diff options
448 files changed, 5563 insertions, 2798 deletions
@@ -21,6 +21,7 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrew Morton <akpm@linux-foundation.org> Andrew Vasquez <andrew.vasquez@qlogic.com> Andy Adamson <andros@citi.umich.edu> +Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com> Archit Taneja <archit@ti.com> Arnaud Patard <arnaud.patard@rtp-net.org> Arnd Bergmann <arnd@arndb.de> diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt index 7b57fc087088..49585b6e1ea2 100644 --- a/Documentation/Intel-IOMMU.txt +++ b/Documentation/Intel-IOMMU.txt @@ -3,7 +3,7 @@ Linux IOMMU Support The architecture spec can be obtained from the below location. -http://www.intel.com/technology/virtualization/ +http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/vt-directed-io-spec.pdf This guide gives a quick cheat sheet for some basic understanding. diff --git a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt index 451fef26b4df..10587bdadbbe 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt +++ b/Documentation/devicetree/bindings/net/brcm,bcmgenet.txt @@ -68,7 +68,7 @@ ethernet@f0b60000 { phy1: ethernet-phy@1 { max-speed = <1000>; reg = <0x1>; - compatible = "brcm,28nm-gphy", "ethernet-phy-ieee802.3-c22"; + compatible = "ethernet-phy-ieee802.3-c22"; }; }; }; @@ -115,7 +115,7 @@ ethernet@f0ba0000 { phy0: ethernet-phy@0 { max-speed = <1000>; reg = <0x0>; - compatible = "brcm,bcm53125", "ethernet-phy-ieee802.3-c22"; + compatible = "ethernet-phy-ieee802.3-c22"; }; }; }; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt index 80411b2f0490..ecacfa44b1eb 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt @@ -4,8 +4,6 @@ Required properties: - compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2". "hisilicon,hns-dsaf-v1" is for hip05. "hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612. -- dsa-name: dsa fabric name who provide this interface. - should be "dsafX", X is the dsaf id. - mode: dsa fabric mode string. only support one of dsaf modes like these: "2port-64vf", "6port-16rss", @@ -26,9 +24,8 @@ Required properties: Example: -dsa: dsa@c7000000 { +dsaf0: dsa@c7000000 { compatible = "hisilicon,hns-dsaf-v1"; - dsa_name = "dsaf0"; mode = "6port-16rss"; interrupt-parent = <&mbigen_dsa>; reg = <0x0 0xC0000000 0x0 0x420000 diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt index 41d19be7011e..e6a9d1c30878 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt @@ -4,8 +4,9 @@ Required properties: - compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2". "hisilicon,hns-nic-v1" is for hip05. "hisilicon,hns-nic-v2" is for Hi1610 and Hi1612. -- ae-name: accelerator name who provides this interface, - is simply a name referring to the name of name in the accelerator node. +- ae-handle: accelerator engine handle for hns, + specifies a reference to the associating hardware driver node. + see Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt - port-id: is the index of port provided by DSAF (the accelerator). DSAF can connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They are called debug ports. @@ -41,7 +42,7 @@ Example: ethernet@0{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <0>; local-mac-address = [a2 14 e4 4b 56 76]; }; diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt index aeea50c84e92..d0cb8693963b 100644 --- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt +++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt @@ -6,12 +6,17 @@ Required properties: - interrupts: interrupt for the device - phy: See ethernet.txt file in the same directory. - phy-mode: See ethernet.txt file in the same directory -- clocks: a pointer to the reference clock for this device. +- clocks: List of clocks for this device. At least one clock is + mandatory for the core clock. If several clocks are given, then the + clock-names property must be used to identify them. Optional properties: - tx-csum-limit: maximum mtu supported by port that allow TX checksum. Value is presented in bytes. If not used, by default 1600B is set for "marvell,armada-370-neta" and 9800B for others. +- clock-names: List of names corresponding to clocks property; shall be + "core" for core clock and "bus" for the optional bus clock. + Example: diff --git a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt index 79384113c2b0..694987d3c17a 100644 --- a/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt +++ b/Documentation/devicetree/bindings/net/mdio-mux-gpio.txt @@ -38,7 +38,6 @@ Example : phy11: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -48,7 +47,6 @@ Example : }; phy12: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -58,7 +56,6 @@ Example : }; phy13: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -68,7 +65,6 @@ Example : }; phy14: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -85,7 +81,6 @@ Example : phy21: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -95,7 +90,6 @@ Example : }; phy22: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -105,7 +99,6 @@ Example : }; phy23: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -115,7 +108,6 @@ Example : }; phy24: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, diff --git a/Documentation/devicetree/bindings/net/mdio-mux.txt b/Documentation/devicetree/bindings/net/mdio-mux.txt index f65606f8d632..491f5bd55203 100644 --- a/Documentation/devicetree/bindings/net/mdio-mux.txt +++ b/Documentation/devicetree/bindings/net/mdio-mux.txt @@ -47,7 +47,6 @@ Example : phy11: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -57,7 +56,6 @@ Example : }; phy12: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -67,7 +65,6 @@ Example : }; phy13: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -77,7 +74,6 @@ Example : }; phy14: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -94,7 +90,6 @@ Example : phy21: ethernet-phy@1 { reg = <1>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -104,7 +99,6 @@ Example : }; phy22: ethernet-phy@2 { reg = <2>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -114,7 +108,6 @@ Example : }; phy23: ethernet-phy@3 { reg = <3>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, @@ -124,7 +117,6 @@ Example : }; phy24: ethernet-phy@4 { reg = <4>; - compatible = "marvell,88e1149r"; marvell,reg-init = <3 0x10 0 0x5777>, <3 0x11 0 0x00aa>, <3 0x12 0 0x4105>, diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt index 525e1658f2da..bc1c3c8bf8fa 100644 --- a/Documentation/devicetree/bindings/net/phy.txt +++ b/Documentation/devicetree/bindings/net/phy.txt @@ -17,8 +17,7 @@ Optional Properties: "ethernet-phy-ieee802.3-c22" or "ethernet-phy-ieee802.3-c45" for PHYs that implement IEEE802.3 clause 22 or IEEE802.3 clause 45 specifications. If neither of these are specified, the default is to - assume clause 22. The compatible list may also contain other - elements. + assume clause 22. If the phy's identifier is known then the list may contain an entry of the form: "ethernet-phy-idAAAA.BBBB" where @@ -28,6 +27,9 @@ Optional Properties: 4 hex digits. This is the chip vendor OUI bits 19:24, followed by 10 bits of a vendor specific ID. + The compatible list should not contain other values than those + listed here. + - max-speed: Maximum PHY supported speed (10, 100, 1000...) - broken-turn-around: If set, indicates the PHY device does not correctly diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ceb44a095a27..73b36d7c7b0d 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -594,7 +594,7 @@ tcp_fastopen - INTEGER tcp_syn_retries - INTEGER Number of times initial SYNs for an active TCP connection attempt - will be retransmitted. Should not be higher than 255. Default value + will be retransmitted. Should not be higher than 127. Default value is 6, which corresponds to 63seconds till the last retransmission with the current initial RTO of 1second. With this the final timeout for an active TCP connection attempt will happen after 127seconds. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 053f613fc9a9..07e4cdf02407 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3025,7 +3025,7 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq), which is the maximum number of possibly pending cpu-local interrupts. -4.90 KVM_SMI +4.96 KVM_SMI Capability: KVM_CAP_X86_SMM Architectures: x86 diff --git a/MAINTAINERS b/MAINTAINERS index 973336739ae5..c245e42cf1d5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10189,7 +10189,7 @@ F: drivers/net/ethernet/natsemi/sonic.* SONICS SILICON BACKPLANE DRIVER (SSB) M: Michael Buesch <m@bues.ch> -L: netdev@vger.kernel.org +L: linux-wireless@vger.kernel.org S: Maintained F: drivers/ssb/ F: include/linux/ssb/ @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 4c23a68a0917..7a6a58ef8aaf 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -106,6 +106,15 @@ ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) endif +# -fstack-protector-strong triggers protection checks in this code, +# but it is being used too early to link to meaningful stack_chk logic. +nossp_flags := $(call cc-option, -fno-stack-protector) +CFLAGS_atags_to_fdt.o := $(nossp_flags) +CFLAGS_fdt.o := $(nossp_flags) +CFLAGS_fdt_ro.o := $(nossp_flags) +CFLAGS_fdt_rw.o := $(nossp_flags) +CFLAGS_fdt_wip.o := $(nossp_flags) + ccflags-y := -fpic -mno-single-pic-base -fno-builtin -I$(obj) asflags-y := -DZIMAGE diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h index ede692ffa32e..5dd2528e9e45 100644 --- a/arch/arm/include/uapi/asm/unistd.h +++ b/arch/arm/include/uapi/asm/unistd.h @@ -417,6 +417,7 @@ #define __NR_userfaultfd (__NR_SYSCALL_BASE+388) #define __NR_membarrier (__NR_SYSCALL_BASE+389) #define __NR_mlock2 (__NR_SYSCALL_BASE+390) +#define __NR_copy_file_range (__NR_SYSCALL_BASE+391) /* * The following SWIs are ARM private. diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index ac368bb068d1..dfc7cd6851ad 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -400,6 +400,7 @@ CALL(sys_userfaultfd) CALL(sys_membarrier) CALL(sys_mlock2) + CALL(sys_copy_file_range) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index cd822d8454c0..307237cfe728 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -27,6 +27,8 @@ $(warning LSE atomics not supported by binutils) endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) KBUILD_AFLAGS += $(lseinstr) ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi index da7b6e613257..933cba359918 100644 --- a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi @@ -23,9 +23,8 @@ soc0: soc@000000000 { }; }; - dsa: dsa@c7000000 { + dsaf0: dsa@c7000000 { compatible = "hisilicon,hns-dsaf-v1"; - dsa_name = "dsaf0"; mode = "6port-16rss"; interrupt-parent = <&mbigen_dsa>; @@ -127,7 +126,7 @@ soc0: soc@000000000 { eth0: ethernet@0{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <0>; local-mac-address = [00 00 00 01 00 58]; status = "disabled"; @@ -135,14 +134,14 @@ soc0: soc@000000000 { }; eth1: ethernet@1{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <1>; status = "disabled"; dma-coherent; }; eth2: ethernet@2{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <2>; local-mac-address = [00 00 00 01 00 5a]; status = "disabled"; @@ -150,7 +149,7 @@ soc0: soc@000000000 { }; eth3: ethernet@3{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <3>; local-mac-address = [00 00 00 01 00 5b]; status = "disabled"; @@ -158,7 +157,7 @@ soc0: soc@000000000 { }; eth4: ethernet@4{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <4>; local-mac-address = [00 00 00 01 00 5c]; status = "disabled"; @@ -166,7 +165,7 @@ soc0: soc@000000000 { }; eth5: ethernet@5{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <5>; local-mac-address = [00 00 00 01 00 5d]; status = "disabled"; @@ -174,7 +173,7 @@ soc0: soc@000000000 { }; eth6: ethernet@6{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <6>; local-mac-address = [00 00 00 01 00 5e]; status = "disabled"; @@ -182,7 +181,7 @@ soc0: soc@000000000 { }; eth7: ethernet@7{ compatible = "hisilicon,hns-nic-v1"; - ae-name = "dsaf0"; + ae-handle = <&dsaf0>; port-id = <7>; local-mac-address = [00 00 00 01 00 5f]; status = "disabled"; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 18ca9fb9e65f..86581f793e39 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -16,7 +16,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y -CONFIG_MEMCG_KMEM=y CONFIG_CGROUP_HUGETLB=y # CONFIG_UTS_NS is not set # CONFIG_IPC_NS is not set @@ -37,15 +36,13 @@ CONFIG_ARCH_EXYNOS7=y CONFIG_ARCH_LAYERSCAPE=y CONFIG_ARCH_HISI=y CONFIG_ARCH_MEDIATEK=y +CONFIG_ARCH_QCOM=y CONFIG_ARCH_ROCKCHIP=y CONFIG_ARCH_SEATTLE=y CONFIG_ARCH_RENESAS=y CONFIG_ARCH_R8A7795=y CONFIG_ARCH_STRATIX10=y CONFIG_ARCH_TEGRA=y -CONFIG_ARCH_TEGRA_132_SOC=y -CONFIG_ARCH_TEGRA_210_SOC=y -CONFIG_ARCH_QCOM=y CONFIG_ARCH_SPRD=y CONFIG_ARCH_THUNDER=y CONFIG_ARCH_UNIPHIER=y @@ -54,14 +51,19 @@ CONFIG_ARCH_XGENE=y CONFIG_ARCH_ZYNQMP=y CONFIG_PCI=y CONFIG_PCI_MSI=y +CONFIG_PCI_IOV=y +CONFIG_PCI_RCAR_GEN2_PCIE=y CONFIG_PCI_HOST_GENERIC=y CONFIG_PCI_XGENE=y -CONFIG_SMP=y +CONFIG_PCI_LAYERSCAPE=y +CONFIG_PCI_HISI=y +CONFIG_PCIE_QCOM=y CONFIG_SCHED_MC=y CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_XEN=y CONFIG_CMDLINE="console=ttyAMA0" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y @@ -100,7 +102,11 @@ CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y CONFIG_TUN=y CONFIG_VIRTIO_NET=y +CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y +CONFIG_E1000E=y +CONFIG_IGB=y +CONFIG_IGBVF=y CONFIG_SKY2=y CONFIG_RAVB=y CONFIG_SMC91X=y @@ -117,25 +123,23 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y CONFIG_SERIAL_8250_MT6577=y CONFIG_SERIAL_8250_UNIPHIER=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y CONFIG_SERIAL_SAMSUNG=y -CONFIG_SERIAL_SAMSUNG_UARTS_4=y -CONFIG_SERIAL_SAMSUNG_UARTS=4 CONFIG_SERIAL_SAMSUNG_CONSOLE=y +CONFIG_SERIAL_TEGRA=y CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=11 CONFIG_SERIAL_SH_SCI_CONSOLE=y -CONFIG_SERIAL_TEGRA=y CONFIG_SERIAL_MSM=y CONFIG_SERIAL_MSM_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_XILINX_PS_UART=y CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y CONFIG_VIRTIO_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_I2C=y CONFIG_I2C_QUP=y +CONFIG_I2C_UNIPHIER_F=y CONFIG_I2C_RCAR=y CONFIG_SPI=y CONFIG_SPI_PL022=y @@ -176,8 +180,6 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_TEGRA=y CONFIG_MMC_SPI=y CONFIG_MMC_DW=y -CONFIG_MMC_DW_IDMAC=y -CONFIG_MMC_DW_PLTFM=y CONFIG_MMC_DW_EXYNOS=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y @@ -187,28 +189,33 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y CONFIG_LEDS_TRIGGER_CPU=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_EFI=y +CONFIG_RTC_DRV_PL031=y CONFIG_RTC_DRV_XGENE=y CONFIG_DMADEVICES=y -CONFIG_RCAR_DMAC=y CONFIG_QCOM_BAM_DMA=y CONFIG_TEGRA20_APB_DMA=y +CONFIG_RCAR_DMAC=y +CONFIG_VFIO=y +CONFIG_VFIO_PCI=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_MMIO=y +CONFIG_XEN_GNTDEV=y +CONFIG_XEN_GRANT_DEV_ALLOC=y CONFIG_COMMON_CLK_CS2000_CP=y CONFIG_COMMON_CLK_QCOM=y CONFIG_MSM_GCC_8916=y CONFIG_HWSPINLOCK_QCOM=y -# CONFIG_IOMMU_SUPPORT is not set +CONFIG_ARM_SMMU=y CONFIG_QCOM_SMEM=y CONFIG_QCOM_SMD=y CONFIG_QCOM_SMD_RPM=y +CONFIG_ARCH_TEGRA_132_SOC=y +CONFIG_ARCH_TEGRA_210_SOC=y +CONFIG_HISILICON_IRQ_MBIGEN=y CONFIG_PHY_XGENE=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -# CONFIG_EXT3_FS_XATTR is not set -CONFIG_EXT4_FS=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y @@ -239,6 +246,7 @@ CONFIG_LOCKUP_DETECTOR=y # CONFIG_FTRACE is not set CONFIG_MEMTEST=y CONFIG_SECURITY=y +CONFIG_CRYPTO_ECHAINIV=y CONFIG_CRYPTO_ANSI_CPRNG=y CONFIG_ARM64_CRYPTO=y CONFIG_CRYPTO_SHA1_ARM64_CE=y diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 2d545d7aa80b..bf464de33f52 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -67,11 +67,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -81,7 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) @@ -153,6 +153,7 @@ extern struct page *empty_zero_page; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -163,8 +164,6 @@ extern struct page *empty_zero_page; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) #define pte_valid_young(pte) \ @@ -278,13 +277,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - if (pte_valid_user(pte)) { - if (!pte_special(pte) && pte_exec(pte)) - __sync_icache_dcache(pte, addr); + if (pte_valid(pte)) { if (pte_sw_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; + if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) + __sync_icache_dcache(pte, addr); } /* diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ffe9c2b6431b..917d98108b3f 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -514,9 +514,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index bc2abb8b1599..999633bd7294 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -65,6 +65,16 @@ #ifdef CONFIG_EFI /* + * Prevent the symbol aliases below from being emitted into the kallsyms + * table, by forcing them to be absolute symbols (which are conveniently + * ignored by scripts/kallsyms) rather than section relative symbols. + * The distinction is only relevant for partial linking, and only for symbols + * that are defined within a section declaration (which is not the case for + * the definitions below) so the resulting values will be identical. + */ +#define KALLSYMS_HIDE(sym) ABSOLUTE(sym) + +/* * The EFI stub has its own symbol namespace prefixed by __efistub_, to * isolate it from the kernel proper. The following symbols are legally * accessed by the stub, so provide some aliases to make them accessible. @@ -73,25 +83,25 @@ * linked at. The routines below are all implemented in assembler in a * position independent manner */ -__efistub_memcmp = __pi_memcmp; -__efistub_memchr = __pi_memchr; -__efistub_memcpy = __pi_memcpy; -__efistub_memmove = __pi_memmove; -__efistub_memset = __pi_memset; -__efistub_strlen = __pi_strlen; -__efistub_strcmp = __pi_strcmp; -__efistub_strncmp = __pi_strncmp; -__efistub___flush_dcache_area = __pi___flush_dcache_area; +__efistub_memcmp = KALLSYMS_HIDE(__pi_memcmp); +__efistub_memchr = KALLSYMS_HIDE(__pi_memchr); +__efistub_memcpy = KALLSYMS_HIDE(__pi_memcpy); +__efistub_memmove = KALLSYMS_HIDE(__pi_memmove); +__efistub_memset = KALLSYMS_HIDE(__pi_memset); +__efistub_strlen = KALLSYMS_HIDE(__pi_strlen); +__efistub_strcmp = KALLSYMS_HIDE(__pi_strcmp); +__efistub_strncmp = KALLSYMS_HIDE(__pi_strncmp); +__efistub___flush_dcache_area = KALLSYMS_HIDE(__pi___flush_dcache_area); #ifdef CONFIG_KASAN -__efistub___memcpy = __pi_memcpy; -__efistub___memmove = __pi_memmove; -__efistub___memset = __pi_memset; +__efistub___memcpy = KALLSYMS_HIDE(__pi_memcpy); +__efistub___memmove = KALLSYMS_HIDE(__pi_memmove); +__efistub___memset = KALLSYMS_HIDE(__pi_memset); #endif -__efistub__text = _text; -__efistub__end = _end; -__efistub__edata = _edata; +__efistub__text = KALLSYMS_HIDE(_text); +__efistub__end = KALLSYMS_HIDE(_end); +__efistub__edata = KALLSYMS_HIDE(_edata); #endif diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 5a22a119a74c..0adbebbc2803 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -46,7 +46,7 @@ enum address_markers_idx { PCI_START_NR, PCI_END_NR, MODULES_START_NR, - MODUELS_END_NR, + MODULES_END_NR, KERNEL_SPACE_NR, }; diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index cf038c7d9fa9..cab7a5be40aa 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -120,6 +120,7 @@ static void __init cpu_set_ttbr1(unsigned long ttbr1) void __init kasan_init(void) { struct memblock_region *reg; + int i; /* * We are going to perform proper setup of shadow memory. @@ -155,6 +156,14 @@ void __init kasan_init(void) pfn_to_nid(virt_to_pfn(start))); } + /* + * KAsan may reuse the contents of kasan_zero_pte directly, so we + * should make sure that it maps the zero page read-only. + */ + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(&kasan_zero_pte[i], + pfn_pte(virt_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); + memset(kasan_zero_page, 0, PAGE_SIZE); cpu_set_ttbr1(__pa(swapper_pg_dir)); flush_tlb_all(); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309c5e..cf6240741134 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 146bd99a7532..e6a30e1268a8 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -84,3 +84,15 @@ b.lo 9998b dsb \domain .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index a3d867e723b4..c164d2cb35c0 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,7 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 - msr pmuserenr_el0, xzr // Disable PMU access from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -154,7 +154,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 - msr pmuserenr_el0, xzr // Disable PMU access from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * diff --git a/arch/mips/bcm63xx/nvram.c b/arch/mips/bcm63xx/nvram.c index 5f2bc1e10eae..05757aed016c 100644 --- a/arch/mips/bcm63xx/nvram.c +++ b/arch/mips/bcm63xx/nvram.c @@ -19,6 +19,8 @@ #include <bcm63xx_nvram.h> +#define BCM63XX_DEFAULT_PSI_SIZE 64 + static struct bcm963xx_nvram nvram; static int mac_addr_used; @@ -85,3 +87,12 @@ int bcm63xx_nvram_get_mac_address(u8 *mac) return 0; } EXPORT_SYMBOL(bcm63xx_nvram_get_mac_address); + +int bcm63xx_nvram_get_psi_size(void) +{ + if (nvram.psi_size > 0) + return nvram.psi_size; + + return BCM63XX_DEFAULT_PSI_SIZE; +} +EXPORT_SYMBOL(bcm63xx_nvram_get_psi_size); diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h index 4e0b6bc1165e..348df49dcc9f 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_nvram.h @@ -30,4 +30,6 @@ u8 *bcm63xx_nvram_get_name(void); */ int bcm63xx_nvram_get_mac_address(u8 *mac); +int bcm63xx_nvram_get_psi_size(void); + #endif /* BCM63XX_NVRAM_H */ diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 06f17e778c27..8d1c8162f0c1 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -50,7 +50,9 @@ * set of bits not changed in pmd_modify. */ #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ - _PAGE_ACCESSED | _PAGE_THP_HUGE) + _PAGE_ACCESSED | _PAGE_THP_HUGE | _PAGE_PTE | \ + _PAGE_SOFT_DIRTY) + #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/hash-64k.h> diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 8204b0c393aa..8d1c41d28318 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -223,7 +223,6 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) -#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 271fefbbe521..9d08d8cbed1a 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -38,8 +38,7 @@ #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS -#define KVM_USER_MEM_SLOTS 32 -#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS +#define KVM_USER_MEM_SLOTS 512 #ifdef CONFIG_KVM_MMIO #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 5654ece02c0d..3fa9df70aa20 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -383,3 +383,4 @@ SYSCALL(ni_syscall) SYSCALL(ni_syscall) SYSCALL(ni_syscall) SYSCALL(mlock2) +SYSCALL(copy_file_range) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 6a5ace5fa0c8..1f2594d45605 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 379 +#define NR_syscalls 380 #define __NR__exit __NR_exit diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 12a05652377a..940290d45b08 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -389,5 +389,6 @@ #define __NR_userfaultfd 364 #define __NR_membarrier 365 #define __NR_mlock2 378 +#define __NR_copy_file_range 379 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166c19..ca9e5371930e 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); + if (loc) - goto out; + return loc; - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index db475d41b57a..f28754c497e5 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -701,31 +701,3 @@ _GLOBAL(kexec_sequence) li r5,0 blr /* image->start(physid, image->start, 0); */ #endif /* CONFIG_KEXEC */ - -#ifdef CONFIG_MODULES -#if defined(_CALL_ELF) && _CALL_ELF == 2 - -#ifdef CONFIG_MODVERSIONS -.weak __crc_TOC. -.section "___kcrctab+TOC.","a" -.globl __kcrctab_TOC. -__kcrctab_TOC.: - .llong __crc_TOC. -#endif - -/* - * Export a fake .TOC. since both modpost and depmod will complain otherwise. - * Both modpost and depmod strip the leading . so we do the same here. - */ -.section "__ksymtab_strings","a" -__kstrtab_TOC.: - .asciz "TOC." - -.section "___ksymtab+TOC.","a" -/* This symbol name is important: it's used by modpost to find exported syms */ -.globl __ksymtab_TOC. -__ksymtab_TOC.: - .llong 0 /* .value */ - .llong __kstrtab_TOC. -#endif /* ELFv2 */ -#endif /* MODULES */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 59663af9315f..ac64ffdb52c8 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -326,7 +326,10 @@ static void dedotify_versions(struct modversion_info *vers, } } -/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */ +/* + * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC. + * seem to be defined (value set later). + */ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) { unsigned int i; @@ -334,8 +337,11 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) for (i = 1; i < numsyms; i++) { if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; - if (name[0] == '.') + if (name[0] == '.') { + if (strcmp(name+1, "TOC.") == 0) + syms[i].st_shndx = SHN_ABS; memmove(name, name+1, strlen(name)); + } } } } @@ -351,7 +357,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym); for (i = 1; i < numsyms; i++) { - if (syms[i].st_shndx == SHN_UNDEF + if (syms[i].st_shndx == SHN_ABS && strcmp(strtab + syms[i].st_name, "TOC.") == 0) return &syms[i]; } diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 774a253ca4e1..9bf7031a67ff 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -377,15 +377,12 @@ no_seg_found: static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb) { - struct kvmppc_vcpu_book3s *vcpu_book3s; u64 esid, esid_1t; int slb_nr; struct kvmppc_slb *slbe; dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb); - vcpu_book3s = to_book3s(vcpu); - esid = GET_ESID(rb); esid_1t = GET_ESID_1T(rb); slb_nr = rb & 0xfff; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index cff207b72c46..baeddb06811d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -833,6 +833,24 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->stat.sum_exits++; + /* + * This can happen if an interrupt occurs in the last stages + * of guest entry or the first stages of guest exit (i.e. after + * setting paca->kvm_hstate.in_guest to KVM_GUEST_MODE_GUEST_HV + * and before setting it to KVM_GUEST_MODE_HOST_HV). + * That can happen due to a bug, or due to a machine check + * occurring at just the wrong time. + */ + if (vcpu->arch.shregs.msr & MSR_HV) { + printk(KERN_EMERG "KVM trap in HV mode!\n"); + printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n", + vcpu->arch.trap, kvmppc_get_pc(vcpu), + vcpu->arch.shregs.msr); + kvmppc_dump_regs(vcpu); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->hw.hardware_exit_reason = vcpu->arch.trap; + return RESUME_HOST; + } run->exit_reason = KVM_EXIT_UNKNOWN; run->ready_for_interrupt_injection = 1; switch (vcpu->arch.trap) { diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..6ee26de9a1de 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) @@ -2404,6 +2404,8 @@ machine_check_realmode: * guest as machine check causing guest to crash. */ ld r11, VCPU_MSR(r9) + rldicl. r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */ + bne mc_cont /* if so, exit to host */ andi. r10, r11, MSR_RI /* check for unrecoverable exception */ beq 1f /* Deliver a machine check to guest */ ld r10, VCPU_PC(r9) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 22d94c3e6fc4..d0f0a514b04e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -560,12 +560,12 @@ subsys_initcall(add_system_ram_resources); */ int devmem_is_allowed(unsigned long pfn) { + if (page_is_rtas_user_buf(pfn)) + return 1; if (iomem_is_exclusive(PFN_PHYS(pfn))) return 0; if (!page_is_ram(pfn)) return 1; - if (page_is_rtas_user_buf(pfn)) - return 1; return 0; } #endif /* CONFIG_STRICT_DEVMEM */ diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index 7d5e295255b7..9958ba8bf0d2 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -816,7 +816,7 @@ static struct power_pmu power8_pmu = { .get_constraint = power8_get_constraint, .get_alternatives = power8_get_alternatives, .disable_pmc = power8_disable_pmc, - .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S, + .flags = PPMU_HAS_SIER | PPMU_ARCH_207S, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, .cache_events = &power8_cache_events, diff --git a/arch/s390/include/asm/irqflags.h b/arch/s390/include/asm/irqflags.h index 16aa0c779e07..595a275c36f8 100644 --- a/arch/s390/include/asm/irqflags.h +++ b/arch/s390/include/asm/irqflags.h @@ -8,6 +8,8 @@ #include <linux/types.h> +#define ARCH_IRQ_ENABLED (3UL << (BITS_PER_LONG - 8)) + /* store then OR system mask. */ #define __arch_local_irq_stosm(__or) \ ({ \ @@ -54,14 +56,17 @@ static inline notrace void arch_local_irq_enable(void) __arch_local_irq_stosm(0x03); } +/* This only restores external and I/O interrupt state */ static inline notrace void arch_local_irq_restore(unsigned long flags) { - __arch_local_irq_ssm(flags); + /* only disabled->disabled and disabled->enabled is valid */ + if (flags & ARCH_IRQ_ENABLED) + arch_local_irq_enable(); } static inline notrace bool arch_irqs_disabled_flags(unsigned long flags) { - return !(flags & (3UL << (BITS_PER_LONG - 8))); + return !(flags & ARCH_IRQ_ENABLED); } static inline notrace bool arch_irqs_disabled(void) diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 6742414dbd6f..8959ebb6d2c9 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -546,7 +546,6 @@ struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; unsigned int host_acrs[NUM_ACRS]; struct fpu host_fpregs; - struct fpu guest_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 1a9a98de5bde..69aa18be61af 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -8,10 +8,13 @@ #include <asm/pci_insn.h> /* I/O Map */ -#define ZPCI_IOMAP_MAX_ENTRIES 0x7fff -#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000ULL -#define ZPCI_IOMAP_ADDR_IDX_MASK 0x7fff000000000000ULL -#define ZPCI_IOMAP_ADDR_OFF_MASK 0x0000ffffffffffffULL +#define ZPCI_IOMAP_SHIFT 48 +#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL +#define ZPCI_IOMAP_ADDR_OFF_MASK ((1UL << ZPCI_IOMAP_SHIFT) - 1) +#define ZPCI_IOMAP_MAX_ENTRIES \ + ((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT)) +#define ZPCI_IOMAP_ADDR_IDX_MASK \ + (~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE) struct zpci_iomap_entry { u32 fh; @@ -21,8 +24,9 @@ struct zpci_iomap_entry { extern struct zpci_iomap_entry *zpci_iomap_start; +#define ZPCI_ADDR(idx) (ZPCI_IOMAP_ADDR_BASE | ((u64) idx << ZPCI_IOMAP_SHIFT)) #define ZPCI_IDX(addr) \ - (((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> 48) + (((__force u64) addr & ZPCI_IOMAP_ADDR_IDX_MASK) >> ZPCI_IOMAP_SHIFT) #define ZPCI_OFFSET(addr) \ ((__force u64) addr & ZPCI_IOMAP_ADDR_OFF_MASK) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index f16debf6a612..1c4fe129486d 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -166,14 +166,14 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS]; */ #define start_thread(regs, new_psw, new_stackp) do { \ regs->psw.mask = PSW_USER_BITS | PSW_MASK_EA | PSW_MASK_BA; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->psw.addr = new_psw; \ regs->gprs[15] = new_stackp; \ execve_tail(); \ } while (0) #define start_thread31(regs, new_psw, new_stackp) do { \ regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ - regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ + regs->psw.addr = new_psw; \ regs->gprs[15] = new_stackp; \ crst_table_downgrade(current->mm, 1UL << 31); \ execve_tail(); \ diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index f00cd35c8ac4..99bc456cc26a 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -149,7 +149,7 @@ static inline int test_pt_regs_flag(struct pt_regs *regs, int flag) #define arch_has_block_step() (1) #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0) -#define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN) +#define instruction_pointer(regs) ((regs)->psw.addr) #define user_stack_pointer(regs)((regs)->gprs[15]) #define profile_pc(regs) instruction_pointer(regs) @@ -161,7 +161,7 @@ static inline long regs_return_value(struct pt_regs *regs) static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { - regs->psw.addr = val | PSW_ADDR_AMODE; + regs->psw.addr = val; } int regs_query_register_offset(const char *name); @@ -171,7 +171,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { - return regs->gprs[15] & PSW_ADDR_INSN; + return regs->gprs[15]; } #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index 34ec202472c6..ab3aa6875a59 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -310,7 +310,8 @@ #define __NR_recvmsg 372 #define __NR_shutdown 373 #define __NR_mlock2 374 -#define NR_syscalls 375 +#define __NR_copy_file_range 375 +#define NR_syscalls 376 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index fac4eeddef91..ae2cda5eee5a 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -177,3 +177,4 @@ COMPAT_SYSCALL_WRAP3(getsockname, int, fd, struct sockaddr __user *, usockaddr, COMPAT_SYSCALL_WRAP3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len); COMPAT_SYSCALL_WRAP6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len); COMPAT_SYSCALL_WRAP3(mlock2, unsigned long, start, size_t, len, int, flags); +COMPAT_SYSCALL_WRAP6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index a92b39fd0e63..3986c9f62191 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -59,8 +59,6 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu) struct save_area *sa; sa = (void *) memblock_alloc(sizeof(*sa), 8); - if (!sa) - return NULL; if (is_boot_cpu) list_add(&sa->list, &dump_save_areas); else diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 6fca0e46464e..c890a5589e59 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1470,7 +1470,7 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view, except_str = "*"; else except_str = "-"; - caller = ((unsigned long) entry->caller) & PSW_ADDR_INSN; + caller = (unsigned long) entry->caller; rc += sprintf(out_buf, "%02i %011lld:%06lu %1u %1s %02i %p ", area, (long long)time_spec.tv_sec, time_spec.tv_nsec / 1000, level, except_str, diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index dc8e20473484..02bd02ff648b 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -34,22 +34,21 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) unsigned long addr; while (1) { - sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - addr = sf->gprs[8] & PSW_ADDR_INSN; + addr = sf->gprs[8]; printk("([<%016lx>] %pSR)\n", addr, (void *)addr); /* Follow the backchain. */ while (1) { low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - addr = sf->gprs[8] & PSW_ADDR_INSN; + addr = sf->gprs[8]; printk(" [<%016lx>] %pSR\n", addr, (void *)addr); } /* Zero backchain detected, check for interrupt frame. */ @@ -57,7 +56,7 @@ __show_trace(unsigned long sp, unsigned long low, unsigned long high) if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *) sp; - addr = regs->psw.addr & PSW_ADDR_INSN; + addr = regs->psw.addr; printk(" [<%016lx>] %pSR\n", addr, (void *)addr); low = sp; sp = regs->gprs[15]; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 20a5caf6d981..c55576bbaa1f 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -252,14 +252,14 @@ static void early_pgm_check_handler(void) unsigned long addr; addr = S390_lowcore.program_old_psw.addr; - fixup = search_exception_tables(addr & PSW_ADDR_INSN); + fixup = search_exception_tables(addr); if (!fixup) disabled_wait(0); /* Disable low address protection before storing into lowcore. */ __ctl_store(cr0, 0, 0); cr0_new = cr0 & ~(1UL << 28); __ctl_load(cr0_new, 0, 0); - S390_lowcore.program_old_psw.addr = extable_fixup(fixup)|PSW_ADDR_AMODE; + S390_lowcore.program_old_psw.addr = extable_fixup(fixup); __ctl_load(cr0, 0, 0); } @@ -268,9 +268,9 @@ static noinline __init void setup_lowcore_early(void) psw_t psw; psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; - psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_ext_handler; + psw.addr = (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; - psw.addr = PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + psw.addr = (unsigned long) s390_base_pgm_handler; S390_lowcore.program_new_psw = psw; s390_base_pgm_handler_fn = early_pgm_check_handler; } diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index e0eaf11134b4..0f7bfeba6da6 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -203,7 +203,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - ip = (ip & PSW_ADDR_INSN) - MCOUNT_INSN_SIZE; + ip -= MCOUNT_INSN_SIZE; trace.func = ip; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to. */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 0a5a6b661b93..f20abdb5630a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2057,12 +2057,12 @@ void s390_reset_system(void) /* Set new machine check handler */ S390_lowcore.mcck_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.mcck_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) s390_base_mcck_handler; + (unsigned long) s390_base_mcck_handler; /* Set new program check handler */ S390_lowcore.program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT; S390_lowcore.program_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler; + (unsigned long) s390_base_pgm_handler; /* * Clear subchannel ID and number to signal new kernel that no CCW or diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 389db56a2208..250f5972536a 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -226,7 +226,7 @@ static void enable_singlestep(struct kprobe_ctlblk *kcb, __ctl_load(per_kprobe, 9, 11); regs->psw.mask |= PSW_MASK_PER; regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); - regs->psw.addr = ip | PSW_ADDR_AMODE; + regs->psw.addr = ip; } NOKPROBE_SYMBOL(enable_singlestep); @@ -238,7 +238,7 @@ static void disable_singlestep(struct kprobe_ctlblk *kcb, __ctl_load(kcb->kprobe_saved_ctl, 9, 11); regs->psw.mask &= ~PSW_MASK_PER; regs->psw.mask |= kcb->kprobe_saved_imask; - regs->psw.addr = ip | PSW_ADDR_AMODE; + regs->psw.addr = ip; } NOKPROBE_SYMBOL(disable_singlestep); @@ -310,7 +310,7 @@ static int kprobe_handler(struct pt_regs *regs) */ preempt_disable(); kcb = get_kprobe_ctlblk(); - p = get_kprobe((void *)((regs->psw.addr & PSW_ADDR_INSN) - 2)); + p = get_kprobe((void *)(regs->psw.addr - 2)); if (p) { if (kprobe_running()) { @@ -460,7 +460,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) break; } - regs->psw.addr = orig_ret_address | PSW_ADDR_AMODE; + regs->psw.addr = orig_ret_address; pop_kprobe(get_kprobe_ctlblk()); kretprobe_hash_unlock(current, &flags); @@ -490,7 +490,7 @@ NOKPROBE_SYMBOL(trampoline_probe_handler); static void resume_execution(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - unsigned long ip = regs->psw.addr & PSW_ADDR_INSN; + unsigned long ip = regs->psw.addr; int fixup = probe_get_fixup_type(p->ainsn.insn); /* Check if the kprobes location is an enabled ftrace caller */ @@ -605,9 +605,9 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr) * In case the user-specified fault handler returned * zero, try to fix up. */ - entry = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + entry = search_exception_tables(regs->psw.addr); if (entry) { - regs->psw.addr = extable_fixup(entry) | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(entry); return 1; } @@ -683,7 +683,7 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs)); /* setup return addr to the jprobe handler routine */ - regs->psw.addr = (unsigned long) jp->entry | PSW_ADDR_AMODE; + regs->psw.addr = (unsigned long) jp->entry; regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); /* r15 is the stack pointer */ diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 61595c1f0a0f..cfcba2dd9bb5 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -74,7 +74,7 @@ static unsigned long guest_is_user_mode(struct pt_regs *regs) static unsigned long instruction_pointer_guest(struct pt_regs *regs) { - return sie_block(regs)->gpsw.addr & PSW_ADDR_INSN; + return sie_block(regs)->gpsw.addr; } unsigned long perf_instruction_pointer(struct pt_regs *regs) @@ -231,29 +231,27 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry, struct pt_regs *regs; while (1) { - sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN); + perf_callchain_store(entry, sf->gprs[8]); /* Follow the backchain. */ while (1) { low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; - perf_callchain_store(entry, - sf->gprs[8] & PSW_ADDR_INSN); + perf_callchain_store(entry, sf->gprs[8]); } /* Zero backchain detected, check for interrupt frame. */ sp = (unsigned long) (sf + 1); if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *) sp; - perf_callchain_store(entry, sf->gprs[8] & PSW_ADDR_INSN); + perf_callchain_store(entry, sf->gprs[8]); low = sp; sp = regs->gprs[15]; } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 114ee8b96f17..2bba7df4ac51 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -56,10 +56,10 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return 0; low = task_stack_page(tsk); high = (struct stack_frame *) task_pt_regs(tsk); - sf = (struct stack_frame *) (tsk->thread.ksp & PSW_ADDR_INSN); + sf = (struct stack_frame *) tsk->thread.ksp; if (sf <= low || sf > high) return 0; - sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN); + sf = (struct stack_frame *) sf->back_chain; if (sf <= low || sf > high) return 0; return sf->gprs[8]; @@ -154,7 +154,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, memset(&frame->childregs, 0, sizeof(struct pt_regs)); frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; - frame->childregs.psw.addr = PSW_ADDR_AMODE | + frame->childregs.psw.addr = (unsigned long) kernel_thread_starter; frame->childregs.gprs[9] = new_stackp; /* function */ frame->childregs.gprs[10] = arg; @@ -220,14 +220,14 @@ unsigned long get_wchan(struct task_struct *p) return 0; low = task_stack_page(p); high = (struct stack_frame *) task_pt_regs(p); - sf = (struct stack_frame *) (p->thread.ksp & PSW_ADDR_INSN); + sf = (struct stack_frame *) p->thread.ksp; if (sf <= low || sf > high) return 0; for (count = 0; count < 16; count++) { - sf = (struct stack_frame *) (sf->back_chain & PSW_ADDR_INSN); + sf = (struct stack_frame *) sf->back_chain; if (sf <= low || sf > high) return 0; - return_address = sf->gprs[8] & PSW_ADDR_INSN; + return_address = sf->gprs[8]; if (!in_sched_functions(return_address)) return return_address; } diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 01c37b36caf9..49b1c13bf6c9 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -84,7 +84,7 @@ void update_cr_regs(struct task_struct *task) if (test_tsk_thread_flag(task, TIF_UPROBE_SINGLESTEP)) new.control |= PER_EVENT_IFETCH; new.start = 0; - new.end = PSW_ADDR_INSN; + new.end = -1UL; } /* Take care of the PER enablement bit in the PSW. */ @@ -148,7 +148,7 @@ static inline unsigned long __peek_user_per(struct task_struct *child, else if (addr == (addr_t) &dummy->cr11) /* End address of the active per set. */ return test_thread_flag(TIF_SINGLE_STEP) ? - PSW_ADDR_INSN : child->thread.per_user.end; + -1UL : child->thread.per_user.end; else if (addr == (addr_t) &dummy->bits) /* Single-step bit. */ return test_thread_flag(TIF_SINGLE_STEP) ? @@ -495,8 +495,6 @@ long arch_ptrace(struct task_struct *child, long request, } return 0; default: - /* Removing high order bit from addr (only for 31 bit). */ - addr &= PSW_ADDR_INSN; return ptrace_request(child, request, addr, data); } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c6878fbbcf13..9220db5c996a 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -301,25 +301,21 @@ static void __init setup_lowcore(void) BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * 4096); lc = __alloc_bootmem_low(LC_PAGES * PAGE_SIZE, LC_PAGES * PAGE_SIZE, 0); lc->restart_psw.mask = PSW_KERNEL_BITS; - lc->restart_psw.addr = - PSW_ADDR_AMODE | (unsigned long) restart_int_handler; + lc->restart_psw.addr = (unsigned long) restart_int_handler; lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; - lc->external_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) ext_int_handler; + lc->external_new_psw.addr = (unsigned long) ext_int_handler; lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; - lc->svc_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) system_call; + lc->svc_new_psw.addr = (unsigned long) system_call; lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; - lc->program_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) pgm_check_handler; + lc->program_new_psw.addr = (unsigned long) pgm_check_handler; lc->mcck_new_psw.mask = PSW_KERNEL_BITS; - lc->mcck_new_psw.addr = - PSW_ADDR_AMODE | (unsigned long) mcck_int_handler; + lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler; lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_MCHECK; - lc->io_new_psw.addr = PSW_ADDR_AMODE | (unsigned long) io_int_handler; + lc->io_new_psw.addr = (unsigned long) io_int_handler; lc->clock_comparator = -1ULL; lc->kernel_stack = ((unsigned long) &init_thread_union) + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 028cc46cb82a..d82562cf0a0e 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -331,13 +331,13 @@ static int setup_frame(int sig, struct k_sigaction *ka, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ka->sa.sa_flags & SA_RESTORER) { - restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE; + restorer = (unsigned long) ka->sa.sa_restorer; } else { /* Signal frame without vector registers are short ! */ __u16 __user *svc = (void __user *) frame + frame_size - 2; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc)) return -EFAULT; - restorer = (unsigned long) svc | PSW_ADDR_AMODE; + restorer = (unsigned long) svc; } /* Set up registers for signal handler */ @@ -347,7 +347,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (unsigned long) ka->sa.sa_handler | PSW_ADDR_AMODE; + regs->psw.addr = (unsigned long) ka->sa.sa_handler; regs->gprs[2] = sig; regs->gprs[3] = (unsigned long) &frame->sc; @@ -394,13 +394,12 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, /* Set up to return from userspace. If provided, use a stub already in userspace. */ if (ksig->ka.sa.sa_flags & SA_RESTORER) { - restorer = (unsigned long) - ksig->ka.sa.sa_restorer | PSW_ADDR_AMODE; + restorer = (unsigned long) ksig->ka.sa.sa_restorer; } else { __u16 __user *svc = &frame->svc_insn; if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn, svc)) return -EFAULT; - restorer = (unsigned long) svc | PSW_ADDR_AMODE; + restorer = (unsigned long) svc; } /* Create siginfo on the signal stack */ @@ -426,7 +425,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, regs->psw.mask = PSW_MASK_EA | PSW_MASK_BA | (PSW_USER_BITS & PSW_MASK_ASC) | (regs->psw.mask & ~PSW_MASK_ASC); - regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler | PSW_ADDR_AMODE; + regs->psw.addr = (unsigned long) ksig->ka.sa.sa_handler; regs->gprs[2] = ksig->sig; regs->gprs[3] = (unsigned long) &frame->info; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index a13468b9a913..3c65a8eae34d 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -623,8 +623,6 @@ void __init smp_save_dump_cpus(void) return; /* Allocate a page as dumping area for the store status sigps */ page = memblock_alloc_base(PAGE_SIZE, PAGE_SIZE, 1UL << 31); - if (!page) - panic("could not allocate memory for save area\n"); /* Set multi-threading state to the previous system. */ pcpu_set_smt(sclp.mtid_prev); boot_cpu_addr = stap(); diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 1785cd82253c..5acba3cb7220 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -21,12 +21,11 @@ static unsigned long save_context_stack(struct stack_trace *trace, unsigned long addr; while(1) { - sp &= PSW_ADDR_INSN; if (sp < low || sp > high) return sp; sf = (struct stack_frame *)sp; while(1) { - addr = sf->gprs[8] & PSW_ADDR_INSN; + addr = sf->gprs[8]; if (!trace->skip) trace->entries[trace->nr_entries++] = addr; else @@ -34,7 +33,7 @@ static unsigned long save_context_stack(struct stack_trace *trace, if (trace->nr_entries >= trace->max_entries) return sp; low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) @@ -46,7 +45,7 @@ static unsigned long save_context_stack(struct stack_trace *trace, if (sp <= low || sp > high - sizeof(*regs)) return sp; regs = (struct pt_regs *)sp; - addr = regs->psw.addr & PSW_ADDR_INSN; + addr = regs->psw.addr; if (savesched || !in_sched_functions(addr)) { if (!trace->skip) trace->entries[trace->nr_entries++] = addr; @@ -65,7 +64,7 @@ void save_stack_trace(struct stack_trace *trace) register unsigned long sp asm ("15"); unsigned long orig_sp, new_sp; - orig_sp = sp & PSW_ADDR_INSN; + orig_sp = sp; new_sp = save_context_stack(trace, orig_sp, S390_lowcore.panic_stack - PAGE_SIZE, S390_lowcore.panic_stack, 1); @@ -86,7 +85,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { unsigned long sp, low, high; - sp = tsk->thread.ksp & PSW_ADDR_INSN; + sp = tsk->thread.ksp; low = (unsigned long) task_stack_page(tsk); high = (unsigned long) task_pt_regs(tsk); save_context_stack(trace, sp, low, high, 0); diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 5378c3ea1b98..293d8b98fd52 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -383,3 +383,4 @@ SYSCALL(sys_recvfrom,compat_sys_recvfrom) SYSCALL(sys_recvmsg,compat_sys_recvmsg) SYSCALL(sys_shutdown,sys_shutdown) SYSCALL(sys_mlock2,compat_sys_mlock2) +SYSCALL(sys_copy_file_range,compat_sys_copy_file_range) /* 375 */ diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index d69d648759c9..017eb03daee2 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -32,8 +32,7 @@ static inline void __user *get_trap_ip(struct pt_regs *regs) address = *(unsigned long *)(current->thread.trap_tdb + 24); else address = regs->psw.addr; - return (void __user *) - ((address - (regs->int_code >> 16)) & PSW_ADDR_INSN); + return (void __user *) (address - (regs->int_code >> 16)); } static inline void report_user_fault(struct pt_regs *regs, int signr) @@ -46,7 +45,7 @@ static inline void report_user_fault(struct pt_regs *regs, int signr) return; printk("User process fault: interruption code %04x ilc:%d ", regs->int_code & 0xffff, regs->int_code >> 17); - print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN); + print_vma_addr("in ", regs->psw.addr); printk("\n"); show_regs(regs); } @@ -69,13 +68,13 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) report_user_fault(regs, si_signo); } else { const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + fixup = search_exception_tables(regs->psw.addr); if (fixup) - regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(fixup); else { enum bug_trap_type btt; - btt = report_bug(regs->psw.addr & PSW_ADDR_INSN, regs); + btt = report_bug(regs->psw.addr, regs); if (btt == BUG_TRAP_TYPE_WARN) return; die(regs, str); diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 5fce52cf0e57..5ea5af3c7db7 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -29,6 +29,7 @@ config KVM select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING select SRCU + select KVM_VFIO ---help--- Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index b3b553469650..d42fa38c2429 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -7,7 +7,7 @@ # as published by the Free Software Foundation. KVM := ../../../virt/kvm -common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o +common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o ccflags-y := -Ivirt/kvm -Iarch/s390/kvm diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c index 47518a324d75..d697312ce9ee 100644 --- a/arch/s390/kvm/guestdbg.c +++ b/arch/s390/kvm/guestdbg.c @@ -116,7 +116,7 @@ static void enable_all_hw_wp(struct kvm_vcpu *vcpu) if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) { *cr9 &= ~PER_CONTROL_ALTERATION; *cr10 = 0; - *cr11 = PSW_ADDR_INSN; + *cr11 = -1UL; } else { *cr9 &= ~PER_CONTROL_ALTERATION; *cr9 |= PER_EVENT_STORE; @@ -159,7 +159,7 @@ void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->gcr[0] &= ~0x800ul; vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH; vcpu->arch.sie_block->gcr[10] = 0; - vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN; + vcpu->arch.sie_block->gcr[11] = -1UL; } if (guestdbg_hw_bp_enabled(vcpu)) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 835d60bedb54..4af21c771f9b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1423,44 +1423,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) return 0; } -/* - * Backs up the current FP/VX register save area on a particular - * destination. Used to switch between different register save - * areas. - */ -static inline void save_fpu_to(struct fpu *dst) -{ - dst->fpc = current->thread.fpu.fpc; - dst->regs = current->thread.fpu.regs; -} - -/* - * Switches the FP/VX register save area from which to lazy - * restore register contents. - */ -static inline void load_fpu_from(struct fpu *from) -{ - current->thread.fpu.fpc = from->fpc; - current->thread.fpu.regs = from->regs; -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Save host register state */ save_fpu_regs(); - save_fpu_to(&vcpu->arch.host_fpregs); - - if (test_kvm_facility(vcpu->kvm, 129)) { - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - /* - * Use the register save area in the SIE-control block - * for register restore and save in kvm_arch_vcpu_put() - */ - current->thread.fpu.vxrs = - (__vector128 *)&vcpu->run->s.regs.vrs; - } else - load_fpu_from(&vcpu->arch.guest_fpregs); + vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; + vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; + /* Depending on MACHINE_HAS_VX, data stored to vrs either + * has vector register or floating point register format. + */ + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + current->thread.fpu.fpc = vcpu->run->s.regs.fpc; if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; @@ -1476,19 +1450,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); + /* Save guest register state */ save_fpu_regs(); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - if (test_kvm_facility(vcpu->kvm, 129)) - /* - * kvm_arch_vcpu_load() set up the register save area to - * the &vcpu->run->s.regs.vrs and, thus, the vector registers - * are already saved. Only the floating-point control must be - * copied. - */ - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - else - save_fpu_to(&vcpu->arch.guest_fpregs); - load_fpu_from(&vcpu->arch.host_fpregs); + /* Restore host register state */ + current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; + current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); @@ -1506,8 +1474,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); vcpu->arch.sie_block->gcr[0] = 0xE0UL; vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; - vcpu->arch.guest_fpregs.fpc = 0; - asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + /* make sure the new fpc will be lazily loaded */ + save_fpu_regs(); + current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; @@ -1648,17 +1617,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - /* - * Allocate a save area for floating-point registers. If the vector - * extension is available, register contents are saved in the SIE - * control block. The allocated save area is still required in - * particular places, for example, in kvm_s390_vcpu_store_status(). - */ - vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS, - GFP_KERNEL); - if (!vcpu->arch.guest_fpregs.fprs) - goto out_free_sie_block; - rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) goto out_free_sie_block; @@ -1879,19 +1837,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + /* make sure the new values will be lazily loaded */ + save_fpu_regs(); if (test_fp_ctl(fpu->fpc)) return -EINVAL; - memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - vcpu->arch.guest_fpregs.fpc = fpu->fpc; - save_fpu_regs(); - load_fpu_from(&vcpu->arch.guest_fpregs); + current->thread.fpu.fpc = fpu->fpc; + if (MACHINE_HAS_VX) + convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs); + else + memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs)); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); - fpu->fpc = vcpu->arch.guest_fpregs.fpc; + /* make sure we have the latest values */ + save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs); + else + memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs)); + fpu->fpc = current->thread.fpu.fpc; return 0; } @@ -2396,6 +2362,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) { unsigned char archmode = 1; + freg_t fprs[NUM_FPRS]; unsigned int px; u64 clkcomp; int rc; @@ -2411,8 +2378,16 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) gpa = px; } else gpa -= __LC_FPREGS_SAVE_AREA; - rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, - vcpu->arch.guest_fpregs.fprs, 128); + + /* manually convert vector registers if necessary */ + if (MACHINE_HAS_VX) { + convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + fprs, 128); + } else { + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + vcpu->run->s.regs.vrs, 128); + } rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA, @@ -2420,7 +2395,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA, &px, 4); rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA, - &vcpu->arch.guest_fpregs.fpc, 4); + &vcpu->run->s.regs.fpc, 4); rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA, &vcpu->arch.sie_block->todpr, 4); rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA, @@ -2443,19 +2418,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * it into the save area */ save_fpu_regs(); - if (test_kvm_facility(vcpu->kvm, 129)) { - /* - * If the vector extension is available, the vector registers - * which overlaps with floating-point registers are saved in - * the SIE-control block. Hence, extract the floating-point - * registers and the FPC value and store them in the - * guest_fpregs structure. - */ - vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc; - convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs, - current->thread.fpu.vxrs); - } else - save_fpu_to(&vcpu->arch.guest_fpregs); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 1b903f6ad54a..791a4146052c 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -228,7 +228,7 @@ static inline void report_user_fault(struct pt_regs *regs, long signr) return; printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d ", regs->int_code & 0xffff, regs->int_code >> 17); - print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN); + print_vma_addr(KERN_CONT "in ", regs->psw.addr); printk(KERN_CONT "\n"); printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n", regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long); @@ -256,9 +256,9 @@ static noinline void do_no_context(struct pt_regs *regs) const struct exception_table_entry *fixup; /* Are we prepared to handle this kernel fault? */ - fixup = search_exception_tables(regs->psw.addr & PSW_ADDR_INSN); + fixup = search_exception_tables(regs->psw.addr); if (fixup) { - regs->psw.addr = extable_fixup(fixup) | PSW_ADDR_AMODE; + regs->psw.addr = extable_fixup(fixup); return; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c722400c7697..73e290337092 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -98,7 +98,7 @@ void __init paging_init(void) __ctl_load(S390_lowcore.kernel_asce, 1, 1); __ctl_load(S390_lowcore.kernel_asce, 7, 7); __ctl_load(S390_lowcore.kernel_asce, 13, 13); - arch_local_irq_restore(4UL << (BITS_PER_LONG - 8)); + __arch_local_irq_stosm(0x04); sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index ea01477b4aa6..45c4daa49930 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -169,12 +169,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) { - if (is_compat_task() || (TASK_SIZE >= (1UL << 53))) + if (is_compat_task() || TASK_SIZE >= TASK_MAX_SIZE) return 0; if (!(flags & MAP_FIXED)) addr = 0; if ((addr + len) >= TASK_SIZE) - return crst_table_upgrade(current->mm, 1UL << 53); + return crst_table_upgrade(current->mm, TASK_MAX_SIZE); return 0; } @@ -189,9 +189,9 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); if (!(area & ~PAGE_MASK)) return area; - if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { + if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm, TASK_MAX_SIZE); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -211,9 +211,9 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, area = arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); if (!(area & ~PAGE_MASK)) return area; - if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { + if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm, TASK_MAX_SIZE); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area_topdown(filp, addr, len, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a809fa8e6f8b..5109827883ac 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -55,7 +55,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) unsigned long entry; int flush; - BUG_ON(limit > (1UL << 53)); + BUG_ON(limit > TASK_MAX_SIZE); flush = 0; repeat: table = crst_table_alloc(mm); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 43f32ce60aa3..2794845061c6 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -57,9 +57,7 @@ static __init pg_data_t *alloc_node_data(void) { pg_data_t *res; - res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 1); - if (!res) - panic("Could not allocate memory for node data!\n"); + res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8); memset(res, 0, sizeof(pg_data_t)); return res; } @@ -162,7 +160,7 @@ static int __init numa_init_late(void) register_one_node(nid); return 0; } -device_initcall(numa_init_late); +arch_initcall(numa_init_late); static int __init parse_debug(char *parm) { diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c index 8a6811b2cdb9..fe0bfe370c45 100644 --- a/arch/s390/oprofile/backtrace.c +++ b/arch/s390/oprofile/backtrace.c @@ -16,24 +16,23 @@ __show_trace(unsigned int *depth, unsigned long sp, struct pt_regs *regs; while (*depth) { - sp = sp & PSW_ADDR_INSN; if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; (*depth)--; - oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN); + oprofile_add_trace(sf->gprs[8]); /* Follow the backchain. */ while (*depth) { low = sp; - sp = sf->back_chain & PSW_ADDR_INSN; + sp = sf->back_chain; if (!sp) break; if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; (*depth)--; - oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN); + oprofile_add_trace(sf->gprs[8]); } @@ -46,7 +45,7 @@ __show_trace(unsigned int *depth, unsigned long sp, return sp; regs = (struct pt_regs *) sp; (*depth)--; - oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN); + oprofile_add_trace(sf->gprs[8]); low = sp; sp = regs->gprs[15]; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 11d4f277e9f6..8f19c8f9d660 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -68,9 +68,12 @@ static struct airq_struct zpci_airq = { .isc = PCI_ISC, }; -/* I/O Map */ +#define ZPCI_IOMAP_ENTRIES \ + min(((unsigned long) CONFIG_PCI_NR_FUNCTIONS * PCI_BAR_COUNT), \ + ZPCI_IOMAP_MAX_ENTRIES) + static DEFINE_SPINLOCK(zpci_iomap_lock); -static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES); +static unsigned long *zpci_iomap_bitmap; struct zpci_iomap_entry *zpci_iomap_start; EXPORT_SYMBOL_GPL(zpci_iomap_start); @@ -265,27 +268,20 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev, unsigned long max) { struct zpci_dev *zdev = to_zpci(pdev); - u64 addr; int idx; - if ((bar & 7) != bar) + if (!pci_resource_len(pdev, bar)) return NULL; idx = zdev->bars[bar].map_idx; spin_lock(&zpci_iomap_lock); - if (zpci_iomap_start[idx].count++) { - BUG_ON(zpci_iomap_start[idx].fh != zdev->fh || - zpci_iomap_start[idx].bar != bar); - } else { - zpci_iomap_start[idx].fh = zdev->fh; - zpci_iomap_start[idx].bar = bar; - } /* Detect overrun */ - BUG_ON(!zpci_iomap_start[idx].count); + WARN_ON(!++zpci_iomap_start[idx].count); + zpci_iomap_start[idx].fh = zdev->fh; + zpci_iomap_start[idx].bar = bar; spin_unlock(&zpci_iomap_lock); - addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48); - return (void __iomem *) addr + offset; + return (void __iomem *) ZPCI_ADDR(idx) + offset; } EXPORT_SYMBOL(pci_iomap_range); @@ -297,12 +293,11 @@ EXPORT_SYMBOL(pci_iomap); void pci_iounmap(struct pci_dev *pdev, void __iomem *addr) { - unsigned int idx; + unsigned int idx = ZPCI_IDX(addr); - idx = (((__force u64) addr) & ~ZPCI_IOMAP_ADDR_BASE) >> 48; spin_lock(&zpci_iomap_lock); /* Detect underrun */ - BUG_ON(!zpci_iomap_start[idx].count); + WARN_ON(!zpci_iomap_start[idx].count); if (!