | RXIE_RES | INTPND_RES); cc770_write_reg(priv, msgobj[mo].ctrl1, RMTPND_RES | TXRQST_RES | CPUUPD_SET | NEWDAT_RES); - cc770_write_reg(priv, msgobj[mo].ctrl0, - MSGVAL_SET | TXIE_SET | RXIE_RES | INTPND_RES); + if (id & CAN_EFF_FLAG) { id &= CAN_EFF_MASK; cc770_write_reg(priv, msgobj[mo].config, @@ -439,22 +425,30 @@ static netdev_tx_t cc770_start_xmit(struct sk_buff *skb, struct net_device *dev) for (i = 0; i < dlc; i++) cc770_write_reg(priv, msgobj[mo].data[i], cf->data[i]); - /* Store echo skb before starting the transfer */ - can_put_echo_skb(skb, dev, 0); - cc770_write_reg(priv, msgobj[mo].ctrl1, - RMTPND_RES | TXRQST_SET | CPUUPD_RES | NEWDAT_UNC); + RMTPND_UNC | TXRQST_SET | CPUUPD_RES | NEWDAT_UNC); + cc770_write_reg(priv, msgobj[mo].ctrl0, + MSGVAL_SET | TXIE_SET | RXIE_SET | INTPND_UNC); +} - stats->tx_bytes += dlc; +static netdev_tx_t cc770_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct cc770_priv *priv = netdev_priv(dev); + unsigned int mo = obj2msgobj(CC770_OBJ_TX); + if (can_dropped_invalid_skb(dev, skb)) + return NETDEV_TX_OK; - /* - * HM: We had some cases of repeated IRQs so make sure the - * INT is acknowledged I know it's already further up, but - * doing again fixed the issue - */ - cc770_write_reg(priv, msgobj[mo].ctrl0, - MSGVAL_UNC | TXIE_UNC | RXIE_UNC | INTPND_RES); + netif_stop_queue(dev); + + if ((cc770_read_reg(priv, + msgobj[mo].ctrl1) & TXRQST_UNC) == TXRQST_SET) { + netdev_err(dev, "TX register is still occupied!\n"); + return NETDEV_TX_BUSY; + } + + priv->tx_skb = skb; + cc770_tx(dev, mo); return NETDEV_TX_OK; } @@ -680,19 +674,46 @@ static void cc770_tx_interrupt(struct net_device *dev, unsigned int o) struct cc770_priv *priv = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; unsigned int mo = obj2msgobj(o); + struct can_frame *cf; + u8 ctrl1; + + ctrl1 = cc770_read_reg(priv, msgobj[mo].ctrl1); - /* Nothing more to send, switch off interrupts */ cc770_write_reg(priv, msgobj[mo].ctrl0, MSGVAL_RES | TXIE_RES | RXIE_RES | INTPND_RES); - /* - * We had some cases of repeated IRQ so make sure the - * INT is acknowledged + cc770_write_reg(priv, msgobj[mo].ctrl1, + RMTPND_RES | TXRQST_RES | MSGLST_RES | NEWDAT_RES); + + if (unlikely(!priv->tx_skb)) { + netdev_err(dev, "missing tx skb in tx interrupt\n"); + return; + } + + if (unlikely(ctrl1 & MSGLST_SET)) { + stats->rx_over_errors++; + stats->rx_errors++; + } + + /* When the CC770 is sending an RTR message and it receives a regular + * message that matches the id of the RTR message, it will overwrite the + * outgoing message in the TX register. When this happens we must + * process the received message and try to transmit the outgoing skb + * again. */ - cc770_write_reg(priv, msgobj[mo].ctrl0, - MSGVAL_UNC | TXIE_UNC | RXIE_UNC | INTPND_RES); + if (unlikely(ctrl1 & NEWDAT_SET)) { + cc770_rx(dev, mo, ctrl1); + cc770_tx(dev, mo); + return; + } + cf = (struct can_frame *)priv->tx_skb->data; + stats->tx_bytes += cf->can_dlc; stats->tx_packets++; + + can_put_echo_skb(priv->tx_skb, dev, 0); can_get_echo_skb(dev, 0); + priv->tx_skb = NULL; + netif_wake_queue(dev); } @@ -804,6 +825,7 @@ struct net_device *alloc_cc770dev(int sizeof_priv) priv->can.do_set_bittiming = cc770_set_bittiming; priv->can.do_set_mode = cc770_set_mode; priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES; + priv->tx_skb = NULL; memcpy(priv->obj_flags, cc770_obj_flags, sizeof(cc770_obj_flags)); diff --git a/drivers/net/can/cc770/cc770.h b/drivers/net/can/cc770/cc770.h index a1739db98d91..95752e1d1283 100644 --- a/drivers/net/can/cc770/cc770.h +++ b/drivers/net/can/cc770/cc770.h @@ -193,6 +193,8 @@ struct cc770_priv { u8 cpu_interface; /* CPU interface register */ u8 clkout; /* Clock out register */ u8 bus_config; /* Bus conffiguration register */ + + struct sk_buff *tx_skb; }; struct net_device *alloc_cc770dev(int sizeof_priv); diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 2772d05ff11c..fedd927ba6ed 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -30,6 +30,7 @@ #define IFI_CANFD_STCMD_ERROR_ACTIVE BIT(2) #define IFI_CANFD_STCMD_ERROR_PASSIVE BIT(3) #define IFI_CANFD_STCMD_BUSOFF BIT(4) +#define IFI_CANFD_STCMD_ERROR_WARNING BIT(5) #define IFI_CANFD_STCMD_BUSMONITOR BIT(16) #define IFI_CANFD_STCMD_LOOPBACK BIT(18) #define IFI_CANFD_STCMD_DISABLE_CANFD BIT(24) @@ -52,7 +53,10 @@ #define IFI_CANFD_TXSTCMD_OVERFLOW BIT(13) #define IFI_CANFD_INTERRUPT 0xc +#define IFI_CANFD_INTERRUPT_ERROR_BUSOFF BIT(0) #define IFI_CANFD_INTERRUPT_ERROR_WARNING BIT(1) +#define IFI_CANFD_INTERRUPT_ERROR_STATE_CHG BIT(2) +#define IFI_CANFD_INTERRUPT_ERROR_REC_TEC_INC BIT(3) #define IFI_CANFD_INTERRUPT_ERROR_COUNTER BIT(10) #define IFI_CANFD_INTERRUPT_TXFIFO_EMPTY BIT(16) #define IFI_CANFD_INTERRUPT_TXFIFO_REMOVE BIT(22) @@ -61,6 +65,10 @@ #define IFI_CANFD_INTERRUPT_SET_IRQ ((u32)BIT(31)) #define IFI_CANFD_IRQMASK 0x10 +#define IFI_CANFD_IRQMASK_ERROR_BUSOFF BIT(0) +#define IFI_CANFD_IRQMASK_ERROR_WARNING BIT(1) +#define IFI_CANFD_IRQMASK_ERROR_STATE_CHG BIT(2) +#define IFI_CANFD_IRQMASK_ERROR_REC_TEC_INC BIT(3) #define IFI_CANFD_IRQMASK_SET_ERR BIT(7) #define IFI_CANFD_IRQMASK_SET_TS BIT(15) #define IFI_CANFD_IRQMASK_TXFIFO_EMPTY BIT(16) @@ -136,6 +144,8 @@ #define IFI_CANFD_SYSCLOCK 0x50 #define IFI_CANFD_VER 0x54 +#define IFI_CANFD_VER_REV_MASK 0xff +#define IFI_CANFD_VER_REV_MIN_SUPPORTED 0x15 #define IFI_CANFD_IP_ID 0x58 #define IFI_CANFD_IP_ID_VALUE 0xD073CAFD @@ -220,7 +230,10 @@ static void ifi_canfd_irq_enable(struct net_device *ndev, bool enable) if (enable) { enirq = IFI_CANFD_IRQMASK_TXFIFO_EMPTY | - IFI_CANFD_IRQMASK_RXFIFO_NEMPTY; + IFI_CANFD_IRQMASK_RXFIFO_NEMPTY | + IFI_CANFD_IRQMASK_ERROR_STATE_CHG | + IFI_CANFD_IRQMASK_ERROR_WARNING | + IFI_CANFD_IRQMASK_ERROR_BUSOFF; if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) enirq |= IFI_CANFD_INTERRUPT_ERROR_COUNTER; } @@ -361,12 +374,13 @@ static int ifi_canfd_handle_lost_msg(struct net_device *ndev) return 1; } -static int ifi_canfd_handle_lec_err(struct net_device *ndev, const u32 errctr) +static int ifi_canfd_handle_lec_err(struct net_device *ndev) { struct ifi_canfd_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; + u32 errctr = readl(priv->base + IFI_CANFD_ERROR_CTR); const u32 errmask = IFI_CANFD_ERROR_CTR_OVERLOAD_FIRST | IFI_CANFD_ERROR_CTR_ACK_ERROR_FIRST | IFI_CANFD_ERROR_CTR_BIT0_ERROR_FIRST | @@ -449,6 +463,11 @@ static int ifi_canfd_handle_state_change(struct net_device *ndev, switch (new_state) { case CAN_STATE_ERROR_ACTIVE: + /* error active state */ + priv->can.can_stats.error_warning++; + priv->can.state = CAN_STATE_ERROR_ACTIVE; + break; + case CAN_STATE_ERROR_WARNING: /* error warning state */ priv->can.can_stats.error_warning++; priv->can.state = CAN_STATE_ERROR_WARNING; @@ -477,7 +496,7 @@ static int ifi_canfd_handle_state_change(struct net_device *ndev, ifi_canfd_get_berr_counter(ndev, &bec); switch (new_state) { - case CAN_STATE_ERROR_ACTIVE: + case CAN_STATE_ERROR_WARNING: /* error warning state */ cf->can_id |= CAN_ERR_CRTL; cf->data[1] = (bec.txerr > bec.rxerr) ? @@ -510,22 +529,21 @@ static int ifi_canfd_handle_state_change(struct net_device *ndev, return 1; } -static int ifi_canfd_handle_state_errors(struct net_device *ndev, u32 stcmd) +static int ifi_canfd_handle_state_errors(struct net_device *ndev) { struct ifi_canfd_priv *priv = netdev_priv(ndev); + u32 stcmd = readl(priv->base + IFI_CANFD_STCMD); int work_done = 0; - u32 isr; - /* - * The ErrWarn condition is a little special, since the bit is - * located in the INTERRUPT register instead of STCMD register. - */ - isr = readl(priv->base + IFI_CANFD_INTERRUPT); - if ((isr & IFI_CANFD_INTERRUPT_ERROR_WARNING) && + if ((stcmd & IFI_CANFD_STCMD_ERROR_ACTIVE) && + (priv->can.state != CAN_STATE_ERROR_ACTIVE)) { + netdev_dbg(ndev, "Error, entered active state\n"); + work_done += ifi_canfd_handle_state_change(ndev, + CAN_STATE_ERROR_ACTIVE); + } + + if ((stcmd & IFI_CANFD_STCMD_ERROR_WARNING) && (priv->can.state != CAN_STATE_ERROR_WARNING)) { - /* Clear the interrupt */ - writel(IFI_CANFD_INTERRUPT_ERROR_WARNING, - priv->base + IFI_CANFD_INTERRUPT); netdev_dbg(ndev, "Error, entered warning state\n"); work_done += ifi_canfd_handle_state_change(ndev, CAN_STATE_ERROR_WARNING); @@ -552,18 +570,11 @@ static int ifi_canfd_poll(struct napi_struct *napi, int quota) { struct net_device *ndev = napi->dev; struct ifi_canfd_priv *priv = netdev_priv(ndev); - const u32 stcmd_state_mask = IFI_CANFD_STCMD_ERROR_PASSIVE | - IFI_CANFD_STCMD_BUSOFF; - int work_done = 0; - - u32 stcmd = readl(priv->base + IFI_CANFD_STCMD); u32 rxstcmd = readl(priv->base + IFI_CANFD_RXSTCMD); - u32 errctr = readl(priv->base + IFI_CANFD_ERROR_CTR); + int work_done = 0; /* Handle bus state changes */ - if ((stcmd & stcmd_state_mask) || - ((stcmd & IFI_CANFD_STCMD_ERROR_ACTIVE) == 0)) - work_done += ifi_canfd_handle_state_errors(ndev, stcmd); + work_done += ifi_canfd_handle_state_errors(ndev); /* Handle lost messages on RX */ if (rxstcmd & IFI_CANFD_RXSTCMD_OVERFLOW) @@ -571,7 +582,7 @@ static int ifi_canfd_poll(struct napi_struct *napi, int quota) /* Handle lec errors on the bus */ if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) - work_done += ifi_canfd_handle_lec_err(ndev, errctr); + work_done += ifi_canfd_handle_lec_err(ndev); /* Handle normal messages on RX */ if (!(rxstcmd & IFI_CANFD_RXSTCMD_EMPTY)) @@ -592,12 +603,13 @@ static irqreturn_t ifi_canfd_isr(int irq, void *dev_id) struct net_device_stats *stats = &ndev->stats; const u32 rx_irq_mask = IFI_CANFD_INTERRUPT_RXFIFO_NEMPTY | IFI_CANFD_INTERRUPT_RXFIFO_NEMPTY_PER | + IFI_CANFD_INTERRUPT_ERROR_COUNTER | + IFI_CANFD_INTERRUPT_ERROR_STATE_CHG | IFI_CANFD_INTERRUPT_ERROR_WARNING | - IFI_CANFD_INTERRUPT_ERROR_COUNTER; + IFI_CANFD_INTERRUPT_ERROR_BUSOFF; const u32 tx_irq_mask = IFI_CANFD_INTERRUPT_TXFIFO_EMPTY | IFI_CANFD_INTERRUPT_TXFIFO_REMOVE; - const u32 clr_irq_mask = ~((u32)(IFI_CANFD_INTERRUPT_SET_IRQ | - IFI_CANFD_INTERRUPT_ERROR_WARNING)); + const u32 clr_irq_mask = ~((u32)IFI_CANFD_INTERRUPT_SET_IRQ); u32 isr; isr = readl(priv->base + IFI_CANFD_INTERRUPT); @@ -933,7 +945,7 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev) struct resource *res; void __iomem *addr; int irq, ret; - u32 id; + u32 id, rev; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); addr = devm_ioremap_resource(dev, res); @@ -947,6 +959,13 @@ static int ifi_canfd_plat_probe(struct platform_device *pdev) return -EINVAL; } + rev = readl(addr + IFI_CANFD_VER) & IFI_CANFD_VER_REV_MASK; + if (rev < IFI_CANFD_VER_REV_MIN_SUPPORTED) { + dev_err(dev, "This block is too old (rev %i), minimum supported is rev %i\n", + rev, IFI_CANFD_VER_REV_MIN_SUPPORTED); + return -EINVAL; + } + ndev = alloc_candev(sizeof(*priv), 1); if (!ndev) return -ENOMEM; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 2594f7779c6f..b397a33f3d32 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -26,6 +26,7 @@ #include <linux/pm_runtime.h> #include <linux/iopoll.h> #include <linux/can/dev.h> +#include <linux/pinctrl/consumer.h> /* napi related */ #define M_CAN_NAPI_WEIGHT 64 @@ -253,7 +254,7 @@ enum m_can_mram_cfg { /* Rx FIFO 0/1 Configuration (RXF0C/RXF1C) */ #define RXFC_FWM_SHIFT 24 -#define RXFC_FWM_MASK (0x7f < RXFC_FWM_SHIFT) +#define RXFC_FWM_MASK (0x7f << RXFC_FWM_SHIFT) #define RXFC_FS_SHIFT 16 #define RXFC_FS_MASK (0x7f << RXFC_FS_SHIFT) @@ -1700,6 +1701,8 @@ static __maybe_unused int m_can_suspend(struct device *dev) m_can_clk_stop(priv); } + pinctrl_pm_select_sleep_state(dev); + priv->can.state = CAN_STATE_SLEEPING; return 0; @@ -1710,6 +1713,8 @@ static __maybe_unused int m_can_resume(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct m_can_priv *priv = netdev_priv(ndev); + pinctrl_pm_select_default_state(dev); + m_can_init_ram(priv); priv->can.state = CAN_STATE_ERROR_ACTIVE; diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index 55513411a82e..ed8561d4a90f 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -262,7 +262,6 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv, spin_lock_irqsave(&priv->echo_lock, flags); can_get_echo_skb(priv->ndev, msg->client); - spin_unlock_irqrestore(&priv->echo_lock, flags); /* count bytes of the echo instead of skb */ stats->tx_bytes += cf_len; @@ -271,6 +270,7 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv, /* restart tx queue (a slot is free) */ netif_wake_queue(priv->ndev); + spin_unlock_irqrestore(&priv->echo_lock, flags); return 0; } @@ -333,7 +333,6 @@ static int pucan_handle_status(struct peak_canfd_priv *priv, /* this STATUS is the CNF of the RX_BARRIER: Tx path can be setup */ if (pucan_status_is_rx_barrier(msg)) { - unsigned long flags; if (priv->enable_tx_path) { int err = priv->enable_tx_path(priv); @@ -342,16 +341,8 @@ static int pucan_handle_status(struct peak_canfd_priv *priv, return err; } - /* restart network queue only if echo skb array is free */ - spin_lock_irqsave(&priv->echo_lock, flags); - - if (!priv->can.echo_skb[priv->echo_idx]) { - spin_unlock_irqrestore(&priv->echo_lock, flags); - - netif_wake_queue(ndev); - } else { - spin_unlock_irqrestore(&priv->echo_lock, flags); - } + /* start network queue (echo_skb array is empty) */ + netif_start_queue(ndev); return 0; } @@ -726,11 +717,6 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb, */ should_stop_tx_queue = !!(priv->can.echo_skb[priv->echo_idx]); - spin_unlock_irqrestore(&priv->echo_lock, flags); - - /* write the skb on the interface */ - priv->write_tx_msg(priv, msg); - /* stop network tx queue if not enough room to save one more msg too */ if (priv->can.ctrlmode & CAN_CTRLMODE_FD) should_stop_tx_queue |= (room_left < @@ -742,6 +728,11 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb, if (should_stop_tx_queue) netif_stop_queue(ndev); + spin_unlock_irqrestore(&priv->echo_lock, flags); + + /* write the skb on the interface */ + priv->write_tx_msg(priv, msg); + return NETDEV_TX_OK; } diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index 788c3464a3b0..3c51a884db87 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -349,8 +349,12 @@ static irqreturn_t pciefd_irq_handler(int irq, void *arg) priv->tx_pages_free++; spin_unlock_irqrestore(&priv->tx_lock, flags); - /* wake producer up */ - netif_wake_queue(priv->ucan.ndev); + /* wake producer up (only if enough room in echo_skb array) */ + spin_lock_irqsave(&priv->ucan.echo_lock, flags); + if (!priv->ucan.can.echo_skb[priv->ucan.echo_idx]) + netif_wake_queue(priv->ucan.ndev); + + spin_unlock_irqrestore(&priv->ucan.echo_lock, flags); } /* re-enable Rx DMA transfer for this CAN */ diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index d040aeb45172..15c2a831edf1 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -1,7 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_NET_DSA_BCM_SF2) += bcm-sf2.o bcm-sf2-objs := bcm_sf2.o bcm_sf2_cfp.o -obj-$(CONFIG_NET_DSA_LOOP) += dsa_loop.o dsa_loop_bdinfo.o +obj-$(CONFIG_NET_DSA_LOOP) += dsa_loop.o +ifdef CONFIG_NET_DSA_LOOP +obj-$(CONFIG_FIXED_PHY) += dsa_loop_bdinfo.o +endif obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index db830a1141d9..63e02a54d537 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -814,8 +814,8 @@ void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data) unsigned int i; for (i = 0; i < mib_size; i++) - memcpy(data + i * ETH_GSTRING_LEN, - mibs[i].name, ETH_GSTRING_LEN); + strlcpy(data + i * ETH_GSTRING_LEN, + mibs[i].name, ETH_GSTRING_LEN); } EXPORT_SYMBOL(b53_get_strings); diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig index 29c3075bfb05..fdc673484add 100644 --- a/drivers/net/ethernet/8390/Kconfig +++ b/drivers/net/ethernet/8390/Kconfig @@ -3,7 +3,7 @@ # config NET_VENDOR_8390 - bool "National Semi-conductor 8390 devices" + bool "National Semiconductor 8390 devices" default y depends on NET_VENDOR_NATSEMI ---help--- diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index 0b49f1aeebd3..fc7383106946 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -36,6 +36,8 @@ #define AQ_CFG_TX_FRAME_MAX (16U * 1024U) #define AQ_CFG_RX_FRAME_MAX (4U * 1024U) +#define AQ_CFG_TX_CLEAN_BUDGET 256U + /* LRO */ #define AQ_CFG_IS_LRO_DEF 1U diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index ebbaf63eaf47..c96a92118b8b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -247,6 +247,8 @@ void aq_nic_ndev_init(struct aq_nic_s *self) self->ndev->hw_features |= aq_hw_caps->hw_features; self->ndev->features = aq_hw_caps->hw_features; self->ndev->priv_flags = aq_hw_caps->hw_priv_flags; + self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN; self->ndev->max_mtu = aq_hw_caps->mtu - ETH_FCS_LEN - ETH_HLEN; @@ -937,3 +939,23 @@ err_exit: out: return err; } + +void aq_nic_shutdown(struct aq_nic_s *self) +{ + int err = 0; + + if (!self->ndev) + return; + + rtnl_lock(); + + netif_device_detach(self->ndev); + + err = aq_nic_stop(self); + if (err < 0) + goto err_exit; + aq_nic_deinit(self); + +err_exit: + rtnl_unlock(); +}
\ No newline at end of file diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index d16b0f1a95aa..219b550d1665 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -118,5 +118,6 @@ struct aq_nic_cfg_s *aq_nic_get_cfg(struct aq_nic_s *self); u32 aq_nic_get_fw_version(struct aq_nic_s *self); int aq_nic_change_pm_state(struct aq_nic_s *self, pm_message_t *pm_msg); int aq_nic_update_interrupt_moderation_settings(struct aq_nic_s *self); +void aq_nic_shutdown(struct aq_nic_s *self); #endif /* AQ_NIC_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 87c4308b52a7..ecc6306f940f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -323,6 +323,20 @@ static void aq_pci_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static void aq_pci_shutdown(struct pci_dev *pdev) +{ + struct aq_nic_s *self = pci_get_drvdata(pdev); + + aq_nic_shutdown(self); + + pci_disable_device(pdev); + + if (system_state == SYSTEM_POWER_OFF) { + pci_wake_from_d3(pdev, false); + pci_set_power_state(pdev, PCI_D3hot); + } +} + static int aq_pci_suspend(struct pci_dev *pdev, pm_message_t pm_msg) { struct aq_nic_s *self = pci_get_drvdata(pdev); @@ -345,6 +359,7 @@ static struct pci_driver aq_pci_ops = { .remove = aq_pci_remove, .suspend = aq_pci_suspend, .resume = aq_pci_resume, + .shutdown = aq_pci_shutdown, }; module_pci_driver(aq_pci_ops); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 0be6a11370bb..b5f1f62e8e25 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -136,11 +136,12 @@ void aq_ring_queue_stop(struct aq_ring_s *ring) netif_stop_subqueue(ndev, ring->idx); } -void aq_ring_tx_clean(struct aq_ring_s *self) +bool aq_ring_tx_clean(struct aq_ring_s *self) { struct device *dev = aq_nic_get_dev(self->aq_nic); + unsigned int budget = AQ_CFG_TX_CLEAN_BUDGET; - for (; self->sw_head != self->hw_head; + for (; self->sw_head != self->hw_head && budget--; self->sw_head = aq_ring_next_dx(self, self->sw_head)) { struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head]; @@ -167,6 +168,8 @@ void aq_ring_tx_clean(struct aq_ring_s *self) buff->pa = 0U; buff->eop_index = 0xffffU; } + + return !!budget; } #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 965fae0fb6e0..ac1329f4051d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -153,7 +153,7 @@ void aq_ring_free(struct aq_ring_s *self); void aq_ring_update_queue_state(struct aq_ring_s *ring); void aq_ring_queue_wake(struct aq_ring_s *ring); void aq_ring_queue_stop(struct aq_ring_s *ring); -void aq_ring_tx_clean(struct aq_ring_s *self); +bool aq_ring_tx_clean(struct aq_ring_s *self); int aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, int *work_done, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index f890b8a5a862..d335c334fa56 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -35,12 +35,12 @@ struct aq_vec_s { static int aq_vec_poll(struct napi_struct *napi, int budget) { struct aq_vec_s *self = container_of(napi, struct aq_vec_s, napi); + unsigned int sw_tail_old = 0U; struct aq_ring_s *ring = NULL; + bool was_tx_cleaned = true; + unsigned int i = 0U; int work_done = 0; int err = 0; - unsigned int i = 0U; - unsigned int sw_tail_old = 0U; - bool was_tx_cleaned = false; if (!self) { err = -EINVAL; @@ -57,9 +57,8 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (ring[AQ_VEC_TX_ID].sw_head != ring[AQ_VEC_TX_ID].hw_head) { - aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); + was_tx_cleaned = aq_ring_tx_clean(&ring[AQ_VEC_TX_ID]); aq_ring_update_queue_state(&ring[AQ_VEC_TX_ID]); - was_tx_cleaned = true; } err = self->aq_hw_ops->hw_ring_rx_receive(self->aq_hw, @@ -90,7 +89,7 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) } } - if (was_tx_cleaned) + if (!was_tx_cleaned) work_done = budget; if (work_done < budget) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 967f0fd07fcf..d3b847ec7465 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -21,6 +21,10 @@ #define HW_ATL_UCP_0X370_REG 0x0370U +#define HW_ATL_MIF_CMD 0x0200U +#define HW_ATL_MIF_ADDR 0x0208U +#define HW_ATL_MIF_VAL 0x020CU + #define HW_ATL_FW_SM_RAM 0x2U #define HW_ATL_MPI_FW_VERSION 0x18 #define HW_ATL_MPI_CONTROL_ADR 0x0368U @@ -79,16 +83,15 @@ int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops) static int hw_atl_utils_soft_reset_flb(struct aq_hw_s *self) { + u32 gsr, val; int k = 0; - u32 gsr; aq_hw_write_reg(self, 0x404, 0x40e1); AQ_HW_SLEEP(50); /* Cleanup SPI */ - aq_hw_write_reg(self, 0x534, 0xA0); - aq_hw_write_reg(self, 0x100, 0x9F); - aq_hw_write_reg(self, 0x100, 0x809F); + val = aq_hw_read_reg(self, 0x53C); + aq_hw_write_reg(self, 0x53C, val | 0x10); gsr = aq_hw_read_reg(self, HW_ATL_GLB_SOFT_RES_ADR); aq_hw_write_reg(self, HW_ATL_GLB_SOFT_RES_ADR, (gsr & 0xBFFF) | 0x8000); @@ -97,7 +100,14 @@ static int hw_atl_utils_soft_reset_flb(struct aq_hw_s *self) aq_hw_write_reg(self, 0x404, 0x80e0); aq_hw_write_reg(self, 0x32a8, 0x0); aq_hw_write_reg(self, 0x520, 0x1); + + /* Reset SPI again because of possible interrupted SPI burst */ + val = aq_hw_read_reg(self, 0x53C); + aq_hw_write_reg(self, 0x53C, val | 0x10); AQ_HW_SLEEP(10); + /* Clear SPI reset state */ + aq_hw_write_reg(self, 0x53C, val & ~0x10); + aq_hw_write_reg(self, 0x404, 0x180e0); for (k = 0; k < 1000; k++) { @@ -141,13 +151,15 @@ static int hw_atl_utils_soft_reset_flb(struct aq_hw_s *self) aq_pr_err("FW kickstart failed\n"); return -EIO; } + /* Old FW requires fixed delay after init */ + AQ_HW_SLEEP(15); return 0; } static int hw_atl_utils_soft_reset_rbl(struct aq_hw_s *self) { - u32 gsr, rbl_status; + u32 gsr, val, rbl_status; int k; aq_hw_write_reg(self, 0x404, 0x40e1); @@ -157,6 +169,10 @@ static int hw_atl_utils_soft_reset_rbl(struct aq_hw_s *self) /* Alter RBL status */ aq_hw_write_reg(self, 0x388, 0xDEAD); + /* Cleanup SPI */ + val = aq_hw_read_reg(self, 0x53C); + aq_hw_write_reg(self, 0x53C, val | 0x10); + /* Global software reset*/ hw_atl_rx_rx_reg_res_dis_set(self, 0U); hw_atl_tx_tx_reg_res_dis_set(self, 0U); @@ -204,6 +220,8 @@ static int hw_atl_utils_soft_reset_rbl(struct aq_hw_s *self) aq_pr_err("FW kickstart failed\n"); return -EIO; } + /* Old FW requires fixed delay after init */ + AQ_HW_SLEEP(15); return 0; } @@ -255,18 +273,22 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a, } } - aq_hw_write_reg(self, 0x00000208U, a); - - for (++cnt; --cnt;) { - u32 i = 0U; + aq_hw_write_reg(self, HW_ATL_MIF_ADDR, a); - aq_hw_write_reg(self, 0x00000200U, 0x00008000U); + for (++cnt; --cnt && !err;) { + aq_hw_write_reg(self, HW_ATL_MIF_CMD, 0x00008000U); - for (i = 1024U; - (0x100U & aq_hw_read_reg(self, 0x00000200U)) && --i;) { - } + if (IS_CHIP_FEATURE(REVISION_B1)) + AQ_HW_WAIT_FOR(a != aq_hw_read_reg(self, + HW_ATL_MIF_ADDR), + 1, 1000U); + else + AQ_HW_WAIT_FOR(!(0x100 & aq_hw_read_reg(self, + HW_ATL_MIF_CMD)), + 1, 1000U); - *(p++) = aq_hw_read_reg(self, 0x0000020CU); + *(p++) = aq_hw_read_reg(self, HW_ATL_MIF_VAL); + a += 4; } hw_atl_reg_glb_cpu_sem_set(self, 1U, HW_ATL_FW_SM_RAM); @@ -662,14 +684,18 @@ void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p) u32 val = hw_atl_reg_glb_mif_id_get(self); u32 mif_rev = val & 0xFFU; - if ((3U & mif_rev) == 1U) { - chip_features |= - HAL_ATLANTIC_UTILS_CHIP_REVISION_A0 | + if ((0xFU & mif_rev) == 1U) { + chip_features |= HAL_ATLANTIC_UTILS_CHIP_REVISION_A0 | HAL_ATLANTIC_UTILS_CHIP_MPI_AQ | HAL_ATLANTIC_UTILS_CHIP_MIPS; - } else if ((3U & mif_rev) == 2U) { - chip_features |= - HAL_ATLANTIC_UTILS_CHIP_REVISION_B0 | + } else if ((0xFU & mif_rev) == 2U) { + chip_features |= HAL_ATLANTIC_UTILS_CHIP_REVISION_B0 | + HAL_ATLANTIC_UTILS_CHIP_MPI_AQ | + HAL_ATLANTIC_UTILS_CHIP_MIPS | + HAL_ATLANTIC_UTILS_CHIP_TPO2 | + HAL_ATLANTIC_UTILS_CHIP_RPF2; + } else if ((0xFU & mif_rev) == 0xAU) { + chip_features |= HAL_ATLANTIC_UTILS_CHIP_REVISION_B1 | HAL_ATLANTIC_UTILS_CHIP_MPI_AQ | HAL_ATLANTIC_UTILS_CHIP_MIPS | HAL_ATLANTIC_UTILS_CHIP_TPO2 | diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h index 2c690947910a..cd8f18f39c61 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h @@ -161,6 +161,7 @@ struct __packed hw_aq_atl_utils_mbox { #define HAL_ATLANTIC_UTILS_CHIP_MPI_AQ 0x00000010U #define HAL_ATLANTIC_UTILS_CHIP_REVISION_A0 0x01000000U #define HAL_ATLANTIC_UTILS_CHIP_REVISION_B0 0x02000000U +#define HAL_ATLANTIC_UTILS_CHIP_REVISION_B1 0x04000000U #define IS_CHIP_FEATURE(_F_) (HAL_ATLANTIC_UTILS_CHIP_##_F_ & \ self->chip_features) diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h index 5265b937677b..a445de6837a6 100644 --- a/drivers/net/ethernet/aquantia/atlantic/ver.h +++ b/drivers/net/ethernet/aquantia/atlantic/ver.h @@ -13,7 +13,7 @@ #define NIC_MAJOR_DRIVER_VERSION 2 #define NIC_MINOR_DRIVER_VERSION 0 #define NIC_BUILD_DRIVER_VERSION 2 -#define NIC_REVISION_DRIVER_VERSION 0 +#define NIC_REVISION_DRIVER_VERSION 1 #define AQ_CFG_DRV_VERSION_SUFFIX "-kern" diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index 16f9bee992fe..0f6576802607 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -169,8 +169,10 @@ static int emac_rockchip_probe(struct platform_device *pdev) /* Optional regulator for PHY */ priv->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(priv->regulator)) { - if (PTR_ERR(priv->regulator) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(priv->regulator) == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto out_clk_disable; + } dev_err(dev, "no regulator found\n"); priv->regulator = NULL; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f15a8fc6dfc9..3fc549b88c43 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -855,10 +855,12 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring, static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, struct bcm_sysport_tx_ring *ring) { - unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs; unsigned int pkts_compl = 0, bytes_compl = 0; struct net_device *ndev = priv->netdev; + unsigned int txbds_processed = 0; struct bcm_sysport_cb *cb; + unsigned int txbds_ready; + unsigned int c_index; u32 hw_ind; /* Clear status before servicing to reduce spurious interrupts */ @@ -871,29 +873,23 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, /* Compute how many descriptors have been processed since last call */ hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index)); c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK; - ring->p_index = (hw_ind & RING_PROD_INDEX_MASK); - - last_c_index = ring->c_index; - num_tx_cbs = ring->size; - - c_index &= (num_tx_cbs - 1); - - if (c_index >= last_c_index) - last_tx_cn = c_index - last_c_index; - else - last_tx_cn = num_tx_cbs - last_c_index + c_index; + txbds_ready = (c_index - ring->c_index) & RING_CONS_INDEX_MASK; netif_dbg(priv, tx_done, ndev, - "ring=%d c_index=%d last_tx_cn=%d last_c_index=%d\n", - ring->index, c_index, last_tx_cn, last_c_index); + "ring=%d old_c_index=%u c_index=%u txbds_ready=%u\n", + ring->index, ring->c_index, c_index, txbds_ready); - while (last_tx_cn-- > 0) { - cb = ring->cbs + last_c_index; + while (txbds_processed < txbds_ready) { + cb = &ring->cbs[ring->clean_index]; bcm_sysport_tx_reclaim_one(ring, cb, &bytes_compl, &pkts_compl); ring->desc_count++; - last_c_index++; - last_c_index &= (num_tx_cbs - 1); + txbds_processed++; + + if (likely(ring->clean_index < ring->size - 1)) + ring->clean_index++; + else + ring->clean_index = 0; } u64_stats_update_begin(&priv->syncp); @@ -1394,6 +1390,7 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, netif_tx_napi_add(priv->netdev, &ring->napi, bcm_sysport_tx_poll, 64); ring->index = index; ring->size = size; + ring->clean_index = 0; ring->alloc_size = ring->size; ring->desc_cpu = p; ring->desc_count = ring->size; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index f5a984c1c986..19c91c76e327 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -706,7 +706,7 @@ struct bcm_sysport_tx_ring { unsigned int desc_count; /* Number of descriptors */ unsigned int curr_desc; /* Current descriptor */ unsigned int c_index; /* Last consumer index */ - unsigned int p_index; /* Current producer index */ + unsigned int clean_index; /* Current clean index */ struct bcm_sysport_cb *cbs; /* Transmit control blocks */ struct dma_desc *desc_cpu; /* CPU view of the descriptor */ struct bcm_sysport_priv *priv; /* private context backpointer */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 74fc9af4aadb..b8388e93520a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13913,7 +13913,7 @@ static void bnx2x_register_phc(struct bnx2x *bp) bp->ptp_clock = ptp_clock_register(&bp->ptp_clock_info, &bp->pdev->dev); if (IS_ERR(bp->ptp_clock)) { bp->ptp_clock = NULL; - BNX2X_ERR("PTP clock registeration failed\n"); + BNX2X_ERR("PTP clock registration failed\n"); } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1500243b9886..c7e5e6f09647 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1439,7 +1439,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { u16 vlan_proto = tpa_info->metadata >> RX_CMP_FLAGS2_METADATA_TPID_SFT; - u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_VID_MASK; + u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK; __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag); } @@ -1623,7 +1623,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) && (skb->dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data); - u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_VID_MASK; + u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK; u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT; __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag); @@ -3847,6 +3847,9 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; struct hwrm_vnic_tpa_cfg_input req = {0}; + if (vnic->fw_vnic_id == INVALID_HW_RING_ID) + return 0; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_TPA_CFG, -1, -1); if (tpa_flags) { @@ -4558,18 +4561,17 @@ int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings) return rc; } -static int -bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, - int ring_grps, int cp_rings, int vnics) +static void +__bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req, + int tx_rings, int rx_rings, int ring_grps, + int cp_rings, int vnics) { - struct hwrm_func_cfg_input req = {0}; u32 enables = 0; - int rc; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); - req.fid = cpu_to_le16(0xffff); + bnxt_hwrm_cmd_hdr_init(bp, req, HWRM_FUNC_CFG, -1, -1); + req->fid = cpu_to_le16(0xffff); enables |= tx_rings ? FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS : 0; - req.num_tx_rings = cpu_to_le16(tx_rings); + req->num_tx_rings = cpu_to_le16(tx_rings); if (bp->flags & BNXT_FLAG_NEW_RM) { enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0; enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS | @@ -4578,16 +4580,53 @@ bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; enables |= vnics ? FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS : 0; - req.num_rx_rings = cpu_to_le16(rx_rings); - req.num_hw_ring_grps = cpu_to_le16(ring_grps); - req.num_cmpl_rings = cpu_to_le16(cp_rings); - req.num_stat_ctxs = req.num_cmpl_rings; - req.num_vnics = cpu_to_le16(vnics); + req->num_rx_rings = cpu_to_le16(rx_rings); + req->num_hw_ring_grps = cpu_to_le16(ring_grps); + req->num_cmpl_rings = cpu_to_le16(cp_rings); + req->num_stat_ctxs = req->num_cmpl_rings; + req->num_vnics = cpu_to_le16(vnics); } - if (!enables) + req->enables = cpu_to_le32(enables); +} + +static void +__bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, + struct hwrm_func_vf_cfg_input *req, int tx_rings, + int rx_rings, int ring_grps, int cp_rings, + int vnics) +{ + u32 enables = 0; + + bnxt_hwrm_cmd_hdr_init(bp, req, HWRM_FUNC_VF_CFG, -1, -1); + enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0; + enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS : 0; + enables |= cp_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS | + FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; + enables |= ring_grps ? FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; + enables |= vnics ? FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS : 0; + + req->num_tx_rings = cpu_to_le16(tx_rings); + req->num_rx_rings = cpu_to_le16(rx_rings); + req->num_hw_ring_grps = cpu_to_le16(ring_grps); + req->num_cmpl_rings = cpu_to_le16(cp_rings); + req->num_stat_ctxs = req->num_cmpl_rings; + req->num_vnics = cpu_to_le16(vnics); + + req->enables = cpu_to_le32(enables); +} + +static int +bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, + int ring_grps, int cp_rings, int vnics) +{ + struct hwrm_func_cfg_input req = {0}; + int rc; + + __bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps, + cp_rings, vnics); + if (!req.enables) return 0; - req.enables = cpu_to_le32(enables); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) return -ENOMEM; @@ -4604,7 +4643,6 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, int ring_grps, int cp_rings, int vnics) { struct hwrm_func_vf_cfg_input req = {0}; - u32 enables = 0; int rc; if (!(bp->flags & BNXT_FLAG_NEW_RM)) { @@ -4612,22 +4650,8 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, return 0; } - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_CFG, -1, -1); - enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0; - enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS : 0; - enables |= cp_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; - enables |= ring_grps ? FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; - enables |= vnics ? FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS : 0; - - req.num_tx_rings = cpu_to_le16(tx_rings); - req.num_rx_rings = cpu_to_le16(rx_rings); - req.num_hw_ring_grps = cpu_to_le16(ring_grps); - req.num_cmpl_rings = cpu_to_le16(cp_rings); - req.num_stat_ctxs = req.num_cmpl_rings; - req.num_vnics = cpu_to_le16(vnics); - - req.enables = cpu_to_le32(enables); + __bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps, + cp_rings, vnics); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) return -ENOMEM; @@ -4743,39 +4767,25 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) } static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, - int ring_grps, int cp_rings) + int ring_grps, int cp_rings, int vnics) { struct hwrm_func_vf_cfg_input req = {0}; - u32 flags, enables; + u32 flags; int rc; if (!(bp->flags & BNXT_FLAG_NEW_RM)) return 0; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_CFG, -1, -1); + __bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps, + cp_rings, vnics); flags = FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST | FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST | FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST | FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST | FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST | FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST; - enables = FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS | - FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS | - FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS | - FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS | - FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS; req.flags = cpu_to_le32(flags); - req.enables = cpu_to_le32(enables); - req.num_tx_rings = cpu_to_le16(tx_rings); - req.num_rx_rings = cpu_to_le16(rx_rings); - req.num_cmpl_rings = cpu_to_le16(cp_rings); - req.num_hw_ring_grps = cpu_to_le16(ring_grps); - req.num_stat_ctxs = cpu_to_le16(cp_rings); - req.num_vnics = cpu_to_le16(1); - if (bp->flags & BNXT_FLAG_RFS) - req.num_vnics = cpu_to_le16(rx_rings + 1); rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) return -ENOMEM; @@ -4783,38 +4793,23 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, } static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, - int ring_grps, int cp_rings) + int ring_grps, int cp_rings, int vnics) { struct hwrm_func_cfg_input req = {0}; - u32 flags, enables; + u32 flags; int rc; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); - req.fid = cpu_to_le16(0xffff); + __bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps, + cp_rings, vnics); flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST; - enables = FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS; - req.num_tx_rings = cpu_to_le16(tx_rings); - if (bp->flags & BNXT_FLAG_NEW_RM) { + if (bp->flags & BNXT_FLAG_NEW_RM) flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST | FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST | FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST | FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST | FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST; - enables |= FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS | - FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS | - FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS | - FUNC_CFG_REQ_ENABLES_NUM_VNICS; - req.num_rx_rings = cpu_to_le16(rx_rings); - req.num_cmpl_rings = cpu_to_le16(cp_rings); - req.num_hw_ring_grps = cpu_to_le16(ring_grps); - req.num_stat_ctxs = cpu_to_le16(cp_rings); - req.num_vnics = cpu_to_le16(1); - if (bp->flags & BNXT_FLAG_RFS) - req.num_vnics = cpu_to_le16(rx_rings + 1); - } + req.flags = cpu_to_le32(flags); - req.enables = cpu_to_le32(enables); rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) return -ENOMEM; @@ -4822,17 +4817,17 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, } static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings, - int ring_grps, int cp_rings) + int ring_grps, int cp_rings, int vnics) { if (bp->hwrm_spec_code < 0x10801) return 0; if (BNXT_PF(bp)) return bnxt_hwrm_check_pf_rings(bp, tx_rings, rx_rings, - ring_grps, cp_rings); + ring_grps, cp_rings, vnics); return bnxt_hwrm_check_vf_rings(bp, tx_rings, rx_rings, ring_grps, - cp_rings); + cp_rings, vnics); } static void bnxt_hwrm_set_coal_params(struct bnxt_coal *hw_coal, @@ -5865,7 +5860,6 @@ static int bnxt_init_msix(struct bnxt *bp) if (rc) goto msix_setup_exit; - bp->tx_nr_rings_per_tc = bp->tx_nr_rings; bp->cp_nr_rings = (min == 1) ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) : bp->tx_nr_rings + bp->rx_nr_rings; @@ -5897,7 +5891,6 @@ static int bnxt_init_inta(struct bnxt *bp) bp->rx_nr_rings = 1; bp->tx_nr_rings = 1; bp->cp_nr_rings = 1; - bp->tx_nr_rings_per_tc = bp->tx_nr_rings; bp->flags |= BNXT_FLAG_SHARED_RINGS; bp->irq_tbl[0].vector = bp->pdev->irq; return 0; @@ -7531,7 +7524,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, int max_rx, max_tx, tx_sets = 1; int tx_rings_needed; int rx_rings = rx; - int cp, rc; + int cp, vnics, rc; if (tcs) tx_sets = tcs; @@ -7547,10 +7540,15 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, if (max_tx < tx_rings_needed) return -ENOMEM; + vnics = 1; + if (bp->flags & BNXT_FLAG_RFS) + vnics += rx_rings; + if (bp->flags & BNXT_FLAG_AGG_RINGS) rx_rings <<= 1; cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx; - return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp); + return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp, + vnics); } static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev) @@ -8437,13 +8435,20 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp) return 0; bnxt_hwrm_func_qcaps(bp); - __bnxt_close_nic(bp, true, false); + + if (netif_running(bp->dev)) + __bnxt_close_nic(bp, true, false); + bnxt_clear_int_mode(bp); rc = bnxt_init_int_mode(bp); - if (rc) - dev_close(bp->dev); - else - rc = bnxt_open_nic(bp, true, false); + + if (netif_running(bp->dev)) { + if (rc) + dev_close(bp->dev); + else + rc = bnxt_open_nic(bp, true, false); + } + return rc; } @@ -8664,6 +8669,11 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; + /* No TC has been set yet and rings may have been trimmed due to + * limited MSIX, so we re-initialize the TX rings per TC. + */ + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + bnxt_get_wol_settings(bp); if (bp->flags & BNXT_FLAG_WOL_CAP) device_set_wakeup_enable(&pdev->dev, bp->wol); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 1989c470172c..5e3d62189cab 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -189,6 +189,7 @@ struct rx_cmp_ext { #define RX_CMP_FLAGS2_T_L4_CS_CALC (0x1 << 3) #define RX_CMP_FLAGS2_META_FORMAT_VLAN (0x1 << 4) __le32 rx_cmp_meta_data; + #define RX_CMP_FLAGS2_METADATA_TCI_MASK 0xffff #define RX_CMP_FLAGS2_METADATA_VID_MASK 0xfff #define RX_CMP_FLAGS2_METADATA_TPID_MASK 0xffff0000 #define RX_CMP_FLAGS2_METADATA_TPID_SFT 16 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index fbe6e208e17b..65c2cee35766 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -349,6 +349,9 @@ static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle) if (rc) netdev_info(bp->dev, "Error: %s: flow_handle=0x%x rc=%d", __func__, flow_handle, rc); + + if (rc) + rc = -EIO; return rc; } @@ -484,13 +487,15 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow, req.action_flags = cpu_to_le16(action_flags); mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) *flow_handle = resp->flow_handle; - mutex_unlock(&bp->hwrm_cmd_lock); + if (rc == HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR) + rc = -ENOSPC; + else if (rc) + rc = -EIO; return rc; } @@ -561,6 +566,8 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp, netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); mutex_unlock(&bp->hwrm_cmd_lock); + if (rc) + rc = -EIO; return rc; } @@ -576,6 +583,9 @@ static int hwrm_cfa_decap_filter_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + + if (rc) + rc = -EIO; return rc; } @@ -624,6 +634,8 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp, netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); mutex_unlock(&bp->hwrm_cmd_lock); + if (rc) + rc = -EIO; return rc; } @@ -639,6 +651,9 @@ static int hwrm_cfa_encap_record_free(struct bnxt *bp, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); + + if (rc) + rc = -EIO; return rc; } @@ -1269,11 +1284,8 @@ static int bnxt_tc_del_flow(struct bnxt *bp, flow_node = rhashtable_lookup_fast(&tc_info->flow_table, &tc_flow_cmd->cookie, tc_info->flow_ht_params); - if (!flow_node) { - netdev_info(bp->dev, "ERROR: no flow_node for cookie %lx", - tc_flow_cmd->cookie); + if (!flow_node) return -EINVAL; - } return __bnxt_tc_del_flow(bp, flow_node); } @@ -1290,11 +1302,8 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp, flow_node = rhashtable_lookup_fast(&tc_info->flow_table, &tc_flow_cmd->cookie, tc_info->flow_ht_params); - if (!flow_node) { - netdev_info(bp->dev, "Error: no flow_node for cookie %lx", - tc_flow_cmd->cookie); + if (!flow_node) return -1; - } flow = &flow_node->flow; curr_stats = &flow->stats; @@ -1344,8 +1353,10 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows, } else { netdev_info(bp->dev, "error rc=%d", rc); } - mutex_unlock(&bp->hwrm_cmd_lock); + + if (rc) + rc = -EIO; return rc; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index c1841db1b500..f2593978ae75 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -820,7 +820,7 @@ static int tg3_ape_event_lock(struct tg3 *tp, u32 timeout_us) tg3_ape_unlock(tp, TG3_APE_LOCK_MEM); - usleep_range(10, 20); + udelay(10); timeout_us -= (timeout_us > 10) ? 10 : timeout_us; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 7b452e85de2a..61022b5f6743 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4970,7 +4970,6 @@ static void cxgb4_mgmt_setup(struct net_device *dev) /* Initialize the device structure. */ dev->netdev_ops = &cxgb4_mgmt_netdev_ops; dev->ethtool_ops = &cxgb4_mgmt_ethtool_ops; - dev->needs_free_netdev = true; } static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) @@ -5181,6 +5180,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->name = pci_name(pdev); adapter->mbox = func; adapter->pf = func; + adapter->params.chip = chip; + adapter->adap_idx = adap_idx; adapter->msg_enable = DFLT_MSG_ENABLE; adapter->mbox_log = kzalloc(sizeof(*adapter->mbox_log) + (sizeof(struct mbox_cmd) * diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 5eb999af2c40..bd3f6e4d1341 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -540,6 +540,7 @@ static int gmac_setup_txqs(struct net_device *netdev) if (port->txq_dma_base & ~DMA_Q_BASE_MASK) { dev_warn(geth->dev, "TX queue base it not aligned\n"); + kfree(skb_tab); return -ENOMEM; } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 7caa8da48421..e4ec32a9ca15 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2008,7 +2008,6 @@ static inline int dpaa_xmit(struct dpaa_priv *priv, } if (unlikely(err < 0)) { - percpu_stats->tx_errors++; percpu_stats->tx_fifo_errors++; return err; } @@ -2278,7 +2277,6 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, vaddr = phys_to_virt(addr); prefetch(vaddr + qm_fd_get_offset(fd)); - fd_format = qm_fd_get_format(fd); /* The only FD types that we may receive are contig and S/G */ WARN_ON((fd_format != qm_fd_contig) && (fd_format != qm_fd_sg)); @@ -2311,8 +2309,10 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, skb_len = skb->len; - if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) + if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) { + percpu_stats->rx_dropped++; return qman_cb_dqrr_consume; + } percpu_stats->rx_packets++; percpu_stats->rx_bytes += skb_len; @@ -2860,7 +2860,7 @@ static int dpaa_remove(struct platform_device *pdev) struct device *dev; int err; - dev = &pdev->dev; + dev = pdev->dev.parent; net_dev = dev_get_drvdata(dev); priv = netdev_priv(net_dev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 7a7f3a42b2aa..d4604bc8eb5b 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3600,6 +3600,8 @@ fec_drv_remove(struct platform_device *pdev) fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); + pm_runtime_put(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index ea43b4974149..7af31ddd093f 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -1100,7 +1100,7 @@ int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr) set_bucket(dtsec->regs, bucket, true); /* Create element to be added to the driver hash table */ - hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC); if (!hash_entry) return -ENOMEM; hash_entry->addr = addr; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f5c87bd35fa1..f27f9bae1a4a 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3063,9 +3063,6 @@ static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb) if (ndev->features & NETIF_F_RXCSUM) gfar_rx_checksum(skb, fcb); - /* Tell the skb what kind of packet this is */ - skb->protocol = eth_type_trans(skb, ndev); - /* There's need to check for NETIF_F_HW_VLAN_CTAG_RX here. * Even if vlan rx accel is disabled, on some chips * RXFCB_VLN is pseudo randomly set. @@ -3136,13 +3133,15 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) continue; } + gfar_process_frame(ndev, skb); + /* Increment the number of packets */ total_pkts++; total_bytes += skb->len; skb_record_rx_queue(skb, rx_queue->qindex); - gfar_process_frame(ndev, skb); + skb->protocol = eth_type_trans(skb, ndev); /* Send the packet up the stack */ napi_gro_receive(&rx_queue->grp->napi_rx, skb); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 86944bc3b273..74bd260ca02a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -666,7 +666,7 @@ static void hns_gmac_get_strings(u32 stringset, u8 *data) static int hns_gmac_get_sset_count(int stringset) { - if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS) + if (stringset == ETH_SS_STATS) return ARRAY_SIZE(g_gmac_stats_string); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index b62816c1574e..93e71e27401b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -422,7 +422,7 @@ void hns_ppe_update_stats(struct hns_ppe_cb *ppe_cb) int hns_ppe_get_sset_count(int stringset) { - if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS) + if (stringset == ETH_SS_STATS) return ETH_PPE_STATIC_NUM; return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 6f3570cfb501..e2e28532e4dc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -876,7 +876,7 @@ void hns_rcb_get_stats(struct hnae_queue *queue, u64 *data) */ int hns_rcb_get_ring_sset_count(int stringset) { - if (stringset == ETH_SS_STATS || stringset == ETH_SS_PRIV_FLAGS) + if (stringset == ETH_SS_STATS) return HNS_RING_STATIC_REG_NUM; return 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 7ea7f8a4aa2a..2e14a3ae1d8b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -993,8 +993,10 @@ int hns_get_sset_count(struct net_device *netdev, int stringset) cnt--; return cnt; - } else { + } else if (stringset == ETH_SS_STATS) { return (HNS_NET_STATS_CNT + ops->get_sset_count(h, stringset)); + } else { + return -EOPNOTSUPP; } } diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index afb7ebe20b24..824fd44e25f0 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -400,6 +400,10 @@ #define E1000_ICR_RXDMT0 0x00000010 /* Rx desc min. threshold (0) */ #define E1000_ICR_RXO 0x00000040 /* Receiver Overrun */ #define E1000_ICR_RXT0 0x00000080 /* Rx timer intr (ring 0) */ +#define E1000_ICR_MDAC 0x00000200 /* MDIO Access Complete */ +#define E1000_ICR_SRPD 0x00010000 /* Small Receive Packet Detected */ +#define E1000_ICR_ACK 0x00020000 /* Receive ACK Frame Detected */ +#define E1000_ICR_MNG 0x00040000 /* Manageability Event Detected */ #define E1000_ICR_ECCER 0x00400000 /* Uncorrectable ECC Error */ /* If this bit asserted, the driver should claim the interrupt */ #define E1000_ICR_INT_ASSERTED 0x80000000 @@ -407,7 +411,7 @@ #define E1000_ICR_RXQ1 0x00200000 /* Rx Queue 1 Interrupt */ #define E1000_ICR_TXQ0 0x00400000 /* Tx Queue 0 Interrupt */ #define E1000_ICR_TXQ1 0x00800000 /* Tx Queue 1 Interrupt */ -#define E1000_ICR_OTHER 0x01000000 /* Other Interrupts */ +#define E1000_ICR_OTHER 0x01000000 /* Other Interrupt */ /* PBA ECC Register */ #define E1000_PBA_ECC_COUNTER_MASK 0xFFF00000 /* ECC counter mask */ @@ -431,12 +435,27 @@ E1000_IMS_RXSEQ | \ E1000_IMS_LSC) +/* These are all of the events related to the OTHER interrupt. + */ +#define IMS_OTHER_MASK ( \ + E1000_IMS_LSC | \ + E1000_IMS_RXO | \ + E1000_IMS_MDAC | \ + E1000_IMS_SRPD | \ + E1000_IMS_ACK | \ + E1000_IMS_MNG) + /* Interrupt Mask Set */ #define E1000_IMS_TXDW E1000_ICR_TXDW /* Transmit desc written back */ #define E1000_IMS_LSC E1000_ICR_LSC /* Link Status Change */ #define E1000_IMS_RXSEQ E1000_ICR_RXSEQ /* Rx sequence error */ #define E1000_IMS_RXDMT0 E1000_ICR_RXDMT0 /* Rx desc min. threshold */ +#define E1000_IMS_RXO E1000_ICR_RXO /* Receiver Overrun */ #define E1000_IMS_RXT0 E1000_ICR_RXT0 /* Rx timer intr */ +#define E1000_IMS_MDAC E1000_ICR_MDAC /* MDIO Access Complete */ +#define E1000_IMS_SRPD E1000_ICR_SRPD /* Small Receive Packet */ +#define E1000_IMS_ACK E1000_ICR_ACK /* Receive ACK Frame Detected */ +#define E1000_IMS_MNG E1000_ICR_MNG /* Manageability Event */ #define E1000_IMS_ECCER E1000_ICR_ECCER /* Uncorrectable ECC Error */ #define E1000_IMS_RXQ0 E1000_ICR_RXQ0 /* Rx Queue 0 Interrupt */ #define E1000_IMS_RXQ1 E1000_ICR_RXQ1 /* Rx Queue 1 Interrupt */ diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 31277d3bb7dc..1dddfb7b2de6 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1367,9 +1367,6 @@ out: * Checks to see of the link status of the hardware has changed. If a * change in link status has been detected, then we read the PHY registers * to get the current speed/duplex if link exists. - * - * Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link - * up). **/ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) { @@ -1385,7 +1382,8 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) * Change or Rx Sequence Error interrupt. */ if (!mac->get_link_status) - return 1; + return 0; + mac->get_link_status = false; /* First we want to see if the MII Status Register reports * link. If so, then we want to get the current speed/duplex @@ -1393,12 +1391,12 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) */ ret_val = e1000e_phy_has_link_generic(hw, 1, 0, &link); if (ret_val) - return ret_val; + goto out; if (hw->mac.type == e1000_pchlan) { ret_val = e1000_k1_gig_workaround_hv(hw, link); if (ret_val) - return ret_val; + goto out; } /* When connected at 10Mbps half-duplex, some parts are excessively @@ -1431,7 +1429,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) ret_val = hw->phy.ops.acquire(hw); if (ret_val) - return ret_val; + goto out; if (hw->mac.type == e1000_pch2lan) emi_addr = I82579_RX_CONFIG; @@ -1453,7 +1451,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) hw->phy.ops.release(hw); if (ret_val) - return ret_val; + goto out; if (hw->mac.type >= e1000_pch_spt) { u16 data; @@ -1462,14 +1460,14 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) if (speed == SPEED_1000) { ret_val = hw->phy.ops.acquire(hw); if (ret_val) - return ret_val; + goto out; ret_val = e1e_rphy_locked(hw, PHY_REG(776, 20), &data); if (ret_val) { hw->phy.ops.release(hw); - return ret_val; + goto out; } ptr_gap = (data & (0x3FF << 2)) >> 2; @@ -1483,18 +1481,18 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) } hw->phy.ops.release(hw); if (ret_val) - return ret_val; + goto out; } else { ret_val = hw->phy.ops.acquire(hw); if (ret_val) - return ret_val; + goto out; ret_val = e1e_wphy_locked(hw, PHY_REG(776, 20), 0xC023); hw->phy.ops.release(hw); if (ret_val) - return ret_val; + goto out; } } @@ -1521,7 +1519,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V3)) { ret_val = e1000_k1_workaround_lpt_lp(hw, link); if (ret_val) - return ret_val; + goto out; } if (hw->mac.type >= e1000_pch_lpt) { /* Set platform power management values for @@ -1529,7 +1527,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) */ ret_val = e1000_platform_pm_pch_lpt(hw, link); if (ret_val) - return ret_val; + goto out; } /* Clear link partner's EEE ability */ @@ -1552,9 +1550,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) } if (!link) - return 0; /* No link detected */ - - mac->get_link_status = false; + goto out; switch (hw->mac.type) { case e1000_pch2lan: @@ -1616,12 +1612,14 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) * different link partner. */ ret_val = e1000e_config_fc_after_link_up(hw); - if (ret_val) { + if (ret_val) e_dbg("Error configuring flow control\n"); - return ret_val; - } - return 1; + return ret_val; + +out: + mac->get_link_status = true; + return ret_val; } static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index f457c5703d0c..5bdc3a2d4fd7 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -410,9 +410,6 @@ void e1000e_clear_hw_cntrs_base(struct e1000_hw *hw) * Checks to see of the link status of the hardware has changed. If a * change in link status has been detected, then we read the PHY registers * to get the current speed/duplex if link exists. - * - * Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link - * up). **/ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) { @@ -426,20 +423,16 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * Change or Rx Sequence Error interrupt. */ if (!mac->get_link_status) - return 1; + return 0; + mac->get_link_status = false; /* First we want to see if the MII Status Register reports * link. If so, then we want to get the current speed/duplex * of the PHY. */ ret_val = e1000e_phy_has_link_generic(hw, 1, 0, &link); - if (ret_val) - return ret_val; - - if (!link) - return 0; /* No link detected */ - - mac->get_link_status = false; + if (ret_val || !link) + goto out; /* Check if there was DownShift, must be checked * immediately after link-up @@ -464,12 +457,14 @@ s32 e1000e_check_for_copper_link(struct e1000_hw *hw) * different link partner. */ ret_val = e1000e_config_fc_after_link_up(hw); - if (ret_val) { + if (ret_val) e_dbg("Error configuring flow control\n"); - return ret_val; - } - return 1; + return ret_val; + +out: + mac->get_link_status = true; + return ret_val; } /** diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 1298b69f990b..dc853b0863af 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1914,30 +1914,20 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 icr; - bool enable = true; - - icr = er32(ICR); - if (icr & E1000_ICR_RXO) { - ew32(ICR, E1000_ICR_RXO); - enable = false; - /* napi poll will re-enable Other, make sure it runs */ - if (napi_schedule_prep(&adapter->napi)) { - adapter->total_rx_bytes = 0; - adapter->total_rx_packets = 0; - __napi_schedule(&adapter->napi); - } - } + u32 icr = er32(ICR); + + if (icr & adapter->eiac_mask) + ew32(ICS, (icr & adapter->eiac_mask)); + if (icr & E1000_ICR_LSC) { - ew32(ICR, E1000_ICR_LSC); hw->mac.get_link_status = true; /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); } - if (enable && !test_bit(__E1000_DOWN, &adapter->state)) - ew32(IMS, E1000_IMS_OTHER); + if (!test_bit(__E1000_DOWN, &adapter->state)) + ew32(IMS, E1000_IMS_OTHER | IMS_OTHER_MASK); return IRQ_HANDLED; } @@ -2040,7 +2030,6 @@ static void e1000_configure_msix(struct e1000_adapter *adapter) hw->hw_addr + E1000_EITR_82574(vector)); else writel(1, hw->hw_addr + E1000_EITR_82574(vector)); - adapter->eiac_mask |= E1000_IMS_OTHER; /* Cause Tx interrupts on every write back */ ivar |= BIT(31); @@ -2265,7 +2254,8 @@ static void e1000_irq_enable(struct e1000_adapter *adapter) if (adapter->msix_entries) { ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574); - ew32(IMS, adapter->eiac_mask | E1000_IMS_LSC); + ew32(IMS, adapter->eiac_mask | E1000_IMS_OTHER | + IMS_OTHER_MASK); } else if (hw->mac.type >= e1000_pch_lpt) { ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER); } else { @@ -2333,8 +2323,8 @@ static int e1000_alloc_ring_dma(struct e1000_adapter *adapter, { struct pci_dev *pdev = adapter->pdev; - ring->desc = dma_alloc_coherent(&pdev->dev, ring->size, &ring->dma, - GFP_KERNEL); + ring->desc = dma_zalloc_coherent(&pdev->dev, ring->size, &ring->dma, + GFP_KERNEL); if (!ring->desc) return -ENOMEM; @@ -2707,8 +2697,7 @@ static int e1000e_poll(struct napi_struct *napi, int weight) napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) - ew32(IMS, adapter->rx_ring->ims_val | - E1000_IMS_OTHER); + ew32(IMS, adapter->rx_ring->ims_val); else e1000_irq_enable(adapter); } @@ -5101,7 +5090,7 @@ static bool e1000e_has_link(struct e1000_adapter *adapter) case e1000_media_type_copper: if (hw->mac.get_link_status) { ret_val = hw->mac.ops.check_for_link(hw); - link_active = ret_val > 0; + link_active = !hw->mac.get_link_status; } else { link_active = true; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0da5aa2c8aba..9fc063af233c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1888,6 +1888,14 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE, IXGBE_RX_DMA_ATTR); + } else if (ring_uses_build_skb(rx_ring)) { + unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK; + + dma_sync_single_range_for_cpu(rx_ring->dev, + IXGBE_CB(skb)->dma, + offset, + skb_headlen(skb), + DMA_FROM_DEVICE); } else { struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 21d29f7936f6..d39b0b7011b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -124,7 +124,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) trigger_cmd_completions(dev); } - mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 0); + mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1); mlx5_core_err(dev, "end\n"); unlock: diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index b698fb481b2e..996dc099cd58 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -443,6 +443,17 @@ int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id) } EXPORT_SYMBOL(mlxsw_afa_block_jump); +int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block) +{ + if (block->finished) + return -EINVAL; + mlxsw_afa_set_goto_set(block->cur_set, + MLXSW_AFA_SET_GOTO_BINDING_CMD_TERM, 0); + block->finished = true; + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_terminate); + static struct mlxsw_afa_fwd_entry * mlxsw_afa_fwd_entry_create(struct mlxsw_afa *mlxsw_afa, u8 local_port) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 43132293475c..b91f2b0829b0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -65,6 +65,7 @@ char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block); u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block); int mlxsw_afa_block_continue(struct mlxsw_afa_block *block); int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); +int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index f6963b0b4a55..122506daa586 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -107,20 +107,20 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12), MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3), MLXSW_AFK_ELEMENT_INFO_U32(TCP_FLAGS, 0x10, 23, 9), - MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x14, 0, 8), - MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x14, 9, 2), - MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x14, 11, 6), - MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32), - MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32), - MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8), - MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x20, 8), - MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x28, 8), - MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x30, 8), MLXSW_AFK_ELEMENT_INFO_U32(DST_L4_PORT, 0x14, 0, 16), MLXSW_AFK_ELEMENT_INFO_U32(SRC_L4_PORT, 0x14, 16, 16), + MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8), + MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2), + MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6), + MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x20, 0, 32), + MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x24, 0, 32), + MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x20, 8), + MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x28, 8), + MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x30, 8), + MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x38, 8), }; -#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x38 +#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40 struct mlxsw_afk_element_inst { /* element instance in actual block */ const struct mlxsw_afk_element_info *info; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 3dcc58d61506..bf400c75fcc8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -655,13 +655,17 @@ static int mlxsw_sp_span_port_mtu_update(struct mlxsw_sp_port *port, u16 mtu) } static struct mlxsw_sp_span_inspected_port * -mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_port *port, - struct mlxsw_sp_span_entry *span_entry) +mlxsw_sp_span_entry_bound_port_find(struct mlxsw_sp_span_entry *span_entry, + enum mlxsw_sp_span_type type, + struct mlxsw_sp_port *port, + bool bind) { struct mlxsw_sp_span_inspected_port *p; list_for_each_entry(p, &span_entry->bound_ports_list, list) - if (port->local_port == p->local_port) + if (type == p->type && + port->local_port == p->local_port && + bind == p->bound) return p; return NULL; } @@ -691,8 +695,22 @@ mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, struct mlxsw_sp_span_inspected_port *inspected_port; struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; char sbib_pl[MLXSW_REG_SBIB_LEN]; + int i; int err; + /* A given (source port, direction) can only be bound to one analyzer, + * so if a binding is requested, check for conflicts. + */ + if (bind) + for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + struct mlxsw_sp_span_entry *curr = + &mlxsw_sp->span.entries[i]; + + if (mlxsw_sp_span_entry_bound_port_find(curr, type, + port, bind)) + return -EEXIST; + } + /* if it is an egress SPAN, bind a shared buffer to it */ if (type == MLXSW_SP_SPAN_EGRESS) { u32 buffsize = mlxsw_sp_span_mtu_to_buffsize(mlxsw_sp, @@ -720,6 +738,7 @@ mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, } inspected_port->local_port = port->local_port; inspected_port->type = type; + inspected_port->bound = bind; list_add_tail(&inspected_port->list, &span_entry->bound_ports_list); return 0; @@ -746,7 +765,8 @@ mlxsw_sp_span_inspected_port_del(struct mlxsw_sp_port *port, struct mlxsw_sp *mlxsw_sp = port->mlxsw_sp; char sbib_pl[MLXSW_REG_SBIB_LEN]; - inspected_port = mlxsw_sp_span_entry_bound_port_find(port, span_entry); + inspected_port = mlxsw_sp_span_entry_bound_port_find(span_entry, type, + port, bind); if (!inspected_port) return; @@ -1459,6 +1479,7 @@ mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) } mlxsw_sp_port_vlan->mlxsw_sp_port = mlxsw_sp_port; + mlxsw_sp_port_vlan->ref_count = 1; mlxsw_sp_port_vlan->vid = vid; list_add(&mlxsw_sp_port_vlan->list, &mlxsw_sp_port->vlans_list); @@ -1486,8 +1507,10 @@ mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid); - if (mlxsw_sp_port_vlan) + if (mlxsw_sp_port_vlan) { + mlxsw_sp_port_vlan->ref_count++; return mlxsw_sp_port_vlan; + } return mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid); } @@ -1496,6 +1519,9 @@ void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) { struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid; + if (--mlxsw_sp_port_vlan->ref_count != 0) + return; + if (mlxsw_sp_port_vlan->bridge_port) mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan); else if (fid) @@ -4207,13 +4233,12 @@ static struct devlink_resource_ops mlxsw_sp_resource_kvd_hash_double_ops = { .size_validate = mlxsw_sp_resource_kvd_hash_double_size_validate, }; -static struct devlink_resource_size_params mlxsw_sp_kvd_size_params; -static struct devlink_resource_size_params mlxsw_sp_linear_size_params; -static struct devlink_resource_size_params mlxsw_sp_hash_single_size_params; -static struct devlink_resource_size_params mlxsw_sp_hash_double_size_params; - static void -mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core) +mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core, + struct devlink_resource_size_params *kvd_size_params, + struct devlink_resource_size_params *linear_size_params, + struct devlink_resource_size_params *hash_double_size_params, + struct devlink_resource_size_params *hash_single_size_params) { u32 single_size_min = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE); @@ -4222,37 +4247,35 @@ mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core) u32 kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); u32 linear_size_min = 0; - /* KVD top resource */ - mlxsw_sp_kvd_size_params.size_min = kvd_size; - mlxsw_sp_kvd_size_params.size_max = kvd_size; - mlxsw_sp_kvd_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_kvd_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Linear part init */ - mlxsw_sp_linear_size_params.size_min = linear_size_min; - mlxsw_sp_linear_size_params.size_max = kvd_size - single_size_min - - double_size_min; - mlxsw_sp_linear_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_linear_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Hash double part init */ - mlxsw_sp_hash_double_size_params.size_min = double_size_min; - mlxsw_sp_hash_double_size_params.size_max = kvd_size - single_size_min - - linear_size_min; - mlxsw_sp_hash_double_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_hash_double_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; - - /* Hash single part init */ - mlxsw_sp_hash_single_size_params.size_min = single_size_min; - mlxsw_sp_hash_single_size_params.size_max = kvd_size - double_size_min - - linear_size_min; - mlxsw_sp_hash_single_size_params.size_granularity = MLXSW_SP_KVD_GRANULARITY; - mlxsw_sp_hash_single_size_params.unit = DEVLINK_RESOURCE_UNIT_ENTRY; + devlink_resource_size_params_init(kvd_size_params, kvd_size, kvd_size, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(linear_size_params, linear_size_min, + kvd_size - single_size_min - + double_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(hash_double_size_params, + double_size_min, + kvd_size - single_size_min - + linear_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + devlink_resource_size_params_init(hash_single_size_params, + single_size_min, + kvd_size - double_size_min - + linear_size_min, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); } static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) { struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params hash_single_size_params; + struct devlink_resource_size_params hash_double_size_params; + struct devlink_resource_size_params linear_size_params; + struct devlink_resource_size_params kvd_size_params; u32 kvd_size, single_size, double_size, linear_size; const struct mlxsw_config_profile *profile; int err; @@ -4261,13 +4284,17 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE)) return -EIO; - mlxsw_sp_resource_size_params_prepare(mlxsw_core); + mlxsw_sp_resource_size_params_prepare(mlxsw_core, &kvd_size_params, + &linear_size_params, + &hash_double_size_params, + &hash_single_size_params); + kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD, true, kvd_size, MLXSW_SP_RESOURCE_KVD, DEVLINK_RESOURCE_ID_PARENT_TOP, - &mlxsw_sp_kvd_size_params, + &kvd_size_params, &mlxsw_sp_resource_kvd_ops); if (err) return err; @@ -4277,7 +4304,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, linear_size, MLXSW_SP_RESOURCE_KVD_LINEAR, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_linear_size_params, + &linear_size_params, &mlxsw_sp_resource_kvd_linear_ops); if (err) return err; @@ -4291,7 +4318,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, double_size, MLXSW_SP_RESOURCE_KVD_HASH_DOUBLE, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_hash_double_size_params, + &hash_double_size_params, &mlxsw_sp_resource_kvd_hash_double_ops); if (err) return err; @@ -4301,7 +4328,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core) false, single_size, MLXSW_SP_RESOURCE_KVD_HASH_SINGLE, MLXSW_SP_RESOURCE_KVD, - &mlxsw_sp_hash_single_size_params, + &hash_single_size_params, &mlxsw_sp_resource_kvd_hash_single_ops); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bdd8f94a452c..92064db2ae44 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -120,6 +120,9 @@ struct mlxsw_sp_span_inspected_port { struct list_head list; enum mlxsw_sp_span_type type; u8 local_port; + + /* Whether this is a directly bound mirror (port-to-port) or an ACL. */ + bool bound; }; struct mlxsw_sp_span_entry { @@ -211,6 +214,7 @@ struct mlxsw_sp_port_vlan { struct list_head list; struct mlxsw_sp_port *mlxsw_sp_port; struct mlxsw_sp_fid *fid; + unsigned int ref_count; u16 vid; struct mlxsw_sp_bridge_port *bridge_port; struct list_head bridge_vlan_node; @@ -552,6 +556,7 @@ void mlxsw_sp_acl_rulei_keymask_buf(struct mlxsw_sp_acl_rule_info *rulei, int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, u16 group_id); +int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 0897a5435cc2..92d90ed7207e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -528,6 +528,11 @@ int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, return mlxsw_afa_block_jump(rulei->act_block, group_id); } +int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei) +{ + return mlxsw_afa_block_terminate(rulei->act_block); +} + int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei) { return mlxsw_afa_block_append_drop(rulei->act_block); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 93728c694e6d..0a9adc5962fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -385,13 +385,13 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = { static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { MLXSW_SP_CPU_PORT_SB_CM, + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_SB_CM(10000, 0, 0), + MLXSW_SP_SB_CM(MLXSW_PORT_MAX_MTU, 0, 0), MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index bbd238e50f05..54262af4e98f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -112,11 +112,11 @@ static const int mlxsw_sp_sfgc_bc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP] = 1, [MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL] = 1, [MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST] = 1, + [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6] = 1, }; static const int mlxsw_sp_sfgc_mc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4] = 1, - [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6] = 1, }; static const int *mlxsw_sp_packet_type_sfgc_types[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 6ce00e28d4ea..89dbf569dff5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -65,7 +65,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { if (is_tcf_gact_ok(a)) { - err = mlxsw_sp_acl_rulei_act_continue(rulei); + err = mlxsw_sp_acl_rulei_act_terminate(rulei); if (err) return err; } else if (is_tcf_gact_shot(a)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 593ad31be749..161bcdc012f0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1203,6 +1203,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, bool dynamic) { char *sfd_pl; + u8 num_rec; int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); @@ -1212,9 +1213,16 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), mac, fid, action, local_port); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); - kfree(sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; +out: + kfree(sfd_pl); return err; } @@ -1239,6 +1247,7 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, bool adding, bool dynamic) { char *sfd_pl; + u8 num_rec; int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); @@ -1249,9 +1258,16 @@ static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id, mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic), mac, fid, MLXSW_REG_SFD_REC_ACTION_NOP, lag_vid, lag_id); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); - kfree(sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; +out: + kfree(sfd_pl); return err; } @@ -1296,6 +1312,7 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr, u16 fid, u16 mid_idx, bool adding) { char *sfd_pl; + u8 num_rec; int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); @@ -1305,7 +1322,15 @@ static int mlxsw_sp_port_mdb_op(struct mlxsw_sp *mlxsw_sp, const char *addr, mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); mlxsw_reg_sfd_mc_pack(sfd_pl, 0, addr, fid, MLXSW_REG_SFD_REC_ACTION_NOP, mid_idx); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; + +out: kfree(sfd_pl); return err; } diff --git a/drivers/net/ethernet/natsemi/Kconfig b/drivers/net/ethernet/natsemi/Kconfig index a10ef50e4f12..017fb2322589 100644 --- a/drivers/net/ethernet/natsemi/Kconfig +++ b/drivers/net/ethernet/natsemi/Kconfig @@ -1,16 +1,16 @@ # -# National Semi-conductor device configuration +# National Semiconductor device configuration # config NET_VENDOR_NATSEMI - bool "National Semi-conductor devices" + bool "National Semiconductor devices" default y ---help--- If you have a network (Ethernet) card belonging to this class, say Y. Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all - the questions about National Semi-conductor devices. If you say Y, + the questions about National Semiconductor devices. If you say Y, you will be asked for your specific card in the following questions. if NET_VENDOR_NATSEMI diff --git a/drivers/net/ethernet/natsemi/Makefile b/drivers/net/ethernet/natsemi/Makefile index cc664977596e..a759aa09ef59 100644 --- a/drivers/net/ethernet/natsemi/Makefile +++ b/drivers/net/ethernet/natsemi/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # -# Makefile for the National Semi-conductor Sonic devices. +# Makefile for the National Semiconductor Sonic devices. # obj-$(CONFIG_MACSONIC) += macsonic.o diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 6f546e869d8d..00f41c145d4d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2480,7 +2480,10 @@ int qed_cxt_free_proto_ilt(struct qed_hwfn *p_hwfn, enum protocol_type proto) if (rc) return rc; - /* Free Task CXT */ + /* Free Task CXT ( Intentionally RoCE as task-id is shared between + * RoCE and iWARP ) + */ + proto = PROTOCOLID_ROCE; rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_TASK, 0, qed_cxt_get_proto_tid_count(p_hwfn, proto)); if (rc) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index ca4a81dc1ace..d5d02be72947 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1703,6 +1703,13 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, iph = (struct iphdr *)((u8 *)(ethh) + eth_hlen); if (eth_type == ETH_P_IP) { + if (iph->protocol != IPPROTO_TCP) { + DP_NOTICE(p_hwfn, + "Unexpected ip protocol on ll2 %x\n", + iph->protocol); + return -EINVAL; + } + cm_info->local_ip[0] = ntohl(iph->daddr); cm_info->remote_ip[0] = ntohl(iph->saddr); cm_info->ip_version = TCP_IPV4; @@ -1711,6 +1718,14 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, *payload_len = ntohs(iph->tot_len) - ip_hlen; } else if (eth_type == ETH_P_IPV6) { ip6h = (struct ipv6hdr *)iph; + + if (ip6h->nexthdr != IPPROTO_TCP) { + DP_NOTICE(p_hwfn, + "Unexpected ip protocol on ll2 %x\n", + iph->protocol); + return -EINVAL; + } + for (i = 0; i < 4; i++) { cm_info->local_ip[i] = ntohl(ip6h->daddr.in6_u.u6_addr32[i]); @@ -1928,8 +1943,8 @@ qed_iwarp_update_fpdu_length(struct qed_hwfn *p_hwfn, /* Missing lower byte is now available */ mpa_len = fpdu->fpdu_length | *mpa_data; fpdu->fpdu_length = QED_IWARP_FPDU_LEN_WITH_PAD(mpa_len); - fpdu->mpa_frag_len = fpdu->fpdu_length; /* one byte of hdr */ + fpdu->mpa_frag_len = 1; fpdu->incomplete_bytes = fpdu->fpdu_length - 1; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index 5d040b873137..a411f9c702a1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -379,6 +379,7 @@ static void qed_rdma_free(struct qed_hwfn *p_hwfn) DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Freeing RDMA\n"); qed_rdma_free_reserved_lkey(p_hwfn); + qed_cxt_free_proto_ilt(p_hwfn, p_hwfn->p_rdma_info->proto); qed_rdma_resc_free(p_hwfn); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 2db70eabddfe..a01e7d6e5442 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -288,7 +288,7 @@ int __init qede_init(void) } /* Must register notifier before pci ops, since we might miss - * interface rename after pci probe and netdev registeration. + * interface rename after pci probe and netdev registration. */ ret = register_netdevice_notifier(&qede_netdev_notifier); if (ret) { @@ -988,7 +988,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, if (rc) goto err3; - /* Prepare the lock prior to the registeration of the netdev, + /* Prepare the lock prior to the registration of the netdev, * as once it's registered we might reach flows requiring it * [it's even possible to reach a flow needing it directly * from there, although it's unlikely]. @@ -2067,8 +2067,6 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, link_params.link_up = true; edev->ops->common->set_link(edev->cdev, &link_params); - qede_rdma_dev_event_open(edev); - edev->state = QEDE_STATE_OPEN; DP_INFO(edev, "Ending successfully qede load\n"); @@ -2169,12 +2167,14 @@ static void qede_link_update(void *dev, struct qed_link_output *link) DP_NOTICE(edev, "Link is up\n"); netif_tx_start_all_queues(edev->ndev); netif_carrier_on(edev->ndev); + qede_rdma_dev_event_open(edev); } } else { if (netif_carrier_ok(edev->ndev)) { DP_NOTICE(edev, "Link is down\n"); netif_tx_disable(edev->ndev); netif_carrier_off(edev->ndev); + qede_rdma_dev_event_close(edev); } } } diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 9b2280badaf7..02adb513f475 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -485,7 +485,7 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc) ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev); if (IS_ERR(ptp->clock)) { rc = -EINVAL; - DP_ERR(edev, "PTP clock registeration failed\n"); + DP_ERR(edev, "PTP clock registration failed\n"); goto err2; } diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 9cbb27263742..d5a32b7c7dc5 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1194,9 +1194,9 @@ void emac_mac_tx_process(struct emac_adapter *adpt, struct emac_tx_queue *tx_q) while (tx_q->tpd.consume_idx != hw_consume_idx) { tpbuf = GET_TPD_BUFFER(tx_q, tx_q->tpd.consume_idx); if (tpbuf->dma_addr) { - dma_unmap_single(adpt->netdev->dev.parent, - tpbuf->dma_addr, tpbuf->length, - DMA_TO_DEVICE); + dma_unmap_page(adpt->netdev->dev.parent, + tpbuf->dma_addr, tpbuf->length, + DMA_TO_DEVICE); tpbuf->dma_addr = 0; } @@ -1353,9 +1353,11 @@ static void emac_tx_fill_tpd(struct emac_adapter *adpt, tpbuf = GET_TPD_BUFFER(tx_q, tx_q->tpd.produce_idx); tpbuf->length = mapped_len; - tpbuf->dma_addr = dma_map_single(adpt->netdev->dev.parent, - skb->data, tpbuf->length, - DMA_TO_DEVICE); + tpbuf->dma_addr = dma_map_page(adpt->netdev->dev.parent, + virt_to_page(skb->data), + offset_in_page(skb->data), + tpbuf->length, + DMA_TO_DEVICE); ret = dma_mapping_error(adpt->netdev->dev.parent, tpbuf->dma_addr); if (ret) @@ -1371,9 +1373,12 @@ static void emac_tx_fill_tpd(struct emac_adapter *adpt, if (mapped_len < len) { tpbuf = GET_TPD_BUFFER(tx_q, tx_q->tpd.produce_idx); tpbuf->length = len - mapped_len; - tpbuf->dma_addr = dma_map_single(adpt->netdev->dev.parent, - skb->data + mapped_len, - tpbuf->length, DMA_TO_DEVICE); + tpbuf->dma_addr = dma_map_page(adpt->netdev->dev.parent, + virt_to_page(skb->data + + mapped_len), + offset_in_page(skb->data + + mapped_len), + tpbuf->length, DMA_TO_DEVICE); ret = dma_mapping_error(adpt->netdev->dev.parent, tpbuf->dma_addr); if (ret) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 92dcf8717fc6..14c839bb09e7 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -439,6 +439,17 @@ static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear, enum_index); } +static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data, + int enum_index) +{ + iowrite32(data, mdp->tsu_addr + mdp->reg_offset[enum_index]); +} + +static u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index) +{ + return ioread32(mdp->tsu_addr + mdp->reg_offset[enum_index]); +} + static bool sh_eth_is_gether(struct sh_eth_private *mdp) { return mdp->reg_offset == sh_eth_offset_gigabit; diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index a6753ccba711..e5fe70134690 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -567,15 +567,4 @@ static inline void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp, return mdp->tsu_addr + mdp->reg_offset[enum_index]; } -static inline void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data, - int enum_index) -{ - iowrite32(data, mdp->tsu_addr + mdp->reg_offset[enum_index]); -} - -static inline u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index) -{ - return ioread32(mdp->tsu_addr + mdp->reg_offset[enum_index]); -} - #endif /* #ifndef __SH_ETH_H__ */ diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 012fb66eed8d..f0afb88d7bc2 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -2335,14 +2335,14 @@ static int smsc911x_drv_remove(struct platform_device *pdev) pdata = netdev_priv(dev); BUG_ON(!pdata); BUG_ON(!pdata->ioaddr); - WARN_ON(dev->phydev); SMSC_TRACE(pdata, ifdown, "Stopping driver"); + unregister_netdev(dev); + mdiobus_unregister(pdata->mii_bus); mdiobus_free(pdata->mii_bus); - unregister_netdev(dev); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "smsc911x-memory"); if (!res) diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 111e7ca9df56..f5c5984afefb 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1295,7 +1295,7 @@ static int ave_open(struct net_device *ndev) val |= AVE_IIRQC_EN0 | (AVE_INTM_COUNT << 16); writel(val, priv->base + AVE_IIRQC); - val = AVE_GI_RXIINT | AVE_GI_RXOVF | AVE_GI_TX; + val = AVE_GI_RXIINT | AVE_GI_RXOVF | AVE_GI_TX | AVE_GI_RXDROP; ave_irq_restore(ndev, val); napi_enable(&priv->napi_rx); diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 63d3d6b215f3..a94f50442613 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -312,7 +312,7 @@ static struct vnet *vnet_new(const u64 *local_mac, dev->ethtool_ops = &vnet_ethtool_ops; dev->watchdog_timeo = VNET_TX_TIMEOUT; - dev->hw_features = NETIF_F_TSO | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | + dev->hw_features = NETIF_F_TSO | NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_HW_CSUM | NETIF_F_SG; dev->features = dev->hw_features; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1b1b78fdc138..b2b30c9df037 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1014,7 +1014,8 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave, /* set speed_in input in case RMII mode is used in 100Mbps */ if (phy->speed == 100) mac_control |= BIT(15); - else if (phy->speed == 10) + /* in band mode only works in 10Mbps RGMII mode */ + else if ((phy->speed == 10) && phy_interface_is_rgmii(phy)) mac_control |= BIT(18); /* In Band mode */ if (priv->rx_pause) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 0db3bd1ea06f..32861036c3fc 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -173,6 +173,7 @@ struct rndis_device { struct list_head req_list; struct work_struct mcast_work; + u32 filter; bool link_state; /* 0 - link up, 1 - link down */ @@ -211,7 +212,6 @@ void netvsc_channel_cb(void *context); int netvsc_poll(struct napi_struct *napi, int budget); void rndis_set_subchannel(struct work_struct *w); -bool rndis_filter_opened(const struct netvsc_device *nvdev); int rndis_filter_open(struct netvsc_device *nvdev); int rndis_filter_close(struct netvsc_device *nvdev); struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 17e529af79dc..7472172823f3 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -90,6 +90,11 @@ static void free_netvsc_device(struct rcu_head *head) = container_of(head, struct netvsc_device, rcu); int i; + kfree(nvdev->extension); + vfree(nvdev->recv_buf); + vfree(nvdev->send_buf); + kfree(nvdev->send_section_map); + for (i = 0; i < VRSS_CHANNEL_MAX; i++) vfree(nvdev->chan_table[i].mrc.slots); @@ -211,12 +216,6 @@ static void netvsc_teardown_gpadl(struct hv_device *device, net_device->recv_buf_gpadl_handle = 0; } - if (net_device->recv_buf) { - /* Free up the receive buffer */ - vfree(net_device->recv_buf); - net_device->recv_buf = NULL; - } - if (net_device->send_buf_gpadl_handle) { ret = vmbus_teardown_gpadl(device->channel, net_device->send_buf_gpadl_handle); @@ -231,12 +230,6 @@ static void netvsc_teardown_gpadl(struct hv_device *device, } net_device->send_buf_gpadl_handle = 0; } - if (net_device->send_buf) { - /* Free up the send buffer */ - vfree(net_device->send_buf); - net_device->send_buf = NULL; - } - kfree(net_device->send_section_map); } int netvsc_alloc_recv_comp_ring(struct netvsc_device *net_device, u32 q_idx) @@ -562,26 +555,29 @@ void netvsc_device_remove(struct hv_device *device) = rtnl_dereference(net_device_ctx->nvdev); int i; - cancel_work_sync(&net_device->subchan_work); - netvsc_revoke_buf(device, net_device); RCU_INIT_POINTER(net_device_ctx->nvdev, NULL); + /* And disassociate NAPI context from device */ + for (i = 0; i < net_device->num_chn; i++) + netif_napi_del(&net_device->chan_table[i].napi); + /* * At this point, no one should be accessing net_device * except in here */ netdev_dbg(ndev, "net device safe to remove\n"); + /* older versions require that buffer be revoked before close */ + if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_4) + netvsc_teardown_gpadl(device, net_device); + /* Now, we can close the channel safely */ vmbus_close(device->channel); - netvsc_teardown_gpadl(device, net_device); - - /* And dissassociate NAPI context from device */ - for (i = 0; i < net_device->num_chn; i++) - netif_napi_del(&net_device->chan_table[i].napi); + if (net_device->nvsp_version >= NVSP_PROTOCOL_VERSION_4) + netvsc_teardown_gpadl(device, net_device); /* Release all resources */ free_netvsc_device_rcu(net_device); @@ -645,14 +641,18 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, queue_sends = atomic_dec_return(&net_device->chan_table[q_idx].queue_sends); - if (net_device->destroy && queue_sends == 0) - wake_up(&net_device->wait_drain); + if (unlikely(net_device->destroy)) { + if (queue_sends == 0) + wake_up(&net_device->wait_drain); + } else { + struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx); - if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) && - (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || - queue_sends < 1)) { - netif_tx_wake_queue(netdev_get_tx_queue(ndev, q_idx)); - ndev_ctx->eth_stats.wake_queue++; + if (netif_tx_queue_stopped(txq) && + (hv_ringbuf_avail_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || + queue_sends < 1)) { + netif_tx_wake_queue(txq); + ndev_ctx->eth_stats.wake_queue++; + } } } @@ -852,13 +852,6 @@ int netvsc_send(struct net_device *ndev, if (unlikely(!net_device || net_device->destroy)) return -ENODEV; - /* We may race with netvsc_connect_vsp()/netvsc_init_buf() and get - * here before the negotiation with the host is finished and - * send_section_map may not be allocated yet. - */ - if (unlikely(!net_device->send_section_map)) - return -EAGAIN; - nvchan = &net_device->chan_table[packet->q_idx]; packet->send_buf_index = NETVSC_INVALID_INDEX; packet->cp_partial = false; @@ -866,10 +859,8 @@ int netvsc_send(struct net_device *ndev, /* Send control message directly without accessing msd (Multi-Send * Data) field which may be changed during data packet processing. */ - if (!skb) { - cur_send = packet; - goto send_now; - } + if (!skb) + return netvsc_send_pkt(device, packet, net_device, pb, skb); /* batch packets in send buffer if possible */ msdp = &nvchan->msd; @@ -953,7 +944,6 @@ int netvsc_send(struct net_device *ndev, } } -send_now: if (cur_send) ret = netvsc_send_pkt(device, cur_send, net_device, pb, skb); @@ -1217,9 +1207,10 @@ int netvsc_poll(struct napi_struct *napi, int budget) if (send_recv_completions(ndev, net_device, nvchan) == 0 && work_done < budget && napi_complete_done(napi, work_done) && - hv_end_read(&channel->inbound)) { + hv_end_read(&channel->inbound) && + napi_schedule_prep(napi)) { hv_begin_read(&channel->inbound); - napi_reschedule(napi); + __napi_schedule(napi); } /* Driver may overshoot since multiple packets per descriptor */ @@ -1242,7 +1233,7 @@ void netvsc_channel_cb(void *context) /* disable interupts from host */ hv_begin_read(rbi); - __napi_schedule(&nvchan->napi); + __napi_schedule_irqoff(&nvchan->napi); } } @@ -1296,7 +1287,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, netvsc_channel_cb, net_device->chan_table); if (ret != 0) { - netif_napi_del(&net_device->chan_table[0].napi); netdev_err(ndev, "unable to open channel: %d\n", ret); goto cleanup; } @@ -1306,11 +1296,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, napi_enable(&net_device->chan_table[0].napi); - /* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is - * populated. - */ - rcu_assign_pointer(net_device_ctx->nvdev, net_device); - /* Connect with the NetVsp */ ret = netvsc_connect_vsp(device, net_device, device_info); if (ret != 0) { @@ -1319,6 +1304,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, goto close; } + /* Writing nvdev pointer unlocks netvsc_send(), make sure chn_table is + * populated. + */ + rcu_assign_pointer(net_device_ctx->nvdev, net_device); + return net_device; close: @@ -1329,6 +1319,7 @@ close: vmbus_close(device->channel); cleanup: + netif_napi_del(&net_device->chan_table[0].napi); free_netvsc_device(&net_device->rcu); return ERR_PTR(ret); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c5584c2d440e..f28c85d212ce 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -46,7 +46,10 @@ #include "hyperv_net.h" -#define RING_SIZE_MIN 64 +#define RING_SIZE_MIN 64 +#define RETRY_US_LO 5000 +#define RETRY_US_HI 10000 +#define RETRY_MAX 2000 /* >10 sec */ #define LINKCHANGE_INT (2 * HZ) #define VF_TAKEOVER_INT (HZ / 10) @@ -66,12 +69,43 @@ static int debug = -1; module_param(debug, int, S_IRUGO); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); -static void netvsc_set_multicast_list(struct net_device *net) +static void netvsc_change_rx_flags(struct net_device *net, int change) { - struct net_device_context *net_device_ctx = netdev_priv(net); - struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); + struct net_device_context *ndev_ctx = netdev_priv(net); + struct net_device *vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); + int inc; + + if (!vf_netdev) + return; + + if (change & IFF_PROMISC) { + inc = (net->flags & IFF_PROMISC) ? 