--zpci_iomap_start[idx].count) { zpci_iomap_start[idx].fh = 0; zpci_iomap_start[idx].bar = 0; @@ -544,15 +539,15 @@ static void zpci_irq_exit(void) static int zpci_alloc_iomap(struct zpci_dev *zdev) { - int entry; + unsigned long entry; spin_lock(&zpci_iomap_lock); - entry = find_first_zero_bit(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES); - if (entry == ZPCI_IOMAP_MAX_ENTRIES) { + entry = find_first_zero_bit(zpci_iomap_bitmap, ZPCI_IOMAP_ENTRIES); + if (entry == ZPCI_IOMAP_ENTRIES) { spin_unlock(&zpci_iomap_lock); return -ENOSPC; } - set_bit(entry, zpci_iomap); + set_bit(entry, zpci_iomap_bitmap); spin_unlock(&zpci_iomap_lock); return entry; } @@ -561,7 +556,7 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) { spin_lock(&zpci_iomap_lock); memset(&zpci_iomap_start[entry], 0, sizeof(struct zpci_iomap_entry)); - clear_bit(entry, zpci_iomap); + clear_bit(entry, zpci_iomap_bitmap); spin_unlock(&zpci_iomap_lock); } @@ -611,8 +606,7 @@ static int zpci_setup_bus_resources(struct zpci_dev *zdev, if (zdev->bars[i].val & 4) flags |= IORESOURCE_MEM_64; - addr = ZPCI_IOMAP_ADDR_BASE + ((u64) entry << 48); - + addr = ZPCI_ADDR(entry); size = 1UL << zdev->bars[i].size; res = __alloc_res(zdev, addr, size, flags); @@ -873,23 +867,30 @@ static int zpci_mem_init(void) zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), 16, 0, NULL); if (!zdev_fmb_cache) - goto error_zdev; + goto error_fmb; - /* TODO: use realloc */ - zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start), - GFP_KERNEL); + zpci_iomap_start = kcalloc(ZPCI_IOMAP_ENTRIES, + sizeof(*zpci_iomap_start), GFP_KERNEL); if (!zpci_iomap_start) goto error_iomap; - return 0; + zpci_iomap_bitmap = kcalloc(BITS_TO_LONGS(ZPCI_IOMAP_ENTRIES), + sizeof(*zpci_iomap_bitmap), GFP_KERNEL); + if (!zpci_iomap_bitmap) + goto error_iomap_bitmap; + + return 0; +error_iomap_bitmap: + kfree(zpci_iomap_start); error_iomap: kmem_cache_destroy(zdev_fmb_cache); -error_zdev: +error_fmb: return -ENOMEM; } static void zpci_mem_exit(void) { + kfree(zpci_iomap_bitmap); kfree(zpci_iomap_start); kmem_cache_destroy(zdev_fmb_cache); } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 369a3e05d468..b0e04751c5d5 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -53,6 +53,11 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n", pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid); + + if (!pdev) + return; + + pdev->error_state = pci_channel_io_perm_failure; } void zpci_event_error(void *data) diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h index f887c6465a82..8a84e05adb2e 100644 --- a/arch/sh/include/asm/barrier.h +++ b/arch/sh/include/asm/barrier.h @@ -33,7 +33,6 @@ #endif #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -#define smp_store_mb(var, value) __smp_store_mb(var, value) #include <asm-generic/barrier.h> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 330e738ccfc1..9af2e6338400 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -509,11 +509,10 @@ config X86_INTEL_CE config X86_INTEL_MID bool "Intel MID platform support" - depends on X86_32 depends on X86_EXTENDED_PLATFORM depends on X86_PLATFORM_DEVICES depends on PCI - depends on PCI_GOANY + depends on X86_64 || (PCI_GOANY && X86_32) depends on X86_IO_APIC select SFI select I2C diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 712b13047b41..3a33124e9112 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - sub $0x40,%rsp + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp # x0..15[0-3] = s0..3[0..3] movq 0x00(%rdi),%xmm1 @@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - add $0x40,%rsp + mov %r11,%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 881b4768644a..e7de5c9a4fbd 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu); #define __ARCH_HAS_DO_SOFTIRQ +struct irq_desc; + #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(int); +extern void irq_force_complete_move(struct irq_desc *desc); #endif #ifdef CONFIG_HAVE_KVM @@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -struct irq_desc; extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 04c27a013165..4432ab7f407c 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -366,20 +366,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f25321894ad2..fdb0fbfb1197 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; const struct cpumask *mask; + struct irq_desc *desc; struct irq_data *idata; struct irq_chip *chip; @@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void) if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; - idata = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + idata = irq_desc_get_irq_data(desc); /* * Honour affinities which have been set in early boot @@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void) /* Might be lapic_chip for irq 0 */ if (chip->irq_set_affinity) chip->irq_set_affinity(idata, mask, false); + raw_spin_unlock_irq(&desc->lock); } } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 908cb37da171..3b670df4ba7b 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -31,7 +31,7 @@ struct apic_chip_data { struct irq_domain *x86_vector_domain; EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask; +static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; static struct irq_chip lapic_controller; #ifdef CONFIG_X86_IO_APIC static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; @@ -118,35 +118,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; + int cpu, vector; - if (d->move_in_progress) + /* + * If there is still a move in progress or the previous move has not + * been cleaned up completely, tell the caller to come back later. + */ + if (d->move_in_progress || + cpumask_intersects(d->old_domain, cpu_online_mask)) return -EBUSY; /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; cpumask_clear(d->old_domain); + cpumask_clear(searched_cpumask); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; + int new_cpu, offset; + /* Get the possible target cpus for @mask/@cpu from the apic */ apic->vector_allocation_domain(cpu, vector_cpumask, mask); + /* + * Clear the offline cpus from @vector_cpumask for searching + * and verify whether the result overlaps with @mask. If true, + * then the call to apic->cpu_mask_to_apicid_and() will + * succeed as well. If not, no point in trying to find a + * vector in this mask. + */ + cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); + if (!cpumask_intersects(vector_searchmask, mask)) + goto next_cpu; + if (cpumask_subset(vector_cpumask, d->domain)) { - err = 0; if (cpumask_equal(vector_cpumask, d->domain)) - break; + goto success; /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. + * Mark the cpus which are not longer in the mask for + * cleanup. */ - cpumask_andnot(d->old_domain, d->domain, - vector_cpumask); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - cpumask_and(d->domain, d->domain, vector_cpumask); - break; + cpumask_andnot(d->old_domain, d->domain, vector_cpumask); + vector = d->cfg.vector; + goto update; } vector = current_vector; @@ -158,45 +170,60 @@ next: vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) { - cpumask_or(d->old_domain, d->old_domain, - vector_cpumask); - cpumask_andnot(vector_cpumask, mask, d->old_domain); - cpu = cpumask_first_and(vector_cpumask, - cpu_online_mask); - continue; - } + /* If the search wrapped around, try the next cpu */ + if (unlikely(current_vector == vector)) + goto next_cpu; if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { + for_each_cpu(new_cpu, vector_searchmask) { if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ current_vector = vector; current_offset = offset; - if (d->cfg.vector) { + /* Schedule the old vector for cleanup on all cpus */ + if (d->cfg.vector) cpumask_copy(d->old_domain, d->domain); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) + for_each_cpu(new_cpu, vector_searchmask) per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); - err = 0; - break; - } + goto update; - if (!err) { - /* cache destination APIC IDs into cfg->dest_apicid */ - err = apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid); +next_cpu: + /* + * We exclude the current @vector_cpumask from the requested + * @mask and try again with the next online cpu in the + * result. We cannot modify @mask, so we use @vector_cpumask + * as a temporary buffer here as it will be reassigned when + * calling apic->vector_allocation_domain() above. + */ + cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); + cpumask_andnot(vector_cpumask, mask, searched_cpumask); + cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); + continue; } + return -ENOSPC; - return err; +update: + /* + * Exclude offline cpus from the cleanup mask and set the + * move_in_progress flag when the result is not empty. + */ + cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); + d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); +success: + /* + * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail + * as we already established, that mask & d->domain & cpu_online_mask + * is not empty. + */ + BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid)); + return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, @@ -226,10 +253,8 @@ static int assign_irq_vector_policy(int irq, int node, static void clear_irq_vector(int irq, struct apic_chip_data *data) { struct irq_desc *desc; - unsigned long flags; int cpu, vector; - raw_spin_lock_irqsave(&vector_lock, flags); BUG_ON(!data->cfg.vector); vector = data->cfg.vector; @@ -239,10 +264,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) data->cfg.vector = 0; cpumask_clear(data->domain); - if (likely(!data->move_in_progress)) { - raw_spin_unlock_irqrestore(&vector_lock, flags); + /* + * If move is in progress or the old_domain mask is not empty, + * i.e. the cleanup IPI has not been processed yet, we need to remove + * the old references to desc from all cpus vector tables. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) return; - } desc = irq_to_desc(irq); for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { @@ -255,7 +283,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) } } data->move_in_progress = 0; - raw_spin_unlock_irqrestore(&vector_lock, flags); } void init_irq_alloc_info(struct irq_alloc_info *info, @@ -276,19 +303,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { + struct apic_chip_data *apic_data; struct irq_data *irq_data; + unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); if (irq_data && irq_data->chip_data) { + raw_spin_lock_irqsave(&vector_lock, flags); clear_irq_vector(virq + i, irq_data->chip_data); - free_apic_chip_data(irq_data->chip_data); + apic_data = irq_data->chip_data; + irq_domain_reset_irq_data(irq_data); + raw_spin_unlock_irqrestore(&vector_lock, flags); + free_apic_chip_data(apic_data); #ifdef CONFIG_X86_IO_APIC if (virq + i < nr_legacy_irqs()) legacy_irq_data[virq + i] = NULL; #endif - irq_domain_reset_irq_data(irq_data); } } } @@ -406,6 +438,8 @@ int __init arch_early_irq_init(void) arch_init_htirq_domain(x86_vector_domain); BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); return arch_early_ioapic_init(); } @@ -494,14 +528,7 @@ static int apic_set_affinity(struct irq_data *irq_data, return -EINVAL; err = assign_irq_vector(irq, data, dest); - if (err) { - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(irq_data))) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - return IRQ_SET_MASK_OK; + return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { @@ -513,20 +540,12 @@ static struct irq_chip lapic_controller = { #ifdef CONFIG_SMP static void __send_cleanup_vector(struct apic_chip_data *data) { - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; - - for_each_cpu_and(i, data->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), - IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } + raw_spin_lock(&vector_lock); + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); data->move_in_progress = 0; + if (!cpumask_empty(data->old_domain)) + apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); + raw_spin_unlock(&vector_lock); } void send_cleanup_vector(struct irq_cfg *cfg) @@ -570,12 +589,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. + * Nothing to cleanup if irq migration is in progress + * or this cpu is not set in the cleanup mask. */ - if (data->move_in_progress) + if (data->move_in_progress || + !cpumask_test_cpu(me, data->old_domain)) goto unlock; + /* + * We have two cases to handle here: + * 1) vector is unchanged but the target mask got reduced + * 2) vector and the target mask has changed + * + * #1 is obvious, but in #2 we have two vectors with the same + * irq descriptor: the old and the new vector. So we need to + * make sure that we only cleanup the old vector. The new + * vector has the current @vector number in the config and + * this cpu is part of the target mask. We better leave that + * one alone. + */ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) goto unlock; @@ -593,6 +625,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; } __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + cpumask_clear_cpu(me, data->old_domain); unlock: raw_spin_unlock(&desc->lock); } @@ -621,12 +654,48 @@ void irq_complete_move(struct irq_cfg *cfg) __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); } -void irq_force_complete_move(int irq) +/* + * Called with @desc->lock held and interrupts disabled. + */ +void irq_force_complete_move(struct irq_desc *desc) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_data *irqdata = irq_desc_get_irq_data(desc); + struct apic_chip_data *data = apic_chip_data(irqdata); + struct irq_cfg *cfg = data ? &data->cfg : NULL; - if (cfg) - __irq_complete_move(cfg, cfg->vector); + if (!cfg) + return; + + __irq_complete_move(cfg, cfg->vector); + + /* + * This is tricky. If the cleanup of @data->old_domain has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * The cleanup cannot make progress because we hold @desc->lock. So in + * case @data->old_domain is not yet cleaned up, we need to drop the + * lock and acquire it again. @desc cannot go away, because the + * hotplug code holds the sparse irq lock. + */ + raw_spin_lock(&vector_lock); + /* Clean out all offline cpus (including ourself) first. */ + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); + while (!cpumask_empty(data->old_domain)) { + raw_spin_unlock(&vector_lock); + raw_spin_unlock(&desc->lock); + cpu_relax(); + raw_spin_lock(&desc->lock); + /* + * Reevaluate apic_chip_data. It might have been cleared after + * we dropped @desc->lock. + */ + data = apic_chip_data(irqdata); + if (!data) + return; + raw_spin_lock(&vector_lock); + } + raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d760c6bb37b5..624db00583f4 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -889,7 +889,10 @@ void __init uv_system_init(void) return; } pr_info("UV: Found %s hub\n", hub); - map_low_mmrs(); + + /* We now only need to map the MMRs on UV1 */ + if (is_uv1_hub()) + map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index a667078a5180..fed2ab1f1065 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1960,7 +1960,8 @@ intel_bts_constraints(struct perf_event *event) static int intel_alt_er(int idx, u64 config) { - int alt_idx; + int alt_idx = idx; + if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; @@ -2897,14 +2898,12 @@ static void intel_pmu_cpu_starting(int cpu) return; if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { - void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - *onln = cpuc->shared_regs; + cpuc->kfree_on_online[0] = cpuc->shared_regs; cpuc->shared_regs = pc; break; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index f97f8075bf04..3bf41d413775 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -995,6 +995,9 @@ static int __init uncore_pci_init(void) case 87: /* Knights Landing */ ret = knl_uncore_pci_init(); break; + case 94: /* SkyLake */ + ret = skl_uncore_pci_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 07aa2d6bd710..a7086b862156 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -336,6 +336,7 @@ int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); +int skl_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); int snb_pci2phy_map_init(int devid); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 0b934820fafd..2bd030ddd0db 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -8,6 +8,7 @@ #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 #define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 +#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -524,6 +525,14 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id skl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -544,6 +553,11 @@ static struct pci_driver bdw_uncore_pci_driver = { .id_table = bdw_uncore_pci_ids, }; +static struct pci_driver skl_uncore_pci_driver = { + .name = "skl_uncore", + .id_table = skl_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -558,6 +572,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ + IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */ { /* end marker */ } }; @@ -610,6 +625,11 @@ int bdw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int skl_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f129a9af6357..2c0f3407bd1f 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -192,5 +192,13 @@ void __init x86_64_start_reservations(char *real_mode_data) reserve_ebda_region(); + switch (boot_params.hdr.hardware_subarch) { + case X86_SUBARCH_INTEL_MID: + x86_intel_mid_early_setup(); + break; + default: + break; + } + start_kernel(); } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f8062aaf5df9..61521dc19c10 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -462,7 +462,7 @@ void fixup_irqs(void) * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -470,6 +470,15 @@ void fixup_irqs(void) } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index fc6a4c8f6e2a..2440814b0069 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -1350,7 +1350,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 1c7380da65ff..2d66db8f80f9 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -8,6 +8,7 @@ #include <linux/memblock.h> #include <linux/bootmem.h> #include <linux/acpi.h> +#include <linux/dmi.h> #include <asm/efi.h> #include <asm/uv/uv.h> @@ -248,6 +249,16 @@ out: return ret; } +static const struct dmi_system_id sgi_uv1_dmi[] = { + { NULL, "SGI UV1", + { DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + DMI_MATCH(DMI_BIOS_VENDOR, "SGI.COM"), + } + }, + { } /* NULL entry stops DMI scanning */ +}; + void __init efi_apply_memmap_quirks(void) { /* @@ -260,10 +271,8 @@ void __init efi_apply_memmap_quirks(void) efi_unmap_memmap(); } - /* - * UV doesn't support the new EFI pagetable mapping yet. - */ - if (is_uv_system()) + /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */ + if (dmi_check_system(sgi_uv1_dmi)) set_bit(EFI_OLD_MEMMAP, &efi.flags); } diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 1bbc21e2e4ae..90bb997ed0a2 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -138,7 +138,7 @@ static void intel_mid_arch_setup(void) intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip](); else { intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL](); - pr_info("ARCH: Unknown SoC, assuming PENWELL!\n"); + pr_info("ARCH: Unknown SoC, assuming Penwell!\n"); } out: @@ -214,12 +214,10 @@ static inline int __init setup_x86_intel_mid_timer(char *arg) else if (strcmp("lapic_and_apbt", arg) == 0) intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT; else { - pr_warn("X86 INTEL_MID timer option %s not recognised" - " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", - arg); + pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", + arg); return -EINVAL; } return 0; } __setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer); - diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index c1bdafaac3ca..c61b6c332e97 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -220,11 +220,12 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused) if (imr_is_enabled(&imr)) { base = imr_to_phys(imr.addr_lo); end = imr_to_phys(imr.addr_hi) + IMR_MASK; + size = end - base + 1; } else { base = 0; end = 0; + size = 0; } - size = end - base; seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx " "rmask=0x%08x, wmask=0x%08x, %s, %s\n", i, &base, &end, size, imr.rmask, imr.wmask, @@ -579,6 +580,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) { phys_addr_t base = virt_to_phys(&_text); size_t size = virt_to_phys(&__end_rodata) - base; + unsigned long start, end; int i; int ret; @@ -586,18 +588,24 @@ static void __init imr_fixup_memmap(struct imr_device *idev) for (i = 0; i < idev->max_imr; i++) imr_clear(i); + start = (unsigned long)_text; + end = (unsigned long)__end_rodata - 1; + /* * Setup a locked IMR around the physical extent of the kernel * from the beginning of the .text secton to the end of the * .rodata section as one physically contiguous block. + * + * We don't round up @size since it is already PAGE_SIZE aligned. + * See vmlinux.lds.S for details. */ ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true); if (ret < 0) { - pr_err("unable to setup IMR for kernel: (%p - %p)\n", - &_text, &__end_rodata); + pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", + size / 1024, start, end); } else { - pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n", - size / 1024, &_text, &__end_rodata); + pr_info("protecting kernel .text - .rodata: %zu KiB (%lx - %lx)\n", + size / 1024, start, end); } } diff --git a/block/blk-merge.c b/block/blk-merge.c index 1699df5b0493..888a7fec81f7 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -70,6 +70,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } +static inline unsigned get_max_io_size(struct request_queue *q, + struct bio *bio) +{ + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned mask = queue_logical_block_size(q) - 1; + + /* aligned to logical block size */ + sectors &= ~(mask >> 9); + + return sectors; +} + static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, @@ -81,6 +93,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, unsigned front_seg_size = bio->bi_seg_front_size; bool do_split = true; struct bio *new = NULL; + const unsigned max_sectors = get_max_io_size(q, bio); bio_for_each_segment(bv, bio, iter) { /* @@ -90,20 +103,19 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; - if (sectors + (bv.bv_len >> 9) > - blk_max_size_offset(q, bio->bi_iter.bi_sector)) { + if (sectors + (bv.bv_len >> 9) > max_sectors) { /* * Consider this a new segment if we're splitting in * the middle of this vector. */ if (nsegs < queue_max_segments(q) && - sectors < blk_max_size_offset(q, - bio->bi_iter.bi_sector)) { + sectors < max_sectors) { nsegs++; - sectors = blk_max_size_offset(q, - bio->bi_iter.bi_sector); + sectors = max_sectors; } - goto split; + if (sectors) + goto split; + /* Make this single bvec as the 1st segment */ } if (bvprvp && blk_queue_cluster(q)) { diff --git a/block/ioctl.c b/block/ioctl.c index 77f5d17779d6..d8996bbd7f12 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -434,42 +434,6 @@ bool blkdev_dax_capable(struct block_device *bdev) return true; } - -static int blkdev_daxset(struct block_device *bdev, unsigned long argp) -{ - unsigned long arg; - int rc = 0; - - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; - - if (get_user(arg, (int __user *)(argp))) - return -EFAULT; - arg = !!arg; - if (arg == !!(bdev->bd_inode->i_flags & S_DAX)) - return 0; - - if (arg) - arg = S_DAX; - - if (arg && !blkdev_dax_capable(bdev)) - return -ENOTTY; - - inode_lock(bdev->bd_inode); - if (bdev->bd_map_count == 0) - inode_set_flags(bdev->bd_inode, arg, S_DAX); - else - rc = -EBUSY; - inode_unlock(bdev->bd_inode); - return rc; -} -#else -static int blkdev_daxset(struct block_device *bdev, int arg) -{ - if (arg) - return -ENOTTY; - return 0; -} #endif static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, @@ -634,8 +598,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); - case BLKDAXSET: - return blkdev_daxset(bdev, arg); case BLKDAXGET: return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); break; diff --git a/block/partition-generic.c b/block/partition-generic.c index 746935a5973c..fefd01b496a0 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -16,6 +16,7 @@ #include <linux/kmod.h> #include <linux/ctype.h> #include <linux/genhd.h> +#include <linux/dax.h> #include <linux/blktrace_api.h> #include "partitions/check.h" @@ -550,13 +551,24 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) return 0; } -unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) +static struct page *read_pagecache_sector(struct block_device *bdev, sector_t n) { struct address_space *mapping = bdev->bd_inode->i_mapping; + + return read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), + NULL); +} + +unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p) +{ struct page *page; - page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_CACHE_SHIFT-9)), - NULL); + /* don't populate page cache for dax capable devices */ + if (IS_DAX(bdev->bd_inode)) + page = read_dax_sector(bdev, n); + else + page = read_pagecache_sector(bdev, n); + if (!IS_ERR(page)) { if (PageError(page)) goto fail; diff --git a/crypto/Kconfig b/crypto/Kconfig index 7240821137fd..3be07ad1d80d 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -472,11 +472,13 @@ config CRYPTO_CRCT10DIF_PCLMUL config CRYPTO_GHASH tristate "GHASH digest algorithm" select CRYPTO_GF128MUL + select CRYPTO_HASH help GHASH is message digest algorithm for GCM (Galois/Counter Mode). config CRYPTO_POLY1305 tristate "Poly1305 authenticator algorithm" + select CRYPTO_HASH help Poly1305 authenticator algorithm, RFC7539. diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 608a7562839d..68a5ceaa04c8 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -54,7 +54,8 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); if (!ctx->more) { - err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(crypto_ahash_init(&ctx->req), + &ctx->completion); if (err) goto unlock; } @@ -125,6 +126,7 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, } else { if (!ctx->more) { err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(err, &ctx->completion); if (err) goto unlock; } diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index 758acabf2d81..8f3056cd0399 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -547,9 +547,7 @@ int pkcs7_sig_note_set_of_authattrs(void *context, size_t hdrlen, struct pkcs7_signed_info *sinfo = ctx->sinfo; if (!test_bit(sinfo_has_content_type, &sinfo->aa_set) || - !test_bit(sinfo_has_message_digest, &sinfo->aa_set) || - (ctx->msg->data_type == OID_msIndirectData && - !test_bit(sinfo_has_ms_opus_info, &sinfo->aa_set))) { + !test_bit(sinfo_has_message_digest, &sinfo->aa_set)) { pr_warn("Missing required AuthAttr\n"); return -EBADMSG; } diff --git a/crypto/shash.c b/crypto/shash.c index 88a27de79848..359754591653 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -354,11 +354,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm) crt->final = shash_async_final; crt->finup = shash_async_finup; crt->digest = shash_async_digest; + crt->setkey = shash_async_setkey; + + crt->has_setkey = alg->setkey != shash_no_setkey; - if (alg->setkey) { - crt->setkey = shash_async_setkey; - crt->has_setkey = true; - } if (alg->export) crt->export = shash_async_export; if (alg->import) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 90e2d54be526..1316ddd92fac 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -135,14 +135,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"), }, }, - { - .callback = video_detect_force_vendor, - .ident = "Dell Inspiron 5737", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"), - }, - }, /* * These models have a working acpi_video backlight control, and using diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 47c43386786b..279e53989374 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -284,6 +284,7 @@ out_free_priv_data: return err; } +EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs); /** * platform_msi_domain_free_irqs - Free MSI interrupts for @dev @@ -301,6 +302,7 @@ void platform_msi_domain_free_irqs(struct device *dev) msi_domain_free_irqs(dev->msi_domain, dev); platform_msi_free_descs(dev, 0, MAX_DEV_MSIS); } +EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); /** * platform_msi_get_host_data - Query the private data associated with diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 73d6e5d39e33..f437afa17f2b 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -558,10 +558,15 @@ static int platform_drv_probe(struct device *_dev) return ret; ret = dev_pm_domain_attach(_dev, true); - if (ret != -EPROBE_DEFER && drv->probe) { - ret = drv->probe(dev); - if (ret) - dev_pm_domain_detach(_dev, true); + if (ret != -EPROBE_DEFER) { + if (drv->probe) { + ret = drv->probe(dev); + if (ret) + dev_pm_domain_detach(_dev, true); + } else { + /* don't fail if just dev_pm_domain_attach failed */ + ret = 0; + } } if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 6ac9a7f33b64..784dbe897a5e 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -162,7 +162,7 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed) /** * genpd_queue_power_off_work - Queue up the execution of genpd_poweroff(). - * @genpd: PM domait to power off. + * @genpd: PM domain to power off. * * Queue up the execution of genpd_poweroff() unless it's already been done * before. @@ -172,16 +172,15 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) queue_work(pm_wq, &genpd->power_off_work); } -static int genpd_poweron(struct generic_pm_domain *genpd); - /** * __genpd_poweron - Restore power to a given PM domain and its masters. * @genpd: PM domain to power up. + * @depth: nesting count for lockdep. * * Restore power to @genpd and all of its masters so that it is possible to * resume a device belonging to it. */ -static int __genpd_poweron(struct generic_pm_domain *genpd) +static int __genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth) { struct gpd_link *link; int ret = 0; @@ -196,11 +195,16 @@ static int __genpd_poweron(struct generic_pm_domain *genpd) * with it. */ list_for_each_entry(link, &genpd->slave_links, slave_node) { - genpd_sd_counter_inc(link->master); + struct generic_pm_domain *master = link->master; + + genpd_sd_counter_inc(master); + + mutex_lock_nested(&master->lock, depth + 1); + ret = __genpd_poweron(master, depth + 1); + mutex_unlock(&master->lock); - ret = genpd_poweron(link->master); if (ret) { - genpd_sd_counter_dec(link->master); + genpd_sd_counter_dec(master); goto err; } } @@ -232,11 +236,12 @@ static int genpd_poweron(struct generic_pm_domain *genpd) int ret; mutex_lock(&genpd->lock); - ret = __genpd_poweron(genpd); + ret = __genpd_poweron(genpd, 0); mutex_unlock(&genpd->lock); return ret; } + static int genpd_save_dev(struct generic_pm_domain *genpd, struct device *dev) { return GENPD_DEV_CALLBACK(genpd, int, save_state, dev); @@ -484,7 +489,7 @@ static int pm_genpd_runtime_resume(struct device *dev) } mutex_lock(&genpd->lock); - ret = __genpd_poweron(genpd); + ret = __genpd_poweron(genpd, 0); mutex_unlock(&genpd->lock); if (ret) @@ -1339,8 +1344,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, if (!link) return -ENOMEM; - mutex_lock(&genpd->lock); - mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING); + mutex_lock(&subdomain->lock); + mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); if (genpd->status == GPD_STATE_POWER_OFF && subdomain->status != GPD_STATE_POWER_OFF) { @@ -1363,8 +1368,8 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, genpd_sd_counter_inc(genpd); out: - mutex_unlock(&subdomain->lock); mutex_unlock(&genpd->lock); + mutex_unlock(&subdomain->lock); if (ret) kfree(link); return ret; @@ -1385,7 +1390,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain)) return -EINVAL; - mutex_lock(&genpd->lock); + mutex_lock(&subdomain->lock); + mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING); if (!list_empty(&subdomain->slave_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, @@ -1398,22 +1404,19 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, if (link->slave != subdomain) continue; - mutex_lock_nested(&subdomain->lock, SINGLE_DEPTH_NESTING); - list_del(&link->master_node); list_del(&link->slave_node); kfree(link); if (subdomain->status != GPD_STATE_POWER_OFF) genpd_sd_counter_dec(genpd); - mutex_unlock(&subdomain->lock); - ret = 0; break; } out: mutex_unlock(&genpd->lock); + mutex_unlock(&subdomain->lock); return ret; } diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig index dbf22719462f..ff00331bff49 100644 --- a/drivers/char/hw_random/Kconfig +++ b/drivers/char/hw_random/Kconfig @@ -372,6 +372,7 @@ config HW_RANDOM_XGENE config HW_RANDOM_STM32 tristate "STMicroelectronics STM32 random number generator" depends on HW_RANDOM && (ARCH_STM32 || COMPILE_TEST) + depends on HAS_IOMEM help This driver provides kernel-side support for the Random Number Generator hardware found on STM32 microcontrollers. diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 56777f04d2d9..33db7406c0e2 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -30,6 +30,8 @@ config CLKSRC_MMIO config DIGICOLOR_TIMER bool "Digicolor timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + select CLKSRC_MMIO + depends on HAS_IOMEM help Enables the support for the digicolor timer driver. @@ -55,6 +57,7 @@ config ARMADA_370_XP_TIMER bool "Armada 370 and XP timer driver" if COMPILE_TEST depends on ARM select CLKSRC_OF + select CLKSRC_MMIO help Enables the support for the Armada 370 and XP timer driver. @@ -76,6 +79,7 @@ config ORION_TIMER config SUN4I_TIMER bool "Sun4i timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM select CLKSRC_MMIO help Enables support for the Sun4i timer. @@ -89,6 +93,7 @@ config SUN5I_HSTIMER config TEGRA_TIMER bool "Tegra timer driver" if COMPILE_TEST + select CLKSRC_MMIO depends on ARM help Enables support for the Tegra driver. @@ -96,6 +101,7 @@ config TEGRA_TIMER config VT8500_TIMER bool "VT8500 timer driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM help Enables support for the VT8500 driver. @@ -131,6 +137,7 @@ config CLKSRC_NOMADIK_MTU_SCHED_CLOCK config CLKSRC_DBX500_PRCMU bool "Clocksource PRCMU Timer" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM help Use the always on PRCMU Timer as clocksource @@ -248,6 +255,7 @@ config CLKSRC_EXYNOS_MCT config CLKSRC_SAMSUNG_PWM bool "PWM timer drvier for Samsung S3C, S5P" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM help This is a new clocksource driver for the PWM timer found in Samsung S3C, S5P and Exynos SoCs, replacing an earlier driver @@ -257,12 +265,14 @@ config CLKSRC_SAMSUNG_PWM config FSL_FTM_TIMER bool "Freescale FlexTimer Module driver" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM select CLKSRC_MMIO help Support for Freescale FlexTimer Module (FTM) timer. config VF_PIT_TIMER bool + select CLKSRC_MMIO help Support for Period Interrupt Timer on Freescale Vybrid Family SoCs. @@ -360,6 +370,7 @@ config CLKSRC_TANGO_XTAL config CLKSRC_PXA bool "Clocksource for PXA or SA-11x0 platform" if COMPILE_TEST depends on GENERIC_CLOCKEVENTS + depends on HAS_IOMEM select CLKSRC_MMIO help This enables OST0 support available on PXA and SA-11x0 @@ -394,6 +405,7 @@ config CLKSRC_ST_LPC bool "Low power clocksource found in the LPC" if COMPILE_TEST select CLKSRC_OF if OF depends on HAS_IOMEM + select CLKSRC_MMIO help Enable this option to use the Low Power controller timer as clocksource. diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 6ee91401918e..4da2af9694a2 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -98,7 +98,8 @@ static int tc_shutdown(struct clock_event_device *d) __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR)); __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); - clk_disable(tcd->clk); + if (!clockevent_state_detached(d)) + clk_disable(tcd->clk); return 0; } diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index 9bc37c437874..0ca74d070058 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -142,15 +142,16 @@ static int allocate_resources(int cpu, struct device **cdev, try_again: cpu_reg = regulator_get_optional(cpu_dev, reg); - if (IS_ERR(cpu_reg)) { + ret = PTR_ERR_OR_ZERO(cpu_reg); + if (ret) { /* * If cpu's regulator supply node is present, but regulator is * not yet registered, we should try defering probe. */ - if (PTR_ERR(cpu_reg) == -EPROBE_DEFER) { + if (ret == -EPROBE_DEFER) { dev_dbg(cpu_dev, "cpu%d regulator not ready, retry\n", cpu); - return -EPROBE_DEFER; + return ret; } /* Try with "cpu-supply" */ @@ -159,18 +160,16 @@ try_again: goto try_again; } - dev_dbg(cpu_dev, "no regulator for cpu%d: %ld\n", - cpu, PTR_ERR(cpu_reg)); + dev_dbg(cpu_dev, "no regulator for cpu%d: %d\n", cpu, ret); } cpu_clk = clk_get(cpu_dev, NULL); - if (IS_ERR(cpu_clk)) { + ret = PTR_ERR_OR_ZERO(cpu_clk); + if (ret) { /* put regulator */ if (!IS_ERR(cpu_reg)) regulator_put(cpu_reg); - ret = PTR_ERR(cpu_clk); - /* * If cpu's clk node is present, but clock is not yet * registered, we should try defering probe. diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index c35e7da1ed7a..e979ec78b695 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -48,11 +48,11 @@ static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy, bool active) { do { - policy = list_next_entry(policy, policy_list); - /* No more policies in the list */ - if (&policy->policy_list == &cpufreq_policy_list) + if (list_is_last(&policy->policy_list, &cpufreq_policy_list)) return NULL; + + policy = list_next_entry(policy, policy_list); } while (!suitable_policy(policy, active)); return policy; diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index bab3a514ec12..e0d111024d48 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -387,16 +387,18 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy, if (!have_governor_per_policy()) cdata->gdbs_data = dbs_data; + policy->governor_data = dbs_data; + ret = sysfs_create_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); if (ret) goto reset_gdbs_data; - policy->governor_data = dbs_data; - return 0; reset_gdbs_data: + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, !policy->governor->initialized); @@ -417,16 +419,19 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy, if (!cdbs->shared || cdbs->shared->policy) return -EBUSY; - policy->governor_data = NULL; if (!--dbs_data->usage_count) { sysfs_remove_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, policy->governor->initialized == 1); kfree(dbs_data); + } else { + policy->governor_data = NULL; } free_common_dbs_info(policy, cdata); diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c index 1d99c97defa9..096377232747 100644 --- a/drivers/cpufreq/pxa2xx-cpufreq.c +++ b/drivers/cpufreq/pxa2xx-cpufreq.c @@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void) } } #else -static int pxa_cpufreq_change_voltage(struct pxa_freqs *pxa_freq) +static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq) { return 0; } diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c index 344058f8501a..d5657d50ac40 100644 --- a/drivers/cpuidle/coupled.c +++ b/drivers/cpuidle/coupled.c @@ -119,7 +119,6 @@ struct cpuidle_coupled { #define CPUIDLE_COUPLED_NOT_IDLE (-1) -static DEFINE_MUTEX(cpuidle_coupled_lock); static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb); /* diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 046423b0c5ca..f996efc56605 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -153,7 +153,7 @@ int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) * be frozen safely. */ index = find_deepest_state(drv, dev, UINT_MAX, 0, true); - if (index >= 0) + if (index > 0) enter_freeze_proper(drv, dev, index); return index; diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 6dd3317ca365..3eb3f1279fb7 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -400,7 +400,7 @@ static int atmel_aes_hw_init(struct atmel_aes_dev *dd) { int err; - err = clk_prepare_enable(dd->iclk); + err = clk_enable(dd->iclk); if (err) return err; @@ -430,7 +430,7 @@ static int atmel_aes_hw_version_init(struct atmel_aes_dev *dd) dev_info(dd->dev, "version: 0x%x\n", dd->hw_version); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); return 0; } @@ -448,7 +448,7 @@ static inline bool atmel_aes_is_encrypt(const struct atmel_aes_dev *dd) static inline int atmel_aes_complete(struct atmel_aes_dev *dd, int err) { - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); dd->flags &= ~AES_FLAGS_BUSY; if (dd->is_async) @@ -2091,10 +2091,14 @@ static int atmel_aes_probe(struct platform_device *pdev) goto res_err; } - err = atmel_aes_hw_version_init(aes_dd); + err = clk_prepare(aes_dd->iclk); if (err) goto res_err; + err = atmel_aes_hw_version_init(aes_dd); + if (err) + goto iclk_unprepare; + atmel_aes_get_cap(aes_dd); err = atmel_aes_buff_init(aes_dd); @@ -2127,6 +2131,8 @@ err_algs: err_aes_dma: atmel_aes_buff_cleanup(aes_dd); err_aes_buff: +iclk_unprepare: + clk_unprepare(aes_dd->iclk); res_err: tasklet_kill(&aes_dd->done_task); tasklet_kill(&aes_dd->queue_task); @@ -2155,6 +2161,8 @@ static int atmel_aes_remove(struct platform_device *pdev) atmel_aes_dma_cleanup(aes_dd); atmel_aes_buff_cleanup(aes_dd); + clk_unprepare(aes_dd->iclk); + return 0; } diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 8abb4bc548cc..69d4a1326fee 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -534,8 +534,8 @@ static int caam_probe(struct platform_device *pdev) * long pointers in master configuration register */ clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ? - MCFGR_LONG_PTR : 0)); + MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | + (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* * Read the Compile Time paramters and SCFGR to determine diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 313b0cc8d676..82edf95b7740 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -2278,60 +2278,60 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_dpm_enable_bapm(adev, e) (adev)->pm.funcs->enable_bapm((adev), (e)) #define amdgpu_dpm_get_temperature(adev) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_temperature((adev)->powerplay.pp_handle) : \ - (adev)->pm.funcs->get_temperature((adev)) + (adev)->pm.funcs->get_temperature((adev))) #define amdgpu_dpm_set_fan_control_mode(adev, m) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->set_fan_control_mode((adev)->powerplay.pp_handle, (m)) : \ - (adev)->pm.funcs->set_fan_control_mode((adev), (m)) + (adev)->pm.funcs->set_fan_control_mode((adev), (m))) #define amdgpu_dpm_get_fan_control_mode(adev) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_fan_control_mode((adev)->powerplay.pp_handle) : \ - (adev)->pm.funcs->get_fan_control_mode((adev)) + (adev)->pm.funcs->get_fan_control_mode((adev))) #define amdgpu_dpm_set_fan_speed_percent(adev, s) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->set_fan_speed_percent((adev)->powerplay.pp_handle, (s)) : \ - (adev)->pm.funcs->set_fan_speed_percent((adev), (s)) + (adev)->pm.funcs->set_fan_speed_percent((adev), (s))) #define amdgpu_dpm_get_fan_speed_percent(adev, s) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_fan_speed_percent((adev)->powerplay.pp_handle, (s)) : \ - (adev)->pm.funcs->get_fan_speed_percent((adev), (s)) + (adev)->pm.funcs->get_fan_speed_percent((adev), (s))) #define amdgpu_dpm_get_sclk(adev, l) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_sclk((adev)->powerplay.pp_handle, (l)) : \ - (adev)->pm.funcs->get_sclk((adev), (l)) + (adev)->pm.funcs->get_sclk((adev), (l))) #define amdgpu_dpm_get_mclk(adev, l) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->get_mclk((adev)->powerplay.pp_handle, (l)) : \ - (adev)->pm.funcs->get_mclk((adev), (l)) + (adev)->pm.funcs->get_mclk((adev), (l))) #define amdgpu_dpm_force_performance_level(adev, l) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->force_performance_level((adev)->powerplay.pp_handle, (l)) : \ - (adev)->pm.funcs->force_performance_level((adev), (l)) + (adev)->pm.funcs->force_performance_level((adev), (l))) #define amdgpu_dpm_powergate_uvd(adev, g) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->powergate_uvd((adev)->powerplay.pp_handle, (g)) : \ - (adev)->pm.funcs->powergate_uvd((adev), (g)) + (adev)->pm.funcs->powergate_uvd((adev), (g))) #define amdgpu_dpm_powergate_vce(adev, g) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->powergate_vce((adev)->powerplay.pp_handle, (g)) : \ - (adev)->pm.funcs->powergate_vce((adev), (g)) + (adev)->pm.funcs->powergate_vce((adev), (g))) #define amdgpu_dpm_debugfs_print_current_performance_level(adev, m) \ - (adev)->pp_enabled ? \ + ((adev)->pp_enabled ? \ (adev)->powerplay.pp_funcs->print_current_performance_level((adev)->powerplay.pp_handle, (m)) : \ - (adev)->pm.funcs->debugfs_print_current_performance_level((adev), (m)) + (adev)->pm.funcs->debugfs_print_current_performance_level((adev), (m))) #define amdgpu_dpm_get_current_power_state(adev) \ (adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 6f89f8e034d0..b882e8175615 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -478,9 +478,9 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; unsigned i; - amdgpu_vm_move_pt_bos_in_lru(parser->adev, &fpriv->vm); - if (!error) { + amdgpu_vm_move_pt_bos_in_lru(parser->adev, &fpriv->vm); + /* Sort the buffer list from the smallest to largest buffer, * which affects the order of buffers in the LRU list. * This assures that the smallest buffers are added first diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index cfb6caad2a73..919146780a15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -333,6 +333,10 @@ int amdgpu_fbdev_init(struct amdgpu_device *adev) if (!adev->mode_info.mode_config_initialized) return 0; + /* don't init fbdev if there are no connectors */ + if (list_empty(&adev->ddev->mode_config.connector_list)) + return 0; + /* select 8 bpp console on low vram cards */ if (adev->mc.real_vram_size <= (32*1024*1024)) bpp_sel = 8; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c3ce103b6a33..a2a16acee34d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -399,7 +399,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, } if (fpfn > bo->placements[i].fpfn) bo->placements[i].fpfn = fpfn; - if (lpfn && lpfn < bo->placements[i].lpfn) + if (!bo->placements[i].lpfn || + (lpfn && lpfn < bo->placements[i].lpfn)) bo->placements[i].lpfn = lpfn; bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index 5ee9a0690278..b9d0d55f6b47 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -99,13 +99,24 @@ static int amdgpu_pp_early_init(void *handle) #ifdef CONFIG_DRM_AMD_POWERPLAY switch (adev->asic_type) { - case CHIP_TONGA: - case CHIP_FIJI: - adev->pp_enabled = (amdgpu_powerplay > 0) ? true : false; - break; - default: - adev->pp_enabled = (amdgpu_powerplay > 0) ? true : false; - break; + case CHIP_TONGA: + case CHIP_FIJI: + adev->pp_enabled = (amdgpu_powerplay == 0) ? false : true; + break; + case CHIP_CARRIZO: + case CHIP_STONEY: + adev->pp_enabled = (amdgpu_powerplay > 0) ? true : false; + break; + /* These chips don't have powerplay implemenations */ + case CHIP_BONAIRE: + case CHIP_HAWAII: + case CHIP_KABINI: + case CHIP_MULLINS: + case CHIP_KAVERI: + case CHIP_TOPAZ: + default: + adev->pp_enabled = false; + break; } #else adev->pp_enabled = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 78e9b0f14661..d1f234dd2126 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -487,7 +487,7 @@ static int amdgpu_debugfs_ring_info(struct seq_file *m, void *data) seq_printf(m, "rptr: 0x%08x [%5d]\n", rptr, rptr); - rptr_next = ~0; + rptr_next = le32_to_cpu(*ring->next_rptr_cpu_addr); seq_printf(m, "driver's copy of the wptr: 0x%08x [%5d]\n", ring->wptr, ring->wptr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index aefc668e6b5d..9599f7559b3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1282,7 +1282,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) { const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE, AMDGPU_VM_PTE_COUNT * 8); - unsigned pd_size, pd_entries, pts_size; + unsigned pd_size, pd_entries; int i, r; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { @@ -1300,8 +1300,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) pd_entries = amdgpu_vm_num_pdes(adev); /* allocate page table array */ - pts_size = pd_entries * sizeof(struct amdgpu_vm_pt); - vm->page_tables = kzalloc(pts_size, GFP_KERNEL); + vm->page_tables = drm_calloc_large(pd_entries, sizeof(struct amdgpu_vm_pt)); if (vm->page_tables == NULL) { DRM_ERROR("Cannot allocate memory for page table array\n"); return -ENOMEM; @@ -1361,7 +1360,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < amdgpu_vm_num_pdes(adev); i++) amdgpu_bo_unref(&vm->page_tables[i].entry.robj); - kfree(vm->page_tables); + drm_free_large(vm->page_tables); amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 13235d84e5a6..95c0cdfbd1b3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4186,7 +4186,18 @@ static int gfx_v8_0_soft_reset(void *handle) gfx_v8_0_cp_gfx_enable(adev, false); /* Disable MEC parsing/prefetching */ - /* XXX todo */ + gfx_v8_0_cp_compute_enable(adev, false); + + if (grbm_soft_reset || srbm_soft_reset) { + tmp = RREG32(mmGMCON_DEBUG); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_STALL, 1); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_CLEAR, 1); + WREG32(mmGMCON_DEBUG, tmp); + + udelay(50); + } if (grbm_soft_reset) { tmp = RREG32(mmGRBM_SOFT_RESET); @@ -4215,6 +4226,16 @@ static int gfx_v8_0_soft_reset(void *handle) WREG32(mmSRBM_SOFT_RESET, tmp); tmp = RREG32(mmSRBM_SOFT_RESET); } + + if (grbm_soft_reset || srbm_soft_reset) { + tmp = RREG32(mmGMCON_DEBUG); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_STALL, 0); + tmp = REG_SET_FIELD(tmp, + GMCON_DEBUG, GFX_CLEAR, 0); + WREG32(mmGMCON_DEBUG, tmp); + } + /* Wait a little for things to settle down */ udelay(50); gfx_v8_0_print_status((void *)adev); diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c index f4a1346525fe..0497784b3652 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c @@ -122,25 +122,12 @@ static int tonga_dpm_hw_fini(void *handle) static int tonga_dpm_suspend(void *handle) { - return 0; + return tonga_dpm_hw_fini(handle); } static int tonga_dpm_resume(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - mutex_lock(&adev->pm.mutex); - - ret = tonga_smu_start(adev); - if (ret) { - DRM_ERROR("SMU start failed\n"); - goto fail; - } - -fail: - mutex_unlock(&adev->pm.mutex); - return ret; + return tonga_dpm_hw_init(handle); } static int tonga_dpm_set_clockgating_state(void *handle, diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index 8f5d5edcf193..aa67244a77ae 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -64,6 +64,11 @@ static int pp_sw_init(void *handle) if (ret == 0) ret = hwmgr->hwmgr_func->backend_init(hwmgr); + if (ret) + printk("amdgpu: powerplay initialization failed\n"); + else + printk("amdgpu: powerplay initialized\n"); + return ret; } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c index 873a8d264d5c..ec222c665602 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/cz_smumgr.c @@ -272,6 +272,9 @@ static int cz_start_smu(struct pp_smumgr *smumgr) UCODE_ID_CP_MEC_JT1_MASK | UCODE_ID_CP_MEC_JT2_MASK; + if (smumgr->chip_id == CHIP_STONEY) + fw_to_check &= ~(UCODE_ID_SDMA1_MASK | UCODE_ID_CP_MEC_JT2_MASK); + cz_request_smu_load_fw(smumgr); cz_check_fw_load_finish(smumgr, fw_to_check); @@ -282,7 +285,7 @@ static int cz_start_smu(struct pp_smumgr *smumgr) return ret; } -static uint8_t cz_translate_firmware_enum_to_arg( +static uint8_t cz_translate_firmware_enum_to_arg(struct pp_smumgr *smumgr, enum cz_scratch_entry firmware_enum) { uint8_t ret = 0; @@ -292,7 +295,10 @@ static uint8_t cz_translate_firmware_enum_to_arg( ret = UCODE_ID_SDMA0; break; case CZ_SCRATCH_ENTRY_UCODE_ID_SDMA1: - ret = UCODE_ID_SDMA1; + if (smumgr->chip_id == CHIP_STONEY) + ret = UCODE_ID_SDMA0; + else + ret = UCODE_ID_SDMA1; break; case CZ_SCRATCH_ENTRY_UCODE_ID_CP_CE: ret = UCODE_ID_CP_CE; @@ -307,7 +313,10 @@ static uint8_t cz_translate_firmware_enum_to_arg( ret = UCODE_ID_CP_MEC_JT1; break; case CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT2: - ret = UCODE_ID_CP_MEC_JT2; + if (smumgr->chip_id == CHIP_STONEY) + ret = UCODE_ID_CP_MEC_JT1; + else + ret = UCODE_ID_CP_MEC_JT2; break; case CZ_SCRATCH_ENTRY_UCODE_ID_GMCON_RENG: ret = UCODE_ID_GMCON_RENG; @@ -396,7 +405,7 @@ static int cz_smu_populate_single_scratch_task( struct SMU_Task *task = &toc->tasks[cz_smu->toc_entry_used_count++]; task->type = type; - task->arg = cz_translate_firmware_enum_to_arg(fw_enum); + task->arg = cz_translate_firmware_enum_to_arg(smumgr, fw_enum); task->next = is_last ? END_OF_TASK_LIST : cz_smu->toc_entry_used_count; for (i = 0; i < cz_smu->scratch_buffer_length; i++) @@ -433,7 +442,7 @@ static int cz_smu_populate_single_ucode_load_task( struct SMU_Task *task = &toc->tasks[cz_smu->toc_entry_used_count++]; task->type = TASK_TYPE_UCODE_LOAD; - task->arg = cz_translate_firmware_enum_to_arg(fw_enum); + task->arg = cz_translate_firmware_enum_to_arg(smumgr, fw_enum); task->next = is_last ? END_OF_TASK_LIST : cz_smu->toc_entry_used_count; for (i = 0; i < cz_smu->driver_buffer_length; i++) @@ -509,8 +518,14 @@ static int cz_smu_construct_toc_for_vddgfx_exit(struct pp_smumgr *smumgr) CZ_SCRATCH_ENTRY_UCODE_ID_CP_ME, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); - cz_smu_populate_single_ucode_load_task(smumgr, + + if (smumgr->chip_id == CHIP_STONEY) + cz_smu_populate_single_ucode_load_task(smumgr, + CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); + else + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT2, false); + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_RLC_G, false); @@ -551,7 +566,11 @@ static int cz_smu_construct_toc_for_bootup(struct pp_smumgr *smumgr) cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_SDMA0, false); - cz_smu_populate_single_ucode_load_task(smumgr, + if (smumgr->chip_id == CHIP_STONEY) + cz_smu_populate_single_ucode_load_task(smumgr, + CZ_SCRATCH_ENTRY_UCODE_ID_SDMA0, false); + else + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_SDMA1, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_CE, false); @@ -561,7 +580,11 @@ static int cz_smu_construct_toc_for_bootup(struct pp_smumgr *smumgr) CZ_SCRATCH_ENTRY_UCODE_ID_CP_ME, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); - cz_smu_populate_single_ucode_load_task(smumgr, + if (smumgr->chip_id == CHIP_STONEY) + cz_smu_populate_single_ucode_load_task(smumgr, + CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT1, false); + else + cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_CP_MEC_JT2, false); cz_smu_populate_single_ucode_load_task(smumgr, CZ_SCRATCH_ENTRY_UCODE_ID_RLC_G, true); @@ -618,7 +641,7 @@ static int cz_smu_populate_firmware_entries(struct pp_smumgr *smumgr) for (i = 0; i < sizeof(firmware_list)/sizeof(*firmware_list); i++) { - firmware_type = cz_translate_firmware_enum_to_arg( + firmware_type = cz_translate_firmware_enum_to_arg(smumgr, firmware_list[i]); ucode_id = cz_convert_fw_type_to_cgs(firmware_type); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 57cccd68ca52..7c523060a076 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -946,9 +946,23 @@ static void wait_for_fences(struct drm_device *dev, } } -static bool framebuffer_changed(struct drm_device *dev, - struct drm_atomic_state *old_state, - struct drm_crtc *crtc) +/** + * drm_atomic_helper_framebuffer_changed - check if framebuffer has changed + * @dev: DRM device + * @old_state: atomic state object with old state structures + * @crtc: DRM crtc + * + * Checks whether the framebuffer used for this CRTC changes as a result of + * the atomic update. This is useful for drivers which cannot use + * drm_atomic_helper_wait_for_vblanks() and need to reimplement its + * functionality. + * + * Returns: + * true if the framebuffer changed. + */ +bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc) { struct drm_plane *plane; struct drm_plane_state *old_plane_state; @@ -965,6 +979,7 @@ static bool framebuffer_changed(struct drm_device *dev, return false; } +EXPORT_SYMBOL(drm_atomic_helper_framebuffer_changed); /** * drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs @@ -999,7 +1014,8 @@ drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, if (old_state->legacy_cursor_update) continue; - if (!framebuffer_changed(dev, old_state, crtc)) + if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) continue; ret = drm_crtc_vblank_get(crtc); diff --git a/drivers/gpu/drm/etnaviv/common.xml.h b/drivers/gpu/drm/etnaviv/common.xml.h index 9e585d51fb78..e881482b5971 100644 --- a/drivers/gpu/drm/etnaviv/common.xml.h +++ b/drivers/gpu/drm/etnaviv/common.xml.h @@ -8,8 +8,8 @@ http://0x04.net/cgit/index.cgi/rules-ng-ng git clone git://0x04.net/rules-ng-ng The rules-ng-ng source files this header was generated from are: -- state_vg.xml ( 5973 bytes, from 2015-03-25 11:26:01) -- common.xml ( 18437 bytes, from 2015-03-25 11:27:41) +- state_hi.xml ( 24309 bytes, from 2015-12-12 09:02:53) +- common.xml ( 18379 bytes, from 2015-12-12 09:02:53) Copyright (C) 2015 */ @@ -30,15 +30,19 @@ Copyright (C) 2015 #define ENDIAN_MODE_NO_SWAP 0x00000000 #define ENDIAN_MODE_SWAP_16 0x00000001 #define ENDIAN_MODE_SWAP_32 0x00000002 +#define chipModel_GC200 0x00000200 #define chipModel_GC300 0x00000300 #define chipModel_GC320 0x00000320 +#define chipModel_GC328 0x00000328 #define chipModel_GC350 0x00000350 #define chipModel_GC355 0x00000355 #define chipModel_GC400 0x00000400 #define chipModel_GC410 0x00000410 #define chipModel_GC420 0x00000420 +#define chipModel_GC428 0x00000428 #define chipModel_GC450 0x00000450 #define chipModel_GC500 0x00000500 +#define chipModel_GC520 0x00000520 #define chipModel_GC530 0x00000530 #define chipModel_GC600 0x00000600 #define chipModel_GC700 0x00000700 @@ -46,9 +50,16 @@ Copyright (C) 2015 #define chipModel_GC860 0x00000860 #define chipModel_GC880 0x00000880 #define chipModel_GC1000 0x00001000 +#define chipModel_GC1500 0x00001500 #define chipModel_GC2000 0x00002000 #define chipModel_GC2100 0x00002100 +#define chipModel_GC2200 0x00002200 +#define chipModel_GC2500 0x00002500 +#define chipModel_GC3000 0x00003000 #define chipModel_GC4000 0x00004000 +#define chipModel_GC5000 0x00005000 +#define chipModel_GC5200 0x00005200 +#define chipModel_GC6400 0x00006400 #define RGBA_BITS_R 0x00000001 #define RGBA_BITS_G 0x00000002 #define RGBA_BITS_B 0x00000004 @@ -160,7 +171,7 @@ Copyright (C) 2015 #define chipMinorFeatures2_UNK8 0x00000100 #define chipMinorFeatures2_UNK9 0x00000200 #define chipMinorFeatures2_UNK10 0x00000400 -#define chipMinorFeatures2_SAMPLERBASE_16 0x00000800 +#define chipMinorFeatures2_HALTI1 0x00000800 #define chipMinorFeatures2_UNK12 0x00001000 #define chipMinorFeatures2_UNK13 0x00002000 #define chipMinorFeatures2_UNK14 0x00004000 @@ -189,7 +200,7 @@ Copyright (C) 2015 #define chipMinorFeatures3_UNK5 0x00000020 #define chipMinorFeatures3_UNK6 0x00000040 #define chipMinorFeatures3_UNK7 0x00000080 -#define chipMinorFeatures3_UNK8 0x00000100 +#define chipMinorFeatures3_FAST_MSAA 0x00000100 #define chipMinorFeatures3_UNK9 0x00000200 #define chipMinorFeatures3_BUG_FIXES10 0x00000400 #define chipMinorFeatures3_UNK11 0x00000800 @@ -199,7 +210,7 @@ Copyright (C) 2015 #define chipMinorFeatures3_UNK15 0x00008000 #define chipMinorFeatures3_UNK16 0x00010000 #define chipMinorFeatures3_UNK17 0x00020000 -#define chipMinorFeatures3_UNK18 0x00040000 +#define chipMinorFeatures3_ACE 0x00040000 #define chipMinorFeatures3_UNK19 0x00080000 #define chipMinorFeatures3_UNK20 0x00100000 #define chipMinorFeatures3_UNK21 0x00200000 @@ -207,7 +218,7 @@ Copyright (C) 2015 #define chipMinorFeatures3_UNK23 0x00800000 #define chipMinorFeatures3_UNK24 0x01000000 #define chipMinorFeatures3_UNK25 0x02000000 -#define chipMinorFeatures3_UNK26 0x04000000 +#define chipMinorFeatures3_NEW_HZ 0x04000000 #define chipMinorFeatures3_UNK27 0x08000000 #define chipMinorFeatures3_UNK28 0x10000000 #define chipMinorFeatures3_UNK29 0x20000000 @@ -229,9 +240,9 @@ Copyright (C) 2015 #define chipMinorFeatures4_UNK13 0x00002000 #define chipMinorFeatures4_UNK14 0x00004000 #define chipMinorFeatures4_UNK15 0x00008000 -#define chipMinorFeatures4_UNK16 0x00010000 +#define chipMinorFeatures4_HALTI2 0x00010000 #define chipMinorFeatures4_UNK17 0x00020000 -#define chipMinorFeatures4_UNK18 0x00040000 +#define chipMinorFeatures4_SMALL_MSAA 0x00040000 #define chipMinorFeatures4_UNK19 0x00080000 #define chipMinorFeatures4_UNK20 0x00100000 #define chipMinorFeatures4_UNK21 0x00200000 @@ -245,5 +256,37 @@ Copyright (C) 2015 #define chipMinorFeatures4_UNK29 0x20000000 #define chipMinorFeatures4_UNK30 0x40000000 #define chipMinorFeatures4_UNK31 0x80000000 +#define chipMinorFeatures5_UNK0 0x00000001 +#define chipMinorFeatures5_UNK1 0x00000002 +#define chipMinorFeatures5_UNK2 0x00000004 +#define chipMinorFeatures5_UNK3 0x00000008 +#define chipMinorFeatures5_UNK4 0x00000010 +#define chipMinorFeatures5_UNK5 0x00000020 +#define chipMinorFeatures5_UNK6 0x00000040 +#define chipMinorFeatures5_UNK7 0x00000080 +#define chipMinorFeatures5_UNK8 0x00000100 +#define chipMinorFeatures5_HALTI3 0x00000200 +#define chipMinorFeatures5_UNK10 0x00000400 +#define chipMinorFeatures5_UNK11 0x00000800 +#define chipMinorFeatures5_UNK12 0x00001000 +#define chipMinorFeatures5_UNK13 0x00002000 +#define chipMinorFeatures5_UNK14 0x00004000 +#define chipMinorFeatures5_UNK15 0x00008000 +#define chipMinorFeatures5_UNK16 0x00010000 +#define chipMinorFeatures5_UNK17 0x00020000 +#define chipMinorFeatures5_UNK18 0x00040000 +#define chipMinorFeatures5_UNK19 0x00080000 +#define chipMinorFeatures5_UNK20 0x00100000 +#define chipMinorFeatures5_UNK21 0x00200000 +#define chipMinorFeatures5_UNK22 0x00400000 +#define chipMinorFeatures5_UNK23 0x00800000 +#define chipMinorFeatures5_UNK24 0x01000000 +#define chipMinorFeatures5_UNK25 0x02000000 +#define chipMinorFeatures5_UNK26 0x04000000 +#define chipMinorFeatures5_UNK27 0x08000000 +#define chipMinorFeatures5_UNK28 0x10000000 +#define chipMinorFeatures5_UNK29 0x20000000 +#define chipMinorFeatures5_UNK30 0x40000000 +#define chipMinorFeatures5_UNK31 0x80000000 #endif /* COMMON_XML */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 5c89ebb52fd2..e8858985f01e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -668,7 +668,6 @@ static struct platform_driver etnaviv_platform_driver = { .probe = etnaviv_pdev_probe, .remove = etnaviv_pdev_remove, .driver = { - .owner = THIS_MODULE, .name = "etnaviv", .of_match_table = dt_match, }, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h index d6bd438bd5be..1cd6046e76b1 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h @@ -85,7 +85,7 @@ struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); int etnaviv_gem_prime_pin(struct drm_gem_object *obj); void etnaviv_gem_prime_unpin(struct drm_gem_object *obj); -void *etnaviv_gem_vaddr(struct drm_gem_object *obj); +void *etnaviv_gem_vmap(struct drm_gem_object *obj); int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, struct timespec *timeout); int etnaviv_gem_cpu_fini(struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index bf8fa859e8be..4a29eeadbf1e 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -201,7 +201,9 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) obj = vram->object; + mutex_lock(&obj->lock); pages = etnaviv_gem_get_pages(obj); + mutex_unlock(&obj->lock); if (pages) { int j; @@ -213,8 +215,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) iter.hdr->iova = cpu_to_le64(vram->iova); - vaddr = etnaviv_gem_vaddr(&obj->base); - if (vaddr && !IS_ERR(vaddr)) + vaddr = etnaviv_gem_vmap(&obj->base); + if (vaddr) memcpy(iter.data, vaddr, obj->base.size); etnaviv_core_dump_header(&iter, ETDUMP_BUF_BO, iter.data + diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 9f77c3b94cc6..4b519e4309b2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -353,25 +353,39 @@ void etnaviv_gem_put_iova(struct etnaviv_gpu *gpu, struct drm_gem_object *obj) drm_gem_object_unreference_unlocked(obj); } -void *etnaviv_gem_vaddr(struct drm_gem_object *obj) +void *etnaviv_gem_vmap(struct drm_gem_object *obj) { struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj); - mutex_lock(&etnaviv_obj->lock); - if (!etnaviv_obj->vaddr) { - struct page **pages = etnaviv_gem_get_pages(etnaviv_obj); - - if (IS_ERR(pages)) - return ERR_CAST(pages); + if (etnaviv_obj->vaddr) + return etnaviv_obj->vaddr; - etnaviv_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT, - VM_MAP, pgprot_writecombine(PAGE_KERNEL)); - } + mutex_lock(&etnaviv_obj->lock); + /* + * Need to check again, as we might have raced with another thread + * while waiting for the mutex. + */ + if (!etnaviv_obj->vaddr) + etnaviv_obj->vaddr = etnaviv_obj->ops->vmap(etnaviv_obj); mutex_unlock(&etnaviv_obj->lock); return etnaviv_obj->vaddr; } +static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) +{ + struct page **pages; + + lockdep_assert_held(&obj->lock); + + pages = etnaviv_gem_get_pages(obj); + if (IS_ERR(pages)) + return NULL; + + return vmap(pages, obj->base.size >> PAGE_SHIFT, + VM_MAP, pgprot_writecombine(PAGE_KERNEL)); +} + static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op) { if (op & ETNA_PREP_READ) @@ -522,6 +536,7 @@ static void etnaviv_gem_shmem_release(struct etnaviv_gem_object *etnaviv_obj) static const struct etnaviv_gem_ops etnaviv_gem_shmem_ops = { .get_pages = etnaviv_gem_shmem_get_pages, .release = etnaviv_gem_shmem_release, + .vmap = etnaviv_gem_vmap_impl, }; void etnaviv_gem_free_object(struct drm_gem_object *obj) @@ -866,6 +881,7 @@ static void etnaviv_gem_userptr_release(struct etnaviv_gem_object *etnaviv_obj) static const struct etnaviv_gem_ops etnaviv_gem_userptr_ops = { .get_pages = etnaviv_gem_userptr_get_pages, .release = etnaviv_gem_userptr_release, + .vmap = etnaviv_gem_vmap_impl, }; int etnaviv_gem_new_userptr(struct drm_device *dev, struct drm_file *file, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h index a300b4b3d545..ab5df8147a5f 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h @@ -78,6 +78,7 @@ struct etnaviv_gem_object *to_etnaviv_bo(struct drm_gem_object *obj) struct etnaviv_gem_ops { int (*get_pages)(struct etnaviv_gem_object *); void (*release)(struct etnaviv_gem_object *); + void *(*vmap)(struct etnaviv_gem_object *); }; static inline bool is_active(struct etnaviv_gem_object *etnaviv_obj) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index e94db4f95770..4e67395f5fa1 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -31,7 +31,7 @@ struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj) void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj) { - return etnaviv_gem_vaddr(obj); + return etnaviv_gem_vmap(obj); } void etnaviv_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) @@ -77,9 +77,17 @@ static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj) drm_prime_gem_destroy(&etnaviv_obj->base, etnaviv_obj->sgt); } +static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj) +{ + lockdep_assert_held(&etnaviv_obj->lock); + + return dma_buf_vmap(etnaviv_obj->base.import_attach->dmabuf); +} + static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = { /* .get_pages should never be called */ .release = etnaviv_gem_prime_release, + .vmap = etnaviv_gem_prime_vmap_impl, }; struct drm_gem_object *etnaviv_gem_prime_import_sg_table(struct drm_device *dev, diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 056a72e6ed26..a33162cf4f4c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -72,6 +72,14 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.minor_features3; break; + case ETNAVIV_PARAM_GPU_FEATURES_5: + *value = gpu->identity.minor_features4; + break; + + case ETNAVIV_PARAM_GPU_FEATURES_6: + *value = gpu->identity.minor_features5; + break; + case ETNAVIV_PARAM_GPU_STREAM_COUNT: *value = gpu->identity.stream_count; break; @@ -112,6 +120,10 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.num_constants; break; + case ETNAVIV_PARAM_GPU_NUM_VARYINGS: + *value = gpu->identity.varyings_count; + break; + default: DBG("%s: invalid param: %u", dev_name(gpu->dev), param); return -EINVAL; @@ -120,46 +132,56 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) return 0; } + +#define etnaviv_is_model_rev(gpu, mod, rev) \ + ((gpu)->identity.model == chipModel_##mod && \ + (gpu)->identity.revision == rev) +#define etnaviv_field(val, field) \ + (((val) & field##__MASK) >> field##__SHIFT) + static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) { if (gpu->identity.minor_features0 & chipMinorFeatures0_MORE_MINOR_FEATURES) { - u32 specs[2]; + u32 specs[4]; + unsigned int streams; specs[0] = gpu_read(gpu, VIVS_HI_CHIP_SPECS); specs[1] = gpu_read(gpu, VIVS_HI_CHIP_SPECS_2); - - gpu->identity.stream_count = - (specs[0] & VIVS_HI_CHIP_SPECS_STREAM_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_STREAM_COUNT__SHIFT; - gpu->identity.register_max = - (specs[0] & VIVS_HI_CHIP_SPECS_REGISTER_MAX__MASK) - >> VIVS_HI_CHIP_SPECS_REGISTER_MAX__SHIFT; - gpu->identity.thread_count = - (specs[0] & VIVS_HI_CHIP_SPECS_THREAD_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_THREAD_COUNT__SHIFT; - gpu->identity.vertex_cache_size = - (specs[0] & VIVS_HI_CHIP_SPECS_VERTEX_CACHE_SIZE__MASK) - >> VIVS_HI_CHIP_SPECS_VERTEX_CACHE_SIZE__SHIFT; - gpu->identity.shader_core_count = - (specs[0] & VIVS_HI_CHIP_SPECS_SHADER_CORE_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_SHADER_CORE_COUNT__SHIFT; - gpu->identity.pixel_pipes = - (specs[0] & VIVS_HI_CHIP_SPECS_PIXEL_PIPES__MASK) - >> VIVS_HI_CHIP_SPECS_PIXEL_PIPES__SHIFT; + specs[2] = gpu_read(gpu, VIVS_HI_CHIP_SPECS_3); + specs[3] = gpu_read(gpu, VIVS_HI_CHIP_SPECS_4); + + gpu->identity.stream_count = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_STREAM_COUNT); + gpu->identity.register_max = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_REGISTER_MAX); + gpu->identity.thread_count = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_THREAD_COUNT); + gpu->identity.vertex_cache_size = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_VERTEX_CACHE_SIZE); + gpu->identity.shader_core_count = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_SHADER_CORE_COUNT); + gpu->identity.pixel_pipes = etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_PIXEL_PIPES); gpu->identity.vertex_output_buffer_size = - (specs[0] & VIVS_HI_CHIP_SPECS_VERTEX_OUTPUT_BUFFER_SIZE__MASK) - >> VIVS_HI_CHIP_SPECS_VERTEX_OUTPUT_BUFFER_SIZE__SHIFT; - - gpu->identity.buffer_size = - (specs[1] & VIVS_HI_CHIP_SPECS_2_BUFFER_SIZE__MASK) - >> VIVS_HI_CHIP_SPECS_2_BUFFER_SIZE__SHIFT; - gpu->identity.instruction_count = - (specs[1] & VIVS_HI_CHIP_SPECS_2_INSTRUCTION_COUNT__MASK) - >> VIVS_HI_CHIP_SPECS_2_INSTRUCTION_COUNT__SHIFT; - gpu->identity.num_constants = - (specs[1] & VIVS_HI_CHIP_SPECS_2_NUM_CONSTANTS__MASK) - >> VIVS_HI_CHIP_SPECS_2_NUM_CONSTANTS__SHIFT; + etnaviv_field(specs[0], + VIVS_HI_CHIP_SPECS_VERTEX_OUTPUT_BUFFER_SIZE); + + gpu->identity.buffer_size = etnaviv_field(specs[1], + VIVS_HI_CHIP_SPECS_2_BUFFER_SIZE); + gpu->identity.instruction_count = etnaviv_field(specs[1], + VIVS_HI_CHIP_SPECS_2_INSTRUCTION_COUNT); + gpu->identity.num_constants = etnaviv_field(specs[1], + VIVS_HI_CHIP_SPECS_2_NUM_CONSTANTS); + + gpu->identity.varyings_count = etnaviv_field(specs[2], + VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT); + + /* This overrides the value from older register if non-zero */ + streams = etnaviv_field(specs[3], + VIVS_HI_CHIP_SPECS_4_STREAM_COUNT); + if (streams) + gpu->identity.stream_count = streams; } /* Fill in the stream count if not specified */ @@ -173,7 +195,7 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) /* Convert the register max value */ if (gpu->identity.register_max) gpu->identity.register_max = 1 << gpu->identity.register_max; - else if (gpu->identity.model == 0x0400) + else if (gpu->identity.model == chipModel_GC400) gpu->identity.register_max = 32; else gpu->identity.register_max = 64; @@ -181,10 +203,10 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) /* Convert thread count */ if (gpu->identity.thread_count) gpu->identity.thread_count = 1 << gpu->identity.thread_count; - else if (gpu->identity.model == 0x0400) + else if (gpu->identity.model == chipModel_GC400) gpu->identity.thread_count = 64; - else if (gpu->identity.model == 0x0500 || - gpu->identity.model == 0x0530) + else if (gpu->identity.model == chipModel_GC500 || + gpu->identity.model == chipModel_GC530) gpu->identity.thread_count = 128; else gpu->identity.thread_count = 256; @@ -206,7 +228,7 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) if (gpu->identity.vertex_output_buffer_size) { gpu->identity.vertex_output_buffer_size = 1 << gpu->identity.vertex_output_buffer_size; - } else if (gpu->identity.model == 0x0400) { + } else if (gpu->identity.model == chipModel_GC400) { if (gpu->identity.revision < 0x4000) gpu->identity.vertex_output_buffer_size = 512; else if (gpu->identity.revision < 0x4200) @@ -219,9 +241,8 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) switch (gpu->identity.instruction_count) { case 0: - if ((gpu->identity.model == 0x2000 && - gpu->identity.revision == 0x5108) || - gpu->identity.model == 0x880) + if (etnaviv_is_model_rev(gpu, GC2000, 0x5108) || + gpu->identity.model == chipModel_GC880) gpu->identity.instruction_count = 512; else gpu->identity.instruction_count = 256; @@ -242,6 +263,30 @@ static void etnaviv_hw_specs(struct etnaviv_gpu *gpu) if (gpu->identity.num_constants == 0) gpu->identity.num_constants = 168; + + if (gpu->identity.varyings_count == 0) { + if (gpu->identity.minor_features1 & chipMinorFeatures1_HALTI0) + gpu->identity.varyings_count = 12; + else + gpu->identity.varyings_count = 8; + } + + /* + * For some cores, two varyings are consumed for position, so the + * maximum varying count needs to be reduced by one. + */ + if (etnaviv_is_model_rev(gpu, GC5000, 0x5434) || + etnaviv_is_model_rev(gpu, GC4000, 0x5222) || + etnaviv_is_model_rev(gpu, GC4000, 0x5245) || + etnaviv_is_model_rev(gpu, GC4000, 0x5208) || + etnaviv_is_model_rev(gpu, GC3000, 0x5435) || + etnaviv_is_model_rev(gpu, GC2200, 0x5244) || + etnaviv_is_model_rev(gpu, GC2100, 0x5108) || + etnaviv_is_model_rev(gpu, GC2000, 0x5108) || + etnaviv_is_model_rev(gpu, GC1500, 0x5246) || + etnaviv_is_model_rev(gpu, GC880, 0x5107) || + etnaviv_is_model_rev(gpu, GC880, 0x5106)) + gpu->identity.varyings_count -= 1; } static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) @@ -251,12 +296,10 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) chipIdentity = gpu_read(gpu, VIVS_HI_CHIP_IDENTITY); /* Special case for older graphic cores. */ - if (((chipIdentity & VIVS_HI_CHIP_IDENTITY_FAMILY__MASK) - >> VIVS_HI_CHIP_IDENTITY_FAMILY__SHIFT) == 0x01) { - gpu->identity.model = 0x500; /* gc500 */ - gpu->identity.revision = - (chipIdentity & VIVS_HI_CHIP_IDENTITY_REVISION__MASK) - >> VIVS_HI_CHIP_IDENTITY_REVISION__SHIFT; + if (etnaviv_field(chipIdentity, VIVS_HI_CHIP_IDENTITY_FAMILY) == 0x01) { + gpu->identity.model = chipModel_GC500; + gpu->identity.revision = etnaviv_field(chipIdentity, + VIVS_HI_CHIP_IDENTITY_REVISION); } else { gpu->identity.model = gpu_read(gpu, VIVS_HI_CHIP_MODEL); @@ -269,13 +312,12 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) * same. Only for GC400 family. */ if ((gpu->identity.model & 0xff00) == 0x0400 && - gpu->identity.model != 0x0420) { + gpu->identity.model != chipModel_GC420) { gpu->identity.model = gpu->identity.model & 0x0400; } /* Another special case */ - if (gpu->identity.model == 0x300 && - gpu->identity.revision == 0x2201) { + if (etnaviv_is_model_rev(gpu, GC300, 0x2201)) { u32 chipDate = gpu_read(gpu, VIVS_HI_CHIP_DATE); u32 chipTime = gpu_read(gpu, VIVS_HI_CHIP_TIME); @@ -295,11 +337,13 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.features = gpu_read(gpu, VIVS_HI_CHIP_FEATURE); /* Disable fast clear on GC700. */ - if (gpu->identity.model == 0x700) + if (gpu->identity.model == chipModel_GC700) gpu->identity.features &= ~chipFeatures_FAST_CLEAR; - if ((gpu->identity.model == 0x500 && gpu->identity.revision < 2) || - (gpu->identity.model == 0x300 && gpu->identity.revision < 0x2000)) { + if ((gpu->identity.model == chipModel_GC500 && + gpu->identity.revision < 2) || + (gpu->identity.model == chipModel_GC300 && + gpu->identity.revision < 0x2000)) { /* * GC500 rev 1.x and GC300 rev < 2.0 doesn't have these @@ -309,6 +353,8 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu->identity.minor_features1 = 0; gpu->identity.minor_features2 = 0; gpu->identity.minor_features3 = 0; + gpu->identity.minor_features4 = 0; + gpu->identity.minor_features5 = 0; } else gpu->identity.minor_features0 = gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_0); @@ -321,6 +367,10 @@ static void etnaviv_hw_identify(struct etnaviv_gpu *gpu) gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_2); gpu->identity.minor_features3 = gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_3); + gpu->identity.minor_features4 = + gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_4); + gpu->identity.minor_features5 = + gpu_read(gpu, VIVS_HI_CHIP_MINOR_FEATURE_5); } /* GC600 idle register reports zero bits where modules aren't present */ @@ -441,10 +491,9 @@ static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) { u16 prefetch; - if (gpu->identity.model == chipModel_GC320 && - gpu_read(gpu, VIVS_HI_CHIP_TIME) != 0x2062400 && - (gpu->identity.revision == 0x5007 || - gpu->identity.revision == 0x5220)) { + if ((etnaviv_is_model_rev(gpu, GC320, 0x5007) || + etnaviv_is_model_rev(gpu, GC320, 0x5220)) && + gpu_read(gpu, VIVS_HI_CHIP_TIME) != 0x2062400) { u32 mc_memory_debug; mc_memory_debug = gpu_read(gpu, VIVS_MC_DEBUG_MEMORY) & ~0xff; @@ -466,7 +515,7 @@ static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) VIVS_HI_AXI_CONFIG_ARCACHE(2)); /* GC2000 rev 5108 needs a special bus config */ - if (gpu->identity.model == 0x2000 && gpu->identity.revision == 0x5108) { + if (etnaviv_is_model_rev(gpu, GC2000, 0x5108)) { u32 bus_config = gpu_read(gpu, VIVS_MC_BUS_CONFIG); bus_config &= ~(VIVS_MC_BUS_CONFIG_FE_BUS_CONFIG__MASK | VIVS_MC_BUS_CONFIG_TX_BUS_CONFIG__MASK); @@ -511,8 +560,16 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) if (gpu->identity.model == 0) { dev_err(gpu->dev, "Unknown GPU model\n"); - pm_runtime_put_autosuspend(gpu->dev); - return -ENXIO; + ret = -ENXIO; + goto fail; + } + + /* Exclude VG cores with FE2.0 */ + if (gpu->identity.features & chipFeatures_PIPE_VG && + gpu->identity.features & chipFeatures_FE20) { + dev_info(gpu->dev, "Ignoring GPU with VG and FE2.0\n"); + ret = -ENXIO; + goto fail; } ret = etnaviv_hw_reset(gpu); @@ -539,10 +596,9 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) goto fail; } - /* TODO: we will leak here memory - fix it! */ - gpu->mmu = etnaviv_iommu_new(gpu, iommu, version); if (!gpu->mmu) { + iommu_domain_free(iommu); ret = -ENOMEM; goto fail; } @@ -552,7 +608,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) if (!gpu->buffer) { ret = -ENOMEM; dev_err(gpu->dev, "could not create command buffer\n"); - goto fail; + goto destroy_iommu; } if (gpu->buffer->paddr - gpu->memory_base > 0x80000000) { ret = -EINVAL; @@ -582,6 +638,9 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) free_buffer: etnaviv_gpu_cmdbuf_free(gpu->buffer); gpu->buffer = NULL; +destroy_iommu: + etnaviv_iommu_destroy(gpu->mmu); + gpu->mmu = NULL; fail: pm_runtime_mark_last_busy(gpu->dev); pm_runtime_put_autosuspend(gpu->dev); @@ -642,6 +701,10 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m) gpu->identity.minor_features2); seq_printf(m, "\t minor_features3: 0x%08x\n", gpu->identity.minor_features3); + seq_printf(m, "\t minor_features4: 0x%08x\n", + gpu->identity.minor_features4); + seq_printf(m, "\t minor_features5: 0x%08x\n", + gpu->identity.minor_features5); seq_puts(m, "\tspecs\n"); seq_printf(m, "\t stream_count: %d\n", @@ -664,6 +727,8 @@ int etnaviv_gpu_debugfs(struct etnaviv_gpu *gpu, struct seq_file *m) gpu->identity.instruction_count); seq_printf(m, "\t num_constants: %d\n", gpu->identity.num_constants); + seq_printf(m, "\t varyings_count: %d\n", + gpu->identity.varyings_count); seq_printf(m, "\taxi: 0x%08x\n", axi); seq_printf(m, "\tidle: 0x%08x\n", idle); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index c75d50359ab0..f233ac4c7c1c 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -46,6 +46,12 @@ struct etnaviv_chip_identity { /* Supported minor feature 3 fields. */ u32 minor_features3; + /* Supported minor feature 4 fields. */ + u32 minor_features4; + + /* Supported minor feature 5 fields. */ + u32 minor_features5; + /* Number of streams supported. */ u32 stream_count; @@ -75,6 +81,9 @@ struct etnaviv_chip_identity { /* Buffer size */ u32 buffer_size; + + /* Number of varyings */ + u8 varyings_count; }; struct etnaviv_event { diff --git a/drivers/gpu/drm/etnaviv/state_hi.xml.h b/drivers/gpu/drm/etnaviv/state_hi.xml.h index 0064f2640396..6a7de5f1454a 100644 --- a/drivers/gpu/drm/etnaviv/state_hi.xml.h +++ b/drivers/gpu/drm/etnaviv/state_hi.xml.h @@ -8,8 +8,8 @@ http://0x04.net/cgit/index.cgi/rules-ng-ng git clone git://0x04.net/rules-ng-ng The rules-ng-ng source files this header was generated from are: -- state_hi.xml ( 23420 bytes, from 2015-03-25 11:47:21) -- common.xml ( 18437 bytes, from 2015-03-25 11:27:41) +- state_hi.xml ( 24309 bytes, from 2015-12-12 09:02:53) +- common.xml ( 18437 bytes, from 2015-12-12 09:02:53) Copyright (C) 2015 */ @@ -182,8 +182,25 @@ Copyright (C) 2015 #define VIVS_HI_CHIP_MINOR_FEATURE_3 0x00000088 +#define VIVS_HI_CHIP_SPECS_3 0x0000008c +#define VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__MASK 0x000001f0 +#define VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__SHIFT 4 +#define VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT(x) (((x) << VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__SHIFT) & VIVS_HI_CHIP_SPECS_3_VARYINGS_COUNT__MASK) +#define VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__MASK 0x00000007 +#define VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__SHIFT 0 +#define VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT(x) (((x) << VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__SHIFT) & VIVS_HI_CHIP_SPECS_3_GPU_CORE_COUNT__MASK) + #define VIVS_HI_CHIP_MINOR_FEATURE_4 0x00000094 +#define VIVS_HI_CHIP_SPECS_4 0x0000009c +#define VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__MASK 0x0001f000 +#define VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__SHIFT 12 +#define VIVS_HI_CHIP_SPECS_4_STREAM_COUNT(x) (((x) << VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__SHIFT) & VIVS_HI_CHIP_SPECS_4_STREAM_COUNT__MASK) + +#define VIVS_HI_CHIP_MINOR_FEATURE_5 0x000000a0 + +#define VIVS_HI_CHIP_PRODUCT_ID 0x000000a8 + #define VIVS_PM 0x00000000 #define VIVS_PM_POWER_CONTROLS 0x00000100 @@ -206,6 +223,11 @@ Copyright (C) 2015 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_FE 0x00000001 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_DE 0x00000002 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_PE 0x00000004 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_SH 0x00000008 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_PA 0x00000010 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_SE 0x00000020 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_RA 0x00000040 +#define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_TX 0x00000080 #define VIVS_PM_PULSE_EATER 0x0000010c diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 6bfc46369db1..367a916f364e 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -304,18 +304,10 @@ void dce6_dp_audio_set_dto(struct radeon_device *rdev, unsigned int div = (RREG32(DENTIST_DISPCLK_CNTL) & DENTIST_DPREFCLK_WDIVIDER_MASK) >> DENTIST_DPREFCLK_WDIVIDER_SHIFT; - - if (div < 128 && div >= 96) - div -= 64; - else if (div >= 64) - div = div / 2 - 16; - else if (div >= 8) - div /= 4; - else - div = 0; + div = radeon_audio_decode_dfs_div(div); if (div) - clock = rdev->clock.gpupll_outputfreq * 10 / div; + clock = clock * 100 / div; WREG32(DCE8_DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCE8_DCCG_AUDIO_DTO1_MODULE, clock); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 9953356fe263..3cf04a2f44bb 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -289,6 +289,16 @@ void dce4_dp_audio_set_dto(struct radeon_device *rdev, * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ + if (ASIC_IS_DCE41(rdev)) { + unsigned int div = (RREG32(DCE41_DENTIST_DISPCLK_CNTL) & + DENTIST_DPREFCLK_WDIVIDER_MASK) >> + DENTIST_DPREFCLK_WDIVIDER_SHIFT; + div = radeon_audio_decode_dfs_div(div); + + if (div) + clock = 100 * clock / div; + } + WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); WREG32(DCCG_AUDIO_DTO1_MODULE, clock); } diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 4aa5f755572b..13b6029d65cc 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -511,6 +511,11 @@ #define DCCG_AUDIO_DTO1_CNTL 0x05cc # define DCCG_AUDIO_DTO1_USE_512FBR_DTO (1 << 3) +#define DCE41_DENTIST_DISPCLK_CNTL 0x049c +# define DENTIST_DPREFCLK_WDIVIDER(x) (((x) & 0x7f) << 24) +# define DENTIST_DPREFCLK_WDIVIDER_MASK (0x7f << 24) +# define DENTIST_DPREFCLK_WDIVIDER_SHIFT 24 + /* DCE 4.0 AFMT */ #define HDMI_CONTROL 0x7030 # define HDMI_KEEPOUT_MODE (1 << 0) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 5ae6db98aa4d..78a51b3eda10 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -268,7 +268,7 @@ struct radeon_clock { uint32_t current_dispclk; uint32_t dp_extclk; uint32_t max_pixel_clock; - uint32_t gpupll_outputfreq; + uint32_t vco_freq; }; /* diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 08fc1b5effa8..de9a2ffcf5f7 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -1106,6 +1106,31 @@ union firmware_info { ATOM_FIRMWARE_INFO_V2_2 info_22; }; +union igp_info { + struct _ATOM_INTEGRATED_SYSTEM_INFO info; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; + struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; +}; + +static void radeon_atombios_get_dentist_vco_freq(struct radeon_device *rdev) +{ + struct radeon_mode_info *mode_info = &rdev->mode_info; + int index = GetIndexIntoMasterTable(DATA, IntegratedSystemInfo); + union igp_info *igp_info; + u8 frev, crev; + u16 data_offset; + + if (atom_parse_data_header(mode_info->atom_context, index, NULL, + &frev, &crev, &data_offset)) { + igp_info = (union igp_info *)(mode_info->atom_context->bios + + data_offset); + rdev->clock.vco_freq = + le32_to_cpu(igp_info->info_6.ulDentistVCOFreq); + } +} + bool radeon_atom_get_clock_info(struct drm_device *dev) { struct radeon_device *rdev = dev->dev_private; @@ -1257,12 +1282,18 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) rdev->mode_info.firmware_flags = le16_to_cpu(firmware_info->info.usFirmwareCapability.susAccess); - if (ASIC_IS_DCE8(rdev)) { - rdev->clock.gpupll_outputfreq = + if (ASIC_IS_DCE8(rdev)) + rdev->clock.vco_freq = le32_to_cpu(firmware_info->info_22.ulGPUPLL_OutputFreq); - if (rdev->clock.gpupll_outputfreq == 0) - rdev->clock.gpupll_outputfreq = 360000; /* 3.6 GHz */ - } + else if (ASIC_IS_DCE5(rdev)) + rdev->clock.vco_freq = rdev->clock.current_dispclk; + else if (ASIC_IS_DCE41(rdev)) + radeon_atombios_get_dentist_vco_freq(rdev); + else + rdev->clock.vco_freq = rdev->clock.current_dispclk; + + if (rdev->clock.vco_freq == 0) + rdev->clock.vco_freq = 360000; /* 3.6 GHz */ return true; } @@ -1270,14 +1301,6 @@ bool radeon_atom_get_clock_info(struct drm_device *dev) return false; } -union igp_info { - struct _ATOM_INTEGRATED_SYSTEM_INFO info; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V2 info_2; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V6 info_6; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_7 info_7; - struct _ATOM_INTEGRATED_SYSTEM_INFO_V1_8 info_8; -}; - bool radeon_atombios_sideport_present(struct radeon_device *rdev) { struct radeon_mode_info *mode_info = &rdev->mode_info; diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index 2c02e99b5f95..b214663b370d 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.c +++ b/drivers/gpu/drm/radeon/radeon_audio.c @@ -739,9 +739,6 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_connector *radeon_connector = to_radeon_connector(connector); - struct radeon_connector_atom_dig *dig_connector = - radeon_connector->con_priv; if (!dig || !dig->afmt) return; @@ -753,10 +750,7 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder, radeon_audio_write_speaker_allocation(encoder); radeon_audio_write_sad_regs(encoder); radeon_audio_write_latency_fields(encoder, mode); - if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev)) - radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10); - else - radeon_audio_set_dto(encoder, dig_connector->dp_clock); + radeon_audio_set_dto(encoder, rdev->clock.vco_freq * 10); radeon_audio_set_audio_packet(encoder); radeon_audio_select_pin(encoder); @@ -781,3 +775,15 @@ void radeon_audio_dpms(struct drm_encoder *encoder, int mode) if (radeon_encoder->audio && radeon_encoder->audio->dpms) radeon_encoder->audio->dpms(encoder, mode == DRM_MODE_DPMS_ON); } + +unsigned int radeon_audio_decode_dfs_div(unsigned int div) +{ + if (div >= 8 && div < 64) + return (div - 8) * 25 + 200; + else if (div >= 64 && div < 96) + return (div - 64) * 50 + 1600; + else if (div >= 96 && div < 128) + return (div - 96) * 100 + 3200; + else + return 0; +} diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h index 059cc3012062..5c70cceaa4a6 100644 --- a/drivers/gpu/drm/radeon/radeon_audio.h +++ b/drivers/gpu/drm/radeon/radeon_audio.h @@ -79,5 +79,6 @@ void radeon_audio_fini(struct radeon_device *rdev); void radeon_audio_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode); void radeon_audio_dpms(struct drm_encoder *encoder, int mode); +unsigned int radeon_audio_decode_dfs_div(unsigned int div); #endif diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index b3bb92368ae0..298ea1c453c3 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1670,8 +1670,10 @@ int radeon_modeset_init(struct radeon_device *rdev) /* setup afmt */ radeon_afmt_init(rdev); - radeon_fbdev_init(rdev); - drm_kms_helper_poll_init(rdev->ddev); + if (!list_empty(&rdev->ddev->mode_config.connector_list)) { + radeon_fbdev_init(rdev); + drm_kms_helper_poll_init(rdev->ddev); + } /* do pm late init */ ret = radeon_pm_late_init(rdev); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 3dcc5733ff69..e26c963f2e93 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -663,6 +663,7 @@ int radeon_gem_va_ioctl(struct drm_device *dev, void *data, bo_va = radeon_vm_bo_find(&fpriv->vm, rbo); if (!bo_va) { args->operation = RADEON_VA_RESULT_ERROR; + radeon_bo_unreserve(rbo); drm_gem_object_unreference_unlocked(gobj); return -ENOENT; } diff --git a/drivers/gpu/drm/radeon/vce_v1_0.c b/drivers/gpu/drm/radeon/vce_v1_0.c index 07a0d378e122..a01efe39a820 100644 --- a/drivers/gpu/drm/radeon/vce_v1_0.c +++ b/drivers/gpu/drm/radeon/vce_v1_0.c @@ -178,12 +178,12 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) return -EINVAL; } - for (i = 0; i < sign->num; ++i) { - if (sign->val[i].chip_id == chip_id) + for (i = 0; i < le32_to_cpu(sign->num); ++i) { + if (le32_to_cpu(sign->val[i].chip_id) == chip_id) break; } - if (i == sign->num) + if (i == le32_to_cpu(sign->num)) return -EINVAL; data += (256 - 64) / 4; @@ -191,18 +191,18 @@ int vce_v1_0_load_fw(struct radeon_device *rdev, uint32_t *data) data[1] = sign->val[i].nonce[1]; data[2] = sign->val[i].nonce[2]; data[3] = sign->val[i].nonce[3]; - data[4] = sign->len + 64; + data[4] = cpu_to_le32(le32_to_cpu(sign->len) + 64); memset(&data[5], 0, 44); memcpy(&data[16], &sign[1], rdev->vce_fw->size - sizeof(*sign)); - data += data[4] / 4; + data += le32_to_cpu(data[4]) / 4; data[0] = sign->val[i].sigval[0]; data[1] = sign->val[i].sigval[1]; data[2] = sign->val[i].sigval[2]; data[3] = sign->val[i].sigval[3]; - rdev->vce.keyselect = sign->val[i].keyselect; + rdev->vce.keyselect = le32_to_cpu(sign->val[i].keyselect); return 0; } diff --git a/drivers/gpu/drm/rockchip/Makefile b/drivers/gpu/drm/rockchip/Makefile index d1dc0f7b01db..f6a809afceec 100644 --- a/drivers/gpu/drm/rockchip/Makefile +++ b/drivers/gpu/drm/rockchip/Makefile @@ -2,11 +2,11 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. -rockchipdrm-y := rockchip_drm_drv.o rockchip_drm_fb.o rockchip_drm_fbdev.o \ - rockchip_drm_gem.o +rockchipdrm-y := rockchip_drm_drv.o rockchip_drm_fb.o \ + rockchip_drm_gem.o rockchip_drm_vop.o +rockchipdrm-$(CONFIG_DRM_FBDEV_EMULATION) += rockchip_drm_fbdev.o obj-$(CONFIG_ROCKCHIP_DW_HDMI) += dw_hdmi-rockchip.o obj-$(CONFIG_ROCKCHIP_DW_MIPI_DSI) += dw-mipi-dsi.o -obj-$(CONFIG_DRM_ROCKCHIP) += rockchipdrm.o rockchip_drm_vop.o \ - rockchip_vop_reg.o +obj-$(CONFIG_DRM_ROCKCHIP) += rockchipdrm.o rockchip_vop_reg.o diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c index 7bfe243c6173..f8f8f29fb7c3 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c @@ -461,10 +461,11 @@ static int dw_mipi_dsi_phy_init(struct dw_mipi_dsi *dsi) static int dw_mipi_dsi_get_lane_bps(struct dw_mipi_dsi *dsi) { - unsigned int bpp, i, pre; + unsigned int i, pre; unsigned long mpclk, pllref, tmp; unsigned int m = 1, n = 1, target_mbps = 1000; unsigned int max_mbps = dptdin_map[ARRAY_SIZE(dptdin_map) - 1].max_mbps; + int bpp; bpp = mipi_dsi_pixel_format_to_bpp(dsi->format); if (bpp < 0) { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 8397d1b62ef9..a0d51ccb6ea4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -55,14 +55,12 @@ int rockchip_drm_dma_attach_device(struct drm_device *drm_dev, return arm_iommu_attach_device(dev, mapping); } -EXPORT_SYMBOL_GPL(rockchip_drm_dma_attach_device); void rockchip_drm_dma_detach_device(struct drm_device *drm_dev, struct device *dev) { arm_iommu_detach_device(dev); } -EXPORT_SYMBOL_GPL(rockchip_drm_dma_detach_device); int rockchip_register_crtc_funcs(struct drm_crtc *crtc, const struct rockchip_crtc_funcs *crtc_funcs) @@ -77,7 +75,6 @@ int rockchip_register_crtc_funcs(struct drm_crtc *crtc, return 0; } -EXPORT_SYMBOL_GPL(rockchip_register_crtc_funcs); void rockchip_unregister_crtc_funcs(struct drm_crtc *crtc) { @@ -89,7 +86,6 @@ void rockchip_unregister_crtc_funcs(struct drm_crtc *crtc) priv->crtc_funcs[pipe] = NULL; } -EXPORT_SYMBOL_GPL(rockchip_unregister_crtc_funcs); static struct drm_crtc *rockchip_crtc_from_pipe(struct drm_device *drm, int pipe) diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c index f7844883cb76..3b8f652698f8 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -39,7 +39,6 @@ struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb, return rk_fb->obj[plane]; } -EXPORT_SYMBOL_GPL(rockchip_fb_get_gem_obj); static void rockchip_drm_fb_destroy(struct drm_framebuffer *fb) { @@ -177,8 +176,23 @@ static void rockchip_crtc_wait_for_update(struct drm_crtc *crtc) crtc_funcs->wait_for_update(crtc); } +/* + * We can't use drm_atomic_helper_wait_for_vblanks() because rk3288 and rk3066 + * have hardware counters for neither vblanks nor scanlines, which results in + * a race where: + * | <-- HW vsync irq and reg take effect + * plane_commit --> | + * get_vblank and wait --> | + * | <-- handle_vblank, vblank->count + 1 + * cleanup_fb --> | + * iommu crash --> | + * | <-- HW vsync irq and reg take effect + * + * This function is equivalent but uses rockchip_crtc_wait_for_update() instead + * of waiting for vblank_count to change. + */ static void -rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) +rockchip_atomic_wait_for_complete(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_crtc_state *old_crtc_state; struct drm_crtc *crtc; @@ -194,6 +208,10 @@ rockchip_atomic_wait_for_complete(struct drm_atomic_state *old_state) if (!crtc->state->active) continue; + if (!drm_atomic_helper_framebuffer_changed(dev, + old_state, crtc)) + continue; + ret = drm_crtc_vblank_get(crtc); if (ret != 0) continue; @@ -241,7 +259,7 @@ rockchip_atomic_commit_complete(struct rockchip_atomic_commit *commit) drm_atomic_helper_commit_planes(dev, state, true); - rockchip_atomic_wait_for_complete(state); + rockchip_atomic_wait_for_complete(dev, state); drm_atomic_helper_cleanup_planes(dev, state); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h index 50432e9b5b37..73718c5f5bbf 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h @@ -15,7 +15,18 @@ #ifndef _ROCKCHIP_DRM_FBDEV_H #define _ROCKCHIP_DRM_FBDEV_H +#ifdef CONFIG_DRM_FBDEV_EMULATION int rockchip_drm_fbdev_init(struct drm_device *dev); void rockchip_drm_fbdev_fini(struct drm_device *dev); +#else +static inline int rockchip_drm_fbdev_init(struct drm_device *dev) +{ + return 0; +} + +static inline void rockchip_drm_fbdev_fini(struct drm_device *dev) +{ +} +#endif #endif /* _ROCKCHIP_DRM_FBDEV_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index d908321b94ce..18e07338c6e5 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -234,13 +234,8 @@ int rockchip_gem_dumb_create(struct drm_file *file_priv, /* * align to 64 bytes since Mali requires it. */ - min_pitch = ALIGN(min_pitch, 64); - - if (args->pitch < min_pitch) - args->pitch = min_pitch; - - if (args->size < args->pitch * args->height) - args->size = args->pitch * args->height; + args->pitch = ALIGN(min_pitch, 64); + args->size = args->pitch * args->height; rk_obj = rockchip_gem_create_with_handle(file_priv, dev, args->size, &args->handle); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 46c2a8dfd8aa..fd370548d7d7 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -43,8 +43,8 @@ #define REG_SET(x, base, reg, v, mode) \ __REG_SET_##mode(x, base + reg.offset, reg.mask, reg.shift, v) -#define REG_SET_MASK(x, base, reg, v, mode) \ - __REG_SET_##mode(x, base + reg.offset, reg.mask, reg.shift, v) +#define REG_SET_MASK(x, base, reg, mask, v, mode) \ + __REG_SET_##mode(x, base + reg.offset, mask, reg.shift, v) #define VOP_WIN_SET(x, win, name, v) \ REG_SET(x, win->base, win->phy->name, v, RELAXED) @@ -58,16 +58,18 @@ #define VOP_INTR_GET(vop, name) \ vop_read_reg(vop, 0, &vop->data->ctrl->name) -#define VOP_INTR_SET(vop, name, v) \ - REG_SET(vop, 0, vop->data->intr->name, v, NORMAL) +#define VOP_INTR_SET(vop, name, mask, v) \ + REG_SET_MASK(vop, 0, vop->data->intr->name, mask, v, NORMAL) #define VOP_INTR_SET_TYPE(vop, name, type, v) \ do { \ - int i, reg = 0; \ + int i, reg = 0, mask = 0; \ for (i = 0; i < vop->data->intr->nintrs; i++) { \ - if (vop->data->intr->intrs[i] & type) \ + if (vop->data->intr->intrs[i] & type) { \ reg |= (v) << i; \ + mask |= 1 << i; \ + } \ } \ - VOP_INTR_SET(vop, name, reg); \ + VOP_INTR_SET(vop, name, mask, reg); \ } while (0) #define VOP_INTR_GET_TYPE(vop, name, type) \ vop_get_intr_type(vop, &vop->data->intr->name, type) diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index 424d515ffcda..314ff71db978 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -144,19 +144,16 @@ int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused) } #endif /* CONFIG_DEBUG_FS */ -/* - * Asks the firmware to turn on power to the V3D engine. - * - * This may be doable with just the clocks interface, though this - * packet does some other register setup from the firmware, too. - */ int vc4_v3d_set_power(struct vc4_dev *vc4, bool on) { - if (on) - return pm_generic_poweroff(&vc4->v3d->pdev->dev); - else - return pm_generic_resume(&vc4->v3d->pdev->dev); + /* XXX: This interface is needed for GPU reset, and the way to + * do it is to turn our power domain off and back on. We + * can't just reset from within the driver, because the reset + * bits are in the power domain's register area, and get set + * during the poweron process. + */ + return 0; } static void vc4_v3d_init_hw(struct drm_device *dev) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index c49812b80dd0..24fb348a44e1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -25,6 +25,7 @@ * **************************************************************************/ #include <linux/module.h> +#include <linux/console.h> #include <drm/drmP.h> #include "vmwgfx_drv.h" @@ -1538,6 +1539,12 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) static int __init vmwgfx_init(void) { int ret; + +#ifdef CONFIG_VGA_CONSOLE + if (vgacon_text_force()) + return -EINVAL; +#endif + ret = drm_pci_init(&driver, &vmw_pci_driver); if (ret) DRM_ERROR("Failed initializing DRM.\n"); diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index c8487894b312..c43318d3416e 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -932,6 +932,17 @@ MODULE_DEVICE_TABLE(dmi, i8k_dmi_table); static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = { { /* + * CPU fan speed going up and down on Dell Studio XPS 8000 + * for unknown reasons. + */ + .ident = "Dell Studio XPS 8000", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8000"), + }, + }, + { + /* * CPU fan speed going up and down on Dell Studio XPS 8100 * for unknown reasons. */ diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c index f77eb971ce95..4f695d8fcafa 100644 --- a/drivers/hwmon/fam15h_power.c +++ b/drivers/hwmon/fam15h_power.c @@ -90,7 +90,15 @@ static ssize_t show_power(struct device *dev, pci_bus_read_config_dword(f4->bus, PCI_DEVFN(PCI_SLOT(f4->devfn), 5), REG_TDP_LIMIT3, &val); - tdp_limit = val >> 16; + /* + * On Carrizo and later platforms, ApmTdpLimit bit field + * is extended to 16:31 from 16:28. + */ + if (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model >= 0x60) + tdp_limit = val >> 16; + else + tdp_limit = (val >> 16) & 0x1fff; + curr_pwr_watts = ((u64)(tdp_limit + data->base_tdp)) << running_avg_range; curr_pwr_watts -= running_avg_capture; diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index ba9732c236c5..10fbd6d841e0 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -874,7 +874,8 @@ int i2c_dw_probe(struct dw_i2c_dev *dev) i2c_set_adapdata(adap, dev); i2c_dw_disable_int(dev); - r = devm_request_irq(dev->dev, dev->irq, i2c_dw_isr, IRQF_SHARED, + r = devm_request_irq(dev->dev, dev->irq, i2c_dw_isr, + IRQF_SHARED | IRQF_COND_SUSPEND, dev_name(dev->dev), dev); if (r) { dev_err(dev->dev, "failure requesting irq %i: %d\n", diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index e04598595073..93f2895383ee 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -137,10 +137,11 @@ static const struct dmi_system_id piix4_dmi_ibm[] = { }; /* SB800 globals */ +static DEFINE_MUTEX(piix4_mutex_sb800); static const char *piix4_main_port_names_sb800[PIIX4_MAX_ADAPTERS] = { - "SDA0", "SDA2", "SDA3", "SDA4" + " port 0", " port 2", " port 3", " port 4" }; -static const char *piix4_aux_port_name_sb800 = "SDA1"; +static const char *piix4_aux_port_name_sb800 = " port 1"; struct i2c_piix4_adapdata { unsigned short smba; @@ -148,7 +149,6 @@ struct i2c_piix4_adapdata { /* SB800 */ bool sb800_main; unsigned short port; - struct mutex *mutex; }; static int piix4_setup(struct pci_dev *PIIX4_dev, @@ -275,10 +275,12 @@ static int piix4_setup_sb800(struct pci_dev *PIIX4_dev, else smb_en = (aux) ? 0x28 : 0x2c; + mutex_lock(&piix4_mutex_sb800); outb_p(smb_en, SB800_PIIX4_SMB_IDX); smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); outb_p(smb_en + 1, SB800_PIIX4_SMB_IDX); smba_en_hi = inb_p(SB800_PIIX4_SMB_IDX + 1); + mutex_unlock(&piix4_mutex_sb800); if (!smb_en) { smb_en_status = smba_en_lo & 0x10; @@ -559,7 +561,7 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, u8 port; int retval; - mutex_lock(adapdata->mutex); + mutex_lock(&piix4_mutex_sb800); outb_p(SB800_PIIX4_PORT_IDX, SB800_PIIX4_SMB_IDX); smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1); @@ -574,7 +576,7 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr, outb_p(smba_en_lo, SB800_PIIX4_SMB_IDX + 1); - mutex_unlock(adapdata->mutex); + mutex_unlock(&piix4_mutex_sb800); return retval; } @@ -625,6 +627,7 @@ static struct i2c_adapter *piix4_main_adapters[PIIX4_MAX_ADAPTERS]; static struct i2c_adapter *piix4_aux_adapter; static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, + bool sb800_main, unsigned short port, const char *name, struct i2c_adapter **padap) { struct i2c_adapter *adap; @@ -639,7 +642,8 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, adap->owner = THIS_MODULE; adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD; - adap->algo = &smbus_algorithm; + adap->algo = sb800_main ? &piix4_smbus_algorithm_sb800 + : &smbus_algorithm; adapdata = kzalloc(sizeof(*adapdata), GFP_KERNEL); if (adapdata == NULL) { @@ -649,12 +653,14 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, } adapdata->smba = smba; + adapdata->sb800_main = sb800_main; + adapdata->port = port; /* set up the sysfs linkage to our parent device */ adap->dev.parent = &dev->dev; snprintf(adap->name, sizeof(adap->name), - "SMBus PIIX4 adapter %s at %04x", name, smba); + "SMBus PIIX4 adapter%s at %04x", name, smba); i2c_set_adapdata(adap, adapdata); @@ -673,30 +679,16 @@ static int piix4_add_adapter(struct pci_dev *dev, unsigned short smba, static int piix4_add_adapters_sb800(struct pci_dev *dev, unsigned short smba) { - struct mutex *mutex; struct i2c_piix4_adapdata *adapdata; int port; int retval; - mutex = kzalloc(sizeof(*mutex), GFP_KERNEL); - if (mutex == NULL) - return -ENOMEM; - - mutex_init(mutex); - for (port = 0; port < PIIX4_MAX_ADAPTERS; port++) { - retval = piix4_add_adapter(dev, smba, + retval = piix4_add_adapter(dev, smba, true, port, piix4_main_port_names_sb800[port], &piix4_main_adapters[port]); if (retval < 0) goto error; - - piix4_main_adapters[port]->algo = &piix4_smbus_algorithm_sb800; - - adapdata = i2c_get_adapdata(piix4_main_adapters[port]); - adapdata->sb800_main = true; - adapdata->port = port; - adapdata->mutex = mutex; } return retval; @@ -714,19 +706,20 @@ error: } } - kfree(mutex); - return retval; } static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) { int retval; + bool is_sb800 = false; if ((dev->vendor == PCI_VENDOR_ID_ATI && dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS && dev->revision >= 0x40) || dev->vendor == PCI_VENDOR_ID_AMD) { + is_sb800 = true; + if (!request_region(SB800_PIIX4_SMB_IDX, 2, "smba_idx")) { dev_err(&dev->dev, "SMBus base address index region 0x%x already in use!\n", @@ -756,7 +749,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) return retval; /* Try to register main SMBus adapter, give up if we can't */ - retval = piix4_add_adapter(dev, retval, "main", + retval = piix4_add_adapter(dev, retval, false, 0, "", &piix4_main_adapters[0]); if (retval < 0) return retval; @@ -783,7 +776,8 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) if (retval > 0) { /* Try to add the aux adapter if it exists, * piix4_add_adapter will clean up if this fails */ - piix4_add_adapter(dev, retval, piix4_aux_port_name_sb800, + piix4_add_adapter(dev, retval, false, 0, + is_sb800 ? piix4_aux_port_name_sb800 : "", &piix4_aux_adapter); } @@ -798,10 +792,8 @@ static void piix4_adap_remove(struct i2c_adapter *adap) i2c_del_adapter(adap); if (adapdata->port == 0) { release_region(adapdata->smba, SMBIOSIZE); - if (adapdata->sb800_main) { - kfree(adapdata->mutex); + if (adapdata->sb800_main) release_region(SB800_PIIX4_SMB_IDX, 2); - } } kfree(adapdata); kfree(adap); diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c index cb32b593f1c5..36607d52fee0 100644 --- a/drivers/iio/imu/adis_buffer.c +++ b/drivers/iio/imu/adis_buffer.c @@ -43,7 +43,7 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, return -ENOMEM; rx = adis->buffer; - tx = rx + indio_dev->scan_bytes; + tx = rx + scan_count; spi_message_init(&adis->msg); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 539b0dea8034..e5e223938eec 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2049,7 +2049,7 @@ static void do_attach(struct iommu_dev_data *dev_data, /* Update device table */ set_dte_entry(dev_data->devid, domain, ats); if (alias != dev_data->devid) - set_dte_entry(dev_data->devid, domain, ats); + set_dte_entry(alias, domain, ats); device_flush_dte(dev_data); } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ac7387686ddc..986a53e3eb96 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -1489,7 +1489,7 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info) { struct pci_dev *pdev; - if (dev_is_pci(info->dev)) + if (!dev_is_pci(info->dev)) return; pdev = to_pci_dev(info->dev); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 8bbcbfe7695c..381ca5a37a7b 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -25,6 +25,7 @@ #include <linux/sizes.h> #include <linux/slab.h> #include <linux/types.h> +#include <linux/dma-mapping.h> #include <asm/barrier.h> diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 715923d5236c..fb50911b3940 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -159,6 +159,7 @@ config TB10X_IRQC config TS4800_IRQ tristate "TS-4800 IRQ controller" select IRQ_DOMAIN + depends on HAS_IOMEM help Support for the TS-4800 FPGA IRQ controller diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c index b12a5d58546f..37199b9b2cfa 100644 --- a/drivers/irqchip/irq-atmel-aic-common.c +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -86,7 +86,7 @@ int aic_common_set_priority(int priority, unsigned *val) priority > AT91_AIC_IRQ_MAX_PRIORITY) return -EINVAL; - *val &= AT91_AIC_PRIOR; + *val &= ~AT91_AIC_PRIOR; *val |= priority; return 0; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index e23d1d18f9d6..3447549fcc93 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -875,6 +875,7 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) } alloc_size = (1 << order) * PAGE_SIZE; +retry_alloc_baser: alloc_pages = (alloc_size / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { alloc_pages = GITS_BASER_PAGES_MAX; @@ -938,13 +939,16 @@ retry_baser: * size and retry. If we reach 4K, then * something is horribly wrong... */ + free_pages((unsigned long)base, order); + its->tables[i] = NULL; + switch (psz) { case SZ_16K: psz = SZ_4K; - goto retry_baser; + goto retry_alloc_baser; case SZ_64K: psz = SZ_16K; - goto retry_baser; + goto retry_alloc_baser; } } diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index c22e2d40cb30..efe50845939d 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -241,6 +241,7 @@ static int __init asm9260_of_init(struct device_node *np, writel(0, icoll_priv.intr + i); icoll_add_domain(np, ASM9260_NUM_IRQS); + set_handle_irq(icoll_handle_irq); return 0; } diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c index c71914e8f596..5dc5a760c723 100644 --- a/drivers/irqchip/irq-s3c24xx.c +++ b/drivers/irqchip/irq-s3c24xx.c @@ -605,7 +605,7 @@ err: return ERR_PTR(ret); } -static struct s3c_irq_data init_eint[32] = { +static struct s3c_irq_data __maybe_unused init_eint[32] = { { .type = S3C_IRQTYPE_NONE, }, /* reserved */ { .type = S3C_IRQTYPE_NONE, }, /* reserved */ { .type = S3C_IRQTYPE_NONE, }, /* reserved */ diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 9fe33fc3c2b9..cf34681af4f6 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1532,7 +1532,7 @@ int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, /* no PVID with ranges, otherwise it's a bug */ if (pvid) - err = _mv88e6xxx_port_pvid_set(ds, port, vid); + err = _mv88e6xxx_port_pvid_set(ds, port, vlan->vid_end); unlock: mutex_unlock(&ps->smi_mutex); @@ -2163,7 +2163,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) * database, and allow every port to egress frames on all other ports. */ reg = BIT(ps->num_ports) - 1; /* all ports */ - ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg & ~port); + reg &= ~BIT(port); /* except itself */ + ret = _mv88e6xxx_port_vlan_map_set(ds, port, reg); if (ret) goto abort; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index a4799c1fc7d4..5eb9b20c0eea 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -628,6 +628,7 @@ static int xgene_enet_register_irq(struct net_device *ndev) int ret; ring = pdata->rx_ring; + irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, IRQF_SHARED, ring->irq_name, ring); if (ret) @@ -635,6 +636,7 @@ static int xgene_enet_register_irq(struct net_device *ndev) if (pdata->cq_cnt) { ring = pdata->tx_ring->cp_ring; + irq_set_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(dev, ring->irq, xgene_enet_rx_irq, IRQF_SHARED, ring->irq_name, ring); if (ret) { @@ -649,15 +651,19 @@ static int xgene_enet_register_irq(struct net_device *ndev) static void xgene_enet_free_irq(struct net_device *ndev) { struct xgene_enet_pdata *pdata; + struct xgene_enet_desc_ring *ring; struct device *dev; pdata = netdev_priv(ndev); dev = ndev_to_dev(ndev); - devm_free_irq(dev, pdata->rx_ring->irq, pdata->rx_ring); + ring = pdata->rx_ring; + irq_clear_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); + devm_free_irq(dev, ring->irq, ring); if (pdata->cq_cnt) { - devm_free_irq(dev, pdata->tx_ring->cp_ring->irq, - pdata->tx_ring->cp_ring); + ring = pdata->tx_ring->cp_ring; + irq_clear_status_flags(ring->irq, IRQ_DISABLE_UNLAZY); + devm_free_irq(dev, ring->irq, ring); } } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 70d5b62c125a..248dfc40a761 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -25,6 +25,7 @@ #include <linux/acpi.h> #include <linux/clk.h> #include <linux/efi.h> +#include <linux/irq.h> #include <linux/io.h> #include <linux/of_platform.h> #include <linux/of_net.h> diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index ecc4a334c507..f71ab2647a3b 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -302,7 +302,7 @@ static int nb8800_poll(struct napi_struct *napi, int budget) nb8800_tx_done(dev); again: - while (work < budget) { + do { struct nb8800_rx_buf *rxb; unsigned int len; @@ -330,7 +330,7 @@ again: rxd->report = 0; last = next; work++; - } + } while (work < budget); if (work) { priv->rx_descs[last].desc.config |= DESC_EOC; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 8550df189ceb..19f7cd02e085 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -151,8 +151,11 @@ config BNX2X_VXLAN config BGMAC tristate "BCMA bus GBit core support" - depends on BCMA_HOST_SOC && HAS_DMA && (BCM47XX || ARCH_BCM_5301X) + depends on BCMA && BCMA_HOST_SOC + depends on HAS_DMA + depends on BCM47XX || ARCH_BCM_5301X || COMPILE_TEST select PHYLIB + select FIXED_PHY ---help--- This driver supports GBit MAC and BCM4706 GBit MAC cores on BCMA bus. They can be found on BCM47xx SoCs and provide gigabit ethernet. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index df835f5e46d8..5dc89e527e7d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1490,10 +1490,11 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) last = tx_buf->nr_frags; j += 2; - for (k = 0; k < last; k++, j = NEXT_TX(j)) { + for (k = 0; k < last; k++, j++) { + int ring_idx = j & bp->tx_ring_mask; skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; - tx_buf = &txr->tx_buf_ring[j]; + tx_buf = &txr->tx_buf_ring[ring_idx]; dma_unmap_page( &pdev->dev, dma_unmap_addr(tx_buf, mapping), @@ -3406,7 +3407,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr; u16 error_code; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, -1, -1); + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1); req.ring_type = ring_type; req.ring_id = cpu_to_le16(ring->fw_ring_id); @@ -4819,8 +4820,6 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->multicast += le64_to_cpu(hw_stats->rx_mcast_pkts); - stats->rx_dropped += le64_to_cpu(hw_stats->rx_drop_pkts); - stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 0d775964b060..457c3bc8cfff 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -401,7 +401,7 @@ int bcmgenet_mii_probe(struct net_device *dev) * Ethernet MAC ISRs */ if (priv->internal_phy) - priv->mii_bus->irq[phydev->mdio.addr] = PHY_IGNORE_INTERRUPT; + priv->phydev->irq = PHY_IGNORE_INTERRUPT; return 0; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9293675df7ba..49eea8981332 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12016,7 +12016,7 @@ static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, int ret; u32 offset, len, b_offset, odd_len; u8 *buf; - __be32 start, end; + __be32 start = 0, end; if (tg3_flag(tp, NO_NVRAM) || eeprom->magic != TG3_EEPROM_MAGIC) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 9d9984a87d42..50c94104f19c 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -2823,7 +2823,7 @@ static int macb_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct device_node *phy_node; const struct macb_config *macb_config = NULL; - struct clk *pclk, *hclk, *tx_clk; + struct clk *pclk, *hclk = NULL, *tx_clk = NULL; unsigned int queue_mask, num_queues; struct macb_platform_data *pdata; bool native_io; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index b89504405b72..872765527081 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1526,7 +1526,6 @@ static int liquidio_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; - u32 remainder; unsigned long flags; struct lio *lio = container_of(ptp, struct lio, ptp_info); struct octeon_device *oct = (struct octeon_device *)lio->oct_dev; @@ -1536,8 +1535,7 @@ static int liquidio_ptp_gettime(struct ptp_clock_info *ptp, ns += lio->ptp_adjust; spin_unlock_irqrestore(&lio->ptp_lock, flags); - ts->tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder); - ts->tv_nsec = remainder; + *ts = ns_to_timespec64(ns); return 0; } diff --git a/drivers/net/ethernet/ezchip/Kconfig b/drivers/net/ethernet/ezchip/Kconfig index 48ecbc8aaaea..b423ad380b6a 100644 --- a/drivers/net/ethernet/ezchip/Kconfig +++ b/drivers/net/ethernet/ezchip/Kconfig @@ -18,6 +18,7 @@ if NET_VENDOR_EZCHIP config EZCHIP_NPS_MANAGEMENT_ENET tristate "EZchip NPS management enet support" depends on OF_IRQ && OF_NET + depends on HAS_IOMEM ---help--- Simple LAN device for debug or management purposes. Device supports interrupts for RX and TX(completion). diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index 4097c58d17a7..cbe21dc7e37e 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -4,6 +4,9 @@ obj-$(CONFIG_FEC) += fec.o fec-objs :=fec_main.o fec_ptp.o +CFLAGS_fec_main.o := -D__CHECK_ENDIAN__ +CFLAGS_fec_ptp.o := -D__CHECK_ENDIAN__ + obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx.o ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y) obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx_phy.o diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 99d33e2d35e6..2106d72c91dc 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -19,8 +19,7 @@ #include <linux/timecounter.h> #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || \ - defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) /* * Just figures, Motorola would have to change the offsets for * registers in the same peripheral device on different models @@ -190,28 +189,45 @@ /* * Define the buffer descriptor structure. + * + * Evidently, ARM SoCs have the FEC block generated in a + * little endian mode so adjust endianness accordingly. */ -#if defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) +#if defined(CONFIG_ARM) +#define fec32_to_cpu le32_to_cpu +#define fec16_to_cpu le16_to_cpu +#define cpu_to_fec32 cpu_to_le32 +#define cpu_to_fec16 cpu_to_le16 +#define __fec32 __le32 +#define __fec16 __le16 + struct bufdesc { - unsigned short cbd_datlen; /* Data length */ - unsigned short cbd_sc; /* Control and status info */ - unsigned long cbd_bufaddr; /* Buffer address */ + __fec16 cbd_datlen; /* Data length */ + __fec16 cbd_sc; /* Control and status info */ + __fec32 cbd_bufaddr; /* Buffer address */ }; #else +#define fec32_to_cpu be32_to_cpu +#define fec16_to_cpu be16_to_cpu +#define cpu_to_fec32 cpu_to_be32 +#define cpu_to_fec16 cpu_to_be16 +#define __fec32 __be32 +#define __fec16 __be16 + struct bufdesc { - unsigned short cbd_sc; /* Control and status info */ - unsigned short cbd_datlen; /* Data length */ - unsigned long cbd_bufaddr; /* Buffer address */ + __fec16 cbd_sc; /* Control and status info */ + __fec16 cbd_datlen; /* Data length */ + __fec32 cbd_bufaddr; /* Buffer address */ }; #endif struct bufdesc_ex { struct bufdesc desc; - unsigned long cbd_esc; - unsigned long cbd_prot; - unsigned long cbd_bdu; - unsigned long ts; - unsigned short res0[4]; + __fec32 cbd_esc; + __fec32 cbd_prot; + __fec32 cbd_bdu; + __fec32 ts; + __fec16 res0[4]; }; /* diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 502da6f48f95..41c81f6ec630 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -332,11 +332,13 @@ static void fec_dump(struct net_device *ndev) bdp = txq->tx_bd_base; do { - pr_info("%3u %c%c 0x%04x 0x%08lx %4u %p\n", + pr_info("%3u %c%c 0x%04x 0x%08x %4u %p\n", index, bdp == txq->cur_tx ? 'S' : ' ', bdp == txq->dirty_tx ? 'H' : ' ', - bdp->cbd_sc, bdp->cbd_bufaddr, bdp->cbd_datlen, + fec16_to_cpu(bdp->cbd_sc), + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), txq->tx_skbuff[index]); bdp = fec_enet_get_nextdesc(bdp, fep, 0); index++; @@ -389,7 +391,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, bdp = fec_enet_get_nextdesc(bdp, fep, queue); ebdp = (struct bufdesc_ex *)bdp; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); frag_len = skb_shinfo(skb)->frags[frag].size; @@ -411,7 +413,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } bufaddr = page_address(this_frag->page.p) + this_frag->page_offset; @@ -435,9 +437,9 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, goto dma_mapping_error; } - bdp->cbd_bufaddr = addr; - bdp->cbd_datlen = frag_len; - bdp->cbd_sc = status; + bdp->cbd_bufaddr = cpu_to_fec32(addr); + bdp->cbd_datlen = cpu_to_fec16(frag_len); + bdp->cbd_sc = cpu_to_fec16(status); } return bdp; @@ -445,8 +447,8 @@ dma_mapping_error: bdp = txq->cur_tx; for (i = 0; i < frag; i++) { bdp = fec_enet_get_nextdesc(bdp, fep, queue); - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, - bdp->cbd_datlen, DMA_TO_DEVICE); + dma_unmap_single(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE); } return ERR_PTR(-ENOMEM); } @@ -483,7 +485,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, /* Fill in a Tx ring entry */ bdp = txq->cur_tx; last_bdp = bdp; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; /* Set buffer length and buffer pointer */ @@ -539,21 +541,21 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq, estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } index = fec_enet_get_bd_index(txq->tx_bd_base, last_bdp, fep); /* Save skb pointer */ txq->tx_skbuff[index] = skb; - bdp->cbd_datlen = buflen; - bdp->cbd_bufaddr = addr; + bdp->cbd_datlen = cpu_to_fec16(buflen); + bdp->cbd_bufaddr = cpu_to_fec32(addr); /* Send it on its way. Tell FEC it's ready, interrupt when done, * it's the last BD of the frame, and to put the CRC on the end. */ status |= (BD_ENET_TX_READY | BD_ENET_TX_TC); - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); /* If this was the last BD in the ring, start at the beginning again. */ bdp = fec_enet_get_nextdesc(last_bdp, fep, queue); @@ -585,7 +587,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, unsigned int estatus = 0; dma_addr_t addr; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); @@ -607,8 +609,8 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, return NETDEV_TX_BUSY; } - bdp->cbd_datlen = size; - bdp->cbd_bufaddr = addr; + bdp->cbd_datlen = cpu_to_fec16(size); + bdp->cbd_bufaddr = cpu_to_fec32(addr); if (fep->bufdesc_ex) { if (fep->quirks & FEC_QUIRK_HAS_AVB) @@ -616,7 +618,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } /* Handle the last BD specially */ @@ -625,10 +627,10 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, if (is_last) { status |= BD_ENET_TX_INTR; if (fep->bufdesc_ex) - ebdp->cbd_esc |= BD_ENET_TX_INT; + ebdp->cbd_esc |= cpu_to_fec32(BD_ENET_TX_INT); } - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); return 0; } @@ -647,7 +649,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, unsigned short status; unsigned int estatus = 0; - status = bdp->cbd_sc; + status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); @@ -671,8 +673,8 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, } } - bdp->cbd_bufaddr = dmabuf; - bdp->cbd_datlen = hdr_len; + bdp->cbd_bufaddr = cpu_to_fec32(dmabuf); + bdp->cbd_datlen = cpu_to_fec16(hdr_len); if (fep->bufdesc_ex) { if (fep->quirks & FEC_QUIRK_HAS_AVB) @@ -680,10 +682,10 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; ebdp->cbd_bdu = 0; - ebdp->cbd_esc = estatus; + ebdp->cbd_esc = cpu_to_fec32(estatus); } - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); return 0; } @@ -823,15 +825,15 @@ static void fec_enet_bd_init(struct net_device *dev) /* Initialize the BD for every fragment in the page. */ if (bdp->cbd_bufaddr) - bdp->cbd_sc = BD_ENET_RX_EMPTY; + bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY); else - bdp->cbd_sc = 0; + bdp->cbd_sc = cpu_to_fec16(0); bdp = fec_enet_get_nextdesc(bdp, fep, q); } /* Set the last buffer to wrap */ bdp = fec_enet_get_prevdesc(bdp, fep, q); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); rxq->cur_rx = rxq->rx_bd_base; } @@ -844,18 +846,18 @@ static void fec_enet_bd_init(struct net_device *dev) for (i = 0; i < txq->tx_ring_size; i++) { /* Initialize the BD for every fragment in the page. */ - bdp->cbd_sc = 0; + bdp->cbd_sc = cpu_to_fec16(0); if (txq->tx_skbuff[i]) { dev_kfree_skb_any(txq->tx_skbuff[i]); txq->tx_skbuff[i] = NULL; } - bdp->cbd_bufaddr = 0; + bdp->cbd_bufaddr = cpu_to_fec32(0); bdp = fec_enet_get_nextdesc(bdp, fep, q); } /* Set the last buffer to wrap */ bdp = fec_enet_get_prevdesc(bdp, fep, q); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); txq->dirty_tx = bdp; } } @@ -947,8 +949,10 @@ fec_restart(struct net_device *ndev) */ if (fep->quirks & FEC_QUIRK_ENET_MAC) { memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN); - writel(cpu_to_be32(temp_mac[0]), fep->hwp + FEC_ADDR_LOW); - writel(cpu_to_be32(temp_mac[1]), fep->hwp + FEC_ADDR_HIGH); + writel((__force u32)cpu_to_be32(temp_mac[0]), + fep->hwp + FEC_ADDR_LOW); + writel((__force u32)cpu_to_be32(temp_mac[1]), + fep->hwp + FEC_ADDR_HIGH); } /* Clear any outstanding interrupt. */ @@ -1222,7 +1226,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) while (bdp != READ_ONCE(txq->cur_tx)) { /* Order the load of cur_tx and cbd_sc */ rmb(); - status = READ_ONCE(bdp->cbd_sc); + status = fec16_to_cpu(READ_ONCE(bdp->cbd_sc)); if (status & BD_ENET_TX_READY) break; @@ -1230,10 +1234,12 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) skb = txq->tx_skbuff[index]; txq->tx_skbuff[index] = NULL; - if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr)) - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, - bdp->cbd_datlen, DMA_TO_DEVICE); - bdp->cbd_bufaddr = 0; + if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); + bdp->cbd_bufaddr = cpu_to_fec32(0); if (!skb) { bdp = fec_enet_get_nextdesc(bdp, fep, queue_id); continue; @@ -1264,7 +1270,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id) struct skb_shared_hwtstamps shhwtstamps; struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - fec_enet_hwtstamp(fep, ebdp->ts, &shhwtstamps); + fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps); skb_tstamp_tx(skb, &shhwtstamps); } @@ -1324,10 +1330,8 @@ fec_enet_new_rxbdp(struct net_device *ndev, struct bufdesc *bdp, struct sk_buff if (off) skb_reserve(skb, fep->rx_align + 1 - off); - bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data, - FEC_ENET_RX_FRSIZE - fep->rx_align, - DMA_FROM_DEVICE); - if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) { + bdp->cbd_bufaddr = cpu_to_fec32(dma_map_single(&fep->pdev->dev, skb->data, FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE)); + if (dma_mapping_error(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr))) { if (net_ratelimit()) netdev_err(ndev, "Rx DMA memory map failed\n"); return -ENOMEM; @@ -1349,7 +1353,8 @@ static bool fec_enet_copybreak(struct net_device *ndev, struct sk_buff **skb, if (!new_skb) return false; - dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr, + dma_sync_single_for_cpu(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); if (!swap) @@ -1396,7 +1401,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) */ bdp = rxq->cur_rx; - while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) { + while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) { if (pkt_received >= budget) break; @@ -1438,7 +1443,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* Process the incoming frame. */ ndev->stats.rx_packets++; - pkt_len = bdp->cbd_datlen; + pkt_len = fec16_to_cpu(bdp->cbd_datlen); ndev->stats.rx_bytes += pkt_len; index = fec_enet_get_bd_index(rxq->rx_bd_base, bdp, fep); @@ -1456,7 +1461,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) ndev->stats.rx_dropped++; goto rx_processing_done; } - dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); } @@ -1475,7 +1481,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* If this is a VLAN packet remove the VLAN Tag */ vlan_packet_rcvd = false; if ((ndev->features & NETIF_F_HW_VLAN_CTAG_RX) && - fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) { + fep->bufdesc_ex && + (ebdp->cbd_esc & cpu_to_fec32(BD_ENET_RX_VLAN))) { /* Push and remove the vlan tag */ struct vlan_hdr *vlan_header = (struct vlan_hdr *) (data + ETH_HLEN); @@ -1491,12 +1498,12 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) /* Get receive timestamp from the skb */ if (fep->hwts_rx_en && fep->bufdesc_ex) - fec_enet_hwtstamp(fep, ebdp->ts, + fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), skb_hwtstamps(skb)); if (fep->bufdesc_ex && (fep->csum_flags & FLAG_RX_CSUM_ENABLED)) { - if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) { + if (!(ebdp->cbd_esc & cpu_to_fec32(FLAG_RX_CSUM_ERROR))) { /* don't check it */ skb->ip_summed = CHECKSUM_UNNECESSARY; } else { @@ -1513,7 +1520,8 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) napi_gro_receive(&fep->napi, skb); if (is_copybreak) { - dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr, + dma_sync_single_for_device(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); } else { @@ -1527,12 +1535,12 @@ rx_processing_done: /* Mark the buffer empty */ status |= BD_ENET_RX_EMPTY; - bdp->cbd_sc = status; + bdp->cbd_sc = cpu_to_fec16(status); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_RX_INT; + ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT); ebdp->cbd_prot = 0; ebdp->cbd_bdu = 0; } @@ -2145,8 +2153,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) /* List of registers that can be safety be read to dump them with ethtool */ #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || \ - defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -2662,7 +2669,7 @@ static void fec_enet_free_buffers(struct net_device *ndev) rxq->rx_skbuff[i] = NULL; if (skb) { dma_unmap_single(&fep->pdev->dev, - bdp->cbd_bufaddr, + fec32_to_cpu(bdp->cbd_bufaddr), FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE); dev_kfree_skb(skb); @@ -2777,11 +2784,11 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) } rxq->rx_skbuff[i] = skb; - bdp->cbd_sc = BD_ENET_RX_EMPTY; + bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_RX_INT; + ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT); } bdp = fec_enet_get_nextdesc(bdp, fep, queue); @@ -2789,7 +2796,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) /* Set the last buffer to wrap. */ bdp = fec_enet_get_prevdesc(bdp, fep, queue); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); return 0; err_alloc: @@ -2812,12 +2819,12 @@ fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue) if (!txq->tx_bounce[i]) goto err_alloc; - bdp->cbd_sc = 0; - bdp->cbd_bufaddr = 0; + bdp->cbd_sc = cpu_to_fec16(0); + bdp->cbd_bufaddr = cpu_to_fec32(0); if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_TX_INT; + ebdp->cbd_esc = cpu_to_fec32(BD_ENET_TX_INT); } bdp = fec_enet_get_nextdesc(bdp, fep, queue); @@ -2825,7 +2832,7 @@ fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue) /* Set the last buffer to wrap. */ bdp = fec_enet_get_prevdesc(bdp, fep, queue); - bdp->cbd_sc |= BD_SC_WRAP; + bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); return 0; diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c index 52e0091b4fb2..1ba359f17ec6 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c @@ -552,7 +552,7 @@ static void tx_restart(struct net_device *dev) cbd_t __iomem *prev_bd; cbd_t __iomem *last_tx_bd; - last_tx_bd = fep->tx_bd_base + ((fpi->tx_ring - 1) * sizeof(cbd_t)); + last_tx_bd = fep->tx_bd_base + (fpi->tx_ring - 1); /* get the current bd held in TBPTR and scan back from this point */ recheck_bd = curr_tbptr = (cbd_t __iomem *) diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index b3645297477e..3bfe36f9405b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -95,21 +95,17 @@ static struct hnae_buf_ops hnae_bops = { static int __ae_match(struct device *dev, const void *data) { struct hnae_ae_dev *hdev = cls_to_ae_dev(dev); - const char *ae_id = data; - if (!strncmp(ae_id, hdev->name, AE_NAME_SIZE)) - return 1; - - return 0; + return hdev->dev->of_node == data; } -static struct hnae_ae_dev *find_ae(const char *ae_id) +static struct hnae_ae_dev *find_ae(const struct device_node *ae_node) { struct device *dev; - WARN_ON(!ae_id); + WARN_ON(!ae_node); - dev = class_find_device(hnae_class, NULL, ae_id, __ae_match); + dev = class_find_device(hnae_class, NULL, ae_node, __ae_match); return dev ? cls_to_ae_dev(dev) : NULL; } @@ -316,7 +312,8 @@ EXPORT_SYMBOL(hnae_reinit_handle); * return handle ptr or ERR_PTR */ struct hnae_handle *hnae_get_handle(struct device *owner_dev, - const char *ae_id, u32 port_id, + const struct device_node *ae_node, + u32 port_id, struct hnae_buf_ops *bops) { struct hnae_ae_dev *dev; @@ -324,7 +321,7 @@ struct hnae_handle *hnae_get_handle(struct device *owner_dev, int i, j; int ret; - dev = find_ae(ae_id); + dev = find_ae(ae_node); if (!dev) return ERR_PTR(-ENODEV); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 6ca94dc3dda3..1cbcb9fa3fb5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -524,8 +524,11 @@ struct hnae_handle { #define ring_to_dev(ring) ((ring)->q->dev->dev) -struct hnae_handle *hnae_get_handle(struct device *owner_dev, const char *ae_id, - u32 port_id, struct hnae_buf_ops *bops); +struct hnae_handle *hnae_get_handle(struct device *owner_dev, + const struct device_node *ae_node, + u32 port_id, + struct hnae_buf_ops *bops); + void hnae_put_handle(struct hnae_handle *handle); int hnae_ae_register(struct hnae_ae_dev *dev, struct module *owner); void hnae_ae_unregister(struct hnae_ae_dev *dev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 522b264866b4..a0070d0e740d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -847,6 +847,7 @@ static struct hnae_ae_ops hns_dsaf_ops = { int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev) { struct hnae_ae_dev *ae_dev = &dsaf_dev->ae_dev; + static atomic_t id = ATOMIC_INIT(-1); switch (dsaf_dev->dsaf_ver) { case AE_VERSION_1: @@ -858,6 +859,9 @@ int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev) default: break; } + + snprintf(ae_dev->name, AE_NAME_SIZE, "%s%d", DSAF_DEVICE_NAME, + (int)atomic_inc_return(&id)); ae_dev->ops = &hns_dsaf_ops; ae_dev->dev = dsaf_dev->dev; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 1c33bd06bd5c..9439f04962e1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -35,7 +35,7 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) int ret, i; u32 desc_num; u32 buf_size; - const char *name, *mode_str; + const char *mode_str; struct device_node *np = dsaf_dev->dev->of_node; if (of_device_is_compatible(np, "hisilicon,hns-dsaf-v1")) @@ -43,14 +43,6 @@ int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) else dsaf_dev->dsaf_ver = AE_VERSION_2; - ret = of_property_read_string(np, "dsa_name", &name); - if (ret) { - dev_err(dsaf_dev->dev, "get dsaf name fail, ret=%d!