1 : -1; + dev_set_promiscuity(vf_netdev, inc); + } + + if (change & IFF_ALLMULTI) { + inc = (net->flags & IFF_ALLMULTI) ? 1 : -1; + dev_set_allmulti(vf_netdev, inc); + } +} - rndis_filter_update(nvdev); +static void netvsc_set_rx_mode(struct net_device *net) +{ + struct net_device_context *ndev_ctx = netdev_priv(net); + struct net_device *vf_netdev; + struct netvsc_device *nvdev; + + rcu_read_lock(); + vf_netdev = rcu_dereference(ndev_ctx->vf_netdev); + if (vf_netdev) { + dev_uc_sync(vf_netdev, net); + dev_mc_sync(vf_netdev, net); + } + + nvdev = rcu_dereference(ndev_ctx->nvdev); + if (nvdev) + rndis_filter_update(nvdev); + rcu_read_unlock(); } static int netvsc_open(struct net_device *net) @@ -91,10 +125,7 @@ static int netvsc_open(struct net_device *net) return ret; } - netif_tx_wake_all_queues(net); - rdev = nvdev->extension; - if (!rdev->link_state) netif_carrier_on(net); @@ -112,36 +143,25 @@ static int netvsc_open(struct net_device *net) return 0; } -static int netvsc_close(struct net_device *net) +static int netvsc_wait_until_empty(struct netvsc_device *nvdev) { - struct net_device_context *net_device_ctx = netdev_priv(net); - struct net_device *vf_netdev - = rtnl_dereference(net_device_ctx->vf_netdev); - struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); - int ret = 0; - u32 aread, i, msec = 10, retry = 0, retry_max = 20; - struct vmbus_channel *chn; - - netif_tx_disable(net); - - /* No need to close rndis filter if it is removed already */ - if (!nvdev) - goto out; - - ret = rndis_filter_close(nvdev); - if (ret != 0) { - netdev_err(net, "unable to close device (ret %d).\n", ret); - return ret; - } + unsigned int retry = 0; + int i; /* Ensure pending bytes in ring are read */ - while (true) { - aread = 0; + for (;;) { + u32 aread = 0; + for (i = 0; i < nvdev->num_chn; i++) { - chn = nvdev->chan_table[i].channel; + struct vmbus_channel *chn + = nvdev->chan_table[i].channel; + if (!chn) continue; + /* make sure receive not running now */ + napi_synchronize(&nvdev->chan_table[i].napi); + aread = hv_get_bytes_to_read(&chn->inbound); if (aread) break; @@ -151,22 +171,40 @@ static int netvsc_close(struct net_device *net) break; } - retry++; - if (retry > retry_max || aread == 0) - break; + if (aread == 0) + return 0; - msleep(msec); + if (++retry > RETRY_MAX) + return -ETIMEDOUT; - if (msec < 1000) - msec *= 2; + usleep_range(RETRY_US_LO, RETRY_US_HI); } +} - if (aread) { - netdev_err(net, "Ring buffer not empty after closing rndis\n"); - ret = -ETIMEDOUT; +static int netvsc_close(struct net_device *net) +{ + struct net_device_context *net_device_ctx = netdev_priv(net); + struct net_device *vf_netdev + = rtnl_dereference(net_device_ctx->vf_netdev); + struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); + int ret; + + netif_tx_disable(net); + + /* No need to close rndis filter if it is removed already */ + if (!nvdev) + return 0; + + ret = rndis_filter_close(nvdev); + if (ret != 0) { + netdev_err(net, "unable to close device (ret %d).\n", ret); + return ret; } -out: + ret = netvsc_wait_until_empty(nvdev); + if (ret) + netdev_err(net, "Ring buffer not empty after closing rndis\n"); + if (vf_netdev) dev_close(vf_netdev); @@ -299,8 +337,19 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, rcu_read_lock(); vf_netdev = rcu_dereference(ndc->vf_netdev); if (vf_netdev) { - txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; - qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + const struct net_device_ops *vf_ops = vf_netdev->netdev_ops; + + if (vf_ops->ndo_select_queue) + txq = vf_ops->ndo_select_queue(vf_netdev, skb, + accel_priv, fallback); + else + txq = fallback(vf_netdev, skb); + + /* Record the queue selected by VF so that it can be + * used for common case where VF has more queues than + * the synthetic device. + */ + qdisc_skb_cb(skb)->slave_dev_queue_mapping = txq; } else { txq = netvsc_pick_tx(ndev, skb); } @@ -804,16 +853,81 @@ static void netvsc_get_channels(struct net_device *net, } } +static int netvsc_detach(struct net_device *ndev, + struct netvsc_device *nvdev) +{ + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hdev = ndev_ctx->device_ctx; + int ret; + + /* Don't try continuing to try and setup sub channels */ + if (cancel_work_sync(&nvdev->subchan_work)) + nvdev->num_chn = 1; + + /* If device was up (receiving) then shutdown */ + if (netif_running(ndev)) { + netif_tx_disable(ndev); + + ret = rndis_filter_close(nvdev); + if (ret) { + netdev_err(ndev, + "unable to close device (ret %d).\n", ret); + return ret; + } + + ret = netvsc_wait_until_empty(nvdev); + if (ret) { + netdev_err(ndev, + "Ring buffer not empty after closing rndis\n"); + return ret; + } + } + + netif_device_detach(ndev); + + rndis_filter_device_remove(hdev, nvdev); + + return 0; +} + +static int netvsc_attach(struct net_device *ndev, + struct netvsc_device_info *dev_info) +{ + struct net_device_context *ndev_ctx = netdev_priv(ndev); + struct hv_device *hdev = ndev_ctx->device_ctx; + struct netvsc_device *nvdev; + struct rndis_device *rdev; + int ret; + + nvdev = rndis_filter_device_add(hdev, dev_info); + if (IS_ERR(nvdev)) + return PTR_ERR(nvdev); + + /* Note: enable and attach happen when sub-channels setup */ + + netif_carrier_off(ndev); + + if (netif_running(ndev)) { + ret = rndis_filter_open(nvdev); + if (ret) + return ret; + + rdev = nvdev->extension; + if (!rdev->link_state) + netif_carrier_on(ndev); + } + + return 0; +} + static int netvsc_set_channels(struct net_device *net, struct ethtool_channels *channels) { struct net_device_context *net_device_ctx = netdev_priv(net); - struct hv_device *dev = net_device_ctx->device_ctx; struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); unsigned int orig, count = channels->combined_count; struct netvsc_device_info device_info; - bool was_opened; - int ret = 0; + int ret; /* We do not support separate count for rx, tx, or other */ if (count == 0 || @@ -830,9 +944,6 @@ static int netvsc_set_channels(struct net_device *net, return -EINVAL; orig = nvdev->num_chn; - was_opened = rndis_filter_opened(nvdev); - if (was_opened) - rndis_filter_close(nvdev); memset(&device_info, 0, sizeof(device_info)); device_info.num_chn = count; @@ -841,28 +952,17 @@ static int netvsc_set_channels(struct net_device *net, device_info.recv_sections = nvdev->recv_section_cnt; device_info.recv_section_size = nvdev->recv_section_size; - rndis_filter_device_remove(dev, nvdev); + ret = netvsc_detach(net, nvdev); + if (ret) + return ret; - nvdev = rndis_filter_device_add(dev, &device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); + ret = netvsc_attach(net, &device_info); + if (ret) { device_info.num_chn = orig; - nvdev = rndis_filter_device_add(dev, &device_info); - - if (IS_ERR(nvdev)) { - netdev_err(net, "restoring channel setting failed: %ld\n", - PTR_ERR(nvdev)); - return ret; - } + if (netvsc_attach(net, &device_info)) + netdev_err(net, "restoring channel setting failed\n"); } - if (was_opened) - rndis_filter_open(nvdev); - - /* We may have missed link change notifications */ - net_device_ctx->last_reconfig = 0; - schedule_delayed_work(&net_device_ctx->dwork, 0); - return ret; } @@ -928,10 +1028,8 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) struct net_device_context *ndevctx = netdev_priv(ndev); struct net_device *vf_netdev = rtnl_dereference(ndevctx->vf_netdev); struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); - struct hv_device *hdev = ndevctx->device_ctx; int orig_mtu = ndev->mtu; struct netvsc_device_info device_info; - bool was_opened; int ret = 0; if (!nvdev || nvdev->destroy) @@ -944,11 +1042,6 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) return ret; } - netif_device_detach(ndev); - was_opened = rndis_filter_opened(nvdev); - if (was_opened) - rndis_filter_close(nvdev); - memset(&device_info, 0, sizeof(device_info)); device_info.num_chn = nvdev->num_chn; device_info.send_sections = nvdev->send_section_cnt; @@ -956,35 +1049,27 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) device_info.recv_sections = nvdev->recv_section_cnt; device_info.recv_section_size = nvdev->recv_section_size; - rndis_filter_device_remove(hdev, nvdev); + ret = netvsc_detach(ndev, nvdev); + if (ret) + goto rollback_vf; ndev->mtu = mtu; - nvdev = rndis_filter_device_add(hdev, &device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); - - /* Attempt rollback to original MTU */ - ndev->mtu = orig_mtu; - nvdev = rndis_filter_device_add(hdev, &device_info); - - if (vf_netdev) - dev_set_mtu(vf_netdev, orig_mtu); - - if (IS_ERR(nvdev)) { - netdev_err(ndev, "restoring mtu failed: %ld\n", - PTR_ERR(nvdev)); - return ret; - } - } + ret = netvsc_attach(ndev, &device_info); + if (ret) + goto rollback; - if (was_opened) - rndis_filter_open(nvdev); + return 0; - netif_device_attach(ndev); +rollback: + /* Attempt rollback to original MTU */ + ndev->mtu = orig_mtu; - /* We may have missed link change notifications */ - schedule_delayed_work(&ndevctx->dwork, 0); + if (netvsc_attach(ndev, &device_info)) + netdev_err(ndev, "restoring mtu failed\n"); +rollback_vf: + if (vf_netdev) + dev_set_mtu(vf_netdev, orig_mtu); return ret; } @@ -1490,11 +1575,9 @@ static int netvsc_set_ringparam(struct net_device *ndev, { struct net_device_context *ndevctx = netdev_priv(ndev); struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); - struct hv_device *hdev = ndevctx->device_ctx; struct netvsc_device_info device_info; struct ethtool_ringparam orig; u32 new_tx, new_rx; - bool was_opened; int ret = 0; if (!nvdev || nvdev->destroy) @@ -1519,34 +1602,18 @@ static int netvsc_set_ringparam(struct net_device *ndev, device_info.recv_sections = new_rx; device_info.recv_section_size = nvdev->recv_section_size; - netif_device_detach(ndev); - was_opened = rndis_filter_opened(nvdev); - if (was_opened) - rndis_filter_close(nvdev); - - rndis_filter_device_remove(hdev, nvdev); - - nvdev = rndis_filter_device_add(hdev, &device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); + ret = netvsc_detach(ndev, nvdev); + if (ret) + return ret; + ret = netvsc_attach(ndev, &device_info); + if (ret) { device_info.send_sections = orig.tx_pending; device_info.recv_sections = orig.rx_pending; - nvdev = rndis_filter_device_add(hdev, &device_info); - if (IS_ERR(nvdev)) { - netdev_err(ndev, "restoring ringparam failed: %ld\n", - PTR_ERR(nvdev)); - return ret; - } - } - if (was_opened) - rndis_filter_open(nvdev); - netif_device_attach(ndev); - - /* We may have missed link change notifications */ - ndevctx->last_reconfig = 0; - schedule_delayed_work(&ndevctx->dwork, 0); + if (netvsc_attach(ndev, &device_info)) + netdev_err(ndev, "restoring ringparam failed"); + } return ret; } @@ -1576,7 +1643,8 @@ static const struct net_device_ops device_ops = { .ndo_open = netvsc_open, .ndo_stop = netvsc_close, .ndo_start_xmit = netvsc_start_xmit, - .ndo_set_rx_mode = netvsc_set_multicast_list, + .ndo_change_rx_flags = netvsc_change_rx_flags, + .ndo_set_rx_mode = netvsc_set_rx_mode, .ndo_change_mtu = netvsc_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = netvsc_set_mac_addr, @@ -1807,6 +1875,15 @@ static void __netvsc_vf_setup(struct net_device *ndev, netdev_warn(vf_netdev, "unable to change mtu to %u\n", ndev->mtu); + /* set multicast etc flags on VF */ + dev_change_flags(vf_netdev, ndev->flags | IFF_SLAVE); + + /* sync address list from ndev to VF */ + netif_addr_lock_bh(ndev); + dev_uc_sync(vf_netdev, ndev); + dev_mc_sync(vf_netdev, ndev); + netif_addr_unlock_bh(ndev); + if (netif_running(ndev)) { ret = dev_open(vf_netdev); if (ret) @@ -2021,8 +2098,8 @@ no_net: static int netvsc_remove(struct hv_device *dev) { struct net_device_context *ndev_ctx; - struct net_device *vf_netdev; - struct net_device *net; + struct net_device *vf_netdev, *net; + struct netvsc_device *nvdev; net = hv_get_drvdata(dev); if (net == NULL) { @@ -2032,10 +2109,14 @@ static int netvsc_remove(struct hv_device *dev) ndev_ctx = netdev_priv(net); - netif_device_detach(net); - cancel_delayed_work_sync(&ndev_ctx->dwork); + rcu_read_lock(); + nvdev = rcu_dereference(ndev_ctx->nvdev); + + if (nvdev) + cancel_work_sync(&nvdev->subchan_work); + /* * Call to the vsc driver to let it know that the device is being * removed. Also blocks mtu and channel changes. @@ -2045,11 +2126,13 @@ static int netvsc_remove(struct hv_device *dev) if (vf_netdev) netvsc_unregister_vf(vf_netdev); + if (nvdev) + rndis_filter_device_remove(dev, nvdev); + unregister_netdevice(net); - rndis_filter_device_remove(dev, - rtnl_dereference(ndev_ctx->nvdev)); rtnl_unlock(); + rcu_read_unlock(); hv_set_drvdata(dev, NULL); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index c3ca191fea7f..a6ec41c399d6 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -264,13 +264,23 @@ static void rndis_set_link_state(struct rndis_device *rdev, } } -static void rndis_filter_receive_response(struct rndis_device *dev, - struct rndis_message *resp) +static void rndis_filter_receive_response(struct net_device *ndev, + struct netvsc_device *nvdev, + const struct rndis_message *resp) { + struct rndis_device *dev = nvdev->extension; struct rndis_request *request = NULL; bool found = false; unsigned long flags; - struct net_device *ndev = dev->ndev; + + /* This should never happen, it means control message + * response received after device removed. + */ + if (dev->state == RNDIS_DEV_UNINITIALIZED) { + netdev_err(ndev, + "got rndis message uninitialized\n"); + return; + } spin_lock_irqsave(&dev->request_lock, flags); list_for_each_entry(request, &dev->req_list, list_ent) { @@ -352,7 +362,6 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, u32 type) static int rndis_filter_receive_data(struct net_device *ndev, struct netvsc_device *nvdev, - struct rndis_device *dev, struct rndis_message *msg, struct vmbus_channel *channel, void *data, u32 data_buflen) @@ -372,7 +381,7 @@ static int rndis_filter_receive_data(struct net_device *ndev, * should be the data packet size plus the trailer padding size */ if (unlikely(data_buflen < rndis_pkt->data_len)) { - netdev_err(dev->ndev, "rndis message buffer " + netdev_err(ndev, "rndis message buffer " "overflow detected (got %u, min %u)" "...dropping this message!\n", data_buflen, rndis_pkt->data_len); @@ -400,35 +409,20 @@ int rndis_filter_receive(struct net_device *ndev, void *data, u32 buflen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct rndis_device *rndis_dev = net_dev->extension; struct rndis_message *rndis_msg = data; - /* Make sure the rndis device state is initialized */ - if (unlikely(!rndis_dev)) { - netif_dbg(net_device_ctx, rx_err, ndev, - "got rndis message but no rndis device!\n"); - return NVSP_STAT_FAIL; - } - - if (unlikely(rndis_dev->state == RNDIS_DEV_UNINITIALIZED)) { - netif_dbg(net_device_ctx, rx_err, ndev, - "got rndis message uninitialized\n"); - return NVSP_STAT_FAIL; - } - if (netif_msg_rx_status(net_device_ctx)) dump_rndis_message(ndev, rndis_msg); switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: - return rndis_filter_receive_data(ndev, net_dev, - rndis_dev, rndis_msg, + return rndis_filter_receive_data(ndev, net_dev, rndis_msg, channel, data, buflen); case RNDIS_MSG_INIT_C: case RNDIS_MSG_QUERY_C: case RNDIS_MSG_SET_C: /* completion msgs */ - rndis_filter_receive_response(rndis_dev, rndis_msg); + rndis_filter_receive_response(ndev, net_dev, rndis_msg); break; case RNDIS_MSG_INDICATE: @@ -825,13 +819,15 @@ static int rndis_filter_set_packet_filter(struct rndis_device *dev, struct rndis_set_request *set; int ret; + if (dev->filter == new_filter) + return 0; + request = get_rndis_request(dev, RNDIS_MSG_SET, RNDIS_MESSAGE_SIZE(struct rndis_set_request) + sizeof(u32)); if (!request) return -ENOMEM; - /* Setup the rndis set */ set = &request->request_msg.msg.set_req; set->oid = RNDIS_OID_GEN_CURRENT_PACKET_FILTER; @@ -842,8 +838,10 @@ static int rndis_filter_set_packet_filter(struct rndis_device *dev, &new_filter, sizeof(u32)); ret = rndis_filter_send_request(dev, request); - if (ret == 0) + if (ret == 0) { wait_for_completion(&request->wait_event); + dev->filter = new_filter; + } put_rndis_request(dev, request); @@ -854,15 +852,19 @@ static void rndis_set_multicast(struct work_struct *w) { struct rndis_device *rdev = container_of(w, struct rndis_device, mcast_work); + u32 filter = NDIS_PACKET_TYPE_DIRECTED; + unsigned int flags = rdev->ndev->flags; - if (rdev->ndev->flags & IFF_PROMISC) - rndis_filter_set_packet_filter(rdev, - NDIS_PACKET_TYPE_PROMISCUOUS); - else - rndis_filter_set_packet_filter(rdev, - NDIS_PACKET_TYPE_BROADCAST | - NDIS_PACKET_TYPE_ALL_MULTICAST | - NDIS_PACKET_TYPE_DIRECTED); + if (flags & IFF_PROMISC) { + filter = NDIS_PACKET_TYPE_PROMISCUOUS; + } else { + if (flags & IFF_ALLMULTI) + filter |= NDIS_PACKET_TYPE_ALL_MULTICAST; + if (flags & IFF_BROADCAST) + filter |= NDIS_PACKET_TYPE_BROADCAST; + } + + rndis_filter_set_packet_filter(rdev, filter); } void rndis_filter_update(struct netvsc_device *nvdev) @@ -1116,6 +1118,7 @@ void rndis_set_subchannel(struct work_struct *w) for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) ndev_ctx->tx_table[i] = i % nvdev->num_chn; + netif_device_attach(ndev); rtnl_unlock(); return; @@ -1126,6 +1129,8 @@ failed: nvdev->max_chn = 1; nvdev->num_chn = 1; + + netif_device_attach(ndev); unlock: rtnl_unlock(); } @@ -1328,6 +1333,10 @@ out: net_device->num_chn = 1; } + /* No sub channels, device is ready */ + if (net_device->num_chn == 1) + netif_device_attach(net); + return net_device; err_dev_remv: @@ -1346,7 +1355,6 @@ void rndis_filter_device_remove(struct hv_device *dev, net_dev->extension = NULL; netvsc_device_remove(dev); - kfree(rndis_dev); } int rndis_filter_open(struct netvsc_device *nvdev) @@ -1364,10 +1372,3 @@ int rndis_filter_close(struct netvsc_device *nvdev) return rndis_filter_close_device(nvdev->extension); } - -bool rndis_filter_opened(const struct netvsc_device *nvdev) -{ - const struct rndis_device *dev = nvdev->extension; - - return dev->state == RNDIS_DEV_DATAINITIALIZED; -} diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 7de88b33d5b9..9cbb0c8a896a 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3277,7 +3277,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev, err = netdev_upper_dev_link(real_dev, dev, extack); if (err < 0) - goto unregister; + goto put_dev; /* need to be already registered so that ->init has run and * the MAC addr is set @@ -3316,7 +3316,8 @@ del_dev: macsec_del_dev(macsec); unlink: netdev_upper_dev_unlink(real_dev, dev); -unregister: +put_dev: + dev_put(real_dev); unregister_netdevice(dev); return err; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 8fc02d9db3d0..725f4b4afc6d 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1036,7 +1036,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, lowerdev_features &= (features | ~NETIF_F_LRO); features = netdev_increment_features(lowerdev_features, features, mask); features |= ALWAYS_ON_FEATURES; - features &= ~NETIF_F_NETNS_LOCAL; + features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES); return features; } diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 171010eb4d9c..5ad130c3da43 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -341,8 +341,8 @@ void bcm_phy_get_strings(struct phy_device *phydev, u8 *data) unsigned int i; for (i = 0; i < ARRAY_SIZE(bcm_phy_hw_stats); i++) - memcpy(data + i * ETH_GSTRING_LEN, - bcm_phy_hw_stats[i].string, ETH_GSTRING_LEN); + strlcpy(data + i * ETH_GSTRING_LEN, + bcm_phy_hw_stats[i].string, ETH_GSTRING_LEN); } EXPORT_SYMBOL_GPL(bcm_phy_get_strings); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 22d9bc9c33a4..0e0978d8a0eb 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1452,8 +1452,8 @@ static void marvell_get_strings(struct phy_device *phydev, u8 *data) int i; for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) { - memcpy(data + i * ETH_GSTRING_LEN, - marvell_hw_stats[i].string, ETH_GSTRING_LEN); + strlcpy(data + i * ETH_GSTRING_LEN, + marvell_hw_stats[i].string, ETH_GSTRING_LEN); } } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 0f45310300f6..f41b224a9cdb 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -635,25 +635,6 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev) return 0; } -/* This routine returns -1 as an indication to the caller that the - * Micrel ksz9021 10/100/1000 PHY does not support standard IEEE - * MMD extended PHY registers. - */ -static int -ksz9021_rd_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum) -{ - return -1; -} - -/* This routine does nothing since the Micrel ksz9021 does not support - * standard IEEE MMD extended PHY registers. - */ -static int -ksz9021_wr_mmd_phyreg(struct phy_device *phydev, int devad, u16 regnum, u16 val) -{ - return -1; -} - static int kszphy_get_sset_count(struct phy_device *phydev) { return ARRAY_SIZE(kszphy_hw_stats); @@ -664,8 +645,8 @@ static void kszphy_get_strings(struct phy_device *phydev, u8 *data) int i; for (i = 0; i < ARRAY_SIZE(kszphy_hw_stats); i++) { - memcpy(data + i * ETH_GSTRING_LEN, - kszphy_hw_stats[i].string, ETH_GSTRING_LEN); + strlcpy(data + i * ETH_GSTRING_LEN, + kszphy_hw_stats[i].string, ETH_GSTRING_LEN); } } @@ -946,8 +927,8 @@ static struct phy_driver ksphy_driver[] = { .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = genphy_resume, - .read_mmd = ksz9021_rd_mmd_phyreg, - .write_mmd = ksz9021_wr_mmd_phyreg, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { .phy_id = PHY_ID_KSZ9031, .phy_id_mask = MICREL_PHY_ID_MASK, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e3e29c2b028b..9aabfa1a455a 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -618,6 +618,77 @@ static void phy_error(struct phy_device *phydev) } /** + * phy_disable_interrupts - Disable the PHY interrupts from the PHY side + * @phydev: target phy_device struct + */ +static int phy_disable_interrupts(struct phy_device *phydev) +{ + int err; + + /* Disable PHY interrupts */ + err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED); + if (err) + goto phy_err; + + /* Clear the interrupt */ + err = phy_clear_interrupt(phydev); + if (err) + goto phy_err; + + return 0; + +phy_err: + phy_error(phydev); + + return err; +} + +/** + * phy_change - Called by the phy_interrupt to handle PHY changes + * @phydev: phy_device struct that interrupted + */ +static irqreturn_t phy_change(struct phy_device *phydev) +{ + if (phy_interrupt_is_valid(phydev)) { + if (phydev->drv->did_interrupt && + !phydev->drv->did_interrupt(phydev)) + return IRQ_NONE; + + if (phydev->state == PHY_HALTED) + if (phy_disable_interrupts(phydev)) + goto phy_err; + } + + mutex_lock(&phydev->lock); + if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state)) + phydev->state = PHY_CHANGELINK; + mutex_unlock(&phydev->lock); + + /* reschedule state queue work to run as soon as possible */ + phy_trigger_machine(phydev, true); + + if (phy_interrupt_is_valid(phydev) && phy_clear_interrupt(phydev)) + goto phy_err; + return IRQ_HANDLED; + +phy_err: + phy_error(phydev); + return IRQ_NONE; +} + +/** + * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes + * @work: work_struct that describes the work to be done + */ +void phy_change_work(struct work_struct *work) +{ + struct phy_device *phydev = + container_of(work, struct phy_device, phy_queue); + + phy_change(phydev); +} + +/** * phy_interrupt - PHY interrupt handler * @irq: interrupt line * @phy_dat: phy_device pointer @@ -632,9 +703,7 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) if (PHY_HALTED == phydev->state) return IRQ_NONE; /* It can't be ours. */ - phy_change(phydev); - - return IRQ_HANDLED; + return phy_change(phydev); } /** @@ -652,32 +721,6 @@ static int phy_enable_interrupts(struct phy_device *phydev) } /** - * phy_disable_interrupts - Disable the PHY interrupts from the PHY side - * @phydev: target phy_device struct - */ -static int phy_disable_interrupts(struct phy_device *phydev) -{ - int err; - - /* Disable PHY interrupts */ - err = phy_config_interrupt(phydev, PHY_INTERRUPT_DISABLED); - if (err) - goto phy_err; - - /* Clear the interrupt */ - err = phy_clear_interrupt(phydev); - if (err) - goto phy_err; - - return 0; - -phy_err: - phy_error(phydev); - - return err; -} - -/** * phy_start_interrupts - request and enable interrupts for a PHY device * @phydev: target phy_device struct * @@ -720,50 +763,6 @@ int phy_stop_interrupts(struct phy_device *phydev) EXPORT_SYMBOL(phy_stop_interrupts); /** - * phy_change - Called by the phy_interrupt to handle PHY changes - * @phydev: phy_device struct that interrupted - */ -void phy_change(struct phy_device *phydev) -{ - if (phy_interrupt_is_valid(phydev)) { - if (phydev->drv->did_interrupt && - !phydev->drv->did_interrupt(phydev)) - return; - - if (phydev->state == PHY_HALTED) - if (phy_disable_interrupts(phydev)) - goto phy_err; - } - - mutex_lock(&phydev->lock); - if ((PHY_RUNNING == phydev->state) || (PHY_NOLINK == phydev->state)) - phydev->state = PHY_CHANGELINK; - mutex_unlock(&phydev->lock); - - /* reschedule state queue work to run as soon as possible */ - phy_trigger_machine(phydev, true); - - if (phy_interrupt_is_valid(phydev) && phy_clear_interrupt(phydev)) - goto phy_err; - return; - -phy_err: - phy_error(phydev); -} - -/** - * phy_change_work - Scheduled by the phy_mac_interrupt to handle PHY changes - * @work: work_struct that describes the work to be done - */ -void phy_change_work(struct work_struct *work) -{ - struct phy_device *phydev = - container_of(work, struct phy_device, phy_queue); - - phy_change(phydev); -} - -/** * phy_stop - Bring down the PHY link, and stop checking the status * @phydev: target phy_device struct */ @@ -819,7 +818,7 @@ void phy_start(struct phy_device *phydev) break; case PHY_HALTED: /* if phy was suspended, bring the physical link up again */ - phy_resume(phydev); + __phy_resume(phydev); /* make sure interrupts are re-enabled for the PHY */ if (phy_interrupt_is_valid(phydev)) { diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d39ae77707ef..74664a6c0cdc 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -135,9 +135,7 @@ static int mdio_bus_phy_resume(struct device *dev) if (!mdio_bus_phy_may_suspend(phydev)) goto no_resume; - mutex_lock(&phydev->lock); ret = phy_resume(phydev); - mutex_unlock(&phydev->lock); if (ret < 0) return ret; @@ -1014,10 +1012,17 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, err = sysfs_create_link(&phydev->mdio.dev.kobj, &dev->dev.kobj, "attached_dev"); if (!err) { - err = sysfs_create_link(&dev->dev.kobj, &phydev->mdio.dev.kobj, - "phydev"); - if (err) - goto error; + err = sysfs_create_link_nowarn(&dev->dev.kobj, + &phydev->mdio.dev.kobj, + "phydev"); + if (err) { + dev_err(&dev->dev, "could not add device link to %s err %d\n", + kobject_name(&phydev->mdio.dev.kobj), + err); + /* non-fatal - some net drivers can use one netdevice + * with more then one phy + */ + } phydev->sysfs_links = true; } @@ -1041,9 +1046,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (err) goto error; - mutex_lock(&phydev->lock); phy_resume(phydev); - mutex_unlock(&phydev->lock); phy_led_triggers_register(phydev); return err; @@ -1172,7 +1175,7 @@ int phy_suspend(struct phy_device *phydev) } EXPORT_SYMBOL(phy_suspend); -int phy_resume(struct phy_device *phydev) +int __phy_resume(struct phy_device *phydev) { struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver); int ret = 0; @@ -1189,6 +1192,18 @@ int phy_resume(struct phy_device *phydev) return ret; } +EXPORT_SYMBOL(__phy_resume); + +int phy_resume(struct phy_device *phydev) +{ + int ret; + + mutex_lock(&phydev->lock); + ret = __phy_resume(phydev); + mutex_unlock(&phydev->lock); + + return ret; +} EXPORT_SYMBOL(phy_resume); int phy_loopback(struct phy_device *phydev, bool enable) @@ -1658,6 +1673,23 @@ int genphy_config_init(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_config_init); +/* This is used for the phy device which doesn't support the MMD extended + * register access, but it does have side effect when we are trying to access + * the MMD register via indirect method. + */ +int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(genphy_read_mmd_unsupported); + +int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, + u16 regnum, u16 val) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(genphy_write_mmd_unsupported); + int genphy_suspend(struct phy_device *phydev) { return phy_set_bits(phydev, MII_BMCR, BMCR_PDOWN); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index ee3ca4a2f12b..9f48ecf9c627 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -172,6 +172,8 @@ static struct phy_driver realtek_drvs[] = { .flags = PHY_HAS_INTERRUPT, .ack_interrupt = &rtl821x_ack_interrupt, .config_intr = &rtl8211b_config_intr, + .read_mmd = &genphy_read_mmd_unsupported, + .write_mmd = &genphy_write_mmd_unsupported, }, { .phy_id = 0x001cc914, .name = "RTL8211DN Gigabit Ethernet", diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 255a5def56e9..da1937832c99 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -257,7 +257,7 @@ struct ppp_net { /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); -static void ppp_xmit_process(struct ppp *ppp); +static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); @@ -513,13 +513,12 @@ static ssize_t ppp_write(struct file *file, const char __user *buf, goto out; } - skb_queue_tail(&pf->xq, skb); - switch (pf->kind) { case INTERFACE: - ppp_xmit_process(PF_TO_PPP(pf)); + ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: + skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } @@ -1267,8 +1266,8 @@ ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); - skb_queue_tail(&ppp->file.xq, skb); - ppp_xmit_process(ppp); + ppp_xmit_process(ppp, skb); + return NETDEV_TX_OK; outf: @@ -1420,13 +1419,14 @@ static void ppp_setup(struct net_device *dev) */ /* Called to do any work queued up on the transmit side that can now be done */ -static void __ppp_xmit_process(struct ppp *ppp) +static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { - struct sk_buff *skb; - ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); + + if (skb) + skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); @@ -1440,7 +1440,7 @@ static void __ppp_xmit_process(struct ppp *ppp) ppp_xmit_unlock(ppp); } -static void ppp_xmit_process(struct ppp *ppp) +static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); @@ -1448,7 +1448,7 @@ static void ppp_xmit_process(struct ppp *ppp) goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; - __ppp_xmit_process(ppp); + __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); @@ -1458,6 +1458,8 @@ static void ppp_xmit_process(struct ppp *ppp) err: local_bh_enable(); + kfree_skb(skb); + if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } @@ -1942,7 +1944,7 @@ static void __ppp_channel_push(struct channel *pch) if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) - __ppp_xmit_process(ppp); + __ppp_xmit_process(ppp, NULL); } } @@ -3161,6 +3163,15 @@ ppp_connect_channel(struct channel *pch, int unit) goto outl; ppp_lock(ppp); + spin_lock_bh(&pch->downl); + if (!pch->chan) { + /* Don't connect unregistered channels */ + spin_unlock_bh(&pch->downl); + ppp_unlock(ppp); + ret = -ENOTCONN; + goto outl; + } + spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index a468439969df..56c701b73c12 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2395,7 +2395,7 @@ send_done: if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) - goto errout; + return err; goto send_done; } @@ -2681,7 +2681,7 @@ send_done: if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) - goto errout; + return err; goto send_done; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b52258c327d2..28cfa642e39a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -181,7 +181,6 @@ struct tun_file { struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; - int xdp_pending_pkts; }; struct tun_flow_entry { @@ -656,7 +655,7 @@ static struct tun_struct *tun_enable_queue(struct tun_file *tfile) return tun; } -static void tun_ptr_free(void *ptr) +void tun_ptr_free(void *ptr) { if (!ptr) return; @@ -668,6 +667,7 @@ static void tun_ptr_free(void *ptr) __skb_array_destroy_skb(ptr); } } +EXPORT_SYMBOL_GPL(tun_ptr_free); static void tun_queue_purge(struct tun_file *tfile) { @@ -1643,6 +1643,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, else *skb_xdp = 0; + preempt_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog && !*skb_xdp) { @@ -1662,11 +1663,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, case XDP_REDIRECT: get_page(alloc_frag->page); alloc_frag->offset += buflen; - ++tfile->xdp_pending_pkts; err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); + xdp_do_flush_map(); if (err) goto err_redirect; rcu_read_unlock(); + preempt_enable(); return NULL; case XDP_TX: xdp_xmit = true; @@ -1688,6 +1690,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, skb = build_skb(buf, buflen); if (!skb) { rcu_read_unlock(); + preempt_enable(); return ERR_PTR(-ENOMEM); } @@ -1700,10 +1703,12 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, skb->dev = tun->dev; generic_xdp_tx(skb, xdp_prog); rcu_read_unlock(); + preempt_enable(); return NULL; } rcu_read_unlock(); + preempt_enable(); return skb; @@ -1711,6 +1716,7 @@ err_redirect: put_page(alloc_frag->page); err_xdp: rcu_read_unlock(); + preempt_enable(); this_cpu_inc(tun->pcpu_stats->rx_dropped); return NULL; } @@ -1984,11 +1990,6 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK, false); - if (tfile->xdp_pending_pkts) { - tfile->xdp_pending_pkts = 0; - xdp_do_flush_map(); - } - tun_put(tun); return result; } @@ -2325,13 +2326,6 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); - - if (tfile->xdp_pending_pkts >= NAPI_POLL_WEIGHT || - !(m->msg_flags & MSG_MORE)) { - tfile->xdp_pending_pkts = 0; - xdp_do_flush_map(); - } - tun_put(tun); return ret; } @@ -3163,7 +3157,6 @@ static int tun_chr_open(struct inode *inode, struct file * file) sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring)); - tfile->xdp_pending_pkts = 0; return 0; } diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 05dca3e5c93d..fff4b13eece2 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -896,6 +896,12 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&wwan_info, }, { + /* Cinterion PLS8 modem by GEMALTO */ + USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0061, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), .driver_info = (unsigned long) &cdc_info, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 958b2e8b90f6..86f7196f9d91 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1794,7 +1794,7 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) tx_data += len; agg->skb_len += len; - agg->skb_num++; + agg->skb_num += skb_shinfo(skb)->gso_segs ?: 1; dev_kfree_skb_any(skb); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 8a22ff67b026..d9eea8cfe6cb 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -315,6 +315,7 @@ static void __usbnet_status_stop_force(struct usbnet *dev) void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) { struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64); + unsigned long flags; int status; if (test_bit(EVENT_RX_PAUSED, &dev->flags)) { @@ -326,10 +327,10 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) if (skb->protocol == 0) skb->protocol = eth_type_trans (skb, dev->net); - u64_stats_update_begin(&stats64->syncp); + flags = u64_stats_update_begin_irqsave(&stats64->syncp); stats64->rx_packets++; stats64->rx_bytes += skb->len; - u64_stats_update_end(&stats64->syncp); + u64_stats_update_end_irqrestore(&stats64->syncp, flags); netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", skb->len + sizeof (struct ethhdr), skb->protocol); @@ -1248,11 +1249,12 @@ static void tx_complete (struct urb *urb) if (urb->status == 0) { struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->stats64); + unsigned long flags; - u64_stats_update_begin(&stats64->syncp); + flags = u64_stats_update_begin_irqsave(&stats64->syncp); stats64->tx_packets += entry->packets; stats64->tx_bytes += entry->length; - u64_stats_update_end(&stats64->syncp); + u64_stats_update_end_irqrestore(&stats64->syncp, flags); } else { dev->net->stats.tx_errors++; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 9bb9e562b893..23374603e4d9 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -504,6 +504,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, page_off += *len; while (--*num_buf) { + int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); unsigned int buflen; void *buf; int off; @@ -518,7 +519,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq, /* guard against a misconfigured or uncooperative backend that * is sending packet larger than the MTU. */ - if ((page_off + buflen) > PAGE_SIZE) { + if ((page_off + buflen + tailroom) > PAGE_SIZE) { put_page(p); goto err_buf; } @@ -690,6 +691,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, unsigned int truesize; unsigned int headroom = mergeable_ctx_to_headroom(ctx); bool sent; + int err; head_skb = NULL; @@ -701,7 +703,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *data; u32 act; - /* This happens when rx buffer size is underestimated */ + /* This happens when rx buffer size is underestimated + * or headroom is not enough because of the buffer + * was refilled before XDP is set. This should only + * happen for the first several packets, so we don't + * care much about its performance. + */ if (unlikely(num_buf > 1 || headroom < virtnet_get_headroom(vi))) { /* linearize data for XDP */ @@ -736,9 +743,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, act = bpf_prog_run_xdp(xdp_prog, &xdp); - if (act != XDP_PASS) - ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len); - switch (act) { case XDP_PASS: /* recalculate offset to account for any header @@ -770,6 +774,18 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto err_xdp; rcu_read_unlock(); goto xdp_xmit; + case XDP_REDIRECT: + err = xdp_do_redirect(dev, &xdp, xdp_prog); + if (err) { + if (unlikely(xdp_page != page)) + put_page(xdp_page); + goto err_xdp; + } + *xdp_xmit = true; + if (unlikely(xdp_page != page)) + goto err_xdp; + rcu_read_unlock(); + goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: @@ -1013,13 +1029,18 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq, } static unsigned int get_mergeable_buf_len(struct receive_queue *rq, - struct ewma_pkt_len *avg_pkt_len) + struct ewma_pkt_len *avg_pkt_len, + unsigned int room) { const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); unsigned int len; - len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), + if (room) + return PAGE_SIZE - room; + + len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), rq->min_buf_len, PAGE_SIZE - hdr_len); + return ALIGN(len, L1_CACHE_BYTES); } @@ -1028,21 +1049,27 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, { struct page_frag *alloc_frag = &rq->alloc_frag; unsigned int headroom = virtnet_get_headroom(vi); + unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; + unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); char *buf; void *ctx; int err; unsigned int len, hole; - len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len); - if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp))) + /* Extra tailroom is needed to satisfy XDP's assumption. This + * means rx frags coalescing won't work, but consider we've + * disabled GSO for XDP, it won't be a big issue. + */ + len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); + if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) return -ENOMEM; buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; buf += headroom; /* advance address leaving hole at front of pkt */ get_page(alloc_frag->page); - alloc_frag->offset += len + headroom; + alloc_frag->offset += len + room; hole = alloc_frag->size - alloc_frag->offset; - if (hole < len + headroom) { + if (hole < len + room) { /* To avoid internal fragmentation, if there is very likely not * enough space for another buffer, add the remaining space to * the current buffer. @@ -2185,8 +2212,9 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } /* Make sure NAPI is not using any XDP TX queues for RX. */ - for (i = 0; i < vi->max_queue_pairs; i++) - napi_disable(&vi->rq[i].napi); + if (netif_running(dev)) + for (i = 0; i < vi->max_queue_pairs; i++) + napi_disable(&vi->rq[i].napi); netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); @@ -2205,7 +2233,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } if (old_prog) bpf_prog_put(old_prog); - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (netif_running(dev)) + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); } return 0; @@ -2576,12 +2605,15 @@ static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue, { struct virtnet_info *vi = netdev_priv(queue->dev); unsigned int queue_index = get_netdev_rx_queue_index(queue); + unsigned int headroom = virtnet_get_headroom(vi); + unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; struct ewma_pkt_len *avg; BUG_ON(queue_index >= vi->max_queue_pairs); avg = &vi->rq[queue_index].mrg_avg_pkt_len; return sprintf(buf, "%u\n", - get_mergeable_buf_len(&vi->rq[queue_index], avg)); + get_mergeable_buf_len(&vi->rq[queue_index], avg, + SKB_DATA_ALIGN(headroom + tailroom))); } static struct rx_queue_attribute mergeable_rx_buffer_size_attribute = diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 8b39c160743d..e04937f44f33 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -977,6 +977,8 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, { int ret; u32 count; + int num_pkts; + int tx_num_deferred; unsigned long flags; struct vmxnet3_tx_ctx ctx; union Vmxnet3_GenericDesc *gdesc; @@ -1075,12 +1077,12 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, #else gdesc = ctx.sop_txd; #endif + tx_num_deferred = le32_to_cpu(tq->shared->txNumDeferred); if (ctx.mss) { gdesc->txd.hlen = ctx.eth_ip_hdr_size + ctx.l4_hdr_size; gdesc->txd.om = VMXNET3_OM_TSO; gdesc->txd.msscof = ctx.mss; - le32_add_cpu(&tq->shared->txNumDeferred, (skb->len - - gdesc->txd.hlen + ctx.mss - 1) / ctx.mss); + num_pkts = (skb->len - gdesc->txd.hlen + ctx.mss - 1) / ctx.mss; } else { if (skb->ip_summed == CHECKSUM_PARTIAL) { gdesc->txd.hlen = ctx.eth_ip_hdr_size; @@ -1091,8 +1093,10 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, gdesc->txd.om = 0; gdesc->txd.msscof = 0; } - le32_add_cpu(&tq->shared->txNumDeferred, 1); + num_pkts = 1; } + le32_add_cpu(&tq->shared->txNumDeferred, num_pkts); + tx_num_deferred += num_pkts; if (skb_vlan_tag_present(skb)) { gdesc->txd.ti = 1; @@ -1118,8 +1122,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, spin_unlock_irqrestore(&tq->tx_lock, flags); - if (le32_to_cpu(tq->shared->txNumDeferred) >= - le32_to_cpu(tq->shared->txThreshold)) { + if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) { tq->shared->txNumDeferred = 0; VMXNET3_WRITE_BAR0_REG(adapter, VMXNET3_REG_TXPROD + tq->qid * 8, @@ -1470,7 +1473,8 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, vmxnet3_rx_csum(adapter, skb, (union Vmxnet3_GenericDesc *)rcd); skb->protocol = eth_type_trans(skb, adapter->netdev); - if (!rcd->tcp || !adapter->lro) + if (!rcd->tcp || + !(adapter->netdev->features & NETIF_F_LRO)) goto not_lro; if (segCnt != 0 && mss != 0) { diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 5ba222920e80..59ec34052a65 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.11.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.13.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040b00 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040d00 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ @@ -342,9 +342,6 @@ struct vmxnet3_adapter { u8 __iomem *hw_addr1; /* for BAR 1 */ u8 version; - bool rxcsum; - bool lro; - #ifdef VMXNET3_RSS struct UPT1_RSSConf *rss_conf; bool rss; diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index afeca6bcdade..ab8b3cbbb205 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -574,7 +574,10 @@ static void ppp_timer(struct timer_list *t) ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, 0, NULL); proto->restart_counter--; - } else + } else if (netif_carrier_ok(proto->dev)) + ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, + 0, NULL); + else ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0, 0, NULL); break; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index e89e5ef2c2a4..f246e9ed4a81 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -729,6 +729,7 @@ static void ath9k_set_hw_capab(struct ath9k_htc_priv *priv, ieee80211_hw_set(hw, SPECTRUM_MGMT); ieee80211_hw_set(hw, SIGNAL_DBM); ieee80211_hw_set(hw, AMPDU_AGGREGATION); + ieee80211_hw_set(hw, DOESNT_SUPPORT_QOS_NDP); if (ath9k_ps_enable) ieee80211_hw_set(hw, SUPPORTS_PS); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h index df8a1ecb9924..232dcbb83311 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h @@ -181,6 +181,7 @@ enum brcmf_netif_stop_reason { * @netif_stop_lock: spinlock for update netif_stop from multiple sources. * @pend_8021x_cnt: tracks outstanding number of 802.1x frames. * @pend_8021x_wait: used for signalling change in count. + * @fwil_fwerr: flag indicating fwil layer should return firmware error codes. */ struct brcmf_if { struct brcmf_pub *drvr; @@ -198,6 +199,7 @@ struct brcmf_if { wait_queue_head_t pend_8021x_wait; struct in6_addr ipv6_addr_tbl[NDOL_MAX_ENTRIES]; u8 ipv6addr_idx; + bool fwil_fwerr; }; int brcmf_netdev_wait_pend8021x(struct brcmf_if *ifp); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c index 47de35a33853..bede7b7fd996 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c @@ -104,6 +104,9 @@ static void brcmf_feat_iovar_int_get(struct brcmf_if *ifp, u32 data; int err; + /* we need to know firmware error */ + ifp->fwil_fwerr = true; + err = brcmf_fil_iovar_int_get(ifp, name, &data); if (err == 0) { brcmf_dbg(INFO, "enabling feature: %s\n", brcmf_feat_names[id]); @@ -112,6 +115,8 @@ static void brcmf_feat_iovar_int_get(struct brcmf_if *ifp, brcmf_dbg(TRACE, "%s feature check failed: %d\n", brcmf_feat_names[id], err); } + + ifp->fwil_fwerr = false; } static void brcmf_feat_iovar_data_set(struct brcmf_if *ifp, @@ -120,6 +125,9 @@ static void brcmf_feat_iovar_data_set(struct brcmf_if *ifp, { int err; + /* we need to know firmware error */ + ifp->fwil_fwerr = true; + err = brcmf_fil_iovar_data_set(ifp, name, data, len); if (err != -BRCMF_FW_UNSUPPORTED) { brcmf_dbg(INFO, "enabling feature: %s\n", brcmf_feat_names[id]); @@ -128,6 +136,8 @@ static void brcmf_feat_iovar_data_set(struct brcmf_if *ifp, brcmf_dbg(TRACE, "%s feature check failed: %d\n", brcmf_feat_names[id], err); } + + ifp->fwil_fwerr = false; } #define MAX_CAPS_BUFFER_SIZE 512 diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c index f2cfdd3b2bf1..fc5751116d99 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.c @@ -131,6 +131,9 @@ brcmf_fil_cmd_data(struct brcmf_if *ifp, u32 cmd, void *data, u32 len, bool set) brcmf_fil_get_errstr((u32)(-fwerr)), fwerr); err = -EBADE; } + if (ifp->fwil_fwerr) + return fwerr; + return err; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 2ee54133efa1..82064e909784 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -462,25 +462,23 @@ static int brcmf_p2p_set_firmware(struct brcmf_if *ifp, u8 *p2p_mac) * @dev_addr: optional device address. * * P2P needs mac addresses for P2P device and interface. If no device - * address it specified, these are derived from the primary net device, ie. - * the permanent ethernet address of the device. + * address it specified, these are derived from a random ethernet + * address. */ static void brcmf_p2p_generate_bss_mac(struct brcmf_p2p_info *p2p, u8 *dev_addr) { - struct brcmf_if *pri_ifp = p2p->bss_idx[P2PAPI_BSSCFG_PRIMARY].vif->ifp; - bool local_admin = false; + bool random_addr = false; - if (!dev_addr || is_zero_ether_addr(dev_addr)) { - dev_addr = pri_ifp->mac_addr; - local_admin = true; - } + if (!dev_addr || is_zero_ether_addr(dev_addr)) + random_addr = true; - /* Generate the P2P Device Address. This consists of the device's - * primary MAC address with the locally administered bit set. + /* Generate the P2P Device Address obtaining a random ethernet + * address with the locally administered bit set. */ - memcpy(p2p->dev_addr, dev_addr, ETH_ALEN); - if (local_admin) - p2p->dev_addr[0] |= 0x02; + if (random_addr) + eth_random_addr(p2p->dev_addr); + else + memcpy(p2p->dev_addr, dev_addr, ETH_ALEN); /* Generate the P2P Interface Address. If the discovery and connection * BSSCFGs need to simultaneously co-exist, then this address must be diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index c5f2ddf9b0fe..e5a2fc738ac3 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -91,7 +91,6 @@ config IWLWIFI_BCAST_FILTERING config IWLWIFI_PCIE_RTPM bool "Enable runtime power management mode for PCIe devices" depends on IWLMVM && PM && EXPERT - default false help Say Y here to enable runtime power management for PCIe devices. If enabled, the device will go into low power mode diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h index 3721a3ed358b..f824bebceb06 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h @@ -211,7 +211,7 @@ enum { * @TE_V2_NOTIF_HOST_FRAG_END:request/receive notification on frag end * @TE_V2_NOTIF_INTERNAL_FRAG_START: internal FW use. * @TE_V2_NOTIF_INTERNAL_FRAG_END: internal FW use. - * @T2_V2_START_IMMEDIATELY: start time event immediately + * @TE_V2_START_IMMEDIATELY: start time event immediately * @TE_V2_DEP_OTHER: depends on another time event * @TE_V2_DEP_TSF: depends on a specific time * @TE_V2_EVENT_SOCIOPATHIC: can't co-exist with other events of tha same MAC @@ -230,7 +230,7 @@ enum iwl_time_event_policy { TE_V2_NOTIF_HOST_FRAG_END = BIT(5), TE_V2_NOTIF_INTERNAL_FRAG_START = BIT(6), TE_V2_NOTIF_INTERNAL_FRAG_END = BIT(7), - T2_V2_START_IMMEDIATELY = BIT(11), + TE_V2_START_IMMEDIATELY = BIT(11), /* placement characteristics */ TE_V2_DEP_OTHER = BIT(TE_V2_PLACEMENT_POS), diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 67aefc8fc9ac..7bd704a3e640 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -8,6 +8,7 @@ * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -33,6 +34,7 @@ * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -942,7 +944,6 @@ dump_trans_data: out: iwl_fw_free_dump_desc(fwrt); - fwrt->dump.trig = NULL; clear_bit(IWL_FWRT_STATUS_DUMPING, &fwrt->status); IWL_DEBUG_INFO(fwrt, "WRT dump done\n"); } @@ -1112,6 +1113,14 @@ void iwl_fw_error_dump_wk(struct work_struct *work) fwrt->ops->dump_start(fwrt->ops_ctx)) return; + if (fwrt->ops && fwrt->ops->fw_running && + !fwrt->ops->fw_running(fwrt->ops_ctx)) { + IWL_ERR(fwrt, "Firmware not running - cannot dump error\n"); + iwl_fw_free_dump_desc(fwrt); + clear_bit(IWL_FWRT_STATUS_DUMPING, &fwrt->status); + goto out; + } + if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) { /* stop recording */ iwl_fw_dbg_stop_recording(fwrt); @@ -1145,7 +1154,7 @@ void iwl_fw_error_dump_wk(struct work_struct *work) iwl_write_prph(fwrt->trans, DBGC_OUT_CTRL, out_ctrl); } } - +out: if (fwrt->ops && fwrt->ops->dump_end) fwrt->ops->dump_end(fwrt->ops_ctx); } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h index 223fb77a3aa9..72259bff9922 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h @@ -8,6 +8,7 @@ * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -33,6 +34,7 @@ * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -91,6 +93,7 @@ static inline void iwl_fw_free_dump_desc(struct iwl_fw_runtime *fwrt) if (fwrt->dump.desc != &iwl_dump_desc_assert) kfree(fwrt->dump.desc); fwrt->dump.desc = NULL; + fwrt->dump.trig = NULL; } void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.h b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.h index e57ff92a68ae..3da468d2cc92 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.h @@ -75,6 +75,20 @@ static inline void iwl_fw_cancel_timestamp(struct iwl_fw_runtime *fwrt) cancel_delayed_work_sync(&fwrt->timestamp.wk); } +static inline void iwl_fw_suspend_timestamp(struct iwl_fw_runtime *fwrt) +{ + cancel_delayed_work_sync(&fwrt->timestamp.wk); +} + +static inline void iwl_fw_resume_timestamp(struct iwl_fw_runtime *fwrt) +{ + if (!fwrt->timestamp.delay) + return; + + schedule_delayed_work(&fwrt->timestamp.wk, + round_jiffies_relative(fwrt->timestamp.delay)); +} + #else static inline int iwl_fwrt_dbgfs_register(struct iwl_fw_runtime *fwrt, struct dentry *dbgfs_dir) @@ -84,4 +98,8 @@ static inline int iwl_fwrt_dbgfs_register(struct iwl_fw_runtime *fwrt, static inline void iwl_fw_cancel_timestamp(struct iwl_fw_runtime *fwrt) {} +static inline void iwl_fw_suspend_timestamp(struct iwl_fw_runtime *fwrt) {} + +static inline void iwl_fw_resume_timestamp(struct iwl_fw_runtime *fwrt) {} + #endif /* CONFIG_IWLWIFI_DEBUGFS */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c index c39fe84bb4c4..2efac307909e 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/init.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c @@ -77,8 +77,14 @@ void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans, } IWL_EXPORT_SYMBOL(iwl_fw_runtime_init); -void iwl_fw_runtime_exit(struct iwl_fw_runtime *fwrt) +void iwl_fw_runtime_suspend(struct iwl_fw_runtime *fwrt) { - iwl_fw_cancel_timestamp(fwrt); + iwl_fw_suspend_timestamp(fwrt); } -IWL_EXPORT_SYMBOL(iwl_fw_runtime_exit); +IWL_EXPORT_SYMBOL(iwl_fw_runtime_suspend); + +void iwl_fw_runtime_resume(struct iwl_fw_runtime *fwrt) +{ + iwl_fw_resume_timestamp(fwrt); +} +IWL_EXPORT_SYMBOL(iwl_fw_runtime_resume); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h index e25c049f980f..3fb940ebd74a 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h @@ -6,6 +6,7 @@ * GPL LICENSE SUMMARY * * Copyright(c) 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -26,6 +27,7 @@ * BSD LICENSE * * Copyright(c) 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -68,6 +70,7 @@ struct iwl_fw_runtime_ops { int (*dump_start)(void *ctx); void (*dump_end)(void *ctx); + bool (*fw_running)(void *ctx); }; #define MAX_NUM_LMAC 2 @@ -150,6 +153,10 @@ void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans, void iwl_fw_runtime_exit(struct iwl_fw_runtime *fwrt); +void iwl_fw_runtime_suspend(struct iwl_fw_runtime *fwrt); + +void iwl_fw_runtime_resume(struct iwl_fw_runtime *fwrt); + static inline void iwl_fw_set_current_image(struct iwl_fw_runtime *fwrt, enum iwl_ucode_type cur_fw_img) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 0e6cf39285f4..2efe9b099556 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1098,6 +1098,8 @@ int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) /* make sure the d0i3 exit work is not pending */ flush_work(&mvm->d0i3_exit_work); + iwl_fw_runtime_suspend(&mvm->fwrt); + ret = iwl_trans_suspend(trans); if (ret) return ret; @@ -2012,6 +2014,8 @@ int iwl_mvm_resume(struct ieee80211_hw *hw) mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED; + iwl_fw_runtime_resume(&mvm->fwrt); + return ret; } @@ -2038,6 +2042,8 @@ static int iwl_mvm_d3_test_open(struct inode *inode, struct file *file) mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_D3; + iwl_fw_runtime_suspend(&mvm->fwrt); + /* start pseudo D3 */ rtnl_lock(); err = __iwl_mvm_suspend(mvm->hw, mvm->hw->wiphy->wowlan_config, true); @@ -2098,6 +2104,8 @@ static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file) __iwl_mvm_resume(mvm, true); rtnl_unlock(); + iwl_fw_runtime_resume(&mvm->fwrt); + mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED; iwl_abort_notification_waits(&mvm->notif_wait); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index a7892c1254a2..9c436d8d001d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -35,6 +36,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -1281,9 +1283,6 @@ static ssize_t iwl_dbgfs_fw_dbg_collect_write(struct iwl_mvm *mvm, { int ret; - if (!iwl_mvm_firmware_running(mvm)) - return -EIO; - ret = iwl_mvm_ref_sync(mvm, IWL_MVM_REF_PRPH_WRITE); if (ret) return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 2f22e14e00fe..8ba16fc24e3a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -438,7 +438,8 @@ int iwl_mvm_mac_ctxt_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif) } /* Allocate the CAB queue for softAP and GO interfaces */ - if (vif->type == NL80211_IFTYPE_AP) { + if (vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_ADHOC) { /* * For TVQM this will be overwritten later with the FW assigned * queue value (when queue is enabled). diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 8aed40a8bc38..ebf511150f4d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -2106,15 +2107,40 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw, if (ret) goto out_remove; - ret = iwl_mvm_add_mcast_sta(mvm, vif); - if (ret) - goto out_unbind; - - /* Send the bcast station. At this stage the TBTT and DTIM time events - * are added and applied to the scheduler */ - ret = iwl_mvm_send_add_bcast_sta(mvm, vif); - if (ret) - goto out_rm_mcast; + /* + * This is not very nice, but the simplest: + * For older FWs adding the mcast sta before the bcast station may + * cause assert 0x2b00. + * This is fixed in later FW so make the order of removal depend on + * the TLV + */ + if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE)) { + ret = iwl_mvm_add_mcast_sta(mvm, vif); + if (ret) + goto out_unbind; + /* + * Send the bcast station. At this stage the TBTT and DTIM time + * events are added and applied to the scheduler + */ + ret = iwl_mvm_send_add_bcast_sta(mvm, vif); + if (ret) { + iwl_mvm_rm_mcast_sta(mvm, vif); + goto out_unbind; + } + } else { + /* + * Send the bcast station. At this stage the TBTT and DTIM time + * events are added and applied to the scheduler + */ + iwl_mvm_send_add_bcast_sta(mvm, vif); + if (ret) + goto out_unbind; + iwl_mvm_add_mcast_sta(mvm, vif); + if (ret) { + iwl_mvm_send_rm_bcast_sta(mvm, vif); + goto out_unbind; + } + } /* must be set before quota calculations */ mvmvif->ap_ibss_active = true; @@ -2144,7 +2170,6 @@ out_quota_failed: iwl_mvm_power_update_mac(mvm); mvmvif->ap_ibss_active = false; iwl_mvm_send_rm_bcast_sta(mvm, vif); -out_rm_mcast: iwl_mvm_rm_mcast_sta(mvm, vif); out_unbind: iwl_mvm_binding_remove_vif(mvm, vif); @@ -2682,6 +2707,10 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, /* enable beacon filtering */ WARN_ON(iwl_mvm_enable_beacon_filter(mvm, vif, 0)); + + iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band, + false); + ret = 0; } else if (old_state == IEEE80211_STA_AUTHORIZED && new_state == IEEE80211_STA_ASSOC) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 2d28e0804218..89ff02d7c876 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -90,6 +90,7 @@ #include "fw/runtime.h" #include "fw/dbg.h" #include "fw/acpi.h" +#include "fw/debugfs.h" #define IWL_MVM_MAX_ADDRESSES 5 /* RSSI offset for WkP */ @@ -1783,6 +1784,7 @@ static inline u32 iwl_mvm_flushable_queues(struct iwl_mvm *mvm) static inline void iwl_mvm_stop_device(struct iwl_mvm *mvm) { + iwl_fw_cancel_timestamp(&mvm->fwrt); iwl_free_fw_paging(&mvm->fwrt); clear_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status); iwl_fw_dump_conf_clear(&mvm->fwrt); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 5d525a0023dc..ab7fb5aad984 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -35,6 +36,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -552,9 +554,15 @@ static void iwl_mvm_fwrt_dump_end(void *ctx) iwl_mvm_unref(mvm, IWL_MVM_REF_FW_DBG_COLLECT); } +static bool iwl_mvm_fwrt_fw_running(void *ctx) +{ + return iwl_mvm_firmware_running(ctx); +} + static const struct iwl_fw_runtime_ops iwl_mvm_fwrt_ops = { .dump_start = iwl_mvm_fwrt_dump_start, .dump_end = iwl_mvm_fwrt_dump_end, + .fw_running = iwl_mvm_fwrt_fw_running, }; static struct iwl_op_mode * @@ -802,7 +810,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_mvm_leds_exit(mvm); iwl_mvm_thermal_exit(mvm); out_free: - iwl_fw_runtime_exit(&mvm->fwrt); iwl_fw_flush_dump(&mvm->fwrt); if (iwlmvm_mod_params.init_dbg) @@ -843,7 +850,6 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_IWLWIFI_DEBUGFS) kfree(mvm->d3_resume_sram); #endif - iwl_fw_runtime_exit(&mvm->fwrt); iwl_trans_op_mode_leave(mvm->trans); iwl_phy_db_free(mvm->phy_db); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 60abb0084ee5..47f4c7a1d80d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2684,7 +2684,8 @@ static void rs_get_initial_rate(struct iwl_mvm *mvm, struct ieee80211_sta *sta, struct iwl_lq_sta *lq_sta, enum nl80211_band band, - struct rs_rate *rate) + struct rs_rate *rate, + bool init) { int i, nentries; unsigned long active_rate; @@ -2738,14 +2739,25 @@ static void rs_get_initial_rate(struct iwl_mvm *mvm, */ if (sta->vht_cap.vht_supported && best_rssi > IWL_RS_LOW_RSSI_THRESHOLD) { - switch (sta->bandwidth) { - case IEEE80211_STA_RX_BW_160: - case IEEE80211_STA_RX_BW_80: - case IEEE80211_STA_RX_BW_40: + /* + * In AP mode, when a new station associates, rs is initialized + * immediately upon association completion, before the phy + * context is updated with the association parameters, so the + * sta bandwidth might be wider than the phy context allows. + * To avoid this issue, always initialize rs with 20mhz + * bandwidth rate, and after authorization, when the phy context + * is already up-to-date, re-init rs with the correct bw. + */ + u32 bw = init ? RATE_MCS_CHAN_WIDTH_20 : rs_bw_from_sta_bw(sta); + + switch (bw) { + case RATE_MCS_CHAN_WIDTH_40: + case RATE_MCS_CHAN_WIDTH_80: + case RATE_MCS_CHAN_WIDTH_160: initial_rates = rs_optimal_rates_vht; nentries = ARRAY_SIZE(rs_optimal_rates_vht); break; - case IEEE80211_STA_RX_BW_20: + case RATE_MCS_CHAN_WIDTH_20: initial_rates = rs_optimal_rates_vht_20mhz; nentries = ARRAY_SIZE(rs_optimal_rates_vht_20mhz); break; @@ -2756,7 +2768,7 @@ static void rs_get_initial_rate(struct iwl_mvm *mvm, active_rate = lq_sta->active_siso_rate; rate->type = LQ_VHT_SISO; - rate->bw = rs_bw_from_sta_bw(sta); + rate->bw = bw; } else if (sta->ht_cap.ht_supported && best_rssi > IWL_RS_LOW_RSSI_THRESHOLD) { initial_rates = rs_optimal_rates_ht; @@ -2839,7 +2851,7 @@ static void rs_initialize_lq(struct iwl_mvm *mvm, tbl = &(lq_sta->lq_info[active_tbl]); rate = &tbl->rate; - rs_get_initial_rate(mvm, sta, lq_sta, band, rate); + rs_get_initial_rate(mvm, sta, lq_sta, band, rate, init); rs_init_optimal_rate(mvm, sta, lq_sta); WARN_ONCE(rate->ant != ANT_A && rate->ant != ANT_B, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index a3f7c1bf3cc8..580de5851fc7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -71,6 +71,7 @@ static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_rx_status *stats = IEEE80211_SKB_RXCB(skb); struct iwl_mvm_key_pn *ptk_pn; + int res; u8 tid, keyidx; u8 pn[IEEE80211_CCMP_PN_LEN]; u8 *extiv; @@ -127,12 +128,13 @@ static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb, pn[4] = extiv[1]; pn[5] = extiv[0]; - if (memcmp(pn, ptk_pn->q[queue].pn[tid], - IEEE80211_CCMP_PN_LEN) <= 0) + res = memcmp(pn, ptk_pn->q[queue].pn[tid], IEEE80211_CCMP_PN_LEN); + if (res < 0) + return -1; + if (!res && !(stats->flag & RX_FLAG_ALLOW_SAME_PN)) return -1; - if (!(stats->flag & RX_FLAG_AMSDU_MORE)) - memcpy(ptk_pn->q[queue].pn[tid], pn, IEEE80211_CCMP_PN_LEN); + memcpy(ptk_pn->q[queue].pn[tid], pn, IEEE80211_CCMP_PN_LEN); stats->flag |= RX_FLAG_PN_VALIDATED; return 0; @@ -314,28 +316,21 @@ static void iwl_mvm_rx_csum(struct ieee80211_sta *sta, } /* - * returns true if a packet outside BA session is a duplicate and - * should be dropped + * returns true if a packet is a duplicate and should be dropped. + * Updates AMSDU PN tracking info */ -static bool iwl_mvm_is_nonagg_dup(struct ieee80211_sta *sta, int queue, - struct ieee80211_rx_status *rx_status, - struct ieee80211_hdr *hdr, - struct iwl_rx_mpdu_desc *desc) +static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue, + struct ieee80211_rx_status *rx_status, + struct ieee80211_hdr *hdr, + struct iwl_rx_mpdu_desc *desc) { struct iwl_mvm_sta *mvm_sta; struct iwl_mvm_rxq_dup_data *dup_data; - u8 baid, tid, sub_frame_idx; + u8 tid, sub_frame_idx; if (WARN_ON(IS_ERR_OR_NULL(sta))) return false; - baid = (le32_to_cpu(desc->reorder_data) & - IWL_RX_MPDU_REORDER_BAID_MASK) >> - IWL_RX_MPDU_REORDER_BAID_SHIFT; - - if (baid != IWL_RX_REORDER_DATA_INVALID_BAID) - return false; - mvm_sta = iwl_mvm_sta_from_mac80211(sta); dup_data = &mvm_sta->dup_data[queue]; @@ -365,6 +360,12 @@ static bool iwl_mvm_is_nonagg_dup(struct ieee80211_sta *sta, int queue, dup_data->last_sub_frame[tid] >= sub_frame_idx)) return true; + /* Allow same PN as the first subframe for following sub frames */ + if (dup_data->last_seq[tid] == hdr->seq_ctrl && + sub_frame_idx > dup_data->last_sub_frame[tid] && + desc->mac_flags2 & IWL_RX_MPDU_MFLG2_AMSDU) + rx_status->flag |= RX_FLAG_ALLOW_SAME_PN; + dup_data->last_seq[tid] = hdr->seq_ctrl; dup_data->last_sub_frame[tid] = sub_frame_idx; @@ -971,7 +972,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, if (ieee80211_is_data(hdr->frame_control)) iwl_mvm_rx_csum(sta, skb, desc); - if (iwl_mvm_is_nonagg_dup(sta, queue, rx_status, hdr, desc)) { + if (iwl_mvm_is_dup(sta, queue, rx_status, hdr, desc)) { kfree_skb(skb); goto out; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 6b2674e02606..630e23cb0ffb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2039,7 +2039,7 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) struct iwl_trans_txq_scd_cfg cfg = { .fifo = IWL_MVM_TX_FIFO_MCAST, .sta_id = msta->sta_id, - .tid = IWL_MAX_TID_COUNT, + .tid = 0, .aggregate = false, .frame_limit = IWL_FRAME_LIMIT, }; @@ -2053,6 +2053,17 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) return -ENOTSUPP; /* + * In IBSS, ieee80211_check_queues() sets the cab_queue to be + * invalid, so make sure we use the queue we want. + * Note that this is done here as we want to avoid making DQA + * changes in mac80211 layer. + */ + if (vif->type == NL80211_IFTYPE_ADHOC) { + vif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE; + mvmvif->cab_queue = vif->cab_queue; + } + + /* * While in previous FWs we had to exclude cab queue from TFD queue * mask, now it is needed as any other queue. */ @@ -2079,24 +2090,13 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) if (iwl_mvm_has_new_tx_api(mvm)) { int queue = iwl_mvm_tvqm_enable_txq(mvm, vif->cab_queue, msta->sta_id, - IWL_MAX_TID_COUNT, + 0, timeout); mvmvif->cab_queue = queue; } else if (!fw_has_api(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_API_STA_TYPE)) { - /* - * In IBSS, ieee80211_check_queues() sets the cab_queue to be - * invalid, so make sure we use the queue we want. - * Note that this is done here as we want to avoid making DQA - * changes in mac80211 layer. - */ - if (vif->type == NL80211_IFTYPE_ADHOC) { - vif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE; - mvmvif->cab_queue = vif->cab_queue; - } + IWL_UCODE_TLV_API_STA_TYPE)) iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue, 0, &cfg, timeout); - } return 0; } @@ -2115,7 +2115,7 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) iwl_mvm_flush_sta(mvm, &mvmvif->mcast_sta, true, 0); iwl_mvm_disable_txq(mvm, mvmvif->cab_queue, vif->cab_queue, - IWL_MAX_TID_COUNT, 0); + 0, 0); ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id); if (ret) @@ -3170,8 +3170,9 @@ static int __iwl_mvm_remove_sta_key(struct iwl_mvm *mvm, u8 sta_id, int ret, size; u32 status; + /* This is a valid situation for GTK removal */ if (sta_id == IWL_MVM_INVALID_STA) - return -EINVAL; + return 0; key_flags = cpu_to_le16((keyconf->keyidx << STA_KEY_FLG_KEYID_POS) & STA_KEY_FLG_KEYID_MSK); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 200ab50ec86b..acb217e666db 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -616,7 +616,7 @@ void iwl_mvm_protect_session(struct iwl_mvm *mvm, time_cmd.repeat = 1; time_cmd.policy = cpu_to_le16(TE_V2_NOTIF_HOST_EVENT_START | TE_V2_NOTIF_HOST_EVENT_END | - T2_V2_START_IMMEDIATELY); + TE_V2_START_IMMEDIATELY); if (!wait_for_notif) { iwl_mvm_time_event_send_add(mvm, vif, te_data, &time_cmd); @@ -803,7 +803,7 @@ int iwl_mvm_start_p2p_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif, time_cmd.repeat = 1; time_cmd.policy = cpu_to_le16(TE_V2_NOTIF_HOST_EVENT_START | TE_V2_NOTIF_HOST_EVENT_END | - T2_V2_START_IMMEDIATELY); + TE_V2_START_IMMEDIATELY); return iwl_mvm_time_event_send_add(mvm, vif, te_data, &time_cmd); } @@ -913,6 +913,8 @@ int iwl_mvm_schedule_csa_period(struct iwl_mvm *mvm, time_cmd.interval = cpu_to_le32(1); time_cmd.policy = cpu_to_le16(TE_V2_NOTIF_HOST_EVENT_START | TE_V2_ABSENCE); + if (!apply_time) + time_cmd.policy |= cpu_to_le16(TE_V2_START_IMMEDIATELY); return iwl_mvm_time_event_send_add(mvm, vif, te_data, &time_cmd); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index dda77b327c98..af6dfceab6b8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -419,11 +419,11 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm, { struct ieee80211_key_conf *keyconf = info->control.hw_key; u8 *crypto_hdr = skb_frag->data + hdrlen; + enum iwl_tx_cmd_sec_ctrl type = TX_CMD_SEC_CCM; u64 pn; switch (keyconf->cipher) { case WLAN_CIPHER_SUITE_CCMP: - case WLAN_CIPHER_SUITE_CCMP_256: iwl_mvm_set_tx_cmd_ccmp(info, tx_cmd); iwl_mvm_set_tx_cmd_pn(info, crypto_hdr); break; @@ -447,13 +447,16 @@ static void iwl_mvm_set_tx_cmd_crypto(struct iwl_mvm *mvm, break; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: + type = TX_CMD_SEC_GCMP; + /* Fall through */ + case WLAN_CIPHER_SUITE_CCMP_256: /* TODO: Taking the key from the table might introduce a race * when PTK rekeying is done, having an old packets with a PN * based on the old key but the message encrypted with a new * one. * Need to handle this. */ - tx_cmd->sec_ctl |= TX_CMD_SEC_GCMP | TX_CMD_SEC_KEY_FROM_TABLE; + tx_cmd->sec_ctl |= type | TX_CMD_SEC_KEY_FROM_TABLE; tx_cmd->key[0] = keyconf->hw_key_idx; iwl_mvm_set_tx_cmd_pn(info, crypto_hdr); break; @@ -645,7 +648,11 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE || info.control.vif->type == NL80211_IFTYPE_AP || info.control.vif->type == NL80211_IFTYPE_ADHOC) { - sta_id = mvmvif->bcast_sta.sta_id; + if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE) + sta_id = mvmvif->bcast_sta.sta_id; + else + sta_id = mvmvif->mcast_sta.sta_id; + queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info, hdr->frame_control); if (queue < 0) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 6d0a907d5ba5..fabae0f60683 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -147,7 +147,7 @@ static void iwl_pcie_gen2_tfd_unmap(struct iwl_trans *trans, /* Sanity check on number of chunks */ num_tbs = iwl_pcie_gen2_get_num_tbs(trans, tfd); - if (num_tbs >= trans_pcie->max_tbs) { + if (num_tbs > trans_pcie->max_tbs) { IWL_ERR(trans, "Too many chunks: %i\n", num_tbs); return; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 3f85713c41dc..1a566287993d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -378,7 +378,7 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans, /* Sanity check on number of chunks */ num_tbs = iwl_pcie_tfd_get_num_tbs(trans, tfd); - if (num_tbs >= trans_pcie->max_tbs) { + if (num_tbs > trans_pcie->max_tbs) { IWL_ERR(trans, "Too many chunks: %i\n", num_tbs); /* @todo issue fatal error, it is quite serious situation */ return; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6e0af815f25e..35b21f8152bb 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2727,6 +2727,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, mutex_init(&data->mutex); data->netgroup = hwsim_net_get_netgroup(net); + data->wmediumd = hwsim_net_get_wmediumd(net); /* Enable frame retransmissions for lossy channels */ hw->max_rates = 4; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c index f9ccd13c79f9..e7bbbc95cdb1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/hw.c @@ -1125,7 +1125,8 @@ static void _rtl8723be_enable_aspm_back_door(struct ieee80211_hw *hw) /* Configuration Space offset 0x70f BIT7 is used to control L0S */ tmp8 = _rtl8723be_dbi_read(rtlpriv, 0x70f); - _rtl8723be_dbi_write(rtlpriv, 0x70f, tmp8 | BIT(7)); + _rtl8723be_dbi_write(rtlpriv, 0x70f, tmp8 | BIT(7) | + ASPM_L1_LATENCY << 3); /* Configuration Space offset 0x719 Bit3 is for L1 * BIT4 is for clock request diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 8328d395e332..3127bc8633ca 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2005,7 +2005,10 @@ static void netback_changed(struct xenbus_device *dev, case XenbusStateInitialised: case XenbusStateReconfiguring: case XenbusStateReconfigured: + break; + case XenbusStateUnknown: + wake_up_all(&module_unload_q); break; case XenbusStateInitWait: @@ -2136,7 +2139,9 @@ static int xennet_remove(struct xenbus_device *dev) xenbus_switch_state(dev, XenbusStateClosing); wait_event(module_unload_q, xenbus_read_driver_state(dev->otherend) == - XenbusStateClosing); + XenbusStateClosing || + xenbus_read_driver_state(dev->otherend) == + XenbusStateUnknown); xenbus_switch_state(dev, XenbusStateClosed); wait_event(module_unload_q, diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 345acca576b3..1bd7b3734751 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -278,8 +278,6 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) disk->queue = q; disk->flags = GENHD_FL_EXT_DEVT; nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name); - set_capacity(disk, 0); - device_add_disk(dev, disk); if (devm_add_action_or_reset(dev, nd_blk_release_disk, disk)) return -ENOMEM; @@ -292,6 +290,7 @@ static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) } set_capacity(disk, available_disk_size >> SECTOR_SHIFT); + device_add_disk(dev, disk); revalidate_disk(disk); return 0; } diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 2ef544f10ec8..4b95ac513de2 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1545,8 +1545,6 @@ static int btt_blk_init(struct btt *btt) queue_flag_set_unlocked(QUEUE_FLAG_NONROT, btt->btt_queue); btt->btt_queue->queuedata = btt; - set_capacity(btt->btt_disk, 0); - device_add_disk(&btt->nd_btt->dev, btt->btt_disk); if (btt_meta_size(btt)) { int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt)); @@ -1558,6 +1556,7 @@ static int btt_blk_init(struct btt *btt) } } set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9); + device_add_disk(&btt->nd_btt->dev, btt->btt_disk); btt->nd_btt->size = btt->nlba * (u64)btt->sector_size; revalidate_disk(btt->btt_disk); diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index f5c4e8c6e29d..2f4d18752c97 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -304,7 +304,7 @@ static const struct attribute_group *nd_pfn_attribute_groups[] = { struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn, struct nd_namespace_common *ndns) { - struct device *dev = &nd_pfn->dev; + struct device *dev; if (!nd_pfn) return NULL; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 10041ac4032c..06f8dcc52ca6 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -335,8 +335,7 @@ static int pmem_attach_disk(struct device *dev, dev_warn(dev, "unable to guarantee persistence of writes\n"); fua = 0; } - wbc = nvdimm_has_cache(nd_region) && - !test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags); + wbc = nvdimm_has_cache(nd_region); if (!devm_request_mem_region(dev, res->start, resource_size(res), dev_name(&ndns->dev))) { diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index e6d01911e092..1593e1806b16 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -532,11 +532,13 @@ static ssize_t persistence_domain_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nd_region *nd_region = to_nd_region(dev); - unsigned long flags = nd_region->flags; - return sprintf(buf, "%s%s\n", - flags & BIT(ND_REGION_PERSIST_CACHE) ? "cpu_cache " : "", - flags & BIT(ND_REGION_PERSIST_MEMCTRL) ? "memory_controller " : ""); + if (test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags)) + return sprintf(buf, "cpu_cache\n"); + else if (test_bit(ND_REGION_PERSIST_MEMCTRL, &nd_region->flags)) + return sprintf(buf, "memory_controller\n"); + else + return sprintf(buf, "\n"); } static DEVICE_ATTR_RO(persistence_domain); @@ -593,6 +595,13 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) return 0; } + if (a == &dev_attr_persistence_domain.attr) { + if ((nd_region->flags & (BIT(ND_REGION_PERSIST_CACHE) + | BIT(ND_REGION_PERSIST_MEMCTRL))) == 0) + return 0; + return a->mode; + } + if (a != &dev_attr_set_cookie.attr && a != &dev_attr_available_size.attr) return a->mode; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0fe7ea35c221..7aeca5db7916 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2844,7 +2844,7 @@ out: } static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, - struct nvme_id_ns *id, bool *new) + struct nvme_id_ns *id) { struct nvme_ctrl *ctrl = ns->ctrl; bool is_shared = id->nmic & (1 << 0); @@ -2860,8 +2860,6 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, ret = PTR_ERR(head); goto out_unlock; } - - *new = true; } else { struct nvme_ns_ids ids; @@ -2873,8 +2871,6 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid, ret = -EINVAL; goto out_unlock; } - - *new = false; } list_add_tail(&ns->siblings, &head->list); @@ -2945,7 +2941,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) struct nvme_id_ns *id; char disk_name[DISK_NAME_LEN]; int node = dev_to_node(ctrl->dev), flags = GENHD_FL_EXT_DEVT; - bool new = true; ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) @@ -2971,7 +2966,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (id->ncap == 0) goto out_free_id; - if (nvme_init_ns_head(ns, nsid, id, &new)) + if (nvme_init_ns_head(ns, nsid, id)) goto out_free_id; nvme_setup_streams_ns(ctrl, ns); @@ -3037,9 +3032,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) pr_warn("%s: failed to register lightnvm sysfs group for identification\n", ns->disk->disk_name); - if (new) - nvme_mpath_add_disk(ns->head); - nvme_mpath_add_disk_links(ns); + nvme_mpath_add_disk(ns->head); return; out_unlink_ns: mutex_lock(&ctrl->subsys->lock); @@ -3059,7 +3052,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) return; if (ns->disk && ns->disk->flags & GENHD_FL_UP) { - nvme_mpath_remove_disk_links(ns); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_id_attr_group); if (ns->ndev) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 5dd4ceefed8f..8f0f34d06d46 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -493,7 +493,7 @@ EXPORT_SYMBOL_GPL(nvmf_should_reconnect); */ int nvmf_register_transport(struct nvmf_transport_ops *ops) { - if (!ops->create_ctrl || !ops->module) + if (!ops->create_ctrl) return -EINVAL; down_write(&nvmf_transports_rwsem); @@ -650,6 +650,11 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, ret = -EINVAL; goto out; } + if (opts->discovery_nqn) { + pr_debug("Ignoring nr_io_queues value for discovery controller\n"); + break; + } + opts->nr_io_queues = min_t(unsigned int, num_online_cpus(), token); break; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 7f51f8414b97..1dc1387b7134 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1206,7 +1206,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl, sizeof(struct fcnvme_lsdesc_cr_assoc_cmd)); assoc_rqst->assoc_cmd.ersp_ratio = cpu_to_be16(ersp_ratio); - assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize); + assoc_rqst->assoc_cmd.sqsize = cpu_to_be16(qsize - 1); /* Linux supports only Dynamic controllers */ assoc_rqst->assoc_cmd.cntlid = cpu_to_be16(0xffff); uuid_copy(&assoc_rqst->assoc_cmd.hostid, &ctrl->ctrl.opts->host->id); @@ -1321,7 +1321,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, sizeof(struct fcnvme_lsdesc_cr_conn_cmd)); conn_rqst->connect_cmd.ersp_ratio = cpu_to_be16(ersp_ratio); conn_rqst->connect_cmd.qid = cpu_to_be16(queue->qnum); - conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize); + conn_rqst->connect_cmd.sqsize = cpu_to_be16(qsize - 1); lsop->queue = queue; lsreq->rqstaddr = conn_rqst; @@ -2481,11 +2481,11 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) goto out_free_tag_set; } - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_cleanup_blk_queue; - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_delete_hw_queues; @@ -2532,11 +2532,11 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl) if (ret) goto out_free_io_queues; - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_free_io_queues; - ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size); + ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) goto out_delete_hw_queues; @@ -2632,13 +2632,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) nvme_fc_init_queue(ctrl, 0); ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0, - NVME_AQ_BLK_MQ_DEPTH); + NVME_AQ_DEPTH); if (ret) goto out_free_queue; ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0], - NVME_AQ_BLK_MQ_DEPTH, - (NVME_AQ_BLK_MQ_DEPTH / 4)); + NVME_AQ_DEPTH, (NVME_AQ_DEPTH / 4)); if (ret) goto out_delete_hw_queue; @@ -2666,7 +2665,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) } ctrl->ctrl.sqsize = - min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap) + 1, ctrl->ctrl.sqsize); + min_t(int, NVME_CAP_MQES(ctrl->ctrl.cap), ctrl->ctrl.sqsize); ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap); if (ret) @@ -2699,6 +2698,14 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) opts->queue_size = ctrl->ctrl.maxcmd; } + if (opts->queue_size > ctrl->ctrl.sqsize + 1) { + /* warn if sqsize is lower than queue_size */ + dev_warn(ctrl->ctrl.device, + "queue_size %zu > ctrl sqsize %u, clamping down\n", + opts->queue_size, ctrl->ctrl.sqsize + 1); + opts->queue_size = ctrl->ctrl.sqsize + 1; + } + ret = nvme_fc_init_aen_ops(ctrl); if (ret) goto out_term_aen_ops; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 3b211d9e58b8..060f69e03427 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -198,30 +198,16 @@ void nvme_mpath_add_disk(struct nvme_ns_head *head) { if (!head->disk) return; - device_add_disk(&head->subsys->dev, head->disk); - if (sysfs_create_group(&disk_to_dev(head->disk)->kobj, - &nvme_ns_id_attr_group)) - pr_warn("%s: failed to create sysfs group for identification\n", - head->disk->disk_name); -} - -void nvme_mpath_add_disk_links(struct nvme_ns *ns) -{ - struct kobject *slave_disk_kobj, *holder_disk_kobj; - - if (!ns->head->disk) - return; - - slave_disk_kobj = &disk_to_dev(ns->disk)->kobj; - if (sysfs_create_link(ns->head->disk->slave_dir, slave_disk_kobj, - kobject_name(slave_disk_kobj))) - return; - holder_disk_kobj = &disk_to_dev(ns->head->disk)->kobj; - if (sysfs_create_link(ns->disk->part0.holder_dir, holder_disk_kobj, - kobject_name(holder_disk_kobj))) - sysfs_remove_link(ns->head->disk->slave_dir, - kobject_name(slave_disk_kobj)); + mutex_lock(&head->subsys->lock); + if (!(head->disk->flags & GENHD_FL_UP)) { + device_add_disk(&head->subsys->dev, head->disk); + if (sysfs_create_group(&disk_to_dev(head->disk)->kobj, + &nvme_ns_id_attr_group)) + pr_warn("%s: failed to create sysfs group for identification\n", + head->disk->disk_name); + } + mutex_unlock(&head->subsys->lock); } void nvme_mpath_remove_disk(struct nvme_ns_head *head) @@ -238,14 +224,3 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) blk_cleanup_queue(head->disk->queue); put_disk(head->disk); } - -void nvme_mpath_remove_disk_links(struct nvme_ns *ns) -{ - if (!ns->head->disk) - return; - - sysfs_remove_link(ns->disk->part0.holder_dir, - kobject_name(&disk_to_dev(ns->head->disk)->kobj)); - sysfs_remove_link(ns->head->disk->slave_dir, - kobject_name(&disk_to_dev(ns->disk)->kobj)); -} diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 0521e4707d1c..d733b14ede9d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,9 +410,7 @@ bool nvme_req_needs_failover(struct request *req, blk_status_t error); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns_head *head); -void nvme_mpath_add_disk_links(struct nvme_ns *ns); void nvme_mpath_remove_disk(struct nvme_ns_head *head); -void nvme_mpath_remove_disk_links(struct nvme_ns *ns); static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) { @@ -454,12 +452,6 @@ static inline void nvme_mpath_add_disk(struct nvme_ns_head *head) static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head) { } -static inline void nvme_mpath_add_disk_links(struct nvme_ns *ns) -{ -} -static inline void nvme_mpath_remove_disk_links(struct nvme_ns *ns) -{ -} static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns) { } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 73036d2fbbd5..b6f43b738f03 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1153,12 +1153,6 @@ static bool nvme_should_reset(struct nvme_dev *dev, u32 csts) if (!(csts & NVME_CSTS_CFS) && !nssro) return false; - /* If PCI error recovery process is happening, we cannot reset or - * the recovery mechanism will surely fail. - */ - if (pci_channel_offline(to_pci_dev(dev->dev))) - return false; - return true; } @@ -1189,6 +1183,13 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) struct nvme_command cmd; u32 csts = readl(dev->bar + NVME_REG_CSTS); + /* If PCI error recovery process is happening, we cannot reset or + * the recovery mechanism will surely fail. + */ + mb(); + if (pci_channel_offline(to_pci_dev(dev->dev))) + return BLK_EH_RESET_TIMER; + /* * Reset immediately if the controller is failed */ @@ -1459,7 +1460,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) nvmeq->cq_vector = qid - 1; result = adapter_alloc_cq(dev, qid, nvmeq); if (result < 0) - return result; + goto release_vector; result = adapter_alloc_sq(dev, qid, nvmeq); if (result < 0) @@ -1473,9 +1474,12 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) return result; release_sq: + dev->online_queues--; adapter_delete_sq(dev, qid); release_cq: adapter_delete_cq(dev, qid); + release_vector: + nvmeq->cq_vector = -1; return result; } @@ -1910,7 +1914,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) int result, nr_io_queues; unsigned long size; - nr_io_queues = num_present_cpus(); + nr_io_queues = num_possible_cpus(); result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues); if (result < 0) return result; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3a51ed50eff2..4d84a73ee12d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1051,7 +1051,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, struct nvme_rdma_device *dev = queue->device; struct ib_device *ibdev = dev->dev; - if (!blk_rq_bytes(rq)) + if (!blk_rq_payload_bytes(rq)) return; if (req->mr) { @@ -1166,7 +1166,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, c->common.flags |= NVME_CMD_SGL_METABUF; - if (!blk_rq_bytes(rq)) + if (!blk_rq_payload_bytes(rq)) return nvme_rdma_set_sg_null(c); req->sg_table.sgl = req->first_sgl; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 0bd737117a80..a78029e4e5f4 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -520,9 +520,12 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, goto fail; } - /* either variant of SGLs is fine, as we don't support metadata */ - if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF && - (flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METASEG)) { + /* + * For fabrics, PSDT field shall describe metadata pointer (MPTR) that + * contains an address of a single contiguous physical buffer that is + * byte aligned. + */ + if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) { status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; goto fail; } diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 7991ec3a17db..861d1509b22b 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -184,7 +184,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } - if (blk_rq_bytes(req)) { + if (blk_rq_payload_bytes(req)) { iod->sg_table.sgl = iod->first_sgl; if (sg_alloc_table_chained(&iod->sg_table, blk_rq_nr_phys_segments(req), @@ -193,7 +193,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, iod->req.sg = iod->sg_table.sgl; iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl); - iod->req.transfer_len = blk_rq_bytes(req); + iod->req.transfer_len = blk_rq_payload_bytes(req); } blk_mq_start_request(req); diff --git a/drivers/pci/dwc/pcie-designware-host.c b/drivers/pci/dwc/pcie-designware-host.c index 8de2d5c69b1d..dc9303abda42 100644 --- a/drivers/pci/dwc/pcie-designware-host.c +++ b/drivers/pci/dwc/pcie-designware-host.c @@ -613,7 +613,7 @@ void dw_pcie_setup_rc(struct pcie_port *pp) /* setup bus numbers */ val = dw_pcie_readl_dbi(pci, PCI_PRIMARY_BUS); val &= 0xff000000; - val |= 0x00010100; + val |= 0x00ff0100; dw_pcie_writel_dbi(pci, PCI_PRIMARY_BUS, val); /* setup command register */ diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 8b14bd326d4a..46d47bd6ca1f 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3908,6 +3908,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9230, quirk_dma_func1_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0642, quirk_dma_func1_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0645, + quirk_dma_func1_alias); /* https://bugs.gentoo.org/show_bug.cgi?id=497630 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_JMICRON, PCI_DEVICE_ID_JMICRON_JMB388_ESD, diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 369d48d6c6f1..365447240d95 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -401,6 +401,10 @@ void pci_release_resource(struct pci_dev *dev, int resno) struct resource *res = dev->resource + resno; pci_info(dev, "BAR %d: releasing %pR\n", resno, res); + + if (!res->parent) + return; + release_resource(res); res->end = resource_size(res) - 1; res->start = 0; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 0c2ed11c0603..f63db346c219 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -638,7 +638,7 @@ static int arm_perf_teardown_cpu(unsigned int cpu, struct hlist_node *node) if (irq_is_percpu_devid(irq)) disable_percpu_irq(irq); else - disable_irq(irq); + disable_irq_nosync(irq); } per_cpu(cpu_armpmu, cpu) = NULL; diff --git a/drivers/phy/qualcomm/phy-qcom-ufs.c b/drivers/phy/qualcomm/phy-qcom-ufs.c index c5ff4525edef..c5493ea51282 100644 --- a/drivers/phy/qualcomm/phy-qcom-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-ufs.c @@ -675,3 +675,8 @@ int ufs_qcom_phy_power_off(struct phy *generic_phy) return 0; } EXPORT_SYMBOL_GPL(ufs_qcom_phy_power_off); + +MODULE_AUTHOR("Yaniv Gardi <ygardi@codeaurora.org>"); +MODULE_AUTHOR("Vivek Gautam <vivek.gautam@codeaurora.org>"); +MODULE_DESCRIPTION("Universal Flash Storage (UFS) QCOM PHY"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c index 1fda9d6c7ea3..4b91ff74779b 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-axg.c +++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c @@ -716,7 +716,7 @@ static const char * const uart_b_groups[] = { "uart_tx_b_x", "uart_rx_b_x", "uart_cts_b_x", "uart_rts_b_x", }; -static const char * const uart_ao_b_gpioz_groups[] = { +static const char * const uart_ao_b_z_groups[] = { "uart_ao_tx_b_z", "uart_ao_rx_b_z", "uart_ao_cts_b_z", "uart_ao_rts_b_z", }; @@ -855,7 +855,7 @@ static struct meson_pmx_func meson_axg_periphs_functions[] = { FUNCTION(nand), FUNCTION(uart_a), FUNCTION(uart_b), - FUNCTION(uart_ao_b_gpioz), + FUNCTION(uart_ao_b_z), FUNCTION(i2c0), FUNCTION(i2c1), FUNCTION(i2c2), diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c index c32399faff57..90c274490181 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c @@ -124,7 +124,7 @@ static const struct samsung_pin_bank_data s5pv210_pin_bank[] __initconst = { EXYNOS_PIN_BANK_EINTW(8, 0xc60, "gph3", 0x0c), }; -const struct samsung_pin_ctrl s5pv210_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl s5pv210_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = s5pv210_pin_bank, @@ -137,6 +137,11 @@ const struct samsung_pin_ctrl s5pv210_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data s5pv210_of_data __initconst = { + .ctrl = s5pv210_pin_ctrl, + .num_ctrl = ARRAY_SIZE(s5pv210_pin_ctrl), +}; + /* Pad retention control code for accessing PMU regmap */ static atomic_t exynos_shared_retention_refcnt; @@ -199,7 +204,7 @@ static const struct samsung_retention_data exynos3250_retention_data __initconst * Samsung pinctrl driver data for Exynos3250 SoC. Exynos3250 SoC includes * two gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos3250_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos3250_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos3250_pin_banks0, @@ -220,6 +225,11 @@ const struct samsung_pin_ctrl exynos3250_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos3250_of_data __initconst = { + .ctrl = exynos3250_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos3250_pin_ctrl), +}; + /* pin banks of exynos4210 pin-controller 0 */ static const struct samsung_pin_bank_data exynos4210_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpa0", 0x00), @@ -303,7 +313,7 @@ static const struct samsung_retention_data exynos4_audio_retention_data __initco * Samsung pinctrl driver data for Exynos4210 SoC. Exynos4210 SoC includes * three gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos4210_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos4210_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos4210_pin_banks0, @@ -329,6 +339,11 @@ const struct samsung_pin_ctrl exynos4210_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos4210_of_data __initconst = { + .ctrl = exynos4210_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos4210_pin_ctrl), +}; + /* pin banks of exynos4x12 pin-controller 0 */ static const struct samsung_pin_bank_data exynos4x12_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpa0", 0x00), @@ -391,7 +406,7 @@ static const struct samsung_pin_bank_data exynos4x12_pin_banks3[] __initconst = * Samsung pinctrl driver data for Exynos4x12 SoC. Exynos4x12 SoC includes * four gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos4x12_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos4x12_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos4x12_pin_banks0, @@ -427,6 +442,11 @@ const struct samsung_pin_ctrl exynos4x12_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos4x12_of_data __initconst = { + .ctrl = exynos4x12_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos4x12_pin_ctrl), +}; + /* pin banks of exynos5250 pin-controller 0 */ static const struct samsung_pin_bank_data exynos5250_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpa0", 0x00), @@ -487,7 +507,7 @@ static const struct samsung_pin_bank_data exynos5250_pin_banks3[] __initconst = * Samsung pinctrl driver data for Exynos5250 SoC. Exynos5250 SoC includes * four gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos5250_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos5250_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos5250_pin_banks0, @@ -523,6 +543,11 @@ const struct samsung_pin_ctrl exynos5250_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos5250_of_data __initconst = { + .ctrl = exynos5250_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos5250_pin_ctrl), +}; + /* pin banks of exynos5260 pin-controller 0 */ static const struct samsung_pin_bank_data exynos5260_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTG(4, 0x000, "gpa0", 0x00), @@ -567,7 +592,7 @@ static const struct samsung_pin_bank_data exynos5260_pin_banks2[] __initconst = * Samsung pinctrl driver data for Exynos5260 SoC. Exynos5260 SoC includes * three gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos5260_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos5260_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos5260_pin_banks0, @@ -587,6 +612,11 @@ const struct samsung_pin_ctrl exynos5260_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos5260_of_data __initconst = { + .ctrl = exynos5260_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos5260_pin_ctrl), +}; + /* pin banks of exynos5410 pin-controller 0 */ static const struct samsung_pin_bank_data exynos5410_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpa0", 0x00), @@ -657,7 +687,7 @@ static const struct samsung_pin_bank_data exynos5410_pin_banks3[] __initconst = * Samsung pinctrl driver data for Exynos5410 SoC. Exynos5410 SoC includes * four gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos5410_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos5410_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos5410_pin_banks0, @@ -690,6 +720,11 @@ const struct samsung_pin_ctrl exynos5410_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos5410_of_data __initconst = { + .ctrl = exynos5410_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos5410_pin_ctrl), +}; + /* pin banks of exynos5420 pin-controller 0 */ static const struct samsung_pin_bank_data exynos5420_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpy7", 0x00), @@ -774,7 +809,7 @@ static const struct samsung_retention_data exynos5420_retention_data __initconst * Samsung pinctrl driver data for Exynos5420 SoC. Exynos5420 SoC includes * four gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos5420_pin_banks0, @@ -808,3 +843,8 @@ const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = { .retention_data = &exynos4_audio_retention_data, }, }; + +const struct samsung_pinctrl_of_match_data exynos5420_of_data __initconst = { + .ctrl = exynos5420_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos5420_pin_ctrl), +}; diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c index fc8f7833bec0..71c9d1d9f345 100644 --- a/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c +++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm64.c @@ -175,7 +175,7 @@ static const struct samsung_retention_data exynos5433_fsys_retention_data __init * Samsung pinctrl driver data for Exynos5433 SoC. Exynos5433 SoC includes * ten gpio/pin-mux/pinconfig controllers. */ -const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = { { /* pin-controller instance 0 data */ .pin_banks = exynos5433_pin_banks0, @@ -260,6 +260,11 @@ const struct samsung_pin_ctrl exynos5433_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data exynos5433_of_data __initconst = { + .ctrl = exynos5433_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos5433_pin_ctrl), +}; + /* pin banks of exynos7 pin-controller - ALIVE */ static const struct samsung_pin_bank_data exynos7_pin_banks0[] __initconst = { EXYNOS_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00), @@ -339,7 +344,7 @@ static const struct samsung_pin_bank_data exynos7_pin_banks9[] __initconst = { EXYNOS_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04), }; -const struct samsung_pin_ctrl exynos7_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl exynos7_pin_ctrl[] __initconst = { { /* pin-controller instance 0 Alive data */ .pin_banks = exynos7_pin_banks0, @@ -392,3 +397,8 @@ const struct samsung_pin_ctrl exynos7_pin_ctrl[] __initconst = { .eint_gpio_init = exynos_eint_gpio_init, }, }; + +const struct samsung_pinctrl_of_match_data exynos7_of_data __initconst = { + .ctrl = exynos7_pin_ctrl, + .num_ctrl = ARRAY_SIZE(exynos7_pin_ctrl), +}; diff --git a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c index 10187cb0e9b9..7e824e4d20f4 100644 --- a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c +++ b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c @@ -565,7 +565,7 @@ static const struct samsung_pin_bank_data s3c2412_pin_banks[] __initconst = { PIN_BANK_2BIT(13, 0x080, "gpj"), }; -const struct samsung_pin_ctrl s3c2412_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl s3c2412_pin_ctrl[] __initconst = { { .pin_banks = s3c2412_pin_banks, .nr_banks = ARRAY_SIZE(s3c2412_pin_banks), @@ -573,6 +573,11 @@ const struct samsung_pin_ctrl s3c2412_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data s3c2412_of_data __initconst = { + .ctrl = s3c2412_pin_ctrl, + .num_ctrl = ARRAY_SIZE(s3c2412_pin_ctrl), +}; + static const struct samsung_pin_bank_data s3c2416_pin_banks[] __initconst = { PIN_BANK_A(27, 0x000, "gpa"), PIN_BANK_2BIT(11, 0x010, "gpb"), @@ -587,7 +592,7 @@ static const struct samsung_pin_bank_data s3c2416_pin_banks[] __initconst = { PIN_BANK_2BIT(2, 0x100, "gpm"), }; -const struct samsung_pin_ctrl s3c2416_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl s3c2416_pin_ctrl[] __initconst = { { .pin_banks = s3c2416_pin_banks, .nr_banks = ARRAY_SIZE(s3c2416_pin_banks), @@ -595,6 +600,11 @@ const struct samsung_pin_ctrl s3c2416_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data s3c2416_of_data __initconst = { + .ctrl = s3c2416_pin_ctrl, + .num_ctrl = ARRAY_SIZE(s3c2416_pin_ctrl), +}; + static const struct samsung_pin_bank_data s3c2440_pin_banks[] __initconst = { PIN_BANK_A(25, 0x000, "gpa"), PIN_BANK_2BIT(11, 0x010, "gpb"), @@ -607,7 +617,7 @@ static const struct samsung_pin_bank_data s3c2440_pin_banks[] __initconst = { PIN_BANK_2BIT(13, 0x0d0, "gpj"), }; -const struct samsung_pin_ctrl s3c2440_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl s3c2440_pin_ctrl[] __initconst = { { .pin_banks = s3c2440_pin_banks, .nr_banks = ARRAY_SIZE(s3c2440_pin_banks), @@ -615,6 +625,11 @@ const struct samsung_pin_ctrl s3c2440_pin_ctrl[] __initconst = { }, }; +const struct samsung_pinctrl_of_match_data s3c2440_of_data __initconst = { + .ctrl = s3c2440_pin_ctrl, + .num_ctrl = ARRAY_SIZE(s3c2440_pin_ctrl), +}; + static const struct samsung_pin_bank_data s3c2450_pin_banks[] __initconst = { PIN_BANK_A(28, 0x000, "gpa"), PIN_BANK_2BIT(11, 0x010, "gpb"), @@ -630,10 +645,15 @@ static const struct samsung_pin_bank_data s3c2450_pin_banks[] __initconst = { PIN_BANK_2BIT(2, 0x100, "gpm"), }; -const struct samsung_pin_ctrl s3c2450_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl s3c2450_pin_ctrl[] __initconst = { { .pin_banks = s3c2450_pin_banks, .nr_banks = ARRAY_SIZE(s3c2450_pin_banks), .eint_wkup_init = s3c24xx_eint_init, }, }; + +const struct samsung_pinctrl_of_match_data s3c2450_of_data __initconst = { + .ctrl = s3c2450_pin_ctrl, + .num_ctrl = ARRAY_SIZE(s3c2450_pin_ctrl), +}; diff --git a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c index 679628ac4b31..288e6567ceb1 100644 --- a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c +++ b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c @@ -789,7 +789,7 @@ static const struct samsung_pin_bank_data s3c64xx_pin_banks0[] __initconst = { * Samsung pinctrl driver data for S3C64xx SoC. S3C64xx SoC includes * one gpio/pin-mux/pinconfig controller. */ -const struct samsung_pin_ctrl s3c64xx_pin_ctrl[] __initconst = { +static const struct samsung_pin_ctrl s3c64xx_pin_ctrl[] __initconst = { { /* pin-controller instance 1 data */ .pin_banks = s3c64xx_pin_banks0, @@ -798,3 +798,8 @@ const struct samsung_pin_ctrl s3c64xx_pin_ctrl[] __initconst = { .eint_wkup_init = s3c64xx_eint_eint0_init, }, }; + +const struct samsung_pinctrl_of_match_data s3c64xx_of_data __initconst = { + .ctrl = s3c64xx_pin_ctrl, + .num_ctrl = ARRAY_SIZE(s3c64xx_pin_ctrl), +}; diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c index da58e4554137..336e88d7bdb9 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.c +++ b/drivers/pinctrl/samsung/pinctrl-samsung.c @@ -942,12 +942,33 @@ static int samsung_gpiolib_register(struct platform_device *pdev, return 0; } +static const struct samsung_pin_ctrl * +samsung_pinctrl_get_soc_data_for_of_alias(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + const struct samsung_pinctrl_of_match_data *of_data; + int id; + + id = of_alias_get_id(node, "pinctrl"); + if (id < 0) { + dev_err(&pdev->dev, "failed to get alias id\n"); + return NULL; + } + + of_data = of_device_get_match_data(&pdev->dev); + if (id >= of_data->num_ctrl) { + dev_err(&pdev->dev, "invalid alias id %d\n", id); + return NULL; + } + + return &(of_data->ctrl[id]); +} + /* retrieve the soc specific data */ static const struct samsung_pin_ctrl * samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d, struct platform_device *pdev) { - int id; struct device_node *node = pdev->dev.of_node; struct device_node *np; const struct samsung_pin_bank_data *bdata; @@ -957,13 +978,9 @@ samsung_pinctrl_get_soc_data(struct samsung_pinctrl_drv_data *d, void __iomem *virt_base[SAMSUNG_PINCTRL_NUM_RESOURCES]; unsigned int i; - id = of_alias_get_id(node, "pinctrl"); - if (id < 0) { - dev_err(&pdev->dev, "failed to get alias id\n"); + ctrl = samsung_pinctrl_get_soc_data_for_of_alias(pdev); + if (!ctrl) return ERR_PTR(-ENOENT); - } - ctrl = of_device_get_match_data(&pdev->dev); - ctrl += id; d->suspend = ctrl->suspend; d->resume = ctrl->resume; @@ -1188,41 +1205,41 @@ static int __maybe_unused samsung_pinctrl_resume(struct device *dev) static const struct of_device_id samsung_pinctrl_dt_match[] = { #ifdef CONFIG_PINCTRL_EXYNOS_ARM { .compatible = "samsung,exynos3250-pinctrl", - .data = exynos3250_pin_ctrl }, + .data = &exynos3250_of_data }, { .compatible = "samsung,exynos4210-pinctrl", - .data = exynos4210_pin_ctrl }, + .data = &exynos4210_of_data }, { .compatible = "samsung,exynos4x12-pinctrl", - .data = exynos4x12_pin_ctrl }, + .data = &exynos4x12_of_data }, { .compatible = "samsung,exynos5250-pinctrl", - .data = exynos5250_pin_ctrl }, + .data = &exynos5250_of_data }, { .compatible = "samsung,exynos5260-pinctrl", - .data = exynos5260_pin_ctrl }, + .data = &exynos5260_of_data }, { .compatible = "samsung,exynos5410-pinctrl", - .data = exynos5410_pin_ctrl }, + .data = &exynos5410_of_data }, { .compatible = "samsung,exynos5420-pinctrl", - .data = exynos5420_pin_ctrl }, + .data = &exynos5420_of_data }, { .compatible = "samsung,s5pv210-pinctrl", - .data = s5pv210_pin_ctrl }, + .data = &s5pv210_of_data }, #endif #ifdef CONFIG_PINCTRL_EXYNOS_ARM64 { .compatible = "samsung,exynos5433-pinctrl", - .data = exynos5433_pin_ctrl }, + .data = &exynos5433_of_data }, { .compatible = "samsung,exynos7-pinctrl", - .data = exynos7_pin_ctrl }, + .data = &exynos7_of_data }, #endif #ifdef CONFIG_PINCTRL_S3C64XX { .compatible = "samsung,s3c64xx-pinctrl", - .data = s3c64xx_pin_ctrl }, + .data = &s3c64xx_of_data }, #endif #ifdef CONFIG_PINCTRL_S3C24XX { .compatible = "samsung,s3c2412-pinctrl", - .data = s3c2412_pin_ctrl }, + .data = &s3c2412_of_data }, { .compatible = "samsung,s3c2416-pinctrl", - .data = s3c2416_pin_ctrl }, + .data = &s3c2416_of_data }, { .compatible = "samsung,s3c2440-pinctrl", - .data = s3c2440_pin_ctrl }, + .data = &s3c2440_of_data }, { .compatible = "samsung,s3c2450-pinctrl", - .data = s3c2450_pin_ctrl }, + .data = &s3c2450_of_data }, #endif {}, }; diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h index e204f609823b..f0cda9424dfe 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.h +++ b/drivers/pinctrl/samsung/pinctrl-samsung.h @@ -282,6 +282,16 @@ struct samsung_pinctrl_drv_data { }; /** + * struct samsung_pinctrl_of_match_data: OF match device specific configuration data. + * @ctrl: array of pin controller data. + * @num_ctrl: size of array @ctrl. + */ +struct samsung_pinctrl_of_match_data { + const struct samsung_pin_ctrl *ctrl; + unsigned int num_ctrl; +}; + +/** * struct samsung_pin_group: represent group of pins of a pinmux function. * @name: name of the pin group, used to lookup the group. * @pins: the pins included in this group. @@ -309,20 +319,20 @@ struct samsung_pmx_func { }; /* list of all exported SoC specific data */ -extern const struct samsung_pin_ctrl exynos3250_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos4210_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos4x12_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos5250_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos5260_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos5410_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos5420_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos5433_pin_ctrl[]; -extern const struct samsung_pin_ctrl exynos7_pin_ctrl[]; -extern const struct samsung_pin_ctrl s3c64xx_pin_ctrl[]; -extern const struct samsung_pin_ctrl s3c2412_pin_ctrl[]; -extern const struct samsung_pin_ctrl s3c2416_pin_ctrl[]; -extern const struct samsung_pin_ctrl s3c2440_pin_ctrl[]; -extern const struct samsung_pin_ctrl s3c2450_pin_ctrl[]; -extern const struct samsung_pin_ctrl s5pv210_pin_ctrl[]; +extern const struct samsung_pinctrl_of_match_data exynos3250_of_data; +extern const struct samsung_pinctrl_of_match_data exynos4210_of_data; +extern const struct samsung_pinctrl_of_match_data exynos4x12_of_data; +extern const struct samsung_pinctrl_of_match_data exynos5250_of_data; +extern const struct samsung_pinctrl_of_match_data exynos5260_of_data; +extern const struct samsung_pinctrl_of_match_data exynos5410_of_data; +extern const struct samsung_pinctrl_of_match_data exynos5420_of_data; +extern const struct samsung_pinctrl_of_match_data exynos5433_of_data; +extern const struct samsung_pinctrl_of_match_data exynos7_of_data; +extern const struct samsung_pinctrl_of_match_data s3c64xx_of_data; +extern const struct samsung_pinctrl_of_match_data s3c2412_of_data; +extern const struct samsung_pinctrl_of_match_data s3c2416_of_data; +extern const struct samsung_pinctrl_of_match_data s3c2440_of_data; +extern const struct samsung_pinctrl_of_match_data s3c2450_of_data; +extern const struct samsung_pinctrl_of_match_data s5pv210_of_data; #endif /* __PINCTRL_SAMSUNG_H */ diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c index 18aeee592fdc..35951e7b89d2 100644 --- a/drivers/pinctrl/sh-pfc/pfc-r8a7795.c +++ b/drivers/pinctrl/sh-pfc/pfc-r8a7795.c @@ -1538,7 +1538,6 @@ static const struct sh_pfc_pin pinmux_pins[] = { SH_PFC_PIN_NAMED_CFG('B', 18, AVB_TD1, CFG_FLAGS), SH_PFC_PIN_NAMED_CFG('B', 19, AVB_RXC, CFG_FLAGS), SH_PFC_PIN_NAMED_CFG('C', 1, PRESETOUT#, CFG_FLAGS), - SH_PFC_PIN_NAMED_CFG('F', 1, CLKOUT, CFG_FLAGS), SH_PFC_PIN_NAMED_CFG('H', 37, MLB_REF, CFG_FLAGS), SH_PFC_PIN_NAMED_CFG('V', 3, QSPI1_SPCLK, CFG_FLAGS), SH_PFC_PIN_NAMED_CFG('V', 5, QSPI1_SSL, CFG_FLAGS), diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c index 6dec6ab13300..d8599736a41a 100644 --- a/drivers/platform/chrome/chromeos_laptop.c +++ b/drivers/platform/chrome/chromeos_laptop.c @@ -423,7 +423,7 @@ static int chromeos_laptop_probe(struct platform_device *pdev) return ret; } -static const struct chromeos_laptop samsung_series_5_550 = { +static struct chromeos_laptop samsung_series_5_550 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, @@ -432,14 +432,14 @@ static const struct chromeos_laptop samsung_series_5_550 = { }, }; -static const struct chromeos_laptop samsung_series_5 = { +static struct chromeos_laptop samsung_series_5 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2583_als, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop chromebook_pixel = { +static struct chromeos_laptop chromebook_pixel = { .i2c_peripherals = { /* Touch Screen. */ { .add = setup_atmel_1664s_ts, I2C_ADAPTER_PANEL }, @@ -450,14 +450,14 @@ static const struct chromeos_laptop chromebook_pixel = { }, }; -static const struct chromeos_laptop hp_chromebook_14 = { +static struct chromeos_laptop hp_chromebook_14 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, }, }; -static const struct chromeos_laptop dell_chromebook_11 = { +static struct chromeos_laptop dell_chromebook_11 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, @@ -466,28 +466,28 @@ static const struct chromeos_laptop dell_chromebook_11 = { }, }; -static const struct chromeos_laptop toshiba_cb35 = { +static struct chromeos_laptop toshiba_cb35 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, }, }; -static const struct chromeos_laptop acer_c7_chromebook = { +static struct chromeos_laptop acer_c7_chromebook = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop acer_ac700 = { +static struct chromeos_laptop acer_ac700 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop acer_c720 = { +static struct chromeos_laptop acer_c720 = { .i2c_peripherals = { /* Touchscreen. */ { .add = setup_atmel_1664s_ts, I2C_ADAPTER_DESIGNWARE_1 }, @@ -500,14 +500,14 @@ static const struct chromeos_laptop acer_c720 = { }, }; -static const struct chromeos_laptop hp_pavilion_14_chromebook = { +static struct chromeos_laptop hp_pavilion_14_chromebook = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, }, }; -static const struct chromeos_laptop cr48 = { +static struct chromeos_laptop cr48 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS }, diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 9a8f96465cdc..51ebc5a6053f 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -105,31 +105,45 @@ config ASUS_LAPTOP If you have an ACPI-compatible ASUS laptop, say Y or M here. +# +# The DELL_SMBIOS driver depends on ACPI_WMI and/or DCDBAS if those +# backends are selected. The "depends" line prevents a configuration +# where DELL_SMBIOS=y while either of those dependencies =m. +# config DELL_SMBIOS - tristate + tristate "Dell SMBIOS driver" + depends on DCDBAS || DCDBAS=n + depends on ACPI_WMI || ACPI_WMI=n + ---help--- + This provides support for the Dell SMBIOS calling interface. + If you have a Dell computer you should enable this option. + + Be sure to select at least one backend for it to work properly. config DELL_SMBIOS_WMI - tristate "Dell SMBIOS calling interface (WMI implementation)" + bool "Dell SMBIOS driver WMI backend" + default y depends on ACPI_WMI select DELL_WMI_DESCRIPTOR - select DELL_SMBIOS + depends on DELL_SMBIOS ---help--- This provides an implementation for the Dell SMBIOS calling interface communicated over ACPI-WMI. - If you have a Dell computer from >2007 you should say Y or M here. + If you have a Dell computer from >2007 you should say Y here. If you aren't sure and this module doesn't work for your computer it just won't load. config DELL_SMBIOS_SMM - tristate "Dell SMBIOS calling interface (SMM implementation)" + bool "Dell SMBIOS driver SMM backend" + default y depends on DCDBAS - select DELL_SMBIOS + depends on DELL_SMBIOS ---help--- This provides an implementation for the Dell SMBIOS calling interface communicated over SMI/SMM. - If you have a Dell computer from <=2017 you should say Y or M here. + If you have a Dell computer from <=2017 you should say Y here. If you aren't sure and this module doesn't work for your computer it just won't load. diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index c388608ad2a3..2ba6cb795338 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -13,8 +13,9 @@ obj-$(CONFIG_MSI_LAPTOP) += msi-laptop.o obj-$(CONFIG_ACPI_CMPC) += classmate-laptop.o obj-$(CONFIG_COMPAL_LAPTOP) += compal-laptop.o obj-$(CONFIG_DELL_SMBIOS) += dell-smbios.o -obj-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o -obj-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o +dell-smbios-objs := dell-smbios-base.o +dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o +dell-smbios-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o obj-$(CONFIG_DELL_LAPTOP) += dell-laptop.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o obj-$(CONFIG_DELL_WMI_DESCRIPTOR) += dell-wmi-descriptor.o diff --git a/drivers/platform/x86/dell-smbios.c b/drivers/platform/x86/dell-smbios-base.c index 8541cde4cb7d..2485c80a9fdd 100644 --- a/drivers/platform/x86/dell-smbios.c +++ b/drivers/platform/x86/dell-smbios-base.c @@ -36,7 +36,7 @@ static DEFINE_MUTEX(smbios_mutex); struct smbios_device { struct list_head list; struct device *device; - int (*call_fn)(struct calling_interface_buffer *); + int (*call_fn)(struct calling_interface_buffer *arg); }; struct smbios_call { @@ -352,8 +352,10 @@ static void __init parse_da_table(const struct dmi_header *dm) struct calling_interface_structure *table = container_of(dm, struct calling_interface_structure, header); - /* 4 bytes of table header, plus 7 bytes of Dell header, plus at least - 6 bytes of entry */ + /* + * 4 bytes of table header, plus 7 bytes of Dell header + * plus at least 6 bytes of entry + */ if (dm->length < 17) return; @@ -554,7 +556,7 @@ static void free_group(struct platform_device *pdev) static int __init dell_smbios_init(void) { const struct dmi_device *valid; - int ret; + int ret, wmi, smm; valid = dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Dell System", NULL); if (!valid) { @@ -589,8 +591,24 @@ static int __init dell_smbios_init(void) if (ret) goto fail_create_group; + /* register backends */ + wmi = init_dell_smbios_wmi(); + if (wmi) + pr_debug("Failed to initialize WMI backend: %d\n", wmi); + smm = init_dell_smbios_smm(); + if (smm) + pr_debug("Failed to initialize SMM backend: %d\n", smm); + if (wmi && smm) { + pr_err("No SMBIOS backends available (wmi: %d, smm: %d)\n", + wmi, smm); + goto fail_sysfs; + } + return 0; +fail_sysfs: + free_group(platform_device); + fail_create_group: platform_device_del(platform_device); @@ -607,6 +625,8 @@ fail_platform_driver: static void __exit dell_smbios_exit(void) { + exit_dell_smbios_wmi(); + exit_dell_smbios_smm(); mutex_lock(&smbios_mutex); if (platform_device) { free_group(platform_device); @@ -617,11 +637,12 @@ static void __exit dell_smbios_exit(void) mutex_unlock(&smbios_mutex); } -subsys_initcall(dell_smbios_init); +module_init(dell_smbios_init); module_exit(dell_smbios_exit); MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); +MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); MODULE_DESCRIPTION("Common functions for kernel modules using Dell SMBIOS"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-smm.c b/drivers/platform/x86/dell-smbios-smm.c index 89f65c4651a0..e9e9da556318 100644 --- a/drivers/platform/x86/dell-smbios-smm.c +++ b/drivers/platform/x86/dell-smbios-smm.c @@ -58,7 +58,7 @@ static const struct dmi_system_id dell_device_table[] __initconst = { }; MODULE_DEVICE_TABLE(dmi, dell_device_table); -static void __init parse_da_table(const struct dmi_header *dm) +static void parse_da_table(const struct dmi_header *dm) { struct calling_interface_structure *table = container_of(dm, struct calling_interface_structure, header); @@ -73,7 +73,7 @@ static void __init parse_da_table(const struct dmi_header *dm) da_command_code = table->cmdIOCode; } -static void __init find_cmd_address(const struct dmi_header *dm, void *dummy) +static void find_cmd_address(const struct dmi_header *dm, void *dummy) { switch (dm->type) { case 0xda: /* Calling interface */ @@ -128,7 +128,7 @@ static bool test_wsmt_enabled(void) return false; } -static int __init dell_smbios_smm_init(void) +int init_dell_smbios_smm(void) { int ret; /* @@ -176,7 +176,7 @@ fail_platform_device_alloc: return ret; } -static void __exit dell_smbios_smm_exit(void) +void exit_dell_smbios_smm(void) { if (platform_device) { dell_smbios_unregister_device(&platform_device->dev); @@ -184,13 +184,3 @@ static void __exit dell_smbios_smm_exit(void) free_page((unsigned long)buffer); } } - -subsys_initcall(dell_smbios_smm_init); -module_exit(dell_smbios_smm_exit); - -MODULE_AUTHOR("Matthew Garrett <mjg@redhat.com>"); -MODULE_AUTHOR("Gabriele Mazzotta <gabriele.mzt@gmail.com>"); -MODULE_AUTHOR("Pali Rohár <pali.rohar@gmail.com>"); -MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); -MODULE_DESCRIPTION("Dell SMBIOS communications over SMI"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c index 609557aa5868..fbefedb1c172 100644 --- a/drivers/platform/x86/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell-smbios-wmi.c @@ -228,7 +228,7 @@ static const struct wmi_device_id dell_smbios_wmi_id_table[] = { { }, }; -static void __init parse_b1_table(const struct dmi_header *dm) +static void parse_b1_table(const struct dmi_header *dm) { struct misc_bios_flags_structure *flags = container_of(dm, struct misc_bios_flags_structure, header); @@ -242,7 +242,7 @@ static void __init parse_b1_table(const struct dmi_header *dm) wmi_supported = 1; } -static void __init find_b1(const struct dmi_header *dm, void *dummy) +static void find_b1(const struct dmi_header *dm, void *dummy) { switch (dm->type) { case 0xb1: /* misc bios flags */ @@ -261,7 +261,7 @@ static struct wmi_driver dell_smbios_wmi_driver = { .filter_callback = dell_smbios_wmi_filter, }; -static int __init init_dell_smbios_wmi(void) +int init_dell_smbios_wmi(void) { dmi_walk(find_b1, NULL); @@ -271,15 +271,9 @@ static int __init init_dell_smbios_wmi(void) return wmi_driver_register(&dell_smbios_wmi_driver); } -static void __exit exit_dell_smbios_wmi(void) +void exit_dell_smbios_wmi(void) { wmi_driver_unregister(&dell_smbios_wmi_driver); } -module_init(init_dell_smbios_wmi); -module_exit(exit_dell_smbios_wmi); - MODULE_ALIAS("wmi:" DELL_WMI_SMBIOS_GUID); -MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); -MODULE_DESCRIPTION("Dell SMBIOS communications over WMI"); -MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/dell-smbios.h b/drivers/platform/x86/dell-smbios.h index 138d478d9adc..d8adaf959740 100644 --- a/drivers/platform/x86/dell-smbios.h +++ b/drivers/platform/x86/dell-smbios.h @@ -75,4 +75,29 @@ int dell_laptop_register_notifier(struct notifier_block *nb); int dell_laptop_unregister_notifier(struct notifier_block *nb); void dell_laptop_call_notifier(unsigned long action, void *data); -#endif +/* for the supported backends */ +#ifdef CONFIG_DELL_SMBIOS_WMI +int init_dell_smbios_wmi(void); +void exit_dell_smbios_wmi(void); +#else /* CONFIG_DELL_SMBIOS_WMI */ +static inline int init_dell_smbios_wmi(void) +{ + return -ENODEV; +} +static inline void exit_dell_smbios_wmi(void) +{} +#endif /* CONFIG_DELL_SMBIOS_WMI */ + +#ifdef CONFIG_DELL_SMBIOS_SMM +int init_dell_smbios_smm(void); +void exit_dell_smbios_smm(void); +#else /* CONFIG_DELL_SMBIOS_SMM */ +static inline int init_dell_smbios_smm(void) +{ + return -ENODEV; +} +static inline void exit_dell_smbios_smm(void) +{} +#endif /* CONFIG_DELL_SMBIOS_SMM */ + +#endif /* _DELL_SMBIOS_H_ */ diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 2c9927430d85..8d102195a392 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -714,7 +714,7 @@ static int __init dell_wmi_init(void) return wmi_driver_register(&dell_wmi_driver); } -module_init(dell_wmi_init); +late_initcall(dell_wmi_init); static void __exit dell_wmi_exit(void) { diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index d1a01311c1a2..5e3df194723e 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -376,6 +376,7 @@ static int intel_hid_remove(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); + device_init_wakeup(&device->dev, false); acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler); intel_hid_set_enable(&device->dev, false); intel_button_array_enable(&device->dev, false); diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index b703d6f5b099..c13780b8dabb 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -7,6 +7,7 @@ */ #include <linux/acpi.h> +#include <linux/dmi.h> #include <linux/input.h> #include <linux/input/sparse-keymap.h> #include <linux/kernel.h> @@ -97,9 +98,35 @@ out_unknown: dev_dbg(&device->dev, "unknown event index 0x%x\n", event); } -static int intel_vbtn_probe(struct platform_device *device) +static void detect_tablet_mode(struct platform_device *device) { + const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE); + struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev); + acpi_handle handle = ACPI_HANDLE(&device->dev); struct acpi_buffer vgbs_output = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *obj; + acpi_status status; + int m; + + if (!(chassis_type && strcmp(chassis_type, "31") == 0)) + goto out; + + status = acpi_evaluate_object(handle, "VGBS", NULL, &vgbs_output); + if (ACPI_FAILURE(status)) + goto out; + + obj = vgbs_output.pointer; + if (!(obj && obj->type == ACPI_TYPE_INTEGER)) + goto out; + + m = !(obj->integer.value & TABLET_MODE_FLAG); + input_report_switch(priv->input_dev, SW_TABLET_MODE, m); +out: + kfree(vgbs_output.pointer); +} + +static int intel_vbtn_probe(struct platform_device *device) +{ acpi_handle handle = ACPI_HANDLE(&device->dev); struct intel_vbtn_priv *priv; acpi_status status; @@ -122,22 +149,7 @@ static int intel_vbtn_probe(struct platform_device *device) return err; } - /* - * VGBS being present and returning something means we have - * a tablet mode switch. - */ - status = acpi_evaluate_object(handle, "VGBS", NULL, &vgbs_output); - if (ACPI_SUCCESS(status)) { - union acpi_object *obj = vgbs_output.pointer; - - if (obj && obj->type == ACPI_TYPE_INTEGER) { - int m = !(obj->integer.value & TABLET_MODE_FLAG); - - input_report_switch(priv->input_dev, SW_TABLET_MODE, m); - } - } - - kfree(vgbs_output.pointer); + detect_tablet_mode(device); status = acpi_install_notify_handler(handle, ACPI_DEVICE_NOTIFY, @@ -154,6 +166,7 @@ static int intel_vbtn_remove(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); + device_init_wakeup(&device->dev, false); acpi_remove_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler); /* diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index c0c8945603cb..8796211ef24a 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -945,7 +945,7 @@ static int wmi_dev_probe(struct device *dev) wblock->char_dev.mode = 0444; ret = misc_register(&wblock->char_dev); if (ret) { - dev_warn(dev, "failed to register char dev: %d", ret); + dev_warn(dev, "failed to register char dev: %d\n", ret); ret = -ENOMEM; goto probe_misc_failure; } @@ -1048,7 +1048,7 @@ static int wmi_create_device(struct device *wmi_bus_dev, if (result) { dev_warn(wmi_bus_dev, - "%s data block query control method not found", + "%s data block query control method not found\n", method); return result; } @@ -1198,7 +1198,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) retval = device_add(&wblock->dev.dev); if (retval) { - dev_err(wmi_bus_dev, "failed to register %pULL\n", + dev_err(wmi_bus_dev, "failed to register %pUL\n", wblock->gblock.guid); if (debug_event) wmi_method_enable(wblock, 0); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index dd4708c58480..1fc0c0811da4 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -4310,7 +4310,7 @@ static int _regulator_resume_early(struct device *dev, void *data) rstate = regulator_get_suspend_state(rdev, *state); if (rstate == NULL) - return -EINVAL; + return 0; mutex_lock(&rdev->mutex); diff --git a/drivers/regulator/stm32-vrefbuf.c b/drivers/regulator/stm32-vrefbuf.c index 72c8b3e1022b..e0a9c445ed67 100644 --- a/drivers/regulator/stm32-vrefbuf.c +++ b/drivers/regulator/stm32-vrefbuf.c @@ -51,7 +51,7 @@ static int stm32_vrefbuf_enable(struct regulator_dev *rdev) * arbitrary timeout. */ ret = readl_poll_timeout(priv->base + STM32_VREFBUF_CSR, val, - !(val & STM32_VRR), 650, 10000); + val & STM32_VRR, 650, 10000); if (ret) { dev_err(&rdev->dev, "stm32 vrefbuf timed out!\n"); val = readl_relaxed(priv->base + STM32_VREFBUF_CSR); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index a7c15f0085e2..ecef8e73d40b 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2581,8 +2581,6 @@ int dasd_cancel_req(struct dasd_ccw_req *cqr) case DASD_CQR_QUEUED: /* request was not started - just set to cleared */ cqr->status = DASD_CQR_CLEARED; - if (cqr->callback_data == DASD_SLEEPON_START_TAG) - cqr->callback_data = DASD_SLEEPON_END_TAG; break; case DASD_CQR_IN_IO: /* request in IO - terminate IO and release again */ @@ -3902,9 +3900,12 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) wait_event(dasd_flush_wq, (cqr->status != DASD_CQR_CLEAR_PENDING)); - /* mark sleepon requests as ended */ - if (cqr->callback_data == DASD_SLEEPON_START_TAG) - cqr->callback_data = DASD_SLEEPON_END_TAG; + /* + * requeue requests to blocklayer will only work + * for block device requests + */ + if (_dasd_requeue_request(cqr)) + continue; /* remove requests from device and block queue */ list_del_init(&cqr->devlist); @@ -3917,13 +3918,6 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) cqr = refers; } - /* - * requeue requests to blocklayer will only work - * for block device requests - */ - if (_dasd_requeue_request(cqr)) - continue; - if (cqr->block) list_del_init(&cqr->blocklist); cqr->block->base->discipline->free_cp( @@ -3940,8 +3934,7 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) list_splice_tail(&requeue_queue, &device->ccw_queue); spin_unlock_irq(get_ccwdev_lock(device->cdev)); } - /* wake up generic waitqueue for eventually ended sleepon requests */ - wake_up(&generic_waitq); + dasd_schedule_device_bh(device); return rc; } diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c index 1319122e9d12..9169af7dbb43 100644 --- a/drivers/s390/cio/device_fsm.c +++ b/drivers/s390/cio/device_fsm.c @@ -795,6 +795,7 @@ ccw_device_online_timeout(struct ccw_device *cdev, enum dev_event dev_event) ccw_device_set_timeout(cdev, 0); cdev->private->iretry = 255; + cdev->private->async_kill_io_rc = -ETIMEDOUT; ret = ccw_device_cancel_halt_clear(cdev); if (ret == -EBUSY) { ccw_device_set_timeout(cdev, 3*HZ); @@ -871,7 +872,7 @@ ccw_device_killing_irq(struct ccw_device *cdev, enum dev_event dev_event) /* OK, i/o is dead now. Call interrupt handler. */ if (cdev->handler) cdev->handler(cdev, cdev->private->intparm, - ERR_PTR(-EIO)); + ERR_PTR(cdev->private->async_kill_io_rc)); } static void @@ -888,14 +889,16 @@ ccw_device_killing_timeout(struct ccw_device *cdev, enum dev_event dev_event) ccw_device_online_verify(cdev, 0); if (cdev->handler) cdev->handler(cdev, cdev->private->intparm, - ERR_PTR(-EIO)); + ERR_PTR(cdev->private->async_kill_io_rc)); } void ccw_device_kill_io(struct ccw_device *cdev) { int ret; + ccw_device_set_timeout(cdev, 0); cdev->private->iretry = 255; + cdev->private->async_kill_io_rc = -EIO; ret = ccw_device_cancel_halt_clear(cdev); if (ret == -EBUSY) { ccw_device_set_timeout(cdev, 3*HZ); diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 1caf6a398760..75ce12a24dc2 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -159,7 +159,7 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) } /** - * ccw_device_start_key() - start a s390 channel program with key + * ccw_device_start_timeout_key() - start a s390 channel program with timeout and key * @cdev: target ccw device * @cpa: logical start address of channel program * @intparm: user specific interruption parameter; will be presented back to @@ -170,10 +170,15 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) * @key: storage key to be used for the I/O * @flags: additional flags; defines the action to be performed for I/O * processing. + * @expires: timeout value in jiffies * * Start a S/390 channel program. When the interrupt arrives, the * IRQ handler is called, either immediately, delayed (dev-end missing, * or sense required) or never (no IRQ handler registered). + * This function notifies the device driver if the channel program has not + * completed during the time specified by @expires. If a timeout occurs, the + * channel program is terminated via xsch, hsch or csch, and the device's + * interrupt handler will be called with an irb containing ERR_PTR(-%ETIMEDOUT). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -182,9 +187,9 @@ int ccw_device_clear(struct ccw_device *cdev, unsigned long intparm) * Context: * Interrupts disabled, ccw device lock held */ -int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, - unsigned long intparm, __u8 lpm, __u8 key, - unsigned long flags) +int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, + unsigned long intparm, __u8 lpm, __u8 key, + unsigned long flags, int expires) { struct subchannel *sch; int ret; @@ -224,6 +229,8 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, switch (ret) { case 0: cdev->private->intparm = intparm; + if (expires) + ccw_device_set_timeout(cdev, expires); break; case -EACCES: case -ENODEV: @@ -234,7 +241,7 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, } /** - * ccw_device_start_timeout_key() - start a s390 channel program with timeout and key + * ccw_device_start_key() - start a s390 channel program with key * @cdev: target ccw device * @cpa: logical start address of channel program * @intparm: user specific interruption parameter; will be presented back to @@ -245,15 +252,10 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, * @key: storage key to be used for the I/O * @flags: additional flags; defines the action to be performed for I/O * processing. - * @expires: timeout value in jiffies * * Start a S/390 channel program. When the interrupt arrives, the * IRQ handler is called, either immediately, delayed (dev-end missing, * or sense required) or never (no IRQ handler registered). - * This function notifies the device driver if the channel program has not - * completed during the time specified by @expires. If a timeout occurs, the - * channel program is terminated via xsch, hsch or csch, and the device's - * interrupt handler will be called with an irb containing ERR_PTR(-%ETIMEDOUT). * Returns: * %0, if the operation was successful; * -%EBUSY, if the device is busy, or status pending; @@ -262,19 +264,12 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, * Context: * Interrupts disabled, ccw device lock held */ -int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, - unsigned long intparm, __u8 lpm, __u8 key, - unsigned long flags, int expires) +int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa, + unsigned long intparm, __u8 lpm, __u8 key, + unsigned long flags) { - int ret; - - if (!cdev) - return -ENODEV; - ccw_device_set_timeout(cdev, expires); - ret = ccw_device_start_key(cdev, cpa, intparm, lpm, key, flags); - if (ret != 0) - ccw_device_set_timeout(cdev, 0); - return ret; + return ccw_device_start_timeout_key(cdev, cpa, intparm, lpm, key, + flags, 0); } /** @@ -489,18 +484,20 @@ void ccw_device_get_id(struct ccw_device *cdev, struct ccw_dev_id *dev_id) EXPORT_SYMBOL(ccw_device_get_id); /** - * ccw_device_tm_start_key() - perform start function + * ccw_device_tm_start_timeout_key() - perform start function * @cdev: ccw device on which to perform the start function * @tcw: transport-command word to be started * @intparm: user defined parameter to be passed to the interrupt handler * @lpm: mask of paths to use * @key: storage key to use for storage access + * @expires: time span in jiffies after which to abort request * * Start the tcw on the given ccw device. Return zero on success, non-zero * otherwise. */ -int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw, - unsigned long intparm, u8 lpm, u8 key) +int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw, + unsigned long intparm, u8 lpm, u8 key, + int expires) { struct subchannel *sch; int rc; @@ -527,37 +524,32 @@ int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw, return -EACCES; } rc = cio_tm_start_key(sch, tcw, lpm, key); - if (rc == 0) + if (rc == 0) { cdev->private->intparm = intparm; + if (expires) + ccw_device_set_timeout(cdev, expires); + } return rc; } -EXPORT_SYMBOL(ccw_device_tm_start_key); +EXPORT_SYMBOL(ccw_device_tm_start_timeout_key); /** - * ccw_device_tm_start_timeout_key() - perform start function + * ccw_device_tm_start_key() - perform start function * @cdev: ccw device on which to perform the start function * @tcw: transport-command word to be started * @intparm: user defined parameter to be passed to the interrupt handler * @lpm: mask of paths to use * @key: storage key to use for storage access - * @expires: time span in jiffies after which to abort request * * Start the tcw on the given ccw device. Return zero on success, non-zero * otherwise. */ -int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw, - unsigned long intparm, u8 lpm, u8 key, - int expires) +int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw, + unsigned long intparm, u8 lpm, u8 key) { - int ret; - - ccw_device_set_timeout(cdev, expires); - ret = ccw_device_tm_start_key(cdev, tcw, intparm, lpm, key); - if (ret != 0) - ccw_device_set_timeout(cdev, 0); - return ret; + return ccw_device_tm_start_timeout_key(cdev, tcw, intparm, lpm, key, 0); } -EXPORT_SYMBOL(ccw_device_tm_start_timeout_key); +EXPORT_SYMBOL(ccw_device_tm_start_key); /** * ccw_device_tm_start() - perform start function diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h index af571d8d6925..90e4e3a7841b 100644 --- a/drivers/s390/cio/io_sch.h +++ b/drivers/s390/cio/io_sch.h @@ -157,6 +157,7 @@ struct ccw_device_private { unsigned long intparm; /* user interruption parameter */ struct qdio_irq *qdio_data; struct irb irb; /* device status */ + int async_kill_io_rc; struct senseid senseid; /* SenseID info */ struct pgid pgid[8]; /* path group IDs per chpid*/ struct ccw1 iccws[2]; /* ccws for SNID/SID/SPGID commands */ diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index ca72f3311004..3653bea38470 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -527,8 +527,7 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue) queue == card->qdio.no_in_queues - 1; } - -static int qeth_issue_next_read(struct qeth_card *card) +static int __qeth_issue_next_read(struct qeth_card *card) { int rc; struct qeth_cmd_buffer *iob; @@ -559,6 +558,17 @@ static int qeth_issue_next_read(struct qeth_card *card) return rc; } +static int qeth_issue_next_read(struct qeth_card *card) +{ + int ret; + + spin_lock_irq(get_ccwdev_lock(CARD_RDEV(card))); + ret = __qeth_issue_next_read(card); + spin_unlock_irq(get_ccwdev_lock(CARD_RDEV(card))); + + return ret; +} + static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card) { struct qeth_reply *reply; @@ -960,7 +970,7 @@ void qeth_clear_thread_running_bit(struct qeth_card *card, unsigned long thread) spin_lock_irqsave(&card->thread_mask_lock, flags); card->thread_running_mask &= ~thread; spin_unlock_irqrestore(&card->thread_mask_lock, flags); - wake_up(&card->wait_q); + wake_up_all(&card->wait_q); } EXPORT_SYMBOL_GPL(qeth_clear_thread_running_bit); @@ -1164,6 +1174,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, } rc = qeth_get_problem(cdev, irb); if (rc) { + card->read_or_write_problem = 1; qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); goto out; @@ -1182,7 +1193,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, return; if (channel == &card->read && channel->state == CH_STATE_UP) - qeth_issue_next_read(card); + __qeth_issue_next_read(card); iob = channel->iob; index = channel->buf_no; @@ -2134,24 +2145,25 @@ int qeth_send_control_data(struct qeth_card *card, int len, } reply->callback = reply_cb; reply->param = reply_param; - if (card->state == CARD_STATE_DOWN) - reply->seqno = QETH_IDX_COMMAND_SEQNO; - else - reply->seqno = card->seqno.ipa++; + init_waitqueue_head(&reply->wait_q); - spin_lock_irqsave(&card->lock, flags); - list_add_tail(&reply->list, &card->cmd_waiter_list); - spin_unlock_irqrestore(&card->lock, flags); while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ; - qeth_prepare_control_data(card, len, iob); if (IS_IPA(iob->data)) { cmd = __ipa_cmd(iob); + cmd->hdr.seqno = card->seqno.ipa++; + reply->seqno = cmd->hdr.seqno; event_timeout = QETH_IPA_TIMEOUT; } else { + reply->seqno = QETH_IDX_COMMAND_SEQNO; event_timeout = QETH_TIMEOUT; } + qeth_prepare_control_data(card, len, iob); + + spin_lock_irqsave(&card->lock, flags); + list_add_tail(&reply->list, &card->cmd_waiter_list); + spin_unlock_irqrestore(&card->lock, flags); timeout = jiffies + event_timeout; @@ -2933,7 +2945,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card, memset(cmd, 0, sizeof(struct qeth_ipa_cmd)); cmd->hdr.command = command; cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST; - cmd->hdr.seqno = card->seqno.ipa; + /* cmd->hdr.seqno is set by qeth_send_control_data() */ cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type); cmd->hdr.rel_adapter_no = (__u8) card->info.portno; if (card->options.layer2) @@ -3898,10 +3910,12 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags); int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, int extra_elems, int data_offset) { - int elements = qeth_get_elements_for_range( - (addr_t)skb->data + data_offset, - (addr_t)skb->data + skb_headlen(skb)) + - qeth_get_elements_for_frags(skb); + addr_t end = (addr_t)skb->data + skb_headlen(skb); + int elements = qeth_get_elements_for_frags(skb); + addr_t start = (addr_t)skb->data + data_offset; + + if (start != end) + elements += qeth_get_elements_for_range(start, end); if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { QETH_DBF_MESSAGE(2, "Invalid size of IP packet " @@ -5084,8 +5098,6 @@ static void qeth_core_free_card(struct qeth_card *card) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); qeth_clean_channel(&card->read); qeth_clean_channel(&card->write); - if (card->dev) - free_netdev(card->dev); qeth_free_qdio_buffers(card); unregister_service_level(&card->qeth_service_level); kfree(card); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 7f236440483f..5ef4c978ad19 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -915,8 +915,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) qeth_l2_set_offline(cgdev); if (card->dev) { - netif_napi_del(&card->napi); unregister_netdev(card->dev); + free_netdev(card->dev); card->dev = NULL; } return; diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h index bdd45f4dcace..498fe9af2cdb 100644 --- a/drivers/s390/net/qeth_l3.h +++ b/drivers/s390/net/qeth_l3.h @@ -40,8 +40,40 @@ struct qeth_ipaddr { unsigned int pfxlen; } a6; } u; - }; + +static inline bool qeth_l3_addr_match_ip(struct qeth_ipaddr *a1, + struct qeth_ipaddr *a2) +{ + if (a1->proto != a2->proto) + return false; + if (a1->proto == QETH_PROT_IPV6) + return ipv6_addr_equal(&a1->u.a6.addr, &a2->u.a6.addr); + return a1->u.a4.addr == a2->u.a4.addr; +} + +static inline bool qeth_l3_addr_match_all(struct qeth_ipaddr *a1, + struct qeth_ipaddr *a2) +{ + /* Assumes that the pair was obtained via qeth_l3_addr_find_by_ip(), + * so 'proto' and 'addr' match for sure. + * + * For ucast: + * - 'mac' is always 0. + * - 'mask'/'pfxlen' for RXIP/VIPA is always 0. For NORMAL, matching + * values are required to avoid mixups in takeover eligibility. + * + * For mcast, + * - 'mac' is mapped from the IP, and thus always matches. + * - 'mask'/'pfxlen' is always 0. + */ + if (a1->type != a2->type) + return false; + if (a1->proto == QETH_PROT_IPV6) + return a1->u.a6.pfxlen == a2->u.a6.pfxlen; + return a1->u.a4.mask == a2->u.a4.mask; +} + static inline u64 qeth_l3_ipaddr_hash(struct qeth_ipaddr *addr) { u64 ret = 0; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index b0c888e86cd4..b6b12220da71 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -67,6 +67,24 @@ void qeth_l3_ipaddr_to_string(enum qeth_prot_versions proto, const __u8 *addr, qeth_l3_ipaddr6_to_string(addr, buf); } +static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card, + struct qeth_ipaddr *query) +{ + u64 key = qeth_l3_ipaddr_hash(query); + struct qeth_ipaddr *addr; + + if (query->is_multicast) { + hash_for_each_possible(card->ip_mc_htable, addr, hnode, key) + if (qeth_l3_addr_match_ip(addr, query)) + return addr; + } else { + hash_for_each_possible(card->ip_htable, addr, hnode, key) + if (qeth_l3_addr_match_ip(addr, query)) + return addr; + } + return NULL; +} + static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len) { int i, j; @@ -120,34 +138,6 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card, return rc; } -inline int -qeth_l3_ipaddrs_is_equal(struct qeth_ipaddr *addr1, struct qeth_ipaddr *addr2) -{ - return addr1->proto == addr2->proto && - !memcmp(&addr1->u, &addr2->u, sizeof(addr1->u)) && - ether_addr_equal_64bits(addr1->mac, addr2->mac); -} - -static struct qeth_ipaddr * -qeth_l3_ip_from_hash(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) -{ - struct qeth_ipaddr *addr; - - if (tmp_addr->is_multicast) { - hash_for_each_possible(card->ip_mc_htable, addr, - hnode, qeth_l3_ipaddr_hash(tmp_addr)) - if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr)) - return addr; - } else { - hash_for_each_possible(card->ip_htable, addr, - hnode, qeth_l3_ipaddr_hash(tmp_addr)) - if (qeth_l3_ipaddrs_is_equal(tmp_addr, addr)) - return addr; - } - - return NULL; -} - int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; @@ -162,23 +152,18 @@ int qeth_l3_delete_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8); } - addr = qeth_l3_ip_from_hash(card, tmp_addr); - if (!addr) + addr = qeth_l3_find_addr_by_ip(card, tmp_addr); + if (!addr || !qeth_l3_addr_match_all(addr, tmp_addr)) return -ENOENT; addr->ref_counter--; - if (addr->ref_counter > 0 && (addr->type == QETH_IP_TYPE_NORMAL || - addr->type == QETH_IP_TYPE_RXIP)) + if (addr->type == QETH_IP_TYPE_NORMAL && addr->ref_counter > 0) return rc; if (addr->in_progress) return -EINPROGRESS; - if (!qeth_card_hw_is_reachable(card)) { - addr->disp_flag = QETH_DISP_ADDR_DELETE; - return 0; - } - - rc = qeth_l3_deregister_addr_entry(card, addr); + if (qeth_card_hw_is_reachable(card)) + rc = qeth_l3_deregister_addr_entry(card, addr); hash_del(&addr->hnode); kfree(addr); @@ -190,6 +175,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; struct qeth_ipaddr *addr; + char buf[40]; QETH_CARD_TEXT(card, 4, "addip"); @@ -200,8 +186,20 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) QETH_CARD_HEX(card, 4, ((char *)&tmp_addr->u.a6.addr) + 8, 8); } - addr = qeth_l3_ip_from_hash(card, tmp_addr); - if (!addr) { + addr = qeth_l3_find_addr_by_ip(card, tmp_addr); + if (addr) { + if (tmp_addr->type != QETH_IP_TYPE_NORMAL) + return -EADDRINUSE; + if (qeth_l3_addr_match_all(addr, tmp_addr)) { + addr->ref_counter++; + return 0; + } + qeth_l3_ipaddr_to_string(tmp_addr->proto, (u8 *)&tmp_addr->u, + buf); + dev_warn(&card->gdev->dev, + "Registering IP address %s failed\n", buf); + return -EADDRINUSE; + } else { addr = qeth_l3_get_addr_buffer(tmp_addr->proto); if (!addr) return -ENOMEM; @@ -241,19 +239,15 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) (rc == IPA_RC_LAN_OFFLINE)) { addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; if (addr->ref_counter < 1) { - qeth_l3_delete_ip(card, addr); + qeth_l3_deregister_addr_entry(card, addr); + hash_del(&addr->hnode); kfree(addr); } } else { hash_del(&addr->hnode); kfree(addr); } - } else { - if (addr->type == QETH_IP_TYPE_NORMAL || - addr->type == QETH_IP_TYPE_RXIP) - addr->ref_counter++; } - return rc; } @@ -321,11 +315,7 @@ static void qeth_l3_recover_ip(struct qeth_card *card) spin_lock_bh(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { - if (addr->disp_flag == QETH_DISP_ADDR_DELETE) { - qeth_l3_deregister_addr_entry(card, addr); - hash_del(&addr->hnode); - kfree(addr); - } else if (addr->disp_flag == QETH_DISP_ADDR_ADD) { + if (addr->disp_flag == QETH_DISP_ADDR_ADD) { if (addr->proto == QETH_PROT_IPV4) { addr->in_progress = 1; spin_unlock_bh(&card->ip_lock); @@ -643,12 +633,7 @@ int qeth_l3_add_vipa(struct qeth_card *card, enum qeth_prot_versions proto, return -ENOMEM; spin_lock_bh(&card->ip_lock); - - if (qeth_l3_ip_from_hash(card, ipaddr)) - rc = -EEXIST; - else - rc = qeth_l3_add_ip(card, ipaddr); - + rc = qeth_l3_add_ip(card, ipaddr); spin_unlock_bh(&card->ip_lock); kfree(ipaddr); @@ -713,12 +698,7 @@ int qeth_l3_add_rxip(struct qeth_card *card, enum qeth_prot_versions proto, return -ENOMEM; spin_lock_bh(&card->ip_lock); - - if (qeth_l3_ip_from_hash(card, ipaddr)) - rc = -EEXIST; - else - rc = qeth_l3_add_ip(card, ipaddr); - + rc = qeth_l3_add_ip(card, ipaddr); spin_unlock_bh(&card->ip_lock); kfree(ipaddr); @@ -1239,8 +1219,9 @@ qeth_l3_add_mc_to_hash(struct qeth_card *card, struct in_device *in4_dev) tmp->u.a4.addr = be32_to_cpu(im4->multiaddr); tmp->is_multicast = 1; - ipm = qeth_l3_ip_from_hash(card, tmp); + ipm = qeth_l3_find_addr_by_ip(card, tmp); if (ipm) { + /* for mcast, by-IP match means full match */ ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING; } else { ipm = qeth_l3_get_addr_buffer(QETH_PROT_IPV4); @@ -1319,8 +1300,9 @@ static void qeth_l3_add_mc6_to_hash(struct qeth_card *card, sizeof(struct in6_addr)); tmp->is_multicast = 1; - ipm = qeth_l3_ip_from_hash(card, tmp); + ipm = qeth_l3_find_addr_by_ip(card, tmp); if (ipm) { + /* for mcast, by-IP match means full match */ ipm->disp_flag = QETH_DISP_ADDR_DO_NOTHING; continue; } @@ -2450,11 +2432,12 @@ static void qeth_tso_fill_header(struct qeth_card *card, static int qeth_l3_get_elements_no_tso(struct qeth_card *card, struct sk_buff *skb, int extra_elems) { - addr_t tcpdptr = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); - int elements = qeth_get_elements_for_range( - tcpdptr, - (addr_t)skb->data + skb_headlen(skb)) + - qeth_get_elements_for_frags(skb); + addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); + addr_t end = (addr_t)skb->data + skb_headlen(skb); + int elements = qeth_get_elements_for_frags(skb); + + if (start != end) + elements += qeth_get_elements_for_range(start, end); if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { QETH_DBF_MESSAGE(2, @@ -2882,8 +2865,8 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) qeth_l3_set_offline(cgdev); if (card->dev) { - netif_napi_del(&card->napi); unregister_netdev(card->dev); + free_netdev(card->dev); card->dev = NULL; } diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 57bf43e34863..dd9464920456 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -328,8 +328,6 @@ static void scsi_host_dev_release(struct device *dev) if (shost->work_q) destroy_workqueue(shost->work_q); - destroy_rcu_head(&shost->rcu); - if (shost->shost_state == SHOST_CREATED) { /* * Free the shost_dev device name here if scsi_host_alloc() @@ -404,7 +402,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); mutex_init(&shost->scan_mutex); - init_rcu_head(&shost->rcu); index = ida_simple_get(&host_index_ida, 0, 0, GFP_KERNEL); if (index < 0) diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 6de9681ace82..ceab5e5c41c2 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -223,6 +223,7 @@ out_done: static void sas_eh_finish_cmd(struct scsi_cmnd *cmd) { struct sas_ha_struct *sas_ha = SHOST_TO_SAS_HA(cmd->device->host); + struct domain_device *dev = cmd_to_domain_dev(cmd); struct sas_task *task = TO_SAS_TASK(cmd); /* At this point, we only get called following an actual abort @@ -231,6 +232,14 @@ static void sas_eh_finish_cmd(struct scsi_cmnd *cmd) */ sas_end_task(cmd, task); + if (dev_is_sata(dev)) { + /* defer commands to libata so that libata EH can + * handle ata qcs correctly + */ + list_move_tail(&cmd->eh_entry, &sas_ha->eh_ata_q); + return; + } + /* now finish the command and move it on to the error * handler done list, this also takes it off the * error handler pending list. @@ -238,22 +247,6 @@ static void sas_eh_finish_cmd(struct scsi_cmnd *cmd) scsi_eh_finish_cmd(cmd, &sas_ha->eh_done_q); } -static void sas_eh_defer_cmd(struct scsi_cmnd *cmd) -{ - struct domain_device *dev = cmd_to_domain_dev(cmd); - struct sas_ha_struct *ha = dev->port->ha; - struct sas_task *task = TO_SAS_TASK(cmd); - - if (!dev_is_sata(dev)) { - sas_eh_finish_cmd(cmd); - return; - } - - /* report the timeout to libata */ - sas_end_task(cmd, task); - list_move_tail(&cmd->eh_entry, &ha->eh_ata_q); -} - static void sas_scsi_clear_queue_lu(struct list_head *error_q, struct scsi_cmnd *my_cmd) { struct scsi_cmnd *cmd, *n; @@ -261,7 +254,7 @@ static void sas_scsi_clear_queue_lu(struct list_head *error_q, struct scsi_cmnd list_for_each_entry_safe(cmd, n, error_q, eh_entry) { if (cmd->device->sdev_target == my_cmd->device->sdev_target && cmd->device->lun == my_cmd->device->lun) - sas_eh_defer_cmd(cmd); + sas_eh_finish_cmd(cmd); } } @@ -631,12 +624,12 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head * case TASK_IS_DONE: SAS_DPRINTK("%s: task 0x%p is done\n", __func__, task); - sas_eh_defer_cmd(cmd); + sas_eh_finish_cmd(cmd); continue; case TASK_IS_ABORTED: SAS_DPRINTK("%s: task 0x%p is aborted\n", __func__, task); - sas_eh_defer_cmd(cmd); + sas_eh_finish_cmd(cmd); continue; case TASK_IS_AT_LU: SAS_DPRINTK("task 0x%p is at LU: lu recover\n", task); @@ -647,7 +640,7 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head * "recovered\n", SAS_ADDR(task->dev), cmd->device->lun); - sas_eh_defer_cmd(cmd); + sas_eh_finish_cmd(cmd); sas_scsi_clear_queue_lu(work_q, cmd); goto Again; } diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 073ced07e662..dc8e850fbfd2 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -216,36 +216,30 @@ inline void megasas_return_cmd_fusion(struct megasas_instance *instance, /** * megasas_fire_cmd_fusion - Sends command to the FW * @instance: Adapter soft state - * @req_desc: 32bit or 64bit Request descriptor + * @req_desc: 64bit Request descriptor * - * Perform PCI Write. Ventura supports 32 bit Descriptor. - * Prior to Ventura (12G) MR controller supports 64 bit Descriptor. + * Perform PCI Write. */ static void megasas_fire_cmd_fusion(struct megasas_instance *instance, union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc) { - if (instance->adapter_type == VENTURA_SERIES) - writel(le32_to_cpu(req_desc->u.low), - &instance->reg_set->inbound_single_queue_port); - else { #if defined(writeq) && defined(CONFIG_64BIT) - u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) | - le32_to_cpu(req_desc->u.low)); + u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) | + le32_to_cpu(req_desc->u.low)); - writeq(req_data, &instance->reg_set->inbound_low_queue_port); + writeq(req_data, &instance->reg_set->inbound_low_queue_port); #else - unsigned long flags; - spin_lock_irqsave(&instance->hba_lock, flags); - writel(le32_to_cpu(req_desc->u.low), - &instance->reg_set->inbound_low_queue_port); - writel(le32_to_cpu(req_desc->u.high), - &instance->reg_set->inbound_high_queue_port); - mmiowb(); - spin_unlock_irqrestore(&instance->hba_lock, flags); + unsigned long flags; + spin_lock_irqsave(&instance->hba_lock, flags); + writel(le32_to_cpu(req_desc->u.low), + &instance->reg_set->inbound_low_queue_port); + writel(le32_to_cpu(req_desc->u.high), + &instance->reg_set->inbound_high_queue_port); + mmiowb(); + spin_unlock_irqrestore(&instance->hba_lock, flags); #endif - } } /** @@ -982,7 +976,6 @@ megasas_ioc_init_fusion(struct megasas_instance *instance) const char *sys_info; MFI_CAPABILITIES *drv_ops; u32 scratch_pad_2; - unsigned long flags; ktime_t time; bool cur_fw_64bit_dma_capable; @@ -1121,14 +1114,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance) break; } - /* For Ventura also IOC INIT required 64 bit Descriptor write. */ - spin_lock_irqsave(&instance->hba_lock, flags); - writel(le32_to_cpu(req_desc.u.low), - &instance->reg_set->inbound_low_queue_port); - writel(le32_to_cpu(req_desc.u.high), - &instance->reg_set->inbound_high_queue_port); - mmiowb(); - spin_unlock_irqrestore(&instance->hba_lock, flags); + megasas_fire_cmd_fusion(instance, &req_desc); wait_and_poll(instance, cmd, MFI_POLL_TIMEOUT_SECS); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 59a87ca328d3..0aafbfd1b746 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -6297,14 +6297,14 @@ _base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase) } /** - * _wait_for_commands_to_complete - reset controller + * mpt3sas_wait_for_commands_to_complete - reset controller * @ioc: Pointer to MPT_ADAPTER structure * * This function is waiting 10s for all pending commands to complete * prior to putting controller in reset. */ -static void -_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) +void +mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) { u32 ioc_state; @@ -6377,7 +6377,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc, is_fault = 1; } _base_reset_handler(ioc, MPT3_IOC_PRE_RESET); - _wait_for_commands_to_complete(ioc); + mpt3sas_wait_for_commands_to_complete(ioc); _base_mask_interrupts(ioc); r = _base_make_ioc_ready(ioc, type); if (r) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 789bc421424b..99ccf83b8c51 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1433,6 +1433,9 @@ void mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc, int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc); +void +mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc); + /* scsih shared API */ struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 74fca184dba9..a1cb0236c550 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2835,7 +2835,8 @@ scsih_abort(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { sdev_printk(KERN_INFO, scmd->device, "device been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -2898,7 +2899,8 @@ scsih_dev_reset(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { sdev_printk(KERN_INFO, scmd->device, "device been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -2961,7 +2963,8 @@ scsih_target_reset(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { starget_printk(KERN_INFO, starget, "target been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -3019,7 +3022,7 @@ scsih_host_reset(struct scsi_cmnd *scmd) ioc->name, scmd); scsi_print_command(scmd); - if (ioc->is_driver_loading) { + if (ioc->is_driver_loading || ioc->remove_host) { pr_info(MPT3SAS_FMT "Blocking the host reset\n", ioc->name); r = FAILED; @@ -4453,7 +4456,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc) st = scsi_cmd_priv(scmd); mpt3sas_base_clear_st(ioc, st); scsi_dma_unmap(scmd); - if (ioc->pci_error_recovery) + if (ioc->pci_error_recovery || ioc->remove_host) scmd->result = DID_NO_CONNECT << 16; else scmd->result = DID_RESET << 16; @@ -9739,6 +9742,10 @@ static void scsih_remove(struct pci_dev *pdev) unsigned long flags; ioc->remove_host = 1; + + mpt3sas_wait_for_commands_to_complete(ioc); + _scsih_flush_running_cmds(ioc); + _scsih_fw_event_cleanup_queue(ioc); spin_lock_irqsave(&ioc->fw_event_lock, flags); @@ -9815,6 +9822,10 @@ scsih_shutdown(struct pci_dev *pdev) unsigned long flags; ioc->remove_host = 1; + + mpt3sas_wait_for_commands_to_complete(ioc); + _scsih_flush_running_cmds(ioc); + _scsih_fw_event_cleanup_queue(ioc); spin_lock_irqsave(&ioc->fw_event_lock, flags); @@ -10547,7 +10558,7 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id) snprintf(ioc->firmware_event_name, sizeof(ioc->firmware_event_name), "fw_event_%s%d", ioc->driver_name, ioc->id); ioc->firmware_event_thread = alloc_ordered_workqueue( - ioc->firmware_event_name, WQ_MEM_RECLAIM); + ioc->firmware_event_name, 0); if (!ioc->firmware_event_thread) { pr_err(MPT3SAS_FMT "failure at %s:%d/%s()!\n", ioc->name, __FILE__, __LINE__, __func__); diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 667d7697ba01..d09afe1b567d 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -762,6 +762,11 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi, iscsi_cid = cqe->conn_id; qedi_conn = qedi->cid_que.conn_cid_tbl[iscsi_cid]; + if (!qedi_conn) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, + "icid not found 0x%x\n", cqe->conn_id); + return; + } /* Based on this itt get the corresponding qedi_cmd */ spin_lock_bh(&qedi_conn->tmf_work_lock); diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index be7d6824581a..c9689f97c307 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -261,9 +261,9 @@ struct name_list_extended { struct get_name_list_extended *l; dma_addr_t ldma; - struct list_head fcports; /* protect by sess_list */ + struct list_head fcports; + spinlock_t fcports_lock; u32 size; - u8 sent; }; /* * Timeout timer counts in seconds @@ -2217,6 +2217,7 @@ typedef struct { /* FCP-4 types */ #define FC4_TYPE_FCP_SCSI 0x08 +#define FC4_TYPE_NVME 0x28 #define FC4_TYPE_OTHER 0x0 #define FC4_TYPE_UNKNOWN 0xff diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 5bf9a59432f6..403fa096f8c8 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3179,6 +3179,7 @@ done_free_sp: sp->free(sp); fcport->flags &= ~FCF_ASYNC_SENT; done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -3370,6 +3371,7 @@ done_free_sp: sp->free(sp); fcport->flags &= ~FCF_ASYNC_SENT; done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -3971,6 +3973,9 @@ out: spin_lock_irqsave(&vha->work_lock, flags); vha->scan.scan_flags &= ~SF_SCANNING; spin_unlock_irqrestore(&vha->work_lock, flags); + + if ((fc4type == FC4_TYPE_FCP_SCSI) && vha->flags.nvme_enabled) + qla24xx_async_gpnft(vha, FC4_TYPE_NVME); } static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res) diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 2dea1129d396..8d7fab3cd01d 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -213,6 +213,7 @@ done_free_sp: sp->free(sp); fcport->flags &= ~FCF_ASYNC_SENT; done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -263,7 +264,7 @@ qla2x00_async_logout(struct scsi_qla_host *vha, fc_port_t *fcport) done_free_sp: sp->free(sp); done: - fcport->flags &= ~FCF_ASYNC_SENT; + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); return rval; } @@ -271,6 +272,7 @@ void qla2x00_async_prlo_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { + fcport->flags &= ~FCF_ASYNC_ACTIVE; /* Don't re-login in target mode */ if (!fcport->tgt_session) qla2x00_mark_device_lost(vha, fcport, 1, 0); @@ -284,6 +286,7 @@ qla2x00_async_prlo_sp_done(void *s, int res) struct srb_iocb *lio = &sp->u.iocb_cmd; struct scsi_qla_host *vha = sp->vha; + sp->fcport->flags &= ~FCF_ASYNC_ACTIVE; if (!test_bit(UNLOADING, &vha->dpc_flags)) qla2x00_post_async_prlo_done_work(sp->fcport->vha, sp->fcport, lio->u.logio.data); @@ -322,6 +325,7 @@ qla2x00_async_prlo(struct scsi_qla_host *vha, fc_port_t *fcport) done_free_sp: sp->free(sp); done: + fcport->flags &= ~FCF_ASYNC_ACTIVE; return rval; } @@ -375,6 +379,8 @@ qla2x00_async_adisc_sp_done(void *ptr, int res) "Async done-%s res %x %8phC\n", sp->name, res, sp->fcport->port_name); + sp->fcport->flags &= ~FCF_ASYNC_SENT; + memset(&ea, 0, sizeof(ea)); ea.event = FCME_ADISC_DONE; ea.rc = res; @@ -425,7 +431,7 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport, done_free_sp: sp->free(sp); done: - fcport->flags &= ~FCF_ASYNC_SENT; + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); qla2x00_post_async_adisc_work(vha, fcport, data); return rval; } @@ -643,8 +649,7 @@ qla24xx_async_gnl_sp_done(void *s, int res) (loop_id & 0x7fff)); } - spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); - vha->gnl.sent = 0; + spin_lock_irqsave(&vha->gnl.fcports_lock, flags); INIT_LIST_HEAD(&h); fcport = tf = NULL; @@ -653,12 +658,16 @@ qla24xx_async_gnl_sp_done(void *s, int res) list_for_each_entry_safe(fcport, tf, &h, gnl_entry) { list_del_init(&fcport->gnl_entry); + spin_lock(&vha->hw->tgt.sess_lock); fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); + spin_unlock(&vha->hw->tgt.sess_lock); ea.fcport = fcport; qla2x00_fcport_event_handler(vha, &ea); } + spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags); + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); /* create new fcport if fw has knowledge of new sessions */ for (i = 0; i < n; i++) { port_id_t id; @@ -710,18 +719,21 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport) ql_dbg(ql_dbg_disc, vha, 0x20d9, "Async-gnlist WWPN %8phC \n", fcport->port_name); - spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); + spin_lock_irqsave(&vha->gnl.fcports_lock, flags); + if (!list_empty(&fcport->gnl_entry)) { + spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags); + rval = QLA_SUCCESS; + goto done; + } + + spin_lock(&vha->hw->tgt.sess_lock); fcport->disc_state = DSC_GNL; fcport->last_rscn_gen = fcport->rscn_gen; fcport->last_login_gen = fcport->login_gen; + spin_unlock(&vha->hw->tgt.sess_lock); list_add_tail(&fcport->gnl_entry, &vha->gnl.fcports); - if (vha->gnl.sent) { - spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); - return QLA_SUCCESS; - } - vha->gnl.sent = 1; - spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + spin_unlock_irqrestore(&vha->gnl.fcports_lock, flags); sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL); if (!sp) @@ -1049,6 +1061,7 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) fc_port_t *fcport = ea->fcport; struct port_database_24xx *pd; struct srb *sp = ea->sp; + uint8_t ls; pd = (struct port_database_24xx *)sp->u.iocb_cmd.u.mbx.in; @@ -1061,7 +1074,12 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea) if (fcport->disc_state == DSC_DELETE_PEND) return; - switch (pd->current_login_state) { + if (fcport->fc4f_nvme) + ls = pd->current_login_state >> 4; + else + ls = pd->current_login_state & 0xf; + + switch (ls) { case PDS_PRLI_COMPLETE: __qla24xx_parse_gpdb(vha, fcport, pd); break; @@ -1151,8 +1169,9 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport) if (fcport->scan_state != QLA_FCPORT_FOUND) return 0; - if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || - (fcport->fw_login_state == DSC_LS_PRLI_PEND)) + if ((fcport->loop_id != FC_NO_LOOP_ID) && + ((fcport->fw_login_state == DSC_LS_PLOGI_PEND) || + (fcport->fw_login_state == DSC_LS_PRLI_PEND))) return 0; if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) { @@ -1527,6 +1546,7 @@ qla24xx_abort_sp_done(void *ptr, int res) srb_t *sp = ptr; struct srb_iocb *abt = &sp->u.iocb_cmd; + del_timer(&sp->u.iocb_cmd.timer); complete(&abt->u.abt.comp); } @@ -1699,7 +1719,6 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea) set_bit(ea->fcport->loop_id, vha->hw->loop_id_map); spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); - ea->fcport->loop_id = FC_NO_LOOP_ID; ea->fcport->chip_reset = vha->hw->base_qpair->chip_reset; ea->fcport->logout_on_delete = 1; ea->fcport->send_els_logo = 0; @@ -1791,6 +1810,7 @@ qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport, qla2x00_mark_device_lost(vha, fcport, 1, 0); qlt_logo_completion_handler(fcport, data[0]); fcport->login_gen++; + fcport->flags &= ~FCF_ASYNC_ACTIVE; return; } @@ -1798,6 +1818,7 @@ void qla2x00_async_adisc_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { + fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE); if (data[0] == MBS_COMMAND_COMPLETE) { qla2x00_update_fcport(vha, fcport); @@ -1805,7 +1826,6 @@ qla2x00_async_adisc_done(struct scsi_qla_host *vha, fc_port_t *fcport, } /* Retry login. */ - fcport->flags &= ~FCF_ASYNC_SENT; if (data[1] & QLA_LOGIO_LOGIN_RETRIED) set_bit(RELOGIN_NEEDED, &vha->dpc_flags); else diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index afcb5567998a..5c5dcca4d1da 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -454,7 +454,7 @@ static int qla2x00_alloc_queues(struct qla_hw_data *ha, struct req_que *req, ha->req_q_map[0] = req; set_bit(0, ha->rsp_qid_map); set_bit(0, ha->req_qid_map); - return 1; + return 0; fail_qpair_map: kfree(ha->base_qpair); @@ -471,6 +471,9 @@ fail_req_map: static void qla2x00_free_req_que(struct qla_hw_data *ha, struct req_que *req) { + if (!ha->req_q_map) + return; + if (IS_QLAFX00(ha)) { if (req && req->ring_fx00) dma_free_coherent(&ha->pdev->dev, @@ -481,14 +484,17 @@ static void qla2x00_free_req_que(struct qla_hw_data *ha, struct req_que *req) (req->length + 1) * sizeof(request_t), req->ring, req->dma); - if (req) + if (req) { kfree(req->outstanding_cmds); - - kfree(req); + kfree(req); + } } static void qla2x00_free_rsp_que(struct qla_hw_data *ha, struct rsp_que *rsp) { + if (!ha->rsp_q_map) + return; + if (IS_QLAFX00(ha)) { if (rsp && rsp->ring) dma_free_coherent(&ha->pdev->dev, @@ -499,7 +505,8 @@ static void qla2x00_free_rsp_que(struct qla_hw_data *ha, struct rsp_que *rsp) (rsp->length + 1) * sizeof(response_t), rsp->ring, rsp->dma); } - kfree(rsp); + if (rsp) + kfree(rsp); } static void qla2x00_free_queues(struct qla_hw_data *ha) @@ -1723,6 +1730,8 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) struct qla_tgt_cmd *cmd; uint8_t trace = 0; + if (!ha->req_q_map) + return; spin_lock_irqsave(qp->qp_lock_ptr, flags); req = qp->req; for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) { @@ -3095,14 +3104,14 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) /* Set up the irqs */ ret = qla2x00_request_irqs(ha, rsp); if (ret) - goto probe_hw_failed; + goto probe_failed; /* Alloc arrays of request and response ring ptrs */ - if (!qla2x00_alloc_queues(ha, req, rsp)) { + if (qla2x00_alloc_queues(ha, req, rsp)) { ql_log(ql_log_fatal, base_vha, 0x003d, "Failed to allocate memory for queue pointers..." "aborting.