\n", ret); - return ret; - } - strncpy(dsaf_dev->ae_dev.name, name, AE_NAME_SIZE); - dsaf_dev->ae_dev.name[AE_NAME_SIZE - 1] = '\0'; - ret = of_property_read_string(np, "mode", &mode_str); if (ret) { dev_err(dsaf_dev->dev, "get dsaf mode fail, ret=%d!\n", ret); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 31c312f9826e..40205b910f80 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -18,6 +18,7 @@ struct hns_mac_cb; #define DSAF_DRV_NAME "hns_dsaf" #define DSAF_MOD_VERSION "v1.0" +#define DSAF_DEVICE_NAME "dsaf" #define HNS_DSAF_DEBUG_NW_REG_OFFSET 0x100000 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 0e30846a24f8..3f77ff77abbc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1802,7 +1802,7 @@ static int hns_nic_try_get_ae(struct net_device *ndev) int ret; h = hnae_get_handle(&priv->netdev->dev, - priv->ae_name, priv->port_id, NULL); + priv->ae_node, priv->port_id, NULL); if (IS_ERR_OR_NULL(h)) { ret = PTR_ERR(h); dev_dbg(priv->dev, "has not handle, register notifier!\n"); @@ -1880,13 +1880,16 @@ static int hns_nic_dev_probe(struct platform_device *pdev) else priv->enet_ver = AE_VERSION_2; - ret = of_property_read_string(node, "ae-name", &priv->ae_name); - if (ret) - goto out_read_string_fail; + priv->ae_node = (void *)of_parse_phandle(node, "ae-handle", 0); + if (IS_ERR_OR_NULL(priv->ae_node)) { + ret = PTR_ERR(priv->ae_node); + dev_err(dev, "not find ae-handle\n"); + goto out_read_prop_fail; + } ret = of_property_read_u32(node, "port-id", &priv->port_id); if (ret) - goto out_read_string_fail; + goto out_read_prop_fail; hns_init_mac_addr(ndev); @@ -1945,7 +1948,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev) out_notify_fail: (void)cancel_work_sync(&priv->service_task); -out_read_string_fail: +out_read_prop_fail: free_netdev(ndev); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h index 4b75270f014e..c68ab3d34fc2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -51,7 +51,7 @@ struct hns_nic_ops { }; struct hns_nic_priv { - const char *ae_name; + const struct device_node *ae_node; u32 enet_ver; u32 port_id; int phy_mode; diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index 1d5c3e16d8f4..3daf2d4a7ca0 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -194,7 +194,6 @@ static const char *hp100_isa_tbl[] = { }; #endif -#ifdef CONFIG_EISA static struct eisa_device_id hp100_eisa_tbl[] = { { "HWPF180" }, /* HP J2577 rev A */ { "HWP1920" }, /* HP 27248B */ @@ -205,9 +204,7 @@ static struct eisa_device_id hp100_eisa_tbl[] = { { "" } /* Mandatory final entry ! */ }; MODULE_DEVICE_TABLE(eisa, hp100_eisa_tbl); -#endif -#ifdef CONFIG_PCI static const struct pci_device_id hp100_pci_tbl[] = { {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_J2585A, PCI_ANY_ID, PCI_ANY_ID,}, {PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_J2585B, PCI_ANY_ID, PCI_ANY_ID,}, @@ -219,7 +216,6 @@ static const struct pci_device_id hp100_pci_tbl[] = { {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(pci, hp100_pci_tbl); -#endif static int hp100_rx_ratio = HP100_DEFAULT_RX_RATIO; static int hp100_priority_tx = HP100_DEFAULT_PRIORITY_TX; @@ -2842,7 +2838,6 @@ static void cleanup_dev(struct net_device *d) free_netdev(d); } -#ifdef CONFIG_EISA static int hp100_eisa_probe(struct device *gendev) { struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private)); @@ -2884,9 +2879,7 @@ static struct eisa_driver hp100_eisa_driver = { .remove = hp100_eisa_remove, } }; -#endif -#ifdef CONFIG_PCI static int hp100_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2955,7 +2948,6 @@ static struct pci_driver hp100_pci_driver = { .probe = hp100_pci_probe, .remove = hp100_pci_remove, }; -#endif /* * module section @@ -3032,23 +3024,17 @@ static int __init hp100_module_init(void) err = hp100_isa_init(); if (err && err != -ENODEV) goto out; -#ifdef CONFIG_EISA err = eisa_driver_register(&hp100_eisa_driver); if (err && err != -ENODEV) goto out2; -#endif -#ifdef CONFIG_PCI err = pci_register_driver(&hp100_pci_driver); if (err && err != -ENODEV) goto out3; -#endif out: return err; out3: -#ifdef CONFIG_EISA eisa_driver_unregister (&hp100_eisa_driver); out2: -#endif hp100_isa_cleanup(); goto out; } @@ -3057,12 +3043,8 @@ static int __init hp100_module_init(void) static void __exit hp100_module_exit(void) { hp100_isa_cleanup(); -#ifdef CONFIG_EISA eisa_driver_unregister (&hp100_eisa_driver); -#endif -#ifdef CONFIG_PCI pci_unregister_driver (&hp100_pci_driver); -#endif } module_init(hp100_module_init) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index bb4612c159fd..8f3b53e0dc46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7117,9 +7117,7 @@ static void i40e_service_task(struct work_struct *work) i40e_watchdog_subtask(pf); i40e_fdir_reinit_subtask(pf); i40e_sync_filters_subtask(pf); -#if IS_ENABLED(CONFIG_VXLAN) || IS_ENABLED(CONFIG_GENEVE) i40e_sync_udp_filters_subtask(pf); -#endif i40e_clean_adminq_subtask(pf); i40e_service_event_complete(pf); @@ -8515,6 +8513,8 @@ static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) } #endif + +#if IS_ENABLED(CONFIG_VXLAN) /** * i40e_add_vxlan_port - Get notifications about VXLAN ports that come up * @netdev: This physical port's netdev @@ -8524,7 +8524,6 @@ static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) static void i40e_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_VXLAN) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8557,7 +8556,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev, pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN; pf->pending_udp_bitmap |= BIT_ULL(next_idx); pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; -#endif } /** @@ -8569,7 +8567,6 @@ static void i40e_add_vxlan_port(struct net_device *netdev, static void i40e_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_VXLAN) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8592,9 +8589,10 @@ static void i40e_del_vxlan_port(struct net_device *netdev, netdev_warn(netdev, "vxlan port %d was not found, not deleting\n", ntohs(port)); } -#endif } +#endif +#if IS_ENABLED(CONFIG_GENEVE) /** * i40e_add_geneve_port - Get notifications about GENEVE ports that come up * @netdev: This physical port's netdev @@ -8604,7 +8602,6 @@ static void i40e_del_vxlan_port(struct net_device *netdev, static void i40e_add_geneve_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_GENEVE) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8639,7 +8636,6 @@ static void i40e_add_geneve_port(struct net_device *netdev, pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; dev_info(&pf->pdev->dev, "adding geneve port %d\n", ntohs(port)); -#endif } /** @@ -8651,7 +8647,6 @@ static void i40e_add_geneve_port(struct net_device *netdev, static void i40e_del_geneve_port(struct net_device *netdev, sa_family_t sa_family, __be16 port) { -#if IS_ENABLED(CONFIG_GENEVE) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; @@ -8677,8 +8672,8 @@ static void i40e_del_geneve_port(struct net_device *netdev, netdev_warn(netdev, "geneve port %d was not found, not deleting\n", ntohs(port)); } -#endif } +#endif static int i40e_get_phys_port_id(struct net_device *netdev, struct netdev_phys_item_id *ppid) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 720516b0e8ee..47bd8b3145a7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2313,8 +2313,8 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, struct iphdr *this_ip_hdr; u32 network_hdr_len; u8 l4_hdr = 0; - struct udphdr *oudph; - struct iphdr *oiph; + struct udphdr *oudph = NULL; + struct iphdr *oiph = NULL; u32 l4_tunnel = 0; if (skb->encapsulation) { diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index a0c03834a2f7..55831188bc32 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -762,10 +762,10 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq, if (length <= 8 && (uintptr_t)data & 0x7) { /* Copy unaligned small data fragment to TSO header data area */ - memcpy(txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE, + memcpy(txq->tso_hdrs + tx_index * TSO_HEADER_SIZE, data, length); desc->buf_ptr = txq->tso_hdrs_dma - + txq->tx_curr_desc * TSO_HEADER_SIZE; + + tx_index * TSO_HEADER_SIZE; } else { /* Alignment is okay, map buffer and hand off to hardware */ txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index fabc8df40392..662c2ee268c7 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -11,28 +11,28 @@ * warranty of any kind, whether express or implied. */ -#include <linux/kernel.h> -#include <linux/netdevice.h> +#include <linux/clk.h> +#include <linux/cpu.h> #include <linux/etherdevice.h> -#include <linux/platform_device.h> -#include <linux/skbuff.h> +#include <linux/if_vlan.h> #include <linux/inetdevice.h> -#include <linux/mbus.h> -#include <linux/module.h> #include <linux/interrupt.h> -#include <linux/if_vlan.h> -#include <net/ip.h> -#include <net/ipv6.h> #include <linux/io.h> -#include <net/tso.h> +#include <linux/kernel.h> +#include <linux/mbus.h> +#include <linux/module.h> +#include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/of_address.h> #include <linux/phy.h> -#include <linux/clk.h> -#include <linux/cpu.h> +#include <linux/platform_device.h> +#include <linux/skbuff.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/tso.h> /* Registers */ #define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2)) @@ -373,6 +373,8 @@ struct mvneta_port { /* Core clock */ struct clk *clk; + /* AXI clock */ + struct clk *clk_bus; u8 mcast_count[256]; u16 tx_ring_size; u16 rx_ring_size; @@ -3242,26 +3244,25 @@ static void mvneta_ethtool_update_stats(struct mvneta_port *pp) const struct mvneta_statistic *s; void __iomem *base = pp->base; u32 high, low, val; + u64 val64; int i; for (i = 0, s = mvneta_statistics; s < mvneta_statistics + ARRAY_SIZE(mvneta_statistics); s++, i++) { - val = 0; - switch (s->type) { case T_REG_32: val = readl_relaxed(base + s->offset); + pp->ethtool_stats[i] += val; break; case T_REG_64: /* Docs say to read low 32-bit then high */ low = readl_relaxed(base + s->offset); high = readl_relaxed(base + s->offset + 4); - val = (u64)high << 32 | low; + val64 = (u64)high << 32 | low; + pp->ethtool_stats[i] += val64; break; } - - pp->ethtool_stats[i] += val; } } @@ -3605,7 +3606,9 @@ static int mvneta_probe(struct platform_device *pdev) pp->indir[0] = rxq_def; - pp->clk = devm_clk_get(&pdev->dev, NULL); + pp->clk = devm_clk_get(&pdev->dev, "core"); + if (IS_ERR(pp->clk)) + pp->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pp->clk)) { err = PTR_ERR(pp->clk); goto err_put_phy_node; @@ -3613,6 +3616,10 @@ static int mvneta_probe(struct platform_device *pdev) clk_prepare_enable(pp->clk); + pp->clk_bus = devm_clk_get(&pdev->dev, "bus"); + if (!IS_ERR(pp->clk_bus)) + clk_prepare_enable(pp->clk_bus); + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); pp->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(pp->base)) { @@ -3724,6 +3731,7 @@ err_free_stats: err_free_ports: free_percpu(pp->ports); err_clk: + clk_disable_unprepare(pp->clk_bus); clk_disable_unprepare(pp->clk); err_put_phy_node: of_node_put(phy_node); @@ -3741,6 +3749,7 @@ static int mvneta_remove(struct platform_device *pdev) struct mvneta_port *pp = netdev_priv(dev); unregister_netdev(dev); + clk_disable_unprepare(pp->clk_bus); clk_disable_unprepare(pp->clk); free_percpu(pp->ports); free_percpu(pp->stats); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 0c5237264e3e..bb77e2207804 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -1044,6 +1044,92 @@ static inline void mlxsw_reg_sftr_pack(char *payload, mlxsw_reg_sftr_port_mask_set(payload, port, 1); } +/* SFDF - Switch Filtering DB Flush + * -------------------------------- + * The switch filtering DB flush register is used to flush the FDB. + * Note that FDB notifications are flushed as well. + */ +#define MLXSW_REG_SFDF_ID 0x2013 +#define MLXSW_REG_SFDF_LEN 0x14 + +static const struct mlxsw_reg_info mlxsw_reg_sfdf = { + .id = MLXSW_REG_SFDF_ID, + .len = MLXSW_REG_SFDF_LEN, +}; + +/* reg_sfdf_swid + * Switch partition ID. + * Access: Index + */ +MLXSW_ITEM32(reg, sfdf, swid, 0x00, 24, 8); + +enum mlxsw_reg_sfdf_flush_type { + MLXSW_REG_SFDF_FLUSH_PER_SWID, + MLXSW_REG_SFDF_FLUSH_PER_FID, + MLXSW_REG_SFDF_FLUSH_PER_PORT, + MLXSW_REG_SFDF_FLUSH_PER_PORT_AND_FID, + MLXSW_REG_SFDF_FLUSH_PER_LAG, + MLXSW_REG_SFDF_FLUSH_PER_LAG_AND_FID, +}; + +/* reg_sfdf_flush_type + * Flush type. + * 0 - All SWID dynamic entries are flushed. + * 1 - All FID dynamic entries are flushed. + * 2 - All dynamic entries pointing to port are flushed. + * 3 - All FID dynamic entries pointing to port are flushed. + * 4 - All dynamic entries pointing to LAG are flushed. + * 5 - All FID dynamic entries pointing to LAG are flushed. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, flush_type, 0x04, 28, 4); + +/* reg_sfdf_flush_static + * Static. + * 0 - Flush only dynamic entries. + * 1 - Flush both dynamic and static entries. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, flush_static, 0x04, 24, 1); + +static inline void mlxsw_reg_sfdf_pack(char *payload, + enum mlxsw_reg_sfdf_flush_type type) +{ + MLXSW_REG_ZERO(sfdf, payload); + mlxsw_reg_sfdf_flush_type_set(payload, type); + mlxsw_reg_sfdf_flush_static_set(payload, true); +} + +/* reg_sfdf_fid + * FID to flush. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, fid, 0x0C, 0, 16); + +/* reg_sfdf_system_port + * Port to flush. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, system_port, 0x0C, 0, 16); + +/* reg_sfdf_port_fid_system_port + * Port to flush, pointed to by FID. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, port_fid_system_port, 0x08, 0, 16); + +/* reg_sfdf_lag_id + * LAG ID to flush. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, lag_id, 0x0C, 0, 10); + +/* reg_sfdf_lag_fid_lag_id + * LAG ID to flush, pointed to by FID. + * Access: RW + */ +MLXSW_ITEM32(reg, sfdf, lag_fid_lag_id, 0x08, 0, 10); + /* SLDR - Switch LAG Descriptor Register * ----------------------------------------- * The switch LAG descriptor register is populated by LAG descriptors. @@ -1701,20 +1787,20 @@ MLXSW_ITEM32(reg, pmlp, width, 0x00, 0, 8); * Module number. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, module, 0x04, 0, 8, 0x04, 0x00, false); /* reg_pmlp_tx_lane * Tx Lane. When rxtx field is cleared, this field is used for Rx as well. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 16, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, tx_lane, 0x04, 16, 2, 0x04, 0x00, false); /* reg_pmlp_rx_lane * Rx Lane. When rxtx field is cleared, this field is ignored and Rx lane is * equal to Tx lane. * Access: RW */ -MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 24, false); +MLXSW_ITEM32_INDEXED(reg, pmlp, rx_lane, 0x04, 24, 2, 0x04, 0x00, false); static inline void mlxsw_reg_pmlp_pack(char *payload, u8 local_port) { @@ -3121,6 +3207,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "SFGC"; case MLXSW_REG_SFTR_ID: return "SFTR"; + case MLXSW_REG_SFDF_ID: + return "SFDF"; case MLXSW_REG_SLDR_ID: return "SLDR"; case MLXSW_REG_SLCR_ID: diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ce6845d534a8..217856bdd400 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1979,6 +1979,115 @@ static struct mlxsw_driver mlxsw_sp_driver = { .profile = &mlxsw_sp_config_profile, }; +static int +mlxsw_sp_port_fdb_flush_by_port(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT); + mlxsw_reg_sfdf_system_port_set(sfdf_pl, mlxsw_sp_port->local_port); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +mlxsw_sp_port_fdb_flush_by_port_fid(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_PORT_AND_FID); + mlxsw_reg_sfdf_fid_set(sfdf_pl, fid); + mlxsw_reg_sfdf_port_fid_system_port_set(sfdf_pl, + mlxsw_sp_port->local_port); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +mlxsw_sp_port_fdb_flush_by_lag_id(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG); + mlxsw_reg_sfdf_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +mlxsw_sp_port_fdb_flush_by_lag_id_fid(const struct mlxsw_sp_port *mlxsw_sp_port, + u16 fid) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char sfdf_pl[MLXSW_REG_SFDF_LEN]; + + mlxsw_reg_sfdf_pack(sfdf_pl, MLXSW_REG_SFDF_FLUSH_PER_LAG_AND_FID); + mlxsw_reg_sfdf_fid_set(sfdf_pl, fid); + mlxsw_reg_sfdf_lag_fid_lag_id_set(sfdf_pl, mlxsw_sp_port->lag_id); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl); +} + +static int +__mlxsw_sp_port_fdb_flush(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err, last_err = 0; + u16 vid; + + for (vid = 1; vid < VLAN_N_VID - 1; vid++) { + err = mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_port, vid); + if (err) + last_err = err; + } + + return last_err; +} + +static int +__mlxsw_sp_port_fdb_flush_lagged(const struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err, last_err = 0; + u16 vid; + + for (vid = 1; vid < VLAN_N_VID - 1; vid++) { + err = mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_port, vid); + if (err) + last_err = err; + } + + return last_err; +} + +static int mlxsw_sp_port_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_port) +{ + if (!list_empty(&mlxsw_sp_port->vports_list)) + if (mlxsw_sp_port->lagged) + return __mlxsw_sp_port_fdb_flush_lagged(mlxsw_sp_port); + else + return __mlxsw_sp_port_fdb_flush(mlxsw_sp_port); + else + if (mlxsw_sp_port->lagged) + return mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port); + else + return mlxsw_sp_port_fdb_flush_by_port(mlxsw_sp_port); +} + +static int mlxsw_sp_vport_fdb_flush(struct mlxsw_sp_port *mlxsw_sp_vport) +{ + u16 vfid = mlxsw_sp_vport_vfid_get(mlxsw_sp_vport); + u16 fid = mlxsw_sp_vfid_to_fid(vfid); + + if (mlxsw_sp_vport->lagged) + return mlxsw_sp_port_fdb_flush_by_lag_id_fid(mlxsw_sp_vport, + fid); + else + return mlxsw_sp_port_fdb_flush_by_port_fid(mlxsw_sp_vport, fid); +} + static bool mlxsw_sp_port_dev_check(const struct net_device *dev) { return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; @@ -2006,10 +2115,14 @@ static int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } -static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port) +static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, + bool flush_fdb) { struct net_device *dev = mlxsw_sp_port->dev; + if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port)) + netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); + mlxsw_sp_port->learning = 0; mlxsw_sp_port->learning_sync = 0; mlxsw_sp_port->uc_flood = 0; @@ -2200,10 +2313,15 @@ err_col_port_enable: return err; } +static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, + struct net_device *br_dev, + bool flush_fdb); + static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *lag_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + struct mlxsw_sp_port *mlxsw_sp_vport; struct mlxsw_sp_upper *lag; u16 lag_id = mlxsw_sp_port->lag_id; int err; @@ -2220,7 +2338,32 @@ static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (err) return err; + /* In case we leave a LAG device that has bridges built on top, + * then their teardown sequence is never issued and we need to + * invoke the necessary cleanup routines ourselves. + */ + list_for_each_entry(mlxsw_sp_vport, &mlxsw_sp_port->vports_list, + vport.list) { + struct net_device *br_dev; + + if (!mlxsw_sp_vport->bridged) + continue; + + br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, false); + } + + if (mlxsw_sp_port->bridged) { + mlxsw_sp_port_active_vlans_del(mlxsw_sp_port); + mlxsw_sp_port_bridge_leave(mlxsw_sp_port, false); + + if (lag->ref_count == 1) + mlxsw_sp_master_bridge_dec(mlxsw_sp, NULL); + } + if (lag->ref_count == 1) { + if (mlxsw_sp_port_fdb_flush_by_lag_id(mlxsw_sp_port)) + netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); if (err) return err; @@ -2272,9 +2415,6 @@ static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled); } -static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *br_dev); - static int mlxsw_sp_port_vlan_link(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *vlan_dev) { @@ -2312,7 +2452,7 @@ static int mlxsw_sp_port_vlan_unlink(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *br_dev; br_dev = mlxsw_sp_vport_br_get(mlxsw_sp_vport); - mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev); + mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, br_dev, true); } mlxsw_sp_vport->dev = mlxsw_sp_port->dev; @@ -2374,7 +2514,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev, } mlxsw_sp_master_bridge_inc(mlxsw_sp, upper_dev); } else { - err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port); + err = mlxsw_sp_port_bridge_leave(mlxsw_sp_port, + true); mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev); if (err) { netdev_err(dev, "Failed to leave bridge\n"); @@ -2541,7 +2682,8 @@ static void mlxsw_sp_br_vfid_destroy(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, - struct net_device *br_dev) + struct net_device *br_dev, + bool flush_fdb) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_vport->mlxsw_sp; u16 vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); @@ -2604,6 +2746,9 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, goto err_vport_flood_set; } + if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport)) + netdev_err(dev, "Failed to flush FDB\n"); + /* Switch between the vFIDs and destroy the old one if needed. */ new_vfid->nr_vports++; mlxsw_sp_vport->vport.vfid = new_vfid; @@ -2777,7 +2922,7 @@ static int mlxsw_sp_netdevice_vport_event(struct net_device *dev, if (!mlxsw_sp_vport) return NOTIFY_DONE; err = mlxsw_sp_vport_bridge_leave(mlxsw_sp_vport, - upper_dev); + upper_dev, true); if (err) { netdev_err(dev, "Failed to leave bridge\n"); return NOTIFY_BAD; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index a23dc610d259..7f42eb1c320e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -120,7 +120,6 @@ struct mlxsw_sp { } fdb_notify; #define MLXSW_SP_DEFAULT_AGEING_TIME 300 u32 ageing_time; - struct mutex fdb_lock; /* Make sure FDB sessions are atomic. */ struct mlxsw_sp_upper master_bridge; struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX]; }; @@ -254,5 +253,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, __be16 __always_unused proto, u16 vid); int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, bool set, bool only_uc); +void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 45479ef5bcf4..e492ca2cdecd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -45,6 +45,7 @@ #include <linux/if_bridge.h> #include <linux/workqueue.h> #include <linux/jiffies.h> +#include <linux/rtnetlink.h> #include <net/switchdev.h> #include "spectrum.h" @@ -124,14 +125,14 @@ static int mlxsw_sp_port_stp_state_set(struct mlxsw_sp_port *mlxsw_sp_port, int err; switch (state) { - case BR_STATE_DISABLED: /* fall-through */ case BR_STATE_FORWARDING: spms_state = MLXSW_REG_SPMS_STATE_FORWARDING; break; - case BR_STATE_LISTENING: /* fall-through */ case BR_STATE_LEARNING: spms_state = MLXSW_REG_SPMS_STATE_LEARNING; break; + case BR_STATE_LISTENING: /* fall-through */ + case BR_STATE_DISABLED: /* fall-through */ case BR_STATE_BLOCKING: spms_state = MLXSW_REG_SPMS_STATE_DISCARDING; break; @@ -936,6 +937,14 @@ static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, vlan->vid_begin, vlan->vid_end, false); } +void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port) +{ + u16 vid; + + for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) + __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid, false); +} + static int mlxsw_sp_port_fdb_static_del(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_fdb *fdb) @@ -1040,10 +1049,12 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, struct switchdev_obj_port_fdb *fdb, - switchdev_obj_dump_cb_t *cb) + switchdev_obj_dump_cb_t *cb, + struct net_device *orig_dev) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - u16 vport_vid = 0, vport_fid = 0; + struct mlxsw_sp_port *tmp; + u16 vport_fid = 0; char *sfd_pl; char mac[ETH_ALEN]; u16 fid; @@ -1058,13 +1069,11 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, if (!sfd_pl) return -ENOMEM; - mutex_lock(&mlxsw_sp_port->mlxsw_sp->fdb_lock); if (mlxsw_sp_port_is_vport(mlxsw_sp_port)) { u16 tmp; tmp = mlxsw_sp_vport_vfid_get(mlxsw_sp_port); vport_fid = mlxsw_sp_vfid_to_fid(tmp); - vport_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_port); } mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0); @@ -1088,12 +1097,13 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_reg_sfd_uc_unpack(sfd_pl, i, mac, &fid, &local_port); if (local_port == mlxsw_sp_port->local_port) { - if (vport_fid && vport_fid != fid) - continue; - else if (vport_fid) - fdb->vid = vport_vid; - else + if (vport_fid && vport_fid == fid) + fdb->vid = 0; + else if (!vport_fid && + !mlxsw_sp_fid_is_vfid(fid)) fdb->vid = fid; + else + continue; ether_addr_copy(fdb->addr, mac); fdb->ndm_state = NUD_REACHABLE; err = cb(&fdb->obj); @@ -1104,14 +1114,22 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, case MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG: mlxsw_reg_sfd_uc_lag_unpack(sfd_pl, i, mac, &fid, &lag_id); - if (mlxsw_sp_port == - mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id)) { - if (vport_fid && vport_fid != fid) + tmp = mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id); + if (tmp && tmp->local_port == + mlxsw_sp_port->local_port) { + /* LAG records can only point to LAG + * devices or VLAN devices on top. + */ + if (!netif_is_lag_master(orig_dev) && + !is_vlan_dev(orig_dev)) continue; - else if (vport_fid) - fdb->vid = vport_vid; - else + if (vport_fid && vport_fid == fid) + fdb->vid = 0; + else if (!vport_fid && + !mlxsw_sp_fid_is_vfid(fid)) fdb->vid = fid; + else + continue; ether_addr_copy(fdb->addr, mac); fdb->ndm_state = NUD_REACHABLE; err = cb(&fdb->obj); @@ -1124,7 +1142,6 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port, } while (num_rec == MLXSW_REG_SFD_REC_MAX_COUNT); out: - mutex_unlock(&mlxsw_sp_port->mlxsw_sp->fdb_lock); kfree(sfd_pl); return stored_err ? stored_err : err; } @@ -1176,7 +1193,8 @@ static int mlxsw_sp_port_obj_dump(struct net_device *dev, break; case SWITCHDEV_OBJ_ID_PORT_FDB: err = mlxsw_sp_port_fdb_dump(mlxsw_sp_port, - SWITCHDEV_OBJ_PORT_FDB(obj), cb); + SWITCHDEV_OBJ_PORT_FDB(obj), cb, + obj->orig_dev); break; default: err = -EOPNOTSUPP; @@ -1194,14 +1212,14 @@ static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = { .switchdev_port_obj_dump = mlxsw_sp_port_obj_dump, }; -static void mlxsw_sp_fdb_call_notifiers(bool learning, bool learning_sync, - bool adding, char *mac, u16 vid, +static void mlxsw_sp_fdb_call_notifiers(bool learning_sync, bool adding, + char *mac, u16 vid, struct net_device *dev) { struct switchdev_notifier_fdb_info info; unsigned long notifier_type; - if (learning && learning_sync) { + if (learning_sync) { info.addr = mac; info.vid = vid; notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL; @@ -1237,7 +1255,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, netdev_err(mlxsw_sp_port->dev, "Failed to find a matching vPort following FDB notification\n"); goto just_remove; } - vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + vid = 0; /* Override the physical port with the vPort. */ mlxsw_sp_port = mlxsw_sp_vport; } else { @@ -1257,8 +1275,7 @@ do_fdb_op: if (!do_notification) return; - mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning, - mlxsw_sp_port->learning_sync, + mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning_sync, adding, mac, vid, mlxsw_sp_port->dev); return; @@ -1273,6 +1290,7 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, bool adding) { struct mlxsw_sp_port *mlxsw_sp_port; + struct net_device *dev; char mac[ETH_ALEN]; u16 lag_vid = 0; u16 lag_id; @@ -1298,11 +1316,13 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, goto just_remove; } - vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); - lag_vid = vid; + lag_vid = mlxsw_sp_vport_vid_get(mlxsw_sp_vport); + dev = mlxsw_sp_vport->dev; + vid = 0; /* Override the physical port with the vPort. */ mlxsw_sp_port = mlxsw_sp_vport; } else { + dev = mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev; vid = fid; } @@ -1319,10 +1339,8 @@ do_fdb_op: if (!do_notification) return; - mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning, - mlxsw_sp_port->learning_sync, - adding, mac, vid, - mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev); + mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning_sync, adding, mac, + vid, dev); return; just_remove: @@ -1374,7 +1392,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp = container_of(work, struct mlxsw_sp, fdb_notify.dw.work); - mutex_lock(&mlxsw_sp->fdb_lock); + rtnl_lock(); do { mlxsw_reg_sfn_pack(sfn_pl); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); @@ -1387,7 +1405,7 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); } while (num_rec); - mutex_unlock(&mlxsw_sp->fdb_lock); + rtnl_unlock(); kfree(sfn_pl); mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); @@ -1402,7 +1420,6 @@ static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) dev_err(mlxsw_sp->bus_info->dev, "Failed to set default ageing time\n"); return err; } - mutex_init(&mlxsw_sp->fdb_lock); INIT_DELAYED_WORK(&mlxsw_sp->fdb_notify.dw, mlxsw_sp_fdb_notify_work); mlxsw_sp->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL; mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index a10c928bbd6b..00cfd95ca59d 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -28,6 +28,16 @@ #include "moxart_ether.h" +static inline void moxart_desc_write(u32 data, u32 *desc) +{ + *desc = cpu_to_le32(data); +} + +static inline u32 moxart_desc_read(u32 *desc) +{ + return le32_to_cpu(*desc); +} + static inline void moxart_emac_write(struct net_device *ndev, unsigned int reg, unsigned long value) { @@ -112,7 +122,7 @@ static void moxart_mac_enable(struct net_device *ndev) static void moxart_mac_setup_desc_ring(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - void __iomem *desc; + void *desc; int i; for (i = 0; i < TX_DESC_NUM; i++) { @@ -121,7 +131,7 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) priv->tx_buf[i] = priv->tx_buf_base + priv->tx_buf_size * i; } - writel(TX_DESC1_END, desc + TX_REG_OFFSET_DESC1); + moxart_desc_write(TX_DESC1_END, desc + TX_REG_OFFSET_DESC1); priv->tx_head = 0; priv->tx_tail = 0; @@ -129,8 +139,8 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) for (i = 0; i < RX_DESC_NUM; i++) { desc = priv->rx_desc_base + i * RX_REG_DESC_SIZE; memset(desc, 0, RX_REG_DESC_SIZE); - writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); - writel(RX_BUF_SIZE & RX_DESC1_BUF_SIZE_MASK, + moxart_desc_write(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); + moxart_desc_write(RX_BUF_SIZE & RX_DESC1_BUF_SIZE_MASK, desc + RX_REG_OFFSET_DESC1); priv->rx_buf[i] = priv->rx_buf_base + priv->rx_buf_size * i; @@ -141,12 +151,12 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) if (dma_mapping_error(&ndev->dev, priv->rx_mapping[i])) netdev_err(ndev, "DMA mapping error\n"); - writel(priv->rx_mapping[i], + moxart_desc_write(priv->rx_mapping[i], desc + RX_REG_OFFSET_DESC2 + RX_DESC2_ADDRESS_PHYS); - writel(priv->rx_buf[i], + moxart_desc_write((uintptr_t)priv->rx_buf[i], desc + RX_REG_OFFSET_DESC2 + RX_DESC2_ADDRESS_VIRT); } - writel(RX_DESC1_END, desc + RX_REG_OFFSET_DESC1); + moxart_desc_write(RX_DESC1_END, desc + RX_REG_OFFSET_DESC1); priv->rx_head = 0; @@ -201,14 +211,15 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) napi); struct net_device *ndev = priv->ndev; struct sk_buff *skb; - void __iomem *desc; + void *desc; unsigned int desc0, len; int rx_head = priv->rx_head; int rx = 0; while (rx < budget) { desc = priv->rx_desc_base + (RX_REG_DESC_SIZE * rx_head); - desc0 = readl(desc + RX_REG_OFFSET_DESC0); + desc0 = moxart_desc_read(desc + RX_REG_OFFSET_DESC0); + rmb(); /* ensure desc0 is up to date */ if (desc0 & RX_DESC0_DMA_OWN) break; @@ -250,7 +261,8 @@ static int moxart_rx_poll(struct napi_struct *napi, int budget) priv->stats.multicast++; rx_next: - writel(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); + wmb(); /* prevent setting ownership back too early */ + moxart_desc_write(RX_DESC0_DMA_OWN, desc + RX_REG_OFFSET_DESC0); rx_head = RX_NEXT(rx_head); priv->rx_head = rx_head; @@ -310,7 +322,7 @@ static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id) static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - void __iomem *desc; + void *desc; unsigned int len; unsigned int tx_head = priv->tx_head; u32 txdes1; @@ -319,11 +331,12 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head); spin_lock_irq(&priv->txlock); - if (readl(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { + if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) { net_dbg_ratelimited("no TX space for packet\n"); priv->stats.tx_dropped++; goto out_unlock; } + rmb(); /* ensure data is only read that had TX_DESC0_DMA_OWN cleared */ len = skb->len > TX_BUF_SIZE ? TX_BUF_SIZE : skb->len; @@ -337,9 +350,9 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) priv->tx_len[tx_head] = len; priv->tx_skb[tx_head] = skb; - writel(priv->tx_mapping[tx_head], + moxart_desc_write(priv->tx_mapping[tx_head], desc + TX_REG_OFFSET_DESC2 + TX_DESC2_ADDRESS_PHYS); - writel(skb->data, + moxart_desc_write((uintptr_t)skb->data, desc + TX_REG_OFFSET_DESC2 + TX_DESC2_ADDRESS_VIRT); if (skb->len < ETH_ZLEN) { @@ -354,8 +367,9 @@ static int moxart_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) txdes1 = TX_DESC1_LTS | TX_DESC1_FTS | (len & TX_DESC1_BUF_SIZE_MASK); if (tx_head == TX_DESC_NUM_MASK) txdes1 |= TX_DESC1_END; - writel(txdes1, desc + TX_REG_OFFSET_DESC1); - writel(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0); + moxart_desc_write(txdes1, desc + TX_REG_OFFSET_DESC1); + wmb(); /* flush descriptor before transferring ownership */ + moxart_desc_write(TX_DESC0_DMA_OWN, desc + TX_REG_OFFSET_DESC0); /* start to send packet */ writel(0xffffffff, priv->base + REG_TX_POLL_DEMAND); diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index 2be9280d608c..93a9563ac7c6 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -300,7 +300,7 @@ struct moxart_mac_priv_t { dma_addr_t rx_base; dma_addr_t rx_mapping[RX_DESC_NUM]; - void __iomem *rx_desc_base; + void *rx_desc_base; unsigned char *rx_buf_base; unsigned char *rx_buf[RX_DESC_NUM]; unsigned int rx_head; @@ -308,7 +308,7 @@ struct moxart_mac_priv_t { dma_addr_t tx_base; dma_addr_t tx_mapping[TX_DESC_NUM]; - void __iomem *tx_desc_base; + void *tx_desc_base; unsigned char *tx_buf_base; unsigned char *tx_buf[RX_DESC_NUM]; unsigned int tx_head; diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 50d5604833ed..e0993eba5df3 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -2223,8 +2223,6 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id) return IRQ_NONE; } -#ifdef CONFIG_PCI_MSI - static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id) { struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id; @@ -2442,16 +2440,13 @@ static void vxge_rem_msix_isr(struct vxgedev *vdev) if (vdev->config.intr_type == MSI_X) pci_disable_msix(vdev->pdev); } -#endif static void vxge_rem_isr(struct vxgedev *vdev) { -#ifdef CONFIG_PCI_MSI - if (vdev->config.intr_type == MSI_X) { + if (IS_ENABLED(CONFIG_PCI_MSI) && + vdev->config.intr_type == MSI_X) { vxge_rem_msix_isr(vdev); - } else -#endif - if (vdev->config.intr_type == INTA) { + } else if (vdev->config.intr_type == INTA) { synchronize_irq(vdev->pdev->irq); free_irq(vdev->pdev->irq, vdev); } @@ -2460,11 +2455,10 @@ static void vxge_rem_isr(struct vxgedev *vdev) static int vxge_add_isr(struct vxgedev *vdev) { int ret = 0; -#ifdef CONFIG_PCI_MSI int vp_idx = 0, intr_idx = 0, intr_cnt = 0, msix_idx = 0, irq_req = 0; int pci_fun = PCI_FUNC(vdev->pdev->devfn); - if (vdev->config.intr_type == MSI_X) + if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X) ret = vxge_enable_msix(vdev); if (ret) { @@ -2475,7 +2469,7 @@ static int vxge_add_isr(struct vxgedev *vdev) vdev->config.intr_type = INTA; } - if (vdev->config.intr_type == MSI_X) { + if (IS_ENABLED(CONFIG_PCI_MSI) && vdev->config.intr_type == MSI_X) { for (intr_idx = 0; intr_idx < (vdev->no_of_vpath * VXGE_HW_VPATH_MSIX_ACTIVE); intr_idx++) { @@ -2576,9 +2570,8 @@ static int vxge_add_isr(struct vxgedev *vdev) vdev->vxge_entries[intr_cnt].in_use = 1; vdev->vxge_entries[intr_cnt].arg = &vdev->vpaths[0]; } -INTA_MODE: -#endif +INTA_MODE: if (vdev->config.intr_type == INTA) { snprintf(vdev->desc[0], VXGE_INTR_STRLEN, "%s:vxge:INTA", vdev->ndev->name); @@ -3889,12 +3882,12 @@ static void vxge_device_config_init(struct vxge_hw_device_config *device_config, if (max_mac_vpath > VXGE_MAX_MAC_ADDR_COUNT) max_mac_vpath = VXGE_MAX_MAC_ADDR_COUNT; -#ifndef CONFIG_PCI_MSI - vxge_debug_init(VXGE_ERR, - "%s: This Kernel does not support " - "MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME); - *intr_type = INTA; -#endif + if (!IS_ENABLED(CONFIG_PCI_MSI)) { + vxge_debug_init(VXGE_ERR, + "%s: This Kernel does not support " + "MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME); + *intr_type = INTA; + } /* Configure whether MSI-X or IRQL. */ switch (*intr_type) { diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index a4ab71d43e4e..166a7fc87e2f 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3531,12 +3531,14 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) info.addr = lw->addr; info.vid = lw->vid; + rtnl_lock(); if (learned && removing) call_switchdev_notifiers(SWITCHDEV_FDB_DEL, lw->rocker_port->dev, &info.info); else if (learned && !removing) call_switchdev_notifiers(SWITCHDEV_FDB_ADD, lw->rocker_port->dev, &info.info); + rtnl_unlock(); rocker_port_kfree(lw->trans, work); } diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index cc106d892e29..23fa29877f5b 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -389,17 +389,27 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) if (vio_version_after_eq(&port->vio, 1, 8)) { struct vio_net_dext *dext = vio_net_ext(desc); + skb_reset_network_header(skb); + if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM) { if (skb->protocol == ETH_P_IP) { - struct iphdr *iph = (struct iphdr *)skb->data; + struct iphdr *iph = ip_hdr(skb); iph->check = 0; ip_send_check(iph); } } if ((dext->flags & VNET_PKT_HCK_FULLCKSUM) && - skb->ip_summed == CHECKSUM_NONE) - vnet_fullcsum(skb); + skb->ip_summed == CHECKSUM_NONE) { + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(skb); + int ihl = iph->ihl * 4; + + skb_reset_transport_header(skb); + skb_set_transport_header(skb, ihl); + vnet_fullcsum(skb); + } + } if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM_OK) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_level = 0; diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index 657b65bf5cac..18bf3a8fdc50 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -82,7 +82,7 @@ struct cpdma_desc { struct cpdma_desc_pool { phys_addr_t phys; - u32 hw_addr; + dma_addr_t hw_addr; void __iomem *iomap; /* ioremap map */ void *cpumap; /* dma_alloc map */ int desc_size, mem_size; @@ -152,7 +152,7 @@ struct cpdma_chan { * abstract out these details */ static struct cpdma_desc_pool * -cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr, +cpdma_desc_pool_create(struct device *dev, u32 phys, dma_addr_t hw_addr, int size, int align) { int bitmap_size; @@ -176,13 +176,13 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr, if (phys) { pool->phys = phys; - pool->iomap = ioremap(phys, size); + pool->iomap = ioremap(phys, size); /* should be memremap? */ pool->hw_addr = hw_addr; } else { - pool->cpumap = dma_alloc_coherent(dev, size, &pool->phys, + pool->cpumap = dma_alloc_coherent(dev, size, &pool->hw_addr, GFP_KERNEL); - pool->iomap = pool->cpumap; - pool->hw_addr = pool->phys; + pool->iomap = (void __iomem __force *)pool->cpumap; + pool->phys = pool->hw_addr; /* assumes no IOMMU, don't use this value */ } if (pool->iomap) diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 7f975a2c8990..b0de8ecd7fe8 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -533,8 +533,8 @@ static int dfx_register(struct device *bdev) const char *print_name = dev_name(bdev); struct net_device *dev; DFX_board_t *bp; /* board pointer */ - resource_size_t bar_start[3]; /* pointers to ports */ - resource_size_t bar_len[3]; /* resource length */ + resource_size_t bar_start[3] = {0}; /* pointers to ports */ + resource_size_t bar_len[3] = {0}; /* resource length */ int alloc_size; /* total buffer size used */ struct resource *region; int err = 0; @@ -3697,8 +3697,8 @@ static void dfx_unregister(struct device *bdev) int dfx_bus_pci = dev_is_pci(bdev); int dfx_bus_tc = DFX_BUS_TC(bdev); int dfx_use_mmio = DFX_MMIO || dfx_bus_tc; - resource_size_t bar_start[3]; /* pointers to ports */ - resource_size_t bar_len[3]; /* resource lengths */ + resource_size_t bar_start[3] = {0}; /* pointers to ports */ + resource_size_t bar_len[3] = {0}; /* resource lengths */ int alloc_size; /* total buffer size used */ unregister_netdev(dev); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 7456569f53c1..0b14ac3b8d11 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -980,9 +980,9 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, opts = ip_tunnel_info_opts(info); if (key->tun_flags & TUNNEL_CSUM) - flags |= GENEVE_F_UDP_CSUM; + flags &= ~GENEVE_F_UDP_ZERO_CSUM6_TX; else - flags &= ~GENEVE_F_UDP_CSUM; + flags |= GENEVE_F_UDP_ZERO_CSUM6_TX; err = geneve6_build_skb(dst, skb, key->tun_flags, vni, info->options_len, opts, diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index f4130af09244..fcb92c0d0eb9 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -624,6 +624,7 @@ struct nvsp_message { #define RNDIS_PKT_ALIGN_DEFAULT 8 struct multi_send_data { + struct sk_buff *skb; /* skb containing the pkt */ struct hv_netvsc_packet *pkt; /* netvsc pkt pending */ u32 count; /* counter of batched packets */ }; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 059fc5231601..ec313fc08d82 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -841,6 +841,18 @@ static inline int netvsc_send_pkt( return ret; } +/* Move packet out of multi send data (msd), and clear msd */ +static inline void move_pkt_msd(struct hv_netvsc_packet **msd_send, + struct sk_buff **msd_skb, + struct multi_send_data *msdp) +{ + *msd_skb = msdp->skb; + *msd_send = msdp->pkt; + msdp->skb = NULL; + msdp->pkt = NULL; + msdp->count = 0; +} + int netvsc_send(struct hv_device *device, struct hv_netvsc_packet *packet, struct rndis_message *rndis_msg, @@ -855,6 +867,7 @@ int netvsc_send(struct hv_device *device, unsigned int section_index = NETVSC_INVALID_INDEX; struct multi_send_data *msdp; struct hv_netvsc_packet *msd_send = NULL, *cur_send = NULL; + struct sk_buff *msd_skb = NULL; bool try_batch; bool xmit_more = (skb != NULL) ? skb->xmit_more : false; @@ -897,10 +910,8 @@ int netvsc_send(struct hv_device *device, net_device->send_section_size) { section_index = netvsc_get_next_send_section(net_device); if (section_index != NETVSC_INVALID_INDEX) { - msd_send = msdp->pkt; - msdp->pkt = NULL; - msdp->count = 0; - msd_len = 0; + move_pkt_msd(&msd_send, &msd_skb, msdp); + msd_len = 0; } } @@ -919,31 +930,31 @@ int netvsc_send(struct hv_device *device, packet->total_data_buflen += msd_len; } - if (msdp->pkt) - dev_kfree_skb_any(skb); + if (msdp->skb) + dev_kfree_skb_any(msdp->skb); if (xmit_more && !packet->cp_partial) { + msdp->skb = skb; msdp->pkt = packet; msdp->count++; } else { cur_send = packet; + msdp->skb = NULL; msdp->pkt = NULL; msdp->count = 0; } } else { - msd_send = msdp->pkt; - msdp->pkt = NULL; - msdp->count = 0; + move_pkt_msd(&msd_send, &msd_skb, msdp); cur_send = packet; } if (msd_send) { - m_ret = netvsc_send_pkt(msd_send, net_device, pb, skb); + m_ret = netvsc_send_pkt(msd_send, net_device, NULL, msd_skb); if (m_ret != 0) { netvsc_free_send_slot(net_device, msd_send->send_buf_index); - dev_kfree_skb_any(skb); + dev_kfree_skb_any(msd_skb); } } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 1c8db9afdcda..1d3a66563bac 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -196,65 +196,6 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size, return ppi; } -union sub_key { - u64 k; - struct { - u8 pad[3]; - u8 kb; - u32 ka; - }; -}; - -/* Toeplitz hash function - * data: network byte order - * return: host byte order - */ -static u32 comp_hash(u8 *key, int klen, void *data, int dlen) -{ - union sub_key subk; - int k_next = 4; - u8 dt; - int i, j; - u32 ret = 0; - - subk.k = 0; - subk.ka = ntohl(*(u32 *)key); - - for (i = 0; i < dlen; i++) { - subk.kb = key[k_next]; - k_next = (k_next + 1) % klen; - dt = ((u8 *)data)[i]; - for (j = 0; j < 8; j++) { - if (dt & 0x80) - ret ^= subk.ka; - dt <<= 1; - subk.k <<= 1; - } - } - - return ret; -} - -static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb) -{ - struct flow_keys flow; - int data_len; - - if (!skb_flow_dissect_flow_keys(skb, &flow, 0) || - !(flow.basic.n_proto == htons(ETH_P_IP) || - flow.basic.n_proto == htons(ETH_P_IPV6))) - return false; - - if (flow.basic.ip_proto == IPPROTO_TCP) - data_len = 12; - else - data_len = 8; - - *hash = comp_hash(netvsc_hash_key, HASH_KEYLEN, &flow, data_len); - - return true; -} - static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback) { @@ -267,11 +208,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1) return 0; - if (netvsc_set_hash(&hash, skb)) { - q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % - ndev->real_num_tx_queues; - skb_set_hash(skb, hash, PKT_HASH_TYPE_L3); - } + hash = skb_get_hash(skb); + q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % + ndev->real_num_tx_queues; if (!nvsc_dev->chn_table[q_idx]) q_idx = 0; diff --git a/drivers/net/irda/bfin_sir.h b/drivers/net/irda/bfin_sir.h index 29cbde8501ed..d47cf14bb4a5 100644 --- a/drivers/net/irda/bfin_sir.h +++ b/drivers/net/irda/bfin_sir.h @@ -82,9 +82,6 @@ struct bfin_sir_self { #define DRIVER_NAME "bfin_sir" -#define port_membase(port) (((struct bfin_sir_port *)(port))->membase) -#define get_lsr_cache(port) (((struct bfin_sir_port *)(port))->lsr) -#define put_lsr_cache(port, v) (((struct bfin_sir_port *)(port))->lsr = (v)) #include <asm/bfin_serial.h> static const unsigned short per[][4] = { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 6a57a005e0ca..94e688805dd2 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1323,6 +1323,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, list_add_tail_rcu(&vlan->list, &port->vlans); netif_stacked_transfer_operstate(lowerdev, dev); + linkwatch_fire_event(dev); return 0; @@ -1522,6 +1523,7 @@ static int macvlan_device_event(struct notifier_block *unused, port = macvlan_port_get_rtnl(dev); switch (event) { + case NETDEV_UP: case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) netif_stacked_transfer_operstate(vlan->lowerdev, diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 60994a83a0d6..f0a77020037a 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -186,6 +186,7 @@ config MDIO_GPIO config MDIO_OCTEON tristate "Support for MDIO buses on Octeon and ThunderX SOCs" depends on 64BIT + depends on HAS_IOMEM help This module provides a driver for the Octeon and ThunderX MDIO diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 180f69952779..7a240fce3a7e 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -846,6 +846,11 @@ static void decode_rxts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps *shhwtstamps = NULL; struct sk_buff *skb; unsigned long flags; + u8 overflow; + + overflow = (phy_rxts->ns_hi >> 14) & 0x3; + if (overflow) + pr_debug("rx timestamp queue overflow, count %d\n", overflow); spin_lock_irqsave(&dp83640->rx_lock, flags); @@ -888,6 +893,7 @@ static void decode_txts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps shhwtstamps; struct sk_buff *skb; u64 ns; + u8 overflow; /* We must already have the skb that triggered this. */ @@ -897,6 +903,17 @@ static void decode_txts(struct dp83640_private *dp83640, pr_debug("have timestamp but tx_queue empty\n"); return; } + + overflow = (phy_txts->ns_hi >> 14) & 0x3; + if (overflow) { + pr_debug("tx timestamp queue overflow, count %d\n", overflow); + while (skb) { + skb_complete_tx_timestamp(skb, NULL); + skb = skb_dequeue(&dp83640->tx_queue); + } + return; + } + ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(ns); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 8763bb20988a..5590b9c182c9 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -692,25 +692,29 @@ void phy_change(struct work_struct *work) struct phy_device *phydev = container_of(work, struct phy_device, phy_queue); - if (phydev->drv->did_interrupt && - !phydev->drv->did_interrupt(phydev)) - goto ignore; + if (phy_interrupt_is_valid(phydev)) { + if (phydev->drv->did_interrupt && + !phydev->drv->did_interrupt(phydev)) + goto ignore; - if (phy_disable_interrupts(phydev)) - goto phy_err; + 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); - atomic_dec(&phydev->irq_disable); - enable_irq(phydev->irq); + if (phy_interrupt_is_valid(phydev)) { + atomic_dec(&phydev->irq_disable); + enable_irq(phydev->irq); - /* Reenable interrupts */ - if (PHY_HALTED != phydev->state && - phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED)) - goto irq_enable_err; + /* Reenable interrupts */ + if (PHY_HALTED != phydev->state && + phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED)) + goto irq_enable_err; + } /* reschedule state queue work to run as soon as possible */ cancel_delayed_work_sync(&phydev->state_queue); @@ -905,10 +909,10 @@ void phy_state_machine(struct work_struct *work) phydev->adjust_link(phydev->attached_dev); break; case PHY_RUNNING: - /* Only register a CHANGE if we are polling or ignoring - * interrupts and link changed since latest checking. + /* Only register a CHANGE if we are polling and link changed + * since latest checking. */ - if (!phy_interrupt_is_valid(phydev)) { + if (phydev->irq == PHY_POLL) { old_link = phydev->link; err = phy_read_status(phydev); if (err) @@ -1000,15 +1004,21 @@ void phy_state_machine(struct work_struct *work) phy_state_to_str(old_state), phy_state_to_str(phydev->state)); - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, - PHY_STATE_TIME * HZ); + /* Only re-schedule a PHY state machine change if we are polling the + * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving + * between states from phy_mac_interrupt() + */ + if (phydev->irq == PHY_POLL) + queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, + PHY_STATE_TIME * HZ); } void phy_mac_interrupt(struct phy_device *phydev, int new_link) { - cancel_work_sync(&phydev->phy_queue); phydev->link = new_link; - schedule_work(&phydev->phy_queue); + + /* Trigger a state machine change */ + queue_work(system_power_efficient_wq, &phydev->phy_queue); } EXPORT_SYMBOL(phy_mac_interrupt); diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index e485f2653c82..2e21e9366f76 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -24,6 +24,10 @@ #include <linux/netdevice.h> #include <linux/smscphy.h> +struct smsc_phy_priv { + bool energy_enable; +}; + static int smsc_phy_config_intr(struct phy_device *phydev) { int rc = phy_write (phydev, MII_LAN83C185_IM, @@ -43,19 +47,14 @@ static int smsc_phy_ack_interrupt(struct phy_device *phydev) static int smsc_phy_config_init(struct phy_device *phydev) { - int __maybe_unused len; - struct device *dev __maybe_unused = &phydev->mdio.dev; - struct device_node *of_node __maybe_unused = dev->of_node; + struct smsc_phy_priv *priv = phydev->priv; + int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); - int enable_energy = 1; if (rc < 0) return rc; - if (of_find_property(of_node, "smsc,disable-energy-detect", &len)) - enable_energy = 0; - - if (enable_energy) { + if (priv->energy_enable) { /* Enable energy detect mode for this SMSC Transceivers */ rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, rc | MII_LAN83C185_EDPWRDOWN); @@ -110,10 +109,13 @@ static int lan911x_config_init(struct phy_device *phydev) */ static int lan87xx_read_status(struct phy_device *phydev) { + struct smsc_phy_priv *priv = phydev->priv; + int err = genphy_read_status(phydev); - int i; - if (!phydev->link) { + if (!phydev->link && priv->energy_enable) { + int i; + /* Disable EDPD to wake up PHY */ int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); if (rc < 0) @@ -149,6 +151,26 @@ static int lan87xx_read_status(struct phy_device *phydev) return err; } +static int smsc_phy_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct device_node *of_node = dev->of_node; + struct smsc_phy_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->energy_enable = true; + + if (of_property_read_bool(of_node, "smsc,disable-energy-detect")) + priv->energy_enable = false; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver smsc_phy_driver[] = { { .phy_id = 0x0007c0a0, /* OUI=0x00800f, Model#=0x0a */ @@ -159,6 +181,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -180,6 +204,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -201,6 +227,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = lan87xx_read_status, @@ -222,6 +250,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, @@ -242,6 +272,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = lan87xx_read_status, @@ -263,6 +295,8 @@ static struct phy_driver smsc_phy_driver[] = { | SUPPORTED_Asym_Pause), .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + .probe = smsc_phy_probe, + /* basic functions */ .config_aneg = genphy_config_aneg, .read_status = lan87xx_read_status, diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 90868ca5e341..ae0905ed4a32 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -129,24 +129,27 @@ static int lookup_chan_dst(u16 call_id, __be32 d_addr) return i < MAX_CALLID; } -static int add_chan(struct pppox_sock *sock) +static int add_chan(struct pppox_sock *sock, + struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); - if (!sock->proto.pptp.src_addr.call_id) { + if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } - sock->proto.pptp.src_addr.call_id = call_id; - } else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap)) + sa->call_id = call_id; + } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; + } - set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); - rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock); + sock->proto.pptp.src_addr = *sa; + set_bit(sa->call_id, callid_bitmap); + rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; @@ -416,7 +419,6 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); - struct pptp_opt *opt = &po->proto.pptp; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) @@ -424,10 +426,22 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); - opt->src_addr = sp->sa_addr.pptp; - if (add_chan(po)) + if (sk->sk_state & PPPOX_DEAD) { + error = -EALREADY; + goto out; + } + + if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; + goto out; + } + + if (add_chan(po, &sp->sa_addr.pptp)) + error = -EBUSY; + else + sk->sk_state |= PPPOX_BOUND; +out: release_sock(sk); return error; } @@ -498,7 +512,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, } opt->dst_addr = sp->sa_addr.pptp; - sk->sk_state = PPPOX_CONNECTED; + sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 2ed53331bfb2..1c299b8a162d 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -36,7 +36,7 @@ #define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>" #define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices" #define DRIVER_NAME "lan78xx" -#define DRIVER_VERSION "1.0.1" +#define DRIVER_VERSION "1.0.2" #define TX_TIMEOUT_JIFFIES (5 * HZ) #define THROTTLE_JIFFIES (HZ / 8) @@ -462,32 +462,53 @@ static int lan78xx_read_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u32 val; + u32 saved; int i, ret; + int retval; - ret = lan78xx_eeprom_confirm_not_busy(dev); - if (ret) - return ret; + /* depends on chip, some EEPROM pins are muxed with LED function. + * disable & restore LED function to access EEPROM. + */ + ret = lan78xx_read_reg(dev, HW_CFG, &val); + saved = val; + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) { + val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); + ret = lan78xx_write_reg(dev, HW_CFG, val); + } + + retval = lan78xx_eeprom_confirm_not_busy(dev); + if (retval) + return retval; for (i = 0; i < length; i++) { val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (unlikely(ret < 0)) - return -EIO; + if (unlikely(ret < 0)) { + retval = -EIO; + goto exit; + } - ret = lan78xx_wait_eeprom(dev); - if (ret < 0) - return ret; + retval = lan78xx_wait_eeprom(dev); + if (retval < 0) + goto exit; ret = lan78xx_read_reg(dev, E2P_DATA, &val); - if (unlikely(ret < 0)) - return -EIO; + if (unlikely(ret < 0)) { + retval = -EIO; + goto exit; + } data[i] = val & 0xFF; offset++; } - return 0; + retval = 0; +exit: + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) + ret = lan78xx_write_reg(dev, HW_CFG, saved); + + return retval; } static int lan78xx_read_eeprom(struct lan78xx_net *dev, u32 offset, @@ -509,44 +530,67 @@ static int lan78xx_write_raw_eeprom(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { u32 val; + u32 saved; int i, ret; + int retval; - ret = lan78xx_eeprom_confirm_not_busy(dev); - if (ret) - return ret; + /* depends on chip, some EEPROM pins are muxed with LED function. + * disable & restore LED function to access EEPROM. + */ + ret = lan78xx_read_reg(dev, HW_CFG, &val); + saved = val; + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) { + val &= ~(HW_CFG_LED1_EN_ | HW_CFG_LED0_EN_); + ret = lan78xx_write_reg(dev, HW_CFG, val); + } + + retval = lan78xx_eeprom_confirm_not_busy(dev); + if (retval) + goto exit; /* Issue write/erase enable command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_; ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (unlikely(ret < 0)) - return -EIO; + if (unlikely(ret < 0)) { + retval = -EIO; + goto exit; + } - ret = lan78xx_wait_eeprom(dev); - if (ret < 0) - return ret; + retval = lan78xx_wait_eeprom(dev); + if (retval < 0) + goto exit; for (i = 0; i < length; i++) { /* Fill data register */ val = data[i]; ret = lan78xx_write_reg(dev, E2P_DATA, val); - if (ret < 0) - return ret; + if (ret < 0) { + retval = -EIO; + goto exit; + } /* Send "write" command */ val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_; val |= (offset & E2P_CMD_EPC_ADDR_MASK_); ret = lan78xx_write_reg(dev, E2P_CMD, val); - if (ret < 0) - return ret; + if (ret < 0) { + retval = -EIO; + goto exit; + } - ret = lan78xx_wait_eeprom(dev); - if (ret < 0) - return ret; + retval = lan78xx_wait_eeprom(dev); + if (retval < 0) + goto exit; offset++; } - return 0; + retval = 0; +exit: + if ((dev->devid & ID_REV_CHIP_ID_MASK_) == 0x78000000) + ret = lan78xx_write_reg(dev, HW_CFG, saved); + + return retval; } static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, @@ -904,7 +948,6 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) if (!phydev->link && dev->link_on) { dev->link_on = false; - netif_carrier_off(dev->net); /* reset MAC */ ret = lan78xx_read_reg(dev, MAC_CR, &buf); @@ -914,6 +957,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ret = lan78xx_write_reg(dev, MAC_CR, buf); if (unlikely(ret < 0)) return -EIO; + + phy_mac_interrupt(phydev, 0); } else if (phydev->link && !dev->link_on) { dev->link_on = true; @@ -953,7 +998,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ethtool_cmd_speed(&ecmd), ecmd.duplex, ladv, radv); ret = lan78xx_update_flowcontrol(dev, ecmd.duplex, ladv, radv); - netif_carrier_on(dev->net); + phy_mac_interrupt(phydev, 1); } return ret; @@ -1495,7 +1540,6 @@ done: static int lan78xx_mdio_init(struct lan78xx_net *dev) { int ret; - int i; dev->mdiobus = mdiobus_alloc(); if (!dev->mdiobus) { @@ -1511,10 +1555,6 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); - /* handle our own interrupt */ - for (i = 0; i < PHY_MAX_ADDR; i++) - dev->mdiobus->irq[i] = PHY_IGNORE_INTERRUPT; - switch (dev->devid & ID_REV_CHIP_ID_MASK_) { case 0x78000000: case 0x78500000: @@ -1558,6 +1598,16 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) return -EIO; } + /* Enable PHY interrupts. + * We handle our own interrupt + */ + ret = phy_read(phydev, LAN88XX_INT_STS); + ret = phy_write(phydev, LAN88XX_INT_MASK, + LAN88XX_INT_MASK_MDINTPIN_EN_ | + LAN88XX_INT_MASK_LINK_CHANGE_); + + phydev->irq = PHY_IGNORE_INTERRUPT; + ret = phy_connect_direct(dev->net, phydev, lan78xx_link_status_change, PHY_INTERFACE_MODE_GMII); @@ -1580,14 +1630,6 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) SUPPORTED_Pause | SUPPORTED_Asym_Pause); genphy_config_aneg(phydev); - /* Workaround to enable PHY interrupt. - * phy_start_interrupts() is API for requesting and enabling - * PHY interrupt. However, USB-to-Ethernet device can't use - * request_irq() called in phy_start_interrupts(). - * Set PHY to PHY_HALTED and call phy_start() - * to make a call to phy_enable_interrupts() - */ - phy_stop(phydev); phy_start(phydev); netif_dbg(dev, ifup, dev->net, "phy initialised successfully"); @@ -2221,7 +2263,9 @@ netdev_tx_t lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) if (skb2) { skb_queue_tail(&dev->txq_pend, skb2); - if (skb_queue_len(&dev->txq_pend) > 10) + /* throttle TX patch at slower than SUPER SPEED USB */ + if ((dev->udev->speed < USB_SPEED_SUPER) && + (skb_queue_len(&dev->txq_pend) > 10)) netif_stop_queue(net); } else { netif_dbg(dev, tx_err, dev->net, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 2d88c799d2ac..65439188c582 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -73,7 +73,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int vxlan_net_id; static struct rtnl_link_ops vxlan_link_ops; -static const u8 all_zeros_mac[ETH_ALEN]; +static const u8 all_zeros_mac[ETH_ALEN + 2]; static int vxlan_sock_add(struct vxlan_dev *vxlan); @@ -1985,11 +1985,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, vxlan->cfg.port_max, true); if (info) { - if (info->key.tun_flags & TUNNEL_CSUM) - flags |= VXLAN_F_UDP_CSUM; - else - flags &= ~VXLAN_F_UDP_CSUM; - ttl = info->key.ttl; tos = info->key.tos; @@ -2004,8 +1999,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto drop; sk = vxlan->vn4_sock->sock->sk; - if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)) - df = htons(IP_DF); + if (info) { + if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + + if (info->key.tun_flags & TUNNEL_CSUM) + flags |= VXLAN_F_UDP_CSUM; + else + flags &= ~VXLAN_F_UDP_CSUM; + } memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0; @@ -2101,6 +2103,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } + if (info) { + if (info->key.tun_flags & TUNNEL_CSUM) + flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX; + else + flags |= VXLAN_F_UDP_ZERO_CSUM6_TX; + } + ttl = ttl ? : ip6_dst_hoplimit(ndst); err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr, 0, ttl, src_port, dst_port, htonl(vni << 8), md, diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index a7afdeee698c..73fb4232f9f2 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -150,18 +150,18 @@ int ath9k_hw_nvram_swap_data(struct ath_hw *ah, bool *swap_needed, int size) return -EIO; } - if (magic == AR5416_EEPROM_MAGIC) { - *swap_needed = false; - } else if (swab16(magic) == AR5416_EEPROM_MAGIC) { + *swap_needed = false; + if (swab16(magic) == AR5416_EEPROM_MAGIC) { if (ah->ah_flags & AH_NO_EEP_SWAP) { ath_info(common, "Ignoring endianness difference in EEPROM magic bytes.\n"); - - *swap_needed = false; } else { *swap_needed = true; } - } else { + } else if (magic != AR5416_EEPROM_MAGIC) { + if (ath9k_hw_use_flash(ah)) + return 0; + ath_err(common, "Invalid EEPROM Magic (0x%04x).