\n"); - goto probe_init_failed; + goto probe_failed; } if (ha->mqenable && shost_use_blk_mq(host)) { @@ -3387,15 +3396,6 @@ skip_dpc: return 0; -probe_init_failed: - qla2x00_free_req_que(ha, req); - ha->req_q_map[0] = NULL; - clear_bit(0, ha->req_qid_map); - qla2x00_free_rsp_que(ha, rsp); - ha->rsp_q_map[0] = NULL; - clear_bit(0, ha->rsp_qid_map); - ha->max_req_queues = ha->max_rsp_queues = 0; - probe_failed: if (base_vha->timer_active) qla2x00_stop_timer(base_vha); @@ -4508,11 +4508,17 @@ qla2x00_mem_free(struct qla_hw_data *ha) if (ha->init_cb) dma_free_coherent(&ha->pdev->dev, ha->init_cb_size, ha->init_cb, ha->init_cb_dma); - vfree(ha->optrom_buffer); - kfree(ha->nvram); - kfree(ha->npiv_info); - kfree(ha->swl); - kfree(ha->loop_id_map); + + if (ha->optrom_buffer) + vfree(ha->optrom_buffer); + if (ha->nvram) + kfree(ha->nvram); + if (ha->npiv_info) + kfree(ha->npiv_info); + if (ha->swl) + kfree(ha->swl); + if (ha->loop_id_map) + kfree(ha->loop_id_map); ha->srb_mempool = NULL; ha->ctx_mempool = NULL; @@ -4528,6 +4534,15 @@ qla2x00_mem_free(struct qla_hw_data *ha) ha->ex_init_cb_dma = 0; ha->async_pd = NULL; ha->async_pd_dma = 0; + ha->loop_id_map = NULL; + ha->npiv_info = NULL; + ha->optrom_buffer = NULL; + ha->swl = NULL; + ha->nvram = NULL; + ha->mctp_dump = NULL; + ha->dcbx_tlv = NULL; + ha->xgmac_data = NULL; + ha->sfp_data = NULL; ha->s_dma_pool = NULL; ha->dl_dma_pool = NULL; @@ -4577,6 +4592,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, spin_lock_init(&vha->work_lock); spin_lock_init(&vha->cmd_list_lock); + spin_lock_init(&vha->gnl.fcports_lock); init_waitqueue_head(&vha->fcport_waitQ); init_waitqueue_head(&vha->vref_waitq); @@ -4806,9 +4822,12 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) fcport->d_id = e->u.new_sess.id; fcport->flags |= FCF_FABRIC_DEVICE; fcport->fw_login_state = DSC_LS_PLOGI_PEND; - if (e->u.new_sess.fc4_type == FC4_TYPE_FCP_SCSI) + if (e->u.new_sess.fc4_type == FC4_TYPE_FCP_SCSI) { fcport->fc4_type = FC4_TYPE_FCP_SCSI; - + } else if (e->u.new_sess.fc4_type == FC4_TYPE_NVME) { + fcport->fc4_type = FC4_TYPE_OTHER; + fcport->fc4f_nvme = FC4_TYPE_NVME; + } memcpy(fcport->port_name, e->u.new_sess.port_name, WWN_SIZE); } else { @@ -4877,6 +4896,8 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) } qlt_plogi_ack_unref(vha, pla); } else { + fc_port_t *dfcp = NULL; + spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags); tfcp = qla2x00_find_fcport_by_nportid(vha, &e->u.new_sess.id, 1); @@ -4899,11 +4920,13 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e) default: fcport->login_pause = 1; tfcp->conflict = fcport; - qlt_schedule_sess_for_deletion(tfcp); + dfcp = tfcp; break; } } spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + if (dfcp) + qlt_schedule_sess_for_deletion(tfcp); wwn = wwn_to_u64(fcport->node_name); diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 896b2d8bd803..b49ac85f3de2 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1224,10 +1224,10 @@ static void qla24xx_chk_fcp_state(struct fc_port *sess) } } -/* ha->tgt.sess_lock supposed to be held on entry */ void qlt_schedule_sess_for_deletion(struct fc_port *sess) { struct qla_tgt *tgt = sess->tgt; + struct qla_hw_data *ha = sess->vha->hw; unsigned long flags; if (sess->disc_state == DSC_DELETE_PEND) @@ -1244,16 +1244,16 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) return; } + spin_lock_irqsave(&ha->tgt.sess_lock, flags); if (sess->deleted == QLA_SESS_DELETED) sess->logout_on_delete = 0; - spin_lock_irqsave(&sess->vha->work_lock, flags); if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { - spin_unlock_irqrestore(&sess->vha->work_lock, flags); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); return; } sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; - spin_unlock_irqrestore(&sess->vha->work_lock, flags); + spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); sess->disc_state = DSC_DELETE_PEND; @@ -1262,13 +1262,10 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, "Scheduling sess %p for deletion\n", sess); - /* use cancel to push work element through before re-queue */ - cancel_work_sync(&sess->del_work); INIT_WORK(&sess->del_work, qla24xx_delete_sess_fn); - queue_work(sess->vha->hw->wq, &sess->del_work); + WARN_ON(!queue_work(sess->vha->hw->wq, &sess->del_work)); } -/* ha->tgt.sess_lock supposed to be held on entry */ static void qlt_clear_tgt_db(struct qla_tgt *tgt) { struct fc_port *sess; @@ -1451,8 +1448,8 @@ qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen) ql_dbg(ql_dbg_tgt_mgt, vha, 0xf008, "qla_tgt_fc_port_deleted %p", sess); sess->local = 1; - qlt_schedule_sess_for_deletion(sess); spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags); + qlt_schedule_sess_for_deletion(sess); } static inline int test_tgt_sess_count(struct qla_tgt *tgt) @@ -1512,10 +1509,8 @@ int qlt_stop_phase1(struct qla_tgt *tgt) * Lock is needed, because we still can get an incoming packet. */ mutex_lock(&vha->vha_tgt.tgt_mutex); - spin_lock_irqsave(&ha->tgt.sess_lock, flags); tgt->tgt_stop = 1; qlt_clear_tgt_db(tgt); - spin_unlock_irqrestore(&ha->tgt.sess_lock, flags); mutex_unlock(&vha->vha_tgt.tgt_mutex); mutex_unlock(&qla_tgt_mutex); diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index d042915ce895..ca53a5f785ee 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -223,7 +223,8 @@ static void scsi_eh_reset(struct scsi_cmnd *scmd) static void scsi_eh_inc_host_failed(struct rcu_head *head) { - struct Scsi_Host *shost = container_of(head, typeof(*shost), rcu); + struct scsi_cmnd *scmd = container_of(head, typeof(*scmd), rcu); + struct Scsi_Host *shost = scmd->device->host; unsigned long flags; spin_lock_irqsave(shost->host_lock, flags); @@ -259,7 +260,7 @@ void scsi_eh_scmd_add(struct scsi_cmnd *scmd) * Ensure that all tasks observe the host state change before the * host_failed change. */ - call_rcu(&shost->rcu, scsi_eh_inc_host_failed); + call_rcu(&scmd->rcu, scsi_eh_inc_host_failed); } /** diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index a86df9ca7d1c..c84f931388f2 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -671,6 +671,7 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (!blk_rq_is_scsi(req)) { WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); cmd->flags &= ~SCMD_INITIALIZED; + destroy_rcu_head(&cmd->rcu); } if (req->mq_ctx) { @@ -720,6 +721,8 @@ static blk_status_t __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result) { switch (host_byte(result)) { + case DID_OK: + return BLK_STS_OK; case DID_TRANSPORT_FAILFAST: return BLK_STS_TRANSPORT; case DID_TARGET_FAILURE: @@ -1151,6 +1154,7 @@ static void scsi_initialize_rq(struct request *rq) struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); scsi_req_init(&cmd->req); + init_rcu_head(&cmd->rcu); cmd->jiffies_at_alloc = jiffies; cmd->retries = 0; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bff21e636ddd..3541caf3fceb 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2595,6 +2595,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) int res; struct scsi_device *sdp = sdkp->device; struct scsi_mode_data data; + int disk_ro = get_disk_ro(sdkp->disk); int old_wp = sdkp->write_prot; set_disk_ro(sdkp->disk, 0); @@ -2635,7 +2636,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) "Test WP failed, assume Write Enabled\n"); } else { sdkp->write_prot = ((data.device_specific & 0x80) != 0); - set_disk_ro(sdkp->disk, sdkp->write_prot); + set_disk_ro(sdkp->disk, sdkp->write_prot || disk_ro); if (sdkp->first_scan || old_wp != sdkp->write_prot) { sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n", sdkp->write_prot ? "on" : "off"); diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 6c348a211ebb..89cf4498f535 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -403,7 +403,7 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf) */ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) { - u64 zone_blocks; + u64 zone_blocks = 0; sector_t block = 0; unsigned char *buf; unsigned char *rec; @@ -421,10 +421,8 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) /* Do a report zone to get the same field */ ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0); - if (ret) { - zone_blocks = 0; - goto out; - } + if (ret) + goto out_free; same = buf[4] & 0x0f; if (same > 0) { @@ -464,7 +462,7 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, block); if (ret) - return ret; + goto out_free; } } while (block < sdkp->capacity); @@ -472,35 +470,32 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp) zone_blocks = sdkp->zone_blocks; out: - kfree(buf); - if (!zone_blocks) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Devices with non constant zone " "size are not supported\n"); - return -ENODEV; - } - - if (!is_power_of_2(zone_blocks)) { + ret = -ENODEV; + } else if (!is_power_of_2(zone_blocks)) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Devices with non power of 2 zone " "size are not supported\n"); - return -ENODEV; - } - - if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) { + ret = -ENODEV; + } else if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) { if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Zone size too large\n"); - return -ENODEV; + ret = -ENODEV; + } else { + sdkp->zone_blocks = zone_blocks; + sdkp->zone_shift = ilog2(zone_blocks); } - sdkp->zone_blocks = zone_blocks; - sdkp->zone_shift = ilog2(zone_blocks); +out_free: + kfree(buf); - return 0; + return ret; } /** diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 6be5ab32c94f..8c51d628b52e 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1311,7 +1311,8 @@ static int storvsc_do_io(struct hv_device *device, */ cpumask_and(&alloced_mask, &stor_device->alloced_cpus, cpumask_of_node(cpu_to_node(q_num))); - for_each_cpu(tgt_cpu, &alloced_mask) { + for_each_cpu_wrap(tgt_cpu, &alloced_mask, + outgoing_channel->target_cpu + 1) { if (tgt_cpu != outgoing_channel->target_cpu) { outgoing_channel = stor_device->stor_chns[tgt_cpu]; diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index e4f5bb056fd2..ba3cfa8e279b 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -2443,39 +2443,21 @@ struct cgr_comp { struct completion completion; }; -static int qman_delete_cgr_thread(void *p) +static void qman_delete_cgr_smp_call(void *p) { - struct cgr_comp *cgr_comp = (struct cgr_comp *)p; - int ret; - - ret = qman_delete_cgr(cgr_comp->cgr); - complete(&cgr_comp->completion); - - return ret; + qman_delete_cgr((struct qman_cgr *)p); } void qman_delete_cgr_safe(struct qman_cgr *cgr) { - struct task_struct *thread; - struct cgr_comp cgr_comp; - preempt_disable(); if (qman_cgr_cpus[cgr->cgrid] != smp_processor_id()) { - init_completion(&cgr_comp.completion); - cgr_comp.cgr = cgr; - thread = kthread_create(qman_delete_cgr_thread, &cgr_comp, - "cgr_del"); - - if (IS_ERR(thread)) - goto out; - - kthread_bind(thread, qman_cgr_cpus[cgr->cgrid]); - wake_up_process(thread); - wait_for_completion(&cgr_comp.completion); + smp_call_function_single(qman_cgr_cpus[cgr->cgrid], + qman_delete_cgr_smp_call, cgr, true); preempt_enable(); return; } -out: + qman_delete_cgr(cgr); preempt_enable(); } diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c index cfb42f5eccb2..750f93197411 100644 --- a/drivers/soc/imx/gpc.c +++ b/drivers/soc/imx/gpc.c @@ -470,13 +470,21 @@ static int imx_gpc_probe(struct platform_device *pdev) static int imx_gpc_remove(struct platform_device *pdev) { + struct device_node *pgc_node; int ret; + pgc_node = of_get_child_by_name(pdev->dev.of_node, "pgc"); + + /* bail out if DT too old and doesn't provide the necessary info */ + if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells") && + !pgc_node) + return 0; + /* * If the old DT binding is used the toplevel driver needs to * de-register the power domains */ - if (!of_get_child_by_name(pdev->dev.of_node, "pgc")) { + if (!pgc_node) { of_genpd_del_provider(pdev->dev.of_node); ret = pm_genpd_remove(&imx_gpc_domains[GPC_PGC_DOMAIN_PU].base); diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 6dbba5aff191..86580b6df33d 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -326,24 +326,23 @@ static loff_t ashmem_llseek(struct file *file, loff_t offset, int origin) mutex_lock(&ashmem_mutex); if (asma->size == 0) { - ret = -EINVAL; - goto out; + mutex_unlock(&ashmem_mutex); + return -EINVAL; } if (!asma->file) { - ret = -EBADF; - goto out; + mutex_unlock(&ashmem_mutex); + return -EBADF; } + mutex_unlock(&ashmem_mutex); + ret = vfs_llseek(asma->file, offset, origin); if (ret < 0) - goto out; + return ret; /** Copy f_pos from backing file, since f_ops->llseek() sets it */ file->f_pos = asma->file->f_pos; - -out: - mutex_unlock(&ashmem_mutex); return ret; } @@ -702,16 +701,14 @@ static int ashmem_pin_unpin(struct ashmem_area *asma, unsigned long cmd, size_t pgstart, pgend; int ret = -EINVAL; + if (unlikely(copy_from_user(&pin, p, sizeof(pin)))) + return -EFAULT; + mutex_lock(&ashmem_mutex); if (unlikely(!asma->file)) goto out_unlock; - if (unlikely(copy_from_user(&pin, p, sizeof(pin)))) { - ret = -EFAULT; - goto out_unlock; - } - /* per custom, you can pass zero for len to mean "everything onward" */ if (!pin.len) pin.len = PAGE_ALIGN(asma->size) - pin.offset; diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c index e618a87521a3..9d733471ca2e 100644 --- a/drivers/staging/comedi/drivers.c +++ b/drivers/staging/comedi/drivers.c @@ -475,8 +475,7 @@ unsigned int comedi_nsamples_left(struct comedi_subdevice *s, struct comedi_cmd *cmd = &async->cmd; if (cmd->stop_src == TRIG_COUNT) { - unsigned int nscans = nsamples / cmd->scan_end_arg; - unsigned int scans_left = __comedi_nscans_left(s, nscans); + unsigned int scans_left = __comedi_nscans_left(s, cmd->stop_arg); unsigned int scan_pos = comedi_bytes_to_samples(s, async->scan_progress); unsigned long long samples_left = 0; diff --git a/drivers/staging/ncpfs/ncplib_kernel.c b/drivers/staging/ncpfs/ncplib_kernel.c index 804adfebba2f..3e047eb4cc7c 100644 --- a/drivers/staging/ncpfs/ncplib_kernel.c +++ b/drivers/staging/ncpfs/ncplib_kernel.c @@ -981,6 +981,10 @@ ncp_read_kernel(struct ncp_server *server, const char *file_id, goto out; } *bytes_read = ncp_reply_be16(server, 0); + if (*bytes_read > to_read) { + result = -EINVAL; + goto out; + } source = ncp_reply_data(server, 2 + (offset & 1)); memcpy(target, source, *bytes_read); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 5c0e59e8fe46..cbe98bc2b998 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2180,6 +2180,12 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, } if (tty_hung_up_p(file)) break; + /* + * Abort readers for ttys which never actually + * get hung up. See __tty_hangup(). + */ + if (test_bit(TTY_HUPPING, &tty->flags)) + break; if (!timeout) break; if (file->f_flags & O_NONBLOCK) { diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 54adf8d56350..a93f77ab3da0 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -3387,11 +3387,9 @@ static int serial_pci_is_class_communication(struct pci_dev *dev) /* * If it is not a communications device or the programming * interface is greater than 6, give up. - * - * (Should we try to make guesses for multiport serial devices - * later?) */ if ((((dev->class >> 8) != PCI_CLASS_COMMUNICATION_SERIAL) && + ((dev->class >> 8) != PCI_CLASS_COMMUNICATION_MULTISERIAL) && ((dev->class >> 8) != PCI_CLASS_COMMUNICATION_MODEM)) || (dev->class & 0xff) > 6) return -ENODEV; @@ -3428,6 +3426,12 @@ serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) { int num_iomem, num_port, first_port = -1, i; + /* + * Should we try to make guesses for multiport serial devices later? + */ + if ((dev->class >> 8) == PCI_CLASS_COMMUNICATION_MULTISERIAL) + return -ENODEV; + num_iomem = num_port = 0; for (i = 0; i < PCI_NUM_BAR_RESOURCES; i++) { if (pci_resource_flags(dev, i) & IORESOURCE_IO) { @@ -4699,6 +4703,17 @@ static const struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, /* 135a.0dc0 */ pbn_b2_4_115200 }, /* + * BrainBoxes UC-260 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0D21, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00, + pbn_b2_4_115200 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0E34, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00, + pbn_b2_4_115200 }, + /* * Perle PCI-RAS cards */ { PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index df46a9e88c34..e287fe8f10fc 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -1734,6 +1734,7 @@ static void atmel_get_ip_name(struct uart_port *port) switch (version) { case 0x302: case 0x10213: + case 0x10302: dev_dbg(port->dev, "This version is usart\n"); atmel_port->has_frac_baudrate = true; atmel_port->has_hw_timer = true; diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c index 870e84fb6e39..a24278380fec 100644 --- a/drivers/tty/serial/earlycon.c +++ b/drivers/tty/serial/earlycon.c @@ -245,11 +245,12 @@ int __init of_setup_earlycon(const struct earlycon_id *match, } port->mapbase = addr; port->uartclk = BASE_BAUD * 16; - port->membase = earlycon_map(port->mapbase, SZ_4K); val = of_get_flat_dt_prop(node, "reg-offset", NULL); if (val) port->mapbase += be32_to_cpu(*val); + port->membase = earlycon_map(port->mapbase, SZ_4K); + val = of_get_flat_dt_prop(node, "reg-shift", NULL); if (val) port->regshift = be32_to_cpu(*val); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 1d7ca382bc12..a33c685af990 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2093,7 +2093,7 @@ static int serial_imx_probe(struct platform_device *pdev) uart_get_rs485_mode(&pdev->dev, &sport->port.rs485); if (sport->port.rs485.flags & SER_RS485_ENABLED && - (!sport->have_rtscts || !sport->have_rtsgpio)) + (!sport->have_rtscts && !sport->have_rtsgpio)) dev_err(&pdev->dev, "no RTS control, disabling rs485\n"); imx_rs485_config(&sport->port, &sport->port.rs485); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index c8dde56b532b..35b9201db3b4 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1144,6 +1144,8 @@ static int uart_do_autoconfig(struct tty_struct *tty,struct uart_state *state) uport->ops->config_port(uport, flags); ret = uart_startup(tty, state, 1); + if (ret == 0) + tty_port_set_initialized(port, true); if (ret > 0) ret = 0; } diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 7257c078e155..44adf9db38f8 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -885,6 +885,8 @@ static void sci_receive_chars(struct uart_port *port) /* Tell the rest of the system the news. New characters! */ tty_flip_buffer_push(tport); } else { + /* TTY buffers full; read from RX reg to prevent lockup */ + serial_port_in(port, SCxRDR); serial_port_in(port, SCxSR); /* dummy read */ sci_clear_SCxSR(port, SCxSR_RDxF_CLEAR(port)); } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index eb9133b472f4..63114ea35ec1 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -586,6 +586,14 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session) return; } + /* + * Some console devices aren't actually hung up for technical and + * historical reasons, which can lead to indefinite interruptible + * sleep in n_tty_read(). The following explicitly tells + * n_tty_read() to abort readers. + */ + set_bit(TTY_HUPPING, &tty->flags); + /* inuse_filps is protected by the single tty lock, this really needs to change if we want to flush the workqueue with the lock held */ @@ -640,6 +648,7 @@ static void __tty_hangup(struct tty_struct *tty, int exit_session) * from the ldisc side, which is now guaranteed. */ set_bit(TTY_HUPPED, &tty->flags); + clear_bit(TTY_HUPPING, &tty->flags); tty_unlock(tty); if (f) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 88b902c525d7..b4e57c5a8bba 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1727,7 +1727,7 @@ static void reset_terminal(struct vc_data *vc, int do_clear) default_attr(vc); update_attr(vc); - vc->vc_tab_stop[0] = 0x01010100; + vc->vc_tab_stop[0] = vc->vc_tab_stop[1] = vc->vc_tab_stop[2] = vc->vc_tab_stop[3] = @@ -1771,7 +1771,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) vc->vc_pos -= (vc->vc_x << 1); while (vc->vc_x < vc->vc_cols - 1) { vc->vc_x++; - if (vc->vc_tab_stop[vc->vc_x >> 5] & (1 << (vc->vc_x & 31))) + if (vc->vc_tab_stop[7 & (vc->vc_x >> 5)] & (1 << (vc->vc_x & 31))) break; } vc->vc_pos += (vc->vc_x << 1); @@ -1831,7 +1831,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) lf(vc); return; case 'H': - vc->vc_tab_stop[vc->vc_x >> 5] |= (1 << (vc->vc_x & 31)); + vc->vc_tab_stop[7 & (vc->vc_x >> 5)] |= (1 << (vc->vc_x & 31)); return; case 'Z': respond_ID(tty); @@ -2024,7 +2024,7 @@ static void do_con_trol(struct tty_struct *tty, struct vc_data *vc, int c) return; case 'g': if (!vc->vc_par[0]) - vc->vc_tab_stop[vc->vc_x >> 5] &= ~(1 << (vc->vc_x & 31)); + vc->vc_tab_stop[7 & (vc->vc_x >> 5)] &= ~(1 << (vc->vc_x & 31)); else if (vc->vc_par[0] == 3) { vc->vc_tab_stop[0] = vc->vc_tab_stop[1] = diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index c64cf6c4a83d..0c11d40a12bc 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -151,6 +151,10 @@ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, ret = usb_internal_control_msg(dev, pipe, dr, data, size, timeout); + /* Linger a bit, prior to the next control message. */ + if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) + msleep(200); + kfree(dr); return ret; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f4a548471f0f..54b019e267c5 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -230,7 +230,8 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT }, /* Corsair Strafe RGB */ - { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT | + USB_QUIRK_DELAY_CTRL_MSG }, /* Corsair K70 LUX */ { USB_DEVICE(0x1b1c, 0x1b36), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c index 03fd20f0b496..c4a47496d2fb 100644 --- a/drivers/usb/dwc2/params.c +++ b/drivers/usb/dwc2/params.c @@ -137,7 +137,7 @@ static void dwc2_set_stm32f4x9_fsotg_params(struct dwc2_hsotg *hsotg) p->activate_stm_fs_transceiver = true; } -static void dwc2_set_stm32f7xx_hsotg_params(struct dwc2_hsotg *hsotg) +static void dwc2_set_stm32f7_hsotg_params(struct dwc2_hsotg *hsotg) { struct dwc2_core_params *p = &hsotg->params; @@ -164,8 +164,8 @@ const struct of_device_id dwc2_of_match_table[] = { { .compatible = "st,stm32f4x9-fsotg", .data = dwc2_set_stm32f4x9_fsotg_params }, { .compatible = "st,stm32f4x9-hsotg" }, - { .compatible = "st,stm32f7xx-hsotg", - .data = dwc2_set_stm32f7xx_hsotg_params }, + { .compatible = "st,stm32f7-hsotg", + .data = dwc2_set_stm32f7_hsotg_params }, {}, }; MODULE_DEVICE_TABLE(of, dwc2_of_match_table); diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index f1d838a4acd6..e94bf91cc58a 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -175,7 +175,7 @@ void dwc3_set_mode(struct dwc3 *dwc, u32 mode) dwc->desired_dr_role = mode; spin_unlock_irqrestore(&dwc->lock, flags); - queue_work(system_power_efficient_wq, &dwc->drd_work); + queue_work(system_freezable_wq, &dwc->drd_work); } u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index c2592d883f67..d2428a9e8900 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1538,7 +1538,6 @@ ffs_fs_kill_sb(struct super_block *sb) if (sb->s_fs_info) { ffs_release_dev(sb->s_fs_info); ffs_data_closed(sb->s_fs_info); - ffs_data_put(sb->s_fs_info); } } diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 84f88fa411cd..d088c340e4d0 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -447,7 +447,8 @@ static int ohci_init (struct ohci_hcd *ohci) struct usb_hcd *hcd = ohci_to_hcd(ohci); /* Accept arbitrarily long scatter-gather lists */ - hcd->self.sg_tablesize = ~0; + if (!(hcd->driver->flags & HCD_LOCAL_MEM)) + hcd->self.sg_tablesize = ~0; if (distrust_firmware) ohci->flags |= OHCI_QUIRK_HUB_POWER; diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index a1ab8acf39ba..c359bae7b754 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -328,13 +328,14 @@ dbc_ep_do_queue(struct dbc_ep *dep, struct dbc_request *req) int dbc_ep_queue(struct dbc_ep *dep, struct dbc_request *req, gfp_t gfp_flags) { + unsigned long flags; struct xhci_dbc *dbc = dep->dbc; int ret = -ESHUTDOWN; - spin_lock(&dbc->lock); + spin_lock_irqsave(&dbc->lock, flags); if (dbc->state == DS_CONFIGURED) ret = dbc_ep_do_queue(dep, req); - spin_unlock(&dbc->lock); + spin_unlock_irqrestore(&dbc->lock, flags); mod_delayed_work(system_wq, &dbc->event_work, 0); @@ -521,15 +522,16 @@ static void xhci_do_dbc_stop(struct xhci_hcd *xhci) static int xhci_dbc_start(struct xhci_hcd *xhci) { int ret; + unsigned long flags; struct xhci_dbc *dbc = xhci->dbc; WARN_ON(!dbc); pm_runtime_get_sync(xhci_to_hcd(xhci)->self.controller); - spin_lock(&dbc->lock); + spin_lock_irqsave(&dbc->lock, flags); ret = xhci_do_dbc_start(xhci); - spin_unlock(&dbc->lock); + spin_unlock_irqrestore(&dbc->lock, flags); if (ret) { pm_runtime_put(xhci_to_hcd(xhci)->self.controller); @@ -541,6 +543,7 @@ static int xhci_dbc_start(struct xhci_hcd *xhci) static void xhci_dbc_stop(struct xhci_hcd *xhci) { + unsigned long flags; struct xhci_dbc *dbc = xhci->dbc; struct dbc_port *port = &dbc->port; @@ -551,9 +554,9 @@ static void xhci_dbc_stop(struct xhci_hcd *xhci) if (port->registered) xhci_dbc_tty_unregister_device(xhci); - spin_lock(&dbc->lock); + spin_lock_irqsave(&dbc->lock, flags); xhci_do_dbc_stop(xhci); - spin_unlock(&dbc->lock); + spin_unlock_irqrestore(&dbc->lock, flags); pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller); } @@ -779,14 +782,15 @@ static void xhci_dbc_handle_events(struct work_struct *work) int ret; enum evtreturn evtr; struct xhci_dbc *dbc; + unsigned long flags; struct xhci_hcd *xhci; dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work); xhci = dbc->xhci; - spin_lock(&dbc->lock); + spin_lock_irqsave(&dbc->lock, flags); evtr = xhci_dbc_do_handle_events(dbc); - spin_unlock(&dbc->lock); + spin_unlock_irqrestore(&dbc->lock, flags); switch (evtr) { case EVT_GSER: diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c index 8d47b6fbf973..75f0b92694ba 100644 --- a/drivers/usb/host/xhci-dbgtty.c +++ b/drivers/usb/host/xhci-dbgtty.c @@ -92,21 +92,23 @@ static void dbc_start_rx(struct dbc_port *port) static void dbc_read_complete(struct xhci_hcd *xhci, struct dbc_request *req) { + unsigned long flags; struct xhci_dbc *dbc = xhci->dbc; struct dbc_port *port = &dbc->port; - spin_lock(&port->port_lock); + spin_lock_irqsave(&port->port_lock, flags); list_add_tail(&req->list_pool, &port->read_queue); tasklet_schedule(&port->push); - spin_unlock(&port->port_lock); + spin_unlock_irqrestore(&port->port_lock, flags); } static void dbc_write_complete(struct xhci_hcd *xhci, struct dbc_request *req) { + unsigned long flags; struct xhci_dbc *dbc = xhci->dbc; struct dbc_port *port = &dbc->port; - spin_lock(&port->port_lock); + spin_lock_irqsave(&port->port_lock, flags); list_add(&req->list_pool, &port->write_pool); switch (req->status) { case 0: @@ -119,7 +121,7 @@ static void dbc_write_complete(struct xhci_hcd *xhci, struct dbc_request *req) req->status); break; } - spin_unlock(&port->port_lock); + spin_unlock_irqrestore(&port->port_lock, flags); } static void xhci_dbc_free_req(struct dbc_ep *dep, struct dbc_request *req) @@ -327,12 +329,13 @@ static void dbc_rx_push(unsigned long _port) { struct dbc_request *req; struct tty_struct *tty; + unsigned long flags; bool do_push = false; bool disconnect = false; struct dbc_port *port = (void *)_port; struct list_head *queue = &port->read_queue; - spin_lock_irq(&port->port_lock); + spin_lock_irqsave(&port->port_lock, flags); tty = port->port.tty; while (!list_empty(queue)) { req = list_first_entry(queue, struct dbc_request, list_pool); @@ -392,16 +395,17 @@ static void dbc_rx_push(unsigned long _port) if (!disconnect) dbc_start_rx(port); - spin_unlock_irq(&port->port_lock); + spin_unlock_irqrestore(&port->port_lock, flags); } static int dbc_port_activate(struct tty_port *_port, struct tty_struct *tty) { + unsigned long flags; struct dbc_port *port = container_of(_port, struct dbc_port, port); - spin_lock_irq(&port->port_lock); + spin_lock_irqsave(&port->port_lock, flags); dbc_start_rx(port); - spin_unlock_irq(&port->port_lock); + spin_unlock_irqrestore(&port->port_lock, flags); return 0; } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5262fa571a5d..d9f831b67e57 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -126,6 +126,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) xhci->quirks |= XHCI_AMD_PLL_FIX; + if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == 0x43bb) + xhci->quirks |= XHCI_SUSPEND_DELAY; + if (pdev->vendor == PCI_VENDOR_ID_AMD) xhci->quirks |= XHCI_TRUST_TX_LENGTH; diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 6f038306c14d..6652e2d5bd2e 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -360,7 +360,6 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev) { struct usb_hcd *hcd = dev_get_drvdata(dev); struct xhci_hcd *xhci = hcd_to_xhci(hcd); - int ret; /* * xhci_suspend() needs `do_wakeup` to know whether host is allowed @@ -370,12 +369,7 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev) * reconsider this when xhci_plat_suspend enlarges its scope, e.g., * also applies to runtime suspend. */ - ret = xhci_suspend(xhci, device_may_wakeup(dev)); - - if (!device_may_wakeup(dev) && !IS_ERR(xhci->clk)) - clk_disable_unprepare(xhci->clk); - - return ret; + return xhci_suspend(xhci, device_may_wakeup(dev)); } static int __maybe_unused xhci_plat_resume(struct device *dev) @@ -384,9 +378,6 @@ static int __maybe_unused xhci_plat_resume(struct device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); int ret; - if (!device_may_wakeup(dev) && !IS_ERR(xhci->clk)) - clk_prepare_enable(xhci->clk); - ret = xhci_priv_resume_quirk(hcd); if (ret) return ret; diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index f0b559660007..f33ffc2bc4ed 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -83,6 +83,10 @@ static const struct soc_device_attribute rcar_quirks_match[] = { .soc_id = "r8a7796", .data = (void *)RCAR_XHCI_FIRMWARE_V3, }, + { + .soc_id = "r8a77965", + .data = (void *)RCAR_XHCI_FIRMWARE_V3, + }, { /* sentinel */ }, }; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 25d4b748a56f..5d37700ae4b0 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -877,6 +877,9 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup) clear_bit(HCD_FLAG_POLL_RH, &xhci->shared_hcd->flags); del_timer_sync(&xhci->shared_hcd->rh_timer); + if (xhci->quirks & XHCI_SUSPEND_DELAY) + usleep_range(1000, 1500); + spin_lock_irq(&xhci->lock); clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags); clear_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index e4d7d3d06a75..866e141d4972 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -718,11 +718,12 @@ struct xhci_ep_ctx { /* bits 10:14 are Max Primary Streams */ /* bit 15 is Linear Stream Array */ /* Interval - period between requests to an endpoint - 125u increments. */ -#define EP_INTERVAL(p) (((p) & 0xff) << 16) -#define EP_INTERVAL_TO_UFRAMES(p) (1 << (((p) >> 16) & 0xff)) -#define CTX_TO_EP_INTERVAL(p) (((p) >> 16) & 0xff) -#define EP_MAXPSTREAMS_MASK (0x1f << 10) -#define EP_MAXPSTREAMS(p) (((p) << 10) & EP_MAXPSTREAMS_MASK) +#define EP_INTERVAL(p) (((p) & 0xff) << 16) +#define EP_INTERVAL_TO_UFRAMES(p) (1 << (((p) >> 16) & 0xff)) +#define CTX_TO_EP_INTERVAL(p) (((p) >> 16) & 0xff) +#define EP_MAXPSTREAMS_MASK (0x1f << 10) +#define EP_MAXPSTREAMS(p) (((p) << 10) & EP_MAXPSTREAMS_MASK) +#define CTX_TO_EP_MAXPSTREAMS(p) (((p) & EP_MAXPSTREAMS_MASK) >> 10) /* Endpoint is set up with a Linear Stream Array (vs. Secondary Stream Array) */ #define EP_HAS_LSA (1 << 15) /* hosts with LEC=1 use bits 31:24 as ESIT high bits. */ @@ -1825,6 +1826,7 @@ struct xhci_hcd { #define XHCI_U2_DISABLE_WAKE (1 << 27) #define XHCI_ASMEDIA_MODIFY_FLOWCONTROL (1 << 28) #define XHCI_HW_LPM_DISABLE (1 << 29) +#define XHCI_SUSPEND_DELAY (1 << 30) unsigned int num_active_eps; unsigned int limit_active_eps; @@ -2549,21 +2551,22 @@ static inline const char *xhci_decode_ep_context(u32 info, u32 info2, u64 deq, u8 burst; u8 cerr; u8 mult; - u8 lsa; - u8 hid; + + bool lsa; + bool hid; esit = CTX_TO_MAX_ESIT_PAYLOAD_HI(info) << 16 | CTX_TO_MAX_ESIT_PAYLOAD(tx_info); ep_state = info & EP_STATE_MASK; - max_pstr = info & EP_MAXPSTREAMS_MASK; + max_pstr = CTX_TO_EP_MAXPSTREAMS(info); interval = CTX_TO_EP_INTERVAL(info); mult = CTX_TO_EP_MULT(info) + 1; - lsa = info & EP_HAS_LSA; + lsa = !!(info & EP_HAS_LSA); cerr = (info2 & (3 << 1)) >> 1; ep_type = CTX_TO_EP_TYPE(info2); - hid = info2 & (1 << 7); + hid = !!(info2 & (1 << 7)); burst = CTX_TO_MAX_BURST(info2); maxp = MAX_PACKET_DECODED(info2); diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c index f5e1bb5e5217..984f7e12a6a5 100644 --- a/drivers/usb/mon/mon_text.c +++ b/drivers/usb/mon/mon_text.c @@ -85,6 +85,8 @@ struct mon_reader_text { wait_queue_head_t wait; int printf_size; + size_t printf_offset; + size_t printf_togo; char *printf_buf; struct mutex printf_lock; @@ -376,75 +378,103 @@ err_alloc: return rc; } -/* - * For simplicity, we read one record in one system call and throw out - * what does not fit. This means that the following does not work: - * dd if=/dbg/usbmon/0t bs=10 - * Also, we do not allow seeks and do not bother advancing the offset. - */ +static ssize_t mon_text_copy_to_user(struct mon_reader_text *rp, + char __user * const buf, const size_t nbytes) +{ + const size_t togo = min(nbytes, rp->printf_togo); + + if (copy_to_user(buf, &rp->printf_buf[rp->printf_offset], togo)) + return -EFAULT; + rp->printf_togo -= togo; + rp->printf_offset += togo; + return togo; +} + +/* ppos is not advanced since the llseek operation is not permitted. */ static ssize_t mon_text_read_t(struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) + size_t nbytes, loff_t *ppos) { struct mon_reader_text *rp = file->private_data; struct mon_event_text *ep; struct mon_text_ptr ptr; + ssize_t ret; - ep = mon_text_read_wait(rp, file); - if (IS_ERR(ep)) - return PTR_ERR(ep); mutex_lock(&rp->printf_lock); - ptr.cnt = 0; - ptr.pbuf = rp->printf_buf; - ptr.limit = rp->printf_size; - - mon_text_read_head_t(rp, &ptr, ep); - mon_text_read_statset(rp, &ptr, ep); - ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt, - " %d", ep->length); - mon_text_read_data(rp, &ptr, ep); - - if (copy_to_user(buf, rp->printf_buf, ptr.cnt)) - ptr.cnt = -EFAULT; + + if (rp->printf_togo == 0) { + + ep = mon_text_read_wait(rp, file); + if (IS_ERR(ep)) { + mutex_unlock(&rp->printf_lock); + return PTR_ERR(ep); + } + ptr.cnt = 0; + ptr.pbuf = rp->printf_buf; + ptr.limit = rp->printf_size; + + mon_text_read_head_t(rp, &ptr, ep); + mon_text_read_statset(rp, &ptr, ep); + ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt, + " %d", ep->length); + mon_text_read_data(rp, &ptr, ep); + + rp->printf_togo = ptr.cnt; + rp->printf_offset = 0; + + kmem_cache_free(rp->e_slab, ep); + } + + ret = mon_text_copy_to_user(rp, buf, nbytes); mutex_unlock(&rp->printf_lock); - kmem_cache_free(rp->e_slab, ep); - return ptr.cnt; + return ret; } +/* ppos is not advanced since the llseek operation is not permitted. */ static ssize_t mon_text_read_u(struct file *file, char __user *buf, - size_t nbytes, loff_t *ppos) + size_t nbytes, loff_t *ppos) { struct mon_reader_text *rp = file->private_data; struct mon_event_text *ep; struct mon_text_ptr ptr; + ssize_t ret; - ep = mon_text_read_wait(rp, file); - if (IS_ERR(ep)) - return PTR_ERR(ep); mutex_lock(&rp->printf_lock); - ptr.cnt = 0; - ptr.pbuf = rp->printf_buf; - ptr.limit = rp->printf_size; - mon_text_read_head_u(rp, &ptr, ep); - if (ep->type == 'E') { - mon_text_read_statset(rp, &ptr, ep); - } else if (ep->xfertype == USB_ENDPOINT_XFER_ISOC) { - mon_text_read_isostat(rp, &ptr, ep); - mon_text_read_isodesc(rp, &ptr, ep); - } else if (ep->xfertype == USB_ENDPOINT_XFER_INT) { - mon_text_read_intstat(rp, &ptr, ep); - } else { - mon_text_read_statset(rp, &ptr, ep); + if (rp->printf_togo == 0) { + + ep = mon_text_read_wait(rp, file); + if (IS_ERR(ep)) { + mutex_unlock(&rp->printf_lock); + return PTR_ERR(ep); + } + ptr.cnt = 0; + ptr.pbuf = rp->printf_buf; + ptr.limit = rp->printf_size; + + mon_text_read_head_u(rp, &ptr, ep); + if (ep->type == 'E') { + mon_text_read_statset(rp, &ptr, ep); + } else if (ep->xfertype == USB_ENDPOINT_XFER_ISOC) { + mon_text_read_isostat(rp, &ptr, ep); + mon_text_read_isodesc(rp, &ptr, ep); + } else if (ep->xfertype == USB_ENDPOINT_XFER_INT) { + mon_text_read_intstat(rp, &ptr, ep); + } else { + mon_text_read_statset(rp, &ptr, ep); + } + ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt, + " %d", ep->length); + mon_text_read_data(rp, &ptr, ep); + + rp->printf_togo = ptr.cnt; + rp->printf_offset = 0; + + kmem_cache_free(rp->e_slab, ep); } - ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt, - " %d", ep->length); - mon_text_read_data(rp, &ptr, ep); - if (copy_to_user(buf, rp->printf_buf, ptr.cnt)) - ptr.cnt = -EFAULT; + ret = mon_text_copy_to_user(rp, buf, nbytes); mutex_unlock(&rp->printf_lock); - kmem_cache_free(rp->e_slab, ep); - return ptr.cnt; + return ret; } static struct mon_event_text *mon_text_read_wait(struct mon_reader_text *rp, diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index eef4ad578b31..4d723077be2b 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1756,6 +1756,7 @@ vbus_show(struct device *dev, struct device_attribute *attr, char *buf) int vbus; u8 devctl; + pm_runtime_get_sync(dev); spin_lock_irqsave(&musb->lock, flags); val = musb->a_wait_bcon; vbus = musb_platform_get_vbus_status(musb); @@ -1769,6 +1770,7 @@ vbus_show(struct device *dev, struct device_attribute *attr, char *buf) vbus = 0; } spin_unlock_irqrestore(&musb->lock, flags); + pm_runtime_put_sync(dev); return sprintf(buf, "Vbus %s, timeout %lu msec\n", vbus ? "on" : "off", val); @@ -2471,11 +2473,11 @@ static int musb_remove(struct platform_device *pdev) musb_disable_interrupts(musb); musb_writeb(musb->mregs, MUSB_DEVCTL, 0); spin_unlock_irqrestore(&musb->lock, flags); + musb_platform_exit(musb); pm_runtime_dont_use_autosuspend(musb->controller); pm_runtime_put_sync(musb->controller); pm_runtime_disable(musb->controller); - musb_platform_exit(musb); musb_phy_callback = NULL; if (musb->dma_controller) musb_dma_controller_destroy(musb->dma_controller); diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 3b1b9695177a..6034c39b67d1 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -1076,7 +1076,7 @@ static int uas_post_reset(struct usb_interface *intf) return 0; err = uas_configure_endpoints(devinfo); - if (err && err != ENODEV) + if (err && err != -ENODEV) shost_printk(KERN_ERR, shost, "%s: alloc streams error %d after reset", __func__, err); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 264af199aec8..747d3a9596d9 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2118,6 +2118,13 @@ UNUSUAL_DEV( 0x152d, 0x2566, 0x0114, 0x0114, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_BROKEN_FUA ), +/* Reported by Teijo Kinnunen <teijo.kinnunen@code-q.fi> */ +UNUSUAL_DEV( 0x152d, 0x2567, 0x0117, 0x0117, + "JMicron", + "USB to ATA/ATAPI Bridge", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_BROKEN_FUA ), + /* Reported-by George Cherian <george.cherian@cavium.com> */ UNUSUAL_DEV(0x152d, 0x9561, 0x0000, 0x9999, "JMicron", diff --git a/drivers/usb/typec/fusb302/fusb302.c b/drivers/usb/typec/fusb302/fusb302.c index 9ce4756adad6..dcd8ef085b30 100644 --- a/drivers/usb/typec/fusb302/fusb302.c +++ b/drivers/usb/typec/fusb302/fusb302.c @@ -1857,7 +1857,8 @@ static int fusb302_probe(struct i2c_client *client, chip->tcpm_port = tcpm_register_port(&client->dev, &chip->tcpc_dev); if (IS_ERR(chip->tcpm_port)) { ret = PTR_ERR(chip->tcpm_port); - dev_err(dev, "cannot register tcpm port, ret=%d", ret); + if (ret != -EPROBE_DEFER) + dev_err(dev, "cannot register tcpm port, ret=%d", ret); goto destroy_workqueue; } diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c index f4d563ee7690..8b637a4b474b 100644 --- a/drivers/usb/typec/tcpm.c +++ b/drivers/usb/typec/tcpm.c @@ -252,9 +252,6 @@ struct tcpm_port { unsigned int nr_src_pdo; u32 snk_pdo[PDO_MAX_OBJECTS]; unsigned int nr_snk_pdo; - unsigned int nr_fixed; /* number of fixed sink PDOs */ - unsigned int nr_var; /* number of variable sink PDOs */ - unsigned int nr_batt; /* number of battery sink PDOs */ u32 snk_vdo[VDO_MAX_OBJECTS]; unsigned int nr_snk_vdo; @@ -1770,90 +1767,39 @@ static int tcpm_pd_check_request(struct tcpm_port *port) return 0; } -#define min_power(x, y) min(pdo_max_power(x), pdo_max_power(y)) -#define min_current(x, y) min(pdo_max_current(x), pdo_max_current(y)) - -static int tcpm_pd_select_pdo(struct tcpm_port *port, int *sink_pdo, - int *src_pdo) +static int tcpm_pd_select_pdo(struct tcpm_port *port) { - unsigned int i, j, max_mw = 0, max_mv = 0, mw = 0, mv = 0, ma = 0; + unsigned int i, max_mw = 0, max_mv = 0; int ret = -EINVAL; /* - * Select the source PDO providing the most power which has a - * matchig sink cap. + * Select the source PDO providing the most power while staying within + * the board's voltage limits. Prefer PDO providing exp */ for (i = 0; i < port->nr_source_caps; i++) { u32 pdo = port->source_caps[i]; enum pd_pdo_type type = pdo_type(pdo); + unsigned int mv, ma, mw; - if (type == PDO_TYPE_FIXED) { - for (j = 0; j < port->nr_fixed; j++) { - if (pdo_fixed_voltage(pdo) == - pdo_fixed_voltage(port->snk_pdo[j])) { - ma = min_current(pdo, port->snk_pdo[j]); - mv = pdo_fixed_voltage(pdo); - mw = ma * mv / 1000; - if (mw > max_mw || - (mw == max_mw && mv > max_mv)) { - ret = 0; - *src_pdo = i; - *sink_pdo = j; - max_mw = mw; - max_mv = mv; - } - /* There could only be one fixed pdo - * at a specific voltage level. - * So breaking here. - */ - break; - } - } - } else if (type == PDO_TYPE_BATT) { - for (j = port->nr_fixed; - j < port->nr_fixed + - port->nr_batt; - j++) { - if (pdo_min_voltage(pdo) >= - pdo_min_voltage(port->snk_pdo[j]) && - pdo_max_voltage(pdo) <= - pdo_max_voltage(port->snk_pdo[j])) { - mw = min_power(pdo, port->snk_pdo[j]); - mv = pdo_min_voltage(pdo); - if (mw > max_mw || - (mw == max_mw && mv > max_mv)) { - ret = 0; - *src_pdo = i; - *sink_pdo = j; - max_mw = mw; - max_mv = mv; - } - } - } - } else if (type == PDO_TYPE_VAR) { - for (j = port->nr_fixed + - port->nr_batt; - j < port->nr_fixed + - port->nr_batt + - port->nr_var; - j++) { - if (pdo_min_voltage(pdo) >= - pdo_min_voltage(port->snk_pdo[j]) && - pdo_max_voltage(pdo) <= - pdo_max_voltage(port->snk_pdo[j])) { - ma = min_current(pdo, port->snk_pdo[j]); - mv = pdo_min_voltage(pdo); - mw = ma * mv / 1000; - if (mw > max_mw || - (mw == max_mw && mv > max_mv)) { - ret = 0; - *src_pdo = i; - *sink_pdo = j; - max_mw = mw; - max_mv = mv; - } - } - } + if (type == PDO_TYPE_FIXED) + mv = pdo_fixed_voltage(pdo); + else + mv = pdo_min_voltage(pdo); + + if (type == PDO_TYPE_BATT) { + mw = pdo_max_power(pdo); + } else { + ma = min(pdo_max_current(pdo), + port->max_snk_ma); + mw = ma * mv / 1000; + } + + /* Perfer higher voltages if available */ + if ((mw > max_mw || (mw == max_mw && mv > max_mv)) && + mv <= port->max_snk_mv) { + ret = i; + max_mw = mw; + max_mv = mv; } } @@ -1865,14 +1811,13 @@ static int tcpm_pd_build_request(struct tcpm_port *port, u32 *rdo) unsigned int mv, ma, mw, flags; unsigned int max_ma, max_mw; enum pd_pdo_type type; - int src_pdo_index, snk_pdo_index; - u32 pdo, matching_snk_pdo; + int index; + u32 pdo; - if (tcpm_pd_select_pdo(port, &snk_pdo_index, &src_pdo_index) < 0) + index = tcpm_pd_select_pdo(port); + if (index < 0) return -EINVAL; - - pdo = port->source_caps[src_pdo_index]; - matching_snk_pdo = port->snk_pdo[snk_pdo_index]; + pdo = port->source_caps[index]; type = pdo_type(pdo); if (type == PDO_TYPE_FIXED) @@ -1880,28 +1825,26 @@ static int tcpm_pd_build_request(struct tcpm_port *port, u32 *rdo) else mv = pdo_min_voltage(pdo); - /* Select maximum available current within the sink pdo's limit */ + /* Select maximum available current within the board's power limit */ if (type == PDO_TYPE_BATT) { - mw = min_power(pdo, matching_snk_pdo); - ma = 1000 * mw / mv; + mw = pdo_max_power(pdo); + ma = 1000 * min(mw, port->max_snk_mw) / mv; } else { - ma = min_current(pdo, matching_snk_pdo); - mw = ma * mv / 1000; + ma = min(pdo_max_current(pdo), + 1000 * port->max_snk_mw / mv); } + ma = min(ma, port->max_snk_ma); flags = RDO_USB_COMM | RDO_NO_SUSPEND; /* Set mismatch bit if offered power is less than operating power */ + mw = ma * mv / 1000; max_ma = ma; max_mw = mw; if (mw < port->operating_snk_mw) { flags |= RDO_CAP_MISMATCH; - if (type == PDO_TYPE_BATT && - (pdo_max_power(matching_snk_pdo) > pdo_max_power(pdo))) - max_mw = pdo_max_power(matching_snk_pdo); - else if (pdo_max_current(matching_snk_pdo) > - pdo_max_current(pdo)) - max_ma = pdo_max_current(matching_snk_pdo); + max_mw = port->operating_snk_mw; + max_ma = max_mw * 1000 / mv; } tcpm_log(port, "cc=%d cc1=%d cc2=%d vbus=%d vconn=%s polarity=%d", @@ -1910,16 +1853,16 @@ static int tcpm_pd_build_request(struct tcpm_port *port, u32 *rdo) port->polarity); if (type == PDO_TYPE_BATT) { - *rdo = RDO_BATT(src_pdo_index + 1, mw, max_mw, flags); + *rdo = RDO_BATT(index + 1, mw, max_mw, flags); tcpm_log(port, "Requesting PDO %d: %u mV, %u mW%s", - src_pdo_index, mv, mw, + index, mv, mw, flags & RDO_CAP_MISMATCH ? " [mismatch]" : ""); } else { - *rdo = RDO_FIXED(src_pdo_index + 1, ma, max_ma, flags); + *rdo = RDO_FIXED(index + 1, ma, max_ma, flags); tcpm_log(port, "Requesting PDO %d: %u mV, %u mA%s", - src_pdo_index, mv, ma, + index, mv, ma, flags & RDO_CAP_MISMATCH ? " [mismatch]" : ""); } @@ -3650,19 +3593,6 @@ int tcpm_update_sink_capabilities(struct tcpm_port *port, const u32 *pdo, } EXPORT_SYMBOL_GPL(tcpm_update_sink_capabilities); -static int nr_type_pdos(const u32 *pdo, unsigned int nr_pdo, - enum pd_pdo_type type) -{ - int count = 0; - int i; - - for (i = 0; i < nr_pdo; i++) { - if (pdo_type(pdo[i]) == type) - count++; - } - return count; -} - struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) { struct tcpm_port *port; @@ -3708,15 +3638,6 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) tcpc->config->nr_src_pdo); port->nr_snk_pdo = tcpm_copy_pdos(port->snk_pdo, tcpc->config->snk_pdo, tcpc->config->nr_snk_pdo); - port->nr_fixed = nr_type_pdos(port->snk_pdo, - port->nr_snk_pdo, - PDO_TYPE_FIXED); - port->nr_var = nr_type_pdos(port->snk_pdo, - port->nr_snk_pdo, - PDO_TYPE_VAR); - port->nr_batt = nr_type_pdos(port->snk_pdo, - port->nr_snk_pdo, - PDO_TYPE_BATT); port->nr_snk_vdo = tcpm_copy_vdos(port->snk_vdo, tcpc->config->snk_vdo, tcpc->config->nr_snk_vdo); diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c index d86f72bbbb91..6dcd3ff655c3 100644 --- a/drivers/usb/usbip/vudc_sysfs.c +++ b/drivers/usb/usbip/vudc_sysfs.c @@ -105,10 +105,14 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a if (rv != 0) return -EINVAL; + if (!udc) { + dev_err(dev, "no device"); + return -ENODEV; + } spin_lock_irqsave(&udc->lock, flags); /* Don't export what we don't have */ - if (!udc || !udc->driver || !udc->pullup) { - dev_err(dev, "no device or gadget not bound"); + if (!udc->driver || !udc->pullup) { + dev_err(dev, "gadget not bound"); ret = -ENODEV; goto unlock; } diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index b0f759476900..8a1508a8e481 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -207,9 +207,6 @@ static bool vfio_pci_nointx(struct pci_dev *pdev) } } - if (!pdev->irq) - return true; - return false; } diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index e30e29ae4819..45657e2b1ff7 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -338,11 +338,12 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, { struct page *page[1]; struct vm_area_struct *vma; + struct vm_area_struct *vmas[1]; int ret; if (mm == current->mm) { - ret = get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE), - page); + ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE), + page, vmas); } else { unsigned int flags = 0; @@ -351,7 +352,18 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, down_read(&mm->mmap_sem); ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page, - NULL, NULL); + vmas, NULL); + /* + * The lifetime of a vaddr_get_pfn() page pin is + * userspace-controlled. In the fs-dax case this could + * lead to indefinite stalls in filesystem operations. + * Disallow attempts to pin fs-dax pages via this + * interface. + */ + if (ret > 0 && vma_is_fsdax(vmas[0])) { + ret = -EOPNOTSUPP; + put_page(page[0]); + } up_read(&mm->mmap_sem); } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 610cba276d47..8139bc70ad7d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -170,7 +170,7 @@ static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq) if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) { ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head, vhost_net_buf_get_size(rxq), - __skb_array_destroy_skb); + tun_ptr_free); rxq->head = rxq->tail = 0; } } @@ -948,6 +948,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].done_idx = 0; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; + n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); @@ -972,6 +973,7 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n, vhost_net_disable_vq(n, vq); vq->private_data = NULL; vhost_net_buf_unproduce(nvq); + nvq->rx_ring = NULL; mutex_unlock(&vq->mutex); return sock; } @@ -1161,14 +1163,14 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) vhost_net_disable_vq(n, vq); vq->private_data = sock; vhost_net_buf_unproduce(nvq); - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); r = vhost_vq_init_access(vq); if (r) goto err_used; r = vhost_net_enable_vq(n, vq); if (r) goto err_used; + if (index == VHOST_NET_VQ_RX) + nvq->rx_ring = get_tap_ptr_ring(fd); oldubufs = nvq->ubufs; nvq->ubufs = ubufs; diff --git a/drivers/video/fbdev/sbuslib.c b/drivers/video/fbdev/sbuslib.c index af6fc97f4ba4..a436d44f1b7f 100644 --- a/drivers/video/fbdev/sbuslib.c +++ b/drivers/video/fbdev/sbuslib.c @@ -122,7 +122,7 @@ int sbusfb_ioctl_helper(unsigned long cmd, unsigned long arg, unsigned char __user *ured; unsigned char __user *ugreen; unsigned char __user *ublue; - int index, count, i; + unsigned int index, count, i; if (get_user(index, &c->index) || __get_user(count, &c->count) || @@ -161,7 +161,7 @@ int sbusfb_ioctl_helper(unsigned long cmd, unsigned long arg, unsigned char __user *ugreen; unsigned char __user *ublue; struct fb_cmap *cmap = &info->cmap; - int index, count, i; + unsigned int index, count, i; u8 red, green, blue; if (get_user(index, &c->index) || diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index eb30f3e09a47..71458f493cf8 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -428,8 +428,6 @@ unmap_release: i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next); } - vq->vq.num_free += total_sg; - if (indirect) kfree(desc); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index aff773bcebdb..37460cd6cabb 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -226,6 +226,7 @@ config ZIIRAVE_WATCHDOG config RAVE_SP_WATCHDOG tristate "RAVE SP Watchdog timer" depends on RAVE_SP_CORE + depends on NVMEM || !NVMEM select WATCHDOG_CORE help Support for the watchdog on RAVE SP device. @@ -903,6 +904,7 @@ config F71808E_WDT config SP5100_TCO tristate "AMD/ATI SP5100 TCO Timer/Watchdog" depends on X86 && PCI + select WATCHDOG_CORE ---help--- Hardware watchdog driver for the AMD/ATI SP5100 chipset. The TCO (Total Cost of Ownership) timer is a watchdog timer that will reboot @@ -1008,6 +1010,7 @@ config WAFER_WDT config I6300ESB_WDT tristate "Intel 6300ESB Timer/Watchdog" depends on PCI + select WATCHDOG_CORE ---help--- Hardware driver for the watchdog timer built into the Intel 6300ESB controller hub. @@ -1837,6 +1840,7 @@ config WATCHDOG_SUN4V config XEN_WDT tristate "Xen Watchdog support" depends on XEN + select WATCHDOG_CORE help Say Y here to support the hypervisor watchdog capability provided by Xen 4.0 and newer. The watchdog timeout period is normally one diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index e0678c14480f..3a33c5344bd5 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -566,7 +566,8 @@ static ssize_t watchdog_write(struct file *file, const char __user *buf, char c; if (get_user(c, buf + i)) return -EFAULT; - expect_close = (c == 'V'); + if (c == 'V') + expect_close = true; } /* Properly order writes across fork()ed processes */ diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index f1f00dfc0e68..b0a158073abd 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -28,16 +28,7 @@ #include <linux/types.h> #include <linux/uaccess.h> #include <linux/watchdog.h> -#ifdef CONFIG_HPWDT_NMI_DECODING -#include <linux/dmi.h> -#include <linux/spinlock.h> -#include <linux/nmi.h> -#include <linux/kdebug.h> -#include <linux/notifier.h> -#include <asm/set_memory.h> -#endif /* CONFIG_HPWDT_NMI_DECODING */ #include <asm/nmi.h> -#include <asm/frame.h> #define HPWDT_VERSION "1.4.0" #define SECS_TO_TICKS(secs) ((secs) * 1000 / 128) @@ -48,6 +39,9 @@ static unsigned int soft_margin = DEFAULT_MARGIN; /* in seconds */ static unsigned int reload; /* the computed soft_margin */ static bool nowayout = WATCHDOG_NOWAYOUT; +#ifdef CONFIG_HPWDT_NMI_DECODING +static unsigned int allow_kdump = 1; +#endif static char expect_release; static unsigned long hpwdt_is_open; @@ -63,373 +57,6 @@ static const struct pci_device_id hpwdt_devices[] = { }; MODULE_DEVICE_TABLE(pci, hpwdt_devices); -#ifdef CONFIG_HPWDT_NMI_DECODING -#define PCI_BIOS32_SD_VALUE 0x5F32335F /* "_32_" */ -#define CRU_BIOS_SIGNATURE_VALUE 0x55524324 -#define PCI_BIOS32_PARAGRAPH_LEN 16 -#define PCI_ROM_BASE1 0x000F0000 -#define ROM_SIZE 0x10000 - -struct bios32_service_dir { - u32 signature; - u32 entry_point; - u8 revision; - u8 length; - u8 checksum; - u8 reserved[5]; -}; - -/* type 212 */ -struct smbios_cru64_info { - u8 type; - u8 byte_length; - u16 handle; - u32 signature; - u64 physical_address; - u32 double_length; - u32 double_offset; -}; -#define SMBIOS_CRU64_INFORMATION 212 - -/* type 219 */ -struct smbios_proliant_info { - u8 type; - u8 byte_length; - u16 handle; - u32 power_features; - u32 omega_features; - u32 reserved; - u32 misc_features; -}; -#define SMBIOS_ICRU_INFORMATION 219 - - -struct cmn_registers { - union { - struct { - u8 ral; - u8 rah; - u16 rea2; - }; - u32 reax; - } u1; - union { - struct { - u8 rbl; - u8 rbh; - u8 reb2l; - u8 reb2h; - }; - u32 rebx; - } u2; - union { - struct { - u8 rcl; - u8 rch; - u16 rec2; - }; - u32 recx; - } u3; - union { - struct { - u8 rdl; - u8 rdh; - u16 red2; - }; - u32 redx; - } u4; - - u32 resi; - u32 redi; - u16 rds; - u16 res; - u32 reflags; -} __attribute__((packed)); - -static unsigned int hpwdt_nmi_decoding; -static unsigned int allow_kdump = 1; -static unsigned int is_icru; -static unsigned int is_uefi; -static DEFINE_SPINLOCK(rom_lock); -static void *cru_rom_addr; -static struct cmn_registers cmn_regs; - -extern asmlinkage void asminline_call(struct cmn_registers *pi86Regs, - unsigned long *pRomEntry); - -#ifdef CONFIG_X86_32 -/* --32 Bit Bios------------------------------------------------------------ */ - -#define HPWDT_ARCH 32 - -asm(".text \n\t" - ".align 4 \n\t" - ".globl asminline_call \n" - "asminline_call: \n\t" - "pushl %ebp \n\t" - "movl %esp, %ebp \n\t" - "pusha \n\t" - "pushf \n\t" - "push %es \n\t" - "push %ds \n\t" - "pop %es \n\t" - "movl 8(%ebp),%eax \n\t" - "movl 4(%eax),%ebx \n\t" - "movl 8(%eax),%ecx \n\t" - "movl 12(%eax),%edx \n\t" - "movl 16(%eax),%esi \n\t" - "movl 20(%eax),%edi \n\t" - "movl (%eax),%eax \n\t" - "push %cs \n\t" - "call *12(%ebp) \n\t" - "pushf \n\t" - "pushl %eax \n\t" - "movl 8(%ebp),%eax \n\t" - "movl %ebx,4(%eax) \n\t" - "movl %ecx,8(%eax) \n\t" - "movl %edx,12(%eax) \n\t" - "movl %esi,16(%eax) \n\t" - "movl %edi,20(%eax) \n\t" - "movw %ds,24(%eax) \n\t" - "movw %es,26(%eax) \n\t" - "popl %ebx \n\t" - "movl %ebx,(%eax) \n\t" - "popl %ebx \n\t" - "movl %ebx,28(%eax) \n\t" - "pop %es \n\t" - "popf \n\t" - "popa \n\t" - "leave \n\t" - "ret \n\t" - ".previous"); - - -/* - * cru_detect - * - * Routine Description: - * This function uses the 32-bit BIOS Service Directory record to - * search for a $CRU record. - * - * Return Value: - * 0 : SUCCESS - * <0 : FAILURE - */ -static int cru_detect(unsigned long map_entry, - unsigned long map_offset) -{ - void *bios32_map; - unsigned long *bios32_entrypoint; - unsigned long cru_physical_address; - unsigned long cru_length; - unsigned long physical_bios_base = 0; - unsigned long physical_bios_offset = 0; - int retval = -ENODEV; - - bios32_map = ioremap(map_entry, (2 * PAGE_SIZE)); - - if (bios32_map == NULL) - return -ENODEV; - - bios32_entrypoint = bios32_map + map_offset; - - cmn_regs.u1.reax = CRU_BIOS_SIGNATURE_VALUE; - - set_memory_x((unsigned long)bios32_map, 2); - asminline_call(&cmn_regs, bios32_entrypoint); - - if (cmn_regs.u1.ral != 0) { - pr_warn("Call succeeded but with an error: 0x%x\n", - cmn_regs.u1.ral); - } else { - physical_bios_base = cmn_regs.u2.rebx; - physical_bios_offset = cmn_regs.u4.redx; - cru_length = cmn_regs.u3.recx; - cru_physical_address = - physical_bios_base + physical_bios_offset; - - /* If the values look OK, then map it in. */ - if ((physical_bios_base + physical_bios_offset)) { - cru_rom_addr = - ioremap(cru_physical_address, cru_length); - if (cru_rom_addr) { - set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK, - (cru_length + PAGE_SIZE - 1) >> PAGE_SHIFT); - retval = 0; - } - } - - pr_debug("CRU Base Address: 0x%lx\n", physical_bios_base); - pr_debug("CRU Offset Address: 0x%lx\n", physical_bios_offset); - pr_debug("CRU Length: 0x%lx\n", cru_length); - pr_debug("CRU Mapped Address: %p\n", &cru_rom_addr); - } - iounmap(bios32_map); - return retval; -} - -/* - * bios_checksum - */ -static int bios_checksum(const char __iomem *ptr, int len) -{ - char sum = 0; - int i; - - /* - * calculate checksum of size bytes. This should add up - * to zero if we have a valid header. - */ - for (i = 0; i < len; i++) - sum += ptr[i]; - - return ((sum == 0) && (len > 0)); -} - -/* - * bios32_present - * - * Routine Description: - * This function finds the 32-bit BIOS Service Directory - * - * Return Value: - * 0 : SUCCESS - * <0 : FAILURE - */ -static int bios32_present(const char __iomem *p) -{ - struct bios32_service_dir *bios_32_ptr; - int length; - unsigned long map_entry, map_offset; - - bios_32_ptr = (struct bios32_service_dir *) p; - - /* - * Search for signature by checking equal to the swizzled value - * instead of calling another routine to perform a strcmp. - */ - if (bios_32_ptr->signature == PCI_BIOS32_SD_VALUE) { - length = bios_32_ptr->length * PCI_BIOS32_PARAGRAPH_LEN; - if (bios_checksum(p, length)) { - /* - * According to the spec, we're looking for the - * first 4KB-aligned address below the entrypoint - * listed in the header. The Service Directory code - * is guaranteed to occupy no more than 2 4KB pages. - */ - map_entry = bios_32_ptr->entry_point & ~(PAGE_SIZE - 1); - map_offset = bios_32_ptr->entry_point - map_entry; - - return cru_detect(map_entry, map_offset); - } - } - return -ENODEV; -} - -static int detect_cru_service(void) -{ - char __iomem *p, *q; - int rc = -1; - - /* - * Search from 0x0f0000 through 0x0fffff, inclusive. - */ - p = ioremap(PCI_ROM_BASE1, ROM_SIZE); - if (p == NULL) - return -ENOMEM; - - for (q = p; q < p + ROM_SIZE; q += 16) { - rc = bios32_present(q); - if (!rc) - break; - } - iounmap(p); - return rc; -} -/* ------------------------------------------------------------------------- */ -#endif /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_64 -/* --64 Bit Bios------------------------------------------------------------ */ - -#define HPWDT_ARCH 64 - -asm(".text \n\t" - ".align 4 \n\t" - ".globl asminline_call \n\t" - ".type asminline_call, @function \n\t" - "asminline_call: \n\t" - FRAME_BEGIN - "pushq %rax \n\t" - "pushq %rbx \n\t" - "pushq %rdx \n\t" - "pushq %r12 \n\t" - "pushq %r9 \n\t" - "movq %rsi, %r12 \n\t" - "movq %rdi, %r9 \n\t" - "movl 4(%r9),%ebx \n\t" - "movl 8(%r9),%ecx \n\t" - "movl 12(%r9),%edx \n\t" - "movl 16(%r9),%esi \n\t" - "movl 20(%r9),%edi \n\t" - "movl (%r9),%eax \n\t" - "call *%r12 \n\t" - "pushfq \n\t" - "popq %r12 \n\t" - "movl %eax, (%r9) \n\t" - "movl %ebx, 4(%r9) \n\t" - "movl %ecx, 8(%r9) \n\t" - "movl %edx, 12(%r9) \n\t" - "movl %esi, 16(%r9) \n\t" - "movl %edi, 20(%r9) \n\t" - "movq %r12, %rax \n\t" - "movl %eax, 28(%r9) \n\t" - "popq %r9 \n\t" - "popq %r12 \n\t" - "popq %rdx \n\t" - "popq %rbx \n\t" - "popq %rax \n\t" - FRAME_END - "ret \n\t" - ".previous"); - -/* - * dmi_find_cru - * - * Routine Description: - * This function checks whether or not a SMBIOS/DMI record is - * the 64bit CRU info or not - */ -static void dmi_find_cru(const struct dmi_header *dm, void *dummy) -{ - struct smbios_cru64_info *smbios_cru64_ptr; - unsigned long cru_physical_address; - - if (dm->type == SMBIOS_CRU64_INFORMATION) { - smbios_cru64_ptr = (struct smbios_cru64_info *) dm; - if (smbios_cru64_ptr->signature == CRU_BIOS_SIGNATURE_VALUE) { - cru_physical_address = - smbios_cru64_ptr->physical_address + - smbios_cru64_ptr->double_offset; - cru_rom_addr = ioremap(cru_physical_address, - smbios_cru64_ptr->double_length); - set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK, - smbios_cru64_ptr->double_length >> PAGE_SHIFT); - } - } -} - -static int detect_cru_service(void) -{ - cru_rom_addr = NULL; - - dmi_walk(dmi_find_cru, NULL); - - /* if cru_rom_addr has been set then we found a CRU service */ - return ((cru_rom_addr != NULL) ? 0 : -ENODEV); -} -/* ------------------------------------------------------------------------- */ -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_HPWDT_NMI_DECODING */ /* * Watchdog operations @@ -486,30 +113,12 @@ static int hpwdt_my_nmi(void) */ static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs) { - unsigned long rom_pl; - static int die_nmi_called; - - if (!hpwdt_nmi_decoding) - return NMI_DONE; - if ((ulReason == NMI_UNKNOWN) && !hpwdt_my_nmi()) return NMI_DONE; - spin_lock_irqsave(&rom_lock, rom_pl); - if (!die_nmi_called && !is_icru && !is_uefi) - asminline_call(&cmn_regs, cru_rom_addr); - die_nmi_called = 1; - spin_unlock_irqrestore(&rom_lock, rom_pl); - if (allow_kdump) hpwdt_stop(); - if (!is_icru && !is_uefi) { - if (cmn_regs.u1.ral == 0) { - nmi_panic(regs, "An NMI occurred, but unable to determine source.\n"); - return NMI_HANDLED; - } - } nmi_panic(regs, "An NMI occurred. Depending on your system the reason " "for the NMI is logged in any one of the following " "resources:\n" @@ -675,84 +284,11 @@ static struct miscdevice hpwdt_miscdev = { * Init & Exit */ -#ifdef CONFIG_HPWDT_NMI_DECODING -#ifdef CONFIG_X86_LOCAL_APIC -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ - /* - * If nmi_watchdog is turned off then we can turn on - * our nmi decoding capability. - */ - hpwdt_nmi_decoding = 1; -} -#else -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ - dev_warn(&dev->dev, "NMI decoding is disabled. " - "Your kernel does not support a NMI Watchdog.\n"); -} -#endif /* CONFIG_X86_LOCAL_APIC */ - -/* - * dmi_find_icru - * - * Routine Description: - * This function checks whether or not we are on an iCRU-based server. - * This check is independent of architecture and needs to be made for - * any ProLiant system. - */ -static void dmi_find_icru(const struct dmi_header *dm, void *dummy) -{ - struct smbios_proliant_info *smbios_proliant_ptr; - - if (dm->type == SMBIOS_ICRU_INFORMATION) { - smbios_proliant_ptr = (struct smbios_proliant_info *) dm; - if (smbios_proliant_ptr->misc_features & 0x01) - is_icru = 1; - if (smbios_proliant_ptr->misc_features & 0x1400) - is_uefi = 1; - } -} static int hpwdt_init_nmi_decoding(struct pci_dev *dev) { +#ifdef CONFIG_HPWDT_NMI_DECODING int retval; - - /* - * On typical CRU-based systems we need to map that service in - * the BIOS. For 32 bit Operating Systems we need to go through - * the 32 Bit BIOS Service Directory. For 64 bit Operating - * Systems we get that service through SMBIOS. - * - * On systems that support the new iCRU service all we need to - * do is call dmi_walk to get the supported flag value and skip - * the old cru detect code. - */ - dmi_walk(dmi_find_icru, NULL); - if (!is_icru && !is_uefi) { - - /* - * We need to map the ROM to get the CRU service. - * For 32 bit Operating Systems we need to go through the 32 Bit - * BIOS Service Directory - * For 64 bit Operating Systems we get that service through SMBIOS. - */ - retval = detect_cru_service(); - if (retval < 0) { - dev_warn(&dev->dev, - "Unable to detect the %d Bit CRU Service.\n", - HPWDT_ARCH); - return retval; - } - - /* - * We know this is the only CRU call we need to make so lets keep as - * few instructions as possible once the NMI comes in. - */ - cmn_regs.u1.rah = 0x0D; - cmn_regs.u1.ral = 0x02; - } - /* * Only one function can register for NMI_UNKNOWN */ @@ -780,45 +316,26 @@ error: dev_warn(&dev->dev, "Unable to register a die notifier (err=%d).\n", retval); - if (cru_rom_addr) - iounmap(cru_rom_addr); return retval; +#endif /* CONFIG_HPWDT_NMI_DECODING */ + return 0; } static void hpwdt_exit_nmi_decoding(void) { +#ifdef CONFIG_HPWDT_NMI_DECODING unregister_nmi_handler(NMI_UNKNOWN, "hpwdt"); unregister_nmi_handler(NMI_SERR, "hpwdt"); unregister_nmi_handler(NMI_IO_CHECK, "hpwdt"); - if (cru_rom_addr) - iounmap(cru_rom_addr); -} -#else /* !CONFIG_HPWDT_NMI_DECODING */ -static void hpwdt_check_nmi_decoding(struct pci_dev *dev) -{ -} - -static int hpwdt_init_nmi_decoding(struct pci_dev *dev) -{ - return 0; +#endif } -static void hpwdt_exit_nmi_decoding(void) -{ -} -#endif /* CONFIG_HPWDT_NMI_DECODING */ - static int hpwdt_init_one(struct pci_dev *dev, const struct pci_device_id *ent) { int retval; /* - * Check if we can do NMI decoding or not - */ - hpwdt_check_nmi_decoding(dev); - - /* * First let's find out if we are on an iLO2+ server. We will * not run on a legacy ASM box. * So we only support the G5 ProLiant servers and higher. @@ -922,6 +439,6 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" #ifdef CONFIG_HPWDT_NMI_DECODING module_param(allow_kdump, int, 0); MODULE_PARM_DESC(allow_kdump, "Start a kernel dump after NMI occurs"); -#endif /* !CONFIG_HPWDT_NMI_DECODING */ +#endif /* CONFIG_HPWDT_NMI_DECODING */ module_pci_driver(hpwdt_driver); diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index 316c2eb122d2..e8bd9887c566 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -50,6 +50,7 @@ */ #include <linux/io.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -159,7 +160,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd) !(readl(gwdt->control_base + SBSA_GWDT_WCS) & SBSA_GWDT_WCS_WS0)) timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR); - timeleft += readq(gwdt->control_base + SBSA_GWDT_WCV) - + timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) - arch_counter_get_cntvct(); do_div(timeleft, gwdt->clk); diff --git a/drivers/watchdog/wdat_wdt.c b/drivers/watchdog/wdat_wdt.c index 6d1fbda0f461..0da9943d405f 100644 --- a/drivers/watchdog/wdat_wdt.c +++ b/drivers/watchdog/wdat_wdt.c @@ -392,7 +392,7 @@ static int wdat_wdt_probe(struct platform_device *pdev) memset(&r, 0, sizeof(r)); r.start = gas->address; - r.end = r.start + gas->access_width; + r.end = r.start + gas->access_width - 1; if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { r.flags = IORESOURCE_MEM; } else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 1ab4bd11f5f3..762378f1811c 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -755,8 +755,8 @@ out: mutex_unlock(&irq_mapping_update_lock); return irq; error_irq: - for (; i >= 0; i--) - __unbind_from_irq(irq + i); + while (nvec--) + __unbind_from_irq(irq + nvec); mutex_unlock(&irq_mapping_update_lock); return ret; } diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 156e5aea36db..b1092fbefa63 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -416,7 +416,7 @@ static int pvcalls_back_connect(struct xenbus_device *dev, sock); if (!map) { ret = -EFAULT; - sock_release(map->sock); + sock_release(sock); } out: diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index aedbee3b2838..2f11ca72a281 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -73,20 +73,25 @@ struct sock_mapping { wait_queue_head_t inflight_conn_req; } active; struct { - /* Socket status */ + /* + * Socket status, needs to be 64-bit aligned due to the + * test_and_* functions which have this requirement on arm64. + */ #define PVCALLS_STATUS_UNINITALIZED 0 #define PVCALLS_STATUS_BIND 1 #define PVCALLS_STATUS_LISTEN 2 - uint8_t status; + uint8_t status __attribute__((aligned(8))); /* * Internal state-machine flags. * Only one accept operation can be inflight for a socket. * Only one poll operation can be inflight for a given socket. + * flags needs to be 64-bit aligned due to the test_and_* + * functions which have this requirement on arm64. */ #define PVCALLS_FLAG_ACCEPT_INFLIGHT 0 #define PVCALLS_FLAG_POLL_INFLIGHT 1 #define PVCALLS_FLAG_POLL_RET 2 - uint8_t flags; + uint8_t flags __attribute__((aligned(8))); uint32_t inflight_req_id; struct sock_mapping *accept_map; wait_queue_head_t inflight_accept_req; diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 74888cacd0b0..ec9eb4fba59c 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -466,8 +466,11 @@ int xenbus_probe_node(struct xen_bus_type *bus, /* Register with generic device framework. */ err = device_register(&xendev->dev); - if (err) + if (err) { + put_device(&xendev->dev); + xendev = NULL; goto fail; + } return 0; fail: @@ -68,9 +68,9 @@ struct aio_ring { #define AIO_RING_PAGES 8 struct kioctx_table { - struct rcu_head rcu; - unsigned nr; - struct kioctx *table[]; + struct rcu_head rcu; + unsigned nr; + struct kioctx __rcu *table[]; }; struct kioctx_cpu { @@ -115,7 +115,8 @@ struct kioctx { struct page **ring_pages; long nr_pages; - struct work_struct free_work; + struct rcu_head free_rcu; + struct work_struct free_work; /* see free_ioctx() */ /* * signals when all in-flight requests are done @@ -329,7 +330,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) for (i = 0; i < table->nr; i++) { struct kioctx *ctx; - ctx = table->table[i]; + ctx = rcu_dereference(table->table[i]); if (ctx && ctx->aio_ring_file == file) { if (!atomic_read(&ctx->dead)) { ctx->user_id = ctx->mmap_base = vma->vm_start; @@ -588,6 +589,12 @@ static int kiocb_cancel(struct aio_kiocb *kiocb) return cancel(&kiocb->common); } +/* + * free_ioctx() should be RCU delayed to synchronize against the RCU + * protected lookup_ioctx() and also needs process context to call + * aio_free_ring(), so the double bouncing through kioctx->free_rcu and + * ->free_work. + */ static void free_ioctx(struct work_struct *work) { struct kioctx *ctx = container_of(work, struct kioctx, free_work); @@ -601,6 +608,14 @@ static void free_ioctx(struct work_struct *work) kmem_cache_free(kioctx_cachep, ctx); } +static void free_ioctx_rcufn(struct rcu_head *head) +{ + struct kioctx *ctx = container_of(head, struct kioctx, free_rcu); + + INIT_WORK(&ctx->free_work, free_ioctx); + schedule_work(&ctx->free_work); +} + static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); @@ -609,8 +624,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref) if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) complete(&ctx->rq_wait->comp); - INIT_WORK(&ctx->free_work, free_ioctx); - schedule_work(&ctx->free_work); + /* Synchronize against RCU protected table->table[] dereferences */ + call_rcu(&ctx->free_rcu, free_ioctx_rcufn); } /* @@ -651,9 +666,9 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) while (1) { if (table) for (i = 0; i < table->nr; i++) - if (!table->table[i]) { + if (!rcu_access_pointer(table->table[i])) { ctx->id = i; - table->table[i] = ctx; + rcu_assign_pointer(table->table[i], ctx); spin_unlock(&mm->ioctx_lock); /* While kioctx setup is in progress, @@ -834,11 +849,11 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, } table = rcu_dereference_raw(mm->ioctx_table); - WARN_ON(ctx != table->table[ctx->id]); - table->table[ctx->id] = NULL; + WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id])); + RCU_INIT_POINTER(table->table[ctx->id], NULL); spin_unlock(&mm->ioctx_lock); - /* percpu_ref_kill() will do the necessary call_rcu() */ + /* free_ioctx_reqs() will do the necessary RCU synchronization */ wake_up_all(&ctx->wait); /* @@ -880,7 +895,8 @@ void exit_aio(struct mm_struct *mm) skipped = 0; for (i = 0; i < table->nr; ++i) { - struct kioctx *ctx = table->table[i]; + struct kioctx *ctx = + rcu_dereference_protected(table->table[i], true); if (!ctx) { skipped++; @@ -1069,7 +1085,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) if (!table || id >= table->nr) goto out; - ctx = table->table[id]; + ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { percpu_ref_get(&ctx->users); ret = ctx; diff --git a/fs/block_dev.c b/fs/block_dev.c index 4a181fcb5175..fe09ef9c21f3 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1058,6 +1058,27 @@ retry: return 0; } +static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) +{ + struct gendisk *disk = get_gendisk(bdev->bd_dev, partno); + + if (!disk) + return NULL; + /* + * Now that we hold gendisk reference we make sure bdev we looked up is + * not stale. If it is, it means device got removed and created before + * we looked up gendisk and we fail open in such case. Associating + * unhashed bdev with newly created gendisk could lead to two bdevs + * (and thus two independent caches) being associated with one device + * which is bad. + */ + if (inode_unhashed(bdev->bd_inode)) { + put_disk_and_module(disk); + return NULL; + } + return disk; +} + /** * bd_start_claiming - start claiming a block device * @bdev: block device of interest @@ -1094,7 +1115,7 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, * @bdev might not have been initialized properly yet, look up * and grab the outer block device the hard way. */ - disk = get_gendisk(bdev->bd_dev, &partno); + disk = bdev_get_gendisk(bdev, &partno); if (!disk) return ERR_PTR(-ENXIO); @@ -1111,8 +1132,7 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, else whole = bdgrab(bdev); - module_put(disk->fops->owner); - put_disk(disk); + put_disk_and_module(disk); if (!whole) return ERR_PTR(-ENOMEM); @@ -1407,10 +1427,10 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) { struct gendisk *disk; - struct module *owner; int ret; int partno; int perm = 0; + bool first_open = false; if (mode & FMODE_READ) perm |= MAY_READ; @@ -1430,14 +1450,14 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) restart: ret = -ENXIO; - disk = get_gendisk(bdev->bd_dev, &partno); + disk = bdev_get_gendisk(bdev, &partno); if (!disk) goto out; - owner = disk->fops->owner; disk_block_events(disk); mutex_lock_nested(&bdev->bd_mutex, for_part); if (!bdev->bd_openers) { + first_open = true; bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; @@ -1463,8 +1483,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_queue = NULL; mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); - put_disk(disk); - module_put(owner); + put_disk_and_module(disk); goto restart; } } @@ -1524,15 +1543,15 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (ret) goto out_unlock_bdev; } - /* only one opener holds refs to the module and disk */ - put_disk(disk); - module_put(owner); } bdev->bd_openers++; if (for_part) bdev->bd_part_count++; mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); + /* only one opener holds refs to the module and disk */ + if (!first_open) + put_disk_and_module(disk); return 0; out_clear: @@ -1546,8 +1565,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) out_unlock_bdev: mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); - put_disk(disk); - module_put(owner); + put_disk_and_module(disk); out: bdput(bdev); @@ -1770,8 +1788,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) disk->fops->release(disk, mode); } if (!bdev->bd_openers) { - struct module *owner = disk->fops->owner; - disk_put_part(bdev->bd_part); bdev->bd_part = NULL; bdev->bd_disk = NULL; @@ -1779,8 +1795,7 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) victim = bdev->bd_contains; bdev->bd_contains = NULL; - put_disk(disk); - module_put(owner); + put_disk_and_module(disk); } mutex_unlock(&bdev->bd_mutex); bdput(bdev); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f94b2d8c744a..26484648d090 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1519,6 +1519,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) if (!node) break; bytenr = node->val; + shared.share_count = 0; cond_resched(); } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1a462ab85c49..da308774b8a4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2974,7 +2974,7 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info) kfree(fs_info->super_copy); kfree(fs_info->super_for_commit); security_free_mnt_opts(&fs_info->security_opts); - kfree(fs_info); + kvfree(fs_info); } /* tree mod log functions from ctree.c */ @@ -3095,7 +3095,10 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, u64 inode_objectid, u64 ref_objectid, int ins_len, int cow); -int btrfs_find_name_in_ext_backref(struct btrfs_path *path, +int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot, + const char *name, + int name_len, struct btrfs_inode_ref **ref_ret); +int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot, u64 ref_objectid, const char *name, int name_len, struct btrfs_inode_extref **extref_ret); diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 39c968f80157..65e1a76bf755 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -22,10 +22,10 @@ #include "transaction.h" #include "print-tree.h" -static int find_name_in_backref(struct btrfs_path *path, const char *name, - int name_len, struct btrfs_inode_ref **ref_ret) +int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot, + const char *name, + int name_len, struct btrfs_inode_ref **ref_ret) { - struct extent_buffer *leaf; struct btrfs_inode_ref *ref; unsigned long ptr; unsigned long name_ptr; @@ -33,9 +33,8 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name, u32 cur_offset = 0; int len; - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, path->slots[0]); - ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); + item_size = btrfs_item_size_nr(leaf, slot); + ptr = btrfs_item_ptr_offset(leaf, slot); while (cur_offset < item_size) { ref = (struct btrfs_inode_ref *)(ptr + cur_offset); len = btrfs_inode_ref_name_len(leaf, ref); @@ -44,18 +43,19 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name, if (len != name_len) continue; if (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) { - *ref_ret = ref; + if (ref_ret) + *ref_ret = ref; return 1; } } return 0; } -int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid, +int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot, + u64 ref_objectid, const char *name, int name_len, struct btrfs_inode_extref **extref_ret) { - struct extent_buffer *leaf; struct btrfs_inode_extref *extref; unsigned long ptr; unsigned long name_ptr; @@ -63,9 +63,8 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid, u32 cur_offset = 0; int ref_name_len; - leaf = path->nodes[0]; - item_size = btrfs_item_size_nr(leaf, path->slots[0]); - ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); + item_size = btrfs_item_size_nr(leaf, slot); + ptr = btrfs_item_ptr_offset(leaf, slot); /* * Search all extended backrefs in this item. We're only @@ -113,7 +112,9 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans, return ERR_PTR(ret); if (ret > 0) return NULL; - if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref)) + if (!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], + ref_objectid, name, name_len, + &extref)) return NULL; return extref; } @@ -155,7 +156,8 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, * This should always succeed so error here will make the FS * readonly. */ - if (!btrfs_find_name_in_ext_backref(path, ref_objectid, + if (!btrfs_find_name_in_ext_backref(path->nodes[0], path->slots[0], + ref_objectid, name, name_len, &extref)) { btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL); ret = -EROFS; @@ -225,7 +227,8 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, } else if (ret < 0) { goto out; } - if (!find_name_in_backref(path, name, name_len, &ref)) { + if (!btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, name_len, &ref)) { ret = -ENOENT; search_ext_refs = 1; goto out; @@ -293,7 +296,9 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, root, path, &key, ins_len); if (ret == -EEXIST) { - if (btrfs_find_name_in_ext_backref(path, ref_objectid, + if (btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], + ref_objectid, name, name_len, NULL)) goto out; @@ -351,7 +356,8 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, if (ret == -EEXIST) { u32 old_size; - if (find_name_in_backref(path, name, name_len, &ref)) + if (btrfs_find_name_in_backref(path->nodes[0], path->slots[0], + name, name_len, &ref)) goto out; old_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]); @@ -365,7 +371,9 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ret = 0; } else if (ret < 0) { if (ret == -EOVERFLOW) { - if (find_name_in_backref(path, name, name_len, &ref)) + if (btrfs_find_name_in_backref(path->nodes[0], + path->slots[0], + name, name_len, &ref)) ret = -EEXIST; else ret = -EMLINK; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a79299a89b7d..f53470112670 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2043,12 +2043,15 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans, struct inode *inode, struct list_head *list) { struct btrfs_ordered_sum *sum; + int ret; list_for_each_entry(sum, list, list) { trans->adding_csums = true; - btrfs_csum_file_blocks(trans, + ret = btrfs_csum_file_blocks(trans, BTRFS_I(inode)->root->fs_info->csum_root, sum); trans->adding_csums = false; + if (ret) + return ret; } return 0; } @@ -3062,7 +3065,11 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) goto out; } - add_pending_csums(trans, inode, &ordered_extent->list); + ret = add_pending_csums(trans, inode, &ordered_extent->list); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out; + } btrfs_ordered_update_i_size(inode, 0, ordered_extent); ret = btrfs_update_inode_fallback(trans, root, inode); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index dec0907dfb8a..fcfc20de2df3 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1370,6 +1370,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, stripe_start = stripe->physical; if (physical >= stripe_start && physical < stripe_start + rbio->stripe_len && + stripe->dev->bdev && bio->bi_disk == stripe->dev->bdev->bd_disk && bio->bi_partno == stripe->dev->bdev->bd_partno) { return i; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index f0c3f00e97cb..cd2298d185dd 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3268,8 +3268,22 @@ static int relocate_file_extent_cluster(struct inode *inode, nr++; } - btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL, - 0); + ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0, + NULL, 0); + if (ret) { + unlock_page(page); + put_page(page); + btrfs_delalloc_release_metadata(BTRFS_I(inode), + PAGE_SIZE); + btrfs_delalloc_release_extents(BTRFS_I(inode), + PAGE_SIZE); + + clear_extent_bits(&BTRFS_I(inode)->io_tree, + page_start, page_end, + EXTENT_LOCKED | EXTENT_BOUNDARY); + goto out; + + } set_page_dirty(page); unlock_extent(&BTRFS_I(inode)->io_tree, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index f306c608dc28..484e2af793de 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5005,6 +5005,9 @@ static int send_hole(struct send_ctx *sctx, u64 end) u64 len; int ret = 0; + if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) + return send_update_extent(sctx, offset, end - offset); + p = fs_path_alloc(); if (!p) return -ENOMEM; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6e71a2a78363..4b817947e00f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1545,7 +1545,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, * it for searching for existing supers, so this lets us do that and * then open_ctree will properly initialize everything later. */ - fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); + fs_info = kvzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); if (!fs_info) { error = -ENOMEM; goto error_sec_opts; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 4fd19b4d6675..434457794c27 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -967,7 +967,9 @@ static noinline int backref_in_log(struct btrfs_root *log, ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); if (key->type == BTRFS_INODE_EXTREF_KEY) { - if (btrfs_find_name_in_ext_backref(path, ref_objectid, + if (btrfs_find_name_in_ext_backref(path->nodes[0], + path->slots[0], + ref_objectid, name, namelen, NULL)) match = 1; @@ -1191,7 +1193,8 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, read_extent_buffer(eb, *name, (unsigned long)&extref->name, *namelen); - *index = btrfs_inode_extref_index(eb, extref); + if (index) + *index = btrfs_inode_extref_index(eb, extref); if (parent_objectid) *parent_objectid = btrfs_inode_extref_parent(eb, extref); @@ -1212,12 +1215,102 @@ static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen); - *index = btrfs_inode_ref_index(eb, ref); + if (index) + *index = btrfs_inode_ref_index(eb, ref); return 0; } /* + * Take an inode reference item from the log tree and iterate all names from the + * inode reference item in the subvolume tree with the same key (if it exists). + * For any name that is not in the inode reference item from the log tree, do a + * proper unlink of that name (that is, remove its entry from the inode + * reference item and both dir index keys). + */ +static int unlink_old_inode_refs(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, + struct btrfs_inode *inode, + struct extent_buffer *log_eb, + int log_slot, + struct btrfs_key *key) +{ + int ret; + unsigned long ref_ptr; + unsigned long ref_end; + struct extent_buffer *eb; + +again: + btrfs_release_path(path); + ret = btrfs_search_slot(NULL, root, key, path, 0, 0); + if (ret > 0) { + ret = 0; + goto out; + } + if (ret < 0) + goto out; + + eb = path->nodes[0]; + ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]); + ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]); + while (ref_ptr < ref_end) { + char *name = NULL; + int namelen; + u64 parent_id; + + if (key->type == BTRFS_INODE_EXTREF_KEY) { + ret = extref_get_fields(eb, ref_ptr, &namelen, &name, + NULL, &parent_id); + } else { + parent_id = key->offset; + ret = ref_get_fields(eb, ref_ptr, &namelen, &name, + NULL); + } + if (ret) + goto out; + + if (key->type == BTRFS_INODE_EXTREF_KEY) + ret = btrfs_find_name_in_ext_backref(log_eb, log_slot, + parent_id, name, + namelen, NULL); + else + ret = btrfs_find_name_in_backref(log_eb, log_slot, name, + namelen, NULL); + + if (!ret) { + struct inode *dir; + + btrfs_release_path(path); + dir = read_one_inode(root, parent_id); + if (!dir) { + ret = -ENOENT; + kfree(name); + goto out; + } + ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), + inode, name, namelen); + kfree(name); + iput(dir); + if (ret) + goto out; + goto again; + } + + kfree(name); + ref_ptr += namelen; + if (key->type == BTRFS_INODE_EXTREF_KEY) + ref_ptr += sizeof(struct btrfs_inode_extref); + else + ref_ptr += sizeof(struct btrfs_inode_ref); + } + ret = 0; + out: + btrfs_release_path(path); + return ret; +} + +/* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. * root is the destination we are replaying into, and path is for temp @@ -1345,6 +1438,19 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, } } + /* + * Before we overwrite the inode reference item in the subvolume tree + * with the item from the log tree, we must unlink all names from the + * parent directory that are in the subvolume's tree inode reference + * item, otherwise we end up with an inconsistent subvolume tree where + * dir index entries exist for a name but there is no inode reference + * item with the same name. + */ + ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot, + key); + if (ret) + goto out; + /* finally write the back reference in the inode */ ret = overwrite_item(trans, root, path, eb, slot, key); out: @@ -5853,7 +5959,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans, * this will force the logging code to walk the dentry chain * up for the file */ - if (S_ISREG(inode->vfs_inode.i_mode)) + if (!S_ISDIR(inode->vfs_inode.i_mode)) inode->last_unlink_trans = trans->transid; /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2ceb924ca0d6..b2d05c6b1c56 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4829,10 +4829,13 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, ndevs = min(ndevs, devs_max); /* - * the primary goal is to maximize the number of stripes, so use as many - * devices as possible, even if the stripes are not maximum sized. + * The primary goal is to maximize the number of stripes, so use as + * many devices as possible, even if the stripes are not maximum sized. + * + * The DUP profile stores more than one stripe per device, the + * max_avail is the total size so we have to adjust. */ - stripe_size = devices_info[ndevs-1].max_avail; + stripe_size = div_u64(devices_info[ndevs - 1].max_avail, dev_stripes); num_stripes = ndevs * dev_stripes; /* @@ -4867,8 +4870,6 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = devices_info[ndevs-1].max_avail; } - stripe_size = div_u64(stripe_size, dev_stripes); - /* align to BTRFS_STRIPE_LEN */ stripe_size = round_down(stripe_size, BTRFS_STRIPE_LEN); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 6582c4507e6c..0e5bd3e3344e 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3965,6 +3965,32 @@ void ceph_put_fmode(struct ceph_inode_info *ci, int fmode) } /* + * For a soon-to-be unlinked file, drop the AUTH_RDCACHE caps. If it + * looks like the link count will hit 0, drop any other caps (other + * than PIN) we don't specifically want (due to the file still being + * open). + */ +int ceph_drop_caps_for_unlink(struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + int drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; + + spin_lock(&ci->i_ceph_lock); + if (inode->i_nlink == 1) { + drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN); + + ci->i_ceph_flags |= CEPH_I_NODELAY; + if (__ceph_caps_dirty(ci)) { + struct ceph_mds_client *mdsc = + ceph_inode_to_client(inode)->mdsc; + __cap_delay_requeue_front(mdsc, ci); + } + } + spin_unlock(&ci->i_ceph_lock); + return drop; +} + +/* * Helpers for embedding cap and dentry lease releases into mds * requests. * diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 0c4346806e17..f1d9c6cc0491 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1003,26 +1003,6 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, } /* - * For a soon-to-be unlinked file, drop the AUTH_RDCACHE caps. If it - * looks like the link count will hit 0, drop any other caps (other - * than PIN) we don't specifically want (due to the file still being - * open). - */ -static int drop_caps_for_unlink(struct inode *inode) -{ - struct ceph_inode_info *ci = ceph_inode(inode); - int drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; - - spin_lock(&ci->i_ceph_lock); - if (inode->i_nlink == 1) { - drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN); - ci->i_ceph_flags |= CEPH_I_NODELAY; - } - spin_unlock(&ci->i_ceph_lock); - return drop; -} - -/* * rmdir and unlink are differ only by the metadata op code */ static int ceph_unlink(struct inode *dir, struct dentry *dentry) @@ -1056,7 +1036,7 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_dentry_drop = CEPH_CAP_FILE_SHARED; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; - req->r_inode_drop = drop_caps_for_unlink(inode); + req->r_inode_drop = ceph_drop_caps_for_unlink(inode); err = ceph_mdsc_do_request(mdsc, dir, req); if (!err && !req->r_reply_info.head->is_dentry) d_delete(dentry); @@ -1104,8 +1084,10 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, req->r_dentry_unless = CEPH_CAP_FILE_EXCL; /* release LINK_RDCACHE on source inode (mds will lock it) */ req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; - if (d_really_is_positive(new_dentry)) - req->r_inode_drop = drop_caps_for_unlink(d_inode(new_dentry)); + if (d_really_is_positive(new_dentry)) { + req->r_inode_drop = + ceph_drop_caps_for_unlink(d_inode(new_dentry)); + } err = ceph_mdsc_do_request(mdsc, old_dir, req); if (!err && !req->r_reply_info.head->is_dentry) { /* diff --git a/fs/ceph/super.c b/fs/ceph/super.c index a62d2a9841dc..fb2bc9c15a23 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -225,6 +225,7 @@ static int parse_fsopt_token(char *c, void *private) return -ENOMEM; break; case Opt_mds_namespace: + kfree(fsopt->mds_namespace); fsopt->mds_namespace = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, GFP_KERNEL); @@ -232,6 +233,7 @@ static int parse_fsopt_token(char *c, void *private) return -ENOMEM; break; case Opt_fscache_uniq: + kfree(fsopt->fscache_uniq); fsopt->fscache_uniq = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, GFP_KERNEL); @@ -711,14 +713,17 @@ static int __init init_caches(void) goto bad_dentry; ceph_file_cachep = KMEM_CACHE(ceph_file_info, SLAB_MEM_SPREAD); - if (!ceph_file_cachep) goto bad_file; - if ((error = ceph_fscache_register())) - goto bad_file; + error = ceph_fscache_register(); + if (error) + goto bad_fscache; return 0; + +bad_fscache: + kmem_cache_destroy(ceph_file_cachep); bad_file: kmem_cache_destroy(ceph_dentry_cachep); bad_dentry: @@ -836,7 +841,6 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) int err; unsigned long started = jiffies; /* note the start time */ struct dentry *root; - int first = 0; /* first vfsmount for this super_block */ dout("mount start %p\n", fsc); mutex_lock(&fsc->client->mount_mutex); @@ -861,17 +865,17 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) path = fsc->mount_options->server_path + 1; dout("mount opening path %s\n", path); } + + err = ceph_fs_debugfs_init(fsc); + if (err < 0) + goto out; + root = open_root_dentry(fsc, path, started); if (IS_ERR(root)) { err = PTR_ERR(root); goto out; } fsc->sb->s_root = dget(root); - first = 1; - - err = ceph_fs_debugfs_init(fsc); - if (err < 0) - goto fail; } else { root = dget(fsc->sb->s_root); } @@ -881,11 +885,6 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) mutex_unlock(&fsc->client->mount_mutex); return root; -fail: - if (first) { - dput(fsc->sb->s_root); - fsc->sb->s_root = NULL; - } out: mutex_unlock(&fsc->client->mount_mutex); return ERR_PTR(err); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 21b2e5b004eb..1c2086e0fec2 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -987,7 +987,7 @@ extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); - +extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, int mds, int drop, int unless, int force); extern int ceph_encode_dentry_release(void **p, struct dentry *dn, diff --git a/fs/dcache.c b/fs/dcache.c index 7c38f39958bc..8945e6cabd93 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -647,11 +647,16 @@ again: spin_unlock(&parent->d_lock); goto again; } - rcu_read_unlock(); - if (parent != dentry) + if (parent != dentry) { spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - else + if (unlikely(dentry->d_lockref.count < 0)) { + spin_unlock(&parent->d_lock); + parent = NULL; + } + } else { parent = NULL; + } + rcu_read_unlock(); return parent; } @@ -2474,7 +2479,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent, retry: rcu_read_lock(); - seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1; + seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { @@ -2495,8 +2500,14 @@ retry: rcu_read_unlock(); goto retry; } + + if (unlikely(seq & 1)) { + rcu_read_unlock(); + goto retry; + } + hlist_bl_lock(b); - if (unlikely(parent->d_inode->i_dir_seq != seq)) { + if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; diff --git a/fs/direct-io.c b/fs/direct-io.c index a0ca9e48e993..1357ef563893 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1274,8 +1274,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, */ if (dio->is_async && iov_iter_rw(iter) == WRITE) { retval = 0; - if ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host)) + if (iocb->ki_flags & IOCB_DSYNC) retval = dio_set_defer_completion(dio); else if (!dio->inode->i_sb->s_dio_done_wq) { /* diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 86d6a4435c87..51f940e76c5e 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -807,9 +807,6 @@ do_alloc: iomap->length = hole_size(inode, lblock, &mp); else iomap->length = size - pos; - } else { - if (height <= ip->i_height) - iomap->length = hole_size(inode, lblock, &mp); } goto out_release; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8fe1b0aa2896..b9a254dcc0e7 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -108,6 +108,16 @@ static void huge_pagevec_release(struct pagevec *pvec) pagevec_reinit(pvec); } +/* + * Mask used when checking the page offset value passed in via system + * calls. This value will be converted to a loff_t which is signed. + * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the + * value. The extra bit (- 1 in the shift value) is to take the sign + * bit into account. + */ +#define PGOFF_LOFFT_MAX \ + (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) + static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); @@ -127,12 +137,13 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_ops = &hugetlb_vm_ops; /* - * Offset passed to mmap (before page shift) could have been - * negative when represented as a (l)off_t. + * page based offset in vm_pgoff could be sufficiently large to + * overflow a (l)off_t when converted to byte offset. */ - if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0) + if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL; + /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; diff --git a/fs/namei.c b/fs/namei.c index 921ae32dbc80..cafa365eeb70 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -559,9 +559,10 @@ static int __nd_alloc_stack(struct nameidata *nd) static bool path_connected(const struct path *path) { struct vfsmount *mnt = path->mnt; + struct super_block *sb = mnt->mnt_sb; - /* Only bind mounts can have disconnected paths */ - if (mnt->mnt_root == mnt->mnt_sb->s_root) + /* Bind mounts and multi-root filesystems can have disconnected paths */ + if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root)) return true; return is_subdir(path->dentry, mnt->mnt_root); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 8c10b0562e75..621c517b325c 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -86,10 +86,10 @@ struct nfs_direct_req { struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX]; int mirror_count; + loff_t io_start; /* Start offset for I/O */ ssize_t count, /* bytes actually processed */ max_count, /* max expected count */ bytes_left, /* bytes left to be sent */ - io_start, /* start of IO */ error; /* any reported error */ struct completion completion; /* wait for i/o completion */ diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c13e826614b5..ee723aa153a3 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -292,8 +292,11 @@ pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo) void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { - struct inode *inode = lo->plh_inode; + struct inode *inode; + if (!lo) + return; + inode = lo->plh_inode; pnfs_layoutreturn_before_put_layout_hdr(lo); if (refcount_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { @@ -1241,10 +1244,12 @@ retry: spin_lock(&ino->i_lock); lo = nfsi->layout; if (!lo || !pnfs_layout_is_valid(lo) || - test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) + test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + lo = NULL; goto out_noroc; + } + pnfs_get_layout_hdr(lo); if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - pnfs_get_layout_hdr(lo); spin_unlock(&ino->i_lock); wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE); @@ -1312,10 +1317,12 @@ out_noroc: struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) ld->prepare_layoutreturn(args); + pnfs_put_layout_hdr(lo); return true; } if (layoutreturn) pnfs_send_layoutreturn(lo, &stateid, iomode, true); + pnfs_put_layout_hdr(lo); return false; } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 29bacdc56f6a..5e470e233c83 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2631,6 +2631,8 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server, /* initial superblock/root creation */ mount_info->fill_super(s, mount_info); nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); + if (!(server->flags & NFS_MOUNT_UNSHARED)) + s->s_iflags |= SB_I_MULTIROOT; } mntroot = nfs_get_root(s, mount_info->mntfh, dev_name); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7428a669d7a7..e7d8ceae8f26 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1876,40 +1876,43 @@ int nfs_generic_commit_list(struct inode *inode, struct list_head *head, return status; } -int nfs_commit_inode(struct inode *inode, int how) +static int __nfs_commit_inode(struct inode *inode, int how, + struct writeback_control *wbc) { LIST_HEAD(head); struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; - int error = 0; - int res; + int ret, nscan; nfs_init_cinfo_from_inode(&cinfo, inode); nfs_commit_begin(cinfo.mds); - res = nfs_scan_commit(inode, &head, &cinfo); - if (res) - error = nfs_generic_commit_list(inode, &head, how, &cinfo); + for (;;) { + ret = nscan = nfs_scan_commit(inode, &head, &cinfo); + if (ret <= 0) + break; + ret = nfs_generic_commit_list(inode, &head, how, &cinfo); + if (ret < 0) + break; + ret = 0; + if (wbc && wbc->sync_mode == WB_SYNC_NONE) { + if (nscan < wbc->nr_to_write) + wbc->nr_to_write -= nscan; + else + wbc->nr_to_write = 0; + } + if (nscan < INT_MAX) + break; + cond_resched(); + } nfs_commit_end(cinfo.mds); - if (res == 0) - return res; - if (error < 0) - goto out_error; - if (!may_wait) - goto out_mark_dirty; - error = wait_on_commit(cinfo.mds); - if (error < 0) - return error; - return res; -out_error: - res = error; - /* Note: If we exit without ensuring that the commit is complete, - * we must mark the inode as dirty. Otherwise, future calls to - * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure - * that the data is on the disk. - */ -out_mark_dirty: - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - return res; + if (ret || !may_wait) + return ret; + return wait_on_commit(cinfo.mds); +} + +int nfs_commit_inode(struct inode *inode, int how) +{ + return __nfs_commit_inode(inode, how, NULL); } EXPORT_SYMBOL_GPL(nfs_commit_inode); @@ -1919,11 +1922,11 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) int flags = FLUSH_SYNC; int ret = 0; - /* no commits means nothing needs to be done */ - if (!atomic_long_read(&nfsi->commit_info.ncommit)) - return ret; - if (wbc->sync_mode == WB_SYNC_NONE) { + /* no commits means nothing needs to be done */ + if (!atomic_long_read(&nfsi->commit_info.ncommit)) + goto check_requests_outstanding; + /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ @@ -1934,16 +1937,16 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) flags = 0; } - ret = nfs_commit_inode(inode, flags); - if (ret >= 0) { - if (wbc->sync_mode == WB_SYNC_NONE) { - if (ret < wbc->nr_to_write) - wbc->nr_to_write -= ret; - else - wbc->nr_to_write = 0; - } - return 0; - } + ret = __nfs_commit_inode(inode, flags, wbc); + if (!ret) { + if (flags & FLUSH_SYNC) + return 0; + } else if (atomic_long_read(&nfsi->commit_info.ncommit)) + goto out_mark_dirty; + +check_requests_outstanding: + if (!atomic_read(&nfsi->commit_info.rpcs_out)) + return ret; out_mark_dirty: __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return ret; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 150521c9671b..61b770e39809 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -268,6 +268,35 @@ free_blocked_lock(struct nfsd4_blocked_lock *nbl) kfree(nbl); } +static void +remove_blocked_locks(struct nfs4_lockowner *lo) +{ + struct nfs4_client *clp = lo->lo_owner.so_client; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + struct nfsd4_blocked_lock *nbl; + LIST_HEAD(reaplist); + + /* Dequeue all blocked locks */ + spin_lock(&nn->blocked_locks_lock); + while (!list_empty(&lo->lo_blocked)) { + nbl = list_first_entry(&lo->lo_blocked, + struct nfsd4_blocked_lock, + nbl_list); + list_del_init(&nbl->nbl_list); + list_move(&nbl->nbl_lru, &reaplist); + } + spin_unlock(&nn->blocked_locks_lock); + + /* Now free them */ + while (!list_empty(&reaplist)) { + nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, + nbl_lru); + list_del_init(&nbl->nbl_lru); + posix_unblock_lock(&nbl->nbl_lock); + free_blocked_lock(nbl); + } +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -1866,6 +1895,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp) static void __destroy_client(struct nfs4_client *clp) { + int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct list_head reaplist; @@ -1895,6 +1925,16 @@ __destroy_client(struct nfs4_client *clp) nfs4_get_stateowner(&oo->oo_owner); release_openowner(oo); } + for (i = 0; i < OWNER_HASH_SIZE; i++) { + struct nfs4_stateowner *so, *tmp; + + list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i], + so_strhash) { + /* Should be no openowners at this point */ + WARN_ON_ONCE(so->so_is_open_owner); + remove_blocked_locks(lockowner(so)); + } + } nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) @@ -6355,6 +6395,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, } spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); + remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); return status; @@ -7140,6 +7181,8 @@ nfs4_state_destroy_net(struct net *net) } } + WARN_ON(!list_empty(&nn->blocked_locks_lru)); + for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->unconf_id_hashtbl[i])) { clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); @@ -7206,7 +7249,6 @@ nfs4_state_shutdown_net(struct net *net) struct nfs4_delegation *dp = NULL; struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd4_blocked_lock *nbl; cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -7227,24 +7269,6 @@ nfs4_state_shutdown_net(struct net *net) nfs4_put_stid(&dp->dl_stid); } - BUG_ON(!list_empty(&reaplist)); - spin_lock(&nn->blocked_locks_lock); - while (!list_empty(&nn->blocked_locks_lru)) { - nbl = list_first_entry(&nn->blocked_locks_lru, - struct nfsd4_blocked_lock, nbl_lru); - list_move(&nbl->nbl_lru, &reaplist); - list_del_init(&nbl->nbl_list); - } - spin_unlock(&nn->blocked_locks_lock); - - while (!list_empty(&reaplist)) { - nbl = list_first_entry(&reaplist, - struct nfsd4_blocked_lock, nbl_lru); - list_del_init(&nbl->nbl_lru); - posix_unblock_lock(&nbl->nbl_lock); - free_blocked_lock(nbl); - } - nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); } diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 406e72de88f6..ce6ff5a0a6e4 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -24,6 +24,8 @@ config OVERLAY_FS_REDIRECT_DIR an overlay which has redirects on a kernel that doesn't support this feature will have unexpected results. + If unsure, say N. + config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW bool "Overlayfs: follow redirects even if redirects are turned off" default y @@ -32,8 +34,13 @@ config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW Disable this to get a possibly more secure configuration, but that might not be backward compatible with previous kernels. + If backward compatibility is not an issue, then it is safe and + recommended to say N here. + For more information, see Documentation/filesystems/overlayfs.txt + If unsure, say Y. + config OVERLAY_FS_INDEX bool "Overlayfs: turn on inodes index feature by default" depends on OVERLAY_FS @@ -51,6 +58,8 @@ config OVERLAY_FS_INDEX That is, mounting an overlay which has an inodes index on a kernel that doesn't support this feature will have unexpected results. + If unsure, say N. + config OVERLAY_FS_NFS_EXPORT bool "Overlayfs: turn on NFS export feature by default" depends on OVERLAY_FS @@ -72,3 +81,8 @@ config OVERLAY_FS_NFS_EXPORT Note, that the NFS export feature is not backward compatible. That is, mounting an overlay which has a full index on a kernel that doesn't support this feature will have unexpected results. + + Most users should say N here and enable this feature on a case-by- + case basis with the "nfs_export=on" mount option. + + Say N unless you fully understand the consequences. diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index bb94ce9da5c8..87bd4148f4fb 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -19,6 +19,142 @@ #include <linux/ratelimit.h> #include "overlayfs.h" +static int ovl_encode_maybe_copy_up(struct dentry *dentry) +{ + int err; + + if (ovl_dentry_upper(dentry)) + return 0; + + err = ovl_want_write(dentry); + if (!err) { + err = ovl_copy_up(dentry); + ovl_drop_write(dentry); + } + + if (err) { + pr_warn_ratelimited("overlayfs: failed to copy up on encode (%pd2, err=%i)\n", + dentry, err); + } + + return err; +} + +/* + * Before encoding a non-upper directory file handle from real layer N, we need + * to check if it will be possible to reconnect an overlay dentry from the real + * lower decoded dentry. This is done by following the overlay ancestry up to a + * "layer N connected" ancestor and verifying that all parents along the way are + * "layer N connectable". If an ancestor that is NOT "layer N connectable" is + * found, we need to copy up an ancestor, which is "layer N connectable", thus + * making that ancestor "layer N connected". For example: + * + * layer 1: /a + * layer 2: /a/b/c + * + * The overlay dentry /a is NOT "layer 2 connectable", because if dir /a is + * copied up and renamed, upper dir /a will be indexed by lower dir /a from + * layer 1. The dir /a from layer 2 will never be indexed, so the algorithm (*) + * in ovl_lookup_real_ancestor() will not be able to lookup a connected overlay + * dentry from the connected lower dentry /a/b/c. + * + * To avoid this problem on decode time, we need to copy up an ancestor of + * /a/b/c, which is "layer 2 connectable", on encode time. That ancestor is + * /a/b. After copy up (and index) of /a/b, it will become "layer 2 connected" + * and when the time comes to decode the file handle from lower dentry /a/b/c, + * ovl_lookup_real_ancestor() will find the indexed ancestor /a/b and decoding + * a connected overlay dentry will be accomplished. + * + * (*) the algorithm in ovl_lookup_real_ancestor() can be improved to lookup an + * entry /a in the lower layers above layer N and find the indexed dir /a from + * layer 1. If that improvement is made, then the check for "layer N connected" + * will need to verify there are no redirects in lower layers above N. In the + * example above, /a will be "layer 2 connectable". However, if layer 2 dir /a + * is a target of a layer 1 redirect, then /a will NOT be "layer 2 connectable": + * + * layer 1: /A (redirect = /a) + * layer 2: /a/b/c + */ + +/* Return the lowest layer for encoding a connectable file handle */ +static int ovl_connectable_layer(struct dentry *dentry) +{ + struct ovl_entry *oe = OVL_E(dentry); + + /* We can get overlay root from root of any layer */ + if (dentry == dentry->d_sb->s_root) + return oe->numlower; + + /* + * If it's an unindexed merge dir, then it's not connectable with any + * lower layer + */ + if (ovl_dentry_upper(dentry) && + !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + return 0; + + /* We can get upper/overlay path from indexed/lower dentry */ + return oe->lowerstack[0].layer->idx; +} + +/* + * @dentry is "connected" if all ancestors up to root or a "connected" ancestor + * have the same uppermost lower layer as the origin's layer. We may need to + * copy up a "connectable" ancestor to make it "connected". A "connected" dentry + * cannot become non "connected", so cache positive result in dentry flags. + * + * Return the connected origin layer or < 0 on error. + */ +static int ovl_connect_layer(struct dentry *dentry) +{ + struct dentry *next, *parent = NULL; + int origin_layer; + int err = 0; + + if (WARN_ON(dentry == dentry->d_sb->s_root) || + WARN_ON(!ovl_dentry_lower(dentry))) + return -EIO; + + origin_layer = OVL_E(dentry)->lowerstack[0].layer->idx; + if (ovl_dentry_test_flag(OVL_E_CONNECTED, dentry)) + return origin_layer; + + /* Find the topmost origin layer connectable ancestor of @dentry */ + next = dget(dentry); + for (;;) { + parent = dget_parent(next); + if (WARN_ON(parent == next)) { + err = -EIO; + break; + } + + /* + * If @parent is not origin layer connectable, then copy up + * @next which is origin layer connectable and we are done. + */ + if (ovl_connectable_layer(parent) < origin_layer) { + err = ovl_encode_maybe_copy_up(next); + break; + } + + /* If @parent is connected or indexed we are done */ + if (ovl_dentry_test_flag(OVL_E_CONNECTED, parent) || + ovl_test_flag(OVL_INDEX, d_inode(parent))) + break; + + dput(next); + next = parent; + } + + dput(parent); + dput(next); + + if (!err) + ovl_dentry_set_flag(OVL_E_CONNECTED, dentry); + + return err ?: origin_layer; +} + /* * We only need to encode origin if there is a chance that the same object was * encoded pre copy up and then we need to stay consistent with the same @@ -41,73 +177,59 @@ * L = lower file handle * * (*) Connecting an overlay dir from real lower dentry is not always - * possible when there are redirects in lower layers. To mitigate this case, - * we copy up the lower dir first and then encode an upper dir file handle. + * possible when there are redirects in lower layers and non-indexed merge dirs. + * To mitigate those case, we may copy up the lower dir ancestor before encode + * a lower dir file handle. + * + * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static bool ovl_should_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct dentry *dentry) { struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + /* Upper file handle for pure upper */ if (!ovl_dentry_lower(dentry)) - return false; + return 0; /* - * Decoding a merge dir, whose origin's parent is under a redirected - * lower dir is not always possible. As a simple aproximation, we do - * not encode lower dir file handles when overlay has multiple lower - * layers and origin is below the topmost lower layer. + * Upper file handle for non-indexed upper. * - * TODO: copy up only the parent that is under redirected lower. + * Root is never indexed, so if there's an upper layer, encode upper for + * root. */ - if (d_is_dir(dentry) && ofs->upper_mnt && - OVL_E(dentry)->lowerstack[0].layer->idx > 1) - return false; - - /* Decoding a non-indexed upper from origin is not implemented */ if (ovl_dentry_upper(dentry) && !ovl_test_flag(OVL_INDEX, d_inode(dentry))) - return false; - - return true; -} - -static int ovl_encode_maybe_copy_up(struct dentry *dentry) -{ - int err; - - if (ovl_dentry_upper(dentry)) return 0; - err = ovl_want_write(dentry); - if (err) - return err; - - err = ovl_copy_up(dentry); + /* + * Decoding a merge dir, whose origin's ancestor is under a redirected + * lower dir or under a non-indexed upper is not always possible. + * ovl_connect_layer() will try to make origin's layer "connected" by + * copying up a "connectable" ancestor. + */ + if (d_is_dir(dentry) && ofs->upper_mnt) + return ovl_connect_layer(dentry); - ovl_drop_write(dentry); - return err; + /* Lower file handle for indexed and non-upper dir/non-dir */ + return 1; } static int ovl_d_to_fh(struct dentry *dentry, char *buf, int buflen) { - struct dentry *origin = ovl_dentry_lower(dentry); struct ovl_fh *fh = NULL; - int err; + int err, enc_lower; /* - * If we should not encode a lower dir file handle, copy up and encode - * an upper dir file handle. + * Check if we should encode a lower or upper file handle and maybe + * copy up an ancestor to make lower file handle connectable. */ - if (!ovl_should_encode_origin(dentry)) { - err = ovl_encode_maybe_copy_up(dentry); - if (err) - goto fail; - - origin = NULL; - } + err = enc_lower = ovl_check_encode_origin(dentry); + if (enc_lower < 0) + goto fail; - /* Encode an upper or origin file handle */ - fh = ovl_encode_fh(origin ?: ovl_dentry_upper(dentry), !origin); + /* Encode an upper or lower file handle */ + fh = ovl_encode_fh(enc_lower ? ovl_dentry_lower(dentry) : + ovl_dentry_upper(dentry), !enc_lower); err = PTR_ERR(fh); if (IS_ERR(fh)) goto fail; @@ -355,8 +477,8 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb, dput(upper); } - if (!this) - return NULL; + if (IS_ERR_OR_NULL(this)) + return this; if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) { dput(this); @@ -498,7 +620,7 @@ static struct dentry *ovl_lookup_real(struct super_block *sb, if (err == -ECHILD) { this = ovl_lookup_real_ancestor(sb, real, layer); - err = IS_ERR(this) ? PTR_ERR(this) : 0; + err = PTR_ERR_OR_ZERO(this); } if (!err) { dput(connected); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index fcd97b783fa1..3b1bd469accd 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -669,38 +669,59 @@ struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, return inode; } +/* + * Does overlay inode need to be hashed by lower inode? + */ +static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper, + struct dentry *lower, struct dentry *index) +{ + struct ovl_fs *ofs = sb->s_fs_info; + + /* No, if pure upper */ + if (!lower) + return false; + + /* Yes, if already indexed */ + if (index) + return true; + + /* Yes, if won't be copied up */ + if (!ofs->upper_mnt) + return true; + + /* No, if lower hardlink is or will be broken on copy up */ + if ((upper || !ovl_indexdir(sb)) && + !d_is_dir(lower) && d_inode(lower)->i_nlink > 1) + return false; + + /* No, if non-indexed upper with NFS export */ + if (sb->s_export_op && upper) + return false; + + /* Otherwise, hash by lower inode for fsnotify */ + return true; +} + struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry, struct dentry *lowerdentry, struct dentry *index, unsigned int numlower) { - struct ovl_fs *ofs = sb->s_fs_info; struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL; struct inode *inode; - /* Already indexed or could be indexed on copy up? */ - bool indexed = (index || (ovl_indexdir(sb) && !upperdentry)); - struct dentry *origin = indexed ? lowerdentry : NULL; + bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index); bool is_dir; - if (WARN_ON(upperdentry && indexed && !lowerdentry)) - return ERR_PTR(-EIO); - if (!realinode) realinode = d_inode(lowerdentry); /* - * Copy up origin (lower) may exist for non-indexed non-dir upper, but - * we must not use lower as hash key in that case. - * Hash non-dir that is or could be indexed by origin inode. - * Hash dir that is or could be merged by origin inode. - * Hash pure upper and non-indexed non-dir by upper inode. - * Hash non-indexed dir by upper inode for NFS export. + * Copy up origin (lower) may exist for non-indexed upper, but we must + * not use lower as hash key if this is a broken hardlink. */ is_dir = S_ISDIR(realinode->i_mode); - if (is_dir && (indexed || !sb->s_export_op || !ofs->upper_mnt)) - origin = lowerdentry; - - if (upperdentry || origin) { - struct inode *key = d_inode(origin ?: upperdentry); + if (upperdentry || bylower) { + struct inode *key = d_inode(bylower ? lowerdentry : + upperdentry); unsigned int nlink = is_dir ? 1 : realinode->i_nlink; inode = iget5_locked(sb, (unsigned long) key, @@ -728,6 +749,7 @@ struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry, nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink); set_nlink(inode, nlink); } else { + /* Lower hardlink that will be broken on copy up */ inode = new_inode(sb); if (!inode) goto out_nomem; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index de3e6da1d5a5..70fcfcc684cc 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -913,9 +913,6 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, stack[ctr].layer = lower.layer; ctr++; - if (d.stop) - break; - /* * Following redirects can have security consequences: it's like * a symlink into the lower layer without the permission checks. @@ -933,6 +930,9 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, goto out_put; } + if (d.stop) + break; + if (d.redirect && d.redirect[0] == '/' && poe != roe) { poe = roe; /* Find the current layer on the root dentry */ diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 0df25a9c94bd..225ff1171147 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -40,6 +40,7 @@ enum ovl_inode_flag { enum ovl_entry_flag { OVL_E_UPPER_ALIAS, OVL_E_OPAQUE, + OVL_E_CONNECTED, }; /* diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 9ee37c76091d..7c24619ae7fc 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1359,6 +1359,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) /* Root is always merge -> can have whiteouts */ ovl_set_flag(OVL_WHITEOUTS, d_inode(root_dentry)); + ovl_dentry_set_flag(OVL_E_CONNECTED, root_dentry); ovl_inode_init(d_inode(root_dentry), upperpath.dentry, ovl_dentry_lower(root_dentry)); diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 8664db25a9a6..215c225b2ca1 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -106,6 +106,7 @@ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target, { return sysfs_do_create_link(kobj, target, name, 0); } +EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn); /** * sysfs_delete_link - remove symlink in object's directory. diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index fd975524f460..05c66e05ae20 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -767,7 +767,7 @@ int xfs_scrub_agfl( struct xfs_scrub_context *sc) { - struct xfs_scrub_agfl_info sai = { 0 }; + struct xfs_scrub_agfl_info sai; struct xfs_agf *agf; xfs_agnumber_t agno; unsigned int agflcount; @@ -795,6 +795,7 @@ xfs_scrub_agfl( xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp); goto out; } + memset(&sai, 0, sizeof(sai)); sai.sz_entries = agflcount; sai.entries = kmem_zalloc(sizeof(xfs_agblock_t) * agflcount, KM_NOFS); if (!sai.entries) { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 66e1edbfb2b2..046469fcc1b8 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -955,15 +955,29 @@ static inline bool imap_needs_alloc(struct inode *inode, (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN); } +static inline bool needs_cow_for_zeroing(struct xfs_bmbt_irec *imap, int nimaps) +{ + return nimaps && + imap->br_startblock != HOLESTARTBLOCK && + imap->br_state != XFS_EXT_UNWRITTEN; +} + static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags) { /* - * COW writes will allocate delalloc space, so we need to make sure - * to take the lock exclusively here. + * COW writes may allocate delalloc space or convert unwritten COW + * extents, so we need to make sure to take the lock exclusively here. */ if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO))) return true; - if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE)) + + /* + * Extents not yet cached requires exclusive access, don't block. + * This is an opencoded xfs_ilock_data_map_shared() to cater for the + * non-blocking behaviour. + */ + if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE && + !(ip->i_df.if_flags & XFS_IFEXTENTS)) return true; return false; } @@ -993,16 +1007,18 @@ xfs_file_iomap_begin( return xfs_file_iomap_begin_delay(inode, offset, length, iomap); } - if (need_excl_ilock(ip, flags)) { + if (need_excl_ilock(ip, flags)) lockmode = XFS_ILOCK_EXCL; - xfs_ilock(ip, XFS_ILOCK_EXCL); - } else { - lockmode = xfs_ilock_data_map_shared(ip); - } + else + lockmode = XFS_ILOCK_SHARED; - if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) { - error = -EAGAIN; - goto out_unlock; + if (flags & IOMAP_NOWAIT) { + if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) + return -EAGAIN; + if (!xfs_ilock_nowait(ip, lockmode)) + return -EAGAIN; + } else { + xfs_ilock(ip, lockmode); } ASSERT(offset <= mp->m_super->s_maxbytes); @@ -1024,7 +1040,9 @@ xfs_file_iomap_begin( goto out_unlock; } - if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + if (xfs_is_reflink_inode(ip) && + ((flags & IOMAP_WRITE) || + ((flags & IOMAP_ZERO) && needs_cow_for_zeroing(&imap, nimaps)))) { if (flags & IOMAP_DIRECT) { /* * A reflinked inode will result in CoW alloc. diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 3a55d6fc271b..7a39f40645f7 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -23,6 +23,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" +#include "xfs_shared.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" @@ -456,10 +457,12 @@ xfs_cui_recover( * transaction. Normally, any work that needs to be deferred * gets attached to the same defer_ops that scheduled the * refcount update. However, we're in log recovery here, so we - * we create our own defer_ops and use that to finish up any - * work that doesn't fit. + * we use the passed in defer_ops and to finish up any work that + * doesn't fit. We need to reserve enough blocks to handle a + * full btree split on either end of the refcount range. */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; cudp = xfs_trans_get_cud(tp, cuip); diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index f3b139c9aa16..49d3124863a8 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -23,6 +23,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" +#include "xfs_shared.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" @@ -470,7 +471,8 @@ xfs_rui_recover( } } - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, + mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; rudp = xfs_trans_get_rud(tp, ruip); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 7aba628dc527..93588ea3d3d2 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -250,6 +250,7 @@ xfs_parseargs( return -EINVAL; break; case Opt_logdev: + kfree(mp->m_logname); mp->m_logname = match_strdup(args); if (!mp->m_logname) return -ENOMEM; @@ -258,6 +259,7 @@ xfs_parseargs( xfs_warn(mp, "%s option not allowed on this system", p); return -EINVAL; case Opt_rtdev: + kfree(mp->m_rtname); mp->m_rtname = match_strdup(args); if (!mp->m_rtname) return -ENOMEM; diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 2cfa3075d148..bfbb44a5ad38 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -983,6 +983,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); +int pud_free_pmd_page(pud_t *pud); +int pmd_free_pte_page(pmd_t *pmd); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { @@ -1008,6 +1010,14 @@ static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } +static inline int pud_free_pmd_page(pud_t *pud) +{ + return 0; +} +static inline int pmd_free_pte_page(pmd_t *pmd) +{ + return 0; +} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index d32b688eb346..d23dcdd1bd95 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -56,6 +56,7 @@ struct drm_printer; #define DRIVER_ATOMIC 0x10000 #define DRIVER_KMS_LEGACY_CONTEXT 0x20000 #define DRIVER_SYNCOBJ 0x40000 +#define DRIVER_PREFER_XBGR_30BPP 0x80000 /** * struct drm_driver - DRM driver structure diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index cdbd142ca7f2..02924ae2527e 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -360,6 +360,7 @@ void kvm_vgic_put(struct kvm_vcpu *vcpu); bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu); void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); +void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid); void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); diff --git a/include/linux/bio.h b/include/linux/bio.h index d0eb659fa733..ce547a25e8ae 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -511,6 +511,7 @@ void zero_fill_bio(struct bio *bio); extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); +extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_set_dev(bio, bdev) \ do { \ @@ -529,9 +530,6 @@ do { \ #define bio_dev(bio) \ disk_devt((bio)->bi_disk) -#define bio_devname(bio, buf) \ - __bdevname(bio_dev(bio), (buf)) - #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); void bio_disassociate_task(struct bio *bio); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9f242b876fde..f8e76d01a5ad 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -755,13 +755,13 @@ struct sock_cgroup_data { * updaters and return part of the previous pointer as the prioidx or * classid. Such races are short-lived and the result isn't critical. */ -static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd) +static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { /* fallback to 1 which is always the ID of the root cgroup */ return (skcd->is_data & 1) ? skcd->prioidx : 1; } -static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) +static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { /* fallback to 0 which is the unconfigured default classid */ return (skcd->is_data & 1) ? skcd->classid : 0; diff --git a/include/linux/compat.h b/include/linux/compat.h index 8a9643857c4a..16c3027074a2 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -17,6 +17,7 @@ #include <linux/if.h> #include <linux/fs.h> #include <linux/aio_abi.h> /* for aio_context_t */ +#include <linux/uaccess.h> #include <linux/unistd.h> #include <asm/compat.h> @@ -229,13 +230,13 @@ typedef struct compat_siginfo { short int _addr_lsb; /* Valid LSB of the reported address. */ /* used when si_code=SEGV_BNDERR */ struct { - short _dummy_bnd; + compat_uptr_t _dummy_bnd; compat_uptr_t _lower; compat_uptr_t _upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { - short _dummy_pkey; + compat_uptr_t _dummy_pkey; u32 _pkey; } _addr_pkey; }; @@ -550,8 +551,29 @@ asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); -extern int put_compat_sigset(compat_sigset_t __user *compat, - const sigset_t *set, unsigned int size); + +/* + * Defined inline such that size can be compile time constant, which avoids + * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct + */ +static inline int +put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, + unsigned int size) +{ + /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ +#ifdef __BIG_ENDIAN + compat_sigset_t v; + switch (_NSIG_WORDS) { + case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; + } + return copy_to_user(compat, &v, size) ? -EFAULT : 0; +#else + return copy_to_user(compat, set, size) ? -EFAULT : 0; +#endif +} asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes, diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d02a4df3f473..d3f264a5b04d 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -27,3 +27,8 @@ #if __has_feature(address_sanitizer) #define __SANITIZE_ADDRESS__ #endif + +/* Clang doesn't have a way to turn it off per-function, yet. */ +#ifdef __noretpoline +#undef __noretpoline +#endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 901c1ccb3374..e2c7f4369eff 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -93,6 +93,10 @@ #define __weak __attribute__((weak)) #define __alias(symbol) __attribute__((alias(#symbol))) +#ifdef RETPOLINE +#define __noretpoline __attribute__((indirect_branch("keep"))) +#endif + /* * it doesn't make sense on ARM (currently the only user of __naked) * to trace naked functions because then mcount is called without diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a815560fda0..c6baf767619e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1317,6 +1317,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ @@ -3198,7 +3199,7 @@ static inline bool vma_is_fsdax(struct vm_area_struct *vma) if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); - if (inode->i_mode == S_IFCHR) + if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h index c332f0a45607..3fdfede2f0f3 100644 --- a/include/linux/fsl_ifc.h +++ b/include/linux/fsl_ifc.h @@ -734,11 +734,7 @@ struct fsl_ifc_nand { u32 res19[0x10]; __be32 nand_fsr; u32 res20; - /* The V1 nand_eccstat is actually 4 words that overlaps the - * V2 nand_eccstat. - */ - __be32 v1_nand_eccstat[2]; - __be32 v2_nand_eccstat[6]; + __be32 nand_eccstat[8]; u32 res21[0x1c]; __be32 nanndcr; u32 res22[0x2]; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 5e3531027b51..c826b0b5232a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -198,6 +198,7 @@ struct gendisk { void *private_data; int flags; + struct rw_semaphore lookup_sem; struct kobject *slave_dir; struct timer_rand_state *random; @@ -600,8 +601,9 @@ extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); extern struct gendisk *__alloc_disk_node(int minors, int node_id); -extern struct kobject *get_disk(struct gendisk *disk); +extern struct kobject *get_disk_and_module(struct gendisk *disk); extern void put_disk(struct gendisk *disk); +extern void put_disk_and_module(struct gendisk *disk); extern void blk_register_region(dev_t devt, unsigned long range, struct module *module, struct kobject *(*probe)(dev_t, int *, void *), diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index c5b0a75a7812..fd00170b494f 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -25,6 +25,7 @@ struct ptr_ring *tun_get_tx_ring(struct file *file); bool tun_is_xdp_buff(void *ptr); void *tun_xdp_to_ptr(void *ptr); void *tun_ptr_to_xdp(void *ptr); +void tun_ptr_free(void *ptr); #else #include <linux/err.h> #include <linux/errno.h> @@ -50,5 +51,8 @@ static inline void *tun_ptr_to_xdp(void *ptr) { return NULL; } +static inline void tun_ptr_free(void *ptr) +{ +} #endif /* CONFIG_TUN */ #endif /* __IF_TUN_H */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 5e6a2d4dc366..c4a1cff9c768 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -300,30 +300,34 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features, } /** - * __vlan_insert_tag - regular VLAN tag inserting + * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert + * @mac_len: MAC header length including outer vlan headers * - * Inserts the VLAN tag into @skb as part of the payload + * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns error if skb_cow_head failes. * * Does not change skb->protocol so this function can be used during receive. */ -static inline int __vlan_insert_tag(struct sk_buff *skb, - __be16 vlan_proto, u16 vlan_tci) +static inline int __vlan_insert_inner_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci, + unsigned int mac_len) { struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; - veth = skb_push(skb, VLAN_HLEN); + skb_push(skb, VLAN_HLEN); - /* Move the mac addresses to the beginning of the new header. */ - memmove(skb->data, skb->data + VLAN_HLEN, 2 * ETH_ALEN); + /* Move the mac header sans proto to the beginning of the new header. */ + memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); skb->mac_header -= VLAN_HLEN; + veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); + /* first, the ethernet type */ veth->h_vlan_proto = vlan_proto; @@ -334,12 +338,30 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, } /** - * vlan_insert_tag - regular VLAN tag inserting + * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload + * Returns error if skb_cow_head failes. + * + * Does not change skb->protocol so this function can be used during receive. + */ +static inline int __vlan_insert_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) +{ + return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); +} + +/** + * vlan_insert_inner_tag - inner VLAN tag inserting + * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol + * @vlan_tci: VLAN TCI to insert + * @mac_len: MAC header length including outer vlan headers + * + * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. * * Following the skb_unshare() example, in case of error, the calling function @@ -347,12 +369,14 @@ static inline int __vlan_insert_tag(struct sk_buff *skb, * * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, - __be16 vlan_proto, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, + __be16 vlan_proto, + u16 vlan_tci, + unsigned int mac_len) { int err; - err = __vlan_insert_tag(skb, vlan_proto, vlan_tci); + err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; @@ -361,6 +385,26 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, } /** + * vlan_insert_tag - regular VLAN tag inserting + * @skb: skbuff to tag + * @vlan_proto: VLAN encapsulation protocol + * @vlan_tci: VLAN TCI to insert + * + * Inserts the VLAN tag into @skb as part of the payload + * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * + * Following the skb_unshare() example, in case of error, the calling function + * doesn't have to worry about freeing the original skb. + * + * Does not change skb->protocol so this function can be used during receive. + */ +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, + __be16 vlan_proto, u16 vlan_tci) +{ + return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); +} + +/** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol diff --git a/include/linux/init.h b/include/linux/init.h index 506a98151131..bc27cf03c41e 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -6,10 +6,10 @@ #include <linux/types.h> /* Built-in __init functions needn't be compiled with retpoline */ -#if defined(RETPOLINE) && !defined(MODULE) -#define __noretpoline __attribute__((indirect_branch("keep"))) +#if defined(__noretpoline) && !defined(MODULE) +#define __noinitretpoline __noretpoline #else -#define __noretpoline +#define __noinitretpoline #endif /* These macros are used to mark some functions or @@ -47,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __latent_entropy __noretpoline +#define __init __section(.init.text) __cold __latent_entropy __noinitretpoline #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index c00c4c33e432..b26eccc78fb1 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -503,6 +503,7 @@ #define ICH_HCR_EN (1 << 0) #define ICH_HCR_UIE (1 << 1) +#define ICH_HCR_NPIE (1 << 3) #define ICH_HCR_TC (1 << 10) #define ICH_HCR_TALL0 (1 << 11) #define ICH_HCR_TALL1 (1 << 12) diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index d3453ee072fc..68d8b1f73682 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -84,6 +84,7 @@ #define GICH_HCR_EN (1 << 0) #define GICH_HCR_UIE (1 << 1) +#define GICH_HCR_NPIE (1 << 3) #define GICH_LR_VIRTUALID (0x3ff << 0) #define GICH_LR_PHYSID_CPUID_SHIFT (10) diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index b6a29c126cc4..b46b541c67c4 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -151,6 +151,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_invalidate_initmem(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -198,6 +199,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static inline void jump_label_invalidate_initmem(void) {} + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely(static_key_count(key) > 0)) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ce51455e2adf..3fd291503576 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -472,6 +472,7 @@ extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); +extern int init_kernel_text(unsigned long addr); extern int core_kernel_data(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ac0062b74aed..6930c63126c7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1105,7 +1105,6 @@ static inline void kvm_irq_routing_update(struct kvm *kvm) { } #endif -void kvm_arch_irq_routing_update(struct kvm *kvm); static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { @@ -1114,6 +1113,8 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) #endif /* CONFIG_HAVE_KVM_EVENTFD */ +void kvm_arch_irq_routing_update(struct kvm *kvm); + static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* @@ -1272,4 +1273,7 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, } #endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ +void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, + unsigned long start, unsigned long end); + #endif diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8be5077efb5f..f92ea7783652 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -187,7 +187,6 @@ int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -unsigned long memblock_next_valid_pfn(unsigned long pfn, unsigned long max_pfn); /** * for_each_mem_pfn_range - early memory pfn range iterator diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 6ed79a8a8318..9d3a03364e6e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -453,8 +453,8 @@ struct mlx5_core_srq { struct mlx5_core_rsc_common common; /* must be first */ u32 srqn; int max; - int max_gs; - int max_avail_gather; + size_t max_gs; + size_t max_avail_gather; int wqe_shift; void (*event) (struct mlx5_core_srq *, enum mlx5_event); diff --git a/include/linux/net.h b/include/linux/net.h index 91216b16feb7..2a0391eea05c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -222,6 +222,7 @@ enum { int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); +bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 1313b35c3ab7..14529511c4b8 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -285,6 +285,8 @@ unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); +int xt_check_proc_name(const char *name, unsigned int size); + int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto, diff --git a/include/linux/nospec.h b/include/linux/nospec.h index fbc98e2c8228..e791ebc65c9c 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -5,6 +5,7 @@ #ifndef _LINUX_NOSPEC_H #define _LINUX_NOSPEC_H +#include <asm/barrier.h> /** * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise @@ -30,26 +31,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, #endif /* - * Warn developers about inappropriate array_index_nospec() usage. - * - * Even if the CPU speculates past the WARN_ONCE branch, the - * sign bit of @index is taken into account when generating the - * mask. - * - * This warning is compiled out when the compiler can infer that - * @index and @size are less than LONG_MAX. - */ -#define array_index_mask_nospec_check(index, size) \ -({ \ - if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX, \ - "array_index_nospec() limited to range of [0, LONG_MAX]\n")) \ - _mask = 0; \ - else \ - _mask = array_index_mask_nospec(index, size); \ - _mask; \ -}) - -/* * array_index_nospec - sanitize an array index after a bounds check * * For a code sequence like: @@ -67,12 +48,11 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, ({ \ typeof(index) _i = (index); \ typeof(size) _s = (size); \ - unsigned long _mask = array_index_mask_nospec_check(_i, _s); \ + unsigned long _mask = array_index_mask_nospec(_i, _s); \ \ BUILD_BUG_ON(sizeof(_i) > sizeof(long)); \ BUILD_BUG_ON(sizeof(_s) > sizeof(long)); \ \ - _i &= _mask; \ - _i; \ + (typeof(_i)) (_i & _mask); \ }) #endif /* _LINUX_NOSPEC_H */ diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 88865e0ebf4d..091033a6b836 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -13,7 +13,6 @@ struct device_node; struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); -int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); int of_pci_parse_bus_range(struct device_node *node, struct resource *res); int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); @@ -34,12 +33,6 @@ static inline int of_pci_get_devfn(struct device_node *np) } static inline int -of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) -{ - return 0; -} - -static inline int of_pci_parse_bus_range(struct device_node *node, struct resource *res) { return -EINVAL; @@ -67,6 +60,16 @@ of_pci_get_max_link_speed(struct device_node *node) static inline void of_pci_check_probe_only(void) { } #endif +#if IS_ENABLED(CONFIG_OF_IRQ) +int of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin); +#else +static inline int +of_irq_parse_and_map_pci(const struct pci_dev *dev, u8 slot, u8 pin) +{ + return 0; +} +#endif + #if defined(CONFIG_OF_ADDRESS) int of_pci_get_host_bridge_resources(struct device_node *dev, unsigned char busno, unsigned char bus_max, diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 864d167a1073..009cdf3d65b6 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -30,10 +30,14 @@ * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it - * calls percpu_ref_kill(), then hlist_del_rcu() and synchronize_rcu() to remove - * the kioctx from the proccess's list of kioctxs - after that, there can't be - * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop - * the initial ref with percpu_ref_put(). + * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. + * After that, there can't be any new users of the kioctx (from lookup_ioctx()) + * and it's then safe to drop the initial ref with percpu_ref_put(). + * + * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() + * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't + * imply RCU grace periods of any kind and if a user wants to combine percpu_ref + * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped @@ -113,8 +117,10 @@ void percpu_ref_reinit(struct percpu_ref *ref); * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * - * Puts @ref in non percpu mode, then does a call_rcu() before gathering up the - * percpu counters and dropping the initial ref. + * Switches @ref into atomic mode before gathering up the percpu counters + * and dropping the initial ref. + * + * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { diff --git a/include/linux/phy.h b/include/linux/phy.h index 5a0c3e53e7c2..7c4c2379e010 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -924,6 +924,7 @@ void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); +int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); @@ -983,6 +984,10 @@ static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; } +int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, + u16 regnum); +int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, + u16 regnum, u16 val); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); @@ -1011,7 +1016,6 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); -void phy_change(struct phy_device *phydev); void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index c9df2527e0cd..668a21f04b09 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -766,8 +766,10 @@ slow_path: if (!key || (params.obj_cmpfn ? params.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head)))) + rhashtable_compare(&arg, rht_obj(ht, head)))) { + pprev = &head->next; continue; + } data = rht_obj(ht, head); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c1e66bdcf583..99df17109e1b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3285,8 +3285,7 @@ int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); -unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); -bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu); +bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); @@ -4038,6 +4037,12 @@ static inline bool skb_is_gso_v6(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } +/* Note: Should be called only if skb_is_gso(skb) is true */ +static inline bool skb_is_gso_sctp(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; +} + static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; @@ -4045,6 +4050,22 @@ static inline void skb_gso_reset(struct sk_buff *skb) skb_shinfo(skb)->gso_type = 0; } +static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, + u16 increment) +{ + if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) + return; + shinfo->gso_size += increment; +} + +static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, + u16 decrement) +{ + if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) + return; + shinfo->gso_size -= decrement; +} + void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) @@ -4104,38 +4125,6 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) return !skb->head_frag || skb_cloned(skb); } -/** - * skb_gso_network_seglen - Return length of individual segments of a gso packet - * - * @skb: GSO skb - * - * skb_gso_network_seglen is used to determine the real size of the - * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). - * - * The MAC/L2 header is not accounted for. - */ -static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) -{ - unsigned int hdr_len = skb_transport_header(skb) - - skb_network_header(skb); - return hdr_len + skb_gso_transport_seglen(skb); -} - -/** - * skb_gso_mac_seglen - Return length of individual segments of a gso packet - * - * @skb: GSO skb - * - * skb_gso_mac_seglen is used to determine the real size of the - * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 - * headers (TCP/UDP). - */ -static inline unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) -{ - unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - return hdr_len + skb_gso_transport_seglen(skb); -} - /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. diff --git a/include/linux/tty.h b/include/linux/tty.h index 0a6c71e0ad01..47f8af22f216 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -364,6 +364,7 @@ struct tty_file_private { #define TTY_PTY_LOCK 16 /* pty private */ #define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ #define TTY_HUPPED 18 /* Post driver->hangup() */ +#define TTY_HUPPING 19 /* Hangup in progress */ #define TTY_LDISC_HALTED 22 /* Line discipline is halted */ /* Values for tty->flow_change */ diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 5bdbd9f49395..07ee0f84a46c 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -90,6 +90,28 @@ static inline void u64_stats_update_end(struct u64_stats_sync *syncp) #endif } +static inline unsigned long +u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) +{ + unsigned long flags = 0; + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + local_irq_save(flags); + write_seqcount_begin(&syncp->seq); +#endif + return flags; +} + +static inline void +u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, + unsigned long flags) +{ +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_end(&syncp->seq); + local_irq_restore(flags); +#endif +} + static inline void u64_stats_update_begin_raw(struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index f1fcec2fd5f8..b7a99ce56bc9 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -63,4 +63,7 @@ */ #define USB_QUIRK_DISCONNECT_SUSPEND BIT(12) +/* Device needs a pause after every control message. */ +#define USB_QUIRK_DELAY_CTRL_MSG BIT(13) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index bc0cda180c8b..0c3301421c57 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -456,7 +456,6 @@ extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); -extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); diff --git a/include/media/demux.h b/include/media/demux.h index c4df6cee48e6..bf00a5a41a90 100644 --- a/include/media/demux.h +++ b/include/media/demux.h @@ -117,7 +117,7 @@ struct dmx_ts_feed { * specified by @filter_value that will be used on the filter * match logic. * @filter_mode: Contains a 16 bytes (128 bits) filter mode. - * @parent: Pointer to struct dmx_section_feed. + * @parent: Back-pointer to struct dmx_section_feed. * @priv: Pointer to private data of the API client. * * @@ -130,8 +130,9 @@ struct dmx_section_filter { u8 filter_value[DMX_MAX_FILTER_SIZE]; u8 filter_mask[DMX_MAX_FILTER_SIZE]; u8 filter_mode[DMX_MAX_FILTER_SIZE]; - struct dmx_section_feed *parent; /* Back-pointer */ - void *priv; /* Pointer to private data of the API client */ + struct dmx_section_feed *parent; + + void *priv; }; /** @@ -193,6 +194,10 @@ struct dmx_section_feed { * @buffer2: Pointer to the tail of the filtered TS packets, or NULL. * @buffer2_length: Length of the TS data in buffer2. * @source: Indicates which TS feed is the source of the callback. + * @buffer_flags: Address where buffer flags are stored. Those are + * used to report discontinuity users via DVB + * memory mapped API, as defined by + * &enum dmx_buffer_flags. * * This function callback prototype, provided by the client of the demux API, * is called from the demux code. The function is only called when filtering @@ -245,7 +250,8 @@ typedef int (*dmx_ts_cb)(const u8 *buffer1, size_t buffer1_length, const u8 *buffer2, size_t buffer2_length, - struct dmx_ts_feed *source); + struct dmx_ts_feed *source, + u32 *buffer_flags); /** * typedef dmx_section_cb - DVB demux TS filter callback function prototype @@ -261,6 +267,10 @@ typedef int (*dmx_ts_cb)(const u8 *buffer1, * including headers and CRC. * @source: Indicates which section feed is the source of the * callback. + * @buffer_flags: Address where buffer flags are stored. Those are + * used to report discontinuity users via DVB + * memory mapped API, as defined by + * &enum dmx_buffer_flags. * * This function callback prototype, provided by the client of the demux API, * is called from the demux code. The function is only called when @@ -286,7 +296,8 @@ typedef int (*dmx_section_cb)(const u8 *buffer1, size_t buffer1_len, const u8 *buffer2, size_t buffer2_len, - struct dmx_section_filter *source); + struct dmx_section_filter *source, + u32 *buffer_flags); /* * DVB Front-End diff --git a/include/media/dmxdev.h b/include/media/dmxdev.h index 2f5cb2c7b6a7..baafa3b8aca4 100644 --- a/include/media/dmxdev.h +++ b/include/media/dmxdev.h @@ -163,6 +163,7 @@ struct dmxdev_filter { * @demux: pointer to &struct dmx_demux. * @filternum: number of filters. * @capabilities: demux capabilities as defined by &enum dmx_demux_caps. + * @may_do_mmap: flag used to indicate if the device may do mmap. * @exit: flag to indicate that the demux is being released. * @dvr_orig_fe: pointer to &struct dmx_frontend. * @dvr_buffer: embedded &struct dvb_ringbuffer for DVB output. @@ -180,6 +181,7 @@ struct dmxdev { int filternum; int capabilities; + unsigned int may_do_mmap:1; unsigned int exit:1; #define DMXDEV_CAP_DUPLEX 1 struct dmx_frontend *dvr_orig_fe; diff --git a/include/media/dvb_demux.h b/include/media/dvb_demux.h index b07092038f4b..3b6aeca7a49e 100644 --- a/include/media/dvb_demux.h +++ b/include/media/dvb_demux.h @@ -115,6 +115,8 @@ struct dvb_demux_filter { * @pid: PID to be filtered. * @timeout: feed timeout. * @filter: pointer to &struct dvb_demux_filter. + * @buffer_flags: Buffer flags used to report discontinuity users via DVB + * memory mapped API, as defined by &enum dmx_buffer_flags. * @ts_type: type of TS, as defined by &enum ts_filter_type. * @pes_type: type of PES, as defined by &enum dmx_ts_pes. * @cc: MPEG-TS packet continuity counter @@ -145,6 +147,8 @@ struct dvb_demux_feed { ktime_t timeout; struct dvb_demux_filter *filter; + u32 buffer_flags; + enum ts_filter_type ts_type; enum dmx_ts_pes pes_type; diff --git a/include/media/dvb_vb2.h b/include/media/dvb_vb2.h index 01d1202d1a55..8cb88452cd6c 100644 --- a/include/media/dvb_vb2.h +++ b/include/media/dvb_vb2.h @@ -85,6 +85,12 @@ struct dvb_buffer { * @nonblocking: * If different than zero, device is operating on non-blocking * mode. + * @flags: buffer flags as defined by &enum dmx_buffer_flags. + * Filled only at &DMX_DQBUF. &DMX_QBUF should zero this field. + * @count: monotonic counter for filled buffers. Helps to identify + * data stream loses. Filled only at &DMX_DQBUF. &DMX_QBUF should + * zero this field. + * * @name: name of the device type. Currently, it can either be * "dvr" or "demux_filter". */ @@ -100,10 +106,14 @@ struct dvb_vb2_ctx { int buf_siz; int buf_cnt; int nonblocking; + + enum dmx_buffer_flags flags; + u32 count; + char name[DVB_VB2_NAME_MAX + 1]; }; -#ifndef DVB_MMAP +#ifndef CONFIG_DVB_MMAP static inline int dvb_vb2_init(struct dvb_vb2_ctx *ctx, const char *name, int non_blocking) { @@ -114,7 +124,7 @@ static inline int dvb_vb2_release(struct dvb_vb2_ctx *ctx) return 0; }; #define dvb_vb2_is_streaming(ctx) (0) -#define dvb_vb2_fill_buffer(ctx, file, wait) (0) +#define dvb_vb2_fill_buffer(ctx, file, wait, flags) (0) static inline __poll_t dvb_vb2_poll(struct dvb_vb2_ctx *ctx, struct file *file, @@ -153,9 +163,13 @@ int dvb_vb2_is_streaming(struct dvb_vb2_ctx *ctx); * @ctx: control struct for VB2 handler * @src: place where the data is stored * @len: number of bytes to be copied from @src + * @buffer_flags: + * pointer to buffer flags as defined by &enum dmx_buffer_flags. + * can be NULL. */ int dvb_vb2_fill_buffer(struct dvb_vb2_ctx *ctx, - const unsigned char *src, int len); + const unsigned char *src, int len, + enum dmx_buffer_flags *buffer_flags); /** * dvb_vb2_poll - Wrapper to vb2_core_streamon() for Digital TV diff --git a/include/net/devlink.h b/include/net/devlink.h index 6545b03e97f7..4de35ed12bcc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -257,6 +257,18 @@ struct devlink_resource_size_params { enum devlink_resource_unit unit; }; +static inline void +devlink_resource_size_params_init(struct devlink_resource_size_params *size_params, + u64 size_min, u64 size_max, + u64 size_granularity, + enum devlink_resource_unit unit) +{ + size_params->size_min = size_min; + size_params->size_max = size_max; + size_params->size_granularity = size_granularity; + size_params->unit = unit; +} + /** * struct devlink_resource - devlink resource * @name: name of the resource @@ -278,7 +290,7 @@ struct devlink_resource { u64 size_new; bool size_valid; struct devlink_resource *parent; - struct devlink_resource_size_params *size_params; + struct devlink_resource_size_params size_params; struct list_head list; struct list_head resource_list; const struct devlink_resource_ops *resource_ops; @@ -402,7 +414,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops); void devlink_resources_unregister(struct devlink *devlink, struct devlink_resource *resource); @@ -556,7 +568,7 @@ devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { return 0; diff --git a/include/net/ip.h b/include/net/ip.h index 746abff9ce51..f49b3a576bec 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -328,6 +328,13 @@ int ip_decrease_ttl(struct iphdr *iph) return --iph->ttl; } +static inline int ip_mtu_locked(const struct dst_entry *dst) +{ + const struct rtable *rt = (const struct rtable *)dst; + + return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU); +} + static inline int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { @@ -335,7 +342,7 @@ int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) return pmtudisc == IP_PMTUDISC_DO || (pmtudisc == IP_PMTUDISC_WANT && - !(dst_metric_locked(dst, RTAX_MTU))); + !ip_mtu_locked(dst)); } static inline bool ip_sk_accept_pmtu(const struct sock *sk) @@ -361,7 +368,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, struct net *net = dev_net(dst->dev); if (net->ipv4.sysctl_ip_fwd_use_pmtu || - dst_metric_locked(dst, RTAX_MTU) || + ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 27d23a65f3cd..ac0866bb9e93 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -179,6 +179,9 @@ void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); void rt6_multipath_rebalance(struct rt6_info *rt); +void rt6_uncached_list_add(struct rt6_info *rt); +void rt6_uncached_list_del(struct rt6_info *rt); + static inline const struct rt6_info *skb_rt6_info(const struct sk_buff *skb) { const struct dst_entry *dst = skb_dst(skb); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index f80524396c06..77d0a78cf7d2 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -59,6 +59,7 @@ struct fib_nh_exception { int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; + bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c96511fa9198..2b581bd93812 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2063,6 +2063,9 @@ struct ieee80211_txq { * @IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA: Hardware supports buffer STA on * TDLS links. * + * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't + * support QoS NDP for AP probing - that's most likely a driver bug. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2106,6 +2109,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_REPORTS_LOW_ACK, IEEE80211_HW_SUPPORTS_TX_FRAG, IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, + IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS diff --git a/include/net/route.h b/include/net/route.h index 1eb9ce470e25..20a92ca9e115 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -63,7 +63,8 @@ struct rtable { __be32 rt_gateway; /* Miscellaneous cached information */ - u32 rt_pmtu; + u32 rt_mtu_locked:1, + rt_pmtu:31; u32 rt_table_id; @@ -227,6 +228,9 @@ struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); +void rt_add_uncached_list(struct rtable *rt); +void rt_del_uncached_list(struct rtable *rt); + static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index e2ab13687fb9..2092d33194dd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -824,6 +824,16 @@ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) *to_free = skb; } +static inline void __qdisc_drop_all(struct sk_buff *skb, + struct sk_buff **to_free) +{ + if (skb->prev) + skb->prev->next = *to_free; + else + skb->next = *to_free; + *to_free = skb; +} + static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct qdisc_skb_head *qh, struct sk_buff **to_free) @@ -956,6 +966,15 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_DROP; } +static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + __qdisc_drop_all(skb, to_free); + qdisc_qstats_drop(sch); + + return NET_XMIT_DROP; +} + /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how long it will take to send a packet given its size. */ diff --git a/include/net/sock.h b/include/net/sock.h index 169c92afcafa..ae23f3b389ca 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1137,6 +1137,7 @@ struct proto { int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); +int sock_load_diag_module(int family, int protocol); #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 73b2387e3f74..ff3ed435701f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1537,10 +1537,6 @@ struct ib_xrcd { struct mutex tgt_qp_mutex; struct list_head tgt_qp_list; - /* - * Implementation details of the RDMA core, don't use in drivers: - */ - struct rdma_restrack_entry res; }; struct ib_ah { diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index d8d4a902a88d..2280b2351739 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -68,6 +68,9 @@ struct scsi_cmnd { struct list_head list; /* scsi_cmnd participates in queue lists */ struct list_head eh_entry; /* entry for the host eh_cmd_q */ struct delayed_work abort_work; + + struct rcu_head rcu; + int eh_eflags; /* Used by error handlr */ /* diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 1a1df0d21ee3..a8b7bf879ced 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -571,8 +571,6 @@ struct Scsi_Host { struct blk_mq_tag_set tag_set; }; - struct rcu_head rcu; - atomic_t host_busy; /* commands actually active on low-level */ atomic_t host_blocked; diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h index c2d1b15da136..a91f25151a5b 100644 --- a/include/soc/arc/mcip.h +++ b/include/soc/arc/mcip.h @@ -15,6 +15,7 @@ #define ARC_REG_MCIP_BCR 0x0d0 #define ARC_REG_MCIP_IDU_BCR 0x0D5 +#define ARC_REG_GFRC_BUILD 0x0D6 #define ARC_REG_MCIP_CMD 0x600 #define ARC_REG_MCIP_WDATA 0x601 #define ARC_REG_MCIP_READBACK 0x602 @@ -36,10 +37,14 @@ struct mcip_cmd { #define CMD_SEMA_RELEASE 0x12 #define CMD_DEBUG_SET_MASK 0x34 +#define CMD_DEBUG_READ_MASK 0x35 #define CMD_DEBUG_SET_SELECT 0x36 +#define CMD_DEBUG_READ_SELECT 0x37 #define CMD_GFRC_READ_LO 0x42 #define CMD_GFRC_READ_HI 0x43 +#define CMD_GFRC_SET_CORE 0x47 +#define CMD_GFRC_READ_CORE 0x48 #define CMD_IDU_ENABLE 0x71 #define CMD_IDU_DISABLE 0x72 diff --git a/include/trace/events/mmc.h b/include/trace/events/mmc.h index 200f731be557..7b706ff21335 100644 --- a/include/trace/events/mmc.h +++ b/include/trace/events/mmc.h @@ -86,8 +86,8 @@ TRACE_EVENT(mmc_request_start, __entry->stop_flags, __entry->stop_retries, __entry->sbc_opcode, __entry->sbc_arg, __entry->sbc_flags, __entry->sbc_retries, - __entry->blocks, __entry->blk_addr, - __entry->blksz, __entry->data_flags, __entry->tag, + __entry->blocks, __entry->blksz, + __entry->blk_addr, __entry->data_flags, __entry->tag, __entry->can_retune, __entry->doing_retune, __entry->retune_now, __entry->need_retune, __entry->hold_retune, __entry->retune_period) diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 85dc965afd89..99c902e460c2 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -102,13 +102,13 @@ typedef struct siginfo { short _addr_lsb; /* LSB of the reported address */ /* used when si_code=SEGV_BNDERR */ struct { - short _dummy_bnd; + void *_dummy_bnd; void __user *_lower; void __user *_upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { - short _dummy_pkey; + void *_dummy_pkey; __u32 _pkey; } _addr_pkey; }; diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index 91a31ffed828..9a781f0611df 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -63,6 +63,7 @@ struct drm_virtgpu_execbuffer { }; #define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */ +#define VIRTGPU_PARAM_CAPSET_QUERY_FIX 2 /* do we have the capset fix */ struct drm_virtgpu_getparam { __u64 param; diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 20d1490d6377..3c50e07ee833 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -131,7 +131,7 @@ enum { #define BLKTRACE_BDEV_SIZE 32 /* - * User setup structure passed with BLKTRACESTART + * User setup structure passed with BLKTRACESETUP */ struct blk_user_trace_setup { char name[BLKTRACE_BDEV_SIZE]; /* output */ diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index 5f3c5a918f00..b4112f0b6dd3 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -212,6 +212,32 @@ struct dmx_stc { }; /** + * enum dmx_buffer_flags - DMX memory-mapped buffer flags + * + * @DMX_BUFFER_FLAG_HAD_CRC32_DISCARD: + * Indicates that the Kernel discarded one or more frames due to wrong + * CRC32 checksum. + * @DMX_BUFFER_FLAG_TEI: + * Indicates that the Kernel has detected a Transport Error indicator + * (TEI) on a filtered pid. + * @DMX_BUFFER_PKT_COUNTER_MISMATCH: + * Indicates that the Kernel has detected a packet counter mismatch + * on a filtered pid. + * @DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED: + * Indicates that the Kernel has detected one or more frame discontinuity. + * @DMX_BUFFER_FLAG_DISCONTINUITY_INDICATOR: + * Received at least one packet with a frame discontinuity indicator. + */ + +enum dmx_buffer_flags { + DMX_BUFFER_FLAG_HAD_CRC32_DISCARD = 1 << 0, + DMX_BUFFER_FLAG_TEI = 1 << 1, + DMX_BUFFER_PKT_COUNTER_MISMATCH = 1 << 2, + DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED = 1 << 3, + DMX_BUFFER_FLAG_DISCONTINUITY_INDICATOR = 1 << 4, +}; + +/** * struct dmx_buffer - dmx buffer info * * @index: id number of the buffer @@ -220,15 +246,24 @@ struct dmx_stc { * offset from the start of the device memory for this plane, * (or a "cookie" that should be passed to mmap() as offset) * @length: size in bytes of the buffer + * @flags: bit array of buffer flags as defined by &enum dmx_buffer_flags. + * Filled only at &DMX_DQBUF. + * @count: monotonic counter for filled buffers. Helps to identify + * data stream loses. Filled only at &DMX_DQBUF. * * Contains data exchanged by application and driver using one of the streaming * I/O methods. + * + * Please notice that, for &DMX_QBUF, only @index should be filled. + * On &DMX_DQBUF calls, all fields will be filled by the Kernel. */ struct dmx_buffer { __u32 index; __u32 bytesused; __u32 offset; __u32 length; + __u32 flags; + __u32 count; }; /** diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 8bbbcb5cd94b..820de5d222d2 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -30,6 +30,7 @@ */ #define ETH_ALEN 6 /* Octets in one ethernet addr */ +#define ETH_TLEN 2 /* Octets in ethernet type field */ #define ETH_HLEN 14 /* Total octets in header. */ #define ETH_ZLEN 60 /* Min. octets in frame sans FCS */ #define ETH_DATA_LEN 1500 /* Max. octets in payload */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0fb5ef939732..7b26d4b0b052 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt { #define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 #define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) /* * Extension capability list. @@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_AIS_MIGRATION 150 #define KVM_CAP_PPC_GET_CPU_CHAR 151 #define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 4fe580d36e41..f5bf06ecd87d 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -54,7 +54,6 @@ #define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW) #define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE) #define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2) -#define LIRC_CAN_SEND_SCANCODE LIRC_MODE2SEND(LIRC_MODE_SCANCODE) #define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE) #define LIRC_CAN_SEND_MASK 0x0000003f diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index 3d77fe91239a..9008f31c7eb6 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -42,7 +42,7 @@ typedef enum { SEV_RET_INVALID_PLATFORM_STATE, SEV_RET_INVALID_GUEST_STATE, SEV_RET_INAVLID_CONFIG, - SEV_RET_INVALID_len, + SEV_RET_INVALID_LEN, SEV_RET_ALREADY_OWNED, SEV_RET_INVALID_CERTIFICATE, SEV_RET_POLICY_FAILURE, diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h index 17a022c5b414..da3315ed1bcd 100644 --- a/include/uapi/linux/usb/audio.h +++ b/include/uapi/linux/usb/audio.h @@ -370,7 +370,7 @@ static inline __u8 uac_processing_unit_bControlSize(struct uac_processing_unit_d { return (protocol == UAC_VERSION_1) ? desc->baSourceID[desc->bNrInPins + 4] : - desc->baSourceID[desc->bNrInPins + 6]; + 2; /* in UAC2, this value is constant */ } static inline __u8 *uac_processing_unit_bmControls(struct uac_processing_unit_descriptor *desc, @@ -378,7 +378,7 @@ static inline __u8 *uac_processing_unit_bmControls(struct uac_processing_unit_de { return (protocol == UAC_VERSION_1) ? &desc->baSourceID[desc->bNrInPins + 5] : - &desc->baSourceID[desc->bNrInPins + 7]; + &desc->baSourceID[desc->bNrInPins + 6]; } static inline __u8 uac_processing_unit_iProcessing(struct uac_processing_unit_descriptor *desc, diff --git a/include/uapi/misc/ocxl.h b/include/uapi/misc/ocxl.h index 4b0b0b756f3e..0af83d80fb3e 100644 --- a/include/uapi/misc/ocxl.h +++ b/include/uapi/misc/ocxl.h @@ -32,6 +32,22 @@ struct ocxl_ioctl_attach { __u64 reserved3; }; +struct ocxl_ioctl_metadata { + __u16 version; // struct version, always backwards compatible + + // Version 0 fields + __u8 afu_version_major; + __u8 afu_version_minor; + __u32 pasid; // PASID assigned to the current context + + __u64 pp_mmio_size; // Per PASID MMIO size + __u64 global_mmio_size; + + // End version 0 fields + + __u64 reserved[13]; // Total of 16*u64 +}; + struct ocxl_ioctl_irq_fd { __u64 irq_offset; __s32 eventfd; @@ -45,5 +61,6 @@ struct ocxl_ioctl_irq_fd { #define OCXL_IOCTL_IRQ_ALLOC _IOR(OCXL_MAGIC, 0x11, __u64) #define OCXL_IOCTL_IRQ_FREE _IOW(OCXL_MAGIC, 0x12, __u64) #define OCXL_IOCTL_IRQ_SET_FD _IOW(OCXL_MAGIC, 0x13, struct ocxl_ioctl_irq_fd) +#define OCXL_IOCTL_GET_METADATA _IOR(OCXL_MAGIC, 0x14, struct ocxl_ioctl_metadata) #endif /* _UAPI_MISC_OCXL_H */ diff --git a/init/main.c b/init/main.c index a8100b954839..21efbf6ace93 100644 --- a/init/main.c +++ b/init/main.c @@ -89,6 +89,7 @@ #include <linux/io.h> #include <linux/cache.h> #include <linux/rodata_test.h> +#include <linux/jump_label.h> #include <asm/io.h> #include <asm/bugs.h> @@ -1000,6 +1001,7 @@ static int __ref kernel_init(void *unused) /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); ftrace_free_init_mem(); + jump_label_invalidate_initmem(); free_initmem(); mark_readonly(); system_state = SYSTEM_RUNNING; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d7f309f74dec..a808f29d4c5a 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -325,9 +325,8 @@ err: static int mqueue_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - struct ipc_namespace *ns = data; + struct ipc_namespace *ns = sb->s_fs_info; - sb->s_fs_info = ns; sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; @@ -344,44 +343,18 @@ static int mqueue_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static struct file_system_type mqueue_fs_type; -/* - * Return value is pinned only by reference in ->mq_mnt; it will - * live until ipcns dies. Caller does not need to drop it. - */ -static struct vfsmount *mq_internal_mount(void) -{ - struct ipc_namespace *ns = current->nsproxy->ipc_ns; - struct vfsmount *m = ns->mq_mnt; - if (m) - return m; - m = kern_mount_data(&mqueue_fs_type, ns); - spin_lock(&mq_lock); - if (unlikely(ns->mq_mnt)) { - spin_unlock(&mq_lock); - if (!IS_ERR(m)) - kern_unmount(m); - return ns->mq_mnt; - } - if (!IS_ERR(m)) - ns->mq_mnt = m; - spin_unlock(&mq_lock); - return m; -} - static struct dentry *mqueue_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - struct vfsmount *m; - if (flags & SB_KERNMOUNT) - return mount_nodev(fs_type, flags, data, mqueue_fill_super); - m = mq_internal_mount(); - if (IS_ERR(m)) - return ERR_CAST(m); - atomic_inc(&m->mnt_sb->s_active); - down_write(&m->mnt_sb->s_umount); - return dget(m->mnt_root); + struct ipc_namespace *ns; + if (flags & SB_KERNMOUNT) { + ns = data; + data = NULL; + } else { + ns = current->nsproxy->ipc_ns; + } + return mount_ns(fs_type, flags, data, ns, ns->user_ns, mqueue_fill_super); } static void init_once(void *foo) @@ -771,16 +744,13 @@ static int prepare_open(struct dentry *dentry, int oflag, int ro, static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, struct mq_attr *attr) { - struct vfsmount *mnt = mq_internal_mount(); - struct dentry *root; + struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt; + struct dentry *root = mnt->mnt_root; struct filename *name; struct path path; int fd, error; int ro; - if (IS_ERR(mnt)) - return PTR_ERR(mnt); - audit_mq_open(oflag, mode, attr); if (IS_ERR(name = getname(u_name))) @@ -791,7 +761,6 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, goto out_putname; ro = mnt_want_write(mnt); /* we'll drop it in any case */ - root = mnt->mnt_root; inode_lock(d_inode(root)); path.dentry = lookup_one_len(name->name, root, strlen(name->name)); if (IS_ERR(path.dentry)) { @@ -840,9 +809,6 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; struct vfsmount *mnt = ipc_ns->mq_mnt; - if (!mnt) - return -ENOENT; - name = getname(u_name); if (IS_ERR(name)) return PTR_ERR(name); @@ -1569,26 +1535,28 @@ int mq_init_ns(struct ipc_namespace *ns) ns->mq_msgsize_max = DFLT_MSGSIZEMAX; ns->mq_msg_default = DFLT_MSG; ns->mq_msgsize_default = DFLT_MSGSIZE; - ns->mq_mnt = NULL; + ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns); + if (IS_ERR(ns->mq_mnt)) { + int err = PTR_ERR(ns->mq_mnt); + ns->mq_mnt = NULL; + return err; + } return 0; } void mq_clear_sbinfo(struct ipc_namespace *ns) { - if (ns->mq_mnt) - ns->mq_mnt->mnt_sb->s_fs_info = NULL; + ns->mq_mnt->mnt_sb->s_fs_info = NULL; } void mq_put_mnt(struct ipc_namespace *ns) { - if (ns->mq_mnt) - kern_unmount(ns->mq_mnt); + kern_unmount(ns->mq_mnt); } static int __init init_mqueue_fs(void) { - struct vfsmount *m; int error; mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache", @@ -1610,10 +1578,6 @@ static int __init init_mqueue_fs(void) if (error) goto out_filesystem; - m = kern_mount_data(&mqueue_fs_type, &init_ipc_ns); - if (IS_ERR(m)) - goto out_filesystem; - init_ipc_ns.mq_mnt = m; return 0; out_filesystem: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e24aa3241387..43f95d190eea 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1845,7 +1845,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz union bpf_attr attr = {}; int err; - if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled) + if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; err = check_uarg_tail_zero(uattr, sizeof(attr), size); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5fb69a85d967..c6eff108aa99 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1356,6 +1356,13 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_CTX; } +static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = cur_regs(env) + regno; + + return type_is_pkt_pointer(reg->type); +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -1416,10 +1423,10 @@ static int check_generic_ptr_alignment(struct bpf_verifier_env *env, } static int check_ptr_alignment(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, - int off, int size) + const struct bpf_reg_state *reg, int off, + int size, bool strict_alignment_once) { - bool strict = env->strict_alignment; + bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { @@ -1576,9 +1583,9 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ -static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, - int bpf_size, enum bpf_access_type t, - int value_regno) +static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, + int off, int bpf_size, enum bpf_access_type t, + int value_regno, bool strict_alignment_once) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; @@ -1590,7 +1597,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return size; /* alignment checks will add in reg->off themselves */ - err = check_ptr_alignment(env, reg, off, size); + err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; @@ -1735,21 +1742,23 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return -EACCES; } - if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_XADD stores into R%d context is not allowed\n", - insn->dst_reg); + if (is_ctx_reg(env, insn->dst_reg) || + is_pkt_reg(env, insn->dst_reg)) { + verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", + insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ? + "context" : "packet"); return -EACCES; } /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, -1); + BPF_SIZE(insn->code), BPF_READ, -1, true); if (err) return err; /* check whether atomic_add can write into the same memory */ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, -1); + BPF_SIZE(insn->code), BPF_WRITE, -1, true); } /* when register 'regno' is passed into function that will read 'access_size' @@ -2388,7 +2397,8 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { - err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1); + err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, + BPF_WRITE, -1, false); if (err) return err; } @@ -4632,7 +4642,7 @@ static int do_check(struct bpf_verifier_env *env) */ err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, - insn->dst_reg); + insn->dst_reg, false); if (err) return err; @@ -4684,7 +4694,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, - insn->src_reg); + insn->src_reg, false); if (err) return err; @@ -4719,7 +4729,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, - -1); + -1, false); if (err) return err; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8cda3bc3ae22..4bfb2908ec15 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3183,6 +3183,16 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) if (cgroup_is_threaded(cgrp)) return 0; + /* + * If @cgroup is populated or has domain controllers enabled, it + * can't be switched. While the below cgroup_can_be_thread_root() + * test can catch the same conditions, that's only when @parent is + * not mixable, so let's check it explicitly. + */ + if (cgroup_is_populated(cgrp) || + cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) + return -EOPNOTSUPP; + /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) diff --git a/kernel/compat.c b/kernel/compat.c index 3247fe761f60..3f5fa8902e7d 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -488,25 +488,6 @@ get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat) } EXPORT_SYMBOL_GPL(get_compat_sigset); -int -put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, - unsigned int size) -{ - /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ -#ifdef __BIG_ENDIAN - compat_sigset_t v; - switch (_NSIG_WORDS) { - case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; - case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; - case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; - case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; - } - return copy_to_user(compat, &v, size) ? -EFAULT : 0; -#else - return copy_to_user(compat, set, size) ? -EFAULT : 0; -#endif -} - #ifdef CONFIG_NUMA COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, compat_uptr_t __user *, pages32, diff --git a/kernel/events/core.c b/kernel/events/core.c index 96db9ae5d5af..709a55b9ad97 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -724,9 +724,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp) static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp_out = cpuctx->cgrp; - if (cgrp_out) - __update_cgrp_time(cgrp_out); + struct perf_cgroup *cgrp = cpuctx->cgrp; + struct cgroup_subsys_state *css; + + if (cgrp) { + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + __update_cgrp_time(cgrp); + } + } } static inline void update_cgrp_time_from_event(struct perf_event *event) @@ -754,6 +760,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, { struct perf_cgroup *cgrp; struct perf_cgroup_info *info; + struct cgroup_subsys_state *css; /* * ctx->lock held by caller @@ -764,8 +771,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, return; cgrp = perf_cgroup_from_task(task, ctx); - info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + info = this_cpu_ptr(cgrp->info); + info->timestamp = ctx->timestamp; + } } static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); @@ -2246,7 +2257,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, struct perf_event_context *task_ctx, enum event_type_t event_type) { - enum event_type_t ctx_event_type = event_type & EVENT_ALL; + enum event_type_t ctx_event_type; bool cpu_event = !!