\n", magic); return -EINVAL; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 53637399bb99..b98db8a0a069 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -879,11 +879,24 @@ int brcmf_sdiod_abort(struct brcmf_sdio_dev *sdiodev, uint fn) return 0; } -static void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) +void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) { + struct sdio_func *func; + struct mmc_host *host; + uint max_blocks; uint nents; int err; + func = sdiodev->func[2]; + host = func->card->host; + sdiodev->sg_support = host->max_segs > 1; + max_blocks = min_t(uint, host->max_blk_count, 511u); + sdiodev->max_request_size = min_t(uint, host->max_req_size, + max_blocks * func->cur_blksize); + sdiodev->max_segment_count = min_t(uint, host->max_segs, + SG_MAX_SINGLE_ALLOC); + sdiodev->max_segment_size = host->max_seg_size; + if (!sdiodev->sg_support) return; @@ -1021,9 +1034,6 @@ static void brcmf_sdiod_host_fixup(struct mmc_host *host) static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) { - struct sdio_func *func; - struct mmc_host *host; - uint max_blocks; int ret = 0; sdiodev->num_funcs = 2; @@ -1054,26 +1064,6 @@ static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) goto out; } - /* - * determine host related variables after brcmf_sdiod_probe() - * as func->cur_blksize is properly set and F2 init has been - * completed successfully. - */ - func = sdiodev->func[2]; - host = func->card->host; - sdiodev->sg_support = host->max_segs > 1; - max_blocks = min_t(uint, host->max_blk_count, 511u); - sdiodev->max_request_size = min_t(uint, host->max_req_size, - max_blocks * func->cur_blksize); - sdiodev->max_segment_count = min_t(uint, host->max_segs, - SG_MAX_SINGLE_ALLOC); - sdiodev->max_segment_size = host->max_seg_size; - - /* allocate scatter-gather table. sg support - * will be disabled upon allocation failure. - */ - brcmf_sdiod_sgtable_alloc(sdiodev); - ret = brcmf_sdiod_freezer_attach(sdiodev); if (ret) goto out; @@ -1084,7 +1074,7 @@ static int brcmf_sdiod_probe(struct brcmf_sdio_dev *sdiodev) ret = -ENODEV; goto out; } - brcmf_sdiod_host_fixup(host); + brcmf_sdiod_host_fixup(sdiodev->func[2]->card->host); out: if (ret) brcmf_sdiod_remove(sdiodev); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index 4265b50faa98..cfee477a6eb1 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/netdevice.h> +#include <linux/module.h> #include <brcmu_wifi.h> #include <brcmu_utils.h> #include "core.h" diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index dd6614332836..a14d9d9da094 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4114,6 +4114,11 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev) goto fail; } + /* allocate scatter-gather table. sg support + * will be disabled upon allocation failure. + */ + brcmf_sdiod_sgtable_alloc(bus->sdiodev); + /* Query the F2 block size, set roundup accordingly */ bus->blocksize = bus->sdiodev->func[2]->cur_blksize; bus->roundup = min(max_roundup, bus->blocksize); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h index 5ec7a6d87672..23f223150cef 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h @@ -342,6 +342,7 @@ int brcmf_sdiod_ramrw(struct brcmf_sdio_dev *sdiodev, bool write, u32 address, /* Issue an abort to the specified function */ int brcmf_sdiod_abort(struct brcmf_sdio_dev *sdiodev, uint fn); +void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev); void brcmf_sdiod_change_state(struct brcmf_sdio_dev *sdiodev, enum brcmf_sdiod_state state); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c index e60cf141ed79..fa41a5e1c890 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-7000.c @@ -74,16 +74,19 @@ #define IWL7260_UCODE_API_MAX 17 #define IWL7265_UCODE_API_MAX 17 #define IWL7265D_UCODE_API_MAX 20 +#define IWL3168_UCODE_API_MAX 20 /* Oldest version we won't warn about */ #define IWL7260_UCODE_API_OK 13 #define IWL7265_UCODE_API_OK 13 #define IWL7265D_UCODE_API_OK 13 +#define IWL3168_UCODE_API_OK 20 /* Lowest firmware API version supported */ #define IWL7260_UCODE_API_MIN 13 #define IWL7265_UCODE_API_MIN 13 #define IWL7265D_UCODE_API_MIN 13 +#define IWL3168_UCODE_API_MIN 20 /* NVM versions */ #define IWL7260_NVM_VERSION 0x0a1d @@ -92,6 +95,8 @@ #define IWL3160_TX_POWER_VERSION 0xffff /* meaningless */ #define IWL3165_NVM_VERSION 0x709 #define IWL3165_TX_POWER_VERSION 0xffff /* meaningless */ +#define IWL3168_NVM_VERSION 0xd01 +#define IWL3168_TX_POWER_VERSION 0xffff /* meaningless */ #define IWL7265_NVM_VERSION 0x0a1d #define IWL7265_TX_POWER_VERSION 0xffff /* meaningless */ #define IWL7265D_NVM_VERSION 0x0c11 @@ -109,6 +114,9 @@ #define IWL3160_FW_PRE "iwlwifi-3160-" #define IWL3160_MODULE_FIRMWARE(api) IWL3160_FW_PRE __stringify(api) ".ucode" +#define IWL3168_FW_PRE "iwlwifi-3168-" +#define IWL3168_MODULE_FIRMWARE(api) IWL3168_FW_PRE __stringify(api) ".ucode" + #define IWL7265_FW_PRE "iwlwifi-7265-" #define IWL7265_MODULE_FIRMWARE(api) IWL7265_FW_PRE __stringify(api) ".ucode" @@ -180,6 +188,12 @@ static const struct iwl_ht_params iwl7000_ht_params = { .ucode_api_ok = IWL7265_UCODE_API_OK, \ .ucode_api_min = IWL7265_UCODE_API_MIN +#define IWL_DEVICE_3008 \ + IWL_DEVICE_7000_COMMON, \ + .ucode_api_max = IWL3168_UCODE_API_MAX, \ + .ucode_api_ok = IWL3168_UCODE_API_OK, \ + .ucode_api_min = IWL3168_UCODE_API_MIN + #define IWL_DEVICE_7005D \ IWL_DEVICE_7000_COMMON, \ .ucode_api_max = IWL7265D_UCODE_API_MAX, \ @@ -299,11 +313,11 @@ const struct iwl_cfg iwl3165_2ac_cfg = { const struct iwl_cfg iwl3168_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 3168", - .fw_name_pre = IWL7265D_FW_PRE, - IWL_DEVICE_7000, + .fw_name_pre = IWL3168_FW_PRE, + IWL_DEVICE_3008, .ht_params = &iwl7000_ht_params, - .nvm_ver = IWL3165_NVM_VERSION, - .nvm_calib_ver = IWL3165_TX_POWER_VERSION, + .nvm_ver = IWL3168_NVM_VERSION, + .nvm_calib_ver = IWL3168_TX_POWER_VERSION, .pwr_tx_backoffs = iwl7265_pwr_tx_backoffs, .dccm_len = IWL7265_DCCM_LEN, }; @@ -376,5 +390,6 @@ const struct iwl_cfg iwl7265d_n_cfg = { MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); +MODULE_FIRMWARE(IWL3168_MODULE_FIRMWARE(IWL3168_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7265_UCODE_API_OK)); MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7265D_UCODE_API_OK)); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h index 0036d18334af..ba3f0bbddde8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api-tx.h @@ -510,6 +510,9 @@ struct iwl_mvm_tx_resp { * @scd_ssn: the index of the last contiguously sent packet * @txed: number of Txed frames in this batch * @txed_2_done: number of Acked frames in this batch + * @reduced_txp: power reduced according to TPC. This is the actual value and + * not a copy from the LQ command. Thus, if not the first rate was used + * for Tx-ing then this value will be set to 0 by FW. */ struct iwl_mvm_ba_notif { __le32 sta_addr_lo32; @@ -524,7 +527,8 @@ struct iwl_mvm_ba_notif { __le16 scd_ssn; u8 txed; u8 txed_2_done; - __le16 reserved1; + u8 reduced_txp; + u8 reserved1; } __packed; /* diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 7bb6fd0e4391..94caa88df442 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2,6 +2,7 @@ * * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * 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 @@ -724,14 +725,28 @@ static int _rs_collect_tx_data(struct iwl_mvm *mvm, return 0; } -static int rs_collect_tx_data(struct iwl_mvm *mvm, - struct iwl_lq_sta *lq_sta, - struct iwl_scale_tbl_info *tbl, - int scale_index, int attempts, int successes, - u8 reduced_txp) +static int rs_collect_tpc_data(struct iwl_mvm *mvm, + struct iwl_lq_sta *lq_sta, + struct iwl_scale_tbl_info *tbl, + int scale_index, int attempts, int successes, + u8 reduced_txp) +{ + struct iwl_rate_scale_data *window = NULL; + + if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION)) + return -EINVAL; + + window = &tbl->tpc_win[reduced_txp]; + return _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes, + window); +} + +static int rs_collect_tlc_data(struct iwl_mvm *mvm, + struct iwl_lq_sta *lq_sta, + struct iwl_scale_tbl_info *tbl, + int scale_index, int attempts, int successes) { struct iwl_rate_scale_data *window = NULL; - int ret; if (scale_index < 0 || scale_index >= IWL_RATE_COUNT) return -EINVAL; @@ -745,16 +760,6 @@ static int rs_collect_tx_data(struct iwl_mvm *mvm, /* Select window for current tx bit rate */ window = &(tbl->win[scale_index]); - - ret = _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes, - window); - if (ret) - return ret; - - if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION)) - return -EINVAL; - - window = &tbl->tpc_win[reduced_txp]; return _rs_collect_tx_data(mvm, tbl, scale_index, attempts, successes, window); } @@ -1301,17 +1306,30 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, * first index into rate scale table. */ if (info->flags & IEEE80211_TX_STAT_AMPDU) { - /* ampdu_ack_len = 0 marks no BA was received. In this case - * treat it as a single frame loss as we don't want the success - * ratio to dip too quickly because a BA wasn't received + rs_collect_tpc_data(mvm, lq_sta, curr_tbl, lq_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len, + reduced_txp); + + /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat + * it as a single frame loss as we don't want the success ratio + * to dip too quickly because a BA wasn't received. + * For TPC, there's no need for this optimisation since we want + * to recover very quickly from a bad power reduction and, + * therefore we'd like the success ratio to get an immediate hit + * when failing to get a BA, so we'd switch back to a lower or + * zero power reduction. When FW transmits agg with a rate + * different from the initial rate, it will not use reduced txp + * and will send BA notification twice (one empty with reduced + * txp equal to the value from LQ and one with reduced txp 0). + * We need to update counters for each txp level accordingly. */ if (info->status.ampdu_ack_len == 0) info->status.ampdu_len = 1; - rs_collect_tx_data(mvm, lq_sta, curr_tbl, lq_rate.index, - info->status.ampdu_len, - info->status.ampdu_ack_len, - reduced_txp); + rs_collect_tlc_data(mvm, lq_sta, curr_tbl, lq_rate.index, + info->status.ampdu_len, + info->status.ampdu_ack_len); /* Update success/fail counts if not searching for new mode */ if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) { @@ -1344,9 +1362,13 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, else continue; - rs_collect_tx_data(mvm, lq_sta, tmp_tbl, lq_rate.index, - 1, i < retries ? 0 : legacy_success, - reduced_txp); + rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, + lq_rate.index, 1, + i < retries ? 0 : legacy_success, + reduced_txp); + rs_collect_tlc_data(mvm, lq_sta, tmp_tbl, + lq_rate.index, 1, + i < retries ? 0 : legacy_success); } /* Update success/fail counts if not searching for new mode */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 8bf48a7d0f4e..0914ec2fd574 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1029,7 +1029,6 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); mvmsta->tid_data[tid].rate_n_flags = le32_to_cpu(tx_resp->initial_rate); - mvmsta->tid_data[tid].reduced_tpc = tx_resp->reduced_tpc; mvmsta->tid_data[tid].tx_time = le16_to_cpu(tx_resp->wireless_media_time); } @@ -1060,7 +1059,7 @@ static void iwl_mvm_tx_info_from_ba_notif(struct ieee80211_tx_info *info, /* TODO: not accounted if the whole A-MPDU failed */ info->status.tx_time = tid_data->tx_time; info->status.status_driver_data[0] = - (void *)(uintptr_t)tid_data->reduced_tpc; + (void *)(uintptr_t)ba_notif->reduced_txp; info->status.status_driver_data[1] = (void *)(uintptr_t)tid_data->rate_n_flags; } @@ -1133,6 +1132,8 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) scd_flow, ba_resp_scd_ssn, ba_notif->txed, ba_notif->txed_2_done); + IWL_DEBUG_TX_REPLY(mvm, "reduced txp from ba notif %d\n", + ba_notif->reduced_txp); tid_data->next_reclaimed = ba_resp_scd_ssn; iwl_mvm_check_ratid_empty(mvm, sta, tid); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 6261a68cae90..00335ea6b3eb 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -378,7 +378,10 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x3165, 0x8110, iwl3165_2ac_cfg)}, /* 3168 Series */ + {IWL_PCI_DEVICE(0x24FB, 0x2010, iwl3168_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FB, 0x2110, iwl3168_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FB, 0x2050, iwl3168_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FB, 0x2150, iwl3168_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FB, 0x0000, iwl3168_2ac_cfg)}, /* 7265 Series */ @@ -475,6 +478,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8265_2ac_cfg)}, /* 9000 Series */ {IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl5165_2ac_cfg)}, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index c32889a1e39c..a28414c50edf 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -991,7 +991,8 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, goto nla_put_failure; } - if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, ETH_ALEN, hdr->addr2)) + if (nla_put(skb, HWSIM_ATTR_ADDR_TRANSMITTER, + ETH_ALEN, data->addresses[1].addr)) goto nla_put_failure; /* We get the skb->data */ @@ -2736,7 +2737,7 @@ static struct mac80211_hwsim_data *get_hwsim_data_ref_from_addr(const u8 *addr) spin_lock_bh(&hwsim_radio_lock); list_for_each_entry(data, &hwsim_radios, list) { - if (mac80211_hwsim_addr_match(data, addr)) { + if (memcmp(data->addresses[1].addr, addr, ETH_ALEN) == 0) { _found = true; break; } diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c index 9a3966cd6fbe..155f343981fe 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c @@ -273,8 +273,10 @@ static void rt2400pci_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, RXCSR0_DROP_CONTROL, !(filter_flags & FIF_CONTROL)); - rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, RXCSR0_DROP_TODS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, RXCSR0_DROP_VERSION_ERROR, 1); rt2x00mmio_register_write(rt2x00dev, RXCSR0, reg); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c index 1a6740b4d396..2553cdd74066 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c @@ -274,8 +274,10 @@ static void rt2500pci_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, RXCSR0_DROP_CONTROL, !(filter_flags & FIF_CONTROL)); - rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, RXCSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, RXCSR0_DROP_TODS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, RXCSR0_DROP_VERSION_ERROR, 1); rt2x00_set_field32(®, RXCSR0_DROP_MCAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c index d26018f30b7d..2d64611de300 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c @@ -437,8 +437,10 @@ static void rt2500usb_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field16(®, TXRX_CSR2_DROP_CONTROL, !(filter_flags & FIF_CONTROL)); - rt2x00_set_field16(®, TXRX_CSR2_DROP_NOT_TO_ME, 1); + rt2x00_set_field16(®, TXRX_CSR2_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field16(®, TXRX_CSR2_DROP_TODS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field16(®, TXRX_CSR2_DROP_VERSION_ERROR, 1); rt2x00_set_field16(®, TXRX_CSR2_DROP_MULTICAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 9733b31a780d..a26afcab03ed 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -1490,7 +1490,8 @@ void rt2800_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_FCSFAIL)); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_PHY_ERROR, !(filter_flags & FIF_PLCPFAIL)); - rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_NOT_MY_BSSD, 0); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_VER_ERROR, 1); rt2x00_set_field32(®, RX_FILTER_CFG_DROP_MULTICAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h index 3282ddb766f4..26427140a963 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h @@ -669,6 +669,7 @@ enum rt2x00_state_flags { CONFIG_POWERSAVING, CONFIG_HT_DISABLED, CONFIG_QOS_DISABLED, + CONFIG_MONITORING, /* * Mark we currently are sequentially reading TX_STA_FIFO register diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00config.c b/drivers/net/wireless/ralink/rt2x00/rt2x00config.c index 7e8bb1198ae9..6a1f508d472f 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00config.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00config.c @@ -277,6 +277,11 @@ void rt2x00lib_config(struct rt2x00_dev *rt2x00dev, else clear_bit(CONFIG_POWERSAVING, &rt2x00dev->flags); + if (conf->flags & IEEE80211_CONF_MONITOR) + set_bit(CONFIG_MONITORING, &rt2x00dev->flags); + else + clear_bit(CONFIG_MONITORING, &rt2x00dev->flags); + rt2x00dev->curr_band = conf->chandef.chan->band; rt2x00dev->curr_freq = conf->chandef.chan->center_freq; rt2x00dev->tx_power = conf->power_level; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c index 3c26ee65a415..13da95a24cf7 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c @@ -385,11 +385,6 @@ void rt2x00mac_configure_filter(struct ieee80211_hw *hw, *total_flags |= FIF_PSPOLL; } - /* - * Check if there is any work left for us. - */ - if (rt2x00dev->packet_filter == *total_flags) - return; rt2x00dev->packet_filter = *total_flags; rt2x00dev->ops->lib->config_filter(rt2x00dev, *total_flags); diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c index c0e730ea1b69..24a3436ef952 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c @@ -530,8 +530,10 @@ static void rt61pci_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, TXRX_CSR0_DROP_CONTROL, !(filter_flags & (FIF_CONTROL | FIF_PSPOLL))); - rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, TXRX_CSR0_DROP_TO_DS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, TXRX_CSR0_DROP_VERSION_ERROR, 1); rt2x00_set_field32(®, TXRX_CSR0_DROP_MULTICAST, diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.c b/drivers/net/wireless/ralink/rt2x00/rt73usb.c index 7081e13b4fd6..7bbc86931168 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt73usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.c @@ -480,8 +480,10 @@ static void rt73usb_config_filter(struct rt2x00_dev *rt2x00dev, !(filter_flags & FIF_PLCPFAIL)); rt2x00_set_field32(®, TXRX_CSR0_DROP_CONTROL, !(filter_flags & (FIF_CONTROL | FIF_PSPOLL))); - rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, 1); + rt2x00_set_field32(®, TXRX_CSR0_DROP_NOT_TO_ME, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags)); rt2x00_set_field32(®, TXRX_CSR0_DROP_TO_DS, + !test_bit(CONFIG_MONITORING, &rt2x00dev->flags) && !rt2x00dev->intf_ap_count); rt2x00_set_field32(®, TXRX_CSR0_DROP_VERSION_ERROR, 1); rt2x00_set_field32(®, TXRX_CSR0_DROP_MULTICAST, diff --git a/drivers/net/wireless/realtek/rtlwifi/regd.c b/drivers/net/wireless/realtek/rtlwifi/regd.c index a62bf0a65c32..5be34118e0af 100644 --- a/drivers/net/wireless/realtek/rtlwifi/regd.c +++ b/drivers/net/wireless/realtek/rtlwifi/regd.c @@ -351,7 +351,6 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( case COUNTRY_CODE_SPAIN: case COUNTRY_CODE_FRANCE: case COUNTRY_CODE_ISRAEL: - case COUNTRY_CODE_WORLD_WIDE_13: return &rtl_regdom_12_13; case COUNTRY_CODE_MKK: case COUNTRY_CODE_MKK1: @@ -360,6 +359,7 @@ static const struct ieee80211_regdomain *_rtl_regdomain_select( return &rtl_regdom_14_60_64; case COUNTRY_CODE_GLOBAL_DOMAIN: return &rtl_regdom_14; + case COUNTRY_CODE_WORLD_WIDE_13: case COUNTRY_CODE_WORLD_WIDE_13_5G_ALL: return &rtl_regdom_12_13_5g_all; default: diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index d6abf191122a..96ccd4e943db 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -364,6 +364,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) RING_IDX cons, prod; unsigned short id; struct sk_buff *skb; + bool more_to_do; BUG_ON(!netif_carrier_ok(queue->info->netdev)); @@ -398,18 +399,8 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) queue->tx.rsp_cons = prod; - /* - * Set a new event, then check for race with update of tx_cons. - * Note that it is essential to schedule a callback, no matter - * how few buffers are pending. Even if there is space in the - * transmit ring, higher layers may be blocked because too much - * data is outstanding: in such cases notification from Xen is - * likely to be the only kick that we'll get. - */ - queue->tx.sring->rsp_event = - prod + ((queue->tx.sring->req_prod - prod) >> 1) + 1; - mb(); /* update shared area */ - } while ((cons == prod) && (prod != queue->tx.sring->rsp_prod)); + RING_FINAL_CHECK_FOR_RESPONSES(&queue->tx, more_to_do); + } while (more_to_do); xennet_maybe_wake_tx(queue); } diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 8ebfcaae3f5a..9edf7eb7d17c 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1277,10 +1277,12 @@ static ssize_t mode_show(struct device *dev, device_lock(dev); claim = ndns->claim; - if (pmem_should_map_pages(dev) || (claim && is_nd_pfn(claim))) - mode = "memory"; - else if (claim && is_nd_btt(claim)) + if (claim && is_nd_btt(claim)) mode = "safe"; + else if (claim && is_nd_pfn(claim)) + mode = "memory"; + else if (!claim && pmem_should_map_pages(dev)) + mode = "memory"; else mode = "raw"; rc = sprintf(buf, "%s\n", mode); diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 0cc9048b86e2..ae81a2f1da50 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -301,10 +301,8 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn) switch (le32_to_cpu(pfn_sb->mode)) { case PFN_MODE_RAM: - break; case PFN_MODE_PMEM: - /* TODO: allocate from PMEM support */ - return -ENOTTY; + break; default: return -ENXIO; } diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 706e3ff67f8b..7ee21ae305ae 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -679,18 +679,6 @@ u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in) return __of_msi_map_rid(dev, &msi_np, rid_in); } -static struct irq_domain *__of_get_msi_domain(struct device_node *np, - enum irq_domain_bus_token token) -{ - struct irq_domain *d; - - d = irq_find_matching_host(np, token); - if (!d) - d = irq_find_host(np); - - return d; -} - /** * of_msi_map_get_device_domain - Use msi-map to find the relevant MSI domain * @dev: device for which the mapping is to be done. @@ -706,7 +694,7 @@ struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid) struct device_node *np = NULL; __of_msi_map_rid(dev, &np, rid); - return __of_get_msi_domain(np, DOMAIN_BUS_PCI_MSI); + return irq_find_matching_host(np, DOMAIN_BUS_PCI_MSI); } /** @@ -730,7 +718,7 @@ struct irq_domain *of_msi_get_domain(struct device *dev, /* Check for a single msi-parent property */ msi_np = of_parse_phandle(np, "msi-parent", 0); if (msi_np && !of_property_read_bool(msi_np, "#msi-cells")) { - d = __of_get_msi_domain(msi_np, token); + d = irq_find_matching_host(msi_np, token); if (!d) of_node_put(msi_np); return d; @@ -744,7 +732,7 @@ struct irq_domain *of_msi_get_domain(struct device *dev, while (!of_parse_phandle_with_args(np, "msi-parent", "#msi-cells", index, &args)) { - d = __of_get_msi_domain(args.np, token); + d = irq_find_matching_host(args.np, token); if (d) return d; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 86829f8064a6..5648317d355f 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -143,11 +143,31 @@ int of_mdio_parse_addr(struct device *dev, const struct device_node *np) } EXPORT_SYMBOL(of_mdio_parse_addr); +/* The following is a list of PHY compatible strings which appear in + * some DTBs. The compatible string is never matched against a PHY + * driver, so is pointless. We only expect devices which are not PHYs + * to have a compatible string, so they can be matched to an MDIO + * driver. Encourage users to upgrade their DT blobs to remove these. + */ +static const struct of_device_id whitelist_phys[] = { + { .compatible = "brcm,40nm-ephy" }, + { .compatible = "marvell,88E1111", }, + { .compatible = "marvell,88e1116", }, + { .compatible = "marvell,88e1118", }, + { .compatible = "marvell,88e1149r", }, + { .compatible = "marvell,88e1310", }, + { .compatible = "marvell,88E1510", }, + { .compatible = "marvell,88E1514", }, + { .compatible = "moxa,moxart-rtl8201cp", }, + {} +}; + /* * Return true if the child node is for a phy. It must either: * o Compatible string of "ethernet-phy-idX.X" * o Compatible string of "ethernet-phy-ieee802.3-c45" * o Compatible string of "ethernet-phy-ieee802.3-c22" + * o In the white list above (and issue a warning) * o No compatibility string * * A device which is not a phy is expected to have a compatible string @@ -166,6 +186,13 @@ static bool of_mdiobus_child_is_phy(struct device_node *child) if (of_device_is_compatible(child, "ethernet-phy-ieee802.3-c22")) return true; + if (of_match_node(whitelist_phys, child)) { + pr_warn(FW_WARN + "%s: Whitelisted compatible string. Please remove\n", + child->full_name); + return true; + } + if (!of_find_property(child, "compatible", NULL)) return true; @@ -256,11 +283,19 @@ static int of_phy_match(struct device *dev, void *phy_np) struct phy_device *of_phy_find_device(struct device_node *phy_np) { struct device *d; + struct mdio_device *mdiodev; + if (!phy_np) return NULL; d = bus_find_device(&mdio_bus_type, NULL, phy_np, of_phy_match); - return d ? to_phy_device(d) : NULL; + if (d) { + mdiodev = to_mdio_device(d); + if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) + return to_phy_device(d); + } + + return NULL; } EXPORT_SYMBOL(of_phy_find_device); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 5f2fda12e006..fa49f9143b80 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -953,8 +953,10 @@ int acpiphp_enable_slot(struct acpiphp_slot *slot) { pci_lock_rescan_remove(); - if (slot->flags & SLOT_IS_GOING_AWAY) + if (slot->flags & SLOT_IS_GOING_AWAY) { + pci_unlock_rescan_remove(); return -ENODEV; + } /* configure all functions */ if (!(slot->flags & SLOT_ENABLED)) diff --git a/drivers/ptp/ptp_ixp46x.c b/drivers/ptp/ptp_ixp46x.c index 934c139916c6..ee4f183ef9ee 100644 --- a/drivers/ptp/ptp_ixp46x.c +++ b/drivers/ptp/ptp_ixp46x.c @@ -178,7 +178,6 @@ static int ptp_ixp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; - u32 remainder; unsigned long flags; struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps); struct ixp46x_ts_regs *regs = ixp_clock->regs; @@ -189,8 +188,7 @@ static int ptp_ixp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) spin_unlock_irqrestore(®ister_lock, flags); - ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder); - ts->tv_nsec = remainder; + *ts = ns_to_timespec64(ns); return 0; } @@ -202,8 +200,7 @@ static int ptp_ixp_settime(struct ptp_clock_info *ptp, struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps); struct ixp46x_ts_regs *regs = ixp_clock->regs; - ns = ts->tv_sec * 1000000000ULL; - ns += ts->tv_nsec; + ns = timespec64_to_ns(ts); spin_lock_irqsave(®ister_lock, flags); diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index c692dfebd0ba..50597f9522fe 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -139,11 +139,11 @@ static ssize_t chp_measurement_chars_read(struct file *filp, device = container_of(kobj, struct device, kobj); chp = to_channelpath(device); - if (!chp->cmg_chars) + if (chp->cmg == -1) return 0; - return memory_read_from_buffer(buf, count, &off, - chp->cmg_chars, sizeof(struct cmg_chars)); + return memory_read_from_buffer(buf, count, &off, &chp->cmg_chars, + sizeof(chp->cmg_chars)); } static struct bin_attribute chp_measurement_chars_attr = { @@ -416,7 +416,8 @@ static void chp_release(struct device *dev) * chp_update_desc - update channel-path description * @chp - channel-path * - * Update the channel-path description of the specified channel-path. + * Update the channel-path description of the specified channel-path + * including channel measurement related information. * Return zero on success, non-zero otherwise. */ int chp_update_desc(struct channel_path *chp) @@ -428,8 +429,10 @@ int chp_update_desc(struct channel_path *chp) return rc; rc = chsc_determine_fmt1_channel_path_desc(chp->chpid, &chp->desc_fmt1); + if (rc) + return rc; - return rc; + return chsc_get_channel_measurement_chars(chp); } /** @@ -466,14 +469,6 @@ int chp_new(struct chp_id chpid) ret = -ENODEV; goto out_free; } - /* Get channel-measurement characteristics. */ - if (css_chsc_characteristics.scmc && css_chsc_characteristics.secm) { - ret = chsc_get_channel_measurement_chars(chp); - if (ret) - goto out_free; - } else { - chp->cmg = -1; - } dev_set_name(&chp->dev, "chp%x.%02x", chpid.cssid, chpid.id); /* make it known to the system */ diff --git a/drivers/s390/cio/chp.h b/drivers/s390/cio/chp.h index 4efd5b867cc3..af0232290dc4 100644 --- a/drivers/s390/cio/chp.h +++ b/drivers/s390/cio/chp.h @@ -48,7 +48,7 @@ struct channel_path { /* Channel-measurement related stuff: */ int cmg; int shared; - void *cmg_chars; + struct cmg_chars cmg_chars; }; /* Return channel_path struct for given chpid. */ diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index a831d18596a5..c424c0c7367e 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/init.h> #include <linux/device.h> +#include <linux/mutex.h> #include <linux/pci.h> #include <asm/cio.h> @@ -224,8 +225,9 @@ out_unreg: void chsc_chp_offline(struct chp_id chpid) { - char dbf_txt[15]; + struct channel_path *chp = chpid_to_chp(chpid); struct chp_link link; + char dbf_txt[15]; sprintf(dbf_txt, "chpr%x.%02x", chpid.cssid, chpid.id); CIO_TRACE_EVENT(2, dbf_txt); @@ -236,6 +238,11 @@ void chsc_chp_offline(struct chp_id chpid) link.chpid = chpid; /* Wait until previous actions have settled. */ css_wait_for_slow_path(); + + mutex_lock(&chp->lock); + chp_update_desc(chp); + mutex_unlock(&chp->lock); + for_each_subchannel_staged(s390_subchannel_remove_chpid, NULL, &link); } @@ -690,8 +697,9 @@ static void chsc_process_crw(struct crw *crw0, struct crw *crw1, int overflow) void chsc_chp_online(struct chp_id chpid) { - char dbf_txt[15]; + struct channel_path *chp = chpid_to_chp(chpid); struct chp_link link; + char dbf_txt[15]; sprintf(dbf_txt, "cadd%x.%02x", chpid.cssid, chpid.id); CIO_TRACE_EVENT(2, dbf_txt); @@ -701,6 +709,11 @@ void chsc_chp_online(struct chp_id chpid) link.chpid = chpid; /* Wait until previous actions have settled. */ css_wait_for_slow_path(); + + mutex_lock(&chp->lock); + chp_update_desc(chp); + mutex_unlock(&chp->lock); + for_each_subchannel_staged(__s390_process_res_acc, NULL, &link); css_schedule_reprobe(); @@ -967,22 +980,19 @@ static void chsc_initialize_cmg_chars(struct channel_path *chp, u8 cmcv, struct cmg_chars *chars) { - struct cmg_chars *cmg_chars; int i, mask; - cmg_chars = chp->cmg_chars; for (i = 0; i < NR_MEASUREMENT_CHARS; i++) { mask = 0x80 >> (i + 3); if (cmcv & mask) - cmg_chars->values[i] = chars->values[i]; + chp->cmg_chars.values[i] = chars->values[i]; else - cmg_chars->values[i] = 0; + chp->cmg_chars.values[i] = 0; } } int chsc_get_channel_measurement_chars(struct channel_path *chp) { - struct cmg_chars *cmg_chars; int ccode, ret; struct { @@ -1006,10 +1016,11 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp) u32 data[NR_MEASUREMENT_CHARS]; } __attribute__ ((packed)) *scmc_area; - chp->cmg_chars = NULL; - cmg_chars = kmalloc(sizeof(*cmg_chars), GFP_KERNEL); - if (!cmg_chars) - return -ENOMEM; + chp->shared = -1; + chp->cmg = -1; + + if (!css_chsc_characteristics.scmc || !css_chsc_characteristics.secm) + return 0; spin_lock_irq(&chsc_page_lock); memset(chsc_page, 0, PAGE_SIZE); @@ -1031,25 +1042,19 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp) scmc_area->response.code); goto out; } - if (scmc_area->not_valid) { - chp->cmg = -1; - chp->shared = -1; + if (scmc_area->not_valid) goto out; - } + chp->cmg = scmc_area->cmg; chp->shared = scmc_area->shared; if (chp->cmg != 2 && chp->cmg != 3) { /* No cmg-dependent data. */ goto out; } - chp->cmg_chars = cmg_chars; chsc_initialize_cmg_chars(chp, scmc_area->cmcv, (struct cmg_chars *) &scmc_area->data); out: spin_unlock_irq(&chsc_page_lock); - if (!chp->cmg_chars) - kfree(cmg_chars); - return ret; } diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index 7b23f43c7b08..de1b6c1d172c 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -112,9 +112,10 @@ static inline int convert_error(struct zcrypt_device *zdev, atomic_set(&zcrypt_rescan_req, 1); zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, ehdr->reply_code); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, + ehdr->reply_code); return -EAGAIN; case REP82_ERROR_TRANSPORT_FAIL: case REP82_ERROR_MACHINE_FAILURE: @@ -123,16 +124,18 @@ static inline int convert_error(struct zcrypt_device *zdev, atomic_set(&zcrypt_rescan_req, 1); zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, ehdr->reply_code); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, + ehdr->reply_code); return -EAGAIN; default: zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, ehdr->reply_code); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, + ehdr->reply_code); return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 74edf2934e7c..eedfaa2cf715 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -336,9 +336,10 @@ static int convert_type80(struct zcrypt_device *zdev, /* The result is too short, the CEX2A card may not do that.. */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, t80h->code); + AP_QID_DEVICE(zdev->ap_dev->qid), + zdev->online, t80h->code); return -EAGAIN; /* repeat the request on a different device. */ } @@ -368,9 +369,9 @@ static int convert_response(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 9a2dd472c1cc..21959719daef 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -572,9 +572,9 @@ static int convert_type86_ica(struct zcrypt_device *zdev, return -EINVAL; zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d", - zdev->ap_dev->qid, zdev->online, + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online, msg->hdr.reply_code); return -EAGAIN; /* repeat the request on a different device. */ } @@ -715,9 +715,9 @@ static int convert_response_ica(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } @@ -747,9 +747,9 @@ static int convert_response_xcrb(struct zcrypt_device *zdev, xcRB->status = 0x0008044DL; /* HDD_InvalidParm */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } @@ -773,9 +773,9 @@ static int convert_response_ep11_xcrb(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } @@ -800,9 +800,9 @@ static int convert_response_rng(struct zcrypt_device *zdev, default: /* Unknown response type, this should NEVER EVER happen */ zdev->online = 0; pr_err("Cryptographic device %x failed and was set offline\n", - zdev->ap_dev->qid); + AP_QID_DEVICE(zdev->ap_dev->qid)); ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail", - zdev->ap_dev->qid, zdev->online); + AP_QID_DEVICE(zdev->ap_dev->qid), zdev->online); return -EAGAIN; /* repeat the request on a different device. */ } } diff --git a/drivers/scsi/hisi_sas/Kconfig b/drivers/scsi/hisi_sas/Kconfig index 37a0c7156087..b67661836c9f 100644 --- a/drivers/scsi/hisi_sas/Kconfig +++ b/drivers/scsi/hisi_sas/Kconfig @@ -1,5 +1,7 @@ config SCSI_HISI_SAS tristate "HiSilicon SAS" + depends on HAS_DMA + depends on ARM64 || COMPILE_TEST select SCSI_SAS_LIBSAS select BLK_DEV_INTEGRITY help diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4e08d1cd704d..bb669d32ccd0 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2893,7 +2893,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE) rw_max = q->limits.io_opt = - logical_to_sectors(sdp, sdkp->opt_xfer_blocks); + sdkp->opt_xfer_blocks * sdp->sector_size; else rw_max = BLK_DEF_MAX_SECTORS; @@ -3268,8 +3268,8 @@ static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret = 0; - if (!sdkp) - return 0; /* this can happen */ + if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ + return 0; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); @@ -3308,6 +3308,9 @@ static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + if (!sdkp->device->manage_start_stop) return 0; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8bd54a64efd6..64c867405ad4 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -144,6 +144,9 @@ static int sr_runtime_suspend(struct device *dev) { struct scsi_cd *cd = dev_get_drvdata(dev); + if (!cd) /* E.g.: runtime suspend following sr_remove() */ + return 0; + if (cd->media_present) return -EBUSY; else @@ -985,6 +988,7 @@ static int sr_remove(struct device *dev) scsi_autopm_get_device(cd->device); del_gendisk(cd->disk); + dev_set_drvdata(dev, NULL); mutex_lock(&sr_ref_mutex); kref_put(&cd->kref, sr_kref_release); diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index cde5ff7529eb..d1a750760cf3 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -613,9 +613,10 @@ out: return err; } -static int ssb_bus_register(struct ssb_bus *bus, - ssb_invariants_func_t get_invariants, - unsigned long baseaddr) +static int __maybe_unused +ssb_bus_register(struct ssb_bus *bus, + ssb_invariants_func_t get_invariants, + unsigned long baseaddr) { int err; diff --git a/drivers/staging/panel/panel.c b/drivers/staging/panel/panel.c index 79ac19246548..70b8f4fabfad 100644 --- a/drivers/staging/panel/panel.c +++ b/drivers/staging/panel/panel.c @@ -825,8 +825,7 @@ static void lcd_write_cmd_s(int cmd) lcd_send_serial(0x1F); /* R/W=W, RS=0 */ lcd_send_serial(cmd & 0x0F); lcd_send_serial((cmd >> 4) & 0x0F); - /* the shortest command takes at least 40 us */ - usleep_range(40, 100); + udelay(40); /* the shortest command takes at least 40 us */ spin_unlock_irq(&pprt_lock); } @@ -837,8 +836,7 @@ static void lcd_write_data_s(int data) lcd_send_serial(0x5F); /* R/W=W, RS=1 */ lcd_send_serial(data & 0x0F); lcd_send_serial((data >> 4) & 0x0F); - /* the shortest data takes at least 40 us */ - usleep_range(40, 100); + udelay(40); /* the shortest data takes at least 40 us */ spin_unlock_irq(&pprt_lock); } @@ -848,20 +846,19 @@ static void lcd_write_cmd_p8(int cmd) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, cmd); - /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); /* maintain the data during 20 us before the strobe */ bits.e = BIT_SET; bits.rs = BIT_CLR; bits.rw = BIT_CLR; set_ctrl_bits(); - usleep_range(40, 100); /* maintain the strobe during 40 us */ + udelay(40); /* maintain the strobe during 40 us */ bits.e = BIT_CLR; set_ctrl_bits(); - usleep_range(120, 500); /* the shortest command takes at least 120 us */ + udelay(120); /* the shortest command takes at least 120 us */ spin_unlock_irq(&pprt_lock); } @@ -871,20 +868,19 @@ static void lcd_write_data_p8(int data) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, data); - /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); /* maintain the data during 20 us before the strobe */ bits.e = BIT_SET; bits.rs = BIT_SET; bits.rw = BIT_CLR; set_ctrl_bits(); - usleep_range(40, 100); /* maintain the strobe during 40 us */ + udelay(40); /* maintain the strobe during 40 us */ bits.e = BIT_CLR; set_ctrl_bits(); - usleep_range(45, 100); /* the shortest data takes at least 45 us */ + udelay(45); /* the shortest data takes at least 45 us */ spin_unlock_irq(&pprt_lock); } @@ -894,7 +890,7 @@ static void lcd_write_cmd_tilcd(int cmd) spin_lock_irq(&pprt_lock); /* present the data to the control port */ w_ctr(pprt, cmd); - usleep_range(60, 120); + udelay(60); spin_unlock_irq(&pprt_lock); } @@ -904,7 +900,7 @@ static void lcd_write_data_tilcd(int data) spin_lock_irq(&pprt_lock); /* present the data to the data port */ w_dtr(pprt, data); - usleep_range(60, 120); + udelay(60); spin_unlock_irq(&pprt_lock); } @@ -947,7 +943,7 @@ static void lcd_clear_fast_s(void) lcd_send_serial(0x5F); /* R/W=W, RS=1 */ lcd_send_serial(' ' & 0x0F); lcd_send_serial((' ' >> 4) & 0x0F); - usleep_range(40, 100); /* the shortest data takes at least 40 us */ + udelay(40); /* the shortest data takes at least 40 us */ } spin_unlock_irq(&pprt_lock); @@ -971,7 +967,7 @@ static void lcd_clear_fast_p8(void) w_dtr(pprt, ' '); /* maintain the data during 20 us before the strobe */ - usleep_range(20, 100); + udelay(20); bits.e = BIT_SET; bits.rs = BIT_SET; @@ -979,13 +975,13 @@ static void lcd_clear_fast_p8(void) set_ctrl_bits(); /* maintain the strobe during 40 us */ - usleep_range(40, 100); + udelay(40); bits.e = BIT_CLR; set_ctrl_bits(); /* the shortest data takes at least 45 us */ - usleep_range(45, 100); + udelay(45); } spin_unlock_irq(&pprt_lock); @@ -1007,7 +1003,7 @@ static void lcd_clear_fast_tilcd(void) for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) { /* present the data to the data port */ w_dtr(pprt, ' '); - usleep_range(60, 120); + udelay(60); } spin_unlock_irq(&pprt_lock); diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c index 63c59bc89b04..30cf973f326d 100644 --- a/drivers/staging/speakup/main.c +++ b/drivers/staging/speakup/main.c @@ -264,8 +264,9 @@ static struct notifier_block vt_notifier_block = { .notifier_call = vt_notifier_call, }; -static unsigned char get_attributes(u16 *pos) +static unsigned char get_attributes(struct vc_data *vc, u16 *pos) { + pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1); return (u_char) (scr_readw(pos) >> 8); } @@ -275,7 +276,7 @@ static void speakup_date(struct vc_data *vc) spk_y = spk_cy = vc->vc_y; spk_pos = spk_cp = vc->vc_pos; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) spk_pos); + spk_attr = get_attributes(vc, (u_short *)spk_pos); } static void bleep(u_short val) @@ -469,8 +470,12 @@ static u16 get_char(struct vc_data *vc, u16 *pos, u_char *attribs) u16 ch = ' '; if (vc && pos) { - u16 w = scr_readw(pos); - u16 c = w & 0xff; + u16 w; + u16 c; + + pos = screen_pos(vc, pos - (u16 *)vc->vc_origin, 1); + w = scr_readw(pos); + c = w & 0xff; if (w & vc->vc_hi_font_mask) c |= 0x100; @@ -746,7 +751,7 @@ static int get_line(struct vc_data *vc) u_char tmp2; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) spk_pos); + spk_attr = get_attributes(vc, (u_short *)spk_pos); for (i = 0; i < vc->vc_cols; i++) { buf[i] = (u_char) get_char(vc, (u_short *) tmp, &tmp2); tmp += 2; @@ -811,7 +816,7 @@ static int say_from_to(struct vc_data *vc, u_long from, u_long to, u_short saved_punc_mask = spk_punc_mask; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) from); + spk_attr = get_attributes(vc, (u_short *)from); while (from < to) { buf[i++] = (char)get_char(vc, (u_short *) from, &tmp); from += 2; @@ -886,7 +891,7 @@ static int get_sentence_buf(struct vc_data *vc, int read_punc) sentmarks[bn][0] = &sentbuf[bn][0]; i = 0; spk_old_attr = spk_attr; - spk_attr = get_attributes((u_short *) start); + spk_attr = get_attributes(vc, (u_short *)start); while (start < end) { sentbuf[bn][i] = (char)get_char(vc, (u_short *) start, &tmp); @@ -1585,7 +1590,7 @@ static int count_highlight_color(struct vc_data *vc) u16 *ptr; for (ptr = start; ptr < end; ptr++) { - ch = get_attributes(ptr); + ch = get_attributes(vc, ptr); bg = (ch & 0x70) >> 4; speakup_console[vc_num]->ht.bgcount[bg]++; } diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c index aa5ab6c80ed4..41ef099b7aa6 100644 --- a/drivers/staging/speakup/selection.c +++ b/drivers/staging/speakup/selection.c @@ -142,7 +142,9 @@ static void __speakup_paste_selection(struct work_struct *work) struct tty_ldisc *ld; DECLARE_WAITQUEUE(wait, current); - ld = tty_ldisc_ref_wait(tty); + ld = tty_ldisc_ref(tty); + if (!ld) + goto tty_unref; tty_buffer_lock_exclusive(&vc->port); add_wait_queue(&vc->paste_wait, &wait); @@ -162,6 +164,7 @@ static void __speakup_paste_selection(struct work_struct *work) tty_buffer_unlock_exclusive(&vc->port); tty_ldisc_deref(ld); +tty_unref: tty_kref_put(tty); } diff --git a/drivers/staging/speakup/serialio.c b/drivers/staging/speakup/serialio.c index 3b5835b28128..a5bbb338f275 100644 --- a/drivers/staging/speakup/serialio.c +++ b/drivers/staging/speakup/serialio.c @@ -6,6 +6,11 @@ #include "spk_priv.h" #include "serialio.h" +#include <linux/serial_core.h> +/* WARNING: Do not change this to <linux/serial.h> without testing that + * SERIAL_PORT_DFNS does get defined to the appropriate value. */ +#include <asm/serial.h> + #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif @@ -23,9 +28,15 @@ const struct old_serial_port *spk_serial_init(int index) int baud = 9600, quot = 0; unsigned int cval = 0; int cflag = CREAD | HUPCL | CLOCAL | B9600 | CS8; - const struct old_serial_port *ser = rs_table + index; + const struct old_serial_port *ser; int err; + if (index >= ARRAY_SIZE(rs_table)) { + pr_info("no port info for ttyS%d\n", index); + return NULL; + } + ser = rs_table + index; + /* Divisor, bytesize and parity */ quot = ser->baud_base / baud; cval = cflag & (CSIZE | CSTOPB); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index d9a5fc28fef4..b280abaad91b 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -269,16 +269,13 @@ static void n_tty_check_throttle(struct tty_struct *tty) static void n_tty_check_unthrottle(struct tty_struct *tty) { - if (tty->driver->type == TTY_DRIVER_TYPE_PTY && - tty->link->ldisc->ops->write_wakeup == n_tty_write_wakeup) { + if (tty->driver->type == TTY_DRIVER_TYPE_PTY) { if (chars_in_buffer(tty) > TTY_THRESHOLD_UNTHROTTLE) return; if (!tty->count) return; n_tty_kick_worker(tty); - n_tty_write_wakeup(tty->link); - if (waitqueue_active(&tty->link->write_wait)) - wake_up_interruptible_poll(&tty->link->write_wait, POLLOUT); + tty_wakeup(tty->link); return; } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 4097f3f65b3b..e71ec78fc11e 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1379,6 +1379,9 @@ ce4100_serial_setup(struct serial_private *priv, #define PCI_DEVICE_ID_INTEL_BSW_UART1 0x228a #define PCI_DEVICE_ID_INTEL_BSW_UART2 0x228c +#define PCI_DEVICE_ID_INTEL_BDW_UART1 0x9ce3 +#define PCI_DEVICE_ID_INTEL_BDW_UART2 0x9ce4 + #define BYT_PRV_CLK 0x800 #define BYT_PRV_CLK_EN (1 << 0) #define BYT_PRV_CLK_M_VAL_SHIFT 1 @@ -1461,11 +1464,13 @@ byt_serial_setup(struct serial_private *priv, switch (pdev->device) { case PCI_DEVICE_ID_INTEL_BYT_UART1: case PCI_DEVICE_ID_INTEL_BSW_UART1: + case PCI_DEVICE_ID_INTEL_BDW_UART1: rx_param->src_id = 3; tx_param->dst_id = 2; break; case PCI_DEVICE_ID_INTEL_BYT_UART2: case PCI_DEVICE_ID_INTEL_BSW_UART2: + case PCI_DEVICE_ID_INTEL_BDW_UART2: rx_param->src_id = 5; tx_param->dst_id = 4; break; @@ -2062,6 +2067,20 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = byt_serial_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART1, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_BDW_UART2, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = byt_serial_setup, + }, /* * ITE */ @@ -5506,6 +5525,16 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, pbn_byt }, + /* Intel Broadwell */ + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART1, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + { PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_UART2, + PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_COMMUNICATION_SERIAL << 8, 0xff0000, + pbn_byt }, + /* * Intel Quark x1000 */ diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 892c92354745..5cec01c75691 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1463,13 +1463,13 @@ static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; - if (!tty->count) - return -EIO; - if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) return -EIO; + if (!tty->count) + return -EAGAIN; + if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; @@ -2065,7 +2065,12 @@ retry_open: if (tty) { mutex_unlock(&tty_mutex); - tty_lock(tty); + retval = tty_lock_interruptible(tty); + if (retval) { + if (retval == -EINTR) + retval = -ERESTARTSYS; + goto err_unref; + } /* safe to drop the kref from tty_driver_lookup_tty() */ tty_kref_put(tty); retval = tty_reopen(tty); @@ -2083,7 +2088,11 @@ retry_open: if (IS_ERR(tty)) { retval = PTR_ERR(tty); - goto err_file; + if (retval != -EAGAIN || signal_pending(current)) + goto err_file; + tty_free_file(filp); + schedule(); + goto retry_open; } tty_add_file(tty, filp); @@ -2152,6 +2161,7 @@ retry_open: return 0; err_unlock: mutex_unlock(&tty_mutex); +err_unref: /* after locks to avoid deadlock */ if (!IS_ERR_OR_NULL(driver)) tty_driver_kref_put(driver); @@ -2649,6 +2659,28 @@ static int tiocsetd(struct tty_struct *tty, int __user *p) } /** + * tiocgetd - get line discipline + * @tty: tty device + * @p: pointer to user data + * + * Retrieves the line discipline id directly from the ldisc. + * + * Locking: waits for ldisc reference (in case the line discipline + * is changing or the tty is being hungup) + */ + +static int tiocgetd(struct tty_struct *tty, int __user *p) +{ + struct tty_ldisc *ld; + int ret; + + ld = tty_ldisc_ref_wait(tty); + ret = put_user(ld->ops->num, p); + tty_ldisc_deref(ld); + return ret; +} + +/** * send_break - performed time break * @tty: device to break on * @duration: timeout in mS @@ -2874,7 +2906,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case TIOCGSID: return tiocgsid(tty, real_tty, p); case TIOCGETD: - return put_user(tty->ldisc->ops->num, (int __user *)p); + return tiocgetd(tty, p); case TIOCSETD: return tiocsetd(tty, p); case TIOCVHANGUP: diff --git a/drivers/tty/tty_mutex.c b/drivers/tty/tty_mutex.c index 77703a391207..d2f3c4cd697f 100644 --- a/drivers/tty/tty_mutex.c +++ b/drivers/tty/tty_mutex.c @@ -19,6 +19,14 @@ void __lockfunc tty_lock(struct tty_struct *tty) } EXPORT_SYMBOL(tty_lock); +int tty_lock_interruptible(struct tty_struct *tty) +{ + if (WARN(tty->magic != TTY_MAGIC, "L Bad %p\n", tty)) + return -EIO; + tty_kref_get(tty); + return mutex_lock_interruptible(&tty->legacy_mutex); +} + void __lockfunc tty_unlock(struct tty_struct *tty) { if (WARN(tty->magic != TTY_MAGIC, "U Bad %p\n", tty)) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e7cbc44eef57..bd51bdd0a7bf 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4250,6 +4250,7 @@ unsigned short *screen_pos(struct vc_data *vc, int w_offset, int viewed) { return screenpos(vc, 2 * w_offset, viewed); } +EXPORT_SYMBOL_GPL(screen_pos); void getconsxy(struct vc_data *vc, unsigned char *p) { diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 26ca4f910cb0..fa4e23930614 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -428,7 +428,8 @@ static void acm_read_bulk_callback(struct urb *urb) set_bit(rb->index, &acm->read_urbs_free); dev_dbg(&acm->data->dev, "%s - non-zero urb status: %d\n", __func__, status); - return; + if ((status != -ENOENT) || (urb->actual_length == 0)) + return; } usb_mark_last_busy(acm->dev); @@ -1404,6 +1405,8 @@ made_compressed_probe: usb_sndbulkpipe(usb_dev, epwrite->bEndpointAddress), NULL, acm->writesize, acm_write_bulk, snd); snd->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + if (quirks & SEND_ZERO_PACKET) + snd->urb->transfer_flags |= URB_ZERO_PACKET; snd->instance = acm; } @@ -1838,6 +1841,11 @@ static const struct usb_device_id acm_ids[] = { }, #endif + /*Samsung phone in firmware update mode */ + { USB_DEVICE(0x04e8, 0x685d), + .driver_info = IGNORE_DEVICE, + }, + /* Exclude Infineon Flash Loader utility */ { USB_DEVICE(0x058b, 0x0041), .driver_info = IGNORE_DEVICE, @@ -1861,6 +1869,10 @@ static const struct usb_device_id acm_ids[] = { { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM, USB_CDC_ACM_PROTO_AT_CDMA) }, + { USB_DEVICE(0x1519, 0x0452), /* Intel 7260 modem */ + .driver_info = SEND_ZERO_PACKET, + }, + { } }; diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index dd9af38e7cda..ccfaba9ab4e4 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -134,3 +134,4 @@ struct acm { #define IGNORE_DEVICE BIT(5) #define QUIRK_CONTROL_LINE_STATE BIT(6) #define CLEAR_HALT_CONDITIONS BIT(7) +#define SEND_ZERO_PACKET BIT(8) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 51b436918f78..350dcd9af5d8 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5401,7 +5401,6 @@ static int usb_reset_and_verify_device(struct usb_device *udev) } bos = udev->bos; - udev->bos = NULL; for (i = 0; i < SET_CONFIG_TRIES; ++i) { @@ -5494,8 +5493,11 @@ done: usb_set_usb2_hardware_lpm(udev, 1); usb_unlocked_enable_lpm(udev); usb_enable_ltm(udev); - usb_release_bos_descriptor(udev); - udev->bos = bos; + /* release the new BOS descriptor allocated by hub_port_init() */ + if (udev->bos != bos) { + usb_release_bos_descriptor(udev); + udev->bos = bos; + } return 0; re_enumerate: diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 9b90ad747d87..987813b8a7f9 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -99,6 +99,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x81AC) }, /* MSD Dash Hawk */ { USB_DEVICE(0x10C4, 0x81AD) }, /* INSYS USB Modem */ { USB_DEVICE(0x10C4, 0x81C8) }, /* Lipowsky Industrie Elektronik GmbH, Baby-JTAG */ + { USB_DEVICE(0x10C4, 0x81D7) }, /* IAI Corp. RCB-CV-USB USB to RS485 Adaptor */ { USB_DEVICE(0x10C4, 0x81E2) }, /* Lipowsky Industrie Elektronik GmbH, Baby-LIN */ { USB_DEVICE(0x10C4, 0x81E7) }, /* Aerocomm Radio */ { USB_DEVICE(0x10C4, 0x81E8) }, /* Zephyr Bioharness */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index a5a0376bbd48..8c660ae401d8 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -824,6 +824,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_TURTELIZER_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_USB60F) }, + { USB_DEVICE(RATOC_VENDOR_ID, RATOC_PRODUCT_ID_SCU18) }, { USB_DEVICE(FTDI_VID, FTDI_REU_TINY_PID) }, /* Papouch devices based on FTDI chip */ diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 67c6d4469730..a84df2513994 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -615,6 +615,7 @@ */ #define RATOC_VENDOR_ID 0x0584 #define RATOC_PRODUCT_ID_USB60F 0xb020 +#define RATOC_PRODUCT_ID_SCU18 0xb03a /* * Infineon Technologies diff --git a/drivers/usb/serial/mxu11x0.c b/drivers/usb/serial/mxu11x0.c index e3c3f57c2d82..619607323bfd 100644 --- a/drivers/usb/serial/mxu11x0.c +++ b/drivers/usb/serial/mxu11x0.c @@ -368,6 +368,16 @@ static int mxu1_port_probe(struct usb_serial_port *port) return 0; } +static int mxu1_port_remove(struct usb_serial_port *port) +{ + struct mxu1_port *mxport; + + mxport = usb_get_serial_port_data(port); + kfree(mxport); + + return 0; +} + static int mxu1_startup(struct usb_serial *serial) { struct mxu1_device *mxdev; @@ -427,6 +437,14 @@ err_free_mxdev: return err; } +static void mxu1_release(struct usb_serial *serial) +{ + struct mxu1_device *mxdev; + + mxdev = usb_get_serial_data(serial); + kfree(mxdev); +} + static int mxu1_write_byte(struct usb_serial_port *port, u32 addr, u8 mask, u8 byte) { @@ -957,7 +975,9 @@ static struct usb_serial_driver mxu11x0_device = { .id_table = mxu1_idtable, .num_ports = 1, .port_probe = mxu1_port_probe, + .port_remove = mxu1_port_remove, .attach = mxu1_startup, + .release = mxu1_release, .open = mxu1_open, .close = mxu1_close, .ioctl = mxu1_ioctl, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index f2280606b73c..db86e512e0fc 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -268,6 +268,8 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_CC864_SINGLE 0x1006 #define TELIT_PRODUCT_DE910_DUAL 0x1010 #define TELIT_PRODUCT_UE910_V2 0x1012 +#define TELIT_PRODUCT_LE922_USBCFG0 0x1042 +#define TELIT_PRODUCT_LE922_USBCFG3 0x1043 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 @@ -615,6 +617,16 @@ static const struct option_blacklist_info telit_le920_blacklist = { .reserved = BIT(1) | BIT(5), }; +static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = { + .sendsetup = BIT(2), + .reserved = BIT(0) | BIT(1) | BIT(3), +}; + +static const struct option_blacklist_info telit_le922_blacklist_usbcfg3 = { + .sendsetup = BIT(0), + .reserved = BIT(1) | BIT(2) | BIT(3), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1160,6 +1172,10 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG3), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), @@ -1679,7 +1695,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, - { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX, 0xff) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, diff --git a/drivers/usb/serial/visor.c b/drivers/usb/serial/visor.c index 60afb39eb73c..337a0be89fcf 100644 --- a/drivers/usb/serial/visor.c +++ b/drivers/usb/serial/visor.c @@ -544,6 +544,11 @@ static int treo_attach(struct usb_serial *serial) (serial->num_interrupt_in == 0)) return 0; + if (serial->num_bulk_in < 2 || serial->num_interrupt_in < 2) { + dev_err(&serial->interface->dev, "missing endpoints\n"); + return -ENODEV; + } + /* * It appears that Treos and Kyoceras want to use the * 1st bulk in endpoint to communicate with the 2nd bulk out endpoint, @@ -597,8 +602,10 @@ static int clie_5_attach(struct usb_serial *serial) */ /* some sanity check */ - if (serial->num_ports < 2) - return -1; + if (serial->num_bulk_out < 2) { + dev_err(&serial->interface->dev, "missing bulk out endpoints\n"); + return -ENODEV; + } /* port 0 now uses the modified endpoint Address */ port = serial->port[0]; diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 82f25cc1c460..ecca316386f5 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -123,8 +123,8 @@ struct iommu_group *vfio_iommu_group_get(struct device *dev) /* * With noiommu enabled, an IOMMU group will be created for a device * that doesn't already have one and doesn't have an iommu_ops on their - * bus. We use iommu_present() again in the main code to detect these - * fake groups. + * bus. We set iommudata simply to be able to identify these groups + * as special use and for reclamation later. */ if (group || !noiommu || iommu_present(dev->bus)) return group; @@ -134,6 +134,7 @@ struct iommu_group *vfio_iommu_group_get(struct device *dev) return NULL; iommu_group_set_name(group, "vfio-noiommu"); + iommu_group_set_iommudata(group, &noiommu, NULL); ret = iommu_group_add_device(group, dev); iommu_group_put(group); if (ret) @@ -158,7 +159,7 @@ EXPORT_SYMBOL_GPL(vfio_iommu_group_get); void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) { #ifdef CONFIG_VFIO_NOIOMMU - if (!iommu_present(dev->bus)) + if (iommu_group_get_iommudata(group) == &noiommu) iommu_group_remove_device(dev); #endif @@ -190,16 +191,10 @@ static long vfio_noiommu_ioctl(void *iommu_data, return -ENOTTY; } -static int vfio_iommu_present(struct device *dev, void *unused) -{ - return iommu_present(dev->bus) ? 1 : 0; -} - static int vfio_noiommu_attach_group(void *iommu_data, struct iommu_group *iommu_group) { - return iommu_group_for_each_dev(iommu_group, NULL, - vfio_iommu_present) ? -EINVAL : 0; + return iommu_group_get_iommudata(iommu_group) == &noiommu ? 0 : -EINVAL; } static void vfio_noiommu_detach_group(void *iommu_data, @@ -323,8 +318,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, - bool iommu_present) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) { struct vfio_group *group, *tmp; struct device *dev; @@ -342,7 +336,9 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; - group->noiommu = !iommu_present; +#ifdef CONFIG_VFIO_NOIOMMU + group->noiommu = (iommu_group_get_iommudata(iommu_group) == &noiommu); +#endif group->nb.notifier_call = vfio_iommu_group_notifier; @@ -767,7 +763,7 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group, iommu_present(dev->bus)); + group = vfio_create_group(iommu_group); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 36205c27c4d0..f6bed86c17f9 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -545,6 +545,7 @@ err_enable_device: static void virtio_pci_remove(struct pci_dev *pci_dev) { struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); + struct device *dev = get_device(&vp_dev->vdev.dev); unregister_virtio_device(&vp_dev->vdev); @@ -554,6 +555,7 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) virtio_pci_modern_remove(vp_dev); pci_disable_device(pci_dev); + put_device(dev); } static struct pci_driver virtio_pci_driver = { diff --git a/drivers/xen/tmem.c b/drivers/xen/tmem.c index 945fc4327201..4ac2ca8a7656 100644 --- a/drivers/xen/tmem.c +++ b/drivers/xen/tmem.c @@ -242,7 +242,7 @@ static int tmem_cleancache_init_shared_fs(char *uuid, size_t pagesize) return xen_tmem_new_pool(shared_uuid, TMEM_POOL_SHARED, pagesize); } -static struct cleancache_ops tmem_cleancache_ops = { +static const struct cleancache_ops tmem_cleancache_ops = { .put_page = tmem_cleancache_put_page, .get_page = tmem_cleancache_get_page, .invalidate_page = tmem_cleancache_flush_page, diff --git a/fs/block_dev.c b/fs/block_dev.c index 7b9cd49622b1..afb437484362 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1736,37 +1736,13 @@ static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); } -static void blkdev_vm_open(struct vm_area_struct *vma) -{ - struct inode *bd_inode = bdev_file_inode(vma->vm_file); - struct block_device *bdev = I_BDEV(bd_inode); - - inode_lock(bd_inode); - bdev->bd_map_count++; - inode_unlock(bd_inode); -} - -static void blkdev_vm_close(struct vm_area_struct *vma) -{ - struct inode *bd_inode = bdev_file_inode(vma->vm_file); - struct block_device *bdev = I_BDEV(bd_inode); - - inode_lock(bd_inode); - bdev->bd_map_count--; - inode_unlock(bd_inode); -} - static const struct vm_operations_struct blkdev_dax_vm_ops = { - .open = blkdev_vm_open, - .close = blkdev_vm_close, .fault = blkdev_dax_fault, .pmd_fault = blkdev_dax_pmd_fault, .pfn_mkwrite = blkdev_dax_fault, }; static const struct vm_operations_struct blkdev_default_vm_ops = { - .open = blkdev_vm_open, - .close = blkdev_vm_close, .fault = filemap_fault, .map_pages = filemap_map_pages, }; @@ -1774,18 +1750,14 @@ static const struct vm_operations_struct blkdev_default_vm_ops = { static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *bd_inode = bdev_file_inode(file); - struct block_device *bdev = I_BDEV(bd_inode); file_accessed(file); - inode_lock(bd_inode); - bdev->bd_map_count++; if (IS_DAX(bd_inode)) { vma->vm_ops = &blkdev_dax_vm_ops; vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; } else { vma->vm_ops = &blkdev_default_vm_ops; } - inode_unlock(bd_inode); return 0; } diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 88d9af3d4581..5fb60ea7eee2 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, list_add_tail(&work->ordered_list, &wq->ordered_list); spin_unlock_irqrestore(&wq->list_lock, flags); } - queue_work(wq->normal_wq, &work->normal_work); trace_btrfs_work_queued(work); + queue_work(wq->normal_wq, &work->normal_work); } void btrfs_queue_work(struct btrfs_workqueue *wq, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dd08e29f5117..4545e2e2ad45 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -182,6 +182,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, + { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" }, { .id = 0, .name_stem = "tree" }, }; @@ -1787,7 +1788,6 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; - set_freezable(); do { again = 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 393e36bd5845..53dbeaf6ce94 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -153,6 +153,20 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize) static unsigned long *alloc_bitmap(u32 bitmap_size) { + void *mem; + + /* + * The allocation size varies, observed numbers were < 4K up to 16K. + * Using vmalloc unconditionally would be too heavy, we'll try + * contiguous allocations first. + */ + if (bitmap_size <= PAGE_SIZE) + return kzalloc(bitmap_size, GFP_NOFS); + + mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN); + if (mem) + return mem; + return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); } @@ -289,7 +303,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, ret = 0; out: - vfree(bitmap); + kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; @@ -438,7 +452,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, ret = 0; out: - vfree(bitmap); + kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e28f3d4691af..5f06eb1f4384 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7116,21 +7116,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, if (ret) return ERR_PTR(ret); - em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, - ins.offset, ins.offset, ins.offset, 0); - if (IS_ERR(em)) { - btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - return em; - } - + /* + * Create the ordered extent before the extent map. This is to avoid + * races with the fast fsync path that would lead to it logging file + * extent items that point to disk extents that were not yet written to. + * The fast fsync path collects ordered extents into a local list and + * then collects all the new extent maps, so we must create the ordered + * extent first and make sure the fast fsync path collects any new + * ordered extents after collecting new extent maps as well. + * The fsync path simply can not rely on inode_dio_wait() because it + * causes deadlock with AIO. + */ ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, ins.offset, ins.offset, 0); if (ret) { btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - free_extent_map(em); return ERR_PTR(ret); } + em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, + ins.offset, ins.offset, ins.offset, 0); + if (IS_ERR(em)) { + struct btrfs_ordered_extent *oe; + + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); + oe = btrfs_lookup_ordered_extent(inode, start); + ASSERT(oe); + if (WARN_ON(!oe)) + return em; + set_bit(BTRFS_ORDERED_IOERR, &oe->flags); + set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags); + btrfs_remove_ordered_extent(inode, oe); + /* Once for our lookup and once for the ordered extents tree. */ + btrfs_put_ordered_extent(oe); + btrfs_put_ordered_extent(oe); + } return em; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index fd1c4d982463..2bd0011450df 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -575,7 +575,8 @@ static int is_cowonly_root(u64 root_objectid) root_objectid == BTRFS_TREE_LOG_OBJECTID || root_objectid == BTRFS_CSUM_TREE_OBJECTID || root_objectid == BTRFS_UUID_TREE_OBJECTID || - root_objectid == BTRFS_QUOTA_TREE_OBJECTID) + root_objectid == BTRFS_QUOTA_TREE_OBJECTID || + root_objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) return 1; return 0; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index e0ac85949067..539e7b5e3f86 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -202,6 +202,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF); BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56); BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES); +BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE); static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(mixed_backref), @@ -213,6 +214,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(raid56), BTRFS_FEAT_ATTR_PTR(skinny_metadata), BTRFS_FEAT_ATTR_PTR(no_holes), + BTRFS_FEAT_ATTR_PTR(free_space_tree), NULL }; @@ -780,6 +782,39 @@ failure: return error; } + +/* + * Change per-fs features in /sys/fs/btrfs/UUID/features to match current + * values in superblock. Call after any changes to incompat/compat_ro flags + */ +void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, + u64 bit, enum btrfs_feature_set set) +{ + struct btrfs_fs_devices *fs_devs; + struct kobject *fsid_kobj; + u64 features; + int ret; + + if (!fs_info) + return; + + features = get_features(fs_info, set); + ASSERT(bit & supported_feature_masks[set]); + + fs_devs = fs_info->fs_devices; + fsid_kobj = &fs_devs->fsid_kobj; + + if (!fsid_kobj->state_initialized) + return; + + /* + * FIXME: this is too heavy to update just one value, ideally we'd like + * to use sysfs_update_group but some refactoring is needed first. + */ + sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group); + ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group); +} + static int btrfs_init_debugfs(void) { #ifdef CONFIG_DEBUG_FS diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 9c09522125a6..d7da1a4c2f6c 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -56,7 +56,7 @@ static struct btrfs_feature_attr btrfs_attr_##_name = { \ #define BTRFS_FEAT_ATTR_COMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature) #define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \ - BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature) + BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature) #define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature) @@ -90,4 +90,7 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, struct kobject *parent); int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs); void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs); +void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, + u64 bit, enum btrfs_feature_set set); + #endif /* _BTRFS_SYSFS_H_ */ diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index b1d920b30070..0e1e61a7ec23 