(event_type & EVENT_CPU); /* @@ -2256,6 +2267,8 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, if (event_type & EVENT_PINNED) event_type |= EVENT_FLEXIBLE; + ctx_event_type = event_type & EVENT_ALL; + perf_pmu_disable(cpuctx->ctx.pmu); if (task_ctx) task_ctx_sched_out(cpuctx, task_ctx, event_type); diff --git a/kernel/extable.c b/kernel/extable.c index a17fdb63dc3e..6a5b61ebc66c 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -64,7 +64,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -static inline int init_kernel_text(unsigned long addr) +int init_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_sinittext && addr < (unsigned long)_einittext) diff --git a/kernel/fail_function.c b/kernel/fail_function.c index 21b0122cb39c..1d5632d8bbcc 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -14,6 +14,15 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs); +static void fei_post_handler(struct kprobe *kp, struct pt_regs *regs, + unsigned long flags) +{ + /* + * A dummy post handler is required to prohibit optimizing, because + * jump optimization does not support execution path overriding. + */ +} + struct fei_attr { struct list_head list; struct kprobe kp; @@ -56,6 +65,7 @@ static struct fei_attr *fei_attr_new(const char *sym, unsigned long addr) return NULL; } attr->kp.pre_handler = fei_kprobe_handler; + attr->kp.post_handler = fei_post_handler; attr->retval = adjust_error_retval(addr, 0); INIT_LIST_HEAD(&attr->list); } diff --git a/kernel/jump_label.c b/kernel/jump_label.c index b4517095db6a..01ebdf1f9f40 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -16,6 +16,7 @@ #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> +#include <asm/sections.h> #ifdef HAVE_JUMP_LABEL @@ -366,12 +367,16 @@ static void __jump_label_update(struct static_key *key, { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { /* - * entry->code set to 0 invalidates module init text sections - * kernel_text_address() verifies we are not in core kernel - * init code, see jump_label_invalidate_module_init(). + * An entry->code of 0 indicates an entry which has been + * disabled because it was in an init text area. */ - if (entry->code && kernel_text_address(entry->code)) - arch_jump_label_transform(entry, jump_label_type(entry)); + if (entry->code) { + if (kernel_text_address(entry->code)) + arch_jump_label_transform(entry, jump_label_type(entry)); + else + WARN_ONCE(1, "can't patch jump_label at %pS", + (void *)(unsigned long)entry->code); + } } } @@ -417,6 +422,19 @@ void __init jump_label_init(void) cpus_read_unlock(); } +/* Disable any jump label entries in __init/__exit code */ +void __init jump_label_invalidate_initmem(void) +{ + struct jump_entry *iter_start = __start___jump_table; + struct jump_entry *iter_stop = __stop___jump_table; + struct jump_entry *iter; + + for (iter = iter_start; iter < iter_stop; iter++) { + if (init_section_contains((void *)(unsigned long)iter->code, 1)) + iter->code = 0; + } +} + #ifdef CONFIG_MODULES static enum jump_label_type jump_label_init_type(struct jump_entry *entry) @@ -633,6 +651,7 @@ static void jump_label_del_module(struct module *mod) } } +/* Disable any jump label entries in module init code */ static void jump_label_invalidate_module_init(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 858a07590e39..2048359f33d2 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -1082,15 +1082,16 @@ static noinline int __sched __mutex_lock_interruptible_slowpath(struct mutex *lock); /** - * mutex_lock_interruptible - acquire the mutex, interruptible - * @lock: the mutex to be acquired + * mutex_lock_interruptible() - Acquire the mutex, interruptible by signals. + * @lock: The mutex to be acquired. * - * Lock the mutex like mutex_lock(), and return 0 if the mutex has - * been acquired or sleep until the mutex becomes available. If a - * signal arrives while waiting for the lock then this function - * returns -EINTR. + * Lock the mutex like mutex_lock(). If a signal is delivered while the + * process is sleeping, this function will return without acquiring the + * mutex. * - * This function is similar to (but not equivalent to) down_interruptible(). + * Context: Process context. + * Return: 0 if the lock was successfully acquired or %-EINTR if a + * signal arrived. */ int __sched mutex_lock_interruptible(struct mutex *lock) { @@ -1104,6 +1105,18 @@ int __sched mutex_lock_interruptible(struct mutex *lock) EXPORT_SYMBOL(mutex_lock_interruptible); +/** + * mutex_lock_killable() - Acquire the mutex, interruptible by fatal signals. + * @lock: The mutex to be acquired. + * + * Lock the mutex like mutex_lock(). If a signal which will be fatal to + * the current process is delivered while the process is sleeping, this + * function will return without acquiring the mutex. + * + * Context: Process context. + * Return: 0 if the lock was successfully acquired or %-EINTR if a + * fatal signal arrived. + */ int __sched mutex_lock_killable(struct mutex *lock) { might_sleep(); @@ -1115,6 +1128,16 @@ int __sched mutex_lock_killable(struct mutex *lock) } EXPORT_SYMBOL(mutex_lock_killable); +/** + * mutex_lock_io() - Acquire the mutex and mark the process as waiting for I/O + * @lock: The mutex to be acquired. + * + * Lock the mutex like mutex_lock(). While the task is waiting for this + * mutex, it will be accounted as being in the IO wait state by the + * scheduler. + * + * Context: Process context. + */ void __sched mutex_lock_io(struct mutex *lock) { int token; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 65cc0cb984e6..940633c63254 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1616,11 +1616,12 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) { DEFINE_WAKE_Q(wake_q); + unsigned long flags; bool postunlock; - raw_spin_lock_irq(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); postunlock = __rt_mutex_futex_unlock(lock, &wake_q); - raw_spin_unlock_irq(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); if (postunlock) rt_mutex_postunlock(&wake_q); diff --git a/kernel/memremap.c b/kernel/memremap.c index 4849be5f9b3c..895e6b76b25e 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -275,8 +275,15 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap) return (res->start + resource_size(res)) >> PAGE_SHIFT; } +static unsigned long pfn_next(unsigned long pfn) +{ + if (pfn % 1024 == 0) + cond_resched(); + return pfn + 1; +} + #define for_each_device_pfn(pfn, map) \ - for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++) + for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn)) static void devm_memremap_pages_release(void *data) { @@ -337,10 +344,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) resource_size_t align_start, align_size, align_end; struct vmem_altmap *altmap = pgmap->altmap_valid ? &pgmap->altmap : NULL; + struct resource *res = &pgmap->res; unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; - int error, nid, is_ram, i = 0; - struct resource *res = &pgmap->res; + int error, nid, is_ram; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -409,8 +416,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(pgmap->ref); - if (!(++i % 1024)) - cond_resched(); } devm_add_action(dev, devm_memremap_pages_release, pgmap); @@ -422,7 +427,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) err_pfn_remap: err_radix: pgmap_radix_release(res, pgoff); - devres_free(pgmap); return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); diff --git a/kernel/module.c b/kernel/module.c index ad2d420024f6..e42764acedb4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4228,7 +4228,7 @@ static int modules_open(struct inode *inode, struct file *file) m->private = kallsyms_show_value() ? NULL : (void *)8ul; } - return 0; + return err; } static const struct file_operations proc_modules_operations = { diff --git a/kernel/panic.c b/kernel/panic.c index 2cfef408fec9..4b794f1d8561 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -640,7 +640,7 @@ device_initcall(register_warn_debugfs); */ __visible void __stack_chk_fail(void) { - panic("stack-protector: Kernel stack is corrupted in: %p\n", + panic("stack-protector: Kernel stack is corrupted in: %pB\n", __builtin_return_address(0)); } EXPORT_SYMBOL(__stack_chk_fail); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fc1123583fa6..f274fbef821d 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2397,7 +2397,7 @@ skip: if (console_lock_spinning_disable_and_check()) { printk_safe_exit_irqrestore(flags); - return; + goto out; } printk_safe_exit_irqrestore(flags); @@ -2430,6 +2430,7 @@ skip: if (retry && console_trylock()) goto again; +out: if (wake_klogd) wake_up_klogd(); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e7c535eee0a6..c94895bc5a2c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6683,13 +6683,18 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) parent_quota = parent_b->hierarchical_quota; /* - * Ensure max(child_quota) <= parent_quota, inherit when no + * Ensure max(child_quota) <= parent_quota. On cgroup2, + * always take the min. On cgroup1, only inherit when no * limit is set: */ - if (quota == RUNTIME_INF) - quota = parent_quota; - else if (parent_quota != RUNTIME_INF && quota > parent_quota) - return -EINVAL; + if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) { + quota = min(quota, parent_quota); + } else { + if (quota == RUNTIME_INF) + quota = parent_quota; + else if (parent_quota != RUNTIME_INF && quota > parent_quota) + return -EINVAL; + } } cfs_b->hierarchical_quota = quota; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 1ca0130ed4f9..72c401b3b15c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -32,7 +32,7 @@ static DEFINE_SPINLOCK(sched_debug_lock); if (m) \ seq_printf(m, x); \ else \ - printk(x); \ + pr_cont(x); \ } while (0) /* @@ -501,12 +501,12 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) { struct task_struct *g, *p; - SEQ_printf(m, - "\nrunnable tasks:\n" - " S task PID tree-key switches prio" - " wait-time sum-exec sum-sleep\n" - "-------------------------------------------------------" - "----------------------------------------------------\n"); + SEQ_printf(m, "\n"); + SEQ_printf(m, "runnable tasks:\n"); + SEQ_printf(m, " S task PID tree-key switches prio" + " wait-time sum-exec sum-sleep\n"); + SEQ_printf(m, "-------------------------------------------------------" + "----------------------------------------------------\n"); rcu_read_lock(); for_each_process_thread(g, p) { @@ -527,9 +527,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) unsigned long flags; #ifdef CONFIG_FAIR_GROUP_SCHED - SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg)); + SEQ_printf(m, "\n"); + SEQ_printf(m, "cfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg)); #else - SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); + SEQ_printf(m, "\n"); + SEQ_printf(m, "cfs_rq[%d]:\n", cpu); #endif SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", SPLIT_NS(cfs_rq->exec_clock)); @@ -595,9 +597,11 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) { #ifdef CONFIG_RT_GROUP_SCHED - SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg)); + SEQ_printf(m, "\n"); + SEQ_printf(m, "rt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg)); #else - SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); + SEQ_printf(m, "\n"); + SEQ_printf(m, "rt_rq[%d]:\n", cpu); #endif #define P(x) \ @@ -624,7 +628,8 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) { struct dl_bw *dl_bw; - SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); + SEQ_printf(m, "\n"); + SEQ_printf(m, "dl_rq[%d]:\n", cpu); #define PU(x) \ SEQ_printf(m, " .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x)) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 75043046914e..10b7186d0638 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -50,6 +50,7 @@ #include <linux/export.h> #include <linux/hashtable.h> #include <linux/compat.h> +#include <linux/nospec.h> #include "timekeeping.h" #include "posix-timers.h" @@ -1346,11 +1347,15 @@ static const struct k_clock * const posix_clocks[] = { static const struct k_clock *clockid_to_kclock(const clockid_t id) { - if (id < 0) + clockid_t idx = id; + + if (id < 0) { return (id & CLOCKFD_MASK) == CLOCKFD ? &clock_posix_dynamic : &clock_posix_cpu; + } - if (id >= ARRAY_SIZE(posix_clocks) || !posix_clocks[id]) + if (id >= ARRAY_SIZE(posix_clocks)) return NULL; - return posix_clocks[id]; + + return posix_clocks[array_index_nospec(idx, ARRAY_SIZE(posix_clocks))]; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 48150ab42de9..4a4fd567fb26 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1894,6 +1894,12 @@ int timers_dead_cpu(unsigned int cpu) raw_spin_lock_irq(&new_base->lock); raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + /* + * The current CPUs base clock might be stale. Update it + * before moving the timers over. + */ + forward_timer_base(new_base); + BUG_ON(old_base->running_timer); for (i = 0; i < WHEEL_SIZE; i++) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c0a9e310d715..01e6b3a38871 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -661,7 +661,41 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, +static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_perf_event_output: + return &bpf_perf_event_output_proto_tp; + case BPF_FUNC_get_stackid: + return &bpf_get_stackid_proto_tp; + default: + return tracing_func_proto(func_id); + } +} + +static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + + BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); + return true; +} + +const struct bpf_verifier_ops tracepoint_verifier_ops = { + .get_func_proto = tp_prog_func_proto, + .is_valid_access = tp_prog_is_valid_access, +}; + +const struct bpf_prog_ops tracepoint_prog_ops = { +}; + +BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; @@ -678,8 +712,8 @@ clear: return err; } -static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { - .func = bpf_perf_prog_read_value_tp, +static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { + .func = bpf_perf_prog_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -687,7 +721,7 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { .arg3_type = ARG_CONST_SIZE, }; -static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) +static const struct bpf_func_proto *pe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_perf_event_output: @@ -695,34 +729,12 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_perf_prog_read_value: - return &bpf_perf_prog_read_value_proto_tp; + return &bpf_perf_prog_read_value_proto; default: return tracing_func_proto(func_id); } } -static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, - struct bpf_insn_access_aux *info) -{ - if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - - BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); - return true; -} - -const struct bpf_verifier_ops tracepoint_verifier_ops = { - .get_func_proto = tp_prog_func_proto, - .is_valid_access = tp_prog_is_valid_access, -}; - -const struct bpf_prog_ops tracepoint_prog_ops = { -}; - static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { @@ -779,7 +791,7 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, } const struct bpf_verifier_ops perf_event_verifier_ops = { - .get_func_proto = tp_prog_func_proto, + .get_func_proto = pe_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 1fad24acd444..ae4147eaebd4 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -659,7 +659,7 @@ static int create_trace_kprobe(int argc, char **argv) char *symbol = NULL, *event = NULL, *group = NULL; int maxactive = 0; char *arg; - unsigned long offset = 0; + long offset = 0; void *addr = NULL; char buf[MAX_EVENT_NAME_LEN]; @@ -747,7 +747,7 @@ static int create_trace_kprobe(int argc, char **argv) symbol = argv[1]; /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); - if (ret) { + if (ret || offset < 0 || offset > UINT_MAX) { pr_info("Failed to parse either an address or a symbol.\n"); return ret; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index d59357308677..daf54bda4dc8 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -320,7 +320,7 @@ static fetch_func_t get_fetch_size_function(const struct fetch_type *type, } /* Split symbol and offset. */ -int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset) +int traceprobe_split_symbol_offset(char *symbol, long *offset) { char *tmp; int ret; @@ -328,13 +328,11 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset) if (!offset) return -EINVAL; - tmp = strchr(symbol, '+'); + tmp = strpbrk(symbol, "+-"); if (tmp) { - /* skip sign because kstrtoul doesn't accept '+' */ - ret = kstrtoul(tmp + 1, 0, offset); + ret = kstrtol(tmp, 0, offset); if (ret) return ret; - *tmp = '\0'; } else *offset = 0; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index e101c5bb9eda..6a4d3fa94042 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -365,7 +365,7 @@ extern int traceprobe_conflict_field_name(const char *name, extern void traceprobe_update_arg(struct probe_arg *arg); extern void traceprobe_free_probe_arg(struct probe_arg *arg); -extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset); +extern int traceprobe_split_symbol_offset(char *symbol, long *offset); /* Sum up total data length for dynamic arraies (strings) */ static nokprobe_inline int diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bb9a519cbf50..6ec6ba65127b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3018,14 +3018,6 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) return ret; } -/* - * See cancel_delayed_work() - */ -bool cancel_work(struct work_struct *work) -{ - return __cancel_work(work, false); -} - /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel @@ -5337,7 +5329,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) ret = device_register(&wq_dev->dev); if (ret) { - kfree(wq_dev); + put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } diff --git a/lib/btree.c b/lib/btree.c index f93a945274af..590facba2c50 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -3,7 +3,7 @@ * * As should be obvious for Linux kernel code, license is GPLv2 * - * Copyright (c) 2007-2008 Joern Engel <joern@logfs.org> + * Copyright (c) 2007-2008 Joern Engel <joern@purestorage.com> * Bits and pieces stolen from Peter Zijlstra's code, which is * Copyright 2007, Red Hat Inc. Peter Zijlstra * GPLv2 @@ -76,6 +76,8 @@ struct btree_geo btree_geo128 = { }; EXPORT_SYMBOL_GPL(btree_geo128); +#define MAX_KEYLEN (2 * LONG_PER_U64) + static struct kmem_cache *btree_cachep; void *btree_alloc(gfp_t gfp_mask, void *pool_data) @@ -313,7 +315,7 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo, { int i, height; unsigned long *node, *oldnode; - unsigned long *retry_key = NULL, key[geo->keylen]; + unsigned long *retry_key = NULL, key[MAX_KEYLEN]; if (keyzero(geo, __key)) return NULL; @@ -639,8 +641,8 @@ EXPORT_SYMBOL_GPL(btree_remove); int btree_merge(struct btree_head *target, struct btree_head *victim, struct btree_geo *geo, gfp_t gfp) { - unsigned long key[geo->keylen]; - unsigned long dup[geo->keylen]; + unsigned long key[MAX_KEYLEN]; + unsigned long dup[MAX_KEYLEN]; void *val; int err; diff --git a/lib/bug.c b/lib/bug.c index c1b0fad31b10..1077366f496b 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -150,6 +150,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) return BUG_TRAP_TYPE_NONE; bug = find_bug(bugaddr); + if (!bug) + return BUG_TRAP_TYPE_NONE; file = NULL; line = 0; @@ -191,7 +193,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) if (file) pr_crit("kernel BUG at %s:%u!\n", file, line); else - pr_crit("Kernel BUG at %p [verbose debug info unavailable]\n", + pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n", (void *)bugaddr); return BUG_TRAP_TYPE_BUG; diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 1b34d210452c..7f5cdc1e6b29 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1491,12 +1491,12 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, if (unlikely(virt == NULL)) return; - entry = dma_entry_alloc(); - if (!entry) + /* handle vmalloc and linear addresses */ + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) return; - /* handle vmalloc and linear addresses */ - if (!is_vmalloc_addr(virt) && !virt_to_page(virt)) + entry = dma_entry_alloc(); + if (!entry) return; entry->type = dma_debug_coherent; @@ -1528,7 +1528,7 @@ void debug_dma_free_coherent(struct device *dev, size_t size, }; /* handle vmalloc and linear addresses */ - if (!is_vmalloc_addr(virt) && !virt_to_page(virt)) + if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt)) return; if (is_vmalloc_addr(virt)) diff --git a/lib/idr.c b/lib/idr.c index 99ec5bc89d25..823b813f08f8 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -36,8 +36,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, { struct radix_tree_iter iter; void __rcu **slot; - int base = idr->idr_base; - int id = *nextid; + unsigned int base = idr->idr_base; + unsigned int id = *nextid; if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr))) return -EINVAL; @@ -204,10 +204,11 @@ int idr_for_each(const struct idr *idr, radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { int ret; + unsigned long id = iter.index + base; - if (WARN_ON_ONCE(iter.index > INT_MAX)) + if (WARN_ON_ONCE(id > INT_MAX)) break; - ret = fn(iter.index + base, rcu_dereference_raw(*slot), data); + ret = fn(id, rcu_dereference_raw(*slot), data); if (ret) return ret; } @@ -230,8 +231,8 @@ void *idr_get_next(struct idr *idr, int *nextid) { struct radix_tree_iter iter; void __rcu **slot; - int base = idr->idr_base; - int id = *nextid; + unsigned long base = idr->idr_base; + unsigned long id = *nextid; id = (id < base) ? 0 : id - base; slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); diff --git a/lib/ioremap.c b/lib/ioremap.c index b808a390e4c3..54e5bbaa3200 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) && - IS_ALIGNED(phys_addr + addr, PMD_SIZE)) { + IS_ALIGNED(phys_addr + addr, PMD_SIZE) && + pmd_free_pte_page(pmd)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue; } @@ -117,7 +118,8 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) && - IS_ALIGNED(phys_addr + addr, PUD_SIZE)) { + IS_ALIGNED(phys_addr + addr, PUD_SIZE) && + pud_free_pmd_page(pud)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue; } diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 30e7dd88148b..9f96fa7bc000 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -322,6 +322,8 @@ EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). + * + * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 3825c30aaa36..47de025b6245 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -506,8 +506,10 @@ static void *rhashtable_lookup_one(struct rhashtable *ht, if (!key || (ht->p.obj_cmpfn ? ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head)))) + rhashtable_compare(&arg, rht_obj(ht, head)))) { + pprev = &head->next; continue; + } if (!ht->rhlist) return rht_obj(ht, head); diff --git a/lib/test_bpf.c b/lib/test_bpf.c index b4e22345963f..3e9335493fe4 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -24,10 +24,11 @@ #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/highmem.h> +#include <linux/sched.h> /* General test specific settings */ #define MAX_SUBTESTS 3 -#define MAX_TESTRUNS 10000 +#define MAX_TESTRUNS 1000 #define MAX_DATA 128 #define MAX_INSNS 512 #define MAX_K 0xffffFFFF @@ -5466,7 +5467,7 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: Jump, gap, jump, ...", { }, -#ifdef CONFIG_BPF_JIT_ALWAYS_ON +#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_X86) CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, #else CLASSIC | FLAG_NO_DATA, @@ -6582,6 +6583,7 @@ static __init int test_bpf(void) struct bpf_prog *fp; int err; + cond_resched(); if (exclude_test(i)) continue; diff --git a/lib/test_kmod.c b/lib/test_kmod.c index e372b97eee13..0e5b7a61460b 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -1141,7 +1141,7 @@ static struct kmod_test_device *register_test_dev_kmod(void) mutex_lock(®_dev_mutex); /* int should suffice for number of devices, test for wrap */ - if (unlikely(num_test_devs + 1) < 0) { + if (num_test_devs + 1 == INT_MAX) { pr_err("reached limit of number of test devices\n"); goto out; } diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 76d3667fdea2..f4000c137dbe 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -79,6 +79,21 @@ struct thread_data { struct test_obj *objs; }; +static u32 my_hashfn(const void *data, u32 len, u32 seed) +{ + const struct test_obj_rhl *obj = data; + + return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE; +} + +static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) +{ + const struct test_obj_rhl *test_obj = obj; + const struct test_obj_val *val = arg->key; + + return test_obj->value.id - val->id; +} + static struct rhashtable_params test_rht_params = { .head_offset = offsetof(struct test_obj, node), .key_offset = offsetof(struct test_obj, value), @@ -87,6 +102,17 @@ static struct rhashtable_params test_rht_params = { .nulls_base = (3U << RHT_BASE_SHIFT), }; +static struct rhashtable_params test_rht_params_dup = { + .head_offset = offsetof(struct test_obj_rhl, list_node), + .key_offset = offsetof(struct test_obj_rhl, value), + .key_len = sizeof(struct test_obj_val), + .hashfn = jhash, + .obj_hashfn = my_hashfn, + .obj_cmpfn = my_cmpfn, + .nelem_hint = 128, + .automatic_shrinking = false, +}; + static struct semaphore prestart_sem; static struct semaphore startup_sem = __SEMAPHORE_INITIALIZER(startup_sem, 0); @@ -465,6 +491,112 @@ static int __init test_rhashtable_max(struct test_obj *array, return err; } +static unsigned int __init print_ht(struct rhltable *rhlt) +{ + struct rhashtable *ht; + const struct bucket_table *tbl; + char buff[512] = ""; + unsigned int i, cnt = 0; + + ht = &rhlt->ht; + tbl = rht_dereference(ht->tbl, ht); + for (i = 0; i < tbl->size; i++) { + struct rhash_head *pos, *next; + struct test_obj_rhl *p; + + pos = rht_dereference(tbl->buckets[i], ht); + next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; + + if (!rht_is_a_nulls(pos)) { + sprintf(buff, "%s\nbucket[%d] -> ", buff, i); + } + + while (!rht_is_a_nulls(pos)) { + struct rhlist_head *list = container_of(pos, struct rhlist_head, rhead); + sprintf(buff, "%s[[", buff); + do { + pos = &list->rhead; + list = rht_dereference(list->next, ht); + p = rht_obj(ht, pos); + + sprintf(buff, "%s val %d (tid=%d)%s", buff, p->value.id, p->value.tid, + list? ", " : " "); + cnt++; + } while (list); + + pos = next, + next = !rht_is_a_nulls(pos) ? + rht_dereference(pos->next, ht) : NULL; + + sprintf(buff, "%s]]%s", buff, !rht_is_a_nulls(pos) ? " -> " : ""); + } + } + printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff); + + return cnt; +} + +static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects, + int cnt, bool slow) +{ + struct rhltable rhlt; + unsigned int i, ret; + const char *key; + int err = 0; + + err = rhltable_init(&rhlt, &test_rht_params_dup); + if (WARN_ON(err)) + return err; + + for (i = 0; i < cnt; i++) { + rhl_test_objects[i].value.tid = i; + key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead); + key += test_rht_params_dup.key_offset; + + if (slow) { + err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key, + &rhl_test_objects[i].list_node.rhead)); + if (err == -EAGAIN) + err = 0; + } else + err = rhltable_insert(&rhlt, + &rhl_test_objects[i].list_node, + test_rht_params_dup); + if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast")) + goto skip_print; + } + + ret = print_ht(&rhlt); + WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast"); + +skip_print: + rhltable_destroy(&rhlt); + + return 0; +} + +static int __init test_insert_duplicates_run(void) +{ + struct test_obj_rhl rhl_test_objects[3] = {}; + + pr_info("test inserting duplicates\n"); + + /* two different values that map to same bucket */ + rhl_test_objects[0].value.id = 1; + rhl_test_objects[1].value.id = 21; + + /* and another duplicate with same as [0] value + * which will be second on the bucket list */ + rhl_test_objects[2].value.id = rhl_test_objects[0].value.id; + + test_insert_dup(rhl_test_objects, 2, false); + test_insert_dup(rhl_test_objects, 3, false); + test_insert_dup(rhl_test_objects, 2, true); + test_insert_dup(rhl_test_objects, 3, true); + + return 0; +} + static int thread_lookup_test(struct thread_data *tdata) { unsigned int entries = tdata->entries; @@ -613,6 +745,8 @@ static int __init test_rht_init(void) do_div(total_time, runs); pr_info("Average test time: %llu\n", total_time); + test_insert_duplicates_run(); + if (!tcount) return 0; @@ -516,7 +516,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; return -EBUSY; } @@ -890,7 +890,10 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, break; } if (*locked) { - /* VM_FAULT_RETRY didn't trigger */ + /* + * VM_FAULT_RETRY didn't trigger or it was a + * FOLL_NOWAIT. + */ if (!pages_done) pages_done = ret; break; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 87ab9b8f56b5..5a68730eebd6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -555,7 +555,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg, + true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1316,7 +1317,7 @@ alloc: } if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm, - huge_gfp, &memcg, true))) { + huge_gfp | __GFP_NORETRY, &memcg, true))) { put_page(new_page); split_huge_pmd(vma, vmf->pmd, vmf->address); if (page) @@ -2783,11 +2784,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); - lock_page(page); + if (!trylock_page(page)) + goto next; /* split_huge_page() removes page from list on success */ if (!split_huge_page(page)) split++; unlock_page(page); +next: put_page(page); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7c204e3d132b..976bbc5646fe 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -18,6 +18,7 @@ #include <linux/bootmem.h> #include <linux/sysfs.h> #include <linux/slab.h> +#include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> @@ -1583,7 +1584,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, page = NULL; } else { h->surplus_huge_pages++; - h->nr_huge_pages_node[page_to_nid(page)]++; + h->surplus_huge_pages_node[page_to_nid(page)]++; } out_unlock: @@ -4374,6 +4375,12 @@ int hugetlb_reserve_pages(struct inode *inode, struct resv_map *resv_map; long gbl_reserve; + /* This should never happen */ + if (from > to) { + VM_WARN(1, "%s called with a negative range\n", __func__); + return -EINVAL; + } + /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b7e2268dfc9a..e42568284e06 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -530,7 +530,12 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } - VM_BUG_ON_PAGE(PageCompound(page), page); + /* TODO: teach khugepaged to collapse THP mapped with pte */ + if (PageCompound(page)) { + result = SCAN_PAGE_COMPOUND; + goto out; + } + VM_BUG_ON_PAGE(!PageAnon(page), page); /* @@ -960,7 +965,9 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + /* Do not oom kill for khugepaged charges */ + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY, + &memcg, true))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1319,7 +1326,9 @@ static void collapse_shmem(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + /* Do not oom kill for khugepaged charges */ + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY, + &memcg, true))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } diff --git a/mm/memblock.c b/mm/memblock.c index 5a9ca2a1751b..48376bd33274 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1101,34 +1101,6 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, *out_nid = r->nid; } -unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn, - unsigned long max_pfn) -{ - struct memblock_type *type = &memblock.memory; - unsigned int right = type->cnt; - unsigned int mid, left = 0; - phys_addr_t addr = PFN_PHYS(pfn + 1); - - do { - mid = (right + left) / 2; - - if (addr < type->regions[mid].base) - right = mid; - else if (addr >= (type->regions[mid].base + - type->regions[mid].size)) - left = mid + 1; - else { - /* addr is within the region, so pfn + 1 is valid */ - return min(pfn + 1, max_pfn); - } - } while (left < right); - - if (right == type->cnt) - return max_pfn; - else - return min(PHYS_PFN(type->regions[right].base), max_pfn); -} - /** * memblock_set_node - set node ID on memblock regions * @base: base of area to set node ID for diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d879f1d8a44a..32cba0332787 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2124,6 +2124,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) case MPOL_INTERLEAVE: return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: + /* a's ->flags is the same as b's */ + if (a->flags & MPOL_F_LOCAL) + return true; return a->v.preferred_node == b->v.preferred_node; default: BUG(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cb416723538f..1741dd23e7c1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1910,7 +1910,9 @@ static int move_freepages(struct zone *zone, * Remove at a later date when no bug reports exist related to * grouping pages by mobility */ - VM_BUG_ON(page_zone(start_page) != page_zone(end_page)); + VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) && + pfn_valid(page_to_pfn(end_page)) && + page_zone(start_page) != page_zone(end_page)); #endif if (num_movable) @@ -3594,7 +3596,7 @@ static bool __need_fs_reclaim(gfp_t gfp_mask) return false; /* this guy won't enter reclaim */ - if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC)) + if (current->flags & PF_MEMALLOC) return false; /* We're only interested __GFP_FS allocations for now */ @@ -5354,17 +5356,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (context != MEMMAP_EARLY) goto not_early; - if (!early_pfn_valid(pfn)) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - /* - * Skip to the pfn preceding the next valid one (or - * end_pfn), such that we hit a valid pfn (or end_pfn) - * on our next iteration of the loop. - */ - pfn = memblock_next_valid_pfn(pfn, end_pfn) - 1; -#endif + if (!early_pfn_valid(pfn)) continue; - } if (!early_pfn_in_nid(pfn, nid)) continue; if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised)) diff --git a/mm/percpu-km.c b/mm/percpu-km.c index d2a76642c4ae..38de70ab1a0d 100644 --- a/mm/percpu-km.c +++ b/mm/percpu-km.c @@ -34,7 +34,7 @@ #include <linux/log2.h> static int pcpu_populate_chunk(struct pcpu_chunk *chunk, - int page_start, int page_end) + int page_start, int page_end, gfp_t gfp) { return 0; } @@ -45,18 +45,18 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, /* nada */ } -static struct pcpu_chunk *pcpu_create_chunk(void) +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT; struct pcpu_chunk *chunk; struct page *pages; int i; - chunk = pcpu_alloc_chunk(); + chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; - pages = alloc_pages(GFP_KERNEL, order_base_2(nr_pages)); + pages = alloc_pages(gfp, order_base_2(nr_pages)); if (!pages) { pcpu_free_chunk(chunk); return NULL; diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 9158e5a81391..d8078de912de 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -37,7 +37,7 @@ static struct page **pcpu_get_pages(void) lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) - pages = pcpu_mem_zalloc(pages_size); + pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } @@ -73,18 +73,21 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk, * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 + * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, - struct page **pages, int page_start, int page_end) + struct page **pages, int page_start, int page_end, + gfp_t gfp) { - const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM; unsigned int cpu, tcpu; int i; + gfp |= __GFP_HIGHMEM; + for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; @@ -262,6 +265,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page + * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. @@ -270,7 +274,7 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, - int page_start, int page_end) + int page_start, int page_end, gfp_t gfp) { struct page **pages; @@ -278,7 +282,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, if (!pages) return -ENOMEM; - if (pcpu_alloc_pages(chunk, pages, page_start, page_end)) + if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { @@ -325,12 +329,12 @@ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, pcpu_free_pages(chunk, pages, page_start, page_end); } -static struct pcpu_chunk *pcpu_create_chunk(void) +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; - chunk = pcpu_alloc_chunk(); + chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; diff --git a/mm/percpu.c b/mm/percpu.c index 50e7fdf84055..9297098519a6 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -80,6 +80,7 @@ #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> +#include <linux/sched.h> #include <asm/cacheflush.h> #include <asm/sections.h> @@ -447,26 +448,25 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate + * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, - * kzalloc() is used; otherwise, vzalloc() is used. The returned - * memory is always zeroed. - * - * CONTEXT: - * Does GFP_KERNEL allocation. + * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. + * This is to facilitate passing through whitelisted flags. The + * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ -static void *pcpu_mem_zalloc(size_t size) +static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) - return kzalloc(size, GFP_KERNEL); + return kzalloc(size, gfp); else - return vzalloc(size); + return __vmalloc(size, gfp | __GFP_ZERO, PAGE_KERNEL); } /** @@ -1154,12 +1154,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, return chunk; } -static struct pcpu_chunk *pcpu_alloc_chunk(void) +static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; - chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size); + chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; @@ -1168,17 +1168,17 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * - sizeof(chunk->alloc_map[0])); + sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * - sizeof(chunk->bound_map[0])); + sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * - sizeof(chunk->md_blocks[0])); + sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; @@ -1277,9 +1277,11 @@ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ -static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size); -static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size); -static struct pcpu_chunk *pcpu_create_chunk(void); +static int pcpu_populate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end, gfp_t gfp); +static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, + int page_start, int page_end); +static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); @@ -1339,6 +1341,8 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { + /* whitelisted flags that can be passed to the backing allocators */ + gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; bool do_warn = !(gfp & __GFP_NOWARN); static int warn_limit = 10; @@ -1369,8 +1373,17 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, return NULL; } - if (!is_atomic) - mutex_lock(&pcpu_alloc_mutex); + if (!is_atomic) { + /* + * pcpu_balance_workfn() allocates memory under this mutex, + * and it may wait for memory reclaim. Allow current task + * to become OOM victim, in case of memory pressure. + */ + if (gfp & __GFP_NOFAIL) + mutex_lock(&pcpu_alloc_mutex); + else if (mutex_lock_killable(&pcpu_alloc_mutex)) + return NULL; + } spin_lock_irqsave(&pcpu_lock, flags); @@ -1421,7 +1434,7 @@ restart: } if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) { - chunk = pcpu_create_chunk(); + chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; @@ -1450,7 +1463,7 @@ area_found: page_start, page_end) { WARN_ON(chunk->immutable); - ret = pcpu_populate_chunk(chunk, rs, re); + ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { @@ -1561,10 +1574,17 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * - * Reclaim all fully free chunks except for the first one. + * Reclaim all fully free chunks except for the first one. This is also + * responsible for maintaining the pool of empty populated pages. However, + * it is possible that this is called when physical memory is scarce causing + * OOM killer to be triggered. We should avoid doing so until an actual + * allocation causes the failure as it is possible that requests can be + * serviced from already backed regions. */ static void pcpu_balance_workfn(struct work_struct *work) { + /* gfp flags passed to underlying allocators */ + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; LIST_HEAD(to_free); struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1]; struct pcpu_chunk *chunk, *next; @@ -1600,6 +1620,7 @@ static void pcpu_balance_workfn(struct work_struct *work) spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); + cond_resched(); } /* @@ -1645,7 +1666,7 @@ retry_pop: chunk->nr_pages) { int nr = min(re - rs, nr_to_pop); - ret = pcpu_populate_chunk(chunk, rs, rs + nr); + ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); if (!ret) { nr_to_pop -= nr; spin_lock_irq(&pcpu_lock); @@ -1662,7 +1683,7 @@ retry_pop: if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ - chunk = pcpu_create_chunk(); + chunk = pcpu_create_chunk(gfp); if (chunk) { spin_lock_irq(&pcpu_lock); pcpu_chunk_relocate(chunk, -1); diff --git a/mm/shmem.c b/mm/shmem.c index 1907688b75ee..b85919243399 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -493,36 +493,45 @@ next: info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; - if (nr_to_split && split >= nr_to_split) { - iput(inode); - continue; - } + if (nr_to_split && split >= nr_to_split) + goto leave; - page = find_lock_page(inode->i_mapping, + page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); if (!page) goto drop; + /* No huge page at the end of the file: nothing to split */ if (!PageTransHuge(page)) { - unlock_page(page); put_page(page); goto drop; } + /* + * Leave the inode on the list if we failed to lock + * the page at this time. + * + * Waiting for the lock may lead to deadlock in the + * reclaim path. + */ + if (!trylock_page(page)) { + put_page(page); + goto leave; + } + ret = split_huge_page(page); unlock_page(page); put_page(page); - if (ret) { - /* split failed: leave it on the list */ - iput(inode); - continue; - } + /* If split failed leave the inode on the list */ + if (ret) + goto leave; split++; drop: list_del_init(&info->shrinklist); removed++; +leave: iput(inode); } diff --git a/mm/vmscan.c b/mm/vmscan.c index bee53495a829..cd5dc3faaa57 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1780,6 +1780,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* + * If dirty pages are scanned that are not queued for IO, it + * implies that flushers are not doing their job. This can + * happen when memory pressure pushes dirty pages to the end of + * the LRU before the dirty limits are breached and the dirty + * data has expired. It can also happen when the proportion of + * dirty pages grows not through writes but through memory + * pressure reclaiming all the clean cache. And in some cases, + * the flushers simply cannot keep up with the allocation + * rate. Nudge the flusher threads in case they are asleep. + */ + if (stat.nr_unqueued_dirty == nr_taken) + wakeup_flusher_threads(WB_REASON_VMSCAN); + + /* * Legacy memcg will stall in page writeback so avoid forcibly * stalling here. */ @@ -1791,22 +1805,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested) set_bit(PGDAT_CONGESTED, &pgdat->flags); - /* - * If dirty pages are scanned that are not queued for IO, it - * implies that flushers are not doing their job. This can - * happen when memory pressure pushes dirty pages to the end of - * the LRU before the dirty limits are breached and the dirty - * data has expired. It can also happen when the proportion of - * dirty pages grows not through writes but through memory - * pressure reclaiming all the clean cache. And in some cases, - * the flushers simply cannot keep up with the allocation - * rate. Nudge the flusher threads in case they are asleep, but - * also allow kswapd to start writing pages during reclaim. - */ - if (stat.nr_unqueued_dirty == nr_taken) { - wakeup_flusher_threads(WB_REASON_VMSCAN); + /* Allow kswapd to start writing pages during reclaim. */ + if (stat.nr_unqueued_dirty == nr_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); - } /* * If kswapd scans pages marked marked for immediate diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 64aa9f755e1d..45c9bf5ff3a0 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -48,8 +48,8 @@ bool vlan_do_receive(struct sk_buff **skbp) * original position later */ skb_push(skb, offset); - skb = *skbp = vlan_insert_tag(skb, skb->vlan_proto, - skb->vlan_tci); + skb = *skbp = vlan_insert_inner_tag(skb, skb->vlan_proto, + skb->vlan_tci, skb->mac_len); if (!skb) return false; skb_pull(skb, offset + VLAN_HLEN); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 79e326383726..99abeadf416e 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -157,7 +157,7 @@ static void batadv_iv_ogm_orig_free(struct batadv_orig_node *orig_node) * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node, - int max_if_num) + unsigned int max_if_num) { void *data_ptr; size_t old_size; @@ -201,7 +201,8 @@ unlock: */ static void batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t chunk_size; size_t if_offset; @@ -239,7 +240,8 @@ batadv_iv_ogm_drop_bcast_own_entry(struct batadv_orig_node *orig_node, */ static void batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { size_t if_offset; void *data_ptr; @@ -276,7 +278,8 @@ batadv_iv_ogm_drop_bcast_own_sum_entry(struct batadv_orig_node *orig_node, * Return: 0 on success, a negative error code otherwise. */ static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node, - int max_if_num, int del_if_num) + unsigned int max_if_num, + unsigned int del_if_num) { spin_lock_bh(&orig_node->bat_iv.ogm_cnt_lock); @@ -311,7 +314,8 @@ static struct batadv_orig_node * batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; - int size, hash_added; + int hash_added; + size_t size; orig_node = batadv_orig_hash_find(bat_priv, addr); if (orig_node) @@ -893,7 +897,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) u32 i; size_t word_index; u8 *w; - int if_num; + unsigned int if_num; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1023,7 +1027,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - int if_num; + unsigned int if_num; u8 sum_orig, sum_neigh; u8 *neigh_addr; u8 tq_avg; @@ -1182,7 +1186,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, u8 total_count; u8 orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; - int if_num; + unsigned int if_num; unsigned int tq_asym_penalty, inv_asym_penalty; unsigned int combined_tq; unsigned int tq_iface_penalty; @@ -1702,9 +1706,9 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset, if (is_my_orig) { unsigned long *word; - int offset; + size_t offset; s32 bit_pos; - s16 if_num; + unsigned int if_num; u8 *weight; orig_neigh_node = batadv_iv_ogm_orig_get(bat_priv, @@ -2729,7 +2733,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 27e165ac9302..c74f81341dab 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -928,7 +928,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; struct batadv_gw_node *curr_gw; - int ret = -EINVAL; + int ret = 0; void *hdr; router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index fad47853ad3c..b1a08374088b 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -2161,22 +2161,25 @@ batadv_bla_claim_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_claim *claim; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(claim, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_claim_dump_entry(msg, portid, seq, - primary_if, claim)) { + + ret = batadv_bla_claim_dump_entry(msg, portid, seq, + primary_if, claim); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** @@ -2391,22 +2394,25 @@ batadv_bla_backbone_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_bla_backbone_gw *backbone_gw; int idx = 0; + int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (idx++ < *idx_skip) continue; - if (batadv_bla_backbone_dump_entry(msg, portid, seq, - primary_if, backbone_gw)) { + + ret = batadv_bla_backbone_dump_entry(msg, portid, seq, + primary_if, backbone_gw); + if (ret) { *idx_skip = idx - 1; goto unlock; } } - *idx_skip = idx; + *idx_skip = 0; unlock: rcu_read_unlock(); - return 0; + return ret; } /** diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 9703c791ffc5..87cd962d28d5 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -393,7 +393,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, batadv_arp_hw_src(skb, hdr_size), &ip_src, batadv_arp_hw_dst(skb, hdr_size), &ip_dst); - if (hdr_size == 0) + if (hdr_size < sizeof(struct batadv_unicast_packet)) return; unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 22dde42fd80e..5afe641ee4b0 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -288,7 +288,8 @@ batadv_frag_merge_packets(struct hlist_head *chain) /* Move the existing MAC header to just before the payload. (Override * the fragment header.) */ - skb_pull_rcsum(skb_out, hdr_size); + skb_pull(skb_out, hdr_size); + skb_out->ip_summed = CHECKSUM_NONE; memmove(skb_out->data - ETH_HLEN, skb_mac_header(skb_out), ETH_HLEN); skb_set_mac_header(skb_out, -ETH_HLEN); skb_reset_network_header(skb_out); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 5f186bff284a..68b54a39c51d 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -763,6 +763,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); + if (bat_priv->num_ifaces >= UINT_MAX) { + ret = -ENOSPC; + goto err_dev; + } + ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface, NULL, NULL, NULL); if (ret) @@ -876,7 +881,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface); /* nobody uses this interface anymore */ - if (!bat_priv->num_ifaces) { + if (bat_priv->num_ifaces == 0) { batadv_gw_check_client_stop(bat_priv); if (autodel == BATADV_IF_CLEANUP_AUTO) @@ -912,7 +917,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) if (ret) goto free_if; - hard_iface->if_num = -1; + hard_iface->if_num = 0; hard_iface->net_dev = net_dev; hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index e91f29c7c638..5daa3d50da17 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -24,6 +24,7 @@ #include <linux/debugfs.h> #include <linux/errno.h> #include <linux/etherdevice.h> +#include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index dc9fa37ddd14..cdbe0e5e208b 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -22,6 +22,7 @@ #include <linux/compiler.h> #include <linux/debugfs.h> #include <linux/errno.h> +#include <linux/eventpoll.h> #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index cbdeb47ec3f6..d70640135e3a 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -543,8 +543,8 @@ update: bat_priv->mcast.enabled = true; } - return !(mcast_data.flags & - (BATADV_MCAST_WANT_ALL_IPV4 | BATADV_MCAST_WANT_ALL_IPV6)); + return !(mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV4 && + mcast_data.flags & BATADV_MCAST_WANT_ALL_IPV6); } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 58a7d9274435..74782426bb77 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1569,7 +1569,7 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_algo_ops *bao = bat_priv->algo_ops; @@ -1611,7 +1611,7 @@ err: * Return: 0 on success or negative error number in case of failure */ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num) + unsigned int max_if_num) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 8e543a3cdc6c..15d896b2de6f 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -73,9 +73,9 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset); int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, - int max_if_num); + unsigned int max_if_num); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index b6891e8b741c..e61dc1293bb5 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -759,6 +759,7 @@ free_skb: /** * batadv_reroute_unicast_packet() - update the unicast header for re-routing * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast packet to process * @unicast_packet: the unicast header to be updated * @dst_addr: the payload destination * @vid: VLAN identifier @@ -770,7 +771,7 @@ free_skb: * Return: true if the packet header has been updated, false otherwise */ static bool -batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, +batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_unicast_packet *unicast_packet, u8 *dst_addr, unsigned short vid) { @@ -799,8 +800,10 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, } /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, orig_addr); unicast_packet->ttvn = orig_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ret = true; out: @@ -841,7 +844,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * the packet to */ if (batadv_tt_local_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) { - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, @@ -887,7 +890,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * destination can possibly be updated and forwarded towards the new * target host */ - if (batadv_reroute_unicast_packet(bat_priv, unicast_packet, + if (batadv_reroute_unicast_packet(bat_priv, skb, unicast_packet, ethhdr->h_dest, vid)) { batadv_dbg_ratelimited(BATADV_DBG_TT, bat_priv, "Rerouting unicast packet to %pM (dst=%pM): TTVN mismatch old_ttvn=%u new_ttvn=%u\n", @@ -910,12 +913,14 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (!primary_if) return false; + /* update the packet header */ + skb_postpull_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr); + unicast_packet->ttvn = curr_ttvn; + skb_postpush_rcsum(skb, unicast_packet, sizeof(*unicast_packet)); batadv_hardif_put(primary_if); - unicast_packet->ttvn = curr_ttvn; - return true; } @@ -968,14 +973,10 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node = NULL, *orig_node_gw = NULL; int check, hdr_size = sizeof(*unicast_packet); enum batadv_subtype subtype; - struct ethhdr *ethhdr; int ret = NET_RX_DROP; bool is4addr, is_gw; unicast_packet = (struct batadv_unicast_packet *)skb->data; - unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; - ethhdr = eth_hdr(skb); - is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR; /* the caller function should have already pulled 2 bytes */ if (is4addr) @@ -995,12 +996,14 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, if (!batadv_check_unicast_ttvn(bat_priv, skb, hdr_size)) goto free_skb; + unicast_packet = (struct batadv_unicast_packet *)skb->data; + /* packet for me */ if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { /* If this is a unicast packet from another backgone gw, * drop it. */ - orig_addr_gw = ethhdr->h_source; + orig_addr_gw = eth_hdr(skb)->h_source; orig_node_gw = batadv_orig_hash_find(bat_priv, orig_addr_gw); if (orig_node_gw) { is_gw = batadv_bla_is_backbone_gw(skb, orig_node_gw, @@ -1015,6 +1018,8 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, } if (is4addr) { + unicast_4addr_packet = + (struct batadv_unicast_4addr_packet *)skb->data; subtype = unicast_4addr_packet->subtype; batadv_dat_inc_counter(bat_priv, subtype); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 900c5ce21cd4..367a81fb785f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -459,13 +459,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* skb->dev & skb->pkt_type are set here */ skb->protocol = eth_type_trans(skb, soft_iface); - - /* should not be necessary anymore as we use skb_pull_rcsum() - * TODO: please verify this and remove this TODO - * -- Dec 21st 2009, Simon Wunderlich - */ - - /* skb->ip_summed = CHECKSUM_UNNECESSARY; */ + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index bb1578410e0c..a5aa6d61f4e2 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -167,7 +167,7 @@ struct batadv_hard_iface { struct list_head list; /** @if_num: identificator of the interface */ - s16 if_num; + unsigned int if_num; /** @if_status: status of the interface for batman-adv */ char if_status; @@ -1596,7 +1596,7 @@ struct batadv_priv { atomic_t batman_queue_left; /** @num_ifaces: number of interfaces assigned to this mesh interface */ - char num_ifaces; + unsigned int num_ifaces; /** @mesh_obj: kobject for sysfs mesh subdirectory */ struct kobject *mesh_obj; @@ -2186,15 +2186,16 @@ struct batadv_algo_orig_ops { * orig_node due to a new hard-interface being added into the mesh * (optional) */ - int (*add_if)(struct batadv_orig_node *orig_node, int max_if_num); + int (*add_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num); /** * @del_if: ask the routing algorithm to apply the needed changes to the * orig_node due to an hard-interface being removed from the mesh * (optional) */ - int (*del_if)(struct batadv_orig_node *orig_node, int max_if_num, - int del_if_num); + int (*del_if)(struct batadv_orig_node *orig_node, + unsigned int max_if_num, unsigned int del_if_num); #ifdef CONFIG_BATMAN_ADV_DEBUGFS /** @print: print the originator table (optional) */ diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 01117ae84f1d..a2ddae2f37d7 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2296,8 +2296,14 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) else sec_level = authreq_to_seclevel(auth); - if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) + if (smp_sufficient_security(hcon, sec_level, SMP_USE_LTK)) { + /* If link is already encrypted with sufficient security we + * still need refresh encryption as per Core Spec 5.0 Vol 3, + * Part H 2.4.6 + */ + smp_ltk_encrypt(conn, hcon->sec_level); return 0; + } if (sec_level > hcon->pending_sec_level) hcon->pending_sec_level = sec_level; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 27f1d4f2114a..9b16eaf33819 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -214,7 +214,7 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) - goto inhdr_error; + goto csum_error; len = ntohs(iph->tot_len); if (skb->len < len) { @@ -236,6 +236,8 @@ static int br_validate_ipv4(struct net *net, struct sk_buff *skb) */ return 0; +csum_error: + __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 51935270c651..9896f4975353 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -168,6 +168,8 @@ static struct net_bridge_vlan *br_vlan_get_master(struct net_bridge *br, u16 vid masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; + refcount_set(&masterv->refcnt, 1); + return masterv; } refcount_inc(&masterv->refcnt); diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index ce7152a12bd8..620e54f08296 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -172,18 +172,69 @@ ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par) return true; } +static bool poolsize_invalid(const struct ebt_mac_wormhash *w) +{ + return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple)); +} + +static bool wormhash_offset_invalid(int off, unsigned int len) +{ + if (off == 0) /* not present */ + return false; + + if (off < (int)sizeof(struct ebt_among_info) || + off % __alignof__(struct ebt_mac_wormhash)) + return true; + + off += sizeof(struct ebt_mac_wormhash); + + return off > len; +} + +static bool wormhash_sizes_valid(const struct ebt_mac_wormhash *wh, int a, int b) +{ + if (a == 0) + a = sizeof(struct ebt_among_info); + + return ebt_mac_wormhash_size(wh) + a == b; +} + static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; const struct ebt_entry_match *em = container_of(par->matchinfo, const struct ebt_entry_match, data); - int expected_length = sizeof(struct ebt_among_info); + unsigned int expected_length = sizeof(struct ebt_among_info); const struct ebt_mac_wormhash *wh_dst, *wh_src; int err; + if (expected_length > em->match_size) + return -EINVAL; + + if (wormhash_offset_invalid(info->wh_dst_ofs, em->match_size) || + wormhash_offset_invalid(info->wh_src_ofs, em->match_size)) + return -EINVAL; + wh_dst = ebt_among_wh_dst(info); - wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_dst)) + return -EINVAL; + expected_length += ebt_mac_wormhash_size(wh_dst); + if (expected_length > em->match_size) + return -EINVAL; + + wh_src = ebt_among_wh_src(info); + if (poolsize_invalid(wh_src)) + return -EINVAL; + + if (info->wh_src_ofs < info->wh_dst_ofs) { + if (!wormhash_sizes_valid(wh_src, info->wh_src_ofs, info->wh_dst_ofs)) + return -EINVAL; + } else { + if (!wormhash_sizes_valid(wh_dst, info->wh_dst_ofs, info->wh_src_ofs)) + return -EINVAL; + } + expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 02c4b409d317..a94d23b0a9af 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1641,7 +1641,8 @@ static int compat_match_to_user(struct ebt_entry_match *m, void __user **dstptr, int off = ebt_compat_match_offset(match, m->match_size); compat_uint_t msize = m->match_size - off; - BUG_ON(off >= m->match_size); + if (WARN_ON(off >= m->match_size)) + return -EINVAL; if (copy_to_user(cm->u.name, match->name, strlen(match->name) + 1) || put_user(msize, &cm->match_size)) @@ -1671,7 +1672,8 @@ static int compat_target_to_user(struct ebt_entry_target *t, int off = xt_compat_target_offset(target); compat_uint_t tsize = t->target_size - off; - BUG_ON(off >= t->target_size); + if (WARN_ON(off >= t->target_size)) + return -EINVAL; if (copy_to_user(cm->u.name, target->name, strlen(target->name) + 1) || put_user(tsize, &cm->match_size)) @@ -1902,7 +1904,8 @@ static int ebt_buf_add(struct ebt_entries_buf_state *state, if (state->buf_kern_start == NULL) goto count_only; - BUG_ON(state->buf_kern_offset + sz > state->buf_kern_len); + if (WARN_ON(state->buf_kern_offset + sz > state->buf_kern_len)) + return -EINVAL; memcpy(state->buf_kern_start + state->buf_kern_offset, data, sz); @@ -1915,7 +1918,8 @@ static int ebt_buf_add_pad(struct ebt_entries_buf_state *state, unsigned int sz) { char *b = state->buf_kern_start; - BUG_ON(b && state->buf_kern_offset > state->buf_kern_len); + if (WARN_ON(b && state->buf_kern_offset > state->buf_kern_len)) + return -EINVAL; if (b != NULL && sz > 0) memset(b + state->buf_kern_offset, 0, sz); @@ -1992,8 +1996,10 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, pad = XT_ALIGN(size_kern) - size_kern; if (pad > 0 && dst) { - BUG_ON(state->buf_kern_len <= pad); - BUG_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad); + if (WARN_ON(state->buf_kern_len <= pad)) + return -EINVAL; + if (WARN_ON(state->buf_kern_offset - (match_size + off) + size_kern > state->buf_kern_len - pad)) + return -EINVAL; memset(dst + size_kern, 0, pad); } return off + match_size; @@ -2043,7 +2049,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (ret < 0) return ret; - BUG_ON(ret < match32->match_size); + if (WARN_ON(ret < match32->match_size)) + return -EINVAL; growth += ret - match32->match_size; growth += ebt_compat_entry_padsize(); @@ -2053,7 +2060,9 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - WARN_ON(type == EBT_COMPAT_TARGET && size_left); + if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + return -EINVAL; + match32 = (struct compat_ebt_entry_mwt *) buf; } @@ -2109,6 +2118,19 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, * * offsets are relative to beginning of struct ebt_entry (i.e., 0). */ + for (i = 0; i < 4 ; ++i) { + if (offsets[i] > *total) + return -EINVAL; + + if (i < 3 && offsets[i] == *total) + return -EINVAL; + + if (i == 0) + continue; + if (offsets[i-1] > offsets[i]) + return -EINVAL; + } + for (i = 0, j = 1 ; j < 4 ; j++, i++) { struct compat_ebt_entry_mwt *match32; unsigned int size; @@ -2140,7 +2162,8 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, startoff = state->buf_user_offset - startoff; - BUG_ON(*total < startoff); + if (WARN_ON(*total < startoff)) + return -EINVAL; *total -= startoff; return 0; } @@ -2267,7 +2290,8 @@ static int compat_do_replace(struct net *net, void __user *user, state.buf_kern_len = size64; ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); - BUG_ON(ret < 0); /* parses same data again */ + if (WARN_ON(ret < 0)) + goto out_unlock; vfree(entries_tmp); tmp.entries_size = size64; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 1e492ef2a33d..4d4c82229e9e 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -418,6 +418,7 @@ ceph_parse_options(char *options, const char *dev_name, opt->flags |= CEPH_OPT_FSID; break; case Opt_name: + kfree(opt->name); opt->name = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, GFP_KERNEL); @@ -427,6 +428,9 @@ ceph_parse_options(char *options, const char *dev_name, } break; case Opt_secret: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); if (!opt->key) { err = -ENOMEM; @@ -437,6 +441,9 @@ ceph_parse_options(char *options, const char *dev_name, goto out; break; case Opt_key: + ceph_crypto_key_destroy(opt->key); + kfree(opt->key); + opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); if (!opt->key) { err = -ENOMEM; diff --git a/net/core/dev.c b/net/core/dev.c index d4362befe7e2..12be20535714 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3278,15 +3278,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { - struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + const struct netprio_map *map; + const struct sock *sk; + unsigned int prioidx; - if (!skb->priority && skb->sk && map) { - unsigned int prioidx = - sock_cgroup_prioidx(&skb->sk->sk_cgrp_data); + if (skb->priority) + return; + map = rcu_dereference_bh(skb->dev->priomap); + if (!map) + return; + sk = skb_to_full_sk(skb); + if (!sk) + return; - if (prioidx < map->priomap_len) - skb->priority = map->priomap[prioidx]; - } + prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) @@ -6396,6 +6404,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, .linking = true, .upper_info = upper_info, }; + struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); @@ -6407,11 +6416,14 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; - if (netdev_has_upper_dev(dev, upper_dev)) - return -EEXIST; - - if (master && netdev_master_upper_dev_get(dev)) - return -EBUSY; + if (!master) { + if (netdev_has_upper_dev(dev, upper_dev)) + return -EEXIST; + } else { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + return master_dev == upper_dev ? -EEXIST : -EBUSY; + } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 0ab1af04296c..a04e1e88bf3a 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -402,8 +402,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c if (colon) *colon = 0; - dev_load(net, ifr->ifr_name); - /* * See which interface the caller is talking about. */ @@ -423,6 +421,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGIFMAP: case SIOCGIFINDEX: case SIOCGIFTXQLEN: + dev_load(net, ifr->ifr_name); rcu_read_lock(); ret = dev_ifsioc_locked(net, ifr, cmd); rcu_read_unlock(); @@ -431,6 +430,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c return ret; case SIOCETHTOOL: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ethtool(net, ifr); rtnl_unlock(); @@ -447,6 +447,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSIFNAME: + dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_lock(); @@ -494,6 +495,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c /* fall through */ case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); @@ -518,6 +520,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_c cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr->ifr_name); rtnl_lock(); ret = dev_ifsioc(net, ifr, cmd); rtnl_unlock(); diff --git a/net/core/devlink.c b/net/core/devlink.c index 18d385ed8237..effd4848c2b4 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1695,10 +1695,11 @@ static int devlink_dpipe_table_put(struct sk_buff *skb, goto nla_put_failure; if (table->resource_valid) { - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, - table->resource_id, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, - table->resource_units, DEVLINK_ATTR_PAD); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID, + table->resource_id, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS, + table->resource_units, DEVLINK_ATTR_PAD)) + goto nla_put_failure; } if (devlink_dpipe_matches_put(table, skb)) goto nla_put_failure; @@ -1797,7 +1798,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } @@ -1806,7 +1807,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@ -2072,7 +2072,7 @@ static int devlink_dpipe_entries_fill(struct genl_info *info, table->counters_enabled, &dump_ctx); if (err) - goto err_entries_dump; + return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, @@ -2080,16 +2080,10 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); - -err_entries_dump: -err_skb_send_alloc: - genlmsg_cancel(dump_ctx.skb, dump_ctx.hdr); - nlmsg_free(dump_ctx.skb); - return err; } static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, @@ -2228,7 +2222,7 @@ send_done: if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) - goto err_skb_send_alloc; + return err; goto send_done; } return genlmsg_reply(skb, info); @@ -2236,7 +2230,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: -err_skb_send_alloc: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; @@ -2332,7 +2325,7 @@ devlink_resource_validate_children(struct devlink_resource *resource) list_for_each_entry(child_resource, &resource->resource_list, list) parts_size += child_resource->size_new; - if (parts_size > resource->size) + if (parts_size > resource->size_new) size_valid = false; out: resource->size_valid = size_valid; @@ -2372,20 +2365,22 @@ static int devlink_nl_cmd_resource_set(struct sk_buff *skb, return 0; } -static void +static int devlink_resource_size_params_put(struct devlink_resource *resource, struct sk_buff *skb) { struct devlink_resource_size_params *size_params; - size_params = resource->size_params; - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, - size_params->size_granularity, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, - size_params->size_max, DEVLINK_ATTR_PAD); - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, - size_params->size_min, DEVLINK_ATTR_PAD); - nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit); + size_params = &resource->size_params; + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_GRAN, + size_params->size_granularity, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MAX, + size_params->size_max, DEVLINK_ATTR_PAD) || + nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_MIN, + size_params->size_min, DEVLINK_ATTR_PAD) || + nla_put_u8(skb, DEVLINK_ATTR_RESOURCE_UNIT, size_params->unit)) + return -EMSGSIZE; + return 0; } static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, @@ -2409,10 +2404,12 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb, nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_SIZE_NEW, resource->size_new, DEVLINK_ATTR_PAD); if (resource->resource_ops && resource->resource_ops->occ_get) - nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, - resource->resource_ops->occ_get(devlink), - DEVLINK_ATTR_PAD); - devlink_resource_size_params_put(resource, skb); + if (nla_put_u64_64bit(skb, DEVLINK_ATTR_RESOURCE_OCC, + resource->resource_ops->occ_get(devlink), + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (devlink_resource_size_params_put(resource, skb)) + goto nla_put_failure; if (list_empty(&resource->resource_list)) goto out; @@ -3151,7 +3148,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_size, u64 resource_id, u64 parent_resource_id, - struct devlink_resource_size_params *size_params, + const struct devlink_resource_size_params *size_params, const struct devlink_resource_ops *resource_ops) { struct devlink_resource *resource; @@ -3194,7 +3191,8 @@ int devlink_resource_register(struct devlink *devlink, resource->id = resource_id; resource->resource_ops = resource_ops; resource->size_valid = true; - resource->size_params = size_params; + memcpy(&resource->size_params, size_params, + sizeof(resource->size_params)); INIT_LIST_HEAD(&resource->resource_list); list_add_tail(&resource->list, resource_list); out: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 494e6a5d7306..3f89c76d5c24 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -2520,11 +2520,14 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr) static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) { struct ethtool_fecparam fecparam = { ETHTOOL_GFECPARAM }; + int rc; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; - dev->ethtool_ops->get_fecparam(dev, &fecparam); + rc = dev->ethtool_ops->get_fecparam(dev, &fecparam); + if (rc) + return rc; if (copy_to_user(useraddr, &fecparam, sizeof(fecparam))) return -EFAULT; diff --git a/net/core/filter.c b/net/core/filter.c index 0c121adbdbaa..48aa7c7320db 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2087,6 +2087,10 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2096,19 +2100,21 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV4 needs to be changed into * SKB_GSO_TCPV6. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV4; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; + if (shinfo->gso_type & SKB_GSO_TCPV4) { + shinfo->gso_type &= ~SKB_GSO_TCPV4; + shinfo->gso_type |= SKB_GSO_TCPV6; } /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -2123,6 +2129,10 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2132,19 +2142,21 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* SKB_GSO_TCPV6 needs to be changed into * SKB_GSO_TCPV4. */ - if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { - skb_shinfo(skb)->gso_type &= ~SKB_GSO_TCPV6; - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; + if (shinfo->gso_type & SKB_GSO_TCPV6) { + shinfo->gso_type &= ~SKB_GSO_TCPV6; + shinfo->gso_type |= SKB_GSO_TCPV4; } /* Due to IPv4 header, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -2243,6 +2255,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -2252,11 +2268,13 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header grow, MSS needs to be downgraded. */ - skb_shinfo(skb)->gso_size -= len_diff; + skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; @@ -2267,6 +2285,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; + /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ + if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + return -ENOTSUPP; + ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -2276,11 +2298,13 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) return ret; if (skb_is_gso(skb)) { + struct skb_shared_info *shinfo = skb_shinfo(skb); + /* Due to header shrink, MSS can be upgraded. */ - skb_shinfo(skb)->gso_size += len_diff; + skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ - skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; - skb_shinfo(skb)->gso_segs = 0; + shinfo->gso_type |= SKB_GSO_DODGY; + shinfo->gso_segs = 0; } return 0; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09bd89c90a71..1e7acdc30732 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4179,7 +4179,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + sk->sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -4891,7 +4891,7 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ -unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; @@ -4904,7 +4904,7 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); - } else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) { + } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } /* UFO sets gso_size to the size of the fragmentation @@ -4913,7 +4913,40 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) */ return thlen + shinfo->gso_size; } -EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} + +/** + * skb_gso_mac_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_mac_seglen is used to determine the real size of the + * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 + * headers (TCP/UDP). + */ +static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + + return hdr_len + skb_gso_transport_seglen(skb); +} /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS @@ -4955,19 +4988,20 @@ static inline bool skb_gso_size_check(const struct sk_buff *skb, } /** - * skb_gso_validate_mtu - Return in case such skb fits a given MTU + * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * - * skb_gso_validate_mtu validates if a given skb will fit a wanted MTU - * once split. + * skb_gso_validate_network_len validates if a given skb will fit a + * wanted MTU once split. It considers L3 headers, L4 headers, and the + * payload. */ -bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu) +bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } -EXPORT_SYMBOL_GPL(skb_gso_validate_mtu); +EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? @@ -4986,13 +5020,16 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { + int mac_len; + if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, - 2 * ETH_ALEN); + mac_len = skb->data - skb_mac_header(skb); + memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), + mac_len - VLAN_HLEN - ETH_TLEN); skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/core/sock.c b/net/core/sock.c index c501499a04fe..85b0b64e7f9d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3261,6 +3261,27 @@ void proto_unregister(struct proto *prot) } EXPORT_SYMBOL(proto_unregister); +int sock_load_diag_module(int family, int protocol) +{ + if (!protocol) { + if (!sock_is_registered(family)) + return -ENOENT; + + return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family); + } + +#ifdef CONFIG_INET + if (family == AF_INET && + !rcu_access_pointer(inet_protos[protocol])) + return -ENOENT; +#endif + + return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, family, protocol); +} +EXPORT_SYMBOL(sock_load_diag_module); + #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) __acquires(proto_list_mutex) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 146b50e30659..c37b5be7c5e4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -220,8 +220,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, req->sdiag_family); + sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; @@ -247,8 +246,7 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) @@ -281,14 +279,12 @@ static int sock_diag_bind(struct net *net, int group) case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET6); + sock_load_diag_module(AF_INET6, 0); break; } return 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 15bdc002d90c..84cd4e3fd01b 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -794,6 +794,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (skb == NULL) goto out_release; + if (sk->sk_state == DCCP_CLOSED) { + rc = -ENOTCONN; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index cb54b81d0bd9..42a7b85b84e1 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -194,7 +194,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, ds->ports[i].dn = cd->port_dn[i]; ds->ports[i].cpu_dp = dst->cpu_dp; - if (dsa_is_user_port(ds, i)) + if (!dsa_is_user_port(ds, i)) continue; ret = dsa_slave_create(&ds->ports[i]); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 974765b7d92a..e9f0489e4229 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -206,9 +206,13 @@ static inline void lowpan_netlink_fini(void) static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *wdev = netdev_notifier_info_to_dev(ptr); + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct wpan_dev *wpan_dev; - if (wdev->type != ARPHRD_IEEE802154) + if (ndev->type != ARPHRD_IEEE802154) + return NOTIFY_DONE; + wpan_dev = ndev->ieee802154_ptr; + if (!wpan_dev) return NOTIFY_DONE; switch (event) { @@ -217,8 +221,8 @@ static int lowpan_device_event(struct notifier_block *unused, * also delete possible lowpan interfaces which belongs * to the wpan interface. */ - if (wdev->ieee802154_ptr->lowpan_dev) - lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL); + if (wpan_dev->lowpan_dev) + lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a383f299ce24..4e5bc4b2f14e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex); static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { if (!inet_diag_table[proto]) - request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET, proto); + sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); if (!inet_diag_table[proto]) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 26a3d0315728..e8ec28999f5c 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -119,6 +119,9 @@ out: static bool inet_fragq_should_evict(const struct inet_frag_queue *q) { + if (!hlist_unhashed(&q->list_evictor)) + return false; + return q->net->low_thresh == 0 || frag_mem_limit(q->net) >= q->net->low_thresh; } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 2dd21c3281a1..b54b948b0596 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -55,7 +55,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 45d97e9b2759..0901de42ed85 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -970,9 +970,6 @@ static void __gre_tunnel_init(struct net_device *dev) t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; - dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1290,8 +1287,6 @@ static int erspan_tunnel_init(struct net_device *dev) erspan_hdr_len(tunnel->erspan_ver); t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->needed_headroom = LL_MAX_HEADER + t_hlen + 4; - dev->mtu = ETH_DATA_LEN - t_hlen - 4; dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index e8e675be60ec..66340ab750e6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -248,7 +248,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, /* common case: seglen is <= mtu */ - if (skb_gso_validate_mtu(skb, mtu)) + if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 9c41a0cef1a5..74c962b9b09c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -258,7 +258,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; - ipc->oif = src_info->ipi6_ifindex; + if (src_info->ipi6_ifindex) + ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } @@ -288,7 +289,8 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); - ipc->oif = info->ipi_ifindex; + if (info->ipi_ifindex) + ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d786a8441bce..6d21068f9b55 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -710,16 +710,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } } - if (tunnel->fwmark) { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); - } - else { - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - skb->mark); - } + init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->fwmark); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4b02ab39ebc5..8a8ae61cea71 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -232,7 +232,6 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->hash_mode = i->hash_mode; c->hash_initval = i->hash_initval; refcount_set(&c->refcount, 1); - refcount_set(&c->entries, 1); spin_lock_bh(&cn->lock); if (__clusterip_config_find(net, ip)) { @@ -263,8 +262,10 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, c->notifier.notifier_call = clusterip_netdev_event; err = register_netdevice_notifier(&c->notifier); - if (!err) + if (!err) { + refcount_set(&c->entries, 1); return c; + } #ifdef CONFIG_PROC_FS proc_remove(c->pde); @@ -273,7 +274,7 @@ err: spin_lock_bh(&cn->lock); list_del_rcu(&c->list); spin_unlock_bh(&cn->lock); - kfree(c); + clusterip_config_put(c); return ERR_PTR(err); } @@ -496,12 +497,15 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) return PTR_ERR(config); } } - cipinfo->config = config; ret = nf_ct_netns_get(par->net, par->family); - if (ret < 0) + if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); + clusterip_config_entry_put(par->net, config); + clusterip_config_put(config); + return ret; + } if (!par->net->xt.clusterip_deprecated_warning) { pr_info("ipt_CLUSTERIP is deprecated and it will removed soon, " @@ -509,6 +513,7 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) par->net->xt.clusterip_deprecated_warning = true; } + cipinfo->config = config; return ret; } diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 25d2975da156..0cd46bffa469 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -111,6 +111,7 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, default: return -1; } + csum_replace4(&iph->check, addr, new_addr); return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); } @@ -185,7 +186,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a4f44d815a61..299e247b2032 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -128,10 +128,11 @@ static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; -static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; +static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; + /* * Interface to generic destination cache. */ @@ -633,6 +634,7 @@ static inline u32 fnhe_hashfun(__be32 daddr) static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; + rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { @@ -643,7 +645,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh } static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, - u32 pmtu, unsigned long expires) + u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; @@ -680,8 +682,10 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; - if (pmtu) + if (pmtu) { fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; + } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); @@ -705,6 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; + fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = expires; /* Exception created; mark the cached routes for the nexthop @@ -786,7 +791,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, jiffies + ip_rt_gc_timeout); + 0, false, + jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -930,14 +936,23 @@ out_put_peer: static int ip_error(struct sk_buff *skb) { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); struct rtable *rt = skb_rtable(skb); + struct net_device *dev = skb->dev; + struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; bool send; int code; + if (netif_is_l3_master(skb->dev)) { + dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); + if (!dev) + goto out; + } + + in_dev = __in_dev_get_rcu(dev); + /* IP on this device is disabled. */ if (!in_dev) goto out; @@ -999,15 +1014,18 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct fib_result res; + bool lock = false; - if (dst_metric_locked(dst, RTAX_MTU)) + if (ip_mtu_locked(dst)) return; if (ipv4_mtu(dst) < mtu) return; - if (mtu < ip_rt_min_pmtu) + if (mtu < ip_rt_min_pmtu) { + lock = true; mtu = ip_rt_min_pmtu; + } if (rt->rt_pmtu == mtu && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) @@ -1017,7 +1035,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); - update_or_create_fnhe(nh, fl4->daddr, 0, mtu, + update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); @@ -1270,7 +1288,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); - if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1383,7 +1401,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); -static void rt_add_uncached_list(struct rtable *rt) +void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); @@ -1394,14 +1412,8 @@ static void rt_add_uncached_list(struct rtable *rt) spin_unlock_bh(&ul->lock); } -static void ipv4_dst_destroy(struct dst_entry *dst) +void rt_del_uncached_list(struct rtable *rt) { - struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); - struct rtable *rt = (struct rtable *) dst; - - if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) - kfree(p); - if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; @@ -1411,6 +1423,17 @@ static void ipv4_dst_destroy(struct dst_entry *dst) } } +static void ipv4_dst_destroy(struct dst_entry *dst) +{ + struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst); + struct rtable *rt = (struct rtable *)dst; + + if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt)) + kfree(p); + + rt_del_uncached_list(rt); +} + void rt_flush_dev(struct net_device *dev) { struct net *net = dev_net(dev); @@ -1506,6 +1529,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; + rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; rt->rt_table_id = 0; @@ -2531,6 +2555,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; + rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; @@ -2633,6 +2658,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; + if (rt->rt_mtu_locked && expires) + metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; @@ -2818,6 +2845,7 @@ void ip_rt_multicast_event(struct in_device *in_dev) static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; +static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer, @@ -2933,7 +2961,8 @@ static struct ctl_table ipv4_route_table[] = { .