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -82,18 +82,18 @@ void btrfs_destroy_test_fs(void) struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void) { struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info), - GFP_NOFS); + GFP_KERNEL); if (!fs_info) return fs_info; fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices), - GFP_NOFS); + GFP_KERNEL); if (!fs_info->fs_devices) { kfree(fs_info); return NULL; } fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block), - GFP_NOFS); + GFP_KERNEL); if (!fs_info->super_copy) { kfree(fs_info->fs_devices); kfree(fs_info); @@ -180,11 +180,11 @@ btrfs_alloc_dummy_block_group(unsigned long length) { struct btrfs_block_group_cache *cache; - cache = kzalloc(sizeof(*cache), GFP_NOFS); + cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (!cache) return NULL; cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl), - GFP_NOFS); + GFP_KERNEL); if (!cache->free_space_ctl) { kfree(cache); return NULL; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index e29fa297e053..669b58201e36 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -94,7 +94,7 @@ static int test_find_delalloc(void) * test. */ for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) { - page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL); if (!page) { test_msg("Failed to allocate test page\n"); ret = -ENOMEM; @@ -113,7 +113,7 @@ static int test_find_delalloc(void) * |--- delalloc ---| * |--- search ---| */ - set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL); start = 0; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -144,7 +144,7 @@ static int test_find_delalloc(void) test_msg("Couldn't find the locked page\n"); goto out_bits; } - set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -199,7 +199,7 @@ static int test_find_delalloc(void) * * We are re-using our test_start from above since it works out well. */ - set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -262,7 +262,7 @@ static int test_find_delalloc(void) } ret = 0; out_bits: - clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS); + clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL); out: if (locked_page) page_cache_release(locked_page); @@ -360,7 +360,7 @@ static int test_eb_bitmaps(void) test_msg("Running extent buffer bitmap tests\n"); - bitmap = kmalloc(len, GFP_NOFS); + bitmap = kmalloc(len, GFP_KERNEL); if (!bitmap) { test_msg("Couldn't allocate test bitmap\n"); return -ENOMEM; diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 5de55fdd28bc..e2d3da02deee 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -974,7 +974,7 @@ static int test_extent_accounting(void) (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095, EXTENT_DELALLOC | EXTENT_DIRTY | EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1045,7 +1045,7 @@ static int test_extent_accounting(void) BTRFS_MAX_EXTENT_SIZE+8191, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1079,7 +1079,7 @@ static int test_extent_accounting(void) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1096,7 +1096,7 @@ out: clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); iput(inode); btrfs_free_dummy_root(root); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 323e12cc9d2f..978c3a810893 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4127,7 +4127,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_path *path, struct list_head *logged_list, - struct btrfs_log_ctx *ctx) + struct btrfs_log_ctx *ctx, + const u64 start, + const u64 end) { struct extent_map *em, *n; struct list_head extents; @@ -4166,7 +4168,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - + /* + * Collect any new ordered extents within the range. This is to + * prevent logging file extent items without waiting for the disk + * location they point to being written. We do this only to deal + * with races against concurrent lockless direct IO writes. + */ + btrfs_get_logged_extents(inode, logged_list, start, end); process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); @@ -4701,7 +4709,7 @@ log_extents: goto out_unlock; } ret = btrfs_log_changed_extents(trans, root, inode, dst_path, - &logged_list, ctx); + &logged_list, ctx, start, end); if (ret) { err = ret; goto out_unlock; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index a5b8eb69a8f4..6402eaf8ab95 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1261,6 +1261,9 @@ COMPATIBLE_IOCTL(HCIUNBLOCKADDR) COMPATIBLE_IOCTL(HCIINQUIRY) COMPATIBLE_IOCTL(HCIUARTSETPROTO) COMPATIBLE_IOCTL(HCIUARTGETPROTO) +COMPATIBLE_IOCTL(HCIUARTGETDEVICE) +COMPATIBLE_IOCTL(HCIUARTSETFLAGS) +COMPATIBLE_IOCTL(HCIUARTGETFLAGS) COMPATIBLE_IOCTL(RFCOMMCREATEDEV) COMPATIBLE_IOCTL(RFCOMMRELEASEDEV) COMPATIBLE_IOCTL(RFCOMMGETDEVLIST) @@ -58,6 +58,26 @@ static void dax_unmap_atomic(struct block_device *bdev, blk_queue_exit(bdev->bd_queue); } +struct page *read_dax_sector(struct block_device *bdev, sector_t n) +{ + struct page *page = alloc_pages(GFP_KERNEL, 0); + struct blk_dax_ctl dax = { + .size = PAGE_SIZE, + .sector = n & ~((((int) PAGE_SIZE) / 512) - 1), + }; + long rc; + + if (!page) + return ERR_PTR(-ENOMEM); + + rc = dax_map_atomic(bdev, &dax); + if (rc < 0) + return ERR_PTR(rc); + memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE); + dax_unmap_atomic(bdev, &dax); + return page; +} + /* * dax_clear_blocks() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 5bcd92d50e82..0cb1abd535e3 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1215,7 +1215,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, hdr->pgio_mirror_idx + 1, &hdr->pgio_mirror_idx)) goto out_eagain; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &hdr->lseg->pls_layout->plh_flags); pnfs_read_resend_pnfs(hdr); return task->tk_status; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 29898a9550fa..eb370460ce20 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -412,7 +412,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, OP_ILLEGAL, GFP_NOIO); if (!fail_return) { if (ff_layout_has_available_ds(lseg)) - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lseg->pls_layout->plh_flags); else pnfs_error_mark_layout_for_return(ino, lseg); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a3592cc34a20..482b6e94bb37 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -52,9 +52,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock); */ static LIST_HEAD(pnfs_modules_tbl); -static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, - enum pnfs_iomode iomode, bool sync); +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo); /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * @@ -243,6 +241,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { struct inode *inode = lo->plh_inode; + pnfs_layoutreturn_before_put_layout_hdr(lo); + if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { if (!list_empty(&lo->plh_segs)) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); @@ -345,58 +345,6 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } -/* Return true if layoutreturn is needed */ -static bool -pnfs_layout_need_return(struct pnfs_layout_hdr *lo, - struct pnfs_layout_segment *lseg) -{ - struct pnfs_layout_segment *s; - - if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - return false; - - list_for_each_entry(s, &lo->plh_segs, pls_list) - if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - - return true; -} - -static bool -pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) -{ - if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) - return false; - lo->plh_return_iomode = 0; - pnfs_get_layout_hdr(lo); - clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - return true; -} - -static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, - struct pnfs_layout_hdr *lo, struct inode *inode) -{ - lo = lseg->pls_layout; - inode = lo->plh_inode; - - spin_lock(&inode->i_lock); - if (pnfs_layout_need_return(lo, lseg)) { - nfs4_stateid stateid; - enum pnfs_iomode iomode; - bool send; - - nfs4_stateid_copy(&stateid, &lo->plh_stateid); - iomode = lo->plh_return_iomode; - send = pnfs_prepare_layoutreturn(lo); - spin_unlock(&inode->i_lock); - if (send) { - /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, &stateid, iomode, false); - } - } else - spin_unlock(&inode->i_lock); -} - void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -410,15 +358,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) atomic_read(&lseg->pls_refcount), test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); - /* Handle the case where refcount != 1 */ - if (atomic_add_unless(&lseg->pls_refcount, -1, 1)) - return; - lo = lseg->pls_layout; inode = lo->plh_inode; - /* Do we need a layoutreturn? */ - if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) { @@ -937,6 +878,17 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } +static bool +pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) +{ + if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + return false; + lo->plh_return_iomode = 0; + pnfs_get_layout_hdr(lo); + clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); + return true; +} + static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync) @@ -971,6 +923,48 @@ out: return status; } +/* Return true if layoutreturn is needed */ +static bool +pnfs_layout_need_return(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *s; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return false; + + /* Defer layoutreturn until all lsegs are done */ + list_for_each_entry(s, &lo->plh_segs, pls_list) { + if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) + return false; + } + + return true; +} + +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct inode *inode= lo->plh_inode; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return; + spin_lock(&inode->i_lock); + if (pnfs_layout_need_return(lo)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode; + bool send; + + nfs4_stateid_copy(&stateid, &lo->plh_stateid); + iomode = lo->plh_return_iomode; + send = pnfs_prepare_layoutreturn(lo); + spin_unlock(&inode->i_lock); + if (send) { + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, &stateid, iomode, false); + } + } else + spin_unlock(&inode->i_lock); +} + /* * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr * when the layout segment list is empty. @@ -1091,7 +1085,7 @@ bool pnfs_roc(struct inode *ino) nfs4_stateid_copy(&stateid, &lo->plh_stateid); /* always send layoutreturn if being marked so */ - if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) layoutreturn = pnfs_prepare_layoutreturn(lo); @@ -1772,7 +1766,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, pnfs_set_plh_return_iomode(lo, return_range->iomode); if (!mark_lseg_invalid(lseg, tmp_list)) remaining++; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } return remaining; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9f4e2a47f4aa..1ac1db5f6dad 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,8 +94,8 @@ enum { NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ - NFS_LAYOUT_RETURN, /* Return this layout ASAP */ - NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ + NFS_LAYOUT_RETURN, /* layoutreturn in progress */ + NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ }; diff --git a/fs/timerfd.c b/fs/timerfd.c index b94fa6c3c6eb..053818dd6c18 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else - remaining = hrtimer_expires_remaining(&ctx->t.tmr); + remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 89d008dc08e2..fe5efada9d68 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -42,6 +42,10 @@ int drm_atomic_helper_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async); +bool drm_atomic_helper_framebuffer_changed(struct drm_device *dev, + struct drm_atomic_state *old_state, + struct drm_crtc *crtc); + void drm_atomic_helper_wait_for_vblanks(struct drm_device *dev, struct drm_atomic_state *old_state); diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h index bda5ec0b4b4d..fccf7f44139d 100644 --- a/include/linux/cleancache.h +++ b/include/linux/cleancache.h @@ -37,7 +37,7 @@ struct cleancache_ops { void (*invalidate_fs)(int); }; -extern int cleancache_register_ops(struct cleancache_ops *ops); +extern int cleancache_register_ops(const struct cleancache_ops *ops); extern void __cleancache_init_fs(struct super_block *); extern void __cleancache_init_shared_fs(struct super_block *); extern int __cleancache_get_page(struct page *); @@ -48,14 +48,14 @@ extern void __cleancache_invalidate_fs(struct super_block *); #ifdef CONFIG_CLEANCACHE #define cleancache_enabled (1) -static inline bool cleancache_fs_enabled(struct page *page) -{ - return page->mapping->host->i_sb->cleancache_poolid >= 0; -} static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) { return mapping->host->i_sb->cleancache_poolid >= 0; } +static inline bool cleancache_fs_enabled(struct page *page) +{ + return cleancache_fs_enabled_mapping(page->mapping); +} #else #define cleancache_enabled (0) #define cleancache_fs_enabled(_page) (0) @@ -89,11 +89,9 @@ static inline void cleancache_init_shared_fs(struct super_block *sb) static inline int cleancache_get_page(struct page *page) { - int ret = -1; - if (cleancache_enabled && cleancache_fs_enabled(page)) - ret = __cleancache_get_page(page); - return ret; + return __cleancache_get_page(page); + return -1; } static inline void cleancache_put_page(struct page *page) diff --git a/include/linux/dax.h b/include/linux/dax.h index 8204c3dc3800..818e45078929 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,17 @@ int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, dax_iodone_t); int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, dax_iodone_t); + +#ifdef CONFIG_FS_DAX +struct page *read_dax_sector(struct block_device *bdev, sector_t n); +#else +static inline struct page *read_dax_sector(struct block_device *bdev, + sector_t n) +{ + return ERR_PTR(-ENXIO); +} +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, unsigned int flags, get_block_t, dax_iodone_t); diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a2046275cdf..ae681002100a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -484,9 +484,6 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -#ifdef CONFIG_FS_DAX - int bd_map_count; -#endif }; /* @@ -2907,7 +2904,7 @@ extern void replace_mount_options(struct super_block *sb, char *options); static inline bool io_is_direct(struct file *filp) { - return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp)); + return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } static inline int iocb_flags(struct file *file) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0639dcc98195..81de7123959d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -165,7 +165,6 @@ struct ftrace_ops { ftrace_func_t saved_func; int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE - int nr_trampolines; struct ftrace_ops_hash local_hash; struct ftrace_ops_hash *func_hash; struct ftrace_ops_hash old_hash; diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 76dd4f0da5ca..2ead22dd74a0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -87,7 +87,8 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @start_pid: timer statistics field to store the pid of the task which + * @is_rel: Set if the timer was armed relative + * @start_pid: timer statistics field to store the pid of the task which * started the timer * @start_site: timer statistics field to store the site where the timer * was started @@ -101,7 +102,8 @@ struct hrtimer { ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; - unsigned long state; + u8 state; + u8 is_rel; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; @@ -321,6 +323,27 @@ static inline void clock_was_set_delayed(void) { } #endif +static inline ktime_t +__hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now) +{ + ktime_t rem = ktime_sub(timer->node.expires, now); + + /* + * Adjust relative timers for the extra we added in + * hrtimer_start_range_ns() to prevent short timeouts. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && timer->is_rel) + rem.tv64 -= hrtimer_resolution; + return rem; +} + +static inline ktime_t +hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) +{ + return __hrtimer_expires_remaining_adjusted(timer, + timer->base->get_time()); +} + extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); @@ -390,7 +413,12 @@ static inline void hrtimer_restart(struct hrtimer *timer) } /* Query timers: */ -extern ktime_t hrtimer_get_remaining(const struct hrtimer *timer); +extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +{ + return __hrtimer_get_remaining(timer, false); +} extern u64 hrtimer_get_next_event(void); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f28dff313b07..a5c539fa5d2b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -133,8 +133,9 @@ struct iommu_dm_region { /** * struct iommu_ops - iommu ops and capabilities - * @domain_init: init iommu domain - * @domain_destroy: destroy iommu domain + * @capable: check capability + * @domain_alloc: allocate iommu domain + * @domain_free: free iommu domain * @attach_dev: attach device to an iommu domain * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain @@ -144,8 +145,15 @@ struct iommu_dm_region { * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping * @remove_device: remove device from iommu grouping + * @device_group: find iommu group for a particular device * @domain_get_attr: Query domain attributes * @domain_set_attr: Change domain attributes + * @get_dm_regions: Request list of direct mapping requirements for a device + * @put_dm_regions: Free list of direct mapping requirements for a device + * @domain_window_enable: Configure and enable a particular window for a domain + * @domain_window_disable: Disable a particular window for a domain + * @domain_set_windows: Set the number of windows for a domain + * @domain_get_windows: Return the number of windows for a domain * @of_xlate: add OF master IDs to iommu grouping * @pgsize_bitmap: bitmap of supported page sizes * @priv: per-instance data private to the iommu driver @@ -182,9 +190,9 @@ struct iommu_ops { int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); - /* Set the numer of window per domain */ + /* Set the number of windows per domain */ int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); - /* Get the numer of window per domain */ + /* Get the number of windows per domain */ u32 (*domain_get_windows)(struct iommu_domain *domain); #ifdef CONFIG_OF_IOMMU diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index f64622ad02c1..04579d9fbce4 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -70,6 +70,7 @@ struct irq_fwspec { */ enum irq_domain_bus_token { DOMAIN_BUS_ANY = 0, + DOMAIN_BUS_WIRED, DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ac140dcb789..289c2314d766 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -512,7 +512,6 @@ static inline void napi_enable(struct napi_struct *n) clear_bit(NAPI_STATE_NPSVC, &n->state); } -#ifdef CONFIG_SMP /** * napi_synchronize - wait until NAPI is not running * @n: napi context @@ -523,12 +522,12 @@ static inline void napi_enable(struct napi_struct *n) */ static inline void napi_synchronize(const struct napi_struct *n) { - while (test_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); + if (IS_ENABLED(CONFIG_SMP)) + while (test_bit(NAPI_STATE_SCHED, &n->state)) + msleep(1); + else + barrier(); } -#else -# define napi_synchronize(n) barrier() -#endif enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f9828a48f16a..b35a61a481fa 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -634,9 +634,6 @@ struct perf_event_context { int nr_cgroups; /* cgroup evts */ void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; - - struct delayed_work orphans_remove; - bool orphans_remove_sched; }; /* @@ -729,7 +726,7 @@ extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); -extern struct perf_event *perf_event_get(unsigned int fd); +extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); @@ -1044,7 +1041,7 @@ extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); -extern int __perf_event_disable(void *info); +extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_task_tick(void); #else /* !CONFIG_PERF_EVENTS: */ static inline void * @@ -1070,7 +1067,7 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } -static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 0703b5360d31..37448ab5fb5c 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -29,7 +29,7 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn) return __pfn_to_pfn_t(pfn, 0); } -extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags); +extern pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags); static inline bool pfn_t_has_page(pfn_t pfn) { @@ -48,7 +48,7 @@ static inline struct page *pfn_t_to_page(pfn_t pfn) return NULL; } -static inline dma_addr_t pfn_t_to_phys(pfn_t pfn) +static inline phys_addr_t pfn_t_to_phys(pfn_t pfn) { return PFN_PHYS(pfn_t_to_pfn(pfn)); } diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index e7a018eaf3a2..017fced60242 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -1,10 +1,13 @@ #ifndef __LINUX_SWIOTLB_H #define __LINUX_SWIOTLB_H +#include <linux/dma-direction.h> +#include <linux/init.h> #include <linux/types.h> struct device; struct dma_attrs; +struct page; struct scatterlist; extern int swiotlb_force; diff --git a/include/linux/tty.h b/include/linux/tty.h index 2fd8708ea888..d9fb4b043f56 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -649,6 +649,7 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* tty_mutex.c */ /* functions for preparation of BKL removal */ extern void __lockfunc tty_lock(struct tty_struct *tty); +extern int tty_lock_interruptible(struct tty_struct *tty); extern void __lockfunc tty_unlock(struct tty_struct *tty); extern void __lockfunc tty_lock_slave(struct tty_struct *tty); extern void __lockfunc tty_unlock_slave(struct tty_struct *tty); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 52899291f401..5ee3c689c863 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -252,6 +252,12 @@ struct l2cap_conn_rsp { #define L2CAP_PSM_3DSP 0x0021 #define L2CAP_PSM_IPSP 0x0023 /* 6LoWPAN */ +#define L2CAP_PSM_DYN_START 0x1001 +#define L2CAP_PSM_DYN_END 0xffff +#define L2CAP_PSM_AUTO_END 0x10ff +#define L2CAP_PSM_LE_DYN_START 0x0080 +#define L2CAP_PSM_LE_DYN_END 0x00ff + /* channel identifier */ #define L2CAP_CID_SIGNALING 0x0001 #define L2CAP_CID_CONN_LESS 0x0002 diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 6816f0fa5693..30a56ab2ccfb 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -44,6 +44,24 @@ static inline bool skb_valid_dst(const struct sk_buff *skb) return dst && !(dst->flags & DST_METADATA); } +static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + const struct metadata_dst *a, *b; + + if (!(skb_a->_skb_refdst | skb_b->_skb_refdst)) + return 0; + + a = (const struct metadata_dst *) skb_dst(skb_a); + b = (const struct metadata_dst *) skb_dst(skb_b); + + if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len) + return 1; + + return memcmp(&a->u.tun_info, &b->u.tun_info, + sizeof(a->u.tun_info) + a->u.tun_info.options_len); +} + struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 877f682989b8..295d291269e2 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -64,8 +64,16 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) void ip6_route_input(struct sk_buff *skb); -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6); +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags); + +static inline struct dst_entry *ip6_route_output(struct net *net, + const struct sock *sk, + struct flowi6 *fl6) +{ + return ip6_route_output_flags(net, sk, fl6, 0); +} + struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 788ef58a66b9..62e17d1319ff 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -79,12 +79,10 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *proto); -#ifdef CONFIG_LOCKDEP -# define CONNTRACK_LOCKS 8 -#else -# define CONNTRACK_LOCKS 1024 -#endif +#define CONNTRACK_LOCKS 1024 + extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; +void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 20e72129be1c..205630bb5010 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -756,7 +756,6 @@ struct sctp_transport { /* Reference counting. */ atomic_t refcnt; - __u32 dead:1, /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, @@ -766,7 +765,7 @@ struct sctp_transport { * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ - rto_pending:1, + __u32 rto_pending:1, /* * hb_sent : a flag that signals that we have a pending @@ -955,7 +954,7 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk); void sctp_transport_free(struct sctp_transport *); void sctp_transport_reset_timers(struct sctp_transport *); -void sctp_transport_hold(struct sctp_transport *); +int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); diff --git a/include/net/sock.h b/include/net/sock.h index b9e7b3d863a0..f5ea148853e2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1036,18 +1036,6 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif -#ifdef CONFIG_MEMCG_KMEM - /* - * cgroup specific init/deinit functions. Called once for all - * protocols that implement it, from cgroups populate function. - * This function has to setup any files the protocol want to - * appear in the kmem cgroup filesystem. - */ - int (*init_cgroup)(struct mem_cgroup *memcg, - struct cgroup_subsys *ss); - void (*destroy_cgroup)(struct mem_cgroup *memcg); - struct cg_proto *(*proto_cgroup)(struct mem_cgroup *memcg); -#endif int (*diag_destroy)(struct sock *sk, int err); }; diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 7dda3d7adba8..aecd30308d50 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -16,7 +16,7 @@ struct sock_reuseport { }; extern int reuseport_alloc(struct sock *sk); -extern int reuseport_add_sock(struct sock *sk, const struct sock *sk2); +extern int reuseport_add_sock(struct sock *sk, struct sock *sk2); extern void reuseport_detach_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, diff --git a/include/net/tcp.h b/include/net/tcp.h index 8ea19977ea53..f6f8f032c73e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -216,7 +216,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ -/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */ +/* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ diff --git a/include/trace/events/fence.h b/include/trace/events/fence.h index 98feb1b82896..d6dfa05ba322 100644 --- a/include/trace/events/fence.h +++ b/include/trace/events/fence.h @@ -17,7 +17,7 @@ TRACE_EVENT(fence_annotate_wait_on, TP_STRUCT__entry( __string(driver, fence->ops->get_driver_name(fence)) - __string(timeline, fence->ops->get_driver_name(fence)) + __string(timeline, fence->ops->get_timeline_name(fence)) __field(unsigned int, context) __field(unsigned int, seqno) diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index 4cc989ad6851..f95e1c43c3fb 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -48,6 +48,8 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_FEATURES_2 0x05 #define ETNAVIV_PARAM_GPU_FEATURES_3 0x06 #define ETNAVIV_PARAM_GPU_FEATURES_4 0x07 +#define ETNAVIV_PARAM_GPU_FEATURES_5 0x08 +#define ETNAVIV_PARAM_GPU_FEATURES_6 0x09 #define ETNAVIV_PARAM_GPU_STREAM_COUNT 0x10 #define ETNAVIV_PARAM_GPU_REGISTER_MAX 0x11 @@ -59,6 +61,7 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_BUFFER_SIZE 0x17 #define ETNAVIV_PARAM_GPU_INSTRUCTION_COUNT 0x18 #define ETNAVIV_PARAM_GPU_NUM_CONSTANTS 0x19 +#define ETNAVIV_PARAM_GPU_NUM_VARYINGS 0x1a #define ETNA_MAX_PIPES 4 diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 41e0433b4a83..149bec83a907 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -222,7 +222,6 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) -#define BLKDAXSET _IO(0x12,128) #define BLKDAXGET _IO(0x12,129) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b0799bced518..89ebbc4d1164 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -291,10 +291,13 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) { struct perf_event *event; const struct perf_event_attr *attr; + struct file *file; - event = perf_event_get(fd); - if (IS_ERR(event)) - return event; + file = perf_event_get(fd); + if (IS_ERR(file)) + return file; + + event = file->private_data; attr = perf_event_attrs(event); if (IS_ERR(attr)) @@ -304,24 +307,22 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) goto err; if (attr->type == PERF_TYPE_RAW) - return event; + return file; if (attr->type == PERF_TYPE_HARDWARE) - return event; + return file; if (attr->type == PERF_TYPE_SOFTWARE && attr->config == PERF_COUNT_SW_BPF_OUTPUT) - return event; + return file; err: - perf_event_release_kernel(event); + fput(file); return ERR_PTR(-EINVAL); } static void perf_event_fd_array_put_ptr(void *ptr) { - struct perf_event *event = ptr; - - perf_event_release_kernel(event); + fput((struct file *)ptr); } static const struct bpf_map_ops perf_event_array_ops = { diff --git a/kernel/events/core.c b/kernel/events/core.c index 06ae52e99ac2..5946460b2425 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -49,8 +49,6 @@ #include <asm/irq_regs.h> -static struct workqueue_struct *perf_wq; - typedef int (*remote_function_f)(void *); struct remote_function_call { @@ -126,44 +124,181 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info) return data.ret; } -static void event_function_call(struct perf_event *event, - int (*active)(void *), - void (*inactive)(void *), - void *data) +static inline struct perf_cpu_context * +__get_cpu_context(struct perf_event_context *ctx) +{ + return this_cpu_ptr(ctx->pmu->pmu_cpu_context); +} + +static void perf_ctx_lock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx) + raw_spin_lock(&ctx->lock); +} + +static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (ctx) + raw_spin_unlock(&ctx->lock); + raw_spin_unlock(&cpuctx->ctx.lock); +} + +#define TASK_TOMBSTONE ((void *)-1L) + +static bool is_kernel_event(struct perf_event *event) +{ + return READ_ONCE(event->owner) == TASK_TOMBSTONE; +} + +/* + * On task ctx scheduling... + * + * When !ctx->nr_events a task context will not be scheduled. This means + * we can disable the scheduler hooks (for performance) without leaving + * pending task ctx state. + * + * This however results in two special cases: + * + * - removing the last event from a task ctx; this is relatively straight + * forward and is done in __perf_remove_from_context. + * + * - adding the first event to a task ctx; this is tricky because we cannot + * rely on ctx->is_active and therefore cannot use event_function_call(). + * See perf_install_in_context(). + * + * This is because we need a ctx->lock serialized variable (ctx->is_active) + * to reliably determine if a particular task/context is scheduled in. The + * task_curr() use in task_function_call() is racy in that a remote context + * switch is not a single atomic operation. + * + * As is, the situation is 'safe' because we set rq->curr before we do the + * actual context switch. This means that task_curr() will fail early, but + * we'll continue spinning on ctx->is_active until we've passed + * perf_event_task_sched_out(). + * + * Without this ctx->lock serialized variable we could have race where we find + * the task (and hence the context) would not be active while in fact they are. + * + * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. + */ + +typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *, + struct perf_event_context *, void *); + +struct event_function_struct { + struct perf_event *event; + event_f func; + void *data; +}; + +static int event_function(void *info) +{ + struct event_function_struct *efs = info; + struct perf_event *event = efs->event; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + int ret = 0; + + WARN_ON_ONCE(!irqs_disabled()); + + perf_ctx_lock(cpuctx, task_ctx); + /* + * Since we do the IPI call without holding ctx->lock things can have + * changed, double check we hit the task we set out to hit. + */ + if (ctx->task) { + if (ctx->task != current) { + ret = -EAGAIN; + goto unlock; + } + + /* + * We only use event_function_call() on established contexts, + * and event_function() is only ever called when active (or + * rather, we'll have bailed in task_function_call() or the + * above ctx->task != current test), therefore we must have + * ctx->is_active here. + */ + WARN_ON_ONCE(!ctx->is_active); + /* + * And since we have ctx->is_active, cpuctx->task_ctx must + * match. + */ + WARN_ON_ONCE(task_ctx != ctx); + } else { + WARN_ON_ONCE(&cpuctx->ctx != ctx); + } + + efs->func(event, cpuctx, ctx, efs->data); +unlock: + perf_ctx_unlock(cpuctx, task_ctx); + + return ret; +} + +static void event_function_local(struct perf_event *event, event_f func, void *data) +{ + struct event_function_struct efs = { + .event = event, + .func = func, + .data = data, + }; + + int ret = event_function(&efs); + WARN_ON_ONCE(ret); +} + +static void event_function_call(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; - struct task_struct *task = ctx->task; + struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */ + struct event_function_struct efs = { + .event = event, + .func = func, + .data = data, + }; + + if (!event->parent) { + /* + * If this is a !child event, we must hold ctx::mutex to + * stabilize the the event->ctx relation. See + * perf_event_ctx_lock(). + */ + lockdep_assert_held(&ctx->mutex); + } if (!task) { - cpu_function_call(event->cpu, active, data); + cpu_function_call(event->cpu, event_function, &efs); return; } again: - if (!task_function_call(task, active, data)) + if (task == TASK_TOMBSTONE) + return; + + if (!task_function_call(task, event_function, &efs)) return; raw_spin_lock_irq(&ctx->lock); - if (ctx->is_active) { - /* - * Reload the task pointer, it might have been changed by - * a concurrent perf_event_context_sched_out(). - */ - task = ctx->task; - raw_spin_unlock_irq(&ctx->lock); - goto again; + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + if (task != TASK_TOMBSTONE) { + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + func(event, NULL, ctx, data); } - inactive(data); raw_spin_unlock_irq(&ctx->lock); } -#define EVENT_OWNER_KERNEL ((void *) -1) - -static bool is_kernel_event(struct perf_event *event) -{ - return event->owner == EVENT_OWNER_KERNEL; -} - #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -368,28 +503,6 @@ static inline u64 perf_event_clock(struct perf_event *event) return event->clock(); } -static inline struct perf_cpu_context * -__get_cpu_context(struct perf_event_context *ctx) -{ - return this_cpu_ptr(ctx->pmu->pmu_cpu_context); -} - -static void perf_ctx_lock(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - raw_spin_lock(&cpuctx->ctx.lock); - if (ctx) - raw_spin_lock(&ctx->lock); -} - -static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - if (ctx) - raw_spin_unlock(&ctx->lock); - raw_spin_unlock(&cpuctx->ctx.lock); -} - #ifdef CONFIG_CGROUP_PERF static inline bool @@ -579,13 +692,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, * we are holding the rcu lock */ cgrp1 = perf_cgroup_from_task(task, NULL); - - /* - * next is NULL when called from perf_event_enable_on_exec() - * that will systematically cause a cgroup_switch() - */ - if (next) - cgrp2 = perf_cgroup_from_task(next, NULL); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -611,8 +718,6 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, * we are holding the rcu lock */ cgrp1 = perf_cgroup_from_task(task, NULL); - - /* prev can never be NULL */ cgrp2 = perf_cgroup_from_task(prev, NULL); /* @@ -917,7 +1022,7 @@ static void put_ctx(struct perf_event_context *ctx) if (atomic_dec_and_test(&ctx->refcount)) { if (ctx->parent_ctx) put_ctx(ctx->parent_ctx); - if (ctx->task) + if (ctx->task && ctx->task != TASK_TOMBSTONE) put_task_struct(ctx->task); call_rcu(&ctx->rcu_head, free_ctx); } @@ -934,9 +1039,8 @@ static void put_ctx(struct perf_event_context *ctx) * perf_event_context::mutex nests and those are: * * - perf_event_exit_task_context() [ child , 0 ] - * __perf_event_exit_task() - * sync_child_event() - * put_event() [ parent, 1 ] + * perf_event_exit_event() + * put_event() [ parent, 1 ] * * - perf_event_init_context() [ parent, 0 ] * inherit_task_group() @@ -979,8 +1083,8 @@ static void put_ctx(struct perf_event_context *ctx) * Lock order: * task_struct::perf_event_mutex * perf_event_context::mutex - * perf_event_context::lock * perf_event::child_mutex; + * perf_event_context::lock * perf_event::mmap_mutex * mmap_sem */ @@ -1078,6 +1182,7 @@ static u64 primary_event_id(struct perf_event *event) /* * Get the perf_event_context for a task and lock it. + * * This has to cope with with the fact that until it is locked, * the context could get moved to another task. */ @@ -1118,9 +1223,12 @@ retry: goto retry; } - if (!atomic_inc_not_zero(&ctx->refcount)) { + if (ctx->task == TASK_TOMBSTONE || + !atomic_inc_not_zero(&ctx->refcount)) { raw_spin_unlock(&ctx->lock); ctx = NULL; + } else { + WARN_ON_ONCE(ctx->task != task); } } rcu_read_unlock(); @@ -1246,6 +1354,8 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { + lockdep_assert_held(&ctx->lock); + WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); event->attach_state |= PERF_ATTACH_CONTEXT; @@ -1448,11 +1558,14 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) if (is_cgroup_event(event)) { ctx->nr_cgroups--; + /* + * Because cgroup events are always per-cpu events, this will + * always be called from the right CPU. + */ cpuctx = __get_cpu_context(ctx); /* - * if there are no more cgroup events - * then cler cgrp to avoid stale pointer - * in update_cgrp_time_from_cpuctx() + * If there are no more cgroup events then clear cgrp to avoid + * stale pointer in update_cgrp_time_from_cpuctx(). */ if (!ctx->nr_cgroups) cpuctx->cgrp = NULL; @@ -1530,45 +1643,11 @@ out: perf_event__header_size(tmp); } -/* - * User event without the task. - */ static bool is_orphaned_event(struct perf_event *event) { - return event && !is_kernel_event(event) && !event->owner; + return event->state == PERF_EVENT_STATE_EXIT; } -/* - * Event has a parent but parent's task finished and it's - * alive only because of children holding refference. - */ -static bool is_orphaned_child(struct perf_event *event) -{ - return is_orphaned_event(event->parent); -} - -static void orphans_remove_work(struct work_struct *work); - -static void schedule_orphans_remove(struct perf_event_context *ctx) -{ - if (!ctx->task || ctx->orphans_remove_sched || !perf_wq) - return; - - if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) { - get_ctx(ctx); - ctx->orphans_remove_sched = true; - } -} - -static int __init perf_workqueue_init(void) -{ - perf_wq = create_singlethread_workqueue("perf"); - WARN(!perf_wq, "failed to create perf workqueue\n"); - return perf_wq ? 0 : -1; -} - -core_initcall(perf_workqueue_init); - static inline int pmu_filter_match(struct perf_event *event) { struct pmu *pmu = event->pmu; @@ -1629,9 +1708,6 @@ event_sched_out(struct perf_event *event, if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; - if (is_orphaned_child(event)) - schedule_orphans_remove(ctx); - perf_pmu_enable(event->pmu); } @@ -1655,21 +1731,8 @@ group_sched_out(struct perf_event *group_event, cpuctx->exclusive = 0; } -struct remove_event { - struct perf_event *event; - bool detach_group; -}; - -static void ___perf_remove_from_context(void *info) -{ - struct remove_event *re = info; - struct perf_event *event = re->event; - struct perf_event_context *ctx = event->ctx; - - if (re->detach_group) - perf_group_detach(event); - list_del_event(event, ctx); -} +#define DETACH_GROUP 0x01UL +#define DETACH_STATE 0x02UL /* * Cross CPU call to remove a performance event @@ -1677,33 +1740,33 @@ static void ___perf_remove_from_context(void *info) * We disable the event on the hardware level first. After that we * remove it from the context list. */ -static int __perf_remove_from_context(void *info) +static void +__perf_remove_from_context(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct remove_event *re = info; - struct perf_event *event = re->event; - struct perf_event_context *ctx = event->ctx; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + unsigned long flags = (unsigned long)info; - raw_spin_lock(&ctx->lock); event_sched_out(event, cpuctx, ctx); - if (re->detach_group) + if (flags & DETACH_GROUP) perf_group_detach(event); list_del_event(event, ctx); - if (!ctx->nr_events && cpuctx->task_ctx == ctx) { + if (flags & DETACH_STATE) + event->state = PERF_EVENT_STATE_EXIT; + + if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; - cpuctx->task_ctx = NULL; + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + cpuctx->task_ctx = NULL; + } } - raw_spin_unlock(&ctx->lock); - - return 0; } /* * Remove the event from a task's (or a CPU's) list of events. * - * CPU events are removed with a smp call. For task events we only - * call when the task is on a CPU. - * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to * remains valid. This is OK when called from perf_release since @@ -1711,73 +1774,32 @@ static int __perf_remove_from_context(void *info) * When called from perf_event_exit_task, it's OK because the * context has been detached from its task. */ -static void perf_remove_from_context(struct perf_event *event, bool detach_group) +static void perf_remove_from_context(struct perf_event *event, unsigned long flags) { - struct perf_event_context *ctx = event->ctx; - struct remove_event re = { - .event = event, - .detach_group = detach_group, - }; + lockdep_assert_held(&event->ctx->mutex); - lockdep_assert_held(&ctx->mutex); - - event_function_call(event, __perf_remove_from_context, - ___perf_remove_from_context, &re); + event_function_call(event, __perf_remove_from_context, (void *)flags); } /* * Cross CPU call to disable a performance event */ -int __perf_event_disable(void *info) -{ - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - - /* - * If this is a per-task event, need to check whether this - * event's task is the current task on this cpu. - * - * Can trigger due to concurrent perf_event_context_sched_out() - * flipping contexts around. - */ - if (ctx->task && cpuctx->task_ctx != ctx) - return -EINVAL; - - raw_spin_lock(&ctx->lock); - - /* - * If the event is on, turn it off. - * If it is in error state, leave it in error state. - */ - if (event->state >= PERF_EVENT_STATE_INACTIVE) { - update_context_time(ctx); - update_cgrp_time_from_event(event); - update_group_times(event); - if (event == event->group_leader) - group_sched_out(event, cpuctx, ctx); - else - event_sched_out(event, cpuctx, ctx); - event->state = PERF_EVENT_STATE_OFF; - } - - raw_spin_unlock(&ctx->lock); - - return 0; -} - -void ___perf_event_disable(void *info) +static void __perf_event_disable(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct perf_event *event = info; + if (event->state < PERF_EVENT_STATE_INACTIVE) + return; - /* - * Since we have the lock this context can't be scheduled - * in, so we can change the state safely. - */ - if (event->state == PERF_EVENT_STATE_INACTIVE) { - update_group_times(event); - event->state = PERF_EVENT_STATE_OFF; - } + update_context_time(ctx); + update_cgrp_time_from_event(event); + update_group_times(event); + if (event == event->group_leader) + group_sched_out(event, cpuctx, ctx); + else + event_sched_out(event, cpuctx, ctx); + event->state = PERF_EVENT_STATE_OFF; } /* @@ -1788,7 +1810,8 @@ void ___perf_event_disable(void *info) * remains valid. This condition is satisifed when called through * perf_event_for_each_child or perf_event_for_each because they * hold the top-level event's child_mutex, so any descendant that - * goes to exit will block in sync_child_event. + * goes to exit will block in perf_event_exit_event(). + * * When called from perf_pending_event it's OK because event->ctx * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. @@ -1804,8 +1827,12 @@ static void _perf_event_disable(struct perf_event *event) } raw_spin_unlock_irq(&ctx->lock); - event_function_call(event, __perf_event_disable, - ___perf_event_disable, event); + event_function_call(event, __perf_event_disable, NULL); +} + +void perf_event_disable_local(struct perf_event *event) +{ + event_function_local(event, __perf_event_disable, NULL); } /* @@ -1918,9 +1945,6 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; - if (is_orphaned_child(event)) - schedule_orphans_remove(ctx); - out: perf_pmu_enable(event->pmu); @@ -2039,7 +2063,8 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void task_ctx_sched_out(struct perf_event_context *ctx); +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx); static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, @@ -2058,16 +2083,15 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx, ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); } -static void ___perf_install_in_context(void *info) +static void ctx_resched(struct perf_cpu_context *cpuctx, + struct perf_event_context *task_ctx) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; - - /* - * Since the task isn't running, its safe to add the event, us holding - * the ctx->lock ensures the task won't get scheduled in. - */ - add_event_to_ctx(event, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + if (task_ctx) + task_ctx_sched_out(cpuctx, task_ctx); + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + perf_event_sched_in(cpuctx, task_ctx, current); + perf_pmu_enable(cpuctx->ctx.pmu); } /* @@ -2077,55 +2101,31 @@ static void ___perf_install_in_context(void *info) */ static int __perf_install_in_context(void *info) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; + struct perf_event_context *ctx = info; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; - struct task_struct *task = current; - - perf_ctx_lock(cpuctx, task_ctx); - perf_pmu_disable(cpuctx->ctx.pmu); - - /* - * If there was an active task_ctx schedule it out. - */ - if (task_ctx) - task_ctx_sched_out(task_ctx); - /* - * If the context we're installing events in is not the - * active task_ctx, flip them. - */ - if (ctx->task && task_ctx != ctx) { - if (task_ctx) - raw_spin_unlock(&task_ctx->lock); + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx->task) { raw_spin_lock(&ctx->lock); + /* + * If we hit the 'wrong' task, we've since scheduled and + * everything should be sorted, nothing to do! + */ task_ctx = ctx; - } + if (ctx->task != current) + goto unlock; - if (task_ctx) { - cpuctx->task_ctx = task_ctx; - task = task_ctx->task; + /* + * If task_ctx is set, it had better be to us. + */ + WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx); + } else if (task_ctx) { + raw_spin_lock(&task_ctx->lock); } - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - - update_context_time(ctx); - /* - * update cgrp time only if current cgrp - * matches event->cgrp. Must be done before - * calling add_event_to_ctx() - */ - update_cgrp_time_from_event(event); - - add_event_to_ctx(event, ctx); - - /* - * Schedule everything back in - */ - perf_event_sched_in(cpuctx, task_ctx, task); - - perf_pmu_enable(cpuctx->ctx.pmu); + ctx_resched(cpuctx, task_ctx); +unlock: perf_ctx_unlock(cpuctx, task_ctx); return 0; @@ -2133,27 +2133,54 @@ static int __perf_install_in_context(void *info) /* * Attach a performance event to a context - * - * First we add the event to the list with the hardware enable bit - * in event->hw_config cleared. - * - * If the event is attached to a task which is on a CPU we use a smp - * call to enable it in the task context. The task might have been - * scheduled away, but we check this in the smp call again. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { + struct task_struct *task = NULL; + lockdep_assert_held(&ctx->mutex); event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; - event_function_call(event, __perf_install_in_context, - ___perf_install_in_context, event); + /* + * Installing events is tricky because we cannot rely on ctx->is_active + * to be set in case this is the nr_events 0 -> 1 transition. + * + * So what we do is we add the event to the list here, which will allow + * a future context switch to DTRT and then send a racy IPI. If the IPI + * fails to hit the right task, this means a context switch must have + * happened and that will have taken care of business. + */ + raw_spin_lock_irq(&ctx->lock); + task = ctx->task; + /* + * Worse, we cannot even rely on the ctx actually existing anymore. If + * between find_get_context() and perf_install_in_context() the task + * went through perf_event_exit_task() its dead and we should not be + * adding new events. + */ + if (task == TASK_TOMBSTONE) { + raw_spin_unlock_irq(&ctx->lock); + return; + } + update_context_time(ctx); + /* + * Update cgrp time only if current cgrp matches event->cgrp. + * Must be done before calling add_event_to_ctx(). + */ + update_cgrp_time_from_event(event); + add_event_to_ctx(event, ctx); + raw_spin_unlock_irq(&ctx->lock); + + if (task) + task_function_call(task, __perf_install_in_context, ctx); + else + cpu_function_call(cpu, __perf_install_in_context, ctx); } /* @@ -2180,43 +2207,30 @@ static void __perf_event_mark_enabled(struct perf_event *event) /* * Cross CPU call to enable a performance event */ -static int __perf_event_enable(void *info) +static void __perf_event_enable(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; struct perf_event *leader = event->group_leader; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - int err; + struct perf_event_context *task_ctx; - /* - * There's a time window between 'ctx->is_active' check - * in perf_event_enable function and this place having: - * - IRQs on - * - ctx->lock unlocked - * - * where the task could be killed and 'ctx' deactivated - * by perf_event_exit_task. - */ - if (!ctx->is_active) - return -EINVAL; + if (event->state >= PERF_EVENT_STATE_INACTIVE || + event->state <= PERF_EVENT_STATE_ERROR) + return; - raw_spin_lock(&ctx->lock); update_context_time(ctx); - - if (event->state >= PERF_EVENT_STATE_INACTIVE) - goto unlock; - - /* - * set current task's cgroup time reference point - */ - perf_cgroup_set_timestamp(current, ctx); - __perf_event_mark_enabled(event); + if (!ctx->is_active) + return; + if (!event_filter_match(event)) { - if (is_cgroup_event(event)) + if (is_cgroup_event(event)) { + perf_cgroup_set_timestamp(current, ctx); // XXX ? perf_cgroup_defer_enabled(event); - goto unlock; + } + return; } /* @@ -2224,41 +2238,13 @@ static int __perf_event_enable(void *info) * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) - goto unlock; - - if (!group_can_go_on(event, cpuctx, 1)) { - err = -EEXIST; - } else { - if (event == leader) - err = group_sched_in(event, cpuctx, ctx); - else - err = event_sched_in(event, cpuctx, ctx); - } - - if (err) { - /* - * If this event can't go on and it's part of a - * group, then the whole group has to come off. - */ - if (leader != event) { - group_sched_out(leader, cpuctx, ctx); - perf_mux_hrtimer_restart(cpuctx); - } - if (leader->attr.pinned) { - update_group_times(leader); - leader->state = PERF_EVENT_STATE_ERROR; - } - } + return; -unlock: - raw_spin_unlock(&ctx->lock); + task_ctx = cpuctx->task_ctx; + if (ctx->task) + WARN_ON_ONCE(task_ctx != ctx); - return 0; -} - -void ___perf_event_enable(void *info) -{ - __perf_event_mark_enabled((struct perf_event *)info); + ctx_resched(cpuctx, task_ctx); } /* @@ -2275,7 +2261,8 @@ static void _perf_event_enable(struct perf_event *event) struct perf_event_context *ctx = event->ctx; raw_spin_lock_irq(&ctx->lock); - if (event->state >= PERF_EVENT_STATE_INACTIVE) { + if (event->state >= PERF_EVENT_STATE_INACTIVE || + event->state < PERF_EVENT_STATE_ERROR) { raw_spin_unlock_irq(&ctx->lock); return; } @@ -2291,8 +2278,7 @@ static void _perf_event_enable(struct perf_event *event) event->state = PERF_EVENT_STATE_OFF; raw_spin_unlock_irq(&ctx->lock); - event_function_call(event, __perf_event_enable, - ___perf_event_enable, event); + event_function_call(event, __perf_event_enable, NULL); } /* @@ -2342,12 +2328,27 @@ static void ctx_sched_out(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type) { - struct perf_event *event; int is_active = ctx->is_active; + struct perf_event *event; - ctx->is_active &= ~event_type; - if (likely(!ctx->nr_events)) + lockdep_assert_held(&ctx->lock); + + if (likely(!ctx->nr_events)) { + /* + * See __perf_remove_from_context(). + */ + WARN_ON_ONCE(ctx->is_active); + if (ctx->task) + WARN_ON_ONCE(cpuctx->task_ctx); return; + } + + ctx->is_active &= ~event_type; + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; + } update_context_time(ctx); update_cgrp_time_from_cpuctx(cpuctx); @@ -2518,17 +2519,21 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, raw_spin_lock(&ctx->lock); raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); if (context_equiv(ctx, next_ctx)) { - /* - * XXX do we need a memory barrier of sorts - * wrt to rcu_dereference() of perf_event_ctxp - */ - task->perf_event_ctxp[ctxn] = next_ctx; - next->perf_event_ctxp[ctxn] = ctx; - ctx->task = next; - next_ctx->task = task; + WRITE_ONCE(ctx->task, next); + WRITE_ONCE(next_ctx->task, task); swap(ctx->task_ctx_data, next_ctx->task_ctx_data); + /* + * RCU_INIT_POINTER here is safe because we've not + * modified the ctx and the above modification of + * ctx->task and ctx->task_ctx_data are immaterial + * since those values are always verified under + * ctx->lock which we're now holding. + */ + RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], next_ctx); + RCU_INIT_POINTER(next->perf_event_ctxp[ctxn], ctx); + do_switch = 0; perf_event_sync_stat(ctx, next_ctx); @@ -2541,8 +2546,7 @@ unlock: if (do_switch) { raw_spin_lock(&ctx->lock); - ctx_sched_out(ctx, cpuctx, EVENT_ALL); - cpuctx->task_ctx = NULL; + task_ctx_sched_out(cpuctx, ctx); raw_spin_unlock(&ctx->lock); } } @@ -2637,10 +2641,9 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task, next); } -static void task_ctx_sched_out(struct perf_event_context *ctx) +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - if (!cpuctx->task_ctx) return; @@ -2648,7 +2651,6 @@ static void task_ctx_sched_out(struct perf_event_context *ctx) return; ctx_sched_out(ctx, cpuctx, EVENT_ALL); - cpuctx->task_ctx = NULL; } /* @@ -2725,13 +2727,22 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type, struct task_struct *task) { - u64 now; int is_active = ctx->is_active; + u64 now; + + lockdep_assert_held(&ctx->lock); - ctx->is_active |= event_type; if (likely(!ctx->nr_events)) return; + ctx->is_active |= event_type; + if (ctx->task) { + if (!is_active) + cpuctx->task_ctx = ctx; + else + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + } + now = perf_clock(); ctx->timestamp = now; perf_cgroup_set_timestamp(task, ctx); @@ -2773,12 +2784,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, * cpu flexible, task flexible. */ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - - if (ctx->nr_events) - cpuctx->task_ctx = ctx; - - perf_event_sched_in(cpuctx, cpuctx->task_ctx, task); - + perf_event_sched_in(cpuctx, ctx, task); perf_pmu_enable(ctx->pmu); perf_ctx_unlock(cpuctx, ctx); } @@ -2800,6 +2806,16 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; + /* + * If cgroup events exist on this CPU, then we need to check if we have + * to switch in PMU state; cgroup event are system-wide mode only. + * + * Since cgroup events are CPU events, we must schedule these in before + * we schedule in the task events. + */ + if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) + perf_cgroup_sched_in(prev, task); + for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -2807,13 +2823,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, perf_event_context_sched_in(ctx, task); } - /* - * if cgroup events exist on this CPU, then we need - * to check if we have to switch in PMU state. - * cgroup event are system-wide mode only - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); if (atomic_read(&nr_switch_events)) perf_event_switch(task, prev, true); @@ -3099,46 +3108,30 @@ static int event_enable_on_exec(struct perf_event *event, static void perf_event_enable_on_exec(int ctxn) { struct perf_event_context *ctx, *clone_ctx = NULL; + struct perf_cpu_context *cpuctx; struct perf_event *event; unsigned long flags; int enabled = 0; - int ret; local_irq_save(flags); ctx = current->perf_event_ctxp[ctxn]; if (!ctx || !ctx->nr_events) goto out; - /* - * We must ctxsw out cgroup events to avoid conflict - * when invoking perf_task_event_sched_in() later on - * in this function. Otherwise we end up trying to - * ctxswin cgroup events which are already scheduled - * in. - */ - perf_cgroup_sched_out(current, NULL); - - raw_spin_lock(&ctx->lock); - task_ctx_sched_out(ctx); - - list_for_each_entry(event, &ctx->event_list, event_entry) { - ret = event_enable_on_exec(event, ctx); - if (ret) - enabled = 1; - } + cpuctx = __get_cpu_context(ctx); + perf_ctx_lock(cpuctx, ctx); + list_for_each_entry(event, &ctx->event_list, event_entry) + enabled |= event_enable_on_exec(event, ctx); /* - * Unclone this context if we enabled any event. + * Unclone and reschedule this context if we enabled any event. */ - if (enabled) + if (enabled) { clone_ctx = unclone_ctx(ctx); + ctx_resched(cpuctx, ctx); + } + perf_ctx_unlock(cpuctx, ctx); - raw_spin_unlock(&ctx->lock); - - /* - * Also calls ctxswin for cgroup events, if any: - */ - perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); @@ -3334,7 +3327,6 @@ static void __perf_event_init_context(struct perf_event_context *ctx) INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); atomic_set(&ctx->refcount, 1); - INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work); } static struct perf_event_context * @@ -3521,11 +3513,13 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) static void unaccount_event(struct perf_event *event) { + bool dec = false; + if (event->parent) return; if (event->attach_state & PERF_ATTACH_TASK) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.comm) @@ -3535,12 +3529,15 @@ static void unaccount_event(struct perf_event *event) if (event->attr.freq) atomic_dec(&nr_freq_events); if (event->attr.context_switch) { - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; atomic_dec(&nr_switch_events); } if (is_cgroup_event(event)) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; if (has_branch_stack(event)) + dec = true; + + if (dec) static_key_slow_dec_deferred(&perf_sched_events); unaccount_event_cpu(event, event->cpu); @@ -3556,7 +3553,7 @@ static void unaccount_event(struct perf_event *event) * 3) two matching events on the same context. * * The former two cases are handled in the allocation path (perf_event_alloc(), - * __free_event()), the latter -- before the first perf_install_in_context(). + * _free_event()), the latter -- before the first perf_install_in_context(). */ static int exclusive_event_init(struct perf_event *event) { @@ -3631,29 +3628,6 @@ static bool exclusive_event_installable(struct perf_event *event, return true; } -static void __free_event(struct perf_event *event) -{ - if (!event->parent) { - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - put_callchain_buffers(); - } - - perf_event_free_bpf_prog(event); - - if (event->destroy) - event->destroy(event); - - if (event->ctx) - put_ctx(event->ctx); - - if (event->pmu) { - exclusive_event_destroy(event); - module_put(event->pmu->module); - } - - call_rcu(&event->rcu_head, free_event_rcu); -} - static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending); @@ -3675,7 +3649,25 @@ static void _free_event(struct perf_event *event) if (is_cgroup_event(event)) perf_detach_cgroup(event); - __free_event(event); + if (!event->parent) { + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + put_callchain_buffers(); + } + + perf_event_free_bpf_prog(event); + + if (event->destroy) + event->destroy(event); + + if (event->ctx) + put_ctx(event->ctx); + + if (event->pmu) { + exclusive_event_destroy(event); + module_put(event->pmu->module); + } + + call_rcu(&event->rcu_head, free_event_rcu); } /* @@ -3702,14 +3694,13 @@ static void perf_remove_from_owner(struct perf_event *event) struct task_struct *owner; rcu_read_lock(); - owner = ACCESS_ONCE(event->owner); /* - * Matches the smp_wmb() in perf_event_exit_task(). If we observe - * !owner it means the list deletion is complete and we can indeed - * free this event, otherwise we need to serialize on + * Matches the smp_store_release() in perf_event_exit_task(). If we + * observe !owner it means the list deletion is complete and we can + * indeed free this event, otherwise we need to serialize on * owner->perf_event_mutex. */ - smp_read_barrier_depends(); + owner = lockless_dereference(event->owner); if (owner) { /* * Since delayed_put_task_struct() also drops the last @@ -3737,8 +3728,10 @@ static void perf_remove_from_owner(struct perf_event *event) * ensured they're done, and we can proceed with freeing the * event. */ - if (event->owner) + if (event->owner) { list_del_init(&event->owner_entry); + smp_store_release(&event->owner, NULL); + } mutex_unlock(&owner->perf_event_mutex); put_task_struct(owner); } @@ -3746,36 +3739,98 @@ static void perf_remove_from_owner(struct perf_event *event) static void put_event(struct perf_event *event) { - struct perf_event_context *ctx; - if (!atomic_long_dec_and_test(&event->refcount)) return; + _free_event(event); +} + +/* + * Kill an event dead; while event:refcount will preserve the event + * object, it will not preserve its functionality. Once the last 'user' + * gives up the object, we'll destroy the thing. + */ +int perf_event_release_kernel(struct perf_event *event) +{ + struct perf_event_context *ctx; + struct perf_event *child, *tmp; + if (!is_kernel_event(event)) perf_remove_from_owner(event); + ctx = perf_event_ctx_lock(event); + WARN_ON_ONCE(ctx->parent_ctx); + perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE); + perf_event_ctx_unlock(event, ctx); + /* - * There are two ways this annotation is useful: + * At this point we must have event->state == PERF_EVENT_STATE_EXIT, + * either from the above perf_remove_from_context() or through + * perf_event_exit_event(). * - * 1) there is a lock recursion from perf_event_exit_task - * see the comment there. + * Therefore, anybody acquiring event->child_mutex after the below + * loop _must_ also see this, most importantly inherit_event() which + * will avoid placing more children on the list. * - * 2) there is a lock-inversion with mmap_sem through - * perf_read_group(), which takes faults while - * holding ctx->mutex, however this is called after - * the last filedesc died, so there is no possibility - * to trigger the AB-BA case. + * Thus this guarantees that we will in fact observe and kill _ALL_ + * child events. */ - ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); - WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, true); - perf_event_ctx_unlock(event, ctx); + WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT); - _free_event(event); -} +again: + mutex_lock(&event->child_mutex); + list_for_each_entry(child, &event->child_list, child_list) { -int perf_event_release_kernel(struct perf_event *event) -{ + /* + * Cannot change, child events are not migrated, see the + * comment with perf_event_ctx_lock_nested(). + */ + ctx = lockless_dereference(child->ctx); + /* + * Since child_mutex nests inside ctx::mutex, we must jump + * through hoops. We start by grabbing a reference on the ctx. + * + * Since the event cannot get freed while we hold the + * child_mutex, the context must also exist and have a !0 + * reference count. + */ + get_ctx(ctx); + + /* + * Now that we have a ctx ref, we can drop child_mutex, and + * acquire ctx::mutex without fear of it going away. Then we + * can re-acquire child_mutex. + */ + mutex_unlock(&event->child_mutex); + mutex_lock(&ctx->mutex); + mutex_lock(&event->child_mutex); + + /* + * Now that we hold ctx::mutex and child_mutex, revalidate our + * state, if child is still the first entry, it didn't get freed + * and we can continue doing so. + */ + tmp = list_first_entry_or_null(&event->child_list, + struct perf_event, child_list); + if (tmp == child) { + perf_remove_from_context(child, DETACH_GROUP); + list_del(&child->child_list); + free_event(child); + /* + * This matches the refcount bump in inherit_event(); + * this can't be the last reference. + */ + put_event(event); + } + + mutex_unlock(&event->child_mutex); + mutex_unlock(&ctx->mutex); + put_ctx(ctx); + goto again; + } + mutex_unlock(&event->child_mutex); + + /* Must be the last reference */ put_event(event); return 0; } @@ -3786,46 +3841,10 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel); */ static int perf_release(struct inode *inode, struct file *file) { - put_event(file->private_data); + perf_event_release_kernel(file->private_data); return 0; } -/* - * Remove all orphanes events from the context. - */ -static void orphans_remove_work(struct work_struct *work) -{ - struct perf_event_context *ctx; - struct perf_event *event, *tmp; - - ctx = container_of(work, struct perf_event_context, - orphans_remove.work); - - mutex_lock(&ctx->mutex); - list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) { - struct perf_event *parent_event = event->parent; - - if (!is_orphaned_child(event)) - continue; - - perf_remove_from_context(event, true); - - mutex_lock(&parent_event->child_mutex); - list_del_init(&event->child_list); - mutex_unlock(&parent_event->child_mutex); - - free_event(event); - put_event(parent_event); - } - - raw_spin_lock_irq(&ctx->lock); - ctx->orphans_remove_sched = false; - raw_spin_unlock_irq(&ctx->lock); - mutex_unlock(&ctx->mutex); - - put_ctx(ctx); -} - u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; @@ -4054,7 +4073,7 @@ static void _perf_event_reset(struct perf_event *event) /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block - * in sync_child_event if it goes to exit, thus satisfying the + * in perf_event_exit_event() if it goes to exit, thus satisfying the * task existence requirements of perf_event_enable/disable. */ static void perf_event_for_each_child(struct perf_event *event, @@ -4086,36 +4105,14 @@ static void perf_event_for_each(struct perf_event *event, perf_event_for_each_child(sibling, func); } -struct period_event { - struct perf_event *event; - u64 value; -}; - -static void ___perf_event_period(void *info) -{ - struct period_event *pe = info; - struct perf_event *event = pe->event; - u64 value = pe->value; - - if (event->attr.freq) { - event->attr.sample_freq = value; - } else { - event->attr.sample_period = value; - event->hw.sample_period = value; - } - - local64_set(&event->hw.period_left, 0); -} - -static int __perf_event_period(void *info) +static void __perf_event_period(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct period_event *pe = info; - struct perf_event *event = pe->event; - struct perf_event_context *ctx = event->ctx; - u64 value = pe->value; + u64 value = *((u64 *)info); bool active; - raw_spin_lock(&ctx->lock); if (event->attr.freq) { event->attr.sample_freq = value; } else { @@ -4135,14 +4132,10 @@ static int __perf_event_period(void *info) event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(ctx->pmu); } - raw_spin_unlock(&ctx->lock); - - return 0; } static int perf_event_period(struct perf_event *event, u64 __user *arg) { - struct period_event pe = { .event = event, }; u64 value; if (!is_sampling_event(event)) @@ -4157,10 +4150,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; - pe.value = value; - - event_function_call(event, __perf_event_period, - ___perf_event_period, &pe); + event_function_call(event, __perf_event_period, &value); return 0; } @@ -4932,7 +4922,7 @@ static void perf_pending_event(struct irq_work *entry) if (event->pending_disable) { event->pending_disable = 0; - __perf_event_disable(event); + perf_event_disable_local(event); } if (event->pending_wakeup) { @@ -7753,11 +7743,13 @@ static void account_event_cpu(struct perf_event *event, int cpu) static void account_event(struct perf_event *event) { + bool inc = false; + if (event->parent) return; if (event->attach_state & PERF_ATTACH_TASK) - static_key_slow_inc(&perf_sched_events.key); + inc = true; if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); if (event->attr.comm) @@ -7770,11 +7762,14 @@ static void account_event(struct perf_event *event) } if (event->attr.context_switch) { atomic_inc(&nr_switch_events); - static_key_slow_inc(&perf_sched_events.key); + inc = true; } if (has_branch_stack(event)) - static_key_slow_inc(&perf_sched_events.key); + inc = true; if (is_cgroup_event(event)) + inc = true; + + if (inc) static_key_slow_inc(&perf_sched_events.key); account_event_cpu(event, event->cpu); @@ -8422,11 +8417,11 @@ SYSCALL_DEFINE5(perf_event_open, * See perf_event_ctx_lock() for comments on the details * of swizzling perf_event::ctx. */ - perf_remove_from_context(group_leader, false); + perf_remove_from_context(group_leader, 0); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_remove_from_context(sibling, false); + perf_remove_from_context(sibling, 0); put_ctx(gctx); } @@ -8479,6 +8474,8 @@ SYSCALL_DEFINE5(perf_event_open, perf_event__header_size(event); perf_event__id_header_size(event); + event->owner = current; + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); @@ -8488,8 +8485,6 @@ SYSCALL_DEFINE5(perf_event_open, put_online_cpus(); - event->owner = current; - mutex_lock(¤t->perf_event_mutex); list_add_tail(&event->owner_entry, ¤t->perf_event_list); mutex_unlock(¤t->perf_event_mutex); @@ -8556,7 +8551,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, } /* Mark owner so we could distinguish it from user events. */ - event->owner = EVENT_OWNER_KERNEL; + event->owner = TASK_TOMBSTONE; account_event(event); @@ -8606,7 +8601,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex); list_for_each_entry_safe(event, tmp, &src_ctx->event_list, event_entry) { - perf_remove_from_context(event, false); + perf_remove_from_context(event, 0); unaccount_event_cpu(event, src_cpu); put_ctx(src_ctx); list_add(&event->migrate_entry, &events); @@ -8673,33 +8668,15 @@ static void sync_child_event(struct perf_event *child_event, &parent_event->child_total_time_enabled); atomic64_add(child_event->total_time_running, &parent_event->child_total_time_running); - - /* - * Remove this event from the parent's list - */ - WARN_ON_ONCE(parent_event->ctx->parent_ctx); - mutex_lock(&parent_event->child_mutex); - list_del_init(&child_event->child_list); - mutex_unlock(&parent_event->child_mutex); - - /* - * Make sure user/parent get notified, that we just - * lost one event. - */ - perf_event_wakeup(parent_event); - - /* - * Release the parent event, if this was the last - * reference to it. - */ - put_event(parent_event); } static void -__perf_event_exit_task(struct perf_event *child_event, - struct perf_event_context *child_ctx, - struct task_struct *child) +perf_event_exit_event(struct perf_event *child_event, + struct perf_event_context *child_ctx, + struct task_struct *child) { + struct perf_event *parent_event = child_event->parent; + /* * Do not destroy the 'original' grouping; because of the context * switch optimization the original events could've ended up in a @@ -8712,57 +8689,86 @@ __perf_event_exit_task(struct perf_event *child_event, * Do destroy all inherited groups, we don't care about those * and being thorough is better. */ - perf_remove_from_context(child_event, !!child_event->parent); + raw_spin_lock_irq(&child_ctx->lock); + WARN_ON_ONCE(child_ctx->is_active); + + if (parent_event) + perf_group_detach(child_event); + list_del_event(child_event, child_ctx); + child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */ + raw_spin_unlock_irq(&child_ctx->lock); /* - * It can happen that the parent exits first, and has events - * that are still around due to the child reference. These - * events need to be zapped. + * Parent events are governed by their filedesc, retain them. */ - if (child_event->parent) { - sync_child_event(child_event, child); - free_event(child_event); - } else { - child_event->state = PERF_EVENT_STATE_EXIT; + if (!parent_event) { perf_event_wakeup(child_event); + return; } + /* + * Child events can be cleaned up. + */ + + sync_child_event(child_event, child); + + /* + * Remove this event from the parent's list + */ + WARN_ON_ONCE(parent_event->ctx->parent_ctx); + mutex_lock(&parent_event->child_mutex); + list_del_init(&child_event->child_list); + mutex_unlock(&parent_event->child_mutex); + + /* + * Kick perf_poll() for is_event_hup(). + */ + perf_event_wakeup(parent_event); + free_event(child_event); + put_event(parent_event); } static void perf_event_exit_task_context(struct task_struct *child, int ctxn) { - struct perf_event *child_event, *next; struct perf_event_context *child_ctx, *clone_ctx = NULL; - unsigned long flags; + struct perf_event *child_event, *next; + + WARN_ON_ONCE(child != current); - if (likely(!child->perf_event_ctxp[ctxn])) + child_ctx = perf_pin_task_context(child, ctxn); + if (!child_ctx) return; - local_irq_save(flags); /* - * We can't reschedule here because interrupts are disabled, - * and either child is current or it is a task that can't be - * scheduled, so we are now safe from rescheduling changing - * our context. + * In order to reduce the amount of tricky in ctx tear-down, we hold + * ctx::mutex over the entire thing. This serializes against almost + * everything that wants to access the ctx. + * + * The exception is sys_perf_event_open() / + * perf_event_create_kernel_count() which does find_get_context() + * without ctx::mutex (it cannot because of the move_group double mutex + * lock thing). See the comments in perf_install_in_context(). */ - child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); + mutex_lock(&child_ctx->mutex); /* - * Take the context lock here so that if find_get_context is - * reading child->perf_event_ctxp, we wait until it has - * incremented the context's refcount before we do put_ctx below. + * In a single ctx::lock section, de-schedule the events and detach the + * context from the task such that we cannot ever get it scheduled back + * in. */ - raw_spin_lock(&child_ctx->lock); - task_ctx_sched_out(child_ctx); - child->perf_event_ctxp[ctxn] = NULL; + raw_spin_lock_irq(&child_ctx->lock); + task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx); /* - * If this context is a clone; unclone it so it can't get - * swapped to another process while we're removing all - * the events from it. + * Now that the context is inactive, destroy the task <-> ctx relation + * and mark the context dead. */ + RCU_INIT_POINTER(child->perf_event_ctxp[ctxn], NULL); + put_ctx(child_ctx); /* cannot be last */ + WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE); + put_task_struct(current); /* cannot be last */ + clone_ctx = unclone_ctx(child_ctx); - update_context_time(child_ctx); - raw_spin_unlock_irqrestore(&child_ctx->lock, flags); + raw_spin_unlock_irq(&child_ctx->lock); if (clone_ctx) put_ctx(clone_ctx); @@ -8774,20 +8780,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) */ perf_event_task(child, child_ctx, 0); - /* - * We can recurse on the same lock type through: - * - * __perf_event_exit_task() - * sync_child_event() - * put_event() - * mutex_lock(&ctx->mutex) - * - * But since its the parent context it won't be the same instance. - */ - mutex_lock(&child_ctx->mutex); - list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) - __perf_event_exit_task(child_event, child_ctx, child); + perf_event_exit_event(child_event, child_ctx, child); mutex_unlock(&child_ctx->mutex); @@ -8812,8 +8806,7 @@ void perf_event_exit_task(struct task_struct *child) * the owner, closes a race against perf_release() where * we need to serialize on the owner->perf_event_mutex. */ - smp_wmb(); - event->owner = NULL; + smp_store_release(&event->owner, NULL); } mutex_unlock(&child->perf_event_mutex); @@ -8896,21 +8889,20 @@ void perf_event_delayed_put(struct task_struct *task) WARN_ON_ONCE(task->perf_event_ctxp[ctxn]); } -struct perf_event *perf_event_get(unsigned int fd) +struct file *perf_event_get(unsigned int fd) { - int err; - struct fd f; - struct perf_event *event; + struct file *file; - err = perf_fget_light(fd, &f); - if (err) - return ERR_PTR(err); + file = fget_raw(fd); + if (!file) + return ERR_PTR(-EBADF); - event = f.file->private_data; - atomic_long_inc(&event->refcount); - fdput(f); + if (file->f_op != &perf_fops) { + fput(file); + return ERR_PTR(-EBADF); + } - return event; + return file; } const struct perf_event_attr *perf_event_attrs(struct perf_event *event) @@ -8953,8 +8945,16 @@ inherit_event(struct perf_event *parent_event, if (IS_ERR(child_event)) return child_event; + /* + * is_orphaned_event() and list_add_tail(&parent_event->child_list) + * must be under the same lock in order to serialize against + * perf_event_release_kernel(), such that either we must observe + * is_orphaned_event() or they will observe us on the child_list. + */ + mutex_lock(&parent_event->child_mutex); if (is_orphaned_event(parent_event) || !atomic_long_inc_not_zero(&parent_event->refcount)) { + mutex_unlock(&parent_event->child_mutex); free_event(child_event); return NULL; } @@ -9002,8 +9002,6 @@ inherit_event(struct perf_event *parent_event, /* * Link this into the parent event's child list */ - WARN_ON_ONCE(parent_event->ctx->parent_ctx); - mutex_lock(&parent_event->child_mutex); list_add_tail(&child_event->child_list, &parent_event->child_list); mutex_unlock(&parent_event->child_mutex); @@ -9221,13 +9219,14 @@ static void perf_event_init_cpu(int cpu) #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE static void __perf_event_exit_context(void *__info) { - struct remove_event re = { .detach_group = true }; struct perf_event_context *ctx = __info; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event *event; - rcu_read_lock(); - list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) - __perf_remove_from_context(&re); - rcu_read_unlock(); + raw_spin_lock(&ctx->lock); + list_for_each_entry(event, &ctx->event_list, event_entry) + __perf_remove_from_context(event, cpuctx, ctx, (void *)DETACH_GROUP); + raw_spin_unlock(&ctx->lock); } static void perf_event_exit_cpu_context(int cpu) diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 92ce5f4ccc26..3f8cb1e14588 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -444,7 +444,7 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att * current task. */ if (irqs_disabled() && bp->ctx && bp->ctx->task == current) - __perf_event_disable(bp); + perf_event_disable_local(bp); else perf_event_disable(bp); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index adfdc0536117..1faad2cfdb9e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -459,6 +459,25 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx) __free_page(page); } +static void __rb_free_aux(struct ring_buffer *rb) +{ + int pg; + + if (rb->aux_priv) { + rb->free_aux(rb->aux_priv); + rb->free_aux = NULL; + rb->aux_priv = NULL; + } + + if (rb->aux_nr_pages) { + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); + + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; + } +} + int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, pgoff_t pgoff, int nr_pages, long watermark, int flags) { @@ -547,30 +566,11 @@ out: if (!ret) rb->aux_pgoff = pgoff; else - rb_free_aux(rb); + __rb_free_aux(rb); return ret; } -static void __rb_free_aux(struct ring_buffer *rb) -{ - int pg; - - if (rb->aux_priv) { - rb->free_aux(rb->aux_priv); - rb->free_aux = NULL; - rb->aux_priv = NULL; - } - - if (rb->aux_nr_pages) { - for (pg = 0; pg < rb->aux_nr_pages; pg++) - rb_free_aux_page(rb, pg); - - kfree(rb->aux_pages); - rb->aux_nr_pages = 0; - } -} - void rb_free_aux(struct ring_buffer *rb) { if (atomic_dec_and_test(&rb->aux_refcount)) diff --git a/kernel/futex.c b/kernel/futex.c index 0773f2b23b10..5d6ce6413ef1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1191,7 +1191,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, if (pi_state->owner != current) return -EINVAL; - raw_spin_lock(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); /* @@ -1217,22 +1217,22 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, else if (curval != uval) ret = -EINVAL; if (ret) { - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; } - raw_spin_lock_irq(&pi_state->owner->pi_lock); + raw_spin_lock(&pi_state->owner->pi_lock); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + raw_spin_unlock(&pi_state->owner->pi_lock); - raw_spin_lock_irq(&new_owner->pi_lock); + raw_spin_lock(&new_owner->pi_lock); WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &new_owner->pi_state_list); pi_state->owner = new_owner; - raw_spin_unlock_irq(&new_owner->pi_lock); + raw_spin_unlock(&new_owner->pi_lock); - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); @@ -2127,11 +2127,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * we returned due to timeout or signal without taking the * rt_mutex. Too late. */ - raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); + raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); owner = rt_mutex_owner(&q->pi_state->pi_mutex); if (!owner) owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); ret = fixup_pi_state_owner(uaddr, q, owner); goto out; } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a302cf9a2126..57bff7857e87 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -138,7 +138,8 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) unsigned int flags = 0, irq = desc->irq_data.irq; struct irqaction *action = desc->action; - do { + /* action might have become NULL since we dropped the lock */ + while (action) { irqreturn_t res; trace_irq_handler_entry(irq, action); @@ -173,7 +174,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval |= res; action = action->next; - } while (action); + } add_interrupt_randomness(irq, flags); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 6e655f7acd3b..3e56d2f03e24 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -575,10 +575,15 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) unsigned int type = IRQ_TYPE_NONE; int virq; - if (fwspec->fwnode) - domain = irq_find_matching_fwnode(fwspec->fwnode, DOMAIN_BUS_ANY); - else + if (fwspec->fwnode) { + domain = irq_find_matching_fwnode(fwspec->fwnode, + DOMAIN_BUS_WIRED); + if (!domain) + domain = irq_find_matching_fwnode(fwspec->fwnode, + DOMAIN_BUS_ANY); + } else { domain = irq_default_domain; + } if (!domain) { pr_warn("no irq domain found for %s !\n", diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 8251e75dd9c0..3e746607abe5 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -99,13 +99,14 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) * 2) Drop lock->wait_lock * 3) Try to unlock the lock with cmpxchg */ -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + unsigned long flags) __releases(lock->wait_lock) { struct task_struct *owner = rt_mutex_owner(lock); clear_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* * If a new waiter comes in between the unlock and the cmpxchg * we have two situations: @@ -147,11 +148,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) /* * Simple slow path only version: lock->owner is protected by lock->wait_lock. */ -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + unsigned long flags) __releases(lock->wait_lock) { lock->owner = NULL; - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return true; } #endif @@ -433,7 +435,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, int ret = 0, depth = 0; struct rt_mutex *lock; bool detect_deadlock; - unsigned long flags; bool requeue = true; detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); @@ -476,7 +477,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * [1] Task cannot go away as we did a get_task() before ! */ - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock_irq(&task->pi_lock); /* * [2] Get the waiter on which @task is blocked on. @@ -560,7 +561,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * operations. */ if (!raw_spin_trylock(&lock->wait_lock)) { - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock_irq(&task->pi_lock); cpu_relax(); goto retry; } @@ -591,7 +592,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * No requeue[7] here. Just release @task [8] */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); put_task_struct(task); /* @@ -599,14 +600,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * If there is no owner of the lock, end of chain. */ if (!rt_mutex_owner(lock)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 0; } /* [10] Grab the next task, i.e. owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); /* * No requeue [11] here. We just do deadlock detection. @@ -621,8 +622,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* [13] Drop locks */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock_irq(&lock->wait_lock); /* If owner is not blocked, end of chain. */ if (!next_lock) @@ -643,7 +644,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, rt_mutex_enqueue(lock, waiter); /* [8] Release the task */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); put_task_struct(task); /* @@ -661,14 +662,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, */ if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) wake_up_process(rt_mutex_top_waiter(lock)->task); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 0; } /* [10] Grab the next task, i.e. the owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); /* [11] requeue the pi waiters if necessary */ if (waiter == rt_mutex_top_waiter(lock)) { @@ -722,8 +723,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* [13] Drop the locks */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock_irq(&lock->wait_lock); /* * Make the actual exit decisions [12], based on the stored @@ -746,7 +747,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto again; out_unlock_pi: - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock_irq(&task->pi_lock); out_put_task: put_task_struct(task); @@ -756,7 +757,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * Try to take an rt-mutex * - * Must be called with lock->wait_lock held. + * Must be called with lock->wait_lock held and interrupts disabled * * @lock: The lock to be acquired. * @task: The task which wants to acquire the lock @@ -766,8 +767,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, struct rt_mutex_waiter *waiter) { - unsigned long flags; - /* * Before testing whether we can acquire @lock, we set the * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all @@ -852,7 +851,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * case, but conditionals are more expensive than a redundant * store. */ - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); task->pi_blocked_on = NULL; /* * Finish the lock acquisition. @task is the new owner. If @@ -861,7 +860,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (rt_mutex_has_waiters(lock)) rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); takeit: /* We got the lock. */ @@ -883,7 +882,7 @@ takeit: * * Prepare waiter and propagate pi chain * - * This must be called with lock->wait_lock held. + * This must be called with lock->wait_lock held and interrupts disabled */ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -894,7 +893,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *top_waiter = waiter; struct rt_mutex *next_lock; int chain_walk = 0, res; - unsigned long flags; /* * Early deadlock detection. We really don't want the task to @@ -908,7 +906,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, if (owner == task) return -EDEADLK; - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); __rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; @@ -921,12 +919,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, task->pi_blocked_on = waiter; - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); if (!owner) return 0; - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock(&owner->pi_lock); if (waiter == rt_mutex_top_waiter(lock)) { rt_mutex_dequeue_pi(owner, top_waiter); rt_mutex_enqueue_pi(owner, waiter); @@ -941,7 +939,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, /* Store the lock on which owner is blocked or NULL */ next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + raw_spin_unlock(&owner->pi_lock); /* * Even if full deadlock detection is on, if the owner is not * blocked itself, we can avoid finding this out in the chain @@ -957,12 +955,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, */ get_task_struct(owner); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, next_lock, waiter, task); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); return res; } @@ -971,15 +969,14 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, * Remove the top waiter from the current tasks pi waiter tree and * queue it up. * - * Called with lock->wait_lock held. + * Called with lock->wait_lock held and interrupts disabled. */ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; - unsigned long flags; - raw_spin_lock_irqsave(¤t->pi_lock, flags); + raw_spin_lock(¤t->pi_lock); waiter = rt_mutex_top_waiter(lock); @@ -1001,7 +998,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, */ lock->owner = (void *) RT_MUTEX_HAS_WAITERS; - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + raw_spin_unlock(¤t->pi_lock); wake_q_add(wake_q, waiter->task); } @@ -1009,7 +1006,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, /* * Remove a waiter from a lock and give up * - * Must be called with lock->wait_lock held and + * Must be called with lock->wait_lock held and interrupts disabled. I must * have just failed to try_to_take_rt_mutex(). */ static void remove_waiter(struct rt_mutex *lock, @@ -1018,12 +1015,11 @@ static void remove_waiter(struct rt_mutex *lock, bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex *next_lock; - unsigned long flags; - raw_spin_lock_irqsave(¤t->pi_lock, flags); + raw_spin_lock(¤t->pi_lock); rt_mutex_dequeue(lock, waiter); current->pi_blocked_on = NULL; - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + raw_spin_unlock(¤t->pi_lock); /* * Only update priority if the waiter was the highest priority @@ -1032,7 +1028,7 @@ static void remove_waiter(struct rt_mutex *lock, if (!owner || !is_top_waiter) return; - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock(&owner->pi_lock); rt_mutex_dequeue_pi(owner, waiter); @@ -1044,7 +1040,7 @@ static void remove_waiter(struct rt_mutex *lock, /* Store the lock on which owner is blocked or NULL */ next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + raw_spin_unlock(&owner->pi_lock); /* * Don't walk the chain, if the owner task is not blocked @@ -1056,12 +1052,12 @@ static void remove_waiter(struct rt_mutex *lock, /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(owner); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, next_lock, NULL, current); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); } /* @@ -1097,11 +1093,11 @@ void rt_mutex_adjust_pi(struct task_struct *task) * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @state: the state the task should block in (TASK_INTERRUPTIBLE - * or TASK_UNINTERRUPTIBLE) + * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter * - * lock->wait_lock must be held by the caller. + * Must be called with lock->wait_lock held and interrupts disabled */ static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, @@ -1129,13 +1125,13 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, break; } - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); schedule(); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); set_current_state(state); } @@ -1172,17 +1168,26 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, enum rtmutex_chainwalk chwalk) { struct rt_mutex_waiter waiter; + unsigned long flags; int ret = 0; debug_rt_mutex_init_waiter(&waiter); RB_CLEAR_NODE(&waiter.pi_tree_entry); RB_CLEAR_NODE(&waiter.tree_entry); - raw_spin_lock(&lock->wait_lock); + /* + * Technically we could use raw_spin_[un]lock_irq() here, but this can + * be called in early boot if the cmpxchg() fast path is disabled + * (debug, no architecture support). In this case we will acquire the + * rtmutex with lock->wait_lock held. But we cannot unconditionally + * enable interrupts in that early boot case. So we need to use the + * irqsave/restore variants. + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); /* Try to acquire the lock again: */ if (try_to_take_rt_mutex(lock, current, NULL)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return 0; } @@ -1211,7 +1216,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* Remove pending timer: */ if (unlikely(timeout)) @@ -1227,6 +1232,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) { + unsigned long flags; int ret; /* @@ -1238,10 +1244,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) return 0; /* - * The mutex has currently no owner. Lock the wait lock and - * try to acquire the lock. + * The mutex has currently no owner. Lock the wait lock and try to + * acquire the lock. We use irqsave here to support early boot calls. */ - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); ret = try_to_take_rt_mutex(lock, current, NULL); @@ -1251,7 +1257,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return ret; } @@ -1263,7 +1269,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, struct wake_q_head *wake_q) { - raw_spin_lock(&lock->wait_lock); + unsigned long flags; + + /* irqsave required to support early boot calls */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); debug_rt_mutex_unlock(lock); @@ -1302,10 +1311,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ while (!rt_mutex_has_waiters(lock)) { /* Drops lock->wait_lock ! */ - if (unlock_rt_mutex_safe(lock) == true) + if (unlock_rt_mutex_safe(lock, flags) == true) return false; /* Relock the rtmutex and try again */ - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); } /* @@ -1316,7 +1325,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ mark_wakeup_next_waiter(wake_q, lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* check PI boosting */ return true; @@ -1596,10 +1605,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, { int ret; - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); if (try_to_take_rt_mutex(lock, task, NULL)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 1; } @@ -1620,7 +1629,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (unlikely(ret)) remove_waiter(lock, waiter); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); @@ -1668,7 +1677,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, { int ret; - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); set_current_state(TASK_INTERRUPTIBLE); @@ -1684,7 +1693,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return ret; } diff --git a/kernel/memremap.c b/kernel/memremap.c index e517a16cb426..70ee3775de24 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -150,7 +150,7 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); -pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +pfn_t phys_to_pfn_t(phys_addr_t addr, unsigned long flags) { return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); } @@ -183,7 +183,11 @@ EXPORT_SYMBOL(put_zone_device_page); static void pgmap_radix_release(struct resource *res) { - resource_size_t key; + resource_size_t key, align_start, align_size, align_end; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + align_end = align_start + align_size - 1; mutex_lock(&pgmap_lock); for (key = res->start; key <= res->end; key += SECTION_SIZE) @@ -226,12 +230,11 @@ static void devm_memremap_pages_release(struct device *dev, void *data) percpu_ref_put(pgmap->ref); } - pgmap_radix_release(res); - /* pages are dead and unused, undo the arch mapping */ align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); arch_remove_memory(align_start, align_size); + pgmap_radix_release(res); dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, "%s: failed to free all reserved pages\n", __func__); } @@ -267,7 +270,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, { int is_ram = region_intersects(res->start, resource_size(res), "System RAM"); - resource_size_t key, align_start, align_size; + resource_size_t key, align_start, align_size, align_end; struct dev_pagemap *pgmap; struct page_map *page_map; unsigned long pfn; @@ -309,7 +312,10 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; - for (key = res->start; key <= res->end; key += SECTION_SIZE) { + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + align_end = align_start + align_size - 1; + for (key = align_start; key <= align_end; key += SECTION_SIZE) { struct dev_pagemap *dup; rcu_read_lock(); @@ -336,8 +342,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (nid < 0) nid = numa_mem_id(); - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); error = arch_add_memory(nid, align_start, align_size, true); if (error) goto err_add_memory; diff --git a/kernel/pid.c b/kernel/pid.c index f4ad91b746f1..4d73a834c7e6 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -588,7 +588,7 @@ void __init pidhash_init(void) void __init pidmap_init(void) { - /* Veryify no one has done anything silly */ + /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); /* bump default and minimum pid_max based on number of cpus */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 02e8dfaa1ce2..68d3ebc12601 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -235,7 +235,7 @@ config PM_TRACE_RTC config APM_EMULATION tristate "Advanced Power Management Emulation" - depends on PM && SYS_SUPPORTS_APM_EMULATION + depends on SYS_SUPPORTS_APM_EMULATION help APM is a BIOS specification for saving power using several different techniques. This is mostly useful for battery powered laptops with diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 63d3a24e081a..9503d590e5ef 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6840,7 +6840,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; - for (k = 0; k < nr_node_ids; k++) { + for_each_node(k) { if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1926606ece80..56b7d4b83947 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1220,8 +1220,6 @@ static void task_numa_assign(struct task_numa_env *env, { if (env->best_task) put_task_struct(env->best_task); - if (p) - get_task_struct(p); env->best_task = p; env->best_imp = imp; @@ -1289,20 +1287,30 @@ static void task_numa_compare(struct task_numa_env *env, long imp = env->p->numa_group ? groupimp : taskimp; long moveimp = imp; int dist = env->dist; + bool assigned = false; rcu_read_lock(); raw_spin_lock_irq(&dst_rq->lock); cur = dst_rq->curr; /* - * No need to move the exiting task, and this ensures that ->curr - * wasn't reaped and thus get_task_struct() in task_numa_assign() - * is safe under RCU read lock. - * Note that rcu_read_lock() itself can't protect from the final - * put_task_struct() after the last schedule(). + * No need to move the exiting task or idle task. */ if ((cur->flags & PF_EXITING) || is_idle_task(cur)) cur = NULL; + else { + /* + * The task_struct must be protected here to protect the + * p->numa_faults access in the task_weight since the + * numa_faults could already be freed in the following path: + * finish_task_switch() + * --> put_task_struct() + * --> __put_task_struct() + * --> task_numa_free() + */ + get_task_struct(cur); + } + raw_spin_unlock_irq(&dst_rq->lock); /* @@ -1386,6 +1394,7 @@ balance: */ if (!load_too_imbalanced(src_load, dst_load, env)) { imp = moveimp - 1; + put_task_struct(cur); cur = NULL; goto assign; } @@ -1411,9 +1420,16 @@ balance: env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); assign: + assigned = true; task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); + /* + * The dst_rq->curr isn't assigned. The protection for task_struct is + * finished. + */ + if (cur && !assigned) + put_task_struct(cur); } static void task_numa_find_cpu(struct task_numa_env *env, diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index de0e786b2667..544a7133cbd1 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -162,7 +162,7 @@ static void cpuidle_idle_call(void) */ if (idle_should_freeze()) { entered_state = cpuidle_enter_freeze(drv, dev); - if (entered_state >= 0) { + if (entered_state > 0) { local_irq_enable(); goto exit_idle; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 580ac2d4024f..15a1795bbba1 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -316,24 +316,24 @@ static inline void seccomp_sync_threads(void) put_seccomp_filter(thread); smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); + + /* + * Don't let an unprivileged task work around + * the no_new_privs restriction by creating + * a thread that sets it up, enters seccomp, + * then dies. + */ + if (task_no_new_privs(caller)) + task_set_no_new_privs(thread); + /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ - if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) { - /* - * Don't let an unprivileged task work around - * the no_new_privs restriction by creating - * a thread that sets it up, enters seccomp, - * then dies. - */ - if (task_no_new_privs(caller)) - task_set_no_new_privs(thread); - + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); - } } } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 435b8850dd80..fa909f9fd559 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -897,10 +897,10 @@ static int enqueue_hrtimer(struct hrtimer *timer, */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, - unsigned long newstate, int reprogram) + u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; - unsigned int state = timer->state; + u8 state = timer->state; timer->state = newstate; if (!(state & HRTIMER_STATE_ENQUEUED)) @@ -930,7 +930,7 @@ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { if (hrtimer_is_queued(timer)) { - unsigned long state = timer->state; + u8 state = timer->state; int reprogram; /* @@ -954,6 +954,22 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest return 0; } +static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ +#ifdef CONFIG_TIME_LOW_RES + /* + * CONFIG_TIME_LOW_RES indicates that the system has no way to return + * granular time values. For relative timers we add hrtimer_resolution + * (i.e. one jiffie) to prevent short timeouts. + */ + timer->is_rel = mode & HRTIMER_MODE_REL; + if (timer->is_rel) + tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); +#endif + return tim; +} + /** * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added @@ -974,19 +990,10 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ remove_hrtimer(timer, base, true); - if (mode & HRTIMER_MODE_REL) { + if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); - /* - * CONFIG_TIME_LOW_RES is a temporary way for architectures - * to signal that they simply return xtime in - * do_gettimeoffset(). In this case we want to round up by - * resolution when starting a relative timer, to avoid short - * timeouts. This will go away with the GTOD framework. - */ -#ifdef CONFIG_TIME_LOW_RES - tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); -#endif - } + + tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); @@ -1074,19 +1081,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read + * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ -ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); - rem = hrtimer_expires_remaining(timer); + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) + rem = hrtimer_expires_remaining_adjusted(timer); + else + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } -EXPORT_SYMBOL_GPL(hrtimer_get_remaining); +EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** @@ -1220,6 +1231,14 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, fn = timer->function; /* + * Clear the 'is relative' flag for the TIME_LOW_RES case. If the + * timer is restarted with a period then it becomes an absolute + * timer. If its not restarted it does not matter. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES)) + timer->is_rel = false; + + /* * Because we run timers from hardirq context, there is no chance * they get migrated to another cpu, therefore its safe to unlock * the timer base. diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8d262b467573..1d5c7204ddc9 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -26,7 +26,7 @@ */ static struct timeval itimer_get_remtime(struct hrtimer *timer) { - ktime_t rem = hrtimer_get_remaining(timer); + ktime_t rem = __hrtimer_get_remaining(timer, true); /* * Racy but safe: if the itimer expires after the above diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 36f2ca09aa5e..6df8927c58a5 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -685,8 +685,18 @@ int ntp_validate_timex(struct timex *txc) if (!capable(CAP_SYS_TIME)) return -EPERM; - if (!timeval_inject_offset_valid(&txc->time)) - return -EINVAL; + if (txc->modes & ADJ_NANO) { + struct timespec ts; + + ts.tv_sec = txc->time.tv_sec; + ts.tv_nsec = txc->time.tv_usec; + if (!timespec_inject_offset_valid(&ts)) + return -EINVAL; + + } else { + if (!timeval_inject_offset_valid(&txc->time)) + return -EINVAL; + } } /* diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31d11ac9fa47..f2826c35e918 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(hrtimer_get_expires(timer), now); + remaining = __hrtimer_expires_remaining_adjusted(timer, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9d7a053545f5..0b17424349eb 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -36,16 +36,17 @@ */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); -/* - * The time, when the last jiffy update happened. Protected by jiffies_lock. - */ -static ktime_t last_jiffies_update; - struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } +#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +/* + * The time, when the last jiffy update happened. Protected by jiffies_lock. + */ +static ktime_t last_jiffies_update; + /* * Must be called with interrupts disabled ! */ @@ -151,6 +152,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } +#endif #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; @@ -993,9 +995,9 @@ static void tick_nohz_switch_to_nohz(void) /* Get the next period */ next = tick_init_jiffy_update(); - hrtimer_forward_now(&ts->sched_timer, tick_period); hrtimer_set_expires(&ts->sched_timer, next); - tick_program_event(next, 1); + hrtimer_forward_now(&ts->sched_timer, tick_period); + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index f75e35b60149..ba7d8b288bb3 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -69,7 +69,7 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, print_name_offset(m, taddr); SEQ_printf(m, ", "); print_name_offset(m, timer->function); - SEQ_printf(m, ", S:%02lx", timer->state); + SEQ_printf(m, ", S:%02x", timer->state); #ifdef CONFIG_TIMER_STATS SEQ_printf(m, ", "); print_name_offset(m, timer->start_site); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 45dd798bcd37..326a75e884db 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -191,14 +191,17 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; struct bpf_array *array = container_of(map, struct bpf_array, map); struct perf_event *event; + struct file *file; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - event = (struct perf_event *)array->ptrs[index]; - if (!event) + file = (struct file *)array->ptrs[index]; + if (unlikely(!file)) return -ENOENT; + event = file->private_data; + /* make sure event is local and doesn't have pmu::count */ if (event->oncpu != smp_processor_id() || event->pmu->count) @@ -228,6 +231,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) void *data = (void *) (long) r4; struct perf_sample_data sample_data; struct perf_event *event; + struct file *file; struct perf_raw_record raw = { .size = size, .data = data, @@ -236,10 +240,12 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) if (unlikely(index >= array->map.max_entries)) return -E2BIG; - event = (struct perf_event *)array->ptrs[index]; - if (unlikely(!event)) + file = (struct file *)array->ptrs[index]; + if (unlikely(!file)) return -ENOENT; + event = file->private_data; + if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87fb9801bd9e..d9293402ee68 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1751,7 +1751,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, regs); + ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index dda9e6742950..202df6cffcca 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -126,6 +126,13 @@ check_stack(unsigned long ip, unsigned long *stack) } /* + * Some archs may not have the passed in ip in the dump. + * If that happens, we need to show everything. + */ + if (i == stack_trace_max.nr_entries) + i = 0; + + /* * Now find where in the stack these are. */ x = 0; diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 547f7f923dbc..519b5a10fd70 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -21,7 +21,7 @@ #define ODEBUG_HASH_BITS 14 #define ODEBUG_HASH_SIZE (1 << ODEBUG_HASH_BITS) -#define ODEBUG_POOL_SIZE 512 +#define ODEBUG_POOL_SIZE 1024 #define ODEBUG_POOL_MIN_LEVEL 256 #define ODEBUG_CHUNK_SHIFT PAGE_SHIFT diff --git a/mm/cleancache.c b/mm/cleancache.c index 8fc50811119b..ba5d8f3e6d68 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -22,7 +22,7 @@ * cleancache_ops is set by cleancache_register_ops to contain the pointers * to the cleancache "backend" implementation functions. */ -static struct cleancache_ops *cleancache_ops __read_mostly; +static const struct cleancache_ops *cleancache_ops __read_mostly; /* * Counters available via /sys/kernel/debug/cleancache (if debugfs is @@ -49,7 +49,7 @@ static void cleancache_register_ops_sb(struct super_block *sb, void *unused) /* * Register operations for cleancache. Returns 0 on success. */ -int cleancache_register_ops(struct cleancache_ops *ops) +int cleancache_register_ops(const struct cleancache_ops *ops) { if (cmpxchg(&cleancache_ops, NULL, ops)) return -EBUSY; @@ -430,10 +430,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * Anon pages in shared mappings are surprising: now * just reject it. */ - if (!is_cow_mapping(vm_flags)) { - WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + if (!is_cow_mapping(vm_flags)) return -EFAULT; - } } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) diff --git a/mm/memory.c b/mm/memory.c index 30991f83d0bf..635451abc8f7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1591,10 +1591,15 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ - if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) { + if (!HAVE_PTE_SPECIAL && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; - page = pfn_t_to_page(pfn); + /* + * At this point we are committed to insert_page() + * regardless of whether the caller specified flags that + * result in pfn_t_has_page() == false. + */ + page = pfn_to_page(pfn_t_to_pfn(pfn)); return insert_page(vma, addr, page, vma->vm_page_prot); } return insert_pfn(vma, addr, pfn, vma->vm_page_prot); @@ -2232,11 +2237,6 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, page_cache_get(old_page); - /* - * Only catch write-faults on shared writable pages, - * read-only shared pages can get COWed by - * get_user_pages(.write=1, .force=1). - */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index d040365ba98e..8a4cc2f7f0db 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -307,6 +307,9 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, /* check that it's our buffer */ if (lowpan_is_ipv6(*skb_network_header(skb))) { + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(skb, 1); + /* Copy the packet so that the IPv6 header is * properly aligned. */ @@ -317,6 +320,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; + local_skb->dev = dev; skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); @@ -335,6 +339,8 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, if (!local_skb) goto drop; + local_skb->dev = dev; + ret = iphc_decompress(local_skb, dev, chan); if (ret < 0) { kfree_skb(local_skb); @@ -343,7 +349,6 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; - local_skb->dev = dev; if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 41b5f3813f02..c78ee2dc9323 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -688,21 +688,29 @@ static u8 update_white_list(struct hci_request *req) * command to remove it from the controller. */ list_for_each_entry(b, &hdev->le_white_list, list) { - struct hci_cp_le_del_from_white_list cp; + /* If the device is neither in pend_le_conns nor + * pend_le_reports then remove it from the whitelist. + */ + if (!hci_pend_le_action_lookup(&hdev->pend_le_conns, + &b->bdaddr, b->bdaddr_type) && + !hci_pend_le_action_lookup(&hdev->pend_le_reports, + &b->bdaddr, b->bdaddr_type)) { + struct hci_cp_le_del_from_white_list cp; + + cp.bdaddr_type = b->bdaddr_type; + bacpy(&cp.bdaddr, &b->bdaddr); - if (hci_pend_le_action_lookup(&hdev->pend_le_conns, - &b->bdaddr, b->bdaddr_type) || - hci_pend_le_action_lookup(&hdev->pend_le_reports, - &b->bdaddr, b->bdaddr_type)) { - white_list_entries++; + hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, + sizeof(cp), &cp); continue; } - cp.bdaddr_type = b->bdaddr_type; - bacpy(&cp.bdaddr, &b->bdaddr); + if (hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { + /* White list can not be used with RPAs */ + return 0x00; + } - hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, - sizeof(cp), &cp); + white_list_entries++; } /* Since all no longer valid white list entries have been diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 39a5149f3010..eb4f5f24cbe3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -197,10 +197,20 @@ int l2cap_add_psm(struct l2cap_chan *chan, bdaddr_t *src, __le16 psm) chan->sport = psm; err = 0; } else { - u16 p; + u16 p, start, end, incr; + + if (chan->src_type == BDADDR_BREDR) { + start = L2CAP_PSM_DYN_START; + end = L2CAP_PSM_AUTO_END; + incr = 2; + } else { + start = L2CAP_PSM_LE_DYN_START; + end = L2CAP_PSM_LE_DYN_END; + incr = 1; + } err = -EINVAL; - for (p = 0x1001; p < 0x1100; p += 2) + for (p = start; p <= end; p += incr) if (!__l2cap_global_chan_by_addr(cpu_to_le16(p), src)) { chan->psm = cpu_to_le16(p); chan->sport = cpu_to_le16(p); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 1bb551527044..e4cae72895a7 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -58,7 +58,7 @@ static int l2cap_validate_bredr_psm(u16 psm) return -EINVAL; /* Restrict usage of well-known PSMs */ - if (psm < 0x1001 && !capable(CAP_NET_BIND_SERVICE)) + if (psm < L2CAP_PSM_DYN_START && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; return 0; @@ -67,11 +67,11 @@ static int l2cap_validate_bredr_psm(u16 psm) static int l2cap_validate_le_psm(u16 psm) { /* Valid LE_PSM ranges are defined only until 0x00ff */ - if (psm > 0x00ff) + if (psm > L2CAP_PSM_LE_DYN_END) return -EINVAL; /* Restrict fixed, SIG assigned PSM values to CAP_NET_BIND_SERVICE */ - if (psm <= 0x007f && !capable(CAP_NET_BIND_SERVICE)) + if (psm < L2CAP_PSM_LE_DYN_START && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; return 0; @@ -125,6 +125,9 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) goto done; } + bacpy(&chan->src, &la.l2_bdaddr); + chan->src_type = la.l2_bdaddr_type; + if (la.l2_cid) err = l2cap_add_scid(chan, __le16_to_cpu(la.l2_cid)); else @@ -156,9 +159,6 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) break; } - bacpy(&chan->src, &la.l2_bdaddr); - chan->src_type = la.l2_bdaddr_type; - if (chan->psm && bdaddr_type_is_le(chan->src_type)) chan->mode = L2CAP_MODE_LE_FLOWCTL; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ffed8a1d4f27..4b175df35184 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1072,22 +1072,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) hcon->dst_type = smp->remote_irk->addr_type; queue_work(hdev->workqueue, &conn->id_addr_update_work); } - - /* When receiving an indentity resolving key for - * a remote device that does not use a resolvable - * private address, just remove the key so that - * it is possible to use the controller white - * list for scanning. - * - * Userspace will have been told to not store - * this key at this point. So it is safe to - * just remove it. - */ - if (!bacmp(&smp->remote_irk->rpa, BDADDR_ANY)) { - list_del_rcu(&smp->remote_irk->list); - kfree_rcu(smp->remote_irk, rcu); - smp->remote_irk = NULL; - } } if (smp->csrk) { diff --git a/net/bridge/br.c b/net/bridge/br.c index a1abe4936fe1..3addc05b9a16 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +/* called with RTNL */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -130,7 +131,6 @@ static int br_switchdev_event(struct notifier_block *unused, struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - rtnl_lock(); p = br_port_get_rtnl(dev); if (!p) goto out; @@ -155,7 +155,6 @@ static int br_switchdev_event(struct notifier_block *unused, } out: - rtnl_unlock(); return err; } diff --git a/net/core/dev.c b/net/core/dev.c index cc9e3652cf93..8cba3d852f25 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4351,6 +4351,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= skb_metadata_dst_cmp(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); @@ -4548,10 +4549,12 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { + skb_dst_drop(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } break; case GRO_HELD: diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 1df98c557440..e92b759d906c 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -93,10 +93,17 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) * @sk2: Socket belonging to the existing reuseport group. * May return ENOMEM and not add socket to group under memory pressure. */ -int reuseport_add_sock(struct sock *sk, const struct sock *sk2) +int reuseport_add_sock(struct sock *sk, struct sock *sk2) { struct sock_reuseport *reuse; + if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { + int err = reuseport_alloc(sk2); + + if (err) + return err; + } + spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)), diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index c22920525e5d..775824720b6b 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -353,6 +353,7 @@ config INET_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 7aea0ccb6be6..d07fc076bea0 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1394,9 +1394,10 @@ found: struct fib_info *fi = fa->fa_info; int nhsel, err; - if ((index >= (1ul << fa->fa_slen)) && - ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH))) - continue; + if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { + if (index >= (1ul << fa->fa_slen)) + continue; + } if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) continue; if (fi->fib_dead) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8bb8e7ad8548..6029157a19ed 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -361,13 +361,20 @@ struct sock *inet_diag_find_one_icsk(struct net *net, req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) - sk = inet6_lookup(net, hashinfo, - (struct in6_addr *)req->id.idiag_dst, - req->id.idiag_dport, - (struct in6_addr *)req->id.idiag_src, - req->id.idiag_sport, - req->id.idiag_if); + else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], + req->id.idiag_dport, req->id.idiag_src[3], + req->id.idiag_sport, req->id.idiag_if); + else + sk = inet6_lookup(net, hashinfo, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if); + } #endif else return ERR_PTR(-EINVAL); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 3f00810b7288..187c6fcc3027 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); + skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b1209b63381f..d77eb0c3b684 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -316,7 +316,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { + if (sysctl_ip_early_demux && + !skb_dst(skb) && + !skb->sk && + !ip_is_fragment(iph)) { const struct net_protocol *ipprot; int protocol = iph->protocol; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 67f7c9de0b16..2ed9dd2b5f2f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -143,7 +143,11 @@ static char dhcp_client_identifier[253] __initdata; /* Persistent data: */ +#ifdef IPCONFIG_DYNAMIC static int ic_proto_used; /* Protocol used, if any */ +#else +#define ic_proto_used 0 +#endif static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */ static u8 ic_domain[64]; /* DNS (not NIS) domain name */ diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 6fb869f646bf..a04dee536b8e 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, { int err; - skb_orphan(skb); - local_bh_disable(); err = ip_defrag(net, skb, user); local_bh_enable(); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fd17eec93525..19746b3fcbbe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <asm/unaligned.h> #include <net/busy_poll.h> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -2638,6 +2639,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); @@ -2703,15 +2705,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); info->tcpi_segs_out = tp->segs_out; info->tcpi_segs_in = tp->segs_in; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0003d409fec5..1c2a73406261 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2164,8 +2164,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt; - int err; + int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; @@ -2205,9 +2204,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = tcp_skb_mss(skb); - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, - mss, GFP_ATOMIC); - if (err < 0) + /* If needed, chop off the prefix to mark as lost. */ + lost = (packets - oldcnt) * mss; + if (lost < skb->len && + tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } @@ -2366,8 +2366,6 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) tp->snd_ssthresh = tp->prior_ssthresh; tcp_ecn_withdraw_cwr(tp); } - } else { - tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh); } tp->snd_cwnd_stamp = tcp_time_stamp; tp->undo_marker = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5ced3e4013e3..a4d523709ab3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -707,7 +707,8 @@ release_sk1: outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, +static void tcp_v4_send_ack(struct net *net, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) @@ -722,7 +723,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -784,7 +784,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(sock_net(sk), skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, @@ -803,8 +804,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? - tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + tcp_v4_send_ack(sock_net(sk), skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd, tcp_time_stamp, req->ts_recent, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index dc45b538e237..be0b21852b13 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -499,6 +499,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -512,14 +513,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -563,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -601,14 +607,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index bb7dabe2ebbf..40c897515ddc 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -69,6 +69,7 @@ config INET6_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 517c55b01ba8..428162155280 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -162,6 +162,9 @@ ipv4_connected: fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) fl6.flowi6_oif = np->mcast_oif; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 23de98f976d5..a163102f1803 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -909,6 +909,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct rt6_info *rt; #endif int err; + int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, @@ -940,10 +941,13 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, dst_release(*dst); *dst = NULL; } + + if (fl6->flowi6_oif) + flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3c8834bc822d..ed446639219c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1183,11 +1183,10 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags) { struct dst_entry *dst; - int flags = 0; bool any_src; dst = l3mdev_rt6_dst_by_oif(net, fl6); @@ -1208,7 +1207,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } -EXPORT_SYMBOL(ip6_route_output); +EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e794ef66a401..2066d1c25a11 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -201,14 +201,14 @@ static int ipip6_tunnel_create(struct net_device *dev) if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; + dev->rtnl_link_ops = &sit_link_ops; + err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); - dev->rtnl_link_ops = &sit_link_ops; - dev_hold(dev); ipip6_tunnel_link(sitn, t); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5d2c2afffe7b..22e28a44e3c8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -257,6 +257,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -270,14 +271,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -321,6 +326,7 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -358,14 +364,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/irda/ircomm/ircomm_param.c b/net/irda/ircomm/ircomm_param.c index 3c4caa60c926..5728e76ca6d5 100644 --- a/net/irda/ircomm/ircomm_param.c +++ b/net/irda/ircomm/ircomm_param.c @@ -134,11 +134,10 @@ int ircomm_param_request(struct ircomm_tty_cb *self, __u8 pi, int flush) return -1; } skb_put(skb, count); + pr_debug("%s(), skb->len=%d\n", __func__, skb->len); spin_unlock_irqrestore(&self->spinlock, flags); - pr_debug("%s(), skb->len=%d\n", __func__ , skb->len); - if (flush) { /* ircomm_tty_do_softint will take care of the rest */ schedule_work(&self->tqueue); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ef50a94d3eb7..fc3598a922b0 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -708,6 +708,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_IUCV) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_iucv)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != IUCV_OPEN) { err = -EBADFD; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index f7fc0e00497f..978d3bc31df7 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1733,7 +1733,6 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) if (sdata->vif.type != NL80211_IFTYPE_ADHOC) continue; sdata->u.ibss.last_scan_completed = jiffies; - ieee80211_queue_work(&local->hw, &sdata->work); } mutex_unlock(&local->iflist_mtx); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 6bcf0faa4a89..8190bf27ebff 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -248,6 +248,7 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for scan work complete */ flush_workqueue(local->workqueue); + flush_work(&local->sched_scan_stopped_work); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); @@ -256,6 +257,11 @@ static void ieee80211_restart_work(struct work_struct *work) list_for_each_entry(sdata, &local->interfaces, list) flush_delayed_work(&sdata->dec_tailroom_needed_wk); ieee80211_scan_cancel(local); + + /* make sure any new ROC will consider local->in_reconfig */ + flush_delayed_work(&local->roc_work); + flush_work(&local->hw_roc_done); + ieee80211_reconfig(local); rtnl_unlock(); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fa28500f28fd..6f85b6ab8e51 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1370,17 +1370,6 @@ out: sdata_unlock(sdata); } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - if (ieee80211_vif_is_mesh(&sdata->vif) && - ieee80211_sdata_running(sdata)) - ieee80211_queue_work(&local->hw, &sdata->work); - rcu_read_unlock(); -} void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index a1596344c3ba..4a8019f79fb2 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -362,14 +362,10 @@ static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local); - void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else -static inline void -ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {} static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1c342e2592c4..bfbb1acafdd1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4005,8 +4005,6 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) if (!ieee80211_hw_check(&sdata->local->hw, CONNECTION_MONITOR)) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.monitor_work); - /* and do all the other regular work too */ - ieee80211_queue_work(&sdata->local->hw, &sdata->work); } } diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 8b2f4eaac2ba..55a9c5b94ce1 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -252,14 +252,11 @@ static bool ieee80211_recalc_sw_work(struct ieee80211_local *local, static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, unsigned long start_time) { - struct ieee80211_local *local = roc->sdata->local; - if (WARN_ON(roc->notified)) return; roc->start_time = start_time; roc->started = true; - roc->hw_begun = true; if (roc->mgmt_tx_cookie) { if (!WARN_ON(!roc->frame)) { @@ -274,9 +271,6 @@ static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc, } roc->notified = true; - - if (!local->ops->remain_on_channel) - ieee80211_recalc_sw_work(local, start_time); } static void ieee80211_hw_roc_start(struct work_struct *work) @@ -291,6 +285,7 @@ static void ieee80211_hw_roc_start(struct work_struct *work) if (!roc->started) break; + roc->hw_begun = true; ieee80211_handle_roc_started(roc, local->hw_roc_start_time); } @@ -413,6 +408,10 @@ void ieee80211_start_next_roc(struct ieee80211_local *local) return; } + /* defer roc if driver is not started (i.e. during reconfig) */ + if (local->in_reconfig) + return; + roc = list_first_entry(&local->roc_list, struct ieee80211_roc_work, list); @@ -534,8 +533,10 @@ ieee80211_coalesce_hw_started_roc(struct ieee80211_local *local, * begin, otherwise they'll both be marked properly by the work * struct that runs once the driver notifies us of the beginning */ - if (cur_roc->hw_begun) + if (cur_roc->hw_begun) { + new_roc->hw_begun = true; ieee80211_handle_roc_started(new_roc, now); + } return true; } @@ -658,6 +659,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, queued = true; roc->on_channel = tmp->on_channel; ieee80211_handle_roc_started(roc, now); + ieee80211_recalc_sw_work(local, now); break; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index a413e52f7691..ae980ce8daff 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -314,6 +314,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; + struct ieee80211_sub_if_data *sdata; lockdep_assert_held(&local->mtx); @@ -373,7 +374,16 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); - ieee80211_mesh_notify_scan_completed(local); + + /* Requeue all the work that might have been ignored while + * the scan was in progress; if there was none this will + * just be a no-op for the particular interface. + */ + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (ieee80211_sdata_running(sdata)) + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + } + if (was_scanning) ieee80211_start_next_roc(local); } @@ -1213,6 +1223,14 @@ void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) trace_api_sched_scan_stopped(local); + /* + * this shouldn't really happen, so for simplicity + * simply ignore it, and let mac80211 reconfigure + * the sched scan later on. + */ + if (local->in_reconfig) + return; + schedule_work(&local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4402ad5b27d1..a4a4f89d3ba0 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1453,7 +1453,7 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, more_data = ieee80211_sta_ps_more_data(sta, ignored_acs, reason, driver_release_tids); - if (reason == IEEE80211_FRAME_RELEASE_PSPOLL) + if (driver_release_tids && reason == IEEE80211_FRAME_RELEASE_PSPOLL) driver_release_tids = BIT(find_highest_prio_tid(driver_release_tids)); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 5bad05e9af90..6101deb805a8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -51,6 +51,11 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, struct ieee80211_hdr *hdr = (void *)skb->data; int ac; + if (info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER) { + ieee80211_free_txskb(&local->hw, skb); + return; + } + /* * This skb 'survived' a round-trip through the driver, and * hopefully the driver didn't mangle it too badly. However, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 3943d4bf289c..58f58bd5202f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2043,16 +2043,26 @@ int ieee80211_reconfig(struct ieee80211_local *local) */ if (sched_scan_req->n_scan_plans > 1 || __ieee80211_request_sched_scan_start(sched_scan_sdata, - sched_scan_req)) + sched_scan_req)) { + RCU_INIT_POINTER(local->sched_scan_sdata, NULL); + RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_stopped = true; + } mutex_unlock(&local->mtx); if (sched_scan_stopped) cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy); wake_up: - local->in_reconfig = false; - barrier(); + if (local->in_reconfig) { + local->in_reconfig = false; + barrier(); + + /* Restart deferred ROCs */ + mutex_lock(&local->mtx); + ieee80211_start_next_roc(local); + mutex_unlock(&local->mtx); + } if (local->monitors == local->open_count && local->monitors > 0) ieee80211_add_virtual_monitor(local); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 43d8c9896fa3..f0f688db6213 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -164,8 +164,6 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - if (e.