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_min_valid_pmtu, }, { .procname = "min_adv_mss", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 48636aee23c3..8b8059b7af4d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3566,6 +3566,7 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); + tcp_write_queue_purge(sk); release_sock(sk); return 0; } diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 7c843578f233..faddf4f9a707 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -6,7 +6,7 @@ * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" - * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf + * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 575d3c1fb6e8..9a1b3c1c1c14 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1971,11 +1971,6 @@ void tcp_enter_loss(struct sock *sk) /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing - * - * In theory F-RTO can be used repeatedly during loss recovery. - * In practice this interacts badly with broken middle-boxes that - * falsely raise the receive window, which results in repeated - * timeouts and stop-and-go behavior. */ tp->frto = net->ipv4.sysctl_tcp_frto && (new_recovery || icsk->icsk_retransmits) && @@ -2631,18 +2626,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack, tcp_try_undo_loss(sk, false)) return; - /* The ACK (s)acks some never-retransmitted data meaning not all - * the data packets before the timeout were lost. Therefore we - * undo the congestion window and state. This is essentially - * the operation in F-RTO (RFC5682 section 3.1 step 3.b). Since - * a retransmitted skb is permantly marked, we can apply such an - * operation even if F-RTO was not used. - */ - if ((flag & FLAG_ORIG_SACK_ACKED) && - tcp_try_undo_loss(sk, tp->undo_marker)) - return; - if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) + return; + if (after(tp->snd_nxt, tp->high_seq)) { if (flag & FLAG_DATA_SACKED || is_dupack) tp->frto = 0; /* Step 3.a. loss was real */ @@ -4001,6 +3992,7 @@ void tcp_reset(struct sock *sk) /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); + tcp_write_queue_purge(sk); tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 71fc60f1b326..f7d944855f8e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -34,6 +34,7 @@ static void tcp_write_err(struct sock *sk) sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; sk->sk_error_report(sk); + tcp_write_queue_purge(sk); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 63faeee989a9..2a9764bd1719 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 94b8702603bc..be980c195fc5 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,7 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if ((!skb_is_gso(skb) && skb->len > mtu) || - (skb_is_gso(skb) && skb_gso_network_seglen(skb) > ip_skb_dst_mtu(skb->sk, skb))) { + (skb_is_gso(skb) && + !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); if (skb->sk) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05017e2c849c..fbebda67ac1b 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,8 +100,10 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); + rt_add_uncached_list(&xdst->u.rt); return 0; } @@ -241,7 +243,8 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); - + if (xdst->u.rt.rt_uncached_list) + rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index fbf08ce3f5ab..a9f7eca0b6a3 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -146,10 +146,12 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr; + struct in6_addr *daddr, old_daddr; + __be32 fl6_flowlabel = 0; + __be32 old_fl6_flowlabel; + __be16 old_dport; int addr_type; int err; - __be32 fl6_flowlabel = 0; if (usin->sin6_family == AF_INET) { if (__ipv6_only_sock(sk)) @@ -238,9 +240,13 @@ ipv4_connected: } } + /* save the current peer information before updating it */ + old_daddr = sk->sk_v6_daddr; + old_fl6_flowlabel = np->flow_label; + old_dport = inet->inet_dport; + sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; - inet->inet_dport = usin->sin6_port; /* @@ -250,11 +256,12 @@ ipv4_connected: err = ip6_datagram_dst_update(sk, true); if (err) { - /* Reset daddr and dport so that udp_v6_early_demux() - * fails to find this socket + /* Restore the socket peer info, to keep it consistent with + * the old socket state */ - memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); - inet->inet_dport = 0; + sk->sk_v6_daddr = old_daddr; + np->flow_label = old_fl6_flowlabel; + inet->inet_dport = old_dport; goto out; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3c353125546d..1bbd0930063e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -126,7 +126,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, struct ip6_tnl *t, *cand = NULL; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB) || - gre_proto == htons(ETH_P_ERSPAN)) ? + gre_proto == htons(ETH_P_ERSPAN) || + gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; @@ -902,6 +903,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } + if (skb_cow_head(skb, dev->needed_headroom)) + goto tx_err; + t->parms.o_flags &= ~TUNNEL_KEY; IPCB(skb)->flags = 0; @@ -944,6 +948,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + } else { + goto tx_err; } } else { switch (skb->protocol) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 997c7f19ad62..a8a919520090 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -412,7 +412,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 4b15fe928278..6e0f21eed88a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1982,14 +1982,14 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - struct ip6_tnl *nt, *t; struct ip_tunnel_encap ipencap; + struct ip6_tnl *nt, *t; + int err; nt = netdev_priv(dev); if (ip6_tnl_netlink_encap_parms(data, &ipencap)) { - int err = ip6_tnl_encap_setup(nt, &ipencap); - + err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } @@ -2005,7 +2005,11 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - return ip6_tnl_create2(dev); + err = ip6_tnl_create2(dev); + if (!err && tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + + return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f61a5b613b52..ba5e04c6ae17 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1554,7 +1554,8 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, *(opt++) = (rd_len >> 3); opt += 6; - memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); + skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, + rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d95ceca7ff8f..531d6957af36 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -21,18 +21,19 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); + struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0, + .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, .flowi6_mark = skb->mark, - .flowi6_uid = sock_net_uid(net, skb->sk), + .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, .saddr = iph->saddr, }; int err; - dst = ip6_route_output(net, skb->sk, &fl6); + dst = ip6_route_output(net, sk, &fl6); err = dst->error; if (err) { IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -50,7 +51,7 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) { skb_dst_set(skb, NULL); - dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0); + dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_set(skb, dst); diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 94deb69bbbda..91ed25a24b79 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,10 +48,6 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - if ((flags & XT_RPFILTER_LOOSE) == 0) { - fl6.flowi6_oif = dev->ifindex; - lookup_flags |= RT6_LOOKUP_F_IFACE; - } rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags); if (rt->dst.error) diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index d346705d6ee6..207cb35569b1 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -178,7 +178,7 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index bed57ee65f7b..6b7f075f811f 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff, target, maniptype)) return false; + + /* must reload, offset might have changed */ + ipv6h = (void *)skb->data + iphdroff; + manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index cc5174c7254c..62fc84d7bdff 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -180,7 +180,6 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, } *dest = 0; - again: rt = (void *)ip6_route_lookup(nft_net(pkt), &fl6, lookup_flags); if (rt->dst.error) goto put_rt_err; @@ -189,15 +188,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) { - /* multipath route? Try again with F_IFACE */ - if ((lookup_flags & RT6_LOOKUP_F_IFACE) == 0) { - lookup_flags |= RT6_LOOKUP_F_IFACE; - fl6.flowi6_oif = oif->ifindex; - ip6_rt_put(rt); - goto again; - } - } + if (oif && oif != rt->rt6i_idev->dev) + goto put_rt_err; switch (priv->result) { case NFT_FIB_RESULT_OIF: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9dcfadddd800..b0d5c64e1978 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,7 @@ struct uncached_list { static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); -static void rt6_uncached_list_add(struct rt6_info *rt) +void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); @@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt) spin_unlock_bh(&ul->lock); } -static void rt6_uncached_list_del(struct rt6_info *rt) +void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->rt6i_uncached)) { struct uncached_list *ul = rt->rt6i_uncached_list; @@ -1509,7 +1509,30 @@ static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) } } -static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) +static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) +{ + /* If the new MTU is lower than the route PMTU, this new MTU will be the + * lowest MTU in the path: always allow updating the route PMTU to + * reflect PMTU decreases. + * + * If the new MTU is higher, and the route PMTU is equal to the local + * MTU, this means the old MTU is the lowest in the path, so allow + * updating it: if other nodes now have lower MTUs, PMTU discovery will + * handle this. + */ + + if (dst_mtu(&rt->dst) >= mtu) + return true; + + if (dst_mtu(&rt->dst) == idev->cnf.mtu6) + return true; + + return false; +} + +static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, + struct rt6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1518,20 +1541,22 @@ static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu) bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - struct rt6_info *entry = rt6_ex->rt6i; - /* For RTF_CACHE with rt6i_pmtu == 0 - * (i.e. a redirected route), - * the metrics of its rt->dst.from has already - * been updated. - */ - if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu) - entry->rt6i_pmtu = mtu; - } - bucket++; + if (!bucket) + return; + + for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { + hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { + struct rt6_info *entry = rt6_ex->rt6i; + + /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected + * route), the metrics of its rt->dst.from have already + * been updated. + */ + if (entry->rt6i_pmtu && + rt6_mtu_change_route_allowed(idev, entry, mtu)) + entry->rt6i_pmtu = mtu; } + bucket++; } } @@ -3809,25 +3834,13 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - /* - If new MTU is less than route PMTU, this new MTU will be the - lowest MTU in the path, update the route PMTU to reflect PMTU - decreases; if new MTU is greater than route PMTU, and the - old MTU is the lowest MTU in the path, update the route PMTU - to reflect the increase. In this case if the other nodes' MTU - also have the lowest MTU, TOO BIG MESSAGE will be lead to - PMTU discovery. - */ if (rt->dst.dev == arg->dev && - dst_metric_raw(&rt->dst, RTAX_MTU) && !dst_metric_locked(&rt->dst, RTAX_MTU)) { spin_lock_bh(&rt6_exception_lock); - if (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + if (dst_metric_raw(&rt->dst, RTAX_MTU) && + rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); - } - rt6_exceptions_update_pmtu(rt, arg->mtu); + rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; @@ -4099,6 +4112,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, r_cfg.fc_encap_type = nla_get_u16(nla); } + r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index bd6cc688bd19..7a78dcfda68a 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -93,7 +93,8 @@ static void set_tun_src(struct net *net, struct net_device *dev, /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; @@ -134,7 +135,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { @@ -418,7 +419,7 @@ static int seg6_build_state(struct nlattr *nla, slwt = seg6_lwt_lwtunnel(newts); - err = dst_cache_init(&slwt->cache, GFP_KERNEL); + err = dst_cache_init(&slwt->cache, GFP_ATOMIC); if (err) { kfree(newts); return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3a1775a62973..0195598f7bb5 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1578,6 +1578,13 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + + if (mtu >= IPV6_MIN_MTU && mtu <= 0xFFF8 - dev->hard_header_len) + dev->mtu = mtu; + } + #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) err = ipip6_tunnel_update_6rd(nt, &ip6rd); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index bb935a3b7fea..de1b0b8c53b0 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -92,7 +92,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) skb_reset_network_header(skb); skb_mac_header_rebuild(skb); - eth_hdr(skb)->h_proto = skb->protocol; + if (skb->mac_len) + eth_hdr(skb)->h_proto = skb->protocol; err = 0; diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8ae87d4ec5ff..5959ce9620eb 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,7 +82,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if ((!skb_is_gso(skb) && skb->len > mtu) || (skb_is_gso(skb) && - skb_gso_network_seglen(skb) > ip6_skb_dst_mtu(skb))) { + !skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) { skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 09fb44ee3b45..416fe67271a9 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; + INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); + rt6_uncached_list_add(&xdst->u.rt6); + atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } @@ -244,6 +247,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); + if (xdst->u.rt6.rt6i_uncached_list) + rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 1e8cc7bcbca3..9e2643ab4ccb 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2433,9 +2433,11 @@ static int afiucv_iucv_init(void) af_iucv_dev->driver = &af_iucv_driver; err = device_register(af_iucv_dev); if (err) - goto out_driver; + goto out_iucv_dev; return 0; +out_iucv_dev: + put_device(af_iucv_dev); out_driver: driver_unregister(&af_iucv_driver); out_iucv: diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index f297d53a11aa..34355fd19f27 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1381,24 +1381,32 @@ static int kcm_attach(struct socket *sock, struct socket *csock, .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; - int err; + int err = 0; csk = csock->sk; if (!csk) return -EINVAL; + lock_sock(csk); + /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || - csk->sk_protocol != IPPROTO_TCP) - return -EOPNOTSUPP; + csk->sk_protocol != IPPROTO_TCP) { + err = -EOPNOTSUPP; + goto out; + } /* Don't allow listeners or closed sockets */ - if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) - return -EOPNOTSUPP; + if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { + err = -EOPNOTSUPP; + goto out; + } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); - if (!psock) - return -ENOMEM; + if (!psock) { + err = -ENOMEM; + goto out; + } psock->mux = mux; psock->sk = csk; @@ -1407,7 +1415,7 @@ static int kcm_attach(struct socket *sock, struct socket *csock, err = strp_init(&psock->strp, csk, &cb); if (err) { kmem_cache_free(kcm_psockp, psock); - return err; + goto out; } write_lock_bh(&csk->sk_callback_lock); @@ -1419,7 +1427,8 @@ static int kcm_attach(struct socket *sock, struct socket *csock, write_unlock_bh(&csk->sk_callback_lock); strp_done(&psock->strp); kmem_cache_free(kcm_psockp, psock); - return -EALREADY; + err = -EALREADY; + goto out; } psock->save_data_ready = csk->sk_data_ready; @@ -1455,7 +1464,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock, /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); - return 0; +out: + release_sock(csk); + + return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) @@ -1507,6 +1519,7 @@ static void kcm_unattach(struct kcm_psock *psock) if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); + release_sock(csk); return; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 194a7483bb93..14b67dfacc4b 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -111,6 +111,13 @@ struct l2tp_net { spinlock_t l2tp_session_hlist_lock; }; +#if IS_ENABLED(CONFIG_IPV6) +static bool l2tp_sk_is_v6(struct sock *sk) +{ + return sk->sk_family == PF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr); +} +#endif static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) { @@ -136,51 +143,6 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } -/* Lookup the tunnel socket, possibly involving the fs code if the socket is - * owned by userspace. A struct sock returned from this function must be - * released using l2tp_tunnel_sock_put once you're done with it. - */ -static struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) -{ - int err = 0; - struct socket *sock = NULL; - struct sock *sk = NULL; - - if (!tunnel) - goto out; - - if (tunnel->fd >= 0) { - /* Socket is owned by userspace, who might be in the process - * of closing it. Look the socket up using the fd to ensure - * consistency. - */ - sock = sockfd_lookup(tunnel->fd, &err); - if (sock) - sk = sock->sk; - } else { - /* Socket is owned by kernelspace */ - sk = tunnel->sock; - sock_hold(sk); - } - -out: - return sk; -} - -/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ -static void l2tp_tunnel_sock_put(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - if (tunnel->fd >= 0) { - /* Socket is owned by userspace */ - sockfd_put(sk->sk_socket); - } - sock_put(sk); - } - sock_put(sk); -} - /* Session hash list. * The session_id SHOULD be random according to RFC2661, but several * L2TP implementations (Cisco and Microsoft) use incrementing @@ -193,6 +155,13 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) +{ + sock_put(tunnel->sock); + /* the tunnel is freed in the socket destructor */ +} +EXPORT_SYMBOL(l2tp_tunnel_free); + /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { @@ -345,13 +314,11 @@ int l2tp_session_register(struct l2tp_session *session, } l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); hlist_add_head_rcu(&session->global_hlist, g_head); spin_unlock_bh(&pn->l2tp_session_hlist_lock); } else { l2tp_tunnel_inc_refcount(tunnel); - sock_hold(tunnel->sock); } hlist_add_head(&session->hlist, head); @@ -969,7 +936,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - tunnel = l2tp_sock_to_tunnel(sk); + tunnel = l2tp_tunnel(sk); if (tunnel == NULL) goto pass_up; @@ -977,13 +944,10 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) tunnel->name, skb->len); if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) - goto pass_up_put; + goto pass_up; - sock_put(sk); return 0; -pass_up_put: - sock_put(sk); pass_up: return 1; } @@ -1092,7 +1056,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif @@ -1155,6 +1119,15 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } + /* The user-space may change the connection status for the user-space + * provided socket at run time: we must check it under the socket lock + */ + if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + ret = NET_XMIT_DROP; + goto out_unlock; + } + /* Get routing info from the tunnel socket */ skb_dst_drop(skb); skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0))); @@ -1174,7 +1147,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); @@ -1207,14 +1180,12 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); - struct l2tp_net *pn; if (tunnel == NULL) goto end; l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: @@ -1231,18 +1202,11 @@ static void l2tp_tunnel_destruct(struct sock *sk) sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - - tunnel->sock = NULL; - l2tp_tunnel_dec_refcount(tunnel); - /* Call the original destructor */ if (sk->sk_destruct) (*sk->sk_destruct)(sk); + + kfree_rcu(tunnel, rcu); end: return; } @@ -1303,49 +1267,43 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + + if (tunnel) + l2tp_tunnel_delete(tunnel); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { - struct l2tp_tunnel *tunnel = NULL; - struct socket *sock = NULL; - struct sock *sk = NULL; - - tunnel = container_of(work, struct l2tp_tunnel, del_work); + struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, + del_work); + struct sock *sk = tunnel->sock; + struct socket *sock = sk->sk_socket; + struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); - sk = l2tp_tunnel_sock_lookup(tunnel); - if (!sk) - goto out; - - sock = sk->sk_socket; - - /* If the tunnel socket was created by userspace, then go through the - * inet layer to shut the socket down, and let userspace close it. - * Otherwise, if we created the socket directly within the kernel, use + /* If the tunnel socket was created within the kernel, use * the sk API to release it here. - * In either case the tunnel resources are freed in the socket - * destructor when the tunnel socket goes away. */ - if (tunnel->fd >= 0) { - if (sock) - inet_shutdown(sock, 2); - } else { + if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } - l2tp_tunnel_sock_put(sk); -out: + /* Remove the tunnel struct from the tunnel list */ + pn = l2tp_pernet(tunnel->l2tp_net); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_del_rcu(&tunnel->list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + + /* drop initial ref */ + l2tp_tunnel_dec_refcount(tunnel); + + /* drop workqueue ref */ l2tp_tunnel_dec_refcount(tunnel); } @@ -1515,9 +1473,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 encap = cfg->encap; /* Quick sanity checks */ + err = -EPROTONOSUPPORT; + if (sk->sk_type != SOCK_DGRAM) { + pr_debug("tunl %hu: fd %d wrong socket type\n", + tunnel_id, fd); + goto err; + } switch (encap) { case L2TP_ENCAPTYPE_UDP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_UDP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP); @@ -1525,7 +1488,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } break; case L2TP_ENCAPTYPE_IP: - err = -EPROTONOSUPPORT; if (sk->sk_protocol != IPPROTO_L2TP) { pr_err("tunl %hu: fd %d wrong protocol, got %d, expected %d\n", tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP); @@ -1565,24 +1527,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - - if (ipv6_addr_v4mapped(&np->saddr) && - ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - struct inet_sock *inet = inet_sk(sk); - - tunnel->v4mapped = true; - inet->inet_saddr = np->saddr.s6_addr32[3]; - inet->inet_rcv_saddr = sk->sk_v6_rcv_saddr.s6_addr32[3]; - inet->inet_daddr = sk->sk_v6_daddr.s6_addr32[3]; - } else { - tunnel->v4mapped = false; - } - } -#endif - /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@ -1598,13 +1542,22 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 sk->sk_user_data = tunnel; } + /* Bump the reference count. The tunnel context is deleted + * only when this drops to zero. A reference is also held on + * the tunnel socket to ensure that it is not released while + * the tunnel is extant. Must be done before sk_destruct is + * set. + */ + refcount_set(&tunnel->ref_count, 1); + sock_hold(sk); + tunnel->sock = sk; + tunnel->fd = fd; + /* Hook on the tunnel socket destructor so that we can cleanup * if the tunnel socket goes away. */ tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - tunnel->sock = sk; - tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; @@ -1614,11 +1567,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); - - /* Bump the reference count. The tunnel context is deleted - * only when this drops to zero. Must be done before list insertion - */ - refcount_set(&tunnel->ref_count, 1); spin_lock_bh(&pn->l2tp_tunnel_list_lock); list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); spin_unlock_bh(&pn->l2tp_tunnel_list_lock); @@ -1659,8 +1607,6 @@ void l2tp_session_free(struct l2tp_session *session) if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - sock_put(tunnel->sock); - session->tunnel = NULL; l2tp_tunnel_dec_refcount(tunnel); } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9bbee90e9963..2718d0b284d0 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -188,9 +188,6 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ -#if IS_ENABLED(CONFIG_IPV6) - bool v4mapped; -#endif struct work_struct del_work; @@ -214,27 +211,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) return &session->priv[0]; } -static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk) -{ - struct l2tp_tunnel *tunnel; - - if (sk == NULL) - return NULL; - - sock_hold(sk); - tunnel = (struct l2tp_tunnel *)(sk->sk_user_data); - if (tunnel == NULL) { - sock_put(sk); - goto out; - } - - BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - -out: - return tunnel; -} - struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); +void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, @@ -283,7 +261,7 @@ static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) - kfree_rcu(tunnel, rcu); + l2tp_tunnel_free(tunnel); } /* Session reference counts. Incremented when code obtains a reference diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index ff61124fdf59..3428fba6f2b7 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -234,17 +234,13 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { struct sk_buff *skb; - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } - - sk_refcnt_debug_dec(sk); + if (tunnel) + l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 192344688c06..6f009eaa5fbe 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -248,16 +248,14 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + struct l2tp_tunnel *tunnel = sk->sk_user_data; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) { - l2tp_tunnel_closeall(tunnel); - sock_put(sk); - } + if (tunnel) + l2tp_tunnel_delete(tunnel); inet6_destroy_sock(sk); } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 59f246d7b290..3b02f24ea9ec 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -416,20 +416,28 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ +static void pppol2tp_put_sk(struct rcu_head *head) +{ + struct pppol2tp_session *ps; + + ps = container_of(head, typeof(*ps), rcu); + sock_put(ps->__sk); +} + /* Called by l2tp_core when a session socket is being closed. */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct sock *sk; - - BUG_ON(session->magic != L2TP_SESSION_MAGIC); + struct pppol2tp_session *ps; - sk = pppol2tp_session_get_sock(session); - if (sk) { - if (sk->sk_socket) - inet_shutdown(sk->sk_socket, SEND_SHUTDOWN); - sock_put(sk); - } + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + if (ps->__sk) + call_rcu(&ps->rcu, pppol2tp_put_sk); + mutex_unlock(&ps->sk_lock); } /* Really kill the session socket. (Called from sock_put() if @@ -449,14 +457,6 @@ static void pppol2tp_session_destruct(struct sock *sk) } } -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Called when the PPPoX socket (session) is closed. */ static int pppol2tp_release(struct socket *sock) @@ -480,26 +480,17 @@ static int pppol2tp_release(struct socket *sock) sock_orphan(sk); sock->sk = NULL; + /* If the socket is associated with a session, + * l2tp_session_delete will call pppol2tp_session_close which + * will drop the session's ref on the socket. + */ session = pppol2tp_sock_to_session(sk); - - if (session != NULL) { - struct pppol2tp_session *ps; - + if (session) { l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop the ref obtained by pppol2tp_sock_to_session */ + sock_put(sk); } + release_sock(sk); /* This will delete the session context via @@ -796,6 +787,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ + sock_hold(sk); sk->sk_user_data = session; rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 1f466d12a6bc..94c7ee9df33b 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -212,6 +212,7 @@ static const char *hw_flag_names[] = { FLAG(REPORTS_LOW_ACK), FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), + FLAG(DOESNT_SUPPORT_QOS_NDP), #undef FLAG }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 39b660b9a908..5f303abac5ad 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -896,7 +896,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, true); + skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, + !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) return; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fd580614085b..56fe16b07538 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3921,7 +3921,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, if ((hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS)) != fast_rx->expected_ds_bits) - goto drop; + return false; /* assign the key to drop unencrypted frames (later) * and strip the IV/MIC if necessary diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 25904af38839..69722504e3e1 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3574,6 +3574,14 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (!IS_ERR_OR_NULL(sta)) { struct ieee80211_fast_tx *fast_tx; + /* We need a bit of data queued to build aggregates properly, so + * instruct the TCP stack to allow more than a single ms of data + * to be queued in the stack. The value is a bit-shift of 1 + * second, so 8 is ~4ms of queued data. Only affects local TCP + * sockets. + */ + sk_pacing_shift_update(skb->sk, 8); + fast_tx = rcu_dereference(sta->fast_tx); if (fast_tx && diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index e545a3c9365f..7a4de6d618b1 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -122,7 +122,7 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 3e17d32b629d..58d5d05aec24 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -260,7 +260,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); - if (ct && (ct->status & IPS_NAT_MASK)) { + if (ct) { bool mangled; /* If mangling fails this function will return 0 diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8b9fe30de0cd..c4acc7340eb1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5037,9 +5037,9 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nf_flowtable_type *type; + struct nft_flowtable *flowtable, *ft; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; - struct nft_flowtable *flowtable; struct nft_table *table; struct nft_ctx ctx; int err, i, k; @@ -5099,6 +5099,22 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err3; for (i = 0; i < flowtable->ops_len; i++) { + if (!flowtable->ops[i].dev) + continue; + + list_for_each_entry(ft, &table->flowtables, list) { + for (k = 0; k < ft->ops_len; k++) { + if (!ft->ops[k].dev) + continue; + + if (flowtable->ops[i].dev == ft->ops[k].dev && + flowtable->ops[i].pf == ft->ops[k].pf) { + err = -EBUSY; + goto err4; + } + } + } + err = nf_register_net_hook(net, &flowtable->ops[i]); if (err < 0) goto err4; @@ -5120,7 +5136,7 @@ err5: i = flowtable->ops_len; err4: for (k = i - 1; k >= 0; k--) - nf_unregister_net_hook(net, &flowtable->ops[i]); + nf_unregister_net_hook(net, &flowtable->ops[k]); kfree(flowtable->ops); err3: @@ -5145,6 +5161,11 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, struct nft_table *table; struct nft_ctx ctx; + if (!nla[NFTA_FLOWTABLE_TABLE] || + (!nla[NFTA_FLOWTABLE_NAME] && + !nla[NFTA_FLOWTABLE_HANDLE])) + return -EINVAL; + table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, genmask); if (IS_ERR(table)) @@ -5402,6 +5423,7 @@ err: static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { cancel_delayed_work_sync(&flowtable->data.gc_work); + kfree(flowtable->ops); kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); rhashtable_destroy(&flowtable->data.rhashtable); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 3f1624ee056f..d40591fe1b2f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -674,7 +674,7 @@ static const struct nft_set_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, u32 flags) { - if (desc->size) { + if (desc->size && !(flags & NFT_SET_TIMEOUT)) { switch (desc->klen) { case 4: return &nft_hash_fast_ops; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index fa1655aff8d3..4aa01c90e9d1 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -423,6 +423,36 @@ textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) return buf; } +/** + * xt_check_proc_name - check that name is suitable for /proc file creation + * + * @name: file name candidate + * @size: length of buffer + * + * some x_tables modules wish to create a file in /proc. + * This function makes sure that the name is suitable for this + * purpose, it checks that name is NUL terminated and isn't a 'special' + * name, like "..". + * + * returns negative number on error or 0 if name is useable. + */ +int xt_check_proc_name(const char *name, unsigned int size) +{ + if (name[0] == '\0') + return -EINVAL; + + if (strnlen(name, size) == size) + return -ENAMETOOLONG; + + if (strcmp(name, ".") == 0 || + strcmp(name, "..") == 0 || + strchr(name, '/')) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(xt_check_proc_name); + int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 66f5aca62a08..3360f13dc208 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -917,8 +917,9 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); @@ -935,8 +936,9 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) struct hashlimit_cfg3 cfg = {}; int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); @@ -950,9 +952,11 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) static int hashlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo3 *info = par->matchinfo; + int ret; - if (info->name[sizeof(info->name) - 1] != '\0') - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, info->name, 3); diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 6d232d18faff..81ee1d6543b2 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -361,9 +361,9 @@ static int recent_mt_check(const struct xt_mtchk_param *par, info->hit_count, XT_RECENT_MAX_NSTAMPS - 1); return -EINVAL; } - if (info->name[0] == '\0' || - strnlen(info->name, XT_RECENT_NAME_LEN) == XT_RECENT_NAME_LEN) - return -EINVAL; + ret = xt_check_proc_name(info->name, sizeof(info->name)); + if (ret) + return ret; if (ip_pkt_list_tot && info->hit_count < ip_pkt_list_tot) nstamp_mask = roundup_pow_of_two(ip_pkt_list_tot) - 1; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 6f02499ef007..b9ce82c9440f 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1106,7 +1106,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, if (!err) delivered = true; else if (err != -ESRCH) - goto error; + return err; return delivered ? 0 : -ESRCH; error: kfree_skb(skb); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 04b94281a30b..b891a91577f8 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -242,14 +242,20 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]); band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]); + if (band->rate == 0) { + err = -EINVAL; + goto exit_free_meter; + } + band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]); /* Figure out max delta_t that is enough to fill any bucket. * Keep max_delta_t size to the bucket units: * pkts => 1/1000 packets, kilobits => bits. + * + * Start with a full bucket. */ - band_max_delta_t = (band->burst_size + band->rate) * 1000; - /* Start with a full bucket. */ - band->bucket = band_max_delta_t; + band->bucket = (band->burst_size + band->rate) * 1000; + band_max_delta_t = band->bucket / band->rate; if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; diff --git a/net/qrtr/smd.c b/net/qrtr/smd.c index 50615d5efac1..9cf089b9754e 100644 --- a/net/qrtr/smd.c +++ b/net/qrtr/smd.c @@ -114,5 +114,6 @@ static struct rpmsg_driver qcom_smd_qrtr_driver = { module_rpmsg_driver(qcom_smd_qrtr_driver); +MODULE_ALIAS("rpmsg:IPCRTR"); MODULE_DESCRIPTION("Qualcomm IPC-Router SMD interface driver"); MODULE_LICENSE("GPL v2"); diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c061d6eb465d..22571189f21e 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2006 Oracle. All rights reserved. + * Copyright (c) 2006, 2018 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -142,12 +142,20 @@ int rds_tcp_accept_one(struct socket *sock) if (ret) goto out; - new_sock->type = sock->type; - new_sock->ops = sock->ops; ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true); if (ret < 0) goto out; + /* sock_create_lite() does not get a hold on the owner module so we + * need to do it here. Note that sock_release() uses sock->ops to + * determine if it needs to decrement the reference count. So set + * sock->ops after calling accept() in case that fails. And there's + * no need to do try_module_get() as the listener should have a hold + * already. + */ + new_sock->ops = sock->ops; + __module_get(new_sock->ops->owner); + ret = rds_tcp_keepalive(new_sock); if (ret < 0) goto out; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index b3f2c15affa7..9d2cabf1dc7e 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -352,7 +352,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return res; out: if (res == ACT_P_CREATED) - tcf_idr_cleanup(*act, est); + tcf_idr_release(*act, bind); return ret; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index b7ba9b06b147..2a5c8fd860cf 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -350,7 +350,7 @@ static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, { struct sctphdr *sctph; - if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); @@ -626,7 +626,8 @@ static void tcf_csum_cleanup(struct tc_action *a) struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); - kfree_rcu(params, rcu); + if (params) + kfree_rcu(params, rcu); } static int tcf_csum_walker(struct net *net, struct sk_buff *skb, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 06e380ae0928..7e06b9b62613 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -80,9 +80,12 @@ static void ipt_destroy_target(struct xt_entry_target *t) static void tcf_ipt_release(struct tc_action *a) { struct tcf_ipt *ipt = to_ipt(a); - ipt_destroy_target(ipt->tcfi_t); + + if (ipt->tcfi_t) { + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_t); + } kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); } static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { @@ -187,7 +190,7 @@ err2: kfree(tname); err1: if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 349beaffb29e..fef08835f26d 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -176,7 +176,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p = to_pedit(*a); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); kfree(keys_ex); return -ENOMEM; } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 95d3c9097b25..faebf82b99f1 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -194,7 +194,7 @@ failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (ret == ACT_P_CREATED) - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1ba0df238756..74c5d7e6a0fa 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -103,7 +103,8 @@ static void tcf_sample_cleanup(struct tc_action *a) psample_group = rtnl_dereference(s->psample_group); RCU_INIT_POINTER(s->psample_group, NULL); - psample_group_put(psample_group); + if (psample_group) + psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 425eac11f6da..b1f38063ada0 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -121,7 +121,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, d = to_defact(*a); ret = alloc_defdata(d, defdata); if (ret < 0) { - tcf_idr_cleanup(*a, est); + tcf_idr_release(*a, bind); return ret; } d->tcf_action = parm->action; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index fa975262dbac..7b0700f52b50 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -152,7 +152,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, ASSERT_RTNL(); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@ -190,7 +190,8 @@ static void tcf_skbmod_cleanup(struct tc_action *a) struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 0e23aac09ad6..1281ca463727 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -153,6 +153,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: + ret = -EINVAL; goto err_out; } @@ -207,11 +208,12 @@ static void tunnel_key_release(struct tc_action *a) struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); + if (params) { + if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(¶ms->tcft_enc_metadata->dst); - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(¶ms->tcft_enc_metadata->dst); - - kfree_rcu(params, rcu); + kfree_rcu(params, rcu); + } } static int tunnel_key_dump_addresses(struct sk_buff *skb, diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index e1a1b3f3983a..c49cb61adedf 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -195,7 +195,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, ASSERT_RTNL(); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { - if (ovr) + if (ret == ACT_P_CREATED) tcf_idr_release(*a, bind); return -ENOMEM; } @@ -225,7 +225,8 @@ static void tcf_vlan_cleanup(struct tc_action *a) struct tcf_vlan_params *p; p = rcu_dereference_protected(v->vlan_p, 1); - kfree_rcu(p, rcu); + if (p) + kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 190570f21b20..7e3fbe9cc936 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -106,6 +106,14 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, __skb_queue_tail(&q->skb_bad_txq, skb); + if (qdisc_is_percpu_stats(q)) { + qdisc_qstats_cpu_backlog_inc(q, skb); + qdisc_qstats_cpu_qlen_inc(q); + } else { + qdisc_qstats_backlog_inc(q, skb); + q->q.qlen++; + } + if (lock) spin_unlock(lock); } @@ -196,14 +204,6 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { qdisc_enqueue_skb_bad_txq(q, nskb); - - if (qdisc_is_percpu_stats(q)) { - qdisc_qstats_cpu_backlog_inc(q, nskb); - qdisc_qstats_cpu_qlen_inc(q); - } else { - qdisc_qstats_backlog_inc(q, nskb); - q->q.qlen++; - } break; } skb->next = nskb; @@ -628,6 +628,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, int band = prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct skb_array *q = band2list(priv, band); + unsigned int pkt_len = qdisc_pkt_len(skb); int err; err = skb_array_produce(q, skb); @@ -636,7 +637,10 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, return qdisc_drop_cpu(skb, qdisc, to_free); qdisc_qstats_cpu_qlen_inc(qdisc); - qdisc_qstats_cpu_backlog_inc(qdisc, skb); + /* Note: skb can not be used after skb_array_produce(), + * so we better not use qdisc_qstats_cpu_backlog_inc() + */ + this_cpu_add(qdisc->cpu_qstats->backlog, pkt_len); return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7c179addebcd..7d6801fc5340 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,7 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop(skb, sch, to_free); + return qdisc_drop_all(skb, sch, to_free); qdisc_qstats_backlog_inc(sch, skb); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 229172d509cc..03225a8df973 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -188,7 +188,8 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, int ret; if (qdisc_pkt_len(skb) > q->max_size) { - if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) + if (skb_is_gso(skb) && + skb_gso_validate_mac_len(skb, q->max_size)) return tbf_segment(skb, sch, to_free); return qdisc_drop(skb, sch, to_free); } diff --git a/net/sctp/input.c b/net/sctp/input.c index 0247cc432e02..b381d78548ac 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -106,6 +106,7 @@ int sctp_rcv(struct sk_buff *skb) int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); + bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -123,8 +124,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && - skb_linearize(skb)) || + if ((!is_gso && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; @@ -135,7 +135,7 @@ int sctp_rcv(struct sk_buff *skb) if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); else if (!sctp_checksum_disable && - !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + !is_gso && sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; @@ -1218,7 +1218,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, * issue as packets hitting this are mostly INIT or INIT-ACK and * those cannot be on GSO-style anyway. */ - if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) + if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return NULL; ch = (struct sctp_chunkhdr *)skb->data; diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 48392552ee7c..23ebc5318edc 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -170,7 +170,7 @@ next_chunk: chunk = list_entry(entry, struct sctp_chunk, list); - if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { + if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) { /* GSO-marked skbs but without frags, handle * them normally */ diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 35bc7106d182..123e9f2dc226 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -45,7 +45,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh; - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)) + if (!skb_is_gso_sctp(skb)) goto out; sh = sctp_hdr(skb); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da1a5cdefd13..1e0d780855c3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -978,10 +978,6 @@ out: lsmc->clcsock = NULL; } release_sock(lsk); - /* no more listening, wake up smc_close_wait_listen_clcsock and - * accept - */ - lsk->sk_state_change(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_listen */ } @@ -1406,8 +1402,10 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, smc->use_fallback = false; /* assume rdma capability first */ rc = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &smc->clcsock); - if (rc) + if (rc) { sk_common_release(sk); + goto out; + } smc->sk.sk_sndbuf = max(smc->clcsock->sk->sk_sndbuf, SMC_BUF_MIN_SIZE); smc->sk.sk_rcvbuf = max(smc->clcsock->sk->sk_rcvbuf, SMC_BUF_MIN_SIZE); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 3cd086e5bd28..b42395d24cba 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -269,7 +269,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ - if (cdc->len != sizeof(*cdc)) + if (cdc->len != SMC_WR_TX_SIZE) return; /* invalid message */ smc_cdc_msg_recv(cdc, link, wc->wr_id); } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index e339c0186dcf..fa41d9881741 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -30,27 +30,6 @@ static void smc_close_cleanup_listen(struct sock *parent) smc_close_non_accepted(sk); } -static void smc_close_wait_listen_clcsock(struct smc_sock *smc) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct sock *sk = &smc->sk; - signed long timeout; - - timeout = SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME; - add_wait_queue(sk_sleep(sk), &wait); - do { - release_sock(sk); - if (smc->clcsock) - timeout = wait_woken(&wait, TASK_UNINTERRUPTIBLE, - timeout); - sched_annotate_sleep(); - lock_sock(sk); - if (!smc->clcsock) - break; - } while (timeout); - remove_wait_queue(sk_sleep(sk), &wait); -} - /* wait for sndbuf data being transmitted */ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) { @@ -204,9 +183,11 @@ again: rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); /* wake up kernel_accept of smc_tcp_listen_worker */ smc->clcsock->sk->sk_data_ready(smc->clcsock->sk); - smc_close_wait_listen_clcsock(smc); } smc_close_cleanup_listen(sk); + release_sock(sk); + flush_work(&smc->tcp_listen_work); + lock_sock(sk); break; case SMC_ACTIVE: smc_close_stream_wait(smc, timeout); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2424c7100aaf..645dd226177b 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -177,6 +177,7 @@ static int smc_lgr_create(struct smc_sock *smc, __be32 peer_in_addr, lnk = &lgr->lnk[SMC_SINGLE_LINK]; /* initialize link */ + lnk->link_id = SMC_SINGLE_LINK; lnk->smcibdev = smcibdev; lnk->ibport = ibport; lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu; @@ -465,7 +466,7 @@ create: rc = smc_link_determine_gid(conn->lgr); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; - conn->local_tx_ctrl.len = sizeof(struct smc_cdc_msg); + conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 92fe4cc8c82c..b4aa4fcedb96 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -92,7 +92,7 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], memcpy(confllc->sender_mac, mac, ETH_ALEN); memcpy(confllc->sender_gid, gid, SMC_GID_SIZE); hton24(confllc->sender_qp_num, link->roce_qp->qp_num); - /* confllc->link_num = SMC_SINGLE_LINK; already done by memset above */ + confllc->link_num = link->link_id; memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE); confllc->max_links = SMC_LINKS_PER_LGR_MAX; /* send llc message */ diff --git a/net/socket.c b/net/socket.c index a93c99b518ca..08847c3b8c39 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2587,6 +2587,11 @@ void sock_unregister(int family) } EXPORT_SYMBOL(sock_unregister); +bool sock_is_registered(int family) +{ + return family < NPROTO && rcu_access_pointer(net_families[family]); +} + static int __init sock_init(void) { int err; diff --git a/net/tipc/group.c b/net/tipc/group.c index 122162a31816..04e516d18054 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -189,6 +189,7 @@ struct tipc_group *tipc_group_create(struct net *net, u32 portid, grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; grp->open = group_is_open; + *grp->open = false; filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, filter, &grp->subid)) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b0323ec7971e..7dfa9fc99ec3 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -473,6 +473,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sk->sk_write_space = tipc_write_space; sk->sk_destruct = tipc_sock_destruct; tsk->conn_timeout = CONN_TIMEOUT_DEFAULT; + tsk->group_is_open = true; atomic_set(&tsk->dupl_rcvcnt, 0); /* Start out with safe limits until we receive an advertised window */ diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index e9b4b53ab53e..d824d548447e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -46,16 +46,26 @@ MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); enum { + TLSV4, + TLSV6, + TLS_NUM_PROTS, +}; + +enum { TLS_BASE_TX, TLS_SW_TX, TLS_NUM_CONFIG, }; -static struct proto tls_prots[TLS_NUM_CONFIG]; +static struct proto *saved_tcpv6_prot; +static DEFINE_MUTEX(tcpv6_prot_mutex); +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG]; static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) { - sk->sk_prot = &tls_prots[ctx->tx_conf]; + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; + + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf]; } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -453,8 +463,21 @@ static int tls_setsockopt(struct sock *sk, int level, int optname, return do_tls_setsockopt(sk, optname, optval, optlen); } +static void build_protos(struct proto *prot, struct proto *base) +{ + prot[TLS_BASE_TX] = *base; + prot[TLS_BASE_TX].setsockopt = tls_setsockopt; + prot[TLS_BASE_TX].getsockopt = tls_getsockopt; + prot[TLS_BASE_TX].close = tls_sk_proto_close; + + prot[TLS_SW_TX] = prot[TLS_BASE_TX]; + prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; + prot[TLS_SW_TX].sendpage = tls_sw_sendpage; +} + static int tls_init(struct sock *sk) { + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; int rc = 0; @@ -479,6 +502,17 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; + /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + if (ip_ver == TLSV6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + mutex_lock(&tcpv6_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + mutex_unlock(&tcpv6_prot_mutex); + } + ctx->tx_conf = TLS_BASE_TX; update_sk_prot(sk, ctx); out: @@ -493,21 +527,9 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .init = tls_init, }; -static void build_protos(struct proto *prot, struct proto *base) -{ - prot[TLS_BASE_TX] = *base; - prot[TLS_BASE_TX].setsockopt = tls_setsockopt; - prot[TLS_BASE_TX].getsockopt = tls_getsockopt; - prot[TLS_BASE_TX].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE_TX]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; -} - static int __init tls_register(void) { - build_protos(tls_prots, &tcp_prot); + build_protos(tls_prots[TLSV4], &tcp_prot); tcp_register_ulp(&tcp_tls_ulp_ops); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index 1abcc4fc4df1..41722046b937 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -34,9 +34,10 @@ config CFG80211 When built as a module it will be called cfg80211. +if CFG80211 + config NL80211_TESTMODE bool "nl80211 testmode command" - depends on CFG80211 help The nl80211 testmode command helps implementing things like factory calibration or validation tools for wireless chips. @@ -51,7 +52,6 @@ config NL80211_TESTMODE config CFG80211_DEVELOPER_WARNINGS bool "enable developer warnings" - depends on CFG80211 default n help This option enables some additional warnings that help @@ -68,7 +68,7 @@ config CFG80211_DEVELOPER_WARNINGS config CFG80211_CERTIFICATION_ONUS bool "cfg80211 certification onus" - depends on CFG80211 && EXPERT + depends on EXPERT default n ---help--- You should disable this option unless you are both capable @@ -159,7 +159,6 @@ config CFG80211_REG_RELAX_NO_IR config CFG80211_DEFAULT_PS bool "enable powersave by default" - depends on CFG80211 default y help This option enables powersave mode by default. @@ -170,7 +169,6 @@ config CFG80211_DEFAULT_PS config CFG80211_DEBUGFS bool "cfg80211 DebugFS entries" - depends on CFG80211 depends on DEBUG_FS ---help--- You can enable this if you want debugfs entries for cfg80211. @@ -180,7 +178,6 @@ config CFG80211_DEBUGFS config CFG80211_CRDA_SUPPORT bool "support CRDA" if EXPERT default y - depends on CFG80211 help You should enable this option unless you know for sure you have no need for it, for example when using internal regdb (above) or the @@ -190,7 +187,6 @@ config CFG80211_CRDA_SUPPORT config CFG80211_WEXT bool "cfg80211 wireless extensions compatibility" if !CFG80211_WEXT_EXPORT - depends on CFG80211 select WEXT_CORE default y if CFG80211_WEXT_EXPORT help @@ -199,11 +195,12 @@ config CFG80211_WEXT config CFG80211_WEXT_EXPORT bool - depends on CFG80211 help Drivers should select this option if they require cfg80211's wext compatibility symbols to be exported. +endif # CFG80211 + config LIB80211 tristate default n diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 8e70291e586a..e87d6c4dd5b6 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -217,7 +217,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) if (skb->len <= mtu) goto ok; - if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index ccfdc7115a83..a00ec715aa46 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -283,7 +283,7 @@ static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name) struct crypto_comp *tfm; /* This can be any valid CPU ID so we don't need locking. */ - tfm = __this_cpu_read(*pos->tfms); + tfm = this_cpu_read(*pos->tfms); if (!strcmp(crypto_comp_name(tfm), alg_name)) { pos->users++; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7a23078132cf..625b3fca5704 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1458,10 +1458,13 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, static int xfrm_get_tos(const struct flowi *fl, int family) { const struct xfrm_policy_afinfo *afinfo; - int tos = 0; + int tos; afinfo = xfrm_policy_get_afinfo(family); - tos = afinfo ? afinfo->get_tos(fl) : 0; + if (!afinfo) + return 0; + + tos = afinfo->get_tos(fl); rcu_read_unlock(); @@ -1891,7 +1894,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); - dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0); + dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; @@ -2729,14 +2732,14 @@ static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; + dst = xfrm_dst_child(dst); + if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; - - dst = xfrm_dst_child(dst); } return daddr; } diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 1d38c6acf8af..9e3a5e85f828 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -660,7 +660,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff } else { XFRM_SKB_CB(skb)->seq.output.low = oseq + 1; XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; - xo->seq.low = oseq = oseq + 1; + xo->seq.low = oseq + 1; xo->seq.hi = oseq_hi; oseq += skb_shinfo(skb)->gso_segs; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 54e21f19d722..f9d2f2233f09 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2056,6 +2056,11 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + return -EOPNOTSUPP; +#endif + if (!optval && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7f52b8eb177d..080035f056d9 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -121,22 +121,17 @@ static inline int verify_replay(struct xfrm_usersa_info *p, struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; struct xfrm_replay_state_esn *rs; - if (p->flags & XFRM_STATE_ESN) { - if (!rt) - return -EINVAL; + if (!rt) + return (p->flags & XFRM_STATE_ESN) ? -EINVAL : 0; - rs = nla_data(rt); + rs = nla_data(rt); - if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) - return -EINVAL; - - if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && - nla_len(rt) != sizeof(*rs)) - return -EINVAL; - } + if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) + return -EINVAL; - if (!rt) - return 0; + if (nla_len(rt) < (int)xfrm_replay_state_esn_len(rs) && + nla_len(rt) != sizeof(*rs)) + return -EINVAL; /* As only ESP and AH support ESN feature. */ if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile index 0e349b80686e..ba942e3ead89 100644 --- a/samples/seccomp/Makefile +++ b/samples/seccomp/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +ifndef CROSS_COMPILE hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include @@ -16,7 +17,6 @@ HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include bpf-direct-objs := bpf-direct.o # Try to match the kernel target. -ifndef CROSS_COMPILE ifndef CONFIG_64BIT # s390 has -m31 flag to build 31 bit binaries @@ -35,12 +35,4 @@ HOSTLOADLIBES_bpf-fancy += $(MFLAG) HOSTLOADLIBES_dropper += $(MFLAG) endif always := $(hostprogs-m) -else -# MIPS system calls are defined based on the -mabi that is passed -# to the toolchain which may or may not be a valid option -# for the host toolchain. So disable tests if target architecture -# is MIPS but the host isn't. -ifndef CONFIG_MIPS -always := $(hostprogs-m) -endif endif diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 47cddf32aeba..4f2b25d43ec9 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -256,6 +256,8 @@ __objtool_obj := $(objtree)/tools/objtool/objtool objtool_args = $(if $(CONFIG_UNWINDER_ORC),orc generate,check) +objtool_args += $(if $(part-of-module), --module,) + ifndef CONFIG_FRAME_POINTER objtool_args += --no-fp endif @@ -264,6 +266,12 @@ objtool_args += --no-unreachable else objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif +ifdef CONFIG_RETPOLINE +ifneq ($(RETPOLINE_CFLAGS),) + objtool_args += --retpoline +endif +endif + ifdef CONFIG_MODVERSIONS objtool_o = $(@D)/.tmp_$(@F) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 5589bae34af6..a6f538b31ad6 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -297,11 +297,11 @@ cmd_dt_S_dtb= \ echo '\#include <asm-generic/vmlinux.lds.h>'; \ echo '.section .dtb.init.rodata,"a"'; \ echo '.balign STRUCT_ALIGNMENT'; \ - echo '.global __dtb_$(*F)_begin'; \ - echo '__dtb_$(*F)_begin:'; \ + echo '.global __dtb_$(subst -,_,$(*F))_begin'; \ + echo '__dtb_$(subst -,_,$(*F))_begin:'; \ echo '.incbin "$<" '; \ - echo '__dtb_$(*F)_end:'; \ - echo '.global __dtb_$(*F)_end'; \ + echo '__dtb_$(subst -,_,$(*F))_end:'; \ + echo '.global __dtb_$(subst -,_,$(*F))_end'; \ echo '.balign STRUCT_ALIGNMENT'; \ ) > $@ diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index fa3d39b6f23b..449b68c4c90c 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -93,14 +93,6 @@ * (Note: it'd be easy to port over the complete mkdep state machine, * but I don't think the added complexity is worth it) */ -/* - * Note 2: if somebody writes HELLO_CONFIG_BOOM in a file, it will depend onto - * CONFIG_BOOM. This could seem a bug (not too hard to fix), but please do not - * fix it! Some UserModeLinux files (look at arch/um/) call CONFIG_BOOM as - * UML_CONFIG_BOOM, to avoid conflicts with /usr/include/linux/autoconf.h, - * through arch/um/include/uml-config.h; this fixdep "bug" makes sure that - * those files will have correct dependencies. - */ #include <sys/types.h> #include <sys/stat.h> @@ -233,8 +225,13 @@ static int str_ends_with(const char *s, int slen, const char *sub) static void parse_config_file(const char *p) { const char *q, *r; + const char *start = p; while ((p = strstr(p, "CONFIG_"))) { + if (p > start && (isalnum(p[-1]) || p[-1] == '_')) { + p += 7; + continue; + } p += 7; q = p; while (*q && (isalnum(*q) || *q == '_')) @@ -286,8 +283,6 @@ static int is_ignored_file(const char *s, int len) { return str_ends_with(s, len, "include/generated/autoconf.h") || str_ends_with(s, len, "include/generated/autoksyms.h") || - str_ends_with(s, len, "arch/um/include/uml-config.h") || - str_ends_with(s, len, "include/linux/kconfig.h") || str_ends_with(s, len, ".ver"); } diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index 94b664817ad9..d84a5674e95e 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -15,7 +15,7 @@ signal(SIGPIPE, SIG_DFL) if len(sys.argv) < 3: sys.stderr.write("usage: %s [option] file1 file2\n" % sys.argv[0]) sys.stderr.write("The options are:\n") - sys.stderr.write("-c cateogrize output based on symbole type\n") + sys.stderr.write("-c categorize output based on symbol type\n") sys.stderr.write("-d Show delta of Data Section\n") sys.stderr.write("-t Show delta of text Section\n") sys.exit(-1) diff --git a/scripts/coccinelle/api/memdup.cocci b/scripts/coccinelle/api/memdup.cocci index 1249b727644b..8fd6437beda8 100644 --- a/scripts/coccinelle/api/memdup.cocci +++ b/scripts/coccinelle/api/memdup.cocci @@ -56,10 +56,10 @@ statement S; p << r.p; @@ -coccilib.org.print_todo(p[0], "WARNING opportunity for kmemdep") +coccilib.org.print_todo(p[0], "WARNING opportunity for kmemdup") @script:python depends on report@ p << r.p; @@ -coccilib.report.print_report(p[0], "WARNING opportunity for kmemdep") +coccilib.report.print_report(p[0], "WARNING opportunity for kmemdup") diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 9ee9bf7fd1a2..65792650c630 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -595,7 +595,7 @@ static void optimize_result(void) * original char code */ if (!best_table_len[i]) { - /* find the token with the breates profit value */ + /* find the token with the best profit value */ best = find_best_token(); if (token_profit[best] == 0) break; diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 5c12dc91ef34..df26c7b0fe13 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -178,7 +178,7 @@ static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p) case S_HEX: done: if (sym_string_valid(sym, p)) { - sym->def[def].val = strdup(p); + sym->def[def].val = xstrdup(p); sym->flags |= def_flags; } else { if (def != S_DEF_AUTO) diff --git a/scripts/kconfig/kxgettext.c b/scripts/kconfig/kxgettext.c index 2858738b22d5..240880a89111 100644 --- a/scripts/kconfig/kxgettext.c +++ b/scripts/kconfig/kxgettext.c @@ -101,7 +101,7 @@ static struct message *message__new(const char *msg, char *option, if (self->files == NULL) goto out_fail; - self->msg = strdup(msg); + self->msg = xstrdup(msg); if (self->msg == NULL) goto out_fail_msg; diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index 4e23febbe4b2..2d5ec2d0e952 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -115,6 +115,7 @@ int file_write_dep(const char *name); void *xmalloc(size_t size); void *xcalloc(size_t nmemb, size_t size); void *xrealloc(void *p, size_t size); +char *xstrdup(const char *s); struct gstr { size_t len; diff --git a/scripts/kconfig/lxdialog/check-lxdialog.sh b/scripts/kconfig/lxdialog/check-lxdialog.sh index a10bd9d6fafd..6c0bcd9c472d 100755 --- a/scripts/kconfig/lxdialog/check-lxdialog.sh +++ b/scripts/kconfig/lxdialog/check-lxdialog.sh @@ -55,7 +55,8 @@ EOF echo " *** required header files." 1>&2 echo " *** 'make menuconfig' requires the ncurses libraries." 1>&2 echo " *** " 1>&2 - echo " *** Install ncurses (ncurses-devel) and try again." 1>&2 + echo " *** Install ncurses (ncurses-devel or libncurses-dev " 1>&2 + echo " *** depending on your distribution) and try again." 1>&2 echo " *** " 1>&2 exit 1 fi diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 99222855544c..36cd3e1f1c28 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -212,6 +212,7 @@ void menu_add_option(int token, char *arg) sym_defconfig_list = current_entry->sym; else if (sym_defconfig_list != current_entry->sym) zconf_error("trying to redefine defconfig symbol"); + sym_defconfig_list->flags |= SYMBOL_AUTO; break; case T_OPT_ENV: prop_add_env(arg); diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index cca9663be5dd..2220bc4b051b 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -183,7 +183,7 @@ static void sym_validate_range(struct symbol *sym) sprintf(str, "%lld", val2); else sprintf(str, "0x%llx", val2); - sym->curr.val = strdup(str); + sym->curr.val = xstrdup(str); } static void sym_set_changed(struct symbol *sym) @@ -849,7 +849,7 @@ struct symbol *sym_lookup(const char *name, int flags) : !(symbol->flags & (SYMBOL_CONST|SYMBOL_CHOICE)))) return symbol; } - new_name = strdup(name); + new_name = xstrdup(name); } else { new_name = NULL; hash = 0; diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c index b98a79e30e04..c6f6e21b809f 100644 --- a/scripts/kconfig/util.c +++ b/scripts/kconfig/util.c @@ -154,3 +154,14 @@ void *xrealloc(void *p, size_t size) fprintf(stderr, "Out of memory.\n"); exit(1); } + +char *xstrdup(const char *s) +{ + char *p; + + p = strdup(s); + if (p) + return p; + fprintf(stderr, "Out of memory.\n"); + exit(1); +} diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l index 02de6fe302a9..88b650eb9cc9 100644 --- a/scripts/kconfig/zconf.l +++ b/scripts/kconfig/zconf.l @@ -332,16 +332,12 @@ void zconf_nextfile(const char *name) "Inclusion path:\n current file : '%s'\n", zconf_curname(), zconf_lineno(), zconf_curname()); - iter = current_file->parent; - while (iter && \ - strcmp(iter->name,current_file->name)) { - fprintf(stderr, " included from: '%s:%d'\n", - iter->name, iter->lineno-1); + iter = current_file; + do { iter = iter->parent; - } - if (iter) fprintf(stderr, " included from: '%s:%d'\n", - iter->name, iter->lineno+1); + iter->name, iter->lineno - 1); + } while (strcmp(iter->name, current_file->name)); exit(1); } } diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y index 4be98050b961..ad6305b0f40c 100644 --- a/scripts/kconfig/zconf.y +++ b/scripts/kconfig/zconf.y @@ -127,7 +127,7 @@ no_mainmenu_stmt: /* empty */ * later regardless of whether it comes from the 'prompt' in * mainmenu_stmt or here */ - menu_add_prompt(P_MENU, strdup("Linux Kernel Configuration"), NULL); + menu_add_prompt(P_MENU, xstrdup("Linux Kernel Configuration"), NULL); }; @@ -276,6 +276,7 @@ choice: T_CHOICE word_opt T_EOL sym->flags |= SYMBOL_AUTO; menu_add_entry(sym); menu_add_expr(P_CHOICE, NULL, NULL); + free($2); printd(DEBUG_PARSE, "%s:%d:choice\n", zconf_curname(), zconf_lineno()); }; diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index c0d129d7f430..be56a1153014 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -246,7 +246,7 @@ else fi; # final build of init/ -${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init GCC_PLUGINS_CFLAGS="${GCC_PLUGINS_CFLAGS}" +${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init archive_builtin diff --git a/sound/core/control.c b/sound/core/control.c index 0b3026d937b1..8a77620a3854 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -889,7 +889,7 @@ static int snd_ctl_elem_read(struct snd_card *card, index_offset = snd_ctl_get_ioff(kctl, &control->id); vd = &kctl->vd[index_offset]; - if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) && kctl->get == NULL) + if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) return -EPERM; snd_ctl_build_ioff(&control->id, kctl, index_offset); diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index b044c0a5a674..02298c9c6020 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1762,10 +1762,9 @@ static int snd_pcm_oss_get_formats(struct snd_pcm_oss_file *pcm_oss_file) return -ENOMEM; _snd_pcm_hw_params_any(params); err = snd_pcm_hw_refine(substream, params); - format_mask = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); - kfree(params); if (err < 0) - return err; + goto error; + format_mask = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); for (fmt = 0; fmt < 32; ++fmt) { if (snd_mask_test(format_mask, fmt)) { int f = snd_pcm_oss_format_to(fmt); @@ -1773,7 +1772,10 @@ static int snd_pcm_oss_get_formats(struct snd_pcm_oss_file *pcm_oss_file) formats |= f; } } - return formats; + + error: + kfree(params); + return err < 0 ? err : formats; } static int snd_pcm_oss_set_format(struct snd_pcm_oss_file *pcm_oss_file, int format) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 04d4db44fae5..61a07fe34cd2 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -255,12 +255,12 @@ static int seq_free_client1(struct snd_seq_client *client) if (!client) return 0; - snd_seq_delete_all_ports(client); - snd_seq_queue_client_leave(client->number); spin_lock_irqsave(&clients_lock, flags); clienttablock[client->number] = 1; clienttab[client->number] = NULL; spin_unlock_irqrestore(&clients_lock, flags); + snd_seq_delete_all_ports(client); + snd_seq_queue_client_leave(client->number); snd_use_lock_sync(&client->use_lock); snd_seq_queue_client_termination(client->number); if (client->pool) @@ -910,7 +910,8 @@ int snd_seq_dispatch_event(struct snd_seq_event_cell *cell, int atomic, int hop) static int snd_seq_client_enqueue_event(struct snd_seq_client *client, struct snd_seq_event *event, struct file *file, int blocking, - int atomic, int hop) + int atomic, int hop, + struct mutex *mutexp) { struct snd_seq_event_cell *cell; int err; @@ -948,7 +949,8 @@ static int snd_seq_client_enqueue_event(struct snd_seq_client *client, return -ENXIO; /* queue is not allocated */ /* allocate an event cell */ - err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic, file); + err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic, + file, mutexp); if (err < 0) return err; @@ -1017,12 +1019,11 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, return -ENXIO; /* allocate the pool now if the pool is not allocated yet */ + mutex_lock(&client->ioctl_mutex); if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) { - mutex_lock(&client->ioctl_mutex); err = snd_seq_pool_init(client->pool); - mutex_unlock(&client->ioctl_mutex); if (err < 0) - return -ENOMEM; + goto out; } /* only process whole events */ @@ -1073,7 +1074,7 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, /* ok, enqueue it */ err = snd_seq_client_enqueue_event(client, &event, file, !(file->f_flags & O_NONBLOCK), - 0, 0); + 0, 0, &client->ioctl_mutex); if (err < 0) break; @@ -1084,6 +1085,8 @@ static ssize_t snd_seq_write(struct file *file, const char __user *buf, written += len; } + out: + mutex_unlock(&client->ioctl_mutex); return written ? written : err; } @@ -1838,9 +1841,11 @@ static int snd_seq_ioctl_set_client_pool(struct snd_seq_client *client, (! snd_seq_write_pool_allocated(client) || info->output_pool != client->pool->size)) { if (snd_seq_write_pool_allocated(client)) { + /* is the pool in use? */ + if (atomic_read(&client->pool->counter)) + return -EBUSY; /* remove all existing cells */ snd_seq_pool_mark_closing(client->pool); - snd_seq_queue_client_leave_cells(client->number); snd_seq_pool_done(client->pool); } client->pool->size = info->output_pool; @@ -2260,7 +2265,8 @@ static int kernel_client_enqueue(int client, struct snd_seq_event *ev, if (! cptr->accept_output) result = -EPERM; else /* send it */ - result = snd_seq_client_enqueue_event(cptr, ev, file, blocking, atomic, hop); + result = snd_seq_client_enqueue_event(cptr, ev, file, blocking, + atomic, hop, NULL); snd_seq_client_unlock(cptr); return result; diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c index a8c2822e0198..72c0302a55d2 100644 --- a/sound/core/seq/seq_fifo.c +++ b/sound/core/seq/seq_fifo.c @@ -125,7 +125,7 @@ int snd_seq_fifo_event_in(struct snd_seq_fifo *f, return -EINVAL; snd_use_lock_use(&f->use_lock); - err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL); /* always non-blocking */ + err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL, NULL); /* always non-blocking */ if (err < 0) { if ((err == -ENOMEM) || (err == -EAGAIN)) atomic_inc(&f->overflow); diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index f763682584a8..ab1112e90f88 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -220,7 +220,8 @@ void snd_seq_cell_free(struct snd_seq_event_cell * cell) */ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, struct snd_seq_event_cell **cellp, - int nonblock, struct file *file) + int nonblock, struct file *file, + struct mutex *mutexp) { struct snd_seq_event_cell *cell; unsigned long flags; @@ -244,7 +245,11 @@ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&pool->output_sleep, &wait); spin_unlock_irq(&pool->lock); + if (mutexp) + mutex_unlock(mutexp); schedule(); + if (mutexp) + mutex_lock(mutexp); spin_lock_irq(&pool->lock); remove_wait_queue(&pool->output_sleep, &wait); /* interrupted? */ @@ -287,7 +292,7 @@ __error: */ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, struct snd_seq_event_cell **cellp, int nonblock, - struct file *file) + struct file *file, struct mutex *mutexp) { int ncells, err; unsigned int extlen; @@ -304,7 +309,7 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, if (ncells >= pool->total_elements) return -ENOMEM; - err = snd_seq_cell_alloc(pool, &cell, nonblock, file); + err = snd_seq_cell_alloc(pool, &cell, nonblock, file, mutexp); if (err < 0) return err; @@ -330,7 +335,8 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, int size = sizeof(struct snd_seq_event); if (len < size) size = len; - err = snd_seq_cell_alloc(pool, &tmp, nonblock, file); + err = snd_seq_cell_alloc(pool, &tmp, nonblock, file, + mutexp); if (err < 0) goto __error; if (cell->event.data.ext.ptr == NULL) diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h index 32f959c17786..3abe306c394a 100644 --- a/sound/core/seq/seq_memory.h +++ b/sound/core/seq/seq_memory.h @@ -66,7 +66,8 @@ struct snd_seq_pool { void snd_seq_cell_free(struct snd_seq_event_cell *cell); int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, - struct snd_seq_event_cell **cellp, int nonblock, struct file *file); + struct snd_seq_event_cell **cellp, int nonblock, + struct file *file, struct mutex *mutexp); /* return number of unused (free) cells */ static inline int snd_seq_unused_cells(struct snd_seq_pool *pool) diff --git a/sound/core/seq/seq_prioq.c b/sound/core/seq/seq_prioq.c index bc1c8488fc2a..2bc6759e4adc 100644 --- a/sound/core/seq/seq_prioq.c +++ b/sound/core/seq/seq_prioq.c @@ -87,7 +87,7 @@ void snd_seq_prioq_delete(struct snd_seq_prioq **fifo) if (f->cells > 0) { /* drain prioQ */ while (f->cells > 0) - snd_seq_cell_free(snd_seq_prioq_cell_out(f)); + snd_seq_cell_free(snd_seq_prioq_cell_out(f, NULL)); } kfree(f); @@ -214,8 +214,18 @@ int snd_seq_prioq_cell_in(struct snd_seq_prioq * f, return 0; } +/* return 1 if the current time >= event timestamp */ +static int event_is_ready(struct snd_seq_event *ev, void *current_time) +{ + if ((ev->flags & SNDRV_SEQ_TIME_STAMP_MASK) == SNDRV_SEQ_TIME_STAMP_TICK) + return snd_seq_compare_tick_time(current_time, &ev->time.tick); + else + return snd_seq_compare_real_time(current_time, &ev->time.time); +} + /* dequeue cell from prioq */ -struct snd_seq_event_cell *snd_seq_prioq_cell_out(struct snd_seq_prioq *f) +struct snd_seq_event_cell *snd_seq_prioq_cell_out(struct snd_seq_prioq *f, + void *current_time) { struct snd_seq_event_cell *cell; unsigned long flags; @@ -227,6 +237,8 @@ struct snd_seq_event_cell *snd_seq_prioq_cell_out(struct snd_seq_prioq *f) spin_lock_irqsave(&f->lock, flags); cell = f->head; + if (cell && current_time && !event_is_ready(&cell->event, current_time)) + cell = NULL; if (cell) { f->head = cell->next; @@ -252,18 +264,6 @@ int snd_seq_prioq_avail(struct snd_seq_prioq * f) return f->cells; } - -/* peek at cell at the head of the prioq */ -struct snd_seq_event_cell *snd_seq_prioq_cell_peek(struct snd_seq_prioq * f) -{ - if (f == NULL) { - pr_debug("ALSA: seq: snd_seq_prioq_cell_in() called with NULL prioq\n"); - return NULL; - } - return f->head; -} - - static inline int prioq_match(struct snd_seq_event_cell *cell, int client, int timestamp) { diff --git a/sound/core/seq/seq_prioq.h b/sound/core/seq/seq_prioq.h index d38bb78d9345..2c315ca10fc4 100644 --- a/sound/core/seq/seq_prioq.h +++ b/sound/core/seq/seq_prioq.h @@ -44,14 +44,12 @@ void snd_seq_prioq_delete(struct snd_seq_prioq **fifo); int snd_seq_prioq_cell_in(struct snd_seq_prioq *f, struct snd_seq_event_cell *cell); /* dequeue cell from prioq */ -struct snd_seq_event_cell *snd_seq_prioq_cell_out(struct snd_seq_prioq *f); +struct snd_seq_event_cell *snd_seq_prioq_cell_out(struct snd_seq_prioq *f, + void *current_time); /* return number of events available in prioq */ int snd_seq_prioq_avail(struct snd_seq_prioq *f); -/* peek at cell at the head of the prioq */ -struct snd_seq_event_cell *snd_seq_prioq_cell_peek(struct snd_seq_prioq *f); - /* client left queue */ void snd_seq_prioq_leave(struct snd_seq_prioq *f, int client, int timestamp); diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index 0428e9061b47..b377f5048352 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -277,30 +277,20 @@ void snd_seq_check_queue(struct snd_seq_queue *q, int atomic, int hop) __again: /* Process tick queue... */ - while ((cell = snd_seq_prioq_cell_peek(q->tickq)) != NULL) { - if (snd_seq_compare_tick_time(&q->timer->tick.cur_tick, - &cell->event.time.tick)) { - cell = snd_seq_prioq_cell_out(q->tickq); - if (cell) - snd_seq_dispatch_event(cell, atomic, hop); - } else { - /* event remains in the queue */ + for (;;) { + cell = snd_seq_prioq_cell_out(q->tickq, + &q->timer->tick.cur_tick); + if (!cell) break; - } + snd_seq_dispatch_event(cell, atomic, hop); } - /* Process time queue... */ - while ((cell = snd_seq_prioq_cell_peek(q->timeq)) != NULL) { - if (snd_seq_compare_real_time(&q->timer->cur_time, - &cell->event.time.time)) { - cell = snd_seq_prioq_cell_out(q->timeq); - if (cell) - snd_seq_dispatch_event(cell, atomic, hop); - } else { - /* event remains in the queue */ + for (;;) { + cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time); + if (!cell) break; - } + snd_seq_dispatch_event(cell, atomic, hop); } /* free lock */ diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 0333143a1fa7..1063a4377502 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -192,6 +192,11 @@ static inline void loopback_timer_stop(struct loopback_pcm *dpcm) dpcm->timer.expires = 0; } +static inline void loopback_timer_stop_sync(struct loopback_pcm *dpcm) +{ + del_timer_sync(&dpcm->timer); +} + #define CABLE_VALID_PLAYBACK (1 << SNDRV_PCM_STREAM_PLAYBACK) #define CABLE_VALID_CAPTURE (1 << SNDRV_PCM_STREAM_CAPTURE) #define CABLE_VALID_BOTH (CABLE_VALID_PLAYBACK|CABLE_VALID_CAPTURE) @@ -326,6 +331,8 @@ static int loopback_prepare(struct snd_pcm_substream *substream) struct loopback_cable *cable = dpcm->cable; int bps, salign; + loopback_timer_stop_sync(dpcm); + salign = (snd_pcm_format_width(runtime->format) * runtime->channels) / 8; bps = salign * runtime->rate; @@ -659,7 +666,9 @@ static void free_cable(struct snd_pcm_substream *substream) return; if (cable->streams[!substream->stream]) { /* other stream is still alive */ + spin_lock_irq(&cable->lock); cable->streams[substream->stream] = NULL; + spin_unlock_irq(&cable->lock); } else { /* free the cable */ loopback->cables[substream->number][dev] = NULL; @@ -698,7 +707,6 @@ static int loopback_open(struct snd_pcm_substream *substream) loopback->cables[substream->number][dev] = cable; } dpcm->cable = cable; - cable->streams[substream->stream] = dpcm; snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); @@ -730,6 +738,11 @@ static int loopback_open(struct snd_pcm_substream *substream) runtime->hw = loopback_pcm_hardware; else runtime->hw = cable->hw; + + spin_lock_irq(&cable->lock); + cable->streams[substream->stream] = dpcm; + spin_unlock_irq(&cable->lock); + unlock: if (err < 0) { free_cable(substream); @@ -744,7 +757,7 @@ static int loopback_close(struct snd_pcm_substream *substream) struct loopback *loopback = substream->private_data; struct loopback_pcm *dpcm = substream->runtime->private_data; - loopback_timer_stop(dpcm); + loopback_timer_stop_sync(dpcm); mutex_lock(&loopback->cable_lock); free_cable(substream); mutex_unlock(&loopback->cable_lock); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index c71dcacea807..c507c69029e3 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -186,6 +186,10 @@ module_param(power_save, xint, 0644); MODULE_PARM_DESC(power_save, "Automatic power-saving timeout " "(in second, 0 = disable)."); +static bool pm_blacklist = true; +module_param(pm_blacklist, bool, 0644); +MODULE_PARM_DESC(pm_blacklist, "Enable power-management blacklist"); + /* reset the HD-audio controller in power save mode. * this may give more power-saving, but will take longer time to * wake up. @@ -371,6 +375,7 @@ enum { ((pci)->device == 0x160c)) #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_CFL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa348) static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", @@ -1740,6 +1745,10 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci, else chip->bdl_pos_adj = bdl_pos_adj[dev]; + /* Workaround for a communication error on CFL (bko#199007) */ + if (IS_CFL(pci)) + chip->polling_mode = 1; + err = azx_bus_init(chip, model[dev], &pci_hda_io_ops); if (err < 0) { kfree(hda); @@ -2186,6 +2195,24 @@ out_free: return err; } +#ifdef CONFIG_PM +/* On some boards setting power_save to a non 0 value leads to clicking / + * popping sounds when ever we enter/leave powersaving mode. Ideally we would + * figure out how to avoid these sounds, but that is not always feasible. + * So we keep a list of devices where we disable powersaving as its known + * to causes problems on these devices. + */ +static struct snd_pci_quirk power_save_blacklist[] = { + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0), + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0), + /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ + SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), + {} +}; +#endif /* CONFIG_PM */ + /* number of codec slots for each chipset: 0 = default slots (i.e. 4) */ static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = { [AZX_DRIVER_NVIDIA] = 8, @@ -2198,6 +2225,7 @@ static int azx_probe_continue(struct azx *chip) struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; int dev = chip->dev_index; + int val; int err; hda->probe_continued = 1; @@ -2278,7 +2306,21 @@ static int azx_probe_continue(struct azx *chip) chip->running = 1; azx_add_card_list(chip); - snd_hda_set_power_save(&chip->bus, power_save * 1000); + + val = power_save; +#ifdef CONFIG_PM + if (pm_blacklist) { + const struct snd_pci_quirk *q; + + q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); + if (q && val) { + dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", + q->subvendor, q->subdevice); + val = 0; + } + } +#endif /* CONFIG_PM */ + snd_hda_set_power_save(&chip->bus, val * 1000); if (azx_has_pm_runtime(chip) || hda->use_vga_switcheroo) pm_runtime_put_autosuspend(&pci->dev); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 37e1cf8218ff..5b4dbcec6de8 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -957,6 +957,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC), SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC), SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index ce28f7ce64e6..aef1f52db7d9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3130,6 +3130,8 @@ static void alc256_init(struct hda_codec *codec) alc_update_coef_idx(codec, 0x46, 3 << 12, 0); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x4); /* Hight power */ + alc_update_coefex_idx(codec, 0x53, 0x02, 0x8000, 1 << 15); /* Clear bit */ + alc_update_coefex_idx(codec, 0x53, 0x02, 0x8000, 0 << 15); } static void alc256_shutup(struct hda_codec *codec) @@ -3596,8 +3598,12 @@ static void alc269_fixup_mic_mute_hook(void *private_data, int enabled) pinval = snd_hda_codec_get_pin_target(codec, spec->mute_led_nid); pinval &= ~AC_PINCTL_VREFEN; pinval |= enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80; - if (spec->mute_led_nid) + if (spec->mute_led_nid) { + /* temporarily power up/down for setting VREF */ + snd_hda_power_up_pm(codec); snd_hda_set_pin_ctl_cache(codec, spec->mute_led_nid, pinval); + snd_hda_power_down_pm(codec); + } } /* Make sure the led works even in runtime suspend */ @@ -4997,13 +5003,14 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PRE_PROBE) { spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP; + snd_hda_apply_pincfgs(codec, pincfgs); + } else if (action == HDA_FIXUP_ACT_INIT) { /* Enable DOCK device */ snd_hda_codec_write(codec, 0x17, 0, AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); /* Enable DOCK device */ snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_CONFIG_DEFAULT_BYTES_3, 0); - snd_hda_apply_pincfgs(codec, pincfgs); } } @@ -5273,6 +5280,16 @@ static void alc298_fixup_speaker_volume(struct hda_codec *codec, } } +/* disable DAC3 (0x06) selection on NID 0x17 as it has no volume amp control */ +static void alc295_fixup_disable_dac3(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + hda_nid_t conn[2] = { 0x02, 0x03 }; + snd_hda_override_conn_list(codec, 0x17, 2, conn); + } +} + /* Hook to update amp GPIO4 for automute */ static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec, struct hda_jack_callback *jack) @@ -5465,6 +5482,7 @@ enum { ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC295_FIXUP_DISABLE_DAC3, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -5479,10 +5497,13 @@ enum { ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, ALC233_FIXUP_LENOVO_MULTI_CODECS, ALC294_FIXUP_LENOVO_MIC_LOCATION, + ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, ALC298_FIXUP_TPT470_DOCK, + ALC255_FIXUP_DUMMY_LINEOUT_VERB, + ALC255_FIXUP_DELL_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -6197,6 +6218,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, }, + [ALC295_FIXUP_DISABLE_DAC3] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc295_fixup_disable_dac3, + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6282,6 +6307,18 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x16, 0x0101102f }, /* Rear Headset HP */ + { 0x19, 0x02a1913c }, /* use as Front headset mic, without its own jack detect */ + { 0x1a, 0x01a19030 }, /* Rear Headset MIC */ + { 0x1b, 0x02011020 }, + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, [ALC700_FIXUP_INTEL_REFERENCE] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -6318,6 +6355,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC293_FIXUP_LENOVO_SPK_NOISE }, + [ALC255_FIXUP_DUMMY_LINEOUT_VERB] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x14, 0x0201101f }, + { } + }, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC255_FIXUP_DELL_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6366,10 +6419,15 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), + SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), + SND_PCI_QUIRK(0x1028, 0x080c, "Dell WYSE", ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -6507,9 +6565,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x2249, "Thinkpad", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x224b, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224c, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x224d, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), + SND_PCI_QUIRK(0x17aa, 0x225d, "Thinkpad T480", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), @@ -6871,7 +6931,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60120}, {0x14, 0x90170110}, {0x21, 0x0321101f}), - SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x12, 0xb7a60130}, {0x14, 0x90170110}, {0x21, 0x04211020}), @@ -7110,6 +7170,8 @@ static int patch_alc269(struct hda_codec *codec) break; case 0x10ec0257: spec->codec_variant = ALC269_TYPE_ALC257; + spec->shutup = alc256_shutup; + spec->init_hook = alc256_init; spec->gen.mixer_nid = 0; break; case 0x10ec0215: diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index c33a512283a4..9fb356db3ab2 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -579,13 +579,6 @@ static int acp_init(void __iomem *acp_mmio, u32 asic_type) for (bank = 1; bank < 48; bank++) acp_set_sram_bank_state(acp_mmio, bank, false); } - - /* Stoney supports 16bit resolution */ - if (asic_type == CHIP_STONEY) { - val = acp_reg_read(acp_mmio, mmACP_I2S_16BIT_RESOLUTION_EN); - val |= 0x03; - acp_reg_write(val, acp_mmio, mmACP_I2S_16BIT_RESOLUTION_EN); - } return 0; } @@ -774,6 +767,7 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream, { int status; uint64_t size; + u32 val = 0; struct page *pg; struct snd_pcm_runtime *runtime; struct audio_substream_data *rtd; @@ -786,6 +780,14 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream, if (WARN_ON(!rtd)) return -EINVAL; + if (adata->asic_type == CHIP_STONEY) { + val = acp_reg_read(adata->acp_mmio, mmACP_I2S_16BIT_RESOLUTION_EN); + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + val |= ACP_I2S_SP_16BIT_RESOLUTION_EN; + else + val |= ACP_I2S_MIC_16BIT_RESOLUTION_EN; + acp_reg_write(val, adata->acp_mmio, mmACP_I2S_16BIT_RESOLUTION_EN); + } size = params_buffer_bytes(params); status = snd_pcm_lib_malloc_pages(substream, size); if (status < 0) diff --git a/sound/soc/amd/acp.h b/sound/soc/amd/acp.h index ecb458935d1e..9293f179f272 100644 --- a/sound/soc/amd/acp.h +++ b/sound/soc/amd/acp.h @@ -70,6 +70,8 @@ #define CAPTURE_END_DMA_DESCR_CH15 7 #define mmACP_I2S_16BIT_RESOLUTION_EN 0x5209 +#define ACP_I2S_MIC_16BIT_RESOLUTION_EN 0x01 +#define ACP_I2S_SP_16BIT_RESOLUTION_EN 0x02 enum acp_dma_priority_level { /* 0x0 Specifies the DMA channel is given normal priority */ ACP_DMA_PRIORITY_LEVEL_NORMAL = 0x0, diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index 5672e516bec3..c1830ccd3bb8 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -798,12 +798,7 @@ static int hdmi_codec_probe(struct platform_device *pdev) static int hdmi_codec_remove(struct platform_device *pdev) { - struct device *dev = &pdev->dev; - struct hdmi_codec_priv *hcp; - - hcp = dev_get_drvdata(dev); - kfree(hcp->chmap_info); - snd_soc_unregister_codec(dev); + snd_soc_unregister_codec(&pdev->dev); return 0; } diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c index 831b297978a4..45a73049cf64 100644 --- a/sound/soc/codecs/rt5651.c +++ b/sound/soc/codecs/rt5651.c @@ -1722,6 +1722,7 @@ static const struct regmap_config rt5651_regmap = { .num_reg_defaults = ARRAY_SIZE(rt5651_reg), .ranges = rt5651_ranges, .num_ranges = ARRAY_SIZE(rt5651_ranges), + .use_single_rw = true, }; #if defined(CONFIG_OF) diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index e1ab5537d27a..c5c76ab8ccf1 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -529,10 +529,15 @@ static const struct snd_kcontrol_new sgtl5000_snd_controls[] = { static int sgtl5000_digital_mute(struct snd_soc_dai *codec_dai, int mute) { struct snd_soc_codec *codec = codec_dai->codec; - u16 adcdac_ctrl = SGTL5000_DAC_MUTE_LEFT | SGTL5000_DAC_MUTE_RIGHT; + u16 i2s_pwr = SGTL5000_I2S_IN_POWERUP; - snd_soc_update_bits(codec, SGTL5000_CHIP_ADCDAC_CTRL, - adcdac_ctrl, mute ? adcdac_ctrl : 0); + /* + * During 'digital mute' do not mute DAC + * because LINE_IN would be muted aswell. We want to mute + * only I2S block - this can be done by powering it off + */ + snd_soc_update_bits(codec, SGTL5000_CHIP_DIG_POWER, + i2s_pwr, mute ? 