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; @@ -377,8 +375,6 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); - if (e.cidr == 0) - return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3cb3cb831591..58882de06bd7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -66,6 +66,21 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks); __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); +static __read_mostly spinlock_t nf_conntrack_locks_all_lock; +static __read_mostly bool nf_conntrack_locks_all; + +void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) +{ + spin_lock(lock); + while (unlikely(nf_conntrack_locks_all)) { + spin_unlock(lock); + spin_lock(&nf_conntrack_locks_all_lock); + spin_unlock(&nf_conntrack_locks_all_lock); + spin_lock(lock); + } +} +EXPORT_SYMBOL_GPL(nf_conntrack_lock); + static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2) { h1 %= CONNTRACK_LOCKS; @@ -82,12 +97,12 @@ static bool nf_conntrack_double_lock(struct net *net, unsigned int h1, h1 %= CONNTRACK_LOCKS; h2 %= CONNTRACK_LOCKS; if (h1 <= h2) { - spin_lock(&nf_conntrack_locks[h1]); + nf_conntrack_lock(&nf_conntrack_locks[h1]); if (h1 != h2) spin_lock_nested(&nf_conntrack_locks[h2], SINGLE_DEPTH_NESTING); } else { - spin_lock(&nf_conntrack_locks[h2]); + nf_conntrack_lock(&nf_conntrack_locks[h2]); spin_lock_nested(&nf_conntrack_locks[h1], SINGLE_DEPTH_NESTING); } @@ -102,16 +117,19 @@ static void nf_conntrack_all_lock(void) { int i; - for (i = 0; i < CONNTRACK_LOCKS; i++) - spin_lock_nested(&nf_conntrack_locks[i], i); + spin_lock(&nf_conntrack_locks_all_lock); + nf_conntrack_locks_all = true; + + for (i = 0; i < CONNTRACK_LOCKS; i++) { + spin_lock(&nf_conntrack_locks[i]); + spin_unlock(&nf_conntrack_locks[i]); + } } static void nf_conntrack_all_unlock(void) { - int i; - - for (i = 0; i < CONNTRACK_LOCKS; i++) - spin_unlock(&nf_conntrack_locks[i]); + nf_conntrack_locks_all = false; + spin_unlock(&nf_conntrack_locks_all_lock); } unsigned int nf_conntrack_htable_size __read_mostly; @@ -757,7 +775,7 @@ restart: hash = hash_bucket(_hash, net); for (; i < net->ct.htable_size; i++) { lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; - spin_lock(lockp); + nf_conntrack_lock(lockp); if (read_seqcount_retry(&net->ct.generation, sequence)) { spin_unlock(lockp); goto restart; @@ -1382,7 +1400,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), for (; *bucket < net->ct.htable_size; (*bucket)++) { lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; local_bh_disable(); - spin_lock(lockp); + nf_conntrack_lock(lockp); if (*bucket < net->ct.htable_size) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index bd9d31537905..3b40ec575cd5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -425,7 +425,7 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } local_bh_disable(); for (i = 0; i < net->ct.htable_size; i++) { - spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); if (i < net->ct.htable_size) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) unhelp(h, me); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index dbb1bb3edb45..355e8552fd5b 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -840,7 +840,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; - spin_lock(lockp); + nf_conntrack_lock(lockp); if (cb->args[0] >= net->ct.htable_size) { spin_unlock(lockp); goto out; diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index b6605e000801..5eefe4a355c6 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -224,12 +224,12 @@ static int __init nf_tables_netdev_init(void) nft_register_chain_type(&nft_filter_chain_netdev); ret = register_pernet_subsys(&nf_tables_netdev_net_ops); - if (ret < 0) + if (ret < 0) { nft_unregister_chain_type(&nft_filter_chain_netdev); - + return ret; + } register_netdevice_notifier(&nf_tables_netdev_notifier); - - return ret; + return 0; } static void __exit nf_tables_netdev_exit(void) diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 5d010f27ac01..94837d236ab0 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -307,12 +307,12 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) local_bh_disable(); for (i = 0; i < net->ct.htable_size; i++) { - spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); if (i < net->ct.htable_size) { hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) untimeout(h, timeout); } - spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); } local_bh_enable(); } diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 383c17138399..b78c28ba465f 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -46,16 +46,14 @@ static void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { - src64 = get_unaligned_be64(&src[i]); - src64 = be64_to_cpu((__force __be64)src64); + src64 = get_unaligned((u64 *)&src[i]); put_unaligned_be64(src64, &dst[i]); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = get_unaligned_be64(&src[i]); - src64 = (__force u64)cpu_to_be64(src64); - put_unaligned_be64(src64, &dst[i]); + put_unaligned(src64, (u64 *)&dst[i]); } break; } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a0eb2161e3ef..d4a4619fcebc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -127,6 +127,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, NF_CT_LABELS_MAX_SIZE - size); return; } +#endif case NFT_CT_BYTES: /* fallthrough */ case NFT_CT_PKTS: { const struct nf_conn_acct *acct = nf_conn_acct_find(ct); @@ -138,7 +139,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, memcpy(dest, &count, sizeof(count)); return; } -#endif default: break; } diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index b7c43def0dc6..e118397254af 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -228,7 +228,7 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); u8 nexthdr; - __be16 frag_off; + __be16 frag_off, oldlen, newlen; int tcphoff; int ret; @@ -244,7 +244,12 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par) return NF_DROP; if (ret > 0) { ipv6h = ipv6_hdr(skb); - ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) + ret); + oldlen = ipv6h->payload_len; + newlen = htons(ntohs(oldlen) + ret); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, oldlen), + newlen); + ipv6h->payload_len = newlen; } return XT_CONTINUE; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 81dc1bb6e016..f1ffb34e253f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2831,7 +2831,8 @@ static int netlink_dump(struct sock *sk) * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ - skb_reserve(skb, skb_tailroom(skb) - alloc_size); + if (!netlink_rx_is_mmaped(sk)) + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f53bf3b6558b..cf5b69ab1829 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1095,17 +1095,6 @@ static unsigned int rfkill_fop_poll(struct file *file, poll_table *wait) return res; } -static bool rfkill_readable(struct rfkill_data *data) -{ - bool r; - - mutex_lock(&data->mtx); - r = !list_empty(&data->events); - mutex_unlock(&data->mtx); - - return r; -} - static ssize_t rfkill_fop_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -1122,8 +1111,11 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, goto out; } mutex_unlock(&data->mtx); + /* since we re-check and it just compares pointers, + * using !list_empty() without locking isn't a problem + */ ret = wait_event_interruptible(data->read_wait, - rfkill_readable(data)); + !list_empty(&data->events)); mutex_lock(&data->mtx); if (ret) diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index f26bdea875c1..a1cd778240cd 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -403,6 +403,8 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) if (len <= cl->deficit) { cl->deficit -= len; skb = qdisc_dequeue_peeked(cl->qdisc); + if (unlikely(skb == NULL)) + goto out; if (cl->qdisc->q.qlen == 0) list_del(&cl->alist); diff --git a/net/sctp/input.c b/net/sctp/input.c index bf61dfb8e09e..49d2cc751386 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -935,15 +935,22 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_transport **pt) { struct sctp_transport *t; + struct sctp_association *asoc = NULL; + rcu_read_lock(); t = sctp_addrs_lookup_transport(net, local, peer); - if (!t || t->dead) - return NULL; + if (!t || !sctp_transport_hold(t)) + goto out; - sctp_association_hold(t->asoc); + asoc = t->asoc; + sctp_association_hold(asoc); *pt = t; - return t->asoc; + sctp_transport_put(t); + +out: + rcu_read_unlock(); + return asoc; } /* Look up an association. protected by RCU read lock */ @@ -955,9 +962,7 @@ struct sctp_association *sctp_lookup_association(struct net *net, { struct sctp_association *asoc; - rcu_read_lock(); asoc = __sctp_lookup_association(net, laddr, paddr, transportp); - rcu_read_unlock(); return asoc; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 684c5b31563b..ded7d931a6a5 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -165,8 +165,6 @@ static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_associa list_for_each_entry_rcu(transport, &assoc->peer.transport_addr_list, transports) { addr = &transport->ipaddr; - if (transport->dead) - continue; af = sctp_get_af_specific(addr->sa.sa_family); if (af->cmp_addr(addr, primary)) { @@ -380,6 +378,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; + if (!sctp_transport_hold(transport)) + return 0; assoc = transport->asoc; epb = &assoc->base; sk = epb->sk; @@ -412,6 +412,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sk->sk_rcvbuf); seq_printf(seq, "\n"); + sctp_transport_put(transport); + return 0; } @@ -489,12 +491,12 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } tsp = (struct sctp_transport *)v; + if (!sctp_transport_hold(tsp)) + return 0; assoc = tsp->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, transports) { - if (tsp->dead) - continue; /* * The remote address (ADDR) */ @@ -544,6 +546,8 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } + sctp_transport_put(tsp); + return 0; } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 2e21384697c2..b5327bb77458 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -259,12 +259,6 @@ void sctp_generate_t3_rtx_event(unsigned long peer) goto out_unlock; } - /* Is this transport really dead and just waiting around for - * the timer to let go of the reference? - */ - if (transport->dead) - goto out_unlock; - /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_T3_RTX), @@ -380,12 +374,6 @@ void sctp_generate_heartbeat_event(unsigned long data) goto out_unlock; } - /* Is this structure just waiting around for us to actually - * get destroyed? - */ - if (transport->dead) - goto out_unlock; - error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_HEARTBEAT), asoc->state, asoc->ep, asoc, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9bb80ec4c08f..5ca2ebfe0be8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6636,6 +6636,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6659,6 +6660,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index aab9e3f29755..a431c14044a4 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -132,8 +132,6 @@ fail: */ void sctp_transport_free(struct sctp_transport *transport) { - transport->dead = 1; - /* Try to delete the heartbeat timer. */ if (del_timer(&transport->hb_timer)) sctp_transport_put(transport); @@ -169,7 +167,7 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) */ static void sctp_transport_destroy(struct sctp_transport *transport) { - if (unlikely(!transport->dead)) { + if (unlikely(atomic_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } @@ -296,9 +294,9 @@ void sctp_transport_route(struct sctp_transport *transport, } /* Hold a reference to a transport. */ -void sctp_transport_hold(struct sctp_transport *transport) +int sctp_transport_hold(struct sctp_transport *transport) { - atomic_inc(&transport->refcnt); + return atomic_add_unless(&transport->refcnt, 1, 0); } /* Release a reference to a transport and clean up diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index ebc661d3b6e3..47f7da58a7f0 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -20,6 +20,7 @@ #include <linux/list.h> #include <linux/workqueue.h> #include <linux/if_vlan.h> +#include <linux/rtnetlink.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -567,7 +568,6 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, } EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); -static DEFINE_MUTEX(switchdev_mutex); static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** @@ -582,9 +582,9 @@ int register_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_register(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_switchdev_notifier); @@ -600,9 +600,9 @@ int unregister_switchdev_notifier(struct notifier_block *nb) { int err; - mutex_lock(&switchdev_mutex); + rtnl_lock(); err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb); - mutex_unlock(&switchdev_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); @@ -616,16 +616,17 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * Call all network notifier blocks. This should be called by driver * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). + * rtnl_lock must be held. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { int err; + ASSERT_RTNL(); + info->dev = dev; - mutex_lock(&switchdev_mutex); err = raw_notifier_call_chain(&switchdev_notif_chain, val, info); - mutex_unlock(&switchdev_mutex); return err; } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 350cca33ee0a..69ee2eeef968 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -289,15 +289,14 @@ static void tipc_subscrb_rcv_cb(struct net *net, int conid, struct sockaddr_tipc *addr, void *usr_data, void *buf, size_t len) { - struct tipc_subscriber *subscriber = usr_data; + struct tipc_subscriber *subscrb = usr_data; struct tipc_subscription *sub = NULL; struct tipc_net *tn = net_generic(net, tipc_net_id); - tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscriber, &sub); - if (sub) - tipc_nametbl_subscribe(sub); - else - tipc_conn_terminate(tn->topsrv, subscriber->conid); + if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub)) + return tipc_conn_terminate(tn->topsrv, subscrb->conid); + + tipc_nametbl_subscribe(sub); } /* Handle one request to establish a new subscriber */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c5bf5ef2bf89..49d5093eb055 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2339,6 +2339,7 @@ again: if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3b0ce1c484a3..547ceecc0523 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -231,20 +231,22 @@ static const struct ieee80211_regdomain world_regdom = { /* IEEE 802.11b/g, channels 1..11 */ REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), /* IEEE 802.11b/g, channels 12..13. */ - REG_RULE(2467-10, 2472+10, 40, 6, 20, - NL80211_RRF_NO_IR), + REG_RULE(2467-10, 2472+10, 20, 6, 20, + NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW), /* IEEE 802.11 channel 14 - Only JP enables * this and for 802.11b only */ REG_RULE(2484-10, 2484+10, 20, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_NO_OFDM), /* IEEE 802.11a, channel 36..48 */ - REG_RULE(5180-10, 5240+10, 160, 6, 20, - NL80211_RRF_NO_IR), + REG_RULE(5180-10, 5240+10, 80, 6, 20, + NL80211_RRF_NO_IR | + NL80211_RRF_AUTO_BW), /* IEEE 802.11a, channel 52..64 - DFS required */ - REG_RULE(5260-10, 5320+10, 160, 6, 20, + REG_RULE(5260-10, 5320+10, 80, 6, 20, NL80211_RRF_NO_IR | + NL80211_RRF_AUTO_BW | NL80211_RRF_DFS), /* IEEE 802.11a, channel 100..144 - DFS required */ @@ -2745,7 +2747,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) const struct ieee80211_power_rule *power_rule = NULL; char bw[32], cac_time[32]; - pr_info(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); + pr_debug(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); for (i = 0; i < rd->n_reg_rules; i++) { reg_rule = &rd->reg_rules[i]; @@ -2772,7 +2774,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) * in certain regions */ if (power_rule->max_antenna_gain) - pr_info(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", + pr_debug(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, @@ -2780,7 +2782,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) power_rule->max_eirp, cac_time); else - pr_info(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", + pr_debug(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, @@ -2813,35 +2815,35 @@ static void print_regdomain(const struct ieee80211_regdomain *rd) struct cfg80211_registered_device *rdev; rdev = cfg80211_rdev_by_wiphy_idx(lr->wiphy_idx); if (rdev) { - pr_info("Current regulatory domain updated by AP to: %c%c\n", + pr_debug("Current regulatory domain updated by AP to: %c%c\n", rdev->country_ie_alpha2[0], rdev->country_ie_alpha2[1]); } else - pr_info("Current regulatory domain intersected:\n"); + pr_debug("Current regulatory domain intersected:\n"); } else - pr_info("Current regulatory domain intersected:\n"); + pr_debug("Current regulatory domain intersected:\n"); } else if (is_world_regdom(rd->alpha2)) { - pr_info("World regulatory domain updated:\n"); + pr_debug("World regulatory domain updated:\n"); } else { if (is_unknown_alpha2(rd->alpha2)) - pr_info("Regulatory domain changed to driver built-in settings (unknown country)\n"); + pr_debug("Regulatory domain changed to driver built-in settings (unknown country)\n"); else { if (reg_request_cell_base(lr)) - pr_info("Regulatory domain changed to country: %c%c by Cell Station\n", + pr_debug("Regulatory domain changed to country: %c%c by Cell Station\n", rd->alpha2[0], rd->alpha2[1]); else - pr_info("Regulatory domain changed to country: %c%c\n", + pr_debug("Regulatory domain changed to country: %c%c\n", rd->alpha2[0], rd->alpha2[1]); } } - pr_info(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); + pr_debug(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); print_rd_rules(rd); } static void print_regdomain_info(const struct ieee80211_regdomain *rd) { - pr_info("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); + pr_debug("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_rd_rules(rd); } @@ -2862,7 +2864,8 @@ static int reg_set_rd_user(const struct ieee80211_regdomain *rd, return -EALREADY; if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } @@ -2898,7 +2901,8 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, return -EALREADY; if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } @@ -2956,7 +2960,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, */ if (!is_valid_rd(rd)) { - pr_err("Invalid regulatory domain detected:\n"); + pr_err("Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index e080746e1a6b..48958d3cec9e 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -594,7 +594,8 @@ static int ignore_undef_symbol(struct elf_info *info, const char *symname) if (strncmp(symname, "_restgpr0_", sizeof("_restgpr0_") - 1) == 0 || strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0 || strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 || - strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0) + strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0 || + strcmp(symname, ".TOC.") == 0) return 1; /* Do not ignore this symbol */ return 0; diff --git a/security/keys/key.c b/security/keys/key.c index 07a87311055c..09ef276c4bdc 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -430,7 +430,8 @@ static int __key_instantiate_and_link(struct key *key, /* and link it into the destination keyring */ if (keyring) { - set_bit(KEY_FLAG_KEEP, &key->flags); + if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) + set_bit(KEY_FLAG_KEEP, &key->flags); __key_link(key, _edit); } diff --git a/sound/core/Kconfig b/sound/core/Kconfig index e3e949126a56..a2a1e24becc6 100644 --- a/sound/core/Kconfig +++ b/sound/core/Kconfig @@ -97,11 +97,11 @@ config SND_PCM_TIMER bool "PCM timer interface" if EXPERT default y help - If you disable this option, pcm timer will be inavailable, so - those stubs used pcm timer (e.g. dmix, dsnoop & co) may work + If you disable this option, pcm timer will be unavailable, so + those stubs that use pcm timer (e.g. dmix, dsnoop & co) may work incorrectlly. - For some embedded device, we may disable it to reduce memory + For some embedded devices, we may disable it to reduce memory footprint, about 20KB on x86_64 platform. config SND_SEQUENCER_OSS diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 18b8dc45bb8f..7fac3cae8abd 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -46,6 +46,13 @@ #include <sound/compress_offload.h> #include <sound/compress_driver.h> +/* struct snd_compr_codec_caps overflows the ioctl bit size for some + * architectures, so we need to disable the relevant ioctls. + */ +#if _IOC_SIZEBITS < 14 +#define COMPR_CODEC_CAPS_OVERFLOW +#endif + /* TODO: * - add substream support for multiple devices in case of * SND_DYNAMIC_MINORS is not used @@ -440,6 +447,7 @@ out: return retval; } +#ifndef COMPR_CODEC_CAPS_OVERFLOW static int snd_compr_get_codec_caps(struct snd_compr_stream *stream, unsigned long arg) { @@ -463,6 +471,7 @@ out: kfree(caps); return retval; } +#endif /* !COMPR_CODEC_CAPS_OVERFLOW */ /* revisit this with snd_pcm_preallocate_xxx */ static int snd_compr_allocate_buffer(struct snd_compr_stream *stream, @@ -801,9 +810,11 @@ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) case _IOC_NR(SNDRV_COMPRESS_GET_CAPS): retval = snd_compr_get_caps(stream, arg); break; +#ifndef COMPR_CODEC_CAPS_OVERFLOW case _IOC_NR(SNDRV_COMPRESS_GET_CODEC_CAPS): retval = snd_compr_get_codec_caps(stream, arg); break; +#endif case _IOC_NR(SNDRV_COMPRESS_SET_PARAMS): retval = snd_compr_set_params(stream, arg); break; diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c index b1221b29728e..6779e82b46dd 100644 --- a/sound/core/seq/oss/seq_oss_init.c +++ b/sound/core/seq/oss/seq_oss_init.c @@ -202,7 +202,7 @@ snd_seq_oss_open(struct file *file, int level) dp->index = i; if (i >= SNDRV_SEQ_OSS_MAX_CLIENTS) { - pr_err("ALSA: seq_oss: too many applications\n"); + pr_debug("ALSA: seq_oss: too many applications\n"); rc = -ENOMEM; goto _error; } diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index 0f3b38184fe5..b16dbef04174 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -308,7 +308,7 @@ snd_seq_oss_synth_cleanup(struct seq_oss_devinfo *dp) struct seq_oss_synth *rec; struct seq_oss_synthinfo *info; - if (snd_BUG_ON(dp->max_synthdev >= SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) + if (snd_BUG_ON(dp->max_synthdev > SNDRV_SEQ_OSS_MAX_SYNTH_DEVS)) return; for (i = 0; i < dp->max_synthdev; i++) { info = &dp->synths[i]; diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 75b74850c005..bde33308f0d6 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver."); module_param(fake_buffer, bool, 0444); MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations."); #ifdef CONFIG_HIGH_RES_TIMERS -module_param(hrtimer, bool, 0644); +module_param(hrtimer, bool, 0444); MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source."); #endif diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c index 926e5dcbb66a..5022c9b97ddf 100644 --- a/sound/firewire/bebob/bebob_stream.c +++ b/sound/firewire/bebob/bebob_stream.c @@ -47,14 +47,16 @@ static const unsigned int bridgeco_freq_table[] = { [6] = 0x07, }; -static unsigned int -get_formation_index(unsigned int rate) +static int +get_formation_index(unsigned int rate, unsigned int *index) { unsigned int i; for (i = 0; i < ARRAY_SIZE(snd_bebob_rate_table); i++) { - if (snd_bebob_rate_table[i] == rate) - return i; + if (snd_bebob_rate_table[i] == rate) { + *index = i; + return 0; + } } return -EINVAL; } @@ -425,7 +427,9 @@ make_both_connections(struct snd_bebob *bebob, unsigned int rate) goto end; /* confirm params for both streams */ - index = get_formation_index(rate); + err = get_formation_index(rate, &index); + if (err < 0) + goto end; pcm_channels = bebob->tx_stream_formations[index].pcm; midi_channels = bebob->tx_stream_formations[index].midi; err = amdtp_am824_set_parameters(&bebob->tx_stream, rate, diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig index 0216475fc759..37adcc6cbe6b 100644 --- a/sound/isa/Kconfig +++ b/sound/isa/Kconfig @@ -3,6 +3,7 @@ config SND_WSS_LIB tristate select SND_PCM + select SND_TIMER config SND_SB_COMMON tristate @@ -42,6 +43,7 @@ config SND_AD1816A select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Analog Devices SoundPort AD1816A or compatible sound chips. @@ -209,6 +211,7 @@ config SND_GUSCLASSIC tristate "Gravis UltraSound Classic" select SND_RAWMIDI select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Classic soundcards. @@ -221,6 +224,7 @@ config SND_GUSEXTREME select SND_OPL3_LIB select SND_MPU401_UART select SND_PCM + select SND_TIMER help Say Y here to include support for Gravis UltraSound Extreme soundcards. diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig index 656ce39bddbc..8f6594a7d37f 100644 --- a/sound/pci/Kconfig +++ b/sound/pci/Kconfig @@ -155,6 +155,7 @@ config SND_AZT3328 select SND_PCM select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y here to include support for Aztech AZF3328 (PCI168) @@ -463,6 +464,7 @@ config SND_EMU10K1 select SND_HWDEP select SND_RAWMIDI select SND_AC97_CODEC + select SND_TIMER depends on ZONE_DMA help Say Y to include support for Sound Blaster PCI 512, Live!, @@ -889,6 +891,7 @@ config SND_YMFPCI select SND_OPL3_LIB select SND_MPU401_UART select SND_AC97_CODEC + select SND_TIMER help Say Y here to include support for Yamaha PCI audio chips - YMF724, YMF724F, YMF740, YMF740C, YMF744, YMF754. diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 256e6cda218f..4045dca3d699 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -90,6 +90,8 @@ enum { #define NVIDIA_HDA_ENABLE_COHBIT 0x01 /* Defines for Intel SCH HDA snoop control */ +#define INTEL_HDA_CGCTL 0x48 +#define INTEL_HDA_CGCTL_MISCBDCGE (0x1 << 6) #define INTEL_SCH_HDA_DEVC 0x78 #define INTEL_SCH_HDA_DEVC_NOSNOOP (0x1<<11) @@ -534,10 +536,21 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) { struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; + u32 val; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); + if (IS_BROXTON(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } azx_init_chip(chip, full_reset); + if (IS_BROXTON(pci)) { + pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); + val = val | INTEL_HDA_CGCTL_MISCBDCGE; + pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); + } if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, false); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 426a29a1c19b..1f52b55d77c9 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -3653,6 +3653,7 @@ HDA_CODEC_ENTRY(0x10de0070, "GPU 70 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0071, "GPU 71 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de0072, "GPU 72 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de007d, "GPU 7d HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de0083, "GPU 83 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f81, "VX900 HDMI/DP", patch_via_hdmi), diff --git a/sound/sparc/Kconfig b/sound/sparc/Kconfig index d75deba5617d..dfcd38647606 100644 --- a/sound/sparc/Kconfig +++ b/sound/sparc/Kconfig @@ -22,6 +22,7 @@ config SND_SUN_AMD7930 config SND_SUN_CS4231 tristate "Sun CS4231" select SND_PCM + select SND_TIMER help Say Y here to include support for CS4231 sound device on Sun. diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 23ea6d800c4c..a75d9ce7d77a 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1205,8 +1205,12 @@ void snd_usb_set_interface_quirk(struct usb_device *dev) * "Playback Design" products need a 50ms delay after setting the * USB interface. */ - if (le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) + switch (le16_to_cpu(dev->descriptor.idVendor)) { + case 0x23ba: /* Playback Design */ + case 0x0644: /* TEAC Corp. */ mdelay(50); + break; + } } void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, @@ -1221,6 +1225,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); + /* + * "TEAC Corp." products need a 20ms delay after each + * class compliant request + */ + if ((le16_to_cpu(dev->descriptor.idVendor) == 0x0644) && + (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) + mdelay(20); + /* Marantz/Denon devices with USB DAC functionality need a delay * after each class compliant request */ diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 0a22407e1d7d..5d34815c7ccb 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -77,6 +77,9 @@ include config/utilities.mak # Define NO_AUXTRACE if you do not want AUX area tracing support # # Define NO_LIBBPF if you do not want BPF support +# +# Define FEATURES_DUMP to provide features detection dump file +# and bypass the feature detection # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -166,6 +169,15 @@ ifeq ($(config),1) include config/Makefile endif +# The FEATURE_DUMP_EXPORT holds location of the actual +# FEATURE_DUMP file to be used to bypass feature detection +# (for bpf or any other subproject) +ifeq ($(FEATURES_DUMP),) +FEATURE_DUMP_EXPORT := $(realpath $(OUTPUT)FEATURE-DUMP) +else +FEATURE_DUMP_EXPORT := $(FEATURES_DUMP) +endif + export prefix bindir sharedir sysconfdir DESTDIR # sparse is architecture-neutral, which means that we need to tell it @@ -436,7 +448,7 @@ $(LIBAPI)-clean: $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null $(LIBBPF): fixdep FORCE - $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP) + $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) @@ -611,6 +623,17 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(python-clean) # +# To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY) +# file if defined, with no further action. +feature-dump: +ifdef FEATURE_DUMP_COPY + @cp $(OUTPUT)FEATURE-DUMP $(FEATURE_DUMP_COPY) + @echo "FEATURE-DUMP file copied into $(FEATURE_DUMP_COPY)" +else + @echo "FEATURE-DUMP file available in $(OUTPUT)FEATURE-DUMP" +endif + +# # Trick: if ../../.git does not exist - we are building out of tree for example, # then force version regeneration: # diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 3e89ba825f6b..7f064eb37158 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -17,7 +17,7 @@ static pid_t spawn(void) if (pid) return pid; - while(1); + while(1) sleep(5); return 0; } diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index e5959c136a19..511141b102e8 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -181,7 +181,11 @@ LDFLAGS += -Wl,-z,noexecstack EXTLIBS = -lpthread -lrt -lm -ldl +ifeq ($(FEATURES_DUMP),) include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif ifeq ($(feature-stackprotector-all), 1) CFLAGS += -fstack-protector-all diff --git a/tools/perf/tests/make b/tools/perf/tests/make index df38decc48c3..f918015512af 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -5,7 +5,7 @@ ifeq ($(MAKECMDGOALS),) # no target specified, trigger the whole suite all: @echo "Testing Makefile"; $(MAKE) -sf tests/make MK=Makefile - @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf + @echo "Testing Makefile.perf"; $(MAKE) -sf tests/make MK=Makefile.perf SET_PARALLEL=1 SET_O=1 else # run only specific test over 'Makefile' %: @@ -13,6 +13,26 @@ else endif else PERF := . +PERF_O := $(PERF) +O_OPT := + +ifneq ($(O),) + FULL_O := $(shell readlink -f $(O) || echo $(O)) + PERF_O := $(FULL_O) + ifeq ($(SET_O),1) + O_OPT := 'O=$(FULL_O)' + endif + K_O_OPT := 'O=$(FULL_O)' +endif + +PARALLEL_OPT= +ifeq ($(SET_PARALLEL),1) + cores := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null) + ifeq ($(cores),0) + cores := 1 + endif + PARALLEL_OPT="-j$(cores)" +endif # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL @@ -156,11 +176,11 @@ test_make_doc := $(test_ok) test_make_help_O := $(test_ok) test_make_doc_O := $(test_ok) -test_make_python_perf_so := test -f $(PERF)/python/perf.so +test_make_python_perf_so := test -f $(PERF_O)/python/perf.so -test_make_perf_o := test -f $(PERF)/perf.o -test_make_util_map_o := test -f $(PERF)/util/map.o -test_make_util_pmu_bison_o := test -f $(PERF)/util/pmu-bison.o +test_make_perf_o := test -f $(PERF_O)/perf.o +test_make_util_map_o := test -f $(PERF_O)/util/map.o +test_make_util_pmu_bison_o := test -f $(PERF_O)/util/pmu-bison.o define test_dest_files for file in $(1); do \ @@ -227,7 +247,7 @@ test_make_perf_o_O := test -f $$TMP_O/perf.o test_make_util_map_o_O := test -f $$TMP_O/util/map.o test_make_util_pmu_bison_o_O := test -f $$TMP_O/util/pmu-bison.o -test_default = test -x $(PERF)/perf +test_default = test -x $(PERF_O)/perf test = $(if $(test_$1),$(test_$1),$(test_default)) test_default_O = test -x $$TMP_O/perf @@ -247,12 +267,12 @@ endif MAKEFLAGS := --no-print-directory -clean := @(cd $(PERF); make -s -f $(MK) clean >/dev/null) +clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null) $(run): $(call clean) @TMP_DEST=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \ + cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1; \ echo " test: $(call test,$@)" >> $@ 2>&1; \ @@ -263,7 +283,7 @@ $(run_O): $(call clean) @TMP_O=$$(mktemp -d); \ TMP_DEST=$$(mktemp -d); \ - cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ + cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ ( eval $$cmd ) >> $@ 2>&1 && \ echo " test: $(call test_O,$@)" >> $@ 2>&1; \ @@ -276,17 +296,22 @@ tarpkg: ( eval $$cmd ) >> $@ 2>&1 && \ rm -f $@ +KERNEL_O := ../.. +ifneq ($(O),) + KERNEL_O := $(O) +endif + make_kernelsrc: - @echo "- make -C <kernelsrc> tools/perf" + @echo "- make -C <kernelsrc> $(PARALLEL_OPT) $(K_O_OPT) tools/perf" $(call clean); \ - (make -C ../.. tools/perf) > $@ 2>&1 && \ - test -x perf && rm -f $@ || (cat $@ ; false) + (make -C ../.. $(PARALLEL_OPT) $(K_O_OPT) tools/perf) > $@ 2>&1 && \ + test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) make_kernelsrc_tools: - @echo "- make -C <kernelsrc>/tools perf" + @echo "- make -C <kernelsrc>/tools $(PARALLEL_OPT) $(K_O_OPT) perf" $(call clean); \ - (make -C ../../tools perf) > $@ 2>&1 && \ - test -x perf && rm -f $@ || (cat $@ ; false) + (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \ + test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false) all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools @echo OK diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index d4d7cc27252f..718bd46d47fa 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser, nd = browser->curr_hot; break; case K_UNTAB: - if (nd != NULL) + if (nd != NULL) { nd = rb_next(nd); if (nd == NULL) nd = rb_first(&browser->entries); - else + } else nd = browser->curr_hot; break; case K_F1: diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index c226303e3da0..68a7612019dc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -131,6 +131,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); + hists__new_col_len(hists, HISTC_MEM_DCACHELINE, + symlen); } if (h->mem_info->iaddr.sym) { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index d5636ba94b20..40b7a0d0905b 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1149,7 +1149,7 @@ static struct machine *machines__find_for_cpumode(struct machines *machines, machine = machines__find(machines, pid); if (!machine) - machine = machines__find(machines, DEFAULT_GUEST_KERNEL_ID); + machine = machines__findnew(machines, DEFAULT_GUEST_KERNEL_ID); return machine; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2f901d15e063..2b58edccd56f 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -310,7 +310,6 @@ int perf_stat_process_counter(struct perf_stat_config *config, int i, ret; aggr->val = aggr->ena = aggr->run = 0; - init_stats(ps->res_stats); if (counter->per_pkg) zero_per_pkg(counter); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3b2de6eb3376..ab02209a7cf3 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1466,7 +1466,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) * Read the build id if possible. This is required for * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ - if (filename__read_build_id(dso->name, build_id, BUILD_ID_SIZE) > 0) + if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); /* diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 7ec7df9e7fc7..0c1a7e65bb81 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -113,7 +113,7 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res, } EXPORT_SYMBOL(__wrap_devm_memremap_pages); -pfn_t __wrap_phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags) { struct nfit_test_resource *nfit_res = get_nfit_res(addr); diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index e86d937cc22c..60fe3c569bd9 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -45,7 +45,17 @@ static inline int ksft_exit_fail(void) } #endif -#define NSEC_PER_SEC 1000000000L +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + +#define ADJ_SETOFFSET 0x0100 + +#include <sys/syscall.h> +static int clock_adjtime(clockid_t id, struct timex *tx) +{ + return syscall(__NR_clock_adjtime, id, tx); +} + /* clear NTP time_status & time_state */ int clear_time_state(void) @@ -193,10 +203,137 @@ out: } +int set_offset(long long offset, int use_nano) +{ + struct timex tmx = {}; + int ret; + + tmx.modes = ADJ_SETOFFSET; + if (use_nano) { + tmx.modes |= ADJ_NANO; + + tmx.time.tv_sec = offset / NSEC_PER_SEC; + tmx.time.tv_usec = offset % NSEC_PER_SEC; + + if (offset < 0 && tmx.time.tv_usec) { + tmx.time.tv_sec -= 1; + tmx.time.tv_usec += NSEC_PER_SEC; + } + } else { + tmx.time.tv_sec = offset / USEC_PER_SEC; + tmx.time.tv_usec = offset % USEC_PER_SEC; + + if (offset < 0 && tmx.time.tv_usec) { + tmx.time.tv_sec -= 1; + tmx.time.tv_usec += USEC_PER_SEC; + } + } + + ret = clock_adjtime(CLOCK_REALTIME, &tmx); + if (ret < 0) { + printf("(sec: %ld usec: %ld) ", tmx.time.tv_sec, tmx.time.tv_usec); + printf("[FAIL]\n"); + return -1; + } + return 0; +} + +int set_bad_offset(long sec, long usec, int use_nano) +{ + struct timex tmx = {}; + int ret; + + tmx.modes = ADJ_SETOFFSET; + if (use_nano) + tmx.modes |= ADJ_NANO; + + tmx.time.tv_sec = sec; + tmx.time.tv_usec = usec; + ret = clock_adjtime(CLOCK_REALTIME, &tmx); + if (ret >= 0) { + printf("Invalid (sec: %ld usec: %ld) did not fail! ", tmx.time.tv_sec, tmx.time.tv_usec); + printf("[FAIL]\n"); + return -1; + } + return 0; +} + +int validate_set_offset(void) +{ + printf("Testing ADJ_SETOFFSET... "); + + /* Test valid values */ + if (set_offset(NSEC_PER_SEC - 1, 1)) + return -1; + + if (set_offset(-NSEC_PER_SEC + 1, 1)) + return -1; + + if (set_offset(-NSEC_PER_SEC - 1, 1)) + return -1; + + if (set_offset(5 * NSEC_PER_SEC, 1)) + return -1; + + if (set_offset(-5 * NSEC_PER_SEC, 1)) + return -1; + + if (set_offset(5 * NSEC_PER_SEC + NSEC_PER_SEC / 2, 1)) + return -1; + + if (set_offset(-5 * NSEC_PER_SEC - NSEC_PER_SEC / 2, 1)) + return -1; + + if (set_offset(USEC_PER_SEC - 1, 0)) + return -1; + + if (set_offset(-USEC_PER_SEC + 1, 0)) + return -1; + + if (set_offset(-USEC_PER_SEC - 1, 0)) + return -1; + + if (set_offset(5 * USEC_PER_SEC, 0)) + return -1; + + if (set_offset(-5 * USEC_PER_SEC, 0)) + return -1; + + if (set_offset(5 * USEC_PER_SEC + USEC_PER_SEC / 2, 0)) + return -1; + + if (set_offset(-5 * USEC_PER_SEC - USEC_PER_SEC / 2, 0)) + return -1; + + /* Test invalid values */ + if (set_bad_offset(0, -1, 1)) + return -1; + if (set_bad_offset(0, -1, 0)) + return -1; + if (set_bad_offset(0, 2 * NSEC_PER_SEC, 1)) + return -1; + if (set_bad_offset(0, 2 * USEC_PER_SEC, 0)) + return -1; + if (set_bad_offset(0, NSEC_PER_SEC, 1)) + return -1; + if (set_bad_offset(0, USEC_PER_SEC, 0)) + return -1; + if (set_bad_offset(0, -NSEC_PER_SEC, 1)) + return -1; + if (set_bad_offset(0, -USEC_PER_SEC, 0)) + return -1; + + printf("[OK]\n"); + return 0; +} + int main(int argc, char **argv) { if (validate_freq()) return ksft_exit_fail(); + if (validate_set_offset()) + return ksft_exit_fail(); + return ksft_exit_pass(); } diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index 26b7926bda88..ba34f9e96efd 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -1,15 +1,19 @@ #if defined(__i386__) || defined(__x86_64__) #define barrier() asm volatile("" ::: "memory") -#define mb() __sync_synchronize() - -#define smp_mb() mb() -# define dma_rmb() barrier() -# define dma_wmb() barrier() -# define smp_rmb() barrier() -# define smp_wmb() barrier() +#define virt_mb() __sync_synchronize() +#define virt_rmb() barrier() +#define virt_wmb() barrier() +/* Atomic store should be enough, but gcc generates worse code in that case. */ +#define virt_store_mb(var, value) do { \ + typeof(var) virt_store_mb_value = (value); \ + __atomic_exchange(&(var), &virt_store_mb_value, &virt_store_mb_value, \ + __ATOMIC_SEQ_CST); \ + barrier(); \ +} while (0); /* Weak barriers should be used. If not - it's a bug */ -# define rmb() abort() -# define wmb() abort() +# define mb() abort() +# define rmb() abort() +# define wmb() abort() #else #error Please fill in barrier macros #endif diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h new file mode 100644 index 000000000000..845960e1cbf2 --- /dev/null +++ b/tools/virtio/linux/compiler.h @@ -0,0 +1,9 @@ +#ifndef LINUX_COMPILER_H +#define LINUX_COMPILER_H + +#define WRITE_ONCE(var, val) \ + (*((volatile typeof(val) *)(&(var))) = (val)) + +#define READ_ONCE(var) (*((volatile typeof(val) *)(&(var)))) + +#endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 4db7d5691ba7..033849948215 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -8,6 +8,7 @@ #include <assert.h> #include <stdarg.h> +#include <linux/compiler.h> #include <linux/types.h> #include <linux/printk.h> #include <linux/bug.h> diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile new file mode 100644 index 000000000000..feaa64ac4630 --- /dev/null +++ b/tools/virtio/ringtest/Makefile @@ -0,0 +1,22 @@ +all: + +all: ring virtio_ring_0_9 virtio_ring_poll + +CFLAGS += -Wall +CFLAGS += -pthread -O2 -ggdb +LDFLAGS += -pthread -O2 -ggdb + +main.o: main.c main.h +ring.o: ring.c main.h +virtio_ring_0_9.o: virtio_ring_0_9.c main.h +virtio_ring_poll.o: virtio_ring_poll.c virtio_ring_0_9.c main.h +ring: ring.o main.o +virtio_ring_0_9: virtio_ring_0_9.o main.o +virtio_ring_poll: virtio_ring_poll.o main.o +clean: + -rm main.o + -rm ring.o ring + -rm virtio_ring_0_9.o virtio_ring_0_9 + -rm virtio_ring_poll.o virtio_ring_poll + +.PHONY: all clean diff --git a/tools/virtio/ringtest/README b/tools/virtio/ringtest/README new file mode 100644 index 000000000000..34e94c46104f --- /dev/null +++ b/tools/virtio/ringtest/README @@ -0,0 +1,2 @@ +Partial implementation of various ring layouts, useful to tune virtio design. +Uses shared memory heavily. diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c new file mode 100644 index 000000000000..3a5ff438bd62 --- /dev/null +++ b/tools/virtio/ringtest/main.c @@ -0,0 +1,366 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Command line processing and common functions for ring benchmarking. + */ +#define _GNU_SOURCE +#include <getopt.h> +#include <pthread.h> +#include <assert.h> +#include <sched.h> +#include "main.h" +#include <sys/eventfd.h> +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <limits.h> + +int runcycles = 10000000; +int max_outstanding = INT_MAX; +int batch = 1; + +bool do_sleep = false; +bool do_relax = false; +bool do_exit = true; + +unsigned ring_size = 256; + +static int kickfd = -1; +static int callfd = -1; + +void notify(int fd) +{ + unsigned long long v = 1; + int r; + + vmexit(); + r = write(fd, &v, sizeof v); + assert(r == sizeof v); + vmentry(); +} + +void wait_for_notify(int fd) +{ + unsigned long long v = 1; + int r; + + vmexit(); + r = read(fd, &v, sizeof v); + assert(r == sizeof v); + vmentry(); +} + +void kick(void) +{ + notify(kickfd); +} + +void wait_for_kick(void) +{ + wait_for_notify(kickfd); +} + +void call(void) +{ + notify(callfd); +} + +void wait_for_call(void) +{ + wait_for_notify(callfd); +} + +void set_affinity(const char *arg) +{ + cpu_set_t cpuset; + int ret; + pthread_t self; + long int cpu; + char *endptr; + + if (!arg) + return; + + cpu = strtol(arg, &endptr, 0); + assert(!*endptr); + + assert(cpu >= 0 || cpu < CPU_SETSIZE); + + self = pthread_self(); + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + + ret = pthread_setaffinity_np(self, sizeof(cpu_set_t), &cpuset); + assert(!ret); +} + +static void run_guest(void) +{ + int completed_before; + int completed = 0; + int started = 0; + int bufs = runcycles; + int spurious = 0; + int r; + unsigned len; + void *buf; + int tokick = batch; + + for (;;) { + if (do_sleep) + disable_call(); + completed_before = completed; + do { + if (started < bufs && + started - completed < max_outstanding) { + r = add_inbuf(0, NULL, "Hello, world!"); + if (__builtin_expect(r == 0, true)) { + ++started; + if (!--tokick) { + tokick = batch; + if (do_sleep) + kick_available(); + } + + } + } else + r = -1; + + /* Flush out completed bufs if any */ + if (get_buf(&len, &buf)) { + ++completed; + if (__builtin_expect(completed == bufs, false)) + return; + r = 0; + } + } while (r == 0); + if (completed == completed_before) + ++spurious; + assert(completed <= bufs); + assert(started <= bufs); + if (do_sleep) { + if (enable_call()) + wait_for_call(); + } else { + poll_used(); + } + } +} + +static void run_host(void) +{ + int completed_before; + int completed = 0; + int spurious = 0; + int bufs = runcycles; + unsigned len; + void *buf; + + for (;;) { + if (do_sleep) { + if (enable_kick()) + wait_for_kick(); + } else { + poll_avail(); + } + if (do_sleep) + disable_kick(); + completed_before = completed; + while (__builtin_expect(use_buf(&len, &buf), true)) { + if (do_sleep) + call_used(); + ++completed; + if (__builtin_expect(completed == bufs, false)) + return; + } + if (completed == completed_before) + ++spurious; + assert(completed <= bufs); + if (completed == bufs) + break; + } +} + +void *start_guest(void *arg) +{ + set_affinity(arg); + run_guest(); + pthread_exit(NULL); +} + +void *start_host(void *arg) +{ + set_affinity(arg); + run_host(); + pthread_exit(NULL); +} + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "help", + .has_arg = no_argument, + .val = 'h', + }, + { + .name = "host-affinity", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "guest-affinity", + .has_arg = required_argument, + .val = 'G', + }, + { + .name = "ring-size", + .has_arg = required_argument, + .val = 'R', + }, + { + .name = "run-cycles", + .has_arg = required_argument, + .val = 'C', + }, + { + .name = "outstanding", + .has_arg = required_argument, + .val = 'o', + }, + { + .name = "batch", + .has_arg = required_argument, + .val = 'b', + }, + { + .name = "sleep", + .has_arg = no_argument, + .val = 's', + }, + { + .name = "relax", + .has_arg = no_argument, + .val = 'x', + }, + { + .name = "exit", + .has_arg = no_argument, + .val = 'e', + }, + { + } +}; + +static void help(void) +{ + fprintf(stderr, "Usage: <test> [--help]" + " [--host-affinity H]" + " [--guest-affinity G]" + " [--ring-size R (default: %d)]" + " [--run-cycles C (default: %d)]" + " [--batch b]" + " [--outstanding o]" + " [--sleep]" + " [--relax]" + " [--exit]" + "\n", + ring_size, + runcycles); +} + +int main(int argc, char **argv) +{ + int ret; + pthread_t host, guest; + void *tret; + char *host_arg = NULL; + char *guest_arg = NULL; + char *endptr; + long int c; + + kickfd = eventfd(0, 0); + assert(kickfd >= 0); + callfd = eventfd(0, 0); + assert(callfd >= 0); + + for (;;) { + int o = getopt_long(argc, argv, optstring, longopts, NULL); + switch (o) { + case -1: + goto done; + case '?': + help(); + exit(2); + case 'H': + host_arg = optarg; + break; + case 'G': + guest_arg = optarg; + break; + case 'R': + ring_size = strtol(optarg, &endptr, 0); + assert(ring_size && !(ring_size & (ring_size - 1))); + assert(!*endptr); + break; + case 'C': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + runcycles = c; + break; + case 'o': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + max_outstanding = c; + break; + case 'b': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + batch = c; + break; + case 's': + do_sleep = true; + break; + case 'x': + do_relax = true; + break; + case 'e': + do_exit = true; + break; + default: + help(); + exit(4); + break; + } + } + + /* does nothing here, used to make sure all smp APIs compile */ + smp_acquire(); + smp_release(); + smp_mb(); +done: + + if (batch > max_outstanding) + batch = max_outstanding; + + if (optind < argc) { + help(); + exit(4); + } + alloc_ring(); + + ret = pthread_create(&host, NULL, start_host, host_arg); + assert(!ret); + ret = pthread_create(&guest, NULL, start_guest, guest_arg); + assert(!ret); + + ret = pthread_join(guest, &tret); + assert(!ret); + ret = pthread_join(host, &tret); + assert(!ret); + return 0; +} diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h new file mode 100644 index 000000000000..16917acb0ade --- /dev/null +++ b/tools/virtio/ringtest/main.h @@ -0,0 +1,119 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Common macros and functions for ring benchmarking. + */ +#ifndef MAIN_H +#define MAIN_H + +#include <stdbool.h> + +extern bool do_exit; + +#if defined(__x86_64__) || defined(__i386__) +#include "x86intrin.h" + +static inline void wait_cycles(unsigned long long cycles) +{ + unsigned long long t; + + t = __rdtsc(); + while (__rdtsc() - t < cycles) {} +} + +#define VMEXIT_CYCLES 500 +#define VMENTRY_CYCLES 500 + +#else +static inline void wait_cycles(unsigned long long cycles) +{ + _Exit(5); +} +#define VMEXIT_CYCLES 0 +#define VMENTRY_CYCLES 0 +#endif + +static inline void vmexit(void) +{ + if (!do_exit) + return; + + wait_cycles(VMEXIT_CYCLES); +} +static inline void vmentry(void) +{ + if (!do_exit) + return; + + wait_cycles(VMENTRY_CYCLES); +} + +/* implemented by ring */ +void alloc_ring(void); +/* guest side */ +int add_inbuf(unsigned, void *, void *); +void *get_buf(unsigned *, void **); +void disable_call(); +bool enable_call(); +void kick_available(); +void poll_used(); +/* host side */ +void disable_kick(); +bool enable_kick(); +bool use_buf(unsigned *, void **); +void call_used(); +void poll_avail(); + +/* implemented by main */ +extern bool do_sleep; +void kick(void); +void wait_for_kick(void); +void call(void); +void wait_for_call(void); + +extern unsigned ring_size; + +/* Compiler barrier - similar to what Linux uses */ +#define barrier() asm volatile("" ::: "memory") + +/* Is there a portable way to do this? */ +#if defined(__x86_64__) || defined(__i386__) +#define cpu_relax() asm ("rep; nop" ::: "memory") +#else +#define cpu_relax() assert(0) +#endif + +extern bool do_relax; + +static inline void busy_wait(void) +{ + if (do_relax) + cpu_relax(); + else + /* prevent compiler from removing busy loops */ + barrier(); +} + +/* + * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized + * with other __ATOMIC_SEQ_CST calls. + */ +#define smp_mb() __sync_synchronize() + +/* + * This abuses the atomic builtins for thread fences, and + * adds a compiler barrier. + */ +#define smp_release() do { \ + barrier(); \ + __atomic_thread_fence(__ATOMIC_RELEASE); \ +} while (0) + +#define smp_acquire() do { \ + __atomic_thread_fence(__ATOMIC_ACQUIRE); \ + barrier(); \ +} while (0) + +#endif diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c new file mode 100644 index 000000000000..c25c8d248b6b --- /dev/null +++ b/tools/virtio/ringtest/ring.c @@ -0,0 +1,272 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Simple descriptor-based ring. virtio 0.9 compatible event index is used for + * signalling, unconditionally. + */ +#define _GNU_SOURCE +#include "main.h" +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +/* Next - Where next entry will be written. + * Prev - "Next" value when event triggered previously. + * Event - Peer requested event after writing this entry. + */ +static inline bool need_event(unsigned short event, + unsigned short next, + unsigned short prev) +{ + return (unsigned short)(next - event - 1) < (unsigned short)(next - prev); +} + +/* Design: + * Guest adds descriptors with unique index values and DESC_HW in flags. + * Host overwrites used descriptors with correct len, index, and DESC_HW clear. + * Flags are always set last. + */ +#define DESC_HW 0x1 + +struct desc { + unsigned short flags; + unsigned short index; + unsigned len; + unsigned long long addr; +}; + +/* how much padding is needed to avoid false cache sharing */ +#define HOST_GUEST_PADDING 0x80 + +/* Mostly read */ +struct event { + unsigned short kick_index; + unsigned char reserved0[HOST_GUEST_PADDING - 2]; + unsigned short call_index; + unsigned char reserved1[HOST_GUEST_PADDING - 2]; +}; + +struct data { + void *buf; /* descriptor is writeable, we can't get buf from there */ + void *data; +} *data; + +struct desc *ring; +struct event *event; + +struct guest { + unsigned avail_idx; + unsigned last_used_idx; + unsigned num_free; + unsigned kicked_avail_idx; + unsigned char reserved[HOST_GUEST_PADDING - 12]; +} guest; + +struct host { + /* we do not need to track last avail index + * unless we have more than one in flight. + */ + unsigned used_idx; + unsigned called_used_idx; + unsigned char reserved[HOST_GUEST_PADDING - 4]; +} host; + +/* implemented by ring */ +void alloc_ring(void) +{ + int ret; + int i; + + ret = posix_memalign((void **)&ring, 0x1000, ring_size * sizeof *ring); + if (ret) { + perror("Unable to allocate ring buffer.\n"); + exit(3); + } + event = malloc(sizeof *event); + if (!event) { + perror("Unable to allocate event buffer.\n"); + exit(3); + } + memset(event, 0, sizeof *event); + guest.avail_idx = 0; + guest.kicked_avail_idx = -1; + guest.last_used_idx = 0; + host.used_idx = 0; + host.called_used_idx = -1; + for (i = 0; i < ring_size; ++i) { + struct desc desc = { + .index = i, + }; + ring[i] = desc; + } + guest.num_free = ring_size; + data = malloc(ring_size * sizeof *data); + if (!data) { + perror("Unable to allocate data buffer.\n"); + exit(3); + } + memset(data, 0, ring_size * sizeof *data); +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + unsigned head, index; + + if (!guest.num_free) + return -1; + + guest.num_free--; + head = (ring_size - 1) & (guest.avail_idx++); + + /* Start with a write. On MESI architectures this helps + * avoid a shared state with consumer that is polling this descriptor. + */ + ring[head].addr = (unsigned long)(void*)buf; + ring[head].len = len; + /* read below might bypass write above. That is OK because it's just an + * optimization. If this happens, we will get the cache line in a + * shared state which is unfortunate, but probably not worth it to + * add an explicit full barrier to avoid this. + */ + barrier(); + index = ring[head].index; + data[index].buf = buf; + data[index].data = datap; + /* Barrier A (for pairing) */ + smp_release(); + ring[head].flags = DESC_HW; + + return 0; +} + +void *get_buf(unsigned *lenp, void **bufp) +{ + unsigned head = (ring_size - 1) & guest.last_used_idx; + unsigned index; + void *datap; + + if (ring[head].flags & DESC_HW) + return NULL; + /* Barrier B (for pairing) */ + smp_acquire(); + *lenp = ring[head].len; + index = ring[head].index & (ring_size - 1); + datap = data[index].data; + *bufp = data[index].buf; + data[index].buf = NULL; + data[index].data = NULL; + guest.num_free++; + guest.last_used_idx++; + return datap; +} + +void poll_used(void) +{ + unsigned head = (ring_size - 1) & guest.last_used_idx; + + while (ring[head].flags & DESC_HW) + busy_wait(); +} + +void disable_call() +{ + /* Doing nothing to disable calls might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_call() +{ + unsigned head = (ring_size - 1) & guest.last_used_idx; + + event->call_index = guest.last_used_idx; + /* Flush call index write */ + /* Barrier D (for pairing) */ + smp_mb(); + return ring[head].flags & DESC_HW; +} + +void kick_available(void) +{ + /* Flush in previous flags write */ + /* Barrier C (for pairing) */ + smp_mb(); + if (!need_event(event->kick_index, + guest.avail_idx, + guest.kicked_avail_idx)) + return; + + guest.kicked_avail_idx = guest.avail_idx; + kick(); +} + +/* host side */ +void disable_kick() +{ + /* Doing nothing to disable kicks might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_kick() +{ + unsigned head = (ring_size - 1) & host.used_idx; + + event->kick_index = host.used_idx; + /* Barrier C (for pairing) */ + smp_mb(); + return !(ring[head].flags & DESC_HW); +} + +void poll_avail(void) +{ + unsigned head = (ring_size - 1) & host.used_idx; + + while (!(ring[head].flags & DESC_HW)) + busy_wait(); +} + +bool use_buf(unsigned *lenp, void **bufp) +{ + unsigned head = (ring_size - 1) & host.used_idx; + + if (!(ring[head].flags & DESC_HW)) + return false; + + /* make sure length read below is not speculated */ + /* Barrier A (for pairing) */ + smp_acquire(); + + /* simple in-order completion: we don't need + * to touch index at all. This also means we + * can just modify the descriptor in-place. + */ + ring[head].len--; + /* Make sure len is valid before flags. + * Note: alternative is to write len and flags in one access - + * possible on 64 bit architectures but wmb is free on Intel anyway + * so I have no way to test whether it's a gain. + */ + /* Barrier B (for pairing) */ + smp_release(); + ring[head].flags = 0; + host.used_idx++; + return true; +} + +void call_used(void) +{ + /* Flush in previous flags write */ + /* Barrier D (for pairing) */ + smp_mb(); + if (!need_event(event->call_index, + host.used_idx, + host.called_used_idx)) + return; + + host.called_used_idx = host.used_idx; + call(); +} diff --git a/tools/virtio/ringtest/run-on-all.sh b/tools/virtio/ringtest/run-on-all.sh new file mode 100755 index 000000000000..52b0f71ffa8d --- /dev/null +++ b/tools/virtio/ringtest/run-on-all.sh @@ -0,0 +1,24 @@ +#!/bin/sh + +#use last CPU for host. Why not the first? +#many devices tend to use cpu0 by default so +#it tends to be busier +HOST_AFFINITY=$(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n|tail -1) + +#run command on all cpus +for cpu in $(cd /dev/cpu; ls|grep -v '[a-z]'|sort -n); +do + #Don't run guest and host on same CPU + #It actually works ok if using signalling + if + (echo "$@" | grep -e "--sleep" > /dev/null) || \ + test $HOST_AFFINITY '!=' $cpu + then + echo "GUEST AFFINITY $cpu" + "$@" --host-affinity $HOST_AFFINITY --guest-affinity $cpu + fi +done +echo "NO GUEST AFFINITY" +"$@" --host-affinity $HOST_AFFINITY +echo "NO AFFINITY" +"$@" diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c new file mode 100644 index 000000000000..47c9a1a18d36 --- /dev/null +++ b/tools/virtio/ringtest/virtio_ring_0_9.c @@ -0,0 +1,316 @@ +/* + * Copyright (C) 2016 Red Hat, Inc. + * Author: Michael S. Tsirkin <mst@redhat.com> + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Partial implementation of virtio 0.9. event index is used for signalling, + * unconditionally. Design roughly follows linux kernel implementation in order + * to be able to judge its performance. + */ +#define _GNU_SOURCE +#include "main.h" +#include <stdlib.h> +#include <stdio.h> +#include <assert.h> +#include <string.h> +#include <linux/virtio_ring.h> + +struct data { + void *data; +} *data; + +struct vring ring; + +/* enabling the below activates experimental ring polling code + * (which skips index reads on consumer in favor of looking at + * high bits of ring id ^ 0x8000). + */ +/* #ifdef RING_POLL */ + +/* how much padding is needed to avoid false cache sharing */ +#define HOST_GUEST_PADDING 0x80 + +struct guest { + unsigned short avail_idx; + unsigned short last_used_idx; + unsigned short num_free; + unsigned short kicked_avail_idx; + unsigned short free_head; + unsigned char reserved[HOST_GUEST_PADDING - 10]; +} guest; + +struct host { + /* we do not need to track last avail index + * unless we have more than one in flight. + */ + unsigned short used_idx; + unsigned short called_used_idx; + unsigned char reserved[HOST_GUEST_PADDING - 4]; +} host; + +/* implemented by ring */ +void alloc_ring(void) +{ + int ret; + int i; + void *p; + + ret = posix_memalign(&p, 0x1000, vring_size(ring_size, 0x1000)); + if (ret) { + perror("Unable to allocate ring buffer.\n"); + exit(3); + } + memset(p, 0, vring_size(ring_size, 0x1000)); + vring_init(&ring, ring_size, p, 0x1000); + + guest.avail_idx = 0; + guest.kicked_avail_idx = -1; + guest.last_used_idx = 0; + /* Put everything in free lists. */ + guest.free_head = 0; + for (i = 0; i < ring_size - 1; i++) + ring.desc[i].next = i + 1; + host.used_idx = 0; + host.called_used_idx = -1; + guest.num_free = ring_size; + data = malloc(ring_size * sizeof *data); + if (!data) { + perror("Unable to allocate data buffer.\n"); + exit(3); + } + memset(data, 0, ring_size * sizeof *data); +} + +/* guest side */ +int add_inbuf(unsigned len, void *buf, void *datap) +{ + unsigned head, avail; + struct vring_desc *desc; + + if (!guest.num_free) + return -1; + + head = guest.free_head; + guest.num_free--; + + desc = ring.desc; + desc[head].flags = VRING_DESC_F_NEXT; + desc[head].addr = (unsigned long)(void *)buf; + desc[head].len = len; + /* We do it like this to simulate the way + * we'd have to flip it if we had multiple + * descriptors. + */ + desc[head].flags &= ~VRING_DESC_F_NEXT; + guest.free_head = desc[head].next; + + data[head].data = datap; + +#ifdef RING_POLL + /* Barrier A (for pairing) */ + smp_release(); + avail = guest.avail_idx++; + ring.avail->ring[avail & (ring_size - 1)] = + (head | (avail & ~(ring_size - 1))) ^ 0x8000; +#else + avail = (ring_size - 1) & (guest.avail_idx++); + ring.avail->ring[avail] = head; + /* Barrier A (for pairing) */ + smp_release(); +#endif + ring.avail->idx = guest.avail_idx; + return 0; +} + +void *get_buf(unsigned *lenp, void **bufp) +{ + unsigned head; + unsigned index; + void *datap; + +#ifdef RING_POLL + head = (ring_size - 1) & guest.last_used_idx; + index = ring.used->ring[head].id; + if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1)) + return NULL; + /* Barrier B (for pairing) */ + smp_acquire(); + index &= ring_size - 1; +#else + if (ring.used->idx == guest.last_used_idx) + return NULL; + /* Barrier B (for pairing) */ + smp_acquire(); + head = (ring_size - 1) & guest.last_used_idx; + index = ring.used->ring[head].id; +#endif + *lenp = ring.used->ring[head].len; + datap = data[index].data; + *bufp = (void*)(unsigned long)ring.desc[index].addr; + data[index].data = NULL; + ring.desc[index].next = guest.free_head; + guest.free_head = index; + guest.num_free++; + guest.last_used_idx++; + return datap; +} + +void poll_used(void) +{ +#ifdef RING_POLL + unsigned head = (ring_size - 1) & guest.last_used_idx; + + for (;;) { + unsigned index = ring.used->ring[head].id; + + if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1)) + busy_wait(); + else + break; + } +#else + unsigned head = guest.last_used_idx; + + while (ring.used->idx == head) + busy_wait(); +#endif +} + +void disable_call() +{ + /* Doing nothing to disable calls might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_call() +{ + unsigned short last_used_idx; + + vring_used_event(&ring) = (last_used_idx = guest.last_used_idx); + /* Flush call index write */ + /* Barrier D (for pairing) */ + smp_mb(); +#ifdef RING_POLL + { + unsigned short head = last_used_idx & (ring_size - 1); + unsigned index = ring.used->ring[head].id; + + return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1); + } +#else + return ring.used->idx == last_used_idx; +#endif +} + +void kick_available(void) +{ + /* Flush in previous flags write */ + /* Barrier C (for pairing) */ + smp_mb(); + if (!vring_need_event(vring_avail_event(&ring), + guest.avail_idx, + guest.kicked_avail_idx)) + return; + + guest.kicked_avail_idx = guest.avail_idx; + kick(); +} + +/* host side */ +void disable_kick() +{ + /* Doing nothing to disable kicks might cause + * extra interrupts, but reduces the number of cache misses. + */ +} + +bool enable_kick() +{ + unsigned head = host.used_idx; + + vring_avail_event(&ring) = head; + /* Barrier C (for pairing) */ + smp_mb(); +#ifdef RING_POLL + { + unsigned index = ring.avail->ring[head & (ring_size - 1)]; + + return (index ^ head ^ 0x8000) & ~(ring_size - 1); + } +#else + return head == ring.avail->idx; +#endif +} + +void poll_avail(void) +{ + unsigned head = host.used_idx; +#ifdef RING_POLL + for (;;) { + unsigned index = ring.avail->ring[head & (ring_size - 1)]; + if ((index ^ head ^ 0x8000) & ~(ring_size - 1)) + busy_wait(); + else + break; + } +#else + while (ring.avail->idx == head) + busy_wait(); +#endif +} + +bool use_buf(unsigned *lenp, void **bufp) +{ + unsigned used_idx = host.used_idx; + struct vring_desc *desc; + unsigned head; + +#ifdef RING_POLL + head = ring.avail->ring[used_idx & (ring_size - 1)]; + if ((used_idx ^ head ^ 0x8000) & ~(ring_size - 1)) + return false; + /* Barrier A (for pairing) */ + smp_acquire(); + + used_idx &= ring_size - 1; + desc = &ring.desc[head & (ring_size - 1)]; +#else + if (used_idx == ring.avail->idx) + return false; + + /* Barrier A (for pairing) */ + smp_acquire(); + + used_idx &= ring_size - 1; + head = ring.avail->ring[used_idx]; + desc = &ring.desc[head]; +#endif + + *lenp = desc->len; + *bufp = (void *)(unsigned long)desc->addr; + + /* now update used ring */ + ring.used->ring[used_idx].id = head; + ring.used->ring[used_idx].len = desc->len - 1; + /* Barrier B (for pairing) */ + smp_release(); + host.used_idx++; + ring.used->idx = host.used_idx; + + return true; +} + +void call_used(void) +{ + /* Flush in previous flags write */ + /* Barrier D (for pairing) */ + smp_mb(); + if (!vring_need_event(vring_used_event(&ring), + host.used_idx, + host.called_used_idx)) + return; + + host.called_used_idx = host.used_idx; + call(); +} diff --git a/tools/virtio/ringtest/virtio_ring_poll.c b/tools/virtio/ringtest/virtio_ring_poll.c new file mode 100644 index 000000000000..84fc2c557aaa --- /dev/null +++ b/tools/virtio/ringtest/virtio_ring_poll.c @@ -0,0 +1,2 @@ +#define RING_POLL 1 +#include "virtio_ring_0_9.c" |