0 : i2s_pwr); return 0; } @@ -871,15 +876,26 @@ static int sgtl5000_pcm_hw_params(struct snd_pcm_substream *substream, static int sgtl5000_set_bias_level(struct snd_soc_codec *codec, enum snd_soc_bias_level level) { + struct sgtl5000_priv *sgtl = snd_soc_codec_get_drvdata(codec); + int ret; + switch (level) { case SND_SOC_BIAS_ON: case SND_SOC_BIAS_PREPARE: case SND_SOC_BIAS_STANDBY: + regcache_cache_only(sgtl->regmap, false); + ret = regcache_sync(sgtl->regmap); + if (ret) { + regcache_cache_only(sgtl->regmap, true); + return ret; + } + snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER, SGTL5000_REFTOP_POWERUP, SGTL5000_REFTOP_POWERUP); break; case SND_SOC_BIAS_OFF: + regcache_cache_only(sgtl->regmap, true); snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER, SGTL5000_REFTOP_POWERUP, 0); break; @@ -1237,6 +1253,10 @@ static int sgtl5000_probe(struct snd_soc_codec *codec) */ snd_soc_write(codec, SGTL5000_DAP_CTRL, 0); + /* Unmute DAC after start */ + snd_soc_update_bits(codec, SGTL5000_CHIP_ADCDAC_CTRL, + SGTL5000_DAC_MUTE_LEFT | SGTL5000_DAC_MUTE_RIGHT, 0); + return 0; err: diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 66e32f5d2917..989d093abda7 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1204,12 +1204,14 @@ static int wmfw_add_ctl(struct wm_adsp *dsp, struct wm_coeff_ctl *ctl) kcontrol->put = wm_coeff_put_acked; break; default: - kcontrol->get = wm_coeff_get; - kcontrol->put = wm_coeff_put; - - ctl->bytes_ext.max = ctl->len; - ctl->bytes_ext.get = wm_coeff_tlv_get; - ctl->bytes_ext.put = wm_coeff_tlv_put; + if (kcontrol->access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) { + ctl->bytes_ext.max = ctl->len; + ctl->bytes_ext.get = wm_coeff_tlv_get; + ctl->bytes_ext.put = wm_coeff_tlv_put; + } else { + kcontrol->get = wm_coeff_get; + kcontrol->put = wm_coeff_put; + } break; } diff --git a/sound/soc/sunxi/sun4i-i2s.c b/sound/soc/sunxi/sun4i-i2s.c index dca1143c1150..a4aa931ebfae 100644 --- a/sound/soc/sunxi/sun4i-i2s.c +++ b/sound/soc/sunxi/sun4i-i2s.c @@ -104,7 +104,7 @@ #define SUN8I_I2S_CHAN_CFG_REG 0x30 #define SUN8I_I2S_CHAN_CFG_RX_SLOT_NUM_MASK GENMASK(6, 4) -#define SUN8I_I2S_CHAN_CFG_RX_SLOT_NUM(chan) (chan - 1) +#define SUN8I_I2S_CHAN_CFG_RX_SLOT_NUM(chan) ((chan - 1) << 4) #define SUN8I_I2S_CHAN_CFG_TX_SLOT_NUM_MASK GENMASK(2, 0) #define SUN8I_I2S_CHAN_CFG_TX_SLOT_NUM(chan) (chan - 1) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 50252046b01d..754e632a27bd 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3325,4 +3325,51 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), } }, +{ + /* + * Bower's & Wilkins PX headphones only support the 48 kHz sample rate + * even though it advertises more. The capture interface doesn't work + * even on windows. + */ + USB_DEVICE(0x19b5, 0x0021), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + /* Capture */ + { + .ifnum = 1, + .type = QUIRK_IGNORE_INTERFACE, + }, + /* Playback */ + { + .ifnum = 2, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels = 2, + .iface = 2, + .altsetting = 1, + .altset_idx = 1, + .attributes = UAC_EP_CS_ATTR_FILL_MAX | + UAC_EP_CS_ATTR_SAMPLE_RATE, + .endpoint = 0x03, + .ep_attr = USB_ENDPOINT_XFER_ISOC, + .rates = SNDRV_PCM_RATE_48000, + .rate_min = 48000, + .rate_max = 48000, + .nr_rates = 1, + .rate_table = (unsigned int[]) { + 48000 + } + } + }, + } + } +}, + #undef USB_DEVICE_VENDOR_SPEC diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index a0951505c7f5..4ed9d0c41843 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -50,6 +50,7 @@ /*standard module options for ALSA. This module supports only one card*/ static int hdmi_card_index = SNDRV_DEFAULT_IDX1; static char *hdmi_card_id = SNDRV_DEFAULT_STR1; +static bool single_port; module_param_named(index, hdmi_card_index, int, 0444); MODULE_PARM_DESC(index, @@ -57,6 +58,9 @@ MODULE_PARM_DESC(index, module_param_named(id, hdmi_card_id, charp, 0444); MODULE_PARM_DESC(id, "ID string for INTEL Intel HDMI Audio controller."); +module_param(single_port, bool, 0444); +MODULE_PARM_DESC(single_port, + "Single-port mode (for compatibility)"); /* * ELD SA bits in the CEA Speaker Allocation data block @@ -1579,7 +1583,11 @@ static irqreturn_t display_pipe_interrupt_handler(int irq, void *dev_id) static void notify_audio_lpe(struct platform_device *pdev, int port) { struct snd_intelhad_card *card_ctx = platform_get_drvdata(pdev); - struct snd_intelhad *ctx = &card_ctx->pcm_ctx[port]; + struct snd_intelhad *ctx; + + ctx = &card_ctx->pcm_ctx[single_port ? 0 : port]; + if (single_port) + ctx->port = port; schedule_work(&ctx->hdmi_audio_wq); } @@ -1743,6 +1751,7 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) { struct snd_card *card; struct snd_intelhad_card *card_ctx; + struct snd_intelhad *ctx; struct snd_pcm *pcm; struct intel_hdmi_lpe_audio_pdata *pdata; int irq; @@ -1787,6 +1796,21 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) platform_set_drvdata(pdev, card_ctx); + card_ctx->num_pipes = pdata->num_pipes; + card_ctx->num_ports = single_port ? 1 : pdata->num_ports; + + for_each_port(card_ctx, port) { + ctx = &card_ctx->pcm_ctx[port]; + ctx->card_ctx = card_ctx; + ctx->dev = card_ctx->dev; + ctx->port = single_port ? -1 : port; + ctx->pipe = -1; + + spin_lock_init(&ctx->had_spinlock); + mutex_init(&ctx->mutex); + INIT_WORK(&ctx->hdmi_audio_wq, had_audio_wq); + } + dev_dbg(&pdev->dev, "%s: mmio_start = 0x%x, mmio_end = 0x%x\n", __func__, (unsigned int)res_mmio->start, (unsigned int)res_mmio->end); @@ -1816,19 +1840,12 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev) init_channel_allocations(); card_ctx->num_pipes = pdata->num_pipes; - card_ctx->num_ports = pdata->num_ports; + card_ctx->num_ports = single_port ? 1 : pdata->num_ports; for_each_port(card_ctx, port) { - struct snd_intelhad *ctx = &card_ctx->pcm_ctx[port]; int i; - ctx->card_ctx = card_ctx; - ctx->dev = card_ctx->dev; - ctx->port = port; - ctx->pipe = -1; - - INIT_WORK(&ctx->hdmi_audio_wq, had_audio_wq); - + ctx = &card_ctx->pcm_ctx[port]; ret = snd_pcm_new(card, INTEL_HAD, port, MAX_PB_STREAMS, MAX_CAP_STREAMS, &pcm); if (ret) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 0dfe4d3f74e2..f41079da38c5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -213,6 +213,7 @@ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 0b482c0070e0..465995281dcd 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -55,6 +55,10 @@ #include "main.h" +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + void p_err(const char *fmt, ...) { va_list ap; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 0fb5ef939732..7b26d4b0b052 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt { #define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07 #define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08 #define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) /* * Extension capability list. @@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_AIS_MIGRATION 150 #define KVM_CAP_PPC_GET_CPU_CHAR 151 #define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index a5684d0968b4..5898c22ba310 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -33,7 +33,7 @@ import resource import struct import re import subprocess -from collections import defaultdict +from collections import defaultdict, namedtuple VMX_EXIT_REASONS = { 'EXCEPTION_NMI': 0, @@ -228,6 +228,7 @@ IOCTL_NUMBERS = { } ENCODING = locale.getpreferredencoding(False) +TRACE_FILTER = re.compile(r'^[^\(]*$') class Arch(object): @@ -260,6 +261,11 @@ class Arch(object): return ArchX86(SVM_EXIT_REASONS) return + def tracepoint_is_child(self, field): + if (TRACE_FILTER.match(field)): + return None + return field.split('(', 1)[0] + class ArchX86(Arch): def __init__(self, exit_reasons): @@ -267,6 +273,10 @@ class ArchX86(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = exit_reasons + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchPPC(Arch): def __init__(self): @@ -282,6 +292,10 @@ class ArchPPC(Arch): self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16 self.exit_reasons = {} + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchA64(Arch): def __init__(self): @@ -289,6 +303,10 @@ class ArchA64(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = AARCH64_EXIT_REASONS + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + return None + class ArchS390(Arch): def __init__(self): @@ -296,6 +314,12 @@ class ArchS390(Arch): self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = None + def debugfs_is_child(self, field): + """ Returns name of parent if 'field' is a child, None otherwise """ + if field.startswith('instruction_'): + return 'exit_instruction' + + ARCH = Arch.get_arch() @@ -331,9 +355,6 @@ class perf_event_attr(ctypes.Structure): PERF_TYPE_TRACEPOINT = 2 PERF_FORMAT_GROUP = 1 << 3 -PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing' -PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm' - class Group(object): """Represents a perf event group.""" @@ -376,8 +397,8 @@ class Event(object): self.syscall = self.libc.syscall self.name = name self.fd = None - self.setup_event(group, trace_cpu, trace_pid, trace_point, - trace_filter, trace_set) + self._setup_event(group, trace_cpu, trace_pid, trace_point, + trace_filter, trace_set) def __del__(self): """Closes the event's file descriptor. @@ -390,7 +411,7 @@ class Event(object): if self.fd: os.close(self.fd) - def perf_event_open(self, attr, pid, cpu, group_fd, flags): + def _perf_event_open(self, attr, pid, cpu, group_fd, flags): """Wrapper for the sys_perf_evt_open() syscall. Used to set up performance events, returns a file descriptor or -1 @@ -409,7 +430,7 @@ class Event(object): ctypes.c_int(pid), ctypes.c_int(cpu), ctypes.c_int(group_fd), ctypes.c_long(flags)) - def setup_event_attribute(self, trace_set, trace_point): + def _setup_event_attribute(self, trace_set, trace_point): """Returns an initialized ctype perf_event_attr struct.""" id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set, @@ -419,8 +440,8 @@ class Event(object): event_attr.config = int(open(id_path).read()) return event_attr - def setup_event(self, group, trace_cpu, trace_pid, trace_point, - trace_filter, trace_set): + def _setup_event(self, group, trace_cpu, trace_pid, trace_point, + trace_filter, trace_set): """Sets up the perf event in Linux. Issues the syscall to register the event in the kernel and @@ -428,7 +449,7 @@ class Event(object): """ - event_attr = self.setup_event_attribute(trace_set, trace_point) + event_attr = self._setup_event_attribute(trace_set, trace_point) # First event will be group leader. group_leader = -1 @@ -437,8 +458,8 @@ class Event(object): if group.events: group_leader = group.events[0].fd - fd = self.perf_event_open(event_attr, trace_pid, - trace_cpu, group_leader, 0) + fd = self._perf_event_open(event_attr, trace_pid, + trace_cpu, group_leader, 0) if fd == -1: err = ctypes.get_errno() raise OSError(err, os.strerror(err), @@ -475,6 +496,10 @@ class Event(object): class Provider(object): """Encapsulates functionalities used by all providers.""" + def __init__(self, pid): + self.child_events = False + self.pid = pid + @staticmethod def is_field_wanted(fields_filter, field): """Indicate whether field is valid according to fields_filter.""" @@ -500,12 +525,12 @@ class TracepointProvider(Provider): """ def __init__(self, pid, fields_filter): self.group_leaders = [] - self.filters = self.get_filters() + self.filters = self._get_filters() self.update_fields(fields_filter) - self.pid = pid + super(TracepointProvider, self).__init__(pid) @staticmethod - def get_filters(): + def _get_filters(): """Returns a dict of trace events, their filter ids and the values that can be filtered. @@ -521,8 +546,8 @@ class TracepointProvider(Provider): filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons) return filters - def get_available_fields(self): - """Returns a list of available event's of format 'event name(filter + def _get_available_fields(self): + """Returns a list of available events of format 'event name(filter name)'. All available events have directories under @@ -549,11 +574,12 @@ class TracepointProvider(Provider): def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" - self.fields = [field for field in self.get_available_fields() - if self.is_field_wanted(fields_filter, field)] + self.fields = [field for field in self._get_available_fields() + if self.is_field_wanted(fields_filter, field) or + ARCH.tracepoint_is_child(field)] @staticmethod - def get_online_cpus(): + def _get_online_cpus(): """Returns a list of cpu id integers.""" def parse_int_list(list_string): """Returns an int list from a string of comma separated integers and @@ -575,17 +601,17 @@ class TracepointProvider(Provider): cpu_string = cpu_list.readline() return parse_int_list(cpu_string) - def setup_traces(self): + def _setup_traces(self): """Creates all event and group objects needed to be able to retrieve data.""" - fields = self.get_available_fields() + fields = self._get_available_fields() if self._pid > 0: # Fetch list of all threads of the monitored pid, as qemu # starts a thread for each vcpu. path = os.path.join('/proc', str(self._pid), 'task') groupids = self.walkdir(path)[1] else: - groupids = self.get_online_cpus() + groupids = self._get_online_cpus() # The constant is needed as a buffer for python libs, std # streams and other files that the script opens. @@ -663,7 +689,7 @@ class TracepointProvider(Provider): # The garbage collector will get rid of all Event/Group # objects and open files after removing the references. self.group_leaders = [] - self.setup_traces() + self._setup_traces() self.fields = self._fields def read(self, by_guest=0): @@ -671,8 +697,12 @@ class TracepointProvider(Provider): ret = defaultdict(int) for group in self.group_leaders: for name, val in group.read().items(): - if name in self._fields: - ret[name] += val + if name not in self._fields: + continue + parent = ARCH.tracepoint_is_child(name) + if parent: + name += ' ' + parent + ret[name] += val return ret def reset(self): @@ -690,11 +720,11 @@ class DebugfsProvider(Provider): self._baseline = {} self.do_read = True self.paths = [] - self.pid = pid + super(DebugfsProvider, self).__init__(pid) if include_past: - self.restore() + self._restore() - def get_available_fields(self): + def _get_available_fields(self): """"Returns a list of available fields. The fields are all available KVM debugfs files @@ -704,8 +734,9 @@ class DebugfsProvider(Provider): def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" - self._fields = [field for field in self.get_available_fields() - if self.is_field_wanted(fields_filter, field)] + self._fields = [field for field in self._get_available_fields() + if self.is_field_wanted(fields_filter, field) or + ARCH.debugfs_is_child(field)] @property def fields(self): @@ -758,7 +789,7 @@ class DebugfsProvider(Provider): paths.append(dir) for path in paths: for field in self._fields: - value = self.read_field(field, path) + value = self._read_field(field, path) key = path + field if reset == 1: self._baseline[key] = value @@ -766,20 +797,21 @@ class DebugfsProvider(Provider): self._baseline[key] = 0 if self._baseline.get(key, -1) == -1: self._baseline[key] = value - increment = (results.get(field, 0) + value - - self._baseline.get(key, 0)) - if by_guest: - pid = key.split('-')[0] - if pid in results: - results[pid] += increment - else: - results[pid] = increment + parent = ARCH.debugfs_is_child(field) + if parent: + field = field + ' ' + parent + else: + if by_guest: + field = key.split('-')[0] # set 'field' to 'pid' + increment = value - self._baseline.get(key, 0) + if field in results: + results[field] += increment else: results[field] = increment return results - def read_field(self, field, path): + def _read_field(self, field, path): """Returns the value of a single field from a specific VM.""" try: return int(open(os.path.join(PATH_DEBUGFS_KVM, @@ -794,12 +826,15 @@ class DebugfsProvider(Provider): self._baseline = {} self.read(1) - def restore(self): + def _restore(self): """Reset field counters""" self._baseline = {} self.read(2) +EventStat = namedtuple('EventStat', ['value', 'delta']) + + class Stats(object): """Manages the data providers and the data they provide. @@ -808,13 +843,13 @@ class Stats(object): """ def __init__(self, options): - self.providers = self.get_providers(options) + self.providers = self._get_providers(options) self._pid_filter = options.pid self._fields_filter = options.fields self.values = {} + self._child_events = False - @staticmethod - def get_providers(options): + def _get_providers(self, options): """Returns a list of data providers depending on the passed options.""" providers = [] @@ -826,7 +861,7 @@ class Stats(object): return providers - def update_provider_filters(self): + def _update_provider_filters(self): """Propagates fields filters to providers.""" # As we reset the counters when updating the fields we can # also clear the cache of old values. @@ -847,7 +882,7 @@ class Stats(object): def fields_filter(self, fields_filter): if fields_filter != self._fields_filter: self._fields_filter = fields_filter - self.update_provider_filters() + self._update_provider_filters() @property def pid_filter(self): @@ -861,16 +896,33 @@ class Stats(object): for provider in self.providers: provider.pid = self._pid_filter + @property + def child_events(self): + return self._child_events + + @child_events.setter + def child_events(self, val): + self._child_events = val + for provider in self.providers: + provider.child_events = val + def get(self, by_guest=0): """Returns a dict with field -> (value, delta to last value) of all - provider data.""" + provider data. + Key formats: + * plain: 'key' is event name + * child-parent: 'key' is in format '<child> <parent>' + * pid: 'key' is the pid of the guest, and the record contains the + aggregated event data + These formats are generated by the providers, and handled in class TUI. + """ for provider in self.providers: new = provider.read(by_guest=by_guest) - for key in new if by_guest else provider.fields: - oldval = self.values.get(key, (0, 0))[0] + for key in new: + oldval = self.values.get(key, EventStat(0, 0)).value newval = new.get(key, 0) newdelta = newval - oldval - self.values[key] = (newval, newdelta) + self.values[key] = EventStat(newval, newdelta) return self.values def toggle_display_guests(self, to_pid): @@ -899,10 +951,10 @@ class Stats(object): self.get(to_pid) return 0 + DELAY_DEFAULT = 3.0 MAX_GUEST_NAME_LEN = 48 MAX_REGEX_LEN = 44 -DEFAULT_REGEX = r'^[^\(]*$' SORT_DEFAULT = 0 @@ -969,7 +1021,7 @@ class Tui(object): return res - def print_all_gnames(self, row): + def _print_all_gnames(self, row): """Print a list of all running guests along with their pids.""" self.screen.addstr(row, 2, '%8s %-60s' % ('Pid', 'Guest Name (fuzzy list, might be ' @@ -1032,19 +1084,13 @@ class Tui(object): return name - def update_drilldown(self): - """Sets or removes a filter that only allows fields without braces.""" - if not self.stats.fields_filter: - self.stats.fields_filter = DEFAULT_REGEX - - elif self.stats.fields_filter == DEFAULT_REGEX: - self.stats.fields_filter = None - - def update_pid(self, pid): + def _update_pid(self, pid): """Propagates pid selection to stats object.""" + self.screen.addstr(4, 1, 'Updating pid filter...') + self.screen.refresh() self.stats.pid_filter = pid - def refresh_header(self, pid=None): + def _refresh_header(self, pid=None): """Refreshes the header.""" if pid is None: pid = self.stats.pid_filter @@ -1059,8 +1105,7 @@ class Tui(object): .format(pid, gname), curses.A_BOLD) else: self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) - if self.stats.fields_filter and self.stats.fields_filter \ - != DEFAULT_REGEX: + if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: regex = regex[:MAX_REGEX_LEN] + '...' @@ -1075,56 +1120,99 @@ class Tui(object): self.screen.addstr(4, 1, 'Collecting data...') self.screen.refresh() - def refresh_body(self, sleeptime): + def _refresh_body(self, sleeptime): + def is_child_field(field): + return field.find('(') != -1 + + def insert_child(sorted_items, child, values, parent): + num = len(sorted_items) + for i in range(0, num): + # only add child if parent is present + if parent.startswith(sorted_items[i][0]): + sorted_items.insert(i + 1, (' ' + child, values)) + + def get_sorted_events(self, stats): + """ separate parent and child events """ + if self._sorting == SORT_DEFAULT: + def sortkey((_k, v)): + # sort by (delta value, overall value) + return (v.delta, v.value) + else: + def sortkey((_k, v)): + # sort by overall value + return v.value + + childs = [] + sorted_items = [] + # we can't rule out child events to appear prior to parents even + # when sorted - separate out all children first, and add in later + for key, values in sorted(stats.items(), key=sortkey, + reverse=True): + if values == (0, 0): + continue + if key.find(' ') != -1: + if not self.stats.child_events: + continue + childs.insert(0, (key, values)) + else: + sorted_items.append((key, values)) + if self.stats.child_events: + for key, values in childs: + (child, parent) = key.split(' ') + insert_child(sorted_items, child, values, parent) + + return sorted_items + row = 3 self.screen.move(row, 0) self.screen.clrtobot() stats = self.stats.get(self._display_guests) - - def sortCurAvg(x): - # sort by current events if available - if stats[x][1]: - return (-stats[x][1], -stats[x][0]) + total = 0. + ctotal = 0. + for key, values in stats.items(): + if self._display_guests: + if self.get_gname_from_pid(key): + total += values.value + continue + if not key.find(' ') != -1: + total += values.value else: - return (0, -stats[x][0]) + ctotal += values.value + if total == 0.: + # we don't have any fields, or all non-child events are filtered + total = ctotal - def sortTotal(x): - # sort by totals - return (0, -stats[x][0]) - total = 0. - for key in stats.keys(): - if key.find('(') is -1: - total += stats[key][0] - if self._sorting == SORT_DEFAULT: - sortkey = sortCurAvg - else: - sortkey = sortTotal + # print events tavg = 0 - for key in sorted(stats.keys(), key=sortkey): - if row >= self.screen.getmaxyx()[0] - 1: - break - values = stats[key] - if not values[0] and not values[1]: + tcur = 0 + for key, values in get_sorted_events(self, stats): + if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break - if values[0] is not None: - cur = int(round(values[1] / sleeptime)) if values[1] else '' - if self._display_guests: - key = self.get_gname_from_pid(key) - self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % - (key, values[0], values[0] * 100 / total, - cur)) - if cur is not '' and key.find('(') is -1: - tavg += cur + if self._display_guests: + key = self.get_gname_from_pid(key) + if not key: + continue + cur = int(round(values.delta / sleeptime)) if values.delta else '' + if key[0] != ' ': + if values.delta: + tcur += values.delta + ptotal = values.value + ltotal = total + else: + ltotal = ptotal + self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key, + values.value, + values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: self.screen.addstr(4, 1, 'No matching events reported yet') - else: + if row > 4: + tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % - ('Total', total, tavg if tavg else ''), - curses.A_BOLD) + ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() - def show_msg(self, text): + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' curses.cbreak() @@ -1139,16 +1227,16 @@ class Tui(object): curses.A_STANDOUT) self.screen.getkey() - def show_help_interactive(self): + def _show_help_interactive(self): """Display help with list of interactive commands""" msg = (' b toggle events by guests (debugfs only, honors' ' filters)', ' c clear filter', ' f filter by regular expression', - ' g filter by guest name', + ' g filter by guest name/PID', ' h display interactive commands reference', ' o toggle sorting order (Total vs CurAvg/s)', - ' p filter by PID', + ' p filter by guest name/PID', ' q quit', ' r reset stats', ' s set update interval', @@ -1165,14 +1253,15 @@ class Tui(object): self.screen.addstr(row, 0, line) row += 1 self.screen.getkey() - self.refresh_header() + self._refresh_header() - def show_filter_selection(self): + def _show_filter_selection(self): """Draws filter selection mask. Asks for a valid regex and sets the fields filter accordingly. """ + msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, @@ -1181,61 +1270,25 @@ class Tui(object): self.screen.addstr(2, 0, "Current regex: {0}" .format(self.stats.fields_filter)) + self.screen.addstr(5, 0, msg) self.screen.addstr(3, 0, "New regex: ") curses.echo() regex = self.screen.getstr().decode(ENCODING) curses.noecho() if len(regex) == 0: - self.stats.fields_filter = DEFAULT_REGEX - self.refresh_header() + self.stats.fields_filter = '' + self._refresh_header() return try: re.compile(regex) self.stats.fields_filter = regex - self.refresh_header() + self._refresh_header() return except re.error: + msg = '"' + regex + '": Not a valid regular expression' continue - def show_vm_selection_by_pid(self): - """Draws PID selection mask. - - Asks for a pid until a valid pid or 0 has been entered. - - """ - msg = '' - while True: - self.screen.erase() - self.screen.addstr(0, 0, - 'Show statistics for specific pid.', - curses.A_BOLD) - self.screen.addstr(1, 0, - 'This might limit the shown data to the trace ' - 'statistics.') - self.screen.addstr(5, 0, msg) - self.print_all_gnames(7) - - curses.echo() - self.screen.addstr(3, 0, "Pid [0 or pid]: ") - pid = self.screen.getstr().decode(ENCODING) - curses.noecho() - - try: - if len(pid) > 0: - pid = int(pid) - if pid != 0 and not os.path.isdir(os.path.join('/proc/', - str(pid))): - msg = '"' + str(pid) + '": Not a running process' - continue - else: - pid = 0 - self.refresh_header(pid) - self.update_pid(pid) - break - except ValueError: - msg = '"' + str(pid) + '": Not a valid pid' - - def show_set_update_interval(self): + def _show_set_update_interval(self): """Draws update interval selection mask.""" msg = '' while True: @@ -1265,60 +1318,67 @@ class Tui(object): except ValueError: msg = '"' + str(val) + '": Invalid value' - self.refresh_header() + self._refresh_header() - def show_vm_selection_by_guest_name(self): + def _show_vm_selection_by_guest(self): """Draws guest selection mask. - Asks for a guest name until a valid guest name or '' is entered. + Asks for a guest name or pid until a valid guest name or '' is entered. """ msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, - 'Show statistics for specific guest.', + 'Show statistics for specific guest or pid.', curses.A_BOLD) self.screen.addstr(1, 0, 'This might limit the shown data to the trace ' 'statistics.') self.screen.addstr(5, 0, msg) - self.print_all_gnames(7) + self._print_all_gnames(7) curses.echo() - self.screen.addstr(3, 0, "Guest [ENTER or guest]: ") - gname = self.screen.getstr().decode(ENCODING) + curses.curs_set(1) + self.screen.addstr(3, 0, "Guest or pid [ENTER exits]: ") + guest = self.screen.getstr().decode(ENCODING) curses.noecho() - if not gname: - self.refresh_header(0) - self.update_pid(0) + pid = 0 + if not guest or guest == '0': break - else: - pids = [] - try: - pids = self.get_pid_from_gname(gname) - except: - msg = '"' + gname + '": Internal error while searching, ' \ - 'use pid filter instead' - continue - if len(pids) == 0: - msg = '"' + gname + '": Not an active guest' + if guest.isdigit(): + if not os.path.isdir(os.path.join('/proc/', guest)): + msg = '"' + guest + '": Not a running process' continue - if len(pids) > 1: - msg = '"' + gname + '": Multiple matches found, use pid ' \ - 'filter instead' - continue - self.refresh_header(pids[0]) - self.update_pid(pids[0]) + pid = int(guest) break + pids = [] + try: + pids = self.get_pid_from_gname(guest) + except: + msg = '"' + guest + '": Internal error while searching, ' \ + 'use pid filter instead' + continue + if len(pids) == 0: + msg = '"' + guest + '": Not an active guest' + continue + if len(pids) > 1: + msg = '"' + guest + '": Multiple matches found, use pid ' \ + 'filter instead' + continue + pid = pids[0] + break + curses.curs_set(0) + self._refresh_header(pid) + self._update_pid(pid) def show_stats(self): """Refreshes the screen and processes user input.""" sleeptime = self._delay_initial - self.refresh_header() + self._refresh_header() start = 0.0 # result based on init value never appears on screen while True: - self.refresh_body(time.time() - start) + self._refresh_body(time.time() - start) curses.halfdelay(int(sleeptime * 10)) start = time.time() sleeptime = self._delay_regular @@ -1327,47 +1387,39 @@ class Tui(object): if char == 'b': self._display_guests = not self._display_guests if self.stats.toggle_display_guests(self._display_guests): - self.show_msg(['Command not available with tracepoints' - ' enabled', 'Restart with debugfs only ' - '(see option \'-d\') and try again!']) + self._show_msg(['Command not available with ' + 'tracepoints enabled', 'Restart with ' + 'debugfs only (see option \'-d\') and ' + 'try again!']) self._display_guests = not self._display_guests - self.refresh_header() + self._refresh_header() if char == 'c': - self.stats.fields_filter = DEFAULT_REGEX - self.refresh_header(0) - self.update_pid(0) + self.stats.fields_filter = '' + self._refresh_header(0) + self._update_pid(0) if char == 'f': curses.curs_set(1) - self.show_filter_selection() + self._show_filter_selection() curses.curs_set(0) sleeptime = self._delay_initial - if char == 'g': - curses.curs_set(1) - self.show_vm_selection_by_guest_name() - curses.curs_set(0) + if char == 'g' or char == 'p': + self._show_vm_selection_by_guest() sleeptime = self._delay_initial if char == 'h': - self.show_help_interactive() + self._show_help_interactive() if char == 'o': self._sorting = not self._sorting - if char == 'p': - curses.curs_set(1) - self.show_vm_selection_by_pid() - curses.curs_set(0) - sleeptime = self._delay_initial if char == 'q': break if char == 'r': self.stats.reset() if char == 's': curses.curs_set(1) - self.show_set_update_interval() + self._show_set_update_interval() curses.curs_set(0) sleeptime = self._delay_initial if char == 'x': - self.update_drilldown() - # prevents display of current values on next refresh - self.stats.get(self._display_guests) + self.stats.child_events = not self.stats.child_events except KeyboardInterrupt: break except curses.error: @@ -1380,9 +1432,9 @@ def batch(stats): s = stats.get() time.sleep(1) s = stats.get() - for key in sorted(s.keys()): - values = s[key] - print('%-42s%10d%10d' % (key, values[0], values[1])) + for key, values in sorted(s.items()): + print('%-42s%10d%10d' % (key.split(' ')[0], values.value, + values.delta)) except KeyboardInterrupt: pass @@ -1392,14 +1444,14 @@ def log(stats): keys = sorted(stats.get().keys()) def banner(): - for k in keys: - print(k, end=' ') + for key in keys: + print(key.split(' ')[0], end=' ') print() def statline(): s = stats.get() - for k in keys: - print(' %9d' % s[k][1], end=' ') + for key in keys: + print(' %9d' % s[key].delta, end=' ') print() line = 0 banner_repeat = 20 @@ -1504,7 +1556,7 @@ Press any other key to refresh statistics immediately. ) optparser.add_option('-f', '--fields', action='store', - default=DEFAULT_REGEX, + default='', dest='fields', help='''fields to display (regex) "-f help" for a list of available events''', @@ -1539,17 +1591,6 @@ Press any other key to refresh statistics immediately. def check_access(options): """Exits if the current user can't access all needed directories.""" - if not os.path.exists('/sys/kernel/debug'): - sys.stderr.write('Please enable CONFIG_DEBUG_FS in your kernel.') - sys.exit(1) - - if not os.path.exists(PATH_DEBUGFS_KVM): - sys.stderr.write("Please make sure, that debugfs is mounted and " - "readable by the current user:\n" - "('mount -t debugfs debugfs /sys/kernel/debug')\n" - "Also ensure, that the kvm modules are loaded.\n") - sys.exit(1) - if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or not options.debugfs): sys.stderr.write("Please enable CONFIG_TRACING in your kernel " @@ -1567,7 +1608,33 @@ def check_access(options): return options +def assign_globals(): + global PATH_DEBUGFS_KVM + global PATH_DEBUGFS_TRACING + + debugfs = '' + for line in file('/proc/mounts'): + if line.split(' ')[0] == 'debugfs': + debugfs = line.split(' ')[1] + break + if debugfs == '': + sys.stderr.write("Please make sure that CONFIG_DEBUG_FS is enabled in " + "your kernel, mounted and\nreadable by the current " + "user:\n" + "('mount -t debugfs debugfs /sys/kernel/debug')\n") + sys.exit(1) + + PATH_DEBUGFS_KVM = os.path.join(debugfs, 'kvm') + PATH_DEBUGFS_TRACING = os.path.join(debugfs, 'tracing') + + if not os.path.exists(PATH_DEBUGFS_KVM): + sys.stderr.write("Please make sure that CONFIG_KVM is enabled in " + "your kernel and that the modules are loaded.\n") + sys.exit(1) + + def main(): + assign_globals() options = get_options() options = check_access(options) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index b5b3810c9e94..0811d860fe75 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -35,13 +35,13 @@ INTERACTIVE COMMANDS *f*:: filter by regular expression -*g*:: filter by guest name +*g*:: filter by guest name/PID *h*:: display interactive commands reference *o*:: toggle sorting order (Total vs CurAvg/s) -*p*:: filter by PID +*p*:: filter by guest name/PID *q*:: quit diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 57254f5b2779..694abc628e9b 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -29,7 +29,7 @@ #include "builtin.h" #include "check.h" -bool no_fp, no_unreachable; +bool no_fp, no_unreachable, retpoline, module; static const char * const check_usage[] = { "objtool check [<options>] file.o", @@ -39,6 +39,8 @@ static const char * const check_usage[] = { const struct option check_options[] = { OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"), OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"), + OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"), + OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"), OPT_END(), }; @@ -53,5 +55,5 @@ int cmd_check(int argc, const char **argv) objname = argv[0]; - return check(objname, no_fp, no_unreachable, false); + return check(objname, false); } diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c index 91e8e19ff5e0..77ea2b97117d 100644 --- a/tools/objtool/builtin-orc.c +++ b/tools/objtool/builtin-orc.c @@ -25,7 +25,6 @@ */ #include <string.h> -#include <subcmd/parse-options.h> #include "builtin.h" #include "check.h" @@ -36,9 +35,6 @@ static const char *orc_usage[] = { NULL, }; -extern const struct option check_options[]; -extern bool no_fp, no_unreachable; - int cmd_orc(int argc, const char **argv) { const char *objname; @@ -54,7 +50,7 @@ int cmd_orc(int argc, const char **argv) objname = argv[0]; - return check(objname, no_fp, no_unreachable, true); + return check(objname, true); } if (!strcmp(argv[0], "dump")) { diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h index dd526067fed5..28ff40e19a14 100644 --- a/tools/objtool/builtin.h +++ b/tools/objtool/builtin.h @@ -17,6 +17,11 @@ #ifndef _BUILTIN_H #define _BUILTIN_H +#include <subcmd/parse-options.h> + +extern const struct option check_options[]; +extern bool no_fp, no_unreachable, retpoline, module; + extern int cmd_check(int argc, const char **argv); extern int cmd_orc(int argc, const char **argv); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a8cb69a26576..92b6a2c21631 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -18,6 +18,7 @@ #include <string.h> #include <stdlib.h> +#include "builtin.h" #include "check.h" #include "elf.h" #include "special.h" @@ -33,7 +34,6 @@ struct alternative { }; const char *objname; -static bool no_fp; struct cfi_state initial_func_cfi; struct instruction *find_insn(struct objtool_file *file, @@ -497,6 +497,7 @@ static int add_jump_destinations(struct objtool_file *file) * disguise, so convert them accordingly. */ insn->type = INSN_JUMP_DYNAMIC; + insn->retpoline_safe = true; continue; } else { /* sibling call */ @@ -548,7 +549,8 @@ static int add_call_destinations(struct objtool_file *file) if (!insn->call_dest && !insn->ignore) { WARN_FUNC("unsupported intra-function call", insn->sec, insn->offset); - WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); + if (retpoline) + WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."); return -1; } @@ -923,7 +925,11 @@ static struct rela *find_switch_table(struct objtool_file *file, if (find_symbol_containing(file->rodata, text_rela->addend)) continue; - return find_rela_by_dest(file->rodata, text_rela->addend); + rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend); + if (!rodata_rela) + continue; + + return rodata_rela; } return NULL; @@ -1108,6 +1114,41 @@ static int read_unwind_hints(struct objtool_file *file) return 0; } +static int read_retpoline_hints(struct objtool_file *file) +{ + struct section *sec; + struct instruction *insn; + struct rela *rela; + + sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("bad .discard.retpoline_safe entry"); + return -1; + } + + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call", + insn->sec, insn->offset); + return -1; + } + + insn->retpoline_safe = true; + } + + return 0; +} + static int decode_sections(struct objtool_file *file) { int ret; @@ -1146,6 +1187,10 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; + ret = read_retpoline_hints(file); + if (ret) + return ret; + return 0; } @@ -1891,6 +1936,38 @@ static int validate_unwind_hints(struct objtool_file *file) return warnings; } +static int validate_retpoline(struct objtool_file *file) +{ + struct instruction *insn; + int warnings = 0; + + for_each_insn(file, insn) { + if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) + continue; + + if (insn->retpoline_safe) + continue; + + /* + * .init.text code is ran before userspace and thus doesn't + * strictly need retpolines, except for modules which are + * loaded late, they very much do need retpoline in their + * .init.text + */ + if (!strcmp(insn->sec->name, ".init.text") && !module) + continue; + + WARN_FUNC("indirect %s found in RETPOLINE build", + insn->sec, insn->offset, + insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + + warnings++; + } + + return warnings; +} + static bool is_kasan_insn(struct instruction *insn) { return (insn->type == INSN_CALL && @@ -2022,13 +2099,12 @@ static void cleanup(struct objtool_file *file) elf_close(file->elf); } -int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) +int check(const char *_objname, bool orc) { struct objtool_file file; int ret, warnings = 0; objname = _objname; - no_fp = _no_fp; file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY); if (!file.elf) @@ -2052,6 +2128,13 @@ int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc) if (list_empty(&file.insn_list)) goto out; + if (retpoline) { + ret = validate_retpoline(&file); + if (ret < 0) + return ret; + warnings += ret; + } + ret = validate_functions(&file); if (ret < 0) goto out; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 23a1d065cae1..c6b68fcb926f 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -45,6 +45,7 @@ struct instruction { unsigned char type; unsigned long immediate; bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; + bool retpoline_safe; struct symbol *call_dest; struct instruction *jump_dest; struct instruction *first_jump_src; @@ -63,7 +64,7 @@ struct objtool_file { bool ignore_unreachables, c_file, hints; }; -int check(const char *objname, bool no_fp, bool no_unreachable, bool orc); +int check(const char *objname, bool orc); struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset); diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt index 954ea9e21236..cf9f4040ea5c 100644 --- a/tools/perf/Documentation/perf-kallsyms.txt +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols SYNOPSIS -------- [verse] -'perf kallsyms <options> symbol_name[,symbol_name...]' +'perf kallsyms' [<options>] symbol_name[,symbol_name...] DESCRIPTION ----------- diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index bf4ca749d1ac..a217623fec2e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } } + /* + * If we have just single event and are sending data + * through pipe, we need to force the ids allocation, + * because we synthesize event name through the pipe + * and need the id for that. + */ + if (data->is_pipe && rec->evlist->nr_entries == 1) + rec->opts.sample_id = true; + if (record__open(rec) != 0) { err = -1; goto out_child; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 98bf9d32f222..54a4c152edb3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx, char buf[64], *vals, *ends; if (unit == NULL || fmt == NULL) { - fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep); + fprintf(out, "%s%s", csv_sep, csv_sep); return; } snprintf(buf, sizeof(buf), fmt, val); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b7c823ba8374..35ac016fcb98 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -991,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top, evlist__for_each_entry(evlist, counter) counter->attr.write_backward = false; opts->overwrite = false; - ui__warning("fall back to non-overwrite mode\n"); + pr_debug2("fall back to non-overwrite mode\n"); return 1; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index cfe46236a5e5..57b9b342d533 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -61,6 +61,7 @@ struct record_opts { bool tail_synthesize; bool overwrite; bool ignore_missing_thread; + bool sample_id; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 286427975112..fbf927cf775d 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser) if (!disasm_line__is_valid_jump(cursor, sym)) return; + /* + * This first was seen with a gcc function, _cpp_lex_token, that + * has the usual jumps: + * + * │1159e6c: ↓ jne 115aa32 <_cpp_lex_token@@Base+0xf92> + * + * I.e. jumps to a label inside that function (_cpp_lex_token), and + * those works, but also this kind: + * + * │1159e8b: ↓ jne c469be <cpp_named_operator2name@@Base+0xa72> + * + * I.e. jumps to another function, outside _cpp_lex_token, which + * are not being correctly handled generating as a side effect references + * to ab->offset[] entries that are set to NULL, so to make this code + * more robust, check that here. + * + * A proper fix for will be put in place, looking at the function + * name right after the '<' token and probably treating this like a + * 'call' instruction. + */ target = ab->offsets[cursor->ops.target.offset]; + if (target == NULL) { + ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n", + cursor->ops.target.offset); + return; + } bcursor = browser_line(&cursor->al); btarget = browser_line(target); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 9faf3b5367db..6470ea2aa25e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -60,6 +60,12 @@ #include "sane_ctype.h" #include "symbol/kallsyms.h" +static bool auxtrace__dont_decode(struct perf_session *session) +{ + return !session->itrace_synth_opts || + session->itrace_synth_opts->dont_decode; +} + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd) @@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues, size_t i; int err; + if (auxtrace__dont_decode(session)) + return 0; + list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) { for (i = 0; i < auxtrace_index->nr; i++) { ent = &auxtrace_index->entries[i]; @@ -892,12 +901,6 @@ out_free: return err; } -static bool auxtrace__dont_decode(struct perf_session *session) -{ - return !session->itrace_synth_opts || - session->itrace_synth_opts->dont_decode; -} - int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session) diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 1e97937b03a9..6f09e4962dad 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, struct perf_evsel *evsel; bool use_sample_identifier = false; bool use_comm_exec; + bool sample_id = opts->sample_id; /* * Set the evsel leader links before we configure attributes, @@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, * match the id. */ use_sample_identifier = perf_can_sample_identifier(); - evlist__for_each_entry(evlist, evsel) - perf_evsel__set_sample_id(evsel, use_sample_identifier); + sample_id = true; } else if (evlist->nr_entries > 1) { struct perf_evsel *first = perf_evlist__first(evlist); @@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts, use_sample_identifier = perf_can_sample_identifier(); break; } + sample_id = true; + } + + if (sample_id) { evlist__for_each_entry(evlist, evsel) perf_evsel__set_sample_id(evsel, use_sample_identifier); } diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h index 370138e7e35c..88223bc7c82b 100644 --- a/tools/perf/util/trigger.h +++ b/tools/perf/util/trigger.h @@ -12,7 +12,7 @@ * States and transits: * * - * OFF--(on)--> READY --(hit)--> HIT + * OFF--> ON --> READY --(hit)--> HIT * ^ | * | (ready) * | | @@ -27,8 +27,9 @@ struct trigger { volatile enum { TRIGGER_ERROR = -2, TRIGGER_OFF = -1, - TRIGGER_READY = 0, - TRIGGER_HIT = 1, + TRIGGER_ON = 0, + TRIGGER_READY = 1, + TRIGGER_HIT = 2, } state; const char *name; }; @@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t) static inline void trigger_on(struct trigger *t) { TRIGGER_WARN_ONCE(t, TRIGGER_OFF); - t->state = TRIGGER_READY; + t->state = TRIGGER_ON; } static inline void trigger_ready(struct trigger *t) diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 44ef9eba5a7a..6c645eb77d42 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -178,6 +178,55 @@ void idr_get_next_test(int base) idr_destroy(&idr); } +int idr_u32_cb(int id, void *ptr, void *data) +{ + BUG_ON(id < 0); + BUG_ON(ptr != DUMMY_PTR); + return 0; +} + +void idr_u32_test1(struct idr *idr, u32 handle) +{ + static bool warned = false; + u32 id = handle; + int sid = 0; + void *ptr; + + BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL)); + BUG_ON(id != handle); + BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL) != -ENOSPC); + BUG_ON(id != handle); + if (!warned && id > INT_MAX) + printk("vvv Ignore these warnings\n"); + ptr = idr_get_next(idr, &sid); + if (id > INT_MAX) { + BUG_ON(ptr != NULL); + BUG_ON(sid != 0); + } else { + BUG_ON(ptr != DUMMY_PTR); + BUG_ON(sid != id); + } + idr_for_each(idr, idr_u32_cb, NULL); + if (!warned && id > INT_MAX) { + printk("^^^ Warnings over\n"); + warned = true; + } + BUG_ON(idr_remove(idr, id) != DUMMY_PTR); + BUG_ON(!idr_is_empty(idr)); +} + +void idr_u32_test(int base) +{ + DEFINE_IDR(idr); + idr_init_base(&idr, base); + idr_u32_test1(&idr, 10); + idr_u32_test1(&idr, 0x7fffffff); + idr_u32_test1(&idr, 0x80000000); + idr_u32_test1(&idr, 0x80000001); + idr_u32_test1(&idr, 0xffe00000); + idr_u32_test1(&idr, 0xffffffff); +} + void idr_checks(void) { unsigned long i; @@ -248,6 +297,9 @@ void idr_checks(void) idr_get_next_test(0); idr_get_next_test(1); idr_get_next_test(4); + idr_u32_test(4); + idr_u32_test(1); + idr_u32_test(0); } /* diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 6903ccf35595..44a0d1ad4408 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -29,7 +29,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) { struct radix_tree_node *node; - if (flags & __GFP_NOWARN) + if (!(flags & __GFP_DIRECT_RECLAIM)) return NULL; pthread_mutex_lock(&cachep->lock); @@ -73,10 +73,17 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) void *kmalloc(size_t size, gfp_t gfp) { - void *ret = malloc(size); + void *ret; + + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return NULL; + + ret = malloc(size); uatomic_inc(&nr_allocated); if (kmalloc_verbose) printf("Allocating %p from malloc\n", ret); + if (gfp & __GFP_ZERO) + memset(ret, 0, size); return ret; } diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/radix-tree/linux/compiler_types.h diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index e9fff59dfd8a..e3201ccf54c3 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -11,6 +11,7 @@ #define __GFP_IO 0x40u #define __GFP_FS 0x80u #define __GFP_NOWARN 0x200u +#define __GFP_ZERO 0x8000u #define __GFP_ATOMIC 0x80000u #define __GFP_ACCOUNT 0x100000u #define __GFP_DIRECT_RECLAIM 0x400000u diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h index 979baeec7e70..a037def0dec6 100644 --- a/tools/testing/radix-tree/linux/slab.h +++ b/tools/testing/radix-tree/linux/slab.h @@ -3,6 +3,7 @@ #define SLAB_H #include <linux/types.h> +#include <linux/gfp.h> #define SLAB_HWCACHE_ALIGN 1 #define SLAB_PANIC 2 @@ -11,6 +12,11 @@ void *kmalloc(size_t size, gfp_t); void kfree(void *); +static inline void *kzalloc(size_t size, gfp_t gfp) +{ + return kmalloc(size, gfp | __GFP_ZERO); +} + void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); void kmem_cache_free(struct kmem_cache *cachep, void *objp); diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 1a7492268993..f6304d2be90c 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -11,11 +11,11 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ - #SUBDIR test prog name should be in the form: SUBDIR_test.sh + #SUBDIR test prog name should be in the form: SUBDIR_test.sh \ TEST=$$DIR"_test.sh"; \ - if [ -e $$DIR/$$TEST ]; then - rsync -a $$DIR/$$TEST $$BUILD_TARGET/; - fi + if [ -e $$DIR/$$TEST ]; then \ + rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \ + fi \ done override define RUN_TESTS diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c73592fa3d41..437c0b1c9d21 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -11163,6 +11163,64 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, + { + "xadd/w check unaligned stack", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "misaligned stack access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned map", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = REJECT, + .errstr = "misaligned value access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned pkt", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 99), + BPF_JMP_IMM(BPF_JA, 0, 0, 6), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_XADD stores into R2 packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc new file mode 100644 index 000000000000..5ba73035e1d9 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -0,0 +1,46 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Kprobe event string type argument + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events + +case `uname -m` in +x86_64) + ARG2=%si + OFFS=8 +;; +i[3456]86) + ARG2=%cx + OFFS=4 +;; +aarch64) + ARG2=%x1 + OFFS=8 +;; +arm*) + ARG2=%r1 + OFFS=4 +;; +*) + echo "Please implement other architecture here" + exit_untested +esac + +: "Test get argument (1)" +echo "p:testprobe create_trace_kprobe arg1=+0(+0(${ARG2})):string" > kprobe_events +echo 1 > events/kprobes/testprobe/enable +! echo test >> kprobe_events +tail -n 1 trace | grep -qe "testprobe.* arg1=\"test\"" + +echo 0 > events/kprobes/testprobe/enable +: "Test get argument (2)" +echo "p:testprobe create_trace_kprobe arg1=+0(+0(${ARG2})):string arg2=+0(+${OFFS}(${ARG2})):string" > kprobe_events +echo 1 > events/kprobes/testprobe/enable +! echo test1 test2 >> kprobe_events +tail -n 1 trace | grep -qe "testprobe.* arg1=\"test1\" arg2=\"test2\"" + +echo 0 > events/enable +echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc new file mode 100644 index 000000000000..231bcd2c4eb5 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -0,0 +1,97 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Kprobe event argument syntax + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue + +echo 0 > events/enable +echo > kprobe_events + +PROBEFUNC="vfs_read" +GOODREG= +BADREG= +GOODSYM="_sdata" +if ! grep -qw ${GOODSYM} /proc/kallsyms ; then + GOODSYM=$PROBEFUNC +fi +BADSYM="deaqswdefr" +SYMADDR=0x`grep -w ${GOODSYM} /proc/kallsyms | cut -f 1 -d " "` +GOODTYPE="x16" +BADTYPE="y16" + +case `uname -m` in +x86_64|i[3456]86) + GOODREG=%ax + BADREG=%ex +;; +aarch64) + GOODREG=%x0 + BADREG=%ax +;; +arm*) + GOODREG=%r0 + BADREG=%ax +;; +esac + +test_goodarg() # Good-args +{ + while [ "$1" ]; do + echo "p ${PROBEFUNC} $1" > kprobe_events + shift 1 + done; +} + +test_badarg() # Bad-args +{ + while [ "$1" ]; do + ! echo "p ${PROBEFUNC} $1" > kprobe_events + shift 1 + done; +} + +echo > kprobe_events + +: "Register access" +test_goodarg ${GOODREG} +test_badarg ${BADREG} + +: "Symbol access" +test_goodarg "@${GOODSYM}" "@${SYMADDR}" "@${GOODSYM}+10" "@${GOODSYM}-10" +test_badarg "@" "@${BADSYM}" "@${GOODSYM}*10" "@${GOODSYM}/10" \ + "@${GOODSYM}%10" "@${GOODSYM}&10" "@${GOODSYM}|10" + +: "Stack access" +test_goodarg "\$stack" "\$stack0" "\$stack1" +test_badarg "\$stackp" "\$stack0+10" "\$stack1-10" + +: "Retval access" +echo "r ${PROBEFUNC} \$retval" > kprobe_events +! echo "p ${PROBEFUNC} \$retval" > kprobe_events + +: "Comm access" +test_goodarg "\$comm" + +: "Indirect memory access" +test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \ + "+0(\$stack1)" "+10(@${GOODSYM}-10)" "+0(+10(+20(\$stack)))" +test_badarg "+(${GOODREG})" "(${GOODREG}+10)" "-(${GOODREG})" "(${GOODREG})" \ + "+10(\$comm)" "+0(${GOODREG})+10" + +: "Name assignment" +test_goodarg "varname=${GOODREG}" +test_badarg "varname=varname2=${GOODREG}" + +: "Type syntax" +test_goodarg "${GOODREG}:${GOODTYPE}" +test_badarg "${GOODREG}::${GOODTYPE}" "${GOODREG}:${BADTYPE}" \ + "${GOODTYPE}:${GOODREG}" + +: "Combination check" + +test_goodarg "\$comm:string" "+0(\$stack):string" +test_badarg "\$comm:x64" "\$stack:string" "${GOODREG}:string" + +echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc new file mode 100644 index 000000000000..4fda01a08da4 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc @@ -0,0 +1,43 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Kprobe events - probe points + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +TARGET_FUNC=create_trace_kprobe + +dec_addr() { # hexaddr + printf "%d" "0x"`echo $1 | tail -c 8` +} + +set_offs() { # prev target next + A1=`dec_addr $1` + A2=`dec_addr $2` + A3=`dec_addr $3` + TARGET="0x$2" # an address + PREV=`expr $A1 - $A2` # offset to previous symbol + NEXT=+`expr $A3 - $A2` # offset to next symbol + OVERFLOW=+`printf "0x%x" ${PREV}` # overflow offset to previous symbol +} + +# We have to decode symbol addresses to get correct offsets. +# If the offset is not an instruction boundary, it cause -EILSEQ. +set_offs `grep -A1 -B1 ${TARGET_FUNC} /proc/kallsyms | cut -f 1 -d " " | xargs` + +UINT_TEST=no +# printf "%x" -1 returns (unsigned long)-1. +if [ `printf "%x" -1 | wc -c` != 9 ]; then + UINT_TEST=yes +fi + +echo 0 > events/enable +echo > kprobe_events +echo "p:testprobe ${TARGET_FUNC}" > kprobe_events +echo "p:testprobe ${TARGET}" > kprobe_events +echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events +! echo "p:testprobe ${TARGET_FUNC}${PREV}" > kprobe_events +if [ "${UINT_TEST}" = yes ]; then +! echo "p:testprobe ${TARGET_FUNC}${OVERFLOW}" > kprobe_events +fi +echo > kprobe_events +clear_trace diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index cea4adcd42b8..a63e8453984d 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -12,9 +12,9 @@ all: BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ - if [ -e $$DIR/$(TEST_PROGS) ]; then - rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; - fi + if [ -e $$DIR/$(TEST_PROGS) ]; then \ + rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ + fi \ done override define RUN_TESTS diff --git a/tools/testing/selftests/memfd/config b/tools/testing/selftests/memfd/config new file mode 100644 index 000000000000..835c7f4dadcd --- /dev/null +++ b/tools/testing/selftests/memfd/config @@ -0,0 +1 @@ +CONFIG_FUSE_FS=m diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile index 86636d207adf..686da510f989 100644 --- a/tools/testing/selftests/memory-hotplug/Makefile +++ b/tools/testing/selftests/memory-hotplug/Makefile @@ -4,8 +4,9 @@ all: include ../lib.mk TEST_PROGS := mem-on-off-test.sh -override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" -override EMIT_TESTS := echo "$(RUN_TESTS)" +override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]" + +override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))" run_full_test: @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]" diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c index 35ade7406dcd..3ae77ba93208 100644 --- a/tools/testing/selftests/powerpc/mm/subpage_prot.c +++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c @@ -135,6 +135,16 @@ static int run_test(void *addr, unsigned long size) return 0; } +static int syscall_available(void) +{ + int rc; + + errno = 0; + rc = syscall(__NR_subpage_prot, 0, 0, 0); + + return rc == 0 || (errno != ENOENT && errno != ENOSYS); +} + int test_anon(void) { unsigned long align; @@ -145,6 +155,8 @@ int test_anon(void) void *mallocblock; unsigned long mallocsize; + SKIP_IF(!syscall_available()); + if (getpagesize() != 0x10000) { fprintf(stderr, "Kernel page size must be 64K!\n"); return 1; @@ -180,6 +192,8 @@ int test_file(void) off_t filesize; int fd; + SKIP_IF(!syscall_available()); + fd = open(file_name, O_RDWR); if (fd == -1) { perror("failed to open file"); diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index a23453943ad2..5c72ff978f27 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -16,7 +16,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include $(OUTPUT)/tm-tmspr: CFLAGS += -pthread $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64 -$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o +$(OUTPUT)/tm-resched-dscr: ../pmu/lib.c $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64 diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c index 5d92c23ee6cb..179d592f0073 100644 --- a/tools/testing/selftests/powerpc/tm/tm-trap.c +++ b/tools/testing/selftests/powerpc/tm/tm-trap.c @@ -255,6 +255,8 @@ int tm_trap_test(void) struct sigaction trap_sa; + SKIP_IF(!have_htm()); + trap_sa.sa_flags = SA_SIGINFO; trap_sa.sa_sigaction = trap_signal_handler; sigaction(SIGTRAP, &trap_sa, NULL); diff --git a/tools/testing/selftests/pstore/config b/tools/testing/selftests/pstore/config index 6a8e5a9bfc10..d148f9f89fb6 100644 --- a/tools/testing/selftests/pstore/config +++ b/tools/testing/selftests/pstore/config @@ -2,3 +2,4 @@ CONFIG_MISC_FILESYSTEMS=y CONFIG_PSTORE=y CONFIG_PSTORE_PMSG=y CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=m diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index b3c8ba3cb668..d0121a8a3523 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -30,7 +30,7 @@ $(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS) $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS) $(OBJS): $(OUTPUT)/%.o: %.c - $(CC) -c $^ -o $@ + $(CC) -c $^ -o $@ $(CFLAGS) $(TESTS): $(OUTPUT)/%.o: %.c $(CC) -c $^ -o $@ diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json index e34075059c26..90bba48c3f07 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -315,7 +315,7 @@ "cmdUnderTest": "$TC actions ls action skbmod", "expExitCode": "0", "verifyCmd": "$TC actions get action skbmod index 4", - "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031", + "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x31", "matchCount": "1", "teardown": [ "$TC actions flush action skbmod" diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 3d5a62ff7d31..f5d7a7851e21 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +include ../lib.mk + ifndef CROSS_COMPILE CFLAGS := -std=gnu99 CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector @@ -6,16 +8,14 @@ ifeq ($(CONFIG_X86_32),y) LDLIBS += -lgcc_s endif -TEST_PROGS := vdso_test vdso_standalone_test_x86 +TEST_PROGS := $(OUTPUT)/vdso_test $(OUTPUT)/vdso_standalone_test_x86 all: $(TEST_PROGS) -vdso_test: parse_vdso.c vdso_test.c -vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c +$(OUTPUT)/vdso_test: parse_vdso.c vdso_test.c +$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \ vdso_standalone_test_x86.c parse_vdso.c \ - -o vdso_standalone_test_x86 + -o $@ -include ../lib.mk -clean: - rm -fr $(TEST_PROGS) +EXTRA_CLEAN := $(TEST_PROGS) endif diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 63c94d776e89..342c7bc9dc8c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -11,3 +11,4 @@ mlock-intersect-test mlock-random-test virtual_address_range gup_benchmark +va_128TBswitch diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index d2561895a021..22d564673830 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -2,25 +2,33 @@ # SPDX-License-Identifier: GPL-2.0 #please run as root -#we need 256M, below is the size in kB -needmem=262144 mnt=./huge exitcode=0 -#get pagesize and freepages from /proc/meminfo +#get huge pagesize and freepages from /proc/meminfo while read name size unit; do if [ "$name" = "HugePages_Free:" ]; then freepgs=$size fi if [ "$name" = "Hugepagesize:" ]; then - pgsize=$size + hpgsize_KB=$size fi done < /proc/meminfo +# Simple hugetlbfs tests have a hardcoded minimum requirement of +# huge pages totaling 256MB (262144KB) in size. The userfaultfd +# hugetlb test requires a minimum of 2 * nr_cpus huge pages. Take +# both of these requirements into account and attempt to increase +# number of huge pages available. +nr_cpus=$(nproc) +hpgsize_MB=$((hpgsize_KB / 1024)) +half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128)) +needmem_KB=$((half_ufd_size_MB * 2 * 1024)) + #set proper nr_hugepages -if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then +if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` - needpgs=`expr $needmem / $pgsize` + needpgs=$((needmem_KB / hpgsize_KB)) tries=2 while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do lackpgs=$(( $needpgs - $freepgs )) @@ -107,8 +115,9 @@ fi echo "---------------------------" echo "running userfaultfd_hugetlb" echo "---------------------------" -# 256MB total huge pages == 128MB src and 128MB dst -./userfaultfd hugetlb 128 32 $mnt/ufd_test_file +# Test requires source and destination huge pages. Size of source +# (half_ufd_size_MB) is passed as argument to test. +./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c index 361466a2eaef..ade443a88421 100644 --- a/tools/testing/selftests/x86/entry_from_vm86.c +++ b/tools/testing/selftests/x86/entry_from_vm86.c @@ -95,6 +95,10 @@ asm ( "int3\n\t" "vmcode_int80:\n\t" "int $0x80\n\t" + "vmcode_popf_hlt:\n\t" + "push %ax\n\t" + "popf\n\t" + "hlt\n\t" "vmcode_umip:\n\t" /* addressing via displacements */ "smsw (2052)\n\t" @@ -124,8 +128,8 @@ asm ( extern unsigned char vmcode[], end_vmcode[]; extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[], - vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_umip[], - vmcode_umip_str[], vmcode_umip_sldt[]; + vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_popf_hlt[], + vmcode_umip[], vmcode_umip_str[], vmcode_umip_sldt[]; /* Returns false if the test was skipped. */ static bool do_test(struct vm86plus_struct *v86, unsigned long eip, @@ -175,7 +179,7 @@ static bool do_test(struct vm86plus_struct *v86, unsigned long eip, (VM86_TYPE(ret) == rettype && VM86_ARG(ret) == retarg)) { printf("[OK]\tReturned correctly\n"); } else { - printf("[FAIL]\tIncorrect return reason\n"); + printf("[FAIL]\tIncorrect return reason (started at eip = 0x%lx, ended at eip = 0x%lx)\n", eip, v86->regs.eip); nerrs++; } @@ -264,6 +268,9 @@ int main(void) v86.regs.ds = load_addr / 16; v86.regs.es = load_addr / 16; + /* Use the end of the page as our stack. */ + v86.regs.esp = 4096; + assert((v86.regs.cs & 3) == 0); /* Looks like RPL = 0 */ /* #BR -- should deliver SIG??? */ @@ -295,6 +302,23 @@ int main(void) v86.regs.eflags &= ~X86_EFLAGS_IF; do_test(&v86, vmcode_sti - vmcode, VM86_STI, 0, "STI with VIP set"); + /* POPF with VIP set but IF clear: should not trap */ + v86.regs.eflags = X86_EFLAGS_VIP; + v86.regs.eax = 0; + do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP set and IF clear"); + + /* POPF with VIP set and IF set: should trap */ + v86.regs.eflags = X86_EFLAGS_VIP; + v86.regs.eax = X86_EFLAGS_IF; + do_test(&v86, vmcode_popf_hlt - vmcode, VM86_STI, 0, "POPF with VIP and IF set"); + + /* POPF with VIP clear and IF set: should not trap */ + v86.regs.eflags = 0; + v86.regs.eax = X86_EFLAGS_IF; + do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP clear and IF set"); + + v86.regs.eflags = 0; + /* INT3 -- should cause #BP */ do_test(&v86, vmcode_int3 - vmcode, VM86_TRAP, 3, "INT3"); @@ -318,7 +342,7 @@ int main(void) clearhandler(SIGSEGV); /* Make sure nothing explodes if we fork. */ - if (fork() > 0) + if (fork() == 0) return 0; return (nerrs == 0 ? 0 : 1); diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c index 1ae1c5a7392e..6f22238f3217 100644 --- a/tools/testing/selftests/x86/ptrace_syscall.c +++ b/tools/testing/selftests/x86/ptrace_syscall.c @@ -183,8 +183,10 @@ static void test_ptrace_syscall_restart(void) if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0) err(1, "PTRACE_TRACEME"); + pid_t pid = getpid(), tid = syscall(SYS_gettid); + printf("\tChild will make one syscall\n"); - raise(SIGSTOP); + syscall(SYS_tgkill, pid, tid, SIGSTOP); syscall(SYS_gettid, 10, 11, 12, 13, 14, 15); _exit(0); @@ -301,9 +303,11 @@ static void test_restart_under_ptrace(void) if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0) err(1, "PTRACE_TRACEME"); + pid_t pid = getpid(), tid = syscall(SYS_gettid); + printf("\tChild will take a nap until signaled\n"); setsigign(SIGUSR1, SA_RESTART); - raise(SIGSTOP); + syscall(SYS_tgkill, pid, tid, SIGSTOP); syscall(SYS_pause, 0, 0, 0, 0, 0, 0); _exit(0); diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index be81621446f0..0b4f1cc2291c 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) num_vsyscall_traps++; } -static int test_native_vsyscall(void) +static int test_emulation(void) { time_t tmp; bool is_native; @@ -458,7 +458,7 @@ static int test_native_vsyscall(void) if (!vtime) return 0; - printf("[RUN]\tchecking for native vsyscall\n"); + printf("[RUN]\tchecking that vsyscalls are emulated\n"); sethandler(SIGTRAP, sigtrap, 0); set_eflags(get_eflags() | X86_EFLAGS_TF); vtime(&tmp); @@ -474,11 +474,12 @@ static int test_native_vsyscall(void) */ is_native = (num_vsyscall_traps > 1); - printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "FAIL" : "OK"), (is_native ? "native" : "emulated"), (int)num_vsyscall_traps); - return 0; + return is_native; } #endif @@ -498,7 +499,7 @@ int main(int argc, char **argv) nerrs += test_vsys_r(); #ifdef __x86_64__ - nerrs += test_native_vsyscall(); + nerrs += test_emulation(); #endif return nerrs ? 1 : 0; diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 70268c0bec79..282389eb204f 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -36,6 +36,8 @@ static struct timecounter *timecounter; static unsigned int host_vtimer_irq; static u32 host_vtimer_irq_flags; +static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); + static const struct kvm_irq_level default_ptimer_irq = { .irq = 30, .level = 1, @@ -56,6 +58,12 @@ u64 kvm_phys_timer_read(void) return timecounter->cc->read(timecounter->cc); } +static inline bool userspace_irqchip(struct kvm *kvm) +{ + return static_branch_unlikely(&userspace_irqchip_in_use) && + unlikely(!irqchip_in_kernel(kvm)); +} + static void soft_timer_start(struct hrtimer *hrt, u64 ns) { hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns), @@ -69,25 +77,6 @@ static void soft_timer_cancel(struct hrtimer *hrt, struct work_struct *work) cancel_work_sync(work); } -static void kvm_vtimer_update_mask_user(struct kvm_vcpu *vcpu) -{ - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - - /* - * When using a userspace irqchip with the architected timers, we must - * prevent continuously exiting from the guest, and therefore mask the - * physical interrupt by disabling it on the host interrupt controller - * when the virtual level is high, such that the guest can make - * forward progress. Once we detect the output level being - * de-asserted, we unmask the interrupt again so that we exit from the - * guest when the timer fires. - */ - if (vtimer->irq.level) - disable_percpu_irq(host_vtimer_irq); - else - enable_percpu_irq(host_vtimer_irq, 0); -} - static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; @@ -106,9 +95,9 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) if (kvm_timer_should_fire(vtimer)) kvm_timer_update_irq(vcpu, true, vtimer); - if (static_branch_unlikely(&userspace_irqchip_in_use) && - unlikely(!irqchip_in_kernel(vcpu->kvm))) - kvm_vtimer_update_mask_user(vcpu); + if (userspace_irqchip(vcpu->kvm) && + !static_branch_unlikely(&has_gic_active_state)) + disable_percpu_irq(host_vtimer_irq); return IRQ_HANDLED; } @@ -290,8 +279,7 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level); - if (!static_branch_unlikely(&userspace_irqchip_in_use) || - likely(irqchip_in_kernel(vcpu->kvm))) { + if (!userspace_irqchip(vcpu->kvm)) { ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level, @@ -350,12 +338,6 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) phys_timer_emulate(vcpu); } -static void __timer_snapshot_state(struct arch_timer_context *timer) -{ - timer->cnt_ctl = read_sysreg_el0(cntv_ctl); - timer->cnt_cval = read_sysreg_el0(cntv_cval); -} - static void vtimer_save_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -367,8 +349,10 @@ static void vtimer_save_state(struct kvm_vcpu *vcpu) if (!vtimer->loaded) goto out; - if (timer->enabled) - __timer_snapshot_state(vtimer); + if (timer->enabled) { + vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); + vtimer->cnt_cval = read_sysreg_el0(cntv_cval); + } /* Disable the virtual timer */ write_sysreg_el0(0, cntv_ctl); @@ -460,23 +444,43 @@ static void set_cntvoff(u64 cntvoff) kvm_call_hyp(__kvm_timer_set_cntvoff, low, high); } -static void kvm_timer_vcpu_load_vgic(struct kvm_vcpu *vcpu) +static inline void set_vtimer_irq_phys_active(struct kvm_vcpu *vcpu, bool active) +{ + int r; + r = irq_set_irqchip_state(host_vtimer_irq, IRQCHIP_STATE_ACTIVE, active); + WARN_ON(r); +} + +static void kvm_timer_vcpu_load_gic(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); bool phys_active; - int ret; - - phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); - ret = irq_set_irqchip_state(host_vtimer_irq, - IRQCHIP_STATE_ACTIVE, - phys_active); - WARN_ON(ret); + if (irqchip_in_kernel(vcpu->kvm)) + phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); + else + phys_active = vtimer->irq.level; + set_vtimer_irq_phys_active(vcpu, phys_active); } -static void kvm_timer_vcpu_load_user(struct kvm_vcpu *vcpu) +static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) { - kvm_vtimer_update_mask_user(vcpu); + struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); + + /* + * When using a userspace irqchip with the architected timers and a + * host interrupt controller that doesn't support an active state, we + * must still prevent continuously exiting from the guest, and + * therefore mask the physical interrupt by disabling it on the host + * interrupt controller when the virtual level is high, such that the + * guest can make forward progress. Once we detect the output level + * being de-asserted, we unmask the interrupt again so that we exit + * from the guest when the timer fires. + */ + if (vtimer->irq.level) + disable_percpu_irq(host_vtimer_irq); + else + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) @@ -487,10 +491,10 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) if (unlikely(!timer->enabled)) return; - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) - kvm_timer_vcpu_load_user(vcpu); + if (static_branch_likely(&has_gic_active_state)) + kvm_timer_vcpu_load_gic(vcpu); else - kvm_timer_vcpu_load_vgic(vcpu); + kvm_timer_vcpu_load_nogic(vcpu); set_cntvoff(vtimer->cntvoff); @@ -555,22 +559,29 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { - __timer_snapshot_state(vtimer); - if (!kvm_timer_should_fire(vtimer)) { - kvm_timer_update_irq(vcpu, false, vtimer); - kvm_vtimer_update_mask_user(vcpu); - } + if (!kvm_timer_should_fire(vtimer)) { + kvm_timer_update_irq(vcpu, false, vtimer); + if (static_branch_likely(&has_gic_active_state)) + set_vtimer_irq_phys_active(vcpu, false); + else + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } } void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) { - unmask_vtimer_irq_user(vcpu); + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + + if (unlikely(!timer->enabled)) + return; + + if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + unmask_vtimer_irq_user(vcpu); } int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) { + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); @@ -584,6 +595,9 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) ptimer->cnt_ctl = 0; kvm_timer_update_state(vcpu); + if (timer->enabled && irqchip_in_kernel(vcpu->kvm)) + kvm_vgic_reset_mapped_irq(vcpu, vtimer->irq.irq); + return 0; } @@ -753,9 +767,11 @@ int kvm_timer_hyp_init(bool has_gic) kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); goto out_free_irq; } + + static_branch_enable(&has_gic_active_state); } - kvm_info("virtual timer IRQ%d\n", host_vtimer_irq); + kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq); cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, "kvm/arm/timer:starting", kvm_timer_starting_cpu, diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 86941f6181bb..53572304843b 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -384,14 +384,11 @@ static void vcpu_power_off(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - vcpu_load(vcpu); - if (vcpu->arch.power_off) mp_state->mp_state = KVM_MP_STATE_STOPPED; else mp_state->mp_state = KVM_MP_STATE_RUNNABLE; - vcpu_put(vcpu); return 0; } @@ -400,8 +397,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, { int ret = 0; - vcpu_load(vcpu); - switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: vcpu->arch.power_off = false; @@ -413,7 +408,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, ret = -EINVAL; } - vcpu_put(vcpu); return ret; } @@ -1036,8 +1030,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_device_attr attr; long r; - vcpu_load(vcpu); - switch (ioctl) { case KVM_ARM_VCPU_INIT: { struct kvm_vcpu_init init; @@ -1114,7 +1106,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; } - vcpu_put(vcpu); return r; } diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c index f5c3d6d7019e..b89ce5432214 100644 --- a/virt/kvm/arm/hyp/vgic-v3-sr.c +++ b/virt/kvm/arm/hyp/vgic-v3-sr.c @@ -215,7 +215,8 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) * are now visible to the system register interface. */ if (!cpu_if->vgic_sre) { - dsb(st); + dsb(sy); + isb(); cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); } diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index ec62d1cccab7..b960acdd0c05 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1810,9 +1810,9 @@ int kvm_mmu_init(void) */ BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); - kvm_info("IDMAP page: %lx\n", hyp_idmap_start); - kvm_info("HYP VA range: %lx:%lx\n", - kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL)); + kvm_debug("IDMAP page: %lx\n", hyp_idmap_start); + kvm_debug("HYP VA range: %lx:%lx\n", + kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL)); if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) && hyp_idmap_start < kern_hyp_va(~0UL) && diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 83d82bd7dc4e..dbe99d635c80 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -113,9 +113,12 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + unsigned long flags; + spin_lock_irqsave(&irq->irq_lock, flags); if (irq_is_pending(irq)) value |= (1U << i); + spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index c32d7b93ffd1..29556f71b691 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -37,6 +37,13 @@ void vgic_v2_init_lrs(void) vgic_v2_write_lr(i, 0); } +void vgic_v2_set_npie(struct kvm_vcpu *vcpu) +{ + struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; + + cpuif->vgic_hcr |= GICH_HCR_NPIE; +} + void vgic_v2_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2; @@ -64,7 +71,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) int lr; unsigned long flags; - cpuif->vgic_hcr &= ~GICH_HCR_UIE; + cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE); for (lr = 0; lr < vgic_cpu->used_lrs; lr++) { u32 val = cpuif->vgic_lr[lr]; @@ -410,7 +417,7 @@ int vgic_v2_probe(const struct gic_kvm_info *info) kvm_vgic_global_state.type = VGIC_V2; kvm_vgic_global_state.max_gic_vcpus = VGIC_V2_MAX_CPUS; - kvm_info("vgic-v2@%llx\n", info->vctrl.start); + kvm_debug("vgic-v2@%llx\n", info->vctrl.start); return 0; out: diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 6b329414e57a..0ff2006f3781 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -26,6 +26,13 @@ static bool group1_trap; static bool common_trap; static bool gicv4_enable; +void vgic_v3_set_npie(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; + + cpuif->vgic_hcr |= ICH_HCR_NPIE; +} + void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; @@ -47,7 +54,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) int lr; unsigned long flags; - cpuif->vgic_hcr &= ~ICH_HCR_UIE; + cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE); for (lr = 0; lr < vgic_cpu->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index c7c5ef190afa..8201899126f6 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -495,6 +495,32 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, return ret; } +/** + * kvm_vgic_reset_mapped_irq - Reset a mapped IRQ + * @vcpu: The VCPU pointer + * @vintid: The INTID of the interrupt + * + * Reset the active and pending states of a mapped interrupt. Kernel + * subsystems injecting mapped interrupts should reset their interrupt lines + * when we are doing a reset of the VM. + */ +void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid) +{ + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + unsigned long flags; + + if (!irq->hw) + goto out; + + spin_lock_irqsave(&irq->irq_lock, flags); + irq->active = false; + irq->pending_latch = false; + irq->line_level = false; + spin_unlock_irqrestore(&irq->irq_lock, flags); +out: + vgic_put_irq(vcpu->kvm, irq); +} + int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) { struct vgic_irq *irq; @@ -684,22 +710,37 @@ static inline void vgic_set_underflow(struct kvm_vcpu *vcpu) vgic_v3_set_underflow(vcpu); } +static inline void vgic_set_npie(struct kvm_vcpu *vcpu) +{ + if (kvm_vgic_global_state.type == VGIC_V2) + vgic_v2_set_npie(vcpu); + else + vgic_v3_set_npie(vcpu); +} + /* Requires the ap_list_lock to be held. */ -static int compute_ap_list_depth(struct kvm_vcpu *vcpu) +static int compute_ap_list_depth(struct kvm_vcpu *vcpu, + bool *multi_sgi) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; int count = 0; + *multi_sgi = false; + DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock)); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { spin_lock(&irq->irq_lock); /* GICv2 SGIs can count for more than one... */ - if (vgic_irq_is_sgi(irq->intid) && irq->source) - count += hweight8(irq->source); - else + if (vgic_irq_is_sgi(irq->intid) && irq->source) { + int w = hweight8(irq->source); + + count += w; + *multi_sgi |= (w > 1); + } else { count++; + } spin_unlock(&irq->irq_lock); } return count; @@ -710,28 +751,43 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq; - int count = 0; + int count; + bool npie = false; + bool multi_sgi; + u8 prio = 0xff; DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock)); - if (compute_ap_list_depth(vcpu) > kvm_vgic_global_state.nr_lr) + count = compute_ap_list_depth(vcpu, &multi_sgi); + if (count > kvm_vgic_global_state.nr_lr || multi_sgi) vgic_sort_ap_list(vcpu); + count = 0; + list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { spin_lock(&irq->irq_lock); - if (unlikely(vgic_target_oracle(irq) != vcpu)) - goto next; - /* - * If we get an SGI with multiple sources, try to get - * them in all at once. + * If we have multi-SGIs in the pipeline, we need to + * guarantee that they are all seen before any IRQ of + * lower priority. In that case, we need to filter out + * these interrupts by exiting early. This is easy as + * the AP list has been sorted already. */ - do { + if (multi_sgi && irq->priority > prio) { + spin_unlock(&irq->irq_lock); + break; + } + + if (likely(vgic_target_oracle(irq) == vcpu)) { vgic_populate_lr(vcpu, irq, count++); - } while (irq->source && count < kvm_vgic_global_state.nr_lr); -next: + if (irq->source) { + npie = true; + prio = irq->priority; + } + } + spin_unlock(&irq->irq_lock); if (count == kvm_vgic_global_state.nr_lr) { @@ -742,6 +798,9 @@ next: } } + if (npie) + vgic_set_npie(vcpu); + vcpu->arch.vgic_cpu.used_lrs = count; /* Nuke remaining LRs */ diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 12c37b89f7a3..f5b8519e5546 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -96,6 +96,7 @@ /* we only support 64 kB translation table page size */ #define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16) +/* Requires the irq_lock to be held by the caller. */ static inline bool irq_is_pending(struct vgic_irq *irq) { if (irq->config == VGIC_CONFIG_EDGE) @@ -159,6 +160,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu); void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); void vgic_v2_clear_lr(struct kvm_vcpu *vcpu, int lr); void vgic_v2_set_underflow(struct kvm_vcpu *vcpu); +void vgic_v2_set_npie(struct kvm_vcpu *vcpu); int vgic_v2_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_v2_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, int offset, u32 *val); @@ -188,6 +190,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu); void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr); void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr); void vgic_v3_set_underflow(struct kvm_vcpu *vcpu); +void vgic_v3_set_npie(struct kvm_vcpu *vcpu); void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); void vgic_v3_enable(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4501e658e8d6..65dea3ffef68 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -969,8 +969,7 @@ int __kvm_set_memory_region(struct kvm *kvm, /* Check for overlaps */ r = -EEXIST; kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { - if ((slot->id >= KVM_USER_MEM_SLOTS) || - (slot->id == id)) + if (slot->id == id) continue; if (!((base_gfn + npages <= slot->base_gfn) || (base_gfn >= slot->base_gfn + slot->npages))) |